The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`.

0it [00:00, ?it/s]
0it [00:00, ?it/s]
/opt/conda/lib/python3.10/site-packages/transformers/deepspeed.py:24: FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations
  warnings.warn(
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 1237 examples [00:00, 12341.15 examples/s]
Generating train split: 2264 examples [00:00, 14207.36 examples/s]

Generating validation split: 0 examples [00:00, ? examples/s]
Generating validation split: 30 examples [00:00, 8467.64 examples/s]

Running tokenizer on train dataset:   0%|          | 0/2264 [00:00<?, ? examples/s]/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:4126: UserWarning: `as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your labels by using the argument `text_target` of the regular `__call__` method (either in the same call as your input texts if you use the same keyword arguments, or in a separate call.
  warnings.warn(

Running tokenizer on train dataset:  44%|████▍     | 1000/2264 [00:00<00:00, 2109.03 examples/s]
Running tokenizer on train dataset:  88%|████████▊ | 2000/2264 [00:01<00:00, 1672.35 examples/s]
Running tokenizer on train dataset: 100%|██████████| 2264/2264 [00:01<00:00, 1618.69 examples/s]
Running tokenizer on train dataset: 100%|██████████| 2264/2264 [00:01<00:00, 1679.44 examples/s]
Saving cached train data ...

Saving the dataset (0/1 shards):   0%|          | 0/2264 [00:00<?, ? examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 2264/2264 [00:00<00:00, 369160.06 examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 2264/2264 [00:00<00:00, 359693.34 examples/s]

Running tokenizer on validation dataset:   0%|          | 0/30 [00:00<?, ? examples/s]
Running tokenizer on validation dataset: 100%|██████████| 30/30 [00:00<00:00, 1337.80 examples/s]
Saving cached validation data ...

Saving the dataset (0/1 shards):   0%|          | 0/30 [00:00<?, ? examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 30/30 [00:00<00:00, 7717.21 examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 30/30 [00:00<00:00, 7422.67 examples/s]

Downloading builder script:   0%|          | 0.00/8.15k [00:00<?, ?B/s]
Downloading builder script: 100%|██████████| 8.15k/8.15k [00:00<00:00, 17.6MB/s]
/opt/conda/lib/python3.10/site-packages/transformers/optimization.py:591: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
  warnings.warn(
All 57600 steps, warm_up steps: 200
wandb: WARNING The `run_name` is currently set to the same value as `TrainingArguments.output_dir`. If this was not intended, please specify a different run name by setting the `TrainingArguments.run_name` parameter.
wandb: Currently logged in as: abdiharyadi. Use `wandb login --relogin` to force relogin
wandb: wandb version 0.18.3 is available!  To upgrade, please run:
wandb:  $ pip install wandb --upgrade
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /kaggle/working/amr-tst-indo/AMRBART-id/fine-tune/wandb/run-20241002_065356-1wo93oi5
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run /kaggle/working/amr-tst-indo/AMRBART-id/fine-tune/../outputs/mbart-en-id-smaller-fted-amr-generation-v2-fted
wandb: ⭐️ View project at https://wandb.ai/abdiharyadi/amr-tst
wandb: 🚀 View run at https://wandb.ai/abdiharyadi/amr-tst/runs/1wo93oi5

  0%|          | 0/57600 [00:00<?, ?it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

  0%|          | 1/57600 [00:01<22:53:19,  1.43s/it]
                                                    
{'loss': 2.1638, 'learning_rate': 5e-09, 'epoch': 0.01}

  0%|          | 1/57600 [00:01<22:53:19,  1.43s/it]
  0%|          | 2/57600 [00:02<14:49:26,  1.08it/s]
  0%|          | 3/57600 [00:02<12:24:25,  1.29it/s]
  0%|          | 4/57600 [00:03<11:36:40,  1.38it/s]
  0%|          | 5/57600 [00:03<11:33:14,  1.38it/s]
  0%|          | 6/57600 [00:04<11:15:21,  1.42it/s]
  0%|          | 7/57600 [00:05<11:02:08,  1.45it/s]
  0%|          | 8/57600 [00:05<10:31:48,  1.52it/s]
  0%|          | 9/57600 [00:06<10:42:17,  1.49it/s]
  0%|          | 10/57600 [00:07<10:22:35,  1.54it/s]
  0%|          | 11/57600 [00:07<10:05:39,  1.58it/s]
  0%|          | 12/57600 [00:08<10:07:27,  1.58it/s]
  0%|          | 13/57600 [00:09<10:15:30,  1.56it/s]
  0%|          | 14/57600 [00:09<10:47:56,  1.48it/s]
  0%|          | 15/57600 [00:10<10:45:47,  1.49it/s]
  0%|          | 16/57600 [00:11<10:58:59,  1.46it/s]
  0%|          | 17/57600 [00:11<10:42:39,  1.49it/s]
  0%|          | 18/57600 [00:12<10:23:51,  1.54it/s]
  0%|          | 19/57600 [00:13<10:27:55,  1.53it/s]
  0%|          | 20/57600 [00:13<10:15:56,  1.56it/s]
                                                     
{'loss': 1.9727, 'learning_rate': 1e-07, 'epoch': 0.22}

  0%|          | 20/57600 [00:13<10:15:56,  1.56it/s]
  0%|          | 21/57600 [00:14<10:20:16,  1.55it/s]
  0%|          | 22/57600 [00:14<10:01:48,  1.59it/s]
  0%|          | 23/57600 [00:15<9:49:05,  1.63it/s] 
  0%|          | 24/57600 [00:16<9:50:40,  1.62it/s]
  0%|          | 25/57600 [00:16<10:09:17,  1.57it/s]
  0%|          | 26/57600 [00:17<10:05:22,  1.59it/s]
  0%|          | 27/57600 [00:18<9:57:37,  1.61it/s] 
  0%|          | 28/57600 [00:18<9:52:31,  1.62it/s]
  0%|          | 29/57600 [00:19<10:10:27,  1.57it/s]
  0%|          | 30/57600 [00:19<9:53:34,  1.62it/s] 
  0%|          | 31/57600 [00:20<10:05:38,  1.58it/s]
  0%|          | 32/57600 [00:21<10:07:26,  1.58it/s]
  0%|          | 33/57600 [00:21<10:02:11,  1.59it/s]
  0%|          | 34/57600 [00:22<10:03:43,  1.59it/s]
  0%|          | 35/57600 [00:23<9:55:40,  1.61it/s] 
  0%|          | 36/57600 [00:23<9:48:05,  1.63it/s]
  0%|          | 37/57600 [00:24<10:04:09,  1.59it/s]
  0%|          | 38/57600 [00:24<9:52:57,  1.62it/s] 
  0%|          | 39/57600 [00:25<9:36:38,  1.66it/s]
  0%|          | 40/57600 [00:26<9:43:41,  1.64it/s]
                                                    
{'loss': 2.0028, 'learning_rate': 2e-07, 'epoch': 0.44}

  0%|          | 40/57600 [00:26<9:43:41,  1.64it/s]
  0%|          | 41/57600 [00:26<9:50:19,  1.63it/s]
  0%|          | 42/57600 [00:27<10:07:03,  1.58it/s]
  0%|          | 43/57600 [00:28<10:16:06,  1.56it/s]
  0%|          | 44/57600 [00:28<9:59:11,  1.60it/s] 
  0%|          | 45/57600 [00:29<10:00:40,  1.60it/s]
  0%|          | 46/57600 [00:29<9:43:02,  1.65it/s] 
  0%|          | 47/57600 [00:30<9:42:39,  1.65it/s]
  0%|          | 48/57600 [00:31<9:42:59,  1.65it/s]
  0%|          | 49/57600 [00:31<9:28:02,  1.69it/s]
  0%|          | 50/57600 [00:32<9:41:40,  1.65it/s]
  0%|          | 51/57600 [00:32<10:04:08,  1.59it/s]
  0%|          | 52/57600 [00:33<9:53:06,  1.62it/s] 
  0%|          | 53/57600 [00:34<9:44:33,  1.64it/s]
  0%|          | 54/57600 [00:34<9:56:32,  1.61it/s]
  0%|          | 55/57600 [00:35<9:45:13,  1.64it/s]
  0%|          | 56/57600 [00:35<9:48:08,  1.63it/s]
  0%|          | 57/57600 [00:36<9:57:28,  1.61it/s]
  0%|          | 58/57600 [00:37<10:01:37,  1.59it/s]
  0%|          | 59/57600 [00:37<10:02:49,  1.59it/s]
  0%|          | 60/57600 [00:38<9:48:06,  1.63it/s] 
                                                    
{'loss': 2.0448, 'learning_rate': 3e-07, 'epoch': 0.66}

  0%|          | 60/57600 [00:38<9:48:06,  1.63it/s]
  0%|          | 61/57600 [00:39<9:52:42,  1.62it/s]
  0%|          | 62/57600 [00:39<10:03:46,  1.59it/s]
  0%|          | 63/57600 [00:40<10:07:58,  1.58it/s]
  0%|          | 64/57600 [00:40<9:50:03,  1.63it/s] 
  0%|          | 65/57600 [00:41<9:41:24,  1.65it/s]
  0%|          | 66/57600 [00:42<9:52:39,  1.62it/s]
  0%|          | 67/57600 [00:42<10:01:19,  1.59it/s]
  0%|          | 68/57600 [00:43<9:46:14,  1.64it/s] 
  0%|          | 69/57600 [00:44<9:57:47,  1.60it/s]
  0%|          | 70/57600 [00:44<10:00:24,  1.60it/s]
  0%|          | 71/57600 [00:45<10:21:04,  1.54it/s]
  0%|          | 72/57600 [00:46<10:38:04,  1.50it/s]
  0%|          | 73/57600 [00:46<10:21:44,  1.54it/s]
  0%|          | 74/57600 [00:47<10:01:08,  1.59it/s]
  0%|          | 75/57600 [00:47<9:47:13,  1.63it/s] 
  0%|          | 76/57600 [00:48<9:46:40,  1.63it/s]
  0%|          | 77/57600 [00:49<10:08:43,  1.57it/s]
  0%|          | 78/57600 [00:49<10:09:48,  1.57it/s]
  0%|          | 79/57600 [00:50<9:55:05,  1.61it/s] 
  0%|          | 80/57600 [00:51<9:56:56,  1.61it/s]
                                                    
{'loss': 1.9696, 'learning_rate': 4e-07, 'epoch': 0.88}

  0%|          | 80/57600 [00:51<9:56:56,  1.61it/s]
  0%|          | 81/57600 [00:51<9:50:10,  1.62it/s]
  0%|          | 82/57600 [00:52<9:55:52,  1.61it/s]
  0%|          | 83/57600 [00:52<9:58:37,  1.60it/s]
  0%|          | 84/57600 [00:53<9:51:15,  1.62it/s]
  0%|          | 85/57600 [00:54<9:53:59,  1.61it/s]
  0%|          | 86/57600 [00:54<9:47:24,  1.63it/s]
  0%|          | 87/57600 [00:55<10:00:03,  1.60it/s]
  0%|          | 88/57600 [00:56<10:19:27,  1.55it/s]
  0%|          | 89/57600 [00:56<10:04:33,  1.59it/s]
  0%|          | 90/57600 [00:57<9:43:04,  1.64it/s] 
  0%|          | 91/57600 [00:58<10:28:24,  1.53it/s]
  0%|          | 92/57600 [00:58<10:22:47,  1.54it/s]
  0%|          | 93/57600 [00:59<10:27:13,  1.53it/s]
  0%|          | 94/57600 [00:59<10:13:40,  1.56it/s]
  0%|          | 95/57600 [01:00<9:59:58,  1.60it/s] 
  0%|          | 96/57600 [01:01<9:41:58,  1.65it/s]
  0%|          | 97/57600 [01:01<9:52:29,  1.62it/s]
  0%|          | 98/57600 [01:02<9:55:22,  1.61it/s]
  0%|          | 99/57600 [01:02<9:59:29,  1.60it/s]
  0%|          | 100/57600 [01:03<10:09:49,  1.57it/s]
                                                      
{'loss': 1.9375, 'learning_rate': 5e-07, 'epoch': 1.1}

  0%|          | 100/57600 [01:03<10:09:49,  1.57it/s]
  0%|          | 101/57600 [01:04<9:49:24,  1.63it/s] 
  0%|          | 102/57600 [01:04<10:00:45,  1.60it/s]
  0%|          | 103/57600 [01:05<10:04:47,  1.58it/s]
  0%|          | 104/57600 [01:06<10:23:08,  1.54it/s]
  0%|          | 105/57600 [01:06<10:18:39,  1.55it/s]
  0%|          | 106/57600 [01:07<10:07:23,  1.58it/s]
  0%|          | 107/57600 [01:08<10:36:06,  1.51it/s]
  0%|          | 108/57600 [01:08<10:38:56,  1.50it/s]
  0%|          | 109/57600 [01:09<10:28:53,  1.52it/s]
  0%|          | 110/57600 [01:10<10:20:51,  1.54it/s]
  0%|          | 111/57600 [01:10<10:03:35,  1.59it/s]
  0%|          | 112/57600 [01:11<9:56:21,  1.61it/s] 
  0%|          | 113/57600 [01:11<9:58:27,  1.60it/s]
  0%|          | 114/57600 [01:12<9:52:16,  1.62it/s]
  0%|          | 115/57600 [01:13<10:02:58,  1.59it/s]
  0%|          | 116/57600 [01:13<10:12:20,  1.56it/s]
  0%|          | 117/57600 [01:14<10:04:37,  1.58it/s]
  0%|          | 118/57600 [01:15<10:24:37,  1.53it/s]
  0%|          | 119/57600 [01:15<10:29:47,  1.52it/s]
  0%|          | 120/57600 [01:16<10:18:04,  1.55it/s]
                                                      
{'loss': 1.9075, 'learning_rate': 6e-07, 'epoch': 1.32}

  0%|          | 120/57600 [01:16<10:18:04,  1.55it/s]
  0%|          | 121/57600 [01:17<10:17:45,  1.55it/s]
  0%|          | 122/57600 [01:17<10:15:36,  1.56it/s]
  0%|          | 123/57600 [01:18<10:30:40,  1.52it/s]
  0%|          | 124/57600 [01:18<10:05:45,  1.58it/s]
  0%|          | 125/57600 [01:19<10:00:32,  1.60it/s]
  0%|          | 126/57600 [01:20<9:52:50,  1.62it/s] 
  0%|          | 127/57600 [01:20<9:50:21,  1.62it/s]
  0%|          | 128/57600 [01:21<9:51:52,  1.62it/s]
  0%|          | 129/57600 [01:22<9:46:15,  1.63it/s]
  0%|          | 130/57600 [01:22<10:05:11,  1.58it/s]
  0%|          | 131/57600 [01:23<9:46:43,  1.63it/s] 
  0%|          | 132/57600 [01:23<9:39:13,  1.65it/s]
  0%|          | 133/57600 [01:24<9:55:48,  1.61it/s]
  0%|          | 134/57600 [01:25<9:53:25,  1.61it/s]
  0%|          | 135/57600 [01:25<10:07:24,  1.58it/s]
  0%|          | 136/57600 [01:26<10:15:23,  1.56it/s]
  0%|          | 137/57600 [01:27<10:00:25,  1.60it/s]
  0%|          | 138/57600 [01:27<9:53:23,  1.61it/s] 
  0%|          | 139/57600 [01:28<9:48:10,  1.63it/s]
  0%|          | 140/57600 [01:28<10:06:43,  1.58it/s]
                                                      
{'loss': 1.9866, 'learning_rate': 7e-07, 'epoch': 1.55}

  0%|          | 140/57600 [01:28<10:06:43,  1.58it/s]
  0%|          | 141/57600 [01:29<10:38:40,  1.50it/s]
  0%|          | 142/57600 [01:30<10:25:16,  1.53it/s]
  0%|          | 143/57600 [01:30<10:25:53,  1.53it/s]
  0%|          | 144/57600 [01:31<10:26:00,  1.53it/s]
  0%|          | 145/57600 [01:32<10:28:33,  1.52it/s]
  0%|          | 146/57600 [01:32<10:16:00,  1.55it/s]
  0%|          | 147/57600 [01:33<10:01:30,  1.59it/s]
  0%|          | 148/57600 [01:34<10:22:07,  1.54it/s]
  0%|          | 149/57600 [01:34<10:09:38,  1.57it/s]
  0%|          | 150/57600 [01:35<10:06:17,  1.58it/s]
  0%|          | 151/57600 [01:36<10:25:19,  1.53it/s]
  0%|          | 152/57600 [01:36<10:24:27,  1.53it/s]
  0%|          | 153/57600 [01:37<10:04:11,  1.58it/s]
  0%|          | 154/57600 [01:37<10:04:57,  1.58it/s]
  0%|          | 155/57600 [01:38<9:54:03,  1.61it/s] 
  0%|          | 156/57600 [01:39<10:14:40,  1.56it/s]
  0%|          | 157/57600 [01:39<10:02:39,  1.59it/s]
  0%|          | 158/57600 [01:40<10:12:43,  1.56it/s]
  0%|          | 159/57600 [01:41<9:49:05,  1.63it/s] 
  0%|          | 160/57600 [01:41<9:58:32,  1.60it/s]
                                                     
{'loss': 1.882, 'learning_rate': 8e-07, 'epoch': 1.77}

  0%|          | 160/57600 [01:41<9:58:32,  1.60it/s]
  0%|          | 161/57600 [01:42<9:50:03,  1.62it/s]
  0%|          | 162/57600 [01:42<9:59:06,  1.60it/s]
  0%|          | 163/57600 [01:43<9:47:42,  1.63it/s]
  0%|          | 164/57600 [01:44<9:56:57,  1.60it/s]
  0%|          | 165/57600 [01:44<9:49:04,  1.63it/s]
  0%|          | 166/57600 [01:45<9:48:55,  1.63it/s]
  0%|          | 167/57600 [01:46<9:36:43,  1.66it/s]
  0%|          | 168/57600 [01:46<10:07:31,  1.58it/s]
  0%|          | 169/57600 [01:47<10:10:58,  1.57it/s]
  0%|          | 170/57600 [01:47<10:06:24,  1.58it/s]
  0%|          | 171/57600 [01:48<9:48:26,  1.63it/s] 
  0%|          | 172/57600 [01:49<9:45:39,  1.63it/s]
  0%|          | 173/57600 [01:49<9:28:28,  1.68it/s]
  0%|          | 174/57600 [01:50<9:34:34,  1.67it/s]
  0%|          | 175/57600 [01:50<9:35:35,  1.66it/s]
  0%|          | 176/57600 [01:51<9:45:28,  1.63it/s]
  0%|          | 177/57600 [01:52<9:44:08,  1.64it/s]
  0%|          | 178/57600 [01:52<9:33:17,  1.67it/s]
  0%|          | 179/57600 [01:53<9:31:29,  1.67it/s]
  0%|          | 180/57600 [01:53<9:33:31,  1.67it/s]
                                                     
{'loss': 1.9916, 'learning_rate': 9e-07, 'epoch': 1.99}

  0%|          | 180/57600 [01:53<9:33:31,  1.67it/s]
  0%|          | 181/57600 [01:54<9:38:02,  1.66it/s]
  0%|          | 182/57600 [01:55<10:19:27,  1.54it/s]
  0%|          | 183/57600 [01:55<10:07:04,  1.58it/s]
  0%|          | 184/57600 [01:56<10:11:37,  1.56it/s]
  0%|          | 185/57600 [01:57<10:18:20,  1.55it/s]
  0%|          | 186/57600 [01:57<10:01:07,  1.59it/s]
  0%|          | 187/57600 [01:58<9:59:35,  1.60it/s] 
  0%|          | 188/57600 [01:59<10:01:04,  1.59it/s]
  0%|          | 189/57600 [01:59<10:06:48,  1.58it/s]
  0%|          | 190/57600 [02:00<10:11:28,  1.56it/s]
  0%|          | 191/57600 [02:01<10:10:43,  1.57it/s]
  0%|          | 192/57600 [02:01<9:53:42,  1.61it/s] 
  0%|          | 193/57600 [02:02<10:08:52,  1.57it/s]
  0%|          | 194/57600 [02:02<10:17:54,  1.55it/s]
  0%|          | 195/57600 [02:03<10:24:18,  1.53it/s]
  0%|          | 196/57600 [02:04<10:14:59,  1.56it/s]
  0%|          | 197/57600 [02:04<10:24:16,  1.53it/s]
  0%|          | 198/57600 [02:05<10:05:08,  1.58it/s]
  0%|          | 199/57600 [02:06<9:53:57,  1.61it/s] 
  0%|          | 200/57600 [02:06<10:22:39,  1.54it/s]
                                                      
{'loss': 1.9132, 'learning_rate': 1e-06, 'epoch': 2.21}

  0%|          | 200/57600 [02:06<10:22:39,  1.54it/s]
  0%|          | 201/57600 [02:07<10:03:36,  1.58it/s]
  0%|          | 202/57600 [02:07<9:52:46,  1.61it/s] 
  0%|          | 203/57600 [02:08<9:51:11,  1.62it/s]
  0%|          | 204/57600 [02:09<9:47:35,  1.63it/s]
  0%|          | 205/57600 [02:09<9:40:58,  1.65it/s]
  0%|          | 206/57600 [02:10<9:59:02,  1.60it/s]
  0%|          | 207/57600 [02:11<9:45:23,  1.63it/s]
  0%|          | 208/57600 [02:11<10:09:04,  1.57it/s]
  0%|          | 209/57600 [02:12<10:05:38,  1.58it/s]
  0%|          | 210/57600 [02:12<9:50:19,  1.62it/s] 
  0%|          | 211/57600 [02:13<9:51:37,  1.62it/s]
  0%|          | 212/57600 [02:14<9:42:21,  1.64it/s]
  0%|          | 213/57600 [02:14<9:51:41,  1.62it/s]
  0%|          | 214/57600 [02:15<9:59:24,  1.60it/s]
  0%|          | 215/57600 [02:15<9:41:42,  1.64it/s]
  0%|          | 216/57600 [02:16<9:56:54,  1.60it/s]
  0%|          | 217/57600 [02:17<9:41:26,  1.64it/s]
  0%|          | 218/57600 [02:17<9:42:02,  1.64it/s]
  0%|          | 219/57600 [02:18<9:45:12,  1.63it/s]
  0%|          | 220/57600 [02:19<9:38:38,  1.65it/s]
                                                     
{'loss': 1.9858, 'learning_rate': 9.996864111498258e-07, 'epoch': 2.43}

  0%|          | 220/57600 [02:19<9:38:38,  1.65it/s]
  0%|          | 221/57600 [02:19<9:36:56,  1.66it/s]
  0%|          | 222/57600 [02:20<9:30:32,  1.68it/s]
  0%|          | 223/57600 [02:20<9:36:27,  1.66it/s]
  0%|          | 224/57600 [02:21<10:08:45,  1.57it/s]
  0%|          | 225/57600 [02:22<9:56:34,  1.60it/s] 
  0%|          | 226/57600 [02:22<9:43:16,  1.64it/s]
  0%|          | 227/57600 [02:23<9:46:49,  1.63it/s]
  0%|          | 228/57600 [02:23<9:42:54,  1.64it/s]
  0%|          | 229/57600 [02:24<9:31:02,  1.67it/s]
  0%|          | 230/57600 [02:25<9:21:39,  1.70it/s]
  0%|          | 231/57600 [02:25<9:34:18,  1.66it/s]
  0%|          | 232/57600 [02:26<9:48:36,  1.62it/s]
  0%|          | 233/57600 [02:26<9:46:53,  1.63it/s]
  0%|          | 234/57600 [02:27<9:56:34,  1.60it/s]
  0%|          | 235/57600 [02:28<9:32:56,  1.67it/s]
  0%|          | 236/57600 [02:28<9:56:33,  1.60it/s]
  0%|          | 237/57600 [02:29<9:55:15,  1.61it/s]
  0%|          | 238/57600 [02:30<9:51:58,  1.61it/s]
  0%|          | 239/57600 [02:30<9:49:33,  1.62it/s]
  0%|          | 240/57600 [02:31<10:05:24,  1.58it/s]
                                                      
{'loss': 1.9373, 'learning_rate': 9.993728222996515e-07, 'epoch': 2.65}

  0%|          | 240/57600 [02:31<10:05:24,  1.58it/s]
  0%|          | 241/57600 [02:31<10:09:45,  1.57it/s]
  0%|          | 242/57600 [02:32<9:48:23,  1.62it/s] 
  0%|          | 243/57600 [02:33<10:26:05,  1.53it/s]
  0%|          | 244/57600 [02:33<10:17:45,  1.55it/s]
  0%|          | 245/57600 [02:34<10:24:33,  1.53it/s]
  0%|          | 246/57600 [02:35<10:10:46,  1.57it/s]
  0%|          | 247/57600 [02:35<10:04:40,  1.58it/s]
  0%|          | 248/57600 [02:36<10:10:09,  1.57it/s]
  0%|          | 249/57600 [02:37<10:07:29,  1.57it/s]
  0%|          | 250/57600 [02:37<10:02:17,  1.59it/s]
  0%|          | 251/57600 [02:38<10:29:58,  1.52it/s]
  0%|          | 252/57600 [02:39<10:01:42,  1.59it/s]
  0%|          | 253/57600 [02:39<10:32:16,  1.51it/s]
  0%|          | 254/57600 [02:40<10:17:51,  1.55it/s]
  0%|          | 255/57600 [02:40<9:54:38,  1.61it/s] 
  0%|          | 256/57600 [02:41<9:45:56,  1.63it/s]
  0%|          | 257/57600 [02:42<9:53:32,  1.61it/s]
  0%|          | 258/57600 [02:42<9:48:26,  1.62it/s]
  0%|          | 259/57600 [02:43<9:53:07,  1.61it/s]
  0%|          | 260/57600 [02:44<9:52:48,  1.61it/s]
                                                     
{'loss': 1.9146, 'learning_rate': 9.990592334494773e-07, 'epoch': 2.87}

  0%|          | 260/57600 [02:44<9:52:48,  1.61it/s]
  0%|          | 261/57600 [02:44<9:58:43,  1.60it/s]
  0%|          | 262/57600 [02:45<10:07:11,  1.57it/s]
  0%|          | 263/57600 [02:45<10:22:58,  1.53it/s]
  0%|          | 264/57600 [02:46<10:15:12,  1.55it/s]
  0%|          | 265/57600 [02:47<10:12:31,  1.56it/s]
  0%|          | 266/57600 [02:47<10:18:45,  1.54it/s]
  0%|          | 267/57600 [02:48<10:20:17,  1.54it/s]
  0%|          | 268/57600 [02:49<10:16:57,  1.55it/s]
  0%|          | 269/57600 [02:49<9:50:41,  1.62it/s] 
  0%|          | 270/57600 [02:50<9:45:05,  1.63it/s]
  0%|          | 271/57600 [02:50<9:48:32,  1.62it/s]
  0%|          | 272/57600 [02:51<9:54:23,  1.61it/s]
  0%|          | 273/57600 [02:52<9:57:59,  1.60it/s]
  0%|          | 274/57600 [02:52<10:10:07,  1.57it/s]
  0%|          | 275/57600 [02:53<10:01:26,  1.59it/s]
  0%|          | 276/57600 [02:54<9:59:15,  1.59it/s] 
  0%|          | 277/57600 [02:54<9:44:20,  1.63it/s]
  0%|          | 278/57600 [02:55<9:41:39,  1.64it/s]
  0%|          | 279/57600 [02:55<9:29:44,  1.68it/s]
  0%|          | 280/57600 [02:56<9:59:29,  1.59it/s]
                                                     
{'loss': 1.8665, 'learning_rate': 9.987456445993032e-07, 'epoch': 3.09}

  0%|          | 280/57600 [02:56<9:59:29,  1.59it/s]
  0%|          | 281/57600 [02:57<9:54:05,  1.61it/s]
  0%|          | 282/57600 [02:57<9:58:41,  1.60it/s]
  0%|          | 283/57600 [02:58<10:04:24,  1.58it/s]
  0%|          | 284/57600 [02:59<10:01:39,  1.59it/s]
  0%|          | 285/57600 [02:59<10:20:33,  1.54it/s]
  0%|          | 286/57600 [03:00<10:09:09,  1.57it/s]
  0%|          | 287/57600 [03:01<9:52:07,  1.61it/s] 
  0%|          | 288/57600 [03:01<10:20:27,  1.54it/s]
  1%|          | 289/57600 [03:02<9:59:23,  1.59it/s] 
  1%|          | 290/57600 [03:02<10:03:13,  1.58it/s]
  1%|          | 291/57600 [03:03<9:57:36,  1.60it/s] 
  1%|          | 292/57600 [03:04<9:52:29,  1.61it/s]
  1%|          | 293/57600 [03:04<9:55:12,  1.60it/s]
  1%|          | 294/57600 [03:05<10:09:58,  1.57it/s]
  1%|          | 295/57600 [03:06<10:05:10,  1.58it/s]
  1%|          | 296/57600 [03:06<9:56:20,  1.60it/s] 
  1%|          | 297/57600 [03:07<9:50:59,  1.62it/s]
  1%|          | 298/57600 [03:07<9:48:46,  1.62it/s]
  1%|          | 299/57600 [03:08<9:49:36,  1.62it/s]
  1%|          | 300/57600 [03:09<9:58:25,  1.60it/s]
                                                     
{'loss': 1.9419, 'learning_rate': 9.98432055749129e-07, 'epoch': 3.31}

  1%|          | 300/57600 [03:09<9:58:25,  1.60it/s]
  1%|          | 301/57600 [03:09<9:52:13,  1.61it/s]
  1%|          | 302/57600 [03:10<10:03:12,  1.58it/s]
  1%|          | 303/57600 [03:11<10:05:07,  1.58it/s]
  1%|          | 304/57600 [03:11<10:19:34,  1.54it/s]
  1%|          | 305/57600 [03:12<10:08:26,  1.57it/s]
  1%|          | 306/57600 [03:13<10:11:44,  1.56it/s]
  1%|          | 307/57600 [03:13<10:24:48,  1.53it/s]
  1%|          | 308/57600 [03:14<10:18:02,  1.55it/s]
  1%|          | 309/57600 [03:15<10:24:42,  1.53it/s]
  1%|          | 310/57600 [03:15<10:23:42,  1.53it/s]
  1%|          | 311/57600 [03:16<10:20:23,  1.54it/s]
  1%|          | 312/57600 [03:16<10:14:58,  1.55it/s]
  1%|          | 313/57600 [03:17<9:52:59,  1.61it/s] 
  1%|          | 314/57600 [03:18<10:07:25,  1.57it/s]
  1%|          | 315/57600 [03:18<10:07:17,  1.57it/s]
  1%|          | 316/57600 [03:19<10:10:11,  1.56it/s]
  1%|          | 317/57600 [03:20<10:00:26,  1.59it/s]
  1%|          | 318/57600 [03:20<9:49:23,  1.62it/s] 
  1%|          | 319/57600 [03:21<9:54:30,  1.61it/s]
  1%|          | 320/57600 [03:21<9:43:43,  1.64it/s]
                                                     
{'loss': 1.8332, 'learning_rate': 9.981184668989545e-07, 'epoch': 3.53}

  1%|          | 320/57600 [03:21<9:43:43,  1.64it/s]
  1%|          | 321/57600 [03:22<9:39:22,  1.65it/s]
  1%|          | 322/57600 [03:23<9:35:57,  1.66it/s]
  1%|          | 323/57600 [03:23<9:38:16,  1.65it/s]
  1%|          | 324/57600 [03:24<9:29:21,  1.68it/s]
  1%|          | 325/57600 [03:25<10:17:13,  1.55it/s]
  1%|          | 326/57600 [03:25<10:21:17,  1.54it/s]
  1%|          | 327/57600 [03:26<10:05:01,  1.58it/s]
  1%|          | 328/57600 [03:26<10:16:35,  1.55it/s]
  1%|          | 329/57600 [03:27<10:00:25,  1.59it/s]
  1%|          | 330/57600 [03:28<10:03:38,  1.58it/s]
  1%|          | 331/57600 [03:28<10:26:10,  1.52it/s]
  1%|          | 332/57600 [03:29<10:16:20,  1.55it/s]
  1%|          | 333/57600 [03:30<10:03:48,  1.58it/s]
  1%|          | 334/57600 [03:30<9:47:56,  1.62it/s] 
  1%|          | 335/57600 [03:31<9:42:24,  1.64it/s]
  1%|          | 336/57600 [03:31<9:47:27,  1.62it/s]
  1%|          | 337/57600 [03:32<9:51:13,  1.61it/s]
  1%|          | 338/57600 [03:33<9:53:47,  1.61it/s]
  1%|          | 339/57600 [03:33<10:06:48,  1.57it/s]
  1%|          | 340/57600 [03:34<10:18:56,  1.54it/s]
                                                      
{'loss': 1.8534, 'learning_rate': 9.978048780487803e-07, 'epoch': 3.75}

  1%|          | 340/57600 [03:34<10:18:56,  1.54it/s]
  1%|          | 341/57600 [03:35<10:14:37,  1.55it/s]
  1%|          | 342/57600 [03:35<10:52:46,  1.46it/s]
  1%|          | 343/57600 [03:36<10:39:13,  1.49it/s]
  1%|          | 344/57600 [03:37<10:05:34,  1.58it/s]
  1%|          | 345/57600 [03:37<10:10:54,  1.56it/s]
  1%|          | 346/57600 [03:38<9:52:21,  1.61it/s] 
  1%|          | 347/57600 [03:38<9:34:05,  1.66it/s]
  1%|          | 348/57600 [03:39<9:25:03,  1.69it/s]
  1%|          | 349/57600 [03:40<9:24:32,  1.69it/s]
  1%|          | 350/57600 [03:40<9:24:33,  1.69it/s]
  1%|          | 351/57600 [03:41<9:32:59,  1.67it/s]
  1%|          | 352/57600 [03:41<9:39:29,  1.65it/s]
  1%|          | 353/57600 [03:42<9:42:51,  1.64it/s]
  1%|          | 354/57600 [03:43<9:39:03,  1.65it/s]
  1%|          | 355/57600 [03:43<9:37:32,  1.65it/s]
  1%|          | 356/57600 [03:44<9:31:27,  1.67it/s]
  1%|          | 357/57600 [03:44<9:40:57,  1.64it/s]
  1%|          | 358/57600 [03:45<9:42:15,  1.64it/s]
  1%|          | 359/57600 [03:46<10:11:15,  1.56it/s]
  1%|          | 360/57600 [03:46<9:59:13,  1.59it/s] 
                                                     
{'loss': 1.9421, 'learning_rate': 9.974912891986062e-07, 'epoch': 3.97}

  1%|          | 360/57600 [03:46<9:59:13,  1.59it/s]
  1%|          | 361/57600 [03:47<10:07:45,  1.57it/s]
  1%|          | 362/57600 [03:48<9:57:42,  1.60it/s] 
  1%|          | 363/57600 [03:48<10:03:49,  1.58it/s]
  1%|          | 364/57600 [03:49<10:02:29,  1.58it/s]
  1%|          | 365/57600 [03:50<10:05:17,  1.58it/s]
  1%|          | 366/57600 [03:50<10:02:33,  1.58it/s]
  1%|          | 367/57600 [03:51<10:01:17,  1.59it/s]
  1%|          | 368/57600 [03:51<10:01:21,  1.59it/s]
  1%|          | 369/57600 [03:52<9:49:13,  1.62it/s] 
  1%|          | 370/57600 [03:53<9:49:24,  1.62it/s]
  1%|          | 371/57600 [03:53<9:53:49,  1.61it/s]
  1%|          | 372/57600 [03:54<9:52:56,  1.61it/s]
  1%|          | 373/57600 [03:54<9:52:34,  1.61it/s]
  1%|          | 374/57600 [03:55<10:16:58,  1.55it/s]
  1%|          | 375/57600 [03:56<10:14:16,  1.55it/s]
  1%|          | 376/57600 [03:56<9:56:17,  1.60it/s] 
  1%|          | 377/57600 [03:57<9:46:20,  1.63it/s]
  1%|          | 378/57600 [03:58<9:48:42,  1.62it/s]
  1%|          | 379/57600 [03:58<9:51:46,  1.61it/s]
  1%|          | 380/57600 [03:59<10:10:09,  1.56it/s]
                                                      
{'loss': 1.9374, 'learning_rate': 9.97177700348432e-07, 'epoch': 4.19}

  1%|          | 380/57600 [03:59<10:10:09,  1.56it/s]
  1%|          | 381/57600 [04:00<9:54:39,  1.60it/s] 
  1%|          | 382/57600 [04:00<9:59:01,  1.59it/s]
  1%|          | 383/57600 [04:01<10:02:48,  1.58it/s]
  1%|          | 384/57600 [04:01<9:58:56,  1.59it/s] 
  1%|          | 385/57600 [04:02<9:54:11,  1.60it/s]
  1%|          | 386/57600 [04:03<10:05:47,  1.57it/s]
  1%|          | 387/57600 [04:03<10:04:29,  1.58it/s]
  1%|          | 388/57600 [04:04<9:43:12,  1.63it/s] 
  1%|          | 389/57600 [04:04<9:38:57,  1.65it/s]
  1%|          | 390/57600 [04:05<9:40:30,  1.64it/s]
  1%|          | 391/57600 [04:06<9:43:43,  1.63it/s]
  1%|          | 392/57600 [04:06<10:08:58,  1.57it/s]
  1%|          | 393/57600 [04:07<10:22:22,  1.53it/s]
  1%|          | 394/57600 [04:08<10:47:40,  1.47it/s]
  1%|          | 395/57600 [04:09<10:59:28,  1.45it/s]
  1%|          | 396/57600 [04:09<10:32:36,  1.51it/s]
  1%|          | 397/57600 [04:10<10:25:46,  1.52it/s]
  1%|          | 398/57600 [04:10<10:10:36,  1.56it/s]
  1%|          | 399/57600 [04:11<10:21:18,  1.53it/s]
  1%|          | 400/57600 [04:12<10:13:11,  1.55it/s]
                                                      
{'loss': 1.8876, 'learning_rate': 9.96864111498258e-07, 'epoch': 4.42}

  1%|          | 400/57600 [04:12<10:13:11,  1.55it/s]
  1%|          | 401/57600 [04:12<10:00:26,  1.59it/s]
  1%|          | 402/57600 [04:13<9:56:21,  1.60it/s] 
  1%|          | 403/57600 [04:14<9:56:01,  1.60it/s]
  1%|          | 404/57600 [04:14<10:07:36,  1.57it/s]
  1%|          | 405/57600 [04:15<10:09:54,  1.56it/s]
  1%|          | 406/57600 [04:16<10:38:28,  1.49it/s]
  1%|          | 407/57600 [04:16<10:36:15,  1.50it/s]
  1%|          | 408/57600 [04:17<10:31:45,  1.51it/s]
  1%|          | 409/57600 [04:18<10:28:38,  1.52it/s]
  1%|          | 410/57600 [04:18<10:13:18,  1.55it/s]
  1%|          | 411/57600 [04:19<10:13:23,  1.55it/s]
  1%|          | 412/57600 [04:19<10:22:57,  1.53it/s]
  1%|          | 413/57600 [04:20<10:09:04,  1.56it/s]
  1%|          | 414/57600 [04:21<10:03:06,  1.58it/s]
  1%|          | 415/57600 [04:21<10:01:48,  1.58it/s]
  1%|          | 416/57600 [04:22<10:06:34,  1.57it/s]
  1%|          | 417/57600 [04:23<9:55:44,  1.60it/s] 
  1%|          | 418/57600 [04:23<9:45:24,  1.63it/s]
  1%|          | 419/57600 [04:24<9:43:34,  1.63it/s]
  1%|          | 420/57600 [04:24<9:41:55,  1.64it/s]
                                                     
{'loss': 1.8593, 'learning_rate': 9.965505226480835e-07, 'epoch': 4.64}

  1%|          | 420/57600 [04:24<9:41:55,  1.64it/s]
  1%|          | 421/57600 [04:25<9:48:57,  1.62it/s]
  1%|          | 422/57600 [04:26<9:54:16,  1.60it/s]
  1%|          | 423/57600 [04:26<9:59:48,  1.59it/s]
  1%|          | 424/57600 [04:27<9:45:13,  1.63it/s]
  1%|          | 425/57600 [04:28<9:55:35,  1.60it/s]
  1%|          | 426/57600 [04:28<9:56:12,  1.60it/s]
  1%|          | 427/57600 [04:29<9:50:17,  1.61it/s]
  1%|          | 428/57600 [04:29<9:48:31,  1.62it/s]
  1%|          | 429/57600 [04:30<10:02:28,  1.58it/s]
  1%|          | 430/57600 [04:31<10:22:56,  1.53it/s]
  1%|          | 431/57600 [04:31<10:17:42,  1.54it/s]
  1%|          | 432/57600 [04:32<10:11:14,  1.56it/s]
  1%|          | 433/57600 [04:33<10:18:13,  1.54it/s]
  1%|          | 434/57600 [04:33<10:21:55,  1.53it/s]
  1%|          | 435/57600 [04:34<10:23:26,  1.53it/s]
  1%|          | 436/57600 [04:35<10:10:50,  1.56it/s]
  1%|          | 437/57600 [04:35<9:56:16,  1.60it/s] 
  1%|          | 438/57600 [04:36<10:05:02,  1.57it/s]
  1%|          | 439/57600 [04:36<9:45:33,  1.63it/s] 
  1%|          | 440/57600 [04:37<9:55:38,  1.60it/s]
                                                     
{'loss': 1.8243, 'learning_rate': 9.962369337979094e-07, 'epoch': 4.86}

  1%|          | 440/57600 [04:37<9:55:38,  1.60it/s]
  1%|          | 441/57600 [04:38<9:55:32,  1.60it/s]
  1%|          | 442/57600 [04:38<9:38:02,  1.65it/s]
  1%|          | 443/57600 [04:39<9:38:58,  1.65it/s]
  1%|          | 444/57600 [04:39<9:32:47,  1.66it/s]
  1%|          | 445/57600 [04:40<9:41:35,  1.64it/s]
  1%|          | 446/57600 [04:41<9:33:02,  1.66it/s]
  1%|          | 447/57600 [04:41<9:57:51,  1.59it/s]
  1%|          | 448/57600 [04:42<9:52:56,  1.61it/s]
  1%|          | 449/57600 [04:43<9:44:22,  1.63it/s]
  1%|          | 450/57600 [04:43<9:52:43,  1.61it/s]
  1%|          | 451/57600 [04:44<9:36:05,  1.65it/s]
  1%|          | 452/57600 [04:44<9:36:48,  1.65it/s]
  1%|          | 453/57600 [04:45<9:38:45,  1.65it/s]
  1%|          | 454/57600 [04:46<10:26:22,  1.52it/s]
  1%|          | 455/57600 [04:46<10:19:30,  1.54it/s]
  1%|          | 456/57600 [04:47<10:05:25,  1.57it/s]
  1%|          | 457/57600 [04:48<10:02:03,  1.58it/s]
  1%|          | 458/57600 [04:48<10:18:55,  1.54it/s]
  1%|          | 459/57600 [04:49<10:37:13,  1.49it/s]
  1%|          | 460/57600 [04:50<10:22:23,  1.53it/s]
                                                      
{'loss': 1.8791, 'learning_rate': 9.95923344947735e-07, 'epoch': 5.08}

  1%|          | 460/57600 [04:50<10:22:23,  1.53it/s]
  1%|          | 461/57600 [04:50<10:05:40,  1.57it/s]
  1%|          | 462/57600 [04:51<9:47:24,  1.62it/s] 
  1%|          | 463/57600 [04:51<10:03:42,  1.58it/s]
  1%|          | 464/57600 [04:52<10:21:11,  1.53it/s]
  1%|          | 465/57600 [04:53<10:16:45,  1.54it/s]
  1%|          | 466/57600 [04:53<10:09:59,  1.56it/s]
  1%|          | 467/57600 [04:54<10:12:55,  1.55it/s]
  1%|          | 468/57600 [04:55<10:10:34,  1.56it/s]
  1%|          | 469/57600 [04:55<10:11:03,  1.56it/s]
  1%|          | 470/57600 [04:56<10:07:17,  1.57it/s]
  1%|          | 471/57600 [04:57<10:08:58,  1.56it/s]
  1%|          | 472/57600 [04:57<9:58:15,  1.59it/s] 
  1%|          | 473/57600 [04:58<9:56:09,  1.60it/s]
  1%|          | 474/57600 [04:59<10:04:05,  1.58it/s]
  1%|          | 475/57600 [04:59<10:00:00,  1.59it/s]
  1%|          | 476/57600 [05:00<9:58:21,  1.59it/s] 
  1%|          | 477/57600 [05:00<10:14:23,  1.55it/s]
  1%|          | 478/57600 [05:01<10:08:47,  1.56it/s]
  1%|          | 479/57600 [05:02<10:11:03,  1.56it/s]
  1%|          | 480/57600 [05:02<9:55:04,  1.60it/s] 
                                                     
{'loss': 1.8878, 'learning_rate': 9.95609756097561e-07, 'epoch': 5.3}

  1%|          | 480/57600 [05:02<9:55:04,  1.60it/s]
  1%|          | 481/57600 [05:03<9:54:05,  1.60it/s]
  1%|          | 482/57600 [05:04<9:48:45,  1.62it/s]
  1%|          | 483/57600 [05:04<10:10:25,  1.56it/s]
  1%|          | 484/57600 [05:05<10:03:51,  1.58it/s]
  1%|          | 485/57600 [05:05<9:50:34,  1.61it/s] 
  1%|          | 486/57600 [05:06<9:53:15,  1.60it/s]
  1%|          | 487/57600 [05:07<10:05:27,  1.57it/s]
  1%|          | 488/57600 [05:07<9:55:04,  1.60it/s] 
  1%|          | 489/57600 [05:08<9:55:16,  1.60it/s]
  1%|          | 490/57600 [05:09<9:39:46,  1.64it/s]
  1%|          | 491/57600 [05:09<9:31:51,  1.66it/s]
  1%|          | 492/57600 [05:10<9:39:29,  1.64it/s]
  1%|          | 493/57600 [05:10<9:42:52,  1.63it/s]
  1%|          | 494/57600 [05:11<9:27:58,  1.68it/s]
  1%|          | 495/57600 [05:12<9:44:57,  1.63it/s]
  1%|          | 496/57600 [05:12<9:52:28,  1.61it/s]
  1%|          | 497/57600 [05:13<9:51:25,  1.61it/s]
  1%|          | 498/57600 [05:13<10:01:12,  1.58it/s]
  1%|          | 499/57600 [05:14<10:03:37,  1.58it/s]
  1%|          | 500/57600 [05:15<10:02:36,  1.58it/s]
                                                      
{'loss': 1.8985, 'learning_rate': 9.952961672473868e-07, 'epoch': 5.52}

  1%|          | 500/57600 [05:15<10:02:36,  1.58it/s]
  1%|          | 501/57600 [05:15<9:55:23,  1.60it/s] 
  1%|          | 502/57600 [05:16<10:06:03,  1.57it/s]
  1%|          | 503/57600 [05:17<10:08:55,  1.56it/s]
  1%|          | 504/57600 [05:17<9:57:07,  1.59it/s] 
  1%|          | 505/57600 [05:18<9:47:34,  1.62it/s]
  1%|          | 506/57600 [05:19<10:07:07,  1.57it/s]
  1%|          | 507/57600 [05:19<10:12:13,  1.55it/s]
  1%|          | 508/57600 [05:20<10:00:28,  1.58it/s]
  1%|          | 509/57600 [05:20<9:46:08,  1.62it/s] 
  1%|          | 510/57600 [05:21<9:43:15,  1.63it/s]
  1%|          | 511/57600 [05:22<9:34:18,  1.66it/s]
  1%|          | 512/57600 [05:22<10:10:05,  1.56it/s]
  1%|          | 513/57600 [05:23<10:26:43,  1.52it/s]
  1%|          | 514/57600 [05:24<10:16:41,  1.54it/s]
  1%|          | 515/57600 [05:24<10:04:48,  1.57it/s]
  1%|          | 516/57600 [05:25<10:12:08,  1.55it/s]
  1%|          | 517/57600 [05:26<10:09:19,  1.56it/s]
  1%|          | 518/57600 [05:26<10:11:28,  1.56it/s]
  1%|          | 519/57600 [05:27<10:10:55,  1.56it/s]
  1%|          | 520/57600 [05:27<9:52:32,  1.61it/s] 
                                                     
{'loss': 1.84, 'learning_rate': 9.949825783972126e-07, 'epoch': 5.74}

  1%|          | 520/57600 [05:27<9:52:32,  1.61it/s]
  1%|          | 521/57600 [05:28<10:10:02,  1.56it/s]
  1%|          | 522/57600 [05:29<10:20:23,  1.53it/s]
  1%|          | 523/57600 [05:29<10:26:24,  1.52it/s]
  1%|          | 524/57600 [05:30<10:02:55,  1.58it/s]
  1%|          | 525/57600 [05:31<10:17:53,  1.54it/s]
  1%|          | 526/57600 [05:31<10:16:26,  1.54it/s]
  1%|          | 527/57600 [05:32<10:17:11,  1.54it/s]
  1%|          | 528/57600 [05:33<10:04:34,  1.57it/s]
  1%|          | 529/57600 [05:33<10:09:08,  1.56it/s]
  1%|          | 530/57600 [05:34<10:05:42,  1.57it/s]
  1%|          | 531/57600 [05:35<10:01:47,  1.58it/s]
  1%|          | 532/57600 [05:35<10:07:44,  1.57it/s]
  1%|          | 533/57600 [05:36<10:00:23,  1.58it/s]
  1%|          | 534/57600 [05:36<10:01:48,  1.58it/s]
  1%|          | 535/57600 [05:37<9:59:37,  1.59it/s] 
  1%|          | 536/57600 [05:38<9:59:45,  1.59it/s]
  1%|          | 537/57600 [05:38<9:51:52,  1.61it/s]
  1%|          | 538/57600 [05:39<10:09:20,  1.56it/s]
  1%|          | 539/57600 [05:40<10:02:46,  1.58it/s]
  1%|          | 540/57600 [05:40<10:02:01,  1.58it/s]
                                                      
{'loss': 1.8468, 'learning_rate': 9.946689895470383e-07, 'epoch': 5.96}

  1%|          | 540/57600 [05:40<10:02:01,  1.58it/s]
  1%|          | 541/57600 [05:41<10:18:25,  1.54it/s]
  1%|          | 542/57600 [05:41<9:59:57,  1.59it/s] 
  1%|          | 543/57600 [05:42<9:43:01,  1.63it/s]
  1%|          | 544/57600 [05:43<10:12:05,  1.55it/s]
  1%|          | 545/57600 [05:43<10:11:36,  1.55it/s]
  1%|          | 546/57600 [05:44<10:09:49,  1.56it/s]
  1%|          | 547/57600 [05:45<10:10:28,  1.56it/s]
  1%|          | 548/57600 [05:45<10:12:20,  1.55it/s]
  1%|          | 549/57600 [05:46<10:32:17,  1.50it/s]
  1%|          | 550/57600 [05:47<10:07:36,  1.56it/s]
  1%|          | 551/57600 [05:47<10:16:06,  1.54it/s]
  1%|          | 552/57600 [05:48<10:08:13,  1.56it/s]
  1%|          | 553/57600 [05:49<10:12:17,  1.55it/s]
  1%|          | 554/57600 [05:49<10:04:07,  1.57it/s]
  1%|          | 555/57600 [05:50<10:18:41,  1.54it/s]
  1%|          | 556/57600 [05:51<10:13:13,  1.55it/s]
  1%|          | 557/57600 [05:51<9:54:50,  1.60it/s] 
  1%|          | 558/57600 [05:52<10:20:35,  1.53it/s]
  1%|          | 559/57600 [05:52<10:27:10,  1.52it/s]
  1%|          | 560/57600 [05:53<10:21:52,  1.53it/s]
                                                      
{'loss': 1.8469, 'learning_rate': 9.94355400696864e-07, 'epoch': 6.18}

  1%|          | 560/57600 [05:53<10:21:52,  1.53it/s]
  1%|          | 561/57600 [05:54<10:20:28,  1.53it/s]
  1%|          | 562/57600 [05:54<10:18:19,  1.54it/s]
  1%|          | 563/57600 [05:55<9:57:51,  1.59it/s] 
  1%|          | 564/57600 [05:56<9:59:39,  1.59it/s]
  1%|          | 565/57600 [05:56<10:35:38,  1.50it/s]
  1%|          | 566/57600 [05:57<10:18:30,  1.54it/s]
  1%|          | 567/57600 [05:58<10:33:18,  1.50it/s]
  1%|          | 568/57600 [05:58<10:14:56,  1.55it/s]
  1%|          | 569/57600 [05:59<9:54:14,  1.60it/s] 
  1%|          | 570/57600 [05:59<9:46:36,  1.62it/s]
  1%|          | 571/57600 [06:00<9:44:32,  1.63it/s]
  1%|          | 572/57600 [06:01<9:38:49,  1.64it/s]
  1%|          | 573/57600 [06:01<9:32:32,  1.66it/s]
  1%|          | 574/57600 [06:02<9:27:05,  1.68it/s]
  1%|          | 575/57600 [06:02<9:40:21,  1.64it/s]
  1%|          | 576/57600 [06:03<9:33:32,  1.66it/s]
  1%|          | 577/57600 [06:04<9:33:52,  1.66it/s]
  1%|          | 578/57600 [06:04<9:47:58,  1.62it/s]
  1%|          | 579/57600 [06:05<9:49:53,  1.61it/s]
  1%|          | 580/57600 [06:06<9:55:13,  1.60it/s]
                                                     
{'loss': 1.8528, 'learning_rate': 9.940418118466898e-07, 'epoch': 6.4}

  1%|          | 580/57600 [06:06<9:55:13,  1.60it/s]
  1%|          | 581/57600 [06:06<10:01:03,  1.58it/s]
  1%|          | 582/57600 [06:07<10:23:03,  1.53it/s]
  1%|          | 583/57600 [06:08<10:22:45,  1.53it/s]
  1%|          | 584/57600 [06:08<10:20:24,  1.53it/s]
  1%|          | 585/57600 [06:09<9:58:31,  1.59it/s] 
  1%|          | 586/57600 [06:09<9:43:04,  1.63it/s]
  1%|          | 587/57600 [06:10<10:03:31,  1.57it/s]
  1%|          | 588/57600 [06:11<10:06:52,  1.57it/s]
  1%|          | 589/57600 [06:11<9:49:29,  1.61it/s] 
  1%|          | 590/57600 [06:12<9:36:04,  1.65it/s]
  1%|          | 591/57600 [06:13<9:50:38,  1.61it/s]
  1%|          | 592/57600 [06:13<9:43:06,  1.63it/s]
  1%|          | 593/57600 [06:14<9:56:19,  1.59it/s]
  1%|          | 594/57600 [06:14<9:43:51,  1.63it/s]
  1%|          | 595/57600 [06:15<9:53:05,  1.60it/s]
  1%|          | 596/57600 [06:16<10:06:11,  1.57it/s]
  1%|          | 597/57600 [06:16<10:13:47,  1.55it/s]
  1%|          | 598/57600 [06:17<10:47:58,  1.47it/s]
  1%|          | 599/57600 [06:18<10:34:51,  1.50it/s]
  1%|          | 600/57600 [06:18<10:23:09,  1.52it/s]
                                                      
{'loss': 1.8269, 'learning_rate': 9.937282229965156e-07, 'epoch': 6.62}

  1%|          | 600/57600 [06:18<10:23:09,  1.52it/s]
  1%|          | 601/57600 [06:19<10:13:05,  1.55it/s]
  1%|          | 602/57600 [06:20<9:56:06,  1.59it/s] 
  1%|          | 603/57600 [06:20<10:06:36,  1.57it/s]
  1%|          | 604/57600 [06:21<9:55:24,  1.60it/s] 
  1%|          | 605/57600 [06:22<10:08:38,  1.56it/s]
  1%|          | 606/57600 [06:22<10:05:35,  1.57it/s]
  1%|          | 607/57600 [06:23<9:49:53,  1.61it/s] 
  1%|          | 608/57600 [06:23<9:46:40,  1.62it/s]
  1%|          | 609/57600 [06:24<9:40:41,  1.64it/s]
  1%|          | 610/57600 [06:25<9:36:23,  1.65it/s]
  1%|          | 611/57600 [06:25<9:59:05,  1.59it/s]
  1%|          | 612/57600 [06:26<9:48:01,  1.62it/s]
  1%|          | 613/57600 [06:26<9:45:12,  1.62it/s]
  1%|          | 614/57600 [06:27<9:54:39,  1.60it/s]
  1%|          | 615/57600 [06:28<10:13:53,  1.55it/s]
  1%|          | 616/57600 [06:28<10:00:54,  1.58it/s]
  1%|          | 617/57600 [06:29<10:06:43,  1.57it/s]
  1%|          | 618/57600 [06:30<10:22:31,  1.53it/s]
  1%|          | 619/57600 [06:30<10:13:03,  1.55it/s]
  1%|          | 620/57600 [06:31<10:16:48,  1.54it/s]
                                                      
{'loss': 1.8324, 'learning_rate': 9.934146341463415e-07, 'epoch': 6.84}

  1%|          | 620/57600 [06:31<10:16:48,  1.54it/s]
  1%|          | 621/57600 [06:32<10:23:20,  1.52it/s]
  1%|          | 622/57600 [06:32<10:43:12,  1.48it/s]
  1%|          | 623/57600 [06:33<10:19:06,  1.53it/s]
  1%|          | 624/57600 [06:34<10:02:43,  1.58it/s]
  1%|          | 625/57600 [06:34<9:55:43,  1.59it/s] 
  1%|          | 626/57600 [06:35<10:12:30,  1.55it/s]
  1%|          | 627/57600 [06:36<10:11:25,  1.55it/s]
  1%|          | 628/57600 [06:36<10:29:53,  1.51it/s]
  1%|          | 629/57600 [06:37<10:17:14,  1.54it/s]
  1%|          | 630/57600 [06:37<10:08:42,  1.56it/s]
  1%|          | 631/57600 [06:38<10:03:10,  1.57it/s]
  1%|          | 632/57600 [06:39<9:54:32,  1.60it/s] 
  1%|          | 633/57600 [06:39<9:38:11,  1.64it/s]
  1%|          | 634/57600 [06:40<9:48:33,  1.61it/s]
  1%|          | 635/57600 [06:41<9:59:13,  1.58it/s]
  1%|          | 636/57600 [06:41<9:45:44,  1.62it/s]
  1%|          | 637/57600 [06:42<9:54:02,  1.60it/s]
  1%|          | 638/57600 [06:42<9:59:12,  1.58it/s]
  1%|          | 639/57600 [06:43<10:10:00,  1.56it/s]
  1%|          | 640/57600 [06:44<10:31:59,  1.50it/s]
                                                      
{'loss': 1.808, 'learning_rate': 9.931010452961673e-07, 'epoch': 7.06}

  1%|          | 640/57600 [06:44<10:31:59,  1.50it/s]
  1%|          | 641/57600 [06:44<10:10:58,  1.55it/s]
  1%|          | 642/57600 [06:45<9:58:29,  1.59it/s] 
  1%|          | 643/57600 [06:46<9:52:25,  1.60it/s]
  1%|          | 644/57600 [06:46<10:03:23,  1.57it/s]
  1%|          | 645/57600 [06:47<10:00:35,  1.58it/s]
  1%|          | 646/57600 [06:48<10:03:12,  1.57it/s]
  1%|          | 647/57600 [06:48<9:52:39,  1.60it/s] 
  1%|          | 648/57600 [06:49<9:55:13,  1.59it/s]
  1%|          | 649/57600 [06:49<10:06:47,  1.56it/s]
  1%|          | 650/57600 [06:50<10:15:12,  1.54it/s]
  1%|          | 651/57600 [06:51<10:17:17,  1.54it/s]
  1%|          | 652/57600 [06:51<10:16:53,  1.54it/s]
  1%|          | 653/57600 [06:52<10:22:29,  1.52it/s]
  1%|          | 654/57600 [06:53<10:19:10,  1.53it/s]
  1%|          | 655/57600 [06:53<10:14:55,  1.54it/s]
  1%|          | 656/57600 [06:54<10:09:22,  1.56it/s]
  1%|          | 657/57600 [06:55<9:59:34,  1.58it/s] 
  1%|          | 658/57600 [06:55<9:58:57,  1.58it/s]
  1%|          | 659/57600 [06:56<10:08:28,  1.56it/s]
  1%|          | 660/57600 [06:57<10:02:34,  1.57it/s]
                                                      
{'loss': 1.9003, 'learning_rate': 9.92787456445993e-07, 'epoch': 7.28}

  1%|          | 660/57600 [06:57<10:02:34,  1.57it/s]
  1%|          | 661/57600 [06:57<10:02:55,  1.57it/s]
  1%|          | 662/57600 [06:58<10:04:02,  1.57it/s]
  1%|          | 663/57600 [06:58<10:05:27,  1.57it/s]
  1%|          | 664/57600 [06:59<10:07:43,  1.56it/s]
  1%|          | 665/57600 [07:00<9:54:28,  1.60it/s] 
  1%|          | 666/57600 [07:00<9:43:00,  1.63it/s]
  1%|          | 667/57600 [07:01<9:36:52,  1.64it/s]
  1%|          | 668/57600 [07:02<10:07:12,  1.56it/s]
  1%|          | 669/57600 [07:02<10:01:33,  1.58it/s]
  1%|          | 670/57600 [07:03<10:09:30,  1.56it/s]
  1%|          | 671/57600 [07:04<10:08:52,  1.56it/s]
  1%|          | 672/57600 [07:04<10:06:51,  1.56it/s]
  1%|          | 673/57600 [07:05<10:12:45,  1.55it/s]
  1%|          | 674/57600 [07:05<9:55:54,  1.59it/s] 
  1%|          | 675/57600 [07:06<9:59:42,  1.58it/s]
  1%|          | 676/57600 [07:07<9:58:34,  1.58it/s]
  1%|          | 677/57600 [07:07<10:10:01,  1.56it/s]
  1%|          | 678/57600 [07:08<10:00:00,  1.58it/s]
  1%|          | 679/57600 [07:09<9:47:42,  1.61it/s] 
  1%|          | 680/57600 [07:09<9:59:14,  1.58it/s]
                                                     
{'loss': 1.908, 'learning_rate': 9.924738675958186e-07, 'epoch': 7.51}

  1%|          | 680/57600 [07:09<9:59:14,  1.58it/s]
  1%|          | 681/57600 [07:10<9:54:34,  1.60it/s]
  1%|          | 682/57600 [07:10<9:47:49,  1.61it/s]
  1%|          | 683/57600 [07:11<9:46:48,  1.62it/s]
  1%|          | 684/57600 [07:12<9:36:41,  1.64it/s]
  1%|          | 685/57600 [07:12<9:47:21,  1.61it/s]
  1%|          | 686/57600 [07:13<9:46:30,  1.62it/s]
  1%|          | 687/57600 [07:14<9:57:37,  1.59it/s]
  1%|          | 688/57600 [07:14<9:47:39,  1.61it/s]
  1%|          | 689/57600 [07:15<9:57:05,  1.59it/s]
  1%|          | 690/57600 [07:15<9:48:41,  1.61it/s]
  1%|          | 691/57600 [07:16<9:42:35,  1.63it/s]
  1%|          | 692/57600 [07:17<9:51:40,  1.60it/s]
  1%|          | 693/57600 [07:17<10:08:50,  1.56it/s]
  1%|          | 694/57600 [07:18<10:00:15,  1.58it/s]
  1%|          | 695/57600 [07:19<10:06:26,  1.56it/s]
  1%|          | 696/57600 [07:19<10:22:48,  1.52it/s]
  1%|          | 697/57600 [07:20<10:09:33,  1.56it/s]
  1%|          | 698/57600 [07:21<10:16:43,  1.54it/s]
  1%|          | 699/57600 [07:21<10:28:12,  1.51it/s]
  1%|          | 700/57600 [07:22<10:38:29,  1.49it/s]
                                                      
{'loss': 1.8165, 'learning_rate': 9.921602787456445e-07, 'epoch': 7.73}

  1%|          | 700/57600 [07:22<10:38:29,  1.49it/s]
  1%|          | 701/57600 [07:23<10:29:03,  1.51it/s]
  1%|          | 702/57600 [07:23<10:22:34,  1.52it/s]
  1%|          | 703/57600 [07:24<10:14:57,  1.54it/s]
  1%|          | 704/57600 [07:24<10:04:41,  1.57it/s]
  1%|          | 705/57600 [07:25<9:50:29,  1.61it/s] 
  1%|          | 706/57600 [07:26<9:43:26,  1.63it/s]
  1%|          | 707/57600 [07:26<9:51:40,  1.60it/s]
  1%|          | 708/57600 [07:27<9:39:45,  1.64it/s]
  1%|          | 709/57600 [07:28<9:57:00,  1.59it/s]
  1%|          | 710/57600 [07:28<9:46:55,  1.62it/s]
  1%|          | 711/57600 [07:29<9:41:45,  1.63it/s]
  1%|          | 712/57600 [07:29<9:51:48,  1.60it/s]
  1%|          | 713/57600 [07:30<10:04:22,  1.57it/s]
  1%|          | 714/57600 [07:31<10:02:21,  1.57it/s]
  1%|          | 715/57600 [07:31<10:12:26,  1.55it/s]
  1%|          | 716/57600 [07:32<10:18:51,  1.53it/s]
  1%|          | 717/57600 [07:33<9:54:37,  1.59it/s] 
  1%|          | 718/57600 [07:33<10:07:30,  1.56it/s]
  1%|          | 719/57600 [07:34<10:24:40,  1.52it/s]
  1%|▏         | 720/57600 [07:35<10:23:31,  1.52it/s]
                                                      
{'loss': 1.7924, 'learning_rate': 9.918466898954704e-07, 'epoch': 7.95}

  1%|▏         | 720/57600 [07:35<10:23:31,  1.52it/s]
  1%|▏         | 721/57600 [07:35<10:13:18,  1.55it/s]
  1%|▏         | 722/57600 [07:36<10:17:07,  1.54it/s]
  1%|▏         | 723/57600 [07:37<10:00:07,  1.58it/s]
  1%|▏         | 724/57600 [07:37<9:58:17,  1.58it/s] 
  1%|▏         | 725/57600 [07:38<10:32:28,  1.50it/s]
  1%|▏         | 726/57600 [07:38<10:13:09,  1.55it/s]
  1%|▏         | 727/57600 [07:39<10:20:27,  1.53it/s]
  1%|▏         | 728/57600 [07:40<10:15:59,  1.54it/s]
  1%|▏         | 729/57600 [07:40<10:16:35,  1.54it/s]
  1%|▏         | 730/57600 [07:41<10:00:10,  1.58it/s]
  1%|▏         | 731/57600 [07:42<10:00:40,  1.58it/s]
  1%|▏         | 732/57600 [07:42<10:10:58,  1.55it/s]
  1%|▏         | 733/57600 [07:43<10:13:24,  1.55it/s]
  1%|▏         | 734/57600 [07:44<9:51:37,  1.60it/s] 
  1%|▏         | 735/57600 [07:44<9:55:08,  1.59it/s]
  1%|▏         | 736/57600 [07:45<9:51:03,  1.60it/s]
  1%|▏         | 737/57600 [07:45<9:41:37,  1.63it/s]
  1%|▏         | 738/57600 [07:46<10:04:02,  1.57it/s]
  1%|▏         | 739/57600 [07:47<10:24:55,  1.52it/s]
  1%|▏         | 740/57600 [07:47<9:56:30,  1.59it/s] 
                                                     
{'loss': 1.8275, 'learning_rate': 9.915331010452962e-07, 'epoch': 8.17}

  1%|▏         | 740/57600 [07:47<9:56:30,  1.59it/s]
  1%|▏         | 741/57600 [07:48<9:56:32,  1.59it/s]
  1%|▏         | 742/57600 [07:49<9:41:29,  1.63it/s]
  1%|▏         | 743/57600 [07:49<9:48:20,  1.61it/s]
  1%|▏         | 744/57600 [07:50<9:34:46,  1.65it/s]
  1%|▏         | 745/57600 [07:50<9:52:51,  1.60it/s]
  1%|▏         | 746/57600 [07:51<10:06:35,  1.56it/s]
  1%|▏         | 747/57600 [07:52<9:39:18,  1.64it/s] 
  1%|▏         | 748/57600 [07:52<9:43:34,  1.62it/s]
  1%|▏         | 749/57600 [07:53<9:32:15,  1.66it/s]
  1%|▏         | 750/57600 [07:53<9:31:26,  1.66it/s]
  1%|▏         | 751/57600 [07:54<9:35:59,  1.64it/s]
  1%|▏         | 752/57600 [07:55<10:07:19,  1.56it/s]
  1%|▏         | 753/57600 [07:55<10:05:30,  1.56it/s]
  1%|▏         | 754/57600 [07:56<9:51:48,  1.60it/s] 
  1%|▏         | 755/57600 [07:57<9:48:29,  1.61it/s]
  1%|▏         | 756/57600 [07:57<10:09:23,  1.55it/s]
  1%|▏         | 757/57600 [07:58<10:00:58,  1.58it/s]
  1%|▏         | 758/57600 [07:59<10:06:40,  1.56it/s]
  1%|▏         | 759/57600 [07:59<10:21:17,  1.52it/s]
  1%|▏         | 760/57600 [08:00<10:10:34,  1.55it/s]
                                                      
{'loss': 1.8033, 'learning_rate': 9.912195121951219e-07, 'epoch': 8.39}

  1%|▏         | 760/57600 [08:00<10:10:34,  1.55it/s]
  1%|▏         | 761/57600 [08:01<9:57:09,  1.59it/s] 
  1%|▏         | 762/57600 [08:01<10:10:34,  1.55it/s]
  1%|▏         | 763/57600 [08:02<10:30:35,  1.50it/s]
  1%|▏         | 764/57600 [08:03<10:17:14,  1.53it/s]
  1%|▏         | 765/57600 [08:03<10:06:08,  1.56it/s]
  1%|▏         | 766/57600 [08:04<10:22:20,  1.52it/s]
  1%|▏         | 767/57600 [08:05<10:25:11,  1.52it/s]
  1%|▏         | 768/57600 [08:05<10:09:07,  1.56it/s]
  1%|▏         | 769/57600 [08:06<9:57:07,  1.59it/s] 
  1%|▏         | 770/57600 [08:06<10:11:59,  1.55it/s]
  1%|▏         | 771/57600 [08:07<10:00:38,  1.58it/s]
  1%|▏         | 772/57600 [08:08<9:59:11,  1.58it/s] 
  1%|▏         | 773/57600 [08:08<9:49:17,  1.61it/s]
  1%|▏         | 774/57600 [08:09<9:58:34,  1.58it/s]
  1%|▏         | 775/57600 [08:09<9:43:08,  1.62it/s]
  1%|▏         | 776/57600 [08:10<9:32:32,  1.65it/s]
  1%|▏         | 777/57600 [08:11<9:41:10,  1.63it/s]
  1%|▏         | 778/57600 [08:11<9:54:57,  1.59it/s]
  1%|▏         | 779/57600 [08:12<10:04:21,  1.57it/s]
  1%|▏         | 780/57600 [08:13<9:53:16,  1.60it/s] 
                                                     
{'loss': 1.8283, 'learning_rate': 9.909059233449477e-07, 'epoch': 8.61}

  1%|▏         | 780/57600 [08:13<9:53:16,  1.60it/s]
  1%|▏         | 781/57600 [08:13<9:52:08,  1.60it/s]
  1%|▏         | 782/57600 [08:14<9:46:51,  1.61it/s]
  1%|▏         | 783/57600 [08:14<9:52:21,  1.60it/s]
  1%|▏         | 784/57600 [08:15<9:59:49,  1.58it/s]
  1%|▏         | 785/57600 [08:16<9:50:53,  1.60it/s]
  1%|▏         | 786/57600 [08:16<9:40:15,  1.63it/s]
  1%|▏         | 787/57600 [08:17<9:46:01,  1.62it/s]
  1%|▏         | 788/57600 [08:18<10:12:15,  1.55it/s]
  1%|▏         | 789/57600 [08:18<10:22:10,  1.52it/s]
  1%|▏         | 790/57600 [08:19<10:01:57,  1.57it/s]
  1%|▏         | 791/57600 [08:20<10:23:15,  1.52it/s]
  1%|▏         | 792/57600 [08:20<10:03:59,  1.57it/s]
  1%|▏         | 793/57600 [08:21<9:47:12,  1.61it/s] 
  1%|▏         | 794/57600 [08:21<9:39:23,  1.63it/s]
  1%|▏         | 795/57600 [08:22<9:29:52,  1.66it/s]
  1%|▏         | 796/57600 [08:23<9:45:18,  1.62it/s]
  1%|▏         | 797/57600 [08:23<9:34:34,  1.65it/s]
  1%|▏         | 798/57600 [08:24<9:59:53,  1.58it/s]
  1%|▏         | 799/57600 [08:25<9:50:52,  1.60it/s]
  1%|▏         | 800/57600 [08:25<9:46:28,  1.61it/s]
                                                     
{'loss': 1.8361, 'learning_rate': 9.905923344947734e-07, 'epoch': 8.83}

  1%|▏         | 800/57600 [08:25<9:46:28,  1.61it/s]
  1%|▏         | 801/57600 [08:26<9:47:10,  1.61it/s]
  1%|▏         | 802/57600 [08:26<10:08:33,  1.56it/s]
  1%|▏         | 803/57600 [08:27<10:06:14,  1.56it/s]
  1%|▏         | 804/57600 [08:28<10:04:38,  1.57it/s]
  1%|▏         | 805/57600 [08:28<9:53:02,  1.60it/s] 
  1%|▏         | 806/57600 [08:29<9:43:10,  1.62it/s]
  1%|▏         | 807/57600 [08:30<9:37:09,  1.64it/s]
  1%|▏         | 808/57600 [08:30<9:40:27,  1.63it/s]
  1%|▏         | 809/57600 [08:31<9:36:43,  1.64it/s]
  1%|▏         | 810/57600 [08:31<9:51:59,  1.60it/s]
  1%|▏         | 811/57600 [08:32<10:16:44,  1.53it/s]
  1%|▏         | 812/57600 [08:33<10:04:15,  1.57it/s]
  1%|▏         | 813/57600 [08:33<10:11:37,  1.55it/s]
  1%|▏         | 814/57600 [08:34<10:13:49,  1.54it/s]
  1%|▏         | 815/57600 [08:35<10:12:47,  1.54it/s]
  1%|▏         | 816/57600 [08:35<10:24:01,  1.52it/s]
  1%|▏         | 817/57600 [08:36<10:15:44,  1.54it/s]
  1%|▏         | 818/57600 [08:37<10:06:10,  1.56it/s]
  1%|▏         | 819/57600 [08:37<10:03:28,  1.57it/s]
  1%|▏         | 820/57600 [08:38<9:54:42,  1.59it/s] 
                                                     
{'loss': 1.8264, 'learning_rate': 9.902787456445992e-07, 'epoch': 9.05}

  1%|▏         | 820/57600 [08:38<9:54:42,  1.59it/s]
  1%|▏         | 821/57600 [08:38<9:52:35,  1.60it/s]
  1%|▏         | 822/57600 [08:39<9:56:20,  1.59it/s]
  1%|▏         | 823/57600 [08:40<9:46:21,  1.61it/s]
  1%|▏         | 824/57600 [08:40<10:33:32,  1.49it/s]
  1%|▏         | 825/57600 [08:41<10:26:54,  1.51it/s]
  1%|▏         | 826/57600 [08:42<10:18:15,  1.53it/s]
  1%|▏         | 827/57600 [08:42<9:55:39,  1.59it/s] 
  1%|▏         | 828/57600 [08:43<9:43:10,  1.62it/s]
  1%|▏         | 829/57600 [08:44<10:02:50,  1.57it/s]
  1%|▏         | 830/57600 [08:44<9:51:43,  1.60it/s] 
  1%|▏         | 831/57600 [08:45<9:41:08,  1.63it/s]
  1%|▏         | 832/57600 [08:45<9:50:36,  1.60it/s]
  1%|▏         | 833/57600 [08:46<9:48:03,  1.61it/s]
  1%|▏         | 834/57600 [08:47<9:39:50,  1.63it/s]
  1%|▏         | 835/57600 [08:47<10:02:43,  1.57it/s]
  1%|▏         | 836/57600 [08:48<10:10:22,  1.55it/s]
  1%|▏         | 837/57600 [08:49<9:50:35,  1.60it/s] 
  1%|▏         | 838/57600 [08:49<9:40:44,  1.63it/s]
  1%|▏         | 839/57600 [08:50<9:47:38,  1.61it/s]
  1%|▏         | 840/57600 [08:50<9:43:03,  1.62it/s]
                                                     
{'loss': 1.8157, 'learning_rate': 9.89965156794425e-07, 'epoch': 9.27}

  1%|▏         | 840/57600 [08:50<9:43:03,  1.62it/s]
  1%|▏         | 841/57600 [08:51<9:54:35,  1.59it/s]
  1%|▏         | 842/57600 [08:52<9:55:47,  1.59it/s]
  1%|▏         | 843/57600 [08:52<9:48:19,  1.61it/s]
  1%|▏         | 844/57600 [08:53<9:58:26,  1.58it/s]
  1%|▏         | 845/57600 [08:54<10:13:57,  1.54it/s]
  1%|▏         | 846/57600 [08:54<10:10:54,  1.55it/s]
  1%|▏         | 847/57600 [08:55<10:16:35,  1.53it/s]
  1%|▏         | 848/57600 [08:56<9:59:26,  1.58it/s] 
  1%|▏         | 849/57600 [08:56<10:10:19,  1.55it/s]
  1%|▏         | 850/57600 [08:57<9:52:38,  1.60it/s] 
  1%|▏         | 851/57600 [08:57<9:52:43,  1.60it/s]
  1%|▏         | 852/57600 [08:58<10:02:48,  1.57it/s]
  1%|▏         | 853/57600 [08:59<10:02:29,  1.57it/s]
  1%|▏         | 854/57600 [08:59<10:16:21,  1.53it/s]
  1%|▏         | 855/57600 [09:00<9:56:47,  1.58it/s] 
  1%|▏         | 856/57600 [09:01<9:48:50,  1.61it/s]
  1%|▏         | 857/57600 [09:01<9:42:11,  1.62it/s]
  1%|▏         | 858/57600 [09:02<9:28:02,  1.66it/s]
  1%|▏         | 859/57600 [09:02<9:32:51,  1.65it/s]
  1%|▏         | 860/57600 [09:03<10:08:39,  1.55it/s]
                                                      
{'loss': 1.8038, 'learning_rate': 9.89651567944251e-07, 'epoch': 9.49}

  1%|▏         | 860/57600 [09:03<10:08:39,  1.55it/s]
  1%|▏         | 861/57600 [09:04<10:31:50,  1.50it/s]
  1%|▏         | 862/57600 [09:04<10:26:41,  1.51it/s]
  1%|▏         | 863/57600 [09:05<10:18:27,  1.53it/s]
  2%|▏         | 864/57600 [09:06<10:14:59,  1.54it/s]
  2%|▏         | 865/57600 [09:06<9:56:33,  1.59it/s] 
  2%|▏         | 866/57600 [09:07<9:44:25,  1.62it/s]
  2%|▏         | 867/57600 [09:08<9:37:56,  1.64it/s]
  2%|▏         | 868/57600 [09:08<9:23:53,  1.68it/s]
  2%|▏         | 869/57600 [09:09<9:41:17,  1.63it/s]
  2%|▏         | 870/57600 [09:09<10:06:24,  1.56it/s]
  2%|▏         | 871/57600 [09:10<9:54:35,  1.59it/s] 
  2%|▏         | 872/57600 [09:11<10:09:17,  1.55it/s]
  2%|▏         | 873/57600 [09:11<10:07:59,  1.56it/s]
  2%|▏         | 874/57600 [09:12<10:17:34,  1.53it/s]
  2%|▏         | 875/57600 [09:13<10:24:48,  1.51it/s]
  2%|▏         | 876/57600 [09:13<10:03:00,  1.57it/s]
  2%|▏         | 877/57600 [09:14<9:45:30,  1.61it/s] 
  2%|▏         | 878/57600 [09:15<9:47:36,  1.61it/s]
  2%|▏         | 879/57600 [09:15<9:38:07,  1.64it/s]
  2%|▏         | 880/57600 [09:16<9:33:48,  1.65it/s]
                                                     
{'loss': 1.8495, 'learning_rate': 9.893379790940768e-07, 'epoch': 9.71}

  2%|▏         | 880/57600 [09:16<9:33:48,  1.65it/s]
  2%|▏         | 881/57600 [09:16<9:41:59,  1.62it/s]
  2%|▏         | 882/57600 [09:17<9:29:14,  1.66it/s]
  2%|▏         | 883/57600 [09:17<9:21:48,  1.68it/s]
  2%|▏         | 884/57600 [09:18<9:34:06,  1.65it/s]
  2%|▏         | 885/57600 [09:19<9:51:54,  1.60it/s]
  2%|▏         | 886/57600 [09:19<9:45:03,  1.62it/s]
  2%|▏         | 887/57600 [09:20<9:37:07,  1.64it/s]
  2%|▏         | 888/57600 [09:21<9:35:12,  1.64it/s]
  2%|▏         | 889/57600 [09:21<9:25:40,  1.67it/s]
  2%|▏         | 890/57600 [09:22<9:44:51,  1.62it/s]
  2%|▏         | 891/57600 [09:22<9:53:01,  1.59it/s]
  2%|▏         | 892/57600 [09:23<10:04:21,  1.56it/s]
  2%|▏         | 893/57600 [09:24<10:23:08,  1.52it/s]
  2%|▏         | 894/57600 [09:25<10:31:56,  1.50it/s]
  2%|▏         | 895/57600 [09:25<10:28:01,  1.50it/s]
  2%|▏         | 896/57600 [09:26<10:25:10,  1.51it/s]
  2%|▏         | 897/57600 [09:27<10:23:39,  1.52it/s]
  2%|▏         | 898/57600 [09:27<10:22:35,  1.52it/s]
  2%|▏         | 899/57600 [09:28<10:07:19,  1.56it/s]
  2%|▏         | 900/57600 [09:28<10:04:26,  1.56it/s]
                                                      
{'loss': 1.8379, 'learning_rate': 9.890243902439024e-07, 'epoch': 9.93}

  2%|▏         | 900/57600 [09:28<10:04:26,  1.56it/s]
  2%|▏         | 901/57600 [09:29<9:59:56,  1.58it/s] 
  2%|▏         | 902/57600 [09:30<9:47:50,  1.61it/s]
  2%|▏         | 903/57600 [09:30<10:09:58,  1.55it/s]
  2%|▏         | 904/57600 [09:31<9:53:47,  1.59it/s] 
  2%|▏         | 905/57600 [09:31<9:33:18,  1.65it/s]
  2%|▏         | 906/57600 [09:32<9:40:16,  1.63it/s]
  2%|▏         | 907/57600 [09:33<9:57:48,  1.58it/s]
  2%|▏         | 908/57600 [09:33<9:55:27,  1.59it/s]
  2%|▏         | 909/57600 [09:34<9:47:33,  1.61it/s]
  2%|▏         | 910/57600 [09:35<9:36:55,  1.64it/s]
  2%|▏         | 911/57600 [09:35<9:30:48,  1.66it/s]
  2%|▏         | 912/57600 [09:36<9:45:35,  1.61it/s]
  2%|▏         | 913/57600 [09:36<9:58:29,  1.58it/s]
  2%|▏         | 914/57600 [09:37<9:51:32,  1.60it/s]
  2%|▏         | 915/57600 [09:38<10:06:08,  1.56it/s]
  2%|▏         | 916/57600 [09:38<10:11:07,  1.55it/s]
  2%|▏         | 917/57600 [09:39<10:18:19,  1.53it/s]
  2%|▏         | 918/57600 [09:40<9:55:57,  1.59it/s] 
  2%|▏         | 919/57600 [09:40<9:38:53,  1.63it/s]
  2%|▏         | 920/57600 [09:41<10:01:53,  1.57it/s]
                                                      
{'loss': 1.807, 'learning_rate': 9.88710801393728e-07, 'epoch': 10.15}

  2%|▏         | 920/57600 [09:41<10:01:53,  1.57it/s]
  2%|▏         | 921/57600 [09:42<10:08:05,  1.55it/s]
  2%|▏         | 922/57600 [09:42<9:53:56,  1.59it/s] 
  2%|▏         | 923/57600 [09:43<9:45:29,  1.61it/s]
  2%|▏         | 924/57600 [09:44<10:09:28,  1.55it/s]
  2%|▏         | 925/57600 [09:44<9:53:33,  1.59it/s] 
  2%|▏         | 926/57600 [09:45<9:40:41,  1.63it/s]
  2%|▏         | 927/57600 [09:45<10:24:01,  1.51it/s]
  2%|▏         | 928/57600 [09:46<10:34:23,  1.49it/s]
  2%|▏         | 929/57600 [09:47<10:32:19,  1.49it/s]
  2%|▏         | 930/57600 [09:47<10:18:44,  1.53it/s]
  2%|▏         | 931/57600 [09:48<10:07:23,  1.55it/s]
  2%|▏         | 932/57600 [09:49<9:54:44,  1.59it/s] 
  2%|▏         | 933/57600 [09:49<9:39:21,  1.63it/s]
  2%|▏         | 934/57600 [09:50<9:54:00,  1.59it/s]
  2%|▏         | 935/57600 [09:50<9:36:29,  1.64it/s]
  2%|▏         | 936/57600 [09:51<9:36:12,  1.64it/s]
  2%|▏         | 937/57600 [09:52<9:33:41,  1.65it/s]
  2%|▏         | 938/57600 [09:52<9:54:04,  1.59it/s]
  2%|▏         | 939/57600 [09:53<9:56:10,  1.58it/s]
  2%|▏         | 940/57600 [09:54<10:15:55,  1.53it/s]
                                                      
{'loss': 1.7354, 'learning_rate': 9.88397212543554e-07, 'epoch': 10.38}

  2%|▏         | 940/57600 [09:54<10:15:55,  1.53it/s]
  2%|▏         | 941/57600 [09:54<10:09:41,  1.55it/s]
  2%|▏         | 942/57600 [09:55<10:15:16,  1.53it/s]
  2%|▏         | 943/57600 [09:56<10:04:47,  1.56it/s]
  2%|▏         | 944/57600 [09:56<10:07:38,  1.55it/s]
  2%|▏         | 945/57600 [09:57<10:07:40,  1.55it/s]
  2%|▏         | 946/57600 [09:57<9:49:43,  1.60it/s] 
  2%|▏         | 947/57600 [09:58<9:51:47,  1.60it/s]
  2%|▏         | 948/57600 [09:59<9:52:13,  1.59it/s]
  2%|▏         | 949/57600 [09:59<9:44:19,  1.62it/s]
  2%|▏         | 950/57600 [10:00<9:46:42,  1.61it/s]
  2%|▏         | 951/57600 [10:01<9:33:15,  1.65it/s]
  2%|▏         | 952/57600 [10:01<9:38:58,  1.63it/s]
  2%|▏         | 953/57600 [10:02<9:32:08,  1.65it/s]
  2%|▏         | 954/57600 [10:02<9:24:55,  1.67it/s]
  2%|▏         | 955/57600 [10:03<9:25:30,  1.67it/s]
  2%|▏         | 956/57600 [10:04<9:44:50,  1.61it/s]
  2%|▏         | 957/57600 [10:04<9:46:30,  1.61it/s]
  2%|▏         | 958/57600 [10:05<10:10:03,  1.55it/s]
  2%|▏         | 959/57600 [10:06<10:08:12,  1.55it/s]
  2%|▏         | 960/57600 [10:06<9:58:02,  1.58it/s] 
                                                     
{'loss': 1.7909, 'learning_rate': 9.880836236933798e-07, 'epoch': 10.6}

  2%|▏         | 960/57600 [10:06<9:58:02,  1.58it/s]
  2%|▏         | 961/57600 [10:07<9:59:02,  1.58it/s]
  2%|▏         | 962/57600 [10:07<10:09:15,  1.55it/s]
  2%|▏         | 963/57600 [10:08<9:56:28,  1.58it/s] 
  2%|▏         | 964/57600 [10:09<9:57:04,  1.58it/s]
  2%|▏         | 965/57600 [10:09<10:04:47,  1.56it/s]
  2%|▏         | 966/57600 [10:10<10:20:54,  1.52it/s]
  2%|▏         | 967/57600 [10:11<10:18:48,  1.53it/s]
  2%|▏         | 968/57600 [10:11<10:04:19,  1.56it/s]
  2%|▏         | 969/57600 [10:12<9:53:09,  1.59it/s] 
  2%|▏         | 970/57600 [10:13<10:06:43,  1.56it/s]
  2%|▏         | 971/57600 [10:13<10:13:47,  1.54it/s]
  2%|▏         | 972/57600 [10:14<9:56:19,  1.58it/s] 
  2%|▏         | 973/57600 [10:15<9:58:32,  1.58it/s]
  2%|▏         | 974/57600 [10:15<9:46:58,  1.61it/s]
  2%|▏         | 975/57600 [10:16<9:53:59,  1.59it/s]
  2%|▏         | 976/57600 [10:16<9:50:43,  1.60it/s]
  2%|▏         | 977/57600 [10:17<9:51:07,  1.60it/s]
  2%|▏         | 978/57600 [10:18<9:42:17,  1.62it/s]
  2%|▏         | 979/57600 [10:18<9:45:50,  1.61it/s]
  2%|▏         | 980/57600 [10:19<9:57:38,  1.58it/s]
                                                     
{'loss': 1.8504, 'learning_rate': 9.877700348432054e-07, 'epoch': 10.82}

  2%|▏         | 980/57600 [10:19<9:57:38,  1.58it/s]
  2%|▏         | 981/57600 [10:19<9:44:16,  1.62it/s]
  2%|▏         | 982/57600 [10:20<9:43:36,  1.62it/s]
  2%|▏         | 983/57600 [10:21<9:49:49,  1.60it/s]
  2%|▏         | 984/57600 [10:21<10:12:34,  1.54it/s]
  2%|▏         | 985/57600 [10:22<9:57:38,  1.58it/s] 
  2%|▏         | 986/57600 [10:23<9:56:44,  1.58it/s]
  2%|▏         | 987/57600 [10:23<10:03:45,  1.56it/s]
  2%|▏         | 988/57600 [10:24<10:30:06,  1.50it/s]
  2%|▏         | 989/57600 [10:25<10:22:19,  1.52it/s]
  2%|▏         | 990/57600 [10:25<10:08:57,  1.55it/s]
  2%|▏         | 991/57600 [10:26<10:01:31,  1.57it/s]
  2%|▏         | 992/57600 [10:27<9:48:45,  1.60it/s] 
  2%|▏         | 993/57600 [10:27<9:46:51,  1.61it/s]
  2%|▏         | 994/57600 [10:28<9:53:35,  1.59it/s]
  2%|▏         | 995/57600 [10:28<9:52:13,  1.59it/s]
  2%|▏         | 996/57600 [10:29<9:41:22,  1.62it/s]
  2%|▏         | 997/57600 [10:30<10:22:29,  1.52it/s]
  2%|▏         | 998/57600 [10:30<10:26:44,  1.51it/s]
  2%|▏         | 999/57600 [10:31<10:25:56,  1.51it/s]
  2%|▏         | 1000/57600 [10:32<10:12:04,  1.54it/s]
                                                       
{'loss': 1.7565, 'learning_rate': 9.874564459930313e-07, 'epoch': 11.04}

  2%|▏         | 1000/57600 [10:32<10:12:04,  1.54it/s]
  2%|▏         | 1001/57600 [10:32<9:52:29,  1.59it/s] 
  2%|▏         | 1002/57600 [10:33<9:32:07,  1.65it/s]
  2%|▏         | 1003/57600 [10:33<9:36:49,  1.64it/s]
  2%|▏         | 1004/57600 [10:34<9:30:57,  1.65it/s]
  2%|▏         | 1005/57600 [10:35<9:33:09,  1.65it/s]
  2%|▏         | 1006/57600 [10:35<9:46:37,  1.61it/s]
  2%|▏         | 1007/57600 [10:36<9:41:20,  1.62it/s]
  2%|▏         | 1008/57600 [10:37<10:01:29,  1.57it/s]
  2%|▏         | 1009/57600 [10:37<9:38:57,  1.63it/s] 
  2%|▏         | 1010/57600 [10:38<10:16:03,  1.53it/s]
  2%|▏         | 1011/57600 [10:38<9:55:30,  1.58it/s] 
  2%|▏         | 1012/57600 [10:39<10:02:53,  1.56it/s]
  2%|▏         | 1013/57600 [10:40<9:54:29,  1.59it/s] 
  2%|▏         | 1014/57600 [10:40<10:12:57,  1.54it/s]
  2%|▏         | 1015/57600 [10:41<10:04:11,  1.56it/s]
  2%|▏         | 1016/57600 [10:42<9:47:57,  1.60it/s] 
  2%|▏         | 1017/57600 [10:42<9:52:39,  1.59it/s]
  2%|▏         | 1018/57600 [10:43<9:29:05,  1.66it/s]
  2%|▏         | 1019/57600 [10:43<9:40:17,  1.63it/s]
  2%|▏         | 1020/57600 [10:44<9:40:24,  1.62it/s]
                                                      
{'loss': 1.8464, 'learning_rate': 9.871428571428572e-07, 'epoch': 11.26}

  2%|▏         | 1020/57600 [10:44<9:40:24,  1.62it/s]
  2%|▏         | 1021/57600 [10:45<9:49:39,  1.60it/s]
  2%|▏         | 1022/57600 [10:45<9:47:37,  1.60it/s]
  2%|▏         | 1023/57600 [10:46<9:49:37,  1.60it/s]
  2%|▏         | 1024/57600 [10:47<10:22:32,  1.51it/s]
  2%|▏         | 1025/57600 [10:47<10:21:51,  1.52it/s]
  2%|▏         | 1026/57600 [10:48<10:29:13,  1.50it/s]
  2%|▏         | 1027/57600 [10:49<10:29:58,  1.50it/s]
  2%|▏         | 1028/57600 [10:49<10:18:56,  1.52it/s]
  2%|▏         | 1029/57600 [10:50<10:17:55,  1.53it/s]
  2%|▏         | 1030/57600 [10:51<10:00:11,  1.57it/s]
  2%|▏         | 1031/57600 [10:51<9:56:18,  1.58it/s] 
  2%|▏         | 1032/57600 [10:52<9:57:41,  1.58it/s]
  2%|▏         | 1033/57600 [10:53<10:23:52,  1.51it/s]
  2%|▏         | 1034/57600 [10:53<10:28:36,  1.50it/s]
  2%|▏         | 1035/57600 [10:54<10:17:03,  1.53it/s]
  2%|▏         | 1036/57600 [10:55<10:00:55,  1.57it/s]
  2%|▏         | 1037/57600 [10:55<9:59:52,  1.57it/s] 
  2%|▏         | 1038/57600 [10:56<9:56:45,  1.58it/s]
  2%|▏         | 1039/57600 [10:56<9:46:25,  1.61it/s]
  2%|▏         | 1040/57600 [10:57<9:45:34,  1.61it/s]
                                                      
{'loss': 1.7463, 'learning_rate': 9.868292682926828e-07, 'epoch': 11.48}

  2%|▏         | 1040/57600 [10:57<9:45:34,  1.61it/s]
  2%|▏         | 1041/57600 [10:58<9:38:44,  1.63it/s]
  2%|▏         | 1042/57600 [10:58<9:26:52,  1.66it/s]
  2%|▏         | 1043/57600 [10:59<9:28:03,  1.66it/s]
  2%|▏         | 1044/57600 [10:59<9:43:50,  1.61it/s]
  2%|▏         | 1045/57600 [11:00<9:43:25,  1.62it/s]
  2%|▏         | 1046/57600 [11:01<9:31:51,  1.65it/s]
  2%|▏         | 1047/57600 [11:01<9:39:20,  1.63it/s]
  2%|▏         | 1048/57600 [11:02<9:59:16,  1.57it/s]
  2%|▏         | 1049/57600 [11:03<9:47:47,  1.60it/s]
  2%|▏         | 1050/57600 [11:03<9:43:13,  1.62it/s]
  2%|▏         | 1051/57600 [11:04<10:00:55,  1.57it/s]
  2%|▏         | 1052/57600 [11:04<9:52:39,  1.59it/s] 
  2%|▏         | 1053/57600 [11:05<10:26:16,  1.50it/s]
  2%|▏         | 1054/57600 [11:06<10:41:37,  1.47it/s]
  2%|▏         | 1055/57600 [11:06<10:10:46,  1.54it/s]
  2%|▏         | 1056/57600 [11:07<10:01:20,  1.57it/s]
  2%|▏         | 1057/57600 [11:08<9:44:55,  1.61it/s] 
  2%|▏         | 1058/57600 [11:08<9:48:05,  1.60it/s]
  2%|▏         | 1059/57600 [11:09<10:01:57,  1.57it/s]
  2%|▏         | 1060/57600 [11:10<9:53:29,  1.59it/s] 
                                                      
{'loss': 1.8286, 'learning_rate': 9.865156794425087e-07, 'epoch': 11.7}

  2%|▏         | 1060/57600 [11:10<9:53:29,  1.59it/s]
  2%|▏         | 1061/57600 [11:10<9:55:38,  1.58it/s]
  2%|▏         | 1062/57600 [11:11<9:55:19,  1.58it/s]
  2%|▏         | 1063/57600 [11:11<9:43:29,  1.61it/s]
  2%|▏         | 1064/57600 [11:12<9:50:59,  1.59it/s]
  2%|▏         | 1065/57600 [11:13<9:33:54,  1.64it/s]
  2%|▏         | 1066/57600 [11:13<9:49:05,  1.60it/s]
  2%|▏         | 1067/57600 [11:14<9:34:33,  1.64it/s]
  2%|▏         | 1068/57600 [11:15<9:40:28,  1.62it/s]
  2%|▏         | 1069/57600 [11:15<9:27:59,  1.66it/s]
  2%|▏         | 1070/57600 [11:16<9:32:30,  1.65it/s]
  2%|▏         | 1071/57600 [11:16<10:01:43,  1.57it/s]
  2%|▏         | 1072/57600 [11:17<9:49:36,  1.60it/s] 
  2%|▏         | 1073/57600 [11:18<9:50:02,  1.60it/s]
  2%|▏         | 1074/57600 [11:18<9:46:32,  1.61it/s]
  2%|▏         | 1075/57600 [11:19<9:56:01,  1.58it/s]
  2%|▏         | 1076/57600 [11:19<9:41:24,  1.62it/s]
  2%|▏         | 1077/57600 [11:20<9:56:16,  1.58it/s]
  2%|▏         | 1078/57600 [11:21<9:57:52,  1.58it/s]
  2%|▏         | 1079/57600 [11:21<9:58:42,  1.57it/s]
  2%|▏         | 1080/57600 [11:22<9:52:38,  1.59it/s]
                                                      
{'loss': 1.7821, 'learning_rate': 9.862020905923345e-07, 'epoch': 11.92}

  2%|▏         | 1080/57600 [11:22<9:52:38,  1.59it/s]
  2%|▏         | 1081/57600 [11:23<9:49:55,  1.60it/s]
  2%|▏         | 1082/57600 [11:23<9:39:19,  1.63it/s]
  2%|▏         | 1083/57600 [11:24<9:58:12,  1.57it/s]
  2%|▏         | 1084/57600 [11:25<9:46:24,  1.61it/s]
  2%|▏         | 1085/57600 [11:25<9:32:13,  1.65it/s]
  2%|▏         | 1086/57600 [11:26<9:53:20,  1.59it/s]
  2%|▏         | 1087/57600 [11:26<9:41:31,  1.62it/s]
  2%|▏         | 1088/57600 [11:27<9:52:24,  1.59it/s]
  2%|▏         | 1089/57600 [11:28<9:37:25,  1.63it/s]
  2%|▏         | 1090/57600 [11:28<9:40:18,  1.62it/s]
  2%|▏         | 1091/57600 [11:29<9:44:43,  1.61it/s]
  2%|▏         | 1092/57600 [11:29<9:45:58,  1.61it/s]
  2%|▏         | 1093/57600 [11:30<9:45:22,  1.61it/s]
  2%|▏         | 1094/57600 [11:31<10:24:17,  1.51it/s]
  2%|▏         | 1095/57600 [11:31<10:02:05,  1.56it/s]
  2%|▏         | 1096/57600 [11:32<9:52:42,  1.59it/s] 
  2%|▏         | 1097/57600 [11:33<9:56:34,  1.58it/s]
  2%|▏         | 1098/57600 [11:33<10:06:08,  1.55it/s]
  2%|▏         | 1099/57600 [11:34<10:19:47,  1.52it/s]
  2%|▏         | 1100/57600 [11:35<10:09:06,  1.55it/s]
                                                       
{'loss': 1.8069, 'learning_rate': 9.858885017421604e-07, 'epoch': 12.14}

  2%|▏         | 1100/57600 [11:35<10:09:06,  1.55it/s]
  2%|▏         | 1101/57600 [11:35<10:04:12,  1.56it/s]
  2%|▏         | 1102/57600 [11:36<10:20:13,  1.52it/s]
  2%|▏         | 1103/57600 [11:37<10:06:45,  1.55it/s]
  2%|▏         | 1104/57600 [11:37<9:49:33,  1.60it/s] 
  2%|▏         | 1105/57600 [11:38<9:38:07,  1.63it/s]
  2%|▏         | 1106/57600 [11:38<9:56:27,  1.58it/s]
  2%|▏         | 1107/57600 [11:39<10:22:34,  1.51it/s]
  2%|▏         | 1108/57600 [11:40<10:13:32,  1.53it/s]
  2%|▏         | 1109/57600 [11:40<10:10:33,  1.54it/s]
  2%|▏         | 1110/57600 [11:41<10:10:39,  1.54it/s]
  2%|▏         | 1111/57600 [11:42<10:18:20,  1.52it/s]
  2%|▏         | 1112/57600 [11:42<10:13:15,  1.54it/s]
  2%|▏         | 1113/57600 [11:43<10:02:58,  1.56it/s]
  2%|▏         | 1114/57600 [11:44<10:02:03,  1.56it/s]
  2%|▏         | 1115/57600 [11:44<9:58:27,  1.57it/s] 
  2%|▏         | 1116/57600 [11:45<9:59:53,  1.57it/s]
  2%|▏         | 1117/57600 [11:46<9:58:08,  1.57it/s]
  2%|▏         | 1118/57600 [11:46<10:07:58,  1.55it/s]
  2%|▏         | 1119/57600 [11:47<9:51:08,  1.59it/s] 
  2%|▏         | 1120/57600 [11:47<9:59:11,  1.57it/s]
                                                      
{'loss': 1.7943, 'learning_rate': 9.85574912891986e-07, 'epoch': 12.36}

  2%|▏         | 1120/57600 [11:47<9:59:11,  1.57it/s]
  2%|▏         | 1121/57600 [11:48<9:50:51,  1.59it/s]
  2%|▏         | 1122/57600 [11:49<9:58:04,  1.57it/s]
  2%|▏         | 1123/57600 [11:49<9:50:10,  1.59it/s]
  2%|▏         | 1124/57600 [11:50<9:46:50,  1.60it/s]
  2%|▏         | 1125/57600 [11:51<9:43:44,  1.61it/s]
  2%|▏         | 1126/57600 [11:51<9:49:23,  1.60it/s]
  2%|▏         | 1127/57600 [11:52<10:01:06,  1.57it/s]
  2%|▏         | 1128/57600 [11:52<9:50:21,  1.59it/s] 
  2%|▏         | 1129/57600 [11:53<10:11:28,  1.54it/s]
  2%|▏         | 1130/57600 [11:54<10:01:05,  1.57it/s]
  2%|▏         | 1131/57600 [11:54<9:52:29,  1.59it/s] 
  2%|▏         | 1132/57600 [11:55<10:27:28,  1.50it/s]
  2%|▏         | 1133/57600 [11:56<10:13:46,  1.53it/s]
  2%|▏         | 1134/57600 [11:56<9:43:42,  1.61it/s] 
  2%|▏         | 1135/57600 [11:57<9:42:01,  1.62it/s]
  2%|▏         | 1136/57600 [11:58<9:30:11,  1.65it/s]
  2%|▏         | 1137/57600 [11:58<9:49:07,  1.60it/s]
  2%|▏         | 1138/57600 [11:59<9:49:30,  1.60it/s]
  2%|▏         | 1139/57600 [11:59<9:50:01,  1.59it/s]
  2%|▏         | 1140/57600 [12:00<9:49:58,  1.59it/s]
                                                      
{'loss': 1.7535, 'learning_rate': 9.852613240418117e-07, 'epoch': 12.58}

  2%|▏         | 1140/57600 [12:00<9:49:58,  1.59it/s]
  2%|▏         | 1141/57600 [12:01<10:00:08,  1.57it/s]
  2%|▏         | 1142/57600 [12:01<10:19:40,  1.52it/s]
  2%|▏         | 1143/57600 [12:02<10:05:44,  1.55it/s]
  2%|▏         | 1144/57600 [12:03<10:16:45,  1.53it/s]
  2%|▏         | 1145/57600 [12:03<10:09:37,  1.54it/s]
  2%|▏         | 1146/57600 [12:04<10:21:11,  1.51it/s]
  2%|▏         | 1147/57600 [12:05<9:58:37,  1.57it/s] 
  2%|▏         | 1148/57600 [12:05<10:15:53,  1.53it/s]
  2%|▏         | 1149/57600 [12:06<10:09:12,  1.54it/s]
  2%|▏         | 1150/57600 [12:07<10:14:05,  1.53it/s]
  2%|▏         | 1151/57600 [12:07<9:58:51,  1.57it/s] 
  2%|▏         | 1152/57600 [12:08<9:53:00,  1.59it/s]
  2%|▏         | 1153/57600 [12:08<9:44:36,  1.61it/s]
  2%|▏         | 1154/57600 [12:09<9:37:05,  1.63it/s]
  2%|▏         | 1155/57600 [12:10<10:01:59,  1.56it/s]
  2%|▏         | 1156/57600 [12:10<9:54:28,  1.58it/s] 
  2%|▏         | 1157/57600 [12:11<9:44:57,  1.61it/s]
  2%|▏         | 1158/57600 [12:12<9:32:16,  1.64it/s]
  2%|▏         | 1159/57600 [12:12<9:23:28,  1.67it/s]
  2%|▏         | 1160/57600 [12:13<9:28:18,  1.66it/s]
                                                      
{'loss': 1.7881, 'learning_rate': 9.849477351916375e-07, 'epoch': 12.8}

  2%|▏         | 1160/57600 [12:13<9:28:18,  1.66it/s]
  2%|▏         | 1161/57600 [12:13<9:32:50,  1.64it/s]
  2%|▏         | 1162/57600 [12:14<9:39:27,  1.62it/s]
  2%|▏         | 1163/57600 [12:15<9:46:56,  1.60it/s]
  2%|▏         | 1164/57600 [12:15<9:51:54,  1.59it/s]
  2%|▏         | 1165/57600 [12:16<9:44:44,  1.61it/s]
  2%|▏         | 1166/57600 [12:17<9:57:13,  1.57it/s]
  2%|▏         | 1167/57600 [12:17<10:00:16,  1.57it/s]
  2%|▏         | 1168/57600 [12:18<9:57:29,  1.57it/s] 
  2%|▏         | 1169/57600 [12:18<9:53:06,  1.59it/s]
  2%|▏         | 1170/57600 [12:19<9:35:15,  1.63it/s]
  2%|▏         | 1171/57600 [12:20<9:56:07,  1.58it/s]
  2%|▏         | 1172/57600 [12:20<9:55:13,  1.58it/s]
  2%|▏         | 1173/57600 [12:21<9:53:38,  1.58it/s]
  2%|▏         | 1174/57600 [12:22<9:44:32,  1.61it/s]
  2%|▏         | 1175/57600 [12:22<9:42:30,  1.61it/s]
  2%|▏         | 1176/57600 [12:23<10:04:17,  1.56it/s]
  2%|▏         | 1177/57600 [12:23<9:55:38,  1.58it/s] 
  2%|▏         | 1178/57600 [12:24<10:11:38,  1.54it/s]
  2%|▏         | 1179/57600 [12:25<10:04:27,  1.56it/s]
  2%|▏         | 1180/57600 [12:26<10:32:23,  1.49it/s]
                                                       
{'loss': 1.815, 'learning_rate': 9.846341463414634e-07, 'epoch': 13.02}

  2%|▏         | 1180/57600 [12:26<10:32:23,  1.49it/s]
  2%|▏         | 1181/57600 [12:26<10:19:30,  1.52it/s]
  2%|▏         | 1182/57600 [12:27<10:09:18,  1.54it/s]
  2%|▏         | 1183/57600 [12:27<10:07:44,  1.55it/s]
  2%|▏         | 1184/57600 [12:28<9:52:36,  1.59it/s] 
  2%|▏         | 1185/57600 [12:29<9:40:31,  1.62it/s]
  2%|▏         | 1186/57600 [12:29<9:31:39,  1.64it/s]
  2%|▏         | 1187/57600 [12:30<10:00:13,  1.57it/s]
  2%|▏         | 1188/57600 [12:31<9:55:39,  1.58it/s] 
  2%|▏         | 1189/57600 [12:31<9:48:59,  1.60it/s]
  2%|▏         | 1190/57600 [12:32<9:51:55,  1.59it/s]
  2%|▏         | 1191/57600 [12:32<10:14:43,  1.53it/s]
  2%|▏         | 1192/57600 [12:33<9:59:32,  1.57it/s] 
  2%|▏         | 1193/57600 [12:34<9:49:51,  1.59it/s]
  2%|▏         | 1194/57600 [12:34<9:46:53,  1.60it/s]
  2%|▏         | 1195/57600 [12:35<9:42:53,  1.61it/s]
  2%|▏         | 1196/57600 [12:36<9:41:50,  1.62it/s]
  2%|▏         | 1197/57600 [12:36<9:35:48,  1.63it/s]
  2%|▏         | 1198/57600 [12:37<9:24:06,  1.67it/s]
  2%|▏         | 1199/57600 [12:37<9:26:23,  1.66it/s]
  2%|▏         | 1200/57600 [12:38<9:13:21,  1.70it/s]
                                                      
{'loss': 1.8258, 'learning_rate': 9.843205574912892e-07, 'epoch': 13.25}

  2%|▏         | 1200/57600 [12:38<9:13:21,  1.70it/s]
  2%|▏         | 1201/57600 [12:38<9:22:25,  1.67it/s]
  2%|▏         | 1202/57600 [12:39<9:41:50,  1.62it/s]
  2%|▏         | 1203/57600 [12:40<9:39:09,  1.62it/s]
  2%|▏         | 1204/57600 [12:40<9:46:19,  1.60it/s]
  2%|▏         | 1205/57600 [12:41<9:40:34,  1.62it/s]
  2%|▏         | 1206/57600 [12:42<9:39:15,  1.62it/s]
  2%|▏         | 1207/57600 [12:42<9:32:57,  1.64it/s]
  2%|▏         | 1208/57600 [12:43<9:39:56,  1.62it/s]
  2%|▏         | 1209/57600 [12:43<9:38:39,  1.62it/s]
  2%|▏         | 1210/57600 [12:44<9:39:03,  1.62it/s]
  2%|▏         | 1211/57600 [12:45<9:46:46,  1.60it/s]
  2%|▏         | 1212/57600 [12:45<10:09:32,  1.54it/s]
  2%|▏         | 1213/57600 [12:46<10:06:26,  1.55it/s]
  2%|▏         | 1214/57600 [12:47<9:49:22,  1.59it/s] 
  2%|▏         | 1215/57600 [12:47<10:01:01,  1.56it/s]
  2%|▏         | 1216/57600 [12:48<9:58:52,  1.57it/s] 
  2%|▏         | 1217/57600 [12:49<10:13:11,  1.53it/s]
  2%|▏         | 1218/57600 [12:49<9:58:33,  1.57it/s] 
  2%|▏         | 1219/57600 [12:50<10:23:31,  1.51it/s]
  2%|▏         | 1220/57600 [12:51<10:31:26,  1.49it/s]
                                                       
{'loss': 1.7228, 'learning_rate': 9.840069686411149e-07, 'epoch': 13.47}

  2%|▏         | 1220/57600 [12:51<10:31:26,  1.49it/s]
  2%|▏         | 1221/57600 [12:51<10:13:48,  1.53it/s]
  2%|▏         | 1222/57600 [12:52<10:04:14,  1.56it/s]
  2%|▏         | 1223/57600 [12:53<10:10:39,  1.54it/s]
  2%|▏         | 1224/57600 [12:53<10:03:33,  1.56it/s]
  2%|▏         | 1225/57600 [12:54<9:56:58,  1.57it/s] 
  2%|▏         | 1226/57600 [12:54<9:42:09,  1.61it/s]
  2%|▏         | 1227/57600 [12:55<9:31:28,  1.64it/s]
  2%|▏         | 1228/57600 [12:56<9:30:11,  1.65it/s]
  2%|▏         | 1229/57600 [12:56<9:31:25,  1.64it/s]
  2%|▏         | 1230/57600 [12:57<9:43:50,  1.61it/s]
  2%|▏         | 1231/57600 [12:57<9:42:30,  1.61it/s]
  2%|▏         | 1232/57600 [12:58<9:48:16,  1.60it/s]
  2%|▏         | 1233/57600 [12:59<9:42:29,  1.61it/s]
  2%|▏         | 1234/57600 [12:59<9:56:23,  1.58it/s]
  2%|▏         | 1235/57600 [13:00<9:51:09,  1.59it/s]
  2%|▏         | 1236/57600 [13:01<9:46:30,  1.60it/s]
  2%|▏         | 1237/57600 [13:01<9:49:17,  1.59it/s]
  2%|▏         | 1238/57600 [13:02<9:52:12,  1.59it/s]
  2%|▏         | 1239/57600 [13:02<9:33:40,  1.64it/s]
  2%|▏         | 1240/57600 [13:03<9:32:40,  1.64it/s]
                                                      
{'loss': 1.7866, 'learning_rate': 9.836933797909407e-07, 'epoch': 13.69}

  2%|▏         | 1240/57600 [13:03<9:32:40,  1.64it/s]
  2%|▏         | 1241/57600 [13:04<9:30:04,  1.65it/s]
  2%|▏         | 1242/57600 [13:04<9:32:18,  1.64it/s]
  2%|▏         | 1243/57600 [13:05<9:52:08,  1.59it/s]
  2%|▏         | 1244/57600 [13:06<9:53:42,  1.58it/s]
  2%|▏         | 1245/57600 [13:06<10:03:33,  1.56it/s]
  2%|▏         | 1246/57600 [13:07<9:39:17,  1.62it/s] 
  2%|▏         | 1247/57600 [13:07<9:47:50,  1.60it/s]
  2%|▏         | 1248/57600 [13:08<9:38:08,  1.62it/s]
  2%|▏         | 1249/57600 [13:09<9:22:25,  1.67it/s]
  2%|▏         | 1250/57600 [13:09<9:20:26,  1.68it/s]
  2%|▏         | 1251/57600 [13:10<9:50:23,  1.59it/s]
  2%|▏         | 1252/57600 [13:11<10:04:40,  1.55it/s]
  2%|▏         | 1253/57600 [13:11<9:51:03,  1.59it/s] 
  2%|▏         | 1254/57600 [13:12<10:04:38,  1.55it/s]
  2%|▏         | 1255/57600 [13:12<9:42:45,  1.61it/s] 
  2%|▏         | 1256/57600 [13:13<9:53:54,  1.58it/s]
  2%|▏         | 1257/57600 [13:14<9:55:52,  1.58it/s]
  2%|▏         | 1258/57600 [13:14<9:47:21,  1.60it/s]
  2%|▏         | 1259/57600 [13:15<9:45:42,  1.60it/s]
  2%|▏         | 1260/57600 [13:16<10:09:46,  1.54it/s]
                                                       
{'loss': 1.7871, 'learning_rate': 9.833797909407664e-07, 'epoch': 13.91}

  2%|▏         | 1260/57600 [13:16<10:09:46,  1.54it/s]
  2%|▏         | 1261/57600 [13:16<10:23:28,  1.51it/s]
  2%|▏         | 1262/57600 [13:17<10:19:56,  1.51it/s]
  2%|▏         | 1263/57600 [13:18<10:07:14,  1.55it/s]
  2%|▏         | 1264/57600 [13:18<10:18:35,  1.52it/s]
  2%|▏         | 1265/57600 [13:19<9:59:59,  1.56it/s] 
  2%|▏         | 1266/57600 [13:19<9:45:51,  1.60it/s]
  2%|▏         | 1267/57600 [13:20<10:01:44,  1.56it/s]
  2%|▏         | 1268/57600 [13:21<10:10:22,  1.54it/s]
  2%|▏         | 1269/57600 [13:22<10:36:54,  1.47it/s]
  2%|▏         | 1270/57600 [13:22<10:20:39,  1.51it/s]
  2%|▏         | 1271/57600 [13:23<10:15:46,  1.52it/s]
  2%|▏         | 1272/57600 [13:23<10:19:48,  1.51it/s]
  2%|▏         | 1273/57600 [13:24<10:05:25,  1.55it/s]
  2%|▏         | 1274/57600 [13:25<10:14:48,  1.53it/s]
  2%|▏         | 1275/57600 [13:25<9:59:05,  1.57it/s] 
  2%|▏         | 1276/57600 [13:26<10:03:14,  1.56it/s]
  2%|▏         | 1277/57600 [13:27<10:02:23,  1.56it/s]
  2%|▏         | 1278/57600 [13:27<10:29:20,  1.49it/s]
  2%|▏         | 1279/57600 [13:28<10:29:38,  1.49it/s]
  2%|▏         | 1280/57600 [13:29<10:20:08,  1.51it/s]
                                                       
{'loss': 1.7238, 'learning_rate': 9.830662020905923e-07, 'epoch': 14.13}

  2%|▏         | 1280/57600 [13:29<10:20:08,  1.51it/s]
  2%|▏         | 1281/57600 [13:29<10:07:37,  1.54it/s]
  2%|▏         | 1282/57600 [13:30<10:15:14,  1.53it/s]
  2%|▏         | 1283/57600 [13:31<9:53:22,  1.58it/s] 
  2%|▏         | 1284/57600 [13:31<9:56:03,  1.57it/s]
  2%|▏         | 1285/57600 [13:32<9:40:54,  1.62it/s]
  2%|▏         | 1286/57600 [13:32<9:31:21,  1.64it/s]
  2%|▏         | 1287/57600 [13:33<9:33:36,  1.64it/s]
  2%|▏         | 1288/57600 [13:34<9:47:24,  1.60it/s]
  2%|▏         | 1289/57600 [13:34<9:37:42,  1.62it/s]
  2%|▏         | 1290/57600 [13:35<9:39:41,  1.62it/s]
  2%|▏         | 1291/57600 [13:35<9:39:53,  1.62it/s]
  2%|▏         | 1292/57600 [13:36<9:52:54,  1.58it/s]
  2%|▏         | 1293/57600 [13:37<9:40:31,  1.62it/s]
  2%|▏         | 1294/57600 [13:37<9:43:30,  1.61it/s]
  2%|▏         | 1295/57600 [13:38<9:51:09,  1.59it/s]
  2%|▏         | 1296/57600 [13:39<9:50:11,  1.59it/s]
  2%|▏         | 1297/57600 [13:39<9:42:36,  1.61it/s]
  2%|▏         | 1298/57600 [13:40<9:28:00,  1.65it/s]
  2%|▏         | 1299/57600 [13:41<9:52:31,  1.58it/s]
  2%|▏         | 1300/57600 [13:41<9:43:16,  1.61it/s]
                                                      
{'loss': 1.805, 'learning_rate': 9.827526132404181e-07, 'epoch': 14.35}

  2%|▏         | 1300/57600 [13:41<9:43:16,  1.61it/s]
  2%|▏         | 1301/57600 [13:42<10:11:59,  1.53it/s]
  2%|▏         | 1302/57600 [13:42<10:11:45,  1.53it/s]
  2%|▏         | 1303/57600 [13:43<9:59:53,  1.56it/s] 
  2%|▏         | 1304/57600 [13:44<10:12:56,  1.53it/s]
  2%|▏         | 1305/57600 [13:44<10:16:50,  1.52it/s]
  2%|▏         | 1306/57600 [13:45<10:19:41,  1.51it/s]
  2%|▏         | 1307/57600 [13:46<10:16:45,  1.52it/s]
  2%|▏         | 1308/57600 [13:46<9:54:29,  1.58it/s] 
  2%|▏         | 1309/57600 [13:47<9:50:34,  1.59it/s]
  2%|▏         | 1310/57600 [13:48<10:05:32,  1.55it/s]
  2%|▏         | 1311/57600 [13:48<10:05:33,  1.55it/s]
  2%|▏         | 1312/57600 [13:49<10:10:02,  1.54it/s]
  2%|▏         | 1313/57600 [13:50<10:06:31,  1.55it/s]
  2%|▏         | 1314/57600 [13:50<9:59:32,  1.56it/s] 
  2%|▏         | 1315/57600 [13:51<10:02:42,  1.56it/s]
  2%|▏         | 1316/57600 [13:52<10:18:21,  1.52it/s]
  2%|▏         | 1317/57600 [13:52<9:56:52,  1.57it/s] 
  2%|▏         | 1318/57600 [13:53<9:54:45,  1.58it/s]
  2%|▏         | 1319/57600 [13:53<9:52:16,  1.58it/s]
  2%|▏         | 1320/57600 [13:54<9:34:41,  1.63it/s]
                                                      
{'loss': 1.7909, 'learning_rate': 9.82439024390244e-07, 'epoch': 14.57}

  2%|▏         | 1320/57600 [13:54<9:34:41,  1.63it/s]
  2%|▏         | 1321/57600 [13:55<9:36:54,  1.63it/s]
  2%|▏         | 1322/57600 [13:55<9:59:46,  1.56it/s]
  2%|▏         | 1323/57600 [13:56<10:02:53,  1.56it/s]
  2%|▏         | 1324/57600 [13:57<9:52:11,  1.58it/s] 
  2%|▏         | 1325/57600 [13:57<9:34:33,  1.63it/s]
  2%|▏         | 1326/57600 [13:58<9:31:40,  1.64it/s]
  2%|▏         | 1327/57600 [13:58<9:22:59,  1.67it/s]
  2%|▏         | 1328/57600 [13:59<9:38:55,  1.62it/s]
  2%|▏         | 1329/57600 [14:00<9:48:24,  1.59it/s]
  2%|▏         | 1330/57600 [14:00<9:42:50,  1.61it/s]
  2%|▏         | 1331/57600 [14:01<9:38:41,  1.62it/s]
  2%|▏         | 1332/57600 [14:01<9:32:01,  1.64it/s]
  2%|▏         | 1333/57600 [14:02<9:29:54,  1.65it/s]
  2%|▏         | 1334/57600 [14:03<9:37:00,  1.63it/s]
  2%|▏         | 1335/57600 [14:03<9:24:29,  1.66it/s]
  2%|▏         | 1336/57600 [14:04<9:30:13,  1.64it/s]
  2%|▏         | 1337/57600 [14:04<9:43:09,  1.61it/s]
  2%|▏         | 1338/57600 [14:05<9:50:45,  1.59it/s]
  2%|▏         | 1339/57600 [14:06<9:49:01,  1.59it/s]
  2%|▏         | 1340/57600 [14:06<10:13:59,  1.53it/s]
                                                       
{'loss': 1.7861, 'learning_rate': 9.821254355400698e-07, 'epoch': 14.79}

  2%|▏         | 1340/57600 [14:06<10:13:59,  1.53it/s]
  2%|▏         | 1341/57600 [14:07<10:11:33,  1.53it/s]
  2%|▏         | 1342/57600 [14:08<9:44:30,  1.60it/s] 
  2%|▏         | 1343/57600 [14:08<9:29:46,  1.65it/s]
  2%|▏         | 1344/57600 [14:09<9:24:28,  1.66it/s]
  2%|▏         | 1345/57600 [14:10<9:49:11,  1.59it/s]
  2%|▏         | 1346/57600 [14:10<10:21:09,  1.51it/s]
  2%|▏         | 1347/57600 [14:11<10:10:21,  1.54it/s]
  2%|▏         | 1348/57600 [14:11<9:48:16,  1.59it/s] 
  2%|▏         | 1349/57600 [14:12<9:48:49,  1.59it/s]
  2%|▏         | 1350/57600 [14:13<9:35:45,  1.63it/s]
  2%|▏         | 1351/57600 [14:13<9:50:25,  1.59it/s]
  2%|▏         | 1352/57600 [14:14<9:38:32,  1.62it/s]
  2%|▏         | 1353/57600 [14:15<9:40:45,  1.61it/s]
  2%|▏         | 1354/57600 [14:15<9:56:32,  1.57it/s]
  2%|▏         | 1355/57600 [14:16<9:52:01,  1.58it/s]
  2%|▏         | 1356/57600 [14:16<9:38:39,  1.62it/s]
  2%|▏         | 1357/57600 [14:17<9:51:52,  1.58it/s]
  2%|▏         | 1358/57600 [14:18<9:41:21,  1.61it/s]
  2%|▏         | 1359/57600 [14:18<9:52:33,  1.58it/s]
  2%|▏         | 1360/57600 [14:19<10:31:38,  1.48it/s]
                                                       
{'loss': 1.7651, 'learning_rate': 9.818118466898953e-07, 'epoch': 15.01}

  2%|▏         | 1360/57600 [14:19<10:31:38,  1.48it/s]
  2%|▏         | 1361/57600 [14:20<10:26:41,  1.50it/s]
  2%|▏         | 1362/57600 [14:20<10:14:12,  1.53it/s]
  2%|▏         | 1363/57600 [14:21<10:23:14,  1.50it/s]
  2%|▏         | 1364/57600 [14:22<10:12:52,  1.53it/s]
  2%|▏         | 1365/57600 [14:22<10:14:29,  1.53it/s]
  2%|▏         | 1366/57600 [14:23<10:41:31,  1.46it/s]
  2%|▏         | 1367/57600 [14:24<10:25:43,  1.50it/s]
  2%|▏         | 1368/57600 [14:24<10:30:25,  1.49it/s]
  2%|▏         | 1369/57600 [14:25<10:15:56,  1.52it/s]
  2%|▏         | 1370/57600 [14:26<10:08:12,  1.54it/s]
  2%|▏         | 1371/57600 [14:26<10:12:21,  1.53it/s]
  2%|▏         | 1372/57600 [14:27<9:52:36,  1.58it/s] 
  2%|▏         | 1373/57600 [14:28<9:40:24,  1.61it/s]
  2%|▏         | 1374/57600 [14:28<9:47:07,  1.60it/s]
  2%|▏         | 1375/57600 [14:29<9:32:55,  1.64it/s]
  2%|▏         | 1376/57600 [14:29<9:48:45,  1.59it/s]
  2%|▏         | 1377/57600 [14:30<9:39:56,  1.62it/s]
  2%|▏         | 1378/57600 [14:31<9:36:39,  1.62it/s]
  2%|▏         | 1379/57600 [14:31<9:37:49,  1.62it/s]
  2%|▏         | 1380/57600 [14:32<9:28:32,  1.65it/s]
                                                      
{'loss': 1.7666, 'learning_rate': 9.814982578397211e-07, 'epoch': 15.23}

  2%|▏         | 1380/57600 [14:32<9:28:32,  1.65it/s]
  2%|▏         | 1381/57600 [14:33<9:58:40,  1.57it/s]
  2%|▏         | 1382/57600 [14:33<10:04:10,  1.55it/s]
  2%|▏         | 1383/57600 [14:34<10:09:35,  1.54it/s]
  2%|▏         | 1384/57600 [14:35<10:21:43,  1.51it/s]
  2%|▏         | 1385/57600 [14:35<10:33:54,  1.48it/s]
  2%|▏         | 1386/57600 [14:36<10:03:07,  1.55it/s]
  2%|▏         | 1387/57600 [14:36<9:38:56,  1.62it/s] 
  2%|▏         | 1388/57600 [14:37<9:44:51,  1.60it/s]
  2%|▏         | 1389/57600 [14:38<9:32:46,  1.64it/s]
  2%|▏         | 1390/57600 [14:38<9:14:35,  1.69it/s]
  2%|▏         | 1391/57600 [14:39<9:16:22,  1.68it/s]
  2%|▏         | 1392/57600 [14:39<9:10:09,  1.70it/s]
  2%|▏         | 1393/57600 [14:40<9:46:02,  1.60it/s]
  2%|▏         | 1394/57600 [14:41<9:37:17,  1.62it/s]
  2%|▏         | 1395/57600 [14:41<9:41:45,  1.61it/s]
  2%|▏         | 1396/57600 [14:42<10:09:42,  1.54it/s]
  2%|▏         | 1397/57600 [14:43<10:07:51,  1.54it/s]
  2%|▏         | 1398/57600 [14:43<9:50:41,  1.59it/s] 
  2%|▏         | 1399/57600 [14:44<10:15:20,  1.52it/s]
  2%|▏         | 1400/57600 [14:45<10:11:41,  1.53it/s]
                                                       
{'loss': 1.7159, 'learning_rate': 9.81184668989547e-07, 'epoch': 15.45}

  2%|▏         | 1400/57600 [14:45<10:11:41,  1.53it/s]
  2%|▏         | 1401/57600 [14:45<9:58:38,  1.56it/s] 
  2%|▏         | 1402/57600 [14:46<10:08:01,  1.54it/s]
  2%|▏         | 1403/57600 [14:46<10:00:04,  1.56it/s]
  2%|▏         | 1404/57600 [14:47<9:53:04,  1.58it/s] 
  2%|▏         | 1405/57600 [14:48<9:51:47,  1.58it/s]
  2%|▏         | 1406/57600 [14:48<9:41:48,  1.61it/s]
  2%|▏         | 1407/57600 [14:49<9:25:13,  1.66it/s]
  2%|▏         | 1408/57600 [14:49<9:18:01,  1.68it/s]
  2%|▏         | 1409/57600 [14:50<9:16:49,  1.68it/s]
  2%|▏         | 1410/57600 [14:51<9:45:09,  1.60it/s]
  2%|▏         | 1411/57600 [14:51<9:56:16,  1.57it/s]
  2%|▏         | 1412/57600 [14:52<9:43:47,  1.60it/s]
  2%|▏         | 1413/57600 [14:53<9:47:15,  1.59it/s]
  2%|▏         | 1414/57600 [14:53<9:31:37,  1.64it/s]
  2%|▏         | 1415/57600 [14:54<9:39:11,  1.62it/s]
  2%|▏         | 1416/57600 [14:55<9:49:35,  1.59it/s]
  2%|▏         | 1417/57600 [14:55<10:00:57,  1.56it/s]
  2%|▏         | 1418/57600 [14:56<9:53:31,  1.58it/s] 
  2%|▏         | 1419/57600 [14:56<9:42:07,  1.61it/s]
  2%|▏         | 1420/57600 [14:57<9:36:02,  1.63it/s]
                                                      
{'loss': 1.7701, 'learning_rate': 9.808710801393728e-07, 'epoch': 15.67}

  2%|▏         | 1420/57600 [14:57<9:36:02,  1.63it/s]
  2%|▏         | 1421/57600 [14:58<9:33:20,  1.63it/s]
  2%|▏         | 1422/57600 [14:58<9:33:59,  1.63it/s]
  2%|▏         | 1423/57600 [14:59<9:22:36,  1.66it/s]
  2%|▏         | 1424/57600 [14:59<9:33:06,  1.63it/s]
  2%|▏         | 1425/57600 [15:00<9:28:36,  1.65it/s]
  2%|▏         | 1426/57600 [15:01<9:39:19,  1.62it/s]
  2%|▏         | 1427/57600 [15:01<9:32:30,  1.64it/s]
  2%|▏         | 1428/57600 [15:02<9:44:24,  1.60it/s]
  2%|▏         | 1429/57600 [15:03<9:52:06,  1.58it/s]
  2%|▏         | 1430/57600 [15:03<9:46:32,  1.60it/s]
  2%|▏         | 1431/57600 [15:04<9:36:05,  1.63it/s]
  2%|▏         | 1432/57600 [15:04<9:35:07,  1.63it/s]
  2%|▏         | 1433/57600 [15:05<9:53:20,  1.58it/s]
  2%|▏         | 1434/57600 [15:06<9:51:29,  1.58it/s]
  2%|▏         | 1435/57600 [15:06<10:02:16,  1.55it/s]
  2%|▏         | 1436/57600 [15:07<9:59:43,  1.56it/s] 
  2%|▏         | 1437/57600 [15:08<9:51:28,  1.58it/s]
  2%|▏         | 1438/57600 [15:08<9:40:33,  1.61it/s]
  2%|▏         | 1439/57600 [15:09<9:30:39,  1.64it/s]
  2%|▎         | 1440/57600 [15:09<9:38:58,  1.62it/s]
                                                      
{'loss': 1.7977, 'learning_rate': 9.805574912891987e-07, 'epoch': 15.89}

  2%|▎         | 1440/57600 [15:09<9:38:58,  1.62it/s]
  3%|▎         | 1441/57600 [15:10<9:36:44,  1.62it/s]
  3%|▎         | 1442/57600 [15:11<9:29:40,  1.64it/s]
  3%|▎         | 1443/57600 [15:11<9:34:51,  1.63it/s]
  3%|▎         | 1444/57600 [15:12<10:13:27,  1.53it/s]
  3%|▎         | 1445/57600 [15:13<10:19:42,  1.51it/s]
  3%|▎         | 1446/57600 [15:13<10:06:24,  1.54it/s]
  3%|▎         | 1447/57600 [15:14<9:45:13,  1.60it/s] 
  3%|▎         | 1448/57600 [15:14<9:39:49,  1.61it/s]
  3%|▎         | 1449/57600 [15:15<9:33:04,  1.63it/s]
  3%|▎         | 1450/57600 [15:16<10:16:08,  1.52it/s]
  3%|▎         | 1451/57600 [15:16<9:56:22,  1.57it/s] 
  3%|▎         | 1452/57600 [15:17<10:02:40,  1.55it/s]
  3%|▎         | 1453/57600 [15:18<9:57:28,  1.57it/s] 
  3%|▎         | 1454/57600 [15:18<9:51:17,  1.58it/s]
  3%|▎         | 1455/57600 [15:19<9:42:39,  1.61it/s]
  3%|▎         | 1456/57600 [15:20<9:41:10,  1.61it/s]
  3%|▎         | 1457/57600 [15:20<9:44:19,  1.60it/s]
  3%|▎         | 1458/57600 [15:21<9:28:03,  1.65it/s]
  3%|▎         | 1459/57600 [15:21<9:45:03,  1.60it/s]
  3%|▎         | 1460/57600 [15:22<9:45:04,  1.60it/s]
                                                      
{'loss': 1.7805, 'learning_rate': 9.802439024390243e-07, 'epoch': 16.11}

  3%|▎         | 1460/57600 [15:22<9:45:04,  1.60it/s]
  3%|▎         | 1461/57600 [15:23<9:57:03,  1.57it/s]
  3%|▎         | 1462/57600 [15:23<9:41:14,  1.61it/s]
  3%|▎         | 1463/57600 [15:24<9:23:56,  1.66it/s]
  3%|▎         | 1464/57600 [15:24<9:27:35,  1.65it/s]
  3%|▎         | 1465/57600 [15:25<9:18:24,  1.68it/s]
  3%|▎         | 1466/57600 [15:26<9:25:12,  1.66it/s]
  3%|▎         | 1467/57600 [15:26<9:36:05,  1.62it/s]
  3%|▎         | 1468/57600 [15:27<9:34:50,  1.63it/s]
  3%|▎         | 1469/57600 [15:27<9:26:46,  1.65it/s]
  3%|▎         | 1470/57600 [15:28<9:31:27,  1.64it/s]
  3%|▎         | 1471/57600 [15:29<9:22:10,  1.66it/s]
  3%|▎         | 1472/57600 [15:29<9:30:30,  1.64it/s]
  3%|▎         | 1473/57600 [15:30<9:17:44,  1.68it/s]
  3%|▎         | 1474/57600 [15:30<9:19:41,  1.67it/s]
  3%|▎         | 1475/57600 [15:31<9:25:01,  1.66it/s]
  3%|▎         | 1476/57600 [15:32<9:32:11,  1.63it/s]
  3%|▎         | 1477/57600 [15:32<9:24:10,  1.66it/s]
  3%|▎         | 1478/57600 [15:33<9:31:28,  1.64it/s]
  3%|▎         | 1479/57600 [15:34<9:30:20,  1.64it/s]
  3%|▎         | 1480/57600 [15:34<9:27:41,  1.65it/s]
                                                      
{'loss': 1.7711, 'learning_rate': 9.799303135888502e-07, 'epoch': 16.34}

  3%|▎         | 1480/57600 [15:34<9:27:41,  1.65it/s]
  3%|▎         | 1481/57600 [15:35<9:33:03,  1.63it/s]
  3%|▎         | 1482/57600 [15:35<9:26:57,  1.65it/s]
  3%|▎         | 1483/57600 [15:36<9:36:22,  1.62it/s]
  3%|▎         | 1484/57600 [15:37<9:27:06,  1.65it/s]
  3%|▎         | 1485/57600 [15:37<9:41:18,  1.61it/s]
  3%|▎         | 1486/57600 [15:38<9:46:34,  1.59it/s]
  3%|▎         | 1487/57600 [15:39<10:07:17,  1.54it/s]
  3%|▎         | 1488/57600 [15:39<10:27:09,  1.49it/s]
  3%|▎         | 1489/57600 [15:40<10:08:57,  1.54it/s]
  3%|▎         | 1490/57600 [15:41<10:09:25,  1.53it/s]
  3%|▎         | 1491/57600 [15:41<10:13:45,  1.52it/s]
  3%|▎         | 1492/57600 [15:42<10:06:28,  1.54it/s]
  3%|▎         | 1493/57600 [15:43<10:04:43,  1.55it/s]
  3%|▎         | 1494/57600 [15:43<10:09:16,  1.53it/s]
  3%|▎         | 1495/57600 [15:44<10:01:34,  1.55it/s]
  3%|▎         | 1496/57600 [15:44<9:50:55,  1.58it/s] 
  3%|▎         | 1497/57600 [15:45<10:00:50,  1.56it/s]
  3%|▎         | 1498/57600 [15:46<9:49:42,  1.59it/s] 
  3%|▎         | 1499/57600 [15:46<10:03:40,  1.55it/s]
  3%|▎         | 1500/57600 [15:47<10:08:54,  1.54it/s]
                                                       
{'loss': 1.6767, 'learning_rate': 9.796167247386758e-07, 'epoch': 16.56}

  3%|▎         | 1500/57600 [15:47<10:08:54,  1.54it/s]
  3%|▎         | 1501/57600 [15:48<9:58:30,  1.56it/s] 
  3%|▎         | 1502/57600 [15:48<9:49:15,  1.59it/s]
  3%|▎         | 1503/57600 [15:49<9:29:55,  1.64it/s]
  3%|▎         | 1504/57600 [15:50<9:59:28,  1.56it/s]
  3%|▎         | 1505/57600 [15:50<9:51:53,  1.58it/s]
  3%|▎         | 1506/57600 [15:51<9:44:18,  1.60it/s]
  3%|▎         | 1507/57600 [15:51<9:36:30,  1.62it/s]
  3%|▎         | 1508/57600 [15:52<9:40:45,  1.61it/s]
  3%|▎         | 1509/57600 [15:53<9:59:23,  1.56it/s]
  3%|▎         | 1510/57600 [15:53<10:01:38,  1.55it/s]
  3%|▎         | 1511/57600 [15:54<9:53:03,  1.58it/s] 
  3%|▎         | 1512/57600 [15:55<9:51:45,  1.58it/s]
  3%|▎         | 1513/57600 [15:55<10:01:15,  1.55it/s]
  3%|▎         | 1514/57600 [15:56<9:40:07,  1.61it/s] 
  3%|▎         | 1515/57600 [15:56<9:40:47,  1.61it/s]
  3%|▎         | 1516/57600 [15:57<9:46:09,  1.59it/s]
  3%|▎         | 1517/57600 [15:58<9:57:57,  1.56it/s]
  3%|▎         | 1518/57600 [15:58<9:40:52,  1.61it/s]
  3%|▎         | 1519/57600 [15:59<9:40:57,  1.61it/s]
  3%|▎         | 1520/57600 [16:00<9:57:55,  1.56it/s]
                                                      
{'loss': 1.722, 'learning_rate': 9.793031358885017e-07, 'epoch': 16.78}

  3%|▎         | 1520/57600 [16:00<9:57:55,  1.56it/s]
  3%|▎         | 1521/57600 [16:00<9:50:30,  1.58it/s]
  3%|▎         | 1522/57600 [16:01<9:30:40,  1.64it/s]
  3%|▎         | 1523/57600 [16:01<9:28:15,  1.64it/s]
  3%|▎         | 1524/57600 [16:02<9:10:53,  1.70it/s]
  3%|▎         | 1525/57600 [16:03<9:25:12,  1.65it/s]
  3%|▎         | 1526/57600 [16:03<9:12:27,  1.69it/s]
  3%|▎         | 1527/57600 [16:04<9:16:48,  1.68it/s]
  3%|▎         | 1528/57600 [16:04<9:10:49,  1.70it/s]
  3%|▎         | 1529/57600 [16:05<9:23:14,  1.66it/s]
  3%|▎         | 1530/57600 [16:06<9:31:12,  1.64it/s]
  3%|▎         | 1531/57600 [16:06<9:32:25,  1.63it/s]
  3%|▎         | 1532/57600 [16:07<9:40:46,  1.61it/s]
  3%|▎         | 1533/57600 [16:07<9:30:23,  1.64it/s]
  3%|▎         | 1534/57600 [16:08<9:47:18,  1.59it/s]
  3%|▎         | 1535/57600 [16:09<9:41:06,  1.61it/s]
  3%|▎         | 1536/57600 [16:09<9:43:39,  1.60it/s]
  3%|▎         | 1537/57600 [16:10<9:55:33,  1.57it/s]
  3%|▎         | 1538/57600 [16:11<9:38:24,  1.62it/s]
  3%|▎         | 1539/57600 [16:11<9:55:07,  1.57it/s]
  3%|▎         | 1540/57600 [16:12<9:53:03,  1.58it/s]
                                                      
{'loss': 1.783, 'learning_rate': 9.789895470383276e-07, 'epoch': 17.0}

  3%|▎         | 1540/57600 [16:12<9:53:03,  1.58it/s]
  3%|▎         | 1541/57600 [16:13<10:09:15,  1.53it/s]
  3%|▎         | 1542/57600 [16:13<10:04:11,  1.55it/s]
  3%|▎         | 1543/57600 [16:14<10:00:15,  1.56it/s]
  3%|▎         | 1544/57600 [16:14<9:55:34,  1.57it/s] 
  3%|▎         | 1545/57600 [16:15<9:52:59,  1.58it/s]
  3%|▎         | 1546/57600 [16:16<9:48:22,  1.59it/s]
  3%|▎         | 1547/57600 [16:16<9:50:14,  1.58it/s]
  3%|▎         | 1548/57600 [16:17<10:00:42,  1.56it/s]
  3%|▎         | 1549/57600 [16:18<9:48:01,  1.59it/s] 
  3%|▎         | 1550/57600 [16:18<9:43:21,  1.60it/s]
  3%|▎         | 1551/57600 [16:19<9:59:09,  1.56it/s]
  3%|▎         | 1552/57600 [16:20<9:59:23,  1.56it/s]
  3%|▎         | 1553/57600 [16:20<9:39:12,  1.61it/s]
  3%|▎         | 1554/57600 [16:21<9:25:35,  1.65it/s]
  3%|▎         | 1555/57600 [16:21<9:57:54,  1.56it/s]
  3%|▎         | 1556/57600 [16:22<9:51:13,  1.58it/s]
  3%|▎         | 1557/57600 [16:23<9:52:30,  1.58it/s]
  3%|▎         | 1558/57600 [16:23<9:48:53,  1.59it/s]
  3%|▎         | 1559/57600 [16:24<9:39:15,  1.61it/s]
  3%|▎         | 1560/57600 [16:24<9:26:14,  1.65it/s]
                                                      
{'loss': 1.7233, 'learning_rate': 9.786759581881534e-07, 'epoch': 17.22}

  3%|▎         | 1560/57600 [16:24<9:26:14,  1.65it/s]
  3%|▎         | 1561/57600 [16:25<9:29:56,  1.64it/s]
  3%|▎         | 1562/57600 [16:26<9:34:24,  1.63it/s]
  3%|▎         | 1563/57600 [16:26<9:45:34,  1.59it/s]
  3%|▎         | 1564/57600 [16:27<9:36:39,  1.62it/s]
  3%|▎         | 1565/57600 [16:28<9:37:46,  1.62it/s]
  3%|▎         | 1566/57600 [16:28<9:23:29,  1.66it/s]
  3%|▎         | 1567/57600 [16:29<9:30:29,  1.64it/s]
  3%|▎         | 1568/57600 [16:29<9:22:07,  1.66it/s]
  3%|▎         | 1569/57600 [16:30<9:34:08,  1.63it/s]
  3%|▎         | 1570/57600 [16:31<9:15:56,  1.68it/s]
  3%|▎         | 1571/57600 [16:31<9:39:41,  1.61it/s]
  3%|▎         | 1572/57600 [16:32<9:53:11,  1.57it/s]
  3%|▎         | 1573/57600 [16:32<9:40:02,  1.61it/s]
  3%|▎         | 1574/57600 [16:33<9:30:00,  1.64it/s]
  3%|▎         | 1575/57600 [16:34<9:41:56,  1.60it/s]
  3%|▎         | 1576/57600 [16:34<9:49:48,  1.58it/s]
  3%|▎         | 1577/57600 [16:35<9:56:35,  1.57it/s]
  3%|▎         | 1578/57600 [16:36<9:52:02,  1.58it/s]
  3%|▎         | 1579/57600 [16:36<9:49:51,  1.58it/s]
  3%|▎         | 1580/57600 [16:37<9:41:12,  1.61it/s]
                                                      
{'loss': 1.7209, 'learning_rate': 9.78362369337979e-07, 'epoch': 17.44}

  3%|▎         | 1580/57600 [16:37<9:41:12,  1.61it/s]
  3%|▎         | 1581/57600 [16:38<9:57:14,  1.56it/s]
  3%|▎         | 1582/57600 [16:38<9:44:15,  1.60it/s]
  3%|▎         | 1583/57600 [16:39<9:33:23,  1.63it/s]
  3%|▎         | 1584/57600 [16:39<9:33:03,  1.63it/s]
  3%|▎         | 1585/57600 [16:40<9:21:03,  1.66it/s]
  3%|▎         | 1586/57600 [16:41<9:35:45,  1.62it/s]
  3%|▎         | 1587/57600 [16:41<9:43:30,  1.60it/s]
  3%|▎         | 1588/57600 [16:42<9:55:48,  1.57it/s]
  3%|▎         | 1589/57600 [16:42<9:47:13,  1.59it/s]
  3%|▎         | 1590/57600 [16:43<10:04:21,  1.54it/s]
  3%|▎         | 1591/57600 [16:44<10:03:31,  1.55it/s]
  3%|▎         | 1592/57600 [16:44<9:52:43,  1.57it/s] 
  3%|▎         | 1593/57600 [16:45<10:02:44,  1.55it/s]
  3%|▎         | 1594/57600 [16:46<9:58:18,  1.56it/s] 
  3%|▎         | 1595/57600 [16:46<9:45:47,  1.59it/s]
  3%|▎         | 1596/57600 [16:47<9:34:30,  1.62it/s]
  3%|▎         | 1597/57600 [16:48<9:55:43,  1.57it/s]
  3%|▎         | 1598/57600 [16:48<10:01:35,  1.55it/s]
  3%|▎         | 1599/57600 [16:49<10:08:15,  1.53it/s]
  3%|▎         | 1600/57600 [16:50<10:09:30,  1.53it/s]
                                                       
{'loss': 1.6968, 'learning_rate': 9.780487804878047e-07, 'epoch': 17.66}

  3%|▎         | 1600/57600 [16:50<10:09:30,  1.53it/s]
  3%|▎         | 1601/57600 [16:50<10:36:20,  1.47it/s]
  3%|▎         | 1602/57600 [16:51<10:10:48,  1.53it/s]
  3%|▎         | 1603/57600 [16:52<10:22:14,  1.50it/s]
  3%|▎         | 1604/57600 [16:52<9:58:38,  1.56it/s] 
  3%|▎         | 1605/57600 [16:53<10:01:00,  1.55it/s]
  3%|▎         | 1606/57600 [16:53<9:54:39,  1.57it/s] 
  3%|▎         | 1607/57600 [16:54<9:59:47,  1.56it/s]
  3%|▎         | 1608/57600 [16:55<10:00:45,  1.55it/s]
  3%|▎         | 1609/57600 [16:55<9:37:46,  1.62it/s] 
  3%|▎         | 1610/57600 [16:56<10:06:41,  1.54it/s]
  3%|▎         | 1611/57600 [16:57<10:11:37,  1.53it/s]
  3%|▎         | 1612/57600 [16:57<9:57:36,  1.56it/s] 
  3%|▎         | 1613/57600 [16:58<9:55:16,  1.57it/s]
  3%|▎         | 1614/57600 [16:59<9:52:55,  1.57it/s]
  3%|▎         | 1615/57600 [16:59<9:45:13,  1.59it/s]
  3%|▎         | 1616/57600 [17:00<9:34:16,  1.62it/s]
  3%|▎         | 1617/57600 [17:00<9:50:24,  1.58it/s]
  3%|▎         | 1618/57600 [17:01<10:00:39,  1.55it/s]
  3%|▎         | 1619/57600 [17:02<9:39:35,  1.61it/s] 
  3%|▎         | 1620/57600 [17:02<10:01:55,  1.55it/s]
                                                       
{'loss': 1.6818, 'learning_rate': 9.777351916376306e-07, 'epoch': 17.88}

  3%|▎         | 1620/57600 [17:02<10:01:55,  1.55it/s]
  3%|▎         | 1621/57600 [17:03<9:58:24,  1.56it/s] 
  3%|▎         | 1622/57600 [17:04<9:45:59,  1.59it/s]
  3%|▎         | 1623/57600 [17:04<9:35:13,  1.62it/s]
  3%|▎         | 1624/57600 [17:05<9:18:13,  1.67it/s]
  3%|▎         | 1625/57600 [17:05<9:23:15,  1.66it/s]
  3%|▎         | 1626/57600 [17:06<9:23:02,  1.66it/s]
  3%|▎         | 1627/57600 [17:07<9:24:03,  1.65it/s]
  3%|▎         | 1628/57600 [17:07<9:12:22,  1.69it/s]
  3%|▎         | 1629/57600 [17:08<9:09:54,  1.70it/s]
  3%|▎         | 1630/57600 [17:08<9:17:18,  1.67it/s]
  3%|▎         | 1631/57600 [17:09<9:32:44,  1.63it/s]
  3%|▎         | 1632/57600 [17:10<9:15:38,  1.68it/s]
  3%|▎         | 1633/57600 [17:10<9:22:02,  1.66it/s]
  3%|▎         | 1634/57600 [17:11<9:22:25,  1.66it/s]
  3%|▎         | 1635/57600 [17:11<9:35:10,  1.62it/s]
  3%|▎         | 1636/57600 [17:12<9:30:14,  1.64it/s]
  3%|▎         | 1637/57600 [17:13<9:45:02,  1.59it/s]
  3%|▎         | 1638/57600 [17:13<9:47:28,  1.59it/s]
  3%|▎         | 1639/57600 [17:14<9:36:29,  1.62it/s]
  3%|▎         | 1640/57600 [17:15<9:40:43,  1.61it/s]
                                                      
{'loss': 1.7819, 'learning_rate': 9.774216027874564e-07, 'epoch': 18.1}

  3%|▎         | 1640/57600 [17:15<9:40:43,  1.61it/s]
  3%|▎         | 1641/57600 [17:15<9:53:33,  1.57it/s]
  3%|▎         | 1642/57600 [17:16<9:57:12,  1.56it/s]
  3%|▎         | 1643/57600 [17:16<9:41:31,  1.60it/s]
  3%|▎         | 1644/57600 [17:17<9:35:35,  1.62it/s]
  3%|▎         | 1645/57600 [17:18<9:44:19,  1.60it/s]
  3%|▎         | 1646/57600 [17:18<9:40:53,  1.61it/s]
  3%|▎         | 1647/57600 [17:19<9:33:09,  1.63it/s]
  3%|▎         | 1648/57600 [17:20<9:22:42,  1.66it/s]
  3%|▎         | 1649/57600 [17:20<9:56:23,  1.56it/s]
  3%|▎         | 1650/57600 [17:21<9:40:34,  1.61it/s]
  3%|▎         | 1651/57600 [17:21<9:33:45,  1.63it/s]
  3%|▎         | 1652/57600 [17:22<9:33:33,  1.63it/s]
  3%|▎         | 1653/57600 [17:23<9:37:58,  1.61it/s]
  3%|▎         | 1654/57600 [17:23<10:00:27,  1.55it/s]
  3%|▎         | 1655/57600 [17:24<9:34:37,  1.62it/s] 
  3%|▎         | 1656/57600 [17:25<9:32:21,  1.63it/s]
  3%|▎         | 1657/57600 [17:25<9:32:13,  1.63it/s]
  3%|▎         | 1658/57600 [17:26<9:34:15,  1.62it/s]
  3%|▎         | 1659/57600 [17:26<9:28:09,  1.64it/s]
  3%|▎         | 1660/57600 [17:27<9:46:06,  1.59it/s]
                                                      
{'loss': 1.7445, 'learning_rate': 9.771080139372823e-07, 'epoch': 18.32}

  3%|▎         | 1660/57600 [17:27<9:46:06,  1.59it/s]
  3%|▎         | 1661/57600 [17:28<9:44:28,  1.60it/s]
  3%|▎         | 1662/57600 [17:28<10:01:59,  1.55it/s]
  3%|▎         | 1663/57600 [17:29<9:51:37,  1.58it/s] 
  3%|▎         | 1664/57600 [17:30<9:38:20,  1.61it/s]
  3%|▎         | 1665/57600 [17:30<9:44:08,  1.60it/s]
  3%|▎         | 1666/57600 [17:31<9:31:10,  1.63it/s]
  3%|▎         | 1667/57600 [17:31<9:30:29,  1.63it/s]
  3%|▎         | 1668/57600 [17:32<9:38:50,  1.61it/s]
  3%|▎         | 1669/57600 [17:33<9:42:59,  1.60it/s]
  3%|▎         | 1670/57600 [17:33<9:39:05,  1.61it/s]
  3%|▎         | 1671/57600 [17:34<9:23:30,  1.65it/s]
  3%|▎         | 1672/57600 [17:35<9:54:15,  1.57it/s]
  3%|▎         | 1673/57600 [17:35<9:56:08,  1.56it/s]
  3%|▎         | 1674/57600 [17:36<9:49:28,  1.58it/s]
  3%|▎         | 1675/57600 [17:36<9:53:18,  1.57it/s]
  3%|▎         | 1676/57600 [17:37<9:50:37,  1.58it/s]
  3%|▎         | 1677/57600 [17:38<9:35:17,  1.62it/s]
  3%|▎         | 1678/57600 [17:38<9:30:30,  1.63it/s]
  3%|▎         | 1679/57600 [17:39<9:30:52,  1.63it/s]
  3%|▎         | 1680/57600 [17:39<9:26:46,  1.64it/s]
                                                      
{'loss': 1.6888, 'learning_rate': 9.76794425087108e-07, 'epoch': 18.54}

  3%|▎         | 1680/57600 [17:39<9:26:46,  1.64it/s]
  3%|▎         | 1681/57600 [17:40<9:28:25,  1.64it/s]
  3%|▎         | 1682/57600 [17:41<9:17:22,  1.67it/s]
  3%|▎         | 1683/57600 [17:41<9:29:33,  1.64it/s]
  3%|▎         | 1684/57600 [17:42<10:12:10,  1.52it/s]
  3%|▎         | 1685/57600 [17:43<9:47:43,  1.59it/s] 
  3%|▎         | 1686/57600 [17:43<9:16:35,  1.67it/s]
  3%|▎         | 1687/57600 [17:44<9:09:53,  1.69it/s]
  3%|▎         | 1688/57600 [17:44<9:13:35,  1.68it/s]
  3%|▎         | 1689/57600 [17:45<9:04:48,  1.71it/s]
  3%|▎         | 1690/57600 [17:45<9:02:54,  1.72it/s]
  3%|▎         | 1691/57600 [17:46<9:33:58,  1.62it/s]
  3%|▎         | 1692/57600 [17:47<9:40:22,  1.61it/s]
  3%|▎         | 1693/57600 [17:47<9:29:09,  1.64it/s]
  3%|▎         | 1694/57600 [17:48<9:25:54,  1.65it/s]
  3%|▎         | 1695/57600 [17:49<9:30:34,  1.63it/s]
  3%|▎         | 1696/57600 [17:49<9:25:51,  1.65it/s]
  3%|▎         | 1697/57600 [17:50<9:28:10,  1.64it/s]
  3%|▎         | 1698/57600 [17:50<9:27:52,  1.64it/s]
  3%|▎         | 1699/57600 [17:51<9:43:06,  1.60it/s]
  3%|▎         | 1700/57600 [17:52<9:23:18,  1.65it/s]
                                                      
{'loss': 1.7562, 'learning_rate': 9.764808362369338e-07, 'epoch': 18.76}

  3%|▎         | 1700/57600 [17:52<9:23:18,  1.65it/s]
  3%|▎         | 1701/57600 [17:52<9:18:32,  1.67it/s]
  3%|▎         | 1702/57600 [17:53<9:08:10,  1.70it/s]
  3%|▎         | 1703/57600 [17:53<9:08:47,  1.70it/s]
  3%|▎         | 1704/57600 [17:54<9:11:54,  1.69it/s]
  3%|▎         | 1705/57600 [17:55<9:26:50,  1.64it/s]
  3%|▎         | 1706/57600 [17:55<9:26:50,  1.64it/s]
  3%|▎         | 1707/57600 [17:56<9:33:21,  1.62it/s]
  3%|▎         | 1708/57600 [17:57<9:42:37,  1.60it/s]
  3%|▎         | 1709/57600 [17:57<9:32:17,  1.63it/s]
  3%|▎         | 1710/57600 [17:58<9:58:51,  1.56it/s]
  3%|▎         | 1711/57600 [17:58<10:00:57,  1.55it/s]
  3%|▎         | 1712/57600 [17:59<10:11:49,  1.52it/s]
  3%|▎         | 1713/57600 [18:00<10:14:10,  1.52it/s]
  3%|▎         | 1714/57600 [18:00<9:44:41,  1.59it/s] 
  3%|▎         | 1715/57600 [18:01<9:53:25,  1.57it/s]
  3%|▎         | 1716/57600 [18:02<9:49:48,  1.58it/s]
  3%|▎         | 1717/57600 [18:02<10:02:23,  1.55it/s]
  3%|▎         | 1718/57600 [18:03<10:28:58,  1.48it/s]
  3%|▎         | 1719/57600 [18:04<10:17:45,  1.51it/s]
  3%|▎         | 1720/57600 [18:04<10:10:27,  1.53it/s]
                                                       
{'loss': 1.7368, 'learning_rate': 9.761672473867594e-07, 'epoch': 18.98}

  3%|▎         | 1720/57600 [18:04<10:10:27,  1.53it/s]
  3%|▎         | 1721/57600 [18:05<10:07:22,  1.53it/s]
  3%|▎         | 1722/57600 [18:06<10:25:42,  1.49it/s]
  3%|▎         | 1723/57600 [18:06<10:07:33,  1.53it/s]
  3%|▎         | 1724/57600 [18:07<10:01:49,  1.55it/s]
  3%|▎         | 1725/57600 [18:08<9:51:01,  1.58it/s] 
  3%|▎         | 1726/57600 [18:08<9:44:10,  1.59it/s]
  3%|▎         | 1727/57600 [18:09<9:50:38,  1.58it/s]
  3%|▎         | 1728/57600 [18:09<9:41:49,  1.60it/s]
  3%|▎         | 1729/57600 [18:10<9:45:08,  1.59it/s]
  3%|▎         | 1730/57600 [18:11<9:45:39,  1.59it/s]
  3%|▎         | 1731/57600 [18:11<9:41:54,  1.60it/s]
  3%|▎         | 1732/57600 [18:12<9:50:31,  1.58it/s]
  3%|▎         | 1733/57600 [18:13<9:44:22,  1.59it/s]
  3%|▎         | 1734/57600 [18:13<9:56:28,  1.56it/s]
  3%|▎         | 1735/57600 [18:14<9:38:09,  1.61it/s]
  3%|▎         | 1736/57600 [18:14<9:33:53,  1.62it/s]
  3%|▎         | 1737/57600 [18:15<9:50:24,  1.58it/s]
  3%|▎         | 1738/57600 [18:16<10:04:00,  1.54it/s]
  3%|▎         | 1739/57600 [18:16<9:50:45,  1.58it/s] 
  3%|▎         | 1740/57600 [18:17<9:39:06,  1.61it/s]
                                                      
{'loss': 1.6816, 'learning_rate': 9.758536585365853e-07, 'epoch': 19.21}

  3%|▎         | 1740/57600 [18:17<9:39:06,  1.61it/s]
  3%|▎         | 1741/57600 [18:18<9:40:49,  1.60it/s]
  3%|▎         | 1742/57600 [18:18<9:36:10,  1.62it/s]
  3%|▎         | 1743/57600 [18:19<9:23:14,  1.65it/s]
  3%|▎         | 1744/57600 [18:19<9:27:29,  1.64it/s]
  3%|▎         | 1745/57600 [18:20<9:18:50,  1.67it/s]
  3%|▎         | 1746/57600 [18:21<9:19:37,  1.66it/s]
  3%|▎         | 1747/57600 [18:21<9:13:35,  1.68it/s]
  3%|▎         | 1748/57600 [18:22<9:13:18,  1.68it/s]
  3%|▎         | 1749/57600 [18:22<9:43:12,  1.60it/s]
  3%|▎         | 1750/57600 [18:23<9:58:42,  1.55it/s]
  3%|▎         | 1751/57600 [18:24<10:12:49,  1.52it/s]
  3%|▎         | 1752/57600 [18:24<10:10:09,  1.53it/s]
  3%|▎         | 1753/57600 [18:25<9:45:31,  1.59it/s] 
  3%|▎         | 1754/57600 [18:26<9:25:57,  1.64it/s]
  3%|▎         | 1755/57600 [18:26<9:24:42,  1.65it/s]
  3%|▎         | 1756/57600 [18:27<9:52:04,  1.57it/s]
  3%|▎         | 1757/57600 [18:27<9:31:43,  1.63it/s]
  3%|▎         | 1758/57600 [18:28<9:30:29,  1.63it/s]
  3%|▎         | 1759/57600 [18:29<9:25:05,  1.65it/s]
  3%|▎         | 1760/57600 [18:29<9:29:03,  1.64it/s]
                                                      
{'loss': 1.7307, 'learning_rate': 9.755400696864111e-07, 'epoch': 19.43}

  3%|▎         | 1760/57600 [18:29<9:29:03,  1.64it/s]
  3%|▎         | 1761/57600 [18:30<9:45:54,  1.59it/s]
  3%|▎         | 1762/57600 [18:31<9:36:38,  1.61it/s]
  3%|▎         | 1763/57600 [18:31<9:41:43,  1.60it/s]
  3%|▎         | 1764/57600 [18:32<9:24:30,  1.65it/s]
  3%|▎         | 1765/57600 [18:32<9:15:15,  1.68it/s]
  3%|▎         | 1766/57600 [18:33<9:23:42,  1.65it/s]
  3%|▎         | 1767/57600 [18:34<9:39:54,  1.60it/s]
  3%|▎         | 1768/57600 [18:34<10:03:03,  1.54it/s]
  3%|▎         | 1769/57600 [18:35<10:26:54,  1.48it/s]
  3%|▎         | 1770/57600 [18:36<10:14:04,  1.52it/s]
  3%|▎         | 1771/57600 [18:36<10:02:20,  1.54it/s]
  3%|▎         | 1772/57600 [18:37<10:01:18,  1.55it/s]
  3%|▎         | 1773/57600 [18:38<9:38:25,  1.61it/s] 
  3%|▎         | 1774/57600 [18:38<9:39:43,  1.60it/s]
  3%|▎         | 1775/57600 [18:39<9:26:35,  1.64it/s]
  3%|▎         | 1776/57600 [18:39<9:28:56,  1.64it/s]
  3%|▎         | 1777/57600 [18:40<9:23:43,  1.65it/s]
  3%|▎         | 1778/57600 [18:41<9:33:08,  1.62it/s]
  3%|▎         | 1779/57600 [18:41<9:33:50,  1.62it/s]
  3%|▎         | 1780/57600 [18:42<9:38:05,  1.61it/s]
                                                      
{'loss': 1.7313, 'learning_rate': 9.75226480836237e-07, 'epoch': 19.65}

  3%|▎         | 1780/57600 [18:42<9:38:05,  1.61it/s]
  3%|▎         | 1781/57600 [18:42<9:22:25,  1.65it/s]
  3%|▎         | 1782/57600 [18:43<9:38:11,  1.61it/s]
  3%|▎         | 1783/57600 [18:44<9:44:22,  1.59it/s]
  3%|▎         | 1784/57600 [18:44<9:44:57,  1.59it/s]
  3%|▎         | 1785/57600 [18:45<9:49:59,  1.58it/s]
  3%|▎         | 1786/57600 [18:46<9:41:57,  1.60it/s]
  3%|▎         | 1787/57600 [18:46<9:46:48,  1.59it/s]
  3%|▎         | 1788/57600 [18:47<9:41:54,  1.60it/s]
  3%|▎         | 1789/57600 [18:47<9:27:35,  1.64it/s]
  3%|▎         | 1790/57600 [18:48<9:24:17,  1.65it/s]
  3%|▎         | 1791/57600 [18:49<9:13:28,  1.68it/s]
  3%|▎         | 1792/57600 [18:49<9:24:21,  1.65it/s]
  3%|▎         | 1793/57600 [18:50<9:09:19,  1.69it/s]
  3%|▎         | 1794/57600 [18:51<9:52:56,  1.57it/s]
  3%|▎         | 1795/57600 [18:51<9:48:57,  1.58it/s]
  3%|▎         | 1796/57600 [18:52<9:33:02,  1.62it/s]
  3%|▎         | 1797/57600 [18:52<9:41:57,  1.60it/s]
  3%|▎         | 1798/57600 [18:53<9:38:40,  1.61it/s]
  3%|▎         | 1799/57600 [18:54<9:32:00,  1.63it/s]
  3%|▎         | 1800/57600 [18:54<9:46:56,  1.58it/s]
                                                      
{'loss': 1.7407, 'learning_rate': 9.749128919860627e-07, 'epoch': 19.87}

  3%|▎         | 1800/57600 [18:54<9:46:56,  1.58it/s]
  3%|▎         | 1801/57600 [18:55<9:42:34,  1.60it/s]
  3%|▎         | 1802/57600 [18:55<9:30:33,  1.63it/s]
  3%|▎         | 1803/57600 [18:56<9:46:05,  1.59it/s]
  3%|▎         | 1804/57600 [18:57<9:53:46,  1.57it/s]
  3%|▎         | 1805/57600 [18:57<10:08:01,  1.53it/s]
  3%|▎         | 1806/57600 [18:58<10:16:06,  1.51it/s]
  3%|▎         | 1807/57600 [18:59<9:56:56,  1.56it/s] 
  3%|▎         | 1808/57600 [18:59<10:05:45,  1.54it/s]
  3%|▎         | 1809/57600 [19:00<9:44:28,  1.59it/s] 
  3%|▎         | 1810/57600 [19:01<9:37:10,  1.61it/s]
  3%|▎         | 1811/57600 [19:01<9:50:55,  1.57it/s]
  3%|▎         | 1812/57600 [19:02<9:52:31,  1.57it/s]
  3%|▎         | 1813/57600 [19:03<9:54:57,  1.56it/s]
  3%|▎         | 1814/57600 [19:03<10:01:46,  1.55it/s]
  3%|▎         | 1815/57600 [19:04<9:59:15,  1.55it/s] 
  3%|▎         | 1816/57600 [19:05<10:06:49,  1.53it/s]
  3%|▎         | 1817/57600 [19:05<9:43:55,  1.59it/s] 
  3%|▎         | 1818/57600 [19:06<9:58:13,  1.55it/s]
  3%|▎         | 1819/57600 [19:06<9:51:43,  1.57it/s]
  3%|▎         | 1820/57600 [19:07<10:00:13,  1.55it/s]
                                                       
{'loss': 1.6885, 'learning_rate': 9.745993031358883e-07, 'epoch': 20.09}

  3%|▎         | 1820/57600 [19:07<10:00:13,  1.55it/s]
  3%|▎         | 1821/57600 [19:08<9:47:39,  1.58it/s] 
  3%|▎         | 1822/57600 [19:08<9:42:52,  1.59it/s]
  3%|▎         | 1823/57600 [19:09<9:36:11,  1.61it/s]
  3%|▎         | 1824/57600 [19:10<9:45:58,  1.59it/s]
  3%|▎         | 1825/57600 [19:10<9:59:40,  1.55it/s]
  3%|▎         | 1826/57600 [19:11<9:45:29,  1.59it/s]
  3%|▎         | 1827/57600 [19:11<9:45:40,  1.59it/s]
  3%|▎         | 1828/57600 [19:12<9:34:59,  1.62it/s]
  3%|▎         | 1829/57600 [19:13<9:47:09,  1.58it/s]
  3%|▎         | 1830/57600 [19:13<9:52:02,  1.57it/s]
  3%|▎         | 1831/57600 [19:14<9:49:17,  1.58it/s]
  3%|▎         | 1832/57600 [19:15<9:33:02,  1.62it/s]
  3%|▎         | 1833/57600 [19:15<9:23:55,  1.65it/s]
  3%|▎         | 1834/57600 [19:16<9:23:17,  1.65it/s]
  3%|▎         | 1835/57600 [19:16<9:44:54,  1.59it/s]
  3%|▎         | 1836/57600 [19:17<9:37:56,  1.61it/s]
  3%|▎         | 1837/57600 [19:18<9:38:29,  1.61it/s]
  3%|▎         | 1838/57600 [19:18<9:26:49,  1.64it/s]
  3%|▎         | 1839/57600 [19:19<9:35:13,  1.62it/s]
  3%|▎         | 1840/57600 [19:19<9:19:46,  1.66it/s]
                                                      
{'loss': 1.6741, 'learning_rate': 9.742857142857142e-07, 'epoch': 20.31}

  3%|▎         | 1840/57600 [19:19<9:19:46,  1.66it/s]
  3%|▎         | 1841/57600 [19:20<9:13:51,  1.68it/s]
  3%|▎         | 1842/57600 [19:21<9:28:51,  1.63it/s]
  3%|▎         | 1843/57600 [19:21<9:35:59,  1.61it/s]
  3%|▎         | 1844/57600 [19:22<9:32:13,  1.62it/s]
  3%|▎         | 1845/57600 [19:23<9:39:43,  1.60it/s]
  3%|▎         | 1846/57600 [19:23<9:49:31,  1.58it/s]
  3%|▎         | 1847/57600 [19:24<10:03:54,  1.54it/s]
  3%|▎         | 1848/57600 [19:24<9:52:26,  1.57it/s] 
  3%|▎         | 1849/57600 [19:25<9:43:59,  1.59it/s]
  3%|▎         | 1850/57600 [19:26<9:55:17,  1.56it/s]
  3%|▎         | 1851/57600 [19:26<9:45:37,  1.59it/s]
  3%|▎         | 1852/57600 [19:27<9:46:02,  1.59it/s]
  3%|▎         | 1853/57600 [19:28<9:39:23,  1.60it/s]
  3%|▎         | 1854/57600 [19:28<9:27:13,  1.64it/s]
  3%|▎         | 1855/57600 [19:29<9:39:39,  1.60it/s]
  3%|▎         | 1856/57600 [19:30<9:51:32,  1.57it/s]
  3%|▎         | 1857/57600 [19:30<10:05:57,  1.53it/s]
  3%|▎         | 1858/57600 [19:31<9:45:55,  1.59it/s] 
  3%|▎         | 1859/57600 [19:31<9:39:56,  1.60it/s]
  3%|▎         | 1860/57600 [19:32<9:34:32,  1.62it/s]
                                                      
{'loss': 1.6958, 'learning_rate': 9.7397212543554e-07, 'epoch': 20.53}

  3%|▎         | 1860/57600 [19:32<9:34:32,  1.62it/s]
  3%|▎         | 1861/57600 [19:33<9:55:45,  1.56it/s]
  3%|▎         | 1862/57600 [19:33<9:48:23,  1.58it/s]
  3%|▎         | 1863/57600 [19:34<9:50:40,  1.57it/s]
  3%|▎         | 1864/57600 [19:35<9:45:34,  1.59it/s]
  3%|▎         | 1865/57600 [19:35<9:41:13,  1.60it/s]
  3%|▎         | 1866/57600 [19:36<9:51:43,  1.57it/s]
  3%|▎         | 1867/57600 [19:36<9:47:47,  1.58it/s]
  3%|▎         | 1868/57600 [19:37<9:51:11,  1.57it/s]
  3%|▎         | 1869/57600 [19:38<9:44:17,  1.59it/s]
  3%|▎         | 1870/57600 [19:38<9:40:02,  1.60it/s]
  3%|▎         | 1871/57600 [19:39<9:32:58,  1.62it/s]
  3%|▎         | 1872/57600 [19:40<9:30:41,  1.63it/s]
  3%|▎         | 1873/57600 [19:40<9:28:22,  1.63it/s]
  3%|▎         | 1874/57600 [19:41<9:17:34,  1.67it/s]
  3%|▎         | 1875/57600 [19:41<9:28:53,  1.63it/s]
  3%|▎         | 1876/57600 [19:42<9:56:17,  1.56it/s]
  3%|▎         | 1877/57600 [19:43<9:57:41,  1.55it/s]
  3%|▎         | 1878/57600 [19:43<9:37:41,  1.61it/s]
  3%|▎         | 1879/57600 [19:44<9:36:13,  1.61it/s]
  3%|▎         | 1880/57600 [19:44<9:25:08,  1.64it/s]
                                                      
{'loss': 1.7036, 'learning_rate': 9.736585365853659e-07, 'epoch': 20.75}

  3%|▎         | 1880/57600 [19:44<9:25:08,  1.64it/s]
  3%|▎         | 1881/57600 [19:45<9:20:43,  1.66it/s]
  3%|▎         | 1882/57600 [19:46<9:43:36,  1.59it/s]
  3%|▎         | 1883/57600 [19:46<9:33:29,  1.62it/s]
  3%|▎         | 1884/57600 [19:47<9:48:18,  1.58it/s]
  3%|▎         | 1885/57600 [19:48<9:42:58,  1.59it/s]
  3%|▎         | 1886/57600 [19:48<10:18:36,  1.50it/s]
  3%|▎         | 1887/57600 [19:49<10:08:18,  1.53it/s]
  3%|▎         | 1888/57600 [19:50<10:02:09,  1.54it/s]
  3%|▎         | 1889/57600 [19:50<10:15:23,  1.51it/s]
  3%|▎         | 1890/57600 [19:51<9:48:22,  1.58it/s] 
  3%|▎         | 1891/57600 [19:52<9:34:09,  1.62it/s]
  3%|▎         | 1892/57600 [19:52<9:32:04,  1.62it/s]
  3%|▎         | 1893/57600 [19:53<9:46:19,  1.58it/s]
  3%|▎         | 1894/57600 [19:53<9:48:22,  1.58it/s]
  3%|▎         | 1895/57600 [19:54<9:53:58,  1.56it/s]
  3%|▎         | 1896/57600 [19:55<9:42:47,  1.59it/s]
  3%|▎         | 1897/57600 [19:55<9:51:52,  1.57it/s]
  3%|▎         | 1898/57600 [19:56<9:57:38,  1.55it/s]
  3%|▎         | 1899/57600 [19:57<9:34:34,  1.62it/s]
  3%|▎         | 1900/57600 [19:57<9:36:05,  1.61it/s]
                                                      
{'loss': 1.7489, 'learning_rate': 9.733449477351917e-07, 'epoch': 20.97}

  3%|▎         | 1900/57600 [19:57<9:36:05,  1.61it/s]
  3%|▎         | 1901/57600 [19:58<9:28:00,  1.63it/s]
  3%|▎         | 1902/57600 [19:58<9:32:58,  1.62it/s]
  3%|▎         | 1903/57600 [19:59<9:43:57,  1.59it/s]
  3%|▎         | 1904/57600 [20:00<9:35:04,  1.61it/s]
  3%|▎         | 1905/57600 [20:00<9:38:08,  1.61it/s]
  3%|▎         | 1906/57600 [20:01<9:47:32,  1.58it/s]
  3%|▎         | 1907/57600 [20:02<9:37:41,  1.61it/s]
  3%|▎         | 1908/57600 [20:02<9:44:55,  1.59it/s]
  3%|▎         | 1909/57600 [20:03<9:29:36,  1.63it/s]
  3%|▎         | 1910/57600 [20:03<9:26:43,  1.64it/s]
  3%|▎         | 1911/57600 [20:04<9:26:15,  1.64it/s]
  3%|▎         | 1912/57600 [20:05<10:01:59,  1.54it/s]
  3%|▎         | 1913/57600 [20:05<10:04:48,  1.53it/s]
  3%|▎         | 1914/57600 [20:06<9:57:18,  1.55it/s] 
  3%|▎         | 1915/57600 [20:07<9:49:46,  1.57it/s]
  3%|▎         | 1916/57600 [20:07<9:45:16,  1.59it/s]
  3%|▎         | 1917/57600 [20:08<9:51:03,  1.57it/s]
  3%|▎         | 1918/57600 [20:09<10:00:37,  1.55it/s]
  3%|▎         | 1919/57600 [20:09<9:44:17,  1.59it/s] 
  3%|▎         | 1920/57600 [20:10<9:41:07,  1.60it/s]
                                                      
{'loss': 1.7719, 'learning_rate': 9.730313588850174e-07, 'epoch': 21.19}

  3%|▎         | 1920/57600 [20:10<9:41:07,  1.60it/s]
  3%|▎         | 1921/57600 [20:10<9:59:45,  1.55it/s]
  3%|▎         | 1922/57600 [20:11<10:09:12,  1.52it/s]
  3%|▎         | 1923/57600 [20:12<10:02:41,  1.54it/s]
  3%|▎         | 1924/57600 [20:12<10:02:38,  1.54it/s]
  3%|▎         | 1925/57600 [20:13<9:52:08,  1.57it/s] 
  3%|▎         | 1926/57600 [20:14<9:46:19,  1.58it/s]
  3%|▎         | 1927/57600 [20:14<9:55:55,  1.56it/s]
  3%|▎         | 1928/57600 [20:15<9:52:57,  1.56it/s]
  3%|▎         | 1929/57600 [20:16<9:34:03,  1.62it/s]
  3%|▎         | 1930/57600 [20:16<10:12:25,  1.52it/s]
  3%|▎         | 1931/57600 [20:17<9:56:33,  1.56it/s] 
  3%|▎         | 1932/57600 [20:17<9:41:28,  1.60it/s]
  3%|▎         | 1933/57600 [20:18<9:34:26,  1.62it/s]
  3%|▎         | 1934/57600 [20:19<9:19:34,  1.66it/s]
  3%|▎         | 1935/57600 [20:19<9:19:11,  1.66it/s]
  3%|▎         | 1936/57600 [20:20<9:31:40,  1.62it/s]
  3%|▎         | 1937/57600 [20:21<9:41:02,  1.60it/s]
  3%|▎         | 1938/57600 [20:21<9:31:10,  1.62it/s]
  3%|▎         | 1939/57600 [20:22<9:53:08,  1.56it/s]
  3%|▎         | 1940/57600 [20:22<9:37:15,  1.61it/s]
                                                      
{'loss': 1.7401, 'learning_rate': 9.72717770034843e-07, 'epoch': 21.41}

  3%|▎         | 1940/57600 [20:22<9:37:15,  1.61it/s]
  3%|▎         | 1941/57600 [20:23<9:21:46,  1.65it/s]
  3%|▎         | 1942/57600 [20:24<9:36:46,  1.61it/s]
  3%|▎         | 1943/57600 [20:24<9:43:24,  1.59it/s]
  3%|▎         | 1944/57600 [20:25<9:35:00,  1.61it/s]
  3%|▎         | 1945/57600 [20:25<9:30:46,  1.63it/s]
  3%|▎         | 1946/57600 [20:26<9:39:19,  1.60it/s]
  3%|▎         | 1947/57600 [20:27<9:52:01,  1.57it/s]
  3%|▎         | 1948/57600 [20:27<9:47:55,  1.58it/s]
  3%|▎         | 1949/57600 [20:28<10:02:29,  1.54it/s]
  3%|▎         | 1950/57600 [20:29<9:40:27,  1.60it/s] 
  3%|▎         | 1951/57600 [20:29<9:49:05,  1.57it/s]
  3%|▎         | 1952/57600 [20:30<9:31:40,  1.62it/s]
  3%|▎         | 1953/57600 [20:31<10:01:15,  1.54it/s]
  3%|▎         | 1954/57600 [20:31<10:03:12,  1.54it/s]
  3%|▎         | 1955/57600 [20:32<9:46:03,  1.58it/s] 
  3%|▎         | 1956/57600 [20:33<9:43:26,  1.59it/s]
  3%|▎         | 1957/57600 [20:33<10:02:13,  1.54it/s]
  3%|▎         | 1958/57600 [20:34<9:57:31,  1.55it/s] 
  3%|▎         | 1959/57600 [20:34<9:51:08,  1.57it/s]
  3%|▎         | 1960/57600 [20:35<9:48:59,  1.57it/s]
                                                      
{'loss': 1.7247, 'learning_rate': 9.724041811846689e-07, 'epoch': 21.63}

  3%|▎         | 1960/57600 [20:35<9:48:59,  1.57it/s]
  3%|▎         | 1961/57600 [20:36<9:53:42,  1.56it/s]
  3%|▎         | 1962/57600 [20:36<9:51:20,  1.57it/s]
  3%|▎         | 1963/57600 [20:37<10:26:12,  1.48it/s]
  3%|▎         | 1964/57600 [20:38<9:59:12,  1.55it/s] 
  3%|▎         | 1965/57600 [20:38<10:01:37,  1.54it/s]
  3%|▎         | 1966/57600 [20:39<9:51:49,  1.57it/s] 
  3%|▎         | 1967/57600 [20:40<9:38:18,  1.60it/s]
  3%|▎         | 1968/57600 [20:40<9:33:48,  1.62it/s]
  3%|▎         | 1969/57600 [20:41<9:19:28,  1.66it/s]
  3%|▎         | 1970/57600 [20:41<9:20:56,  1.65it/s]
  3%|▎         | 1971/57600 [20:42<9:36:53,  1.61it/s]
  3%|▎         | 1972/57600 [20:43<9:42:33,  1.59it/s]
  3%|▎         | 1973/57600 [20:43<9:27:01,  1.64it/s]
  3%|▎         | 1974/57600 [20:44<9:18:21,  1.66it/s]
  3%|▎         | 1975/57600 [20:44<9:09:24,  1.69it/s]
  3%|▎         | 1976/57600 [20:45<9:26:32,  1.64it/s]
  3%|▎         | 1977/57600 [20:46<9:29:43,  1.63it/s]
  3%|▎         | 1978/57600 [20:46<9:30:33,  1.62it/s]
  3%|▎         | 1979/57600 [20:47<9:49:06,  1.57it/s]
  3%|▎         | 1980/57600 [20:48<9:37:45,  1.60it/s]
                                                      
{'loss': 1.7175, 'learning_rate': 9.720905923344947e-07, 'epoch': 21.85}

  3%|▎         | 1980/57600 [20:48<9:37:45,  1.60it/s]
  3%|▎         | 1981/57600 [20:48<9:24:23,  1.64it/s]
  3%|▎         | 1982/57600 [20:49<9:33:06,  1.62it/s]
  3%|▎         | 1983/57600 [20:49<9:49:48,  1.57it/s]
  3%|▎         | 1984/57600 [20:50<10:04:48,  1.53it/s]
  3%|▎         | 1985/57600 [20:51<9:47:17,  1.58it/s] 
  3%|▎         | 1986/57600 [20:51<9:33:20,  1.62it/s]
  3%|▎         | 1987/57600 [20:52<9:27:01,  1.63it/s]
  3%|▎         | 1988/57600 [20:53<9:37:40,  1.60it/s]
  3%|▎         | 1989/57600 [20:53<9:26:25,  1.64it/s]
  3%|▎         | 1990/57600 [20:54<9:23:21,  1.65it/s]
  3%|▎         | 1991/57600 [20:54<9:22:29,  1.65it/s]
  3%|▎         | 1992/57600 [20:55<9:26:22,  1.64it/s]
  3%|▎         | 1993/57600 [20:56<9:48:02,  1.58it/s]
  3%|▎         | 1994/57600 [20:56<10:16:04,  1.50it/s]
  3%|▎         | 1995/57600 [20:57<10:06:36,  1.53it/s]
  3%|▎         | 1996/57600 [20:58<9:53:30,  1.56it/s] 
  3%|▎         | 1997/57600 [20:58<9:42:54,  1.59it/s]
  3%|▎         | 1998/57600 [20:59<9:47:49,  1.58it/s]
  3%|▎         | 1999/57600 [20:59<9:38:57,  1.60it/s]
  3%|▎         | 2000/57600 [21:00<9:29:47,  1.63it/s]
                                                      
{'loss': 1.7288, 'learning_rate': 9.717770034843206e-07, 'epoch': 22.08}

  3%|▎         | 2000/57600 [21:00<9:29:47,  1.63it/s]
  3%|▎         | 2001/57600 [21:01<9:30:31,  1.62it/s]
  3%|▎         | 2002/57600 [21:01<10:01:40,  1.54it/s]
  3%|▎         | 2003/57600 [21:02<10:11:53,  1.51it/s]
  3%|▎         | 2004/57600 [21:03<10:04:40,  1.53it/s]
  3%|▎         | 2005/57600 [21:03<9:53:15,  1.56it/s] 
  3%|▎         | 2006/57600 [21:04<9:52:26,  1.56it/s]
  3%|▎         | 2007/57600 [21:05<9:40:40,  1.60it/s]
  3%|▎         | 2008/57600 [21:05<9:36:32,  1.61it/s]
  3%|▎         | 2009/57600 [21:06<9:37:29,  1.60it/s]
  3%|▎         | 2010/57600 [21:06<9:41:48,  1.59it/s]
  3%|▎         | 2011/57600 [21:07<9:44:05,  1.59it/s]
  3%|▎         | 2012/57600 [21:08<9:43:25,  1.59it/s]
  3%|▎         | 2013/57600 [21:08<9:51:40,  1.57it/s]
  3%|▎         | 2014/57600 [21:09<9:56:25,  1.55it/s]
  3%|▎         | 2015/57600 [21:10<9:33:49,  1.61it/s]
  4%|▎         | 2016/57600 [21:10<9:32:07,  1.62it/s]
  4%|▎         | 2017/57600 [21:11<9:22:31,  1.65it/s]
  4%|▎         | 2018/57600 [21:11<9:32:52,  1.62it/s]
  4%|▎         | 2019/57600 [21:12<9:27:09,  1.63it/s]
  4%|▎         | 2020/57600 [21:13<9:36:13,  1.61it/s]
                                                      
{'loss': 1.7068, 'learning_rate': 9.714634146341462e-07, 'epoch': 22.3}

  4%|▎         | 2020/57600 [21:13<9:36:13,  1.61it/s]
  4%|▎         | 2021/57600 [21:13<9:25:06,  1.64it/s]
  4%|▎         | 2022/57600 [21:14<9:26:39,  1.63it/s]
  4%|▎         | 2023/57600 [21:15<9:52:20,  1.56it/s]
  4%|▎         | 2024/57600 [21:15<9:41:37,  1.59it/s]
  4%|▎         | 2025/57600 [21:16<10:00:10,  1.54it/s]
  4%|▎         | 2026/57600 [21:17<9:56:26,  1.55it/s] 
  4%|▎         | 2027/57600 [21:17<9:36:08,  1.61it/s]
  4%|▎         | 2028/57600 [21:18<9:35:45,  1.61it/s]
  4%|▎         | 2029/57600 [21:18<9:29:09,  1.63it/s]
  4%|▎         | 2030/57600 [21:19<9:45:45,  1.58it/s]
  4%|▎         | 2031/57600 [21:20<9:48:39,  1.57it/s]
  4%|▎         | 2032/57600 [21:20<9:33:55,  1.61it/s]
  4%|▎         | 2033/57600 [21:21<9:35:16,  1.61it/s]
  4%|▎         | 2034/57600 [21:21<9:45:27,  1.58it/s]
  4%|▎         | 2035/57600 [21:22<9:56:02,  1.55it/s]
  4%|▎         | 2036/57600 [21:23<10:05:39,  1.53it/s]
  4%|▎         | 2037/57600 [21:23<9:54:03,  1.56it/s] 
  4%|▎         | 2038/57600 [21:24<9:46:01,  1.58it/s]
  4%|▎         | 2039/57600 [21:25<9:41:45,  1.59it/s]
  4%|▎         | 2040/57600 [21:25<9:37:09,  1.60it/s]
                                                      
{'loss': 1.6812, 'learning_rate': 9.71149825783972e-07, 'epoch': 22.52}

  4%|▎         | 2040/57600 [21:25<9:37:09,  1.60it/s]
  4%|▎         | 2041/57600 [21:26<9:45:33,  1.58it/s]
  4%|▎         | 2042/57600 [21:27<9:33:27,  1.61it/s]
  4%|▎         | 2043/57600 [21:27<9:30:39,  1.62it/s]
  4%|▎         | 2044/57600 [21:28<9:40:25,  1.60it/s]
  4%|▎         | 2045/57600 [21:28<9:59:21,  1.54it/s]
  4%|▎         | 2046/57600 [21:29<10:03:11,  1.53it/s]
  4%|▎         | 2047/57600 [21:30<10:00:42,  1.54it/s]
  4%|▎         | 2048/57600 [21:30<9:47:51,  1.57it/s] 
  4%|▎         | 2049/57600 [21:31<9:54:55,  1.56it/s]
  4%|▎         | 2050/57600 [21:32<10:11:42,  1.51it/s]
  4%|▎         | 2051/57600 [21:32<10:03:30,  1.53it/s]
  4%|▎         | 2052/57600 [21:33<9:57:08,  1.55it/s] 
  4%|▎         | 2053/57600 [21:34<9:58:11,  1.55it/s]
  4%|▎         | 2054/57600 [21:34<9:39:03,  1.60it/s]
  4%|▎         | 2055/57600 [21:35<9:34:04,  1.61it/s]
  4%|▎         | 2056/57600 [21:35<9:42:20,  1.59it/s]
  4%|▎         | 2057/57600 [21:36<10:02:16,  1.54it/s]
  4%|▎         | 2058/57600 [21:37<9:40:07,  1.60it/s] 
  4%|▎         | 2059/57600 [21:37<9:34:05,  1.61it/s]
  4%|▎         | 2060/57600 [21:38<9:48:02,  1.57it/s]
                                                      
{'loss': 1.6772, 'learning_rate': 9.708362369337977e-07, 'epoch': 22.74}

  4%|▎         | 2060/57600 [21:38<9:48:02,  1.57it/s]
  4%|▎         | 2061/57600 [21:39<9:47:17,  1.58it/s]
  4%|▎         | 2062/57600 [21:39<10:06:34,  1.53it/s]
  4%|▎         | 2063/57600 [21:40<10:08:47,  1.52it/s]
  4%|▎         | 2064/57600 [21:41<9:57:47,  1.55it/s] 
  4%|▎         | 2065/57600 [21:41<10:10:44,  1.52it/s]
  4%|▎         | 2066/57600 [21:42<10:04:18,  1.53it/s]
  4%|▎         | 2067/57600 [21:43<10:33:17,  1.46it/s]
  4%|▎         | 2068/57600 [21:43<10:23:05,  1.49it/s]
  4%|▎         | 2069/57600 [21:44<10:15:23,  1.50it/s]
  4%|▎         | 2070/57600 [21:45<10:06:34,  1.53it/s]
  4%|▎         | 2071/57600 [21:45<9:48:10,  1.57it/s] 
  4%|▎         | 2072/57600 [21:46<9:40:23,  1.59it/s]
  4%|▎         | 2073/57600 [21:47<9:44:23,  1.58it/s]
  4%|▎         | 2074/57600 [21:47<9:55:57,  1.55it/s]
  4%|▎         | 2075/57600 [21:48<9:50:06,  1.57it/s]
  4%|▎         | 2076/57600 [21:48<9:40:20,  1.59it/s]
  4%|▎         | 2077/57600 [21:49<9:47:55,  1.57it/s]
  4%|▎         | 2078/57600 [21:50<9:40:46,  1.59it/s]
  4%|▎         | 2079/57600 [21:50<9:49:20,  1.57it/s]
  4%|▎         | 2080/57600 [21:51<10:02:24,  1.54it/s]
                                                       
{'loss': 1.7103, 'learning_rate': 9.705226480836236e-07, 'epoch': 22.96}

  4%|▎         | 2080/57600 [21:51<10:02:24,  1.54it/s]
  4%|▎         | 2081/57600 [21:52<9:41:56,  1.59it/s] 
  4%|▎         | 2082/57600 [21:52<9:33:07,  1.61it/s]
  4%|▎         | 2083/57600 [21:53<9:30:36,  1.62it/s]
  4%|▎         | 2084/57600 [21:53<9:43:49,  1.58it/s]
  4%|▎         | 2085/57600 [21:54<10:10:55,  1.51it/s]
  4%|▎         | 2086/57600 [21:55<9:56:07,  1.55it/s] 
  4%|▎         | 2087/57600 [21:55<9:42:13,  1.59it/s]
  4%|▎         | 2088/57600 [21:56<10:03:36,  1.53it/s]
  4%|▎         | 2089/57600 [21:57<10:26:25,  1.48it/s]
  4%|▎         | 2090/57600 [21:57<10:18:01,  1.50it/s]
  4%|▎         | 2091/57600 [21:58<9:56:30,  1.55it/s] 
  4%|▎         | 2092/57600 [21:59<9:51:02,  1.57it/s]
  4%|▎         | 2093/57600 [21:59<9:40:34,  1.59it/s]
  4%|▎         | 2094/57600 [22:00<9:26:08,  1.63it/s]
  4%|▎         | 2095/57600 [22:01<9:35:57,  1.61it/s]
  4%|▎         | 2096/57600 [22:01<9:28:47,  1.63it/s]
  4%|▎         | 2097/57600 [22:02<9:42:54,  1.59it/s]
  4%|▎         | 2098/57600 [22:02<9:24:54,  1.64it/s]
  4%|▎         | 2099/57600 [22:03<9:38:29,  1.60it/s]
  4%|▎         | 2100/57600 [22:04<9:49:48,  1.57it/s]
                                                      
{'loss': 1.6984, 'learning_rate': 9.702090592334495e-07, 'epoch': 23.18}

  4%|▎         | 2100/57600 [22:04<9:49:48,  1.57it/s]
  4%|▎         | 2101/57600 [22:04<9:38:03,  1.60it/s]
  4%|▎         | 2102/57600 [22:05<9:29:23,  1.62it/s]
  4%|▎         | 2103/57600 [22:06<9:37:25,  1.60it/s]
  4%|▎         | 2104/57600 [22:06<10:15:25,  1.50it/s]
  4%|▎         | 2105/57600 [22:07<10:01:08,  1.54it/s]
  4%|▎         | 2106/57600 [22:07<9:34:20,  1.61it/s] 
  4%|▎         | 2107/57600 [22:08<10:01:01,  1.54it/s]
  4%|▎         | 2108/57600 [22:09<9:55:20,  1.55it/s] 
  4%|▎         | 2109/57600 [22:09<9:47:37,  1.57it/s]
  4%|▎         | 2110/57600 [22:10<9:49:28,  1.57it/s]
  4%|▎         | 2111/57600 [22:11<10:04:02,  1.53it/s]
  4%|▎         | 2112/57600 [22:11<10:11:57,  1.51it/s]
  4%|▎         | 2113/57600 [22:12<10:30:59,  1.47it/s]
  4%|▎         | 2114/57600 [22:13<10:02:18,  1.54it/s]
  4%|▎         | 2115/57600 [22:13<10:10:34,  1.51it/s]
  4%|▎         | 2116/57600 [22:14<10:08:16,  1.52it/s]
  4%|▎         | 2117/57600 [22:15<10:07:09,  1.52it/s]
  4%|▎         | 2118/57600 [22:15<9:55:57,  1.55it/s] 
  4%|▎         | 2119/57600 [22:16<10:14:44,  1.50it/s]
  4%|▎         | 2120/57600 [22:17<10:02:49,  1.53it/s]
                                                       
{'loss': 1.7281, 'learning_rate': 9.698954703832753e-07, 'epoch': 23.4}

  4%|▎         | 2120/57600 [22:17<10:02:49,  1.53it/s]
  4%|▎         | 2121/57600 [22:17<9:51:21,  1.56it/s] 
  4%|▎         | 2122/57600 [22:18<9:49:27,  1.57it/s]
  4%|▎         | 2123/57600 [22:19<9:37:31,  1.60it/s]
  4%|▎         | 2124/57600 [22:19<9:24:42,  1.64it/s]
  4%|▎         | 2125/57600 [22:20<9:19:13,  1.65it/s]
  4%|▎         | 2126/57600 [22:20<9:44:40,  1.58it/s]
  4%|▎         | 2127/57600 [22:21<9:52:43,  1.56it/s]
  4%|▎         | 2128/57600 [22:22<9:53:54,  1.56it/s]
  4%|▎         | 2129/57600 [22:22<9:48:11,  1.57it/s]
  4%|▎         | 2130/57600 [22:23<9:40:38,  1.59it/s]
  4%|▎         | 2131/57600 [22:24<9:39:14,  1.60it/s]
  4%|▎         | 2132/57600 [22:24<10:04:07,  1.53it/s]
  4%|▎         | 2133/57600 [22:25<10:22:38,  1.48it/s]
  4%|▎         | 2134/57600 [22:26<10:26:11,  1.48it/s]
  4%|▎         | 2135/57600 [22:26<10:02:54,  1.53it/s]
  4%|▎         | 2136/57600 [22:27<10:04:12,  1.53it/s]
  4%|▎         | 2137/57600 [22:28<9:54:52,  1.55it/s] 
  4%|▎         | 2138/57600 [22:28<9:53:54,  1.56it/s]
  4%|▎         | 2139/57600 [22:29<9:55:05,  1.55it/s]
  4%|▎         | 2140/57600 [22:29<9:44:40,  1.58it/s]
                                                      
{'loss': 1.7123, 'learning_rate': 9.695818815331012e-07, 'epoch': 23.62}

  4%|▎         | 2140/57600 [22:29<9:44:40,  1.58it/s]
  4%|▎         | 2141/57600 [22:30<9:57:19,  1.55it/s]
  4%|▎         | 2142/57600 [22:31<9:57:03,  1.55it/s]
  4%|▎         | 2143/57600 [22:31<9:46:42,  1.58it/s]
  4%|▎         | 2144/57600 [22:32<9:45:47,  1.58it/s]
  4%|▎         | 2145/57600 [22:33<9:20:49,  1.65it/s]
  4%|▎         | 2146/57600 [22:33<9:24:06,  1.64it/s]
  4%|▎         | 2147/57600 [22:34<9:32:35,  1.61it/s]
  4%|▎         | 2148/57600 [22:35<10:00:46,  1.54it/s]
  4%|▎         | 2149/57600 [22:35<9:47:22,  1.57it/s] 
  4%|▎         | 2150/57600 [22:36<9:43:26,  1.58it/s]
  4%|▎         | 2151/57600 [22:36<9:38:28,  1.60it/s]
  4%|▎         | 2152/57600 [22:37<9:50:32,  1.56it/s]
  4%|▎         | 2153/57600 [22:38<9:35:26,  1.61it/s]
  4%|▎         | 2154/57600 [22:38<9:33:09,  1.61it/s]
  4%|▎         | 2155/57600 [22:39<9:20:32,  1.65it/s]
  4%|▎         | 2156/57600 [22:39<9:36:58,  1.60it/s]
  4%|▎         | 2157/57600 [22:40<9:29:21,  1.62it/s]
  4%|▎         | 2158/57600 [22:41<9:26:30,  1.63it/s]
  4%|▎         | 2159/57600 [22:41<9:17:06,  1.66it/s]
  4%|▍         | 2160/57600 [22:42<9:14:58,  1.66it/s]
                                                      
{'loss': 1.7174, 'learning_rate': 9.692682926829266e-07, 'epoch': 23.84}

  4%|▍         | 2160/57600 [22:42<9:14:58,  1.66it/s]
  4%|▍         | 2161/57600 [22:42<9:25:47,  1.63it/s]
  4%|▍         | 2162/57600 [22:43<9:20:33,  1.65it/s]
  4%|▍         | 2163/57600 [22:44<9:33:33,  1.61it/s]
  4%|▍         | 2164/57600 [22:44<9:30:40,  1.62it/s]
  4%|▍         | 2165/57600 [22:45<9:34:02,  1.61it/s]
  4%|▍         | 2166/57600 [22:46<9:41:00,  1.59it/s]
  4%|▍         | 2167/57600 [22:46<9:40:03,  1.59it/s]
  4%|▍         | 2168/57600 [22:47<9:35:03,  1.61it/s]
  4%|▍         | 2169/57600 [22:47<9:45:46,  1.58it/s]
  4%|▍         | 2170/57600 [22:48<9:45:48,  1.58it/s]
  4%|▍         | 2171/57600 [22:49<9:36:19,  1.60it/s]
  4%|▍         | 2172/57600 [22:49<9:26:26,  1.63it/s]
  4%|▍         | 2173/57600 [22:50<9:24:35,  1.64it/s]
  4%|▍         | 2174/57600 [22:51<9:28:45,  1.62it/s]
  4%|▍         | 2175/57600 [22:51<10:01:54,  1.53it/s]
  4%|▍         | 2176/57600 [22:52<9:46:39,  1.57it/s] 
  4%|▍         | 2177/57600 [22:52<9:31:32,  1.62it/s]
  4%|▍         | 2178/57600 [22:53<9:28:57,  1.62it/s]
  4%|▍         | 2179/57600 [22:54<9:20:52,  1.65it/s]
  4%|▍         | 2180/57600 [22:54<9:21:48,  1.64it/s]
                                                      
{'loss': 1.7281, 'learning_rate': 9.689547038327525e-07, 'epoch': 24.06}

  4%|▍         | 2180/57600 [22:54<9:21:48,  1.64it/s]
  4%|▍         | 2181/57600 [22:55<9:22:59,  1.64it/s]
  4%|▍         | 2182/57600 [22:55<9:23:16,  1.64it/s]
  4%|▍         | 2183/57600 [22:56<9:34:30,  1.61it/s]
  4%|▍         | 2184/57600 [22:57<9:38:20,  1.60it/s]
  4%|▍         | 2185/57600 [22:57<9:22:40,  1.64it/s]
  4%|▍         | 2186/57600 [22:58<9:34:57,  1.61it/s]
  4%|▍         | 2187/57600 [22:59<9:43:08,  1.58it/s]
  4%|▍         | 2188/57600 [22:59<9:33:00,  1.61it/s]
  4%|▍         | 2189/57600 [23:00<9:28:39,  1.62it/s]
  4%|▍         | 2190/57600 [23:00<9:34:42,  1.61it/s]
  4%|▍         | 2191/57600 [23:01<9:24:52,  1.63it/s]
  4%|▍         | 2192/57600 [23:02<9:29:10,  1.62it/s]
  4%|▍         | 2193/57600 [23:02<9:49:34,  1.57it/s]
  4%|▍         | 2194/57600 [23:03<10:28:26,  1.47it/s]
  4%|▍         | 2195/57600 [23:04<10:04:41,  1.53it/s]
  4%|▍         | 2196/57600 [23:04<10:03:53,  1.53it/s]
  4%|▍         | 2197/57600 [23:05<9:59:03,  1.54it/s] 
  4%|▍         | 2198/57600 [23:06<9:52:31,  1.56it/s]
  4%|▍         | 2199/57600 [23:06<9:47:14,  1.57it/s]
  4%|▍         | 2200/57600 [23:07<9:37:21,  1.60it/s]
                                                      
{'loss': 1.7189, 'learning_rate': 9.686411149825783e-07, 'epoch': 24.28}

  4%|▍         | 2200/57600 [23:07<9:37:21,  1.60it/s]
  4%|▍         | 2201/57600 [23:08<9:32:34,  1.61it/s]
  4%|▍         | 2202/57600 [23:08<9:39:54,  1.59it/s]
  4%|▍         | 2203/57600 [23:09<9:31:21,  1.62it/s]
  4%|▍         | 2204/57600 [23:09<9:40:04,  1.59it/s]
  4%|▍         | 2205/57600 [23:10<9:32:01,  1.61it/s]
  4%|▍         | 2206/57600 [23:11<10:13:43,  1.50it/s]
  4%|▍         | 2207/57600 [23:11<10:16:01,  1.50it/s]
  4%|▍         | 2208/57600 [23:12<10:05:07,  1.53it/s]
  4%|▍         | 2209/57600 [23:13<10:20:57,  1.49it/s]
  4%|▍         | 2210/57600 [23:13<10:18:12,  1.49it/s]
  4%|▍         | 2211/57600 [23:14<10:16:01,  1.50it/s]
  4%|▍         | 2212/57600 [23:15<10:08:06,  1.52it/s]
  4%|▍         | 2213/57600 [23:15<9:51:11,  1.56it/s] 
  4%|▍         | 2214/57600 [23:16<9:58:53,  1.54it/s]
  4%|▍         | 2215/57600 [23:17<9:51:45,  1.56it/s]
  4%|▍         | 2216/57600 [23:17<9:55:46,  1.55it/s]
  4%|▍         | 2217/57600 [23:18<9:46:22,  1.57it/s]
  4%|▍         | 2218/57600 [23:19<10:03:01,  1.53it/s]
  4%|▍         | 2219/57600 [23:19<10:02:13,  1.53it/s]
  4%|▍         | 2220/57600 [23:20<9:41:37,  1.59it/s] 
                                                      
{'loss': 1.6272, 'learning_rate': 9.683275261324042e-07, 'epoch': 24.5}

  4%|▍         | 2220/57600 [23:20<9:41:37,  1.59it/s]
  4%|▍         | 2221/57600 [23:20<9:37:36,  1.60it/s]
  4%|▍         | 2222/57600 [23:21<9:32:55,  1.61it/s]
  4%|▍         | 2223/57600 [23:22<9:38:08,  1.60it/s]
  4%|▍         | 2224/57600 [23:22<9:34:39,  1.61it/s]
  4%|▍         | 2225/57600 [23:23<9:52:40,  1.56it/s]
  4%|▍         | 2226/57600 [23:24<9:45:47,  1.58it/s]
  4%|▍         | 2227/57600 [23:24<9:48:22,  1.57it/s]
  4%|▍         | 2228/57600 [23:25<9:58:09,  1.54it/s]
  4%|▍         | 2229/57600 [23:26<10:33:26,  1.46it/s]
  4%|▍         | 2230/57600 [23:26<10:29:36,  1.47it/s]
  4%|▍         | 2231/57600 [23:27<10:02:26,  1.53it/s]
  4%|▍         | 2232/57600 [23:28<10:06:35,  1.52it/s]
  4%|▍         | 2233/57600 [23:28<9:49:26,  1.57it/s] 
  4%|▍         | 2234/57600 [23:29<9:38:41,  1.59it/s]
  4%|▍         | 2235/57600 [23:29<9:29:46,  1.62it/s]
  4%|▍         | 2236/57600 [23:30<9:28:51,  1.62it/s]
  4%|▍         | 2237/57600 [23:31<9:29:10,  1.62it/s]
  4%|▍         | 2238/57600 [23:31<9:18:36,  1.65it/s]
  4%|▍         | 2239/57600 [23:32<9:33:52,  1.61it/s]
  4%|▍         | 2240/57600 [23:33<10:02:08,  1.53it/s]
                                                       
{'loss': 1.6588, 'learning_rate': 9.6801393728223e-07, 'epoch': 24.72}

  4%|▍         | 2240/57600 [23:33<10:02:08,  1.53it/s]
  4%|▍         | 2241/57600 [23:33<9:54:09,  1.55it/s] 
  4%|▍         | 2242/57600 [23:34<9:40:26,  1.59it/s]
  4%|▍         | 2243/57600 [23:35<9:49:13,  1.57it/s]
  4%|▍         | 2244/57600 [23:35<9:46:29,  1.57it/s]
  4%|▍         | 2245/57600 [23:36<9:49:42,  1.56it/s]
  4%|▍         | 2246/57600 [23:36<9:36:39,  1.60it/s]
  4%|▍         | 2247/57600 [23:37<9:42:22,  1.58it/s]
  4%|▍         | 2248/57600 [23:38<9:35:23,  1.60it/s]
  4%|▍         | 2249/57600 [23:38<9:36:50,  1.60it/s]
  4%|▍         | 2250/57600 [23:39<9:40:38,  1.59it/s]
  4%|▍         | 2251/57600 [23:40<9:42:30,  1.58it/s]
  4%|▍         | 2252/57600 [23:40<9:29:14,  1.62it/s]
  4%|▍         | 2253/57600 [23:41<9:34:29,  1.61it/s]
  4%|▍         | 2254/57600 [23:41<9:25:28,  1.63it/s]
  4%|▍         | 2255/57600 [23:42<9:57:32,  1.54it/s]
  4%|▍         | 2256/57600 [23:43<10:08:31,  1.52it/s]
  4%|▍         | 2257/57600 [23:43<9:55:53,  1.55it/s] 
  4%|▍         | 2258/57600 [23:44<9:42:12,  1.58it/s]
  4%|▍         | 2259/57600 [23:45<10:09:07,  1.51it/s]
  4%|▍         | 2260/57600 [23:45<10:19:50,  1.49it/s]
                                                       
{'loss': 1.6627, 'learning_rate': 9.677003484320557e-07, 'epoch': 24.94}

  4%|▍         | 2260/57600 [23:45<10:19:50,  1.49it/s]
  4%|▍         | 2261/57600 [23:46<10:15:57,  1.50it/s]
  4%|▍         | 2262/57600 [23:47<10:03:09,  1.53it/s]
  4%|▍         | 2263/57600 [23:47<10:00:02,  1.54it/s]
  4%|▍         | 2264/57600 [23:48<10:05:49,  1.52it/s]
  4%|▍         | 2265/57600 [23:49<9:53:04,  1.56it/s] 
  4%|▍         | 2266/57600 [23:49<10:21:45,  1.48it/s]
  4%|▍         | 2267/57600 [23:50<10:11:08,  1.51it/s]
  4%|▍         | 2268/57600 [23:51<9:55:21,  1.55it/s] 
  4%|▍         | 2269/57600 [23:51<9:36:05,  1.60it/s]
  4%|▍         | 2270/57600 [23:52<9:30:03,  1.62it/s]
  4%|▍         | 2271/57600 [23:52<9:26:44,  1.63it/s]
  4%|▍         | 2272/57600 [23:53<9:25:45,  1.63it/s]
  4%|▍         | 2273/57600 [23:54<9:39:47,  1.59it/s]
  4%|▍         | 2274/57600 [23:54<9:39:16,  1.59it/s]
  4%|▍         | 2275/57600 [23:55<9:27:57,  1.62it/s]
  4%|▍         | 2276/57600 [23:55<9:25:18,  1.63it/s]
  4%|▍         | 2277/57600 [23:56<9:32:52,  1.61it/s]
  4%|▍         | 2278/57600 [23:57<9:22:06,  1.64it/s]
  4%|▍         | 2279/57600 [23:57<9:35:34,  1.60it/s]
  4%|▍         | 2280/57600 [23:58<9:49:31,  1.56it/s]
                                                      
{'loss': 1.6504, 'learning_rate': 9.673867595818815e-07, 'epoch': 25.17}

  4%|▍         | 2280/57600 [23:58<9:49:31,  1.56it/s]
  4%|▍         | 2281/57600 [23:59<9:34:57,  1.60it/s]
  4%|▍         | 2282/57600 [23:59<9:30:34,  1.62it/s]
  4%|▍         | 2283/57600 [24:00<9:24:39,  1.63it/s]
  4%|▍         | 2284/57600 [24:00<9:27:11,  1.63it/s]
  4%|▍         | 2285/57600 [24:01<9:23:28,  1.64it/s]
  4%|▍         | 2286/57600 [24:02<9:23:10,  1.64it/s]
  4%|▍         | 2287/57600 [24:02<9:18:31,  1.65it/s]
  4%|▍         | 2288/57600 [24:03<9:21:23,  1.64it/s]
  4%|▍         | 2289/57600 [24:03<9:25:53,  1.63it/s]
  4%|▍         | 2290/57600 [24:04<9:29:15,  1.62it/s]
  4%|▍         | 2291/57600 [24:05<10:00:02,  1.54it/s]
  4%|▍         | 2292/57600 [24:06<10:21:45,  1.48it/s]
  4%|▍         | 2293/57600 [24:06<9:59:28,  1.54it/s] 
  4%|▍         | 2294/57600 [24:07<9:52:01,  1.56it/s]
  4%|▍         | 2295/57600 [24:07<9:55:56,  1.55it/s]
  4%|▍         | 2296/57600 [24:08<9:47:02,  1.57it/s]
  4%|▍         | 2297/57600 [24:09<9:41:54,  1.58it/s]
  4%|▍         | 2298/57600 [24:09<9:29:36,  1.62it/s]
  4%|▍         | 2299/57600 [24:10<10:15:01,  1.50it/s]
  4%|▍         | 2300/57600 [24:11<9:56:47,  1.54it/s] 
                                                      
{'loss': 1.6847, 'learning_rate': 9.670731707317072e-07, 'epoch': 25.39}

  4%|▍         | 2300/57600 [24:11<9:56:47,  1.54it/s]
  4%|▍         | 2301/57600 [24:11<9:53:54,  1.55it/s]
  4%|▍         | 2302/57600 [24:12<9:43:43,  1.58it/s]
  4%|▍         | 2303/57600 [24:13<9:42:26,  1.58it/s]
  4%|▍         | 2304/57600 [24:13<9:36:14,  1.60it/s]
  4%|▍         | 2305/57600 [24:14<9:38:03,  1.59it/s]
  4%|▍         | 2306/57600 [24:14<9:50:28,  1.56it/s]
  4%|▍         | 2307/57600 [24:15<9:58:51,  1.54it/s]
  4%|▍         | 2308/57600 [24:16<10:12:53,  1.50it/s]
  4%|▍         | 2309/57600 [24:16<9:59:50,  1.54it/s] 
  4%|▍         | 2310/57600 [24:17<9:55:34,  1.55it/s]
  4%|▍         | 2311/57600 [24:18<9:56:28,  1.54it/s]
  4%|▍         | 2312/57600 [24:18<9:37:03,  1.60it/s]
  4%|▍         | 2313/57600 [24:19<9:30:56,  1.61it/s]
  4%|▍         | 2314/57600 [24:20<9:44:07,  1.58it/s]
  4%|▍         | 2315/57600 [24:20<9:38:49,  1.59it/s]
  4%|▍         | 2316/57600 [24:21<9:40:47,  1.59it/s]
  4%|▍         | 2317/57600 [24:21<9:42:03,  1.58it/s]
  4%|▍         | 2318/57600 [24:22<9:58:24,  1.54it/s]
  4%|▍         | 2319/57600 [24:23<9:44:09,  1.58it/s]
  4%|▍         | 2320/57600 [24:23<9:25:45,  1.63it/s]
                                                      
{'loss': 1.6793, 'learning_rate': 9.66759581881533e-07, 'epoch': 25.61}

  4%|▍         | 2320/57600 [24:23<9:25:45,  1.63it/s]
  4%|▍         | 2321/57600 [24:24<9:35:57,  1.60it/s]
  4%|▍         | 2322/57600 [24:25<9:27:12,  1.62it/s]
  4%|▍         | 2323/57600 [24:25<9:23:43,  1.63it/s]
  4%|▍         | 2324/57600 [24:26<9:26:00,  1.63it/s]
  4%|▍         | 2325/57600 [24:26<9:17:48,  1.65it/s]
  4%|▍         | 2326/57600 [24:27<9:14:49,  1.66it/s]
  4%|▍         | 2327/57600 [24:28<9:22:35,  1.64it/s]
  4%|▍         | 2328/57600 [24:28<9:14:29,  1.66it/s]
  4%|▍         | 2329/57600 [24:29<9:16:13,  1.66it/s]
  4%|▍         | 2330/57600 [24:29<9:26:05,  1.63it/s]
  4%|▍         | 2331/57600 [24:30<9:34:45,  1.60it/s]
  4%|▍         | 2332/57600 [24:31<9:44:54,  1.57it/s]
  4%|▍         | 2333/57600 [24:31<9:37:04,  1.60it/s]
  4%|▍         | 2334/57600 [24:32<9:28:51,  1.62it/s]
  4%|▍         | 2335/57600 [24:33<9:28:26,  1.62it/s]
  4%|▍         | 2336/57600 [24:33<9:47:48,  1.57it/s]
  4%|▍         | 2337/57600 [24:34<9:37:55,  1.59it/s]
  4%|▍         | 2338/57600 [24:34<9:18:40,  1.65it/s]
  4%|▍         | 2339/57600 [24:35<9:36:08,  1.60it/s]
  4%|▍         | 2340/57600 [24:36<9:47:05,  1.57it/s]
                                                      
{'loss': 1.7009, 'learning_rate': 9.66445993031359e-07, 'epoch': 25.83}

  4%|▍         | 2340/57600 [24:36<9:47:05,  1.57it/s]
  4%|▍         | 2341/57600 [24:36<9:46:57,  1.57it/s]
  4%|▍         | 2342/57600 [24:37<9:34:46,  1.60it/s]
  4%|▍         | 2343/57600 [24:38<10:15:00,  1.50it/s]
  4%|▍         | 2344/57600 [24:38<9:48:50,  1.56it/s] 
  4%|▍         | 2345/57600 [24:39<9:48:49,  1.56it/s]
  4%|▍         | 2346/57600 [24:40<9:57:28,  1.54it/s]
  4%|▍         | 2347/57600 [24:40<10:04:18,  1.52it/s]
  4%|▍         | 2348/57600 [24:41<9:45:33,  1.57it/s] 
  4%|▍         | 2349/57600 [24:42<10:21:48,  1.48it/s]
  4%|▍         | 2350/57600 [24:42<10:31:42,  1.46it/s]
  4%|▍         | 2351/57600 [24:43<10:13:16,  1.50it/s]
  4%|▍         | 2352/57600 [24:44<10:01:28,  1.53it/s]
  4%|▍         | 2353/57600 [24:44<9:48:07,  1.57it/s] 
  4%|▍         | 2354/57600 [24:45<9:55:05,  1.55it/s]
  4%|▍         | 2355/57600 [24:46<9:56:18,  1.54it/s]
  4%|▍         | 2356/57600 [24:46<9:59:40,  1.54it/s]
  4%|▍         | 2357/57600 [24:47<9:45:19,  1.57it/s]
  4%|▍         | 2358/57600 [24:47<9:56:29,  1.54it/s]
  4%|▍         | 2359/57600 [24:48<9:52:46,  1.55it/s]
  4%|▍         | 2360/57600 [24:49<9:46:14,  1.57it/s]
                                                      
{'loss': 1.6581, 'learning_rate': 9.661324041811848e-07, 'epoch': 26.05}

  4%|▍         | 2360/57600 [24:49<9:46:14,  1.57it/s]
  4%|▍         | 2361/57600 [24:49<10:05:01,  1.52it/s]
  4%|▍         | 2362/57600 [24:50<10:01:35,  1.53it/s]
  4%|▍         | 2363/57600 [24:51<9:59:41,  1.54it/s] 
  4%|▍         | 2364/57600 [24:51<9:53:25,  1.55it/s]
  4%|▍         | 2365/57600 [24:52<9:44:32,  1.57it/s]
  4%|▍         | 2366/57600 [24:53<9:40:20,  1.59it/s]
  4%|▍         | 2367/57600 [24:53<9:46:30,  1.57it/s]
  4%|▍         | 2368/57600 [24:54<9:39:08,  1.59it/s]
  4%|▍         | 2369/57600 [24:54<9:36:28,  1.60it/s]
  4%|▍         | 2370/57600 [24:55<9:29:07,  1.62it/s]
  4%|▍         | 2371/57600 [24:56<9:39:04,  1.59it/s]
  4%|▍         | 2372/57600 [24:56<9:52:52,  1.55it/s]
  4%|▍         | 2373/57600 [24:57<9:41:22,  1.58it/s]
  4%|▍         | 2374/57600 [24:58<9:54:02,  1.55it/s]
  4%|▍         | 2375/57600 [24:58<10:00:56,  1.53it/s]
  4%|▍         | 2376/57600 [24:59<10:09:23,  1.51it/s]
  4%|▍         | 2377/57600 [25:00<9:43:59,  1.58it/s] 
  4%|▍         | 2378/57600 [25:00<9:59:05,  1.54it/s]
  4%|▍         | 2379/57600 [25:01<9:56:00,  1.54it/s]
  4%|▍         | 2380/57600 [25:02<9:54:26,  1.55it/s]
                                                      
{'loss': 1.6648, 'learning_rate': 9.658188153310104e-07, 'epoch': 26.27}

  4%|▍         | 2380/57600 [25:02<9:54:26,  1.55it/s]
  4%|▍         | 2381/57600 [25:02<9:49:34,  1.56it/s]
  4%|▍         | 2382/57600 [25:03<9:42:26,  1.58it/s]
  4%|▍         | 2383/57600 [25:03<9:44:32,  1.57it/s]
  4%|▍         | 2384/57600 [25:04<9:39:01,  1.59it/s]
  4%|▍         | 2385/57600 [25:05<9:50:35,  1.56it/s]
  4%|▍         | 2386/57600 [25:05<9:46:59,  1.57it/s]
  4%|▍         | 2387/57600 [25:06<9:56:43,  1.54it/s]
  4%|▍         | 2388/57600 [25:07<9:34:34,  1.60it/s]
  4%|▍         | 2389/57600 [25:07<9:35:57,  1.60it/s]
  4%|▍         | 2390/57600 [25:08<9:37:58,  1.59it/s]
  4%|▍         | 2391/57600 [25:08<9:28:34,  1.62it/s]
  4%|▍         | 2392/57600 [25:09<9:19:55,  1.64it/s]
  4%|▍         | 2393/57600 [25:10<9:14:19,  1.66it/s]
  4%|▍         | 2394/57600 [25:10<9:19:47,  1.64it/s]
  4%|▍         | 2395/57600 [25:11<9:38:49,  1.59it/s]
  4%|▍         | 2396/57600 [25:12<9:45:37,  1.57it/s]
  4%|▍         | 2397/57600 [25:12<10:10:31,  1.51it/s]
  4%|▍         | 2398/57600 [25:13<9:56:48,  1.54it/s] 
  4%|▍         | 2399/57600 [25:14<10:00:59,  1.53it/s]
  4%|▍         | 2400/57600 [25:14<10:23:09,  1.48it/s]
                                                       
{'loss': 1.6303, 'learning_rate': 9.65505226480836e-07, 'epoch': 26.49}

  4%|▍         | 2400/57600 [25:14<10:23:09,  1.48it/s]
  4%|▍         | 2401/57600 [25:15<10:17:00,  1.49it/s]
  4%|▍         | 2402/57600 [25:16<9:59:49,  1.53it/s] 
  4%|▍         | 2403/57600 [25:16<9:44:41,  1.57it/s]
  4%|▍         | 2404/57600 [25:17<9:25:06,  1.63it/s]
  4%|▍         | 2405/57600 [25:17<10:03:26,  1.52it/s]
  4%|▍         | 2406/57600 [25:18<9:48:58,  1.56it/s] 
  4%|▍         | 2407/57600 [25:19<9:56:03,  1.54it/s]
  4%|▍         | 2408/57600 [25:19<9:52:02,  1.55it/s]
  4%|▍         | 2409/57600 [25:20<9:58:10,  1.54it/s]
  4%|▍         | 2410/57600 [25:21<9:46:35,  1.57it/s]
  4%|▍         | 2411/57600 [25:21<9:25:31,  1.63it/s]
  4%|▍         | 2412/57600 [25:22<9:24:45,  1.63it/s]
  4%|▍         | 2413/57600 [25:22<9:16:04,  1.65it/s]
  4%|▍         | 2414/57600 [25:23<9:35:53,  1.60it/s]
  4%|▍         | 2415/57600 [25:24<9:29:39,  1.61it/s]
  4%|▍         | 2416/57600 [25:24<9:26:56,  1.62it/s]
  4%|▍         | 2417/57600 [25:25<9:19:42,  1.64it/s]
  4%|▍         | 2418/57600 [25:26<9:18:54,  1.65it/s]
  4%|▍         | 2419/57600 [25:26<9:33:27,  1.60it/s]
  4%|▍         | 2420/57600 [25:27<9:24:37,  1.63it/s]
                                                      
{'loss': 1.7222, 'learning_rate': 9.65191637630662e-07, 'epoch': 26.71}

  4%|▍         | 2420/57600 [25:27<9:24:37,  1.63it/s]
  4%|▍         | 2421/57600 [25:27<9:15:18,  1.66it/s]
  4%|▍         | 2422/57600 [25:28<9:17:57,  1.65it/s]
  4%|▍         | 2423/57600 [25:29<9:14:16,  1.66it/s]
  4%|▍         | 2424/57600 [25:29<9:10:48,  1.67it/s]
  4%|▍         | 2425/57600 [25:30<9:13:26,  1.66it/s]
  4%|▍         | 2426/57600 [25:30<9:06:45,  1.68it/s]
  4%|▍         | 2427/57600 [25:31<9:15:32,  1.66it/s]
  4%|▍         | 2428/57600 [25:32<9:11:15,  1.67it/s]
  4%|▍         | 2429/57600 [25:32<9:27:42,  1.62it/s]
  4%|▍         | 2430/57600 [25:33<9:16:17,  1.65it/s]
  4%|▍         | 2431/57600 [25:33<9:09:07,  1.67it/s]
  4%|▍         | 2432/57600 [25:34<9:17:58,  1.65it/s]
  4%|▍         | 2433/57600 [25:35<9:08:15,  1.68it/s]
  4%|▍         | 2434/57600 [25:35<9:28:47,  1.62it/s]
  4%|▍         | 2435/57600 [25:36<9:58:50,  1.54it/s]
  4%|▍         | 2436/57600 [25:37<9:47:30,  1.56it/s]
  4%|▍         | 2437/57600 [25:37<9:55:41,  1.54it/s]
  4%|▍         | 2438/57600 [25:38<9:55:39,  1.54it/s]
  4%|▍         | 2439/57600 [25:38<9:37:38,  1.59it/s]
  4%|▍         | 2440/57600 [25:39<9:35:21,  1.60it/s]
                                                      
{'loss': 1.7164, 'learning_rate': 9.648780487804878e-07, 'epoch': 26.93}

  4%|▍         | 2440/57600 [25:39<9:35:21,  1.60it/s]
  4%|▍         | 2441/57600 [25:40<9:36:49,  1.59it/s]
  4%|▍         | 2442/57600 [25:40<9:28:10,  1.62it/s]
  4%|▍         | 2443/57600 [25:41<9:16:57,  1.65it/s]
  4%|▍         | 2444/57600 [25:41<9:19:38,  1.64it/s]
  4%|▍         | 2445/57600 [25:42<9:24:34,  1.63it/s]
  4%|▍         | 2446/57600 [25:43<9:30:05,  1.61it/s]
  4%|▍         | 2447/57600 [25:44<10:13:09,  1.50it/s]
  4%|▍         | 2448/57600 [25:44<9:47:16,  1.57it/s] 
  4%|▍         | 2449/57600 [25:45<9:44:11,  1.57it/s]
  4%|▍         | 2450/57600 [25:45<9:40:52,  1.58it/s]
  4%|▍         | 2451/57600 [25:46<9:56:19,  1.54it/s]
  4%|▍         | 2452/57600 [25:47<10:04:52,  1.52it/s]
  4%|▍         | 2453/57600 [25:47<9:57:09,  1.54it/s] 
  4%|▍         | 2454/57600 [25:48<9:43:57,  1.57it/s]
  4%|▍         | 2455/57600 [25:49<9:58:48,  1.53it/s]
  4%|▍         | 2456/57600 [25:49<9:38:22,  1.59it/s]
  4%|▍         | 2457/57600 [25:50<9:45:50,  1.57it/s]
  4%|▍         | 2458/57600 [25:51<9:46:54,  1.57it/s]
  4%|▍         | 2459/57600 [25:51<9:32:55,  1.60it/s]
  4%|▍         | 2460/57600 [25:52<9:40:26,  1.58it/s]
                                                      
{'loss': 1.6894, 'learning_rate': 9.645644599303136e-07, 'epoch': 27.15}

  4%|▍         | 2460/57600 [25:52<9:40:26,  1.58it/s]
  4%|▍         | 2461/57600 [25:52<9:48:07,  1.56it/s]
  4%|▍         | 2462/57600 [25:53<9:29:12,  1.61it/s]
  4%|▍         | 2463/57600 [25:54<9:46:46,  1.57it/s]
  4%|▍         | 2464/57600 [25:54<9:32:14,  1.61it/s]
  4%|▍         | 2465/57600 [25:55<9:31:20,  1.61it/s]
  4%|▍         | 2466/57600 [25:56<9:35:51,  1.60it/s]
  4%|▍         | 2467/57600 [25:56<9:37:37,  1.59it/s]
  4%|▍         | 2468/57600 [25:57<9:25:02,  1.63it/s]
  4%|▍         | 2469/57600 [25:57<9:28:07,  1.62it/s]
  4%|▍         | 2470/57600 [25:58<9:36:52,  1.59it/s]
  4%|▍         | 2471/57600 [25:59<9:44:05,  1.57it/s]
  4%|▍         | 2472/57600 [25:59<9:33:13,  1.60it/s]
  4%|▍         | 2473/57600 [26:00<9:40:59,  1.58it/s]
  4%|▍         | 2474/57600 [26:01<9:31:52,  1.61it/s]
  4%|▍         | 2475/57600 [26:01<9:18:37,  1.64it/s]
  4%|▍         | 2476/57600 [26:02<9:31:57,  1.61it/s]
  4%|▍         | 2477/57600 [26:02<9:17:17,  1.65it/s]
  4%|▍         | 2478/57600 [26:03<9:36:21,  1.59it/s]
  4%|▍         | 2479/57600 [26:04<9:42:50,  1.58it/s]
  4%|▍         | 2480/57600 [26:04<9:44:32,  1.57it/s]
                                                      
{'loss': 1.6904, 'learning_rate': 9.642508710801393e-07, 'epoch': 27.37}

  4%|▍         | 2480/57600 [26:04<9:44:32,  1.57it/s]
  4%|▍         | 2481/57600 [26:05<9:35:31,  1.60it/s]
  4%|▍         | 2482/57600 [26:06<9:37:47,  1.59it/s]
  4%|▍         | 2483/57600 [26:06<9:53:38,  1.55it/s]
  4%|▍         | 2484/57600 [26:07<10:06:08,  1.52it/s]
  4%|▍         | 2485/57600 [26:08<9:55:54,  1.54it/s] 
  4%|▍         | 2486/57600 [26:08<9:45:00,  1.57it/s]
  4%|▍         | 2487/57600 [26:09<9:40:47,  1.58it/s]
  4%|▍         | 2488/57600 [26:09<9:20:10,  1.64it/s]
  4%|▍         | 2489/57600 [26:10<9:35:26,  1.60it/s]
  4%|▍         | 2490/57600 [26:11<9:34:12,  1.60it/s]
  4%|▍         | 2491/57600 [26:11<9:21:58,  1.63it/s]
  4%|▍         | 2492/57600 [26:12<9:26:20,  1.62it/s]
  4%|▍         | 2493/57600 [26:12<9:12:41,  1.66it/s]
  4%|▍         | 2494/57600 [26:13<9:13:22,  1.66it/s]
  4%|▍         | 2495/57600 [26:14<9:23:28,  1.63it/s]
  4%|▍         | 2496/57600 [26:14<9:15:38,  1.65it/s]
  4%|▍         | 2497/57600 [26:15<9:34:43,  1.60it/s]
  4%|▍         | 2498/57600 [26:15<9:28:28,  1.62it/s]
  4%|▍         | 2499/57600 [26:16<9:30:28,  1.61it/s]
  4%|▍         | 2500/57600 [26:17<9:44:42,  1.57it/s]
                                                      
{'loss': 1.6133, 'learning_rate': 9.639372822299651e-07, 'epoch': 27.59}

  4%|▍         | 2500/57600 [26:17<9:44:42,  1.57it/s]
  4%|▍         | 2501/57600 [26:17<9:36:27,  1.59it/s]
  4%|▍         | 2502/57600 [26:18<9:43:19,  1.57it/s]
  4%|▍         | 2503/57600 [26:19<9:48:24,  1.56it/s]
  4%|▍         | 2504/57600 [26:19<9:40:19,  1.58it/s]
  4%|▍         | 2505/57600 [26:20<9:46:58,  1.56it/s]
  4%|▍         | 2506/57600 [26:21<9:44:12,  1.57it/s]
  4%|▍         | 2507/57600 [26:21<9:36:18,  1.59it/s]
  4%|▍         | 2508/57600 [26:22<9:29:56,  1.61it/s]
  4%|▍         | 2509/57600 [26:22<9:45:57,  1.57it/s]
  4%|▍         | 2510/57600 [26:23<9:35:36,  1.60it/s]
  4%|▍         | 2511/57600 [26:24<9:41:05,  1.58it/s]
  4%|▍         | 2512/57600 [26:24<9:47:37,  1.56it/s]
  4%|▍         | 2513/57600 [26:25<9:36:29,  1.59it/s]
  4%|▍         | 2514/57600 [26:26<9:45:44,  1.57it/s]
  4%|▍         | 2515/57600 [26:26<9:48:19,  1.56it/s]
  4%|▍         | 2516/57600 [26:27<9:46:52,  1.56it/s]
  4%|▍         | 2517/57600 [26:28<9:42:17,  1.58it/s]
  4%|▍         | 2518/57600 [26:28<9:46:07,  1.57it/s]
  4%|▍         | 2519/57600 [26:29<9:44:29,  1.57it/s]
  4%|▍         | 2520/57600 [26:29<9:45:21,  1.57it/s]
                                                      
{'loss': 1.6445, 'learning_rate': 9.636236933797908e-07, 'epoch': 27.81}

  4%|▍         | 2520/57600 [26:29<9:45:21,  1.57it/s]
  4%|▍         | 2521/57600 [26:30<9:39:07,  1.59it/s]
  4%|▍         | 2522/57600 [26:31<9:49:57,  1.56it/s]
  4%|▍         | 2523/57600 [26:31<9:33:52,  1.60it/s]
  4%|▍         | 2524/57600 [26:32<9:59:17,  1.53it/s]
  4%|▍         | 2525/57600 [26:33<10:05:25,  1.52it/s]
  4%|▍         | 2526/57600 [26:33<10:14:51,  1.49it/s]
  4%|▍         | 2527/57600 [26:34<9:58:42,  1.53it/s] 
  4%|▍         | 2528/57600 [26:35<9:52:02,  1.55it/s]
  4%|▍         | 2529/57600 [26:35<9:46:37,  1.56it/s]
  4%|▍         | 2530/57600 [26:36<9:50:22,  1.55it/s]
  4%|▍         | 2531/57600 [26:37<9:39:33,  1.58it/s]
  4%|▍         | 2532/57600 [26:37<9:45:26,  1.57it/s]
  4%|▍         | 2533/57600 [26:38<9:35:57,  1.59it/s]
  4%|▍         | 2534/57600 [26:38<9:35:13,  1.60it/s]
  4%|▍         | 2535/57600 [26:39<9:26:33,  1.62it/s]
  4%|▍         | 2536/57600 [26:40<9:19:22,  1.64it/s]
  4%|▍         | 2537/57600 [26:40<9:32:51,  1.60it/s]
  4%|▍         | 2538/57600 [26:41<9:20:13,  1.64it/s]
  4%|▍         | 2539/57600 [26:41<9:31:00,  1.61it/s]
  4%|▍         | 2540/57600 [26:42<9:23:08,  1.63it/s]
                                                      
{'loss': 1.6421, 'learning_rate': 9.633101045296166e-07, 'epoch': 28.04}

  4%|▍         | 2540/57600 [26:42<9:23:08,  1.63it/s]
  4%|▍         | 2541/57600 [26:43<9:22:59,  1.63it/s]
  4%|▍         | 2542/57600 [26:43<9:48:24,  1.56it/s]
  4%|▍         | 2543/57600 [26:44<9:38:08,  1.59it/s]
  4%|▍         | 2544/57600 [26:45<9:55:47,  1.54it/s]
  4%|▍         | 2545/57600 [26:45<9:57:51,  1.53it/s]
  4%|▍         | 2546/57600 [26:46<10:07:22,  1.51it/s]
  4%|▍         | 2547/57600 [26:47<10:19:59,  1.48it/s]
  4%|▍         | 2548/57600 [26:47<9:57:29,  1.54it/s] 
  4%|▍         | 2549/57600 [26:48<9:54:20,  1.54it/s]
  4%|▍         | 2550/57600 [26:49<9:40:29,  1.58it/s]
  4%|▍         | 2551/57600 [26:49<9:43:19,  1.57it/s]
  4%|▍         | 2552/57600 [26:50<9:27:50,  1.62it/s]
  4%|▍         | 2553/57600 [26:50<9:42:33,  1.57it/s]
  4%|▍         | 2554/57600 [26:51<9:47:19,  1.56it/s]
  4%|▍         | 2555/57600 [26:52<9:42:47,  1.57it/s]
  4%|▍         | 2556/57600 [26:52<10:01:38,  1.52it/s]
  4%|▍         | 2557/57600 [26:53<9:48:52,  1.56it/s] 
  4%|▍         | 2558/57600 [26:54<9:53:25,  1.55it/s]
  4%|▍         | 2559/57600 [26:54<9:49:14,  1.56it/s]
  4%|▍         | 2560/57600 [26:55<9:39:46,  1.58it/s]
                                                      
{'loss': 1.672, 'learning_rate': 9.629965156794425e-07, 'epoch': 28.26}

  4%|▍         | 2560/57600 [26:55<9:39:46,  1.58it/s]
  4%|▍         | 2561/57600 [26:56<9:32:42,  1.60it/s]
  4%|▍         | 2562/57600 [26:56<9:39:49,  1.58it/s]
  4%|▍         | 2563/57600 [26:57<9:20:36,  1.64it/s]
  4%|▍         | 2564/57600 [26:57<9:33:07,  1.60it/s]
  4%|▍         | 2565/57600 [26:58<9:28:29,  1.61it/s]
  4%|▍         | 2566/57600 [26:59<9:30:13,  1.61it/s]
  4%|▍         | 2567/57600 [26:59<9:30:10,  1.61it/s]
  4%|▍         | 2568/57600 [27:00<9:35:38,  1.59it/s]
  4%|▍         | 2569/57600 [27:01<9:39:22,  1.58it/s]
  4%|▍         | 2570/57600 [27:01<9:26:43,  1.62it/s]
  4%|▍         | 2571/57600 [27:02<9:31:53,  1.60it/s]
  4%|▍         | 2572/57600 [27:02<9:38:08,  1.59it/s]
  4%|▍         | 2573/57600 [27:03<9:51:21,  1.55it/s]
  4%|▍         | 2574/57600 [27:04<10:10:34,  1.50it/s]
  4%|▍         | 2575/57600 [27:05<10:07:18,  1.51it/s]
  4%|▍         | 2576/57600 [27:05<9:44:45,  1.57it/s] 
  4%|▍         | 2577/57600 [27:06<9:40:04,  1.58it/s]
  4%|▍         | 2578/57600 [27:06<9:42:19,  1.57it/s]
  4%|▍         | 2579/57600 [27:07<9:52:20,  1.55it/s]
  4%|▍         | 2580/57600 [27:08<9:46:18,  1.56it/s]
                                                      
{'loss': 1.6592, 'learning_rate': 9.626829268292684e-07, 'epoch': 28.48}

  4%|▍         | 2580/57600 [27:08<9:46:18,  1.56it/s]
  4%|▍         | 2581/57600 [27:08<9:36:08,  1.59it/s]
  4%|▍         | 2582/57600 [27:09<9:32:47,  1.60it/s]
  4%|▍         | 2583/57600 [27:09<9:21:33,  1.63it/s]
  4%|▍         | 2584/57600 [27:10<9:16:37,  1.65it/s]
  4%|▍         | 2585/57600 [27:11<9:40:10,  1.58it/s]
  4%|▍         | 2586/57600 [27:11<9:43:09,  1.57it/s]
  4%|▍         | 2587/57600 [27:12<10:05:51,  1.51it/s]
  4%|▍         | 2588/57600 [27:13<9:54:28,  1.54it/s] 
  4%|▍         | 2589/57600 [27:13<9:34:33,  1.60it/s]
  4%|▍         | 2590/57600 [27:14<9:23:19,  1.63it/s]
  4%|▍         | 2591/57600 [27:14<9:17:44,  1.64it/s]
  4%|▍         | 2592/57600 [27:15<9:14:42,  1.65it/s]
  5%|▍         | 2593/57600 [27:16<9:24:40,  1.62it/s]
  5%|▍         | 2594/57600 [27:16<9:41:01,  1.58it/s]
  5%|▍         | 2595/57600 [27:17<9:35:21,  1.59it/s]
  5%|▍         | 2596/57600 [27:18<9:28:37,  1.61it/s]
  5%|▍         | 2597/57600 [27:18<9:54:31,  1.54it/s]
  5%|▍         | 2598/57600 [27:19<9:33:35,  1.60it/s]
  5%|▍         | 2599/57600 [27:19<9:19:28,  1.64it/s]
  5%|▍         | 2600/57600 [27:20<9:25:35,  1.62it/s]
                                                      
{'loss': 1.649, 'learning_rate': 9.62369337979094e-07, 'epoch': 28.7}

  5%|▍         | 2600/57600 [27:20<9:25:35,  1.62it/s]
  5%|▍         | 2601/57600 [27:21<9:20:20,  1.64it/s]
  5%|▍         | 2602/57600 [27:21<9:16:15,  1.65it/s]
  5%|▍         | 2603/57600 [27:22<9:04:03,  1.68it/s]
  5%|▍         | 2604/57600 [27:23<9:33:05,  1.60it/s]
  5%|▍         | 2605/57600 [27:23<9:31:32,  1.60it/s]
  5%|▍         | 2606/57600 [27:24<9:29:25,  1.61it/s]
  5%|▍         | 2607/57600 [27:24<9:36:56,  1.59it/s]
  5%|▍         | 2608/57600 [27:25<10:10:05,  1.50it/s]
  5%|▍         | 2609/57600 [27:26<9:55:33,  1.54it/s] 
  5%|▍         | 2610/57600 [27:26<9:50:08,  1.55it/s]
  5%|▍         | 2611/57600 [27:27<9:40:32,  1.58it/s]
  5%|▍         | 2612/57600 [27:28<9:30:42,  1.61it/s]
  5%|▍         | 2613/57600 [27:28<9:31:44,  1.60it/s]
  5%|▍         | 2614/57600 [27:29<9:35:42,  1.59it/s]
  5%|▍         | 2615/57600 [27:30<9:28:44,  1.61it/s]
  5%|▍         | 2616/57600 [27:30<9:33:51,  1.60it/s]
  5%|▍         | 2617/57600 [27:31<9:38:18,  1.58it/s]
  5%|▍         | 2618/57600 [27:31<9:50:07,  1.55it/s]
  5%|▍         | 2619/57600 [27:32<9:39:37,  1.58it/s]
  5%|▍         | 2620/57600 [27:33<9:43:23,  1.57it/s]
                                                      
{'loss': 1.6667, 'learning_rate': 9.620557491289199e-07, 'epoch': 28.92}

  5%|▍         | 2620/57600 [27:33<9:43:23,  1.57it/s]
  5%|▍         | 2621/57600 [27:33<9:27:14,  1.62it/s]
  5%|▍         | 2622/57600 [27:34<9:21:32,  1.63it/s]
  5%|▍         | 2623/57600 [27:35<9:49:08,  1.56it/s]
  5%|▍         | 2624/57600 [27:35<9:39:46,  1.58it/s]
  5%|▍         | 2625/57600 [27:36<9:44:50,  1.57it/s]
  5%|▍         | 2626/57600 [27:37<9:46:53,  1.56it/s]
  5%|▍         | 2627/57600 [27:37<9:23:27,  1.63it/s]
  5%|▍         | 2628/57600 [27:38<9:48:51,  1.56it/s]
  5%|▍         | 2629/57600 [27:38<9:34:08,  1.60it/s]
  5%|▍         | 2630/57600 [27:39<9:40:39,  1.58it/s]
  5%|▍         | 2631/57600 [27:40<9:37:02,  1.59it/s]
  5%|▍         | 2632/57600 [27:40<9:48:22,  1.56it/s]
  5%|▍         | 2633/57600 [27:41<9:37:46,  1.59it/s]
  5%|▍         | 2634/57600 [27:42<9:37:03,  1.59it/s]
  5%|▍         | 2635/57600 [27:42<9:34:43,  1.59it/s]
  5%|▍         | 2636/57600 [27:43<9:25:21,  1.62it/s]
  5%|▍         | 2637/57600 [27:43<9:28:48,  1.61it/s]
  5%|▍         | 2638/57600 [27:44<9:25:57,  1.62it/s]
  5%|▍         | 2639/57600 [27:45<9:35:20,  1.59it/s]
  5%|▍         | 2640/57600 [27:45<9:39:07,  1.58it/s]
                                                      
{'loss': 1.6172, 'learning_rate': 9.617421602787455e-07, 'epoch': 29.14}

  5%|▍         | 2640/57600 [27:45<9:39:07,  1.58it/s]
  5%|▍         | 2641/57600 [27:46<9:37:14,  1.59it/s]
  5%|▍         | 2642/57600 [27:46<9:22:20,  1.63it/s]
  5%|▍         | 2643/57600 [27:47<9:12:54,  1.66it/s]
  5%|▍         | 2644/57600 [27:48<9:28:38,  1.61it/s]
  5%|▍         | 2645/57600 [27:48<9:27:28,  1.61it/s]
  5%|▍         | 2646/57600 [27:49<9:18:21,  1.64it/s]
  5%|▍         | 2647/57600 [27:50<9:38:28,  1.58it/s]
  5%|▍         | 2648/57600 [27:50<9:36:39,  1.59it/s]
  5%|▍         | 2649/57600 [27:51<9:43:30,  1.57it/s]
  5%|▍         | 2650/57600 [27:52<10:07:41,  1.51it/s]
  5%|▍         | 2651/57600 [27:52<9:47:16,  1.56it/s] 
  5%|▍         | 2652/57600 [27:53<10:00:47,  1.52it/s]
  5%|▍         | 2653/57600 [27:53<9:34:15,  1.59it/s] 
  5%|▍         | 2654/57600 [27:54<9:16:57,  1.64it/s]
  5%|▍         | 2655/57600 [27:55<9:31:59,  1.60it/s]
  5%|▍         | 2656/57600 [27:55<9:38:55,  1.58it/s]
  5%|▍         | 2657/57600 [27:56<9:28:33,  1.61it/s]
  5%|▍         | 2658/57600 [27:57<9:39:45,  1.58it/s]
  5%|▍         | 2659/57600 [27:57<9:32:30,  1.60it/s]
  5%|▍         | 2660/57600 [27:58<9:32:32,  1.60it/s]
                                                      
{'loss': 1.6696, 'learning_rate': 9.614285714285714e-07, 'epoch': 29.36}

  5%|▍         | 2660/57600 [27:58<9:32:32,  1.60it/s]
  5%|▍         | 2661/57600 [27:58<9:19:17,  1.64it/s]
  5%|▍         | 2662/57600 [27:59<9:29:54,  1.61it/s]
  5%|▍         | 2663/57600 [28:00<9:22:39,  1.63it/s]
  5%|▍         | 2664/57600 [28:00<9:12:54,  1.66it/s]
  5%|▍         | 2665/57600 [28:01<9:17:17,  1.64it/s]
  5%|▍         | 2666/57600 [28:02<9:35:42,  1.59it/s]
  5%|▍         | 2667/57600 [28:02<9:55:50,  1.54it/s]
  5%|▍         | 2668/57600 [28:03<9:32:55,  1.60it/s]
  5%|▍         | 2669/57600 [28:03<9:33:20,  1.60it/s]
  5%|▍         | 2670/57600 [28:04<9:46:09,  1.56it/s]
  5%|▍         | 2671/57600 [28:05<9:34:25,  1.59it/s]
  5%|▍         | 2672/57600 [28:05<9:24:39,  1.62it/s]
  5%|▍         | 2673/57600 [28:06<9:25:06,  1.62it/s]
  5%|▍         | 2674/57600 [28:07<9:25:45,  1.62it/s]
  5%|▍         | 2675/57600 [28:07<9:22:10,  1.63it/s]
  5%|▍         | 2676/57600 [28:08<9:19:26,  1.64it/s]
  5%|▍         | 2677/57600 [28:08<9:24:34,  1.62it/s]
  5%|▍         | 2678/57600 [28:09<9:26:39,  1.62it/s]
  5%|▍         | 2679/57600 [28:10<9:35:27,  1.59it/s]
  5%|▍         | 2680/57600 [28:10<9:23:28,  1.62it/s]
                                                      
{'loss': 1.7091, 'learning_rate': 9.611149825783972e-07, 'epoch': 29.58}

  5%|▍         | 2680/57600 [28:10<9:23:28,  1.62it/s]
  5%|▍         | 2681/57600 [28:11<9:26:02,  1.62it/s]
  5%|▍         | 2682/57600 [28:12<9:41:27,  1.57it/s]
  5%|▍         | 2683/57600 [28:12<9:28:32,  1.61it/s]
  5%|▍         | 2684/57600 [28:13<9:49:34,  1.55it/s]
  5%|▍         | 2685/57600 [28:13<9:57:06,  1.53it/s]
  5%|▍         | 2686/57600 [28:14<10:17:13,  1.48it/s]
  5%|▍         | 2687/57600 [28:15<10:08:10,  1.50it/s]
  5%|▍         | 2688/57600 [28:15<9:41:41,  1.57it/s] 
  5%|▍         | 2689/57600 [28:16<9:39:14,  1.58it/s]
  5%|▍         | 2690/57600 [28:17<9:57:13,  1.53it/s]
  5%|▍         | 2691/57600 [28:17<9:38:35,  1.58it/s]
  5%|▍         | 2692/57600 [28:18<9:41:07,  1.57it/s]
  5%|▍         | 2693/57600 [28:19<9:31:26,  1.60it/s]
  5%|▍         | 2694/57600 [28:19<9:22:59,  1.63it/s]
  5%|▍         | 2695/57600 [28:20<9:33:04,  1.60it/s]
  5%|▍         | 2696/57600 [28:20<9:19:17,  1.64it/s]
  5%|▍         | 2697/57600 [28:21<9:31:47,  1.60it/s]
  5%|▍         | 2698/57600 [28:22<9:48:32,  1.55it/s]
  5%|▍         | 2699/57600 [28:22<9:49:59,  1.55it/s]
  5%|▍         | 2700/57600 [28:23<9:53:24,  1.54it/s]
                                                      
{'loss': 1.6111, 'learning_rate': 9.60801393728223e-07, 'epoch': 29.8}

  5%|▍         | 2700/57600 [28:23<9:53:24,  1.54it/s]
  5%|▍         | 2701/57600 [28:24<10:09:10,  1.50it/s]
  5%|▍         | 2702/57600 [28:24<10:07:32,  1.51it/s]
  5%|▍         | 2703/57600 [28:25<9:55:16,  1.54it/s] 
  5%|▍         | 2704/57600 [28:26<9:45:01,  1.56it/s]
  5%|▍         | 2705/57600 [28:26<9:51:47,  1.55it/s]
  5%|▍         | 2706/57600 [28:27<9:30:42,  1.60it/s]
  5%|▍         | 2707/57600 [28:27<9:28:21,  1.61it/s]
  5%|▍         | 2708/57600 [28:28<9:42:19,  1.57it/s]
  5%|▍         | 2709/57600 [28:29<10:07:07,  1.51it/s]
  5%|▍         | 2710/57600 [28:30<10:01:26,  1.52it/s]
  5%|▍         | 2711/57600 [28:30<9:50:08,  1.55it/s] 
  5%|▍         | 2712/57600 [28:31<9:49:45,  1.55it/s]
  5%|▍         | 2713/57600 [28:31<9:55:02,  1.54it/s]
  5%|▍         | 2714/57600 [28:32<10:02:11,  1.52it/s]
  5%|▍         | 2715/57600 [28:33<9:48:37,  1.55it/s] 
  5%|▍         | 2716/57600 [28:33<9:45:15,  1.56it/s]
  5%|▍         | 2717/57600 [28:34<9:45:45,  1.56it/s]
  5%|▍         | 2718/57600 [28:35<9:30:17,  1.60it/s]
  5%|▍         | 2719/57600 [28:35<9:45:16,  1.56it/s]
  5%|▍         | 2720/57600 [28:36<9:44:42,  1.56it/s]
                                                      
{'loss': 1.6274, 'learning_rate': 9.604878048780487e-07, 'epoch': 30.02}

  5%|▍         | 2720/57600 [28:36<9:44:42,  1.56it/s]
  5%|▍         | 2721/57600 [28:36<9:33:25,  1.60it/s]
  5%|▍         | 2722/57600 [28:37<9:21:33,  1.63it/s]
  5%|▍         | 2723/57600 [28:38<9:28:24,  1.61it/s]
  5%|▍         | 2724/57600 [28:38<9:38:57,  1.58it/s]
  5%|▍         | 2725/57600 [28:39<9:34:02,  1.59it/s]
  5%|▍         | 2726/57600 [28:40<9:56:56,  1.53it/s]
  5%|▍         | 2727/57600 [28:40<10:06:38,  1.51it/s]
  5%|▍         | 2728/57600 [28:41<9:50:05,  1.55it/s] 
  5%|▍         | 2729/57600 [28:42<9:53:58,  1.54it/s]
  5%|▍         | 2730/57600 [28:42<9:52:54,  1.54it/s]
  5%|▍         | 2731/57600 [28:43<9:38:02,  1.58it/s]
  5%|▍         | 2732/57600 [28:44<9:57:31,  1.53it/s]
  5%|▍         | 2733/57600 [28:44<9:59:05,  1.53it/s]
  5%|▍         | 2734/57600 [28:45<10:17:13,  1.48it/s]
  5%|▍         | 2735/57600 [28:46<10:05:14,  1.51it/s]
  5%|▍         | 2736/57600 [28:46<9:59:40,  1.52it/s] 
  5%|▍         | 2737/57600 [28:47<10:06:46,  1.51it/s]
  5%|▍         | 2738/57600 [28:48<10:05:31,  1.51it/s]
  5%|▍         | 2739/57600 [28:48<9:49:39,  1.55it/s] 
  5%|▍         | 2740/57600 [28:49<9:47:25,  1.56it/s]
                                                      
{'loss': 1.6186, 'learning_rate': 9.601742160278746e-07, 'epoch': 30.24}

  5%|▍         | 2740/57600 [28:49<9:47:25,  1.56it/s]
  5%|▍         | 2741/57600 [28:49<9:40:49,  1.57it/s]
  5%|▍         | 2742/57600 [28:50<9:45:24,  1.56it/s]
  5%|▍         | 2743/57600 [28:51<9:45:01,  1.56it/s]
  5%|▍         | 2744/57600 [28:51<9:47:00,  1.56it/s]
  5%|▍         | 2745/57600 [28:52<9:37:39,  1.58it/s]
  5%|▍         | 2746/57600 [28:53<9:32:40,  1.60it/s]
  5%|▍         | 2747/57600 [28:53<9:34:03,  1.59it/s]
  5%|▍         | 2748/57600 [28:54<9:27:10,  1.61it/s]
  5%|▍         | 2749/57600 [28:54<9:28:58,  1.61it/s]
  5%|▍         | 2750/57600 [28:55<9:14:32,  1.65it/s]
  5%|▍         | 2751/57600 [28:56<9:14:51,  1.65it/s]
  5%|▍         | 2752/57600 [28:56<9:24:05,  1.62it/s]
  5%|▍         | 2753/57600 [28:57<9:28:48,  1.61it/s]
  5%|▍         | 2754/57600 [28:58<9:41:57,  1.57it/s]
  5%|▍         | 2755/57600 [28:58<9:39:31,  1.58it/s]
  5%|▍         | 2756/57600 [28:59<9:45:15,  1.56it/s]
  5%|▍         | 2757/57600 [29:00<9:58:37,  1.53it/s]
  5%|▍         | 2758/57600 [29:00<10:02:21,  1.52it/s]
  5%|▍         | 2759/57600 [29:01<9:38:13,  1.58it/s] 
  5%|▍         | 2760/57600 [29:01<9:20:25,  1.63it/s]
                                                      
{'loss': 1.6336, 'learning_rate': 9.598606271777002e-07, 'epoch': 30.46}

  5%|▍         | 2760/57600 [29:01<9:20:25,  1.63it/s]
  5%|▍         | 2761/57600 [29:02<9:06:46,  1.67it/s]
  5%|▍         | 2762/57600 [29:03<9:11:21,  1.66it/s]
  5%|▍         | 2763/57600 [29:03<9:06:26,  1.67it/s]
  5%|▍         | 2764/57600 [29:04<9:31:45,  1.60it/s]
  5%|▍         | 2765/57600 [29:04<9:42:24,  1.57it/s]
  5%|▍         | 2766/57600 [29:05<9:27:24,  1.61it/s]
  5%|▍         | 2767/57600 [29:06<9:34:20,  1.59it/s]
  5%|▍         | 2768/57600 [29:06<9:28:28,  1.61it/s]
  5%|▍         | 2769/57600 [29:07<10:08:30,  1.50it/s]
  5%|▍         | 2770/57600 [29:08<9:58:54,  1.53it/s] 
  5%|▍         | 2771/57600 [29:08<9:45:48,  1.56it/s]
  5%|▍         | 2772/57600 [29:09<9:38:32,  1.58it/s]
  5%|▍         | 2773/57600 [29:10<9:40:56,  1.57it/s]
  5%|▍         | 2774/57600 [29:10<9:42:24,  1.57it/s]
  5%|▍         | 2775/57600 [29:11<9:35:55,  1.59it/s]
  5%|▍         | 2776/57600 [29:11<9:21:46,  1.63it/s]
  5%|▍         | 2777/57600 [29:12<9:25:06,  1.62it/s]
  5%|▍         | 2778/57600 [29:13<9:33:33,  1.59it/s]
  5%|▍         | 2779/57600 [29:13<9:23:09,  1.62it/s]
  5%|▍         | 2780/57600 [29:14<9:15:55,  1.64it/s]
                                                      
{'loss': 1.6414, 'learning_rate': 9.59547038327526e-07, 'epoch': 30.68}

  5%|▍         | 2780/57600 [29:14<9:15:55,  1.64it/s]
  5%|▍         | 2781/57600 [29:15<9:32:27,  1.60it/s]
  5%|▍         | 2782/57600 [29:15<9:17:49,  1.64it/s]
  5%|▍         | 2783/57600 [29:16<9:09:15,  1.66it/s]
  5%|▍         | 2784/57600 [29:16<9:23:06,  1.62it/s]
  5%|▍         | 2785/57600 [29:17<9:22:20,  1.62it/s]
  5%|▍         | 2786/57600 [29:18<9:16:46,  1.64it/s]
  5%|▍         | 2787/57600 [29:18<9:42:21,  1.57it/s]
  5%|▍         | 2788/57600 [29:19<9:36:13,  1.59it/s]
  5%|▍         | 2789/57600 [29:19<9:30:21,  1.60it/s]
  5%|▍         | 2790/57600 [29:20<9:40:32,  1.57it/s]
  5%|▍         | 2791/57600 [29:21<9:21:03,  1.63it/s]
  5%|▍         | 2792/57600 [29:21<9:26:36,  1.61it/s]
  5%|▍         | 2793/57600 [29:22<9:23:01,  1.62it/s]
  5%|▍         | 2794/57600 [29:23<9:36:06,  1.59it/s]
  5%|▍         | 2795/57600 [29:23<9:31:45,  1.60it/s]
  5%|▍         | 2796/57600 [29:24<9:26:37,  1.61it/s]
  5%|▍         | 2797/57600 [29:25<9:45:44,  1.56it/s]
  5%|▍         | 2798/57600 [29:25<9:36:13,  1.59it/s]
  5%|▍         | 2799/57600 [29:26<9:43:42,  1.56it/s]
  5%|▍         | 2800/57600 [29:26<9:40:56,  1.57it/s]
                                                      
{'loss': 1.6628, 'learning_rate': 9.59233449477352e-07, 'epoch': 30.91}

  5%|▍         | 2800/57600 [29:26<9:40:56,  1.57it/s]
  5%|▍         | 2801/57600 [29:27<9:50:26,  1.55it/s]
  5%|▍         | 2802/57600 [29:28<9:33:03,  1.59it/s]
  5%|▍         | 2803/57600 [29:28<9:22:27,  1.62it/s]
  5%|▍         | 2804/57600 [29:29<9:34:41,  1.59it/s]
  5%|▍         | 2805/57600 [29:30<9:43:45,  1.56it/s]
  5%|▍         | 2806/57600 [29:30<10:00:43,  1.52it/s]
  5%|▍         | 2807/57600 [29:31<9:57:00,  1.53it/s] 
  5%|▍         | 2808/57600 [29:32<9:49:29,  1.55it/s]
  5%|▍         | 2809/57600 [29:32<9:57:54,  1.53it/s]
  5%|▍         | 2810/57600 [29:33<9:39:12,  1.58it/s]
  5%|▍         | 2811/57600 [29:33<9:42:05,  1.57it/s]
  5%|▍         | 2812/57600 [29:34<9:45:29,  1.56it/s]
  5%|▍         | 2813/57600 [29:35<10:06:00,  1.51it/s]
  5%|▍         | 2814/57600 [29:35<10:03:43,  1.51it/s]
  5%|▍         | 2815/57600 [29:36<9:58:18,  1.53it/s] 
  5%|▍         | 2816/57600 [29:37<10:12:30,  1.49it/s]
  5%|▍         | 2817/57600 [29:37<9:47:27,  1.55it/s] 
  5%|▍         | 2818/57600 [29:38<9:36:28,  1.58it/s]
  5%|▍         | 2819/57600 [29:39<9:40:17,  1.57it/s]
  5%|▍         | 2820/57600 [29:39<9:40:32,  1.57it/s]
                                                      
{'loss': 1.6092, 'learning_rate': 9.589198606271776e-07, 'epoch': 31.13}

  5%|▍         | 2820/57600 [29:39<9:40:32,  1.57it/s]
  5%|▍         | 2821/57600 [29:40<9:32:48,  1.59it/s]
  5%|▍         | 2822/57600 [29:41<9:26:25,  1.61it/s]
  5%|▍         | 2823/57600 [29:41<9:41:22,  1.57it/s]
  5%|▍         | 2824/57600 [29:42<9:30:07,  1.60it/s]
  5%|▍         | 2825/57600 [29:42<9:38:23,  1.58it/s]
  5%|▍         | 2826/57600 [29:43<9:29:28,  1.60it/s]
  5%|▍         | 2827/57600 [29:44<9:34:05,  1.59it/s]
  5%|▍         | 2828/57600 [29:44<9:25:03,  1.62it/s]
  5%|▍         | 2829/57600 [29:45<9:20:57,  1.63it/s]
  5%|▍         | 2830/57600 [29:46<9:22:33,  1.62it/s]
  5%|▍         | 2831/57600 [29:46<9:25:32,  1.61it/s]
  5%|▍         | 2832/57600 [29:47<9:21:42,  1.63it/s]
  5%|▍         | 2833/57600 [29:47<9:40:04,  1.57it/s]
  5%|▍         | 2834/57600 [29:48<9:49:03,  1.55it/s]
  5%|▍         | 2835/57600 [29:49<9:48:30,  1.55it/s]
  5%|▍         | 2836/57600 [29:50<10:34:34,  1.44it/s]
  5%|▍         | 2837/57600 [29:50<10:32:07,  1.44it/s]
  5%|▍         | 2838/57600 [29:51<10:11:56,  1.49it/s]
  5%|▍         | 2839/57600 [29:51<9:58:59,  1.52it/s] 
  5%|▍         | 2840/57600 [29:52<9:43:03,  1.57it/s]
                                                      
{'loss': 1.669, 'learning_rate': 9.586062717770034e-07, 'epoch': 31.35}

  5%|▍         | 2840/57600 [29:52<9:43:03,  1.57it/s]
  5%|▍         | 2841/57600 [29:53<9:45:26,  1.56it/s]
  5%|▍         | 2842/57600 [29:53<9:45:13,  1.56it/s]
  5%|▍         | 2843/57600 [29:54<9:43:25,  1.56it/s]
  5%|▍         | 2844/57600 [29:55<9:44:46,  1.56it/s]
  5%|▍         | 2845/57600 [29:55<9:36:38,  1.58it/s]
  5%|▍         | 2846/57600 [29:56<9:50:32,  1.55it/s]
  5%|▍         | 2847/57600 [29:57<9:35:57,  1.58it/s]
  5%|▍         | 2848/57600 [29:57<9:22:34,  1.62it/s]
  5%|▍         | 2849/57600 [29:58<9:22:55,  1.62it/s]
  5%|▍         | 2850/57600 [29:58<9:22:46,  1.62it/s]
  5%|▍         | 2851/57600 [29:59<9:29:48,  1.60it/s]
  5%|▍         | 2852/57600 [30:00<9:16:53,  1.64it/s]
  5%|▍         | 2853/57600 [30:00<9:13:56,  1.65it/s]
  5%|▍         | 2854/57600 [30:01<9:11:02,  1.66it/s]
  5%|▍         | 2855/57600 [30:01<9:04:16,  1.68it/s]
  5%|▍         | 2856/57600 [30:02<9:00:09,  1.69it/s]
  5%|▍         | 2857/57600 [30:03<9:10:02,  1.66it/s]
  5%|▍         | 2858/57600 [30:03<9:09:58,  1.66it/s]
  5%|▍         | 2859/57600 [30:04<9:20:04,  1.63it/s]
  5%|▍         | 2860/57600 [30:04<9:15:37,  1.64it/s]
                                                      
{'loss': 1.6597, 'learning_rate': 9.58292682926829e-07, 'epoch': 31.57}

  5%|▍         | 2860/57600 [30:04<9:15:37,  1.64it/s]
  5%|▍         | 2861/57600 [30:05<9:38:50,  1.58it/s]
  5%|▍         | 2862/57600 [30:06<9:47:08,  1.55it/s]
  5%|▍         | 2863/57600 [30:06<9:34:14,  1.59it/s]
  5%|▍         | 2864/57600 [30:07<9:31:57,  1.59it/s]
  5%|▍         | 2865/57600 [30:08<9:30:35,  1.60it/s]
  5%|▍         | 2866/57600 [30:08<9:35:56,  1.58it/s]
  5%|▍         | 2867/57600 [30:09<9:34:01,  1.59it/s]
  5%|▍         | 2868/57600 [30:09<9:34:22,  1.59it/s]
  5%|▍         | 2869/57600 [30:10<9:32:41,  1.59it/s]
  5%|▍         | 2870/57600 [30:11<9:37:18,  1.58it/s]
  5%|▍         | 2871/57600 [30:11<9:41:51,  1.57it/s]
  5%|▍         | 2872/57600 [30:12<9:38:51,  1.58it/s]
  5%|▍         | 2873/57600 [30:13<9:50:41,  1.54it/s]
  5%|▍         | 2874/57600 [30:13<10:02:53,  1.51it/s]
  5%|▍         | 2875/57600 [30:14<9:52:01,  1.54it/s] 
  5%|▍         | 2876/57600 [30:15<9:45:59,  1.56it/s]
  5%|▍         | 2877/57600 [30:15<10:06:21,  1.50it/s]
  5%|▍         | 2878/57600 [30:16<10:21:43,  1.47it/s]
  5%|▍         | 2879/57600 [30:17<10:35:00,  1.44it/s]
  5%|▌         | 2880/57600 [30:17<10:26:44,  1.46it/s]
                                                       
{'loss': 1.5658, 'learning_rate': 9.57979094076655e-07, 'epoch': 31.79}

  5%|▌         | 2880/57600 [30:17<10:26:44,  1.46it/s]
  5%|▌         | 2881/57600 [30:18<9:55:45,  1.53it/s] 
  5%|▌         | 2882/57600 [30:19<9:39:22,  1.57it/s]
  5%|▌         | 2883/57600 [30:19<9:44:54,  1.56it/s]
  5%|▌         | 2884/57600 [30:20<9:27:08,  1.61it/s]
  5%|▌         | 2885/57600 [30:20<9:21:49,  1.62it/s]
  5%|▌         | 2886/57600 [30:21<9:31:12,  1.60it/s]
  5%|▌         | 2887/57600 [30:22<9:37:05,  1.58it/s]
  5%|▌         | 2888/57600 [30:22<9:40:20,  1.57it/s]
  5%|▌         | 2889/57600 [30:23<9:36:09,  1.58it/s]
  5%|▌         | 2890/57600 [30:24<9:48:37,  1.55it/s]
  5%|▌         | 2891/57600 [30:24<9:53:28,  1.54it/s]
  5%|▌         | 2892/57600 [30:25<9:47:44,  1.55it/s]
  5%|▌         | 2893/57600 [30:26<9:47:58,  1.55it/s]
  5%|▌         | 2894/57600 [30:26<10:06:51,  1.50it/s]
  5%|▌         | 2895/57600 [30:27<9:42:15,  1.57it/s] 
  5%|▌         | 2896/57600 [30:28<9:44:49,  1.56it/s]
  5%|▌         | 2897/57600 [30:28<10:15:33,  1.48it/s]
  5%|▌         | 2898/57600 [30:29<10:00:06,  1.52it/s]
  5%|▌         | 2899/57600 [30:30<9:44:10,  1.56it/s] 
  5%|▌         | 2900/57600 [30:30<10:06:17,  1.50it/s]
                                                       
{'loss': 1.6662, 'learning_rate': 9.576655052264808e-07, 'epoch': 32.01}

  5%|▌         | 2900/57600 [30:30<10:06:17,  1.50it/s]
  5%|▌         | 2901/57600 [30:31<9:58:04,  1.52it/s] 
  5%|▌         | 2902/57600 [30:32<9:52:41,  1.54it/s]
  5%|▌         | 2903/57600 [30:32<9:36:37,  1.58it/s]
  5%|▌         | 2904/57600 [30:33<9:28:14,  1.60it/s]
  5%|▌         | 2905/57600 [30:33<9:38:13,  1.58it/s]
  5%|▌         | 2906/57600 [30:34<9:39:37,  1.57it/s]
  5%|▌         | 2907/57600 [30:35<9:45:57,  1.56it/s]
  5%|▌         | 2908/57600 [30:35<9:38:50,  1.57it/s]
  5%|▌         | 2909/57600 [30:36<10:01:54,  1.51it/s]
  5%|▌         | 2910/57600 [30:37<9:37:54,  1.58it/s] 
  5%|▌         | 2911/57600 [30:37<9:23:28,  1.62it/s]
  5%|▌         | 2912/57600 [30:38<9:36:58,  1.58it/s]
  5%|▌         | 2913/57600 [30:39<9:52:57,  1.54it/s]
  5%|▌         | 2914/57600 [30:39<9:59:56,  1.52it/s]
  5%|▌         | 2915/57600 [30:40<9:59:14,  1.52it/s]
  5%|▌         | 2916/57600 [30:41<9:44:48,  1.56it/s]
  5%|▌         | 2917/57600 [30:41<10:08:20,  1.50it/s]
  5%|▌         | 2918/57600 [30:42<10:01:16,  1.52it/s]
  5%|▌         | 2919/57600 [30:42<9:38:39,  1.57it/s] 
  5%|▌         | 2920/57600 [30:43<9:22:57,  1.62it/s]
                                                      
{'loss': 1.6241, 'learning_rate': 9.573519163763067e-07, 'epoch': 32.23}

  5%|▌         | 2920/57600 [30:43<9:22:57,  1.62it/s]
  5%|▌         | 2921/57600 [30:44<9:19:45,  1.63it/s]
  5%|▌         | 2922/57600 [30:44<9:33:44,  1.59it/s]
  5%|▌         | 2923/57600 [30:45<9:58:10,  1.52it/s]
  5%|▌         | 2924/57600 [30:46<9:44:46,  1.56it/s]
  5%|▌         | 2925/57600 [30:46<9:42:53,  1.56it/s]
  5%|▌         | 2926/57600 [30:47<9:37:41,  1.58it/s]
  5%|▌         | 2927/57600 [30:48<9:32:18,  1.59it/s]
  5%|▌         | 2928/57600 [30:48<9:41:13,  1.57it/s]
  5%|▌         | 2929/57600 [30:49<9:37:01,  1.58it/s]
  5%|▌         | 2930/57600 [30:50<10:12:37,  1.49it/s]
  5%|▌         | 2931/57600 [30:50<9:51:56,  1.54it/s] 
  5%|▌         | 2932/57600 [30:51<10:01:44,  1.51it/s]
  5%|▌         | 2933/57600 [30:51<10:00:55,  1.52it/s]
  5%|▌         | 2934/57600 [30:52<9:56:47,  1.53it/s] 
  5%|▌         | 2935/57600 [30:53<9:35:41,  1.58it/s]
  5%|▌         | 2936/57600 [30:53<9:23:44,  1.62it/s]
  5%|▌         | 2937/57600 [30:54<9:27:38,  1.60it/s]
  5%|▌         | 2938/57600 [30:55<9:34:34,  1.59it/s]
  5%|▌         | 2939/57600 [30:55<9:34:42,  1.59it/s]
  5%|▌         | 2940/57600 [30:56<9:29:57,  1.60it/s]
                                                      
{'loss': 1.6181, 'learning_rate': 9.570383275261325e-07, 'epoch': 32.45}

  5%|▌         | 2940/57600 [30:56<9:29:57,  1.60it/s]
  5%|▌         | 2941/57600 [30:56<9:39:58,  1.57it/s]
  5%|▌         | 2942/57600 [30:57<9:56:12,  1.53it/s]
  5%|▌         | 2943/57600 [30:58<10:04:14,  1.51it/s]
  5%|▌         | 2944/57600 [30:59<10:10:09,  1.49it/s]
  5%|▌         | 2945/57600 [30:59<9:54:55,  1.53it/s] 
  5%|▌         | 2946/57600 [31:00<9:35:09,  1.58it/s]
  5%|▌         | 2947/57600 [31:00<9:28:26,  1.60it/s]
  5%|▌         | 2948/57600 [31:01<9:16:12,  1.64it/s]
  5%|▌         | 2949/57600 [31:02<9:10:21,  1.66it/s]
  5%|▌         | 2950/57600 [31:02<9:04:27,  1.67it/s]
  5%|▌         | 2951/57600 [31:03<9:03:28,  1.68it/s]
  5%|▌         | 2952/57600 [31:03<9:07:10,  1.66it/s]
  5%|▌         | 2953/57600 [31:04<8:59:24,  1.69it/s]
  5%|▌         | 2954/57600 [31:05<9:06:02,  1.67it/s]
  5%|▌         | 2955/57600 [31:05<9:22:34,  1.62it/s]
  5%|▌         | 2956/57600 [31:06<9:28:12,  1.60it/s]
  5%|▌         | 2957/57600 [31:06<9:27:11,  1.61it/s]
  5%|▌         | 2958/57600 [31:07<9:31:03,  1.59it/s]
  5%|▌         | 2959/57600 [31:08<9:35:02,  1.58it/s]
  5%|▌         | 2960/57600 [31:08<9:33:22,  1.59it/s]
                                                      
{'loss': 1.6561, 'learning_rate': 9.567247386759582e-07, 'epoch': 32.67}

  5%|▌         | 2960/57600 [31:08<9:33:22,  1.59it/s]
  5%|▌         | 2961/57600 [31:09<9:20:42,  1.62it/s]
  5%|▌         | 2962/57600 [31:10<9:25:45,  1.61it/s]
  5%|▌         | 2963/57600 [31:10<9:43:40,  1.56it/s]
  5%|▌         | 2964/57600 [31:11<9:34:58,  1.58it/s]
  5%|▌         | 2965/57600 [31:11<9:43:07,  1.56it/s]
  5%|▌         | 2966/57600 [31:12<9:52:05,  1.54it/s]
  5%|▌         | 2967/57600 [31:13<9:53:14,  1.53it/s]
  5%|▌         | 2968/57600 [31:14<10:06:41,  1.50it/s]
  5%|▌         | 2969/57600 [31:14<10:00:50,  1.52it/s]
  5%|▌         | 2970/57600 [31:15<10:01:20,  1.51it/s]
  5%|▌         | 2971/57600 [31:15<9:52:25,  1.54it/s] 
  5%|▌         | 2972/57600 [31:16<9:48:32,  1.55it/s]
  5%|▌         | 2973/57600 [31:17<9:37:08,  1.58it/s]
  5%|▌         | 2974/57600 [31:17<9:25:18,  1.61it/s]
  5%|▌         | 2975/57600 [31:18<9:35:14,  1.58it/s]
  5%|▌         | 2976/57600 [31:19<9:45:16,  1.56it/s]
  5%|▌         | 2977/57600 [31:19<9:29:13,  1.60it/s]
  5%|▌         | 2978/57600 [31:20<9:33:25,  1.59it/s]
  5%|▌         | 2979/57600 [31:20<9:25:38,  1.61it/s]
  5%|▌         | 2980/57600 [31:21<9:34:53,  1.58it/s]
                                                      
{'loss': 1.6176, 'learning_rate': 9.564111498257838e-07, 'epoch': 32.89}

  5%|▌         | 2980/57600 [31:21<9:34:53,  1.58it/s]
  5%|▌         | 2981/57600 [31:22<9:33:40,  1.59it/s]
  5%|▌         | 2982/57600 [31:22<9:39:36,  1.57it/s]
  5%|▌         | 2983/57600 [31:23<9:27:14,  1.60it/s]
  5%|▌         | 2984/57600 [31:24<9:16:22,  1.64it/s]
  5%|▌         | 2985/57600 [31:24<9:25:13,  1.61it/s]
  5%|▌         | 2986/57600 [31:25<9:28:32,  1.60it/s]
  5%|▌         | 2987/57600 [31:25<9:08:44,  1.66it/s]
  5%|▌         | 2988/57600 [31:26<9:19:13,  1.63it/s]
  5%|▌         | 2989/57600 [31:27<9:28:38,  1.60it/s]
  5%|▌         | 2990/57600 [31:27<10:01:57,  1.51it/s]
  5%|▌         | 2991/57600 [31:28<9:40:14,  1.57it/s] 
  5%|▌         | 2992/57600 [31:29<9:28:25,  1.60it/s]
  5%|▌         | 2993/57600 [31:29<9:23:20,  1.62it/s]
  5%|▌         | 2994/57600 [31:30<9:12:24,  1.65it/s]
  5%|▌         | 2995/57600 [31:30<9:13:33,  1.64it/s]
  5%|▌         | 2996/57600 [31:31<9:32:15,  1.59it/s]
  5%|▌         | 2997/57600 [31:32<9:24:51,  1.61it/s]
  5%|▌         | 2998/57600 [31:32<9:21:44,  1.62it/s]
  5%|▌         | 2999/57600 [31:33<9:19:20,  1.63it/s]
  5%|▌         | 3000/57600 [31:33<9:12:10,  1.65it/s]
                                                      
{'loss': 1.686, 'learning_rate': 9.560975609756097e-07, 'epoch': 33.11}

  5%|▌         | 3000/57600 [31:33<9:12:10,  1.65it/s]
  5%|▌         | 3001/57600 [31:34<9:14:59,  1.64it/s]
  5%|▌         | 3002/57600 [31:35<9:24:46,  1.61it/s]
  5%|▌         | 3003/57600 [31:35<9:14:55,  1.64it/s]
  5%|▌         | 3004/57600 [31:36<9:22:59,  1.62it/s]
  5%|▌         | 3005/57600 [31:37<9:31:53,  1.59it/s]
  5%|▌         | 3006/57600 [31:37<9:38:03,  1.57it/s]
  5%|▌         | 3007/57600 [31:38<9:45:26,  1.55it/s]
  5%|▌         | 3008/57600 [31:39<9:39:29,  1.57it/s]
  5%|▌         | 3009/57600 [31:39<9:47:40,  1.55it/s]
  5%|▌         | 3010/57600 [31:40<9:45:02,  1.56it/s]
  5%|▌         | 3011/57600 [31:41<9:50:40,  1.54it/s]
  5%|▌         | 3012/57600 [31:41<9:46:23,  1.55it/s]
  5%|▌         | 3013/57600 [31:42<9:45:41,  1.55it/s]
  5%|▌         | 3014/57600 [31:42<9:45:00,  1.56it/s]
  5%|▌         | 3015/57600 [31:43<9:50:36,  1.54it/s]
  5%|▌         | 3016/57600 [31:44<9:55:52,  1.53it/s]
  5%|▌         | 3017/57600 [31:44<9:39:59,  1.57it/s]
  5%|▌         | 3018/57600 [31:45<9:39:35,  1.57it/s]
  5%|▌         | 3019/57600 [31:46<9:23:48,  1.61it/s]
  5%|▌         | 3020/57600 [31:46<9:50:14,  1.54it/s]
                                                      
{'loss': 1.5938, 'learning_rate': 9.557839721254355e-07, 'epoch': 33.33}

  5%|▌         | 3020/57600 [31:46<9:50:14,  1.54it/s]
  5%|▌         | 3021/57600 [31:47<9:52:15,  1.54it/s]
  5%|▌         | 3022/57600 [31:48<9:33:52,  1.59it/s]
  5%|▌         | 3023/57600 [31:48<9:30:52,  1.59it/s]
  5%|▌         | 3024/57600 [31:49<9:28:52,  1.60it/s]
  5%|▌         | 3025/57600 [31:49<9:31:08,  1.59it/s]
  5%|▌         | 3026/57600 [31:50<9:40:27,  1.57it/s]
  5%|▌         | 3027/57600 [31:51<9:45:20,  1.55it/s]
  5%|▌         | 3028/57600 [31:51<9:45:49,  1.55it/s]
  5%|▌         | 3029/57600 [31:52<9:33:24,  1.59it/s]
  5%|▌         | 3030/57600 [31:53<9:29:00,  1.60it/s]
  5%|▌         | 3031/57600 [31:53<9:39:02,  1.57it/s]
  5%|▌         | 3032/57600 [31:54<9:59:59,  1.52it/s]
  5%|▌         | 3033/57600 [31:55<9:51:51,  1.54it/s]
  5%|▌         | 3034/57600 [31:55<9:47:14,  1.55it/s]
  5%|▌         | 3035/57600 [31:56<9:37:28,  1.57it/s]
  5%|▌         | 3036/57600 [31:56<9:23:26,  1.61it/s]
  5%|▌         | 3037/57600 [31:57<9:07:28,  1.66it/s]
  5%|▌         | 3038/57600 [31:58<9:10:08,  1.65it/s]
  5%|▌         | 3039/57600 [31:58<9:11:36,  1.65it/s]
  5%|▌         | 3040/57600 [31:59<9:20:27,  1.62it/s]
                                                      
{'loss': 1.5952, 'learning_rate': 9.554703832752614e-07, 'epoch': 33.55}

  5%|▌         | 3040/57600 [31:59<9:20:27,  1.62it/s]
  5%|▌         | 3041/57600 [31:59<9:16:23,  1.63it/s]
  5%|▌         | 3042/57600 [32:00<9:04:06,  1.67it/s]
  5%|▌         | 3043/57600 [32:01<9:04:55,  1.67it/s]
  5%|▌         | 3044/57600 [32:01<9:23:52,  1.61it/s]
  5%|▌         | 3045/57600 [32:02<9:25:39,  1.61it/s]
  5%|▌         | 3046/57600 [32:03<9:44:34,  1.56it/s]
  5%|▌         | 3047/57600 [32:03<9:35:18,  1.58it/s]
  5%|▌         | 3048/57600 [32:04<10:07:24,  1.50it/s]
  5%|▌         | 3049/57600 [32:05<9:39:51,  1.57it/s] 
  5%|▌         | 3050/57600 [32:05<9:30:43,  1.59it/s]
  5%|▌         | 3051/57600 [32:06<9:39:06,  1.57it/s]
  5%|▌         | 3052/57600 [32:06<9:29:19,  1.60it/s]
  5%|▌         | 3053/57600 [32:07<9:24:39,  1.61it/s]
  5%|▌         | 3054/57600 [32:08<9:33:17,  1.59it/s]
  5%|▌         | 3055/57600 [32:08<9:58:33,  1.52it/s]
  5%|▌         | 3056/57600 [32:09<9:42:03,  1.56it/s]
  5%|▌         | 3057/57600 [32:10<9:39:00,  1.57it/s]
  5%|▌         | 3058/57600 [32:10<9:49:38,  1.54it/s]
  5%|▌         | 3059/57600 [32:11<9:40:40,  1.57it/s]
  5%|▌         | 3060/57600 [32:12<9:41:18,  1.56it/s]
                                                      
{'loss': 1.5772, 'learning_rate': 9.55156794425087e-07, 'epoch': 33.77}

  5%|▌         | 3060/57600 [32:12<9:41:18,  1.56it/s]
  5%|▌         | 3061/57600 [32:12<9:40:15,  1.57it/s]
  5%|▌         | 3062/57600 [32:13<9:51:36,  1.54it/s]
  5%|▌         | 3063/57600 [32:14<10:00:56,  1.51it/s]
  5%|▌         | 3064/57600 [32:14<9:59:05,  1.52it/s] 
  5%|▌         | 3065/57600 [32:15<9:54:20,  1.53it/s]
  5%|▌         | 3066/57600 [32:15<9:57:38,  1.52it/s]
  5%|▌         | 3067/57600 [32:16<9:51:50,  1.54it/s]
  5%|▌         | 3068/57600 [32:17<9:40:29,  1.57it/s]
  5%|▌         | 3069/57600 [32:17<9:38:51,  1.57it/s]
  5%|▌         | 3070/57600 [32:18<9:43:37,  1.56it/s]
  5%|▌         | 3071/57600 [32:19<9:52:39,  1.53it/s]
  5%|▌         | 3072/57600 [32:19<10:02:24,  1.51it/s]
  5%|▌         | 3073/57600 [32:20<9:55:03,  1.53it/s] 
  5%|▌         | 3074/57600 [32:21<9:51:18,  1.54it/s]
  5%|▌         | 3075/57600 [32:21<9:35:58,  1.58it/s]
  5%|▌         | 3076/57600 [32:22<9:30:01,  1.59it/s]
  5%|▌         | 3077/57600 [32:23<9:30:53,  1.59it/s]
  5%|▌         | 3078/57600 [32:23<9:21:12,  1.62it/s]
  5%|▌         | 3079/57600 [32:24<9:40:44,  1.56it/s]
  5%|▌         | 3080/57600 [32:24<9:36:59,  1.57it/s]
                                                      
{'loss': 1.5889, 'learning_rate': 9.548432055749129e-07, 'epoch': 34.0}

  5%|▌         | 3080/57600 [32:24<9:36:59,  1.57it/s]
  5%|▌         | 3081/57600 [32:25<10:07:45,  1.50it/s]
  5%|▌         | 3082/57600 [32:26<9:48:10,  1.54it/s] 
  5%|▌         | 3083/57600 [32:26<9:51:48,  1.54it/s]
  5%|▌         | 3084/57600 [32:27<9:55:29,  1.53it/s]
  5%|▌         | 3085/57600 [32:28<9:47:42,  1.55it/s]
  5%|▌         | 3086/57600 [32:28<9:56:03,  1.52it/s]
  5%|▌         | 3087/57600 [32:29<9:42:57,  1.56it/s]
  5%|▌         | 3088/57600 [32:30<10:02:47,  1.51it/s]
  5%|▌         | 3089/57600 [32:30<10:05:13,  1.50it/s]
  5%|▌         | 3090/57600 [32:31<9:54:46,  1.53it/s] 
  5%|▌         | 3091/57600 [32:32<10:13:26,  1.48it/s]
  5%|▌         | 3092/57600 [32:32<9:59:50,  1.51it/s] 
  5%|▌         | 3093/57600 [32:33<9:52:38,  1.53it/s]
  5%|▌         | 3094/57600 [32:34<9:47:24,  1.55it/s]
  5%|▌         | 3095/57600 [32:34<9:49:11,  1.54it/s]
  5%|▌         | 3096/57600 [32:35<10:00:21,  1.51it/s]
  5%|▌         | 3097/57600 [32:36<9:51:17,  1.54it/s] 
  5%|▌         | 3098/57600 [32:36<9:46:11,  1.55it/s]
  5%|▌         | 3099/57600 [32:37<9:37:51,  1.57it/s]
  5%|▌         | 3100/57600 [32:37<9:37:38,  1.57it/s]
                                                      
{'loss': 1.5953, 'learning_rate': 9.545296167247385e-07, 'epoch': 34.22}

  5%|▌         | 3100/57600 [32:37<9:37:38,  1.57it/s]
  5%|▌         | 3101/57600 [32:38<9:56:14,  1.52it/s]
  5%|▌         | 3102/57600 [32:39<9:50:43,  1.54it/s]
  5%|▌         | 3103/57600 [32:39<9:36:28,  1.58it/s]
  5%|▌         | 3104/57600 [32:40<9:49:19,  1.54it/s]
  5%|▌         | 3105/57600 [32:41<9:40:46,  1.56it/s]
  5%|▌         | 3106/57600 [32:41<9:26:39,  1.60it/s]
  5%|▌         | 3107/57600 [32:42<9:22:48,  1.61it/s]
  5%|▌         | 3108/57600 [32:43<9:19:07,  1.62it/s]
  5%|▌         | 3109/57600 [32:43<9:17:40,  1.63it/s]
  5%|▌         | 3110/57600 [32:44<9:30:19,  1.59it/s]
  5%|▌         | 3111/57600 [32:44<9:32:30,  1.59it/s]
  5%|▌         | 3112/57600 [32:45<9:30:16,  1.59it/s]
  5%|▌         | 3113/57600 [32:46<9:27:14,  1.60it/s]
  5%|▌         | 3114/57600 [32:46<9:23:46,  1.61it/s]
  5%|▌         | 3115/57600 [32:47<9:25:20,  1.61it/s]
  5%|▌         | 3116/57600 [32:48<9:35:41,  1.58it/s]
  5%|▌         | 3117/57600 [32:48<9:33:20,  1.58it/s]
  5%|▌         | 3118/57600 [32:49<9:26:05,  1.60it/s]
  5%|▌         | 3119/57600 [32:49<9:21:28,  1.62it/s]
  5%|▌         | 3120/57600 [32:50<9:22:24,  1.61it/s]
                                                      
{'loss': 1.6379, 'learning_rate': 9.542160278745644e-07, 'epoch': 34.44}

  5%|▌         | 3120/57600 [32:50<9:22:24,  1.61it/s]
  5%|▌         | 3121/57600 [32:51<9:28:33,  1.60it/s]
  5%|▌         | 3122/57600 [32:51<9:13:59,  1.64it/s]
  5%|▌         | 3123/57600 [32:52<9:28:48,  1.60it/s]
  5%|▌         | 3124/57600 [32:53<9:38:18,  1.57it/s]
  5%|▌         | 3125/57600 [32:53<9:22:07,  1.62it/s]
  5%|▌         | 3126/57600 [32:54<9:26:49,  1.60it/s]
  5%|▌         | 3127/57600 [32:54<9:36:17,  1.58it/s]
  5%|▌         | 3128/57600 [32:55<9:42:21,  1.56it/s]
  5%|▌         | 3129/57600 [32:56<9:50:35,  1.54it/s]
  5%|▌         | 3130/57600 [32:56<9:57:05,  1.52it/s]
  5%|▌         | 3131/57600 [32:57<9:47:25,  1.55it/s]
  5%|▌         | 3132/57600 [32:58<9:26:07,  1.60it/s]
  5%|▌         | 3133/57600 [32:58<9:43:23,  1.56it/s]
  5%|▌         | 3134/57600 [32:59<9:30:30,  1.59it/s]
  5%|▌         | 3135/57600 [33:00<9:19:36,  1.62it/s]
  5%|▌         | 3136/57600 [33:00<9:16:31,  1.63it/s]
  5%|▌         | 3137/57600 [33:01<9:07:34,  1.66it/s]
  5%|▌         | 3138/57600 [33:01<9:29:26,  1.59it/s]
  5%|▌         | 3139/57600 [33:02<9:17:39,  1.63it/s]
  5%|▌         | 3140/57600 [33:03<9:09:25,  1.65it/s]
                                                      
{'loss': 1.6252, 'learning_rate': 9.539024390243903e-07, 'epoch': 34.66}

  5%|▌         | 3140/57600 [33:03<9:09:25,  1.65it/s]
  5%|▌         | 3141/57600 [33:03<9:28:23,  1.60it/s]
  5%|▌         | 3142/57600 [33:04<9:21:28,  1.62it/s]
  5%|▌         | 3143/57600 [33:05<9:41:11,  1.56it/s]
  5%|▌         | 3144/57600 [33:05<9:36:16,  1.57it/s]
  5%|▌         | 3145/57600 [33:06<9:29:49,  1.59it/s]
  5%|▌         | 3146/57600 [33:06<9:30:46,  1.59it/s]
  5%|▌         | 3147/57600 [33:07<9:21:01,  1.62it/s]
  5%|▌         | 3148/57600 [33:08<9:11:34,  1.65it/s]
  5%|▌         | 3149/57600 [33:08<9:07:12,  1.66it/s]
  5%|▌         | 3150/57600 [33:09<9:20:48,  1.62it/s]
  5%|▌         | 3151/57600 [33:09<9:30:27,  1.59it/s]
  5%|▌         | 3152/57600 [33:10<9:18:50,  1.62it/s]
  5%|▌         | 3153/57600 [33:11<9:42:43,  1.56it/s]
  5%|▌         | 3154/57600 [33:11<10:05:42,  1.50it/s]
  5%|▌         | 3155/57600 [33:12<9:46:58,  1.55it/s] 
  5%|▌         | 3156/57600 [33:13<9:47:25,  1.54it/s]
  5%|▌         | 3157/57600 [33:13<9:24:09,  1.61it/s]
  5%|▌         | 3158/57600 [33:14<9:32:18,  1.59it/s]
  5%|▌         | 3159/57600 [33:15<9:26:11,  1.60it/s]
  5%|▌         | 3160/57600 [33:15<9:12:08,  1.64it/s]
                                                      
{'loss': 1.628, 'learning_rate': 9.53588850174216e-07, 'epoch': 34.88}

  5%|▌         | 3160/57600 [33:15<9:12:08,  1.64it/s]
  5%|▌         | 3161/57600 [33:16<9:02:46,  1.67it/s]
  5%|▌         | 3162/57600 [33:16<9:04:37,  1.67it/s]
  5%|▌         | 3163/57600 [33:17<9:30:55,  1.59it/s]
  5%|▌         | 3164/57600 [33:18<9:24:59,  1.61it/s]
  5%|▌         | 3165/57600 [33:18<9:27:05,  1.60it/s]
  5%|▌         | 3166/57600 [33:19<9:25:14,  1.61it/s]
  5%|▌         | 3167/57600 [33:19<9:28:54,  1.59it/s]
  6%|▌         | 3168/57600 [33:20<9:45:12,  1.55it/s]
  6%|▌         | 3169/57600 [33:21<9:55:13,  1.52it/s]
  6%|▌         | 3170/57600 [33:21<9:40:28,  1.56it/s]
  6%|▌         | 3171/57600 [33:22<9:28:26,  1.60it/s]
  6%|▌         | 3172/57600 [33:23<9:43:37,  1.55it/s]
  6%|▌         | 3173/57600 [33:23<9:32:53,  1.58it/s]
  6%|▌         | 3174/57600 [33:24<9:20:12,  1.62it/s]
  6%|▌         | 3175/57600 [33:25<9:23:55,  1.61it/s]
  6%|▌         | 3176/57600 [33:25<9:23:23,  1.61it/s]
  6%|▌         | 3177/57600 [33:26<9:25:33,  1.60it/s]
  6%|▌         | 3178/57600 [33:26<9:15:09,  1.63it/s]
  6%|▌         | 3179/57600 [33:27<9:30:03,  1.59it/s]
  6%|▌         | 3180/57600 [33:28<9:15:18,  1.63it/s]
                                                      
{'loss': 1.6547, 'learning_rate': 9.532752613240419e-07, 'epoch': 35.1}

  6%|▌         | 3180/57600 [33:28<9:15:18,  1.63it/s]
  6%|▌         | 3181/57600 [33:28<9:12:29,  1.64it/s]
  6%|▌         | 3182/57600 [33:29<9:01:43,  1.67it/s]
  6%|▌         | 3183/57600 [33:29<9:27:53,  1.60it/s]
  6%|▌         | 3184/57600 [33:30<9:15:50,  1.63it/s]
  6%|▌         | 3185/57600 [33:31<9:12:26,  1.64it/s]
  6%|▌         | 3186/57600 [33:31<9:07:35,  1.66it/s]
  6%|▌         | 3187/57600 [33:32<9:06:26,  1.66it/s]
  6%|▌         | 3188/57600 [33:33<9:17:00,  1.63it/s]
  6%|▌         | 3189/57600 [33:33<9:29:23,  1.59it/s]
  6%|▌         | 3190/57600 [33:34<9:36:40,  1.57it/s]
  6%|▌         | 3191/57600 [33:34<9:20:47,  1.62it/s]
  6%|▌         | 3192/57600 [33:35<9:42:45,  1.56it/s]
  6%|▌         | 3193/57600 [33:36<9:22:48,  1.61it/s]
  6%|▌         | 3194/57600 [33:36<9:30:28,  1.59it/s]
  6%|▌         | 3195/57600 [33:37<9:38:55,  1.57it/s]
  6%|▌         | 3196/57600 [33:38<9:27:03,  1.60it/s]
  6%|▌         | 3197/57600 [33:38<9:13:23,  1.64it/s]
  6%|▌         | 3198/57600 [33:39<9:19:06,  1.62it/s]
  6%|▌         | 3199/57600 [33:39<9:09:05,  1.65it/s]
  6%|▌         | 3200/57600 [33:40<8:57:42,  1.69it/s]
                                                      
{'loss': 1.6308, 'learning_rate': 9.529616724738675e-07, 'epoch': 35.32}

  6%|▌         | 3200/57600 [33:40<8:57:42,  1.69it/s]
  6%|▌         | 3201/57600 [33:41<9:00:00,  1.68it/s]
  6%|▌         | 3202/57600 [33:41<9:17:25,  1.63it/s]
  6%|▌         | 3203/57600 [33:42<9:39:33,  1.56it/s]
  6%|▌         | 3204/57600 [33:43<9:49:04,  1.54it/s]
  6%|▌         | 3205/57600 [33:43<9:50:23,  1.54it/s]
  6%|▌         | 3206/57600 [33:44<9:49:00,  1.54it/s]
  6%|▌         | 3207/57600 [33:44<9:32:55,  1.58it/s]
  6%|▌         | 3208/57600 [33:45<9:31:07,  1.59it/s]
  6%|▌         | 3209/57600 [33:46<9:33:15,  1.58it/s]
  6%|▌         | 3210/57600 [33:46<9:20:19,  1.62it/s]
  6%|▌         | 3211/57600 [33:47<9:16:00,  1.63it/s]
  6%|▌         | 3212/57600 [33:48<9:22:50,  1.61it/s]
  6%|▌         | 3213/57600 [33:48<9:23:46,  1.61it/s]
  6%|▌         | 3214/57600 [33:49<9:17:16,  1.63it/s]
  6%|▌         | 3215/57600 [33:49<9:25:04,  1.60it/s]
  6%|▌         | 3216/57600 [33:50<9:20:22,  1.62it/s]
  6%|▌         | 3217/57600 [33:51<9:22:54,  1.61it/s]
  6%|▌         | 3218/57600 [33:51<9:37:39,  1.57it/s]
  6%|▌         | 3219/57600 [33:52<9:39:13,  1.56it/s]
  6%|▌         | 3220/57600 [33:53<9:44:06,  1.55it/s]
                                                      
{'loss': 1.599, 'learning_rate': 9.526480836236935e-07, 'epoch': 35.54}

  6%|▌         | 3220/57600 [33:53<9:44:06,  1.55it/s]
  6%|▌         | 3221/57600 [33:53<9:45:41,  1.55it/s]
  6%|▌         | 3222/57600 [33:54<10:00:11,  1.51it/s]
  6%|▌         | 3223/57600 [33:55<9:51:50,  1.53it/s] 
  6%|▌         | 3224/57600 [33:55<9:45:17,  1.55it/s]
  6%|▌         | 3225/57600 [33:56<9:55:44,  1.52it/s]
  6%|▌         | 3226/57600 [33:57<9:51:09,  1.53it/s]
  6%|▌         | 3227/57600 [33:57<9:33:12,  1.58it/s]
  6%|▌         | 3228/57600 [33:58<9:33:22,  1.58it/s]
  6%|▌         | 3229/57600 [33:58<9:27:37,  1.60it/s]
  6%|▌         | 3230/57600 [33:59<9:34:56,  1.58it/s]
  6%|▌         | 3231/57600 [34:00<9:46:30,  1.55it/s]
  6%|▌         | 3232/57600 [34:00<9:34:46,  1.58it/s]
  6%|▌         | 3233/57600 [34:01<9:28:35,  1.59it/s]
  6%|▌         | 3234/57600 [34:02<9:30:09,  1.59it/s]
  6%|▌         | 3235/57600 [34:02<9:37:21,  1.57it/s]
  6%|▌         | 3236/57600 [34:03<9:35:58,  1.57it/s]
  6%|▌         | 3237/57600 [34:03<9:38:51,  1.57it/s]
  6%|▌         | 3238/57600 [34:04<9:42:20,  1.56it/s]
  6%|▌         | 3239/57600 [34:05<9:39:07,  1.56it/s]
  6%|▌         | 3240/57600 [34:05<9:22:02,  1.61it/s]
                                                      
{'loss': 1.6198, 'learning_rate': 9.523344947735191e-07, 'epoch': 35.76}

  6%|▌         | 3240/57600 [34:05<9:22:02,  1.61it/s]
  6%|▌         | 3241/57600 [34:06<9:41:40,  1.56it/s]
  6%|▌         | 3242/57600 [34:07<9:46:08,  1.55it/s]
  6%|▌         | 3243/57600 [34:07<9:41:12,  1.56it/s]
  6%|▌         | 3244/57600 [34:08<9:40:43,  1.56it/s]
  6%|▌         | 3245/57600 [34:09<9:43:09,  1.55it/s]
  6%|▌         | 3246/57600 [34:09<9:45:44,  1.55it/s]
  6%|▌         | 3247/57600 [34:10<9:46:31,  1.54it/s]
  6%|▌         | 3248/57600 [34:11<9:44:21,  1.55it/s]
  6%|▌         | 3249/57600 [34:11<9:29:40,  1.59it/s]
  6%|▌         | 3250/57600 [34:12<9:39:07,  1.56it/s]
  6%|▌         | 3251/57600 [34:12<9:41:31,  1.56it/s]
  6%|▌         | 3252/57600 [34:13<9:31:36,  1.58it/s]
  6%|▌         | 3253/57600 [34:14<9:26:35,  1.60it/s]
  6%|▌         | 3254/57600 [34:14<9:37:11,  1.57it/s]
  6%|▌         | 3255/57600 [34:15<9:26:38,  1.60it/s]
  6%|▌         | 3256/57600 [34:16<9:35:14,  1.57it/s]
  6%|▌         | 3257/57600 [34:16<9:28:01,  1.59it/s]
  6%|▌         | 3258/57600 [34:17<9:44:18,  1.55it/s]
  6%|▌         | 3259/57600 [34:18<9:44:22,  1.55it/s]
  6%|▌         | 3260/57600 [34:18<9:25:30,  1.60it/s]
                                                      
{'loss': 1.6248, 'learning_rate': 9.520209059233449e-07, 'epoch': 35.98}

  6%|▌         | 3260/57600 [34:18<9:25:30,  1.60it/s]
  6%|▌         | 3261/57600 [34:19<9:10:26,  1.65it/s]
  6%|▌         | 3262/57600 [34:19<9:24:50,  1.60it/s]
  6%|▌         | 3263/57600 [34:20<9:28:02,  1.59it/s]
  6%|▌         | 3264/57600 [34:21<9:16:58,  1.63it/s]
  6%|▌         | 3265/57600 [34:21<9:34:56,  1.58it/s]
  6%|▌         | 3266/57600 [34:22<9:39:31,  1.56it/s]
  6%|▌         | 3267/57600 [34:23<9:45:44,  1.55it/s]
  6%|▌         | 3268/57600 [34:23<9:41:00,  1.56it/s]
  6%|▌         | 3269/57600 [34:24<9:50:05,  1.53it/s]
  6%|▌         | 3270/57600 [34:24<9:30:05,  1.59it/s]
  6%|▌         | 3271/57600 [34:25<9:30:47,  1.59it/s]
  6%|▌         | 3272/57600 [34:26<9:14:17,  1.63it/s]
  6%|▌         | 3273/57600 [34:26<9:19:32,  1.62it/s]
  6%|▌         | 3274/57600 [34:27<9:30:20,  1.59it/s]
  6%|▌         | 3275/57600 [34:28<9:15:52,  1.63it/s]
  6%|▌         | 3276/57600 [34:28<9:35:40,  1.57it/s]
  6%|▌         | 3277/57600 [34:29<9:38:34,  1.56it/s]
  6%|▌         | 3278/57600 [34:29<9:38:59,  1.56it/s]
  6%|▌         | 3279/57600 [34:30<9:29:34,  1.59it/s]
  6%|▌         | 3280/57600 [34:31<9:30:58,  1.59it/s]
                                                      
{'loss': 1.576, 'learning_rate': 9.517073170731706e-07, 'epoch': 36.2}

  6%|▌         | 3280/57600 [34:31<9:30:58,  1.59it/s]
  6%|▌         | 3281/57600 [34:31<9:37:55,  1.57it/s]
  6%|▌         | 3282/57600 [34:32<9:54:18,  1.52it/s]
  6%|▌         | 3283/57600 [34:33<9:40:27,  1.56it/s]
  6%|▌         | 3284/57600 [34:33<9:38:26,  1.56it/s]
  6%|▌         | 3285/57600 [34:34<9:20:17,  1.62it/s]
  6%|▌         | 3286/57600 [34:35<9:26:47,  1.60it/s]
  6%|▌         | 3287/57600 [34:35<9:35:42,  1.57it/s]
  6%|▌         | 3288/57600 [34:36<9:31:08,  1.58it/s]
  6%|▌         | 3289/57600 [34:36<9:41:38,  1.56it/s]
  6%|▌         | 3290/57600 [34:37<9:22:00,  1.61it/s]
  6%|▌         | 3291/57600 [34:38<9:28:38,  1.59it/s]
  6%|▌         | 3292/57600 [34:38<9:16:10,  1.63it/s]
  6%|▌         | 3293/57600 [34:39<9:10:51,  1.64it/s]
  6%|▌         | 3294/57600 [34:40<9:23:08,  1.61it/s]
  6%|▌         | 3295/57600 [34:40<9:11:06,  1.64it/s]
  6%|▌         | 3296/57600 [34:41<9:18:34,  1.62it/s]
  6%|▌         | 3297/57600 [34:41<8:58:32,  1.68it/s]
  6%|▌         | 3298/57600 [34:42<9:03:43,  1.66it/s]
  6%|▌         | 3299/57600 [34:43<9:05:25,  1.66it/s]
  6%|▌         | 3300/57600 [34:43<9:07:56,  1.65it/s]
                                                      
{'loss': 1.6648, 'learning_rate': 9.513937282229965e-07, 'epoch': 36.42}

  6%|▌         | 3300/57600 [34:43<9:07:56,  1.65it/s]
  6%|▌         | 3301/57600 [34:44<9:21:29,  1.61it/s]
  6%|▌         | 3302/57600 [34:44<9:10:19,  1.64it/s]
  6%|▌         | 3303/57600 [34:45<9:05:13,  1.66it/s]
  6%|▌         | 3304/57600 [34:46<9:21:51,  1.61it/s]
  6%|▌         | 3305/57600 [34:46<9:24:46,  1.60it/s]
  6%|▌         | 3306/57600 [34:47<9:09:14,  1.65it/s]
  6%|▌         | 3307/57600 [34:47<9:07:51,  1.65it/s]
  6%|▌         | 3308/57600 [34:48<9:28:09,  1.59it/s]
  6%|▌         | 3309/57600 [34:49<9:28:03,  1.59it/s]
  6%|▌         | 3310/57600 [34:49<9:22:00,  1.61it/s]
  6%|▌         | 3311/57600 [34:50<9:46:51,  1.54it/s]
  6%|▌         | 3312/57600 [34:51<9:41:03,  1.56it/s]
  6%|▌         | 3313/57600 [34:51<9:21:02,  1.61it/s]
  6%|▌         | 3314/57600 [34:52<9:26:57,  1.60it/s]
  6%|▌         | 3315/57600 [34:53<9:37:22,  1.57it/s]
  6%|▌         | 3316/57600 [34:53<9:59:15,  1.51it/s]
  6%|▌         | 3317/57600 [34:54<10:08:00,  1.49it/s]
  6%|▌         | 3318/57600 [34:55<9:57:43,  1.51it/s] 
  6%|▌         | 3319/57600 [34:55<9:43:51,  1.55it/s]
  6%|▌         | 3320/57600 [34:56<10:01:22,  1.50it/s]
                                                       
{'loss': 1.6035, 'learning_rate': 9.510801393728223e-07, 'epoch': 36.64}

  6%|▌         | 3320/57600 [34:56<10:01:22,  1.50it/s]
  6%|▌         | 3321/57600 [34:57<10:01:08,  1.50it/s]
  6%|▌         | 3322/57600 [34:57<10:04:02,  1.50it/s]
  6%|▌         | 3323/57600 [34:58<9:53:36,  1.52it/s] 
  6%|▌         | 3324/57600 [34:58<9:41:04,  1.56it/s]
  6%|▌         | 3325/57600 [34:59<9:38:35,  1.56it/s]
  6%|▌         | 3326/57600 [35:00<9:51:19,  1.53it/s]
  6%|▌         | 3327/57600 [35:00<9:39:51,  1.56it/s]
  6%|▌         | 3328/57600 [35:01<9:28:58,  1.59it/s]
  6%|▌         | 3329/57600 [35:02<9:31:09,  1.58it/s]
  6%|▌         | 3330/57600 [35:02<9:11:59,  1.64it/s]
  6%|▌         | 3331/57600 [35:03<9:13:27,  1.63it/s]
  6%|▌         | 3332/57600 [35:03<9:15:21,  1.63it/s]
  6%|▌         | 3333/57600 [35:04<9:20:32,  1.61it/s]
  6%|▌         | 3334/57600 [35:05<9:37:36,  1.57it/s]
  6%|▌         | 3335/57600 [35:05<9:53:29,  1.52it/s]
  6%|▌         | 3336/57600 [35:06<10:01:13,  1.50it/s]
  6%|▌         | 3337/57600 [35:07<9:49:09,  1.54it/s] 
  6%|▌         | 3338/57600 [35:07<9:32:00,  1.58it/s]
  6%|▌         | 3339/57600 [35:08<9:40:41,  1.56it/s]
  6%|▌         | 3340/57600 [35:09<9:29:12,  1.59it/s]
                                                      
{'loss': 1.6051, 'learning_rate': 9.50766550522648e-07, 'epoch': 36.87}

  6%|▌         | 3340/57600 [35:09<9:29:12,  1.59it/s]
  6%|▌         | 3341/57600 [35:09<9:31:25,  1.58it/s]
  6%|▌         | 3342/57600 [35:10<9:29:45,  1.59it/s]
  6%|▌         | 3343/57600 [35:11<9:25:34,  1.60it/s]
  6%|▌         | 3344/57600 [35:11<9:26:40,  1.60it/s]
  6%|▌         | 3345/57600 [35:12<9:15:09,  1.63it/s]
  6%|▌         | 3346/57600 [35:12<9:21:30,  1.61it/s]
  6%|▌         | 3347/57600 [35:13<9:21:05,  1.61it/s]
  6%|▌         | 3348/57600 [35:14<9:33:08,  1.58it/s]
  6%|▌         | 3349/57600 [35:14<9:44:13,  1.55it/s]
  6%|▌         | 3350/57600 [35:15<9:26:09,  1.60it/s]
  6%|▌         | 3351/57600 [35:15<9:17:04,  1.62it/s]
  6%|▌         | 3352/57600 [35:16<9:16:26,  1.62it/s]
  6%|▌         | 3353/57600 [35:17<9:43:50,  1.55it/s]
  6%|▌         | 3354/57600 [35:18<9:58:21,  1.51it/s]
  6%|▌         | 3355/57600 [35:18<10:12:12,  1.48it/s]
  6%|▌         | 3356/57600 [35:19<10:07:18,  1.49it/s]
  6%|▌         | 3357/57600 [35:19<9:44:07,  1.55it/s] 
  6%|▌         | 3358/57600 [35:20<9:35:50,  1.57it/s]
  6%|▌         | 3359/57600 [35:21<9:28:49,  1.59it/s]
  6%|▌         | 3360/57600 [35:21<9:33:01,  1.58it/s]
                                                      
{'loss': 1.6052, 'learning_rate': 9.504529616724738e-07, 'epoch': 37.09}

  6%|▌         | 3360/57600 [35:21<9:33:01,  1.58it/s]
  6%|▌         | 3361/57600 [35:22<9:37:22,  1.57it/s]
  6%|▌         | 3362/57600 [35:23<9:29:37,  1.59it/s]
  6%|▌         | 3363/57600 [35:23<9:37:23,  1.57it/s]
  6%|▌         | 3364/57600 [35:24<10:05:25,  1.49it/s]
  6%|▌         | 3365/57600 [35:25<10:06:13,  1.49it/s]
  6%|▌         | 3366/57600 [35:25<10:14:05,  1.47it/s]
  6%|▌         | 3367/57600 [35:26<10:03:20,  1.50it/s]
  6%|▌         | 3368/57600 [35:27<9:52:22,  1.53it/s] 
  6%|▌         | 3369/57600 [35:27<9:39:31,  1.56it/s]
  6%|▌         | 3370/57600 [35:28<9:38:13,  1.56it/s]
  6%|▌         | 3371/57600 [35:29<9:35:45,  1.57it/s]
  6%|▌         | 3372/57600 [35:29<9:34:41,  1.57it/s]
  6%|▌         | 3373/57600 [35:30<9:25:37,  1.60it/s]
  6%|▌         | 3374/57600 [35:30<9:37:14,  1.57it/s]
  6%|▌         | 3375/57600 [35:31<9:22:01,  1.61it/s]
  6%|▌         | 3376/57600 [35:32<9:28:19,  1.59it/s]
  6%|▌         | 3377/57600 [35:32<9:27:12,  1.59it/s]
  6%|▌         | 3378/57600 [35:33<9:22:32,  1.61it/s]
  6%|▌         | 3379/57600 [35:34<9:29:32,  1.59it/s]
  6%|▌         | 3380/57600 [35:34<9:32:25,  1.58it/s]
                                                      
{'loss': 1.6081, 'learning_rate': 9.501393728222996e-07, 'epoch': 37.31}

  6%|▌         | 3380/57600 [35:34<9:32:25,  1.58it/s]
  6%|▌         | 3381/57600 [35:35<9:26:14,  1.60it/s]
  6%|▌         | 3382/57600 [35:35<9:47:06,  1.54it/s]
  6%|▌         | 3383/57600 [35:36<10:02:02,  1.50it/s]
  6%|▌         | 3384/57600 [35:37<9:46:14,  1.54it/s] 
  6%|▌         | 3385/57600 [35:37<9:55:41,  1.52it/s]
  6%|▌         | 3386/57600 [35:38<9:36:23,  1.57it/s]
  6%|▌         | 3387/57600 [35:39<9:34:33,  1.57it/s]
  6%|▌         | 3388/57600 [35:39<9:26:42,  1.59it/s]
  6%|▌         | 3389/57600 [35:40<9:34:08,  1.57it/s]
  6%|▌         | 3390/57600 [35:41<9:20:32,  1.61it/s]
  6%|▌         | 3391/57600 [35:41<9:27:11,  1.59it/s]
  6%|▌         | 3392/57600 [35:42<9:28:47,  1.59it/s]
  6%|▌         | 3393/57600 [35:42<9:18:38,  1.62it/s]
  6%|▌         | 3394/57600 [35:43<9:27:56,  1.59it/s]
  6%|▌         | 3395/57600 [35:44<9:21:35,  1.61it/s]
  6%|▌         | 3396/57600 [35:44<9:30:23,  1.58it/s]
  6%|▌         | 3397/57600 [35:45<9:38:16,  1.56it/s]
  6%|▌         | 3398/57600 [35:46<9:18:38,  1.62it/s]
  6%|▌         | 3399/57600 [35:46<9:31:34,  1.58it/s]
  6%|▌         | 3400/57600 [35:47<9:33:41,  1.57it/s]
                                                      
{'loss': 1.6066, 'learning_rate': 9.498257839721255e-07, 'epoch': 37.53}

  6%|▌         | 3400/57600 [35:47<9:33:41,  1.57it/s]
  6%|▌         | 3401/57600 [35:48<9:59:34,  1.51it/s]
  6%|▌         | 3402/57600 [35:48<9:52:44,  1.52it/s]
  6%|▌         | 3403/57600 [35:49<9:42:40,  1.55it/s]
  6%|▌         | 3404/57600 [35:49<9:34:45,  1.57it/s]
  6%|▌         | 3405/57600 [35:50<9:52:51,  1.52it/s]
  6%|▌         | 3406/57600 [35:51<9:53:21,  1.52it/s]
  6%|▌         | 3407/57600 [35:52<9:59:30,  1.51it/s]
  6%|▌         | 3408/57600 [35:52<9:57:22,  1.51it/s]
  6%|▌         | 3409/57600 [35:53<9:34:53,  1.57it/s]
  6%|▌         | 3410/57600 [35:53<9:29:58,  1.58it/s]
  6%|▌         | 3411/57600 [35:54<9:28:18,  1.59it/s]
  6%|▌         | 3412/57600 [35:55<9:44:05,  1.55it/s]
  6%|▌         | 3413/57600 [35:55<9:50:25,  1.53it/s]
  6%|▌         | 3414/57600 [35:56<9:40:03,  1.56it/s]
  6%|▌         | 3415/57600 [35:57<9:32:47,  1.58it/s]
  6%|▌         | 3416/57600 [35:57<9:32:26,  1.58it/s]
  6%|▌         | 3417/57600 [35:58<9:55:27,  1.52it/s]
  6%|▌         | 3418/57600 [35:59<9:44:16,  1.55it/s]
  6%|▌         | 3419/57600 [35:59<9:24:34,  1.60it/s]
  6%|▌         | 3420/57600 [36:00<9:43:15,  1.55it/s]
                                                      
{'loss': 1.5763, 'learning_rate': 9.495121951219511e-07, 'epoch': 37.75}

  6%|▌         | 3420/57600 [36:00<9:43:15,  1.55it/s]
  6%|▌         | 3421/57600 [36:00<9:28:26,  1.59it/s]
  6%|▌         | 3422/57600 [36:01<9:30:54,  1.58it/s]
  6%|▌         | 3423/57600 [36:02<9:33:49,  1.57it/s]
  6%|▌         | 3424/57600 [36:02<9:37:35,  1.56it/s]
  6%|▌         | 3425/57600 [36:03<9:43:23,  1.55it/s]
  6%|▌         | 3426/57600 [36:04<9:33:20,  1.57it/s]
  6%|▌         | 3427/57600 [36:04<9:18:13,  1.62it/s]
  6%|▌         | 3428/57600 [36:05<9:20:58,  1.61it/s]
  6%|▌         | 3429/57600 [36:05<9:12:35,  1.63it/s]
  6%|▌         | 3430/57600 [36:06<9:21:26,  1.61it/s]
  6%|▌         | 3431/57600 [36:07<9:36:00,  1.57it/s]
  6%|▌         | 3432/57600 [36:07<9:41:19,  1.55it/s]
  6%|▌         | 3433/57600 [36:08<9:42:41,  1.55it/s]
  6%|▌         | 3434/57600 [36:09<9:26:12,  1.59it/s]
  6%|▌         | 3435/57600 [36:09<9:30:04,  1.58it/s]
  6%|▌         | 3436/57600 [36:10<9:14:47,  1.63it/s]
  6%|▌         | 3437/57600 [36:10<9:18:27,  1.62it/s]
  6%|▌         | 3438/57600 [36:11<9:09:17,  1.64it/s]
  6%|▌         | 3439/57600 [36:12<9:20:45,  1.61it/s]
  6%|▌         | 3440/57600 [36:12<9:20:31,  1.61it/s]
                                                      
{'loss': 1.6039, 'learning_rate': 9.49198606271777e-07, 'epoch': 37.97}

  6%|▌         | 3440/57600 [36:12<9:20:31,  1.61it/s]
  6%|▌         | 3441/57600 [36:13<9:18:49,  1.62it/s]
  6%|▌         | 3442/57600 [36:14<9:23:08,  1.60it/s]
  6%|▌         | 3443/57600 [36:14<9:43:37,  1.55it/s]
  6%|▌         | 3444/57600 [36:15<9:30:38,  1.58it/s]
  6%|▌         | 3445/57600 [36:16<9:31:40,  1.58it/s]
  6%|▌         | 3446/57600 [36:16<9:33:01,  1.58it/s]
  6%|▌         | 3447/57600 [36:17<9:43:31,  1.55it/s]
  6%|▌         | 3448/57600 [36:17<9:36:57,  1.56it/s]
  6%|▌         | 3449/57600 [36:18<9:25:06,  1.60it/s]
  6%|▌         | 3450/57600 [36:19<9:33:24,  1.57it/s]
  6%|▌         | 3451/57600 [36:19<9:33:11,  1.57it/s]
  6%|▌         | 3452/57600 [36:20<9:30:36,  1.58it/s]
  6%|▌         | 3453/57600 [36:21<9:28:07,  1.59it/s]
  6%|▌         | 3454/57600 [36:21<9:12:39,  1.63it/s]
  6%|▌         | 3455/57600 [36:22<9:09:26,  1.64it/s]
  6%|▌         | 3456/57600 [36:22<9:04:03,  1.66it/s]
  6%|▌         | 3457/57600 [36:23<9:15:34,  1.62it/s]
  6%|▌         | 3458/57600 [36:24<9:32:31,  1.58it/s]
  6%|▌         | 3459/57600 [36:24<9:31:30,  1.58it/s]
  6%|▌         | 3460/57600 [36:25<9:26:25,  1.59it/s]
                                                      
{'loss': 1.6203, 'learning_rate': 9.488850174216028e-07, 'epoch': 38.19}

  6%|▌         | 3460/57600 [36:25<9:26:25,  1.59it/s]
  6%|▌         | 3461/57600 [36:26<9:23:26,  1.60it/s]
  6%|▌         | 3462/57600 [36:26<9:44:31,  1.54it/s]
  6%|▌         | 3463/57600 [36:27<9:40:13,  1.56it/s]
  6%|▌         | 3464/57600 [36:27<9:28:39,  1.59it/s]
  6%|▌         | 3465/57600 [36:28<9:59:17,  1.51it/s]
  6%|▌         | 3466/57600 [36:29<9:44:52,  1.54it/s]
  6%|▌         | 3467/57600 [36:29<9:30:00,  1.58it/s]
  6%|▌         | 3468/57600 [36:30<9:27:50,  1.59it/s]
  6%|▌         | 3469/57600 [36:31<9:16:30,  1.62it/s]
  6%|▌         | 3470/57600 [36:31<9:37:39,  1.56it/s]
  6%|▌         | 3471/57600 [36:32<9:55:17,  1.52it/s]
  6%|▌         | 3472/57600 [36:33<9:58:17,  1.51it/s]
  6%|▌         | 3473/57600 [36:33<9:57:29,  1.51it/s]
  6%|▌         | 3474/57600 [36:34<9:53:23,  1.52it/s]
  6%|▌         | 3475/57600 [36:35<9:40:17,  1.55it/s]
  6%|▌         | 3476/57600 [36:35<9:57:44,  1.51it/s]
  6%|▌         | 3477/57600 [36:36<9:42:54,  1.55it/s]
  6%|▌         | 3478/57600 [36:37<9:41:54,  1.55it/s]
  6%|▌         | 3479/57600 [36:37<9:24:49,  1.60it/s]
  6%|▌         | 3480/57600 [36:38<9:15:08,  1.62it/s]
                                                      
{'loss': 1.619, 'learning_rate': 9.485714285714285e-07, 'epoch': 38.41}

  6%|▌         | 3480/57600 [36:38<9:15:08,  1.62it/s]
  6%|▌         | 3481/57600 [36:38<9:15:30,  1.62it/s]
  6%|▌         | 3482/57600 [36:39<9:11:56,  1.63it/s]
  6%|▌         | 3483/57600 [36:40<9:10:15,  1.64it/s]
  6%|▌         | 3484/57600 [36:40<9:16:40,  1.62it/s]
  6%|▌         | 3485/57600 [36:41<9:08:26,  1.64it/s]
  6%|▌         | 3486/57600 [36:41<9:06:49,  1.65it/s]
  6%|▌         | 3487/57600 [36:42<9:08:56,  1.64it/s]
  6%|▌         | 3488/57600 [36:43<9:12:06,  1.63it/s]
  6%|▌         | 3489/57600 [36:43<9:09:11,  1.64it/s]
  6%|▌         | 3490/57600 [36:44<9:18:09,  1.62it/s]
  6%|▌         | 3491/57600 [36:45<9:32:49,  1.57it/s]
  6%|▌         | 3492/57600 [36:45<9:18:12,  1.62it/s]
  6%|▌         | 3493/57600 [36:46<9:27:15,  1.59it/s]
  6%|▌         | 3494/57600 [36:46<9:45:08,  1.54it/s]
  6%|▌         | 3495/57600 [36:47<9:51:39,  1.52it/s]
  6%|▌         | 3496/57600 [36:48<9:42:26,  1.55it/s]
  6%|▌         | 3497/57600 [36:48<9:37:01,  1.56it/s]
  6%|▌         | 3498/57600 [36:49<9:42:23,  1.55it/s]
  6%|▌         | 3499/57600 [36:50<10:01:32,  1.50it/s]
  6%|▌         | 3500/57600 [36:50<9:47:34,  1.53it/s] 
                                                      
{'loss': 1.6055, 'learning_rate': 9.482578397212543e-07, 'epoch': 38.63}

  6%|▌         | 3500/57600 [36:50<9:47:34,  1.53it/s]
  6%|▌         | 3501/57600 [36:51<9:38:50,  1.56it/s]
  6%|▌         | 3502/57600 [36:52<9:32:19,  1.58it/s]
  6%|▌         | 3503/57600 [36:52<9:33:36,  1.57it/s]
  6%|▌         | 3504/57600 [36:53<9:48:18,  1.53it/s]
  6%|▌         | 3505/57600 [36:54<9:44:42,  1.54it/s]
  6%|▌         | 3506/57600 [36:54<9:59:03,  1.50it/s]
  6%|▌         | 3507/57600 [36:55<9:38:35,  1.56it/s]
  6%|▌         | 3508/57600 [36:56<9:45:11,  1.54it/s]
  6%|▌         | 3509/57600 [36:56<9:37:27,  1.56it/s]
  6%|▌         | 3510/57600 [36:57<10:00:38,  1.50it/s]
  6%|▌         | 3511/57600 [36:58<10:14:03,  1.47it/s]
  6%|▌         | 3512/57600 [36:58<10:21:35,  1.45it/s]
  6%|▌         | 3513/57600 [36:59<10:30:06,  1.43it/s]
  6%|▌         | 3514/57600 [37:00<10:01:37,  1.50it/s]
  6%|▌         | 3515/57600 [37:00<9:55:39,  1.51it/s] 
  6%|▌         | 3516/57600 [37:01<9:44:30,  1.54it/s]
  6%|▌         | 3517/57600 [37:02<9:43:35,  1.54it/s]
  6%|▌         | 3518/57600 [37:02<9:33:45,  1.57it/s]
  6%|▌         | 3519/57600 [37:03<9:28:23,  1.59it/s]
  6%|▌         | 3520/57600 [37:03<9:32:10,  1.58it/s]
                                                      
{'loss': 1.6037, 'learning_rate': 9.479442508710801e-07, 'epoch': 38.85}

  6%|▌         | 3520/57600 [37:03<9:32:10,  1.58it/s]
  6%|▌         | 3521/57600 [37:04<9:15:57,  1.62it/s]
  6%|▌         | 3522/57600 [37:05<9:14:06,  1.63it/s]
  6%|▌         | 3523/57600 [37:05<9:07:52,  1.65it/s]
  6%|▌         | 3524/57600 [37:06<9:14:40,  1.62it/s]
  6%|▌         | 3525/57600 [37:06<9:06:55,  1.65it/s]
  6%|▌         | 3526/57600 [37:07<9:26:53,  1.59it/s]
  6%|▌         | 3527/57600 [37:08<9:19:25,  1.61it/s]
  6%|▌         | 3528/57600 [37:08<9:36:47,  1.56it/s]
  6%|▌         | 3529/57600 [37:09<9:34:22,  1.57it/s]
  6%|▌         | 3530/57600 [37:10<9:24:25,  1.60it/s]
  6%|▌         | 3531/57600 [37:10<9:34:20,  1.57it/s]
  6%|▌         | 3532/57600 [37:11<9:19:26,  1.61it/s]
  6%|▌         | 3533/57600 [37:11<9:24:53,  1.60it/s]
  6%|▌         | 3534/57600 [37:12<9:39:17,  1.56it/s]
  6%|▌         | 3535/57600 [37:13<9:31:12,  1.58it/s]
  6%|▌         | 3536/57600 [37:13<9:25:42,  1.59it/s]
  6%|▌         | 3537/57600 [37:14<9:28:10,  1.59it/s]
  6%|▌         | 3538/57600 [37:15<9:34:58,  1.57it/s]
  6%|▌         | 3539/57600 [37:15<9:34:43,  1.57it/s]
  6%|▌         | 3540/57600 [37:16<9:32:34,  1.57it/s]
                                                      
{'loss': 1.6259, 'learning_rate': 9.476306620209059e-07, 'epoch': 39.07}

  6%|▌         | 3540/57600 [37:16<9:32:34,  1.57it/s]
  6%|▌         | 3541/57600 [37:17<9:22:07,  1.60it/s]
  6%|▌         | 3542/57600 [37:17<9:35:20,  1.57it/s]
  6%|▌         | 3543/57600 [37:18<9:46:22,  1.54it/s]
  6%|▌         | 3544/57600 [37:19<9:33:33,  1.57it/s]
  6%|▌         | 3545/57600 [37:19<9:45:09,  1.54it/s]
  6%|▌         | 3546/57600 [37:20<9:47:43,  1.53it/s]
  6%|▌         | 3547/57600 [37:21<9:47:35,  1.53it/s]
  6%|▌         | 3548/57600 [37:21<9:49:02,  1.53it/s]
  6%|▌         | 3549/57600 [37:22<9:35:53,  1.56it/s]
  6%|▌         | 3550/57600 [37:22<9:31:30,  1.58it/s]
  6%|▌         | 3551/57600 [37:23<9:43:34,  1.54it/s]
  6%|▌         | 3552/57600 [37:24<9:40:43,  1.55it/s]
  6%|▌         | 3553/57600 [37:24<9:33:35,  1.57it/s]
  6%|▌         | 3554/57600 [37:25<9:19:14,  1.61it/s]
  6%|▌         | 3555/57600 [37:25<9:07:55,  1.64it/s]
  6%|▌         | 3556/57600 [37:26<9:16:15,  1.62it/s]
  6%|▌         | 3557/57600 [37:27<9:22:12,  1.60it/s]
  6%|▌         | 3558/57600 [37:27<9:18:16,  1.61it/s]
  6%|▌         | 3559/57600 [37:28<9:20:52,  1.61it/s]
  6%|▌         | 3560/57600 [37:29<9:24:20,  1.60it/s]
                                                      
{'loss': 1.5917, 'learning_rate': 9.473170731707316e-07, 'epoch': 39.29}

  6%|▌         | 3560/57600 [37:29<9:24:20,  1.60it/s]
  6%|▌         | 3561/57600 [37:29<9:19:31,  1.61it/s]
  6%|▌         | 3562/57600 [37:30<9:24:32,  1.60it/s]
  6%|▌         | 3563/57600 [37:31<9:26:57,  1.59it/s]
  6%|▌         | 3564/57600 [37:31<9:17:40,  1.61it/s]
  6%|▌         | 3565/57600 [37:32<9:22:11,  1.60it/s]
  6%|▌         | 3566/57600 [37:32<9:19:48,  1.61it/s]
  6%|▌         | 3567/57600 [37:33<9:28:44,  1.58it/s]
  6%|▌         | 3568/57600 [37:34<9:20:59,  1.61it/s]
  6%|▌         | 3569/57600 [37:34<9:16:04,  1.62it/s]
  6%|▌         | 3570/57600 [37:35<9:37:01,  1.56it/s]
  6%|▌         | 3571/57600 [37:36<9:32:36,  1.57it/s]
  6%|▌         | 3572/57600 [37:36<9:34:16,  1.57it/s]
  6%|▌         | 3573/57600 [37:37<9:35:28,  1.56it/s]
  6%|▌         | 3574/57600 [37:38<9:47:41,  1.53it/s]
  6%|▌         | 3575/57600 [37:38<9:48:34,  1.53it/s]
  6%|▌         | 3576/57600 [37:39<9:39:22,  1.55it/s]
  6%|▌         | 3577/57600 [37:39<9:52:31,  1.52it/s]
  6%|▌         | 3578/57600 [37:40<9:37:12,  1.56it/s]
  6%|▌         | 3579/57600 [37:41<9:20:40,  1.61it/s]
  6%|▌         | 3580/57600 [37:41<9:29:15,  1.58it/s]
                                                      
{'loss': 1.6039, 'learning_rate': 9.470034843205574e-07, 'epoch': 39.51}

  6%|▌         | 3580/57600 [37:41<9:29:15,  1.58it/s]
  6%|▌         | 3581/57600 [37:42<9:37:12,  1.56it/s]
  6%|▌         | 3582/57600 [37:43<9:33:42,  1.57it/s]
  6%|▌         | 3583/57600 [37:43<9:23:16,  1.60it/s]
  6%|▌         | 3584/57600 [37:44<9:26:19,  1.59it/s]
  6%|▌         | 3585/57600 [37:44<9:18:08,  1.61it/s]
  6%|▌         | 3586/57600 [37:45<9:11:53,  1.63it/s]
  6%|▌         | 3587/57600 [37:46<9:16:29,  1.62it/s]
  6%|▌         | 3588/57600 [37:46<9:46:40,  1.53it/s]
  6%|▌         | 3589/57600 [37:47<9:33:15,  1.57it/s]
  6%|▌         | 3590/57600 [37:48<9:34:06,  1.57it/s]
  6%|▌         | 3591/57600 [37:48<9:46:55,  1.53it/s]
  6%|▌         | 3592/57600 [37:49<10:00:42,  1.50it/s]
  6%|▌         | 3593/57600 [37:50<9:42:58,  1.54it/s] 
  6%|▌         | 3594/57600 [37:50<9:44:44,  1.54it/s]
  6%|▌         | 3595/57600 [37:51<9:36:23,  1.56it/s]
  6%|▌         | 3596/57600 [37:52<9:29:09,  1.58it/s]
  6%|▌         | 3597/57600 [37:52<9:41:07,  1.55it/s]
  6%|▌         | 3598/57600 [37:53<9:30:30,  1.58it/s]
  6%|▌         | 3599/57600 [37:54<9:53:17,  1.52it/s]
  6%|▋         | 3600/57600 [37:54<9:54:29,  1.51it/s]
                                                      
{'loss': 1.5364, 'learning_rate': 9.466898954703833e-07, 'epoch': 39.74}

  6%|▋         | 3600/57600 [37:54<9:54:29,  1.51it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00,  9.02it/s]

 50%|█████     | 3/6 [00:00<00:00,  5.83it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  5.38it/s]

 83%|████████▎ | 5/6 [00:01<00:00,  3.48it/s]

100%|██████████| 6/6 [00:01<00:00,  2.62it/s]{'score': 41.135867840420225, 'counts': [147, 94, 64, 45], 'totals': [241, 211, 181, 151], 'precisions': [60.995850622406635, 44.54976303317535, 35.35911602209945, 29.801324503311257], 'bp': 1.0, 'sys_len': 241, 'ref_len': 207}

                                                      

                                             
{'eval_loss': 2.0473527908325195, 'eval_bleu': 41.1359, 'eval_gen_len': 9.5667, 'eval_runtime': 3.9497, 'eval_samples_per_second': 7.596, 'eval_steps_per_second': 1.519, 'epoch': 39.74}

  6%|▋         | 3600/57600 [37:58<9:54:29,  1.51it/s]

100%|██████████| 6/6 [00:03<00:00,  2.62it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 07:32:11,487 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

  6%|▋         | 3601/57600 [38:10<77:18:32,  5.15s/it]
  6%|▋         | 3602/57600 [38:10<56:58:09,  3.80s/it]
  6%|▋         | 3603/57600 [38:11<42:32:48,  2.84s/it]
  6%|▋         | 3604/57600 [38:12<33:09:29,  2.21s/it]
  6%|▋         | 3605/57600 [38:13<26:21:20,  1.76s/it]
  6%|▋         | 3606/57600 [38:13<21:24:38,  1.43s/it]
  6%|▋         | 3607/57600 [38:14<18:00:56,  1.20s/it]
  6%|▋         | 3608/57600 [38:15<15:36:26,  1.04s/it]
  6%|▋         | 3609/57600 [38:15<14:03:05,  1.07it/s]
  6%|▋         | 3610/57600 [38:16<12:49:33,  1.17it/s]
  6%|▋         | 3611/57600 [38:17<11:52:32,  1.26it/s]
  6%|▋         | 3612/57600 [38:17<11:01:44,  1.36it/s]
  6%|▋         | 3613/57600 [38:18<10:45:01,  1.39it/s]
  6%|▋         | 3614/57600 [38:18<10:24:02,  1.44it/s]
  6%|▋         | 3615/57600 [38:19<10:36:15,  1.41it/s]
  6%|▋         | 3616/57600 [38:20<10:26:30,  1.44it/s]
  6%|▋         | 3617/57600 [38:20<10:11:00,  1.47it/s]
  6%|▋         | 3618/57600 [38:21<9:57:48,  1.51it/s] 
  6%|▋         | 3619/57600 [38:22<9:35:15,  1.56it/s]
  6%|▋         | 3620/57600 [38:22<9:30:56,  1.58it/s]
                                                      
{'loss': 1.6224, 'learning_rate': 9.46376306620209e-07, 'epoch': 39.96}

  6%|▋         | 3620/57600 [38:22<9:30:56,  1.58it/s]
  6%|▋         | 3621/57600 [38:23<9:27:30,  1.59it/s]
  6%|▋         | 3622/57600 [38:24<9:40:11,  1.55it/s]
  6%|▋         | 3623/57600 [38:24<9:45:42,  1.54it/s]
  6%|▋         | 3624/57600 [38:25<9:47:09,  1.53it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

  6%|▋         | 3625/57600 [38:26<10:44:05,  1.40it/s]
  6%|▋         | 3626/57600 [38:27<10:48:36,  1.39it/s]
  6%|▋         | 3627/57600 [38:27<10:24:37,  1.44it/s]
  6%|▋         | 3628/57600 [38:28<10:15:02,  1.46it/s]
  6%|▋         | 3629/57600 [38:28<9:58:55,  1.50it/s] 
  6%|▋         | 3630/57600 [38:29<10:07:58,  1.48it/s]
  6%|▋         | 3631/57600 [38:30<10:12:33,  1.47it/s]
  6%|▋         | 3632/57600 [38:31<10:10:27,  1.47it/s]
  6%|▋         | 3633/57600 [38:31<10:17:02,  1.46it/s]
  6%|▋         | 3634/57600 [38:32<10:05:00,  1.49it/s]
  6%|▋         | 3635/57600 [38:33<10:30:39,  1.43it/s]
  6%|▋         | 3636/57600 [38:33<10:22:58,  1.44it/s]
  6%|▋         | 3637/57600 [38:34<10:25:13,  1.44it/s]
  6%|▋         | 3638/57600 [38:35<10:09:49,  1.47it/s]
  6%|▋         | 3639/57600 [38:35<10:01:33,  1.50it/s]
  6%|▋         | 3640/57600 [38:36<10:04:11,  1.49it/s]
                                                       
{'loss': 1.5808, 'learning_rate': 9.460627177700348e-07, 'epoch': 40.18}

  6%|▋         | 3640/57600 [38:36<10:04:11,  1.49it/s]
  6%|▋         | 3641/57600 [38:37<10:16:48,  1.46it/s]
  6%|▋         | 3642/57600 [38:37<10:19:03,  1.45it/s]
  6%|▋         | 3643/57600 [38:38<10:01:49,  1.49it/s]
  6%|▋         | 3644/57600 [38:39<10:07:37,  1.48it/s]
  6%|▋         | 3645/57600 [38:39<10:08:04,  1.48it/s]
  6%|▋         | 3646/57600 [38:40<10:00:50,  1.50it/s]
  6%|▋         | 3647/57600 [38:41<10:01:40,  1.49it/s]
  6%|▋         | 3648/57600 [38:41<9:59:15,  1.50it/s] 
  6%|▋         | 3649/57600 [38:42<9:49:19,  1.53it/s]
  6%|▋         | 3650/57600 [38:43<9:42:36,  1.54it/s]
  6%|▋         | 3651/57600 [38:43<9:37:36,  1.56it/s]
  6%|▋         | 3652/57600 [38:44<9:33:28,  1.57it/s]
  6%|▋         | 3653/57600 [38:44<9:14:42,  1.62it/s]
  6%|▋         | 3654/57600 [38:45<9:21:59,  1.60it/s]
  6%|▋         | 3655/57600 [38:46<9:26:05,  1.59it/s]
  6%|▋         | 3656/57600 [38:46<9:36:17,  1.56it/s]
  6%|▋         | 3657/57600 [38:47<9:43:08,  1.54it/s]
  6%|▋         | 3658/57600 [38:48<9:43:14,  1.54it/s]
  6%|▋         | 3659/57600 [38:48<9:45:57,  1.53it/s]
  6%|▋         | 3660/57600 [38:49<9:43:23,  1.54it/s]
                                                      
{'loss': 1.6187, 'learning_rate': 9.457491289198605e-07, 'epoch': 40.4}

  6%|▋         | 3660/57600 [38:49<9:43:23,  1.54it/s]
  6%|▋         | 3661/57600 [38:50<9:34:42,  1.56it/s]
  6%|▋         | 3662/57600 [38:50<9:45:25,  1.54it/s]
  6%|▋         | 3663/57600 [38:51<10:01:29,  1.49it/s]
  6%|▋         | 3664/57600 [38:52<10:10:18,  1.47it/s]
  6%|▋         | 3665/57600 [38:52<9:54:31,  1.51it/s] 
  6%|▋         | 3666/57600 [38:53<9:45:01,  1.54it/s]
  6%|▋         | 3667/57600 [38:54<9:29:23,  1.58it/s]
  6%|▋         | 3668/57600 [38:54<9:28:24,  1.58it/s]
  6%|▋         | 3669/57600 [38:55<9:09:31,  1.64it/s]
  6%|▋         | 3670/57600 [38:55<9:34:01,  1.57it/s]
  6%|▋         | 3671/57600 [38:56<9:21:37,  1.60it/s]
  6%|▋         | 3672/57600 [38:57<9:55:03,  1.51it/s]
  6%|▋         | 3673/57600 [38:58<10:16:21,  1.46it/s]
  6%|▋         | 3674/57600 [38:58<10:13:03,  1.47it/s]
  6%|▋         | 3675/57600 [38:59<10:06:49,  1.48it/s]
  6%|▋         | 3676/57600 [39:00<10:07:25,  1.48it/s]
  6%|▋         | 3677/57600 [39:00<9:48:35,  1.53it/s] 
  6%|▋         | 3678/57600 [39:01<9:45:35,  1.53it/s]
  6%|▋         | 3679/57600 [39:01<9:29:18,  1.58it/s]
  6%|▋         | 3680/57600 [39:02<9:22:46,  1.60it/s]
                                                      
{'loss': 1.6131, 'learning_rate': 9.454355400696864e-07, 'epoch': 40.62}

  6%|▋         | 3680/57600 [39:02<9:22:46,  1.60it/s]
  6%|▋         | 3681/57600 [39:03<9:33:43,  1.57it/s]
  6%|▋         | 3682/57600 [39:03<9:29:50,  1.58it/s]
  6%|▋         | 3683/57600 [39:04<9:17:03,  1.61it/s]
  6%|▋         | 3684/57600 [39:05<9:23:26,  1.59it/s]
  6%|▋         | 3685/57600 [39:05<9:39:51,  1.55it/s]
  6%|▋         | 3686/57600 [39:06<9:53:18,  1.51it/s]
  6%|▋         | 3687/57600 [39:07<9:58:37,  1.50it/s]
  6%|▋         | 3688/57600 [39:07<9:40:15,  1.55it/s]
  6%|▋         | 3689/57600 [39:08<9:27:09,  1.58it/s]
  6%|▋         | 3690/57600 [39:08<9:26:00,  1.59it/s]
  6%|▋         | 3691/57600 [39:09<9:48:53,  1.53it/s]
  6%|▋         | 3692/57600 [39:10<9:35:17,  1.56it/s]
  6%|▋         | 3693/57600 [39:10<9:38:07,  1.55it/s]
  6%|▋         | 3694/57600 [39:11<9:46:46,  1.53it/s]
  6%|▋         | 3695/57600 [39:12<9:35:51,  1.56it/s]
  6%|▋         | 3696/57600 [39:12<9:23:59,  1.59it/s]
  6%|▋         | 3697/57600 [39:13<9:30:12,  1.58it/s]
  6%|▋         | 3698/57600 [39:14<9:22:53,  1.60it/s]
  6%|▋         | 3699/57600 [39:14<9:34:22,  1.56it/s]
  6%|▋         | 3700/57600 [39:15<9:36:34,  1.56it/s]
                                                      
{'loss': 1.603, 'learning_rate': 9.451219512195122e-07, 'epoch': 40.84}

  6%|▋         | 3700/57600 [39:15<9:36:34,  1.56it/s]
  6%|▋         | 3701/57600 [39:15<9:41:34,  1.54it/s]
  6%|▋         | 3702/57600 [39:16<10:17:18,  1.46it/s]
  6%|▋         | 3703/57600 [39:17<10:09:12,  1.47it/s]
  6%|▋         | 3704/57600 [39:18<10:09:56,  1.47it/s]
  6%|▋         | 3705/57600 [39:18<9:45:47,  1.53it/s] 
  6%|▋         | 3706/57600 [39:19<9:50:34,  1.52it/s]
  6%|▋         | 3707/57600 [39:20<10:02:34,  1.49it/s]
  6%|▋         | 3708/57600 [39:20<9:46:10,  1.53it/s] 
  6%|▋         | 3709/57600 [39:21<9:51:16,  1.52it/s]
  6%|▋         | 3710/57600 [39:21<9:45:58,  1.53it/s]
  6%|▋         | 3711/57600 [39:22<9:36:04,  1.56it/s]
  6%|▋         | 3712/57600 [39:23<9:41:26,  1.54it/s]
  6%|▋         | 3713/57600 [39:23<9:52:09,  1.52it/s]
  6%|▋         | 3714/57600 [39:24<9:47:03,  1.53it/s]
  6%|▋         | 3715/57600 [39:25<10:09:56,  1.47it/s]
  6%|▋         | 3716/57600 [39:25<10:04:48,  1.48it/s]
  6%|▋         | 3717/57600 [39:26<10:24:56,  1.44it/s]
  6%|▋         | 3718/57600 [39:27<10:13:27,  1.46it/s]
  6%|▋         | 3719/57600 [39:28<9:55:48,  1.51it/s] 
  6%|▋         | 3720/57600 [39:28<9:45:06,  1.53it/s]
                                                      
{'loss': 1.6253, 'learning_rate': 9.448083623693379e-07, 'epoch': 41.06}

  6%|▋         | 3720/57600 [39:28<9:45:06,  1.53it/s]
  6%|▋         | 3721/57600 [39:29<9:58:29,  1.50it/s]
  6%|▋         | 3722/57600 [39:30<10:07:01,  1.48it/s]
  6%|▋         | 3723/57600 [39:30<10:17:47,  1.45it/s]
  6%|▋         | 3724/57600 [39:31<9:58:55,  1.50it/s] 
  6%|▋         | 3725/57600 [39:32<10:33:28,  1.42it/s]
  6%|▋         | 3726/57600 [39:32<10:08:26,  1.48it/s]
  6%|▋         | 3727/57600 [39:33<10:00:44,  1.49it/s]
  6%|▋         | 3728/57600 [39:34<9:57:54,  1.50it/s] 
  6%|▋         | 3729/57600 [39:34<9:59:52,  1.50it/s]
  6%|▋         | 3730/57600 [39:35<9:59:37,  1.50it/s]
  6%|▋         | 3731/57600 [39:36<9:50:06,  1.52it/s]
  6%|▋         | 3732/57600 [39:36<9:43:38,  1.54it/s]
  6%|▋         | 3733/57600 [39:37<9:41:28,  1.54it/s]
  6%|▋         | 3734/57600 [39:37<9:45:44,  1.53it/s]
  6%|▋         | 3735/57600 [39:38<9:50:21,  1.52it/s]
  6%|▋         | 3736/57600 [39:39<9:57:34,  1.50it/s]
  6%|▋         | 3737/57600 [39:40<9:57:04,  1.50it/s]
  6%|▋         | 3738/57600 [39:40<10:05:00,  1.48it/s]
  6%|▋         | 3739/57600 [39:41<10:01:50,  1.49it/s]
  6%|▋         | 3740/57600 [39:41<9:49:38,  1.52it/s] 
                                                      
{'loss': 1.6125, 'learning_rate': 9.444947735191638e-07, 'epoch': 41.28}

  6%|▋         | 3740/57600 [39:41<9:49:38,  1.52it/s]
  6%|▋         | 3741/57600 [39:42<9:46:23,  1.53it/s]
  6%|▋         | 3742/57600 [39:43<9:40:11,  1.55it/s]
  6%|▋         | 3743/57600 [39:43<9:41:58,  1.54it/s]
  6%|▋         | 3744/57600 [39:44<9:30:58,  1.57it/s]
  7%|▋         | 3745/57600 [39:45<9:35:05,  1.56it/s]
  7%|▋         | 3746/57600 [39:45<9:57:59,  1.50it/s]
  7%|▋         | 3747/57600 [39:46<10:00:15,  1.50it/s]
  7%|▋         | 3748/57600 [39:47<10:01:23,  1.49it/s]
  7%|▋         | 3749/57600 [39:47<9:57:19,  1.50it/s] 
  7%|▋         | 3750/57600 [39:48<9:59:49,  1.50it/s]
  7%|▋         | 3751/57600 [39:49<10:06:23,  1.48it/s]
  7%|▋         | 3752/57600 [39:49<9:59:54,  1.50it/s] 
  7%|▋         | 3753/57600 [39:50<10:02:04,  1.49it/s]
  7%|▋         | 3754/57600 [39:51<9:41:37,  1.54it/s] 
  7%|▋         | 3755/57600 [39:51<9:49:31,  1.52it/s]
  7%|▋         | 3756/57600 [39:52<9:41:26,  1.54it/s]
  7%|▋         | 3757/57600 [39:53<9:51:40,  1.52it/s]
  7%|▋         | 3758/57600 [39:53<9:37:58,  1.55it/s]
  7%|▋         | 3759/57600 [39:54<9:36:16,  1.56it/s]
  7%|▋         | 3760/57600 [39:55<9:33:51,  1.56it/s]
                                                      
{'loss': 1.5777, 'learning_rate': 9.441811846689895e-07, 'epoch': 41.5}

  7%|▋         | 3760/57600 [39:55<9:33:51,  1.56it/s]
  7%|▋         | 3761/57600 [39:55<10:01:02,  1.49it/s]
  7%|▋         | 3762/57600 [39:56<10:18:44,  1.45it/s]
  7%|▋         | 3763/57600 [39:57<10:13:42,  1.46it/s]
  7%|▋         | 3764/57600 [39:57<10:17:01,  1.45it/s]
  7%|▋         | 3765/57600 [39:58<10:20:35,  1.45it/s]
  7%|▋         | 3766/57600 [39:59<10:02:47,  1.49it/s]
  7%|▋         | 3767/57600 [39:59<9:59:17,  1.50it/s] 
  7%|▋         | 3768/57600 [40:00<11:01:26,  1.36it/s]
  7%|▋         | 3769/57600 [40:01<10:40:30,  1.40it/s]
  7%|▋         | 3770/57600 [40:02<10:26:45,  1.43it/s]
  7%|▋         | 3771/57600 [40:02<10:15:22,  1.46it/s]
  7%|▋         | 3772/57600 [40:03<10:10:40,  1.47it/s]
  7%|▋         | 3773/57600 [40:04<10:00:21,  1.49it/s]
  7%|▋         | 3774/57600 [40:04<9:54:24,  1.51it/s] 
  7%|▋         | 3775/57600 [40:05<9:50:33,  1.52it/s]
  7%|▋         | 3776/57600 [40:06<9:59:02,  1.50it/s]
  7%|▋         | 3777/57600 [40:06<10:16:47,  1.45it/s]
  7%|▋         | 3778/57600 [40:07<10:29:57,  1.42it/s]
  7%|▋         | 3779/57600 [40:08<10:15:03,  1.46it/s]
  7%|▋         | 3780/57600 [40:08<10:28:42,  1.43it/s]
                                                       
{'loss': 1.5642, 'learning_rate': 9.438675958188153e-07, 'epoch': 41.72}

  7%|▋         | 3780/57600 [40:08<10:28:42,  1.43it/s]
  7%|▋         | 3781/57600 [40:09<10:18:14,  1.45it/s]
  7%|▋         | 3782/57600 [40:10<10:11:52,  1.47it/s]
  7%|▋         | 3783/57600 [40:10<10:03:49,  1.49it/s]
  7%|▋         | 3784/57600 [40:11<10:30:57,  1.42it/s]
  7%|▋         | 3785/57600 [40:12<10:14:52,  1.46it/s]
  7%|▋         | 3786/57600 [40:13<10:15:15,  1.46it/s]
  7%|▋         | 3787/57600 [40:13<10:08:30,  1.47it/s]
  7%|▋         | 3788/57600 [40:14<10:08:18,  1.47it/s]
  7%|▋         | 3789/57600 [40:15<10:01:46,  1.49it/s]
  7%|▋         | 3790/57600 [40:15<9:55:09,  1.51it/s] 
  7%|▋         | 3791/57600 [40:16<10:07:54,  1.48it/s]
  7%|▋         | 3792/57600 [40:17<10:33:36,  1.42it/s]
  7%|▋         | 3793/57600 [40:17<10:15:07,  1.46it/s]
  7%|▋         | 3794/57600 [40:18<10:04:51,  1.48it/s]
  7%|▋         | 3795/57600 [40:19<10:24:19,  1.44it/s]
  7%|▋         | 3796/57600 [40:19<10:20:11,  1.45it/s]
  7%|▋         | 3797/57600 [40:20<10:31:54,  1.42it/s]
  7%|▋         | 3798/57600 [40:21<10:05:52,  1.48it/s]
  7%|▋         | 3799/57600 [40:21<9:50:37,  1.52it/s] 
  7%|▋         | 3800/57600 [40:22<9:56:26,  1.50it/s]
                                                      
{'loss': 1.5773, 'learning_rate': 9.43554006968641e-07, 'epoch': 41.94}

  7%|▋         | 3800/57600 [40:22<9:56:26,  1.50it/s]
  7%|▋         | 3801/57600 [40:23<9:53:03,  1.51it/s]
  7%|▋         | 3802/57600 [40:23<10:11:38,  1.47it/s]
  7%|▋         | 3803/57600 [40:24<9:56:44,  1.50it/s] 
  7%|▋         | 3804/57600 [40:25<9:41:02,  1.54it/s]
  7%|▋         | 3805/57600 [40:25<9:40:43,  1.54it/s]
  7%|▋         | 3806/57600 [40:26<10:17:45,  1.45it/s]
  7%|▋         | 3807/57600 [40:27<10:17:56,  1.45it/s]
  7%|▋         | 3808/57600 [40:27<10:09:31,  1.47it/s]
  7%|▋         | 3809/57600 [40:28<10:11:09,  1.47it/s]
  7%|▋         | 3810/57600 [40:29<10:00:51,  1.49it/s]
  7%|▋         | 3811/57600 [40:29<10:06:32,  1.48it/s]
  7%|▋         | 3812/57600 [40:30<9:54:22,  1.51it/s] 
  7%|▋         | 3813/57600 [40:31<10:05:34,  1.48it/s]
  7%|▋         | 3814/57600 [40:31<10:09:26,  1.47it/s]
  7%|▋         | 3815/57600 [40:32<10:07:59,  1.47it/s]
  7%|▋         | 3816/57600 [40:33<10:51:16,  1.38it/s]
  7%|▋         | 3817/57600 [40:34<10:27:45,  1.43it/s]
  7%|▋         | 3818/57600 [40:34<10:11:00,  1.47it/s]
  7%|▋         | 3819/57600 [40:35<9:59:31,  1.50it/s] 
  7%|▋         | 3820/57600 [40:35<9:50:57,  1.52it/s]
                                                      
{'loss': 1.5218, 'learning_rate': 9.432404181184669e-07, 'epoch': 42.16}

  7%|▋         | 3820/57600 [40:36<9:50:57,  1.52it/s]
  7%|▋         | 3821/57600 [40:36<9:37:08,  1.55it/s]
  7%|▋         | 3822/57600 [40:37<9:37:12,  1.55it/s]
  7%|▋         | 3823/57600 [40:37<9:41:15,  1.54it/s]
  7%|▋         | 3824/57600 [40:38<9:49:05,  1.52it/s]
  7%|▋         | 3825/57600 [40:39<9:48:56,  1.52it/s]
  7%|▋         | 3826/57600 [40:39<9:42:10,  1.54it/s]
  7%|▋         | 3827/57600 [40:40<9:41:27,  1.54it/s]
  7%|▋         | 3828/57600 [40:41<9:38:45,  1.55it/s]
  7%|▋         | 3829/57600 [40:41<9:27:51,  1.58it/s]
  7%|▋         | 3830/57600 [40:42<9:40:01,  1.55it/s]
  7%|▋         | 3831/57600 [40:43<9:30:01,  1.57it/s]
  7%|▋         | 3832/57600 [40:43<9:22:59,  1.59it/s]
  7%|▋         | 3833/57600 [40:44<9:25:50,  1.58it/s]
  7%|▋         | 3834/57600 [40:44<9:25:52,  1.58it/s]
  7%|▋         | 3835/57600 [40:45<9:34:11,  1.56it/s]
  7%|▋         | 3836/57600 [40:46<9:32:17,  1.57it/s]
  7%|▋         | 3837/57600 [40:46<9:36:55,  1.55it/s]
  7%|▋         | 3838/57600 [40:47<9:40:36,  1.54it/s]
  7%|▋         | 3839/57600 [40:48<9:35:04,  1.56it/s]
  7%|▋         | 3840/57600 [40:48<9:35:52,  1.56it/s]
                                                      
{'loss': 1.5751, 'learning_rate': 9.429268292682926e-07, 'epoch': 42.38}

  7%|▋         | 3840/57600 [40:48<9:35:52,  1.56it/s]
  7%|▋         | 3841/57600 [40:49<9:19:19,  1.60it/s]
  7%|▋         | 3842/57600 [40:49<9:10:18,  1.63it/s]
  7%|▋         | 3843/57600 [40:50<9:24:32,  1.59it/s]
  7%|▋         | 3844/57600 [40:51<9:23:48,  1.59it/s]
  7%|▋         | 3845/57600 [40:51<9:16:09,  1.61it/s]
  7%|▋         | 3846/57600 [40:52<9:39:54,  1.54it/s]
  7%|▋         | 3847/57600 [40:53<9:27:38,  1.58it/s]
  7%|▋         | 3848/57600 [40:53<9:52:10,  1.51it/s]
  7%|▋         | 3849/57600 [40:54<9:34:24,  1.56it/s]
  7%|▋         | 3850/57600 [40:55<9:28:54,  1.57it/s]
  7%|▋         | 3851/57600 [40:55<9:09:23,  1.63it/s]
  7%|▋         | 3852/57600 [40:56<9:32:49,  1.56it/s]
  7%|▋         | 3853/57600 [40:57<9:43:08,  1.54it/s]
  7%|▋         | 3854/57600 [40:57<10:07:05,  1.48it/s]
  7%|▋         | 3855/57600 [40:58<9:43:28,  1.54it/s] 
  7%|▋         | 3856/57600 [40:59<9:39:00,  1.55it/s]
  7%|▋         | 3857/57600 [40:59<9:33:11,  1.56it/s]
  7%|▋         | 3858/57600 [41:00<9:26:12,  1.58it/s]
  7%|▋         | 3859/57600 [41:00<9:26:58,  1.58it/s]
  7%|▋         | 3860/57600 [41:01<9:21:28,  1.60it/s]
                                                      
{'loss': 1.5686, 'learning_rate': 9.426132404181184e-07, 'epoch': 42.6}

  7%|▋         | 3860/57600 [41:01<9:21:28,  1.60it/s]
  7%|▋         | 3861/57600 [41:02<9:23:37,  1.59it/s]
  7%|▋         | 3862/57600 [41:02<9:25:00,  1.59it/s]
  7%|▋         | 3863/57600 [41:03<9:17:53,  1.61it/s]
  7%|▋         | 3864/57600 [41:04<9:33:26,  1.56it/s]
  7%|▋         | 3865/57600 [41:04<9:28:51,  1.57it/s]
  7%|▋         | 3866/57600 [41:05<9:30:25,  1.57it/s]
  7%|▋         | 3867/57600 [41:05<9:32:04,  1.57it/s]
  7%|▋         | 3868/57600 [41:06<9:42:08,  1.54it/s]
  7%|▋         | 3869/57600 [41:07<9:42:59,  1.54it/s]
  7%|▋         | 3870/57600 [41:07<9:44:47,  1.53it/s]
  7%|▋         | 3871/57600 [41:08<9:48:00,  1.52it/s]
  7%|▋         | 3872/57600 [41:09<9:39:09,  1.55it/s]
  7%|▋         | 3873/57600 [41:09<9:40:38,  1.54it/s]
  7%|▋         | 3874/57600 [41:10<9:33:15,  1.56it/s]
  7%|▋         | 3875/57600 [41:11<9:27:34,  1.58it/s]
  7%|▋         | 3876/57600 [41:11<9:14:30,  1.61it/s]
  7%|▋         | 3877/57600 [41:12<9:13:14,  1.62it/s]
  7%|▋         | 3878/57600 [41:12<9:06:11,  1.64it/s]
  7%|▋         | 3879/57600 [41:13<9:33:49,  1.56it/s]
  7%|▋         | 3880/57600 [41:14<9:42:58,  1.54it/s]
                                                      
{'loss': 1.5917, 'learning_rate': 9.422996515679442e-07, 'epoch': 42.83}

  7%|▋         | 3880/57600 [41:14<9:42:58,  1.54it/s]
  7%|▋         | 3881/57600 [41:14<9:25:51,  1.58it/s]
  7%|▋         | 3882/57600 [41:15<9:17:55,  1.60it/s]
  7%|▋         | 3883/57600 [41:16<9:19:56,  1.60it/s]
  7%|▋         | 3884/57600 [41:16<9:28:06,  1.58it/s]
  7%|▋         | 3885/57600 [41:17<9:14:05,  1.62it/s]
  7%|▋         | 3886/57600 [41:18<9:35:40,  1.56it/s]
  7%|▋         | 3887/57600 [41:18<9:24:43,  1.59it/s]
  7%|▋         | 3888/57600 [41:19<9:57:13,  1.50it/s]
  7%|▋         | 3889/57600 [41:20<10:03:53,  1.48it/s]
  7%|▋         | 3890/57600 [41:20<10:02:46,  1.49it/s]
  7%|▋         | 3891/57600 [41:21<9:40:33,  1.54it/s] 
  7%|▋         | 3892/57600 [41:22<9:26:31,  1.58it/s]
  7%|▋         | 3893/57600 [41:22<9:18:32,  1.60it/s]
  7%|▋         | 3894/57600 [41:23<9:49:30,  1.52it/s]
  7%|▋         | 3895/57600 [41:23<9:37:56,  1.55it/s]
  7%|▋         | 3896/57600 [41:24<9:53:33,  1.51it/s]
  7%|▋         | 3897/57600 [41:25<9:35:32,  1.56it/s]
  7%|▋         | 3898/57600 [41:25<9:44:07,  1.53it/s]
  7%|▋         | 3899/57600 [41:26<10:08:04,  1.47it/s]
  7%|▋         | 3900/57600 [41:27<10:13:44,  1.46it/s]
                                                       
{'loss': 1.5427, 'learning_rate': 9.4198606271777e-07, 'epoch': 43.05}

  7%|▋         | 3900/57600 [41:27<10:13:44,  1.46it/s]
  7%|▋         | 3901/57600 [41:28<9:58:14,  1.50it/s] 
  7%|▋         | 3902/57600 [41:28<9:51:13,  1.51it/s]
  7%|▋         | 3903/57600 [41:29<9:46:16,  1.53it/s]
  7%|▋         | 3904/57600 [41:29<9:38:00,  1.55it/s]
  7%|▋         | 3905/57600 [41:30<9:45:31,  1.53it/s]
  7%|▋         | 3906/57600 [41:31<9:29:12,  1.57it/s]
  7%|▋         | 3907/57600 [41:31<9:15:58,  1.61it/s]
  7%|▋         | 3908/57600 [41:32<9:04:35,  1.64it/s]
  7%|▋         | 3909/57600 [41:32<9:09:09,  1.63it/s]
  7%|▋         | 3910/57600 [41:33<9:21:17,  1.59it/s]
  7%|▋         | 3911/57600 [41:34<9:19:39,  1.60it/s]
  7%|▋         | 3912/57600 [41:34<9:15:09,  1.61it/s]
  7%|▋         | 3913/57600 [41:35<9:17:15,  1.61it/s]
  7%|▋         | 3914/57600 [41:36<9:16:48,  1.61it/s]
  7%|▋         | 3915/57600 [41:36<9:35:04,  1.56it/s]
  7%|▋         | 3916/57600 [41:37<9:31:29,  1.57it/s]
  7%|▋         | 3917/57600 [41:38<9:41:09,  1.54it/s]
  7%|▋         | 3918/57600 [41:38<9:24:55,  1.58it/s]
  7%|▋         | 3919/57600 [41:39<9:21:09,  1.59it/s]
  7%|▋         | 3920/57600 [41:39<9:27:40,  1.58it/s]
                                                      
{'loss': 1.6199, 'learning_rate': 9.416724738675958e-07, 'epoch': 43.27}

  7%|▋         | 3920/57600 [41:39<9:27:40,  1.58it/s]
  7%|▋         | 3921/57600 [41:40<9:39:30,  1.54it/s]
  7%|▋         | 3922/57600 [41:41<9:34:42,  1.56it/s]
  7%|▋         | 3923/57600 [41:41<9:53:12,  1.51it/s]
  7%|▋         | 3924/57600 [41:42<9:35:10,  1.56it/s]
  7%|▋         | 3925/57600 [41:43<9:29:43,  1.57it/s]
  7%|▋         | 3926/57600 [41:43<9:45:51,  1.53it/s]
  7%|▋         | 3927/57600 [41:44<9:46:58,  1.52it/s]
  7%|▋         | 3928/57600 [41:45<9:43:20,  1.53it/s]
  7%|▋         | 3929/57600 [41:45<10:02:03,  1.49it/s]
  7%|▋         | 3930/57600 [41:46<10:08:10,  1.47it/s]
  7%|▋         | 3931/57600 [41:47<9:57:08,  1.50it/s] 
  7%|▋         | 3932/57600 [41:47<9:34:01,  1.56it/s]
  7%|▋         | 3933/57600 [41:48<9:27:27,  1.58it/s]
  7%|▋         | 3934/57600 [41:49<9:26:04,  1.58it/s]
  7%|▋         | 3935/57600 [41:49<9:22:58,  1.59it/s]
  7%|▋         | 3936/57600 [41:50<9:18:44,  1.60it/s]
  7%|▋         | 3937/57600 [41:50<9:10:48,  1.62it/s]
  7%|▋         | 3938/57600 [41:51<9:23:22,  1.59it/s]
  7%|▋         | 3939/57600 [41:52<9:32:42,  1.56it/s]
  7%|▋         | 3940/57600 [41:52<9:29:52,  1.57it/s]
                                                      
{'loss': 1.5946, 'learning_rate': 9.413588850174215e-07, 'epoch': 43.49}

  7%|▋         | 3940/57600 [41:52<9:29:52,  1.57it/s]
  7%|▋         | 3941/57600 [41:53<9:39:03,  1.54it/s]
  7%|▋         | 3942/57600 [41:54<9:21:19,  1.59it/s]
  7%|▋         | 3943/57600 [41:54<9:30:07,  1.57it/s]
  7%|▋         | 3944/57600 [41:55<9:41:41,  1.54it/s]
  7%|▋         | 3945/57600 [41:56<9:35:40,  1.55it/s]
  7%|▋         | 3946/57600 [41:56<9:24:11,  1.58it/s]
  7%|▋         | 3947/57600 [41:57<9:27:03,  1.58it/s]
  7%|▋         | 3948/57600 [41:57<9:27:08,  1.58it/s]
  7%|▋         | 3949/57600 [41:58<9:25:41,  1.58it/s]
  7%|▋         | 3950/57600 [41:59<9:20:20,  1.60it/s]
  7%|▋         | 3951/57600 [41:59<9:26:14,  1.58it/s]
  7%|▋         | 3952/57600 [42:00<9:23:37,  1.59it/s]
  7%|▋         | 3953/57600 [42:01<9:27:48,  1.57it/s]
  7%|▋         | 3954/57600 [42:01<9:33:25,  1.56it/s]
  7%|▋         | 3955/57600 [42:02<9:36:04,  1.55it/s]
  7%|▋         | 3956/57600 [42:03<9:26:35,  1.58it/s]
  7%|▋         | 3957/57600 [42:03<9:15:29,  1.61it/s]
  7%|▋         | 3958/57600 [42:04<9:06:51,  1.63it/s]
  7%|▋         | 3959/57600 [42:04<8:58:57,  1.66it/s]
  7%|▋         | 3960/57600 [42:05<8:54:02,  1.67it/s]
                                                      
{'loss': 1.6212, 'learning_rate': 9.410452961672474e-07, 'epoch': 43.71}

  7%|▋         | 3960/57600 [42:05<8:54:02,  1.67it/s]
  7%|▋         | 3961/57600 [42:06<9:16:00,  1.61it/s]
  7%|▋         | 3962/57600 [42:06<9:38:31,  1.55it/s]
  7%|▋         | 3963/57600 [42:07<10:04:58,  1.48it/s]
  7%|▋         | 3964/57600 [42:08<9:52:11,  1.51it/s] 
  7%|▋         | 3965/57600 [42:08<9:42:28,  1.53it/s]
  7%|▋         | 3966/57600 [42:09<9:31:24,  1.56it/s]
  7%|▋         | 3967/57600 [42:10<9:27:45,  1.57it/s]
  7%|▋         | 3968/57600 [42:10<9:19:05,  1.60it/s]
  7%|▋         | 3969/57600 [42:11<9:16:42,  1.61it/s]
  7%|▋         | 3970/57600 [42:11<9:19:56,  1.60it/s]
  7%|▋         | 3971/57600 [42:12<9:31:45,  1.56it/s]
  7%|▋         | 3972/57600 [42:13<9:37:32,  1.55it/s]
  7%|▋         | 3973/57600 [42:13<9:40:15,  1.54it/s]
  7%|▋         | 3974/57600 [42:14<9:47:02,  1.52it/s]
  7%|▋         | 3975/57600 [42:15<9:28:10,  1.57it/s]
  7%|▋         | 3976/57600 [42:15<9:31:02,  1.57it/s]
  7%|▋         | 3977/57600 [42:16<9:31:33,  1.56it/s]
  7%|▋         | 3978/57600 [42:17<9:29:02,  1.57it/s]
  7%|▋         | 3979/57600 [42:17<9:40:31,  1.54it/s]
  7%|▋         | 3980/57600 [42:18<9:24:02,  1.58it/s]
                                                      
{'loss': 1.5569, 'learning_rate': 9.407317073170731e-07, 'epoch': 43.93}

  7%|▋         | 3980/57600 [42:18<9:24:02,  1.58it/s]
  7%|▋         | 3981/57600 [42:18<9:25:38,  1.58it/s]
  7%|▋         | 3982/57600 [42:19<9:24:53,  1.58it/s]
  7%|▋         | 3983/57600 [42:20<9:28:26,  1.57it/s]
  7%|▋         | 3984/57600 [42:20<9:23:44,  1.59it/s]
  7%|▋         | 3985/57600 [42:21<9:15:12,  1.61it/s]
  7%|▋         | 3986/57600 [42:22<9:04:21,  1.64it/s]
  7%|▋         | 3987/57600 [42:22<9:37:41,  1.55it/s]
  7%|▋         | 3988/57600 [42:23<9:25:22,  1.58it/s]
  7%|▋         | 3989/57600 [42:24<9:36:58,  1.55it/s]
  7%|▋         | 3990/57600 [42:24<9:43:16,  1.53it/s]
  7%|▋         | 3991/57600 [42:25<9:43:01,  1.53it/s]
  7%|▋         | 3992/57600 [42:26<9:50:09,  1.51it/s]
  7%|▋         | 3993/57600 [42:26<9:43:41,  1.53it/s]
  7%|▋         | 3994/57600 [42:27<9:31:17,  1.56it/s]
  7%|▋         | 3995/57600 [42:27<9:31:14,  1.56it/s]
  7%|▋         | 3996/57600 [42:28<9:49:53,  1.51it/s]
  7%|▋         | 3997/57600 [42:29<10:02:11,  1.48it/s]
  7%|▋         | 3998/57600 [42:29<9:37:43,  1.55it/s] 
  7%|▋         | 3999/57600 [42:30<9:36:42,  1.55it/s]
  7%|▋         | 4000/57600 [42:31<9:20:58,  1.59it/s]
                                                      
{'loss': 1.521, 'learning_rate': 9.404181184668989e-07, 'epoch': 44.15}

  7%|▋         | 4000/57600 [42:31<9:20:58,  1.59it/s]
  7%|▋         | 4001/57600 [42:31<9:47:19,  1.52it/s]
  7%|▋         | 4002/57600 [42:32<9:31:55,  1.56it/s]
  7%|▋         | 4003/57600 [42:33<9:29:50,  1.57it/s]
  7%|▋         | 4004/57600 [42:33<9:15:11,  1.61it/s]
  7%|▋         | 4005/57600 [42:34<9:21:05,  1.59it/s]
  7%|▋         | 4006/57600 [42:34<9:11:53,  1.62it/s]
  7%|▋         | 4007/57600 [42:35<9:04:08,  1.64it/s]
  7%|▋         | 4008/57600 [42:36<9:16:15,  1.61it/s]
  7%|▋         | 4009/57600 [42:36<9:21:02,  1.59it/s]
  7%|▋         | 4010/57600 [42:37<9:30:07,  1.57it/s]
  7%|▋         | 4011/57600 [42:38<9:24:09,  1.58it/s]
  7%|▋         | 4012/57600 [42:38<9:16:08,  1.61it/s]
  7%|▋         | 4013/57600 [42:39<9:33:42,  1.56it/s]
  7%|▋         | 4014/57600 [42:40<9:43:05,  1.53it/s]
  7%|▋         | 4015/57600 [42:40<9:26:26,  1.58it/s]
  7%|▋         | 4016/57600 [42:41<9:09:53,  1.62it/s]
  7%|▋         | 4017/57600 [42:41<9:19:50,  1.60it/s]
  7%|▋         | 4018/57600 [42:42<9:17:38,  1.60it/s]
  7%|▋         | 4019/57600 [42:43<9:12:24,  1.62it/s]
  7%|▋         | 4020/57600 [42:43<9:09:20,  1.63it/s]
                                                      
{'loss': 1.56, 'learning_rate': 9.401045296167247e-07, 'epoch': 44.37}

  7%|▋         | 4020/57600 [42:43<9:09:20,  1.63it/s]
  7%|▋         | 4021/57600 [42:44<9:01:18,  1.65it/s]
  7%|▋         | 4022/57600 [42:44<9:24:20,  1.58it/s]
  7%|▋         | 4023/57600 [42:45<9:33:12,  1.56it/s]
  7%|▋         | 4024/57600 [42:46<9:19:36,  1.60it/s]
  7%|▋         | 4025/57600 [42:46<9:20:25,  1.59it/s]
  7%|▋         | 4026/57600 [42:47<9:15:06,  1.61it/s]
  7%|▋         | 4027/57600 [42:48<9:05:03,  1.64it/s]
  7%|▋         | 4028/57600 [42:48<9:00:28,  1.65it/s]
  7%|▋         | 4029/57600 [42:49<9:23:05,  1.59it/s]
  7%|▋         | 4030/57600 [42:50<9:43:03,  1.53it/s]
  7%|▋         | 4031/57600 [42:50<9:30:42,  1.56it/s]
  7%|▋         | 4032/57600 [42:51<10:11:25,  1.46it/s]
  7%|▋         | 4033/57600 [42:52<9:51:54,  1.51it/s] 
  7%|▋         | 4034/57600 [42:52<9:29:55,  1.57it/s]
  7%|▋         | 4035/57600 [42:53<9:23:15,  1.58it/s]
  7%|▋         | 4036/57600 [42:53<9:22:07,  1.59it/s]
  7%|▋         | 4037/57600 [42:54<9:07:39,  1.63it/s]
  7%|▋         | 4038/57600 [42:55<9:10:04,  1.62it/s]
  7%|▋         | 4039/57600 [42:55<9:21:44,  1.59it/s]
  7%|▋         | 4040/57600 [42:56<9:27:16,  1.57it/s]
                                                      
{'loss': 1.6059, 'learning_rate': 9.397909407665504e-07, 'epoch': 44.59}

  7%|▋         | 4040/57600 [42:56<9:27:16,  1.57it/s]
  7%|▋         | 4041/57600 [42:56<9:16:34,  1.60it/s]
  7%|▋         | 4042/57600 [42:57<9:09:56,  1.62it/s]
  7%|▋         | 4043/57600 [42:58<9:29:38,  1.57it/s]
  7%|▋         | 4044/57600 [42:58<9:41:38,  1.53it/s]
  7%|▋         | 4045/57600 [42:59<9:28:40,  1.57it/s]
  7%|▋         | 4046/57600 [43:00<9:23:15,  1.58it/s]
  7%|▋         | 4047/57600 [43:00<9:12:03,  1.62it/s]
  7%|▋         | 4048/57600 [43:01<9:22:03,  1.59it/s]
  7%|▋         | 4049/57600 [43:02<9:28:38,  1.57it/s]
  7%|▋         | 4050/57600 [43:02<9:24:22,  1.58it/s]
  7%|▋         | 4051/57600 [43:03<9:25:15,  1.58it/s]
  7%|▋         | 4052/57600 [43:03<9:27:06,  1.57it/s]
  7%|▋         | 4053/57600 [43:04<9:43:09,  1.53it/s]
  7%|▋         | 4054/57600 [43:05<9:41:45,  1.53it/s]
  7%|▋         | 4055/57600 [43:05<9:37:59,  1.54it/s]
  7%|▋         | 4056/57600 [43:06<9:29:50,  1.57it/s]
  7%|▋         | 4057/57600 [43:07<9:23:29,  1.58it/s]
  7%|▋         | 4058/57600 [43:07<9:19:17,  1.60it/s]
  7%|▋         | 4059/57600 [43:08<9:30:38,  1.56it/s]
  7%|▋         | 4060/57600 [43:09<9:13:53,  1.61it/s]
                                                      
{'loss': 1.5684, 'learning_rate': 9.394773519163763e-07, 'epoch': 44.81}

  7%|▋         | 4060/57600 [43:09<9:13:53,  1.61it/s]
  7%|▋         | 4061/57600 [43:09<9:22:13,  1.59it/s]
  7%|▋         | 4062/57600 [43:10<9:25:17,  1.58it/s]
  7%|▋         | 4063/57600 [43:10<9:15:22,  1.61it/s]
  7%|▋         | 4064/57600 [43:11<9:27:33,  1.57it/s]
  7%|▋         | 4065/57600 [43:12<9:51:37,  1.51it/s]
  7%|▋         | 4066/57600 [43:12<9:43:17,  1.53it/s]
  7%|▋         | 4067/57600 [43:13<9:19:19,  1.60it/s]
  7%|▋         | 4068/57600 [43:14<9:07:48,  1.63it/s]
  7%|▋         | 4069/57600 [43:14<9:22:30,  1.59it/s]
  7%|▋         | 4070/57600 [43:15<9:31:16,  1.56it/s]
  7%|▋         | 4071/57600 [43:16<9:28:07,  1.57it/s]
  7%|▋         | 4072/57600 [43:16<10:00:59,  1.48it/s]
  7%|▋         | 4073/57600 [43:17<9:47:29,  1.52it/s] 
  7%|▋         | 4074/57600 [43:18<9:47:17,  1.52it/s]
  7%|▋         | 4075/57600 [43:18<9:46:00,  1.52it/s]
  7%|▋         | 4076/57600 [43:19<9:35:37,  1.55it/s]
  7%|▋         | 4077/57600 [43:19<9:25:25,  1.58it/s]
  7%|▋         | 4078/57600 [43:20<9:44:44,  1.53it/s]
  7%|▋         | 4079/57600 [43:21<9:36:00,  1.55it/s]
  7%|▋         | 4080/57600 [43:21<9:13:04,  1.61it/s]
                                                      
{'loss': 1.539, 'learning_rate': 9.39163763066202e-07, 'epoch': 45.03}

  7%|▋         | 4080/57600 [43:21<9:13:04,  1.61it/s]
  7%|▋         | 4081/57600 [43:22<9:15:23,  1.61it/s]
  7%|▋         | 4082/57600 [43:23<9:06:19,  1.63it/s]
  7%|▋         | 4083/57600 [43:23<9:09:59,  1.62it/s]
  7%|▋         | 4084/57600 [43:24<9:09:10,  1.62it/s]
  7%|▋         | 4085/57600 [43:24<9:18:11,  1.60it/s]
  7%|▋         | 4086/57600 [43:25<9:06:21,  1.63it/s]
  7%|▋         | 4087/57600 [43:26<9:03:01,  1.64it/s]
  7%|▋         | 4088/57600 [43:26<9:27:34,  1.57it/s]
  7%|▋         | 4089/57600 [43:27<9:42:00,  1.53it/s]
  7%|▋         | 4090/57600 [43:28<9:35:57,  1.55it/s]
  7%|▋         | 4091/57600 [43:28<9:18:07,  1.60it/s]
  7%|▋         | 4092/57600 [43:29<9:42:52,  1.53it/s]
  7%|▋         | 4093/57600 [43:30<9:53:45,  1.50it/s]
  7%|▋         | 4094/57600 [43:30<9:51:40,  1.51it/s]
  7%|▋         | 4095/57600 [43:31<9:38:09,  1.54it/s]
  7%|▋         | 4096/57600 [43:32<9:49:59,  1.51it/s]
  7%|▋         | 4097/57600 [43:32<9:41:25,  1.53it/s]
  7%|▋         | 4098/57600 [43:33<9:36:56,  1.55it/s]
  7%|▋         | 4099/57600 [43:33<9:20:58,  1.59it/s]
  7%|▋         | 4100/57600 [43:34<9:06:11,  1.63it/s]
                                                      
{'loss': 1.5336, 'learning_rate': 9.388501742160278e-07, 'epoch': 45.25}

  7%|▋         | 4100/57600 [43:34<9:06:11,  1.63it/s]
  7%|▋         | 4101/57600 [43:35<9:14:47,  1.61it/s]
  7%|▋         | 4102/57600 [43:35<9:13:35,  1.61it/s]
  7%|▋         | 4103/57600 [43:36<9:12:17,  1.61it/s]
  7%|▋         | 4104/57600 [43:37<9:24:55,  1.58it/s]
  7%|▋         | 4105/57600 [43:37<9:19:12,  1.59it/s]
  7%|▋         | 4106/57600 [43:38<9:32:59,  1.56it/s]
  7%|▋         | 4107/57600 [43:39<9:37:25,  1.54it/s]
  7%|▋         | 4108/57600 [43:39<9:36:46,  1.55it/s]
  7%|▋         | 4109/57600 [43:40<9:29:29,  1.57it/s]
  7%|▋         | 4110/57600 [43:40<9:26:54,  1.57it/s]
  7%|▋         | 4111/57600 [43:41<9:29:54,  1.56it/s]
  7%|▋         | 4112/57600 [43:42<9:18:15,  1.60it/s]
  7%|▋         | 4113/57600 [43:42<9:15:07,  1.61it/s]
  7%|▋         | 4114/57600 [43:43<9:05:42,  1.63it/s]
  7%|▋         | 4115/57600 [43:43<8:59:30,  1.65it/s]
  7%|▋         | 4116/57600 [43:44<9:12:24,  1.61it/s]
  7%|▋         | 4117/57600 [43:45<9:28:07,  1.57it/s]
  7%|▋         | 4118/57600 [43:45<9:23:39,  1.58it/s]
  7%|▋         | 4119/57600 [43:46<9:42:16,  1.53it/s]
  7%|▋         | 4120/57600 [43:47<9:41:39,  1.53it/s]
                                                      
{'loss': 1.5521, 'learning_rate': 9.385365853658536e-07, 'epoch': 45.47}

  7%|▋         | 4120/57600 [43:47<9:41:39,  1.53it/s]
  7%|▋         | 4121/57600 [43:47<9:30:50,  1.56it/s]
  7%|▋         | 4122/57600 [43:48<9:25:18,  1.58it/s]
  7%|▋         | 4123/57600 [43:49<9:47:21,  1.52it/s]
  7%|▋         | 4124/57600 [43:49<9:44:50,  1.52it/s]
  7%|▋         | 4125/57600 [43:50<9:32:31,  1.56it/s]
  7%|▋         | 4126/57600 [43:51<9:17:21,  1.60it/s]
  7%|▋         | 4127/57600 [43:51<9:22:26,  1.58it/s]
  7%|▋         | 4128/57600 [43:52<9:40:01,  1.54it/s]
  7%|▋         | 4129/57600 [43:53<9:34:36,  1.55it/s]
  7%|▋         | 4130/57600 [43:53<9:29:05,  1.57it/s]
  7%|▋         | 4131/57600 [43:54<9:33:29,  1.55it/s]
  7%|▋         | 4132/57600 [43:54<9:21:54,  1.59it/s]
  7%|▋         | 4133/57600 [43:55<9:22:12,  1.59it/s]
  7%|▋         | 4134/57600 [43:56<9:30:19,  1.56it/s]
  7%|▋         | 4135/57600 [43:56<9:20:31,  1.59it/s]
  7%|▋         | 4136/57600 [43:57<9:20:21,  1.59it/s]
  7%|▋         | 4137/57600 [43:58<9:47:35,  1.52it/s]
  7%|▋         | 4138/57600 [43:58<9:53:53,  1.50it/s]
  7%|▋         | 4139/57600 [43:59<9:36:06,  1.55it/s]
  7%|▋         | 4140/57600 [44:00<9:40:32,  1.53it/s]
                                                      
{'loss': 1.5281, 'learning_rate': 9.382229965156794e-07, 'epoch': 45.7}

  7%|▋         | 4140/57600 [44:00<9:40:32,  1.53it/s]
  7%|▋         | 4141/57600 [44:00<9:40:56,  1.53it/s]
  7%|▋         | 4142/57600 [44:01<9:24:36,  1.58it/s]
  7%|▋         | 4143/57600 [44:02<9:27:40,  1.57it/s]
  7%|▋         | 4144/57600 [44:02<9:18:59,  1.59it/s]
  7%|▋         | 4145/57600 [44:03<9:16:28,  1.60it/s]
  7%|▋         | 4146/57600 [44:03<9:30:56,  1.56it/s]
  7%|▋         | 4147/57600 [44:04<9:44:38,  1.52it/s]
  7%|▋         | 4148/57600 [44:05<9:37:53,  1.54it/s]
  7%|▋         | 4149/57600 [44:05<9:28:14,  1.57it/s]
  7%|▋         | 4150/57600 [44:06<9:17:54,  1.60it/s]
  7%|▋         | 4151/57600 [44:07<9:06:37,  1.63it/s]
  7%|▋         | 4152/57600 [44:07<9:08:39,  1.62it/s]
  7%|▋         | 4153/57600 [44:08<9:07:02,  1.63it/s]
  7%|▋         | 4154/57600 [44:08<9:01:56,  1.64it/s]
  7%|▋         | 4155/57600 [44:09<9:00:06,  1.65it/s]
  7%|▋         | 4156/57600 [44:10<8:50:53,  1.68it/s]
  7%|▋         | 4157/57600 [44:10<9:00:18,  1.65it/s]
  7%|▋         | 4158/57600 [44:11<8:55:59,  1.66it/s]
  7%|▋         | 4159/57600 [44:12<9:32:55,  1.55it/s]
  7%|▋         | 4160/57600 [44:12<9:36:34,  1.54it/s]
                                                      
{'loss': 1.6375, 'learning_rate': 9.379094076655052e-07, 'epoch': 45.92}

  7%|▋         | 4160/57600 [44:12<9:36:34,  1.54it/s]
  7%|▋         | 4161/57600 [44:13<9:54:21,  1.50it/s]
  7%|▋         | 4162/57600 [44:14<9:49:17,  1.51it/s]
  7%|▋         | 4163/57600 [44:14<9:43:04,  1.53it/s]
  7%|▋         | 4164/57600 [44:15<9:25:33,  1.57it/s]
  7%|▋         | 4165/57600 [44:15<9:18:12,  1.60it/s]
  7%|▋         | 4166/57600 [44:16<9:20:39,  1.59it/s]
  7%|▋         | 4167/57600 [44:17<9:13:20,  1.61it/s]
  7%|▋         | 4168/57600 [44:17<9:52:59,  1.50it/s]
  7%|▋         | 4169/57600 [44:18<9:39:55,  1.54it/s]
  7%|▋         | 4170/57600 [44:19<9:36:24,  1.54it/s]
  7%|▋         | 4171/57600 [44:19<9:32:28,  1.56it/s]
  7%|▋         | 4172/57600 [44:20<9:27:40,  1.57it/s]
  7%|▋         | 4173/57600 [44:21<9:29:15,  1.56it/s]
  7%|▋         | 4174/57600 [44:21<9:29:30,  1.56it/s]
  7%|▋         | 4175/57600 [44:22<9:10:47,  1.62it/s]
  7%|▋         | 4176/57600 [44:22<9:03:39,  1.64it/s]
  7%|▋         | 4177/57600 [44:23<9:31:45,  1.56it/s]
  7%|▋         | 4178/57600 [44:24<9:37:29,  1.54it/s]
  7%|▋         | 4179/57600 [44:24<9:30:57,  1.56it/s]
  7%|▋         | 4180/57600 [44:25<9:47:38,  1.52it/s]
                                                      
{'loss': 1.5615, 'learning_rate': 9.375958188153309e-07, 'epoch': 46.14}

  7%|▋         | 4180/57600 [44:25<9:47:38,  1.52it/s]
  7%|▋         | 4181/57600 [44:26<9:49:49,  1.51it/s]
  7%|▋         | 4182/57600 [44:26<9:38:04,  1.54it/s]
  7%|▋         | 4183/57600 [44:27<9:29:48,  1.56it/s]
  7%|▋         | 4184/57600 [44:28<9:19:29,  1.59it/s]
  7%|▋         | 4185/57600 [44:28<9:14:21,  1.61it/s]
  7%|▋         | 4186/57600 [44:29<9:03:26,  1.64it/s]
  7%|▋         | 4187/57600 [44:29<9:04:38,  1.63it/s]
  7%|▋         | 4188/57600 [44:30<9:23:30,  1.58it/s]
  7%|▋         | 4189/57600 [44:31<9:21:15,  1.59it/s]
  7%|▋         | 4190/57600 [44:31<9:33:35,  1.55it/s]
  7%|▋         | 4191/57600 [44:32<9:18:02,  1.60it/s]
  7%|▋         | 4192/57600 [44:33<9:38:44,  1.54it/s]
  7%|▋         | 4193/57600 [44:33<9:43:45,  1.52it/s]
  7%|▋         | 4194/57600 [44:34<9:45:51,  1.52it/s]
  7%|▋         | 4195/57600 [44:35<9:28:03,  1.57it/s]
  7%|▋         | 4196/57600 [44:35<9:16:12,  1.60it/s]
  7%|▋         | 4197/57600 [44:36<9:16:11,  1.60it/s]
  7%|▋         | 4198/57600 [44:36<9:25:30,  1.57it/s]
  7%|▋         | 4199/57600 [44:37<9:23:24,  1.58it/s]
  7%|▋         | 4200/57600 [44:38<9:13:57,  1.61it/s]
                                                      
{'loss': 1.5181, 'learning_rate': 9.372822299651568e-07, 'epoch': 46.36}

  7%|▋         | 4200/57600 [44:38<9:13:57,  1.61it/s]
  7%|▋         | 4201/57600 [44:38<9:02:46,  1.64it/s]
  7%|▋         | 4202/57600 [44:39<9:19:44,  1.59it/s]
  7%|▋         | 4203/57600 [44:39<9:08:49,  1.62it/s]
  7%|▋         | 4204/57600 [44:40<9:13:10,  1.61it/s]
  7%|▋         | 4205/57600 [44:41<9:19:44,  1.59it/s]
  7%|▋         | 4206/57600 [44:41<9:12:22,  1.61it/s]
  7%|▋         | 4207/57600 [44:42<9:10:39,  1.62it/s]
  7%|▋         | 4208/57600 [44:43<9:14:06,  1.61it/s]
  7%|▋         | 4209/57600 [44:43<9:14:00,  1.61it/s]
  7%|▋         | 4210/57600 [44:44<9:22:58,  1.58it/s]
  7%|▋         | 4211/57600 [44:45<9:20:06,  1.59it/s]
  7%|▋         | 4212/57600 [44:45<9:25:05,  1.57it/s]
  7%|▋         | 4213/57600 [44:46<9:21:39,  1.58it/s]
  7%|▋         | 4214/57600 [44:46<9:12:35,  1.61it/s]
  7%|▋         | 4215/57600 [44:47<9:09:54,  1.62it/s]
  7%|▋         | 4216/57600 [44:48<9:16:43,  1.60it/s]
  7%|▋         | 4217/57600 [44:48<9:29:57,  1.56it/s]
  7%|▋         | 4218/57600 [44:49<9:27:35,  1.57it/s]
  7%|▋         | 4219/57600 [44:50<9:47:38,  1.51it/s]
  7%|▋         | 4220/57600 [44:50<9:38:03,  1.54it/s]
                                                      
{'loss': 1.6009, 'learning_rate': 9.369686411149824e-07, 'epoch': 46.58}

  7%|▋         | 4220/57600 [44:50<9:38:03,  1.54it/s]
  7%|▋         | 4221/57600 [44:51<9:28:55,  1.56it/s]
  7%|▋         | 4222/57600 [44:52<9:32:26,  1.55it/s]
  7%|▋         | 4223/57600 [44:52<9:19:45,  1.59it/s]
  7%|▋         | 4224/57600 [44:53<9:15:48,  1.60it/s]
  7%|▋         | 4225/57600 [44:54<9:55:28,  1.49it/s]
  7%|▋         | 4226/57600 [44:54<9:34:33,  1.55it/s]
  7%|▋         | 4227/57600 [44:55<9:22:31,  1.58it/s]
  7%|▋         | 4228/57600 [44:55<9:21:26,  1.58it/s]
  7%|▋         | 4229/57600 [44:56<9:20:58,  1.59it/s]
  7%|▋         | 4230/57600 [44:57<9:20:57,  1.59it/s]
  7%|▋         | 4231/57600 [44:57<9:13:41,  1.61it/s]
  7%|▋         | 4232/57600 [44:58<9:57:30,  1.49it/s]
  7%|▋         | 4233/57600 [44:59<9:39:05,  1.54it/s]
  7%|▋         | 4234/57600 [44:59<9:46:24,  1.52it/s]
  7%|▋         | 4235/57600 [45:00<10:03:56,  1.47it/s]
  7%|▋         | 4236/57600 [45:01<9:41:33,  1.53it/s] 
  7%|▋         | 4237/57600 [45:01<9:38:34,  1.54it/s]
  7%|▋         | 4238/57600 [45:02<9:25:53,  1.57it/s]
  7%|▋         | 4239/57600 [45:03<9:29:34,  1.56it/s]
  7%|▋         | 4240/57600 [45:03<9:16:52,  1.60it/s]
                                                      
{'loss': 1.5895, 'learning_rate': 9.366550522648083e-07, 'epoch': 46.8}

  7%|▋         | 4240/57600 [45:03<9:16:52,  1.60it/s]
  7%|▋         | 4241/57600 [45:04<9:24:15,  1.58it/s]
  7%|▋         | 4242/57600 [45:04<9:26:21,  1.57it/s]
  7%|▋         | 4243/57600 [45:05<9:21:21,  1.58it/s]
  7%|▋         | 4244/57600 [45:06<9:43:49,  1.52it/s]
  7%|▋         | 4245/57600 [45:07<10:24:36,  1.42it/s]
  7%|▋         | 4246/57600 [45:07<10:28:50,  1.41it/s]
  7%|▋         | 4247/57600 [45:08<10:30:23,  1.41it/s]
  7%|▋         | 4248/57600 [45:09<10:01:13,  1.48it/s]
  7%|▋         | 4249/57600 [45:09<9:49:39,  1.51it/s] 
  7%|▋         | 4250/57600 [45:10<9:43:39,  1.52it/s]
  7%|▋         | 4251/57600 [45:10<9:16:43,  1.60it/s]
  7%|▋         | 4252/57600 [45:11<9:33:43,  1.55it/s]
  7%|▋         | 4253/57600 [45:12<9:27:21,  1.57it/s]
  7%|▋         | 4254/57600 [45:12<9:20:54,  1.59it/s]
  7%|▋         | 4255/57600 [45:13<9:14:54,  1.60it/s]
  7%|▋         | 4256/57600 [45:14<9:15:58,  1.60it/s]
  7%|▋         | 4257/57600 [45:14<8:58:16,  1.65it/s]
  7%|▋         | 4258/57600 [45:15<9:10:03,  1.62it/s]
  7%|▋         | 4259/57600 [45:16<9:42:43,  1.53it/s]
  7%|▋         | 4260/57600 [45:16<9:50:08,  1.51it/s]
                                                      
{'loss': 1.5159, 'learning_rate': 9.363414634146342e-07, 'epoch': 47.02}

  7%|▋         | 4260/57600 [45:16<9:50:08,  1.51it/s]
  7%|▋         | 4261/57600 [45:17<9:41:13,  1.53it/s]
  7%|▋         | 4262/57600 [45:17<9:33:05,  1.55it/s]
  7%|▋         | 4263/57600 [45:18<9:21:42,  1.58it/s]
  7%|▋         | 4264/57600 [45:19<9:30:37,  1.56it/s]
  7%|▋         | 4265/57600 [45:19<9:15:39,  1.60it/s]
  7%|▋         | 4266/57600 [45:20<9:26:07,  1.57it/s]
  7%|▋         | 4267/57600 [45:21<9:28:46,  1.56it/s]
  7%|▋         | 4268/57600 [45:21<9:29:02,  1.56it/s]
  7%|▋         | 4269/57600 [45:22<9:26:15,  1.57it/s]
  7%|▋         | 4270/57600 [45:23<9:22:29,  1.58it/s]
  7%|▋         | 4271/57600 [45:23<9:20:36,  1.59it/s]
  7%|▋         | 4272/57600 [45:24<9:40:28,  1.53it/s]
  7%|▋         | 4273/57600 [45:24<9:23:50,  1.58it/s]
  7%|▋         | 4274/57600 [45:25<9:34:12,  1.55it/s]
  7%|▋         | 4275/57600 [45:26<9:22:27,  1.58it/s]
  7%|▋         | 4276/57600 [45:26<9:45:11,  1.52it/s]
  7%|▋         | 4277/57600 [45:27<9:34:55,  1.55it/s]
  7%|▋         | 4278/57600 [45:28<9:39:19,  1.53it/s]
  7%|▋         | 4279/57600 [45:28<9:28:08,  1.56it/s]
  7%|▋         | 4280/57600 [45:29<9:41:30,  1.53it/s]
                                                      
{'loss': 1.5179, 'learning_rate': 9.360278745644599e-07, 'epoch': 47.24}

  7%|▋         | 4280/57600 [45:29<9:41:30,  1.53it/s]
  7%|▋         | 4281/57600 [45:30<9:51:08,  1.50it/s]
  7%|▋         | 4282/57600 [45:30<9:33:14,  1.55it/s]
  7%|▋         | 4283/57600 [45:31<9:17:20,  1.59it/s]
  7%|▋         | 4284/57600 [45:31<9:07:14,  1.62it/s]
  7%|▋         | 4285/57600 [45:32<9:14:19,  1.60it/s]
  7%|▋         | 4286/57600 [45:33<9:01:35,  1.64it/s]
  7%|▋         | 4287/57600 [45:33<9:15:38,  1.60it/s]
  7%|▋         | 4288/57600 [45:34<9:37:38,  1.54it/s]
  7%|▋         | 4289/57600 [45:35<9:13:32,  1.61it/s]
  7%|▋         | 4290/57600 [45:35<9:20:05,  1.59it/s]
  7%|▋         | 4291/57600 [45:36<9:29:27,  1.56it/s]
  7%|▋         | 4292/57600 [45:36<9:04:37,  1.63it/s]
  7%|▋         | 4293/57600 [45:37<9:15:05,  1.60it/s]
  7%|▋         | 4294/57600 [45:38<9:29:39,  1.56it/s]
  7%|▋         | 4295/57600 [45:38<9:23:03,  1.58it/s]
  7%|▋         | 4296/57600 [45:39<9:29:04,  1.56it/s]
  7%|▋         | 4297/57600 [45:40<9:29:53,  1.56it/s]
  7%|▋         | 4298/57600 [45:40<9:27:21,  1.57it/s]
  7%|▋         | 4299/57600 [45:41<9:20:17,  1.59it/s]
  7%|▋         | 4300/57600 [45:42<9:14:13,  1.60it/s]
                                                      
{'loss': 1.5585, 'learning_rate': 9.357142857142857e-07, 'epoch': 47.46}

  7%|▋         | 4300/57600 [45:42<9:14:13,  1.60it/s]
  7%|▋         | 4301/57600 [45:42<9:18:29,  1.59it/s]
  7%|▋         | 4302/57600 [45:43<8:59:11,  1.65it/s]
  7%|▋         | 4303/57600 [45:43<8:55:04,  1.66it/s]
  7%|▋         | 4304/57600 [45:44<9:07:28,  1.62it/s]
  7%|▋         | 4305/57600 [45:45<9:01:28,  1.64it/s]
  7%|▋         | 4306/57600 [45:45<9:25:59,  1.57it/s]
  7%|▋         | 4307/57600 [45:46<9:17:44,  1.59it/s]
  7%|▋         | 4308/57600 [45:47<9:13:39,  1.60it/s]
  7%|▋         | 4309/57600 [45:47<9:06:53,  1.62it/s]
  7%|▋         | 4310/57600 [45:48<9:09:44,  1.62it/s]
  7%|▋         | 4311/57600 [45:48<9:02:57,  1.64it/s]
  7%|▋         | 4312/57600 [45:49<8:53:26,  1.66it/s]
  7%|▋         | 4313/57600 [45:49<8:42:27,  1.70it/s]
  7%|▋         | 4314/57600 [45:50<8:36:57,  1.72it/s]
  7%|▋         | 4315/57600 [45:51<8:36:12,  1.72it/s]
  7%|▋         | 4316/57600 [45:51<8:40:46,  1.71it/s]
  7%|▋         | 4317/57600 [45:52<8:50:41,  1.67it/s]
  7%|▋         | 4318/57600 [45:52<8:42:35,  1.70it/s]
  7%|▋         | 4319/57600 [45:53<8:57:14,  1.65it/s]
  8%|▊         | 4320/57600 [45:54<9:03:02,  1.64it/s]
                                                      
{'loss': 1.6147, 'learning_rate': 9.354006968641114e-07, 'epoch': 47.68}

  8%|▊         | 4320/57600 [45:54<9:03:02,  1.64it/s]
  8%|▊         | 4321/57600 [45:54<9:17:38,  1.59it/s]
  8%|▊         | 4322/57600 [45:55<9:21:11,  1.58it/s]
  8%|▊         | 4323/57600 [45:56<9:35:14,  1.54it/s]
  8%|▊         | 4324/57600 [45:56<9:37:05,  1.54it/s]
  8%|▊         | 4325/57600 [45:57<9:17:03,  1.59it/s]
  8%|▊         | 4326/57600 [45:58<9:12:23,  1.61it/s]
  8%|▊         | 4327/57600 [45:58<9:12:17,  1.61it/s]
  8%|▊         | 4328/57600 [45:59<9:16:00,  1.60it/s]
  8%|▊         | 4329/57600 [45:59<9:15:57,  1.60it/s]
  8%|▊         | 4330/57600 [46:00<9:17:56,  1.59it/s]
  8%|▊         | 4331/57600 [46:01<9:22:50,  1.58it/s]
  8%|▊         | 4332/57600 [46:01<9:15:02,  1.60it/s]
  8%|▊         | 4333/57600 [46:02<9:03:11,  1.63it/s]
  8%|▊         | 4334/57600 [46:03<9:07:21,  1.62it/s]
  8%|▊         | 4335/57600 [46:03<9:14:27,  1.60it/s]
  8%|▊         | 4336/57600 [46:04<9:03:40,  1.63it/s]
  8%|▊         | 4337/57600 [46:04<9:05:12,  1.63it/s]
  8%|▊         | 4338/57600 [46:05<8:57:09,  1.65it/s]
  8%|▊         | 4339/57600 [46:06<9:25:16,  1.57it/s]
  8%|▊         | 4340/57600 [46:06<9:29:59,  1.56it/s]
                                                      
{'loss': 1.5307, 'learning_rate': 9.350871080139373e-07, 'epoch': 47.9}

  8%|▊         | 4340/57600 [46:06<9:29:59,  1.56it/s]
  8%|▊         | 4341/57600 [46:07<9:37:25,  1.54it/s]
  8%|▊         | 4342/57600 [46:08<9:17:35,  1.59it/s]
  8%|▊         | 4343/57600 [46:08<9:10:53,  1.61it/s]
  8%|▊         | 4344/57600 [46:09<8:58:48,  1.65it/s]
  8%|▊         | 4345/57600 [46:09<8:54:00,  1.66it/s]
  8%|▊         | 4346/57600 [46:10<8:54:01,  1.66it/s]
  8%|▊         | 4347/57600 [46:11<9:12:44,  1.61it/s]
  8%|▊         | 4348/57600 [46:11<9:04:26,  1.63it/s]
  8%|▊         | 4349/57600 [46:12<9:30:11,  1.56it/s]
  8%|▊         | 4350/57600 [46:12<9:16:42,  1.59it/s]
  8%|▊         | 4351/57600 [46:13<8:57:33,  1.65it/s]
  8%|▊         | 4352/57600 [46:14<9:14:35,  1.60it/s]
  8%|▊         | 4353/57600 [46:14<9:20:41,  1.58it/s]
  8%|▊         | 4354/57600 [46:15<9:00:05,  1.64it/s]
  8%|▊         | 4355/57600 [46:16<8:55:55,  1.66it/s]
  8%|▊         | 4356/57600 [46:16<9:01:59,  1.64it/s]
  8%|▊         | 4357/57600 [46:17<9:00:05,  1.64it/s]
  8%|▊         | 4358/57600 [46:17<9:06:29,  1.62it/s]
  8%|▊         | 4359/57600 [46:18<9:20:49,  1.58it/s]
  8%|▊         | 4360/57600 [46:19<9:23:09,  1.58it/s]
                                                      
{'loss': 1.5673, 'learning_rate': 9.34773519163763e-07, 'epoch': 48.12}

  8%|▊         | 4360/57600 [46:19<9:23:09,  1.58it/s]
  8%|▊         | 4361/57600 [46:19<9:35:10,  1.54it/s]
  8%|▊         | 4362/57600 [46:20<9:28:33,  1.56it/s]
  8%|▊         | 4363/57600 [46:21<9:45:29,  1.52it/s]
  8%|▊         | 4364/57600 [46:21<9:27:41,  1.56it/s]
  8%|▊         | 4365/57600 [46:22<9:31:30,  1.55it/s]
  8%|▊         | 4366/57600 [46:23<9:19:09,  1.59it/s]
  8%|▊         | 4367/57600 [46:23<9:20:47,  1.58it/s]
  8%|▊         | 4368/57600 [46:24<9:30:40,  1.55it/s]
  8%|▊         | 4369/57600 [46:25<9:55:18,  1.49it/s]
  8%|▊         | 4370/57600 [46:25<9:48:00,  1.51it/s]
  8%|▊         | 4371/57600 [46:26<9:33:09,  1.55it/s]
  8%|▊         | 4372/57600 [46:26<9:17:24,  1.59it/s]
  8%|▊         | 4373/57600 [46:27<8:58:47,  1.65it/s]
  8%|▊         | 4374/57600 [46:28<8:50:01,  1.67it/s]
  8%|▊         | 4375/57600 [46:28<9:01:46,  1.64it/s]
  8%|▊         | 4376/57600 [46:29<8:56:54,  1.65it/s]
  8%|▊         | 4377/57600 [46:29<9:17:00,  1.59it/s]
  8%|▊         | 4378/57600 [46:30<9:24:13,  1.57it/s]
  8%|▊         | 4379/57600 [46:31<9:12:20,  1.61it/s]
  8%|▊         | 4380/57600 [46:31<8:59:35,  1.64it/s]
                                                      
{'loss': 1.5442, 'learning_rate': 9.344599303135888e-07, 'epoch': 48.34}

  8%|▊         | 4380/57600 [46:31<8:59:35,  1.64it/s]
  8%|▊         | 4381/57600 [46:32<8:55:56,  1.65it/s]
  8%|▊         | 4382/57600 [46:33<9:04:28,  1.63it/s]
  8%|▊         | 4383/57600 [46:33<8:56:32,  1.65it/s]
  8%|▊         | 4384/57600 [46:34<9:09:20,  1.61it/s]
  8%|▊         | 4385/57600 [46:34<9:04:11,  1.63it/s]
  8%|▊         | 4386/57600 [46:35<9:15:24,  1.60it/s]
  8%|▊         | 4387/57600 [46:36<9:10:39,  1.61it/s]
  8%|▊         | 4388/57600 [46:36<9:19:16,  1.59it/s]
  8%|▊         | 4389/57600 [46:37<9:11:09,  1.61it/s]
  8%|▊         | 4390/57600 [46:38<9:19:21,  1.59it/s]
  8%|▊         | 4391/57600 [46:38<9:17:56,  1.59it/s]
  8%|▊         | 4392/57600 [46:39<9:11:58,  1.61it/s]
  8%|▊         | 4393/57600 [46:39<9:07:32,  1.62it/s]
  8%|▊         | 4394/57600 [46:40<8:56:47,  1.65it/s]
  8%|▊         | 4395/57600 [46:41<9:12:48,  1.60it/s]
  8%|▊         | 4396/57600 [46:41<9:24:28,  1.57it/s]
  8%|▊         | 4397/57600 [46:42<9:25:14,  1.57it/s]
  8%|▊         | 4398/57600 [46:43<9:24:09,  1.57it/s]
  8%|▊         | 4399/57600 [46:43<9:19:09,  1.59it/s]
  8%|▊         | 4400/57600 [46:44<9:11:05,  1.61it/s]
                                                      
{'loss': 1.5177, 'learning_rate': 9.341463414634146e-07, 'epoch': 48.57}

  8%|▊         | 4400/57600 [46:44<9:11:05,  1.61it/s]
  8%|▊         | 4401/57600 [46:44<9:19:51,  1.58it/s]
  8%|▊         | 4402/57600 [46:45<9:14:55,  1.60it/s]
  8%|▊         | 4403/57600 [46:46<9:04:59,  1.63it/s]
  8%|▊         | 4404/57600 [46:46<8:56:08,  1.65it/s]
  8%|▊         | 4405/57600 [46:47<8:49:04,  1.68it/s]
  8%|▊         | 4406/57600 [46:47<8:40:54,  1.70it/s]
  8%|▊         | 4407/57600 [46:48<8:55:35,  1.66it/s]
  8%|▊         | 4408/57600 [46:49<8:47:51,  1.68it/s]
  8%|▊         | 4409/57600 [46:49<9:04:17,  1.63it/s]
  8%|▊         | 4410/57600 [46:50<9:09:59,  1.61it/s]
  8%|▊         | 4411/57600 [46:50<8:54:59,  1.66it/s]
  8%|▊         | 4412/57600 [46:51<8:47:45,  1.68it/s]
  8%|▊         | 4413/57600 [46:52<8:45:29,  1.69it/s]
  8%|▊         | 4414/57600 [46:52<9:01:00,  1.64it/s]
  8%|▊         | 4415/57600 [46:53<8:58:54,  1.64it/s]
  8%|▊         | 4416/57600 [46:53<9:04:47,  1.63it/s]
  8%|▊         | 4417/57600 [46:54<8:56:36,  1.65it/s]
  8%|▊         | 4418/57600 [46:55<9:06:34,  1.62it/s]
  8%|▊         | 4419/57600 [46:55<9:17:30,  1.59it/s]
  8%|▊         | 4420/57600 [46:56<9:18:05,  1.59it/s]
                                                      
{'loss': 1.5909, 'learning_rate': 9.338327526132404e-07, 'epoch': 48.79}

  8%|▊         | 4420/57600 [46:56<9:18:05,  1.59it/s]
  8%|▊         | 4421/57600 [46:57<9:04:32,  1.63it/s]
  8%|▊         | 4422/57600 [46:57<8:59:26,  1.64it/s]
  8%|▊         | 4423/57600 [46:58<8:55:38,  1.65it/s]
  8%|▊         | 4424/57600 [46:58<9:08:05,  1.62it/s]
  8%|▊         | 4425/57600 [46:59<9:05:45,  1.62it/s]
  8%|▊         | 4426/57600 [47:00<9:16:27,  1.59it/s]
  8%|▊         | 4427/57600 [47:00<9:15:03,  1.60it/s]
  8%|▊         | 4428/57600 [47:01<9:03:34,  1.63it/s]
  8%|▊         | 4429/57600 [47:01<9:04:44,  1.63it/s]
  8%|▊         | 4430/57600 [47:02<8:54:36,  1.66it/s]
  8%|▊         | 4431/57600 [47:03<8:50:21,  1.67it/s]
  8%|▊         | 4432/57600 [47:03<8:57:42,  1.65it/s]
  8%|▊         | 4433/57600 [47:04<9:19:33,  1.58it/s]
  8%|▊         | 4434/57600 [47:05<9:25:06,  1.57it/s]
  8%|▊         | 4435/57600 [47:05<9:07:20,  1.62it/s]
  8%|▊         | 4436/57600 [47:06<10:01:49,  1.47it/s]
  8%|▊         | 4437/57600 [47:07<9:51:08,  1.50it/s] 
  8%|▊         | 4438/57600 [47:07<9:30:35,  1.55it/s]
  8%|▊         | 4439/57600 [47:08<9:27:34,  1.56it/s]
  8%|▊         | 4440/57600 [47:09<9:36:46,  1.54it/s]
                                                      
{'loss': 1.5565, 'learning_rate': 9.335191637630661e-07, 'epoch': 49.01}

  8%|▊         | 4440/57600 [47:09<9:36:46,  1.54it/s]
  8%|▊         | 4441/57600 [47:09<9:31:27,  1.55it/s]
  8%|▊         | 4442/57600 [47:10<9:55:59,  1.49it/s]
  8%|▊         | 4443/57600 [47:10<9:33:01,  1.55it/s]
  8%|▊         | 4444/57600 [47:11<9:19:07,  1.58it/s]
  8%|▊         | 4445/57600 [47:12<9:27:32,  1.56it/s]
  8%|▊         | 4446/57600 [47:12<9:04:56,  1.63it/s]
  8%|▊         | 4447/57600 [47:13<8:59:39,  1.64it/s]
  8%|▊         | 4448/57600 [47:14<8:56:22,  1.65it/s]
  8%|▊         | 4449/57600 [47:14<9:24:52,  1.57it/s]
  8%|▊         | 4450/57600 [47:15<9:16:03,  1.59it/s]
  8%|▊         | 4451/57600 [47:15<9:04:58,  1.63it/s]
  8%|▊         | 4452/57600 [47:16<9:30:01,  1.55it/s]
  8%|▊         | 4453/57600 [47:17<9:30:49,  1.55it/s]
  8%|▊         | 4454/57600 [47:17<9:52:28,  1.50it/s]
  8%|▊         | 4455/57600 [47:18<9:41:36,  1.52it/s]
  8%|▊         | 4456/57600 [47:19<9:59:37,  1.48it/s]
  8%|▊         | 4457/57600 [47:19<9:40:21,  1.53it/s]
  8%|▊         | 4458/57600 [47:20<9:24:17,  1.57it/s]
  8%|▊         | 4459/57600 [47:21<9:33:25,  1.54it/s]
  8%|▊         | 4460/57600 [47:21<9:33:49,  1.54it/s]
                                                      
{'loss': 1.4945, 'learning_rate': 9.332055749128919e-07, 'epoch': 49.23}

  8%|▊         | 4460/57600 [47:21<9:33:49,  1.54it/s]
  8%|▊         | 4461/57600 [47:22<9:18:25,  1.59it/s]
  8%|▊         | 4462/57600 [47:23<9:02:42,  1.63it/s]
  8%|▊         | 4463/57600 [47:23<8:54:32,  1.66it/s]
  8%|▊         | 4464/57600 [47:24<8:42:25,  1.70it/s]
  8%|▊         | 4465/57600 [47:24<8:33:40,  1.72it/s]
  8%|▊         | 4466/57600 [47:25<8:53:28,  1.66it/s]
  8%|▊         | 4467/57600 [47:25<8:53:02,  1.66it/s]
  8%|▊         | 4468/57600 [47:26<9:05:57,  1.62it/s]
  8%|▊         | 4469/57600 [47:27<9:37:20,  1.53it/s]
  8%|▊         | 4470/57600 [47:28<9:46:07,  1.51it/s]
  8%|▊         | 4471/57600 [47:28<9:46:08,  1.51it/s]
  8%|▊         | 4472/57600 [47:29<9:20:52,  1.58it/s]
  8%|▊         | 4473/57600 [47:29<9:04:23,  1.63it/s]
  8%|▊         | 4474/57600 [47:30<9:10:52,  1.61it/s]
  8%|▊         | 4475/57600 [47:31<8:59:02,  1.64it/s]
  8%|▊         | 4476/57600 [47:31<9:07:42,  1.62it/s]
  8%|▊         | 4477/57600 [47:32<9:11:02,  1.61it/s]
  8%|▊         | 4478/57600 [47:33<9:33:02,  1.55it/s]
  8%|▊         | 4479/57600 [47:33<9:38:19,  1.53it/s]
  8%|▊         | 4480/57600 [47:34<9:30:41,  1.55it/s]
                                                      
{'loss': 1.5253, 'learning_rate': 9.328919860627177e-07, 'epoch': 49.45}

  8%|▊         | 4480/57600 [47:34<9:30:41,  1.55it/s]
  8%|▊         | 4481/57600 [47:34<9:23:43,  1.57it/s]
  8%|▊         | 4482/57600 [47:35<9:30:42,  1.55it/s]
  8%|▊         | 4483/57600 [47:36<9:13:25,  1.60it/s]
  8%|▊         | 4484/57600 [47:36<9:27:48,  1.56it/s]
  8%|▊         | 4485/57600 [47:37<9:30:32,  1.55it/s]
  8%|▊         | 4486/57600 [47:38<9:20:53,  1.58it/s]
  8%|▊         | 4487/57600 [47:38<9:21:30,  1.58it/s]
  8%|▊         | 4488/57600 [47:39<9:09:57,  1.61it/s]
  8%|▊         | 4489/57600 [47:39<8:58:21,  1.64it/s]
  8%|▊         | 4490/57600 [47:40<9:19:25,  1.58it/s]
  8%|▊         | 4491/57600 [47:41<9:00:06,  1.64it/s]
  8%|▊         | 4492/57600 [47:41<9:19:40,  1.58it/s]
  8%|▊         | 4493/57600 [47:42<9:17:38,  1.59it/s]
  8%|▊         | 4494/57600 [47:43<9:08:50,  1.61it/s]
  8%|▊         | 4495/57600 [47:43<9:07:22,  1.62it/s]
  8%|▊         | 4496/57600 [47:44<9:24:04,  1.57it/s]
  8%|▊         | 4497/57600 [47:44<9:12:46,  1.60it/s]
  8%|▊         | 4498/57600 [47:45<9:13:38,  1.60it/s]
  8%|▊         | 4499/57600 [47:46<9:05:11,  1.62it/s]
  8%|▊         | 4500/57600 [47:46<9:06:39,  1.62it/s]
                                                      
{'loss': 1.563, 'learning_rate': 9.325783972125436e-07, 'epoch': 49.67}

  8%|▊         | 4500/57600 [47:46<9:06:39,  1.62it/s]
  8%|▊         | 4501/57600 [47:47<8:58:00,  1.64it/s]
  8%|▊         | 4502/57600 [47:48<8:57:18,  1.65it/s]
  8%|▊         | 4503/57600 [47:48<9:03:25,  1.63it/s]
  8%|▊         | 4504/57600 [47:49<9:01:03,  1.64it/s]
  8%|▊         | 4505/57600 [47:49<8:52:01,  1.66it/s]
  8%|▊         | 4506/57600 [47:50<8:59:57,  1.64it/s]
  8%|▊         | 4507/57600 [47:51<9:03:44,  1.63it/s]
  8%|▊         | 4508/57600 [47:51<8:54:07,  1.66it/s]
  8%|▊         | 4509/57600 [47:52<8:48:34,  1.67it/s]
  8%|▊         | 4510/57600 [47:52<8:46:45,  1.68it/s]
  8%|▊         | 4511/57600 [47:53<8:46:43,  1.68it/s]
  8%|▊         | 4512/57600 [47:53<8:34:57,  1.72it/s]
  8%|▊         | 4513/57600 [47:54<8:31:09,  1.73it/s]
  8%|▊         | 4514/57600 [47:55<8:28:10,  1.74it/s]
  8%|▊         | 4515/57600 [47:55<8:49:13,  1.67it/s]
  8%|▊         | 4516/57600 [47:56<8:56:05,  1.65it/s]
  8%|▊         | 4517/57600 [47:57<9:02:31,  1.63it/s]
  8%|▊         | 4518/57600 [47:57<8:47:56,  1.68it/s]
  8%|▊         | 4519/57600 [47:58<8:56:53,  1.65it/s]
  8%|▊         | 4520/57600 [47:58<9:02:37,  1.63it/s]
                                                      
{'loss': 1.6016, 'learning_rate': 9.322648083623693e-07, 'epoch': 49.89}

  8%|▊         | 4520/57600 [47:58<9:02:37,  1.63it/s]
  8%|▊         | 4521/57600 [47:59<9:00:27,  1.64it/s]
  8%|▊         | 4522/57600 [48:00<9:04:24,  1.62it/s]
  8%|▊         | 4523/57600 [48:00<9:06:38,  1.62it/s]
  8%|▊         | 4524/57600 [48:01<8:45:24,  1.68it/s]
  8%|▊         | 4525/57600 [48:01<8:51:07,  1.67it/s]
  8%|▊         | 4526/57600 [48:02<8:43:08,  1.69it/s]
  8%|▊         | 4527/57600 [48:03<8:41:12,  1.70it/s]
  8%|▊         | 4528/57600 [48:03<8:50:16,  1.67it/s]
  8%|▊         | 4529/57600 [48:04<8:47:31,  1.68it/s]
  8%|▊         | 4530/57600 [48:04<8:50:44,  1.67it/s]
  8%|▊         | 4531/57600 [48:05<9:13:42,  1.60it/s]
  8%|▊         | 4532/57600 [48:06<9:05:12,  1.62it/s]
  8%|▊         | 4533/57600 [48:06<8:53:59,  1.66it/s]
  8%|▊         | 4534/57600 [48:07<8:48:15,  1.67it/s]
  8%|▊         | 4535/57600 [48:07<8:48:46,  1.67it/s]
  8%|▊         | 4536/57600 [48:08<8:53:48,  1.66it/s]
  8%|▊         | 4537/57600 [48:09<8:50:22,  1.67it/s]
  8%|▊         | 4538/57600 [48:09<8:50:57,  1.67it/s]
  8%|▊         | 4539/57600 [48:10<8:56:31,  1.65it/s]
  8%|▊         | 4540/57600 [48:10<9:01:51,  1.63it/s]
                                                      
{'loss': 1.6032, 'learning_rate': 9.319512195121951e-07, 'epoch': 50.11}

  8%|▊         | 4540/57600 [48:10<9:01:51,  1.63it/s]
  8%|▊         | 4541/57600 [48:11<9:04:20,  1.62it/s]
  8%|▊         | 4542/57600 [48:12<9:00:56,  1.63it/s]
  8%|▊         | 4543/57600 [48:12<8:54:55,  1.65it/s]
  8%|▊         | 4544/57600 [48:13<8:59:42,  1.64it/s]
  8%|▊         | 4545/57600 [48:13<9:04:32,  1.62it/s]
  8%|▊         | 4546/57600 [48:14<8:56:36,  1.65it/s]
  8%|▊         | 4547/57600 [48:15<8:53:11,  1.66it/s]
  8%|▊         | 4548/57600 [48:15<9:15:33,  1.59it/s]
  8%|▊         | 4549/57600 [48:16<9:22:46,  1.57it/s]
  8%|▊         | 4550/57600 [48:17<9:46:57,  1.51it/s]
  8%|▊         | 4551/57600 [48:17<9:34:36,  1.54it/s]
  8%|▊         | 4552/57600 [48:18<9:31:28,  1.55it/s]
  8%|▊         | 4553/57600 [48:19<9:41:42,  1.52it/s]
  8%|▊         | 4554/57600 [48:19<9:28:49,  1.55it/s]
  8%|▊         | 4555/57600 [48:20<9:24:55,  1.56it/s]
  8%|▊         | 4556/57600 [48:20<9:01:26,  1.63it/s]
  8%|▊         | 4557/57600 [48:21<9:19:28,  1.58it/s]
  8%|▊         | 4558/57600 [48:22<9:18:34,  1.58it/s]
  8%|▊         | 4559/57600 [48:22<9:08:52,  1.61it/s]
  8%|▊         | 4560/57600 [48:23<9:31:13,  1.55it/s]
                                                      
{'loss': 1.5038, 'learning_rate': 9.316376306620209e-07, 'epoch': 50.33}

  8%|▊         | 4560/57600 [48:23<9:31:13,  1.55it/s]
  8%|▊         | 4561/57600 [48:24<9:50:21,  1.50it/s]
  8%|▊         | 4562/57600 [48:24<9:35:16,  1.54it/s]
  8%|▊         | 4563/57600 [48:25<9:26:12,  1.56it/s]
  8%|▊         | 4564/57600 [48:26<9:19:15,  1.58it/s]
  8%|▊         | 4565/57600 [48:26<9:18:01,  1.58it/s]
  8%|▊         | 4566/57600 [48:27<9:00:12,  1.64it/s]
  8%|▊         | 4567/57600 [48:27<9:04:27,  1.62it/s]
  8%|▊         | 4568/57600 [48:28<9:11:00,  1.60it/s]
  8%|▊         | 4569/57600 [48:29<9:26:12,  1.56it/s]
  8%|▊         | 4570/57600 [48:29<9:12:01,  1.60it/s]
  8%|▊         | 4571/57600 [48:30<8:59:30,  1.64it/s]
  8%|▊         | 4572/57600 [48:31<8:54:59,  1.65it/s]
  8%|▊         | 4573/57600 [48:31<8:52:00,  1.66it/s]
  8%|▊         | 4574/57600 [48:32<8:52:22,  1.66it/s]
  8%|▊         | 4575/57600 [48:32<8:47:47,  1.67it/s]
  8%|▊         | 4576/57600 [48:33<9:03:38,  1.63it/s]
  8%|▊         | 4577/57600 [48:34<9:04:15,  1.62it/s]
  8%|▊         | 4578/57600 [48:34<9:03:40,  1.63it/s]
  8%|▊         | 4579/57600 [48:35<9:06:55,  1.62it/s]
  8%|▊         | 4580/57600 [48:35<9:17:24,  1.59it/s]
                                                      
{'loss': 1.545, 'learning_rate': 9.313240418118467e-07, 'epoch': 50.55}

  8%|▊         | 4580/57600 [48:35<9:17:24,  1.59it/s]
  8%|▊         | 4581/57600 [48:36<9:44:14,  1.51it/s]
  8%|▊         | 4582/57600 [48:37<9:28:26,  1.55it/s]
  8%|▊         | 4583/57600 [48:37<9:31:54,  1.55it/s]
  8%|▊         | 4584/57600 [48:38<9:33:51,  1.54it/s]
  8%|▊         | 4585/57600 [48:39<9:26:58,  1.56it/s]
  8%|▊         | 4586/57600 [48:39<9:09:20,  1.61it/s]
  8%|▊         | 4587/57600 [48:40<9:07:32,  1.61it/s]
  8%|▊         | 4588/57600 [48:41<9:19:52,  1.58it/s]
  8%|▊         | 4589/57600 [48:41<9:43:47,  1.51it/s]
  8%|▊         | 4590/57600 [48:42<9:25:26,  1.56it/s]
  8%|▊         | 4591/57600 [48:43<9:24:11,  1.57it/s]
  8%|▊         | 4592/57600 [48:43<9:24:57,  1.56it/s]
  8%|▊         | 4593/57600 [48:44<9:30:59,  1.55it/s]
  8%|▊         | 4594/57600 [48:45<9:28:58,  1.55it/s]
  8%|▊         | 4595/57600 [48:45<9:20:00,  1.58it/s]
  8%|▊         | 4596/57600 [48:46<9:18:13,  1.58it/s]
  8%|▊         | 4597/57600 [48:46<9:22:50,  1.57it/s]
  8%|▊         | 4598/57600 [48:47<9:03:22,  1.63it/s]
  8%|▊         | 4599/57600 [48:48<9:23:37,  1.57it/s]
  8%|▊         | 4600/57600 [48:48<9:02:06,  1.63it/s]
                                                      
{'loss': 1.5676, 'learning_rate': 9.310104529616724e-07, 'epoch': 50.77}

  8%|▊         | 4600/57600 [48:48<9:02:06,  1.63it/s]
  8%|▊         | 4601/57600 [48:49<8:58:20,  1.64it/s]
  8%|▊         | 4602/57600 [48:49<9:06:39,  1.62it/s]
  8%|▊         | 4603/57600 [48:50<8:57:21,  1.64it/s]
  8%|▊         | 4604/57600 [48:51<9:04:13,  1.62it/s]
  8%|▊         | 4605/57600 [48:51<8:52:11,  1.66it/s]
  8%|▊         | 4606/57600 [48:52<9:01:09,  1.63it/s]
  8%|▊         | 4607/57600 [48:53<9:10:50,  1.60it/s]
  8%|▊         | 4608/57600 [48:53<9:10:57,  1.60it/s]
  8%|▊         | 4609/57600 [48:54<9:07:50,  1.61it/s]
  8%|▊         | 4610/57600 [48:54<9:07:53,  1.61it/s]
  8%|▊         | 4611/57600 [48:55<9:04:34,  1.62it/s]
  8%|▊         | 4612/57600 [48:56<9:05:29,  1.62it/s]
  8%|▊         | 4613/57600 [48:56<9:01:25,  1.63it/s]
  8%|▊         | 4614/57600 [48:57<9:06:53,  1.61it/s]
  8%|▊         | 4615/57600 [48:57<8:59:47,  1.64it/s]
  8%|▊         | 4616/57600 [48:58<9:12:53,  1.60it/s]
  8%|▊         | 4617/57600 [48:59<9:22:26,  1.57it/s]
  8%|▊         | 4618/57600 [48:59<9:27:55,  1.55it/s]
  8%|▊         | 4619/57600 [49:00<9:15:07,  1.59it/s]
  8%|▊         | 4620/57600 [49:01<8:56:07,  1.65it/s]
                                                      
{'loss': 1.5443, 'learning_rate': 9.306968641114981e-07, 'epoch': 50.99}

  8%|▊         | 4620/57600 [49:01<8:56:07,  1.65it/s]
  8%|▊         | 4621/57600 [49:01<9:23:44,  1.57it/s]
  8%|▊         | 4622/57600 [49:02<9:25:30,  1.56it/s]
  8%|▊         | 4623/57600 [49:02<9:05:06,  1.62it/s]
  8%|▊         | 4624/57600 [49:03<9:07:59,  1.61it/s]
  8%|▊         | 4625/57600 [49:04<8:57:50,  1.64it/s]
  8%|▊         | 4626/57600 [49:04<9:01:56,  1.63it/s]
  8%|▊         | 4627/57600 [49:05<9:49:57,  1.50it/s]
  8%|▊         | 4628/57600 [49:06<9:40:07,  1.52it/s]
  8%|▊         | 4629/57600 [49:06<9:47:35,  1.50it/s]
  8%|▊         | 4630/57600 [49:07<9:30:48,  1.55it/s]
  8%|▊         | 4631/57600 [49:08<9:27:35,  1.56it/s]
  8%|▊         | 4632/57600 [49:08<9:25:21,  1.56it/s]
  8%|▊         | 4633/57600 [49:09<9:10:26,  1.60it/s]
  8%|▊         | 4634/57600 [49:09<9:05:51,  1.62it/s]
  8%|▊         | 4635/57600 [49:10<9:00:47,  1.63it/s]
  8%|▊         | 4636/57600 [49:11<8:50:57,  1.66it/s]
  8%|▊         | 4637/57600 [49:11<8:50:54,  1.66it/s]
  8%|▊         | 4638/57600 [49:12<8:54:49,  1.65it/s]
  8%|▊         | 4639/57600 [49:13<8:59:12,  1.64it/s]
  8%|▊         | 4640/57600 [49:13<8:53:10,  1.66it/s]
                                                      
{'loss': 1.5608, 'learning_rate': 9.303832752613241e-07, 'epoch': 51.21}

  8%|▊         | 4640/57600 [49:13<8:53:10,  1.66it/s]
  8%|▊         | 4641/57600 [49:14<8:55:57,  1.65it/s]
  8%|▊         | 4642/57600 [49:14<8:45:37,  1.68it/s]
  8%|▊         | 4643/57600 [49:15<9:14:26,  1.59it/s]
  8%|▊         | 4644/57600 [49:16<9:26:18,  1.56it/s]
  8%|▊         | 4645/57600 [49:16<9:26:18,  1.56it/s]
  8%|▊         | 4646/57600 [49:17<9:30:09,  1.55it/s]
  8%|▊         | 4647/57600 [49:18<9:12:56,  1.60it/s]
  8%|▊         | 4648/57600 [49:18<9:02:29,  1.63it/s]
  8%|▊         | 4649/57600 [49:19<8:52:36,  1.66it/s]
  8%|▊         | 4650/57600 [49:19<9:03:28,  1.62it/s]
  8%|▊         | 4651/57600 [49:20<8:44:36,  1.68it/s]
  8%|▊         | 4652/57600 [49:20<8:47:28,  1.67it/s]
  8%|▊         | 4653/57600 [49:21<9:05:14,  1.62it/s]
  8%|▊         | 4654/57600 [49:22<9:03:38,  1.62it/s]
  8%|▊         | 4655/57600 [49:22<8:51:50,  1.66it/s]
  8%|▊         | 4656/57600 [49:23<9:17:32,  1.58it/s]
  8%|▊         | 4657/57600 [49:24<9:10:18,  1.60it/s]
  8%|▊         | 4658/57600 [49:24<9:13:51,  1.59it/s]
  8%|▊         | 4659/57600 [49:25<9:12:03,  1.60it/s]
  8%|▊         | 4660/57600 [49:25<8:51:46,  1.66it/s]
                                                      
{'loss': 1.551, 'learning_rate': 9.300696864111497e-07, 'epoch': 51.43}

  8%|▊         | 4660/57600 [49:25<8:51:46,  1.66it/s]
  8%|▊         | 4661/57600 [49:26<9:10:01,  1.60it/s]
  8%|▊         | 4662/57600 [49:27<9:20:10,  1.58it/s]
  8%|▊         | 4663/57600 [49:27<9:17:57,  1.58it/s]
  8%|▊         | 4664/57600 [49:28<9:19:32,  1.58it/s]
  8%|▊         | 4665/57600 [49:29<9:04:22,  1.62it/s]
  8%|▊         | 4666/57600 [49:29<9:03:04,  1.62it/s]
  8%|▊         | 4667/57600 [49:30<8:57:42,  1.64it/s]
  8%|▊         | 4668/57600 [49:30<9:01:00,  1.63it/s]
  8%|▊         | 4669/57600 [49:31<9:17:22,  1.58it/s]
  8%|▊         | 4670/57600 [49:32<9:20:42,  1.57it/s]
  8%|▊         | 4671/57600 [49:32<9:09:42,  1.60it/s]
  8%|▊         | 4672/57600 [49:33<9:20:55,  1.57it/s]
  8%|▊         | 4673/57600 [49:34<9:05:39,  1.62it/s]
  8%|▊         | 4674/57600 [49:34<9:09:04,  1.61it/s]
  8%|▊         | 4675/57600 [49:35<8:49:37,  1.67it/s]
  8%|▊         | 4676/57600 [49:35<8:40:03,  1.70it/s]
  8%|▊         | 4677/57600 [49:36<8:44:24,  1.68it/s]
  8%|▊         | 4678/57600 [49:37<8:45:47,  1.68it/s]
  8%|▊         | 4679/57600 [49:37<8:40:52,  1.69it/s]
  8%|▊         | 4680/57600 [49:38<8:45:36,  1.68it/s]
                                                      
{'loss': 1.5556, 'learning_rate': 9.297560975609756e-07, 'epoch': 51.66}

  8%|▊         | 4680/57600 [49:38<8:45:36,  1.68it/s]
  8%|▊         | 4681/57600 [49:38<8:45:07,  1.68it/s]
  8%|▊         | 4682/57600 [49:39<8:47:33,  1.67it/s]
  8%|▊         | 4683/57600 [49:40<9:03:20,  1.62it/s]
  8%|▊         | 4684/57600 [49:40<8:48:12,  1.67it/s]
  8%|▊         | 4685/57600 [49:41<8:52:52,  1.66it/s]
  8%|▊         | 4686/57600 [49:41<8:47:15,  1.67it/s]
  8%|▊         | 4687/57600 [49:42<8:58:20,  1.64it/s]
  8%|▊         | 4688/57600 [49:43<8:44:38,  1.68it/s]
  8%|▊         | 4689/57600 [49:43<9:03:37,  1.62it/s]
  8%|▊         | 4690/57600 [49:44<8:59:46,  1.63it/s]
  8%|▊         | 4691/57600 [49:45<9:16:42,  1.58it/s]
  8%|▊         | 4692/57600 [49:45<9:16:08,  1.59it/s]
  8%|▊         | 4693/57600 [49:46<9:11:23,  1.60it/s]
  8%|▊         | 4694/57600 [49:46<9:41:29,  1.52it/s]
  8%|▊         | 4695/57600 [49:47<9:54:18,  1.48it/s]
  8%|▊         | 4696/57600 [49:48<9:54:07,  1.48it/s]
  8%|▊         | 4697/57600 [49:49<9:40:12,  1.52it/s]
  8%|▊         | 4698/57600 [49:49<9:09:35,  1.60it/s]
  8%|▊         | 4699/57600 [49:50<8:59:32,  1.63it/s]
  8%|▊         | 4700/57600 [49:50<8:51:53,  1.66it/s]
                                                      
{'loss': 1.5517, 'learning_rate': 9.294425087108013e-07, 'epoch': 51.88}

  8%|▊         | 4700/57600 [49:50<8:51:53,  1.66it/s]
  8%|▊         | 4701/57600 [49:51<8:46:40,  1.67it/s]
  8%|▊         | 4702/57600 [49:51<8:45:53,  1.68it/s]
  8%|▊         | 4703/57600 [49:52<8:46:07,  1.68it/s]
  8%|▊         | 4704/57600 [49:53<9:04:35,  1.62it/s]
  8%|▊         | 4705/57600 [49:53<8:56:54,  1.64it/s]
  8%|▊         | 4706/57600 [49:54<9:14:39,  1.59it/s]
  8%|▊         | 4707/57600 [49:54<8:51:25,  1.66it/s]
  8%|▊         | 4708/57600 [49:55<9:06:55,  1.61it/s]
  8%|▊         | 4709/57600 [49:56<9:04:04,  1.62it/s]
  8%|▊         | 4710/57600 [49:56<9:00:38,  1.63it/s]
  8%|▊         | 4711/57600 [49:57<8:59:49,  1.63it/s]
  8%|▊         | 4712/57600 [49:58<9:10:45,  1.60it/s]
  8%|▊         | 4713/57600 [49:58<9:11:18,  1.60it/s]
  8%|▊         | 4714/57600 [49:59<9:08:23,  1.61it/s]
  8%|▊         | 4715/57600 [49:59<9:04:04,  1.62it/s]
  8%|▊         | 4716/57600 [50:00<8:46:29,  1.67it/s]
  8%|▊         | 4717/57600 [50:01<8:54:14,  1.65it/s]
  8%|▊         | 4718/57600 [50:01<8:48:44,  1.67it/s]
  8%|▊         | 4719/57600 [50:02<8:51:55,  1.66it/s]
  8%|▊         | 4720/57600 [50:02<8:56:26,  1.64it/s]
                                                      
{'loss': 1.5384, 'learning_rate': 9.291289198606272e-07, 'epoch': 52.1}

  8%|▊         | 4720/57600 [50:02<8:56:26,  1.64it/s]
  8%|▊         | 4721/57600 [50:03<9:00:10,  1.63it/s]
  8%|▊         | 4722/57600 [50:04<9:10:36,  1.60it/s]
  8%|▊         | 4723/57600 [50:04<9:19:49,  1.57it/s]
  8%|▊         | 4724/57600 [50:05<9:08:48,  1.61it/s]
  8%|▊         | 4725/57600 [50:06<9:11:40,  1.60it/s]
  8%|▊         | 4726/57600 [50:06<9:15:11,  1.59it/s]
  8%|▊         | 4727/57600 [50:07<9:17:53,  1.58it/s]
  8%|▊         | 4728/57600 [50:08<9:24:21,  1.56it/s]
  8%|▊         | 4729/57600 [50:08<8:57:54,  1.64it/s]
  8%|▊         | 4730/57600 [50:09<9:04:13,  1.62it/s]
  8%|▊         | 4731/57600 [50:09<9:00:31,  1.63it/s]
  8%|▊         | 4732/57600 [50:10<8:49:54,  1.66it/s]
  8%|▊         | 4733/57600 [50:11<9:03:01,  1.62it/s]
  8%|▊         | 4734/57600 [50:11<8:57:01,  1.64it/s]
  8%|▊         | 4735/57600 [50:12<8:55:10,  1.65it/s]
  8%|▊         | 4736/57600 [50:12<8:53:11,  1.65it/s]
  8%|▊         | 4737/57600 [50:13<8:59:24,  1.63it/s]
  8%|▊         | 4738/57600 [50:14<8:57:25,  1.64it/s]
  8%|▊         | 4739/57600 [50:14<8:53:41,  1.65it/s]
  8%|▊         | 4740/57600 [50:15<9:06:03,  1.61it/s]
                                                      
{'loss': 1.4869, 'learning_rate': 9.288153310104528e-07, 'epoch': 52.32}

  8%|▊         | 4740/57600 [50:15<9:06:03,  1.61it/s]
  8%|▊         | 4741/57600 [50:15<9:02:00,  1.63it/s]
  8%|▊         | 4742/57600 [50:16<9:14:21,  1.59it/s]
  8%|▊         | 4743/57600 [50:17<9:11:12,  1.60it/s]
  8%|▊         | 4744/57600 [50:17<9:32:14,  1.54it/s]
  8%|▊         | 4745/57600 [50:18<9:19:42,  1.57it/s]
  8%|▊         | 4746/57600 [50:19<9:36:10,  1.53it/s]
  8%|▊         | 4747/57600 [50:19<9:25:26,  1.56it/s]
  8%|▊         | 4748/57600 [50:20<9:06:51,  1.61it/s]
  8%|▊         | 4749/57600 [50:20<9:00:55,  1.63it/s]
  8%|▊         | 4750/57600 [50:21<9:07:54,  1.61it/s]
  8%|▊         | 4751/57600 [50:22<9:18:36,  1.58it/s]
  8%|▊         | 4752/57600 [50:22<8:55:05,  1.65it/s]
  8%|▊         | 4753/57600 [50:23<8:43:07,  1.68it/s]
  8%|▊         | 4754/57600 [50:24<9:03:04,  1.62it/s]
  8%|▊         | 4755/57600 [50:24<8:50:02,  1.66it/s]
  8%|▊         | 4756/57600 [50:25<9:01:19,  1.63it/s]
  8%|▊         | 4757/57600 [50:25<9:03:13,  1.62it/s]
  8%|▊         | 4758/57600 [50:26<9:09:00,  1.60it/s]
  8%|▊         | 4759/57600 [50:27<8:55:33,  1.64it/s]
  8%|▊         | 4760/57600 [50:27<9:06:03,  1.61it/s]
                                                      
{'loss': 1.5221, 'learning_rate': 9.285017421602787e-07, 'epoch': 52.54}

  8%|▊         | 4760/57600 [50:27<9:06:03,  1.61it/s]
  8%|▊         | 4761/57600 [50:28<8:57:15,  1.64it/s]
  8%|▊         | 4762/57600 [50:28<8:55:41,  1.64it/s]
  8%|▊         | 4763/57600 [50:29<9:11:33,  1.60it/s]
  8%|▊         | 4764/57600 [50:30<9:02:14,  1.62it/s]
  8%|▊         | 4765/57600 [50:30<9:08:56,  1.60it/s]
  8%|▊         | 4766/57600 [50:31<9:01:17,  1.63it/s]
  8%|▊         | 4767/57600 [50:32<9:06:32,  1.61it/s]
  8%|▊         | 4768/57600 [50:32<9:11:36,  1.60it/s]
  8%|▊         | 4769/57600 [50:33<9:12:30,  1.59it/s]
  8%|▊         | 4770/57600 [50:34<9:16:56,  1.58it/s]
  8%|▊         | 4771/57600 [50:34<9:07:42,  1.61it/s]
  8%|▊         | 4772/57600 [50:35<9:01:51,  1.62it/s]
  8%|▊         | 4773/57600 [50:35<9:05:40,  1.61it/s]
  8%|▊         | 4774/57600 [50:36<9:16:59,  1.58it/s]
  8%|▊         | 4775/57600 [50:37<9:08:54,  1.60it/s]
  8%|▊         | 4776/57600 [50:37<9:14:19,  1.59it/s]
  8%|▊         | 4777/57600 [50:38<9:11:32,  1.60it/s]
  8%|▊         | 4778/57600 [50:38<8:52:54,  1.65it/s]
  8%|▊         | 4779/57600 [50:39<8:42:09,  1.69it/s]
  8%|▊         | 4780/57600 [50:40<8:40:23,  1.69it/s]
                                                      
{'loss': 1.5883, 'learning_rate': 9.281881533101046e-07, 'epoch': 52.76}

  8%|▊         | 4780/57600 [50:40<8:40:23,  1.69it/s]
  8%|▊         | 4781/57600 [50:40<8:49:56,  1.66it/s]
  8%|▊         | 4782/57600 [50:41<9:02:18,  1.62it/s]
  8%|▊         | 4783/57600 [50:41<8:51:49,  1.66it/s]
  8%|▊         | 4784/57600 [50:42<9:09:12,  1.60it/s]
  8%|▊         | 4785/57600 [50:43<9:07:23,  1.61it/s]
  8%|▊         | 4786/57600 [50:43<8:59:03,  1.63it/s]
  8%|▊         | 4787/57600 [50:44<9:28:03,  1.55it/s]
  8%|▊         | 4788/57600 [50:45<9:08:44,  1.60it/s]
  8%|▊         | 4789/57600 [50:45<8:48:03,  1.67it/s]
  8%|▊         | 4790/57600 [50:46<8:43:47,  1.68it/s]
  8%|▊         | 4791/57600 [50:46<8:55:14,  1.64it/s]
  8%|▊         | 4792/57600 [50:47<9:07:45,  1.61it/s]
  8%|▊         | 4793/57600 [50:48<9:14:47,  1.59it/s]
  8%|▊         | 4794/57600 [50:48<9:09:05,  1.60it/s]
  8%|▊         | 4795/57600 [50:49<8:55:25,  1.64it/s]
  8%|▊         | 4796/57600 [50:49<8:59:46,  1.63it/s]
  8%|▊         | 4797/57600 [50:50<9:11:50,  1.59it/s]
  8%|▊         | 4798/57600 [50:51<9:32:59,  1.54it/s]
  8%|▊         | 4799/57600 [50:51<9:23:03,  1.56it/s]
  8%|▊         | 4800/57600 [50:52<9:27:58,  1.55it/s]
                                                      
{'loss': 1.5276, 'learning_rate': 9.278745644599303e-07, 'epoch': 52.98}

  8%|▊         | 4800/57600 [50:52<9:27:58,  1.55it/s]
  8%|▊         | 4801/57600 [50:53<9:09:57,  1.60it/s]
  8%|▊         | 4802/57600 [50:53<9:24:37,  1.56it/s]
  8%|▊         | 4803/57600 [50:54<9:14:36,  1.59it/s]
  8%|▊         | 4804/57600 [50:55<9:04:20,  1.62it/s]
  8%|▊         | 4805/57600 [50:55<8:49:41,  1.66it/s]
  8%|▊         | 4806/57600 [50:56<8:44:31,  1.68it/s]
  8%|▊         | 4807/57600 [50:56<8:59:35,  1.63it/s]
  8%|▊         | 4808/57600 [50:57<8:48:23,  1.67it/s]
  8%|▊         | 4809/57600 [50:58<9:00:05,  1.63it/s]
  8%|▊         | 4810/57600 [50:58<9:12:13,  1.59it/s]
  8%|▊         | 4811/57600 [50:59<9:07:56,  1.61it/s]
  8%|▊         | 4812/57600 [50:59<9:04:29,  1.62it/s]
  8%|▊         | 4813/57600 [51:00<9:08:49,  1.60it/s]
  8%|▊         | 4814/57600 [51:01<9:12:23,  1.59it/s]
  8%|▊         | 4815/57600 [51:01<9:03:54,  1.62it/s]
  8%|▊         | 4816/57600 [51:02<9:10:07,  1.60it/s]
  8%|▊         | 4817/57600 [51:03<9:09:44,  1.60it/s]
  8%|▊         | 4818/57600 [51:03<9:13:03,  1.59it/s]
  8%|▊         | 4819/57600 [51:04<9:04:13,  1.62it/s]
  8%|▊         | 4820/57600 [51:04<8:54:18,  1.65it/s]
                                                      
{'loss': 1.4969, 'learning_rate': 9.275609756097561e-07, 'epoch': 53.2}

  8%|▊         | 4820/57600 [51:04<8:54:18,  1.65it/s]
  8%|▊         | 4821/57600 [51:05<8:49:50,  1.66it/s]
  8%|▊         | 4822/57600 [51:06<8:43:45,  1.68it/s]
  8%|▊         | 4823/57600 [51:06<8:49:04,  1.66it/s]
  8%|▊         | 4824/57600 [51:07<8:48:46,  1.66it/s]
  8%|▊         | 4825/57600 [51:07<8:38:09,  1.70it/s]
  8%|▊         | 4826/57600 [51:08<8:53:15,  1.65it/s]
  8%|▊         | 4827/57600 [51:09<8:48:30,  1.66it/s]
  8%|▊         | 4828/57600 [51:09<8:57:50,  1.64it/s]
  8%|▊         | 4829/57600 [51:10<8:54:32,  1.65it/s]
  8%|▊         | 4830/57600 [51:10<8:56:31,  1.64it/s]
  8%|▊         | 4831/57600 [51:11<8:50:04,  1.66it/s]
  8%|▊         | 4832/57600 [51:12<9:04:33,  1.62it/s]
  8%|▊         | 4833/57600 [51:12<9:23:10,  1.56it/s]
  8%|▊         | 4834/57600 [51:13<9:14:50,  1.59it/s]
  8%|▊         | 4835/57600 [51:14<9:19:29,  1.57it/s]
  8%|▊         | 4836/57600 [51:14<9:18:07,  1.58it/s]
  8%|▊         | 4837/57600 [51:15<9:04:37,  1.61it/s]
  8%|▊         | 4838/57600 [51:15<8:47:47,  1.67it/s]
  8%|▊         | 4839/57600 [51:16<9:06:37,  1.61it/s]
  8%|▊         | 4840/57600 [51:17<9:21:55,  1.56it/s]
                                                      
{'loss': 1.5043, 'learning_rate': 9.272473867595818e-07, 'epoch': 53.42}

  8%|▊         | 4840/57600 [51:17<9:21:55,  1.56it/s]
  8%|▊         | 4841/57600 [51:17<9:45:56,  1.50it/s]
  8%|▊         | 4842/57600 [51:18<9:34:58,  1.53it/s]
  8%|▊         | 4843/57600 [51:19<9:28:45,  1.55it/s]
  8%|▊         | 4844/57600 [51:19<9:20:09,  1.57it/s]
  8%|▊         | 4845/57600 [51:20<9:07:47,  1.61it/s]
  8%|▊         | 4846/57600 [51:21<9:11:43,  1.59it/s]
  8%|▊         | 4847/57600 [51:21<9:15:36,  1.58it/s]
  8%|▊         | 4848/57600 [51:22<9:31:35,  1.54it/s]
  8%|▊         | 4849/57600 [51:23<9:16:25,  1.58it/s]
  8%|▊         | 4850/57600 [51:23<9:03:02,  1.62it/s]
  8%|▊         | 4851/57600 [51:24<8:49:30,  1.66it/s]
  8%|▊         | 4852/57600 [51:24<8:50:16,  1.66it/s]
  8%|▊         | 4853/57600 [51:25<8:57:58,  1.63it/s]
  8%|▊         | 4854/57600 [51:25<8:51:32,  1.65it/s]
  8%|▊         | 4855/57600 [51:26<8:57:20,  1.64it/s]
  8%|▊         | 4856/57600 [51:27<9:05:14,  1.61it/s]
  8%|▊         | 4857/57600 [51:27<8:51:55,  1.65it/s]
  8%|▊         | 4858/57600 [51:28<8:45:31,  1.67it/s]
  8%|▊         | 4859/57600 [51:28<8:46:41,  1.67it/s]
  8%|▊         | 4860/57600 [51:29<8:42:38,  1.68it/s]
                                                      
{'loss': 1.5205, 'learning_rate': 9.269337979094077e-07, 'epoch': 53.64}

  8%|▊         | 4860/57600 [51:29<8:42:38,  1.68it/s]
  8%|▊         | 4861/57600 [51:30<8:58:07,  1.63it/s]
  8%|▊         | 4862/57600 [51:30<8:57:46,  1.63it/s]
  8%|▊         | 4863/57600 [51:31<9:15:43,  1.58it/s]
  8%|▊         | 4864/57600 [51:32<9:13:03,  1.59it/s]
  8%|▊         | 4865/57600 [51:32<9:39:08,  1.52it/s]
  8%|▊         | 4866/57600 [51:33<9:35:13,  1.53it/s]
  8%|▊         | 4867/57600 [51:34<9:39:58,  1.52it/s]
  8%|▊         | 4868/57600 [51:34<9:13:02,  1.59it/s]
  8%|▊         | 4869/57600 [51:35<9:12:55,  1.59it/s]
  8%|▊         | 4870/57600 [51:36<9:25:00,  1.56it/s]
  8%|▊         | 4871/57600 [51:36<9:28:10,  1.55it/s]
  8%|▊         | 4872/57600 [51:37<9:30:00,  1.54it/s]
  8%|▊         | 4873/57600 [51:37<9:10:15,  1.60it/s]
  8%|▊         | 4874/57600 [51:38<9:11:19,  1.59it/s]
  8%|▊         | 4875/57600 [51:39<9:05:02,  1.61it/s]
  8%|▊         | 4876/57600 [51:39<9:11:16,  1.59it/s]
  8%|▊         | 4877/57600 [51:40<9:04:18,  1.61it/s]
  8%|▊         | 4878/57600 [51:41<9:13:31,  1.59it/s]
  8%|▊         | 4879/57600 [51:41<9:03:14,  1.62it/s]
  8%|▊         | 4880/57600 [51:42<9:08:27,  1.60it/s]
                                                      
{'loss': 1.4685, 'learning_rate': 9.266202090592334e-07, 'epoch': 53.86}

  8%|▊         | 4880/57600 [51:42<9:08:27,  1.60it/s]
  8%|▊         | 4881/57600 [51:42<8:57:12,  1.64it/s]
  8%|▊         | 4882/57600 [51:43<8:52:56,  1.65it/s]
  8%|▊         | 4883/57600 [51:44<8:58:31,  1.63it/s]
  8%|▊         | 4884/57600 [51:44<9:00:12,  1.63it/s]
  8%|▊         | 4885/57600 [51:45<9:03:40,  1.62it/s]
  8%|▊         | 4886/57600 [51:46<9:24:31,  1.56it/s]
  8%|▊         | 4887/57600 [51:46<9:34:13,  1.53it/s]
  8%|▊         | 4888/57600 [51:47<9:46:53,  1.50it/s]
  8%|▊         | 4889/57600 [51:48<9:29:25,  1.54it/s]
  8%|▊         | 4890/57600 [51:48<9:31:31,  1.54it/s]
  8%|▊         | 4891/57600 [51:49<9:48:12,  1.49it/s]
  8%|▊         | 4892/57600 [51:50<9:41:58,  1.51it/s]
  8%|▊         | 4893/57600 [51:50<9:50:26,  1.49it/s]
  8%|▊         | 4894/57600 [51:51<9:28:26,  1.55it/s]
  8%|▊         | 4895/57600 [51:52<9:36:18,  1.52it/s]
  8%|▊         | 4896/57600 [51:52<9:47:22,  1.50it/s]
  9%|▊         | 4897/57600 [51:53<9:42:59,  1.51it/s]
  9%|▊         | 4898/57600 [51:54<10:04:29,  1.45it/s]
  9%|▊         | 4899/57600 [51:54<9:35:49,  1.53it/s] 
  9%|▊         | 4900/57600 [51:55<9:31:03,  1.54it/s]
                                                      
{'loss': 1.5099, 'learning_rate': 9.263066202090592e-07, 'epoch': 54.08}

  9%|▊         | 4900/57600 [51:55<9:31:03,  1.54it/s]
  9%|▊         | 4901/57600 [51:55<9:26:51,  1.55it/s]
  9%|▊         | 4902/57600 [51:56<9:18:19,  1.57it/s]
  9%|▊         | 4903/57600 [51:57<8:53:48,  1.65it/s]
  9%|▊         | 4904/57600 [51:57<9:08:27,  1.60it/s]
  9%|▊         | 4905/57600 [51:58<9:08:28,  1.60it/s]
  9%|▊         | 4906/57600 [51:59<9:08:28,  1.60it/s]
  9%|▊         | 4907/57600 [51:59<9:04:49,  1.61it/s]
  9%|▊         | 4908/57600 [52:00<9:36:18,  1.52it/s]
  9%|▊         | 4909/57600 [52:01<9:28:43,  1.54it/s]
  9%|▊         | 4910/57600 [52:01<9:20:26,  1.57it/s]
  9%|▊         | 4911/57600 [52:02<9:05:54,  1.61it/s]
  9%|▊         | 4912/57600 [52:02<9:13:39,  1.59it/s]
  9%|▊         | 4913/57600 [52:03<9:03:21,  1.62it/s]
  9%|▊         | 4914/57600 [52:04<9:21:24,  1.56it/s]
  9%|▊         | 4915/57600 [52:04<9:11:49,  1.59it/s]
  9%|▊         | 4916/57600 [52:05<8:53:08,  1.65it/s]
  9%|▊         | 4917/57600 [52:05<8:46:11,  1.67it/s]
  9%|▊         | 4918/57600 [52:06<8:54:26,  1.64it/s]
  9%|▊         | 4919/57600 [52:07<8:54:25,  1.64it/s]
  9%|▊         | 4920/57600 [52:07<9:06:45,  1.61it/s]
                                                      
{'loss': 1.531, 'learning_rate': 9.25993031358885e-07, 'epoch': 54.3}

  9%|▊         | 4920/57600 [52:07<9:06:45,  1.61it/s]
  9%|▊         | 4921/57600 [52:08<9:03:10,  1.62it/s]
  9%|▊         | 4922/57600 [52:08<8:57:48,  1.63it/s]
  9%|▊         | 4923/57600 [52:09<8:49:05,  1.66it/s]
  9%|▊         | 4924/57600 [52:10<8:46:14,  1.67it/s]
  9%|▊         | 4925/57600 [52:10<9:15:48,  1.58it/s]
  9%|▊         | 4926/57600 [52:11<8:57:27,  1.63it/s]
  9%|▊         | 4927/57600 [52:12<8:49:30,  1.66it/s]
  9%|▊         | 4928/57600 [52:12<8:47:30,  1.66it/s]
  9%|▊         | 4929/57600 [52:13<8:37:27,  1.70it/s]
  9%|▊         | 4930/57600 [52:13<8:34:04,  1.71it/s]
  9%|▊         | 4931/57600 [52:14<8:44:10,  1.67it/s]
  9%|▊         | 4932/57600 [52:15<8:56:46,  1.64it/s]
  9%|▊         | 4933/57600 [52:15<8:53:41,  1.64it/s]
  9%|▊         | 4934/57600 [52:16<9:12:05,  1.59it/s]
  9%|▊         | 4935/57600 [52:16<9:00:10,  1.62it/s]
  9%|▊         | 4936/57600 [52:17<9:00:35,  1.62it/s]
  9%|▊         | 4937/57600 [52:18<9:03:05,  1.62it/s]
  9%|▊         | 4938/57600 [52:18<9:40:46,  1.51it/s]
  9%|▊         | 4939/57600 [52:19<9:27:56,  1.55it/s]
  9%|▊         | 4940/57600 [52:20<9:17:07,  1.58it/s]
                                                      
{'loss': 1.5637, 'learning_rate': 9.256794425087108e-07, 'epoch': 54.53}

  9%|▊         | 4940/57600 [52:20<9:17:07,  1.58it/s]
  9%|▊         | 4941/57600 [52:20<9:24:31,  1.55it/s]
  9%|▊         | 4942/57600 [52:21<9:36:07,  1.52it/s]
  9%|▊         | 4943/57600 [52:22<9:14:22,  1.58it/s]
  9%|▊         | 4944/57600 [52:22<9:11:23,  1.59it/s]
  9%|▊         | 4945/57600 [52:23<9:03:18,  1.62it/s]
  9%|▊         | 4946/57600 [52:23<9:11:46,  1.59it/s]
  9%|▊         | 4947/57600 [52:24<9:04:29,  1.61it/s]
  9%|▊         | 4948/57600 [52:25<8:59:54,  1.63it/s]
  9%|▊         | 4949/57600 [52:25<8:57:19,  1.63it/s]
  9%|▊         | 4950/57600 [52:26<8:54:51,  1.64it/s]
  9%|▊         | 4951/57600 [52:26<8:48:40,  1.66it/s]
  9%|▊         | 4952/57600 [52:27<9:03:13,  1.62it/s]
  9%|▊         | 4953/57600 [52:28<9:04:12,  1.61it/s]
  9%|▊         | 4954/57600 [52:28<8:53:01,  1.65it/s]
  9%|▊         | 4955/57600 [52:29<8:50:39,  1.65it/s]
  9%|▊         | 4956/57600 [52:30<9:07:38,  1.60it/s]
  9%|▊         | 4957/57600 [52:30<9:05:22,  1.61it/s]
  9%|▊         | 4958/57600 [52:31<9:01:19,  1.62it/s]
  9%|▊         | 4959/57600 [52:31<8:46:02,  1.67it/s]
  9%|▊         | 4960/57600 [52:32<8:37:13,  1.70it/s]
                                                      
{'loss': 1.5795, 'learning_rate': 9.253658536585365e-07, 'epoch': 54.75}

  9%|▊         | 4960/57600 [52:32<8:37:13,  1.70it/s]
  9%|▊         | 4961/57600 [52:33<8:51:25,  1.65it/s]
  9%|▊         | 4962/57600 [52:33<9:08:45,  1.60it/s]
  9%|▊         | 4963/57600 [52:34<8:57:54,  1.63it/s]
  9%|▊         | 4964/57600 [52:34<9:14:45,  1.58it/s]
  9%|▊         | 4965/57600 [52:35<9:31:12,  1.54it/s]
  9%|▊         | 4966/57600 [52:36<9:26:18,  1.55it/s]
  9%|▊         | 4967/57600 [52:36<9:23:49,  1.56it/s]
  9%|▊         | 4968/57600 [52:37<9:22:24,  1.56it/s]
  9%|▊         | 4969/57600 [52:38<9:24:58,  1.55it/s]
  9%|▊         | 4970/57600 [52:38<9:32:55,  1.53it/s]
  9%|▊         | 4971/57600 [52:39<9:34:13,  1.53it/s]
  9%|▊         | 4972/57600 [52:40<9:43:01,  1.50it/s]
  9%|▊         | 4973/57600 [52:40<9:23:56,  1.56it/s]
  9%|▊         | 4974/57600 [52:41<9:45:42,  1.50it/s]
  9%|▊         | 4975/57600 [52:42<9:34:09,  1.53it/s]
  9%|▊         | 4976/57600 [52:42<9:20:00,  1.57it/s]
  9%|▊         | 4977/57600 [52:43<9:00:27,  1.62it/s]
  9%|▊         | 4978/57600 [52:43<9:09:33,  1.60it/s]
  9%|▊         | 4979/57600 [52:44<9:06:34,  1.60it/s]
  9%|▊         | 4980/57600 [52:45<9:06:50,  1.60it/s]
                                                      
{'loss': 1.473, 'learning_rate': 9.250522648083623e-07, 'epoch': 54.97}

  9%|▊         | 4980/57600 [52:45<9:06:50,  1.60it/s]
  9%|▊         | 4981/57600 [52:45<9:18:28,  1.57it/s]
  9%|▊         | 4982/57600 [52:46<9:11:49,  1.59it/s]
  9%|▊         | 4983/57600 [52:47<9:20:34,  1.56it/s]
  9%|▊         | 4984/57600 [52:47<9:43:05,  1.50it/s]
  9%|▊         | 4985/57600 [52:48<9:32:16,  1.53it/s]
  9%|▊         | 4986/57600 [52:49<9:38:37,  1.52it/s]
  9%|▊         | 4987/57600 [52:49<9:32:10,  1.53it/s]
  9%|▊         | 4988/57600 [52:50<9:38:10,  1.52it/s]
  9%|▊         | 4989/57600 [52:51<9:24:28,  1.55it/s]
  9%|▊         | 4990/57600 [52:51<9:24:16,  1.55it/s]
  9%|▊         | 4991/57600 [52:52<9:10:23,  1.59it/s]
  9%|▊         | 4992/57600 [52:52<9:01:48,  1.62it/s]
  9%|▊         | 4993/57600 [52:53<9:02:32,  1.62it/s]
  9%|▊         | 4994/57600 [52:54<9:04:16,  1.61it/s]
  9%|▊         | 4995/57600 [52:54<9:05:44,  1.61it/s]
  9%|▊         | 4996/57600 [52:55<8:42:52,  1.68it/s]
  9%|▊         | 4997/57600 [52:55<8:52:17,  1.65it/s]
  9%|▊         | 4998/57600 [52:56<9:13:37,  1.58it/s]
  9%|▊         | 4999/57600 [52:57<9:09:32,  1.60it/s]
  9%|▊         | 5000/57600 [52:57<9:01:25,  1.62it/s]
                                                      
{'loss': 1.4921, 'learning_rate': 9.247386759581881e-07, 'epoch': 55.19}

  9%|▊         | 5000/57600 [52:57<9:01:25,  1.62it/s]
  9%|▊         | 5001/57600 [52:58<8:56:59,  1.63it/s]
  9%|▊         | 5002/57600 [52:59<9:13:53,  1.58it/s]
  9%|▊         | 5003/57600 [52:59<9:05:54,  1.61it/s]
  9%|▊         | 5004/57600 [53:00<9:02:02,  1.62it/s]
  9%|▊         | 5005/57600 [53:00<8:48:59,  1.66it/s]
  9%|▊         | 5006/57600 [53:01<8:51:40,  1.65it/s]
  9%|▊         | 5007/57600 [53:02<8:56:07,  1.63it/s]
  9%|▊         | 5008/57600 [53:02<8:57:53,  1.63it/s]
  9%|▊         | 5009/57600 [53:03<8:58:54,  1.63it/s]
  9%|▊         | 5010/57600 [53:04<9:19:37,  1.57it/s]
  9%|▊         | 5011/57600 [53:04<9:19:50,  1.57it/s]
  9%|▊         | 5012/57600 [53:05<9:09:01,  1.60it/s]
  9%|▊         | 5013/57600 [53:05<9:07:27,  1.60it/s]
  9%|▊         | 5014/57600 [53:06<9:23:11,  1.56it/s]
  9%|▊         | 5015/57600 [53:07<9:14:11,  1.58it/s]
  9%|▊         | 5016/57600 [53:07<9:17:03,  1.57it/s]
  9%|▊         | 5017/57600 [53:08<9:03:42,  1.61it/s]
  9%|▊         | 5018/57600 [53:09<8:55:37,  1.64it/s]
  9%|▊         | 5019/57600 [53:09<8:50:49,  1.65it/s]
  9%|▊         | 5020/57600 [53:10<8:40:53,  1.68it/s]
                                                      
{'loss': 1.5147, 'learning_rate': 9.244250871080139e-07, 'epoch': 55.41}

  9%|▊         | 5020/57600 [53:10<8:40:53,  1.68it/s]
  9%|▊         | 5021/57600 [53:10<8:49:39,  1.65it/s]
  9%|▊         | 5022/57600 [53:11<8:56:42,  1.63it/s]
  9%|▊         | 5023/57600 [53:12<8:40:10,  1.68it/s]
  9%|▊         | 5024/57600 [53:12<8:49:46,  1.65it/s]
  9%|▊         | 5025/57600 [53:13<8:46:42,  1.66it/s]
  9%|▊         | 5026/57600 [53:13<9:15:38,  1.58it/s]
  9%|▊         | 5027/57600 [53:14<8:59:35,  1.62it/s]
  9%|▊         | 5028/57600 [53:15<8:49:31,  1.65it/s]
  9%|▊         | 5029/57600 [53:15<8:47:47,  1.66it/s]
  9%|▊         | 5030/57600 [53:16<8:51:53,  1.65it/s]
  9%|▊         | 5031/57600 [53:16<8:40:51,  1.68it/s]
  9%|▊         | 5032/57600 [53:17<8:50:19,  1.65it/s]
  9%|▊         | 5033/57600 [53:18<8:54:16,  1.64it/s]
  9%|▊         | 5034/57600 [53:18<8:56:47,  1.63it/s]
  9%|▊         | 5035/57600 [53:19<8:52:32,  1.65it/s]
  9%|▊         | 5036/57600 [53:19<8:38:24,  1.69it/s]
  9%|▊         | 5037/57600 [53:20<9:01:37,  1.62it/s]
  9%|▊         | 5038/57600 [53:21<9:01:53,  1.62it/s]
  9%|▊         | 5039/57600 [53:21<8:56:56,  1.63it/s]
  9%|▉         | 5040/57600 [53:22<9:09:29,  1.59it/s]
                                                      
{'loss': 1.5259, 'learning_rate': 9.241114982578397e-07, 'epoch': 55.63}

  9%|▉         | 5040/57600 [53:22<9:09:29,  1.59it/s]
  9%|▉         | 5041/57600 [53:23<9:18:31,  1.57it/s]
  9%|▉         | 5042/57600 [53:23<9:11:52,  1.59it/s]
  9%|▉         | 5043/57600 [53:24<9:20:23,  1.56it/s]
  9%|▉         | 5044/57600 [53:25<9:12:24,  1.59it/s]
  9%|▉         | 5045/57600 [53:25<9:07:43,  1.60it/s]
  9%|▉         | 5046/57600 [53:26<9:26:11,  1.55it/s]
  9%|▉         | 5047/57600 [53:26<9:27:41,  1.54it/s]
  9%|▉         | 5048/57600 [53:27<9:11:33,  1.59it/s]
  9%|▉         | 5049/57600 [53:28<8:54:36,  1.64it/s]
  9%|▉         | 5050/57600 [53:28<9:03:31,  1.61it/s]
  9%|▉         | 5051/57600 [53:29<8:54:43,  1.64it/s]
  9%|▉         | 5052/57600 [53:30<9:06:13,  1.60it/s]
  9%|▉         | 5053/57600 [53:30<8:52:20,  1.65it/s]
  9%|▉         | 5054/57600 [53:31<8:40:58,  1.68it/s]
  9%|▉         | 5055/57600 [53:31<8:33:15,  1.71it/s]
  9%|▉         | 5056/57600 [53:32<8:36:13,  1.70it/s]
  9%|▉         | 5057/57600 [53:32<8:53:21,  1.64it/s]
  9%|▉         | 5058/57600 [53:33<8:48:41,  1.66it/s]
  9%|▉         | 5059/57600 [53:34<8:44:43,  1.67it/s]
  9%|▉         | 5060/57600 [53:34<8:51:50,  1.65it/s]
                                                      
{'loss': 1.5481, 'learning_rate': 9.237979094076655e-07, 'epoch': 55.85}

  9%|▉         | 5060/57600 [53:34<8:51:50,  1.65it/s]
  9%|▉         | 5061/57600 [53:35<8:44:43,  1.67it/s]
  9%|▉         | 5062/57600 [53:35<8:32:33,  1.71it/s]
  9%|▉         | 5063/57600 [53:36<8:49:35,  1.65it/s]
  9%|▉         | 5064/57600 [53:37<8:51:59,  1.65it/s]
  9%|▉         | 5065/57600 [53:37<9:14:23,  1.58it/s]
  9%|▉         | 5066/57600 [53:38<9:25:16,  1.55it/s]
  9%|▉         | 5067/57600 [53:39<9:10:18,  1.59it/s]
  9%|▉         | 5068/57600 [53:39<9:04:13,  1.61it/s]
  9%|▉         | 5069/57600 [53:40<8:57:28,  1.63it/s]
  9%|▉         | 5070/57600 [53:40<8:50:43,  1.65it/s]
  9%|▉         | 5071/57600 [53:41<8:53:01,  1.64it/s]
  9%|▉         | 5072/57600 [53:42<8:35:57,  1.70it/s]
  9%|▉         | 5073/57600 [53:42<8:32:31,  1.71it/s]
  9%|▉         | 5074/57600 [53:43<9:08:26,  1.60it/s]
  9%|▉         | 5075/57600 [53:43<9:05:14,  1.61it/s]
  9%|▉         | 5076/57600 [53:44<9:07:24,  1.60it/s]
  9%|▉         | 5077/57600 [53:45<9:07:42,  1.60it/s]
  9%|▉         | 5078/57600 [53:45<9:11:33,  1.59it/s]
  9%|▉         | 5079/57600 [53:46<9:06:53,  1.60it/s]
  9%|▉         | 5080/57600 [53:47<9:26:06,  1.55it/s]
                                                      
{'loss': 1.5238, 'learning_rate': 9.234843205574913e-07, 'epoch': 56.07}

  9%|▉         | 5080/57600 [53:47<9:26:06,  1.55it/s]
  9%|▉         | 5081/57600 [53:47<9:25:32,  1.55it/s]
  9%|▉         | 5082/57600 [53:48<9:12:54,  1.58it/s]
  9%|▉         | 5083/57600 [53:49<9:09:16,  1.59it/s]
  9%|▉         | 5084/57600 [53:49<9:17:51,  1.57it/s]
  9%|▉         | 5085/57600 [53:50<9:01:07,  1.62it/s]
  9%|▉         | 5086/57600 [53:50<8:49:03,  1.65it/s]
  9%|▉         | 5087/57600 [53:51<8:41:47,  1.68it/s]
  9%|▉         | 5088/57600 [53:52<8:47:13,  1.66it/s]
  9%|▉         | 5089/57600 [53:52<9:08:20,  1.60it/s]
  9%|▉         | 5090/57600 [53:53<9:08:09,  1.60it/s]
  9%|▉         | 5091/57600 [53:53<9:07:56,  1.60it/s]
  9%|▉         | 5092/57600 [53:54<8:58:26,  1.63it/s]
  9%|▉         | 5093/57600 [53:55<8:49:51,  1.65it/s]
  9%|▉         | 5094/57600 [53:55<8:36:39,  1.69it/s]
  9%|▉         | 5095/57600 [53:56<8:43:04,  1.67it/s]
  9%|▉         | 5096/57600 [53:56<8:34:23,  1.70it/s]
  9%|▉         | 5097/57600 [53:57<8:47:24,  1.66it/s]
  9%|▉         | 5098/57600 [53:58<8:35:24,  1.70it/s]
  9%|▉         | 5099/57600 [53:58<8:38:55,  1.69it/s]
  9%|▉         | 5100/57600 [53:59<8:34:16,  1.70it/s]
                                                      
{'loss': 1.5497, 'learning_rate': 9.23170731707317e-07, 'epoch': 56.29}

  9%|▉         | 5100/57600 [53:59<8:34:16,  1.70it/s]
  9%|▉         | 5101/57600 [53:59<8:34:36,  1.70it/s]
  9%|▉         | 5102/57600 [54:00<8:38:15,  1.69it/s]
  9%|▉         | 5103/57600 [54:01<8:38:34,  1.69it/s]
  9%|▉         | 5104/57600 [54:01<8:38:42,  1.69it/s]
  9%|▉         | 5105/57600 [54:02<8:56:36,  1.63it/s]
  9%|▉         | 5106/57600 [54:02<8:59:41,  1.62it/s]
  9%|▉         | 5107/57600 [54:03<9:00:05,  1.62it/s]
  9%|▉         | 5108/57600 [54:04<9:16:17,  1.57it/s]
  9%|▉         | 5109/57600 [54:04<9:06:46,  1.60it/s]
  9%|▉         | 5110/57600 [54:05<9:01:11,  1.62it/s]
  9%|▉         | 5111/57600 [54:06<9:06:12,  1.60it/s]
  9%|▉         | 5112/57600 [54:06<8:53:37,  1.64it/s]
  9%|▉         | 5113/57600 [54:07<9:04:13,  1.61it/s]
  9%|▉         | 5114/57600 [54:07<8:59:42,  1.62it/s]
  9%|▉         | 5115/57600 [54:08<8:51:34,  1.65it/s]
  9%|▉         | 5116/57600 [54:09<8:58:19,  1.62it/s]
  9%|▉         | 5117/57600 [54:09<9:08:14,  1.60it/s]
  9%|▉         | 5118/57600 [54:10<8:56:04,  1.63it/s]
  9%|▉         | 5119/57600 [54:10<8:56:46,  1.63it/s]
  9%|▉         | 5120/57600 [54:11<8:48:15,  1.66it/s]
                                                      
{'loss': 1.5003, 'learning_rate': 9.228571428571428e-07, 'epoch': 56.51}

  9%|▉         | 5120/57600 [54:11<8:48:15,  1.66it/s]
  9%|▉         | 5121/57600 [54:12<8:47:53,  1.66it/s]
  9%|▉         | 5122/57600 [54:12<9:09:23,  1.59it/s]
  9%|▉         | 5123/57600 [54:13<9:18:10,  1.57it/s]
  9%|▉         | 5124/57600 [54:14<9:03:33,  1.61it/s]
  9%|▉         | 5125/57600 [54:14<8:51:45,  1.64it/s]
  9%|▉         | 5126/57600 [54:15<9:04:40,  1.61it/s]
  9%|▉         | 5127/57600 [54:15<8:53:21,  1.64it/s]
  9%|▉         | 5128/57600 [54:16<8:53:55,  1.64it/s]
  9%|▉         | 5129/57600 [54:17<9:07:53,  1.60it/s]
  9%|▉         | 5130/57600 [54:17<9:17:54,  1.57it/s]
  9%|▉         | 5131/57600 [54:18<9:25:28,  1.55it/s]
  9%|▉         | 5132/57600 [54:19<9:27:29,  1.54it/s]
  9%|▉         | 5133/57600 [54:19<9:14:28,  1.58it/s]
  9%|▉         | 5134/57600 [54:20<8:51:15,  1.65it/s]
  9%|▉         | 5135/57600 [54:20<9:12:49,  1.58it/s]
  9%|▉         | 5136/57600 [54:21<9:23:48,  1.55it/s]
  9%|▉         | 5137/57600 [54:22<9:18:11,  1.57it/s]
  9%|▉         | 5138/57600 [54:22<9:16:35,  1.57it/s]
  9%|▉         | 5139/57600 [54:23<9:09:06,  1.59it/s]
  9%|▉         | 5140/57600 [54:24<9:03:52,  1.61it/s]
                                                      
{'loss': 1.511, 'learning_rate': 9.225435540069686e-07, 'epoch': 56.73}

  9%|▉         | 5140/57600 [54:24<9:03:52,  1.61it/s]
  9%|▉         | 5141/57600 [54:24<9:05:08,  1.60it/s]
  9%|▉         | 5142/57600 [54:25<8:54:23,  1.64it/s]
  9%|▉         | 5143/57600 [54:26<9:18:46,  1.56it/s]
  9%|▉         | 5144/57600 [54:26<9:05:14,  1.60it/s]
  9%|▉         | 5145/57600 [54:27<9:09:40,  1.59it/s]
  9%|▉         | 5146/57600 [54:27<8:57:56,  1.63it/s]
  9%|▉         | 5147/57600 [54:28<9:33:32,  1.52it/s]
  9%|▉         | 5148/57600 [54:29<9:26:45,  1.54it/s]
  9%|▉         | 5149/57600 [54:29<9:10:59,  1.59it/s]
  9%|▉         | 5150/57600 [54:30<9:03:57,  1.61it/s]
  9%|▉         | 5151/57600 [54:31<8:53:10,  1.64it/s]
  9%|▉         | 5152/57600 [54:31<8:53:08,  1.64it/s]
  9%|▉         | 5153/57600 [54:32<9:13:06,  1.58it/s]
  9%|▉         | 5154/57600 [54:32<9:15:40,  1.57it/s]
  9%|▉         | 5155/57600 [54:33<9:03:08,  1.61it/s]
  9%|▉         | 5156/57600 [54:34<9:12:23,  1.58it/s]
  9%|▉         | 5157/57600 [54:34<9:00:22,  1.62it/s]
  9%|▉         | 5158/57600 [54:35<8:53:10,  1.64it/s]
  9%|▉         | 5159/57600 [54:35<8:38:17,  1.69it/s]
  9%|▉         | 5160/57600 [54:36<8:37:11,  1.69it/s]
                                                      
{'loss': 1.5426, 'learning_rate': 9.222299651567944e-07, 'epoch': 56.95}

  9%|▉         | 5160/57600 [54:36<8:37:11,  1.69it/s]
  9%|▉         | 5161/57600 [54:37<8:38:39,  1.69it/s]
  9%|▉         | 5162/57600 [54:37<8:34:42,  1.70it/s]
  9%|▉         | 5163/57600 [54:38<8:42:16,  1.67it/s]
  9%|▉         | 5164/57600 [54:38<8:46:03,  1.66it/s]
  9%|▉         | 5165/57600 [54:39<9:33:20,  1.52it/s]
  9%|▉         | 5166/57600 [54:40<9:18:34,  1.56it/s]
  9%|▉         | 5167/57600 [54:40<9:28:25,  1.54it/s]
  9%|▉         | 5168/57600 [54:41<9:29:47,  1.53it/s]
  9%|▉         | 5169/57600 [54:42<9:38:09,  1.51it/s]
  9%|▉         | 5170/57600 [54:42<9:21:47,  1.56it/s]
  9%|▉         | 5171/57600 [54:43<9:19:31,  1.56it/s]
  9%|▉         | 5172/57600 [54:44<9:13:20,  1.58it/s]
  9%|▉         | 5173/57600 [54:44<9:02:21,  1.61it/s]
  9%|▉         | 5174/57600 [54:45<8:46:59,  1.66it/s]
  9%|▉         | 5175/57600 [54:45<8:56:23,  1.63it/s]
  9%|▉         | 5176/57600 [54:46<9:07:49,  1.59it/s]
  9%|▉         | 5177/57600 [54:47<9:27:13,  1.54it/s]
  9%|▉         | 5178/57600 [54:47<9:14:13,  1.58it/s]
  9%|▉         | 5179/57600 [54:48<9:01:20,  1.61it/s]
  9%|▉         | 5180/57600 [54:49<9:01:12,  1.61it/s]
                                                      
{'loss': 1.4937, 'learning_rate': 9.219163763066201e-07, 'epoch': 57.17}

  9%|▉         | 5180/57600 [54:49<9:01:12,  1.61it/s]
  9%|▉         | 5181/57600 [54:49<8:46:58,  1.66it/s]
  9%|▉         | 5182/57600 [54:50<8:57:33,  1.63it/s]
  9%|▉         | 5183/57600 [54:51<9:16:54,  1.57it/s]
  9%|▉         | 5184/57600 [54:51<9:14:18,  1.58it/s]
  9%|▉         | 5185/57600 [54:52<9:09:31,  1.59it/s]
  9%|▉         | 5186/57600 [54:52<9:08:36,  1.59it/s]
  9%|▉         | 5187/57600 [54:53<9:21:39,  1.56it/s]
  9%|▉         | 5188/57600 [54:54<9:16:25,  1.57it/s]
  9%|▉         | 5189/57600 [54:54<9:10:40,  1.59it/s]
  9%|▉         | 5190/57600 [54:55<9:06:12,  1.60it/s]
  9%|▉         | 5191/57600 [54:56<8:52:15,  1.64it/s]
  9%|▉         | 5192/57600 [54:56<9:14:15,  1.58it/s]
  9%|▉         | 5193/57600 [54:57<9:21:47,  1.55it/s]
  9%|▉         | 5194/57600 [54:57<9:11:36,  1.58it/s]
  9%|▉         | 5195/57600 [54:58<9:11:29,  1.58it/s]
  9%|▉         | 5196/57600 [54:59<8:59:15,  1.62it/s]
  9%|▉         | 5197/57600 [54:59<9:01:40,  1.61it/s]
  9%|▉         | 5198/57600 [55:00<9:06:02,  1.60it/s]
  9%|▉         | 5199/57600 [55:01<8:58:22,  1.62it/s]
  9%|▉         | 5200/57600 [55:01<8:48:11,  1.65it/s]
                                                      
{'loss': 1.5059, 'learning_rate': 9.216027874564459e-07, 'epoch': 57.4}

  9%|▉         | 5200/57600 [55:01<8:48:11,  1.65it/s]
  9%|▉         | 5201/57600 [55:02<9:01:39,  1.61it/s]
  9%|▉         | 5202/57600 [55:02<8:43:24,  1.67it/s]
  9%|▉         | 5203/57600 [55:03<9:18:00,  1.57it/s]
  9%|▉         | 5204/57600 [55:04<9:10:56,  1.59it/s]
  9%|▉         | 5205/57600 [55:04<9:04:54,  1.60it/s]
  9%|▉         | 5206/57600 [55:05<8:45:26,  1.66it/s]
  9%|▉         | 5207/57600 [55:05<8:38:33,  1.68it/s]
  9%|▉         | 5208/57600 [55:06<8:50:30,  1.65it/s]
  9%|▉         | 5209/57600 [55:07<9:03:00,  1.61it/s]
  9%|▉         | 5210/57600 [55:07<9:02:03,  1.61it/s]
  9%|▉         | 5211/57600 [55:08<8:45:35,  1.66it/s]
  9%|▉         | 5212/57600 [55:08<8:46:32,  1.66it/s]
  9%|▉         | 5213/57600 [55:09<8:57:29,  1.62it/s]
  9%|▉         | 5214/57600 [55:10<8:51:24,  1.64it/s]
  9%|▉         | 5215/57600 [55:10<8:36:33,  1.69it/s]
  9%|▉         | 5216/57600 [55:11<8:25:10,  1.73it/s]
  9%|▉         | 5217/57600 [55:11<8:44:27,  1.66it/s]
  9%|▉         | 5218/57600 [55:12<9:05:09,  1.60it/s]
  9%|▉         | 5219/57600 [55:13<8:48:27,  1.65it/s]
  9%|▉         | 5220/57600 [55:13<8:49:28,  1.65it/s]
                                                      
{'loss': 1.548, 'learning_rate': 9.212891986062717e-07, 'epoch': 57.62}

  9%|▉         | 5220/57600 [55:13<8:49:28,  1.65it/s]
  9%|▉         | 5221/57600 [55:14<8:35:27,  1.69it/s]
  9%|▉         | 5222/57600 [55:14<8:23:39,  1.73it/s]
  9%|▉         | 5223/57600 [55:15<8:37:51,  1.69it/s]
  9%|▉         | 5224/57600 [55:16<9:05:34,  1.60it/s]
  9%|▉         | 5225/57600 [55:16<9:14:27,  1.57it/s]
  9%|▉         | 5226/57600 [55:17<9:21:21,  1.55it/s]
  9%|▉         | 5227/57600 [55:18<9:04:29,  1.60it/s]
  9%|▉         | 5228/57600 [55:18<8:57:21,  1.62it/s]
  9%|▉         | 5229/57600 [55:19<9:02:56,  1.61it/s]
  9%|▉         | 5230/57600 [55:20<9:39:12,  1.51it/s]
  9%|▉         | 5231/57600 [55:20<9:27:13,  1.54it/s]
  9%|▉         | 5232/57600 [55:21<9:23:22,  1.55it/s]
  9%|▉         | 5233/57600 [55:22<9:27:52,  1.54it/s]
  9%|▉         | 5234/57600 [55:22<9:24:15,  1.55it/s]
  9%|▉         | 5235/57600 [55:23<9:00:24,  1.61it/s]
  9%|▉         | 5236/57600 [55:23<9:08:23,  1.59it/s]
  9%|▉         | 5237/57600 [55:24<9:11:44,  1.58it/s]
  9%|▉         | 5238/57600 [55:25<9:26:45,  1.54it/s]
  9%|▉         | 5239/57600 [55:25<9:16:56,  1.57it/s]
  9%|▉         | 5240/57600 [55:26<9:20:17,  1.56it/s]
                                                      
{'loss': 1.4691, 'learning_rate': 9.209756097560976e-07, 'epoch': 57.84}

  9%|▉         | 5240/57600 [55:26<9:20:17,  1.56it/s]
  9%|▉         | 5241/57600 [55:27<8:59:33,  1.62it/s]
  9%|▉         | 5242/57600 [55:27<9:01:21,  1.61it/s]
  9%|▉         | 5243/57600 [55:28<8:56:51,  1.63it/s]
  9%|▉         | 5244/57600 [55:28<8:46:06,  1.66it/s]
  9%|▉         | 5245/57600 [55:29<8:49:29,  1.65it/s]
  9%|▉         | 5246/57600 [55:30<8:44:35,  1.66it/s]
  9%|▉         | 5247/57600 [55:30<8:45:30,  1.66it/s]
  9%|▉         | 5248/57600 [55:31<8:54:35,  1.63it/s]
  9%|▉         | 5249/57600 [55:31<8:39:22,  1.68it/s]
  9%|▉         | 5250/57600 [55:32<8:39:44,  1.68it/s]
  9%|▉         | 5251/57600 [55:33<8:42:49,  1.67it/s]
  9%|▉         | 5252/57600 [55:33<8:28:52,  1.71it/s]
  9%|▉         | 5253/57600 [55:34<8:30:04,  1.71it/s]
  9%|▉         | 5254/57600 [55:34<8:21:30,  1.74it/s]
  9%|▉         | 5255/57600 [55:35<8:45:25,  1.66it/s]
  9%|▉         | 5256/57600 [55:36<8:45:20,  1.66it/s]
  9%|▉         | 5257/57600 [55:36<8:51:14,  1.64it/s]
  9%|▉         | 5258/57600 [55:37<8:45:42,  1.66it/s]
  9%|▉         | 5259/57600 [55:37<9:04:40,  1.60it/s]
  9%|▉         | 5260/57600 [55:38<9:18:00,  1.56it/s]
                                                      
{'loss': 1.5459, 'learning_rate': 9.206620209059232e-07, 'epoch': 58.06}

  9%|▉         | 5260/57600 [55:38<9:18:00,  1.56it/s]
  9%|▉         | 5261/57600 [55:39<9:01:32,  1.61it/s]
  9%|▉         | 5262/57600 [55:39<8:51:46,  1.64it/s]
  9%|▉         | 5263/57600 [55:40<8:41:30,  1.67it/s]
  9%|▉         | 5264/57600 [55:40<8:34:43,  1.69it/s]
  9%|▉         | 5265/57600 [55:41<8:41:44,  1.67it/s]
  9%|▉         | 5266/57600 [55:42<8:41:04,  1.67it/s]
  9%|▉         | 5267/57600 [55:42<8:44:32,  1.66it/s]
  9%|▉         | 5268/57600 [55:43<8:36:34,  1.69it/s]
  9%|▉         | 5269/57600 [55:43<9:00:51,  1.61it/s]
  9%|▉         | 5270/57600 [55:44<8:53:27,  1.63it/s]
  9%|▉         | 5271/57600 [55:45<8:56:24,  1.63it/s]
  9%|▉         | 5272/57600 [55:45<8:39:35,  1.68it/s]
  9%|▉         | 5273/57600 [55:46<8:41:06,  1.67it/s]
  9%|▉         | 5274/57600 [55:47<9:01:48,  1.61it/s]
  9%|▉         | 5275/57600 [55:47<8:52:14,  1.64it/s]
  9%|▉         | 5276/57600 [55:48<9:03:29,  1.60it/s]
  9%|▉         | 5277/57600 [55:48<9:02:52,  1.61it/s]
  9%|▉         | 5278/57600 [55:49<9:05:54,  1.60it/s]
  9%|▉         | 5279/57600 [55:50<8:55:37,  1.63it/s]
  9%|▉         | 5280/57600 [55:50<9:05:44,  1.60it/s]
                                                      
{'loss': 1.5569, 'learning_rate': 9.203484320557491e-07, 'epoch': 58.28}

  9%|▉         | 5280/57600 [55:50<9:05:44,  1.60it/s]
  9%|▉         | 5281/57600 [55:51<9:11:06,  1.58it/s]
  9%|▉         | 5282/57600 [55:52<9:25:32,  1.54it/s]
  9%|▉         | 5283/57600 [55:52<9:14:04,  1.57it/s]
  9%|▉         | 5284/57600 [55:53<9:09:22,  1.59it/s]
  9%|▉         | 5285/57600 [55:53<9:00:56,  1.61it/s]
  9%|▉         | 5286/57600 [55:54<9:02:42,  1.61it/s]
  9%|▉         | 5287/57600 [55:55<8:58:48,  1.62it/s]
  9%|▉         | 5288/57600 [55:55<9:00:34,  1.61it/s]
  9%|▉         | 5289/57600 [55:56<9:15:50,  1.57it/s]
  9%|▉         | 5290/57600 [55:57<9:10:11,  1.58it/s]
  9%|▉         | 5291/57600 [55:57<9:04:02,  1.60it/s]
  9%|▉         | 5292/57600 [55:58<9:03:20,  1.60it/s]
  9%|▉         | 5293/57600 [55:58<8:54:54,  1.63it/s]
  9%|▉         | 5294/57600 [55:59<9:21:55,  1.55it/s]
  9%|▉         | 5295/57600 [56:00<9:37:40,  1.51it/s]
  9%|▉         | 5296/57600 [56:00<9:40:03,  1.50it/s]
  9%|▉         | 5297/57600 [56:01<9:20:11,  1.56it/s]
  9%|▉         | 5298/57600 [56:02<9:10:33,  1.58it/s]
  9%|▉         | 5299/57600 [56:02<9:04:57,  1.60it/s]
  9%|▉         | 5300/57600 [56:03<8:56:44,  1.62it/s]
                                                      
{'loss': 1.4634, 'learning_rate': 9.200348432055748e-07, 'epoch': 58.5}

  9%|▉         | 5300/57600 [56:03<8:56:44,  1.62it/s]
  9%|▉         | 5301/57600 [56:03<8:54:19,  1.63it/s]
  9%|▉         | 5302/57600 [56:04<9:28:56,  1.53it/s]
  9%|▉         | 5303/57600 [56:05<9:24:37,  1.54it/s]
  9%|▉         | 5304/57600 [56:05<9:07:15,  1.59it/s]
  9%|▉         | 5305/57600 [56:06<9:01:13,  1.61it/s]
  9%|▉         | 5306/57600 [56:07<9:08:44,  1.59it/s]
  9%|▉         | 5307/57600 [56:07<8:50:40,  1.64it/s]
  9%|▉         | 5308/57600 [56:08<8:51:36,  1.64it/s]
  9%|▉         | 5309/57600 [56:08<8:51:18,  1.64it/s]
  9%|▉         | 5310/57600 [56:09<9:15:42,  1.57it/s]
  9%|▉         | 5311/57600 [56:10<9:22:42,  1.55it/s]
  9%|▉         | 5312/57600 [56:10<9:20:04,  1.56it/s]
  9%|▉         | 5313/57600 [56:11<9:12:23,  1.58it/s]
  9%|▉         | 5314/57600 [56:12<9:12:30,  1.58it/s]
  9%|▉         | 5315/57600 [56:12<9:31:23,  1.53it/s]
  9%|▉         | 5316/57600 [56:13<9:12:56,  1.58it/s]
  9%|▉         | 5317/57600 [56:14<9:05:11,  1.60it/s]
  9%|▉         | 5318/57600 [56:14<8:54:52,  1.63it/s]
  9%|▉         | 5319/57600 [56:15<9:01:53,  1.61it/s]
  9%|▉         | 5320/57600 [56:15<8:57:18,  1.62it/s]
                                                      
{'loss': 1.4567, 'learning_rate': 9.197212543554007e-07, 'epoch': 58.72}

  9%|▉         | 5320/57600 [56:15<8:57:18,  1.62it/s]
  9%|▉         | 5321/57600 [56:16<8:57:07,  1.62it/s]
  9%|▉         | 5322/57600 [56:17<8:58:50,  1.62it/s]
  9%|▉         | 5323/57600 [56:17<8:49:42,  1.64it/s]
  9%|▉         | 5324/57600 [56:18<8:38:56,  1.68it/s]
  9%|▉         | 5325/57600 [56:18<8:42:25,  1.67it/s]
  9%|▉         | 5326/57600 [56:19<8:47:28,  1.65it/s]
  9%|▉         | 5327/57600 [56:20<8:43:41,  1.66it/s]
  9%|▉         | 5328/57600 [56:20<8:41:33,  1.67it/s]
  9%|▉         | 5329/57600 [56:21<8:49:57,  1.64it/s]
  9%|▉         | 5330/57600 [56:22<8:54:59,  1.63it/s]
  9%|▉         | 5331/57600 [56:22<8:40:17,  1.67it/s]
  9%|▉         | 5332/57600 [56:23<8:47:42,  1.65it/s]
  9%|▉         | 5333/57600 [56:23<8:56:41,  1.62it/s]
  9%|▉         | 5334/57600 [56:24<8:54:36,  1.63it/s]
  9%|▉         | 5335/57600 [56:25<8:58:21,  1.62it/s]
  9%|▉         | 5336/57600 [56:25<8:47:10,  1.65it/s]
  9%|▉         | 5337/57600 [56:26<8:38:19,  1.68it/s]
  9%|▉         | 5338/57600 [56:26<8:57:27,  1.62it/s]
  9%|▉         | 5339/57600 [56:27<9:11:25,  1.58it/s]
  9%|▉         | 5340/57600 [56:28<9:05:37,  1.60it/s]
                                                      
{'loss': 1.5349, 'learning_rate': 9.194076655052265e-07, 'epoch': 58.94}

  9%|▉         | 5340/57600 [56:28<9:05:37,  1.60it/s]
  9%|▉         | 5341/57600 [56:28<8:59:46,  1.61it/s]
  9%|▉         | 5342/57600 [56:29<8:43:23,  1.66it/s]
  9%|▉         | 5343/57600 [56:29<8:43:31,  1.66it/s]
  9%|▉         | 5344/57600 [56:30<8:57:06,  1.62it/s]
  9%|▉         | 5345/57600 [56:31<8:52:12,  1.64it/s]
  9%|▉         | 5346/57600 [56:31<9:04:14,  1.60it/s]
  9%|▉         | 5347/57600 [56:32<9:15:58,  1.57it/s]
  9%|▉         | 5348/57600 [56:33<9:21:54,  1.55it/s]
  9%|▉         | 5349/57600 [56:33<9:11:17,  1.58it/s]
  9%|▉         | 5350/57600 [56:34<8:58:26,  1.62it/s]
  9%|▉         | 5351/57600 [56:35<9:17:44,  1.56it/s]
  9%|▉         | 5352/57600 [56:35<9:22:36,  1.55it/s]
  9%|▉         | 5353/57600 [56:36<9:10:05,  1.58it/s]
  9%|▉         | 5354/57600 [56:36<8:58:28,  1.62it/s]
  9%|▉         | 5355/57600 [56:37<9:05:25,  1.60it/s]
  9%|▉         | 5356/57600 [56:38<9:11:37,  1.58it/s]
  9%|▉         | 5357/57600 [56:38<8:57:20,  1.62it/s]
  9%|▉         | 5358/57600 [56:39<9:03:57,  1.60it/s]
  9%|▉         | 5359/57600 [56:40<9:18:36,  1.56it/s]
  9%|▉         | 5360/57600 [56:40<9:07:09,  1.59it/s]
                                                      
{'loss': 1.4706, 'learning_rate': 9.190940766550522e-07, 'epoch': 59.16}

  9%|▉         | 5360/57600 [56:40<9:07:09,  1.59it/s]
  9%|▉         | 5361/57600 [56:41<9:24:21,  1.54it/s]
  9%|▉         | 5362/57600 [56:41<9:04:08,  1.60it/s]
  9%|▉         | 5363/57600 [56:42<8:56:59,  1.62it/s]
  9%|▉         | 5364/57600 [56:43<8:46:02,  1.66it/s]
  9%|▉         | 5365/57600 [56:43<8:42:57,  1.66it/s]
  9%|▉         | 5366/57600 [56:44<8:53:42,  1.63it/s]
  9%|▉         | 5367/57600 [56:44<8:36:07,  1.69it/s]
  9%|▉         | 5368/57600 [56:45<8:30:26,  1.71it/s]
  9%|▉         | 5369/57600 [56:46<8:37:27,  1.68it/s]
  9%|▉         | 5370/57600 [56:46<9:10:24,  1.58it/s]
  9%|▉         | 5371/57600 [56:47<9:01:17,  1.61it/s]
  9%|▉         | 5372/57600 [56:48<9:00:09,  1.61it/s]
  9%|▉         | 5373/57600 [56:48<8:55:05,  1.63it/s]
  9%|▉         | 5374/57600 [56:49<9:17:32,  1.56it/s]
  9%|▉         | 5375/57600 [56:49<9:15:21,  1.57it/s]
  9%|▉         | 5376/57600 [56:50<9:18:15,  1.56it/s]
  9%|▉         | 5377/57600 [56:51<8:59:13,  1.61it/s]
  9%|▉         | 5378/57600 [56:51<9:02:29,  1.60it/s]
  9%|▉         | 5379/57600 [56:52<9:07:54,  1.59it/s]
  9%|▉         | 5380/57600 [56:53<9:04:07,  1.60it/s]
                                                      
{'loss': 1.4932, 'learning_rate': 9.187804878048781e-07, 'epoch': 59.38}

  9%|▉         | 5380/57600 [56:53<9:04:07,  1.60it/s]
  9%|▉         | 5381/57600 [56:53<8:57:00,  1.62it/s]
  9%|▉         | 5382/57600 [56:54<9:00:24,  1.61it/s]
  9%|▉         | 5383/57600 [56:54<8:55:22,  1.63it/s]
  9%|▉         | 5384/57600 [56:55<8:59:10,  1.61it/s]
  9%|▉         | 5385/57600 [56:56<8:51:20,  1.64it/s]
  9%|▉         | 5386/57600 [56:56<8:52:35,  1.63it/s]
  9%|▉         | 5387/57600 [56:57<9:16:10,  1.56it/s]
  9%|▉         | 5388/57600 [56:57<8:53:53,  1.63it/s]
  9%|▉         | 5389/57600 [56:58<8:53:56,  1.63it/s]
  9%|▉         | 5390/57600 [56:59<9:10:35,  1.58it/s]
  9%|▉         | 5391/57600 [56:59<8:59:08,  1.61it/s]
  9%|▉         | 5392/57600 [57:00<8:43:25,  1.66it/s]
  9%|▉         | 5393/57600 [57:01<8:55:55,  1.62it/s]
  9%|▉         | 5394/57600 [57:01<8:44:29,  1.66it/s]
  9%|▉         | 5395/57600 [57:02<8:31:24,  1.70it/s]
  9%|▉         | 5396/57600 [57:02<8:38:23,  1.68it/s]
  9%|▉         | 5397/57600 [57:03<8:39:36,  1.67it/s]
  9%|▉         | 5398/57600 [57:03<8:32:43,  1.70it/s]
  9%|▉         | 5399/57600 [57:04<8:51:32,  1.64it/s]
  9%|▉         | 5400/57600 [57:05<8:44:18,  1.66it/s]
                                                      
{'loss': 1.5204, 'learning_rate': 9.184668989547037e-07, 'epoch': 59.6}

  9%|▉         | 5400/57600 [57:05<8:44:18,  1.66it/s]
  9%|▉         | 5401/57600 [57:05<8:37:29,  1.68it/s]
  9%|▉         | 5402/57600 [57:06<8:58:59,  1.61it/s]
  9%|▉         | 5403/57600 [57:07<9:22:40,  1.55it/s]
  9%|▉         | 5404/57600 [57:07<8:56:41,  1.62it/s]
  9%|▉         | 5405/57600 [57:08<8:51:56,  1.64it/s]
  9%|▉         | 5406/57600 [57:08<9:03:14,  1.60it/s]
  9%|▉         | 5407/57600 [57:09<9:01:32,  1.61it/s]
  9%|▉         | 5408/57600 [57:10<9:15:15,  1.57it/s]
  9%|▉         | 5409/57600 [57:10<9:12:21,  1.57it/s]
  9%|▉         | 5410/57600 [57:11<9:05:20,  1.60it/s]
  9%|▉         | 5411/57600 [57:12<9:05:16,  1.60it/s]
  9%|▉         | 5412/57600 [57:12<8:56:55,  1.62it/s]
  9%|▉         | 5413/57600 [57:13<8:57:33,  1.62it/s]
  9%|▉         | 5414/57600 [57:13<8:48:30,  1.65it/s]
  9%|▉         | 5415/57600 [57:14<8:46:02,  1.65it/s]
  9%|▉         | 5416/57600 [57:15<8:33:44,  1.69it/s]
  9%|▉         | 5417/57600 [57:15<8:34:10,  1.69it/s]
  9%|▉         | 5418/57600 [57:16<8:47:23,  1.65it/s]
  9%|▉         | 5419/57600 [57:16<8:50:39,  1.64it/s]
  9%|▉         | 5420/57600 [57:17<8:39:49,  1.67it/s]
                                                      
{'loss': 1.5267, 'learning_rate': 9.181533101045296e-07, 'epoch': 59.82}

  9%|▉         | 5420/57600 [57:17<8:39:49,  1.67it/s]
  9%|▉         | 5421/57600 [57:18<8:39:04,  1.68it/s]
  9%|▉         | 5422/57600 [57:18<8:45:59,  1.65it/s]
  9%|▉         | 5423/57600 [57:19<8:47:07,  1.65it/s]
  9%|▉         | 5424/57600 [57:19<8:33:00,  1.70it/s]
  9%|▉         | 5425/57600 [57:20<8:41:58,  1.67it/s]
  9%|▉         | 5426/57600 [57:21<8:43:09,  1.66it/s]
  9%|▉         | 5427/57600 [57:21<9:06:32,  1.59it/s]
  9%|▉         | 5428/57600 [57:22<9:07:37,  1.59it/s]
  9%|▉         | 5429/57600 [57:23<9:01:07,  1.61it/s]
  9%|▉         | 5430/57600 [57:23<8:54:56,  1.63it/s]
  9%|▉         | 5431/57600 [57:24<8:57:01,  1.62it/s]
  9%|▉         | 5432/57600 [57:24<8:45:55,  1.65it/s]
  9%|▉         | 5433/57600 [57:25<8:48:45,  1.64it/s]
  9%|▉         | 5434/57600 [57:26<9:13:46,  1.57it/s]
  9%|▉         | 5435/57600 [57:26<9:14:25,  1.57it/s]
  9%|▉         | 5436/57600 [57:27<9:29:08,  1.53it/s]
  9%|▉         | 5437/57600 [57:28<9:39:20,  1.50it/s]
  9%|▉         | 5438/57600 [57:28<9:24:50,  1.54it/s]
  9%|▉         | 5439/57600 [57:29<9:38:11,  1.50it/s]
  9%|▉         | 5440/57600 [57:30<9:26:16,  1.54it/s]
                                                      
{'loss': 1.5275, 'learning_rate': 9.178397212543552e-07, 'epoch': 60.04}

  9%|▉         | 5440/57600 [57:30<9:26:16,  1.54it/s]
  9%|▉         | 5441/57600 [57:30<9:32:35,  1.52it/s]
  9%|▉         | 5442/57600 [57:31<9:04:40,  1.60it/s]
  9%|▉         | 5443/57600 [57:32<9:19:25,  1.55it/s]
  9%|▉         | 5444/57600 [57:32<9:02:19,  1.60it/s]
  9%|▉         | 5445/57600 [57:33<8:44:27,  1.66it/s]
  9%|▉         | 5446/57600 [57:33<9:21:04,  1.55it/s]
  9%|▉         | 5447/57600 [57:34<9:07:19,  1.59it/s]
  9%|▉         | 5448/57600 [57:35<8:57:44,  1.62it/s]
  9%|▉         | 5449/57600 [57:35<8:49:12,  1.64it/s]
  9%|▉         | 5450/57600 [57:36<8:57:57,  1.62it/s]
  9%|▉         | 5451/57600 [57:36<8:46:17,  1.65it/s]
  9%|▉         | 5452/57600 [57:37<8:35:45,  1.69it/s]
  9%|▉         | 5453/57600 [57:38<8:47:22,  1.65it/s]
  9%|▉         | 5454/57600 [57:38<8:54:39,  1.63it/s]
  9%|▉         | 5455/57600 [57:39<8:52:41,  1.63it/s]
  9%|▉         | 5456/57600 [57:40<9:08:10,  1.59it/s]
  9%|▉         | 5457/57600 [57:40<9:04:47,  1.60it/s]
  9%|▉         | 5458/57600 [57:41<9:10:16,  1.58it/s]
  9%|▉         | 5459/57600 [57:41<8:43:05,  1.66it/s]
  9%|▉         | 5460/57600 [57:42<8:44:10,  1.66it/s]
                                                      
{'loss': 1.5116, 'learning_rate': 9.175261324041812e-07, 'epoch': 60.26}

  9%|▉         | 5460/57600 [57:42<8:44:10,  1.66it/s]
  9%|▉         | 5461/57600 [57:43<9:00:57,  1.61it/s]
  9%|▉         | 5462/57600 [57:43<8:56:22,  1.62it/s]
  9%|▉         | 5463/57600 [57:44<8:52:10,  1.63it/s]
  9%|▉         | 5464/57600 [57:44<8:54:45,  1.62it/s]
  9%|▉         | 5465/57600 [57:45<8:53:07,  1.63it/s]
  9%|▉         | 5466/57600 [57:46<9:13:49,  1.57it/s]
  9%|▉         | 5467/57600 [57:46<8:56:20,  1.62it/s]
  9%|▉         | 5468/57600 [57:47<8:58:06,  1.61it/s]
  9%|▉         | 5469/57600 [57:48<8:53:06,  1.63it/s]
  9%|▉         | 5470/57600 [57:48<8:54:54,  1.62it/s]
  9%|▉         | 5471/57600 [57:49<9:02:46,  1.60it/s]
 10%|▉         | 5472/57600 [57:49<9:08:31,  1.58it/s]
 10%|▉         | 5473/57600 [57:50<8:59:15,  1.61it/s]
 10%|▉         | 5474/57600 [57:51<8:50:27,  1.64it/s]
 10%|▉         | 5475/57600 [57:51<8:55:28,  1.62it/s]
 10%|▉         | 5476/57600 [57:52<9:02:41,  1.60it/s]
 10%|▉         | 5477/57600 [57:52<8:55:03,  1.62it/s]
 10%|▉         | 5478/57600 [57:53<8:54:09,  1.63it/s]
 10%|▉         | 5479/57600 [57:54<9:05:02,  1.59it/s]
 10%|▉         | 5480/57600 [57:54<9:23:56,  1.54it/s]
                                                      
{'loss': 1.4686, 'learning_rate': 9.172125435540069e-07, 'epoch': 60.49}

 10%|▉         | 5480/57600 [57:54<9:23:56,  1.54it/s]
 10%|▉         | 5481/57600 [57:55<9:03:52,  1.60it/s]
 10%|▉         | 5482/57600 [57:56<9:26:32,  1.53it/s]
 10%|▉         | 5483/57600 [57:56<9:15:07,  1.56it/s]
 10%|▉         | 5484/57600 [57:57<9:12:33,  1.57it/s]
 10%|▉         | 5485/57600 [57:58<9:24:59,  1.54it/s]
 10%|▉         | 5486/57600 [57:58<9:34:57,  1.51it/s]
 10%|▉         | 5487/57600 [57:59<9:23:34,  1.54it/s]
 10%|▉         | 5488/57600 [58:00<9:25:01,  1.54it/s]
 10%|▉         | 5489/57600 [58:00<9:21:47,  1.55it/s]
 10%|▉         | 5490/57600 [58:01<9:19:34,  1.55it/s]
 10%|▉         | 5491/57600 [58:02<9:06:39,  1.59it/s]
 10%|▉         | 5492/57600 [58:02<9:05:32,  1.59it/s]
 10%|▉         | 5493/57600 [58:03<9:26:03,  1.53it/s]
 10%|▉         | 5494/57600 [58:03<9:09:33,  1.58it/s]
 10%|▉         | 5495/57600 [58:04<8:46:11,  1.65it/s]
 10%|▉         | 5496/57600 [58:05<8:46:47,  1.65it/s]
 10%|▉         | 5497/57600 [58:05<8:44:27,  1.66it/s]
 10%|▉         | 5498/57600 [58:06<8:34:10,  1.69it/s]
 10%|▉         | 5499/57600 [58:06<8:40:46,  1.67it/s]
 10%|▉         | 5500/57600 [58:07<8:33:19,  1.69it/s]
                                                      
{'loss': 1.4902, 'learning_rate': 9.168989547038327e-07, 'epoch': 60.71}

 10%|▉         | 5500/57600 [58:07<8:33:19,  1.69it/s]
 10%|▉         | 5501/57600 [58:08<8:44:26,  1.66it/s]
 10%|▉         | 5502/57600 [58:08<8:40:56,  1.67it/s]
 10%|▉         | 5503/57600 [58:09<8:58:47,  1.61it/s]
 10%|▉         | 5504/57600 [58:09<9:01:19,  1.60it/s]
 10%|▉         | 5505/57600 [58:10<9:02:39,  1.60it/s]
 10%|▉         | 5506/57600 [58:11<8:53:39,  1.63it/s]
 10%|▉         | 5507/57600 [58:11<9:03:27,  1.60it/s]
 10%|▉         | 5508/57600 [58:12<8:59:32,  1.61it/s]
 10%|▉         | 5509/57600 [58:13<8:48:59,  1.64it/s]
 10%|▉         | 5510/57600 [58:13<8:44:50,  1.65it/s]
 10%|▉         | 5511/57600 [58:14<9:06:13,  1.59it/s]
 10%|▉         | 5512/57600 [58:14<9:26:03,  1.53it/s]
 10%|▉         | 5513/57600 [58:15<9:11:45,  1.57it/s]
 10%|▉         | 5514/57600 [58:16<8:45:57,  1.65it/s]
 10%|▉         | 5515/57600 [58:16<8:52:12,  1.63it/s]
 10%|▉         | 5516/57600 [58:17<8:40:01,  1.67it/s]
 10%|▉         | 5517/57600 [58:17<8:43:58,  1.66it/s]
 10%|▉         | 5518/57600 [58:18<8:30:14,  1.70it/s]
 10%|▉         | 5519/57600 [58:19<8:48:24,  1.64it/s]
 10%|▉         | 5520/57600 [58:19<8:37:14,  1.68it/s]
                                                      
{'loss': 1.4856, 'learning_rate': 9.165853658536585e-07, 'epoch': 60.93}

 10%|▉         | 5520/57600 [58:19<8:37:14,  1.68it/s]
 10%|▉         | 5521/57600 [58:20<8:48:08,  1.64it/s]
 10%|▉         | 5522/57600 [58:20<8:53:59,  1.63it/s]
 10%|▉         | 5523/57600 [58:21<9:04:31,  1.59it/s]
 10%|▉         | 5524/57600 [58:22<8:50:14,  1.64it/s]
 10%|▉         | 5525/57600 [58:22<8:50:07,  1.64it/s]
 10%|▉         | 5526/57600 [58:23<8:45:17,  1.65it/s]
 10%|▉         | 5527/57600 [58:24<9:07:09,  1.59it/s]
 10%|▉         | 5528/57600 [58:24<9:13:22,  1.57it/s]
 10%|▉         | 5529/57600 [58:25<9:12:41,  1.57it/s]
 10%|▉         | 5530/57600 [58:26<9:06:18,  1.59it/s]
 10%|▉         | 5531/57600 [58:26<9:01:26,  1.60it/s]
 10%|▉         | 5532/57600 [58:27<9:07:49,  1.58it/s]
 10%|▉         | 5533/57600 [58:27<8:50:29,  1.64it/s]
 10%|▉         | 5534/57600 [58:28<8:40:41,  1.67it/s]
 10%|▉         | 5535/57600 [58:29<8:47:48,  1.64it/s]
 10%|▉         | 5536/57600 [58:29<9:07:47,  1.58it/s]
 10%|▉         | 5537/57600 [58:30<8:51:47,  1.63it/s]
 10%|▉         | 5538/57600 [58:30<8:53:06,  1.63it/s]
 10%|▉         | 5539/57600 [58:31<8:56:26,  1.62it/s]
 10%|▉         | 5540/57600 [58:32<9:09:57,  1.58it/s]
                                                      
{'loss': 1.4982, 'learning_rate': 9.162717770034843e-07, 'epoch': 61.15}

 10%|▉         | 5540/57600 [58:32<9:09:57,  1.58it/s]
 10%|▉         | 5541/57600 [58:32<9:00:24,  1.61it/s]
 10%|▉         | 5542/57600 [58:33<9:06:59,  1.59it/s]
 10%|▉         | 5543/57600 [58:34<9:16:48,  1.56it/s]
 10%|▉         | 5544/57600 [58:34<9:09:57,  1.58it/s]
 10%|▉         | 5545/57600 [58:35<8:48:53,  1.64it/s]
 10%|▉         | 5546/57600 [58:35<9:00:52,  1.60it/s]
 10%|▉         | 5547/57600 [58:36<9:28:36,  1.53it/s]
 10%|▉         | 5548/57600 [58:37<9:13:54,  1.57it/s]
 10%|▉         | 5549/57600 [58:37<9:04:35,  1.59it/s]
 10%|▉         | 5550/57600 [58:38<8:56:27,  1.62it/s]
 10%|▉         | 5551/57600 [58:39<8:57:23,  1.61it/s]
 10%|▉         | 5552/57600 [58:39<8:46:59,  1.65it/s]
 10%|▉         | 5553/57600 [58:40<9:07:01,  1.59it/s]
 10%|▉         | 5554/57600 [58:40<8:53:43,  1.63it/s]
 10%|▉         | 5555/57600 [58:41<8:49:52,  1.64it/s]
 10%|▉         | 5556/57600 [58:42<8:51:47,  1.63it/s]
 10%|▉         | 5557/57600 [58:42<8:42:45,  1.66it/s]
 10%|▉         | 5558/57600 [58:43<8:45:35,  1.65it/s]
 10%|▉         | 5559/57600 [58:43<8:46:55,  1.65it/s]
 10%|▉         | 5560/57600 [58:44<8:49:23,  1.64it/s]
                                                      
{'loss': 1.4829, 'learning_rate': 9.1595818815331e-07, 'epoch': 61.37}

 10%|▉         | 5560/57600 [58:44<8:49:23,  1.64it/s]
 10%|▉         | 5561/57600 [58:45<8:41:51,  1.66it/s]
 10%|▉         | 5562/57600 [58:45<8:56:57,  1.62it/s]
 10%|▉         | 5563/57600 [58:46<8:58:13,  1.61it/s]
 10%|▉         | 5564/57600 [58:47<8:43:41,  1.66it/s]
 10%|▉         | 5565/57600 [58:47<8:36:29,  1.68it/s]
 10%|▉         | 5566/57600 [58:48<8:30:07,  1.70it/s]
 10%|▉         | 5567/57600 [58:48<8:34:38,  1.69it/s]
 10%|▉         | 5568/57600 [58:49<8:23:02,  1.72it/s]
 10%|▉         | 5569/57600 [58:49<8:36:00,  1.68it/s]
 10%|▉         | 5570/57600 [58:50<8:50:09,  1.64it/s]
 10%|▉         | 5571/57600 [58:51<8:50:13,  1.64it/s]
 10%|▉         | 5572/57600 [58:51<8:51:00,  1.63it/s]
 10%|▉         | 5573/57600 [58:52<9:17:49,  1.55it/s]
 10%|▉         | 5574/57600 [58:53<9:25:48,  1.53it/s]
 10%|▉         | 5575/57600 [58:53<8:55:42,  1.62it/s]
 10%|▉         | 5576/57600 [58:54<9:03:22,  1.60it/s]
 10%|▉         | 5577/57600 [58:55<9:03:12,  1.60it/s]
 10%|▉         | 5578/57600 [58:55<8:57:09,  1.61it/s]
 10%|▉         | 5579/57600 [58:56<8:50:24,  1.63it/s]
 10%|▉         | 5580/57600 [58:56<9:05:31,  1.59it/s]
                                                      
{'loss': 1.5049, 'learning_rate': 9.156445993031358e-07, 'epoch': 61.59}

 10%|▉         | 5580/57600 [58:56<9:05:31,  1.59it/s]
 10%|▉         | 5581/57600 [58:57<8:54:05,  1.62it/s]
 10%|▉         | 5582/57600 [58:58<8:51:20,  1.63it/s]
 10%|▉         | 5583/57600 [58:58<8:41:01,  1.66it/s]
 10%|▉         | 5584/57600 [58:59<8:36:03,  1.68it/s]
 10%|▉         | 5585/57600 [58:59<8:41:15,  1.66it/s]
 10%|▉         | 5586/57600 [59:00<8:47:59,  1.64it/s]
 10%|▉         | 5587/57600 [59:01<8:47:52,  1.64it/s]
 10%|▉         | 5588/57600 [59:01<8:56:23,  1.62it/s]
 10%|▉         | 5589/57600 [59:02<8:47:30,  1.64it/s]
 10%|▉         | 5590/57600 [59:02<8:57:32,  1.61it/s]
 10%|▉         | 5591/57600 [59:03<8:50:56,  1.63it/s]
 10%|▉         | 5592/57600 [59:04<8:51:50,  1.63it/s]
 10%|▉         | 5593/57600 [59:04<8:39:04,  1.67it/s]
 10%|▉         | 5594/57600 [59:05<8:42:51,  1.66it/s]
 10%|▉         | 5595/57600 [59:05<8:28:15,  1.71it/s]
 10%|▉         | 5596/57600 [59:06<8:35:30,  1.68it/s]
 10%|▉         | 5597/57600 [59:07<8:33:52,  1.69it/s]
 10%|▉         | 5598/57600 [59:07<8:37:11,  1.68it/s]
 10%|▉         | 5599/57600 [59:08<9:13:03,  1.57it/s]
 10%|▉         | 5600/57600 [59:09<9:22:32,  1.54it/s]
                                                      
{'loss': 1.5125, 'learning_rate': 9.153310104529617e-07, 'epoch': 61.81}

 10%|▉         | 5600/57600 [59:09<9:22:32,  1.54it/s]
 10%|▉         | 5601/57600 [59:09<9:04:11,  1.59it/s]
 10%|▉         | 5602/57600 [59:10<9:15:54,  1.56it/s]
 10%|▉         | 5603/57600 [59:11<9:35:26,  1.51it/s]
 10%|▉         | 5604/57600 [59:11<9:08:15,  1.58it/s]
 10%|▉         | 5605/57600 [59:12<9:02:44,  1.60it/s]
 10%|▉         | 5606/57600 [59:12<9:07:18,  1.58it/s]
 10%|▉         | 5607/57600 [59:13<9:11:10,  1.57it/s]
 10%|▉         | 5608/57600 [59:14<8:58:30,  1.61it/s]
 10%|▉         | 5609/57600 [59:14<8:46:56,  1.64it/s]
 10%|▉         | 5610/57600 [59:15<8:54:34,  1.62it/s]
 10%|▉         | 5611/57600 [59:15<8:51:14,  1.63it/s]
 10%|▉         | 5612/57600 [59:16<8:58:03,  1.61it/s]
 10%|▉         | 5613/57600 [59:17<8:59:15,  1.61it/s]
 10%|▉         | 5614/57600 [59:17<8:59:30,  1.61it/s]
 10%|▉         | 5615/57600 [59:18<9:09:07,  1.58it/s]
 10%|▉         | 5616/57600 [59:19<9:08:55,  1.58it/s]
 10%|▉         | 5617/57600 [59:19<8:57:25,  1.61it/s]
 10%|▉         | 5618/57600 [59:20<9:13:05,  1.57it/s]
 10%|▉         | 5619/57600 [59:20<8:53:04,  1.63it/s]
 10%|▉         | 5620/57600 [59:21<8:35:31,  1.68it/s]
                                                      
{'loss': 1.4746, 'learning_rate': 9.150174216027874e-07, 'epoch': 62.03}

 10%|▉         | 5620/57600 [59:21<8:35:31,  1.68it/s]
 10%|▉         | 5621/57600 [59:22<8:31:27,  1.69it/s]
 10%|▉         | 5622/57600 [59:22<8:32:05,  1.69it/s]
 10%|▉         | 5623/57600 [59:23<8:38:28,  1.67it/s]
 10%|▉         | 5624/57600 [59:23<8:43:45,  1.65it/s]
 10%|▉         | 5625/57600 [59:24<8:44:42,  1.65it/s]
 10%|▉         | 5626/57600 [59:25<8:58:35,  1.61it/s]
 10%|▉         | 5627/57600 [59:25<8:54:14,  1.62it/s]
 10%|▉         | 5628/57600 [59:26<8:57:13,  1.61it/s]
 10%|▉         | 5629/57600 [59:27<9:07:42,  1.58it/s]
 10%|▉         | 5630/57600 [59:27<9:11:39,  1.57it/s]
 10%|▉         | 5631/57600 [59:28<9:08:08,  1.58it/s]
 10%|▉         | 5632/57600 [59:28<9:12:49,  1.57it/s]
 10%|▉         | 5633/57600 [59:29<9:02:53,  1.60it/s]
 10%|▉         | 5634/57600 [59:30<8:47:10,  1.64it/s]
 10%|▉         | 5635/57600 [59:30<8:55:45,  1.62it/s]
 10%|▉         | 5636/57600 [59:31<8:46:02,  1.65it/s]
 10%|▉         | 5637/57600 [59:31<8:45:56,  1.65it/s]
 10%|▉         | 5638/57600 [59:32<8:44:53,  1.65it/s]
 10%|▉         | 5639/57600 [59:33<8:54:19,  1.62it/s]
 10%|▉         | 5640/57600 [59:33<9:28:35,  1.52it/s]
                                                      
{'loss': 1.5128, 'learning_rate': 9.147038327526132e-07, 'epoch': 62.25}

 10%|▉         | 5640/57600 [59:33<9:28:35,  1.52it/s]
 10%|▉         | 5641/57600 [59:34<9:07:59,  1.58it/s]
 10%|▉         | 5642/57600 [59:35<9:02:43,  1.60it/s]
 10%|▉         | 5643/57600 [59:35<8:40:28,  1.66it/s]
 10%|▉         | 5644/57600 [59:36<8:48:37,  1.64it/s]
 10%|▉         | 5645/57600 [59:36<8:58:10,  1.61it/s]
 10%|▉         | 5646/57600 [59:37<9:02:13,  1.60it/s]
 10%|▉         | 5647/57600 [59:38<8:53:36,  1.62it/s]
 10%|▉         | 5648/57600 [59:38<8:42:46,  1.66it/s]
 10%|▉         | 5649/57600 [59:39<8:50:00,  1.63it/s]
 10%|▉         | 5650/57600 [59:40<8:42:51,  1.66it/s]
 10%|▉         | 5651/57600 [59:40<8:54:43,  1.62it/s]
 10%|▉         | 5652/57600 [59:41<8:42:49,  1.66it/s]
 10%|▉         | 5653/57600 [59:41<9:07:25,  1.58it/s]
 10%|▉         | 5654/57600 [59:42<9:01:18,  1.60it/s]
 10%|▉         | 5655/57600 [59:43<8:57:47,  1.61it/s]
 10%|▉         | 5656/57600 [59:43<9:19:42,  1.55it/s]
 10%|▉         | 5657/57600 [59:44<9:05:13,  1.59it/s]
 10%|▉         | 5658/57600 [59:45<9:07:58,  1.58it/s]
 10%|▉         | 5659/57600 [59:45<9:02:14,  1.60it/s]
 10%|▉         | 5660/57600 [59:46<9:08:37,  1.58it/s]
                                                      
{'loss': 1.4799, 'learning_rate': 9.14390243902439e-07, 'epoch': 62.47}

 10%|▉         | 5660/57600 [59:46<9:08:37,  1.58it/s]
 10%|▉         | 5661/57600 [59:46<8:57:51,  1.61it/s]
 10%|▉         | 5662/57600 [59:47<9:08:46,  1.58it/s]
 10%|▉         | 5663/57600 [59:48<9:22:43,  1.54it/s]
 10%|▉         | 5664/57600 [59:48<9:11:18,  1.57it/s]
 10%|▉         | 5665/57600 [59:49<9:17:42,  1.55it/s]
 10%|▉         | 5666/57600 [59:50<9:22:29,  1.54it/s]
 10%|▉         | 5667/57600 [59:50<9:07:53,  1.58it/s]
 10%|▉         | 5668/57600 [59:51<9:03:40,  1.59it/s]
 10%|▉         | 5669/57600 [59:52<8:48:47,  1.64it/s]
 10%|▉         | 5670/57600 [59:52<8:46:21,  1.64it/s]
 10%|▉         | 5671/57600 [59:53<9:02:58,  1.59it/s]
 10%|▉         | 5672/57600 [59:53<8:52:25,  1.63it/s]
 10%|▉         | 5673/57600 [59:54<9:00:03,  1.60it/s]
 10%|▉         | 5674/57600 [59:55<9:13:00,  1.56it/s]
 10%|▉         | 5675/57600 [59:55<9:04:59,  1.59it/s]
 10%|▉         | 5676/57600 [59:56<9:38:01,  1.50it/s]
 10%|▉         | 5677/57600 [59:57<9:55:49,  1.45it/s]
 10%|▉         | 5678/57600 [59:57<9:40:46,  1.49it/s]
 10%|▉         | 5679/57600 [59:58<9:29:56,  1.52it/s]
 10%|▉         | 5680/57600 [59:59<9:12:38,  1.57it/s]
                                                      
{'loss': 1.4395, 'learning_rate': 9.140766550522648e-07, 'epoch': 62.69}

 10%|▉         | 5680/57600 [59:59<9:12:38,  1.57it/s]
 10%|▉         | 5681/57600 [59:59<9:24:09,  1.53it/s]
 10%|▉         | 5682/57600 [1:00:00<9:14:06,  1.56it/s]
 10%|▉         | 5683/57600 [1:00:01<9:10:41,  1.57it/s]
 10%|▉         | 5684/57600 [1:00:01<8:54:04,  1.62it/s]
 10%|▉         | 5685/57600 [1:00:02<8:44:36,  1.65it/s]
 10%|▉         | 5686/57600 [1:00:02<8:41:11,  1.66it/s]
 10%|▉         | 5687/57600 [1:00:03<8:41:36,  1.66it/s]
 10%|▉         | 5688/57600 [1:00:04<8:46:31,  1.64it/s]
 10%|▉         | 5689/57600 [1:00:04<8:48:29,  1.64it/s]
 10%|▉         | 5690/57600 [1:00:05<9:03:21,  1.59it/s]
 10%|▉         | 5691/57600 [1:00:05<8:56:10,  1.61it/s]
 10%|▉         | 5692/57600 [1:00:06<8:58:31,  1.61it/s]
 10%|▉         | 5693/57600 [1:00:07<9:09:41,  1.57it/s]
 10%|▉         | 5694/57600 [1:00:07<9:09:06,  1.58it/s]
 10%|▉         | 5695/57600 [1:00:08<9:02:59,  1.59it/s]
 10%|▉         | 5696/57600 [1:00:09<8:55:29,  1.62it/s]
 10%|▉         | 5697/57600 [1:00:09<8:56:22,  1.61it/s]
 10%|▉         | 5698/57600 [1:00:10<8:49:50,  1.63it/s]
 10%|▉         | 5699/57600 [1:00:10<8:38:33,  1.67it/s]
 10%|▉         | 5700/57600 [1:00:11<8:23:58,  1.72it/s]
                                                        
{'loss': 1.5277, 'learning_rate': 9.137630662020905e-07, 'epoch': 62.91}

 10%|▉         | 5700/57600 [1:00:11<8:23:58,  1.72it/s]
 10%|▉         | 5701/57600 [1:00:12<8:35:02,  1.68it/s]
 10%|▉         | 5702/57600 [1:00:12<8:25:18,  1.71it/s]
 10%|▉         | 5703/57600 [1:00:13<8:25:33,  1.71it/s]
 10%|▉         | 5704/57600 [1:00:13<8:29:24,  1.70it/s]
 10%|▉         | 5705/57600 [1:00:14<8:38:25,  1.67it/s]
 10%|▉         | 5706/57600 [1:00:14<8:26:57,  1.71it/s]
 10%|▉         | 5707/57600 [1:00:15<8:30:39,  1.69it/s]
 10%|▉         | 5708/57600 [1:00:16<9:00:58,  1.60it/s]
 10%|▉         | 5709/57600 [1:00:16<9:06:27,  1.58it/s]
 10%|▉         | 5710/57600 [1:00:17<9:03:49,  1.59it/s]
 10%|▉         | 5711/57600 [1:00:18<9:12:18,  1.57it/s]
 10%|▉         | 5712/57600 [1:00:18<9:03:32,  1.59it/s]
 10%|▉         | 5713/57600 [1:00:19<9:11:02,  1.57it/s]
 10%|▉         | 5714/57600 [1:00:19<8:48:41,  1.64it/s]
 10%|▉         | 5715/57600 [1:00:20<8:36:19,  1.67it/s]
 10%|▉         | 5716/57600 [1:00:21<8:41:52,  1.66it/s]
 10%|▉         | 5717/57600 [1:00:21<8:48:04,  1.64it/s]
 10%|▉         | 5718/57600 [1:00:22<8:52:12,  1.62it/s]
 10%|▉         | 5719/57600 [1:00:23<9:03:01,  1.59it/s]
 10%|▉         | 5720/57600 [1:00:23<9:35:04,  1.50it/s]
                                                        
{'loss': 1.4806, 'learning_rate': 9.134494773519163e-07, 'epoch': 63.13}

 10%|▉         | 5720/57600 [1:00:23<9:35:04,  1.50it/s]
 10%|▉         | 5721/57600 [1:00:24<9:27:56,  1.52it/s]
 10%|▉         | 5722/57600 [1:00:25<9:34:02,  1.51it/s]
 10%|▉         | 5723/57600 [1:00:25<9:27:57,  1.52it/s]
 10%|▉         | 5724/57600 [1:00:26<9:42:19,  1.48it/s]
 10%|▉         | 5725/57600 [1:00:27<9:37:47,  1.50it/s]
 10%|▉         | 5726/57600 [1:00:27<9:27:52,  1.52it/s]
 10%|▉         | 5727/57600 [1:00:28<9:06:36,  1.58it/s]
 10%|▉         | 5728/57600 [1:00:28<8:57:04,  1.61it/s]
 10%|▉         | 5729/57600 [1:00:29<8:41:51,  1.66it/s]
 10%|▉         | 5730/57600 [1:00:30<8:37:33,  1.67it/s]
 10%|▉         | 5731/57600 [1:00:30<8:29:11,  1.70it/s]
 10%|▉         | 5732/57600 [1:00:31<8:47:35,  1.64it/s]
 10%|▉         | 5733/57600 [1:00:31<8:42:52,  1.65it/s]
 10%|▉         | 5734/57600 [1:00:32<8:35:00,  1.68it/s]
 10%|▉         | 5735/57600 [1:00:33<8:43:04,  1.65it/s]
 10%|▉         | 5736/57600 [1:00:33<8:36:02,  1.68it/s]
 10%|▉         | 5737/57600 [1:00:34<8:29:29,  1.70it/s]
 10%|▉         | 5738/57600 [1:00:34<8:35:14,  1.68it/s]
 10%|▉         | 5739/57600 [1:00:35<8:36:49,  1.67it/s]
 10%|▉         | 5740/57600 [1:00:36<9:06:33,  1.58it/s]
                                                        
{'loss': 1.5123, 'learning_rate': 9.131358885017421e-07, 'epoch': 63.36}

 10%|▉         | 5740/57600 [1:00:36<9:06:33,  1.58it/s]
 10%|▉         | 5741/57600 [1:00:36<8:56:46,  1.61it/s]
 10%|▉         | 5742/57600 [1:00:37<8:37:12,  1.67it/s]
 10%|▉         | 5743/57600 [1:00:37<8:38:11,  1.67it/s]
 10%|▉         | 5744/57600 [1:00:38<8:45:28,  1.64it/s]
 10%|▉         | 5745/57600 [1:00:39<8:48:22,  1.64it/s]
 10%|▉         | 5746/57600 [1:00:39<8:29:59,  1.69it/s]
 10%|▉         | 5747/57600 [1:00:40<8:21:39,  1.72it/s]
 10%|▉         | 5748/57600 [1:00:40<8:22:21,  1.72it/s]
 10%|▉         | 5749/57600 [1:00:41<8:32:12,  1.69it/s]
 10%|▉         | 5750/57600 [1:00:42<8:51:50,  1.62it/s]
 10%|▉         | 5751/57600 [1:00:42<9:21:07,  1.54it/s]
 10%|▉         | 5752/57600 [1:00:43<9:08:12,  1.58it/s]
 10%|▉         | 5753/57600 [1:00:44<9:00:25,  1.60it/s]
 10%|▉         | 5754/57600 [1:00:44<9:06:26,  1.58it/s]
 10%|▉         | 5755/57600 [1:00:45<9:21:41,  1.54it/s]
 10%|▉         | 5756/57600 [1:00:46<9:14:07,  1.56it/s]
 10%|▉         | 5757/57600 [1:00:46<9:02:28,  1.59it/s]
 10%|▉         | 5758/57600 [1:00:47<8:49:59,  1.63it/s]
 10%|▉         | 5759/57600 [1:00:47<8:32:56,  1.68it/s]
 10%|█         | 5760/57600 [1:00:48<8:37:46,  1.67it/s]
                                                        
{'loss': 1.5502, 'learning_rate': 9.12822299651568e-07, 'epoch': 63.58}

 10%|█         | 5760/57600 [1:00:48<8:37:46,  1.67it/s]
 10%|█         | 5761/57600 [1:00:48<8:38:33,  1.67it/s]
 10%|█         | 5762/57600 [1:00:49<8:57:23,  1.61it/s]
 10%|█         | 5763/57600 [1:00:50<9:05:56,  1.58it/s]
 10%|█         | 5764/57600 [1:00:50<8:59:21,  1.60it/s]
 10%|█         | 5765/57600 [1:00:51<8:47:23,  1.64it/s]
 10%|█         | 5766/57600 [1:00:52<8:42:50,  1.65it/s]
 10%|█         | 5767/57600 [1:00:52<8:42:04,  1.65it/s]
 10%|█         | 5768/57600 [1:00:53<8:59:27,  1.60it/s]
 10%|█         | 5769/57600 [1:00:53<8:56:35,  1.61it/s]
 10%|█         | 5770/57600 [1:00:54<8:42:41,  1.65it/s]
 10%|█         | 5771/57600 [1:00:55<8:35:41,  1.68it/s]
 10%|█         | 5772/57600 [1:00:55<8:51:01,  1.63it/s]
 10%|█         | 5773/57600 [1:00:56<8:44:09,  1.65it/s]
 10%|█         | 5774/57600 [1:00:56<8:32:57,  1.68it/s]
 10%|█         | 5775/57600 [1:00:57<8:52:37,  1.62it/s]
 10%|█         | 5776/57600 [1:00:58<8:47:42,  1.64it/s]
 10%|█         | 5777/57600 [1:00:58<8:53:42,  1.62it/s]
 10%|█         | 5778/57600 [1:00:59<9:02:58,  1.59it/s]
 10%|█         | 5779/57600 [1:01:00<8:44:53,  1.65it/s]
 10%|█         | 5780/57600 [1:01:00<8:54:20,  1.62it/s]
                                                        
{'loss': 1.4732, 'learning_rate': 9.125087108013936e-07, 'epoch': 63.8}

 10%|█         | 5780/57600 [1:01:00<8:54:20,  1.62it/s]
 10%|█         | 5781/57600 [1:01:01<9:06:48,  1.58it/s]
 10%|█         | 5782/57600 [1:01:02<9:10:19,  1.57it/s]
 10%|█         | 5783/57600 [1:01:02<9:03:07,  1.59it/s]
 10%|█         | 5784/57600 [1:01:03<9:04:20,  1.59it/s]
 10%|█         | 5785/57600 [1:01:03<8:51:36,  1.62it/s]
 10%|█         | 5786/57600 [1:01:04<8:36:53,  1.67it/s]
 10%|█         | 5787/57600 [1:01:05<9:02:33,  1.59it/s]
 10%|█         | 5788/57600 [1:01:05<9:24:10,  1.53it/s]
 10%|█         | 5789/57600 [1:01:06<9:17:30,  1.55it/s]
 10%|█         | 5790/57600 [1:01:07<9:12:40,  1.56it/s]
 10%|█         | 5791/57600 [1:01:07<9:01:21,  1.60it/s]
 10%|█         | 5792/57600 [1:01:08<8:46:24,  1.64it/s]
 10%|█         | 5793/57600 [1:01:08<8:52:56,  1.62it/s]
 10%|█         | 5794/57600 [1:01:09<8:38:16,  1.67it/s]
 10%|█         | 5795/57600 [1:01:10<8:40:48,  1.66it/s]
 10%|█         | 5796/57600 [1:01:10<8:47:35,  1.64it/s]
 10%|█         | 5797/57600 [1:01:11<8:51:11,  1.63it/s]
 10%|█         | 5798/57600 [1:01:11<8:40:51,  1.66it/s]
 10%|█         | 5799/57600 [1:01:12<9:01:20,  1.59it/s]
 10%|█         | 5800/57600 [1:01:13<8:48:41,  1.63it/s]
                                                        
{'loss': 1.4694, 'learning_rate': 9.121951219512195e-07, 'epoch': 64.02}

 10%|█         | 5800/57600 [1:01:13<8:48:41,  1.63it/s]
 10%|█         | 5801/57600 [1:01:13<9:06:58,  1.58it/s]
 10%|█         | 5802/57600 [1:01:14<8:58:45,  1.60it/s]
 10%|█         | 5803/57600 [1:01:15<9:08:05,  1.58it/s]
 10%|█         | 5804/57600 [1:01:15<8:48:44,  1.63it/s]
 10%|█         | 5805/57600 [1:01:16<8:46:54,  1.64it/s]
 10%|█         | 5806/57600 [1:01:16<8:53:08,  1.62it/s]
 10%|█         | 5807/57600 [1:01:17<9:03:07,  1.59it/s]
 10%|█         | 5808/57600 [1:01:18<9:05:17,  1.58it/s]
 10%|█         | 5809/57600 [1:01:18<8:47:27,  1.64it/s]
 10%|█         | 5810/57600 [1:01:19<8:54:35,  1.61it/s]
 10%|█         | 5811/57600 [1:01:19<8:52:32,  1.62it/s]
 10%|█         | 5812/57600 [1:01:20<8:50:32,  1.63it/s]
 10%|█         | 5813/57600 [1:01:21<8:49:17,  1.63it/s]
 10%|█         | 5814/57600 [1:01:21<8:39:53,  1.66it/s]
 10%|█         | 5815/57600 [1:01:22<8:46:31,  1.64it/s]
 10%|█         | 5816/57600 [1:01:23<8:45:18,  1.64it/s]
 10%|█         | 5817/57600 [1:01:23<8:49:04,  1.63it/s]
 10%|█         | 5818/57600 [1:01:24<8:51:44,  1.62it/s]
 10%|█         | 5819/57600 [1:01:24<8:59:49,  1.60it/s]
 10%|█         | 5820/57600 [1:01:25<9:13:21,  1.56it/s]
                                                        
{'loss': 1.4394, 'learning_rate': 9.118815331010452e-07, 'epoch': 64.24}

 10%|█         | 5820/57600 [1:01:25<9:13:21,  1.56it/s]
 10%|█         | 5821/57600 [1:01:26<9:01:47,  1.59it/s]
 10%|█         | 5822/57600 [1:01:26<9:02:04,  1.59it/s]
 10%|█         | 5823/57600 [1:01:27<8:54:20,  1.61it/s]
 10%|█         | 5824/57600 [1:01:27<8:40:00,  1.66it/s]
 10%|█         | 5825/57600 [1:01:28<8:45:19,  1.64it/s]
 10%|█         | 5826/57600 [1:01:29<8:51:49,  1.62it/s]
 10%|█         | 5827/57600 [1:01:29<9:19:58,  1.54it/s]
 10%|█         | 5828/57600 [1:01:30<9:37:38,  1.49it/s]
 10%|█         | 5829/57600 [1:01:31<9:24:53,  1.53it/s]
 10%|█         | 5830/57600 [1:01:31<9:16:21,  1.55it/s]
 10%|█         | 5831/57600 [1:01:32<8:50:32,  1.63it/s]
 10%|█         | 5832/57600 [1:01:33<8:49:15,  1.63it/s]
 10%|█         | 5833/57600 [1:01:33<8:44:03,  1.65it/s]
 10%|█         | 5834/57600 [1:01:34<8:38:02,  1.67it/s]
 10%|█         | 5835/57600 [1:01:34<8:38:33,  1.66it/s]
 10%|█         | 5836/57600 [1:01:35<8:42:03,  1.65it/s]
 10%|█         | 5837/57600 [1:01:36<8:47:44,  1.63it/s]
 10%|█         | 5838/57600 [1:01:36<8:50:49,  1.63it/s]
 10%|█         | 5839/57600 [1:01:37<8:42:35,  1.65it/s]
 10%|█         | 5840/57600 [1:01:37<8:51:04,  1.62it/s]
                                                        
{'loss': 1.4776, 'learning_rate': 9.11567944250871e-07, 'epoch': 64.46}

 10%|█         | 5840/57600 [1:01:37<8:51:04,  1.62it/s]
 10%|█         | 5841/57600 [1:01:38<8:43:20,  1.65it/s]
 10%|█         | 5842/57600 [1:01:39<8:41:24,  1.65it/s]
 10%|█         | 5843/57600 [1:01:39<8:40:15,  1.66it/s]
 10%|█         | 5844/57600 [1:01:40<8:38:50,  1.66it/s]
 10%|█         | 5845/57600 [1:01:40<8:46:47,  1.64it/s]
 10%|█         | 5846/57600 [1:01:41<9:07:25,  1.58it/s]
 10%|█         | 5847/57600 [1:01:42<9:06:49,  1.58it/s]
 10%|█         | 5848/57600 [1:01:42<9:27:14,  1.52it/s]
 10%|█         | 5849/57600 [1:01:43<9:25:19,  1.53it/s]
 10%|█         | 5850/57600 [1:01:44<9:02:22,  1.59it/s]
 10%|█         | 5851/57600 [1:01:44<9:01:39,  1.59it/s]
 10%|█         | 5852/57600 [1:01:45<9:13:56,  1.56it/s]
 10%|█         | 5853/57600 [1:01:46<8:56:05,  1.61it/s]
 10%|█         | 5854/57600 [1:01:46<8:46:18,  1.64it/s]
 10%|█         | 5855/57600 [1:01:47<8:31:07,  1.69it/s]
 10%|█         | 5856/57600 [1:01:47<8:30:56,  1.69it/s]
 10%|█         | 5857/57600 [1:01:48<8:39:32,  1.66it/s]
 10%|█         | 5858/57600 [1:01:48<8:24:06,  1.71it/s]
 10%|█         | 5859/57600 [1:01:49<8:28:05,  1.70it/s]
 10%|█         | 5860/57600 [1:01:50<8:17:34,  1.73it/s]
                                                        
{'loss': 1.5363, 'learning_rate': 9.112543554006967e-07, 'epoch': 64.68}

 10%|█         | 5860/57600 [1:01:50<8:17:34,  1.73it/s]
 10%|█         | 5861/57600 [1:01:50<9:01:38,  1.59it/s]
 10%|█         | 5862/57600 [1:01:51<9:04:53,  1.58it/s]
 10%|█         | 5863/57600 [1:01:52<9:08:55,  1.57it/s]
 10%|█         | 5864/57600 [1:01:52<9:07:52,  1.57it/s]
 10%|█         | 5865/57600 [1:01:53<9:16:27,  1.55it/s]
 10%|█         | 5866/57600 [1:01:53<8:47:03,  1.64it/s]
 10%|█         | 5867/57600 [1:01:54<8:46:39,  1.64it/s]
 10%|█         | 5868/57600 [1:01:55<8:35:29,  1.67it/s]
 10%|█         | 5869/57600 [1:01:55<8:57:21,  1.60it/s]
 10%|█         | 5870/57600 [1:01:56<9:14:04,  1.56it/s]
 10%|█         | 5871/57600 [1:01:57<9:20:05,  1.54it/s]
 10%|█         | 5872/57600 [1:01:57<9:01:54,  1.59it/s]
 10%|█         | 5873/57600 [1:01:58<8:50:25,  1.63it/s]
 10%|█         | 5874/57600 [1:01:58<8:32:37,  1.68it/s]
 10%|█         | 5875/57600 [1:01:59<8:48:10,  1.63it/s]
 10%|█         | 5876/57600 [1:02:00<8:55:15,  1.61it/s]
 10%|█         | 5877/57600 [1:02:00<9:07:37,  1.57it/s]
 10%|█         | 5878/57600 [1:02:01<9:12:02,  1.56it/s]
 10%|█         | 5879/57600 [1:02:02<8:57:07,  1.60it/s]
 10%|█         | 5880/57600 [1:02:02<9:07:57,  1.57it/s]
                                                        
{'loss': 1.4584, 'learning_rate': 9.109407665505226e-07, 'epoch': 64.9}

 10%|█         | 5880/57600 [1:02:02<9:07:57,  1.57it/s]
 10%|█         | 5881/57600 [1:02:03<8:47:18,  1.63it/s]
 10%|█         | 5882/57600 [1:02:03<8:50:26,  1.63it/s]
 10%|█         | 5883/57600 [1:02:04<8:50:29,  1.62it/s]
 10%|█         | 5884/57600 [1:02:05<8:57:08,  1.60it/s]
 10%|█         | 5885/57600 [1:02:05<9:07:12,  1.58it/s]
 10%|█         | 5886/57600 [1:02:06<9:16:15,  1.55it/s]
 10%|█         | 5887/57600 [1:02:07<9:14:41,  1.55it/s]
 10%|█         | 5888/57600 [1:02:07<9:18:51,  1.54it/s]
 10%|█         | 5889/57600 [1:02:08<9:20:43,  1.54it/s]
 10%|█         | 5890/57600 [1:02:09<9:33:35,  1.50it/s]
 10%|█         | 5891/57600 [1:02:09<9:12:25,  1.56it/s]
 10%|█         | 5892/57600 [1:02:10<9:09:11,  1.57it/s]
 10%|█         | 5893/57600 [1:02:11<9:02:20,  1.59it/s]
 10%|█         | 5894/57600 [1:02:11<9:00:04,  1.60it/s]
 10%|█         | 5895/57600 [1:02:12<9:08:44,  1.57it/s]
 10%|█         | 5896/57600 [1:02:12<9:04:38,  1.58it/s]
 10%|█         | 5897/57600 [1:02:13<9:01:45,  1.59it/s]
 10%|█         | 5898/57600 [1:02:14<8:46:10,  1.64it/s]
 10%|█         | 5899/57600 [1:02:14<8:33:26,  1.68it/s]
 10%|█         | 5900/57600 [1:02:15<8:51:47,  1.62it/s]
                                                        
{'loss': 1.4956, 'learning_rate': 9.106271777003485e-07, 'epoch': 65.12}

 10%|█         | 5900/57600 [1:02:15<8:51:47,  1.62it/s]
 10%|█         | 5901/57600 [1:02:16<9:18:46,  1.54it/s]
 10%|█         | 5902/57600 [1:02:16<9:14:18,  1.55it/s]
 10%|█         | 5903/57600 [1:02:17<9:08:36,  1.57it/s]
 10%|█         | 5904/57600 [1:02:17<9:19:01,  1.54it/s]
 10%|█         | 5905/57600 [1:02:18<9:09:36,  1.57it/s]
 10%|█         | 5906/57600 [1:02:19<9:11:20,  1.56it/s]
 10%|█         | 5907/57600 [1:02:19<9:11:08,  1.56it/s]
 10%|█         | 5908/57600 [1:02:20<9:06:05,  1.58it/s]
 10%|█         | 5909/57600 [1:02:21<8:58:52,  1.60it/s]
 10%|█         | 5910/57600 [1:02:21<9:22:05,  1.53it/s]
 10%|█         | 5911/57600 [1:02:22<9:18:31,  1.54it/s]
 10%|█         | 5912/57600 [1:02:23<9:12:54,  1.56it/s]
 10%|█         | 5913/57600 [1:02:23<9:13:24,  1.56it/s]
 10%|█         | 5914/57600 [1:02:24<9:27:37,  1.52it/s]
 10%|█         | 5915/57600 [1:02:25<9:37:02,  1.49it/s]
 10%|█         | 5916/57600 [1:02:25<9:17:58,  1.54it/s]
 10%|█         | 5917/57600 [1:02:26<9:25:04,  1.52it/s]
 10%|█         | 5918/57600 [1:02:26<9:06:14,  1.58it/s]
 10%|█         | 5919/57600 [1:02:27<9:23:45,  1.53it/s]
 10%|█         | 5920/57600 [1:02:28<9:32:31,  1.50it/s]
                                                        
{'loss': 1.4672, 'learning_rate': 9.103135888501741e-07, 'epoch': 65.34}

 10%|█         | 5920/57600 [1:02:28<9:32:31,  1.50it/s]
 10%|█         | 5921/57600 [1:02:29<9:43:43,  1.48it/s]
 10%|█         | 5922/57600 [1:02:29<9:24:22,  1.53it/s]
 10%|█         | 5923/57600 [1:02:30<9:14:51,  1.55it/s]
 10%|█         | 5924/57600 [1:02:30<9:09:40,  1.57it/s]
 10%|█         | 5925/57600 [1:02:31<9:19:55,  1.54it/s]
 10%|█         | 5926/57600 [1:02:32<9:18:59,  1.54it/s]
 10%|█         | 5927/57600 [1:02:32<9:09:52,  1.57it/s]
 10%|█         | 5928/57600 [1:02:33<9:06:52,  1.57it/s]
 10%|█         | 5929/57600 [1:02:34<9:23:46,  1.53it/s]
 10%|█         | 5930/57600 [1:02:34<9:31:06,  1.51it/s]
 10%|█         | 5931/57600 [1:02:35<9:07:44,  1.57it/s]
 10%|█         | 5932/57600 [1:02:36<8:50:16,  1.62it/s]
 10%|█         | 5933/57600 [1:02:36<8:49:30,  1.63it/s]
 10%|█         | 5934/57600 [1:02:37<8:50:27,  1.62it/s]
 10%|█         | 5935/57600 [1:02:37<8:48:19,  1.63it/s]
 10%|█         | 5936/57600 [1:02:38<8:45:31,  1.64it/s]
 10%|█         | 5937/57600 [1:02:39<8:51:15,  1.62it/s]
 10%|█         | 5938/57600 [1:02:39<8:53:28,  1.61it/s]
 10%|█         | 5939/57600 [1:02:40<9:02:15,  1.59it/s]
 10%|█         | 5940/57600 [1:02:41<9:27:15,  1.52it/s]
                                                        
{'loss': 1.4765, 'learning_rate': 9.1e-07, 'epoch': 65.56}

 10%|█         | 5940/57600 [1:02:41<9:27:15,  1.52it/s]
 10%|█         | 5941/57600 [1:02:41<9:06:44,  1.57it/s]
 10%|█         | 5942/57600 [1:02:42<9:03:14,  1.58it/s]
 10%|█         | 5943/57600 [1:02:42<8:57:21,  1.60it/s]
 10%|█         | 5944/57600 [1:02:43<8:48:53,  1.63it/s]
 10%|█         | 5945/57600 [1:02:44<8:35:11,  1.67it/s]
 10%|█         | 5946/57600 [1:02:44<8:59:25,  1.60it/s]
 10%|█         | 5947/57600 [1:02:45<9:10:20,  1.56it/s]
 10%|█         | 5948/57600 [1:02:46<9:09:19,  1.57it/s]
 10%|█         | 5949/57600 [1:02:46<9:13:08,  1.56it/s]
 10%|█         | 5950/57600 [1:02:47<8:52:22,  1.62it/s]
 10%|█         | 5951/57600 [1:02:47<9:04:27,  1.58it/s]
 10%|█         | 5952/57600 [1:02:48<8:50:47,  1.62it/s]
 10%|█         | 5953/57600 [1:02:49<8:51:16,  1.62it/s]
 10%|█         | 5954/57600 [1:02:49<8:46:40,  1.63it/s]
 10%|█         | 5955/57600 [1:02:50<8:42:03,  1.65it/s]
 10%|█         | 5956/57600 [1:02:50<8:45:40,  1.64it/s]
 10%|█         | 5957/57600 [1:02:51<8:40:51,  1.65it/s]
 10%|█         | 5958/57600 [1:02:52<8:58:19,  1.60it/s]
 10%|█         | 5959/57600 [1:02:52<8:49:28,  1.63it/s]
 10%|█         | 5960/57600 [1:02:53<8:51:17,  1.62it/s]
                                                        
{'loss': 1.4821, 'learning_rate': 9.096864111498257e-07, 'epoch': 65.78}

 10%|█         | 5960/57600 [1:02:53<8:51:17,  1.62it/s]
 10%|█         | 5961/57600 [1:02:54<8:42:43,  1.65it/s]
 10%|█         | 5962/57600 [1:02:54<8:45:00,  1.64it/s]
 10%|█         | 5963/57600 [1:02:55<8:47:18,  1.63it/s]
 10%|█         | 5964/57600 [1:02:55<8:42:59,  1.65it/s]
 10%|█         | 5965/57600 [1:02:56<8:40:49,  1.65it/s]
 10%|█         | 5966/57600 [1:02:57<9:01:54,  1.59it/s]
 10%|█         | 5967/57600 [1:02:57<9:00:39,  1.59it/s]
 10%|█         | 5968/57600 [1:02:58<9:13:52,  1.55it/s]
 10%|█         | 5969/57600 [1:02:59<9:14:35,  1.55it/s]
 10%|█         | 5970/57600 [1:02:59<8:52:47,  1.62it/s]
 10%|█         | 5971/57600 [1:03:00<8:51:20,  1.62it/s]
 10%|█         | 5972/57600 [1:03:00<8:43:20,  1.64it/s]
 10%|█         | 5973/57600 [1:03:01<8:38:18,  1.66it/s]
 10%|█         | 5974/57600 [1:03:02<8:54:08,  1.61it/s]
 10%|█         | 5975/57600 [1:03:02<8:49:40,  1.62it/s]
 10%|█         | 5976/57600 [1:03:03<8:57:04,  1.60it/s]
 10%|█         | 5977/57600 [1:03:03<9:05:49,  1.58it/s]
 10%|█         | 5978/57600 [1:03:04<9:11:32,  1.56it/s]
 10%|█         | 5979/57600 [1:03:05<8:56:21,  1.60it/s]
 10%|█         | 5980/57600 [1:03:05<9:06:01,  1.58it/s]
                                                        
{'loss': 1.4561, 'learning_rate': 9.093728222996516e-07, 'epoch': 66.0}

 10%|█         | 5980/57600 [1:03:05<9:06:01,  1.58it/s]
 10%|█         | 5981/57600 [1:03:06<8:56:16,  1.60it/s]
 10%|█         | 5982/57600 [1:03:07<8:47:04,  1.63it/s]
 10%|█         | 5983/57600 [1:03:07<8:50:37,  1.62it/s]
 10%|█         | 5984/57600 [1:03:08<8:42:38,  1.65it/s]
 10%|█         | 5985/57600 [1:03:08<8:27:53,  1.69it/s]
 10%|█         | 5986/57600 [1:03:09<8:37:53,  1.66it/s]
 10%|█         | 5987/57600 [1:03:10<8:40:56,  1.65it/s]
 10%|█         | 5988/57600 [1:03:10<8:51:26,  1.62it/s]
 10%|█         | 5989/57600 [1:03:11<9:12:08,  1.56it/s]
 10%|█         | 5990/57600 [1:03:11<8:46:14,  1.63it/s]
 10%|█         | 5991/57600 [1:03:12<8:34:45,  1.67it/s]
 10%|█         | 5992/57600 [1:03:13<8:29:08,  1.69it/s]
 10%|█         | 5993/57600 [1:03:13<8:24:27,  1.71it/s]
 10%|█         | 5994/57600 [1:03:14<9:01:55,  1.59it/s]
 10%|█         | 5995/57600 [1:03:15<8:51:13,  1.62it/s]
 10%|█         | 5996/57600 [1:03:15<8:56:12,  1.60it/s]
 10%|█         | 5997/57600 [1:03:16<8:43:42,  1.64it/s]
 10%|█         | 5998/57600 [1:03:16<8:51:28,  1.62it/s]
 10%|█         | 5999/57600 [1:03:17<8:51:43,  1.62it/s]
 10%|█         | 6000/57600 [1:03:18<8:43:40,  1.64it/s]
                                                        
{'loss': 1.514, 'learning_rate': 9.090592334494772e-07, 'epoch': 66.23}

 10%|█         | 6000/57600 [1:03:18<8:43:40,  1.64it/s]
 10%|█         | 6001/57600 [1:03:18<8:43:24,  1.64it/s]
 10%|█         | 6002/57600 [1:03:19<8:31:54,  1.68it/s]
 10%|█         | 6003/57600 [1:03:19<8:39:57,  1.65it/s]
 10%|█         | 6004/57600 [1:03:20<8:38:17,  1.66it/s]
 10%|█         | 6005/57600 [1:03:21<8:42:55,  1.64it/s]
 10%|█         | 6006/57600 [1:03:21<8:49:21,  1.62it/s]
 10%|█         | 6007/57600 [1:03:22<8:47:23,  1.63it/s]
 10%|█         | 6008/57600 [1:03:22<8:53:45,  1.61it/s]
 10%|█         | 6009/57600 [1:03:23<8:58:10,  1.60it/s]
 10%|█         | 6010/57600 [1:03:24<8:52:08,  1.62it/s]
 10%|█         | 6011/57600 [1:03:24<8:52:04,  1.62it/s]
 10%|█         | 6012/57600 [1:03:25<8:49:41,  1.62it/s]
 10%|█         | 6013/57600 [1:03:26<8:44:07,  1.64it/s]
 10%|█         | 6014/57600 [1:03:26<8:43:15,  1.64it/s]
 10%|█         | 6015/57600 [1:03:27<8:39:09,  1.66it/s]
 10%|█         | 6016/57600 [1:03:27<9:06:27,  1.57it/s]
 10%|█         | 6017/57600 [1:03:28<9:21:10,  1.53it/s]
 10%|█         | 6018/57600 [1:03:29<9:13:57,  1.55it/s]
 10%|█         | 6019/57600 [1:03:29<8:55:50,  1.60it/s]
 10%|█         | 6020/57600 [1:03:30<8:50:11,  1.62it/s]
                                                        
{'loss': 1.495, 'learning_rate': 9.08745644599303e-07, 'epoch': 66.45}

 10%|█         | 6020/57600 [1:03:30<8:50:11,  1.62it/s]
 10%|█         | 6021/57600 [1:03:31<8:49:48,  1.62it/s]
 10%|█         | 6022/57600 [1:03:31<9:12:47,  1.56it/s]
 10%|█         | 6023/57600 [1:03:32<9:10:34,  1.56it/s]
 10%|█         | 6024/57600 [1:03:33<9:04:54,  1.58it/s]
 10%|█         | 6025/57600 [1:03:33<8:52:18,  1.61it/s]
 10%|█         | 6026/57600 [1:03:34<8:46:44,  1.63it/s]
 10%|█         | 6027/57600 [1:03:34<8:44:13,  1.64it/s]
 10%|█         | 6028/57600 [1:03:35<8:53:23,  1.61it/s]
 10%|█         | 6029/57600 [1:03:35<8:33:36,  1.67it/s]
 10%|█         | 6030/57600 [1:03:36<8:29:40,  1.69it/s]
 10%|█         | 6031/57600 [1:03:37<8:20:34,  1.72it/s]
 10%|█         | 6032/57600 [1:03:37<8:36:38,  1.66it/s]
 10%|█         | 6033/57600 [1:03:38<8:33:53,  1.67it/s]
 10%|█         | 6034/57600 [1:03:39<8:53:08,  1.61it/s]
 10%|█         | 6035/57600 [1:03:39<9:04:29,  1.58it/s]
 10%|█         | 6036/57600 [1:03:40<9:02:33,  1.58it/s]
 10%|█         | 6037/57600 [1:03:40<9:13:08,  1.55it/s]
 10%|█         | 6038/57600 [1:03:41<9:23:16,  1.53it/s]
 10%|█         | 6039/57600 [1:03:42<9:18:13,  1.54it/s]
 10%|█         | 6040/57600 [1:03:42<9:05:25,  1.58it/s]
                                                        
{'loss': 1.4413, 'learning_rate': 9.084320557491289e-07, 'epoch': 66.67}

 10%|█         | 6040/57600 [1:03:42<9:05:25,  1.58it/s]
 10%|█         | 6041/57600 [1:03:43<9:17:28,  1.54it/s]
 10%|█         | 6042/57600 [1:03:44<9:08:12,  1.57it/s]
 10%|█         | 6043/57600 [1:03:44<8:59:22,  1.59it/s]
 10%|█         | 6044/57600 [1:03:45<9:02:59,  1.58it/s]
 10%|█         | 6045/57600 [1:03:46<8:51:44,  1.62it/s]
 10%|█         | 6046/57600 [1:03:46<8:57:36,  1.60it/s]
 10%|█         | 6047/57600 [1:03:47<8:49:09,  1.62it/s]
 10%|█         | 6048/57600 [1:03:47<8:43:54,  1.64it/s]
 11%|█         | 6049/57600 [1:03:48<8:53:24,  1.61it/s]
 11%|█         | 6050/57600 [1:03:49<8:44:33,  1.64it/s]
 11%|█         | 6051/57600 [1:03:49<8:41:37,  1.65it/s]
 11%|█         | 6052/57600 [1:03:50<8:58:54,  1.59it/s]
 11%|█         | 6053/57600 [1:03:51<9:11:07,  1.56it/s]
 11%|█         | 6054/57600 [1:03:51<8:56:35,  1.60it/s]
 11%|█         | 6055/57600 [1:03:52<9:02:53,  1.58it/s]
 11%|█         | 6056/57600 [1:03:52<8:58:35,  1.60it/s]
 11%|█         | 6057/57600 [1:03:53<8:50:10,  1.62it/s]
 11%|█         | 6058/57600 [1:03:54<8:33:27,  1.67it/s]
 11%|█         | 6059/57600 [1:03:54<8:44:46,  1.64it/s]
 11%|█         | 6060/57600 [1:03:55<9:05:23,  1.58it/s]
                                                        
{'loss': 1.4489, 'learning_rate': 9.081184668989546e-07, 'epoch': 66.89}

 11%|█         | 6060/57600 [1:03:55<9:05:23,  1.58it/s]
 11%|█         | 6061/57600 [1:03:55<9:00:45,  1.59it/s]
 11%|█         | 6062/57600 [1:03:56<8:48:07,  1.63it/s]
 11%|█         | 6063/57600 [1:03:57<8:59:51,  1.59it/s]
 11%|█         | 6064/57600 [1:03:57<8:56:37,  1.60it/s]
 11%|█         | 6065/57600 [1:03:58<8:49:51,  1.62it/s]
 11%|█         | 6066/57600 [1:03:59<8:45:13,  1.64it/s]
 11%|█         | 6067/57600 [1:03:59<8:29:17,  1.69it/s]
 11%|█         | 6068/57600 [1:04:00<8:46:07,  1.63it/s]
 11%|█         | 6069/57600 [1:04:00<9:06:24,  1.57it/s]
 11%|█         | 6070/57600 [1:04:01<8:53:49,  1.61it/s]
 11%|█         | 6071/57600 [1:04:02<9:29:59,  1.51it/s]
 11%|█         | 6072/57600 [1:04:02<9:22:52,  1.53it/s]
 11%|█         | 6073/57600 [1:04:03<9:21:55,  1.53it/s]
 11%|█         | 6074/57600 [1:04:04<9:05:54,  1.57it/s]
 11%|█         | 6075/57600 [1:04:04<9:04:57,  1.58it/s]
 11%|█         | 6076/57600 [1:04:05<8:56:05,  1.60it/s]
 11%|█         | 6077/57600 [1:04:06<9:02:34,  1.58it/s]
 11%|█         | 6078/57600 [1:04:06<9:16:36,  1.54it/s]
 11%|█         | 6079/57600 [1:04:07<9:11:39,  1.56it/s]
 11%|█         | 6080/57600 [1:04:07<8:56:05,  1.60it/s]
                                                        
{'loss': 1.4897, 'learning_rate': 9.078048780487804e-07, 'epoch': 67.11}

 11%|█         | 6080/57600 [1:04:07<8:56:05,  1.60it/s]
 11%|█         | 6081/57600 [1:04:08<8:51:51,  1.61it/s]
 11%|█         | 6082/57600 [1:04:09<8:38:26,  1.66it/s]
 11%|█         | 6083/57600 [1:04:09<8:54:50,  1.61it/s]
 11%|█         | 6084/57600 [1:04:10<9:02:18,  1.58it/s]
 11%|█         | 6085/57600 [1:04:11<8:48:27,  1.62it/s]
 11%|█         | 6086/57600 [1:04:11<8:48:06,  1.63it/s]
 11%|█         | 6087/57600 [1:04:12<8:42:14,  1.64it/s]
 11%|█         | 6088/57600 [1:04:12<8:47:07,  1.63it/s]
 11%|█         | 6089/57600 [1:04:13<8:48:57,  1.62it/s]
 11%|█         | 6090/57600 [1:04:14<9:09:22,  1.56it/s]
 11%|█         | 6091/57600 [1:04:14<9:03:21,  1.58it/s]
 11%|█         | 6092/57600 [1:04:15<9:11:32,  1.56it/s]
 11%|█         | 6093/57600 [1:04:16<9:06:26,  1.57it/s]
 11%|█         | 6094/57600 [1:04:16<8:53:44,  1.61it/s]
 11%|█         | 6095/57600 [1:04:17<8:52:19,  1.61it/s]
 11%|█         | 6096/57600 [1:04:17<9:03:43,  1.58it/s]
 11%|█         | 6097/57600 [1:04:18<8:55:04,  1.60it/s]
 11%|█         | 6098/57600 [1:04:19<8:50:12,  1.62it/s]
 11%|█         | 6099/57600 [1:04:19<8:48:17,  1.62it/s]
 11%|█         | 6100/57600 [1:04:20<8:43:05,  1.64it/s]
                                                        
{'loss': 1.4299, 'learning_rate': 9.074912891986062e-07, 'epoch': 67.33}

 11%|█         | 6100/57600 [1:04:20<8:43:05,  1.64it/s]
 11%|█         | 6101/57600 [1:04:20<8:30:16,  1.68it/s]
 11%|█         | 6102/57600 [1:04:21<8:40:56,  1.65it/s]
 11%|█         | 6103/57600 [1:04:22<8:48:48,  1.62it/s]
 11%|█         | 6104/57600 [1:04:22<8:39:19,  1.65it/s]
 11%|█         | 6105/57600 [1:04:23<8:44:37,  1.64it/s]
 11%|█         | 6106/57600 [1:04:23<8:35:46,  1.66it/s]
 11%|█         | 6107/57600 [1:04:24<8:47:01,  1.63it/s]
 11%|█         | 6108/57600 [1:04:25<9:16:05,  1.54it/s]
 11%|█         | 6109/57600 [1:04:25<9:09:39,  1.56it/s]
 11%|█         | 6110/57600 [1:04:26<9:12:54,  1.55it/s]
 11%|█         | 6111/57600 [1:04:27<9:08:26,  1.56it/s]
 11%|█         | 6112/57600 [1:04:27<8:56:38,  1.60it/s]
 11%|█         | 6113/57600 [1:04:28<9:01:49,  1.58it/s]
 11%|█         | 6114/57600 [1:04:29<8:52:00,  1.61it/s]
 11%|█         | 6115/57600 [1:04:29<8:55:05,  1.60it/s]
 11%|█         | 6116/57600 [1:04:30<8:43:01,  1.64it/s]
 11%|█         | 6117/57600 [1:04:30<8:31:54,  1.68it/s]
 11%|█         | 6118/57600 [1:04:31<8:56:07,  1.60it/s]
 11%|█         | 6119/57600 [1:04:32<8:57:25,  1.60it/s]
 11%|█         | 6120/57600 [1:04:32<8:49:49,  1.62it/s]
                                                        
{'loss': 1.4706, 'learning_rate': 9.071777003484321e-07, 'epoch': 67.55}

 11%|█         | 6120/57600 [1:04:32<8:49:49,  1.62it/s]
 11%|█         | 6121/57600 [1:04:33<8:48:44,  1.62it/s]
 11%|█         | 6122/57600 [1:04:33<8:42:10,  1.64it/s]
 11%|█         | 6123/57600 [1:04:34<8:52:56,  1.61it/s]
 11%|█         | 6124/57600 [1:04:35<9:03:32,  1.58it/s]
 11%|█         | 6125/57600 [1:04:35<8:53:32,  1.61it/s]
 11%|█         | 6126/57600 [1:04:36<8:54:53,  1.60it/s]
 11%|█         | 6127/57600 [1:04:37<8:33:30,  1.67it/s]
 11%|█         | 6128/57600 [1:04:37<8:40:42,  1.65it/s]
 11%|█         | 6129/57600 [1:04:38<8:29:29,  1.68it/s]
 11%|█         | 6130/57600 [1:04:38<8:26:18,  1.69it/s]
 11%|█         | 6131/57600 [1:04:39<8:33:38,  1.67it/s]
 11%|█         | 6132/57600 [1:04:40<8:54:14,  1.61it/s]
 11%|█         | 6133/57600 [1:04:40<8:46:03,  1.63it/s]
 11%|█         | 6134/57600 [1:04:41<8:49:35,  1.62it/s]
 11%|█         | 6135/57600 [1:04:41<8:54:32,  1.60it/s]
 11%|█         | 6136/57600 [1:04:42<8:43:50,  1.64it/s]
 11%|█         | 6137/57600 [1:04:43<8:43:28,  1.64it/s]
 11%|█         | 6138/57600 [1:04:43<8:47:11,  1.63it/s]
 11%|█         | 6139/57600 [1:04:44<8:34:07,  1.67it/s]
 11%|█         | 6140/57600 [1:04:44<8:27:34,  1.69it/s]
                                                        
{'loss': 1.5075, 'learning_rate': 9.068641114982577e-07, 'epoch': 67.77}

 11%|█         | 6140/57600 [1:04:44<8:27:34,  1.69it/s]
 11%|█         | 6141/57600 [1:04:45<8:34:41,  1.67it/s]
 11%|█         | 6142/57600 [1:04:46<8:31:03,  1.68it/s]
 11%|█         | 6143/57600 [1:04:46<8:44:02,  1.64it/s]
 11%|█         | 6144/57600 [1:04:47<8:38:46,  1.65it/s]
 11%|█         | 6145/57600 [1:04:47<8:34:52,  1.67it/s]
 11%|█         | 6146/57600 [1:04:48<8:47:55,  1.62it/s]
 11%|█         | 6147/57600 [1:04:49<8:54:08,  1.61it/s]
 11%|█         | 6148/57600 [1:04:49<8:44:47,  1.63it/s]
 11%|█         | 6149/57600 [1:04:50<8:59:24,  1.59it/s]
 11%|█         | 6150/57600 [1:04:51<8:58:32,  1.59it/s]
 11%|█         | 6151/57600 [1:04:51<8:52:43,  1.61it/s]
 11%|█         | 6152/57600 [1:04:52<9:01:11,  1.58it/s]
 11%|█         | 6153/57600 [1:04:53<8:55:23,  1.60it/s]
 11%|█         | 6154/57600 [1:04:53<8:30:04,  1.68it/s]
 11%|█         | 6155/57600 [1:04:54<8:46:08,  1.63it/s]
 11%|█         | 6156/57600 [1:04:54<8:34:39,  1.67it/s]
 11%|█         | 6157/57600 [1:04:55<8:51:18,  1.61it/s]
 11%|█         | 6158/57600 [1:04:56<8:40:15,  1.65it/s]
 11%|█         | 6159/57600 [1:04:56<8:41:32,  1.64it/s]
 11%|█         | 6160/57600 [1:04:57<8:34:59,  1.66it/s]
                                                        
{'loss': 1.5227, 'learning_rate': 9.065505226480836e-07, 'epoch': 67.99}

 11%|█         | 6160/57600 [1:04:57<8:34:59,  1.66it/s]
 11%|█         | 6161/57600 [1:04:57<9:08:11,  1.56it/s]
 11%|█         | 6162/57600 [1:04:58<9:11:30,  1.55it/s]
 11%|█         | 6163/57600 [1:04:59<9:09:09,  1.56it/s]
 11%|█         | 6164/57600 [1:04:59<8:58:02,  1.59it/s]
 11%|█         | 6165/57600 [1:05:00<9:02:10,  1.58it/s]
 11%|█         | 6166/57600 [1:05:01<9:01:35,  1.58it/s]
 11%|█         | 6167/57600 [1:05:01<8:51:59,  1.61it/s]
 11%|█         | 6168/57600 [1:05:02<8:43:06,  1.64it/s]
 11%|█         | 6169/57600 [1:05:02<8:58:40,  1.59it/s]
 11%|█         | 6170/57600 [1:05:03<9:01:09,  1.58it/s]
 11%|█         | 6171/57600 [1:05:04<8:57:27,  1.59it/s]
 11%|█         | 6172/57600 [1:05:04<8:47:48,  1.62it/s]
 11%|█         | 6173/57600 [1:05:05<8:48:28,  1.62it/s]
 11%|█         | 6174/57600 [1:05:05<8:41:00,  1.65it/s]
 11%|█         | 6175/57600 [1:05:06<8:45:39,  1.63it/s]
 11%|█         | 6176/57600 [1:05:07<8:40:12,  1.65it/s]
 11%|█         | 6177/57600 [1:05:07<8:43:11,  1.64it/s]
 11%|█         | 6178/57600 [1:05:08<8:30:02,  1.68it/s]
 11%|█         | 6179/57600 [1:05:09<8:42:20,  1.64it/s]
 11%|█         | 6180/57600 [1:05:09<8:45:29,  1.63it/s]
                                                        
{'loss': 1.456, 'learning_rate': 9.062369337979094e-07, 'epoch': 68.21}

 11%|█         | 6180/57600 [1:05:09<8:45:29,  1.63it/s]
 11%|█         | 6181/57600 [1:05:10<8:51:55,  1.61it/s]
 11%|█         | 6182/57600 [1:05:10<8:41:20,  1.64it/s]
 11%|█         | 6183/57600 [1:05:11<8:49:33,  1.62it/s]
 11%|█         | 6184/57600 [1:05:12<8:43:54,  1.64it/s]
 11%|█         | 6185/57600 [1:05:12<8:47:45,  1.62it/s]
 11%|█         | 6186/57600 [1:05:13<8:44:03,  1.64it/s]
 11%|█         | 6187/57600 [1:05:13<8:29:28,  1.68it/s]
 11%|█         | 6188/57600 [1:05:14<8:24:21,  1.70it/s]
 11%|█         | 6189/57600 [1:05:15<8:34:55,  1.66it/s]
 11%|█         | 6190/57600 [1:05:15<8:37:21,  1.66it/s]
 11%|█         | 6191/57600 [1:05:16<8:38:18,  1.65it/s]
 11%|█         | 6192/57600 [1:05:16<8:32:27,  1.67it/s]
 11%|█         | 6193/57600 [1:05:17<8:29:40,  1.68it/s]
 11%|█         | 6194/57600 [1:05:18<8:32:50,  1.67it/s]
 11%|█         | 6195/57600 [1:05:18<8:51:45,  1.61it/s]
 11%|█         | 6196/57600 [1:05:19<9:03:16,  1.58it/s]
 11%|█         | 6197/57600 [1:05:20<8:58:49,  1.59it/s]
 11%|█         | 6198/57600 [1:05:20<9:08:11,  1.56it/s]
 11%|█         | 6199/57600 [1:05:21<9:21:02,  1.53it/s]
 11%|█         | 6200/57600 [1:05:22<9:15:11,  1.54it/s]
                                                        
{'loss': 1.4677, 'learning_rate': 9.059233449477352e-07, 'epoch': 68.43}

 11%|█         | 6200/57600 [1:05:22<9:15:11,  1.54it/s]
 11%|█         | 6201/57600 [1:05:22<9:06:22,  1.57it/s]
 11%|█         | 6202/57600 [1:05:23<9:00:42,  1.58it/s]
 11%|█         | 6203/57600 [1:05:23<8:45:04,  1.63it/s]
 11%|█         | 6204/57600 [1:05:24<8:42:11,  1.64it/s]
 11%|█         | 6205/57600 [1:05:24<8:24:49,  1.70it/s]
 11%|█         | 6206/57600 [1:05:25<8:33:24,  1.67it/s]
 11%|█         | 6207/57600 [1:05:26<9:02:22,  1.58it/s]
 11%|█         | 6208/57600 [1:05:26<8:48:13,  1.62it/s]
 11%|█         | 6209/57600 [1:05:27<9:02:19,  1.58it/s]
 11%|█         | 6210/57600 [1:05:28<9:04:42,  1.57it/s]
 11%|█         | 6211/57600 [1:05:28<8:48:11,  1.62it/s]
 11%|█         | 6212/57600 [1:05:29<8:34:20,  1.67it/s]
 11%|█         | 6213/57600 [1:05:29<8:29:47,  1.68it/s]
 11%|█         | 6214/57600 [1:05:30<8:19:13,  1.72it/s]
 11%|█         | 6215/57600 [1:05:31<8:17:02,  1.72it/s]
 11%|█         | 6216/57600 [1:05:31<8:30:54,  1.68it/s]
 11%|█         | 6217/57600 [1:05:32<8:36:31,  1.66it/s]
 11%|█         | 6218/57600 [1:05:33<9:08:35,  1.56it/s]
 11%|█         | 6219/57600 [1:05:33<8:45:53,  1.63it/s]
 11%|█         | 6220/57600 [1:05:34<8:34:25,  1.66it/s]
                                                        
{'loss': 1.4993, 'learning_rate': 9.056097560975609e-07, 'epoch': 68.65}

 11%|█         | 6220/57600 [1:05:34<8:34:25,  1.66it/s]
 11%|█         | 6221/57600 [1:05:34<8:34:17,  1.67it/s]
 11%|█         | 6222/57600 [1:05:35<8:37:53,  1.65it/s]
 11%|█         | 6223/57600 [1:05:35<8:31:52,  1.67it/s]
 11%|█         | 6224/57600 [1:05:36<8:39:44,  1.65it/s]
 11%|█         | 6225/57600 [1:05:37<8:57:54,  1.59it/s]
 11%|█         | 6226/57600 [1:05:37<9:00:08,  1.59it/s]
 11%|█         | 6227/57600 [1:05:38<8:43:32,  1.64it/s]
 11%|█         | 6228/57600 [1:05:39<8:33:25,  1.67it/s]
 11%|█         | 6229/57600 [1:05:39<8:27:13,  1.69it/s]
 11%|█         | 6230/57600 [1:05:40<8:25:30,  1.69it/s]
 11%|█         | 6231/57600 [1:05:40<8:49:11,  1.62it/s]
 11%|█         | 6232/57600 [1:05:41<8:39:48,  1.65it/s]
 11%|█         | 6233/57600 [1:05:42<8:36:53,  1.66it/s]
 11%|█         | 6234/57600 [1:05:42<8:47:30,  1.62it/s]
 11%|█         | 6235/57600 [1:05:43<9:04:24,  1.57it/s]
 11%|█         | 6236/57600 [1:05:44<9:03:24,  1.58it/s]
 11%|█         | 6237/57600 [1:05:44<8:59:10,  1.59it/s]
 11%|█         | 6238/57600 [1:05:45<8:49:39,  1.62it/s]
 11%|█         | 6239/57600 [1:05:45<8:51:40,  1.61it/s]
 11%|█         | 6240/57600 [1:05:46<9:07:56,  1.56it/s]
                                                        
{'loss': 1.4612, 'learning_rate': 9.052961672473867e-07, 'epoch': 68.87}

 11%|█         | 6240/57600 [1:05:46<9:07:56,  1.56it/s]
 11%|█         | 6241/57600 [1:05:47<9:20:07,  1.53it/s]
 11%|█         | 6242/57600 [1:05:47<9:13:14,  1.55it/s]
 11%|█         | 6243/57600 [1:05:48<9:08:33,  1.56it/s]
 11%|█         | 6244/57600 [1:05:49<8:50:36,  1.61it/s]
 11%|█         | 6245/57600 [1:05:49<8:35:20,  1.66it/s]
 11%|█         | 6246/57600 [1:05:50<8:25:30,  1.69it/s]
 11%|█         | 6247/57600 [1:05:50<8:42:53,  1.64it/s]
 11%|█         | 6248/57600 [1:05:51<9:08:39,  1.56it/s]
 11%|█         | 6249/57600 [1:05:52<9:12:10,  1.55it/s]
 11%|█         | 6250/57600 [1:05:52<9:12:36,  1.55it/s]
 11%|█         | 6251/57600 [1:05:53<9:00:21,  1.58it/s]
 11%|█         | 6252/57600 [1:05:54<9:10:57,  1.55it/s]
 11%|█         | 6253/57600 [1:05:54<9:21:39,  1.52it/s]
 11%|█         | 6254/57600 [1:05:55<9:05:16,  1.57it/s]
 11%|█         | 6255/57600 [1:05:55<8:39:00,  1.65it/s]
 11%|█         | 6256/57600 [1:05:56<8:37:40,  1.65it/s]
 11%|█         | 6257/57600 [1:05:57<8:34:12,  1.66it/s]
 11%|█         | 6258/57600 [1:05:57<8:39:07,  1.65it/s]
 11%|█         | 6259/57600 [1:05:58<8:39:24,  1.65it/s]
 11%|█         | 6260/57600 [1:05:59<9:05:48,  1.57it/s]
                                                        
{'loss': 1.4549, 'learning_rate': 9.049825783972125e-07, 'epoch': 69.09}

 11%|█         | 6260/57600 [1:05:59<9:05:48,  1.57it/s]
 11%|█         | 6261/57600 [1:05:59<8:46:28,  1.63it/s]
 11%|█         | 6262/57600 [1:06:00<8:30:39,  1.68it/s]
 11%|█         | 6263/57600 [1:06:00<8:30:44,  1.68it/s]
 11%|█         | 6264/57600 [1:06:01<8:30:41,  1.68it/s]
 11%|█         | 6265/57600 [1:06:01<8:16:55,  1.72it/s]
 11%|█         | 6266/57600 [1:06:02<8:16:10,  1.72it/s]
 11%|█         | 6267/57600 [1:06:03<8:13:37,  1.73it/s]
 11%|█         | 6268/57600 [1:06:03<8:24:23,  1.70it/s]
 11%|█         | 6269/57600 [1:06:04<8:20:49,  1.71it/s]
 11%|█         | 6270/57600 [1:06:04<8:15:56,  1.72it/s]
 11%|█         | 6271/57600 [1:06:05<8:28:49,  1.68it/s]
 11%|█         | 6272/57600 [1:06:06<8:43:50,  1.63it/s]
 11%|█         | 6273/57600 [1:06:06<8:41:04,  1.64it/s]
 11%|█         | 6274/57600 [1:06:07<8:33:57,  1.66it/s]
 11%|█         | 6275/57600 [1:06:07<8:44:29,  1.63it/s]
 11%|█         | 6276/57600 [1:06:08<8:40:25,  1.64it/s]
 11%|█         | 6277/57600 [1:06:09<8:56:52,  1.59it/s]
 11%|█         | 6278/57600 [1:06:09<9:14:56,  1.54it/s]
 11%|█         | 6279/57600 [1:06:10<9:06:09,  1.57it/s]
 11%|█         | 6280/57600 [1:06:11<8:59:39,  1.58it/s]
                                                        
{'loss': 1.5033, 'learning_rate': 9.046689895470383e-07, 'epoch': 69.32}

 11%|█         | 6280/57600 [1:06:11<8:59:39,  1.58it/s]
 11%|█         | 6281/57600 [1:06:11<8:49:03,  1.62it/s]
 11%|█         | 6282/57600 [1:06:12<9:07:02,  1.56it/s]
 11%|█         | 6283/57600 [1:06:13<9:09:38,  1.56it/s]
 11%|█         | 6284/57600 [1:06:13<9:00:50,  1.58it/s]
 11%|█         | 6285/57600 [1:06:14<9:07:33,  1.56it/s]
 11%|█         | 6286/57600 [1:06:14<9:02:45,  1.58it/s]
 11%|█         | 6287/57600 [1:06:15<8:55:57,  1.60it/s]
 11%|█         | 6288/57600 [1:06:16<9:08:43,  1.56it/s]
 11%|█         | 6289/57600 [1:06:16<9:05:23,  1.57it/s]
 11%|█         | 6290/57600 [1:06:17<9:04:42,  1.57it/s]
 11%|█         | 6291/57600 [1:06:18<8:56:17,  1.59it/s]
 11%|█         | 6292/57600 [1:06:18<8:53:08,  1.60it/s]
 11%|█         | 6293/57600 [1:06:19<8:42:07,  1.64it/s]
 11%|█         | 6294/57600 [1:06:19<8:46:04,  1.63it/s]
 11%|█         | 6295/57600 [1:06:20<8:49:30,  1.61it/s]
 11%|█         | 6296/57600 [1:06:21<8:43:32,  1.63it/s]
 11%|█         | 6297/57600 [1:06:21<8:33:03,  1.67it/s]
 11%|█         | 6298/57600 [1:06:22<8:43:51,  1.63it/s]
 11%|█         | 6299/57600 [1:06:22<8:32:26,  1.67it/s]
 11%|█         | 6300/57600 [1:06:23<8:39:28,  1.65it/s]
                                                        
{'loss': 1.4558, 'learning_rate': 9.04355400696864e-07, 'epoch': 69.54}

 11%|█         | 6300/57600 [1:06:23<8:39:28,  1.65it/s]
 11%|█         | 6301/57600 [1:06:24<8:36:26,  1.66it/s]
 11%|█         | 6302/57600 [1:06:24<8:28:02,  1.68it/s]
 11%|█         | 6303/57600 [1:06:25<8:36:20,  1.66it/s]
 11%|█         | 6304/57600 [1:06:25<8:31:33,  1.67it/s]
 11%|█         | 6305/57600 [1:06:26<8:30:17,  1.68it/s]
 11%|█         | 6306/57600 [1:06:27<8:19:43,  1.71it/s]
 11%|█         | 6307/57600 [1:06:27<8:37:11,  1.65it/s]
 11%|█         | 6308/57600 [1:06:28<8:37:57,  1.65it/s]
 11%|█         | 6309/57600 [1:06:28<8:51:06,  1.61it/s]
 11%|█         | 6310/57600 [1:06:29<8:56:21,  1.59it/s]
 11%|█         | 6311/57600 [1:06:30<8:49:08,  1.62it/s]
 11%|█         | 6312/57600 [1:06:30<8:28:17,  1.68it/s]
 11%|█         | 6313/57600 [1:06:31<8:26:45,  1.69it/s]
 11%|█         | 6314/57600 [1:06:31<8:26:16,  1.69it/s]
 11%|█         | 6315/57600 [1:06:32<8:28:43,  1.68it/s]
 11%|█         | 6316/57600 [1:06:33<8:34:49,  1.66it/s]
 11%|█         | 6317/57600 [1:06:33<8:21:13,  1.71it/s]
 11%|█         | 6318/57600 [1:06:34<8:22:16,  1.70it/s]
 11%|█         | 6319/57600 [1:06:34<8:17:02,  1.72it/s]
 11%|█         | 6320/57600 [1:06:35<8:49:37,  1.61it/s]
                                                        
{'loss': 1.4884, 'learning_rate': 9.040418118466899e-07, 'epoch': 69.76}

 11%|█         | 6320/57600 [1:06:35<8:49:37,  1.61it/s]
 11%|█         | 6321/57600 [1:06:36<8:56:05,  1.59it/s]
 11%|█         | 6322/57600 [1:06:36<8:58:16,  1.59it/s]
 11%|█         | 6323/57600 [1:06:37<9:09:11,  1.56it/s]
 11%|█         | 6324/57600 [1:06:38<9:25:35,  1.51it/s]
 11%|█         | 6325/57600 [1:06:38<9:33:34,  1.49it/s]
 11%|█         | 6326/57600 [1:06:39<9:17:21,  1.53it/s]
 11%|█         | 6327/57600 [1:06:40<9:08:57,  1.56it/s]
 11%|█         | 6328/57600 [1:06:40<8:53:31,  1.60it/s]
 11%|█         | 6329/57600 [1:06:41<8:41:14,  1.64it/s]
 11%|█         | 6330/57600 [1:06:41<8:53:32,  1.60it/s]
 11%|█         | 6331/57600 [1:06:42<9:08:57,  1.56it/s]
 11%|█         | 6332/57600 [1:06:43<9:02:18,  1.58it/s]
 11%|█         | 6333/57600 [1:06:43<9:09:21,  1.56it/s]
 11%|█         | 6334/57600 [1:06:44<9:06:12,  1.56it/s]
 11%|█         | 6335/57600 [1:06:45<8:43:45,  1.63it/s]
 11%|█         | 6336/57600 [1:06:45<8:44:13,  1.63it/s]
 11%|█         | 6337/57600 [1:06:46<8:50:24,  1.61it/s]
 11%|█         | 6338/57600 [1:06:47<8:53:26,  1.60it/s]
 11%|█         | 6339/57600 [1:06:47<8:49:52,  1.61it/s]
 11%|█         | 6340/57600 [1:06:48<9:03:45,  1.57it/s]
                                                        
{'loss': 1.4332, 'learning_rate': 9.037282229965156e-07, 'epoch': 69.98}

 11%|█         | 6340/57600 [1:06:48<9:03:45,  1.57it/s]
 11%|█         | 6341/57600 [1:06:48<8:53:16,  1.60it/s]
 11%|█         | 6342/57600 [1:06:49<9:05:53,  1.56it/s]
 11%|█         | 6343/57600 [1:06:50<9:18:47,  1.53it/s]
 11%|█         | 6344/57600 [1:06:50<9:09:38,  1.55it/s]
 11%|█         | 6345/57600 [1:06:51<8:51:23,  1.61it/s]
 11%|█         | 6346/57600 [1:06:52<8:48:01,  1.62it/s]
 11%|█         | 6347/57600 [1:06:52<9:11:29,  1.55it/s]
 11%|█         | 6348/57600 [1:06:53<8:44:14,  1.63it/s]
 11%|█         | 6349/57600 [1:06:53<8:58:11,  1.59it/s]
 11%|█         | 6350/57600 [1:06:54<8:44:07,  1.63it/s]
 11%|█         | 6351/57600 [1:06:55<8:52:03,  1.61it/s]
 11%|█         | 6352/57600 [1:06:55<8:57:39,  1.59it/s]
 11%|█         | 6353/57600 [1:06:56<8:55:37,  1.59it/s]
 11%|█         | 6354/57600 [1:06:57<8:50:01,  1.61it/s]
 11%|█         | 6355/57600 [1:06:57<8:49:22,  1.61it/s]
 11%|█         | 6356/57600 [1:06:58<9:05:19,  1.57it/s]
 11%|█         | 6357/57600 [1:06:59<9:07:33,  1.56it/s]
 11%|█         | 6358/57600 [1:06:59<8:58:52,  1.58it/s]
 11%|█         | 6359/57600 [1:07:00<8:43:38,  1.63it/s]
 11%|█         | 6360/57600 [1:07:00<8:48:22,  1.62it/s]
                                                        
{'loss': 1.455, 'learning_rate': 9.034146341463414e-07, 'epoch': 70.2}

 11%|█         | 6360/57600 [1:07:00<8:48:22,  1.62it/s]
 11%|█         | 6361/57600 [1:07:01<8:52:37,  1.60it/s]
 11%|█         | 6362/57600 [1:07:02<8:47:55,  1.62it/s]
 11%|█         | 6363/57600 [1:07:02<8:59:00,  1.58it/s]
 11%|█         | 6364/57600 [1:07:03<8:45:56,  1.62it/s]
 11%|█         | 6365/57600 [1:07:03<8:42:36,  1.63it/s]
 11%|█         | 6366/57600 [1:07:04<8:49:30,  1.61it/s]
 11%|█         | 6367/57600 [1:07:05<8:45:12,  1.63it/s]
 11%|█         | 6368/57600 [1:07:05<8:25:58,  1.69it/s]
 11%|█         | 6369/57600 [1:07:06<8:22:38,  1.70it/s]
 11%|█         | 6370/57600 [1:07:06<8:23:24,  1.70it/s]
 11%|█         | 6371/57600 [1:07:07<8:24:21,  1.69it/s]
 11%|█         | 6372/57600 [1:07:08<8:27:35,  1.68it/s]
 11%|█         | 6373/57600 [1:07:08<8:47:17,  1.62it/s]
 11%|█         | 6374/57600 [1:07:09<8:54:19,  1.60it/s]
 11%|█         | 6375/57600 [1:07:10<9:01:40,  1.58it/s]
 11%|█         | 6376/57600 [1:07:10<8:49:32,  1.61it/s]
 11%|█         | 6377/57600 [1:07:11<8:58:21,  1.59it/s]
 11%|█         | 6378/57600 [1:07:11<9:23:42,  1.51it/s]
 11%|█         | 6379/57600 [1:07:12<9:07:46,  1.56it/s]
 11%|█         | 6380/57600 [1:07:13<9:13:47,  1.54it/s]
                                                        
{'loss': 1.4155, 'learning_rate': 9.031010452961671e-07, 'epoch': 70.42}

 11%|█         | 6380/57600 [1:07:13<9:13:47,  1.54it/s]
 11%|█         | 6381/57600 [1:07:13<8:51:26,  1.61it/s]
 11%|█         | 6382/57600 [1:07:14<9:06:26,  1.56it/s]
 11%|█         | 6383/57600 [1:07:15<8:50:46,  1.61it/s]
 11%|█         | 6384/57600 [1:07:15<9:02:03,  1.57it/s]
 11%|█         | 6385/57600 [1:07:16<8:47:47,  1.62it/s]
 11%|█         | 6386/57600 [1:07:16<8:47:36,  1.62it/s]
 11%|█         | 6387/57600 [1:07:17<8:31:45,  1.67it/s]
 11%|█         | 6388/57600 [1:07:18<8:32:01,  1.67it/s]
 11%|█         | 6389/57600 [1:07:18<8:33:40,  1.66it/s]
 11%|█         | 6390/57600 [1:07:19<8:34:39,  1.66it/s]
 11%|█         | 6391/57600 [1:07:19<8:36:17,  1.65it/s]
 11%|█         | 6392/57600 [1:07:20<8:32:14,  1.67it/s]
 11%|█         | 6393/57600 [1:07:21<8:20:42,  1.70it/s]
 11%|█         | 6394/57600 [1:07:21<8:12:16,  1.73it/s]
 11%|█         | 6395/57600 [1:07:22<8:24:38,  1.69it/s]
 11%|█         | 6396/57600 [1:07:22<8:16:23,  1.72it/s]
 11%|█         | 6397/57600 [1:07:23<8:26:33,  1.68it/s]
 11%|█         | 6398/57600 [1:07:24<8:22:10,  1.70it/s]
 11%|█         | 6399/57600 [1:07:24<8:32:09,  1.67it/s]
 11%|█         | 6400/57600 [1:07:25<8:30:30,  1.67it/s]
                                                        
{'loss': 1.5361, 'learning_rate': 9.02787456445993e-07, 'epoch': 70.64}

 11%|█         | 6400/57600 [1:07:25<8:30:30,  1.67it/s]
 11%|█         | 6401/57600 [1:07:25<8:22:45,  1.70it/s]
 11%|█         | 6402/57600 [1:07:26<8:36:55,  1.65it/s]
 11%|█         | 6403/57600 [1:07:27<8:35:21,  1.66it/s]
 11%|█         | 6404/57600 [1:07:27<8:41:37,  1.64it/s]
 11%|█         | 6405/57600 [1:07:28<8:33:51,  1.66it/s]
 11%|█         | 6406/57600 [1:07:28<8:45:01,  1.63it/s]
 11%|█         | 6407/57600 [1:07:29<8:56:13,  1.59it/s]
 11%|█         | 6408/57600 [1:07:30<9:08:08,  1.56it/s]
 11%|█         | 6409/57600 [1:07:30<8:45:09,  1.62it/s]
 11%|█         | 6410/57600 [1:07:31<8:52:38,  1.60it/s]
 11%|█         | 6411/57600 [1:07:32<8:40:28,  1.64it/s]
 11%|█         | 6412/57600 [1:07:32<8:40:21,  1.64it/s]
 11%|█         | 6413/57600 [1:07:33<8:38:13,  1.65it/s]
 11%|█         | 6414/57600 [1:07:33<8:58:10,  1.59it/s]
 11%|█         | 6415/57600 [1:07:34<9:10:53,  1.55it/s]
 11%|█         | 6416/57600 [1:07:35<8:51:36,  1.60it/s]
 11%|█         | 6417/57600 [1:07:35<8:48:36,  1.61it/s]
 11%|█         | 6418/57600 [1:07:36<8:51:45,  1.60it/s]
 11%|█         | 6419/57600 [1:07:36<8:41:10,  1.64it/s]
 11%|█         | 6420/57600 [1:07:37<8:43:48,  1.63it/s]
                                                        
{'loss': 1.4696, 'learning_rate': 9.024738675958189e-07, 'epoch': 70.86}

 11%|█         | 6420/57600 [1:07:37<8:43:48,  1.63it/s]
 11%|█         | 6421/57600 [1:07:38<9:15:10,  1.54it/s]
 11%|█         | 6422/57600 [1:07:38<8:53:25,  1.60it/s]
 11%|█         | 6423/57600 [1:07:39<8:45:17,  1.62it/s]
 11%|█         | 6424/57600 [1:07:40<8:33:23,  1.66it/s]
 11%|█         | 6425/57600 [1:07:40<8:52:03,  1.60it/s]
 11%|█         | 6426/57600 [1:07:41<8:47:27,  1.62it/s]
 11%|█         | 6427/57600 [1:07:41<8:50:51,  1.61it/s]
 11%|█         | 6428/57600 [1:07:42<9:05:32,  1.56it/s]
 11%|█         | 6429/57600 [1:07:43<9:19:07,  1.53it/s]
 11%|█         | 6430/57600 [1:07:43<9:02:56,  1.57it/s]
 11%|█         | 6431/57600 [1:07:44<8:52:46,  1.60it/s]
 11%|█         | 6432/57600 [1:07:45<8:52:28,  1.60it/s]
 11%|█         | 6433/57600 [1:07:45<9:26:32,  1.51it/s]
 11%|█         | 6434/57600 [1:07:46<9:31:12,  1.49it/s]
 11%|█         | 6435/57600 [1:07:47<9:21:15,  1.52it/s]
 11%|█         | 6436/57600 [1:07:47<9:16:20,  1.53it/s]
 11%|█         | 6437/57600 [1:07:48<8:58:47,  1.58it/s]
 11%|█         | 6438/57600 [1:07:49<9:04:26,  1.57it/s]
 11%|█         | 6439/57600 [1:07:49<8:51:01,  1.61it/s]
 11%|█         | 6440/57600 [1:07:50<8:53:38,  1.60it/s]
                                                        
{'loss': 1.4936, 'learning_rate': 9.021602787456445e-07, 'epoch': 71.08}

 11%|█         | 6440/57600 [1:07:50<8:53:38,  1.60it/s]
 11%|█         | 6441/57600 [1:07:50<8:34:41,  1.66it/s]
 11%|█         | 6442/57600 [1:07:51<8:22:02,  1.70it/s]
 11%|█         | 6443/57600 [1:07:52<8:24:32,  1.69it/s]
 11%|█         | 6444/57600 [1:07:52<8:16:02,  1.72it/s]
 11%|█         | 6445/57600 [1:07:53<8:51:52,  1.60it/s]
 11%|█         | 6446/57600 [1:07:53<8:42:42,  1.63it/s]
 11%|█         | 6447/57600 [1:07:54<8:33:08,  1.66it/s]
 11%|█         | 6448/57600 [1:07:55<8:50:49,  1.61it/s]
 11%|█         | 6449/57600 [1:07:55<8:48:53,  1.61it/s]
 11%|█         | 6450/57600 [1:07:56<8:52:58,  1.60it/s]
 11%|█         | 6451/57600 [1:07:56<8:41:53,  1.63it/s]
 11%|█         | 6452/57600 [1:07:57<8:54:44,  1.59it/s]
 11%|█         | 6453/57600 [1:07:58<8:50:22,  1.61it/s]
 11%|█         | 6454/57600 [1:07:58<9:05:51,  1.56it/s]
 11%|█         | 6455/57600 [1:07:59<9:03:01,  1.57it/s]
 11%|█         | 6456/57600 [1:08:00<8:55:33,  1.59it/s]
 11%|█         | 6457/57600 [1:08:00<8:58:56,  1.58it/s]
 11%|█         | 6458/57600 [1:08:01<8:55:15,  1.59it/s]
 11%|█         | 6459/57600 [1:08:02<9:25:38,  1.51it/s]
 11%|█         | 6460/57600 [1:08:02<9:18:20,  1.53it/s]
                                                        
{'loss': 1.4689, 'learning_rate': 9.018466898954704e-07, 'epoch': 71.3}

 11%|█         | 6460/57600 [1:08:02<9:18:20,  1.53it/s]
 11%|█         | 6461/57600 [1:08:03<9:21:41,  1.52it/s]
 11%|█         | 6462/57600 [1:08:04<9:09:58,  1.55it/s]
 11%|█         | 6463/57600 [1:08:04<9:01:07,  1.58it/s]
 11%|█         | 6464/57600 [1:08:05<8:42:25,  1.63it/s]
 11%|█         | 6465/57600 [1:08:05<8:43:05,  1.63it/s]
 11%|█         | 6466/57600 [1:08:06<8:51:11,  1.60it/s]
 11%|█         | 6467/57600 [1:08:07<8:43:12,  1.63it/s]
 11%|█         | 6468/57600 [1:08:07<8:43:13,  1.63it/s]
 11%|█         | 6469/57600 [1:08:08<8:46:28,  1.62it/s]
 11%|█         | 6470/57600 [1:08:08<8:41:40,  1.63it/s]
 11%|█         | 6471/57600 [1:08:09<9:00:13,  1.58it/s]
 11%|█         | 6472/57600 [1:08:10<8:51:20,  1.60it/s]
 11%|█         | 6473/57600 [1:08:10<8:51:11,  1.60it/s]
 11%|█         | 6474/57600 [1:08:11<9:03:48,  1.57it/s]
 11%|█         | 6475/57600 [1:08:12<8:53:00,  1.60it/s]
 11%|█         | 6476/57600 [1:08:12<8:33:16,  1.66it/s]
 11%|█         | 6477/57600 [1:08:13<8:33:19,  1.66it/s]
 11%|█         | 6478/57600 [1:08:13<8:28:26,  1.68it/s]
 11%|█         | 6479/57600 [1:08:14<8:18:19,  1.71it/s]
 11%|█▏        | 6480/57600 [1:08:14<8:12:10,  1.73it/s]
                                                        
{'loss': 1.4862, 'learning_rate': 9.015331010452961e-07, 'epoch': 71.52}

 11%|█▏        | 6480/57600 [1:08:14<8:12:10,  1.73it/s]
 11%|█▏        | 6481/57600 [1:08:15<8:17:25,  1.71it/s]
 11%|█▏        | 6482/57600 [1:08:16<8:26:05,  1.68it/s]
 11%|█▏        | 6483/57600 [1:08:16<8:27:20,  1.68it/s]
 11%|█▏        | 6484/57600 [1:08:17<8:39:54,  1.64it/s]
 11%|█▏        | 6485/57600 [1:08:18<8:44:08,  1.63it/s]
 11%|█▏        | 6486/57600 [1:08:18<8:54:04,  1.60it/s]
 11%|█▏        | 6487/57600 [1:08:19<8:57:11,  1.59it/s]
 11%|█▏        | 6488/57600 [1:08:19<8:46:51,  1.62it/s]
 11%|█▏        | 6489/57600 [1:08:20<8:54:29,  1.59it/s]
 11%|█▏        | 6490/57600 [1:08:21<8:36:46,  1.65it/s]
 11%|█▏        | 6491/57600 [1:08:21<8:24:14,  1.69it/s]
 11%|█▏        | 6492/57600 [1:08:22<8:30:39,  1.67it/s]
 11%|█▏        | 6493/57600 [1:08:23<8:57:39,  1.58it/s]
 11%|█▏        | 6494/57600 [1:08:23<8:32:56,  1.66it/s]
 11%|█▏        | 6495/57600 [1:08:24<8:48:32,  1.61it/s]
 11%|█▏        | 6496/57600 [1:08:24<8:31:26,  1.67it/s]
 11%|█▏        | 6497/57600 [1:08:25<8:25:12,  1.69it/s]
 11%|█▏        | 6498/57600 [1:08:25<8:26:22,  1.68it/s]
 11%|█▏        | 6499/57600 [1:08:26<8:38:28,  1.64it/s]
 11%|█▏        | 6500/57600 [1:08:27<8:42:13,  1.63it/s]
                                                        
{'loss': 1.463, 'learning_rate': 9.012195121951219e-07, 'epoch': 71.74}

 11%|█▏        | 6500/57600 [1:08:27<8:42:13,  1.63it/s]
 11%|█▏        | 6501/57600 [1:08:27<8:37:48,  1.64it/s]
 11%|█▏        | 6502/57600 [1:08:28<8:31:22,  1.67it/s]
 11%|█▏        | 6503/57600 [1:08:29<8:34:21,  1.66it/s]
 11%|█▏        | 6504/57600 [1:08:29<8:37:16,  1.65it/s]
 11%|█▏        | 6505/57600 [1:08:30<9:05:12,  1.56it/s]
 11%|█▏        | 6506/57600 [1:08:31<9:05:21,  1.56it/s]
 11%|█▏        | 6507/57600 [1:08:31<9:17:29,  1.53it/s]
 11%|█▏        | 6508/57600 [1:08:32<9:07:11,  1.56it/s]
 11%|█▏        | 6509/57600 [1:08:32<8:48:55,  1.61it/s]
 11%|█▏        | 6510/57600 [1:08:33<8:51:11,  1.60it/s]
 11%|█▏        | 6511/57600 [1:08:34<8:34:21,  1.66it/s]
 11%|█▏        | 6512/57600 [1:08:34<8:18:53,  1.71it/s]
 11%|█▏        | 6513/57600 [1:08:35<8:51:14,  1.60it/s]
 11%|█▏        | 6514/57600 [1:08:35<8:37:17,  1.65it/s]
 11%|█▏        | 6515/57600 [1:08:36<8:25:11,  1.69it/s]
 11%|█▏        | 6516/57600 [1:08:37<8:34:14,  1.66it/s]
 11%|█▏        | 6517/57600 [1:08:37<8:32:39,  1.66it/s]
 11%|█▏        | 6518/57600 [1:08:38<8:52:06,  1.60it/s]
 11%|█▏        | 6519/57600 [1:08:39<9:00:44,  1.57it/s]
 11%|█▏        | 6520/57600 [1:08:39<8:51:32,  1.60it/s]
                                                        
{'loss': 1.4663, 'learning_rate': 9.009059233449477e-07, 'epoch': 71.96}

 11%|█▏        | 6520/57600 [1:08:39<8:51:32,  1.60it/s]
 11%|█▏        | 6521/57600 [1:08:40<8:33:51,  1.66it/s]
 11%|█▏        | 6522/57600 [1:08:40<8:28:24,  1.67it/s]
 11%|█▏        | 6523/57600 [1:08:41<8:25:29,  1.68it/s]
 11%|█▏        | 6524/57600 [1:08:42<8:48:09,  1.61it/s]
 11%|█▏        | 6525/57600 [1:08:42<8:47:10,  1.61it/s]
 11%|█▏        | 6526/57600 [1:08:43<8:52:13,  1.60it/s]
 11%|█▏        | 6527/57600 [1:08:43<8:38:22,  1.64it/s]
 11%|█▏        | 6528/57600 [1:08:44<8:30:56,  1.67it/s]
 11%|█▏        | 6529/57600 [1:08:45<8:39:31,  1.64it/s]
 11%|█▏        | 6530/57600 [1:08:45<8:37:07,  1.65it/s]
 11%|█▏        | 6531/57600 [1:08:46<8:36:26,  1.65it/s]
 11%|█▏        | 6532/57600 [1:08:46<8:52:58,  1.60it/s]
 11%|█▏        | 6533/57600 [1:08:47<9:05:46,  1.56it/s]
 11%|█▏        | 6534/57600 [1:08:48<8:44:15,  1.62it/s]
 11%|█▏        | 6535/57600 [1:08:48<8:48:07,  1.61it/s]
 11%|█▏        | 6536/57600 [1:08:49<8:50:51,  1.60it/s]
 11%|█▏        | 6537/57600 [1:08:50<8:40:08,  1.64it/s]
 11%|█▏        | 6538/57600 [1:08:50<8:57:20,  1.58it/s]
 11%|█▏        | 6539/57600 [1:08:51<9:04:26,  1.56it/s]
 11%|█▏        | 6540/57600 [1:08:51<8:58:54,  1.58it/s]
                                                        
{'loss': 1.4918, 'learning_rate': 9.005923344947735e-07, 'epoch': 72.19}

 11%|█▏        | 6540/57600 [1:08:51<8:58:54,  1.58it/s]
 11%|█▏        | 6541/57600 [1:08:52<8:50:01,  1.61it/s]
 11%|█▏        | 6542/57600 [1:08:53<8:31:34,  1.66it/s]
 11%|█▏        | 6543/57600 [1:08:53<8:23:05,  1.69it/s]
 11%|█▏        | 6544/57600 [1:08:54<8:17:51,  1.71it/s]
 11%|█▏        | 6545/57600 [1:08:54<8:15:08,  1.72it/s]
 11%|█▏        | 6546/57600 [1:08:55<8:26:55,  1.68it/s]
 11%|█▏        | 6547/57600 [1:08:56<8:18:46,  1.71it/s]
 11%|█▏        | 6548/57600 [1:08:56<8:33:12,  1.66it/s]
 11%|█▏        | 6549/57600 [1:08:57<8:22:47,  1.69it/s]
 11%|█▏        | 6550/57600 [1:08:57<8:29:58,  1.67it/s]
 11%|█▏        | 6551/57600 [1:08:58<8:49:14,  1.61it/s]
 11%|█▏        | 6552/57600 [1:08:59<8:47:45,  1.61it/s]
 11%|█▏        | 6553/57600 [1:08:59<8:42:51,  1.63it/s]
 11%|█▏        | 6554/57600 [1:09:00<8:29:00,  1.67it/s]
 11%|█▏        | 6555/57600 [1:09:00<8:30:42,  1.67it/s]
 11%|█▏        | 6556/57600 [1:09:01<8:49:05,  1.61it/s]
 11%|█▏        | 6557/57600 [1:09:02<9:05:39,  1.56it/s]
 11%|█▏        | 6558/57600 [1:09:02<8:58:37,  1.58it/s]
 11%|█▏        | 6559/57600 [1:09:03<9:08:40,  1.55it/s]
 11%|█▏        | 6560/57600 [1:09:04<9:10:10,  1.55it/s]
                                                        
{'loss': 1.474, 'learning_rate': 9.002787456445993e-07, 'epoch': 72.41}

 11%|█▏        | 6560/57600 [1:09:04<9:10:10,  1.55it/s]
 11%|█▏        | 6561/57600 [1:09:04<9:06:37,  1.56it/s]
 11%|█▏        | 6562/57600 [1:09:05<9:05:06,  1.56it/s]
 11%|█▏        | 6563/57600 [1:09:06<8:57:38,  1.58it/s]
 11%|█▏        | 6564/57600 [1:09:06<8:58:18,  1.58it/s]
 11%|█▏        | 6565/57600 [1:09:07<9:00:41,  1.57it/s]
 11%|█▏        | 6566/57600 [1:09:07<8:42:14,  1.63it/s]
 11%|█▏        | 6567/57600 [1:09:08<9:02:11,  1.57it/s]
 11%|█▏        | 6568/57600 [1:09:09<9:01:26,  1.57it/s]
 11%|█▏        | 6569/57600 [1:09:09<8:56:20,  1.59it/s]
 11%|█▏        | 6570/57600 [1:09:10<8:42:07,  1.63it/s]
 11%|█▏        | 6571/57600 [1:09:11<8:35:52,  1.65it/s]
 11%|█▏        | 6572/57600 [1:09:11<8:36:45,  1.65it/s]
 11%|█▏        | 6573/57600 [1:09:12<9:00:51,  1.57it/s]
 11%|█▏        | 6574/57600 [1:09:13<9:29:28,  1.49it/s]
 11%|█▏        | 6575/57600 [1:09:13<9:15:18,  1.53it/s]
 11%|█▏        | 6576/57600 [1:09:14<9:09:01,  1.55it/s]
 11%|█▏        | 6577/57600 [1:09:14<8:49:19,  1.61it/s]
 11%|█▏        | 6578/57600 [1:09:15<8:40:53,  1.63it/s]
 11%|█▏        | 6579/57600 [1:09:16<8:51:03,  1.60it/s]
 11%|█▏        | 6580/57600 [1:09:16<8:41:52,  1.63it/s]
                                                        
{'loss': 1.4693, 'learning_rate': 8.99965156794425e-07, 'epoch': 72.63}

 11%|█▏        | 6580/57600 [1:09:16<8:41:52,  1.63it/s]
 11%|█▏        | 6581/57600 [1:09:17<8:31:25,  1.66it/s]
 11%|█▏        | 6582/57600 [1:09:17<8:28:00,  1.67it/s]
 11%|█▏        | 6583/57600 [1:09:18<8:21:19,  1.70it/s]
 11%|█▏        | 6584/57600 [1:09:19<8:08:14,  1.74it/s]
 11%|█▏        | 6585/57600 [1:09:19<8:22:52,  1.69it/s]
 11%|█▏        | 6586/57600 [1:09:20<8:49:03,  1.61it/s]
 11%|█▏        | 6587/57600 [1:09:20<8:42:05,  1.63it/s]
 11%|█▏        | 6588/57600 [1:09:21<8:51:39,  1.60it/s]
 11%|█▏        | 6589/57600 [1:09:22<8:46:33,  1.61it/s]
 11%|█▏        | 6590/57600 [1:09:22<8:30:51,  1.66it/s]
 11%|█▏        | 6591/57600 [1:09:23<8:42:23,  1.63it/s]
 11%|█▏        | 6592/57600 [1:09:24<8:45:30,  1.62it/s]
 11%|█▏        | 6593/57600 [1:09:24<8:46:14,  1.62it/s]
 11%|█▏        | 6594/57600 [1:09:25<8:31:56,  1.66it/s]
 11%|█▏        | 6595/57600 [1:09:25<8:48:05,  1.61it/s]
 11%|█▏        | 6596/57600 [1:09:26<8:41:22,  1.63it/s]
 11%|█▏        | 6597/57600 [1:09:27<8:46:19,  1.62it/s]
 11%|█▏        | 6598/57600 [1:09:27<8:33:12,  1.66it/s]
 11%|█▏        | 6599/57600 [1:09:28<8:27:02,  1.68it/s]
 11%|█▏        | 6600/57600 [1:09:28<8:32:02,  1.66it/s]
                                                        
{'loss': 1.438, 'learning_rate': 8.996515679442507e-07, 'epoch': 72.85}

 11%|█▏        | 6600/57600 [1:09:28<8:32:02,  1.66it/s]
 11%|█▏        | 6601/57600 [1:09:29<8:25:14,  1.68it/s]
 11%|█▏        | 6602/57600 [1:09:30<8:26:18,  1.68it/s]
 11%|█▏        | 6603/57600 [1:09:30<8:26:04,  1.68it/s]
 11%|█▏        | 6604/57600 [1:09:31<8:33:29,  1.66it/s]
 11%|█▏        | 6605/57600 [1:09:31<8:32:34,  1.66it/s]
 11%|█▏        | 6606/57600 [1:09:32<8:40:01,  1.63it/s]
 11%|█▏        | 6607/57600 [1:09:33<8:52:34,  1.60it/s]
 11%|█▏        | 6608/57600 [1:09:33<8:55:56,  1.59it/s]
 11%|█▏        | 6609/57600 [1:09:34<8:53:38,  1.59it/s]
 11%|█▏        | 6610/57600 [1:09:35<8:52:45,  1.60it/s]
 11%|█▏        | 6611/57600 [1:09:35<8:42:43,  1.63it/s]
 11%|█▏        | 6612/57600 [1:09:36<8:42:54,  1.63it/s]
 11%|█▏        | 6613/57600 [1:09:36<8:53:54,  1.59it/s]
 11%|█▏        | 6614/57600 [1:09:37<9:01:16,  1.57it/s]
 11%|█▏        | 6615/57600 [1:09:38<8:46:50,  1.61it/s]
 11%|█▏        | 6616/57600 [1:09:38<8:38:27,  1.64it/s]
 11%|█▏        | 6617/57600 [1:09:39<8:47:02,  1.61it/s]
 11%|█▏        | 6618/57600 [1:09:39<8:47:56,  1.61it/s]
 11%|█▏        | 6619/57600 [1:09:40<8:51:45,  1.60it/s]
 11%|█▏        | 6620/57600 [1:09:41<8:41:50,  1.63it/s]
                                                        
{'loss': 1.4405, 'learning_rate': 8.993379790940766e-07, 'epoch': 73.07}

 11%|█▏        | 6620/57600 [1:09:41<8:41:50,  1.63it/s]
 11%|█▏        | 6621/57600 [1:09:41<9:04:58,  1.56it/s]
 11%|█▏        | 6622/57600 [1:09:42<8:48:49,  1.61it/s]
 11%|█▏        | 6623/57600 [1:09:43<8:34:22,  1.65it/s]
 12%|█▏        | 6624/57600 [1:09:43<8:37:44,  1.64it/s]
 12%|█▏        | 6625/57600 [1:09:44<8:46:33,  1.61it/s]
 12%|█▏        | 6626/57600 [1:09:44<8:38:14,  1.64it/s]
 12%|█▏        | 6627/57600 [1:09:45<8:20:11,  1.70it/s]
 12%|█▏        | 6628/57600 [1:09:46<8:40:34,  1.63it/s]
 12%|█▏        | 6629/57600 [1:09:46<8:42:50,  1.62it/s]
 12%|█▏        | 6630/57600 [1:09:47<8:37:55,  1.64it/s]
 12%|█▏        | 6631/57600 [1:09:47<8:42:12,  1.63it/s]
 12%|█▏        | 6632/57600 [1:09:48<8:35:55,  1.65it/s]
 12%|█▏        | 6633/57600 [1:09:49<8:57:58,  1.58it/s]
 12%|█▏        | 6634/57600 [1:09:49<8:56:29,  1.58it/s]
 12%|█▏        | 6635/57600 [1:09:50<8:38:58,  1.64it/s]
 12%|█▏        | 6636/57600 [1:09:51<8:45:46,  1.62it/s]
 12%|█▏        | 6637/57600 [1:09:51<9:09:43,  1.55it/s]
 12%|█▏        | 6638/57600 [1:09:52<8:53:21,  1.59it/s]
 12%|█▏        | 6639/57600 [1:09:53<9:10:57,  1.54it/s]
 12%|█▏        | 6640/57600 [1:09:53<9:13:47,  1.53it/s]
                                                        
{'loss': 1.4501, 'learning_rate': 8.990243902439025e-07, 'epoch': 73.29}

 12%|█▏        | 6640/57600 [1:09:53<9:13:47,  1.53it/s]
 12%|█▏        | 6641/57600 [1:09:54<9:10:44,  1.54it/s]
 12%|█▏        | 6642/57600 [1:09:55<9:21:21,  1.51it/s]
 12%|█▏        | 6643/57600 [1:09:55<9:02:05,  1.57it/s]
 12%|█▏        | 6644/57600 [1:09:56<8:55:29,  1.59it/s]
 12%|█▏        | 6645/57600 [1:09:56<8:44:48,  1.62it/s]
 12%|█▏        | 6646/57600 [1:09:57<8:53:22,  1.59it/s]
 12%|█▏        | 6647/57600 [1:09:58<8:36:29,  1.64it/s]
 12%|█▏        | 6648/57600 [1:09:58<8:40:40,  1.63it/s]
 12%|█▏        | 6649/57600 [1:09:59<8:39:17,  1.64it/s]
 12%|█▏        | 6650/57600 [1:09:59<8:24:00,  1.68it/s]
 12%|█▏        | 6651/57600 [1:10:00<8:36:04,  1.65it/s]
 12%|█▏        | 6652/57600 [1:10:01<8:51:23,  1.60it/s]
 12%|█▏        | 6653/57600 [1:10:01<8:49:43,  1.60it/s]
 12%|█▏        | 6654/57600 [1:10:02<8:37:18,  1.64it/s]
 12%|█▏        | 6655/57600 [1:10:02<8:45:32,  1.62it/s]
 12%|█▏        | 6656/57600 [1:10:03<8:29:30,  1.67it/s]
 12%|█▏        | 6657/57600 [1:10:04<8:22:56,  1.69it/s]
 12%|█▏        | 6658/57600 [1:10:04<8:31:59,  1.66it/s]
 12%|█▏        | 6659/57600 [1:10:05<8:32:59,  1.66it/s]
 12%|█▏        | 6660/57600 [1:10:06<8:51:57,  1.60it/s]
                                                        
{'loss': 1.4801, 'learning_rate': 8.987108013937282e-07, 'epoch': 73.51}

 12%|█▏        | 6660/57600 [1:10:06<8:51:57,  1.60it/s]
 12%|█▏        | 6661/57600 [1:10:06<8:41:48,  1.63it/s]
 12%|█▏        | 6662/57600 [1:10:07<9:01:35,  1.57it/s]
 12%|█▏        | 6663/57600 [1:10:07<9:09:25,  1.55it/s]
 12%|█▏        | 6664/57600 [1:10:08<8:50:53,  1.60it/s]
 12%|█▏        | 6665/57600 [1:10:09<8:44:36,  1.62it/s]
 12%|█▏        | 6666/57600 [1:10:09<8:39:04,  1.64it/s]
 12%|█▏        | 6667/57600 [1:10:10<8:50:03,  1.60it/s]
 12%|█▏        | 6668/57600 [1:10:10<8:35:06,  1.65it/s]
 12%|█▏        | 6669/57600 [1:10:11<8:47:26,  1.61it/s]
 12%|█▏        | 6670/57600 [1:10:12<8:33:52,  1.65it/s]
 12%|█▏        | 6671/57600 [1:10:12<8:55:17,  1.59it/s]
 12%|█▏        | 6672/57600 [1:10:13<8:49:50,  1.60it/s]
 12%|█▏        | 6673/57600 [1:10:14<8:39:24,  1.63it/s]
 12%|█▏        | 6674/57600 [1:10:14<8:49:21,  1.60it/s]
 12%|█▏        | 6675/57600 [1:10:15<8:40:34,  1.63it/s]
 12%|█▏        | 6676/57600 [1:10:15<8:36:26,  1.64it/s]
 12%|█▏        | 6677/57600 [1:10:16<8:37:43,  1.64it/s]
 12%|█▏        | 6678/57600 [1:10:17<8:45:01,  1.62it/s]
 12%|█▏        | 6679/57600 [1:10:17<8:41:04,  1.63it/s]
 12%|█▏        | 6680/57600 [1:10:18<8:23:22,  1.69it/s]
                                                        
{'loss': 1.4407, 'learning_rate': 8.98397212543554e-07, 'epoch': 73.73}

 12%|█▏        | 6680/57600 [1:10:18<8:23:22,  1.69it/s]
 12%|█▏        | 6681/57600 [1:10:18<8:41:50,  1.63it/s]
 12%|█▏        | 6682/57600 [1:10:19<9:01:37,  1.57it/s]
 12%|█▏        | 6683/57600 [1:10:20<8:57:24,  1.58it/s]
 12%|█▏        | 6684/57600 [1:10:20<8:45:53,  1.61it/s]
 12%|█▏        | 6685/57600 [1:10:21<8:51:07,  1.60it/s]
 12%|█▏        | 6686/57600 [1:10:22<8:33:49,  1.65it/s]
 12%|█▏        | 6687/57600 [1:10:22<8:52:33,  1.59it/s]
 12%|█▏        | 6688/57600 [1:10:23<8:51:22,  1.60it/s]
 12%|█▏        | 6689/57600 [1:10:24<8:52:01,  1.59it/s]
 12%|█▏        | 6690/57600 [1:10:24<9:04:49,  1.56it/s]
 12%|█▏        | 6691/57600 [1:10:25<9:08:04,  1.55it/s]
 12%|█▏        | 6692/57600 [1:10:25<8:46:26,  1.61it/s]
 12%|█▏        | 6693/57600 [1:10:26<9:05:02,  1.56it/s]
 12%|█▏        | 6694/57600 [1:10:27<8:56:24,  1.58it/s]
 12%|█▏        | 6695/57600 [1:10:27<8:56:05,  1.58it/s]
 12%|█▏        | 6696/57600 [1:10:28<8:51:47,  1.60it/s]
 12%|█▏        | 6697/57600 [1:10:29<8:59:27,  1.57it/s]
 12%|█▏        | 6698/57600 [1:10:29<8:53:37,  1.59it/s]
 12%|█▏        | 6699/57600 [1:10:30<8:46:20,  1.61it/s]
 12%|█▏        | 6700/57600 [1:10:30<8:52:29,  1.59it/s]
                                                        
{'loss': 1.4393, 'learning_rate': 8.980836236933798e-07, 'epoch': 73.95}

 12%|█▏        | 6700/57600 [1:10:30<8:52:29,  1.59it/s]
 12%|█▏        | 6701/57600 [1:10:31<9:11:48,  1.54it/s]
 12%|█▏        | 6702/57600 [1:10:32<9:05:33,  1.55it/s]
 12%|█▏        | 6703/57600 [1:10:32<9:20:18,  1.51it/s]
 12%|█▏        | 6704/57600 [1:10:33<8:51:35,  1.60it/s]
 12%|█▏        | 6705/57600 [1:10:34<9:09:08,  1.54it/s]
 12%|█▏        | 6706/57600 [1:10:34<9:02:39,  1.56it/s]
 12%|█▏        | 6707/57600 [1:10:35<9:05:51,  1.55it/s]
 12%|█▏        | 6708/57600 [1:10:36<9:16:52,  1.52it/s]
 12%|█▏        | 6709/57600 [1:10:36<9:20:38,  1.51it/s]
 12%|█▏        | 6710/57600 [1:10:37<9:05:29,  1.55it/s]
 12%|█▏        | 6711/57600 [1:10:38<9:25:13,  1.50it/s]
 12%|█▏        | 6712/57600 [1:10:38<9:03:31,  1.56it/s]
 12%|█▏        | 6713/57600 [1:10:39<8:55:09,  1.58it/s]
 12%|█▏        | 6714/57600 [1:10:40<9:01:02,  1.57it/s]
 12%|█▏        | 6715/57600 [1:10:40<9:25:14,  1.50it/s]
 12%|█▏        | 6716/57600 [1:10:41<9:15:56,  1.53it/s]
 12%|█▏        | 6717/57600 [1:10:42<9:35:46,  1.47it/s]
 12%|█▏        | 6718/57600 [1:10:42<9:22:57,  1.51it/s]
 12%|█▏        | 6719/57600 [1:10:43<8:58:35,  1.57it/s]
 12%|█▏        | 6720/57600 [1:10:44<9:08:39,  1.55it/s]
                                                        
{'loss': 1.3913, 'learning_rate': 8.977700348432056e-07, 'epoch': 74.17}

 12%|█▏        | 6720/57600 [1:10:44<9:08:39,  1.55it/s]
 12%|█▏        | 6721/57600 [1:10:44<8:55:47,  1.58it/s]
 12%|█▏        | 6722/57600 [1:10:45<8:50:49,  1.60it/s]
 12%|█▏        | 6723/57600 [1:10:45<9:05:47,  1.55it/s]
 12%|█▏        | 6724/57600 [1:10:46<9:11:17,  1.54it/s]
 12%|█▏        | 6725/57600 [1:10:47<9:07:12,  1.55it/s]
 12%|█▏        | 6726/57600 [1:10:47<8:44:44,  1.62it/s]
 12%|█▏        | 6727/57600 [1:10:48<8:29:42,  1.66it/s]
 12%|█▏        | 6728/57600 [1:10:48<8:19:31,  1.70it/s]
 12%|█▏        | 6729/57600 [1:10:49<8:46:06,  1.61it/s]
 12%|█▏        | 6730/57600 [1:10:50<8:29:27,  1.66it/s]
 12%|█▏        | 6731/57600 [1:10:50<8:34:41,  1.65it/s]
 12%|█▏        | 6732/57600 [1:10:51<8:54:02,  1.59it/s]
 12%|█▏        | 6733/57600 [1:10:52<9:02:11,  1.56it/s]
 12%|█▏        | 6734/57600 [1:10:52<8:48:54,  1.60it/s]
 12%|█▏        | 6735/57600 [1:10:53<8:27:48,  1.67it/s]
 12%|█▏        | 6736/57600 [1:10:53<8:25:38,  1.68it/s]
 12%|█▏        | 6737/57600 [1:10:54<8:36:30,  1.64it/s]
 12%|█▏        | 6738/57600 [1:10:55<8:55:21,  1.58it/s]
 12%|█▏        | 6739/57600 [1:10:55<8:49:19,  1.60it/s]
 12%|█▏        | 6740/57600 [1:10:56<8:44:42,  1.62it/s]
                                                        
{'loss': 1.4949, 'learning_rate': 8.974564459930313e-07, 'epoch': 74.39}

 12%|█▏        | 6740/57600 [1:10:56<8:44:42,  1.62it/s]
 12%|█▏        | 6741/57600 [1:10:57<9:05:01,  1.56it/s]
 12%|█▏        | 6742/57600 [1:10:57<9:03:11,  1.56it/s]
 12%|█▏        | 6743/57600 [1:10:58<8:52:24,  1.59it/s]
 12%|█▏        | 6744/57600 [1:10:58<8:44:47,  1.62it/s]
 12%|█▏        | 6745/57600 [1:10:59<8:51:23,  1.60it/s]
 12%|█▏        | 6746/57600 [1:11:00<8:48:57,  1.60it/s]
 12%|█▏        | 6747/57600 [1:11:00<8:58:58,  1.57it/s]
 12%|█▏        | 6748/57600 [1:11:01<9:09:13,  1.54it/s]
 12%|█▏        | 6749/57600 [1:11:02<8:54:07,  1.59it/s]
 12%|█▏        | 6750/57600 [1:11:02<8:45:59,  1.61it/s]
 12%|█▏        | 6751/57600 [1:11:03<8:54:59,  1.58it/s]
 12%|█▏        | 6752/57600 [1:11:03<8:37:49,  1.64it/s]
 12%|█▏        | 6753/57600 [1:11:04<8:31:06,  1.66it/s]
 12%|█▏        | 6754/57600 [1:11:05<8:40:39,  1.63it/s]
 12%|█▏        | 6755/57600 [1:11:05<8:27:01,  1.67it/s]
 12%|█▏        | 6756/57600 [1:11:06<8:19:48,  1.70it/s]
 12%|█▏        | 6757/57600 [1:11:06<8:12:41,  1.72it/s]
 12%|█▏        | 6758/57600 [1:11:07<8:17:02,  1.70it/s]
 12%|█▏        | 6759/57600 [1:11:08<8:20:09,  1.69it/s]
 12%|█▏        | 6760/57600 [1:11:08<8:33:04,  1.65it/s]
                                                        
{'loss': 1.4363, 'learning_rate': 8.971428571428571e-07, 'epoch': 74.61}

 12%|█▏        | 6760/57600 [1:11:08<8:33:04,  1.65it/s]
 12%|█▏        | 6761/57600 [1:11:09<8:41:17,  1.63it/s]
 12%|█▏        | 6762/57600 [1:11:09<8:37:36,  1.64it/s]
 12%|█▏        | 6763/57600 [1:11:10<8:23:38,  1.68it/s]
 12%|█▏        | 6764/57600 [1:11:11<8:29:30,  1.66it/s]
 12%|█▏        | 6765/57600 [1:11:11<8:36:30,  1.64it/s]
 12%|█▏        | 6766/57600 [1:11:12<8:31:29,  1.66it/s]
 12%|█▏        | 6767/57600 [1:11:12<8:40:51,  1.63it/s]
 12%|█▏        | 6768/57600 [1:11:13<8:41:06,  1.63it/s]
 12%|█▏        | 6769/57600 [1:11:14<8:48:01,  1.60it/s]
 12%|█▏        | 6770/57600 [1:11:14<8:36:28,  1.64it/s]
 12%|█▏        | 6771/57600 [1:11:15<8:27:44,  1.67it/s]
 12%|█▏        | 6772/57600 [1:11:15<8:19:28,  1.70it/s]
 12%|█▏        | 6773/57600 [1:11:16<8:51:46,  1.59it/s]
 12%|█▏        | 6774/57600 [1:11:17<8:44:50,  1.61it/s]
 12%|█▏        | 6775/57600 [1:11:17<8:27:56,  1.67it/s]
 12%|█▏        | 6776/57600 [1:11:18<8:31:44,  1.66it/s]
 12%|█▏        | 6777/57600 [1:11:19<8:43:25,  1.62it/s]
 12%|█▏        | 6778/57600 [1:11:19<9:01:56,  1.56it/s]
 12%|█▏        | 6779/57600 [1:11:20<8:55:24,  1.58it/s]
 12%|█▏        | 6780/57600 [1:11:21<9:07:41,  1.55it/s]
                                                        
{'loss': 1.4655, 'learning_rate': 8.968292682926829e-07, 'epoch': 74.83}

 12%|█▏        | 6780/57600 [1:11:21<9:07:41,  1.55it/s]
 12%|█▏        | 6781/57600 [1:11:21<9:15:16,  1.53it/s]
 12%|█▏        | 6782/57600 [1:11:22<9:00:24,  1.57it/s]
 12%|█▏        | 6783/57600 [1:11:22<8:59:54,  1.57it/s]
 12%|█▏        | 6784/57600 [1:11:23<8:39:52,  1.63it/s]
 12%|█▏        | 6785/57600 [1:11:24<8:25:42,  1.67it/s]
 12%|█▏        | 6786/57600 [1:11:24<8:14:00,  1.71it/s]
 12%|█▏        | 6787/57600 [1:11:25<8:10:04,  1.73it/s]
 12%|█▏        | 6788/57600 [1:11:25<8:24:44,  1.68it/s]
 12%|█▏        | 6789/57600 [1:11:26<8:32:18,  1.65it/s]
 12%|█▏        | 6790/57600 [1:11:27<8:43:12,  1.62it/s]
 12%|█▏        | 6791/57600 [1:11:27<8:37:08,  1.64it/s]
 12%|█▏        | 6792/57600 [1:11:28<8:24:36,  1.68it/s]
 12%|█▏        | 6793/57600 [1:11:28<8:46:29,  1.61it/s]
 12%|█▏        | 6794/57600 [1:11:29<8:41:18,  1.62it/s]
 12%|█▏        | 6795/57600 [1:11:30<8:29:05,  1.66it/s]
 12%|█▏        | 6796/57600 [1:11:30<8:40:42,  1.63it/s]
 12%|█▏        | 6797/57600 [1:11:31<8:33:50,  1.65it/s]
 12%|█▏        | 6798/57600 [1:11:32<8:55:56,  1.58it/s]
 12%|█▏        | 6799/57600 [1:11:32<8:38:44,  1.63it/s]
 12%|█▏        | 6800/57600 [1:11:33<8:41:38,  1.62it/s]
                                                        
{'loss': 1.4991, 'learning_rate': 8.965156794425087e-07, 'epoch': 75.06}

 12%|█▏        | 6800/57600 [1:11:33<8:41:38,  1.62it/s]
 12%|█▏        | 6801/57600 [1:11:33<8:34:13,  1.65it/s]
 12%|█▏        | 6802/57600 [1:11:34<8:27:19,  1.67it/s]
 12%|█▏        | 6803/57600 [1:11:34<8:35:18,  1.64it/s]
 12%|█▏        | 6804/57600 [1:11:35<8:37:48,  1.63it/s]
 12%|█▏        | 6805/57600 [1:11:36<9:00:55,  1.57it/s]
 12%|█▏        | 6806/57600 [1:11:36<9:09:28,  1.54it/s]
 12%|█▏        | 6807/57600 [1:11:37<9:09:57,  1.54it/s]
 12%|█▏        | 6808/57600 [1:11:38<8:57:08,  1.58it/s]
 12%|█▏        | 6809/57600 [1:11:38<8:45:56,  1.61it/s]
 12%|█▏        | 6810/57600 [1:11:39<8:42:38,  1.62it/s]
 12%|█▏        | 6811/57600 [1:11:40<8:57:51,  1.57it/s]
 12%|█▏        | 6812/57600 [1:11:40<9:13:25,  1.53it/s]
 12%|█▏        | 6813/57600 [1:11:41<8:53:57,  1.59it/s]
 12%|█▏        | 6814/57600 [1:11:42<8:59:58,  1.57it/s]
 12%|█▏        | 6815/57600 [1:11:42<9:12:00,  1.53it/s]
 12%|█▏        | 6816/57600 [1:11:43<9:16:52,  1.52it/s]
 12%|█▏        | 6817/57600 [1:11:43<8:55:11,  1.58it/s]
 12%|█▏        | 6818/57600 [1:11:44<9:09:36,  1.54it/s]
 12%|█▏        | 6819/57600 [1:11:45<9:10:43,  1.54it/s]
 12%|█▏        | 6820/57600 [1:11:45<8:59:41,  1.57it/s]
                                                        
{'loss': 1.4516, 'learning_rate': 8.962020905923344e-07, 'epoch': 75.28}

 12%|█▏        | 6820/57600 [1:11:45<8:59:41,  1.57it/s]
 12%|█▏        | 6821/57600 [1:11:46<9:02:35,  1.56it/s]
 12%|█▏        | 6822/57600 [1:11:47<8:53:22,  1.59it/s]
 12%|█▏        | 6823/57600 [1:11:47<8:47:07,  1.61it/s]
 12%|█▏        | 6824/57600 [1:11:48<8:36:20,  1.64it/s]
 12%|█▏        | 6825/57600 [1:11:48<8:30:18,  1.66it/s]
 12%|█▏        | 6826/57600 [1:11:49<8:41:25,  1.62it/s]
 12%|█▏        | 6827/57600 [1:11:50<8:37:00,  1.64it/s]
 12%|█▏        | 6828/57600 [1:11:50<8:54:11,  1.58it/s]
 12%|█▏        | 6829/57600 [1:11:51<8:50:03,  1.60it/s]
 12%|█▏        | 6830/57600 [1:11:52<9:03:15,  1.56it/s]
 12%|█▏        | 6831/57600 [1:11:52<8:41:59,  1.62it/s]
 12%|█▏        | 6832/57600 [1:11:53<8:54:58,  1.58it/s]
 12%|█▏        | 6833/57600 [1:11:54<9:09:51,  1.54it/s]
 12%|█▏        | 6834/57600 [1:11:54<8:59:33,  1.57it/s]
 12%|█▏        | 6835/57600 [1:11:55<8:45:46,  1.61it/s]
 12%|█▏        | 6836/57600 [1:11:55<8:31:11,  1.66it/s]
 12%|█▏        | 6837/57600 [1:11:56<8:27:03,  1.67it/s]
 12%|█▏        | 6838/57600 [1:11:57<8:26:49,  1.67it/s]
 12%|█▏        | 6839/57600 [1:11:57<8:42:38,  1.62it/s]
 12%|█▏        | 6840/57600 [1:11:58<8:24:50,  1.68it/s]
                                                        
{'loss': 1.5084, 'learning_rate': 8.958885017421603e-07, 'epoch': 75.5}

 12%|█▏        | 6840/57600 [1:11:58<8:24:50,  1.68it/s]
 12%|█▏        | 6841/57600 [1:11:58<8:45:36,  1.61it/s]
 12%|█▏        | 6842/57600 [1:11:59<8:31:08,  1.66it/s]
 12%|█▏        | 6843/57600 [1:12:00<8:35:55,  1.64it/s]
 12%|█▏        | 6844/57600 [1:12:00<9:06:15,  1.55it/s]
 12%|█▏        | 6845/57600 [1:12:01<9:01:17,  1.56it/s]
 12%|█▏        | 6846/57600 [1:12:02<8:54:46,  1.58it/s]
 12%|█▏        | 6847/57600 [1:12:02<9:16:07,  1.52it/s]
 12%|█▏        | 6848/57600 [1:12:03<8:45:44,  1.61it/s]
 12%|█▏        | 6849/57600 [1:12:03<8:40:58,  1.62it/s]
 12%|█▏        | 6850/57600 [1:12:04<8:53:34,  1.59it/s]
 12%|█▏        | 6851/57600 [1:12:05<8:47:24,  1.60it/s]
 12%|█▏        | 6852/57600 [1:12:05<9:06:26,  1.55it/s]
 12%|█▏        | 6853/57600 [1:12:06<9:07:02,  1.55it/s]
 12%|█▏        | 6854/57600 [1:12:07<8:42:15,  1.62it/s]
 12%|█▏        | 6855/57600 [1:12:07<8:39:37,  1.63it/s]
 12%|█▏        | 6856/57600 [1:12:08<8:25:33,  1.67it/s]
 12%|█▏        | 6857/57600 [1:12:08<8:36:04,  1.64it/s]
 12%|█▏        | 6858/57600 [1:12:09<8:24:11,  1.68it/s]
 12%|█▏        | 6859/57600 [1:12:10<8:27:31,  1.67it/s]
 12%|█▏        | 6860/57600 [1:12:10<8:22:28,  1.68it/s]
                                                        
{'loss': 1.4542, 'learning_rate': 8.95574912891986e-07, 'epoch': 75.72}

 12%|█▏        | 6860/57600 [1:12:10<8:22:28,  1.68it/s]
 12%|█▏        | 6861/57600 [1:12:11<8:44:46,  1.61it/s]
 12%|█▏        | 6862/57600 [1:12:12<9:08:42,  1.54it/s]
 12%|█▏        | 6863/57600 [1:12:12<8:50:56,  1.59it/s]
 12%|█▏        | 6864/57600 [1:12:13<8:47:20,  1.60it/s]
 12%|█▏        | 6865/57600 [1:12:13<8:42:58,  1.62it/s]
 12%|█▏        | 6866/57600 [1:12:14<8:40:21,  1.62it/s]
 12%|█▏        | 6867/57600 [1:12:15<8:33:42,  1.65it/s]
 12%|█▏        | 6868/57600 [1:12:15<8:39:13,  1.63it/s]
 12%|█▏        | 6869/57600 [1:12:16<8:18:34,  1.70it/s]
 12%|█▏        | 6870/57600 [1:12:16<8:24:45,  1.68it/s]
 12%|█▏        | 6871/57600 [1:12:17<8:37:03,  1.64it/s]
 12%|█▏        | 6872/57600 [1:12:18<8:29:31,  1.66it/s]
 12%|█▏        | 6873/57600 [1:12:18<8:33:49,  1.65it/s]
 12%|█▏        | 6874/57600 [1:12:19<8:41:43,  1.62it/s]
 12%|█▏        | 6875/57600 [1:12:19<8:38:41,  1.63it/s]
 12%|█▏        | 6876/57600 [1:12:20<8:28:30,  1.66it/s]
 12%|█▏        | 6877/57600 [1:12:21<8:30:17,  1.66it/s]
 12%|█▏        | 6878/57600 [1:12:21<9:02:54,  1.56it/s]
 12%|█▏        | 6879/57600 [1:12:22<8:54:15,  1.58it/s]
 12%|█▏        | 6880/57600 [1:12:23<8:38:15,  1.63it/s]
                                                        
{'loss': 1.475, 'learning_rate': 8.952613240418118e-07, 'epoch': 75.94}

 12%|█▏        | 6880/57600 [1:12:23<8:38:15,  1.63it/s]
 12%|█▏        | 6881/57600 [1:12:23<8:29:39,  1.66it/s]
 12%|█▏        | 6882/57600 [1:12:24<8:25:24,  1.67it/s]
 12%|█▏        | 6883/57600 [1:12:24<8:27:47,  1.66it/s]
 12%|█▏        | 6884/57600 [1:12:25<8:33:28,  1.65it/s]
 12%|█▏        | 6885/57600 [1:12:25<8:29:31,  1.66it/s]
 12%|█▏        | 6886/57600 [1:12:26<9:20:29,  1.51it/s]
 12%|█▏        | 6887/57600 [1:12:27<9:06:36,  1.55it/s]
 12%|█▏        | 6888/57600 [1:12:27<8:49:11,  1.60it/s]
 12%|█▏        | 6889/57600 [1:12:28<8:57:40,  1.57it/s]
 12%|█▏        | 6890/57600 [1:12:29<8:51:47,  1.59it/s]
 12%|█▏        | 6891/57600 [1:12:29<9:06:07,  1.55it/s]
 12%|█▏        | 6892/57600 [1:12:30<8:54:41,  1.58it/s]
 12%|█▏        | 6893/57600 [1:12:31<8:36:54,  1.63it/s]
 12%|█▏        | 6894/57600 [1:12:31<8:22:57,  1.68it/s]
 12%|█▏        | 6895/57600 [1:12:32<8:18:03,  1.70it/s]
 12%|█▏        | 6896/57600 [1:12:32<8:16:53,  1.70it/s]
 12%|█▏        | 6897/57600 [1:12:33<8:12:30,  1.72it/s]
 12%|█▏        | 6898/57600 [1:12:33<8:13:15,  1.71it/s]
 12%|█▏        | 6899/57600 [1:12:34<8:24:18,  1.68it/s]
 12%|█▏        | 6900/57600 [1:12:35<8:21:50,  1.68it/s]
                                                        
{'loss': 1.4287, 'learning_rate': 8.949477351916375e-07, 'epoch': 76.16}

 12%|█▏        | 6900/57600 [1:12:35<8:21:50,  1.68it/s]
 12%|█▏        | 6901/57600 [1:12:35<8:54:22,  1.58it/s]
 12%|█▏        | 6902/57600 [1:12:36<9:12:16,  1.53it/s]
 12%|█▏        | 6903/57600 [1:12:37<9:00:36,  1.56it/s]
 12%|█▏        | 6904/57600 [1:12:37<8:40:41,  1.62it/s]
 12%|█▏        | 6905/57600 [1:12:38<8:51:01,  1.59it/s]
 12%|█▏        | 6906/57600 [1:12:39<8:52:08,  1.59it/s]
 12%|█▏        | 6907/57600 [1:12:39<8:42:28,  1.62it/s]
 12%|█▏        | 6908/57600 [1:12:40<8:38:06,  1.63it/s]
 12%|█▏        | 6909/57600 [1:12:40<8:42:26,  1.62it/s]
 12%|█▏        | 6910/57600 [1:12:41<8:42:26,  1.62it/s]
 12%|█▏        | 6911/57600 [1:12:42<8:48:45,  1.60it/s]
 12%|█▏        | 6912/57600 [1:12:42<8:45:00,  1.61it/s]
 12%|█▏        | 6913/57600 [1:12:43<8:36:02,  1.64it/s]
 12%|█▏        | 6914/57600 [1:12:43<8:18:53,  1.69it/s]
 12%|█▏        | 6915/57600 [1:12:44<8:26:16,  1.67it/s]
 12%|█▏        | 6916/57600 [1:12:45<8:20:58,  1.69it/s]
 12%|█▏        | 6917/57600 [1:12:45<8:17:04,  1.70it/s]
 12%|█▏        | 6918/57600 [1:12:46<8:43:53,  1.61it/s]
 12%|█▏        | 6919/57600 [1:12:46<8:36:53,  1.63it/s]
 12%|█▏        | 6920/57600 [1:12:47<8:38:55,  1.63it/s]
                                                        
{'loss': 1.453, 'learning_rate': 8.946341463414634e-07, 'epoch': 76.38}

 12%|█▏        | 6920/57600 [1:12:47<8:38:55,  1.63it/s]
 12%|█▏        | 6921/57600 [1:12:48<8:51:10,  1.59it/s]
 12%|█▏        | 6922/57600 [1:12:48<8:32:44,  1.65it/s]
 12%|█▏        | 6923/57600 [1:12:49<8:29:29,  1.66it/s]
 12%|█▏        | 6924/57600 [1:12:50<8:49:57,  1.59it/s]
 12%|█▏        | 6925/57600 [1:12:50<8:38:25,  1.63it/s]
 12%|█▏        | 6926/57600 [1:12:51<8:45:02,  1.61it/s]
 12%|█▏        | 6927/57600 [1:12:51<8:44:15,  1.61it/s]
 12%|█▏        | 6928/57600 [1:12:52<8:30:51,  1.65it/s]
 12%|█▏        | 6929/57600 [1:12:53<8:45:15,  1.61it/s]
 12%|█▏        | 6930/57600 [1:12:53<8:37:52,  1.63it/s]
 12%|█▏        | 6931/57600 [1:12:54<8:58:07,  1.57it/s]
 12%|█▏        | 6932/57600 [1:12:55<8:44:55,  1.61it/s]
 12%|█▏        | 6933/57600 [1:12:55<8:36:27,  1.64it/s]
 12%|█▏        | 6934/57600 [1:12:56<8:37:41,  1.63it/s]
 12%|█▏        | 6935/57600 [1:12:56<8:50:51,  1.59it/s]
 12%|█▏        | 6936/57600 [1:12:57<8:47:29,  1.60it/s]
 12%|█▏        | 6937/57600 [1:12:58<8:40:32,  1.62it/s]
 12%|█▏        | 6938/57600 [1:12:58<8:37:52,  1.63it/s]
 12%|█▏        | 6939/57600 [1:12:59<9:00:29,  1.56it/s]
 12%|█▏        | 6940/57600 [1:13:00<9:02:26,  1.56it/s]
                                                        
{'loss': 1.4372, 'learning_rate': 8.943205574912893e-07, 'epoch': 76.6}

 12%|█▏        | 6940/57600 [1:13:00<9:02:26,  1.56it/s]
 12%|█▏        | 6941/57600 [1:13:00<8:53:16,  1.58it/s]
 12%|█▏        | 6942/57600 [1:13:01<9:00:07,  1.56it/s]
 12%|█▏        | 6943/57600 [1:13:01<8:58:19,  1.57it/s]
 12%|█▏        | 6944/57600 [1:13:02<8:57:09,  1.57it/s]
 12%|█▏        | 6945/57600 [1:13:03<8:49:26,  1.59it/s]
 12%|█▏        | 6946/57600 [1:13:03<9:06:05,  1.55it/s]
 12%|█▏        | 6947/57600 [1:13:04<9:01:51,  1.56it/s]
 12%|█▏        | 6948/57600 [1:13:05<8:58:37,  1.57it/s]
 12%|█▏        | 6949/57600 [1:13:05<9:06:53,  1.54it/s]
 12%|█▏        | 6950/57600 [1:13:06<8:58:29,  1.57it/s]
 12%|█▏        | 6951/57600 [1:13:07<8:52:21,  1.59it/s]
 12%|█▏        | 6952/57600 [1:13:07<8:50:23,  1.59it/s]
 12%|█▏        | 6953/57600 [1:13:08<9:01:21,  1.56it/s]
 12%|█▏        | 6954/57600 [1:13:08<8:55:13,  1.58it/s]
 12%|█▏        | 6955/57600 [1:13:09<8:50:01,  1.59it/s]
 12%|█▏        | 6956/57600 [1:13:10<8:38:34,  1.63it/s]
 12%|█▏        | 6957/57600 [1:13:10<8:36:13,  1.64it/s]
 12%|█▏        | 6958/57600 [1:13:11<8:32:15,  1.65it/s]
 12%|█▏        | 6959/57600 [1:13:11<8:24:24,  1.67it/s]
 12%|█▏        | 6960/57600 [1:13:12<8:30:46,  1.65it/s]
                                                        
{'loss': 1.4665, 'learning_rate': 8.940069686411149e-07, 'epoch': 76.82}

 12%|█▏        | 6960/57600 [1:13:12<8:30:46,  1.65it/s]
 12%|█▏        | 6961/57600 [1:13:13<8:40:03,  1.62it/s]
 12%|█▏        | 6962/57600 [1:13:13<8:42:09,  1.62it/s]
 12%|█▏        | 6963/57600 [1:13:14<8:40:46,  1.62it/s]
 12%|█▏        | 6964/57600 [1:13:15<8:40:55,  1.62it/s]
 12%|█▏        | 6965/57600 [1:13:15<8:21:38,  1.68it/s]
 12%|█▏        | 6966/57600 [1:13:16<8:25:28,  1.67it/s]
 12%|█▏        | 6967/57600 [1:13:16<8:37:33,  1.63it/s]
 12%|█▏        | 6968/57600 [1:13:17<8:37:48,  1.63it/s]
 12%|█▏        | 6969/57600 [1:13:18<8:31:00,  1.65it/s]
 12%|█▏        | 6970/57600 [1:13:18<8:49:09,  1.59it/s]
 12%|█▏        | 6971/57600 [1:13:19<8:45:08,  1.61it/s]
 12%|█▏        | 6972/57600 [1:13:20<8:54:46,  1.58it/s]
 12%|█▏        | 6973/57600 [1:13:20<8:49:51,  1.59it/s]
 12%|█▏        | 6974/57600 [1:13:21<8:36:36,  1.63it/s]
 12%|█▏        | 6975/57600 [1:13:21<8:25:40,  1.67it/s]
 12%|█▏        | 6976/57600 [1:13:22<8:36:28,  1.63it/s]
 12%|█▏        | 6977/57600 [1:13:23<8:47:27,  1.60it/s]
 12%|█▏        | 6978/57600 [1:13:23<8:44:29,  1.61it/s]
 12%|█▏        | 6979/57600 [1:13:24<8:37:16,  1.63it/s]
 12%|█▏        | 6980/57600 [1:13:24<8:31:59,  1.65it/s]
                                                        
{'loss': 1.4841, 'learning_rate': 8.936933797909408e-07, 'epoch': 77.04}

 12%|█▏        | 6980/57600 [1:13:24<8:31:59,  1.65it/s]
 12%|█▏        | 6981/57600 [1:13:25<8:30:11,  1.65it/s]
 12%|█▏        | 6982/57600 [1:13:26<8:28:07,  1.66it/s]
 12%|█▏        | 6983/57600 [1:13:26<8:40:21,  1.62it/s]
 12%|█▏        | 6984/57600 [1:13:27<8:42:14,  1.62it/s]
 12%|█▏        | 6985/57600 [1:13:27<8:49:12,  1.59it/s]
 12%|█▏        | 6986/57600 [1:13:28<8:49:08,  1.59it/s]
 12%|█▏        | 6987/57600 [1:13:29<8:36:48,  1.63it/s]
 12%|█▏        | 6988/57600 [1:13:29<8:30:12,  1.65it/s]
 12%|█▏        | 6989/57600 [1:13:30<8:36:25,  1.63it/s]
 12%|█▏        | 6990/57600 [1:13:31<8:38:38,  1.63it/s]
 12%|█▏        | 6991/57600 [1:13:31<8:41:03,  1.62it/s]
 12%|█▏        | 6992/57600 [1:13:32<8:35:55,  1.63it/s]
 12%|█▏        | 6993/57600 [1:13:32<8:38:14,  1.63it/s]
 12%|█▏        | 6994/57600 [1:13:33<8:42:18,  1.61it/s]
 12%|█▏        | 6995/57600 [1:13:34<8:31:38,  1.65it/s]
 12%|█▏        | 6996/57600 [1:13:34<8:31:22,  1.65it/s]
 12%|█▏        | 6997/57600 [1:13:35<8:23:44,  1.67it/s]
 12%|█▏        | 6998/57600 [1:13:35<8:34:57,  1.64it/s]
 12%|█▏        | 6999/57600 [1:13:36<8:42:04,  1.62it/s]
 12%|█▏        | 7000/57600 [1:13:37<8:28:51,  1.66it/s]
                                                        
{'loss': 1.4491, 'learning_rate': 8.933797909407665e-07, 'epoch': 77.26}

 12%|█▏        | 7000/57600 [1:13:37<8:28:51,  1.66it/s]
 12%|█▏        | 7001/57600 [1:13:37<8:44:31,  1.61it/s]
 12%|█▏        | 7002/57600 [1:13:38<9:20:10,  1.51it/s]
 12%|█▏        | 7003/57600 [1:13:39<9:10:34,  1.53it/s]
 12%|█▏        | 7004/57600 [1:13:39<9:10:19,  1.53it/s]
 12%|█▏        | 7005/57600 [1:13:40<9:19:34,  1.51it/s]
 12%|█▏        | 7006/57600 [1:13:41<9:07:30,  1.54it/s]
 12%|█▏        | 7007/57600 [1:13:41<9:06:38,  1.54it/s]
 12%|█▏        | 7008/57600 [1:13:42<8:55:10,  1.58it/s]
 12%|█▏        | 7009/57600 [1:13:42<8:46:38,  1.60it/s]
 12%|█▏        | 7010/57600 [1:13:43<8:48:47,  1.59it/s]
 12%|█▏        | 7011/57600 [1:13:44<8:53:41,  1.58it/s]
 12%|█▏        | 7012/57600 [1:13:44<8:52:21,  1.58it/s]
 12%|█▏        | 7013/57600 [1:13:45<8:58:47,  1.56it/s]
 12%|█▏        | 7014/57600 [1:13:46<9:08:16,  1.54it/s]
 12%|█▏        | 7015/57600 [1:13:46<9:26:03,  1.49it/s]
 12%|█▏        | 7016/57600 [1:13:47<9:12:20,  1.53it/s]
 12%|█▏        | 7017/57600 [1:13:48<8:58:58,  1.56it/s]
 12%|█▏        | 7018/57600 [1:13:48<8:37:25,  1.63it/s]
 12%|█▏        | 7019/57600 [1:13:49<8:43:14,  1.61it/s]
 12%|█▏        | 7020/57600 [1:13:49<8:42:25,  1.61it/s]
                                                        
{'loss': 1.4382, 'learning_rate': 8.930662020905923e-07, 'epoch': 77.48}

 12%|█▏        | 7020/57600 [1:13:49<8:42:25,  1.61it/s]
 12%|█▏        | 7021/57600 [1:13:50<9:14:34,  1.52it/s]
 12%|█▏        | 7022/57600 [1:13:51<8:57:54,  1.57it/s]
 12%|█▏        | 7023/57600 [1:13:51<8:48:05,  1.60it/s]
 12%|█▏        | 7024/57600 [1:13:52<8:59:22,  1.56it/s]
 12%|█▏        | 7025/57600 [1:13:53<8:42:55,  1.61it/s]
 12%|█▏        | 7026/57600 [1:13:53<8:34:21,  1.64it/s]
 12%|█▏        | 7027/57600 [1:13:54<8:25:53,  1.67it/s]
 12%|█▏        | 7028/57600 [1:13:54<8:11:38,  1.71it/s]
 12%|█▏        | 7029/57600 [1:13:55<8:35:42,  1.63it/s]
 12%|█▏        | 7030/57600 [1:13:56<8:38:29,  1.63it/s]
 12%|█▏        | 7031/57600 [1:13:56<8:29:19,  1.65it/s]
 12%|█▏        | 7032/57600 [1:13:57<8:20:14,  1.68it/s]
 12%|█▏        | 7033/57600 [1:13:57<8:10:10,  1.72it/s]
 12%|█▏        | 7034/57600 [1:13:58<8:16:27,  1.70it/s]
 12%|█▏        | 7035/57600 [1:13:59<8:23:54,  1.67it/s]
 12%|█▏        | 7036/57600 [1:13:59<8:36:01,  1.63it/s]
 12%|█▏        | 7037/57600 [1:14:00<8:32:13,  1.65it/s]
 12%|█▏        | 7038/57600 [1:14:00<8:27:55,  1.66it/s]
 12%|█▏        | 7039/57600 [1:14:01<8:29:18,  1.65it/s]
 12%|█▏        | 7040/57600 [1:14:02<8:38:21,  1.63it/s]
                                                        
{'loss': 1.4206, 'learning_rate': 8.92752613240418e-07, 'epoch': 77.7}

 12%|█▏        | 7040/57600 [1:14:02<8:38:21,  1.63it/s]
 12%|█▏        | 7041/57600 [1:14:02<8:49:08,  1.59it/s]
 12%|█▏        | 7042/57600 [1:14:03<8:50:32,  1.59it/s]
 12%|█▏        | 7043/57600 [1:14:04<8:39:08,  1.62it/s]
 12%|█▏        | 7044/57600 [1:14:04<8:30:15,  1.65it/s]
 12%|█▏        | 7045/57600 [1:14:05<8:31:09,  1.65it/s]
 12%|█▏        | 7046/57600 [1:14:05<8:32:56,  1.64it/s]
 12%|█▏        | 7047/57600 [1:14:06<8:58:15,  1.57it/s]
 12%|█▏        | 7048/57600 [1:14:07<8:44:15,  1.61it/s]
 12%|█▏        | 7049/57600 [1:14:07<8:43:50,  1.61it/s]
 12%|█▏        | 7050/57600 [1:14:08<8:37:58,  1.63it/s]
 12%|█▏        | 7051/57600 [1:14:08<8:27:31,  1.66it/s]
 12%|█▏        | 7052/57600 [1:14:09<8:46:08,  1.60it/s]
 12%|█▏        | 7053/57600 [1:14:10<8:57:34,  1.57it/s]
 12%|█▏        | 7054/57600 [1:14:10<8:46:27,  1.60it/s]
 12%|█▏        | 7055/57600 [1:14:11<8:43:02,  1.61it/s]
 12%|█▏        | 7056/57600 [1:14:12<8:37:20,  1.63it/s]
 12%|█▏        | 7057/57600 [1:14:12<8:38:39,  1.62it/s]
 12%|█▏        | 7058/57600 [1:14:13<8:33:45,  1.64it/s]
 12%|█▏        | 7059/57600 [1:14:13<8:29:18,  1.65it/s]
 12%|█▏        | 7060/57600 [1:14:14<8:21:26,  1.68it/s]
                                                        
{'loss': 1.4521, 'learning_rate': 8.924390243902439e-07, 'epoch': 77.92}

 12%|█▏        | 7060/57600 [1:14:14<8:21:26,  1.68it/s]
 12%|█▏        | 7061/57600 [1:14:15<8:15:20,  1.70it/s]
 12%|█▏        | 7062/57600 [1:14:15<8:21:04,  1.68it/s]
 12%|█▏        | 7063/57600 [1:14:16<8:50:04,  1.59it/s]
 12%|█▏        | 7064/57600 [1:14:16<8:48:38,  1.59it/s]
 12%|█▏        | 7065/57600 [1:14:17<9:05:59,  1.54it/s]
 12%|█▏        | 7066/57600 [1:14:18<8:56:55,  1.57it/s]
 12%|█▏        | 7067/57600 [1:14:18<9:12:23,  1.52it/s]
 12%|█▏        | 7068/57600 [1:14:19<8:47:28,  1.60it/s]
 12%|█▏        | 7069/57600 [1:14:20<8:45:13,  1.60it/s]
 12%|█▏        | 7070/57600 [1:14:20<8:43:38,  1.61it/s]
 12%|█▏        | 7071/57600 [1:14:21<8:51:42,  1.58it/s]
 12%|█▏        | 7072/57600 [1:14:21<8:35:25,  1.63it/s]
 12%|█▏        | 7073/57600 [1:14:22<8:21:20,  1.68it/s]
 12%|█▏        | 7074/57600 [1:14:23<8:14:44,  1.70it/s]
 12%|█▏        | 7075/57600 [1:14:23<8:10:22,  1.72it/s]
 12%|█▏        | 7076/57600 [1:14:24<8:10:18,  1.72it/s]
 12%|█▏        | 7077/57600 [1:14:24<8:17:46,  1.69it/s]
 12%|█▏        | 7078/57600 [1:14:25<8:25:58,  1.66it/s]
 12%|█▏        | 7079/57600 [1:14:26<8:25:58,  1.66it/s]
 12%|█▏        | 7080/57600 [1:14:26<8:48:11,  1.59it/s]
                                                        
{'loss': 1.4688, 'learning_rate': 8.921254355400697e-07, 'epoch': 78.15}

 12%|█▏        | 7080/57600 [1:14:26<8:48:11,  1.59it/s]
 12%|█▏        | 7081/57600 [1:14:27<8:33:08,  1.64it/s]
 12%|█▏        | 7082/57600 [1:14:27<8:34:37,  1.64it/s]
 12%|█▏        | 7083/57600 [1:14:28<8:28:55,  1.65it/s]
 12%|█▏        | 7084/57600 [1:14:29<8:28:26,  1.66it/s]
 12%|█▏        | 7085/57600 [1:14:29<8:41:52,  1.61it/s]
 12%|█▏        | 7086/57600 [1:14:30<8:37:22,  1.63it/s]
 12%|█▏        | 7087/57600 [1:14:31<8:29:07,  1.65it/s]
 12%|█▏        | 7088/57600 [1:14:31<8:19:59,  1.68it/s]
 12%|█▏        | 7089/57600 [1:14:32<8:28:39,  1.66it/s]
 12%|█▏        | 7090/57600 [1:14:32<8:47:20,  1.60it/s]
 12%|█▏        | 7091/57600 [1:14:33<8:48:45,  1.59it/s]
 12%|█▏        | 7092/57600 [1:14:34<8:41:31,  1.61it/s]
 12%|█▏        | 7093/57600 [1:14:34<8:52:03,  1.58it/s]
 12%|█▏        | 7094/57600 [1:14:35<9:00:02,  1.56it/s]
 12%|█▏        | 7095/57600 [1:14:36<8:47:01,  1.60it/s]
 12%|█▏        | 7096/57600 [1:14:36<8:54:09,  1.58it/s]
 12%|█▏        | 7097/57600 [1:14:37<9:10:29,  1.53it/s]
 12%|█▏        | 7098/57600 [1:14:38<9:01:41,  1.55it/s]
 12%|█▏        | 7099/57600 [1:14:38<8:36:11,  1.63it/s]
 12%|█▏        | 7100/57600 [1:14:39<8:27:12,  1.66it/s]
                                                        
{'loss': 1.4304, 'learning_rate': 8.918118466898954e-07, 'epoch': 78.37}

 12%|█▏        | 7100/57600 [1:14:39<8:27:12,  1.66it/s]
 12%|█▏        | 7101/57600 [1:14:39<8:27:37,  1.66it/s]
 12%|█▏        | 7102/57600 [1:14:40<8:36:21,  1.63it/s]
 12%|█▏        | 7103/57600 [1:14:40<8:42:16,  1.61it/s]
 12%|█▏        | 7104/57600 [1:14:41<8:48:23,  1.59it/s]
 12%|█▏        | 7105/57600 [1:14:42<8:27:31,  1.66it/s]
 12%|█▏        | 7106/57600 [1:14:42<9:00:14,  1.56it/s]
 12%|█▏        | 7107/57600 [1:14:43<8:41:12,  1.61it/s]
 12%|█▏        | 7108/57600 [1:14:44<9:07:13,  1.54it/s]
 12%|█▏        | 7109/57600 [1:14:44<8:54:53,  1.57it/s]
 12%|█▏        | 7110/57600 [1:14:45<8:46:56,  1.60it/s]
 12%|█▏        | 7111/57600 [1:14:46<8:38:12,  1.62it/s]
 12%|█▏        | 7112/57600 [1:14:46<8:49:18,  1.59it/s]
 12%|█▏        | 7113/57600 [1:14:47<9:02:51,  1.55it/s]
 12%|█▏        | 7114/57600 [1:14:48<9:10:49,  1.53it/s]
 12%|█▏        | 7115/57600 [1:14:48<9:18:04,  1.51it/s]
 12%|█▏        | 7116/57600 [1:14:49<8:57:32,  1.57it/s]
 12%|█▏        | 7117/57600 [1:14:49<8:43:23,  1.61it/s]
 12%|█▏        | 7118/57600 [1:14:50<8:44:02,  1.61it/s]
 12%|█▏        | 7119/57600 [1:14:51<8:43:35,  1.61it/s]
 12%|█▏        | 7120/57600 [1:14:51<8:41:39,  1.61it/s]
                                                        
{'loss': 1.4165, 'learning_rate': 8.914982578397212e-07, 'epoch': 78.59}

 12%|█▏        | 7120/57600 [1:14:51<8:41:39,  1.61it/s]
 12%|█▏        | 7121/57600 [1:14:52<8:35:12,  1.63it/s]
 12%|█▏        | 7122/57600 [1:14:52<8:37:22,  1.63it/s]
 12%|█▏        | 7123/57600 [1:14:53<8:46:32,  1.60it/s]
 12%|█▏        | 7124/57600 [1:14:54<8:30:47,  1.65it/s]
 12%|█▏        | 7125/57600 [1:14:54<8:19:00,  1.69it/s]
 12%|█▏        | 7126/57600 [1:14:55<8:29:02,  1.65it/s]
 12%|█▏        | 7127/57600 [1:14:56<8:38:58,  1.62it/s]
 12%|█▏        | 7128/57600 [1:14:56<8:44:01,  1.61it/s]
 12%|█▏        | 7129/57600 [1:14:57<8:41:54,  1.61it/s]
 12%|█▏        | 7130/57600 [1:14:57<8:20:48,  1.68it/s]
 12%|█▏        | 7131/57600 [1:14:58<8:22:48,  1.67it/s]
 12%|█▏        | 7132/57600 [1:14:59<8:30:49,  1.65it/s]
 12%|█▏        | 7133/57600 [1:14:59<8:31:54,  1.64it/s]
 12%|█▏        | 7134/57600 [1:15:00<8:38:57,  1.62it/s]
 12%|█▏        | 7135/57600 [1:15:00<8:49:24,  1.59it/s]
 12%|█▏        | 7136/57600 [1:15:01<8:50:49,  1.58it/s]
 12%|█▏        | 7137/57600 [1:15:02<8:57:50,  1.56it/s]
 12%|█▏        | 7138/57600 [1:15:02<8:39:22,  1.62it/s]
 12%|█▏        | 7139/57600 [1:15:03<8:39:36,  1.62it/s]
 12%|█▏        | 7140/57600 [1:15:04<8:47:55,  1.59it/s]
                                                        
{'loss': 1.4728, 'learning_rate': 8.91184668989547e-07, 'epoch': 78.81}

 12%|█▏        | 7140/57600 [1:15:04<8:47:55,  1.59it/s]
 12%|█▏        | 7141/57600 [1:15:04<9:04:12,  1.55it/s]
 12%|█▏        | 7142/57600 [1:15:05<8:55:45,  1.57it/s]
 12%|█▏        | 7143/57600 [1:15:05<8:37:43,  1.62it/s]
 12%|█▏        | 7144/57600 [1:15:06<8:36:28,  1.63it/s]
 12%|█▏        | 7145/57600 [1:15:07<8:32:17,  1.64it/s]
 12%|█▏        | 7146/57600 [1:15:07<8:16:12,  1.69it/s]
 12%|█▏        | 7147/57600 [1:15:08<8:17:43,  1.69it/s]
 12%|█▏        | 7148/57600 [1:15:08<8:25:18,  1.66it/s]
 12%|█▏        | 7149/57600 [1:15:09<8:24:55,  1.67it/s]
 12%|█▏        | 7150/57600 [1:15:10<8:27:24,  1.66it/s]
 12%|█▏        | 7151/57600 [1:15:10<8:37:57,  1.62it/s]
 12%|█▏        | 7152/57600 [1:15:11<8:35:39,  1.63it/s]
 12%|█▏        | 7153/57600 [1:15:11<8:34:24,  1.63it/s]
 12%|█▏        | 7154/57600 [1:15:12<8:26:49,  1.66it/s]
 12%|█▏        | 7155/57600 [1:15:13<8:41:14,  1.61it/s]
 12%|█▏        | 7156/57600 [1:15:13<8:49:37,  1.59it/s]
 12%|█▏        | 7157/57600 [1:15:14<8:43:33,  1.61it/s]
 12%|█▏        | 7158/57600 [1:15:15<8:51:29,  1.58it/s]
 12%|█▏        | 7159/57600 [1:15:15<8:40:02,  1.62it/s]
 12%|█▏        | 7160/57600 [1:15:16<8:38:29,  1.62it/s]
                                                        
{'loss': 1.4959, 'learning_rate': 8.908710801393728e-07, 'epoch': 79.03}

 12%|█▏        | 7160/57600 [1:15:16<8:38:29,  1.62it/s]
 12%|█▏        | 7161/57600 [1:15:16<8:31:52,  1.64it/s]
 12%|█▏        | 7162/57600 [1:15:17<8:19:17,  1.68it/s]
 12%|█▏        | 7163/57600 [1:15:18<8:32:36,  1.64it/s]
 12%|█▏        | 7164/57600 [1:15:18<8:34:52,  1.63it/s]
 12%|█▏        | 7165/57600 [1:15:19<8:37:47,  1.62it/s]
 12%|█▏        | 7166/57600 [1:15:19<8:34:56,  1.63it/s]
 12%|█▏        | 7167/57600 [1:15:20<8:32:06,  1.64it/s]
 12%|█▏        | 7168/57600 [1:15:21<8:44:41,  1.60it/s]
 12%|█▏        | 7169/57600 [1:15:21<8:46:21,  1.60it/s]
 12%|█▏        | 7170/57600 [1:15:22<8:27:17,  1.66it/s]
 12%|█▏        | 7171/57600 [1:15:23<8:30:13,  1.65it/s]
 12%|█▏        | 7172/57600 [1:15:23<8:42:43,  1.61it/s]
 12%|█▏        | 7173/57600 [1:15:24<8:55:58,  1.57it/s]
 12%|█▏        | 7174/57600 [1:15:24<8:44:14,  1.60it/s]
 12%|█▏        | 7175/57600 [1:15:25<8:50:31,  1.58it/s]
 12%|█▏        | 7176/57600 [1:15:26<8:42:15,  1.61it/s]
 12%|█▏        | 7177/57600 [1:15:26<8:42:32,  1.61it/s]
 12%|█▏        | 7178/57600 [1:15:27<8:23:47,  1.67it/s]
 12%|█▏        | 7179/57600 [1:15:28<8:41:48,  1.61it/s]
 12%|█▏        | 7180/57600 [1:15:28<8:43:55,  1.60it/s]
                                                        
{'loss': 1.4211, 'learning_rate': 8.905574912891986e-07, 'epoch': 79.25}

 12%|█▏        | 7180/57600 [1:15:28<8:43:55,  1.60it/s]
 12%|█▏        | 7181/57600 [1:15:29<9:03:16,  1.55it/s]
 12%|█▏        | 7182/57600 [1:15:29<8:53:02,  1.58it/s]
 12%|█▏        | 7183/57600 [1:15:30<8:45:06,  1.60it/s]
 12%|█▏        | 7184/57600 [1:15:31<8:47:14,  1.59it/s]
 12%|█▏        | 7185/57600 [1:15:31<8:46:14,  1.60it/s]
 12%|█▏        | 7186/57600 [1:15:32<8:50:47,  1.58it/s]
 12%|█▏        | 7187/57600 [1:15:33<8:51:46,  1.58it/s]
 12%|█▏        | 7188/57600 [1:15:33<8:41:36,  1.61it/s]
 12%|█▏        | 7189/57600 [1:15:34<8:34:48,  1.63it/s]
 12%|█▏        | 7190/57600 [1:15:34<8:42:52,  1.61it/s]
 12%|█▏        | 7191/57600 [1:15:35<8:33:11,  1.64it/s]
 12%|█▏        | 7192/57600 [1:15:36<8:30:27,  1.65it/s]
 12%|█▏        | 7193/57600 [1:15:36<8:42:21,  1.61it/s]
 12%|█▏        | 7194/57600 [1:15:37<8:48:11,  1.59it/s]
 12%|█▏        | 7195/57600 [1:15:38<8:57:04,  1.56it/s]
 12%|█▏        | 7196/57600 [1:15:38<8:46:16,  1.60it/s]
 12%|█▏        | 7197/57600 [1:15:39<8:35:39,  1.63it/s]
 12%|█▏        | 7198/57600 [1:15:39<8:27:21,  1.66it/s]
 12%|█▏        | 7199/57600 [1:15:40<8:34:41,  1.63it/s]
 12%|█▎        | 7200/57600 [1:15:41<8:43:23,  1.60it/s]
                                                        
{'loss': 1.4794, 'learning_rate': 8.902439024390244e-07, 'epoch': 79.47}

 12%|█▎        | 7200/57600 [1:15:41<8:43:23,  1.60it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00,  9.61it/s]

 50%|█████     | 3/6 [00:00<00:00,  6.73it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  5.76it/s]

 83%|████████▎ | 5/6 [00:01<00:00,  3.52it/s]

100%|██████████| 6/6 [00:01<00:00,  2.73it/s]{'score': 44.412454378232546, 'counts': [148, 97, 66, 47], 'totals': [232, 202, 172, 142], 'precisions': [63.793103448275865, 48.01980198019802, 38.372093023255815, 33.098591549295776], 'bp': 1.0, 'sys_len': 232, 'ref_len': 207}

                                                        

                                             
{'eval_loss': 2.0255990028381348, 'eval_bleu': 44.4125, 'eval_gen_len': 9.0667, 'eval_runtime': 3.4282, 'eval_samples_per_second': 8.751, 'eval_steps_per_second': 1.75, 'epoch': 79.47}

 12%|█▎        | 7200/57600 [1:15:44<8:43:23,  1.60it/s]

100%|██████████| 6/6 [00:03<00:00,  2.73it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 08:09:57,415 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 13%|█▎        | 7201/57600 [1:16:12<135:47:37,  9.70s/it]
 13%|█▎        | 7202/57600 [1:16:12<97:57:35,  7.00s/it] 
 13%|█▎        | 7203/57600 [1:16:13<71:19:43,  5.10s/it]
 13%|█▎        | 7204/57600 [1:16:14<52:36:02,  3.76s/it]
 13%|█▎        | 7205/57600 [1:16:14<39:30:25,  2.82s/it]
 13%|█▎        | 7206/57600 [1:16:15<30:11:39,  2.16s/it]
 13%|█▎        | 7207/57600 [1:16:15<23:51:23,  1.70s/it]
 13%|█▎        | 7208/57600 [1:16:16<19:40:59,  1.41s/it]
 13%|█▎        | 7209/57600 [1:16:17<16:27:56,  1.18s/it]
 13%|█▎        | 7210/57600 [1:16:17<14:32:29,  1.04s/it]
 13%|█▎        | 7211/57600 [1:16:18<12:49:26,  1.09it/s]
 13%|█▎        | 7212/57600 [1:16:19<11:56:05,  1.17it/s]
 13%|█▎        | 7213/57600 [1:16:19<11:01:46,  1.27it/s]
 13%|█▎        | 7214/57600 [1:16:20<10:12:07,  1.37it/s]
 13%|█▎        | 7215/57600 [1:16:21<10:01:56,  1.40it/s]
 13%|█▎        | 7216/57600 [1:16:21<9:47:59,  1.43it/s] 
 13%|█▎        | 7217/57600 [1:16:22<9:46:18,  1.43it/s]
 13%|█▎        | 7218/57600 [1:16:23<9:25:22,  1.49it/s]
 13%|█▎        | 7219/57600 [1:16:23<9:11:01,  1.52it/s]
 13%|█▎        | 7220/57600 [1:16:24<9:02:56,  1.55it/s]
                                                        
{'loss': 1.4294, 'learning_rate': 8.899303135888502e-07, 'epoch': 79.69}

 13%|█▎        | 7220/57600 [1:16:24<9:02:56,  1.55it/s]
 13%|█▎        | 7221/57600 [1:16:25<8:52:33,  1.58it/s]
 13%|█▎        | 7222/57600 [1:16:25<9:14:48,  1.51it/s]
 13%|█▎        | 7223/57600 [1:16:26<9:33:01,  1.47it/s]
 13%|█▎        | 7224/57600 [1:16:27<9:24:56,  1.49it/s]
 13%|█▎        | 7225/57600 [1:16:27<9:20:28,  1.50it/s]
 13%|█▎        | 7226/57600 [1:16:28<9:24:01,  1.49it/s]
 13%|█▎        | 7227/57600 [1:16:29<9:05:00,  1.54it/s]
 13%|█▎        | 7228/57600 [1:16:29<8:54:20,  1.57it/s]
 13%|█▎        | 7229/57600 [1:16:30<8:37:15,  1.62it/s]
 13%|█▎        | 7230/57600 [1:16:30<8:36:40,  1.62it/s]
 13%|█▎        | 7231/57600 [1:16:31<8:41:44,  1.61it/s]
 13%|█▎        | 7232/57600 [1:16:32<8:44:50,  1.60it/s]
 13%|█▎        | 7233/57600 [1:16:32<8:43:48,  1.60it/s]
 13%|█▎        | 7234/57600 [1:16:33<9:01:46,  1.55it/s]
 13%|█▎        | 7235/57600 [1:16:34<9:01:19,  1.55it/s]
 13%|█▎        | 7236/57600 [1:16:34<9:12:49,  1.52it/s]
 13%|█▎        | 7237/57600 [1:16:35<9:06:05,  1.54it/s]
 13%|█▎        | 7238/57600 [1:16:36<9:19:57,  1.50it/s]
 13%|█▎        | 7239/57600 [1:16:36<9:14:53,  1.51it/s]
 13%|█▎        | 7240/57600 [1:16:37<9:07:08,  1.53it/s]
                                                        
{'loss': 1.4691, 'learning_rate': 8.896167247386759e-07, 'epoch': 79.91}

 13%|█▎        | 7240/57600 [1:16:37<9:07:08,  1.53it/s]
 13%|█▎        | 7241/57600 [1:16:38<9:07:00,  1.53it/s]
 13%|█▎        | 7242/57600 [1:16:38<9:12:29,  1.52it/s]
 13%|█▎        | 7243/57600 [1:16:39<9:06:48,  1.53it/s]
 13%|█▎        | 7244/57600 [1:16:40<9:06:26,  1.54it/s]
 13%|█▎        | 7245/57600 [1:16:40<9:11:01,  1.52it/s]
 13%|█▎        | 7246/57600 [1:16:41<9:01:54,  1.55it/s]
 13%|█▎        | 7247/57600 [1:16:41<9:00:13,  1.55it/s]
 13%|█▎        | 7248/57600 [1:16:42<8:56:01,  1.57it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 13%|█▎        | 7249/57600 [1:16:43<9:24:10,  1.49it/s]
 13%|█▎        | 7250/57600 [1:16:43<9:11:51,  1.52it/s]
 13%|█▎        | 7251/57600 [1:16:44<9:17:59,  1.50it/s]
 13%|█▎        | 7252/57600 [1:16:45<9:05:09,  1.54it/s]
 13%|█▎        | 7253/57600 [1:16:45<9:07:11,  1.53it/s]
 13%|█▎        | 7254/57600 [1:16:46<8:56:35,  1.56it/s]
 13%|█▎        | 7255/57600 [1:16:47<8:49:17,  1.59it/s]
 13%|█▎        | 7256/57600 [1:16:47<9:26:51,  1.48it/s]
 13%|█▎        | 7257/57600 [1:16:48<9:16:37,  1.51it/s]
 13%|█▎        | 7258/57600 [1:16:49<8:59:47,  1.55it/s]
 13%|█▎        | 7259/57600 [1:16:49<9:08:39,  1.53it/s]
 13%|█▎        | 7260/57600 [1:16:50<8:56:11,  1.56it/s]
                                                        
{'loss': 1.4619, 'learning_rate': 8.893031358885017e-07, 'epoch': 80.13}

 13%|█▎        | 7260/57600 [1:16:50<8:56:11,  1.56it/s]
 13%|█▎        | 7261/57600 [1:16:50<8:41:06,  1.61it/s]
 13%|█▎        | 7262/57600 [1:16:51<8:35:51,  1.63it/s]
 13%|█▎        | 7263/57600 [1:16:52<8:49:37,  1.58it/s]
 13%|█▎        | 7264/57600 [1:16:52<8:44:13,  1.60it/s]
 13%|█▎        | 7265/57600 [1:16:53<8:35:09,  1.63it/s]
 13%|█▎        | 7266/57600 [1:16:54<8:36:06,  1.63it/s]
 13%|█▎        | 7267/57600 [1:16:54<8:47:29,  1.59it/s]
 13%|█▎        | 7268/57600 [1:16:55<8:38:06,  1.62it/s]
 13%|█▎        | 7269/57600 [1:16:55<8:40:19,  1.61it/s]
 13%|█▎        | 7270/57600 [1:16:56<8:37:12,  1.62it/s]
 13%|█▎        | 7271/57600 [1:16:57<8:39:35,  1.61it/s]
 13%|█▎        | 7272/57600 [1:16:57<8:31:43,  1.64it/s]
 13%|█▎        | 7273/57600 [1:16:58<8:21:15,  1.67it/s]
 13%|█▎        | 7274/57600 [1:16:58<8:11:41,  1.71it/s]
 13%|█▎        | 7275/57600 [1:16:59<8:23:52,  1.66it/s]
 13%|█▎        | 7276/57600 [1:17:00<8:21:13,  1.67it/s]
 13%|█▎        | 7277/57600 [1:17:00<8:35:52,  1.63it/s]
 13%|█▎        | 7278/57600 [1:17:01<8:42:24,  1.61it/s]
 13%|█▎        | 7279/57600 [1:17:02<8:53:42,  1.57it/s]
 13%|█▎        | 7280/57600 [1:17:02<8:48:55,  1.59it/s]
                                                        
{'loss': 1.4952, 'learning_rate': 8.889895470383275e-07, 'epoch': 80.35}

 13%|█▎        | 7280/57600 [1:17:02<8:48:55,  1.59it/s]
 13%|█▎        | 7281/57600 [1:17:03<8:40:33,  1.61it/s]
 13%|█▎        | 7282/57600 [1:17:03<8:43:07,  1.60it/s]
 13%|█▎        | 7283/57600 [1:17:04<8:54:04,  1.57it/s]
 13%|█▎        | 7284/57600 [1:17:05<9:03:45,  1.54it/s]
 13%|█▎        | 7285/57600 [1:17:05<8:57:22,  1.56it/s]
 13%|█▎        | 7286/57600 [1:17:06<8:55:22,  1.57it/s]
 13%|█▎        | 7287/57600 [1:17:07<9:07:58,  1.53it/s]
 13%|█▎        | 7288/57600 [1:17:07<9:01:10,  1.55it/s]
 13%|█▎        | 7289/57600 [1:17:08<9:09:17,  1.53it/s]
 13%|█▎        | 7290/57600 [1:17:09<9:10:19,  1.52it/s]
 13%|█▎        | 7291/57600 [1:17:09<9:00:48,  1.55it/s]
 13%|█▎        | 7292/57600 [1:17:10<9:27:19,  1.48it/s]
 13%|█▎        | 7293/57600 [1:17:11<9:15:12,  1.51it/s]
 13%|█▎        | 7294/57600 [1:17:11<9:08:43,  1.53it/s]
 13%|█▎        | 7295/57600 [1:17:12<8:48:58,  1.58it/s]
 13%|█▎        | 7296/57600 [1:17:13<8:50:23,  1.58it/s]
 13%|█▎        | 7297/57600 [1:17:13<8:48:55,  1.59it/s]
 13%|█▎        | 7298/57600 [1:17:14<8:34:15,  1.63it/s]
 13%|█▎        | 7299/57600 [1:17:14<8:49:59,  1.58it/s]
 13%|█▎        | 7300/57600 [1:17:15<9:09:52,  1.52it/s]
                                                        
{'loss': 1.4284, 'learning_rate': 8.886759581881533e-07, 'epoch': 80.57}

 13%|█▎        | 7300/57600 [1:17:15<9:09:52,  1.52it/s]
 13%|█▎        | 7301/57600 [1:17:16<9:00:48,  1.55it/s]
 13%|█▎        | 7302/57600 [1:17:16<9:12:44,  1.52it/s]
 13%|█▎        | 7303/57600 [1:17:17<9:04:07,  1.54it/s]
 13%|█▎        | 7304/57600 [1:17:18<9:09:01,  1.53it/s]
 13%|█▎        | 7305/57600 [1:17:18<9:14:19,  1.51it/s]
 13%|█▎        | 7306/57600 [1:17:19<9:22:55,  1.49it/s]
 13%|█▎        | 7307/57600 [1:17:20<9:07:55,  1.53it/s]
 13%|█▎        | 7308/57600 [1:17:20<9:09:59,  1.52it/s]
 13%|█▎        | 7309/57600 [1:17:21<9:22:35,  1.49it/s]
 13%|█▎        | 7310/57600 [1:17:22<9:13:08,  1.52it/s]
 13%|█▎        | 7311/57600 [1:17:22<9:00:29,  1.55it/s]
 13%|█▎        | 7312/57600 [1:17:23<8:41:01,  1.61it/s]
 13%|█▎        | 7313/57600 [1:17:24<8:46:26,  1.59it/s]
 13%|█▎        | 7314/57600 [1:17:24<8:36:35,  1.62it/s]
 13%|█▎        | 7315/57600 [1:17:25<8:53:56,  1.57it/s]
 13%|█▎        | 7316/57600 [1:17:26<9:13:52,  1.51it/s]
 13%|█▎        | 7317/57600 [1:17:26<9:18:10,  1.50it/s]
 13%|█▎        | 7318/57600 [1:17:27<9:18:47,  1.50it/s]
 13%|█▎        | 7319/57600 [1:17:28<9:29:27,  1.47it/s]
 13%|█▎        | 7320/57600 [1:17:28<9:09:02,  1.53it/s]
                                                        
{'loss': 1.3992, 'learning_rate': 8.88362369337979e-07, 'epoch': 80.79}

 13%|█▎        | 7320/57600 [1:17:28<9:09:02,  1.53it/s]
 13%|█▎        | 7321/57600 [1:17:29<8:55:38,  1.56it/s]
 13%|█▎        | 7322/57600 [1:17:29<8:53:23,  1.57it/s]
 13%|█▎        | 7323/57600 [1:17:30<9:05:51,  1.54it/s]
 13%|█▎        | 7324/57600 [1:17:31<9:20:48,  1.49it/s]
 13%|█▎        | 7325/57600 [1:17:31<9:23:56,  1.49it/s]
 13%|█▎        | 7326/57600 [1:17:32<9:06:31,  1.53it/s]
 13%|█▎        | 7327/57600 [1:17:33<8:53:49,  1.57it/s]
 13%|█▎        | 7328/57600 [1:17:33<8:53:51,  1.57it/s]
 13%|█▎        | 7329/57600 [1:17:34<8:46:19,  1.59it/s]
 13%|█▎        | 7330/57600 [1:17:35<8:49:39,  1.58it/s]
 13%|█▎        | 7331/57600 [1:17:35<8:40:49,  1.61it/s]
 13%|█▎        | 7332/57600 [1:17:36<9:04:04,  1.54it/s]
 13%|█▎        | 7333/57600 [1:17:37<8:55:00,  1.57it/s]
 13%|█▎        | 7334/57600 [1:17:37<8:51:17,  1.58it/s]
 13%|█▎        | 7335/57600 [1:17:38<8:58:19,  1.56it/s]
 13%|█▎        | 7336/57600 [1:17:38<8:49:51,  1.58it/s]
 13%|█▎        | 7337/57600 [1:17:39<8:45:06,  1.60it/s]
 13%|█▎        | 7338/57600 [1:17:40<8:54:04,  1.57it/s]
 13%|█▎        | 7339/57600 [1:17:40<9:05:17,  1.54it/s]
 13%|█▎        | 7340/57600 [1:17:41<8:51:41,  1.58it/s]
                                                        
{'loss': 1.4512, 'learning_rate': 8.880487804878048e-07, 'epoch': 81.02}

 13%|█▎        | 7340/57600 [1:17:41<8:51:41,  1.58it/s]
 13%|█▎        | 7341/57600 [1:17:42<8:57:11,  1.56it/s]
 13%|█▎        | 7342/57600 [1:17:42<9:18:15,  1.50it/s]
 13%|█▎        | 7343/57600 [1:17:43<9:18:35,  1.50it/s]
 13%|█▎        | 7344/57600 [1:17:44<9:15:15,  1.51it/s]
 13%|█▎        | 7345/57600 [1:17:44<8:57:55,  1.56it/s]
 13%|█▎        | 7346/57600 [1:17:45<9:05:41,  1.53it/s]
 13%|█▎        | 7347/57600 [1:17:46<9:25:51,  1.48it/s]
 13%|█▎        | 7348/57600 [1:17:46<9:28:08,  1.47it/s]
 13%|█▎        | 7349/57600 [1:17:47<9:28:07,  1.47it/s]
 13%|█▎        | 7350/57600 [1:17:48<9:19:56,  1.50it/s]
 13%|█▎        | 7351/57600 [1:17:48<9:19:07,  1.50it/s]
 13%|█▎        | 7352/57600 [1:17:49<9:23:18,  1.49it/s]
 13%|█▎        | 7353/57600 [1:17:50<9:34:32,  1.46it/s]
 13%|█▎        | 7354/57600 [1:17:50<9:18:13,  1.50it/s]
 13%|█▎        | 7355/57600 [1:17:51<9:11:42,  1.52it/s]
 13%|█▎        | 7356/57600 [1:17:52<8:56:14,  1.56it/s]
 13%|█▎        | 7357/57600 [1:17:52<9:01:04,  1.55it/s]
 13%|█▎        | 7358/57600 [1:17:53<8:50:40,  1.58it/s]
 13%|█▎        | 7359/57600 [1:17:53<8:40:13,  1.61it/s]
 13%|█▎        | 7360/57600 [1:17:54<8:24:32,  1.66it/s]
                                                        
{'loss': 1.4298, 'learning_rate': 8.877351916376307e-07, 'epoch': 81.24}

 13%|█▎        | 7360/57600 [1:17:54<8:24:32,  1.66it/s]
 13%|█▎        | 7361/57600 [1:17:55<8:42:47,  1.60it/s]
 13%|█▎        | 7362/57600 [1:17:55<8:32:28,  1.63it/s]
 13%|█▎        | 7363/57600 [1:17:56<8:51:58,  1.57it/s]
 13%|█▎        | 7364/57600 [1:17:57<8:42:29,  1.60it/s]
 13%|█▎        | 7365/57600 [1:17:57<8:42:35,  1.60it/s]
 13%|█▎        | 7366/57600 [1:17:58<8:46:16,  1.59it/s]
 13%|█▎        | 7367/57600 [1:17:59<9:01:16,  1.55it/s]
 13%|█▎        | 7368/57600 [1:17:59<9:14:58,  1.51it/s]
 13%|█▎        | 7369/57600 [1:18:00<8:53:21,  1.57it/s]
 13%|█▎        | 7370/57600 [1:18:00<8:39:27,  1.61it/s]
 13%|█▎        | 7371/57600 [1:18:01<8:36:20,  1.62it/s]
 13%|█▎        | 7372/57600 [1:18:02<8:36:48,  1.62it/s]
 13%|█▎        | 7373/57600 [1:18:02<8:47:37,  1.59it/s]
 13%|█▎        | 7374/57600 [1:18:03<8:53:10,  1.57it/s]
 13%|█▎        | 7375/57600 [1:18:04<9:08:22,  1.53it/s]
 13%|█▎        | 7376/57600 [1:18:04<9:15:53,  1.51it/s]
 13%|█▎        | 7377/57600 [1:18:05<8:55:08,  1.56it/s]
 13%|█▎        | 7378/57600 [1:18:06<9:28:48,  1.47it/s]
 13%|█▎        | 7379/57600 [1:18:06<9:16:34,  1.50it/s]
 13%|█▎        | 7380/57600 [1:18:07<9:04:00,  1.54it/s]
                                                        
{'loss': 1.4442, 'learning_rate': 8.874216027874564e-07, 'epoch': 81.46}

 13%|█▎        | 7380/57600 [1:18:07<9:04:00,  1.54it/s]
 13%|█▎        | 7381/57600 [1:18:08<9:10:10,  1.52it/s]
 13%|█▎        | 7382/57600 [1:18:08<9:14:41,  1.51it/s]
 13%|█▎        | 7383/57600 [1:18:09<9:11:30,  1.52it/s]
 13%|█▎        | 7384/57600 [1:18:10<9:13:03,  1.51it/s]
 13%|█▎        | 7385/57600 [1:18:10<8:56:22,  1.56it/s]
 13%|█▎        | 7386/57600 [1:18:11<8:55:23,  1.56it/s]
 13%|█▎        | 7387/57600 [1:18:11<8:51:36,  1.57it/s]
 13%|█▎        | 7388/57600 [1:18:12<9:23:51,  1.48it/s]
 13%|█▎        | 7389/57600 [1:18:13<9:10:46,  1.52it/s]
 13%|█▎        | 7390/57600 [1:18:14<9:22:32,  1.49it/s]
 13%|█▎        | 7391/57600 [1:18:14<9:40:08,  1.44it/s]
 13%|█▎        | 7392/57600 [1:18:15<9:44:22,  1.43it/s]
 13%|█▎        | 7393/57600 [1:18:16<9:52:05,  1.41it/s]
 13%|█▎        | 7394/57600 [1:18:16<9:34:49,  1.46it/s]
 13%|█▎        | 7395/57600 [1:18:17<9:16:37,  1.50it/s]
 13%|█▎        | 7396/57600 [1:18:18<9:01:34,  1.55it/s]
 13%|█▎        | 7397/57600 [1:18:18<9:08:07,  1.53it/s]
 13%|█▎        | 7398/57600 [1:18:19<8:59:21,  1.55it/s]
 13%|█▎        | 7399/57600 [1:18:19<8:52:11,  1.57it/s]
 13%|█▎        | 7400/57600 [1:18:20<9:03:55,  1.54it/s]
                                                        
{'loss': 1.4112, 'learning_rate': 8.871080139372822e-07, 'epoch': 81.68}

 13%|█▎        | 7400/57600 [1:18:20<9:03:55,  1.54it/s]
 13%|█▎        | 7401/57600 [1:18:21<8:59:57,  1.55it/s]
 13%|█▎        | 7402/57600 [1:18:21<8:55:22,  1.56it/s]
 13%|█▎        | 7403/57600 [1:18:22<8:48:34,  1.58it/s]
 13%|█▎        | 7404/57600 [1:18:23<8:37:53,  1.62it/s]
 13%|█▎        | 7405/57600 [1:18:23<8:31:31,  1.64it/s]
 13%|█▎        | 7406/57600 [1:18:24<8:37:56,  1.62it/s]
 13%|█▎        | 7407/57600 [1:18:24<8:31:45,  1.63it/s]
 13%|█▎        | 7408/57600 [1:18:25<8:23:51,  1.66it/s]
 13%|█▎        | 7409/57600 [1:18:26<8:20:37,  1.67it/s]
 13%|█▎        | 7410/57600 [1:18:26<8:27:45,  1.65it/s]
 13%|█▎        | 7411/57600 [1:18:27<8:31:47,  1.63it/s]
 13%|█▎        | 7412/57600 [1:18:27<8:26:39,  1.65it/s]
 13%|█▎        | 7413/57600 [1:18:28<9:13:19,  1.51it/s]
 13%|█▎        | 7414/57600 [1:18:29<9:06:43,  1.53it/s]
 13%|█▎        | 7415/57600 [1:18:30<9:03:36,  1.54it/s]
 13%|█▎        | 7416/57600 [1:18:30<9:09:49,  1.52it/s]
 13%|█▎        | 7417/57600 [1:18:31<8:58:41,  1.55it/s]
 13%|█▎        | 7418/57600 [1:18:31<8:37:44,  1.62it/s]
 13%|█▎        | 7419/57600 [1:18:32<8:32:12,  1.63it/s]
 13%|█▎        | 7420/57600 [1:18:33<8:49:03,  1.58it/s]
                                                        
{'loss': 1.4365, 'learning_rate': 8.867944250871079e-07, 'epoch': 81.9}

 13%|█▎        | 7420/57600 [1:18:33<8:49:03,  1.58it/s]
 13%|█▎        | 7421/57600 [1:18:33<8:24:47,  1.66it/s]
 13%|█▎        | 7422/57600 [1:18:34<8:15:32,  1.69it/s]
 13%|█▎        | 7423/57600 [1:18:34<8:19:35,  1.67it/s]
 13%|█▎        | 7424/57600 [1:18:35<8:24:02,  1.66it/s]
 13%|█▎        | 7425/57600 [1:18:36<8:36:45,  1.62it/s]
 13%|█▎        | 7426/57600 [1:18:36<8:24:30,  1.66it/s]
 13%|█▎        | 7427/57600 [1:18:37<8:25:01,  1.66it/s]
 13%|█▎        | 7428/57600 [1:18:37<8:20:33,  1.67it/s]
 13%|█▎        | 7429/57600 [1:18:38<8:15:16,  1.69it/s]
 13%|█▎        | 7430/57600 [1:18:39<8:40:06,  1.61it/s]
 13%|█▎        | 7431/57600 [1:18:39<8:30:45,  1.64it/s]
 13%|█▎        | 7432/57600 [1:18:40<8:16:26,  1.68it/s]
 13%|█▎        | 7433/57600 [1:18:40<8:16:17,  1.68it/s]
 13%|█▎        | 7434/57600 [1:18:41<8:13:49,  1.69it/s]
 13%|█▎        | 7435/57600 [1:18:42<8:24:08,  1.66it/s]
 13%|█▎        | 7436/57600 [1:18:42<8:22:59,  1.66it/s]
 13%|█▎        | 7437/57600 [1:18:43<8:32:32,  1.63it/s]
 13%|█▎        | 7438/57600 [1:18:43<8:13:15,  1.69it/s]
 13%|█▎        | 7439/57600 [1:18:44<8:12:58,  1.70it/s]
 13%|█▎        | 7440/57600 [1:18:45<8:15:12,  1.69it/s]
                                                        
{'loss': 1.5076, 'learning_rate': 8.864808362369338e-07, 'epoch': 82.12}

 13%|█▎        | 7440/57600 [1:18:45<8:15:12,  1.69it/s]
 13%|█▎        | 7441/57600 [1:18:45<8:18:02,  1.68it/s]
 13%|█▎        | 7442/57600 [1:18:46<8:19:38,  1.67it/s]
 13%|█▎        | 7443/57600 [1:18:46<8:35:39,  1.62it/s]
 13%|█▎        | 7444/57600 [1:18:47<8:40:49,  1.61it/s]
 13%|█▎        | 7445/57600 [1:18:48<8:44:27,  1.59it/s]
 13%|█▎        | 7446/57600 [1:18:48<8:43:26,  1.60it/s]
 13%|█▎        | 7447/57600 [1:18:49<8:34:18,  1.63it/s]
 13%|█▎        | 7448/57600 [1:18:49<8:25:00,  1.66it/s]
 13%|█▎        | 7449/57600 [1:18:50<8:26:31,  1.65it/s]
 13%|█▎        | 7450/57600 [1:18:51<8:41:27,  1.60it/s]
 13%|█▎        | 7451/57600 [1:18:51<8:47:21,  1.58it/s]
 13%|█▎        | 7452/57600 [1:18:52<9:01:19,  1.54it/s]
 13%|█▎        | 7453/57600 [1:18:53<8:57:49,  1.55it/s]
 13%|█▎        | 7454/57600 [1:18:53<8:35:18,  1.62it/s]
 13%|█▎        | 7455/57600 [1:18:54<8:36:20,  1.62it/s]
 13%|█▎        | 7456/57600 [1:18:54<8:29:27,  1.64it/s]
 13%|█▎        | 7457/57600 [1:18:55<8:51:32,  1.57it/s]
 13%|█▎        | 7458/57600 [1:18:56<9:00:08,  1.55it/s]
 13%|█▎        | 7459/57600 [1:18:56<8:42:18,  1.60it/s]
 13%|█▎        | 7460/57600 [1:18:57<8:24:27,  1.66it/s]
                                                        
{'loss': 1.4004, 'learning_rate': 8.861672473867594e-07, 'epoch': 82.34}

 13%|█▎        | 7460/57600 [1:18:57<8:24:27,  1.66it/s]
 13%|█▎        | 7461/57600 [1:18:58<8:25:37,  1.65it/s]
 13%|█▎        | 7462/57600 [1:18:58<8:29:09,  1.64it/s]
 13%|█▎        | 7463/57600 [1:18:59<8:27:27,  1.65it/s]
 13%|█▎        | 7464/57600 [1:18:59<8:29:11,  1.64it/s]
 13%|█▎        | 7465/57600 [1:19:00<8:40:37,  1.60it/s]
 13%|█▎        | 7466/57600 [1:19:01<8:48:01,  1.58it/s]
 13%|█▎        | 7467/57600 [1:19:01<8:27:13,  1.65it/s]
 13%|█▎        | 7468/57600 [1:19:02<8:35:40,  1.62it/s]
 13%|█▎        | 7469/57600 [1:19:03<8:30:54,  1.64it/s]
 13%|█▎        | 7470/57600 [1:19:03<8:38:55,  1.61it/s]
 13%|█▎        | 7471/57600 [1:19:04<8:46:58,  1.59it/s]
 13%|█▎        | 7472/57600 [1:19:04<8:35:42,  1.62it/s]
 13%|█▎        | 7473/57600 [1:19:05<8:21:59,  1.66it/s]
 13%|█▎        | 7474/57600 [1:19:06<8:22:17,  1.66it/s]
 13%|█▎        | 7475/57600 [1:19:06<8:15:01,  1.69it/s]
 13%|█▎        | 7476/57600 [1:19:07<8:28:13,  1.64it/s]
 13%|█▎        | 7477/57600 [1:19:07<8:26:25,  1.65it/s]
 13%|█▎        | 7478/57600 [1:19:08<8:22:45,  1.66it/s]
 13%|█▎        | 7479/57600 [1:19:09<8:13:18,  1.69it/s]
 13%|█▎        | 7480/57600 [1:19:09<8:22:30,  1.66it/s]
                                                        
{'loss': 1.4641, 'learning_rate': 8.858536585365853e-07, 'epoch': 82.56}

 13%|█▎        | 7480/57600 [1:19:09<8:22:30,  1.66it/s]
 13%|█▎        | 7481/57600 [1:19:10<8:25:35,  1.65it/s]
 13%|█▎        | 7482/57600 [1:19:10<8:39:32,  1.61it/s]
 13%|█▎        | 7483/57600 [1:19:11<8:43:59,  1.59it/s]
 13%|█▎        | 7484/57600 [1:19:12<8:49:23,  1.58it/s]
 13%|█▎        | 7485/57600 [1:19:12<8:40:00,  1.61it/s]
 13%|█▎        | 7486/57600 [1:19:13<8:46:33,  1.59it/s]
 13%|█▎        | 7487/57600 [1:19:14<9:00:47,  1.54it/s]
 13%|█▎        | 7488/57600 [1:19:14<8:38:17,  1.61it/s]
 13%|█▎        | 7489/57600 [1:19:15<8:27:03,  1.65it/s]
 13%|█▎        | 7490/57600 [1:19:15<8:36:17,  1.62it/s]
 13%|█▎        | 7491/57600 [1:19:16<8:27:20,  1.65it/s]
 13%|█▎        | 7492/57600 [1:19:17<8:54:33,  1.56it/s]
 13%|█▎        | 7493/57600 [1:19:17<8:56:21,  1.56it/s]
 13%|█▎        | 7494/57600 [1:19:18<8:44:46,  1.59it/s]
 13%|█▎        | 7495/57600 [1:19:19<8:37:54,  1.61it/s]
 13%|█▎        | 7496/57600 [1:19:19<8:35:59,  1.62it/s]
 13%|█▎        | 7497/57600 [1:19:20<9:01:01,  1.54it/s]
 13%|█▎        | 7498/57600 [1:19:21<8:56:23,  1.56it/s]
 13%|█▎        | 7499/57600 [1:19:21<8:45:54,  1.59it/s]
 13%|█▎        | 7500/57600 [1:19:22<8:47:26,  1.58it/s]
                                                        
{'loss': 1.4321, 'learning_rate': 8.855400696864112e-07, 'epoch': 82.78}

 13%|█▎        | 7500/57600 [1:19:22<8:47:26,  1.58it/s]
 13%|█▎        | 7501/57600 [1:19:22<8:47:55,  1.58it/s]
 13%|█▎        | 7502/57600 [1:19:23<8:43:26,  1.60it/s]
 13%|█▎        | 7503/57600 [1:19:24<8:52:50,  1.57it/s]
 13%|█▎        | 7504/57600 [1:19:24<8:31:30,  1.63it/s]
 13%|█▎        | 7505/57600 [1:19:25<8:24:08,  1.66it/s]
 13%|█▎        | 7506/57600 [1:19:25<8:21:52,  1.66it/s]
 13%|█▎        | 7507/57600 [1:19:26<8:46:33,  1.59it/s]
 13%|█▎        | 7508/57600 [1:19:27<8:47:16,  1.58it/s]
 13%|█▎        | 7509/57600 [1:19:27<8:31:28,  1.63it/s]
 13%|█▎        | 7510/57600 [1:19:28<8:16:53,  1.68it/s]
 13%|█▎        | 7511/57600 [1:19:28<8:17:32,  1.68it/s]
 13%|█▎        | 7512/57600 [1:19:29<8:26:34,  1.65it/s]
 13%|█▎        | 7513/57600 [1:19:30<8:35:08,  1.62it/s]
 13%|█▎        | 7514/57600 [1:19:30<8:34:51,  1.62it/s]
 13%|█▎        | 7515/57600 [1:19:31<8:45:39,  1.59it/s]
 13%|█▎        | 7516/57600 [1:19:32<8:53:36,  1.56it/s]
 13%|█▎        | 7517/57600 [1:19:32<8:50:52,  1.57it/s]
 13%|█▎        | 7518/57600 [1:19:33<8:44:35,  1.59it/s]
 13%|█▎        | 7519/57600 [1:19:34<8:39:05,  1.61it/s]
 13%|█▎        | 7520/57600 [1:19:34<8:49:40,  1.58it/s]
                                                        
{'loss': 1.4592, 'learning_rate': 8.85226480836237e-07, 'epoch': 83.0}

 13%|█▎        | 7520/57600 [1:19:34<8:49:40,  1.58it/s]
 13%|█▎        | 7521/57600 [1:19:35<9:12:33,  1.51it/s]
 13%|█▎        | 7522/57600 [1:19:36<8:52:42,  1.57it/s]
 13%|█▎        | 7523/57600 [1:19:36<8:47:31,  1.58it/s]
 13%|█▎        | 7524/57600 [1:19:37<8:31:01,  1.63it/s]
 13%|█▎        | 7525/57600 [1:19:37<8:35:22,  1.62it/s]
 13%|█▎        | 7526/57600 [1:19:38<8:28:39,  1.64it/s]
 13%|█▎        | 7527/57600 [1:19:39<8:31:56,  1.63it/s]
 13%|█▎        | 7528/57600 [1:19:39<8:36:24,  1.62it/s]
 13%|█▎        | 7529/57600 [1:19:40<8:40:15,  1.60it/s]
 13%|█▎        | 7530/57600 [1:19:40<8:30:08,  1.64it/s]
 13%|█▎        | 7531/57600 [1:19:41<8:54:34,  1.56it/s]
 13%|█▎        | 7532/57600 [1:19:42<8:42:39,  1.60it/s]
 13%|█▎        | 7533/57600 [1:19:42<8:34:56,  1.62it/s]
 13%|█▎        | 7534/57600 [1:19:43<8:44:47,  1.59it/s]
 13%|█▎        | 7535/57600 [1:19:44<8:46:52,  1.58it/s]
 13%|█▎        | 7536/57600 [1:19:44<8:30:40,  1.63it/s]
 13%|█▎        | 7537/57600 [1:19:45<8:23:09,  1.66it/s]
 13%|█▎        | 7538/57600 [1:19:45<8:14:52,  1.69it/s]
 13%|█▎        | 7539/57600 [1:19:46<8:25:10,  1.65it/s]
 13%|█▎        | 7540/57600 [1:19:47<8:24:17,  1.65it/s]
                                                        
{'loss': 1.4101, 'learning_rate': 8.849128919860627e-07, 'epoch': 83.22}

 13%|█▎        | 7540/57600 [1:19:47<8:24:17,  1.65it/s]
 13%|█▎        | 7541/57600 [1:19:47<8:40:33,  1.60it/s]
 13%|█▎        | 7542/57600 [1:19:48<8:45:41,  1.59it/s]
 13%|█▎        | 7543/57600 [1:19:48<8:33:48,  1.62it/s]
 13%|█▎        | 7544/57600 [1:19:49<8:35:45,  1.62it/s]
 13%|█▎        | 7545/57600 [1:19:50<8:36:32,  1.62it/s]
 13%|█▎        | 7546/57600 [1:19:50<8:31:57,  1.63it/s]
 13%|█▎        | 7547/57600 [1:19:51<8:19:27,  1.67it/s]
 13%|█▎        | 7548/57600 [1:19:51<8:10:39,  1.70it/s]
 13%|█▎        | 7549/57600 [1:19:52<8:14:55,  1.69it/s]
 13%|█▎        | 7550/57600 [1:19:53<8:31:37,  1.63it/s]
 13%|█▎        | 7551/57600 [1:19:53<8:32:07,  1.63it/s]
 13%|█▎        | 7552/57600 [1:19:54<8:22:48,  1.66it/s]
 13%|█▎        | 7553/57600 [1:19:54<8:19:07,  1.67it/s]
 13%|█▎        | 7554/57600 [1:19:55<8:47:46,  1.58it/s]
 13%|█▎        | 7555/57600 [1:19:56<8:39:01,  1.61it/s]
 13%|█▎        | 7556/57600 [1:19:56<8:45:32,  1.59it/s]
 13%|█▎        | 7557/57600 [1:19:57<8:51:51,  1.57it/s]
 13%|█▎        | 7558/57600 [1:19:58<9:02:58,  1.54it/s]
 13%|█▎        | 7559/57600 [1:19:58<8:58:28,  1.55it/s]
 13%|█▎        | 7560/57600 [1:19:59<8:40:17,  1.60it/s]
                                                        
{'loss': 1.4455, 'learning_rate': 8.845993031358884e-07, 'epoch': 83.44}

 13%|█▎        | 7560/57600 [1:19:59<8:40:17,  1.60it/s]
 13%|█▎        | 7561/57600 [1:20:00<8:46:49,  1.58it/s]
 13%|█▎        | 7562/57600 [1:20:00<8:37:41,  1.61it/s]
 13%|█▎        | 7563/57600 [1:20:01<8:36:35,  1.61it/s]
 13%|█▎        | 7564/57600 [1:20:01<8:45:20,  1.59it/s]
 13%|█▎        | 7565/57600 [1:20:02<8:32:55,  1.63it/s]
 13%|█▎        | 7566/57600 [1:20:03<8:21:15,  1.66it/s]
 13%|█▎        | 7567/57600 [1:20:03<8:47:42,  1.58it/s]
 13%|█▎        | 7568/57600 [1:20:04<8:51:51,  1.57it/s]
 13%|█▎        | 7569/57600 [1:20:05<9:12:32,  1.51it/s]
 13%|█▎        | 7570/57600 [1:20:05<8:46:24,  1.58it/s]
 13%|█▎        | 7571/57600 [1:20:06<8:43:29,  1.59it/s]
 13%|█▎        | 7572/57600 [1:20:06<8:28:27,  1.64it/s]
 13%|█▎        | 7573/57600 [1:20:07<8:28:33,  1.64it/s]
 13%|█▎        | 7574/57600 [1:20:08<8:31:11,  1.63it/s]
 13%|█▎        | 7575/57600 [1:20:08<8:31:45,  1.63it/s]
 13%|█▎        | 7576/57600 [1:20:09<8:36:19,  1.61it/s]
 13%|█▎        | 7577/57600 [1:20:10<8:32:17,  1.63it/s]
 13%|█▎        | 7578/57600 [1:20:10<9:04:21,  1.53it/s]
 13%|█▎        | 7579/57600 [1:20:11<8:52:22,  1.57it/s]
 13%|█▎        | 7580/57600 [1:20:12<8:50:55,  1.57it/s]
                                                        
{'loss': 1.4175, 'learning_rate': 8.842857142857143e-07, 'epoch': 83.66}

 13%|█▎        | 7580/57600 [1:20:12<8:50:55,  1.57it/s]
 13%|█▎        | 7581/57600 [1:20:12<8:41:23,  1.60it/s]
 13%|█▎        | 7582/57600 [1:20:13<8:39:15,  1.61it/s]
 13%|█▎        | 7583/57600 [1:20:13<8:34:25,  1.62it/s]
 13%|█▎        | 7584/57600 [1:20:14<8:32:01,  1.63it/s]
 13%|█▎        | 7585/57600 [1:20:15<8:39:18,  1.61it/s]
 13%|█▎        | 7586/57600 [1:20:15<8:44:32,  1.59it/s]
 13%|█▎        | 7587/57600 [1:20:16<8:34:57,  1.62it/s]
 13%|█▎        | 7588/57600 [1:20:16<8:41:30,  1.60it/s]
 13%|█▎        | 7589/57600 [1:20:17<8:29:45,  1.64it/s]
 13%|█▎        | 7590/57600 [1:20:18<8:39:15,  1.61it/s]
 13%|█▎        | 7591/57600 [1:20:18<8:28:23,  1.64it/s]
 13%|█▎        | 7592/57600 [1:20:19<8:33:36,  1.62it/s]
 13%|█▎        | 7593/57600 [1:20:20<8:39:23,  1.60it/s]
 13%|█▎        | 7594/57600 [1:20:20<8:51:24,  1.57it/s]
 13%|█▎        | 7595/57600 [1:20:21<8:36:33,  1.61it/s]
 13%|█▎        | 7596/57600 [1:20:21<8:42:13,  1.60it/s]
 13%|█▎        | 7597/57600 [1:20:22<8:28:52,  1.64it/s]
 13%|█▎        | 7598/57600 [1:20:23<8:30:32,  1.63it/s]
 13%|█▎        | 7599/57600 [1:20:23<8:53:27,  1.56it/s]
 13%|█▎        | 7600/57600 [1:20:24<8:43:43,  1.59it/s]
                                                        
{'loss': 1.4389, 'learning_rate': 8.8397212543554e-07, 'epoch': 83.89}

 13%|█▎        | 7600/57600 [1:20:24<8:43:43,  1.59it/s]
 13%|█▎        | 7601/57600 [1:20:25<8:39:32,  1.60it/s]
 13%|█▎        | 7602/57600 [1:20:25<8:37:34,  1.61it/s]
 13%|█▎        | 7603/57600 [1:20:26<8:30:50,  1.63it/s]
 13%|█▎        | 7604/57600 [1:20:26<8:27:39,  1.64it/s]
 13%|█▎        | 7605/57600 [1:20:27<8:10:08,  1.70it/s]
 13%|█▎        | 7606/57600 [1:20:27<8:12:58,  1.69it/s]
 13%|█▎        | 7607/57600 [1:20:28<8:02:08,  1.73it/s]
 13%|█▎        | 7608/57600 [1:20:29<8:01:41,  1.73it/s]
 13%|█▎        | 7609/57600 [1:20:29<8:01:34,  1.73it/s]
 13%|█▎        | 7610/57600 [1:20:30<8:32:33,  1.63it/s]
 13%|█▎        | 7611/57600 [1:20:31<8:46:06,  1.58it/s]
 13%|█▎        | 7612/57600 [1:20:31<8:50:29,  1.57it/s]
 13%|█▎        | 7613/57600 [1:20:32<8:30:48,  1.63it/s]
 13%|█▎        | 7614/57600 [1:20:32<8:22:08,  1.66it/s]
 13%|█▎        | 7615/57600 [1:20:33<8:26:42,  1.64it/s]
 13%|█▎        | 7616/57600 [1:20:34<8:23:45,  1.65it/s]
 13%|█▎        | 7617/57600 [1:20:34<8:11:29,  1.69it/s]
 13%|█▎        | 7618/57600 [1:20:35<8:22:31,  1.66it/s]
 13%|█▎        | 7619/57600 [1:20:35<8:08:06,  1.71it/s]
 13%|█▎        | 7620/57600 [1:20:36<8:15:40,  1.68it/s]
                                                        
{'loss': 1.4963, 'learning_rate': 8.836585365853658e-07, 'epoch': 84.11}

 13%|█▎        | 7620/57600 [1:20:36<8:15:40,  1.68it/s]
 13%|█▎        | 7621/57600 [1:20:37<8:14:27,  1.68it/s]
 13%|█▎        | 7622/57600 [1:20:37<8:29:02,  1.64it/s]
 13%|█▎        | 7623/57600 [1:20:38<8:28:17,  1.64it/s]
 13%|█▎        | 7624/57600 [1:20:38<8:27:21,  1.64it/s]
 13%|█▎        | 7625/57600 [1:20:39<8:24:03,  1.65it/s]
 13%|█▎        | 7626/57600 [1:20:40<8:35:15,  1.62it/s]
 13%|█▎        | 7627/57600 [1:20:40<8:28:32,  1.64it/s]
 13%|█▎        | 7628/57600 [1:20:41<8:16:25,  1.68it/s]
 13%|█▎        | 7629/57600 [1:20:41<8:14:33,  1.68it/s]
 13%|█▎        | 7630/57600 [1:20:42<8:23:21,  1.65it/s]
 13%|█▎        | 7631/57600 [1:20:43<8:23:11,  1.66it/s]
 13%|█▎        | 7632/57600 [1:20:43<8:53:09,  1.56it/s]
 13%|█▎        | 7633/57600 [1:20:44<8:34:51,  1.62it/s]
 13%|█▎        | 7634/57600 [1:20:44<8:30:17,  1.63it/s]
 13%|█▎        | 7635/57600 [1:20:45<8:38:20,  1.61it/s]
 13%|█▎        | 7636/57600 [1:20:46<8:37:41,  1.61it/s]
 13%|█▎        | 7637/57600 [1:20:46<8:30:21,  1.63it/s]
 13%|█▎        | 7638/57600 [1:20:47<8:15:24,  1.68it/s]
 13%|█▎        | 7639/57600 [1:20:47<8:12:39,  1.69it/s]
 13%|█▎        | 7640/57600 [1:20:48<8:21:12,  1.66it/s]
                                                        
{'loss': 1.4683, 'learning_rate': 8.833449477351916e-07, 'epoch': 84.33}

 13%|█▎        | 7640/57600 [1:20:48<8:21:12,  1.66it/s]
 13%|█▎        | 7641/57600 [1:20:49<8:34:57,  1.62it/s]
 13%|█▎        | 7642/57600 [1:20:49<8:40:39,  1.60it/s]
 13%|█▎        | 7643/57600 [1:20:50<8:28:31,  1.64it/s]
 13%|█▎        | 7644/57600 [1:20:51<8:53:31,  1.56it/s]
 13%|█▎        | 7645/57600 [1:20:51<9:00:12,  1.54it/s]
 13%|█▎        | 7646/57600 [1:20:52<8:46:36,  1.58it/s]
 13%|█▎        | 7647/57600 [1:20:53<8:44:18,  1.59it/s]
 13%|█▎        | 7648/57600 [1:20:53<8:33:23,  1.62it/s]
 13%|█▎        | 7649/57600 [1:20:54<8:34:39,  1.62it/s]
 13%|█▎        | 7650/57600 [1:20:54<8:29:46,  1.63it/s]
 13%|█▎        | 7651/57600 [1:20:55<8:37:30,  1.61it/s]
 13%|█▎        | 7652/57600 [1:20:56<8:27:56,  1.64it/s]
 13%|█▎        | 7653/57600 [1:20:56<8:27:46,  1.64it/s]
 13%|█▎        | 7654/57600 [1:20:57<8:40:39,  1.60it/s]
 13%|█▎        | 7655/57600 [1:20:57<8:33:25,  1.62it/s]
 13%|█▎        | 7656/57600 [1:20:58<8:23:02,  1.65it/s]
 13%|█▎        | 7657/57600 [1:20:59<8:13:50,  1.69it/s]
 13%|█▎        | 7658/57600 [1:20:59<8:06:48,  1.71it/s]
 13%|█▎        | 7659/57600 [1:21:00<8:25:42,  1.65it/s]
 13%|█▎        | 7660/57600 [1:21:01<8:46:27,  1.58it/s]
                                                        
{'loss': 1.4528, 'learning_rate': 8.830313588850174e-07, 'epoch': 84.55}

 13%|█▎        | 7660/57600 [1:21:01<8:46:27,  1.58it/s]
 13%|█▎        | 7661/57600 [1:21:01<8:37:20,  1.61it/s]
 13%|█▎        | 7662/57600 [1:21:02<8:24:06,  1.65it/s]
 13%|█▎        | 7663/57600 [1:21:02<8:27:58,  1.64it/s]
 13%|█▎        | 7664/57600 [1:21:03<8:33:29,  1.62it/s]
 13%|█▎        | 7665/57600 [1:21:04<8:47:56,  1.58it/s]
 13%|█▎        | 7666/57600 [1:21:04<8:46:24,  1.58it/s]
 13%|█▎        | 7667/57600 [1:21:05<8:52:19,  1.56it/s]
 13%|█▎        | 7668/57600 [1:21:06<8:57:48,  1.55it/s]
 13%|█▎        | 7669/57600 [1:21:06<8:40:42,  1.60it/s]
 13%|█▎        | 7670/57600 [1:21:07<8:51:37,  1.57it/s]
 13%|█▎        | 7671/57600 [1:21:07<8:57:47,  1.55it/s]
 13%|█▎        | 7672/57600 [1:21:08<8:59:02,  1.54it/s]
 13%|█▎        | 7673/57600 [1:21:09<8:54:30,  1.56it/s]
 13%|█▎        | 7674/57600 [1:21:09<8:38:20,  1.61it/s]
 13%|█▎        | 7675/57600 [1:21:10<8:32:11,  1.62it/s]
 13%|█▎        | 7676/57600 [1:21:11<8:19:53,  1.66it/s]
 13%|█▎        | 7677/57600 [1:21:11<8:20:53,  1.66it/s]
 13%|█▎        | 7678/57600 [1:21:12<8:19:19,  1.67it/s]
 13%|█▎        | 7679/57600 [1:21:12<8:13:25,  1.69it/s]
 13%|█▎        | 7680/57600 [1:21:13<8:24:31,  1.65it/s]
                                                        
{'loss': 1.4128, 'learning_rate': 8.827177700348431e-07, 'epoch': 84.77}

 13%|█▎        | 7680/57600 [1:21:13<8:24:31,  1.65it/s]
 13%|█▎        | 7681/57600 [1:21:14<8:35:16,  1.61it/s]
 13%|█▎        | 7682/57600 [1:21:14<8:48:06,  1.58it/s]
 13%|█▎        | 7683/57600 [1:21:15<8:44:55,  1.58it/s]
 13%|█▎        | 7684/57600 [1:21:15<8:32:59,  1.62it/s]
 13%|█▎        | 7685/57600 [1:21:16<8:47:54,  1.58it/s]
 13%|█▎        | 7686/57600 [1:21:17<8:56:00,  1.55it/s]
 13%|█▎        | 7687/57600 [1:21:17<9:00:31,  1.54it/s]
 13%|█▎        | 7688/57600 [1:21:18<8:43:12,  1.59it/s]
 13%|█▎        | 7689/57600 [1:21:19<8:20:44,  1.66it/s]
 13%|█▎        | 7690/57600 [1:21:19<9:00:09,  1.54it/s]
 13%|█▎        | 7691/57600 [1:21:20<8:52:20,  1.56it/s]
 13%|█▎        | 7692/57600 [1:21:21<8:42:33,  1.59it/s]
 13%|█▎        | 7693/57600 [1:21:21<8:45:11,  1.58it/s]
 13%|█▎        | 7694/57600 [1:21:22<8:47:36,  1.58it/s]
 13%|█▎        | 7695/57600 [1:21:22<8:48:00,  1.58it/s]
 13%|█▎        | 7696/57600 [1:21:23<9:13:45,  1.50it/s]
 13%|█▎        | 7697/57600 [1:21:24<8:46:10,  1.58it/s]
 13%|█▎        | 7698/57600 [1:21:24<8:34:54,  1.62it/s]
 13%|█▎        | 7699/57600 [1:21:25<8:34:18,  1.62it/s]
 13%|█▎        | 7700/57600 [1:21:26<8:37:20,  1.61it/s]
                                                        
{'loss': 1.4012, 'learning_rate': 8.824041811846689e-07, 'epoch': 84.99}

 13%|█▎        | 7700/57600 [1:21:26<8:37:20,  1.61it/s]
 13%|█▎        | 7701/57600 [1:21:26<8:36:00,  1.61it/s]
 13%|█▎        | 7702/57600 [1:21:27<8:42:35,  1.59it/s]
 13%|█▎        | 7703/57600 [1:21:27<8:42:10,  1.59it/s]
 13%|█▎        | 7704/57600 [1:21:28<8:39:21,  1.60it/s]
 13%|█▎        | 7705/57600 [1:21:29<8:23:04,  1.65it/s]
 13%|█▎        | 7706/57600 [1:21:29<8:22:57,  1.65it/s]
 13%|█▎        | 7707/57600 [1:21:30<8:20:47,  1.66it/s]
 13%|█▎        | 7708/57600 [1:21:30<8:17:21,  1.67it/s]
 13%|█▎        | 7709/57600 [1:21:31<8:40:37,  1.60it/s]
 13%|█▎        | 7710/57600 [1:21:32<8:49:45,  1.57it/s]
 13%|█▎        | 7711/57600 [1:21:32<8:51:03,  1.57it/s]
 13%|█▎        | 7712/57600 [1:21:33<8:30:11,  1.63it/s]
 13%|█▎        | 7713/57600 [1:21:34<8:36:26,  1.61it/s]
 13%|█▎        | 7714/57600 [1:21:34<8:26:27,  1.64it/s]
 13%|█▎        | 7715/57600 [1:21:35<8:12:31,  1.69it/s]
 13%|█▎        | 7716/57600 [1:21:35<8:23:57,  1.65it/s]
 13%|█▎        | 7717/57600 [1:21:36<8:31:46,  1.62it/s]
 13%|█▎        | 7718/57600 [1:21:37<8:33:41,  1.62it/s]
 13%|█▎        | 7719/57600 [1:21:37<8:27:26,  1.64it/s]
 13%|█▎        | 7720/57600 [1:21:38<8:33:22,  1.62it/s]
                                                        
{'loss': 1.4448, 'learning_rate': 8.820905923344947e-07, 'epoch': 85.21}

 13%|█▎        | 7720/57600 [1:21:38<8:33:22,  1.62it/s]
 13%|█▎        | 7721/57600 [1:21:38<8:22:18,  1.65it/s]
 13%|█▎        | 7722/57600 [1:21:39<8:25:25,  1.64it/s]
 13%|█▎        | 7723/57600 [1:21:40<8:29:04,  1.63it/s]
 13%|█▎        | 7724/57600 [1:21:40<8:52:51,  1.56it/s]
 13%|█▎        | 7725/57600 [1:21:41<8:23:28,  1.65it/s]
 13%|█▎        | 7726/57600 [1:21:42<8:23:11,  1.65it/s]
 13%|█▎        | 7727/57600 [1:21:42<8:30:22,  1.63it/s]
 13%|█▎        | 7728/57600 [1:21:43<8:28:05,  1.64it/s]
 13%|█▎        | 7729/57600 [1:21:43<8:28:38,  1.63it/s]
 13%|█▎        | 7730/57600 [1:21:44<8:31:03,  1.63it/s]
 13%|█▎        | 7731/57600 [1:21:45<8:33:13,  1.62it/s]
 13%|█▎        | 7732/57600 [1:21:45<8:44:38,  1.58it/s]
 13%|█▎        | 7733/57600 [1:21:46<8:33:52,  1.62it/s]
 13%|█▎        | 7734/57600 [1:21:47<8:40:44,  1.60it/s]
 13%|█▎        | 7735/57600 [1:21:47<9:05:11,  1.52it/s]
 13%|█▎        | 7736/57600 [1:21:48<9:09:41,  1.51it/s]
 13%|█▎        | 7737/57600 [1:21:49<9:02:51,  1.53it/s]
 13%|█▎        | 7738/57600 [1:21:49<9:04:08,  1.53it/s]
 13%|█▎        | 7739/57600 [1:21:50<8:44:55,  1.58it/s]
 13%|█▎        | 7740/57600 [1:21:50<8:51:43,  1.56it/s]
                                                        
{'loss': 1.3746, 'learning_rate': 8.817770034843205e-07, 'epoch': 85.43}

 13%|█▎        | 7740/57600 [1:21:50<8:51:43,  1.56it/s]
 13%|█▎        | 7741/57600 [1:21:51<9:02:55,  1.53it/s]
 13%|█▎        | 7742/57600 [1:21:52<8:44:08,  1.59it/s]
 13%|█▎        | 7743/57600 [1:21:52<8:48:17,  1.57it/s]
 13%|█▎        | 7744/57600 [1:21:53<8:29:00,  1.63it/s]
 13%|█▎        | 7745/57600 [1:21:54<8:50:57,  1.56it/s]
 13%|█▎        | 7746/57600 [1:21:54<9:07:36,  1.52it/s]
 13%|█▎        | 7747/57600 [1:21:55<8:54:55,  1.55it/s]
 13%|█▎        | 7748/57600 [1:21:56<8:46:28,  1.58it/s]
 13%|█▎        | 7749/57600 [1:21:56<8:54:51,  1.55it/s]
 13%|█▎        | 7750/57600 [1:21:57<8:35:17,  1.61it/s]
 13%|█▎        | 7751/57600 [1:21:57<8:33:25,  1.62it/s]
 13%|█▎        | 7752/57600 [1:21:58<8:37:37,  1.61it/s]
 13%|█▎        | 7753/57600 [1:21:59<8:42:49,  1.59it/s]
 13%|█▎        | 7754/57600 [1:21:59<8:29:02,  1.63it/s]
 13%|█▎        | 7755/57600 [1:22:00<8:37:09,  1.61it/s]
 13%|█▎        | 7756/57600 [1:22:01<9:00:41,  1.54it/s]
 13%|█▎        | 7757/57600 [1:22:01<8:53:32,  1.56it/s]
 13%|█▎        | 7758/57600 [1:22:02<8:41:33,  1.59it/s]
 13%|█▎        | 7759/57600 [1:22:02<8:35:35,  1.61it/s]
 13%|█▎        | 7760/57600 [1:22:03<8:30:00,  1.63it/s]
                                                        
{'loss': 1.4086, 'learning_rate': 8.814634146341464e-07, 'epoch': 85.65}

 13%|█▎        | 7760/57600 [1:22:03<8:30:00,  1.63it/s]
 13%|█▎        | 7761/57600 [1:22:04<8:21:59,  1.65it/s]
 13%|█▎        | 7762/57600 [1:22:04<8:23:22,  1.65it/s]
 13%|█▎        | 7763/57600 [1:22:05<8:21:22,  1.66it/s]
 13%|█▎        | 7764/57600 [1:22:05<8:16:11,  1.67it/s]
 13%|█▎        | 7765/57600 [1:22:06<8:32:46,  1.62it/s]
 13%|█▎        | 7766/57600 [1:22:07<8:22:24,  1.65it/s]
 13%|█▎        | 7767/57600 [1:22:07<8:36:48,  1.61it/s]
 13%|█▎        | 7768/57600 [1:22:08<8:19:22,  1.66it/s]
 13%|█▎        | 7769/57600 [1:22:08<8:19:38,  1.66it/s]
 13%|█▎        | 7770/57600 [1:22:09<8:24:15,  1.65it/s]
 13%|█▎        | 7771/57600 [1:22:10<8:29:05,  1.63it/s]
 13%|█▎        | 7772/57600 [1:22:10<8:17:21,  1.67it/s]
 13%|█▎        | 7773/57600 [1:22:11<8:14:46,  1.68it/s]
 13%|█▎        | 7774/57600 [1:22:11<8:14:58,  1.68it/s]
 13%|█▎        | 7775/57600 [1:22:12<8:08:44,  1.70it/s]
 14%|█▎        | 7776/57600 [1:22:13<8:27:59,  1.63it/s]
 14%|█▎        | 7777/57600 [1:22:13<8:28:56,  1.63it/s]
 14%|█▎        | 7778/57600 [1:22:14<8:32:02,  1.62it/s]
 14%|█▎        | 7779/57600 [1:22:15<8:39:12,  1.60it/s]
 14%|█▎        | 7780/57600 [1:22:15<9:03:34,  1.53it/s]
                                                        
{'loss': 1.4774, 'learning_rate': 8.811498257839721e-07, 'epoch': 85.87}

 14%|█▎        | 7780/57600 [1:22:15<9:03:34,  1.53it/s]
 14%|█▎        | 7781/57600 [1:22:16<8:43:38,  1.59it/s]
 14%|█▎        | 7782/57600 [1:22:16<8:34:49,  1.61it/s]
 14%|█▎        | 7783/57600 [1:22:17<8:26:56,  1.64it/s]
 14%|█▎        | 7784/57600 [1:22:18<8:52:20,  1.56it/s]
 14%|█▎        | 7785/57600 [1:22:18<8:32:59,  1.62it/s]
 14%|█▎        | 7786/57600 [1:22:19<8:44:38,  1.58it/s]
 14%|█▎        | 7787/57600 [1:22:20<8:34:06,  1.61it/s]
 14%|█▎        | 7788/57600 [1:22:20<8:38:28,  1.60it/s]
 14%|█▎        | 7789/57600 [1:22:21<8:30:56,  1.62it/s]
 14%|█▎        | 7790/57600 [1:22:21<8:33:58,  1.62it/s]
 14%|█▎        | 7791/57600 [1:22:22<8:33:12,  1.62it/s]
 14%|█▎        | 7792/57600 [1:22:23<8:47:00,  1.58it/s]
 14%|█▎        | 7793/57600 [1:22:23<8:29:03,  1.63it/s]
 14%|█▎        | 7794/57600 [1:22:24<8:29:23,  1.63it/s]
 14%|█▎        | 7795/57600 [1:22:25<8:33:07,  1.62it/s]
 14%|█▎        | 7796/57600 [1:22:25<8:57:50,  1.54it/s]
 14%|█▎        | 7797/57600 [1:22:26<9:00:51,  1.53it/s]
 14%|█▎        | 7798/57600 [1:22:27<8:56:53,  1.55it/s]
 14%|█▎        | 7799/57600 [1:22:27<8:42:07,  1.59it/s]
 14%|█▎        | 7800/57600 [1:22:28<8:49:45,  1.57it/s]
                                                        
{'loss': 1.4534, 'learning_rate': 8.808362369337979e-07, 'epoch': 86.09}

 14%|█▎        | 7800/57600 [1:22:28<8:49:45,  1.57it/s]
 14%|█▎        | 7801/57600 [1:22:28<8:41:44,  1.59it/s]
 14%|█▎        | 7802/57600 [1:22:29<8:28:38,  1.63it/s]
 14%|█▎        | 7803/57600 [1:22:30<8:35:33,  1.61it/s]
 14%|█▎        | 7804/57600 [1:22:30<8:38:50,  1.60it/s]
 14%|█▎        | 7805/57600 [1:22:31<8:31:08,  1.62it/s]
 14%|█▎        | 7806/57600 [1:22:31<8:22:13,  1.65it/s]
 14%|█▎        | 7807/57600 [1:22:32<8:45:11,  1.58it/s]
 14%|█▎        | 7808/57600 [1:22:33<8:59:10,  1.54it/s]
 14%|█▎        | 7809/57600 [1:22:33<8:51:33,  1.56it/s]
 14%|█▎        | 7810/57600 [1:22:34<8:54:54,  1.55it/s]
 14%|█▎        | 7811/57600 [1:22:35<8:34:54,  1.61it/s]
 14%|█▎        | 7812/57600 [1:22:35<8:51:37,  1.56it/s]
 14%|█▎        | 7813/57600 [1:22:36<8:56:43,  1.55it/s]
 14%|█▎        | 7814/57600 [1:22:37<9:01:06,  1.53it/s]
 14%|█▎        | 7815/57600 [1:22:37<8:51:41,  1.56it/s]
 14%|█▎        | 7816/57600 [1:22:38<8:45:35,  1.58it/s]
 14%|█▎        | 7817/57600 [1:22:39<9:07:37,  1.52it/s]
 14%|█▎        | 7818/57600 [1:22:39<8:55:04,  1.55it/s]
 14%|█▎        | 7819/57600 [1:22:40<9:08:26,  1.51it/s]
 14%|█▎        | 7820/57600 [1:22:41<8:53:46,  1.55it/s]
                                                        
{'loss': 1.3844, 'learning_rate': 8.805226480836237e-07, 'epoch': 86.31}

 14%|█▎        | 7820/57600 [1:22:41<8:53:46,  1.55it/s]
 14%|█▎        | 7821/57600 [1:22:41<8:42:50,  1.59it/s]
 14%|█▎        | 7822/57600 [1:22:42<8:28:42,  1.63it/s]
 14%|█▎        | 7823/57600 [1:22:42<8:22:36,  1.65it/s]
 14%|█▎        | 7824/57600 [1:22:43<8:14:04,  1.68it/s]
 14%|█▎        | 7825/57600 [1:22:44<8:17:39,  1.67it/s]
 14%|█▎        | 7826/57600 [1:22:44<8:12:55,  1.68it/s]
 14%|█▎        | 7827/57600 [1:22:45<8:11:17,  1.69it/s]
 14%|█▎        | 7828/57600 [1:22:45<8:22:35,  1.65it/s]
 14%|█▎        | 7829/57600 [1:22:46<8:28:53,  1.63it/s]
 14%|█▎        | 7830/57600 [1:22:46<8:13:41,  1.68it/s]
 14%|█▎        | 7831/57600 [1:22:47<8:13:41,  1.68it/s]
 14%|█▎        | 7832/57600 [1:22:48<8:15:30,  1.67it/s]
 14%|█▎        | 7833/57600 [1:22:48<8:23:22,  1.65it/s]
 14%|█▎        | 7834/57600 [1:22:49<8:20:08,  1.66it/s]
 14%|█▎        | 7835/57600 [1:22:50<8:43:28,  1.58it/s]
 14%|█▎        | 7836/57600 [1:22:50<8:47:59,  1.57it/s]
 14%|█▎        | 7837/57600 [1:22:51<8:36:30,  1.61it/s]
 14%|█▎        | 7838/57600 [1:22:51<8:41:07,  1.59it/s]
 14%|█▎        | 7839/57600 [1:22:52<8:52:28,  1.56it/s]
 14%|█▎        | 7840/57600 [1:22:53<8:25:23,  1.64it/s]
                                                        
{'loss': 1.4751, 'learning_rate': 8.802090592334494e-07, 'epoch': 86.53}

 14%|█▎        | 7840/57600 [1:22:53<8:25:23,  1.64it/s]
 14%|█▎        | 7841/57600 [1:22:53<8:11:26,  1.69it/s]
 14%|█▎        | 7842/57600 [1:22:54<8:27:36,  1.63it/s]
 14%|█▎        | 7843/57600 [1:22:55<8:32:30,  1.62it/s]
 14%|█▎        | 7844/57600 [1:22:55<8:31:12,  1.62it/s]
 14%|█▎        | 7845/57600 [1:22:56<8:23:57,  1.65it/s]
 14%|█▎        | 7846/57600 [1:22:56<8:45:37,  1.58it/s]
 14%|█▎        | 7847/57600 [1:22:57<8:42:50,  1.59it/s]
 14%|█▎        | 7848/57600 [1:22:58<8:51:09,  1.56it/s]
 14%|█▎        | 7849/57600 [1:22:58<8:55:29,  1.55it/s]
 14%|█▎        | 7850/57600 [1:22:59<8:46:05,  1.58it/s]
 14%|█▎        | 7851/57600 [1:23:00<8:28:15,  1.63it/s]
 14%|█▎        | 7852/57600 [1:23:00<8:30:02,  1.63it/s]
 14%|█▎        | 7853/57600 [1:23:01<8:28:32,  1.63it/s]
 14%|█▎        | 7854/57600 [1:23:01<8:22:33,  1.65it/s]
 14%|█▎        | 7855/57600 [1:23:02<8:27:28,  1.63it/s]
 14%|█▎        | 7856/57600 [1:23:03<8:29:39,  1.63it/s]
 14%|█▎        | 7857/57600 [1:23:03<8:33:53,  1.61it/s]
 14%|█▎        | 7858/57600 [1:23:04<8:17:28,  1.67it/s]
 14%|█▎        | 7859/57600 [1:23:04<8:17:57,  1.66it/s]
 14%|█▎        | 7860/57600 [1:23:05<8:25:00,  1.64it/s]
                                                        
{'loss': 1.4002, 'learning_rate': 8.798954703832752e-07, 'epoch': 86.75}

 14%|█▎        | 7860/57600 [1:23:05<8:25:00,  1.64it/s]
 14%|█▎        | 7861/57600 [1:23:06<8:22:29,  1.65it/s]
 14%|█▎        | 7862/57600 [1:23:06<8:19:06,  1.66it/s]
 14%|█▎        | 7863/57600 [1:23:07<8:17:24,  1.67it/s]
 14%|█▎        | 7864/57600 [1:23:07<8:17:33,  1.67it/s]
 14%|█▎        | 7865/57600 [1:23:08<8:22:45,  1.65it/s]
 14%|█▎        | 7866/57600 [1:23:09<8:21:05,  1.65it/s]
 14%|█▎        | 7867/57600 [1:23:09<8:13:25,  1.68it/s]
 14%|█▎        | 7868/57600 [1:23:10<8:16:18,  1.67it/s]
 14%|█▎        | 7869/57600 [1:23:10<8:04:58,  1.71it/s]
 14%|█▎        | 7870/57600 [1:23:11<8:03:21,  1.71it/s]
 14%|█▎        | 7871/57600 [1:23:12<8:00:02,  1.73it/s]
 14%|█▎        | 7872/57600 [1:23:12<8:27:18,  1.63it/s]
 14%|█▎        | 7873/57600 [1:23:13<8:35:41,  1.61it/s]
 14%|█▎        | 7874/57600 [1:23:13<8:38:28,  1.60it/s]
 14%|█▎        | 7875/57600 [1:23:14<8:54:12,  1.55it/s]
 14%|█▎        | 7876/57600 [1:23:15<8:43:39,  1.58it/s]
 14%|█▎        | 7877/57600 [1:23:15<8:47:48,  1.57it/s]
 14%|█▎        | 7878/57600 [1:23:16<8:57:25,  1.54it/s]
 14%|█▎        | 7879/57600 [1:23:17<8:46:53,  1.57it/s]
 14%|█▎        | 7880/57600 [1:23:17<8:36:43,  1.60it/s]
                                                        
{'loss': 1.4659, 'learning_rate': 8.79581881533101e-07, 'epoch': 86.98}

 14%|█▎        | 7880/57600 [1:23:17<8:36:43,  1.60it/s]
 14%|█▎        | 7881/57600 [1:23:18<8:21:47,  1.65it/s]
 14%|█▎        | 7882/57600 [1:23:18<8:04:10,  1.71it/s]
 14%|█▎        | 7883/57600 [1:23:19<8:29:29,  1.63it/s]
 14%|█▎        | 7884/57600 [1:23:20<8:31:02,  1.62it/s]
 14%|█▎        | 7885/57600 [1:23:20<8:48:29,  1.57it/s]
 14%|█▎        | 7886/57600 [1:23:21<8:48:47,  1.57it/s]
 14%|█▎        | 7887/57600 [1:23:22<8:34:16,  1.61it/s]
 14%|█▎        | 7888/57600 [1:23:22<8:34:05,  1.61it/s]
 14%|█▎        | 7889/57600 [1:23:23<8:28:36,  1.63it/s]
 14%|█▎        | 7890/57600 [1:23:23<8:33:37,  1.61it/s]
 14%|█▎        | 7891/57600 [1:23:24<8:34:20,  1.61it/s]
 14%|█▎        | 7892/57600 [1:23:25<8:37:20,  1.60it/s]
 14%|█▎        | 7893/57600 [1:23:25<8:33:36,  1.61it/s]
 14%|█▎        | 7894/57600 [1:23:26<8:40:06,  1.59it/s]
 14%|█▎        | 7895/57600 [1:23:27<8:40:48,  1.59it/s]
 14%|█▎        | 7896/57600 [1:23:27<8:45:26,  1.58it/s]
 14%|█▎        | 7897/57600 [1:23:28<8:58:30,  1.54it/s]
 14%|█▎        | 7898/57600 [1:23:29<9:06:37,  1.52it/s]
 14%|█▎        | 7899/57600 [1:23:29<9:03:43,  1.52it/s]
 14%|█▎        | 7900/57600 [1:23:30<8:47:58,  1.57it/s]
                                                        
{'loss': 1.4322, 'learning_rate': 8.792682926829268e-07, 'epoch': 87.2}

 14%|█▎        | 7900/57600 [1:23:30<8:47:58,  1.57it/s]
 14%|█▎        | 7901/57600 [1:23:30<8:39:06,  1.60it/s]
 14%|█▎        | 7902/57600 [1:23:31<8:49:02,  1.57it/s]
 14%|█▎        | 7903/57600 [1:23:32<8:24:02,  1.64it/s]
 14%|█▎        | 7904/57600 [1:23:32<8:29:30,  1.63it/s]
 14%|█▎        | 7905/57600 [1:23:33<8:15:38,  1.67it/s]
 14%|█▎        | 7906/57600 [1:23:34<8:32:13,  1.62it/s]
 14%|█▎        | 7907/57600 [1:23:34<8:19:56,  1.66it/s]
 14%|█▎        | 7908/57600 [1:23:35<8:15:09,  1.67it/s]
 14%|█▎        | 7909/57600 [1:23:35<8:18:27,  1.66it/s]
 14%|█▎        | 7910/57600 [1:23:36<8:25:02,  1.64it/s]
 14%|█▎        | 7911/57600 [1:23:37<8:20:25,  1.65it/s]
 14%|█▎        | 7912/57600 [1:23:37<8:32:21,  1.62it/s]
 14%|█▎        | 7913/57600 [1:23:38<8:25:57,  1.64it/s]
 14%|█▎        | 7914/57600 [1:23:38<8:17:47,  1.66it/s]
 14%|█▎        | 7915/57600 [1:23:39<8:44:06,  1.58it/s]
 14%|█▎        | 7916/57600 [1:23:40<8:32:59,  1.61it/s]
 14%|█▎        | 7917/57600 [1:23:40<8:40:35,  1.59it/s]
 14%|█▎        | 7918/57600 [1:23:41<8:53:30,  1.55it/s]
 14%|█▎        | 7919/57600 [1:23:42<9:04:56,  1.52it/s]
 14%|█▍        | 7920/57600 [1:23:42<8:51:06,  1.56it/s]
                                                        
{'loss': 1.4278, 'learning_rate': 8.789547038327526e-07, 'epoch': 87.42}

 14%|█▍        | 7920/57600 [1:23:42<8:51:06,  1.56it/s]
 14%|█▍        | 7921/57600 [1:23:43<8:40:42,  1.59it/s]
 14%|█▍        | 7922/57600 [1:23:43<8:37:17,  1.60it/s]
 14%|█▍        | 7923/57600 [1:23:44<8:37:28,  1.60it/s]
 14%|█▍        | 7924/57600 [1:23:45<8:31:40,  1.62it/s]
 14%|█▍        | 7925/57600 [1:23:45<8:35:55,  1.60it/s]
 14%|█▍        | 7926/57600 [1:23:46<8:24:38,  1.64it/s]
 14%|█▍        | 7927/57600 [1:23:47<8:20:24,  1.65it/s]
 14%|█▍        | 7928/57600 [1:23:47<8:23:54,  1.64it/s]
 14%|█▍        | 7929/57600 [1:23:48<8:22:28,  1.65it/s]
 14%|█▍        | 7930/57600 [1:23:48<8:45:03,  1.58it/s]
 14%|█▍        | 7931/57600 [1:23:49<8:29:14,  1.63it/s]
 14%|█▍        | 7932/57600 [1:23:50<8:16:02,  1.67it/s]
 14%|█▍        | 7933/57600 [1:23:50<8:30:28,  1.62it/s]
 14%|█▍        | 7934/57600 [1:23:51<8:28:09,  1.63it/s]
 14%|█▍        | 7935/57600 [1:23:51<8:07:35,  1.70it/s]
 14%|█▍        | 7936/57600 [1:23:52<8:32:25,  1.62it/s]
 14%|█▍        | 7937/57600 [1:23:53<8:26:26,  1.63it/s]
 14%|█▍        | 7938/57600 [1:23:53<8:21:43,  1.65it/s]
 14%|█▍        | 7939/57600 [1:23:54<8:21:27,  1.65it/s]
 14%|█▍        | 7940/57600 [1:23:55<8:35:38,  1.61it/s]
                                                        
{'loss': 1.453, 'learning_rate': 8.786411149825783e-07, 'epoch': 87.64}

 14%|█▍        | 7940/57600 [1:23:55<8:35:38,  1.61it/s]
 14%|█▍        | 7941/57600 [1:23:55<8:33:29,  1.61it/s]
 14%|█▍        | 7942/57600 [1:23:56<8:45:52,  1.57it/s]
 14%|█▍        | 7943/57600 [1:23:56<8:27:14,  1.63it/s]
 14%|█▍        | 7944/57600 [1:23:57<8:21:21,  1.65it/s]
 14%|█▍        | 7945/57600 [1:23:58<8:14:28,  1.67it/s]
 14%|█▍        | 7946/57600 [1:23:58<8:15:03,  1.67it/s]
 14%|█▍        | 7947/57600 [1:23:59<8:20:43,  1.65it/s]
 14%|█▍        | 7948/57600 [1:23:59<8:14:14,  1.67it/s]
 14%|█▍        | 7949/57600 [1:24:00<8:13:31,  1.68it/s]
 14%|█▍        | 7950/57600 [1:24:01<8:18:23,  1.66it/s]
 14%|█▍        | 7951/57600 [1:24:01<8:14:28,  1.67it/s]
 14%|█▍        | 7952/57600 [1:24:02<8:24:36,  1.64it/s]
 14%|█▍        | 7953/57600 [1:24:02<8:14:07,  1.67it/s]
 14%|█▍        | 7954/57600 [1:24:03<8:11:46,  1.68it/s]
 14%|█▍        | 7955/57600 [1:24:04<8:33:28,  1.61it/s]
 14%|█▍        | 7956/57600 [1:24:04<8:18:47,  1.66it/s]
 14%|█▍        | 7957/57600 [1:24:05<8:08:21,  1.69it/s]
 14%|█▍        | 7958/57600 [1:24:05<8:05:00,  1.71it/s]
 14%|█▍        | 7959/57600 [1:24:06<8:14:47,  1.67it/s]
 14%|█▍        | 7960/57600 [1:24:07<8:13:05,  1.68it/s]
                                                        
{'loss': 1.4371, 'learning_rate': 8.783275261324042e-07, 'epoch': 87.86}

 14%|█▍        | 7960/57600 [1:24:07<8:13:05,  1.68it/s]
 14%|█▍        | 7961/57600 [1:24:07<8:22:42,  1.65it/s]
 14%|█▍        | 7962/57600 [1:24:08<8:18:54,  1.66it/s]
 14%|█▍        | 7963/57600 [1:24:08<8:13:01,  1.68it/s]
 14%|█▍        | 7964/57600 [1:24:09<8:20:58,  1.65it/s]
 14%|█▍        | 7965/57600 [1:24:10<8:28:00,  1.63it/s]
 14%|█▍        | 7966/57600 [1:24:10<8:39:26,  1.59it/s]
 14%|█▍        | 7967/57600 [1:24:11<8:33:21,  1.61it/s]
 14%|█▍        | 7968/57600 [1:24:11<8:25:03,  1.64it/s]
 14%|█▍        | 7969/57600 [1:24:12<8:52:01,  1.55it/s]
 14%|█▍        | 7970/57600 [1:24:13<8:41:48,  1.59it/s]
 14%|█▍        | 7971/57600 [1:24:13<8:48:40,  1.56it/s]
 14%|█▍        | 7972/57600 [1:24:14<8:26:17,  1.63it/s]
 14%|█▍        | 7973/57600 [1:24:15<8:35:40,  1.60it/s]
 14%|█▍        | 7974/57600 [1:24:15<8:44:38,  1.58it/s]
 14%|█▍        | 7975/57600 [1:24:16<8:42:36,  1.58it/s]
 14%|█▍        | 7976/57600 [1:24:16<8:33:11,  1.61it/s]
 14%|█▍        | 7977/57600 [1:24:17<8:29:57,  1.62it/s]
 14%|█▍        | 7978/57600 [1:24:18<8:49:03,  1.56it/s]
 14%|█▍        | 7979/57600 [1:24:18<8:28:15,  1.63it/s]
 14%|█▍        | 7980/57600 [1:24:19<8:30:57,  1.62it/s]
                                                        
{'loss': 1.4775, 'learning_rate': 8.780139372822298e-07, 'epoch': 88.08}

 14%|█▍        | 7980/57600 [1:24:19<8:30:57,  1.62it/s]
 14%|█▍        | 7981/57600 [1:24:20<8:41:20,  1.59it/s]
 14%|█▍        | 7982/57600 [1:24:20<8:44:57,  1.58it/s]
 14%|█▍        | 7983/57600 [1:24:21<8:27:27,  1.63it/s]
 14%|█▍        | 7984/57600 [1:24:21<8:23:13,  1.64it/s]
 14%|█▍        | 7985/57600 [1:24:22<8:30:18,  1.62it/s]
 14%|█▍        | 7986/57600 [1:24:23<8:46:44,  1.57it/s]
 14%|█▍        | 7987/57600 [1:24:23<8:52:08,  1.55it/s]
 14%|█▍        | 7988/57600 [1:24:24<8:37:22,  1.60it/s]
 14%|█▍        | 7989/57600 [1:24:25<8:42:57,  1.58it/s]
 14%|█▍        | 7990/57600 [1:24:25<8:50:52,  1.56it/s]
 14%|█▍        | 7991/57600 [1:24:26<8:46:11,  1.57it/s]
 14%|█▍        | 7992/57600 [1:24:27<8:33:21,  1.61it/s]
 14%|█▍        | 7993/57600 [1:24:27<8:31:12,  1.62it/s]
 14%|█▍        | 7994/57600 [1:24:28<8:17:42,  1.66it/s]
 14%|█▍        | 7995/57600 [1:24:28<8:20:09,  1.65it/s]
 14%|█▍        | 7996/57600 [1:24:29<8:14:57,  1.67it/s]
 14%|█▍        | 7997/57600 [1:24:30<8:37:29,  1.60it/s]
 14%|█▍        | 7998/57600 [1:24:30<8:35:02,  1.61it/s]
 14%|█▍        | 7999/57600 [1:24:31<8:39:19,  1.59it/s]
 14%|█▍        | 8000/57600 [1:24:31<8:39:28,  1.59it/s]
                                                        
{'loss': 1.4058, 'learning_rate': 8.777003484320557e-07, 'epoch': 88.3}

 14%|█▍        | 8000/57600 [1:24:31<8:39:28,  1.59it/s]
 14%|█▍        | 8001/57600 [1:24:32<8:38:21,  1.59it/s]
 14%|█▍        | 8002/57600 [1:24:33<8:37:57,  1.60it/s]
 14%|█▍        | 8003/57600 [1:24:33<8:41:43,  1.58it/s]
 14%|█▍        | 8004/57600 [1:24:34<8:43:10,  1.58it/s]
 14%|█▍        | 8005/57600 [1:24:35<8:43:02,  1.58it/s]
 14%|█▍        | 8006/57600 [1:24:35<8:46:13,  1.57it/s]
 14%|█▍        | 8007/57600 [1:24:36<8:40:56,  1.59it/s]
 14%|█▍        | 8008/57600 [1:24:37<8:56:58,  1.54it/s]
 14%|█▍        | 8009/57600 [1:24:37<9:00:52,  1.53it/s]
 14%|█▍        | 8010/57600 [1:24:38<8:55:29,  1.54it/s]
 14%|█▍        | 8011/57600 [1:24:38<8:34:26,  1.61it/s]
 14%|█▍        | 8012/57600 [1:24:39<8:38:45,  1.59it/s]
 14%|█▍        | 8013/57600 [1:24:40<8:28:13,  1.63it/s]
 14%|█▍        | 8014/57600 [1:24:40<8:51:15,  1.56it/s]
 14%|█▍        | 8015/57600 [1:24:41<8:41:14,  1.59it/s]
 14%|█▍        | 8016/57600 [1:24:42<8:31:01,  1.62it/s]
 14%|█▍        | 8017/57600 [1:24:42<8:22:50,  1.64it/s]
 14%|█▍        | 8018/57600 [1:24:43<8:35:42,  1.60it/s]
 14%|█▍        | 8019/57600 [1:24:43<8:22:46,  1.64it/s]
 14%|█▍        | 8020/57600 [1:24:44<8:21:54,  1.65it/s]
                                                        
{'loss': 1.4119, 'learning_rate': 8.773867595818815e-07, 'epoch': 88.52}

 14%|█▍        | 8020/57600 [1:24:44<8:21:54,  1.65it/s]
 14%|█▍        | 8021/57600 [1:24:45<8:12:03,  1.68it/s]
 14%|█▍        | 8022/57600 [1:24:45<8:19:59,  1.65it/s]
 14%|█▍        | 8023/57600 [1:24:46<8:44:50,  1.57it/s]
 14%|█▍        | 8024/57600 [1:24:46<8:35:42,  1.60it/s]
 14%|█▍        | 8025/57600 [1:24:47<8:34:29,  1.61it/s]
 14%|█▍        | 8026/57600 [1:24:48<8:40:48,  1.59it/s]
 14%|█▍        | 8027/57600 [1:24:48<8:30:49,  1.62it/s]
 14%|█▍        | 8028/57600 [1:24:49<8:30:35,  1.62it/s]
 14%|█▍        | 8029/57600 [1:24:49<8:07:15,  1.70it/s]
 14%|█▍        | 8030/57600 [1:24:50<8:07:50,  1.69it/s]
 14%|█▍        | 8031/57600 [1:24:51<7:59:30,  1.72it/s]
 14%|█▍        | 8032/57600 [1:24:51<8:03:13,  1.71it/s]
 14%|█▍        | 8033/57600 [1:24:52<8:19:54,  1.65it/s]
 14%|█▍        | 8034/57600 [1:24:52<8:13:21,  1.67it/s]
 14%|█▍        | 8035/57600 [1:24:53<8:28:12,  1.63it/s]
 14%|█▍        | 8036/57600 [1:24:54<8:16:10,  1.66it/s]
 14%|█▍        | 8037/57600 [1:24:54<8:33:53,  1.61it/s]
 14%|█▍        | 8038/57600 [1:24:55<8:39:34,  1.59it/s]
 14%|█▍        | 8039/57600 [1:24:56<8:32:05,  1.61it/s]
 14%|█▍        | 8040/57600 [1:24:56<8:33:33,  1.61it/s]
                                                        
{'loss': 1.4316, 'learning_rate': 8.770731707317073e-07, 'epoch': 88.74}

 14%|█▍        | 8040/57600 [1:24:56<8:33:33,  1.61it/s]
 14%|█▍        | 8041/57600 [1:24:57<8:46:46,  1.57it/s]
 14%|█▍        | 8042/57600 [1:24:57<8:35:41,  1.60it/s]
 14%|█▍        | 8043/57600 [1:24:58<8:23:05,  1.64it/s]
 14%|█▍        | 8044/57600 [1:24:59<8:09:57,  1.69it/s]
 14%|█▍        | 8045/57600 [1:24:59<8:25:55,  1.63it/s]
 14%|█▍        | 8046/57600 [1:25:00<8:46:37,  1.57it/s]
 14%|█▍        | 8047/57600 [1:25:01<8:49:18,  1.56it/s]
 14%|█▍        | 8048/57600 [1:25:01<8:39:35,  1.59it/s]
 14%|█▍        | 8049/57600 [1:25:02<8:31:13,  1.62it/s]
 14%|█▍        | 8050/57600 [1:25:02<8:44:36,  1.57it/s]
 14%|█▍        | 8051/57600 [1:25:03<8:33:24,  1.61it/s]
 14%|█▍        | 8052/57600 [1:25:04<8:33:24,  1.61it/s]
 14%|█▍        | 8053/57600 [1:25:04<8:18:18,  1.66it/s]
 14%|█▍        | 8054/57600 [1:25:05<8:34:39,  1.60it/s]
 14%|█▍        | 8055/57600 [1:25:06<8:34:01,  1.61it/s]
 14%|█▍        | 8056/57600 [1:25:06<8:22:48,  1.64it/s]
 14%|█▍        | 8057/57600 [1:25:07<8:25:17,  1.63it/s]
 14%|█▍        | 8058/57600 [1:25:07<8:27:11,  1.63it/s]
 14%|█▍        | 8059/57600 [1:25:08<8:18:53,  1.66it/s]
 14%|█▍        | 8060/57600 [1:25:09<8:08:39,  1.69it/s]
                                                        
{'loss': 1.4198, 'learning_rate': 8.767595818815331e-07, 'epoch': 88.96}

 14%|█▍        | 8060/57600 [1:25:09<8:08:39,  1.69it/s]
 14%|█▍        | 8061/57600 [1:25:09<8:17:23,  1.66it/s]
 14%|█▍        | 8062/57600 [1:25:10<8:34:52,  1.60it/s]
 14%|█▍        | 8063/57600 [1:25:10<8:31:16,  1.61it/s]
 14%|█▍        | 8064/57600 [1:25:11<8:42:26,  1.58it/s]
 14%|█▍        | 8065/57600 [1:25:12<8:51:14,  1.55it/s]
 14%|█▍        | 8066/57600 [1:25:12<8:40:22,  1.59it/s]
 14%|█▍        | 8067/57600 [1:25:13<8:32:06,  1.61it/s]
 14%|█▍        | 8068/57600 [1:25:14<8:37:13,  1.60it/s]
 14%|█▍        | 8069/57600 [1:25:14<8:21:51,  1.64it/s]
 14%|█▍        | 8070/57600 [1:25:15<8:09:12,  1.69it/s]
 14%|█▍        | 8071/57600 [1:25:15<8:11:22,  1.68it/s]
 14%|█▍        | 8072/57600 [1:25:16<8:43:38,  1.58it/s]
 14%|█▍        | 8073/57600 [1:25:17<8:35:01,  1.60it/s]
 14%|█▍        | 8074/57600 [1:25:17<8:53:31,  1.55it/s]
 14%|█▍        | 8075/57600 [1:25:18<8:34:01,  1.61it/s]
 14%|█▍        | 8076/57600 [1:25:18<8:21:31,  1.65it/s]
 14%|█▍        | 8077/57600 [1:25:19<8:10:47,  1.68it/s]
 14%|█▍        | 8078/57600 [1:25:20<8:17:21,  1.66it/s]
 14%|█▍        | 8079/57600 [1:25:20<8:19:45,  1.65it/s]
 14%|█▍        | 8080/57600 [1:25:21<8:20:50,  1.65it/s]
                                                        
{'loss': 1.4434, 'learning_rate': 8.764459930313588e-07, 'epoch': 89.18}

 14%|█▍        | 8080/57600 [1:25:21<8:20:50,  1.65it/s]
 14%|█▍        | 8081/57600 [1:25:22<8:28:38,  1.62it/s]
 14%|█▍        | 8082/57600 [1:25:22<8:40:16,  1.59it/s]
 14%|█▍        | 8083/57600 [1:25:23<8:43:24,  1.58it/s]
 14%|█▍        | 8084/57600 [1:25:23<8:38:30,  1.59it/s]
 14%|█▍        | 8085/57600 [1:25:24<9:00:26,  1.53it/s]
 14%|█▍        | 8086/57600 [1:25:25<8:51:05,  1.55it/s]
 14%|█▍        | 8087/57600 [1:25:25<8:47:28,  1.56it/s]
 14%|█▍        | 8088/57600 [1:25:26<9:02:48,  1.52it/s]
 14%|█▍        | 8089/57600 [1:25:27<8:44:42,  1.57it/s]
 14%|█▍        | 8090/57600 [1:25:27<8:39:17,  1.59it/s]
 14%|█▍        | 8091/57600 [1:25:28<8:30:04,  1.62it/s]
 14%|█▍        | 8092/57600 [1:25:29<8:28:10,  1.62it/s]
 14%|█▍        | 8093/57600 [1:25:29<8:23:59,  1.64it/s]
 14%|█▍        | 8094/57600 [1:25:30<8:20:45,  1.65it/s]
 14%|█▍        | 8095/57600 [1:25:30<8:12:29,  1.68it/s]
 14%|█▍        | 8096/57600 [1:25:31<8:11:02,  1.68it/s]
 14%|█▍        | 8097/57600 [1:25:32<8:25:47,  1.63it/s]
 14%|█▍        | 8098/57600 [1:25:32<8:21:18,  1.65it/s]
 14%|█▍        | 8099/57600 [1:25:33<8:07:24,  1.69it/s]
 14%|█▍        | 8100/57600 [1:25:33<8:32:34,  1.61it/s]
                                                        
{'loss': 1.4309, 'learning_rate': 8.761324041811848e-07, 'epoch': 89.4}

 14%|█▍        | 8100/57600 [1:25:33<8:32:34,  1.61it/s]
 14%|█▍        | 8101/57600 [1:25:34<8:36:41,  1.60it/s]
 14%|█▍        | 8102/57600 [1:25:35<8:35:19,  1.60it/s]
 14%|█▍        | 8103/57600 [1:25:35<8:58:26,  1.53it/s]
 14%|█▍        | 8104/57600 [1:25:36<8:44:45,  1.57it/s]
 14%|█▍        | 8105/57600 [1:25:37<8:27:21,  1.63it/s]
 14%|█▍        | 8106/57600 [1:25:37<8:44:22,  1.57it/s]
 14%|█▍        | 8107/57600 [1:25:38<8:51:54,  1.55it/s]
 14%|█▍        | 8108/57600 [1:25:38<8:36:40,  1.60it/s]
 14%|█▍        | 8109/57600 [1:25:39<8:27:19,  1.63it/s]
 14%|█▍        | 8110/57600 [1:25:40<8:18:08,  1.66it/s]
 14%|█▍        | 8111/57600 [1:25:40<8:15:33,  1.66it/s]
 14%|█▍        | 8112/57600 [1:25:41<8:26:36,  1.63it/s]
 14%|█▍        | 8113/57600 [1:25:41<8:30:24,  1.62it/s]
 14%|█▍        | 8114/57600 [1:25:42<8:24:12,  1.64it/s]
 14%|█▍        | 8115/57600 [1:25:43<8:41:11,  1.58it/s]
 14%|█▍        | 8116/57600 [1:25:43<8:20:57,  1.65it/s]
 14%|█▍        | 8117/57600 [1:25:44<8:22:42,  1.64it/s]
 14%|█▍        | 8118/57600 [1:25:45<8:22:57,  1.64it/s]
 14%|█▍        | 8119/57600 [1:25:45<8:11:24,  1.68it/s]
 14%|█▍        | 8120/57600 [1:25:46<8:23:44,  1.64it/s]
                                                        
{'loss': 1.3757, 'learning_rate': 8.758188153310104e-07, 'epoch': 89.62}

 14%|█▍        | 8120/57600 [1:25:46<8:23:44,  1.64it/s]
 14%|█▍        | 8121/57600 [1:25:46<8:12:35,  1.67it/s]
 14%|█▍        | 8122/57600 [1:25:47<8:07:42,  1.69it/s]
 14%|█▍        | 8123/57600 [1:25:48<8:20:09,  1.65it/s]
 14%|█▍        | 8124/57600 [1:25:48<8:15:37,  1.66it/s]
 14%|█▍        | 8125/57600 [1:25:49<8:23:30,  1.64it/s]
 14%|█▍        | 8126/57600 [1:25:49<8:25:52,  1.63it/s]
 14%|█▍        | 8127/57600 [1:25:50<8:23:32,  1.64it/s]
 14%|█▍        | 8128/57600 [1:25:51<8:24:50,  1.63it/s]
 14%|█▍        | 8129/57600 [1:25:51<8:16:44,  1.66it/s]
 14%|█▍        | 8130/57600 [1:25:52<8:17:48,  1.66it/s]
 14%|█▍        | 8131/57600 [1:25:52<8:37:57,  1.59it/s]
 14%|█▍        | 8132/57600 [1:25:53<8:32:42,  1.61it/s]
 14%|█▍        | 8133/57600 [1:25:54<8:24:42,  1.63it/s]
 14%|█▍        | 8134/57600 [1:25:54<8:20:44,  1.65it/s]
 14%|█▍        | 8135/57600 [1:25:55<8:16:33,  1.66it/s]
 14%|█▍        | 8136/57600 [1:25:55<8:25:17,  1.63it/s]
 14%|█▍        | 8137/57600 [1:25:56<8:31:33,  1.61it/s]
 14%|█▍        | 8138/57600 [1:25:57<8:30:40,  1.61it/s]
 14%|█▍        | 8139/57600 [1:25:57<8:42:39,  1.58it/s]
 14%|█▍        | 8140/57600 [1:25:58<8:44:15,  1.57it/s]
                                                        
{'loss': 1.479, 'learning_rate': 8.755052264808362e-07, 'epoch': 89.85}

 14%|█▍        | 8140/57600 [1:25:58<8:44:15,  1.57it/s]
 14%|█▍        | 8141/57600 [1:25:59<8:36:23,  1.60it/s]
 14%|█▍        | 8142/57600 [1:25:59<8:43:52,  1.57it/s]
 14%|█▍        | 8143/57600 [1:26:00<8:29:51,  1.62it/s]
 14%|█▍        | 8144/57600 [1:26:01<8:39:45,  1.59it/s]
 14%|█▍        | 8145/57600 [1:26:01<8:45:07,  1.57it/s]
 14%|█▍        | 8146/57600 [1:26:02<8:51:19,  1.55it/s]
 14%|█▍        | 8147/57600 [1:26:03<9:21:18,  1.47it/s]
 14%|█▍        | 8148/57600 [1:26:03<9:05:17,  1.51it/s]
 14%|█▍        | 8149/57600 [1:26:04<8:59:43,  1.53it/s]
 14%|█▍        | 8150/57600 [1:26:04<8:50:22,  1.55it/s]
 14%|█▍        | 8151/57600 [1:26:05<8:59:46,  1.53it/s]
 14%|█▍        | 8152/57600 [1:26:06<8:52:20,  1.55it/s]
 14%|█▍        | 8153/57600 [1:26:06<8:48:25,  1.56it/s]
 14%|█▍        | 8154/57600 [1:26:07<8:36:12,  1.60it/s]
 14%|█▍        | 8155/57600 [1:26:08<8:44:57,  1.57it/s]
 14%|█▍        | 8156/57600 [1:26:08<8:38:20,  1.59it/s]
 14%|█▍        | 8157/57600 [1:26:09<8:32:08,  1.61it/s]
 14%|█▍        | 8158/57600 [1:26:10<8:29:10,  1.62it/s]
 14%|█▍        | 8159/57600 [1:26:10<8:23:58,  1.64it/s]
 14%|█▍        | 8160/57600 [1:26:11<8:43:39,  1.57it/s]
                                                        
{'loss': 1.3926, 'learning_rate': 8.751916376306619e-07, 'epoch': 90.07}

 14%|█▍        | 8160/57600 [1:26:11<8:43:39,  1.57it/s]
 14%|█▍        | 8161/57600 [1:26:11<8:53:00,  1.55it/s]
 14%|█▍        | 8162/57600 [1:26:12<8:32:24,  1.61it/s]
 14%|█▍        | 8163/57600 [1:26:13<8:32:46,  1.61it/s]
 14%|█▍        | 8164/57600 [1:26:13<8:20:14,  1.65it/s]
 14%|█▍        | 8165/57600 [1:26:14<8:05:26,  1.70it/s]
 14%|█▍        | 8166/57600 [1:26:14<8:01:31,  1.71it/s]
 14%|█▍        | 8167/57600 [1:26:15<8:14:57,  1.66it/s]
 14%|█▍        | 8168/57600 [1:26:16<8:47:02,  1.56it/s]
 14%|█▍        | 8169/57600 [1:26:16<8:35:29,  1.60it/s]
 14%|█▍        | 8170/57600 [1:26:17<8:31:23,  1.61it/s]
 14%|█▍        | 8171/57600 [1:26:18<8:36:53,  1.59it/s]
 14%|█▍        | 8172/57600 [1:26:18<8:25:32,  1.63it/s]
 14%|█▍        | 8173/57600 [1:26:19<8:09:00,  1.68it/s]
 14%|█▍        | 8174/57600 [1:26:19<8:11:36,  1.68it/s]
 14%|█▍        | 8175/57600 [1:26:20<8:10:22,  1.68it/s]
 14%|█▍        | 8176/57600 [1:26:20<8:09:59,  1.68it/s]
 14%|█▍        | 8177/57600 [1:26:21<8:25:54,  1.63it/s]
 14%|█▍        | 8178/57600 [1:26:22<8:36:08,  1.60it/s]
 14%|█▍        | 8179/57600 [1:26:22<8:29:23,  1.62it/s]
 14%|█▍        | 8180/57600 [1:26:23<8:22:30,  1.64it/s]
                                                        
{'loss': 1.4629, 'learning_rate': 8.748780487804878e-07, 'epoch': 90.29}

 14%|█▍        | 8180/57600 [1:26:23<8:22:30,  1.64it/s]
 14%|█▍        | 8181/57600 [1:26:24<8:28:24,  1.62it/s]
 14%|█▍        | 8182/57600 [1:26:24<8:29:13,  1.62it/s]
 14%|█▍        | 8183/57600 [1:26:25<8:20:56,  1.64it/s]
 14%|█▍        | 8184/57600 [1:26:25<8:29:04,  1.62it/s]
 14%|█▍        | 8185/57600 [1:26:26<8:38:45,  1.59it/s]
 14%|█▍        | 8186/57600 [1:26:27<8:21:13,  1.64it/s]
 14%|█▍        | 8187/57600 [1:26:27<8:18:35,  1.65it/s]
 14%|█▍        | 8188/57600 [1:26:28<8:20:08,  1.65it/s]
 14%|█▍        | 8189/57600 [1:26:28<8:10:32,  1.68it/s]
 14%|█▍        | 8190/57600 [1:26:29<8:35:13,  1.60it/s]
 14%|█▍        | 8191/57600 [1:26:30<8:43:26,  1.57it/s]
 14%|█▍        | 8192/57600 [1:26:30<8:34:45,  1.60it/s]
 14%|█▍        | 8193/57600 [1:26:31<8:32:42,  1.61it/s]
 14%|█▍        | 8194/57600 [1:26:32<8:27:05,  1.62it/s]
 14%|█▍        | 8195/57600 [1:26:32<8:36:02,  1.60it/s]
 14%|█▍        | 8196/57600 [1:26:33<8:34:05,  1.60it/s]
 14%|█▍        | 8197/57600 [1:26:34<8:29:24,  1.62it/s]
 14%|█▍        | 8198/57600 [1:26:34<8:43:19,  1.57it/s]
 14%|█▍        | 8199/57600 [1:26:35<8:40:18,  1.58it/s]
 14%|█▍        | 8200/57600 [1:26:35<8:35:11,  1.60it/s]
                                                        
{'loss': 1.3793, 'learning_rate': 8.745644599303135e-07, 'epoch': 90.51}

 14%|█▍        | 8200/57600 [1:26:35<8:35:11,  1.60it/s]
 14%|█▍        | 8201/57600 [1:26:36<8:39:53,  1.58it/s]
 14%|█▍        | 8202/57600 [1:26:37<8:42:51,  1.57it/s]
 14%|█▍        | 8203/57600 [1:26:37<8:50:42,  1.55it/s]
 14%|█▍        | 8204/57600 [1:26:38<8:38:10,  1.59it/s]
 14%|█▍        | 8205/57600 [1:26:39<8:27:01,  1.62it/s]
 14%|█▍        | 8206/57600 [1:26:39<8:39:09,  1.59it/s]
 14%|█▍        | 8207/57600 [1:26:40<8:39:17,  1.59it/s]
 14%|█▍        | 8208/57600 [1:26:40<8:37:11,  1.59it/s]
 14%|█▍        | 8209/57600 [1:26:41<8:47:09,  1.56it/s]
 14%|█▍        | 8210/57600 [1:26:42<8:33:27,  1.60it/s]
 14%|█▍        | 8211/57600 [1:26:42<8:30:59,  1.61it/s]
 14%|█▍        | 8212/57600 [1:26:43<8:17:39,  1.65it/s]
 14%|█▍        | 8213/57600 [1:26:44<8:25:17,  1.63it/s]
 14%|█▍        | 8214/57600 [1:26:44<8:24:08,  1.63it/s]
 14%|█▍        | 8215/57600 [1:26:45<8:18:35,  1.65it/s]
 14%|█▍        | 8216/57600 [1:26:45<8:19:13,  1.65it/s]
 14%|█▍        | 8217/57600 [1:26:46<8:10:10,  1.68it/s]
 14%|█▍        | 8218/57600 [1:26:46<8:01:20,  1.71it/s]
 14%|█▍        | 8219/57600 [1:26:47<8:27:53,  1.62it/s]
 14%|█▍        | 8220/57600 [1:26:48<8:34:48,  1.60it/s]
                                                        
{'loss': 1.4113, 'learning_rate': 8.742508710801393e-07, 'epoch': 90.73}

 14%|█▍        | 8220/57600 [1:26:48<8:34:48,  1.60it/s]
 14%|█▍        | 8221/57600 [1:26:49<8:49:46,  1.55it/s]
 14%|█▍        | 8222/57600 [1:26:49<8:58:54,  1.53it/s]
 14%|█▍        | 8223/57600 [1:26:50<8:55:47,  1.54it/s]
 14%|█▍        | 8224/57600 [1:26:50<8:55:23,  1.54it/s]
 14%|█▍        | 8225/57600 [1:26:51<8:53:10,  1.54it/s]
 14%|█▍        | 8226/57600 [1:26:52<8:39:35,  1.58it/s]
 14%|█▍        | 8227/57600 [1:26:52<8:38:24,  1.59it/s]
 14%|█▍        | 8228/57600 [1:26:53<8:42:08,  1.58it/s]
 14%|█▍        | 8229/57600 [1:26:54<8:42:55,  1.57it/s]
 14%|█▍        | 8230/57600 [1:26:54<8:27:27,  1.62it/s]
 14%|█▍        | 8231/57600 [1:26:55<8:28:23,  1.62it/s]
 14%|█▍        | 8232/57600 [1:26:55<8:16:31,  1.66it/s]
 14%|█▍        | 8233/57600 [1:26:56<8:16:14,  1.66it/s]
 14%|█▍        | 8234/57600 [1:26:57<8:33:51,  1.60it/s]
 14%|█▍        | 8235/57600 [1:26:57<8:35:39,  1.60it/s]
 14%|█▍        | 8236/57600 [1:26:58<8:33:11,  1.60it/s]
 14%|█▍        | 8237/57600 [1:26:59<8:37:15,  1.59it/s]
 14%|█▍        | 8238/57600 [1:26:59<8:24:59,  1.63it/s]
 14%|█▍        | 8239/57600 [1:27:00<8:14:45,  1.66it/s]
 14%|█▍        | 8240/57600 [1:27:00<8:11:07,  1.68it/s]
                                                        
{'loss': 1.4187, 'learning_rate': 8.739372822299651e-07, 'epoch': 90.95}

 14%|█▍        | 8240/57600 [1:27:00<8:11:07,  1.68it/s]
 14%|█▍        | 8241/57600 [1:27:01<8:33:28,  1.60it/s]
 14%|█▍        | 8242/57600 [1:27:02<8:17:21,  1.65it/s]
 14%|█▍        | 8243/57600 [1:27:02<8:06:36,  1.69it/s]
 14%|█▍        | 8244/57600 [1:27:03<8:10:20,  1.68it/s]
 14%|█▍        | 8245/57600 [1:27:03<8:51:51,  1.55it/s]
 14%|█▍        | 8246/57600 [1:27:04<8:55:20,  1.54it/s]
 14%|█▍        | 8247/57600 [1:27:05<8:57:37,  1.53it/s]
 14%|█▍        | 8248/57600 [1:27:05<8:34:22,  1.60it/s]
 14%|█▍        | 8249/57600 [1:27:06<8:34:15,  1.60it/s]
 14%|█▍        | 8250/57600 [1:27:07<8:29:26,  1.61it/s]
 14%|█▍        | 8251/57600 [1:27:07<8:40:10,  1.58it/s]
 14%|█▍        | 8252/57600 [1:27:08<9:00:26,  1.52it/s]
 14%|█▍        | 8253/57600 [1:27:09<8:44:22,  1.57it/s]
 14%|█▍        | 8254/57600 [1:27:09<8:46:48,  1.56it/s]
 14%|█▍        | 8255/57600 [1:27:10<8:43:24,  1.57it/s]
 14%|█▍        | 8256/57600 [1:27:10<8:33:19,  1.60it/s]
 14%|█▍        | 8257/57600 [1:27:11<8:28:25,  1.62it/s]
 14%|█▍        | 8258/57600 [1:27:12<8:31:15,  1.61it/s]
 14%|█▍        | 8259/57600 [1:27:12<8:26:46,  1.62it/s]
 14%|█▍        | 8260/57600 [1:27:13<8:12:29,  1.67it/s]
                                                        
{'loss': 1.4466, 'learning_rate': 8.73623693379791e-07, 'epoch': 91.17}

 14%|█▍        | 8260/57600 [1:27:13<8:12:29,  1.67it/s]
 14%|█▍        | 8261/57600 [1:27:13<8:15:46,  1.66it/s]
 14%|█▍        | 8262/57600 [1:27:14<8:13:25,  1.67it/s]
 14%|█▍        | 8263/57600 [1:27:15<8:04:12,  1.70it/s]
 14%|█▍        | 8264/57600 [1:27:15<8:29:21,  1.61it/s]
 14%|█▍        | 8265/57600 [1:27:16<8:30:15,  1.61it/s]
 14%|█▍        | 8266/57600 [1:27:17<8:29:12,  1.61it/s]
 14%|█▍        | 8267/57600 [1:27:17<8:41:51,  1.58it/s]
 14%|█▍        | 8268/57600 [1:27:18<8:44:12,  1.57it/s]
 14%|█▍        | 8269/57600 [1:27:18<8:26:58,  1.62it/s]
 14%|█▍        | 8270/57600 [1:27:19<8:21:19,  1.64it/s]
 14%|█▍        | 8271/57600 [1:27:20<8:29:38,  1.61it/s]
 14%|█▍        | 8272/57600 [1:27:20<8:32:35,  1.60it/s]
 14%|█▍        | 8273/57600 [1:27:21<8:33:52,  1.60it/s]
 14%|█▍        | 8274/57600 [1:27:21<8:18:41,  1.65it/s]
 14%|█▍        | 8275/57600 [1:27:22<8:33:10,  1.60it/s]
 14%|█▍        | 8276/57600 [1:27:23<8:42:44,  1.57it/s]
 14%|█▍        | 8277/57600 [1:27:23<8:37:40,  1.59it/s]
 14%|█▍        | 8278/57600 [1:27:24<8:33:10,  1.60it/s]
 14%|█▍        | 8279/57600 [1:27:25<8:32:52,  1.60it/s]
 14%|█▍        | 8280/57600 [1:27:25<8:34:28,  1.60it/s]
                                                        
{'loss': 1.4219, 'learning_rate': 8.733101045296167e-07, 'epoch': 91.39}

 14%|█▍        | 8280/57600 [1:27:25<8:34:28,  1.60it/s]
 14%|█▍        | 8281/57600 [1:27:26<8:30:33,  1.61it/s]
 14%|█▍        | 8282/57600 [1:27:26<8:28:49,  1.62it/s]
 14%|█▍        | 8283/57600 [1:27:27<8:19:31,  1.65it/s]
 14%|█▍        | 8284/57600 [1:27:28<8:17:34,  1.65it/s]
 14%|█▍        | 8285/57600 [1:27:28<8:30:59,  1.61it/s]
 14%|█▍        | 8286/57600 [1:27:29<8:25:58,  1.62it/s]
 14%|█▍        | 8287/57600 [1:27:29<8:12:21,  1.67it/s]
 14%|█▍        | 8288/57600 [1:27:30<8:23:21,  1.63it/s]
 14%|█▍        | 8289/57600 [1:27:31<8:07:44,  1.69it/s]
 14%|█▍        | 8290/57600 [1:27:31<8:09:41,  1.68it/s]
 14%|█▍        | 8291/57600 [1:27:32<8:21:19,  1.64it/s]
 14%|█▍        | 8292/57600 [1:27:33<8:26:43,  1.62it/s]
 14%|█▍        | 8293/57600 [1:27:33<8:11:33,  1.67it/s]
 14%|█▍        | 8294/57600 [1:27:34<8:01:53,  1.71it/s]
 14%|█▍        | 8295/57600 [1:27:34<7:54:26,  1.73it/s]
 14%|█▍        | 8296/57600 [1:27:35<7:50:10,  1.75it/s]
 14%|█▍        | 8297/57600 [1:27:35<7:52:08,  1.74it/s]
 14%|█▍        | 8298/57600 [1:27:36<8:11:04,  1.67it/s]
 14%|█▍        | 8299/57600 [1:27:37<8:03:07,  1.70it/s]
 14%|█▍        | 8300/57600 [1:27:37<8:20:36,  1.64it/s]
                                                        
{'loss': 1.4783, 'learning_rate': 8.729965156794424e-07, 'epoch': 91.61}

 14%|█▍        | 8300/57600 [1:27:37<8:20:36,  1.64it/s]
 14%|█▍        | 8301/57600 [1:27:38<8:24:52,  1.63it/s]
 14%|█▍        | 8302/57600 [1:27:38<8:21:34,  1.64it/s]
 14%|█▍        | 8303/57600 [1:27:39<8:35:49,  1.59it/s]
 14%|█▍        | 8304/57600 [1:27:40<8:32:33,  1.60it/s]
 14%|█▍        | 8305/57600 [1:27:40<8:26:51,  1.62it/s]
 14%|█▍        | 8306/57600 [1:27:41<8:31:52,  1.61it/s]
 14%|█▍        | 8307/57600 [1:27:42<8:37:48,  1.59it/s]
 14%|█▍        | 8308/57600 [1:27:42<8:27:22,  1.62it/s]
 14%|█▍        | 8309/57600 [1:27:43<8:42:32,  1.57it/s]
 14%|█▍        | 8310/57600 [1:27:43<8:27:02,  1.62it/s]
 14%|█▍        | 8311/57600 [1:27:44<8:30:52,  1.61it/s]
 14%|█▍        | 8312/57600 [1:27:45<8:16:59,  1.65it/s]
 14%|█▍        | 8313/57600 [1:27:45<8:19:44,  1.64it/s]
 14%|█▍        | 8314/57600 [1:27:46<8:22:51,  1.63it/s]
 14%|█▍        | 8315/57600 [1:27:47<8:16:43,  1.65it/s]
 14%|█▍        | 8316/57600 [1:27:47<8:10:12,  1.68it/s]
 14%|█▍        | 8317/57600 [1:27:48<8:47:59,  1.56it/s]
 14%|█▍        | 8318/57600 [1:27:48<8:32:55,  1.60it/s]
 14%|█▍        | 8319/57600 [1:27:49<8:26:25,  1.62it/s]
 14%|█▍        | 8320/57600 [1:27:50<8:27:15,  1.62it/s]
                                                        
{'loss': 1.4111, 'learning_rate': 8.726829268292683e-07, 'epoch': 91.83}

 14%|█▍        | 8320/57600 [1:27:50<8:27:15,  1.62it/s]
 14%|█▍        | 8321/57600 [1:27:50<8:37:53,  1.59it/s]
 14%|█▍        | 8322/57600 [1:27:51<8:29:19,  1.61it/s]
 14%|█▍        | 8323/57600 [1:27:51<8:19:23,  1.64it/s]
 14%|█▍        | 8324/57600 [1:27:52<8:16:02,  1.66it/s]
 14%|█▍        | 8325/57600 [1:27:53<8:22:09,  1.64it/s]
 14%|█▍        | 8326/57600 [1:27:53<8:27:01,  1.62it/s]
 14%|█▍        | 8327/57600 [1:27:54<8:39:56,  1.58it/s]
 14%|█▍        | 8328/57600 [1:27:55<8:35:05,  1.59it/s]
 14%|█▍        | 8329/57600 [1:27:55<8:29:04,  1.61it/s]
 14%|█▍        | 8330/57600 [1:27:56<8:45:14,  1.56it/s]
 14%|█▍        | 8331/57600 [1:27:56<8:23:08,  1.63it/s]
 14%|█▍        | 8332/57600 [1:27:57<8:39:38,  1.58it/s]
 14%|█▍        | 8333/57600 [1:27:58<8:39:13,  1.58it/s]
 14%|█▍        | 8334/57600 [1:27:58<8:27:02,  1.62it/s]
 14%|█▍        | 8335/57600 [1:27:59<8:59:24,  1.52it/s]
 14%|█▍        | 8336/57600 [1:28:00<9:07:57,  1.50it/s]
 14%|█▍        | 8337/57600 [1:28:00<8:56:57,  1.53it/s]
 14%|█▍        | 8338/57600 [1:28:01<9:07:41,  1.50it/s]
 14%|█▍        | 8339/57600 [1:28:02<8:51:15,  1.55it/s]
 14%|█▍        | 8340/57600 [1:28:02<8:33:34,  1.60it/s]
                                                        
{'loss': 1.427, 'learning_rate': 8.723693379790941e-07, 'epoch': 92.05}

 14%|█▍        | 8340/57600 [1:28:02<8:33:34,  1.60it/s]
 14%|█▍        | 8341/57600 [1:28:03<8:48:25,  1.55it/s]
 14%|█▍        | 8342/57600 [1:28:04<8:33:30,  1.60it/s]
 14%|█▍        | 8343/57600 [1:28:04<8:24:54,  1.63it/s]
 14%|█▍        | 8344/57600 [1:28:05<8:36:15,  1.59it/s]
 14%|█▍        | 8345/57600 [1:28:05<8:44:43,  1.56it/s]
 14%|█▍        | 8346/57600 [1:28:06<8:38:54,  1.58it/s]
 14%|█▍        | 8347/57600 [1:28:07<8:37:20,  1.59it/s]
 14%|█▍        | 8348/57600 [1:28:07<8:41:35,  1.57it/s]
 14%|█▍        | 8349/57600 [1:28:08<8:48:24,  1.55it/s]
 14%|█▍        | 8350/57600 [1:28:09<8:40:53,  1.58it/s]
 14%|█▍        | 8351/57600 [1:28:09<8:31:51,  1.60it/s]
 14%|█▍        | 8352/57600 [1:28:10<8:25:16,  1.62it/s]
 15%|█▍        | 8353/57600 [1:28:10<8:30:46,  1.61it/s]
 15%|█▍        | 8354/57600 [1:28:11<8:29:48,  1.61it/s]
 15%|█▍        | 8355/57600 [1:28:12<8:43:27,  1.57it/s]
 15%|█▍        | 8356/57600 [1:28:12<8:16:22,  1.65it/s]
 15%|█▍        | 8357/57600 [1:28:13<8:08:53,  1.68it/s]
 15%|█▍        | 8358/57600 [1:28:13<8:11:10,  1.67it/s]
 15%|█▍        | 8359/57600 [1:28:14<8:11:25,  1.67it/s]
 15%|█▍        | 8360/57600 [1:28:15<8:29:21,  1.61it/s]
                                                        
{'loss': 1.414, 'learning_rate': 8.720557491289198e-07, 'epoch': 92.27}

 15%|█▍        | 8360/57600 [1:28:15<8:29:21,  1.61it/s]
 15%|█▍        | 8361/57600 [1:28:15<8:18:04,  1.65it/s]
 15%|█▍        | 8362/57600 [1:28:16<8:09:15,  1.68it/s]
 15%|█▍        | 8363/57600 [1:28:16<8:00:18,  1.71it/s]
 15%|█▍        | 8364/57600 [1:28:17<8:12:45,  1.67it/s]
 15%|█▍        | 8365/57600 [1:28:18<8:37:38,  1.59it/s]
 15%|█▍        | 8366/57600 [1:28:18<8:27:07,  1.62it/s]
 15%|█▍        | 8367/57600 [1:28:19<8:15:32,  1.66it/s]
 15%|█▍        | 8368/57600 [1:28:19<8:02:47,  1.70it/s]
 15%|█▍        | 8369/57600 [1:28:20<8:01:32,  1.70it/s]
 15%|█▍        | 8370/57600 [1:28:21<8:10:57,  1.67it/s]
 15%|█▍        | 8371/57600 [1:28:21<8:23:12,  1.63it/s]
 15%|█▍        | 8372/57600 [1:28:22<8:36:12,  1.59it/s]
 15%|█▍        | 8373/57600 [1:28:23<8:41:02,  1.57it/s]
 15%|█▍        | 8374/57600 [1:28:23<8:28:52,  1.61it/s]
 15%|█▍        | 8375/57600 [1:28:24<8:06:54,  1.68it/s]
 15%|█▍        | 8376/57600 [1:28:24<8:20:37,  1.64it/s]
 15%|█▍        | 8377/57600 [1:28:25<8:34:51,  1.59it/s]
 15%|█▍        | 8378/57600 [1:28:26<8:28:45,  1.61it/s]
 15%|█▍        | 8379/57600 [1:28:26<8:38:38,  1.58it/s]
 15%|█▍        | 8380/57600 [1:28:27<8:54:07,  1.54it/s]
                                                        
{'loss': 1.4097, 'learning_rate': 8.717421602787456e-07, 'epoch': 92.49}

 15%|█▍        | 8380/57600 [1:28:27<8:54:07,  1.54it/s]
 15%|█▍        | 8381/57600 [1:28:28<8:32:12,  1.60it/s]
 15%|█▍        | 8382/57600 [1:28:28<8:19:05,  1.64it/s]
 15%|█▍        | 8383/57600 [1:28:29<8:09:24,  1.68it/s]
 15%|█▍        | 8384/57600 [1:28:29<8:04:20,  1.69it/s]
 15%|█▍        | 8385/57600 [1:28:30<8:00:03,  1.71it/s]
 15%|█▍        | 8386/57600 [1:28:31<8:11:11,  1.67it/s]
 15%|█▍        | 8387/57600 [1:28:31<8:19:41,  1.64it/s]
 15%|█▍        | 8388/57600 [1:28:32<8:18:19,  1.65it/s]
 15%|█▍        | 8389/57600 [1:28:32<8:17:24,  1.65it/s]
 15%|█▍        | 8390/57600 [1:28:33<8:13:24,  1.66it/s]
 15%|█▍        | 8391/57600 [1:28:34<8:12:14,  1.67it/s]
 15%|█▍        | 8392/57600 [1:28:34<8:13:28,  1.66it/s]
 15%|█▍        | 8393/57600 [1:28:35<8:23:05,  1.63it/s]
 15%|█▍        | 8394/57600 [1:28:35<8:19:04,  1.64it/s]
 15%|█▍        | 8395/57600 [1:28:36<8:17:50,  1.65it/s]
 15%|█▍        | 8396/57600 [1:28:37<8:19:09,  1.64it/s]
 15%|█▍        | 8397/57600 [1:28:37<8:17:48,  1.65it/s]
 15%|█▍        | 8398/57600 [1:28:38<8:31:46,  1.60it/s]
 15%|█▍        | 8399/57600 [1:28:39<8:28:26,  1.61it/s]
 15%|█▍        | 8400/57600 [1:28:39<8:22:35,  1.63it/s]
                                                        
{'loss': 1.4818, 'learning_rate': 8.714285714285715e-07, 'epoch': 92.72}

 15%|█▍        | 8400/57600 [1:28:39<8:22:35,  1.63it/s]
 15%|█▍        | 8401/57600 [1:28:40<8:26:30,  1.62it/s]
 15%|█▍        | 8402/57600 [1:28:40<8:18:28,  1.64it/s]
 15%|█▍        | 8403/57600 [1:28:41<8:29:46,  1.61it/s]
 15%|█▍        | 8404/57600 [1:28:42<8:29:22,  1.61it/s]
 15%|█▍        | 8405/57600 [1:28:42<8:48:01,  1.55it/s]
 15%|█▍        | 8406/57600 [1:28:43<8:57:58,  1.52it/s]
 15%|█▍        | 8407/57600 [1:28:44<8:30:34,  1.61it/s]
 15%|█▍        | 8408/57600 [1:28:44<8:42:52,  1.57it/s]
 15%|█▍        | 8409/57600 [1:28:45<8:34:22,  1.59it/s]
 15%|█▍        | 8410/57600 [1:28:45<8:32:16,  1.60it/s]
 15%|█▍        | 8411/57600 [1:28:46<8:50:33,  1.55it/s]
 15%|█▍        | 8412/57600 [1:28:47<8:47:28,  1.55it/s]
 15%|█▍        | 8413/57600 [1:28:47<8:45:21,  1.56it/s]
 15%|█▍        | 8414/57600 [1:28:48<8:49:05,  1.55it/s]
 15%|█▍        | 8415/57600 [1:28:49<8:31:37,  1.60it/s]
 15%|█▍        | 8416/57600 [1:28:49<8:25:12,  1.62it/s]
 15%|█▍        | 8417/57600 [1:28:50<8:40:47,  1.57it/s]
 15%|█▍        | 8418/57600 [1:28:51<8:52:01,  1.54it/s]
 15%|█▍        | 8419/57600 [1:28:51<8:51:04,  1.54it/s]
 15%|█▍        | 8420/57600 [1:28:52<8:40:40,  1.57it/s]
                                                        
{'loss': 1.4127, 'learning_rate': 8.711149825783971e-07, 'epoch': 92.94}

 15%|█▍        | 8420/57600 [1:28:52<8:40:40,  1.57it/s]
 15%|█▍        | 8421/57600 [1:28:52<8:43:01,  1.57it/s]
 15%|█▍        | 8422/57600 [1:28:53<8:33:35,  1.60it/s]
 15%|█▍        | 8423/57600 [1:28:54<8:50:05,  1.55it/s]
 15%|█▍        | 8424/57600 [1:28:54<8:36:33,  1.59it/s]
 15%|█▍        | 8425/57600 [1:28:55<8:27:50,  1.61it/s]
 15%|█▍        | 8426/57600 [1:28:56<8:38:01,  1.58it/s]
 15%|█▍        | 8427/57600 [1:28:56<8:39:24,  1.58it/s]
 15%|█▍        | 8428/57600 [1:28:57<8:40:18,  1.58it/s]
 15%|█▍        | 8429/57600 [1:28:57<8:30:38,  1.60it/s]
 15%|█▍        | 8430/57600 [1:28:58<8:22:55,  1.63it/s]
 15%|█▍        | 8431/57600 [1:28:59<8:18:13,  1.64it/s]
 15%|█▍        | 8432/57600 [1:28:59<8:16:50,  1.65it/s]
 15%|█▍        | 8433/57600 [1:29:00<8:15:04,  1.66it/s]
 15%|█▍        | 8434/57600 [1:29:00<8:20:54,  1.64it/s]
 15%|█▍        | 8435/57600 [1:29:01<8:25:26,  1.62it/s]
 15%|█▍        | 8436/57600 [1:29:02<8:35:06,  1.59it/s]
 15%|█▍        | 8437/57600 [1:29:02<8:51:09,  1.54it/s]
 15%|█▍        | 8438/57600 [1:29:03<8:32:51,  1.60it/s]
 15%|█▍        | 8439/57600 [1:29:04<8:28:08,  1.61it/s]
 15%|█▍        | 8440/57600 [1:29:04<8:15:34,  1.65it/s]
                                                        
{'loss': 1.4264, 'learning_rate': 8.708013937282229e-07, 'epoch': 93.16}

 15%|█▍        | 8440/57600 [1:29:04<8:15:34,  1.65it/s]
 15%|█▍        | 8441/57600 [1:29:05<8:11:10,  1.67it/s]
 15%|█▍        | 8442/57600 [1:29:05<8:16:08,  1.65it/s]
 15%|█▍        | 8443/57600 [1:29:06<8:21:29,  1.63it/s]
 15%|█▍        | 8444/57600 [1:29:07<8:26:00,  1.62it/s]
 15%|█▍        | 8445/57600 [1:29:07<8:09:23,  1.67it/s]
 15%|█▍        | 8446/57600 [1:29:08<8:26:04,  1.62it/s]
 15%|█▍        | 8447/57600 [1:29:09<8:23:20,  1.63it/s]
 15%|█▍        | 8448/57600 [1:29:09<8:27:25,  1.61it/s]
 15%|█▍        | 8449/57600 [1:29:10<8:26:58,  1.62it/s]
 15%|█▍        | 8450/57600 [1:29:10<8:19:32,  1.64it/s]
 15%|█▍        | 8451/57600 [1:29:11<8:15:47,  1.65it/s]
 15%|█▍        | 8452/57600 [1:29:12<8:12:35,  1.66it/s]
 15%|█▍        | 8453/57600 [1:29:12<8:17:11,  1.65it/s]
 15%|█▍        | 8454/57600 [1:29:13<8:09:56,  1.67it/s]
 15%|█▍        | 8455/57600 [1:29:13<8:06:58,  1.68it/s]
 15%|█▍        | 8456/57600 [1:29:14<8:17:08,  1.65it/s]
 15%|█▍        | 8457/57600 [1:29:15<8:11:23,  1.67it/s]
 15%|█▍        | 8458/57600 [1:29:15<8:18:48,  1.64it/s]
 15%|█▍        | 8459/57600 [1:29:16<8:17:47,  1.65it/s]
 15%|█▍        | 8460/57600 [1:29:16<8:11:41,  1.67it/s]
                                                        
{'loss': 1.4663, 'learning_rate': 8.704878048780487e-07, 'epoch': 93.38}

 15%|█▍        | 8460/57600 [1:29:16<8:11:41,  1.67it/s]
 15%|█▍        | 8461/57600 [1:29:17<8:07:30,  1.68it/s]
 15%|█▍        | 8462/57600 [1:29:18<8:37:49,  1.58it/s]
 15%|█▍        | 8463/57600 [1:29:18<8:42:39,  1.57it/s]
 15%|█▍        | 8464/57600 [1:29:19<8:38:27,  1.58it/s]
 15%|█▍        | 8465/57600 [1:29:20<8:32:31,  1.60it/s]
 15%|█▍        | 8466/57600 [1:29:20<8:40:13,  1.57it/s]
 15%|█▍        | 8467/57600 [1:29:21<8:49:21,  1.55it/s]
 15%|█▍        | 8468/57600 [1:29:22<8:49:35,  1.55it/s]
 15%|█▍        | 8469/57600 [1:29:22<8:31:44,  1.60it/s]
 15%|█▍        | 8470/57600 [1:29:23<8:18:38,  1.64it/s]
 15%|█▍        | 8471/57600 [1:29:23<8:34:58,  1.59it/s]
 15%|█▍        | 8472/57600 [1:29:24<8:45:01,  1.56it/s]
 15%|█▍        | 8473/57600 [1:29:25<8:51:52,  1.54it/s]
 15%|█▍        | 8474/57600 [1:29:25<8:37:02,  1.58it/s]
 15%|█▍        | 8475/57600 [1:29:26<8:36:23,  1.59it/s]
 15%|█▍        | 8476/57600 [1:29:27<8:51:58,  1.54it/s]
 15%|█▍        | 8477/57600 [1:29:27<8:45:29,  1.56it/s]
 15%|█▍        | 8478/57600 [1:29:28<8:50:46,  1.54it/s]
 15%|█▍        | 8479/57600 [1:29:28<8:34:29,  1.59it/s]
 15%|█▍        | 8480/57600 [1:29:29<8:34:21,  1.59it/s]
                                                        
{'loss': 1.4151, 'learning_rate': 8.701742160278746e-07, 'epoch': 93.6}

 15%|█▍        | 8480/57600 [1:29:29<8:34:21,  1.59it/s]
 15%|█▍        | 8481/57600 [1:29:30<8:24:57,  1.62it/s]
 15%|█▍        | 8482/57600 [1:29:30<8:24:15,  1.62it/s]
 15%|█▍        | 8483/57600 [1:29:31<8:11:45,  1.66it/s]
 15%|█▍        | 8484/57600 [1:29:32<8:32:16,  1.60it/s]
 15%|█▍        | 8485/57600 [1:29:32<8:23:16,  1.63it/s]
 15%|█▍        | 8486/57600 [1:29:33<8:19:24,  1.64it/s]
 15%|█▍        | 8487/57600 [1:29:33<8:07:41,  1.68it/s]
 15%|█▍        | 8488/57600 [1:29:34<8:07:03,  1.68it/s]
 15%|█▍        | 8489/57600 [1:29:35<8:22:51,  1.63it/s]
 15%|█▍        | 8490/57600 [1:29:35<8:23:35,  1.63it/s]
 15%|█▍        | 8491/57600 [1:29:36<8:14:27,  1.66it/s]
 15%|█▍        | 8492/57600 [1:29:36<8:27:25,  1.61it/s]
 15%|█▍        | 8493/57600 [1:29:37<8:12:08,  1.66it/s]
 15%|█▍        | 8494/57600 [1:29:38<8:21:43,  1.63it/s]
 15%|█▍        | 8495/57600 [1:29:38<8:36:41,  1.58it/s]
 15%|█▍        | 8496/57600 [1:29:39<8:36:17,  1.59it/s]
 15%|█▍        | 8497/57600 [1:29:39<8:24:24,  1.62it/s]
 15%|█▍        | 8498/57600 [1:29:40<8:22:44,  1.63it/s]
 15%|█▍        | 8499/57600 [1:29:41<8:18:21,  1.64it/s]
 15%|█▍        | 8500/57600 [1:29:41<8:10:05,  1.67it/s]
                                                        
{'loss': 1.4362, 'learning_rate': 8.698606271777002e-07, 'epoch': 93.82}

 15%|█▍        | 8500/57600 [1:29:41<8:10:05,  1.67it/s]
 15%|█▍        | 8501/57600 [1:29:42<8:24:23,  1.62it/s]
 15%|█▍        | 8502/57600 [1:29:43<8:29:08,  1.61it/s]
 15%|█▍        | 8503/57600 [1:29:43<8:27:19,  1.61it/s]
 15%|█▍        | 8504/57600 [1:29:44<8:11:12,  1.67it/s]
 15%|█▍        | 8505/57600 [1:29:44<8:07:20,  1.68it/s]
 15%|█▍        | 8506/57600 [1:29:45<8:45:04,  1.56it/s]
 15%|█▍        | 8507/57600 [1:29:46<8:39:40,  1.57it/s]
 15%|█▍        | 8508/57600 [1:29:46<8:41:13,  1.57it/s]
 15%|█▍        | 8509/57600 [1:29:47<9:03:32,  1.51it/s]
 15%|█▍        | 8510/57600 [1:29:48<9:01:24,  1.51it/s]
 15%|█▍        | 8511/57600 [1:29:48<8:56:33,  1.52it/s]
 15%|█▍        | 8512/57600 [1:29:49<9:06:52,  1.50it/s]
 15%|█▍        | 8513/57600 [1:29:50<9:11:11,  1.48it/s]
 15%|█▍        | 8514/57600 [1:29:50<9:19:43,  1.46it/s]
 15%|█▍        | 8515/57600 [1:29:51<9:05:06,  1.50it/s]
 15%|█▍        | 8516/57600 [1:29:52<8:42:42,  1.57it/s]
 15%|█▍        | 8517/57600 [1:29:52<8:48:31,  1.55it/s]
 15%|█▍        | 8518/57600 [1:29:53<8:27:53,  1.61it/s]
 15%|█▍        | 8519/57600 [1:29:53<8:22:55,  1.63it/s]
 15%|█▍        | 8520/57600 [1:29:54<8:23:48,  1.62it/s]
                                                        
{'loss': 1.3755, 'learning_rate': 8.695470383275261e-07, 'epoch': 94.04}

 15%|█▍        | 8520/57600 [1:29:54<8:23:48,  1.62it/s]
 15%|█▍        | 8521/57600 [1:29:55<8:26:23,  1.62it/s]
 15%|█▍        | 8522/57600 [1:29:55<8:30:32,  1.60it/s]
 15%|█▍        | 8523/57600 [1:29:56<8:18:39,  1.64it/s]
 15%|█▍        | 8524/57600 [1:29:57<8:18:41,  1.64it/s]
 15%|█▍        | 8525/57600 [1:29:57<8:12:45,  1.66it/s]
 15%|█▍        | 8526/57600 [1:29:58<8:35:33,  1.59it/s]
 15%|█▍        | 8527/57600 [1:29:58<8:31:41,  1.60it/s]
 15%|█▍        | 8528/57600 [1:29:59<8:24:21,  1.62it/s]
 15%|█▍        | 8529/57600 [1:30:00<8:43:30,  1.56it/s]
 15%|█▍        | 8530/57600 [1:30:00<8:51:17,  1.54it/s]
 15%|█▍        | 8531/57600 [1:30:01<8:49:18,  1.55it/s]
 15%|█▍        | 8532/57600 [1:30:02<8:53:43,  1.53it/s]
 15%|█▍        | 8533/57600 [1:30:02<8:51:50,  1.54it/s]
 15%|█▍        | 8534/57600 [1:30:03<8:47:18,  1.55it/s]
 15%|█▍        | 8535/57600 [1:30:04<8:53:33,  1.53it/s]
 15%|█▍        | 8536/57600 [1:30:04<8:52:34,  1.54it/s]
 15%|█▍        | 8537/57600 [1:30:05<8:34:04,  1.59it/s]
 15%|█▍        | 8538/57600 [1:30:05<8:24:33,  1.62it/s]
 15%|█▍        | 8539/57600 [1:30:06<8:28:46,  1.61it/s]
 15%|█▍        | 8540/57600 [1:30:07<8:31:19,  1.60it/s]
                                                        
{'loss': 1.3927, 'learning_rate': 8.69233449477352e-07, 'epoch': 94.26}

 15%|█▍        | 8540/57600 [1:30:07<8:31:19,  1.60it/s]
 15%|█▍        | 8541/57600 [1:30:07<8:30:11,  1.60it/s]
 15%|█▍        | 8542/57600 [1:30:08<8:41:08,  1.57it/s]
 15%|█▍        | 8543/57600 [1:30:09<8:27:46,  1.61it/s]
 15%|█▍        | 8544/57600 [1:30:09<8:28:56,  1.61it/s]
 15%|█▍        | 8545/57600 [1:30:10<8:45:18,  1.56it/s]
 15%|█▍        | 8546/57600 [1:30:11<8:35:57,  1.58it/s]
 15%|█▍        | 8547/57600 [1:30:11<8:24:13,  1.62it/s]
 15%|█▍        | 8548/57600 [1:30:12<8:45:39,  1.56it/s]
 15%|█▍        | 8549/57600 [1:30:12<8:38:08,  1.58it/s]
 15%|█▍        | 8550/57600 [1:30:13<8:51:06,  1.54it/s]
 15%|█▍        | 8551/57600 [1:30:14<8:42:02,  1.57it/s]
 15%|█▍        | 8552/57600 [1:30:14<8:33:19,  1.59it/s]
 15%|█▍        | 8553/57600 [1:30:15<8:52:13,  1.54it/s]
 15%|█▍        | 8554/57600 [1:30:16<8:38:02,  1.58it/s]
 15%|█▍        | 8555/57600 [1:30:16<8:54:27,  1.53it/s]
 15%|█▍        | 8556/57600 [1:30:17<8:48:16,  1.55it/s]
 15%|█▍        | 8557/57600 [1:30:18<8:43:46,  1.56it/s]
 15%|█▍        | 8558/57600 [1:30:18<8:28:48,  1.61it/s]
 15%|█▍        | 8559/57600 [1:30:19<8:37:29,  1.58it/s]
 15%|█▍        | 8560/57600 [1:30:19<8:33:57,  1.59it/s]
                                                        
{'loss': 1.4137, 'learning_rate': 8.689198606271777e-07, 'epoch': 94.48}

 15%|█▍        | 8560/57600 [1:30:19<8:33:57,  1.59it/s]
 15%|█▍        | 8561/57600 [1:30:20<8:23:45,  1.62it/s]
 15%|█▍        | 8562/57600 [1:30:21<8:19:00,  1.64it/s]
 15%|█▍        | 8563/57600 [1:30:21<8:06:50,  1.68it/s]
 15%|█▍        | 8564/57600 [1:30:22<7:58:26,  1.71it/s]
 15%|█▍        | 8565/57600 [1:30:22<7:56:25,  1.72it/s]
 15%|█▍        | 8566/57600 [1:30:23<8:01:01,  1.70it/s]
 15%|█▍        | 8567/57600 [1:30:23<7:52:17,  1.73it/s]
 15%|█▍        | 8568/57600 [1:30:24<8:02:50,  1.69it/s]
 15%|█▍        | 8569/57600 [1:30:25<8:16:54,  1.64it/s]
 15%|█▍        | 8570/57600 [1:30:25<8:11:21,  1.66it/s]
 15%|█▍        | 8571/57600 [1:30:26<8:29:07,  1.61it/s]
 15%|█▍        | 8572/57600 [1:30:27<8:28:15,  1.61it/s]
 15%|█▍        | 8573/57600 [1:30:27<8:42:28,  1.56it/s]
 15%|█▍        | 8574/57600 [1:30:28<8:41:19,  1.57it/s]
 15%|█▍        | 8575/57600 [1:30:29<8:42:13,  1.56it/s]
 15%|█▍        | 8576/57600 [1:30:29<8:36:33,  1.58it/s]
 15%|█▍        | 8577/57600 [1:30:30<8:21:32,  1.63it/s]
 15%|█▍        | 8578/57600 [1:30:30<8:25:47,  1.62it/s]
 15%|█▍        | 8579/57600 [1:30:31<8:33:16,  1.59it/s]
 15%|█▍        | 8580/57600 [1:30:32<8:49:50,  1.54it/s]
                                                        
{'loss': 1.4284, 'learning_rate': 8.686062717770035e-07, 'epoch': 94.7}

 15%|█▍        | 8580/57600 [1:30:32<8:49:50,  1.54it/s]
 15%|█▍        | 8581/57600 [1:30:32<9:06:42,  1.49it/s]
 15%|█▍        | 8582/57600 [1:30:33<8:42:25,  1.56it/s]
 15%|█▍        | 8583/57600 [1:30:34<8:36:38,  1.58it/s]
 15%|█▍        | 8584/57600 [1:30:34<8:39:38,  1.57it/s]
 15%|█▍        | 8585/57600 [1:30:35<8:27:34,  1.61it/s]
 15%|█▍        | 8586/57600 [1:30:35<8:24:14,  1.62it/s]
 15%|█▍        | 8587/57600 [1:30:36<8:35:26,  1.58it/s]
 15%|█▍        | 8588/57600 [1:30:37<8:40:23,  1.57it/s]
 15%|█▍        | 8589/57600 [1:30:37<8:19:34,  1.64it/s]
 15%|█▍        | 8590/57600 [1:30:38<8:28:54,  1.61it/s]
 15%|█▍        | 8591/57600 [1:30:39<8:27:25,  1.61it/s]
 15%|█▍        | 8592/57600 [1:30:39<8:10:49,  1.66it/s]
 15%|█▍        | 8593/57600 [1:30:40<8:09:34,  1.67it/s]
 15%|█▍        | 8594/57600 [1:30:40<8:11:22,  1.66it/s]
 15%|█▍        | 8595/57600 [1:30:41<8:16:09,  1.65it/s]
 15%|█▍        | 8596/57600 [1:30:42<8:19:18,  1.64it/s]
 15%|█▍        | 8597/57600 [1:30:42<8:14:31,  1.65it/s]
 15%|█▍        | 8598/57600 [1:30:43<8:04:51,  1.68it/s]
 15%|█▍        | 8599/57600 [1:30:43<8:02:39,  1.69it/s]
 15%|█▍        | 8600/57600 [1:30:44<8:11:44,  1.66it/s]
                                                        
{'loss': 1.4287, 'learning_rate': 8.682926829268292e-07, 'epoch': 94.92}

 15%|█▍        | 8600/57600 [1:30:44<8:11:44,  1.66it/s]
 15%|█▍        | 8601/57600 [1:30:45<8:33:10,  1.59it/s]
 15%|█▍        | 8602/57600 [1:30:45<8:15:06,  1.65it/s]
 15%|█▍        | 8603/57600 [1:30:46<8:41:38,  1.57it/s]
 15%|█▍        | 8604/57600 [1:30:47<8:39:33,  1.57it/s]
 15%|█▍        | 8605/57600 [1:30:47<8:50:16,  1.54it/s]
 15%|█▍        | 8606/57600 [1:30:48<8:58:08,  1.52it/s]
 15%|█▍        | 8607/57600 [1:30:49<8:59:06,  1.51it/s]
 15%|█▍        | 8608/57600 [1:30:49<9:09:14,  1.49it/s]
 15%|█▍        | 8609/57600 [1:30:50<9:02:39,  1.50it/s]
 15%|█▍        | 8610/57600 [1:30:51<8:54:09,  1.53it/s]
 15%|█▍        | 8611/57600 [1:30:51<8:28:50,  1.60it/s]
 15%|█▍        | 8612/57600 [1:30:52<8:25:37,  1.61it/s]
 15%|█▍        | 8613/57600 [1:30:52<8:40:33,  1.57it/s]
 15%|█▍        | 8614/57600 [1:30:53<8:39:40,  1.57it/s]
 15%|█▍        | 8615/57600 [1:30:54<8:23:29,  1.62it/s]
 15%|█▍        | 8616/57600 [1:30:54<8:12:36,  1.66it/s]
 15%|█▍        | 8617/57600 [1:30:55<8:19:12,  1.64it/s]
 15%|█▍        | 8618/57600 [1:30:55<8:13:52,  1.65it/s]
 15%|█▍        | 8619/57600 [1:30:56<8:43:11,  1.56it/s]
 15%|█▍        | 8620/57600 [1:30:57<8:34:28,  1.59it/s]
                                                        
{'loss': 1.4243, 'learning_rate': 8.679790940766551e-07, 'epoch': 95.14}

 15%|█▍        | 8620/57600 [1:30:57<8:34:28,  1.59it/s]
 15%|█▍        | 8621/57600 [1:30:57<8:29:07,  1.60it/s]
 15%|█▍        | 8622/57600 [1:30:58<8:20:26,  1.63it/s]
 15%|█▍        | 8623/57600 [1:30:59<8:25:24,  1.62it/s]
 15%|█▍        | 8624/57600 [1:30:59<8:42:46,  1.56it/s]
 15%|█▍        | 8625/57600 [1:31:00<8:52:03,  1.53it/s]
 15%|█▍        | 8626/57600 [1:31:01<8:54:38,  1.53it/s]
 15%|█▍        | 8627/57600 [1:31:01<8:49:51,  1.54it/s]
 15%|█▍        | 8628/57600 [1:31:02<8:49:01,  1.54it/s]
 15%|█▍        | 8629/57600 [1:31:02<8:30:46,  1.60it/s]
 15%|█▍        | 8630/57600 [1:31:03<8:26:29,  1.61it/s]
 15%|█▍        | 8631/57600 [1:31:04<8:24:15,  1.62it/s]
 15%|█▍        | 8632/57600 [1:31:04<8:28:56,  1.60it/s]
 15%|█▍        | 8633/57600 [1:31:05<8:29:39,  1.60it/s]
 15%|█▍        | 8634/57600 [1:31:06<8:34:43,  1.59it/s]
 15%|█▍        | 8635/57600 [1:31:06<8:37:21,  1.58it/s]
 15%|█▍        | 8636/57600 [1:31:07<8:39:39,  1.57it/s]
 15%|█▍        | 8637/57600 [1:31:07<8:35:45,  1.58it/s]
 15%|█▍        | 8638/57600 [1:31:08<8:57:15,  1.52it/s]
 15%|█▍        | 8639/57600 [1:31:09<8:41:55,  1.56it/s]
 15%|█▌        | 8640/57600 [1:31:09<8:53:42,  1.53it/s]
                                                        
{'loss': 1.3588, 'learning_rate': 8.676655052264807e-07, 'epoch': 95.36}

 15%|█▌        | 8640/57600 [1:31:09<8:53:42,  1.53it/s]
 15%|█▌        | 8641/57600 [1:31:10<8:46:13,  1.55it/s]
 15%|█▌        | 8642/57600 [1:31:11<8:45:55,  1.55it/s]
 15%|█▌        | 8643/57600 [1:31:11<8:42:36,  1.56it/s]
 15%|█▌        | 8644/57600 [1:31:12<8:45:28,  1.55it/s]
 15%|█▌        | 8645/57600 [1:31:13<8:46:22,  1.55it/s]
 15%|█▌        | 8646/57600 [1:31:13<8:36:52,  1.58it/s]
 15%|█▌        | 8647/57600 [1:31:14<8:26:06,  1.61it/s]
 15%|█▌        | 8648/57600 [1:31:15<8:25:47,  1.61it/s]
 15%|█▌        | 8649/57600 [1:31:15<8:24:35,  1.62it/s]
 15%|█▌        | 8650/57600 [1:31:16<8:32:50,  1.59it/s]
 15%|█▌        | 8651/57600 [1:31:16<8:39:08,  1.57it/s]
 15%|█▌        | 8652/57600 [1:31:17<8:51:05,  1.54it/s]
 15%|█▌        | 8653/57600 [1:31:18<8:54:56,  1.52it/s]
 15%|█▌        | 8654/57600 [1:31:18<8:44:27,  1.56it/s]
 15%|█▌        | 8655/57600 [1:31:19<8:37:26,  1.58it/s]
 15%|█▌        | 8656/57600 [1:31:20<8:44:28,  1.56it/s]
 15%|█▌        | 8657/57600 [1:31:20<8:37:07,  1.58it/s]
 15%|█▌        | 8658/57600 [1:31:21<8:49:45,  1.54it/s]
 15%|█▌        | 8659/57600 [1:31:22<8:29:35,  1.60it/s]
 15%|█▌        | 8660/57600 [1:31:22<8:37:27,  1.58it/s]
                                                        
{'loss': 1.3846, 'learning_rate': 8.673519163763066e-07, 'epoch': 95.58}

 15%|█▌        | 8660/57600 [1:31:22<8:37:27,  1.58it/s]
 15%|█▌        | 8661/57600 [1:31:23<8:41:40,  1.56it/s]
 15%|█▌        | 8662/57600 [1:31:23<8:35:05,  1.58it/s]
 15%|█▌        | 8663/57600 [1:31:24<8:28:41,  1.60it/s]
 15%|█▌        | 8664/57600 [1:31:25<8:29:41,  1.60it/s]
 15%|█▌        | 8665/57600 [1:31:25<8:42:38,  1.56it/s]
 15%|█▌        | 8666/57600 [1:31:26<8:50:43,  1.54it/s]
 15%|█▌        | 8667/57600 [1:31:27<8:26:34,  1.61it/s]
 15%|█▌        | 8668/57600 [1:31:27<8:14:50,  1.65it/s]
 15%|█▌        | 8669/57600 [1:31:28<8:12:15,  1.66it/s]
 15%|█▌        | 8670/57600 [1:31:28<8:12:34,  1.66it/s]
 15%|█▌        | 8671/57600 [1:31:29<8:06:12,  1.68it/s]
 15%|█▌        | 8672/57600 [1:31:30<8:06:28,  1.68it/s]
 15%|█▌        | 8673/57600 [1:31:30<8:07:44,  1.67it/s]
 15%|█▌        | 8674/57600 [1:31:31<8:05:18,  1.68it/s]
 15%|█▌        | 8675/57600 [1:31:31<8:17:45,  1.64it/s]
 15%|█▌        | 8676/57600 [1:31:32<8:11:00,  1.66it/s]
 15%|█▌        | 8677/57600 [1:31:33<8:04:49,  1.68it/s]
 15%|█▌        | 8678/57600 [1:31:33<8:03:37,  1.69it/s]
 15%|█▌        | 8679/57600 [1:31:34<8:15:31,  1.65it/s]
 15%|█▌        | 8680/57600 [1:31:34<8:24:05,  1.62it/s]
                                                        
{'loss': 1.4513, 'learning_rate': 8.670383275261325e-07, 'epoch': 95.81}

 15%|█▌        | 8680/57600 [1:31:34<8:24:05,  1.62it/s]
 15%|█▌        | 8681/57600 [1:31:35<8:37:40,  1.57it/s]
 15%|█▌        | 8682/57600 [1:31:36<8:25:17,  1.61it/s]
 15%|█▌        | 8683/57600 [1:31:36<8:17:48,  1.64it/s]
 15%|█▌        | 8684/57600 [1:31:37<8:15:52,  1.64it/s]
 15%|█▌        | 8685/57600 [1:31:37<8:10:35,  1.66it/s]
 15%|█▌        | 8686/57600 [1:31:38<8:28:57,  1.60it/s]
 15%|█▌        | 8687/57600 [1:31:39<8:30:25,  1.60it/s]
 15%|█▌        | 8688/57600 [1:31:39<8:25:09,  1.61it/s]
 15%|█▌        | 8689/57600 [1:31:40<8:37:10,  1.58it/s]
 15%|█▌        | 8690/57600 [1:31:41<8:36:50,  1.58it/s]
 15%|█▌        | 8691/57600 [1:31:41<8:30:11,  1.60it/s]
 15%|█▌        | 8692/57600 [1:31:42<8:22:43,  1.62it/s]
 15%|█▌        | 8693/57600 [1:31:42<8:20:22,  1.63it/s]
 15%|█▌        | 8694/57600 [1:31:43<8:16:07,  1.64it/s]
 15%|█▌        | 8695/57600 [1:31:44<8:26:36,  1.61it/s]
 15%|█▌        | 8696/57600 [1:31:44<8:12:42,  1.65it/s]
 15%|█▌        | 8697/57600 [1:31:45<8:02:32,  1.69it/s]
 15%|█▌        | 8698/57600 [1:31:46<8:41:03,  1.56it/s]
 15%|█▌        | 8699/57600 [1:31:46<8:28:20,  1.60it/s]
 15%|█▌        | 8700/57600 [1:31:47<8:36:41,  1.58it/s]
                                                        
{'loss': 1.4022, 'learning_rate': 8.667247386759582e-07, 'epoch': 96.03}

 15%|█▌        | 8700/57600 [1:31:47<8:36:41,  1.58it/s]
 15%|█▌        | 8701/57600 [1:31:47<8:23:20,  1.62it/s]
 15%|█▌        | 8702/57600 [1:31:48<8:08:08,  1.67it/s]
 15%|█▌        | 8703/57600 [1:31:49<8:11:29,  1.66it/s]
 15%|█▌        | 8704/57600 [1:31:49<8:00:40,  1.70it/s]
 15%|█▌        | 8705/57600 [1:31:50<8:18:28,  1.63it/s]
 15%|█▌        | 8706/57600 [1:31:50<8:08:56,  1.67it/s]
 15%|█▌        | 8707/57600 [1:31:51<8:18:45,  1.63it/s]
 15%|█▌        | 8708/57600 [1:31:52<8:30:51,  1.60it/s]
 15%|█▌        | 8709/57600 [1:31:52<8:39:06,  1.57it/s]
 15%|█▌        | 8710/57600 [1:31:53<8:36:06,  1.58it/s]
 15%|█▌        | 8711/57600 [1:31:54<8:57:15,  1.52it/s]
 15%|█▌        | 8712/57600 [1:31:54<8:55:42,  1.52it/s]
 15%|█▌        | 8713/57600 [1:31:55<8:43:49,  1.56it/s]
 15%|█▌        | 8714/57600 [1:31:56<8:32:31,  1.59it/s]
 15%|█▌        | 8715/57600 [1:31:56<8:31:58,  1.59it/s]
 15%|█▌        | 8716/57600 [1:31:57<8:21:45,  1.62it/s]
 15%|█▌        | 8717/57600 [1:31:57<8:24:28,  1.61it/s]
 15%|█▌        | 8718/57600 [1:31:58<8:29:22,  1.60it/s]
 15%|█▌        | 8719/57600 [1:31:59<8:25:33,  1.61it/s]
 15%|█▌        | 8720/57600 [1:31:59<8:44:27,  1.55it/s]
                                                        
{'loss': 1.3969, 'learning_rate': 8.664111498257838e-07, 'epoch': 96.25}

 15%|█▌        | 8720/57600 [1:31:59<8:44:27,  1.55it/s]
 15%|█▌        | 8721/57600 [1:32:00<8:41:00,  1.56it/s]
 15%|█▌        | 8722/57600 [1:32:01<8:31:38,  1.59it/s]
 15%|█▌        | 8723/57600 [1:32:01<8:34:36,  1.58it/s]
 15%|█▌        | 8724/57600 [1:32:02<8:41:52,  1.56it/s]
 15%|█▌        | 8725/57600 [1:32:02<8:35:17,  1.58it/s]
 15%|█▌        | 8726/57600 [1:32:03<8:37:48,  1.57it/s]
 15%|█▌        | 8727/57600 [1:32:04<8:45:45,  1.55it/s]
 15%|█▌        | 8728/57600 [1:32:04<8:41:48,  1.56it/s]
 15%|█▌        | 8729/57600 [1:32:05<8:37:32,  1.57it/s]
 15%|█▌        | 8730/57600 [1:32:06<8:27:31,  1.60it/s]
 15%|█▌        | 8731/57600 [1:32:06<8:13:11,  1.65it/s]
 15%|█▌        | 8732/57600 [1:32:07<8:16:21,  1.64it/s]
 15%|█▌        | 8733/57600 [1:32:08<8:43:35,  1.56it/s]
 15%|█▌        | 8734/57600 [1:32:08<8:37:26,  1.57it/s]
 15%|█▌        | 8735/57600 [1:32:09<8:53:28,  1.53it/s]
 15%|█▌        | 8736/57600 [1:32:09<8:44:44,  1.55it/s]
 15%|█▌        | 8737/57600 [1:32:10<8:36:38,  1.58it/s]
 15%|█▌        | 8738/57600 [1:32:11<8:42:05,  1.56it/s]
 15%|█▌        | 8739/57600 [1:32:11<8:31:25,  1.59it/s]
 15%|█▌        | 8740/57600 [1:32:12<8:33:14,  1.59it/s]
                                                        
{'loss': 1.38, 'learning_rate': 8.660975609756097e-07, 'epoch': 96.47}

 15%|█▌        | 8740/57600 [1:32:12<8:33:14,  1.59it/s]
 15%|█▌        | 8741/57600 [1:32:13<8:23:00,  1.62it/s]
 15%|█▌        | 8742/57600 [1:32:13<8:15:13,  1.64it/s]
 15%|█▌        | 8743/57600 [1:32:14<8:34:43,  1.58it/s]
 15%|█▌        | 8744/57600 [1:32:14<8:23:11,  1.62it/s]
 15%|█▌        | 8745/57600 [1:32:15<8:40:08,  1.57it/s]
 15%|█▌        | 8746/57600 [1:32:16<8:27:36,  1.60it/s]
 15%|█▌        | 8747/57600 [1:32:16<8:30:43,  1.59it/s]
 15%|█▌        | 8748/57600 [1:32:17<8:31:04,  1.59it/s]
 15%|█▌        | 8749/57600 [1:32:18<8:25:58,  1.61it/s]
 15%|█▌        | 8750/57600 [1:32:18<8:22:13,  1.62it/s]
 15%|█▌        | 8751/57600 [1:32:19<8:25:50,  1.61it/s]
 15%|█▌        | 8752/57600 [1:32:19<8:20:46,  1.63it/s]
 15%|█▌        | 8753/57600 [1:32:20<8:18:20,  1.63it/s]
 15%|█▌        | 8754/57600 [1:32:21<8:19:22,  1.63it/s]
 15%|█▌        | 8755/57600 [1:32:21<8:16:09,  1.64it/s]
 15%|█▌        | 8756/57600 [1:32:22<8:26:45,  1.61it/s]
 15%|█▌        | 8757/57600 [1:32:23<8:24:28,  1.61it/s]
 15%|█▌        | 8758/57600 [1:32:23<8:24:41,  1.61it/s]
 15%|█▌        | 8759/57600 [1:32:24<8:12:03,  1.65it/s]
 15%|█▌        | 8760/57600 [1:32:24<8:17:50,  1.64it/s]
                                                        
{'loss': 1.4701, 'learning_rate': 8.657839721254355e-07, 'epoch': 96.69}

 15%|█▌        | 8760/57600 [1:32:24<8:17:50,  1.64it/s]
 15%|█▌        | 8761/57600 [1:32:25<8:26:15,  1.61it/s]
 15%|█▌        | 8762/57600 [1:32:26<8:30:45,  1.59it/s]
 15%|█▌        | 8763/57600 [1:32:26<8:34:39,  1.58it/s]
 15%|█▌        | 8764/57600 [1:32:27<8:34:22,  1.58it/s]
 15%|█▌        | 8765/57600 [1:32:27<8:21:42,  1.62it/s]
 15%|█▌        | 8766/57600 [1:32:28<8:22:20,  1.62it/s]
 15%|█▌        | 8767/57600 [1:32:29<9:08:27,  1.48it/s]
 15%|█▌        | 8768/57600 [1:32:30<9:15:20,  1.47it/s]
 15%|█▌        | 8769/57600 [1:32:30<9:01:38,  1.50it/s]
 15%|█▌        | 8770/57600 [1:32:31<8:59:25,  1.51it/s]
 15%|█▌        | 8771/57600 [1:32:31<8:47:11,  1.54it/s]
 15%|█▌        | 8772/57600 [1:32:32<8:41:00,  1.56it/s]
 15%|█▌        | 8773/57600 [1:32:33<8:31:52,  1.59it/s]
 15%|█▌        | 8774/57600 [1:32:33<8:17:23,  1.64it/s]
 15%|█▌        | 8775/57600 [1:32:34<8:26:33,  1.61it/s]
 15%|█▌        | 8776/57600 [1:32:35<8:24:10,  1.61it/s]
 15%|█▌        | 8777/57600 [1:32:35<8:24:45,  1.61it/s]
 15%|█▌        | 8778/57600 [1:32:36<8:34:58,  1.58it/s]
 15%|█▌        | 8779/57600 [1:32:36<8:32:46,  1.59it/s]
 15%|█▌        | 8780/57600 [1:32:37<8:43:29,  1.55it/s]
                                                        
{'loss': 1.3637, 'learning_rate': 8.654703832752613e-07, 'epoch': 96.91}

 15%|█▌        | 8780/57600 [1:32:37<8:43:29,  1.55it/s]
 15%|█▌        | 8781/57600 [1:32:38<8:57:27,  1.51it/s]
 15%|█▌        | 8782/57600 [1:32:38<8:55:45,  1.52it/s]
 15%|█▌        | 8783/57600 [1:32:39<8:47:20,  1.54it/s]
 15%|█▌        | 8784/57600 [1:32:40<8:47:16,  1.54it/s]
 15%|█▌        | 8785/57600 [1:32:40<8:30:53,  1.59it/s]
 15%|█▌        | 8786/57600 [1:32:41<8:30:07,  1.59it/s]
 15%|█▌        | 8787/57600 [1:32:42<8:33:11,  1.59it/s]
 15%|█▌        | 8788/57600 [1:32:42<8:53:46,  1.52it/s]
 15%|█▌        | 8789/57600 [1:32:43<9:07:11,  1.49it/s]
 15%|█▌        | 8790/57600 [1:32:44<8:45:54,  1.55it/s]
 15%|█▌        | 8791/57600 [1:32:44<8:54:19,  1.52it/s]
 15%|█▌        | 8792/57600 [1:32:45<8:53:43,  1.52it/s]
 15%|█▌        | 8793/57600 [1:32:46<8:43:02,  1.56it/s]
 15%|█▌        | 8794/57600 [1:32:46<8:45:10,  1.55it/s]
 15%|█▌        | 8795/57600 [1:32:47<8:47:56,  1.54it/s]
 15%|█▌        | 8796/57600 [1:32:48<8:56:30,  1.52it/s]
 15%|█▌        | 8797/57600 [1:32:48<8:51:13,  1.53it/s]
 15%|█▌        | 8798/57600 [1:32:49<8:44:44,  1.55it/s]
 15%|█▌        | 8799/57600 [1:32:49<8:32:54,  1.59it/s]
 15%|█▌        | 8800/57600 [1:32:50<8:30:22,  1.59it/s]
                                                        
{'loss': 1.3748, 'learning_rate': 8.65156794425087e-07, 'epoch': 97.13}

 15%|█▌        | 8800/57600 [1:32:50<8:30:22,  1.59it/s]
 15%|█▌        | 8801/57600 [1:32:51<8:27:27,  1.60it/s]
 15%|█▌        | 8802/57600 [1:32:51<8:32:14,  1.59it/s]
 15%|█▌        | 8803/57600 [1:32:52<8:31:06,  1.59it/s]
 15%|█▌        | 8804/57600 [1:32:53<8:22:48,  1.62it/s]
 15%|█▌        | 8805/57600 [1:32:53<8:15:17,  1.64it/s]
 15%|█▌        | 8806/57600 [1:32:54<8:15:55,  1.64it/s]
 15%|█▌        | 8807/57600 [1:32:54<8:09:35,  1.66it/s]
 15%|█▌        | 8808/57600 [1:32:55<8:15:19,  1.64it/s]
 15%|█▌        | 8809/57600 [1:32:56<8:13:52,  1.65it/s]
 15%|█▌        | 8810/57600 [1:32:56<8:20:59,  1.62it/s]
 15%|█▌        | 8811/57600 [1:32:57<8:32:18,  1.59it/s]
 15%|█▌        | 8812/57600 [1:32:57<8:33:07,  1.58it/s]
 15%|█▌        | 8813/57600 [1:32:58<8:33:31,  1.58it/s]
 15%|█▌        | 8814/57600 [1:32:59<8:26:24,  1.61it/s]
 15%|█▌        | 8815/57600 [1:32:59<8:31:07,  1.59it/s]
 15%|█▌        | 8816/57600 [1:33:00<8:41:38,  1.56it/s]
 15%|█▌        | 8817/57600 [1:33:01<8:33:54,  1.58it/s]
 15%|█▌        | 8818/57600 [1:33:01<8:50:25,  1.53it/s]
 15%|█▌        | 8819/57600 [1:33:02<8:37:12,  1.57it/s]
 15%|█▌        | 8820/57600 [1:33:02<8:24:46,  1.61it/s]
                                                        
{'loss': 1.461, 'learning_rate': 8.648432055749129e-07, 'epoch': 97.35}

 15%|█▌        | 8820/57600 [1:33:02<8:24:46,  1.61it/s]
 15%|█▌        | 8821/57600 [1:33:03<8:24:30,  1.61it/s]
 15%|█▌        | 8822/57600 [1:33:04<8:42:12,  1.56it/s]
 15%|█▌        | 8823/57600 [1:33:04<8:39:52,  1.56it/s]
 15%|█▌        | 8824/57600 [1:33:05<8:35:43,  1.58it/s]
 15%|█▌        | 8825/57600 [1:33:06<8:31:14,  1.59it/s]
 15%|█▌        | 8826/57600 [1:33:06<8:40:45,  1.56it/s]
 15%|█▌        | 8827/57600 [1:33:07<8:51:05,  1.53it/s]
 15%|█▌        | 8828/57600 [1:33:08<8:33:46,  1.58it/s]
 15%|█▌        | 8829/57600 [1:33:08<8:21:15,  1.62it/s]
 15%|█▌        | 8830/57600 [1:33:09<8:22:11,  1.62it/s]
 15%|█▌        | 8831/57600 [1:33:09<8:33:59,  1.58it/s]
 15%|█▌        | 8832/57600 [1:33:10<8:34:05,  1.58it/s]
 15%|█▌        | 8833/57600 [1:33:11<8:20:49,  1.62it/s]
 15%|█▌        | 8834/57600 [1:33:11<8:26:17,  1.61it/s]
 15%|█▌        | 8835/57600 [1:33:12<8:16:48,  1.64it/s]
 15%|█▌        | 8836/57600 [1:33:13<8:30:09,  1.59it/s]
 15%|█▌        | 8837/57600 [1:33:13<8:23:16,  1.61it/s]
 15%|█▌        | 8838/57600 [1:33:14<8:22:41,  1.62it/s]
 15%|█▌        | 8839/57600 [1:33:14<8:23:50,  1.61it/s]
 15%|█▌        | 8840/57600 [1:33:15<8:14:52,  1.64it/s]
                                                        
{'loss': 1.4615, 'learning_rate': 8.645296167247387e-07, 'epoch': 97.57}

 15%|█▌        | 8840/57600 [1:33:15<8:14:52,  1.64it/s]
 15%|█▌        | 8841/57600 [1:33:16<8:19:09,  1.63it/s]
 15%|█▌        | 8842/57600 [1:33:16<8:11:18,  1.65it/s]
 15%|█▌        | 8843/57600 [1:33:17<8:06:38,  1.67it/s]
 15%|█▌        | 8844/57600 [1:33:17<8:19:24,  1.63it/s]
 15%|█▌        | 8845/57600 [1:33:18<8:18:36,  1.63it/s]
 15%|█▌        | 8846/57600 [1:33:19<8:27:33,  1.60it/s]
 15%|█▌        | 8847/57600 [1:33:19<8:28:03,  1.60it/s]
 15%|█▌        | 8848/57600 [1:33:20<8:53:17,  1.52it/s]
 15%|█▌        | 8849/57600 [1:33:21<8:53:33,  1.52it/s]
 15%|█▌        | 8850/57600 [1:33:21<8:58:07,  1.51it/s]
 15%|█▌        | 8851/57600 [1:33:22<8:37:59,  1.57it/s]
 15%|█▌        | 8852/57600 [1:33:23<8:33:57,  1.58it/s]
 15%|█▌        | 8853/57600 [1:33:23<8:37:31,  1.57it/s]
 15%|█▌        | 8854/57600 [1:33:24<8:29:38,  1.59it/s]
 15%|█▌        | 8855/57600 [1:33:25<8:40:10,  1.56it/s]
 15%|█▌        | 8856/57600 [1:33:25<8:57:53,  1.51it/s]
 15%|█▌        | 8857/57600 [1:33:26<8:59:41,  1.51it/s]
 15%|█▌        | 8858/57600 [1:33:27<8:51:55,  1.53it/s]
 15%|█▌        | 8859/57600 [1:33:27<8:49:48,  1.53it/s]
 15%|█▌        | 8860/57600 [1:33:28<8:43:27,  1.55it/s]
                                                        
{'loss': 1.3775, 'learning_rate': 8.642160278745644e-07, 'epoch': 97.79}

 15%|█▌        | 8860/57600 [1:33:28<8:43:27,  1.55it/s]
 15%|█▌        | 8861/57600 [1:33:28<8:40:16,  1.56it/s]
 15%|█▌        | 8862/57600 [1:33:29<8:39:36,  1.56it/s]
 15%|█▌        | 8863/57600 [1:33:30<8:48:06,  1.54it/s]
 15%|█▌        | 8864/57600 [1:33:30<8:30:42,  1.59it/s]
 15%|█▌        | 8865/57600 [1:33:31<8:20:06,  1.62it/s]
 15%|█▌        | 8866/57600 [1:33:32<8:21:34,  1.62it/s]
 15%|█▌        | 8867/57600 [1:33:32<8:19:03,  1.63it/s]
 15%|█▌        | 8868/57600 [1:33:33<8:29:12,  1.60it/s]
 15%|█▌        | 8869/57600 [1:33:33<8:13:44,  1.64it/s]
 15%|█▌        | 8870/57600 [1:33:34<8:15:36,  1.64it/s]
 15%|█▌        | 8871/57600 [1:33:35<8:26:39,  1.60it/s]
 15%|█▌        | 8872/57600 [1:33:35<8:31:35,  1.59it/s]
 15%|█▌        | 8873/57600 [1:33:36<8:30:05,  1.59it/s]
 15%|█▌        | 8874/57600 [1:33:37<8:26:18,  1.60it/s]
 15%|█▌        | 8875/57600 [1:33:37<8:20:57,  1.62it/s]
 15%|█▌        | 8876/57600 [1:33:38<8:42:54,  1.55it/s]
 15%|█▌        | 8877/57600 [1:33:39<9:07:54,  1.48it/s]
 15%|█▌        | 8878/57600 [1:33:39<8:57:26,  1.51it/s]
 15%|█▌        | 8879/57600 [1:33:40<9:06:00,  1.49it/s]
 15%|█▌        | 8880/57600 [1:33:40<8:43:41,  1.55it/s]
                                                        
{'loss': 1.4125, 'learning_rate': 8.639024390243902e-07, 'epoch': 98.01}

 15%|█▌        | 8880/57600 [1:33:40<8:43:41,  1.55it/s]
 15%|█▌        | 8881/57600 [1:33:41<8:31:55,  1.59it/s]
 15%|█▌        | 8882/57600 [1:33:42<8:34:52,  1.58it/s]
 15%|█▌        | 8883/57600 [1:33:42<8:37:59,  1.57it/s]
 15%|█▌        | 8884/57600 [1:33:43<8:23:33,  1.61it/s]
 15%|█▌        | 8885/57600 [1:33:44<8:28:08,  1.60it/s]
 15%|█▌        | 8886/57600 [1:33:44<8:22:26,  1.62it/s]
 15%|█▌        | 8887/57600 [1:33:45<8:07:44,  1.66it/s]
 15%|█▌        | 8888/57600 [1:33:45<8:16:16,  1.64it/s]
 15%|█▌        | 8889/57600 [1:33:46<8:32:00,  1.59it/s]
 15%|█▌        | 8890/57600 [1:33:47<8:25:07,  1.61it/s]
 15%|█▌        | 8891/57600 [1:33:47<8:14:32,  1.64it/s]
 15%|█▌        | 8892/57600 [1:33:48<8:29:44,  1.59it/s]
 15%|█▌        | 8893/57600 [1:33:49<8:24:18,  1.61it/s]
 15%|█▌        | 8894/57600 [1:33:49<8:27:09,  1.60it/s]
 15%|█▌        | 8895/57600 [1:33:50<8:38:10,  1.57it/s]
 15%|█▌        | 8896/57600 [1:33:50<8:29:51,  1.59it/s]
 15%|█▌        | 8897/57600 [1:33:51<8:41:00,  1.56it/s]
 15%|█▌        | 8898/57600 [1:33:52<8:23:22,  1.61it/s]
 15%|█▌        | 8899/57600 [1:33:52<8:21:24,  1.62it/s]
 15%|█▌        | 8900/57600 [1:33:53<8:14:43,  1.64it/s]
                                                        
{'loss': 1.3846, 'learning_rate': 8.63588850174216e-07, 'epoch': 98.23}

 15%|█▌        | 8900/57600 [1:33:53<8:14:43,  1.64it/s]
 15%|█▌        | 8901/57600 [1:33:53<8:12:21,  1.65it/s]
 15%|█▌        | 8902/57600 [1:33:54<8:09:36,  1.66it/s]
 15%|█▌        | 8903/57600 [1:33:55<8:16:15,  1.64it/s]
 15%|█▌        | 8904/57600 [1:33:55<8:28:38,  1.60it/s]
 15%|█▌        | 8905/57600 [1:33:56<8:42:12,  1.55it/s]
 15%|█▌        | 8906/57600 [1:33:57<8:37:23,  1.57it/s]
 15%|█▌        | 8907/57600 [1:33:57<8:23:35,  1.61it/s]
 15%|█▌        | 8908/57600 [1:33:58<8:10:31,  1.65it/s]
 15%|█▌        | 8909/57600 [1:33:58<8:10:11,  1.66it/s]
 15%|█▌        | 8910/57600 [1:33:59<8:10:46,  1.65it/s]
 15%|█▌        | 8911/57600 [1:34:00<8:18:27,  1.63it/s]
 15%|█▌        | 8912/57600 [1:34:00<8:05:56,  1.67it/s]
 15%|█▌        | 8913/57600 [1:34:01<8:38:39,  1.56it/s]
 15%|█▌        | 8914/57600 [1:34:02<8:21:02,  1.62it/s]
 15%|█▌        | 8915/57600 [1:34:02<8:22:54,  1.61it/s]
 15%|█▌        | 8916/57600 [1:34:03<8:18:32,  1.63it/s]
 15%|█▌        | 8917/57600 [1:34:03<8:34:13,  1.58it/s]
 15%|█▌        | 8918/57600 [1:34:04<8:16:18,  1.63it/s]
 15%|█▌        | 8919/57600 [1:34:05<8:11:06,  1.65it/s]
 15%|█▌        | 8920/57600 [1:34:05<8:12:11,  1.65it/s]
                                                        
{'loss': 1.3948, 'learning_rate': 8.632752613240419e-07, 'epoch': 98.45}

 15%|█▌        | 8920/57600 [1:34:05<8:12:11,  1.65it/s]
 15%|█▌        | 8921/57600 [1:34:06<8:12:27,  1.65it/s]
 15%|█▌        | 8922/57600 [1:34:06<8:19:43,  1.62it/s]
 15%|█▌        | 8923/57600 [1:34:07<8:09:04,  1.66it/s]
 15%|█▌        | 8924/57600 [1:34:08<8:10:42,  1.65it/s]
 15%|█▌        | 8925/57600 [1:34:08<8:11:20,  1.65it/s]
 15%|█▌        | 8926/57600 [1:34:09<8:29:12,  1.59it/s]
 15%|█▌        | 8927/57600 [1:34:09<8:20:03,  1.62it/s]
 16%|█▌        | 8928/57600 [1:34:10<8:29:08,  1.59it/s]
 16%|█▌        | 8929/57600 [1:34:11<8:38:12,  1.57it/s]
 16%|█▌        | 8930/57600 [1:34:11<8:39:37,  1.56it/s]
 16%|█▌        | 8931/57600 [1:34:12<8:36:03,  1.57it/s]
 16%|█▌        | 8932/57600 [1:34:13<8:52:06,  1.52it/s]
 16%|█▌        | 8933/57600 [1:34:13<8:24:29,  1.61it/s]
 16%|█▌        | 8934/57600 [1:34:14<8:14:47,  1.64it/s]
 16%|█▌        | 8935/57600 [1:34:15<8:11:10,  1.65it/s]
 16%|█▌        | 8936/57600 [1:34:15<8:19:03,  1.63it/s]
 16%|█▌        | 8937/57600 [1:34:16<8:36:07,  1.57it/s]
 16%|█▌        | 8938/57600 [1:34:16<8:22:07,  1.62it/s]
 16%|█▌        | 8939/57600 [1:34:17<8:50:13,  1.53it/s]
 16%|█▌        | 8940/57600 [1:34:18<8:40:43,  1.56it/s]
                                                        
{'loss': 1.348, 'learning_rate': 8.629616724738675e-07, 'epoch': 98.68}

 16%|█▌        | 8940/57600 [1:34:18<8:40:43,  1.56it/s]
 16%|█▌        | 8941/57600 [1:34:18<8:27:54,  1.60it/s]
 16%|█▌        | 8942/57600 [1:34:19<8:12:23,  1.65it/s]
 16%|█▌        | 8943/57600 [1:34:20<8:22:45,  1.61it/s]
 16%|█▌        | 8944/57600 [1:34:20<8:27:45,  1.60it/s]
 16%|█▌        | 8945/57600 [1:34:21<8:22:36,  1.61it/s]
 16%|█▌        | 8946/57600 [1:34:21<8:26:07,  1.60it/s]
 16%|█▌        | 8947/57600 [1:34:22<8:12:32,  1.65it/s]
 16%|█▌        | 8948/57600 [1:34:23<8:11:49,  1.65it/s]
 16%|█▌        | 8949/57600 [1:34:23<8:25:00,  1.61it/s]
 16%|█▌        | 8950/57600 [1:34:24<8:15:45,  1.64it/s]
 16%|█▌        | 8951/57600 [1:34:24<8:17:34,  1.63it/s]
 16%|█▌        | 8952/57600 [1:34:25<8:20:45,  1.62it/s]
 16%|█▌        | 8953/57600 [1:34:26<8:18:34,  1.63it/s]
 16%|█▌        | 8954/57600 [1:34:26<8:24:29,  1.61it/s]
 16%|█▌        | 8955/57600 [1:34:27<8:28:25,  1.59it/s]
 16%|█▌        | 8956/57600 [1:34:28<8:17:48,  1.63it/s]
 16%|█▌        | 8957/57600 [1:34:28<8:37:39,  1.57it/s]
 16%|█▌        | 8958/57600 [1:34:29<8:25:50,  1.60it/s]
 16%|█▌        | 8959/57600 [1:34:29<8:19:21,  1.62it/s]
 16%|█▌        | 8960/57600 [1:34:30<8:26:23,  1.60it/s]
                                                        
{'loss': 1.4504, 'learning_rate': 8.626480836236934e-07, 'epoch': 98.9}

 16%|█▌        | 8960/57600 [1:34:30<8:26:23,  1.60it/s]
 16%|█▌        | 8961/57600 [1:34:31<8:23:51,  1.61it/s]
 16%|█▌        | 8962/57600 [1:34:31<8:42:28,  1.55it/s]
 16%|█▌        | 8963/57600 [1:34:32<8:37:08,  1.57it/s]
 16%|█▌        | 8964/57600 [1:34:33<8:29:59,  1.59it/s]
 16%|█▌        | 8965/57600 [1:34:33<8:30:13,  1.59it/s]
 16%|█▌        | 8966/57600 [1:34:34<8:28:27,  1.59it/s]
 16%|█▌        | 8967/57600 [1:34:35<8:37:20,  1.57it/s]
 16%|█▌        | 8968/57600 [1:34:35<8:16:47,  1.63it/s]
 16%|█▌        | 8969/57600 [1:34:36<8:19:15,  1.62it/s]
 16%|█▌        | 8970/57600 [1:34:36<8:50:52,  1.53it/s]
 16%|█▌        | 8971/57600 [1:34:37<8:37:55,  1.56it/s]
 16%|█▌        | 8972/57600 [1:34:38<8:55:07,  1.51it/s]
 16%|█▌        | 8973/57600 [1:34:38<8:35:16,  1.57it/s]
 16%|█▌        | 8974/57600 [1:34:39<8:39:04,  1.56it/s]
 16%|█▌        | 8975/57600 [1:34:40<8:29:16,  1.59it/s]
 16%|█▌        | 8976/57600 [1:34:40<8:24:40,  1.61it/s]
 16%|█▌        | 8977/57600 [1:34:41<8:14:10,  1.64it/s]
 16%|█▌        | 8978/57600 [1:34:41<8:06:36,  1.67it/s]
 16%|█▌        | 8979/57600 [1:34:42<8:15:48,  1.63it/s]
 16%|█▌        | 8980/57600 [1:34:43<8:15:28,  1.64it/s]
                                                        
{'loss': 1.3899, 'learning_rate': 8.623344947735191e-07, 'epoch': 99.12}

 16%|█▌        | 8980/57600 [1:34:43<8:15:28,  1.64it/s]
 16%|█▌        | 8981/57600 [1:34:43<8:26:35,  1.60it/s]
 16%|█▌        | 8982/57600 [1:34:44<8:20:11,  1.62it/s]
 16%|█▌        | 8983/57600 [1:34:45<8:21:06,  1.62it/s]
 16%|█▌        | 8984/57600 [1:34:45<8:04:55,  1.67it/s]
 16%|█▌        | 8985/57600 [1:34:46<8:14:00,  1.64it/s]
 16%|█▌        | 8986/57600 [1:34:46<8:13:44,  1.64it/s]
 16%|█▌        | 8987/57600 [1:34:47<8:11:38,  1.65it/s]
 16%|█▌        | 8988/57600 [1:34:48<8:23:15,  1.61it/s]
 16%|█▌        | 8989/57600 [1:34:48<8:30:28,  1.59it/s]
 16%|█▌        | 8990/57600 [1:34:49<8:36:50,  1.57it/s]
 16%|█▌        | 8991/57600 [1:34:50<8:35:48,  1.57it/s]
 16%|█▌        | 8992/57600 [1:34:50<8:38:48,  1.56it/s]
 16%|█▌        | 8993/57600 [1:34:51<8:35:13,  1.57it/s]
 16%|█▌        | 8994/57600 [1:34:51<8:17:27,  1.63it/s]
 16%|█▌        | 8995/57600 [1:34:52<8:15:03,  1.64it/s]
 16%|█▌        | 8996/57600 [1:34:53<8:18:05,  1.63it/s]
 16%|█▌        | 8997/57600 [1:34:53<8:01:27,  1.68it/s]
 16%|█▌        | 8998/57600 [1:34:54<8:13:15,  1.64it/s]
 16%|█▌        | 8999/57600 [1:34:54<8:18:15,  1.63it/s]
 16%|█▌        | 9000/57600 [1:34:55<8:13:15,  1.64it/s]
                                                        
{'loss': 1.4558, 'learning_rate': 8.62020905923345e-07, 'epoch': 99.34}

 16%|█▌        | 9000/57600 [1:34:55<8:13:15,  1.64it/s]
 16%|█▌        | 9001/57600 [1:34:56<8:15:38,  1.63it/s]
 16%|█▌        | 9002/57600 [1:34:56<8:19:46,  1.62it/s]
 16%|█▌        | 9003/57600 [1:34:57<8:07:58,  1.66it/s]
 16%|█▌        | 9004/57600 [1:34:57<8:16:02,  1.63it/s]
 16%|█▌        | 9005/57600 [1:34:58<8:41:30,  1.55it/s]
 16%|█▌        | 9006/57600 [1:34:59<8:41:05,  1.55it/s]
 16%|█▌        | 9007/57600 [1:34:59<8:37:13,  1.57it/s]
 16%|█▌        | 9008/57600 [1:35:00<8:42:22,  1.55it/s]
 16%|█▌        | 9009/57600 [1:35:01<8:24:39,  1.60it/s]
 16%|█▌        | 9010/57600 [1:35:01<8:30:37,  1.59it/s]
 16%|█▌        | 9011/57600 [1:35:02<8:24:29,  1.61it/s]
 16%|█▌        | 9012/57600 [1:35:02<8:14:36,  1.64it/s]
 16%|█▌        | 9013/57600 [1:35:03<8:17:09,  1.63it/s]
 16%|█▌        | 9014/57600 [1:35:04<8:27:58,  1.59it/s]
 16%|█▌        | 9015/57600 [1:35:04<8:25:51,  1.60it/s]
 16%|█▌        | 9016/57600 [1:35:05<8:31:02,  1.58it/s]
 16%|█▌        | 9017/57600 [1:35:06<8:50:28,  1.53it/s]
 16%|█▌        | 9018/57600 [1:35:06<8:47:22,  1.54it/s]
 16%|█▌        | 9019/57600 [1:35:07<8:36:51,  1.57it/s]
 16%|█▌        | 9020/57600 [1:35:08<8:24:54,  1.60it/s]
                                                        
{'loss': 1.3781, 'learning_rate': 8.617073170731706e-07, 'epoch': 99.56}

 16%|█▌        | 9020/57600 [1:35:08<8:24:54,  1.60it/s]
 16%|█▌        | 9021/57600 [1:35:08<8:36:55,  1.57it/s]
 16%|█▌        | 9022/57600 [1:35:09<8:19:25,  1.62it/s]
 16%|█▌        | 9023/57600 [1:35:10<8:34:43,  1.57it/s]
 16%|█▌        | 9024/57600 [1:35:10<8:28:48,  1.59it/s]
 16%|█▌        | 9025/57600 [1:35:11<8:15:06,  1.64it/s]
 16%|█▌        | 9026/57600 [1:35:11<8:05:28,  1.67it/s]
 16%|█▌        | 9027/57600 [1:35:12<8:03:10,  1.68it/s]
 16%|█▌        | 9028/57600 [1:35:12<8:11:17,  1.65it/s]
 16%|█▌        | 9029/57600 [1:35:13<8:25:58,  1.60it/s]
 16%|█▌        | 9030/57600 [1:35:14<8:25:27,  1.60it/s]
 16%|█▌        | 9031/57600 [1:35:14<8:27:08,  1.60it/s]
 16%|█▌        | 9032/57600 [1:35:15<8:44:03,  1.54it/s]
 16%|█▌        | 9033/57600 [1:35:16<8:57:00,  1.51it/s]
 16%|█▌        | 9034/57600 [1:35:16<8:30:56,  1.58it/s]
 16%|█▌        | 9035/57600 [1:35:17<8:29:18,  1.59it/s]
 16%|█▌        | 9036/57600 [1:35:18<8:39:08,  1.56it/s]
 16%|█▌        | 9037/57600 [1:35:18<8:11:51,  1.65it/s]
 16%|█▌        | 9038/57600 [1:35:19<8:25:44,  1.60it/s]
 16%|█▌        | 9039/57600 [1:35:19<8:25:21,  1.60it/s]
 16%|█▌        | 9040/57600 [1:35:20<8:20:28,  1.62it/s]
                                                        
{'loss': 1.3847, 'learning_rate': 8.613937282229965e-07, 'epoch': 99.78}

 16%|█▌        | 9040/57600 [1:35:20<8:20:28,  1.62it/s]
 16%|█▌        | 9041/57600 [1:35:21<8:25:55,  1.60it/s]
 16%|█▌        | 9042/57600 [1:35:21<8:29:07,  1.59it/s]
 16%|█▌        | 9043/57600 [1:35:22<8:20:25,  1.62it/s]
 16%|█▌        | 9044/57600 [1:35:23<8:16:54,  1.63it/s]
 16%|█▌        | 9045/57600 [1:35:23<8:10:36,  1.65it/s]
 16%|█▌        | 9046/57600 [1:35:24<7:56:46,  1.70it/s]
 16%|█▌        | 9047/57600 [1:35:24<8:03:30,  1.67it/s]
 16%|█▌        | 9048/57600 [1:35:25<8:13:06,  1.64it/s]
 16%|█▌        | 9049/57600 [1:35:26<8:12:15,  1.64it/s]
 16%|█▌        | 9050/57600 [1:35:26<8:28:12,  1.59it/s]
 16%|█▌        | 9051/57600 [1:35:27<8:23:43,  1.61it/s]
 16%|█▌        | 9052/57600 [1:35:27<8:16:55,  1.63it/s]
 16%|█▌        | 9053/57600 [1:35:28<8:25:15,  1.60it/s]
 16%|█▌        | 9054/57600 [1:35:29<8:23:20,  1.61it/s]
 16%|█▌        | 9055/57600 [1:35:29<8:14:03,  1.64it/s]
 16%|█▌        | 9056/57600 [1:35:30<8:13:43,  1.64it/s]
 16%|█▌        | 9057/57600 [1:35:31<8:27:28,  1.59it/s]
 16%|█▌        | 9058/57600 [1:35:31<8:12:02,  1.64it/s]
 16%|█▌        | 9059/57600 [1:35:32<8:10:22,  1.65it/s]
 16%|█▌        | 9060/57600 [1:35:32<8:02:48,  1.68it/s]
                                                        
{'loss': 1.4043, 'learning_rate': 8.610801393728222e-07, 'epoch': 100.0}

 16%|█▌        | 9060/57600 [1:35:32<8:02:48,  1.68it/s]
 16%|█▌        | 9061/57600 [1:35:33<8:21:52,  1.61it/s]
 16%|█▌        | 9062/57600 [1:35:34<8:14:03,  1.64it/s]
 16%|█▌        | 9063/57600 [1:35:34<8:33:47,  1.57it/s]
 16%|█▌        | 9064/57600 [1:35:35<8:18:59,  1.62it/s]
 16%|█▌        | 9065/57600 [1:35:35<8:21:46,  1.61it/s]
 16%|█▌        | 9066/57600 [1:35:36<8:17:06,  1.63it/s]
 16%|█▌        | 9067/57600 [1:35:37<8:21:17,  1.61it/s]
 16%|█▌        | 9068/57600 [1:35:37<8:31:44,  1.58it/s]
 16%|█▌        | 9069/57600 [1:35:38<8:28:10,  1.59it/s]
 16%|█▌        | 9070/57600 [1:35:39<8:28:18,  1.59it/s]
 16%|█▌        | 9071/57600 [1:35:39<8:25:20,  1.60it/s]
 16%|█▌        | 9072/57600 [1:35:40<8:08:49,  1.65it/s]
 16%|█▌        | 9073/57600 [1:35:40<7:59:16,  1.69it/s]
 16%|█▌        | 9074/57600 [1:35:41<7:49:18,  1.72it/s]
 16%|█▌        | 9075/57600 [1:35:41<7:56:02,  1.70it/s]
 16%|█▌        | 9076/57600 [1:35:42<8:05:07,  1.67it/s]
 16%|█▌        | 9077/57600 [1:35:43<8:14:09,  1.64it/s]
 16%|█▌        | 9078/57600 [1:35:43<8:26:27,  1.60it/s]
 16%|█▌        | 9079/57600 [1:35:44<8:17:42,  1.62it/s]
 16%|█▌        | 9080/57600 [1:35:45<8:22:27,  1.61it/s]
                                                        
{'loss': 1.4069, 'learning_rate': 8.60766550522648e-07, 'epoch': 100.22}

 16%|█▌        | 9080/57600 [1:35:45<8:22:27,  1.61it/s]
 16%|█▌        | 9081/57600 [1:35:45<8:39:40,  1.56it/s]
 16%|█▌        | 9082/57600 [1:35:46<8:29:54,  1.59it/s]
 16%|█▌        | 9083/57600 [1:35:47<8:37:27,  1.56it/s]
 16%|█▌        | 9084/57600 [1:35:47<8:36:32,  1.57it/s]
 16%|█▌        | 9085/57600 [1:35:48<8:30:25,  1.58it/s]
 16%|█▌        | 9086/57600 [1:35:49<8:49:17,  1.53it/s]
 16%|█▌        | 9087/57600 [1:35:49<8:36:44,  1.56it/s]
 16%|█▌        | 9088/57600 [1:35:50<8:26:15,  1.60it/s]
 16%|█▌        | 9089/57600 [1:35:50<8:21:12,  1.61it/s]
 16%|█▌        | 9090/57600 [1:35:51<8:25:45,  1.60it/s]
 16%|█▌        | 9091/57600 [1:35:52<8:16:30,  1.63it/s]
 16%|█▌        | 9092/57600 [1:35:52<8:15:00,  1.63it/s]
 16%|█▌        | 9093/57600 [1:35:53<8:22:15,  1.61it/s]
 16%|█▌        | 9094/57600 [1:35:53<8:24:19,  1.60it/s]
 16%|█▌        | 9095/57600 [1:35:54<8:41:37,  1.55it/s]
 16%|█▌        | 9096/57600 [1:35:55<8:51:36,  1.52it/s]
 16%|█▌        | 9097/57600 [1:35:55<8:35:01,  1.57it/s]
 16%|█▌        | 9098/57600 [1:35:56<8:26:09,  1.60it/s]
 16%|█▌        | 9099/57600 [1:35:57<8:23:40,  1.60it/s]
 16%|█▌        | 9100/57600 [1:35:57<8:41:47,  1.55it/s]
                                                        
{'loss': 1.3562, 'learning_rate': 8.604529616724739e-07, 'epoch': 100.44}

 16%|█▌        | 9100/57600 [1:35:57<8:41:47,  1.55it/s]
 16%|█▌        | 9101/57600 [1:35:58<8:26:09,  1.60it/s]
 16%|█▌        | 9102/57600 [1:35:59<8:33:20,  1.57it/s]
 16%|█▌        | 9103/57600 [1:35:59<8:31:51,  1.58it/s]
 16%|█▌        | 9104/57600 [1:36:00<8:23:06,  1.61it/s]
 16%|█▌        | 9105/57600 [1:36:00<8:13:34,  1.64it/s]
 16%|█▌        | 9106/57600 [1:36:01<8:18:02,  1.62it/s]
 16%|█▌        | 9107/57600 [1:36:02<8:29:25,  1.59it/s]
 16%|█▌        | 9108/57600 [1:36:02<8:16:52,  1.63it/s]
 16%|█▌        | 9109/57600 [1:36:03<8:25:20,  1.60it/s]
 16%|█▌        | 9110/57600 [1:36:04<8:23:00,  1.61it/s]
 16%|█▌        | 9111/57600 [1:36:04<8:11:12,  1.65it/s]
 16%|█▌        | 9112/57600 [1:36:05<8:22:14,  1.61it/s]
 16%|█▌        | 9113/57600 [1:36:05<8:30:33,  1.58it/s]
 16%|█▌        | 9114/57600 [1:36:06<8:37:15,  1.56it/s]
 16%|█▌        | 9115/57600 [1:36:07<8:22:55,  1.61it/s]
 16%|█▌        | 9116/57600 [1:36:07<8:17:13,  1.63it/s]
 16%|█▌        | 9117/57600 [1:36:08<8:30:13,  1.58it/s]
 16%|█▌        | 9118/57600 [1:36:09<8:29:10,  1.59it/s]
 16%|█▌        | 9119/57600 [1:36:09<8:30:22,  1.58it/s]
 16%|█▌        | 9120/57600 [1:36:10<8:36:11,  1.57it/s]
                                                        
{'loss': 1.3854, 'learning_rate': 8.601393728222996e-07, 'epoch': 100.66}

 16%|█▌        | 9120/57600 [1:36:10<8:36:11,  1.57it/s]
 16%|█▌        | 9121/57600 [1:36:10<8:26:06,  1.60it/s]
 16%|█▌        | 9122/57600 [1:36:11<8:09:31,  1.65it/s]
 16%|█▌        | 9123/57600 [1:36:12<8:11:25,  1.64it/s]
 16%|█▌        | 9124/57600 [1:36:12<8:30:03,  1.58it/s]
 16%|█▌        | 9125/57600 [1:36:13<8:46:15,  1.54it/s]
 16%|█▌        | 9126/57600 [1:36:14<8:59:29,  1.50it/s]
 16%|█▌        | 9127/57600 [1:36:14<8:46:58,  1.53it/s]
 16%|█▌        | 9128/57600 [1:36:15<8:21:15,  1.61it/s]
 16%|█▌        | 9129/57600 [1:36:16<8:38:58,  1.56it/s]
 16%|█▌        | 9130/57600 [1:36:16<8:43:16,  1.54it/s]
 16%|█▌        | 9131/57600 [1:36:17<8:36:59,  1.56it/s]
 16%|█▌        | 9132/57600 [1:36:18<8:45:52,  1.54it/s]
 16%|█▌        | 9133/57600 [1:36:18<8:45:24,  1.54it/s]
 16%|█▌        | 9134/57600 [1:36:19<8:36:36,  1.56it/s]
 16%|█▌        | 9135/57600 [1:36:19<8:27:50,  1.59it/s]
 16%|█▌        | 9136/57600 [1:36:20<8:18:41,  1.62it/s]
 16%|█▌        | 9137/57600 [1:36:21<8:25:01,  1.60it/s]
 16%|█▌        | 9138/57600 [1:36:21<8:16:54,  1.63it/s]
 16%|█▌        | 9139/57600 [1:36:22<8:15:01,  1.63it/s]
 16%|█▌        | 9140/57600 [1:36:22<8:12:29,  1.64it/s]
                                                        
{'loss': 1.3842, 'learning_rate': 8.598257839721255e-07, 'epoch': 100.88}

 16%|█▌        | 9140/57600 [1:36:22<8:12:29,  1.64it/s]
 16%|█▌        | 9141/57600 [1:36:23<8:13:35,  1.64it/s]
 16%|█▌        | 9142/57600 [1:36:24<8:05:45,  1.66it/s]
 16%|█▌        | 9143/57600 [1:36:24<8:03:33,  1.67it/s]
 16%|█▌        | 9144/57600 [1:36:25<7:53:46,  1.70it/s]
 16%|█▌        | 9145/57600 [1:36:25<8:13:51,  1.64it/s]
 16%|█▌        | 9146/57600 [1:36:26<8:06:43,  1.66it/s]
 16%|█▌        | 9147/57600 [1:36:27<8:17:01,  1.62it/s]
 16%|█▌        | 9148/57600 [1:36:27<8:08:51,  1.65it/s]
 16%|█▌        | 9149/57600 [1:36:28<8:13:00,  1.64it/s]
 16%|█▌        | 9150/57600 [1:36:29<8:26:47,  1.59it/s]
 16%|█▌        | 9151/57600 [1:36:29<8:32:12,  1.58it/s]
 16%|█▌        | 9152/57600 [1:36:30<8:20:19,  1.61it/s]
 16%|█▌        | 9153/57600 [1:36:30<8:25:29,  1.60it/s]
 16%|█▌        | 9154/57600 [1:36:31<8:13:05,  1.64it/s]
 16%|█▌        | 9155/57600 [1:36:32<8:14:04,  1.63it/s]
 16%|█▌        | 9156/57600 [1:36:32<8:26:14,  1.59it/s]
 16%|█▌        | 9157/57600 [1:36:33<8:21:18,  1.61it/s]
 16%|█▌        | 9158/57600 [1:36:34<8:43:13,  1.54it/s]
 16%|█▌        | 9159/57600 [1:36:34<8:54:37,  1.51it/s]
 16%|█▌        | 9160/57600 [1:36:35<8:39:08,  1.56it/s]
                                                        
{'loss': 1.3954, 'learning_rate': 8.595121951219512e-07, 'epoch': 101.1}

 16%|█▌        | 9160/57600 [1:36:35<8:39:08,  1.56it/s]
 16%|█▌        | 9161/57600 [1:36:36<8:58:28,  1.50it/s]
 16%|█▌        | 9162/57600 [1:36:36<8:46:45,  1.53it/s]
 16%|█▌        | 9163/57600 [1:36:37<8:41:15,  1.55it/s]
 16%|█▌        | 9164/57600 [1:36:37<8:18:49,  1.62it/s]
 16%|█▌        | 9165/57600 [1:36:38<8:40:32,  1.55it/s]
 16%|█▌        | 9166/57600 [1:36:39<8:38:27,  1.56it/s]
 16%|█▌        | 9167/57600 [1:36:39<8:21:31,  1.61it/s]
 16%|█▌        | 9168/57600 [1:36:40<7:58:32,  1.69it/s]
 16%|█▌        | 9169/57600 [1:36:40<8:11:13,  1.64it/s]
 16%|█▌        | 9170/57600 [1:36:41<8:23:00,  1.60it/s]
 16%|█▌        | 9171/57600 [1:36:42<8:11:15,  1.64it/s]
 16%|█▌        | 9172/57600 [1:36:42<7:51:31,  1.71it/s]
 16%|█▌        | 9173/57600 [1:36:43<7:45:46,  1.73it/s]
 16%|█▌        | 9174/57600 [1:36:43<7:49:14,  1.72it/s]
 16%|█▌        | 9175/57600 [1:36:44<8:20:57,  1.61it/s]
 16%|█▌        | 9176/57600 [1:36:45<8:26:43,  1.59it/s]
 16%|█▌        | 9177/57600 [1:36:45<8:16:01,  1.63it/s]
 16%|█▌        | 9178/57600 [1:36:46<8:17:46,  1.62it/s]
 16%|█▌        | 9179/57600 [1:36:47<8:18:08,  1.62it/s]
 16%|█▌        | 9180/57600 [1:36:47<8:08:56,  1.65it/s]
                                                        
{'loss': 1.3966, 'learning_rate': 8.59198606271777e-07, 'epoch': 101.32}

 16%|█▌        | 9180/57600 [1:36:47<8:08:56,  1.65it/s]
 16%|█▌        | 9181/57600 [1:36:48<8:15:55,  1.63it/s]
 16%|█▌        | 9182/57600 [1:36:48<8:07:00,  1.66it/s]
 16%|█▌        | 9183/57600 [1:36:49<8:11:17,  1.64it/s]
 16%|█▌        | 9184/57600 [1:36:50<8:13:43,  1.63it/s]
 16%|█▌        | 9185/57600 [1:36:50<8:07:07,  1.66it/s]
 16%|█▌        | 9186/57600 [1:36:51<8:03:47,  1.67it/s]
 16%|█▌        | 9187/57600 [1:36:51<8:14:02,  1.63it/s]
 16%|█▌        | 9188/57600 [1:36:52<8:10:25,  1.65it/s]
 16%|█▌        | 9189/57600 [1:36:53<8:11:21,  1.64it/s]
 16%|█▌        | 9190/57600 [1:36:53<8:03:37,  1.67it/s]
 16%|█▌        | 9191/57600 [1:36:54<8:05:54,  1.66it/s]
 16%|█▌        | 9192/57600 [1:36:54<8:12:07,  1.64it/s]
 16%|█▌        | 9193/57600 [1:36:55<8:05:42,  1.66it/s]
 16%|█▌        | 9194/57600 [1:36:56<7:58:34,  1.69it/s]
 16%|█▌        | 9195/57600 [1:36:56<8:04:34,  1.66it/s]
 16%|█▌        | 9196/57600 [1:36:57<8:09:37,  1.65it/s]
 16%|█▌        | 9197/57600 [1:36:57<8:10:20,  1.65it/s]
 16%|█▌        | 9198/57600 [1:36:58<7:53:41,  1.70it/s]
 16%|█▌        | 9199/57600 [1:36:59<7:51:35,  1.71it/s]
 16%|█▌        | 9200/57600 [1:36:59<7:55:30,  1.70it/s]
                                                        
{'loss': 1.4175, 'learning_rate': 8.588850174216027e-07, 'epoch': 101.55}

 16%|█▌        | 9200/57600 [1:36:59<7:55:30,  1.70it/s]
 16%|█▌        | 9201/57600 [1:37:00<7:51:48,  1.71it/s]
 16%|█▌        | 9202/57600 [1:37:00<7:55:21,  1.70it/s]
 16%|█▌        | 9203/57600 [1:37:01<7:58:04,  1.69it/s]
 16%|█▌        | 9204/57600 [1:37:02<7:51:55,  1.71it/s]
 16%|█▌        | 9205/57600 [1:37:02<7:56:05,  1.69it/s]
 16%|█▌        | 9206/57600 [1:37:03<8:12:59,  1.64it/s]
 16%|█▌        | 9207/57600 [1:37:03<8:16:18,  1.63it/s]
 16%|█▌        | 9208/57600 [1:37:04<8:05:24,  1.66it/s]
 16%|█▌        | 9209/57600 [1:37:05<8:03:32,  1.67it/s]
 16%|█▌        | 9210/57600 [1:37:05<8:20:06,  1.61it/s]
 16%|█▌        | 9211/57600 [1:37:06<8:25:00,  1.60it/s]
 16%|█▌        | 9212/57600 [1:37:06<8:17:50,  1.62it/s]
 16%|█▌        | 9213/57600 [1:37:07<8:15:35,  1.63it/s]
 16%|█▌        | 9214/57600 [1:37:08<8:31:12,  1.58it/s]
 16%|█▌        | 9215/57600 [1:37:08<8:21:03,  1.61it/s]
 16%|█▌        | 9216/57600 [1:37:09<8:11:38,  1.64it/s]
 16%|█▌        | 9217/57600 [1:37:10<8:19:13,  1.62it/s]
 16%|█▌        | 9218/57600 [1:37:10<8:07:14,  1.65it/s]
 16%|█▌        | 9219/57600 [1:37:11<8:10:10,  1.65it/s]
 16%|█▌        | 9220/57600 [1:37:11<8:30:31,  1.58it/s]
                                                        
{'loss': 1.3944, 'learning_rate': 8.585714285714286e-07, 'epoch': 101.77}

 16%|█▌        | 9220/57600 [1:37:11<8:30:31,  1.58it/s]
 16%|█▌        | 9221/57600 [1:37:12<8:42:18,  1.54it/s]
 16%|█▌        | 9222/57600 [1:37:13<8:36:42,  1.56it/s]
 16%|█▌        | 9223/57600 [1:37:13<8:20:22,  1.61it/s]
 16%|█▌        | 9224/57600 [1:37:14<8:43:41,  1.54it/s]
 16%|█▌        | 9225/57600 [1:37:15<8:43:43,  1.54it/s]
 16%|█▌        | 9226/57600 [1:37:15<8:27:07,  1.59it/s]
 16%|█▌        | 9227/57600 [1:37:16<8:24:32,  1.60it/s]
 16%|█▌        | 9228/57600 [1:37:16<8:15:40,  1.63it/s]
 16%|█▌        | 9229/57600 [1:37:17<8:17:50,  1.62it/s]
 16%|█▌        | 9230/57600 [1:37:18<8:35:04,  1.57it/s]
 16%|█▌        | 9231/57600 [1:37:18<8:36:39,  1.56it/s]
 16%|█▌        | 9232/57600 [1:37:19<8:32:34,  1.57it/s]
 16%|█▌        | 9233/57600 [1:37:20<8:57:55,  1.50it/s]
 16%|█▌        | 9234/57600 [1:37:20<8:41:37,  1.55it/s]
 16%|█▌        | 9235/57600 [1:37:21<8:29:00,  1.58it/s]
 16%|█▌        | 9236/57600 [1:37:22<8:23:15,  1.60it/s]
 16%|█▌        | 9237/57600 [1:37:22<8:25:52,  1.59it/s]
 16%|█▌        | 9238/57600 [1:37:23<8:21:51,  1.61it/s]
 16%|█▌        | 9239/57600 [1:37:23<8:11:06,  1.64it/s]
 16%|█▌        | 9240/57600 [1:37:24<8:03:27,  1.67it/s]
                                                        
{'loss': 1.343, 'learning_rate': 8.582578397212543e-07, 'epoch': 101.99}

 16%|█▌        | 9240/57600 [1:37:24<8:03:27,  1.67it/s]
 16%|█▌        | 9241/57600 [1:37:25<8:27:03,  1.59it/s]
 16%|█▌        | 9242/57600 [1:37:25<8:42:31,  1.54it/s]
 16%|█▌        | 9243/57600 [1:37:26<8:42:01,  1.54it/s]
 16%|█▌        | 9244/57600 [1:37:27<8:28:32,  1.58it/s]
 16%|█▌        | 9245/57600 [1:37:27<8:38:40,  1.55it/s]
 16%|█▌        | 9246/57600 [1:37:28<8:50:51,  1.52it/s]
 16%|█▌        | 9247/57600 [1:37:29<9:03:23,  1.48it/s]
 16%|█▌        | 9248/57600 [1:37:29<8:57:43,  1.50it/s]
 16%|█▌        | 9249/57600 [1:37:30<8:51:23,  1.52it/s]
 16%|█▌        | 9250/57600 [1:37:31<8:36:04,  1.56it/s]
 16%|█▌        | 9251/57600 [1:37:31<8:24:20,  1.60it/s]
 16%|█▌        | 9252/57600 [1:37:32<8:32:30,  1.57it/s]
 16%|█▌        | 9253/57600 [1:37:32<8:18:40,  1.62it/s]
 16%|█▌        | 9254/57600 [1:37:33<8:29:36,  1.58it/s]
 16%|█▌        | 9255/57600 [1:37:34<8:05:14,  1.66it/s]
 16%|█▌        | 9256/57600 [1:37:34<7:57:24,  1.69it/s]
 16%|█▌        | 9257/57600 [1:37:35<8:10:39,  1.64it/s]
 16%|█▌        | 9258/57600 [1:37:35<8:06:40,  1.66it/s]
 16%|█▌        | 9259/57600 [1:37:36<8:18:16,  1.62it/s]
 16%|█▌        | 9260/57600 [1:37:37<8:09:55,  1.64it/s]
                                                        
{'loss': 1.3974, 'learning_rate': 8.579442508710801e-07, 'epoch': 102.21}

 16%|█▌        | 9260/57600 [1:37:37<8:09:55,  1.64it/s]
 16%|█▌        | 9261/57600 [1:37:37<8:15:04,  1.63it/s]
 16%|█▌        | 9262/57600 [1:37:38<8:20:48,  1.61it/s]
 16%|█▌        | 9263/57600 [1:37:39<8:07:51,  1.65it/s]
 16%|█▌        | 9264/57600 [1:37:39<8:12:42,  1.64it/s]
 16%|█▌        | 9265/57600 [1:37:40<8:09:30,  1.65it/s]
 16%|█▌        | 9266/57600 [1:37:40<7:56:46,  1.69it/s]
 16%|█▌        | 9267/57600 [1:37:41<8:03:31,  1.67it/s]
 16%|█▌        | 9268/57600 [1:37:42<8:09:50,  1.64it/s]
 16%|█▌        | 9269/57600 [1:37:42<7:56:46,  1.69it/s]
 16%|█▌        | 9270/57600 [1:37:43<8:06:03,  1.66it/s]
 16%|█▌        | 9271/57600 [1:37:43<7:52:25,  1.71it/s]
 16%|█▌        | 9272/57600 [1:37:44<8:05:49,  1.66it/s]
 16%|█▌        | 9273/57600 [1:37:44<7:57:22,  1.69it/s]
 16%|█▌        | 9274/57600 [1:37:45<8:05:26,  1.66it/s]
 16%|█▌        | 9275/57600 [1:37:46<8:30:21,  1.58it/s]
 16%|█▌        | 9276/57600 [1:37:46<8:19:40,  1.61it/s]
 16%|█▌        | 9277/57600 [1:37:47<8:05:16,  1.66it/s]
 16%|█▌        | 9278/57600 [1:37:48<7:57:11,  1.69it/s]
 16%|█▌        | 9279/57600 [1:37:48<8:21:37,  1.61it/s]
 16%|█▌        | 9280/57600 [1:37:49<8:12:20,  1.64it/s]
                                                        
{'loss': 1.4235, 'learning_rate': 8.576306620209059e-07, 'epoch': 102.43}

 16%|█▌        | 9280/57600 [1:37:49<8:12:20,  1.64it/s]
 16%|█▌        | 9281/57600 [1:37:49<8:15:44,  1.62it/s]
 16%|█▌        | 9282/57600 [1:37:50<8:07:15,  1.65it/s]
 16%|█▌        | 9283/57600 [1:37:51<7:59:42,  1.68it/s]
 16%|█▌        | 9284/57600 [1:37:51<8:09:22,  1.65it/s]
 16%|█▌        | 9285/57600 [1:37:52<7:56:05,  1.69it/s]
 16%|█▌        | 9286/57600 [1:37:52<7:44:41,  1.73it/s]
 16%|█▌        | 9287/57600 [1:37:53<7:49:33,  1.71it/s]
 16%|█▌        | 9288/57600 [1:37:54<8:11:43,  1.64it/s]
 16%|█▌        | 9289/57600 [1:37:54<8:19:00,  1.61it/s]
 16%|█▌        | 9290/57600 [1:37:55<8:20:40,  1.61it/s]
 16%|█▌        | 9291/57600 [1:37:56<8:37:44,  1.56it/s]
 16%|█▌        | 9292/57600 [1:37:56<8:26:04,  1.59it/s]
 16%|█▌        | 9293/57600 [1:37:57<8:38:10,  1.55it/s]
 16%|█▌        | 9294/57600 [1:37:57<8:30:29,  1.58it/s]
 16%|█▌        | 9295/57600 [1:37:58<8:38:33,  1.55it/s]
 16%|█▌        | 9296/57600 [1:37:59<8:42:26,  1.54it/s]
 16%|█▌        | 9297/57600 [1:37:59<8:53:42,  1.51it/s]
 16%|█▌        | 9298/57600 [1:38:00<8:40:03,  1.55it/s]
 16%|█▌        | 9299/57600 [1:38:01<8:21:57,  1.60it/s]
 16%|█▌        | 9300/57600 [1:38:01<8:09:21,  1.65it/s]
                                                        
{'loss': 1.379, 'learning_rate': 8.573170731707317e-07, 'epoch': 102.65}

 16%|█▌        | 9300/57600 [1:38:01<8:09:21,  1.65it/s]
 16%|█▌        | 9301/57600 [1:38:02<8:00:50,  1.67it/s]
 16%|█▌        | 9302/57600 [1:38:02<8:03:38,  1.66it/s]
 16%|█▌        | 9303/57600 [1:38:03<8:00:10,  1.68it/s]
 16%|█▌        | 9304/57600 [1:38:04<7:47:34,  1.72it/s]
 16%|█▌        | 9305/57600 [1:38:04<7:52:38,  1.70it/s]
 16%|█▌        | 9306/57600 [1:38:05<7:45:22,  1.73it/s]
 16%|█▌        | 9307/57600 [1:38:05<8:09:46,  1.64it/s]
 16%|█▌        | 9308/57600 [1:38:06<8:23:35,  1.60it/s]
 16%|█▌        | 9309/57600 [1:38:07<8:16:20,  1.62it/s]
 16%|█▌        | 9310/57600 [1:38:07<8:48:20,  1.52it/s]
 16%|█▌        | 9311/57600 [1:38:08<8:42:29,  1.54it/s]
 16%|█▌        | 9312/57600 [1:38:09<8:41:33,  1.54it/s]
 16%|█▌        | 9313/57600 [1:38:09<8:27:16,  1.59it/s]
 16%|█▌        | 9314/57600 [1:38:10<8:07:19,  1.65it/s]
 16%|█▌        | 9315/57600 [1:38:10<8:19:36,  1.61it/s]
 16%|█▌        | 9316/57600 [1:38:11<8:24:51,  1.59it/s]
 16%|█▌        | 9317/57600 [1:38:12<8:18:55,  1.61it/s]
 16%|█▌        | 9318/57600 [1:38:12<8:20:52,  1.61it/s]
 16%|█▌        | 9319/57600 [1:38:13<8:30:40,  1.58it/s]
 16%|█▌        | 9320/57600 [1:38:14<8:18:48,  1.61it/s]
                                                        
{'loss': 1.3593, 'learning_rate': 8.570034843205574e-07, 'epoch': 102.87}

 16%|█▌        | 9320/57600 [1:38:14<8:18:48,  1.61it/s]
 16%|█▌        | 9321/57600 [1:38:14<8:15:47,  1.62it/s]
 16%|█▌        | 9322/57600 [1:38:15<8:02:49,  1.67it/s]
 16%|█▌        | 9323/57600 [1:38:15<7:52:30,  1.70it/s]
 16%|█▌        | 9324/57600 [1:38:16<8:06:32,  1.65it/s]
 16%|█▌        | 9325/57600 [1:38:17<7:55:10,  1.69it/s]
 16%|█▌        | 9326/57600 [1:38:17<7:39:52,  1.75it/s]
 16%|█▌        | 9327/57600 [1:38:18<7:43:16,  1.74it/s]
 16%|█▌        | 9328/57600 [1:38:18<7:46:34,  1.72it/s]
 16%|█▌        | 9329/57600 [1:38:19<7:52:34,  1.70it/s]
 16%|█▌        | 9330/57600 [1:38:19<7:52:15,  1.70it/s]
 16%|█▌        | 9331/57600 [1:38:20<8:11:53,  1.64it/s]
 16%|█▌        | 9332/57600 [1:38:21<8:31:12,  1.57it/s]
 16%|█▌        | 9333/57600 [1:38:21<8:21:54,  1.60it/s]
 16%|█▌        | 9334/57600 [1:38:22<8:22:13,  1.60it/s]
 16%|█▌        | 9335/57600 [1:38:23<8:18:00,  1.62it/s]
 16%|█▌        | 9336/57600 [1:38:23<8:26:34,  1.59it/s]
 16%|█▌        | 9337/57600 [1:38:24<8:15:27,  1.62it/s]
 16%|█▌        | 9338/57600 [1:38:24<7:56:12,  1.69it/s]
 16%|█▌        | 9339/57600 [1:38:25<8:21:20,  1.60it/s]
 16%|█▌        | 9340/57600 [1:38:26<8:30:01,  1.58it/s]
                                                        
{'loss': 1.4164, 'learning_rate': 8.566898954703832e-07, 'epoch': 103.09}

 16%|█▌        | 9340/57600 [1:38:26<8:30:01,  1.58it/s]
 16%|█▌        | 9341/57600 [1:38:26<8:19:52,  1.61it/s]
 16%|█▌        | 9342/57600 [1:38:27<8:23:30,  1.60it/s]
 16%|█▌        | 9343/57600 [1:38:28<8:20:36,  1.61it/s]
 16%|█▌        | 9344/57600 [1:38:28<8:11:30,  1.64it/s]
 16%|█▌        | 9345/57600 [1:38:29<8:13:29,  1.63it/s]
 16%|█▌        | 9346/57600 [1:38:29<8:09:20,  1.64it/s]
 16%|█▌        | 9347/57600 [1:38:30<8:07:55,  1.65it/s]
 16%|█▌        | 9348/57600 [1:38:31<8:22:42,  1.60it/s]
 16%|█▌        | 9349/57600 [1:38:31<8:05:38,  1.66it/s]
 16%|█▌        | 9350/57600 [1:38:32<8:00:45,  1.67it/s]
 16%|█▌        | 9351/57600 [1:38:32<8:11:36,  1.64it/s]
 16%|█▌        | 9352/57600 [1:38:33<8:18:46,  1.61it/s]
 16%|█▌        | 9353/57600 [1:38:34<8:04:52,  1.66it/s]
 16%|█▌        | 9354/57600 [1:38:34<8:26:14,  1.59it/s]
 16%|█▌        | 9355/57600 [1:38:35<8:05:38,  1.66it/s]
 16%|█▌        | 9356/57600 [1:38:36<8:18:39,  1.61it/s]
 16%|█▌        | 9357/57600 [1:38:36<8:11:37,  1.64it/s]
 16%|█▌        | 9358/57600 [1:38:37<8:27:55,  1.58it/s]
 16%|█▌        | 9359/57600 [1:38:37<8:34:21,  1.56it/s]
 16%|█▋        | 9360/57600 [1:38:38<8:36:19,  1.56it/s]
                                                        
{'loss': 1.3811, 'learning_rate': 8.563763066202091e-07, 'epoch': 103.31}

 16%|█▋        | 9360/57600 [1:38:38<8:36:19,  1.56it/s]
 16%|█▋        | 9361/57600 [1:38:39<8:21:44,  1.60it/s]
 16%|█▋        | 9362/57600 [1:38:39<8:33:28,  1.57it/s]
 16%|█▋        | 9363/57600 [1:38:40<8:27:06,  1.59it/s]
 16%|█▋        | 9364/57600 [1:38:41<8:23:09,  1.60it/s]
 16%|█▋        | 9365/57600 [1:38:41<8:29:31,  1.58it/s]
 16%|█▋        | 9366/57600 [1:38:42<8:31:02,  1.57it/s]
 16%|█▋        | 9367/57600 [1:38:42<8:26:53,  1.59it/s]
 16%|█▋        | 9368/57600 [1:38:43<8:42:10,  1.54it/s]
 16%|█▋        | 9369/57600 [1:38:44<8:36:57,  1.55it/s]
 16%|█▋        | 9370/57600 [1:38:44<8:19:57,  1.61it/s]
 16%|█▋        | 9371/57600 [1:38:45<8:27:09,  1.58it/s]
 16%|█▋        | 9372/57600 [1:38:46<8:18:15,  1.61it/s]
 16%|█▋        | 9373/57600 [1:38:46<8:10:27,  1.64it/s]
 16%|█▋        | 9374/57600 [1:38:47<8:04:31,  1.66it/s]
 16%|█▋        | 9375/57600 [1:38:47<8:20:15,  1.61it/s]
 16%|█▋        | 9376/57600 [1:38:48<8:13:24,  1.63it/s]
 16%|█▋        | 9377/57600 [1:38:49<8:10:49,  1.64it/s]
 16%|█▋        | 9378/57600 [1:38:49<8:29:51,  1.58it/s]
 16%|█▋        | 9379/57600 [1:38:50<8:22:12,  1.60it/s]
 16%|█▋        | 9380/57600 [1:38:51<8:39:05,  1.55it/s]
                                                        
{'loss': 1.3853, 'learning_rate': 8.560627177700348e-07, 'epoch': 103.53}

 16%|█▋        | 9380/57600 [1:38:51<8:39:05,  1.55it/s]
 16%|█▋        | 9381/57600 [1:38:51<8:43:54,  1.53it/s]
 16%|█▋        | 9382/57600 [1:38:52<8:51:11,  1.51it/s]
 16%|█▋        | 9383/57600 [1:38:53<8:47:53,  1.52it/s]
 16%|█▋        | 9384/57600 [1:38:53<8:23:33,  1.60it/s]
 16%|█▋        | 9385/57600 [1:38:54<8:50:08,  1.52it/s]
 16%|█▋        | 9386/57600 [1:38:55<8:27:54,  1.58it/s]
 16%|█▋        | 9387/57600 [1:38:55<8:14:30,  1.62it/s]
 16%|█▋        | 9388/57600 [1:38:56<8:05:41,  1.65it/s]
 16%|█▋        | 9389/57600 [1:38:56<8:12:00,  1.63it/s]
 16%|█▋        | 9390/57600 [1:38:57<7:57:14,  1.68it/s]
 16%|█▋        | 9391/57600 [1:38:57<8:02:43,  1.66it/s]
 16%|█▋        | 9392/57600 [1:38:58<8:11:25,  1.63it/s]
 16%|█▋        | 9393/57600 [1:38:59<8:18:23,  1.61it/s]
 16%|█▋        | 9394/57600 [1:38:59<8:28:17,  1.58it/s]
 16%|█▋        | 9395/57600 [1:39:00<8:34:50,  1.56it/s]
 16%|█▋        | 9396/57600 [1:39:01<8:30:04,  1.58it/s]
 16%|█▋        | 9397/57600 [1:39:01<8:25:49,  1.59it/s]
 16%|█▋        | 9398/57600 [1:39:02<8:22:08,  1.60it/s]
 16%|█▋        | 9399/57600 [1:39:02<8:09:18,  1.64it/s]
 16%|█▋        | 9400/57600 [1:39:03<8:03:09,  1.66it/s]
                                                        
{'loss': 1.3948, 'learning_rate': 8.557491289198606e-07, 'epoch': 103.75}

 16%|█▋        | 9400/57600 [1:39:03<8:03:09,  1.66it/s]
 16%|█▋        | 9401/57600 [1:39:04<7:51:44,  1.70it/s]
 16%|█▋        | 9402/57600 [1:39:04<7:48:40,  1.71it/s]
 16%|█▋        | 9403/57600 [1:39:05<7:55:26,  1.69it/s]
 16%|█▋        | 9404/57600 [1:39:05<7:56:31,  1.69it/s]
 16%|█▋        | 9405/57600 [1:39:06<8:17:12,  1.62it/s]
 16%|█▋        | 9406/57600 [1:39:07<8:23:23,  1.60it/s]
 16%|█▋        | 9407/57600 [1:39:07<8:32:37,  1.57it/s]
 16%|█▋        | 9408/57600 [1:39:08<8:26:50,  1.58it/s]
 16%|█▋        | 9409/57600 [1:39:09<8:29:40,  1.58it/s]
 16%|█▋        | 9410/57600 [1:39:09<8:11:14,  1.63it/s]
 16%|█▋        | 9411/57600 [1:39:10<8:21:29,  1.60it/s]
 16%|█▋        | 9412/57600 [1:39:10<8:23:50,  1.59it/s]
 16%|█▋        | 9413/57600 [1:39:11<8:16:04,  1.62it/s]
 16%|█▋        | 9414/57600 [1:39:12<8:31:33,  1.57it/s]
 16%|█▋        | 9415/57600 [1:39:12<8:23:46,  1.59it/s]
 16%|█▋        | 9416/57600 [1:39:13<8:28:35,  1.58it/s]
 16%|█▋        | 9417/57600 [1:39:14<8:28:19,  1.58it/s]
 16%|█▋        | 9418/57600 [1:39:14<8:26:45,  1.58it/s]
 16%|█▋        | 9419/57600 [1:39:15<8:15:22,  1.62it/s]
 16%|█▋        | 9420/57600 [1:39:15<8:08:01,  1.65it/s]
                                                        
{'loss': 1.4206, 'learning_rate': 8.554355400696864e-07, 'epoch': 103.97}

 16%|█▋        | 9420/57600 [1:39:15<8:08:01,  1.65it/s]
 16%|█▋        | 9421/57600 [1:39:16<8:29:27,  1.58it/s]
 16%|█▋        | 9422/57600 [1:39:17<8:24:49,  1.59it/s]
 16%|█▋        | 9423/57600 [1:39:17<8:49:47,  1.52it/s]
 16%|█▋        | 9424/57600 [1:39:18<8:43:38,  1.53it/s]
 16%|█▋        | 9425/57600 [1:39:19<8:33:51,  1.56it/s]
 16%|█▋        | 9426/57600 [1:39:19<8:36:18,  1.56it/s]
 16%|█▋        | 9427/57600 [1:39:20<8:20:55,  1.60it/s]
 16%|█▋        | 9428/57600 [1:39:21<8:04:49,  1.66it/s]
 16%|█▋        | 9429/57600 [1:39:21<8:03:00,  1.66it/s]
 16%|█▋        | 9430/57600 [1:39:22<8:08:59,  1.64it/s]
 16%|█▋        | 9431/57600 [1:39:22<8:06:14,  1.65it/s]
 16%|█▋        | 9432/57600 [1:39:23<8:01:56,  1.67it/s]
 16%|█▋        | 9433/57600 [1:39:24<8:02:56,  1.66it/s]
 16%|█▋        | 9434/57600 [1:39:24<8:09:45,  1.64it/s]
 16%|█▋        | 9435/57600 [1:39:25<8:11:17,  1.63it/s]
 16%|█▋        | 9436/57600 [1:39:25<8:09:36,  1.64it/s]
 16%|█▋        | 9437/57600 [1:39:26<8:18:21,  1.61it/s]
 16%|█▋        | 9438/57600 [1:39:27<8:23:41,  1.59it/s]
 16%|█▋        | 9439/57600 [1:39:27<8:22:38,  1.60it/s]
 16%|█▋        | 9440/57600 [1:39:28<8:16:47,  1.62it/s]
                                                        
{'loss': 1.3967, 'learning_rate': 8.551219512195122e-07, 'epoch': 104.19}

 16%|█▋        | 9440/57600 [1:39:28<8:16:47,  1.62it/s]
 16%|█▋        | 9441/57600 [1:39:28<8:08:27,  1.64it/s]
 16%|█▋        | 9442/57600 [1:39:29<8:02:11,  1.66it/s]
 16%|█▋        | 9443/57600 [1:39:30<8:14:34,  1.62it/s]
 16%|█▋        | 9444/57600 [1:39:30<8:06:47,  1.65it/s]
 16%|█▋        | 9445/57600 [1:39:31<8:12:19,  1.63it/s]
 16%|█▋        | 9446/57600 [1:39:32<8:10:30,  1.64it/s]
 16%|█▋        | 9447/57600 [1:39:32<8:07:44,  1.65it/s]
 16%|█▋        | 9448/57600 [1:39:33<8:16:49,  1.62it/s]
 16%|█▋        | 9449/57600 [1:39:33<8:13:43,  1.63it/s]
 16%|█▋        | 9450/57600 [1:39:34<8:09:51,  1.64it/s]
 16%|█▋        | 9451/57600 [1:39:35<8:19:29,  1.61it/s]
 16%|█▋        | 9452/57600 [1:39:35<8:27:45,  1.58it/s]
 16%|█▋        | 9453/57600 [1:39:36<8:43:54,  1.53it/s]
 16%|█▋        | 9454/57600 [1:39:37<8:38:40,  1.55it/s]
 16%|█▋        | 9455/57600 [1:39:37<8:33:56,  1.56it/s]
 16%|█▋        | 9456/57600 [1:39:38<8:45:25,  1.53it/s]
 16%|█▋        | 9457/57600 [1:39:39<8:39:38,  1.54it/s]
 16%|█▋        | 9458/57600 [1:39:39<8:33:58,  1.56it/s]
 16%|█▋        | 9459/57600 [1:39:40<8:32:04,  1.57it/s]
 16%|█▋        | 9460/57600 [1:39:40<8:30:18,  1.57it/s]
                                                        
{'loss': 1.3597, 'learning_rate': 8.548083623693379e-07, 'epoch': 104.42}

 16%|█▋        | 9460/57600 [1:39:40<8:30:18,  1.57it/s]
 16%|█▋        | 9461/57600 [1:39:41<8:14:25,  1.62it/s]
 16%|█▋        | 9462/57600 [1:39:42<8:19:45,  1.61it/s]
 16%|█▋        | 9463/57600 [1:39:42<8:17:16,  1.61it/s]
 16%|█▋        | 9464/57600 [1:39:43<8:16:28,  1.62it/s]
 16%|█▋        | 9465/57600 [1:39:44<8:13:12,  1.63it/s]
 16%|█▋        | 9466/57600 [1:39:44<8:08:53,  1.64it/s]
 16%|█▋        | 9467/57600 [1:39:45<8:05:45,  1.65it/s]
 16%|█▋        | 9468/57600 [1:39:45<8:14:13,  1.62it/s]
 16%|█▋        | 9469/57600 [1:39:46<8:12:14,  1.63it/s]
 16%|█▋        | 9470/57600 [1:39:47<8:15:22,  1.62it/s]
 16%|█▋        | 9471/57600 [1:39:47<8:23:37,  1.59it/s]
 16%|█▋        | 9472/57600 [1:39:48<8:01:30,  1.67it/s]
 16%|█▋        | 9473/57600 [1:39:48<8:05:19,  1.65it/s]
 16%|█▋        | 9474/57600 [1:39:49<8:04:36,  1.66it/s]
 16%|█▋        | 9475/57600 [1:39:50<8:01:16,  1.67it/s]
 16%|█▋        | 9476/57600 [1:39:50<7:59:04,  1.67it/s]
 16%|█▋        | 9477/57600 [1:39:51<8:13:37,  1.62it/s]
 16%|█▋        | 9478/57600 [1:39:51<8:10:11,  1.64it/s]
 16%|█▋        | 9479/57600 [1:39:52<8:22:39,  1.60it/s]
 16%|█▋        | 9480/57600 [1:39:53<8:41:44,  1.54it/s]
                                                        
{'loss': 1.4107, 'learning_rate': 8.544947735191637e-07, 'epoch': 104.64}

 16%|█▋        | 9480/57600 [1:39:53<8:41:44,  1.54it/s]
 16%|█▋        | 9481/57600 [1:39:53<8:27:24,  1.58it/s]
 16%|█▋        | 9482/57600 [1:39:54<8:17:15,  1.61it/s]
 16%|█▋        | 9483/57600 [1:39:55<8:23:39,  1.59it/s]
 16%|█▋        | 9484/57600 [1:39:55<8:33:20,  1.56it/s]
 16%|█▋        | 9485/57600 [1:39:56<8:36:16,  1.55it/s]
 16%|█▋        | 9486/57600 [1:39:57<8:31:44,  1.57it/s]
 16%|█▋        | 9487/57600 [1:39:57<8:29:26,  1.57it/s]
 16%|█▋        | 9488/57600 [1:39:58<8:27:44,  1.58it/s]
 16%|█▋        | 9489/57600 [1:39:58<8:33:54,  1.56it/s]
 16%|█▋        | 9490/57600 [1:39:59<8:14:43,  1.62it/s]
 16%|█▋        | 9491/57600 [1:40:00<8:12:15,  1.63it/s]
 16%|█▋        | 9492/57600 [1:40:00<8:07:36,  1.64it/s]
 16%|█▋        | 9493/57600 [1:40:01<8:15:35,  1.62it/s]
 16%|█▋        | 9494/57600 [1:40:02<8:38:42,  1.55it/s]
 16%|█▋        | 9495/57600 [1:40:02<8:23:16,  1.59it/s]
 16%|█▋        | 9496/57600 [1:40:03<8:08:51,  1.64it/s]
 16%|█▋        | 9497/57600 [1:40:03<8:12:52,  1.63it/s]
 16%|█▋        | 9498/57600 [1:40:04<8:12:55,  1.63it/s]
 16%|█▋        | 9499/57600 [1:40:05<8:22:56,  1.59it/s]
 16%|█▋        | 9500/57600 [1:40:05<8:17:28,  1.61it/s]
                                                        
{'loss': 1.3626, 'learning_rate': 8.541811846689896e-07, 'epoch': 104.86}

 16%|█▋        | 9500/57600 [1:40:05<8:17:28,  1.61it/s]
 16%|█▋        | 9501/57600 [1:40:06<8:11:45,  1.63it/s]
 16%|█▋        | 9502/57600 [1:40:06<8:16:31,  1.61it/s]
 16%|█▋        | 9503/57600 [1:40:07<7:59:46,  1.67it/s]
 16%|█▋        | 9504/57600 [1:40:08<8:01:33,  1.66it/s]
 17%|█▋        | 9505/57600 [1:40:08<8:16:05,  1.62it/s]
 17%|█▋        | 9506/57600 [1:40:09<8:31:51,  1.57it/s]
 17%|█▋        | 9507/57600 [1:40:10<8:15:58,  1.62it/s]
 17%|█▋        | 9508/57600 [1:40:10<8:25:43,  1.58it/s]
 17%|█▋        | 9509/57600 [1:40:11<8:15:03,  1.62it/s]
 17%|█▋        | 9510/57600 [1:40:11<8:26:47,  1.58it/s]
 17%|█▋        | 9511/57600 [1:40:12<8:20:26,  1.60it/s]
 17%|█▋        | 9512/57600 [1:40:13<8:15:56,  1.62it/s]
 17%|█▋        | 9513/57600 [1:40:13<8:31:03,  1.57it/s]
 17%|█▋        | 9514/57600 [1:40:14<8:39:11,  1.54it/s]
 17%|█▋        | 9515/57600 [1:40:15<8:33:59,  1.56it/s]
 17%|█▋        | 9516/57600 [1:40:15<8:12:56,  1.63it/s]
 17%|█▋        | 9517/57600 [1:40:16<8:10:47,  1.63it/s]
 17%|█▋        | 9518/57600 [1:40:17<8:26:53,  1.58it/s]
 17%|█▋        | 9519/57600 [1:40:17<8:17:48,  1.61it/s]
 17%|█▋        | 9520/57600 [1:40:18<8:32:59,  1.56it/s]
                                                        
{'loss': 1.4051, 'learning_rate': 8.538675958188153e-07, 'epoch': 105.08}

 17%|█▋        | 9520/57600 [1:40:18<8:32:59,  1.56it/s]
 17%|█▋        | 9521/57600 [1:40:18<8:39:00,  1.54it/s]
 17%|█▋        | 9522/57600 [1:40:19<8:23:43,  1.59it/s]
 17%|█▋        | 9523/57600 [1:40:20<8:19:46,  1.60it/s]
 17%|█▋        | 9524/57600 [1:40:20<8:22:19,  1.60it/s]
 17%|█▋        | 9525/57600 [1:40:21<8:18:09,  1.61it/s]
 17%|█▋        | 9526/57600 [1:40:22<8:17:21,  1.61it/s]
 17%|█▋        | 9527/57600 [1:40:22<8:23:33,  1.59it/s]
 17%|█▋        | 9528/57600 [1:40:23<8:24:59,  1.59it/s]
 17%|█▋        | 9529/57600 [1:40:23<8:30:11,  1.57it/s]
 17%|█▋        | 9530/57600 [1:40:24<8:20:47,  1.60it/s]
 17%|█▋        | 9531/57600 [1:40:25<8:11:13,  1.63it/s]
 17%|█▋        | 9532/57600 [1:40:25<8:16:23,  1.61it/s]
 17%|█▋        | 9533/57600 [1:40:26<8:31:39,  1.57it/s]
 17%|█▋        | 9534/57600 [1:40:27<8:23:05,  1.59it/s]
 17%|█▋        | 9535/57600 [1:40:27<8:25:20,  1.59it/s]
 17%|█▋        | 9536/57600 [1:40:28<8:31:27,  1.57it/s]
 17%|█▋        | 9537/57600 [1:40:28<8:07:22,  1.64it/s]
 17%|█▋        | 9538/57600 [1:40:29<8:07:26,  1.64it/s]
 17%|█▋        | 9539/57600 [1:40:30<8:05:20,  1.65it/s]
 17%|█▋        | 9540/57600 [1:40:30<8:17:22,  1.61it/s]
                                                        
{'loss': 1.4063, 'learning_rate': 8.53554006968641e-07, 'epoch': 105.3}

 17%|█▋        | 9540/57600 [1:40:30<8:17:22,  1.61it/s]
 17%|█▋        | 9541/57600 [1:40:31<8:13:22,  1.62it/s]
 17%|█▋        | 9542/57600 [1:40:31<8:07:37,  1.64it/s]
 17%|█▋        | 9543/57600 [1:40:32<8:21:43,  1.60it/s]
 17%|█▋        | 9544/57600 [1:40:33<8:18:17,  1.61it/s]
 17%|█▋        | 9545/57600 [1:40:33<8:05:06,  1.65it/s]
 17%|█▋        | 9546/57600 [1:40:34<8:14:48,  1.62it/s]
 17%|█▋        | 9547/57600 [1:40:35<8:10:25,  1.63it/s]
 17%|█▋        | 9548/57600 [1:40:35<8:25:01,  1.59it/s]
 17%|█▋        | 9549/57600 [1:40:36<8:36:12,  1.55it/s]
 17%|█▋        | 9550/57600 [1:40:36<8:20:39,  1.60it/s]
 17%|█▋        | 9551/57600 [1:40:37<8:08:21,  1.64it/s]
 17%|█▋        | 9552/57600 [1:40:38<8:31:07,  1.57it/s]
 17%|█▋        | 9553/57600 [1:40:38<8:18:59,  1.60it/s]
 17%|█▋        | 9554/57600 [1:40:39<8:18:09,  1.61it/s]
 17%|█▋        | 9555/57600 [1:40:40<8:17:41,  1.61it/s]
 17%|█▋        | 9556/57600 [1:40:40<8:19:24,  1.60it/s]
 17%|█▋        | 9557/57600 [1:40:41<8:08:47,  1.64it/s]
 17%|█▋        | 9558/57600 [1:40:41<7:56:09,  1.68it/s]
 17%|█▋        | 9559/57600 [1:40:42<8:03:20,  1.66it/s]
 17%|█▋        | 9560/57600 [1:40:43<8:20:28,  1.60it/s]
                                                        
{'loss': 1.4275, 'learning_rate': 8.532404181184669e-07, 'epoch': 105.52}

 17%|█▋        | 9560/57600 [1:40:43<8:20:28,  1.60it/s]
 17%|█▋        | 9561/57600 [1:40:43<8:16:30,  1.61it/s]
 17%|█▋        | 9562/57600 [1:40:44<8:09:23,  1.64it/s]
 17%|█▋        | 9563/57600 [1:40:44<8:22:46,  1.59it/s]
 17%|█▋        | 9564/57600 [1:40:45<8:25:53,  1.58it/s]
 17%|█▋        | 9565/57600 [1:40:46<8:21:20,  1.60it/s]
 17%|█▋        | 9566/57600 [1:40:46<8:16:38,  1.61it/s]
 17%|█▋        | 9567/57600 [1:40:47<8:04:19,  1.65it/s]
 17%|█▋        | 9568/57600 [1:40:47<7:50:55,  1.70it/s]
 17%|█▋        | 9569/57600 [1:40:48<7:57:02,  1.68it/s]
 17%|█▋        | 9570/57600 [1:40:49<8:03:19,  1.66it/s]
 17%|█▋        | 9571/57600 [1:40:49<8:01:39,  1.66it/s]
 17%|█▋        | 9572/57600 [1:40:50<8:00:33,  1.67it/s]
 17%|█▋        | 9573/57600 [1:40:51<8:16:09,  1.61it/s]
 17%|█▋        | 9574/57600 [1:40:51<8:36:31,  1.55it/s]
 17%|█▋        | 9575/57600 [1:40:52<8:28:24,  1.57it/s]
 17%|█▋        | 9576/57600 [1:40:53<8:27:12,  1.58it/s]
 17%|█▋        | 9577/57600 [1:40:53<8:28:45,  1.57it/s]
 17%|█▋        | 9578/57600 [1:40:54<8:35:42,  1.55it/s]
 17%|█▋        | 9579/57600 [1:40:54<8:36:20,  1.55it/s]
 17%|█▋        | 9580/57600 [1:40:55<8:26:52,  1.58it/s]
                                                        
{'loss': 1.3462, 'learning_rate': 8.529268292682926e-07, 'epoch': 105.74}

 17%|█▋        | 9580/57600 [1:40:55<8:26:52,  1.58it/s]
 17%|█▋        | 9581/57600 [1:40:56<8:25:19,  1.58it/s]
 17%|█▋        | 9582/57600 [1:40:56<8:19:42,  1.60it/s]
 17%|█▋        | 9583/57600 [1:40:57<8:26:17,  1.58it/s]
 17%|█▋        | 9584/57600 [1:40:58<8:31:24,  1.56it/s]
 17%|█▋        | 9585/57600 [1:40:58<8:28:58,  1.57it/s]
 17%|█▋        | 9586/57600 [1:40:59<8:19:23,  1.60it/s]
 17%|█▋        | 9587/57600 [1:40:59<8:11:20,  1.63it/s]
 17%|█▋        | 9588/57600 [1:41:00<8:18:00,  1.61it/s]
 17%|█▋        | 9589/57600 [1:41:01<8:18:24,  1.61it/s]
 17%|█▋        | 9590/57600 [1:41:01<8:39:03,  1.54it/s]
 17%|█▋        | 9591/57600 [1:41:02<8:29:35,  1.57it/s]
 17%|█▋        | 9592/57600 [1:41:03<8:31:24,  1.56it/s]
 17%|█▋        | 9593/57600 [1:41:03<8:23:22,  1.59it/s]
 17%|█▋        | 9594/57600 [1:41:04<8:24:29,  1.59it/s]
 17%|█▋        | 9595/57600 [1:41:05<8:32:15,  1.56it/s]
 17%|█▋        | 9596/57600 [1:41:05<8:17:56,  1.61it/s]
 17%|█▋        | 9597/57600 [1:41:06<8:16:09,  1.61it/s]
 17%|█▋        | 9598/57600 [1:41:06<8:15:24,  1.61it/s]
 17%|█▋        | 9599/57600 [1:41:07<8:23:42,  1.59it/s]
 17%|█▋        | 9600/57600 [1:41:08<8:16:45,  1.61it/s]
                                                        
{'loss': 1.3702, 'learning_rate': 8.526132404181184e-07, 'epoch': 105.96}

 17%|█▋        | 9600/57600 [1:41:08<8:16:45,  1.61it/s]
 17%|█▋        | 9601/57600 [1:41:08<8:45:45,  1.52it/s]
 17%|█▋        | 9602/57600 [1:41:09<8:33:37,  1.56it/s]
 17%|█▋        | 9603/57600 [1:41:10<8:23:18,  1.59it/s]
 17%|█▋        | 9604/57600 [1:41:10<8:31:03,  1.57it/s]
 17%|█▋        | 9605/57600 [1:41:11<8:35:17,  1.55it/s]
 17%|█▋        | 9606/57600 [1:41:12<8:37:07,  1.55it/s]
 17%|█▋        | 9607/57600 [1:41:12<8:15:29,  1.61it/s]
 17%|█▋        | 9608/57600 [1:41:13<8:08:37,  1.64it/s]
 17%|█▋        | 9609/57600 [1:41:13<8:16:22,  1.61it/s]
 17%|█▋        | 9610/57600 [1:41:14<8:09:47,  1.63it/s]
 17%|█▋        | 9611/57600 [1:41:14<7:54:56,  1.68it/s]
 17%|█▋        | 9612/57600 [1:41:15<8:03:40,  1.65it/s]
 17%|█▋        | 9613/57600 [1:41:16<9:01:43,  1.48it/s]
 17%|█▋        | 9614/57600 [1:41:17<8:35:27,  1.55it/s]
 17%|█▋        | 9615/57600 [1:41:17<8:24:46,  1.58it/s]
 17%|█▋        | 9616/57600 [1:41:18<8:33:35,  1.56it/s]
 17%|█▋        | 9617/57600 [1:41:18<8:11:19,  1.63it/s]
 17%|█▋        | 9618/57600 [1:41:19<8:07:31,  1.64it/s]
 17%|█▋        | 9619/57600 [1:41:20<8:23:32,  1.59it/s]
 17%|█▋        | 9620/57600 [1:41:20<8:20:07,  1.60it/s]
                                                        
{'loss': 1.3683, 'learning_rate': 8.522996515679441e-07, 'epoch': 106.18}

 17%|█▋        | 9620/57600 [1:41:20<8:20:07,  1.60it/s]
 17%|█▋        | 9621/57600 [1:41:21<8:19:59,  1.60it/s]
 17%|█▋        | 9622/57600 [1:41:22<8:26:14,  1.58it/s]
 17%|█▋        | 9623/57600 [1:41:22<8:14:20,  1.62it/s]
 17%|█▋        | 9624/57600 [1:41:23<8:07:18,  1.64it/s]
 17%|█▋        | 9625/57600 [1:41:23<8:09:29,  1.63it/s]
 17%|█▋        | 9626/57600 [1:41:24<8:25:16,  1.58it/s]
 17%|█▋        | 9627/57600 [1:41:25<8:31:50,  1.56it/s]
 17%|█▋        | 9628/57600 [1:41:25<8:26:12,  1.58it/s]
 17%|█▋        | 9629/57600 [1:41:26<8:31:07,  1.56it/s]
 17%|█▋        | 9630/57600 [1:41:27<8:21:17,  1.59it/s]
 17%|█▋        | 9631/57600 [1:41:27<8:30:06,  1.57it/s]
 17%|█▋        | 9632/57600 [1:41:28<8:22:52,  1.59it/s]
 17%|█▋        | 9633/57600 [1:41:28<8:35:11,  1.55it/s]
 17%|█▋        | 9634/57600 [1:41:29<8:14:48,  1.62it/s]
 17%|█▋        | 9635/57600 [1:41:30<8:19:06,  1.60it/s]
 17%|█▋        | 9636/57600 [1:41:30<8:08:36,  1.64it/s]
 17%|█▋        | 9637/57600 [1:41:31<8:14:01,  1.62it/s]
 17%|█▋        | 9638/57600 [1:41:31<8:03:44,  1.65it/s]
 17%|█▋        | 9639/57600 [1:41:32<7:52:27,  1.69it/s]
 17%|█▋        | 9640/57600 [1:41:33<7:51:42,  1.69it/s]
                                                        
{'loss': 1.4073, 'learning_rate': 8.5198606271777e-07, 'epoch': 106.4}

 17%|█▋        | 9640/57600 [1:41:33<7:51:42,  1.69it/s]
 17%|█▋        | 9641/57600 [1:41:33<8:07:51,  1.64it/s]
 17%|█▋        | 9642/57600 [1:41:34<8:02:13,  1.66it/s]
 17%|█▋        | 9643/57600 [1:41:34<7:59:33,  1.67it/s]
 17%|█▋        | 9644/57600 [1:41:35<8:08:27,  1.64it/s]
 17%|█▋        | 9645/57600 [1:41:36<8:07:22,  1.64it/s]
 17%|█▋        | 9646/57600 [1:41:36<8:04:52,  1.65it/s]
 17%|█▋        | 9647/57600 [1:41:37<8:10:55,  1.63it/s]
 17%|█▋        | 9648/57600 [1:41:37<8:04:57,  1.65it/s]
 17%|█▋        | 9649/57600 [1:41:38<8:08:39,  1.64it/s]
 17%|█▋        | 9650/57600 [1:41:39<8:02:51,  1.66it/s]
 17%|█▋        | 9651/57600 [1:41:39<8:10:28,  1.63it/s]
 17%|█▋        | 9652/57600 [1:41:40<8:37:38,  1.54it/s]
 17%|█▋        | 9653/57600 [1:41:41<8:29:39,  1.57it/s]
 17%|█▋        | 9654/57600 [1:41:41<8:33:52,  1.56it/s]
 17%|█▋        | 9655/57600 [1:41:42<8:40:38,  1.53it/s]
 17%|█▋        | 9656/57600 [1:41:43<8:22:55,  1.59it/s]
 17%|█▋        | 9657/57600 [1:41:43<8:18:12,  1.60it/s]
 17%|█▋        | 9658/57600 [1:41:44<8:08:38,  1.64it/s]
 17%|█▋        | 9659/57600 [1:41:44<8:19:28,  1.60it/s]
 17%|█▋        | 9660/57600 [1:41:45<8:28:39,  1.57it/s]
                                                        
{'loss': 1.3627, 'learning_rate': 8.516724738675959e-07, 'epoch': 106.62}

 17%|█▋        | 9660/57600 [1:41:45<8:28:39,  1.57it/s]
 17%|█▋        | 9661/57600 [1:41:46<8:36:10,  1.55it/s]
 17%|█▋        | 9662/57600 [1:41:46<8:38:21,  1.54it/s]
 17%|█▋        | 9663/57600 [1:41:47<8:21:47,  1.59it/s]
 17%|█▋        | 9664/57600 [1:41:48<8:24:13,  1.58it/s]
 17%|█▋        | 9665/57600 [1:41:48<8:16:48,  1.61it/s]
 17%|█▋        | 9666/57600 [1:41:49<8:04:53,  1.65it/s]
 17%|█▋        | 9667/57600 [1:41:49<8:19:52,  1.60it/s]
 17%|█▋        | 9668/57600 [1:41:50<8:13:15,  1.62it/s]
 17%|█▋        | 9669/57600 [1:41:51<8:10:17,  1.63it/s]
 17%|█▋        | 9670/57600 [1:41:51<8:09:54,  1.63it/s]
 17%|█▋        | 9671/57600 [1:41:52<8:11:09,  1.63it/s]
 17%|█▋        | 9672/57600 [1:41:53<8:16:10,  1.61it/s]
 17%|█▋        | 9673/57600 [1:41:53<8:35:30,  1.55it/s]
 17%|█▋        | 9674/57600 [1:41:54<8:20:00,  1.60it/s]
 17%|█▋        | 9675/57600 [1:41:54<8:14:44,  1.61it/s]
 17%|█▋        | 9676/57600 [1:41:55<8:21:19,  1.59it/s]
 17%|█▋        | 9677/57600 [1:41:56<8:12:44,  1.62it/s]
 17%|█▋        | 9678/57600 [1:41:56<8:10:44,  1.63it/s]
 17%|█▋        | 9679/57600 [1:41:57<8:07:17,  1.64it/s]
 17%|█▋        | 9680/57600 [1:41:58<8:10:32,  1.63it/s]
                                                        
{'loss': 1.4, 'learning_rate': 8.513588850174215e-07, 'epoch': 106.84}

 17%|█▋        | 9680/57600 [1:41:58<8:10:32,  1.63it/s]
 17%|█▋        | 9681/57600 [1:41:58<8:07:20,  1.64it/s]
 17%|█▋        | 9682/57600 [1:41:59<7:59:49,  1.66it/s]
 17%|█▋        | 9683/57600 [1:41:59<8:22:12,  1.59it/s]
 17%|█▋        | 9684/57600 [1:42:00<8:40:19,  1.53it/s]
 17%|█▋        | 9685/57600 [1:42:01<8:41:05,  1.53it/s]
 17%|█▋        | 9686/57600 [1:42:01<8:22:55,  1.59it/s]
 17%|█▋        | 9687/57600 [1:42:02<8:23:24,  1.59it/s]
 17%|█▋        | 9688/57600 [1:42:03<8:21:38,  1.59it/s]
 17%|█▋        | 9689/57600 [1:42:03<8:18:18,  1.60it/s]
 17%|█▋        | 9690/57600 [1:42:04<8:23:57,  1.58it/s]
 17%|█▋        | 9691/57600 [1:42:04<8:15:05,  1.61it/s]
 17%|█▋        | 9692/57600 [1:42:05<8:30:48,  1.56it/s]
 17%|█▋        | 9693/57600 [1:42:06<8:25:50,  1.58it/s]
 17%|█▋        | 9694/57600 [1:42:06<8:15:43,  1.61it/s]
 17%|█▋        | 9695/57600 [1:42:07<8:42:30,  1.53it/s]
 17%|█▋        | 9696/57600 [1:42:08<8:56:53,  1.49it/s]
 17%|█▋        | 9697/57600 [1:42:08<8:43:21,  1.53it/s]
 17%|█▋        | 9698/57600 [1:42:09<8:43:05,  1.53it/s]
 17%|█▋        | 9699/57600 [1:42:10<8:36:35,  1.55it/s]
 17%|█▋        | 9700/57600 [1:42:10<8:15:15,  1.61it/s]
                                                        
{'loss': 1.3322, 'learning_rate': 8.510452961672474e-07, 'epoch': 107.06}

 17%|█▋        | 9700/57600 [1:42:10<8:15:15,  1.61it/s]
 17%|█▋        | 9701/57600 [1:42:11<8:02:29,  1.65it/s]
 17%|█▋        | 9702/57600 [1:42:11<8:08:54,  1.63it/s]
 17%|█▋        | 9703/57600 [1:42:12<8:30:09,  1.56it/s]
 17%|█▋        | 9704/57600 [1:42:13<8:27:03,  1.57it/s]
 17%|█▋        | 9705/57600 [1:42:13<8:09:30,  1.63it/s]
 17%|█▋        | 9706/57600 [1:42:14<8:27:13,  1.57it/s]
 17%|█▋        | 9707/57600 [1:42:15<8:14:41,  1.61it/s]
 17%|█▋        | 9708/57600 [1:42:15<8:30:17,  1.56it/s]
 17%|█▋        | 9709/57600 [1:42:16<8:36:49,  1.54it/s]
 17%|█▋        | 9710/57600 [1:42:16<8:11:43,  1.62it/s]
 17%|█▋        | 9711/57600 [1:42:17<8:21:02,  1.59it/s]
 17%|█▋        | 9712/57600 [1:42:18<8:27:52,  1.57it/s]
 17%|█▋        | 9713/57600 [1:42:18<8:32:33,  1.56it/s]
 17%|█▋        | 9714/57600 [1:42:19<8:28:12,  1.57it/s]
 17%|█▋        | 9715/57600 [1:42:20<8:22:57,  1.59it/s]
 17%|█▋        | 9716/57600 [1:42:20<8:06:33,  1.64it/s]
 17%|█▋        | 9717/57600 [1:42:21<8:21:02,  1.59it/s]
 17%|█▋        | 9718/57600 [1:42:22<8:19:24,  1.60it/s]
 17%|█▋        | 9719/57600 [1:42:22<8:26:34,  1.58it/s]
 17%|█▋        | 9720/57600 [1:42:23<8:40:44,  1.53it/s]
                                                        
{'loss': 1.3776, 'learning_rate': 8.507317073170731e-07, 'epoch': 107.28}

 17%|█▋        | 9720/57600 [1:42:23<8:40:44,  1.53it/s]
 17%|█▋        | 9721/57600 [1:42:24<8:32:45,  1.56it/s]
 17%|█▋        | 9722/57600 [1:42:24<8:16:25,  1.61it/s]
 17%|█▋        | 9723/57600 [1:42:25<8:18:44,  1.60it/s]
 17%|█▋        | 9724/57600 [1:42:25<8:25:37,  1.58it/s]
 17%|█▋        | 9725/57600 [1:42:26<8:14:46,  1.61it/s]
 17%|█▋        | 9726/57600 [1:42:27<8:31:25,  1.56it/s]
 17%|█▋        | 9727/57600 [1:42:27<8:29:23,  1.57it/s]
 17%|█▋        | 9728/57600 [1:42:28<8:41:28,  1.53it/s]
 17%|█▋        | 9729/57600 [1:42:29<8:33:05,  1.55it/s]
 17%|█▋        | 9730/57600 [1:42:29<8:34:56,  1.55it/s]
 17%|█▋        | 9731/57600 [1:42:30<8:39:08,  1.54it/s]
 17%|█▋        | 9732/57600 [1:42:31<8:25:36,  1.58it/s]
 17%|█▋        | 9733/57600 [1:42:31<8:32:17,  1.56it/s]
 17%|█▋        | 9734/57600 [1:42:32<8:24:36,  1.58it/s]
 17%|█▋        | 9735/57600 [1:42:32<8:18:46,  1.60it/s]
 17%|█▋        | 9736/57600 [1:42:33<8:07:05,  1.64it/s]
 17%|█▋        | 9737/57600 [1:42:34<7:59:34,  1.66it/s]
 17%|█▋        | 9738/57600 [1:42:34<7:50:01,  1.70it/s]
 17%|█▋        | 9739/57600 [1:42:35<8:03:46,  1.65it/s]
 17%|█▋        | 9740/57600 [1:42:35<8:04:07,  1.65it/s]
                                                        
{'loss': 1.3837, 'learning_rate': 8.50418118466899e-07, 'epoch': 107.51}

 17%|█▋        | 9740/57600 [1:42:35<8:04:07,  1.65it/s]
 17%|█▋        | 9741/57600 [1:42:36<8:18:20,  1.60it/s]
 17%|█▋        | 9742/57600 [1:42:37<8:37:03,  1.54it/s]
 17%|█▋        | 9743/57600 [1:42:37<8:18:04,  1.60it/s]
 17%|█▋        | 9744/57600 [1:42:38<8:22:53,  1.59it/s]
 17%|█▋        | 9745/57600 [1:42:39<8:17:30,  1.60it/s]
 17%|█▋        | 9746/57600 [1:42:39<8:15:45,  1.61it/s]
 17%|█▋        | 9747/57600 [1:42:40<8:03:18,  1.65it/s]
 17%|█▋        | 9748/57600 [1:42:40<8:12:14,  1.62it/s]
 17%|█▋        | 9749/57600 [1:42:41<8:08:02,  1.63it/s]
 17%|█▋        | 9750/57600 [1:42:42<7:54:20,  1.68it/s]
 17%|█▋        | 9751/57600 [1:42:42<7:54:38,  1.68it/s]
 17%|█▋        | 9752/57600 [1:42:43<7:41:01,  1.73it/s]
 17%|█▋        | 9753/57600 [1:42:43<8:09:46,  1.63it/s]
 17%|█▋        | 9754/57600 [1:42:44<7:56:26,  1.67it/s]
 17%|█▋        | 9755/57600 [1:42:45<7:54:46,  1.68it/s]
 17%|█▋        | 9756/57600 [1:42:45<8:08:13,  1.63it/s]
 17%|█▋        | 9757/57600 [1:42:46<8:08:49,  1.63it/s]
 17%|█▋        | 9758/57600 [1:42:46<8:04:49,  1.64it/s]
 17%|█▋        | 9759/57600 [1:42:47<8:03:07,  1.65it/s]
 17%|█▋        | 9760/57600 [1:42:48<7:58:41,  1.67it/s]
                                                        
{'loss': 1.3633, 'learning_rate': 8.501045296167246e-07, 'epoch': 107.73}

 17%|█▋        | 9760/57600 [1:42:48<7:58:41,  1.67it/s]
 17%|█▋        | 9761/57600 [1:42:48<7:45:28,  1.71it/s]
 17%|█▋        | 9762/57600 [1:42:49<8:00:05,  1.66it/s]
 17%|█▋        | 9763/57600 [1:42:49<7:51:16,  1.69it/s]
 17%|█▋        | 9764/57600 [1:42:50<8:04:40,  1.64it/s]
 17%|█▋        | 9765/57600 [1:42:51<8:09:42,  1.63it/s]
 17%|█▋        | 9766/57600 [1:42:51<8:10:11,  1.63it/s]
 17%|█▋        | 9767/57600 [1:42:52<8:05:56,  1.64it/s]
 17%|█▋        | 9768/57600 [1:42:52<8:08:08,  1.63it/s]
 17%|█▋        | 9769/57600 [1:42:53<8:02:12,  1.65it/s]
 17%|█▋        | 9770/57600 [1:42:54<7:55:53,  1.68it/s]
 17%|█▋        | 9771/57600 [1:42:54<7:52:49,  1.69it/s]
 17%|█▋        | 9772/57600 [1:42:55<8:18:53,  1.60it/s]
 17%|█▋        | 9773/57600 [1:42:55<8:13:09,  1.62it/s]
 17%|█▋        | 9774/57600 [1:42:56<8:06:30,  1.64it/s]
 17%|█▋        | 9775/57600 [1:42:57<7:57:46,  1.67it/s]
 17%|█▋        | 9776/57600 [1:42:57<7:51:43,  1.69it/s]
 17%|█▋        | 9777/57600 [1:42:58<8:01:58,  1.65it/s]
 17%|█▋        | 9778/57600 [1:42:58<7:53:11,  1.68it/s]
 17%|█▋        | 9779/57600 [1:42:59<7:52:28,  1.69it/s]
 17%|█▋        | 9780/57600 [1:43:00<8:02:52,  1.65it/s]
                                                        
{'loss': 1.4582, 'learning_rate': 8.497909407665505e-07, 'epoch': 107.95}

 17%|█▋        | 9780/57600 [1:43:00<8:02:52,  1.65it/s]
 17%|█▋        | 9781/57600 [1:43:00<7:57:01,  1.67it/s]
 17%|█▋        | 9782/57600 [1:43:01<8:15:25,  1.61it/s]
 17%|█▋        | 9783/57600 [1:43:01<8:00:58,  1.66it/s]
 17%|█▋        | 9784/57600 [1:43:02<7:59:30,  1.66it/s]
 17%|█▋        | 9785/57600 [1:43:03<8:22:28,  1.59it/s]
 17%|█▋        | 9786/57600 [1:43:03<8:22:33,  1.59it/s]
 17%|█▋        | 9787/57600 [1:43:04<8:28:35,  1.57it/s]
 17%|█▋        | 9788/57600 [1:43:05<8:18:13,  1.60it/s]
 17%|█▋        | 9789/57600 [1:43:05<8:02:03,  1.65it/s]
 17%|█▋        | 9790/57600 [1:43:06<8:01:24,  1.66it/s]
 17%|█▋        | 9791/57600 [1:43:06<7:55:27,  1.68it/s]
 17%|█▋        | 9792/57600 [1:43:07<7:43:54,  1.72it/s]
 17%|█▋        | 9793/57600 [1:43:07<7:39:32,  1.73it/s]
 17%|█▋        | 9794/57600 [1:43:08<7:55:43,  1.67it/s]
 17%|█▋        | 9795/57600 [1:43:09<7:52:08,  1.69it/s]
 17%|█▋        | 9796/57600 [1:43:09<7:59:31,  1.66it/s]
 17%|█▋        | 9797/57600 [1:43:10<7:54:26,  1.68it/s]
 17%|█▋        | 9798/57600 [1:43:11<8:03:20,  1.65it/s]
 17%|█▋        | 9799/57600 [1:43:11<8:03:32,  1.65it/s]
 17%|█▋        | 9800/57600 [1:43:12<8:14:50,  1.61it/s]
                                                        
{'loss': 1.4204, 'learning_rate': 8.494773519163763e-07, 'epoch': 108.17}

 17%|█▋        | 9800/57600 [1:43:12<8:14:50,  1.61it/s]
 17%|█▋        | 9801/57600 [1:43:12<8:11:21,  1.62it/s]
 17%|█▋        | 9802/57600 [1:43:13<8:05:00,  1.64it/s]
 17%|█▋        | 9803/57600 [1:43:14<7:58:24,  1.67it/s]
 17%|█▋        | 9804/57600 [1:43:14<8:02:29,  1.65it/s]
 17%|█▋        | 9805/57600 [1:43:15<8:23:41,  1.58it/s]
 17%|█▋        | 9806/57600 [1:43:16<8:31:02,  1.56it/s]
 17%|█▋        | 9807/57600 [1:43:16<8:27:22,  1.57it/s]
 17%|█▋        | 9808/57600 [1:43:17<8:14:19,  1.61it/s]
 17%|█▋        | 9809/57600 [1:43:17<8:19:48,  1.59it/s]
 17%|█▋        | 9810/57600 [1:43:18<8:17:31,  1.60it/s]
 17%|█▋        | 9811/57600 [1:43:19<8:02:41,  1.65it/s]
 17%|█▋        | 9812/57600 [1:43:19<8:09:27,  1.63it/s]
 17%|█▋        | 9813/57600 [1:43:20<8:22:30,  1.58it/s]
 17%|█▋        | 9814/57600 [1:43:21<8:24:13,  1.58it/s]
 17%|█▋        | 9815/57600 [1:43:21<8:33:52,  1.55it/s]
 17%|█▋        | 9816/57600 [1:43:22<8:38:44,  1.54it/s]
 17%|█▋        | 9817/57600 [1:43:23<8:44:33,  1.52it/s]
 17%|█▋        | 9818/57600 [1:43:23<8:36:04,  1.54it/s]
 17%|█▋        | 9819/57600 [1:43:24<8:22:15,  1.59it/s]
 17%|█▋        | 9820/57600 [1:43:24<8:12:57,  1.62it/s]
                                                        
{'loss': 1.3606, 'learning_rate': 8.49163763066202e-07, 'epoch': 108.39}

 17%|█▋        | 9820/57600 [1:43:24<8:12:57,  1.62it/s]
 17%|█▋        | 9821/57600 [1:43:25<8:20:44,  1.59it/s]
 17%|█▋        | 9822/57600 [1:43:26<8:26:51,  1.57it/s]
 17%|█▋        | 9823/57600 [1:43:26<8:18:57,  1.60it/s]
 17%|█▋        | 9824/57600 [1:43:27<8:21:20,  1.59it/s]
 17%|█▋        | 9825/57600 [1:43:28<8:20:59,  1.59it/s]
 17%|█▋        | 9826/57600 [1:43:28<8:20:36,  1.59it/s]
 17%|█▋        | 9827/57600 [1:43:29<8:03:36,  1.65it/s]
 17%|█▋        | 9828/57600 [1:43:29<8:13:54,  1.61it/s]
 17%|█▋        | 9829/57600 [1:43:30<8:22:30,  1.58it/s]
 17%|█▋        | 9830/57600 [1:43:31<8:10:43,  1.62it/s]
 17%|█▋        | 9831/57600 [1:43:31<7:55:17,  1.68it/s]
 17%|█▋        | 9832/57600 [1:43:32<7:58:28,  1.66it/s]
 17%|█▋        | 9833/57600 [1:43:32<7:55:59,  1.67it/s]
 17%|█▋        | 9834/57600 [1:43:33<7:36:17,  1.74it/s]
 17%|█▋        | 9835/57600 [1:43:33<7:40:15,  1.73it/s]
 17%|█▋        | 9836/57600 [1:43:34<7:40:43,  1.73it/s]
 17%|█▋        | 9837/57600 [1:43:35<7:41:36,  1.72it/s]
 17%|█▋        | 9838/57600 [1:43:35<7:49:32,  1.70it/s]
 17%|█▋        | 9839/57600 [1:43:36<7:49:50,  1.69it/s]
 17%|█▋        | 9840/57600 [1:43:37<8:07:47,  1.63it/s]
                                                        
{'loss': 1.41, 'learning_rate': 8.488501742160278e-07, 'epoch': 108.61}

 17%|█▋        | 9840/57600 [1:43:37<8:07:47,  1.63it/s]
 17%|█▋        | 9841/57600 [1:43:37<8:22:33,  1.58it/s]
 17%|█▋        | 9842/57600 [1:43:38<8:23:54,  1.58it/s]
 17%|█▋        | 9843/57600 [1:43:39<8:40:27,  1.53it/s]
 17%|█▋        | 9844/57600 [1:43:39<8:37:10,  1.54it/s]
 17%|█▋        | 9845/57600 [1:43:40<8:33:03,  1.55it/s]
 17%|█▋        | 9846/57600 [1:43:40<8:27:55,  1.57it/s]
 17%|█▋        | 9847/57600 [1:43:41<8:29:16,  1.56it/s]
 17%|█▋        | 9848/57600 [1:43:42<8:16:37,  1.60it/s]
 17%|█▋        | 9849/57600 [1:43:42<8:30:15,  1.56it/s]
 17%|█▋        | 9850/57600 [1:43:43<8:25:30,  1.57it/s]
 17%|█▋        | 9851/57600 [1:43:44<8:12:23,  1.62it/s]
 17%|█▋        | 9852/57600 [1:43:44<8:03:43,  1.65it/s]
 17%|█▋        | 9853/57600 [1:43:45<8:07:28,  1.63it/s]
 17%|█▋        | 9854/57600 [1:43:45<8:06:48,  1.63it/s]
 17%|█▋        | 9855/57600 [1:43:46<8:13:08,  1.61it/s]
 17%|█▋        | 9856/57600 [1:43:47<8:07:43,  1.63it/s]
 17%|█▋        | 9857/57600 [1:43:47<8:10:07,  1.62it/s]
 17%|█▋        | 9858/57600 [1:43:48<8:22:23,  1.58it/s]
 17%|█▋        | 9859/57600 [1:43:48<8:20:29,  1.59it/s]
 17%|█▋        | 9860/57600 [1:43:49<8:27:59,  1.57it/s]
                                                        
{'loss': 1.321, 'learning_rate': 8.485365853658536e-07, 'epoch': 108.83}

 17%|█▋        | 9860/57600 [1:43:49<8:27:59,  1.57it/s]
 17%|█▋        | 9861/57600 [1:43:50<8:13:05,  1.61it/s]
 17%|█▋        | 9862/57600 [1:43:50<8:09:40,  1.62it/s]
 17%|█▋        | 9863/57600 [1:43:51<8:04:51,  1.64it/s]
 17%|█▋        | 9864/57600 [1:43:52<8:11:16,  1.62it/s]
 17%|█▋        | 9865/57600 [1:43:52<8:15:03,  1.61it/s]
 17%|█▋        | 9866/57600 [1:43:53<8:10:57,  1.62it/s]
 17%|█▋        | 9867/57600 [1:43:54<8:34:26,  1.55it/s]
 17%|█▋        | 9868/57600 [1:43:54<8:26:23,  1.57it/s]
 17%|█▋        | 9869/57600 [1:43:55<8:20:20,  1.59it/s]
 17%|█▋        | 9870/57600 [1:43:55<8:43:34,  1.52it/s]
 17%|█▋        | 9871/57600 [1:43:56<8:38:57,  1.53it/s]
 17%|█▋        | 9872/57600 [1:43:57<8:22:27,  1.58it/s]
 17%|█▋        | 9873/57600 [1:43:57<8:20:36,  1.59it/s]
 17%|█▋        | 9874/57600 [1:43:58<8:14:55,  1.61it/s]
 17%|█▋        | 9875/57600 [1:43:58<7:54:13,  1.68it/s]
 17%|█▋        | 9876/57600 [1:43:59<8:32:52,  1.55it/s]
 17%|█▋        | 9877/57600 [1:44:00<8:36:42,  1.54it/s]
 17%|█▋        | 9878/57600 [1:44:00<8:23:21,  1.58it/s]
 17%|█▋        | 9879/57600 [1:44:01<8:28:34,  1.56it/s]
 17%|█▋        | 9880/57600 [1:44:02<8:30:02,  1.56it/s]
                                                        
{'loss': 1.3471, 'learning_rate': 8.482229965156795e-07, 'epoch': 109.05}

 17%|█▋        | 9880/57600 [1:44:02<8:30:02,  1.56it/s]
 17%|█▋        | 9881/57600 [1:44:02<8:19:18,  1.59it/s]
 17%|█▋        | 9882/57600 [1:44:03<8:13:39,  1.61it/s]
 17%|█▋        | 9883/57600 [1:44:04<8:05:08,  1.64it/s]
 17%|█▋        | 9884/57600 [1:44:04<7:59:24,  1.66it/s]
 17%|█▋        | 9885/57600 [1:44:05<7:53:55,  1.68it/s]
 17%|█▋        | 9886/57600 [1:44:05<8:08:15,  1.63it/s]
 17%|█▋        | 9887/57600 [1:44:06<8:10:17,  1.62it/s]
 17%|█▋        | 9888/57600 [1:44:07<8:00:18,  1.66it/s]
 17%|█▋        | 9889/57600 [1:44:07<8:11:53,  1.62it/s]
 17%|█▋        | 9890/57600 [1:44:08<8:04:51,  1.64it/s]
 17%|█▋        | 9891/57600 [1:44:08<8:05:38,  1.64it/s]
 17%|█▋        | 9892/57600 [1:44:09<8:01:43,  1.65it/s]
 17%|█▋        | 9893/57600 [1:44:10<8:05:46,  1.64it/s]
 17%|█▋        | 9894/57600 [1:44:10<8:00:24,  1.66it/s]
 17%|█▋        | 9895/57600 [1:44:11<8:09:23,  1.62it/s]
 17%|█▋        | 9896/57600 [1:44:12<8:27:13,  1.57it/s]
 17%|█▋        | 9897/57600 [1:44:12<8:23:06,  1.58it/s]
 17%|█▋        | 9898/57600 [1:44:13<8:29:19,  1.56it/s]
 17%|█▋        | 9899/57600 [1:44:13<8:21:47,  1.58it/s]
 17%|█▋        | 9900/57600 [1:44:14<8:37:09,  1.54it/s]
                                                        
{'loss': 1.3809, 'learning_rate': 8.479094076655051e-07, 'epoch': 109.27}

 17%|█▋        | 9900/57600 [1:44:14<8:37:09,  1.54it/s]
 17%|█▋        | 9901/57600 [1:44:15<8:38:13,  1.53it/s]
 17%|█▋        | 9902/57600 [1:44:15<8:19:38,  1.59it/s]
 17%|█▋        | 9903/57600 [1:44:16<8:13:13,  1.61it/s]
 17%|█▋        | 9904/57600 [1:44:17<8:00:17,  1.66it/s]
 17%|█▋        | 9905/57600 [1:44:17<8:14:41,  1.61it/s]
 17%|█▋        | 9906/57600 [1:44:18<8:04:03,  1.64it/s]
 17%|█▋        | 9907/57600 [1:44:18<7:56:54,  1.67it/s]
 17%|█▋        | 9908/57600 [1:44:19<8:16:17,  1.60it/s]
 17%|█▋        | 9909/57600 [1:44:20<8:08:31,  1.63it/s]
 17%|█▋        | 9910/57600 [1:44:20<8:13:55,  1.61it/s]
 17%|█▋        | 9911/57600 [1:44:21<8:15:04,  1.61it/s]
 17%|█▋        | 9912/57600 [1:44:21<8:05:43,  1.64it/s]
 17%|█▋        | 9913/57600 [1:44:22<8:14:45,  1.61it/s]
 17%|█▋        | 9914/57600 [1:44:23<8:02:02,  1.65it/s]
 17%|█▋        | 9915/57600 [1:44:23<8:00:39,  1.65it/s]
 17%|█▋        | 9916/57600 [1:44:24<7:56:40,  1.67it/s]
 17%|█▋        | 9917/57600 [1:44:25<8:05:30,  1.64it/s]
 17%|█▋        | 9918/57600 [1:44:25<8:17:19,  1.60it/s]
 17%|█▋        | 9919/57600 [1:44:26<8:13:32,  1.61it/s]
 17%|█▋        | 9920/57600 [1:44:26<8:14:53,  1.61it/s]
                                                        
{'loss': 1.3795, 'learning_rate': 8.47595818815331e-07, 'epoch': 109.49}

 17%|█▋        | 9920/57600 [1:44:26<8:14:53,  1.61it/s]
 17%|█▋        | 9921/57600 [1:44:27<8:08:51,  1.63it/s]
 17%|█▋        | 9922/57600 [1:44:28<8:07:29,  1.63it/s]
 17%|█▋        | 9923/57600 [1:44:28<8:27:15,  1.57it/s]
 17%|█▋        | 9924/57600 [1:44:29<8:33:17,  1.55it/s]
 17%|█▋        | 9925/57600 [1:44:30<8:34:43,  1.54it/s]
 17%|█▋        | 9926/57600 [1:44:30<8:16:21,  1.60it/s]
 17%|█▋        | 9927/57600 [1:44:31<8:24:31,  1.57it/s]
 17%|█▋        | 9928/57600 [1:44:31<8:11:02,  1.62it/s]
 17%|█▋        | 9929/57600 [1:44:32<7:57:56,  1.66it/s]
 17%|█▋        | 9930/57600 [1:44:33<7:50:34,  1.69it/s]
 17%|█▋        | 9931/57600 [1:44:33<8:08:31,  1.63it/s]
 17%|█▋        | 9932/57600 [1:44:34<8:00:42,  1.65it/s]
 17%|█▋        | 9933/57600 [1:44:35<8:29:52,  1.56it/s]
 17%|█▋        | 9934/57600 [1:44:35<8:17:11,  1.60it/s]
 17%|█▋        | 9935/57600 [1:44:36<8:26:35,  1.57it/s]
 17%|█▋        | 9936/57600 [1:44:36<8:18:47,  1.59it/s]
 17%|█▋        | 9937/57600 [1:44:37<8:12:31,  1.61it/s]
 17%|█▋        | 9938/57600 [1:44:38<8:08:30,  1.63it/s]
 17%|█▋        | 9939/57600 [1:44:38<7:55:29,  1.67it/s]
 17%|█▋        | 9940/57600 [1:44:39<7:48:00,  1.70it/s]
                                                        
{'loss': 1.3751, 'learning_rate': 8.472822299651568e-07, 'epoch': 109.71}

 17%|█▋        | 9940/57600 [1:44:39<7:48:00,  1.70it/s]
 17%|█▋        | 9941/57600 [1:44:39<7:48:46,  1.69it/s]
 17%|█▋        | 9942/57600 [1:44:40<7:51:02,  1.69it/s]
 17%|█▋        | 9943/57600 [1:44:41<7:43:00,  1.72it/s]
 17%|█▋        | 9944/57600 [1:44:41<7:54:18,  1.67it/s]
 17%|█▋        | 9945/57600 [1:44:42<8:09:48,  1.62it/s]
 17%|█▋        | 9946/57600 [1:44:42<8:12:53,  1.61it/s]
 17%|█▋        | 9947/57600 [1:44:43<8:25:40,  1.57it/s]
 17%|█▋        | 9948/57600 [1:44:44<8:06:09,  1.63it/s]
 17%|█▋        | 9949/57600 [1:44:44<7:54:38,  1.67it/s]
 17%|█▋        | 9950/57600 [1:44:45<8:10:46,  1.62it/s]
 17%|█▋        | 9951/57600 [1:44:46<8:32:00,  1.55it/s]
 17%|█▋        | 9952/57600 [1:44:46<8:44:37,  1.51it/s]
 17%|█▋        | 9953/57600 [1:44:47<8:28:34,  1.56it/s]
 17%|█▋        | 9954/57600 [1:44:47<8:16:57,  1.60it/s]
 17%|█▋        | 9955/57600 [1:44:48<8:15:12,  1.60it/s]
 17%|█▋        | 9956/57600 [1:44:49<8:05:45,  1.63it/s]
 17%|█▋        | 9957/57600 [1:44:49<8:12:33,  1.61it/s]
 17%|█▋        | 9958/57600 [1:44:50<7:59:51,  1.65it/s]
 17%|█▋        | 9959/57600 [1:44:50<7:47:33,  1.70it/s]
 17%|█▋        | 9960/57600 [1:44:51<8:19:10,  1.59it/s]
                                                        
{'loss': 1.3513, 'learning_rate': 8.469686411149826e-07, 'epoch': 109.93}

 17%|█▋        | 9960/57600 [1:44:51<8:19:10,  1.59it/s]
 17%|█▋        | 9961/57600 [1:44:52<8:11:58,  1.61it/s]
 17%|█▋        | 9962/57600 [1:44:52<8:10:14,  1.62it/s]
 17%|█▋        | 9963/57600 [1:44:53<8:01:39,  1.65it/s]
 17%|█▋        | 9964/57600 [1:44:54<8:18:45,  1.59it/s]
 17%|█▋        | 9965/57600 [1:44:54<8:39:16,  1.53it/s]
 17%|█▋        | 9966/57600 [1:44:55<8:41:31,  1.52it/s]
 17%|█▋        | 9967/57600 [1:44:56<9:00:21,  1.47it/s]
 17%|█▋        | 9968/57600 [1:44:56<8:56:05,  1.48it/s]
 17%|█▋        | 9969/57600 [1:44:57<8:38:54,  1.53it/s]
 17%|█▋        | 9970/57600 [1:44:58<8:37:31,  1.53it/s]
 17%|█▋        | 9971/57600 [1:44:58<8:20:09,  1.59it/s]
 17%|█▋        | 9972/57600 [1:44:59<8:09:17,  1.62it/s]
 17%|█▋        | 9973/57600 [1:45:00<8:25:24,  1.57it/s]
 17%|█▋        | 9974/57600 [1:45:00<8:23:08,  1.58it/s]
 17%|█▋        | 9975/57600 [1:45:01<8:06:26,  1.63it/s]
 17%|█▋        | 9976/57600 [1:45:01<7:55:38,  1.67it/s]
 17%|█▋        | 9977/57600 [1:45:02<7:54:11,  1.67it/s]
 17%|█▋        | 9978/57600 [1:45:03<8:18:43,  1.59it/s]
 17%|█▋        | 9979/57600 [1:45:03<8:18:43,  1.59it/s]
 17%|█▋        | 9980/57600 [1:45:04<8:17:53,  1.59it/s]
                                                        
{'loss': 1.3526, 'learning_rate': 8.466550522648083e-07, 'epoch': 110.15}

 17%|█▋        | 9980/57600 [1:45:04<8:17:53,  1.59it/s]
 17%|█▋        | 9981/57600 [1:45:04<8:09:00,  1.62it/s]
 17%|█▋        | 9982/57600 [1:45:05<8:17:16,  1.60it/s]
 17%|█▋        | 9983/57600 [1:45:06<8:05:00,  1.64it/s]
 17%|█▋        | 9984/57600 [1:45:06<8:22:54,  1.58it/s]
 17%|█▋        | 9985/57600 [1:45:07<8:11:01,  1.62it/s]
 17%|█▋        | 9986/57600 [1:45:08<8:06:56,  1.63it/s]
 17%|█▋        | 9987/57600 [1:45:08<8:09:42,  1.62it/s]
 17%|█▋        | 9988/57600 [1:45:09<8:11:59,  1.61it/s]
 17%|█▋        | 9989/57600 [1:45:09<8:16:04,  1.60it/s]
 17%|█▋        | 9990/57600 [1:45:10<8:25:54,  1.57it/s]
 17%|█▋        | 9991/57600 [1:45:11<8:34:19,  1.54it/s]
 17%|█▋        | 9992/57600 [1:45:11<8:24:23,  1.57it/s]
 17%|█▋        | 9993/57600 [1:45:12<8:20:27,  1.59it/s]
 17%|█▋        | 9994/57600 [1:45:13<8:13:28,  1.61it/s]
 17%|█▋        | 9995/57600 [1:45:13<8:14:15,  1.61it/s]
 17%|█▋        | 9996/57600 [1:45:14<8:09:17,  1.62it/s]
 17%|█▋        | 9997/57600 [1:45:14<8:13:52,  1.61it/s]
 17%|█▋        | 9998/57600 [1:45:15<8:02:25,  1.64it/s]
 17%|█▋        | 9999/57600 [1:45:16<7:58:57,  1.66it/s]
 17%|█▋        | 10000/57600 [1:45:16<7:56:16,  1.67it/s]
                                                         
{'loss': 1.3819, 'learning_rate': 8.463414634146341e-07, 'epoch': 110.38}

 17%|█▋        | 10000/57600 [1:45:16<7:56:16,  1.67it/s]
 17%|█▋        | 10001/57600 [1:45:17<8:01:01,  1.65it/s]
 17%|█▋        | 10002/57600 [1:45:17<7:58:32,  1.66it/s]
 17%|█▋        | 10003/57600 [1:45:18<8:27:54,  1.56it/s]
 17%|█▋        | 10004/57600 [1:45:19<8:02:13,  1.65it/s]
 17%|█▋        | 10005/57600 [1:45:19<8:02:41,  1.64it/s]
 17%|█▋        | 10006/57600 [1:45:20<8:07:19,  1.63it/s]
 17%|█▋        | 10007/57600 [1:45:20<7:59:42,  1.65it/s]
 17%|█▋        | 10008/57600 [1:45:21<8:01:37,  1.65it/s]
 17%|█▋        | 10009/57600 [1:45:22<8:09:23,  1.62it/s]
 17%|█▋        | 10010/57600 [1:45:22<7:53:14,  1.68it/s]
 17%|█▋        | 10011/57600 [1:45:23<8:16:26,  1.60it/s]
 17%|█▋        | 10012/57600 [1:45:24<8:06:47,  1.63it/s]
 17%|█▋        | 10013/57600 [1:45:24<7:58:43,  1.66it/s]
 17%|█▋        | 10014/57600 [1:45:25<8:00:26,  1.65it/s]
 17%|█▋        | 10015/57600 [1:45:25<7:58:57,  1.66it/s]
 17%|█▋        | 10016/57600 [1:45:26<8:13:28,  1.61it/s]
 17%|█▋        | 10017/57600 [1:45:27<8:19:42,  1.59it/s]
 17%|█▋        | 10018/57600 [1:45:27<8:23:43,  1.57it/s]
 17%|█▋        | 10019/57600 [1:45:28<8:12:01,  1.61it/s]
 17%|█▋        | 10020/57600 [1:45:29<8:12:37,  1.61it/s]
                                                         
{'loss': 1.3961, 'learning_rate': 8.460278745644599e-07, 'epoch': 110.6}

 17%|█▋        | 10020/57600 [1:45:29<8:12:37,  1.61it/s]
 17%|█▋        | 10021/57600 [1:45:29<7:54:02,  1.67it/s]
 17%|█▋        | 10022/57600 [1:45:30<7:56:31,  1.66it/s]
 17%|█▋        | 10023/57600 [1:45:30<7:51:43,  1.68it/s]
 17%|█▋        | 10024/57600 [1:45:31<7:59:35,  1.65it/s]
 17%|█▋        | 10025/57600 [1:45:32<8:07:58,  1.62it/s]
 17%|█▋        | 10026/57600 [1:45:32<7:52:20,  1.68it/s]
 17%|█▋        | 10027/57600 [1:45:33<7:51:15,  1.68it/s]
 17%|█▋        | 10028/57600 [1:45:33<8:11:38,  1.61it/s]
 17%|█▋        | 10029/57600 [1:45:34<8:16:17,  1.60it/s]
 17%|█▋        | 10030/57600 [1:45:35<8:24:43,  1.57it/s]
 17%|█▋        | 10031/57600 [1:45:35<8:10:42,  1.62it/s]
 17%|█▋        | 10032/57600 [1:45:36<8:18:23,  1.59it/s]
 17%|█▋        | 10033/57600 [1:45:36<8:02:38,  1.64it/s]
 17%|█▋        | 10034/57600 [1:45:37<7:59:01,  1.65it/s]
 17%|█▋        | 10035/57600 [1:45:38<8:01:30,  1.65it/s]
 17%|█▋        | 10036/57600 [1:45:38<8:01:04,  1.65it/s]
 17%|█▋        | 10037/57600 [1:45:39<8:09:49,  1.62it/s]
 17%|█▋        | 10038/57600 [1:45:40<8:15:08,  1.60it/s]
 17%|█▋        | 10039/57600 [1:45:40<8:08:59,  1.62it/s]
 17%|█▋        | 10040/57600 [1:45:41<8:08:06,  1.62it/s]
                                                         
{'loss': 1.3934, 'learning_rate': 8.457142857142856e-07, 'epoch': 110.82}

 17%|█▋        | 10040/57600 [1:45:41<8:08:06,  1.62it/s]
 17%|█▋        | 10041/57600 [1:45:41<8:06:26,  1.63it/s]
 17%|█▋        | 10042/57600 [1:45:42<7:58:09,  1.66it/s]
 17%|█▋        | 10043/57600 [1:45:43<7:56:52,  1.66it/s]
 17%|█▋        | 10044/57600 [1:45:43<7:52:39,  1.68it/s]
 17%|█▋        | 10045/57600 [1:45:44<7:55:45,  1.67it/s]
 17%|█▋        | 10046/57600 [1:45:44<8:02:24,  1.64it/s]
 17%|█▋        | 10047/57600 [1:45:45<8:38:32,  1.53it/s]
 17%|█▋        | 10048/57600 [1:45:46<8:15:07,  1.60it/s]
 17%|█▋        | 10049/57600 [1:45:46<8:27:48,  1.56it/s]
 17%|█▋        | 10050/57600 [1:45:47<8:22:30,  1.58it/s]
 17%|█▋        | 10051/57600 [1:45:48<8:10:13,  1.62it/s]
 17%|█▋        | 10052/57600 [1:45:48<8:51:30,  1.49it/s]
 17%|█▋        | 10053/57600 [1:45:49<8:34:59,  1.54it/s]
 17%|█▋        | 10054/57600 [1:45:50<8:23:45,  1.57it/s]
 17%|█▋        | 10055/57600 [1:45:50<8:27:47,  1.56it/s]
 17%|█▋        | 10056/57600 [1:45:51<8:17:07,  1.59it/s]
 17%|█▋        | 10057/57600 [1:45:51<8:29:23,  1.56it/s]
 17%|█▋        | 10058/57600 [1:45:52<8:12:53,  1.61it/s]
 17%|█▋        | 10059/57600 [1:45:53<8:10:15,  1.62it/s]
 17%|█▋        | 10060/57600 [1:45:53<8:14:17,  1.60it/s]
                                                         
{'loss': 1.3603, 'learning_rate': 8.454006968641114e-07, 'epoch': 111.04}

 17%|█▋        | 10060/57600 [1:45:53<8:14:17,  1.60it/s]
 17%|█▋        | 10061/57600 [1:45:54<8:01:06,  1.65it/s]
 17%|█▋        | 10062/57600 [1:45:55<8:19:35,  1.59it/s]
 17%|█▋        | 10063/57600 [1:45:55<8:05:26,  1.63it/s]
 17%|█▋        | 10064/57600 [1:45:56<8:31:40,  1.55it/s]
 17%|█▋        | 10065/57600 [1:45:56<8:23:34,  1.57it/s]
 17%|█▋        | 10066/57600 [1:45:57<8:15:44,  1.60it/s]
 17%|█▋        | 10067/57600 [1:45:58<8:10:17,  1.62it/s]
 17%|█▋        | 10068/57600 [1:45:58<8:05:09,  1.63it/s]
 17%|█▋        | 10069/57600 [1:45:59<7:59:54,  1.65it/s]
 17%|█▋        | 10070/57600 [1:45:59<7:59:48,  1.65it/s]
 17%|█▋        | 10071/57600 [1:46:00<8:10:11,  1.62it/s]
 17%|█▋        | 10072/57600 [1:46:01<8:02:56,  1.64it/s]
 17%|█▋        | 10073/57600 [1:46:01<7:57:36,  1.66it/s]
 17%|█▋        | 10074/57600 [1:46:02<8:09:50,  1.62it/s]
 17%|█▋        | 10075/57600 [1:46:03<8:19:58,  1.58it/s]
 17%|█▋        | 10076/57600 [1:46:03<8:29:21,  1.56it/s]
 17%|█▋        | 10077/57600 [1:46:04<8:18:26,  1.59it/s]
 17%|█▋        | 10078/57600 [1:46:04<8:13:44,  1.60it/s]
 17%|█▋        | 10079/57600 [1:46:05<8:06:49,  1.63it/s]
 18%|█▊        | 10080/57600 [1:46:06<7:58:14,  1.66it/s]
                                                         
{'loss': 1.3933, 'learning_rate': 8.450871080139372e-07, 'epoch': 111.26}

 18%|█▊        | 10080/57600 [1:46:06<7:58:14,  1.66it/s]
 18%|█▊        | 10081/57600 [1:46:06<8:07:25,  1.62it/s]
 18%|█▊        | 10082/57600 [1:46:07<8:01:06,  1.65it/s]
 18%|█▊        | 10083/57600 [1:46:08<8:06:51,  1.63it/s]
 18%|█▊        | 10084/57600 [1:46:08<8:21:39,  1.58it/s]
 18%|█▊        | 10085/57600 [1:46:09<8:08:48,  1.62it/s]
 18%|█▊        | 10086/57600 [1:46:09<8:05:05,  1.63it/s]
 18%|█▊        | 10087/57600 [1:46:10<8:12:51,  1.61it/s]
 18%|█▊        | 10088/57600 [1:46:11<8:44:50,  1.51it/s]
 18%|█▊        | 10089/57600 [1:46:11<8:27:24,  1.56it/s]
 18%|█▊        | 10090/57600 [1:46:12<8:31:06,  1.55it/s]
 18%|█▊        | 10091/57600 [1:46:13<8:25:06,  1.57it/s]
 18%|█▊        | 10092/57600 [1:46:13<8:28:50,  1.56it/s]
 18%|█▊        | 10093/57600 [1:46:14<8:21:20,  1.58it/s]
 18%|█▊        | 10094/57600 [1:46:15<8:21:19,  1.58it/s]
 18%|█▊        | 10095/57600 [1:46:15<8:03:33,  1.64it/s]
 18%|█▊        | 10096/57600 [1:46:16<8:09:47,  1.62it/s]
 18%|█▊        | 10097/57600 [1:46:16<8:09:42,  1.62it/s]
 18%|█▊        | 10098/57600 [1:46:17<8:13:14,  1.61it/s]
 18%|█▊        | 10099/57600 [1:46:18<8:09:26,  1.62it/s]
 18%|█▊        | 10100/57600 [1:46:18<8:10:00,  1.62it/s]
                                                         
{'loss': 1.381, 'learning_rate': 8.44773519163763e-07, 'epoch': 111.48}

 18%|█▊        | 10100/57600 [1:46:18<8:10:00,  1.62it/s]
 18%|█▊        | 10101/57600 [1:46:19<8:14:59,  1.60it/s]
 18%|█▊        | 10102/57600 [1:46:19<7:58:28,  1.65it/s]
 18%|█▊        | 10103/57600 [1:46:20<7:47:16,  1.69it/s]
 18%|█▊        | 10104/57600 [1:46:21<8:15:03,  1.60it/s]
 18%|█▊        | 10105/57600 [1:46:21<8:14:23,  1.60it/s]
 18%|█▊        | 10106/57600 [1:46:22<8:01:38,  1.64it/s]
 18%|█▊        | 10107/57600 [1:46:23<8:16:11,  1.60it/s]
 18%|█▊        | 10108/57600 [1:46:23<8:14:06,  1.60it/s]
 18%|█▊        | 10109/57600 [1:46:24<8:09:36,  1.62it/s]
 18%|█▊        | 10110/57600 [1:46:24<7:57:57,  1.66it/s]
 18%|█▊        | 10111/57600 [1:46:25<8:23:27,  1.57it/s]
 18%|█▊        | 10112/57600 [1:46:26<8:17:54,  1.59it/s]
 18%|█▊        | 10113/57600 [1:46:26<8:07:57,  1.62it/s]
 18%|█▊        | 10114/57600 [1:46:27<8:01:50,  1.64it/s]
 18%|█▊        | 10115/57600 [1:46:27<8:01:37,  1.64it/s]
 18%|█▊        | 10116/57600 [1:46:28<7:52:03,  1.68it/s]
 18%|█▊        | 10117/57600 [1:46:29<7:40:29,  1.72it/s]
 18%|█▊        | 10118/57600 [1:46:29<7:37:14,  1.73it/s]
 18%|█▊        | 10119/57600 [1:46:30<7:43:38,  1.71it/s]
 18%|█▊        | 10120/57600 [1:46:30<7:34:35,  1.74it/s]
                                                         
{'loss': 1.4153, 'learning_rate': 8.444599303135888e-07, 'epoch': 111.7}

 18%|█▊        | 10120/57600 [1:46:30<7:34:35,  1.74it/s]
 18%|█▊        | 10121/57600 [1:46:31<8:01:18,  1.64it/s]
 18%|█▊        | 10122/57600 [1:46:32<8:03:57,  1.64it/s]
 18%|█▊        | 10123/57600 [1:46:32<8:14:02,  1.60it/s]
 18%|█▊        | 10124/57600 [1:46:33<8:05:50,  1.63it/s]
 18%|█▊        | 10125/57600 [1:46:33<7:56:24,  1.66it/s]
 18%|█▊        | 10126/57600 [1:46:34<8:31:48,  1.55it/s]
 18%|█▊        | 10127/57600 [1:46:35<8:36:19,  1.53it/s]
 18%|█▊        | 10128/57600 [1:46:35<8:23:48,  1.57it/s]
 18%|█▊        | 10129/57600 [1:46:36<8:49:55,  1.49it/s]
 18%|█▊        | 10130/57600 [1:46:37<8:47:59,  1.50it/s]
 18%|█▊        | 10131/57600 [1:46:37<8:29:44,  1.55it/s]
 18%|█▊        | 10132/57600 [1:46:38<8:07:41,  1.62it/s]
 18%|█▊        | 10133/57600 [1:46:39<8:22:04,  1.58it/s]
 18%|█▊        | 10134/57600 [1:46:39<8:14:42,  1.60it/s]
 18%|█▊        | 10135/57600 [1:46:40<8:13:07,  1.60it/s]
 18%|█▊        | 10136/57600 [1:46:41<8:15:56,  1.60it/s]
 18%|█▊        | 10137/57600 [1:46:41<8:14:54,  1.60it/s]
 18%|█▊        | 10138/57600 [1:46:42<7:58:07,  1.65it/s]
 18%|█▊        | 10139/57600 [1:46:42<7:51:10,  1.68it/s]
 18%|█▊        | 10140/57600 [1:46:43<7:55:57,  1.66it/s]
                                                         
{'loss': 1.361, 'learning_rate': 8.441463414634147e-07, 'epoch': 111.92}

 18%|█▊        | 10140/57600 [1:46:43<7:55:57,  1.66it/s]
 18%|█▊        | 10141/57600 [1:46:43<7:55:41,  1.66it/s]
 18%|█▊        | 10142/57600 [1:46:44<7:50:46,  1.68it/s]
 18%|█▊        | 10143/57600 [1:46:45<7:48:58,  1.69it/s]
 18%|█▊        | 10144/57600 [1:46:45<7:55:10,  1.66it/s]
 18%|█▊        | 10145/57600 [1:46:46<7:58:38,  1.65it/s]
 18%|█▊        | 10146/57600 [1:46:47<8:05:35,  1.63it/s]
 18%|█▊        | 10147/57600 [1:46:47<8:08:59,  1.62it/s]
 18%|█▊        | 10148/57600 [1:46:48<8:23:23,  1.57it/s]
 18%|█▊        | 10149/57600 [1:46:48<8:20:25,  1.58it/s]
 18%|█▊        | 10150/57600 [1:46:49<8:33:15,  1.54it/s]
 18%|█▊        | 10151/57600 [1:46:50<8:32:09,  1.54it/s]
 18%|█▊        | 10152/57600 [1:46:50<8:09:28,  1.62it/s]
 18%|█▊        | 10153/57600 [1:46:51<8:17:05,  1.59it/s]
 18%|█▊        | 10154/57600 [1:46:52<8:30:49,  1.55it/s]
 18%|█▊        | 10155/57600 [1:46:52<8:32:42,  1.54it/s]
 18%|█▊        | 10156/57600 [1:46:53<8:31:25,  1.55it/s]
 18%|█▊        | 10157/57600 [1:46:54<8:14:28,  1.60it/s]
 18%|█▊        | 10158/57600 [1:46:54<8:21:47,  1.58it/s]
 18%|█▊        | 10159/57600 [1:46:55<8:29:25,  1.55it/s]
 18%|█▊        | 10160/57600 [1:46:55<8:15:54,  1.59it/s]
                                                         
{'loss': 1.3341, 'learning_rate': 8.438327526132404e-07, 'epoch': 112.14}

 18%|█▊        | 10160/57600 [1:46:55<8:15:54,  1.59it/s]
 18%|█▊        | 10161/57600 [1:46:56<8:04:55,  1.63it/s]
 18%|█▊        | 10162/57600 [1:46:57<8:04:40,  1.63it/s]
 18%|█▊        | 10163/57600 [1:46:57<7:54:04,  1.67it/s]
 18%|█▊        | 10164/57600 [1:46:58<8:03:46,  1.63it/s]
 18%|█▊        | 10165/57600 [1:46:58<7:59:34,  1.65it/s]
 18%|█▊        | 10166/57600 [1:46:59<7:58:30,  1.65it/s]
 18%|█▊        | 10167/57600 [1:47:00<8:05:32,  1.63it/s]
 18%|█▊        | 10168/57600 [1:47:00<7:56:43,  1.66it/s]
 18%|█▊        | 10169/57600 [1:47:01<7:55:11,  1.66it/s]
 18%|█▊        | 10170/57600 [1:47:01<8:05:48,  1.63it/s]
 18%|█▊        | 10171/57600 [1:47:02<8:09:05,  1.62it/s]
 18%|█▊        | 10172/57600 [1:47:03<8:07:44,  1.62it/s]
 18%|█▊        | 10173/57600 [1:47:03<8:17:59,  1.59it/s]
 18%|█▊        | 10174/57600 [1:47:04<7:59:21,  1.65it/s]
 18%|█▊        | 10175/57600 [1:47:05<7:56:51,  1.66it/s]
 18%|█▊        | 10176/57600 [1:47:05<8:16:46,  1.59it/s]
 18%|█▊        | 10177/57600 [1:47:06<8:30:43,  1.55it/s]
 18%|█▊        | 10178/57600 [1:47:07<8:31:40,  1.54it/s]
 18%|█▊        | 10179/57600 [1:47:07<8:36:32,  1.53it/s]
 18%|█▊        | 10180/57600 [1:47:08<8:27:25,  1.56it/s]
                                                         
{'loss': 1.3696, 'learning_rate': 8.435191637630662e-07, 'epoch': 112.36}

 18%|█▊        | 10180/57600 [1:47:08<8:27:25,  1.56it/s]
 18%|█▊        | 10181/57600 [1:47:09<8:35:50,  1.53it/s]
 18%|█▊        | 10182/57600 [1:47:09<8:17:25,  1.59it/s]
 18%|█▊        | 10183/57600 [1:47:10<8:20:06,  1.58it/s]
 18%|█▊        | 10184/57600 [1:47:10<8:10:53,  1.61it/s]
 18%|█▊        | 10185/57600 [1:47:11<8:00:21,  1.65it/s]
 18%|█▊        | 10186/57600 [1:47:12<8:05:56,  1.63it/s]
 18%|█▊        | 10187/57600 [1:47:12<8:20:49,  1.58it/s]
 18%|█▊        | 10188/57600 [1:47:13<8:20:31,  1.58it/s]
 18%|█▊        | 10189/57600 [1:47:13<8:16:01,  1.59it/s]
 18%|█▊        | 10190/57600 [1:47:14<8:14:42,  1.60it/s]
 18%|█▊        | 10191/57600 [1:47:15<8:06:12,  1.63it/s]
 18%|█▊        | 10192/57600 [1:47:15<8:06:26,  1.62it/s]
 18%|█▊        | 10193/57600 [1:47:16<8:16:12,  1.59it/s]
 18%|█▊        | 10194/57600 [1:47:17<8:12:47,  1.60it/s]
 18%|█▊        | 10195/57600 [1:47:17<8:09:13,  1.61it/s]
 18%|█▊        | 10196/57600 [1:47:18<8:00:33,  1.64it/s]
 18%|█▊        | 10197/57600 [1:47:18<8:11:33,  1.61it/s]
 18%|█▊        | 10198/57600 [1:47:19<8:02:26,  1.64it/s]
 18%|█▊        | 10199/57600 [1:47:20<7:52:58,  1.67it/s]
 18%|█▊        | 10200/57600 [1:47:20<7:55:33,  1.66it/s]
                                                         
{'loss': 1.3899, 'learning_rate': 8.432055749128919e-07, 'epoch': 112.58}

 18%|█▊        | 10200/57600 [1:47:20<7:55:33,  1.66it/s]
 18%|█▊        | 10201/57600 [1:47:21<7:55:26,  1.66it/s]
 18%|█▊        | 10202/57600 [1:47:21<8:02:52,  1.64it/s]
 18%|█▊        | 10203/57600 [1:47:22<8:07:52,  1.62it/s]
 18%|█▊        | 10204/57600 [1:47:23<8:03:39,  1.63it/s]
 18%|█▊        | 10205/57600 [1:47:23<8:01:35,  1.64it/s]
 18%|█▊        | 10206/57600 [1:47:24<8:17:14,  1.59it/s]
 18%|█▊        | 10207/57600 [1:47:25<8:27:19,  1.56it/s]
 18%|█▊        | 10208/57600 [1:47:25<8:16:20,  1.59it/s]
 18%|█▊        | 10209/57600 [1:47:26<8:01:58,  1.64it/s]
 18%|█▊        | 10210/57600 [1:47:26<7:52:55,  1.67it/s]
 18%|█▊        | 10211/57600 [1:47:27<7:56:34,  1.66it/s]
 18%|█▊        | 10212/57600 [1:47:28<7:49:09,  1.68it/s]
 18%|█▊        | 10213/57600 [1:47:28<7:41:05,  1.71it/s]
 18%|█▊        | 10214/57600 [1:47:29<7:46:28,  1.69it/s]
 18%|█▊        | 10215/57600 [1:47:29<7:56:42,  1.66it/s]
 18%|█▊        | 10216/57600 [1:47:30<7:54:55,  1.66it/s]
 18%|█▊        | 10217/57600 [1:47:31<7:51:23,  1.68it/s]
 18%|█▊        | 10218/57600 [1:47:31<7:50:01,  1.68it/s]
 18%|█▊        | 10219/57600 [1:47:32<7:48:16,  1.69it/s]
 18%|█▊        | 10220/57600 [1:47:32<8:02:14,  1.64it/s]
                                                         
{'loss': 1.3883, 'learning_rate': 8.428919860627178e-07, 'epoch': 112.8}

 18%|█▊        | 10220/57600 [1:47:32<8:02:14,  1.64it/s]
 18%|█▊        | 10221/57600 [1:47:33<8:01:53,  1.64it/s]
 18%|█▊        | 10222/57600 [1:47:34<8:09:38,  1.61it/s]
 18%|█▊        | 10223/57600 [1:47:34<8:08:42,  1.62it/s]
 18%|█▊        | 10224/57600 [1:47:35<7:54:43,  1.66it/s]
 18%|█▊        | 10225/57600 [1:47:35<8:09:41,  1.61it/s]
 18%|█▊        | 10226/57600 [1:47:36<8:17:18,  1.59it/s]
 18%|█▊        | 10227/57600 [1:47:37<8:25:31,  1.56it/s]
 18%|█▊        | 10228/57600 [1:47:37<8:22:30,  1.57it/s]
 18%|█▊        | 10229/57600 [1:47:38<8:33:30,  1.54it/s]
 18%|█▊        | 10230/57600 [1:47:39<8:16:49,  1.59it/s]
 18%|█▊        | 10231/57600 [1:47:39<8:11:08,  1.61it/s]
 18%|█▊        | 10232/57600 [1:47:40<8:14:54,  1.60it/s]
 18%|█▊        | 10233/57600 [1:47:40<8:00:20,  1.64it/s]
 18%|█▊        | 10234/57600 [1:47:41<7:56:27,  1.66it/s]
 18%|█▊        | 10235/57600 [1:47:42<7:59:56,  1.64it/s]
 18%|█▊        | 10236/57600 [1:47:42<8:01:17,  1.64it/s]
 18%|█▊        | 10237/57600 [1:47:43<7:57:25,  1.65it/s]
 18%|█▊        | 10238/57600 [1:47:44<8:32:02,  1.54it/s]
 18%|█▊        | 10239/57600 [1:47:44<8:38:30,  1.52it/s]
 18%|█▊        | 10240/57600 [1:47:45<8:29:22,  1.55it/s]
                                                         
{'loss': 1.3401, 'learning_rate': 8.425783972125435e-07, 'epoch': 113.02}

 18%|█▊        | 10240/57600 [1:47:45<8:29:22,  1.55it/s]
 18%|█▊        | 10241/57600 [1:47:46<8:19:23,  1.58it/s]
 18%|█▊        | 10242/57600 [1:47:46<8:12:49,  1.60it/s]
 18%|█▊        | 10243/57600 [1:47:47<8:08:27,  1.62it/s]
 18%|█▊        | 10244/57600 [1:47:47<8:27:32,  1.56it/s]
 18%|█▊        | 10245/57600 [1:47:48<8:13:30,  1.60it/s]
 18%|█▊        | 10246/57600 [1:47:49<8:33:25,  1.54it/s]
 18%|█▊        | 10247/57600 [1:47:49<8:28:08,  1.55it/s]
 18%|█▊        | 10248/57600 [1:47:50<8:24:26,  1.56it/s]
 18%|█▊        | 10249/57600 [1:47:51<8:26:08,  1.56it/s]
 18%|█▊        | 10250/57600 [1:47:51<8:37:52,  1.52it/s]
 18%|█▊        | 10251/57600 [1:47:52<8:23:27,  1.57it/s]
 18%|█▊        | 10252/57600 [1:47:53<8:31:18,  1.54it/s]
 18%|█▊        | 10253/57600 [1:47:53<8:14:26,  1.60it/s]
 18%|█▊        | 10254/57600 [1:47:54<7:58:11,  1.65it/s]
 18%|█▊        | 10255/57600 [1:47:54<7:49:52,  1.68it/s]
 18%|█▊        | 10256/57600 [1:47:55<7:58:53,  1.65it/s]
 18%|█▊        | 10257/57600 [1:47:56<7:55:16,  1.66it/s]
 18%|█▊        | 10258/57600 [1:47:56<8:04:42,  1.63it/s]
 18%|█▊        | 10259/57600 [1:47:57<8:12:03,  1.60it/s]
 18%|█▊        | 10260/57600 [1:47:57<8:11:26,  1.61it/s]
                                                         
{'loss': 1.3599, 'learning_rate': 8.422648083623693e-07, 'epoch': 113.25}

 18%|█▊        | 10260/57600 [1:47:57<8:11:26,  1.61it/s]
 18%|█▊        | 10261/57600 [1:47:58<8:16:06,  1.59it/s]
 18%|█▊        | 10262/57600 [1:47:59<8:00:35,  1.64it/s]
 18%|█▊        | 10263/57600 [1:47:59<8:03:54,  1.63it/s]
 18%|█▊        | 10264/57600 [1:48:00<8:02:18,  1.64it/s]
 18%|█▊        | 10265/57600 [1:48:00<7:56:58,  1.65it/s]
 18%|█▊        | 10266/57600 [1:48:01<8:16:55,  1.59it/s]
 18%|█▊        | 10267/57600 [1:48:02<8:04:16,  1.63it/s]
 18%|█▊        | 10268/57600 [1:48:02<8:18:51,  1.58it/s]
 18%|█▊        | 10269/57600 [1:48:03<8:10:39,  1.61it/s]
 18%|█▊        | 10270/57600 [1:48:04<8:20:23,  1.58it/s]
 18%|█▊        | 10271/57600 [1:48:04<8:07:10,  1.62it/s]
 18%|█▊        | 10272/57600 [1:48:05<8:05:00,  1.63it/s]
 18%|█▊        | 10273/57600 [1:48:06<8:51:19,  1.48it/s]
 18%|█▊        | 10274/57600 [1:48:06<8:33:50,  1.54it/s]
 18%|█▊        | 10275/57600 [1:48:07<8:26:26,  1.56it/s]
 18%|█▊        | 10276/57600 [1:48:08<8:36:55,  1.53it/s]
 18%|█▊        | 10277/57600 [1:48:08<8:27:01,  1.56it/s]
 18%|█▊        | 10278/57600 [1:48:09<8:07:06,  1.62it/s]
 18%|█▊        | 10279/57600 [1:48:09<8:02:18,  1.64it/s]
 18%|█▊        | 10280/57600 [1:48:10<8:28:32,  1.55it/s]
                                                         
{'loss': 1.3688, 'learning_rate': 8.419512195121951e-07, 'epoch': 113.47}

 18%|█▊        | 10280/57600 [1:48:10<8:28:32,  1.55it/s]
 18%|█▊        | 10281/57600 [1:48:11<8:07:34,  1.62it/s]
 18%|█▊        | 10282/57600 [1:48:11<7:53:56,  1.66it/s]
 18%|█▊        | 10283/57600 [1:48:12<8:01:10,  1.64it/s]
 18%|█▊        | 10284/57600 [1:48:12<7:50:18,  1.68it/s]
 18%|█▊        | 10285/57600 [1:48:13<8:09:21,  1.61it/s]
 18%|█▊        | 10286/57600 [1:48:14<8:09:59,  1.61it/s]
 18%|█▊        | 10287/57600 [1:48:14<8:01:24,  1.64it/s]
 18%|█▊        | 10288/57600 [1:48:15<8:07:28,  1.62it/s]
 18%|█▊        | 10289/57600 [1:48:16<8:10:07,  1.61it/s]
 18%|█▊        | 10290/57600 [1:48:16<8:19:52,  1.58it/s]
 18%|█▊        | 10291/57600 [1:48:17<8:21:10,  1.57it/s]
 18%|█▊        | 10292/57600 [1:48:17<8:06:27,  1.62it/s]
 18%|█▊        | 10293/57600 [1:48:18<7:56:15,  1.66it/s]
 18%|█▊        | 10294/57600 [1:48:19<7:44:46,  1.70it/s]
 18%|█▊        | 10295/57600 [1:48:19<7:56:51,  1.65it/s]
 18%|█▊        | 10296/57600 [1:48:20<8:00:36,  1.64it/s]
 18%|█▊        | 10297/57600 [1:48:20<7:59:45,  1.64it/s]
 18%|█▊        | 10298/57600 [1:48:21<8:00:34,  1.64it/s]
 18%|█▊        | 10299/57600 [1:48:22<7:59:04,  1.65it/s]
 18%|█▊        | 10300/57600 [1:48:22<7:59:42,  1.64it/s]
                                                         
{'loss': 1.3976, 'learning_rate': 8.416376306620209e-07, 'epoch': 113.69}

 18%|█▊        | 10300/57600 [1:48:22<7:59:42,  1.64it/s]
 18%|█▊        | 10301/57600 [1:48:23<8:06:32,  1.62it/s]
 18%|█▊        | 10302/57600 [1:48:23<7:58:57,  1.65it/s]
 18%|█▊        | 10303/57600 [1:48:24<7:44:06,  1.70it/s]
 18%|█▊        | 10304/57600 [1:48:25<7:58:56,  1.65it/s]
 18%|█▊        | 10305/57600 [1:48:25<7:56:43,  1.65it/s]
 18%|█▊        | 10306/57600 [1:48:26<8:10:41,  1.61it/s]
 18%|█▊        | 10307/57600 [1:48:26<8:05:57,  1.62it/s]
 18%|█▊        | 10308/57600 [1:48:27<8:03:57,  1.63it/s]
 18%|█▊        | 10309/57600 [1:48:28<7:50:24,  1.68it/s]
 18%|█▊        | 10310/57600 [1:48:28<7:46:07,  1.69it/s]
 18%|█▊        | 10311/57600 [1:48:29<8:00:33,  1.64it/s]
 18%|█▊        | 10312/57600 [1:48:29<7:47:45,  1.68it/s]
 18%|█▊        | 10313/57600 [1:48:30<7:48:26,  1.68it/s]
 18%|█▊        | 10314/57600 [1:48:31<7:45:24,  1.69it/s]
 18%|█▊        | 10315/57600 [1:48:31<8:07:31,  1.62it/s]
 18%|█▊        | 10316/57600 [1:48:32<8:05:03,  1.62it/s]
 18%|█▊        | 10317/57600 [1:48:33<8:08:43,  1.61it/s]
 18%|█▊        | 10318/57600 [1:48:33<8:02:48,  1.63it/s]
 18%|█▊        | 10319/57600 [1:48:34<8:06:03,  1.62it/s]
 18%|█▊        | 10320/57600 [1:48:34<8:12:15,  1.60it/s]
                                                         
{'loss': 1.3909, 'learning_rate': 8.413240418118465e-07, 'epoch': 113.91}

 18%|█▊        | 10320/57600 [1:48:34<8:12:15,  1.60it/s]
 18%|█▊        | 10321/57600 [1:48:35<8:24:14,  1.56it/s]
 18%|█▊        | 10322/57600 [1:48:36<8:27:03,  1.55it/s]
 18%|█▊        | 10323/57600 [1:48:36<8:16:29,  1.59it/s]
 18%|█▊        | 10324/57600 [1:48:37<8:02:23,  1.63it/s]
 18%|█▊        | 10325/57600 [1:48:38<8:02:33,  1.63it/s]
 18%|█▊        | 10326/57600 [1:48:38<7:56:03,  1.66it/s]
 18%|█▊        | 10327/57600 [1:48:39<7:42:29,  1.70it/s]
 18%|█▊        | 10328/57600 [1:48:39<7:36:09,  1.73it/s]
 18%|█▊        | 10329/57600 [1:48:40<7:56:56,  1.65it/s]
 18%|█▊        | 10330/57600 [1:48:40<7:58:58,  1.64it/s]
 18%|█▊        | 10331/57600 [1:48:41<7:58:29,  1.65it/s]
 18%|█▊        | 10332/57600 [1:48:42<8:11:04,  1.60it/s]
 18%|█▊        | 10333/57600 [1:48:42<8:08:32,  1.61it/s]
 18%|█▊        | 10334/57600 [1:48:43<7:56:47,  1.65it/s]
 18%|█▊        | 10335/57600 [1:48:43<7:44:46,  1.69it/s]
 18%|█▊        | 10336/57600 [1:48:44<8:10:06,  1.61it/s]
 18%|█▊        | 10337/57600 [1:48:45<7:55:08,  1.66it/s]
 18%|█▊        | 10338/57600 [1:48:45<7:58:48,  1.65it/s]
 18%|█▊        | 10339/57600 [1:48:46<8:09:16,  1.61it/s]
 18%|█▊        | 10340/57600 [1:48:47<8:13:44,  1.60it/s]
                                                         
{'loss': 1.4132, 'learning_rate': 8.410104529616724e-07, 'epoch': 114.13}

 18%|█▊        | 10340/57600 [1:48:47<8:13:44,  1.60it/s]
 18%|█▊        | 10341/57600 [1:48:47<8:15:26,  1.59it/s]
 18%|█▊        | 10342/57600 [1:48:48<8:10:30,  1.61it/s]
 18%|█▊        | 10343/57600 [1:48:49<8:08:37,  1.61it/s]
 18%|█▊        | 10344/57600 [1:48:49<8:00:58,  1.64it/s]
 18%|█▊        | 10345/57600 [1:48:50<7:59:21,  1.64it/s]
 18%|█▊        | 10346/57600 [1:48:50<7:56:37,  1.65it/s]
 18%|█▊        | 10347/57600 [1:48:51<7:57:06,  1.65it/s]
 18%|█▊        | 10348/57600 [1:48:52<8:11:01,  1.60it/s]
 18%|█▊        | 10349/57600 [1:48:52<8:24:09,  1.56it/s]
 18%|█▊        | 10350/57600 [1:48:53<8:17:40,  1.58it/s]
 18%|█▊        | 10351/57600 [1:48:53<8:10:20,  1.61it/s]
 18%|█▊        | 10352/57600 [1:48:54<8:02:55,  1.63it/s]
 18%|█▊        | 10353/57600 [1:48:55<8:00:02,  1.64it/s]
 18%|█▊        | 10354/57600 [1:48:55<8:06:58,  1.62it/s]
 18%|█▊        | 10355/57600 [1:48:56<8:25:42,  1.56it/s]
 18%|█▊        | 10356/57600 [1:48:57<8:38:26,  1.52it/s]
 18%|█▊        | 10357/57600 [1:48:57<8:19:53,  1.58it/s]
 18%|█▊        | 10358/57600 [1:48:58<8:17:02,  1.58it/s]
 18%|█▊        | 10359/57600 [1:48:58<7:57:20,  1.65it/s]
 18%|█▊        | 10360/57600 [1:48:59<7:47:52,  1.68it/s]
                                                         
{'loss': 1.3741, 'learning_rate': 8.406968641114982e-07, 'epoch': 114.35}

 18%|█▊        | 10360/57600 [1:48:59<7:47:52,  1.68it/s]
 18%|█▊        | 10361/57600 [1:49:00<7:53:37,  1.66it/s]
 18%|█▊        | 10362/57600 [1:49:00<7:46:05,  1.69it/s]
 18%|█▊        | 10363/57600 [1:49:01<7:43:19,  1.70it/s]
 18%|█▊        | 10364/57600 [1:49:01<7:48:44,  1.68it/s]
 18%|█▊        | 10365/57600 [1:49:02<7:42:20,  1.70it/s]
 18%|█▊        | 10366/57600 [1:49:03<7:45:43,  1.69it/s]
 18%|█▊        | 10367/57600 [1:49:03<7:55:10,  1.66it/s]
 18%|█▊        | 10368/57600 [1:49:04<8:04:13,  1.63it/s]
 18%|█▊        | 10369/57600 [1:49:05<8:22:50,  1.57it/s]
 18%|█▊        | 10370/57600 [1:49:05<8:17:25,  1.58it/s]
 18%|█▊        | 10371/57600 [1:49:06<8:14:39,  1.59it/s]
 18%|█▊        | 10372/57600 [1:49:07<8:44:32,  1.50it/s]
 18%|█▊        | 10373/57600 [1:49:07<8:47:12,  1.49it/s]
 18%|█▊        | 10374/57600 [1:49:08<8:31:26,  1.54it/s]
 18%|█▊        | 10375/57600 [1:49:08<8:37:25,  1.52it/s]
 18%|█▊        | 10376/57600 [1:49:09<8:17:07,  1.58it/s]
 18%|█▊        | 10377/57600 [1:49:10<8:18:35,  1.58it/s]
 18%|█▊        | 10378/57600 [1:49:10<8:08:46,  1.61it/s]
 18%|█▊        | 10379/57600 [1:49:11<7:59:14,  1.64it/s]
 18%|█▊        | 10380/57600 [1:49:11<8:03:29,  1.63it/s]
                                                         
{'loss': 1.3339, 'learning_rate': 8.40383275261324e-07, 'epoch': 114.57}

 18%|█▊        | 10380/57600 [1:49:11<8:03:29,  1.63it/s]
 18%|█▊        | 10381/57600 [1:49:12<8:07:19,  1.61it/s]
 18%|█▊        | 10382/57600 [1:49:13<8:04:08,  1.63it/s]
 18%|█▊        | 10383/57600 [1:49:13<7:58:08,  1.65it/s]
 18%|█▊        | 10384/57600 [1:49:14<7:59:18,  1.64it/s]
 18%|█▊        | 10385/57600 [1:49:15<7:55:20,  1.66it/s]
 18%|█▊        | 10386/57600 [1:49:15<7:46:40,  1.69it/s]
 18%|█▊        | 10387/57600 [1:49:16<7:59:25,  1.64it/s]
 18%|█▊        | 10388/57600 [1:49:16<8:00:10,  1.64it/s]
 18%|█▊        | 10389/57600 [1:49:17<8:17:15,  1.58it/s]
 18%|█▊        | 10390/57600 [1:49:18<8:19:20,  1.58it/s]
 18%|█▊        | 10391/57600 [1:49:18<8:03:36,  1.63it/s]
 18%|█▊        | 10392/57600 [1:49:19<8:17:06,  1.58it/s]
 18%|█▊        | 10393/57600 [1:49:19<8:06:50,  1.62it/s]
 18%|█▊        | 10394/57600 [1:49:20<8:03:31,  1.63it/s]
 18%|█▊        | 10395/57600 [1:49:21<8:16:51,  1.58it/s]
 18%|█▊        | 10396/57600 [1:49:21<8:07:37,  1.61it/s]
 18%|█▊        | 10397/57600 [1:49:22<8:07:59,  1.61it/s]
 18%|█▊        | 10398/57600 [1:49:23<8:12:36,  1.60it/s]
 18%|█▊        | 10399/57600 [1:49:23<8:10:45,  1.60it/s]
 18%|█▊        | 10400/57600 [1:49:24<7:59:19,  1.64it/s]
                                                         
{'loss': 1.3869, 'learning_rate': 8.400696864111498e-07, 'epoch': 114.79}

 18%|█▊        | 10400/57600 [1:49:24<7:59:19,  1.64it/s]
 18%|█▊        | 10401/57600 [1:49:24<8:14:07,  1.59it/s]
 18%|█▊        | 10402/57600 [1:49:25<8:15:03,  1.59it/s]
 18%|█▊        | 10403/57600 [1:49:26<8:09:50,  1.61it/s]
 18%|█▊        | 10404/57600 [1:49:26<7:55:44,  1.65it/s]
 18%|█▊        | 10405/57600 [1:49:27<7:54:49,  1.66it/s]
 18%|█▊        | 10406/57600 [1:49:28<8:06:51,  1.62it/s]
 18%|█▊        | 10407/57600 [1:49:28<8:06:20,  1.62it/s]
 18%|█▊        | 10408/57600 [1:49:29<8:00:06,  1.64it/s]
 18%|█▊        | 10409/57600 [1:49:29<7:59:36,  1.64it/s]
 18%|█▊        | 10410/57600 [1:49:30<7:54:40,  1.66it/s]
 18%|█▊        | 10411/57600 [1:49:31<8:05:20,  1.62it/s]
 18%|█▊        | 10412/57600 [1:49:31<8:14:59,  1.59it/s]
 18%|█▊        | 10413/57600 [1:49:32<8:00:35,  1.64it/s]
 18%|█▊        | 10414/57600 [1:49:32<7:59:47,  1.64it/s]
 18%|█▊        | 10415/57600 [1:49:33<8:10:57,  1.60it/s]
 18%|█▊        | 10416/57600 [1:49:34<8:13:33,  1.59it/s]
 18%|█▊        | 10417/57600 [1:49:34<8:05:08,  1.62it/s]
 18%|█▊        | 10418/57600 [1:49:35<8:07:53,  1.61it/s]
 18%|█▊        | 10419/57600 [1:49:36<8:20:03,  1.57it/s]
 18%|█▊        | 10420/57600 [1:49:36<8:39:06,  1.51it/s]
                                                         
{'loss': 1.3644, 'learning_rate': 8.397560975609756e-07, 'epoch': 115.01}

 18%|█▊        | 10420/57600 [1:49:36<8:39:06,  1.51it/s]
 18%|█▊        | 10421/57600 [1:49:37<8:34:03,  1.53it/s]
 18%|█▊        | 10422/57600 [1:49:38<8:24:25,  1.56it/s]
 18%|█▊        | 10423/57600 [1:49:38<8:14:54,  1.59it/s]
 18%|█▊        | 10424/57600 [1:49:39<8:16:37,  1.58it/s]
 18%|█▊        | 10425/57600 [1:49:40<8:38:43,  1.52it/s]
 18%|█▊        | 10426/57600 [1:49:40<8:30:40,  1.54it/s]
 18%|█▊        | 10427/57600 [1:49:41<8:08:49,  1.61it/s]
 18%|█▊        | 10428/57600 [1:49:41<8:17:19,  1.58it/s]
 18%|█▊        | 10429/57600 [1:49:42<8:17:43,  1.58it/s]
 18%|█▊        | 10430/57600 [1:49:43<8:02:04,  1.63it/s]
 18%|█▊        | 10431/57600 [1:49:43<8:19:58,  1.57it/s]
 18%|█▊        | 10432/57600 [1:49:44<8:24:51,  1.56it/s]
 18%|█▊        | 10433/57600 [1:49:45<8:23:22,  1.56it/s]
 18%|█▊        | 10434/57600 [1:49:45<8:16:24,  1.58it/s]
 18%|█▊        | 10435/57600 [1:49:46<8:17:23,  1.58it/s]
 18%|█▊        | 10436/57600 [1:49:46<8:16:03,  1.58it/s]
 18%|█▊        | 10437/57600 [1:49:47<8:06:37,  1.62it/s]
 18%|█▊        | 10438/57600 [1:49:48<8:03:46,  1.62it/s]
 18%|█▊        | 10439/57600 [1:49:48<7:45:19,  1.69it/s]
 18%|█▊        | 10440/57600 [1:49:49<7:53:07,  1.66it/s]
                                                         
{'loss': 1.3584, 'learning_rate': 8.394425087108014e-07, 'epoch': 115.23}

 18%|█▊        | 10440/57600 [1:49:49<7:53:07,  1.66it/s]
 18%|█▊        | 10441/57600 [1:49:49<7:59:23,  1.64it/s]
 18%|█▊        | 10442/57600 [1:49:50<7:54:09,  1.66it/s]
 18%|█▊        | 10443/57600 [1:49:51<7:56:09,  1.65it/s]
 18%|█▊        | 10444/57600 [1:49:51<8:08:36,  1.61it/s]
 18%|█▊        | 10445/57600 [1:49:52<8:08:42,  1.61it/s]
 18%|█▊        | 10446/57600 [1:49:52<7:56:37,  1.65it/s]
 18%|█▊        | 10447/57600 [1:49:53<7:51:28,  1.67it/s]
 18%|█▊        | 10448/57600 [1:49:54<7:49:55,  1.67it/s]
 18%|█▊        | 10449/57600 [1:49:54<7:37:16,  1.72it/s]
 18%|█▊        | 10450/57600 [1:49:55<8:03:04,  1.63it/s]
 18%|█▊        | 10451/57600 [1:49:56<8:13:56,  1.59it/s]
 18%|█▊        | 10452/57600 [1:49:56<8:32:57,  1.53it/s]
 18%|█▊        | 10453/57600 [1:49:57<8:10:06,  1.60it/s]
 18%|█▊        | 10454/57600 [1:49:57<7:52:31,  1.66it/s]
 18%|█▊        | 10455/57600 [1:49:58<8:05:35,  1.62it/s]
 18%|█▊        | 10456/57600 [1:49:59<8:23:06,  1.56it/s]
 18%|█▊        | 10457/57600 [1:49:59<8:13:43,  1.59it/s]
 18%|█▊        | 10458/57600 [1:50:00<8:11:55,  1.60it/s]
 18%|█▊        | 10459/57600 [1:50:01<8:19:46,  1.57it/s]
 18%|█▊        | 10460/57600 [1:50:01<7:59:24,  1.64it/s]
                                                         
{'loss': 1.3698, 'learning_rate': 8.391289198606271e-07, 'epoch': 115.45}

 18%|█▊        | 10460/57600 [1:50:01<7:59:24,  1.64it/s]
 18%|█▊        | 10461/57600 [1:50:02<8:20:48,  1.57it/s]
 18%|█▊        | 10462/57600 [1:50:02<8:04:00,  1.62it/s]
 18%|█▊        | 10463/57600 [1:50:03<8:22:24,  1.56it/s]
 18%|█▊        | 10464/57600 [1:50:04<8:14:22,  1.59it/s]
 18%|█▊        | 10465/57600 [1:50:04<8:13:57,  1.59it/s]
 18%|█▊        | 10466/57600 [1:50:05<8:17:59,  1.58it/s]
 18%|█▊        | 10467/57600 [1:50:06<8:03:07,  1.63it/s]
 18%|█▊        | 10468/57600 [1:50:06<8:07:08,  1.61it/s]
 18%|█▊        | 10469/57600 [1:50:07<7:54:07,  1.66it/s]
 18%|█▊        | 10470/57600 [1:50:07<7:50:36,  1.67it/s]
 18%|█▊        | 10471/57600 [1:50:08<7:50:01,  1.67it/s]
 18%|█▊        | 10472/57600 [1:50:09<8:04:24,  1.62it/s]
 18%|█▊        | 10473/57600 [1:50:09<7:58:47,  1.64it/s]
 18%|█▊        | 10474/57600 [1:50:10<8:02:18,  1.63it/s]
 18%|█▊        | 10475/57600 [1:50:10<7:57:01,  1.65it/s]
 18%|█▊        | 10476/57600 [1:50:11<7:59:37,  1.64it/s]
 18%|█▊        | 10477/57600 [1:50:12<7:52:23,  1.66it/s]
 18%|█▊        | 10478/57600 [1:50:12<7:58:31,  1.64it/s]
 18%|█▊        | 10479/57600 [1:50:13<8:11:30,  1.60it/s]
 18%|█▊        | 10480/57600 [1:50:14<8:08:42,  1.61it/s]
                                                         
{'loss': 1.39, 'learning_rate': 8.388153310104529e-07, 'epoch': 115.67}

 18%|█▊        | 10480/57600 [1:50:14<8:08:42,  1.61it/s]
 18%|█▊        | 10481/57600 [1:50:14<8:18:38,  1.57it/s]
 18%|█▊        | 10482/57600 [1:50:15<8:17:39,  1.58it/s]
 18%|█▊        | 10483/57600 [1:50:15<8:24:21,  1.56it/s]
 18%|█▊        | 10484/57600 [1:50:16<8:18:07,  1.58it/s]
 18%|█▊        | 10485/57600 [1:50:17<8:14:20,  1.59it/s]
 18%|█▊        | 10486/57600 [1:50:17<7:54:25,  1.66it/s]
 18%|█▊        | 10487/57600 [1:50:18<7:55:13,  1.65it/s]
 18%|█▊        | 10488/57600 [1:50:18<7:58:13,  1.64it/s]
 18%|█▊        | 10489/57600 [1:50:19<8:11:10,  1.60it/s]
 18%|█▊        | 10490/57600 [1:50:20<7:53:06,  1.66it/s]
 18%|█▊        | 10491/57600 [1:50:20<8:02:58,  1.63it/s]
 18%|█▊        | 10492/57600 [1:50:21<7:58:57,  1.64it/s]
 18%|█▊        | 10493/57600 [1:50:22<7:54:28,  1.65it/s]
 18%|█▊        | 10494/57600 [1:50:22<8:14:44,  1.59it/s]
 18%|█▊        | 10495/57600 [1:50:23<8:05:21,  1.62it/s]
 18%|█▊        | 10496/57600 [1:50:23<8:14:45,  1.59it/s]
 18%|█▊        | 10497/57600 [1:50:24<8:07:17,  1.61it/s]
 18%|█▊        | 10498/57600 [1:50:25<7:55:49,  1.65it/s]
 18%|█▊        | 10499/57600 [1:50:25<7:52:17,  1.66it/s]
 18%|█▊        | 10500/57600 [1:50:26<7:49:25,  1.67it/s]
                                                         
{'loss': 1.3651, 'learning_rate': 8.385017421602787e-07, 'epoch': 115.89}

 18%|█▊        | 10500/57600 [1:50:26<7:49:25,  1.67it/s]
 18%|█▊        | 10501/57600 [1:50:26<7:52:28,  1.66it/s]
 18%|█▊        | 10502/57600 [1:50:27<8:07:18,  1.61it/s]
 18%|█▊        | 10503/57600 [1:50:28<8:06:31,  1.61it/s]
 18%|█▊        | 10504/57600 [1:50:28<8:13:51,  1.59it/s]
 18%|█▊        | 10505/57600 [1:50:29<8:15:27,  1.58it/s]
 18%|█▊        | 10506/57600 [1:50:30<8:39:45,  1.51it/s]
 18%|█▊        | 10507/57600 [1:50:30<8:19:30,  1.57it/s]
 18%|█▊        | 10508/57600 [1:50:31<8:29:50,  1.54it/s]
 18%|█▊        | 10509/57600 [1:50:32<8:25:09,  1.55it/s]
 18%|█▊        | 10510/57600 [1:50:32<8:31:15,  1.54it/s]
 18%|█▊        | 10511/57600 [1:50:33<8:26:08,  1.55it/s]
 18%|█▊        | 10512/57600 [1:50:34<8:12:02,  1.60it/s]
 18%|█▊        | 10513/57600 [1:50:34<8:17:23,  1.58it/s]
 18%|█▊        | 10514/57600 [1:50:35<8:12:26,  1.59it/s]
 18%|█▊        | 10515/57600 [1:50:35<7:52:17,  1.66it/s]
 18%|█▊        | 10516/57600 [1:50:36<7:49:36,  1.67it/s]
 18%|█▊        | 10517/57600 [1:50:37<8:05:01,  1.62it/s]
 18%|█▊        | 10518/57600 [1:50:37<8:16:54,  1.58it/s]
 18%|█▊        | 10519/57600 [1:50:38<8:01:23,  1.63it/s]
 18%|█▊        | 10520/57600 [1:50:38<8:08:16,  1.61it/s]
                                                         
{'loss': 1.339, 'learning_rate': 8.381881533101045e-07, 'epoch': 116.11}

 18%|█▊        | 10520/57600 [1:50:38<8:08:16,  1.61it/s]
 18%|█▊        | 10521/57600 [1:50:39<8:29:47,  1.54it/s]
 18%|█▊        | 10522/57600 [1:50:40<8:34:15,  1.53it/s]
 18%|█▊        | 10523/57600 [1:50:40<8:24:46,  1.55it/s]
 18%|█▊        | 10524/57600 [1:50:41<8:20:56,  1.57it/s]
 18%|█▊        | 10525/57600 [1:50:42<8:13:49,  1.59it/s]
 18%|█▊        | 10526/57600 [1:50:42<8:11:15,  1.60it/s]
 18%|█▊        | 10527/57600 [1:50:43<8:27:01,  1.55it/s]
 18%|█▊        | 10528/57600 [1:50:44<8:26:13,  1.55it/s]
 18%|█▊        | 10529/57600 [1:50:44<8:17:21,  1.58it/s]
 18%|█▊        | 10530/57600 [1:50:45<8:08:01,  1.61it/s]
 18%|█▊        | 10531/57600 [1:50:45<8:12:29,  1.59it/s]
 18%|█▊        | 10532/57600 [1:50:46<8:27:09,  1.55it/s]
 18%|█▊        | 10533/57600 [1:50:47<8:14:05,  1.59it/s]
 18%|█▊        | 10534/57600 [1:50:47<8:06:10,  1.61it/s]
 18%|█▊        | 10535/57600 [1:50:48<8:16:06,  1.58it/s]
 18%|█▊        | 10536/57600 [1:50:49<8:08:01,  1.61it/s]
 18%|█▊        | 10537/57600 [1:50:49<8:15:09,  1.58it/s]
 18%|█▊        | 10538/57600 [1:50:50<8:12:33,  1.59it/s]
 18%|█▊        | 10539/57600 [1:50:51<8:07:35,  1.61it/s]
 18%|█▊        | 10540/57600 [1:50:51<7:52:40,  1.66it/s]
                                                         
{'loss': 1.3469, 'learning_rate': 8.378745644599303e-07, 'epoch': 116.34}

 18%|█▊        | 10540/57600 [1:50:51<7:52:40,  1.66it/s]
 18%|█▊        | 10541/57600 [1:50:52<7:59:57,  1.63it/s]
 18%|█▊        | 10542/57600 [1:50:52<7:51:17,  1.66it/s]
 18%|█▊        | 10543/57600 [1:50:53<7:46:48,  1.68it/s]
 18%|█▊        | 10544/57600 [1:50:54<8:02:33,  1.63it/s]
 18%|█▊        | 10545/57600 [1:50:54<8:22:42,  1.56it/s]
 18%|█▊        | 10546/57600 [1:50:55<8:16:11,  1.58it/s]
 18%|█▊        | 10547/57600 [1:50:55<8:05:45,  1.61it/s]
 18%|█▊        | 10548/57600 [1:50:56<8:07:51,  1.61it/s]
 18%|█▊        | 10549/57600 [1:50:57<8:08:12,  1.61it/s]
 18%|█▊        | 10550/57600 [1:50:57<8:07:09,  1.61it/s]
 18%|█▊        | 10551/57600 [1:50:58<8:08:58,  1.60it/s]
 18%|█▊        | 10552/57600 [1:50:58<7:58:16,  1.64it/s]
 18%|█▊        | 10553/57600 [1:50:59<7:39:42,  1.71it/s]
 18%|█▊        | 10554/57600 [1:51:00<7:47:09,  1.68it/s]
 18%|█▊        | 10555/57600 [1:51:00<7:45:02,  1.69it/s]
 18%|█▊        | 10556/57600 [1:51:01<7:47:22,  1.68it/s]
 18%|█▊        | 10557/57600 [1:51:01<7:50:14,  1.67it/s]
 18%|█▊        | 10558/57600 [1:51:02<7:41:08,  1.70it/s]
 18%|█▊        | 10559/57600 [1:51:03<7:53:09,  1.66it/s]
 18%|█▊        | 10560/57600 [1:51:03<7:57:50,  1.64it/s]
                                                         
{'loss': 1.4008, 'learning_rate': 8.375609756097561e-07, 'epoch': 116.56}

 18%|█▊        | 10560/57600 [1:51:03<7:57:50,  1.64it/s]
 18%|█▊        | 10561/57600 [1:51:04<8:15:38,  1.58it/s]
 18%|█▊        | 10562/57600 [1:51:05<8:14:37,  1.58it/s]
 18%|█▊        | 10563/57600 [1:51:05<8:06:33,  1.61it/s]
 18%|█▊        | 10564/57600 [1:51:06<8:03:02,  1.62it/s]
 18%|█▊        | 10565/57600 [1:51:06<8:03:25,  1.62it/s]
 18%|█▊        | 10566/57600 [1:51:07<8:12:18,  1.59it/s]
 18%|█▊        | 10567/57600 [1:51:08<8:11:19,  1.60it/s]
 18%|█▊        | 10568/57600 [1:51:08<8:08:38,  1.60it/s]
 18%|█▊        | 10569/57600 [1:51:09<8:04:34,  1.62it/s]
 18%|█▊        | 10570/57600 [1:51:10<8:02:09,  1.63it/s]
 18%|█▊        | 10571/57600 [1:51:10<7:58:52,  1.64it/s]
 18%|█▊        | 10572/57600 [1:51:11<7:57:47,  1.64it/s]
 18%|█▊        | 10573/57600 [1:51:11<7:57:24,  1.64it/s]
 18%|█▊        | 10574/57600 [1:51:12<7:59:38,  1.63it/s]
 18%|█▊        | 10575/57600 [1:51:13<8:03:02,  1.62it/s]
 18%|█▊        | 10576/57600 [1:51:13<7:55:07,  1.65it/s]
 18%|█▊        | 10577/57600 [1:51:14<8:11:27,  1.59it/s]
 18%|█▊        | 10578/57600 [1:51:15<8:28:06,  1.54it/s]
 18%|█▊        | 10579/57600 [1:51:15<8:38:09,  1.51it/s]
 18%|█▊        | 10580/57600 [1:51:16<8:34:33,  1.52it/s]
                                                         
{'loss': 1.3757, 'learning_rate': 8.372473867595818e-07, 'epoch': 116.78}

 18%|█▊        | 10580/57600 [1:51:16<8:34:33,  1.52it/s]
 18%|█▊        | 10581/57600 [1:51:17<8:36:07,  1.52it/s]
 18%|█▊        | 10582/57600 [1:51:17<8:21:45,  1.56it/s]
 18%|█▊        | 10583/57600 [1:51:18<8:06:13,  1.61it/s]
 18%|█▊        | 10584/57600 [1:51:18<8:22:26,  1.56it/s]
 18%|█▊        | 10585/57600 [1:51:19<8:19:09,  1.57it/s]
 18%|█▊        | 10586/57600 [1:51:20<8:11:04,  1.60it/s]
 18%|█▊        | 10587/57600 [1:51:20<8:04:26,  1.62it/s]
 18%|█▊        | 10588/57600 [1:51:21<8:24:12,  1.55it/s]
 18%|█▊        | 10589/57600 [1:51:22<8:17:19,  1.58it/s]
 18%|█▊        | 10590/57600 [1:51:22<8:05:43,  1.61it/s]
 18%|█▊        | 10591/57600 [1:51:23<7:53:56,  1.65it/s]
 18%|█▊        | 10592/57600 [1:51:23<8:06:18,  1.61it/s]
 18%|█▊        | 10593/57600 [1:51:24<7:58:56,  1.64it/s]
 18%|█▊        | 10594/57600 [1:51:24<7:48:27,  1.67it/s]
 18%|█▊        | 10595/57600 [1:51:25<7:41:44,  1.70it/s]
 18%|█▊        | 10596/57600 [1:51:26<7:34:57,  1.72it/s]
 18%|█▊        | 10597/57600 [1:51:26<7:40:01,  1.70it/s]
 18%|█▊        | 10598/57600 [1:51:27<7:36:16,  1.72it/s]
 18%|█▊        | 10599/57600 [1:51:27<7:46:41,  1.68it/s]
 18%|█▊        | 10600/57600 [1:51:28<7:51:47,  1.66it/s]
                                                         
{'loss': 1.3792, 'learning_rate': 8.369337979094076e-07, 'epoch': 117.0}

 18%|█▊        | 10600/57600 [1:51:28<7:51:47,  1.66it/s]
 18%|█▊        | 10601/57600 [1:51:29<8:07:25,  1.61it/s]
 18%|█▊        | 10602/57600 [1:51:29<7:59:35,  1.63it/s]
 18%|█▊        | 10603/57600 [1:51:30<7:46:18,  1.68it/s]
 18%|█▊        | 10604/57600 [1:51:30<7:30:04,  1.74it/s]
 18%|█▊        | 10605/57600 [1:51:31<7:35:19,  1.72it/s]
 18%|█▊        | 10606/57600 [1:51:32<7:40:02,  1.70it/s]
 18%|█▊        | 10607/57600 [1:51:32<7:48:56,  1.67it/s]
 18%|█▊        | 10608/57600 [1:51:33<8:03:12,  1.62it/s]
 18%|█▊        | 10609/57600 [1:51:33<8:04:09,  1.62it/s]
 18%|█▊        | 10610/57600 [1:51:34<8:07:35,  1.61it/s]
 18%|█▊        | 10611/57600 [1:51:35<8:12:08,  1.59it/s]
 18%|█▊        | 10612/57600 [1:51:35<8:15:04,  1.58it/s]
 18%|█▊        | 10613/57600 [1:51:36<8:23:35,  1.56it/s]
 18%|█▊        | 10614/57600 [1:51:37<8:04:42,  1.62it/s]
 18%|█▊        | 10615/57600 [1:51:37<8:11:10,  1.59it/s]
 18%|█▊        | 10616/57600 [1:51:38<7:59:09,  1.63it/s]
 18%|█▊        | 10617/57600 [1:51:38<7:57:48,  1.64it/s]
 18%|█▊        | 10618/57600 [1:51:39<8:15:46,  1.58it/s]
 18%|█▊        | 10619/57600 [1:51:40<8:17:30,  1.57it/s]
 18%|█▊        | 10620/57600 [1:51:40<8:00:29,  1.63it/s]
                                                         
{'loss': 1.3422, 'learning_rate': 8.366202090592334e-07, 'epoch': 117.22}

 18%|█▊        | 10620/57600 [1:51:40<8:00:29,  1.63it/s]
 18%|█▊        | 10621/57600 [1:51:41<7:56:07,  1.64it/s]
 18%|█▊        | 10622/57600 [1:51:42<7:57:54,  1.64it/s]
 18%|█▊        | 10623/57600 [1:51:42<8:02:59,  1.62it/s]
 18%|█▊        | 10624/57600 [1:51:43<7:52:18,  1.66it/s]
 18%|█▊        | 10625/57600 [1:51:43<8:21:04,  1.56it/s]
 18%|█▊        | 10626/57600 [1:51:44<8:05:29,  1.61it/s]
 18%|█▊        | 10627/57600 [1:51:45<8:18:22,  1.57it/s]
 18%|█▊        | 10628/57600 [1:51:45<8:05:09,  1.61it/s]
 18%|█▊        | 10629/57600 [1:51:46<8:12:57,  1.59it/s]
 18%|█▊        | 10630/57600 [1:51:47<8:04:24,  1.62it/s]
 18%|█▊        | 10631/57600 [1:51:47<8:10:00,  1.60it/s]
 18%|█▊        | 10632/57600 [1:51:48<8:00:46,  1.63it/s]
 18%|█▊        | 10633/57600 [1:51:48<8:11:08,  1.59it/s]
 18%|█▊        | 10634/57600 [1:51:49<7:56:32,  1.64it/s]
 18%|█▊        | 10635/57600 [1:51:50<7:58:23,  1.64it/s]
 18%|█▊        | 10636/57600 [1:51:50<7:52:12,  1.66it/s]
 18%|█▊        | 10637/57600 [1:51:51<7:46:53,  1.68it/s]
 18%|█▊        | 10638/57600 [1:51:51<7:40:55,  1.70it/s]
 18%|█▊        | 10639/57600 [1:51:52<7:59:06,  1.63it/s]
 18%|█▊        | 10640/57600 [1:51:53<8:04:46,  1.61it/s]
                                                         
{'loss': 1.3876, 'learning_rate': 8.363066202090592e-07, 'epoch': 117.44}

 18%|█▊        | 10640/57600 [1:51:53<8:04:46,  1.61it/s]
 18%|█▊        | 10641/57600 [1:51:53<7:59:42,  1.63it/s]
 18%|█▊        | 10642/57600 [1:51:54<7:48:57,  1.67it/s]
 18%|█▊        | 10643/57600 [1:51:55<8:11:13,  1.59it/s]
 18%|█▊        | 10644/57600 [1:51:55<8:27:57,  1.54it/s]
 18%|█▊        | 10645/57600 [1:51:56<8:34:07,  1.52it/s]
 18%|█▊        | 10646/57600 [1:51:57<8:37:21,  1.51it/s]
 18%|█▊        | 10647/57600 [1:51:57<8:36:37,  1.51it/s]
 18%|█▊        | 10648/57600 [1:51:58<8:38:08,  1.51it/s]
 18%|█▊        | 10649/57600 [1:51:58<8:17:41,  1.57it/s]
 18%|█▊        | 10650/57600 [1:51:59<8:18:48,  1.57it/s]
 18%|█▊        | 10651/57600 [1:52:00<8:01:31,  1.63it/s]
 18%|█▊        | 10652/57600 [1:52:00<7:51:31,  1.66it/s]
 18%|█▊        | 10653/57600 [1:52:01<7:48:29,  1.67it/s]
 18%|█▊        | 10654/57600 [1:52:02<8:05:41,  1.61it/s]
 18%|█▊        | 10655/57600 [1:52:02<7:56:14,  1.64it/s]
 18%|█▊        | 10656/57600 [1:52:03<8:05:17,  1.61it/s]
 19%|█▊        | 10657/57600 [1:52:03<8:04:18,  1.62it/s]
 19%|█▊        | 10658/57600 [1:52:04<7:50:54,  1.66it/s]
 19%|█▊        | 10659/57600 [1:52:05<7:57:43,  1.64it/s]
 19%|█▊        | 10660/57600 [1:52:05<7:43:38,  1.69it/s]
                                                         
{'loss': 1.3519, 'learning_rate': 8.359930313588849e-07, 'epoch': 117.66}

 19%|█▊        | 10660/57600 [1:52:05<7:43:38,  1.69it/s]
 19%|█▊        | 10661/57600 [1:52:06<7:50:37,  1.66it/s]
 19%|█▊        | 10662/57600 [1:52:06<7:41:25,  1.70it/s]
 19%|█▊        | 10663/57600 [1:52:07<7:55:01,  1.65it/s]
 19%|█▊        | 10664/57600 [1:52:08<7:45:07,  1.68it/s]
 19%|█▊        | 10665/57600 [1:52:08<8:00:28,  1.63it/s]
 19%|█▊        | 10666/57600 [1:52:09<8:05:57,  1.61it/s]
 19%|█▊        | 10667/57600 [1:52:09<8:17:15,  1.57it/s]
 19%|█▊        | 10668/57600 [1:52:10<8:15:23,  1.58it/s]
 19%|█▊        | 10669/57600 [1:52:11<7:58:25,  1.63it/s]
 19%|█▊        | 10670/57600 [1:52:11<8:09:37,  1.60it/s]
 19%|█▊        | 10671/57600 [1:52:12<8:00:31,  1.63it/s]
 19%|█▊        | 10672/57600 [1:52:13<8:00:52,  1.63it/s]
 19%|█▊        | 10673/57600 [1:52:13<8:03:47,  1.62it/s]
 19%|█▊        | 10674/57600 [1:52:14<8:01:24,  1.62it/s]
 19%|█▊        | 10675/57600 [1:52:14<7:58:17,  1.64it/s]
 19%|█▊        | 10676/57600 [1:52:15<8:27:08,  1.54it/s]
 19%|█▊        | 10677/57600 [1:52:16<8:27:42,  1.54it/s]
 19%|█▊        | 10678/57600 [1:52:16<8:27:34,  1.54it/s]
 19%|█▊        | 10679/57600 [1:52:17<8:16:03,  1.58it/s]
 19%|█▊        | 10680/57600 [1:52:18<8:02:30,  1.62it/s]
                                                         
{'loss': 1.3268, 'learning_rate': 8.356794425087108e-07, 'epoch': 117.88}

 19%|█▊        | 10680/57600 [1:52:18<8:02:30,  1.62it/s]
 19%|█▊        | 10681/57600 [1:52:18<8:06:58,  1.61it/s]
 19%|█▊        | 10682/57600 [1:52:19<7:58:46,  1.63it/s]
 19%|█▊        | 10683/57600 [1:52:19<7:48:39,  1.67it/s]
 19%|█▊        | 10684/57600 [1:52:20<7:33:37,  1.72it/s]
 19%|█▊        | 10685/57600 [1:52:20<7:24:50,  1.76it/s]
 19%|█▊        | 10686/57600 [1:52:21<7:39:01,  1.70it/s]
 19%|█▊        | 10687/57600 [1:52:22<8:01:28,  1.62it/s]
 19%|█▊        | 10688/57600 [1:52:22<8:02:06,  1.62it/s]
 19%|█▊        | 10689/57600 [1:52:23<7:47:38,  1.67it/s]
 19%|█▊        | 10690/57600 [1:52:24<7:40:14,  1.70it/s]
 19%|█▊        | 10691/57600 [1:52:24<7:52:15,  1.66it/s]
 19%|█▊        | 10692/57600 [1:52:25<7:42:23,  1.69it/s]
 19%|█▊        | 10693/57600 [1:52:25<7:52:22,  1.65it/s]
 19%|█▊        | 10694/57600 [1:52:26<7:50:33,  1.66it/s]
 19%|█▊        | 10695/57600 [1:52:26<7:40:52,  1.70it/s]
 19%|█▊        | 10696/57600 [1:52:27<8:05:58,  1.61it/s]
 19%|█▊        | 10697/57600 [1:52:28<7:59:41,  1.63it/s]
 19%|█▊        | 10698/57600 [1:52:28<7:49:52,  1.66it/s]
 19%|█▊        | 10699/57600 [1:52:29<7:46:39,  1.68it/s]
 19%|█▊        | 10700/57600 [1:52:30<8:19:20,  1.57it/s]
                                                         
{'loss': 1.4245, 'learning_rate': 8.353658536585366e-07, 'epoch': 118.1}

 19%|█▊        | 10700/57600 [1:52:30<8:19:20,  1.57it/s]
 19%|█▊        | 10701/57600 [1:52:30<8:16:40,  1.57it/s]
 19%|█▊        | 10702/57600 [1:52:31<8:07:34,  1.60it/s]
 19%|█▊        | 10703/57600 [1:52:31<7:52:09,  1.66it/s]
 19%|█▊        | 10704/57600 [1:52:32<7:53:58,  1.65it/s]
 19%|█▊        | 10705/57600 [1:52:33<7:56:44,  1.64it/s]
 19%|█▊        | 10706/57600 [1:52:33<7:58:09,  1.63it/s]
 19%|█▊        | 10707/57600 [1:52:34<7:52:29,  1.65it/s]
 19%|█▊        | 10708/57600 [1:52:35<7:57:28,  1.64it/s]
 19%|█▊        | 10709/57600 [1:52:35<8:01:44,  1.62it/s]
 19%|█▊        | 10710/57600 [1:52:36<8:02:56,  1.62it/s]
 19%|█▊        | 10711/57600 [1:52:36<7:58:33,  1.63it/s]
 19%|█▊        | 10712/57600 [1:52:37<8:05:59,  1.61it/s]
 19%|█▊        | 10713/57600 [1:52:38<8:09:21,  1.60it/s]
 19%|█▊        | 10714/57600 [1:52:38<8:14:33,  1.58it/s]
 19%|█▊        | 10715/57600 [1:52:39<8:06:40,  1.61it/s]
 19%|█▊        | 10716/57600 [1:52:39<8:00:24,  1.63it/s]
 19%|█▊        | 10717/57600 [1:52:40<7:49:45,  1.66it/s]
 19%|█▊        | 10718/57600 [1:52:41<8:04:53,  1.61it/s]
 19%|█▊        | 10719/57600 [1:52:41<7:55:03,  1.64it/s]
 19%|█▊        | 10720/57600 [1:52:42<8:14:50,  1.58it/s]
                                                         
{'loss': 1.3755, 'learning_rate': 8.350522648083623e-07, 'epoch': 118.32}

 19%|█▊        | 10720/57600 [1:52:42<8:14:50,  1.58it/s]
 19%|█▊        | 10721/57600 [1:52:43<8:03:46,  1.62it/s]
 19%|█▊        | 10722/57600 [1:52:43<8:10:06,  1.59it/s]
 19%|█▊        | 10723/57600 [1:52:44<8:09:33,  1.60it/s]
 19%|█▊        | 10724/57600 [1:52:44<8:11:16,  1.59it/s]
 19%|█▊        | 10725/57600 [1:52:45<8:11:19,  1.59it/s]
 19%|█▊        | 10726/57600 [1:52:46<8:07:17,  1.60it/s]
 19%|█▊        | 10727/57600 [1:52:46<8:31:17,  1.53it/s]
 19%|█▊        | 10728/57600 [1:52:47<8:35:00,  1.52it/s]
 19%|█▊        | 10729/57600 [1:52:48<8:26:31,  1.54it/s]
 19%|█▊        | 10730/57600 [1:52:48<8:27:25,  1.54it/s]
 19%|█▊        | 10731/57600 [1:52:49<8:10:37,  1.59it/s]
 19%|█▊        | 10732/57600 [1:52:50<8:03:07,  1.62it/s]
 19%|█▊        | 10733/57600 [1:52:50<8:01:22,  1.62it/s]
 19%|█▊        | 10734/57600 [1:52:51<8:01:30,  1.62it/s]
 19%|█▊        | 10735/57600 [1:52:51<8:04:51,  1.61it/s]
 19%|█▊        | 10736/57600 [1:52:52<8:05:12,  1.61it/s]
 19%|█▊        | 10737/57600 [1:52:53<8:05:36,  1.61it/s]
 19%|█▊        | 10738/57600 [1:52:53<8:03:27,  1.62it/s]
 19%|█▊        | 10739/57600 [1:52:54<8:10:20,  1.59it/s]
 19%|█▊        | 10740/57600 [1:52:55<8:13:44,  1.58it/s]
                                                         
{'loss': 1.3318, 'learning_rate': 8.347386759581881e-07, 'epoch': 118.54}

 19%|█▊        | 10740/57600 [1:52:55<8:13:44,  1.58it/s]
 19%|█▊        | 10741/57600 [1:52:55<8:04:46,  1.61it/s]
 19%|█▊        | 10742/57600 [1:52:56<8:09:32,  1.60it/s]
 19%|█▊        | 10743/57600 [1:52:57<8:28:28,  1.54it/s]
 19%|█▊        | 10744/57600 [1:52:57<8:32:22,  1.52it/s]
 19%|█▊        | 10745/57600 [1:52:58<8:15:25,  1.58it/s]
 19%|█▊        | 10746/57600 [1:52:58<8:02:42,  1.62it/s]
 19%|█▊        | 10747/57600 [1:52:59<7:54:04,  1.65it/s]
 19%|█▊        | 10748/57600 [1:53:00<8:23:56,  1.55it/s]
 19%|█▊        | 10749/57600 [1:53:00<8:19:00,  1.56it/s]
 19%|█▊        | 10750/57600 [1:53:01<8:13:03,  1.58it/s]
 19%|█▊        | 10751/57600 [1:53:02<8:04:30,  1.61it/s]
 19%|█▊        | 10752/57600 [1:53:02<7:56:42,  1.64it/s]
 19%|█▊        | 10753/57600 [1:53:03<7:46:29,  1.67it/s]
 19%|█▊        | 10754/57600 [1:53:03<7:47:14,  1.67it/s]
 19%|█▊        | 10755/57600 [1:53:04<7:47:22,  1.67it/s]
 19%|█▊        | 10756/57600 [1:53:04<7:52:28,  1.65it/s]
 19%|█▊        | 10757/57600 [1:53:05<8:25:59,  1.54it/s]
 19%|█▊        | 10758/57600 [1:53:06<8:41:08,  1.50it/s]
 19%|█▊        | 10759/57600 [1:53:07<8:31:21,  1.53it/s]
 19%|█▊        | 10760/57600 [1:53:07<8:45:33,  1.49it/s]
                                                         
{'loss': 1.3395, 'learning_rate': 8.344250871080139e-07, 'epoch': 118.76}

 19%|█▊        | 10760/57600 [1:53:07<8:45:33,  1.49it/s]
 19%|█▊        | 10761/57600 [1:53:08<8:28:08,  1.54it/s]
 19%|█▊        | 10762/57600 [1:53:08<8:14:40,  1.58it/s]
 19%|█▊        | 10763/57600 [1:53:09<8:07:54,  1.60it/s]
 19%|█▊        | 10764/57600 [1:53:10<7:56:05,  1.64it/s]
 19%|█▊        | 10765/57600 [1:53:10<7:52:30,  1.65it/s]
 19%|█▊        | 10766/57600 [1:53:11<7:47:52,  1.67it/s]
 19%|█▊        | 10767/57600 [1:53:11<7:46:58,  1.67it/s]
 19%|█▊        | 10768/57600 [1:53:12<7:41:33,  1.69it/s]
 19%|█▊        | 10769/57600 [1:53:13<7:45:19,  1.68it/s]
 19%|█▊        | 10770/57600 [1:53:13<7:42:26,  1.69it/s]
 19%|█▊        | 10771/57600 [1:53:14<7:36:19,  1.71it/s]
 19%|█▊        | 10772/57600 [1:53:14<7:43:24,  1.68it/s]
 19%|█▊        | 10773/57600 [1:53:15<7:45:23,  1.68it/s]
 19%|█▊        | 10774/57600 [1:53:16<7:42:46,  1.69it/s]
 19%|█▊        | 10775/57600 [1:53:16<7:49:17,  1.66it/s]
 19%|█▊        | 10776/57600 [1:53:17<7:46:18,  1.67it/s]
 19%|█▊        | 10777/57600 [1:53:17<7:45:48,  1.68it/s]
 19%|█▊        | 10778/57600 [1:53:18<7:57:05,  1.64it/s]
 19%|█▊        | 10779/57600 [1:53:19<7:54:39,  1.64it/s]
 19%|█▊        | 10780/57600 [1:53:19<7:48:01,  1.67it/s]
                                                         
{'loss': 1.407, 'learning_rate': 8.341114982578397e-07, 'epoch': 118.98}

 19%|█▊        | 10780/57600 [1:53:19<7:48:01,  1.67it/s]
 19%|█▊        | 10781/57600 [1:53:20<7:39:10,  1.70it/s]
 19%|█▊        | 10782/57600 [1:53:20<8:00:07,  1.63it/s]
 19%|█▊        | 10783/57600 [1:53:21<7:45:05,  1.68it/s]
 19%|█▊        | 10784/57600 [1:53:22<7:44:50,  1.68it/s]
 19%|█▊        | 10785/57600 [1:53:22<7:43:08,  1.68it/s]
 19%|█▊        | 10786/57600 [1:53:23<7:43:11,  1.68it/s]
 19%|█▊        | 10787/57600 [1:53:23<7:43:22,  1.68it/s]
 19%|█▊        | 10788/57600 [1:53:24<7:56:51,  1.64it/s]
 19%|█▊        | 10789/57600 [1:53:25<8:08:45,  1.60it/s]
 19%|█▊        | 10790/57600 [1:53:25<8:04:55,  1.61it/s]
 19%|█▊        | 10791/57600 [1:53:26<8:09:21,  1.59it/s]
 19%|█▊        | 10792/57600 [1:53:27<8:10:13,  1.59it/s]
 19%|█▊        | 10793/57600 [1:53:27<8:03:25,  1.61it/s]
 19%|█▊        | 10794/57600 [1:53:28<8:11:04,  1.59it/s]
 19%|█▊        | 10795/57600 [1:53:28<8:08:50,  1.60it/s]
 19%|█▊        | 10796/57600 [1:53:29<8:10:46,  1.59it/s]
 19%|█▊        | 10797/57600 [1:53:30<8:06:03,  1.60it/s]
 19%|█▊        | 10798/57600 [1:53:30<7:58:40,  1.63it/s]
 19%|█▊        | 10799/57600 [1:53:31<8:04:03,  1.61it/s]
 19%|█▉        | 10800/57600 [1:53:32<7:59:55,  1.63it/s]
                                                         
{'loss': 1.3621, 'learning_rate': 8.337979094076654e-07, 'epoch': 119.21}

 19%|█▉        | 10800/57600 [1:53:32<7:59:55,  1.63it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.06it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  6.60it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.39it/s]

100%|██████████| 6/6 [00:01<00:00,  3.28it/s]{'score': 49.1209857249113, 'counts': [148, 101, 71, 50], 'totals': [222, 192, 162, 132], 'precisions': [66.66666666666667, 52.604166666666664, 43.82716049382716, 37.878787878787875], 'bp': 1.0, 'sys_len': 222, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 2.0037317276000977, 'eval_bleu': 49.121, 'eval_gen_len': 8.8, 'eval_runtime': 3.2416, 'eval_samples_per_second': 9.255, 'eval_steps_per_second': 1.851, 'epoch': 119.21}

 19%|█▉        | 10800/57600 [1:53:35<7:59:55,  1.63it/s]

100%|██████████| 6/6 [00:02<00:00,  3.28it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 08:47:48,097 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 19%|█▉        | 10801/57600 [1:53:59<112:54:18,  8.69s/it]
 19%|█▉        | 10802/57600 [1:54:00<81:39:28,  6.28s/it] 
 19%|█▉        | 10803/57600 [1:54:00<59:28:03,  4.57s/it]
 19%|█▉        | 10804/57600 [1:54:01<44:00:01,  3.38s/it]
 19%|█▉        | 10805/57600 [1:54:02<33:14:10,  2.56s/it]
 19%|█▉        | 10806/57600 [1:54:02<25:50:59,  1.99s/it]
 19%|█▉        | 10807/57600 [1:54:03<20:46:27,  1.60s/it]
 19%|█▉        | 10808/57600 [1:54:04<16:59:46,  1.31s/it]
 19%|█▉        | 10809/57600 [1:54:04<14:21:26,  1.10s/it]
 19%|█▉        | 10810/57600 [1:54:05<12:19:14,  1.05it/s]
 19%|█▉        | 10811/57600 [1:54:05<11:15:26,  1.15it/s]
 19%|█▉        | 10812/57600 [1:54:06<10:34:25,  1.23it/s]
 19%|█▉        | 10813/57600 [1:54:07<9:48:14,  1.33it/s] 
 19%|█▉        | 10814/57600 [1:54:07<9:18:17,  1.40it/s]
 19%|█▉        | 10815/57600 [1:54:08<9:04:28,  1.43it/s]
 19%|█▉        | 10816/57600 [1:54:09<8:51:11,  1.47it/s]
 19%|█▉        | 10817/57600 [1:54:09<8:39:51,  1.50it/s]
 19%|█▉        | 10818/57600 [1:54:10<8:33:09,  1.52it/s]
 19%|█▉        | 10819/57600 [1:54:11<8:21:00,  1.56it/s]
 19%|█▉        | 10820/57600 [1:54:11<8:21:19,  1.56it/s]
                                                         
{'loss': 1.3468, 'learning_rate': 8.334843205574913e-07, 'epoch': 119.43}

 19%|█▉        | 10820/57600 [1:54:11<8:21:19,  1.56it/s]
 19%|█▉        | 10821/57600 [1:54:12<8:46:30,  1.48it/s]
 19%|█▉        | 10822/57600 [1:54:13<8:57:00,  1.45it/s]
 19%|█▉        | 10823/57600 [1:54:13<8:52:51,  1.46it/s]
 19%|█▉        | 10824/57600 [1:54:14<8:49:36,  1.47it/s]
 19%|█▉        | 10825/57600 [1:54:15<8:32:04,  1.52it/s]
 19%|█▉        | 10826/57600 [1:54:15<8:58:36,  1.45it/s]
 19%|█▉        | 10827/57600 [1:54:16<8:40:58,  1.50it/s]
 19%|█▉        | 10828/57600 [1:54:17<8:34:45,  1.51it/s]
 19%|█▉        | 10829/57600 [1:54:17<8:32:17,  1.52it/s]
 19%|█▉        | 10830/57600 [1:54:18<8:36:23,  1.51it/s]
 19%|█▉        | 10831/57600 [1:54:19<8:32:31,  1.52it/s]
 19%|█▉        | 10832/57600 [1:54:19<8:34:54,  1.51it/s]
 19%|█▉        | 10833/57600 [1:54:20<8:43:29,  1.49it/s]
 19%|█▉        | 10834/57600 [1:54:21<8:28:12,  1.53it/s]
 19%|█▉        | 10835/57600 [1:54:21<8:19:51,  1.56it/s]
 19%|█▉        | 10836/57600 [1:54:22<8:24:06,  1.55it/s]
 19%|█▉        | 10837/57600 [1:54:22<8:19:59,  1.56it/s]
 19%|█▉        | 10838/57600 [1:54:23<8:13:57,  1.58it/s]
 19%|█▉        | 10839/57600 [1:54:24<8:15:12,  1.57it/s]
 19%|█▉        | 10840/57600 [1:54:24<8:04:08,  1.61it/s]
                                                         
{'loss': 1.3168, 'learning_rate': 8.331707317073171e-07, 'epoch': 119.65}

 19%|█▉        | 10840/57600 [1:54:24<8:04:08,  1.61it/s]
 19%|█▉        | 10841/57600 [1:54:25<8:16:05,  1.57it/s]
 19%|█▉        | 10842/57600 [1:54:26<8:12:52,  1.58it/s]
 19%|█▉        | 10843/57600 [1:54:26<8:22:16,  1.55it/s]
 19%|█▉        | 10844/57600 [1:54:27<8:28:02,  1.53it/s]
 19%|█▉        | 10845/57600 [1:54:28<8:16:01,  1.57it/s]
 19%|█▉        | 10846/57600 [1:54:28<8:09:58,  1.59it/s]
 19%|█▉        | 10847/57600 [1:54:29<8:29:36,  1.53it/s]
 19%|█▉        | 10848/57600 [1:54:29<8:29:44,  1.53it/s]
 19%|█▉        | 10849/57600 [1:54:30<8:11:57,  1.58it/s]
 19%|█▉        | 10850/57600 [1:54:31<7:58:34,  1.63it/s]
 19%|█▉        | 10851/57600 [1:54:31<7:49:39,  1.66it/s]
 19%|█▉        | 10852/57600 [1:54:32<8:05:29,  1.60it/s]
 19%|█▉        | 10853/57600 [1:54:33<8:12:26,  1.58it/s]
 19%|█▉        | 10854/57600 [1:54:33<8:18:09,  1.56it/s]
 19%|█▉        | 10855/57600 [1:54:34<8:38:13,  1.50it/s]
 19%|█▉        | 10856/57600 [1:54:35<8:37:22,  1.51it/s]
 19%|█▉        | 10857/57600 [1:54:35<8:27:51,  1.53it/s]
 19%|█▉        | 10858/57600 [1:54:36<8:22:44,  1.55it/s]
 19%|█▉        | 10859/57600 [1:54:37<8:38:49,  1.50it/s]
 19%|█▉        | 10860/57600 [1:54:37<8:32:42,  1.52it/s]
                                                         
{'loss': 1.3797, 'learning_rate': 8.328571428571428e-07, 'epoch': 119.87}

 19%|█▉        | 10860/57600 [1:54:37<8:32:42,  1.52it/s]
 19%|█▉        | 10861/57600 [1:54:38<8:40:01,  1.50it/s]
 19%|█▉        | 10862/57600 [1:54:39<8:34:03,  1.52it/s]
 19%|█▉        | 10863/57600 [1:54:39<8:25:25,  1.54it/s]
 19%|█▉        | 10864/57600 [1:54:40<8:25:39,  1.54it/s]
 19%|█▉        | 10865/57600 [1:54:40<8:25:09,  1.54it/s]
 19%|█▉        | 10866/57600 [1:54:41<8:13:07,  1.58it/s]
 19%|█▉        | 10867/57600 [1:54:42<8:09:20,  1.59it/s]
 19%|█▉        | 10868/57600 [1:54:42<8:07:58,  1.60it/s]
 19%|█▉        | 10869/57600 [1:54:43<8:11:57,  1.58it/s]
 19%|█▉        | 10870/57600 [1:54:44<8:07:26,  1.60it/s]
 19%|█▉        | 10871/57600 [1:54:44<8:13:41,  1.58it/s]
 19%|█▉        | 10872/57600 [1:54:45<8:09:03,  1.59it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 19%|█▉        | 10873/57600 [1:54:45<8:18:53,  1.56it/s]
 19%|█▉        | 10874/57600 [1:54:46<8:19:27,  1.56it/s]
 19%|█▉        | 10875/57600 [1:54:47<8:19:42,  1.56it/s]
 19%|█▉        | 10876/57600 [1:54:47<8:02:41,  1.61it/s]
 19%|█▉        | 10877/57600 [1:54:48<7:55:32,  1.64it/s]
 19%|█▉        | 10878/57600 [1:54:49<8:04:31,  1.61it/s]
 19%|█▉        | 10879/57600 [1:54:49<8:08:47,  1.59it/s]
 19%|█▉        | 10880/57600 [1:54:50<7:53:50,  1.64it/s]
                                                         
{'loss': 1.3921, 'learning_rate': 8.325435540069686e-07, 'epoch': 120.09}

 19%|█▉        | 10880/57600 [1:54:50<7:53:50,  1.64it/s]
 19%|█▉        | 10881/57600 [1:54:50<7:56:33,  1.63it/s]
 19%|█▉        | 10882/57600 [1:54:51<7:54:31,  1.64it/s]
 19%|█▉        | 10883/57600 [1:54:52<8:13:29,  1.58it/s]
 19%|█▉        | 10884/57600 [1:54:52<8:27:31,  1.53it/s]
 19%|█▉        | 10885/57600 [1:54:53<8:36:54,  1.51it/s]
 19%|█▉        | 10886/57600 [1:54:54<8:36:44,  1.51it/s]
 19%|█▉        | 10887/57600 [1:54:54<8:19:18,  1.56it/s]
 19%|█▉        | 10888/57600 [1:54:55<8:17:27,  1.57it/s]
 19%|█▉        | 10889/57600 [1:54:56<8:17:52,  1.56it/s]
 19%|█▉        | 10890/57600 [1:54:56<8:21:27,  1.55it/s]
 19%|█▉        | 10891/57600 [1:54:57<9:00:44,  1.44it/s]
 19%|█▉        | 10892/57600 [1:54:58<9:08:49,  1.42it/s]
 19%|█▉        | 10893/57600 [1:54:58<8:46:58,  1.48it/s]
 19%|█▉        | 10894/57600 [1:54:59<8:46:03,  1.48it/s]
 19%|█▉        | 10895/57600 [1:55:00<8:37:30,  1.50it/s]
 19%|█▉        | 10896/57600 [1:55:00<8:39:45,  1.50it/s]
 19%|█▉        | 10897/57600 [1:55:01<8:31:06,  1.52it/s]
 19%|█▉        | 10898/57600 [1:55:02<8:24:49,  1.54it/s]
 19%|█▉        | 10899/57600 [1:55:02<8:14:51,  1.57it/s]
 19%|█▉        | 10900/57600 [1:55:03<8:04:01,  1.61it/s]
                                                         
{'loss': 1.3714, 'learning_rate': 8.322299651567943e-07, 'epoch': 120.31}

 19%|█▉        | 10900/57600 [1:55:03<8:04:01,  1.61it/s]
 19%|█▉        | 10901/57600 [1:55:03<7:55:52,  1.64it/s]
 19%|█▉        | 10902/57600 [1:55:04<8:10:15,  1.59it/s]
 19%|█▉        | 10903/57600 [1:55:05<8:10:50,  1.59it/s]
 19%|█▉        | 10904/57600 [1:55:05<8:25:27,  1.54it/s]
 19%|█▉        | 10905/57600 [1:55:06<8:22:58,  1.55it/s]
 19%|█▉        | 10906/57600 [1:55:07<8:05:26,  1.60it/s]
 19%|█▉        | 10907/57600 [1:55:07<8:09:05,  1.59it/s]
 19%|█▉        | 10908/57600 [1:55:08<8:22:11,  1.55it/s]
 19%|█▉        | 10909/57600 [1:55:09<8:17:04,  1.57it/s]
 19%|█▉        | 10910/57600 [1:55:09<7:56:55,  1.63it/s]
 19%|█▉        | 10911/57600 [1:55:10<8:10:19,  1.59it/s]
 19%|█▉        | 10912/57600 [1:55:10<8:03:31,  1.61it/s]
 19%|█▉        | 10913/57600 [1:55:11<8:05:25,  1.60it/s]
 19%|█▉        | 10914/57600 [1:55:12<8:06:14,  1.60it/s]
 19%|█▉        | 10915/57600 [1:55:12<8:21:34,  1.55it/s]
 19%|█▉        | 10916/57600 [1:55:13<8:30:22,  1.52it/s]
 19%|█▉        | 10917/57600 [1:55:14<8:13:28,  1.58it/s]
 19%|█▉        | 10918/57600 [1:55:14<8:18:16,  1.56it/s]
 19%|█▉        | 10919/57600 [1:55:15<8:01:45,  1.61it/s]
 19%|█▉        | 10920/57600 [1:55:15<7:54:26,  1.64it/s]
                                                         
{'loss': 1.3932, 'learning_rate': 8.319163763066202e-07, 'epoch': 120.53}

 19%|█▉        | 10920/57600 [1:55:15<7:54:26,  1.64it/s]
 19%|█▉        | 10921/57600 [1:55:16<7:58:15,  1.63it/s]
 19%|█▉        | 10922/57600 [1:55:17<8:04:27,  1.61it/s]
 19%|█▉        | 10923/57600 [1:55:17<8:14:22,  1.57it/s]
 19%|█▉        | 10924/57600 [1:55:18<8:29:26,  1.53it/s]
 19%|█▉        | 10925/57600 [1:55:19<8:34:35,  1.51it/s]
 19%|█▉        | 10926/57600 [1:55:19<8:24:57,  1.54it/s]
 19%|█▉        | 10927/57600 [1:55:20<8:14:24,  1.57it/s]
 19%|█▉        | 10928/57600 [1:55:21<8:11:49,  1.58it/s]
 19%|█▉        | 10929/57600 [1:55:21<8:23:34,  1.54it/s]
 19%|█▉        | 10930/57600 [1:55:22<8:24:31,  1.54it/s]
 19%|█▉        | 10931/57600 [1:55:23<8:23:57,  1.54it/s]
 19%|█▉        | 10932/57600 [1:55:23<8:06:41,  1.60it/s]
 19%|█▉        | 10933/57600 [1:55:24<8:40:11,  1.50it/s]
 19%|█▉        | 10934/57600 [1:55:25<8:39:52,  1.50it/s]
 19%|█▉        | 10935/57600 [1:55:25<8:52:58,  1.46it/s]
 19%|█▉        | 10936/57600 [1:55:26<8:45:45,  1.48it/s]
 19%|█▉        | 10937/57600 [1:55:27<8:29:33,  1.53it/s]
 19%|█▉        | 10938/57600 [1:55:27<8:49:07,  1.47it/s]
 19%|█▉        | 10939/57600 [1:55:28<8:45:54,  1.48it/s]
 19%|█▉        | 10940/57600 [1:55:29<8:29:49,  1.53it/s]
                                                         
{'loss': 1.361, 'learning_rate': 8.316027874564459e-07, 'epoch': 120.75}

 19%|█▉        | 10940/57600 [1:55:29<8:29:49,  1.53it/s]
 19%|█▉        | 10941/57600 [1:55:29<8:27:07,  1.53it/s]
 19%|█▉        | 10942/57600 [1:55:30<8:14:12,  1.57it/s]
 19%|█▉        | 10943/57600 [1:55:30<8:19:26,  1.56it/s]
 19%|█▉        | 10944/57600 [1:55:31<8:06:53,  1.60it/s]
 19%|█▉        | 10945/57600 [1:55:32<8:18:23,  1.56it/s]
 19%|█▉        | 10946/57600 [1:55:32<8:22:32,  1.55it/s]
 19%|█▉        | 10947/57600 [1:55:33<8:13:34,  1.58it/s]
 19%|█▉        | 10948/57600 [1:55:34<8:25:46,  1.54it/s]
 19%|█▉        | 10949/57600 [1:55:34<8:25:45,  1.54it/s]
 19%|█▉        | 10950/57600 [1:55:35<8:30:36,  1.52it/s]
 19%|█▉        | 10951/57600 [1:55:36<8:23:11,  1.55it/s]
 19%|█▉        | 10952/57600 [1:55:36<8:25:46,  1.54it/s]
 19%|█▉        | 10953/57600 [1:55:37<8:30:42,  1.52it/s]
 19%|█▉        | 10954/57600 [1:55:38<8:04:02,  1.61it/s]
 19%|█▉        | 10955/57600 [1:55:38<8:04:37,  1.60it/s]
 19%|█▉        | 10956/57600 [1:55:39<8:13:09,  1.58it/s]
 19%|█▉        | 10957/57600 [1:55:39<8:12:03,  1.58it/s]
 19%|█▉        | 10958/57600 [1:55:40<8:17:32,  1.56it/s]
 19%|█▉        | 10959/57600 [1:55:41<8:28:13,  1.53it/s]
 19%|█▉        | 10960/57600 [1:55:41<8:30:55,  1.52it/s]
                                                         
{'loss': 1.3852, 'learning_rate': 8.312891986062718e-07, 'epoch': 120.97}

 19%|█▉        | 10960/57600 [1:55:41<8:30:55,  1.52it/s]
 19%|█▉        | 10961/57600 [1:55:42<8:29:17,  1.53it/s]
 19%|█▉        | 10962/57600 [1:55:43<8:35:03,  1.51it/s]
 19%|█▉        | 10963/57600 [1:55:44<8:54:26,  1.45it/s]
 19%|█▉        | 10964/57600 [1:55:44<8:36:03,  1.51it/s]
 19%|█▉        | 10965/57600 [1:55:45<8:23:52,  1.54it/s]
 19%|█▉        | 10966/57600 [1:55:45<8:34:08,  1.51it/s]
 19%|█▉        | 10967/57600 [1:55:46<8:35:33,  1.51it/s]
 19%|█▉        | 10968/57600 [1:55:47<8:15:48,  1.57it/s]
 19%|█▉        | 10969/57600 [1:55:47<8:08:06,  1.59it/s]
 19%|█▉        | 10970/57600 [1:55:48<7:56:00,  1.63it/s]
 19%|█▉        | 10971/57600 [1:55:48<7:57:48,  1.63it/s]
 19%|█▉        | 10972/57600 [1:55:49<8:24:37,  1.54it/s]
 19%|█▉        | 10973/57600 [1:55:50<8:10:44,  1.58it/s]
 19%|█▉        | 10974/57600 [1:55:50<8:05:38,  1.60it/s]
 19%|█▉        | 10975/57600 [1:55:51<8:09:30,  1.59it/s]
 19%|█▉        | 10976/57600 [1:55:52<8:32:03,  1.52it/s]
 19%|█▉        | 10977/57600 [1:55:53<8:51:15,  1.46it/s]
 19%|█▉        | 10978/57600 [1:55:53<8:40:11,  1.49it/s]
 19%|█▉        | 10979/57600 [1:55:54<8:32:13,  1.52it/s]
 19%|█▉        | 10980/57600 [1:55:54<8:34:53,  1.51it/s]
                                                         
{'loss': 1.3572, 'learning_rate': 8.309756097560976e-07, 'epoch': 121.19}

 19%|█▉        | 10980/57600 [1:55:54<8:34:53,  1.51it/s]
 19%|█▉        | 10981/57600 [1:55:55<8:50:38,  1.46it/s]
 19%|█▉        | 10982/57600 [1:55:56<9:12:27,  1.41it/s]
 19%|█▉        | 10983/57600 [1:55:57<8:49:03,  1.47it/s]
 19%|█▉        | 10984/57600 [1:55:57<8:47:43,  1.47it/s]
 19%|█▉        | 10985/57600 [1:55:58<8:46:22,  1.48it/s]
 19%|█▉        | 10986/57600 [1:55:59<8:45:06,  1.48it/s]
 19%|█▉        | 10987/57600 [1:55:59<8:45:54,  1.48it/s]
 19%|█▉        | 10988/57600 [1:56:00<8:45:59,  1.48it/s]
 19%|█▉        | 10989/57600 [1:56:01<8:34:31,  1.51it/s]
 19%|█▉        | 10990/57600 [1:56:01<8:29:24,  1.52it/s]
 19%|█▉        | 10991/57600 [1:56:02<8:53:25,  1.46it/s]
 19%|█▉        | 10992/57600 [1:56:03<8:35:30,  1.51it/s]
 19%|█▉        | 10993/57600 [1:56:03<8:34:33,  1.51it/s]
 19%|█▉        | 10994/57600 [1:56:04<8:31:52,  1.52it/s]
 19%|█▉        | 10995/57600 [1:56:05<8:39:04,  1.50it/s]
 19%|█▉        | 10996/57600 [1:56:05<8:14:28,  1.57it/s]
 19%|█▉        | 10997/57600 [1:56:06<8:17:22,  1.56it/s]
 19%|█▉        | 10998/57600 [1:56:06<8:09:27,  1.59it/s]
 19%|█▉        | 10999/57600 [1:56:07<8:13:49,  1.57it/s]
 19%|█▉        | 11000/57600 [1:56:08<8:10:32,  1.58it/s]
                                                         
{'loss': 1.368, 'learning_rate': 8.306620209059233e-07, 'epoch': 121.41}

 19%|█▉        | 11000/57600 [1:56:08<8:10:32,  1.58it/s]
 19%|█▉        | 11001/57600 [1:56:08<8:15:33,  1.57it/s]
 19%|█▉        | 11002/57600 [1:56:09<8:36:35,  1.50it/s]
 19%|█▉        | 11003/57600 [1:56:10<8:33:44,  1.51it/s]
 19%|█▉        | 11004/57600 [1:56:10<8:12:03,  1.58it/s]
 19%|█▉        | 11005/57600 [1:56:11<8:09:27,  1.59it/s]
 19%|█▉        | 11006/57600 [1:56:12<8:09:52,  1.59it/s]
 19%|█▉        | 11007/57600 [1:56:12<8:02:41,  1.61it/s]
 19%|█▉        | 11008/57600 [1:56:13<8:01:43,  1.61it/s]
 19%|█▉        | 11009/57600 [1:56:13<7:55:13,  1.63it/s]
 19%|█▉        | 11010/57600 [1:56:14<7:55:15,  1.63it/s]
 19%|█▉        | 11011/57600 [1:56:15<7:52:55,  1.64it/s]
 19%|█▉        | 11012/57600 [1:56:15<7:46:49,  1.66it/s]
 19%|█▉        | 11013/57600 [1:56:16<7:58:12,  1.62it/s]
 19%|█▉        | 11014/57600 [1:56:16<8:00:27,  1.62it/s]
 19%|█▉        | 11015/57600 [1:56:17<8:18:32,  1.56it/s]
 19%|█▉        | 11016/57600 [1:56:18<8:08:54,  1.59it/s]
 19%|█▉        | 11017/57600 [1:56:18<8:03:24,  1.61it/s]
 19%|█▉        | 11018/57600 [1:56:19<8:02:33,  1.61it/s]
 19%|█▉        | 11019/57600 [1:56:20<8:00:05,  1.62it/s]
 19%|█▉        | 11020/57600 [1:56:20<7:47:49,  1.66it/s]
                                                         
{'loss': 1.3301, 'learning_rate': 8.303484320557491e-07, 'epoch': 121.63}

 19%|█▉        | 11020/57600 [1:56:20<7:47:49,  1.66it/s]
 19%|█▉        | 11021/57600 [1:56:21<7:53:16,  1.64it/s]
 19%|█▉        | 11022/57600 [1:56:21<7:43:01,  1.68it/s]
 19%|█▉        | 11023/57600 [1:56:22<8:01:08,  1.61it/s]
 19%|█▉        | 11024/57600 [1:56:23<7:56:34,  1.63it/s]
 19%|█▉        | 11025/57600 [1:56:23<8:01:20,  1.61it/s]
 19%|█▉        | 11026/57600 [1:56:24<7:43:32,  1.67it/s]
 19%|█▉        | 11027/57600 [1:56:24<7:55:50,  1.63it/s]
 19%|█▉        | 11028/57600 [1:56:25<7:43:42,  1.67it/s]
 19%|█▉        | 11029/57600 [1:56:26<7:48:03,  1.66it/s]
 19%|█▉        | 11030/57600 [1:56:26<8:08:03,  1.59it/s]
 19%|█▉        | 11031/57600 [1:56:27<8:12:54,  1.57it/s]
 19%|█▉        | 11032/57600 [1:56:28<8:11:32,  1.58it/s]
 19%|█▉        | 11033/57600 [1:56:28<8:17:08,  1.56it/s]
 19%|█▉        | 11034/57600 [1:56:29<8:18:54,  1.56it/s]
 19%|█▉        | 11035/57600 [1:56:29<8:06:28,  1.60it/s]
 19%|█▉        | 11036/57600 [1:56:30<7:51:45,  1.65it/s]
 19%|█▉        | 11037/57600 [1:56:31<8:14:03,  1.57it/s]
 19%|█▉        | 11038/57600 [1:56:31<8:08:11,  1.59it/s]
 19%|█▉        | 11039/57600 [1:56:32<8:28:01,  1.53it/s]
 19%|█▉        | 11040/57600 [1:56:33<8:23:16,  1.54it/s]
                                                         
{'loss': 1.3618, 'learning_rate': 8.300348432055749e-07, 'epoch': 121.85}

 19%|█▉        | 11040/57600 [1:56:33<8:23:16,  1.54it/s]
 19%|█▉        | 11041/57600 [1:56:33<8:22:05,  1.55it/s]
 19%|█▉        | 11042/57600 [1:56:34<8:15:12,  1.57it/s]
 19%|█▉        | 11043/57600 [1:56:35<8:00:02,  1.62it/s]
 19%|█▉        | 11044/57600 [1:56:35<8:08:10,  1.59it/s]
 19%|█▉        | 11045/57600 [1:56:36<8:05:07,  1.60it/s]
 19%|█▉        | 11046/57600 [1:56:36<7:55:51,  1.63it/s]
 19%|█▉        | 11047/57600 [1:56:37<7:42:03,  1.68it/s]
 19%|█▉        | 11048/57600 [1:56:38<7:33:57,  1.71it/s]
 19%|█▉        | 11049/57600 [1:56:38<7:37:45,  1.69it/s]
 19%|█▉        | 11050/57600 [1:56:39<7:35:49,  1.70it/s]
 19%|█▉        | 11051/57600 [1:56:39<8:02:19,  1.61it/s]
 19%|█▉        | 11052/57600 [1:56:40<8:02:00,  1.61it/s]
 19%|█▉        | 11053/57600 [1:56:41<7:48:58,  1.65it/s]
 19%|█▉        | 11054/57600 [1:56:41<8:11:22,  1.58it/s]
 19%|█▉        | 11055/57600 [1:56:42<8:06:32,  1.59it/s]
 19%|█▉        | 11056/57600 [1:56:42<8:00:30,  1.61it/s]
 19%|█▉        | 11057/57600 [1:56:43<8:06:27,  1.59it/s]
 19%|█▉        | 11058/57600 [1:56:44<7:50:51,  1.65it/s]
 19%|█▉        | 11059/57600 [1:56:44<7:41:32,  1.68it/s]
 19%|█▉        | 11060/57600 [1:56:45<7:51:27,  1.65it/s]
                                                         
{'loss': 1.3663, 'learning_rate': 8.297212543554007e-07, 'epoch': 122.08}

 19%|█▉        | 11060/57600 [1:56:45<7:51:27,  1.65it/s]
 19%|█▉        | 11061/57600 [1:56:46<8:07:49,  1.59it/s]
 19%|█▉        | 11062/57600 [1:56:46<8:01:52,  1.61it/s]
 19%|█▉        | 11063/57600 [1:56:47<8:14:56,  1.57it/s]
 19%|█▉        | 11064/57600 [1:56:47<8:14:39,  1.57it/s]
 19%|█▉        | 11065/57600 [1:56:48<8:16:22,  1.56it/s]
 19%|█▉        | 11066/57600 [1:56:49<8:02:28,  1.61it/s]
 19%|█▉        | 11067/57600 [1:56:49<7:57:26,  1.62it/s]
 19%|█▉        | 11068/57600 [1:56:50<8:04:16,  1.60it/s]
 19%|█▉        | 11069/57600 [1:56:51<7:55:22,  1.63it/s]
 19%|█▉        | 11070/57600 [1:56:51<7:40:51,  1.68it/s]
 19%|█▉        | 11071/57600 [1:56:52<7:48:45,  1.65it/s]
 19%|█▉        | 11072/57600 [1:56:52<7:44:44,  1.67it/s]
 19%|█▉        | 11073/57600 [1:56:53<7:52:16,  1.64it/s]
 19%|█▉        | 11074/57600 [1:56:54<8:08:38,  1.59it/s]
 19%|█▉        | 11075/57600 [1:56:54<8:04:57,  1.60it/s]
 19%|█▉        | 11076/57600 [1:56:55<7:52:34,  1.64it/s]
 19%|█▉        | 11077/57600 [1:56:55<8:05:14,  1.60it/s]
 19%|█▉        | 11078/57600 [1:56:56<8:02:29,  1.61it/s]
 19%|█▉        | 11079/57600 [1:56:57<7:48:05,  1.66it/s]
 19%|█▉        | 11080/57600 [1:56:57<7:54:07,  1.64it/s]
                                                         
{'loss': 1.3595, 'learning_rate': 8.294076655052264e-07, 'epoch': 122.3}

 19%|█▉        | 11080/57600 [1:56:57<7:54:07,  1.64it/s]
 19%|█▉        | 11081/57600 [1:56:58<8:02:37,  1.61it/s]
 19%|█▉        | 11082/57600 [1:56:59<8:06:07,  1.59it/s]
 19%|█▉        | 11083/57600 [1:56:59<7:51:20,  1.64it/s]
 19%|█▉        | 11084/57600 [1:57:00<7:47:26,  1.66it/s]
 19%|█▉        | 11085/57600 [1:57:00<7:37:21,  1.70it/s]
 19%|█▉        | 11086/57600 [1:57:01<7:47:53,  1.66it/s]
 19%|█▉        | 11087/57600 [1:57:02<7:59:17,  1.62it/s]
 19%|█▉        | 11088/57600 [1:57:02<7:55:40,  1.63it/s]
 19%|█▉        | 11089/57600 [1:57:03<8:16:10,  1.56it/s]
 19%|█▉        | 11090/57600 [1:57:04<8:14:13,  1.57it/s]
 19%|█▉        | 11091/57600 [1:57:04<8:20:29,  1.55it/s]
 19%|█▉        | 11092/57600 [1:57:05<8:16:22,  1.56it/s]
 19%|█▉        | 11093/57600 [1:57:05<8:04:32,  1.60it/s]
 19%|█▉        | 11094/57600 [1:57:06<8:03:17,  1.60it/s]
 19%|█▉        | 11095/57600 [1:57:07<7:58:23,  1.62it/s]
 19%|█▉        | 11096/57600 [1:57:07<8:07:54,  1.59it/s]
 19%|█▉        | 11097/57600 [1:57:08<8:14:18,  1.57it/s]
 19%|█▉        | 11098/57600 [1:57:09<8:01:36,  1.61it/s]
 19%|█▉        | 11099/57600 [1:57:09<8:04:42,  1.60it/s]
 19%|█▉        | 11100/57600 [1:57:10<8:01:37,  1.61it/s]
                                                         
{'loss': 1.3469, 'learning_rate': 8.290940766550522e-07, 'epoch': 122.52}

 19%|█▉        | 11100/57600 [1:57:10<8:01:37,  1.61it/s]
 19%|█▉        | 11101/57600 [1:57:10<8:10:43,  1.58it/s]
 19%|█▉        | 11102/57600 [1:57:11<8:19:46,  1.55it/s]
 19%|█▉        | 11103/57600 [1:57:12<8:25:52,  1.53it/s]
 19%|█▉        | 11104/57600 [1:57:12<8:22:53,  1.54it/s]
 19%|█▉        | 11105/57600 [1:57:13<8:31:35,  1.51it/s]
 19%|█▉        | 11106/57600 [1:57:14<8:30:35,  1.52it/s]
 19%|█▉        | 11107/57600 [1:57:14<8:13:18,  1.57it/s]
 19%|█▉        | 11108/57600 [1:57:15<8:17:06,  1.56it/s]
 19%|█▉        | 11109/57600 [1:57:16<8:02:40,  1.61it/s]
 19%|█▉        | 11110/57600 [1:57:16<7:54:07,  1.63it/s]
 19%|█▉        | 11111/57600 [1:57:17<7:45:35,  1.66it/s]
 19%|█▉        | 11112/57600 [1:57:17<7:45:48,  1.66it/s]
 19%|█▉        | 11113/57600 [1:57:18<7:48:27,  1.65it/s]
 19%|█▉        | 11114/57600 [1:57:19<7:43:00,  1.67it/s]
 19%|█▉        | 11115/57600 [1:57:19<7:36:44,  1.70it/s]
 19%|█▉        | 11116/57600 [1:57:20<7:39:17,  1.69it/s]
 19%|█▉        | 11117/57600 [1:57:20<7:47:16,  1.66it/s]
 19%|█▉        | 11118/57600 [1:57:21<7:28:44,  1.73it/s]
 19%|█▉        | 11119/57600 [1:57:21<7:46:32,  1.66it/s]
 19%|█▉        | 11120/57600 [1:57:22<7:31:49,  1.71it/s]
                                                         
{'loss': 1.3225, 'learning_rate': 8.287804878048781e-07, 'epoch': 122.74}

 19%|█▉        | 11120/57600 [1:57:22<7:31:49,  1.71it/s]
 19%|█▉        | 11121/57600 [1:57:23<7:41:25,  1.68it/s]
 19%|█▉        | 11122/57600 [1:57:23<7:48:13,  1.65it/s]
 19%|█▉        | 11123/57600 [1:57:24<7:40:41,  1.68it/s]
 19%|█▉        | 11124/57600 [1:57:24<7:36:05,  1.70it/s]
 19%|█▉        | 11125/57600 [1:57:25<7:50:38,  1.65it/s]
 19%|█▉        | 11126/57600 [1:57:26<8:09:03,  1.58it/s]
 19%|█▉        | 11127/57600 [1:57:26<8:16:15,  1.56it/s]
 19%|█▉        | 11128/57600 [1:57:27<8:01:39,  1.61it/s]
 19%|█▉        | 11129/57600 [1:57:28<8:05:28,  1.60it/s]
 19%|█▉        | 11130/57600 [1:57:28<8:03:46,  1.60it/s]
 19%|█▉        | 11131/57600 [1:57:29<8:05:28,  1.60it/s]
 19%|█▉        | 11132/57600 [1:57:30<8:06:13,  1.59it/s]
 19%|█▉        | 11133/57600 [1:57:30<7:59:51,  1.61it/s]
 19%|█▉        | 11134/57600 [1:57:31<7:51:09,  1.64it/s]
 19%|█▉        | 11135/57600 [1:57:31<8:05:01,  1.60it/s]
 19%|█▉        | 11136/57600 [1:57:32<7:57:10,  1.62it/s]
 19%|█▉        | 11137/57600 [1:57:33<8:01:58,  1.61it/s]
 19%|█▉        | 11138/57600 [1:57:33<8:14:27,  1.57it/s]
 19%|█▉        | 11139/57600 [1:57:34<8:03:45,  1.60it/s]
 19%|█▉        | 11140/57600 [1:57:34<7:49:52,  1.65it/s]
                                                         
{'loss': 1.3757, 'learning_rate': 8.284668989547038e-07, 'epoch': 122.96}

 19%|█▉        | 11140/57600 [1:57:34<7:49:52,  1.65it/s]
 19%|█▉        | 11141/57600 [1:57:35<7:51:33,  1.64it/s]
 19%|█▉        | 11142/57600 [1:57:36<8:00:27,  1.61it/s]
 19%|█▉        | 11143/57600 [1:57:36<8:14:30,  1.57it/s]
 19%|█▉        | 11144/57600 [1:57:37<8:21:59,  1.54it/s]
 19%|█▉        | 11145/57600 [1:57:38<8:15:57,  1.56it/s]
 19%|█▉        | 11146/57600 [1:57:38<8:14:18,  1.57it/s]
 19%|█▉        | 11147/57600 [1:57:39<7:59:10,  1.62it/s]
 19%|█▉        | 11148/57600 [1:57:39<7:45:05,  1.66it/s]
 19%|█▉        | 11149/57600 [1:57:40<7:52:22,  1.64it/s]
 19%|█▉        | 11150/57600 [1:57:41<7:54:29,  1.63it/s]
 19%|█▉        | 11151/57600 [1:57:41<7:34:23,  1.70it/s]
 19%|█▉        | 11152/57600 [1:57:42<7:58:39,  1.62it/s]
 19%|█▉        | 11153/57600 [1:57:43<7:59:49,  1.61it/s]
 19%|█▉        | 11154/57600 [1:57:43<7:51:25,  1.64it/s]
 19%|█▉        | 11155/57600 [1:57:44<8:04:00,  1.60it/s]
 19%|█▉        | 11156/57600 [1:57:44<7:57:57,  1.62it/s]
 19%|█▉        | 11157/57600 [1:57:45<7:55:21,  1.63it/s]
 19%|█▉        | 11158/57600 [1:57:46<8:03:49,  1.60it/s]
 19%|█▉        | 11159/57600 [1:57:46<8:17:10,  1.56it/s]
 19%|█▉        | 11160/57600 [1:57:47<8:19:17,  1.55it/s]
                                                         
{'loss': 1.3782, 'learning_rate': 8.281533101045296e-07, 'epoch': 123.18}

 19%|█▉        | 11160/57600 [1:57:47<8:19:17,  1.55it/s]
 19%|█▉        | 11161/57600 [1:57:48<8:00:55,  1.61it/s]
 19%|█▉        | 11162/57600 [1:57:48<7:52:42,  1.64it/s]
 19%|█▉        | 11163/57600 [1:57:49<7:43:50,  1.67it/s]
 19%|█▉        | 11164/57600 [1:57:49<7:47:53,  1.65it/s]
 19%|█▉        | 11165/57600 [1:57:50<7:47:45,  1.65it/s]
 19%|█▉        | 11166/57600 [1:57:51<7:55:10,  1.63it/s]
 19%|█▉        | 11167/57600 [1:57:51<7:56:26,  1.62it/s]
 19%|█▉        | 11168/57600 [1:57:52<7:46:51,  1.66it/s]
 19%|█▉        | 11169/57600 [1:57:52<8:06:03,  1.59it/s]
 19%|█▉        | 11170/57600 [1:57:53<8:15:20,  1.56it/s]
 19%|█▉        | 11171/57600 [1:57:54<8:26:36,  1.53it/s]
 19%|█▉        | 11172/57600 [1:57:54<8:06:42,  1.59it/s]
 19%|█▉        | 11173/57600 [1:57:55<8:00:29,  1.61it/s]
 19%|█▉        | 11174/57600 [1:57:55<7:39:56,  1.68it/s]
 19%|█▉        | 11175/57600 [1:57:56<7:49:49,  1.65it/s]
 19%|█▉        | 11176/57600 [1:57:57<8:15:30,  1.56it/s]
 19%|█▉        | 11177/57600 [1:57:58<8:23:26,  1.54it/s]
 19%|█▉        | 11178/57600 [1:57:58<8:13:33,  1.57it/s]
 19%|█▉        | 11179/57600 [1:57:59<8:00:35,  1.61it/s]
 19%|█▉        | 11180/57600 [1:57:59<8:18:17,  1.55it/s]
                                                         
{'loss': 1.3417, 'learning_rate': 8.278397212543553e-07, 'epoch': 123.4}

 19%|█▉        | 11180/57600 [1:57:59<8:18:17,  1.55it/s]
 19%|█▉        | 11181/57600 [1:58:00<8:26:44,  1.53it/s]
 19%|█▉        | 11182/57600 [1:58:01<8:28:45,  1.52it/s]
 19%|█▉        | 11183/57600 [1:58:01<8:24:30,  1.53it/s]
 19%|█▉        | 11184/57600 [1:58:02<8:06:31,  1.59it/s]
 19%|█▉        | 11185/57600 [1:58:03<8:05:42,  1.59it/s]
 19%|█▉        | 11186/57600 [1:58:03<8:01:14,  1.61it/s]
 19%|█▉        | 11187/57600 [1:58:04<7:48:35,  1.65it/s]
 19%|█▉        | 11188/57600 [1:58:04<7:46:33,  1.66it/s]
 19%|█▉        | 11189/57600 [1:58:05<7:29:30,  1.72it/s]
 19%|█▉        | 11190/57600 [1:58:05<7:25:45,  1.74it/s]
 19%|█▉        | 11191/57600 [1:58:06<7:43:51,  1.67it/s]
 19%|█▉        | 11192/57600 [1:58:07<7:41:26,  1.68it/s]
 19%|█▉        | 11193/57600 [1:58:07<7:42:52,  1.67it/s]
 19%|█▉        | 11194/57600 [1:58:08<7:46:37,  1.66it/s]
 19%|█▉        | 11195/57600 [1:58:09<7:51:27,  1.64it/s]
 19%|█▉        | 11196/57600 [1:58:09<7:56:51,  1.62it/s]
 19%|█▉        | 11197/57600 [1:58:10<7:48:30,  1.65it/s]
 19%|█▉        | 11198/57600 [1:58:10<7:49:34,  1.65it/s]
 19%|█▉        | 11199/57600 [1:58:11<7:47:45,  1.65it/s]
 19%|█▉        | 11200/57600 [1:58:12<7:53:45,  1.63it/s]
                                                         
{'loss': 1.353, 'learning_rate': 8.275261324041812e-07, 'epoch': 123.62}

 19%|█▉        | 11200/57600 [1:58:12<7:53:45,  1.63it/s]
 19%|█▉        | 11201/57600 [1:58:12<7:57:21,  1.62it/s]
 19%|█▉        | 11202/57600 [1:58:13<7:54:51,  1.63it/s]
 19%|█▉        | 11203/57600 [1:58:13<7:47:55,  1.65it/s]
 19%|█▉        | 11204/57600 [1:58:14<7:48:20,  1.65it/s]
 19%|█▉        | 11205/57600 [1:58:15<7:50:56,  1.64it/s]
 19%|█▉        | 11206/57600 [1:58:15<8:02:55,  1.60it/s]
 19%|█▉        | 11207/57600 [1:58:16<7:59:32,  1.61it/s]
 19%|█▉        | 11208/57600 [1:58:17<8:12:16,  1.57it/s]
 19%|█▉        | 11209/57600 [1:58:17<7:58:43,  1.62it/s]
 19%|█▉        | 11210/57600 [1:58:18<7:55:17,  1.63it/s]
 19%|█▉        | 11211/57600 [1:58:18<7:56:21,  1.62it/s]
 19%|█▉        | 11212/57600 [1:58:19<8:15:07,  1.56it/s]
 19%|█▉        | 11213/57600 [1:58:20<8:05:49,  1.59it/s]
 19%|█▉        | 11214/57600 [1:58:20<8:10:19,  1.58it/s]
 19%|█▉        | 11215/57600 [1:58:21<8:04:36,  1.60it/s]
 19%|█▉        | 11216/57600 [1:58:22<8:03:32,  1.60it/s]
 19%|█▉        | 11217/57600 [1:58:22<8:00:42,  1.61it/s]
 19%|█▉        | 11218/57600 [1:58:23<8:07:54,  1.58it/s]
 19%|█▉        | 11219/57600 [1:58:23<7:50:15,  1.64it/s]
 19%|█▉        | 11220/57600 [1:58:24<7:42:32,  1.67it/s]
                                                         
{'loss': 1.3455, 'learning_rate': 8.272125435540068e-07, 'epoch': 123.84}

 19%|█▉        | 11220/57600 [1:58:24<7:42:32,  1.67it/s]
 19%|█▉        | 11221/57600 [1:58:25<7:43:19,  1.67it/s]
 19%|█▉        | 11222/57600 [1:58:25<7:34:15,  1.70it/s]
 19%|█▉        | 11223/57600 [1:58:26<7:25:00,  1.74it/s]
 19%|█▉        | 11224/57600 [1:58:26<7:26:22,  1.73it/s]
 19%|█▉        | 11225/57600 [1:58:27<7:43:00,  1.67it/s]
 19%|█▉        | 11226/57600 [1:58:28<7:47:29,  1.65it/s]
 19%|█▉        | 11227/57600 [1:58:28<7:55:50,  1.62it/s]
 19%|█▉        | 11228/57600 [1:58:29<7:58:41,  1.61it/s]
 19%|█▉        | 11229/57600 [1:58:29<7:43:36,  1.67it/s]
 19%|█▉        | 11230/57600 [1:58:30<8:03:03,  1.60it/s]
 19%|█▉        | 11231/57600 [1:58:31<8:02:16,  1.60it/s]
 20%|█▉        | 11232/57600 [1:58:31<8:04:17,  1.60it/s]
 20%|█▉        | 11233/57600 [1:58:32<8:14:53,  1.56it/s]
 20%|█▉        | 11234/57600 [1:58:33<8:33:29,  1.50it/s]
 20%|█▉        | 11235/57600 [1:58:33<8:47:17,  1.47it/s]
 20%|█▉        | 11236/57600 [1:58:34<8:41:11,  1.48it/s]
 20%|█▉        | 11237/57600 [1:58:35<8:25:48,  1.53it/s]
 20%|█▉        | 11238/57600 [1:58:35<8:19:27,  1.55it/s]
 20%|█▉        | 11239/57600 [1:58:36<8:25:31,  1.53it/s]
 20%|█▉        | 11240/57600 [1:58:37<8:13:39,  1.57it/s]
                                                         
{'loss': 1.3426, 'learning_rate': 8.268989547038327e-07, 'epoch': 124.06}

 20%|█▉        | 11240/57600 [1:58:37<8:13:39,  1.57it/s]
 20%|█▉        | 11241/57600 [1:58:37<8:09:40,  1.58it/s]
 20%|█▉        | 11242/57600 [1:58:38<8:02:39,  1.60it/s]
 20%|█▉        | 11243/57600 [1:58:38<7:58:52,  1.61it/s]
 20%|█▉        | 11244/57600 [1:58:39<7:57:52,  1.62it/s]
 20%|█▉        | 11245/57600 [1:58:40<8:06:42,  1.59it/s]
 20%|█▉        | 11246/57600 [1:58:40<7:54:13,  1.63it/s]
 20%|█▉        | 11247/57600 [1:58:41<7:42:49,  1.67it/s]
 20%|█▉        | 11248/57600 [1:58:41<7:45:09,  1.66it/s]
 20%|█▉        | 11249/57600 [1:58:42<7:48:56,  1.65it/s]
 20%|█▉        | 11250/57600 [1:58:43<8:01:38,  1.60it/s]
 20%|█▉        | 11251/57600 [1:58:43<8:04:16,  1.60it/s]
 20%|█▉        | 11252/57600 [1:58:44<8:10:11,  1.58it/s]
 20%|█▉        | 11253/57600 [1:58:45<8:27:33,  1.52it/s]
 20%|█▉        | 11254/57600 [1:58:45<8:07:09,  1.59it/s]
 20%|█▉        | 11255/57600 [1:58:46<8:24:49,  1.53it/s]
 20%|█▉        | 11256/57600 [1:58:47<8:22:30,  1.54it/s]
 20%|█▉        | 11257/57600 [1:58:47<8:21:03,  1.54it/s]
 20%|█▉        | 11258/57600 [1:58:48<8:11:25,  1.57it/s]
 20%|█▉        | 11259/57600 [1:58:48<7:57:59,  1.62it/s]
 20%|█▉        | 11260/57600 [1:58:49<7:51:37,  1.64it/s]
                                                         
{'loss': 1.3728, 'learning_rate': 8.265853658536586e-07, 'epoch': 124.28}

 20%|█▉        | 11260/57600 [1:58:49<7:51:37,  1.64it/s]
 20%|█▉        | 11261/57600 [1:58:50<8:02:36,  1.60it/s]
 20%|█▉        | 11262/57600 [1:58:50<8:04:03,  1.60it/s]
 20%|█▉        | 11263/57600 [1:58:51<8:03:58,  1.60it/s]
 20%|█▉        | 11264/57600 [1:58:52<8:01:38,  1.60it/s]
 20%|█▉        | 11265/57600 [1:58:52<8:00:28,  1.61it/s]
 20%|█▉        | 11266/57600 [1:58:53<7:50:32,  1.64it/s]
 20%|█▉        | 11267/57600 [1:58:53<7:40:46,  1.68it/s]
 20%|█▉        | 11268/57600 [1:58:54<8:08:07,  1.58it/s]
 20%|█▉        | 11269/57600 [1:58:55<8:00:08,  1.61it/s]
 20%|█▉        | 11270/57600 [1:58:55<7:50:32,  1.64it/s]
 20%|█▉        | 11271/57600 [1:58:56<7:53:49,  1.63it/s]
 20%|█▉        | 11272/57600 [1:58:57<8:00:03,  1.61it/s]
 20%|█▉        | 11273/57600 [1:58:57<8:03:17,  1.60it/s]
 20%|█▉        | 11274/57600 [1:58:58<8:02:02,  1.60it/s]
 20%|█▉        | 11275/57600 [1:58:58<8:05:56,  1.59it/s]
 20%|█▉        | 11276/57600 [1:58:59<8:10:32,  1.57it/s]
 20%|█▉        | 11277/57600 [1:59:00<8:18:23,  1.55it/s]
 20%|█▉        | 11278/57600 [1:59:00<7:59:50,  1.61it/s]
 20%|█▉        | 11279/57600 [1:59:01<7:59:01,  1.61it/s]
 20%|█▉        | 11280/57600 [1:59:02<7:57:10,  1.62it/s]
                                                         
{'loss': 1.3162, 'learning_rate': 8.262717770034843e-07, 'epoch': 124.5}

 20%|█▉        | 11280/57600 [1:59:02<7:57:10,  1.62it/s]
 20%|█▉        | 11281/57600 [1:59:02<7:59:19,  1.61it/s]
 20%|█▉        | 11282/57600 [1:59:03<7:49:06,  1.65it/s]
 20%|█▉        | 11283/57600 [1:59:03<8:10:27,  1.57it/s]
 20%|█▉        | 11284/57600 [1:59:04<8:04:17,  1.59it/s]
 20%|█▉        | 11285/57600 [1:59:05<8:04:07,  1.59it/s]
 20%|█▉        | 11286/57600 [1:59:05<7:51:35,  1.64it/s]
 20%|█▉        | 11287/57600 [1:59:06<8:04:27,  1.59it/s]
 20%|█▉        | 11288/57600 [1:59:06<7:51:48,  1.64it/s]
 20%|█▉        | 11289/57600 [1:59:07<7:53:07,  1.63it/s]
 20%|█▉        | 11290/57600 [1:59:08<7:52:58,  1.63it/s]
 20%|█▉        | 11291/57600 [1:59:08<7:56:36,  1.62it/s]
 20%|█▉        | 11292/57600 [1:59:09<7:59:57,  1.61it/s]
 20%|█▉        | 11293/57600 [1:59:10<7:53:35,  1.63it/s]
 20%|█▉        | 11294/57600 [1:59:10<7:49:36,  1.64it/s]
 20%|█▉        | 11295/57600 [1:59:11<8:07:50,  1.58it/s]
 20%|█▉        | 11296/57600 [1:59:11<7:51:06,  1.64it/s]
 20%|█▉        | 11297/57600 [1:59:12<7:49:31,  1.64it/s]
 20%|█▉        | 11298/57600 [1:59:13<7:57:55,  1.61it/s]
 20%|█▉        | 11299/57600 [1:59:13<7:52:34,  1.63it/s]
 20%|█▉        | 11300/57600 [1:59:14<7:53:50,  1.63it/s]
                                                         
{'loss': 1.3784, 'learning_rate': 8.259581881533101e-07, 'epoch': 124.72}

 20%|█▉        | 11300/57600 [1:59:14<7:53:50,  1.63it/s]
 20%|█▉        | 11301/57600 [1:59:14<7:51:30,  1.64it/s]
 20%|█▉        | 11302/57600 [1:59:15<7:38:09,  1.68it/s]
 20%|█▉        | 11303/57600 [1:59:16<7:40:32,  1.68it/s]
 20%|█▉        | 11304/57600 [1:59:16<7:50:20,  1.64it/s]
 20%|█▉        | 11305/57600 [1:59:17<8:05:49,  1.59it/s]
 20%|█▉        | 11306/57600 [1:59:18<8:09:26,  1.58it/s]
 20%|█▉        | 11307/57600 [1:59:18<8:05:16,  1.59it/s]
 20%|█▉        | 11308/57600 [1:59:19<8:02:53,  1.60it/s]
 20%|█▉        | 11309/57600 [1:59:19<7:54:22,  1.63it/s]
 20%|█▉        | 11310/57600 [1:59:20<7:51:46,  1.64it/s]
 20%|█▉        | 11311/57600 [1:59:21<7:52:17,  1.63it/s]
 20%|█▉        | 11312/57600 [1:59:21<8:03:44,  1.59it/s]
 20%|█▉        | 11313/57600 [1:59:22<7:52:28,  1.63it/s]
 20%|█▉        | 11314/57600 [1:59:22<7:41:37,  1.67it/s]
 20%|█▉        | 11315/57600 [1:59:23<7:41:32,  1.67it/s]
 20%|█▉        | 11316/57600 [1:59:24<7:43:08,  1.67it/s]
 20%|█▉        | 11317/57600 [1:59:24<7:55:47,  1.62it/s]
 20%|█▉        | 11318/57600 [1:59:25<8:01:19,  1.60it/s]
 20%|█▉        | 11319/57600 [1:59:26<8:06:07,  1.59it/s]
 20%|█▉        | 11320/57600 [1:59:26<8:26:02,  1.52it/s]
                                                         
{'loss': 1.3341, 'learning_rate': 8.256445993031358e-07, 'epoch': 124.94}

 20%|█▉        | 11320/57600 [1:59:26<8:26:02,  1.52it/s]
 20%|█▉        | 11321/57600 [1:59:27<8:10:41,  1.57it/s]
 20%|█▉        | 11322/57600 [1:59:27<7:52:45,  1.63it/s]
 20%|█▉        | 11323/57600 [1:59:28<7:43:41,  1.66it/s]
 20%|█▉        | 11324/57600 [1:59:29<7:37:49,  1.68it/s]
 20%|█▉        | 11325/57600 [1:59:29<7:26:25,  1.73it/s]
 20%|█▉        | 11326/57600 [1:59:30<7:53:11,  1.63it/s]
 20%|█▉        | 11327/57600 [1:59:30<7:57:23,  1.62it/s]
 20%|█▉        | 11328/57600 [1:59:31<7:56:01,  1.62it/s]
 20%|█▉        | 11329/57600 [1:59:32<7:52:56,  1.63it/s]
 20%|█▉        | 11330/57600 [1:59:32<7:56:26,  1.62it/s]
 20%|█▉        | 11331/57600 [1:59:33<8:00:28,  1.60it/s]
 20%|█▉        | 11332/57600 [1:59:33<7:44:25,  1.66it/s]
 20%|█▉        | 11333/57600 [1:59:34<7:33:41,  1.70it/s]
 20%|█▉        | 11334/57600 [1:59:35<7:29:44,  1.71it/s]
 20%|█▉        | 11335/57600 [1:59:35<7:40:02,  1.68it/s]
 20%|█▉        | 11336/57600 [1:59:36<7:42:16,  1.67it/s]
 20%|█▉        | 11337/57600 [1:59:36<7:47:06,  1.65it/s]
 20%|█▉        | 11338/57600 [1:59:37<8:03:03,  1.60it/s]
 20%|█▉        | 11339/57600 [1:59:38<7:52:06,  1.63it/s]
 20%|█▉        | 11340/57600 [1:59:38<7:57:55,  1.61it/s]
                                                         
{'loss': 1.3837, 'learning_rate': 8.253310104529617e-07, 'epoch': 125.17}

 20%|█▉        | 11340/57600 [1:59:38<7:57:55,  1.61it/s]
 20%|█▉        | 11341/57600 [1:59:39<8:02:25,  1.60it/s]
 20%|█▉        | 11342/57600 [1:59:40<8:01:46,  1.60it/s]
 20%|█▉        | 11343/57600 [1:59:40<7:54:34,  1.62it/s]
 20%|█▉        | 11344/57600 [1:59:41<7:37:51,  1.68it/s]
 20%|█▉        | 11345/57600 [1:59:41<7:36:07,  1.69it/s]
 20%|█▉        | 11346/57600 [1:59:42<7:26:10,  1.73it/s]
 20%|█▉        | 11347/57600 [1:59:42<7:23:31,  1.74it/s]
 20%|█▉        | 11348/57600 [1:59:43<7:40:01,  1.68it/s]
 20%|█▉        | 11349/57600 [1:59:44<7:44:52,  1.66it/s]
 20%|█▉        | 11350/57600 [1:59:44<7:31:01,  1.71it/s]
 20%|█▉        | 11351/57600 [1:59:45<7:41:41,  1.67it/s]
 20%|█▉        | 11352/57600 [1:59:46<7:45:14,  1.66it/s]
 20%|█▉        | 11353/57600 [1:59:46<7:45:09,  1.66it/s]
 20%|█▉        | 11354/57600 [1:59:47<7:56:39,  1.62it/s]
 20%|█▉        | 11355/57600 [1:59:47<8:06:27,  1.58it/s]
 20%|█▉        | 11356/57600 [1:59:48<7:52:32,  1.63it/s]
 20%|█▉        | 11357/57600 [1:59:49<7:49:49,  1.64it/s]
 20%|█▉        | 11358/57600 [1:59:49<7:52:13,  1.63it/s]
 20%|█▉        | 11359/57600 [1:59:50<7:53:21,  1.63it/s]
 20%|█▉        | 11360/57600 [1:59:50<7:47:09,  1.65it/s]
                                                         
{'loss': 1.3848, 'learning_rate': 8.250174216027874e-07, 'epoch': 125.39}

 20%|█▉        | 11360/57600 [1:59:50<7:47:09,  1.65it/s]
 20%|█▉        | 11361/57600 [1:59:51<7:42:03,  1.67it/s]
 20%|█▉        | 11362/57600 [1:59:52<7:50:21,  1.64it/s]
 20%|█▉        | 11363/57600 [1:59:52<7:41:47,  1.67it/s]
 20%|█▉        | 11364/57600 [1:59:53<7:40:56,  1.67it/s]
 20%|█▉        | 11365/57600 [1:59:54<8:00:34,  1.60it/s]
 20%|█▉        | 11366/57600 [1:59:54<7:59:59,  1.61it/s]
 20%|█▉        | 11367/57600 [1:59:55<7:59:05,  1.61it/s]
 20%|█▉        | 11368/57600 [1:59:55<8:11:01,  1.57it/s]
 20%|█▉        | 11369/57600 [1:59:56<8:04:04,  1.59it/s]
 20%|█▉        | 11370/57600 [1:59:57<8:06:41,  1.58it/s]
 20%|█▉        | 11371/57600 [1:59:57<8:02:03,  1.60it/s]
 20%|█▉        | 11372/57600 [1:59:58<7:50:11,  1.64it/s]
 20%|█▉        | 11373/57600 [1:59:58<7:56:39,  1.62it/s]
 20%|█▉        | 11374/57600 [1:59:59<7:48:10,  1.65it/s]
 20%|█▉        | 11375/57600 [2:00:00<8:00:46,  1.60it/s]
 20%|█▉        | 11376/57600 [2:00:00<8:10:31,  1.57it/s]
 20%|█▉        | 11377/57600 [2:00:01<7:58:16,  1.61it/s]
 20%|█▉        | 11378/57600 [2:00:02<7:56:17,  1.62it/s]
 20%|█▉        | 11379/57600 [2:00:02<7:47:08,  1.65it/s]
 20%|█▉        | 11380/57600 [2:00:03<8:15:03,  1.56it/s]
                                                         
{'loss': 1.3667, 'learning_rate': 8.247038327526132e-07, 'epoch': 125.61}

 20%|█▉        | 11380/57600 [2:00:03<8:15:03,  1.56it/s]
 20%|█▉        | 11381/57600 [2:00:03<8:02:43,  1.60it/s]
 20%|█▉        | 11382/57600 [2:00:04<8:11:30,  1.57it/s]
 20%|█▉        | 11383/57600 [2:00:05<7:55:53,  1.62it/s]
 20%|█▉        | 11384/57600 [2:00:05<8:09:23,  1.57it/s]
 20%|█▉        | 11385/57600 [2:00:06<8:09:28,  1.57it/s]
 20%|█▉        | 11386/57600 [2:00:07<8:18:08,  1.55it/s]
 20%|█▉        | 11387/57600 [2:00:07<8:31:38,  1.51it/s]
 20%|█▉        | 11388/57600 [2:00:08<8:33:00,  1.50it/s]
 20%|█▉        | 11389/57600 [2:00:09<8:22:54,  1.53it/s]
 20%|█▉        | 11390/57600 [2:00:09<8:28:01,  1.52it/s]
 20%|█▉        | 11391/57600 [2:00:10<8:34:52,  1.50it/s]
 20%|█▉        | 11392/57600 [2:00:11<8:09:04,  1.57it/s]
 20%|█▉        | 11393/57600 [2:00:11<8:15:50,  1.55it/s]
 20%|█▉        | 11394/57600 [2:00:12<8:18:21,  1.55it/s]
 20%|█▉        | 11395/57600 [2:00:13<8:03:42,  1.59it/s]
 20%|█▉        | 11396/57600 [2:00:13<8:04:06,  1.59it/s]
 20%|█▉        | 11397/57600 [2:00:14<8:12:05,  1.56it/s]
 20%|█▉        | 11398/57600 [2:00:14<8:10:58,  1.57it/s]
 20%|█▉        | 11399/57600 [2:00:15<8:07:27,  1.58it/s]
 20%|█▉        | 11400/57600 [2:00:16<8:04:21,  1.59it/s]
                                                         
{'loss': 1.3061, 'learning_rate': 8.24390243902439e-07, 'epoch': 125.83}

 20%|█▉        | 11400/57600 [2:00:16<8:04:21,  1.59it/s]
 20%|█▉        | 11401/57600 [2:00:16<8:15:20,  1.55it/s]
 20%|█▉        | 11402/57600 [2:00:17<7:57:41,  1.61it/s]
 20%|█▉        | 11403/57600 [2:00:18<8:01:59,  1.60it/s]
 20%|█▉        | 11404/57600 [2:00:18<7:54:47,  1.62it/s]
 20%|█▉        | 11405/57600 [2:00:19<7:45:46,  1.65it/s]
 20%|█▉        | 11406/57600 [2:00:19<7:41:47,  1.67it/s]
 20%|█▉        | 11407/57600 [2:00:20<7:46:56,  1.65it/s]
 20%|█▉        | 11408/57600 [2:00:21<7:56:53,  1.61it/s]
 20%|█▉        | 11409/57600 [2:00:21<7:51:56,  1.63it/s]
 20%|█▉        | 11410/57600 [2:00:22<7:58:13,  1.61it/s]
 20%|█▉        | 11411/57600 [2:00:23<8:05:30,  1.59it/s]
 20%|█▉        | 11412/57600 [2:00:23<7:58:21,  1.61it/s]
 20%|█▉        | 11413/57600 [2:00:24<7:46:04,  1.65it/s]
 20%|█▉        | 11414/57600 [2:00:24<7:36:59,  1.68it/s]
 20%|█▉        | 11415/57600 [2:00:25<7:38:38,  1.68it/s]
 20%|█▉        | 11416/57600 [2:00:26<8:05:23,  1.59it/s]
 20%|█▉        | 11417/57600 [2:00:26<8:25:51,  1.52it/s]
 20%|█▉        | 11418/57600 [2:00:27<8:22:17,  1.53it/s]
 20%|█▉        | 11419/57600 [2:00:28<8:06:28,  1.58it/s]
 20%|█▉        | 11420/57600 [2:00:28<7:54:05,  1.62it/s]
                                                         
{'loss': 1.3405, 'learning_rate': 8.240766550522648e-07, 'epoch': 126.05}

 20%|█▉        | 11420/57600 [2:00:28<7:54:05,  1.62it/s]
 20%|█▉        | 11421/57600 [2:00:29<7:55:59,  1.62it/s]
 20%|█▉        | 11422/57600 [2:00:29<7:49:07,  1.64it/s]
 20%|█▉        | 11423/57600 [2:00:30<7:43:35,  1.66it/s]
 20%|█▉        | 11424/57600 [2:00:30<7:44:44,  1.66it/s]
 20%|█▉        | 11425/57600 [2:00:31<7:34:37,  1.69it/s]
 20%|█▉        | 11426/57600 [2:00:32<7:40:35,  1.67it/s]
 20%|█▉        | 11427/57600 [2:00:32<7:54:40,  1.62it/s]
 20%|█▉        | 11428/57600 [2:00:33<7:48:22,  1.64it/s]
 20%|█▉        | 11429/57600 [2:00:34<7:53:53,  1.62it/s]
 20%|█▉        | 11430/57600 [2:00:34<8:11:21,  1.57it/s]
 20%|█▉        | 11431/57600 [2:00:35<8:06:03,  1.58it/s]
 20%|█▉        | 11432/57600 [2:00:36<8:16:27,  1.55it/s]
 20%|█▉        | 11433/57600 [2:00:36<8:19:07,  1.54it/s]
 20%|█▉        | 11434/57600 [2:00:37<8:08:51,  1.57it/s]
 20%|█▉        | 11435/57600 [2:00:37<8:10:28,  1.57it/s]
 20%|█▉        | 11436/57600 [2:00:38<8:01:50,  1.60it/s]
 20%|█▉        | 11437/57600 [2:00:39<8:19:58,  1.54it/s]
 20%|█▉        | 11438/57600 [2:00:39<8:26:12,  1.52it/s]
 20%|█▉        | 11439/57600 [2:00:40<8:09:09,  1.57it/s]
 20%|█▉        | 11440/57600 [2:00:41<8:00:37,  1.60it/s]
                                                         
{'loss': 1.3561, 'learning_rate': 8.237630662020905e-07, 'epoch': 126.27}

 20%|█▉        | 11440/57600 [2:00:41<8:00:37,  1.60it/s]
 20%|█▉        | 11441/57600 [2:00:41<8:03:31,  1.59it/s]
 20%|█▉        | 11442/57600 [2:00:42<8:01:34,  1.60it/s]
 20%|█▉        | 11443/57600 [2:00:42<7:56:10,  1.62it/s]
 20%|█▉        | 11444/57600 [2:00:43<7:47:46,  1.64it/s]
 20%|█▉        | 11445/57600 [2:00:44<7:38:56,  1.68it/s]
 20%|█▉        | 11446/57600 [2:00:44<7:42:33,  1.66it/s]
 20%|█▉        | 11447/57600 [2:00:45<7:34:07,  1.69it/s]
 20%|█▉        | 11448/57600 [2:00:45<7:25:33,  1.73it/s]
 20%|█▉        | 11449/57600 [2:00:46<7:56:19,  1.61it/s]
 20%|█▉        | 11450/57600 [2:00:47<7:55:31,  1.62it/s]
 20%|█▉        | 11451/57600 [2:00:47<7:54:18,  1.62it/s]
 20%|█▉        | 11452/57600 [2:00:48<7:48:50,  1.64it/s]
 20%|█▉        | 11453/57600 [2:00:48<7:48:05,  1.64it/s]
 20%|█▉        | 11454/57600 [2:00:49<7:41:23,  1.67it/s]
 20%|█▉        | 11455/57600 [2:00:50<7:49:48,  1.64it/s]
 20%|█▉        | 11456/57600 [2:00:50<7:44:13,  1.66it/s]
 20%|█▉        | 11457/57600 [2:00:51<7:43:34,  1.66it/s]
 20%|█▉        | 11458/57600 [2:00:52<7:46:19,  1.65it/s]
 20%|█▉        | 11459/57600 [2:00:52<7:45:45,  1.65it/s]
 20%|█▉        | 11460/57600 [2:00:53<7:47:42,  1.64it/s]
                                                         
{'loss': 1.3472, 'learning_rate': 8.234494773519163e-07, 'epoch': 126.49}

 20%|█▉        | 11460/57600 [2:00:53<7:47:42,  1.64it/s]
 20%|█▉        | 11461/57600 [2:00:53<7:44:04,  1.66it/s]
 20%|█▉        | 11462/57600 [2:00:54<7:35:37,  1.69it/s]
 20%|█▉        | 11463/57600 [2:00:55<7:43:30,  1.66it/s]
 20%|█▉        | 11464/57600 [2:00:55<7:40:39,  1.67it/s]
 20%|█▉        | 11465/57600 [2:00:56<7:42:12,  1.66it/s]
 20%|█▉        | 11466/57600 [2:00:56<7:45:01,  1.65it/s]
 20%|█▉        | 11467/57600 [2:00:57<7:48:56,  1.64it/s]
 20%|█▉        | 11468/57600 [2:00:58<7:46:41,  1.65it/s]
 20%|█▉        | 11469/57600 [2:00:58<7:48:11,  1.64it/s]
 20%|█▉        | 11470/57600 [2:00:59<7:34:14,  1.69it/s]
 20%|█▉        | 11471/57600 [2:00:59<7:37:32,  1.68it/s]
 20%|█▉        | 11472/57600 [2:01:00<7:38:37,  1.68it/s]
 20%|█▉        | 11473/57600 [2:01:01<7:54:12,  1.62it/s]
 20%|█▉        | 11474/57600 [2:01:01<7:50:37,  1.63it/s]
 20%|█▉        | 11475/57600 [2:01:02<8:06:21,  1.58it/s]
 20%|█▉        | 11476/57600 [2:01:02<7:58:48,  1.61it/s]
 20%|█▉        | 11477/57600 [2:01:03<8:00:10,  1.60it/s]
 20%|█▉        | 11478/57600 [2:01:04<7:53:46,  1.62it/s]
 20%|█▉        | 11479/57600 [2:01:04<8:13:39,  1.56it/s]
 20%|█▉        | 11480/57600 [2:01:05<8:23:23,  1.53it/s]
                                                         
{'loss': 1.3836, 'learning_rate': 8.23135888501742e-07, 'epoch': 126.71}

 20%|█▉        | 11480/57600 [2:01:05<8:23:23,  1.53it/s]
 20%|█▉        | 11481/57600 [2:01:06<8:03:52,  1.59it/s]
 20%|█▉        | 11482/57600 [2:01:06<8:05:20,  1.58it/s]
 20%|█▉        | 11483/57600 [2:01:07<7:56:51,  1.61it/s]
 20%|█▉        | 11484/57600 [2:01:08<8:19:26,  1.54it/s]
 20%|█▉        | 11485/57600 [2:01:08<8:04:14,  1.59it/s]
 20%|█▉        | 11486/57600 [2:01:09<7:57:49,  1.61it/s]
 20%|█▉        | 11487/57600 [2:01:09<7:56:00,  1.61it/s]
 20%|█▉        | 11488/57600 [2:01:10<7:48:41,  1.64it/s]
 20%|█▉        | 11489/57600 [2:01:11<7:52:37,  1.63it/s]
 20%|█▉        | 11490/57600 [2:01:11<7:45:11,  1.65it/s]
 20%|█▉        | 11491/57600 [2:01:12<7:48:37,  1.64it/s]
 20%|█▉        | 11492/57600 [2:01:12<7:51:18,  1.63it/s]
 20%|█▉        | 11493/57600 [2:01:13<8:05:55,  1.58it/s]
 20%|█▉        | 11494/57600 [2:01:14<7:46:35,  1.65it/s]
 20%|█▉        | 11495/57600 [2:01:14<7:32:37,  1.70it/s]
 20%|█▉        | 11496/57600 [2:01:15<7:34:03,  1.69it/s]
 20%|█▉        | 11497/57600 [2:01:15<7:26:43,  1.72it/s]
 20%|█▉        | 11498/57600 [2:01:16<7:44:42,  1.65it/s]
 20%|█▉        | 11499/57600 [2:01:17<7:54:02,  1.62it/s]
 20%|█▉        | 11500/57600 [2:01:17<7:54:50,  1.62it/s]
                                                         
{'loss': 1.4228, 'learning_rate': 8.228222996515679e-07, 'epoch': 126.93}

 20%|█▉        | 11500/57600 [2:01:17<7:54:50,  1.62it/s]
 20%|█▉        | 11501/57600 [2:01:18<7:59:40,  1.60it/s]
 20%|█▉        | 11502/57600 [2:01:19<7:56:51,  1.61it/s]
 20%|█▉        | 11503/57600 [2:01:19<7:52:51,  1.62it/s]
 20%|█▉        | 11504/57600 [2:01:20<8:01:02,  1.60it/s]
 20%|█▉        | 11505/57600 [2:01:20<7:56:48,  1.61it/s]
 20%|█▉        | 11506/57600 [2:01:21<7:58:59,  1.60it/s]
 20%|█▉        | 11507/57600 [2:01:22<8:07:50,  1.57it/s]
 20%|█▉        | 11508/57600 [2:01:22<8:04:57,  1.58it/s]
 20%|█▉        | 11509/57600 [2:01:23<7:52:59,  1.62it/s]
 20%|█▉        | 11510/57600 [2:01:24<8:06:12,  1.58it/s]
 20%|█▉        | 11511/57600 [2:01:24<8:11:39,  1.56it/s]
 20%|█▉        | 11512/57600 [2:01:25<8:18:54,  1.54it/s]
 20%|█▉        | 11513/57600 [2:01:25<7:57:46,  1.61it/s]
 20%|█▉        | 11514/57600 [2:01:26<7:52:00,  1.63it/s]
 20%|█▉        | 11515/57600 [2:01:27<7:52:22,  1.63it/s]
 20%|█▉        | 11516/57600 [2:01:27<8:07:42,  1.57it/s]
 20%|█▉        | 11517/57600 [2:01:28<7:56:51,  1.61it/s]
 20%|█▉        | 11518/57600 [2:01:29<7:57:11,  1.61it/s]
 20%|█▉        | 11519/57600 [2:01:29<7:59:24,  1.60it/s]
 20%|██        | 11520/57600 [2:01:30<8:06:30,  1.58it/s]
                                                         
{'loss': 1.3512, 'learning_rate': 8.225087108013937e-07, 'epoch': 127.15}

 20%|██        | 11520/57600 [2:01:30<8:06:30,  1.58it/s]
 20%|██        | 11521/57600 [2:01:30<7:59:43,  1.60it/s]
 20%|██        | 11522/57600 [2:01:31<8:04:22,  1.59it/s]
 20%|██        | 11523/57600 [2:01:32<7:59:43,  1.60it/s]
 20%|██        | 11524/57600 [2:01:32<7:46:13,  1.65it/s]
 20%|██        | 11525/57600 [2:01:33<7:52:48,  1.62it/s]
 20%|██        | 11526/57600 [2:01:34<7:57:51,  1.61it/s]
 20%|██        | 11527/57600 [2:01:34<8:02:08,  1.59it/s]
 20%|██        | 11528/57600 [2:01:35<8:07:54,  1.57it/s]
 20%|██        | 11529/57600 [2:01:35<8:11:18,  1.56it/s]
 20%|██        | 11530/57600 [2:01:36<8:00:50,  1.60it/s]
 20%|██        | 11531/57600 [2:01:37<7:53:07,  1.62it/s]
 20%|██        | 11532/57600 [2:01:37<7:51:57,  1.63it/s]
 20%|██        | 11533/57600 [2:01:38<7:51:20,  1.63it/s]
 20%|██        | 11534/57600 [2:01:38<7:48:07,  1.64it/s]
 20%|██        | 11535/57600 [2:01:39<7:43:58,  1.65it/s]
 20%|██        | 11536/57600 [2:01:40<7:34:27,  1.69it/s]
 20%|██        | 11537/57600 [2:01:40<7:34:14,  1.69it/s]
 20%|██        | 11538/57600 [2:01:41<7:53:12,  1.62it/s]
 20%|██        | 11539/57600 [2:01:42<8:09:42,  1.57it/s]
 20%|██        | 11540/57600 [2:01:42<8:15:34,  1.55it/s]
                                                         
{'loss': 1.3561, 'learning_rate': 8.221951219512195e-07, 'epoch': 127.37}

 20%|██        | 11540/57600 [2:01:42<8:15:34,  1.55it/s]
 20%|██        | 11541/57600 [2:01:43<8:09:22,  1.57it/s]
 20%|██        | 11542/57600 [2:01:43<7:47:04,  1.64it/s]
 20%|██        | 11543/57600 [2:01:44<7:42:09,  1.66it/s]
 20%|██        | 11544/57600 [2:01:45<7:41:12,  1.66it/s]
 20%|██        | 11545/57600 [2:01:45<7:37:50,  1.68it/s]
 20%|██        | 11546/57600 [2:01:46<7:44:13,  1.65it/s]
 20%|██        | 11547/57600 [2:01:46<7:40:08,  1.67it/s]
 20%|██        | 11548/57600 [2:01:47<7:52:28,  1.62it/s]
 20%|██        | 11549/57600 [2:01:48<7:58:57,  1.60it/s]
 20%|██        | 11550/57600 [2:01:48<8:01:39,  1.59it/s]
 20%|██        | 11551/57600 [2:01:49<7:56:43,  1.61it/s]
 20%|██        | 11552/57600 [2:01:50<7:52:24,  1.62it/s]
 20%|██        | 11553/57600 [2:01:50<7:43:27,  1.66it/s]
 20%|██        | 11554/57600 [2:01:51<7:45:26,  1.65it/s]
 20%|██        | 11555/57600 [2:01:51<7:58:40,  1.60it/s]
 20%|██        | 11556/57600 [2:01:52<8:05:54,  1.58it/s]
 20%|██        | 11557/57600 [2:01:53<8:04:47,  1.58it/s]
 20%|██        | 11558/57600 [2:01:53<7:53:03,  1.62it/s]
 20%|██        | 11559/57600 [2:01:54<7:39:48,  1.67it/s]
 20%|██        | 11560/57600 [2:01:55<8:01:07,  1.59it/s]
                                                         
{'loss': 1.3186, 'learning_rate': 8.218815331010453e-07, 'epoch': 127.59}

 20%|██        | 11560/57600 [2:01:55<8:01:07,  1.59it/s]
 20%|██        | 11561/57600 [2:01:55<8:05:27,  1.58it/s]
 20%|██        | 11562/57600 [2:01:56<8:01:03,  1.60it/s]
 20%|██        | 11563/57600 [2:01:56<7:53:50,  1.62it/s]
 20%|██        | 11564/57600 [2:01:57<7:36:30,  1.68it/s]
 20%|██        | 11565/57600 [2:01:57<7:21:31,  1.74it/s]
 20%|██        | 11566/57600 [2:01:58<7:53:52,  1.62it/s]
 20%|██        | 11567/57600 [2:01:59<7:53:54,  1.62it/s]
 20%|██        | 11568/57600 [2:01:59<7:44:55,  1.65it/s]
 20%|██        | 11569/57600 [2:02:00<7:42:43,  1.66it/s]
 20%|██        | 11570/57600 [2:02:01<7:40:14,  1.67it/s]
 20%|██        | 11571/57600 [2:02:01<7:37:28,  1.68it/s]
 20%|██        | 11572/57600 [2:02:02<7:51:13,  1.63it/s]
 20%|██        | 11573/57600 [2:02:02<7:41:53,  1.66it/s]
 20%|██        | 11574/57600 [2:02:03<7:36:46,  1.68it/s]
 20%|██        | 11575/57600 [2:02:04<7:57:59,  1.60it/s]
 20%|██        | 11576/57600 [2:02:04<8:09:13,  1.57it/s]
 20%|██        | 11577/57600 [2:02:05<8:20:32,  1.53it/s]
 20%|██        | 11578/57600 [2:02:06<8:11:35,  1.56it/s]
 20%|██        | 11579/57600 [2:02:06<7:58:48,  1.60it/s]
 20%|██        | 11580/57600 [2:02:07<7:50:59,  1.63it/s]
                                                         
{'loss': 1.3349, 'learning_rate': 8.215679442508711e-07, 'epoch': 127.81}

 20%|██        | 11580/57600 [2:02:07<7:50:59,  1.63it/s]
 20%|██        | 11581/57600 [2:02:07<7:49:34,  1.63it/s]
 20%|██        | 11582/57600 [2:02:08<7:56:55,  1.61it/s]
 20%|██        | 11583/57600 [2:02:09<7:58:20,  1.60it/s]
 20%|██        | 11584/57600 [2:02:09<8:08:57,  1.57it/s]
 20%|██        | 11585/57600 [2:02:10<8:20:07,  1.53it/s]
 20%|██        | 11586/57600 [2:02:11<8:13:28,  1.55it/s]
 20%|██        | 11587/57600 [2:02:11<8:32:53,  1.50it/s]
 20%|██        | 11588/57600 [2:02:12<8:23:51,  1.52it/s]
 20%|██        | 11589/57600 [2:02:13<8:06:39,  1.58it/s]
 20%|██        | 11590/57600 [2:02:13<8:09:31,  1.57it/s]
 20%|██        | 11591/57600 [2:02:14<8:13:28,  1.55it/s]
 20%|██        | 11592/57600 [2:02:14<7:59:46,  1.60it/s]
 20%|██        | 11593/57600 [2:02:15<8:05:42,  1.58it/s]
 20%|██        | 11594/57600 [2:02:16<8:05:47,  1.58it/s]
 20%|██        | 11595/57600 [2:02:16<7:55:06,  1.61it/s]
 20%|██        | 11596/57600 [2:02:17<7:42:26,  1.66it/s]
 20%|██        | 11597/57600 [2:02:18<7:52:23,  1.62it/s]
 20%|██        | 11598/57600 [2:02:18<7:52:52,  1.62it/s]
 20%|██        | 11599/57600 [2:02:19<7:37:40,  1.68it/s]
 20%|██        | 11600/57600 [2:02:19<7:33:22,  1.69it/s]
                                                         
{'loss': 1.3944, 'learning_rate': 8.212543554006968e-07, 'epoch': 128.04}

 20%|██        | 11600/57600 [2:02:19<7:33:22,  1.69it/s]
 20%|██        | 11601/57600 [2:02:20<7:48:05,  1.64it/s]
 20%|██        | 11602/57600 [2:02:21<7:49:13,  1.63it/s]
 20%|██        | 11603/57600 [2:02:21<7:33:15,  1.69it/s]
 20%|██        | 11604/57600 [2:02:22<7:32:08,  1.70it/s]
 20%|██        | 11605/57600 [2:02:22<7:36:03,  1.68it/s]
 20%|██        | 11606/57600 [2:02:23<7:44:07,  1.65it/s]
 20%|██        | 11607/57600 [2:02:23<7:34:32,  1.69it/s]
 20%|██        | 11608/57600 [2:02:24<7:40:29,  1.66it/s]
 20%|██        | 11609/57600 [2:02:25<7:39:44,  1.67it/s]
 20%|██        | 11610/57600 [2:02:25<7:49:20,  1.63it/s]
 20%|██        | 11611/57600 [2:02:26<7:53:06,  1.62it/s]
 20%|██        | 11612/57600 [2:02:27<7:56:22,  1.61it/s]
 20%|██        | 11613/57600 [2:02:27<8:10:15,  1.56it/s]
 20%|██        | 11614/57600 [2:02:28<8:15:06,  1.55it/s]
 20%|██        | 11615/57600 [2:02:29<8:19:10,  1.54it/s]
 20%|██        | 11616/57600 [2:02:29<8:03:45,  1.58it/s]
 20%|██        | 11617/57600 [2:02:30<7:50:25,  1.63it/s]
 20%|██        | 11618/57600 [2:02:30<7:53:21,  1.62it/s]
 20%|██        | 11619/57600 [2:02:31<8:00:40,  1.59it/s]
 20%|██        | 11620/57600 [2:02:32<8:07:09,  1.57it/s]
                                                         
{'loss': 1.3425, 'learning_rate': 8.209407665505226e-07, 'epoch': 128.26}

 20%|██        | 11620/57600 [2:02:32<8:07:09,  1.57it/s]
 20%|██        | 11621/57600 [2:02:32<8:07:19,  1.57it/s]
 20%|██        | 11622/57600 [2:02:33<7:56:32,  1.61it/s]
 20%|██        | 11623/57600 [2:02:33<7:42:49,  1.66it/s]
 20%|██        | 11624/57600 [2:02:34<7:39:48,  1.67it/s]
 20%|██        | 11625/57600 [2:02:35<7:37:45,  1.67it/s]
 20%|██        | 11626/57600 [2:02:35<7:40:22,  1.66it/s]
 20%|██        | 11627/57600 [2:02:36<7:39:37,  1.67it/s]
 20%|██        | 11628/57600 [2:02:37<7:49:01,  1.63it/s]
 20%|██        | 11629/57600 [2:02:37<7:36:20,  1.68it/s]
 20%|██        | 11630/57600 [2:02:38<7:43:56,  1.65it/s]
 20%|██        | 11631/57600 [2:02:38<7:32:21,  1.69it/s]
 20%|██        | 11632/57600 [2:02:39<7:39:13,  1.67it/s]
 20%|██        | 11633/57600 [2:02:39<7:23:35,  1.73it/s]
 20%|██        | 11634/57600 [2:02:40<7:36:50,  1.68it/s]
 20%|██        | 11635/57600 [2:02:41<7:37:46,  1.67it/s]
 20%|██        | 11636/57600 [2:02:41<7:32:09,  1.69it/s]
 20%|██        | 11637/57600 [2:02:42<7:34:18,  1.69it/s]
 20%|██        | 11638/57600 [2:02:43<7:58:29,  1.60it/s]
 20%|██        | 11639/57600 [2:02:43<7:57:38,  1.60it/s]
 20%|██        | 11640/57600 [2:02:44<8:00:38,  1.59it/s]
                                                         
{'loss': 1.3553, 'learning_rate': 8.206271777003484e-07, 'epoch': 128.48}

 20%|██        | 11640/57600 [2:02:44<8:00:38,  1.59it/s]
 20%|██        | 11641/57600 [2:02:44<8:12:54,  1.55it/s]
 20%|██        | 11642/57600 [2:02:45<8:02:43,  1.59it/s]
 20%|██        | 11643/57600 [2:02:46<8:11:29,  1.56it/s]
 20%|██        | 11644/57600 [2:02:46<8:10:01,  1.56it/s]
 20%|██        | 11645/57600 [2:02:47<8:10:15,  1.56it/s]
 20%|██        | 11646/57600 [2:02:48<8:03:17,  1.58it/s]
 20%|██        | 11647/57600 [2:02:48<7:55:37,  1.61it/s]
 20%|██        | 11648/57600 [2:02:49<8:03:03,  1.59it/s]
 20%|██        | 11649/57600 [2:02:50<8:13:28,  1.55it/s]
 20%|██        | 11650/57600 [2:02:50<8:07:42,  1.57it/s]
 20%|██        | 11651/57600 [2:02:51<7:47:19,  1.64it/s]
 20%|██        | 11652/57600 [2:02:51<7:40:18,  1.66it/s]
 20%|██        | 11653/57600 [2:02:52<7:54:35,  1.61it/s]
 20%|██        | 11654/57600 [2:02:53<7:44:52,  1.65it/s]
 20%|██        | 11655/57600 [2:02:53<7:53:14,  1.62it/s]
 20%|██        | 11656/57600 [2:02:54<7:46:19,  1.64it/s]
 20%|██        | 11657/57600 [2:02:54<8:00:14,  1.59it/s]
 20%|██        | 11658/57600 [2:02:55<8:00:15,  1.59it/s]
 20%|██        | 11659/57600 [2:02:56<8:04:41,  1.58it/s]
 20%|██        | 11660/57600 [2:02:56<7:59:48,  1.60it/s]
                                                         
{'loss': 1.339, 'learning_rate': 8.203135888501741e-07, 'epoch': 128.7}

 20%|██        | 11660/57600 [2:02:56<7:59:48,  1.60it/s]
 20%|██        | 11661/57600 [2:02:57<8:19:41,  1.53it/s]
 20%|██        | 11662/57600 [2:02:58<8:18:15,  1.54it/s]
 20%|██        | 11663/57600 [2:02:58<8:05:37,  1.58it/s]
 20%|██        | 11664/57600 [2:02:59<8:22:11,  1.52it/s]
 20%|██        | 11665/57600 [2:03:00<8:03:16,  1.58it/s]
 20%|██        | 11666/57600 [2:03:00<7:54:26,  1.61it/s]
 20%|██        | 11667/57600 [2:03:01<7:42:42,  1.65it/s]
 20%|██        | 11668/57600 [2:03:01<7:47:30,  1.64it/s]
 20%|██        | 11669/57600 [2:03:02<8:03:01,  1.58it/s]
 20%|██        | 11670/57600 [2:03:03<7:55:10,  1.61it/s]
 20%|██        | 11671/57600 [2:03:03<8:15:31,  1.54it/s]
 20%|██        | 11672/57600 [2:03:04<8:19:10,  1.53it/s]
 20%|██        | 11673/57600 [2:03:05<8:38:17,  1.48it/s]
 20%|██        | 11674/57600 [2:03:05<8:17:46,  1.54it/s]
 20%|██        | 11675/57600 [2:03:06<8:22:34,  1.52it/s]
 20%|██        | 11676/57600 [2:03:07<8:05:22,  1.58it/s]
 20%|██        | 11677/57600 [2:03:07<8:07:19,  1.57it/s]
 20%|██        | 11678/57600 [2:03:08<8:03:06,  1.58it/s]
 20%|██        | 11679/57600 [2:03:08<8:06:00,  1.57it/s]
 20%|██        | 11680/57600 [2:03:09<8:05:55,  1.58it/s]
                                                         
{'loss': 1.303, 'learning_rate': 8.2e-07, 'epoch': 128.92}

 20%|██        | 11680/57600 [2:03:09<8:05:55,  1.58it/s]
 20%|██        | 11681/57600 [2:03:10<7:55:51,  1.61it/s]
 20%|██        | 11682/57600 [2:03:10<7:45:48,  1.64it/s]
 20%|██        | 11683/57600 [2:03:11<7:45:46,  1.64it/s]
 20%|██        | 11684/57600 [2:03:11<7:35:26,  1.68it/s]
 20%|██        | 11685/57600 [2:03:12<7:47:31,  1.64it/s]
 20%|██        | 11686/57600 [2:03:13<7:39:46,  1.66it/s]
 20%|██        | 11687/57600 [2:03:13<7:48:44,  1.63it/s]
 20%|██        | 11688/57600 [2:03:14<8:09:10,  1.56it/s]
 20%|██        | 11689/57600 [2:03:15<8:07:40,  1.57it/s]
 20%|██        | 11690/57600 [2:03:15<7:53:48,  1.61it/s]
 20%|██        | 11691/57600 [2:03:16<7:53:38,  1.62it/s]
 20%|██        | 11692/57600 [2:03:16<7:46:52,  1.64it/s]
 20%|██        | 11693/57600 [2:03:17<7:42:42,  1.65it/s]
 20%|██        | 11694/57600 [2:03:18<7:52:20,  1.62it/s]
 20%|██        | 11695/57600 [2:03:18<7:53:13,  1.62it/s]
 20%|██        | 11696/57600 [2:03:19<7:55:55,  1.61it/s]
 20%|██        | 11697/57600 [2:03:19<7:38:38,  1.67it/s]
 20%|██        | 11698/57600 [2:03:20<7:38:33,  1.67it/s]
 20%|██        | 11699/57600 [2:03:21<7:38:40,  1.67it/s]
 20%|██        | 11700/57600 [2:03:21<7:38:11,  1.67it/s]
                                                         
{'loss': 1.3808, 'learning_rate': 8.196864111498257e-07, 'epoch': 129.14}

 20%|██        | 11700/57600 [2:03:21<7:38:11,  1.67it/s]
 20%|██        | 11701/57600 [2:03:22<7:49:22,  1.63it/s]
 20%|██        | 11702/57600 [2:03:22<7:41:56,  1.66it/s]
 20%|██        | 11703/57600 [2:03:23<8:01:31,  1.59it/s]
 20%|██        | 11704/57600 [2:03:24<8:18:57,  1.53it/s]
 20%|██        | 11705/57600 [2:03:24<8:05:09,  1.58it/s]
 20%|██        | 11706/57600 [2:03:25<8:05:49,  1.57it/s]
 20%|██        | 11707/57600 [2:03:26<8:02:59,  1.58it/s]
 20%|██        | 11708/57600 [2:03:26<7:49:09,  1.63it/s]
 20%|██        | 11709/57600 [2:03:27<7:56:53,  1.60it/s]
 20%|██        | 11710/57600 [2:03:28<8:10:45,  1.56it/s]
 20%|██        | 11711/57600 [2:03:28<8:09:07,  1.56it/s]
 20%|██        | 11712/57600 [2:03:29<8:01:52,  1.59it/s]
 20%|██        | 11713/57600 [2:03:29<7:50:41,  1.62it/s]
 20%|██        | 11714/57600 [2:03:30<7:55:21,  1.61it/s]
 20%|██        | 11715/57600 [2:03:31<7:43:38,  1.65it/s]
 20%|██        | 11716/57600 [2:03:31<7:50:35,  1.63it/s]
 20%|██        | 11717/57600 [2:03:32<7:57:37,  1.60it/s]
 20%|██        | 11718/57600 [2:03:33<7:51:34,  1.62it/s]
 20%|██        | 11719/57600 [2:03:33<7:45:05,  1.64it/s]
 20%|██        | 11720/57600 [2:03:34<7:37:16,  1.67it/s]
                                                         
{'loss': 1.3813, 'learning_rate': 8.193728222996516e-07, 'epoch': 129.36}

 20%|██        | 11720/57600 [2:03:34<7:37:16,  1.67it/s]
 20%|██        | 11721/57600 [2:03:34<7:28:29,  1.70it/s]
 20%|██        | 11722/57600 [2:03:35<8:03:18,  1.58it/s]
 20%|██        | 11723/57600 [2:03:36<7:57:40,  1.60it/s]
 20%|██        | 11724/57600 [2:03:36<8:04:40,  1.58it/s]
 20%|██        | 11725/57600 [2:03:37<7:48:49,  1.63it/s]
 20%|██        | 11726/57600 [2:03:37<7:48:41,  1.63it/s]
 20%|██        | 11727/57600 [2:03:38<7:44:27,  1.65it/s]
 20%|██        | 11728/57600 [2:03:39<7:34:17,  1.68it/s]
 20%|██        | 11729/57600 [2:03:39<7:54:15,  1.61it/s]
 20%|██        | 11730/57600 [2:03:40<7:47:44,  1.63it/s]
 20%|██        | 11731/57600 [2:03:41<7:53:02,  1.62it/s]
 20%|██        | 11732/57600 [2:03:41<7:38:56,  1.67it/s]
 20%|██        | 11733/57600 [2:03:42<7:41:39,  1.66it/s]
 20%|██        | 11734/57600 [2:03:42<7:57:49,  1.60it/s]
 20%|██        | 11735/57600 [2:03:43<8:10:42,  1.56it/s]
 20%|██        | 11736/57600 [2:03:44<7:57:58,  1.60it/s]
 20%|██        | 11737/57600 [2:03:44<8:05:19,  1.58it/s]
 20%|██        | 11738/57600 [2:03:45<8:06:23,  1.57it/s]
 20%|██        | 11739/57600 [2:03:46<8:03:18,  1.58it/s]
 20%|██        | 11740/57600 [2:03:46<8:09:14,  1.56it/s]
                                                         
{'loss': 1.321, 'learning_rate': 8.190592334494772e-07, 'epoch': 129.58}

 20%|██        | 11740/57600 [2:03:46<8:09:14,  1.56it/s]
 20%|██        | 11741/57600 [2:03:47<8:11:14,  1.56it/s]
 20%|██        | 11742/57600 [2:03:47<8:05:39,  1.57it/s]
 20%|██        | 11743/57600 [2:03:48<7:49:23,  1.63it/s]
 20%|██        | 11744/57600 [2:03:49<7:38:54,  1.67it/s]
 20%|██        | 11745/57600 [2:03:49<7:30:46,  1.70it/s]
 20%|██        | 11746/57600 [2:03:50<7:36:13,  1.68it/s]
 20%|██        | 11747/57600 [2:03:50<7:40:42,  1.66it/s]
 20%|██        | 11748/57600 [2:03:51<7:45:28,  1.64it/s]
 20%|██        | 11749/57600 [2:03:52<7:56:41,  1.60it/s]
 20%|██        | 11750/57600 [2:03:52<7:54:14,  1.61it/s]
 20%|██        | 11751/57600 [2:03:53<8:08:04,  1.57it/s]
 20%|██        | 11752/57600 [2:03:54<8:07:02,  1.57it/s]
 20%|██        | 11753/57600 [2:03:54<8:09:12,  1.56it/s]
 20%|██        | 11754/57600 [2:03:55<8:38:19,  1.47it/s]
 20%|██        | 11755/57600 [2:03:56<8:21:30,  1.52it/s]
 20%|██        | 11756/57600 [2:03:56<8:09:49,  1.56it/s]
 20%|██        | 11757/57600 [2:03:57<7:51:12,  1.62it/s]
 20%|██        | 11758/57600 [2:03:57<7:50:33,  1.62it/s]
 20%|██        | 11759/57600 [2:03:58<7:53:58,  1.61it/s]
 20%|██        | 11760/57600 [2:03:59<7:45:14,  1.64it/s]
                                                         
{'loss': 1.3458, 'learning_rate': 8.187456445993031e-07, 'epoch': 129.8}

 20%|██        | 11760/57600 [2:03:59<7:45:14,  1.64it/s]
 20%|██        | 11761/57600 [2:03:59<7:45:16,  1.64it/s]
 20%|██        | 11762/57600 [2:04:00<7:45:04,  1.64it/s]
 20%|██        | 11763/57600 [2:04:00<7:40:25,  1.66it/s]
 20%|██        | 11764/57600 [2:04:01<7:43:25,  1.65it/s]
 20%|██        | 11765/57600 [2:04:02<7:53:14,  1.61it/s]
 20%|██        | 11766/57600 [2:04:02<7:51:51,  1.62it/s]
 20%|██        | 11767/57600 [2:04:03<7:54:48,  1.61it/s]
 20%|██        | 11768/57600 [2:04:04<7:41:14,  1.66it/s]
 20%|██        | 11769/57600 [2:04:04<7:37:35,  1.67it/s]
 20%|██        | 11770/57600 [2:04:05<7:51:07,  1.62it/s]
 20%|██        | 11771/57600 [2:04:05<7:53:01,  1.61it/s]
 20%|██        | 11772/57600 [2:04:06<7:59:53,  1.59it/s]
 20%|██        | 11773/57600 [2:04:07<7:58:08,  1.60it/s]
 20%|██        | 11774/57600 [2:04:07<8:18:42,  1.53it/s]
 20%|██        | 11775/57600 [2:04:08<8:14:38,  1.54it/s]
 20%|██        | 11776/57600 [2:04:09<7:54:28,  1.61it/s]
 20%|██        | 11777/57600 [2:04:09<8:01:59,  1.58it/s]
 20%|██        | 11778/57600 [2:04:10<7:48:09,  1.63it/s]
 20%|██        | 11779/57600 [2:04:10<7:58:22,  1.60it/s]
 20%|██        | 11780/57600 [2:04:11<7:54:33,  1.61it/s]
                                                         
{'loss': 1.3039, 'learning_rate': 8.184320557491288e-07, 'epoch': 130.02}

 20%|██        | 11780/57600 [2:04:11<7:54:33,  1.61it/s]
 20%|██        | 11781/57600 [2:04:12<7:38:25,  1.67it/s]
 20%|██        | 11782/57600 [2:04:12<7:40:00,  1.66it/s]
 20%|██        | 11783/57600 [2:04:13<7:44:11,  1.65it/s]
 20%|██        | 11784/57600 [2:04:13<7:45:29,  1.64it/s]
 20%|██        | 11785/57600 [2:04:14<8:04:49,  1.57it/s]
 20%|██        | 11786/57600 [2:04:15<8:22:17,  1.52it/s]
 20%|██        | 11787/57600 [2:04:15<8:07:16,  1.57it/s]
 20%|██        | 11788/57600 [2:04:16<7:54:22,  1.61it/s]
 20%|██        | 11789/57600 [2:04:17<7:52:27,  1.62it/s]
 20%|██        | 11790/57600 [2:04:17<7:44:45,  1.64it/s]
 20%|██        | 11791/57600 [2:04:18<7:50:02,  1.62it/s]
 20%|██        | 11792/57600 [2:04:18<7:48:02,  1.63it/s]
 20%|██        | 11793/57600 [2:04:19<7:52:22,  1.62it/s]
 20%|██        | 11794/57600 [2:04:20<7:51:57,  1.62it/s]
 20%|██        | 11795/57600 [2:04:20<7:54:37,  1.61it/s]
 20%|██        | 11796/57600 [2:04:21<7:59:34,  1.59it/s]
 20%|██        | 11797/57600 [2:04:22<7:42:40,  1.65it/s]
 20%|██        | 11798/57600 [2:04:22<7:38:50,  1.66it/s]
 20%|██        | 11799/57600 [2:04:23<7:47:50,  1.63it/s]
 20%|██        | 11800/57600 [2:04:23<7:51:45,  1.62it/s]
                                                         
{'loss': 1.3619, 'learning_rate': 8.181184668989547e-07, 'epoch': 130.24}

 20%|██        | 11800/57600 [2:04:23<7:51:45,  1.62it/s]
 20%|██        | 11801/57600 [2:04:24<7:47:20,  1.63it/s]
 20%|██        | 11802/57600 [2:04:25<7:50:50,  1.62it/s]
 20%|██        | 11803/57600 [2:04:25<8:19:25,  1.53it/s]
 20%|██        | 11804/57600 [2:04:26<7:57:31,  1.60it/s]
 20%|██        | 11805/57600 [2:04:27<7:48:21,  1.63it/s]
 20%|██        | 11806/57600 [2:04:27<7:41:17,  1.65it/s]
 20%|██        | 11807/57600 [2:04:28<7:41:59,  1.65it/s]
 20%|██        | 11808/57600 [2:04:28<7:33:12,  1.68it/s]
 21%|██        | 11809/57600 [2:04:29<7:33:05,  1.68it/s]
 21%|██        | 11810/57600 [2:04:29<7:34:55,  1.68it/s]
 21%|██        | 11811/57600 [2:04:30<7:39:45,  1.66it/s]
 21%|██        | 11812/57600 [2:04:31<7:41:17,  1.65it/s]
 21%|██        | 11813/57600 [2:04:31<7:58:45,  1.59it/s]
 21%|██        | 11814/57600 [2:04:32<7:59:49,  1.59it/s]
 21%|██        | 11815/57600 [2:04:33<7:55:00,  1.61it/s]
 21%|██        | 11816/57600 [2:04:33<7:38:18,  1.66it/s]
 21%|██        | 11817/57600 [2:04:34<7:43:00,  1.65it/s]
 21%|██        | 11818/57600 [2:04:34<7:59:10,  1.59it/s]
 21%|██        | 11819/57600 [2:04:35<8:03:29,  1.58it/s]
 21%|██        | 11820/57600 [2:04:36<8:06:47,  1.57it/s]
                                                         
{'loss': 1.3726, 'learning_rate': 8.178048780487805e-07, 'epoch': 130.46}

 21%|██        | 11820/57600 [2:04:36<8:06:47,  1.57it/s]
 21%|██        | 11821/57600 [2:04:36<7:53:23,  1.61it/s]
 21%|██        | 11822/57600 [2:04:37<7:46:39,  1.63it/s]
 21%|██        | 11823/57600 [2:04:38<7:53:30,  1.61it/s]
 21%|██        | 11824/57600 [2:04:38<7:55:59,  1.60it/s]
 21%|██        | 11825/57600 [2:04:39<7:41:29,  1.65it/s]
 21%|██        | 11826/57600 [2:04:39<7:45:56,  1.64it/s]
 21%|██        | 11827/57600 [2:04:40<7:37:18,  1.67it/s]
 21%|██        | 11828/57600 [2:04:41<7:32:14,  1.69it/s]
 21%|██        | 11829/57600 [2:04:41<7:37:05,  1.67it/s]
 21%|██        | 11830/57600 [2:04:42<7:29:08,  1.70it/s]
 21%|██        | 11831/57600 [2:04:42<7:45:42,  1.64it/s]
 21%|██        | 11832/57600 [2:04:43<8:08:00,  1.56it/s]
 21%|██        | 11833/57600 [2:04:44<7:57:42,  1.60it/s]
 21%|██        | 11834/57600 [2:04:44<7:52:05,  1.62it/s]
 21%|██        | 11835/57600 [2:04:45<7:40:25,  1.66it/s]
 21%|██        | 11836/57600 [2:04:45<7:38:49,  1.66it/s]
 21%|██        | 11837/57600 [2:04:46<7:45:43,  1.64it/s]
 21%|██        | 11838/57600 [2:04:47<7:41:14,  1.65it/s]
 21%|██        | 11839/57600 [2:04:47<7:39:10,  1.66it/s]
 21%|██        | 11840/57600 [2:04:48<7:47:31,  1.63it/s]
                                                         
{'loss': 1.3511, 'learning_rate': 8.174912891986062e-07, 'epoch': 130.68}

 21%|██        | 11840/57600 [2:04:48<7:47:31,  1.63it/s]
 21%|██        | 11841/57600 [2:04:48<7:40:19,  1.66it/s]
 21%|██        | 11842/57600 [2:04:49<7:48:37,  1.63it/s]
 21%|██        | 11843/57600 [2:04:50<7:55:05,  1.61it/s]
 21%|██        | 11844/57600 [2:04:50<7:44:52,  1.64it/s]
 21%|██        | 11845/57600 [2:04:51<7:52:22,  1.61it/s]
 21%|██        | 11846/57600 [2:04:52<7:56:59,  1.60it/s]
 21%|██        | 11847/57600 [2:04:52<7:59:00,  1.59it/s]
 21%|██        | 11848/57600 [2:04:53<7:53:28,  1.61it/s]
 21%|██        | 11849/57600 [2:04:53<7:47:15,  1.63it/s]
 21%|██        | 11850/57600 [2:04:54<7:49:58,  1.62it/s]
 21%|██        | 11851/57600 [2:04:55<7:57:20,  1.60it/s]
 21%|██        | 11852/57600 [2:04:55<8:08:51,  1.56it/s]
 21%|██        | 11853/57600 [2:04:56<8:02:41,  1.58it/s]
 21%|██        | 11854/57600 [2:04:57<8:05:28,  1.57it/s]
 21%|██        | 11855/57600 [2:04:57<8:08:10,  1.56it/s]
 21%|██        | 11856/57600 [2:04:58<7:51:30,  1.62it/s]
 21%|██        | 11857/57600 [2:04:59<7:57:24,  1.60it/s]
 21%|██        | 11858/57600 [2:04:59<7:58:25,  1.59it/s]
 21%|██        | 11859/57600 [2:05:00<7:45:43,  1.64it/s]
 21%|██        | 11860/57600 [2:05:00<7:43:33,  1.64it/s]
                                                         
{'loss': 1.3184, 'learning_rate': 8.171777003484321e-07, 'epoch': 130.91}

 21%|██        | 11860/57600 [2:05:00<7:43:33,  1.64it/s]
 21%|██        | 11861/57600 [2:05:01<7:43:50,  1.64it/s]
 21%|██        | 11862/57600 [2:05:01<7:27:22,  1.70it/s]
 21%|██        | 11863/57600 [2:05:02<7:59:50,  1.59it/s]
 21%|██        | 11864/57600 [2:05:03<7:52:10,  1.61it/s]
 21%|██        | 11865/57600 [2:05:03<7:51:55,  1.62it/s]
 21%|██        | 11866/57600 [2:05:04<8:07:17,  1.56it/s]
 21%|██        | 11867/57600 [2:05:05<8:03:20,  1.58it/s]
 21%|██        | 11868/57600 [2:05:05<8:03:02,  1.58it/s]
 21%|██        | 11869/57600 [2:05:06<8:18:23,  1.53it/s]
 21%|██        | 11870/57600 [2:05:07<8:01:15,  1.58it/s]
 21%|██        | 11871/57600 [2:05:07<7:59:11,  1.59it/s]
 21%|██        | 11872/57600 [2:05:08<7:50:42,  1.62it/s]
 21%|██        | 11873/57600 [2:05:08<7:53:28,  1.61it/s]
 21%|██        | 11874/57600 [2:05:09<7:51:21,  1.62it/s]
 21%|██        | 11875/57600 [2:05:10<7:54:40,  1.61it/s]
 21%|██        | 11876/57600 [2:05:10<7:47:55,  1.63it/s]
 21%|██        | 11877/57600 [2:05:11<7:55:41,  1.60it/s]
 21%|██        | 11878/57600 [2:05:12<7:52:28,  1.61it/s]
 21%|██        | 11879/57600 [2:05:12<7:59:48,  1.59it/s]
 21%|██        | 11880/57600 [2:05:13<8:06:44,  1.57it/s]
                                                         
{'loss': 1.3295, 'learning_rate': 8.168641114982578e-07, 'epoch': 131.13}

 21%|██        | 11880/57600 [2:05:13<8:06:44,  1.57it/s]
 21%|██        | 11881/57600 [2:05:14<8:01:31,  1.58it/s]
 21%|██        | 11882/57600 [2:05:14<7:44:30,  1.64it/s]
 21%|██        | 11883/57600 [2:05:15<7:52:22,  1.61it/s]
 21%|██        | 11884/57600 [2:05:15<7:58:44,  1.59it/s]
 21%|██        | 11885/57600 [2:05:16<7:59:13,  1.59it/s]
 21%|██        | 11886/57600 [2:05:17<7:54:20,  1.61it/s]
 21%|██        | 11887/57600 [2:05:17<7:55:49,  1.60it/s]
 21%|██        | 11888/57600 [2:05:18<7:56:23,  1.60it/s]
 21%|██        | 11889/57600 [2:05:18<7:44:47,  1.64it/s]
 21%|██        | 11890/57600 [2:05:19<7:47:34,  1.63it/s]
 21%|██        | 11891/57600 [2:05:20<7:47:46,  1.63it/s]
 21%|██        | 11892/57600 [2:05:20<7:47:04,  1.63it/s]
 21%|██        | 11893/57600 [2:05:21<7:42:41,  1.65it/s]
 21%|██        | 11894/57600 [2:05:22<7:51:09,  1.62it/s]
 21%|██        | 11895/57600 [2:05:22<7:39:12,  1.66it/s]
 21%|██        | 11896/57600 [2:05:23<8:00:33,  1.59it/s]
 21%|██        | 11897/57600 [2:05:23<8:00:16,  1.59it/s]
 21%|██        | 11898/57600 [2:05:24<8:17:16,  1.53it/s]
 21%|██        | 11899/57600 [2:05:25<8:02:58,  1.58it/s]
 21%|██        | 11900/57600 [2:05:25<7:59:06,  1.59it/s]
                                                         
{'loss': 1.3437, 'learning_rate': 8.165505226480836e-07, 'epoch': 131.35}

 21%|██        | 11900/57600 [2:05:25<7:59:06,  1.59it/s]
 21%|██        | 11901/57600 [2:05:26<7:51:21,  1.62it/s]
 21%|██        | 11902/57600 [2:05:26<7:32:12,  1.68it/s]
 21%|██        | 11903/57600 [2:05:27<7:43:06,  1.64it/s]
 21%|██        | 11904/57600 [2:05:28<8:00:23,  1.59it/s]
 21%|██        | 11905/57600 [2:05:28<7:48:00,  1.63it/s]
 21%|██        | 11906/57600 [2:05:29<7:49:37,  1.62it/s]
 21%|██        | 11907/57600 [2:05:30<7:47:49,  1.63it/s]
 21%|██        | 11908/57600 [2:05:30<8:06:41,  1.56it/s]
 21%|██        | 11909/57600 [2:05:31<7:56:46,  1.60it/s]
 21%|██        | 11910/57600 [2:05:31<7:54:23,  1.61it/s]
 21%|██        | 11911/57600 [2:05:32<7:44:49,  1.64it/s]
 21%|██        | 11912/57600 [2:05:33<7:47:54,  1.63it/s]
 21%|██        | 11913/57600 [2:05:33<7:39:25,  1.66it/s]
 21%|██        | 11914/57600 [2:05:34<7:47:15,  1.63it/s]
 21%|██        | 11915/57600 [2:05:35<7:51:04,  1.62it/s]
 21%|██        | 11916/57600 [2:05:35<7:52:12,  1.61it/s]
 21%|██        | 11917/57600 [2:05:36<8:00:35,  1.58it/s]
 21%|██        | 11918/57600 [2:05:36<7:54:31,  1.60it/s]
 21%|██        | 11919/57600 [2:05:37<7:52:35,  1.61it/s]
 21%|██        | 11920/57600 [2:05:38<7:52:46,  1.61it/s]
                                                         
{'loss': 1.3191, 'learning_rate': 8.162369337979093e-07, 'epoch': 131.57}

 21%|██        | 11920/57600 [2:05:38<7:52:46,  1.61it/s]
 21%|██        | 11921/57600 [2:05:38<7:52:12,  1.61it/s]
 21%|██        | 11922/57600 [2:05:39<7:51:45,  1.61it/s]
 21%|██        | 11923/57600 [2:05:39<7:38:17,  1.66it/s]
 21%|██        | 11924/57600 [2:05:40<7:35:23,  1.67it/s]
 21%|██        | 11925/57600 [2:05:41<7:26:46,  1.70it/s]
 21%|██        | 11926/57600 [2:05:41<7:34:42,  1.67it/s]
 21%|██        | 11927/57600 [2:05:42<7:39:34,  1.66it/s]
 21%|██        | 11928/57600 [2:05:42<7:43:38,  1.64it/s]
 21%|██        | 11929/57600 [2:05:43<7:37:31,  1.66it/s]
 21%|██        | 11930/57600 [2:05:44<7:22:31,  1.72it/s]
 21%|██        | 11931/57600 [2:05:44<7:33:16,  1.68it/s]
 21%|██        | 11932/57600 [2:05:45<7:34:37,  1.67it/s]
 21%|██        | 11933/57600 [2:05:45<7:35:52,  1.67it/s]
 21%|██        | 11934/57600 [2:05:46<7:42:42,  1.64it/s]
 21%|██        | 11935/57600 [2:05:47<7:41:16,  1.65it/s]
 21%|██        | 11936/57600 [2:05:47<7:26:49,  1.70it/s]
 21%|██        | 11937/57600 [2:05:48<7:43:53,  1.64it/s]
 21%|██        | 11938/57600 [2:05:49<8:04:52,  1.57it/s]
 21%|██        | 11939/57600 [2:05:49<7:56:11,  1.60it/s]
 21%|██        | 11940/57600 [2:05:50<7:42:34,  1.65it/s]
                                                         
{'loss': 1.3698, 'learning_rate': 8.159233449477352e-07, 'epoch': 131.79}

 21%|██        | 11940/57600 [2:05:50<7:42:34,  1.65it/s]
 21%|██        | 11941/57600 [2:05:50<8:00:18,  1.58it/s]
 21%|██        | 11942/57600 [2:05:51<7:53:54,  1.61it/s]
 21%|██        | 11943/57600 [2:05:52<7:52:14,  1.61it/s]
 21%|██        | 11944/57600 [2:05:52<7:51:35,  1.61it/s]
 21%|██        | 11945/57600 [2:05:53<8:05:02,  1.57it/s]
 21%|██        | 11946/57600 [2:05:54<8:13:46,  1.54it/s]
 21%|██        | 11947/57600 [2:05:54<8:09:18,  1.56it/s]
 21%|██        | 11948/57600 [2:05:55<8:11:53,  1.55it/s]
 21%|██        | 11949/57600 [2:05:55<7:59:06,  1.59it/s]
 21%|██        | 11950/57600 [2:05:56<8:04:37,  1.57it/s]
 21%|██        | 11951/57600 [2:05:57<8:08:21,  1.56it/s]
 21%|██        | 11952/57600 [2:05:57<7:57:54,  1.59it/s]
 21%|██        | 11953/57600 [2:05:58<8:02:51,  1.58it/s]
 21%|██        | 11954/57600 [2:05:59<7:53:24,  1.61it/s]
 21%|██        | 11955/57600 [2:05:59<7:47:21,  1.63it/s]
 21%|██        | 11956/57600 [2:06:00<7:41:06,  1.65it/s]
 21%|██        | 11957/57600 [2:06:00<7:46:27,  1.63it/s]
 21%|██        | 11958/57600 [2:06:01<7:34:33,  1.67it/s]
 21%|██        | 11959/57600 [2:06:02<7:48:04,  1.63it/s]
 21%|██        | 11960/57600 [2:06:02<8:15:56,  1.53it/s]
                                                         
{'loss': 1.3018, 'learning_rate': 8.156097560975609e-07, 'epoch': 132.01}

 21%|██        | 11960/57600 [2:06:02<8:15:56,  1.53it/s]
 21%|██        | 11961/57600 [2:06:03<8:05:22,  1.57it/s]
 21%|██        | 11962/57600 [2:06:04<7:53:11,  1.61it/s]
 21%|██        | 11963/57600 [2:06:04<8:02:19,  1.58it/s]
 21%|██        | 11964/57600 [2:06:05<7:44:17,  1.64it/s]
 21%|██        | 11965/57600 [2:06:05<7:45:30,  1.63it/s]
 21%|██        | 11966/57600 [2:06:06<7:55:49,  1.60it/s]
 21%|██        | 11967/57600 [2:06:07<7:54:52,  1.60it/s]
 21%|██        | 11968/57600 [2:06:07<7:52:04,  1.61it/s]
 21%|██        | 11969/57600 [2:06:08<7:43:04,  1.64it/s]
 21%|██        | 11970/57600 [2:06:09<7:50:46,  1.62it/s]
 21%|██        | 11971/57600 [2:06:09<7:41:56,  1.65it/s]
 21%|██        | 11972/57600 [2:06:10<7:35:22,  1.67it/s]
 21%|██        | 11973/57600 [2:06:10<7:29:14,  1.69it/s]
 21%|██        | 11974/57600 [2:06:11<7:59:49,  1.58it/s]
 21%|██        | 11975/57600 [2:06:12<8:11:12,  1.55it/s]
 21%|██        | 11976/57600 [2:06:12<8:11:59,  1.55it/s]
 21%|██        | 11977/57600 [2:06:13<7:54:31,  1.60it/s]
 21%|██        | 11978/57600 [2:06:14<7:55:24,  1.60it/s]
 21%|██        | 11979/57600 [2:06:14<7:42:34,  1.64it/s]
 21%|██        | 11980/57600 [2:06:15<7:43:53,  1.64it/s]
                                                         
{'loss': 1.3678, 'learning_rate': 8.152961672473867e-07, 'epoch': 132.23}

 21%|██        | 11980/57600 [2:06:15<7:43:53,  1.64it/s]
 21%|██        | 11981/57600 [2:06:15<7:44:59,  1.64it/s]
 21%|██        | 11982/57600 [2:06:16<8:11:27,  1.55it/s]
 21%|██        | 11983/57600 [2:06:17<7:59:33,  1.59it/s]
 21%|██        | 11984/57600 [2:06:17<8:05:38,  1.57it/s]
 21%|██        | 11985/57600 [2:06:18<8:01:00,  1.58it/s]
 21%|██        | 11986/57600 [2:06:19<7:52:51,  1.61it/s]
 21%|██        | 11987/57600 [2:06:19<8:01:38,  1.58it/s]
 21%|██        | 11988/57600 [2:06:20<7:58:20,  1.59it/s]
 21%|██        | 11989/57600 [2:06:20<8:01:43,  1.58it/s]
 21%|██        | 11990/57600 [2:06:21<7:54:49,  1.60it/s]
 21%|██        | 11991/57600 [2:06:22<8:08:43,  1.56it/s]
 21%|██        | 11992/57600 [2:06:22<7:59:49,  1.58it/s]
 21%|██        | 11993/57600 [2:06:23<7:56:44,  1.59it/s]
 21%|██        | 11994/57600 [2:06:24<7:52:48,  1.61it/s]
 21%|██        | 11995/57600 [2:06:24<7:52:52,  1.61it/s]
 21%|██        | 11996/57600 [2:06:25<7:55:31,  1.60it/s]
 21%|██        | 11997/57600 [2:06:25<7:53:36,  1.60it/s]
 21%|██        | 11998/57600 [2:06:26<7:48:36,  1.62it/s]
 21%|██        | 11999/57600 [2:06:27<8:00:07,  1.58it/s]
 21%|██        | 12000/57600 [2:06:27<7:42:05,  1.64it/s]
                                                         
{'loss': 1.3626, 'learning_rate': 8.149825783972125e-07, 'epoch': 132.45}

 21%|██        | 12000/57600 [2:06:27<7:42:05,  1.64it/s]
 21%|██        | 12001/57600 [2:06:28<7:37:59,  1.66it/s]
 21%|██        | 12002/57600 [2:06:28<7:41:21,  1.65it/s]
 21%|██        | 12003/57600 [2:06:29<7:44:06,  1.64it/s]
 21%|██        | 12004/57600 [2:06:30<7:29:46,  1.69it/s]
 21%|██        | 12005/57600 [2:06:30<7:25:23,  1.71it/s]
 21%|██        | 12006/57600 [2:06:31<7:27:32,  1.70it/s]
 21%|██        | 12007/57600 [2:06:31<7:34:14,  1.67it/s]
 21%|██        | 12008/57600 [2:06:32<7:36:47,  1.66it/s]
 21%|██        | 12009/57600 [2:06:33<7:23:57,  1.71it/s]
 21%|██        | 12010/57600 [2:06:33<7:19:44,  1.73it/s]
 21%|██        | 12011/57600 [2:06:34<7:29:11,  1.69it/s]
 21%|██        | 12012/57600 [2:06:34<7:58:52,  1.59it/s]
 21%|██        | 12013/57600 [2:06:35<8:02:46,  1.57it/s]
 21%|██        | 12014/57600 [2:06:36<7:48:16,  1.62it/s]
 21%|██        | 12015/57600 [2:06:36<8:22:05,  1.51it/s]
 21%|██        | 12016/57600 [2:06:37<8:18:07,  1.53it/s]
 21%|██        | 12017/57600 [2:06:38<8:14:14,  1.54it/s]
 21%|██        | 12018/57600 [2:06:38<8:01:30,  1.58it/s]
 21%|██        | 12019/57600 [2:06:39<7:49:57,  1.62it/s]
 21%|██        | 12020/57600 [2:06:40<7:47:53,  1.62it/s]
                                                         
{'loss': 1.3456, 'learning_rate': 8.146689895470383e-07, 'epoch': 132.67}

 21%|██        | 12020/57600 [2:06:40<7:47:53,  1.62it/s]
 21%|██        | 12021/57600 [2:06:40<7:45:24,  1.63it/s]
 21%|██        | 12022/57600 [2:06:41<7:32:44,  1.68it/s]
 21%|██        | 12023/57600 [2:06:41<7:47:24,  1.63it/s]
 21%|██        | 12024/57600 [2:06:42<7:48:31,  1.62it/s]
 21%|██        | 12025/57600 [2:06:43<7:48:04,  1.62it/s]
 21%|██        | 12026/57600 [2:06:43<8:02:21,  1.57it/s]
 21%|██        | 12027/57600 [2:06:44<7:57:36,  1.59it/s]
 21%|██        | 12028/57600 [2:06:44<7:37:56,  1.66it/s]
 21%|██        | 12029/57600 [2:06:45<7:34:12,  1.67it/s]
 21%|██        | 12030/57600 [2:06:46<7:34:29,  1.67it/s]
 21%|██        | 12031/57600 [2:06:46<7:48:24,  1.62it/s]
 21%|██        | 12032/57600 [2:06:47<7:44:51,  1.63it/s]
 21%|██        | 12033/57600 [2:06:47<7:46:30,  1.63it/s]
 21%|██        | 12034/57600 [2:06:48<7:38:22,  1.66it/s]
 21%|██        | 12035/57600 [2:06:49<7:27:11,  1.70it/s]
 21%|██        | 12036/57600 [2:06:49<7:40:27,  1.65it/s]
 21%|██        | 12037/57600 [2:06:50<7:35:57,  1.67it/s]
 21%|██        | 12038/57600 [2:06:50<7:46:05,  1.63it/s]
 21%|██        | 12039/57600 [2:06:51<7:35:02,  1.67it/s]
 21%|██        | 12040/57600 [2:06:52<7:34:32,  1.67it/s]
                                                         
{'loss': 1.3649, 'learning_rate': 8.14355400696864e-07, 'epoch': 132.89}

 21%|██        | 12040/57600 [2:06:52<7:34:32,  1.67it/s]
 21%|██        | 12041/57600 [2:06:52<7:46:03,  1.63it/s]
 21%|██        | 12042/57600 [2:06:53<7:48:58,  1.62it/s]
 21%|██        | 12043/57600 [2:06:54<7:46:44,  1.63it/s]
 21%|██        | 12044/57600 [2:06:54<7:37:23,  1.66it/s]
 21%|██        | 12045/57600 [2:06:55<7:40:56,  1.65it/s]
 21%|██        | 12046/57600 [2:06:55<7:44:00,  1.64it/s]
 21%|██        | 12047/57600 [2:06:56<7:51:10,  1.61it/s]
 21%|██        | 12048/57600 [2:06:57<7:36:39,  1.66it/s]
 21%|██        | 12049/57600 [2:06:57<7:32:25,  1.68it/s]
 21%|██        | 12050/57600 [2:06:58<7:52:56,  1.61it/s]
 21%|██        | 12051/57600 [2:06:58<7:55:37,  1.60it/s]
 21%|██        | 12052/57600 [2:06:59<7:46:03,  1.63it/s]
 21%|██        | 12053/57600 [2:07:00<7:50:07,  1.61it/s]
 21%|██        | 12054/57600 [2:07:00<7:47:50,  1.62it/s]
 21%|██        | 12055/57600 [2:07:01<7:37:39,  1.66it/s]
 21%|██        | 12056/57600 [2:07:01<7:35:38,  1.67it/s]
 21%|██        | 12057/57600 [2:07:02<7:32:33,  1.68it/s]
 21%|██        | 12058/57600 [2:07:03<7:35:49,  1.67it/s]
 21%|██        | 12059/57600 [2:07:03<7:41:13,  1.65it/s]
 21%|██        | 12060/57600 [2:07:04<7:38:05,  1.66it/s]
                                                         
{'loss': 1.3615, 'learning_rate': 8.140418118466898e-07, 'epoch': 133.11}

 21%|██        | 12060/57600 [2:07:04<7:38:05,  1.66it/s]
 21%|██        | 12061/57600 [2:07:04<7:47:03,  1.63it/s]
 21%|██        | 12062/57600 [2:07:05<8:08:04,  1.56it/s]
 21%|██        | 12063/57600 [2:07:06<8:02:49,  1.57it/s]
 21%|██        | 12064/57600 [2:07:06<7:52:23,  1.61it/s]
 21%|██        | 12065/57600 [2:07:07<7:45:58,  1.63it/s]
 21%|██        | 12066/57600 [2:07:08<7:53:13,  1.60it/s]
 21%|██        | 12067/57600 [2:07:08<7:47:23,  1.62it/s]
 21%|██        | 12068/57600 [2:07:09<7:43:16,  1.64it/s]
 21%|██        | 12069/57600 [2:07:09<7:40:22,  1.65it/s]
 21%|██        | 12070/57600 [2:07:10<7:29:25,  1.69it/s]
 21%|██        | 12071/57600 [2:07:11<7:28:46,  1.69it/s]
 21%|██        | 12072/57600 [2:07:11<7:34:02,  1.67it/s]
 21%|██        | 12073/57600 [2:07:12<7:26:10,  1.70it/s]
 21%|██        | 12074/57600 [2:07:12<7:27:20,  1.70it/s]
 21%|██        | 12075/57600 [2:07:13<7:30:38,  1.68it/s]
 21%|██        | 12076/57600 [2:07:14<7:26:54,  1.70it/s]
 21%|██        | 12077/57600 [2:07:14<7:45:43,  1.63it/s]
 21%|██        | 12078/57600 [2:07:15<8:00:27,  1.58it/s]
 21%|██        | 12079/57600 [2:07:16<8:06:26,  1.56it/s]
 21%|██        | 12080/57600 [2:07:16<8:06:14,  1.56it/s]
                                                         
{'loss': 1.3447, 'learning_rate': 8.137282229965157e-07, 'epoch': 133.33}

 21%|██        | 12080/57600 [2:07:16<8:06:14,  1.56it/s]
 21%|██        | 12081/57600 [2:07:17<7:56:42,  1.59it/s]
 21%|██        | 12082/57600 [2:07:17<7:48:45,  1.62it/s]
 21%|██        | 12083/57600 [2:07:18<8:04:10,  1.57it/s]
 21%|██        | 12084/57600 [2:07:19<8:05:16,  1.56it/s]
 21%|██        | 12085/57600 [2:07:19<7:56:23,  1.59it/s]
 21%|██        | 12086/57600 [2:07:20<8:18:31,  1.52it/s]
 21%|██        | 12087/57600 [2:07:21<8:16:47,  1.53it/s]
 21%|██        | 12088/57600 [2:07:21<8:08:20,  1.55it/s]
 21%|██        | 12089/57600 [2:07:22<8:01:31,  1.58it/s]
 21%|██        | 12090/57600 [2:07:23<7:54:12,  1.60it/s]
 21%|██        | 12091/57600 [2:07:23<7:37:07,  1.66it/s]
 21%|██        | 12092/57600 [2:07:24<7:31:27,  1.68it/s]
 21%|██        | 12093/57600 [2:07:24<7:32:54,  1.67it/s]
 21%|██        | 12094/57600 [2:07:25<7:26:45,  1.70it/s]
 21%|██        | 12095/57600 [2:07:25<7:20:12,  1.72it/s]
 21%|██        | 12096/57600 [2:07:26<7:33:56,  1.67it/s]
 21%|██        | 12097/57600 [2:07:27<7:43:01,  1.64it/s]
 21%|██        | 12098/57600 [2:07:27<7:36:20,  1.66it/s]
 21%|██        | 12099/57600 [2:07:28<7:44:02,  1.63it/s]
 21%|██        | 12100/57600 [2:07:28<7:31:37,  1.68it/s]
                                                         
{'loss': 1.3378, 'learning_rate': 8.134146341463414e-07, 'epoch': 133.55}

 21%|██        | 12100/57600 [2:07:28<7:31:37,  1.68it/s]
 21%|██        | 12101/57600 [2:07:29<7:34:55,  1.67it/s]
 21%|██        | 12102/57600 [2:07:30<7:43:21,  1.64it/s]
 21%|██        | 12103/57600 [2:07:30<7:47:15,  1.62it/s]
 21%|██        | 12104/57600 [2:07:31<7:45:38,  1.63it/s]
 21%|██        | 12105/57600 [2:07:32<7:50:17,  1.61it/s]
 21%|██        | 12106/57600 [2:07:32<7:46:24,  1.63it/s]
 21%|██        | 12107/57600 [2:07:33<7:39:24,  1.65it/s]
 21%|██        | 12108/57600 [2:07:33<7:57:15,  1.59it/s]
 21%|██        | 12109/57600 [2:07:34<7:43:58,  1.63it/s]
 21%|██        | 12110/57600 [2:07:35<7:46:29,  1.63it/s]
 21%|██        | 12111/57600 [2:07:35<7:50:23,  1.61it/s]
 21%|██        | 12112/57600 [2:07:36<7:51:14,  1.61it/s]
 21%|██        | 12113/57600 [2:07:37<7:51:57,  1.61it/s]
 21%|██        | 12114/57600 [2:07:37<7:51:44,  1.61it/s]
 21%|██        | 12115/57600 [2:07:38<7:55:51,  1.59it/s]
 21%|██        | 12116/57600 [2:07:38<7:44:36,  1.63it/s]
 21%|██        | 12117/57600 [2:07:39<7:35:45,  1.66it/s]
 21%|██        | 12118/57600 [2:07:40<7:54:35,  1.60it/s]
 21%|██        | 12119/57600 [2:07:40<8:16:17,  1.53it/s]
 21%|██        | 12120/57600 [2:07:41<8:17:18,  1.52it/s]
                                                         
{'loss': 1.2747, 'learning_rate': 8.131010452961672e-07, 'epoch': 133.77}

 21%|██        | 12120/57600 [2:07:41<8:17:18,  1.52it/s]
 21%|██        | 12121/57600 [2:07:42<8:11:30,  1.54it/s]
 21%|██        | 12122/57600 [2:07:42<8:13:08,  1.54it/s]
 21%|██        | 12123/57600 [2:07:43<8:05:20,  1.56it/s]
 21%|██        | 12124/57600 [2:07:44<8:06:33,  1.56it/s]
 21%|██        | 12125/57600 [2:07:44<7:50:38,  1.61it/s]
 21%|██        | 12126/57600 [2:07:45<7:45:53,  1.63it/s]
 21%|██        | 12127/57600 [2:07:45<7:41:58,  1.64it/s]
 21%|██        | 12128/57600 [2:07:46<7:37:19,  1.66it/s]
 21%|██        | 12129/57600 [2:07:47<7:43:32,  1.63it/s]
 21%|██        | 12130/57600 [2:07:47<7:52:06,  1.61it/s]
 21%|██        | 12131/57600 [2:07:48<7:53:28,  1.60it/s]
 21%|██        | 12132/57600 [2:07:48<7:57:29,  1.59it/s]
 21%|██        | 12133/57600 [2:07:49<8:09:52,  1.55it/s]
 21%|██        | 12134/57600 [2:07:50<8:08:29,  1.55it/s]
 21%|██        | 12135/57600 [2:07:50<8:00:28,  1.58it/s]
 21%|██        | 12136/57600 [2:07:51<8:23:00,  1.51it/s]
 21%|██        | 12137/57600 [2:07:52<8:18:44,  1.52it/s]
 21%|██        | 12138/57600 [2:07:52<8:14:11,  1.53it/s]
 21%|██        | 12139/57600 [2:07:53<8:19:36,  1.52it/s]
 21%|██        | 12140/57600 [2:07:54<7:54:13,  1.60it/s]
                                                         
{'loss': 1.3212, 'learning_rate': 8.12787456445993e-07, 'epoch': 134.0}

 21%|██        | 12140/57600 [2:07:54<7:54:13,  1.60it/s]
 21%|██        | 12141/57600 [2:07:54<8:21:54,  1.51it/s]
 21%|██        | 12142/57600 [2:07:55<8:08:11,  1.55it/s]
 21%|██        | 12143/57600 [2:07:56<8:25:41,  1.50it/s]
 21%|██        | 12144/57600 [2:07:56<8:25:35,  1.50it/s]
 21%|██        | 12145/57600 [2:07:57<8:18:31,  1.52it/s]
 21%|██        | 12146/57600 [2:07:58<8:16:20,  1.53it/s]
 21%|██        | 12147/57600 [2:07:58<8:04:18,  1.56it/s]
 21%|██        | 12148/57600 [2:07:59<8:11:37,  1.54it/s]
 21%|██        | 12149/57600 [2:08:00<8:03:37,  1.57it/s]
 21%|██        | 12150/57600 [2:08:00<8:05:03,  1.56it/s]
 21%|██        | 12151/57600 [2:08:01<8:00:58,  1.57it/s]
 21%|██        | 12152/57600 [2:08:01<8:12:57,  1.54it/s]
 21%|██        | 12153/57600 [2:08:02<8:12:09,  1.54it/s]
 21%|██        | 12154/57600 [2:08:03<7:58:48,  1.58it/s]
 21%|██        | 12155/57600 [2:08:03<8:02:47,  1.57it/s]
 21%|██        | 12156/57600 [2:08:04<7:49:11,  1.61it/s]
 21%|██        | 12157/57600 [2:08:05<7:51:29,  1.61it/s]
 21%|██        | 12158/57600 [2:08:05<7:47:34,  1.62it/s]
 21%|██        | 12159/57600 [2:08:06<8:10:56,  1.54it/s]
 21%|██        | 12160/57600 [2:08:07<8:14:32,  1.53it/s]
                                                         
{'loss': 1.274, 'learning_rate': 8.124738675958189e-07, 'epoch': 134.22}

 21%|██        | 12160/57600 [2:08:07<8:14:32,  1.53it/s]
 21%|██        | 12161/57600 [2:08:07<8:15:14,  1.53it/s]
 21%|██        | 12162/57600 [2:08:08<7:51:13,  1.61it/s]
 21%|██        | 12163/57600 [2:08:08<7:50:02,  1.61it/s]
 21%|██        | 12164/57600 [2:08:09<7:50:12,  1.61it/s]
 21%|██        | 12165/57600 [2:08:10<7:54:20,  1.60it/s]
 21%|██        | 12166/57600 [2:08:10<7:38:05,  1.65it/s]
 21%|██        | 12167/57600 [2:08:11<7:43:35,  1.63it/s]
 21%|██        | 12168/57600 [2:08:11<7:45:44,  1.63it/s]
 21%|██        | 12169/57600 [2:08:12<7:40:50,  1.64it/s]
 21%|██        | 12170/57600 [2:08:13<7:26:30,  1.70it/s]
 21%|██        | 12171/57600 [2:08:13<7:34:07,  1.67it/s]
 21%|██        | 12172/57600 [2:08:14<7:54:46,  1.59it/s]
 21%|██        | 12173/57600 [2:08:15<7:56:37,  1.59it/s]
 21%|██        | 12174/57600 [2:08:15<7:54:37,  1.60it/s]
 21%|██        | 12175/57600 [2:08:16<7:54:56,  1.59it/s]
 21%|██        | 12176/57600 [2:08:16<7:49:07,  1.61it/s]
 21%|██        | 12177/57600 [2:08:17<7:55:00,  1.59it/s]
 21%|██        | 12178/57600 [2:08:18<7:40:03,  1.65it/s]
 21%|██        | 12179/57600 [2:08:18<7:28:45,  1.69it/s]
 21%|██        | 12180/57600 [2:08:19<7:37:07,  1.66it/s]
                                                         
{'loss': 1.3424, 'learning_rate': 8.121602787456445e-07, 'epoch': 134.44}

 21%|██        | 12180/57600 [2:08:19<7:37:07,  1.66it/s]
 21%|██        | 12181/57600 [2:08:19<7:25:17,  1.70it/s]
 21%|██        | 12182/57600 [2:08:20<7:35:50,  1.66it/s]
 21%|██        | 12183/57600 [2:08:21<7:31:24,  1.68it/s]
 21%|██        | 12184/57600 [2:08:21<7:42:56,  1.64it/s]
 21%|██        | 12185/57600 [2:08:22<7:37:28,  1.65it/s]
 21%|██        | 12186/57600 [2:08:22<7:53:35,  1.60it/s]
 21%|██        | 12187/57600 [2:08:23<7:39:18,  1.65it/s]
 21%|██        | 12188/57600 [2:08:24<7:30:28,  1.68it/s]
 21%|██        | 12189/57600 [2:08:24<7:23:27,  1.71it/s]
 21%|██        | 12190/57600 [2:08:25<7:33:11,  1.67it/s]
 21%|██        | 12191/57600 [2:08:25<7:22:30,  1.71it/s]
 21%|██        | 12192/57600 [2:08:26<7:19:15,  1.72it/s]
 21%|██        | 12193/57600 [2:08:27<7:21:34,  1.71it/s]
 21%|██        | 12194/57600 [2:08:27<7:21:08,  1.72it/s]
 21%|██        | 12195/57600 [2:08:28<7:18:30,  1.73it/s]
 21%|██        | 12196/57600 [2:08:28<7:19:10,  1.72it/s]
 21%|██        | 12197/57600 [2:08:29<7:41:27,  1.64it/s]
 21%|██        | 12198/57600 [2:08:30<8:04:35,  1.56it/s]
 21%|██        | 12199/57600 [2:08:30<8:04:29,  1.56it/s]
 21%|██        | 12200/57600 [2:08:31<8:12:58,  1.53it/s]
                                                         
{'loss': 1.3688, 'learning_rate': 8.118466898954703e-07, 'epoch': 134.66}

 21%|██        | 12200/57600 [2:08:31<8:12:58,  1.53it/s]
 21%|██        | 12201/57600 [2:08:32<8:12:19,  1.54it/s]
 21%|██        | 12202/57600 [2:08:32<8:06:00,  1.56it/s]
 21%|██        | 12203/57600 [2:08:33<7:52:07,  1.60it/s]
 21%|██        | 12204/57600 [2:08:33<7:45:40,  1.62it/s]
 21%|██        | 12205/57600 [2:08:34<7:39:52,  1.65it/s]
 21%|██        | 12206/57600 [2:08:35<7:35:51,  1.66it/s]
 21%|██        | 12207/57600 [2:08:35<7:47:11,  1.62it/s]
 21%|██        | 12208/57600 [2:08:36<7:44:49,  1.63it/s]
 21%|██        | 12209/57600 [2:08:37<7:53:27,  1.60it/s]
 21%|██        | 12210/57600 [2:08:37<7:44:56,  1.63it/s]
 21%|██        | 12211/57600 [2:08:38<7:45:53,  1.62it/s]
 21%|██        | 12212/57600 [2:08:38<7:44:26,  1.63it/s]
 21%|██        | 12213/57600 [2:08:39<7:50:37,  1.61it/s]
 21%|██        | 12214/57600 [2:08:40<7:36:31,  1.66it/s]
 21%|██        | 12215/57600 [2:08:40<7:43:44,  1.63it/s]
 21%|██        | 12216/57600 [2:08:41<7:37:34,  1.65it/s]
 21%|██        | 12217/57600 [2:08:41<7:49:35,  1.61it/s]
 21%|██        | 12218/57600 [2:08:42<7:32:56,  1.67it/s]
 21%|██        | 12219/57600 [2:08:43<7:42:42,  1.63it/s]
 21%|██        | 12220/57600 [2:08:43<7:47:28,  1.62it/s]
                                                         
{'loss': 1.2944, 'learning_rate': 8.115331010452961e-07, 'epoch': 134.88}

 21%|██        | 12220/57600 [2:08:43<7:47:28,  1.62it/s]
 21%|██        | 12221/57600 [2:08:44<7:39:09,  1.65it/s]
 21%|██        | 12222/57600 [2:08:44<7:34:48,  1.66it/s]
 21%|██        | 12223/57600 [2:08:45<8:11:01,  1.54it/s]
 21%|██        | 12224/57600 [2:08:46<8:07:37,  1.55it/s]
 21%|██        | 12225/57600 [2:08:46<7:44:43,  1.63it/s]
 21%|██        | 12226/57600 [2:08:47<7:53:35,  1.60it/s]
 21%|██        | 12227/57600 [2:08:48<7:57:40,  1.58it/s]
 21%|██        | 12228/57600 [2:08:48<7:44:20,  1.63it/s]
 21%|██        | 12229/57600 [2:08:49<7:38:28,  1.65it/s]
 21%|██        | 12230/57600 [2:08:49<7:40:33,  1.64it/s]
 21%|██        | 12231/57600 [2:08:50<7:45:27,  1.62it/s]
 21%|██        | 12232/57600 [2:08:51<7:59:13,  1.58it/s]
 21%|██        | 12233/57600 [2:08:51<7:57:13,  1.58it/s]
 21%|██        | 12234/57600 [2:08:52<7:50:36,  1.61it/s]
 21%|██        | 12235/57600 [2:08:52<7:32:25,  1.67it/s]
 21%|██        | 12236/57600 [2:08:53<7:29:11,  1.68it/s]
 21%|██        | 12237/57600 [2:08:54<7:21:37,  1.71it/s]
 21%|██        | 12238/57600 [2:08:54<7:25:24,  1.70it/s]
 21%|██        | 12239/57600 [2:08:55<7:33:56,  1.67it/s]
 21%|██▏       | 12240/57600 [2:08:55<7:31:08,  1.68it/s]
                                                         
{'loss': 1.4009, 'learning_rate': 8.11219512195122e-07, 'epoch': 135.1}

 21%|██▏       | 12240/57600 [2:08:55<7:31:08,  1.68it/s]
 21%|██▏       | 12241/57600 [2:08:56<7:43:48,  1.63it/s]
 21%|██▏       | 12242/57600 [2:08:57<7:42:20,  1.64it/s]
 21%|██▏       | 12243/57600 [2:08:57<7:29:22,  1.68it/s]
 21%|██▏       | 12244/57600 [2:08:58<8:00:03,  1.57it/s]
 21%|██▏       | 12245/57600 [2:08:59<7:57:42,  1.58it/s]
 21%|██▏       | 12246/57600 [2:08:59<7:43:23,  1.63it/s]
 21%|██▏       | 12247/57600 [2:09:00<7:43:25,  1.63it/s]
 21%|██▏       | 12248/57600 [2:09:00<7:44:46,  1.63it/s]
 21%|██▏       | 12249/57600 [2:09:01<7:41:56,  1.64it/s]
 21%|██▏       | 12250/57600 [2:09:02<7:40:19,  1.64it/s]
 21%|██▏       | 12251/57600 [2:09:02<7:45:48,  1.62it/s]
 21%|██▏       | 12252/57600 [2:09:03<7:31:58,  1.67it/s]
 21%|██▏       | 12253/57600 [2:09:03<7:44:26,  1.63it/s]
 21%|██▏       | 12254/57600 [2:09:04<7:48:09,  1.61it/s]
 21%|██▏       | 12255/57600 [2:09:05<7:37:16,  1.65it/s]
 21%|██▏       | 12256/57600 [2:09:05<7:46:14,  1.62it/s]
 21%|██▏       | 12257/57600 [2:09:06<7:51:09,  1.60it/s]
 21%|██▏       | 12258/57600 [2:09:07<7:52:31,  1.60it/s]
 21%|██▏       | 12259/57600 [2:09:07<8:02:05,  1.57it/s]
 21%|██▏       | 12260/57600 [2:09:08<7:57:54,  1.58it/s]
                                                         
{'loss': 1.3217, 'learning_rate': 8.109059233449476e-07, 'epoch': 135.32}

 21%|██▏       | 12260/57600 [2:09:08<7:57:54,  1.58it/s]
 21%|██▏       | 12261/57600 [2:09:09<8:07:05,  1.55it/s]
 21%|██▏       | 12262/57600 [2:09:09<8:13:13,  1.53it/s]
 21%|██▏       | 12263/57600 [2:09:10<8:04:22,  1.56it/s]
 21%|██▏       | 12264/57600 [2:09:10<8:00:01,  1.57it/s]
 21%|██▏       | 12265/57600 [2:09:11<7:54:50,  1.59it/s]
 21%|██▏       | 12266/57600 [2:09:12<7:52:05,  1.60it/s]
 21%|██▏       | 12267/57600 [2:09:12<7:38:13,  1.65it/s]
 21%|██▏       | 12268/57600 [2:09:13<7:36:01,  1.66it/s]
 21%|██▏       | 12269/57600 [2:09:13<7:45:51,  1.62it/s]
 21%|██▏       | 12270/57600 [2:09:14<7:49:43,  1.61it/s]
 21%|██▏       | 12271/57600 [2:09:15<7:55:53,  1.59it/s]
 21%|██▏       | 12272/57600 [2:09:15<8:08:30,  1.55it/s]
 21%|██▏       | 12273/57600 [2:09:16<8:26:55,  1.49it/s]
 21%|██▏       | 12274/57600 [2:09:17<8:10:52,  1.54it/s]
 21%|██▏       | 12275/57600 [2:09:17<8:05:24,  1.56it/s]
 21%|██▏       | 12276/57600 [2:09:18<7:52:45,  1.60it/s]
 21%|██▏       | 12277/57600 [2:09:19<7:53:52,  1.59it/s]
 21%|██▏       | 12278/57600 [2:09:19<7:46:03,  1.62it/s]
 21%|██▏       | 12279/57600 [2:09:20<7:48:03,  1.61it/s]
 21%|██▏       | 12280/57600 [2:09:20<7:51:53,  1.60it/s]
                                                         
{'loss': 1.3039, 'learning_rate': 8.105923344947735e-07, 'epoch': 135.54}

 21%|██▏       | 12280/57600 [2:09:20<7:51:53,  1.60it/s]
 21%|██▏       | 12281/57600 [2:09:21<7:40:08,  1.64it/s]
 21%|██▏       | 12282/57600 [2:09:22<7:33:47,  1.66it/s]
 21%|██▏       | 12283/57600 [2:09:22<7:32:27,  1.67it/s]
 21%|██▏       | 12284/57600 [2:09:23<7:52:45,  1.60it/s]
 21%|██▏       | 12285/57600 [2:09:24<7:44:57,  1.62it/s]
 21%|██▏       | 12286/57600 [2:09:24<7:48:06,  1.61it/s]
 21%|██▏       | 12287/57600 [2:09:25<7:55:10,  1.59it/s]
 21%|██▏       | 12288/57600 [2:09:25<8:09:24,  1.54it/s]
 21%|██▏       | 12289/57600 [2:09:26<7:59:50,  1.57it/s]
 21%|██▏       | 12290/57600 [2:09:27<7:56:23,  1.59it/s]
 21%|██▏       | 12291/57600 [2:09:27<8:05:36,  1.56it/s]
 21%|██▏       | 12292/57600 [2:09:28<7:58:24,  1.58it/s]
 21%|██▏       | 12293/57600 [2:09:29<7:48:39,  1.61it/s]
 21%|██▏       | 12294/57600 [2:09:29<7:41:47,  1.64it/s]
 21%|██▏       | 12295/57600 [2:09:30<7:52:27,  1.60it/s]
 21%|██▏       | 12296/57600 [2:09:30<7:33:39,  1.66it/s]
 21%|██▏       | 12297/57600 [2:09:31<7:43:49,  1.63it/s]
 21%|██▏       | 12298/57600 [2:09:32<7:47:08,  1.62it/s]
 21%|██▏       | 12299/57600 [2:09:32<7:39:08,  1.64it/s]
 21%|██▏       | 12300/57600 [2:09:33<7:32:59,  1.67it/s]
                                                         
{'loss': 1.3223, 'learning_rate': 8.102787456445994e-07, 'epoch': 135.76}

 21%|██▏       | 12300/57600 [2:09:33<7:32:59,  1.67it/s]
 21%|██▏       | 12301/57600 [2:09:33<7:44:40,  1.62it/s]
 21%|██▏       | 12302/57600 [2:09:34<7:42:55,  1.63it/s]
 21%|██▏       | 12303/57600 [2:09:35<7:39:52,  1.64it/s]
 21%|██▏       | 12304/57600 [2:09:35<7:22:16,  1.71it/s]
 21%|██▏       | 12305/57600 [2:09:36<7:27:03,  1.69it/s]
 21%|██▏       | 12306/57600 [2:09:36<7:26:35,  1.69it/s]
 21%|██▏       | 12307/57600 [2:09:37<7:24:20,  1.70it/s]
 21%|██▏       | 12308/57600 [2:09:38<7:18:32,  1.72it/s]
 21%|██▏       | 12309/57600 [2:09:38<7:41:45,  1.63it/s]
 21%|██▏       | 12310/57600 [2:09:39<7:39:54,  1.64it/s]
 21%|██▏       | 12311/57600 [2:09:39<7:32:46,  1.67it/s]
 21%|██▏       | 12312/57600 [2:09:40<7:25:29,  1.69it/s]
 21%|██▏       | 12313/57600 [2:09:41<7:14:50,  1.74it/s]
 21%|██▏       | 12314/57600 [2:09:41<7:32:45,  1.67it/s]
 21%|██▏       | 12315/57600 [2:09:42<7:37:06,  1.65it/s]
 21%|██▏       | 12316/57600 [2:09:42<7:34:16,  1.66it/s]
 21%|██▏       | 12317/57600 [2:09:43<7:46:10,  1.62it/s]
 21%|██▏       | 12318/57600 [2:09:44<7:29:43,  1.68it/s]
 21%|██▏       | 12319/57600 [2:09:44<7:39:18,  1.64it/s]
 21%|██▏       | 12320/57600 [2:09:45<7:38:03,  1.65it/s]
                                                         
{'loss': 1.3649, 'learning_rate': 8.099651567944251e-07, 'epoch': 135.98}

 21%|██▏       | 12320/57600 [2:09:45<7:38:03,  1.65it/s]
 21%|██▏       | 12321/57600 [2:09:45<7:44:14,  1.63it/s]
 21%|██▏       | 12322/57600 [2:09:46<8:16:21,  1.52it/s]
 21%|██▏       | 12323/57600 [2:09:47<7:52:54,  1.60it/s]
 21%|██▏       | 12324/57600 [2:09:47<7:37:42,  1.65it/s]
 21%|██▏       | 12325/57600 [2:09:48<8:12:27,  1.53it/s]
 21%|██▏       | 12326/57600 [2:09:49<8:10:34,  1.54it/s]
 21%|██▏       | 12327/57600 [2:09:49<7:52:02,  1.60it/s]
 21%|██▏       | 12328/57600 [2:09:50<7:48:06,  1.61it/s]
 21%|██▏       | 12329/57600 [2:09:51<7:44:13,  1.63it/s]
 21%|██▏       | 12330/57600 [2:09:51<7:53:20,  1.59it/s]
 21%|██▏       | 12331/57600 [2:09:52<8:15:56,  1.52it/s]
 21%|██▏       | 12332/57600 [2:09:53<8:09:52,  1.54it/s]
 21%|██▏       | 12333/57600 [2:09:53<7:53:26,  1.59it/s]
 21%|██▏       | 12334/57600 [2:09:54<7:52:27,  1.60it/s]
 21%|██▏       | 12335/57600 [2:09:54<7:41:17,  1.64it/s]
 21%|██▏       | 12336/57600 [2:09:55<7:33:03,  1.67it/s]
 21%|██▏       | 12337/57600 [2:09:55<7:25:53,  1.69it/s]
 21%|██▏       | 12338/57600 [2:09:56<7:37:01,  1.65it/s]
 21%|██▏       | 12339/57600 [2:09:57<7:36:46,  1.65it/s]
 21%|██▏       | 12340/57600 [2:09:57<7:48:24,  1.61it/s]
                                                         
{'loss': 1.3254, 'learning_rate': 8.096515679442508e-07, 'epoch': 136.2}

 21%|██▏       | 12340/57600 [2:09:57<7:48:24,  1.61it/s]
 21%|██▏       | 12341/57600 [2:09:58<7:47:32,  1.61it/s]
 21%|██▏       | 12342/57600 [2:09:59<7:55:38,  1.59it/s]
 21%|██▏       | 12343/57600 [2:09:59<8:06:17,  1.55it/s]
 21%|██▏       | 12344/57600 [2:10:00<8:09:02,  1.54it/s]
 21%|██▏       | 12345/57600 [2:10:01<7:54:22,  1.59it/s]
 21%|██▏       | 12346/57600 [2:10:01<7:49:14,  1.61it/s]
 21%|██▏       | 12347/57600 [2:10:02<7:50:45,  1.60it/s]
 21%|██▏       | 12348/57600 [2:10:02<7:50:25,  1.60it/s]
 21%|██▏       | 12349/57600 [2:10:03<7:58:05,  1.58it/s]
 21%|██▏       | 12350/57600 [2:10:04<7:56:30,  1.58it/s]
 21%|██▏       | 12351/57600 [2:10:04<8:07:38,  1.55it/s]
 21%|██▏       | 12352/57600 [2:10:05<7:56:55,  1.58it/s]
 21%|██▏       | 12353/57600 [2:10:06<7:46:26,  1.62it/s]
 21%|██▏       | 12354/57600 [2:10:06<7:45:36,  1.62it/s]
 21%|██▏       | 12355/57600 [2:10:07<7:27:38,  1.68it/s]
 21%|██▏       | 12356/57600 [2:10:07<7:31:57,  1.67it/s]
 21%|██▏       | 12357/57600 [2:10:08<7:37:50,  1.65it/s]
 21%|██▏       | 12358/57600 [2:10:09<7:29:44,  1.68it/s]
 21%|██▏       | 12359/57600 [2:10:09<7:46:34,  1.62it/s]
 21%|██▏       | 12360/57600 [2:10:10<7:44:19,  1.62it/s]
                                                         
{'loss': 1.3474, 'learning_rate': 8.093379790940766e-07, 'epoch': 136.42}

 21%|██▏       | 12360/57600 [2:10:10<7:44:19,  1.62it/s]
 21%|██▏       | 12361/57600 [2:10:10<7:38:37,  1.64it/s]
 21%|██▏       | 12362/57600 [2:10:11<7:38:04,  1.65it/s]
 21%|██▏       | 12363/57600 [2:10:12<7:31:08,  1.67it/s]
 21%|██▏       | 12364/57600 [2:10:12<7:41:29,  1.63it/s]
 21%|██▏       | 12365/57600 [2:10:13<7:45:50,  1.62it/s]
 21%|██▏       | 12366/57600 [2:10:13<7:42:00,  1.63it/s]
 21%|██▏       | 12367/57600 [2:10:14<7:33:04,  1.66it/s]
 21%|██▏       | 12368/57600 [2:10:15<7:57:36,  1.58it/s]
 21%|██▏       | 12369/57600 [2:10:15<7:45:35,  1.62it/s]
 21%|██▏       | 12370/57600 [2:10:16<7:43:48,  1.63it/s]
 21%|██▏       | 12371/57600 [2:10:16<7:33:04,  1.66it/s]
 21%|██▏       | 12372/57600 [2:10:17<7:32:19,  1.67it/s]
 21%|██▏       | 12373/57600 [2:10:18<7:45:19,  1.62it/s]
 21%|██▏       | 12374/57600 [2:10:18<7:43:17,  1.63it/s]
 21%|██▏       | 12375/57600 [2:10:19<7:44:49,  1.62it/s]
 21%|██▏       | 12376/57600 [2:10:20<7:36:28,  1.65it/s]
 21%|██▏       | 12377/57600 [2:10:20<7:30:41,  1.67it/s]
 21%|██▏       | 12378/57600 [2:10:21<7:37:12,  1.65it/s]
 21%|██▏       | 12379/57600 [2:10:21<7:44:03,  1.62it/s]
 21%|██▏       | 12380/57600 [2:10:22<7:31:16,  1.67it/s]
                                                         
{'loss': 1.3528, 'learning_rate': 8.090243902439025e-07, 'epoch': 136.64}

 21%|██▏       | 12380/57600 [2:10:22<7:31:16,  1.67it/s]
 21%|██▏       | 12381/57600 [2:10:23<7:23:41,  1.70it/s]
 21%|██▏       | 12382/57600 [2:10:23<7:18:26,  1.72it/s]
 21%|██▏       | 12383/57600 [2:10:24<7:22:33,  1.70it/s]
 22%|██▏       | 12384/57600 [2:10:24<7:28:53,  1.68it/s]
 22%|██▏       | 12385/57600 [2:10:25<7:41:23,  1.63it/s]
 22%|██▏       | 12386/57600 [2:10:26<7:48:47,  1.61it/s]
 22%|██▏       | 12387/57600 [2:10:26<8:02:20,  1.56it/s]
 22%|██▏       | 12388/57600 [2:10:27<7:50:02,  1.60it/s]
 22%|██▏       | 12389/57600 [2:10:27<7:47:06,  1.61it/s]
 22%|██▏       | 12390/57600 [2:10:28<7:42:27,  1.63it/s]
 22%|██▏       | 12391/57600 [2:10:29<7:28:06,  1.68it/s]
 22%|██▏       | 12392/57600 [2:10:29<7:23:28,  1.70it/s]
 22%|██▏       | 12393/57600 [2:10:30<7:37:37,  1.65it/s]
 22%|██▏       | 12394/57600 [2:10:30<7:30:15,  1.67it/s]
 22%|██▏       | 12395/57600 [2:10:31<7:51:22,  1.60it/s]
 22%|██▏       | 12396/57600 [2:10:32<7:40:18,  1.64it/s]
 22%|██▏       | 12397/57600 [2:10:32<7:39:00,  1.64it/s]
 22%|██▏       | 12398/57600 [2:10:33<7:51:11,  1.60it/s]
 22%|██▏       | 12399/57600 [2:10:34<7:39:41,  1.64it/s]
 22%|██▏       | 12400/57600 [2:10:34<7:50:01,  1.60it/s]
                                                         
{'loss': 1.3654, 'learning_rate': 8.087108013937281e-07, 'epoch': 136.87}

 22%|██▏       | 12400/57600 [2:10:34<7:50:01,  1.60it/s]
 22%|██▏       | 12401/57600 [2:10:35<7:48:05,  1.61it/s]
 22%|██▏       | 12402/57600 [2:10:35<7:52:33,  1.59it/s]
 22%|██▏       | 12403/57600 [2:10:36<7:37:01,  1.65it/s]
 22%|██▏       | 12404/57600 [2:10:37<7:22:51,  1.70it/s]
 22%|██▏       | 12405/57600 [2:10:37<7:22:22,  1.70it/s]
 22%|██▏       | 12406/57600 [2:10:38<7:24:27,  1.69it/s]
 22%|██▏       | 12407/57600 [2:10:38<7:17:14,  1.72it/s]
 22%|██▏       | 12408/57600 [2:10:39<7:34:02,  1.66it/s]
 22%|██▏       | 12409/57600 [2:10:40<7:26:49,  1.69it/s]
 22%|██▏       | 12410/57600 [2:10:40<7:24:02,  1.70it/s]
 22%|██▏       | 12411/57600 [2:10:41<7:35:37,  1.65it/s]
 22%|██▏       | 12412/57600 [2:10:41<7:31:14,  1.67it/s]
 22%|██▏       | 12413/57600 [2:10:42<7:54:21,  1.59it/s]
 22%|██▏       | 12414/57600 [2:10:43<7:44:58,  1.62it/s]
 22%|██▏       | 12415/57600 [2:10:43<7:34:14,  1.66it/s]
 22%|██▏       | 12416/57600 [2:10:44<7:39:09,  1.64it/s]
 22%|██▏       | 12417/57600 [2:10:44<7:36:15,  1.65it/s]
 22%|██▏       | 12418/57600 [2:10:45<7:27:13,  1.68it/s]
 22%|██▏       | 12419/57600 [2:10:46<7:38:59,  1.64it/s]
 22%|██▏       | 12420/57600 [2:10:46<7:22:19,  1.70it/s]
                                                         
{'loss': 1.3761, 'learning_rate': 8.08397212543554e-07, 'epoch': 137.09}

 22%|██▏       | 12420/57600 [2:10:46<7:22:19,  1.70it/s]
 22%|██▏       | 12421/57600 [2:10:47<7:25:21,  1.69it/s]
 22%|██▏       | 12422/57600 [2:10:47<7:18:11,  1.72it/s]
 22%|██▏       | 12423/57600 [2:10:48<7:34:37,  1.66it/s]
 22%|██▏       | 12424/57600 [2:10:49<7:31:56,  1.67it/s]
 22%|██▏       | 12425/57600 [2:10:49<7:32:42,  1.66it/s]
 22%|██▏       | 12426/57600 [2:10:50<7:17:48,  1.72it/s]
 22%|██▏       | 12427/57600 [2:10:50<7:14:06,  1.73it/s]
 22%|██▏       | 12428/57600 [2:10:51<7:11:06,  1.75it/s]
 22%|██▏       | 12429/57600 [2:10:51<7:11:35,  1.74it/s]
 22%|██▏       | 12430/57600 [2:10:52<7:20:15,  1.71it/s]
 22%|██▏       | 12431/57600 [2:10:53<7:20:25,  1.71it/s]
 22%|██▏       | 12432/57600 [2:10:53<7:32:11,  1.66it/s]
 22%|██▏       | 12433/57600 [2:10:54<7:23:49,  1.70it/s]
 22%|██▏       | 12434/57600 [2:10:54<7:31:58,  1.67it/s]
 22%|██▏       | 12435/57600 [2:10:55<7:51:11,  1.60it/s]
 22%|██▏       | 12436/57600 [2:10:56<7:44:29,  1.62it/s]
 22%|██▏       | 12437/57600 [2:10:56<7:56:10,  1.58it/s]
 22%|██▏       | 12438/57600 [2:10:57<7:56:52,  1.58it/s]
 22%|██▏       | 12439/57600 [2:10:58<7:43:57,  1.62it/s]
 22%|██▏       | 12440/57600 [2:10:58<7:37:38,  1.64it/s]
                                                         
{'loss': 1.3623, 'learning_rate': 8.080836236933798e-07, 'epoch': 137.31}

 22%|██▏       | 12440/57600 [2:10:58<7:37:38,  1.64it/s]
 22%|██▏       | 12441/57600 [2:10:59<7:31:07,  1.67it/s]
 22%|██▏       | 12442/57600 [2:10:59<7:56:48,  1.58it/s]
 22%|██▏       | 12443/57600 [2:11:00<7:55:40,  1.58it/s]
 22%|██▏       | 12444/57600 [2:11:01<8:02:11,  1.56it/s]
 22%|██▏       | 12445/57600 [2:11:01<8:24:37,  1.49it/s]
 22%|██▏       | 12446/57600 [2:11:02<8:19:18,  1.51it/s]
 22%|██▏       | 12447/57600 [2:11:03<8:17:37,  1.51it/s]
 22%|██▏       | 12448/57600 [2:11:03<8:03:03,  1.56it/s]
 22%|██▏       | 12449/57600 [2:11:04<7:46:17,  1.61it/s]
 22%|██▏       | 12450/57600 [2:11:05<7:46:37,  1.61it/s]
 22%|██▏       | 12451/57600 [2:11:05<7:37:10,  1.65it/s]
 22%|██▏       | 12452/57600 [2:11:06<8:02:09,  1.56it/s]
 22%|██▏       | 12453/57600 [2:11:06<7:49:46,  1.60it/s]
 22%|██▏       | 12454/57600 [2:11:07<7:47:39,  1.61it/s]
 22%|██▏       | 12455/57600 [2:11:08<7:53:49,  1.59it/s]
 22%|██▏       | 12456/57600 [2:11:08<8:07:52,  1.54it/s]
 22%|██▏       | 12457/57600 [2:11:09<7:49:01,  1.60it/s]
 22%|██▏       | 12458/57600 [2:11:10<7:51:29,  1.60it/s]
 22%|██▏       | 12459/57600 [2:11:10<7:36:56,  1.65it/s]
 22%|██▏       | 12460/57600 [2:11:11<7:27:04,  1.68it/s]
                                                         
{'loss': 1.322, 'learning_rate': 8.077700348432056e-07, 'epoch': 137.53}

 22%|██▏       | 12460/57600 [2:11:11<7:27:04,  1.68it/s]
 22%|██▏       | 12461/57600 [2:11:11<7:31:34,  1.67it/s]
 22%|██▏       | 12462/57600 [2:11:12<7:49:03,  1.60it/s]
 22%|██▏       | 12463/57600 [2:11:13<8:05:34,  1.55it/s]
 22%|██▏       | 12464/57600 [2:11:13<7:49:14,  1.60it/s]
 22%|██▏       | 12465/57600 [2:11:14<7:41:22,  1.63it/s]
 22%|██▏       | 12466/57600 [2:11:15<7:51:39,  1.59it/s]
 22%|██▏       | 12467/57600 [2:11:15<7:46:03,  1.61it/s]
 22%|██▏       | 12468/57600 [2:11:16<7:41:37,  1.63it/s]
 22%|██▏       | 12469/57600 [2:11:16<7:30:39,  1.67it/s]
 22%|██▏       | 12470/57600 [2:11:17<7:32:01,  1.66it/s]
 22%|██▏       | 12471/57600 [2:11:18<7:44:52,  1.62it/s]
 22%|██▏       | 12472/57600 [2:11:18<7:40:45,  1.63it/s]
 22%|██▏       | 12473/57600 [2:11:19<7:46:06,  1.61it/s]
 22%|██▏       | 12474/57600 [2:11:19<7:32:15,  1.66it/s]
 22%|██▏       | 12475/57600 [2:11:20<7:25:32,  1.69it/s]
 22%|██▏       | 12476/57600 [2:11:21<7:41:17,  1.63it/s]
 22%|██▏       | 12477/57600 [2:11:21<7:56:57,  1.58it/s]
 22%|██▏       | 12478/57600 [2:11:22<7:59:14,  1.57it/s]
 22%|██▏       | 12479/57600 [2:11:22<7:36:17,  1.65it/s]
 22%|██▏       | 12480/57600 [2:11:23<7:27:03,  1.68it/s]
                                                         
{'loss': 1.3221, 'learning_rate': 8.074564459930312e-07, 'epoch': 137.75}

 22%|██▏       | 12480/57600 [2:11:23<7:27:03,  1.68it/s]
 22%|██▏       | 12481/57600 [2:11:24<7:42:37,  1.63it/s]
 22%|██▏       | 12482/57600 [2:11:24<7:44:06,  1.62it/s]
 22%|██▏       | 12483/57600 [2:11:25<7:39:29,  1.64it/s]
 22%|██▏       | 12484/57600 [2:11:25<7:28:49,  1.68it/s]
 22%|██▏       | 12485/57600 [2:11:26<7:47:17,  1.61it/s]
 22%|██▏       | 12486/57600 [2:11:27<7:48:34,  1.60it/s]
 22%|██▏       | 12487/57600 [2:11:27<7:38:24,  1.64it/s]
 22%|██▏       | 12488/57600 [2:11:28<7:42:16,  1.63it/s]
 22%|██▏       | 12489/57600 [2:11:29<7:33:59,  1.66it/s]
 22%|██▏       | 12490/57600 [2:11:29<7:24:34,  1.69it/s]
 22%|██▏       | 12491/57600 [2:11:30<7:21:45,  1.70it/s]
 22%|██▏       | 12492/57600 [2:11:30<7:24:43,  1.69it/s]
 22%|██▏       | 12493/57600 [2:11:31<7:31:00,  1.67it/s]
 22%|██▏       | 12494/57600 [2:11:32<7:40:02,  1.63it/s]
 22%|██▏       | 12495/57600 [2:11:32<7:53:36,  1.59it/s]
 22%|██▏       | 12496/57600 [2:11:33<7:43:36,  1.62it/s]
 22%|██▏       | 12497/57600 [2:11:33<7:42:04,  1.63it/s]
 22%|██▏       | 12498/57600 [2:11:34<8:00:11,  1.57it/s]
 22%|██▏       | 12499/57600 [2:11:35<8:01:18,  1.56it/s]
 22%|██▏       | 12500/57600 [2:11:35<7:53:47,  1.59it/s]
                                                         
{'loss': 1.3333, 'learning_rate': 8.071428571428571e-07, 'epoch': 137.97}

 22%|██▏       | 12500/57600 [2:11:35<7:53:47,  1.59it/s]
 22%|██▏       | 12501/57600 [2:11:36<8:04:44,  1.55it/s]
 22%|██▏       | 12502/57600 [2:11:37<8:01:57,  1.56it/s]
 22%|██▏       | 12503/57600 [2:11:37<8:29:04,  1.48it/s]
 22%|██▏       | 12504/57600 [2:11:38<8:15:12,  1.52it/s]
 22%|██▏       | 12505/57600 [2:11:39<8:08:26,  1.54it/s]
 22%|██▏       | 12506/57600 [2:11:39<7:47:36,  1.61it/s]
 22%|██▏       | 12507/57600 [2:11:40<7:46:36,  1.61it/s]
 22%|██▏       | 12508/57600 [2:11:40<7:31:34,  1.66it/s]
 22%|██▏       | 12509/57600 [2:11:41<7:41:56,  1.63it/s]
 22%|██▏       | 12510/57600 [2:11:42<7:41:48,  1.63it/s]
 22%|██▏       | 12511/57600 [2:11:42<8:00:21,  1.56it/s]
 22%|██▏       | 12512/57600 [2:11:43<7:56:06,  1.58it/s]
 22%|██▏       | 12513/57600 [2:11:44<7:46:32,  1.61it/s]
 22%|██▏       | 12514/57600 [2:11:44<7:55:53,  1.58it/s]
 22%|██▏       | 12515/57600 [2:11:45<7:57:37,  1.57it/s]
 22%|██▏       | 12516/57600 [2:11:45<7:44:39,  1.62it/s]
 22%|██▏       | 12517/57600 [2:11:46<7:44:47,  1.62it/s]
 22%|██▏       | 12518/57600 [2:11:47<8:04:30,  1.55it/s]
 22%|██▏       | 12519/57600 [2:11:47<7:44:07,  1.62it/s]
 22%|██▏       | 12520/57600 [2:11:48<7:51:26,  1.59it/s]
                                                         
{'loss': 1.3036, 'learning_rate': 8.068292682926829e-07, 'epoch': 138.19}

 22%|██▏       | 12520/57600 [2:11:48<7:51:26,  1.59it/s]
 22%|██▏       | 12521/57600 [2:11:49<8:01:48,  1.56it/s]
 22%|██▏       | 12522/57600 [2:11:49<8:03:11,  1.55it/s]
 22%|██▏       | 12523/57600 [2:11:50<7:58:19,  1.57it/s]
 22%|██▏       | 12524/57600 [2:11:51<7:58:19,  1.57it/s]
 22%|██▏       | 12525/57600 [2:11:51<7:47:39,  1.61it/s]
 22%|██▏       | 12526/57600 [2:11:52<7:41:06,  1.63it/s]
 22%|██▏       | 12527/57600 [2:11:52<7:53:02,  1.59it/s]
 22%|██▏       | 12528/57600 [2:11:53<7:44:49,  1.62it/s]
 22%|██▏       | 12529/57600 [2:11:54<7:34:37,  1.65it/s]
 22%|██▏       | 12530/57600 [2:11:54<7:45:47,  1.61it/s]
 22%|██▏       | 12531/57600 [2:11:55<7:35:21,  1.65it/s]
 22%|██▏       | 12532/57600 [2:11:56<7:47:56,  1.61it/s]
 22%|██▏       | 12533/57600 [2:11:56<7:46:51,  1.61it/s]
 22%|██▏       | 12534/57600 [2:11:57<7:45:11,  1.61it/s]
 22%|██▏       | 12535/57600 [2:11:57<7:32:31,  1.66it/s]
 22%|██▏       | 12536/57600 [2:11:58<7:26:35,  1.68it/s]
 22%|██▏       | 12537/57600 [2:11:58<7:16:28,  1.72it/s]
 22%|██▏       | 12538/57600 [2:11:59<7:19:36,  1.71it/s]
 22%|██▏       | 12539/57600 [2:12:00<7:42:57,  1.62it/s]
 22%|██▏       | 12540/57600 [2:12:00<7:46:19,  1.61it/s]
                                                         
{'loss': 1.3236, 'learning_rate': 8.065156794425087e-07, 'epoch': 138.41}

 22%|██▏       | 12540/57600 [2:12:00<7:46:19,  1.61it/s]
 22%|██▏       | 12541/57600 [2:12:01<7:51:47,  1.59it/s]
 22%|██▏       | 12542/57600 [2:12:02<7:59:25,  1.57it/s]
 22%|██▏       | 12543/57600 [2:12:02<7:42:31,  1.62it/s]
 22%|██▏       | 12544/57600 [2:12:03<7:53:08,  1.59it/s]
 22%|██▏       | 12545/57600 [2:12:03<7:45:50,  1.61it/s]
 22%|██▏       | 12546/57600 [2:12:04<7:43:04,  1.62it/s]
 22%|██▏       | 12547/57600 [2:12:05<7:37:57,  1.64it/s]
 22%|██▏       | 12548/57600 [2:12:05<7:34:24,  1.65it/s]
 22%|██▏       | 12549/57600 [2:12:06<8:00:14,  1.56it/s]
 22%|██▏       | 12550/57600 [2:12:07<8:07:18,  1.54it/s]
 22%|██▏       | 12551/57600 [2:12:07<7:50:30,  1.60it/s]
 22%|██▏       | 12552/57600 [2:12:08<7:58:45,  1.57it/s]
 22%|██▏       | 12553/57600 [2:12:09<7:54:32,  1.58it/s]
 22%|██▏       | 12554/57600 [2:12:09<7:38:31,  1.64it/s]
 22%|██▏       | 12555/57600 [2:12:10<7:38:39,  1.64it/s]
 22%|██▏       | 12556/57600 [2:12:10<7:48:17,  1.60it/s]
 22%|██▏       | 12557/57600 [2:12:11<7:35:48,  1.65it/s]
 22%|██▏       | 12558/57600 [2:12:12<7:38:25,  1.64it/s]
 22%|██▏       | 12559/57600 [2:12:12<7:45:42,  1.61it/s]
 22%|██▏       | 12560/57600 [2:12:13<7:44:20,  1.62it/s]
                                                         
{'loss': 1.2922, 'learning_rate': 8.062020905923344e-07, 'epoch': 138.63}

 22%|██▏       | 12560/57600 [2:12:13<7:44:20,  1.62it/s]
 22%|██▏       | 12561/57600 [2:12:13<7:39:17,  1.63it/s]
 22%|██▏       | 12562/57600 [2:12:14<7:28:16,  1.67it/s]
 22%|██▏       | 12563/57600 [2:12:15<7:25:05,  1.69it/s]
 22%|██▏       | 12564/57600 [2:12:15<7:08:45,  1.75it/s]
 22%|██▏       | 12565/57600 [2:12:16<7:08:52,  1.75it/s]
 22%|██▏       | 12566/57600 [2:12:16<7:19:20,  1.71it/s]
 22%|██▏       | 12567/57600 [2:12:17<7:40:49,  1.63it/s]
 22%|██▏       | 12568/57600 [2:12:18<7:33:25,  1.66it/s]
 22%|██▏       | 12569/57600 [2:12:18<7:52:17,  1.59it/s]
 22%|██▏       | 12570/57600 [2:12:19<7:46:55,  1.61it/s]
 22%|██▏       | 12571/57600 [2:12:19<7:50:12,  1.60it/s]
 22%|██▏       | 12572/57600 [2:12:20<7:37:06,  1.64it/s]
 22%|██▏       | 12573/57600 [2:12:21<7:25:48,  1.68it/s]
 22%|██▏       | 12574/57600 [2:12:21<7:11:43,  1.74it/s]
 22%|██▏       | 12575/57600 [2:12:22<7:24:15,  1.69it/s]
 22%|██▏       | 12576/57600 [2:12:22<7:23:08,  1.69it/s]
 22%|██▏       | 12577/57600 [2:12:23<7:26:17,  1.68it/s]
 22%|██▏       | 12578/57600 [2:12:24<7:39:44,  1.63it/s]
 22%|██▏       | 12579/57600 [2:12:24<7:45:06,  1.61it/s]
 22%|██▏       | 12580/57600 [2:12:25<7:49:53,  1.60it/s]
                                                         
{'loss': 1.3773, 'learning_rate': 8.058885017421603e-07, 'epoch': 138.85}

 22%|██▏       | 12580/57600 [2:12:25<7:49:53,  1.60it/s]
 22%|██▏       | 12581/57600 [2:12:25<7:38:41,  1.64it/s]
 22%|██▏       | 12582/57600 [2:12:26<7:35:29,  1.65it/s]
 22%|██▏       | 12583/57600 [2:12:27<7:39:43,  1.63it/s]
 22%|██▏       | 12584/57600 [2:12:27<7:24:41,  1.69it/s]
 22%|██▏       | 12585/57600 [2:12:28<7:17:18,  1.72it/s]
 22%|██▏       | 12586/57600 [2:12:28<7:21:52,  1.70it/s]
 22%|██▏       | 12587/57600 [2:12:29<7:26:23,  1.68it/s]
 22%|██▏       | 12588/57600 [2:12:30<7:23:39,  1.69it/s]
 22%|██▏       | 12589/57600 [2:12:30<7:35:44,  1.65it/s]
 22%|██▏       | 12590/57600 [2:12:31<7:30:35,  1.66it/s]
 22%|██▏       | 12591/57600 [2:12:31<7:33:50,  1.65it/s]
 22%|██▏       | 12592/57600 [2:12:32<7:37:53,  1.64it/s]
 22%|██▏       | 12593/57600 [2:12:33<7:46:23,  1.61it/s]
 22%|██▏       | 12594/57600 [2:12:33<8:02:57,  1.55it/s]
 22%|██▏       | 12595/57600 [2:12:34<8:00:05,  1.56it/s]
 22%|██▏       | 12596/57600 [2:12:35<7:47:40,  1.60it/s]
 22%|██▏       | 12597/57600 [2:12:35<7:41:22,  1.63it/s]
 22%|██▏       | 12598/57600 [2:12:36<7:59:44,  1.56it/s]
 22%|██▏       | 12599/57600 [2:12:36<7:46:47,  1.61it/s]
 22%|██▏       | 12600/57600 [2:12:37<7:46:13,  1.61it/s]
                                                         
{'loss': 1.3378, 'learning_rate': 8.055749128919861e-07, 'epoch': 139.07}

 22%|██▏       | 12600/57600 [2:12:37<7:46:13,  1.61it/s]
 22%|██▏       | 12601/57600 [2:12:38<7:48:34,  1.60it/s]
 22%|██▏       | 12602/57600 [2:12:38<7:44:37,  1.61it/s]
 22%|██▏       | 12603/57600 [2:12:39<7:36:20,  1.64it/s]
 22%|██▏       | 12604/57600 [2:12:39<7:31:55,  1.66it/s]
 22%|██▏       | 12605/57600 [2:12:40<7:28:03,  1.67it/s]
 22%|██▏       | 12606/57600 [2:12:41<7:41:51,  1.62it/s]
 22%|██▏       | 12607/57600 [2:12:41<7:56:22,  1.57it/s]
 22%|██▏       | 12608/57600 [2:12:42<7:42:54,  1.62it/s]
 22%|██▏       | 12609/57600 [2:12:43<7:43:45,  1.62it/s]
 22%|██▏       | 12610/57600 [2:12:43<7:30:04,  1.67it/s]
 22%|██▏       | 12611/57600 [2:12:44<7:28:20,  1.67it/s]
 22%|██▏       | 12612/57600 [2:12:44<7:24:15,  1.69it/s]
 22%|██▏       | 12613/57600 [2:12:45<7:32:43,  1.66it/s]
 22%|██▏       | 12614/57600 [2:12:46<7:27:02,  1.68it/s]
 22%|██▏       | 12615/57600 [2:12:46<7:21:51,  1.70it/s]
 22%|██▏       | 12616/57600 [2:12:47<7:34:45,  1.65it/s]
 22%|██▏       | 12617/57600 [2:12:47<7:33:49,  1.65it/s]
 22%|██▏       | 12618/57600 [2:12:48<7:25:55,  1.68it/s]
 22%|██▏       | 12619/57600 [2:12:49<7:31:33,  1.66it/s]
 22%|██▏       | 12620/57600 [2:12:49<7:29:43,  1.67it/s]
                                                         
{'loss': 1.3817, 'learning_rate': 8.052613240418117e-07, 'epoch': 139.29}

 22%|██▏       | 12620/57600 [2:12:49<7:29:43,  1.67it/s]
 22%|██▏       | 12621/57600 [2:12:50<7:57:14,  1.57it/s]
 22%|██▏       | 12622/57600 [2:12:51<8:01:02,  1.56it/s]
 22%|██▏       | 12623/57600 [2:12:51<7:39:04,  1.63it/s]
 22%|██▏       | 12624/57600 [2:12:52<7:30:28,  1.66it/s]
 22%|██▏       | 12625/57600 [2:12:52<7:55:54,  1.58it/s]
 22%|██▏       | 12626/57600 [2:12:53<7:55:08,  1.58it/s]
 22%|██▏       | 12627/57600 [2:12:54<7:39:23,  1.63it/s]
 22%|██▏       | 12628/57600 [2:12:54<7:35:17,  1.65it/s]
 22%|██▏       | 12629/57600 [2:12:55<7:27:54,  1.67it/s]
 22%|██▏       | 12630/57600 [2:12:55<7:30:06,  1.67it/s]
 22%|██▏       | 12631/57600 [2:12:56<7:56:05,  1.57it/s]
 22%|██▏       | 12632/57600 [2:12:57<7:49:31,  1.60it/s]
 22%|██▏       | 12633/57600 [2:12:57<7:43:50,  1.62it/s]
 22%|██▏       | 12634/57600 [2:12:58<7:35:36,  1.64it/s]
 22%|██▏       | 12635/57600 [2:12:58<7:33:56,  1.65it/s]
 22%|██▏       | 12636/57600 [2:12:59<7:25:39,  1.68it/s]
 22%|██▏       | 12637/57600 [2:13:00<7:23:24,  1.69it/s]
 22%|██▏       | 12638/57600 [2:13:00<7:28:32,  1.67it/s]
 22%|██▏       | 12639/57600 [2:13:01<7:31:51,  1.66it/s]
 22%|██▏       | 12640/57600 [2:13:02<7:52:17,  1.59it/s]
                                                         
{'loss': 1.3296, 'learning_rate': 8.049477351916376e-07, 'epoch': 139.51}

 22%|██▏       | 12640/57600 [2:13:02<7:52:17,  1.59it/s]
 22%|██▏       | 12641/57600 [2:13:02<7:50:40,  1.59it/s]
 22%|██▏       | 12642/57600 [2:13:03<7:46:00,  1.61it/s]
 22%|██▏       | 12643/57600 [2:13:03<7:42:16,  1.62it/s]
 22%|██▏       | 12644/57600 [2:13:04<7:51:20,  1.59it/s]
 22%|██▏       | 12645/57600 [2:13:05<8:09:58,  1.53it/s]
 22%|██▏       | 12646/57600 [2:13:05<8:00:35,  1.56it/s]
 22%|██▏       | 12647/57600 [2:13:06<7:50:11,  1.59it/s]
 22%|██▏       | 12648/57600 [2:13:07<8:02:46,  1.55it/s]
 22%|██▏       | 12649/57600 [2:13:07<7:47:23,  1.60it/s]
 22%|██▏       | 12650/57600 [2:13:08<7:37:19,  1.64it/s]
 22%|██▏       | 12651/57600 [2:13:08<7:24:08,  1.69it/s]
 22%|██▏       | 12652/57600 [2:13:09<7:30:00,  1.66it/s]
 22%|██▏       | 12653/57600 [2:13:10<7:34:49,  1.65it/s]
 22%|██▏       | 12654/57600 [2:13:10<7:18:43,  1.71it/s]
 22%|██▏       | 12655/57600 [2:13:11<7:42:15,  1.62it/s]
 22%|██▏       | 12656/57600 [2:13:11<7:51:04,  1.59it/s]
 22%|██▏       | 12657/57600 [2:13:12<7:44:00,  1.61it/s]
 22%|██▏       | 12658/57600 [2:13:13<7:36:40,  1.64it/s]
 22%|██▏       | 12659/57600 [2:13:13<7:31:13,  1.66it/s]
 22%|██▏       | 12660/57600 [2:13:14<7:47:56,  1.60it/s]
                                                         
{'loss': 1.311, 'learning_rate': 8.046341463414634e-07, 'epoch': 139.74}

 22%|██▏       | 12660/57600 [2:13:14<7:47:56,  1.60it/s]
 22%|██▏       | 12661/57600 [2:13:15<7:58:17,  1.57it/s]
 22%|██▏       | 12662/57600 [2:13:15<7:38:47,  1.63it/s]
 22%|██▏       | 12663/57600 [2:13:16<7:40:14,  1.63it/s]
 22%|██▏       | 12664/57600 [2:13:16<7:25:52,  1.68it/s]
 22%|██▏       | 12665/57600 [2:13:17<7:19:21,  1.70it/s]
 22%|██▏       | 12666/57600 [2:13:17<7:32:37,  1.65it/s]
 22%|██▏       | 12667/57600 [2:13:18<7:46:34,  1.61it/s]
 22%|██▏       | 12668/57600 [2:13:19<7:33:52,  1.65it/s]
 22%|██▏       | 12669/57600 [2:13:19<7:38:07,  1.63it/s]
 22%|██▏       | 12670/57600 [2:13:20<7:42:31,  1.62it/s]
 22%|██▏       | 12671/57600 [2:13:21<7:56:53,  1.57it/s]
 22%|██▏       | 12672/57600 [2:13:21<7:52:08,  1.59it/s]
 22%|██▏       | 12673/57600 [2:13:22<7:51:45,  1.59it/s]
 22%|██▏       | 12674/57600 [2:13:23<7:42:28,  1.62it/s]
 22%|██▏       | 12675/57600 [2:13:23<8:04:27,  1.55it/s]
 22%|██▏       | 12676/57600 [2:13:24<8:00:25,  1.56it/s]
 22%|██▏       | 12677/57600 [2:13:24<7:47:15,  1.60it/s]
 22%|██▏       | 12678/57600 [2:13:25<7:43:22,  1.62it/s]
 22%|██▏       | 12679/57600 [2:13:26<7:49:34,  1.59it/s]
 22%|██▏       | 12680/57600 [2:13:26<7:47:40,  1.60it/s]
                                                         
{'loss': 1.3402, 'learning_rate': 8.043205574912892e-07, 'epoch': 139.96}

 22%|██▏       | 12680/57600 [2:13:26<7:47:40,  1.60it/s]
 22%|██▏       | 12681/57600 [2:13:27<7:52:38,  1.58it/s]
 22%|██▏       | 12682/57600 [2:13:28<7:39:23,  1.63it/s]
 22%|██▏       | 12683/57600 [2:13:28<7:34:18,  1.65it/s]
 22%|██▏       | 12684/57600 [2:13:29<7:31:36,  1.66it/s]
 22%|██▏       | 12685/57600 [2:13:29<8:11:44,  1.52it/s]
 22%|██▏       | 12686/57600 [2:13:30<7:49:00,  1.60it/s]
 22%|██▏       | 12687/57600 [2:13:31<7:46:03,  1.61it/s]
 22%|██▏       | 12688/57600 [2:13:31<7:37:11,  1.64it/s]
 22%|██▏       | 12689/57600 [2:13:32<7:43:53,  1.61it/s]
 22%|██▏       | 12690/57600 [2:13:33<7:46:17,  1.61it/s]
 22%|██▏       | 12691/57600 [2:13:33<7:43:35,  1.61it/s]
 22%|██▏       | 12692/57600 [2:13:34<7:37:06,  1.64it/s]
 22%|██▏       | 12693/57600 [2:13:34<7:35:16,  1.64it/s]
 22%|██▏       | 12694/57600 [2:13:35<7:25:53,  1.68it/s]
 22%|██▏       | 12695/57600 [2:13:36<7:46:07,  1.61it/s]
 22%|██▏       | 12696/57600 [2:13:36<7:44:49,  1.61it/s]
 22%|██▏       | 12697/57600 [2:13:37<7:36:07,  1.64it/s]
 22%|██▏       | 12698/57600 [2:13:37<7:41:42,  1.62it/s]
 22%|██▏       | 12699/57600 [2:13:38<7:40:48,  1.62it/s]
 22%|██▏       | 12700/57600 [2:13:39<7:41:29,  1.62it/s]
                                                         
{'loss': 1.3487, 'learning_rate': 8.040069686411149e-07, 'epoch': 140.18}

 22%|██▏       | 12700/57600 [2:13:39<7:41:29,  1.62it/s]
 22%|██▏       | 12701/57600 [2:13:39<7:45:45,  1.61it/s]
 22%|██▏       | 12702/57600 [2:13:40<7:43:02,  1.62it/s]
 22%|██▏       | 12703/57600 [2:13:40<7:36:47,  1.64it/s]
 22%|██▏       | 12704/57600 [2:13:41<7:27:47,  1.67it/s]
 22%|██▏       | 12705/57600 [2:13:42<7:42:47,  1.62it/s]
 22%|██▏       | 12706/57600 [2:13:42<7:52:25,  1.58it/s]
 22%|██▏       | 12707/57600 [2:13:43<7:58:46,  1.56it/s]
 22%|██▏       | 12708/57600 [2:13:44<7:47:33,  1.60it/s]
 22%|██▏       | 12709/57600 [2:13:44<7:42:14,  1.62it/s]
 22%|██▏       | 12710/57600 [2:13:45<7:43:36,  1.61it/s]
 22%|██▏       | 12711/57600 [2:13:45<7:31:29,  1.66it/s]
 22%|██▏       | 12712/57600 [2:13:46<7:32:37,  1.65it/s]
 22%|██▏       | 12713/57600 [2:13:47<7:30:19,  1.66it/s]
 22%|██▏       | 12714/57600 [2:13:47<7:26:37,  1.68it/s]
 22%|██▏       | 12715/57600 [2:13:48<7:22:54,  1.69it/s]
 22%|██▏       | 12716/57600 [2:13:48<7:29:14,  1.67it/s]
 22%|██▏       | 12717/57600 [2:13:49<7:49:36,  1.59it/s]
 22%|██▏       | 12718/57600 [2:13:50<7:42:57,  1.62it/s]
 22%|██▏       | 12719/57600 [2:13:50<7:40:12,  1.63it/s]
 22%|██▏       | 12720/57600 [2:13:51<7:45:05,  1.61it/s]
                                                         
{'loss': 1.3242, 'learning_rate': 8.036933797909408e-07, 'epoch': 140.4}

 22%|██▏       | 12720/57600 [2:13:51<7:45:05,  1.61it/s]
 22%|██▏       | 12721/57600 [2:13:52<7:48:37,  1.60it/s]
 22%|██▏       | 12722/57600 [2:13:52<7:36:35,  1.64it/s]
 22%|██▏       | 12723/57600 [2:13:53<7:24:28,  1.68it/s]
 22%|██▏       | 12724/57600 [2:13:53<7:34:34,  1.65it/s]
 22%|██▏       | 12725/57600 [2:13:54<7:25:47,  1.68it/s]
 22%|██▏       | 12726/57600 [2:13:54<7:17:13,  1.71it/s]
 22%|██▏       | 12727/57600 [2:13:55<7:23:59,  1.68it/s]
 22%|██▏       | 12728/57600 [2:13:56<7:27:36,  1.67it/s]
 22%|██▏       | 12729/57600 [2:13:56<7:37:15,  1.64it/s]
 22%|██▏       | 12730/57600 [2:13:57<7:32:56,  1.65it/s]
 22%|██▏       | 12731/57600 [2:13:58<7:42:16,  1.62it/s]
 22%|██▏       | 12732/57600 [2:13:58<7:32:19,  1.65it/s]
 22%|██▏       | 12733/57600 [2:13:59<7:31:08,  1.66it/s]
 22%|██▏       | 12734/57600 [2:13:59<7:26:32,  1.67it/s]
 22%|██▏       | 12735/57600 [2:14:00<7:34:53,  1.64it/s]
 22%|██▏       | 12736/57600 [2:14:01<7:42:10,  1.62it/s]
 22%|██▏       | 12737/57600 [2:14:01<7:25:54,  1.68it/s]
 22%|██▏       | 12738/57600 [2:14:02<7:28:29,  1.67it/s]
 22%|██▏       | 12739/57600 [2:14:02<7:38:00,  1.63it/s]
 22%|██▏       | 12740/57600 [2:14:03<7:58:25,  1.56it/s]
                                                         
{'loss': 1.3486, 'learning_rate': 8.033797909407665e-07, 'epoch': 140.62}

 22%|██▏       | 12740/57600 [2:14:03<7:58:25,  1.56it/s]
 22%|██▏       | 12741/57600 [2:14:04<7:34:02,  1.65it/s]
 22%|██▏       | 12742/57600 [2:14:04<7:51:07,  1.59it/s]
 22%|██▏       | 12743/57600 [2:14:05<7:43:56,  1.61it/s]
 22%|██▏       | 12744/57600 [2:14:05<7:28:47,  1.67it/s]
 22%|██▏       | 12745/57600 [2:14:06<8:02:18,  1.55it/s]
 22%|██▏       | 12746/57600 [2:14:07<8:00:59,  1.55it/s]
 22%|██▏       | 12747/57600 [2:14:07<7:55:51,  1.57it/s]
 22%|██▏       | 12748/57600 [2:14:08<7:42:15,  1.62it/s]
 22%|██▏       | 12749/57600 [2:14:09<7:52:50,  1.58it/s]
 22%|██▏       | 12750/57600 [2:14:09<7:58:42,  1.56it/s]
 22%|██▏       | 12751/57600 [2:14:10<7:58:54,  1.56it/s]
 22%|██▏       | 12752/57600 [2:14:11<7:51:01,  1.59it/s]
 22%|██▏       | 12753/57600 [2:14:11<7:46:42,  1.60it/s]
 22%|██▏       | 12754/57600 [2:14:12<8:06:00,  1.54it/s]
 22%|██▏       | 12755/57600 [2:14:12<7:43:55,  1.61it/s]
 22%|██▏       | 12756/57600 [2:14:13<7:35:36,  1.64it/s]
 22%|██▏       | 12757/57600 [2:14:14<7:48:34,  1.59it/s]
 22%|██▏       | 12758/57600 [2:14:14<7:49:13,  1.59it/s]
 22%|██▏       | 12759/57600 [2:14:15<7:38:41,  1.63it/s]
 22%|██▏       | 12760/57600 [2:14:16<7:35:29,  1.64it/s]
                                                         
{'loss': 1.3231, 'learning_rate': 8.030662020905923e-07, 'epoch': 140.84}

 22%|██▏       | 12760/57600 [2:14:16<7:35:29,  1.64it/s]
 22%|██▏       | 12761/57600 [2:14:16<7:34:36,  1.64it/s]
 22%|██▏       | 12762/57600 [2:14:17<7:21:31,  1.69it/s]
 22%|██▏       | 12763/57600 [2:14:17<7:22:23,  1.69it/s]
 22%|██▏       | 12764/57600 [2:14:18<7:41:28,  1.62it/s]
 22%|██▏       | 12765/57600 [2:14:19<7:36:39,  1.64it/s]
 22%|██▏       | 12766/57600 [2:14:19<7:27:39,  1.67it/s]
 22%|██▏       | 12767/57600 [2:14:20<7:42:49,  1.61it/s]
 22%|██▏       | 12768/57600 [2:14:20<7:48:47,  1.59it/s]
 22%|██▏       | 12769/57600 [2:14:21<7:57:59,  1.56it/s]
 22%|██▏       | 12770/57600 [2:14:22<7:50:36,  1.59it/s]
 22%|██▏       | 12771/57600 [2:14:22<7:45:15,  1.61it/s]
 22%|██▏       | 12772/57600 [2:14:23<7:40:43,  1.62it/s]
 22%|██▏       | 12773/57600 [2:14:24<7:40:47,  1.62it/s]
 22%|██▏       | 12774/57600 [2:14:24<7:49:09,  1.59it/s]
 22%|██▏       | 12775/57600 [2:14:25<8:01:23,  1.55it/s]
 22%|██▏       | 12776/57600 [2:14:26<7:54:09,  1.58it/s]
 22%|██▏       | 12777/57600 [2:14:26<8:00:20,  1.56it/s]
 22%|██▏       | 12778/57600 [2:14:27<7:48:40,  1.59it/s]
 22%|██▏       | 12779/57600 [2:14:27<7:30:32,  1.66it/s]
 22%|██▏       | 12780/57600 [2:14:28<7:39:16,  1.63it/s]
                                                         
{'loss': 1.3466, 'learning_rate': 8.02752613240418e-07, 'epoch': 141.06}

 22%|██▏       | 12780/57600 [2:14:28<7:39:16,  1.63it/s]
 22%|██▏       | 12781/57600 [2:14:29<7:39:03,  1.63it/s]
 22%|██▏       | 12782/57600 [2:14:29<7:44:48,  1.61it/s]
 22%|██▏       | 12783/57600 [2:14:30<8:25:18,  1.48it/s]
 22%|██▏       | 12784/57600 [2:14:31<8:11:07,  1.52it/s]
 22%|██▏       | 12785/57600 [2:14:31<7:52:20,  1.58it/s]
 22%|██▏       | 12786/57600 [2:14:32<7:36:24,  1.64it/s]
 22%|██▏       | 12787/57600 [2:14:32<7:35:03,  1.64it/s]
 22%|██▏       | 12788/57600 [2:14:33<7:36:32,  1.64it/s]
 22%|██▏       | 12789/57600 [2:14:34<7:29:37,  1.66it/s]
 22%|██▏       | 12790/57600 [2:14:34<7:16:44,  1.71it/s]
 22%|██▏       | 12791/57600 [2:14:35<7:20:46,  1.69it/s]
 22%|██▏       | 12792/57600 [2:14:35<7:25:09,  1.68it/s]
 22%|██▏       | 12793/57600 [2:14:36<7:38:07,  1.63it/s]
 22%|██▏       | 12794/57600 [2:14:37<7:37:56,  1.63it/s]
 22%|██▏       | 12795/57600 [2:14:37<7:43:42,  1.61it/s]
 22%|██▏       | 12796/57600 [2:14:38<7:31:24,  1.65it/s]
 22%|██▏       | 12797/57600 [2:14:38<7:35:28,  1.64it/s]
 22%|██▏       | 12798/57600 [2:14:39<7:47:02,  1.60it/s]
 22%|██▏       | 12799/57600 [2:14:40<7:52:00,  1.58it/s]
 22%|██▏       | 12800/57600 [2:14:40<7:49:35,  1.59it/s]
                                                         
{'loss': 1.3044, 'learning_rate': 8.024390243902439e-07, 'epoch': 141.28}

 22%|██▏       | 12800/57600 [2:14:40<7:49:35,  1.59it/s]
 22%|██▏       | 12801/57600 [2:14:41<7:44:48,  1.61it/s]
 22%|██▏       | 12802/57600 [2:14:42<7:32:10,  1.65it/s]
 22%|██▏       | 12803/57600 [2:14:42<7:55:36,  1.57it/s]
 22%|██▏       | 12804/57600 [2:14:43<7:51:03,  1.58it/s]
 22%|██▏       | 12805/57600 [2:14:43<7:34:47,  1.64it/s]
 22%|██▏       | 12806/57600 [2:14:44<7:26:44,  1.67it/s]
 22%|██▏       | 12807/57600 [2:14:45<7:20:16,  1.70it/s]
 22%|██▏       | 12808/57600 [2:14:45<7:59:29,  1.56it/s]
 22%|██▏       | 12809/57600 [2:14:46<7:58:50,  1.56it/s]
 22%|██▏       | 12810/57600 [2:14:47<7:46:11,  1.60it/s]
 22%|██▏       | 12811/57600 [2:14:47<7:36:42,  1.63it/s]
 22%|██▏       | 12812/57600 [2:14:48<7:53:18,  1.58it/s]
 22%|██▏       | 12813/57600 [2:14:48<8:03:16,  1.54it/s]
 22%|██▏       | 12814/57600 [2:14:49<8:01:02,  1.55it/s]
 22%|██▏       | 12815/57600 [2:14:50<7:55:56,  1.57it/s]
 22%|██▏       | 12816/57600 [2:14:50<7:39:53,  1.62it/s]
 22%|██▏       | 12817/57600 [2:14:51<7:47:48,  1.60it/s]
 22%|██▏       | 12818/57600 [2:14:52<7:32:58,  1.65it/s]
 22%|██▏       | 12819/57600 [2:14:52<7:44:42,  1.61it/s]
 22%|██▏       | 12820/57600 [2:14:53<7:28:45,  1.66it/s]
                                                         
{'loss': 1.3127, 'learning_rate': 8.021254355400696e-07, 'epoch': 141.5}

 22%|██▏       | 12820/57600 [2:14:53<7:28:45,  1.66it/s]
 22%|██▏       | 12821/57600 [2:14:53<7:12:45,  1.72it/s]
 22%|██▏       | 12822/57600 [2:14:54<7:14:20,  1.72it/s]
 22%|██▏       | 12823/57600 [2:14:54<7:14:57,  1.72it/s]
 22%|██▏       | 12824/57600 [2:14:55<7:44:54,  1.61it/s]
 22%|██▏       | 12825/57600 [2:14:56<7:54:10,  1.57it/s]
 22%|██▏       | 12826/57600 [2:14:56<7:51:22,  1.58it/s]
 22%|██▏       | 12827/57600 [2:14:57<7:50:48,  1.58it/s]
 22%|██▏       | 12828/57600 [2:14:58<7:56:26,  1.57it/s]
 22%|██▏       | 12829/57600 [2:14:58<7:54:13,  1.57it/s]
 22%|██▏       | 12830/57600 [2:14:59<8:00:35,  1.55it/s]
 22%|██▏       | 12831/57600 [2:15:00<8:08:19,  1.53it/s]
 22%|██▏       | 12832/57600 [2:15:00<7:59:36,  1.56it/s]
 22%|██▏       | 12833/57600 [2:15:01<7:50:58,  1.58it/s]
 22%|██▏       | 12834/57600 [2:15:02<7:55:13,  1.57it/s]
 22%|██▏       | 12835/57600 [2:15:02<7:41:52,  1.62it/s]
 22%|██▏       | 12836/57600 [2:15:03<7:35:03,  1.64it/s]
 22%|██▏       | 12837/57600 [2:15:03<7:29:28,  1.66it/s]
 22%|██▏       | 12838/57600 [2:15:04<7:29:05,  1.66it/s]
 22%|██▏       | 12839/57600 [2:15:04<7:20:04,  1.70it/s]
 22%|██▏       | 12840/57600 [2:15:05<7:25:42,  1.67it/s]
                                                         
{'loss': 1.3426, 'learning_rate': 8.018118466898954e-07, 'epoch': 141.72}

 22%|██▏       | 12840/57600 [2:15:05<7:25:42,  1.67it/s]
 22%|██▏       | 12841/57600 [2:15:06<7:37:07,  1.63it/s]
 22%|██▏       | 12842/57600 [2:15:06<7:40:50,  1.62it/s]
 22%|██▏       | 12843/57600 [2:15:07<7:24:48,  1.68it/s]
 22%|██▏       | 12844/57600 [2:15:07<7:17:42,  1.70it/s]
 22%|██▏       | 12845/57600 [2:15:08<7:15:38,  1.71it/s]
 22%|██▏       | 12846/57600 [2:15:09<7:24:36,  1.68it/s]
 22%|██▏       | 12847/57600 [2:15:09<7:15:45,  1.71it/s]
 22%|██▏       | 12848/57600 [2:15:10<7:14:33,  1.72it/s]
 22%|██▏       | 12849/57600 [2:15:10<7:18:39,  1.70it/s]
 22%|██▏       | 12850/57600 [2:15:11<7:23:25,  1.68it/s]
 22%|██▏       | 12851/57600 [2:15:12<7:14:50,  1.72it/s]
 22%|██▏       | 12852/57600 [2:15:12<7:32:58,  1.65it/s]
 22%|██▏       | 12853/57600 [2:15:13<7:20:11,  1.69it/s]
 22%|██▏       | 12854/57600 [2:15:13<7:09:17,  1.74it/s]
 22%|██▏       | 12855/57600 [2:15:14<7:23:35,  1.68it/s]
 22%|██▏       | 12856/57600 [2:15:15<7:32:53,  1.65it/s]
 22%|██▏       | 12857/57600 [2:15:15<7:42:07,  1.61it/s]
 22%|██▏       | 12858/57600 [2:15:16<7:51:45,  1.58it/s]
 22%|██▏       | 12859/57600 [2:15:17<7:46:13,  1.60it/s]
 22%|██▏       | 12860/57600 [2:15:17<7:48:35,  1.59it/s]
                                                         
{'loss': 1.3484, 'learning_rate': 8.014982578397213e-07, 'epoch': 141.94}

 22%|██▏       | 12860/57600 [2:15:17<7:48:35,  1.59it/s]
 22%|██▏       | 12861/57600 [2:15:18<7:49:47,  1.59it/s]
 22%|██▏       | 12862/57600 [2:15:18<7:45:31,  1.60it/s]
 22%|██▏       | 12863/57600 [2:15:19<7:26:21,  1.67it/s]
 22%|██▏       | 12864/57600 [2:15:20<7:22:05,  1.69it/s]
 22%|██▏       | 12865/57600 [2:15:20<7:25:09,  1.67it/s]
 22%|██▏       | 12866/57600 [2:15:21<7:43:02,  1.61it/s]
 22%|██▏       | 12867/57600 [2:15:21<7:47:46,  1.59it/s]
 22%|██▏       | 12868/57600 [2:15:22<7:34:33,  1.64it/s]
 22%|██▏       | 12869/57600 [2:15:23<7:39:39,  1.62it/s]
 22%|██▏       | 12870/57600 [2:15:23<7:36:31,  1.63it/s]
 22%|██▏       | 12871/57600 [2:15:24<7:35:26,  1.64it/s]
 22%|██▏       | 12872/57600 [2:15:25<7:59:21,  1.56it/s]
 22%|██▏       | 12873/57600 [2:15:25<7:52:54,  1.58it/s]
 22%|██▏       | 12874/57600 [2:15:26<7:47:05,  1.60it/s]
 22%|██▏       | 12875/57600 [2:15:26<7:41:12,  1.62it/s]
 22%|██▏       | 12876/57600 [2:15:27<7:47:17,  1.60it/s]
 22%|██▏       | 12877/57600 [2:15:28<7:53:47,  1.57it/s]
 22%|██▏       | 12878/57600 [2:15:28<7:52:58,  1.58it/s]
 22%|██▏       | 12879/57600 [2:15:29<7:48:12,  1.59it/s]
 22%|██▏       | 12880/57600 [2:15:30<7:33:34,  1.64it/s]
                                                         
{'loss': 1.3492, 'learning_rate': 8.011846689895469e-07, 'epoch': 142.16}

 22%|██▏       | 12880/57600 [2:15:30<7:33:34,  1.64it/s]
 22%|██▏       | 12881/57600 [2:15:30<7:45:22,  1.60it/s]
 22%|██▏       | 12882/57600 [2:15:31<7:59:24,  1.55it/s]
 22%|██▏       | 12883/57600 [2:15:32<8:04:57,  1.54it/s]
 22%|██▏       | 12884/57600 [2:15:32<7:49:06,  1.59it/s]
 22%|██▏       | 12885/57600 [2:15:33<7:52:53,  1.58it/s]
 22%|██▏       | 12886/57600 [2:15:33<7:37:25,  1.63it/s]
 22%|██▏       | 12887/57600 [2:15:34<7:29:35,  1.66it/s]
 22%|██▏       | 12888/57600 [2:15:34<7:19:51,  1.69it/s]
 22%|██▏       | 12889/57600 [2:15:35<7:37:23,  1.63it/s]
 22%|██▏       | 12890/57600 [2:15:36<7:40:00,  1.62it/s]
 22%|██▏       | 12891/57600 [2:15:36<8:04:49,  1.54it/s]
 22%|██▏       | 12892/57600 [2:15:37<8:06:09,  1.53it/s]
 22%|██▏       | 12893/57600 [2:15:38<8:01:13,  1.55it/s]
 22%|██▏       | 12894/57600 [2:15:38<7:43:33,  1.61it/s]
 22%|██▏       | 12895/57600 [2:15:39<7:27:07,  1.67it/s]
 22%|██▏       | 12896/57600 [2:15:39<7:23:46,  1.68it/s]
 22%|██▏       | 12897/57600 [2:15:40<7:23:09,  1.68it/s]
 22%|██▏       | 12898/57600 [2:15:41<7:18:32,  1.70it/s]
 22%|██▏       | 12899/57600 [2:15:41<7:14:10,  1.72it/s]
 22%|██▏       | 12900/57600 [2:15:42<7:25:37,  1.67it/s]
                                                         
{'loss': 1.3381, 'learning_rate': 8.008710801393729e-07, 'epoch': 142.38}

 22%|██▏       | 12900/57600 [2:15:42<7:25:37,  1.67it/s]
 22%|██▏       | 12901/57600 [2:15:42<7:30:19,  1.65it/s]
 22%|██▏       | 12902/57600 [2:15:43<7:41:48,  1.61it/s]
 22%|██▏       | 12903/57600 [2:15:44<7:27:42,  1.66it/s]
 22%|██▏       | 12904/57600 [2:15:44<7:19:02,  1.70it/s]
 22%|██▏       | 12905/57600 [2:15:45<7:30:13,  1.65it/s]
 22%|██▏       | 12906/57600 [2:15:46<7:45:51,  1.60it/s]
 22%|██▏       | 12907/57600 [2:15:46<7:49:44,  1.59it/s]
 22%|██▏       | 12908/57600 [2:15:47<8:09:49,  1.52it/s]
 22%|██▏       | 12909/57600 [2:15:47<7:47:53,  1.59it/s]
 22%|██▏       | 12910/57600 [2:15:48<7:51:44,  1.58it/s]
 22%|██▏       | 12911/57600 [2:15:49<7:48:04,  1.59it/s]
 22%|██▏       | 12912/57600 [2:15:49<7:40:33,  1.62it/s]
 22%|██▏       | 12913/57600 [2:15:50<7:41:08,  1.62it/s]
 22%|██▏       | 12914/57600 [2:15:51<7:32:40,  1.65it/s]
 22%|██▏       | 12915/57600 [2:15:51<7:22:18,  1.68it/s]
 22%|██▏       | 12916/57600 [2:15:52<7:28:51,  1.66it/s]
 22%|██▏       | 12917/57600 [2:15:52<7:27:56,  1.66it/s]
 22%|██▏       | 12918/57600 [2:15:53<7:26:41,  1.67it/s]
 22%|██▏       | 12919/57600 [2:15:54<7:24:35,  1.67it/s]
 22%|██▏       | 12920/57600 [2:15:54<7:29:45,  1.66it/s]
                                                         
{'loss': 1.3326, 'learning_rate': 8.005574912891985e-07, 'epoch': 142.6}

 22%|██▏       | 12920/57600 [2:15:54<7:29:45,  1.66it/s]
 22%|██▏       | 12921/57600 [2:15:55<7:44:40,  1.60it/s]
 22%|██▏       | 12922/57600 [2:15:55<7:51:41,  1.58it/s]
 22%|██▏       | 12923/57600 [2:15:56<8:01:06,  1.55it/s]
 22%|██▏       | 12924/57600 [2:15:57<7:50:38,  1.58it/s]
 22%|██▏       | 12925/57600 [2:15:57<7:49:00,  1.59it/s]
 22%|██▏       | 12926/57600 [2:15:58<7:50:57,  1.58it/s]
 22%|██▏       | 12927/57600 [2:15:59<7:32:21,  1.65it/s]
 22%|██▏       | 12928/57600 [2:15:59<7:22:45,  1.68it/s]
 22%|██▏       | 12929/57600 [2:16:00<7:18:51,  1.70it/s]
 22%|██▏       | 12930/57600 [2:16:00<7:24:21,  1.68it/s]
 22%|██▏       | 12931/57600 [2:16:01<7:30:22,  1.65it/s]
 22%|██▏       | 12932/57600 [2:16:02<7:23:13,  1.68it/s]
 22%|██▏       | 12933/57600 [2:16:02<7:25:15,  1.67it/s]
 22%|██▏       | 12934/57600 [2:16:03<7:37:31,  1.63it/s]
 22%|██▏       | 12935/57600 [2:16:03<7:46:30,  1.60it/s]
 22%|██▏       | 12936/57600 [2:16:04<7:29:12,  1.66it/s]
 22%|██▏       | 12937/57600 [2:16:05<7:25:54,  1.67it/s]
 22%|██▏       | 12938/57600 [2:16:05<7:22:13,  1.68it/s]
 22%|██▏       | 12939/57600 [2:16:06<7:36:46,  1.63it/s]
 22%|██▏       | 12940/57600 [2:16:06<7:33:37,  1.64it/s]
                                                         
{'loss': 1.3415, 'learning_rate': 8.002439024390244e-07, 'epoch': 142.83}

 22%|██▏       | 12940/57600 [2:16:06<7:33:37,  1.64it/s]
 22%|██▏       | 12941/57600 [2:16:07<7:20:11,  1.69it/s]
 22%|██▏       | 12942/57600 [2:16:08<7:38:24,  1.62it/s]
 22%|██▏       | 12943/57600 [2:16:08<7:47:53,  1.59it/s]
 22%|██▏       | 12944/57600 [2:16:09<7:49:21,  1.59it/s]
 22%|██▏       | 12945/57600 [2:16:10<7:50:32,  1.58it/s]
 22%|██▏       | 12946/57600 [2:16:10<7:43:06,  1.61it/s]
 22%|██▏       | 12947/57600 [2:16:11<7:23:29,  1.68it/s]
 22%|██▏       | 12948/57600 [2:16:11<7:24:15,  1.68it/s]
 22%|██▏       | 12949/57600 [2:16:12<7:40:12,  1.62it/s]
 22%|██▏       | 12950/57600 [2:16:13<7:38:33,  1.62it/s]
 22%|██▏       | 12951/57600 [2:16:13<7:33:41,  1.64it/s]
 22%|██▏       | 12952/57600 [2:16:14<7:34:03,  1.64it/s]
 22%|██▏       | 12953/57600 [2:16:14<7:14:51,  1.71it/s]
 22%|██▏       | 12954/57600 [2:16:15<7:35:37,  1.63it/s]
 22%|██▏       | 12955/57600 [2:16:16<7:33:38,  1.64it/s]
 22%|██▏       | 12956/57600 [2:16:16<7:57:48,  1.56it/s]
 22%|██▏       | 12957/57600 [2:16:17<7:43:58,  1.60it/s]
 22%|██▏       | 12958/57600 [2:16:17<7:35:59,  1.63it/s]
 22%|██▏       | 12959/57600 [2:16:18<7:40:53,  1.61it/s]
 22%|██▎       | 12960/57600 [2:16:19<7:39:06,  1.62it/s]
                                                         
{'loss': 1.3218, 'learning_rate': 7.999303135888501e-07, 'epoch': 143.05}

 22%|██▎       | 12960/57600 [2:16:19<7:39:06,  1.62it/s]
 23%|██▎       | 12961/57600 [2:16:19<7:51:31,  1.58it/s]
 23%|██▎       | 12962/57600 [2:16:20<8:07:22,  1.53it/s]
 23%|██▎       | 12963/57600 [2:16:21<8:09:36,  1.52it/s]
 23%|██▎       | 12964/57600 [2:16:21<8:01:57,  1.54it/s]
 23%|██▎       | 12965/57600 [2:16:22<7:51:07,  1.58it/s]
 23%|██▎       | 12966/57600 [2:16:23<7:34:46,  1.64it/s]
 23%|██▎       | 12967/57600 [2:16:23<7:29:23,  1.66it/s]
 23%|██▎       | 12968/57600 [2:16:24<7:53:21,  1.57it/s]
 23%|██▎       | 12969/57600 [2:16:24<7:45:40,  1.60it/s]
 23%|██▎       | 12970/57600 [2:16:25<7:53:20,  1.57it/s]
 23%|██▎       | 12971/57600 [2:16:26<7:50:00,  1.58it/s]
 23%|██▎       | 12972/57600 [2:16:26<7:45:18,  1.60it/s]
 23%|██▎       | 12973/57600 [2:16:27<7:28:30,  1.66it/s]
 23%|██▎       | 12974/57600 [2:16:27<7:28:51,  1.66it/s]
 23%|██▎       | 12975/57600 [2:16:28<7:25:25,  1.67it/s]
 23%|██▎       | 12976/57600 [2:16:29<7:20:03,  1.69it/s]
 23%|██▎       | 12977/57600 [2:16:29<7:28:01,  1.66it/s]
 23%|██▎       | 12978/57600 [2:16:30<7:18:07,  1.70it/s]
 23%|██▎       | 12979/57600 [2:16:30<7:28:15,  1.66it/s]
 23%|██▎       | 12980/57600 [2:16:31<7:45:20,  1.60it/s]
                                                         
{'loss': 1.3619, 'learning_rate': 7.99616724738676e-07, 'epoch': 143.27}

 23%|██▎       | 12980/57600 [2:16:31<7:45:20,  1.60it/s]
 23%|██▎       | 12981/57600 [2:16:32<7:46:56,  1.59it/s]
 23%|██▎       | 12982/57600 [2:16:32<7:37:13,  1.63it/s]
 23%|██▎       | 12983/57600 [2:16:33<7:24:00,  1.67it/s]
 23%|██▎       | 12984/57600 [2:16:34<7:32:58,  1.64it/s]
 23%|██▎       | 12985/57600 [2:16:34<8:01:20,  1.54it/s]
 23%|██▎       | 12986/57600 [2:16:35<7:49:36,  1.58it/s]
 23%|██▎       | 12987/57600 [2:16:35<7:40:20,  1.62it/s]
 23%|██▎       | 12988/57600 [2:16:36<7:31:24,  1.65it/s]
 23%|██▎       | 12989/57600 [2:16:37<7:33:43,  1.64it/s]
 23%|██▎       | 12990/57600 [2:16:37<7:21:33,  1.68it/s]
 23%|██▎       | 12991/57600 [2:16:38<7:24:34,  1.67it/s]
 23%|██▎       | 12992/57600 [2:16:39<7:40:37,  1.61it/s]
 23%|██▎       | 12993/57600 [2:16:39<7:53:51,  1.57it/s]
 23%|██▎       | 12994/57600 [2:16:40<8:04:15,  1.54it/s]
 23%|██▎       | 12995/57600 [2:16:41<8:06:16,  1.53it/s]
 23%|██▎       | 12996/57600 [2:16:41<8:05:41,  1.53it/s]
 23%|██▎       | 12997/57600 [2:16:42<7:49:34,  1.58it/s]
 23%|██▎       | 12998/57600 [2:16:42<7:50:43,  1.58it/s]
 23%|██▎       | 12999/57600 [2:16:43<7:40:43,  1.61it/s]
 23%|██▎       | 13000/57600 [2:16:44<7:47:38,  1.59it/s]
                                                         
{'loss': 1.2859, 'learning_rate': 7.993031358885017e-07, 'epoch': 143.49}

 23%|██▎       | 13000/57600 [2:16:44<7:47:38,  1.59it/s]
 23%|██▎       | 13001/57600 [2:16:44<7:38:05,  1.62it/s]
 23%|██▎       | 13002/57600 [2:16:45<7:25:42,  1.67it/s]
 23%|██▎       | 13003/57600 [2:16:45<7:43:47,  1.60it/s]
 23%|██▎       | 13004/57600 [2:16:46<7:41:40,  1.61it/s]
 23%|██▎       | 13005/57600 [2:16:47<7:27:32,  1.66it/s]
 23%|██▎       | 13006/57600 [2:16:47<7:26:29,  1.66it/s]
 23%|██▎       | 13007/57600 [2:16:48<7:25:43,  1.67it/s]
 23%|██▎       | 13008/57600 [2:16:48<7:37:49,  1.62it/s]
 23%|██▎       | 13009/57600 [2:16:49<7:35:15,  1.63it/s]
 23%|██▎       | 13010/57600 [2:16:50<7:30:49,  1.65it/s]
 23%|██▎       | 13011/57600 [2:16:50<7:27:33,  1.66it/s]
 23%|██▎       | 13012/57600 [2:16:51<7:28:54,  1.66it/s]
 23%|██▎       | 13013/57600 [2:16:52<7:38:36,  1.62it/s]
 23%|██▎       | 13014/57600 [2:16:52<7:43:35,  1.60it/s]
 23%|██▎       | 13015/57600 [2:16:53<7:39:50,  1.62it/s]
 23%|██▎       | 13016/57600 [2:16:53<7:31:42,  1.65it/s]
 23%|██▎       | 13017/57600 [2:16:54<7:42:37,  1.61it/s]
 23%|██▎       | 13018/57600 [2:16:55<7:47:55,  1.59it/s]
 23%|██▎       | 13019/57600 [2:16:55<7:58:46,  1.55it/s]
 23%|██▎       | 13020/57600 [2:16:56<8:00:55,  1.54it/s]
                                                         
{'loss': 1.3311, 'learning_rate': 7.989895470383275e-07, 'epoch': 143.71}

 23%|██▎       | 13020/57600 [2:16:56<8:00:55,  1.54it/s]
 23%|██▎       | 13021/57600 [2:16:57<7:55:46,  1.56it/s]
 23%|██▎       | 13022/57600 [2:16:57<7:52:39,  1.57it/s]
 23%|██▎       | 13023/57600 [2:16:58<7:38:12,  1.62it/s]
 23%|██▎       | 13024/57600 [2:16:58<7:24:00,  1.67it/s]
 23%|██▎       | 13025/57600 [2:16:59<7:41:53,  1.61it/s]
 23%|██▎       | 13026/57600 [2:17:00<7:29:42,  1.65it/s]
 23%|██▎       | 13027/57600 [2:17:00<7:28:57,  1.65it/s]
 23%|██▎       | 13028/57600 [2:17:01<7:31:07,  1.65it/s]
 23%|██▎       | 13029/57600 [2:17:01<7:17:43,  1.70it/s]
 23%|██▎       | 13030/57600 [2:17:02<7:19:29,  1.69it/s]
 23%|██▎       | 13031/57600 [2:17:03<7:19:11,  1.69it/s]
 23%|██▎       | 13032/57600 [2:17:03<7:07:24,  1.74it/s]
 23%|██▎       | 13033/57600 [2:17:04<7:15:00,  1.71it/s]
 23%|██▎       | 13034/57600 [2:17:04<7:14:21,  1.71it/s]
 23%|██▎       | 13035/57600 [2:17:05<7:18:02,  1.70it/s]
 23%|██▎       | 13036/57600 [2:17:06<7:31:38,  1.64it/s]
 23%|██▎       | 13037/57600 [2:17:06<7:36:58,  1.63it/s]
 23%|██▎       | 13038/57600 [2:17:07<7:40:06,  1.61it/s]
 23%|██▎       | 13039/57600 [2:17:07<7:34:32,  1.63it/s]
 23%|██▎       | 13040/57600 [2:17:08<7:24:14,  1.67it/s]
                                                         
{'loss': 1.3699, 'learning_rate': 7.986759581881533e-07, 'epoch': 143.93}

 23%|██▎       | 13040/57600 [2:17:08<7:24:14,  1.67it/s]
 23%|██▎       | 13041/57600 [2:17:09<7:27:57,  1.66it/s]
 23%|██▎       | 13042/57600 [2:17:09<7:26:44,  1.66it/s]
 23%|██▎       | 13043/57600 [2:17:10<7:27:20,  1.66it/s]
 23%|██▎       | 13044/57600 [2:17:10<7:35:53,  1.63it/s]
 23%|██▎       | 13045/57600 [2:17:11<7:33:46,  1.64it/s]
 23%|██▎       | 13046/57600 [2:17:12<7:50:26,  1.58it/s]
 23%|██▎       | 13047/57600 [2:17:12<8:06:57,  1.52it/s]
 23%|██▎       | 13048/57600 [2:17:13<7:46:25,  1.59it/s]
 23%|██▎       | 13049/57600 [2:17:14<7:42:02,  1.61it/s]
 23%|██▎       | 13050/57600 [2:17:14<7:45:14,  1.60it/s]
 23%|██▎       | 13051/57600 [2:17:15<7:33:35,  1.64it/s]
 23%|██▎       | 13052/57600 [2:17:15<7:42:42,  1.60it/s]
 23%|██▎       | 13053/57600 [2:17:16<7:54:46,  1.56it/s]
 23%|██▎       | 13054/57600 [2:17:17<7:49:41,  1.58it/s]
 23%|██▎       | 13055/57600 [2:17:17<7:46:16,  1.59it/s]
 23%|██▎       | 13056/57600 [2:17:18<7:53:51,  1.57it/s]
 23%|██▎       | 13057/57600 [2:17:19<7:39:27,  1.62it/s]
 23%|██▎       | 13058/57600 [2:17:19<7:33:13,  1.64it/s]
 23%|██▎       | 13059/57600 [2:17:20<7:28:55,  1.65it/s]
 23%|██▎       | 13060/57600 [2:17:20<7:24:30,  1.67it/s]
                                                         
{'loss': 1.3038, 'learning_rate': 7.98362369337979e-07, 'epoch': 144.15}

 23%|██▎       | 13060/57600 [2:17:20<7:24:30,  1.67it/s]
 23%|██▎       | 13061/57600 [2:17:21<7:13:40,  1.71it/s]
 23%|██▎       | 13062/57600 [2:17:22<7:16:00,  1.70it/s]
 23%|██▎       | 13063/57600 [2:17:22<7:21:43,  1.68it/s]
 23%|██▎       | 13064/57600 [2:17:23<7:46:23,  1.59it/s]
 23%|██▎       | 13065/57600 [2:17:23<7:40:54,  1.61it/s]
 23%|██▎       | 13066/57600 [2:17:24<7:37:10,  1.62it/s]
 23%|██▎       | 13067/57600 [2:17:25<7:44:40,  1.60it/s]
 23%|██▎       | 13068/57600 [2:17:25<7:36:59,  1.62it/s]
 23%|██▎       | 13069/57600 [2:17:26<7:44:50,  1.60it/s]
 23%|██▎       | 13070/57600 [2:17:27<7:38:53,  1.62it/s]
 23%|██▎       | 13071/57600 [2:17:27<7:52:12,  1.57it/s]
 23%|██▎       | 13072/57600 [2:17:28<7:57:19,  1.55it/s]
 23%|██▎       | 13073/57600 [2:17:28<7:49:19,  1.58it/s]
 23%|██▎       | 13074/57600 [2:17:29<7:30:00,  1.65it/s]
 23%|██▎       | 13075/57600 [2:17:30<7:19:46,  1.69it/s]
 23%|██▎       | 13076/57600 [2:17:30<7:51:10,  1.57it/s]
 23%|██▎       | 13077/57600 [2:17:31<7:35:22,  1.63it/s]
 23%|██▎       | 13078/57600 [2:17:32<7:45:43,  1.59it/s]
 23%|██▎       | 13079/57600 [2:17:32<7:44:53,  1.60it/s]
 23%|██▎       | 13080/57600 [2:17:33<7:51:16,  1.57it/s]
                                                         
{'loss': 1.3118, 'learning_rate': 7.980487804878048e-07, 'epoch': 144.37}

 23%|██▎       | 13080/57600 [2:17:33<7:51:16,  1.57it/s]
 23%|██▎       | 13081/57600 [2:17:33<7:57:47,  1.55it/s]
 23%|██▎       | 13082/57600 [2:17:34<7:41:06,  1.61it/s]
 23%|██▎       | 13083/57600 [2:17:35<7:38:31,  1.62it/s]
 23%|██▎       | 13084/57600 [2:17:35<7:39:00,  1.62it/s]
 23%|██▎       | 13085/57600 [2:17:36<7:34:49,  1.63it/s]
 23%|██▎       | 13086/57600 [2:17:37<7:39:43,  1.61it/s]
 23%|██▎       | 13087/57600 [2:17:37<7:35:45,  1.63it/s]
 23%|██▎       | 13088/57600 [2:17:38<7:20:06,  1.69it/s]
 23%|██▎       | 13089/57600 [2:17:38<7:23:03,  1.67it/s]
 23%|██▎       | 13090/57600 [2:17:39<7:18:34,  1.69it/s]
 23%|██▎       | 13091/57600 [2:17:39<7:11:49,  1.72it/s]
 23%|██▎       | 13092/57600 [2:17:40<7:19:43,  1.69it/s]
 23%|██▎       | 13093/57600 [2:17:41<7:44:00,  1.60it/s]
 23%|██▎       | 13094/57600 [2:17:41<7:43:03,  1.60it/s]
 23%|██▎       | 13095/57600 [2:17:42<7:48:22,  1.58it/s]
 23%|██▎       | 13096/57600 [2:17:43<7:49:27,  1.58it/s]
 23%|██▎       | 13097/57600 [2:17:43<7:46:51,  1.59it/s]
 23%|██▎       | 13098/57600 [2:17:44<7:54:14,  1.56it/s]
 23%|██▎       | 13099/57600 [2:17:44<7:35:31,  1.63it/s]
 23%|██▎       | 13100/57600 [2:17:45<7:41:14,  1.61it/s]
                                                         
{'loss': 1.3181, 'learning_rate': 7.977351916376306e-07, 'epoch': 144.59}

 23%|██▎       | 13100/57600 [2:17:45<7:41:14,  1.61it/s]
 23%|██▎       | 13101/57600 [2:17:46<7:31:09,  1.64it/s]
 23%|██▎       | 13102/57600 [2:17:46<7:30:33,  1.65it/s]
 23%|██▎       | 13103/57600 [2:17:47<7:31:30,  1.64it/s]
 23%|██▎       | 13104/57600 [2:17:48<7:29:23,  1.65it/s]
 23%|██▎       | 13105/57600 [2:17:48<7:30:33,  1.65it/s]
 23%|██▎       | 13106/57600 [2:17:49<7:32:18,  1.64it/s]
 23%|██▎       | 13107/57600 [2:17:49<7:19:33,  1.69it/s]
 23%|██▎       | 13108/57600 [2:17:50<7:36:55,  1.62it/s]
 23%|██▎       | 13109/57600 [2:17:51<7:42:01,  1.60it/s]
 23%|██▎       | 13110/57600 [2:17:51<7:40:50,  1.61it/s]
 23%|██▎       | 13111/57600 [2:17:52<7:42:13,  1.60it/s]
 23%|██▎       | 13112/57600 [2:17:52<7:26:43,  1.66it/s]
 23%|██▎       | 13113/57600 [2:17:53<7:51:52,  1.57it/s]
 23%|██▎       | 13114/57600 [2:17:54<7:48:38,  1.58it/s]
 23%|██▎       | 13115/57600 [2:17:54<7:58:26,  1.55it/s]
 23%|██▎       | 13116/57600 [2:17:55<8:09:04,  1.52it/s]
 23%|██▎       | 13117/57600 [2:17:56<7:56:20,  1.56it/s]
 23%|██▎       | 13118/57600 [2:17:56<7:49:13,  1.58it/s]
 23%|██▎       | 13119/57600 [2:17:57<7:29:01,  1.65it/s]
 23%|██▎       | 13120/57600 [2:17:57<7:34:02,  1.63it/s]
                                                         
{'loss': 1.3102, 'learning_rate': 7.974216027874565e-07, 'epoch': 144.81}

 23%|██▎       | 13120/57600 [2:17:57<7:34:02,  1.63it/s]
 23%|██▎       | 13121/57600 [2:17:58<7:29:48,  1.65it/s]
 23%|██▎       | 13122/57600 [2:17:59<7:32:43,  1.64it/s]
 23%|██▎       | 13123/57600 [2:17:59<7:15:45,  1.70it/s]
 23%|██▎       | 13124/57600 [2:18:00<7:24:40,  1.67it/s]
 23%|██▎       | 13125/57600 [2:18:00<7:17:43,  1.69it/s]
 23%|██▎       | 13126/57600 [2:18:01<7:24:08,  1.67it/s]
 23%|██▎       | 13127/57600 [2:18:02<7:40:22,  1.61it/s]
 23%|██▎       | 13128/57600 [2:18:02<7:43:12,  1.60it/s]
 23%|██▎       | 13129/57600 [2:18:03<7:35:23,  1.63it/s]
 23%|██▎       | 13130/57600 [2:18:03<7:19:22,  1.69it/s]
 23%|██▎       | 13131/57600 [2:18:04<7:24:53,  1.67it/s]
 23%|██▎       | 13132/57600 [2:18:05<7:43:52,  1.60it/s]
 23%|██▎       | 13133/57600 [2:18:05<7:41:47,  1.60it/s]
 23%|██▎       | 13134/57600 [2:18:06<7:45:58,  1.59it/s]
 23%|██▎       | 13135/57600 [2:18:07<7:48:30,  1.58it/s]
 23%|██▎       | 13136/57600 [2:18:07<7:35:39,  1.63it/s]
 23%|██▎       | 13137/57600 [2:18:08<7:47:12,  1.59it/s]
 23%|██▎       | 13138/57600 [2:18:09<7:54:15,  1.56it/s]
 23%|██▎       | 13139/57600 [2:18:09<7:57:11,  1.55it/s]
 23%|██▎       | 13140/57600 [2:18:10<7:57:32,  1.55it/s]
                                                         
{'loss': 1.3476, 'learning_rate': 7.971080139372822e-07, 'epoch': 145.03}

 23%|██▎       | 13140/57600 [2:18:10<7:57:32,  1.55it/s]
 23%|██▎       | 13141/57600 [2:18:10<7:43:11,  1.60it/s]
 23%|██▎       | 13142/57600 [2:18:11<7:34:10,  1.63it/s]
 23%|██▎       | 13143/57600 [2:18:12<7:40:28,  1.61it/s]
 23%|██▎       | 13144/57600 [2:18:12<7:40:48,  1.61it/s]
 23%|██▎       | 13145/57600 [2:18:13<7:38:26,  1.62it/s]
 23%|██▎       | 13146/57600 [2:18:14<7:40:10,  1.61it/s]
 23%|██▎       | 13147/57600 [2:18:14<8:03:52,  1.53it/s]
 23%|██▎       | 13148/57600 [2:18:15<8:02:05,  1.54it/s]
 23%|██▎       | 13149/57600 [2:18:16<8:07:29,  1.52it/s]
 23%|██▎       | 13150/57600 [2:18:16<7:55:09,  1.56it/s]
 23%|██▎       | 13151/57600 [2:18:17<7:46:14,  1.59it/s]
 23%|██▎       | 13152/57600 [2:18:17<7:51:28,  1.57it/s]
 23%|██▎       | 13153/57600 [2:18:18<8:11:39,  1.51it/s]
 23%|██▎       | 13154/57600 [2:18:19<8:09:10,  1.51it/s]
 23%|██▎       | 13155/57600 [2:18:19<7:55:39,  1.56it/s]
 23%|██▎       | 13156/57600 [2:18:20<7:48:47,  1.58it/s]
 23%|██▎       | 13157/57600 [2:18:21<7:43:54,  1.60it/s]
 23%|██▎       | 13158/57600 [2:18:21<7:29:20,  1.65it/s]
 23%|██▎       | 13159/57600 [2:18:22<7:23:38,  1.67it/s]
 23%|██▎       | 13160/57600 [2:18:22<7:21:32,  1.68it/s]
                                                         
{'loss': 1.3301, 'learning_rate': 7.96794425087108e-07, 'epoch': 145.25}

 23%|██▎       | 13160/57600 [2:18:22<7:21:32,  1.68it/s]
 23%|██▎       | 13161/57600 [2:18:23<7:30:04,  1.65it/s]
 23%|██▎       | 13162/57600 [2:18:24<7:36:29,  1.62it/s]
 23%|██▎       | 13163/57600 [2:18:24<7:31:38,  1.64it/s]
 23%|██▎       | 13164/57600 [2:18:25<7:27:19,  1.66it/s]
 23%|██▎       | 13165/57600 [2:18:26<7:44:13,  1.60it/s]
 23%|██▎       | 13166/57600 [2:18:26<7:54:51,  1.56it/s]
 23%|██▎       | 13167/57600 [2:18:27<7:45:00,  1.59it/s]
 23%|██▎       | 13168/57600 [2:18:27<7:42:32,  1.60it/s]
 23%|██▎       | 13169/57600 [2:18:28<7:31:21,  1.64it/s]
 23%|██▎       | 13170/57600 [2:18:29<7:27:52,  1.65it/s]
 23%|██▎       | 13171/57600 [2:18:29<7:18:25,  1.69it/s]
 23%|██▎       | 13172/57600 [2:18:30<7:14:55,  1.70it/s]
 23%|██▎       | 13173/57600 [2:18:30<7:21:43,  1.68it/s]
 23%|██▎       | 13174/57600 [2:18:31<7:25:40,  1.66it/s]
 23%|██▎       | 13175/57600 [2:18:32<7:30:42,  1.64it/s]
 23%|██▎       | 13176/57600 [2:18:32<7:31:37,  1.64it/s]
 23%|██▎       | 13177/57600 [2:18:33<7:21:21,  1.68it/s]
 23%|██▎       | 13178/57600 [2:18:33<7:18:59,  1.69it/s]
 23%|██▎       | 13179/57600 [2:18:34<7:39:57,  1.61it/s]
 23%|██▎       | 13180/57600 [2:18:35<7:37:37,  1.62it/s]
                                                         
{'loss': 1.3198, 'learning_rate': 7.964808362369338e-07, 'epoch': 145.47}

 23%|██▎       | 13180/57600 [2:18:35<7:37:37,  1.62it/s]
 23%|██▎       | 13181/57600 [2:18:35<7:28:01,  1.65it/s]
 23%|██▎       | 13182/57600 [2:18:36<7:33:36,  1.63it/s]
 23%|██▎       | 13183/57600 [2:18:36<7:31:51,  1.64it/s]
 23%|██▎       | 13184/57600 [2:18:37<7:27:02,  1.66it/s]
 23%|██▎       | 13185/57600 [2:18:38<7:47:10,  1.58it/s]
 23%|██▎       | 13186/57600 [2:18:38<7:29:01,  1.65it/s]
 23%|██▎       | 13187/57600 [2:18:39<7:25:37,  1.66it/s]
 23%|██▎       | 13188/57600 [2:18:39<7:17:20,  1.69it/s]
 23%|██▎       | 13189/57600 [2:18:40<7:32:16,  1.64it/s]
 23%|██▎       | 13190/57600 [2:18:41<7:31:11,  1.64it/s]
 23%|██▎       | 13191/57600 [2:18:41<7:35:16,  1.63it/s]
 23%|██▎       | 13192/57600 [2:18:42<7:31:55,  1.64it/s]
 23%|██▎       | 13193/57600 [2:18:43<7:22:12,  1.67it/s]
 23%|██▎       | 13194/57600 [2:18:43<7:44:01,  1.59it/s]
 23%|██▎       | 13195/57600 [2:18:44<7:30:24,  1.64it/s]
 23%|██▎       | 13196/57600 [2:18:44<7:48:32,  1.58it/s]
 23%|██▎       | 13197/57600 [2:18:45<7:46:40,  1.59it/s]
 23%|██▎       | 13198/57600 [2:18:46<7:35:39,  1.62it/s]
 23%|██▎       | 13199/57600 [2:18:46<7:32:01,  1.64it/s]
 23%|██▎       | 13200/57600 [2:18:47<7:31:22,  1.64it/s]
                                                         
{'loss': 1.3133, 'learning_rate': 7.961672473867596e-07, 'epoch': 145.7}

 23%|██▎       | 13200/57600 [2:18:47<7:31:22,  1.64it/s]
 23%|██▎       | 13201/57600 [2:18:47<7:30:28,  1.64it/s]
 23%|██▎       | 13202/57600 [2:18:48<7:21:54,  1.67it/s]
 23%|██▎       | 13203/57600 [2:18:49<7:29:47,  1.65it/s]
 23%|██▎       | 13204/57600 [2:18:49<7:39:23,  1.61it/s]
 23%|██▎       | 13205/57600 [2:18:50<7:41:03,  1.60it/s]
 23%|██▎       | 13206/57600 [2:18:51<7:47:22,  1.58it/s]
 23%|██▎       | 13207/57600 [2:18:51<7:43:16,  1.60it/s]
 23%|██▎       | 13208/57600 [2:18:52<7:44:24,  1.59it/s]
 23%|██▎       | 13209/57600 [2:18:52<7:38:30,  1.61it/s]
 23%|██▎       | 13210/57600 [2:18:53<7:45:53,  1.59it/s]
 23%|██▎       | 13211/57600 [2:18:54<7:33:49,  1.63it/s]
 23%|██▎       | 13212/57600 [2:18:54<7:32:50,  1.63it/s]
 23%|██▎       | 13213/57600 [2:18:55<7:26:25,  1.66it/s]
 23%|██▎       | 13214/57600 [2:18:55<7:18:24,  1.69it/s]
 23%|██▎       | 13215/57600 [2:18:56<7:14:28,  1.70it/s]
 23%|██▎       | 13216/57600 [2:18:57<7:19:43,  1.68it/s]
 23%|██▎       | 13217/57600 [2:18:57<7:21:52,  1.67it/s]
 23%|██▎       | 13218/57600 [2:18:58<7:22:59,  1.67it/s]
 23%|██▎       | 13219/57600 [2:18:58<7:14:19,  1.70it/s]
 23%|██▎       | 13220/57600 [2:18:59<7:29:47,  1.64it/s]
                                                         
{'loss': 1.3621, 'learning_rate': 7.958536585365853e-07, 'epoch': 145.92}

 23%|██▎       | 13220/57600 [2:18:59<7:29:47,  1.64it/s]
 23%|██▎       | 13221/57600 [2:19:00<7:28:24,  1.65it/s]
 23%|██▎       | 13222/57600 [2:19:00<7:46:01,  1.59it/s]
 23%|██▎       | 13223/57600 [2:19:01<8:03:56,  1.53it/s]
 23%|██▎       | 13224/57600 [2:19:02<7:45:25,  1.59it/s]
 23%|██▎       | 13225/57600 [2:19:02<7:34:02,  1.63it/s]
 23%|██▎       | 13226/57600 [2:19:03<7:32:27,  1.63it/s]
 23%|██▎       | 13227/57600 [2:19:04<7:49:24,  1.58it/s]
 23%|██▎       | 13228/57600 [2:19:04<7:58:55,  1.54it/s]
 23%|██▎       | 13229/57600 [2:19:05<7:45:24,  1.59it/s]
 23%|██▎       | 13230/57600 [2:19:05<7:53:02,  1.56it/s]
 23%|██▎       | 13231/57600 [2:19:06<7:58:15,  1.55it/s]
 23%|██▎       | 13232/57600 [2:19:07<8:00:46,  1.54it/s]
 23%|██▎       | 13233/57600 [2:19:07<7:53:54,  1.56it/s]
 23%|██▎       | 13234/57600 [2:19:08<7:54:46,  1.56it/s]
 23%|██▎       | 13235/57600 [2:19:09<7:44:50,  1.59it/s]
 23%|██▎       | 13236/57600 [2:19:09<8:08:40,  1.51it/s]
 23%|██▎       | 13237/57600 [2:19:10<7:49:09,  1.58it/s]
 23%|██▎       | 13238/57600 [2:19:11<7:46:41,  1.58it/s]
 23%|██▎       | 13239/57600 [2:19:11<7:35:54,  1.62it/s]
 23%|██▎       | 13240/57600 [2:19:12<7:36:41,  1.62it/s]
                                                         
{'loss': 1.2893, 'learning_rate': 7.955400696864111e-07, 'epoch': 146.14}

 23%|██▎       | 13240/57600 [2:19:12<7:36:41,  1.62it/s]
 23%|██▎       | 13241/57600 [2:19:12<7:30:02,  1.64it/s]
 23%|██▎       | 13242/57600 [2:19:13<7:49:09,  1.58it/s]
 23%|██▎       | 13243/57600 [2:19:14<7:38:33,  1.61it/s]
 23%|██▎       | 13244/57600 [2:19:14<7:46:19,  1.59it/s]
 23%|██▎       | 13245/57600 [2:19:15<7:32:01,  1.64it/s]
 23%|██▎       | 13246/57600 [2:19:15<7:28:00,  1.65it/s]
 23%|██▎       | 13247/57600 [2:19:16<7:38:38,  1.61it/s]
 23%|██▎       | 13248/57600 [2:19:17<7:39:12,  1.61it/s]
 23%|██▎       | 13249/57600 [2:19:17<7:32:18,  1.63it/s]
 23%|██▎       | 13250/57600 [2:19:18<7:27:14,  1.65it/s]
 23%|██▎       | 13251/57600 [2:19:18<7:25:22,  1.66it/s]
 23%|██▎       | 13252/57600 [2:19:19<7:25:35,  1.66it/s]
 23%|██▎       | 13253/57600 [2:19:20<7:15:02,  1.70it/s]
 23%|██▎       | 13254/57600 [2:19:20<7:36:34,  1.62it/s]
 23%|██▎       | 13255/57600 [2:19:21<7:38:29,  1.61it/s]
 23%|██▎       | 13256/57600 [2:19:22<7:22:46,  1.67it/s]
 23%|██▎       | 13257/57600 [2:19:22<7:35:23,  1.62it/s]
 23%|██▎       | 13258/57600 [2:19:23<7:30:43,  1.64it/s]
 23%|██▎       | 13259/57600 [2:19:23<7:55:25,  1.55it/s]
 23%|██▎       | 13260/57600 [2:19:24<7:44:03,  1.59it/s]
                                                         
{'loss': 1.3464, 'learning_rate': 7.952264808362369e-07, 'epoch': 146.36}

 23%|██▎       | 13260/57600 [2:19:24<7:44:03,  1.59it/s]
 23%|██▎       | 13261/57600 [2:19:25<7:36:51,  1.62it/s]
 23%|██▎       | 13262/57600 [2:19:25<7:35:28,  1.62it/s]
 23%|██▎       | 13263/57600 [2:19:26<7:37:26,  1.62it/s]
 23%|██▎       | 13264/57600 [2:19:27<7:40:06,  1.61it/s]
 23%|██▎       | 13265/57600 [2:19:27<7:40:15,  1.61it/s]
 23%|██▎       | 13266/57600 [2:19:28<7:42:18,  1.60it/s]
 23%|██▎       | 13267/57600 [2:19:28<7:52:26,  1.56it/s]
 23%|██▎       | 13268/57600 [2:19:29<7:39:00,  1.61it/s]
 23%|██▎       | 13269/57600 [2:19:30<7:25:45,  1.66it/s]
 23%|██▎       | 13270/57600 [2:19:30<7:22:15,  1.67it/s]
 23%|██▎       | 13271/57600 [2:19:31<7:28:43,  1.65it/s]
 23%|██▎       | 13272/57600 [2:19:31<7:42:14,  1.60it/s]
 23%|██▎       | 13273/57600 [2:19:32<7:31:04,  1.64it/s]
 23%|██▎       | 13274/57600 [2:19:33<7:39:20,  1.61it/s]
 23%|██▎       | 13275/57600 [2:19:33<7:34:27,  1.63it/s]
 23%|██▎       | 13276/57600 [2:19:34<7:33:14,  1.63it/s]
 23%|██▎       | 13277/57600 [2:19:35<7:28:36,  1.65it/s]
 23%|██▎       | 13278/57600 [2:19:35<7:33:28,  1.63it/s]
 23%|██▎       | 13279/57600 [2:19:36<7:21:47,  1.67it/s]
 23%|██▎       | 13280/57600 [2:19:36<7:44:52,  1.59it/s]
                                                         
{'loss': 1.3016, 'learning_rate': 7.949128919860627e-07, 'epoch': 146.58}

 23%|██▎       | 13280/57600 [2:19:36<7:44:52,  1.59it/s]
 23%|██▎       | 13281/57600 [2:19:37<8:04:39,  1.52it/s]
 23%|██▎       | 13282/57600 [2:19:38<7:47:38,  1.58it/s]
 23%|██▎       | 13283/57600 [2:19:38<7:35:16,  1.62it/s]
 23%|██▎       | 13284/57600 [2:19:39<7:35:59,  1.62it/s]
 23%|██▎       | 13285/57600 [2:19:40<7:44:29,  1.59it/s]
 23%|██▎       | 13286/57600 [2:19:40<7:54:08,  1.56it/s]
 23%|██▎       | 13287/57600 [2:19:41<8:07:46,  1.51it/s]
 23%|██▎       | 13288/57600 [2:19:42<7:57:55,  1.55it/s]
 23%|██▎       | 13289/57600 [2:19:42<7:45:00,  1.59it/s]
 23%|██▎       | 13290/57600 [2:19:43<7:44:14,  1.59it/s]
 23%|██▎       | 13291/57600 [2:19:43<7:39:44,  1.61it/s]
 23%|██▎       | 13292/57600 [2:19:44<7:41:39,  1.60it/s]
 23%|██▎       | 13293/57600 [2:19:45<7:35:14,  1.62it/s]
 23%|██▎       | 13294/57600 [2:19:45<7:36:53,  1.62it/s]
 23%|██▎       | 13295/57600 [2:19:46<7:35:40,  1.62it/s]
 23%|██▎       | 13296/57600 [2:19:46<7:28:16,  1.65it/s]
 23%|██▎       | 13297/57600 [2:19:47<7:30:06,  1.64it/s]
 23%|██▎       | 13298/57600 [2:19:48<7:18:34,  1.68it/s]
 23%|██▎       | 13299/57600 [2:19:48<7:22:31,  1.67it/s]
 23%|██▎       | 13300/57600 [2:19:49<7:16:51,  1.69it/s]
                                                         
{'loss': 1.3302, 'learning_rate': 7.945993031358884e-07, 'epoch': 146.8}

 23%|██▎       | 13300/57600 [2:19:49<7:16:51,  1.69it/s]
 23%|██▎       | 13301/57600 [2:19:49<7:14:53,  1.70it/s]
 23%|██▎       | 13302/57600 [2:19:50<7:30:32,  1.64it/s]
 23%|██▎       | 13303/57600 [2:19:51<7:48:40,  1.58it/s]
 23%|██▎       | 13304/57600 [2:19:51<7:39:35,  1.61it/s]
 23%|██▎       | 13305/57600 [2:19:52<7:26:45,  1.65it/s]
 23%|██▎       | 13306/57600 [2:19:52<7:18:07,  1.68it/s]
 23%|██▎       | 13307/57600 [2:19:53<7:23:59,  1.66it/s]
 23%|██▎       | 13308/57600 [2:19:54<7:18:23,  1.68it/s]
 23%|██▎       | 13309/57600 [2:19:54<7:30:26,  1.64it/s]
 23%|██▎       | 13310/57600 [2:19:55<7:16:32,  1.69it/s]
 23%|██▎       | 13311/57600 [2:19:56<7:45:34,  1.59it/s]
 23%|██▎       | 13312/57600 [2:19:56<7:50:47,  1.57it/s]
 23%|██▎       | 13313/57600 [2:19:57<7:38:48,  1.61it/s]
 23%|██▎       | 13314/57600 [2:19:57<7:31:20,  1.64it/s]
 23%|██▎       | 13315/57600 [2:19:58<7:37:07,  1.61it/s]
 23%|██▎       | 13316/57600 [2:19:59<7:36:24,  1.62it/s]
 23%|██▎       | 13317/57600 [2:19:59<7:32:46,  1.63it/s]
 23%|██▎       | 13318/57600 [2:20:00<7:39:01,  1.61it/s]
 23%|██▎       | 13319/57600 [2:20:01<8:00:44,  1.54it/s]
 23%|██▎       | 13320/57600 [2:20:01<7:39:38,  1.61it/s]
                                                         
{'loss': 1.3465, 'learning_rate': 7.942857142857143e-07, 'epoch': 147.02}

 23%|██▎       | 13320/57600 [2:20:01<7:39:38,  1.61it/s]
 23%|██▎       | 13321/57600 [2:20:02<7:48:04,  1.58it/s]
 23%|██▎       | 13322/57600 [2:20:02<7:49:30,  1.57it/s]
 23%|██▎       | 13323/57600 [2:20:03<7:40:15,  1.60it/s]
 23%|██▎       | 13324/57600 [2:20:04<7:36:18,  1.62it/s]
 23%|██▎       | 13325/57600 [2:20:04<7:56:29,  1.55it/s]
 23%|██▎       | 13326/57600 [2:20:05<7:47:44,  1.58it/s]
 23%|██▎       | 13327/57600 [2:20:06<7:41:25,  1.60it/s]
 23%|██▎       | 13328/57600 [2:20:06<7:49:01,  1.57it/s]
 23%|██▎       | 13329/57600 [2:20:07<7:53:45,  1.56it/s]
 23%|██▎       | 13330/57600 [2:20:07<7:35:44,  1.62it/s]
 23%|██▎       | 13331/57600 [2:20:08<7:24:08,  1.66it/s]
 23%|██▎       | 13332/57600 [2:20:09<7:34:11,  1.62it/s]
 23%|██▎       | 13333/57600 [2:20:09<7:48:34,  1.57it/s]
 23%|██▎       | 13334/57600 [2:20:10<7:28:39,  1.64it/s]
 23%|██▎       | 13335/57600 [2:20:10<7:17:37,  1.69it/s]
 23%|██▎       | 13336/57600 [2:20:11<7:18:26,  1.68it/s]
 23%|██▎       | 13337/57600 [2:20:12<7:17:03,  1.69it/s]
 23%|██▎       | 13338/57600 [2:20:12<7:23:03,  1.67it/s]
 23%|██▎       | 13339/57600 [2:20:13<7:15:48,  1.69it/s]
 23%|██▎       | 13340/57600 [2:20:13<7:19:03,  1.68it/s]
                                                         
{'loss': 1.3497, 'learning_rate': 7.9397212543554e-07, 'epoch': 147.24}

 23%|██▎       | 13340/57600 [2:20:13<7:19:03,  1.68it/s]
 23%|██▎       | 13341/57600 [2:20:14<7:37:39,  1.61it/s]
 23%|██▎       | 13342/57600 [2:20:15<7:29:36,  1.64it/s]
 23%|██▎       | 13343/57600 [2:20:15<7:27:12,  1.65it/s]
 23%|██▎       | 13344/57600 [2:20:16<7:26:26,  1.65it/s]
 23%|██▎       | 13345/57600 [2:20:17<7:28:35,  1.64it/s]
 23%|██▎       | 13346/57600 [2:20:17<7:28:40,  1.64it/s]
 23%|██▎       | 13347/57600 [2:20:18<7:49:19,  1.57it/s]
 23%|██▎       | 13348/57600 [2:20:18<7:46:16,  1.58it/s]
 23%|██▎       | 13349/57600 [2:20:19<7:33:11,  1.63it/s]
 23%|██▎       | 13350/57600 [2:20:20<7:18:52,  1.68it/s]
 23%|██▎       | 13351/57600 [2:20:20<7:13:25,  1.70it/s]
 23%|██▎       | 13352/57600 [2:20:21<7:26:37,  1.65it/s]
 23%|██▎       | 13353/57600 [2:20:21<7:25:11,  1.66it/s]
 23%|██▎       | 13354/57600 [2:20:22<7:53:43,  1.56it/s]
 23%|██▎       | 13355/57600 [2:20:23<7:45:58,  1.58it/s]
 23%|██▎       | 13356/57600 [2:20:23<7:43:08,  1.59it/s]
 23%|██▎       | 13357/57600 [2:20:24<7:41:37,  1.60it/s]
 23%|██▎       | 13358/57600 [2:20:25<7:25:14,  1.66it/s]
 23%|██▎       | 13359/57600 [2:20:25<7:40:25,  1.60it/s]
 23%|██▎       | 13360/57600 [2:20:26<7:31:54,  1.63it/s]
                                                         
{'loss': 1.335, 'learning_rate': 7.936585365853658e-07, 'epoch': 147.46}

 23%|██▎       | 13360/57600 [2:20:26<7:31:54,  1.63it/s]
 23%|██▎       | 13361/57600 [2:20:26<7:34:56,  1.62it/s]
 23%|██▎       | 13362/57600 [2:20:27<7:29:45,  1.64it/s]
 23%|██▎       | 13363/57600 [2:20:28<7:32:53,  1.63it/s]
 23%|██▎       | 13364/57600 [2:20:28<7:32:36,  1.63it/s]
 23%|██▎       | 13365/57600 [2:20:29<7:34:40,  1.62it/s]
 23%|██▎       | 13366/57600 [2:20:29<7:30:27,  1.64it/s]
 23%|██▎       | 13367/57600 [2:20:30<7:33:51,  1.62it/s]
 23%|██▎       | 13368/57600 [2:20:31<7:32:04,  1.63it/s]
 23%|██▎       | 13369/57600 [2:20:31<8:00:49,  1.53it/s]
 23%|██▎       | 13370/57600 [2:20:32<7:57:26,  1.54it/s]
 23%|██▎       | 13371/57600 [2:20:33<7:55:44,  1.55it/s]
 23%|██▎       | 13372/57600 [2:20:33<7:31:29,  1.63it/s]
 23%|██▎       | 13373/57600 [2:20:34<7:37:09,  1.61it/s]
 23%|██▎       | 13374/57600 [2:20:35<7:45:12,  1.58it/s]
 23%|██▎       | 13375/57600 [2:20:35<7:33:36,  1.62it/s]
 23%|██▎       | 13376/57600 [2:20:36<7:35:06,  1.62it/s]
 23%|██▎       | 13377/57600 [2:20:36<7:35:13,  1.62it/s]
 23%|██▎       | 13378/57600 [2:20:37<7:28:10,  1.64it/s]
 23%|██▎       | 13379/57600 [2:20:38<7:27:18,  1.65it/s]
 23%|██▎       | 13380/57600 [2:20:38<7:19:47,  1.68it/s]
                                                         
{'loss': 1.312, 'learning_rate': 7.933449477351915e-07, 'epoch': 147.68}

 23%|██▎       | 13380/57600 [2:20:38<7:19:47,  1.68it/s]
 23%|██▎       | 13381/57600 [2:20:39<7:32:06,  1.63it/s]
 23%|██▎       | 13382/57600 [2:20:39<7:34:43,  1.62it/s]
 23%|██▎       | 13383/57600 [2:20:40<7:43:14,  1.59it/s]
 23%|██▎       | 13384/57600 [2:20:41<7:34:50,  1.62it/s]
 23%|██▎       | 13385/57600 [2:20:41<7:30:52,  1.63it/s]
 23%|██▎       | 13386/57600 [2:20:42<7:31:31,  1.63it/s]
 23%|██▎       | 13387/57600 [2:20:42<7:29:16,  1.64it/s]
 23%|██▎       | 13388/57600 [2:20:43<7:18:36,  1.68it/s]
 23%|██▎       | 13389/57600 [2:20:44<7:13:08,  1.70it/s]
 23%|██▎       | 13390/57600 [2:20:44<7:23:01,  1.66it/s]
 23%|██▎       | 13391/57600 [2:20:45<7:15:03,  1.69it/s]
 23%|██▎       | 13392/57600 [2:20:45<7:10:47,  1.71it/s]
 23%|██▎       | 13393/57600 [2:20:46<7:36:21,  1.61it/s]
 23%|██▎       | 13394/57600 [2:20:47<7:35:38,  1.62it/s]
 23%|██▎       | 13395/57600 [2:20:47<7:31:41,  1.63it/s]
 23%|██▎       | 13396/57600 [2:20:48<7:24:44,  1.66it/s]
 23%|██▎       | 13397/57600 [2:20:49<7:38:05,  1.61it/s]
 23%|██▎       | 13398/57600 [2:20:49<7:23:05,  1.66it/s]
 23%|██▎       | 13399/57600 [2:20:50<7:24:00,  1.66it/s]
 23%|██▎       | 13400/57600 [2:20:50<7:26:44,  1.65it/s]
                                                         
{'loss': 1.3215, 'learning_rate': 7.930313588850174e-07, 'epoch': 147.9}

 23%|██▎       | 13400/57600 [2:20:50<7:26:44,  1.65it/s]
 23%|██▎       | 13401/57600 [2:20:51<7:37:22,  1.61it/s]
 23%|██▎       | 13402/57600 [2:20:52<7:30:39,  1.63it/s]
 23%|██▎       | 13403/57600 [2:20:52<7:26:56,  1.65it/s]
 23%|██▎       | 13404/57600 [2:20:53<7:17:00,  1.69it/s]
 23%|██▎       | 13405/57600 [2:20:53<7:29:40,  1.64it/s]
 23%|██▎       | 13406/57600 [2:20:54<7:44:33,  1.59it/s]
 23%|██▎       | 13407/57600 [2:20:55<7:39:50,  1.60it/s]
 23%|██▎       | 13408/57600 [2:20:55<7:36:20,  1.61it/s]
 23%|██▎       | 13409/57600 [2:20:56<8:11:53,  1.50it/s]
 23%|██▎       | 13410/57600 [2:20:57<7:49:22,  1.57it/s]
 23%|██▎       | 13411/57600 [2:20:57<7:34:10,  1.62it/s]
 23%|██▎       | 13412/57600 [2:20:58<7:36:34,  1.61it/s]
 23%|██▎       | 13413/57600 [2:20:58<7:29:31,  1.64it/s]
 23%|██▎       | 13414/57600 [2:20:59<7:34:54,  1.62it/s]
 23%|██▎       | 13415/57600 [2:21:00<7:26:49,  1.65it/s]
 23%|██▎       | 13416/57600 [2:21:00<7:25:06,  1.65it/s]
 23%|██▎       | 13417/57600 [2:21:01<7:28:54,  1.64it/s]
 23%|██▎       | 13418/57600 [2:21:01<7:28:50,  1.64it/s]
 23%|██▎       | 13419/57600 [2:21:02<7:38:54,  1.60it/s]
 23%|██▎       | 13420/57600 [2:21:03<7:32:18,  1.63it/s]
                                                         
{'loss': 1.3434, 'learning_rate': 7.927177700348433e-07, 'epoch': 148.12}

 23%|██▎       | 13420/57600 [2:21:03<7:32:18,  1.63it/s]
 23%|██▎       | 13421/57600 [2:21:03<7:27:38,  1.64it/s]
 23%|██▎       | 13422/57600 [2:21:04<7:36:47,  1.61it/s]
 23%|██▎       | 13423/57600 [2:21:05<7:39:31,  1.60it/s]
 23%|██▎       | 13424/57600 [2:21:05<7:38:11,  1.61it/s]
 23%|██▎       | 13425/57600 [2:21:06<7:32:33,  1.63it/s]
 23%|██▎       | 13426/57600 [2:21:06<7:42:34,  1.59it/s]
 23%|██▎       | 13427/57600 [2:21:07<7:55:43,  1.55it/s]
 23%|██▎       | 13428/57600 [2:21:08<7:48:54,  1.57it/s]
 23%|██▎       | 13429/57600 [2:21:08<7:44:19,  1.59it/s]
 23%|██▎       | 13430/57600 [2:21:09<7:41:16,  1.60it/s]
 23%|██▎       | 13431/57600 [2:21:10<7:35:29,  1.62it/s]
 23%|██▎       | 13432/57600 [2:21:10<7:35:12,  1.62it/s]
 23%|██▎       | 13433/57600 [2:21:11<7:21:42,  1.67it/s]
 23%|██▎       | 13434/57600 [2:21:11<7:18:02,  1.68it/s]
 23%|██▎       | 13435/57600 [2:21:12<7:23:55,  1.66it/s]
 23%|██▎       | 13436/57600 [2:21:13<7:44:29,  1.58it/s]
 23%|██▎       | 13437/57600 [2:21:13<7:41:25,  1.60it/s]
 23%|██▎       | 13438/57600 [2:21:14<7:26:01,  1.65it/s]
 23%|██▎       | 13439/57600 [2:21:14<7:37:37,  1.61it/s]
 23%|██▎       | 13440/57600 [2:21:15<7:50:19,  1.56it/s]
                                                         
{'loss': 1.3217, 'learning_rate': 7.924041811846689e-07, 'epoch': 148.34}

 23%|██▎       | 13440/57600 [2:21:15<7:50:19,  1.56it/s]
 23%|██▎       | 13441/57600 [2:21:16<7:40:46,  1.60it/s]
 23%|██▎       | 13442/57600 [2:21:16<7:36:10,  1.61it/s]
 23%|██▎       | 13443/57600 [2:21:17<7:41:51,  1.59it/s]
 23%|██▎       | 13444/57600 [2:21:18<7:36:17,  1.61it/s]
 23%|██▎       | 13445/57600 [2:21:18<7:21:38,  1.67it/s]
 23%|██▎       | 13446/57600 [2:21:19<7:13:20,  1.70it/s]
 23%|██▎       | 13447/57600 [2:21:19<7:26:48,  1.65it/s]
 23%|██▎       | 13448/57600 [2:21:20<7:34:29,  1.62it/s]
 23%|██▎       | 13449/57600 [2:21:21<7:41:05,  1.60it/s]
 23%|██▎       | 13450/57600 [2:21:21<7:29:44,  1.64it/s]
 23%|██▎       | 13451/57600 [2:21:22<7:26:46,  1.65it/s]
 23%|██▎       | 13452/57600 [2:21:22<7:36:28,  1.61it/s]
 23%|██▎       | 13453/57600 [2:21:23<7:35:16,  1.62it/s]
 23%|██▎       | 13454/57600 [2:21:24<7:53:19,  1.55it/s]
 23%|██▎       | 13455/57600 [2:21:24<7:48:38,  1.57it/s]
 23%|██▎       | 13456/57600 [2:21:25<7:36:53,  1.61it/s]
 23%|██▎       | 13457/57600 [2:21:26<7:41:07,  1.60it/s]
 23%|██▎       | 13458/57600 [2:21:26<7:48:18,  1.57it/s]
 23%|██▎       | 13459/57600 [2:21:27<7:42:05,  1.59it/s]
 23%|██▎       | 13460/57600 [2:21:28<7:36:10,  1.61it/s]
                                                         
{'loss': 1.3013, 'learning_rate': 7.920905923344948e-07, 'epoch': 148.57}

 23%|██▎       | 13460/57600 [2:21:28<7:36:10,  1.61it/s]
 23%|██▎       | 13461/57600 [2:21:28<7:29:02,  1.64it/s]
 23%|██▎       | 13462/57600 [2:21:29<7:22:12,  1.66it/s]
 23%|██▎       | 13463/57600 [2:21:29<7:30:31,  1.63it/s]
 23%|██▎       | 13464/57600 [2:21:30<7:19:32,  1.67it/s]
 23%|██▎       | 13465/57600 [2:21:31<7:31:24,  1.63it/s]
 23%|██▎       | 13466/57600 [2:21:31<7:33:21,  1.62it/s]
 23%|██▎       | 13467/57600 [2:21:32<7:19:42,  1.67it/s]
 23%|██▎       | 13468/57600 [2:21:32<7:17:27,  1.68it/s]
 23%|██▎       | 13469/57600 [2:21:33<7:31:16,  1.63it/s]
 23%|██▎       | 13470/57600 [2:21:34<7:58:34,  1.54it/s]
 23%|██▎       | 13471/57600 [2:21:34<7:50:32,  1.56it/s]
 23%|██▎       | 13472/57600 [2:21:35<7:44:50,  1.58it/s]
 23%|██▎       | 13473/57600 [2:21:36<7:53:46,  1.55it/s]
 23%|██▎       | 13474/57600 [2:21:36<7:47:31,  1.57it/s]
 23%|██▎       | 13475/57600 [2:21:37<7:49:22,  1.57it/s]
 23%|██▎       | 13476/57600 [2:21:37<7:38:40,  1.60it/s]
 23%|██▎       | 13477/57600 [2:21:38<7:36:27,  1.61it/s]
 23%|██▎       | 13478/57600 [2:21:39<7:42:42,  1.59it/s]
 23%|██▎       | 13479/57600 [2:21:39<7:46:44,  1.58it/s]
 23%|██▎       | 13480/57600 [2:21:40<7:33:09,  1.62it/s]
                                                         
{'loss': 1.2845, 'learning_rate': 7.917770034843205e-07, 'epoch': 148.79}

 23%|██▎       | 13480/57600 [2:21:40<7:33:09,  1.62it/s]
 23%|██▎       | 13481/57600 [2:21:41<7:32:09,  1.63it/s]
 23%|██▎       | 13482/57600 [2:21:41<7:16:21,  1.69it/s]
 23%|██▎       | 13483/57600 [2:21:42<7:27:34,  1.64it/s]
 23%|██▎       | 13484/57600 [2:21:42<7:32:06,  1.63it/s]
 23%|██▎       | 13485/57600 [2:21:43<7:34:10,  1.62it/s]
 23%|██▎       | 13486/57600 [2:21:44<7:53:44,  1.55it/s]
 23%|██▎       | 13487/57600 [2:21:44<7:34:59,  1.62it/s]
 23%|██▎       | 13488/57600 [2:21:45<7:41:33,  1.59it/s]
 23%|██▎       | 13489/57600 [2:21:46<7:43:34,  1.59it/s]
 23%|██▎       | 13490/57600 [2:21:46<7:40:13,  1.60it/s]
 23%|██▎       | 13491/57600 [2:21:47<7:33:09,  1.62it/s]
 23%|██▎       | 13492/57600 [2:21:47<7:25:57,  1.65it/s]
 23%|██▎       | 13493/57600 [2:21:48<7:23:40,  1.66it/s]
 23%|██▎       | 13494/57600 [2:21:49<7:32:28,  1.62it/s]
 23%|██▎       | 13495/57600 [2:21:49<7:26:57,  1.64it/s]
 23%|██▎       | 13496/57600 [2:21:50<7:20:25,  1.67it/s]
 23%|██▎       | 13497/57600 [2:21:50<7:14:09,  1.69it/s]
 23%|██▎       | 13498/57600 [2:21:51<7:09:55,  1.71it/s]
 23%|██▎       | 13499/57600 [2:21:51<7:18:41,  1.68it/s]
 23%|██▎       | 13500/57600 [2:21:52<7:35:42,  1.61it/s]
                                                         
{'loss': 1.3128, 'learning_rate': 7.914634146341463e-07, 'epoch': 149.01}

 23%|██▎       | 13500/57600 [2:21:52<7:35:42,  1.61it/s]
 23%|██▎       | 13501/57600 [2:21:53<7:46:00,  1.58it/s]
 23%|██▎       | 13502/57600 [2:21:53<7:32:51,  1.62it/s]
 23%|██▎       | 13503/57600 [2:21:54<7:49:59,  1.56it/s]
 23%|██▎       | 13504/57600 [2:21:55<7:37:37,  1.61it/s]
 23%|██▎       | 13505/57600 [2:21:55<7:20:34,  1.67it/s]
 23%|██▎       | 13506/57600 [2:21:56<7:15:30,  1.69it/s]
 23%|██▎       | 13507/57600 [2:21:56<7:25:19,  1.65it/s]
 23%|██▎       | 13508/57600 [2:21:57<7:26:12,  1.65it/s]
 23%|██▎       | 13509/57600 [2:21:58<7:27:24,  1.64it/s]
 23%|██▎       | 13510/57600 [2:21:58<7:26:23,  1.65it/s]
 23%|██▎       | 13511/57600 [2:21:59<7:27:25,  1.64it/s]
 23%|██▎       | 13512/57600 [2:22:00<7:38:15,  1.60it/s]
 23%|██▎       | 13513/57600 [2:22:00<7:35:15,  1.61it/s]
 23%|██▎       | 13514/57600 [2:22:01<7:27:27,  1.64it/s]
 23%|██▎       | 13515/57600 [2:22:01<7:35:03,  1.61it/s]
 23%|██▎       | 13516/57600 [2:22:02<7:35:23,  1.61it/s]
 23%|██▎       | 13517/57600 [2:22:03<7:28:05,  1.64it/s]
 23%|██▎       | 13518/57600 [2:22:03<7:40:19,  1.60it/s]
 23%|██▎       | 13519/57600 [2:22:04<7:35:56,  1.61it/s]
 23%|██▎       | 13520/57600 [2:22:04<7:32:12,  1.62it/s]
                                                         
{'loss': 1.3168, 'learning_rate': 7.91149825783972e-07, 'epoch': 149.23}

 23%|██▎       | 13520/57600 [2:22:04<7:32:12,  1.62it/s]
 23%|██▎       | 13521/57600 [2:22:05<7:47:45,  1.57it/s]
 23%|██▎       | 13522/57600 [2:22:06<7:37:04,  1.61it/s]
 23%|██▎       | 13523/57600 [2:22:06<7:22:18,  1.66it/s]
 23%|██▎       | 13524/57600 [2:22:07<7:39:08,  1.60it/s]
 23%|██▎       | 13525/57600 [2:22:08<7:37:50,  1.60it/s]
 23%|██▎       | 13526/57600 [2:22:08<7:36:53,  1.61it/s]
 23%|██▎       | 13527/57600 [2:22:09<7:29:08,  1.64it/s]
 23%|██▎       | 13528/57600 [2:22:09<7:44:55,  1.58it/s]
 23%|██▎       | 13529/57600 [2:22:10<7:54:19,  1.55it/s]
 23%|██▎       | 13530/57600 [2:22:11<7:42:18,  1.59it/s]
 23%|██▎       | 13531/57600 [2:22:11<7:33:33,  1.62it/s]
 23%|██▎       | 13532/57600 [2:22:12<7:23:28,  1.66it/s]
 23%|██▎       | 13533/57600 [2:22:13<7:24:15,  1.65it/s]
 23%|██▎       | 13534/57600 [2:22:13<7:15:11,  1.69it/s]
 23%|██▎       | 13535/57600 [2:22:14<7:22:01,  1.66it/s]
 24%|██▎       | 13536/57600 [2:22:14<7:25:00,  1.65it/s]
 24%|██▎       | 13537/57600 [2:22:15<7:17:04,  1.68it/s]
 24%|██▎       | 13538/57600 [2:22:16<7:29:17,  1.63it/s]
 24%|██▎       | 13539/57600 [2:22:16<7:23:29,  1.66it/s]
 24%|██▎       | 13540/57600 [2:22:17<7:18:21,  1.68it/s]
                                                         
{'loss': 1.2723, 'learning_rate': 7.908362369337979e-07, 'epoch': 149.45}

 24%|██▎       | 13540/57600 [2:22:17<7:18:21,  1.68it/s]
 24%|██▎       | 13541/57600 [2:22:17<7:29:05,  1.64it/s]
 24%|██▎       | 13542/57600 [2:22:18<7:26:27,  1.64it/s]
 24%|██▎       | 13543/57600 [2:22:19<7:24:26,  1.65it/s]
 24%|██▎       | 13544/57600 [2:22:19<7:40:29,  1.59it/s]
 24%|██▎       | 13545/57600 [2:22:20<7:54:04,  1.55it/s]
 24%|██▎       | 13546/57600 [2:22:21<7:46:13,  1.57it/s]
 24%|██▎       | 13547/57600 [2:22:21<7:48:03,  1.57it/s]
 24%|██▎       | 13548/57600 [2:22:22<7:42:28,  1.59it/s]
 24%|██▎       | 13549/57600 [2:22:22<7:24:51,  1.65it/s]
 24%|██▎       | 13550/57600 [2:22:23<7:28:09,  1.64it/s]
 24%|██▎       | 13551/57600 [2:22:23<7:11:44,  1.70it/s]
 24%|██▎       | 13552/57600 [2:22:24<7:19:33,  1.67it/s]
 24%|██▎       | 13553/57600 [2:22:25<7:28:58,  1.64it/s]
 24%|██▎       | 13554/57600 [2:22:25<7:43:56,  1.58it/s]
 24%|██▎       | 13555/57600 [2:22:26<7:29:24,  1.63it/s]
 24%|██▎       | 13556/57600 [2:22:27<7:35:10,  1.61it/s]
 24%|██▎       | 13557/57600 [2:22:27<7:43:23,  1.58it/s]
 24%|██▎       | 13558/57600 [2:22:28<7:26:38,  1.64it/s]
 24%|██▎       | 13559/57600 [2:22:29<7:37:14,  1.61it/s]
 24%|██▎       | 13560/57600 [2:22:29<7:41:17,  1.59it/s]
                                                         
{'loss': 1.3252, 'learning_rate': 7.905226480836238e-07, 'epoch': 149.67}

 24%|██▎       | 13560/57600 [2:22:29<7:41:17,  1.59it/s]
 24%|██▎       | 13561/57600 [2:22:30<7:24:22,  1.65it/s]
 24%|██▎       | 13562/57600 [2:22:30<7:20:38,  1.67it/s]
 24%|██▎       | 13563/57600 [2:22:31<7:32:35,  1.62it/s]
 24%|██▎       | 13564/57600 [2:22:32<7:26:30,  1.64it/s]
 24%|██▎       | 13565/57600 [2:22:32<7:45:58,  1.58it/s]
 24%|██▎       | 13566/57600 [2:22:33<7:44:54,  1.58it/s]
 24%|██▎       | 13567/57600 [2:22:33<7:40:05,  1.60it/s]
 24%|██▎       | 13568/57600 [2:22:34<7:42:29,  1.59it/s]
 24%|██▎       | 13569/57600 [2:22:35<7:41:17,  1.59it/s]
 24%|██▎       | 13570/57600 [2:22:35<7:50:08,  1.56it/s]
 24%|██▎       | 13571/57600 [2:22:36<7:40:32,  1.59it/s]
 24%|██▎       | 13572/57600 [2:22:37<7:51:12,  1.56it/s]
 24%|██▎       | 13573/57600 [2:22:37<7:51:45,  1.56it/s]
 24%|██▎       | 13574/57600 [2:22:38<7:41:05,  1.59it/s]
 24%|██▎       | 13575/57600 [2:22:39<7:53:37,  1.55it/s]
 24%|██▎       | 13576/57600 [2:22:39<7:33:37,  1.62it/s]
 24%|██▎       | 13577/57600 [2:22:40<7:27:53,  1.64it/s]
 24%|██▎       | 13578/57600 [2:22:40<7:32:45,  1.62it/s]
 24%|██▎       | 13579/57600 [2:22:41<7:21:09,  1.66it/s]
 24%|██▎       | 13580/57600 [2:22:42<7:28:52,  1.63it/s]
                                                         
{'loss': 1.3171, 'learning_rate': 7.902090592334494e-07, 'epoch': 149.89}

 24%|██▎       | 13580/57600 [2:22:42<7:28:52,  1.63it/s]
 24%|██▎       | 13581/57600 [2:22:42<7:40:38,  1.59it/s]
 24%|██▎       | 13582/57600 [2:22:43<7:34:50,  1.61it/s]
 24%|██▎       | 13583/57600 [2:22:43<7:34:25,  1.61it/s]
 24%|██▎       | 13584/57600 [2:22:44<7:18:49,  1.67it/s]
 24%|██▎       | 13585/57600 [2:22:45<7:23:42,  1.65it/s]
 24%|██▎       | 13586/57600 [2:22:45<7:27:17,  1.64it/s]
 24%|██▎       | 13587/57600 [2:22:46<7:31:36,  1.62it/s]
 24%|██▎       | 13588/57600 [2:22:46<7:20:46,  1.66it/s]
 24%|██▎       | 13589/57600 [2:22:47<7:21:09,  1.66it/s]
 24%|██▎       | 13590/57600 [2:22:48<7:32:15,  1.62it/s]
 24%|██▎       | 13591/57600 [2:22:48<7:36:37,  1.61it/s]
 24%|██▎       | 13592/57600 [2:22:49<7:36:23,  1.61it/s]
 24%|██▎       | 13593/57600 [2:22:50<7:46:56,  1.57it/s]
 24%|██▎       | 13594/57600 [2:22:50<7:44:28,  1.58it/s]
 24%|██▎       | 13595/57600 [2:22:51<7:31:09,  1.63it/s]
 24%|██▎       | 13596/57600 [2:22:51<7:26:46,  1.64it/s]
 24%|██▎       | 13597/57600 [2:22:52<7:28:49,  1.63it/s]
 24%|██▎       | 13598/57600 [2:22:53<7:55:17,  1.54it/s]
 24%|██▎       | 13599/57600 [2:22:53<7:54:32,  1.55it/s]
 24%|██▎       | 13600/57600 [2:22:54<7:39:32,  1.60it/s]
                                                         
{'loss': 1.2999, 'learning_rate': 7.898954703832752e-07, 'epoch': 150.11}

 24%|██▎       | 13600/57600 [2:22:54<7:39:32,  1.60it/s]
 24%|██▎       | 13601/57600 [2:22:55<7:39:15,  1.60it/s]
 24%|██▎       | 13602/57600 [2:22:55<7:27:18,  1.64it/s]
 24%|██▎       | 13603/57600 [2:22:56<7:39:55,  1.59it/s]
 24%|██▎       | 13604/57600 [2:22:57<7:44:15,  1.58it/s]
 24%|██▎       | 13605/57600 [2:22:57<7:31:46,  1.62it/s]
 24%|██▎       | 13606/57600 [2:22:58<7:31:17,  1.62it/s]
 24%|██▎       | 13607/57600 [2:22:58<7:27:19,  1.64it/s]
 24%|██▎       | 13608/57600 [2:22:59<7:16:25,  1.68it/s]
 24%|██▎       | 13609/57600 [2:22:59<7:23:44,  1.65it/s]
 24%|██▎       | 13610/57600 [2:23:00<7:30:44,  1.63it/s]
 24%|██▎       | 13611/57600 [2:23:01<7:36:29,  1.61it/s]
 24%|██▎       | 13612/57600 [2:23:01<7:39:08,  1.60it/s]
 24%|██▎       | 13613/57600 [2:23:02<7:51:51,  1.55it/s]
 24%|██▎       | 13614/57600 [2:23:03<7:55:05,  1.54it/s]
 24%|██▎       | 13615/57600 [2:23:03<7:37:32,  1.60it/s]
 24%|██▎       | 13616/57600 [2:23:04<7:36:09,  1.61it/s]
 24%|██▎       | 13617/57600 [2:23:04<7:22:07,  1.66it/s]
 24%|██▎       | 13618/57600 [2:23:05<7:21:14,  1.66it/s]
 24%|██▎       | 13619/57600 [2:23:06<7:17:15,  1.68it/s]
 24%|██▎       | 13620/57600 [2:23:06<7:33:35,  1.62it/s]
                                                         
{'loss': 1.3204, 'learning_rate': 7.89581881533101e-07, 'epoch': 150.33}

 24%|██▎       | 13620/57600 [2:23:06<7:33:35,  1.62it/s]
 24%|██▎       | 13621/57600 [2:23:07<7:18:32,  1.67it/s]
 24%|██▎       | 13622/57600 [2:23:08<7:35:57,  1.61it/s]
 24%|██▎       | 13623/57600 [2:23:08<7:36:23,  1.61it/s]
 24%|██▎       | 13624/57600 [2:23:09<7:34:51,  1.61it/s]
 24%|██▎       | 13625/57600 [2:23:09<7:45:37,  1.57it/s]
 24%|██▎       | 13626/57600 [2:23:10<7:49:58,  1.56it/s]
 24%|██▎       | 13627/57600 [2:23:11<7:41:49,  1.59it/s]
 24%|██▎       | 13628/57600 [2:23:11<7:33:28,  1.62it/s]
 24%|██▎       | 13629/57600 [2:23:12<7:27:13,  1.64it/s]
 24%|██▎       | 13630/57600 [2:23:12<7:15:40,  1.68it/s]
 24%|██▎       | 13631/57600 [2:23:13<7:33:45,  1.61it/s]
 24%|██▎       | 13632/57600 [2:23:14<7:23:32,  1.65it/s]
 24%|██▎       | 13633/57600 [2:23:14<7:25:04,  1.65it/s]
 24%|██▎       | 13634/57600 [2:23:15<7:19:49,  1.67it/s]
 24%|██▎       | 13635/57600 [2:23:16<7:17:43,  1.67it/s]
 24%|██▎       | 13636/57600 [2:23:16<7:29:32,  1.63it/s]
 24%|██▎       | 13637/57600 [2:23:17<7:22:38,  1.66it/s]
 24%|██▎       | 13638/57600 [2:23:17<7:40:49,  1.59it/s]
 24%|██▎       | 13639/57600 [2:23:18<7:36:20,  1.61it/s]
 24%|██▎       | 13640/57600 [2:23:19<7:20:52,  1.66it/s]
                                                         
{'loss': 1.3109, 'learning_rate': 7.892682926829268e-07, 'epoch': 150.55}

 24%|██▎       | 13640/57600 [2:23:19<7:20:52,  1.66it/s]
 24%|██▎       | 13641/57600 [2:23:19<7:18:46,  1.67it/s]
 24%|██▎       | 13642/57600 [2:23:20<7:49:15,  1.56it/s]
 24%|██▎       | 13643/57600 [2:23:21<7:57:54,  1.53it/s]
 24%|██▎       | 13644/57600 [2:23:21<7:31:58,  1.62it/s]
 24%|██▎       | 13645/57600 [2:23:22<7:15:23,  1.68it/s]
 24%|██▎       | 13646/57600 [2:23:22<7:19:08,  1.67it/s]
 24%|██▎       | 13647/57600 [2:23:23<7:20:38,  1.66it/s]
 24%|██▎       | 13648/57600 [2:23:23<7:17:57,  1.67it/s]
 24%|██▎       | 13649/57600 [2:23:24<7:44:54,  1.58it/s]
 24%|██▎       | 13650/57600 [2:23:25<7:44:55,  1.58it/s]
 24%|██▎       | 13651/57600 [2:23:26<7:49:17,  1.56it/s]
 24%|██▎       | 13652/57600 [2:23:26<7:51:10,  1.55it/s]
 24%|██▎       | 13653/57600 [2:23:27<8:08:39,  1.50it/s]
 24%|██▎       | 13654/57600 [2:23:28<8:04:16,  1.51it/s]
 24%|██▎       | 13655/57600 [2:23:28<7:56:20,  1.54it/s]
 24%|██▎       | 13656/57600 [2:23:29<7:40:04,  1.59it/s]
 24%|██▎       | 13657/57600 [2:23:29<7:32:47,  1.62it/s]
 24%|██▎       | 13658/57600 [2:23:30<7:31:06,  1.62it/s]
 24%|██▎       | 13659/57600 [2:23:31<7:38:36,  1.60it/s]
 24%|██▎       | 13660/57600 [2:23:31<7:35:08,  1.61it/s]
                                                         
{'loss': 1.2844, 'learning_rate': 7.889547038327525e-07, 'epoch': 150.77}

 24%|██▎       | 13660/57600 [2:23:31<7:35:08,  1.61it/s]
 24%|██▎       | 13661/57600 [2:23:32<7:35:43,  1.61it/s]
 24%|██▎       | 13662/57600 [2:23:32<7:30:46,  1.62it/s]
 24%|██▎       | 13663/57600 [2:23:33<7:18:09,  1.67it/s]
 24%|██▎       | 13664/57600 [2:23:34<7:11:05,  1.70it/s]
 24%|██▎       | 13665/57600 [2:23:34<7:13:50,  1.69it/s]
 24%|██▎       | 13666/57600 [2:23:35<7:12:06,  1.69it/s]
 24%|██▎       | 13667/57600 [2:23:35<7:23:02,  1.65it/s]
 24%|██▎       | 13668/57600 [2:23:36<7:19:53,  1.66it/s]
 24%|██▎       | 13669/57600 [2:23:37<7:12:50,  1.69it/s]
 24%|██▎       | 13670/57600 [2:23:37<7:14:24,  1.69it/s]
 24%|██▎       | 13671/57600 [2:23:38<7:26:40,  1.64it/s]
 24%|██▎       | 13672/57600 [2:23:38<7:20:54,  1.66it/s]
 24%|██▎       | 13673/57600 [2:23:39<7:21:06,  1.66it/s]
 24%|██▎       | 13674/57600 [2:23:40<7:38:36,  1.60it/s]
 24%|██▎       | 13675/57600 [2:23:40<7:31:25,  1.62it/s]
 24%|██▎       | 13676/57600 [2:23:41<7:37:53,  1.60it/s]
 24%|██▎       | 13677/57600 [2:23:42<7:48:26,  1.56it/s]
 24%|██▎       | 13678/57600 [2:23:42<7:49:03,  1.56it/s]
 24%|██▎       | 13679/57600 [2:23:43<7:45:05,  1.57it/s]
 24%|██▍       | 13680/57600 [2:23:43<7:30:53,  1.62it/s]
                                                         
{'loss': 1.3289, 'learning_rate': 7.886411149825784e-07, 'epoch': 150.99}

 24%|██▍       | 13680/57600 [2:23:43<7:30:53,  1.62it/s]
 24%|██▍       | 13681/57600 [2:23:44<7:47:00,  1.57it/s]
 24%|██▍       | 13682/57600 [2:23:45<7:31:14,  1.62it/s]
 24%|██▍       | 13683/57600 [2:23:45<7:23:00,  1.65it/s]
 24%|██▍       | 13684/57600 [2:23:46<7:19:24,  1.67it/s]
 24%|██▍       | 13685/57600 [2:23:46<7:24:28,  1.65it/s]
 24%|██▍       | 13686/57600 [2:23:47<7:30:22,  1.63it/s]
 24%|██▍       | 13687/57600 [2:23:48<7:38:03,  1.60it/s]
 24%|██▍       | 13688/57600 [2:23:48<7:26:20,  1.64it/s]
 24%|██▍       | 13689/57600 [2:23:49<7:20:39,  1.66it/s]
 24%|██▍       | 13690/57600 [2:23:50<7:33:49,  1.61it/s]
 24%|██▍       | 13691/57600 [2:23:50<7:20:48,  1.66it/s]
 24%|██▍       | 13692/57600 [2:23:51<7:22:34,  1.65it/s]
 24%|██▍       | 13693/57600 [2:23:51<7:23:56,  1.65it/s]
 24%|██▍       | 13694/57600 [2:23:52<7:39:19,  1.59it/s]
 24%|██▍       | 13695/57600 [2:23:53<7:50:53,  1.55it/s]
 24%|██▍       | 13696/57600 [2:23:53<7:28:06,  1.63it/s]
 24%|██▍       | 13697/57600 [2:23:54<7:40:56,  1.59it/s]
 24%|██▍       | 13698/57600 [2:23:55<7:39:57,  1.59it/s]
 24%|██▍       | 13699/57600 [2:23:55<7:46:33,  1.57it/s]
 24%|██▍       | 13700/57600 [2:23:56<7:57:22,  1.53it/s]
                                                         
{'loss': 1.2994, 'learning_rate': 7.883275261324042e-07, 'epoch': 151.21}

 24%|██▍       | 13700/57600 [2:23:56<7:57:22,  1.53it/s]
 24%|██▍       | 13701/57600 [2:23:56<7:52:10,  1.55it/s]
 24%|██▍       | 13702/57600 [2:23:57<7:34:18,  1.61it/s]
 24%|██▍       | 13703/57600 [2:23:58<7:55:38,  1.54it/s]
 24%|██▍       | 13704/57600 [2:23:58<7:36:40,  1.60it/s]
 24%|██▍       | 13705/57600 [2:23:59<7:33:43,  1.61it/s]
 24%|██▍       | 13706/57600 [2:24:00<7:24:12,  1.65it/s]
 24%|██▍       | 13707/57600 [2:24:00<7:20:36,  1.66it/s]
 24%|██▍       | 13708/57600 [2:24:01<7:23:00,  1.65it/s]
 24%|██▍       | 13709/57600 [2:24:01<7:22:12,  1.65it/s]
 24%|██▍       | 13710/57600 [2:24:02<7:17:15,  1.67it/s]
 24%|██▍       | 13711/57600 [2:24:03<7:40:24,  1.59it/s]
 24%|██▍       | 13712/57600 [2:24:03<7:30:36,  1.62it/s]
 24%|██▍       | 13713/57600 [2:24:04<7:18:36,  1.67it/s]
 24%|██▍       | 13714/57600 [2:24:04<7:14:24,  1.68it/s]
 24%|██▍       | 13715/57600 [2:24:05<7:13:25,  1.69it/s]
 24%|██▍       | 13716/57600 [2:24:06<7:19:56,  1.66it/s]
 24%|██▍       | 13717/57600 [2:24:06<7:12:24,  1.69it/s]
 24%|██▍       | 13718/57600 [2:24:07<7:15:19,  1.68it/s]
 24%|██▍       | 13719/57600 [2:24:07<7:22:18,  1.65it/s]
 24%|██▍       | 13720/57600 [2:24:08<7:09:48,  1.70it/s]
                                                         
{'loss': 1.3577, 'learning_rate': 7.8801393728223e-07, 'epoch': 151.43}

 24%|██▍       | 13720/57600 [2:24:08<7:09:48,  1.70it/s]
 24%|██▍       | 13721/57600 [2:24:08<7:05:42,  1.72it/s]
 24%|██▍       | 13722/57600 [2:24:09<7:02:11,  1.73it/s]
 24%|██▍       | 13723/57600 [2:24:10<7:07:37,  1.71it/s]
 24%|██▍       | 13724/57600 [2:24:10<7:25:45,  1.64it/s]
 24%|██▍       | 13725/57600 [2:24:11<7:32:55,  1.61it/s]
 24%|██▍       | 13726/57600 [2:24:12<7:34:41,  1.61it/s]
 24%|██▍       | 13727/57600 [2:24:12<7:31:33,  1.62it/s]
 24%|██▍       | 13728/57600 [2:24:13<7:26:34,  1.64it/s]
 24%|██▍       | 13729/57600 [2:24:13<7:29:05,  1.63it/s]
 24%|██▍       | 13730/57600 [2:24:14<7:14:47,  1.68it/s]
 24%|██▍       | 13731/57600 [2:24:15<7:23:46,  1.65it/s]
 24%|██▍       | 13732/57600 [2:24:15<7:31:34,  1.62it/s]
 24%|██▍       | 13733/57600 [2:24:16<7:25:55,  1.64it/s]
 24%|██▍       | 13734/57600 [2:24:16<7:17:44,  1.67it/s]
 24%|██▍       | 13735/57600 [2:24:17<7:32:13,  1.62it/s]
 24%|██▍       | 13736/57600 [2:24:18<7:44:06,  1.58it/s]
 24%|██▍       | 13737/57600 [2:24:18<7:41:42,  1.58it/s]
 24%|██▍       | 13738/57600 [2:24:19<7:43:36,  1.58it/s]
 24%|██▍       | 13739/57600 [2:24:20<7:45:36,  1.57it/s]
 24%|██▍       | 13740/57600 [2:24:20<7:29:06,  1.63it/s]
                                                         
{'loss': 1.3082, 'learning_rate': 7.877003484320557e-07, 'epoch': 151.66}

 24%|██▍       | 13740/57600 [2:24:20<7:29:06,  1.63it/s]
 24%|██▍       | 13741/57600 [2:24:21<7:20:07,  1.66it/s]
 24%|██▍       | 13742/57600 [2:24:21<7:12:05,  1.69it/s]
 24%|██▍       | 13743/57600 [2:24:22<7:11:15,  1.69it/s]
 24%|██▍       | 13744/57600 [2:24:23<7:21:32,  1.66it/s]
 24%|██▍       | 13745/57600 [2:24:23<7:09:55,  1.70it/s]
 24%|██▍       | 13746/57600 [2:24:24<7:28:34,  1.63it/s]
 24%|██▍       | 13747/57600 [2:24:24<7:25:02,  1.64it/s]
 24%|██▍       | 13748/57600 [2:24:25<7:22:53,  1.65it/s]
 24%|██▍       | 13749/57600 [2:24:26<7:13:33,  1.69it/s]
 24%|██▍       | 13750/57600 [2:24:26<7:21:11,  1.66it/s]
 24%|██▍       | 13751/57600 [2:24:27<7:19:33,  1.66it/s]
 24%|██▍       | 13752/57600 [2:24:27<7:26:43,  1.64it/s]
 24%|██▍       | 13753/57600 [2:24:28<7:16:58,  1.67it/s]
 24%|██▍       | 13754/57600 [2:24:29<7:24:18,  1.64it/s]
 24%|██▍       | 13755/57600 [2:24:29<7:23:04,  1.65it/s]
 24%|██▍       | 13756/57600 [2:24:30<7:25:49,  1.64it/s]
 24%|██▍       | 13757/57600 [2:24:30<7:35:03,  1.61it/s]
 24%|██▍       | 13758/57600 [2:24:31<7:43:56,  1.57it/s]
 24%|██▍       | 13759/57600 [2:24:32<7:29:04,  1.63it/s]
 24%|██▍       | 13760/57600 [2:24:32<7:44:13,  1.57it/s]
                                                         
{'loss': 1.327, 'learning_rate': 7.873867595818815e-07, 'epoch': 151.88}

 24%|██▍       | 13760/57600 [2:24:32<7:44:13,  1.57it/s]
 24%|██▍       | 13761/57600 [2:24:33<7:43:03,  1.58it/s]
 24%|██▍       | 13762/57600 [2:24:34<7:26:24,  1.64it/s]
 24%|██▍       | 13763/57600 [2:24:34<7:37:41,  1.60it/s]
 24%|██▍       | 13764/57600 [2:24:35<7:42:50,  1.58it/s]
 24%|██▍       | 13765/57600 [2:24:36<7:44:09,  1.57it/s]
 24%|██▍       | 13766/57600 [2:24:36<7:59:47,  1.52it/s]
 24%|██▍       | 13767/57600 [2:24:37<7:58:52,  1.53it/s]
 24%|██▍       | 13768/57600 [2:24:37<7:47:08,  1.56it/s]
 24%|██▍       | 13769/57600 [2:24:38<7:48:39,  1.56it/s]
 24%|██▍       | 13770/57600 [2:24:39<7:36:39,  1.60it/s]
 24%|██▍       | 13771/57600 [2:24:39<7:36:50,  1.60it/s]
 24%|██▍       | 13772/57600 [2:24:40<7:46:41,  1.57it/s]
 24%|██▍       | 13773/57600 [2:24:41<7:47:13,  1.56it/s]
 24%|██▍       | 13774/57600 [2:24:41<7:46:00,  1.57it/s]
 24%|██▍       | 13775/57600 [2:24:42<7:51:23,  1.55it/s]
 24%|██▍       | 13776/57600 [2:24:43<7:42:25,  1.58it/s]
 24%|██▍       | 13777/57600 [2:24:43<7:31:04,  1.62it/s]
 24%|██▍       | 13778/57600 [2:24:44<7:22:14,  1.65it/s]
 24%|██▍       | 13779/57600 [2:24:44<7:39:33,  1.59it/s]
 24%|██▍       | 13780/57600 [2:24:45<7:46:57,  1.56it/s]
                                                         
{'loss': 1.2884, 'learning_rate': 7.870731707317073e-07, 'epoch': 152.1}

 24%|██▍       | 13780/57600 [2:24:45<7:46:57,  1.56it/s]
 24%|██▍       | 13781/57600 [2:24:46<7:36:04,  1.60it/s]
 24%|██▍       | 13782/57600 [2:24:46<7:37:07,  1.60it/s]
 24%|██▍       | 13783/57600 [2:24:47<7:39:24,  1.59it/s]
 24%|██▍       | 13784/57600 [2:24:48<7:43:10,  1.58it/s]
 24%|██▍       | 13785/57600 [2:24:48<7:42:31,  1.58it/s]
 24%|██▍       | 13786/57600 [2:24:49<7:45:55,  1.57it/s]
 24%|██▍       | 13787/57600 [2:24:49<7:31:46,  1.62it/s]
 24%|██▍       | 13788/57600 [2:24:50<7:37:23,  1.60it/s]
 24%|██▍       | 13789/57600 [2:24:51<7:34:14,  1.61it/s]
 24%|██▍       | 13790/57600 [2:24:51<7:36:53,  1.60it/s]
 24%|██▍       | 13791/57600 [2:24:52<7:42:54,  1.58it/s]
 24%|██▍       | 13792/57600 [2:24:53<7:52:16,  1.55it/s]
 24%|██▍       | 13793/57600 [2:24:53<7:40:37,  1.59it/s]
 24%|██▍       | 13794/57600 [2:24:54<7:24:26,  1.64it/s]
 24%|██▍       | 13795/57600 [2:24:54<7:41:15,  1.58it/s]
 24%|██▍       | 13796/57600 [2:24:55<7:35:43,  1.60it/s]
 24%|██▍       | 13797/57600 [2:24:56<7:32:17,  1.61it/s]
 24%|██▍       | 13798/57600 [2:24:56<7:35:47,  1.60it/s]
 24%|██▍       | 13799/57600 [2:24:57<7:51:52,  1.55it/s]
 24%|██▍       | 13800/57600 [2:24:58<8:01:05,  1.52it/s]
                                                         
{'loss': 1.3056, 'learning_rate': 7.86759581881533e-07, 'epoch': 152.32}

 24%|██▍       | 13800/57600 [2:24:58<8:01:05,  1.52it/s]
 24%|██▍       | 13801/57600 [2:24:58<7:50:58,  1.55it/s]
 24%|██▍       | 13802/57600 [2:24:59<7:41:38,  1.58it/s]
 24%|██▍       | 13803/57600 [2:24:59<7:23:49,  1.64it/s]
 24%|██▍       | 13804/57600 [2:25:00<7:51:55,  1.55it/s]
 24%|██▍       | 13805/57600 [2:25:01<7:46:38,  1.56it/s]
 24%|██▍       | 13806/57600 [2:25:02<7:51:11,  1.55it/s]
 24%|██▍       | 13807/57600 [2:25:02<7:42:24,  1.58it/s]
 24%|██▍       | 13808/57600 [2:25:03<7:33:45,  1.61it/s]
 24%|██▍       | 13809/57600 [2:25:03<7:46:51,  1.56it/s]
 24%|██▍       | 13810/57600 [2:25:04<7:25:27,  1.64it/s]
 24%|██▍       | 13811/57600 [2:25:05<7:20:17,  1.66it/s]
 24%|██▍       | 13812/57600 [2:25:05<7:19:45,  1.66it/s]
 24%|██▍       | 13813/57600 [2:25:06<7:19:50,  1.66it/s]
 24%|██▍       | 13814/57600 [2:25:06<7:22:27,  1.65it/s]
 24%|██▍       | 13815/57600 [2:25:07<7:16:39,  1.67it/s]
 24%|██▍       | 13816/57600 [2:25:07<7:12:19,  1.69it/s]
 24%|██▍       | 13817/57600 [2:25:08<7:39:41,  1.59it/s]
 24%|██▍       | 13818/57600 [2:25:09<7:40:47,  1.58it/s]
 24%|██▍       | 13819/57600 [2:25:09<7:24:36,  1.64it/s]
 24%|██▍       | 13820/57600 [2:25:10<7:26:43,  1.63it/s]
                                                         
{'loss': 1.3033, 'learning_rate': 7.864459930313588e-07, 'epoch': 152.54}

 24%|██▍       | 13820/57600 [2:25:10<7:26:43,  1.63it/s]
 24%|██▍       | 13821/57600 [2:25:11<7:23:15,  1.65it/s]
 24%|██▍       | 13822/57600 [2:25:11<7:19:07,  1.66it/s]
 24%|██▍       | 13823/57600 [2:25:12<7:12:10,  1.69it/s]
 24%|██▍       | 13824/57600 [2:25:12<7:13:25,  1.68it/s]
 24%|██▍       | 13825/57600 [2:25:13<7:19:54,  1.66it/s]
 24%|██▍       | 13826/57600 [2:25:14<7:26:08,  1.64it/s]
 24%|██▍       | 13827/57600 [2:25:14<7:18:48,  1.66it/s]
 24%|██▍       | 13828/57600 [2:25:15<7:17:15,  1.67it/s]
 24%|██▍       | 13829/57600 [2:25:15<7:15:57,  1.67it/s]
 24%|██▍       | 13830/57600 [2:25:16<7:16:43,  1.67it/s]
 24%|██▍       | 13831/57600 [2:25:17<7:23:20,  1.65it/s]
 24%|██▍       | 13832/57600 [2:25:17<7:16:02,  1.67it/s]
 24%|██▍       | 13833/57600 [2:25:18<7:08:29,  1.70it/s]
 24%|██▍       | 13834/57600 [2:25:18<7:10:32,  1.69it/s]
 24%|██▍       | 13835/57600 [2:25:19<7:56:18,  1.53it/s]
 24%|██▍       | 13836/57600 [2:25:20<7:49:38,  1.55it/s]
 24%|██▍       | 13837/57600 [2:25:20<7:36:22,  1.60it/s]
 24%|██▍       | 13838/57600 [2:25:21<7:40:53,  1.58it/s]
 24%|██▍       | 13839/57600 [2:25:22<7:32:58,  1.61it/s]
 24%|██▍       | 13840/57600 [2:25:22<7:30:57,  1.62it/s]
                                                         
{'loss': 1.3124, 'learning_rate': 7.861324041811847e-07, 'epoch': 152.76}

 24%|██▍       | 13840/57600 [2:25:22<7:30:57,  1.62it/s]
 24%|██▍       | 13841/57600 [2:25:23<7:40:36,  1.58it/s]
 24%|██▍       | 13842/57600 [2:25:24<7:51:26,  1.55it/s]
 24%|██▍       | 13843/57600 [2:25:24<7:42:24,  1.58it/s]
 24%|██▍       | 13844/57600 [2:25:25<7:42:23,  1.58it/s]
 24%|██▍       | 13845/57600 [2:25:25<7:31:57,  1.61it/s]
 24%|██▍       | 13846/57600 [2:25:26<7:20:21,  1.66it/s]
 24%|██▍       | 13847/57600 [2:25:27<7:30:16,  1.62it/s]
 24%|██▍       | 13848/57600 [2:25:27<7:23:13,  1.65it/s]
 24%|██▍       | 13849/57600 [2:25:28<7:16:01,  1.67it/s]
 24%|██▍       | 13850/57600 [2:25:28<7:17:28,  1.67it/s]
 24%|██▍       | 13851/57600 [2:25:29<7:08:18,  1.70it/s]
 24%|██▍       | 13852/57600 [2:25:30<7:10:36,  1.69it/s]
 24%|██▍       | 13853/57600 [2:25:30<7:05:12,  1.71it/s]
 24%|██▍       | 13854/57600 [2:25:31<6:56:13,  1.75it/s]
 24%|██▍       | 13855/57600 [2:25:31<7:03:59,  1.72it/s]
 24%|██▍       | 13856/57600 [2:25:32<7:14:05,  1.68it/s]
 24%|██▍       | 13857/57600 [2:25:33<7:29:23,  1.62it/s]
 24%|██▍       | 13858/57600 [2:25:33<7:31:34,  1.61it/s]
 24%|██▍       | 13859/57600 [2:25:34<7:19:55,  1.66it/s]
 24%|██▍       | 13860/57600 [2:25:34<7:26:10,  1.63it/s]
                                                         
{'loss': 1.3514, 'learning_rate': 7.858188153310104e-07, 'epoch': 152.98}

 24%|██▍       | 13860/57600 [2:25:34<7:26:10,  1.63it/s]
 24%|██▍       | 13861/57600 [2:25:35<7:19:04,  1.66it/s]
 24%|██▍       | 13862/57600 [2:25:36<7:53:03,  1.54it/s]
 24%|██▍       | 13863/57600 [2:25:36<7:55:07,  1.53it/s]
 24%|██▍       | 13864/57600 [2:25:37<7:34:59,  1.60it/s]
 24%|██▍       | 13865/57600 [2:25:38<7:32:48,  1.61it/s]
 24%|██▍       | 13866/57600 [2:25:38<7:30:02,  1.62it/s]
 24%|██▍       | 13867/57600 [2:25:39<7:45:06,  1.57it/s]
 24%|██▍       | 13868/57600 [2:25:39<7:42:39,  1.58it/s]
 24%|██▍       | 13869/57600 [2:25:40<7:37:56,  1.59it/s]
 24%|██▍       | 13870/57600 [2:25:41<7:37:11,  1.59it/s]
 24%|██▍       | 13871/57600 [2:25:41<7:32:24,  1.61it/s]
 24%|██▍       | 13872/57600 [2:25:42<7:30:27,  1.62it/s]
 24%|██▍       | 13873/57600 [2:25:42<7:22:51,  1.65it/s]
 24%|██▍       | 13874/57600 [2:25:43<7:20:55,  1.65it/s]
 24%|██▍       | 13875/57600 [2:25:44<7:08:02,  1.70it/s]
 24%|██▍       | 13876/57600 [2:25:44<7:13:36,  1.68it/s]
 24%|██▍       | 13877/57600 [2:25:45<7:26:11,  1.63it/s]
 24%|██▍       | 13878/57600 [2:25:45<7:21:47,  1.65it/s]
 24%|██▍       | 13879/57600 [2:25:46<7:20:48,  1.65it/s]
 24%|██▍       | 13880/57600 [2:25:47<7:31:53,  1.61it/s]
                                                         
{'loss': 1.3502, 'learning_rate': 7.855052264808362e-07, 'epoch': 153.2}

 24%|██▍       | 13880/57600 [2:25:47<7:31:53,  1.61it/s]
 24%|██▍       | 13881/57600 [2:25:47<7:20:50,  1.65it/s]
 24%|██▍       | 13882/57600 [2:25:48<7:18:57,  1.66it/s]
 24%|██▍       | 13883/57600 [2:25:49<7:23:34,  1.64it/s]
 24%|██▍       | 13884/57600 [2:25:49<7:30:21,  1.62it/s]
 24%|██▍       | 13885/57600 [2:25:50<7:17:06,  1.67it/s]
 24%|██▍       | 13886/57600 [2:25:50<7:25:32,  1.64it/s]
 24%|██▍       | 13887/57600 [2:25:51<7:33:02,  1.61it/s]
 24%|██▍       | 13888/57600 [2:25:52<7:22:09,  1.65it/s]
 24%|██▍       | 13889/57600 [2:25:52<7:14:34,  1.68it/s]
 24%|██▍       | 13890/57600 [2:25:53<7:34:10,  1.60it/s]
 24%|██▍       | 13891/57600 [2:25:53<7:26:12,  1.63it/s]
 24%|██▍       | 13892/57600 [2:25:54<7:20:55,  1.65it/s]
 24%|██▍       | 13893/57600 [2:25:55<7:11:25,  1.69it/s]
 24%|██▍       | 13894/57600 [2:25:55<7:10:58,  1.69it/s]
 24%|██▍       | 13895/57600 [2:25:56<7:16:47,  1.67it/s]
 24%|██▍       | 13896/57600 [2:25:56<7:27:21,  1.63it/s]
 24%|██▍       | 13897/57600 [2:25:57<7:28:38,  1.62it/s]
 24%|██▍       | 13898/57600 [2:25:58<7:22:39,  1.65it/s]
 24%|██▍       | 13899/57600 [2:25:58<7:29:43,  1.62it/s]
 24%|██▍       | 13900/57600 [2:25:59<7:27:58,  1.63it/s]
                                                         
{'loss': 1.3594, 'learning_rate': 7.851916376306619e-07, 'epoch': 153.42}

 24%|██▍       | 13900/57600 [2:25:59<7:27:58,  1.63it/s]
 24%|██▍       | 13901/57600 [2:25:59<7:18:19,  1.66it/s]
 24%|██▍       | 13902/57600 [2:26:00<7:12:29,  1.68it/s]
 24%|██▍       | 13903/57600 [2:26:01<7:07:36,  1.70it/s]
 24%|██▍       | 13904/57600 [2:26:01<7:31:29,  1.61it/s]
 24%|██▍       | 13905/57600 [2:26:02<7:59:34,  1.52it/s]
 24%|██▍       | 13906/57600 [2:26:03<7:59:47,  1.52it/s]
 24%|██▍       | 13907/57600 [2:26:03<8:00:16,  1.52it/s]
 24%|██▍       | 13908/57600 [2:26:04<7:37:21,  1.59it/s]
 24%|██▍       | 13909/57600 [2:26:05<7:35:37,  1.60it/s]
 24%|██▍       | 13910/57600 [2:26:05<7:28:43,  1.62it/s]
 24%|██▍       | 13911/57600 [2:26:06<7:32:18,  1.61it/s]
 24%|██▍       | 13912/57600 [2:26:06<7:33:29,  1.61it/s]
 24%|██▍       | 13913/57600 [2:26:07<7:20:50,  1.65it/s]
 24%|██▍       | 13914/57600 [2:26:08<7:20:57,  1.65it/s]
 24%|██▍       | 13915/57600 [2:26:08<7:22:12,  1.65it/s]
 24%|██▍       | 13916/57600 [2:26:09<7:22:05,  1.65it/s]
 24%|██▍       | 13917/57600 [2:26:09<7:31:38,  1.61it/s]
 24%|██▍       | 13918/57600 [2:26:10<7:27:03,  1.63it/s]
 24%|██▍       | 13919/57600 [2:26:11<7:15:09,  1.67it/s]
 24%|██▍       | 13920/57600 [2:26:11<7:10:54,  1.69it/s]
                                                         
{'loss': 1.3061, 'learning_rate': 7.848780487804878e-07, 'epoch': 153.64}

 24%|██▍       | 13920/57600 [2:26:11<7:10:54,  1.69it/s]
 24%|██▍       | 13921/57600 [2:26:12<7:12:59,  1.68it/s]
 24%|██▍       | 13922/57600 [2:26:12<7:08:35,  1.70it/s]
 24%|██▍       | 13923/57600 [2:26:13<7:24:33,  1.64it/s]
 24%|██▍       | 13924/57600 [2:26:14<7:27:48,  1.63it/s]
 24%|██▍       | 13925/57600 [2:26:14<7:20:29,  1.65it/s]
 24%|██▍       | 13926/57600 [2:26:15<7:20:05,  1.65it/s]
 24%|██▍       | 13927/57600 [2:26:15<7:13:38,  1.68it/s]
 24%|██▍       | 13928/57600 [2:26:16<7:21:46,  1.65it/s]
 24%|██▍       | 13929/57600 [2:26:17<7:21:53,  1.65it/s]
 24%|██▍       | 13930/57600 [2:26:17<7:18:38,  1.66it/s]
 24%|██▍       | 13931/57600 [2:26:18<7:18:06,  1.66it/s]
 24%|██▍       | 13932/57600 [2:26:19<7:34:28,  1.60it/s]
 24%|██▍       | 13933/57600 [2:26:19<7:42:48,  1.57it/s]
 24%|██▍       | 13934/57600 [2:26:20<7:35:28,  1.60it/s]
 24%|██▍       | 13935/57600 [2:26:20<7:33:43,  1.60it/s]
 24%|██▍       | 13936/57600 [2:26:21<7:41:23,  1.58it/s]
 24%|██▍       | 13937/57600 [2:26:22<7:44:18,  1.57it/s]
 24%|██▍       | 13938/57600 [2:26:22<7:43:53,  1.57it/s]
 24%|██▍       | 13939/57600 [2:26:23<7:29:14,  1.62it/s]
 24%|██▍       | 13940/57600 [2:26:24<7:26:15,  1.63it/s]
                                                         
{'loss': 1.2751, 'learning_rate': 7.845644599303136e-07, 'epoch': 153.86}

 24%|██▍       | 13940/57600 [2:26:24<7:26:15,  1.63it/s]
 24%|██▍       | 13941/57600 [2:26:24<7:34:53,  1.60it/s]
 24%|██▍       | 13942/57600 [2:26:25<7:47:29,  1.56it/s]
 24%|██▍       | 13943/57600 [2:26:25<7:31:42,  1.61it/s]
 24%|██▍       | 13944/57600 [2:26:26<7:34:07,  1.60it/s]
 24%|██▍       | 13945/57600 [2:26:27<7:27:30,  1.63it/s]
 24%|██▍       | 13946/57600 [2:26:27<7:28:46,  1.62it/s]
 24%|██▍       | 13947/57600 [2:26:28<7:29:57,  1.62it/s]
 24%|██▍       | 13948/57600 [2:26:28<7:24:13,  1.64it/s]
 24%|██▍       | 13949/57600 [2:26:29<7:19:37,  1.65it/s]
 24%|██▍       | 13950/57600 [2:26:30<7:17:56,  1.66it/s]
 24%|██▍       | 13951/57600 [2:26:30<7:19:09,  1.66it/s]
 24%|██▍       | 13952/57600 [2:26:31<7:11:20,  1.69it/s]
 24%|██▍       | 13953/57600 [2:26:32<7:51:41,  1.54it/s]
 24%|██▍       | 13954/57600 [2:26:32<7:39:10,  1.58it/s]
 24%|██▍       | 13955/57600 [2:26:33<7:33:28,  1.60it/s]
 24%|██▍       | 13956/57600 [2:26:33<7:26:01,  1.63it/s]
 24%|██▍       | 13957/57600 [2:26:34<7:36:31,  1.59it/s]
 24%|██▍       | 13958/57600 [2:26:35<7:43:40,  1.57it/s]
 24%|██▍       | 13959/57600 [2:26:35<7:40:27,  1.58it/s]
 24%|██▍       | 13960/57600 [2:26:36<7:37:59,  1.59it/s]
                                                         
{'loss': 1.3334, 'learning_rate': 7.842508710801393e-07, 'epoch': 154.08}

 24%|██▍       | 13960/57600 [2:26:36<7:37:59,  1.59it/s]
 24%|██▍       | 13961/57600 [2:26:37<7:35:24,  1.60it/s]
 24%|██▍       | 13962/57600 [2:26:37<7:26:50,  1.63it/s]
 24%|██▍       | 13963/57600 [2:26:38<7:10:47,  1.69it/s]
 24%|██▍       | 13964/57600 [2:26:38<7:11:28,  1.69it/s]
 24%|██▍       | 13965/57600 [2:26:39<7:09:36,  1.69it/s]
 24%|██▍       | 13966/57600 [2:26:39<6:57:24,  1.74it/s]
 24%|██▍       | 13967/57600 [2:26:40<7:09:50,  1.69it/s]
 24%|██▍       | 13968/57600 [2:26:41<7:11:11,  1.69it/s]
 24%|██▍       | 13969/57600 [2:26:41<7:11:47,  1.68it/s]
 24%|██▍       | 13970/57600 [2:26:42<7:13:59,  1.68it/s]
 24%|██▍       | 13971/57600 [2:26:42<7:13:44,  1.68it/s]
 24%|██▍       | 13972/57600 [2:26:43<7:19:17,  1.66it/s]
 24%|██▍       | 13973/57600 [2:26:44<7:19:52,  1.65it/s]
 24%|██▍       | 13974/57600 [2:26:44<7:19:53,  1.65it/s]
 24%|██▍       | 13975/57600 [2:26:45<7:19:16,  1.66it/s]
 24%|██▍       | 13976/57600 [2:26:46<7:38:59,  1.58it/s]
 24%|██▍       | 13977/57600 [2:26:46<7:34:41,  1.60it/s]
 24%|██▍       | 13978/57600 [2:26:47<7:27:44,  1.62it/s]
 24%|██▍       | 13979/57600 [2:26:47<7:26:58,  1.63it/s]
 24%|██▍       | 13980/57600 [2:26:48<7:25:06,  1.63it/s]
                                                         
{'loss': 1.337, 'learning_rate': 7.839372822299652e-07, 'epoch': 154.3}

 24%|██▍       | 13980/57600 [2:26:48<7:25:06,  1.63it/s]
 24%|██▍       | 13981/57600 [2:26:49<7:38:06,  1.59it/s]
 24%|██▍       | 13982/57600 [2:26:49<7:25:32,  1.63it/s]
 24%|██▍       | 13983/57600 [2:26:50<7:28:48,  1.62it/s]
 24%|██▍       | 13984/57600 [2:26:50<7:19:38,  1.65it/s]
 24%|██▍       | 13985/57600 [2:26:51<7:21:29,  1.65it/s]
 24%|██▍       | 13986/57600 [2:26:52<7:44:50,  1.56it/s]
 24%|██▍       | 13987/57600 [2:26:52<7:39:28,  1.58it/s]
 24%|██▍       | 13988/57600 [2:26:53<7:35:43,  1.59it/s]
 24%|██▍       | 13989/57600 [2:26:54<7:29:41,  1.62it/s]
 24%|██▍       | 13990/57600 [2:26:54<7:48:40,  1.55it/s]
 24%|██▍       | 13991/57600 [2:26:55<7:29:37,  1.62it/s]
 24%|██▍       | 13992/57600 [2:26:56<7:31:14,  1.61it/s]
 24%|██▍       | 13993/57600 [2:26:56<7:21:10,  1.65it/s]
 24%|██▍       | 13994/57600 [2:26:57<7:24:48,  1.63it/s]
 24%|██▍       | 13995/57600 [2:26:57<7:09:51,  1.69it/s]
 24%|██▍       | 13996/57600 [2:26:58<7:11:07,  1.69it/s]
 24%|██▍       | 13997/57600 [2:26:59<7:25:42,  1.63it/s]
 24%|██▍       | 13998/57600 [2:26:59<7:29:09,  1.62it/s]
 24%|██▍       | 13999/57600 [2:27:00<7:29:56,  1.62it/s]
 24%|██▍       | 14000/57600 [2:27:00<7:34:05,  1.60it/s]
                                                         
{'loss': 1.3272, 'learning_rate': 7.836236933797909e-07, 'epoch': 154.53}

 24%|██▍       | 14000/57600 [2:27:00<7:34:05,  1.60it/s]
 24%|██▍       | 14001/57600 [2:27:01<7:35:54,  1.59it/s]
 24%|██▍       | 14002/57600 [2:27:02<7:21:19,  1.65it/s]
 24%|██▍       | 14003/57600 [2:27:02<7:34:24,  1.60it/s]
 24%|██▍       | 14004/57600 [2:27:03<7:31:50,  1.61it/s]
 24%|██▍       | 14005/57600 [2:27:04<7:52:24,  1.54it/s]
 24%|██▍       | 14006/57600 [2:27:04<7:57:18,  1.52it/s]
 24%|██▍       | 14007/57600 [2:27:05<7:43:04,  1.57it/s]
 24%|██▍       | 14008/57600 [2:27:05<7:37:04,  1.59it/s]
 24%|██▍       | 14009/57600 [2:27:06<7:40:01,  1.58it/s]
 24%|██▍       | 14010/57600 [2:27:07<7:55:00,  1.53it/s]
 24%|██▍       | 14011/57600 [2:27:07<7:55:49,  1.53it/s]
 24%|██▍       | 14012/57600 [2:27:08<7:36:34,  1.59it/s]
 24%|██▍       | 14013/57600 [2:27:09<7:32:51,  1.60it/s]
 24%|██▍       | 14014/57600 [2:27:09<7:16:30,  1.66it/s]
 24%|██▍       | 14015/57600 [2:27:10<7:11:56,  1.68it/s]
 24%|██▍       | 14016/57600 [2:27:10<7:23:37,  1.64it/s]
 24%|██▍       | 14017/57600 [2:27:11<7:34:17,  1.60it/s]
 24%|██▍       | 14018/57600 [2:27:12<7:36:22,  1.59it/s]
 24%|██▍       | 14019/57600 [2:27:12<7:35:42,  1.59it/s]
 24%|██▍       | 14020/57600 [2:27:13<7:31:27,  1.61it/s]
                                                         
{'loss': 1.3093, 'learning_rate': 7.833101045296167e-07, 'epoch': 154.75}

 24%|██▍       | 14020/57600 [2:27:13<7:31:27,  1.61it/s]
 24%|██▍       | 14021/57600 [2:27:14<7:38:39,  1.58it/s]
 24%|██▍       | 14022/57600 [2:27:14<7:25:04,  1.63it/s]
 24%|██▍       | 14023/57600 [2:27:15<7:25:05,  1.63it/s]
 24%|██▍       | 14024/57600 [2:27:15<7:18:24,  1.66it/s]
 24%|██▍       | 14025/57600 [2:27:16<7:10:41,  1.69it/s]
 24%|██▍       | 14026/57600 [2:27:17<7:01:48,  1.72it/s]
 24%|██▍       | 14027/57600 [2:27:17<7:17:24,  1.66it/s]
 24%|██▍       | 14028/57600 [2:27:18<7:11:56,  1.68it/s]
 24%|██▍       | 14029/57600 [2:27:18<7:20:52,  1.65it/s]
 24%|██▍       | 14030/57600 [2:27:19<7:25:27,  1.63it/s]
 24%|██▍       | 14031/57600 [2:27:20<7:27:49,  1.62it/s]
 24%|██▍       | 14032/57600 [2:27:20<7:18:55,  1.65it/s]
 24%|██▍       | 14033/57600 [2:27:21<7:32:12,  1.61it/s]
 24%|██▍       | 14034/57600 [2:27:21<7:23:23,  1.64it/s]
 24%|██▍       | 14035/57600 [2:27:22<7:28:05,  1.62it/s]
 24%|██▍       | 14036/57600 [2:27:23<7:35:30,  1.59it/s]
 24%|██▍       | 14037/57600 [2:27:23<7:40:11,  1.58it/s]
 24%|██▍       | 14038/57600 [2:27:24<7:28:49,  1.62it/s]
 24%|██▍       | 14039/57600 [2:27:25<7:21:50,  1.64it/s]
 24%|██▍       | 14040/57600 [2:27:25<7:18:14,  1.66it/s]
                                                         
{'loss': 1.2967, 'learning_rate': 7.829965156794425e-07, 'epoch': 154.97}

 24%|██▍       | 14040/57600 [2:27:25<7:18:14,  1.66it/s]
 24%|██▍       | 14041/57600 [2:27:26<7:34:08,  1.60it/s]
 24%|██▍       | 14042/57600 [2:27:26<7:42:34,  1.57it/s]
 24%|██▍       | 14043/57600 [2:27:27<7:37:20,  1.59it/s]
 24%|██▍       | 14044/57600 [2:27:28<7:47:53,  1.55it/s]
 24%|██▍       | 14045/57600 [2:27:28<7:32:20,  1.60it/s]
 24%|██▍       | 14046/57600 [2:27:29<7:33:08,  1.60it/s]
 24%|██▍       | 14047/57600 [2:27:30<7:34:33,  1.60it/s]
 24%|██▍       | 14048/57600 [2:27:30<7:39:25,  1.58it/s]
 24%|██▍       | 14049/57600 [2:27:31<7:37:04,  1.59it/s]
 24%|██▍       | 14050/57600 [2:27:31<7:25:24,  1.63it/s]
 24%|██▍       | 14051/57600 [2:27:32<7:26:10,  1.63it/s]
 24%|██▍       | 14052/57600 [2:27:33<7:25:21,  1.63it/s]
 24%|██▍       | 14053/57600 [2:27:33<7:44:24,  1.56it/s]
 24%|██▍       | 14054/57600 [2:27:34<7:26:56,  1.62it/s]
 24%|██▍       | 14055/57600 [2:27:35<7:20:57,  1.65it/s]
 24%|██▍       | 14056/57600 [2:27:35<7:18:27,  1.66it/s]
 24%|██▍       | 14057/57600 [2:27:36<7:05:01,  1.71it/s]
 24%|██▍       | 14058/57600 [2:27:36<7:21:59,  1.64it/s]
 24%|██▍       | 14059/57600 [2:27:37<7:26:01,  1.63it/s]
 24%|██▍       | 14060/57600 [2:27:38<7:22:26,  1.64it/s]
                                                         
{'loss': 1.3127, 'learning_rate': 7.826829268292683e-07, 'epoch': 155.19}

 24%|██▍       | 14060/57600 [2:27:38<7:22:26,  1.64it/s]
 24%|██▍       | 14061/57600 [2:27:38<7:37:51,  1.58it/s]
 24%|██▍       | 14062/57600 [2:27:39<7:40:46,  1.57it/s]
 24%|██▍       | 14063/57600 [2:27:39<7:33:54,  1.60it/s]
 24%|██▍       | 14064/57600 [2:27:40<7:23:14,  1.64it/s]
 24%|██▍       | 14065/57600 [2:27:41<7:20:06,  1.65it/s]
 24%|██▍       | 14066/57600 [2:27:41<7:25:35,  1.63it/s]
 24%|██▍       | 14067/57600 [2:27:42<7:36:58,  1.59it/s]
 24%|██▍       | 14068/57600 [2:27:43<7:28:22,  1.62it/s]
 24%|██▍       | 14069/57600 [2:27:43<7:14:25,  1.67it/s]
 24%|██▍       | 14070/57600 [2:27:44<7:03:17,  1.71it/s]
 24%|██▍       | 14071/57600 [2:27:44<7:23:12,  1.64it/s]
 24%|██▍       | 14072/57600 [2:27:45<7:27:42,  1.62it/s]
 24%|██▍       | 14073/57600 [2:27:46<7:23:16,  1.64it/s]
 24%|██▍       | 14074/57600 [2:27:46<7:30:58,  1.61it/s]
 24%|██▍       | 14075/57600 [2:27:47<7:18:43,  1.65it/s]
 24%|██▍       | 14076/57600 [2:27:47<7:14:47,  1.67it/s]
 24%|██▍       | 14077/57600 [2:27:48<7:18:29,  1.65it/s]
 24%|██▍       | 14078/57600 [2:27:49<7:30:25,  1.61it/s]
 24%|██▍       | 14079/57600 [2:27:49<7:39:18,  1.58it/s]
 24%|██▍       | 14080/57600 [2:27:50<7:33:43,  1.60it/s]
                                                         
{'loss': 1.3198, 'learning_rate': 7.82369337979094e-07, 'epoch': 155.41}

 24%|██▍       | 14080/57600 [2:27:50<7:33:43,  1.60it/s]
 24%|██▍       | 14081/57600 [2:27:51<7:33:34,  1.60it/s]
 24%|██▍       | 14082/57600 [2:27:51<7:29:58,  1.61it/s]
 24%|██▍       | 14083/57600 [2:27:52<7:28:47,  1.62it/s]
 24%|██▍       | 14084/57600 [2:27:52<7:16:11,  1.66it/s]
 24%|██▍       | 14085/57600 [2:27:53<7:18:22,  1.65it/s]
 24%|██▍       | 14086/57600 [2:27:54<7:15:05,  1.67it/s]
 24%|██▍       | 14087/57600 [2:27:54<7:22:17,  1.64it/s]
 24%|██▍       | 14088/57600 [2:27:55<7:35:51,  1.59it/s]
 24%|██▍       | 14089/57600 [2:27:55<7:28:49,  1.62it/s]
 24%|██▍       | 14090/57600 [2:27:56<7:27:23,  1.62it/s]
 24%|██▍       | 14091/57600 [2:27:57<7:21:59,  1.64it/s]
 24%|██▍       | 14092/57600 [2:27:57<7:22:37,  1.64it/s]
 24%|██▍       | 14093/57600 [2:27:58<7:28:06,  1.62it/s]
 24%|██▍       | 14094/57600 [2:27:58<7:21:18,  1.64it/s]
 24%|██▍       | 14095/57600 [2:27:59<7:51:14,  1.54it/s]
 24%|██▍       | 14096/57600 [2:28:00<7:49:21,  1.54it/s]
 24%|██▍       | 14097/57600 [2:28:00<7:45:05,  1.56it/s]
 24%|██▍       | 14098/57600 [2:28:01<7:43:34,  1.56it/s]
 24%|██▍       | 14099/57600 [2:28:02<7:43:47,  1.56it/s]
 24%|██▍       | 14100/57600 [2:28:02<7:26:27,  1.62it/s]
                                                         
{'loss': 1.2706, 'learning_rate': 7.820557491289198e-07, 'epoch': 155.63}

 24%|██▍       | 14100/57600 [2:28:02<7:26:27,  1.62it/s]
 24%|██▍       | 14101/57600 [2:28:03<7:37:58,  1.58it/s]
 24%|██▍       | 14102/57600 [2:28:04<7:23:35,  1.63it/s]
 24%|██▍       | 14103/57600 [2:28:04<7:35:22,  1.59it/s]
 24%|██▍       | 14104/57600 [2:28:05<7:28:59,  1.61it/s]
 24%|██▍       | 14105/57600 [2:28:05<7:22:24,  1.64it/s]
 24%|██▍       | 14106/57600 [2:28:06<7:27:06,  1.62it/s]
 24%|██▍       | 14107/57600 [2:28:07<7:17:03,  1.66it/s]
 24%|██▍       | 14108/57600 [2:28:07<7:18:21,  1.65it/s]
 24%|██▍       | 14109/57600 [2:28:08<7:16:23,  1.66it/s]
 24%|██▍       | 14110/57600 [2:28:08<7:20:44,  1.64it/s]
 24%|██▍       | 14111/57600 [2:28:09<7:15:06,  1.67it/s]
 24%|██▍       | 14112/57600 [2:28:10<7:10:49,  1.68it/s]
 25%|██▍       | 14113/57600 [2:28:10<7:15:46,  1.66it/s]
 25%|██▍       | 14114/57600 [2:28:11<7:25:44,  1.63it/s]
 25%|██▍       | 14115/57600 [2:28:12<7:48:21,  1.55it/s]
 25%|██▍       | 14116/57600 [2:28:12<7:50:18,  1.54it/s]
 25%|██▍       | 14117/57600 [2:28:13<7:49:52,  1.54it/s]
 25%|██▍       | 14118/57600 [2:28:13<7:34:31,  1.59it/s]
 25%|██▍       | 14119/57600 [2:28:14<7:26:43,  1.62it/s]
 25%|██▍       | 14120/57600 [2:28:15<7:27:42,  1.62it/s]
                                                         
{'loss': 1.3346, 'learning_rate': 7.817421602787456e-07, 'epoch': 155.85}

 25%|██▍       | 14120/57600 [2:28:15<7:27:42,  1.62it/s]
 25%|██▍       | 14121/57600 [2:28:15<7:29:46,  1.61it/s]
 25%|██▍       | 14122/57600 [2:28:16<7:33:25,  1.60it/s]
 25%|██▍       | 14123/57600 [2:28:17<7:29:41,  1.61it/s]
 25%|██▍       | 14124/57600 [2:28:17<7:11:56,  1.68it/s]
 25%|██▍       | 14125/57600 [2:28:18<7:06:00,  1.70it/s]
 25%|██▍       | 14126/57600 [2:28:18<7:16:30,  1.66it/s]
 25%|██▍       | 14127/57600 [2:28:19<7:23:51,  1.63it/s]
 25%|██▍       | 14128/57600 [2:28:19<7:15:19,  1.66it/s]
 25%|██▍       | 14129/57600 [2:28:20<7:07:18,  1.70it/s]
 25%|██▍       | 14130/57600 [2:28:21<7:10:43,  1.68it/s]
 25%|██▍       | 14131/57600 [2:28:21<7:20:25,  1.64it/s]
 25%|██▍       | 14132/57600 [2:28:22<7:31:34,  1.60it/s]
 25%|██▍       | 14133/57600 [2:28:23<7:16:25,  1.66it/s]
 25%|██▍       | 14134/57600 [2:28:23<7:48:33,  1.55it/s]
 25%|██▍       | 14135/57600 [2:28:24<8:08:21,  1.48it/s]
 25%|██▍       | 14136/57600 [2:28:25<7:46:55,  1.55it/s]
 25%|██▍       | 14137/57600 [2:28:25<7:39:44,  1.58it/s]
 25%|██▍       | 14138/57600 [2:28:26<7:41:34,  1.57it/s]
 25%|██▍       | 14139/57600 [2:28:26<7:32:02,  1.60it/s]
 25%|██▍       | 14140/57600 [2:28:27<7:37:47,  1.58it/s]
                                                         
{'loss': 1.3161, 'learning_rate': 7.814285714285714e-07, 'epoch': 156.07}

 25%|██▍       | 14140/57600 [2:28:27<7:37:47,  1.58it/s]
 25%|██▍       | 14141/57600 [2:28:28<7:27:58,  1.62it/s]
 25%|██▍       | 14142/57600 [2:28:28<7:38:23,  1.58it/s]
 25%|██▍       | 14143/57600 [2:28:29<7:30:54,  1.61it/s]
 25%|██▍       | 14144/57600 [2:28:30<7:35:58,  1.59it/s]
 25%|██▍       | 14145/57600 [2:28:30<7:37:05,  1.58it/s]
 25%|██▍       | 14146/57600 [2:28:31<7:36:16,  1.59it/s]
 25%|██▍       | 14147/57600 [2:28:31<7:24:49,  1.63it/s]
 25%|██▍       | 14148/57600 [2:28:32<7:33:16,  1.60it/s]
 25%|██▍       | 14149/57600 [2:28:33<7:27:51,  1.62it/s]
 25%|██▍       | 14150/57600 [2:28:33<7:20:26,  1.64it/s]
 25%|██▍       | 14151/57600 [2:28:34<7:33:30,  1.60it/s]
 25%|██▍       | 14152/57600 [2:28:35<7:37:04,  1.58it/s]
 25%|██▍       | 14153/57600 [2:28:35<7:23:10,  1.63it/s]
 25%|██▍       | 14154/57600 [2:28:36<7:29:43,  1.61it/s]
 25%|██▍       | 14155/57600 [2:28:36<7:32:57,  1.60it/s]
 25%|██▍       | 14156/57600 [2:28:37<7:21:53,  1.64it/s]
 25%|██▍       | 14157/57600 [2:28:38<7:25:55,  1.62it/s]
 25%|██▍       | 14158/57600 [2:28:38<7:25:03,  1.63it/s]
 25%|██▍       | 14159/57600 [2:28:39<7:32:01,  1.60it/s]
 25%|██▍       | 14160/57600 [2:28:39<7:30:23,  1.61it/s]
                                                         
{'loss': 1.3083, 'learning_rate': 7.811149825783972e-07, 'epoch': 156.29}

 25%|██▍       | 14160/57600 [2:28:39<7:30:23,  1.61it/s]
 25%|██▍       | 14161/57600 [2:28:40<7:21:34,  1.64it/s]
 25%|██▍       | 14162/57600 [2:28:41<7:08:43,  1.69it/s]
 25%|██▍       | 14163/57600 [2:28:41<6:58:58,  1.73it/s]
 25%|██▍       | 14164/57600 [2:28:42<6:55:13,  1.74it/s]
 25%|██▍       | 14165/57600 [2:28:42<7:15:09,  1.66it/s]
 25%|██▍       | 14166/57600 [2:28:43<7:09:34,  1.69it/s]
 25%|██▍       | 14167/57600 [2:28:44<7:06:55,  1.70it/s]
 25%|██▍       | 14168/57600 [2:28:44<7:02:21,  1.71it/s]
 25%|██▍       | 14169/57600 [2:28:45<6:59:35,  1.73it/s]
 25%|██▍       | 14170/57600 [2:28:45<7:19:25,  1.65it/s]
 25%|██▍       | 14171/57600 [2:28:46<7:12:31,  1.67it/s]
 25%|██▍       | 14172/57600 [2:28:47<7:22:13,  1.64it/s]
 25%|██▍       | 14173/57600 [2:28:47<7:27:09,  1.62it/s]
 25%|██▍       | 14174/57600 [2:28:48<7:20:52,  1.64it/s]
 25%|██▍       | 14175/57600 [2:28:48<7:18:09,  1.65it/s]
 25%|██▍       | 14176/57600 [2:28:49<7:25:23,  1.62it/s]
 25%|██▍       | 14177/57600 [2:28:50<7:14:42,  1.66it/s]
 25%|██▍       | 14178/57600 [2:28:50<7:14:43,  1.66it/s]
 25%|██▍       | 14179/57600 [2:28:51<7:16:00,  1.66it/s]
 25%|██▍       | 14180/57600 [2:28:51<7:36:08,  1.59it/s]
                                                         
{'loss': 1.3371, 'learning_rate': 7.80801393728223e-07, 'epoch': 156.51}

 25%|██▍       | 14180/57600 [2:28:51<7:36:08,  1.59it/s]
 25%|██▍       | 14181/57600 [2:28:52<7:28:07,  1.61it/s]
 25%|██▍       | 14182/57600 [2:28:53<7:20:03,  1.64it/s]
 25%|██▍       | 14183/57600 [2:28:53<7:22:28,  1.64it/s]
 25%|██▍       | 14184/57600 [2:28:54<7:17:25,  1.65it/s]
 25%|██▍       | 14185/57600 [2:28:55<7:24:18,  1.63it/s]
 25%|██▍       | 14186/57600 [2:28:55<7:49:23,  1.54it/s]
 25%|██▍       | 14187/57600 [2:28:56<7:53:40,  1.53it/s]
 25%|██▍       | 14188/57600 [2:28:57<7:39:31,  1.57it/s]
 25%|██▍       | 14189/57600 [2:28:57<7:20:46,  1.64it/s]
 25%|██▍       | 14190/57600 [2:28:58<7:36:51,  1.58it/s]
 25%|██▍       | 14191/57600 [2:28:58<7:29:23,  1.61it/s]
 25%|██▍       | 14192/57600 [2:28:59<7:56:05,  1.52it/s]
 25%|██▍       | 14193/57600 [2:29:00<7:49:33,  1.54it/s]
 25%|██▍       | 14194/57600 [2:29:00<7:55:51,  1.52it/s]
 25%|██▍       | 14195/57600 [2:29:01<7:50:43,  1.54it/s]
 25%|██▍       | 14196/57600 [2:29:02<7:27:52,  1.62it/s]
 25%|██▍       | 14197/57600 [2:29:02<7:35:52,  1.59it/s]
 25%|██▍       | 14198/57600 [2:29:03<7:42:33,  1.56it/s]
 25%|██▍       | 14199/57600 [2:29:04<7:41:10,  1.57it/s]
 25%|██▍       | 14200/57600 [2:29:04<7:29:29,  1.61it/s]
                                                         
{'loss': 1.3168, 'learning_rate': 7.804878048780488e-07, 'epoch': 156.73}

 25%|██▍       | 14200/57600 [2:29:04<7:29:29,  1.61it/s]
 25%|██▍       | 14201/57600 [2:29:05<7:36:50,  1.58it/s]
 25%|██▍       | 14202/57600 [2:29:05<7:28:18,  1.61it/s]
 25%|██▍       | 14203/57600 [2:29:06<7:33:05,  1.60it/s]
 25%|██▍       | 14204/57600 [2:29:07<7:29:40,  1.61it/s]
 25%|██▍       | 14205/57600 [2:29:07<7:26:12,  1.62it/s]
 25%|██▍       | 14206/57600 [2:29:08<7:38:48,  1.58it/s]
 25%|██▍       | 14207/57600 [2:29:08<7:34:43,  1.59it/s]
 25%|██▍       | 14208/57600 [2:29:09<7:28:56,  1.61it/s]
 25%|██▍       | 14209/57600 [2:29:10<7:18:58,  1.65it/s]
 25%|██▍       | 14210/57600 [2:29:10<7:05:22,  1.70it/s]
 25%|██▍       | 14211/57600 [2:29:11<7:08:45,  1.69it/s]
 25%|██▍       | 14212/57600 [2:29:11<7:19:25,  1.65it/s]
 25%|██▍       | 14213/57600 [2:29:12<7:22:42,  1.63it/s]
 25%|██▍       | 14214/57600 [2:29:13<7:24:40,  1.63it/s]
 25%|██▍       | 14215/57600 [2:29:13<7:26:37,  1.62it/s]
 25%|██▍       | 14216/57600 [2:29:14<7:18:39,  1.65it/s]
 25%|██▍       | 14217/57600 [2:29:14<7:06:28,  1.70it/s]
 25%|██▍       | 14218/57600 [2:29:15<6:58:06,  1.73it/s]
 25%|██▍       | 14219/57600 [2:29:16<6:55:39,  1.74it/s]
 25%|██▍       | 14220/57600 [2:29:16<7:17:03,  1.65it/s]
                                                         
{'loss': 1.3037, 'learning_rate': 7.801742160278745e-07, 'epoch': 156.95}

 25%|██▍       | 14220/57600 [2:29:16<7:17:03,  1.65it/s]
 25%|██▍       | 14221/57600 [2:29:17<7:24:00,  1.63it/s]
 25%|██▍       | 14222/57600 [2:29:18<7:36:27,  1.58it/s]
 25%|██▍       | 14223/57600 [2:29:18<7:34:07,  1.59it/s]
 25%|██▍       | 14224/57600 [2:29:19<7:15:52,  1.66it/s]
 25%|██▍       | 14225/57600 [2:29:19<7:30:32,  1.60it/s]
 25%|██▍       | 14226/57600 [2:29:20<7:34:39,  1.59it/s]
 25%|██▍       | 14227/57600 [2:29:21<7:33:10,  1.60it/s]
 25%|██▍       | 14228/57600 [2:29:21<7:20:14,  1.64it/s]
 25%|██▍       | 14229/57600 [2:29:22<7:13:32,  1.67it/s]
 25%|██▍       | 14230/57600 [2:29:22<7:13:56,  1.67it/s]
 25%|██▍       | 14231/57600 [2:29:23<7:07:01,  1.69it/s]
 25%|██▍       | 14232/57600 [2:29:24<7:07:40,  1.69it/s]
 25%|██▍       | 14233/57600 [2:29:24<7:14:13,  1.66it/s]
 25%|██▍       | 14234/57600 [2:29:25<7:15:15,  1.66it/s]
 25%|██▍       | 14235/57600 [2:29:25<7:14:26,  1.66it/s]
 25%|██▍       | 14236/57600 [2:29:26<7:23:55,  1.63it/s]
 25%|██▍       | 14237/57600 [2:29:27<7:27:28,  1.62it/s]
 25%|██▍       | 14238/57600 [2:29:27<7:19:04,  1.65it/s]
 25%|██▍       | 14239/57600 [2:29:28<7:17:21,  1.65it/s]
 25%|██▍       | 14240/57600 [2:29:28<7:11:01,  1.68it/s]
                                                         
{'loss': 1.2958, 'learning_rate': 7.798606271777003e-07, 'epoch': 157.17}

 25%|██▍       | 14240/57600 [2:29:28<7:11:01,  1.68it/s]
 25%|██▍       | 14241/57600 [2:29:29<7:25:26,  1.62it/s]
 25%|██▍       | 14242/57600 [2:29:30<7:13:29,  1.67it/s]
 25%|██▍       | 14243/57600 [2:29:30<7:13:43,  1.67it/s]
 25%|██▍       | 14244/57600 [2:29:31<7:19:41,  1.64it/s]
 25%|██▍       | 14245/57600 [2:29:32<7:29:14,  1.61it/s]
 25%|██▍       | 14246/57600 [2:29:32<7:16:14,  1.66it/s]
 25%|██▍       | 14247/57600 [2:29:33<7:22:21,  1.63it/s]
 25%|██▍       | 14248/57600 [2:29:33<7:28:18,  1.61it/s]
 25%|██▍       | 14249/57600 [2:29:34<7:33:35,  1.59it/s]
 25%|██▍       | 14250/57600 [2:29:35<7:19:58,  1.64it/s]
 25%|██▍       | 14251/57600 [2:29:35<7:29:38,  1.61it/s]
 25%|██▍       | 14252/57600 [2:29:36<7:41:40,  1.56it/s]
 25%|██▍       | 14253/57600 [2:29:37<7:38:01,  1.58it/s]
 25%|██▍       | 14254/57600 [2:29:37<7:31:15,  1.60it/s]
 25%|██▍       | 14255/57600 [2:29:38<7:19:50,  1.64it/s]
 25%|██▍       | 14256/57600 [2:29:38<7:13:25,  1.67it/s]
 25%|██▍       | 14257/57600 [2:29:39<7:06:55,  1.69it/s]
 25%|██▍       | 14258/57600 [2:29:39<7:17:47,  1.65it/s]
 25%|██▍       | 14259/57600 [2:29:40<7:15:29,  1.66it/s]
 25%|██▍       | 14260/57600 [2:29:41<7:09:31,  1.68it/s]
                                                         
{'loss': 1.3027, 'learning_rate': 7.795470383275261e-07, 'epoch': 157.4}

 25%|██▍       | 14260/57600 [2:29:41<7:09:31,  1.68it/s]
 25%|██▍       | 14261/57600 [2:29:41<7:08:24,  1.69it/s]
 25%|██▍       | 14262/57600 [2:29:42<7:17:34,  1.65it/s]
 25%|██▍       | 14263/57600 [2:29:42<7:17:59,  1.65it/s]
 25%|██▍       | 14264/57600 [2:29:43<7:18:15,  1.65it/s]
 25%|██▍       | 14265/57600 [2:29:44<7:38:57,  1.57it/s]
 25%|██▍       | 14266/57600 [2:29:44<7:33:35,  1.59it/s]
 25%|██▍       | 14267/57600 [2:29:45<7:33:13,  1.59it/s]
 25%|██▍       | 14268/57600 [2:29:46<7:35:53,  1.58it/s]
 25%|██▍       | 14269/57600 [2:29:46<7:36:21,  1.58it/s]
 25%|██▍       | 14270/57600 [2:29:47<7:36:58,  1.58it/s]
 25%|██▍       | 14271/57600 [2:29:48<7:32:57,  1.59it/s]
 25%|██▍       | 14272/57600 [2:29:48<7:30:45,  1.60it/s]
 25%|██▍       | 14273/57600 [2:29:49<7:22:35,  1.63it/s]
 25%|██▍       | 14274/57600 [2:29:49<7:30:36,  1.60it/s]
 25%|██▍       | 14275/57600 [2:29:50<7:31:33,  1.60it/s]
 25%|██▍       | 14276/57600 [2:29:51<7:22:59,  1.63it/s]
 25%|██▍       | 14277/57600 [2:29:51<7:16:48,  1.65it/s]
 25%|██▍       | 14278/57600 [2:29:52<7:29:31,  1.61it/s]
 25%|██▍       | 14279/57600 [2:29:53<7:36:00,  1.58it/s]
 25%|██▍       | 14280/57600 [2:29:53<7:25:30,  1.62it/s]
                                                         
{'loss': 1.2728, 'learning_rate': 7.792334494773519e-07, 'epoch': 157.62}

 25%|██▍       | 14280/57600 [2:29:53<7:25:30,  1.62it/s]
 25%|██▍       | 14281/57600 [2:29:54<7:13:28,  1.67it/s]
 25%|██▍       | 14282/57600 [2:29:54<7:17:31,  1.65it/s]
 25%|██▍       | 14283/57600 [2:29:55<7:23:16,  1.63it/s]
 25%|██▍       | 14284/57600 [2:29:56<7:23:57,  1.63it/s]
 25%|██▍       | 14285/57600 [2:29:56<7:26:27,  1.62it/s]
 25%|██▍       | 14286/57600 [2:29:57<7:26:15,  1.62it/s]
 25%|██▍       | 14287/57600 [2:29:57<7:16:59,  1.65it/s]
 25%|██▍       | 14288/57600 [2:29:58<7:18:54,  1.64it/s]
 25%|██▍       | 14289/57600 [2:29:59<7:32:42,  1.59it/s]
 25%|██▍       | 14290/57600 [2:29:59<7:29:23,  1.61it/s]
 25%|██▍       | 14291/57600 [2:30:00<7:12:05,  1.67it/s]
 25%|██▍       | 14292/57600 [2:30:00<7:10:08,  1.68it/s]
 25%|██▍       | 14293/57600 [2:30:01<7:09:31,  1.68it/s]
 25%|██▍       | 14294/57600 [2:30:02<7:07:30,  1.69it/s]
 25%|██▍       | 14295/57600 [2:30:02<7:27:03,  1.61it/s]
 25%|██▍       | 14296/57600 [2:30:03<7:27:03,  1.61it/s]
 25%|██▍       | 14297/57600 [2:30:04<7:34:22,  1.59it/s]
 25%|██▍       | 14298/57600 [2:30:04<7:24:52,  1.62it/s]
 25%|██▍       | 14299/57600 [2:30:05<7:27:23,  1.61it/s]
 25%|██▍       | 14300/57600 [2:30:05<7:41:38,  1.56it/s]
                                                         
{'loss': 1.3138, 'learning_rate': 7.789198606271777e-07, 'epoch': 157.84}

 25%|██▍       | 14300/57600 [2:30:05<7:41:38,  1.56it/s]
 25%|██▍       | 14301/57600 [2:30:06<7:33:35,  1.59it/s]
 25%|██▍       | 14302/57600 [2:30:07<7:57:39,  1.51it/s]
 25%|██▍       | 14303/57600 [2:30:07<7:43:45,  1.56it/s]
 25%|██▍       | 14304/57600 [2:30:08<7:33:55,  1.59it/s]
 25%|██▍       | 14305/57600 [2:30:09<7:34:09,  1.59it/s]
 25%|██▍       | 14306/57600 [2:30:09<7:23:49,  1.63it/s]
 25%|██▍       | 14307/57600 [2:30:10<7:25:08,  1.62it/s]
 25%|██▍       | 14308/57600 [2:30:10<7:15:45,  1.66it/s]
 25%|██▍       | 14309/57600 [2:30:11<7:13:38,  1.66it/s]
 25%|██▍       | 14310/57600 [2:30:12<7:52:52,  1.53it/s]
 25%|██▍       | 14311/57600 [2:30:12<7:42:16,  1.56it/s]
 25%|██▍       | 14312/57600 [2:30:13<7:24:13,  1.62it/s]
 25%|██▍       | 14313/57600 [2:30:14<7:31:21,  1.60it/s]
 25%|██▍       | 14314/57600 [2:30:14<7:41:52,  1.56it/s]
 25%|██▍       | 14315/57600 [2:30:15<8:04:29,  1.49it/s]
 25%|██▍       | 14316/57600 [2:30:16<8:05:45,  1.49it/s]
 25%|██▍       | 14317/57600 [2:30:16<7:58:37,  1.51it/s]
 25%|██▍       | 14318/57600 [2:30:17<7:33:42,  1.59it/s]
 25%|██▍       | 14319/57600 [2:30:17<7:29:15,  1.61it/s]
 25%|██▍       | 14320/57600 [2:30:18<7:28:28,  1.61it/s]
                                                         
{'loss': 1.3205, 'learning_rate': 7.786062717770035e-07, 'epoch': 158.06}

 25%|██▍       | 14320/57600 [2:30:18<7:28:28,  1.61it/s]
 25%|██▍       | 14321/57600 [2:30:19<7:23:01,  1.63it/s]
 25%|██▍       | 14322/57600 [2:30:19<7:16:59,  1.65it/s]
 25%|██▍       | 14323/57600 [2:30:20<7:15:24,  1.66it/s]
 25%|██▍       | 14324/57600 [2:30:20<7:10:29,  1.68it/s]
 25%|██▍       | 14325/57600 [2:30:21<7:05:36,  1.69it/s]
 25%|██▍       | 14326/57600 [2:30:22<7:21:35,  1.63it/s]
 25%|██▍       | 14327/57600 [2:30:22<7:36:13,  1.58it/s]
 25%|██▍       | 14328/57600 [2:30:23<7:29:49,  1.60it/s]
 25%|██▍       | 14329/57600 [2:30:24<7:29:01,  1.61it/s]
 25%|██▍       | 14330/57600 [2:30:24<7:35:42,  1.58it/s]
 25%|██▍       | 14331/57600 [2:30:25<7:28:31,  1.61it/s]
 25%|██▍       | 14332/57600 [2:30:25<7:15:55,  1.65it/s]
 25%|██▍       | 14333/57600 [2:30:26<7:16:34,  1.65it/s]
 25%|██▍       | 14334/57600 [2:30:27<7:11:52,  1.67it/s]
 25%|██▍       | 14335/57600 [2:30:27<7:11:15,  1.67it/s]
 25%|██▍       | 14336/57600 [2:30:28<7:25:03,  1.62it/s]
 25%|██▍       | 14337/57600 [2:30:28<7:24:24,  1.62it/s]
 25%|██▍       | 14338/57600 [2:30:29<7:25:30,  1.62it/s]
 25%|██▍       | 14339/57600 [2:30:30<7:12:03,  1.67it/s]
 25%|██▍       | 14340/57600 [2:30:30<7:27:34,  1.61it/s]
                                                         
{'loss': 1.308, 'learning_rate': 7.782926829268292e-07, 'epoch': 158.28}

 25%|██▍       | 14340/57600 [2:30:30<7:27:34,  1.61it/s]
 25%|██▍       | 14341/57600 [2:30:31<7:20:18,  1.64it/s]
 25%|██▍       | 14342/57600 [2:30:31<7:12:12,  1.67it/s]
 25%|██▍       | 14343/57600 [2:30:32<7:03:08,  1.70it/s]
 25%|██▍       | 14344/57600 [2:30:33<7:12:38,  1.67it/s]
 25%|██▍       | 14345/57600 [2:30:33<7:27:48,  1.61it/s]
 25%|██▍       | 14346/57600 [2:30:34<7:30:11,  1.60it/s]
 25%|██▍       | 14347/57600 [2:30:35<7:31:28,  1.60it/s]
 25%|██▍       | 14348/57600 [2:30:35<7:37:41,  1.58it/s]
 25%|██▍       | 14349/57600 [2:30:36<7:41:57,  1.56it/s]
 25%|██▍       | 14350/57600 [2:30:36<7:24:11,  1.62it/s]
 25%|██▍       | 14351/57600 [2:30:37<7:38:55,  1.57it/s]
 25%|██▍       | 14352/57600 [2:30:38<7:38:52,  1.57it/s]
 25%|██▍       | 14353/57600 [2:30:38<7:35:26,  1.58it/s]
 25%|██▍       | 14354/57600 [2:30:39<7:47:39,  1.54it/s]
 25%|██▍       | 14355/57600 [2:30:40<7:34:51,  1.58it/s]
 25%|██▍       | 14356/57600 [2:30:40<7:34:46,  1.58it/s]
 25%|██▍       | 14357/57600 [2:30:41<7:25:36,  1.62it/s]
 25%|██▍       | 14358/57600 [2:30:42<7:33:21,  1.59it/s]
 25%|██▍       | 14359/57600 [2:30:42<7:54:32,  1.52it/s]
 25%|██▍       | 14360/57600 [2:30:43<7:51:35,  1.53it/s]
                                                         
{'loss': 1.2679, 'learning_rate': 7.77979094076655e-07, 'epoch': 158.5}

 25%|██▍       | 14360/57600 [2:30:43<7:51:35,  1.53it/s]
 25%|██▍       | 14361/57600 [2:30:43<7:27:28,  1.61it/s]
 25%|██▍       | 14362/57600 [2:30:44<7:38:01,  1.57it/s]
 25%|██▍       | 14363/57600 [2:30:45<7:54:50,  1.52it/s]
 25%|██▍       | 14364/57600 [2:30:46<7:55:40,  1.51it/s]
 25%|██▍       | 14365/57600 [2:30:46<7:53:46,  1.52it/s]
 25%|██▍       | 14366/57600 [2:30:47<7:39:21,  1.57it/s]
 25%|██▍       | 14367/57600 [2:30:47<7:27:08,  1.61it/s]
 25%|██▍       | 14368/57600 [2:30:48<7:27:30,  1.61it/s]
 25%|██▍       | 14369/57600 [2:30:49<7:27:33,  1.61it/s]
 25%|██▍       | 14370/57600 [2:30:49<7:31:16,  1.60it/s]
 25%|██▍       | 14371/57600 [2:30:50<7:18:50,  1.64it/s]
 25%|██▍       | 14372/57600 [2:30:50<7:20:56,  1.63it/s]
 25%|██▍       | 14373/57600 [2:30:51<7:29:58,  1.60it/s]
 25%|██▍       | 14374/57600 [2:30:52<7:21:49,  1.63it/s]
 25%|██▍       | 14375/57600 [2:30:52<7:18:47,  1.64it/s]
 25%|██▍       | 14376/57600 [2:30:53<7:17:17,  1.65it/s]
 25%|██▍       | 14377/57600 [2:30:53<7:11:38,  1.67it/s]
 25%|██▍       | 14378/57600 [2:30:54<7:13:52,  1.66it/s]
 25%|██▍       | 14379/57600 [2:30:55<7:15:43,  1.65it/s]
 25%|██▍       | 14380/57600 [2:30:55<7:06:44,  1.69it/s]
                                                         
{'loss': 1.3194, 'learning_rate': 7.776655052264809e-07, 'epoch': 158.72}

 25%|██▍       | 14380/57600 [2:30:55<7:06:44,  1.69it/s]
 25%|██▍       | 14381/57600 [2:30:56<7:21:05,  1.63it/s]
 25%|██▍       | 14382/57600 [2:30:56<7:08:46,  1.68it/s]
 25%|██▍       | 14383/57600 [2:30:57<7:18:28,  1.64it/s]
 25%|██▍       | 14384/57600 [2:30:58<7:13:02,  1.66it/s]
 25%|██▍       | 14385/57600 [2:30:58<7:06:20,  1.69it/s]
 25%|██▍       | 14386/57600 [2:30:59<7:12:46,  1.66it/s]
 25%|██▍       | 14387/57600 [2:30:59<7:15:51,  1.65it/s]
 25%|██▍       | 14388/57600 [2:31:00<7:15:59,  1.65it/s]
 25%|██▍       | 14389/57600 [2:31:01<7:14:20,  1.66it/s]
 25%|██▍       | 14390/57600 [2:31:01<7:38:34,  1.57it/s]
 25%|██▍       | 14391/57600 [2:31:02<7:22:44,  1.63it/s]
 25%|██▍       | 14392/57600 [2:31:03<7:15:27,  1.65it/s]
 25%|██▍       | 14393/57600 [2:31:03<7:10:11,  1.67it/s]
 25%|██▍       | 14394/57600 [2:31:04<7:29:25,  1.60it/s]
 25%|██▍       | 14395/57600 [2:31:04<7:12:51,  1.66it/s]
 25%|██▍       | 14396/57600 [2:31:05<7:15:08,  1.65it/s]
 25%|██▍       | 14397/57600 [2:31:06<7:12:30,  1.66it/s]
 25%|██▍       | 14398/57600 [2:31:06<7:13:00,  1.66it/s]
 25%|██▍       | 14399/57600 [2:31:07<7:03:19,  1.70it/s]
 25%|██▌       | 14400/57600 [2:31:07<6:58:00,  1.72it/s]
                                                         
{'loss': 1.3278, 'learning_rate': 7.773519163763066e-07, 'epoch': 158.94}

 25%|██▌       | 14400/57600 [2:31:07<6:58:00,  1.72it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.39it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.21it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.81it/s]

100%|██████████| 6/6 [00:01<00:00,  3.45it/s]{'score': 52.14981342939325, 'counts': [148, 103, 70, 50], 'totals': [212, 182, 152, 123], 'precisions': [69.81132075471699, 56.59340659340659, 46.05263157894737, 40.65040650406504], 'bp': 1.0, 'sys_len': 212, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 1.9856631755828857, 'eval_bleu': 52.1498, 'eval_gen_len': 8.5, 'eval_runtime': 3.1482, 'eval_samples_per_second': 9.529, 'eval_steps_per_second': 1.906, 'epoch': 158.94}

 25%|██▌       | 14400/57600 [2:31:10<6:58:00,  1.72it/s]

100%|██████████| 6/6 [00:02<00:00,  3.45it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 09:25:23,759 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 25%|██▌       | 14401/57600 [2:31:29<84:33:23,  7.05s/it]
 25%|██▌       | 14402/57600 [2:31:30<61:53:38,  5.16s/it]
 25%|██▌       | 14403/57600 [2:31:31<46:07:41,  3.84s/it]
 25%|██▌       | 14404/57600 [2:31:32<34:48:31,  2.90s/it]
 25%|██▌       | 14405/57600 [2:31:32<26:39:30,  2.22s/it]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 25%|██▌       | 14406/57600 [2:31:33<21:15:10,  1.77s/it]
 25%|██▌       | 14407/57600 [2:31:34<17:00:23,  1.42s/it]
 25%|██▌       | 14408/57600 [2:31:34<14:26:23,  1.20s/it]
 25%|██▌       | 14409/57600 [2:31:35<12:16:00,  1.02s/it]
 25%|██▌       | 14410/57600 [2:31:35<10:46:02,  1.11it/s]
 25%|██▌       | 14411/57600 [2:31:36<9:52:56,  1.21it/s] 
 25%|██▌       | 14412/57600 [2:31:37<9:31:03,  1.26it/s]
 25%|██▌       | 14413/57600 [2:31:38<9:11:07,  1.31it/s]
 25%|██▌       | 14414/57600 [2:31:38<8:46:11,  1.37it/s]
 25%|██▌       | 14415/57600 [2:31:39<8:13:04,  1.46it/s]
 25%|██▌       | 14416/57600 [2:31:39<8:06:47,  1.48it/s]
 25%|██▌       | 14417/57600 [2:31:40<8:00:21,  1.50it/s]
 25%|██▌       | 14418/57600 [2:31:41<8:02:46,  1.49it/s]
 25%|██▌       | 14419/57600 [2:31:41<7:58:43,  1.50it/s]
 25%|██▌       | 14420/57600 [2:31:42<7:48:02,  1.54it/s]
                                                         
{'loss': 1.2825, 'learning_rate': 7.770383275261323e-07, 'epoch': 159.16}

 25%|██▌       | 14420/57600 [2:31:42<7:48:02,  1.54it/s]
 25%|██▌       | 14421/57600 [2:31:43<7:57:24,  1.51it/s]
 25%|██▌       | 14422/57600 [2:31:43<7:44:31,  1.55it/s]
 25%|██▌       | 14423/57600 [2:31:44<7:48:24,  1.54it/s]
 25%|██▌       | 14424/57600 [2:31:45<7:40:26,  1.56it/s]
 25%|██▌       | 14425/57600 [2:31:45<7:32:19,  1.59it/s]
 25%|██▌       | 14426/57600 [2:31:46<7:38:00,  1.57it/s]
 25%|██▌       | 14427/57600 [2:31:46<7:21:54,  1.63it/s]
 25%|██▌       | 14428/57600 [2:31:47<7:33:16,  1.59it/s]
 25%|██▌       | 14429/57600 [2:31:48<7:44:30,  1.55it/s]
 25%|██▌       | 14430/57600 [2:31:48<7:39:01,  1.57it/s]
 25%|██▌       | 14431/57600 [2:31:49<7:44:01,  1.55it/s]
 25%|██▌       | 14432/57600 [2:31:50<7:42:24,  1.56it/s]
 25%|██▌       | 14433/57600 [2:31:50<7:30:10,  1.60it/s]
 25%|██▌       | 14434/57600 [2:31:51<7:34:01,  1.58it/s]
 25%|██▌       | 14435/57600 [2:31:52<7:34:22,  1.58it/s]
 25%|██▌       | 14436/57600 [2:31:52<7:37:57,  1.57it/s]
 25%|██▌       | 14437/57600 [2:31:53<7:55:38,  1.51it/s]
 25%|██▌       | 14438/57600 [2:31:54<7:47:13,  1.54it/s]
 25%|██▌       | 14439/57600 [2:31:54<7:39:37,  1.57it/s]
 25%|██▌       | 14440/57600 [2:31:55<7:55:09,  1.51it/s]
                                                         
{'loss': 1.3146, 'learning_rate': 7.767247386759582e-07, 'epoch': 159.38}

 25%|██▌       | 14440/57600 [2:31:55<7:55:09,  1.51it/s]
 25%|██▌       | 14441/57600 [2:31:56<7:48:46,  1.53it/s]
 25%|██▌       | 14442/57600 [2:31:56<7:49:35,  1.53it/s]
 25%|██▌       | 14443/57600 [2:31:57<7:49:36,  1.53it/s]
 25%|██▌       | 14444/57600 [2:31:57<7:39:20,  1.57it/s]
 25%|██▌       | 14445/57600 [2:31:58<7:28:28,  1.60it/s]
 25%|██▌       | 14446/57600 [2:31:59<7:20:04,  1.63it/s]
 25%|██▌       | 14447/57600 [2:31:59<7:29:32,  1.60it/s]
 25%|██▌       | 14448/57600 [2:32:00<7:25:49,  1.61it/s]
 25%|██▌       | 14449/57600 [2:32:01<7:30:49,  1.60it/s]
 25%|██▌       | 14450/57600 [2:32:01<7:31:12,  1.59it/s]
 25%|██▌       | 14451/57600 [2:32:02<7:59:19,  1.50it/s]
 25%|██▌       | 14452/57600 [2:32:03<8:12:50,  1.46it/s]
 25%|██▌       | 14453/57600 [2:32:03<8:21:55,  1.43it/s]
 25%|██▌       | 14454/57600 [2:32:04<8:39:06,  1.39it/s]
 25%|██▌       | 14455/57600 [2:32:05<8:04:46,  1.48it/s]
 25%|██▌       | 14456/57600 [2:32:05<7:48:54,  1.53it/s]
 25%|██▌       | 14457/57600 [2:32:06<7:49:22,  1.53it/s]
 25%|██▌       | 14458/57600 [2:32:07<7:33:15,  1.59it/s]
 25%|██▌       | 14459/57600 [2:32:07<7:29:17,  1.60it/s]
 25%|██▌       | 14460/57600 [2:32:08<7:31:25,  1.59it/s]
                                                         
{'loss': 1.3051, 'learning_rate': 7.76411149825784e-07, 'epoch': 159.6}

 25%|██▌       | 14460/57600 [2:32:08<7:31:25,  1.59it/s]
 25%|██▌       | 14461/57600 [2:32:08<7:16:50,  1.65it/s]
 25%|██▌       | 14462/57600 [2:32:09<7:13:25,  1.66it/s]
 25%|██▌       | 14463/57600 [2:32:10<7:13:54,  1.66it/s]
 25%|██▌       | 14464/57600 [2:32:10<7:19:33,  1.64it/s]
 25%|██▌       | 14465/57600 [2:32:11<7:19:05,  1.64it/s]
 25%|██▌       | 14466/57600 [2:32:11<7:19:23,  1.64it/s]
 25%|██▌       | 14467/57600 [2:32:12<7:14:52,  1.65it/s]
 25%|██▌       | 14468/57600 [2:32:13<7:09:33,  1.67it/s]
 25%|██▌       | 14469/57600 [2:32:13<7:22:21,  1.63it/s]
 25%|██▌       | 14470/57600 [2:32:14<7:44:56,  1.55it/s]
 25%|██▌       | 14471/57600 [2:32:15<7:30:24,  1.60it/s]
 25%|██▌       | 14472/57600 [2:32:15<7:28:44,  1.60it/s]
 25%|██▌       | 14473/57600 [2:32:16<7:12:44,  1.66it/s]
 25%|██▌       | 14474/57600 [2:32:16<7:24:07,  1.62it/s]
 25%|██▌       | 14475/57600 [2:32:17<7:20:09,  1.63it/s]
 25%|██▌       | 14476/57600 [2:32:18<7:39:36,  1.56it/s]
 25%|██▌       | 14477/57600 [2:32:18<7:36:52,  1.57it/s]
 25%|██▌       | 14478/57600 [2:32:19<7:52:15,  1.52it/s]
 25%|██▌       | 14479/57600 [2:32:20<7:48:28,  1.53it/s]
 25%|██▌       | 14480/57600 [2:32:20<7:34:42,  1.58it/s]
                                                         
{'loss': 1.2975, 'learning_rate': 7.760975609756097e-07, 'epoch': 159.82}

 25%|██▌       | 14480/57600 [2:32:20<7:34:42,  1.58it/s]
 25%|██▌       | 14481/57600 [2:32:21<7:27:48,  1.60it/s]
 25%|██▌       | 14482/57600 [2:32:21<7:33:26,  1.58it/s]
 25%|██▌       | 14483/57600 [2:32:22<7:29:37,  1.60it/s]
 25%|██▌       | 14484/57600 [2:32:23<7:28:11,  1.60it/s]
 25%|██▌       | 14485/57600 [2:32:23<7:26:11,  1.61it/s]
 25%|██▌       | 14486/57600 [2:32:24<7:35:41,  1.58it/s]
 25%|██▌       | 14487/57600 [2:32:25<7:30:49,  1.59it/s]
 25%|██▌       | 14488/57600 [2:32:25<7:39:26,  1.56it/s]
 25%|██▌       | 14489/57600 [2:32:26<7:50:04,  1.53it/s]
 25%|██▌       | 14490/57600 [2:32:27<7:43:05,  1.55it/s]
 25%|██▌       | 14491/57600 [2:32:27<7:35:19,  1.58it/s]
 25%|██▌       | 14492/57600 [2:32:28<7:28:21,  1.60it/s]
 25%|██▌       | 14493/57600 [2:32:28<7:21:33,  1.63it/s]
 25%|██▌       | 14494/57600 [2:32:29<7:33:03,  1.59it/s]
 25%|██▌       | 14495/57600 [2:32:30<7:24:44,  1.62it/s]
 25%|██▌       | 14496/57600 [2:32:30<7:38:40,  1.57it/s]
 25%|██▌       | 14497/57600 [2:32:31<8:06:09,  1.48it/s]
 25%|██▌       | 14498/57600 [2:32:32<8:04:09,  1.48it/s]
 25%|██▌       | 14499/57600 [2:32:32<7:57:34,  1.50it/s]
 25%|██▌       | 14500/57600 [2:32:33<8:00:59,  1.49it/s]
                                                         
{'loss': 1.3279, 'learning_rate': 7.757839721254355e-07, 'epoch': 160.04}

 25%|██▌       | 14500/57600 [2:32:33<8:00:59,  1.49it/s]
 25%|██▌       | 14501/57600 [2:32:34<7:54:01,  1.52it/s]
 25%|██▌       | 14502/57600 [2:32:34<8:20:32,  1.44it/s]
 25%|██▌       | 14503/57600 [2:32:35<8:34:23,  1.40it/s]
 25%|██▌       | 14504/57600 [2:32:36<8:26:31,  1.42it/s]
 25%|██▌       | 14505/57600 [2:32:37<8:03:07,  1.49it/s]
 25%|██▌       | 14506/57600 [2:32:37<7:52:02,  1.52it/s]
 25%|██▌       | 14507/57600 [2:32:38<7:51:49,  1.52it/s]
 25%|██▌       | 14508/57600 [2:32:38<7:37:34,  1.57it/s]
 25%|██▌       | 14509/57600 [2:32:39<7:36:39,  1.57it/s]
 25%|██▌       | 14510/57600 [2:32:40<7:33:36,  1.58it/s]
 25%|██▌       | 14511/57600 [2:32:40<7:20:28,  1.63it/s]
 25%|██▌       | 14512/57600 [2:32:41<7:34:23,  1.58it/s]
 25%|██▌       | 14513/57600 [2:32:42<7:32:31,  1.59it/s]
 25%|██▌       | 14514/57600 [2:32:42<7:25:07,  1.61it/s]
 25%|██▌       | 14515/57600 [2:32:43<7:28:59,  1.60it/s]
 25%|██▌       | 14516/57600 [2:32:43<7:44:29,  1.55it/s]
 25%|██▌       | 14517/57600 [2:32:44<7:47:39,  1.54it/s]
 25%|██▌       | 14518/57600 [2:32:45<7:58:50,  1.50it/s]
 25%|██▌       | 14519/57600 [2:32:45<7:50:53,  1.52it/s]
 25%|██▌       | 14520/57600 [2:32:46<8:00:15,  1.50it/s]
                                                         
{'loss': 1.3128, 'learning_rate': 7.754703832752613e-07, 'epoch': 160.26}

 25%|██▌       | 14520/57600 [2:32:46<8:00:15,  1.50it/s]
 25%|██▌       | 14521/57600 [2:32:47<7:53:19,  1.52it/s]
 25%|██▌       | 14522/57600 [2:32:47<7:53:12,  1.52it/s]
 25%|██▌       | 14523/57600 [2:32:48<7:48:42,  1.53it/s]
 25%|██▌       | 14524/57600 [2:32:49<7:35:42,  1.58it/s]
 25%|██▌       | 14525/57600 [2:32:49<7:33:30,  1.58it/s]
 25%|██▌       | 14526/57600 [2:32:50<7:28:18,  1.60it/s]
 25%|██▌       | 14527/57600 [2:32:51<7:29:14,  1.60it/s]
 25%|██▌       | 14528/57600 [2:32:51<7:47:29,  1.54it/s]
 25%|██▌       | 14529/57600 [2:32:52<8:00:11,  1.49it/s]
 25%|██▌       | 14530/57600 [2:32:53<7:52:35,  1.52it/s]
 25%|██▌       | 14531/57600 [2:32:53<7:58:40,  1.50it/s]
 25%|██▌       | 14532/57600 [2:32:54<7:50:53,  1.52it/s]
 25%|██▌       | 14533/57600 [2:32:54<7:33:20,  1.58it/s]
 25%|██▌       | 14534/57600 [2:32:55<7:29:45,  1.60it/s]
 25%|██▌       | 14535/57600 [2:32:56<7:39:49,  1.56it/s]
 25%|██▌       | 14536/57600 [2:32:56<7:42:28,  1.55it/s]
 25%|██▌       | 14537/57600 [2:32:57<7:57:06,  1.50it/s]
 25%|██▌       | 14538/57600 [2:32:58<7:43:57,  1.55it/s]
 25%|██▌       | 14539/57600 [2:32:58<7:45:38,  1.54it/s]
 25%|██▌       | 14540/57600 [2:32:59<8:00:15,  1.49it/s]
                                                         
{'loss': 1.2796, 'learning_rate': 7.751567944250871e-07, 'epoch': 160.49}

 25%|██▌       | 14540/57600 [2:32:59<8:00:15,  1.49it/s]
 25%|██▌       | 14541/57600 [2:33:00<7:32:49,  1.58it/s]
 25%|██▌       | 14542/57600 [2:33:00<7:45:04,  1.54it/s]
 25%|██▌       | 14543/57600 [2:33:01<7:46:55,  1.54it/s]
 25%|██▌       | 14544/57600 [2:33:02<7:34:27,  1.58it/s]
 25%|██▌       | 14545/57600 [2:33:02<7:55:55,  1.51it/s]
 25%|██▌       | 14546/57600 [2:33:03<7:48:44,  1.53it/s]
 25%|██▌       | 14547/57600 [2:33:04<7:44:49,  1.54it/s]
 25%|██▌       | 14548/57600 [2:33:04<7:52:43,  1.52it/s]
 25%|██▌       | 14549/57600 [2:33:05<7:53:14,  1.52it/s]
 25%|██▌       | 14550/57600 [2:33:06<7:46:08,  1.54it/s]
 25%|██▌       | 14551/57600 [2:33:06<8:21:56,  1.43it/s]
 25%|██▌       | 14552/57600 [2:33:07<8:28:08,  1.41it/s]
 25%|██▌       | 14553/57600 [2:33:08<8:10:54,  1.46it/s]
 25%|██▌       | 14554/57600 [2:33:08<8:12:48,  1.46it/s]
 25%|██▌       | 14555/57600 [2:33:09<8:09:45,  1.46it/s]
 25%|██▌       | 14556/57600 [2:33:10<7:54:49,  1.51it/s]
 25%|██▌       | 14557/57600 [2:33:10<7:54:14,  1.51it/s]
 25%|██▌       | 14558/57600 [2:33:11<7:52:13,  1.52it/s]
 25%|██▌       | 14559/57600 [2:33:12<7:37:24,  1.57it/s]
 25%|██▌       | 14560/57600 [2:33:12<7:52:35,  1.52it/s]
                                                         
{'loss': 1.313, 'learning_rate': 7.748432055749128e-07, 'epoch': 160.71}

 25%|██▌       | 14560/57600 [2:33:12<7:52:35,  1.52it/s]
 25%|██▌       | 14561/57600 [2:33:13<7:47:46,  1.53it/s]
 25%|██▌       | 14562/57600 [2:33:14<7:45:32,  1.54it/s]
 25%|██▌       | 14563/57600 [2:33:14<8:00:47,  1.49it/s]
 25%|██▌       | 14564/57600 [2:33:15<8:12:00,  1.46it/s]
 25%|██▌       | 14565/57600 [2:33:16<8:12:00,  1.46it/s]
 25%|██▌       | 14566/57600 [2:33:16<7:57:57,  1.50it/s]
 25%|██▌       | 14567/57600 [2:33:17<7:43:56,  1.55it/s]
 25%|██▌       | 14568/57600 [2:33:18<7:43:05,  1.55it/s]
 25%|██▌       | 14569/57600 [2:33:18<7:36:17,  1.57it/s]
 25%|██▌       | 14570/57600 [2:33:19<7:29:47,  1.59it/s]
 25%|██▌       | 14571/57600 [2:33:19<7:28:50,  1.60it/s]
 25%|██▌       | 14572/57600 [2:33:20<7:29:24,  1.60it/s]
 25%|██▌       | 14573/57600 [2:33:21<7:32:26,  1.58it/s]
 25%|██▌       | 14574/57600 [2:33:21<7:27:47,  1.60it/s]
 25%|██▌       | 14575/57600 [2:33:22<7:22:40,  1.62it/s]
 25%|██▌       | 14576/57600 [2:33:22<7:18:48,  1.63it/s]
 25%|██▌       | 14577/57600 [2:33:23<7:08:57,  1.67it/s]
 25%|██▌       | 14578/57600 [2:33:24<7:04:13,  1.69it/s]
 25%|██▌       | 14579/57600 [2:33:24<7:20:11,  1.63it/s]
 25%|██▌       | 14580/57600 [2:33:25<7:22:18,  1.62it/s]
                                                         
{'loss': 1.2979, 'learning_rate': 7.745296167247387e-07, 'epoch': 160.93}

 25%|██▌       | 14580/57600 [2:33:25<7:22:18,  1.62it/s]
 25%|██▌       | 14581/57600 [2:33:26<7:24:32,  1.61it/s]
 25%|██▌       | 14582/57600 [2:33:26<7:36:39,  1.57it/s]
 25%|██▌       | 14583/57600 [2:33:27<7:28:54,  1.60it/s]
 25%|██▌       | 14584/57600 [2:33:27<7:24:05,  1.61it/s]
 25%|██▌       | 14585/57600 [2:33:28<7:28:20,  1.60it/s]
 25%|██▌       | 14586/57600 [2:33:29<7:31:17,  1.59it/s]
 25%|██▌       | 14587/57600 [2:33:29<7:44:14,  1.54it/s]
 25%|██▌       | 14588/57600 [2:33:30<7:53:41,  1.51it/s]
 25%|██▌       | 14589/57600 [2:33:31<7:44:47,  1.54it/s]
 25%|██▌       | 14590/57600 [2:33:31<7:41:49,  1.55it/s]
 25%|██▌       | 14591/57600 [2:33:32<7:34:44,  1.58it/s]
 25%|██▌       | 14592/57600 [2:33:33<7:43:48,  1.55it/s]
 25%|██▌       | 14593/57600 [2:33:33<7:37:36,  1.57it/s]
 25%|██▌       | 14594/57600 [2:33:34<7:32:33,  1.58it/s]
 25%|██▌       | 14595/57600 [2:33:34<7:26:38,  1.60it/s]
 25%|██▌       | 14596/57600 [2:33:35<7:33:57,  1.58it/s]
 25%|██▌       | 14597/57600 [2:33:36<7:29:28,  1.59it/s]
 25%|██▌       | 14598/57600 [2:33:36<7:34:58,  1.58it/s]
 25%|██▌       | 14599/57600 [2:33:37<7:22:36,  1.62it/s]
 25%|██▌       | 14600/57600 [2:33:38<7:38:10,  1.56it/s]
                                                         
{'loss': 1.3405, 'learning_rate': 7.742160278745645e-07, 'epoch': 161.15}

 25%|██▌       | 14600/57600 [2:33:38<7:38:10,  1.56it/s]
 25%|██▌       | 14601/57600 [2:33:38<7:37:07,  1.57it/s]
 25%|██▌       | 14602/57600 [2:33:39<7:45:52,  1.54it/s]
 25%|██▌       | 14603/57600 [2:33:40<7:43:44,  1.55it/s]
 25%|██▌       | 14604/57600 [2:33:40<7:41:22,  1.55it/s]
 25%|██▌       | 14605/57600 [2:33:41<7:45:37,  1.54it/s]
 25%|██▌       | 14606/57600 [2:33:42<7:52:58,  1.52it/s]
 25%|██▌       | 14607/57600 [2:33:42<7:49:21,  1.53it/s]
 25%|██▌       | 14608/57600 [2:33:43<7:37:22,  1.57it/s]
 25%|██▌       | 14609/57600 [2:33:43<7:38:18,  1.56it/s]
 25%|██▌       | 14610/57600 [2:33:44<7:34:40,  1.58it/s]
 25%|██▌       | 14611/57600 [2:33:45<7:18:26,  1.63it/s]
 25%|██▌       | 14612/57600 [2:33:45<7:11:01,  1.66it/s]
 25%|██▌       | 14613/57600 [2:33:46<7:20:36,  1.63it/s]
 25%|██▌       | 14614/57600 [2:33:46<7:14:58,  1.65it/s]
 25%|██▌       | 14615/57600 [2:33:47<7:04:04,  1.69it/s]
 25%|██▌       | 14616/57600 [2:33:48<7:07:19,  1.68it/s]
 25%|██▌       | 14617/57600 [2:33:48<7:10:26,  1.66it/s]
 25%|██▌       | 14618/57600 [2:33:49<6:58:58,  1.71it/s]
 25%|██▌       | 14619/57600 [2:33:49<7:15:45,  1.64it/s]
 25%|██▌       | 14620/57600 [2:33:50<7:23:56,  1.61it/s]
                                                         
{'loss': 1.2926, 'learning_rate': 7.739024390243903e-07, 'epoch': 161.37}

 25%|██▌       | 14620/57600 [2:33:50<7:23:56,  1.61it/s]
 25%|██▌       | 14621/57600 [2:33:51<7:11:36,  1.66it/s]
 25%|██▌       | 14622/57600 [2:33:51<7:14:24,  1.65it/s]
 25%|██▌       | 14623/57600 [2:33:52<7:19:03,  1.63it/s]
 25%|██▌       | 14624/57600 [2:33:53<7:29:19,  1.59it/s]
 25%|██▌       | 14625/57600 [2:33:53<7:17:11,  1.64it/s]
 25%|██▌       | 14626/57600 [2:33:54<7:08:42,  1.67it/s]
 25%|██▌       | 14627/57600 [2:33:54<7:12:07,  1.66it/s]
 25%|██▌       | 14628/57600 [2:33:55<7:06:55,  1.68it/s]
 25%|██▌       | 14629/57600 [2:33:56<7:13:31,  1.65it/s]
 25%|██▌       | 14630/57600 [2:33:56<7:16:32,  1.64it/s]
 25%|██▌       | 14631/57600 [2:33:57<7:17:26,  1.64it/s]
 25%|██▌       | 14632/57600 [2:33:57<7:16:37,  1.64it/s]
 25%|██▌       | 14633/57600 [2:33:58<7:06:22,  1.68it/s]
 25%|██▌       | 14634/57600 [2:33:59<7:05:31,  1.68it/s]
 25%|██▌       | 14635/57600 [2:33:59<6:57:19,  1.72it/s]
 25%|██▌       | 14636/57600 [2:34:00<6:53:48,  1.73it/s]
 25%|██▌       | 14637/57600 [2:34:00<7:23:43,  1.61it/s]
 25%|██▌       | 14638/57600 [2:34:01<7:14:32,  1.65it/s]
 25%|██▌       | 14639/57600 [2:34:02<7:12:02,  1.66it/s]
 25%|██▌       | 14640/57600 [2:34:02<7:17:52,  1.64it/s]
                                                         
{'loss': 1.3202, 'learning_rate': 7.735888501742159e-07, 'epoch': 161.59}

 25%|██▌       | 14640/57600 [2:34:02<7:17:52,  1.64it/s]
 25%|██▌       | 14641/57600 [2:34:03<7:14:54,  1.65it/s]
 25%|██▌       | 14642/57600 [2:34:03<7:24:56,  1.61it/s]
 25%|██▌       | 14643/57600 [2:34:04<7:13:38,  1.65it/s]
 25%|██▌       | 14644/57600 [2:34:05<7:23:06,  1.62it/s]
 25%|██▌       | 14645/57600 [2:34:05<7:27:09,  1.60it/s]
 25%|██▌       | 14646/57600 [2:34:06<7:28:09,  1.60it/s]
 25%|██▌       | 14647/57600 [2:34:07<7:30:07,  1.59it/s]
 25%|██▌       | 14648/57600 [2:34:07<7:21:11,  1.62it/s]
 25%|██▌       | 14649/57600 [2:34:08<7:26:03,  1.60it/s]
 25%|██▌       | 14650/57600 [2:34:08<7:16:37,  1.64it/s]
 25%|██▌       | 14651/57600 [2:34:09<7:21:42,  1.62it/s]
 25%|██▌       | 14652/57600 [2:34:10<7:20:41,  1.62it/s]
 25%|██▌       | 14653/57600 [2:34:10<7:20:26,  1.63it/s]
 25%|██▌       | 14654/57600 [2:34:11<7:23:15,  1.61it/s]
 25%|██▌       | 14655/57600 [2:34:11<7:16:16,  1.64it/s]
 25%|██▌       | 14656/57600 [2:34:12<7:14:34,  1.65it/s]
 25%|██▌       | 14657/57600 [2:34:13<7:02:16,  1.69it/s]
 25%|██▌       | 14658/57600 [2:34:13<7:03:47,  1.69it/s]
 25%|██▌       | 14659/57600 [2:34:14<7:18:17,  1.63it/s]
 25%|██▌       | 14660/57600 [2:34:14<7:20:56,  1.62it/s]
                                                         
{'loss': 1.3303, 'learning_rate': 7.732752613240418e-07, 'epoch': 161.81}

 25%|██▌       | 14660/57600 [2:34:14<7:20:56,  1.62it/s]
 25%|██▌       | 14661/57600 [2:34:15<7:24:38,  1.61it/s]
 25%|██▌       | 14662/57600 [2:34:16<7:27:37,  1.60it/s]
 25%|██▌       | 14663/57600 [2:34:16<7:37:51,  1.56it/s]
 25%|██▌       | 14664/57600 [2:34:17<7:28:43,  1.59it/s]
 25%|██▌       | 14665/57600 [2:34:18<7:42:51,  1.55it/s]
 25%|██▌       | 14666/57600 [2:34:18<7:54:59,  1.51it/s]
 25%|██▌       | 14667/57600 [2:34:19<7:54:47,  1.51it/s]
 25%|██▌       | 14668/57600 [2:34:20<7:37:45,  1.56it/s]
 25%|██▌       | 14669/57600 [2:34:20<7:35:50,  1.57it/s]
 25%|██▌       | 14670/57600 [2:34:21<7:29:55,  1.59it/s]
 25%|██▌       | 14671/57600 [2:34:22<7:34:06,  1.58it/s]
 25%|██▌       | 14672/57600 [2:34:22<7:33:16,  1.58it/s]
 25%|██▌       | 14673/57600 [2:34:23<7:16:32,  1.64it/s]
 25%|██▌       | 14674/57600 [2:34:23<7:30:27,  1.59it/s]
 25%|██▌       | 14675/57600 [2:34:24<7:22:28,  1.62it/s]
 25%|██▌       | 14676/57600 [2:34:25<7:19:57,  1.63it/s]
 25%|██▌       | 14677/57600 [2:34:25<7:17:06,  1.64it/s]
 25%|██▌       | 14678/57600 [2:34:26<7:44:31,  1.54it/s]
 25%|██▌       | 14679/57600 [2:34:27<7:36:59,  1.57it/s]
 25%|██▌       | 14680/57600 [2:34:27<7:44:26,  1.54it/s]
                                                         
{'loss': 1.271, 'learning_rate': 7.729616724738675e-07, 'epoch': 162.03}

 25%|██▌       | 14680/57600 [2:34:27<7:44:26,  1.54it/s]
 25%|██▌       | 14681/57600 [2:34:28<7:28:52,  1.59it/s]
 25%|██▌       | 14682/57600 [2:34:28<7:32:14,  1.58it/s]
 25%|██▌       | 14683/57600 [2:34:29<7:43:26,  1.54it/s]
 25%|██▌       | 14684/57600 [2:34:30<7:32:57,  1.58it/s]
 25%|██▌       | 14685/57600 [2:34:30<7:34:30,  1.57it/s]
 25%|██▌       | 14686/57600 [2:34:31<7:41:51,  1.55it/s]
 25%|██▌       | 14687/57600 [2:34:32<7:24:05,  1.61it/s]
 26%|██▌       | 14688/57600 [2:34:32<7:11:52,  1.66it/s]
 26%|██▌       | 14689/57600 [2:34:33<7:27:10,  1.60it/s]
 26%|██▌       | 14690/57600 [2:34:33<7:32:43,  1.58it/s]
 26%|██▌       | 14691/57600 [2:34:34<7:14:51,  1.64it/s]
 26%|██▌       | 14692/57600 [2:34:35<7:12:14,  1.65it/s]
 26%|██▌       | 14693/57600 [2:34:35<7:08:52,  1.67it/s]
 26%|██▌       | 14694/57600 [2:34:36<7:02:10,  1.69it/s]
 26%|██▌       | 14695/57600 [2:34:36<7:15:40,  1.64it/s]
 26%|██▌       | 14696/57600 [2:34:37<7:15:25,  1.64it/s]
 26%|██▌       | 14697/57600 [2:34:38<7:13:58,  1.65it/s]
 26%|██▌       | 14698/57600 [2:34:38<7:27:00,  1.60it/s]
 26%|██▌       | 14699/57600 [2:34:39<7:49:24,  1.52it/s]
 26%|██▌       | 14700/57600 [2:34:40<7:49:18,  1.52it/s]
                                                         
{'loss': 1.2651, 'learning_rate': 7.726480836236933e-07, 'epoch': 162.25}

 26%|██▌       | 14700/57600 [2:34:40<7:49:18,  1.52it/s]
 26%|██▌       | 14701/57600 [2:34:40<7:39:13,  1.56it/s]
 26%|██▌       | 14702/57600 [2:34:41<7:39:36,  1.56it/s]
 26%|██▌       | 14703/57600 [2:34:42<7:48:03,  1.53it/s]
 26%|██▌       | 14704/57600 [2:34:42<7:33:43,  1.58it/s]
 26%|██▌       | 14705/57600 [2:34:43<7:30:21,  1.59it/s]
 26%|██▌       | 14706/57600 [2:34:43<7:23:28,  1.61it/s]
 26%|██▌       | 14707/57600 [2:34:44<7:12:25,  1.65it/s]
 26%|██▌       | 14708/57600 [2:34:45<7:21:24,  1.62it/s]
 26%|██▌       | 14709/57600 [2:34:45<7:22:44,  1.61it/s]
 26%|██▌       | 14710/57600 [2:34:46<7:31:08,  1.58it/s]
 26%|██▌       | 14711/57600 [2:34:47<7:26:24,  1.60it/s]
 26%|██▌       | 14712/57600 [2:34:47<7:33:31,  1.58it/s]
 26%|██▌       | 14713/57600 [2:34:48<7:17:14,  1.63it/s]
 26%|██▌       | 14714/57600 [2:34:48<7:03:51,  1.69it/s]
 26%|██▌       | 14715/57600 [2:34:49<7:15:56,  1.64it/s]
 26%|██▌       | 14716/57600 [2:34:50<7:13:04,  1.65it/s]
 26%|██▌       | 14717/57600 [2:34:50<7:09:17,  1.66it/s]
 26%|██▌       | 14718/57600 [2:34:51<7:16:24,  1.64it/s]
 26%|██▌       | 14719/57600 [2:34:51<7:33:31,  1.58it/s]
 26%|██▌       | 14720/57600 [2:34:52<7:25:13,  1.61it/s]
                                                         
{'loss': 1.2809, 'learning_rate': 7.723344947735191e-07, 'epoch': 162.47}

 26%|██▌       | 14720/57600 [2:34:52<7:25:13,  1.61it/s]
 26%|██▌       | 14721/57600 [2:34:53<7:13:25,  1.65it/s]
 26%|██▌       | 14722/57600 [2:34:53<7:08:58,  1.67it/s]
 26%|██▌       | 14723/57600 [2:34:54<7:16:22,  1.64it/s]
 26%|██▌       | 14724/57600 [2:34:54<7:05:36,  1.68it/s]
 26%|██▌       | 14725/57600 [2:34:55<7:02:15,  1.69it/s]
 26%|██▌       | 14726/57600 [2:34:56<7:02:23,  1.69it/s]
 26%|██▌       | 14727/57600 [2:34:56<7:05:19,  1.68it/s]
 26%|██▌       | 14728/57600 [2:34:57<6:59:23,  1.70it/s]
 26%|██▌       | 14729/57600 [2:34:57<7:12:23,  1.65it/s]
 26%|██▌       | 14730/57600 [2:34:58<7:01:11,  1.70it/s]
 26%|██▌       | 14731/57600 [2:34:59<6:53:11,  1.73it/s]
 26%|██▌       | 14732/57600 [2:34:59<6:47:16,  1.75it/s]
 26%|██▌       | 14733/57600 [2:35:00<7:01:52,  1.69it/s]
 26%|██▌       | 14734/57600 [2:35:00<6:59:15,  1.70it/s]
 26%|██▌       | 14735/57600 [2:35:01<6:59:59,  1.70it/s]
 26%|██▌       | 14736/57600 [2:35:02<7:17:36,  1.63it/s]
 26%|██▌       | 14737/57600 [2:35:02<7:15:29,  1.64it/s]
 26%|██▌       | 14738/57600 [2:35:03<7:21:09,  1.62it/s]
 26%|██▌       | 14739/57600 [2:35:03<7:18:09,  1.63it/s]
 26%|██▌       | 14740/57600 [2:35:04<7:10:15,  1.66it/s]
                                                         
{'loss': 1.3978, 'learning_rate': 7.72020905923345e-07, 'epoch': 162.69}

 26%|██▌       | 14740/57600 [2:35:04<7:10:15,  1.66it/s]
 26%|██▌       | 14741/57600 [2:35:05<7:00:54,  1.70it/s]
 26%|██▌       | 14742/57600 [2:35:05<7:04:12,  1.68it/s]
 26%|██▌       | 14743/57600 [2:35:06<7:03:56,  1.68it/s]
 26%|██▌       | 14744/57600 [2:35:06<7:21:14,  1.62it/s]
 26%|██▌       | 14745/57600 [2:35:07<7:22:49,  1.61it/s]
 26%|██▌       | 14746/57600 [2:35:08<7:25:04,  1.60it/s]
 26%|██▌       | 14747/57600 [2:35:08<7:48:52,  1.52it/s]
 26%|██▌       | 14748/57600 [2:35:09<7:41:19,  1.55it/s]
 26%|██▌       | 14749/57600 [2:35:10<7:28:41,  1.59it/s]
 26%|██▌       | 14750/57600 [2:35:10<7:27:49,  1.59it/s]
 26%|██▌       | 14751/57600 [2:35:11<7:07:31,  1.67it/s]
 26%|██▌       | 14752/57600 [2:35:11<7:16:07,  1.64it/s]
 26%|██▌       | 14753/57600 [2:35:12<7:29:36,  1.59it/s]
 26%|██▌       | 14754/57600 [2:35:13<7:27:13,  1.60it/s]
 26%|██▌       | 14755/57600 [2:35:13<7:30:17,  1.59it/s]
 26%|██▌       | 14756/57600 [2:35:14<7:32:46,  1.58it/s]
 26%|██▌       | 14757/57600 [2:35:15<7:18:54,  1.63it/s]
 26%|██▌       | 14758/57600 [2:35:15<7:32:50,  1.58it/s]
 26%|██▌       | 14759/57600 [2:35:16<7:28:37,  1.59it/s]
 26%|██▌       | 14760/57600 [2:35:17<7:38:52,  1.56it/s]
                                                         
{'loss': 1.2972, 'learning_rate': 7.717073170731707e-07, 'epoch': 162.91}

 26%|██▌       | 14760/57600 [2:35:17<7:38:52,  1.56it/s]
 26%|██▌       | 14761/57600 [2:35:17<7:44:00,  1.54it/s]
 26%|██▌       | 14762/57600 [2:35:18<7:50:39,  1.52it/s]
 26%|██▌       | 14763/57600 [2:35:18<7:26:05,  1.60it/s]
 26%|██▌       | 14764/57600 [2:35:19<7:14:00,  1.64it/s]
 26%|██▌       | 14765/57600 [2:35:20<7:22:59,  1.61it/s]
 26%|██▌       | 14766/57600 [2:35:20<7:09:04,  1.66it/s]
 26%|██▌       | 14767/57600 [2:35:21<7:03:24,  1.69it/s]
 26%|██▌       | 14768/57600 [2:35:21<7:28:09,  1.59it/s]
 26%|██▌       | 14769/57600 [2:35:22<7:24:32,  1.61it/s]
 26%|██▌       | 14770/57600 [2:35:23<7:25:07,  1.60it/s]
 26%|██▌       | 14771/57600 [2:35:23<7:25:32,  1.60it/s]
 26%|██▌       | 14772/57600 [2:35:24<7:23:16,  1.61it/s]
 26%|██▌       | 14773/57600 [2:35:25<7:15:45,  1.64it/s]
 26%|██▌       | 14774/57600 [2:35:25<7:04:33,  1.68it/s]
 26%|██▌       | 14775/57600 [2:35:26<6:58:33,  1.71it/s]
 26%|██▌       | 14776/57600 [2:35:26<7:34:03,  1.57it/s]
 26%|██▌       | 14777/57600 [2:35:27<7:24:18,  1.61it/s]
 26%|██▌       | 14778/57600 [2:35:28<7:30:25,  1.58it/s]
 26%|██▌       | 14779/57600 [2:35:28<7:34:24,  1.57it/s]
 26%|██▌       | 14780/57600 [2:35:29<7:32:18,  1.58it/s]
                                                         
{'loss': 1.3079, 'learning_rate': 7.713937282229964e-07, 'epoch': 163.13}

 26%|██▌       | 14780/57600 [2:35:29<7:32:18,  1.58it/s]
 26%|██▌       | 14781/57600 [2:35:30<7:35:36,  1.57it/s]
 26%|██▌       | 14782/57600 [2:35:30<7:29:32,  1.59it/s]
 26%|██▌       | 14783/57600 [2:35:31<7:33:47,  1.57it/s]
 26%|██▌       | 14784/57600 [2:35:32<7:46:53,  1.53it/s]
 26%|██▌       | 14785/57600 [2:35:32<7:33:42,  1.57it/s]
 26%|██▌       | 14786/57600 [2:35:33<7:25:53,  1.60it/s]
 26%|██▌       | 14787/57600 [2:35:33<7:18:08,  1.63it/s]
 26%|██▌       | 14788/57600 [2:35:34<7:20:14,  1.62it/s]
 26%|██▌       | 14789/57600 [2:35:35<7:15:34,  1.64it/s]
 26%|██▌       | 14790/57600 [2:35:35<7:14:59,  1.64it/s]
 26%|██▌       | 14791/57600 [2:35:36<7:12:58,  1.65it/s]
 26%|██▌       | 14792/57600 [2:35:36<7:12:43,  1.65it/s]
 26%|██▌       | 14793/57600 [2:35:37<7:05:14,  1.68it/s]
 26%|██▌       | 14794/57600 [2:35:37<7:01:18,  1.69it/s]
 26%|██▌       | 14795/57600 [2:35:38<7:02:43,  1.69it/s]
 26%|██▌       | 14796/57600 [2:35:39<7:04:20,  1.68it/s]
 26%|██▌       | 14797/57600 [2:35:39<7:16:53,  1.63it/s]
 26%|██▌       | 14798/57600 [2:35:40<7:14:49,  1.64it/s]
 26%|██▌       | 14799/57600 [2:35:41<7:24:24,  1.61it/s]
 26%|██▌       | 14800/57600 [2:35:41<7:12:08,  1.65it/s]
                                                         
{'loss': 1.2769, 'learning_rate': 7.710801393728223e-07, 'epoch': 163.36}

 26%|██▌       | 14800/57600 [2:35:41<7:12:08,  1.65it/s]
 26%|██▌       | 14801/57600 [2:35:42<7:30:57,  1.58it/s]
 26%|██▌       | 14802/57600 [2:35:43<7:36:41,  1.56it/s]
 26%|██▌       | 14803/57600 [2:35:43<7:25:34,  1.60it/s]
 26%|██▌       | 14804/57600 [2:35:44<7:24:55,  1.60it/s]
 26%|██▌       | 14805/57600 [2:35:44<7:13:42,  1.64it/s]
 26%|██▌       | 14806/57600 [2:35:45<7:21:10,  1.62it/s]
 26%|██▌       | 14807/57600 [2:35:46<7:15:45,  1.64it/s]
 26%|██▌       | 14808/57600 [2:35:46<7:05:47,  1.68it/s]
 26%|██▌       | 14809/57600 [2:35:47<6:57:23,  1.71it/s]
 26%|██▌       | 14810/57600 [2:35:47<7:00:14,  1.70it/s]
 26%|██▌       | 14811/57600 [2:35:48<6:56:19,  1.71it/s]
 26%|██▌       | 14812/57600 [2:35:48<7:09:02,  1.66it/s]
 26%|██▌       | 14813/57600 [2:35:49<6:56:54,  1.71it/s]
 26%|██▌       | 14814/57600 [2:35:50<6:54:20,  1.72it/s]
 26%|██▌       | 14815/57600 [2:35:50<6:53:31,  1.72it/s]
 26%|██▌       | 14816/57600 [2:35:51<6:54:03,  1.72it/s]
 26%|██▌       | 14817/57600 [2:35:51<6:53:57,  1.72it/s]
 26%|██▌       | 14818/57600 [2:35:52<7:24:14,  1.61it/s]
 26%|██▌       | 14819/57600 [2:35:53<7:15:27,  1.64it/s]
 26%|██▌       | 14820/57600 [2:35:53<7:17:29,  1.63it/s]
                                                         
{'loss': 1.3133, 'learning_rate': 7.707665505226481e-07, 'epoch': 163.58}

 26%|██▌       | 14820/57600 [2:35:53<7:17:29,  1.63it/s]
 26%|██▌       | 14821/57600 [2:35:54<7:31:26,  1.58it/s]
 26%|██▌       | 14822/57600 [2:35:55<7:32:37,  1.58it/s]
 26%|██▌       | 14823/57600 [2:35:55<7:32:08,  1.58it/s]
 26%|██▌       | 14824/57600 [2:35:56<7:32:36,  1.58it/s]
 26%|██▌       | 14825/57600 [2:35:56<7:32:45,  1.57it/s]
 26%|██▌       | 14826/57600 [2:35:57<7:35:26,  1.57it/s]
 26%|██▌       | 14827/57600 [2:35:58<7:23:06,  1.61it/s]
 26%|██▌       | 14828/57600 [2:35:58<7:27:24,  1.59it/s]
 26%|██▌       | 14829/57600 [2:35:59<7:48:35,  1.52it/s]
 26%|██▌       | 14830/57600 [2:36:00<7:26:37,  1.60it/s]
 26%|██▌       | 14831/57600 [2:36:00<7:13:49,  1.64it/s]
 26%|██▌       | 14832/57600 [2:36:01<7:21:35,  1.61it/s]
 26%|██▌       | 14833/57600 [2:36:01<7:15:26,  1.64it/s]
 26%|██▌       | 14834/57600 [2:36:02<7:13:54,  1.64it/s]
 26%|██▌       | 14835/57600 [2:36:03<7:12:17,  1.65it/s]
 26%|██▌       | 14836/57600 [2:36:03<7:22:38,  1.61it/s]
 26%|██▌       | 14837/57600 [2:36:04<7:08:36,  1.66it/s]
 26%|██▌       | 14838/57600 [2:36:04<6:58:02,  1.70it/s]
 26%|██▌       | 14839/57600 [2:36:05<7:14:15,  1.64it/s]
 26%|██▌       | 14840/57600 [2:36:06<7:27:49,  1.59it/s]
                                                         
{'loss': 1.2618, 'learning_rate': 7.704529616724738e-07, 'epoch': 163.8}

 26%|██▌       | 14840/57600 [2:36:06<7:27:49,  1.59it/s]
 26%|██▌       | 14841/57600 [2:36:06<7:31:05,  1.58it/s]
 26%|██▌       | 14842/57600 [2:36:07<7:28:18,  1.59it/s]
 26%|██▌       | 14843/57600 [2:36:08<7:31:28,  1.58it/s]
 26%|██▌       | 14844/57600 [2:36:08<7:18:52,  1.62it/s]
 26%|██▌       | 14845/57600 [2:36:09<7:12:28,  1.65it/s]
 26%|██▌       | 14846/57600 [2:36:09<7:16:45,  1.63it/s]
 26%|██▌       | 14847/57600 [2:36:10<7:28:45,  1.59it/s]
 26%|██▌       | 14848/57600 [2:36:11<7:23:06,  1.61it/s]
 26%|██▌       | 14849/57600 [2:36:11<7:39:42,  1.55it/s]
 26%|██▌       | 14850/57600 [2:36:12<7:29:30,  1.59it/s]
 26%|██▌       | 14851/57600 [2:36:13<7:38:02,  1.56it/s]
 26%|██▌       | 14852/57600 [2:36:13<7:26:28,  1.60it/s]
 26%|██▌       | 14853/57600 [2:36:14<7:13:08,  1.64it/s]
 26%|██▌       | 14854/57600 [2:36:14<7:25:32,  1.60it/s]
 26%|██▌       | 14855/57600 [2:36:15<7:15:24,  1.64it/s]
 26%|██▌       | 14856/57600 [2:36:16<7:10:36,  1.65it/s]
 26%|██▌       | 14857/57600 [2:36:16<7:13:15,  1.64it/s]
 26%|██▌       | 14858/57600 [2:36:17<7:22:06,  1.61it/s]
 26%|██▌       | 14859/57600 [2:36:18<7:45:43,  1.53it/s]
 26%|██▌       | 14860/57600 [2:36:18<7:31:27,  1.58it/s]
                                                         
{'loss': 1.2768, 'learning_rate': 7.701393728222996e-07, 'epoch': 164.02}

 26%|██▌       | 14860/57600 [2:36:18<7:31:27,  1.58it/s]
 26%|██▌       | 14861/57600 [2:36:19<7:31:18,  1.58it/s]
 26%|██▌       | 14862/57600 [2:36:19<7:23:27,  1.61it/s]
 26%|██▌       | 14863/57600 [2:36:20<7:25:17,  1.60it/s]
 26%|██▌       | 14864/57600 [2:36:21<7:33:24,  1.57it/s]
 26%|██▌       | 14865/57600 [2:36:21<7:28:55,  1.59it/s]
 26%|██▌       | 14866/57600 [2:36:22<7:34:57,  1.57it/s]
 26%|██▌       | 14867/57600 [2:36:23<7:42:08,  1.54it/s]
 26%|██▌       | 14868/57600 [2:36:23<7:38:20,  1.55it/s]
 26%|██▌       | 14869/57600 [2:36:24<7:25:08,  1.60it/s]
 26%|██▌       | 14870/57600 [2:36:25<7:25:42,  1.60it/s]
 26%|██▌       | 14871/57600 [2:36:25<7:19:11,  1.62it/s]
 26%|██▌       | 14872/57600 [2:36:26<7:21:04,  1.61it/s]
 26%|██▌       | 14873/57600 [2:36:26<7:14:48,  1.64it/s]
 26%|██▌       | 14874/57600 [2:36:27<7:29:54,  1.58it/s]
 26%|██▌       | 14875/57600 [2:36:28<7:42:18,  1.54it/s]
 26%|██▌       | 14876/57600 [2:36:28<7:22:27,  1.61it/s]
 26%|██▌       | 14877/57600 [2:36:29<7:07:52,  1.66it/s]
 26%|██▌       | 14878/57600 [2:36:29<7:12:45,  1.65it/s]
 26%|██▌       | 14879/57600 [2:36:30<7:04:22,  1.68it/s]
 26%|██▌       | 14880/57600 [2:36:31<7:04:01,  1.68it/s]
                                                         
{'loss': 1.2407, 'learning_rate': 7.698257839721255e-07, 'epoch': 164.24}

 26%|██▌       | 14880/57600 [2:36:31<7:04:01,  1.68it/s]
 26%|██▌       | 14881/57600 [2:36:31<7:14:36,  1.64it/s]
 26%|██▌       | 14882/57600 [2:36:32<7:05:00,  1.68it/s]
 26%|██▌       | 14883/57600 [2:36:32<7:10:03,  1.66it/s]
 26%|██▌       | 14884/57600 [2:36:33<7:08:47,  1.66it/s]
 26%|██▌       | 14885/57600 [2:36:34<7:11:39,  1.65it/s]
 26%|██▌       | 14886/57600 [2:36:34<7:32:37,  1.57it/s]
 26%|██▌       | 14887/57600 [2:36:35<7:32:40,  1.57it/s]
 26%|██▌       | 14888/57600 [2:36:36<7:23:15,  1.61it/s]
 26%|██▌       | 14889/57600 [2:36:36<7:10:37,  1.65it/s]
 26%|██▌       | 14890/57600 [2:36:37<7:22:01,  1.61it/s]
 26%|██▌       | 14891/57600 [2:36:37<7:12:57,  1.64it/s]
 26%|██▌       | 14892/57600 [2:36:38<7:11:40,  1.65it/s]
 26%|██▌       | 14893/57600 [2:36:39<7:02:03,  1.69it/s]
 26%|██▌       | 14894/57600 [2:36:39<7:04:39,  1.68it/s]
 26%|██▌       | 14895/57600 [2:36:40<7:03:32,  1.68it/s]
 26%|██▌       | 14896/57600 [2:36:40<7:17:38,  1.63it/s]
 26%|██▌       | 14897/57600 [2:36:41<7:37:25,  1.56it/s]
 26%|██▌       | 14898/57600 [2:36:42<7:29:16,  1.58it/s]
 26%|██▌       | 14899/57600 [2:36:42<7:26:14,  1.59it/s]
 26%|██▌       | 14900/57600 [2:36:43<7:22:54,  1.61it/s]
                                                         
{'loss': 1.2921, 'learning_rate': 7.695121951219512e-07, 'epoch': 164.46}

 26%|██▌       | 14900/57600 [2:36:43<7:22:54,  1.61it/s]
 26%|██▌       | 14901/57600 [2:36:44<7:26:23,  1.59it/s]
 26%|██▌       | 14902/57600 [2:36:44<7:18:17,  1.62it/s]
 26%|██▌       | 14903/57600 [2:36:45<7:09:39,  1.66it/s]
 26%|██▌       | 14904/57600 [2:36:46<7:39:12,  1.55it/s]
 26%|██▌       | 14905/57600 [2:36:46<7:43:16,  1.54it/s]
 26%|██▌       | 14906/57600 [2:36:47<7:32:04,  1.57it/s]
 26%|██▌       | 14907/57600 [2:36:47<7:26:32,  1.59it/s]
 26%|██▌       | 14908/57600 [2:36:48<7:28:55,  1.58it/s]
 26%|██▌       | 14909/57600 [2:36:49<7:20:53,  1.61it/s]
 26%|██▌       | 14910/57600 [2:36:49<7:21:03,  1.61it/s]
 26%|██▌       | 14911/57600 [2:36:50<7:14:18,  1.64it/s]
 26%|██▌       | 14912/57600 [2:36:50<7:19:56,  1.62it/s]
 26%|██▌       | 14913/57600 [2:36:51<7:18:34,  1.62it/s]
 26%|██▌       | 14914/57600 [2:36:52<7:07:11,  1.67it/s]
 26%|██▌       | 14915/57600 [2:36:52<7:13:01,  1.64it/s]
 26%|██▌       | 14916/57600 [2:36:53<7:11:32,  1.65it/s]
 26%|██▌       | 14917/57600 [2:36:53<7:01:04,  1.69it/s]
 26%|██▌       | 14918/57600 [2:36:54<7:07:10,  1.67it/s]
 26%|██▌       | 14919/57600 [2:36:55<7:03:07,  1.68it/s]
 26%|██▌       | 14920/57600 [2:36:55<7:11:09,  1.65it/s]
                                                         
{'loss': 1.3135, 'learning_rate': 7.691986062717769e-07, 'epoch': 164.68}

 26%|██▌       | 14920/57600 [2:36:55<7:11:09,  1.65it/s]
 26%|██▌       | 14921/57600 [2:36:56<7:12:28,  1.64it/s]
 26%|██▌       | 14922/57600 [2:36:56<7:10:51,  1.65it/s]
 26%|██▌       | 14923/57600 [2:36:57<7:27:54,  1.59it/s]
 26%|██▌       | 14924/57600 [2:36:58<7:28:02,  1.59it/s]
 26%|██▌       | 14925/57600 [2:36:58<7:29:59,  1.58it/s]
 26%|██▌       | 14926/57600 [2:36:59<7:28:33,  1.59it/s]
 26%|██▌       | 14927/57600 [2:37:00<7:32:43,  1.57it/s]
 26%|██▌       | 14928/57600 [2:37:00<7:43:57,  1.53it/s]
 26%|██▌       | 14929/57600 [2:37:01<7:47:21,  1.52it/s]
 26%|██▌       | 14930/57600 [2:37:02<7:27:17,  1.59it/s]
 26%|██▌       | 14931/57600 [2:37:02<7:13:08,  1.64it/s]
 26%|██▌       | 14932/57600 [2:37:03<7:11:53,  1.65it/s]
 26%|██▌       | 14933/57600 [2:37:03<7:23:07,  1.60it/s]
 26%|██▌       | 14934/57600 [2:37:04<7:21:14,  1.61it/s]
 26%|██▌       | 14935/57600 [2:37:05<7:40:58,  1.54it/s]
 26%|██▌       | 14936/57600 [2:37:05<7:28:58,  1.58it/s]
 26%|██▌       | 14937/57600 [2:37:06<7:23:37,  1.60it/s]
 26%|██▌       | 14938/57600 [2:37:07<7:10:58,  1.65it/s]
 26%|██▌       | 14939/57600 [2:37:07<7:11:03,  1.65it/s]
 26%|██▌       | 14940/57600 [2:37:08<7:21:08,  1.61it/s]
                                                         
{'loss': 1.2811, 'learning_rate': 7.688850174216027e-07, 'epoch': 164.9}

 26%|██▌       | 14940/57600 [2:37:08<7:21:08,  1.61it/s]
 26%|██▌       | 14941/57600 [2:37:08<7:15:56,  1.63it/s]
 26%|██▌       | 14942/57600 [2:37:09<7:07:42,  1.66it/s]
 26%|██▌       | 14943/57600 [2:37:10<6:59:42,  1.69it/s]
 26%|██▌       | 14944/57600 [2:37:10<7:07:21,  1.66it/s]
 26%|██▌       | 14945/57600 [2:37:11<7:21:40,  1.61it/s]
 26%|██▌       | 14946/57600 [2:37:11<7:18:16,  1.62it/s]
 26%|██▌       | 14947/57600 [2:37:12<7:30:54,  1.58it/s]
 26%|██▌       | 14948/57600 [2:37:13<7:21:15,  1.61it/s]
 26%|██▌       | 14949/57600 [2:37:13<7:25:56,  1.59it/s]
 26%|██▌       | 14950/57600 [2:37:14<7:30:13,  1.58it/s]
 26%|██▌       | 14951/57600 [2:37:15<7:17:38,  1.62it/s]
 26%|██▌       | 14952/57600 [2:37:15<7:19:04,  1.62it/s]
 26%|██▌       | 14953/57600 [2:37:16<7:08:41,  1.66it/s]
 26%|██▌       | 14954/57600 [2:37:16<6:59:29,  1.69it/s]
 26%|██▌       | 14955/57600 [2:37:17<7:04:16,  1.68it/s]
 26%|██▌       | 14956/57600 [2:37:18<7:28:04,  1.59it/s]
 26%|██▌       | 14957/57600 [2:37:18<7:13:23,  1.64it/s]
 26%|██▌       | 14958/57600 [2:37:19<7:12:31,  1.64it/s]
 26%|██▌       | 14959/57600 [2:37:19<7:07:35,  1.66it/s]
 26%|██▌       | 14960/57600 [2:37:20<7:14:43,  1.63it/s]
                                                         
{'loss': 1.2964, 'learning_rate': 7.685714285714287e-07, 'epoch': 165.12}

 26%|██▌       | 14960/57600 [2:37:20<7:14:43,  1.63it/s]
 26%|██▌       | 14961/57600 [2:37:21<7:35:48,  1.56it/s]
 26%|██▌       | 14962/57600 [2:37:21<7:53:18,  1.50it/s]
 26%|██▌       | 14963/57600 [2:37:22<7:44:55,  1.53it/s]
 26%|██▌       | 14964/57600 [2:37:23<7:53:34,  1.50it/s]
 26%|██▌       | 14965/57600 [2:37:23<7:57:48,  1.49it/s]
 26%|██▌       | 14966/57600 [2:37:24<7:41:03,  1.54it/s]
 26%|██▌       | 14967/57600 [2:37:25<7:37:44,  1.55it/s]
 26%|██▌       | 14968/57600 [2:37:25<7:32:03,  1.57it/s]
 26%|██▌       | 14969/57600 [2:37:26<7:35:18,  1.56it/s]
 26%|██▌       | 14970/57600 [2:37:27<7:31:48,  1.57it/s]
 26%|██▌       | 14971/57600 [2:37:27<7:30:14,  1.58it/s]
 26%|██▌       | 14972/57600 [2:37:28<7:28:00,  1.59it/s]
 26%|██▌       | 14973/57600 [2:37:28<7:27:16,  1.59it/s]
 26%|██▌       | 14974/57600 [2:37:29<7:33:06,  1.57it/s]
 26%|██▌       | 14975/57600 [2:37:30<7:32:26,  1.57it/s]
 26%|██▌       | 14976/57600 [2:37:30<7:34:49,  1.56it/s]
 26%|██▌       | 14977/57600 [2:37:31<7:31:16,  1.57it/s]
 26%|██▌       | 14978/57600 [2:37:32<7:44:46,  1.53it/s]
 26%|██▌       | 14979/57600 [2:37:32<7:43:27,  1.53it/s]
 26%|██▌       | 14980/57600 [2:37:33<7:25:38,  1.59it/s]
                                                         
{'loss': 1.2674, 'learning_rate': 7.682578397212542e-07, 'epoch': 165.34}

 26%|██▌       | 14980/57600 [2:37:33<7:25:38,  1.59it/s]
 26%|██▌       | 14981/57600 [2:37:34<7:18:11,  1.62it/s]
 26%|██▌       | 14982/57600 [2:37:34<7:21:13,  1.61it/s]
 26%|██▌       | 14983/57600 [2:37:35<7:27:17,  1.59it/s]
 26%|██▌       | 14984/57600 [2:37:36<7:47:48,  1.52it/s]
 26%|██▌       | 14985/57600 [2:37:36<7:30:26,  1.58it/s]
 26%|██▌       | 14986/57600 [2:37:37<7:22:15,  1.61it/s]
 26%|██▌       | 14987/57600 [2:37:37<7:21:44,  1.61it/s]
 26%|██▌       | 14988/57600 [2:37:38<7:39:45,  1.54it/s]
 26%|██▌       | 14989/57600 [2:37:39<7:45:12,  1.53it/s]
 26%|██▌       | 14990/57600 [2:37:39<7:23:46,  1.60it/s]
 26%|██▌       | 14991/57600 [2:37:40<7:20:42,  1.61it/s]
 26%|██▌       | 14992/57600 [2:37:40<7:17:32,  1.62it/s]
 26%|██▌       | 14993/57600 [2:37:41<7:16:29,  1.63it/s]
 26%|██▌       | 14994/57600 [2:37:42<7:28:52,  1.58it/s]
 26%|██▌       | 14995/57600 [2:37:42<7:20:23,  1.61it/s]
 26%|██▌       | 14996/57600 [2:37:43<7:19:07,  1.62it/s]
 26%|██▌       | 14997/57600 [2:37:44<7:40:33,  1.54it/s]
 26%|██▌       | 14998/57600 [2:37:44<7:25:43,  1.59it/s]
 26%|██▌       | 14999/57600 [2:37:45<7:19:33,  1.62it/s]
 26%|██▌       | 15000/57600 [2:37:45<7:18:47,  1.62it/s]
                                                         
{'loss': 1.3111, 'learning_rate': 7.679442508710801e-07, 'epoch': 165.56}

 26%|██▌       | 15000/57600 [2:37:45<7:18:47,  1.62it/s]
 26%|██▌       | 15001/57600 [2:37:46<7:32:34,  1.57it/s]
 26%|██▌       | 15002/57600 [2:37:47<7:22:34,  1.60it/s]
 26%|██▌       | 15003/57600 [2:37:47<7:18:15,  1.62it/s]
 26%|██▌       | 15004/57600 [2:37:48<7:13:53,  1.64it/s]
 26%|██▌       | 15005/57600 [2:37:49<7:24:24,  1.60it/s]
 26%|██▌       | 15006/57600 [2:37:49<7:21:51,  1.61it/s]
 26%|██▌       | 15007/57600 [2:37:50<7:28:09,  1.58it/s]
 26%|██▌       | 15008/57600 [2:37:51<7:24:59,  1.60it/s]
 26%|██▌       | 15009/57600 [2:37:51<7:32:29,  1.57it/s]
 26%|██▌       | 15010/57600 [2:37:52<7:31:10,  1.57it/s]
 26%|██▌       | 15011/57600 [2:37:52<7:28:14,  1.58it/s]
 26%|██▌       | 15012/57600 [2:37:53<7:26:31,  1.59it/s]
 26%|██▌       | 15013/57600 [2:37:54<7:25:43,  1.59it/s]
 26%|██▌       | 15014/57600 [2:37:54<7:25:14,  1.59it/s]
 26%|██▌       | 15015/57600 [2:37:55<7:11:21,  1.65it/s]
 26%|██▌       | 15016/57600 [2:37:55<7:14:52,  1.63it/s]
 26%|██▌       | 15017/57600 [2:37:56<7:18:03,  1.62it/s]
 26%|██▌       | 15018/57600 [2:37:57<7:23:28,  1.60it/s]
 26%|██▌       | 15019/57600 [2:37:57<7:21:53,  1.61it/s]
 26%|██▌       | 15020/57600 [2:37:58<7:12:56,  1.64it/s]
                                                         
{'loss': 1.2993, 'learning_rate': 7.67630662020906e-07, 'epoch': 165.78}

 26%|██▌       | 15020/57600 [2:37:58<7:12:56,  1.64it/s]
 26%|██▌       | 15021/57600 [2:37:59<7:16:25,  1.63it/s]
 26%|██▌       | 15022/57600 [2:37:59<7:08:14,  1.66it/s]
 26%|██▌       | 15023/57600 [2:38:00<7:23:01,  1.60it/s]
 26%|██▌       | 15024/57600 [2:38:00<7:23:23,  1.60it/s]
 26%|██▌       | 15025/57600 [2:38:01<7:22:11,  1.60it/s]
 26%|██▌       | 15026/57600 [2:38:02<7:24:45,  1.60it/s]
 26%|██▌       | 15027/57600 [2:38:02<7:32:35,  1.57it/s]
 26%|██▌       | 15028/57600 [2:38:03<7:32:02,  1.57it/s]
 26%|██▌       | 15029/57600 [2:38:04<7:38:53,  1.55it/s]
 26%|██▌       | 15030/57600 [2:38:04<7:23:14,  1.60it/s]
 26%|██▌       | 15031/57600 [2:38:05<7:27:21,  1.59it/s]
 26%|██▌       | 15032/57600 [2:38:06<7:37:35,  1.55it/s]
 26%|██▌       | 15033/57600 [2:38:06<7:35:09,  1.56it/s]
 26%|██▌       | 15034/57600 [2:38:07<7:32:29,  1.57it/s]
 26%|██▌       | 15035/57600 [2:38:07<7:31:57,  1.57it/s]
 26%|██▌       | 15036/57600 [2:38:08<7:24:14,  1.60it/s]
 26%|██▌       | 15037/57600 [2:38:09<7:23:13,  1.60it/s]
 26%|██▌       | 15038/57600 [2:38:09<7:19:48,  1.61it/s]
 26%|██▌       | 15039/57600 [2:38:10<7:08:57,  1.65it/s]
 26%|██▌       | 15040/57600 [2:38:11<7:40:04,  1.54it/s]
                                                         
{'loss': 1.268, 'learning_rate': 7.673170731707317e-07, 'epoch': 166.0}

 26%|██▌       | 15040/57600 [2:38:11<7:40:04,  1.54it/s]
 26%|██▌       | 15041/57600 [2:38:11<7:41:44,  1.54it/s]
 26%|██▌       | 15042/57600 [2:38:12<7:49:41,  1.51it/s]
 26%|██▌       | 15043/57600 [2:38:13<7:35:52,  1.56it/s]
 26%|██▌       | 15044/57600 [2:38:13<7:34:26,  1.56it/s]
 26%|██▌       | 15045/57600 [2:38:14<7:33:07,  1.57it/s]
 26%|██▌       | 15046/57600 [2:38:14<7:37:14,  1.55it/s]
 26%|██▌       | 15047/57600 [2:38:15<7:39:56,  1.54it/s]
 26%|██▌       | 15048/57600 [2:38:16<7:45:38,  1.52it/s]
 26%|██▌       | 15049/57600 [2:38:16<7:24:27,  1.60it/s]
 26%|██▌       | 15050/57600 [2:38:17<7:21:07,  1.61it/s]
 26%|██▌       | 15051/57600 [2:38:18<7:06:53,  1.66it/s]
 26%|██▌       | 15052/57600 [2:38:18<7:23:08,  1.60it/s]
 26%|██▌       | 15053/57600 [2:38:19<7:31:43,  1.57it/s]
 26%|██▌       | 15054/57600 [2:38:19<7:12:13,  1.64it/s]
 26%|██▌       | 15055/57600 [2:38:20<7:16:25,  1.62it/s]
 26%|██▌       | 15056/57600 [2:38:21<7:20:56,  1.61it/s]
 26%|██▌       | 15057/57600 [2:38:21<7:20:35,  1.61it/s]
 26%|██▌       | 15058/57600 [2:38:22<7:12:43,  1.64it/s]
 26%|██▌       | 15059/57600 [2:38:23<7:22:06,  1.60it/s]
 26%|██▌       | 15060/57600 [2:38:23<7:18:14,  1.62it/s]
                                                         
{'loss': 1.3067, 'learning_rate': 7.670034843205574e-07, 'epoch': 166.23}

 26%|██▌       | 15060/57600 [2:38:23<7:18:14,  1.62it/s]
 26%|██▌       | 15061/57600 [2:38:24<7:31:34,  1.57it/s]
 26%|██▌       | 15062/57600 [2:38:24<7:30:05,  1.58it/s]
 26%|██▌       | 15063/57600 [2:38:25<7:35:05,  1.56it/s]
 26%|██▌       | 15064/57600 [2:38:26<7:24:48,  1.59it/s]
 26%|██▌       | 15065/57600 [2:38:26<7:19:37,  1.61it/s]
 26%|██▌       | 15066/57600 [2:38:27<7:31:09,  1.57it/s]
 26%|██▌       | 15067/57600 [2:38:28<7:32:56,  1.57it/s]
 26%|██▌       | 15068/57600 [2:38:28<7:27:56,  1.58it/s]
 26%|██▌       | 15069/57600 [2:38:29<7:18:02,  1.62it/s]
 26%|██▌       | 15070/57600 [2:38:29<7:14:02,  1.63it/s]
 26%|██▌       | 15071/57600 [2:38:30<7:20:04,  1.61it/s]
 26%|██▌       | 15072/57600 [2:38:31<7:15:41,  1.63it/s]
 26%|██▌       | 15073/57600 [2:38:31<7:21:17,  1.61it/s]
 26%|██▌       | 15074/57600 [2:38:32<7:10:14,  1.65it/s]
 26%|██▌       | 15075/57600 [2:38:32<7:05:36,  1.67it/s]
 26%|██▌       | 15076/57600 [2:38:33<7:03:42,  1.67it/s]
 26%|██▌       | 15077/57600 [2:38:34<7:02:09,  1.68it/s]
 26%|██▌       | 15078/57600 [2:38:34<6:56:00,  1.70it/s]
 26%|██▌       | 15079/57600 [2:38:35<7:04:14,  1.67it/s]
 26%|██▌       | 15080/57600 [2:38:35<7:02:38,  1.68it/s]
                                                         
{'loss': 1.3156, 'learning_rate': 7.666898954703832e-07, 'epoch': 166.45}

 26%|██▌       | 15080/57600 [2:38:35<7:02:38,  1.68it/s]
 26%|██▌       | 15081/57600 [2:38:36<7:05:50,  1.66it/s]
 26%|██▌       | 15082/57600 [2:38:37<7:08:41,  1.65it/s]
 26%|██▌       | 15083/57600 [2:38:37<7:28:44,  1.58it/s]
 26%|██▌       | 15084/57600 [2:38:38<7:23:12,  1.60it/s]
 26%|██▌       | 15085/57600 [2:38:39<7:20:15,  1.61it/s]
 26%|██▌       | 15086/57600 [2:38:39<7:18:39,  1.62it/s]
 26%|██▌       | 15087/57600 [2:38:40<7:11:20,  1.64it/s]
 26%|██▌       | 15088/57600 [2:38:40<7:14:26,  1.63it/s]
 26%|██▌       | 15089/57600 [2:38:41<7:17:12,  1.62it/s]
 26%|██▌       | 15090/57600 [2:38:42<7:09:38,  1.65it/s]
 26%|██▌       | 15091/57600 [2:38:42<7:09:32,  1.65it/s]
 26%|██▌       | 15092/57600 [2:38:43<7:10:05,  1.65it/s]
 26%|██▌       | 15093/57600 [2:38:44<7:23:19,  1.60it/s]
 26%|██▌       | 15094/57600 [2:38:44<7:23:10,  1.60it/s]
 26%|██▌       | 15095/57600 [2:38:45<7:24:15,  1.59it/s]
 26%|██▌       | 15096/57600 [2:38:45<7:19:11,  1.61it/s]
 26%|██▌       | 15097/57600 [2:38:46<7:18:38,  1.61it/s]
 26%|██▌       | 15098/57600 [2:38:47<7:21:00,  1.61it/s]
 26%|██▌       | 15099/57600 [2:38:47<7:36:56,  1.55it/s]
 26%|██▌       | 15100/57600 [2:38:48<7:34:48,  1.56it/s]
                                                         
{'loss': 1.3127, 'learning_rate': 7.663763066202091e-07, 'epoch': 166.67}

 26%|██▌       | 15100/57600 [2:38:48<7:34:48,  1.56it/s]
 26%|██▌       | 15101/57600 [2:38:49<7:35:16,  1.56it/s]
 26%|██▌       | 15102/57600 [2:38:49<7:27:35,  1.58it/s]
 26%|██▌       | 15103/57600 [2:38:50<7:29:59,  1.57it/s]
 26%|██▌       | 15104/57600 [2:38:50<7:31:30,  1.57it/s]
 26%|██▌       | 15105/57600 [2:38:51<7:26:35,  1.59it/s]
 26%|██▌       | 15106/57600 [2:38:52<7:31:06,  1.57it/s]
 26%|██▌       | 15107/57600 [2:38:52<7:32:46,  1.56it/s]
 26%|██▌       | 15108/57600 [2:38:53<7:26:38,  1.59it/s]
 26%|██▌       | 15109/57600 [2:38:54<7:31:59,  1.57it/s]
 26%|██▌       | 15110/57600 [2:38:54<7:37:44,  1.55it/s]
 26%|██▌       | 15111/57600 [2:38:55<7:34:48,  1.56it/s]
 26%|██▌       | 15112/57600 [2:38:56<7:45:20,  1.52it/s]
 26%|██▌       | 15113/57600 [2:38:56<8:01:13,  1.47it/s]
 26%|██▌       | 15114/57600 [2:38:57<7:50:24,  1.51it/s]
 26%|██▌       | 15115/57600 [2:38:58<7:36:29,  1.55it/s]
 26%|██▌       | 15116/57600 [2:38:58<7:26:05,  1.59it/s]
 26%|██▌       | 15117/57600 [2:38:59<7:20:28,  1.61it/s]
 26%|██▌       | 15118/57600 [2:38:59<7:25:39,  1.59it/s]
 26%|██▌       | 15119/57600 [2:39:00<7:17:58,  1.62it/s]
 26%|██▋       | 15120/57600 [2:39:01<7:16:33,  1.62it/s]
                                                         
{'loss': 1.2802, 'learning_rate': 7.660627177700348e-07, 'epoch': 166.89}

 26%|██▋       | 15120/57600 [2:39:01<7:16:33,  1.62it/s]
 26%|██▋       | 15121/57600 [2:39:01<7:28:14,  1.58it/s]
 26%|██▋       | 15122/57600 [2:39:02<7:31:01,  1.57it/s]
 26%|██▋       | 15123/57600 [2:39:03<7:19:56,  1.61it/s]
 26%|██▋       | 15124/57600 [2:39:03<7:22:54,  1.60it/s]
 26%|██▋       | 15125/57600 [2:39:04<7:11:07,  1.64it/s]
 26%|██▋       | 15126/57600 [2:39:04<7:18:27,  1.61it/s]
 26%|██▋       | 15127/57600 [2:39:05<7:41:40,  1.53it/s]
 26%|██▋       | 15128/57600 [2:39:06<7:45:09,  1.52it/s]
 26%|██▋       | 15129/57600 [2:39:06<7:40:26,  1.54it/s]
 26%|██▋       | 15130/57600 [2:39:07<7:29:23,  1.58it/s]
 26%|██▋       | 15131/57600 [2:39:08<7:48:43,  1.51it/s]
 26%|██▋       | 15132/57600 [2:39:08<7:43:09,  1.53it/s]
 26%|██▋       | 15133/57600 [2:39:09<7:47:45,  1.51it/s]
 26%|██▋       | 15134/57600 [2:39:10<7:40:01,  1.54it/s]
 26%|██▋       | 15135/57600 [2:39:10<7:21:31,  1.60it/s]
 26%|██▋       | 15136/57600 [2:39:11<7:26:16,  1.59it/s]
 26%|██▋       | 15137/57600 [2:39:12<9:05:52,  1.30it/s]
 26%|██▋       | 15138/57600 [2:39:13<8:29:56,  1.39it/s]
 26%|██▋       | 15139/57600 [2:39:13<8:09:39,  1.45it/s]
 26%|██▋       | 15140/57600 [2:39:14<7:49:52,  1.51it/s]
                                                         
{'loss': 1.252, 'learning_rate': 7.657491289198606e-07, 'epoch': 167.11}

 26%|██▋       | 15140/57600 [2:39:14<7:49:52,  1.51it/s]
 26%|██▋       | 15141/57600 [2:39:14<7:40:37,  1.54it/s]
 26%|██▋       | 15142/57600 [2:39:15<7:36:52,  1.55it/s]
 26%|██▋       | 15143/57600 [2:39:16<7:39:33,  1.54it/s]
 26%|██▋       | 15144/57600 [2:39:16<7:22:49,  1.60it/s]
 26%|██▋       | 15145/57600 [2:39:17<7:24:41,  1.59it/s]
 26%|██▋       | 15146/57600 [2:39:18<7:35:39,  1.55it/s]
 26%|██▋       | 15147/57600 [2:39:18<7:13:32,  1.63it/s]
 26%|██▋       | 15148/57600 [2:39:19<7:13:45,  1.63it/s]
 26%|██▋       | 15149/57600 [2:39:19<6:58:01,  1.69it/s]
 26%|██▋       | 15150/57600 [2:39:20<7:07:13,  1.66it/s]
 26%|██▋       | 15151/57600 [2:39:21<7:08:30,  1.65it/s]
 26%|██▋       | 15152/57600 [2:39:21<7:00:44,  1.68it/s]
 26%|██▋       | 15153/57600 [2:39:22<7:03:01,  1.67it/s]
 26%|██▋       | 15154/57600 [2:39:22<7:22:31,  1.60it/s]
 26%|██▋       | 15155/57600 [2:39:23<7:36:33,  1.55it/s]
 26%|██▋       | 15156/57600 [2:39:24<7:33:22,  1.56it/s]
 26%|██▋       | 15157/57600 [2:39:24<7:41:03,  1.53it/s]
 26%|██▋       | 15158/57600 [2:39:25<7:35:24,  1.55it/s]
 26%|██▋       | 15159/57600 [2:39:26<7:43:03,  1.53it/s]
 26%|██▋       | 15160/57600 [2:39:26<7:40:11,  1.54it/s]
                                                         
{'loss': 1.3094, 'learning_rate': 7.654355400696864e-07, 'epoch': 167.33}

 26%|██▋       | 15160/57600 [2:39:26<7:40:11,  1.54it/s]
 26%|██▋       | 15161/57600 [2:39:27<7:22:12,  1.60it/s]
 26%|██▋       | 15162/57600 [2:39:28<7:17:33,  1.62it/s]
 26%|██▋       | 15163/57600 [2:39:28<7:23:46,  1.59it/s]
 26%|██▋       | 15164/57600 [2:39:29<7:19:18,  1.61it/s]
 26%|██▋       | 15165/57600 [2:39:29<7:23:49,  1.59it/s]
 26%|██▋       | 15166/57600 [2:39:30<7:21:31,  1.60it/s]
 26%|██▋       | 15167/57600 [2:39:31<7:22:23,  1.60it/s]
 26%|██▋       | 15168/57600 [2:39:31<7:07:11,  1.66it/s]
 26%|██▋       | 15169/57600 [2:39:32<6:59:36,  1.69it/s]
 26%|██▋       | 15170/57600 [2:39:32<7:10:35,  1.64it/s]
 26%|██▋       | 15171/57600 [2:39:33<7:10:33,  1.64it/s]
 26%|██▋       | 15172/57600 [2:39:34<7:06:19,  1.66it/s]
 26%|██▋       | 15173/57600 [2:39:34<7:09:56,  1.64it/s]
 26%|██▋       | 15174/57600 [2:39:35<7:23:37,  1.59it/s]
 26%|██▋       | 15175/57600 [2:39:36<7:11:28,  1.64it/s]
 26%|██▋       | 15176/57600 [2:39:36<7:16:55,  1.62it/s]
 26%|██▋       | 15177/57600 [2:39:37<7:23:04,  1.60it/s]
 26%|██▋       | 15178/57600 [2:39:37<7:23:06,  1.60it/s]
 26%|██▋       | 15179/57600 [2:39:38<7:31:30,  1.57it/s]
 26%|██▋       | 15180/57600 [2:39:39<7:27:53,  1.58it/s]
                                                         
{'loss': 1.2655, 'learning_rate': 7.651219512195122e-07, 'epoch': 167.55}

 26%|██▋       | 15180/57600 [2:39:39<7:27:53,  1.58it/s]
 26%|██▋       | 15181/57600 [2:39:39<7:25:01,  1.59it/s]
 26%|██▋       | 15182/57600 [2:39:40<7:34:33,  1.56it/s]
 26%|██▋       | 15183/57600 [2:39:41<7:12:35,  1.63it/s]
 26%|██▋       | 15184/57600 [2:39:41<7:08:22,  1.65it/s]
 26%|██▋       | 15185/57600 [2:39:42<6:56:07,  1.70it/s]
 26%|██▋       | 15186/57600 [2:39:42<6:49:10,  1.73it/s]
 26%|██▋       | 15187/57600 [2:39:43<7:14:53,  1.63it/s]
 26%|██▋       | 15188/57600 [2:39:44<7:37:31,  1.55it/s]
 26%|██▋       | 15189/57600 [2:39:44<7:25:46,  1.59it/s]
 26%|██▋       | 15190/57600 [2:39:45<7:09:42,  1.64it/s]
 26%|██▋       | 15191/57600 [2:39:45<7:04:37,  1.66it/s]
 26%|██▋       | 15192/57600 [2:39:46<7:13:00,  1.63it/s]
 26%|██▋       | 15193/57600 [2:39:47<7:16:49,  1.62it/s]
 26%|██▋       | 15194/57600 [2:39:47<7:16:16,  1.62it/s]
 26%|██▋       | 15195/57600 [2:39:48<7:18:02,  1.61it/s]
 26%|██▋       | 15196/57600 [2:39:49<7:19:43,  1.61it/s]
 26%|██▋       | 15197/57600 [2:39:49<7:05:48,  1.66it/s]
 26%|██▋       | 15198/57600 [2:39:50<7:00:57,  1.68it/s]
 26%|██▋       | 15199/57600 [2:39:50<7:00:53,  1.68it/s]
 26%|██▋       | 15200/57600 [2:39:51<7:12:40,  1.63it/s]
                                                         
{'loss': 1.315, 'learning_rate': 7.648083623693378e-07, 'epoch': 167.77}

 26%|██▋       | 15200/57600 [2:39:51<7:12:40,  1.63it/s]
 26%|██▋       | 15201/57600 [2:39:52<7:19:26,  1.61it/s]
 26%|██▋       | 15202/57600 [2:39:52<7:15:37,  1.62it/s]
 26%|██▋       | 15203/57600 [2:39:53<7:14:56,  1.62it/s]
 26%|██▋       | 15204/57600 [2:39:53<7:10:43,  1.64it/s]
 26%|██▋       | 15205/57600 [2:39:54<7:15:12,  1.62it/s]
 26%|██▋       | 15206/57600 [2:39:55<7:18:29,  1.61it/s]
 26%|██▋       | 15207/57600 [2:39:55<7:25:53,  1.58it/s]
 26%|██▋       | 15208/57600 [2:39:56<7:40:22,  1.53it/s]
 26%|██▋       | 15209/57600 [2:39:57<7:32:29,  1.56it/s]
 26%|██▋       | 15210/57600 [2:39:57<7:21:26,  1.60it/s]
 26%|██▋       | 15211/57600 [2:39:58<7:36:51,  1.55it/s]
 26%|██▋       | 15212/57600 [2:39:59<7:30:50,  1.57it/s]
 26%|██▋       | 15213/57600 [2:39:59<7:20:28,  1.60it/s]
 26%|██▋       | 15214/57600 [2:40:00<7:15:38,  1.62it/s]
 26%|██▋       | 15215/57600 [2:40:00<7:12:56,  1.63it/s]
 26%|██▋       | 15216/57600 [2:40:01<7:11:50,  1.64it/s]
 26%|██▋       | 15217/57600 [2:40:02<7:21:54,  1.60it/s]
 26%|██▋       | 15218/57600 [2:40:02<7:28:21,  1.58it/s]
 26%|██▋       | 15219/57600 [2:40:03<7:28:39,  1.57it/s]
 26%|██▋       | 15220/57600 [2:40:03<7:15:56,  1.62it/s]
                                                         
{'loss': 1.2746, 'learning_rate': 7.644947735191637e-07, 'epoch': 167.99}

 26%|██▋       | 15220/57600 [2:40:03<7:15:56,  1.62it/s]
 26%|██▋       | 15221/57600 [2:40:04<7:23:49,  1.59it/s]
 26%|██▋       | 15222/57600 [2:40:05<7:28:15,  1.58it/s]
 26%|██▋       | 15223/57600 [2:40:05<7:22:28,  1.60it/s]
 26%|██▋       | 15224/57600 [2:40:06<7:36:36,  1.55it/s]
 26%|██▋       | 15225/57600 [2:40:07<7:33:25,  1.56it/s]
 26%|██▋       | 15226/57600 [2:40:07<7:22:53,  1.59it/s]
 26%|██▋       | 15227/57600 [2:40:08<7:19:40,  1.61it/s]
 26%|██▋       | 15228/57600 [2:40:09<7:14:40,  1.62it/s]
 26%|██▋       | 15229/57600 [2:40:09<7:02:44,  1.67it/s]
 26%|██▋       | 15230/57600 [2:40:10<6:54:19,  1.70it/s]
 26%|██▋       | 15231/57600 [2:40:10<6:53:27,  1.71it/s]
 26%|██▋       | 15232/57600 [2:40:11<6:50:03,  1.72it/s]
 26%|██▋       | 15233/57600 [2:40:11<7:04:10,  1.66it/s]
 26%|██▋       | 15234/57600 [2:40:12<7:07:20,  1.65it/s]
 26%|██▋       | 15235/57600 [2:40:13<6:59:43,  1.68it/s]
 26%|██▋       | 15236/57600 [2:40:13<7:10:49,  1.64it/s]
 26%|██▋       | 15237/57600 [2:40:14<7:02:37,  1.67it/s]
 26%|██▋       | 15238/57600 [2:40:14<6:57:26,  1.69it/s]
 26%|██▋       | 15239/57600 [2:40:15<7:13:29,  1.63it/s]
 26%|██▋       | 15240/57600 [2:40:16<7:26:33,  1.58it/s]
                                                         
{'loss': 1.279, 'learning_rate': 7.641811846689895e-07, 'epoch': 168.21}

 26%|██▋       | 15240/57600 [2:40:16<7:26:33,  1.58it/s]
 26%|██▋       | 15241/57600 [2:40:16<7:30:39,  1.57it/s]
 26%|██▋       | 15242/57600 [2:40:17<7:44:27,  1.52it/s]
 26%|██▋       | 15243/57600 [2:40:18<7:40:11,  1.53it/s]
 26%|██▋       | 15244/57600 [2:40:18<7:30:10,  1.57it/s]
 26%|██▋       | 15245/57600 [2:40:19<7:31:07,  1.56it/s]
 26%|██▋       | 15246/57600 [2:40:20<7:34:31,  1.55it/s]
 26%|██▋       | 15247/57600 [2:40:20<7:32:33,  1.56it/s]
 26%|██▋       | 15248/57600 [2:40:21<7:28:52,  1.57it/s]
 26%|██▋       | 15249/57600 [2:40:22<7:21:38,  1.60it/s]
 26%|██▋       | 15250/57600 [2:40:22<7:07:02,  1.65it/s]
 26%|██▋       | 15251/57600 [2:40:23<6:55:57,  1.70it/s]
 26%|██▋       | 15252/57600 [2:40:23<7:07:23,  1.65it/s]
 26%|██▋       | 15253/57600 [2:40:24<7:10:12,  1.64it/s]
 26%|██▋       | 15254/57600 [2:40:25<7:16:39,  1.62it/s]
 26%|██▋       | 15255/57600 [2:40:25<7:13:33,  1.63it/s]
 26%|██▋       | 15256/57600 [2:40:26<7:19:33,  1.61it/s]
 26%|██▋       | 15257/57600 [2:40:26<7:14:57,  1.62it/s]
 26%|██▋       | 15258/57600 [2:40:27<7:09:10,  1.64it/s]
 26%|██▋       | 15259/57600 [2:40:28<7:13:19,  1.63it/s]
 26%|██▋       | 15260/57600 [2:40:28<7:23:20,  1.59it/s]
                                                         
{'loss': 1.288, 'learning_rate': 7.638675958188153e-07, 'epoch': 168.43}

 26%|██▋       | 15260/57600 [2:40:28<7:23:20,  1.59it/s]
 26%|██▋       | 15261/57600 [2:40:29<7:15:49,  1.62it/s]
 26%|██▋       | 15262/57600 [2:40:29<7:15:46,  1.62it/s]
 26%|██▋       | 15263/57600 [2:40:30<7:08:44,  1.65it/s]
 26%|██▋       | 15264/57600 [2:40:31<7:07:47,  1.65it/s]
 27%|██▋       | 15265/57600 [2:40:31<7:01:08,  1.68it/s]
 27%|██▋       | 15266/57600 [2:40:32<7:15:55,  1.62it/s]
 27%|██▋       | 15267/57600 [2:40:32<7:16:12,  1.62it/s]
 27%|██▋       | 15268/57600 [2:40:33<7:52:39,  1.49it/s]
 27%|██▋       | 15269/57600 [2:40:34<7:40:24,  1.53it/s]
 27%|██▋       | 15270/57600 [2:40:35<7:29:35,  1.57it/s]
 27%|██▋       | 15271/57600 [2:40:35<7:27:44,  1.58it/s]
 27%|██▋       | 15272/57600 [2:40:36<7:23:46,  1.59it/s]
 27%|██▋       | 15273/57600 [2:40:36<7:19:13,  1.61it/s]
 27%|██▋       | 15274/57600 [2:40:37<7:37:29,  1.54it/s]
 27%|██▋       | 15275/57600 [2:40:38<7:28:59,  1.57it/s]
 27%|██▋       | 15276/57600 [2:40:38<7:13:10,  1.63it/s]
 27%|██▋       | 15277/57600 [2:40:39<7:05:13,  1.66it/s]
 27%|██▋       | 15278/57600 [2:40:39<6:59:43,  1.68it/s]
 27%|██▋       | 15279/57600 [2:40:40<7:06:05,  1.66it/s]
 27%|██▋       | 15280/57600 [2:40:41<7:00:02,  1.68it/s]
                                                         
{'loss': 1.3345, 'learning_rate': 7.63554006968641e-07, 'epoch': 168.65}

 27%|██▋       | 15280/57600 [2:40:41<7:00:02,  1.68it/s]
 27%|██▋       | 15281/57600 [2:40:41<6:59:17,  1.68it/s]
 27%|██▋       | 15282/57600 [2:40:42<6:53:12,  1.71it/s]
 27%|██▋       | 15283/57600 [2:40:42<6:59:51,  1.68it/s]
 27%|██▋       | 15284/57600 [2:40:43<6:59:03,  1.68it/s]
 27%|██▋       | 15285/57600 [2:40:44<6:57:18,  1.69it/s]
 27%|██▋       | 15286/57600 [2:40:44<7:09:33,  1.64it/s]
 27%|██▋       | 15287/57600 [2:40:45<7:01:37,  1.67it/s]
 27%|██▋       | 15288/57600 [2:40:45<7:05:54,  1.66it/s]
 27%|██▋       | 15289/57600 [2:40:46<7:14:32,  1.62it/s]
 27%|██▋       | 15290/57600 [2:40:47<7:04:19,  1.66it/s]
 27%|██▋       | 15291/57600 [2:40:47<6:57:19,  1.69it/s]
 27%|██▋       | 15292/57600 [2:40:48<7:07:04,  1.65it/s]
 27%|██▋       | 15293/57600 [2:40:49<7:28:06,  1.57it/s]
 27%|██▋       | 15294/57600 [2:40:49<7:23:05,  1.59it/s]
 27%|██▋       | 15295/57600 [2:40:50<7:35:00,  1.55it/s]
 27%|██▋       | 15296/57600 [2:40:50<7:35:11,  1.55it/s]
 27%|██▋       | 15297/57600 [2:40:51<7:38:03,  1.54it/s]
 27%|██▋       | 15298/57600 [2:40:52<7:28:53,  1.57it/s]
 27%|██▋       | 15299/57600 [2:40:52<7:19:46,  1.60it/s]
 27%|██▋       | 15300/57600 [2:40:53<7:32:15,  1.56it/s]
                                                         
{'loss': 1.2753, 'learning_rate': 7.632404181184669e-07, 'epoch': 168.87}

 27%|██▋       | 15300/57600 [2:40:53<7:32:15,  1.56it/s]
 27%|██▋       | 15301/57600 [2:40:54<7:15:29,  1.62it/s]
 27%|██▋       | 15302/57600 [2:40:54<7:09:10,  1.64it/s]
 27%|██▋       | 15303/57600 [2:40:55<7:13:05,  1.63it/s]
 27%|██▋       | 15304/57600 [2:40:55<7:11:27,  1.63it/s]
 27%|██▋       | 15305/57600 [2:40:56<7:16:52,  1.61it/s]
 27%|██▋       | 15306/57600 [2:40:57<7:13:52,  1.62it/s]
 27%|██▋       | 15307/57600 [2:40:57<7:13:33,  1.63it/s]
 27%|██▋       | 15308/57600 [2:40:58<7:11:56,  1.63it/s]
 27%|██▋       | 15309/57600 [2:40:59<7:23:04,  1.59it/s]
 27%|██▋       | 15310/57600 [2:40:59<7:12:45,  1.63it/s]
 27%|██▋       | 15311/57600 [2:41:00<7:26:21,  1.58it/s]
 27%|██▋       | 15312/57600 [2:41:01<7:56:57,  1.48it/s]
 27%|██▋       | 15313/57600 [2:41:01<7:46:32,  1.51it/s]
 27%|██▋       | 15314/57600 [2:41:02<7:42:07,  1.53it/s]
 27%|██▋       | 15315/57600 [2:41:02<7:27:58,  1.57it/s]
 27%|██▋       | 15316/57600 [2:41:03<7:27:19,  1.58it/s]
 27%|██▋       | 15317/57600 [2:41:04<7:19:19,  1.60it/s]
 27%|██▋       | 15318/57600 [2:41:04<7:15:11,  1.62it/s]
 27%|██▋       | 15319/57600 [2:41:05<7:05:35,  1.66it/s]
 27%|██▋       | 15320/57600 [2:41:05<7:15:34,  1.62it/s]
                                                         
{'loss': 1.3172, 'learning_rate': 7.629268292682927e-07, 'epoch': 169.09}

 27%|██▋       | 15320/57600 [2:41:05<7:15:34,  1.62it/s]
 27%|██▋       | 15321/57600 [2:41:06<7:19:15,  1.60it/s]
 27%|██▋       | 15322/57600 [2:41:07<7:23:13,  1.59it/s]
 27%|██▋       | 15323/57600 [2:41:07<7:24:11,  1.59it/s]
 27%|██▋       | 15324/57600 [2:41:08<7:08:11,  1.65it/s]
 27%|██▋       | 15325/57600 [2:41:09<7:21:51,  1.59it/s]
 27%|██▋       | 15326/57600 [2:41:09<7:09:37,  1.64it/s]
 27%|██▋       | 15327/57600 [2:41:10<7:15:13,  1.62it/s]
 27%|██▋       | 15328/57600 [2:41:10<7:07:46,  1.65it/s]
 27%|██▋       | 15329/57600 [2:41:11<7:20:45,  1.60it/s]
 27%|██▋       | 15330/57600 [2:41:12<7:09:37,  1.64it/s]
 27%|██▋       | 15331/57600 [2:41:12<6:59:52,  1.68it/s]
 27%|██▋       | 15332/57600 [2:41:13<6:56:29,  1.69it/s]
 27%|██▋       | 15333/57600 [2:41:13<7:17:53,  1.61it/s]
 27%|██▋       | 15334/57600 [2:41:14<7:13:48,  1.62it/s]
 27%|██▋       | 15335/57600 [2:41:15<7:36:15,  1.54it/s]
 27%|██▋       | 15336/57600 [2:41:15<7:48:38,  1.50it/s]
 27%|██▋       | 15337/57600 [2:41:16<7:46:02,  1.51it/s]
 27%|██▋       | 15338/57600 [2:41:17<7:26:56,  1.58it/s]
 27%|██▋       | 15339/57600 [2:41:17<7:22:21,  1.59it/s]
 27%|██▋       | 15340/57600 [2:41:18<7:23:29,  1.59it/s]
                                                         
{'loss': 1.26, 'learning_rate': 7.626132404181184e-07, 'epoch': 169.32}

 27%|██▋       | 15340/57600 [2:41:18<7:23:29,  1.59it/s]
 27%|██▋       | 15341/57600 [2:41:19<7:28:31,  1.57it/s]
 27%|██▋       | 15342/57600 [2:41:19<7:15:45,  1.62it/s]
 27%|██▋       | 15343/57600 [2:41:20<7:22:13,  1.59it/s]
 27%|██▋       | 15344/57600 [2:41:20<7:26:42,  1.58it/s]
 27%|██▋       | 15345/57600 [2:41:21<7:16:12,  1.61it/s]
 27%|██▋       | 15346/57600 [2:41:22<7:20:06,  1.60it/s]
 27%|██▋       | 15347/57600 [2:41:22<7:10:47,  1.63it/s]
 27%|██▋       | 15348/57600 [2:41:23<7:19:13,  1.60it/s]
 27%|██▋       | 15349/57600 [2:41:24<7:19:57,  1.60it/s]
 27%|██▋       | 15350/57600 [2:41:24<7:21:53,  1.59it/s]
 27%|██▋       | 15351/57600 [2:41:25<7:20:27,  1.60it/s]
 27%|██▋       | 15352/57600 [2:41:25<7:11:36,  1.63it/s]
 27%|██▋       | 15353/57600 [2:41:26<7:23:11,  1.59it/s]
 27%|██▋       | 15354/57600 [2:41:27<7:30:40,  1.56it/s]
 27%|██▋       | 15355/57600 [2:41:27<7:34:20,  1.55it/s]
 27%|██▋       | 15356/57600 [2:41:28<7:25:37,  1.58it/s]
 27%|██▋       | 15357/57600 [2:41:29<7:22:46,  1.59it/s]
 27%|██▋       | 15358/57600 [2:41:29<7:25:45,  1.58it/s]
 27%|██▋       | 15359/57600 [2:41:30<7:28:08,  1.57it/s]
 27%|██▋       | 15360/57600 [2:41:31<7:22:35,  1.59it/s]
                                                         
{'loss': 1.2803, 'learning_rate': 7.622996515679443e-07, 'epoch': 169.54}

 27%|██▋       | 15360/57600 [2:41:31<7:22:35,  1.59it/s]
 27%|██▋       | 15361/57600 [2:41:31<7:21:56,  1.59it/s]
 27%|██▋       | 15362/57600 [2:41:32<7:10:29,  1.64it/s]
 27%|██▋       | 15363/57600 [2:41:32<7:14:43,  1.62it/s]
 27%|██▋       | 15364/57600 [2:41:33<7:19:34,  1.60it/s]
 27%|██▋       | 15365/57600 [2:41:34<7:28:38,  1.57it/s]
 27%|██▋       | 15366/57600 [2:41:34<7:08:54,  1.64it/s]
 27%|██▋       | 15367/57600 [2:41:35<6:57:06,  1.69it/s]
 27%|██▋       | 15368/57600 [2:41:35<6:48:20,  1.72it/s]
 27%|██▋       | 15369/57600 [2:41:36<6:49:41,  1.72it/s]
 27%|██▋       | 15370/57600 [2:41:37<7:06:50,  1.65it/s]
 27%|██▋       | 15371/57600 [2:41:37<7:05:43,  1.65it/s]
 27%|██▋       | 15372/57600 [2:41:38<6:57:58,  1.68it/s]
 27%|██▋       | 15373/57600 [2:41:38<7:05:34,  1.65it/s]
 27%|██▋       | 15374/57600 [2:41:39<7:01:05,  1.67it/s]
 27%|██▋       | 15375/57600 [2:41:40<6:58:13,  1.68it/s]
 27%|██▋       | 15376/57600 [2:41:40<7:30:16,  1.56it/s]
 27%|██▋       | 15377/57600 [2:41:41<7:41:28,  1.52it/s]
 27%|██▋       | 15378/57600 [2:41:42<7:25:27,  1.58it/s]
 27%|██▋       | 15379/57600 [2:41:42<7:21:05,  1.60it/s]
 27%|██▋       | 15380/57600 [2:41:43<7:06:57,  1.65it/s]
                                                         
{'loss': 1.2895, 'learning_rate': 7.6198606271777e-07, 'epoch': 169.76}

 27%|██▋       | 15380/57600 [2:41:43<7:06:57,  1.65it/s]
 27%|██▋       | 15381/57600 [2:41:43<6:59:33,  1.68it/s]
 27%|██▋       | 15382/57600 [2:41:44<7:00:46,  1.67it/s]
 27%|██▋       | 15383/57600 [2:41:44<7:02:37,  1.66it/s]
 27%|██▋       | 15384/57600 [2:41:45<6:51:46,  1.71it/s]
 27%|██▋       | 15385/57600 [2:41:46<6:59:43,  1.68it/s]
 27%|██▋       | 15386/57600 [2:41:46<7:11:34,  1.63it/s]
 27%|██▋       | 15387/57600 [2:41:47<6:58:27,  1.68it/s]
 27%|██▋       | 15388/57600 [2:41:47<6:56:55,  1.69it/s]
 27%|██▋       | 15389/57600 [2:41:48<6:49:05,  1.72it/s]
 27%|██▋       | 15390/57600 [2:41:49<7:17:00,  1.61it/s]
 27%|██▋       | 15391/57600 [2:41:49<7:24:07,  1.58it/s]
 27%|██▋       | 15392/57600 [2:41:50<7:08:35,  1.64it/s]
 27%|██▋       | 15393/57600 [2:41:51<7:10:01,  1.64it/s]
 27%|██▋       | 15394/57600 [2:41:51<7:03:36,  1.66it/s]
 27%|██▋       | 15395/57600 [2:41:52<7:11:35,  1.63it/s]
 27%|██▋       | 15396/57600 [2:41:52<7:02:07,  1.67it/s]
 27%|██▋       | 15397/57600 [2:41:53<6:56:01,  1.69it/s]
 27%|██▋       | 15398/57600 [2:41:53<6:53:01,  1.70it/s]
 27%|██▋       | 15399/57600 [2:41:54<7:02:59,  1.66it/s]
 27%|██▋       | 15400/57600 [2:41:55<7:08:54,  1.64it/s]
                                                         
{'loss': 1.3389, 'learning_rate': 7.616724738675958e-07, 'epoch': 169.98}

 27%|██▋       | 15400/57600 [2:41:55<7:08:54,  1.64it/s]
 27%|██▋       | 15401/57600 [2:41:55<7:11:18,  1.63it/s]
 27%|██▋       | 15402/57600 [2:41:56<7:16:40,  1.61it/s]
 27%|██▋       | 15403/57600 [2:41:57<7:24:41,  1.58it/s]
 27%|██▋       | 15404/57600 [2:41:57<7:19:20,  1.60it/s]
 27%|██▋       | 15405/57600 [2:41:58<7:23:07,  1.59it/s]
 27%|██▋       | 15406/57600 [2:41:59<7:15:05,  1.62it/s]
 27%|██▋       | 15407/57600 [2:41:59<7:05:37,  1.65it/s]
 27%|██▋       | 15408/57600 [2:42:00<7:02:29,  1.66it/s]
 27%|██▋       | 15409/57600 [2:42:00<7:22:11,  1.59it/s]
 27%|██▋       | 15410/57600 [2:42:01<7:16:46,  1.61it/s]
 27%|██▋       | 15411/57600 [2:42:02<7:12:13,  1.63it/s]
 27%|██▋       | 15412/57600 [2:42:02<7:22:37,  1.59it/s]
 27%|██▋       | 15413/57600 [2:42:03<7:24:29,  1.58it/s]
 27%|██▋       | 15414/57600 [2:42:04<7:32:29,  1.55it/s]
 27%|██▋       | 15415/57600 [2:42:04<7:21:37,  1.59it/s]
 27%|██▋       | 15416/57600 [2:42:05<7:22:59,  1.59it/s]
 27%|██▋       | 15417/57600 [2:42:05<7:22:17,  1.59it/s]
 27%|██▋       | 15418/57600 [2:42:06<7:31:23,  1.56it/s]
 27%|██▋       | 15419/57600 [2:42:07<7:26:54,  1.57it/s]
 27%|██▋       | 15420/57600 [2:42:07<7:21:47,  1.59it/s]
                                                         
{'loss': 1.2815, 'learning_rate': 7.613588850174215e-07, 'epoch': 170.2}

 27%|██▋       | 15420/57600 [2:42:07<7:21:47,  1.59it/s]
 27%|██▋       | 15421/57600 [2:42:08<7:09:17,  1.64it/s]
 27%|██▋       | 15422/57600 [2:42:09<7:14:41,  1.62it/s]
 27%|██▋       | 15423/57600 [2:42:09<7:22:13,  1.59it/s]
 27%|██▋       | 15424/57600 [2:42:10<7:19:50,  1.60it/s]
 27%|██▋       | 15425/57600 [2:42:10<7:06:24,  1.65it/s]
 27%|██▋       | 15426/57600 [2:42:11<7:06:11,  1.65it/s]
 27%|██▋       | 15427/57600 [2:42:12<6:58:21,  1.68it/s]
 27%|██▋       | 15428/57600 [2:42:12<6:57:47,  1.68it/s]
 27%|██▋       | 15429/57600 [2:42:13<7:05:44,  1.65it/s]
 27%|██▋       | 15430/57600 [2:42:13<7:16:49,  1.61it/s]
 27%|██▋       | 15431/57600 [2:42:14<7:41:56,  1.52it/s]
 27%|██▋       | 15432/57600 [2:42:15<7:38:17,  1.53it/s]
 27%|██▋       | 15433/57600 [2:42:15<7:27:04,  1.57it/s]
 27%|██▋       | 15434/57600 [2:42:16<7:19:16,  1.60it/s]
 27%|██▋       | 15435/57600 [2:42:17<7:03:08,  1.66it/s]
 27%|██▋       | 15436/57600 [2:42:17<7:01:25,  1.67it/s]
 27%|██▋       | 15437/57600 [2:42:18<7:14:36,  1.62it/s]
 27%|██▋       | 15438/57600 [2:42:18<7:25:44,  1.58it/s]
 27%|██▋       | 15439/57600 [2:42:19<7:14:33,  1.62it/s]
 27%|██▋       | 15440/57600 [2:42:20<7:21:23,  1.59it/s]
                                                         
{'loss': 1.2479, 'learning_rate': 7.610452961672474e-07, 'epoch': 170.42}

 27%|██▋       | 15440/57600 [2:42:20<7:21:23,  1.59it/s]
 27%|██▋       | 15441/57600 [2:42:20<7:27:59,  1.57it/s]
 27%|██▋       | 15442/57600 [2:42:21<7:19:38,  1.60it/s]
 27%|██▋       | 15443/57600 [2:42:22<7:12:59,  1.62it/s]
 27%|██▋       | 15444/57600 [2:42:22<7:09:58,  1.63it/s]
 27%|██▋       | 15445/57600 [2:42:23<7:22:50,  1.59it/s]
 27%|██▋       | 15446/57600 [2:42:24<7:32:19,  1.55it/s]
 27%|██▋       | 15447/57600 [2:42:24<7:09:57,  1.63it/s]
 27%|██▋       | 15448/57600 [2:42:25<7:38:11,  1.53it/s]
 27%|██▋       | 15449/57600 [2:42:25<7:28:34,  1.57it/s]
 27%|██▋       | 15450/57600 [2:42:26<7:23:44,  1.58it/s]
 27%|██▋       | 15451/57600 [2:42:27<7:35:06,  1.54it/s]
 27%|██▋       | 15452/57600 [2:42:27<7:18:34,  1.60it/s]
 27%|██▋       | 15453/57600 [2:42:28<7:32:10,  1.55it/s]
 27%|██▋       | 15454/57600 [2:42:29<7:19:46,  1.60it/s]
 27%|██▋       | 15455/57600 [2:42:29<7:26:21,  1.57it/s]
 27%|██▋       | 15456/57600 [2:42:30<7:19:51,  1.60it/s]
 27%|██▋       | 15457/57600 [2:42:30<7:25:24,  1.58it/s]
 27%|██▋       | 15458/57600 [2:42:31<7:32:18,  1.55it/s]
 27%|██▋       | 15459/57600 [2:42:32<7:34:48,  1.54it/s]
 27%|██▋       | 15460/57600 [2:42:32<7:26:32,  1.57it/s]
                                                         
{'loss': 1.2462, 'learning_rate': 7.607317073170731e-07, 'epoch': 170.64}

 27%|██▋       | 15460/57600 [2:42:32<7:26:32,  1.57it/s]
 27%|██▋       | 15461/57600 [2:42:33<7:15:16,  1.61it/s]
 27%|██▋       | 15462/57600 [2:42:34<7:12:50,  1.62it/s]
 27%|██▋       | 15463/57600 [2:42:34<7:06:13,  1.65it/s]
 27%|██▋       | 15464/57600 [2:42:35<7:05:47,  1.65it/s]
 27%|██▋       | 15465/57600 [2:42:35<7:10:56,  1.63it/s]
 27%|██▋       | 15466/57600 [2:42:36<7:13:58,  1.62it/s]
 27%|██▋       | 15467/57600 [2:42:37<7:30:38,  1.56it/s]
 27%|██▋       | 15468/57600 [2:42:37<7:28:51,  1.56it/s]
 27%|██▋       | 15469/57600 [2:42:38<7:16:04,  1.61it/s]
 27%|██▋       | 15470/57600 [2:42:39<7:12:53,  1.62it/s]
 27%|██▋       | 15471/57600 [2:42:39<7:16:41,  1.61it/s]
 27%|██▋       | 15472/57600 [2:42:40<7:14:08,  1.62it/s]
 27%|██▋       | 15473/57600 [2:42:40<7:10:33,  1.63it/s]
 27%|██▋       | 15474/57600 [2:42:41<7:08:29,  1.64it/s]
 27%|██▋       | 15475/57600 [2:42:42<6:56:03,  1.69it/s]
 27%|██▋       | 15476/57600 [2:42:42<6:59:19,  1.67it/s]
 27%|██▋       | 15477/57600 [2:42:43<6:58:32,  1.68it/s]
 27%|██▋       | 15478/57600 [2:42:43<6:48:48,  1.72it/s]
 27%|██▋       | 15479/57600 [2:42:44<6:51:55,  1.70it/s]
 27%|██▋       | 15480/57600 [2:42:44<6:52:22,  1.70it/s]
                                                         
{'loss': 1.2922, 'learning_rate': 7.604181184668989e-07, 'epoch': 170.86}

 27%|██▋       | 15480/57600 [2:42:44<6:52:22,  1.70it/s]
 27%|██▋       | 15481/57600 [2:42:45<7:01:48,  1.66it/s]
 27%|██▋       | 15482/57600 [2:42:46<6:50:46,  1.71it/s]
 27%|██▋       | 15483/57600 [2:42:46<7:13:22,  1.62it/s]
 27%|██▋       | 15484/57600 [2:42:47<7:05:43,  1.65it/s]
 27%|██▋       | 15485/57600 [2:42:48<7:07:10,  1.64it/s]
 27%|██▋       | 15486/57600 [2:42:48<7:01:47,  1.66it/s]
 27%|██▋       | 15487/57600 [2:42:49<7:04:46,  1.65it/s]
 27%|██▋       | 15488/57600 [2:42:49<6:58:41,  1.68it/s]
 27%|██▋       | 15489/57600 [2:42:50<7:08:31,  1.64it/s]
 27%|██▋       | 15490/57600 [2:42:51<7:01:58,  1.66it/s]
 27%|██▋       | 15491/57600 [2:42:51<7:10:51,  1.63it/s]
 27%|██▋       | 15492/57600 [2:42:52<7:16:43,  1.61it/s]
 27%|██▋       | 15493/57600 [2:42:53<7:37:37,  1.53it/s]
 27%|██▋       | 15494/57600 [2:42:53<7:24:51,  1.58it/s]
 27%|██▋       | 15495/57600 [2:42:54<7:33:42,  1.55it/s]
 27%|██▋       | 15496/57600 [2:42:54<7:20:40,  1.59it/s]
 27%|██▋       | 15497/57600 [2:42:55<7:33:40,  1.55it/s]
 27%|██▋       | 15498/57600 [2:42:56<7:21:48,  1.59it/s]
 27%|██▋       | 15499/57600 [2:42:56<7:18:26,  1.60it/s]
 27%|██▋       | 15500/57600 [2:42:57<7:15:02,  1.61it/s]
                                                         
{'loss': 1.3001, 'learning_rate': 7.601045296167247e-07, 'epoch': 171.08}

 27%|██▋       | 15500/57600 [2:42:57<7:15:02,  1.61it/s]
 27%|██▋       | 15501/57600 [2:42:57<7:09:29,  1.63it/s]
 27%|██▋       | 15502/57600 [2:42:58<7:01:37,  1.66it/s]
 27%|██▋       | 15503/57600 [2:42:59<6:57:38,  1.68it/s]
 27%|██▋       | 15504/57600 [2:42:59<6:57:02,  1.68it/s]
 27%|██▋       | 15505/57600 [2:43:00<6:57:00,  1.68it/s]
 27%|██▋       | 15506/57600 [2:43:00<6:51:22,  1.71it/s]
 27%|██▋       | 15507/57600 [2:43:01<6:45:14,  1.73it/s]
 27%|██▋       | 15508/57600 [2:43:02<6:59:32,  1.67it/s]
 27%|██▋       | 15509/57600 [2:43:02<6:56:49,  1.68it/s]
 27%|██▋       | 15510/57600 [2:43:03<7:06:22,  1.65it/s]
 27%|██▋       | 15511/57600 [2:43:03<7:10:46,  1.63it/s]
 27%|██▋       | 15512/57600 [2:43:04<7:16:07,  1.61it/s]
 27%|██▋       | 15513/57600 [2:43:05<7:31:09,  1.55it/s]
 27%|██▋       | 15514/57600 [2:43:05<7:12:44,  1.62it/s]
 27%|██▋       | 15515/57600 [2:43:06<7:39:28,  1.53it/s]
 27%|██▋       | 15516/57600 [2:43:07<7:42:30,  1.52it/s]
 27%|██▋       | 15517/57600 [2:43:07<7:20:41,  1.59it/s]
 27%|██▋       | 15518/57600 [2:43:08<7:30:09,  1.56it/s]
 27%|██▋       | 15519/57600 [2:43:09<7:21:55,  1.59it/s]
 27%|██▋       | 15520/57600 [2:43:09<7:27:47,  1.57it/s]
                                                         
{'loss': 1.2975, 'learning_rate': 7.597909407665505e-07, 'epoch': 171.3}

 27%|██▋       | 15520/57600 [2:43:09<7:27:47,  1.57it/s]
 27%|██▋       | 15521/57600 [2:43:10<7:24:40,  1.58it/s]
 27%|██▋       | 15522/57600 [2:43:11<7:22:54,  1.58it/s]
 27%|██▋       | 15523/57600 [2:43:11<7:18:26,  1.60it/s]
 27%|██▋       | 15524/57600 [2:43:12<7:15:39,  1.61it/s]
 27%|██▋       | 15525/57600 [2:43:12<7:24:59,  1.58it/s]
 27%|██▋       | 15526/57600 [2:43:13<7:14:45,  1.61it/s]
 27%|██▋       | 15527/57600 [2:43:14<7:20:33,  1.59it/s]
 27%|██▋       | 15528/57600 [2:43:14<7:17:12,  1.60it/s]
 27%|██▋       | 15529/57600 [2:43:15<7:00:10,  1.67it/s]
 27%|██▋       | 15530/57600 [2:43:15<7:13:58,  1.62it/s]
 27%|██▋       | 15531/57600 [2:43:16<7:21:00,  1.59it/s]
 27%|██▋       | 15532/57600 [2:43:17<7:13:48,  1.62it/s]
 27%|██▋       | 15533/57600 [2:43:17<7:37:55,  1.53it/s]
 27%|██▋       | 15534/57600 [2:43:18<7:17:34,  1.60it/s]
 27%|██▋       | 15535/57600 [2:43:19<7:18:49,  1.60it/s]
 27%|██▋       | 15536/57600 [2:43:19<7:04:01,  1.65it/s]
 27%|██▋       | 15537/57600 [2:43:20<6:55:56,  1.69it/s]
 27%|██▋       | 15538/57600 [2:43:20<6:54:57,  1.69it/s]
 27%|██▋       | 15539/57600 [2:43:21<6:50:11,  1.71it/s]
 27%|██▋       | 15540/57600 [2:43:21<6:49:17,  1.71it/s]
                                                         
{'loss': 1.2716, 'learning_rate': 7.594773519163762e-07, 'epoch': 171.52}

 27%|██▋       | 15540/57600 [2:43:21<6:49:17,  1.71it/s]
 27%|██▋       | 15541/57600 [2:43:22<6:49:21,  1.71it/s]
 27%|██▋       | 15542/57600 [2:43:23<6:58:52,  1.67it/s]
 27%|██▋       | 15543/57600 [2:43:23<7:08:57,  1.63it/s]
 27%|██▋       | 15544/57600 [2:43:24<7:11:14,  1.63it/s]
 27%|██▋       | 15545/57600 [2:43:25<7:21:17,  1.59it/s]
 27%|██▋       | 15546/57600 [2:43:25<7:23:27,  1.58it/s]
 27%|██▋       | 15547/57600 [2:43:26<7:22:32,  1.58it/s]
 27%|██▋       | 15548/57600 [2:43:26<7:09:08,  1.63it/s]
 27%|██▋       | 15549/57600 [2:43:27<7:15:42,  1.61it/s]
 27%|██▋       | 15550/57600 [2:43:28<7:12:43,  1.62it/s]
 27%|██▋       | 15551/57600 [2:43:28<7:06:47,  1.64it/s]
 27%|██▋       | 15552/57600 [2:43:29<6:59:54,  1.67it/s]
 27%|██▋       | 15553/57600 [2:43:29<6:55:37,  1.69it/s]
 27%|██▋       | 15554/57600 [2:43:30<7:06:54,  1.64it/s]
 27%|██▋       | 15555/57600 [2:43:31<6:58:53,  1.67it/s]
 27%|██▋       | 15556/57600 [2:43:31<6:47:37,  1.72it/s]
 27%|██▋       | 15557/57600 [2:43:32<6:49:08,  1.71it/s]
 27%|██▋       | 15558/57600 [2:43:32<7:06:34,  1.64it/s]
 27%|██▋       | 15559/57600 [2:43:33<7:37:25,  1.53it/s]
 27%|██▋       | 15560/57600 [2:43:34<7:45:29,  1.51it/s]
                                                         
{'loss': 1.2841, 'learning_rate': 7.591637630662021e-07, 'epoch': 171.74}

 27%|██▋       | 15560/57600 [2:43:34<7:45:29,  1.51it/s]
 27%|██▋       | 15561/57600 [2:43:35<8:01:51,  1.45it/s]
 27%|██▋       | 15562/57600 [2:43:35<7:41:38,  1.52it/s]
 27%|██▋       | 15563/57600 [2:43:36<7:35:27,  1.54it/s]
 27%|██▋       | 15564/57600 [2:43:36<7:12:35,  1.62it/s]
 27%|██▋       | 15565/57600 [2:43:37<7:16:24,  1.61it/s]
 27%|██▋       | 15566/57600 [2:43:38<7:05:59,  1.64it/s]
 27%|██▋       | 15567/57600 [2:43:38<7:11:31,  1.62it/s]
 27%|██▋       | 15568/57600 [2:43:39<7:23:11,  1.58it/s]
 27%|██▋       | 15569/57600 [2:43:40<7:17:08,  1.60it/s]
 27%|██▋       | 15570/57600 [2:43:40<7:27:37,  1.56it/s]
 27%|██▋       | 15571/57600 [2:43:41<7:18:08,  1.60it/s]
 27%|██▋       | 15572/57600 [2:43:41<7:09:05,  1.63it/s]
 27%|██▋       | 15573/57600 [2:43:42<7:02:44,  1.66it/s]
 27%|██▋       | 15574/57600 [2:43:43<7:01:55,  1.66it/s]
 27%|██▋       | 15575/57600 [2:43:43<6:52:13,  1.70it/s]
 27%|██▋       | 15576/57600 [2:43:44<6:52:50,  1.70it/s]
 27%|██▋       | 15577/57600 [2:43:44<6:56:01,  1.68it/s]
 27%|██▋       | 15578/57600 [2:43:45<7:20:56,  1.59it/s]
 27%|██▋       | 15579/57600 [2:43:46<7:14:13,  1.61it/s]
 27%|██▋       | 15580/57600 [2:43:46<7:04:07,  1.65it/s]
                                                         
{'loss': 1.2861, 'learning_rate': 7.588501742160279e-07, 'epoch': 171.96}

 27%|██▋       | 15580/57600 [2:43:46<7:04:07,  1.65it/s]
 27%|██▋       | 15581/57600 [2:43:47<7:20:18,  1.59it/s]
 27%|██▋       | 15582/57600 [2:43:48<7:23:05,  1.58it/s]
 27%|██▋       | 15583/57600 [2:43:48<7:14:38,  1.61it/s]
 27%|██▋       | 15584/57600 [2:43:49<7:29:35,  1.56it/s]
 27%|██▋       | 15585/57600 [2:43:49<7:11:08,  1.62it/s]
 27%|██▋       | 15586/57600 [2:43:50<7:08:55,  1.63it/s]
 27%|██▋       | 15587/57600 [2:43:51<7:21:46,  1.58it/s]
 27%|██▋       | 15588/57600 [2:43:51<7:21:11,  1.59it/s]
 27%|██▋       | 15589/57600 [2:43:52<7:16:24,  1.60it/s]
 27%|██▋       | 15590/57600 [2:43:53<7:14:59,  1.61it/s]
 27%|██▋       | 15591/57600 [2:43:53<7:07:41,  1.64it/s]
 27%|██▋       | 15592/57600 [2:43:54<7:23:04,  1.58it/s]
 27%|██▋       | 15593/57600 [2:43:54<7:14:51,  1.61it/s]
 27%|██▋       | 15594/57600 [2:43:55<7:19:10,  1.59it/s]
 27%|██▋       | 15595/57600 [2:43:56<7:15:29,  1.61it/s]
 27%|██▋       | 15596/57600 [2:43:56<7:09:18,  1.63it/s]
 27%|██▋       | 15597/57600 [2:43:57<6:59:58,  1.67it/s]
 27%|██▋       | 15598/57600 [2:43:57<7:02:04,  1.66it/s]
 27%|██▋       | 15599/57600 [2:43:58<7:22:18,  1.58it/s]
 27%|██▋       | 15600/57600 [2:43:59<7:24:12,  1.58it/s]
                                                         
{'loss': 1.2708, 'learning_rate': 7.585365853658536e-07, 'epoch': 172.19}

 27%|██▋       | 15600/57600 [2:43:59<7:24:12,  1.58it/s]
 27%|██▋       | 15601/57600 [2:43:59<7:17:27,  1.60it/s]
 27%|██▋       | 15602/57600 [2:44:00<7:08:58,  1.63it/s]
 27%|██▋       | 15603/57600 [2:44:01<7:11:41,  1.62it/s]
 27%|██▋       | 15604/57600 [2:44:01<7:12:35,  1.62it/s]
 27%|██▋       | 15605/57600 [2:44:02<7:14:13,  1.61it/s]
 27%|██▋       | 15606/57600 [2:44:02<7:01:10,  1.66it/s]
 27%|██▋       | 15607/57600 [2:44:03<7:13:49,  1.61it/s]
 27%|██▋       | 15608/57600 [2:44:04<7:30:56,  1.55it/s]
 27%|██▋       | 15609/57600 [2:44:04<7:20:21,  1.59it/s]
 27%|██▋       | 15610/57600 [2:44:05<7:04:11,  1.65it/s]
 27%|██▋       | 15611/57600 [2:44:05<7:09:52,  1.63it/s]
 27%|██▋       | 15612/57600 [2:44:06<7:14:09,  1.61it/s]
 27%|██▋       | 15613/57600 [2:44:07<7:31:16,  1.55it/s]
 27%|██▋       | 15614/57600 [2:44:07<7:14:41,  1.61it/s]
 27%|██▋       | 15615/57600 [2:44:08<7:18:35,  1.60it/s]
 27%|██▋       | 15616/57600 [2:44:09<7:15:37,  1.61it/s]
 27%|██▋       | 15617/57600 [2:44:09<7:05:58,  1.64it/s]
 27%|██▋       | 15618/57600 [2:44:10<7:09:02,  1.63it/s]
 27%|██▋       | 15619/57600 [2:44:10<7:06:37,  1.64it/s]
 27%|██▋       | 15620/57600 [2:44:11<7:05:54,  1.64it/s]
                                                         
{'loss': 1.2853, 'learning_rate': 7.582229965156794e-07, 'epoch': 172.41}

 27%|██▋       | 15620/57600 [2:44:11<7:05:54,  1.64it/s]
 27%|██▋       | 15621/57600 [2:44:12<7:01:10,  1.66it/s]
 27%|██▋       | 15622/57600 [2:44:12<7:28:14,  1.56it/s]
 27%|██▋       | 15623/57600 [2:44:13<7:28:50,  1.56it/s]
 27%|██▋       | 15624/57600 [2:44:14<7:33:32,  1.54it/s]
 27%|██▋       | 15625/57600 [2:44:14<7:30:36,  1.55it/s]
 27%|██▋       | 15626/57600 [2:44:15<7:14:24,  1.61it/s]
 27%|██▋       | 15627/57600 [2:44:15<6:59:18,  1.67it/s]
 27%|██▋       | 15628/57600 [2:44:16<6:56:37,  1.68it/s]
 27%|██▋       | 15629/57600 [2:44:17<6:56:52,  1.68it/s]
 27%|██▋       | 15630/57600 [2:44:17<7:01:11,  1.66it/s]
 27%|██▋       | 15631/57600 [2:44:18<6:50:19,  1.70it/s]
 27%|██▋       | 15632/57600 [2:44:18<6:49:43,  1.71it/s]
 27%|██▋       | 15633/57600 [2:44:19<6:47:52,  1.71it/s]
 27%|██▋       | 15634/57600 [2:44:19<6:39:16,  1.75it/s]
 27%|██▋       | 15635/57600 [2:44:20<6:39:22,  1.75it/s]
 27%|██▋       | 15636/57600 [2:44:21<6:45:26,  1.73it/s]
 27%|██▋       | 15637/57600 [2:44:21<6:53:49,  1.69it/s]
 27%|██▋       | 15638/57600 [2:44:22<7:00:39,  1.66it/s]
 27%|██▋       | 15639/57600 [2:44:23<7:01:40,  1.66it/s]
 27%|██▋       | 15640/57600 [2:44:23<7:14:35,  1.61it/s]
                                                         
{'loss': 1.2959, 'learning_rate': 7.579094076655052e-07, 'epoch': 172.63}

 27%|██▋       | 15640/57600 [2:44:23<7:14:35,  1.61it/s]
 27%|██▋       | 15641/57600 [2:44:24<7:29:41,  1.56it/s]
 27%|██▋       | 15642/57600 [2:44:24<7:18:55,  1.59it/s]
 27%|██▋       | 15643/57600 [2:44:25<7:18:06,  1.60it/s]
 27%|██▋       | 15644/57600 [2:44:26<7:24:01,  1.57it/s]
 27%|██▋       | 15645/57600 [2:44:26<7:24:24,  1.57it/s]
 27%|██▋       | 15646/57600 [2:44:27<7:21:21,  1.58it/s]
 27%|██▋       | 15647/57600 [2:44:28<7:16:28,  1.60it/s]
 27%|██▋       | 15648/57600 [2:44:28<7:13:54,  1.61it/s]
 27%|██▋       | 15649/57600 [2:44:29<7:10:18,  1.62it/s]
 27%|██▋       | 15650/57600 [2:44:29<6:57:38,  1.67it/s]
 27%|██▋       | 15651/57600 [2:44:30<7:09:58,  1.63it/s]
 27%|██▋       | 15652/57600 [2:44:31<6:55:33,  1.68it/s]
 27%|██▋       | 15653/57600 [2:44:31<6:54:00,  1.69it/s]
 27%|██▋       | 15654/57600 [2:44:32<6:50:09,  1.70it/s]
 27%|██▋       | 15655/57600 [2:44:32<7:00:07,  1.66it/s]
 27%|██▋       | 15656/57600 [2:44:33<6:57:32,  1.67it/s]
 27%|██▋       | 15657/57600 [2:44:34<7:01:34,  1.66it/s]
 27%|██▋       | 15658/57600 [2:44:34<7:08:51,  1.63it/s]
 27%|██▋       | 15659/57600 [2:44:35<7:27:09,  1.56it/s]
 27%|██▋       | 15660/57600 [2:44:36<7:34:11,  1.54it/s]
                                                         
{'loss': 1.2862, 'learning_rate': 7.57595818815331e-07, 'epoch': 172.85}

 27%|██▋       | 15660/57600 [2:44:36<7:34:11,  1.54it/s]
 27%|██▋       | 15661/57600 [2:44:36<7:32:52,  1.54it/s]
 27%|██▋       | 15662/57600 [2:44:37<7:36:04,  1.53it/s]
 27%|██▋       | 15663/57600 [2:44:37<7:24:25,  1.57it/s]
 27%|██▋       | 15664/57600 [2:44:38<7:15:39,  1.60it/s]
 27%|██▋       | 15665/57600 [2:44:39<7:07:20,  1.64it/s]
 27%|██▋       | 15666/57600 [2:44:39<7:08:02,  1.63it/s]
 27%|██▋       | 15667/57600 [2:44:40<7:00:22,  1.66it/s]
 27%|██▋       | 15668/57600 [2:44:41<7:11:12,  1.62it/s]
 27%|██▋       | 15669/57600 [2:44:41<7:12:13,  1.62it/s]
 27%|██▋       | 15670/57600 [2:44:42<7:18:00,  1.60it/s]
 27%|██▋       | 15671/57600 [2:44:42<7:31:44,  1.55it/s]
 27%|██▋       | 15672/57600 [2:44:43<7:24:09,  1.57it/s]
 27%|██▋       | 15673/57600 [2:44:44<7:42:19,  1.51it/s]
 27%|██▋       | 15674/57600 [2:44:44<7:44:48,  1.50it/s]
 27%|██▋       | 15675/57600 [2:44:45<7:46:16,  1.50it/s]
 27%|██▋       | 15676/57600 [2:44:46<7:25:27,  1.57it/s]
 27%|██▋       | 15677/57600 [2:44:46<7:28:58,  1.56it/s]
 27%|██▋       | 15678/57600 [2:44:47<7:10:32,  1.62it/s]
 27%|██▋       | 15679/57600 [2:44:47<7:00:18,  1.66it/s]
 27%|██▋       | 15680/57600 [2:44:48<6:53:33,  1.69it/s]
                                                         
{'loss': 1.287, 'learning_rate': 7.572822299651567e-07, 'epoch': 173.07}

 27%|██▋       | 15680/57600 [2:44:48<6:53:33,  1.69it/s]
 27%|██▋       | 15681/57600 [2:44:49<7:16:35,  1.60it/s]
 27%|██▋       | 15682/57600 [2:44:49<7:08:49,  1.63it/s]
 27%|██▋       | 15683/57600 [2:44:50<7:06:02,  1.64it/s]
 27%|██▋       | 15684/57600 [2:44:51<7:04:13,  1.65it/s]
 27%|██▋       | 15685/57600 [2:44:51<7:04:57,  1.64it/s]
 27%|██▋       | 15686/57600 [2:44:52<6:54:11,  1.69it/s]
 27%|██▋       | 15687/57600 [2:44:52<6:49:41,  1.71it/s]
 27%|██▋       | 15688/57600 [2:44:53<6:57:10,  1.67it/s]
 27%|██▋       | 15689/57600 [2:44:54<7:09:14,  1.63it/s]
 27%|██▋       | 15690/57600 [2:44:54<7:05:40,  1.64it/s]
 27%|██▋       | 15691/57600 [2:44:55<6:58:54,  1.67it/s]
 27%|██▋       | 15692/57600 [2:44:55<6:50:54,  1.70it/s]
 27%|██▋       | 15693/57600 [2:44:56<6:53:44,  1.69it/s]
 27%|██▋       | 15694/57600 [2:44:56<6:41:44,  1.74it/s]
 27%|██▋       | 15695/57600 [2:44:57<6:59:34,  1.66it/s]
 27%|██▋       | 15696/57600 [2:44:58<7:06:07,  1.64it/s]
 27%|██▋       | 15697/57600 [2:44:58<7:12:52,  1.61it/s]
 27%|██▋       | 15698/57600 [2:44:59<7:12:19,  1.62it/s]
 27%|██▋       | 15699/57600 [2:45:00<7:16:22,  1.60it/s]
 27%|██▋       | 15700/57600 [2:45:00<7:18:24,  1.59it/s]
                                                         
{'loss': 1.2946, 'learning_rate': 7.569686411149826e-07, 'epoch': 173.29}

 27%|██▋       | 15700/57600 [2:45:00<7:18:24,  1.59it/s]
 27%|██▋       | 15701/57600 [2:45:01<7:19:27,  1.59it/s]
 27%|██▋       | 15702/57600 [2:45:02<7:21:42,  1.58it/s]
 27%|██▋       | 15703/57600 [2:45:02<7:21:24,  1.58it/s]
 27%|██▋       | 15704/57600 [2:45:03<7:05:46,  1.64it/s]
 27%|██▋       | 15705/57600 [2:45:03<7:02:11,  1.65it/s]
 27%|██▋       | 15706/57600 [2:45:04<6:54:52,  1.68it/s]
 27%|██▋       | 15707/57600 [2:45:05<6:58:50,  1.67it/s]
 27%|██▋       | 15708/57600 [2:45:05<6:52:54,  1.69it/s]
 27%|██▋       | 15709/57600 [2:45:06<7:12:42,  1.61it/s]
 27%|██▋       | 15710/57600 [2:45:06<7:00:15,  1.66it/s]
 27%|██▋       | 15711/57600 [2:45:07<7:07:43,  1.63it/s]
 27%|██▋       | 15712/57600 [2:45:08<7:02:32,  1.65it/s]
 27%|██▋       | 15713/57600 [2:45:08<6:58:53,  1.67it/s]
 27%|██▋       | 15714/57600 [2:45:09<7:10:15,  1.62it/s]
 27%|██▋       | 15715/57600 [2:45:09<7:04:35,  1.64it/s]
 27%|██▋       | 15716/57600 [2:45:10<7:06:26,  1.64it/s]
 27%|██▋       | 15717/57600 [2:45:11<7:23:09,  1.58it/s]
 27%|██▋       | 15718/57600 [2:45:11<7:23:16,  1.57it/s]
 27%|██▋       | 15719/57600 [2:45:12<7:28:04,  1.56it/s]
 27%|██▋       | 15720/57600 [2:45:13<7:31:22,  1.55it/s]
                                                         
{'loss': 1.2862, 'learning_rate': 7.566550522648083e-07, 'epoch': 173.51}

 27%|██▋       | 15720/57600 [2:45:13<7:31:22,  1.55it/s]
 27%|██▋       | 15721/57600 [2:45:13<7:41:03,  1.51it/s]
 27%|██▋       | 15722/57600 [2:45:14<7:33:39,  1.54it/s]
 27%|██▋       | 15723/57600 [2:45:15<7:23:26,  1.57it/s]
 27%|██▋       | 15724/57600 [2:45:15<7:23:17,  1.57it/s]
 27%|██▋       | 15725/57600 [2:45:16<7:09:55,  1.62it/s]
 27%|██▋       | 15726/57600 [2:45:16<6:59:32,  1.66it/s]
 27%|██▋       | 15727/57600 [2:45:17<6:57:40,  1.67it/s]
 27%|██▋       | 15728/57600 [2:45:18<7:13:15,  1.61it/s]
 27%|██▋       | 15729/57600 [2:45:18<7:40:57,  1.51it/s]
 27%|██▋       | 15730/57600 [2:45:19<7:45:35,  1.50it/s]
 27%|██▋       | 15731/57600 [2:45:20<7:30:05,  1.55it/s]
 27%|██▋       | 15732/57600 [2:45:20<7:24:32,  1.57it/s]
 27%|██▋       | 15733/57600 [2:45:21<7:11:50,  1.62it/s]
 27%|██▋       | 15734/57600 [2:45:21<7:00:11,  1.66it/s]
 27%|██▋       | 15735/57600 [2:45:22<7:00:16,  1.66it/s]
 27%|██▋       | 15736/57600 [2:45:23<7:05:00,  1.64it/s]
 27%|██▋       | 15737/57600 [2:45:23<7:15:41,  1.60it/s]
 27%|██▋       | 15738/57600 [2:45:24<7:10:09,  1.62it/s]
 27%|██▋       | 15739/57600 [2:45:24<7:11:51,  1.62it/s]
 27%|██▋       | 15740/57600 [2:45:25<7:17:15,  1.60it/s]
                                                         
{'loss': 1.2715, 'learning_rate': 7.563414634146341e-07, 'epoch': 173.73}

 27%|██▋       | 15740/57600 [2:45:25<7:17:15,  1.60it/s]
 27%|██▋       | 15741/57600 [2:45:26<7:17:21,  1.60it/s]
 27%|██▋       | 15742/57600 [2:45:26<7:21:32,  1.58it/s]
 27%|██▋       | 15743/57600 [2:45:27<7:19:39,  1.59it/s]
 27%|██▋       | 15744/57600 [2:45:28<7:24:02,  1.57it/s]
 27%|██▋       | 15745/57600 [2:45:28<7:40:57,  1.51it/s]
 27%|██▋       | 15746/57600 [2:45:29<7:28:26,  1.56it/s]
 27%|██▋       | 15747/57600 [2:45:30<7:15:19,  1.60it/s]
 27%|██▋       | 15748/57600 [2:45:30<7:16:00,  1.60it/s]
 27%|██▋       | 15749/57600 [2:45:31<7:12:01,  1.61it/s]
 27%|██▋       | 15750/57600 [2:45:31<7:23:42,  1.57it/s]
 27%|██▋       | 15751/57600 [2:45:32<7:12:51,  1.61it/s]
 27%|██▋       | 15752/57600 [2:45:33<7:07:17,  1.63it/s]
 27%|██▋       | 15753/57600 [2:45:33<7:15:50,  1.60it/s]
 27%|██▋       | 15754/57600 [2:45:34<7:11:41,  1.62it/s]
 27%|██▋       | 15755/57600 [2:45:35<7:10:52,  1.62it/s]
 27%|██▋       | 15756/57600 [2:45:35<7:05:16,  1.64it/s]
 27%|██▋       | 15757/57600 [2:45:36<7:02:13,  1.65it/s]
 27%|██▋       | 15758/57600 [2:45:36<6:57:45,  1.67it/s]
 27%|██▋       | 15759/57600 [2:45:37<6:48:05,  1.71it/s]
 27%|██▋       | 15760/57600 [2:45:37<6:44:52,  1.72it/s]
                                                         
{'loss': 1.3114, 'learning_rate': 7.560278745644598e-07, 'epoch': 173.95}

 27%|██▋       | 15760/57600 [2:45:37<6:44:52,  1.72it/s]
 27%|██▋       | 15761/57600 [2:45:38<6:37:25,  1.75it/s]
 27%|██▋       | 15762/57600 [2:45:39<6:43:18,  1.73it/s]
 27%|██▋       | 15763/57600 [2:45:39<6:36:16,  1.76it/s]
 27%|██▋       | 15764/57600 [2:45:40<6:37:27,  1.75it/s]
 27%|██▋       | 15765/57600 [2:45:40<6:57:40,  1.67it/s]
 27%|██▋       | 15766/57600 [2:45:41<6:54:41,  1.68it/s]
 27%|██▋       | 15767/57600 [2:45:42<7:24:17,  1.57it/s]
 27%|██▋       | 15768/57600 [2:45:42<7:21:10,  1.58it/s]
 27%|██▋       | 15769/57600 [2:45:43<7:05:06,  1.64it/s]
 27%|██▋       | 15770/57600 [2:45:43<7:08:11,  1.63it/s]
 27%|██▋       | 15771/57600 [2:45:44<7:01:57,  1.65it/s]
 27%|██▋       | 15772/57600 [2:45:45<7:03:21,  1.65it/s]
 27%|██▋       | 15773/57600 [2:45:45<7:03:19,  1.65it/s]
 27%|██▋       | 15774/57600 [2:45:46<7:16:33,  1.60it/s]
 27%|██▋       | 15775/57600 [2:45:47<7:11:03,  1.62it/s]
 27%|██▋       | 15776/57600 [2:45:47<7:16:21,  1.60it/s]
 27%|██▋       | 15777/57600 [2:45:48<7:05:22,  1.64it/s]
 27%|██▋       | 15778/57600 [2:45:48<7:07:51,  1.63it/s]
 27%|██▋       | 15779/57600 [2:45:49<7:09:11,  1.62it/s]
 27%|██▋       | 15780/57600 [2:45:50<6:59:02,  1.66it/s]
                                                         
{'loss': 1.3279, 'learning_rate': 7.557142857142858e-07, 'epoch': 174.17}

 27%|██▋       | 15780/57600 [2:45:50<6:59:02,  1.66it/s]
 27%|██▋       | 15781/57600 [2:45:50<7:14:20,  1.60it/s]
 27%|██▋       | 15782/57600 [2:45:51<7:00:06,  1.66it/s]
 27%|██▋       | 15783/57600 [2:45:51<7:09:55,  1.62it/s]
 27%|██▋       | 15784/57600 [2:45:52<7:09:13,  1.62it/s]
 27%|██▋       | 15785/57600 [2:45:53<7:02:34,  1.65it/s]
 27%|██▋       | 15786/57600 [2:45:53<7:27:13,  1.56it/s]
 27%|██▋       | 15787/57600 [2:45:54<7:14:37,  1.60it/s]
 27%|██▋       | 15788/57600 [2:45:55<6:58:25,  1.67it/s]
 27%|██▋       | 15789/57600 [2:45:55<7:02:50,  1.65it/s]
 27%|██▋       | 15790/57600 [2:45:56<6:57:29,  1.67it/s]
 27%|██▋       | 15791/57600 [2:45:56<7:04:06,  1.64it/s]
 27%|██▋       | 15792/57600 [2:45:57<7:03:12,  1.65it/s]
 27%|██▋       | 15793/57600 [2:45:58<7:04:56,  1.64it/s]
 27%|██▋       | 15794/57600 [2:45:58<7:17:16,  1.59it/s]
 27%|██▋       | 15795/57600 [2:45:59<7:24:43,  1.57it/s]
 27%|██▋       | 15796/57600 [2:46:00<7:18:41,  1.59it/s]
 27%|██▋       | 15797/57600 [2:46:00<7:18:01,  1.59it/s]
 27%|██▋       | 15798/57600 [2:46:01<6:58:40,  1.66it/s]
 27%|██▋       | 15799/57600 [2:46:01<6:55:54,  1.68it/s]
 27%|██▋       | 15800/57600 [2:46:02<7:13:05,  1.61it/s]
                                                         
{'loss': 1.2848, 'learning_rate': 7.554006968641114e-07, 'epoch': 174.39}

 27%|██▋       | 15800/57600 [2:46:02<7:13:05,  1.61it/s]
 27%|██▋       | 15801/57600 [2:46:03<7:07:13,  1.63it/s]
 27%|██▋       | 15802/57600 [2:46:03<7:20:17,  1.58it/s]
 27%|██▋       | 15803/57600 [2:46:04<7:16:57,  1.59it/s]
 27%|██▋       | 15804/57600 [2:46:04<7:11:59,  1.61it/s]
 27%|██▋       | 15805/57600 [2:46:05<7:09:25,  1.62it/s]
 27%|██▋       | 15806/57600 [2:46:06<7:24:05,  1.57it/s]
 27%|██▋       | 15807/57600 [2:46:06<7:13:51,  1.61it/s]
 27%|██▋       | 15808/57600 [2:46:07<7:09:37,  1.62it/s]
 27%|██▋       | 15809/57600 [2:46:08<7:07:16,  1.63it/s]
 27%|██▋       | 15810/57600 [2:46:08<7:13:44,  1.61it/s]
 27%|██▋       | 15811/57600 [2:46:09<6:57:59,  1.67it/s]
 27%|██▋       | 15812/57600 [2:46:09<6:57:27,  1.67it/s]
 27%|██▋       | 15813/57600 [2:46:10<6:55:38,  1.68it/s]
 27%|██▋       | 15814/57600 [2:46:11<6:54:12,  1.68it/s]
 27%|██▋       | 15815/57600 [2:46:11<6:58:17,  1.66it/s]
 27%|██▋       | 15816/57600 [2:46:12<7:03:50,  1.64it/s]
 27%|██▋       | 15817/57600 [2:46:12<7:10:38,  1.62it/s]
 27%|██▋       | 15818/57600 [2:46:13<7:07:18,  1.63it/s]
 27%|██▋       | 15819/57600 [2:46:14<6:54:03,  1.68it/s]
 27%|██▋       | 15820/57600 [2:46:14<6:43:43,  1.72it/s]
                                                         
{'loss': 1.3029, 'learning_rate': 7.550871080139372e-07, 'epoch': 174.61}

 27%|██▋       | 15820/57600 [2:46:14<6:43:43,  1.72it/s]
 27%|██▋       | 15821/57600 [2:46:15<7:01:06,  1.65it/s]
 27%|██▋       | 15822/57600 [2:46:15<7:10:22,  1.62it/s]
 27%|██▋       | 15823/57600 [2:46:16<7:01:15,  1.65it/s]
 27%|██▋       | 15824/57600 [2:46:17<6:55:34,  1.68it/s]
 27%|██▋       | 15825/57600 [2:46:17<7:05:01,  1.64it/s]
 27%|██▋       | 15826/57600 [2:46:18<7:02:38,  1.65it/s]
 27%|██▋       | 15827/57600 [2:46:18<7:05:53,  1.63it/s]
 27%|██▋       | 15828/57600 [2:46:19<7:14:03,  1.60it/s]
 27%|██▋       | 15829/57600 [2:46:20<7:07:10,  1.63it/s]
 27%|██▋       | 15830/57600 [2:46:20<7:17:02,  1.59it/s]
 27%|██▋       | 15831/57600 [2:46:21<7:09:13,  1.62it/s]
 27%|██▋       | 15832/57600 [2:46:22<7:16:17,  1.60it/s]
 27%|██▋       | 15833/57600 [2:46:22<7:07:58,  1.63it/s]
 27%|██▋       | 15834/57600 [2:46:23<7:33:45,  1.53it/s]
 27%|██▋       | 15835/57600 [2:46:23<7:20:57,  1.58it/s]
 27%|██▋       | 15836/57600 [2:46:24<7:16:53,  1.59it/s]
 27%|██▋       | 15837/57600 [2:46:25<7:24:32,  1.57it/s]
 27%|██▋       | 15838/57600 [2:46:25<7:30:19,  1.55it/s]
 27%|██▋       | 15839/57600 [2:46:26<7:21:26,  1.58it/s]
 28%|██▊       | 15840/57600 [2:46:27<7:33:21,  1.54it/s]
                                                         
{'loss': 1.2794, 'learning_rate': 7.547735191637631e-07, 'epoch': 174.83}

 28%|██▊       | 15840/57600 [2:46:27<7:33:21,  1.54it/s]
 28%|██▊       | 15841/57600 [2:46:27<7:32:19,  1.54it/s]
 28%|██▊       | 15842/57600 [2:46:28<7:10:22,  1.62it/s]
 28%|██▊       | 15843/57600 [2:46:29<7:07:39,  1.63it/s]
 28%|██▊       | 15844/57600 [2:46:29<7:07:02,  1.63it/s]
 28%|██▊       | 15845/57600 [2:46:30<7:05:56,  1.63it/s]
 28%|██▊       | 15846/57600 [2:46:30<7:05:00,  1.64it/s]
 28%|██▊       | 15847/57600 [2:46:31<6:59:20,  1.66it/s]
 28%|██▊       | 15848/57600 [2:46:32<7:12:35,  1.61it/s]
 28%|██▊       | 15849/57600 [2:46:32<7:10:03,  1.62it/s]
 28%|██▊       | 15850/57600 [2:46:33<6:59:01,  1.66it/s]
 28%|██▊       | 15851/57600 [2:46:33<6:52:23,  1.69it/s]
 28%|██▊       | 15852/57600 [2:46:34<6:44:44,  1.72it/s]
 28%|██▊       | 15853/57600 [2:46:35<6:53:11,  1.68it/s]
 28%|██▊       | 15854/57600 [2:46:35<7:11:23,  1.61it/s]
 28%|██▊       | 15855/57600 [2:46:36<7:00:00,  1.66it/s]
 28%|██▊       | 15856/57600 [2:46:36<7:14:14,  1.60it/s]
 28%|██▊       | 15857/57600 [2:46:37<7:04:51,  1.64it/s]
 28%|██▊       | 15858/57600 [2:46:38<6:57:10,  1.67it/s]
 28%|██▊       | 15859/57600 [2:46:38<7:10:22,  1.62it/s]
 28%|██▊       | 15860/57600 [2:46:39<7:13:52,  1.60it/s]
                                                         
{'loss': 1.3058, 'learning_rate': 7.544599303135888e-07, 'epoch': 175.06}

 28%|██▊       | 15860/57600 [2:46:39<7:13:52,  1.60it/s]
 28%|██▊       | 15861/57600 [2:46:40<7:24:53,  1.56it/s]
 28%|██▊       | 15862/57600 [2:46:40<7:17:12,  1.59it/s]
 28%|██▊       | 15863/57600 [2:46:41<7:34:03,  1.53it/s]
 28%|██▊       | 15864/57600 [2:46:41<7:20:57,  1.58it/s]
 28%|██▊       | 15865/57600 [2:46:42<7:20:37,  1.58it/s]
 28%|██▊       | 15866/57600 [2:46:43<7:20:35,  1.58it/s]
 28%|██▊       | 15867/57600 [2:46:43<7:24:42,  1.56it/s]
 28%|██▊       | 15868/57600 [2:46:44<7:17:52,  1.59it/s]
 28%|██▊       | 15869/57600 [2:46:45<7:34:29,  1.53it/s]
 28%|██▊       | 15870/57600 [2:46:45<7:17:33,  1.59it/s]
 28%|██▊       | 15871/57600 [2:46:46<7:20:56,  1.58it/s]
 28%|██▊       | 15872/57600 [2:46:47<7:22:03,  1.57it/s]
 28%|██▊       | 15873/57600 [2:46:47<7:12:50,  1.61it/s]
 28%|██▊       | 15874/57600 [2:46:48<7:21:01,  1.58it/s]
 28%|██▊       | 15875/57600 [2:46:48<7:18:18,  1.59it/s]
 28%|██▊       | 15876/57600 [2:46:49<7:20:22,  1.58it/s]
 28%|██▊       | 15877/57600 [2:46:50<7:17:36,  1.59it/s]
 28%|██▊       | 15878/57600 [2:46:50<7:08:07,  1.62it/s]
 28%|██▊       | 15879/57600 [2:46:51<7:03:32,  1.64it/s]
 28%|██▊       | 15880/57600 [2:46:52<7:13:46,  1.60it/s]
                                                         
{'loss': 1.2509, 'learning_rate': 7.541463414634146e-07, 'epoch': 175.28}

 28%|██▊       | 15880/57600 [2:46:52<7:13:46,  1.60it/s]
 28%|██▊       | 15881/57600 [2:46:52<7:10:54,  1.61it/s]
 28%|██▊       | 15882/57600 [2:46:53<7:05:49,  1.63it/s]
 28%|██▊       | 15883/57600 [2:46:53<7:18:58,  1.58it/s]
 28%|██▊       | 15884/57600 [2:46:54<7:27:41,  1.55it/s]
 28%|██▊       | 15885/57600 [2:46:55<7:15:58,  1.59it/s]
 28%|██▊       | 15886/57600 [2:46:55<7:26:36,  1.56it/s]
 28%|██▊       | 15887/57600 [2:46:56<7:23:33,  1.57it/s]
 28%|██▊       | 15888/57600 [2:46:57<7:25:57,  1.56it/s]
 28%|██▊       | 15889/57600 [2:46:57<7:22:19,  1.57it/s]
 28%|██▊       | 15890/57600 [2:46:58<7:11:56,  1.61it/s]
 28%|██▊       | 15891/57600 [2:46:59<7:24:59,  1.56it/s]
 28%|██▊       | 15892/57600 [2:46:59<7:23:08,  1.57it/s]
 28%|██▊       | 15893/57600 [2:47:00<7:10:46,  1.61it/s]
 28%|██▊       | 15894/57600 [2:47:00<7:14:13,  1.60it/s]
 28%|██▊       | 15895/57600 [2:47:01<7:06:25,  1.63it/s]
 28%|██▊       | 15896/57600 [2:47:02<7:01:58,  1.65it/s]
 28%|██▊       | 15897/57600 [2:47:02<7:10:44,  1.61it/s]
 28%|██▊       | 15898/57600 [2:47:03<7:10:20,  1.62it/s]
 28%|██▊       | 15899/57600 [2:47:03<7:03:07,  1.64it/s]
 28%|██▊       | 15900/57600 [2:47:04<7:02:30,  1.64it/s]
                                                         
{'loss': 1.2677, 'learning_rate': 7.538327526132404e-07, 'epoch': 175.5}

 28%|██▊       | 15900/57600 [2:47:04<7:02:30,  1.64it/s]
 28%|██▊       | 15901/57600 [2:47:05<7:10:23,  1.61it/s]
 28%|██▊       | 15902/57600 [2:47:05<7:01:01,  1.65it/s]
 28%|██▊       | 15903/57600 [2:47:06<7:07:03,  1.63it/s]
 28%|██▊       | 15904/57600 [2:47:07<7:19:20,  1.58it/s]
 28%|██▊       | 15905/57600 [2:47:07<7:10:07,  1.62it/s]
 28%|██▊       | 15906/57600 [2:47:08<7:17:54,  1.59it/s]
 28%|██▊       | 15907/57600 [2:47:08<7:31:34,  1.54it/s]
 28%|██▊       | 15908/57600 [2:47:09<7:37:53,  1.52it/s]
 28%|██▊       | 15909/57600 [2:47:10<7:28:49,  1.55it/s]
 28%|██▊       | 15910/57600 [2:47:10<7:14:41,  1.60it/s]
 28%|██▊       | 15911/57600 [2:47:11<7:19:52,  1.58it/s]
 28%|██▊       | 15912/57600 [2:47:12<7:10:05,  1.62it/s]
 28%|██▊       | 15913/57600 [2:47:12<7:07:37,  1.62it/s]
 28%|██▊       | 15914/57600 [2:47:13<7:07:12,  1.63it/s]
 28%|██▊       | 15915/57600 [2:47:13<7:18:43,  1.58it/s]
 28%|██▊       | 15916/57600 [2:47:14<7:20:28,  1.58it/s]
 28%|██▊       | 15917/57600 [2:47:15<7:38:01,  1.52it/s]
 28%|██▊       | 15918/57600 [2:47:15<7:35:39,  1.52it/s]
 28%|██▊       | 15919/57600 [2:47:16<7:32:53,  1.53it/s]
 28%|██▊       | 15920/57600 [2:47:17<7:31:16,  1.54it/s]
                                                         
{'loss': 1.2854, 'learning_rate': 7.535191637630663e-07, 'epoch': 175.72}

 28%|██▊       | 15920/57600 [2:47:17<7:31:16,  1.54it/s]
 28%|██▊       | 15921/57600 [2:47:17<7:18:59,  1.58it/s]
 28%|██▊       | 15922/57600 [2:47:18<7:11:30,  1.61it/s]
 28%|██▊       | 15923/57600 [2:47:19<7:11:44,  1.61it/s]
 28%|██▊       | 15924/57600 [2:47:19<7:09:11,  1.62it/s]
 28%|██▊       | 15925/57600 [2:47:20<7:17:28,  1.59it/s]
 28%|██▊       | 15926/57600 [2:47:21<7:48:38,  1.48it/s]
 28%|██▊       | 15927/57600 [2:47:21<7:47:34,  1.49it/s]
 28%|██▊       | 15928/57600 [2:47:22<7:35:34,  1.52it/s]
 28%|██▊       | 15929/57600 [2:47:23<7:33:03,  1.53it/s]
 28%|██▊       | 15930/57600 [2:47:23<7:21:23,  1.57it/s]
 28%|██▊       | 15931/57600 [2:47:24<7:15:30,  1.59it/s]
 28%|██▊       | 15932/57600 [2:47:24<7:26:05,  1.56it/s]
 28%|██▊       | 15933/57600 [2:47:25<7:33:04,  1.53it/s]
 28%|██▊       | 15934/57600 [2:47:26<7:33:16,  1.53it/s]
 28%|██▊       | 15935/57600 [2:47:26<7:30:58,  1.54it/s]
 28%|██▊       | 15936/57600 [2:47:27<7:28:33,  1.55it/s]
 28%|██▊       | 15937/57600 [2:47:28<7:36:44,  1.52it/s]
 28%|██▊       | 15938/57600 [2:47:28<7:27:18,  1.55it/s]
 28%|██▊       | 15939/57600 [2:47:29<7:21:49,  1.57it/s]
 28%|██▊       | 15940/57600 [2:47:30<7:19:12,  1.58it/s]
                                                         
{'loss': 1.2456, 'learning_rate': 7.532055749128919e-07, 'epoch': 175.94}

 28%|██▊       | 15940/57600 [2:47:30<7:19:12,  1.58it/s]
 28%|██▊       | 15941/57600 [2:47:30<7:28:09,  1.55it/s]
 28%|██▊       | 15942/57600 [2:47:31<7:17:28,  1.59it/s]
 28%|██▊       | 15943/57600 [2:47:31<7:14:35,  1.60it/s]
 28%|██▊       | 15944/57600 [2:47:32<7:06:18,  1.63it/s]
 28%|██▊       | 15945/57600 [2:47:33<7:09:30,  1.62it/s]
 28%|██▊       | 15946/57600 [2:47:33<7:16:30,  1.59it/s]
 28%|██▊       | 15947/57600 [2:47:34<7:08:35,  1.62it/s]
 28%|██▊       | 15948/57600 [2:47:35<7:20:15,  1.58it/s]
 28%|██▊       | 15949/57600 [2:47:35<7:17:22,  1.59it/s]
 28%|██▊       | 15950/57600 [2:47:36<7:26:29,  1.55it/s]
 28%|██▊       | 15951/57600 [2:47:37<7:27:59,  1.55it/s]
 28%|██▊       | 15952/57600 [2:47:37<7:19:28,  1.58it/s]
 28%|██▊       | 15953/57600 [2:47:38<7:26:14,  1.56it/s]
 28%|██▊       | 15954/57600 [2:47:38<7:35:28,  1.52it/s]
 28%|██▊       | 15955/57600 [2:47:39<7:35:49,  1.52it/s]
 28%|██▊       | 15956/57600 [2:47:40<7:35:03,  1.53it/s]
 28%|██▊       | 15957/57600 [2:47:40<7:33:45,  1.53it/s]
 28%|██▊       | 15958/57600 [2:47:41<7:24:04,  1.56it/s]
 28%|██▊       | 15959/57600 [2:47:42<7:25:49,  1.56it/s]
 28%|██▊       | 15960/57600 [2:47:42<7:20:03,  1.58it/s]
                                                         
{'loss': 1.2687, 'learning_rate': 7.528919860627177e-07, 'epoch': 176.16}

 28%|██▊       | 15960/57600 [2:47:42<7:20:03,  1.58it/s]
 28%|██▊       | 15961/57600 [2:47:43<7:40:56,  1.51it/s]
 28%|██▊       | 15962/57600 [2:47:44<7:42:15,  1.50it/s]
 28%|██▊       | 15963/57600 [2:47:44<7:40:29,  1.51it/s]
 28%|██▊       | 15964/57600 [2:47:45<7:44:47,  1.49it/s]
 28%|██▊       | 15965/57600 [2:47:46<7:41:57,  1.50it/s]
 28%|██▊       | 15966/57600 [2:47:46<7:45:00,  1.49it/s]
 28%|██▊       | 15967/57600 [2:47:47<7:36:09,  1.52it/s]
 28%|██▊       | 15968/57600 [2:47:48<7:27:20,  1.55it/s]
 28%|██▊       | 15969/57600 [2:47:48<7:47:55,  1.48it/s]
 28%|██▊       | 15970/57600 [2:47:49<7:43:32,  1.50it/s]
 28%|██▊       | 15971/57600 [2:47:50<7:35:26,  1.52it/s]
 28%|██▊       | 15972/57600 [2:47:50<7:45:42,  1.49it/s]
 28%|██▊       | 15973/57600 [2:47:51<7:40:33,  1.51it/s]
 28%|██▊       | 15974/57600 [2:47:52<7:18:41,  1.58it/s]
 28%|██▊       | 15975/57600 [2:47:52<7:10:17,  1.61it/s]
 28%|██▊       | 15976/57600 [2:47:53<7:10:15,  1.61it/s]
 28%|██▊       | 15977/57600 [2:47:53<7:08:47,  1.62it/s]
 28%|██▊       | 15978/57600 [2:47:54<7:16:37,  1.59it/s]
 28%|██▊       | 15979/57600 [2:47:55<7:31:10,  1.54it/s]
 28%|██▊       | 15980/57600 [2:47:55<7:39:49,  1.51it/s]
                                                         
{'loss': 1.2569, 'learning_rate': 7.525783972125435e-07, 'epoch': 176.38}

 28%|██▊       | 15980/57600 [2:47:55<7:39:49,  1.51it/s]
 28%|██▊       | 15981/57600 [2:47:56<7:29:15,  1.54it/s]
 28%|██▊       | 15982/57600 [2:47:57<7:17:50,  1.58it/s]
 28%|██▊       | 15983/57600 [2:47:57<7:10:13,  1.61it/s]
 28%|██▊       | 15984/57600 [2:47:58<7:08:12,  1.62it/s]
 28%|██▊       | 15985/57600 [2:47:59<7:11:55,  1.61it/s]
 28%|██▊       | 15986/57600 [2:47:59<7:08:55,  1.62it/s]
 28%|██▊       | 15987/57600 [2:48:00<7:05:57,  1.63it/s]
 28%|██▊       | 15988/57600 [2:48:00<7:07:43,  1.62it/s]
 28%|██▊       | 15989/57600 [2:48:01<7:06:32,  1.63it/s]
 28%|██▊       | 15990/57600 [2:48:02<7:10:04,  1.61it/s]
 28%|██▊       | 15991/57600 [2:48:02<7:03:58,  1.64it/s]
 28%|██▊       | 15992/57600 [2:48:03<7:07:26,  1.62it/s]
 28%|██▊       | 15993/57600 [2:48:03<7:08:01,  1.62it/s]
 28%|██▊       | 15994/57600 [2:48:04<7:33:28,  1.53it/s]
 28%|██▊       | 15995/57600 [2:48:05<7:29:51,  1.54it/s]
 28%|██▊       | 15996/57600 [2:48:05<7:37:15,  1.52it/s]
 28%|██▊       | 15997/57600 [2:48:06<7:27:31,  1.55it/s]
 28%|██▊       | 15998/57600 [2:48:07<7:22:14,  1.57it/s]
 28%|██▊       | 15999/57600 [2:48:07<7:24:48,  1.56it/s]
 28%|██▊       | 16000/57600 [2:48:08<7:09:31,  1.61it/s]
                                                         
{'loss': 1.2962, 'learning_rate': 7.522648083623694e-07, 'epoch': 176.6}

 28%|██▊       | 16000/57600 [2:48:08<7:09:31,  1.61it/s]
 28%|██▊       | 16001/57600 [2:48:09<7:31:29,  1.54it/s]
 28%|██▊       | 16002/57600 [2:48:09<7:26:20,  1.55it/s]
 28%|██▊       | 16003/57600 [2:48:10<7:18:58,  1.58it/s]
 28%|██▊       | 16004/57600 [2:48:11<7:36:43,  1.52it/s]
 28%|██▊       | 16005/57600 [2:48:11<7:18:52,  1.58it/s]
 28%|██▊       | 16006/57600 [2:48:12<7:25:45,  1.56it/s]
 28%|██▊       | 16007/57600 [2:48:12<7:14:46,  1.59it/s]
 28%|██▊       | 16008/57600 [2:48:13<7:16:05,  1.59it/s]
 28%|██▊       | 16009/57600 [2:48:14<7:11:52,  1.61it/s]
 28%|██▊       | 16010/57600 [2:48:14<7:11:35,  1.61it/s]
 28%|██▊       | 16011/57600 [2:48:15<7:26:09,  1.55it/s]
 28%|██▊       | 16012/57600 [2:48:16<7:22:10,  1.57it/s]
 28%|██▊       | 16013/57600 [2:48:16<7:14:33,  1.59it/s]
 28%|██▊       | 16014/57600 [2:48:17<7:20:20,  1.57it/s]
 28%|██▊       | 16015/57600 [2:48:18<7:17:31,  1.58it/s]
 28%|██▊       | 16016/57600 [2:48:18<7:29:34,  1.54it/s]
 28%|██▊       | 16017/57600 [2:48:19<7:12:03,  1.60it/s]
 28%|██▊       | 16018/57600 [2:48:19<7:13:53,  1.60it/s]
 28%|██▊       | 16019/57600 [2:48:20<7:12:31,  1.60it/s]
 28%|██▊       | 16020/57600 [2:48:21<7:10:34,  1.61it/s]
                                                         
{'loss': 1.2896, 'learning_rate': 7.519512195121951e-07, 'epoch': 176.82}

 28%|██▊       | 16020/57600 [2:48:21<7:10:34,  1.61it/s]
 28%|██▊       | 16021/57600 [2:48:21<7:04:40,  1.63it/s]
 28%|██▊       | 16022/57600 [2:48:22<7:12:40,  1.60it/s]
 28%|██▊       | 16023/57600 [2:48:22<7:07:00,  1.62it/s]
 28%|██▊       | 16024/57600 [2:48:23<7:07:00,  1.62it/s]
 28%|██▊       | 16025/57600 [2:48:24<7:13:20,  1.60it/s]
 28%|██▊       | 16026/57600 [2:48:24<7:11:00,  1.61it/s]
 28%|██▊       | 16027/57600 [2:48:25<7:15:57,  1.59it/s]
 28%|██▊       | 16028/57600 [2:48:26<7:09:05,  1.61it/s]
 28%|██▊       | 16029/57600 [2:48:26<7:01:13,  1.64it/s]
 28%|██▊       | 16030/57600 [2:48:27<7:07:54,  1.62it/s]
 28%|██▊       | 16031/57600 [2:48:27<7:05:17,  1.63it/s]
 28%|██▊       | 16032/57600 [2:48:28<7:11:06,  1.61it/s]
 28%|██▊       | 16033/57600 [2:48:29<7:07:25,  1.62it/s]
 28%|██▊       | 16034/57600 [2:48:29<7:13:28,  1.60it/s]
 28%|██▊       | 16035/57600 [2:48:30<7:06:41,  1.62it/s]
 28%|██▊       | 16036/57600 [2:48:31<7:08:03,  1.62it/s]
 28%|██▊       | 16037/57600 [2:48:31<7:23:17,  1.56it/s]
 28%|██▊       | 16038/57600 [2:48:32<7:08:19,  1.62it/s]
 28%|██▊       | 16039/57600 [2:48:32<7:12:10,  1.60it/s]
 28%|██▊       | 16040/57600 [2:48:33<7:18:01,  1.58it/s]
                                                         
{'loss': 1.2979, 'learning_rate': 7.516376306620209e-07, 'epoch': 177.04}

 28%|██▊       | 16040/57600 [2:48:33<7:18:01,  1.58it/s]
 28%|██▊       | 16041/57600 [2:48:34<7:16:32,  1.59it/s]
 28%|██▊       | 16042/57600 [2:48:34<7:14:17,  1.59it/s]
 28%|██▊       | 16043/57600 [2:48:35<7:28:01,  1.55it/s]
 28%|██▊       | 16044/57600 [2:48:36<7:26:30,  1.55it/s]
 28%|██▊       | 16045/57600 [2:48:36<7:41:59,  1.50it/s]
 28%|██▊       | 16046/57600 [2:48:37<7:36:50,  1.52it/s]
 28%|██▊       | 16047/57600 [2:48:38<7:27:39,  1.55it/s]
 28%|██▊       | 16048/57600 [2:48:38<7:23:24,  1.56it/s]
 28%|██▊       | 16049/57600 [2:48:39<7:11:45,  1.60it/s]
 28%|██▊       | 16050/57600 [2:48:39<7:08:56,  1.61it/s]
 28%|██▊       | 16051/57600 [2:48:40<7:06:17,  1.62it/s]
 28%|██▊       | 16052/57600 [2:48:41<7:14:44,  1.59it/s]
 28%|██▊       | 16053/57600 [2:48:41<7:23:03,  1.56it/s]
 28%|██▊       | 16054/57600 [2:48:42<7:26:06,  1.55it/s]
 28%|██▊       | 16055/57600 [2:48:43<7:21:48,  1.57it/s]
 28%|██▊       | 16056/57600 [2:48:43<7:18:11,  1.58it/s]
 28%|██▊       | 16057/57600 [2:48:44<7:09:29,  1.61it/s]
 28%|██▊       | 16058/57600 [2:48:44<7:05:33,  1.63it/s]
 28%|██▊       | 16059/57600 [2:48:45<7:02:38,  1.64it/s]
 28%|██▊       | 16060/57600 [2:48:46<6:49:12,  1.69it/s]
                                                         
{'loss': 1.2901, 'learning_rate': 7.513240418118468e-07, 'epoch': 177.26}

 28%|██▊       | 16060/57600 [2:48:46<6:49:12,  1.69it/s]
 28%|██▊       | 16061/57600 [2:48:46<7:03:08,  1.64it/s]
 28%|██▊       | 16062/57600 [2:48:47<7:27:26,  1.55it/s]
 28%|██▊       | 16063/57600 [2:48:48<7:23:58,  1.56it/s]
 28%|██▊       | 16064/57600 [2:48:48<7:33:30,  1.53it/s]
 28%|██▊       | 16065/57600 [2:48:49<7:26:48,  1.55it/s]
 28%|██▊       | 16066/57600 [2:48:50<7:17:08,  1.58it/s]
 28%|██▊       | 16067/57600 [2:48:50<7:24:27,  1.56it/s]
 28%|██▊       | 16068/57600 [2:48:51<7:21:44,  1.57it/s]
 28%|██▊       | 16069/57600 [2:48:52<7:48:58,  1.48it/s]
 28%|██▊       | 16070/57600 [2:48:52<7:31:24,  1.53it/s]
 28%|██▊       | 16071/57600 [2:48:53<7:20:49,  1.57it/s]
 28%|██▊       | 16072/57600 [2:48:53<7:21:34,  1.57it/s]
 28%|██▊       | 16073/57600 [2:48:54<7:16:08,  1.59it/s]
 28%|██▊       | 16074/57600 [2:48:55<7:16:02,  1.59it/s]
 28%|██▊       | 16075/57600 [2:48:55<7:11:46,  1.60it/s]
 28%|██▊       | 16076/57600 [2:48:56<7:24:56,  1.56it/s]
 28%|██▊       | 16077/57600 [2:48:57<7:23:32,  1.56it/s]
 28%|██▊       | 16078/57600 [2:48:57<7:32:42,  1.53it/s]
 28%|██▊       | 16079/57600 [2:48:58<7:21:40,  1.57it/s]
 28%|██▊       | 16080/57600 [2:48:59<7:29:05,  1.54it/s]
                                                         
{'loss': 1.2471, 'learning_rate': 7.510104529616724e-07, 'epoch': 177.48}

 28%|██▊       | 16080/57600 [2:48:59<7:29:05,  1.54it/s]
 28%|██▊       | 16081/57600 [2:48:59<7:32:20,  1.53it/s]
 28%|██▊       | 16082/57600 [2:49:00<7:27:31,  1.55it/s]
 28%|██▊       | 16083/57600 [2:49:01<7:30:55,  1.53it/s]
 28%|██▊       | 16084/57600 [2:49:01<7:40:06,  1.50it/s]
 28%|██▊       | 16085/57600 [2:49:02<7:30:56,  1.53it/s]
 28%|██▊       | 16086/57600 [2:49:02<7:28:38,  1.54it/s]
 28%|██▊       | 16087/57600 [2:49:03<7:13:26,  1.60it/s]
 28%|██▊       | 16088/57600 [2:49:04<7:05:05,  1.63it/s]
 28%|██▊       | 16089/57600 [2:49:04<7:09:32,  1.61it/s]
 28%|██▊       | 16090/57600 [2:49:05<7:14:14,  1.59it/s]
 28%|██▊       | 16091/57600 [2:49:06<7:17:57,  1.58it/s]
 28%|██▊       | 16092/57600 [2:49:06<7:24:11,  1.56it/s]
 28%|██▊       | 16093/57600 [2:49:07<7:43:30,  1.49it/s]
 28%|██▊       | 16094/57600 [2:49:08<7:23:01,  1.56it/s]
 28%|██▊       | 16095/57600 [2:49:08<7:10:43,  1.61it/s]
 28%|██▊       | 16096/57600 [2:49:09<7:16:07,  1.59it/s]
 28%|██▊       | 16097/57600 [2:49:09<7:22:53,  1.56it/s]
 28%|██▊       | 16098/57600 [2:49:10<7:29:17,  1.54it/s]
 28%|██▊       | 16099/57600 [2:49:11<7:24:39,  1.56it/s]
 28%|██▊       | 16100/57600 [2:49:11<7:34:26,  1.52it/s]
                                                         
{'loss': 1.2514, 'learning_rate': 7.506968641114981e-07, 'epoch': 177.7}

 28%|██▊       | 16100/57600 [2:49:11<7:34:26,  1.52it/s]
 28%|██▊       | 16101/57600 [2:49:12<7:22:56,  1.56it/s]
 28%|██▊       | 16102/57600 [2:49:13<7:08:33,  1.61it/s]
 28%|██▊       | 16103/57600 [2:49:13<7:16:53,  1.58it/s]
 28%|██▊       | 16104/57600 [2:49:14<7:19:47,  1.57it/s]
 28%|██▊       | 16105/57600 [2:49:14<7:00:40,  1.64it/s]
 28%|██▊       | 16106/57600 [2:49:15<7:06:00,  1.62it/s]
 28%|██▊       | 16107/57600 [2:49:16<6:58:02,  1.65it/s]
 28%|██▊       | 16108/57600 [2:49:16<6:59:25,  1.65it/s]
 28%|██▊       | 16109/57600 [2:49:17<7:03:43,  1.63it/s]
 28%|██▊       | 16110/57600 [2:49:18<7:07:21,  1.62it/s]
 28%|██▊       | 16111/57600 [2:49:18<7:15:51,  1.59it/s]
 28%|██▊       | 16112/57600 [2:49:19<7:08:18,  1.61it/s]
 28%|██▊       | 16113/57600 [2:49:19<7:12:00,  1.60it/s]
 28%|██▊       | 16114/57600 [2:49:20<7:24:28,  1.56it/s]
 28%|██▊       | 16115/57600 [2:49:21<7:25:52,  1.55it/s]
 28%|██▊       | 16116/57600 [2:49:21<7:11:13,  1.60it/s]
 28%|██▊       | 16117/57600 [2:49:22<7:10:18,  1.61it/s]
 28%|██▊       | 16118/57600 [2:49:23<7:01:40,  1.64it/s]
 28%|██▊       | 16119/57600 [2:49:23<6:53:19,  1.67it/s]
 28%|██▊       | 16120/57600 [2:49:24<7:10:43,  1.61it/s]
                                                         
{'loss': 1.2979, 'learning_rate': 7.50383275261324e-07, 'epoch': 177.92}

 28%|██▊       | 16120/57600 [2:49:24<7:10:43,  1.61it/s]
 28%|██▊       | 16121/57600 [2:49:24<6:58:36,  1.65it/s]
 28%|██▊       | 16122/57600 [2:49:25<6:59:05,  1.65it/s]
 28%|██▊       | 16123/57600 [2:49:26<7:05:20,  1.63it/s]
 28%|██▊       | 16124/57600 [2:49:26<7:01:05,  1.64it/s]
 28%|██▊       | 16125/57600 [2:49:27<7:07:59,  1.62it/s]
 28%|██▊       | 16126/57600 [2:49:27<7:06:23,  1.62it/s]
 28%|██▊       | 16127/57600 [2:49:28<7:40:51,  1.50it/s]
 28%|██▊       | 16128/57600 [2:49:29<7:42:43,  1.49it/s]
 28%|██▊       | 16129/57600 [2:49:30<7:35:45,  1.52it/s]
 28%|██▊       | 16130/57600 [2:49:30<7:25:09,  1.55it/s]
 28%|██▊       | 16131/57600 [2:49:31<7:11:06,  1.60it/s]
 28%|██▊       | 16132/57600 [2:49:31<7:04:49,  1.63it/s]
 28%|██▊       | 16133/57600 [2:49:32<7:08:54,  1.61it/s]
 28%|██▊       | 16134/57600 [2:49:33<7:01:53,  1.64it/s]
 28%|██▊       | 16135/57600 [2:49:33<6:52:42,  1.67it/s]
 28%|██▊       | 16136/57600 [2:49:34<7:01:10,  1.64it/s]
 28%|██▊       | 16137/57600 [2:49:34<7:00:18,  1.64it/s]
 28%|██▊       | 16138/57600 [2:49:35<7:16:41,  1.58it/s]
 28%|██▊       | 16139/57600 [2:49:36<7:06:48,  1.62it/s]
 28%|██▊       | 16140/57600 [2:49:36<6:59:00,  1.65it/s]
                                                         
{'loss': 1.275, 'learning_rate': 7.500696864111499e-07, 'epoch': 178.15}

 28%|██▊       | 16140/57600 [2:49:36<6:59:00,  1.65it/s]
 28%|██▊       | 16141/57600 [2:49:37<6:55:32,  1.66it/s]
 28%|██▊       | 16142/57600 [2:49:37<6:57:43,  1.65it/s]
 28%|██▊       | 16143/57600 [2:49:38<7:05:19,  1.62it/s]
 28%|██▊       | 16144/57600 [2:49:39<7:06:42,  1.62it/s]
 28%|██▊       | 16145/57600 [2:49:39<7:16:40,  1.58it/s]
 28%|██▊       | 16146/57600 [2:49:40<7:22:12,  1.56it/s]
 28%|██▊       | 16147/57600 [2:49:41<7:12:09,  1.60it/s]
 28%|██▊       | 16148/57600 [2:49:41<7:17:33,  1.58it/s]
 28%|██▊       | 16149/57600 [2:49:42<7:22:37,  1.56it/s]
 28%|██▊       | 16150/57600 [2:49:43<7:29:08,  1.54it/s]
 28%|██▊       | 16151/57600 [2:49:43<7:22:05,  1.56it/s]
 28%|██▊       | 16152/57600 [2:49:44<7:07:48,  1.61it/s]
 28%|██▊       | 16153/57600 [2:49:44<7:15:39,  1.59it/s]
 28%|██▊       | 16154/57600 [2:49:45<7:28:03,  1.54it/s]
 28%|██▊       | 16155/57600 [2:49:46<7:22:33,  1.56it/s]
 28%|██▊       | 16156/57600 [2:49:46<7:24:22,  1.55it/s]
 28%|██▊       | 16157/57600 [2:49:47<7:20:14,  1.57it/s]
 28%|██▊       | 16158/57600 [2:49:48<7:24:57,  1.55it/s]
 28%|██▊       | 16159/57600 [2:49:48<7:17:30,  1.58it/s]
 28%|██▊       | 16160/57600 [2:49:49<7:18:03,  1.58it/s]
                                                         
{'loss': 1.2554, 'learning_rate': 7.497560975609755e-07, 'epoch': 178.37}

 28%|██▊       | 16160/57600 [2:49:49<7:18:03,  1.58it/s]
 28%|██▊       | 16161/57600 [2:49:50<7:14:50,  1.59it/s]
 28%|██▊       | 16162/57600 [2:49:50<7:06:11,  1.62it/s]
 28%|██▊       | 16163/57600 [2:49:51<7:10:48,  1.60it/s]
 28%|██▊       | 16164/57600 [2:49:51<7:22:42,  1.56it/s]
 28%|██▊       | 16165/57600 [2:49:52<7:22:49,  1.56it/s]
 28%|██▊       | 16166/57600 [2:49:53<7:20:36,  1.57it/s]
 28%|██▊       | 16167/57600 [2:49:53<7:11:18,  1.60it/s]
 28%|██▊       | 16168/57600 [2:49:54<7:22:10,  1.56it/s]
 28%|██▊       | 16169/57600 [2:49:55<7:16:27,  1.58it/s]
 28%|██▊       | 16170/57600 [2:49:55<7:16:46,  1.58it/s]
 28%|██▊       | 16171/57600 [2:49:56<7:10:21,  1.60it/s]
 28%|██▊       | 16172/57600 [2:49:56<7:11:53,  1.60it/s]
 28%|██▊       | 16173/57600 [2:49:57<7:10:11,  1.60it/s]
 28%|██▊       | 16174/57600 [2:49:58<7:05:50,  1.62it/s]
 28%|██▊       | 16175/57600 [2:49:58<7:08:49,  1.61it/s]
 28%|██▊       | 16176/57600 [2:49:59<7:17:54,  1.58it/s]
 28%|██▊       | 16177/57600 [2:50:00<7:09:00,  1.61it/s]
 28%|██▊       | 16178/57600 [2:50:00<7:06:51,  1.62it/s]
 28%|██▊       | 16179/57600 [2:50:01<7:02:23,  1.63it/s]
 28%|██▊       | 16180/57600 [2:50:01<7:05:08,  1.62it/s]
                                                         
{'loss': 1.2885, 'learning_rate': 7.494425087108014e-07, 'epoch': 178.59}

 28%|██▊       | 16180/57600 [2:50:01<7:05:08,  1.62it/s]
 28%|██▊       | 16181/57600 [2:50:02<7:11:09,  1.60it/s]
 28%|██▊       | 16182/57600 [2:50:03<7:15:59,  1.58it/s]
 28%|██▊       | 16183/57600 [2:50:03<7:28:03,  1.54it/s]
 28%|██▊       | 16184/57600 [2:50:04<7:19:31,  1.57it/s]
 28%|██▊       | 16185/57600 [2:50:05<7:23:25,  1.56it/s]
 28%|██▊       | 16186/57600 [2:50:05<7:24:06,  1.55it/s]
 28%|██▊       | 16187/57600 [2:50:06<7:18:56,  1.57it/s]
 28%|██▊       | 16188/57600 [2:50:07<7:16:27,  1.58it/s]
 28%|██▊       | 16189/57600 [2:50:07<7:28:01,  1.54it/s]
 28%|██▊       | 16190/57600 [2:50:08<7:22:50,  1.56it/s]
 28%|██▊       | 16191/57600 [2:50:08<7:23:33,  1.56it/s]
 28%|██▊       | 16192/57600 [2:50:09<7:17:50,  1.58it/s]
 28%|██▊       | 16193/57600 [2:50:10<7:33:33,  1.52it/s]
 28%|██▊       | 16194/57600 [2:50:10<7:30:37,  1.53it/s]
 28%|██▊       | 16195/57600 [2:50:11<7:32:54,  1.52it/s]
 28%|██▊       | 16196/57600 [2:50:12<7:19:45,  1.57it/s]
 28%|██▊       | 16197/57600 [2:50:12<7:16:30,  1.58it/s]
 28%|██▊       | 16198/57600 [2:50:13<7:15:59,  1.58it/s]
 28%|██▊       | 16199/57600 [2:50:14<7:09:27,  1.61it/s]
 28%|██▊       | 16200/57600 [2:50:14<7:02:32,  1.63it/s]
                                                         
{'loss': 1.2416, 'learning_rate': 7.491289198606272e-07, 'epoch': 178.81}

 28%|██▊       | 16200/57600 [2:50:14<7:02:32,  1.63it/s]
 28%|██▊       | 16201/57600 [2:50:15<7:24:06,  1.55it/s]
 28%|██▊       | 16202/57600 [2:50:16<7:25:57,  1.55it/s]
 28%|██▊       | 16203/57600 [2:50:16<7:20:28,  1.57it/s]
 28%|██▊       | 16204/57600 [2:50:17<7:41:43,  1.49it/s]
 28%|██▊       | 16205/57600 [2:50:17<7:29:37,  1.53it/s]
 28%|██▊       | 16206/57600 [2:50:18<7:29:44,  1.53it/s]
 28%|██▊       | 16207/57600 [2:50:19<7:21:38,  1.56it/s]
 28%|██▊       | 16208/57600 [2:50:19<7:19:08,  1.57it/s]
 28%|██▊       | 16209/57600 [2:50:20<7:17:19,  1.58it/s]
 28%|██▊       | 16210/57600 [2:50:21<7:19:44,  1.57it/s]
 28%|██▊       | 16211/57600 [2:50:21<7:15:05,  1.59it/s]
 28%|██▊       | 16212/57600 [2:50:22<7:13:59,  1.59it/s]
 28%|██▊       | 16213/57600 [2:50:23<7:15:36,  1.58it/s]
 28%|██▊       | 16214/57600 [2:50:23<7:06:31,  1.62it/s]
 28%|██▊       | 16215/57600 [2:50:24<7:20:11,  1.57it/s]
 28%|██▊       | 16216/57600 [2:50:24<7:28:09,  1.54it/s]
 28%|██▊       | 16217/57600 [2:50:25<7:14:19,  1.59it/s]
 28%|██▊       | 16218/57600 [2:50:26<7:32:34,  1.52it/s]
 28%|██▊       | 16219/57600 [2:50:26<7:18:35,  1.57it/s]
 28%|██▊       | 16220/57600 [2:50:27<7:11:27,  1.60it/s]
                                                         
{'loss': 1.2668, 'learning_rate': 7.48815331010453e-07, 'epoch': 179.03}

 28%|██▊       | 16220/57600 [2:50:27<7:11:27,  1.60it/s]
 28%|██▊       | 16221/57600 [2:50:28<7:09:16,  1.61it/s]
 28%|██▊       | 16222/57600 [2:50:28<7:11:13,  1.60it/s]
 28%|██▊       | 16223/57600 [2:50:29<7:00:39,  1.64it/s]
 28%|██▊       | 16224/57600 [2:50:29<7:00:01,  1.64it/s]
 28%|██▊       | 16225/57600 [2:50:30<7:09:42,  1.60it/s]
 28%|██▊       | 16226/57600 [2:50:31<7:08:46,  1.61it/s]
 28%|██▊       | 16227/57600 [2:50:31<7:00:48,  1.64it/s]
 28%|██▊       | 16228/57600 [2:50:32<7:00:31,  1.64it/s]
 28%|██▊       | 16229/57600 [2:50:32<6:59:45,  1.64it/s]
 28%|██▊       | 16230/57600 [2:50:33<7:05:07,  1.62it/s]
 28%|██▊       | 16231/57600 [2:50:34<7:00:38,  1.64it/s]
 28%|██▊       | 16232/57600 [2:50:34<7:10:54,  1.60it/s]
 28%|██▊       | 16233/57600 [2:50:35<7:04:58,  1.62it/s]
 28%|██▊       | 16234/57600 [2:50:36<6:59:18,  1.64it/s]
 28%|██▊       | 16235/57600 [2:50:36<6:57:47,  1.65it/s]
 28%|██▊       | 16236/57600 [2:50:37<6:44:39,  1.70it/s]
 28%|██▊       | 16237/57600 [2:50:37<6:58:58,  1.65it/s]
 28%|██▊       | 16238/57600 [2:50:38<7:06:03,  1.62it/s]
 28%|██▊       | 16239/57600 [2:50:39<7:17:48,  1.57it/s]
 28%|██▊       | 16240/57600 [2:50:39<7:23:35,  1.55it/s]
                                                         
{'loss': 1.2995, 'learning_rate': 7.485017421602786e-07, 'epoch': 179.25}

 28%|██▊       | 16240/57600 [2:50:39<7:23:35,  1.55it/s]
 28%|██▊       | 16241/57600 [2:50:40<7:28:47,  1.54it/s]
 28%|██▊       | 16242/57600 [2:50:41<7:09:54,  1.60it/s]
 28%|██▊       | 16243/57600 [2:50:41<7:02:39,  1.63it/s]
 28%|██▊       | 16244/57600 [2:50:42<7:12:56,  1.59it/s]
 28%|██▊       | 16245/57600 [2:50:42<7:22:22,  1.56it/s]
 28%|██▊       | 16246/57600 [2:50:43<7:26:32,  1.54it/s]
 28%|██▊       | 16247/57600 [2:50:44<7:15:29,  1.58it/s]
 28%|██▊       | 16248/57600 [2:50:44<7:31:12,  1.53it/s]
 28%|██▊       | 16249/57600 [2:50:45<7:21:11,  1.56it/s]
 28%|██▊       | 16250/57600 [2:50:46<7:15:44,  1.58it/s]
 28%|██▊       | 16251/57600 [2:50:46<7:20:21,  1.56it/s]
 28%|██▊       | 16252/57600 [2:50:47<7:38:03,  1.50it/s]
 28%|██▊       | 16253/57600 [2:50:48<7:30:10,  1.53it/s]
 28%|██▊       | 16254/57600 [2:50:48<7:20:12,  1.57it/s]
 28%|██▊       | 16255/57600 [2:50:49<7:27:44,  1.54it/s]
 28%|██▊       | 16256/57600 [2:50:50<7:18:25,  1.57it/s]
 28%|██▊       | 16257/57600 [2:50:50<7:12:46,  1.59it/s]
 28%|██▊       | 16258/57600 [2:50:51<6:58:35,  1.65it/s]
 28%|██▊       | 16259/57600 [2:50:51<6:58:23,  1.65it/s]
 28%|██▊       | 16260/57600 [2:50:52<6:49:23,  1.68it/s]
                                                         
{'loss': 1.2525, 'learning_rate': 7.481881533101045e-07, 'epoch': 179.47}

 28%|██▊       | 16260/57600 [2:50:52<6:49:23,  1.68it/s]
 28%|██▊       | 16261/57600 [2:50:53<6:56:30,  1.65it/s]
 28%|██▊       | 16262/57600 [2:50:53<7:09:26,  1.60it/s]
 28%|██▊       | 16263/57600 [2:50:54<7:15:49,  1.58it/s]
 28%|██▊       | 16264/57600 [2:50:54<7:15:04,  1.58it/s]
 28%|██▊       | 16265/57600 [2:50:55<7:17:33,  1.57it/s]
 28%|██▊       | 16266/57600 [2:50:56<7:15:08,  1.58it/s]
 28%|██▊       | 16267/57600 [2:50:56<7:20:10,  1.57it/s]
 28%|██▊       | 16268/57600 [2:50:57<7:18:02,  1.57it/s]
 28%|██▊       | 16269/57600 [2:50:58<7:26:29,  1.54it/s]
 28%|██▊       | 16270/57600 [2:50:58<7:25:40,  1.55it/s]
 28%|██▊       | 16271/57600 [2:50:59<7:08:07,  1.61it/s]
 28%|██▊       | 16272/57600 [2:51:00<7:19:30,  1.57it/s]
 28%|██▊       | 16273/57600 [2:51:00<7:08:56,  1.61it/s]
 28%|██▊       | 16274/57600 [2:51:01<7:03:00,  1.63it/s]
 28%|██▊       | 16275/57600 [2:51:01<7:00:36,  1.64it/s]
 28%|██▊       | 16276/57600 [2:51:02<6:59:42,  1.64it/s]
 28%|██▊       | 16277/57600 [2:51:03<7:05:06,  1.62it/s]
 28%|██▊       | 16278/57600 [2:51:03<7:05:41,  1.62it/s]
 28%|██▊       | 16279/57600 [2:51:04<7:02:54,  1.63it/s]
 28%|██▊       | 16280/57600 [2:51:04<7:10:34,  1.60it/s]
                                                         
{'loss': 1.2723, 'learning_rate': 7.478745644599303e-07, 'epoch': 179.69}

 28%|██▊       | 16280/57600 [2:51:04<7:10:34,  1.60it/s]
 28%|██▊       | 16281/57600 [2:51:05<7:01:43,  1.63it/s]
 28%|██▊       | 16282/57600 [2:51:06<7:00:07,  1.64it/s]
 28%|██▊       | 16283/57600 [2:51:06<6:52:12,  1.67it/s]
 28%|██▊       | 16284/57600 [2:51:07<6:50:17,  1.68it/s]
 28%|██▊       | 16285/57600 [2:51:07<6:53:03,  1.67it/s]
 28%|██▊       | 16286/57600 [2:51:08<7:01:30,  1.63it/s]
 28%|██▊       | 16287/57600 [2:51:09<6:53:53,  1.66it/s]
 28%|██▊       | 16288/57600 [2:51:09<6:52:15,  1.67it/s]
 28%|██▊       | 16289/57600 [2:51:10<6:50:37,  1.68it/s]
 28%|██▊       | 16290/57600 [2:51:10<6:44:05,  1.70it/s]
 28%|██▊       | 16291/57600 [2:51:11<7:03:35,  1.63it/s]
 28%|██▊       | 16292/57600 [2:51:12<6:58:44,  1.64it/s]
 28%|██▊       | 16293/57600 [2:51:12<7:13:29,  1.59it/s]
 28%|██▊       | 16294/57600 [2:51:13<7:03:02,  1.63it/s]
 28%|██▊       | 16295/57600 [2:51:14<7:02:40,  1.63it/s]
 28%|██▊       | 16296/57600 [2:51:14<7:09:08,  1.60it/s]
 28%|██▊       | 16297/57600 [2:51:15<6:55:31,  1.66it/s]
 28%|██▊       | 16298/57600 [2:51:15<6:53:36,  1.66it/s]
 28%|██▊       | 16299/57600 [2:51:16<7:05:05,  1.62it/s]
 28%|██▊       | 16300/57600 [2:51:17<7:02:58,  1.63it/s]
                                                         
{'loss': 1.3271, 'learning_rate': 7.475609756097561e-07, 'epoch': 179.91}

 28%|██▊       | 16300/57600 [2:51:17<7:02:58,  1.63it/s]
 28%|██▊       | 16301/57600 [2:51:17<6:58:43,  1.64it/s]
 28%|██▊       | 16302/57600 [2:51:18<7:20:25,  1.56it/s]
 28%|██▊       | 16303/57600 [2:51:19<7:15:32,  1.58it/s]
 28%|██▊       | 16304/57600 [2:51:19<7:12:17,  1.59it/s]
 28%|██▊       | 16305/57600 [2:51:20<7:09:51,  1.60it/s]
 28%|██▊       | 16306/57600 [2:51:20<7:05:52,  1.62it/s]
 28%|██▊       | 16307/57600 [2:51:21<7:13:19,  1.59it/s]
 28%|██▊       | 16308/57600 [2:51:22<7:07:13,  1.61it/s]
 28%|██▊       | 16309/57600 [2:51:22<7:25:07,  1.55it/s]
 28%|██▊       | 16310/57600 [2:51:23<7:42:45,  1.49it/s]
 28%|██▊       | 16311/57600 [2:51:24<7:27:03,  1.54it/s]
 28%|██▊       | 16312/57600 [2:51:24<7:30:22,  1.53it/s]
 28%|██▊       | 16313/57600 [2:51:25<7:15:43,  1.58it/s]
 28%|██▊       | 16314/57600 [2:51:26<7:20:58,  1.56it/s]
 28%|██▊       | 16315/57600 [2:51:26<7:33:55,  1.52it/s]
 28%|██▊       | 16316/57600 [2:51:27<7:21:28,  1.56it/s]
 28%|██▊       | 16317/57600 [2:51:27<7:17:05,  1.57it/s]
 28%|██▊       | 16318/57600 [2:51:28<7:11:51,  1.59it/s]
 28%|██▊       | 16319/57600 [2:51:29<7:23:10,  1.55it/s]
 28%|██▊       | 16320/57600 [2:51:29<7:16:45,  1.58it/s]
                                                         
{'loss': 1.2475, 'learning_rate': 7.472473867595818e-07, 'epoch': 180.13}

 28%|██▊       | 16320/57600 [2:51:29<7:16:45,  1.58it/s]
 28%|██▊       | 16321/57600 [2:51:30<7:01:02,  1.63it/s]
 28%|██▊       | 16322/57600 [2:51:31<7:10:02,  1.60it/s]
 28%|██▊       | 16323/57600 [2:51:31<6:59:34,  1.64it/s]
 28%|██▊       | 16324/57600 [2:51:32<7:04:34,  1.62it/s]
 28%|██▊       | 16325/57600 [2:51:32<7:05:37,  1.62it/s]
 28%|██▊       | 16326/57600 [2:51:33<7:01:26,  1.63it/s]
 28%|██▊       | 16327/57600 [2:51:34<7:02:55,  1.63it/s]
 28%|██▊       | 16328/57600 [2:51:34<6:55:54,  1.65it/s]
 28%|██▊       | 16329/57600 [2:51:35<7:02:40,  1.63it/s]
 28%|██▊       | 16330/57600 [2:51:36<7:27:25,  1.54it/s]
 28%|██▊       | 16331/57600 [2:51:36<7:21:21,  1.56it/s]
 28%|██▊       | 16332/57600 [2:51:37<7:15:39,  1.58it/s]
 28%|██▊       | 16333/57600 [2:51:37<6:59:38,  1.64it/s]
 28%|██▊       | 16334/57600 [2:51:38<6:58:55,  1.64it/s]
 28%|██▊       | 16335/57600 [2:51:39<6:51:55,  1.67it/s]
 28%|██▊       | 16336/57600 [2:51:39<6:50:20,  1.68it/s]
 28%|██▊       | 16337/57600 [2:51:40<6:56:29,  1.65it/s]
 28%|██▊       | 16338/57600 [2:51:40<6:49:33,  1.68it/s]
 28%|██▊       | 16339/57600 [2:51:41<6:59:55,  1.64it/s]
 28%|██▊       | 16340/57600 [2:51:42<7:01:48,  1.63it/s]
                                                         
{'loss': 1.2938, 'learning_rate': 7.469337979094077e-07, 'epoch': 180.35}

 28%|██▊       | 16340/57600 [2:51:42<7:01:48,  1.63it/s]
 28%|██▊       | 16341/57600 [2:51:42<6:58:36,  1.64it/s]
 28%|██▊       | 16342/57600 [2:51:43<6:52:39,  1.67it/s]
 28%|██▊       | 16343/57600 [2:51:43<6:54:34,  1.66it/s]
 28%|██▊       | 16344/57600 [2:51:44<6:53:31,  1.66it/s]
 28%|██▊       | 16345/57600 [2:51:45<6:53:41,  1.66it/s]
 28%|██▊       | 16346/57600 [2:51:45<6:51:36,  1.67it/s]
 28%|██▊       | 16347/57600 [2:51:46<6:58:44,  1.64it/s]
 28%|██▊       | 16348/57600 [2:51:46<6:59:43,  1.64it/s]
 28%|██▊       | 16349/57600 [2:51:47<7:30:43,  1.53it/s]
 28%|██▊       | 16350/57600 [2:51:48<7:19:49,  1.56it/s]
 28%|██▊       | 16351/57600 [2:51:48<7:22:17,  1.55it/s]
 28%|██▊       | 16352/57600 [2:51:49<7:25:27,  1.54it/s]
 28%|██▊       | 16353/57600 [2:51:50<7:39:36,  1.50it/s]
 28%|██▊       | 16354/57600 [2:51:51<7:34:21,  1.51it/s]
 28%|██▊       | 16355/57600 [2:51:51<7:24:07,  1.55it/s]
 28%|██▊       | 16356/57600 [2:51:52<7:20:00,  1.56it/s]
 28%|██▊       | 16357/57600 [2:51:52<7:21:04,  1.56it/s]
 28%|██▊       | 16358/57600 [2:51:53<7:11:26,  1.59it/s]
 28%|██▊       | 16359/57600 [2:51:54<7:17:56,  1.57it/s]
 28%|██▊       | 16360/57600 [2:51:54<7:21:23,  1.56it/s]
                                                         
{'loss': 1.28, 'learning_rate': 7.466202090592336e-07, 'epoch': 180.57}

 28%|██▊       | 16360/57600 [2:51:54<7:21:23,  1.56it/s]
 28%|██▊       | 16361/57600 [2:51:55<7:17:30,  1.57it/s]
 28%|██▊       | 16362/57600 [2:51:56<7:18:08,  1.57it/s]
 28%|██▊       | 16363/57600 [2:51:56<7:27:00,  1.54it/s]
 28%|██▊       | 16364/57600 [2:51:57<7:30:40,  1.52it/s]
 28%|██▊       | 16365/57600 [2:51:58<7:31:50,  1.52it/s]
 28%|██▊       | 16366/57600 [2:51:58<7:24:51,  1.54it/s]
 28%|██▊       | 16367/57600 [2:51:59<7:09:20,  1.60it/s]
 28%|██▊       | 16368/57600 [2:51:59<7:10:03,  1.60it/s]
 28%|██▊       | 16369/57600 [2:52:00<7:01:27,  1.63it/s]
 28%|██▊       | 16370/57600 [2:52:01<7:03:58,  1.62it/s]
 28%|██▊       | 16371/57600 [2:52:01<7:05:42,  1.61it/s]
 28%|██▊       | 16372/57600 [2:52:02<6:56:49,  1.65it/s]
 28%|██▊       | 16373/57600 [2:52:02<6:54:53,  1.66it/s]
 28%|██▊       | 16374/57600 [2:52:03<6:50:48,  1.67it/s]
 28%|██▊       | 16375/57600 [2:52:04<6:52:29,  1.67it/s]
 28%|██▊       | 16376/57600 [2:52:04<6:45:44,  1.69it/s]
 28%|██▊       | 16377/57600 [2:52:05<6:50:31,  1.67it/s]
 28%|██▊       | 16378/57600 [2:52:05<6:55:48,  1.65it/s]
 28%|██▊       | 16379/57600 [2:52:06<7:03:12,  1.62it/s]
 28%|██▊       | 16380/57600 [2:52:07<6:59:49,  1.64it/s]
                                                         
{'loss': 1.2954, 'learning_rate': 7.463066202090591e-07, 'epoch': 180.79}

 28%|██▊       | 16380/57600 [2:52:07<6:59:49,  1.64it/s]
 28%|██▊       | 16381/57600 [2:52:07<6:57:05,  1.65it/s]
 28%|██▊       | 16382/57600 [2:52:08<7:26:05,  1.54it/s]
 28%|██▊       | 16383/57600 [2:52:09<7:16:02,  1.58it/s]
 28%|██▊       | 16384/57600 [2:52:09<7:04:49,  1.62it/s]
 28%|██▊       | 16385/57600 [2:52:10<6:57:13,  1.65it/s]
 28%|██▊       | 16386/57600 [2:52:10<6:47:14,  1.69it/s]
 28%|██▊       | 16387/57600 [2:52:11<6:43:26,  1.70it/s]
 28%|██▊       | 16388/57600 [2:52:11<6:45:12,  1.70it/s]
 28%|██▊       | 16389/57600 [2:52:12<6:45:58,  1.69it/s]
 28%|██▊       | 16390/57600 [2:52:13<6:48:51,  1.68it/s]
 28%|██▊       | 16391/57600 [2:52:13<7:10:55,  1.59it/s]
 28%|██▊       | 16392/57600 [2:52:14<6:59:17,  1.64it/s]
 28%|██▊       | 16393/57600 [2:52:15<7:07:11,  1.61it/s]
 28%|██▊       | 16394/57600 [2:52:15<7:00:25,  1.63it/s]
 28%|██▊       | 16395/57600 [2:52:16<7:03:58,  1.62it/s]
 28%|██▊       | 16396/57600 [2:52:16<7:13:27,  1.58it/s]
 28%|██▊       | 16397/57600 [2:52:17<7:03:59,  1.62it/s]
 28%|██▊       | 16398/57600 [2:52:18<7:15:12,  1.58it/s]
 28%|██▊       | 16399/57600 [2:52:18<7:29:01,  1.53it/s]
 28%|██▊       | 16400/57600 [2:52:19<7:31:50,  1.52it/s]
                                                         
{'loss': 1.2661, 'learning_rate': 7.45993031358885e-07, 'epoch': 181.02}

 28%|██▊       | 16400/57600 [2:52:19<7:31:50,  1.52it/s]
 28%|██▊       | 16401/57600 [2:52:20<7:13:16,  1.58it/s]
 28%|██▊       | 16402/57600 [2:52:20<7:10:46,  1.59it/s]
 28%|██▊       | 16403/57600 [2:52:21<7:02:49,  1.62it/s]
 28%|██▊       | 16404/57600 [2:52:21<7:03:03,  1.62it/s]
 28%|██▊       | 16405/57600 [2:52:22<6:59:26,  1.64it/s]
 28%|██▊       | 16406/57600 [2:52:23<6:54:19,  1.66it/s]
 28%|██▊       | 16407/57600 [2:52:23<6:44:24,  1.70it/s]
 28%|██▊       | 16408/57600 [2:52:24<6:37:22,  1.73it/s]
 28%|██▊       | 16409/57600 [2:52:24<6:31:29,  1.75it/s]
 28%|██▊       | 16410/57600 [2:52:25<6:39:30,  1.72it/s]
 28%|██▊       | 16411/57600 [2:52:26<6:40:53,  1.71it/s]
 28%|██▊       | 16412/57600 [2:52:26<6:46:38,  1.69it/s]
 28%|██▊       | 16413/57600 [2:52:27<7:01:54,  1.63it/s]
 28%|██▊       | 16414/57600 [2:52:28<7:19:09,  1.56it/s]
 28%|██▊       | 16415/57600 [2:52:28<7:17:38,  1.57it/s]
 28%|██▊       | 16416/57600 [2:52:29<7:24:34,  1.54it/s]
 29%|██▊       | 16417/57600 [2:52:29<7:24:41,  1.54it/s]
 29%|██▊       | 16418/57600 [2:52:30<7:14:47,  1.58it/s]
 29%|██▊       | 16419/57600 [2:52:31<7:12:28,  1.59it/s]
 29%|██▊       | 16420/57600 [2:52:31<7:11:25,  1.59it/s]
                                                         
{'loss': 1.3225, 'learning_rate': 7.456794425087108e-07, 'epoch': 181.24}

 29%|██▊       | 16420/57600 [2:52:31<7:11:25,  1.59it/s]
 29%|██▊       | 16421/57600 [2:52:32<7:01:23,  1.63it/s]
 29%|██▊       | 16422/57600 [2:52:33<7:10:35,  1.59it/s]
 29%|██▊       | 16423/57600 [2:52:33<7:17:16,  1.57it/s]
 29%|██▊       | 16424/57600 [2:52:34<7:18:53,  1.56it/s]
 29%|██▊       | 16425/57600 [2:52:34<7:16:52,  1.57it/s]
 29%|██▊       | 16426/57600 [2:52:35<7:24:17,  1.54it/s]
 29%|██▊       | 16427/57600 [2:52:36<7:38:41,  1.50it/s]
 29%|██▊       | 16428/57600 [2:52:37<7:30:41,  1.52it/s]
 29%|██▊       | 16429/57600 [2:52:37<7:31:13,  1.52it/s]
 29%|██▊       | 16430/57600 [2:52:38<7:28:21,  1.53it/s]
 29%|██▊       | 16431/57600 [2:52:38<7:20:13,  1.56it/s]
 29%|██▊       | 16432/57600 [2:52:39<7:11:58,  1.59it/s]
 29%|██▊       | 16433/57600 [2:52:40<7:03:11,  1.62it/s]
 29%|██▊       | 16434/57600 [2:52:40<6:55:03,  1.65it/s]
 29%|██▊       | 16435/57600 [2:52:41<7:01:02,  1.63it/s]
 29%|██▊       | 16436/57600 [2:52:41<6:57:13,  1.64it/s]
 29%|██▊       | 16437/57600 [2:52:42<7:05:04,  1.61it/s]
 29%|██▊       | 16438/57600 [2:52:43<7:00:48,  1.63it/s]
 29%|██▊       | 16439/57600 [2:52:43<7:02:46,  1.62it/s]
 29%|██▊       | 16440/57600 [2:52:44<7:08:06,  1.60it/s]
                                                         
{'loss': 1.2522, 'learning_rate': 7.453658536585366e-07, 'epoch': 181.46}

 29%|██▊       | 16440/57600 [2:52:44<7:08:06,  1.60it/s]
 29%|██▊       | 16441/57600 [2:52:45<7:06:44,  1.61it/s]
 29%|██▊       | 16442/57600 [2:52:45<7:18:08,  1.57it/s]
 29%|██▊       | 16443/57600 [2:52:46<7:11:34,  1.59it/s]
 29%|██▊       | 16444/57600 [2:52:46<6:54:37,  1.65it/s]
 29%|██▊       | 16445/57600 [2:52:47<7:00:40,  1.63it/s]
 29%|██▊       | 16446/57600 [2:52:48<6:53:28,  1.66it/s]
 29%|██▊       | 16447/57600 [2:52:48<6:45:57,  1.69it/s]
 29%|██▊       | 16448/57600 [2:52:49<6:53:01,  1.66it/s]
 29%|██▊       | 16449/57600 [2:52:49<6:46:10,  1.69it/s]
 29%|██▊       | 16450/57600 [2:52:50<6:40:02,  1.71it/s]
 29%|██▊       | 16451/57600 [2:52:50<6:28:31,  1.77it/s]
 29%|██▊       | 16452/57600 [2:52:51<6:33:48,  1.74it/s]
 29%|██▊       | 16453/57600 [2:52:52<6:40:09,  1.71it/s]
 29%|██▊       | 16454/57600 [2:52:52<6:43:13,  1.70it/s]
 29%|██▊       | 16455/57600 [2:52:53<6:51:16,  1.67it/s]
 29%|██▊       | 16456/57600 [2:52:54<7:06:16,  1.61it/s]
 29%|██▊       | 16457/57600 [2:52:54<7:00:02,  1.63it/s]
 29%|██▊       | 16458/57600 [2:52:55<7:13:12,  1.58it/s]
 29%|██▊       | 16459/57600 [2:52:55<7:16:08,  1.57it/s]
 29%|██▊       | 16460/57600 [2:52:56<7:18:12,  1.56it/s]
                                                         
{'loss': 1.312, 'learning_rate': 7.450522648083623e-07, 'epoch': 181.68}

 29%|██▊       | 16460/57600 [2:52:56<7:18:12,  1.56it/s]
 29%|██▊       | 16461/57600 [2:52:57<7:11:16,  1.59it/s]
 29%|██▊       | 16462/57600 [2:52:57<7:18:52,  1.56it/s]
 29%|██▊       | 16463/57600 [2:52:58<7:07:12,  1.60it/s]
 29%|██▊       | 16464/57600 [2:52:59<6:57:32,  1.64it/s]
 29%|██▊       | 16465/57600 [2:52:59<6:49:42,  1.67it/s]
 29%|██▊       | 16466/57600 [2:53:00<6:58:54,  1.64it/s]
 29%|██▊       | 16467/57600 [2:53:00<7:05:13,  1.61it/s]
 29%|██▊       | 16468/57600 [2:53:01<7:41:09,  1.49it/s]
 29%|██▊       | 16469/57600 [2:53:02<7:31:20,  1.52it/s]
 29%|██▊       | 16470/57600 [2:53:02<7:26:34,  1.54it/s]
 29%|██▊       | 16471/57600 [2:53:03<7:26:27,  1.54it/s]
 29%|██▊       | 16472/57600 [2:53:04<7:14:28,  1.58it/s]
 29%|██▊       | 16473/57600 [2:53:04<7:14:55,  1.58it/s]
 29%|██▊       | 16474/57600 [2:53:05<7:00:11,  1.63it/s]
 29%|██▊       | 16475/57600 [2:53:06<7:06:23,  1.61it/s]
 29%|██▊       | 16476/57600 [2:53:06<7:14:17,  1.58it/s]
 29%|██▊       | 16477/57600 [2:53:07<7:06:13,  1.61it/s]
 29%|██▊       | 16478/57600 [2:53:07<7:03:07,  1.62it/s]
 29%|██▊       | 16479/57600 [2:53:08<6:58:48,  1.64it/s]
 29%|██▊       | 16480/57600 [2:53:09<7:07:04,  1.60it/s]
                                                         
{'loss': 1.2597, 'learning_rate': 7.447386759581882e-07, 'epoch': 181.9}

 29%|██▊       | 16480/57600 [2:53:09<7:07:04,  1.60it/s]
 29%|██▊       | 16481/57600 [2:53:09<7:10:59,  1.59it/s]
 29%|██▊       | 16482/57600 [2:53:10<7:21:13,  1.55it/s]
 29%|██▊       | 16483/57600 [2:53:11<7:19:15,  1.56it/s]
 29%|██▊       | 16484/57600 [2:53:11<7:20:59,  1.55it/s]
 29%|██▊       | 16485/57600 [2:53:12<7:12:34,  1.58it/s]
 29%|██▊       | 16486/57600 [2:53:13<7:20:56,  1.55it/s]
 29%|██▊       | 16487/57600 [2:53:13<7:18:01,  1.56it/s]
 29%|██▊       | 16488/57600 [2:53:14<7:22:36,  1.55it/s]
 29%|██▊       | 16489/57600 [2:53:14<7:13:38,  1.58it/s]
 29%|██▊       | 16490/57600 [2:53:15<7:18:49,  1.56it/s]
 29%|██▊       | 16491/57600 [2:53:16<7:17:09,  1.57it/s]
 29%|██▊       | 16492/57600 [2:53:16<7:17:01,  1.57it/s]
 29%|██▊       | 16493/57600 [2:53:17<7:16:43,  1.57it/s]
 29%|██▊       | 16494/57600 [2:53:18<7:22:06,  1.55it/s]
 29%|██▊       | 16495/57600 [2:53:18<7:03:39,  1.62it/s]
 29%|██▊       | 16496/57600 [2:53:19<7:08:21,  1.60it/s]
 29%|██▊       | 16497/57600 [2:53:19<6:59:54,  1.63it/s]
 29%|██▊       | 16498/57600 [2:53:20<7:06:10,  1.61it/s]
 29%|██▊       | 16499/57600 [2:53:21<7:00:53,  1.63it/s]
 29%|██▊       | 16500/57600 [2:53:21<7:04:54,  1.61it/s]
                                                         
{'loss': 1.3262, 'learning_rate': 7.444250871080139e-07, 'epoch': 182.12}

 29%|██▊       | 16500/57600 [2:53:21<7:04:54,  1.61it/s]
 29%|██▊       | 16501/57600 [2:53:22<7:10:18,  1.59it/s]
 29%|██▊       | 16502/57600 [2:53:23<7:23:31,  1.54it/s]
 29%|██▊       | 16503/57600 [2:53:23<7:27:55,  1.53it/s]
 29%|██▊       | 16504/57600 [2:53:24<7:06:44,  1.61it/s]
 29%|██▊       | 16505/57600 [2:53:24<7:02:44,  1.62it/s]
 29%|██▊       | 16506/57600 [2:53:25<7:05:19,  1.61it/s]
 29%|██▊       | 16507/57600 [2:53:26<7:07:14,  1.60it/s]
 29%|██▊       | 16508/57600 [2:53:26<7:08:14,  1.60it/s]
 29%|██▊       | 16509/57600 [2:53:27<7:15:42,  1.57it/s]
 29%|██▊       | 16510/57600 [2:53:28<7:00:50,  1.63it/s]
 29%|██▊       | 16511/57600 [2:53:28<6:59:48,  1.63it/s]
 29%|██▊       | 16512/57600 [2:53:29<6:53:07,  1.66it/s]
 29%|██▊       | 16513/57600 [2:53:29<6:59:35,  1.63it/s]
 29%|██▊       | 16514/57600 [2:53:30<6:56:21,  1.64it/s]
 29%|██▊       | 16515/57600 [2:53:31<6:46:39,  1.68it/s]
 29%|██▊       | 16516/57600 [2:53:31<6:44:54,  1.69it/s]
 29%|██▊       | 16517/57600 [2:53:32<6:41:13,  1.71it/s]
 29%|██▊       | 16518/57600 [2:53:32<6:36:30,  1.73it/s]
 29%|██▊       | 16519/57600 [2:53:33<6:36:46,  1.73it/s]
 29%|██▊       | 16520/57600 [2:53:33<6:34:39,  1.73it/s]
                                                         
{'loss': 1.3519, 'learning_rate': 7.441114982578397e-07, 'epoch': 182.34}

 29%|██▊       | 16520/57600 [2:53:33<6:34:39,  1.73it/s]
 29%|██▊       | 16521/57600 [2:53:34<6:59:11,  1.63it/s]
 29%|██▊       | 16522/57600 [2:53:35<7:06:22,  1.61it/s]
 29%|██▊       | 16523/57600 [2:53:35<7:17:03,  1.57it/s]
 29%|██▊       | 16524/57600 [2:53:36<7:19:51,  1.56it/s]
 29%|██▊       | 16525/57600 [2:53:37<7:22:53,  1.55it/s]
 29%|██▊       | 16526/57600 [2:53:37<7:40:36,  1.49it/s]
 29%|██▊       | 16527/57600 [2:53:38<7:41:36,  1.48it/s]
 29%|██▊       | 16528/57600 [2:53:39<7:14:29,  1.58it/s]
 29%|██▊       | 16529/57600 [2:53:39<7:03:00,  1.62it/s]
 29%|██▊       | 16530/57600 [2:53:40<7:00:18,  1.63it/s]
 29%|██▊       | 16531/57600 [2:53:41<7:03:26,  1.62it/s]
 29%|██▊       | 16532/57600 [2:53:41<7:17:06,  1.57it/s]
 29%|██▊       | 16533/57600 [2:53:42<7:07:02,  1.60it/s]
 29%|██▊       | 16534/57600 [2:53:42<7:13:58,  1.58it/s]
 29%|██▊       | 16535/57600 [2:53:43<7:12:03,  1.58it/s]
 29%|██▊       | 16536/57600 [2:53:44<7:01:12,  1.62it/s]
 29%|██▊       | 16537/57600 [2:53:44<7:08:31,  1.60it/s]
 29%|██▊       | 16538/57600 [2:53:45<7:06:30,  1.60it/s]
 29%|██▊       | 16539/57600 [2:53:46<7:18:56,  1.56it/s]
 29%|██▊       | 16540/57600 [2:53:46<7:20:32,  1.55it/s]
                                                         
{'loss': 1.2241, 'learning_rate': 7.437979094076654e-07, 'epoch': 182.56}

 29%|██▊       | 16540/57600 [2:53:46<7:20:32,  1.55it/s]
 29%|██▊       | 16541/57600 [2:53:47<7:19:02,  1.56it/s]
 29%|██▊       | 16542/57600 [2:53:47<7:06:28,  1.60it/s]
 29%|██▊       | 16543/57600 [2:53:48<7:17:59,  1.56it/s]
 29%|██▊       | 16544/57600 [2:53:49<7:04:11,  1.61it/s]
 29%|██▊       | 16545/57600 [2:53:49<6:57:24,  1.64it/s]
 29%|██▊       | 16546/57600 [2:53:50<6:53:44,  1.65it/s]
 29%|██▊       | 16547/57600 [2:53:51<6:58:14,  1.64it/s]
 29%|██▊       | 16548/57600 [2:53:51<6:48:46,  1.67it/s]
 29%|██▊       | 16549/57600 [2:53:52<6:49:07,  1.67it/s]
 29%|██▊       | 16550/57600 [2:53:52<7:00:40,  1.63it/s]
 29%|██▊       | 16551/57600 [2:53:53<6:56:26,  1.64it/s]
 29%|██▊       | 16552/57600 [2:53:54<7:02:05,  1.62it/s]
 29%|██▊       | 16553/57600 [2:53:54<6:43:55,  1.69it/s]
 29%|██▊       | 16554/57600 [2:53:55<7:01:30,  1.62it/s]
 29%|██▊       | 16555/57600 [2:53:55<6:53:15,  1.66it/s]
 29%|██▊       | 16556/57600 [2:53:56<7:08:19,  1.60it/s]
 29%|██▊       | 16557/57600 [2:53:57<7:10:27,  1.59it/s]
 29%|██▊       | 16558/57600 [2:53:57<7:04:04,  1.61it/s]
 29%|██▊       | 16559/57600 [2:53:58<7:18:43,  1.56it/s]
 29%|██▉       | 16560/57600 [2:53:59<7:17:30,  1.56it/s]
                                                         
{'loss': 1.3083, 'learning_rate': 7.434843205574913e-07, 'epoch': 182.78}

 29%|██▉       | 16560/57600 [2:53:59<7:17:30,  1.56it/s]
 29%|██▉       | 16561/57600 [2:53:59<7:18:15,  1.56it/s]
 29%|██▉       | 16562/57600 [2:54:00<7:14:42,  1.57it/s]
 29%|██▉       | 16563/57600 [2:54:00<7:01:02,  1.62it/s]
 29%|██▉       | 16564/57600 [2:54:01<7:10:07,  1.59it/s]
 29%|██▉       | 16565/57600 [2:54:02<7:13:49,  1.58it/s]
 29%|██▉       | 16566/57600 [2:54:02<7:28:03,  1.53it/s]
 29%|██▉       | 16567/57600 [2:54:03<7:13:32,  1.58it/s]
 29%|██▉       | 16568/57600 [2:54:04<7:02:58,  1.62it/s]
 29%|██▉       | 16569/57600 [2:54:04<7:06:42,  1.60it/s]
 29%|██▉       | 16570/57600 [2:54:05<6:57:45,  1.64it/s]
 29%|██▉       | 16571/57600 [2:54:06<7:14:25,  1.57it/s]
 29%|██▉       | 16572/57600 [2:54:06<7:24:16,  1.54it/s]
 29%|██▉       | 16573/57600 [2:54:07<7:11:34,  1.58it/s]
 29%|██▉       | 16574/57600 [2:54:07<7:07:41,  1.60it/s]
 29%|██▉       | 16575/57600 [2:54:08<7:00:02,  1.63it/s]
 29%|██▉       | 16576/57600 [2:54:09<6:54:31,  1.65it/s]
 29%|██▉       | 16577/57600 [2:54:09<6:51:29,  1.66it/s]
 29%|██▉       | 16578/57600 [2:54:10<6:57:24,  1.64it/s]
 29%|██▉       | 16579/57600 [2:54:10<6:58:00,  1.64it/s]
 29%|██▉       | 16580/57600 [2:54:11<7:07:36,  1.60it/s]
                                                         
{'loss': 1.2853, 'learning_rate': 7.43170731707317e-07, 'epoch': 183.0}

 29%|██▉       | 16580/57600 [2:54:11<7:07:36,  1.60it/s]
 29%|██▉       | 16581/57600 [2:54:12<7:08:14,  1.60it/s]
 29%|██▉       | 16582/57600 [2:54:12<7:15:42,  1.57it/s]
 29%|██▉       | 16583/57600 [2:54:13<7:11:01,  1.59it/s]
 29%|██▉       | 16584/57600 [2:54:14<7:01:07,  1.62it/s]
 29%|██▉       | 16585/57600 [2:54:14<6:53:35,  1.65it/s]
 29%|██▉       | 16586/57600 [2:54:15<7:02:02,  1.62it/s]
 29%|██▉       | 16587/57600 [2:54:15<7:02:03,  1.62it/s]
 29%|██▉       | 16588/57600 [2:54:16<6:53:12,  1.65it/s]
 29%|██▉       | 16589/57600 [2:54:17<7:07:30,  1.60it/s]
 29%|██▉       | 16590/57600 [2:54:17<6:57:55,  1.64it/s]
 29%|██▉       | 16591/57600 [2:54:18<6:45:09,  1.69it/s]
 29%|██▉       | 16592/57600 [2:54:18<6:49:41,  1.67it/s]
 29%|██▉       | 16593/57600 [2:54:19<7:12:27,  1.58it/s]
 29%|██▉       | 16594/57600 [2:54:20<7:04:05,  1.61it/s]
 29%|██▉       | 16595/57600 [2:54:20<7:03:11,  1.61it/s]
 29%|██▉       | 16596/57600 [2:54:21<6:56:54,  1.64it/s]
 29%|██▉       | 16597/57600 [2:54:22<6:59:40,  1.63it/s]
 29%|██▉       | 16598/57600 [2:54:22<6:57:27,  1.64it/s]
 29%|██▉       | 16599/57600 [2:54:23<6:54:36,  1.65it/s]
 29%|██▉       | 16600/57600 [2:54:23<6:57:12,  1.64it/s]
                                                         
{'loss': 1.3211, 'learning_rate': 7.428571428571427e-07, 'epoch': 183.22}

 29%|██▉       | 16600/57600 [2:54:23<6:57:12,  1.64it/s]
 29%|██▉       | 16601/57600 [2:54:24<7:13:11,  1.58it/s]
 29%|██▉       | 16602/57600 [2:54:25<7:23:26,  1.54it/s]
 29%|██▉       | 16603/57600 [2:54:25<7:18:16,  1.56it/s]
 29%|██▉       | 16604/57600 [2:54:26<7:30:28,  1.52it/s]
 29%|██▉       | 16605/57600 [2:54:27<7:15:09,  1.57it/s]
 29%|██▉       | 16606/57600 [2:54:27<7:08:40,  1.59it/s]
 29%|██▉       | 16607/57600 [2:54:28<6:58:23,  1.63it/s]
 29%|██▉       | 16608/57600 [2:54:28<6:46:44,  1.68it/s]
 29%|██▉       | 16609/57600 [2:54:29<6:53:52,  1.65it/s]
 29%|██▉       | 16610/57600 [2:54:30<7:01:49,  1.62it/s]
 29%|██▉       | 16611/57600 [2:54:30<7:18:11,  1.56it/s]
 29%|██▉       | 16612/57600 [2:54:31<7:23:38,  1.54it/s]
 29%|██▉       | 16613/57600 [2:54:32<7:15:13,  1.57it/s]
 29%|██▉       | 16614/57600 [2:54:32<7:18:57,  1.56it/s]
 29%|██▉       | 16615/57600 [2:54:33<7:02:48,  1.62it/s]
 29%|██▉       | 16616/57600 [2:54:33<7:07:55,  1.60it/s]
 29%|██▉       | 16617/57600 [2:54:34<7:10:06,  1.59it/s]
 29%|██▉       | 16618/57600 [2:54:35<7:15:43,  1.57it/s]
 29%|██▉       | 16619/57600 [2:54:35<7:13:36,  1.58it/s]
 29%|██▉       | 16620/57600 [2:54:36<7:19:39,  1.55it/s]
                                                         
{'loss': 1.2444, 'learning_rate': 7.425435540069687e-07, 'epoch': 183.44}

 29%|██▉       | 16620/57600 [2:54:36<7:19:39,  1.55it/s]
 29%|██▉       | 16621/57600 [2:54:37<7:05:55,  1.60it/s]
 29%|██▉       | 16622/57600 [2:54:37<6:53:05,  1.65it/s]
 29%|██▉       | 16623/57600 [2:54:38<6:56:42,  1.64it/s]
 29%|██▉       | 16624/57600 [2:54:38<6:51:08,  1.66it/s]
 29%|██▉       | 16625/57600 [2:54:39<6:50:32,  1.66it/s]
 29%|██▉       | 16626/57600 [2:54:40<7:11:19,  1.58it/s]
 29%|██▉       | 16627/57600 [2:54:40<7:03:28,  1.61it/s]
 29%|██▉       | 16628/57600 [2:54:41<7:10:29,  1.59it/s]
 29%|██▉       | 16629/57600 [2:54:42<7:20:36,  1.55it/s]
 29%|██▉       | 16630/57600 [2:54:42<7:19:25,  1.55it/s]
 29%|██▉       | 16631/57600 [2:54:43<7:14:50,  1.57it/s]
 29%|██▉       | 16632/57600 [2:54:43<7:03:35,  1.61it/s]
 29%|██▉       | 16633/57600 [2:54:44<6:56:16,  1.64it/s]
 29%|██▉       | 16634/57600 [2:54:45<6:52:19,  1.66it/s]
 29%|██▉       | 16635/57600 [2:54:45<7:00:50,  1.62it/s]
 29%|██▉       | 16636/57600 [2:54:46<6:58:56,  1.63it/s]
 29%|██▉       | 16637/57600 [2:54:47<7:03:10,  1.61it/s]
 29%|██▉       | 16638/57600 [2:54:47<7:13:37,  1.57it/s]
 29%|██▉       | 16639/57600 [2:54:48<7:18:51,  1.56it/s]
 29%|██▉       | 16640/57600 [2:54:48<6:58:17,  1.63it/s]
                                                         
{'loss': 1.2557, 'learning_rate': 7.422299651567944e-07, 'epoch': 183.66}

 29%|██▉       | 16640/57600 [2:54:48<6:58:17,  1.63it/s]
 29%|██▉       | 16641/57600 [2:54:49<6:53:13,  1.65it/s]
 29%|██▉       | 16642/57600 [2:54:50<6:59:30,  1.63it/s]
 29%|██▉       | 16643/57600 [2:54:50<6:55:12,  1.64it/s]
 29%|██▉       | 16644/57600 [2:54:51<6:57:04,  1.64it/s]
 29%|██▉       | 16645/57600 [2:54:52<7:03:45,  1.61it/s]
 29%|██▉       | 16646/57600 [2:54:52<7:00:02,  1.62it/s]
 29%|██▉       | 16647/57600 [2:54:53<7:06:24,  1.60it/s]
 29%|██▉       | 16648/57600 [2:54:53<7:00:30,  1.62it/s]
 29%|██▉       | 16649/57600 [2:54:54<6:52:09,  1.66it/s]
 29%|██▉       | 16650/57600 [2:54:55<6:53:46,  1.65it/s]
 29%|██▉       | 16651/57600 [2:54:55<6:57:40,  1.63it/s]
 29%|██▉       | 16652/57600 [2:54:56<6:55:27,  1.64it/s]
 29%|██▉       | 16653/57600 [2:54:56<6:58:09,  1.63it/s]
 29%|██▉       | 16654/57600 [2:54:57<6:46:16,  1.68it/s]
 29%|██▉       | 16655/57600 [2:54:58<7:07:57,  1.59it/s]
 29%|██▉       | 16656/57600 [2:54:58<6:59:59,  1.62it/s]
 29%|██▉       | 16657/57600 [2:54:59<6:59:31,  1.63it/s]
 29%|██▉       | 16658/57600 [2:54:59<6:57:44,  1.63it/s]
 29%|██▉       | 16659/57600 [2:55:00<7:01:33,  1.62it/s]
 29%|██▉       | 16660/57600 [2:55:01<7:08:28,  1.59it/s]
                                                         
{'loss': 1.249, 'learning_rate': 7.419163763066202e-07, 'epoch': 183.89}

 29%|██▉       | 16660/57600 [2:55:01<7:08:28,  1.59it/s]
 29%|██▉       | 16661/57600 [2:55:01<7:11:10,  1.58it/s]
 29%|██▉       | 16662/57600 [2:55:02<7:13:00,  1.58it/s]
 29%|██▉       | 16663/57600 [2:55:03<7:27:01,  1.53it/s]
 29%|██▉       | 16664/57600 [2:55:03<7:41:23,  1.48it/s]
 29%|██▉       | 16665/57600 [2:55:04<7:36:30,  1.49it/s]
 29%|██▉       | 16666/57600 [2:55:05<7:42:23,  1.48it/s]
 29%|██▉       | 16667/57600 [2:55:05<7:30:31,  1.51it/s]
 29%|██▉       | 16668/57600 [2:55:06<7:37:40,  1.49it/s]
 29%|██▉       | 16669/57600 [2:55:07<7:28:25,  1.52it/s]
 29%|██▉       | 16670/57600 [2:55:07<7:18:48,  1.55it/s]
 29%|██▉       | 16671/57600 [2:55:08<7:30:20,  1.51it/s]
 29%|██▉       | 16672/57600 [2:55:09<7:27:39,  1.52it/s]
 29%|██▉       | 16673/57600 [2:55:09<7:22:10,  1.54it/s]
 29%|██▉       | 16674/57600 [2:55:10<7:15:04,  1.57it/s]
 29%|██▉       | 16675/57600 [2:55:11<7:06:31,  1.60it/s]
 29%|██▉       | 16676/57600 [2:55:11<7:07:43,  1.59it/s]
 29%|██▉       | 16677/57600 [2:55:12<7:01:43,  1.62it/s]
 29%|██▉       | 16678/57600 [2:55:12<7:03:12,  1.61it/s]
 29%|██▉       | 16679/57600 [2:55:13<7:04:43,  1.61it/s]
 29%|██▉       | 16680/57600 [2:55:14<6:55:06,  1.64it/s]
                                                         
{'loss': 1.2379, 'learning_rate': 7.416027874564459e-07, 'epoch': 184.11}

 29%|██▉       | 16680/57600 [2:55:14<6:55:06,  1.64it/s]
 29%|██▉       | 16681/57600 [2:55:14<7:21:04,  1.55it/s]
 29%|██▉       | 16682/57600 [2:55:15<7:03:42,  1.61it/s]
 29%|██▉       | 16683/57600 [2:55:15<6:59:31,  1.63it/s]
 29%|██▉       | 16684/57600 [2:55:16<7:05:42,  1.60it/s]
 29%|██▉       | 16685/57600 [2:55:17<6:55:00,  1.64it/s]
 29%|██▉       | 16686/57600 [2:55:17<6:57:30,  1.63it/s]
 29%|██▉       | 16687/57600 [2:55:18<7:08:10,  1.59it/s]
 29%|██▉       | 16688/57600 [2:55:19<7:18:15,  1.56it/s]
 29%|██▉       | 16689/57600 [2:55:19<7:04:48,  1.61it/s]
 29%|██▉       | 16690/57600 [2:55:20<7:19:15,  1.55it/s]
 29%|██▉       | 16691/57600 [2:55:21<7:29:02,  1.52it/s]
 29%|██▉       | 16692/57600 [2:55:21<7:33:23,  1.50it/s]
 29%|██▉       | 16693/57600 [2:55:22<7:25:33,  1.53it/s]
 29%|██▉       | 16694/57600 [2:55:23<7:09:00,  1.59it/s]
 29%|██▉       | 16695/57600 [2:55:23<7:11:25,  1.58it/s]
 29%|██▉       | 16696/57600 [2:55:24<6:56:28,  1.64it/s]
 29%|██▉       | 16697/57600 [2:55:24<7:02:52,  1.61it/s]
 29%|██▉       | 16698/57600 [2:55:25<7:16:33,  1.56it/s]
 29%|██▉       | 16699/57600 [2:55:26<7:02:07,  1.61it/s]
 29%|██▉       | 16700/57600 [2:55:26<7:09:12,  1.59it/s]
                                                         
{'loss': 1.2756, 'learning_rate': 7.412891986062718e-07, 'epoch': 184.33}

 29%|██▉       | 16700/57600 [2:55:26<7:09:12,  1.59it/s]
 29%|██▉       | 16701/57600 [2:55:27<6:56:21,  1.64it/s]
 29%|██▉       | 16702/57600 [2:55:27<7:00:56,  1.62it/s]
 29%|██▉       | 16703/57600 [2:55:28<6:59:05,  1.63it/s]
 29%|██▉       | 16704/57600 [2:55:29<7:08:38,  1.59it/s]
 29%|██▉       | 16705/57600 [2:55:29<7:07:55,  1.59it/s]
 29%|██▉       | 16706/57600 [2:55:30<7:26:03,  1.53it/s]
 29%|██▉       | 16707/57600 [2:55:31<7:13:13,  1.57it/s]
 29%|██▉       | 16708/57600 [2:55:31<7:05:57,  1.60it/s]
 29%|██▉       | 16709/57600 [2:55:32<7:07:07,  1.60it/s]
 29%|██▉       | 16710/57600 [2:55:33<7:07:00,  1.60it/s]
 29%|██▉       | 16711/57600 [2:55:33<7:11:44,  1.58it/s]
 29%|██▉       | 16712/57600 [2:55:34<7:11:12,  1.58it/s]
 29%|██▉       | 16713/57600 [2:55:34<7:04:52,  1.60it/s]
 29%|██▉       | 16714/57600 [2:55:35<6:59:27,  1.62it/s]
 29%|██▉       | 16715/57600 [2:55:36<6:59:17,  1.63it/s]
 29%|██▉       | 16716/57600 [2:55:36<7:09:01,  1.59it/s]
 29%|██▉       | 16717/57600 [2:55:37<7:21:08,  1.54it/s]
 29%|██▉       | 16718/57600 [2:55:38<7:14:02,  1.57it/s]
 29%|██▉       | 16719/57600 [2:55:38<7:20:12,  1.55it/s]
 29%|██▉       | 16720/57600 [2:55:39<7:09:42,  1.59it/s]
                                                         
{'loss': 1.2827, 'learning_rate': 7.409756097560975e-07, 'epoch': 184.55}

 29%|██▉       | 16720/57600 [2:55:39<7:09:42,  1.59it/s]
 29%|██▉       | 16721/57600 [2:55:39<7:03:09,  1.61it/s]
 29%|██▉       | 16722/57600 [2:55:40<7:03:27,  1.61it/s]
 29%|██▉       | 16723/57600 [2:55:41<6:56:19,  1.64it/s]
 29%|██▉       | 16724/57600 [2:55:41<7:14:50,  1.57it/s]
 29%|██▉       | 16725/57600 [2:55:42<7:07:21,  1.59it/s]
 29%|██▉       | 16726/57600 [2:55:43<6:53:47,  1.65it/s]
 29%|██▉       | 16727/57600 [2:55:43<7:00:09,  1.62it/s]
 29%|██▉       | 16728/57600 [2:55:44<6:51:26,  1.66it/s]
 29%|██▉       | 16729/57600 [2:55:44<6:59:43,  1.62it/s]
 29%|██▉       | 16730/57600 [2:55:45<7:14:31,  1.57it/s]
 29%|██▉       | 16731/57600 [2:55:46<7:02:22,  1.61it/s]
 29%|██▉       | 16732/57600 [2:55:46<7:04:15,  1.61it/s]
 29%|██▉       | 16733/57600 [2:55:47<7:06:52,  1.60it/s]
 29%|██▉       | 16734/57600 [2:55:47<6:54:37,  1.64it/s]
 29%|██▉       | 16735/57600 [2:55:48<7:04:08,  1.61it/s]
 29%|██▉       | 16736/57600 [2:55:49<7:00:52,  1.62it/s]
 29%|██▉       | 16737/57600 [2:55:49<7:19:50,  1.55it/s]
 29%|██▉       | 16738/57600 [2:55:50<7:11:00,  1.58it/s]
 29%|██▉       | 16739/57600 [2:55:51<7:00:19,  1.62it/s]
 29%|██▉       | 16740/57600 [2:55:51<6:45:14,  1.68it/s]
                                                         
{'loss': 1.2726, 'learning_rate': 7.406620209059234e-07, 'epoch': 184.77}

 29%|██▉       | 16740/57600 [2:55:51<6:45:14,  1.68it/s]
 29%|██▉       | 16741/57600 [2:55:52<6:47:18,  1.67it/s]
 29%|██▉       | 16742/57600 [2:55:52<7:03:26,  1.61it/s]
 29%|██▉       | 16743/57600 [2:55:53<6:59:34,  1.62it/s]
 29%|██▉       | 16744/57600 [2:55:54<6:58:18,  1.63it/s]
 29%|██▉       | 16745/57600 [2:55:54<6:52:03,  1.65it/s]
 29%|██▉       | 16746/57600 [2:55:55<6:44:36,  1.68it/s]
 29%|██▉       | 16747/57600 [2:55:55<7:01:07,  1.62it/s]
 29%|██▉       | 16748/57600 [2:55:56<6:56:42,  1.63it/s]
 29%|██▉       | 16749/57600 [2:55:57<7:06:04,  1.60it/s]
 29%|██▉       | 16750/57600 [2:55:57<6:58:41,  1.63it/s]
 29%|██▉       | 16751/57600 [2:55:58<7:03:16,  1.61it/s]
 29%|██▉       | 16752/57600 [2:55:59<6:59:35,  1.62it/s]
 29%|██▉       | 16753/57600 [2:55:59<6:51:04,  1.66it/s]
 29%|██▉       | 16754/57600 [2:56:00<7:11:03,  1.58it/s]
 29%|██▉       | 16755/57600 [2:56:00<7:03:26,  1.61it/s]
 29%|██▉       | 16756/57600 [2:56:01<7:04:32,  1.60it/s]
 29%|██▉       | 16757/57600 [2:56:02<7:15:11,  1.56it/s]
 29%|██▉       | 16758/57600 [2:56:02<7:10:48,  1.58it/s]
 29%|██▉       | 16759/57600 [2:56:03<7:07:33,  1.59it/s]
 29%|██▉       | 16760/57600 [2:56:04<7:02:21,  1.61it/s]
                                                         
{'loss': 1.298, 'learning_rate': 7.403484320557491e-07, 'epoch': 184.99}

 29%|██▉       | 16760/57600 [2:56:04<7:02:21,  1.61it/s]
 29%|██▉       | 16761/57600 [2:56:04<7:10:52,  1.58it/s]
 29%|██▉       | 16762/57600 [2:56:05<7:13:56,  1.57it/s]
 29%|██▉       | 16763/57600 [2:56:06<7:14:31,  1.57it/s]
 29%|██▉       | 16764/57600 [2:56:06<7:25:42,  1.53it/s]
 29%|██▉       | 16765/57600 [2:56:07<7:10:45,  1.58it/s]
 29%|██▉       | 16766/57600 [2:56:08<7:31:07,  1.51it/s]
 29%|██▉       | 16767/57600 [2:56:08<7:39:50,  1.48it/s]
 29%|██▉       | 16768/57600 [2:56:09<7:21:58,  1.54it/s]
 29%|██▉       | 16769/57600 [2:56:09<7:02:49,  1.61it/s]
 29%|██▉       | 16770/57600 [2:56:10<6:56:04,  1.64it/s]
 29%|██▉       | 16771/57600 [2:56:11<6:46:03,  1.68it/s]
 29%|██▉       | 16772/57600 [2:56:11<6:49:06,  1.66it/s]
 29%|██▉       | 16773/57600 [2:56:12<6:54:39,  1.64it/s]
 29%|██▉       | 16774/57600 [2:56:12<7:13:08,  1.57it/s]
 29%|██▉       | 16775/57600 [2:56:13<7:11:06,  1.58it/s]
 29%|██▉       | 16776/57600 [2:56:14<7:06:40,  1.59it/s]
 29%|██▉       | 16777/57600 [2:56:14<7:14:53,  1.56it/s]
 29%|██▉       | 16778/57600 [2:56:15<7:14:12,  1.57it/s]
 29%|██▉       | 16779/57600 [2:56:16<7:11:26,  1.58it/s]
 29%|██▉       | 16780/57600 [2:56:16<7:11:27,  1.58it/s]
                                                         
{'loss': 1.2739, 'learning_rate': 7.400348432055749e-07, 'epoch': 185.21}

 29%|██▉       | 16780/57600 [2:56:16<7:11:27,  1.58it/s]
 29%|██▉       | 16781/57600 [2:56:17<7:01:56,  1.61it/s]
 29%|██▉       | 16782/57600 [2:56:17<6:57:03,  1.63it/s]
 29%|██▉       | 16783/57600 [2:56:18<6:59:15,  1.62it/s]
 29%|██▉       | 16784/57600 [2:56:19<7:05:16,  1.60it/s]
 29%|██▉       | 16785/57600 [2:56:19<7:16:20,  1.56it/s]
 29%|██▉       | 16786/57600 [2:56:20<7:13:09,  1.57it/s]
 29%|██▉       | 16787/57600 [2:56:21<7:14:25,  1.57it/s]
 29%|██▉       | 16788/57600 [2:56:21<7:01:45,  1.61it/s]
 29%|██▉       | 16789/57600 [2:56:22<6:53:38,  1.64it/s]
 29%|██▉       | 16790/57600 [2:56:22<6:49:15,  1.66it/s]
 29%|██▉       | 16791/57600 [2:56:23<6:46:13,  1.67it/s]
 29%|██▉       | 16792/57600 [2:56:24<6:57:28,  1.63it/s]
 29%|██▉       | 16793/57600 [2:56:24<7:01:50,  1.61it/s]
 29%|██▉       | 16794/57600 [2:56:25<6:54:07,  1.64it/s]
 29%|██▉       | 16795/57600 [2:56:26<7:01:42,  1.61it/s]
 29%|██▉       | 16796/57600 [2:56:26<6:53:26,  1.64it/s]
 29%|██▉       | 16797/57600 [2:56:27<6:56:02,  1.63it/s]
 29%|██▉       | 16798/57600 [2:56:27<7:06:55,  1.59it/s]
 29%|██▉       | 16799/57600 [2:56:28<7:05:25,  1.60it/s]
 29%|██▉       | 16800/57600 [2:56:29<6:56:20,  1.63it/s]
                                                         
{'loss': 1.2657, 'learning_rate': 7.397212543554006e-07, 'epoch': 185.43}

 29%|██▉       | 16800/57600 [2:56:29<6:56:20,  1.63it/s]
 29%|██▉       | 16801/57600 [2:56:29<6:52:18,  1.65it/s]
 29%|██▉       | 16802/57600 [2:56:30<6:59:56,  1.62it/s]
 29%|██▉       | 16803/57600 [2:56:30<6:55:22,  1.64it/s]
 29%|██▉       | 16804/57600 [2:56:31<6:55:06,  1.64it/s]
 29%|██▉       | 16805/57600 [2:56:32<6:53:56,  1.64it/s]
 29%|██▉       | 16806/57600 [2:56:32<7:04:37,  1.60it/s]
 29%|██▉       | 16807/57600 [2:56:33<7:01:44,  1.61it/s]
 29%|██▉       | 16808/57600 [2:56:34<7:06:42,  1.59it/s]
 29%|██▉       | 16809/57600 [2:56:34<7:21:11,  1.54it/s]
 29%|██▉       | 16810/57600 [2:56:35<7:14:31,  1.56it/s]
 29%|██▉       | 16811/57600 [2:56:35<7:04:34,  1.60it/s]
 29%|██▉       | 16812/57600 [2:56:36<7:09:26,  1.58it/s]
 29%|██▉       | 16813/57600 [2:56:37<7:16:31,  1.56it/s]
 29%|██▉       | 16814/57600 [2:56:37<7:02:08,  1.61it/s]
 29%|██▉       | 16815/57600 [2:56:38<6:49:44,  1.66it/s]
 29%|██▉       | 16816/57600 [2:56:39<6:51:30,  1.65it/s]
 29%|██▉       | 16817/57600 [2:56:39<7:05:08,  1.60it/s]
 29%|██▉       | 16818/57600 [2:56:40<6:53:49,  1.64it/s]
 29%|██▉       | 16819/57600 [2:56:40<6:56:46,  1.63it/s]
 29%|██▉       | 16820/57600 [2:56:41<7:07:19,  1.59it/s]
                                                         
{'loss': 1.2605, 'learning_rate': 7.394076655052264e-07, 'epoch': 185.65}

 29%|██▉       | 16820/57600 [2:56:41<7:07:19,  1.59it/s]
 29%|██▉       | 16821/57600 [2:56:42<6:57:49,  1.63it/s]
 29%|██▉       | 16822/57600 [2:56:42<6:56:43,  1.63it/s]
 29%|██▉       | 16823/57600 [2:56:43<6:47:30,  1.67it/s]
 29%|██▉       | 16824/57600 [2:56:43<6:41:32,  1.69it/s]
 29%|██▉       | 16825/57600 [2:56:44<7:01:46,  1.61it/s]
 29%|██▉       | 16826/57600 [2:56:45<7:00:30,  1.62it/s]
 29%|██▉       | 16827/57600 [2:56:45<7:09:09,  1.58it/s]
 29%|██▉       | 16828/57600 [2:56:46<7:03:46,  1.60it/s]
 29%|██▉       | 16829/57600 [2:56:47<7:09:37,  1.58it/s]
 29%|██▉       | 16830/57600 [2:56:47<7:01:04,  1.61it/s]
 29%|██▉       | 16831/57600 [2:56:48<7:16:17,  1.56it/s]
 29%|██▉       | 16832/57600 [2:56:49<7:19:16,  1.55it/s]
 29%|██▉       | 16833/57600 [2:56:49<7:22:26,  1.54it/s]
 29%|██▉       | 16834/57600 [2:56:50<7:05:55,  1.60it/s]
 29%|██▉       | 16835/57600 [2:56:50<7:00:28,  1.62it/s]
 29%|██▉       | 16836/57600 [2:56:51<7:02:42,  1.61it/s]
 29%|██▉       | 16837/57600 [2:56:52<6:57:05,  1.63it/s]
 29%|██▉       | 16838/57600 [2:56:52<7:09:48,  1.58it/s]
 29%|██▉       | 16839/57600 [2:56:53<7:14:33,  1.56it/s]
 29%|██▉       | 16840/57600 [2:56:54<7:05:17,  1.60it/s]
                                                         
{'loss': 1.2664, 'learning_rate': 7.390940766550522e-07, 'epoch': 185.87}

 29%|██▉       | 16840/57600 [2:56:54<7:05:17,  1.60it/s]
 29%|██▉       | 16841/57600 [2:56:54<7:09:07,  1.58it/s]
 29%|██▉       | 16842/57600 [2:56:55<7:04:31,  1.60it/s]
 29%|██▉       | 16843/57600 [2:56:55<6:49:15,  1.66it/s]
 29%|██▉       | 16844/57600 [2:56:56<7:04:15,  1.60it/s]
 29%|██▉       | 16845/57600 [2:56:57<7:03:47,  1.60it/s]
 29%|██▉       | 16846/57600 [2:56:57<7:00:04,  1.62it/s]
 29%|██▉       | 16847/57600 [2:56:58<7:03:39,  1.60it/s]
 29%|██▉       | 16848/57600 [2:56:58<6:49:47,  1.66it/s]
 29%|██▉       | 16849/57600 [2:56:59<6:43:33,  1.68it/s]
 29%|██▉       | 16850/57600 [2:57:00<6:35:27,  1.72it/s]
 29%|██▉       | 16851/57600 [2:57:00<6:35:59,  1.72it/s]
 29%|██▉       | 16852/57600 [2:57:01<7:05:24,  1.60it/s]
 29%|██▉       | 16853/57600 [2:57:02<7:13:23,  1.57it/s]
 29%|██▉       | 16854/57600 [2:57:02<7:06:37,  1.59it/s]
 29%|██▉       | 16855/57600 [2:57:03<7:04:27,  1.60it/s]
 29%|██▉       | 16856/57600 [2:57:03<7:09:46,  1.58it/s]
 29%|██▉       | 16857/57600 [2:57:04<7:05:12,  1.60it/s]
 29%|██▉       | 16858/57600 [2:57:05<7:04:23,  1.60it/s]
 29%|██▉       | 16859/57600 [2:57:05<7:00:53,  1.61it/s]
 29%|██▉       | 16860/57600 [2:57:06<7:02:30,  1.61it/s]
                                                         
{'loss': 1.278, 'learning_rate': 7.38780487804878e-07, 'epoch': 186.09}

 29%|██▉       | 16860/57600 [2:57:06<7:02:30,  1.61it/s]
 29%|██▉       | 16861/57600 [2:57:07<7:03:37,  1.60it/s]
 29%|██▉       | 16862/57600 [2:57:07<7:00:07,  1.62it/s]
 29%|██▉       | 16863/57600 [2:57:08<7:05:42,  1.59it/s]
 29%|██▉       | 16864/57600 [2:57:08<7:07:06,  1.59it/s]
 29%|██▉       | 16865/57600 [2:57:09<7:25:04,  1.53it/s]
 29%|██▉       | 16866/57600 [2:57:10<7:08:35,  1.58it/s]
 29%|██▉       | 16867/57600 [2:57:10<7:18:21,  1.55it/s]
 29%|██▉       | 16868/57600 [2:57:11<7:23:34,  1.53it/s]
 29%|██▉       | 16869/57600 [2:57:12<7:22:18,  1.53it/s]
 29%|██▉       | 16870/57600 [2:57:12<7:16:12,  1.56it/s]
 29%|██▉       | 16871/57600 [2:57:13<7:12:13,  1.57it/s]
 29%|██▉       | 16872/57600 [2:57:14<7:21:05,  1.54it/s]
 29%|██▉       | 16873/57600 [2:57:14<7:07:42,  1.59it/s]
 29%|██▉       | 16874/57600 [2:57:15<7:00:20,  1.61it/s]
 29%|██▉       | 16875/57600 [2:57:15<6:50:32,  1.65it/s]
 29%|██▉       | 16876/57600 [2:57:16<6:51:14,  1.65it/s]
 29%|██▉       | 16877/57600 [2:57:17<6:50:05,  1.66it/s]
 29%|██▉       | 16878/57600 [2:57:17<6:54:06,  1.64it/s]
 29%|██▉       | 16879/57600 [2:57:18<6:58:44,  1.62it/s]
 29%|██▉       | 16880/57600 [2:57:18<6:48:30,  1.66it/s]
                                                         
{'loss': 1.276, 'learning_rate': 7.384668989547038e-07, 'epoch': 186.31}

 29%|██▉       | 16880/57600 [2:57:18<6:48:30,  1.66it/s]
 29%|██▉       | 16881/57600 [2:57:19<6:53:45,  1.64it/s]
 29%|██▉       | 16882/57600 [2:57:20<6:52:54,  1.64it/s]
 29%|██▉       | 16883/57600 [2:57:20<6:52:31,  1.65it/s]
 29%|██▉       | 16884/57600 [2:57:21<6:56:01,  1.63it/s]
 29%|██▉       | 16885/57600 [2:57:22<7:15:13,  1.56it/s]
 29%|██▉       | 16886/57600 [2:57:22<7:10:53,  1.57it/s]
 29%|██▉       | 16887/57600 [2:57:23<6:54:05,  1.64it/s]
 29%|██▉       | 16888/57600 [2:57:23<7:01:55,  1.61it/s]
 29%|██▉       | 16889/57600 [2:57:24<7:06:28,  1.59it/s]
 29%|██▉       | 16890/57600 [2:57:25<7:10:27,  1.58it/s]
 29%|██▉       | 16891/57600 [2:57:25<6:59:44,  1.62it/s]
 29%|██▉       | 16892/57600 [2:57:26<6:56:54,  1.63it/s]
 29%|██▉       | 16893/57600 [2:57:26<6:52:55,  1.64it/s]
 29%|██▉       | 16894/57600 [2:57:27<7:02:24,  1.61it/s]
 29%|██▉       | 16895/57600 [2:57:28<7:12:19,  1.57it/s]
 29%|██▉       | 16896/57600 [2:57:28<6:57:04,  1.63it/s]
 29%|██▉       | 16897/57600 [2:57:29<7:09:45,  1.58it/s]
 29%|██▉       | 16898/57600 [2:57:30<7:12:15,  1.57it/s]
 29%|██▉       | 16899/57600 [2:57:30<7:17:23,  1.55it/s]
 29%|██▉       | 16900/57600 [2:57:31<6:54:35,  1.64it/s]
                                                         
{'loss': 1.2683, 'learning_rate': 7.381533101045296e-07, 'epoch': 186.53}

 29%|██▉       | 16900/57600 [2:57:31<6:54:35,  1.64it/s]
 29%|██▉       | 16901/57600 [2:57:32<7:00:52,  1.61it/s]
 29%|██▉       | 16902/57600 [2:57:32<7:12:22,  1.57it/s]
 29%|██▉       | 16903/57600 [2:57:33<7:09:08,  1.58it/s]
 29%|██▉       | 16904/57600 [2:57:33<7:16:03,  1.56it/s]
 29%|██▉       | 16905/57600 [2:57:34<7:10:51,  1.57it/s]
 29%|██▉       | 16906/57600 [2:57:35<7:12:46,  1.57it/s]
 29%|██▉       | 16907/57600 [2:57:35<6:58:03,  1.62it/s]
 29%|██▉       | 16908/57600 [2:57:36<7:00:43,  1.61it/s]
 29%|██▉       | 16909/57600 [2:57:37<6:56:55,  1.63it/s]
 29%|██▉       | 16910/57600 [2:57:37<7:05:16,  1.59it/s]
 29%|██▉       | 16911/57600 [2:57:38<6:57:38,  1.62it/s]
 29%|██▉       | 16912/57600 [2:57:39<7:16:53,  1.55it/s]
 29%|██▉       | 16913/57600 [2:57:39<7:20:15,  1.54it/s]
 29%|██▉       | 16914/57600 [2:57:40<7:14:50,  1.56it/s]
 29%|██▉       | 16915/57600 [2:57:40<7:00:24,  1.61it/s]
 29%|██▉       | 16916/57600 [2:57:41<6:56:47,  1.63it/s]
 29%|██▉       | 16917/57600 [2:57:42<6:53:30,  1.64it/s]
 29%|██▉       | 16918/57600 [2:57:42<6:58:09,  1.62it/s]
 29%|██▉       | 16919/57600 [2:57:43<6:55:59,  1.63it/s]
 29%|██▉       | 16920/57600 [2:57:43<6:57:46,  1.62it/s]
                                                         
{'loss': 1.265, 'learning_rate': 7.378397212543554e-07, 'epoch': 186.75}

 29%|██▉       | 16920/57600 [2:57:43<6:57:46,  1.62it/s]
 29%|██▉       | 16921/57600 [2:57:44<7:01:12,  1.61it/s]
 29%|██▉       | 16922/57600 [2:57:45<6:52:15,  1.64it/s]
 29%|██▉       | 16923/57600 [2:57:45<6:48:06,  1.66it/s]
 29%|██▉       | 16924/57600 [2:57:46<6:48:36,  1.66it/s]
 29%|██▉       | 16925/57600 [2:57:46<6:48:38,  1.66it/s]
 29%|██▉       | 16926/57600 [2:57:47<6:39:00,  1.70it/s]
 29%|██▉       | 16927/57600 [2:57:48<6:41:09,  1.69it/s]
 29%|██▉       | 16928/57600 [2:57:48<6:43:36,  1.68it/s]
 29%|██▉       | 16929/57600 [2:57:49<6:50:36,  1.65it/s]
 29%|██▉       | 16930/57600 [2:57:49<6:40:15,  1.69it/s]
 29%|██▉       | 16931/57600 [2:57:50<6:56:07,  1.63it/s]
 29%|██▉       | 16932/57600 [2:57:51<6:45:07,  1.67it/s]
 29%|██▉       | 16933/57600 [2:57:51<6:39:31,  1.70it/s]
 29%|██▉       | 16934/57600 [2:57:52<7:01:26,  1.61it/s]
 29%|██▉       | 16935/57600 [2:57:52<6:59:41,  1.61it/s]
 29%|██▉       | 16936/57600 [2:57:53<7:08:27,  1.58it/s]
 29%|██▉       | 16937/57600 [2:57:54<7:05:03,  1.59it/s]
 29%|██▉       | 16938/57600 [2:57:54<7:03:51,  1.60it/s]
 29%|██▉       | 16939/57600 [2:57:55<7:23:43,  1.53it/s]
 29%|██▉       | 16940/57600 [2:57:56<7:22:36,  1.53it/s]
                                                         
{'loss': 1.3122, 'learning_rate': 7.375261324041811e-07, 'epoch': 186.98}

 29%|██▉       | 16940/57600 [2:57:56<7:22:36,  1.53it/s]
 29%|██▉       | 16941/57600 [2:57:56<7:23:07,  1.53it/s]
 29%|██▉       | 16942/57600 [2:57:57<7:16:03,  1.55it/s]
 29%|██▉       | 16943/57600 [2:57:58<7:24:58,  1.52it/s]
 29%|██▉       | 16944/57600 [2:57:58<7:16:08,  1.55it/s]
 29%|██▉       | 16945/57600 [2:57:59<7:13:25,  1.56it/s]
 29%|██▉       | 16946/57600 [2:58:00<7:05:49,  1.59it/s]
 29%|██▉       | 16947/57600 [2:58:00<7:21:39,  1.53it/s]
 29%|██▉       | 16948/57600 [2:58:01<7:08:53,  1.58it/s]
 29%|██▉       | 16949/57600 [2:58:01<7:06:33,  1.59it/s]
 29%|██▉       | 16950/57600 [2:58:02<6:58:01,  1.62it/s]
 29%|██▉       | 16951/57600 [2:58:03<6:44:24,  1.68it/s]
 29%|██▉       | 16952/57600 [2:58:03<6:40:03,  1.69it/s]
 29%|██▉       | 16953/57600 [2:58:04<6:52:32,  1.64it/s]
 29%|██▉       | 16954/57600 [2:58:04<6:52:16,  1.64it/s]
 29%|██▉       | 16955/57600 [2:58:05<6:45:00,  1.67it/s]
 29%|██▉       | 16956/57600 [2:58:06<6:58:09,  1.62it/s]
 29%|██▉       | 16957/57600 [2:58:06<7:06:38,  1.59it/s]
 29%|██▉       | 16958/57600 [2:58:07<7:05:24,  1.59it/s]
 29%|██▉       | 16959/57600 [2:58:08<7:00:19,  1.61it/s]
 29%|██▉       | 16960/57600 [2:58:08<6:47:13,  1.66it/s]
                                                         
{'loss': 1.2669, 'learning_rate': 7.37212543554007e-07, 'epoch': 187.2}

 29%|██▉       | 16960/57600 [2:58:08<6:47:13,  1.66it/s]
 29%|██▉       | 16961/57600 [2:58:09<6:38:43,  1.70it/s]
 29%|██▉       | 16962/57600 [2:58:09<6:40:36,  1.69it/s]
 29%|██▉       | 16963/57600 [2:58:10<6:43:04,  1.68it/s]
 29%|██▉       | 16964/57600 [2:58:10<6:42:37,  1.68it/s]
 29%|██▉       | 16965/57600 [2:58:11<6:41:10,  1.69it/s]
 29%|██▉       | 16966/57600 [2:58:12<6:33:34,  1.72it/s]
 29%|██▉       | 16967/57600 [2:58:12<6:44:19,  1.67it/s]
 29%|██▉       | 16968/57600 [2:58:13<7:20:43,  1.54it/s]
 29%|██▉       | 16969/57600 [2:58:14<7:33:17,  1.49it/s]
 29%|██▉       | 16970/57600 [2:58:14<7:26:00,  1.52it/s]
 29%|██▉       | 16971/57600 [2:58:15<7:11:39,  1.57it/s]
 29%|██▉       | 16972/57600 [2:58:16<7:03:31,  1.60it/s]
 29%|██▉       | 16973/57600 [2:58:16<7:09:03,  1.58it/s]
 29%|██▉       | 16974/57600 [2:58:17<7:05:52,  1.59it/s]
 29%|██▉       | 16975/57600 [2:58:17<6:58:42,  1.62it/s]
 29%|██▉       | 16976/57600 [2:58:18<6:56:37,  1.63it/s]
 29%|██▉       | 16977/57600 [2:58:19<6:54:29,  1.63it/s]
 29%|██▉       | 16978/57600 [2:58:19<6:56:53,  1.62it/s]
 29%|██▉       | 16979/57600 [2:58:20<6:54:20,  1.63it/s]
 29%|██▉       | 16980/57600 [2:58:21<7:00:21,  1.61it/s]
                                                         
{'loss': 1.2789, 'learning_rate': 7.368989547038327e-07, 'epoch': 187.42}

 29%|██▉       | 16980/57600 [2:58:21<7:00:21,  1.61it/s]
 29%|██▉       | 16981/57600 [2:58:21<7:03:46,  1.60it/s]
 29%|██▉       | 16982/57600 [2:58:22<7:02:14,  1.60it/s]
 29%|██▉       | 16983/57600 [2:58:22<7:05:15,  1.59it/s]
 29%|██▉       | 16984/57600 [2:58:23<7:03:43,  1.60it/s]
 29%|██▉       | 16985/57600 [2:58:24<6:55:37,  1.63it/s]
 29%|██▉       | 16986/57600 [2:58:24<6:50:39,  1.65it/s]
 29%|██▉       | 16987/57600 [2:58:25<6:52:02,  1.64it/s]
 29%|██▉       | 16988/57600 [2:58:25<6:54:34,  1.63it/s]
 29%|██▉       | 16989/57600 [2:58:26<6:58:07,  1.62it/s]
 29%|██▉       | 16990/57600 [2:58:27<7:03:59,  1.60it/s]
 29%|██▉       | 16991/57600 [2:58:27<6:57:03,  1.62it/s]
 30%|██▉       | 16992/57600 [2:58:28<7:13:16,  1.56it/s]
 30%|██▉       | 16993/57600 [2:58:29<7:00:51,  1.61it/s]
 30%|██▉       | 16994/57600 [2:58:29<6:56:24,  1.63it/s]
 30%|██▉       | 16995/57600 [2:58:30<7:14:27,  1.56it/s]
 30%|██▉       | 16996/57600 [2:58:30<7:04:09,  1.60it/s]
 30%|██▉       | 16997/57600 [2:58:31<7:23:31,  1.53it/s]
 30%|██▉       | 16998/57600 [2:58:32<7:21:05,  1.53it/s]
 30%|██▉       | 16999/57600 [2:58:32<7:21:02,  1.53it/s]
 30%|██▉       | 17000/57600 [2:58:33<7:17:42,  1.55it/s]
                                                         
{'loss': 1.2457, 'learning_rate': 7.365853658536585e-07, 'epoch': 187.64}

 30%|██▉       | 17000/57600 [2:58:33<7:17:42,  1.55it/s]
 30%|██▉       | 17001/57600 [2:58:34<7:03:58,  1.60it/s]
 30%|██▉       | 17002/57600 [2:58:34<6:57:14,  1.62it/s]
 30%|██▉       | 17003/57600 [2:58:35<7:06:29,  1.59it/s]
 30%|██▉       | 17004/57600 [2:58:36<7:11:20,  1.57it/s]
 30%|██▉       | 17005/57600 [2:58:36<7:15:18,  1.55it/s]
 30%|██▉       | 17006/57600 [2:58:37<7:16:57,  1.55it/s]
 30%|██▉       | 17007/57600 [2:58:38<7:06:14,  1.59it/s]
 30%|██▉       | 17008/57600 [2:58:38<6:54:15,  1.63it/s]
 30%|██▉       | 17009/57600 [2:58:39<7:02:13,  1.60it/s]
 30%|██▉       | 17010/57600 [2:58:39<7:01:32,  1.60it/s]
 30%|██▉       | 17011/57600 [2:58:40<6:51:58,  1.64it/s]
 30%|██▉       | 17012/57600 [2:58:41<6:47:09,  1.66it/s]
 30%|██▉       | 17013/57600 [2:58:41<6:46:40,  1.66it/s]
 30%|██▉       | 17014/57600 [2:58:42<7:09:56,  1.57it/s]
 30%|██▉       | 17015/57600 [2:58:42<6:58:13,  1.62it/s]
 30%|██▉       | 17016/57600 [2:58:43<6:55:13,  1.63it/s]
 30%|██▉       | 17017/57600 [2:58:44<6:50:14,  1.65it/s]
 30%|██▉       | 17018/57600 [2:58:44<6:55:03,  1.63it/s]
 30%|██▉       | 17019/57600 [2:58:45<7:01:38,  1.60it/s]
 30%|██▉       | 17020/57600 [2:58:46<7:09:51,  1.57it/s]
                                                         
{'loss': 1.3173, 'learning_rate': 7.362717770034843e-07, 'epoch': 187.86}

 30%|██▉       | 17020/57600 [2:58:46<7:09:51,  1.57it/s]
 30%|██▉       | 17021/57600 [2:58:46<7:18:38,  1.54it/s]
 30%|██▉       | 17022/57600 [2:58:47<7:31:54,  1.50it/s]
 30%|██▉       | 17023/57600 [2:58:48<7:34:35,  1.49it/s]
 30%|██▉       | 17024/57600 [2:58:48<7:29:45,  1.50it/s]
 30%|██▉       | 17025/57600 [2:58:49<7:17:43,  1.54it/s]
 30%|██▉       | 17026/57600 [2:58:49<7:08:27,  1.58it/s]
 30%|██▉       | 17027/57600 [2:58:50<7:07:12,  1.58it/s]
 30%|██▉       | 17028/57600 [2:58:51<7:08:11,  1.58it/s]
 30%|██▉       | 17029/57600 [2:58:51<6:54:41,  1.63it/s]
 30%|██▉       | 17030/57600 [2:58:52<6:49:25,  1.65it/s]
 30%|██▉       | 17031/57600 [2:58:53<6:50:16,  1.65it/s]
 30%|██▉       | 17032/57600 [2:58:53<6:44:03,  1.67it/s]
 30%|██▉       | 17033/57600 [2:58:54<7:03:03,  1.60it/s]
 30%|██▉       | 17034/57600 [2:58:54<7:03:28,  1.60it/s]
 30%|██▉       | 17035/57600 [2:58:55<6:59:04,  1.61it/s]
 30%|██▉       | 17036/57600 [2:58:56<6:52:30,  1.64it/s]
 30%|██▉       | 17037/57600 [2:58:56<7:04:06,  1.59it/s]
 30%|██▉       | 17038/57600 [2:58:57<6:58:58,  1.61it/s]
 30%|██▉       | 17039/57600 [2:58:57<6:58:02,  1.62it/s]
 30%|██▉       | 17040/57600 [2:58:58<6:46:57,  1.66it/s]
                                                         
{'loss': 1.2793, 'learning_rate': 7.359581881533101e-07, 'epoch': 188.08}

 30%|██▉       | 17040/57600 [2:58:58<6:46:57,  1.66it/s]
 30%|██▉       | 17041/57600 [2:58:59<6:47:04,  1.66it/s]
 30%|██▉       | 17042/57600 [2:58:59<6:59:02,  1.61it/s]
 30%|██▉       | 17043/57600 [2:59:00<7:05:52,  1.59it/s]
 30%|██▉       | 17044/57600 [2:59:01<6:50:45,  1.65it/s]
 30%|██▉       | 17045/57600 [2:59:01<6:44:58,  1.67it/s]
 30%|██▉       | 17046/57600 [2:59:02<6:41:03,  1.69it/s]
 30%|██▉       | 17047/57600 [2:59:02<6:58:02,  1.62it/s]
 30%|██▉       | 17048/57600 [2:59:03<7:02:21,  1.60it/s]
 30%|██▉       | 17049/57600 [2:59:04<6:48:10,  1.66it/s]
 30%|██▉       | 17050/57600 [2:59:04<6:56:34,  1.62it/s]
 30%|██▉       | 17051/57600 [2:59:05<7:05:31,  1.59it/s]
 30%|██▉       | 17052/57600 [2:59:05<7:01:29,  1.60it/s]
 30%|██▉       | 17053/57600 [2:59:06<6:54:16,  1.63it/s]
 30%|██▉       | 17054/57600 [2:59:07<6:50:46,  1.65it/s]
 30%|██▉       | 17055/57600 [2:59:07<6:51:29,  1.64it/s]
 30%|██▉       | 17056/57600 [2:59:08<7:00:10,  1.61it/s]
 30%|██▉       | 17057/57600 [2:59:09<7:12:30,  1.56it/s]
 30%|██▉       | 17058/57600 [2:59:09<7:03:42,  1.59it/s]
 30%|██▉       | 17059/57600 [2:59:10<6:58:10,  1.62it/s]
 30%|██▉       | 17060/57600 [2:59:10<7:06:38,  1.58it/s]
                                                         
{'loss': 1.2538, 'learning_rate': 7.356445993031358e-07, 'epoch': 188.3}

 30%|██▉       | 17060/57600 [2:59:10<7:06:38,  1.58it/s]
 30%|██▉       | 17061/57600 [2:59:11<7:02:09,  1.60it/s]
 30%|██▉       | 17062/57600 [2:59:12<7:02:24,  1.60it/s]
 30%|██▉       | 17063/57600 [2:59:12<7:24:32,  1.52it/s]
 30%|██▉       | 17064/57600 [2:59:13<7:30:15,  1.50it/s]
 30%|██▉       | 17065/57600 [2:59:14<7:18:38,  1.54it/s]
 30%|██▉       | 17066/57600 [2:59:14<7:19:36,  1.54it/s]
 30%|██▉       | 17067/57600 [2:59:15<7:07:00,  1.58it/s]
 30%|██▉       | 17068/57600 [2:59:16<7:24:54,  1.52it/s]
 30%|██▉       | 17069/57600 [2:59:16<7:18:58,  1.54it/s]
 30%|██▉       | 17070/57600 [2:59:17<7:04:25,  1.59it/s]
 30%|██▉       | 17071/57600 [2:59:18<7:05:06,  1.59it/s]
 30%|██▉       | 17072/57600 [2:59:18<7:08:04,  1.58it/s]
 30%|██▉       | 17073/57600 [2:59:19<6:49:04,  1.65it/s]
 30%|██▉       | 17074/57600 [2:59:19<6:50:15,  1.65it/s]
 30%|██▉       | 17075/57600 [2:59:20<6:46:56,  1.66it/s]
 30%|██▉       | 17076/57600 [2:59:21<6:45:38,  1.67it/s]
 30%|██▉       | 17077/57600 [2:59:21<6:52:14,  1.64it/s]
 30%|██▉       | 17078/57600 [2:59:22<7:12:32,  1.56it/s]
 30%|██▉       | 17079/57600 [2:59:22<7:11:52,  1.56it/s]
 30%|██▉       | 17080/57600 [2:59:23<7:07:34,  1.58it/s]
                                                         
{'loss': 1.2564, 'learning_rate': 7.353310104529616e-07, 'epoch': 188.52}

 30%|██▉       | 17080/57600 [2:59:23<7:07:34,  1.58it/s]
 30%|██▉       | 17081/57600 [2:59:24<7:03:33,  1.59it/s]
 30%|██▉       | 17082/57600 [2:59:24<6:59:32,  1.61it/s]
 30%|██▉       | 17083/57600 [2:59:25<7:04:07,  1.59it/s]
 30%|██▉       | 17084/57600 [2:59:26<7:07:47,  1.58it/s]
 30%|██▉       | 17085/57600 [2:59:26<7:00:58,  1.60it/s]
 30%|██▉       | 17086/57600 [2:59:27<6:47:50,  1.66it/s]
 30%|██▉       | 17087/57600 [2:59:27<7:01:14,  1.60it/s]
 30%|██▉       | 17088/57600 [2:59:28<7:01:51,  1.60it/s]
 30%|██▉       | 17089/57600 [2:59:29<6:52:41,  1.64it/s]
 30%|██▉       | 17090/57600 [2:59:29<6:48:09,  1.65it/s]
 30%|██▉       | 17091/57600 [2:59:30<6:46:09,  1.66it/s]
 30%|██▉       | 17092/57600 [2:59:30<6:39:28,  1.69it/s]
 30%|██▉       | 17093/57600 [2:59:31<6:58:18,  1.61it/s]
 30%|██▉       | 17094/57600 [2:59:32<7:11:39,  1.56it/s]
 30%|██▉       | 17095/57600 [2:59:32<6:58:28,  1.61it/s]
 30%|██▉       | 17096/57600 [2:59:33<7:05:38,  1.59it/s]
 30%|██▉       | 17097/57600 [2:59:34<6:59:56,  1.61it/s]
 30%|██▉       | 17098/57600 [2:59:34<7:16:53,  1.55it/s]
 30%|██▉       | 17099/57600 [2:59:35<7:00:20,  1.61it/s]
 30%|██▉       | 17100/57600 [2:59:35<6:59:13,  1.61it/s]
                                                         
{'loss': 1.2794, 'learning_rate': 7.350174216027874e-07, 'epoch': 188.74}

 30%|██▉       | 17100/57600 [2:59:35<6:59:13,  1.61it/s]
 30%|██▉       | 17101/57600 [2:59:36<7:11:48,  1.56it/s]
 30%|██▉       | 17102/57600 [2:59:37<7:00:11,  1.61it/s]
 30%|██▉       | 17103/57600 [2:59:37<6:48:56,  1.65it/s]
 30%|██▉       | 17104/57600 [2:59:38<6:45:56,  1.66it/s]
 30%|██▉       | 17105/57600 [2:59:39<7:00:08,  1.61it/s]
 30%|██▉       | 17106/57600 [2:59:39<6:58:38,  1.61it/s]
 30%|██▉       | 17107/57600 [2:59:40<7:11:09,  1.57it/s]
 30%|██▉       | 17108/57600 [2:59:41<7:28:30,  1.50it/s]
 30%|██▉       | 17109/57600 [2:59:41<7:28:32,  1.50it/s]
 30%|██▉       | 17110/57600 [2:59:42<7:25:34,  1.51it/s]
 30%|██▉       | 17111/57600 [2:59:43<7:11:48,  1.56it/s]
 30%|██▉       | 17112/57600 [2:59:43<7:04:16,  1.59it/s]
 30%|██▉       | 17113/57600 [2:59:44<6:55:19,  1.62it/s]
 30%|██▉       | 17114/57600 [2:59:44<6:49:57,  1.65it/s]
 30%|██▉       | 17115/57600 [2:59:45<6:54:51,  1.63it/s]
 30%|██▉       | 17116/57600 [2:59:46<6:49:34,  1.65it/s]
 30%|██▉       | 17117/57600 [2:59:46<6:44:39,  1.67it/s]
 30%|██▉       | 17118/57600 [2:59:47<7:05:02,  1.59it/s]
 30%|██▉       | 17119/57600 [2:59:47<7:09:51,  1.57it/s]
 30%|██▉       | 17120/57600 [2:59:48<7:15:43,  1.55it/s]
                                                         
{'loss': 1.2664, 'learning_rate': 7.347038327526132e-07, 'epoch': 188.96}

 30%|██▉       | 17120/57600 [2:59:48<7:15:43,  1.55it/s]
 30%|██▉       | 17121/57600 [2:59:49<7:14:04,  1.55it/s]
 30%|██▉       | 17122/57600 [2:59:49<6:59:21,  1.61it/s]
 30%|██▉       | 17123/57600 [2:59:50<7:00:32,  1.60it/s]
 30%|██▉       | 17124/57600 [2:59:51<7:15:05,  1.55it/s]
 30%|██▉       | 17125/57600 [2:59:51<7:10:57,  1.57it/s]
 30%|██▉       | 17126/57600 [2:59:52<7:12:06,  1.56it/s]
 30%|██▉       | 17127/57600 [2:59:52<6:54:50,  1.63it/s]
 30%|██▉       | 17128/57600 [2:59:53<7:06:58,  1.58it/s]
 30%|██▉       | 17129/57600 [2:59:54<7:06:32,  1.58it/s]
 30%|██▉       | 17130/57600 [2:59:54<7:13:57,  1.55it/s]
 30%|██▉       | 17131/57600 [2:59:55<7:06:35,  1.58it/s]
 30%|██▉       | 17132/57600 [2:59:56<7:05:04,  1.59it/s]
 30%|██▉       | 17133/57600 [2:59:56<7:08:05,  1.58it/s]
 30%|██▉       | 17134/57600 [2:59:57<7:02:24,  1.60it/s]
 30%|██▉       | 17135/57600 [2:59:58<6:57:04,  1.62it/s]
 30%|██▉       | 17136/57600 [2:59:58<7:02:25,  1.60it/s]
 30%|██▉       | 17137/57600 [2:59:59<7:05:09,  1.59it/s]
 30%|██▉       | 17138/57600 [3:00:00<7:17:50,  1.54it/s]
 30%|██▉       | 17139/57600 [3:00:00<7:24:22,  1.52it/s]
 30%|██▉       | 17140/57600 [3:00:01<7:23:22,  1.52it/s]
                                                         
{'loss': 1.2489, 'learning_rate': 7.343902439024389e-07, 'epoch': 189.18}

 30%|██▉       | 17140/57600 [3:00:01<7:23:22,  1.52it/s]
 30%|██▉       | 17141/57600 [3:00:01<6:59:01,  1.61it/s]
 30%|██▉       | 17142/57600 [3:00:02<6:57:26,  1.62it/s]
 30%|██▉       | 17143/57600 [3:00:03<7:17:07,  1.54it/s]
 30%|██▉       | 17144/57600 [3:00:03<7:11:03,  1.56it/s]
 30%|██▉       | 17145/57600 [3:00:04<7:11:48,  1.56it/s]
 30%|██▉       | 17146/57600 [3:00:05<7:01:40,  1.60it/s]
 30%|██▉       | 17147/57600 [3:00:05<6:56:50,  1.62it/s]
 30%|██▉       | 17148/57600 [3:00:06<7:06:24,  1.58it/s]
 30%|██▉       | 17149/57600 [3:00:06<7:02:24,  1.60it/s]
 30%|██▉       | 17150/57600 [3:00:07<6:49:29,  1.65it/s]
 30%|██▉       | 17151/57600 [3:00:08<6:56:32,  1.62it/s]
 30%|██▉       | 17152/57600 [3:00:08<7:11:58,  1.56it/s]
 30%|██▉       | 17153/57600 [3:00:09<6:59:15,  1.61it/s]
 30%|██▉       | 17154/57600 [3:00:10<7:11:23,  1.56it/s]
 30%|██▉       | 17155/57600 [3:00:10<7:04:31,  1.59it/s]
 30%|██▉       | 17156/57600 [3:00:11<6:55:12,  1.62it/s]
 30%|██▉       | 17157/57600 [3:00:11<6:58:01,  1.61it/s]
 30%|██▉       | 17158/57600 [3:00:12<6:46:57,  1.66it/s]
 30%|██▉       | 17159/57600 [3:00:13<6:39:06,  1.69it/s]
 30%|██▉       | 17160/57600 [3:00:13<6:39:29,  1.69it/s]
                                                         
{'loss': 1.29, 'learning_rate': 7.340766550522648e-07, 'epoch': 189.4}

 30%|██▉       | 17160/57600 [3:00:13<6:39:29,  1.69it/s]
 30%|██▉       | 17161/57600 [3:00:14<6:46:20,  1.66it/s]
 30%|██▉       | 17162/57600 [3:00:14<6:41:21,  1.68it/s]
 30%|██▉       | 17163/57600 [3:00:15<6:44:44,  1.67it/s]
 30%|██▉       | 17164/57600 [3:00:16<6:53:59,  1.63it/s]
 30%|██▉       | 17165/57600 [3:00:16<6:59:38,  1.61it/s]
 30%|██▉       | 17166/57600 [3:00:17<6:58:42,  1.61it/s]
 30%|██▉       | 17167/57600 [3:00:18<7:12:04,  1.56it/s]
 30%|██▉       | 17168/57600 [3:00:18<7:09:33,  1.57it/s]
 30%|██▉       | 17169/57600 [3:00:19<7:16:42,  1.54it/s]
 30%|██▉       | 17170/57600 [3:00:20<7:18:44,  1.54it/s]
 30%|██▉       | 17171/57600 [3:00:20<7:12:52,  1.56it/s]
 30%|██▉       | 17172/57600 [3:00:21<7:04:36,  1.59it/s]
 30%|██▉       | 17173/57600 [3:00:21<6:57:47,  1.61it/s]
 30%|██▉       | 17174/57600 [3:00:22<6:54:57,  1.62it/s]
 30%|██▉       | 17175/57600 [3:00:23<7:08:59,  1.57it/s]
 30%|██▉       | 17176/57600 [3:00:23<6:58:40,  1.61it/s]
 30%|██▉       | 17177/57600 [3:00:24<7:02:26,  1.59it/s]
 30%|██▉       | 17178/57600 [3:00:25<7:10:33,  1.56it/s]
 30%|██▉       | 17179/57600 [3:00:25<7:05:36,  1.58it/s]
 30%|██▉       | 17180/57600 [3:00:26<6:54:31,  1.63it/s]
                                                         
{'loss': 1.2308, 'learning_rate': 7.337630662020907e-07, 'epoch': 189.62}

 30%|██▉       | 17180/57600 [3:00:26<6:54:31,  1.63it/s]
 30%|██▉       | 17181/57600 [3:00:26<6:59:39,  1.61it/s]
 30%|██▉       | 17182/57600 [3:00:27<6:49:49,  1.64it/s]
 30%|██▉       | 17183/57600 [3:00:28<6:48:41,  1.65it/s]
 30%|██▉       | 17184/57600 [3:00:28<6:45:12,  1.66it/s]
 30%|██▉       | 17185/57600 [3:00:29<6:52:38,  1.63it/s]
 30%|██▉       | 17186/57600 [3:00:29<6:59:45,  1.60it/s]
 30%|██▉       | 17187/57600 [3:00:30<6:54:08,  1.63it/s]
 30%|██▉       | 17188/57600 [3:00:31<6:47:59,  1.65it/s]
 30%|██▉       | 17189/57600 [3:00:31<6:41:20,  1.68it/s]
 30%|██▉       | 17190/57600 [3:00:32<6:37:58,  1.69it/s]
 30%|██▉       | 17191/57600 [3:00:32<6:37:55,  1.69it/s]
 30%|██▉       | 17192/57600 [3:00:33<6:44:35,  1.66it/s]
 30%|██▉       | 17193/57600 [3:00:34<6:49:25,  1.64it/s]
 30%|██▉       | 17194/57600 [3:00:34<7:04:17,  1.59it/s]
 30%|██▉       | 17195/57600 [3:00:35<7:03:03,  1.59it/s]
 30%|██▉       | 17196/57600 [3:00:36<7:08:27,  1.57it/s]
 30%|██▉       | 17197/57600 [3:00:36<6:55:29,  1.62it/s]
 30%|██▉       | 17198/57600 [3:00:37<6:53:40,  1.63it/s]
 30%|██▉       | 17199/57600 [3:00:37<6:49:33,  1.64it/s]
 30%|██▉       | 17200/57600 [3:00:38<7:04:35,  1.59it/s]
                                                         
{'loss': 1.2809, 'learning_rate': 7.334494773519163e-07, 'epoch': 189.85}

 30%|██▉       | 17200/57600 [3:00:38<7:04:35,  1.59it/s]
 30%|██▉       | 17201/57600 [3:00:39<6:56:31,  1.62it/s]
 30%|██▉       | 17202/57600 [3:00:39<6:46:43,  1.66it/s]
 30%|██▉       | 17203/57600 [3:00:40<6:45:51,  1.66it/s]
 30%|██▉       | 17204/57600 [3:00:40<6:41:56,  1.68it/s]
 30%|██▉       | 17205/57600 [3:00:41<6:45:36,  1.66it/s]
 30%|██▉       | 17206/57600 [3:00:42<6:49:23,  1.64it/s]
 30%|██▉       | 17207/57600 [3:00:42<6:43:40,  1.67it/s]
 30%|██▉       | 17208/57600 [3:00:43<6:48:17,  1.65it/s]
 30%|██▉       | 17209/57600 [3:00:43<6:58:08,  1.61it/s]
 30%|██▉       | 17210/57600 [3:00:44<6:54:17,  1.62it/s]
 30%|██▉       | 17211/57600 [3:00:45<6:58:40,  1.61it/s]
 30%|██▉       | 17212/57600 [3:00:45<6:59:59,  1.60it/s]
 30%|██▉       | 17213/57600 [3:00:46<7:00:36,  1.60it/s]
 30%|██▉       | 17214/57600 [3:00:47<7:20:05,  1.53it/s]
 30%|██▉       | 17215/57600 [3:00:47<7:24:20,  1.51it/s]
 30%|██▉       | 17216/57600 [3:00:48<7:18:36,  1.53it/s]
 30%|██▉       | 17217/57600 [3:00:49<7:06:51,  1.58it/s]
 30%|██▉       | 17218/57600 [3:00:49<7:13:50,  1.55it/s]
 30%|██▉       | 17219/57600 [3:00:50<7:08:31,  1.57it/s]
 30%|██▉       | 17220/57600 [3:00:50<7:09:57,  1.57it/s]
                                                         
{'loss': 1.2614, 'learning_rate': 7.331358885017421e-07, 'epoch': 190.07}

 30%|██▉       | 17220/57600 [3:00:50<7:09:57,  1.57it/s]
 30%|██▉       | 17221/57600 [3:00:51<7:16:49,  1.54it/s]
 30%|██▉       | 17222/57600 [3:00:52<7:05:56,  1.58it/s]
 30%|██▉       | 17223/57600 [3:00:52<7:16:51,  1.54it/s]
 30%|██▉       | 17224/57600 [3:00:53<7:13:25,  1.55it/s]
 30%|██▉       | 17225/57600 [3:00:54<7:09:13,  1.57it/s]
 30%|██▉       | 17226/57600 [3:00:54<7:06:13,  1.58it/s]
 30%|██▉       | 17227/57600 [3:00:55<7:00:04,  1.60it/s]
 30%|██▉       | 17228/57600 [3:00:56<6:54:58,  1.62it/s]
 30%|██▉       | 17229/57600 [3:00:56<7:14:49,  1.55it/s]
 30%|██▉       | 17230/57600 [3:00:57<7:17:36,  1.54it/s]
 30%|██▉       | 17231/57600 [3:00:57<6:54:46,  1.62it/s]
 30%|██▉       | 17232/57600 [3:00:58<7:00:59,  1.60it/s]
 30%|██▉       | 17233/57600 [3:00:59<7:09:40,  1.57it/s]
 30%|██▉       | 17234/57600 [3:00:59<6:55:36,  1.62it/s]
 30%|██▉       | 17235/57600 [3:01:00<6:50:56,  1.64it/s]
 30%|██▉       | 17236/57600 [3:01:00<6:43:49,  1.67it/s]
 30%|██▉       | 17237/57600 [3:01:01<6:53:08,  1.63it/s]
 30%|██▉       | 17238/57600 [3:01:02<6:44:13,  1.66it/s]
 30%|██▉       | 17239/57600 [3:01:02<6:35:32,  1.70it/s]
 30%|██▉       | 17240/57600 [3:01:03<6:27:58,  1.73it/s]
                                                         
{'loss': 1.3223, 'learning_rate': 7.328222996515679e-07, 'epoch': 190.29}

 30%|██▉       | 17240/57600 [3:01:03<6:27:58,  1.73it/s]
 30%|██▉       | 17241/57600 [3:01:03<6:27:29,  1.74it/s]
 30%|██▉       | 17242/57600 [3:01:04<6:27:16,  1.74it/s]
 30%|██▉       | 17243/57600 [3:01:05<6:21:15,  1.76it/s]
 30%|██▉       | 17244/57600 [3:01:05<6:32:37,  1.71it/s]
 30%|██▉       | 17245/57600 [3:01:06<6:41:08,  1.68it/s]
 30%|██▉       | 17246/57600 [3:01:06<6:50:59,  1.64it/s]
 30%|██▉       | 17247/57600 [3:01:07<6:52:07,  1.63it/s]
 30%|██▉       | 17248/57600 [3:01:08<6:58:47,  1.61it/s]
 30%|██▉       | 17249/57600 [3:01:08<7:02:53,  1.59it/s]
 30%|██▉       | 17250/57600 [3:01:09<7:12:11,  1.56it/s]
 30%|██▉       | 17251/57600 [3:01:10<7:04:38,  1.58it/s]
 30%|██▉       | 17252/57600 [3:01:10<7:04:08,  1.59it/s]
 30%|██▉       | 17253/57600 [3:01:11<6:53:23,  1.63it/s]
 30%|██▉       | 17254/57600 [3:01:11<6:48:20,  1.65it/s]
 30%|██▉       | 17255/57600 [3:01:12<6:36:14,  1.70it/s]
 30%|██▉       | 17256/57600 [3:01:13<6:46:23,  1.65it/s]
 30%|██▉       | 17257/57600 [3:01:13<6:45:46,  1.66it/s]
 30%|██▉       | 17258/57600 [3:01:14<6:55:57,  1.62it/s]
 30%|██▉       | 17259/57600 [3:01:14<6:47:33,  1.65it/s]
 30%|██▉       | 17260/57600 [3:01:15<7:01:39,  1.59it/s]
                                                         
{'loss': 1.3043, 'learning_rate': 7.325087108013937e-07, 'epoch': 190.51}

 30%|██▉       | 17260/57600 [3:01:15<7:01:39,  1.59it/s]
 30%|██▉       | 17261/57600 [3:01:16<7:11:26,  1.56it/s]
 30%|██▉       | 17262/57600 [3:01:16<7:04:09,  1.59it/s]
 30%|██▉       | 17263/57600 [3:01:17<7:02:16,  1.59it/s]
 30%|██▉       | 17264/57600 [3:01:18<7:16:56,  1.54it/s]
 30%|██▉       | 17265/57600 [3:01:18<7:19:35,  1.53it/s]
 30%|██▉       | 17266/57600 [3:01:19<7:03:40,  1.59it/s]
 30%|██▉       | 17267/57600 [3:01:19<6:51:55,  1.63it/s]
 30%|██▉       | 17268/57600 [3:01:20<6:39:09,  1.68it/s]
 30%|██▉       | 17269/57600 [3:01:21<6:38:48,  1.69it/s]
 30%|██▉       | 17270/57600 [3:01:21<6:39:55,  1.68it/s]
 30%|██▉       | 17271/57600 [3:01:22<6:44:29,  1.66it/s]
 30%|██▉       | 17272/57600 [3:01:23<6:57:20,  1.61it/s]
 30%|██▉       | 17273/57600 [3:01:23<7:07:18,  1.57it/s]
 30%|██▉       | 17274/57600 [3:01:24<6:50:48,  1.64it/s]
 30%|██▉       | 17275/57600 [3:01:24<6:58:53,  1.60it/s]
 30%|██▉       | 17276/57600 [3:01:25<6:59:47,  1.60it/s]
 30%|██▉       | 17277/57600 [3:01:26<7:04:32,  1.58it/s]
 30%|██▉       | 17278/57600 [3:01:26<7:08:06,  1.57it/s]
 30%|██▉       | 17279/57600 [3:01:27<7:02:45,  1.59it/s]
 30%|███       | 17280/57600 [3:01:28<7:10:29,  1.56it/s]
                                                         
{'loss': 1.2612, 'learning_rate': 7.321951219512194e-07, 'epoch': 190.73}

 30%|███       | 17280/57600 [3:01:28<7:10:29,  1.56it/s]
 30%|███       | 17281/57600 [3:01:28<7:12:54,  1.55it/s]
 30%|███       | 17282/57600 [3:01:29<7:17:24,  1.54it/s]
 30%|███       | 17283/57600 [3:01:30<7:22:54,  1.52it/s]
 30%|███       | 17284/57600 [3:01:30<7:30:44,  1.49it/s]
 30%|███       | 17285/57600 [3:01:31<7:23:36,  1.51it/s]
 30%|███       | 17286/57600 [3:01:32<7:08:47,  1.57it/s]
 30%|███       | 17287/57600 [3:01:32<6:57:03,  1.61it/s]
 30%|███       | 17288/57600 [3:01:33<7:01:53,  1.59it/s]
 30%|███       | 17289/57600 [3:01:33<7:10:53,  1.56it/s]
 30%|███       | 17290/57600 [3:01:34<7:09:18,  1.56it/s]
 30%|███       | 17291/57600 [3:01:35<6:54:55,  1.62it/s]
 30%|███       | 17292/57600 [3:01:35<7:02:01,  1.59it/s]
 30%|███       | 17293/57600 [3:01:36<7:03:15,  1.59it/s]
 30%|███       | 17294/57600 [3:01:37<7:12:28,  1.55it/s]
 30%|███       | 17295/57600 [3:01:37<7:05:11,  1.58it/s]
 30%|███       | 17296/57600 [3:01:38<7:13:30,  1.55it/s]
 30%|███       | 17297/57600 [3:01:38<7:11:53,  1.56it/s]
 30%|███       | 17298/57600 [3:01:39<6:59:27,  1.60it/s]
 30%|███       | 17299/57600 [3:01:40<6:55:41,  1.62it/s]
 30%|███       | 17300/57600 [3:01:40<6:55:20,  1.62it/s]
                                                         
{'loss': 1.2209, 'learning_rate': 7.318815331010453e-07, 'epoch': 190.95}

 30%|███       | 17300/57600 [3:01:40<6:55:20,  1.62it/s]
 30%|███       | 17301/57600 [3:01:41<6:51:31,  1.63it/s]
 30%|███       | 17302/57600 [3:01:41<6:39:02,  1.68it/s]
 30%|███       | 17303/57600 [3:01:42<6:41:23,  1.67it/s]
 30%|███       | 17304/57600 [3:01:43<7:00:38,  1.60it/s]
 30%|███       | 17305/57600 [3:01:43<7:15:45,  1.54it/s]
 30%|███       | 17306/57600 [3:01:44<7:03:01,  1.59it/s]
 30%|███       | 17307/57600 [3:01:45<7:01:50,  1.59it/s]
 30%|███       | 17308/57600 [3:01:45<7:14:45,  1.54it/s]
 30%|███       | 17309/57600 [3:01:46<7:06:42,  1.57it/s]
 30%|███       | 17310/57600 [3:01:47<7:10:51,  1.56it/s]
 30%|███       | 17311/57600 [3:01:47<7:19:38,  1.53it/s]
 30%|███       | 17312/57600 [3:01:48<7:23:56,  1.51it/s]
 30%|███       | 17313/57600 [3:01:49<7:20:38,  1.52it/s]
 30%|███       | 17314/57600 [3:01:49<7:07:08,  1.57it/s]
 30%|███       | 17315/57600 [3:01:50<6:57:34,  1.61it/s]
 30%|███       | 17316/57600 [3:01:50<6:58:54,  1.60it/s]
 30%|███       | 17317/57600 [3:01:51<6:57:46,  1.61it/s]
 30%|███       | 17318/57600 [3:01:52<7:06:40,  1.57it/s]
 30%|███       | 17319/57600 [3:01:52<7:15:23,  1.54it/s]
 30%|███       | 17320/57600 [3:01:53<7:24:23,  1.51it/s]
                                                         
{'loss': 1.2478, 'learning_rate': 7.315679442508711e-07, 'epoch': 191.17}

 30%|███       | 17320/57600 [3:01:53<7:24:23,  1.51it/s]
 30%|███       | 17321/57600 [3:01:54<7:07:08,  1.57it/s]
 30%|███       | 17322/57600 [3:01:54<7:04:58,  1.58it/s]
 30%|███       | 17323/57600 [3:01:55<7:05:40,  1.58it/s]
 30%|███       | 17324/57600 [3:01:56<6:54:56,  1.62it/s]
 30%|███       | 17325/57600 [3:01:56<7:03:02,  1.59it/s]
 30%|███       | 17326/57600 [3:01:57<6:50:36,  1.63it/s]
 30%|███       | 17327/57600 [3:01:57<6:48:08,  1.64it/s]
 30%|███       | 17328/57600 [3:01:58<7:00:20,  1.60it/s]
 30%|███       | 17329/57600 [3:01:59<6:59:57,  1.60it/s]
 30%|███       | 17330/57600 [3:01:59<7:06:22,  1.57it/s]
 30%|███       | 17331/57600 [3:02:00<7:01:45,  1.59it/s]
 30%|███       | 17332/57600 [3:02:01<7:00:25,  1.60it/s]
 30%|███       | 17333/57600 [3:02:01<6:56:06,  1.61it/s]
 30%|███       | 17334/57600 [3:02:02<6:45:38,  1.65it/s]
 30%|███       | 17335/57600 [3:02:02<7:08:00,  1.57it/s]
 30%|███       | 17336/57600 [3:02:03<7:03:47,  1.58it/s]
 30%|███       | 17337/57600 [3:02:04<7:03:58,  1.58it/s]
 30%|███       | 17338/57600 [3:02:04<7:01:46,  1.59it/s]
 30%|███       | 17339/57600 [3:02:05<7:03:27,  1.58it/s]
 30%|███       | 17340/57600 [3:02:06<7:04:26,  1.58it/s]
                                                         
{'loss': 1.3277, 'learning_rate': 7.312543554006968e-07, 'epoch': 191.39}

 30%|███       | 17340/57600 [3:02:06<7:04:26,  1.58it/s]
 30%|███       | 17341/57600 [3:02:06<6:54:27,  1.62it/s]
 30%|███       | 17342/57600 [3:02:07<6:59:34,  1.60it/s]
 30%|███       | 17343/57600 [3:02:07<6:47:24,  1.65it/s]
 30%|███       | 17344/57600 [3:02:08<6:43:30,  1.66it/s]
 30%|███       | 17345/57600 [3:02:09<6:42:47,  1.67it/s]
 30%|███       | 17346/57600 [3:02:09<6:47:49,  1.65it/s]
 30%|███       | 17347/57600 [3:02:10<6:51:58,  1.63it/s]
 30%|███       | 17348/57600 [3:02:10<7:07:19,  1.57it/s]
 30%|███       | 17349/57600 [3:02:11<6:58:26,  1.60it/s]
 30%|███       | 17350/57600 [3:02:12<6:51:56,  1.63it/s]
 30%|███       | 17351/57600 [3:02:12<6:53:06,  1.62it/s]
 30%|███       | 17352/57600 [3:02:13<6:50:13,  1.64it/s]
 30%|███       | 17353/57600 [3:02:14<6:59:08,  1.60it/s]
 30%|███       | 17354/57600 [3:02:14<6:53:02,  1.62it/s]
 30%|███       | 17355/57600 [3:02:15<6:53:57,  1.62it/s]
 30%|███       | 17356/57600 [3:02:15<6:50:52,  1.63it/s]
 30%|███       | 17357/57600 [3:02:16<6:52:24,  1.63it/s]
 30%|███       | 17358/57600 [3:02:17<6:49:36,  1.64it/s]
 30%|███       | 17359/57600 [3:02:17<7:00:58,  1.59it/s]
 30%|███       | 17360/57600 [3:02:18<7:06:48,  1.57it/s]
                                                         
{'loss': 1.2715, 'learning_rate': 7.309407665505225e-07, 'epoch': 191.61}

 30%|███       | 17360/57600 [3:02:18<7:06:48,  1.57it/s]
 30%|███       | 17361/57600 [3:02:19<7:16:41,  1.54it/s]
 30%|███       | 17362/57600 [3:02:19<6:59:30,  1.60it/s]
 30%|███       | 17363/57600 [3:02:20<6:59:02,  1.60it/s]
 30%|███       | 17364/57600 [3:02:20<7:05:39,  1.58it/s]
 30%|███       | 17365/57600 [3:02:21<6:53:04,  1.62it/s]
 30%|███       | 17366/57600 [3:02:22<7:07:40,  1.57it/s]
 30%|███       | 17367/57600 [3:02:22<7:01:47,  1.59it/s]
 30%|███       | 17368/57600 [3:02:23<6:47:21,  1.65it/s]
 30%|███       | 17369/57600 [3:02:23<6:46:58,  1.65it/s]
 30%|███       | 17370/57600 [3:02:24<6:50:02,  1.64it/s]
 30%|███       | 17371/57600 [3:02:25<7:14:55,  1.54it/s]
 30%|███       | 17372/57600 [3:02:25<7:09:35,  1.56it/s]
 30%|███       | 17373/57600 [3:02:26<7:11:21,  1.55it/s]
 30%|███       | 17374/57600 [3:02:27<7:03:49,  1.58it/s]
 30%|███       | 17375/57600 [3:02:27<7:10:40,  1.56it/s]
 30%|███       | 17376/57600 [3:02:28<7:28:57,  1.49it/s]
 30%|███       | 17377/57600 [3:02:29<7:23:52,  1.51it/s]
 30%|███       | 17378/57600 [3:02:29<7:13:32,  1.55it/s]
 30%|███       | 17379/57600 [3:02:30<6:59:18,  1.60it/s]
 30%|███       | 17380/57600 [3:02:31<7:07:00,  1.57it/s]
                                                         
{'loss': 1.2433, 'learning_rate': 7.306271777003485e-07, 'epoch': 191.83}

 30%|███       | 17380/57600 [3:02:31<7:07:00,  1.57it/s]
 30%|███       | 17381/57600 [3:02:31<6:59:43,  1.60it/s]
 30%|███       | 17382/57600 [3:02:32<6:49:28,  1.64it/s]
 30%|███       | 17383/57600 [3:02:32<6:53:15,  1.62it/s]
 30%|███       | 17384/57600 [3:02:33<6:51:55,  1.63it/s]
 30%|███       | 17385/57600 [3:02:34<7:05:28,  1.58it/s]
 30%|███       | 17386/57600 [3:02:34<6:52:58,  1.62it/s]
 30%|███       | 17387/57600 [3:02:35<6:49:10,  1.64it/s]
 30%|███       | 17388/57600 [3:02:35<6:45:34,  1.65it/s]
 30%|███       | 17389/57600 [3:02:36<6:59:32,  1.60it/s]
 30%|███       | 17390/57600 [3:02:37<6:52:35,  1.62it/s]
 30%|███       | 17391/57600 [3:02:37<6:45:37,  1.65it/s]
 30%|███       | 17392/57600 [3:02:38<6:42:41,  1.66it/s]
 30%|███       | 17393/57600 [3:02:39<6:51:11,  1.63it/s]
 30%|███       | 17394/57600 [3:02:39<6:58:51,  1.60it/s]
 30%|███       | 17395/57600 [3:02:40<6:54:04,  1.62it/s]
 30%|███       | 17396/57600 [3:02:41<7:23:08,  1.51it/s]
 30%|███       | 17397/57600 [3:02:41<7:18:56,  1.53it/s]
 30%|███       | 17398/57600 [3:02:42<7:13:46,  1.54it/s]
 30%|███       | 17399/57600 [3:02:42<7:02:06,  1.59it/s]
 30%|███       | 17400/57600 [3:02:43<6:59:54,  1.60it/s]
                                                         
{'loss': 1.2975, 'learning_rate': 7.303135888501742e-07, 'epoch': 192.05}

 30%|███       | 17400/57600 [3:02:43<6:59:54,  1.60it/s]
 30%|███       | 17401/57600 [3:02:44<7:00:14,  1.59it/s]
 30%|███       | 17402/57600 [3:02:44<6:52:38,  1.62it/s]
 30%|███       | 17403/57600 [3:02:45<6:49:10,  1.64it/s]
 30%|███       | 17404/57600 [3:02:45<6:41:54,  1.67it/s]
 30%|███       | 17405/57600 [3:02:46<6:45:12,  1.65it/s]
 30%|███       | 17406/57600 [3:02:47<7:10:07,  1.56it/s]
 30%|███       | 17407/57600 [3:02:47<7:15:00,  1.54it/s]
 30%|███       | 17408/57600 [3:02:48<7:18:08,  1.53it/s]
 30%|███       | 17409/57600 [3:02:49<7:15:05,  1.54it/s]
 30%|███       | 17410/57600 [3:02:49<7:07:59,  1.57it/s]
 30%|███       | 17411/57600 [3:02:50<6:57:55,  1.60it/s]
 30%|███       | 17412/57600 [3:02:51<6:54:34,  1.62it/s]
 30%|███       | 17413/57600 [3:02:51<6:59:04,  1.60it/s]
 30%|███       | 17414/57600 [3:02:52<6:56:14,  1.61it/s]
 30%|███       | 17415/57600 [3:02:52<6:55:34,  1.61it/s]
 30%|███       | 17416/57600 [3:02:53<7:06:29,  1.57it/s]
 30%|███       | 17417/57600 [3:02:54<7:04:06,  1.58it/s]
 30%|███       | 17418/57600 [3:02:54<7:16:15,  1.54it/s]
 30%|███       | 17419/57600 [3:02:55<7:05:39,  1.57it/s]
 30%|███       | 17420/57600 [3:02:56<6:59:31,  1.60it/s]
                                                         
{'loss': 1.2325, 'learning_rate': 7.299999999999998e-07, 'epoch': 192.27}

 30%|███       | 17420/57600 [3:02:56<6:59:31,  1.60it/s]
 30%|███       | 17421/57600 [3:02:56<7:10:43,  1.55it/s]
 30%|███       | 17422/57600 [3:02:57<7:01:54,  1.59it/s]
 30%|███       | 17423/57600 [3:02:58<7:00:30,  1.59it/s]
 30%|███       | 17424/57600 [3:02:58<6:49:44,  1.63it/s]
 30%|███       | 17425/57600 [3:02:59<6:54:56,  1.61it/s]
 30%|███       | 17426/57600 [3:02:59<6:59:04,  1.60it/s]
 30%|███       | 17427/57600 [3:03:00<6:57:06,  1.61it/s]
 30%|███       | 17428/57600 [3:03:01<6:56:50,  1.61it/s]
 30%|███       | 17429/57600 [3:03:01<6:55:03,  1.61it/s]
 30%|███       | 17430/57600 [3:03:02<6:56:35,  1.61it/s]
 30%|███       | 17431/57600 [3:03:02<6:55:37,  1.61it/s]
 30%|███       | 17432/57600 [3:03:03<6:47:50,  1.64it/s]
 30%|███       | 17433/57600 [3:03:04<7:13:31,  1.54it/s]
 30%|███       | 17434/57600 [3:03:04<6:57:15,  1.60it/s]
 30%|███       | 17435/57600 [3:03:05<6:48:19,  1.64it/s]
 30%|███       | 17436/57600 [3:03:06<6:47:46,  1.64it/s]
 30%|███       | 17437/57600 [3:03:06<6:51:21,  1.63it/s]
 30%|███       | 17438/57600 [3:03:07<6:59:41,  1.59it/s]
 30%|███       | 17439/57600 [3:03:07<7:04:29,  1.58it/s]
 30%|███       | 17440/57600 [3:03:08<6:59:51,  1.59it/s]
                                                         
{'loss': 1.2685, 'learning_rate': 7.296864111498258e-07, 'epoch': 192.49}

 30%|███       | 17440/57600 [3:03:08<6:59:51,  1.59it/s]
 30%|███       | 17441/57600 [3:03:09<7:07:24,  1.57it/s]
 30%|███       | 17442/57600 [3:03:09<7:01:10,  1.59it/s]
 30%|███       | 17443/57600 [3:03:10<7:16:29,  1.53it/s]
 30%|███       | 17444/57600 [3:03:11<7:11:13,  1.55it/s]
 30%|███       | 17445/57600 [3:03:11<7:06:44,  1.57it/s]
 30%|███       | 17446/57600 [3:03:12<7:00:42,  1.59it/s]
 30%|███       | 17447/57600 [3:03:12<6:49:04,  1.64it/s]
 30%|███       | 17448/57600 [3:03:13<6:53:46,  1.62it/s]
 30%|███       | 17449/57600 [3:03:14<6:47:05,  1.64it/s]
 30%|███       | 17450/57600 [3:03:14<6:44:14,  1.66it/s]
 30%|███       | 17451/57600 [3:03:15<6:48:58,  1.64it/s]
 30%|███       | 17452/57600 [3:03:16<7:05:26,  1.57it/s]
 30%|███       | 17453/57600 [3:03:16<6:51:38,  1.63it/s]
 30%|███       | 17454/57600 [3:03:17<6:48:40,  1.64it/s]
 30%|███       | 17455/57600 [3:03:17<6:46:12,  1.65it/s]
 30%|███       | 17456/57600 [3:03:18<6:49:29,  1.63it/s]
 30%|███       | 17457/57600 [3:03:19<6:57:27,  1.60it/s]
 30%|███       | 17458/57600 [3:03:19<7:01:38,  1.59it/s]
 30%|███       | 17459/57600 [3:03:20<6:56:21,  1.61it/s]
 30%|███       | 17460/57600 [3:03:21<6:56:38,  1.61it/s]
                                                         
{'loss': 1.285, 'learning_rate': 7.293728222996516e-07, 'epoch': 192.72}

 30%|███       | 17460/57600 [3:03:21<6:56:38,  1.61it/s]
 30%|███       | 17461/57600 [3:03:21<7:10:26,  1.55it/s]
 30%|███       | 17462/57600 [3:03:22<7:10:42,  1.55it/s]
 30%|███       | 17463/57600 [3:03:23<7:09:32,  1.56it/s]
 30%|███       | 17464/57600 [3:03:23<6:58:33,  1.60it/s]
 30%|███       | 17465/57600 [3:03:24<6:49:29,  1.63it/s]
 30%|███       | 17466/57600 [3:03:24<6:58:33,  1.60it/s]
 30%|███       | 17467/57600 [3:03:25<6:53:24,  1.62it/s]
 30%|███       | 17468/57600 [3:03:26<6:54:57,  1.61it/s]
 30%|███       | 17469/57600 [3:03:26<7:02:52,  1.58it/s]
 30%|███       | 17470/57600 [3:03:27<7:03:45,  1.58it/s]
 30%|███       | 17471/57600 [3:03:27<6:56:16,  1.61it/s]
 30%|███       | 17472/57600 [3:03:28<7:05:01,  1.57it/s]
 30%|███       | 17473/57600 [3:03:29<7:04:13,  1.58it/s]
 30%|███       | 17474/57600 [3:03:29<6:50:08,  1.63it/s]
 30%|███       | 17475/57600 [3:03:30<6:59:44,  1.59it/s]
 30%|███       | 17476/57600 [3:03:31<6:50:50,  1.63it/s]
 30%|███       | 17477/57600 [3:03:31<6:55:26,  1.61it/s]
 30%|███       | 17478/57600 [3:03:32<6:59:23,  1.59it/s]
 30%|███       | 17479/57600 [3:03:32<7:03:34,  1.58it/s]
 30%|███       | 17480/57600 [3:03:33<7:01:28,  1.59it/s]
                                                         
{'loss': 1.2741, 'learning_rate': 7.290592334494773e-07, 'epoch': 192.94}

 30%|███       | 17480/57600 [3:03:33<7:01:28,  1.59it/s]
 30%|███       | 17481/57600 [3:03:34<6:58:36,  1.60it/s]
 30%|███       | 17482/57600 [3:03:34<6:52:34,  1.62it/s]
 30%|███       | 17483/57600 [3:03:35<6:51:03,  1.63it/s]
 30%|███       | 17484/57600 [3:03:36<6:52:47,  1.62it/s]
 30%|███       | 17485/57600 [3:03:36<6:46:06,  1.65it/s]
 30%|███       | 17486/57600 [3:03:37<7:09:57,  1.55it/s]
 30%|███       | 17487/57600 [3:03:38<7:12:32,  1.55it/s]
 30%|███       | 17488/57600 [3:03:38<7:01:41,  1.59it/s]
 30%|███       | 17489/57600 [3:03:39<7:11:21,  1.55it/s]
 30%|███       | 17490/57600 [3:03:39<7:10:11,  1.55it/s]
 30%|███       | 17491/57600 [3:03:40<7:05:35,  1.57it/s]
 30%|███       | 17492/57600 [3:03:41<7:23:44,  1.51it/s]
 30%|███       | 17493/57600 [3:03:41<7:11:31,  1.55it/s]
 30%|███       | 17494/57600 [3:03:42<7:13:19,  1.54it/s]
 30%|███       | 17495/57600 [3:03:43<7:09:58,  1.55it/s]
 30%|███       | 17496/57600 [3:03:43<7:10:49,  1.55it/s]
 30%|███       | 17497/57600 [3:03:44<7:01:24,  1.59it/s]
 30%|███       | 17498/57600 [3:03:44<6:51:24,  1.62it/s]
 30%|███       | 17499/57600 [3:03:45<6:56:48,  1.60it/s]
 30%|███       | 17500/57600 [3:03:46<7:20:37,  1.52it/s]
                                                         
{'loss': 1.275, 'learning_rate': 7.28745644599303e-07, 'epoch': 193.16}

 30%|███       | 17500/57600 [3:03:46<7:20:37,  1.52it/s]
 30%|███       | 17501/57600 [3:03:46<7:08:24,  1.56it/s]
 30%|███       | 17502/57600 [3:03:47<7:09:53,  1.55it/s]
 30%|███       | 17503/57600 [3:03:48<6:55:14,  1.61it/s]
 30%|███       | 17504/57600 [3:03:48<7:01:29,  1.59it/s]
 30%|███       | 17505/57600 [3:03:49<6:59:16,  1.59it/s]
 30%|███       | 17506/57600 [3:03:50<6:50:38,  1.63it/s]
 30%|███       | 17507/57600 [3:03:50<6:59:23,  1.59it/s]
 30%|███       | 17508/57600 [3:03:51<7:02:34,  1.58it/s]
 30%|███       | 17509/57600 [3:03:51<6:54:43,  1.61it/s]
 30%|███       | 17510/57600 [3:03:52<6:52:39,  1.62it/s]
 30%|███       | 17511/57600 [3:03:53<6:46:33,  1.64it/s]
 30%|███       | 17512/57600 [3:03:53<7:04:06,  1.58it/s]
 30%|███       | 17513/57600 [3:03:54<7:06:33,  1.57it/s]
 30%|███       | 17514/57600 [3:03:55<7:00:49,  1.59it/s]
 30%|███       | 17515/57600 [3:03:55<6:56:00,  1.61it/s]
 30%|███       | 17516/57600 [3:03:56<7:06:23,  1.57it/s]
 30%|███       | 17517/57600 [3:03:56<6:55:42,  1.61it/s]
 30%|███       | 17518/57600 [3:03:57<6:49:35,  1.63it/s]
 30%|███       | 17519/57600 [3:03:58<6:42:24,  1.66it/s]
 30%|███       | 17520/57600 [3:03:58<6:39:48,  1.67it/s]
                                                         
{'loss': 1.2641, 'learning_rate': 7.284320557491289e-07, 'epoch': 193.38}

 30%|███       | 17520/57600 [3:03:58<6:39:48,  1.67it/s]
 30%|███       | 17521/57600 [3:03:59<6:42:12,  1.66it/s]
 30%|███       | 17522/57600 [3:03:59<6:51:40,  1.62it/s]
 30%|███       | 17523/57600 [3:04:00<7:05:58,  1.57it/s]
 30%|███       | 17524/57600 [3:04:01<7:05:37,  1.57it/s]
 30%|███       | 17525/57600 [3:04:01<7:05:51,  1.57it/s]
 30%|███       | 17526/57600 [3:04:02<6:57:39,  1.60it/s]
 30%|███       | 17527/57600 [3:04:03<6:55:21,  1.61it/s]
 30%|███       | 17528/57600 [3:04:03<6:43:54,  1.65it/s]
 30%|███       | 17529/57600 [3:04:04<6:50:34,  1.63it/s]
 30%|███       | 17530/57600 [3:04:04<6:42:04,  1.66it/s]
 30%|███       | 17531/57600 [3:04:05<6:36:54,  1.68it/s]
 30%|███       | 17532/57600 [3:04:06<6:51:50,  1.62it/s]
 30%|███       | 17533/57600 [3:04:06<6:43:34,  1.65it/s]
 30%|███       | 17534/57600 [3:04:07<6:48:10,  1.64it/s]
 30%|███       | 17535/57600 [3:04:07<6:42:19,  1.66it/s]
 30%|███       | 17536/57600 [3:04:08<6:40:26,  1.67it/s]
 30%|███       | 17537/57600 [3:04:09<6:41:14,  1.66it/s]
 30%|███       | 17538/57600 [3:04:09<6:46:11,  1.64it/s]
 30%|███       | 17539/57600 [3:04:10<6:32:00,  1.70it/s]
 30%|███       | 17540/57600 [3:04:10<6:33:02,  1.70it/s]
                                                         
{'loss': 1.3078, 'learning_rate': 7.281184668989547e-07, 'epoch': 193.6}

 30%|███       | 17540/57600 [3:04:10<6:33:02,  1.70it/s]
 30%|███       | 17541/57600 [3:04:11<6:40:38,  1.67it/s]
 30%|███       | 17542/57600 [3:04:12<6:44:07,  1.65it/s]
 30%|███       | 17543/57600 [3:04:12<6:52:36,  1.62it/s]
 30%|███       | 17544/57600 [3:04:13<6:58:39,  1.59it/s]
 30%|███       | 17545/57600 [3:04:14<6:53:12,  1.62it/s]
 30%|███       | 17546/57600 [3:04:14<6:54:20,  1.61it/s]
 30%|███       | 17547/57600 [3:04:15<6:48:27,  1.63it/s]
 30%|███       | 17548/57600 [3:04:15<7:03:43,  1.58it/s]
 30%|███       | 17549/57600 [3:04:16<7:01:19,  1.58it/s]
 30%|███       | 17550/57600 [3:04:17<7:17:05,  1.53it/s]
 30%|███       | 17551/57600 [3:04:17<7:16:06,  1.53it/s]
 30%|███       | 17552/57600 [3:04:18<7:08:48,  1.56it/s]
 30%|███       | 17553/57600 [3:04:19<7:04:31,  1.57it/s]
 30%|███       | 17554/57600 [3:04:19<7:08:06,  1.56it/s]
 30%|███       | 17555/57600 [3:04:20<6:58:43,  1.59it/s]
 30%|███       | 17556/57600 [3:04:21<6:59:12,  1.59it/s]
 30%|███       | 17557/57600 [3:04:21<7:10:08,  1.55it/s]
 30%|███       | 17558/57600 [3:04:22<7:17:51,  1.52it/s]
 30%|███       | 17559/57600 [3:04:23<7:12:36,  1.54it/s]
 30%|███       | 17560/57600 [3:04:23<7:00:46,  1.59it/s]
                                                         
{'loss': 1.2516, 'learning_rate': 7.278048780487804e-07, 'epoch': 193.82}

 30%|███       | 17560/57600 [3:04:23<7:00:46,  1.59it/s]
 30%|███       | 17561/57600 [3:04:24<6:53:58,  1.61it/s]
 30%|███       | 17562/57600 [3:04:24<7:05:42,  1.57it/s]
 30%|███       | 17563/57600 [3:04:25<7:05:47,  1.57it/s]
 30%|███       | 17564/57600 [3:04:26<6:58:21,  1.59it/s]
 30%|███       | 17565/57600 [3:04:26<6:57:42,  1.60it/s]
 30%|███       | 17566/57600 [3:04:27<6:50:31,  1.63it/s]
 30%|███       | 17567/57600 [3:04:28<7:00:11,  1.59it/s]
 30%|███       | 17568/57600 [3:04:28<6:48:50,  1.63it/s]
 31%|███       | 17569/57600 [3:04:29<6:52:13,  1.62it/s]
 31%|███       | 17570/57600 [3:04:29<6:47:23,  1.64it/s]
 31%|███       | 17571/57600 [3:04:30<6:48:11,  1.63it/s]
 31%|███       | 17572/57600 [3:04:31<6:56:36,  1.60it/s]
 31%|███       | 17573/57600 [3:04:31<6:56:51,  1.60it/s]
 31%|███       | 17574/57600 [3:04:32<6:49:33,  1.63it/s]
 31%|███       | 17575/57600 [3:04:32<6:45:42,  1.64it/s]
 31%|███       | 17576/57600 [3:04:33<6:50:33,  1.62it/s]
 31%|███       | 17577/57600 [3:04:34<7:03:02,  1.58it/s]
 31%|███       | 17578/57600 [3:04:34<6:58:58,  1.59it/s]
 31%|███       | 17579/57600 [3:04:35<6:59:11,  1.59it/s]
 31%|███       | 17580/57600 [3:04:36<6:49:04,  1.63it/s]
                                                         
{'loss': 1.2708, 'learning_rate': 7.274912891986062e-07, 'epoch': 194.04}

 31%|███       | 17580/57600 [3:04:36<6:49:04,  1.63it/s]
 31%|███       | 17581/57600 [3:04:36<6:57:41,  1.60it/s]
 31%|███       | 17582/57600 [3:04:37<6:43:57,  1.65it/s]
 31%|███       | 17583/57600 [3:04:37<6:36:18,  1.68it/s]
 31%|███       | 17584/57600 [3:04:38<6:43:08,  1.65it/s]
 31%|███       | 17585/57600 [3:04:39<6:43:31,  1.65it/s]
 31%|███       | 17586/57600 [3:04:39<6:38:11,  1.67it/s]
 31%|███       | 17587/57600 [3:04:40<6:44:35,  1.65it/s]
 31%|███       | 17588/57600 [3:04:40<6:42:13,  1.66it/s]
 31%|███       | 17589/57600 [3:04:41<6:42:25,  1.66it/s]
 31%|███       | 17590/57600 [3:04:42<6:45:57,  1.64it/s]
 31%|███       | 17591/57600 [3:04:42<6:59:06,  1.59it/s]
 31%|███       | 17592/57600 [3:04:43<6:56:59,  1.60it/s]
 31%|███       | 17593/57600 [3:04:44<7:12:06,  1.54it/s]
 31%|███       | 17594/57600 [3:04:44<7:06:47,  1.56it/s]
 31%|███       | 17595/57600 [3:04:45<6:52:02,  1.62it/s]
 31%|███       | 17596/57600 [3:04:45<6:57:22,  1.60it/s]
 31%|███       | 17597/57600 [3:04:46<7:12:55,  1.54it/s]
 31%|███       | 17598/57600 [3:04:47<6:58:41,  1.59it/s]
 31%|███       | 17599/57600 [3:04:47<6:50:25,  1.62it/s]
 31%|███       | 17600/57600 [3:04:48<6:55:38,  1.60it/s]
                                                         
{'loss': 1.265, 'learning_rate': 7.271777003484321e-07, 'epoch': 194.26}

 31%|███       | 17600/57600 [3:04:48<6:55:38,  1.60it/s]
 31%|███       | 17601/57600 [3:04:49<6:57:57,  1.59it/s]
 31%|███       | 17602/57600 [3:04:49<7:01:14,  1.58it/s]
 31%|███       | 17603/57600 [3:04:50<6:56:02,  1.60it/s]
 31%|███       | 17604/57600 [3:04:50<6:48:46,  1.63it/s]
 31%|███       | 17605/57600 [3:04:51<6:51:30,  1.62it/s]
 31%|███       | 17606/57600 [3:04:52<6:42:40,  1.66it/s]
 31%|███       | 17607/57600 [3:04:52<6:46:46,  1.64it/s]
 31%|███       | 17608/57600 [3:04:53<6:39:48,  1.67it/s]
 31%|███       | 17609/57600 [3:04:53<6:38:57,  1.67it/s]
 31%|███       | 17610/57600 [3:04:54<6:33:41,  1.69it/s]
 31%|███       | 17611/57600 [3:04:55<7:11:33,  1.54it/s]
 31%|███       | 17612/57600 [3:04:55<7:01:41,  1.58it/s]
 31%|███       | 17613/57600 [3:04:56<7:08:13,  1.56it/s]
 31%|███       | 17614/57600 [3:04:57<6:52:53,  1.61it/s]
 31%|███       | 17615/57600 [3:04:57<7:04:58,  1.57it/s]
 31%|███       | 17616/57600 [3:04:58<7:15:41,  1.53it/s]
 31%|███       | 17617/57600 [3:04:59<7:16:59,  1.52it/s]
 31%|███       | 17618/57600 [3:04:59<7:17:30,  1.52it/s]
 31%|███       | 17619/57600 [3:05:00<6:54:51,  1.61it/s]
 31%|███       | 17620/57600 [3:05:00<6:56:18,  1.60it/s]
                                                         
{'loss': 1.2597, 'learning_rate': 7.268641114982578e-07, 'epoch': 194.48}

 31%|███       | 17620/57600 [3:05:00<6:56:18,  1.60it/s]
 31%|███       | 17621/57600 [3:05:01<6:59:50,  1.59it/s]
 31%|███       | 17622/57600 [3:05:02<7:00:11,  1.59it/s]
 31%|███       | 17623/57600 [3:05:02<6:58:32,  1.59it/s]
 31%|███       | 17624/57600 [3:05:03<6:59:05,  1.59it/s]
 31%|███       | 17625/57600 [3:05:04<6:52:48,  1.61it/s]
 31%|███       | 17626/57600 [3:05:04<7:15:10,  1.53it/s]
 31%|███       | 17627/57600 [3:05:05<7:02:50,  1.58it/s]
 31%|███       | 17628/57600 [3:05:06<7:01:09,  1.58it/s]
 31%|███       | 17629/57600 [3:05:06<7:14:20,  1.53it/s]
 31%|███       | 17630/57600 [3:05:07<7:01:36,  1.58it/s]
 31%|███       | 17631/57600 [3:05:07<7:10:24,  1.55it/s]
 31%|███       | 17632/57600 [3:05:08<7:07:14,  1.56it/s]
 31%|███       | 17633/57600 [3:05:09<6:53:43,  1.61it/s]
 31%|███       | 17634/57600 [3:05:09<6:47:50,  1.63it/s]
 31%|███       | 17635/57600 [3:05:10<6:44:12,  1.65it/s]
 31%|███       | 17636/57600 [3:05:11<6:49:52,  1.63it/s]
 31%|███       | 17637/57600 [3:05:11<6:54:58,  1.61it/s]
 31%|███       | 17638/57600 [3:05:12<6:50:27,  1.62it/s]
 31%|███       | 17639/57600 [3:05:12<6:49:14,  1.63it/s]
 31%|███       | 17640/57600 [3:05:13<6:53:52,  1.61it/s]
                                                         
{'loss': 1.2685, 'learning_rate': 7.265505226480835e-07, 'epoch': 194.7}

 31%|███       | 17640/57600 [3:05:13<6:53:52,  1.61it/s]
 31%|███       | 17641/57600 [3:05:14<6:43:53,  1.65it/s]
 31%|███       | 17642/57600 [3:05:14<6:41:32,  1.66it/s]
 31%|███       | 17643/57600 [3:05:15<6:46:51,  1.64it/s]
 31%|███       | 17644/57600 [3:05:15<6:45:52,  1.64it/s]
 31%|███       | 17645/57600 [3:05:16<6:47:17,  1.63it/s]
 31%|███       | 17646/57600 [3:05:17<6:40:30,  1.66it/s]
 31%|███       | 17647/57600 [3:05:17<6:58:53,  1.59it/s]
 31%|███       | 17648/57600 [3:05:18<6:54:37,  1.61it/s]
 31%|███       | 17649/57600 [3:05:18<6:45:12,  1.64it/s]
 31%|███       | 17650/57600 [3:05:19<6:51:35,  1.62it/s]
 31%|███       | 17651/57600 [3:05:20<6:38:45,  1.67it/s]
 31%|███       | 17652/57600 [3:05:20<6:41:50,  1.66it/s]
 31%|███       | 17653/57600 [3:05:21<6:46:42,  1.64it/s]
 31%|███       | 17654/57600 [3:05:21<6:39:02,  1.67it/s]
 31%|███       | 17655/57600 [3:05:22<7:00:17,  1.58it/s]
 31%|███       | 17656/57600 [3:05:23<6:54:15,  1.61it/s]
 31%|███       | 17657/57600 [3:05:23<7:05:57,  1.56it/s]
 31%|███       | 17658/57600 [3:05:24<6:55:28,  1.60it/s]
 31%|███       | 17659/57600 [3:05:25<6:53:10,  1.61it/s]
 31%|███       | 17660/57600 [3:05:25<6:48:29,  1.63it/s]
                                                         
{'loss': 1.2869, 'learning_rate': 7.262369337979094e-07, 'epoch': 194.92}

 31%|███       | 17660/57600 [3:05:25<6:48:29,  1.63it/s]
 31%|███       | 17661/57600 [3:05:26<6:48:23,  1.63it/s]
 31%|███       | 17662/57600 [3:05:27<6:50:51,  1.62it/s]
 31%|███       | 17663/57600 [3:05:27<6:58:54,  1.59it/s]
 31%|███       | 17664/57600 [3:05:28<6:59:03,  1.59it/s]
 31%|███       | 17665/57600 [3:05:28<6:57:07,  1.60it/s]
 31%|███       | 17666/57600 [3:05:29<6:48:41,  1.63it/s]
 31%|███       | 17667/57600 [3:05:30<6:50:39,  1.62it/s]
 31%|███       | 17668/57600 [3:05:30<6:58:51,  1.59it/s]
 31%|███       | 17669/57600 [3:05:31<6:59:16,  1.59it/s]
 31%|███       | 17670/57600 [3:05:32<7:13:27,  1.54it/s]
 31%|███       | 17671/57600 [3:05:32<7:14:40,  1.53it/s]
 31%|███       | 17672/57600 [3:05:33<7:13:06,  1.54it/s]
 31%|███       | 17673/57600 [3:05:34<7:03:00,  1.57it/s]
 31%|███       | 17674/57600 [3:05:34<7:12:40,  1.54it/s]
 31%|███       | 17675/57600 [3:05:35<6:51:59,  1.62it/s]
 31%|███       | 17676/57600 [3:05:35<6:51:20,  1.62it/s]
 31%|███       | 17677/57600 [3:05:36<6:43:49,  1.65it/s]
 31%|███       | 17678/57600 [3:05:37<6:52:26,  1.61it/s]
 31%|███       | 17679/57600 [3:05:37<7:08:21,  1.55it/s]
 31%|███       | 17680/57600 [3:05:38<7:05:45,  1.56it/s]
                                                         
{'loss': 1.2597, 'learning_rate': 7.259233449477352e-07, 'epoch': 195.14}

 31%|███       | 17680/57600 [3:05:38<7:05:45,  1.56it/s]
 31%|███       | 17681/57600 [3:05:39<6:55:55,  1.60it/s]
 31%|███       | 17682/57600 [3:05:39<6:47:07,  1.63it/s]
 31%|███       | 17683/57600 [3:05:40<6:49:35,  1.62it/s]
 31%|███       | 17684/57600 [3:05:40<6:54:26,  1.61it/s]
 31%|███       | 17685/57600 [3:05:41<6:53:49,  1.61it/s]
 31%|███       | 17686/57600 [3:05:42<6:50:41,  1.62it/s]
 31%|███       | 17687/57600 [3:05:42<6:56:11,  1.60it/s]
 31%|███       | 17688/57600 [3:05:43<6:39:17,  1.67it/s]
 31%|███       | 17689/57600 [3:05:43<6:55:49,  1.60it/s]
 31%|███       | 17690/57600 [3:05:44<7:04:12,  1.57it/s]
 31%|███       | 17691/57600 [3:05:45<6:59:03,  1.59it/s]
 31%|███       | 17692/57600 [3:05:45<6:50:32,  1.62it/s]
 31%|███       | 17693/57600 [3:05:46<6:45:32,  1.64it/s]
 31%|███       | 17694/57600 [3:05:47<6:51:54,  1.61it/s]
 31%|███       | 17695/57600 [3:05:47<6:48:23,  1.63it/s]
 31%|███       | 17696/57600 [3:05:48<6:53:13,  1.61it/s]
 31%|███       | 17697/57600 [3:05:48<6:59:02,  1.59it/s]
 31%|███       | 17698/57600 [3:05:49<6:49:39,  1.62it/s]
 31%|███       | 17699/57600 [3:05:50<6:38:19,  1.67it/s]
 31%|███       | 17700/57600 [3:05:50<6:56:36,  1.60it/s]
                                                         
{'loss': 1.2579, 'learning_rate': 7.25609756097561e-07, 'epoch': 195.36}

 31%|███       | 17700/57600 [3:05:50<6:56:36,  1.60it/s]
 31%|███       | 17701/57600 [3:05:51<7:01:18,  1.58it/s]
 31%|███       | 17702/57600 [3:05:52<7:00:21,  1.58it/s]
 31%|███       | 17703/57600 [3:05:52<6:54:16,  1.61it/s]
 31%|███       | 17704/57600 [3:05:53<6:52:56,  1.61it/s]
 31%|███       | 17705/57600 [3:05:53<6:52:46,  1.61it/s]
 31%|███       | 17706/57600 [3:05:54<7:02:30,  1.57it/s]
 31%|███       | 17707/57600 [3:05:55<6:54:55,  1.60it/s]
 31%|███       | 17708/57600 [3:05:55<6:52:37,  1.61it/s]
 31%|███       | 17709/57600 [3:05:56<7:08:02,  1.55it/s]
 31%|███       | 17710/57600 [3:05:57<7:14:31,  1.53it/s]
 31%|███       | 17711/57600 [3:05:57<7:07:43,  1.55it/s]
 31%|███       | 17712/57600 [3:05:58<7:00:29,  1.58it/s]
 31%|███       | 17713/57600 [3:05:58<6:49:48,  1.62it/s]
 31%|███       | 17714/57600 [3:05:59<6:44:03,  1.65it/s]
 31%|███       | 17715/57600 [3:06:00<6:34:48,  1.68it/s]
 31%|███       | 17716/57600 [3:06:00<6:45:16,  1.64it/s]
 31%|███       | 17717/57600 [3:06:01<6:46:31,  1.64it/s]
 31%|███       | 17718/57600 [3:06:02<6:56:41,  1.60it/s]
 31%|███       | 17719/57600 [3:06:02<6:52:43,  1.61it/s]
 31%|███       | 17720/57600 [3:06:03<7:02:03,  1.57it/s]
                                                         
{'loss': 1.2641, 'learning_rate': 7.252961672473867e-07, 'epoch': 195.58}

 31%|███       | 17720/57600 [3:06:03<7:02:03,  1.57it/s]
 31%|███       | 17721/57600 [3:06:03<6:51:30,  1.62it/s]
 31%|███       | 17722/57600 [3:06:04<6:58:12,  1.59it/s]
 31%|███       | 17723/57600 [3:06:05<7:19:01,  1.51it/s]
 31%|███       | 17724/57600 [3:06:05<7:18:36,  1.52it/s]
 31%|███       | 17725/57600 [3:06:06<7:13:47,  1.53it/s]
 31%|███       | 17726/57600 [3:06:07<7:09:00,  1.55it/s]
 31%|███       | 17727/57600 [3:06:07<7:08:11,  1.55it/s]
 31%|███       | 17728/57600 [3:06:08<7:07:49,  1.55it/s]
 31%|███       | 17729/57600 [3:06:09<7:01:03,  1.58it/s]
 31%|███       | 17730/57600 [3:06:09<6:58:35,  1.59it/s]
 31%|███       | 17731/57600 [3:06:10<7:02:31,  1.57it/s]
 31%|███       | 17732/57600 [3:06:10<7:02:09,  1.57it/s]
 31%|███       | 17733/57600 [3:06:11<6:54:40,  1.60it/s]
 31%|███       | 17734/57600 [3:06:12<6:39:23,  1.66it/s]
 31%|███       | 17735/57600 [3:06:12<6:44:11,  1.64it/s]
 31%|███       | 17736/57600 [3:06:13<6:43:27,  1.65it/s]
 31%|███       | 17737/57600 [3:06:14<6:49:10,  1.62it/s]
 31%|███       | 17738/57600 [3:06:14<6:52:29,  1.61it/s]
 31%|███       | 17739/57600 [3:06:15<6:57:02,  1.59it/s]
 31%|███       | 17740/57600 [3:06:15<6:49:57,  1.62it/s]
                                                         
{'loss': 1.2782, 'learning_rate': 7.249825783972126e-07, 'epoch': 195.81}

 31%|███       | 17740/57600 [3:06:15<6:49:57,  1.62it/s]
 31%|███       | 17741/57600 [3:06:16<6:52:02,  1.61it/s]
 31%|███       | 17742/57600 [3:06:17<6:52:56,  1.61it/s]
 31%|███       | 17743/57600 [3:06:17<6:42:23,  1.65it/s]
 31%|███       | 17744/57600 [3:06:18<6:34:11,  1.69it/s]
 31%|███       | 17745/57600 [3:06:18<6:24:32,  1.73it/s]
 31%|███       | 17746/57600 [3:06:19<6:32:12,  1.69it/s]
 31%|███       | 17747/57600 [3:06:19<6:22:18,  1.74it/s]
 31%|███       | 17748/57600 [3:06:20<6:29:55,  1.70it/s]
 31%|███       | 17749/57600 [3:06:21<6:39:42,  1.66it/s]
 31%|███       | 17750/57600 [3:06:21<6:40:45,  1.66it/s]
 31%|███       | 17751/57600 [3:06:22<6:44:54,  1.64it/s]
 31%|███       | 17752/57600 [3:06:23<6:46:28,  1.63it/s]
 31%|███       | 17753/57600 [3:06:23<6:56:10,  1.60it/s]
 31%|███       | 17754/57600 [3:06:24<6:57:29,  1.59it/s]
 31%|███       | 17755/57600 [3:06:25<7:09:42,  1.55it/s]
 31%|███       | 17756/57600 [3:06:25<7:09:49,  1.54it/s]
 31%|███       | 17757/57600 [3:06:26<7:05:30,  1.56it/s]
 31%|███       | 17758/57600 [3:06:27<7:16:14,  1.52it/s]
 31%|███       | 17759/57600 [3:06:27<6:55:16,  1.60it/s]
 31%|███       | 17760/57600 [3:06:28<6:55:18,  1.60it/s]
                                                         
{'loss': 1.2705, 'learning_rate': 7.246689895470382e-07, 'epoch': 196.03}

 31%|███       | 17760/57600 [3:06:28<6:55:18,  1.60it/s]
 31%|███       | 17761/57600 [3:06:28<6:56:44,  1.59it/s]
 31%|███       | 17762/57600 [3:06:29<7:05:33,  1.56it/s]
 31%|███       | 17763/57600 [3:06:30<6:52:26,  1.61it/s]
 31%|███       | 17764/57600 [3:06:30<6:56:42,  1.59it/s]
 31%|███       | 17765/57600 [3:06:31<7:02:36,  1.57it/s]
 31%|███       | 17766/57600 [3:06:32<7:05:27,  1.56it/s]
 31%|███       | 17767/57600 [3:06:32<7:00:16,  1.58it/s]
 31%|███       | 17768/57600 [3:06:33<7:09:37,  1.55it/s]
 31%|███       | 17769/57600 [3:06:33<6:56:24,  1.59it/s]
 31%|███       | 17770/57600 [3:06:34<6:55:09,  1.60it/s]
 31%|███       | 17771/57600 [3:06:35<6:54:04,  1.60it/s]
 31%|███       | 17772/57600 [3:06:35<6:54:28,  1.60it/s]
 31%|███       | 17773/57600 [3:06:36<7:01:13,  1.58it/s]
 31%|███       | 17774/57600 [3:06:37<6:55:57,  1.60it/s]
 31%|███       | 17775/57600 [3:06:37<6:50:35,  1.62it/s]
 31%|███       | 17776/57600 [3:06:38<6:41:44,  1.65it/s]
 31%|███       | 17777/57600 [3:06:38<6:59:45,  1.58it/s]
 31%|███       | 17778/57600 [3:06:39<6:59:14,  1.58it/s]
 31%|███       | 17779/57600 [3:06:40<7:00:47,  1.58it/s]
 31%|███       | 17780/57600 [3:06:40<6:57:32,  1.59it/s]
                                                         
{'loss': 1.2878, 'learning_rate': 7.24355400696864e-07, 'epoch': 196.25}

 31%|███       | 17780/57600 [3:06:40<6:57:32,  1.59it/s]
 31%|███       | 17781/57600 [3:06:41<6:48:48,  1.62it/s]
 31%|███       | 17782/57600 [3:06:41<6:45:29,  1.64it/s]
 31%|███       | 17783/57600 [3:06:42<6:50:37,  1.62it/s]
 31%|███       | 17784/57600 [3:06:43<7:09:38,  1.54it/s]
 31%|███       | 17785/57600 [3:06:43<6:57:11,  1.59it/s]
 31%|███       | 17786/57600 [3:06:44<7:01:26,  1.57it/s]
 31%|███       | 17787/57600 [3:06:45<6:49:07,  1.62it/s]
 31%|███       | 17788/57600 [3:06:45<6:45:13,  1.64it/s]
 31%|███       | 17789/57600 [3:06:46<6:40:05,  1.66it/s]
 31%|███       | 17790/57600 [3:06:46<6:50:58,  1.61it/s]
 31%|███       | 17791/57600 [3:06:47<7:00:51,  1.58it/s]
 31%|███       | 17792/57600 [3:06:48<6:53:51,  1.60it/s]
 31%|███       | 17793/57600 [3:06:48<6:54:10,  1.60it/s]
 31%|███       | 17794/57600 [3:06:49<6:52:19,  1.61it/s]
 31%|███       | 17795/57600 [3:06:50<6:51:34,  1.61it/s]
 31%|███       | 17796/57600 [3:06:50<6:53:41,  1.60it/s]
 31%|███       | 17797/57600 [3:06:51<6:42:45,  1.65it/s]
 31%|███       | 17798/57600 [3:06:51<6:34:14,  1.68it/s]
 31%|███       | 17799/57600 [3:06:52<6:33:12,  1.69it/s]
 31%|███       | 17800/57600 [3:06:53<6:34:45,  1.68it/s]
                                                         
{'loss': 1.3158, 'learning_rate': 7.240418118466899e-07, 'epoch': 196.47}

 31%|███       | 17800/57600 [3:06:53<6:34:45,  1.68it/s]
 31%|███       | 17801/57600 [3:06:53<6:31:46,  1.69it/s]
 31%|███       | 17802/57600 [3:06:54<6:35:01,  1.68it/s]
 31%|███       | 17803/57600 [3:06:54<6:43:23,  1.64it/s]
 31%|███       | 17804/57600 [3:06:55<6:52:03,  1.61it/s]
 31%|███       | 17805/57600 [3:06:56<6:57:40,  1.59it/s]
 31%|███       | 17806/57600 [3:06:56<7:04:42,  1.56it/s]
 31%|███       | 17807/57600 [3:06:57<7:05:35,  1.56it/s]
 31%|███       | 17808/57600 [3:06:58<7:07:30,  1.55it/s]
 31%|███       | 17809/57600 [3:06:58<6:57:55,  1.59it/s]
 31%|███       | 17810/57600 [3:06:59<7:04:52,  1.56it/s]
 31%|███       | 17811/57600 [3:07:00<7:09:35,  1.54it/s]
 31%|███       | 17812/57600 [3:07:00<7:30:52,  1.47it/s]
 31%|███       | 17813/57600 [3:07:01<7:09:08,  1.55it/s]
 31%|███       | 17814/57600 [3:07:02<7:19:46,  1.51it/s]
 31%|███       | 17815/57600 [3:07:02<7:13:39,  1.53it/s]
 31%|███       | 17816/57600 [3:07:03<6:59:59,  1.58it/s]
 31%|███       | 17817/57600 [3:07:03<6:52:15,  1.61it/s]
 31%|███       | 17818/57600 [3:07:04<6:59:06,  1.58it/s]
 31%|███       | 17819/57600 [3:07:05<6:53:29,  1.60it/s]
 31%|███       | 17820/57600 [3:07:05<6:48:28,  1.62it/s]
                                                         
{'loss': 1.2371, 'learning_rate': 7.237282229965157e-07, 'epoch': 196.69}

 31%|███       | 17820/57600 [3:07:05<6:48:28,  1.62it/s]
 31%|███       | 17821/57600 [3:07:06<6:42:36,  1.65it/s]
 31%|███       | 17822/57600 [3:07:06<6:42:17,  1.65it/s]
 31%|███       | 17823/57600 [3:07:07<6:51:11,  1.61it/s]
 31%|███       | 17824/57600 [3:07:08<7:00:37,  1.58it/s]
 31%|███       | 17825/57600 [3:07:08<6:58:55,  1.58it/s]
 31%|███       | 17826/57600 [3:07:09<6:47:10,  1.63it/s]
 31%|███       | 17827/57600 [3:07:10<6:40:06,  1.66it/s]
 31%|███       | 17828/57600 [3:07:10<6:37:22,  1.67it/s]
 31%|███       | 17829/57600 [3:07:11<6:43:27,  1.64it/s]
 31%|███       | 17830/57600 [3:07:11<6:57:16,  1.59it/s]
 31%|███       | 17831/57600 [3:07:12<7:00:02,  1.58it/s]
 31%|███       | 17832/57600 [3:07:13<7:07:42,  1.55it/s]
 31%|███       | 17833/57600 [3:07:13<6:57:10,  1.59it/s]
 31%|███       | 17834/57600 [3:07:14<6:45:34,  1.63it/s]
 31%|███       | 17835/57600 [3:07:15<6:49:29,  1.62it/s]
 31%|███       | 17836/57600 [3:07:15<6:39:23,  1.66it/s]
 31%|███       | 17837/57600 [3:07:16<6:41:11,  1.65it/s]
 31%|███       | 17838/57600 [3:07:16<6:41:52,  1.65it/s]
 31%|███       | 17839/57600 [3:07:17<6:39:17,  1.66it/s]
 31%|███       | 17840/57600 [3:07:18<6:37:59,  1.66it/s]
                                                         
{'loss': 1.2553, 'learning_rate': 7.234146341463414e-07, 'epoch': 196.91}

 31%|███       | 17840/57600 [3:07:18<6:37:59,  1.66it/s]
 31%|███       | 17841/57600 [3:07:18<6:35:10,  1.68it/s]
 31%|███       | 17842/57600 [3:07:19<6:42:47,  1.65it/s]
 31%|███       | 17843/57600 [3:07:19<6:49:53,  1.62it/s]
 31%|███       | 17844/57600 [3:07:20<6:40:30,  1.65it/s]
 31%|███       | 17845/57600 [3:07:21<6:55:15,  1.60it/s]
 31%|███       | 17846/57600 [3:07:21<6:52:37,  1.61it/s]
 31%|███       | 17847/57600 [3:07:22<6:37:19,  1.67it/s]
 31%|███       | 17848/57600 [3:07:22<6:41:17,  1.65it/s]
 31%|███       | 17849/57600 [3:07:23<7:03:18,  1.57it/s]
 31%|███       | 17850/57600 [3:07:24<7:01:22,  1.57it/s]
 31%|███       | 17851/57600 [3:07:24<6:46:28,  1.63it/s]
 31%|███       | 17852/57600 [3:07:25<6:36:57,  1.67it/s]
 31%|███       | 17853/57600 [3:07:26<6:49:15,  1.62it/s]
 31%|███       | 17854/57600 [3:07:26<7:02:11,  1.57it/s]
 31%|███       | 17855/57600 [3:07:27<6:58:23,  1.58it/s]
 31%|███       | 17856/57600 [3:07:27<6:47:39,  1.62it/s]
 31%|███       | 17857/57600 [3:07:28<6:48:15,  1.62it/s]
 31%|███       | 17858/57600 [3:07:29<6:54:48,  1.60it/s]
 31%|███       | 17859/57600 [3:07:29<6:49:43,  1.62it/s]
 31%|███       | 17860/57600 [3:07:30<6:46:59,  1.63it/s]
                                                         
{'loss': 1.2847, 'learning_rate': 7.231010452961672e-07, 'epoch': 197.13}

 31%|███       | 17860/57600 [3:07:30<6:46:59,  1.63it/s]
 31%|███       | 17861/57600 [3:07:31<6:41:23,  1.65it/s]
 31%|███       | 17862/57600 [3:07:31<7:05:03,  1.56it/s]
 31%|███       | 17863/57600 [3:07:32<7:09:47,  1.54it/s]
 31%|███       | 17864/57600 [3:07:32<6:58:42,  1.58it/s]
 31%|███       | 17865/57600 [3:07:33<6:50:26,  1.61it/s]
 31%|███       | 17866/57600 [3:07:34<6:49:34,  1.62it/s]
 31%|███       | 17867/57600 [3:07:34<6:43:04,  1.64it/s]
 31%|███       | 17868/57600 [3:07:35<6:41:01,  1.65it/s]
 31%|███       | 17869/57600 [3:07:35<6:32:58,  1.69it/s]
 31%|███       | 17870/57600 [3:07:36<6:53:33,  1.60it/s]
 31%|███       | 17871/57600 [3:07:37<7:07:50,  1.55it/s]
 31%|███       | 17872/57600 [3:07:37<7:06:47,  1.55it/s]
 31%|███       | 17873/57600 [3:07:38<6:57:53,  1.58it/s]
 31%|███       | 17874/57600 [3:07:39<7:01:25,  1.57it/s]
 31%|███       | 17875/57600 [3:07:39<6:56:31,  1.59it/s]
 31%|███       | 17876/57600 [3:07:40<6:55:34,  1.59it/s]
 31%|███       | 17877/57600 [3:07:41<6:49:18,  1.62it/s]
 31%|███       | 17878/57600 [3:07:41<6:58:37,  1.58it/s]
 31%|███       | 17879/57600 [3:07:42<7:17:10,  1.51it/s]
 31%|███       | 17880/57600 [3:07:43<7:12:01,  1.53it/s]
                                                         
{'loss': 1.2516, 'learning_rate': 7.22787456445993e-07, 'epoch': 197.35}

 31%|███       | 17880/57600 [3:07:43<7:12:01,  1.53it/s]
 31%|███       | 17881/57600 [3:07:43<6:52:05,  1.61it/s]
 31%|███       | 17882/57600 [3:07:44<7:13:55,  1.53it/s]
 31%|███       | 17883/57600 [3:07:44<7:07:37,  1.55it/s]
 31%|███       | 17884/57600 [3:07:45<6:58:50,  1.58it/s]
 31%|███       | 17885/57600 [3:07:46<6:47:45,  1.62it/s]
 31%|███       | 17886/57600 [3:07:46<6:58:23,  1.58it/s]
 31%|███       | 17887/57600 [3:07:47<6:41:34,  1.65it/s]
 31%|███       | 17888/57600 [3:07:47<6:41:31,  1.65it/s]
 31%|███       | 17889/57600 [3:07:48<6:46:27,  1.63it/s]
 31%|███       | 17890/57600 [3:07:49<6:47:32,  1.62it/s]
 31%|███       | 17891/57600 [3:07:49<6:48:10,  1.62it/s]
 31%|███       | 17892/57600 [3:07:50<6:53:36,  1.60it/s]
 31%|███       | 17893/57600 [3:07:51<6:56:07,  1.59it/s]
 31%|███       | 17894/57600 [3:07:51<6:49:12,  1.62it/s]
 31%|███       | 17895/57600 [3:07:52<6:54:22,  1.60it/s]
 31%|███       | 17896/57600 [3:07:52<6:50:30,  1.61it/s]
 31%|███       | 17897/57600 [3:07:53<7:00:18,  1.57it/s]
 31%|███       | 17898/57600 [3:07:54<6:47:45,  1.62it/s]
 31%|███       | 17899/57600 [3:07:54<6:57:28,  1.58it/s]
 31%|███       | 17900/57600 [3:07:55<7:00:06,  1.57it/s]
                                                         
{'loss': 1.2802, 'learning_rate': 7.224738675958188e-07, 'epoch': 197.57}

 31%|███       | 17900/57600 [3:07:55<7:00:06,  1.57it/s]
 31%|███       | 17901/57600 [3:07:56<7:03:53,  1.56it/s]
 31%|███       | 17902/57600 [3:07:56<7:02:57,  1.56it/s]
 31%|███       | 17903/57600 [3:07:57<6:58:41,  1.58it/s]
 31%|███       | 17904/57600 [3:07:58<7:06:22,  1.55it/s]
 31%|███       | 17905/57600 [3:07:58<6:59:21,  1.58it/s]
 31%|███       | 17906/57600 [3:07:59<7:05:41,  1.55it/s]
 31%|███       | 17907/57600 [3:07:59<6:55:15,  1.59it/s]
 31%|███       | 17908/57600 [3:08:00<6:49:10,  1.62it/s]
 31%|███       | 17909/57600 [3:08:01<6:51:43,  1.61it/s]
 31%|███       | 17910/57600 [3:08:01<6:48:18,  1.62it/s]
 31%|███       | 17911/57600 [3:08:02<6:40:24,  1.65it/s]
 31%|███       | 17912/57600 [3:08:03<6:51:43,  1.61it/s]
 31%|███       | 17913/57600 [3:08:03<6:47:25,  1.62it/s]
 31%|███       | 17914/57600 [3:08:04<6:47:25,  1.62it/s]
 31%|███       | 17915/57600 [3:08:04<7:05:23,  1.55it/s]
 31%|███       | 17916/57600 [3:08:05<6:59:59,  1.57it/s]
 31%|███       | 17917/57600 [3:08:06<6:58:43,  1.58it/s]
 31%|███       | 17918/57600 [3:08:06<6:59:01,  1.58it/s]
 31%|███       | 17919/57600 [3:08:07<6:42:45,  1.64it/s]
 31%|███       | 17920/57600 [3:08:07<6:35:39,  1.67it/s]
                                                         
{'loss': 1.2839, 'learning_rate': 7.221602787456446e-07, 'epoch': 197.79}

 31%|███       | 17920/57600 [3:08:07<6:35:39,  1.67it/s]
 31%|███       | 17921/57600 [3:08:08<6:37:36,  1.66it/s]
 31%|███       | 17922/57600 [3:08:09<7:13:31,  1.53it/s]
 31%|███       | 17923/57600 [3:08:09<7:05:01,  1.56it/s]
 31%|███       | 17924/57600 [3:08:10<6:56:34,  1.59it/s]
 31%|███       | 17925/57600 [3:08:11<6:45:43,  1.63it/s]
 31%|███       | 17926/57600 [3:08:11<6:42:04,  1.64it/s]
 31%|███       | 17927/57600 [3:08:12<6:47:21,  1.62it/s]
 31%|███       | 17928/57600 [3:08:13<6:48:29,  1.62it/s]
 31%|███       | 17929/57600 [3:08:13<6:37:43,  1.66it/s]
 31%|███       | 17930/57600 [3:08:14<6:42:18,  1.64it/s]
 31%|███       | 17931/57600 [3:08:14<6:42:51,  1.64it/s]
 31%|███       | 17932/57600 [3:08:15<6:44:34,  1.63it/s]
 31%|███       | 17933/57600 [3:08:16<6:38:24,  1.66it/s]
 31%|███       | 17934/57600 [3:08:16<6:39:58,  1.65it/s]
 31%|███       | 17935/57600 [3:08:17<6:39:47,  1.65it/s]
 31%|███       | 17936/57600 [3:08:17<6:51:48,  1.61it/s]
 31%|███       | 17937/57600 [3:08:18<7:02:10,  1.57it/s]
 31%|███       | 17938/57600 [3:08:19<7:01:34,  1.57it/s]
 31%|███       | 17939/57600 [3:08:19<7:06:35,  1.55it/s]
 31%|███       | 17940/57600 [3:08:20<7:15:52,  1.52it/s]
                                                         
{'loss': 1.2259, 'learning_rate': 7.218466898954704e-07, 'epoch': 198.01}

 31%|███       | 17940/57600 [3:08:20<7:15:52,  1.52it/s]
 31%|███       | 17941/57600 [3:08:21<7:01:12,  1.57it/s]
 31%|███       | 17942/57600 [3:08:21<7:08:38,  1.54it/s]
 31%|███       | 17943/57600 [3:08:22<7:21:25,  1.50it/s]
 31%|███       | 17944/57600 [3:08:23<7:05:43,  1.55it/s]
 31%|███       | 17945/57600 [3:08:23<7:02:02,  1.57it/s]
 31%|███       | 17946/57600 [3:08:24<7:04:58,  1.56it/s]
 31%|███       | 17947/57600 [3:08:25<6:59:27,  1.58it/s]
 31%|███       | 17948/57600 [3:08:25<6:57:58,  1.58it/s]
 31%|███       | 17949/57600 [3:08:26<6:47:33,  1.62it/s]
 31%|███       | 17950/57600 [3:08:26<7:01:48,  1.57it/s]
 31%|███       | 17951/57600 [3:08:27<6:45:28,  1.63it/s]
 31%|███       | 17952/57600 [3:08:28<6:43:48,  1.64it/s]
 31%|███       | 17953/57600 [3:08:28<6:52:10,  1.60it/s]
 31%|███       | 17954/57600 [3:08:29<6:44:50,  1.63it/s]
 31%|███       | 17955/57600 [3:08:29<6:48:10,  1.62it/s]
 31%|███       | 17956/57600 [3:08:30<6:42:47,  1.64it/s]
 31%|███       | 17957/57600 [3:08:31<6:40:57,  1.65it/s]
 31%|███       | 17958/57600 [3:08:31<6:38:41,  1.66it/s]
 31%|███       | 17959/57600 [3:08:32<7:04:25,  1.56it/s]
 31%|███       | 17960/57600 [3:08:33<7:03:00,  1.56it/s]
                                                         
{'loss': 1.2203, 'learning_rate': 7.215331010452961e-07, 'epoch': 198.23}

 31%|███       | 17960/57600 [3:08:33<7:03:00,  1.56it/s]
 31%|███       | 17961/57600 [3:08:33<6:52:15,  1.60it/s]
 31%|███       | 17962/57600 [3:08:34<6:48:22,  1.62it/s]
 31%|███       | 17963/57600 [3:08:34<6:45:49,  1.63it/s]
 31%|███       | 17964/57600 [3:08:35<6:36:21,  1.67it/s]
 31%|███       | 17965/57600 [3:08:36<6:45:34,  1.63it/s]
 31%|███       | 17966/57600 [3:08:36<6:54:37,  1.59it/s]
 31%|███       | 17967/57600 [3:08:37<6:50:39,  1.61it/s]
 31%|███       | 17968/57600 [3:08:37<6:49:19,  1.61it/s]
 31%|███       | 17969/57600 [3:08:38<6:47:13,  1.62it/s]
 31%|███       | 17970/57600 [3:08:39<7:00:51,  1.57it/s]
 31%|███       | 17971/57600 [3:08:39<7:08:41,  1.54it/s]
 31%|███       | 17972/57600 [3:08:40<7:04:25,  1.56it/s]
 31%|███       | 17973/57600 [3:08:41<6:49:01,  1.61it/s]
 31%|███       | 17974/57600 [3:08:41<6:59:24,  1.57it/s]
 31%|███       | 17975/57600 [3:08:42<6:58:04,  1.58it/s]
 31%|███       | 17976/57600 [3:08:43<6:51:43,  1.60it/s]
 31%|███       | 17977/57600 [3:08:43<7:00:50,  1.57it/s]
 31%|███       | 17978/57600 [3:08:44<6:59:01,  1.58it/s]
 31%|███       | 17979/57600 [3:08:44<6:48:46,  1.62it/s]
 31%|███       | 17980/57600 [3:08:45<6:56:49,  1.58it/s]
                                                         
{'loss': 1.2837, 'learning_rate': 7.212195121951219e-07, 'epoch': 198.45}

 31%|███       | 17980/57600 [3:08:45<6:56:49,  1.58it/s]
 31%|███       | 17981/57600 [3:08:46<6:38:30,  1.66it/s]
 31%|███       | 17982/57600 [3:08:46<6:37:22,  1.66it/s]
 31%|███       | 17983/57600 [3:08:47<6:22:39,  1.73it/s]
 31%|███       | 17984/57600 [3:08:47<6:31:26,  1.69it/s]
 31%|███       | 17985/57600 [3:08:48<6:26:06,  1.71it/s]
 31%|███       | 17986/57600 [3:08:49<6:41:59,  1.64it/s]
 31%|███       | 17987/57600 [3:08:49<6:31:07,  1.69it/s]
 31%|███       | 17988/57600 [3:08:50<6:24:32,  1.72it/s]
 31%|███       | 17989/57600 [3:08:50<6:32:13,  1.68it/s]
 31%|███       | 17990/57600 [3:08:51<6:29:49,  1.69it/s]
 31%|███       | 17991/57600 [3:08:52<6:35:28,  1.67it/s]
 31%|███       | 17992/57600 [3:08:52<6:28:31,  1.70it/s]
 31%|███       | 17993/57600 [3:08:53<6:44:00,  1.63it/s]
 31%|███       | 17994/57600 [3:08:53<6:41:53,  1.64it/s]
 31%|███       | 17995/57600 [3:08:54<6:53:16,  1.60it/s]
 31%|███       | 17996/57600 [3:08:55<7:05:27,  1.55it/s]
 31%|███       | 17997/57600 [3:08:55<7:18:30,  1.51it/s]
 31%|███       | 17998/57600 [3:08:56<7:05:20,  1.55it/s]
 31%|███       | 17999/57600 [3:08:57<7:14:47,  1.52it/s]
 31%|███▏      | 18000/57600 [3:08:57<7:04:51,  1.55it/s]
                                                         
{'loss': 1.2906, 'learning_rate': 7.209059233449475e-07, 'epoch': 198.68}

 31%|███▏      | 18000/57600 [3:08:57<7:04:51,  1.55it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.33it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.18it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.68it/s]

100%|██████████| 6/6 [00:01<00:00,  3.34it/s]{'score': 48.30438755836409, 'counts': [140, 95, 64, 45], 'totals': [211, 181, 151, 122], 'precisions': [66.35071090047393, 52.48618784530387, 42.384105960264904, 36.885245901639344], 'bp': 1.0, 'sys_len': 211, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 2.004776954650879, 'eval_bleu': 48.3044, 'eval_gen_len': 8.5333, 'eval_runtime': 3.1873, 'eval_samples_per_second': 9.412, 'eval_steps_per_second': 1.882, 'epoch': 198.68}

 31%|███▏      | 18000/57600 [3:09:01<7:04:51,  1.55it/s]

100%|██████████| 6/6 [00:02<00:00,  3.34it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 10:03:13,884 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 31%|███▏      | 18001/57600 [3:09:19<77:58:33,  7.09s/it]
 31%|███▏      | 18002/57600 [3:09:20<56:48:56,  5.17s/it]
 31%|███▏      | 18003/57600 [3:09:21<42:01:40,  3.82s/it]
 31%|███▏      | 18004/57600 [3:09:22<31:42:41,  2.88s/it]
 31%|███▏      | 18005/57600 [3:09:22<24:28:20,  2.23s/it]
 31%|███▏      | 18006/57600 [3:09:23<19:12:19,  1.75s/it]
 31%|███▏      | 18007/57600 [3:09:23<15:16:34,  1.39s/it]
 31%|███▏      | 18008/57600 [3:09:24<12:51:51,  1.17s/it]
 31%|███▏      | 18009/57600 [3:09:25<11:24:24,  1.04s/it]
 31%|███▏      | 18010/57600 [3:09:25<10:10:26,  1.08it/s]
 31%|███▏      | 18011/57600 [3:09:26<9:21:31,  1.18it/s] 
 31%|███▏      | 18012/57600 [3:09:27<8:45:11,  1.26it/s]
 31%|███▏      | 18013/57600 [3:09:27<8:20:44,  1.32it/s]
 31%|███▏      | 18014/57600 [3:09:28<7:57:43,  1.38it/s]
 31%|███▏      | 18015/57600 [3:09:29<7:53:51,  1.39it/s]
 31%|███▏      | 18016/57600 [3:09:29<7:37:21,  1.44it/s]
 31%|███▏      | 18017/57600 [3:09:30<7:43:42,  1.42it/s]
 31%|███▏      | 18018/57600 [3:09:31<7:34:06,  1.45it/s]
 31%|███▏      | 18019/57600 [3:09:32<7:29:31,  1.47it/s]
 31%|███▏      | 18020/57600 [3:09:32<7:18:42,  1.50it/s]
                                                         
{'loss': 1.2383, 'learning_rate': 7.205923344947735e-07, 'epoch': 198.9}

 31%|███▏      | 18020/57600 [3:09:32<7:18:42,  1.50it/s]
 31%|███▏      | 18021/57600 [3:09:33<7:18:46,  1.50it/s]
 31%|███▏      | 18022/57600 [3:09:33<7:22:52,  1.49it/s]
 31%|███▏      | 18023/57600 [3:09:34<7:13:30,  1.52it/s]
 31%|███▏      | 18024/57600 [3:09:35<7:21:33,  1.49it/s]
 31%|███▏      | 18025/57600 [3:09:35<7:16:04,  1.51it/s]
 31%|███▏      | 18026/57600 [3:09:36<7:17:04,  1.51it/s]
 31%|███▏      | 18027/57600 [3:09:37<7:03:02,  1.56it/s]
 31%|███▏      | 18028/57600 [3:09:37<7:01:17,  1.57it/s]
 31%|███▏      | 18029/57600 [3:09:38<7:01:10,  1.57it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 31%|███▏      | 18030/57600 [3:09:39<7:22:51,  1.49it/s]
 31%|███▏      | 18031/57600 [3:09:39<7:07:52,  1.54it/s]
 31%|███▏      | 18032/57600 [3:09:40<7:03:41,  1.56it/s]
 31%|███▏      | 18033/57600 [3:09:41<7:03:47,  1.56it/s]
 31%|███▏      | 18034/57600 [3:09:41<7:04:25,  1.55it/s]
 31%|███▏      | 18035/57600 [3:09:42<7:02:56,  1.56it/s]
 31%|███▏      | 18036/57600 [3:09:43<7:10:01,  1.53it/s]
 31%|███▏      | 18037/57600 [3:09:43<7:14:08,  1.52it/s]
 31%|███▏      | 18038/57600 [3:09:44<7:32:11,  1.46it/s]
 31%|███▏      | 18039/57600 [3:09:45<7:19:55,  1.50it/s]
 31%|███▏      | 18040/57600 [3:09:45<7:23:48,  1.49it/s]
                                                         
{'loss': 1.2724, 'learning_rate': 7.202787456445993e-07, 'epoch': 199.12}

 31%|███▏      | 18040/57600 [3:09:45<7:23:48,  1.49it/s]
 31%|███▏      | 18041/57600 [3:09:46<7:31:52,  1.46it/s]
 31%|███▏      | 18042/57600 [3:09:47<7:23:39,  1.49it/s]
 31%|███▏      | 18043/57600 [3:09:47<7:22:53,  1.49it/s]
 31%|███▏      | 18044/57600 [3:09:48<7:09:41,  1.53it/s]
 31%|███▏      | 18045/57600 [3:09:49<7:07:01,  1.54it/s]
 31%|███▏      | 18046/57600 [3:09:49<7:03:55,  1.56it/s]
 31%|███▏      | 18047/57600 [3:09:50<7:01:01,  1.57it/s]
 31%|███▏      | 18048/57600 [3:09:50<6:48:23,  1.61it/s]
 31%|███▏      | 18049/57600 [3:09:51<6:50:52,  1.60it/s]
 31%|███▏      | 18050/57600 [3:09:52<6:34:12,  1.67it/s]
 31%|███▏      | 18051/57600 [3:09:52<6:56:43,  1.58it/s]
 31%|███▏      | 18052/57600 [3:09:53<6:56:17,  1.58it/s]
 31%|███▏      | 18053/57600 [3:09:54<6:59:41,  1.57it/s]
 31%|███▏      | 18054/57600 [3:09:54<7:00:36,  1.57it/s]
 31%|███▏      | 18055/57600 [3:09:55<7:03:13,  1.56it/s]
 31%|███▏      | 18056/57600 [3:09:55<6:57:36,  1.58it/s]
 31%|███▏      | 18057/57600 [3:09:56<7:06:51,  1.54it/s]
 31%|███▏      | 18058/57600 [3:09:57<7:11:51,  1.53it/s]
 31%|███▏      | 18059/57600 [3:09:57<7:08:29,  1.54it/s]
 31%|███▏      | 18060/57600 [3:09:58<7:07:10,  1.54it/s]
                                                         
{'loss': 1.2588, 'learning_rate': 7.199651567944251e-07, 'epoch': 199.34}

 31%|███▏      | 18060/57600 [3:09:58<7:07:10,  1.54it/s]
 31%|███▏      | 18061/57600 [3:09:59<7:02:25,  1.56it/s]
 31%|███▏      | 18062/57600 [3:09:59<7:02:43,  1.56it/s]
 31%|███▏      | 18063/57600 [3:10:00<7:17:35,  1.51it/s]
 31%|███▏      | 18064/57600 [3:10:01<7:10:06,  1.53it/s]
 31%|███▏      | 18065/57600 [3:10:01<7:08:37,  1.54it/s]
 31%|███▏      | 18066/57600 [3:10:02<7:05:13,  1.55it/s]
 31%|███▏      | 18067/57600 [3:10:03<7:00:49,  1.57it/s]
 31%|███▏      | 18068/57600 [3:10:03<6:58:51,  1.57it/s]
 31%|███▏      | 18069/57600 [3:10:04<6:48:38,  1.61it/s]
 31%|███▏      | 18070/57600 [3:10:04<6:43:51,  1.63it/s]
 31%|███▏      | 18071/57600 [3:10:05<6:45:31,  1.62it/s]
 31%|███▏      | 18072/57600 [3:10:06<7:05:40,  1.55it/s]
 31%|███▏      | 18073/57600 [3:10:06<7:02:32,  1.56it/s]
 31%|███▏      | 18074/57600 [3:10:07<6:46:56,  1.62it/s]
 31%|███▏      | 18075/57600 [3:10:08<6:54:06,  1.59it/s]
 31%|███▏      | 18076/57600 [3:10:08<7:08:46,  1.54it/s]
 31%|███▏      | 18077/57600 [3:10:09<7:01:32,  1.56it/s]
 31%|███▏      | 18078/57600 [3:10:09<6:48:49,  1.61it/s]
 31%|███▏      | 18079/57600 [3:10:10<6:53:45,  1.59it/s]
 31%|███▏      | 18080/57600 [3:10:11<7:20:26,  1.50it/s]
                                                         
{'loss': 1.2528, 'learning_rate': 7.196515679442509e-07, 'epoch': 199.56}

 31%|███▏      | 18080/57600 [3:10:11<7:20:26,  1.50it/s]
 31%|███▏      | 18081/57600 [3:10:12<7:24:20,  1.48it/s]
 31%|███▏      | 18082/57600 [3:10:12<7:18:24,  1.50it/s]
 31%|███▏      | 18083/57600 [3:10:13<7:17:46,  1.50it/s]
 31%|███▏      | 18084/57600 [3:10:13<7:01:39,  1.56it/s]
 31%|███▏      | 18085/57600 [3:10:14<6:56:57,  1.58it/s]
 31%|███▏      | 18086/57600 [3:10:15<7:01:43,  1.56it/s]
 31%|███▏      | 18087/57600 [3:10:15<7:12:39,  1.52it/s]
 31%|███▏      | 18088/57600 [3:10:16<7:40:09,  1.43it/s]
 31%|███▏      | 18089/57600 [3:10:17<7:18:46,  1.50it/s]
 31%|███▏      | 18090/57600 [3:10:17<7:05:02,  1.55it/s]
 31%|███▏      | 18091/57600 [3:10:18<7:23:35,  1.48it/s]
 31%|███▏      | 18092/57600 [3:10:19<7:11:50,  1.52it/s]
 31%|███▏      | 18093/57600 [3:10:19<7:03:32,  1.55it/s]
 31%|███▏      | 18094/57600 [3:10:20<7:21:13,  1.49it/s]
 31%|███▏      | 18095/57600 [3:10:21<7:15:12,  1.51it/s]
 31%|███▏      | 18096/57600 [3:10:21<7:18:03,  1.50it/s]
 31%|███▏      | 18097/57600 [3:10:22<7:09:28,  1.53it/s]
 31%|███▏      | 18098/57600 [3:10:23<6:55:57,  1.58it/s]
 31%|███▏      | 18099/57600 [3:10:23<6:47:08,  1.62it/s]
 31%|███▏      | 18100/57600 [3:10:24<6:43:54,  1.63it/s]
                                                         
{'loss': 1.247, 'learning_rate': 7.193379790940766e-07, 'epoch': 199.78}

 31%|███▏      | 18100/57600 [3:10:24<6:43:54,  1.63it/s]
 31%|███▏      | 18101/57600 [3:10:25<6:52:38,  1.60it/s]
 31%|███▏      | 18102/57600 [3:10:25<6:59:57,  1.57it/s]
 31%|███▏      | 18103/57600 [3:10:26<6:59:10,  1.57it/s]
 31%|███▏      | 18104/57600 [3:10:26<6:54:20,  1.59it/s]
 31%|███▏      | 18105/57600 [3:10:27<6:46:58,  1.62it/s]
 31%|███▏      | 18106/57600 [3:10:28<6:59:27,  1.57it/s]
 31%|███▏      | 18107/57600 [3:10:28<7:12:46,  1.52it/s]
 31%|███▏      | 18108/57600 [3:10:29<7:17:30,  1.50it/s]
 31%|███▏      | 18109/57600 [3:10:30<7:38:17,  1.44it/s]
 31%|███▏      | 18110/57600 [3:10:30<7:22:26,  1.49it/s]
 31%|███▏      | 18111/57600 [3:10:31<7:23:14,  1.48it/s]
 31%|███▏      | 18112/57600 [3:10:32<7:19:18,  1.50it/s]
 31%|███▏      | 18113/57600 [3:10:32<7:12:39,  1.52it/s]
 31%|███▏      | 18114/57600 [3:10:33<7:03:12,  1.56it/s]
 31%|███▏      | 18115/57600 [3:10:34<6:55:35,  1.58it/s]
 31%|███▏      | 18116/57600 [3:10:34<6:56:36,  1.58it/s]
 31%|███▏      | 18117/57600 [3:10:35<7:00:21,  1.57it/s]
 31%|███▏      | 18118/57600 [3:10:36<6:54:54,  1.59it/s]
 31%|███▏      | 18119/57600 [3:10:36<6:55:15,  1.58it/s]
 31%|███▏      | 18120/57600 [3:10:37<7:04:54,  1.55it/s]
                                                         
{'loss': 1.2697, 'learning_rate': 7.190243902439024e-07, 'epoch': 200.0}

 31%|███▏      | 18120/57600 [3:10:37<7:04:54,  1.55it/s]
 31%|███▏      | 18121/57600 [3:10:38<7:19:50,  1.50it/s]
 31%|███▏      | 18122/57600 [3:10:38<7:04:59,  1.55it/s]
 31%|███▏      | 18123/57600 [3:10:39<6:51:18,  1.60it/s]
 31%|███▏      | 18124/57600 [3:10:39<6:53:34,  1.59it/s]
 31%|███▏      | 18125/57600 [3:10:40<6:54:40,  1.59it/s]
 31%|███▏      | 18126/57600 [3:10:41<6:50:38,  1.60it/s]
 31%|███▏      | 18127/57600 [3:10:41<6:56:00,  1.58it/s]
 31%|███▏      | 18128/57600 [3:10:42<7:08:33,  1.54it/s]
 31%|███▏      | 18129/57600 [3:10:43<6:57:37,  1.58it/s]
 31%|███▏      | 18130/57600 [3:10:43<7:04:17,  1.55it/s]
 31%|███▏      | 18131/57600 [3:10:44<7:08:54,  1.53it/s]
 31%|███▏      | 18132/57600 [3:10:45<6:59:12,  1.57it/s]
 31%|███▏      | 18133/57600 [3:10:45<6:53:57,  1.59it/s]
 31%|███▏      | 18134/57600 [3:10:46<7:11:18,  1.53it/s]
 31%|███▏      | 18135/57600 [3:10:46<7:00:26,  1.56it/s]
 31%|███▏      | 18136/57600 [3:10:47<7:24:47,  1.48it/s]
 31%|███▏      | 18137/57600 [3:10:48<7:20:53,  1.49it/s]
 31%|███▏      | 18138/57600 [3:10:48<7:08:15,  1.54it/s]
 31%|███▏      | 18139/57600 [3:10:49<7:11:33,  1.52it/s]
 31%|███▏      | 18140/57600 [3:10:50<7:01:42,  1.56it/s]
                                                         
{'loss': 1.2868, 'learning_rate': 7.187108013937282e-07, 'epoch': 200.22}

 31%|███▏      | 18140/57600 [3:10:50<7:01:42,  1.56it/s]
 31%|███▏      | 18141/57600 [3:10:50<6:59:41,  1.57it/s]
 31%|███▏      | 18142/57600 [3:10:51<6:57:03,  1.58it/s]
 31%|███▏      | 18143/57600 [3:10:52<6:56:33,  1.58it/s]
 32%|███▏      | 18144/57600 [3:10:52<6:50:36,  1.60it/s]
 32%|███▏      | 18145/57600 [3:10:53<7:01:12,  1.56it/s]
 32%|███▏      | 18146/57600 [3:10:54<7:16:31,  1.51it/s]
 32%|███▏      | 18147/57600 [3:10:54<7:08:27,  1.53it/s]
 32%|███▏      | 18148/57600 [3:10:55<7:08:46,  1.53it/s]
 32%|███▏      | 18149/57600 [3:10:56<7:03:12,  1.55it/s]
 32%|███▏      | 18150/57600 [3:10:56<7:04:47,  1.55it/s]
 32%|███▏      | 18151/57600 [3:10:57<7:03:52,  1.55it/s]
 32%|███▏      | 18152/57600 [3:10:57<6:54:12,  1.59it/s]
 32%|███▏      | 18153/57600 [3:10:58<7:02:54,  1.55it/s]
 32%|███▏      | 18154/57600 [3:10:59<7:07:06,  1.54it/s]
 32%|███▏      | 18155/57600 [3:10:59<7:07:13,  1.54it/s]
 32%|███▏      | 18156/57600 [3:11:00<7:19:20,  1.50it/s]
 32%|███▏      | 18157/57600 [3:11:01<7:24:35,  1.48it/s]
 32%|███▏      | 18158/57600 [3:11:01<7:18:53,  1.50it/s]
 32%|███▏      | 18159/57600 [3:11:02<7:23:12,  1.48it/s]
 32%|███▏      | 18160/57600 [3:11:03<7:29:18,  1.46it/s]
                                                         
{'loss': 1.291, 'learning_rate': 7.18397212543554e-07, 'epoch': 200.44}

 32%|███▏      | 18160/57600 [3:11:03<7:29:18,  1.46it/s]
 32%|███▏      | 18161/57600 [3:11:03<7:18:37,  1.50it/s]
 32%|███▏      | 18162/57600 [3:11:04<7:14:36,  1.51it/s]
 32%|███▏      | 18163/57600 [3:11:05<6:54:09,  1.59it/s]
 32%|███▏      | 18164/57600 [3:11:05<6:48:02,  1.61it/s]
 32%|███▏      | 18165/57600 [3:11:06<6:50:35,  1.60it/s]
 32%|███▏      | 18166/57600 [3:11:07<6:52:41,  1.59it/s]
 32%|███▏      | 18167/57600 [3:11:07<6:36:25,  1.66it/s]
 32%|███▏      | 18168/57600 [3:11:08<6:35:31,  1.66it/s]
 32%|███▏      | 18169/57600 [3:11:08<6:42:30,  1.63it/s]
 32%|███▏      | 18170/57600 [3:11:09<6:48:23,  1.61it/s]
 32%|███▏      | 18171/57600 [3:11:10<6:45:29,  1.62it/s]
 32%|███▏      | 18172/57600 [3:11:10<6:53:29,  1.59it/s]
 32%|███▏      | 18173/57600 [3:11:11<7:00:36,  1.56it/s]
 32%|███▏      | 18174/57600 [3:11:12<6:54:26,  1.59it/s]
 32%|███▏      | 18175/57600 [3:11:12<6:43:12,  1.63it/s]
 32%|███▏      | 18176/57600 [3:11:13<7:04:38,  1.55it/s]
 32%|███▏      | 18177/57600 [3:11:14<7:15:05,  1.51it/s]
 32%|███▏      | 18178/57600 [3:11:14<7:15:26,  1.51it/s]
 32%|███▏      | 18179/57600 [3:11:15<7:06:15,  1.54it/s]
 32%|███▏      | 18180/57600 [3:11:15<6:54:30,  1.59it/s]
                                                         
{'loss': 1.2906, 'learning_rate': 7.180836236933797e-07, 'epoch': 200.66}

 32%|███▏      | 18180/57600 [3:11:15<6:54:30,  1.59it/s]
 32%|███▏      | 18181/57600 [3:11:16<6:57:39,  1.57it/s]
 32%|███▏      | 18182/57600 [3:11:17<6:59:01,  1.57it/s]
 32%|███▏      | 18183/57600 [3:11:17<7:08:59,  1.53it/s]
 32%|███▏      | 18184/57600 [3:11:18<6:59:08,  1.57it/s]
 32%|███▏      | 18185/57600 [3:11:19<7:06:47,  1.54it/s]
 32%|███▏      | 18186/57600 [3:11:19<7:22:27,  1.48it/s]
 32%|███▏      | 18187/57600 [3:11:20<7:29:09,  1.46it/s]
 32%|███▏      | 18188/57600 [3:11:21<7:24:59,  1.48it/s]
 32%|███▏      | 18189/57600 [3:11:21<7:05:21,  1.54it/s]
 32%|███▏      | 18190/57600 [3:11:22<7:00:24,  1.56it/s]
 32%|███▏      | 18191/57600 [3:11:23<7:09:48,  1.53it/s]
 32%|███▏      | 18192/57600 [3:11:23<7:13:22,  1.52it/s]
 32%|███▏      | 18193/57600 [3:11:24<7:03:51,  1.55it/s]
 32%|███▏      | 18194/57600 [3:11:25<7:00:11,  1.56it/s]
 32%|███▏      | 18195/57600 [3:11:25<6:56:08,  1.58it/s]
 32%|███▏      | 18196/57600 [3:11:26<6:48:25,  1.61it/s]
 32%|███▏      | 18197/57600 [3:11:26<6:51:10,  1.60it/s]
 32%|███▏      | 18198/57600 [3:11:27<7:09:38,  1.53it/s]
 32%|███▏      | 18199/57600 [3:11:28<7:08:48,  1.53it/s]
 32%|███▏      | 18200/57600 [3:11:28<7:22:46,  1.48it/s]
                                                         
{'loss': 1.2543, 'learning_rate': 7.177700348432056e-07, 'epoch': 200.88}

 32%|███▏      | 18200/57600 [3:11:28<7:22:46,  1.48it/s]
 32%|███▏      | 18201/57600 [3:11:29<7:32:36,  1.45it/s]
 32%|███▏      | 18202/57600 [3:11:30<7:27:03,  1.47it/s]
 32%|███▏      | 18203/57600 [3:11:31<7:22:44,  1.48it/s]
 32%|███▏      | 18204/57600 [3:11:31<7:14:54,  1.51it/s]
 32%|███▏      | 18205/57600 [3:11:32<7:16:51,  1.50it/s]
 32%|███▏      | 18206/57600 [3:11:32<7:09:47,  1.53it/s]
 32%|███▏      | 18207/57600 [3:11:33<7:03:41,  1.55it/s]
 32%|███▏      | 18208/57600 [3:11:34<7:13:52,  1.51it/s]
 32%|███▏      | 18209/57600 [3:11:34<7:13:51,  1.51it/s]
 32%|███▏      | 18210/57600 [3:11:35<7:04:22,  1.55it/s]
 32%|███▏      | 18211/57600 [3:11:36<7:23:29,  1.48it/s]
 32%|███▏      | 18212/57600 [3:11:36<7:10:00,  1.53it/s]
 32%|███▏      | 18213/57600 [3:11:37<6:52:55,  1.59it/s]
 32%|███▏      | 18214/57600 [3:11:38<6:37:25,  1.65it/s]
 32%|███▏      | 18215/57600 [3:11:38<6:39:44,  1.64it/s]
 32%|███▏      | 18216/57600 [3:11:39<6:42:11,  1.63it/s]
 32%|███▏      | 18217/57600 [3:11:39<6:46:44,  1.61it/s]
 32%|███▏      | 18218/57600 [3:11:40<6:53:27,  1.59it/s]
 32%|███▏      | 18219/57600 [3:11:41<7:04:09,  1.55it/s]
 32%|███▏      | 18220/57600 [3:11:41<7:01:30,  1.56it/s]
                                                         
{'loss': 1.2414, 'learning_rate': 7.174564459930313e-07, 'epoch': 201.1}

 32%|███▏      | 18220/57600 [3:11:41<7:01:30,  1.56it/s]
 32%|███▏      | 18221/57600 [3:11:42<6:57:32,  1.57it/s]
 32%|███▏      | 18222/57600 [3:11:43<6:54:47,  1.58it/s]
 32%|███▏      | 18223/57600 [3:11:43<6:49:34,  1.60it/s]
 32%|███▏      | 18224/57600 [3:11:44<6:57:00,  1.57it/s]
 32%|███▏      | 18225/57600 [3:11:45<7:20:34,  1.49it/s]
 32%|███▏      | 18226/57600 [3:11:45<7:15:04,  1.51it/s]
 32%|███▏      | 18227/57600 [3:11:46<7:10:09,  1.53it/s]
 32%|███▏      | 18228/57600 [3:11:47<7:01:38,  1.56it/s]
 32%|███▏      | 18229/57600 [3:11:47<7:08:36,  1.53it/s]
 32%|███▏      | 18230/57600 [3:11:48<7:01:29,  1.56it/s]
 32%|███▏      | 18231/57600 [3:11:48<6:49:28,  1.60it/s]
 32%|███▏      | 18232/57600 [3:11:49<6:52:03,  1.59it/s]
 32%|███▏      | 18233/57600 [3:11:50<6:50:47,  1.60it/s]
 32%|███▏      | 18234/57600 [3:11:50<6:49:27,  1.60it/s]
 32%|███▏      | 18235/57600 [3:11:51<6:50:00,  1.60it/s]
 32%|███▏      | 18236/57600 [3:11:52<6:56:50,  1.57it/s]
 32%|███▏      | 18237/57600 [3:11:52<6:40:41,  1.64it/s]
 32%|███▏      | 18238/57600 [3:11:53<6:42:31,  1.63it/s]
 32%|███▏      | 18239/57600 [3:11:53<6:42:56,  1.63it/s]
 32%|███▏      | 18240/57600 [3:11:54<6:45:32,  1.62it/s]
                                                         
{'loss': 1.2393, 'learning_rate': 7.171428571428571e-07, 'epoch': 201.32}

 32%|███▏      | 18240/57600 [3:11:54<6:45:32,  1.62it/s]
 32%|███▏      | 18241/57600 [3:11:55<6:44:30,  1.62it/s]
 32%|███▏      | 18242/57600 [3:11:55<6:53:42,  1.59it/s]
 32%|███▏      | 18243/57600 [3:11:56<6:52:04,  1.59it/s]
 32%|███▏      | 18244/57600 [3:11:56<6:45:33,  1.62it/s]
 32%|███▏      | 18245/57600 [3:11:57<6:36:54,  1.65it/s]
 32%|███▏      | 18246/57600 [3:11:58<7:00:44,  1.56it/s]
 32%|███▏      | 18247/57600 [3:11:58<6:53:00,  1.59it/s]
 32%|███▏      | 18248/57600 [3:11:59<6:36:30,  1.65it/s]
 32%|███▏      | 18249/57600 [3:12:00<6:43:57,  1.62it/s]
 32%|███▏      | 18250/57600 [3:12:00<6:45:37,  1.62it/s]
 32%|███▏      | 18251/57600 [3:12:01<7:00:01,  1.56it/s]
 32%|███▏      | 18252/57600 [3:12:01<6:50:57,  1.60it/s]
 32%|███▏      | 18253/57600 [3:12:02<6:49:09,  1.60it/s]
 32%|███▏      | 18254/57600 [3:12:03<6:47:13,  1.61it/s]
 32%|███▏      | 18255/57600 [3:12:03<6:50:02,  1.60it/s]
 32%|███▏      | 18256/57600 [3:12:04<6:37:25,  1.65it/s]
 32%|███▏      | 18257/57600 [3:12:05<6:33:59,  1.66it/s]
 32%|███▏      | 18258/57600 [3:12:05<6:33:45,  1.67it/s]
 32%|███▏      | 18259/57600 [3:12:06<6:39:13,  1.64it/s]
 32%|███▏      | 18260/57600 [3:12:06<6:47:34,  1.61it/s]
                                                         
{'loss': 1.2781, 'learning_rate': 7.168292682926829e-07, 'epoch': 201.55}

 32%|███▏      | 18260/57600 [3:12:06<6:47:34,  1.61it/s]
 32%|███▏      | 18261/57600 [3:12:07<6:49:13,  1.60it/s]
 32%|███▏      | 18262/57600 [3:12:08<6:41:45,  1.63it/s]
 32%|███▏      | 18263/57600 [3:12:08<6:42:11,  1.63it/s]
 32%|███▏      | 18264/57600 [3:12:09<6:36:59,  1.65it/s]
 32%|███▏      | 18265/57600 [3:12:09<6:35:09,  1.66it/s]
 32%|███▏      | 18266/57600 [3:12:10<6:38:58,  1.64it/s]
 32%|███▏      | 18267/57600 [3:12:11<6:28:45,  1.69it/s]
 32%|███▏      | 18268/57600 [3:12:11<6:45:07,  1.62it/s]
 32%|███▏      | 18269/57600 [3:12:12<6:38:10,  1.65it/s]
 32%|███▏      | 18270/57600 [3:12:13<7:06:44,  1.54it/s]
 32%|███▏      | 18271/57600 [3:12:13<7:08:49,  1.53it/s]
 32%|███▏      | 18272/57600 [3:12:14<6:59:06,  1.56it/s]
 32%|███▏      | 18273/57600 [3:12:15<7:16:50,  1.50it/s]
 32%|███▏      | 18274/57600 [3:12:15<7:09:45,  1.53it/s]
 32%|███▏      | 18275/57600 [3:12:16<6:58:24,  1.57it/s]
 32%|███▏      | 18276/57600 [3:12:16<6:57:15,  1.57it/s]
 32%|███▏      | 18277/57600 [3:12:17<6:47:55,  1.61it/s]
 32%|███▏      | 18278/57600 [3:12:18<6:33:58,  1.66it/s]
 32%|███▏      | 18279/57600 [3:12:18<6:35:23,  1.66it/s]
 32%|███▏      | 18280/57600 [3:12:19<6:36:38,  1.65it/s]
                                                         
{'loss': 1.2625, 'learning_rate': 7.165156794425087e-07, 'epoch': 201.77}

 32%|███▏      | 18280/57600 [3:12:19<6:36:38,  1.65it/s]
 32%|███▏      | 18281/57600 [3:12:19<6:45:55,  1.61it/s]
 32%|███▏      | 18282/57600 [3:12:20<6:38:02,  1.65it/s]
 32%|███▏      | 18283/57600 [3:12:21<6:46:10,  1.61it/s]
 32%|███▏      | 18284/57600 [3:12:21<7:03:55,  1.55it/s]
 32%|███▏      | 18285/57600 [3:12:22<7:05:20,  1.54it/s]
 32%|███▏      | 18286/57600 [3:12:23<7:11:34,  1.52it/s]
 32%|███▏      | 18287/57600 [3:12:23<7:02:34,  1.55it/s]
 32%|███▏      | 18288/57600 [3:12:24<6:56:37,  1.57it/s]
 32%|███▏      | 18289/57600 [3:12:25<6:58:17,  1.57it/s]
 32%|███▏      | 18290/57600 [3:12:25<6:45:30,  1.62it/s]
 32%|███▏      | 18291/57600 [3:12:26<6:44:25,  1.62it/s]
 32%|███▏      | 18292/57600 [3:12:26<6:44:52,  1.62it/s]
 32%|███▏      | 18293/57600 [3:12:27<6:36:13,  1.65it/s]
 32%|███▏      | 18294/57600 [3:12:28<6:36:48,  1.65it/s]
 32%|███▏      | 18295/57600 [3:12:28<6:33:31,  1.66it/s]
 32%|███▏      | 18296/57600 [3:12:29<6:31:22,  1.67it/s]
 32%|███▏      | 18297/57600 [3:12:29<6:46:29,  1.61it/s]
 32%|███▏      | 18298/57600 [3:12:30<6:40:16,  1.64it/s]
 32%|███▏      | 18299/57600 [3:12:31<6:35:08,  1.66it/s]
 32%|███▏      | 18300/57600 [3:12:31<6:38:34,  1.64it/s]
                                                         
{'loss': 1.2435, 'learning_rate': 7.162020905923345e-07, 'epoch': 201.99}

 32%|███▏      | 18300/57600 [3:12:31<6:38:34,  1.64it/s]
 32%|███▏      | 18301/57600 [3:12:32<6:39:07,  1.64it/s]
 32%|███▏      | 18302/57600 [3:12:33<7:05:17,  1.54it/s]
 32%|███▏      | 18303/57600 [3:12:33<7:05:06,  1.54it/s]
 32%|███▏      | 18304/57600 [3:12:34<7:05:14,  1.54it/s]
 32%|███▏      | 18305/57600 [3:12:35<7:03:42,  1.55it/s]
 32%|███▏      | 18306/57600 [3:12:35<7:02:00,  1.55it/s]
 32%|███▏      | 18307/57600 [3:12:36<7:08:36,  1.53it/s]
 32%|███▏      | 18308/57600 [3:12:36<7:05:41,  1.54it/s]
 32%|███▏      | 18309/57600 [3:12:37<6:57:38,  1.57it/s]
 32%|███▏      | 18310/57600 [3:12:38<6:52:11,  1.59it/s]
 32%|███▏      | 18311/57600 [3:12:38<6:51:34,  1.59it/s]
 32%|███▏      | 18312/57600 [3:12:39<6:43:00,  1.62it/s]
 32%|███▏      | 18313/57600 [3:12:40<7:03:55,  1.54it/s]
 32%|███▏      | 18314/57600 [3:12:40<6:47:17,  1.61it/s]
 32%|███▏      | 18315/57600 [3:12:41<7:00:33,  1.56it/s]
 32%|███▏      | 18316/57600 [3:12:41<6:47:36,  1.61it/s]
 32%|███▏      | 18317/57600 [3:12:42<6:38:28,  1.64it/s]
 32%|███▏      | 18318/57600 [3:12:43<6:35:10,  1.66it/s]
 32%|███▏      | 18319/57600 [3:12:43<6:43:19,  1.62it/s]
 32%|███▏      | 18320/57600 [3:12:44<6:44:04,  1.62it/s]
                                                         
{'loss': 1.2254, 'learning_rate': 7.158885017421602e-07, 'epoch': 202.21}

 32%|███▏      | 18320/57600 [3:12:44<6:44:04,  1.62it/s]
 32%|███▏      | 18321/57600 [3:12:45<6:45:55,  1.61it/s]
 32%|███▏      | 18322/57600 [3:12:45<6:35:46,  1.65it/s]
 32%|███▏      | 18323/57600 [3:12:46<6:33:46,  1.66it/s]
 32%|███▏      | 18324/57600 [3:12:46<6:49:32,  1.60it/s]
 32%|███▏      | 18325/57600 [3:12:47<6:55:04,  1.58it/s]
 32%|███▏      | 18326/57600 [3:12:48<6:56:21,  1.57it/s]
 32%|███▏      | 18327/57600 [3:12:48<7:06:13,  1.54it/s]
 32%|███▏      | 18328/57600 [3:12:49<7:01:32,  1.55it/s]
 32%|███▏      | 18329/57600 [3:12:50<6:49:05,  1.60it/s]
 32%|███▏      | 18330/57600 [3:12:50<6:46:47,  1.61it/s]
 32%|███▏      | 18331/57600 [3:12:51<6:40:25,  1.63it/s]
 32%|███▏      | 18332/57600 [3:12:51<6:37:42,  1.65it/s]
 32%|███▏      | 18333/57600 [3:12:52<6:44:33,  1.62it/s]
 32%|███▏      | 18334/57600 [3:12:53<6:43:33,  1.62it/s]
 32%|███▏      | 18335/57600 [3:12:53<6:37:41,  1.65it/s]
 32%|███▏      | 18336/57600 [3:12:54<6:39:54,  1.64it/s]
 32%|███▏      | 18337/57600 [3:12:54<6:38:33,  1.64it/s]
 32%|███▏      | 18338/57600 [3:12:55<6:38:36,  1.64it/s]
 32%|███▏      | 18339/57600 [3:12:56<6:42:48,  1.62it/s]
 32%|███▏      | 18340/57600 [3:12:56<6:41:37,  1.63it/s]
                                                         
{'loss': 1.2802, 'learning_rate': 7.15574912891986e-07, 'epoch': 202.43}

 32%|███▏      | 18340/57600 [3:12:56<6:41:37,  1.63it/s]
 32%|███▏      | 18341/57600 [3:12:57<6:47:21,  1.61it/s]
 32%|███▏      | 18342/57600 [3:12:58<6:52:30,  1.59it/s]
 32%|███▏      | 18343/57600 [3:12:58<6:57:12,  1.57it/s]
 32%|███▏      | 18344/57600 [3:12:59<6:37:45,  1.64it/s]
 32%|███▏      | 18345/57600 [3:12:59<6:43:19,  1.62it/s]
 32%|███▏      | 18346/57600 [3:13:00<6:34:59,  1.66it/s]
 32%|███▏      | 18347/57600 [3:13:01<6:34:09,  1.66it/s]
 32%|███▏      | 18348/57600 [3:13:01<6:35:24,  1.65it/s]
 32%|███▏      | 18349/57600 [3:13:02<6:39:16,  1.64it/s]
 32%|███▏      | 18350/57600 [3:13:03<7:01:07,  1.55it/s]
 32%|███▏      | 18351/57600 [3:13:03<6:49:44,  1.60it/s]
 32%|███▏      | 18352/57600 [3:13:04<6:46:56,  1.61it/s]
 32%|███▏      | 18353/57600 [3:13:04<6:52:27,  1.59it/s]
 32%|███▏      | 18354/57600 [3:13:05<6:45:05,  1.61it/s]
 32%|███▏      | 18355/57600 [3:13:06<6:54:43,  1.58it/s]
 32%|███▏      | 18356/57600 [3:13:06<6:56:34,  1.57it/s]
 32%|███▏      | 18357/57600 [3:13:07<6:49:14,  1.60it/s]
 32%|███▏      | 18358/57600 [3:13:08<7:05:54,  1.54it/s]
 32%|███▏      | 18359/57600 [3:13:08<7:15:33,  1.50it/s]
 32%|███▏      | 18360/57600 [3:13:09<6:53:39,  1.58it/s]
                                                         
{'loss': 1.259, 'learning_rate': 7.152613240418119e-07, 'epoch': 202.65}

 32%|███▏      | 18360/57600 [3:13:09<6:53:39,  1.58it/s]
 32%|███▏      | 18361/57600 [3:13:09<6:45:14,  1.61it/s]
 32%|███▏      | 18362/57600 [3:13:10<6:45:39,  1.61it/s]
 32%|███▏      | 18363/57600 [3:13:11<6:44:59,  1.61it/s]
 32%|███▏      | 18364/57600 [3:13:11<6:44:26,  1.62it/s]
 32%|███▏      | 18365/57600 [3:13:12<6:41:03,  1.63it/s]
 32%|███▏      | 18366/57600 [3:13:12<6:33:43,  1.66it/s]
 32%|███▏      | 18367/57600 [3:13:13<6:30:47,  1.67it/s]
 32%|███▏      | 18368/57600 [3:13:14<6:36:55,  1.65it/s]
 32%|███▏      | 18369/57600 [3:13:14<6:35:58,  1.65it/s]
 32%|███▏      | 18370/57600 [3:13:15<6:38:37,  1.64it/s]
 32%|███▏      | 18371/57600 [3:13:15<6:32:48,  1.66it/s]
 32%|███▏      | 18372/57600 [3:13:16<6:35:24,  1.65it/s]
 32%|███▏      | 18373/57600 [3:13:17<6:39:32,  1.64it/s]
 32%|███▏      | 18374/57600 [3:13:17<6:39:02,  1.64it/s]
 32%|███▏      | 18375/57600 [3:13:18<6:34:44,  1.66it/s]
 32%|███▏      | 18376/57600 [3:13:19<6:33:50,  1.66it/s]
 32%|███▏      | 18377/57600 [3:13:19<6:40:33,  1.63it/s]
 32%|███▏      | 18378/57600 [3:13:20<6:29:00,  1.68it/s]
 32%|███▏      | 18379/57600 [3:13:20<6:41:56,  1.63it/s]
 32%|███▏      | 18380/57600 [3:13:21<6:50:37,  1.59it/s]
                                                         
{'loss': 1.2928, 'learning_rate': 7.149477351916376e-07, 'epoch': 202.87}

 32%|███▏      | 18380/57600 [3:13:21<6:50:37,  1.59it/s]
 32%|███▏      | 18381/57600 [3:13:22<7:00:01,  1.56it/s]
 32%|███▏      | 18382/57600 [3:13:22<6:59:49,  1.56it/s]
 32%|███▏      | 18383/57600 [3:13:23<6:46:25,  1.61it/s]
 32%|███▏      | 18384/57600 [3:13:24<6:52:50,  1.58it/s]
 32%|███▏      | 18385/57600 [3:13:24<6:52:32,  1.58it/s]
 32%|███▏      | 18386/57600 [3:13:25<7:13:51,  1.51it/s]
 32%|███▏      | 18387/57600 [3:13:26<7:11:06,  1.52it/s]
 32%|███▏      | 18388/57600 [3:13:26<7:02:15,  1.55it/s]
 32%|███▏      | 18389/57600 [3:13:27<6:55:46,  1.57it/s]
 32%|███▏      | 18390/57600 [3:13:27<7:01:38,  1.55it/s]
 32%|███▏      | 18391/57600 [3:13:28<6:56:28,  1.57it/s]
 32%|███▏      | 18392/57600 [3:13:29<7:05:55,  1.53it/s]
 32%|███▏      | 18393/57600 [3:13:29<6:55:42,  1.57it/s]
 32%|███▏      | 18394/57600 [3:13:30<6:48:18,  1.60it/s]
 32%|███▏      | 18395/57600 [3:13:31<6:51:17,  1.59it/s]
 32%|███▏      | 18396/57600 [3:13:31<6:43:17,  1.62it/s]
 32%|███▏      | 18397/57600 [3:13:32<6:58:07,  1.56it/s]
 32%|███▏      | 18398/57600 [3:13:33<6:49:31,  1.60it/s]
 32%|███▏      | 18399/57600 [3:13:33<6:42:39,  1.62it/s]
 32%|███▏      | 18400/57600 [3:13:34<6:28:39,  1.68it/s]
                                                         
{'loss': 1.2767, 'learning_rate': 7.146341463414633e-07, 'epoch': 203.09}

 32%|███▏      | 18400/57600 [3:13:34<6:28:39,  1.68it/s]
 32%|███▏      | 18401/57600 [3:13:34<6:20:05,  1.72it/s]
 32%|███▏      | 18402/57600 [3:13:35<6:45:10,  1.61it/s]
 32%|███▏      | 18403/57600 [3:13:36<6:58:39,  1.56it/s]
 32%|███▏      | 18404/57600 [3:13:36<6:55:52,  1.57it/s]
 32%|███▏      | 18405/57600 [3:13:37<6:53:57,  1.58it/s]
 32%|███▏      | 18406/57600 [3:13:37<6:51:01,  1.59it/s]
 32%|███▏      | 18407/57600 [3:13:38<6:54:54,  1.57it/s]
 32%|███▏      | 18408/57600 [3:13:39<6:45:23,  1.61it/s]
 32%|███▏      | 18409/57600 [3:13:39<7:05:04,  1.54it/s]
 32%|███▏      | 18410/57600 [3:13:40<6:59:36,  1.56it/s]
 32%|███▏      | 18411/57600 [3:13:41<7:07:13,  1.53it/s]
 32%|███▏      | 18412/57600 [3:13:41<6:54:42,  1.57it/s]
 32%|███▏      | 18413/57600 [3:13:42<6:50:34,  1.59it/s]
 32%|███▏      | 18414/57600 [3:13:43<6:42:52,  1.62it/s]
 32%|███▏      | 18415/57600 [3:13:43<6:47:28,  1.60it/s]
 32%|███▏      | 18416/57600 [3:13:44<6:39:19,  1.64it/s]
 32%|███▏      | 18417/57600 [3:13:44<7:04:48,  1.54it/s]
 32%|███▏      | 18418/57600 [3:13:45<7:01:10,  1.55it/s]
 32%|███▏      | 18419/57600 [3:13:46<6:59:50,  1.56it/s]
 32%|███▏      | 18420/57600 [3:13:46<7:06:36,  1.53it/s]
                                                         
{'loss': 1.2271, 'learning_rate': 7.143205574912892e-07, 'epoch': 203.31}

 32%|███▏      | 18420/57600 [3:13:46<7:06:36,  1.53it/s]
 32%|███▏      | 18421/57600 [3:13:47<7:00:21,  1.55it/s]
 32%|███▏      | 18422/57600 [3:13:48<7:02:40,  1.54it/s]
 32%|███▏      | 18423/57600 [3:13:48<7:01:25,  1.55it/s]
 32%|███▏      | 18424/57600 [3:13:49<7:02:57,  1.54it/s]
 32%|███▏      | 18425/57600 [3:13:50<6:44:37,  1.61it/s]
 32%|███▏      | 18426/57600 [3:13:50<6:43:49,  1.62it/s]
 32%|███▏      | 18427/57600 [3:13:51<6:41:12,  1.63it/s]
 32%|███▏      | 18428/57600 [3:13:51<6:53:26,  1.58it/s]
 32%|███▏      | 18429/57600 [3:13:52<6:57:04,  1.57it/s]
 32%|███▏      | 18430/57600 [3:13:53<6:50:08,  1.59it/s]
 32%|███▏      | 18431/57600 [3:13:53<6:40:26,  1.63it/s]
 32%|███▏      | 18432/57600 [3:13:54<6:42:17,  1.62it/s]
 32%|███▏      | 18433/57600 [3:13:54<6:23:59,  1.70it/s]
 32%|███▏      | 18434/57600 [3:13:55<6:27:11,  1.69it/s]
 32%|███▏      | 18435/57600 [3:13:56<6:48:17,  1.60it/s]
 32%|███▏      | 18436/57600 [3:13:56<6:47:01,  1.60it/s]
 32%|███▏      | 18437/57600 [3:13:57<6:54:55,  1.57it/s]
 32%|███▏      | 18438/57600 [3:13:58<6:44:55,  1.61it/s]
 32%|███▏      | 18439/57600 [3:13:58<6:52:24,  1.58it/s]
 32%|███▏      | 18440/57600 [3:13:59<6:46:59,  1.60it/s]
                                                         
{'loss': 1.241, 'learning_rate': 7.140069686411149e-07, 'epoch': 203.53}

 32%|███▏      | 18440/57600 [3:13:59<6:46:59,  1.60it/s]
 32%|███▏      | 18441/57600 [3:13:59<6:45:36,  1.61it/s]
 32%|███▏      | 18442/57600 [3:14:00<6:49:20,  1.59it/s]
 32%|███▏      | 18443/57600 [3:14:01<6:46:04,  1.61it/s]
 32%|███▏      | 18444/57600 [3:14:01<6:42:38,  1.62it/s]
 32%|███▏      | 18445/57600 [3:14:02<6:35:18,  1.65it/s]
 32%|███▏      | 18446/57600 [3:14:02<6:23:35,  1.70it/s]
 32%|███▏      | 18447/57600 [3:14:03<6:30:49,  1.67it/s]
 32%|███▏      | 18448/57600 [3:14:04<6:49:26,  1.59it/s]
 32%|███▏      | 18449/57600 [3:14:04<6:49:01,  1.60it/s]
 32%|███▏      | 18450/57600 [3:14:05<6:44:31,  1.61it/s]
 32%|███▏      | 18451/57600 [3:14:06<6:38:53,  1.64it/s]
 32%|███▏      | 18452/57600 [3:14:06<6:28:22,  1.68it/s]
 32%|███▏      | 18453/57600 [3:14:07<6:37:12,  1.64it/s]
 32%|███▏      | 18454/57600 [3:14:07<6:51:24,  1.59it/s]
 32%|███▏      | 18455/57600 [3:14:08<6:43:40,  1.62it/s]
 32%|███▏      | 18456/57600 [3:14:09<6:40:49,  1.63it/s]
 32%|███▏      | 18457/57600 [3:14:09<6:40:26,  1.63it/s]
 32%|███▏      | 18458/57600 [3:14:10<6:54:15,  1.57it/s]
 32%|███▏      | 18459/57600 [3:14:11<6:52:55,  1.58it/s]
 32%|███▏      | 18460/57600 [3:14:11<6:54:27,  1.57it/s]
                                                         
{'loss': 1.261, 'learning_rate': 7.136933797909407e-07, 'epoch': 203.75}

 32%|███▏      | 18460/57600 [3:14:11<6:54:27,  1.57it/s]
 32%|███▏      | 18461/57600 [3:14:12<6:38:28,  1.64it/s]
 32%|███▏      | 18462/57600 [3:14:12<6:36:12,  1.65it/s]
 32%|███▏      | 18463/57600 [3:14:13<6:42:30,  1.62it/s]
 32%|███▏      | 18464/57600 [3:14:14<6:33:44,  1.66it/s]
 32%|███▏      | 18465/57600 [3:14:14<6:29:44,  1.67it/s]
 32%|███▏      | 18466/57600 [3:14:15<6:45:43,  1.61it/s]
 32%|███▏      | 18467/57600 [3:14:16<6:55:39,  1.57it/s]
 32%|███▏      | 18468/57600 [3:14:16<6:42:22,  1.62it/s]
 32%|███▏      | 18469/57600 [3:14:17<6:32:52,  1.66it/s]
 32%|███▏      | 18470/57600 [3:14:17<6:29:53,  1.67it/s]
 32%|███▏      | 18471/57600 [3:14:18<6:31:30,  1.67it/s]
 32%|███▏      | 18472/57600 [3:14:19<6:44:47,  1.61it/s]
 32%|███▏      | 18473/57600 [3:14:19<6:47:53,  1.60it/s]
 32%|███▏      | 18474/57600 [3:14:20<6:50:11,  1.59it/s]
 32%|███▏      | 18475/57600 [3:14:20<6:57:21,  1.56it/s]
 32%|███▏      | 18476/57600 [3:14:21<6:53:46,  1.58it/s]
 32%|███▏      | 18477/57600 [3:14:22<6:50:15,  1.59it/s]
 32%|███▏      | 18478/57600 [3:14:22<6:45:32,  1.61it/s]
 32%|███▏      | 18479/57600 [3:14:23<6:41:57,  1.62it/s]
 32%|███▏      | 18480/57600 [3:14:24<6:43:28,  1.62it/s]
                                                         
{'loss': 1.2636, 'learning_rate': 7.133797909407665e-07, 'epoch': 203.97}

 32%|███▏      | 18480/57600 [3:14:24<6:43:28,  1.62it/s]
 32%|███▏      | 18481/57600 [3:14:24<6:32:07,  1.66it/s]
 32%|███▏      | 18482/57600 [3:14:25<6:28:24,  1.68it/s]
 32%|███▏      | 18483/57600 [3:14:25<6:41:00,  1.63it/s]
 32%|███▏      | 18484/57600 [3:14:26<6:38:28,  1.64it/s]
 32%|███▏      | 18485/57600 [3:14:27<6:37:07,  1.64it/s]
 32%|███▏      | 18486/57600 [3:14:27<6:45:22,  1.61it/s]
 32%|███▏      | 18487/57600 [3:14:28<6:40:00,  1.63it/s]
 32%|███▏      | 18488/57600 [3:14:29<6:56:16,  1.57it/s]
 32%|███▏      | 18489/57600 [3:14:29<6:54:10,  1.57it/s]
 32%|███▏      | 18490/57600 [3:14:30<6:50:16,  1.59it/s]
 32%|███▏      | 18491/57600 [3:14:30<6:59:05,  1.56it/s]
 32%|███▏      | 18492/57600 [3:14:31<6:46:19,  1.60it/s]
 32%|███▏      | 18493/57600 [3:14:32<6:40:07,  1.63it/s]
 32%|███▏      | 18494/57600 [3:14:32<6:34:22,  1.65it/s]
 32%|███▏      | 18495/57600 [3:14:33<6:45:32,  1.61it/s]
 32%|███▏      | 18496/57600 [3:14:33<6:32:41,  1.66it/s]
 32%|███▏      | 18497/57600 [3:14:34<6:31:07,  1.67it/s]
 32%|███▏      | 18498/57600 [3:14:35<6:33:55,  1.65it/s]
 32%|███▏      | 18499/57600 [3:14:35<6:35:37,  1.65it/s]
 32%|███▏      | 18500/57600 [3:14:36<6:56:22,  1.57it/s]
                                                         
{'loss': 1.2872, 'learning_rate': 7.130662020905924e-07, 'epoch': 204.19}

 32%|███▏      | 18500/57600 [3:14:36<6:56:22,  1.57it/s]
 32%|███▏      | 18501/57600 [3:14:37<6:47:09,  1.60it/s]
 32%|███▏      | 18502/57600 [3:14:37<6:34:27,  1.65it/s]
 32%|███▏      | 18503/57600 [3:14:38<6:34:24,  1.65it/s]
 32%|███▏      | 18504/57600 [3:14:38<6:43:16,  1.62it/s]
 32%|███▏      | 18505/57600 [3:14:39<6:31:35,  1.66it/s]
 32%|███▏      | 18506/57600 [3:14:40<6:36:46,  1.64it/s]
 32%|███▏      | 18507/57600 [3:14:40<6:46:48,  1.60it/s]
 32%|███▏      | 18508/57600 [3:14:41<6:35:49,  1.65it/s]
 32%|███▏      | 18509/57600 [3:14:41<6:35:49,  1.65it/s]
 32%|███▏      | 18510/57600 [3:14:42<6:44:17,  1.61it/s]
 32%|███▏      | 18511/57600 [3:14:43<6:52:52,  1.58it/s]
 32%|███▏      | 18512/57600 [3:14:43<6:54:42,  1.57it/s]
 32%|███▏      | 18513/57600 [3:14:44<6:53:46,  1.57it/s]
 32%|███▏      | 18514/57600 [3:14:45<6:49:46,  1.59it/s]
 32%|███▏      | 18515/57600 [3:14:45<6:48:56,  1.59it/s]
 32%|███▏      | 18516/57600 [3:14:46<6:58:23,  1.56it/s]
 32%|███▏      | 18517/57600 [3:14:47<7:06:54,  1.53it/s]
 32%|███▏      | 18518/57600 [3:14:47<6:55:53,  1.57it/s]
 32%|███▏      | 18519/57600 [3:14:48<6:54:55,  1.57it/s]
 32%|███▏      | 18520/57600 [3:14:48<7:00:51,  1.55it/s]
                                                         
{'loss': 1.2455, 'learning_rate': 7.12752613240418e-07, 'epoch': 204.42}

 32%|███▏      | 18520/57600 [3:14:48<7:00:51,  1.55it/s]
 32%|███▏      | 18521/57600 [3:14:49<6:52:11,  1.58it/s]
 32%|███▏      | 18522/57600 [3:14:50<6:48:02,  1.60it/s]
 32%|███▏      | 18523/57600 [3:14:50<6:41:10,  1.62it/s]
 32%|███▏      | 18524/57600 [3:14:51<6:43:03,  1.62it/s]
 32%|███▏      | 18525/57600 [3:14:52<6:40:13,  1.63it/s]
 32%|███▏      | 18526/57600 [3:14:52<6:39:42,  1.63it/s]
 32%|███▏      | 18527/57600 [3:14:53<6:30:58,  1.67it/s]
 32%|███▏      | 18528/57600 [3:14:53<6:36:24,  1.64it/s]
 32%|███▏      | 18529/57600 [3:14:54<6:24:54,  1.69it/s]
 32%|███▏      | 18530/57600 [3:14:55<6:36:38,  1.64it/s]
 32%|███▏      | 18531/57600 [3:14:55<6:47:36,  1.60it/s]
 32%|███▏      | 18532/57600 [3:14:56<6:50:46,  1.59it/s]
 32%|███▏      | 18533/57600 [3:14:56<6:49:06,  1.59it/s]
 32%|███▏      | 18534/57600 [3:14:57<6:53:51,  1.57it/s]
 32%|███▏      | 18535/57600 [3:14:58<7:09:13,  1.52it/s]
 32%|███▏      | 18536/57600 [3:14:58<7:04:27,  1.53it/s]
 32%|███▏      | 18537/57600 [3:14:59<7:05:54,  1.53it/s]
 32%|███▏      | 18538/57600 [3:15:00<7:05:30,  1.53it/s]
 32%|███▏      | 18539/57600 [3:15:00<6:47:33,  1.60it/s]
 32%|███▏      | 18540/57600 [3:15:01<6:53:50,  1.57it/s]
                                                         
{'loss': 1.2424, 'learning_rate': 7.124390243902438e-07, 'epoch': 204.64}

 32%|███▏      | 18540/57600 [3:15:01<6:53:50,  1.57it/s]
 32%|███▏      | 18541/57600 [3:15:02<6:47:45,  1.60it/s]
 32%|███▏      | 18542/57600 [3:15:02<6:58:37,  1.56it/s]
 32%|███▏      | 18543/57600 [3:15:03<6:46:16,  1.60it/s]
 32%|███▏      | 18544/57600 [3:15:04<7:02:17,  1.54it/s]
 32%|███▏      | 18545/57600 [3:15:04<7:08:16,  1.52it/s]
 32%|███▏      | 18546/57600 [3:15:05<7:05:45,  1.53it/s]
 32%|███▏      | 18547/57600 [3:15:06<7:09:45,  1.51it/s]
 32%|███▏      | 18548/57600 [3:15:06<7:01:12,  1.55it/s]
 32%|███▏      | 18549/57600 [3:15:07<6:46:23,  1.60it/s]
 32%|███▏      | 18550/57600 [3:15:07<6:40:19,  1.63it/s]
 32%|███▏      | 18551/57600 [3:15:08<6:43:22,  1.61it/s]
 32%|███▏      | 18552/57600 [3:15:09<6:53:13,  1.57it/s]
 32%|███▏      | 18553/57600 [3:15:09<6:45:16,  1.61it/s]
 32%|███▏      | 18554/57600 [3:15:10<6:36:55,  1.64it/s]
 32%|███▏      | 18555/57600 [3:15:10<6:40:50,  1.62it/s]
 32%|███▏      | 18556/57600 [3:15:11<6:43:10,  1.61it/s]
 32%|███▏      | 18557/57600 [3:15:12<6:47:28,  1.60it/s]
 32%|███▏      | 18558/57600 [3:15:12<6:55:47,  1.56it/s]
 32%|███▏      | 18559/57600 [3:15:13<6:58:49,  1.55it/s]
 32%|███▏      | 18560/57600 [3:15:14<6:49:37,  1.59it/s]
                                                         
{'loss': 1.2389, 'learning_rate': 7.121254355400697e-07, 'epoch': 204.86}

 32%|███▏      | 18560/57600 [3:15:14<6:49:37,  1.59it/s]
 32%|███▏      | 18561/57600 [3:15:14<6:46:12,  1.60it/s]
 32%|███▏      | 18562/57600 [3:15:15<6:43:42,  1.61it/s]
 32%|███▏      | 18563/57600 [3:15:15<6:33:17,  1.65it/s]
 32%|███▏      | 18564/57600 [3:15:16<6:45:32,  1.60it/s]
 32%|███▏      | 18565/57600 [3:15:17<6:34:31,  1.65it/s]
 32%|███▏      | 18566/57600 [3:15:17<6:35:19,  1.65it/s]
 32%|███▏      | 18567/57600 [3:15:18<6:41:54,  1.62it/s]
 32%|███▏      | 18568/57600 [3:15:18<6:33:16,  1.65it/s]
 32%|███▏      | 18569/57600 [3:15:19<6:44:32,  1.61it/s]
 32%|███▏      | 18570/57600 [3:15:20<6:40:01,  1.63it/s]
 32%|███▏      | 18571/57600 [3:15:20<6:41:47,  1.62it/s]
 32%|███▏      | 18572/57600 [3:15:21<6:32:21,  1.66it/s]
 32%|███▏      | 18573/57600 [3:15:22<6:31:49,  1.66it/s]
 32%|███▏      | 18574/57600 [3:15:22<6:58:27,  1.55it/s]
 32%|███▏      | 18575/57600 [3:15:23<7:07:58,  1.52it/s]
 32%|███▏      | 18576/57600 [3:15:24<7:11:34,  1.51it/s]
 32%|███▏      | 18577/57600 [3:15:24<7:08:33,  1.52it/s]
 32%|███▏      | 18578/57600 [3:15:25<7:09:14,  1.52it/s]
 32%|███▏      | 18579/57600 [3:15:26<7:10:38,  1.51it/s]
 32%|███▏      | 18580/57600 [3:15:26<7:05:49,  1.53it/s]
                                                         
{'loss': 1.2512, 'learning_rate': 7.118118466898955e-07, 'epoch': 205.08}

 32%|███▏      | 18580/57600 [3:15:26<7:05:49,  1.53it/s]
 32%|███▏      | 18581/57600 [3:15:27<6:54:47,  1.57it/s]
 32%|███▏      | 18582/57600 [3:15:27<6:52:14,  1.58it/s]
 32%|███▏      | 18583/57600 [3:15:28<6:39:32,  1.63it/s]
 32%|███▏      | 18584/57600 [3:15:29<6:36:27,  1.64it/s]
 32%|███▏      | 18585/57600 [3:15:29<6:29:41,  1.67it/s]
 32%|███▏      | 18586/57600 [3:15:30<6:52:50,  1.58it/s]
 32%|███▏      | 18587/57600 [3:15:31<7:05:40,  1.53it/s]
 32%|███▏      | 18588/57600 [3:15:31<7:01:38,  1.54it/s]
 32%|███▏      | 18589/57600 [3:15:32<6:50:29,  1.58it/s]
 32%|███▏      | 18590/57600 [3:15:32<6:37:34,  1.64it/s]
 32%|███▏      | 18591/57600 [3:15:33<6:28:39,  1.67it/s]
 32%|███▏      | 18592/57600 [3:15:34<6:42:40,  1.61it/s]
 32%|███▏      | 18593/57600 [3:15:34<6:34:21,  1.65it/s]
 32%|███▏      | 18594/57600 [3:15:35<6:32:58,  1.65it/s]
 32%|███▏      | 18595/57600 [3:15:35<6:34:43,  1.65it/s]
 32%|███▏      | 18596/57600 [3:15:36<6:46:09,  1.60it/s]
 32%|███▏      | 18597/57600 [3:15:37<6:36:00,  1.64it/s]
 32%|███▏      | 18598/57600 [3:15:37<6:32:49,  1.65it/s]
 32%|███▏      | 18599/57600 [3:15:38<6:27:41,  1.68it/s]
 32%|███▏      | 18600/57600 [3:15:39<6:40:57,  1.62it/s]
                                                         
{'loss': 1.2628, 'learning_rate': 7.114982578397212e-07, 'epoch': 205.3}

 32%|███▏      | 18600/57600 [3:15:39<6:40:57,  1.62it/s]
 32%|███▏      | 18601/57600 [3:15:39<6:32:52,  1.65it/s]
 32%|███▏      | 18602/57600 [3:15:40<6:34:16,  1.65it/s]
 32%|███▏      | 18603/57600 [3:15:40<6:21:06,  1.71it/s]
 32%|███▏      | 18604/57600 [3:15:41<6:11:52,  1.75it/s]
 32%|███▏      | 18605/57600 [3:15:41<6:20:11,  1.71it/s]
 32%|███▏      | 18606/57600 [3:15:42<6:35:52,  1.64it/s]
 32%|███▏      | 18607/57600 [3:15:43<6:44:02,  1.61it/s]
 32%|███▏      | 18608/57600 [3:15:43<6:45:05,  1.60it/s]
 32%|███▏      | 18609/57600 [3:15:44<6:55:00,  1.57it/s]
 32%|███▏      | 18610/57600 [3:15:45<7:06:16,  1.52it/s]
 32%|███▏      | 18611/57600 [3:15:45<7:13:07,  1.50it/s]
 32%|███▏      | 18612/57600 [3:15:46<6:59:54,  1.55it/s]
 32%|███▏      | 18613/57600 [3:15:47<6:59:36,  1.55it/s]
 32%|███▏      | 18614/57600 [3:15:47<6:52:12,  1.58it/s]
 32%|███▏      | 18615/57600 [3:15:48<7:00:29,  1.55it/s]
 32%|███▏      | 18616/57600 [3:15:49<6:56:13,  1.56it/s]
 32%|███▏      | 18617/57600 [3:15:49<6:49:03,  1.59it/s]
 32%|███▏      | 18618/57600 [3:15:50<6:36:25,  1.64it/s]
 32%|███▏      | 18619/57600 [3:15:50<6:33:12,  1.65it/s]
 32%|███▏      | 18620/57600 [3:15:51<6:29:20,  1.67it/s]
                                                         
{'loss': 1.2864, 'learning_rate': 7.11184668989547e-07, 'epoch': 205.52}

 32%|███▏      | 18620/57600 [3:15:51<6:29:20,  1.67it/s]
 32%|███▏      | 18621/57600 [3:15:52<6:43:35,  1.61it/s]
 32%|███▏      | 18622/57600 [3:15:52<6:45:15,  1.60it/s]
 32%|███▏      | 18623/57600 [3:15:53<6:42:05,  1.62it/s]
 32%|███▏      | 18624/57600 [3:15:53<6:45:43,  1.60it/s]
 32%|███▏      | 18625/57600 [3:15:54<6:40:51,  1.62it/s]
 32%|███▏      | 18626/57600 [3:15:55<6:37:41,  1.63it/s]
 32%|███▏      | 18627/57600 [3:15:55<6:28:40,  1.67it/s]
 32%|███▏      | 18628/57600 [3:15:56<6:34:28,  1.65it/s]
 32%|███▏      | 18629/57600 [3:15:57<6:53:22,  1.57it/s]
 32%|███▏      | 18630/57600 [3:15:57<6:47:27,  1.59it/s]
 32%|███▏      | 18631/57600 [3:15:58<6:34:44,  1.65it/s]
 32%|███▏      | 18632/57600 [3:15:58<6:40:34,  1.62it/s]
 32%|███▏      | 18633/57600 [3:15:59<6:37:12,  1.64it/s]
 32%|███▏      | 18634/57600 [3:16:00<6:41:01,  1.62it/s]
 32%|███▏      | 18635/57600 [3:16:00<6:44:22,  1.61it/s]
 32%|███▏      | 18636/57600 [3:16:01<6:46:48,  1.60it/s]
 32%|███▏      | 18637/57600 [3:16:02<6:49:43,  1.58it/s]
 32%|███▏      | 18638/57600 [3:16:02<6:38:50,  1.63it/s]
 32%|███▏      | 18639/57600 [3:16:03<6:45:22,  1.60it/s]
 32%|███▏      | 18640/57600 [3:16:03<6:56:40,  1.56it/s]
                                                         
{'loss': 1.2508, 'learning_rate': 7.108710801393729e-07, 'epoch': 205.74}

 32%|███▏      | 18640/57600 [3:16:03<6:56:40,  1.56it/s]
 32%|███▏      | 18641/57600 [3:16:04<6:58:53,  1.55it/s]
 32%|███▏      | 18642/57600 [3:16:05<6:47:37,  1.59it/s]
 32%|███▏      | 18643/57600 [3:16:05<6:48:26,  1.59it/s]
 32%|███▏      | 18644/57600 [3:16:06<6:42:54,  1.61it/s]
 32%|███▏      | 18645/57600 [3:16:07<6:46:11,  1.60it/s]
 32%|███▏      | 18646/57600 [3:16:07<6:52:45,  1.57it/s]
 32%|███▏      | 18647/57600 [3:16:08<6:45:48,  1.60it/s]
 32%|███▏      | 18648/57600 [3:16:08<6:46:42,  1.60it/s]
 32%|███▏      | 18649/57600 [3:16:09<6:44:42,  1.60it/s]
 32%|███▏      | 18650/57600 [3:16:10<6:34:52,  1.64it/s]
 32%|███▏      | 18651/57600 [3:16:10<6:34:02,  1.65it/s]
 32%|███▏      | 18652/57600 [3:16:11<6:46:09,  1.60it/s]
 32%|███▏      | 18653/57600 [3:16:11<6:44:01,  1.61it/s]
 32%|███▏      | 18654/57600 [3:16:12<6:34:16,  1.65it/s]
 32%|███▏      | 18655/57600 [3:16:13<6:42:40,  1.61it/s]
 32%|███▏      | 18656/57600 [3:16:13<6:26:06,  1.68it/s]
 32%|███▏      | 18657/57600 [3:16:14<6:34:49,  1.64it/s]
 32%|███▏      | 18658/57600 [3:16:14<6:32:03,  1.66it/s]
 32%|███▏      | 18659/57600 [3:16:15<6:31:40,  1.66it/s]
 32%|███▏      | 18660/57600 [3:16:16<6:30:19,  1.66it/s]
                                                         
{'loss': 1.2848, 'learning_rate': 7.105574912891985e-07, 'epoch': 205.96}

 32%|███▏      | 18660/57600 [3:16:16<6:30:19,  1.66it/s]
 32%|███▏      | 18661/57600 [3:16:16<6:35:45,  1.64it/s]
 32%|███▏      | 18662/57600 [3:16:17<6:36:47,  1.64it/s]
 32%|███▏      | 18663/57600 [3:16:18<6:37:49,  1.63it/s]
 32%|███▏      | 18664/57600 [3:16:18<6:53:07,  1.57it/s]
 32%|███▏      | 18665/57600 [3:16:19<6:48:43,  1.59it/s]
 32%|███▏      | 18666/57600 [3:16:20<6:53:17,  1.57it/s]
 32%|███▏      | 18667/57600 [3:16:20<6:36:55,  1.63it/s]
 32%|███▏      | 18668/57600 [3:16:21<6:39:10,  1.63it/s]
 32%|███▏      | 18669/57600 [3:16:21<6:39:49,  1.62it/s]
 32%|███▏      | 18670/57600 [3:16:22<6:39:33,  1.62it/s]
 32%|███▏      | 18671/57600 [3:16:23<6:48:23,  1.59it/s]
 32%|███▏      | 18672/57600 [3:16:23<6:41:33,  1.62it/s]
 32%|███▏      | 18673/57600 [3:16:24<6:59:44,  1.55it/s]
 32%|███▏      | 18674/57600 [3:16:24<6:47:09,  1.59it/s]
 32%|███▏      | 18675/57600 [3:16:25<6:56:45,  1.56it/s]
 32%|███▏      | 18676/57600 [3:16:26<6:54:15,  1.57it/s]
 32%|███▏      | 18677/57600 [3:16:26<6:38:32,  1.63it/s]
 32%|███▏      | 18678/57600 [3:16:27<6:27:30,  1.67it/s]
 32%|███▏      | 18679/57600 [3:16:28<6:50:01,  1.58it/s]
 32%|███▏      | 18680/57600 [3:16:28<6:55:36,  1.56it/s]
                                                         
{'loss': 1.2312, 'learning_rate': 7.102439024390243e-07, 'epoch': 206.18}

 32%|███▏      | 18680/57600 [3:16:28<6:55:36,  1.56it/s]
 32%|███▏      | 18681/57600 [3:16:29<6:50:31,  1.58it/s]
 32%|███▏      | 18682/57600 [3:16:29<6:37:01,  1.63it/s]
 32%|███▏      | 18683/57600 [3:16:30<6:47:14,  1.59it/s]
 32%|███▏      | 18684/57600 [3:16:31<6:53:57,  1.57it/s]
 32%|███▏      | 18685/57600 [3:16:31<6:59:16,  1.55it/s]
 32%|███▏      | 18686/57600 [3:16:32<6:59:59,  1.54it/s]
 32%|███▏      | 18687/57600 [3:16:33<7:01:44,  1.54it/s]
 32%|███▏      | 18688/57600 [3:16:33<6:43:14,  1.61it/s]
 32%|███▏      | 18689/57600 [3:16:34<6:34:45,  1.64it/s]
 32%|███▏      | 18690/57600 [3:16:35<6:40:32,  1.62it/s]
 32%|███▏      | 18691/57600 [3:16:35<6:56:48,  1.56it/s]
 32%|███▏      | 18692/57600 [3:16:36<6:49:29,  1.58it/s]
 32%|███▏      | 18693/57600 [3:16:36<6:50:07,  1.58it/s]
 32%|███▏      | 18694/57600 [3:16:37<6:37:50,  1.63it/s]
 32%|███▏      | 18695/57600 [3:16:38<6:45:28,  1.60it/s]
 32%|███▏      | 18696/57600 [3:16:38<6:47:24,  1.59it/s]
 32%|███▏      | 18697/57600 [3:16:39<6:39:37,  1.62it/s]
 32%|███▏      | 18698/57600 [3:16:39<6:34:14,  1.64it/s]
 32%|███▏      | 18699/57600 [3:16:40<6:36:07,  1.64it/s]
 32%|███▏      | 18700/57600 [3:16:41<6:37:01,  1.63it/s]
                                                         
{'loss': 1.262, 'learning_rate': 7.099303135888501e-07, 'epoch': 206.4}

 32%|███▏      | 18700/57600 [3:16:41<6:37:01,  1.63it/s]
 32%|███▏      | 18701/57600 [3:16:41<6:27:40,  1.67it/s]
 32%|███▏      | 18702/57600 [3:16:42<6:31:49,  1.65it/s]
 32%|███▏      | 18703/57600 [3:16:43<6:35:07,  1.64it/s]
 32%|███▏      | 18704/57600 [3:16:43<6:27:19,  1.67it/s]
 32%|███▏      | 18705/57600 [3:16:44<6:28:28,  1.67it/s]
 32%|███▏      | 18706/57600 [3:16:44<6:27:40,  1.67it/s]
 32%|███▏      | 18707/57600 [3:16:45<6:25:19,  1.68it/s]
 32%|███▏      | 18708/57600 [3:16:46<6:36:11,  1.64it/s]
 32%|███▏      | 18709/57600 [3:16:46<6:46:38,  1.59it/s]
 32%|███▏      | 18710/57600 [3:16:47<6:50:19,  1.58it/s]
 32%|███▏      | 18711/57600 [3:16:47<6:52:00,  1.57it/s]
 32%|███▏      | 18712/57600 [3:16:48<6:49:05,  1.58it/s]
 32%|███▏      | 18713/57600 [3:16:49<6:48:09,  1.59it/s]
 32%|███▏      | 18714/57600 [3:16:49<6:49:29,  1.58it/s]
 32%|███▏      | 18715/57600 [3:16:50<6:38:30,  1.63it/s]
 32%|███▏      | 18716/57600 [3:16:51<6:42:17,  1.61it/s]
 32%|███▏      | 18717/57600 [3:16:51<6:51:35,  1.57it/s]
 32%|███▏      | 18718/57600 [3:16:52<6:52:59,  1.57it/s]
 32%|███▏      | 18719/57600 [3:16:53<7:08:35,  1.51it/s]
 32%|███▎      | 18720/57600 [3:16:53<7:04:09,  1.53it/s]
                                                         
{'loss': 1.2394, 'learning_rate': 7.09616724738676e-07, 'epoch': 206.62}

 32%|███▎      | 18720/57600 [3:16:53<7:04:09,  1.53it/s]
 33%|███▎      | 18721/57600 [3:16:54<6:55:49,  1.56it/s]
 33%|███▎      | 18722/57600 [3:16:54<6:47:12,  1.59it/s]
 33%|███▎      | 18723/57600 [3:16:55<7:06:43,  1.52it/s]
 33%|███▎      | 18724/57600 [3:16:56<6:50:44,  1.58it/s]
 33%|███▎      | 18725/57600 [3:16:56<6:38:43,  1.62it/s]
 33%|███▎      | 18726/57600 [3:16:57<6:30:34,  1.66it/s]
 33%|███▎      | 18727/57600 [3:16:57<6:20:44,  1.70it/s]
 33%|███▎      | 18728/57600 [3:16:58<6:24:44,  1.68it/s]
 33%|███▎      | 18729/57600 [3:16:59<6:23:01,  1.69it/s]
 33%|███▎      | 18730/57600 [3:16:59<6:26:10,  1.68it/s]
 33%|███▎      | 18731/57600 [3:17:00<6:26:26,  1.68it/s]
 33%|███▎      | 18732/57600 [3:17:00<6:30:46,  1.66it/s]
 33%|███▎      | 18733/57600 [3:17:01<6:19:08,  1.71it/s]
 33%|███▎      | 18734/57600 [3:17:02<6:09:20,  1.75it/s]
 33%|███▎      | 18735/57600 [3:17:02<6:22:14,  1.69it/s]
 33%|███▎      | 18736/57600 [3:17:03<6:44:04,  1.60it/s]
 33%|███▎      | 18737/57600 [3:17:04<6:48:16,  1.59it/s]
 33%|███▎      | 18738/57600 [3:17:04<7:05:01,  1.52it/s]
 33%|███▎      | 18739/57600 [3:17:05<6:56:41,  1.55it/s]
 33%|███▎      | 18740/57600 [3:17:06<7:08:51,  1.51it/s]
                                                         
{'loss': 1.2877, 'learning_rate': 7.093031358885016e-07, 'epoch': 206.84}

 33%|███▎      | 18740/57600 [3:17:06<7:08:51,  1.51it/s]
 33%|███▎      | 18741/57600 [3:17:06<6:58:03,  1.55it/s]
 33%|███▎      | 18742/57600 [3:17:07<6:47:00,  1.59it/s]
 33%|███▎      | 18743/57600 [3:17:07<6:52:39,  1.57it/s]
 33%|███▎      | 18744/57600 [3:17:08<6:40:31,  1.62it/s]
 33%|███▎      | 18745/57600 [3:17:09<6:46:22,  1.59it/s]
 33%|███▎      | 18746/57600 [3:17:09<6:41:31,  1.61it/s]
 33%|███▎      | 18747/57600 [3:17:10<6:53:33,  1.57it/s]
 33%|███▎      | 18748/57600 [3:17:10<6:37:34,  1.63it/s]
 33%|███▎      | 18749/57600 [3:17:11<6:30:40,  1.66it/s]
 33%|███▎      | 18750/57600 [3:17:12<6:22:49,  1.69it/s]
 33%|███▎      | 18751/57600 [3:17:12<6:31:14,  1.65it/s]
 33%|███▎      | 18752/57600 [3:17:13<6:33:00,  1.65it/s]
 33%|███▎      | 18753/57600 [3:17:13<6:32:28,  1.65it/s]
 33%|███▎      | 18754/57600 [3:17:14<6:37:33,  1.63it/s]
 33%|███▎      | 18755/57600 [3:17:15<6:38:45,  1.62it/s]
 33%|███▎      | 18756/57600 [3:17:15<6:34:23,  1.64it/s]
 33%|███▎      | 18757/57600 [3:17:16<6:34:56,  1.64it/s]
 33%|███▎      | 18758/57600 [3:17:17<6:39:57,  1.62it/s]
 33%|███▎      | 18759/57600 [3:17:17<6:46:01,  1.59it/s]
 33%|███▎      | 18760/57600 [3:17:18<6:37:19,  1.63it/s]
                                                         
{'loss': 1.3101, 'learning_rate': 7.089895470383275e-07, 'epoch': 207.06}

 33%|███▎      | 18760/57600 [3:17:18<6:37:19,  1.63it/s]
 33%|███▎      | 18761/57600 [3:17:18<6:38:19,  1.63it/s]
 33%|███▎      | 18762/57600 [3:17:19<6:34:28,  1.64it/s]
 33%|███▎      | 18763/57600 [3:17:20<6:30:56,  1.66it/s]
 33%|███▎      | 18764/57600 [3:17:20<6:36:13,  1.63it/s]
 33%|███▎      | 18765/57600 [3:17:21<6:48:50,  1.58it/s]
 33%|███▎      | 18766/57600 [3:17:21<6:35:50,  1.64it/s]
 33%|███▎      | 18767/57600 [3:17:22<6:55:57,  1.56it/s]
 33%|███▎      | 18768/57600 [3:17:23<6:40:20,  1.62it/s]
 33%|███▎      | 18769/57600 [3:17:23<6:45:16,  1.60it/s]
 33%|███▎      | 18770/57600 [3:17:24<7:03:11,  1.53it/s]
 33%|███▎      | 18771/57600 [3:17:25<6:50:02,  1.58it/s]
 33%|███▎      | 18772/57600 [3:17:25<6:45:39,  1.60it/s]
 33%|███▎      | 18773/57600 [3:17:26<7:02:00,  1.53it/s]
 33%|███▎      | 18774/57600 [3:17:27<6:43:51,  1.60it/s]
 33%|███▎      | 18775/57600 [3:17:27<6:52:54,  1.57it/s]
 33%|███▎      | 18776/57600 [3:17:28<7:06:57,  1.52it/s]
 33%|███▎      | 18777/57600 [3:17:29<6:53:20,  1.57it/s]
 33%|███▎      | 18778/57600 [3:17:29<6:55:33,  1.56it/s]
 33%|███▎      | 18779/57600 [3:17:30<6:53:13,  1.57it/s]
 33%|███▎      | 18780/57600 [3:17:30<6:43:52,  1.60it/s]
                                                         
{'loss': 1.2197, 'learning_rate': 7.086759581881534e-07, 'epoch': 207.28}

 33%|███▎      | 18780/57600 [3:17:30<6:43:52,  1.60it/s]
 33%|███▎      | 18781/57600 [3:17:31<6:27:38,  1.67it/s]
 33%|███▎      | 18782/57600 [3:17:32<6:34:53,  1.64it/s]
 33%|███▎      | 18783/57600 [3:17:32<6:41:49,  1.61it/s]
 33%|███▎      | 18784/57600 [3:17:33<6:42:33,  1.61it/s]
 33%|███▎      | 18785/57600 [3:17:33<6:37:27,  1.63it/s]
 33%|███▎      | 18786/57600 [3:17:34<6:38:14,  1.62it/s]
 33%|███▎      | 18787/57600 [3:17:35<6:44:14,  1.60it/s]
 33%|███▎      | 18788/57600 [3:17:35<7:07:33,  1.51it/s]
 33%|███▎      | 18789/57600 [3:17:36<6:53:29,  1.56it/s]
 33%|███▎      | 18790/57600 [3:17:37<6:52:51,  1.57it/s]
 33%|███▎      | 18791/57600 [3:17:37<7:08:36,  1.51it/s]
 33%|███▎      | 18792/57600 [3:17:38<6:47:38,  1.59it/s]
 33%|███▎      | 18793/57600 [3:17:39<7:02:25,  1.53it/s]
 33%|███▎      | 18794/57600 [3:17:39<6:49:42,  1.58it/s]
 33%|███▎      | 18795/57600 [3:17:40<6:40:49,  1.61it/s]
 33%|███▎      | 18796/57600 [3:17:41<6:41:40,  1.61it/s]
 33%|███▎      | 18797/57600 [3:17:41<6:28:39,  1.66it/s]
 33%|███▎      | 18798/57600 [3:17:42<6:28:11,  1.67it/s]
 33%|███▎      | 18799/57600 [3:17:42<6:26:23,  1.67it/s]
 33%|███▎      | 18800/57600 [3:17:43<6:24:05,  1.68it/s]
                                                         
{'loss': 1.275, 'learning_rate': 7.083623693379791e-07, 'epoch': 207.51}

 33%|███▎      | 18800/57600 [3:17:43<6:24:05,  1.68it/s]
 33%|███▎      | 18801/57600 [3:17:43<6:19:47,  1.70it/s]
 33%|███▎      | 18802/57600 [3:17:44<6:28:36,  1.66it/s]
 33%|███▎      | 18803/57600 [3:17:45<6:39:02,  1.62it/s]
 33%|███▎      | 18804/57600 [3:17:45<6:31:12,  1.65it/s]
 33%|███▎      | 18805/57600 [3:17:46<6:32:04,  1.65it/s]
 33%|███▎      | 18806/57600 [3:17:46<6:33:26,  1.64it/s]
 33%|███▎      | 18807/57600 [3:17:47<6:32:20,  1.65it/s]
 33%|███▎      | 18808/57600 [3:17:48<6:42:15,  1.61it/s]
 33%|███▎      | 18809/57600 [3:17:48<6:40:06,  1.62it/s]
 33%|███▎      | 18810/57600 [3:17:49<6:42:12,  1.61it/s]
 33%|███▎      | 18811/57600 [3:17:50<6:39:46,  1.62it/s]
 33%|███▎      | 18812/57600 [3:17:50<6:40:39,  1.61it/s]
 33%|███▎      | 18813/57600 [3:17:51<6:37:31,  1.63it/s]
 33%|███▎      | 18814/57600 [3:17:51<6:41:32,  1.61it/s]
 33%|███▎      | 18815/57600 [3:17:52<6:32:43,  1.65it/s]
 33%|███▎      | 18816/57600 [3:17:53<6:30:20,  1.66it/s]
 33%|███▎      | 18817/57600 [3:17:53<6:45:54,  1.59it/s]
 33%|███▎      | 18818/57600 [3:17:54<6:37:46,  1.62it/s]
 33%|███▎      | 18819/57600 [3:17:54<6:32:58,  1.64it/s]
 33%|███▎      | 18820/57600 [3:17:55<6:42:04,  1.61it/s]
                                                         
{'loss': 1.2956, 'learning_rate': 7.080487804878046e-07, 'epoch': 207.73}

 33%|███▎      | 18820/57600 [3:17:55<6:42:04,  1.61it/s]
 33%|███▎      | 18821/57600 [3:17:56<6:50:01,  1.58it/s]
 33%|███▎      | 18822/57600 [3:17:56<6:45:40,  1.59it/s]
 33%|███▎      | 18823/57600 [3:17:57<6:38:31,  1.62it/s]
 33%|███▎      | 18824/57600 [3:17:58<6:36:51,  1.63it/s]
 33%|███▎      | 18825/57600 [3:17:58<6:47:12,  1.59it/s]
 33%|███▎      | 18826/57600 [3:17:59<6:31:43,  1.65it/s]
 33%|███▎      | 18827/57600 [3:17:59<6:23:21,  1.69it/s]
 33%|███▎      | 18828/57600 [3:18:00<6:28:23,  1.66it/s]
 33%|███▎      | 18829/57600 [3:18:01<6:35:15,  1.63it/s]
 33%|███▎      | 18830/57600 [3:18:01<6:36:42,  1.63it/s]
 33%|███▎      | 18831/57600 [3:18:02<6:29:54,  1.66it/s]
 33%|███▎      | 18832/57600 [3:18:02<6:23:35,  1.68it/s]
 33%|███▎      | 18833/57600 [3:18:03<6:36:25,  1.63it/s]
 33%|███▎      | 18834/57600 [3:18:04<6:32:19,  1.65it/s]
 33%|███▎      | 18835/57600 [3:18:04<6:34:31,  1.64it/s]
 33%|███▎      | 18836/57600 [3:18:05<6:23:39,  1.68it/s]
 33%|███▎      | 18837/57600 [3:18:06<6:34:16,  1.64it/s]
 33%|███▎      | 18838/57600 [3:18:06<6:47:18,  1.59it/s]
 33%|███▎      | 18839/57600 [3:18:07<7:01:26,  1.53it/s]
 33%|███▎      | 18840/57600 [3:18:08<7:14:52,  1.49it/s]
                                                         
{'loss': 1.2694, 'learning_rate': 7.077351916376306e-07, 'epoch': 207.95}

 33%|███▎      | 18840/57600 [3:18:08<7:14:52,  1.49it/s]
 33%|███▎      | 18841/57600 [3:18:08<7:11:55,  1.50it/s]
 33%|███▎      | 18842/57600 [3:18:09<6:56:22,  1.55it/s]
 33%|███▎      | 18843/57600 [3:18:09<6:41:47,  1.61it/s]
 33%|███▎      | 18844/57600 [3:18:10<6:36:42,  1.63it/s]
 33%|███▎      | 18845/57600 [3:18:11<6:57:58,  1.55it/s]
 33%|███▎      | 18846/57600 [3:18:11<6:49:00,  1.58it/s]
 33%|███▎      | 18847/57600 [3:18:12<6:55:48,  1.55it/s]
 33%|███▎      | 18848/57600 [3:18:13<6:45:16,  1.59it/s]
 33%|███▎      | 18849/57600 [3:18:13<6:51:05,  1.57it/s]
 33%|███▎      | 18850/57600 [3:18:14<6:37:27,  1.62it/s]
 33%|███▎      | 18851/57600 [3:18:14<6:38:01,  1.62it/s]
 33%|███▎      | 18852/57600 [3:18:15<6:55:29,  1.55it/s]
 33%|███▎      | 18853/57600 [3:18:16<6:44:18,  1.60it/s]
 33%|███▎      | 18854/57600 [3:18:16<6:36:37,  1.63it/s]
 33%|███▎      | 18855/57600 [3:18:17<6:34:42,  1.64it/s]
 33%|███▎      | 18856/57600 [3:18:17<6:23:25,  1.68it/s]
 33%|███▎      | 18857/57600 [3:18:18<6:25:49,  1.67it/s]
 33%|███▎      | 18858/57600 [3:18:19<6:43:24,  1.60it/s]
 33%|███▎      | 18859/57600 [3:18:19<6:41:22,  1.61it/s]
 33%|███▎      | 18860/57600 [3:18:20<6:46:21,  1.59it/s]
                                                         
{'loss': 1.2505, 'learning_rate': 7.074216027874565e-07, 'epoch': 208.17}

 33%|███▎      | 18860/57600 [3:18:20<6:46:21,  1.59it/s]
 33%|███▎      | 18861/57600 [3:18:21<6:51:50,  1.57it/s]
 33%|███▎      | 18862/57600 [3:18:21<6:51:46,  1.57it/s]
 33%|███▎      | 18863/57600 [3:18:22<6:49:40,  1.58it/s]
 33%|███▎      | 18864/57600 [3:18:23<6:49:26,  1.58it/s]
 33%|███▎      | 18865/57600 [3:18:23<6:44:45,  1.59it/s]
 33%|███▎      | 18866/57600 [3:18:24<6:53:13,  1.56it/s]
 33%|███▎      | 18867/57600 [3:18:25<6:53:11,  1.56it/s]
 33%|███▎      | 18868/57600 [3:18:25<6:56:39,  1.55it/s]
 33%|███▎      | 18869/57600 [3:18:26<7:02:59,  1.53it/s]
 33%|███▎      | 18870/57600 [3:18:26<6:45:15,  1.59it/s]
 33%|███▎      | 18871/57600 [3:18:27<6:34:25,  1.64it/s]
 33%|███▎      | 18872/57600 [3:18:28<6:42:05,  1.61it/s]
 33%|███▎      | 18873/57600 [3:18:28<6:33:49,  1.64it/s]
 33%|███▎      | 18874/57600 [3:18:29<6:28:21,  1.66it/s]
 33%|███▎      | 18875/57600 [3:18:29<6:33:07,  1.64it/s]
 33%|███▎      | 18876/57600 [3:18:30<6:43:04,  1.60it/s]
 33%|███▎      | 18877/57600 [3:18:31<6:35:39,  1.63it/s]
 33%|███▎      | 18878/57600 [3:18:31<6:24:53,  1.68it/s]
 33%|███▎      | 18879/57600 [3:18:32<6:50:24,  1.57it/s]
 33%|███▎      | 18880/57600 [3:18:33<6:45:44,  1.59it/s]
                                                         
{'loss': 1.2509, 'learning_rate': 7.071080139372822e-07, 'epoch': 208.39}

 33%|███▎      | 18880/57600 [3:18:33<6:45:44,  1.59it/s]
 33%|███▎      | 18881/57600 [3:18:33<6:49:29,  1.58it/s]
 33%|███▎      | 18882/57600 [3:18:34<6:47:24,  1.58it/s]
 33%|███▎      | 18883/57600 [3:18:34<6:32:51,  1.64it/s]
 33%|███▎      | 18884/57600 [3:18:35<6:34:38,  1.64it/s]
 33%|███▎      | 18885/57600 [3:18:36<6:27:42,  1.66it/s]
 33%|███▎      | 18886/57600 [3:18:36<6:26:53,  1.67it/s]
 33%|███▎      | 18887/57600 [3:18:37<6:39:23,  1.62it/s]
 33%|███▎      | 18888/57600 [3:18:37<6:29:21,  1.66it/s]
 33%|███▎      | 18889/57600 [3:18:38<6:32:31,  1.64it/s]
 33%|███▎      | 18890/57600 [3:18:39<6:41:46,  1.61it/s]
 33%|███▎      | 18891/57600 [3:18:39<6:34:17,  1.64it/s]
 33%|███▎      | 18892/57600 [3:18:40<6:31:18,  1.65it/s]
 33%|███▎      | 18893/57600 [3:18:40<6:24:51,  1.68it/s]
 33%|███▎      | 18894/57600 [3:18:41<6:16:35,  1.71it/s]
 33%|███▎      | 18895/57600 [3:18:42<6:15:59,  1.72it/s]
 33%|███▎      | 18896/57600 [3:18:42<6:16:18,  1.71it/s]
 33%|███▎      | 18897/57600 [3:18:43<6:20:12,  1.70it/s]
 33%|███▎      | 18898/57600 [3:18:43<6:14:41,  1.72it/s]
 33%|███▎      | 18899/57600 [3:18:44<6:20:01,  1.70it/s]
 33%|███▎      | 18900/57600 [3:18:45<6:26:39,  1.67it/s]
                                                         
{'loss': 1.2856, 'learning_rate': 7.06794425087108e-07, 'epoch': 208.61}

 33%|███▎      | 18900/57600 [3:18:45<6:26:39,  1.67it/s]
 33%|███▎      | 18901/57600 [3:18:45<6:21:25,  1.69it/s]
 33%|███▎      | 18902/57600 [3:18:46<6:27:41,  1.66it/s]
 33%|███▎      | 18903/57600 [3:18:46<6:24:17,  1.68it/s]
 33%|███▎      | 18904/57600 [3:18:47<6:28:35,  1.66it/s]
 33%|███▎      | 18905/57600 [3:18:48<6:28:12,  1.66it/s]
 33%|███▎      | 18906/57600 [3:18:48<6:38:21,  1.62it/s]
 33%|███▎      | 18907/57600 [3:18:49<6:43:26,  1.60it/s]
 33%|███▎      | 18908/57600 [3:18:50<6:56:55,  1.55it/s]
 33%|███▎      | 18909/57600 [3:18:50<6:51:21,  1.57it/s]
 33%|███▎      | 18910/57600 [3:18:51<6:52:06,  1.56it/s]
 33%|███▎      | 18911/57600 [3:18:51<6:49:09,  1.58it/s]
 33%|███▎      | 18912/57600 [3:18:52<6:39:55,  1.61it/s]
 33%|███▎      | 18913/57600 [3:18:53<6:40:52,  1.61it/s]
 33%|███▎      | 18914/57600 [3:18:53<6:47:09,  1.58it/s]
 33%|███▎      | 18915/57600 [3:18:54<6:50:20,  1.57it/s]
 33%|███▎      | 18916/57600 [3:18:55<6:55:08,  1.55it/s]
 33%|███▎      | 18917/57600 [3:18:55<6:52:04,  1.56it/s]
 33%|███▎      | 18918/57600 [3:18:56<6:58:30,  1.54it/s]
 33%|███▎      | 18919/57600 [3:18:56<6:42:07,  1.60it/s]
 33%|███▎      | 18920/57600 [3:18:57<6:39:35,  1.61it/s]
                                                         
{'loss': 1.2689, 'learning_rate': 7.064808362369337e-07, 'epoch': 208.83}

 33%|███▎      | 18920/57600 [3:18:57<6:39:35,  1.61it/s]
 33%|███▎      | 18921/57600 [3:18:58<6:30:57,  1.65it/s]
 33%|███▎      | 18922/57600 [3:18:58<6:40:31,  1.61it/s]
 33%|███▎      | 18923/57600 [3:18:59<6:43:14,  1.60it/s]
 33%|███▎      | 18924/57600 [3:19:00<6:46:41,  1.58it/s]
 33%|███▎      | 18925/57600 [3:19:00<6:37:47,  1.62it/s]
 33%|███▎      | 18926/57600 [3:19:01<6:41:25,  1.61it/s]
 33%|███▎      | 18927/57600 [3:19:01<6:50:47,  1.57it/s]
 33%|███▎      | 18928/57600 [3:19:02<6:38:48,  1.62it/s]
 33%|███▎      | 18929/57600 [3:19:03<6:54:51,  1.55it/s]
 33%|███▎      | 18930/57600 [3:19:03<6:40:48,  1.61it/s]
 33%|███▎      | 18931/57600 [3:19:04<6:33:19,  1.64it/s]
 33%|███▎      | 18932/57600 [3:19:05<6:31:29,  1.65it/s]
 33%|███▎      | 18933/57600 [3:19:05<6:28:43,  1.66it/s]
 33%|███▎      | 18934/57600 [3:19:06<6:38:19,  1.62it/s]
 33%|███▎      | 18935/57600 [3:19:06<6:34:05,  1.64it/s]
 33%|███▎      | 18936/57600 [3:19:07<6:47:17,  1.58it/s]
 33%|███▎      | 18937/57600 [3:19:08<6:36:49,  1.62it/s]
 33%|███▎      | 18938/57600 [3:19:08<6:48:21,  1.58it/s]
 33%|███▎      | 18939/57600 [3:19:09<6:59:45,  1.54it/s]
 33%|███▎      | 18940/57600 [3:19:10<7:06:57,  1.51it/s]
                                                         
{'loss': 1.2656, 'learning_rate': 7.061672473867596e-07, 'epoch': 209.05}

 33%|███▎      | 18940/57600 [3:19:10<7:06:57,  1.51it/s]
 33%|███▎      | 18941/57600 [3:19:10<7:13:00,  1.49it/s]
 33%|███▎      | 18942/57600 [3:19:11<7:08:14,  1.50it/s]
 33%|███▎      | 18943/57600 [3:19:12<7:02:04,  1.53it/s]
 33%|███▎      | 18944/57600 [3:19:12<6:50:25,  1.57it/s]
 33%|███▎      | 18945/57600 [3:19:13<6:40:36,  1.61it/s]
 33%|███▎      | 18946/57600 [3:19:13<6:29:42,  1.65it/s]
 33%|███▎      | 18947/57600 [3:19:14<6:31:47,  1.64it/s]
 33%|███▎      | 18948/57600 [3:19:15<6:22:54,  1.68it/s]
 33%|███▎      | 18949/57600 [3:19:15<6:43:23,  1.60it/s]
 33%|███▎      | 18950/57600 [3:19:16<6:45:24,  1.59it/s]
 33%|███▎      | 18951/57600 [3:19:17<6:40:59,  1.61it/s]
 33%|███▎      | 18952/57600 [3:19:17<6:57:20,  1.54it/s]
 33%|███▎      | 18953/57600 [3:19:18<6:59:18,  1.54it/s]
 33%|███▎      | 18954/57600 [3:19:18<6:44:40,  1.59it/s]
 33%|███▎      | 18955/57600 [3:19:19<6:34:23,  1.63it/s]
 33%|███▎      | 18956/57600 [3:19:20<6:34:43,  1.63it/s]
 33%|███▎      | 18957/57600 [3:19:20<6:46:45,  1.58it/s]
 33%|███▎      | 18958/57600 [3:19:21<6:46:35,  1.58it/s]
 33%|███▎      | 18959/57600 [3:19:22<6:45:29,  1.59it/s]
 33%|███▎      | 18960/57600 [3:19:22<6:41:13,  1.61it/s]
                                                         
{'loss': 1.2616, 'learning_rate': 7.058536585365852e-07, 'epoch': 209.27}

 33%|███▎      | 18960/57600 [3:19:22<6:41:13,  1.61it/s]
 33%|███▎      | 18961/57600 [3:19:23<6:50:58,  1.57it/s]
 33%|███▎      | 18962/57600 [3:19:23<6:42:34,  1.60it/s]
 33%|███▎      | 18963/57600 [3:19:24<6:41:04,  1.61it/s]
 33%|███▎      | 18964/57600 [3:19:25<6:47:01,  1.58it/s]
 33%|███▎      | 18965/57600 [3:19:25<6:37:56,  1.62it/s]
 33%|███▎      | 18966/57600 [3:19:26<6:42:03,  1.60it/s]
 33%|███▎      | 18967/57600 [3:19:27<6:44:45,  1.59it/s]
 33%|███▎      | 18968/57600 [3:19:27<6:37:13,  1.62it/s]
 33%|███▎      | 18969/57600 [3:19:28<6:27:57,  1.66it/s]
 33%|███▎      | 18970/57600 [3:19:28<6:33:52,  1.63it/s]
 33%|███▎      | 18971/57600 [3:19:29<6:36:19,  1.62it/s]
 33%|███▎      | 18972/57600 [3:19:30<6:28:14,  1.66it/s]
 33%|███▎      | 18973/57600 [3:19:30<6:30:32,  1.65it/s]
 33%|███▎      | 18974/57600 [3:19:31<6:25:23,  1.67it/s]
 33%|███▎      | 18975/57600 [3:19:31<6:33:20,  1.64it/s]
 33%|███▎      | 18976/57600 [3:19:32<6:26:24,  1.67it/s]
 33%|███▎      | 18977/57600 [3:19:33<6:43:21,  1.60it/s]
 33%|███▎      | 18978/57600 [3:19:33<6:38:16,  1.62it/s]
 33%|███▎      | 18979/57600 [3:19:34<6:31:43,  1.64it/s]
 33%|███▎      | 18980/57600 [3:19:34<6:25:24,  1.67it/s]
                                                         
{'loss': 1.2555, 'learning_rate': 7.055400696864111e-07, 'epoch': 209.49}

 33%|███▎      | 18980/57600 [3:19:34<6:25:24,  1.67it/s]
 33%|███▎      | 18981/57600 [3:19:35<6:25:05,  1.67it/s]
 33%|███▎      | 18982/57600 [3:19:36<6:23:47,  1.68it/s]
 33%|███▎      | 18983/57600 [3:19:36<6:20:41,  1.69it/s]
 33%|███▎      | 18984/57600 [3:19:37<6:24:23,  1.67it/s]
 33%|███▎      | 18985/57600 [3:19:37<6:21:46,  1.69it/s]
 33%|███▎      | 18986/57600 [3:19:38<6:40:04,  1.61it/s]
 33%|███▎      | 18987/57600 [3:19:39<6:46:59,  1.58it/s]
 33%|███▎      | 18988/57600 [3:19:39<6:43:09,  1.60it/s]
 33%|███▎      | 18989/57600 [3:19:40<6:47:24,  1.58it/s]
 33%|███▎      | 18990/57600 [3:19:41<6:47:51,  1.58it/s]
 33%|███▎      | 18991/57600 [3:19:41<6:49:02,  1.57it/s]
 33%|███▎      | 18992/57600 [3:19:42<6:39:35,  1.61it/s]
 33%|███▎      | 18993/57600 [3:19:42<6:36:23,  1.62it/s]
 33%|███▎      | 18994/57600 [3:19:43<6:37:50,  1.62it/s]
 33%|███▎      | 18995/57600 [3:19:44<6:32:54,  1.64it/s]
 33%|███▎      | 18996/57600 [3:19:44<6:44:31,  1.59it/s]
 33%|███▎      | 18997/57600 [3:19:45<6:49:15,  1.57it/s]
 33%|███▎      | 18998/57600 [3:19:46<6:50:59,  1.57it/s]
 33%|███▎      | 18999/57600 [3:19:46<6:57:13,  1.54it/s]
 33%|███▎      | 19000/57600 [3:19:47<6:49:17,  1.57it/s]
                                                         
{'loss': 1.2557, 'learning_rate': 7.052264808362369e-07, 'epoch': 209.71}

 33%|███▎      | 19000/57600 [3:19:47<6:49:17,  1.57it/s]
 33%|███▎      | 19001/57600 [3:19:48<6:39:46,  1.61it/s]
 33%|███▎      | 19002/57600 [3:19:48<6:39:08,  1.61it/s]
 33%|███▎      | 19003/57600 [3:19:49<6:36:08,  1.62it/s]
 33%|███▎      | 19004/57600 [3:19:49<6:34:42,  1.63it/s]
 33%|███▎      | 19005/57600 [3:19:50<6:43:58,  1.59it/s]
 33%|███▎      | 19006/57600 [3:19:51<6:39:21,  1.61it/s]
 33%|███▎      | 19007/57600 [3:19:51<6:42:59,  1.60it/s]
 33%|███▎      | 19008/57600 [3:19:52<6:34:45,  1.63it/s]
 33%|███▎      | 19009/57600 [3:19:53<6:53:24,  1.56it/s]
 33%|███▎      | 19010/57600 [3:19:53<6:51:21,  1.56it/s]
 33%|███▎      | 19011/57600 [3:19:54<6:48:39,  1.57it/s]
 33%|███▎      | 19012/57600 [3:19:54<6:47:13,  1.58it/s]
 33%|███▎      | 19013/57600 [3:19:55<6:46:24,  1.58it/s]
 33%|███▎      | 19014/57600 [3:19:56<6:45:08,  1.59it/s]
 33%|███▎      | 19015/57600 [3:19:56<6:47:30,  1.58it/s]
 33%|███▎      | 19016/57600 [3:19:57<6:54:44,  1.55it/s]
 33%|███▎      | 19017/57600 [3:19:58<6:38:30,  1.61it/s]
 33%|███▎      | 19018/57600 [3:19:58<6:24:07,  1.67it/s]
 33%|███▎      | 19019/57600 [3:19:59<6:36:30,  1.62it/s]
 33%|███▎      | 19020/57600 [3:19:59<6:35:34,  1.63it/s]
                                                         
{'loss': 1.2544, 'learning_rate': 7.049128919860627e-07, 'epoch': 209.93}

 33%|███▎      | 19020/57600 [3:19:59<6:35:34,  1.63it/s]
 33%|███▎      | 19021/57600 [3:20:00<6:38:48,  1.61it/s]
 33%|███▎      | 19022/57600 [3:20:01<6:41:22,  1.60it/s]
 33%|███▎      | 19023/57600 [3:20:01<6:52:32,  1.56it/s]
 33%|███▎      | 19024/57600 [3:20:02<6:36:14,  1.62it/s]
 33%|███▎      | 19025/57600 [3:20:02<6:27:07,  1.66it/s]
 33%|███▎      | 19026/57600 [3:20:03<6:29:39,  1.65it/s]
 33%|███▎      | 19027/57600 [3:20:04<6:40:34,  1.60it/s]
 33%|███▎      | 19028/57600 [3:20:04<6:31:10,  1.64it/s]
 33%|███▎      | 19029/57600 [3:20:05<6:35:20,  1.63it/s]
 33%|███▎      | 19030/57600 [3:20:06<6:44:08,  1.59it/s]
 33%|███▎      | 19031/57600 [3:20:06<6:33:33,  1.63it/s]
 33%|███▎      | 19032/57600 [3:20:07<6:51:03,  1.56it/s]
 33%|███▎      | 19033/57600 [3:20:07<6:37:16,  1.62it/s]
 33%|███▎      | 19034/57600 [3:20:08<6:33:54,  1.63it/s]
 33%|███▎      | 19035/57600 [3:20:09<6:50:06,  1.57it/s]
 33%|███▎      | 19036/57600 [3:20:09<6:44:35,  1.59it/s]
 33%|███▎      | 19037/57600 [3:20:10<6:39:01,  1.61it/s]
 33%|███▎      | 19038/57600 [3:20:11<6:43:49,  1.59it/s]
 33%|███▎      | 19039/57600 [3:20:11<6:48:27,  1.57it/s]
 33%|███▎      | 19040/57600 [3:20:12<6:38:11,  1.61it/s]
                                                         
{'loss': 1.2361, 'learning_rate': 7.045993031358884e-07, 'epoch': 210.15}

 33%|███▎      | 19040/57600 [3:20:12<6:38:11,  1.61it/s]
 33%|███▎      | 19041/57600 [3:20:12<6:35:48,  1.62it/s]
 33%|███▎      | 19042/57600 [3:20:13<6:45:12,  1.59it/s]
 33%|███▎      | 19043/57600 [3:20:14<6:36:16,  1.62it/s]
 33%|███▎      | 19044/57600 [3:20:14<6:37:49,  1.62it/s]
 33%|███▎      | 19045/57600 [3:20:15<6:39:48,  1.61it/s]
 33%|███▎      | 19046/57600 [3:20:16<6:32:45,  1.64it/s]
 33%|███▎      | 19047/57600 [3:20:16<6:26:37,  1.66it/s]
 33%|███▎      | 19048/57600 [3:20:17<6:25:40,  1.67it/s]
 33%|███▎      | 19049/57600 [3:20:17<6:39:01,  1.61it/s]
 33%|███▎      | 19050/57600 [3:20:18<6:41:46,  1.60it/s]
 33%|███▎      | 19051/57600 [3:20:19<6:48:30,  1.57it/s]
 33%|███▎      | 19052/57600 [3:20:19<6:44:38,  1.59it/s]
 33%|███▎      | 19053/57600 [3:20:20<6:35:32,  1.62it/s]
 33%|███▎      | 19054/57600 [3:20:21<6:40:42,  1.60it/s]
 33%|███▎      | 19055/57600 [3:20:21<6:27:37,  1.66it/s]
 33%|███▎      | 19056/57600 [3:20:22<6:37:35,  1.62it/s]
 33%|███▎      | 19057/57600 [3:20:22<6:33:16,  1.63it/s]
 33%|███▎      | 19058/57600 [3:20:23<6:35:03,  1.63it/s]
 33%|███▎      | 19059/57600 [3:20:24<6:37:06,  1.62it/s]
 33%|███▎      | 19060/57600 [3:20:24<6:33:49,  1.63it/s]
                                                         
{'loss': 1.2912, 'learning_rate': 7.042857142857143e-07, 'epoch': 210.38}

 33%|███▎      | 19060/57600 [3:20:24<6:33:49,  1.63it/s]
 33%|███▎      | 19061/57600 [3:20:25<6:27:14,  1.66it/s]
 33%|███▎      | 19062/57600 [3:20:25<6:23:35,  1.67it/s]
 33%|███▎      | 19063/57600 [3:20:26<6:44:39,  1.59it/s]
 33%|███▎      | 19064/57600 [3:20:27<6:41:49,  1.60it/s]
 33%|███▎      | 19065/57600 [3:20:27<6:36:02,  1.62it/s]
 33%|███▎      | 19066/57600 [3:20:28<6:29:47,  1.65it/s]
 33%|███▎      | 19067/57600 [3:20:29<6:46:03,  1.58it/s]
 33%|███▎      | 19068/57600 [3:20:29<6:36:59,  1.62it/s]
 33%|███▎      | 19069/57600 [3:20:30<6:26:03,  1.66it/s]
 33%|███▎      | 19070/57600 [3:20:30<6:43:59,  1.59it/s]
 33%|███▎      | 19071/57600 [3:20:31<6:51:46,  1.56it/s]
 33%|███▎      | 19072/57600 [3:20:32<6:37:42,  1.61it/s]
 33%|███▎      | 19073/57600 [3:20:32<6:29:34,  1.65it/s]
 33%|███▎      | 19074/57600 [3:20:33<6:25:30,  1.67it/s]
 33%|███▎      | 19075/57600 [3:20:33<6:29:40,  1.65it/s]
 33%|███▎      | 19076/57600 [3:20:34<6:32:11,  1.64it/s]
 33%|███▎      | 19077/57600 [3:20:35<6:30:32,  1.64it/s]
 33%|███▎      | 19078/57600 [3:20:35<6:31:51,  1.64it/s]
 33%|███▎      | 19079/57600 [3:20:36<6:29:31,  1.65it/s]
 33%|███▎      | 19080/57600 [3:20:36<6:33:20,  1.63it/s]
                                                         
{'loss': 1.2768, 'learning_rate': 7.039721254355401e-07, 'epoch': 210.6}

 33%|███▎      | 19080/57600 [3:20:36<6:33:20,  1.63it/s]
 33%|███▎      | 19081/57600 [3:20:37<6:23:24,  1.67it/s]
 33%|███▎      | 19082/57600 [3:20:38<6:53:21,  1.55it/s]
 33%|███▎      | 19083/57600 [3:20:38<6:45:20,  1.58it/s]
 33%|███▎      | 19084/57600 [3:20:39<6:40:23,  1.60it/s]
 33%|███▎      | 19085/57600 [3:20:40<6:34:37,  1.63it/s]
 33%|███▎      | 19086/57600 [3:20:40<6:27:11,  1.66it/s]
 33%|███▎      | 19087/57600 [3:20:41<6:26:08,  1.66it/s]
 33%|███▎      | 19088/57600 [3:20:41<6:20:47,  1.69it/s]
 33%|███▎      | 19089/57600 [3:20:42<6:20:38,  1.69it/s]
 33%|███▎      | 19090/57600 [3:20:42<6:15:48,  1.71it/s]
 33%|███▎      | 19091/57600 [3:20:43<6:14:11,  1.72it/s]
 33%|███▎      | 19092/57600 [3:20:44<6:26:17,  1.66it/s]
 33%|███▎      | 19093/57600 [3:20:44<6:36:40,  1.62it/s]
 33%|███▎      | 19094/57600 [3:20:45<6:42:43,  1.59it/s]
 33%|███▎      | 19095/57600 [3:20:46<6:38:41,  1.61it/s]
 33%|███▎      | 19096/57600 [3:20:46<6:46:50,  1.58it/s]
 33%|███▎      | 19097/57600 [3:20:47<6:32:53,  1.63it/s]
 33%|███▎      | 19098/57600 [3:20:48<6:48:37,  1.57it/s]
 33%|███▎      | 19099/57600 [3:20:48<6:56:33,  1.54it/s]
 33%|███▎      | 19100/57600 [3:20:49<6:48:06,  1.57it/s]
                                                         
{'loss': 1.2375, 'learning_rate': 7.036585365853658e-07, 'epoch': 210.82}

 33%|███▎      | 19100/57600 [3:20:49<6:48:06,  1.57it/s]
 33%|███▎      | 19101/57600 [3:20:49<6:47:57,  1.57it/s]
 33%|███▎      | 19102/57600 [3:20:50<6:35:08,  1.62it/s]
 33%|███▎      | 19103/57600 [3:20:51<6:37:28,  1.61it/s]
 33%|███▎      | 19104/57600 [3:20:51<6:40:13,  1.60it/s]
 33%|███▎      | 19105/57600 [3:20:52<6:38:17,  1.61it/s]
 33%|███▎      | 19106/57600 [3:20:53<6:38:56,  1.61it/s]
 33%|███▎      | 19107/57600 [3:20:53<6:45:21,  1.58it/s]
 33%|███▎      | 19108/57600 [3:20:54<6:46:16,  1.58it/s]
 33%|███▎      | 19109/57600 [3:20:54<6:51:02,  1.56it/s]
 33%|███▎      | 19110/57600 [3:20:55<6:59:44,  1.53it/s]
 33%|███▎      | 19111/57600 [3:20:56<7:02:45,  1.52it/s]
 33%|███▎      | 19112/57600 [3:20:56<6:56:49,  1.54it/s]
 33%|███▎      | 19113/57600 [3:20:57<6:47:18,  1.57it/s]
 33%|███▎      | 19114/57600 [3:20:58<6:41:53,  1.60it/s]
 33%|███▎      | 19115/57600 [3:20:58<6:44:07,  1.59it/s]
 33%|███▎      | 19116/57600 [3:20:59<6:44:09,  1.59it/s]
 33%|███▎      | 19117/57600 [3:21:00<6:53:27,  1.55it/s]
 33%|███▎      | 19118/57600 [3:21:00<6:40:13,  1.60it/s]
 33%|███▎      | 19119/57600 [3:21:01<6:46:15,  1.58it/s]
 33%|███▎      | 19120/57600 [3:21:01<6:41:37,  1.60it/s]
                                                         
{'loss': 1.2215, 'learning_rate': 7.033449477351916e-07, 'epoch': 211.04}

 33%|███▎      | 19120/57600 [3:21:01<6:41:37,  1.60it/s]
 33%|███▎      | 19121/57600 [3:21:02<6:33:45,  1.63it/s]
 33%|███▎      | 19122/57600 [3:21:03<6:30:14,  1.64it/s]
 33%|███▎      | 19123/57600 [3:21:03<6:28:23,  1.65it/s]
 33%|███▎      | 19124/57600 [3:21:04<6:47:29,  1.57it/s]
 33%|███▎      | 19125/57600 [3:21:05<6:41:06,  1.60it/s]
 33%|███▎      | 19126/57600 [3:21:05<6:36:09,  1.62it/s]
 33%|███▎      | 19127/57600 [3:21:06<6:33:42,  1.63it/s]
 33%|███▎      | 19128/57600 [3:21:06<6:22:36,  1.68it/s]
 33%|███▎      | 19129/57600 [3:21:07<6:33:27,  1.63it/s]
 33%|███▎      | 19130/57600 [3:21:08<6:35:26,  1.62it/s]
 33%|███▎      | 19131/57600 [3:21:08<6:41:47,  1.60it/s]
 33%|███▎      | 19132/57600 [3:21:09<6:48:47,  1.57it/s]
 33%|███▎      | 19133/57600 [3:21:09<6:35:12,  1.62it/s]
 33%|███▎      | 19134/57600 [3:21:10<6:27:52,  1.65it/s]
 33%|███▎      | 19135/57600 [3:21:11<6:40:46,  1.60it/s]
 33%|███▎      | 19136/57600 [3:21:11<6:43:20,  1.59it/s]
 33%|███▎      | 19137/57600 [3:21:12<6:46:47,  1.58it/s]
 33%|███▎      | 19138/57600 [3:21:13<6:38:54,  1.61it/s]
 33%|███▎      | 19139/57600 [3:21:13<6:25:48,  1.66it/s]
 33%|███▎      | 19140/57600 [3:21:14<6:23:11,  1.67it/s]
                                                         
{'loss': 1.2571, 'learning_rate': 7.030313588850174e-07, 'epoch': 211.26}

 33%|███▎      | 19140/57600 [3:21:14<6:23:11,  1.67it/s]
 33%|███▎      | 19141/57600 [3:21:14<6:35:42,  1.62it/s]
 33%|███▎      | 19142/57600 [3:21:15<6:34:28,  1.62it/s]
 33%|███▎      | 19143/57600 [3:21:16<6:41:36,  1.60it/s]
 33%|███▎      | 19144/57600 [3:21:16<6:56:13,  1.54it/s]
 33%|███▎      | 19145/57600 [3:21:17<6:51:03,  1.56it/s]
 33%|███▎      | 19146/57600 [3:21:18<6:46:22,  1.58it/s]
 33%|███▎      | 19147/57600 [3:21:18<6:43:51,  1.59it/s]
 33%|███▎      | 19148/57600 [3:21:19<6:48:19,  1.57it/s]
 33%|███▎      | 19149/57600 [3:21:19<6:42:09,  1.59it/s]
 33%|███▎      | 19150/57600 [3:21:20<6:33:51,  1.63it/s]
 33%|███▎      | 19151/57600 [3:21:21<6:29:04,  1.65it/s]
 33%|███▎      | 19152/57600 [3:21:21<6:38:21,  1.61it/s]
 33%|███▎      | 19153/57600 [3:21:22<6:25:43,  1.66it/s]
 33%|███▎      | 19154/57600 [3:21:22<6:25:33,  1.66it/s]
 33%|███▎      | 19155/57600 [3:21:23<6:23:13,  1.67it/s]
 33%|███▎      | 19156/57600 [3:21:24<6:24:24,  1.67it/s]
 33%|███▎      | 19157/57600 [3:21:24<6:28:17,  1.65it/s]
 33%|███▎      | 19158/57600 [3:21:25<6:23:53,  1.67it/s]
 33%|███▎      | 19159/57600 [3:21:26<6:31:38,  1.64it/s]
 33%|███▎      | 19160/57600 [3:21:26<6:43:43,  1.59it/s]
                                                         
{'loss': 1.2415, 'learning_rate': 7.027177700348431e-07, 'epoch': 211.48}

 33%|███▎      | 19160/57600 [3:21:26<6:43:43,  1.59it/s]
 33%|███▎      | 19161/57600 [3:21:27<6:45:02,  1.58it/s]
 33%|███▎      | 19162/57600 [3:21:27<6:36:50,  1.61it/s]
 33%|███▎      | 19163/57600 [3:21:28<6:30:48,  1.64it/s]
 33%|███▎      | 19164/57600 [3:21:29<6:29:04,  1.65it/s]
 33%|███▎      | 19165/57600 [3:21:29<6:34:38,  1.62it/s]
 33%|███▎      | 19166/57600 [3:21:30<6:27:44,  1.65it/s]
 33%|███▎      | 19167/57600 [3:21:30<6:21:54,  1.68it/s]
 33%|███▎      | 19168/57600 [3:21:31<6:21:04,  1.68it/s]
 33%|███▎      | 19169/57600 [3:21:32<6:16:17,  1.70it/s]
 33%|███▎      | 19170/57600 [3:21:32<6:12:27,  1.72it/s]
 33%|███▎      | 19171/57600 [3:21:33<6:23:28,  1.67it/s]
 33%|███▎      | 19172/57600 [3:21:33<6:41:05,  1.60it/s]
 33%|███▎      | 19173/57600 [3:21:34<6:34:10,  1.62it/s]
 33%|███▎      | 19174/57600 [3:21:35<6:28:52,  1.65it/s]
 33%|███▎      | 19175/57600 [3:21:35<6:38:21,  1.61it/s]
 33%|███▎      | 19176/57600 [3:21:36<6:38:48,  1.61it/s]
 33%|███▎      | 19177/57600 [3:21:37<6:38:08,  1.61it/s]
 33%|███▎      | 19178/57600 [3:21:37<6:32:37,  1.63it/s]
 33%|███▎      | 19179/57600 [3:21:38<6:34:37,  1.62it/s]
 33%|███▎      | 19180/57600 [3:21:38<6:50:25,  1.56it/s]
                                                         
{'loss': 1.2412, 'learning_rate': 7.024041811846689e-07, 'epoch': 211.7}

 33%|███▎      | 19180/57600 [3:21:38<6:50:25,  1.56it/s]
 33%|███▎      | 19181/57600 [3:21:39<6:54:52,  1.54it/s]
 33%|███▎      | 19182/57600 [3:21:40<6:48:59,  1.57it/s]
 33%|███▎      | 19183/57600 [3:21:40<7:05:18,  1.51it/s]
 33%|███▎      | 19184/57600 [3:21:41<7:02:57,  1.51it/s]
 33%|███▎      | 19185/57600 [3:21:42<6:45:51,  1.58it/s]
 33%|███▎      | 19186/57600 [3:21:42<6:50:12,  1.56it/s]
 33%|███▎      | 19187/57600 [3:21:43<6:45:57,  1.58it/s]
 33%|███▎      | 19188/57600 [3:21:44<6:57:46,  1.53it/s]
 33%|███▎      | 19189/57600 [3:21:44<6:36:08,  1.62it/s]
 33%|███▎      | 19190/57600 [3:21:45<6:30:42,  1.64it/s]
 33%|███▎      | 19191/57600 [3:21:45<6:36:18,  1.62it/s]
 33%|███▎      | 19192/57600 [3:21:46<6:30:09,  1.64it/s]
 33%|███▎      | 19193/57600 [3:21:47<6:33:25,  1.63it/s]
 33%|███▎      | 19194/57600 [3:21:47<6:31:06,  1.64it/s]
 33%|███▎      | 19195/57600 [3:21:48<6:27:23,  1.65it/s]
 33%|███▎      | 19196/57600 [3:21:48<6:22:25,  1.67it/s]
 33%|███▎      | 19197/57600 [3:21:49<6:18:45,  1.69it/s]
 33%|███▎      | 19198/57600 [3:21:50<6:24:40,  1.66it/s]
 33%|███▎      | 19199/57600 [3:21:50<6:26:47,  1.65it/s]
 33%|███▎      | 19200/57600 [3:21:51<6:21:59,  1.68it/s]
                                                         
{'loss': 1.2865, 'learning_rate': 7.020905923344948e-07, 'epoch': 211.92}

 33%|███▎      | 19200/57600 [3:21:51<6:21:59,  1.68it/s]
 33%|███▎      | 19201/57600 [3:21:51<6:26:07,  1.66it/s]
 33%|███▎      | 19202/57600 [3:21:52<6:43:20,  1.59it/s]
 33%|███▎      | 19203/57600 [3:21:53<6:48:29,  1.57it/s]
 33%|███▎      | 19204/57600 [3:21:53<7:04:17,  1.51it/s]
 33%|███▎      | 19205/57600 [3:21:54<6:49:58,  1.56it/s]
 33%|███▎      | 19206/57600 [3:21:55<6:48:50,  1.57it/s]
 33%|███▎      | 19207/57600 [3:21:55<6:48:30,  1.57it/s]
 33%|███▎      | 19208/57600 [3:21:56<7:00:33,  1.52it/s]
 33%|███▎      | 19209/57600 [3:21:57<6:44:38,  1.58it/s]
 33%|███▎      | 19210/57600 [3:21:57<6:42:32,  1.59it/s]
 33%|███▎      | 19211/57600 [3:21:58<6:37:26,  1.61it/s]
 33%|███▎      | 19212/57600 [3:21:58<6:41:11,  1.59it/s]
 33%|███▎      | 19213/57600 [3:21:59<6:34:23,  1.62it/s]
 33%|███▎      | 19214/57600 [3:22:00<6:33:47,  1.62it/s]
 33%|███▎      | 19215/57600 [3:22:00<6:32:42,  1.63it/s]
 33%|███▎      | 19216/57600 [3:22:01<6:44:18,  1.58it/s]
 33%|███▎      | 19217/57600 [3:22:02<6:37:05,  1.61it/s]
 33%|███▎      | 19218/57600 [3:22:02<6:26:48,  1.65it/s]
 33%|███▎      | 19219/57600 [3:22:03<6:20:49,  1.68it/s]
 33%|███▎      | 19220/57600 [3:22:03<6:08:20,  1.74it/s]
                                                         
{'loss': 1.2568, 'learning_rate': 7.017770034843205e-07, 'epoch': 212.14}

 33%|███▎      | 19220/57600 [3:22:03<6:08:20,  1.74it/s]
 33%|███▎      | 19221/57600 [3:22:04<6:05:21,  1.75it/s]
 33%|███▎      | 19222/57600 [3:22:04<6:12:13,  1.72it/s]
 33%|███▎      | 19223/57600 [3:22:05<6:35:53,  1.62it/s]
 33%|███▎      | 19224/57600 [3:22:06<6:36:42,  1.61it/s]
 33%|███▎      | 19225/57600 [3:22:06<6:34:20,  1.62it/s]
 33%|███▎      | 19226/57600 [3:22:07<6:19:42,  1.68it/s]
 33%|███▎      | 19227/57600 [3:22:07<6:16:33,  1.70it/s]
 33%|███▎      | 19228/57600 [3:22:08<6:16:21,  1.70it/s]
 33%|███▎      | 19229/57600 [3:22:09<6:12:24,  1.72it/s]
 33%|███▎      | 19230/57600 [3:22:09<6:38:21,  1.61it/s]
 33%|███▎      | 19231/57600 [3:22:10<6:47:21,  1.57it/s]
 33%|███▎      | 19232/57600 [3:22:11<6:50:35,  1.56it/s]
 33%|███▎      | 19233/57600 [3:22:11<6:53:23,  1.55it/s]
 33%|███▎      | 19234/57600 [3:22:12<6:50:01,  1.56it/s]
 33%|███▎      | 19235/57600 [3:22:12<6:32:47,  1.63it/s]
 33%|███▎      | 19236/57600 [3:22:13<6:37:10,  1.61it/s]
 33%|███▎      | 19237/57600 [3:22:14<6:28:51,  1.64it/s]
 33%|███▎      | 19238/57600 [3:22:14<6:41:55,  1.59it/s]
 33%|███▎      | 19239/57600 [3:22:15<6:45:29,  1.58it/s]
 33%|███▎      | 19240/57600 [3:22:16<7:03:32,  1.51it/s]
                                                         
{'loss': 1.234, 'learning_rate': 7.014634146341463e-07, 'epoch': 212.36}

 33%|███▎      | 19240/57600 [3:22:16<7:03:32,  1.51it/s]
 33%|███▎      | 19241/57600 [3:22:16<6:56:13,  1.54it/s]
 33%|███▎      | 19242/57600 [3:22:17<6:41:49,  1.59it/s]
 33%|███▎      | 19243/57600 [3:22:18<6:43:28,  1.58it/s]
 33%|███▎      | 19244/57600 [3:22:18<6:34:00,  1.62it/s]
 33%|███▎      | 19245/57600 [3:22:19<6:40:06,  1.60it/s]
 33%|███▎      | 19246/57600 [3:22:19<6:31:36,  1.63it/s]
 33%|███▎      | 19247/57600 [3:22:20<6:30:30,  1.64it/s]
 33%|███▎      | 19248/57600 [3:22:21<6:33:45,  1.62it/s]
 33%|███▎      | 19249/57600 [3:22:21<6:33:17,  1.63it/s]
 33%|███▎      | 19250/57600 [3:22:22<6:55:10,  1.54it/s]
 33%|███▎      | 19251/57600 [3:22:23<6:55:03,  1.54it/s]
 33%|███▎      | 19252/57600 [3:22:23<6:52:29,  1.55it/s]
 33%|███▎      | 19253/57600 [3:22:24<6:43:18,  1.58it/s]
 33%|███▎      | 19254/57600 [3:22:24<6:34:10,  1.62it/s]
 33%|███▎      | 19255/57600 [3:22:25<6:52:11,  1.55it/s]
 33%|███▎      | 19256/57600 [3:22:26<6:37:53,  1.61it/s]
 33%|███▎      | 19257/57600 [3:22:26<6:28:56,  1.64it/s]
 33%|███▎      | 19258/57600 [3:22:27<6:22:08,  1.67it/s]
 33%|███▎      | 19259/57600 [3:22:28<6:28:36,  1.64it/s]
 33%|███▎      | 19260/57600 [3:22:28<6:24:18,  1.66it/s]
                                                         
{'loss': 1.2683, 'learning_rate': 7.01149825783972e-07, 'epoch': 212.58}

 33%|███▎      | 19260/57600 [3:22:28<6:24:18,  1.66it/s]
 33%|███▎      | 19261/57600 [3:22:29<6:33:39,  1.62it/s]
 33%|███▎      | 19262/57600 [3:22:29<6:30:05,  1.64it/s]
 33%|███▎      | 19263/57600 [3:22:30<6:35:25,  1.62it/s]
 33%|███▎      | 19264/57600 [3:22:31<6:37:30,  1.61it/s]
 33%|███▎      | 19265/57600 [3:22:31<6:26:15,  1.65it/s]
 33%|███▎      | 19266/57600 [3:22:32<6:37:35,  1.61it/s]
 33%|███▎      | 19267/57600 [3:22:32<6:30:21,  1.64it/s]
 33%|███▎      | 19268/57600 [3:22:33<6:27:53,  1.65it/s]
 33%|███▎      | 19269/57600 [3:22:34<6:41:29,  1.59it/s]
 33%|███▎      | 19270/57600 [3:22:34<6:30:50,  1.63it/s]
 33%|███▎      | 19271/57600 [3:22:35<6:27:43,  1.65it/s]
 33%|███▎      | 19272/57600 [3:22:35<6:26:24,  1.65it/s]
 33%|███▎      | 19273/57600 [3:22:36<6:34:10,  1.62it/s]
 33%|███▎      | 19274/57600 [3:22:37<6:31:17,  1.63it/s]
 33%|███▎      | 19275/57600 [3:22:37<6:29:40,  1.64it/s]
 33%|███▎      | 19276/57600 [3:22:38<6:31:25,  1.63it/s]
 33%|███▎      | 19277/57600 [3:22:39<6:24:38,  1.66it/s]
 33%|███▎      | 19278/57600 [3:22:39<6:26:01,  1.65it/s]
 33%|███▎      | 19279/57600 [3:22:40<6:21:33,  1.67it/s]
 33%|███▎      | 19280/57600 [3:22:40<6:32:08,  1.63it/s]
                                                         
{'loss': 1.2617, 'learning_rate': 7.008362369337979e-07, 'epoch': 212.8}

 33%|███▎      | 19280/57600 [3:22:40<6:32:08,  1.63it/s]
 33%|███▎      | 19281/57600 [3:22:41<6:33:09,  1.62it/s]
 33%|███▎      | 19282/57600 [3:22:42<6:31:16,  1.63it/s]
 33%|███▎      | 19283/57600 [3:22:42<6:28:42,  1.64it/s]
 33%|███▎      | 19284/57600 [3:22:43<6:34:07,  1.62it/s]
 33%|███▎      | 19285/57600 [3:22:43<6:29:37,  1.64it/s]
 33%|███▎      | 19286/57600 [3:22:44<6:16:40,  1.70it/s]
 33%|███▎      | 19287/57600 [3:22:45<6:26:57,  1.65it/s]
 33%|███▎      | 19288/57600 [3:22:45<6:32:17,  1.63it/s]
 33%|███▎      | 19289/57600 [3:22:46<6:40:11,  1.60it/s]
 33%|███▎      | 19290/57600 [3:22:46<6:33:48,  1.62it/s]
 33%|███▎      | 19291/57600 [3:22:47<6:43:40,  1.58it/s]
 33%|███▎      | 19292/57600 [3:22:48<6:54:25,  1.54it/s]
 33%|███▎      | 19293/57600 [3:22:48<6:37:38,  1.61it/s]
 33%|███▎      | 19294/57600 [3:22:49<6:40:11,  1.60it/s]
 33%|███▎      | 19295/57600 [3:22:50<7:02:37,  1.51it/s]
 34%|███▎      | 19296/57600 [3:22:50<6:55:36,  1.54it/s]
 34%|███▎      | 19297/57600 [3:22:51<6:48:31,  1.56it/s]
 34%|███▎      | 19298/57600 [3:22:52<6:49:26,  1.56it/s]
 34%|███▎      | 19299/57600 [3:22:52<6:55:50,  1.54it/s]
 34%|███▎      | 19300/57600 [3:22:53<6:49:23,  1.56it/s]
                                                         
{'loss': 1.2274, 'learning_rate': 7.005226480836236e-07, 'epoch': 213.02}

 34%|███▎      | 19300/57600 [3:22:53<6:49:23,  1.56it/s]
 34%|███▎      | 19301/57600 [3:22:54<6:49:27,  1.56it/s]
 34%|███▎      | 19302/57600 [3:22:54<6:42:39,  1.59it/s]
 34%|███▎      | 19303/57600 [3:22:55<6:36:52,  1.61it/s]
 34%|███▎      | 19304/57600 [3:22:55<6:43:51,  1.58it/s]
 34%|███▎      | 19305/57600 [3:22:56<6:49:33,  1.56it/s]
 34%|███▎      | 19306/57600 [3:22:57<6:40:44,  1.59it/s]
 34%|███▎      | 19307/57600 [3:22:57<6:53:34,  1.54it/s]
 34%|███▎      | 19308/57600 [3:22:58<6:44:37,  1.58it/s]
 34%|███▎      | 19309/57600 [3:22:59<6:51:13,  1.55it/s]
 34%|███▎      | 19310/57600 [3:22:59<7:01:51,  1.51it/s]
 34%|███▎      | 19311/57600 [3:23:00<6:48:12,  1.56it/s]
 34%|███▎      | 19312/57600 [3:23:01<6:41:37,  1.59it/s]
 34%|███▎      | 19313/57600 [3:23:01<6:41:34,  1.59it/s]
 34%|███▎      | 19314/57600 [3:23:02<6:42:26,  1.59it/s]
 34%|███▎      | 19315/57600 [3:23:02<6:26:17,  1.65it/s]
 34%|███▎      | 19316/57600 [3:23:03<6:20:04,  1.68it/s]
 34%|███▎      | 19317/57600 [3:23:04<6:18:55,  1.68it/s]
 34%|███▎      | 19318/57600 [3:23:04<6:17:13,  1.69it/s]
 34%|███▎      | 19319/57600 [3:23:05<6:28:13,  1.64it/s]
 34%|███▎      | 19320/57600 [3:23:05<6:25:32,  1.65it/s]
                                                         
{'loss': 1.2525, 'learning_rate': 7.002090592334495e-07, 'epoch': 213.25}

 34%|███▎      | 19320/57600 [3:23:05<6:25:32,  1.65it/s]
 34%|███▎      | 19321/57600 [3:23:06<6:31:04,  1.63it/s]
 34%|███▎      | 19322/57600 [3:23:07<6:26:05,  1.65it/s]
 34%|███▎      | 19323/57600 [3:23:07<6:28:30,  1.64it/s]
 34%|███▎      | 19324/57600 [3:23:08<6:31:01,  1.63it/s]
 34%|███▎      | 19325/57600 [3:23:08<6:29:34,  1.64it/s]
 34%|███▎      | 19326/57600 [3:23:09<6:26:25,  1.65it/s]
 34%|███▎      | 19327/57600 [3:23:10<6:35:32,  1.61it/s]
 34%|███▎      | 19328/57600 [3:23:10<6:55:47,  1.53it/s]
 34%|███▎      | 19329/57600 [3:23:11<6:47:54,  1.56it/s]
 34%|███▎      | 19330/57600 [3:23:12<6:40:23,  1.59it/s]
 34%|███▎      | 19331/57600 [3:23:12<6:40:20,  1.59it/s]
 34%|███▎      | 19332/57600 [3:23:13<6:32:25,  1.63it/s]
 34%|███▎      | 19333/57600 [3:23:13<6:29:06,  1.64it/s]
 34%|███▎      | 19334/57600 [3:23:14<6:34:07,  1.62it/s]
 34%|███▎      | 19335/57600 [3:23:15<6:41:20,  1.59it/s]
 34%|███▎      | 19336/57600 [3:23:15<6:28:17,  1.64it/s]
 34%|███▎      | 19337/57600 [3:23:16<6:38:45,  1.60it/s]
 34%|███▎      | 19338/57600 [3:23:17<6:32:49,  1.62it/s]
 34%|███▎      | 19339/57600 [3:23:17<6:39:22,  1.60it/s]
 34%|███▎      | 19340/57600 [3:23:18<6:38:53,  1.60it/s]
                                                         
{'loss': 1.2286, 'learning_rate': 6.998954703832753e-07, 'epoch': 213.47}

 34%|███▎      | 19340/57600 [3:23:18<6:38:53,  1.60it/s]
 34%|███▎      | 19341/57600 [3:23:18<6:30:42,  1.63it/s]
 34%|███▎      | 19342/57600 [3:23:19<6:33:20,  1.62it/s]
 34%|███▎      | 19343/57600 [3:23:20<6:26:59,  1.65it/s]
 34%|███▎      | 19344/57600 [3:23:20<6:24:30,  1.66it/s]
 34%|███▎      | 19345/57600 [3:23:21<6:19:02,  1.68it/s]
 34%|███▎      | 19346/57600 [3:23:22<6:41:38,  1.59it/s]
 34%|███▎      | 19347/57600 [3:23:22<6:39:59,  1.59it/s]
 34%|███▎      | 19348/57600 [3:23:23<6:37:15,  1.60it/s]
 34%|███▎      | 19349/57600 [3:23:23<6:37:20,  1.60it/s]
 34%|███▎      | 19350/57600 [3:23:24<6:35:14,  1.61it/s]
 34%|███▎      | 19351/57600 [3:23:25<6:30:46,  1.63it/s]
 34%|███▎      | 19352/57600 [3:23:25<6:29:01,  1.64it/s]
 34%|███▎      | 19353/57600 [3:23:26<6:36:16,  1.61it/s]
 34%|███▎      | 19354/57600 [3:23:27<6:50:26,  1.55it/s]
 34%|███▎      | 19355/57600 [3:23:27<6:54:30,  1.54it/s]
 34%|███▎      | 19356/57600 [3:23:28<6:52:16,  1.55it/s]
 34%|███▎      | 19357/57600 [3:23:28<6:50:53,  1.55it/s]
 34%|███▎      | 19358/57600 [3:23:29<6:58:31,  1.52it/s]
 34%|███▎      | 19359/57600 [3:23:30<7:00:03,  1.52it/s]
 34%|███▎      | 19360/57600 [3:23:30<6:50:48,  1.55it/s]
                                                         
{'loss': 1.2269, 'learning_rate': 6.99581881533101e-07, 'epoch': 213.69}

 34%|███▎      | 19360/57600 [3:23:30<6:50:48,  1.55it/s]
 34%|███▎      | 19361/57600 [3:23:31<6:56:30,  1.53it/s]
 34%|███▎      | 19362/57600 [3:23:32<6:56:59,  1.53it/s]
 34%|███▎      | 19363/57600 [3:23:32<6:51:42,  1.55it/s]
 34%|███▎      | 19364/57600 [3:23:33<6:35:29,  1.61it/s]
 34%|███▎      | 19365/57600 [3:23:34<6:24:29,  1.66it/s]
 34%|███▎      | 19366/57600 [3:23:34<6:26:33,  1.65it/s]
 34%|███▎      | 19367/57600 [3:23:35<6:21:07,  1.67it/s]
 34%|███▎      | 19368/57600 [3:23:35<6:27:00,  1.65it/s]
 34%|███▎      | 19369/57600 [3:23:36<6:45:13,  1.57it/s]
 34%|███▎      | 19370/57600 [3:23:37<6:46:13,  1.57it/s]
 34%|███▎      | 19371/57600 [3:23:37<6:40:31,  1.59it/s]
 34%|███▎      | 19372/57600 [3:23:38<6:27:54,  1.64it/s]
 34%|███▎      | 19373/57600 [3:23:39<6:41:53,  1.59it/s]
 34%|███▎      | 19374/57600 [3:23:39<6:44:26,  1.58it/s]
 34%|███▎      | 19375/57600 [3:23:40<6:30:42,  1.63it/s]
 34%|███▎      | 19376/57600 [3:23:40<6:32:25,  1.62it/s]
 34%|███▎      | 19377/57600 [3:23:41<6:26:43,  1.65it/s]
 34%|███▎      | 19378/57600 [3:23:42<6:20:51,  1.67it/s]
 34%|███▎      | 19379/57600 [3:23:42<6:24:00,  1.66it/s]
 34%|███▎      | 19380/57600 [3:23:43<6:16:17,  1.69it/s]
                                                         
{'loss': 1.2655, 'learning_rate': 6.992682926829268e-07, 'epoch': 213.91}

 34%|███▎      | 19380/57600 [3:23:43<6:16:17,  1.69it/s]
 34%|███▎      | 19381/57600 [3:23:43<6:13:42,  1.70it/s]
 34%|███▎      | 19382/57600 [3:23:44<6:20:54,  1.67it/s]
 34%|███▎      | 19383/57600 [3:23:45<6:24:36,  1.66it/s]
 34%|███▎      | 19384/57600 [3:23:45<6:21:38,  1.67it/s]
 34%|███▎      | 19385/57600 [3:23:46<6:12:26,  1.71it/s]
 34%|███▎      | 19386/57600 [3:23:46<6:22:06,  1.67it/s]
 34%|███▎      | 19387/57600 [3:23:47<6:27:13,  1.64it/s]
 34%|███▎      | 19388/57600 [3:23:48<6:26:42,  1.65it/s]
 34%|███▎      | 19389/57600 [3:23:48<6:45:55,  1.57it/s]
 34%|███▎      | 19390/57600 [3:23:49<6:45:08,  1.57it/s]
 34%|███▎      | 19391/57600 [3:23:49<6:40:53,  1.59it/s]
 34%|███▎      | 19392/57600 [3:23:50<6:46:30,  1.57it/s]
 34%|███▎      | 19393/57600 [3:23:51<6:46:17,  1.57it/s]
 34%|███▎      | 19394/57600 [3:23:51<6:51:59,  1.55it/s]
 34%|███▎      | 19395/57600 [3:23:52<6:50:22,  1.55it/s]
 34%|███▎      | 19396/57600 [3:23:53<6:43:10,  1.58it/s]
 34%|███▎      | 19397/57600 [3:23:53<6:37:18,  1.60it/s]
 34%|███▎      | 19398/57600 [3:23:54<6:47:11,  1.56it/s]
 34%|███▎      | 19399/57600 [3:23:55<6:45:52,  1.57it/s]
 34%|███▎      | 19400/57600 [3:23:55<6:46:55,  1.56it/s]
                                                         
{'loss': 1.2273, 'learning_rate': 6.989547038327524e-07, 'epoch': 214.13}

 34%|███▎      | 19400/57600 [3:23:55<6:46:55,  1.56it/s]
 34%|███▎      | 19401/57600 [3:23:56<6:43:22,  1.58it/s]
 34%|███▎      | 19402/57600 [3:23:57<6:46:30,  1.57it/s]
 34%|███▎      | 19403/57600 [3:23:57<6:40:02,  1.59it/s]
 34%|███▎      | 19404/57600 [3:23:58<6:42:48,  1.58it/s]
 34%|███▎      | 19405/57600 [3:23:58<6:49:50,  1.55it/s]
 34%|███▎      | 19406/57600 [3:23:59<6:55:21,  1.53it/s]
 34%|███▎      | 19407/57600 [3:24:00<6:44:52,  1.57it/s]
 34%|███▎      | 19408/57600 [3:24:00<6:41:39,  1.58it/s]
 34%|███▎      | 19409/57600 [3:24:01<6:31:50,  1.62it/s]
 34%|███▎      | 19410/57600 [3:24:02<6:53:23,  1.54it/s]
 34%|███▎      | 19411/57600 [3:24:02<6:45:41,  1.57it/s]
 34%|███▎      | 19412/57600 [3:24:03<6:50:36,  1.55it/s]
 34%|███▎      | 19413/57600 [3:24:04<6:48:49,  1.56it/s]
 34%|███▎      | 19414/57600 [3:24:04<6:43:20,  1.58it/s]
 34%|███▎      | 19415/57600 [3:24:05<6:38:37,  1.60it/s]
 34%|███▎      | 19416/57600 [3:24:05<6:31:19,  1.63it/s]
 34%|███▎      | 19417/57600 [3:24:06<6:31:16,  1.63it/s]
 34%|███▎      | 19418/57600 [3:24:07<6:29:13,  1.63it/s]
 34%|███▎      | 19419/57600 [3:24:07<6:39:12,  1.59it/s]
 34%|███▎      | 19420/57600 [3:24:08<6:39:10,  1.59it/s]
                                                         
{'loss': 1.2376, 'learning_rate': 6.986411149825784e-07, 'epoch': 214.35}

 34%|███▎      | 19420/57600 [3:24:08<6:39:10,  1.59it/s]
 34%|███▎      | 19421/57600 [3:24:09<6:44:11,  1.57it/s]
 34%|███▎      | 19422/57600 [3:24:09<6:38:57,  1.59it/s]
 34%|███▎      | 19423/57600 [3:24:10<6:31:45,  1.62it/s]
 34%|███▎      | 19424/57600 [3:24:10<6:44:54,  1.57it/s]
 34%|███▎      | 19425/57600 [3:24:11<6:45:18,  1.57it/s]
 34%|███▎      | 19426/57600 [3:24:12<6:34:57,  1.61it/s]
 34%|███▎      | 19427/57600 [3:24:12<6:32:24,  1.62it/s]
 34%|███▎      | 19428/57600 [3:24:13<6:21:20,  1.67it/s]
 34%|███▎      | 19429/57600 [3:24:13<6:37:39,  1.60it/s]
 34%|███▎      | 19430/57600 [3:24:14<6:37:23,  1.60it/s]
 34%|███▎      | 19431/57600 [3:24:15<6:28:05,  1.64it/s]
 34%|███▎      | 19432/57600 [3:24:15<6:29:28,  1.63it/s]
 34%|███▎      | 19433/57600 [3:24:16<6:34:59,  1.61it/s]
 34%|███▎      | 19434/57600 [3:24:17<6:29:28,  1.63it/s]
 34%|███▎      | 19435/57600 [3:24:17<6:23:09,  1.66it/s]
 34%|███▎      | 19436/57600 [3:24:18<6:22:52,  1.66it/s]
 34%|███▎      | 19437/57600 [3:24:18<6:29:17,  1.63it/s]
 34%|███▎      | 19438/57600 [3:24:19<6:23:58,  1.66it/s]
 34%|███▎      | 19439/57600 [3:24:20<6:36:08,  1.61it/s]
 34%|███▍      | 19440/57600 [3:24:20<6:37:47,  1.60it/s]
                                                         
{'loss': 1.2571, 'learning_rate': 6.983275261324041e-07, 'epoch': 214.57}

 34%|███▍      | 19440/57600 [3:24:20<6:37:47,  1.60it/s]
 34%|███▍      | 19441/57600 [3:24:21<6:42:15,  1.58it/s]
 34%|███▍      | 19442/57600 [3:24:21<6:34:55,  1.61it/s]
 34%|███▍      | 19443/57600 [3:24:22<6:32:38,  1.62it/s]
 34%|███▍      | 19444/57600 [3:24:23<6:25:36,  1.65it/s]
 34%|███▍      | 19445/57600 [3:24:23<6:41:57,  1.58it/s]
 34%|███▍      | 19446/57600 [3:24:24<6:30:05,  1.63it/s]
 34%|███▍      | 19447/57600 [3:24:24<6:19:11,  1.68it/s]
 34%|███▍      | 19448/57600 [3:24:25<6:16:18,  1.69it/s]
 34%|███▍      | 19449/57600 [3:24:26<6:17:37,  1.68it/s]
 34%|███▍      | 19450/57600 [3:24:26<6:19:41,  1.67it/s]
 34%|███▍      | 19451/57600 [3:24:27<6:27:32,  1.64it/s]
 34%|███▍      | 19452/57600 [3:24:28<6:25:53,  1.65it/s]
 34%|███▍      | 19453/57600 [3:24:28<6:30:14,  1.63it/s]
 34%|███▍      | 19454/57600 [3:24:29<6:32:57,  1.62it/s]
 34%|███▍      | 19455/57600 [3:24:29<6:34:04,  1.61it/s]
 34%|███▍      | 19456/57600 [3:24:30<6:35:44,  1.61it/s]
 34%|███▍      | 19457/57600 [3:24:31<6:28:16,  1.64it/s]
 34%|███▍      | 19458/57600 [3:24:31<6:30:15,  1.63it/s]
 34%|███▍      | 19459/57600 [3:24:32<6:28:13,  1.64it/s]
 34%|███▍      | 19460/57600 [3:24:32<6:20:46,  1.67it/s]
                                                         
{'loss': 1.2735, 'learning_rate': 6.9801393728223e-07, 'epoch': 214.79}

 34%|███▍      | 19460/57600 [3:24:32<6:20:46,  1.67it/s]
 34%|███▍      | 19461/57600 [3:24:33<6:13:23,  1.70it/s]
 34%|███▍      | 19462/57600 [3:24:34<6:34:47,  1.61it/s]
 34%|███▍      | 19463/57600 [3:24:34<6:32:52,  1.62it/s]
 34%|███▍      | 19464/57600 [3:24:35<6:31:01,  1.63it/s]
 34%|███▍      | 19465/57600 [3:24:35<6:30:16,  1.63it/s]
 34%|███▍      | 19466/57600 [3:24:36<6:26:13,  1.65it/s]
 34%|███▍      | 19467/57600 [3:24:37<6:18:34,  1.68it/s]
 34%|███▍      | 19468/57600 [3:24:37<6:26:39,  1.64it/s]
 34%|███▍      | 19469/57600 [3:24:38<6:23:17,  1.66it/s]
 34%|███▍      | 19470/57600 [3:24:38<6:12:17,  1.71it/s]
 34%|███▍      | 19471/57600 [3:24:39<6:22:43,  1.66it/s]
 34%|███▍      | 19472/57600 [3:24:40<6:16:19,  1.69it/s]
 34%|███▍      | 19473/57600 [3:24:40<6:24:19,  1.65it/s]
 34%|███▍      | 19474/57600 [3:24:41<6:32:03,  1.62it/s]
 34%|███▍      | 19475/57600 [3:24:41<6:21:37,  1.67it/s]
 34%|███▍      | 19476/57600 [3:24:42<6:28:31,  1.64it/s]
 34%|███▍      | 19477/57600 [3:24:43<6:32:43,  1.62it/s]
 34%|███▍      | 19478/57600 [3:24:43<6:34:56,  1.61it/s]
 34%|███▍      | 19479/57600 [3:24:44<6:31:46,  1.62it/s]
 34%|███▍      | 19480/57600 [3:24:45<6:43:40,  1.57it/s]
                                                         
{'loss': 1.2574, 'learning_rate': 6.977003484320557e-07, 'epoch': 215.01}

 34%|███▍      | 19480/57600 [3:24:45<6:43:40,  1.57it/s]
 34%|███▍      | 19481/57600 [3:24:45<6:46:11,  1.56it/s]
 34%|███▍      | 19482/57600 [3:24:46<6:39:38,  1.59it/s]
 34%|███▍      | 19483/57600 [3:24:47<6:37:26,  1.60it/s]
 34%|███▍      | 19484/57600 [3:24:47<6:43:24,  1.57it/s]
 34%|███▍      | 19485/57600 [3:24:48<6:32:03,  1.62it/s]
 34%|███▍      | 19486/57600 [3:24:48<6:35:15,  1.61it/s]
 34%|███▍      | 19487/57600 [3:24:49<6:48:21,  1.56it/s]
 34%|███▍      | 19488/57600 [3:24:50<6:53:18,  1.54it/s]
 34%|███▍      | 19489/57600 [3:24:50<6:35:59,  1.60it/s]
 34%|███▍      | 19490/57600 [3:24:51<6:37:21,  1.60it/s]
 34%|███▍      | 19491/57600 [3:24:52<6:42:05,  1.58it/s]
 34%|███▍      | 19492/57600 [3:24:52<6:35:27,  1.61it/s]
 34%|███▍      | 19493/57600 [3:24:53<7:00:25,  1.51it/s]
 34%|███▍      | 19494/57600 [3:24:54<6:51:47,  1.54it/s]
 34%|███▍      | 19495/57600 [3:24:54<6:34:03,  1.61it/s]
 34%|███▍      | 19496/57600 [3:24:55<6:42:21,  1.58it/s]
 34%|███▍      | 19497/57600 [3:24:55<6:40:49,  1.58it/s]
 34%|███▍      | 19498/57600 [3:24:56<6:31:36,  1.62it/s]
 34%|███▍      | 19499/57600 [3:24:57<6:28:10,  1.64it/s]
 34%|███▍      | 19500/57600 [3:24:57<6:27:32,  1.64it/s]
                                                         
{'loss': 1.2462, 'learning_rate': 6.973867595818815e-07, 'epoch': 215.23}

 34%|███▍      | 19500/57600 [3:24:57<6:27:32,  1.64it/s]
 34%|███▍      | 19501/57600 [3:24:58<6:32:40,  1.62it/s]
 34%|███▍      | 19502/57600 [3:24:59<6:48:51,  1.55it/s]
 34%|███▍      | 19503/57600 [3:24:59<6:29:59,  1.63it/s]
 34%|███▍      | 19504/57600 [3:25:00<6:27:06,  1.64it/s]
 34%|███▍      | 19505/57600 [3:25:00<6:24:17,  1.65it/s]
 34%|███▍      | 19506/57600 [3:25:01<6:15:39,  1.69it/s]
 34%|███▍      | 19507/57600 [3:25:01<6:24:38,  1.65it/s]
 34%|███▍      | 19508/57600 [3:25:02<6:28:12,  1.64it/s]
 34%|███▍      | 19509/57600 [3:25:03<6:23:53,  1.65it/s]
 34%|███▍      | 19510/57600 [3:25:03<6:22:38,  1.66it/s]
 34%|███▍      | 19511/57600 [3:25:04<6:20:18,  1.67it/s]
 34%|███▍      | 19512/57600 [3:25:04<6:20:17,  1.67it/s]
 34%|███▍      | 19513/57600 [3:25:05<6:34:00,  1.61it/s]
 34%|███▍      | 19514/57600 [3:25:06<6:45:22,  1.57it/s]
 34%|███▍      | 19515/57600 [3:25:07<6:55:19,  1.53it/s]
 34%|███▍      | 19516/57600 [3:25:07<6:48:48,  1.55it/s]
 34%|███▍      | 19517/57600 [3:25:08<6:40:15,  1.59it/s]
 34%|███▍      | 19518/57600 [3:25:08<6:36:40,  1.60it/s]
 34%|███▍      | 19519/57600 [3:25:09<6:39:30,  1.59it/s]
 34%|███▍      | 19520/57600 [3:25:10<6:29:53,  1.63it/s]
                                                         
{'loss': 1.2383, 'learning_rate': 6.970731707317072e-07, 'epoch': 215.45}

 34%|███▍      | 19520/57600 [3:25:10<6:29:53,  1.63it/s]
 34%|███▍      | 19521/57600 [3:25:10<6:36:43,  1.60it/s]
 34%|███▍      | 19522/57600 [3:25:11<6:29:46,  1.63it/s]
 34%|███▍      | 19523/57600 [3:25:11<6:39:07,  1.59it/s]
 34%|███▍      | 19524/57600 [3:25:12<6:35:53,  1.60it/s]
 34%|███▍      | 19525/57600 [3:25:13<6:34:10,  1.61it/s]
 34%|███▍      | 19526/57600 [3:25:13<6:28:40,  1.63it/s]
 34%|███▍      | 19527/57600 [3:25:14<6:25:06,  1.65it/s]
 34%|███▍      | 19528/57600 [3:25:15<6:27:50,  1.64it/s]
 34%|███▍      | 19529/57600 [3:25:15<6:28:57,  1.63it/s]
 34%|███▍      | 19530/57600 [3:25:16<6:21:27,  1.66it/s]
 34%|███▍      | 19531/57600 [3:25:16<6:41:24,  1.58it/s]
 34%|███▍      | 19532/57600 [3:25:17<6:35:33,  1.60it/s]
 34%|███▍      | 19533/57600 [3:25:18<6:28:05,  1.63it/s]
 34%|███▍      | 19534/57600 [3:25:18<6:34:51,  1.61it/s]
 34%|███▍      | 19535/57600 [3:25:19<6:31:23,  1.62it/s]
 34%|███▍      | 19536/57600 [3:25:19<6:27:49,  1.64it/s]
 34%|███▍      | 19537/57600 [3:25:20<6:28:43,  1.63it/s]
 34%|███▍      | 19538/57600 [3:25:21<6:21:16,  1.66it/s]
 34%|███▍      | 19539/57600 [3:25:21<6:19:04,  1.67it/s]
 34%|███▍      | 19540/57600 [3:25:22<6:12:12,  1.70it/s]
                                                         
{'loss': 1.2504, 'learning_rate': 6.967595818815331e-07, 'epoch': 215.67}

 34%|███▍      | 19540/57600 [3:25:22<6:12:12,  1.70it/s]
 34%|███▍      | 19541/57600 [3:25:22<6:23:49,  1.65it/s]
 34%|███▍      | 19542/57600 [3:25:23<6:31:35,  1.62it/s]
 34%|███▍      | 19543/57600 [3:25:24<6:27:12,  1.64it/s]
 34%|███▍      | 19544/57600 [3:25:24<6:29:57,  1.63it/s]
 34%|███▍      | 19545/57600 [3:25:25<6:34:05,  1.61it/s]
 34%|███▍      | 19546/57600 [3:25:26<6:35:21,  1.60it/s]
 34%|███▍      | 19547/57600 [3:25:26<6:44:59,  1.57it/s]
 34%|███▍      | 19548/57600 [3:25:27<6:44:06,  1.57it/s]
 34%|███▍      | 19549/57600 [3:25:28<6:47:45,  1.56it/s]
 34%|███▍      | 19550/57600 [3:25:28<6:49:10,  1.55it/s]
 34%|███▍      | 19551/57600 [3:25:29<6:38:11,  1.59it/s]
 34%|███▍      | 19552/57600 [3:25:29<6:33:00,  1.61it/s]
 34%|███▍      | 19553/57600 [3:25:30<6:40:11,  1.58it/s]
 34%|███▍      | 19554/57600 [3:25:31<6:38:34,  1.59it/s]
 34%|███▍      | 19555/57600 [3:25:31<6:25:02,  1.65it/s]
 34%|███▍      | 19556/57600 [3:25:32<6:22:24,  1.66it/s]
 34%|███▍      | 19557/57600 [3:25:32<6:17:41,  1.68it/s]
 34%|███▍      | 19558/57600 [3:25:33<6:35:18,  1.60it/s]
 34%|███▍      | 19559/57600 [3:25:34<6:23:14,  1.65it/s]
 34%|███▍      | 19560/57600 [3:25:34<6:17:08,  1.68it/s]
                                                         
{'loss': 1.2697, 'learning_rate': 6.964459930313588e-07, 'epoch': 215.89}

 34%|███▍      | 19560/57600 [3:25:34<6:17:08,  1.68it/s]
 34%|███▍      | 19561/57600 [3:25:35<6:13:59,  1.70it/s]
 34%|███▍      | 19562/57600 [3:25:35<6:13:47,  1.70it/s]
 34%|███▍      | 19563/57600 [3:25:36<6:26:18,  1.64it/s]
 34%|███▍      | 19564/57600 [3:25:37<6:36:51,  1.60it/s]
 34%|███▍      | 19565/57600 [3:25:37<6:34:35,  1.61it/s]
 34%|███▍      | 19566/57600 [3:25:38<6:35:32,  1.60it/s]
 34%|███▍      | 19567/57600 [3:25:39<7:08:28,  1.48it/s]
 34%|███▍      | 19568/57600 [3:25:39<6:55:24,  1.53it/s]
 34%|███▍      | 19569/57600 [3:25:40<6:41:14,  1.58it/s]
 34%|███▍      | 19570/57600 [3:25:41<6:58:03,  1.52it/s]
 34%|███▍      | 19571/57600 [3:25:41<6:41:28,  1.58it/s]
 34%|███▍      | 19572/57600 [3:25:42<6:42:40,  1.57it/s]
 34%|███▍      | 19573/57600 [3:25:42<6:31:09,  1.62it/s]
 34%|███▍      | 19574/57600 [3:25:43<6:29:01,  1.63it/s]
 34%|███▍      | 19575/57600 [3:25:44<6:22:54,  1.66it/s]
 34%|███▍      | 19576/57600 [3:25:44<6:34:27,  1.61it/s]
 34%|███▍      | 19577/57600 [3:25:45<6:49:17,  1.55it/s]
 34%|███▍      | 19578/57600 [3:25:46<6:48:17,  1.55it/s]
 34%|███▍      | 19579/57600 [3:25:46<6:37:18,  1.59it/s]
 34%|███▍      | 19580/57600 [3:25:47<6:32:14,  1.62it/s]
                                                         
{'loss': 1.2213, 'learning_rate': 6.961324041811846e-07, 'epoch': 216.11}

 34%|███▍      | 19580/57600 [3:25:47<6:32:14,  1.62it/s]
 34%|███▍      | 19581/57600 [3:25:47<6:35:52,  1.60it/s]
 34%|███▍      | 19582/57600 [3:25:48<6:43:35,  1.57it/s]
 34%|███▍      | 19583/57600 [3:25:49<6:32:19,  1.62it/s]
 34%|███▍      | 19584/57600 [3:25:49<6:29:22,  1.63it/s]
 34%|███▍      | 19585/57600 [3:25:50<6:23:17,  1.65it/s]
 34%|███▍      | 19586/57600 [3:25:51<6:31:17,  1.62it/s]
 34%|███▍      | 19587/57600 [3:25:51<6:32:57,  1.61it/s]
 34%|███▍      | 19588/57600 [3:25:52<6:32:25,  1.61it/s]
 34%|███▍      | 19589/57600 [3:25:52<6:16:38,  1.68it/s]
 34%|███▍      | 19590/57600 [3:25:53<6:11:18,  1.71it/s]
 34%|███▍      | 19591/57600 [3:25:54<6:25:48,  1.64it/s]
 34%|███▍      | 19592/57600 [3:25:54<6:32:29,  1.61it/s]
 34%|███▍      | 19593/57600 [3:25:55<6:26:08,  1.64it/s]
 34%|███▍      | 19594/57600 [3:25:55<6:26:23,  1.64it/s]
 34%|███▍      | 19595/57600 [3:25:56<6:19:08,  1.67it/s]
 34%|███▍      | 19596/57600 [3:25:57<6:57:18,  1.52it/s]
 34%|███▍      | 19597/57600 [3:25:57<6:48:34,  1.55it/s]
 34%|███▍      | 19598/57600 [3:25:58<6:44:22,  1.57it/s]
 34%|███▍      | 19599/57600 [3:25:59<6:47:51,  1.55it/s]
 34%|███▍      | 19600/57600 [3:25:59<6:41:01,  1.58it/s]
                                                         
{'loss': 1.2401, 'learning_rate': 6.958188153310105e-07, 'epoch': 216.34}

 34%|███▍      | 19600/57600 [3:25:59<6:41:01,  1.58it/s]
 34%|███▍      | 19601/57600 [3:26:00<6:44:10,  1.57it/s]
 34%|███▍      | 19602/57600 [3:26:01<6:51:05,  1.54it/s]
 34%|███▍      | 19603/57600 [3:26:01<6:48:18,  1.55it/s]
 34%|███▍      | 19604/57600 [3:26:02<6:37:45,  1.59it/s]
 34%|███▍      | 19605/57600 [3:26:02<6:29:54,  1.62it/s]
 34%|███▍      | 19606/57600 [3:26:03<6:30:44,  1.62it/s]
 34%|███▍      | 19607/57600 [3:26:04<6:22:36,  1.66it/s]
 34%|███▍      | 19608/57600 [3:26:04<6:29:36,  1.63it/s]
 34%|███▍      | 19609/57600 [3:26:05<6:27:54,  1.63it/s]
 34%|███▍      | 19610/57600 [3:26:05<6:33:34,  1.61it/s]
 34%|███▍      | 19611/57600 [3:26:06<6:42:51,  1.57it/s]
 34%|███▍      | 19612/57600 [3:26:07<6:50:45,  1.54it/s]
 34%|███▍      | 19613/57600 [3:26:07<6:38:03,  1.59it/s]
 34%|███▍      | 19614/57600 [3:26:08<6:44:38,  1.56it/s]
 34%|███▍      | 19615/57600 [3:26:09<6:39:17,  1.59it/s]
 34%|███▍      | 19616/57600 [3:26:09<6:30:04,  1.62it/s]
 34%|███▍      | 19617/57600 [3:26:10<6:25:15,  1.64it/s]
 34%|███▍      | 19618/57600 [3:26:10<6:30:22,  1.62it/s]
 34%|███▍      | 19619/57600 [3:26:11<6:23:58,  1.65it/s]
 34%|███▍      | 19620/57600 [3:26:12<6:17:57,  1.67it/s]
                                                         
{'loss': 1.247, 'learning_rate': 6.955052264808362e-07, 'epoch': 216.56}

 34%|███▍      | 19620/57600 [3:26:12<6:17:57,  1.67it/s]
 34%|███▍      | 19621/57600 [3:26:12<6:33:40,  1.61it/s]
 34%|███▍      | 19622/57600 [3:26:13<6:30:24,  1.62it/s]
 34%|███▍      | 19623/57600 [3:26:14<6:38:36,  1.59it/s]
 34%|███▍      | 19624/57600 [3:26:14<6:41:14,  1.58it/s]
 34%|███▍      | 19625/57600 [3:26:15<6:45:28,  1.56it/s]
 34%|███▍      | 19626/57600 [3:26:15<6:41:52,  1.57it/s]
 34%|███▍      | 19627/57600 [3:26:16<6:28:51,  1.63it/s]
 34%|███▍      | 19628/57600 [3:26:17<6:22:48,  1.65it/s]
 34%|███▍      | 19629/57600 [3:26:17<6:30:34,  1.62it/s]
 34%|███▍      | 19630/57600 [3:26:18<6:26:39,  1.64it/s]
 34%|███▍      | 19631/57600 [3:26:18<6:25:15,  1.64it/s]
 34%|███▍      | 19632/57600 [3:26:19<6:28:43,  1.63it/s]
 34%|███▍      | 19633/57600 [3:26:20<6:27:44,  1.63it/s]
 34%|███▍      | 19634/57600 [3:26:20<6:21:50,  1.66it/s]
 34%|███▍      | 19635/57600 [3:26:21<6:21:52,  1.66it/s]
 34%|███▍      | 19636/57600 [3:26:22<6:38:52,  1.59it/s]
 34%|███▍      | 19637/57600 [3:26:22<6:38:38,  1.59it/s]
 34%|███▍      | 19638/57600 [3:26:23<6:39:19,  1.58it/s]
 34%|███▍      | 19639/57600 [3:26:23<6:29:04,  1.63it/s]
 34%|███▍      | 19640/57600 [3:26:24<6:56:27,  1.52it/s]
                                                         
{'loss': 1.2869, 'learning_rate': 6.95191637630662e-07, 'epoch': 216.78}

 34%|███▍      | 19640/57600 [3:26:24<6:56:27,  1.52it/s]
 34%|███▍      | 19641/57600 [3:26:25<6:49:26,  1.55it/s]
 34%|███▍      | 19642/57600 [3:26:25<6:45:07,  1.56it/s]
 34%|███▍      | 19643/57600 [3:26:26<6:35:14,  1.60it/s]
 34%|███▍      | 19644/57600 [3:26:27<6:24:41,  1.64it/s]
 34%|███▍      | 19645/57600 [3:26:27<6:29:54,  1.62it/s]
 34%|███▍      | 19646/57600 [3:26:28<6:29:44,  1.62it/s]
 34%|███▍      | 19647/57600 [3:26:29<6:36:35,  1.59it/s]
 34%|███▍      | 19648/57600 [3:26:29<6:31:20,  1.62it/s]
 34%|███▍      | 19649/57600 [3:26:30<6:21:20,  1.66it/s]
 34%|███▍      | 19650/57600 [3:26:30<6:15:52,  1.68it/s]
 34%|███▍      | 19651/57600 [3:26:31<6:27:27,  1.63it/s]
 34%|███▍      | 19652/57600 [3:26:31<6:21:22,  1.66it/s]
 34%|███▍      | 19653/57600 [3:26:32<6:15:39,  1.68it/s]
 34%|███▍      | 19654/57600 [3:26:33<6:08:02,  1.72it/s]
 34%|███▍      | 19655/57600 [3:26:33<6:26:53,  1.63it/s]
 34%|███▍      | 19656/57600 [3:26:34<6:33:58,  1.61it/s]
 34%|███▍      | 19657/57600 [3:26:35<6:25:01,  1.64it/s]
 34%|███▍      | 19658/57600 [3:26:35<6:24:25,  1.64it/s]
 34%|███▍      | 19659/57600 [3:26:36<6:27:37,  1.63it/s]
 34%|███▍      | 19660/57600 [3:26:36<6:18:09,  1.67it/s]
                                                         
{'loss': 1.3116, 'learning_rate': 6.948780487804877e-07, 'epoch': 217.0}

 34%|███▍      | 19660/57600 [3:26:36<6:18:09,  1.67it/s]
 34%|███▍      | 19661/57600 [3:26:37<6:28:49,  1.63it/s]
 34%|███▍      | 19662/57600 [3:26:38<6:42:01,  1.57it/s]
 34%|███▍      | 19663/57600 [3:26:38<6:40:35,  1.58it/s]
 34%|███▍      | 19664/57600 [3:26:39<6:29:40,  1.62it/s]
 34%|███▍      | 19665/57600 [3:26:39<6:29:51,  1.62it/s]
 34%|███▍      | 19666/57600 [3:26:40<6:20:25,  1.66it/s]
 34%|███▍      | 19667/57600 [3:26:41<6:23:35,  1.65it/s]
 34%|███▍      | 19668/57600 [3:26:41<6:18:00,  1.67it/s]
 34%|███▍      | 19669/57600 [3:26:42<6:39:30,  1.58it/s]
 34%|███▍      | 19670/57600 [3:26:42<6:22:26,  1.65it/s]
 34%|███▍      | 19671/57600 [3:26:43<6:34:40,  1.60it/s]
 34%|███▍      | 19672/57600 [3:26:44<6:26:21,  1.64it/s]
 34%|███▍      | 19673/57600 [3:26:44<6:21:35,  1.66it/s]
 34%|███▍      | 19674/57600 [3:26:45<6:29:36,  1.62it/s]
 34%|███▍      | 19675/57600 [3:26:46<6:22:05,  1.65it/s]
 34%|███▍      | 19676/57600 [3:26:46<6:27:09,  1.63it/s]
 34%|███▍      | 19677/57600 [3:26:47<6:41:56,  1.57it/s]
 34%|███▍      | 19678/57600 [3:26:47<6:33:58,  1.60it/s]
 34%|███▍      | 19679/57600 [3:26:48<6:27:27,  1.63it/s]
 34%|███▍      | 19680/57600 [3:26:49<6:19:22,  1.67it/s]
                                                         
{'loss': 1.2763, 'learning_rate': 6.945644599303137e-07, 'epoch': 217.22}

 34%|███▍      | 19680/57600 [3:26:49<6:19:22,  1.67it/s]
 34%|███▍      | 19681/57600 [3:26:49<6:17:02,  1.68it/s]
 34%|███▍      | 19682/57600 [3:26:50<6:21:10,  1.66it/s]
 34%|███▍      | 19683/57600 [3:26:51<6:39:53,  1.58it/s]
 34%|███▍      | 19684/57600 [3:26:51<6:37:46,  1.59it/s]
 34%|███▍      | 19685/57600 [3:26:52<6:46:27,  1.55it/s]
 34%|███▍      | 19686/57600 [3:26:52<6:46:37,  1.55it/s]
 34%|███▍      | 19687/57600 [3:26:53<6:45:48,  1.56it/s]
 34%|███▍      | 19688/57600 [3:26:54<6:35:06,  1.60it/s]
 34%|███▍      | 19689/57600 [3:26:54<6:37:21,  1.59it/s]
 34%|███▍      | 19690/57600 [3:26:55<6:31:53,  1.61it/s]
 34%|███▍      | 19691/57600 [3:26:56<6:26:29,  1.63it/s]
 34%|███▍      | 19692/57600 [3:26:56<6:27:53,  1.63it/s]
 34%|███▍      | 19693/57600 [3:26:57<6:44:25,  1.56it/s]
 34%|███▍      | 19694/57600 [3:26:58<6:56:07,  1.52it/s]
 34%|███▍      | 19695/57600 [3:26:58<6:46:28,  1.55it/s]
 34%|███▍      | 19696/57600 [3:26:59<6:50:12,  1.54it/s]
 34%|███▍      | 19697/57600 [3:26:59<6:33:57,  1.60it/s]
 34%|███▍      | 19698/57600 [3:27:00<6:46:05,  1.56it/s]
 34%|███▍      | 19699/57600 [3:27:01<6:38:32,  1.58it/s]
 34%|███▍      | 19700/57600 [3:27:01<6:34:45,  1.60it/s]
                                                         
{'loss': 1.2473, 'learning_rate': 6.942508710801393e-07, 'epoch': 217.44}

 34%|███▍      | 19700/57600 [3:27:01<6:34:45,  1.60it/s]
 34%|███▍      | 19701/57600 [3:27:02<6:23:05,  1.65it/s]
 34%|███▍      | 19702/57600 [3:27:02<6:28:25,  1.63it/s]
 34%|███▍      | 19703/57600 [3:27:03<6:23:31,  1.65it/s]
 34%|███▍      | 19704/57600 [3:27:04<6:20:02,  1.66it/s]
 34%|███▍      | 19705/57600 [3:27:04<6:12:39,  1.69it/s]
 34%|███▍      | 19706/57600 [3:27:05<6:05:49,  1.73it/s]
 34%|███▍      | 19707/57600 [3:27:05<6:08:26,  1.71it/s]
 34%|███▍      | 19708/57600 [3:27:06<6:08:49,  1.71it/s]
 34%|███▍      | 19709/57600 [3:27:07<6:13:28,  1.69it/s]
 34%|███▍      | 19710/57600 [3:27:07<6:13:43,  1.69it/s]
 34%|███▍      | 19711/57600 [3:27:08<6:15:31,  1.68it/s]
 34%|███▍      | 19712/57600 [3:27:08<6:18:42,  1.67it/s]
 34%|███▍      | 19713/57600 [3:27:09<6:16:15,  1.68it/s]
 34%|███▍      | 19714/57600 [3:27:10<6:20:32,  1.66it/s]
 34%|███▍      | 19715/57600 [3:27:10<6:14:16,  1.69it/s]
 34%|███▍      | 19716/57600 [3:27:11<6:17:15,  1.67it/s]
 34%|███▍      | 19717/57600 [3:27:11<6:25:53,  1.64it/s]
 34%|███▍      | 19718/57600 [3:27:12<6:33:29,  1.60it/s]
 34%|███▍      | 19719/57600 [3:27:13<6:30:48,  1.62it/s]
 34%|███▍      | 19720/57600 [3:27:13<6:30:49,  1.62it/s]
                                                         
{'loss': 1.2393, 'learning_rate': 6.939372822299651e-07, 'epoch': 217.66}

 34%|███▍      | 19720/57600 [3:27:13<6:30:49,  1.62it/s]
 34%|███▍      | 19721/57600 [3:27:14<6:38:12,  1.59it/s]
 34%|███▍      | 19722/57600 [3:27:15<6:41:07,  1.57it/s]
 34%|███▍      | 19723/57600 [3:27:15<6:30:10,  1.62it/s]
 34%|███▍      | 19724/57600 [3:27:16<6:23:33,  1.65it/s]
 34%|███▍      | 19725/57600 [3:27:16<6:28:51,  1.62it/s]
 34%|███▍      | 19726/57600 [3:27:17<6:25:59,  1.64it/s]
 34%|███▍      | 19727/57600 [3:27:18<6:38:19,  1.58it/s]
 34%|███▍      | 19728/57600 [3:27:18<6:47:22,  1.55it/s]
 34%|███▍      | 19729/57600 [3:27:19<6:36:39,  1.59it/s]
 34%|███▍      | 19730/57600 [3:27:20<6:37:07,  1.59it/s]
 34%|███▍      | 19731/57600 [3:27:20<6:29:35,  1.62it/s]
 34%|███▍      | 19732/57600 [3:27:21<6:36:37,  1.59it/s]
 34%|███▍      | 19733/57600 [3:27:21<6:50:32,  1.54it/s]
 34%|███▍      | 19734/57600 [3:27:22<6:52:30,  1.53it/s]
 34%|███▍      | 19735/57600 [3:27:23<6:33:21,  1.60it/s]
 34%|███▍      | 19736/57600 [3:27:23<6:45:24,  1.56it/s]
 34%|███▍      | 19737/57600 [3:27:24<6:46:34,  1.55it/s]
 34%|███▍      | 19738/57600 [3:27:25<6:31:58,  1.61it/s]
 34%|███▍      | 19739/57600 [3:27:25<6:27:41,  1.63it/s]
 34%|███▍      | 19740/57600 [3:27:26<6:31:29,  1.61it/s]
                                                         
{'loss': 1.2357, 'learning_rate': 6.936236933797909e-07, 'epoch': 217.88}

 34%|███▍      | 19740/57600 [3:27:26<6:31:29,  1.61it/s]
 34%|███▍      | 19741/57600 [3:27:26<6:23:01,  1.65it/s]
 34%|███▍      | 19742/57600 [3:27:27<6:31:58,  1.61it/s]
 34%|███▍      | 19743/57600 [3:27:28<6:47:27,  1.55it/s]
 34%|███▍      | 19744/57600 [3:27:28<6:40:59,  1.57it/s]
 34%|███▍      | 19745/57600 [3:27:29<6:38:12,  1.58it/s]
 34%|███▍      | 19746/57600 [3:27:30<6:29:52,  1.62it/s]
 34%|███▍      | 19747/57600 [3:27:30<6:38:50,  1.58it/s]
 34%|███▍      | 19748/57600 [3:27:31<6:34:41,  1.60it/s]
 34%|███▍      | 19749/57600 [3:27:31<6:33:41,  1.60it/s]
 34%|███▍      | 19750/57600 [3:27:32<6:29:11,  1.62it/s]
 34%|███▍      | 19751/57600 [3:27:33<6:32:27,  1.61it/s]
 34%|███▍      | 19752/57600 [3:27:33<6:46:43,  1.55it/s]
 34%|███▍      | 19753/57600 [3:27:34<6:40:59,  1.57it/s]
 34%|███▍      | 19754/57600 [3:27:35<6:35:28,  1.59it/s]
 34%|███▍      | 19755/57600 [3:27:35<6:31:34,  1.61it/s]
 34%|███▍      | 19756/57600 [3:27:36<6:30:59,  1.61it/s]
 34%|███▍      | 19757/57600 [3:27:37<6:36:37,  1.59it/s]
 34%|███▍      | 19758/57600 [3:27:37<6:37:21,  1.59it/s]
 34%|███▍      | 19759/57600 [3:27:38<6:23:02,  1.65it/s]
 34%|███▍      | 19760/57600 [3:27:38<6:16:37,  1.67it/s]
                                                         
{'loss': 1.2495, 'learning_rate': 6.933101045296168e-07, 'epoch': 218.1}

 34%|███▍      | 19760/57600 [3:27:38<6:16:37,  1.67it/s]
 34%|███▍      | 19761/57600 [3:27:39<6:30:22,  1.62it/s]
 34%|███▍      | 19762/57600 [3:27:40<6:32:55,  1.60it/s]
 34%|███▍      | 19763/57600 [3:27:40<6:29:33,  1.62it/s]
 34%|███▍      | 19764/57600 [3:27:41<6:37:15,  1.59it/s]
 34%|███▍      | 19765/57600 [3:27:41<6:27:42,  1.63it/s]
 34%|███▍      | 19766/57600 [3:27:42<6:24:39,  1.64it/s]
 34%|███▍      | 19767/57600 [3:27:43<6:20:31,  1.66it/s]
 34%|███▍      | 19768/57600 [3:27:43<6:40:39,  1.57it/s]
 34%|███▍      | 19769/57600 [3:27:44<6:33:10,  1.60it/s]
 34%|███▍      | 19770/57600 [3:27:45<6:39:59,  1.58it/s]
 34%|███▍      | 19771/57600 [3:27:45<6:33:15,  1.60it/s]
 34%|███▍      | 19772/57600 [3:27:46<6:31:08,  1.61it/s]
 34%|███▍      | 19773/57600 [3:27:46<6:36:23,  1.59it/s]
 34%|███▍      | 19774/57600 [3:27:47<6:35:44,  1.59it/s]
 34%|███▍      | 19775/57600 [3:27:48<6:33:16,  1.60it/s]
 34%|███▍      | 19776/57600 [3:27:48<6:38:42,  1.58it/s]
 34%|███▍      | 19777/57600 [3:27:49<6:41:25,  1.57it/s]
 34%|███▍      | 19778/57600 [3:27:50<6:37:06,  1.59it/s]
 34%|███▍      | 19779/57600 [3:27:50<6:29:49,  1.62it/s]
 34%|███▍      | 19780/57600 [3:27:51<6:36:10,  1.59it/s]
                                                         
{'loss': 1.2524, 'learning_rate': 6.929965156794424e-07, 'epoch': 218.32}

 34%|███▍      | 19780/57600 [3:27:51<6:36:10,  1.59it/s]
 34%|███▍      | 19781/57600 [3:27:51<6:35:41,  1.59it/s]
 34%|███▍      | 19782/57600 [3:27:52<6:30:06,  1.62it/s]
 34%|███▍      | 19783/57600 [3:27:53<6:34:42,  1.60it/s]
 34%|███▍      | 19784/57600 [3:27:53<6:32:41,  1.61it/s]
 34%|███▍      | 19785/57600 [3:27:54<6:34:16,  1.60it/s]
 34%|███▍      | 19786/57600 [3:27:55<6:35:21,  1.59it/s]
 34%|███▍      | 19787/57600 [3:27:55<6:21:38,  1.65it/s]
 34%|███▍      | 19788/57600 [3:27:56<6:16:11,  1.68it/s]
 34%|███▍      | 19789/57600 [3:27:56<6:17:24,  1.67it/s]
 34%|███▍      | 19790/57600 [3:27:57<6:19:14,  1.66it/s]
 34%|███▍      | 19791/57600 [3:27:58<6:28:05,  1.62it/s]
 34%|███▍      | 19792/57600 [3:27:58<6:42:30,  1.57it/s]
 34%|███▍      | 19793/57600 [3:27:59<6:29:15,  1.62it/s]
 34%|███▍      | 19794/57600 [3:27:59<6:37:21,  1.59it/s]
 34%|███▍      | 19795/57600 [3:28:00<6:22:34,  1.65it/s]
 34%|███▍      | 19796/57600 [3:28:01<6:16:09,  1.68it/s]
 34%|███▍      | 19797/57600 [3:28:01<6:16:41,  1.67it/s]
 34%|███▍      | 19798/57600 [3:28:02<6:25:57,  1.63it/s]
 34%|███▍      | 19799/57600 [3:28:02<6:22:38,  1.65it/s]
 34%|███▍      | 19800/57600 [3:28:03<6:24:07,  1.64it/s]
                                                         
{'loss': 1.2583, 'learning_rate': 6.926829268292682e-07, 'epoch': 218.54}

 34%|███▍      | 19800/57600 [3:28:03<6:24:07,  1.64it/s]
 34%|███▍      | 19801/57600 [3:28:04<6:37:40,  1.58it/s]
 34%|███▍      | 19802/57600 [3:28:04<6:39:51,  1.58it/s]
 34%|███▍      | 19803/57600 [3:28:05<6:30:16,  1.61it/s]
 34%|███▍      | 19804/57600 [3:28:06<6:29:40,  1.62it/s]
 34%|███▍      | 19805/57600 [3:28:06<6:32:41,  1.60it/s]
 34%|███▍      | 19806/57600 [3:28:07<6:38:37,  1.58it/s]
 34%|███▍      | 19807/57600 [3:28:08<6:36:16,  1.59it/s]
 34%|███▍      | 19808/57600 [3:28:08<6:35:32,  1.59it/s]
 34%|███▍      | 19809/57600 [3:28:09<6:30:19,  1.61it/s]
 34%|███▍      | 19810/57600 [3:28:09<6:30:30,  1.61it/s]
 34%|███▍      | 19811/57600 [3:28:10<6:24:40,  1.64it/s]
 34%|███▍      | 19812/57600 [3:28:11<6:27:25,  1.63it/s]
 34%|███▍      | 19813/57600 [3:28:11<6:28:01,  1.62it/s]
 34%|███▍      | 19814/57600 [3:28:12<6:41:15,  1.57it/s]
 34%|███▍      | 19815/57600 [3:28:12<6:27:06,  1.63it/s]
 34%|███▍      | 19816/57600 [3:28:13<6:17:52,  1.67it/s]
 34%|███▍      | 19817/57600 [3:28:14<6:20:12,  1.66it/s]
 34%|███▍      | 19818/57600 [3:28:14<6:13:56,  1.68it/s]
 34%|███▍      | 19819/57600 [3:28:15<6:18:36,  1.66it/s]
 34%|███▍      | 19820/57600 [3:28:15<6:17:16,  1.67it/s]
                                                         
{'loss': 1.2818, 'learning_rate': 6.923693379790941e-07, 'epoch': 218.76}

 34%|███▍      | 19820/57600 [3:28:15<6:17:16,  1.67it/s]
 34%|███▍      | 19821/57600 [3:28:16<6:23:25,  1.64it/s]
 34%|███▍      | 19822/57600 [3:28:17<6:19:45,  1.66it/s]
 34%|███▍      | 19823/57600 [3:28:17<6:27:23,  1.63it/s]
 34%|███▍      | 19824/57600 [3:28:18<6:17:05,  1.67it/s]
 34%|███▍      | 19825/57600 [3:28:18<6:13:07,  1.69it/s]
 34%|███▍      | 19826/57600 [3:28:19<6:23:57,  1.64it/s]
 34%|███▍      | 19827/57600 [3:28:20<6:25:46,  1.63it/s]
 34%|███▍      | 19828/57600 [3:28:20<6:27:03,  1.63it/s]
 34%|███▍      | 19829/57600 [3:28:21<6:31:18,  1.61it/s]
 34%|███▍      | 19830/57600 [3:28:22<6:22:13,  1.65it/s]
 34%|███▍      | 19831/57600 [3:28:22<6:11:36,  1.69it/s]
 34%|███▍      | 19832/57600 [3:28:23<6:19:33,  1.66it/s]
 34%|███▍      | 19833/57600 [3:28:23<6:26:19,  1.63it/s]
 34%|███▍      | 19834/57600 [3:28:24<6:51:39,  1.53it/s]
 34%|███▍      | 19835/57600 [3:28:25<6:51:08,  1.53it/s]
 34%|███▍      | 19836/57600 [3:28:25<6:51:13,  1.53it/s]
 34%|███▍      | 19837/57600 [3:28:26<6:44:37,  1.56it/s]
 34%|███▍      | 19838/57600 [3:28:27<6:35:18,  1.59it/s]
 34%|███▍      | 19839/57600 [3:28:27<6:28:30,  1.62it/s]
 34%|███▍      | 19840/57600 [3:28:28<6:27:45,  1.62it/s]
                                                         
{'loss': 1.2079, 'learning_rate': 6.920557491289198e-07, 'epoch': 218.98}

 34%|███▍      | 19840/57600 [3:28:28<6:27:45,  1.62it/s]
 34%|███▍      | 19841/57600 [3:28:28<6:28:47,  1.62it/s]
 34%|███▍      | 19842/57600 [3:28:29<6:47:14,  1.55it/s]
 34%|███▍      | 19843/57600 [3:28:30<6:32:54,  1.60it/s]
 34%|███▍      | 19844/57600 [3:28:30<6:30:01,  1.61it/s]
 34%|███▍      | 19845/57600 [3:28:31<6:35:32,  1.59it/s]
 34%|███▍      | 19846/57600 [3:28:32<6:33:50,  1.60it/s]
 34%|███▍      | 19847/57600 [3:28:32<6:32:21,  1.60it/s]
 34%|███▍      | 19848/57600 [3:28:33<6:14:51,  1.68it/s]
 34%|███▍      | 19849/57600 [3:28:33<6:13:04,  1.69it/s]
 34%|███▍      | 19850/57600 [3:28:34<6:14:04,  1.68it/s]
 34%|███▍      | 19851/57600 [3:28:35<6:23:53,  1.64it/s]
 34%|███▍      | 19852/57600 [3:28:35<6:30:13,  1.61it/s]
 34%|███▍      | 19853/57600 [3:28:36<6:45:41,  1.55it/s]
 34%|███▍      | 19854/57600 [3:28:37<6:38:42,  1.58it/s]
 34%|███▍      | 19855/57600 [3:28:37<6:37:13,  1.58it/s]
 34%|███▍      | 19856/57600 [3:28:38<6:23:06,  1.64it/s]
 34%|███▍      | 19857/57600 [3:28:38<6:11:31,  1.69it/s]
 34%|███▍      | 19858/57600 [3:28:39<6:13:33,  1.68it/s]
 34%|███▍      | 19859/57600 [3:28:39<6:07:46,  1.71it/s]
 34%|███▍      | 19860/57600 [3:28:40<6:08:19,  1.71it/s]
                                                         
{'loss': 1.2712, 'learning_rate': 6.917421602787455e-07, 'epoch': 219.21}

 34%|███▍      | 19860/57600 [3:28:40<6:08:19,  1.71it/s]
 34%|███▍      | 19861/57600 [3:28:41<6:32:02,  1.60it/s]
 34%|███▍      | 19862/57600 [3:28:41<6:28:28,  1.62it/s]
 34%|███▍      | 19863/57600 [3:28:42<6:24:26,  1.64it/s]
 34%|███▍      | 19864/57600 [3:28:43<6:23:58,  1.64it/s]
 34%|███▍      | 19865/57600 [3:28:43<6:22:29,  1.64it/s]
 34%|███▍      | 19866/57600 [3:28:44<6:27:23,  1.62it/s]
 34%|███▍      | 19867/57600 [3:28:44<6:25:37,  1.63it/s]
 34%|███▍      | 19868/57600 [3:28:45<6:19:59,  1.65it/s]
 34%|███▍      | 19869/57600 [3:28:46<6:30:20,  1.61it/s]
 34%|███▍      | 19870/57600 [3:28:46<6:29:10,  1.62it/s]
 34%|███▍      | 19871/57600 [3:28:47<6:34:48,  1.59it/s]
 34%|███▍      | 19872/57600 [3:28:48<6:35:15,  1.59it/s]
 35%|███▍      | 19873/57600 [3:28:48<6:22:19,  1.64it/s]
 35%|███▍      | 19874/57600 [3:28:49<6:09:18,  1.70it/s]
 35%|███▍      | 19875/57600 [3:28:49<6:18:05,  1.66it/s]
 35%|███▍      | 19876/57600 [3:28:50<6:20:00,  1.65it/s]
 35%|███▍      | 19877/57600 [3:28:50<6:16:35,  1.67it/s]
 35%|███▍      | 19878/57600 [3:28:51<6:18:40,  1.66it/s]
 35%|███▍      | 19879/57600 [3:28:52<6:21:02,  1.65it/s]
 35%|███▍      | 19880/57600 [3:28:52<6:39:35,  1.57it/s]
                                                         
{'loss': 1.2168, 'learning_rate': 6.914285714285714e-07, 'epoch': 219.43}

 35%|███▍      | 19880/57600 [3:28:52<6:39:35,  1.57it/s]
 35%|███▍      | 19881/57600 [3:28:53<6:35:51,  1.59it/s]
 35%|███▍      | 19882/57600 [3:28:54<6:38:29,  1.58it/s]
 35%|███▍      | 19883/57600 [3:28:54<6:34:33,  1.59it/s]
 35%|███▍      | 19884/57600 [3:28:55<6:24:34,  1.63it/s]
 35%|███▍      | 19885/57600 [3:28:55<6:38:19,  1.58it/s]
 35%|███▍      | 19886/57600 [3:28:56<6:42:18,  1.56it/s]
 35%|███▍      | 19887/57600 [3:28:57<6:48:42,  1.54it/s]
 35%|███▍      | 19888/57600 [3:28:57<6:42:35,  1.56it/s]
 35%|███▍      | 19889/57600 [3:28:58<6:35:32,  1.59it/s]
 35%|███▍      | 19890/57600 [3:28:59<6:24:41,  1.63it/s]
 35%|███▍      | 19891/57600 [3:28:59<6:23:53,  1.64it/s]
 35%|███▍      | 19892/57600 [3:29:00<6:30:26,  1.61it/s]
 35%|███▍      | 19893/57600 [3:29:00<6:21:08,  1.65it/s]
 35%|███▍      | 19894/57600 [3:29:01<6:14:20,  1.68it/s]
 35%|███▍      | 19895/57600 [3:29:02<6:23:25,  1.64it/s]
 35%|███▍      | 19896/57600 [3:29:02<6:19:33,  1.66it/s]
 35%|███▍      | 19897/57600 [3:29:03<6:33:42,  1.60it/s]
 35%|███▍      | 19898/57600 [3:29:04<6:31:43,  1.60it/s]
 35%|███▍      | 19899/57600 [3:29:04<6:20:58,  1.65it/s]
 35%|███▍      | 19900/57600 [3:29:05<6:22:24,  1.64it/s]
                                                         
{'loss': 1.2321, 'learning_rate': 6.911149825783973e-07, 'epoch': 219.65}

 35%|███▍      | 19900/57600 [3:29:05<6:22:24,  1.64it/s]
 35%|███▍      | 19901/57600 [3:29:05<6:34:48,  1.59it/s]
 35%|███▍      | 19902/57600 [3:29:06<6:47:10,  1.54it/s]
 35%|███▍      | 19903/57600 [3:29:07<6:34:10,  1.59it/s]
 35%|███▍      | 19904/57600 [3:29:07<6:41:16,  1.57it/s]
 35%|███▍      | 19905/57600 [3:29:08<6:32:30,  1.60it/s]
 35%|███▍      | 19906/57600 [3:29:09<6:28:11,  1.62it/s]
 35%|███▍      | 19907/57600 [3:29:09<6:33:38,  1.60it/s]
 35%|███▍      | 19908/57600 [3:29:10<6:40:21,  1.57it/s]
 35%|███▍      | 19909/57600 [3:29:11<6:45:23,  1.55it/s]
 35%|███▍      | 19910/57600 [3:29:11<6:48:42,  1.54it/s]
 35%|███▍      | 19911/57600 [3:29:12<7:06:12,  1.47it/s]
 35%|███▍      | 19912/57600 [3:29:13<6:51:08,  1.53it/s]
 35%|███▍      | 19913/57600 [3:29:13<6:41:48,  1.56it/s]
 35%|███▍      | 19914/57600 [3:29:14<6:41:16,  1.57it/s]
 35%|███▍      | 19915/57600 [3:29:14<6:38:15,  1.58it/s]
 35%|███▍      | 19916/57600 [3:29:15<6:31:58,  1.60it/s]
 35%|███▍      | 19917/57600 [3:29:16<6:25:05,  1.63it/s]
 35%|███▍      | 19918/57600 [3:29:16<6:22:02,  1.64it/s]
 35%|███▍      | 19919/57600 [3:29:17<6:16:22,  1.67it/s]
 35%|███▍      | 19920/57600 [3:29:17<6:10:58,  1.69it/s]
                                                         
{'loss': 1.2472, 'learning_rate': 6.908013937282229e-07, 'epoch': 219.87}

 35%|███▍      | 19920/57600 [3:29:17<6:10:58,  1.69it/s]
 35%|███▍      | 19921/57600 [3:29:18<6:20:40,  1.65it/s]
 35%|███▍      | 19922/57600 [3:29:19<6:26:35,  1.62it/s]
 35%|███▍      | 19923/57600 [3:29:19<6:22:09,  1.64it/s]
 35%|███▍      | 19924/57600 [3:29:20<6:21:53,  1.64it/s]
 35%|███▍      | 19925/57600 [3:29:20<6:26:39,  1.62it/s]
 35%|███▍      | 19926/57600 [3:29:21<6:27:55,  1.62it/s]
 35%|███▍      | 19927/57600 [3:29:22<6:23:30,  1.64it/s]
 35%|███▍      | 19928/57600 [3:29:22<6:27:26,  1.62it/s]
 35%|███▍      | 19929/57600 [3:29:23<6:39:52,  1.57it/s]
 35%|███▍      | 19930/57600 [3:29:24<6:31:31,  1.60it/s]
 35%|███▍      | 19931/57600 [3:29:24<6:31:36,  1.60it/s]
 35%|███▍      | 19932/57600 [3:29:25<6:34:57,  1.59it/s]
 35%|███▍      | 19933/57600 [3:29:25<6:39:03,  1.57it/s]
 35%|███▍      | 19934/57600 [3:29:26<6:37:41,  1.58it/s]
 35%|███▍      | 19935/57600 [3:29:27<6:41:27,  1.56it/s]
 35%|███▍      | 19936/57600 [3:29:27<6:39:28,  1.57it/s]
 35%|███▍      | 19937/57600 [3:29:28<6:35:37,  1.59it/s]
 35%|███▍      | 19938/57600 [3:29:29<6:29:43,  1.61it/s]
 35%|███▍      | 19939/57600 [3:29:29<6:25:23,  1.63it/s]
 35%|███▍      | 19940/57600 [3:29:30<6:38:01,  1.58it/s]
                                                         
{'loss': 1.2392, 'learning_rate': 6.904878048780488e-07, 'epoch': 220.09}

 35%|███▍      | 19940/57600 [3:29:30<6:38:01,  1.58it/s]
 35%|███▍      | 19941/57600 [3:29:30<6:27:26,  1.62it/s]
 35%|███▍      | 19942/57600 [3:29:31<6:13:05,  1.68it/s]
 35%|███▍      | 19943/57600 [3:29:32<6:24:50,  1.63it/s]
 35%|███▍      | 19944/57600 [3:29:32<6:17:26,  1.66it/s]
 35%|███▍      | 19945/57600 [3:29:33<6:18:28,  1.66it/s]
 35%|███▍      | 19946/57600 [3:29:33<6:23:51,  1.63it/s]
 35%|███▍      | 19947/57600 [3:29:34<6:27:42,  1.62it/s]
 35%|███▍      | 19948/57600 [3:29:35<6:45:07,  1.55it/s]
 35%|███▍      | 19949/57600 [3:29:35<6:45:19,  1.55it/s]
 35%|███▍      | 19950/57600 [3:29:36<6:40:08,  1.57it/s]
 35%|███▍      | 19951/57600 [3:29:37<6:38:44,  1.57it/s]
 35%|███▍      | 19952/57600 [3:29:37<6:47:57,  1.54it/s]
 35%|███▍      | 19953/57600 [3:29:38<6:49:00,  1.53it/s]
 35%|███▍      | 19954/57600 [3:29:39<6:34:10,  1.59it/s]
 35%|███▍      | 19955/57600 [3:29:39<6:25:11,  1.63it/s]
 35%|███▍      | 19956/57600 [3:29:40<6:15:45,  1.67it/s]
 35%|███▍      | 19957/57600 [3:29:40<6:09:30,  1.70it/s]
 35%|███▍      | 19958/57600 [3:29:41<6:14:53,  1.67it/s]
 35%|███▍      | 19959/57600 [3:29:42<6:18:55,  1.66it/s]
 35%|███▍      | 19960/57600 [3:29:42<6:34:36,  1.59it/s]
                                                         
{'loss': 1.2442, 'learning_rate': 6.901742160278746e-07, 'epoch': 220.31}

 35%|███▍      | 19960/57600 [3:29:42<6:34:36,  1.59it/s]
 35%|███▍      | 19961/57600 [3:29:43<6:26:51,  1.62it/s]
 35%|███▍      | 19962/57600 [3:29:43<6:35:27,  1.59it/s]
 35%|███▍      | 19963/57600 [3:29:44<6:22:31,  1.64it/s]
 35%|███▍      | 19964/57600 [3:29:45<6:25:59,  1.63it/s]
 35%|███▍      | 19965/57600 [3:29:45<6:16:46,  1.66it/s]
 35%|███▍      | 19966/57600 [3:29:46<6:22:40,  1.64it/s]
 35%|███▍      | 19967/57600 [3:29:47<6:42:12,  1.56it/s]
 35%|███▍      | 19968/57600 [3:29:47<6:56:58,  1.50it/s]
 35%|███▍      | 19969/57600 [3:29:48<6:40:48,  1.56it/s]
 35%|███▍      | 19970/57600 [3:29:49<6:36:52,  1.58it/s]
 35%|███▍      | 19971/57600 [3:29:49<6:43:31,  1.55it/s]
 35%|███▍      | 19972/57600 [3:29:50<6:49:03,  1.53it/s]
 35%|███▍      | 19973/57600 [3:29:50<6:43:30,  1.55it/s]
 35%|███▍      | 19974/57600 [3:29:51<6:45:13,  1.55it/s]
 35%|███▍      | 19975/57600 [3:29:52<6:40:22,  1.57it/s]
 35%|███▍      | 19976/57600 [3:29:52<6:36:15,  1.58it/s]
 35%|███▍      | 19977/57600 [3:29:53<6:30:45,  1.60it/s]
 35%|███▍      | 19978/57600 [3:29:54<6:33:06,  1.60it/s]
 35%|███▍      | 19979/57600 [3:29:54<6:34:50,  1.59it/s]
 35%|███▍      | 19980/57600 [3:29:55<6:23:25,  1.64it/s]
                                                         
{'loss': 1.2349, 'learning_rate': 6.898606271777004e-07, 'epoch': 220.53}

 35%|███▍      | 19980/57600 [3:29:55<6:23:25,  1.64it/s]
 35%|███▍      | 19981/57600 [3:29:55<6:35:27,  1.59it/s]
 35%|███▍      | 19982/57600 [3:29:56<6:41:20,  1.56it/s]
 35%|███▍      | 19983/57600 [3:29:57<6:35:09,  1.59it/s]
 35%|███▍      | 19984/57600 [3:29:57<6:28:40,  1.61it/s]
 35%|███▍      | 19985/57600 [3:29:58<6:20:05,  1.65it/s]
 35%|███▍      | 19986/57600 [3:29:59<6:20:51,  1.65it/s]
 35%|███▍      | 19987/57600 [3:29:59<6:24:37,  1.63it/s]
 35%|███▍      | 19988/57600 [3:30:00<6:16:21,  1.67it/s]
 35%|███▍      | 19989/57600 [3:30:00<6:37:06,  1.58it/s]
 35%|███▍      | 19990/57600 [3:30:01<6:31:00,  1.60it/s]
 35%|███▍      | 19991/57600 [3:30:02<6:16:26,  1.67it/s]
 35%|███▍      | 19992/57600 [3:30:02<6:06:01,  1.71it/s]
 35%|███▍      | 19993/57600 [3:30:03<6:09:52,  1.69it/s]
 35%|███▍      | 19994/57600 [3:30:03<6:23:44,  1.63it/s]
 35%|███▍      | 19995/57600 [3:30:04<6:32:06,  1.60it/s]
 35%|███▍      | 19996/57600 [3:30:05<6:29:56,  1.61it/s]
 35%|███▍      | 19997/57600 [3:30:05<6:31:21,  1.60it/s]
 35%|███▍      | 19998/57600 [3:30:06<6:42:39,  1.56it/s]
 35%|███▍      | 19999/57600 [3:30:07<6:34:37,  1.59it/s]
 35%|███▍      | 20000/57600 [3:30:07<6:21:01,  1.64it/s]
                                                         
{'loss': 1.2566, 'learning_rate': 6.89547038327526e-07, 'epoch': 220.75}

 35%|███▍      | 20000/57600 [3:30:07<6:21:01,  1.64it/s]
 35%|███▍      | 20001/57600 [3:30:08<6:15:28,  1.67it/s]
 35%|███▍      | 20002/57600 [3:30:08<6:35:29,  1.58it/s]
 35%|███▍      | 20003/57600 [3:30:09<6:46:24,  1.54it/s]
 35%|███▍      | 20004/57600 [3:30:10<6:39:01,  1.57it/s]
 35%|███▍      | 20005/57600 [3:30:10<6:34:10,  1.59it/s]
 35%|███▍      | 20006/57600 [3:30:11<6:43:16,  1.55it/s]
 35%|███▍      | 20007/57600 [3:30:12<6:32:11,  1.60it/s]
 35%|███▍      | 20008/57600 [3:30:12<6:24:23,  1.63it/s]
 35%|███▍      | 20009/57600 [3:30:13<6:34:38,  1.59it/s]
 35%|███▍      | 20010/57600 [3:30:13<6:31:38,  1.60it/s]
 35%|███▍      | 20011/57600 [3:30:14<6:36:11,  1.58it/s]
 35%|███▍      | 20012/57600 [3:30:15<6:31:46,  1.60it/s]
 35%|███▍      | 20013/57600 [3:30:15<6:23:40,  1.63it/s]
 35%|███▍      | 20014/57600 [3:30:16<6:23:41,  1.63it/s]
 35%|███▍      | 20015/57600 [3:30:17<6:21:56,  1.64it/s]
 35%|███▍      | 20016/57600 [3:30:17<6:23:00,  1.64it/s]
 35%|███▍      | 20017/57600 [3:30:18<6:28:08,  1.61it/s]
 35%|███▍      | 20018/57600 [3:30:18<6:27:32,  1.62it/s]
 35%|███▍      | 20019/57600 [3:30:19<6:17:57,  1.66it/s]
 35%|███▍      | 20020/57600 [3:30:20<6:32:12,  1.60it/s]
                                                         
{'loss': 1.2482, 'learning_rate': 6.892334494773519e-07, 'epoch': 220.97}

 35%|███▍      | 20020/57600 [3:30:20<6:32:12,  1.60it/s]
 35%|███▍      | 20021/57600 [3:30:20<6:15:17,  1.67it/s]
 35%|███▍      | 20022/57600 [3:30:21<6:11:31,  1.69it/s]
 35%|███▍      | 20023/57600 [3:30:21<6:17:40,  1.66it/s]
 35%|███▍      | 20024/57600 [3:30:22<6:22:11,  1.64it/s]
 35%|███▍      | 20025/57600 [3:30:23<6:34:56,  1.59it/s]
 35%|███▍      | 20026/57600 [3:30:23<6:26:04,  1.62it/s]
 35%|███▍      | 20027/57600 [3:30:24<6:21:43,  1.64it/s]
 35%|███▍      | 20028/57600 [3:30:24<6:18:08,  1.66it/s]
 35%|███▍      | 20029/57600 [3:30:25<6:29:26,  1.61it/s]
 35%|███▍      | 20030/57600 [3:30:26<6:23:04,  1.63it/s]
 35%|███▍      | 20031/57600 [3:30:26<6:23:22,  1.63it/s]
 35%|███▍      | 20032/57600 [3:30:27<6:15:49,  1.67it/s]
 35%|███▍      | 20033/57600 [3:30:28<6:21:03,  1.64it/s]
 35%|███▍      | 20034/57600 [3:30:28<6:23:52,  1.63it/s]
 35%|███▍      | 20035/57600 [3:30:29<6:33:01,  1.59it/s]
 35%|███▍      | 20036/57600 [3:30:29<6:43:10,  1.55it/s]
 35%|███▍      | 20037/57600 [3:30:30<7:01:33,  1.49it/s]
 35%|███▍      | 20038/57600 [3:30:31<6:45:12,  1.54it/s]
 35%|███▍      | 20039/57600 [3:30:32<7:01:37,  1.48it/s]
 35%|███▍      | 20040/57600 [3:30:32<6:48:24,  1.53it/s]
                                                         
{'loss': 1.2711, 'learning_rate': 6.889198606271777e-07, 'epoch': 221.19}

 35%|███▍      | 20040/57600 [3:30:32<6:48:24,  1.53it/s]
 35%|███▍      | 20041/57600 [3:30:33<6:43:36,  1.55it/s]
 35%|███▍      | 20042/57600 [3:30:33<6:43:15,  1.55it/s]
 35%|███▍      | 20043/57600 [3:30:34<6:50:55,  1.52it/s]
 35%|███▍      | 20044/57600 [3:30:35<6:42:09,  1.56it/s]
 35%|███▍      | 20045/57600 [3:30:35<6:35:57,  1.58it/s]
 35%|███▍      | 20046/57600 [3:30:36<6:26:17,  1.62it/s]
 35%|███▍      | 20047/57600 [3:30:37<6:46:06,  1.54it/s]
 35%|███▍      | 20048/57600 [3:30:37<6:30:17,  1.60it/s]
 35%|███▍      | 20049/57600 [3:30:38<6:27:48,  1.61it/s]
 35%|███▍      | 20050/57600 [3:30:38<6:20:55,  1.64it/s]
 35%|███▍      | 20051/57600 [3:30:39<6:14:32,  1.67it/s]
 35%|███▍      | 20052/57600 [3:30:40<6:17:13,  1.66it/s]
 35%|███▍      | 20053/57600 [3:30:40<6:36:00,  1.58it/s]
 35%|███▍      | 20054/57600 [3:30:41<6:25:20,  1.62it/s]
 35%|███▍      | 20055/57600 [3:30:41<6:27:26,  1.62it/s]
 35%|███▍      | 20056/57600 [3:30:42<6:23:13,  1.63it/s]
 35%|███▍      | 20057/57600 [3:30:43<6:15:03,  1.67it/s]
 35%|███▍      | 20058/57600 [3:30:43<6:06:44,  1.71it/s]
 35%|███▍      | 20059/57600 [3:30:44<6:26:05,  1.62it/s]
 35%|███▍      | 20060/57600 [3:30:45<6:32:30,  1.59it/s]
                                                         
{'loss': 1.23, 'learning_rate': 6.886062717770034e-07, 'epoch': 221.41}

 35%|███▍      | 20060/57600 [3:30:45<6:32:30,  1.59it/s]
 35%|███▍      | 20061/57600 [3:30:45<6:24:23,  1.63it/s]
 35%|███▍      | 20062/57600 [3:30:46<6:24:19,  1.63it/s]
 35%|███▍      | 20063/57600 [3:30:46<6:33:09,  1.59it/s]
 35%|███▍      | 20064/57600 [3:30:47<6:36:19,  1.58it/s]
 35%|███▍      | 20065/57600 [3:30:48<6:26:52,  1.62it/s]
 35%|███▍      | 20066/57600 [3:30:48<6:14:51,  1.67it/s]
 35%|███▍      | 20067/57600 [3:30:49<6:10:25,  1.69it/s]
 35%|███▍      | 20068/57600 [3:30:49<6:13:14,  1.68it/s]
 35%|███▍      | 20069/57600 [3:30:50<6:34:13,  1.59it/s]
 35%|███▍      | 20070/57600 [3:30:51<6:25:01,  1.62it/s]
 35%|███▍      | 20071/57600 [3:30:51<6:13:15,  1.68it/s]
 35%|███▍      | 20072/57600 [3:30:52<6:21:49,  1.64it/s]
 35%|███▍      | 20073/57600 [3:30:53<6:28:45,  1.61it/s]
 35%|███▍      | 20074/57600 [3:30:53<6:32:25,  1.59it/s]
 35%|███▍      | 20075/57600 [3:30:54<6:25:21,  1.62it/s]
 35%|███▍      | 20076/57600 [3:30:54<6:23:14,  1.63it/s]
 35%|███▍      | 20077/57600 [3:30:55<6:18:23,  1.65it/s]
 35%|███▍      | 20078/57600 [3:30:56<6:26:09,  1.62it/s]
 35%|███▍      | 20079/57600 [3:30:56<6:32:29,  1.59it/s]
 35%|███▍      | 20080/57600 [3:30:57<6:31:43,  1.60it/s]
                                                         
{'loss': 1.2464, 'learning_rate': 6.882926829268293e-07, 'epoch': 221.63}

 35%|███▍      | 20080/57600 [3:30:57<6:31:43,  1.60it/s]
 35%|███▍      | 20081/57600 [3:30:57<6:20:16,  1.64it/s]
 35%|███▍      | 20082/57600 [3:30:58<6:22:01,  1.64it/s]
 35%|███▍      | 20083/57600 [3:30:59<6:19:22,  1.65it/s]
 35%|███▍      | 20084/57600 [3:30:59<6:15:13,  1.67it/s]
 35%|███▍      | 20085/57600 [3:31:00<6:03:42,  1.72it/s]
 35%|███▍      | 20086/57600 [3:31:00<6:20:47,  1.64it/s]
 35%|███▍      | 20087/57600 [3:31:01<6:08:10,  1.70it/s]
 35%|███▍      | 20088/57600 [3:31:02<6:09:03,  1.69it/s]
 35%|███▍      | 20089/57600 [3:31:02<6:03:00,  1.72it/s]
 35%|███▍      | 20090/57600 [3:31:03<6:01:11,  1.73it/s]
 35%|███▍      | 20091/57600 [3:31:03<6:13:46,  1.67it/s]
 35%|███▍      | 20092/57600 [3:31:04<6:16:55,  1.66it/s]
 35%|███▍      | 20093/57600 [3:31:05<6:25:33,  1.62it/s]
 35%|███▍      | 20094/57600 [3:31:05<6:26:12,  1.62it/s]
 35%|███▍      | 20095/57600 [3:31:06<6:37:16,  1.57it/s]
 35%|███▍      | 20096/57600 [3:31:07<6:50:00,  1.52it/s]
 35%|███▍      | 20097/57600 [3:31:07<6:35:55,  1.58it/s]
 35%|███▍      | 20098/57600 [3:31:08<6:27:00,  1.62it/s]
 35%|███▍      | 20099/57600 [3:31:08<6:24:06,  1.63it/s]
 35%|███▍      | 20100/57600 [3:31:09<6:23:48,  1.63it/s]
                                                         
{'loss': 1.2735, 'learning_rate': 6.879790940766551e-07, 'epoch': 221.85}

 35%|███▍      | 20100/57600 [3:31:09<6:23:48,  1.63it/s]
 35%|███▍      | 20101/57600 [3:31:10<6:16:49,  1.66it/s]
 35%|███▍      | 20102/57600 [3:31:10<6:12:53,  1.68it/s]
 35%|███▍      | 20103/57600 [3:31:11<6:34:51,  1.58it/s]
 35%|███▍      | 20104/57600 [3:31:11<6:33:41,  1.59it/s]
 35%|███▍      | 20105/57600 [3:31:12<6:40:30,  1.56it/s]
 35%|███▍      | 20106/57600 [3:31:13<6:38:51,  1.57it/s]
 35%|███▍      | 20107/57600 [3:31:13<6:33:04,  1.59it/s]
 35%|███▍      | 20108/57600 [3:31:14<6:32:12,  1.59it/s]
 35%|███▍      | 20109/57600 [3:31:15<6:17:25,  1.66it/s]
 35%|███▍      | 20110/57600 [3:31:15<6:27:26,  1.61it/s]
 35%|███▍      | 20111/57600 [3:31:16<6:35:19,  1.58it/s]
 35%|███▍      | 20112/57600 [3:31:16<6:19:53,  1.64it/s]
 35%|███▍      | 20113/57600 [3:31:17<6:18:59,  1.65it/s]
 35%|███▍      | 20114/57600 [3:31:18<6:34:50,  1.58it/s]
 35%|███▍      | 20115/57600 [3:31:18<6:55:34,  1.50it/s]
 35%|███▍      | 20116/57600 [3:31:19<6:50:57,  1.52it/s]
 35%|███▍      | 20117/57600 [3:31:20<6:42:21,  1.55it/s]
 35%|███▍      | 20118/57600 [3:31:20<6:40:05,  1.56it/s]
 35%|███▍      | 20119/57600 [3:31:21<6:24:23,  1.63it/s]
 35%|███▍      | 20120/57600 [3:31:22<6:22:55,  1.63it/s]
                                                         
{'loss': 1.2507, 'learning_rate': 6.876655052264808e-07, 'epoch': 222.08}

 35%|███▍      | 20120/57600 [3:31:22<6:22:55,  1.63it/s]
 35%|███▍      | 20121/57600 [3:31:22<6:42:25,  1.55it/s]
 35%|███▍      | 20122/57600 [3:31:23<6:30:53,  1.60it/s]
 35%|███▍      | 20123/57600 [3:31:23<6:35:06,  1.58it/s]
 35%|███▍      | 20124/57600 [3:31:24<6:42:58,  1.55it/s]
 35%|███▍      | 20125/57600 [3:31:25<6:51:27,  1.52it/s]
 35%|███▍      | 20126/57600 [3:31:25<6:38:06,  1.57it/s]
 35%|███▍      | 20127/57600 [3:31:26<6:38:29,  1.57it/s]
 35%|███▍      | 20128/57600 [3:31:27<6:25:59,  1.62it/s]
 35%|███▍      | 20129/57600 [3:31:27<6:21:49,  1.64it/s]
 35%|███▍      | 20130/57600 [3:31:28<6:13:01,  1.67it/s]
 35%|███▍      | 20131/57600 [3:31:28<6:12:38,  1.68it/s]
 35%|███▍      | 20132/57600 [3:31:29<6:04:13,  1.71it/s]
 35%|███▍      | 20133/57600 [3:31:30<6:16:10,  1.66it/s]
 35%|███▍      | 20134/57600 [3:31:30<6:23:44,  1.63it/s]
 35%|███▍      | 20135/57600 [3:31:31<6:24:47,  1.62it/s]
 35%|███▍      | 20136/57600 [3:31:31<6:17:27,  1.65it/s]
 35%|███▍      | 20137/57600 [3:31:32<6:08:11,  1.70it/s]
 35%|███▍      | 20138/57600 [3:31:33<6:16:53,  1.66it/s]
 35%|███▍      | 20139/57600 [3:31:33<6:10:43,  1.68it/s]
 35%|███▍      | 20140/57600 [3:31:34<6:13:17,  1.67it/s]
                                                         
{'loss': 1.2515, 'learning_rate': 6.873519163763065e-07, 'epoch': 222.3}

 35%|███▍      | 20140/57600 [3:31:34<6:13:17,  1.67it/s]
 35%|███▍      | 20141/57600 [3:31:34<6:11:05,  1.68it/s]
 35%|███▍      | 20142/57600 [3:31:35<6:17:05,  1.66it/s]
 35%|███▍      | 20143/57600 [3:31:36<6:15:51,  1.66it/s]
 35%|███▍      | 20144/57600 [3:31:36<6:20:24,  1.64it/s]
 35%|███▍      | 20145/57600 [3:31:37<6:15:29,  1.66it/s]
 35%|███▍      | 20146/57600 [3:31:37<6:12:01,  1.68it/s]
 35%|███▍      | 20147/57600 [3:31:38<6:04:58,  1.71it/s]
 35%|███▍      | 20148/57600 [3:31:39<6:13:46,  1.67it/s]
 35%|███▍      | 20149/57600 [3:31:39<6:14:35,  1.67it/s]
 35%|███▍      | 20150/57600 [3:31:40<6:25:13,  1.62it/s]
 35%|███▍      | 20151/57600 [3:31:40<6:14:13,  1.67it/s]
 35%|███▍      | 20152/57600 [3:31:41<6:20:18,  1.64it/s]
 35%|███▍      | 20153/57600 [3:31:42<6:34:21,  1.58it/s]
 35%|███▍      | 20154/57600 [3:31:42<6:44:29,  1.54it/s]
 35%|███▍      | 20155/57600 [3:31:43<7:00:13,  1.49it/s]
 35%|███▍      | 20156/57600 [3:31:44<6:45:49,  1.54it/s]
 35%|███▍      | 20157/57600 [3:31:44<6:42:37,  1.55it/s]
 35%|███▍      | 20158/57600 [3:31:45<6:45:32,  1.54it/s]
 35%|███▍      | 20159/57600 [3:31:46<6:31:18,  1.59it/s]
 35%|███▌      | 20160/57600 [3:31:46<6:40:29,  1.56it/s]
                                                         
{'loss': 1.2369, 'learning_rate': 6.870383275261324e-07, 'epoch': 222.52}

 35%|███▌      | 20160/57600 [3:31:46<6:40:29,  1.56it/s]
 35%|███▌      | 20161/57600 [3:31:47<6:39:38,  1.56it/s]
 35%|███▌      | 20162/57600 [3:31:48<6:37:59,  1.57it/s]
 35%|███▌      | 20163/57600 [3:31:48<6:34:06,  1.58it/s]
 35%|███▌      | 20164/57600 [3:31:49<6:20:55,  1.64it/s]
 35%|███▌      | 20165/57600 [3:31:49<6:23:31,  1.63it/s]
 35%|███▌      | 20166/57600 [3:31:50<6:13:26,  1.67it/s]
 35%|███▌      | 20167/57600 [3:31:51<6:18:10,  1.65it/s]
 35%|███▌      | 20168/57600 [3:31:51<6:16:58,  1.65it/s]
 35%|███▌      | 20169/57600 [3:31:52<6:10:51,  1.68it/s]
 35%|███▌      | 20170/57600 [3:31:52<6:19:45,  1.64it/s]
 35%|███▌      | 20171/57600 [3:31:53<6:36:35,  1.57it/s]
 35%|███▌      | 20172/57600 [3:31:54<6:29:17,  1.60it/s]
 35%|███▌      | 20173/57600 [3:31:54<6:30:02,  1.60it/s]
 35%|███▌      | 20174/57600 [3:31:55<6:23:23,  1.63it/s]
 35%|███▌      | 20175/57600 [3:31:55<6:26:12,  1.62it/s]
 35%|███▌      | 20176/57600 [3:31:56<6:28:21,  1.61it/s]
 35%|███▌      | 20177/57600 [3:31:57<6:22:04,  1.63it/s]
 35%|███▌      | 20178/57600 [3:31:57<6:13:03,  1.67it/s]
 35%|███▌      | 20179/57600 [3:31:58<6:19:25,  1.64it/s]
 35%|███▌      | 20180/57600 [3:31:59<6:15:44,  1.66it/s]
                                                         
{'loss': 1.2528, 'learning_rate': 6.867247386759582e-07, 'epoch': 222.74}

 35%|███▌      | 20180/57600 [3:31:59<6:15:44,  1.66it/s]
 35%|███▌      | 20181/57600 [3:31:59<6:12:44,  1.67it/s]
 35%|███▌      | 20182/57600 [3:32:00<6:29:03,  1.60it/s]
 35%|███▌      | 20183/57600 [3:32:00<6:20:09,  1.64it/s]
 35%|███▌      | 20184/57600 [3:32:01<6:25:03,  1.62it/s]
 35%|███▌      | 20185/57600 [3:32:02<6:27:02,  1.61it/s]
 35%|███▌      | 20186/57600 [3:32:02<6:42:58,  1.55it/s]
 35%|███▌      | 20187/57600 [3:32:03<6:23:19,  1.63it/s]
 35%|███▌      | 20188/57600 [3:32:03<6:22:51,  1.63it/s]
 35%|███▌      | 20189/57600 [3:32:04<6:17:53,  1.65it/s]
 35%|███▌      | 20190/57600 [3:32:05<6:22:07,  1.63it/s]
 35%|███▌      | 20191/57600 [3:32:05<6:27:42,  1.61it/s]
 35%|███▌      | 20192/57600 [3:32:06<6:47:07,  1.53it/s]
 35%|███▌      | 20193/57600 [3:32:07<6:47:02,  1.53it/s]
 35%|███▌      | 20194/57600 [3:32:07<6:56:39,  1.50it/s]
 35%|███▌      | 20195/57600 [3:32:08<6:51:01,  1.52it/s]
 35%|███▌      | 20196/57600 [3:32:09<6:38:14,  1.57it/s]
 35%|███▌      | 20197/57600 [3:32:09<6:23:46,  1.62it/s]
 35%|███▌      | 20198/57600 [3:32:10<6:23:02,  1.63it/s]
 35%|███▌      | 20199/57600 [3:32:10<6:29:33,  1.60it/s]
 35%|███▌      | 20200/57600 [3:32:11<6:20:59,  1.64it/s]
                                                         
{'loss': 1.2579, 'learning_rate': 6.86411149825784e-07, 'epoch': 222.96}

 35%|███▌      | 20200/57600 [3:32:11<6:20:59,  1.64it/s]
 35%|███▌      | 20201/57600 [3:32:12<6:21:30,  1.63it/s]
 35%|███▌      | 20202/57600 [3:32:12<6:20:45,  1.64it/s]
 35%|███▌      | 20203/57600 [3:32:13<6:12:50,  1.67it/s]
 35%|███▌      | 20204/57600 [3:32:14<6:28:10,  1.61it/s]
 35%|███▌      | 20205/57600 [3:32:14<6:34:08,  1.58it/s]
 35%|███▌      | 20206/57600 [3:32:15<6:43:36,  1.54it/s]
 35%|███▌      | 20207/57600 [3:32:15<6:41:13,  1.55it/s]
 35%|███▌      | 20208/57600 [3:32:16<6:54:46,  1.50it/s]
 35%|███▌      | 20209/57600 [3:32:17<6:54:00,  1.51it/s]
 35%|███▌      | 20210/57600 [3:32:18<6:48:58,  1.52it/s]
 35%|███▌      | 20211/57600 [3:32:18<6:46:19,  1.53it/s]
 35%|███▌      | 20212/57600 [3:32:19<6:42:57,  1.55it/s]
 35%|███▌      | 20213/57600 [3:32:19<6:36:12,  1.57it/s]
 35%|███▌      | 20214/57600 [3:32:20<6:27:39,  1.61it/s]
 35%|███▌      | 20215/57600 [3:32:21<6:17:47,  1.65it/s]
 35%|███▌      | 20216/57600 [3:32:21<6:27:25,  1.61it/s]
 35%|███▌      | 20217/57600 [3:32:22<6:27:08,  1.61it/s]
 35%|███▌      | 20218/57600 [3:32:22<6:26:58,  1.61it/s]
 35%|███▌      | 20219/57600 [3:32:23<6:28:50,  1.60it/s]
 35%|███▌      | 20220/57600 [3:32:24<6:29:14,  1.60it/s]
                                                         
{'loss': 1.2472, 'learning_rate': 6.860975609756097e-07, 'epoch': 223.18}

 35%|███▌      | 20220/57600 [3:32:24<6:29:14,  1.60it/s]
 35%|███▌      | 20221/57600 [3:32:24<6:37:21,  1.57it/s]
 35%|███▌      | 20222/57600 [3:32:25<6:27:35,  1.61it/s]
 35%|███▌      | 20223/57600 [3:32:26<6:18:00,  1.65it/s]
 35%|███▌      | 20224/57600 [3:32:26<6:09:19,  1.69it/s]
 35%|███▌      | 20225/57600 [3:32:27<6:14:43,  1.66it/s]
 35%|███▌      | 20226/57600 [3:32:27<6:13:48,  1.67it/s]
 35%|███▌      | 20227/57600 [3:32:28<6:06:39,  1.70it/s]
 35%|███▌      | 20228/57600 [3:32:29<6:15:54,  1.66it/s]
 35%|███▌      | 20229/57600 [3:32:29<6:06:11,  1.70it/s]
 35%|███▌      | 20230/57600 [3:32:30<6:04:41,  1.71it/s]
 35%|███▌      | 20231/57600 [3:32:30<6:01:23,  1.72it/s]
 35%|███▌      | 20232/57600 [3:32:31<6:03:20,  1.71it/s]
 35%|███▌      | 20233/57600 [3:32:32<6:29:38,  1.60it/s]
 35%|███▌      | 20234/57600 [3:32:32<6:28:53,  1.60it/s]
 35%|███▌      | 20235/57600 [3:32:33<6:15:48,  1.66it/s]
 35%|███▌      | 20236/57600 [3:32:33<6:20:44,  1.64it/s]
 35%|███▌      | 20237/57600 [3:32:34<6:48:13,  1.53it/s]
 35%|███▌      | 20238/57600 [3:32:35<6:34:30,  1.58it/s]
 35%|███▌      | 20239/57600 [3:32:35<6:31:39,  1.59it/s]
 35%|███▌      | 20240/57600 [3:32:36<6:29:11,  1.60it/s]
                                                         
{'loss': 1.2572, 'learning_rate': 6.857839721254356e-07, 'epoch': 223.4}

 35%|███▌      | 20240/57600 [3:32:36<6:29:11,  1.60it/s]
 35%|███▌      | 20241/57600 [3:32:37<6:25:00,  1.62it/s]
 35%|███▌      | 20242/57600 [3:32:37<6:19:03,  1.64it/s]
 35%|███▌      | 20243/57600 [3:32:38<6:14:58,  1.66it/s]
 35%|███▌      | 20244/57600 [3:32:38<6:25:47,  1.61it/s]
 35%|███▌      | 20245/57600 [3:32:39<6:19:53,  1.64it/s]
 35%|███▌      | 20246/57600 [3:32:40<6:21:22,  1.63it/s]
 35%|███▌      | 20247/57600 [3:32:40<6:36:13,  1.57it/s]
 35%|███▌      | 20248/57600 [3:32:41<6:45:40,  1.53it/s]
 35%|███▌      | 20249/57600 [3:32:42<6:44:29,  1.54it/s]
 35%|███▌      | 20250/57600 [3:32:42<6:34:34,  1.58it/s]
 35%|███▌      | 20251/57600 [3:32:43<6:40:17,  1.56it/s]
 35%|███▌      | 20252/57600 [3:32:43<6:33:55,  1.58it/s]
 35%|███▌      | 20253/57600 [3:32:44<6:48:29,  1.52it/s]
 35%|███▌      | 20254/57600 [3:32:45<6:36:41,  1.57it/s]
 35%|███▌      | 20255/57600 [3:32:45<6:49:27,  1.52it/s]
 35%|███▌      | 20256/57600 [3:32:46<6:48:07,  1.53it/s]
 35%|███▌      | 20257/57600 [3:32:47<6:58:34,  1.49it/s]
 35%|███▌      | 20258/57600 [3:32:48<7:14:51,  1.43it/s]
 35%|███▌      | 20259/57600 [3:32:48<7:14:22,  1.43it/s]
 35%|███▌      | 20260/57600 [3:32:49<6:57:44,  1.49it/s]
                                                         
{'loss': 1.2051, 'learning_rate': 6.854703832752613e-07, 'epoch': 223.62}

 35%|███▌      | 20260/57600 [3:32:49<6:57:44,  1.49it/s]
 35%|███▌      | 20261/57600 [3:32:49<6:42:48,  1.54it/s]
 35%|███▌      | 20262/57600 [3:32:50<6:33:46,  1.58it/s]
 35%|███▌      | 20263/57600 [3:32:51<6:29:59,  1.60it/s]
 35%|███▌      | 20264/57600 [3:32:51<6:21:19,  1.63it/s]
 35%|███▌      | 20265/57600 [3:32:52<6:22:02,  1.63it/s]
 35%|███▌      | 20266/57600 [3:32:52<6:15:47,  1.66it/s]
 35%|███▌      | 20267/57600 [3:32:53<6:17:27,  1.65it/s]
 35%|███▌      | 20268/57600 [3:32:54<6:29:01,  1.60it/s]
 35%|███▌      | 20269/57600 [3:32:54<6:27:52,  1.60it/s]
 35%|███▌      | 20270/57600 [3:32:55<6:24:13,  1.62it/s]
 35%|███▌      | 20271/57600 [3:32:56<6:13:38,  1.67it/s]
 35%|███▌      | 20272/57600 [3:32:56<6:08:18,  1.69it/s]
 35%|███▌      | 20273/57600 [3:32:57<6:02:33,  1.72it/s]
 35%|███▌      | 20274/57600 [3:32:57<6:14:13,  1.66it/s]
 35%|███▌      | 20275/57600 [3:32:58<6:26:30,  1.61it/s]
 35%|███▌      | 20276/57600 [3:32:59<6:34:12,  1.58it/s]
 35%|███▌      | 20277/57600 [3:32:59<6:19:38,  1.64it/s]
 35%|███▌      | 20278/57600 [3:33:00<6:08:13,  1.69it/s]
 35%|███▌      | 20279/57600 [3:33:00<6:09:39,  1.68it/s]
 35%|███▌      | 20280/57600 [3:33:01<6:11:22,  1.67it/s]
                                                         
{'loss': 1.2518, 'learning_rate': 6.851567944250871e-07, 'epoch': 223.84}

 35%|███▌      | 20280/57600 [3:33:01<6:11:22,  1.67it/s]
 35%|███▌      | 20281/57600 [3:33:02<6:10:00,  1.68it/s]
 35%|███▌      | 20282/57600 [3:33:02<6:02:54,  1.71it/s]
 35%|███▌      | 20283/57600 [3:33:03<6:04:23,  1.71it/s]
 35%|███▌      | 20284/57600 [3:33:03<6:11:02,  1.68it/s]
 35%|███▌      | 20285/57600 [3:33:04<6:28:25,  1.60it/s]
 35%|███▌      | 20286/57600 [3:33:05<6:25:22,  1.61it/s]
 35%|███▌      | 20287/57600 [3:33:05<6:24:43,  1.62it/s]
 35%|███▌      | 20288/57600 [3:33:06<6:13:18,  1.67it/s]
 35%|███▌      | 20289/57600 [3:33:06<6:19:25,  1.64it/s]
 35%|███▌      | 20290/57600 [3:33:07<6:17:12,  1.65it/s]
 35%|███▌      | 20291/57600 [3:33:08<6:12:21,  1.67it/s]
 35%|███▌      | 20292/57600 [3:33:08<6:06:07,  1.70it/s]
 35%|███▌      | 20293/57600 [3:33:09<6:03:00,  1.71it/s]
 35%|███▌      | 20294/57600 [3:33:09<6:01:01,  1.72it/s]
 35%|███▌      | 20295/57600 [3:33:10<6:21:09,  1.63it/s]
 35%|███▌      | 20296/57600 [3:33:11<6:19:37,  1.64it/s]
 35%|███▌      | 20297/57600 [3:33:11<6:16:41,  1.65it/s]
 35%|███▌      | 20298/57600 [3:33:12<6:26:15,  1.61it/s]
 35%|███▌      | 20299/57600 [3:33:12<6:23:44,  1.62it/s]
 35%|███▌      | 20300/57600 [3:33:13<6:22:30,  1.63it/s]
                                                         
{'loss': 1.3164, 'learning_rate': 6.848432055749128e-07, 'epoch': 224.06}

 35%|███▌      | 20300/57600 [3:33:13<6:22:30,  1.63it/s]
 35%|███▌      | 20301/57600 [3:33:14<6:19:39,  1.64it/s]
 35%|███▌      | 20302/57600 [3:33:14<6:19:31,  1.64it/s]
 35%|███▌      | 20303/57600 [3:33:15<6:18:17,  1.64it/s]
 35%|███▌      | 20304/57600 [3:33:15<6:17:33,  1.65it/s]
 35%|███▌      | 20305/57600 [3:33:16<6:16:20,  1.65it/s]
 35%|███▌      | 20306/57600 [3:33:17<6:36:36,  1.57it/s]
 35%|███▌      | 20307/57600 [3:33:17<6:43:27,  1.54it/s]
 35%|███▌      | 20308/57600 [3:33:18<6:36:17,  1.57it/s]
 35%|███▌      | 20309/57600 [3:33:19<6:37:37,  1.56it/s]
 35%|███▌      | 20310/57600 [3:33:19<6:31:21,  1.59it/s]
 35%|███▌      | 20311/57600 [3:33:20<6:42:29,  1.54it/s]
 35%|███▌      | 20312/57600 [3:33:21<6:33:54,  1.58it/s]
 35%|███▌      | 20313/57600 [3:33:21<6:21:54,  1.63it/s]
 35%|███▌      | 20314/57600 [3:33:22<6:24:38,  1.62it/s]
 35%|███▌      | 20315/57600 [3:33:23<6:35:06,  1.57it/s]
 35%|███▌      | 20316/57600 [3:33:23<6:31:27,  1.59it/s]
 35%|███▌      | 20317/57600 [3:33:24<6:22:51,  1.62it/s]
 35%|███▌      | 20318/57600 [3:33:24<6:28:49,  1.60it/s]
 35%|███▌      | 20319/57600 [3:33:25<6:22:34,  1.62it/s]
 35%|███▌      | 20320/57600 [3:33:26<6:32:27,  1.58it/s]
                                                         
{'loss': 1.2392, 'learning_rate': 6.845296167247387e-07, 'epoch': 224.28}

 35%|███▌      | 20320/57600 [3:33:26<6:32:27,  1.58it/s]
 35%|███▌      | 20321/57600 [3:33:26<6:35:12,  1.57it/s]
 35%|███▌      | 20322/57600 [3:33:27<6:25:30,  1.61it/s]
 35%|███▌      | 20323/57600 [3:33:27<6:23:49,  1.62it/s]
 35%|███▌      | 20324/57600 [3:33:28<6:33:02,  1.58it/s]
 35%|███▌      | 20325/57600 [3:33:29<6:29:03,  1.60it/s]
 35%|███▌      | 20326/57600 [3:33:29<6:19:18,  1.64it/s]
 35%|███▌      | 20327/57600 [3:33:30<6:16:53,  1.65it/s]
 35%|███▌      | 20328/57600 [3:33:31<6:20:14,  1.63it/s]
 35%|███▌      | 20329/57600 [3:33:31<6:24:06,  1.62it/s]
 35%|███▌      | 20330/57600 [3:33:32<6:33:50,  1.58it/s]
 35%|███▌      | 20331/57600 [3:33:32<6:26:23,  1.61it/s]
 35%|███▌      | 20332/57600 [3:33:33<6:20:59,  1.63it/s]
 35%|███▌      | 20333/57600 [3:33:34<6:27:55,  1.60it/s]
 35%|███▌      | 20334/57600 [3:33:34<6:43:17,  1.54it/s]
 35%|███▌      | 20335/57600 [3:33:35<6:33:59,  1.58it/s]
 35%|███▌      | 20336/57600 [3:33:36<6:22:24,  1.62it/s]
 35%|███▌      | 20337/57600 [3:33:36<6:13:14,  1.66it/s]
 35%|███▌      | 20338/57600 [3:33:37<6:05:53,  1.70it/s]
 35%|███▌      | 20339/57600 [3:33:37<6:03:30,  1.71it/s]
 35%|███▌      | 20340/57600 [3:33:38<6:13:11,  1.66it/s]
                                                         
{'loss': 1.2513, 'learning_rate': 6.842160278745644e-07, 'epoch': 224.5}

 35%|███▌      | 20340/57600 [3:33:38<6:13:11,  1.66it/s]
 35%|███▌      | 20341/57600 [3:33:38<6:09:27,  1.68it/s]
 35%|███▌      | 20342/57600 [3:33:39<6:10:11,  1.68it/s]
 35%|███▌      | 20343/57600 [3:33:40<6:13:44,  1.66it/s]
 35%|███▌      | 20344/57600 [3:33:40<6:04:02,  1.71it/s]
 35%|███▌      | 20345/57600 [3:33:41<6:09:57,  1.68it/s]
 35%|███▌      | 20346/57600 [3:33:41<6:09:39,  1.68it/s]
 35%|███▌      | 20347/57600 [3:33:42<6:03:11,  1.71it/s]
 35%|███▌      | 20348/57600 [3:33:43<6:03:47,  1.71it/s]
 35%|███▌      | 20349/57600 [3:33:43<5:58:19,  1.73it/s]
 35%|███▌      | 20350/57600 [3:33:44<5:54:44,  1.75it/s]
 35%|███▌      | 20351/57600 [3:33:44<6:11:53,  1.67it/s]
 35%|███▌      | 20352/57600 [3:33:45<6:23:27,  1.62it/s]
 35%|███▌      | 20353/57600 [3:33:46<6:25:56,  1.61it/s]
 35%|███▌      | 20354/57600 [3:33:46<6:27:28,  1.60it/s]
 35%|███▌      | 20355/57600 [3:33:47<6:38:46,  1.56it/s]
 35%|███▌      | 20356/57600 [3:33:48<6:29:55,  1.59it/s]
 35%|███▌      | 20357/57600 [3:33:48<6:25:54,  1.61it/s]
 35%|███▌      | 20358/57600 [3:33:49<6:24:55,  1.61it/s]
 35%|███▌      | 20359/57600 [3:33:49<6:21:42,  1.63it/s]
 35%|███▌      | 20360/57600 [3:33:50<6:27:19,  1.60it/s]
                                                         
{'loss': 1.2702, 'learning_rate': 6.839024390243902e-07, 'epoch': 224.72}

 35%|███▌      | 20360/57600 [3:33:50<6:27:19,  1.60it/s]
 35%|███▌      | 20361/57600 [3:33:51<6:40:25,  1.55it/s]
 35%|███▌      | 20362/57600 [3:33:51<6:36:15,  1.57it/s]
 35%|███▌      | 20363/57600 [3:33:52<6:42:57,  1.54it/s]
 35%|███▌      | 20364/57600 [3:33:53<6:39:39,  1.55it/s]
 35%|███▌      | 20365/57600 [3:33:53<6:42:44,  1.54it/s]
 35%|███▌      | 20366/57600 [3:33:54<6:34:57,  1.57it/s]
 35%|███▌      | 20367/57600 [3:33:55<6:34:11,  1.57it/s]
 35%|███▌      | 20368/57600 [3:33:55<6:21:08,  1.63it/s]
 35%|███▌      | 20369/57600 [3:33:56<6:38:02,  1.56it/s]
 35%|███▌      | 20370/57600 [3:33:56<6:25:41,  1.61it/s]
 35%|███▌      | 20371/57600 [3:33:57<6:18:58,  1.64it/s]
 35%|███▌      | 20372/57600 [3:33:58<6:14:46,  1.66it/s]
 35%|███▌      | 20373/57600 [3:33:58<6:06:50,  1.69it/s]
 35%|███▌      | 20374/57600 [3:33:59<5:58:30,  1.73it/s]
 35%|███▌      | 20375/57600 [3:33:59<6:01:55,  1.71it/s]
 35%|███▌      | 20376/57600 [3:34:00<6:08:29,  1.68it/s]
 35%|███▌      | 20377/57600 [3:34:01<6:15:38,  1.65it/s]
 35%|███▌      | 20378/57600 [3:34:01<6:30:47,  1.59it/s]
 35%|███▌      | 20379/57600 [3:34:02<6:22:04,  1.62it/s]
 35%|███▌      | 20380/57600 [3:34:02<6:19:12,  1.64it/s]
                                                         
{'loss': 1.2733, 'learning_rate': 6.83588850174216e-07, 'epoch': 224.94}

 35%|███▌      | 20380/57600 [3:34:02<6:19:12,  1.64it/s]
 35%|███▌      | 20381/57600 [3:34:03<6:16:52,  1.65it/s]
 35%|███▌      | 20382/57600 [3:34:04<6:09:50,  1.68it/s]
 35%|███▌      | 20383/57600 [3:34:04<6:24:44,  1.61it/s]
 35%|███▌      | 20384/57600 [3:34:05<6:24:13,  1.61it/s]
 35%|███▌      | 20385/57600 [3:34:06<6:40:06,  1.55it/s]
 35%|███▌      | 20386/57600 [3:34:06<6:47:30,  1.52it/s]
 35%|███▌      | 20387/57600 [3:34:07<6:47:36,  1.52it/s]
 35%|███▌      | 20388/57600 [3:34:07<6:27:12,  1.60it/s]
 35%|███▌      | 20389/57600 [3:34:08<6:21:52,  1.62it/s]
 35%|███▌      | 20390/57600 [3:34:09<6:19:09,  1.64it/s]
 35%|███▌      | 20391/57600 [3:34:09<6:34:10,  1.57it/s]
 35%|███▌      | 20392/57600 [3:34:10<6:33:07,  1.58it/s]
 35%|███▌      | 20393/57600 [3:34:11<6:29:38,  1.59it/s]
 35%|███▌      | 20394/57600 [3:34:11<6:32:24,  1.58it/s]
 35%|███▌      | 20395/57600 [3:34:12<6:30:26,  1.59it/s]
 35%|███▌      | 20396/57600 [3:34:13<6:33:07,  1.58it/s]
 35%|███▌      | 20397/57600 [3:34:13<6:25:01,  1.61it/s]
 35%|███▌      | 20398/57600 [3:34:14<6:26:42,  1.60it/s]
 35%|███▌      | 20399/57600 [3:34:14<6:37:50,  1.56it/s]
 35%|███▌      | 20400/57600 [3:34:15<6:30:05,  1.59it/s]
                                                         
{'loss': 1.2207, 'learning_rate': 6.832752613240418e-07, 'epoch': 225.17}

 35%|███▌      | 20400/57600 [3:34:15<6:30:05,  1.59it/s]
 35%|███▌      | 20401/57600 [3:34:16<6:16:35,  1.65it/s]
 35%|███▌      | 20402/57600 [3:34:16<6:13:55,  1.66it/s]
 35%|███▌      | 20403/57600 [3:34:17<6:15:18,  1.65it/s]
 35%|███▌      | 20404/57600 [3:34:17<6:23:24,  1.62it/s]
 35%|███▌      | 20405/57600 [3:34:18<6:24:04,  1.61it/s]
 35%|███▌      | 20406/57600 [3:34:19<6:20:10,  1.63it/s]
 35%|███▌      | 20407/57600 [3:34:19<6:24:58,  1.61it/s]
 35%|███▌      | 20408/57600 [3:34:20<6:20:24,  1.63it/s]
 35%|███▌      | 20409/57600 [3:34:21<6:23:38,  1.62it/s]
 35%|███▌      | 20410/57600 [3:34:21<6:29:50,  1.59it/s]
 35%|███▌      | 20411/57600 [3:34:22<6:30:59,  1.59it/s]
 35%|███▌      | 20412/57600 [3:34:22<6:35:36,  1.57it/s]
 35%|███▌      | 20413/57600 [3:34:23<6:31:30,  1.58it/s]
 35%|███▌      | 20414/57600 [3:34:24<6:21:35,  1.62it/s]
 35%|███▌      | 20415/57600 [3:34:24<6:10:00,  1.67it/s]
 35%|███▌      | 20416/57600 [3:34:25<6:21:18,  1.63it/s]
 35%|███▌      | 20417/57600 [3:34:25<6:18:25,  1.64it/s]
 35%|███▌      | 20418/57600 [3:34:26<6:11:56,  1.67it/s]
 35%|███▌      | 20419/57600 [3:34:27<6:19:49,  1.63it/s]
 35%|███▌      | 20420/57600 [3:34:27<6:21:16,  1.63it/s]
                                                         
{'loss': 1.2608, 'learning_rate': 6.829616724738676e-07, 'epoch': 225.39}

 35%|███▌      | 20420/57600 [3:34:27<6:21:16,  1.63it/s]
 35%|███▌      | 20421/57600 [3:34:28<6:27:53,  1.60it/s]
 35%|███▌      | 20422/57600 [3:34:29<6:29:39,  1.59it/s]
 35%|███▌      | 20423/57600 [3:34:29<6:28:41,  1.59it/s]
 35%|███▌      | 20424/57600 [3:34:30<6:26:25,  1.60it/s]
 35%|███▌      | 20425/57600 [3:34:30<6:33:55,  1.57it/s]
 35%|███▌      | 20426/57600 [3:34:31<6:26:43,  1.60it/s]
 35%|███▌      | 20427/57600 [3:34:32<6:19:57,  1.63it/s]
 35%|███▌      | 20428/57600 [3:34:32<6:11:51,  1.67it/s]
 35%|███▌      | 20429/57600 [3:34:33<6:07:31,  1.69it/s]
 35%|███▌      | 20430/57600 [3:34:33<6:21:49,  1.62it/s]
 35%|███▌      | 20431/57600 [3:34:34<6:15:42,  1.65it/s]
 35%|███▌      | 20432/57600 [3:34:35<6:20:04,  1.63it/s]
 35%|███▌      | 20433/57600 [3:34:35<6:12:32,  1.66it/s]
 35%|███▌      | 20434/57600 [3:34:36<6:22:17,  1.62it/s]
 35%|███▌      | 20435/57600 [3:34:37<6:24:51,  1.61it/s]
 35%|███▌      | 20436/57600 [3:34:37<6:16:56,  1.64it/s]
 35%|███▌      | 20437/57600 [3:34:38<6:18:11,  1.64it/s]
 35%|███▌      | 20438/57600 [3:34:38<6:11:06,  1.67it/s]
 35%|███▌      | 20439/57600 [3:34:39<6:14:46,  1.65it/s]
 35%|███▌      | 20440/57600 [3:34:40<6:18:47,  1.64it/s]
                                                         
{'loss': 1.2361, 'learning_rate': 6.826480836236933e-07, 'epoch': 225.61}

 35%|███▌      | 20440/57600 [3:34:40<6:18:47,  1.64it/s]
 35%|███▌      | 20441/57600 [3:34:40<6:36:58,  1.56it/s]
 35%|███▌      | 20442/57600 [3:34:41<6:44:56,  1.53it/s]
 35%|███▌      | 20443/57600 [3:34:42<6:35:18,  1.57it/s]
 35%|███▌      | 20444/57600 [3:34:42<6:29:12,  1.59it/s]
 35%|███▌      | 20445/57600 [3:34:43<6:27:08,  1.60it/s]
 35%|███▌      | 20446/57600 [3:34:43<6:21:15,  1.62it/s]
 35%|███▌      | 20447/57600 [3:34:44<6:18:32,  1.64it/s]
 36%|███▌      | 20448/57600 [3:34:45<6:12:24,  1.66it/s]
 36%|███▌      | 20449/57600 [3:34:45<6:05:37,  1.69it/s]
 36%|███▌      | 20450/57600 [3:34:46<6:07:23,  1.69it/s]
 36%|███▌      | 20451/57600 [3:34:46<6:08:12,  1.68it/s]
 36%|███▌      | 20452/57600 [3:34:47<6:09:03,  1.68it/s]
 36%|███▌      | 20453/57600 [3:34:48<6:07:56,  1.68it/s]
 36%|███▌      | 20454/57600 [3:34:48<6:27:58,  1.60it/s]
 36%|███▌      | 20455/57600 [3:34:49<6:42:45,  1.54it/s]
 36%|███▌      | 20456/57600 [3:34:50<6:49:27,  1.51it/s]
 36%|███▌      | 20457/57600 [3:34:50<6:36:40,  1.56it/s]
 36%|███▌      | 20458/57600 [3:34:51<6:39:44,  1.55it/s]
 36%|███▌      | 20459/57600 [3:34:52<6:39:50,  1.55it/s]
 36%|███▌      | 20460/57600 [3:34:52<6:46:43,  1.52it/s]
                                                         
{'loss': 1.2218, 'learning_rate': 6.823344947735192e-07, 'epoch': 225.83}

 36%|███▌      | 20460/57600 [3:34:52<6:46:43,  1.52it/s]
 36%|███▌      | 20461/57600 [3:34:53<6:45:58,  1.52it/s]
 36%|███▌      | 20462/57600 [3:34:54<6:44:56,  1.53it/s]
 36%|███▌      | 20463/57600 [3:34:54<6:35:01,  1.57it/s]
 36%|███▌      | 20464/57600 [3:34:55<6:30:25,  1.59it/s]
 36%|███▌      | 20465/57600 [3:34:55<6:23:41,  1.61it/s]
 36%|███▌      | 20466/57600 [3:34:56<6:36:07,  1.56it/s]
 36%|███▌      | 20467/57600 [3:34:57<6:33:59,  1.57it/s]
 36%|███▌      | 20468/57600 [3:34:57<6:35:40,  1.56it/s]
 36%|███▌      | 20469/57600 [3:34:58<6:21:08,  1.62it/s]
 36%|███▌      | 20470/57600 [3:34:58<6:19:29,  1.63it/s]
 36%|███▌      | 20471/57600 [3:34:59<6:14:41,  1.65it/s]
 36%|███▌      | 20472/57600 [3:35:00<6:08:15,  1.68it/s]
 36%|███▌      | 20473/57600 [3:35:00<6:04:57,  1.70it/s]
 36%|███▌      | 20474/57600 [3:35:01<6:21:48,  1.62it/s]
 36%|███▌      | 20475/57600 [3:35:01<6:09:03,  1.68it/s]
 36%|███▌      | 20476/57600 [3:35:02<6:25:50,  1.60it/s]
 36%|███▌      | 20477/57600 [3:35:03<6:41:01,  1.54it/s]
 36%|███▌      | 20478/57600 [3:35:04<6:50:46,  1.51it/s]
 36%|███▌      | 20479/57600 [3:35:04<6:34:22,  1.57it/s]
 36%|███▌      | 20480/57600 [3:35:05<6:35:13,  1.57it/s]
                                                         
{'loss': 1.2405, 'learning_rate': 6.820209059233449e-07, 'epoch': 226.05}

 36%|███▌      | 20480/57600 [3:35:05<6:35:13,  1.57it/s]
 36%|███▌      | 20481/57600 [3:35:05<6:24:58,  1.61it/s]
 36%|███▌      | 20482/57600 [3:35:06<6:30:36,  1.58it/s]
 36%|███▌      | 20483/57600 [3:35:07<6:20:57,  1.62it/s]
 36%|███▌      | 20484/57600 [3:35:07<6:10:00,  1.67it/s]
 36%|███▌      | 20485/57600 [3:35:08<6:09:05,  1.68it/s]
 36%|███▌      | 20486/57600 [3:35:08<6:09:47,  1.67it/s]
 36%|███▌      | 20487/57600 [3:35:09<6:03:49,  1.70it/s]
 36%|███▌      | 20488/57600 [3:35:09<6:08:28,  1.68it/s]
 36%|███▌      | 20489/57600 [3:35:10<6:10:24,  1.67it/s]
 36%|███▌      | 20490/57600 [3:35:11<6:39:41,  1.55it/s]
 36%|███▌      | 20491/57600 [3:35:11<6:30:38,  1.58it/s]
 36%|███▌      | 20492/57600 [3:35:12<6:18:54,  1.63it/s]
 36%|███▌      | 20493/57600 [3:35:13<6:24:00,  1.61it/s]
 36%|███▌      | 20494/57600 [3:35:13<6:27:38,  1.60it/s]
 36%|███▌      | 20495/57600 [3:35:14<6:16:44,  1.64it/s]
 36%|███▌      | 20496/57600 [3:35:14<6:16:30,  1.64it/s]
 36%|███▌      | 20497/57600 [3:35:15<6:21:20,  1.62it/s]
 36%|███▌      | 20498/57600 [3:35:16<6:48:42,  1.51it/s]
 36%|███▌      | 20499/57600 [3:35:16<6:33:00,  1.57it/s]
 36%|███▌      | 20500/57600 [3:35:17<6:43:10,  1.53it/s]
                                                         
{'loss': 1.2829, 'learning_rate': 6.817073170731707e-07, 'epoch': 226.27}

 36%|███▌      | 20500/57600 [3:35:17<6:43:10,  1.53it/s]
 36%|███▌      | 20501/57600 [3:35:18<6:35:49,  1.56it/s]
 36%|███▌      | 20502/57600 [3:35:18<6:30:55,  1.58it/s]
 36%|███▌      | 20503/57600 [3:35:19<6:27:56,  1.59it/s]
 36%|███▌      | 20504/57600 [3:35:20<6:30:32,  1.58it/s]
 36%|███▌      | 20505/57600 [3:35:20<6:32:10,  1.58it/s]
 36%|███▌      | 20506/57600 [3:35:21<6:23:13,  1.61it/s]
 36%|███▌      | 20507/57600 [3:35:21<6:27:21,  1.60it/s]
 36%|███▌      | 20508/57600 [3:35:22<6:22:38,  1.62it/s]
 36%|███▌      | 20509/57600 [3:35:23<6:11:45,  1.66it/s]
 36%|███▌      | 20510/57600 [3:35:23<6:16:19,  1.64it/s]
 36%|███▌      | 20511/57600 [3:35:24<6:11:30,  1.66it/s]
 36%|███▌      | 20512/57600 [3:35:24<6:05:09,  1.69it/s]
 36%|███▌      | 20513/57600 [3:35:25<6:18:53,  1.63it/s]
 36%|███▌      | 20514/57600 [3:35:26<6:15:22,  1.65it/s]
 36%|███▌      | 20515/57600 [3:35:26<6:13:17,  1.66it/s]
 36%|███▌      | 20516/57600 [3:35:27<6:23:00,  1.61it/s]
 36%|███▌      | 20517/57600 [3:35:28<6:30:51,  1.58it/s]
 36%|███▌      | 20518/57600 [3:35:28<6:22:23,  1.62it/s]
 36%|███▌      | 20519/57600 [3:35:29<6:29:25,  1.59it/s]
 36%|███▌      | 20520/57600 [3:35:30<6:44:14,  1.53it/s]
                                                         
{'loss': 1.2286, 'learning_rate': 6.813937282229965e-07, 'epoch': 226.49}

 36%|███▌      | 20520/57600 [3:35:30<6:44:14,  1.53it/s]
 36%|███▌      | 20521/57600 [3:35:30<6:25:55,  1.60it/s]
 36%|███▌      | 20522/57600 [3:35:31<6:20:21,  1.62it/s]
 36%|███▌      | 20523/57600 [3:35:31<6:25:58,  1.60it/s]
 36%|███▌      | 20524/57600 [3:35:32<6:25:00,  1.60it/s]
 36%|███▌      | 20525/57600 [3:35:33<6:42:17,  1.54it/s]
 36%|███▌      | 20526/57600 [3:35:33<6:39:46,  1.55it/s]
 36%|███▌      | 20527/57600 [3:35:34<6:25:54,  1.60it/s]
 36%|███▌      | 20528/57600 [3:35:35<6:31:39,  1.58it/s]
 36%|███▌      | 20529/57600 [3:35:35<6:32:57,  1.57it/s]
 36%|███▌      | 20530/57600 [3:35:36<6:36:39,  1.56it/s]
 36%|███▌      | 20531/57600 [3:35:36<6:21:50,  1.62it/s]
 36%|███▌      | 20532/57600 [3:35:37<6:12:28,  1.66it/s]
 36%|███▌      | 20533/57600 [3:35:38<6:06:05,  1.69it/s]
 36%|███▌      | 20534/57600 [3:35:38<6:18:53,  1.63it/s]
 36%|███▌      | 20535/57600 [3:35:39<6:23:45,  1.61it/s]
 36%|███▌      | 20536/57600 [3:35:39<6:15:42,  1.64it/s]
 36%|███▌      | 20537/57600 [3:35:40<6:19:57,  1.63it/s]
 36%|███▌      | 20538/57600 [3:35:41<6:13:06,  1.66it/s]
 36%|███▌      | 20539/57600 [3:35:41<6:11:03,  1.66it/s]
 36%|███▌      | 20540/57600 [3:35:42<6:12:30,  1.66it/s]
                                                         
{'loss': 1.2402, 'learning_rate': 6.810801393728223e-07, 'epoch': 226.71}

 36%|███▌      | 20540/57600 [3:35:42<6:12:30,  1.66it/s]
 36%|███▌      | 20541/57600 [3:35:42<6:19:35,  1.63it/s]
 36%|███▌      | 20542/57600 [3:35:43<6:24:13,  1.61it/s]
 36%|███▌      | 20543/57600 [3:35:44<6:36:07,  1.56it/s]
 36%|███▌      | 20544/57600 [3:35:44<6:30:52,  1.58it/s]
 36%|███▌      | 20545/57600 [3:35:45<6:25:22,  1.60it/s]
 36%|███▌      | 20546/57600 [3:35:46<6:12:55,  1.66it/s]
 36%|███▌      | 20547/57600 [3:35:46<6:14:05,  1.65it/s]
 36%|███▌      | 20548/57600 [3:35:47<6:23:15,  1.61it/s]
 36%|███▌      | 20549/57600 [3:35:48<6:35:21,  1.56it/s]
 36%|███▌      | 20550/57600 [3:35:48<6:27:31,  1.59it/s]
 36%|███▌      | 20551/57600 [3:35:49<6:12:40,  1.66it/s]
 36%|███▌      | 20552/57600 [3:35:49<6:25:47,  1.60it/s]
 36%|███▌      | 20553/57600 [3:35:50<6:20:44,  1.62it/s]
 36%|███▌      | 20554/57600 [3:35:50<6:09:55,  1.67it/s]
 36%|███▌      | 20555/57600 [3:35:51<6:03:02,  1.70it/s]
 36%|███▌      | 20556/57600 [3:35:52<6:11:17,  1.66it/s]
 36%|███▌      | 20557/57600 [3:35:52<6:08:44,  1.67it/s]
 36%|███▌      | 20558/57600 [3:35:53<6:00:45,  1.71it/s]
 36%|███▌      | 20559/57600 [3:35:53<6:11:52,  1.66it/s]
 36%|███▌      | 20560/57600 [3:35:54<6:19:49,  1.63it/s]
                                                         
{'loss': 1.2534, 'learning_rate': 6.80766550522648e-07, 'epoch': 226.93}

 36%|███▌      | 20560/57600 [3:35:54<6:19:49,  1.63it/s]
 36%|███▌      | 20561/57600 [3:35:55<6:24:08,  1.61it/s]
 36%|███▌      | 20562/57600 [3:35:55<6:21:16,  1.62it/s]
 36%|███▌      | 20563/57600 [3:35:56<6:27:58,  1.59it/s]
 36%|███▌      | 20564/57600 [3:35:57<6:17:56,  1.63it/s]
 36%|███▌      | 20565/57600 [3:35:57<6:21:51,  1.62it/s]
 36%|███▌      | 20566/57600 [3:35:58<6:13:30,  1.65it/s]
 36%|███▌      | 20567/57600 [3:35:59<6:48:55,  1.51it/s]
 36%|███▌      | 20568/57600 [3:35:59<6:38:23,  1.55it/s]
 36%|███▌      | 20569/57600 [3:36:00<6:36:37,  1.56it/s]
 36%|███▌      | 20570/57600 [3:36:00<6:31:27,  1.58it/s]
 36%|███▌      | 20571/57600 [3:36:01<6:21:52,  1.62it/s]
 36%|███▌      | 20572/57600 [3:36:02<6:21:25,  1.62it/s]
 36%|███▌      | 20573/57600 [3:36:02<6:21:14,  1.62it/s]
 36%|███▌      | 20574/57600 [3:36:03<6:16:47,  1.64it/s]
 36%|███▌      | 20575/57600 [3:36:04<6:25:04,  1.60it/s]
 36%|███▌      | 20576/57600 [3:36:04<6:12:16,  1.66it/s]
 36%|███▌      | 20577/57600 [3:36:05<6:12:41,  1.66it/s]
 36%|███▌      | 20578/57600 [3:36:05<6:20:54,  1.62it/s]
 36%|███▌      | 20579/57600 [3:36:06<6:13:13,  1.65it/s]
 36%|███▌      | 20580/57600 [3:36:06<6:12:02,  1.66it/s]
                                                         
{'loss': 1.2742, 'learning_rate': 6.804529616724738e-07, 'epoch': 227.15}

 36%|███▌      | 20580/57600 [3:36:06<6:12:02,  1.66it/s]
 36%|███▌      | 20581/57600 [3:36:07<6:11:27,  1.66it/s]
 36%|███▌      | 20582/57600 [3:36:08<6:17:16,  1.64it/s]
 36%|███▌      | 20583/57600 [3:36:08<6:13:54,  1.65it/s]
 36%|███▌      | 20584/57600 [3:36:09<6:03:55,  1.70it/s]
 36%|███▌      | 20585/57600 [3:36:09<6:03:12,  1.70it/s]
 36%|███▌      | 20586/57600 [3:36:10<6:05:42,  1.69it/s]
 36%|███▌      | 20587/57600 [3:36:11<5:58:53,  1.72it/s]
 36%|███▌      | 20588/57600 [3:36:11<6:00:19,  1.71it/s]
 36%|███▌      | 20589/57600 [3:36:12<6:00:57,  1.71it/s]
 36%|███▌      | 20590/57600 [3:36:12<6:02:18,  1.70it/s]
 36%|███▌      | 20591/57600 [3:36:13<6:02:29,  1.70it/s]
 36%|███▌      | 20592/57600 [3:36:14<6:16:40,  1.64it/s]
 36%|███▌      | 20593/57600 [3:36:14<6:18:29,  1.63it/s]
 36%|███▌      | 20594/57600 [3:36:15<6:23:14,  1.61it/s]
 36%|███▌      | 20595/57600 [3:36:16<6:28:46,  1.59it/s]
 36%|███▌      | 20596/57600 [3:36:16<6:38:40,  1.55it/s]
 36%|███▌      | 20597/57600 [3:36:17<6:23:03,  1.61it/s]
 36%|███▌      | 20598/57600 [3:36:17<6:13:27,  1.65it/s]
 36%|███▌      | 20599/57600 [3:36:18<6:20:10,  1.62it/s]
 36%|███▌      | 20600/57600 [3:36:19<6:16:31,  1.64it/s]
                                                         
{'loss': 1.2341, 'learning_rate': 6.801393728222996e-07, 'epoch': 227.37}

 36%|███▌      | 20600/57600 [3:36:19<6:16:31,  1.64it/s]
 36%|███▌      | 20601/57600 [3:36:19<6:03:06,  1.70it/s]
 36%|███▌      | 20602/57600 [3:36:20<6:01:47,  1.70it/s]
 36%|███▌      | 20603/57600 [3:36:20<5:57:38,  1.72it/s]
 36%|███▌      | 20604/57600 [3:36:21<6:23:21,  1.61it/s]
 36%|███▌      | 20605/57600 [3:36:22<6:31:28,  1.58it/s]
 36%|███▌      | 20606/57600 [3:36:22<6:16:42,  1.64it/s]
 36%|███▌      | 20607/57600 [3:36:23<6:20:05,  1.62it/s]
 36%|███▌      | 20608/57600 [3:36:23<6:12:54,  1.65it/s]
 36%|███▌      | 20609/57600 [3:36:24<6:16:21,  1.64it/s]
 36%|███▌      | 20610/57600 [3:36:25<6:13:27,  1.65it/s]
 36%|███▌      | 20611/57600 [3:36:25<6:06:36,  1.68it/s]
 36%|███▌      | 20612/57600 [3:36:26<6:02:03,  1.70it/s]
 36%|███▌      | 20613/57600 [3:36:26<6:18:51,  1.63it/s]
 36%|███▌      | 20614/57600 [3:36:27<6:27:51,  1.59it/s]
 36%|███▌      | 20615/57600 [3:36:28<6:20:33,  1.62it/s]
 36%|███▌      | 20616/57600 [3:36:28<6:11:58,  1.66it/s]
 36%|███▌      | 20617/57600 [3:36:29<6:14:13,  1.65it/s]
 36%|███▌      | 20618/57600 [3:36:30<6:15:37,  1.64it/s]
 36%|███▌      | 20619/57600 [3:36:30<6:25:16,  1.60it/s]
 36%|███▌      | 20620/57600 [3:36:31<6:34:53,  1.56it/s]
                                                         
{'loss': 1.2615, 'learning_rate': 6.798257839721254e-07, 'epoch': 227.59}

 36%|███▌      | 20620/57600 [3:36:31<6:34:53,  1.56it/s]
 36%|███▌      | 20621/57600 [3:36:31<6:26:42,  1.59it/s]
 36%|███▌      | 20622/57600 [3:36:32<6:11:29,  1.66it/s]
 36%|███▌      | 20623/57600 [3:36:33<6:18:01,  1.63it/s]
 36%|███▌      | 20624/57600 [3:36:33<6:22:31,  1.61it/s]
 36%|███▌      | 20625/57600 [3:36:34<6:11:37,  1.66it/s]
 36%|███▌      | 20626/57600 [3:36:34<6:18:43,  1.63it/s]
 36%|███▌      | 20627/57600 [3:36:35<6:14:27,  1.65it/s]
 36%|███▌      | 20628/57600 [3:36:36<6:28:24,  1.59it/s]
 36%|███▌      | 20629/57600 [3:36:36<6:28:47,  1.58it/s]
 36%|███▌      | 20630/57600 [3:36:37<6:29:26,  1.58it/s]
 36%|███▌      | 20631/57600 [3:36:38<6:18:06,  1.63it/s]
 36%|███▌      | 20632/57600 [3:36:38<6:24:56,  1.60it/s]
 36%|███▌      | 20633/57600 [3:36:39<6:32:48,  1.57it/s]
 36%|███▌      | 20634/57600 [3:36:40<6:28:45,  1.58it/s]
 36%|███▌      | 20635/57600 [3:36:40<6:23:37,  1.61it/s]
 36%|███▌      | 20636/57600 [3:36:41<6:12:10,  1.66it/s]
 36%|███▌      | 20637/57600 [3:36:41<6:12:59,  1.65it/s]
 36%|███▌      | 20638/57600 [3:36:42<6:30:22,  1.58it/s]
 36%|███▌      | 20639/57600 [3:36:43<6:30:13,  1.58it/s]
 36%|███▌      | 20640/57600 [3:36:43<6:29:55,  1.58it/s]
                                                         
{'loss': 1.239, 'learning_rate': 6.795121951219512e-07, 'epoch': 227.81}

 36%|███▌      | 20640/57600 [3:36:43<6:29:55,  1.58it/s]
 36%|███▌      | 20641/57600 [3:36:44<6:22:22,  1.61it/s]
 36%|███▌      | 20642/57600 [3:36:44<6:20:25,  1.62it/s]
 36%|███▌      | 20643/57600 [3:36:45<6:17:09,  1.63it/s]
 36%|███▌      | 20644/57600 [3:36:46<6:22:32,  1.61it/s]
 36%|███▌      | 20645/57600 [3:36:46<6:30:15,  1.58it/s]
 36%|███▌      | 20646/57600 [3:36:47<6:39:38,  1.54it/s]
 36%|███▌      | 20647/57600 [3:36:48<6:35:46,  1.56it/s]
 36%|███▌      | 20648/57600 [3:36:48<6:30:58,  1.58it/s]
 36%|███▌      | 20649/57600 [3:36:49<6:27:33,  1.59it/s]
 36%|███▌      | 20650/57600 [3:36:50<6:19:14,  1.62it/s]
 36%|███▌      | 20651/57600 [3:36:50<6:25:19,  1.60it/s]
 36%|███▌      | 20652/57600 [3:36:51<6:27:06,  1.59it/s]
 36%|███▌      | 20653/57600 [3:36:51<6:32:46,  1.57it/s]
 36%|███▌      | 20654/57600 [3:36:52<6:25:17,  1.60it/s]
 36%|███▌      | 20655/57600 [3:36:53<6:24:15,  1.60it/s]
 36%|███▌      | 20656/57600 [3:36:53<6:23:33,  1.61it/s]
 36%|███▌      | 20657/57600 [3:36:54<6:45:15,  1.52it/s]
 36%|███▌      | 20658/57600 [3:36:55<6:28:43,  1.58it/s]
 36%|███▌      | 20659/57600 [3:36:55<6:32:32,  1.57it/s]
 36%|███▌      | 20660/57600 [3:36:56<6:26:02,  1.59it/s]
                                                         
{'loss': 1.2177, 'learning_rate': 6.791986062717771e-07, 'epoch': 228.04}

 36%|███▌      | 20660/57600 [3:36:56<6:26:02,  1.59it/s]
 36%|███▌      | 20661/57600 [3:36:56<6:25:30,  1.60it/s]
 36%|███▌      | 20662/57600 [3:36:57<6:21:25,  1.61it/s]
 36%|███▌      | 20663/57600 [3:36:58<6:35:16,  1.56it/s]
 36%|███▌      | 20664/57600 [3:36:58<6:33:26,  1.56it/s]
 36%|███▌      | 20665/57600 [3:36:59<6:43:56,  1.52it/s]
 36%|███▌      | 20666/57600 [3:37:00<6:36:34,  1.55it/s]
 36%|███▌      | 20667/57600 [3:37:00<6:31:47,  1.57it/s]
 36%|███▌      | 20668/57600 [3:37:01<6:24:41,  1.60it/s]
 36%|███▌      | 20669/57600 [3:37:02<6:21:49,  1.61it/s]
 36%|███▌      | 20670/57600 [3:37:02<6:20:25,  1.62it/s]
 36%|███▌      | 20671/57600 [3:37:03<6:22:18,  1.61it/s]
 36%|███▌      | 20672/57600 [3:37:03<6:29:23,  1.58it/s]
 36%|███▌      | 20673/57600 [3:37:04<6:30:11,  1.58it/s]
 36%|███▌      | 20674/57600 [3:37:05<6:33:24,  1.56it/s]
 36%|███▌      | 20675/57600 [3:37:05<6:47:10,  1.51it/s]
 36%|███▌      | 20676/57600 [3:37:06<6:48:53,  1.51it/s]
 36%|███▌      | 20677/57600 [3:37:07<6:36:31,  1.55it/s]
 36%|███▌      | 20678/57600 [3:37:07<6:45:09,  1.52it/s]
 36%|███▌      | 20679/57600 [3:37:08<6:33:38,  1.56it/s]
 36%|███▌      | 20680/57600 [3:37:09<6:31:23,  1.57it/s]
                                                         
{'loss': 1.1791, 'learning_rate': 6.788850174216028e-07, 'epoch': 228.26}

 36%|███▌      | 20680/57600 [3:37:09<6:31:23,  1.57it/s]
 36%|███▌      | 20681/57600 [3:37:09<6:33:04,  1.57it/s]
 36%|███▌      | 20682/57600 [3:37:10<6:19:20,  1.62it/s]
 36%|███▌      | 20683/57600 [3:37:10<6:19:04,  1.62it/s]
 36%|███▌      | 20684/57600 [3:37:11<6:16:19,  1.63it/s]
 36%|███▌      | 20685/57600 [3:37:12<6:44:56,  1.52it/s]
 36%|███▌      | 20686/57600 [3:37:12<6:32:04,  1.57it/s]
 36%|███▌      | 20687/57600 [3:37:13<6:34:30,  1.56it/s]
 36%|███▌      | 20688/57600 [3:37:14<6:26:30,  1.59it/s]
 36%|███▌      | 20689/57600 [3:37:14<6:27:24,  1.59it/s]
 36%|███▌      | 20690/57600 [3:37:15<6:26:03,  1.59it/s]
 36%|███▌      | 20691/57600 [3:37:15<6:16:30,  1.63it/s]
 36%|███▌      | 20692/57600 [3:37:16<6:20:45,  1.62it/s]
 36%|███▌      | 20693/57600 [3:37:17<6:22:56,  1.61it/s]
 36%|███▌      | 20694/57600 [3:37:17<6:19:36,  1.62it/s]
 36%|███▌      | 20695/57600 [3:37:18<6:17:29,  1.63it/s]
 36%|███▌      | 20696/57600 [3:37:19<6:23:20,  1.60it/s]
 36%|███▌      | 20697/57600 [3:37:19<6:20:16,  1.62it/s]
 36%|███▌      | 20698/57600 [3:37:20<6:22:31,  1.61it/s]
 36%|███▌      | 20699/57600 [3:37:20<6:16:58,  1.63it/s]
 36%|███▌      | 20700/57600 [3:37:21<6:29:15,  1.58it/s]
                                                         
{'loss': 1.2365, 'learning_rate': 6.785714285714285e-07, 'epoch': 228.48}

 36%|███▌      | 20700/57600 [3:37:21<6:29:15,  1.58it/s]
 36%|███▌      | 20701/57600 [3:37:22<6:24:42,  1.60it/s]
 36%|███▌      | 20702/57600 [3:37:22<6:16:19,  1.63it/s]
 36%|███▌      | 20703/57600 [3:37:23<6:04:31,  1.69it/s]
 36%|███▌      | 20704/57600 [3:37:23<6:05:27,  1.68it/s]
 36%|███▌      | 20705/57600 [3:37:24<6:07:30,  1.67it/s]
 36%|███▌      | 20706/57600 [3:37:25<6:20:23,  1.62it/s]
 36%|███▌      | 20707/57600 [3:37:25<6:09:42,  1.66it/s]
 36%|███▌      | 20708/57600 [3:37:26<6:11:16,  1.66it/s]
 36%|███▌      | 20709/57600 [3:37:26<6:02:51,  1.69it/s]
 36%|███▌      | 20710/57600 [3:37:27<6:11:31,  1.65it/s]
 36%|███▌      | 20711/57600 [3:37:28<6:13:51,  1.64it/s]
 36%|███▌      | 20712/57600 [3:37:28<6:07:18,  1.67it/s]
 36%|███▌      | 20713/57600 [3:37:29<6:19:42,  1.62it/s]
 36%|███▌      | 20714/57600 [3:37:30<6:11:03,  1.66it/s]
 36%|███▌      | 20715/57600 [3:37:30<6:07:39,  1.67it/s]
 36%|███▌      | 20716/57600 [3:37:31<6:16:42,  1.63it/s]
 36%|███▌      | 20717/57600 [3:37:31<6:16:16,  1.63it/s]
 36%|███▌      | 20718/57600 [3:37:32<6:16:57,  1.63it/s]
 36%|███▌      | 20719/57600 [3:37:33<6:18:36,  1.62it/s]
 36%|███▌      | 20720/57600 [3:37:33<6:08:45,  1.67it/s]
                                                         
{'loss': 1.3025, 'learning_rate': 6.782578397212544e-07, 'epoch': 228.7}

 36%|███▌      | 20720/57600 [3:37:33<6:08:45,  1.67it/s]
 36%|███▌      | 20721/57600 [3:37:34<6:09:54,  1.66it/s]
 36%|███▌      | 20722/57600 [3:37:34<6:09:27,  1.66it/s]
 36%|███▌      | 20723/57600 [3:37:35<6:06:27,  1.68it/s]
 36%|███▌      | 20724/57600 [3:37:36<6:16:15,  1.63it/s]
 36%|███▌      | 20725/57600 [3:37:36<6:13:16,  1.65it/s]
 36%|███▌      | 20726/57600 [3:37:37<6:19:37,  1.62it/s]
 36%|███▌      | 20727/57600 [3:37:37<6:25:01,  1.60it/s]
 36%|███▌      | 20728/57600 [3:37:38<6:25:22,  1.59it/s]
 36%|███▌      | 20729/57600 [3:37:39<6:10:27,  1.66it/s]
 36%|███▌      | 20730/57600 [3:37:39<6:20:37,  1.61it/s]
 36%|███▌      | 20731/57600 [3:37:40<6:27:49,  1.58it/s]
 36%|███▌      | 20732/57600 [3:37:41<6:19:38,  1.62it/s]
 36%|███▌      | 20733/57600 [3:37:41<6:32:55,  1.56it/s]
 36%|███▌      | 20734/57600 [3:37:42<6:33:44,  1.56it/s]
 36%|███▌      | 20735/57600 [3:37:43<6:41:50,  1.53it/s]
 36%|███▌      | 20736/57600 [3:37:43<6:29:53,  1.58it/s]
 36%|███▌      | 20737/57600 [3:37:44<6:16:51,  1.63it/s]
 36%|███▌      | 20738/57600 [3:37:44<6:16:53,  1.63it/s]
 36%|███▌      | 20739/57600 [3:37:45<6:26:37,  1.59it/s]
 36%|███▌      | 20740/57600 [3:37:46<6:43:06,  1.52it/s]
                                                         
{'loss': 1.2399, 'learning_rate': 6.779442508710801e-07, 'epoch': 228.92}

 36%|███▌      | 20740/57600 [3:37:46<6:43:06,  1.52it/s]
 36%|███▌      | 20741/57600 [3:37:46<6:36:24,  1.55it/s]
 36%|███▌      | 20742/57600 [3:37:47<6:28:27,  1.58it/s]
 36%|███▌      | 20743/57600 [3:37:48<6:25:40,  1.59it/s]
 36%|███▌      | 20744/57600 [3:37:48<6:24:10,  1.60it/s]
 36%|███▌      | 20745/57600 [3:37:49<6:31:04,  1.57it/s]
 36%|███▌      | 20746/57600 [3:37:49<6:16:15,  1.63it/s]
 36%|███▌      | 20747/57600 [3:37:50<6:14:43,  1.64it/s]
 36%|███▌      | 20748/57600 [3:37:51<6:40:24,  1.53it/s]
 36%|███▌      | 20749/57600 [3:37:51<6:42:42,  1.53it/s]
 36%|███▌      | 20750/57600 [3:37:52<6:29:45,  1.58it/s]
 36%|███▌      | 20751/57600 [3:37:53<6:27:29,  1.58it/s]
 36%|███▌      | 20752/57600 [3:37:53<6:29:48,  1.58it/s]
 36%|███▌      | 20753/57600 [3:37:54<6:26:48,  1.59it/s]
 36%|███▌      | 20754/57600 [3:37:55<6:24:45,  1.60it/s]
 36%|███▌      | 20755/57600 [3:37:55<6:17:53,  1.63it/s]
 36%|███▌      | 20756/57600 [3:37:56<6:29:03,  1.58it/s]
 36%|███▌      | 20757/57600 [3:37:56<6:20:22,  1.61it/s]
 36%|███▌      | 20758/57600 [3:37:57<6:30:58,  1.57it/s]
 36%|███▌      | 20759/57600 [3:37:58<6:14:08,  1.64it/s]
 36%|███▌      | 20760/57600 [3:37:58<6:05:41,  1.68it/s]
                                                         
{'loss': 1.2693, 'learning_rate': 6.776306620209059e-07, 'epoch': 229.14}

 36%|███▌      | 20760/57600 [3:37:58<6:05:41,  1.68it/s]
 36%|███▌      | 20761/57600 [3:37:59<5:58:25,  1.71it/s]
 36%|███▌      | 20762/57600 [3:37:59<6:26:04,  1.59it/s]
 36%|███▌      | 20763/57600 [3:38:00<6:36:14,  1.55it/s]
 36%|███▌      | 20764/57600 [3:38:01<6:26:37,  1.59it/s]
 36%|███▌      | 20765/57600 [3:38:01<6:28:51,  1.58it/s]
 36%|███▌      | 20766/57600 [3:38:02<6:20:51,  1.61it/s]
 36%|███▌      | 20767/57600 [3:38:03<6:26:24,  1.59it/s]
 36%|███▌      | 20768/57600 [3:38:03<6:22:18,  1.61it/s]
 36%|███▌      | 20769/57600 [3:38:04<6:21:43,  1.61it/s]
 36%|███▌      | 20770/57600 [3:38:04<6:13:44,  1.64it/s]
 36%|███▌      | 20771/57600 [3:38:05<6:04:15,  1.69it/s]
 36%|███▌      | 20772/57600 [3:38:06<6:09:10,  1.66it/s]
 36%|███▌      | 20773/57600 [3:38:06<6:13:02,  1.65it/s]
 36%|███▌      | 20774/57600 [3:38:07<6:17:55,  1.62it/s]
 36%|███▌      | 20775/57600 [3:38:07<6:05:48,  1.68it/s]
 36%|███▌      | 20776/57600 [3:38:08<6:13:51,  1.64it/s]
 36%|███▌      | 20777/57600 [3:38:09<6:18:26,  1.62it/s]
 36%|███▌      | 20778/57600 [3:38:09<6:32:27,  1.56it/s]
 36%|███▌      | 20779/57600 [3:38:10<6:44:14,  1.52it/s]
 36%|███▌      | 20780/57600 [3:38:11<6:35:20,  1.55it/s]
                                                         
{'loss': 1.2371, 'learning_rate': 6.773170731707317e-07, 'epoch': 229.36}

 36%|███▌      | 20780/57600 [3:38:11<6:35:20,  1.55it/s]
 36%|███▌      | 20781/57600 [3:38:11<6:27:57,  1.58it/s]
 36%|███▌      | 20782/57600 [3:38:12<6:16:24,  1.63it/s]
 36%|███▌      | 20783/57600 [3:38:13<6:26:05,  1.59it/s]
 36%|███▌      | 20784/57600 [3:38:13<6:34:07,  1.56it/s]
 36%|███▌      | 20785/57600 [3:38:14<6:27:45,  1.58it/s]
 36%|███▌      | 20786/57600 [3:38:14<6:21:52,  1.61it/s]
 36%|███▌      | 20787/57600 [3:38:15<6:11:57,  1.65it/s]
 36%|███▌      | 20788/57600 [3:38:16<6:21:00,  1.61it/s]
 36%|███▌      | 20789/57600 [3:38:16<6:31:36,  1.57it/s]
 36%|███▌      | 20790/57600 [3:38:17<6:21:44,  1.61it/s]
 36%|███▌      | 20791/57600 [3:38:17<6:11:34,  1.65it/s]
 36%|███▌      | 20792/57600 [3:38:18<6:08:23,  1.67it/s]
 36%|███▌      | 20793/57600 [3:38:19<6:00:31,  1.70it/s]
 36%|███▌      | 20794/57600 [3:38:19<5:58:36,  1.71it/s]
 36%|███▌      | 20795/57600 [3:38:20<6:07:57,  1.67it/s]
 36%|███▌      | 20796/57600 [3:38:20<6:21:19,  1.61it/s]
 36%|███▌      | 20797/57600 [3:38:21<6:21:51,  1.61it/s]
 36%|███▌      | 20798/57600 [3:38:22<6:28:56,  1.58it/s]
 36%|███▌      | 20799/57600 [3:38:22<6:19:04,  1.62it/s]
 36%|███▌      | 20800/57600 [3:38:23<6:10:20,  1.66it/s]
                                                         
{'loss': 1.2414, 'learning_rate': 6.770034843205575e-07, 'epoch': 229.58}

 36%|███▌      | 20800/57600 [3:38:23<6:10:20,  1.66it/s]
 36%|███▌      | 20801/57600 [3:38:24<6:14:56,  1.64it/s]
 36%|███▌      | 20802/57600 [3:38:24<6:02:21,  1.69it/s]
 36%|███▌      | 20803/57600 [3:38:25<6:11:17,  1.65it/s]
 36%|███▌      | 20804/57600 [3:38:25<6:05:36,  1.68it/s]
 36%|███▌      | 20805/57600 [3:38:26<6:12:01,  1.65it/s]
 36%|███▌      | 20806/57600 [3:38:27<6:14:40,  1.64it/s]
 36%|███▌      | 20807/57600 [3:38:27<6:04:13,  1.68it/s]
 36%|███▌      | 20808/57600 [3:38:28<6:20:17,  1.61it/s]
 36%|███▌      | 20809/57600 [3:38:28<6:11:57,  1.65it/s]
 36%|███▌      | 20810/57600 [3:38:29<6:26:22,  1.59it/s]
 36%|███▌      | 20811/57600 [3:38:30<6:30:29,  1.57it/s]
 36%|███▌      | 20812/57600 [3:38:30<6:15:19,  1.63it/s]
 36%|███▌      | 20813/57600 [3:38:31<6:21:01,  1.61it/s]
 36%|███▌      | 20814/57600 [3:38:32<6:34:51,  1.55it/s]
 36%|███▌      | 20815/57600 [3:38:32<6:37:47,  1.54it/s]
 36%|███▌      | 20816/57600 [3:38:33<6:25:16,  1.59it/s]
 36%|███▌      | 20817/57600 [3:38:33<6:23:44,  1.60it/s]
 36%|███▌      | 20818/57600 [3:38:34<6:17:52,  1.62it/s]
 36%|███▌      | 20819/57600 [3:38:35<6:11:10,  1.65it/s]
 36%|███▌      | 20820/57600 [3:38:35<6:06:34,  1.67it/s]
                                                         
{'loss': 1.2504, 'learning_rate': 6.766898954703832e-07, 'epoch': 229.8}

 36%|███▌      | 20820/57600 [3:38:35<6:06:34,  1.67it/s]
 36%|███▌      | 20821/57600 [3:38:36<6:09:10,  1.66it/s]
 36%|███▌      | 20822/57600 [3:38:36<6:05:13,  1.68it/s]
 36%|███▌      | 20823/57600 [3:38:37<6:00:19,  1.70it/s]
 36%|███▌      | 20824/57600 [3:38:38<5:52:39,  1.74it/s]
 36%|███▌      | 20825/57600 [3:38:38<6:04:28,  1.68it/s]
 36%|███▌      | 20826/57600 [3:38:39<6:01:58,  1.69it/s]
 36%|███▌      | 20827/57600 [3:38:39<6:01:30,  1.70it/s]
 36%|███▌      | 20828/57600 [3:38:40<6:01:42,  1.69it/s]
 36%|███▌      | 20829/57600 [3:38:41<6:16:07,  1.63it/s]
 36%|███▌      | 20830/57600 [3:38:41<6:18:22,  1.62it/s]
 36%|███▌      | 20831/57600 [3:38:42<6:21:14,  1.61it/s]
 36%|███▌      | 20832/57600 [3:38:42<6:13:34,  1.64it/s]
 36%|███▌      | 20833/57600 [3:38:43<6:11:26,  1.65it/s]
 36%|███▌      | 20834/57600 [3:38:44<6:23:06,  1.60it/s]
 36%|███▌      | 20835/57600 [3:38:44<6:12:55,  1.64it/s]
 36%|███▌      | 20836/57600 [3:38:45<6:13:45,  1.64it/s]
 36%|███▌      | 20837/57600 [3:38:46<6:14:43,  1.64it/s]
 36%|███▌      | 20838/57600 [3:38:46<6:21:37,  1.61it/s]
 36%|███▌      | 20839/57600 [3:38:47<6:26:57,  1.58it/s]
 36%|███▌      | 20840/57600 [3:38:47<6:27:33,  1.58it/s]
                                                         
{'loss': 1.251, 'learning_rate': 6.76376306620209e-07, 'epoch': 230.02}

 36%|███▌      | 20840/57600 [3:38:47<6:27:33,  1.58it/s]
 36%|███▌      | 20841/57600 [3:38:48<6:21:00,  1.61it/s]
 36%|███▌      | 20842/57600 [3:38:49<6:10:59,  1.65it/s]
 36%|███▌      | 20843/57600 [3:38:49<6:25:09,  1.59it/s]
 36%|███▌      | 20844/57600 [3:38:50<6:10:43,  1.65it/s]
 36%|███▌      | 20845/57600 [3:38:51<6:29:17,  1.57it/s]
 36%|███▌      | 20846/57600 [3:38:51<6:43:58,  1.52it/s]
 36%|███▌      | 20847/57600 [3:38:52<6:38:44,  1.54it/s]
 36%|███▌      | 20848/57600 [3:38:52<6:20:09,  1.61it/s]
 36%|███▌      | 20849/57600 [3:38:53<6:35:38,  1.55it/s]
 36%|███▌      | 20850/57600 [3:38:54<6:40:10,  1.53it/s]
 36%|███▌      | 20851/57600 [3:38:54<6:23:11,  1.60it/s]
 36%|███▌      | 20852/57600 [3:38:55<6:15:50,  1.63it/s]
 36%|███▌      | 20853/57600 [3:38:56<6:05:06,  1.68it/s]
 36%|███▌      | 20854/57600 [3:38:56<6:02:06,  1.69it/s]
 36%|███▌      | 20855/57600 [3:38:57<6:11:10,  1.65it/s]
 36%|███▌      | 20856/57600 [3:38:57<6:16:21,  1.63it/s]
 36%|███▌      | 20857/57600 [3:38:58<6:13:23,  1.64it/s]
 36%|███▌      | 20858/57600 [3:38:59<6:21:05,  1.61it/s]
 36%|███▌      | 20859/57600 [3:38:59<6:21:58,  1.60it/s]
 36%|███▌      | 20860/57600 [3:39:00<6:26:51,  1.58it/s]
                                                         
{'loss': 1.278, 'learning_rate': 6.760627177700348e-07, 'epoch': 230.24}

 36%|███▌      | 20860/57600 [3:39:00<6:26:51,  1.58it/s]
 36%|███▌      | 20861/57600 [3:39:00<6:19:16,  1.61it/s]
 36%|███▌      | 20862/57600 [3:39:01<6:25:20,  1.59it/s]
 36%|███▌      | 20863/57600 [3:39:02<6:33:18,  1.56it/s]
 36%|███▌      | 20864/57600 [3:39:02<6:23:56,  1.59it/s]
 36%|███▌      | 20865/57600 [3:39:03<6:23:55,  1.59it/s]
 36%|███▌      | 20866/57600 [3:39:04<6:22:59,  1.60it/s]
 36%|███▌      | 20867/57600 [3:39:04<6:18:21,  1.62it/s]
 36%|███▌      | 20868/57600 [3:39:05<6:16:44,  1.62it/s]
 36%|███▌      | 20869/57600 [3:39:06<6:37:25,  1.54it/s]
 36%|███▌      | 20870/57600 [3:39:06<6:28:54,  1.57it/s]
 36%|███▌      | 20871/57600 [3:39:07<6:27:04,  1.58it/s]
 36%|███▌      | 20872/57600 [3:39:07<6:16:32,  1.63it/s]
 36%|███▌      | 20873/57600 [3:39:08<6:11:37,  1.65it/s]
 36%|███▌      | 20874/57600 [3:39:09<6:03:48,  1.68it/s]
 36%|███▌      | 20875/57600 [3:39:09<6:02:02,  1.69it/s]
 36%|███▌      | 20876/57600 [3:39:10<6:10:58,  1.65it/s]
 36%|███▌      | 20877/57600 [3:39:10<6:07:46,  1.66it/s]
 36%|███▌      | 20878/57600 [3:39:11<6:05:09,  1.68it/s]
 36%|███▌      | 20879/57600 [3:39:12<6:30:37,  1.57it/s]
 36%|███▋      | 20880/57600 [3:39:12<6:17:27,  1.62it/s]
                                                         
{'loss': 1.2421, 'learning_rate': 6.757491289198606e-07, 'epoch': 230.46}

 36%|███▋      | 20880/57600 [3:39:12<6:17:27,  1.62it/s]
 36%|███▋      | 20881/57600 [3:39:13<6:10:49,  1.65it/s]
 36%|███▋      | 20882/57600 [3:39:13<6:16:22,  1.63it/s]
 36%|███▋      | 20883/57600 [3:39:14<6:34:07,  1.55it/s]
 36%|███▋      | 20884/57600 [3:39:15<6:24:03,  1.59it/s]
 36%|███▋      | 20885/57600 [3:39:15<6:34:47,  1.55it/s]
 36%|███▋      | 20886/57600 [3:39:16<6:35:42,  1.55it/s]
 36%|███▋      | 20887/57600 [3:39:17<6:22:00,  1.60it/s]
 36%|███▋      | 20888/57600 [3:39:17<6:16:43,  1.62it/s]
 36%|███▋      | 20889/57600 [3:39:18<6:13:13,  1.64it/s]
 36%|███▋      | 20890/57600 [3:39:18<6:13:09,  1.64it/s]
 36%|███▋      | 20891/57600 [3:39:19<6:06:43,  1.67it/s]
 36%|███▋      | 20892/57600 [3:39:20<6:04:15,  1.68it/s]
 36%|███▋      | 20893/57600 [3:39:20<6:13:40,  1.64it/s]
 36%|███▋      | 20894/57600 [3:39:21<6:11:10,  1.65it/s]
 36%|███▋      | 20895/57600 [3:39:22<6:13:55,  1.64it/s]
 36%|███▋      | 20896/57600 [3:39:22<6:25:46,  1.59it/s]
 36%|███▋      | 20897/57600 [3:39:23<6:24:23,  1.59it/s]
 36%|███▋      | 20898/57600 [3:39:23<6:26:32,  1.58it/s]
 36%|███▋      | 20899/57600 [3:39:24<6:44:18,  1.51it/s]
 36%|███▋      | 20900/57600 [3:39:25<6:37:48,  1.54it/s]
                                                         
{'loss': 1.2473, 'learning_rate': 6.754355400696864e-07, 'epoch': 230.68}

 36%|███▋      | 20900/57600 [3:39:25<6:37:48,  1.54it/s]
 36%|███▋      | 20901/57600 [3:39:25<6:40:44,  1.53it/s]
 36%|███▋      | 20902/57600 [3:39:26<6:44:17,  1.51it/s]
 36%|███▋      | 20903/57600 [3:39:27<6:33:13,  1.56it/s]
 36%|███▋      | 20904/57600 [3:39:27<6:21:09,  1.60it/s]
 36%|███▋      | 20905/57600 [3:39:28<6:17:16,  1.62it/s]
 36%|███▋      | 20906/57600 [3:39:29<6:25:46,  1.59it/s]
 36%|███▋      | 20907/57600 [3:39:29<6:23:47,  1.59it/s]
 36%|███▋      | 20908/57600 [3:39:30<6:34:48,  1.55it/s]
 36%|███▋      | 20909/57600 [3:39:31<6:35:16,  1.55it/s]
 36%|███▋      | 20910/57600 [3:39:31<6:30:17,  1.57it/s]
 36%|███▋      | 20911/57600 [3:39:32<6:23:07,  1.60it/s]
 36%|███▋      | 20912/57600 [3:39:32<6:18:05,  1.62it/s]
 36%|███▋      | 20913/57600 [3:39:33<6:16:58,  1.62it/s]
 36%|███▋      | 20914/57600 [3:39:34<6:09:12,  1.66it/s]
 36%|███▋      | 20915/57600 [3:39:34<6:18:27,  1.62it/s]
 36%|███▋      | 20916/57600 [3:39:35<6:20:25,  1.61it/s]
 36%|███▋      | 20917/57600 [3:39:35<6:28:33,  1.57it/s]
 36%|███▋      | 20918/57600 [3:39:36<6:26:40,  1.58it/s]
 36%|███▋      | 20919/57600 [3:39:37<6:24:54,  1.59it/s]
 36%|███▋      | 20920/57600 [3:39:37<6:27:53,  1.58it/s]
                                                         
{'loss': 1.2127, 'learning_rate': 6.751219512195122e-07, 'epoch': 230.91}

 36%|███▋      | 20920/57600 [3:39:37<6:27:53,  1.58it/s]
 36%|███▋      | 20921/57600 [3:39:38<6:20:24,  1.61it/s]
 36%|███▋      | 20922/57600 [3:39:39<6:12:19,  1.64it/s]
 36%|███▋      | 20923/57600 [3:39:39<6:06:11,  1.67it/s]
 36%|███▋      | 20924/57600 [3:39:40<6:12:45,  1.64it/s]
 36%|███▋      | 20925/57600 [3:39:40<6:03:59,  1.68it/s]
 36%|███▋      | 20926/57600 [3:39:41<6:02:18,  1.69it/s]
 36%|███▋      | 20927/57600 [3:39:42<6:10:30,  1.65it/s]
 36%|███▋      | 20928/57600 [3:39:42<6:04:39,  1.68it/s]
 36%|███▋      | 20929/57600 [3:39:43<6:21:29,  1.60it/s]
 36%|███▋      | 20930/57600 [3:39:43<6:15:23,  1.63it/s]
 36%|███▋      | 20931/57600 [3:39:44<6:12:06,  1.64it/s]
 36%|███▋      | 20932/57600 [3:39:45<6:17:19,  1.62it/s]
 36%|███▋      | 20933/57600 [3:39:45<6:14:52,  1.63it/s]
 36%|███▋      | 20934/57600 [3:39:46<6:26:42,  1.58it/s]
 36%|███▋      | 20935/57600 [3:39:47<6:26:42,  1.58it/s]
 36%|███▋      | 20936/57600 [3:39:47<6:37:02,  1.54it/s]
 36%|███▋      | 20937/57600 [3:39:48<6:44:11,  1.51it/s]
 36%|███▋      | 20938/57600 [3:39:49<6:45:52,  1.51it/s]
 36%|███▋      | 20939/57600 [3:39:49<6:40:22,  1.53it/s]
 36%|███▋      | 20940/57600 [3:39:50<6:24:22,  1.59it/s]
                                                         
{'loss': 1.2465, 'learning_rate': 6.74808362369338e-07, 'epoch': 231.13}

 36%|███▋      | 20940/57600 [3:39:50<6:24:22,  1.59it/s]
 36%|███▋      | 20941/57600 [3:39:50<6:29:24,  1.57it/s]
 36%|███▋      | 20942/57600 [3:39:51<6:33:57,  1.55it/s]
 36%|███▋      | 20943/57600 [3:39:52<6:32:25,  1.56it/s]
 36%|███▋      | 20944/57600 [3:39:52<6:20:33,  1.61it/s]
 36%|███▋      | 20945/57600 [3:39:53<6:10:37,  1.65it/s]
 36%|███▋      | 20946/57600 [3:39:53<6:02:31,  1.69it/s]
 36%|███▋      | 20947/57600 [3:39:54<6:02:09,  1.69it/s]
 36%|███▋      | 20948/57600 [3:39:55<5:59:56,  1.70it/s]
 36%|███▋      | 20949/57600 [3:39:55<6:18:21,  1.61it/s]
 36%|███▋      | 20950/57600 [3:39:56<6:16:38,  1.62it/s]
 36%|███▋      | 20951/57600 [3:39:57<6:16:40,  1.62it/s]
 36%|███▋      | 20952/57600 [3:39:57<6:19:35,  1.61it/s]
 36%|███▋      | 20953/57600 [3:39:58<6:13:18,  1.64it/s]
 36%|███▋      | 20954/57600 [3:39:58<6:11:26,  1.64it/s]
 36%|███▋      | 20955/57600 [3:39:59<6:10:28,  1.65it/s]
 36%|███▋      | 20956/57600 [3:40:00<6:16:09,  1.62it/s]
 36%|███▋      | 20957/57600 [3:40:00<6:22:33,  1.60it/s]
 36%|███▋      | 20958/57600 [3:40:01<6:17:01,  1.62it/s]
 36%|███▋      | 20959/57600 [3:40:02<6:21:49,  1.60it/s]
 36%|███▋      | 20960/57600 [3:40:02<6:13:44,  1.63it/s]
                                                         
{'loss': 1.238, 'learning_rate': 6.744947735191637e-07, 'epoch': 231.35}

 36%|███▋      | 20960/57600 [3:40:02<6:13:44,  1.63it/s]
 36%|███▋      | 20961/57600 [3:40:03<6:13:00,  1.64it/s]
 36%|███▋      | 20962/57600 [3:40:03<6:22:51,  1.59it/s]
 36%|███▋      | 20963/57600 [3:40:04<6:18:47,  1.61it/s]
 36%|███▋      | 20964/57600 [3:40:05<6:17:29,  1.62it/s]
 36%|███▋      | 20965/57600 [3:40:05<6:09:05,  1.65it/s]
 36%|███▋      | 20966/57600 [3:40:06<6:14:24,  1.63it/s]
 36%|███▋      | 20967/57600 [3:40:06<6:10:59,  1.65it/s]
 36%|███▋      | 20968/57600 [3:40:07<6:17:30,  1.62it/s]
 36%|███▋      | 20969/57600 [3:40:08<6:04:19,  1.68it/s]
 36%|███▋      | 20970/57600 [3:40:08<6:03:57,  1.68it/s]
 36%|███▋      | 20971/57600 [3:40:09<5:59:55,  1.70it/s]
 36%|███▋      | 20972/57600 [3:40:09<6:11:57,  1.64it/s]
 36%|███▋      | 20973/57600 [3:40:10<6:21:29,  1.60it/s]
 36%|███▋      | 20974/57600 [3:40:11<6:24:55,  1.59it/s]
 36%|███▋      | 20975/57600 [3:40:11<6:16:18,  1.62it/s]
 36%|███▋      | 20976/57600 [3:40:12<6:08:25,  1.66it/s]
 36%|███▋      | 20977/57600 [3:40:13<6:19:46,  1.61it/s]
 36%|███▋      | 20978/57600 [3:40:13<6:11:08,  1.64it/s]
 36%|███▋      | 20979/57600 [3:40:14<6:02:08,  1.69it/s]
 36%|███▋      | 20980/57600 [3:40:14<6:03:09,  1.68it/s]
                                                         
{'loss': 1.2301, 'learning_rate': 6.741811846689895e-07, 'epoch': 231.57}

 36%|███▋      | 20980/57600 [3:40:14<6:03:09,  1.68it/s]
 36%|███▋      | 20981/57600 [3:40:15<6:06:31,  1.67it/s]
 36%|███▋      | 20982/57600 [3:40:16<6:21:24,  1.60it/s]
 36%|███▋      | 20983/57600 [3:40:16<6:31:58,  1.56it/s]
 36%|███▋      | 20984/57600 [3:40:17<6:41:43,  1.52it/s]
 36%|███▋      | 20985/57600 [3:40:18<6:43:56,  1.51it/s]
 36%|███▋      | 20986/57600 [3:40:18<6:46:35,  1.50it/s]
 36%|███▋      | 20987/57600 [3:40:19<6:38:24,  1.53it/s]
 36%|███▋      | 20988/57600 [3:40:20<6:43:42,  1.51it/s]
 36%|███▋      | 20989/57600 [3:40:20<6:35:21,  1.54it/s]
 36%|███▋      | 20990/57600 [3:40:21<6:41:01,  1.52it/s]
 36%|███▋      | 20991/57600 [3:40:21<6:20:46,  1.60it/s]
 36%|███▋      | 20992/57600 [3:40:22<6:19:35,  1.61it/s]
 36%|███▋      | 20993/57600 [3:40:23<6:09:23,  1.65it/s]
 36%|███▋      | 20994/57600 [3:40:23<6:13:49,  1.63it/s]
 36%|███▋      | 20995/57600 [3:40:24<6:10:38,  1.65it/s]
 36%|███▋      | 20996/57600 [3:40:24<6:13:22,  1.63it/s]
 36%|███▋      | 20997/57600 [3:40:25<6:20:15,  1.60it/s]
 36%|███▋      | 20998/57600 [3:40:26<6:12:48,  1.64it/s]
 36%|███▋      | 20999/57600 [3:40:26<6:15:18,  1.63it/s]
 36%|███▋      | 21000/57600 [3:40:27<6:13:20,  1.63it/s]
                                                         
{'loss': 1.2398, 'learning_rate': 6.738675958188153e-07, 'epoch': 231.79}

 36%|███▋      | 21000/57600 [3:40:27<6:13:20,  1.63it/s]
 36%|███▋      | 21001/57600 [3:40:28<6:24:19,  1.59it/s]
 36%|███▋      | 21002/57600 [3:40:28<6:25:55,  1.58it/s]
 36%|███▋      | 21003/57600 [3:40:29<6:16:31,  1.62it/s]
 36%|███▋      | 21004/57600 [3:40:29<6:15:38,  1.62it/s]
 36%|███▋      | 21005/57600 [3:40:30<6:21:25,  1.60it/s]
 36%|███▋      | 21006/57600 [3:40:31<6:13:29,  1.63it/s]
 36%|███▋      | 21007/57600 [3:40:31<6:07:30,  1.66it/s]
 36%|███▋      | 21008/57600 [3:40:32<6:11:49,  1.64it/s]
 36%|███▋      | 21009/57600 [3:40:32<6:10:15,  1.65it/s]
 36%|███▋      | 21010/57600 [3:40:33<6:20:03,  1.60it/s]
 36%|███▋      | 21011/57600 [3:40:34<6:12:40,  1.64it/s]
 36%|███▋      | 21012/57600 [3:40:34<6:14:26,  1.63it/s]
 36%|███▋      | 21013/57600 [3:40:35<6:06:54,  1.66it/s]
 36%|███▋      | 21014/57600 [3:40:36<6:05:30,  1.67it/s]
 36%|███▋      | 21015/57600 [3:40:36<6:07:28,  1.66it/s]
 36%|███▋      | 21016/57600 [3:40:37<6:08:44,  1.65it/s]
 36%|███▋      | 21017/57600 [3:40:37<6:22:24,  1.59it/s]
 36%|███▋      | 21018/57600 [3:40:38<6:28:12,  1.57it/s]
 36%|███▋      | 21019/57600 [3:40:39<6:35:20,  1.54it/s]
 36%|███▋      | 21020/57600 [3:40:39<6:42:51,  1.51it/s]
                                                         
{'loss': 1.2685, 'learning_rate': 6.735540069686411e-07, 'epoch': 232.01}

 36%|███▋      | 21020/57600 [3:40:39<6:42:51,  1.51it/s]
 36%|███▋      | 21021/57600 [3:40:40<6:25:23,  1.58it/s]
 36%|███▋      | 21022/57600 [3:40:41<6:25:57,  1.58it/s]
 36%|███▋      | 21023/57600 [3:40:41<6:30:08,  1.56it/s]
 36%|███▋      | 21024/57600 [3:40:42<6:31:58,  1.56it/s]
 37%|███▋      | 21025/57600 [3:40:43<6:20:50,  1.60it/s]
 37%|███▋      | 21026/57600 [3:40:43<6:14:10,  1.63it/s]
 37%|███▋      | 21027/57600 [3:40:44<6:13:37,  1.63it/s]
 37%|███▋      | 21028/57600 [3:40:44<6:19:59,  1.60it/s]
 37%|███▋      | 21029/57600 [3:40:45<6:19:12,  1.61it/s]
 37%|███▋      | 21030/57600 [3:40:46<6:26:17,  1.58it/s]
 37%|███▋      | 21031/57600 [3:40:46<6:33:45,  1.55it/s]
 37%|███▋      | 21032/57600 [3:40:47<6:35:34,  1.54it/s]
 37%|███▋      | 21033/57600 [3:40:48<6:33:34,  1.55it/s]
 37%|███▋      | 21034/57600 [3:40:48<6:23:00,  1.59it/s]
 37%|███▋      | 21035/57600 [3:40:49<6:31:03,  1.56it/s]
 37%|███▋      | 21036/57600 [3:40:49<6:22:14,  1.59it/s]
 37%|███▋      | 21037/57600 [3:40:50<6:22:21,  1.59it/s]
 37%|███▋      | 21038/57600 [3:40:51<6:34:19,  1.55it/s]
 37%|███▋      | 21039/57600 [3:40:51<6:17:06,  1.62it/s]
 37%|███▋      | 21040/57600 [3:40:52<6:22:32,  1.59it/s]
                                                         
{'loss': 1.2084, 'learning_rate': 6.732404181184668e-07, 'epoch': 232.23}

 37%|███▋      | 21040/57600 [3:40:52<6:22:32,  1.59it/s]
 37%|███▋      | 21041/57600 [3:40:53<6:13:31,  1.63it/s]
 37%|███▋      | 21042/57600 [3:40:53<6:11:01,  1.64it/s]
 37%|███▋      | 21043/57600 [3:40:54<6:06:04,  1.66it/s]
 37%|███▋      | 21044/57600 [3:40:54<6:16:42,  1.62it/s]
 37%|███▋      | 21045/57600 [3:40:55<6:21:25,  1.60it/s]
 37%|███▋      | 21046/57600 [3:40:56<6:13:18,  1.63it/s]
 37%|███▋      | 21047/57600 [3:40:56<6:24:48,  1.58it/s]
 37%|███▋      | 21048/57600 [3:40:57<6:27:39,  1.57it/s]
 37%|███▋      | 21049/57600 [3:40:58<6:17:30,  1.61it/s]
 37%|███▋      | 21050/57600 [3:40:58<6:12:00,  1.64it/s]
 37%|███▋      | 21051/57600 [3:40:59<6:16:42,  1.62it/s]
 37%|███▋      | 21052/57600 [3:40:59<6:14:05,  1.63it/s]
 37%|███▋      | 21053/57600 [3:41:00<6:16:20,  1.62it/s]
 37%|███▋      | 21054/57600 [3:41:01<6:18:15,  1.61it/s]
 37%|███▋      | 21055/57600 [3:41:01<6:20:04,  1.60it/s]
 37%|███▋      | 21056/57600 [3:41:02<6:17:20,  1.61it/s]
 37%|███▋      | 21057/57600 [3:41:03<6:38:11,  1.53it/s]
 37%|███▋      | 21058/57600 [3:41:03<6:35:23,  1.54it/s]
 37%|███▋      | 21059/57600 [3:41:04<6:23:18,  1.59it/s]
 37%|███▋      | 21060/57600 [3:41:04<6:14:31,  1.63it/s]
                                                         
{'loss': 1.2448, 'learning_rate': 6.729268292682927e-07, 'epoch': 232.45}

 37%|███▋      | 21060/57600 [3:41:04<6:14:31,  1.63it/s]
 37%|███▋      | 21061/57600 [3:41:05<6:17:28,  1.61it/s]
 37%|███▋      | 21062/57600 [3:41:06<6:15:07,  1.62it/s]
 37%|███▋      | 21063/57600 [3:41:06<6:16:31,  1.62it/s]
 37%|███▋      | 21064/57600 [3:41:07<6:14:16,  1.63it/s]
 37%|███▋      | 21065/57600 [3:41:07<6:15:27,  1.62it/s]
 37%|███▋      | 21066/57600 [3:41:08<6:09:05,  1.65it/s]
 37%|███▋      | 21067/57600 [3:41:09<6:27:10,  1.57it/s]
 37%|███▋      | 21068/57600 [3:41:09<6:20:12,  1.60it/s]
 37%|███▋      | 21069/57600 [3:41:10<6:26:42,  1.57it/s]
 37%|███▋      | 21070/57600 [3:41:11<6:11:10,  1.64it/s]
 37%|███▋      | 21071/57600 [3:41:11<6:11:03,  1.64it/s]
 37%|███▋      | 21072/57600 [3:41:12<6:04:47,  1.67it/s]
 37%|███▋      | 21073/57600 [3:41:12<6:08:13,  1.65it/s]
 37%|███▋      | 21074/57600 [3:41:13<6:02:01,  1.68it/s]
 37%|███▋      | 21075/57600 [3:41:14<6:26:31,  1.57it/s]
 37%|███▋      | 21076/57600 [3:41:14<6:38:36,  1.53it/s]
 37%|███▋      | 21077/57600 [3:41:15<6:32:09,  1.55it/s]
 37%|███▋      | 21078/57600 [3:41:16<6:31:13,  1.56it/s]
 37%|███▋      | 21079/57600 [3:41:16<6:29:48,  1.56it/s]
 37%|███▋      | 21080/57600 [3:41:17<6:31:36,  1.55it/s]
                                                         
{'loss': 1.2279, 'learning_rate': 6.726132404181185e-07, 'epoch': 232.67}

 37%|███▋      | 21080/57600 [3:41:17<6:31:36,  1.55it/s]
 37%|███▋      | 21081/57600 [3:41:18<6:33:47,  1.55it/s]
 37%|███▋      | 21082/57600 [3:41:18<6:25:10,  1.58it/s]
 37%|███▋      | 21083/57600 [3:41:19<6:16:59,  1.61it/s]
 37%|███▋      | 21084/57600 [3:41:19<6:23:33,  1.59it/s]
 37%|███▋      | 21085/57600 [3:41:20<6:15:31,  1.62it/s]
 37%|███▋      | 21086/57600 [3:41:21<6:16:34,  1.62it/s]
 37%|███▋      | 21087/57600 [3:41:21<6:14:49,  1.62it/s]
 37%|███▋      | 21088/57600 [3:41:22<6:18:30,  1.61it/s]
 37%|███▋      | 21089/57600 [3:41:22<6:10:28,  1.64it/s]
 37%|███▋      | 21090/57600 [3:41:23<6:08:43,  1.65it/s]
 37%|███▋      | 21091/57600 [3:41:24<6:04:57,  1.67it/s]
 37%|███▋      | 21092/57600 [3:41:24<6:09:12,  1.65it/s]
 37%|███▋      | 21093/57600 [3:41:25<6:05:03,  1.67it/s]
 37%|███▋      | 21094/57600 [3:41:26<6:16:01,  1.62it/s]
 37%|███▋      | 21095/57600 [3:41:26<6:26:24,  1.57it/s]
 37%|███▋      | 21096/57600 [3:41:27<6:23:52,  1.58it/s]
 37%|███▋      | 21097/57600 [3:41:27<6:14:49,  1.62it/s]
 37%|███▋      | 21098/57600 [3:41:28<6:10:32,  1.64it/s]
 37%|███▋      | 21099/57600 [3:41:29<6:00:48,  1.69it/s]
 37%|███▋      | 21100/57600 [3:41:29<5:56:31,  1.71it/s]
                                                         
{'loss': 1.2432, 'learning_rate': 6.722996515679442e-07, 'epoch': 232.89}

 37%|███▋      | 21100/57600 [3:41:29<5:56:31,  1.71it/s]
 37%|███▋      | 21101/57600 [3:41:30<5:52:20,  1.73it/s]
 37%|███▋      | 21102/57600 [3:41:30<6:04:48,  1.67it/s]
 37%|███▋      | 21103/57600 [3:41:31<6:05:12,  1.67it/s]
 37%|███▋      | 21104/57600 [3:41:32<6:16:07,  1.62it/s]
 37%|███▋      | 21105/57600 [3:41:32<6:12:48,  1.63it/s]
 37%|███▋      | 21106/57600 [3:41:33<6:15:40,  1.62it/s]
 37%|███▋      | 21107/57600 [3:41:33<6:16:43,  1.61it/s]
 37%|███▋      | 21108/57600 [3:41:34<6:18:01,  1.61it/s]
 37%|███▋      | 21109/57600 [3:41:35<6:06:34,  1.66it/s]
 37%|███▋      | 21110/57600 [3:41:35<6:22:43,  1.59it/s]
 37%|███▋      | 21111/57600 [3:41:36<6:27:36,  1.57it/s]
 37%|███▋      | 21112/57600 [3:41:37<6:48:06,  1.49it/s]
 37%|███▋      | 21113/57600 [3:41:37<6:31:29,  1.55it/s]
 37%|███▋      | 21114/57600 [3:41:38<6:25:14,  1.58it/s]
 37%|███▋      | 21115/57600 [3:41:39<6:21:58,  1.59it/s]
 37%|███▋      | 21116/57600 [3:41:39<6:19:48,  1.60it/s]
 37%|███▋      | 21117/57600 [3:41:40<6:19:24,  1.60it/s]
 37%|███▋      | 21118/57600 [3:41:40<6:24:57,  1.58it/s]
 37%|███▋      | 21119/57600 [3:41:41<6:22:16,  1.59it/s]
 37%|███▋      | 21120/57600 [3:41:42<6:18:13,  1.61it/s]
                                                         
{'loss': 1.2139, 'learning_rate': 6.719860627177699e-07, 'epoch': 233.11}

 37%|███▋      | 21120/57600 [3:41:42<6:18:13,  1.61it/s]
 37%|███▋      | 21121/57600 [3:41:42<6:27:50,  1.57it/s]
 37%|███▋      | 21122/57600 [3:41:43<6:22:00,  1.59it/s]
 37%|███▋      | 21123/57600 [3:41:44<6:16:01,  1.62it/s]
 37%|███▋      | 21124/57600 [3:41:44<6:20:08,  1.60it/s]
 37%|███▋      | 21125/57600 [3:41:45<6:11:28,  1.64it/s]
 37%|███▋      | 21126/57600 [3:41:45<6:17:37,  1.61it/s]
 37%|███▋      | 21127/57600 [3:41:46<6:14:36,  1.62it/s]
 37%|███▋      | 21128/57600 [3:41:47<6:19:13,  1.60it/s]
 37%|███▋      | 21129/57600 [3:41:47<6:16:10,  1.62it/s]
 37%|███▋      | 21130/57600 [3:41:48<6:13:19,  1.63it/s]
 37%|███▋      | 21131/57600 [3:41:48<6:19:34,  1.60it/s]
 37%|███▋      | 21132/57600 [3:41:49<6:24:35,  1.58it/s]
 37%|███▋      | 21133/57600 [3:41:50<6:26:57,  1.57it/s]
 37%|███▋      | 21134/57600 [3:41:50<6:19:16,  1.60it/s]
 37%|███▋      | 21135/57600 [3:41:51<6:35:02,  1.54it/s]
 37%|███▋      | 21136/57600 [3:41:52<6:22:45,  1.59it/s]
 37%|███▋      | 21137/57600 [3:41:52<6:23:40,  1.58it/s]
 37%|███▋      | 21138/57600 [3:41:53<6:24:10,  1.58it/s]
 37%|███▋      | 21139/57600 [3:41:54<6:28:53,  1.56it/s]
 37%|███▋      | 21140/57600 [3:41:54<6:16:58,  1.61it/s]
                                                         
{'loss': 1.2181, 'learning_rate': 6.716724738675958e-07, 'epoch': 233.33}

 37%|███▋      | 21140/57600 [3:41:54<6:16:58,  1.61it/s]
 37%|███▋      | 21141/57600 [3:41:55<6:05:50,  1.66it/s]
 37%|███▋      | 21142/57600 [3:41:55<6:12:01,  1.63it/s]
 37%|███▋      | 21143/57600 [3:41:56<6:19:22,  1.60it/s]
 37%|███▋      | 21144/57600 [3:41:57<6:32:25,  1.55it/s]
 37%|███▋      | 21145/57600 [3:41:57<6:24:03,  1.58it/s]
 37%|███▋      | 21146/57600 [3:41:58<6:25:16,  1.58it/s]
 37%|███▋      | 21147/57600 [3:41:59<6:23:09,  1.59it/s]
 37%|███▋      | 21148/57600 [3:41:59<6:19:47,  1.60it/s]
 37%|███▋      | 21149/57600 [3:42:00<6:10:13,  1.64it/s]
 37%|███▋      | 21150/57600 [3:42:00<6:09:47,  1.64it/s]
 37%|███▋      | 21151/57600 [3:42:01<6:06:23,  1.66it/s]
 37%|███▋      | 21152/57600 [3:42:02<6:04:58,  1.66it/s]
 37%|███▋      | 21153/57600 [3:42:02<5:57:17,  1.70it/s]
 37%|███▋      | 21154/57600 [3:42:03<5:53:12,  1.72it/s]
 37%|███▋      | 21155/57600 [3:42:03<6:09:25,  1.64it/s]
 37%|███▋      | 21156/57600 [3:42:04<6:14:26,  1.62it/s]
 37%|███▋      | 21157/57600 [3:42:05<6:19:00,  1.60it/s]
 37%|███▋      | 21158/57600 [3:42:05<6:15:54,  1.62it/s]
 37%|███▋      | 21159/57600 [3:42:06<6:31:53,  1.55it/s]
 37%|███▋      | 21160/57600 [3:42:07<6:17:42,  1.61it/s]
                                                         
{'loss': 1.2451, 'learning_rate': 6.713588850174216e-07, 'epoch': 233.55}

 37%|███▋      | 21160/57600 [3:42:07<6:17:42,  1.61it/s]
 37%|███▋      | 21161/57600 [3:42:07<6:15:39,  1.62it/s]
 37%|███▋      | 21162/57600 [3:42:08<6:18:49,  1.60it/s]
 37%|███▋      | 21163/57600 [3:42:08<6:09:50,  1.64it/s]
 37%|███▋      | 21164/57600 [3:42:09<6:06:09,  1.66it/s]
 37%|███▋      | 21165/57600 [3:42:10<6:13:05,  1.63it/s]
 37%|███▋      | 21166/57600 [3:42:10<6:14:42,  1.62it/s]
 37%|███▋      | 21167/57600 [3:42:11<6:06:19,  1.66it/s]
 37%|███▋      | 21168/57600 [3:42:11<6:11:25,  1.63it/s]
 37%|███▋      | 21169/57600 [3:42:12<6:16:57,  1.61it/s]
 37%|███▋      | 21170/57600 [3:42:13<6:05:05,  1.66it/s]
 37%|███▋      | 21171/57600 [3:42:13<6:06:36,  1.66it/s]
 37%|███▋      | 21172/57600 [3:42:14<6:18:16,  1.60it/s]
 37%|███▋      | 21173/57600 [3:42:14<6:13:12,  1.63it/s]
 37%|███▋      | 21174/57600 [3:42:15<6:06:31,  1.66it/s]
 37%|███▋      | 21175/57600 [3:42:16<6:03:51,  1.67it/s]
 37%|███▋      | 21176/57600 [3:42:16<6:02:39,  1.67it/s]
 37%|███▋      | 21177/57600 [3:42:17<6:02:20,  1.68it/s]
 37%|███▋      | 21178/57600 [3:42:17<6:03:23,  1.67it/s]
 37%|███▋      | 21179/57600 [3:42:18<6:12:49,  1.63it/s]
 37%|███▋      | 21180/57600 [3:42:19<6:05:17,  1.66it/s]
                                                         
{'loss': 1.2809, 'learning_rate': 6.710452961672473e-07, 'epoch': 233.77}

 37%|███▋      | 21180/57600 [3:42:19<6:05:17,  1.66it/s]
 37%|███▋      | 21181/57600 [3:42:19<6:04:56,  1.66it/s]
 37%|███▋      | 21182/57600 [3:42:20<6:11:11,  1.64it/s]
 37%|███▋      | 21183/57600 [3:42:20<6:10:10,  1.64it/s]
 37%|███▋      | 21184/57600 [3:42:21<6:28:02,  1.56it/s]
 37%|███▋      | 21185/57600 [3:42:22<6:17:03,  1.61it/s]
 37%|███▋      | 21186/57600 [3:42:22<6:18:21,  1.60it/s]
 37%|███▋      | 21187/57600 [3:42:23<6:11:47,  1.63it/s]
 37%|███▋      | 21188/57600 [3:42:24<6:25:52,  1.57it/s]
 37%|███▋      | 21189/57600 [3:42:24<6:13:50,  1.62it/s]
 37%|███▋      | 21190/57600 [3:42:25<6:04:45,  1.66it/s]
 37%|███▋      | 21191/57600 [3:42:25<6:15:08,  1.62it/s]
 37%|███▋      | 21192/57600 [3:42:26<6:26:22,  1.57it/s]
 37%|███▋      | 21193/57600 [3:42:27<6:34:34,  1.54it/s]
 37%|███▋      | 21194/57600 [3:42:27<6:21:47,  1.59it/s]
 37%|███▋      | 21195/57600 [3:42:28<6:30:13,  1.55it/s]
 37%|███▋      | 21196/57600 [3:42:29<6:31:23,  1.55it/s]
 37%|███▋      | 21197/57600 [3:42:29<6:24:43,  1.58it/s]
 37%|███▋      | 21198/57600 [3:42:30<6:11:24,  1.63it/s]
 37%|███▋      | 21199/57600 [3:42:31<6:09:29,  1.64it/s]
 37%|███▋      | 21200/57600 [3:42:31<6:15:20,  1.62it/s]
                                                         
{'loss': 1.2033, 'learning_rate': 6.707317073170731e-07, 'epoch': 234.0}

 37%|███▋      | 21200/57600 [3:42:31<6:15:20,  1.62it/s]
 37%|███▋      | 21201/57600 [3:42:32<6:34:21,  1.54it/s]
 37%|███▋      | 21202/57600 [3:42:33<6:42:44,  1.51it/s]
 37%|███▋      | 21203/57600 [3:42:33<6:31:26,  1.55it/s]
 37%|███▋      | 21204/57600 [3:42:34<6:36:28,  1.53it/s]
 37%|███▋      | 21205/57600 [3:42:34<6:28:53,  1.56it/s]
 37%|███▋      | 21206/57600 [3:42:35<6:34:10,  1.54it/s]
 37%|███▋      | 21207/57600 [3:42:36<6:21:29,  1.59it/s]
 37%|███▋      | 21208/57600 [3:42:36<6:19:46,  1.60it/s]
 37%|███▋      | 21209/57600 [3:42:37<6:07:57,  1.65it/s]
 37%|███▋      | 21210/57600 [3:42:37<6:03:10,  1.67it/s]
 37%|███▋      | 21211/57600 [3:42:38<6:02:21,  1.67it/s]
 37%|███▋      | 21212/57600 [3:42:39<5:59:06,  1.69it/s]
 37%|███▋      | 21213/57600 [3:42:39<5:58:06,  1.69it/s]
 37%|███▋      | 21214/57600 [3:42:40<6:01:22,  1.68it/s]
 37%|███▋      | 21215/57600 [3:42:40<6:12:57,  1.63it/s]
 37%|███▋      | 21216/57600 [3:42:41<6:22:06,  1.59it/s]
 37%|███▋      | 21217/57600 [3:42:42<6:06:57,  1.65it/s]
 37%|███▋      | 21218/57600 [3:42:42<6:19:52,  1.60it/s]
 37%|███▋      | 21219/57600 [3:42:43<6:23:45,  1.58it/s]
 37%|███▋      | 21220/57600 [3:42:44<6:13:39,  1.62it/s]
                                                         
{'loss': 1.2253, 'learning_rate': 6.70418118466899e-07, 'epoch': 234.22}

 37%|███▋      | 21220/57600 [3:42:44<6:13:39,  1.62it/s]
 37%|███▋      | 21221/57600 [3:42:44<6:12:16,  1.63it/s]
 37%|███▋      | 21222/57600 [3:42:45<6:10:40,  1.64it/s]
 37%|███▋      | 21223/57600 [3:42:45<6:05:44,  1.66it/s]
 37%|███▋      | 21224/57600 [3:42:46<6:10:08,  1.64it/s]
 37%|███▋      | 21225/57600 [3:42:47<6:24:00,  1.58it/s]
 37%|███▋      | 21226/57600 [3:42:47<6:37:40,  1.52it/s]
 37%|███▋      | 21227/57600 [3:42:48<6:23:27,  1.58it/s]
 37%|███▋      | 21228/57600 [3:42:49<6:32:53,  1.54it/s]
 37%|███▋      | 21229/57600 [3:42:49<6:28:31,  1.56it/s]
 37%|███▋      | 21230/57600 [3:42:50<6:18:48,  1.60it/s]
 37%|███▋      | 21231/57600 [3:42:51<6:27:16,  1.57it/s]
 37%|███▋      | 21232/57600 [3:42:51<6:34:38,  1.54it/s]
 37%|███▋      | 21233/57600 [3:42:52<6:35:02,  1.53it/s]
 37%|███▋      | 21234/57600 [3:42:53<6:30:21,  1.55it/s]
 37%|███▋      | 21235/57600 [3:42:53<6:23:32,  1.58it/s]
 37%|███▋      | 21236/57600 [3:42:54<6:23:13,  1.58it/s]
 37%|███▋      | 21237/57600 [3:42:54<6:09:17,  1.64it/s]
 37%|███▋      | 21238/57600 [3:42:55<6:00:24,  1.68it/s]
 37%|███▋      | 21239/57600 [3:42:55<5:48:39,  1.74it/s]
 37%|███▋      | 21240/57600 [3:42:56<6:24:38,  1.58it/s]
                                                         
{'loss': 1.2227, 'learning_rate': 6.701045296167247e-07, 'epoch': 234.44}

 37%|███▋      | 21240/57600 [3:42:56<6:24:38,  1.58it/s]
 37%|███▋      | 21241/57600 [3:42:57<6:19:34,  1.60it/s]
 37%|███▋      | 21242/57600 [3:42:57<6:09:11,  1.64it/s]
 37%|███▋      | 21243/57600 [3:42:58<6:13:36,  1.62it/s]
 37%|███▋      | 21244/57600 [3:42:59<6:06:28,  1.65it/s]
 37%|███▋      | 21245/57600 [3:42:59<6:05:38,  1.66it/s]
 37%|███▋      | 21246/57600 [3:43:00<6:19:57,  1.59it/s]
 37%|███▋      | 21247/57600 [3:43:01<6:34:08,  1.54it/s]
 37%|███▋      | 21248/57600 [3:43:01<6:37:07,  1.53it/s]
 37%|███▋      | 21249/57600 [3:43:02<6:22:24,  1.58it/s]
 37%|███▋      | 21250/57600 [3:43:02<6:16:19,  1.61it/s]
 37%|███▋      | 21251/57600 [3:43:03<6:22:08,  1.59it/s]
 37%|███▋      | 21252/57600 [3:43:04<6:17:17,  1.61it/s]
 37%|███▋      | 21253/57600 [3:43:04<6:19:41,  1.60it/s]
 37%|███▋      | 21254/57600 [3:43:05<6:33:07,  1.54it/s]
 37%|███▋      | 21255/57600 [3:43:06<6:22:32,  1.58it/s]
 37%|███▋      | 21256/57600 [3:43:06<6:21:41,  1.59it/s]
 37%|███▋      | 21257/57600 [3:43:07<6:18:16,  1.60it/s]
 37%|███▋      | 21258/57600 [3:43:07<6:07:06,  1.65it/s]
 37%|███▋      | 21259/57600 [3:43:08<5:57:40,  1.69it/s]
 37%|███▋      | 21260/57600 [3:43:09<6:02:47,  1.67it/s]
                                                         
{'loss': 1.2314, 'learning_rate': 6.697909407665504e-07, 'epoch': 234.66}

 37%|███▋      | 21260/57600 [3:43:09<6:02:47,  1.67it/s]
 37%|███▋      | 21261/57600 [3:43:09<5:56:26,  1.70it/s]
 37%|███▋      | 21262/57600 [3:43:10<6:07:54,  1.65it/s]
 37%|███▋      | 21263/57600 [3:43:10<6:04:29,  1.66it/s]
 37%|███▋      | 21264/57600 [3:43:11<6:07:20,  1.65it/s]
 37%|███▋      | 21265/57600 [3:43:12<6:03:29,  1.67it/s]
 37%|███▋      | 21266/57600 [3:43:12<5:57:54,  1.69it/s]
 37%|███▋      | 21267/57600 [3:43:13<6:07:04,  1.65it/s]
 37%|███▋      | 21268/57600 [3:43:13<6:18:13,  1.60it/s]
 37%|███▋      | 21269/57600 [3:43:14<6:18:40,  1.60it/s]
 37%|███▋      | 21270/57600 [3:43:15<6:12:55,  1.62it/s]
 37%|███▋      | 21271/57600 [3:43:15<6:09:59,  1.64it/s]
 37%|███▋      | 21272/57600 [3:43:16<6:13:38,  1.62it/s]
 37%|███▋      | 21273/57600 [3:43:16<6:08:08,  1.64it/s]
 37%|███▋      | 21274/57600 [3:43:17<6:11:34,  1.63it/s]
 37%|███▋      | 21275/57600 [3:43:18<6:13:17,  1.62it/s]
 37%|███▋      | 21276/57600 [3:43:18<6:24:55,  1.57it/s]
 37%|███▋      | 21277/57600 [3:43:19<6:13:54,  1.62it/s]
 37%|███▋      | 21278/57600 [3:43:20<6:13:37,  1.62it/s]
 37%|███▋      | 21279/57600 [3:43:20<6:17:56,  1.60it/s]
 37%|███▋      | 21280/57600 [3:43:21<6:20:23,  1.59it/s]
                                                         
{'loss': 1.2252, 'learning_rate': 6.694773519163763e-07, 'epoch': 234.88}

 37%|███▋      | 21280/57600 [3:43:21<6:20:23,  1.59it/s]
 37%|███▋      | 21281/57600 [3:43:22<6:36:22,  1.53it/s]
 37%|███▋      | 21282/57600 [3:43:22<6:34:08,  1.54it/s]
 37%|███▋      | 21283/57600 [3:43:23<6:21:50,  1.59it/s]
 37%|███▋      | 21284/57600 [3:43:23<6:09:41,  1.64it/s]
 37%|███▋      | 21285/57600 [3:43:24<6:17:23,  1.60it/s]
 37%|███▋      | 21286/57600 [3:43:25<6:16:03,  1.61it/s]
 37%|███▋      | 21287/57600 [3:43:25<6:06:47,  1.65it/s]
 37%|███▋      | 21288/57600 [3:43:26<6:05:05,  1.66it/s]
 37%|███▋      | 21289/57600 [3:43:26<6:00:33,  1.68it/s]
 37%|███▋      | 21290/57600 [3:43:27<6:09:21,  1.64it/s]
 37%|███▋      | 21291/57600 [3:43:28<6:04:38,  1.66it/s]
 37%|███▋      | 21292/57600 [3:43:28<6:31:56,  1.54it/s]
 37%|███▋      | 21293/57600 [3:43:29<6:13:08,  1.62it/s]
 37%|███▋      | 21294/57600 [3:43:30<6:22:20,  1.58it/s]
 37%|███▋      | 21295/57600 [3:43:30<6:29:28,  1.55it/s]
 37%|███▋      | 21296/57600 [3:43:31<6:18:50,  1.60it/s]
 37%|███▋      | 21297/57600 [3:43:31<6:10:41,  1.63it/s]
 37%|███▋      | 21298/57600 [3:43:32<6:05:30,  1.66it/s]
 37%|███▋      | 21299/57600 [3:43:33<6:11:26,  1.63it/s]
 37%|███▋      | 21300/57600 [3:43:33<6:18:38,  1.60it/s]
                                                         
{'loss': 1.2433, 'learning_rate': 6.691637630662021e-07, 'epoch': 235.1}

 37%|███▋      | 21300/57600 [3:43:33<6:18:38,  1.60it/s]
 37%|███▋      | 21301/57600 [3:43:34<6:27:42,  1.56it/s]
 37%|███▋      | 21302/57600 [3:43:35<6:23:32,  1.58it/s]
 37%|███▋      | 21303/57600 [3:43:35<6:08:08,  1.64it/s]
 37%|███▋      | 21304/57600 [3:43:36<6:19:25,  1.59it/s]
 37%|███▋      | 21305/57600 [3:43:36<6:08:04,  1.64it/s]
 37%|███▋      | 21306/57600 [3:43:37<6:03:50,  1.66it/s]
 37%|███▋      | 21307/57600 [3:43:38<6:04:19,  1.66it/s]
 37%|███▋      | 21308/57600 [3:43:38<6:14:36,  1.61it/s]
 37%|███▋      | 21309/57600 [3:43:39<6:11:47,  1.63it/s]
 37%|███▋      | 21310/57600 [3:43:39<6:09:51,  1.64it/s]
 37%|███▋      | 21311/57600 [3:43:40<6:09:04,  1.64it/s]
 37%|███▋      | 21312/57600 [3:43:41<6:08:29,  1.64it/s]
 37%|███▋      | 21313/57600 [3:43:41<6:04:25,  1.66it/s]
 37%|███▋      | 21314/57600 [3:43:42<6:03:50,  1.66it/s]
 37%|███▋      | 21315/57600 [3:43:42<6:09:19,  1.64it/s]
 37%|███▋      | 21316/57600 [3:43:43<6:14:46,  1.61it/s]
 37%|███▋      | 21317/57600 [3:43:44<6:05:57,  1.65it/s]
 37%|███▋      | 21318/57600 [3:43:44<5:55:52,  1.70it/s]
 37%|███▋      | 21319/57600 [3:43:45<5:56:07,  1.70it/s]
 37%|███▋      | 21320/57600 [3:43:45<6:06:47,  1.65it/s]
                                                         
{'loss': 1.2805, 'learning_rate': 6.688501742160278e-07, 'epoch': 235.32}

 37%|███▋      | 21320/57600 [3:43:45<6:06:47,  1.65it/s]
 37%|███▋      | 21321/57600 [3:43:46<6:09:24,  1.64it/s]
 37%|███▋      | 21322/57600 [3:43:47<6:08:18,  1.64it/s]
 37%|███▋      | 21323/57600 [3:43:47<6:14:00,  1.62it/s]
 37%|███▋      | 21324/57600 [3:43:48<6:08:26,  1.64it/s]
 37%|███▋      | 21325/57600 [3:43:49<6:02:29,  1.67it/s]
 37%|███▋      | 21326/57600 [3:43:49<6:00:14,  1.68it/s]
 37%|███▋      | 21327/57600 [3:43:50<6:11:20,  1.63it/s]
 37%|███▋      | 21328/57600 [3:43:50<6:31:17,  1.54it/s]
 37%|███▋      | 21329/57600 [3:43:51<6:18:37,  1.60it/s]
 37%|███▋      | 21330/57600 [3:43:52<6:11:42,  1.63it/s]
 37%|███▋      | 21331/57600 [3:43:52<6:21:20,  1.59it/s]
 37%|███▋      | 21332/57600 [3:43:53<6:26:08,  1.57it/s]
 37%|███▋      | 21333/57600 [3:43:54<6:22:50,  1.58it/s]
 37%|███▋      | 21334/57600 [3:43:54<6:35:48,  1.53it/s]
 37%|███▋      | 21335/57600 [3:43:55<6:34:29,  1.53it/s]
 37%|███▋      | 21336/57600 [3:43:56<6:30:08,  1.55it/s]
 37%|███▋      | 21337/57600 [3:43:56<6:40:40,  1.51it/s]
 37%|███▋      | 21338/57600 [3:43:57<6:26:35,  1.56it/s]
 37%|███▋      | 21339/57600 [3:43:58<6:30:18,  1.55it/s]
 37%|███▋      | 21340/57600 [3:43:58<6:30:21,  1.55it/s]
                                                         
{'loss': 1.2463, 'learning_rate': 6.685365853658536e-07, 'epoch': 235.54}

 37%|███▋      | 21340/57600 [3:43:58<6:30:21,  1.55it/s]
 37%|███▋      | 21341/57600 [3:43:59<6:29:05,  1.55it/s]
 37%|███▋      | 21342/57600 [3:43:59<6:23:45,  1.57it/s]
 37%|███▋      | 21343/57600 [3:44:00<6:18:26,  1.60it/s]
 37%|███▋      | 21344/57600 [3:44:01<6:17:49,  1.60it/s]
 37%|███▋      | 21345/57600 [3:44:01<6:25:50,  1.57it/s]
 37%|███▋      | 21346/57600 [3:44:02<6:15:28,  1.61it/s]
 37%|███▋      | 21347/57600 [3:44:03<6:16:41,  1.60it/s]
 37%|███▋      | 21348/57600 [3:44:03<6:12:39,  1.62it/s]
 37%|███▋      | 21349/57600 [3:44:04<6:18:45,  1.60it/s]
 37%|███▋      | 21350/57600 [3:44:04<6:16:50,  1.60it/s]
 37%|███▋      | 21351/57600 [3:44:05<6:22:14,  1.58it/s]
 37%|███▋      | 21352/57600 [3:44:06<6:33:42,  1.53it/s]
 37%|███▋      | 21353/57600 [3:44:06<6:34:57,  1.53it/s]
 37%|███▋      | 21354/57600 [3:44:07<6:24:37,  1.57it/s]
 37%|███▋      | 21355/57600 [3:44:08<6:15:28,  1.61it/s]
 37%|███▋      | 21356/57600 [3:44:08<6:05:21,  1.65it/s]
 37%|███▋      | 21357/57600 [3:44:09<6:13:51,  1.62it/s]
 37%|███▋      | 21358/57600 [3:44:09<6:18:01,  1.60it/s]
 37%|███▋      | 21359/57600 [3:44:10<6:16:02,  1.61it/s]
 37%|███▋      | 21360/57600 [3:44:11<6:14:39,  1.61it/s]
                                                         
{'loss': 1.2023, 'learning_rate': 6.682229965156795e-07, 'epoch': 235.76}

 37%|███▋      | 21360/57600 [3:44:11<6:14:39,  1.61it/s]
 37%|███▋      | 21361/57600 [3:44:11<6:27:33,  1.56it/s]
 37%|███▋      | 21362/57600 [3:44:12<6:30:49,  1.55it/s]
 37%|███▋      | 21363/57600 [3:44:13<6:25:02,  1.57it/s]
 37%|███▋      | 21364/57600 [3:44:13<6:23:32,  1.57it/s]
 37%|███▋      | 21365/57600 [3:44:14<6:29:25,  1.55it/s]
 37%|███▋      | 21366/57600 [3:44:15<6:23:33,  1.57it/s]
 37%|███▋      | 21367/57600 [3:44:15<6:16:34,  1.60it/s]
 37%|███▋      | 21368/57600 [3:44:16<6:15:37,  1.61it/s]
 37%|███▋      | 21369/57600 [3:44:16<6:11:25,  1.63it/s]
 37%|███▋      | 21370/57600 [3:44:17<6:20:22,  1.59it/s]
 37%|███▋      | 21371/57600 [3:44:18<6:13:44,  1.62it/s]
 37%|███▋      | 21372/57600 [3:44:18<6:02:46,  1.66it/s]
 37%|███▋      | 21373/57600 [3:44:19<5:59:30,  1.68it/s]
 37%|███▋      | 21374/57600 [3:44:19<6:04:10,  1.66it/s]
 37%|███▋      | 21375/57600 [3:44:20<5:57:06,  1.69it/s]
 37%|███▋      | 21376/57600 [3:44:21<6:02:39,  1.66it/s]
 37%|███▋      | 21377/57600 [3:44:21<6:06:05,  1.65it/s]
 37%|███▋      | 21378/57600 [3:44:22<6:14:34,  1.61it/s]
 37%|███▋      | 21379/57600 [3:44:22<6:10:40,  1.63it/s]
 37%|███▋      | 21380/57600 [3:44:23<6:06:04,  1.65it/s]
                                                         
{'loss': 1.2361, 'learning_rate': 6.679094076655052e-07, 'epoch': 235.98}

 37%|███▋      | 21380/57600 [3:44:23<6:06:04,  1.65it/s]
 37%|███▋      | 21381/57600 [3:44:24<6:00:08,  1.68it/s]
 37%|███▋      | 21382/57600 [3:44:24<6:14:40,  1.61it/s]
 37%|███▋      | 21383/57600 [3:44:25<6:05:44,  1.65it/s]
 37%|███▋      | 21384/57600 [3:44:25<5:59:20,  1.68it/s]
 37%|███▋      | 21385/57600 [3:44:26<6:00:25,  1.67it/s]
 37%|███▋      | 21386/57600 [3:44:27<5:54:37,  1.70it/s]
 37%|███▋      | 21387/57600 [3:44:27<6:00:34,  1.67it/s]
 37%|███▋      | 21388/57600 [3:44:28<5:56:16,  1.69it/s]
 37%|███▋      | 21389/57600 [3:44:28<6:07:03,  1.64it/s]
 37%|███▋      | 21390/57600 [3:44:29<6:15:28,  1.61it/s]
 37%|███▋      | 21391/57600 [3:44:30<6:23:21,  1.57it/s]
 37%|███▋      | 21392/57600 [3:44:30<6:20:21,  1.59it/s]
 37%|███▋      | 21393/57600 [3:44:31<6:08:23,  1.64it/s]
 37%|███▋      | 21394/57600 [3:44:32<6:13:22,  1.62it/s]
 37%|███▋      | 21395/57600 [3:44:32<6:04:02,  1.66it/s]
 37%|███▋      | 21396/57600 [3:44:33<6:07:51,  1.64it/s]
 37%|███▋      | 21397/57600 [3:44:34<6:28:20,  1.55it/s]
 37%|███▋      | 21398/57600 [3:44:34<6:39:45,  1.51it/s]
 37%|███▋      | 21399/57600 [3:44:35<6:48:33,  1.48it/s]
 37%|███▋      | 21400/57600 [3:44:36<6:33:16,  1.53it/s]
                                                         
{'loss': 1.2028, 'learning_rate': 6.675958188153309e-07, 'epoch': 236.2}

 37%|███▋      | 21400/57600 [3:44:36<6:33:16,  1.53it/s]
 37%|███▋      | 21401/57600 [3:44:36<6:29:27,  1.55it/s]
 37%|███▋      | 21402/57600 [3:44:37<6:32:40,  1.54it/s]
 37%|███▋      | 21403/57600 [3:44:37<6:26:34,  1.56it/s]
 37%|███▋      | 21404/57600 [3:44:38<6:38:14,  1.51it/s]
 37%|███▋      | 21405/57600 [3:44:39<6:37:21,  1.52it/s]
 37%|███▋      | 21406/57600 [3:44:39<6:30:29,  1.54it/s]
 37%|███▋      | 21407/57600 [3:44:40<6:30:04,  1.55it/s]
 37%|███▋      | 21408/57600 [3:44:41<6:42:15,  1.50it/s]
 37%|███▋      | 21409/57600 [3:44:41<6:32:07,  1.54it/s]
 37%|███▋      | 21410/57600 [3:44:42<6:30:00,  1.55it/s]
 37%|███▋      | 21411/57600 [3:44:43<6:19:58,  1.59it/s]
 37%|███▋      | 21412/57600 [3:44:43<6:22:12,  1.58it/s]
 37%|███▋      | 21413/57600 [3:44:44<6:36:41,  1.52it/s]
 37%|███▋      | 21414/57600 [3:44:45<6:27:52,  1.55it/s]
 37%|███▋      | 21415/57600 [3:44:45<6:24:28,  1.57it/s]
 37%|███▋      | 21416/57600 [3:44:46<6:22:36,  1.58it/s]
 37%|███▋      | 21417/57600 [3:44:46<6:18:39,  1.59it/s]
 37%|███▋      | 21418/57600 [3:44:47<6:29:48,  1.55it/s]
 37%|███▋      | 21419/57600 [3:44:48<6:23:10,  1.57it/s]
 37%|███▋      | 21420/57600 [3:44:48<6:33:40,  1.53it/s]
                                                         
{'loss': 1.2244, 'learning_rate': 6.672822299651567e-07, 'epoch': 236.42}

 37%|███▋      | 21420/57600 [3:44:48<6:33:40,  1.53it/s]
 37%|███▋      | 21421/57600 [3:44:49<6:22:31,  1.58it/s]
 37%|███▋      | 21422/57600 [3:44:50<6:21:37,  1.58it/s]
 37%|███▋      | 21423/57600 [3:44:50<6:28:14,  1.55it/s]
 37%|███▋      | 21424/57600 [3:44:51<6:16:02,  1.60it/s]
 37%|███▋      | 21425/57600 [3:44:52<6:17:16,  1.60it/s]
 37%|███▋      | 21426/57600 [3:44:52<6:06:06,  1.65it/s]
 37%|███▋      | 21427/57600 [3:44:53<6:04:48,  1.65it/s]
 37%|███▋      | 21428/57600 [3:44:53<5:55:13,  1.70it/s]
 37%|███▋      | 21429/57600 [3:44:54<5:51:06,  1.72it/s]
 37%|███▋      | 21430/57600 [3:44:54<5:48:00,  1.73it/s]
 37%|███▋      | 21431/57600 [3:44:55<5:58:12,  1.68it/s]
 37%|███▋      | 21432/57600 [3:44:56<6:08:36,  1.64it/s]
 37%|███▋      | 21433/57600 [3:44:56<6:02:16,  1.66it/s]
 37%|███▋      | 21434/57600 [3:44:57<6:08:24,  1.64it/s]
 37%|███▋      | 21435/57600 [3:44:57<6:00:45,  1.67it/s]
 37%|███▋      | 21436/57600 [3:44:58<5:59:26,  1.68it/s]
 37%|███▋      | 21437/57600 [3:44:59<6:11:24,  1.62it/s]
 37%|███▋      | 21438/57600 [3:44:59<6:09:51,  1.63it/s]
 37%|███▋      | 21439/57600 [3:45:00<6:05:48,  1.65it/s]
 37%|███▋      | 21440/57600 [3:45:00<6:05:21,  1.65it/s]
                                                         
{'loss': 1.2769, 'learning_rate': 6.669686411149826e-07, 'epoch': 236.64}

 37%|███▋      | 21440/57600 [3:45:00<6:05:21,  1.65it/s]
 37%|███▋      | 21441/57600 [3:45:01<6:00:37,  1.67it/s]
 37%|███▋      | 21442/57600 [3:45:02<5:58:22,  1.68it/s]
 37%|███▋      | 21443/57600 [3:45:02<6:00:40,  1.67it/s]
 37%|███▋      | 21444/57600 [3:45:03<5:56:07,  1.69it/s]
 37%|███▋      | 21445/57600 [3:45:03<5:58:55,  1.68it/s]
 37%|███▋      | 21446/57600 [3:45:04<6:02:17,  1.66it/s]
 37%|███▋      | 21447/57600 [3:45:05<5:55:56,  1.69it/s]
 37%|███▋      | 21448/57600 [3:45:05<6:03:16,  1.66it/s]
 37%|███▋      | 21449/57600 [3:45:06<6:16:58,  1.60it/s]
 37%|███▋      | 21450/57600 [3:45:07<6:11:29,  1.62it/s]
 37%|███▋      | 21451/57600 [3:45:07<6:15:31,  1.60it/s]
 37%|███▋      | 21452/57600 [3:45:08<6:02:55,  1.66it/s]
 37%|███▋      | 21453/57600 [3:45:08<6:06:29,  1.64it/s]
 37%|███▋      | 21454/57600 [3:45:09<6:02:20,  1.66it/s]
 37%|███▋      | 21455/57600 [3:45:10<6:04:09,  1.65it/s]
 37%|███▋      | 21456/57600 [3:45:10<6:06:27,  1.64it/s]
 37%|███▋      | 21457/57600 [3:45:11<6:09:30,  1.63it/s]
 37%|███▋      | 21458/57600 [3:45:11<6:07:03,  1.64it/s]
 37%|███▋      | 21459/57600 [3:45:12<6:02:46,  1.66it/s]
 37%|███▋      | 21460/57600 [3:45:13<6:10:01,  1.63it/s]
                                                         
{'loss': 1.2867, 'learning_rate': 6.666550522648082e-07, 'epoch': 236.87}

 37%|███▋      | 21460/57600 [3:45:13<6:10:01,  1.63it/s]
 37%|███▋      | 21461/57600 [3:45:13<6:06:18,  1.64it/s]
 37%|███▋      | 21462/57600 [3:45:14<6:07:57,  1.64it/s]
 37%|███▋      | 21463/57600 [3:45:15<6:24:49,  1.57it/s]
 37%|███▋      | 21464/57600 [3:45:15<6:16:57,  1.60it/s]
 37%|███▋      | 21465/57600 [3:45:16<6:05:10,  1.65it/s]
 37%|███▋      | 21466/57600 [3:45:16<6:07:54,  1.64it/s]
 37%|███▋      | 21467/57600 [3:45:17<6:16:24,  1.60it/s]
 37%|███▋      | 21468/57600 [3:45:18<6:15:29,  1.60it/s]
 37%|███▋      | 21469/57600 [3:45:18<6:24:03,  1.57it/s]
 37%|███▋      | 21470/57600 [3:45:19<6:19:04,  1.59it/s]
 37%|███▋      | 21471/57600 [3:45:20<6:23:48,  1.57it/s]
 37%|███▋      | 21472/57600 [3:45:20<6:14:17,  1.61it/s]
 37%|███▋      | 21473/57600 [3:45:21<6:30:38,  1.54it/s]
 37%|███▋      | 21474/57600 [3:45:21<6:18:10,  1.59it/s]
 37%|███▋      | 21475/57600 [3:45:22<6:07:06,  1.64it/s]
 37%|███▋      | 21476/57600 [3:45:23<6:23:10,  1.57it/s]
 37%|███▋      | 21477/57600 [3:45:23<6:18:09,  1.59it/s]
 37%|███▋      | 21478/57600 [3:45:24<6:19:33,  1.59it/s]
 37%|███▋      | 21479/57600 [3:45:25<6:11:42,  1.62it/s]
 37%|███▋      | 21480/57600 [3:45:25<6:17:40,  1.59it/s]
                                                         
{'loss': 1.2298, 'learning_rate': 6.663414634146342e-07, 'epoch': 237.09}

 37%|███▋      | 21480/57600 [3:45:25<6:17:40,  1.59it/s]
 37%|███▋      | 21481/57600 [3:45:26<6:37:25,  1.51it/s]
 37%|███▋      | 21482/57600 [3:45:27<6:38:14,  1.51it/s]
 37%|███▋      | 21483/57600 [3:45:27<6:29:29,  1.55it/s]
 37%|███▋      | 21484/57600 [3:45:28<6:18:42,  1.59it/s]
 37%|███▋      | 21485/57600 [3:45:28<6:05:43,  1.65it/s]
 37%|███▋      | 21486/57600 [3:45:29<6:04:48,  1.65it/s]
 37%|███▋      | 21487/57600 [3:45:29<6:00:34,  1.67it/s]
 37%|███▋      | 21488/57600 [3:45:30<6:13:02,  1.61it/s]
 37%|███▋      | 21489/57600 [3:45:31<6:07:22,  1.64it/s]
 37%|███▋      | 21490/57600 [3:45:31<6:10:15,  1.63it/s]
 37%|███▋      | 21491/57600 [3:45:32<6:05:36,  1.65it/s]
 37%|███▋      | 21492/57600 [3:45:33<5:57:44,  1.68it/s]
 37%|███▋      | 21493/57600 [3:45:33<6:00:45,  1.67it/s]
 37%|███▋      | 21494/57600 [3:45:34<6:01:50,  1.66it/s]
 37%|███▋      | 21495/57600 [3:45:34<6:13:02,  1.61it/s]
 37%|███▋      | 21496/57600 [3:45:35<6:09:58,  1.63it/s]
 37%|███▋      | 21497/57600 [3:45:36<5:58:56,  1.68it/s]
 37%|███▋      | 21498/57600 [3:45:36<6:07:59,  1.64it/s]
 37%|███▋      | 21499/57600 [3:45:37<6:18:27,  1.59it/s]
 37%|███▋      | 21500/57600 [3:45:37<6:07:12,  1.64it/s]
                                                         
{'loss': 1.2307, 'learning_rate': 6.6602787456446e-07, 'epoch': 237.31}

 37%|███▋      | 21500/57600 [3:45:37<6:07:12,  1.64it/s]
 37%|███▋      | 21501/57600 [3:45:38<6:12:09,  1.62it/s]
 37%|███▋      | 21502/57600 [3:45:39<6:10:22,  1.62it/s]
 37%|███▋      | 21503/57600 [3:45:39<6:08:26,  1.63it/s]
 37%|███▋      | 21504/57600 [3:45:40<6:23:42,  1.57it/s]
 37%|███▋      | 21505/57600 [3:45:41<6:15:08,  1.60it/s]
 37%|███▋      | 21506/57600 [3:45:41<6:16:35,  1.60it/s]
 37%|███▋      | 21507/57600 [3:45:42<6:12:17,  1.62it/s]
 37%|███▋      | 21508/57600 [3:45:42<6:00:56,  1.67it/s]
 37%|███▋      | 21509/57600 [3:45:43<6:11:06,  1.62it/s]
 37%|███▋      | 21510/57600 [3:45:44<6:11:12,  1.62it/s]
 37%|███▋      | 21511/57600 [3:45:44<6:07:53,  1.63it/s]
 37%|███▋      | 21512/57600 [3:45:45<6:15:54,  1.60it/s]
 37%|███▋      | 21513/57600 [3:45:46<6:12:57,  1.61it/s]
 37%|███▋      | 21514/57600 [3:45:46<6:09:16,  1.63it/s]
 37%|███▋      | 21515/57600 [3:45:47<6:09:46,  1.63it/s]
 37%|███▋      | 21516/57600 [3:45:47<6:19:51,  1.58it/s]
 37%|███▋      | 21517/57600 [3:45:48<6:07:37,  1.64it/s]
 37%|███▋      | 21518/57600 [3:45:49<6:17:57,  1.59it/s]
 37%|███▋      | 21519/57600 [3:45:49<6:13:38,  1.61it/s]
 37%|███▋      | 21520/57600 [3:45:50<6:34:17,  1.53it/s]
                                                         
{'loss': 1.2522, 'learning_rate': 6.657142857142857e-07, 'epoch': 237.53}

 37%|███▋      | 21520/57600 [3:45:50<6:34:17,  1.53it/s]
 37%|███▋      | 21521/57600 [3:45:51<6:18:20,  1.59it/s]
 37%|███▋      | 21522/57600 [3:45:51<6:15:56,  1.60it/s]
 37%|███▋      | 21523/57600 [3:45:52<6:08:48,  1.63it/s]
 37%|███▋      | 21524/57600 [3:45:52<6:11:15,  1.62it/s]
 37%|███▋      | 21525/57600 [3:45:53<6:03:54,  1.65it/s]
 37%|███▋      | 21526/57600 [3:45:54<6:10:40,  1.62it/s]
 37%|███▋      | 21527/57600 [3:45:54<6:03:29,  1.65it/s]
 37%|███▋      | 21528/57600 [3:45:55<6:01:59,  1.66it/s]
 37%|███▋      | 21529/57600 [3:45:55<6:07:18,  1.64it/s]
 37%|███▋      | 21530/57600 [3:45:56<6:13:44,  1.61it/s]
 37%|███▋      | 21531/57600 [3:45:57<6:18:23,  1.59it/s]
 37%|███▋      | 21532/57600 [3:45:57<6:11:09,  1.62it/s]
 37%|███▋      | 21533/57600 [3:45:58<6:06:53,  1.64it/s]
 37%|███▋      | 21534/57600 [3:45:58<6:07:13,  1.64it/s]
 37%|███▋      | 21535/57600 [3:45:59<6:05:53,  1.64it/s]
 37%|███▋      | 21536/57600 [3:46:00<6:06:51,  1.64it/s]
 37%|███▋      | 21537/57600 [3:46:00<6:11:14,  1.62it/s]
 37%|███▋      | 21538/57600 [3:46:01<6:09:40,  1.63it/s]
 37%|███▋      | 21539/57600 [3:46:02<6:10:56,  1.62it/s]
 37%|███▋      | 21540/57600 [3:46:02<6:04:42,  1.65it/s]
                                                         
{'loss': 1.2607, 'learning_rate': 6.654006968641114e-07, 'epoch': 237.75}

 37%|███▋      | 21540/57600 [3:46:02<6:04:42,  1.65it/s]
 37%|███▋      | 21541/57600 [3:46:03<6:09:32,  1.63it/s]
 37%|███▋      | 21542/57600 [3:46:03<5:57:48,  1.68it/s]
 37%|███▋      | 21543/57600 [3:46:04<5:58:08,  1.68it/s]
 37%|███▋      | 21544/57600 [3:46:05<6:03:03,  1.66it/s]
 37%|███▋      | 21545/57600 [3:46:05<6:04:17,  1.65it/s]
 37%|███▋      | 21546/57600 [3:46:06<6:05:37,  1.64it/s]
 37%|███▋      | 21547/57600 [3:46:06<6:06:39,  1.64it/s]
 37%|███▋      | 21548/57600 [3:46:07<6:14:35,  1.60it/s]
 37%|███▋      | 21549/57600 [3:46:08<6:10:42,  1.62it/s]
 37%|███▋      | 21550/57600 [3:46:08<6:25:42,  1.56it/s]
 37%|███▋      | 21551/57600 [3:46:09<6:23:14,  1.57it/s]
 37%|███▋      | 21552/57600 [3:46:10<6:17:53,  1.59it/s]
 37%|███▋      | 21553/57600 [3:46:10<6:08:07,  1.63it/s]
 37%|███▋      | 21554/57600 [3:46:11<6:01:57,  1.66it/s]
 37%|███▋      | 21555/57600 [3:46:11<6:10:58,  1.62it/s]
 37%|███▋      | 21556/57600 [3:46:12<6:24:28,  1.56it/s]
 37%|███▋      | 21557/57600 [3:46:13<6:30:11,  1.54it/s]
 37%|███▋      | 21558/57600 [3:46:13<6:25:04,  1.56it/s]
 37%|███▋      | 21559/57600 [3:46:14<6:16:44,  1.59it/s]
 37%|███▋      | 21560/57600 [3:46:15<6:18:20,  1.59it/s]
                                                         
{'loss': 1.1926, 'learning_rate': 6.650871080139373e-07, 'epoch': 237.97}

 37%|███▋      | 21560/57600 [3:46:15<6:18:20,  1.59it/s]
 37%|███▋      | 21561/57600 [3:46:15<6:17:12,  1.59it/s]
 37%|███▋      | 21562/57600 [3:46:16<6:18:55,  1.59it/s]
 37%|███▋      | 21563/57600 [3:46:17<6:29:34,  1.54it/s]
 37%|███▋      | 21564/57600 [3:46:17<6:20:07,  1.58it/s]
 37%|███▋      | 21565/57600 [3:46:18<6:22:29,  1.57it/s]
 37%|███▋      | 21566/57600 [3:46:18<6:24:47,  1.56it/s]
 37%|███▋      | 21567/57600 [3:46:19<6:14:01,  1.61it/s]
 37%|███▋      | 21568/57600 [3:46:20<6:10:00,  1.62it/s]
 37%|███▋      | 21569/57600 [3:46:20<6:14:41,  1.60it/s]
 37%|███▋      | 21570/57600 [3:46:21<6:07:08,  1.64it/s]
 37%|███▋      | 21571/57600 [3:46:22<6:21:29,  1.57it/s]
 37%|███▋      | 21572/57600 [3:46:22<6:26:08,  1.56it/s]
 37%|███▋      | 21573/57600 [3:46:23<6:28:31,  1.55it/s]
 37%|███▋      | 21574/57600 [3:46:23<6:18:30,  1.59it/s]
 37%|███▋      | 21575/57600 [3:46:24<6:19:13,  1.58it/s]
 37%|███▋      | 21576/57600 [3:46:25<6:10:47,  1.62it/s]
 37%|███▋      | 21577/57600 [3:46:25<6:07:11,  1.64it/s]
 37%|███▋      | 21578/57600 [3:46:26<6:07:14,  1.63it/s]
 37%|███▋      | 21579/57600 [3:46:27<6:09:01,  1.63it/s]
 37%|███▋      | 21580/57600 [3:46:27<6:12:30,  1.61it/s]
                                                         
{'loss': 1.209, 'learning_rate': 6.647735191637631e-07, 'epoch': 238.19}

 37%|███▋      | 21580/57600 [3:46:27<6:12:30,  1.61it/s]
 37%|███▋      | 21581/57600 [3:46:28<6:12:35,  1.61it/s]
 37%|███▋      | 21582/57600 [3:46:28<6:00:49,  1.66it/s]
 37%|███▋      | 21583/57600 [3:46:29<5:52:34,  1.70it/s]
 37%|███▋      | 21584/57600 [3:46:30<5:59:32,  1.67it/s]
 37%|███▋      | 21585/57600 [3:46:30<6:00:23,  1.67it/s]
 37%|███▋      | 21586/57600 [3:46:31<6:16:21,  1.59it/s]
 37%|███▋      | 21587/57600 [3:46:31<6:16:56,  1.59it/s]
 37%|███▋      | 21588/57600 [3:46:32<6:10:14,  1.62it/s]
 37%|███▋      | 21589/57600 [3:46:33<6:25:07,  1.56it/s]
 37%|███▋      | 21590/57600 [3:46:33<6:18:20,  1.59it/s]
 37%|███▋      | 21591/57600 [3:46:34<6:08:58,  1.63it/s]
 37%|███▋      | 21592/57600 [3:46:35<6:10:18,  1.62it/s]
 37%|███▋      | 21593/57600 [3:46:35<6:15:50,  1.60it/s]
 37%|███▋      | 21594/57600 [3:46:36<6:21:51,  1.57it/s]
 37%|███▋      | 21595/57600 [3:46:37<6:28:33,  1.54it/s]
 37%|███▋      | 21596/57600 [3:46:37<6:23:07,  1.57it/s]
 37%|███▋      | 21597/57600 [3:46:38<6:13:18,  1.61it/s]
 37%|███▋      | 21598/57600 [3:46:38<6:07:57,  1.63it/s]
 37%|███▋      | 21599/57600 [3:46:39<6:09:31,  1.62it/s]
 38%|███▊      | 21600/57600 [3:46:39<6:02:28,  1.66it/s]
                                                         
{'loss': 1.2272, 'learning_rate': 6.644599303135888e-07, 'epoch': 238.41}

 38%|███▊      | 21600/57600 [3:46:39<6:02:28,  1.66it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.59it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.22it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.91it/s]

100%|██████████| 6/6 [00:01<00:00,  3.46it/s]{'score': 47.33670601217836, 'counts': [141, 95, 63, 44], 'totals': [213, 183, 153, 124], 'precisions': [66.19718309859155, 51.91256830601093, 41.1764705882353, 35.483870967741936], 'bp': 1.0, 'sys_len': 213, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 2.001694440841675, 'eval_bleu': 47.3367, 'eval_gen_len': 8.6, 'eval_runtime': 3.1432, 'eval_samples_per_second': 9.544, 'eval_steps_per_second': 1.909, 'epoch': 238.41}

 38%|███▊      | 21600/57600 [3:46:43<6:02:28,  1.66it/s]

100%|██████████| 6/6 [00:02<00:00,  3.46it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 10:40:55,987 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 38%|███▊      | 21601/57600 [3:47:07<86:25:56,  8.64s/it]
 38%|███▊      | 21602/57600 [3:47:08<62:20:47,  6.24s/it]
 38%|███▊      | 21603/57600 [3:47:08<45:30:49,  4.55s/it]
 38%|███▊      | 21604/57600 [3:47:09<33:50:31,  3.38s/it]
 38%|███▊      | 21605/57600 [3:47:09<25:29:36,  2.55s/it]
 38%|███▊      | 21606/57600 [3:47:10<19:41:21,  1.97s/it]
 38%|███▊      | 21607/57600 [3:47:11<15:40:49,  1.57s/it]
 38%|███▊      | 21608/57600 [3:47:11<13:09:04,  1.32s/it]
 38%|███▊      | 21609/57600 [3:47:12<11:04:54,  1.11s/it]
 38%|███▊      | 21610/57600 [3:47:13<9:53:12,  1.01it/s] 
 38%|███▊      | 21611/57600 [3:47:13<8:56:14,  1.12it/s]
 38%|███▊      | 21612/57600 [3:47:14<8:15:41,  1.21it/s]
 38%|███▊      | 21613/57600 [3:47:15<7:42:40,  1.30it/s]
 38%|███▊      | 21614/57600 [3:47:15<7:20:43,  1.36it/s]
 38%|███▊      | 21615/57600 [3:47:16<7:01:50,  1.42it/s]
 38%|███▊      | 21616/57600 [3:47:17<6:56:42,  1.44it/s]
 38%|███▊      | 21617/57600 [3:47:17<6:48:43,  1.47it/s]
 38%|███▊      | 21618/57600 [3:47:18<6:41:24,  1.49it/s]
 38%|███▊      | 21619/57600 [3:47:19<6:33:41,  1.52it/s]
 38%|███▊      | 21620/57600 [3:47:19<6:23:32,  1.56it/s]
                                                         
{'loss': 1.2312, 'learning_rate': 6.641463414634146e-07, 'epoch': 238.63}

 38%|███▊      | 21620/57600 [3:47:19<6:23:32,  1.56it/s]
 38%|███▊      | 21621/57600 [3:47:20<6:17:05,  1.59it/s]
 38%|███▊      | 21622/57600 [3:47:20<6:14:10,  1.60it/s]
 38%|███▊      | 21623/57600 [3:47:21<6:12:11,  1.61it/s]
 38%|███▊      | 21624/57600 [3:47:22<6:00:01,  1.67it/s]
 38%|███▊      | 21625/57600 [3:47:22<6:28:51,  1.54it/s]
 38%|███▊      | 21626/57600 [3:47:23<6:20:50,  1.57it/s]
 38%|███▊      | 21627/57600 [3:47:24<6:15:41,  1.60it/s]
 38%|███▊      | 21628/57600 [3:47:24<6:16:26,  1.59it/s]
 38%|███▊      | 21629/57600 [3:47:25<6:16:40,  1.59it/s]
 38%|███▊      | 21630/57600 [3:47:26<6:38:07,  1.51it/s]
 38%|███▊      | 21631/57600 [3:47:26<6:42:38,  1.49it/s]
 38%|███▊      | 21632/57600 [3:47:27<6:37:10,  1.51it/s]
 38%|███▊      | 21633/57600 [3:47:27<6:27:22,  1.55it/s]
 38%|███▊      | 21634/57600 [3:47:28<6:37:44,  1.51it/s]
 38%|███▊      | 21635/57600 [3:47:29<6:25:15,  1.56it/s]
 38%|███▊      | 21636/57600 [3:47:29<6:21:47,  1.57it/s]
 38%|███▊      | 21637/57600 [3:47:30<6:05:55,  1.64it/s]
 38%|███▊      | 21638/57600 [3:47:31<6:17:57,  1.59it/s]
 38%|███▊      | 21639/57600 [3:47:31<6:11:34,  1.61it/s]
 38%|███▊      | 21640/57600 [3:47:32<6:10:50,  1.62it/s]
                                                         
{'loss': 1.295, 'learning_rate': 6.638327526132404e-07, 'epoch': 238.85}

 38%|███▊      | 21640/57600 [3:47:32<6:10:50,  1.62it/s]
 38%|███▊      | 21641/57600 [3:47:32<6:16:58,  1.59it/s]
 38%|███▊      | 21642/57600 [3:47:33<6:23:58,  1.56it/s]
 38%|███▊      | 21643/57600 [3:47:34<6:20:22,  1.58it/s]
 38%|███▊      | 21644/57600 [3:47:34<6:21:50,  1.57it/s]
 38%|███▊      | 21645/57600 [3:47:35<6:31:43,  1.53it/s]
 38%|███▊      | 21646/57600 [3:47:36<6:29:55,  1.54it/s]
 38%|███▊      | 21647/57600 [3:47:36<6:38:15,  1.50it/s]
 38%|███▊      | 21648/57600 [3:47:37<6:52:53,  1.45it/s]
 38%|███▊      | 21649/57600 [3:47:38<6:52:14,  1.45it/s]
 38%|███▊      | 21650/57600 [3:47:39<6:41:06,  1.49it/s]
 38%|███▊      | 21651/57600 [3:47:39<6:29:28,  1.54it/s]
 38%|███▊      | 21652/57600 [3:47:40<6:18:15,  1.58it/s]
 38%|███▊      | 21653/57600 [3:47:40<6:19:14,  1.58it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 38%|███▊      | 21654/57600 [3:47:41<6:58:59,  1.43it/s]
 38%|███▊      | 21655/57600 [3:47:42<6:42:29,  1.49it/s]
 38%|███▊      | 21656/57600 [3:47:42<6:48:30,  1.47it/s]
 38%|███▊      | 21657/57600 [3:47:43<6:33:31,  1.52it/s]
 38%|███▊      | 21658/57600 [3:47:44<6:38:39,  1.50it/s]
 38%|███▊      | 21659/57600 [3:47:44<6:27:41,  1.55it/s]
 38%|███▊      | 21660/57600 [3:47:45<6:25:27,  1.55it/s]
                                                         
{'loss': 1.2304, 'learning_rate': 6.635191637630662e-07, 'epoch': 239.07}

 38%|███▊      | 21660/57600 [3:47:45<6:25:27,  1.55it/s]
 38%|███▊      | 21661/57600 [3:47:46<6:15:38,  1.59it/s]
 38%|███▊      | 21662/57600 [3:47:46<6:17:41,  1.59it/s]
 38%|███▊      | 21663/57600 [3:47:47<6:30:33,  1.53it/s]
 38%|███▊      | 21664/57600 [3:47:48<6:23:04,  1.56it/s]
 38%|███▊      | 21665/57600 [3:47:48<6:26:19,  1.55it/s]
 38%|███▊      | 21666/57600 [3:47:49<6:25:02,  1.56it/s]
 38%|███▊      | 21667/57600 [3:47:49<6:14:55,  1.60it/s]
 38%|███▊      | 21668/57600 [3:47:50<6:08:58,  1.62it/s]
 38%|███▊      | 21669/57600 [3:47:51<6:01:47,  1.66it/s]
 38%|███▊      | 21670/57600 [3:47:51<5:56:58,  1.68it/s]
 38%|███▊      | 21671/57600 [3:47:52<6:03:23,  1.65it/s]
 38%|███▊      | 21672/57600 [3:47:52<6:10:01,  1.62it/s]
 38%|███▊      | 21673/57600 [3:47:53<6:11:02,  1.61it/s]
 38%|███▊      | 21674/57600 [3:47:54<6:05:51,  1.64it/s]
 38%|███▊      | 21675/57600 [3:47:54<6:07:04,  1.63it/s]
 38%|███▊      | 21676/57600 [3:47:55<6:06:09,  1.64it/s]
 38%|███▊      | 21677/57600 [3:47:56<6:05:25,  1.64it/s]
 38%|███▊      | 21678/57600 [3:47:56<6:09:10,  1.62it/s]
 38%|███▊      | 21679/57600 [3:47:57<6:28:34,  1.54it/s]
 38%|███▊      | 21680/57600 [3:47:58<6:39:28,  1.50it/s]
                                                         
{'loss': 1.2744, 'learning_rate': 6.632055749128919e-07, 'epoch': 239.29}

 38%|███▊      | 21680/57600 [3:47:58<6:39:28,  1.50it/s]
 38%|███▊      | 21681/57600 [3:47:58<6:26:26,  1.55it/s]
 38%|███▊      | 21682/57600 [3:47:59<6:19:36,  1.58it/s]
 38%|███▊      | 21683/57600 [3:47:59<6:25:36,  1.55it/s]
 38%|███▊      | 21684/57600 [3:48:00<6:33:54,  1.52it/s]
 38%|███▊      | 21685/57600 [3:48:01<6:22:58,  1.56it/s]
 38%|███▊      | 21686/57600 [3:48:01<6:09:21,  1.62it/s]
 38%|███▊      | 21687/57600 [3:48:02<6:12:44,  1.61it/s]
 38%|███▊      | 21688/57600 [3:48:03<6:06:07,  1.63it/s]
 38%|███▊      | 21689/57600 [3:48:03<6:07:57,  1.63it/s]
 38%|███▊      | 21690/57600 [3:48:04<6:13:05,  1.60it/s]
 38%|███▊      | 21691/57600 [3:48:04<6:07:55,  1.63it/s]
 38%|███▊      | 21692/57600 [3:48:05<6:05:57,  1.64it/s]
 38%|███▊      | 21693/57600 [3:48:06<6:05:27,  1.64it/s]
 38%|███▊      | 21694/57600 [3:48:06<6:09:25,  1.62it/s]
 38%|███▊      | 21695/57600 [3:48:07<6:25:29,  1.55it/s]
 38%|███▊      | 21696/57600 [3:48:08<6:21:19,  1.57it/s]
 38%|███▊      | 21697/57600 [3:48:08<6:19:31,  1.58it/s]
 38%|███▊      | 21698/57600 [3:48:09<6:32:38,  1.52it/s]
 38%|███▊      | 21699/57600 [3:48:09<6:16:20,  1.59it/s]
 38%|███▊      | 21700/57600 [3:48:10<6:14:30,  1.60it/s]
                                                         
{'loss': 1.2519, 'learning_rate': 6.628919860627178e-07, 'epoch': 239.51}

 38%|███▊      | 21700/57600 [3:48:10<6:14:30,  1.60it/s]
 38%|███▊      | 21701/57600 [3:48:11<6:04:48,  1.64it/s]
 38%|███▊      | 21702/57600 [3:48:11<6:10:02,  1.62it/s]
 38%|███▊      | 21703/57600 [3:48:12<6:09:30,  1.62it/s]
 38%|███▊      | 21704/57600 [3:48:13<6:26:39,  1.55it/s]
 38%|███▊      | 21705/57600 [3:48:13<6:22:26,  1.56it/s]
 38%|███▊      | 21706/57600 [3:48:14<6:21:35,  1.57it/s]
 38%|███▊      | 21707/57600 [3:48:15<6:40:26,  1.49it/s]
 38%|███▊      | 21708/57600 [3:48:15<6:38:28,  1.50it/s]
 38%|███▊      | 21709/57600 [3:48:16<6:33:52,  1.52it/s]
 38%|███▊      | 21710/57600 [3:48:17<6:39:25,  1.50it/s]
 38%|███▊      | 21711/57600 [3:48:17<6:47:17,  1.47it/s]
 38%|███▊      | 21712/57600 [3:48:18<6:37:49,  1.50it/s]
 38%|███▊      | 21713/57600 [3:48:19<6:37:47,  1.50it/s]
 38%|███▊      | 21714/57600 [3:48:19<6:27:19,  1.54it/s]
 38%|███▊      | 21715/57600 [3:48:20<6:41:13,  1.49it/s]
 38%|███▊      | 21716/57600 [3:48:21<6:31:19,  1.53it/s]
 38%|███▊      | 21717/57600 [3:48:21<6:45:14,  1.48it/s]
 38%|███▊      | 21718/57600 [3:48:22<6:35:31,  1.51it/s]
 38%|███▊      | 21719/57600 [3:48:23<6:41:36,  1.49it/s]
 38%|███▊      | 21720/57600 [3:48:23<6:47:43,  1.47it/s]
                                                         
{'loss': 1.2586, 'learning_rate': 6.625783972125435e-07, 'epoch': 239.74}

 38%|███▊      | 21720/57600 [3:48:23<6:47:43,  1.47it/s]
 38%|███▊      | 21721/57600 [3:48:24<6:32:15,  1.52it/s]
 38%|███▊      | 21722/57600 [3:48:25<6:22:13,  1.56it/s]
 38%|███▊      | 21723/57600 [3:48:25<6:26:50,  1.55it/s]
 38%|███▊      | 21724/57600 [3:48:26<6:35:58,  1.51it/s]
 38%|███▊      | 21725/57600 [3:48:27<6:34:06,  1.52it/s]
 38%|███▊      | 21726/57600 [3:48:27<6:33:18,  1.52it/s]
 38%|███▊      | 21727/57600 [3:48:28<6:27:08,  1.54it/s]
 38%|███▊      | 21728/57600 [3:48:28<6:32:51,  1.52it/s]
 38%|███▊      | 21729/57600 [3:48:29<6:19:43,  1.57it/s]
 38%|███▊      | 21730/57600 [3:48:30<6:37:13,  1.51it/s]
 38%|███▊      | 21731/57600 [3:48:30<6:27:26,  1.54it/s]
 38%|███▊      | 21732/57600 [3:48:31<6:24:13,  1.56it/s]
 38%|███▊      | 21733/57600 [3:48:32<6:36:49,  1.51it/s]
 38%|███▊      | 21734/57600 [3:48:32<6:40:01,  1.49it/s]
 38%|███▊      | 21735/57600 [3:48:33<6:47:18,  1.47it/s]
 38%|███▊      | 21736/57600 [3:48:34<6:41:53,  1.49it/s]
 38%|███▊      | 21737/57600 [3:48:34<6:33:23,  1.52it/s]
 38%|███▊      | 21738/57600 [3:48:35<6:45:50,  1.47it/s]
 38%|███▊      | 21739/57600 [3:48:36<6:47:57,  1.47it/s]
 38%|███▊      | 21740/57600 [3:48:36<6:41:51,  1.49it/s]
                                                         
{'loss': 1.2388, 'learning_rate': 6.622648083623693e-07, 'epoch': 239.96}

 38%|███▊      | 21740/57600 [3:48:36<6:41:51,  1.49it/s]
 38%|███▊      | 21741/57600 [3:48:37<6:43:41,  1.48it/s]
 38%|███▊      | 21742/57600 [3:48:38<6:39:37,  1.50it/s]
 38%|███▊      | 21743/57600 [3:48:38<6:40:15,  1.49it/s]
 38%|███▊      | 21744/57600 [3:48:39<6:34:33,  1.51it/s]
 38%|███▊      | 21745/57600 [3:48:40<6:44:39,  1.48it/s]
 38%|███▊      | 21746/57600 [3:48:41<6:41:24,  1.49it/s]
 38%|███▊      | 21747/57600 [3:48:41<6:46:43,  1.47it/s]
 38%|███▊      | 21748/57600 [3:48:42<6:35:08,  1.51it/s]
 38%|███▊      | 21749/57600 [3:48:42<6:27:04,  1.54it/s]
 38%|███▊      | 21750/57600 [3:48:43<6:32:45,  1.52it/s]
 38%|███▊      | 21751/57600 [3:48:44<6:37:40,  1.50it/s]
 38%|███▊      | 21752/57600 [3:48:44<6:25:58,  1.55it/s]
 38%|███▊      | 21753/57600 [3:48:45<6:18:12,  1.58it/s]
 38%|███▊      | 21754/57600 [3:48:46<6:20:14,  1.57it/s]
 38%|███▊      | 21755/57600 [3:48:46<6:31:05,  1.53it/s]
 38%|███▊      | 21756/57600 [3:48:47<6:41:13,  1.49it/s]
 38%|███▊      | 21757/57600 [3:48:48<6:34:44,  1.51it/s]
 38%|███▊      | 21758/57600 [3:48:48<6:33:40,  1.52it/s]
 38%|███▊      | 21759/57600 [3:48:49<6:39:20,  1.50it/s]
 38%|███▊      | 21760/57600 [3:48:50<6:37:46,  1.50it/s]
                                                         
{'loss': 1.2829, 'learning_rate': 6.61951219512195e-07, 'epoch': 240.18}

 38%|███▊      | 21760/57600 [3:48:50<6:37:46,  1.50it/s]
 38%|███▊      | 21761/57600 [3:48:50<6:26:38,  1.54it/s]
 38%|███▊      | 21762/57600 [3:48:51<6:24:40,  1.55it/s]
 38%|███▊      | 21763/57600 [3:48:52<6:24:44,  1.55it/s]
 38%|███▊      | 21764/57600 [3:48:52<6:27:04,  1.54it/s]
 38%|███▊      | 21765/57600 [3:48:53<6:31:28,  1.53it/s]
 38%|███▊      | 21766/57600 [3:48:54<6:37:29,  1.50it/s]
 38%|███▊      | 21767/57600 [3:48:54<6:27:51,  1.54it/s]
 38%|███▊      | 21768/57600 [3:48:55<6:35:48,  1.51it/s]
 38%|███▊      | 21769/57600 [3:48:56<6:26:29,  1.55it/s]
 38%|███▊      | 21770/57600 [3:48:56<6:31:12,  1.53it/s]
 38%|███▊      | 21771/57600 [3:48:57<6:23:53,  1.56it/s]
 38%|███▊      | 21772/57600 [3:48:57<6:26:04,  1.55it/s]
 38%|███▊      | 21773/57600 [3:48:58<6:39:27,  1.49it/s]
 38%|███▊      | 21774/57600 [3:48:59<6:49:43,  1.46it/s]
 38%|███▊      | 21775/57600 [3:49:00<6:55:40,  1.44it/s]
 38%|███▊      | 21776/57600 [3:49:00<6:50:11,  1.46it/s]
 38%|███▊      | 21777/57600 [3:49:01<6:41:31,  1.49it/s]
 38%|███▊      | 21778/57600 [3:49:02<6:44:51,  1.47it/s]
 38%|███▊      | 21779/57600 [3:49:02<6:44:21,  1.48it/s]
 38%|███▊      | 21780/57600 [3:49:03<6:45:07,  1.47it/s]
                                                         
{'loss': 1.1969, 'learning_rate': 6.616376306620209e-07, 'epoch': 240.4}

 38%|███▊      | 21780/57600 [3:49:03<6:45:07,  1.47it/s]
 38%|███▊      | 21781/57600 [3:49:04<6:33:59,  1.52it/s]
 38%|███▊      | 21782/57600 [3:49:04<6:33:17,  1.52it/s]
 38%|███▊      | 21783/57600 [3:49:05<6:23:37,  1.56it/s]
 38%|███▊      | 21784/57600 [3:49:05<6:16:14,  1.59it/s]
 38%|███▊      | 21785/57600 [3:49:06<6:26:44,  1.54it/s]
 38%|███▊      | 21786/57600 [3:49:07<6:12:39,  1.60it/s]
 38%|███▊      | 21787/57600 [3:49:07<6:18:12,  1.58it/s]
 38%|███▊      | 21788/57600 [3:49:08<6:14:58,  1.59it/s]
 38%|███▊      | 21789/57600 [3:49:09<6:13:44,  1.60it/s]
 38%|███▊      | 21790/57600 [3:49:09<6:10:25,  1.61it/s]
 38%|███▊      | 21791/57600 [3:49:10<6:20:58,  1.57it/s]
 38%|███▊      | 21792/57600 [3:49:11<6:27:07,  1.54it/s]
 38%|███▊      | 21793/57600 [3:49:11<7:02:58,  1.41it/s]
 38%|███▊      | 21794/57600 [3:49:12<6:46:25,  1.47it/s]
 38%|███▊      | 21795/57600 [3:49:13<6:39:27,  1.49it/s]
 38%|███▊      | 21796/57600 [3:49:13<6:25:26,  1.55it/s]
 38%|███▊      | 21797/57600 [3:49:14<6:24:46,  1.55it/s]
 38%|███▊      | 21798/57600 [3:49:15<6:27:24,  1.54it/s]
 38%|███▊      | 21799/57600 [3:49:15<6:14:54,  1.59it/s]
 38%|███▊      | 21800/57600 [3:49:16<6:01:26,  1.65it/s]
                                                         
{'loss': 1.2442, 'learning_rate': 6.613240418118467e-07, 'epoch': 240.62}

 38%|███▊      | 21800/57600 [3:49:16<6:01:26,  1.65it/s]
 38%|███▊      | 21801/57600 [3:49:16<6:09:26,  1.62it/s]
 38%|███▊      | 21802/57600 [3:49:17<6:11:54,  1.60it/s]
 38%|███▊      | 21803/57600 [3:49:18<6:22:02,  1.56it/s]
 38%|███▊      | 21804/57600 [3:49:18<6:14:16,  1.59it/s]
 38%|███▊      | 21805/57600 [3:49:19<6:05:57,  1.63it/s]
 38%|███▊      | 21806/57600 [3:49:19<6:11:06,  1.61it/s]
 38%|███▊      | 21807/57600 [3:49:20<6:10:29,  1.61it/s]
 38%|███▊      | 21808/57600 [3:49:21<6:04:46,  1.64it/s]
 38%|███▊      | 21809/57600 [3:49:21<5:54:04,  1.68it/s]
 38%|███▊      | 21810/57600 [3:49:22<5:52:42,  1.69it/s]
 38%|███▊      | 21811/57600 [3:49:23<6:09:14,  1.62it/s]
 38%|███▊      | 21812/57600 [3:49:23<6:04:32,  1.64it/s]
 38%|███▊      | 21813/57600 [3:49:24<6:06:18,  1.63it/s]
 38%|███▊      | 21814/57600 [3:49:24<6:01:54,  1.65it/s]
 38%|███▊      | 21815/57600 [3:49:25<6:32:40,  1.52it/s]
 38%|███▊      | 21816/57600 [3:49:26<6:34:29,  1.51it/s]
 38%|███▊      | 21817/57600 [3:49:26<6:21:24,  1.56it/s]
 38%|███▊      | 21818/57600 [3:49:27<6:16:38,  1.58it/s]
 38%|███▊      | 21819/57600 [3:49:28<6:04:21,  1.64it/s]
 38%|███▊      | 21820/57600 [3:49:28<6:06:46,  1.63it/s]
                                                         
{'loss': 1.2221, 'learning_rate': 6.610104529616724e-07, 'epoch': 240.84}

 38%|███▊      | 21820/57600 [3:49:28<6:06:46,  1.63it/s]
 38%|███▊      | 21821/57600 [3:49:29<6:03:52,  1.64it/s]
 38%|███▊      | 21822/57600 [3:49:29<6:02:13,  1.65it/s]
 38%|███▊      | 21823/57600 [3:49:30<6:02:57,  1.64it/s]
 38%|███▊      | 21824/57600 [3:49:31<6:02:53,  1.64it/s]
 38%|███▊      | 21825/57600 [3:49:31<6:20:43,  1.57it/s]
 38%|███▊      | 21826/57600 [3:49:32<6:12:25,  1.60it/s]
 38%|███▊      | 21827/57600 [3:49:33<6:16:09,  1.59it/s]
 38%|███▊      | 21828/57600 [3:49:33<6:20:56,  1.57it/s]
 38%|███▊      | 21829/57600 [3:49:34<6:20:04,  1.57it/s]
 38%|███▊      | 21830/57600 [3:49:34<6:13:25,  1.60it/s]
 38%|███▊      | 21831/57600 [3:49:35<6:12:16,  1.60it/s]
 38%|███▊      | 21832/57600 [3:49:36<6:10:13,  1.61it/s]
 38%|███▊      | 21833/57600 [3:49:36<6:08:56,  1.62it/s]
 38%|███▊      | 21834/57600 [3:49:37<6:07:10,  1.62it/s]
 38%|███▊      | 21835/57600 [3:49:38<6:27:51,  1.54it/s]
 38%|███▊      | 21836/57600 [3:49:38<6:26:11,  1.54it/s]
 38%|███▊      | 21837/57600 [3:49:39<6:19:19,  1.57it/s]
 38%|███▊      | 21838/57600 [3:49:39<6:12:36,  1.60it/s]
 38%|███▊      | 21839/57600 [3:49:40<6:12:44,  1.60it/s]
 38%|███▊      | 21840/57600 [3:49:41<6:21:09,  1.56it/s]
                                                         
{'loss': 1.1862, 'learning_rate': 6.606968641114983e-07, 'epoch': 241.06}

 38%|███▊      | 21840/57600 [3:49:41<6:21:09,  1.56it/s]
 38%|███▊      | 21841/57600 [3:49:41<6:28:58,  1.53it/s]
 38%|███▊      | 21842/57600 [3:49:42<6:14:31,  1.59it/s]
 38%|███▊      | 21843/57600 [3:49:43<6:07:16,  1.62it/s]
 38%|███▊      | 21844/57600 [3:49:43<5:58:50,  1.66it/s]
 38%|███▊      | 21845/57600 [3:49:44<6:10:24,  1.61it/s]
 38%|███▊      | 21846/57600 [3:49:45<6:19:13,  1.57it/s]
 38%|███▊      | 21847/57600 [3:49:45<6:15:17,  1.59it/s]
 38%|███▊      | 21848/57600 [3:49:46<6:29:17,  1.53it/s]
 38%|███▊      | 21849/57600 [3:49:46<6:21:51,  1.56it/s]
 38%|███▊      | 21850/57600 [3:49:47<6:19:20,  1.57it/s]
 38%|███▊      | 21851/57600 [3:49:48<6:11:08,  1.61it/s]
 38%|███▊      | 21852/57600 [3:49:48<6:08:13,  1.62it/s]
 38%|███▊      | 21853/57600 [3:49:49<6:14:26,  1.59it/s]
 38%|███▊      | 21854/57600 [3:49:50<6:06:19,  1.63it/s]
 38%|███▊      | 21855/57600 [3:49:50<6:07:17,  1.62it/s]
 38%|███▊      | 21856/57600 [3:49:51<6:20:17,  1.57it/s]
 38%|███▊      | 21857/57600 [3:49:51<6:13:45,  1.59it/s]
 38%|███▊      | 21858/57600 [3:49:52<6:14:44,  1.59it/s]
 38%|███▊      | 21859/57600 [3:49:53<6:05:16,  1.63it/s]
 38%|███▊      | 21860/57600 [3:49:53<6:04:59,  1.63it/s]
                                                         
{'loss': 1.2341, 'learning_rate': 6.60383275261324e-07, 'epoch': 241.28}

 38%|███▊      | 21860/57600 [3:49:53<6:04:59,  1.63it/s]
 38%|███▊      | 21861/57600 [3:49:54<6:03:08,  1.64it/s]
 38%|███▊      | 21862/57600 [3:49:54<6:04:54,  1.63it/s]
 38%|███▊      | 21863/57600 [3:49:55<6:16:27,  1.58it/s]
 38%|███▊      | 21864/57600 [3:49:56<6:29:08,  1.53it/s]
 38%|███▊      | 21865/57600 [3:49:56<6:27:47,  1.54it/s]
 38%|███▊      | 21866/57600 [3:49:57<6:18:47,  1.57it/s]
 38%|███▊      | 21867/57600 [3:49:58<6:11:47,  1.60it/s]
 38%|███▊      | 21868/57600 [3:49:58<6:15:46,  1.58it/s]
 38%|███▊      | 21869/57600 [3:49:59<6:22:26,  1.56it/s]
 38%|███▊      | 21870/57600 [3:50:00<6:23:54,  1.55it/s]
 38%|███▊      | 21871/57600 [3:50:00<6:17:58,  1.58it/s]
 38%|███▊      | 21872/57600 [3:50:01<6:19:23,  1.57it/s]
 38%|███▊      | 21873/57600 [3:50:02<6:16:27,  1.58it/s]
 38%|███▊      | 21874/57600 [3:50:02<6:23:23,  1.55it/s]
 38%|███▊      | 21875/57600 [3:50:03<6:19:02,  1.57it/s]
 38%|███▊      | 21876/57600 [3:50:03<6:13:41,  1.59it/s]
 38%|███▊      | 21877/57600 [3:50:04<6:08:52,  1.61it/s]
 38%|███▊      | 21878/57600 [3:50:05<6:13:01,  1.60it/s]
 38%|███▊      | 21879/57600 [3:50:05<6:13:20,  1.59it/s]
 38%|███▊      | 21880/57600 [3:50:06<6:11:14,  1.60it/s]
                                                         
{'loss': 1.1884, 'learning_rate': 6.600696864111498e-07, 'epoch': 241.5}

 38%|███▊      | 21880/57600 [3:50:06<6:11:14,  1.60it/s]
 38%|███▊      | 21881/57600 [3:50:07<6:07:36,  1.62it/s]
 38%|███▊      | 21882/57600 [3:50:07<6:15:53,  1.58it/s]
 38%|███▊      | 21883/57600 [3:50:08<6:20:45,  1.56it/s]
 38%|███▊      | 21884/57600 [3:50:08<6:19:00,  1.57it/s]
 38%|███▊      | 21885/57600 [3:50:09<6:10:59,  1.60it/s]
 38%|███▊      | 21886/57600 [3:50:10<5:56:39,  1.67it/s]
 38%|███▊      | 21887/57600 [3:50:10<6:00:15,  1.65it/s]
 38%|███▊      | 21888/57600 [3:50:11<6:04:44,  1.63it/s]
 38%|███▊      | 21889/57600 [3:50:11<6:07:43,  1.62it/s]
 38%|███▊      | 21890/57600 [3:50:12<6:09:18,  1.61it/s]
 38%|███▊      | 21891/57600 [3:50:13<6:17:18,  1.58it/s]
 38%|███▊      | 21892/57600 [3:50:13<6:06:58,  1.62it/s]
 38%|███▊      | 21893/57600 [3:50:14<5:56:46,  1.67it/s]
 38%|███▊      | 21894/57600 [3:50:15<6:01:43,  1.65it/s]
 38%|███▊      | 21895/57600 [3:50:15<5:54:31,  1.68it/s]
 38%|███▊      | 21896/57600 [3:50:16<6:00:45,  1.65it/s]
 38%|███▊      | 21897/57600 [3:50:16<6:09:53,  1.61it/s]
 38%|███▊      | 21898/57600 [3:50:17<5:58:57,  1.66it/s]
 38%|███▊      | 21899/57600 [3:50:18<5:58:58,  1.66it/s]
 38%|███▊      | 21900/57600 [3:50:18<5:47:39,  1.71it/s]
                                                         
{'loss': 1.2691, 'learning_rate': 6.597560975609756e-07, 'epoch': 241.72}

 38%|███▊      | 21900/57600 [3:50:18<5:47:39,  1.71it/s]
 38%|███▊      | 21901/57600 [3:50:19<5:57:38,  1.66it/s]
 38%|███▊      | 21902/57600 [3:50:19<5:50:18,  1.70it/s]
 38%|███▊      | 21903/57600 [3:50:20<6:01:43,  1.64it/s]
 38%|███▊      | 21904/57600 [3:50:21<5:58:33,  1.66it/s]
 38%|███▊      | 21905/57600 [3:50:21<5:56:42,  1.67it/s]
 38%|███▊      | 21906/57600 [3:50:22<6:05:37,  1.63it/s]
 38%|███▊      | 21907/57600 [3:50:22<5:59:06,  1.66it/s]
 38%|███▊      | 21908/57600 [3:50:23<5:54:00,  1.68it/s]
 38%|███▊      | 21909/57600 [3:50:24<5:59:50,  1.65it/s]
 38%|███▊      | 21910/57600 [3:50:24<6:07:54,  1.62it/s]
 38%|███▊      | 21911/57600 [3:50:25<6:03:49,  1.63it/s]
 38%|███▊      | 21912/57600 [3:50:25<5:57:27,  1.66it/s]
 38%|███▊      | 21913/57600 [3:50:26<5:56:24,  1.67it/s]
 38%|███▊      | 21914/57600 [3:50:27<5:54:52,  1.68it/s]
 38%|███▊      | 21915/57600 [3:50:27<5:57:47,  1.66it/s]
 38%|███▊      | 21916/57600 [3:50:28<6:03:39,  1.64it/s]
 38%|███▊      | 21917/57600 [3:50:28<6:08:42,  1.61it/s]
 38%|███▊      | 21918/57600 [3:50:29<6:16:16,  1.58it/s]
 38%|███▊      | 21919/57600 [3:50:30<6:05:35,  1.63it/s]
 38%|███▊      | 21920/57600 [3:50:30<6:16:22,  1.58it/s]
                                                         
{'loss': 1.2316, 'learning_rate': 6.594425087108014e-07, 'epoch': 241.94}

 38%|███▊      | 21920/57600 [3:50:30<6:16:22,  1.58it/s]
 38%|███▊      | 21921/57600 [3:50:31<6:07:54,  1.62it/s]
 38%|███▊      | 21922/57600 [3:50:32<6:12:42,  1.60it/s]
 38%|███▊      | 21923/57600 [3:50:32<6:18:46,  1.57it/s]
 38%|███▊      | 21924/57600 [3:50:33<6:21:35,  1.56it/s]
 38%|███▊      | 21925/57600 [3:50:34<6:13:30,  1.59it/s]
 38%|███▊      | 21926/57600 [3:50:34<6:36:11,  1.50it/s]
 38%|███▊      | 21927/57600 [3:50:35<6:18:54,  1.57it/s]
 38%|███▊      | 21928/57600 [3:50:35<6:07:44,  1.62it/s]
 38%|███▊      | 21929/57600 [3:50:36<6:03:58,  1.63it/s]
 38%|███▊      | 21930/57600 [3:50:37<6:07:32,  1.62it/s]
 38%|███▊      | 21931/57600 [3:50:37<6:00:45,  1.65it/s]
 38%|███▊      | 21932/57600 [3:50:38<6:04:06,  1.63it/s]
 38%|███▊      | 21933/57600 [3:50:39<6:16:00,  1.58it/s]
 38%|███▊      | 21934/57600 [3:50:39<6:13:43,  1.59it/s]
 38%|███▊      | 21935/57600 [3:50:40<6:09:18,  1.61it/s]
 38%|███▊      | 21936/57600 [3:50:40<6:21:35,  1.56it/s]
 38%|███▊      | 21937/57600 [3:50:41<6:12:05,  1.60it/s]
 38%|███▊      | 21938/57600 [3:50:42<6:05:46,  1.62it/s]
 38%|███▊      | 21939/57600 [3:50:42<6:08:54,  1.61it/s]
 38%|███▊      | 21940/57600 [3:50:43<6:20:55,  1.56it/s]
                                                         
{'loss': 1.224, 'learning_rate': 6.591289198606271e-07, 'epoch': 242.16}

 38%|███▊      | 21940/57600 [3:50:43<6:20:55,  1.56it/s]
 38%|███▊      | 21941/57600 [3:50:44<6:18:38,  1.57it/s]
 38%|███▊      | 21942/57600 [3:50:44<6:12:52,  1.59it/s]
 38%|███▊      | 21943/57600 [3:50:45<6:07:22,  1.62it/s]
 38%|███▊      | 21944/57600 [3:50:45<6:19:32,  1.57it/s]
 38%|███▊      | 21945/57600 [3:50:46<6:15:17,  1.58it/s]
 38%|███▊      | 21946/57600 [3:50:47<6:15:40,  1.58it/s]
 38%|███▊      | 21947/57600 [3:50:47<6:18:38,  1.57it/s]
 38%|███▊      | 21948/57600 [3:50:48<6:22:26,  1.55it/s]
 38%|███▊      | 21949/57600 [3:50:49<6:07:41,  1.62it/s]
 38%|███▊      | 21950/57600 [3:50:49<6:04:01,  1.63it/s]
 38%|███▊      | 21951/57600 [3:50:50<5:57:05,  1.66it/s]
 38%|███▊      | 21952/57600 [3:50:50<5:48:25,  1.71it/s]
 38%|███▊      | 21953/57600 [3:50:51<5:46:56,  1.71it/s]
 38%|███▊      | 21954/57600 [3:50:52<6:09:58,  1.61it/s]
 38%|███▊      | 21955/57600 [3:50:52<6:02:04,  1.64it/s]
 38%|███▊      | 21956/57600 [3:50:53<6:16:25,  1.58it/s]
 38%|███▊      | 21957/57600 [3:50:53<6:16:22,  1.58it/s]
 38%|███▊      | 21958/57600 [3:50:54<6:10:53,  1.60it/s]
 38%|███▊      | 21959/57600 [3:50:55<6:01:36,  1.64it/s]
 38%|███▊      | 21960/57600 [3:50:55<6:06:54,  1.62it/s]
                                                         
{'loss': 1.256, 'learning_rate': 6.588153310104529e-07, 'epoch': 242.38}

 38%|███▊      | 21960/57600 [3:50:55<6:06:54,  1.62it/s]
 38%|███▊      | 21961/57600 [3:50:56<6:10:16,  1.60it/s]
 38%|███▊      | 21962/57600 [3:50:57<6:13:34,  1.59it/s]
 38%|███▊      | 21963/57600 [3:50:57<6:16:00,  1.58it/s]
 38%|███▊      | 21964/57600 [3:50:58<6:07:17,  1.62it/s]
 38%|███▊      | 21965/57600 [3:50:58<6:08:11,  1.61it/s]
 38%|███▊      | 21966/57600 [3:50:59<5:53:46,  1.68it/s]
 38%|███▊      | 21967/57600 [3:51:00<6:03:01,  1.64it/s]
 38%|███▊      | 21968/57600 [3:51:00<6:09:29,  1.61it/s]
 38%|███▊      | 21969/57600 [3:51:01<6:03:54,  1.63it/s]
 38%|███▊      | 21970/57600 [3:51:01<6:03:12,  1.63it/s]
 38%|███▊      | 21971/57600 [3:51:02<5:59:24,  1.65it/s]
 38%|███▊      | 21972/57600 [3:51:03<5:56:40,  1.66it/s]
 38%|███▊      | 21973/57600 [3:51:03<6:11:20,  1.60it/s]
 38%|███▊      | 21974/57600 [3:51:04<6:18:34,  1.57it/s]
 38%|███▊      | 21975/57600 [3:51:05<6:13:14,  1.59it/s]
 38%|███▊      | 21976/57600 [3:51:05<6:22:53,  1.55it/s]
 38%|███▊      | 21977/57600 [3:51:06<6:16:53,  1.58it/s]
 38%|███▊      | 21978/57600 [3:51:06<6:10:31,  1.60it/s]
 38%|███▊      | 21979/57600 [3:51:07<6:09:10,  1.61it/s]
 38%|███▊      | 21980/57600 [3:51:08<6:37:43,  1.49it/s]
                                                         
{'loss': 1.2487, 'learning_rate': 6.585017421602787e-07, 'epoch': 242.6}

 38%|███▊      | 21980/57600 [3:51:08<6:37:43,  1.49it/s]
 38%|███▊      | 21981/57600 [3:51:08<6:24:44,  1.54it/s]
 38%|███▊      | 21982/57600 [3:51:09<6:17:00,  1.57it/s]
 38%|███▊      | 21983/57600 [3:51:10<6:16:22,  1.58it/s]
 38%|███▊      | 21984/57600 [3:51:10<6:13:51,  1.59it/s]
 38%|███▊      | 21985/57600 [3:51:11<6:02:11,  1.64it/s]
 38%|███▊      | 21986/57600 [3:51:12<5:58:45,  1.65it/s]
 38%|███▊      | 21987/57600 [3:51:12<6:09:54,  1.60it/s]
 38%|███▊      | 21988/57600 [3:51:13<5:56:57,  1.66it/s]
 38%|███▊      | 21989/57600 [3:51:13<6:02:31,  1.64it/s]
 38%|███▊      | 21990/57600 [3:51:14<6:03:17,  1.63it/s]
 38%|███▊      | 21991/57600 [3:51:15<6:01:59,  1.64it/s]
 38%|███▊      | 21992/57600 [3:51:15<6:06:32,  1.62it/s]
 38%|███▊      | 21993/57600 [3:51:16<6:18:16,  1.57it/s]
 38%|███▊      | 21994/57600 [3:51:16<6:10:02,  1.60it/s]
 38%|███▊      | 21995/57600 [3:51:17<6:06:15,  1.62it/s]
 38%|███▊      | 21996/57600 [3:51:18<6:06:22,  1.62it/s]
 38%|███▊      | 21997/57600 [3:51:18<6:08:16,  1.61it/s]
 38%|███▊      | 21998/57600 [3:51:19<6:00:31,  1.65it/s]
 38%|███▊      | 21999/57600 [3:51:20<5:59:27,  1.65it/s]
 38%|███▊      | 22000/57600 [3:51:20<5:57:12,  1.66it/s]
                                                         
{'loss': 1.2238, 'learning_rate': 6.581881533101045e-07, 'epoch': 242.83}

 38%|███▊      | 22000/57600 [3:51:20<5:57:12,  1.66it/s]
 38%|███▊      | 22001/57600 [3:51:21<6:06:00,  1.62it/s]
 38%|███▊      | 22002/57600 [3:51:21<6:05:12,  1.62it/s]
 38%|███▊      | 22003/57600 [3:51:22<6:10:13,  1.60it/s]
 38%|███▊      | 22004/57600 [3:51:23<6:08:23,  1.61it/s]
 38%|███▊      | 22005/57600 [3:51:23<6:12:54,  1.59it/s]
 38%|███▊      | 22006/57600 [3:51:24<6:11:24,  1.60it/s]
 38%|███▊      | 22007/57600 [3:51:24<5:59:38,  1.65it/s]
 38%|███▊      | 22008/57600 [3:51:25<6:09:06,  1.61it/s]
 38%|███▊      | 22009/57600 [3:51:26<6:04:41,  1.63it/s]
 38%|███▊      | 22010/57600 [3:51:26<6:07:14,  1.62it/s]
 38%|███▊      | 22011/57600 [3:51:27<6:05:32,  1.62it/s]
 38%|███▊      | 22012/57600 [3:51:28<6:15:22,  1.58it/s]
 38%|███▊      | 22013/57600 [3:51:28<6:31:38,  1.51it/s]
 38%|███▊      | 22014/57600 [3:51:29<6:20:26,  1.56it/s]
 38%|███▊      | 22015/57600 [3:51:30<6:15:23,  1.58it/s]
 38%|███▊      | 22016/57600 [3:51:30<6:34:39,  1.50it/s]
 38%|███▊      | 22017/57600 [3:51:31<6:32:56,  1.51it/s]
 38%|███▊      | 22018/57600 [3:51:32<6:22:17,  1.55it/s]
 38%|███▊      | 22019/57600 [3:51:32<6:10:08,  1.60it/s]
 38%|███▊      | 22020/57600 [3:51:33<5:58:21,  1.65it/s]
                                                         
{'loss': 1.2165, 'learning_rate': 6.578745644599302e-07, 'epoch': 243.05}

 38%|███▊      | 22020/57600 [3:51:33<5:58:21,  1.65it/s]
 38%|███▊      | 22021/57600 [3:51:33<5:50:47,  1.69it/s]
 38%|███▊      | 22022/57600 [3:51:34<6:09:22,  1.61it/s]
 38%|███▊      | 22023/57600 [3:51:35<6:10:10,  1.60it/s]
 38%|███▊      | 22024/57600 [3:51:35<6:09:30,  1.60it/s]
 38%|███▊      | 22025/57600 [3:51:36<5:54:23,  1.67it/s]
 38%|███▊      | 22026/57600 [3:51:36<5:53:19,  1.68it/s]
 38%|███▊      | 22027/57600 [3:51:37<6:17:27,  1.57it/s]
 38%|███▊      | 22028/57600 [3:51:38<6:13:13,  1.59it/s]
 38%|███▊      | 22029/57600 [3:51:38<6:08:49,  1.61it/s]
 38%|███▊      | 22030/57600 [3:51:39<6:03:17,  1.63it/s]
 38%|███▊      | 22031/57600 [3:51:40<6:07:46,  1.61it/s]
 38%|███▊      | 22032/57600 [3:51:40<5:58:29,  1.65it/s]
 38%|███▊      | 22033/57600 [3:51:41<6:12:28,  1.59it/s]
 38%|███▊      | 22034/57600 [3:51:41<5:58:50,  1.65it/s]
 38%|███▊      | 22035/57600 [3:51:42<6:03:15,  1.63it/s]
 38%|███▊      | 22036/57600 [3:51:43<6:00:15,  1.65it/s]
 38%|███▊      | 22037/57600 [3:51:43<6:18:09,  1.57it/s]
 38%|███▊      | 22038/57600 [3:51:44<6:14:47,  1.58it/s]
 38%|███▊      | 22039/57600 [3:51:44<6:07:00,  1.61it/s]
 38%|███▊      | 22040/57600 [3:51:45<6:17:30,  1.57it/s]
                                                         
{'loss': 1.2546, 'learning_rate': 6.575609756097561e-07, 'epoch': 243.27}

 38%|███▊      | 22040/57600 [3:51:45<6:17:30,  1.57it/s]
 38%|███▊      | 22041/57600 [3:51:46<6:18:38,  1.57it/s]
 38%|███▊      | 22042/57600 [3:51:46<6:07:07,  1.61it/s]
 38%|███▊      | 22043/57600 [3:51:47<6:14:57,  1.58it/s]
 38%|███▊      | 22044/57600 [3:51:48<6:32:26,  1.51it/s]
 38%|███▊      | 22045/57600 [3:51:48<6:32:51,  1.51it/s]
 38%|███▊      | 22046/57600 [3:51:49<6:27:17,  1.53it/s]
 38%|███▊      | 22047/57600 [3:51:50<6:28:00,  1.53it/s]
 38%|███▊      | 22048/57600 [3:51:50<6:18:25,  1.57it/s]
 38%|███▊      | 22049/57600 [3:51:51<6:03:09,  1.63it/s]
 38%|███▊      | 22050/57600 [3:51:51<6:00:49,  1.64it/s]
 38%|███▊      | 22051/57600 [3:51:52<6:07:13,  1.61it/s]
 38%|███▊      | 22052/57600 [3:51:53<5:58:10,  1.65it/s]
 38%|███▊      | 22053/57600 [3:51:53<6:05:51,  1.62it/s]
 38%|███▊      | 22054/57600 [3:51:54<5:59:03,  1.65it/s]
 38%|███▊      | 22055/57600 [3:51:54<5:56:52,  1.66it/s]
 38%|███▊      | 22056/57600 [3:51:55<6:04:59,  1.62it/s]
 38%|███▊      | 22057/57600 [3:51:56<6:08:34,  1.61it/s]
 38%|███▊      | 22058/57600 [3:51:56<6:06:34,  1.62it/s]
 38%|███▊      | 22059/57600 [3:51:57<6:04:10,  1.63it/s]
 38%|███▊      | 22060/57600 [3:51:58<6:06:25,  1.62it/s]
                                                         
{'loss': 1.2281, 'learning_rate': 6.57247386759582e-07, 'epoch': 243.49}

 38%|███▊      | 22060/57600 [3:51:58<6:06:25,  1.62it/s]
 38%|███▊      | 22061/57600 [3:51:58<6:10:54,  1.60it/s]
 38%|███▊      | 22062/57600 [3:51:59<6:20:49,  1.56it/s]
 38%|███▊      | 22063/57600 [3:52:00<6:21:55,  1.55it/s]
 38%|███▊      | 22064/57600 [3:52:00<6:27:22,  1.53it/s]
 38%|███▊      | 22065/57600 [3:52:01<6:24:30,  1.54it/s]
 38%|███▊      | 22066/57600 [3:52:02<6:26:43,  1.53it/s]
 38%|███▊      | 22067/57600 [3:52:02<6:25:35,  1.54it/s]
 38%|███▊      | 22068/57600 [3:52:03<6:32:26,  1.51it/s]
 38%|███▊      | 22069/57600 [3:52:04<6:25:55,  1.53it/s]
 38%|███▊      | 22070/57600 [3:52:04<6:14:12,  1.58it/s]
 38%|███▊      | 22071/57600 [3:52:05<6:08:42,  1.61it/s]
 38%|███▊      | 22072/57600 [3:52:05<6:03:58,  1.63it/s]
 38%|███▊      | 22073/57600 [3:52:06<6:06:16,  1.62it/s]
 38%|███▊      | 22074/57600 [3:52:07<6:02:06,  1.64it/s]
 38%|███▊      | 22075/57600 [3:52:07<5:52:40,  1.68it/s]
 38%|███▊      | 22076/57600 [3:52:08<6:02:20,  1.63it/s]
 38%|███▊      | 22077/57600 [3:52:08<6:04:31,  1.62it/s]
 38%|███▊      | 22078/57600 [3:52:09<5:58:33,  1.65it/s]
 38%|███▊      | 22079/57600 [3:52:10<5:50:02,  1.69it/s]
 38%|███▊      | 22080/57600 [3:52:10<6:00:10,  1.64it/s]
                                                         
{'loss': 1.2472, 'learning_rate': 6.569337979094076e-07, 'epoch': 243.71}

 38%|███▊      | 22080/57600 [3:52:10<6:00:10,  1.64it/s]
 38%|███▊      | 22081/57600 [3:52:11<5:52:07,  1.68it/s]
 38%|███▊      | 22082/57600 [3:52:11<6:01:14,  1.64it/s]
 38%|███▊      | 22083/57600 [3:52:12<6:06:05,  1.62it/s]
 38%|███▊      | 22084/57600 [3:52:13<6:06:18,  1.62it/s]
 38%|███▊      | 22085/57600 [3:52:13<6:00:29,  1.64it/s]
 38%|███▊      | 22086/57600 [3:52:14<5:54:53,  1.67it/s]
 38%|███▊      | 22087/57600 [3:52:14<5:51:47,  1.68it/s]
 38%|███▊      | 22088/57600 [3:52:15<5:58:47,  1.65it/s]
 38%|███▊      | 22089/57600 [3:52:16<6:04:56,  1.62it/s]
 38%|███▊      | 22090/57600 [3:52:16<6:19:02,  1.56it/s]
 38%|███▊      | 22091/57600 [3:52:17<6:15:30,  1.58it/s]
 38%|███▊      | 22092/57600 [3:52:18<6:04:29,  1.62it/s]
 38%|███▊      | 22093/57600 [3:52:18<6:18:45,  1.56it/s]
 38%|███▊      | 22094/57600 [3:52:19<6:04:47,  1.62it/s]
 38%|███▊      | 22095/57600 [3:52:19<6:06:13,  1.62it/s]
 38%|███▊      | 22096/57600 [3:52:20<6:14:17,  1.58it/s]
 38%|███▊      | 22097/57600 [3:52:21<6:10:36,  1.60it/s]
 38%|███▊      | 22098/57600 [3:52:21<6:10:55,  1.60it/s]
 38%|███▊      | 22099/57600 [3:52:22<6:27:43,  1.53it/s]
 38%|███▊      | 22100/57600 [3:52:23<6:22:43,  1.55it/s]
                                                         
{'loss': 1.2454, 'learning_rate': 6.566202090592335e-07, 'epoch': 243.93}

 38%|███▊      | 22100/57600 [3:52:23<6:22:43,  1.55it/s]
 38%|███▊      | 22101/57600 [3:52:23<6:18:06,  1.56it/s]
 38%|███▊      | 22102/57600 [3:52:24<6:09:54,  1.60it/s]
 38%|███▊      | 22103/57600 [3:52:24<6:06:43,  1.61it/s]
 38%|███▊      | 22104/57600 [3:52:25<6:01:53,  1.63it/s]
 38%|███▊      | 22105/57600 [3:52:26<6:04:33,  1.62it/s]
 38%|███▊      | 22106/57600 [3:52:26<6:08:01,  1.61it/s]
 38%|███▊      | 22107/57600 [3:52:27<6:20:58,  1.55it/s]
 38%|███▊      | 22108/57600 [3:52:28<6:21:58,  1.55it/s]
 38%|███▊      | 22109/57600 [3:52:28<6:09:26,  1.60it/s]
 38%|███▊      | 22110/57600 [3:52:29<6:09:53,  1.60it/s]
 38%|███▊      | 22111/57600 [3:52:30<6:23:15,  1.54it/s]
 38%|███▊      | 22112/57600 [3:52:30<6:21:33,  1.55it/s]
 38%|███▊      | 22113/57600 [3:52:31<6:22:45,  1.55it/s]
 38%|███▊      | 22114/57600 [3:52:32<6:27:25,  1.53it/s]
 38%|███▊      | 22115/57600 [3:52:32<6:27:07,  1.53it/s]
 38%|███▊      | 22116/57600 [3:52:33<6:22:31,  1.55it/s]
 38%|███▊      | 22117/57600 [3:52:33<6:14:52,  1.58it/s]
 38%|███▊      | 22118/57600 [3:52:34<6:09:55,  1.60it/s]
 38%|███▊      | 22119/57600 [3:52:35<6:03:16,  1.63it/s]
 38%|███▊      | 22120/57600 [3:52:35<6:14:00,  1.58it/s]
                                                         
{'loss': 1.1844, 'learning_rate': 6.563066202090592e-07, 'epoch': 244.15}

 38%|███▊      | 22120/57600 [3:52:35<6:14:00,  1.58it/s]
 38%|███▊      | 22121/57600 [3:52:36<6:24:28,  1.54it/s]
 38%|███▊      | 22122/57600 [3:52:37<6:11:39,  1.59it/s]
 38%|███▊      | 22123/57600 [3:52:37<6:08:42,  1.60it/s]
 38%|███▊      | 22124/57600 [3:52:38<6:06:10,  1.61it/s]
 38%|███▊      | 22125/57600 [3:52:38<5:59:51,  1.64it/s]
 38%|███▊      | 22126/57600 [3:52:39<6:20:37,  1.55it/s]
 38%|███▊      | 22127/57600 [3:52:40<6:23:16,  1.54it/s]
 38%|███▊      | 22128/57600 [3:52:40<6:21:02,  1.55it/s]
 38%|███▊      | 22129/57600 [3:52:41<6:33:28,  1.50it/s]
 38%|███▊      | 22130/57600 [3:52:42<6:21:51,  1.55it/s]
 38%|███▊      | 22131/57600 [3:52:42<6:21:22,  1.55it/s]
 38%|███▊      | 22132/57600 [3:52:43<6:18:02,  1.56it/s]
 38%|███▊      | 22133/57600 [3:52:44<6:24:10,  1.54it/s]
 38%|███▊      | 22134/57600 [3:52:44<6:15:45,  1.57it/s]
 38%|███▊      | 22135/57600 [3:52:45<6:05:25,  1.62it/s]
 38%|███▊      | 22136/57600 [3:52:45<6:04:00,  1.62it/s]
 38%|███▊      | 22137/57600 [3:52:46<6:07:58,  1.61it/s]
 38%|███▊      | 22138/57600 [3:52:47<6:08:46,  1.60it/s]
 38%|███▊      | 22139/57600 [3:52:47<6:02:41,  1.63it/s]
 38%|███▊      | 22140/57600 [3:52:48<6:09:45,  1.60it/s]
                                                         
{'loss': 1.2077, 'learning_rate': 6.55993031358885e-07, 'epoch': 244.37}

 38%|███▊      | 22140/57600 [3:52:48<6:09:45,  1.60it/s]
 38%|███▊      | 22141/57600 [3:52:49<6:09:31,  1.60it/s]
 38%|███▊      | 22142/57600 [3:52:49<6:09:12,  1.60it/s]
 38%|███▊      | 22143/57600 [3:52:50<6:03:46,  1.62it/s]
 38%|███▊      | 22144/57600 [3:52:50<6:04:01,  1.62it/s]
 38%|███▊      | 22145/57600 [3:52:51<6:20:20,  1.55it/s]
 38%|███▊      | 22146/57600 [3:52:52<6:07:13,  1.61it/s]
 38%|███▊      | 22147/57600 [3:52:52<5:59:33,  1.64it/s]
 38%|███▊      | 22148/57600 [3:52:53<6:07:39,  1.61it/s]
 38%|███▊      | 22149/57600 [3:52:54<6:00:48,  1.64it/s]
 38%|███▊      | 22150/57600 [3:52:54<6:01:13,  1.64it/s]
 38%|███▊      | 22151/57600 [3:52:55<6:14:26,  1.58it/s]
 38%|███▊      | 22152/57600 [3:52:55<6:08:19,  1.60it/s]
 38%|███▊      | 22153/57600 [3:52:56<6:06:46,  1.61it/s]
 38%|███▊      | 22154/57600 [3:52:57<5:53:10,  1.67it/s]
 38%|███▊      | 22155/57600 [3:52:57<5:47:04,  1.70it/s]
 38%|███▊      | 22156/57600 [3:52:58<5:55:53,  1.66it/s]
 38%|███▊      | 22157/57600 [3:52:58<6:08:13,  1.60it/s]
 38%|███▊      | 22158/57600 [3:52:59<6:15:50,  1.57it/s]
 38%|███▊      | 22159/57600 [3:53:00<6:07:44,  1.61it/s]
 38%|███▊      | 22160/57600 [3:53:00<6:08:11,  1.60it/s]
                                                         
{'loss': 1.266, 'learning_rate': 6.556794425087107e-07, 'epoch': 244.59}

 38%|███▊      | 22160/57600 [3:53:00<6:08:11,  1.60it/s]
 38%|███▊      | 22161/57600 [3:53:01<6:07:46,  1.61it/s]
 38%|███▊      | 22162/57600 [3:53:02<6:10:23,  1.59it/s]
 38%|███▊      | 22163/57600 [3:53:02<6:08:44,  1.60it/s]
 38%|███▊      | 22164/57600 [3:53:03<6:16:22,  1.57it/s]
 38%|███▊      | 22165/57600 [3:53:04<6:16:41,  1.57it/s]
 38%|███▊      | 22166/57600 [3:53:04<6:14:39,  1.58it/s]
 38%|███▊      | 22167/57600 [3:53:05<6:28:43,  1.52it/s]
 38%|███▊      | 22168/57600 [3:53:06<6:28:12,  1.52it/s]
 38%|███▊      | 22169/57600 [3:53:06<6:16:29,  1.57it/s]
 38%|███▊      | 22170/57600 [3:53:07<6:04:33,  1.62it/s]
 38%|███▊      | 22171/57600 [3:53:07<6:01:35,  1.63it/s]
 38%|███▊      | 22172/57600 [3:53:08<6:02:07,  1.63it/s]
 38%|███▊      | 22173/57600 [3:53:09<6:17:22,  1.56it/s]
 38%|███▊      | 22174/57600 [3:53:09<6:13:03,  1.58it/s]
 38%|███▊      | 22175/57600 [3:53:10<6:12:36,  1.58it/s]
 38%|███▊      | 22176/57600 [3:53:10<6:11:57,  1.59it/s]
 39%|███▊      | 22177/57600 [3:53:11<6:18:21,  1.56it/s]
 39%|███▊      | 22178/57600 [3:53:12<6:07:35,  1.61it/s]
 39%|███▊      | 22179/57600 [3:53:12<6:13:02,  1.58it/s]
 39%|███▊      | 22180/57600 [3:53:13<6:07:55,  1.60it/s]
                                                         
{'loss': 1.2259, 'learning_rate': 6.553658536585366e-07, 'epoch': 244.81}

 39%|███▊      | 22180/57600 [3:53:13<6:07:55,  1.60it/s]
 39%|███▊      | 22181/57600 [3:53:14<6:03:21,  1.62it/s]
 39%|███▊      | 22182/57600 [3:53:14<5:54:02,  1.67it/s]
 39%|███▊      | 22183/57600 [3:53:15<6:09:19,  1.60it/s]
 39%|███▊      | 22184/57600 [3:53:15<6:02:43,  1.63it/s]
 39%|███▊      | 22185/57600 [3:53:16<5:58:24,  1.65it/s]
 39%|███▊      | 22186/57600 [3:53:17<5:55:05,  1.66it/s]
 39%|███▊      | 22187/57600 [3:53:17<5:56:43,  1.65it/s]
 39%|███▊      | 22188/57600 [3:53:18<5:54:26,  1.67it/s]
 39%|███▊      | 22189/57600 [3:53:18<5:55:51,  1.66it/s]
 39%|███▊      | 22190/57600 [3:53:19<5:56:49,  1.65it/s]
 39%|███▊      | 22191/57600 [3:53:20<5:51:54,  1.68it/s]
 39%|███▊      | 22192/57600 [3:53:20<5:50:41,  1.68it/s]
 39%|███▊      | 22193/57600 [3:53:21<5:48:29,  1.69it/s]
 39%|███▊      | 22194/57600 [3:53:21<5:51:59,  1.68it/s]
 39%|███▊      | 22195/57600 [3:53:22<5:54:04,  1.67it/s]
 39%|███▊      | 22196/57600 [3:53:23<5:51:10,  1.68it/s]
 39%|███▊      | 22197/57600 [3:53:23<5:51:18,  1.68it/s]
 39%|███▊      | 22198/57600 [3:53:24<5:59:32,  1.64it/s]
 39%|███▊      | 22199/57600 [3:53:24<5:52:07,  1.68it/s]
 39%|███▊      | 22200/57600 [3:53:25<6:03:25,  1.62it/s]
                                                         
{'loss': 1.3201, 'learning_rate': 6.550522648083623e-07, 'epoch': 245.03}

 39%|███▊      | 22200/57600 [3:53:25<6:03:25,  1.62it/s]
 39%|███▊      | 22201/57600 [3:53:26<5:57:29,  1.65it/s]
 39%|███▊      | 22202/57600 [3:53:26<6:06:25,  1.61it/s]
 39%|███▊      | 22203/57600 [3:53:27<5:57:54,  1.65it/s]
 39%|███▊      | 22204/57600 [3:53:27<5:59:09,  1.64it/s]
 39%|███▊      | 22205/57600 [3:53:28<6:00:07,  1.64it/s]
 39%|███▊      | 22206/57600 [3:53:29<5:50:25,  1.68it/s]
 39%|███▊      | 22207/57600 [3:53:29<5:45:15,  1.71it/s]
 39%|███▊      | 22208/57600 [3:53:30<5:57:31,  1.65it/s]
 39%|███▊      | 22209/57600 [3:53:30<5:55:00,  1.66it/s]
 39%|███▊      | 22210/57600 [3:53:31<5:48:37,  1.69it/s]
 39%|███▊      | 22211/57600 [3:53:32<5:49:20,  1.69it/s]
 39%|███▊      | 22212/57600 [3:53:32<5:44:48,  1.71it/s]
 39%|███▊      | 22213/57600 [3:53:33<5:41:01,  1.73it/s]
 39%|███▊      | 22214/57600 [3:53:33<5:58:03,  1.65it/s]
 39%|███▊      | 22215/57600 [3:53:34<6:03:54,  1.62it/s]
 39%|███▊      | 22216/57600 [3:53:35<6:11:11,  1.59it/s]
 39%|███▊      | 22217/57600 [3:53:35<6:04:14,  1.62it/s]
 39%|███▊      | 22218/57600 [3:53:36<6:12:47,  1.58it/s]
 39%|███▊      | 22219/57600 [3:53:37<6:15:19,  1.57it/s]
 39%|███▊      | 22220/57600 [3:53:37<6:14:12,  1.58it/s]
                                                         
{'loss': 1.2751, 'learning_rate': 6.547386759581881e-07, 'epoch': 245.25}

 39%|███▊      | 22220/57600 [3:53:37<6:14:12,  1.58it/s]
 39%|███▊      | 22221/57600 [3:53:38<6:11:14,  1.59it/s]
 39%|███▊      | 22222/57600 [3:53:38<6:07:41,  1.60it/s]
 39%|███▊      | 22223/57600 [3:53:39<6:15:58,  1.57it/s]
 39%|███▊      | 22224/57600 [3:53:40<6:13:33,  1.58it/s]
 39%|███▊      | 22225/57600 [3:53:40<6:11:15,  1.59it/s]
 39%|███▊      | 22226/57600 [3:53:41<6:13:20,  1.58it/s]
 39%|███▊      | 22227/57600 [3:53:42<6:20:51,  1.55it/s]
 39%|███▊      | 22228/57600 [3:53:42<6:24:39,  1.53it/s]
 39%|███▊      | 22229/57600 [3:53:43<6:25:34,  1.53it/s]
 39%|███▊      | 22230/57600 [3:53:44<6:20:23,  1.55it/s]
 39%|███▊      | 22231/57600 [3:53:44<6:02:51,  1.62it/s]
 39%|███▊      | 22232/57600 [3:53:45<5:55:32,  1.66it/s]
 39%|███▊      | 22233/57600 [3:53:45<5:48:38,  1.69it/s]
 39%|███▊      | 22234/57600 [3:53:46<6:01:33,  1.63it/s]
 39%|███▊      | 22235/57600 [3:53:47<6:04:59,  1.61it/s]
 39%|███▊      | 22236/57600 [3:53:47<6:07:14,  1.60it/s]
 39%|███▊      | 22237/57600 [3:53:48<6:02:55,  1.62it/s]
 39%|███▊      | 22238/57600 [3:53:48<6:07:36,  1.60it/s]
 39%|███▊      | 22239/57600 [3:53:49<6:01:20,  1.63it/s]
 39%|███▊      | 22240/57600 [3:53:50<6:14:35,  1.57it/s]
                                                         
{'loss': 1.2238, 'learning_rate': 6.544250871080139e-07, 'epoch': 245.47}

 39%|███▊      | 22240/57600 [3:53:50<6:14:35,  1.57it/s]
 39%|███▊      | 22241/57600 [3:53:50<6:14:11,  1.57it/s]
 39%|███▊      | 22242/57600 [3:53:51<6:13:30,  1.58it/s]
 39%|███▊      | 22243/57600 [3:53:52<6:02:56,  1.62it/s]
 39%|███▊      | 22244/57600 [3:53:52<5:57:20,  1.65it/s]
 39%|███▊      | 22245/57600 [3:53:53<6:16:16,  1.57it/s]
 39%|███▊      | 22246/57600 [3:53:54<6:21:24,  1.54it/s]
 39%|███▊      | 22247/57600 [3:53:54<6:19:53,  1.55it/s]
 39%|███▊      | 22248/57600 [3:53:55<6:30:32,  1.51it/s]
 39%|███▊      | 22249/57600 [3:53:55<6:18:49,  1.56it/s]
 39%|███▊      | 22250/57600 [3:53:56<6:19:00,  1.55it/s]
 39%|███▊      | 22251/57600 [3:53:57<6:15:21,  1.57it/s]
 39%|███▊      | 22252/57600 [3:53:57<6:10:27,  1.59it/s]
 39%|███▊      | 22253/57600 [3:53:58<6:05:18,  1.61it/s]
 39%|███▊      | 22254/57600 [3:53:59<5:55:18,  1.66it/s]
 39%|███▊      | 22255/57600 [3:53:59<5:50:15,  1.68it/s]
 39%|███▊      | 22256/57600 [3:54:00<5:49:35,  1.69it/s]
 39%|███▊      | 22257/57600 [3:54:00<6:01:33,  1.63it/s]
 39%|███▊      | 22258/57600 [3:54:01<6:05:39,  1.61it/s]
 39%|███▊      | 22259/57600 [3:54:02<6:13:29,  1.58it/s]
 39%|███▊      | 22260/57600 [3:54:02<6:08:14,  1.60it/s]
                                                         
{'loss': 1.256, 'learning_rate': 6.541114982578398e-07, 'epoch': 245.7}

 39%|███▊      | 22260/57600 [3:54:02<6:08:14,  1.60it/s]
 39%|███▊      | 22261/57600 [3:54:03<6:18:57,  1.55it/s]
 39%|███▊      | 22262/57600 [3:54:04<6:17:00,  1.56it/s]
 39%|███▊      | 22263/57600 [3:54:04<6:15:38,  1.57it/s]
 39%|███▊      | 22264/57600 [3:54:05<6:07:11,  1.60it/s]
 39%|███▊      | 22265/57600 [3:54:05<6:17:01,  1.56it/s]
 39%|███▊      | 22266/57600 [3:54:06<6:20:07,  1.55it/s]
 39%|███▊      | 22267/57600 [3:54:07<6:10:08,  1.59it/s]
 39%|███▊      | 22268/57600 [3:54:07<6:23:51,  1.53it/s]
 39%|███▊      | 22269/57600 [3:54:08<6:22:50,  1.54it/s]
 39%|███▊      | 22270/57600 [3:54:09<6:23:49,  1.53it/s]
 39%|███▊      | 22271/57600 [3:54:09<6:28:37,  1.52it/s]
 39%|███▊      | 22272/57600 [3:54:10<6:21:55,  1.54it/s]
 39%|███▊      | 22273/57600 [3:54:11<6:11:19,  1.59it/s]
 39%|███▊      | 22274/57600 [3:54:11<6:03:05,  1.62it/s]
 39%|███▊      | 22275/57600 [3:54:12<5:53:11,  1.67it/s]
 39%|███▊      | 22276/57600 [3:54:12<5:51:01,  1.68it/s]
 39%|███▊      | 22277/57600 [3:54:13<5:49:52,  1.68it/s]
 39%|███▊      | 22278/57600 [3:54:14<6:01:55,  1.63it/s]
 39%|███▊      | 22279/57600 [3:54:14<6:04:42,  1.61it/s]
 39%|███▊      | 22280/57600 [3:54:15<6:19:31,  1.55it/s]
                                                         
{'loss': 1.2226, 'learning_rate': 6.537979094076654e-07, 'epoch': 245.92}

 39%|███▊      | 22280/57600 [3:54:15<6:19:31,  1.55it/s]
 39%|███▊      | 22281/57600 [3:54:16<6:11:43,  1.58it/s]
 39%|███▊      | 22282/57600 [3:54:16<6:00:47,  1.63it/s]
 39%|███▊      | 22283/57600 [3:54:17<6:01:20,  1.63it/s]
 39%|███▊      | 22284/57600 [3:54:17<6:00:33,  1.63it/s]
 39%|███▊      | 22285/57600 [3:54:18<6:05:42,  1.61it/s]
 39%|███▊      | 22286/57600 [3:54:19<6:01:09,  1.63it/s]
 39%|███▊      | 22287/57600 [3:54:19<6:03:40,  1.62it/s]
 39%|███▊      | 22288/57600 [3:54:20<6:22:30,  1.54it/s]
 39%|███▊      | 22289/57600 [3:54:21<6:37:56,  1.48it/s]
 39%|███▊      | 22290/57600 [3:54:21<6:28:25,  1.52it/s]
 39%|███▊      | 22291/57600 [3:54:22<6:16:47,  1.56it/s]
 39%|███▊      | 22292/57600 [3:54:23<6:17:34,  1.56it/s]
 39%|███▊      | 22293/57600 [3:54:23<6:19:21,  1.55it/s]
 39%|███▊      | 22294/57600 [3:54:24<6:14:53,  1.57it/s]
 39%|███▊      | 22295/57600 [3:54:24<6:11:49,  1.58it/s]
 39%|███▊      | 22296/57600 [3:54:25<6:09:55,  1.59it/s]
 39%|███▊      | 22297/57600 [3:54:26<6:14:45,  1.57it/s]
 39%|███▊      | 22298/57600 [3:54:26<6:16:13,  1.56it/s]
 39%|███▊      | 22299/57600 [3:54:27<6:10:53,  1.59it/s]
 39%|███▊      | 22300/57600 [3:54:28<6:23:33,  1.53it/s]
                                                         
{'loss': 1.2107, 'learning_rate': 6.534843205574913e-07, 'epoch': 246.14}

 39%|███▊      | 22300/57600 [3:54:28<6:23:33,  1.53it/s]
 39%|███▊      | 22301/57600 [3:54:28<6:27:35,  1.52it/s]
 39%|███▊      | 22302/57600 [3:54:29<6:21:51,  1.54it/s]
 39%|███▊      | 22303/57600 [3:54:30<6:19:11,  1.55it/s]
 39%|███▊      | 22304/57600 [3:54:30<6:05:32,  1.61it/s]
 39%|███▊      | 22305/57600 [3:54:31<5:57:24,  1.65it/s]
 39%|███▊      | 22306/57600 [3:54:31<6:02:58,  1.62it/s]
 39%|███▊      | 22307/57600 [3:54:32<5:59:32,  1.64it/s]
 39%|███▊      | 22308/57600 [3:54:33<5:55:10,  1.66it/s]
 39%|███▊      | 22309/57600 [3:54:33<5:56:54,  1.65it/s]
 39%|███▊      | 22310/57600 [3:54:34<5:50:11,  1.68it/s]
 39%|███▊      | 22311/57600 [3:54:34<5:47:53,  1.69it/s]
 39%|███▊      | 22312/57600 [3:54:35<6:06:01,  1.61it/s]
 39%|███▊      | 22313/57600 [3:54:36<6:02:23,  1.62it/s]
 39%|███▊      | 22314/57600 [3:54:36<6:12:57,  1.58it/s]
 39%|███▊      | 22315/57600 [3:54:37<6:05:27,  1.61it/s]
 39%|███▊      | 22316/57600 [3:54:38<6:03:28,  1.62it/s]
 39%|███▊      | 22317/57600 [3:54:38<6:12:17,  1.58it/s]
 39%|███▊      | 22318/57600 [3:54:39<6:10:20,  1.59it/s]
 39%|███▊      | 22319/57600 [3:54:39<6:12:23,  1.58it/s]
 39%|███▉      | 22320/57600 [3:54:40<6:02:46,  1.62it/s]
                                                         
{'loss': 1.2401, 'learning_rate': 6.531707317073171e-07, 'epoch': 246.36}

 39%|███▉      | 22320/57600 [3:54:40<6:02:46,  1.62it/s]
 39%|███▉      | 22321/57600 [3:54:41<6:01:41,  1.63it/s]
 39%|███▉      | 22322/57600 [3:54:41<6:03:23,  1.62it/s]
 39%|███▉      | 22323/57600 [3:54:42<6:07:35,  1.60it/s]
 39%|███▉      | 22324/57600 [3:54:42<5:59:57,  1.63it/s]
 39%|███▉      | 22325/57600 [3:54:43<6:09:10,  1.59it/s]
 39%|███▉      | 22326/57600 [3:54:44<6:00:55,  1.63it/s]
 39%|███▉      | 22327/57600 [3:54:44<6:05:39,  1.61it/s]
 39%|███▉      | 22328/57600 [3:54:45<6:09:29,  1.59it/s]
 39%|███▉      | 22329/57600 [3:54:46<6:05:29,  1.61it/s]
 39%|███▉      | 22330/57600 [3:54:46<5:58:12,  1.64it/s]
 39%|███▉      | 22331/57600 [3:54:47<5:56:55,  1.65it/s]
 39%|███▉      | 22332/57600 [3:54:47<5:51:24,  1.67it/s]
 39%|███▉      | 22333/57600 [3:54:48<5:49:49,  1.68it/s]
 39%|███▉      | 22334/57600 [3:54:49<5:49:19,  1.68it/s]
 39%|███▉      | 22335/57600 [3:54:49<6:02:01,  1.62it/s]
 39%|███▉      | 22336/57600 [3:54:50<6:01:38,  1.63it/s]
 39%|███▉      | 22337/57600 [3:54:50<6:03:15,  1.62it/s]
 39%|███▉      | 22338/57600 [3:54:51<5:59:22,  1.64it/s]
 39%|███▉      | 22339/57600 [3:54:52<6:07:14,  1.60it/s]
 39%|███▉      | 22340/57600 [3:54:52<6:10:21,  1.59it/s]
                                                         
{'loss': 1.2591, 'learning_rate': 6.528571428571429e-07, 'epoch': 246.58}

 39%|███▉      | 22340/57600 [3:54:52<6:10:21,  1.59it/s]
 39%|███▉      | 22341/57600 [3:54:53<6:07:25,  1.60it/s]
 39%|███▉      | 22342/57600 [3:54:54<5:59:59,  1.63it/s]
 39%|███▉      | 22343/57600 [3:54:54<5:56:00,  1.65it/s]
 39%|███▉      | 22344/57600 [3:54:55<5:48:22,  1.69it/s]
 39%|███▉      | 22345/57600 [3:54:55<6:08:05,  1.60it/s]
 39%|███▉      | 22346/57600 [3:54:56<6:08:42,  1.59it/s]
 39%|███▉      | 22347/57600 [3:54:57<6:15:35,  1.56it/s]
 39%|███▉      | 22348/57600 [3:54:57<6:02:53,  1.62it/s]
 39%|███▉      | 22349/57600 [3:54:58<6:08:10,  1.60it/s]
 39%|███▉      | 22350/57600 [3:54:59<6:02:03,  1.62it/s]
 39%|███▉      | 22351/57600 [3:54:59<5:56:30,  1.65it/s]
 39%|███▉      | 22352/57600 [3:55:00<6:09:55,  1.59it/s]
 39%|███▉      | 22353/57600 [3:55:00<6:08:15,  1.60it/s]
 39%|███▉      | 22354/57600 [3:55:01<6:02:15,  1.62it/s]
 39%|███▉      | 22355/57600 [3:55:02<6:06:38,  1.60it/s]
 39%|███▉      | 22356/57600 [3:55:02<6:10:28,  1.59it/s]
 39%|███▉      | 22357/57600 [3:55:03<6:01:31,  1.62it/s]
 39%|███▉      | 22358/57600 [3:55:03<5:53:19,  1.66it/s]
 39%|███▉      | 22359/57600 [3:55:04<6:07:23,  1.60it/s]
 39%|███▉      | 22360/57600 [3:55:05<6:11:33,  1.58it/s]
                                                         
{'loss': 1.2154, 'learning_rate': 6.525435540069686e-07, 'epoch': 246.8}

 39%|███▉      | 22360/57600 [3:55:05<6:11:33,  1.58it/s]
 39%|███▉      | 22361/57600 [3:55:05<6:06:43,  1.60it/s]
 39%|███▉      | 22362/57600 [3:55:06<5:58:53,  1.64it/s]
 39%|███▉      | 22363/57600 [3:55:07<5:58:23,  1.64it/s]
 39%|███▉      | 22364/57600 [3:55:07<6:00:17,  1.63it/s]
 39%|███▉      | 22365/57600 [3:55:08<5:57:14,  1.64it/s]
 39%|███▉      | 22366/57600 [3:55:08<6:05:21,  1.61it/s]
 39%|███▉      | 22367/57600 [3:55:09<6:00:51,  1.63it/s]
 39%|███▉      | 22368/57600 [3:55:10<5:47:47,  1.69it/s]
 39%|███▉      | 22369/57600 [3:55:10<5:47:27,  1.69it/s]
 39%|███▉      | 22370/57600 [3:55:11<5:48:20,  1.69it/s]
 39%|███▉      | 22371/57600 [3:55:11<6:05:06,  1.61it/s]
 39%|███▉      | 22372/57600 [3:55:12<5:55:40,  1.65it/s]
 39%|███▉      | 22373/57600 [3:55:13<5:54:48,  1.65it/s]
 39%|███▉      | 22374/57600 [3:55:13<5:49:16,  1.68it/s]
 39%|███▉      | 22375/57600 [3:55:14<5:51:29,  1.67it/s]
 39%|███▉      | 22376/57600 [3:55:14<5:49:24,  1.68it/s]
 39%|███▉      | 22377/57600 [3:55:15<5:45:51,  1.70it/s]
 39%|███▉      | 22378/57600 [3:55:16<5:41:53,  1.72it/s]
 39%|███▉      | 22379/57600 [3:55:16<6:03:55,  1.61it/s]
 39%|███▉      | 22380/57600 [3:55:17<6:04:32,  1.61it/s]
                                                         
{'loss': 1.2455, 'learning_rate': 6.522299651567944e-07, 'epoch': 247.02}

 39%|███▉      | 22380/57600 [3:55:17<6:04:32,  1.61it/s]
 39%|███▉      | 22381/57600 [3:55:17<6:04:26,  1.61it/s]
 39%|███▉      | 22382/57600 [3:55:18<5:59:55,  1.63it/s]
 39%|███▉      | 22383/57600 [3:55:19<6:01:25,  1.62it/s]
 39%|███▉      | 22384/57600 [3:55:19<5:52:01,  1.67it/s]
 39%|███▉      | 22385/57600 [3:55:20<5:47:00,  1.69it/s]
 39%|███▉      | 22386/57600 [3:55:20<5:47:20,  1.69it/s]
 39%|███▉      | 22387/57600 [3:55:21<5:48:52,  1.68it/s]
 39%|███▉      | 22388/57600 [3:55:22<5:48:19,  1.68it/s]
 39%|███▉      | 22389/57600 [3:55:22<5:41:36,  1.72it/s]
 39%|███▉      | 22390/57600 [3:55:23<5:47:47,  1.69it/s]
 39%|███▉      | 22391/57600 [3:55:23<5:46:17,  1.69it/s]
 39%|███▉      | 22392/57600 [3:55:24<5:50:23,  1.67it/s]
 39%|███▉      | 22393/57600 [3:55:25<6:03:57,  1.61it/s]
 39%|███▉      | 22394/57600 [3:55:25<5:59:43,  1.63it/s]
 39%|███▉      | 22395/57600 [3:55:26<6:02:28,  1.62it/s]
 39%|███▉      | 22396/57600 [3:55:26<6:01:43,  1.62it/s]
 39%|███▉      | 22397/57600 [3:55:27<5:59:01,  1.63it/s]
 39%|███▉      | 22398/57600 [3:55:28<5:55:41,  1.65it/s]
 39%|███▉      | 22399/57600 [3:55:28<6:03:22,  1.61it/s]
 39%|███▉      | 22400/57600 [3:55:29<6:04:27,  1.61it/s]
                                                         
{'loss': 1.2695, 'learning_rate': 6.519163763066204e-07, 'epoch': 247.24}

 39%|███▉      | 22400/57600 [3:55:29<6:04:27,  1.61it/s]
 39%|███▉      | 22401/57600 [3:55:30<6:09:30,  1.59it/s]
 39%|███▉      | 22402/57600 [3:55:30<6:06:10,  1.60it/s]
 39%|███▉      | 22403/57600 [3:55:31<5:56:18,  1.65it/s]
 39%|███▉      | 22404/57600 [3:55:31<6:07:02,  1.60it/s]
 39%|███▉      | 22405/57600 [3:55:32<5:53:57,  1.66it/s]
 39%|███▉      | 22406/57600 [3:55:33<6:09:34,  1.59it/s]
 39%|███▉      | 22407/57600 [3:55:33<6:14:19,  1.57it/s]
 39%|███▉      | 22408/57600 [3:55:34<6:21:30,  1.54it/s]
 39%|███▉      | 22409/57600 [3:55:35<6:09:29,  1.59it/s]
 39%|███▉      | 22410/57600 [3:55:35<6:19:02,  1.55it/s]
 39%|███▉      | 22411/57600 [3:55:36<6:14:35,  1.57it/s]
 39%|███▉      | 22412/57600 [3:55:37<6:24:05,  1.53it/s]
 39%|███▉      | 22413/57600 [3:55:37<6:12:05,  1.58it/s]
 39%|███▉      | 22414/57600 [3:55:38<6:19:55,  1.54it/s]
 39%|███▉      | 22415/57600 [3:55:38<6:14:56,  1.56it/s]
 39%|███▉      | 22416/57600 [3:55:39<6:10:09,  1.58it/s]
 39%|███▉      | 22417/57600 [3:55:40<6:21:54,  1.54it/s]
 39%|███▉      | 22418/57600 [3:55:40<6:16:49,  1.56it/s]
 39%|███▉      | 22419/57600 [3:55:41<6:23:53,  1.53it/s]
 39%|███▉      | 22420/57600 [3:55:42<6:12:38,  1.57it/s]
                                                         
{'loss': 1.2037, 'learning_rate': 6.516027874564459e-07, 'epoch': 247.46}

 39%|███▉      | 22420/57600 [3:55:42<6:12:38,  1.57it/s]
 39%|███▉      | 22421/57600 [3:55:42<6:11:47,  1.58it/s]
 39%|███▉      | 22422/57600 [3:55:43<6:20:46,  1.54it/s]
 39%|███▉      | 22423/57600 [3:55:44<6:22:45,  1.53it/s]
 39%|███▉      | 22424/57600 [3:55:44<6:26:06,  1.52it/s]
 39%|███▉      | 22425/57600 [3:55:45<6:08:31,  1.59it/s]
 39%|███▉      | 22426/57600 [3:55:46<6:02:58,  1.62it/s]
 39%|███▉      | 22427/57600 [3:55:46<5:58:27,  1.64it/s]
 39%|███▉      | 22428/57600 [3:55:47<6:04:26,  1.61it/s]
 39%|███▉      | 22429/57600 [3:55:47<6:23:10,  1.53it/s]
 39%|███▉      | 22430/57600 [3:55:48<6:22:48,  1.53it/s]
 39%|███▉      | 22431/57600 [3:55:49<6:17:46,  1.55it/s]
 39%|███▉      | 22432/57600 [3:55:49<6:11:53,  1.58it/s]
 39%|███▉      | 22433/57600 [3:55:50<6:02:22,  1.62it/s]
 39%|███▉      | 22434/57600 [3:55:51<5:54:54,  1.65it/s]
 39%|███▉      | 22435/57600 [3:55:51<5:55:06,  1.65it/s]
 39%|███▉      | 22436/57600 [3:55:52<6:04:54,  1.61it/s]
 39%|███▉      | 22437/57600 [3:55:52<5:55:40,  1.65it/s]
 39%|███▉      | 22438/57600 [3:55:53<5:51:41,  1.67it/s]
 39%|███▉      | 22439/57600 [3:55:54<6:00:30,  1.63it/s]
 39%|███▉      | 22440/57600 [3:55:54<6:10:29,  1.58it/s]
                                                         
{'loss': 1.2058, 'learning_rate': 6.512891986062717e-07, 'epoch': 247.68}

 39%|███▉      | 22440/57600 [3:55:54<6:10:29,  1.58it/s]
 39%|███▉      | 22441/57600 [3:55:55<6:17:49,  1.55it/s]
 39%|███▉      | 22442/57600 [3:55:56<6:22:10,  1.53it/s]
 39%|███▉      | 22443/57600 [3:55:56<6:19:36,  1.54it/s]
 39%|███▉      | 22444/57600 [3:55:57<6:18:21,  1.55it/s]
 39%|███▉      | 22445/57600 [3:55:57<6:09:08,  1.59it/s]
 39%|███▉      | 22446/57600 [3:55:58<6:02:55,  1.61it/s]
 39%|███▉      | 22447/57600 [3:55:59<5:57:57,  1.64it/s]
 39%|███▉      | 22448/57600 [3:55:59<6:00:10,  1.63it/s]
 39%|███▉      | 22449/57600 [3:56:00<5:55:49,  1.65it/s]
 39%|███▉      | 22450/57600 [3:56:01<5:59:09,  1.63it/s]
 39%|███▉      | 22451/57600 [3:56:01<6:09:03,  1.59it/s]
 39%|███▉      | 22452/57600 [3:56:02<6:08:25,  1.59it/s]
 39%|███▉      | 22453/57600 [3:56:02<5:57:23,  1.64it/s]
 39%|███▉      | 22454/57600 [3:56:03<5:50:55,  1.67it/s]
 39%|███▉      | 22455/57600 [3:56:04<5:52:53,  1.66it/s]
 39%|███▉      | 22456/57600 [3:56:04<5:47:57,  1.68it/s]
 39%|███▉      | 22457/57600 [3:56:05<5:46:59,  1.69it/s]
 39%|███▉      | 22458/57600 [3:56:05<5:47:45,  1.68it/s]
 39%|███▉      | 22459/57600 [3:56:06<5:55:39,  1.65it/s]
 39%|███▉      | 22460/57600 [3:56:07<6:01:44,  1.62it/s]
                                                         
{'loss': 1.2298, 'learning_rate': 6.509756097560975e-07, 'epoch': 247.9}

 39%|███▉      | 22460/57600 [3:56:07<6:01:44,  1.62it/s]
 39%|███▉      | 22461/57600 [3:56:07<5:54:14,  1.65it/s]
 39%|███▉      | 22462/57600 [3:56:08<5:53:48,  1.66it/s]
 39%|███▉      | 22463/57600 [3:56:08<6:10:34,  1.58it/s]
 39%|███▉      | 22464/57600 [3:56:09<5:58:51,  1.63it/s]
 39%|███▉      | 22465/57600 [3:56:10<5:57:50,  1.64it/s]
 39%|███▉      | 22466/57600 [3:56:10<5:56:05,  1.64it/s]
 39%|███▉      | 22467/57600 [3:56:11<5:59:48,  1.63it/s]
 39%|███▉      | 22468/57600 [3:56:11<5:49:25,  1.68it/s]
 39%|███▉      | 22469/57600 [3:56:12<6:09:04,  1.59it/s]
 39%|███▉      | 22470/57600 [3:56:13<6:08:03,  1.59it/s]
 39%|███▉      | 22471/57600 [3:56:13<6:10:05,  1.58it/s]
 39%|███▉      | 22472/57600 [3:56:14<6:04:14,  1.61it/s]
 39%|███▉      | 22473/57600 [3:56:15<6:00:03,  1.63it/s]
 39%|███▉      | 22474/57600 [3:56:15<5:52:25,  1.66it/s]
 39%|███▉      | 22475/57600 [3:56:16<5:53:06,  1.66it/s]
 39%|███▉      | 22476/57600 [3:56:16<5:51:57,  1.66it/s]
 39%|███▉      | 22477/57600 [3:56:17<5:57:43,  1.64it/s]
 39%|███▉      | 22478/57600 [3:56:18<6:11:01,  1.58it/s]
 39%|███▉      | 22479/57600 [3:56:18<6:01:41,  1.62it/s]
 39%|███▉      | 22480/57600 [3:56:19<6:08:50,  1.59it/s]
                                                         
{'loss': 1.2185, 'learning_rate': 6.506620209059234e-07, 'epoch': 248.12}

 39%|███▉      | 22480/57600 [3:56:19<6:08:50,  1.59it/s]
 39%|███▉      | 22481/57600 [3:56:20<6:02:17,  1.62it/s]
 39%|███▉      | 22482/57600 [3:56:20<6:08:29,  1.59it/s]
 39%|███▉      | 22483/57600 [3:56:21<6:03:20,  1.61it/s]
 39%|███▉      | 22484/57600 [3:56:21<5:56:50,  1.64it/s]
 39%|███▉      | 22485/57600 [3:56:22<6:00:27,  1.62it/s]
 39%|███▉      | 22486/57600 [3:56:23<6:22:41,  1.53it/s]
 39%|███▉      | 22487/57600 [3:56:23<6:22:17,  1.53it/s]
 39%|███▉      | 22488/57600 [3:56:24<6:19:37,  1.54it/s]
 39%|███▉      | 22489/57600 [3:56:25<6:28:46,  1.51it/s]
 39%|███▉      | 22490/57600 [3:56:25<6:19:10,  1.54it/s]
 39%|███▉      | 22491/57600 [3:56:26<6:25:25,  1.52it/s]
 39%|███▉      | 22492/57600 [3:56:27<6:10:15,  1.58it/s]
 39%|███▉      | 22493/57600 [3:56:27<6:05:01,  1.60it/s]
 39%|███▉      | 22494/57600 [3:56:28<6:04:21,  1.61it/s]
 39%|███▉      | 22495/57600 [3:56:28<6:04:21,  1.61it/s]
 39%|███▉      | 22496/57600 [3:56:29<5:55:37,  1.65it/s]
 39%|███▉      | 22497/57600 [3:56:30<5:54:21,  1.65it/s]
 39%|███▉      | 22498/57600 [3:56:30<5:55:13,  1.65it/s]
 39%|███▉      | 22499/57600 [3:56:31<6:03:25,  1.61it/s]
 39%|███▉      | 22500/57600 [3:56:31<5:53:10,  1.66it/s]
                                                         
{'loss': 1.2271, 'learning_rate': 6.50348432055749e-07, 'epoch': 248.34}

 39%|███▉      | 22500/57600 [3:56:31<5:53:10,  1.66it/s]
 39%|███▉      | 22501/57600 [3:56:32<5:57:30,  1.64it/s]
 39%|███▉      | 22502/57600 [3:56:33<6:05:13,  1.60it/s]
 39%|███▉      | 22503/57600 [3:56:33<5:57:52,  1.63it/s]
 39%|███▉      | 22504/57600 [3:56:34<5:54:06,  1.65it/s]
 39%|███▉      | 22505/57600 [3:56:35<5:57:55,  1.63it/s]
 39%|███▉      | 22506/57600 [3:56:35<6:02:42,  1.61it/s]
 39%|███▉      | 22507/57600 [3:56:36<6:09:20,  1.58it/s]
 39%|███▉      | 22508/57600 [3:56:36<6:05:45,  1.60it/s]
 39%|███▉      | 22509/57600 [3:56:37<6:06:14,  1.60it/s]
 39%|███▉      | 22510/57600 [3:56:38<6:09:44,  1.58it/s]
 39%|███▉      | 22511/57600 [3:56:38<6:03:25,  1.61it/s]
 39%|███▉      | 22512/57600 [3:56:39<6:00:10,  1.62it/s]
 39%|███▉      | 22513/57600 [3:56:39<5:55:26,  1.65it/s]
 39%|███▉      | 22514/57600 [3:56:40<6:19:29,  1.54it/s]
 39%|███▉      | 22515/57600 [3:56:41<6:21:09,  1.53it/s]
 39%|███▉      | 22516/57600 [3:56:41<6:09:24,  1.58it/s]
 39%|███▉      | 22517/57600 [3:56:42<6:01:48,  1.62it/s]
 39%|███▉      | 22518/57600 [3:56:43<5:53:31,  1.65it/s]
 39%|███▉      | 22519/57600 [3:56:43<5:50:44,  1.67it/s]
 39%|███▉      | 22520/57600 [3:56:44<5:45:49,  1.69it/s]
                                                         
{'loss': 1.2277, 'learning_rate': 6.500348432055749e-07, 'epoch': 248.57}

 39%|███▉      | 22520/57600 [3:56:44<5:45:49,  1.69it/s]
 39%|███▉      | 22521/57600 [3:56:44<5:49:33,  1.67it/s]
 39%|███▉      | 22522/57600 [3:56:45<5:44:06,  1.70it/s]
 39%|███▉      | 22523/57600 [3:56:46<5:45:07,  1.69it/s]
 39%|███▉      | 22524/57600 [3:56:46<6:05:09,  1.60it/s]
 39%|███▉      | 22525/57600 [3:56:47<6:01:22,  1.62it/s]
 39%|███▉      | 22526/57600 [3:56:48<6:03:22,  1.61it/s]
 39%|███▉      | 22527/57600 [3:56:48<6:00:50,  1.62it/s]
 39%|███▉      | 22528/57600 [3:56:49<6:00:12,  1.62it/s]
 39%|███▉      | 22529/57600 [3:56:49<5:58:00,  1.63it/s]
 39%|███▉      | 22530/57600 [3:56:50<5:57:38,  1.63it/s]
 39%|███▉      | 22531/57600 [3:56:51<5:55:52,  1.64it/s]
 39%|███▉      | 22532/57600 [3:56:51<6:09:16,  1.58it/s]
 39%|███▉      | 22533/57600 [3:56:52<6:10:56,  1.58it/s]
 39%|███▉      | 22534/57600 [3:56:52<6:01:03,  1.62it/s]
 39%|███▉      | 22535/57600 [3:56:53<5:55:31,  1.64it/s]
 39%|███▉      | 22536/57600 [3:56:54<5:48:01,  1.68it/s]
 39%|███▉      | 22537/57600 [3:56:54<5:46:45,  1.69it/s]
 39%|███▉      | 22538/57600 [3:56:55<5:46:27,  1.69it/s]
 39%|███▉      | 22539/57600 [3:56:55<5:44:10,  1.70it/s]
 39%|███▉      | 22540/57600 [3:56:56<5:45:50,  1.69it/s]
                                                         
{'loss': 1.2763, 'learning_rate': 6.497212543554008e-07, 'epoch': 248.79}

 39%|███▉      | 22540/57600 [3:56:56<5:45:50,  1.69it/s]
 39%|███▉      | 22541/57600 [3:56:57<6:00:59,  1.62it/s]
 39%|███▉      | 22542/57600 [3:56:57<6:13:44,  1.56it/s]
 39%|███▉      | 22543/57600 [3:56:58<6:04:05,  1.60it/s]
 39%|███▉      | 22544/57600 [3:56:58<5:54:00,  1.65it/s]
 39%|███▉      | 22545/57600 [3:56:59<6:07:25,  1.59it/s]
 39%|███▉      | 22546/57600 [3:57:00<6:04:34,  1.60it/s]
 39%|███▉      | 22547/57600 [3:57:00<5:58:52,  1.63it/s]
 39%|███▉      | 22548/57600 [3:57:01<5:56:24,  1.64it/s]
 39%|███▉      | 22549/57600 [3:57:02<5:53:05,  1.65it/s]
 39%|███▉      | 22550/57600 [3:57:02<5:56:53,  1.64it/s]
 39%|███▉      | 22551/57600 [3:57:03<6:00:40,  1.62it/s]
 39%|███▉      | 22552/57600 [3:57:03<5:50:37,  1.67it/s]
 39%|███▉      | 22553/57600 [3:57:04<6:08:19,  1.59it/s]
 39%|███▉      | 22554/57600 [3:57:05<6:19:39,  1.54it/s]
 39%|███▉      | 22555/57600 [3:57:05<6:04:13,  1.60it/s]
 39%|███▉      | 22556/57600 [3:57:06<5:58:49,  1.63it/s]
 39%|███▉      | 22557/57600 [3:57:07<6:15:13,  1.56it/s]
 39%|███▉      | 22558/57600 [3:57:07<6:11:47,  1.57it/s]
 39%|███▉      | 22559/57600 [3:57:08<6:06:39,  1.59it/s]
 39%|███▉      | 22560/57600 [3:57:09<6:30:08,  1.50it/s]
                                                         
{'loss': 1.2158, 'learning_rate': 6.494076655052265e-07, 'epoch': 249.01}

 39%|███▉      | 22560/57600 [3:57:09<6:30:08,  1.50it/s]
 39%|███▉      | 22561/57600 [3:57:09<6:16:35,  1.55it/s]
 39%|███▉      | 22562/57600 [3:57:10<6:09:42,  1.58it/s]
 39%|███▉      | 22563/57600 [3:57:10<6:03:48,  1.61it/s]
 39%|███▉      | 22564/57600 [3:57:11<5:53:29,  1.65it/s]
 39%|███▉      | 22565/57600 [3:57:12<5:47:34,  1.68it/s]
 39%|███▉      | 22566/57600 [3:57:12<6:03:12,  1.61it/s]
 39%|███▉      | 22567/57600 [3:57:13<5:56:04,  1.64it/s]
 39%|███▉      | 22568/57600 [3:57:14<6:09:48,  1.58it/s]
 39%|███▉      | 22569/57600 [3:57:14<6:35:30,  1.48it/s]
 39%|███▉      | 22570/57600 [3:57:15<6:25:14,  1.52it/s]
 39%|███▉      | 22571/57600 [3:57:16<6:25:04,  1.52it/s]
 39%|███▉      | 22572/57600 [3:57:16<6:18:13,  1.54it/s]
 39%|███▉      | 22573/57600 [3:57:17<6:09:39,  1.58it/s]
 39%|███▉      | 22574/57600 [3:57:17<5:54:44,  1.65it/s]
 39%|███▉      | 22575/57600 [3:57:18<5:52:31,  1.66it/s]
 39%|███▉      | 22576/57600 [3:57:19<6:06:34,  1.59it/s]
 39%|███▉      | 22577/57600 [3:57:19<5:51:16,  1.66it/s]
 39%|███▉      | 22578/57600 [3:57:20<5:57:31,  1.63it/s]
 39%|███▉      | 22579/57600 [3:57:20<5:59:36,  1.62it/s]
 39%|███▉      | 22580/57600 [3:57:21<5:59:05,  1.63it/s]
                                                         
{'loss': 1.205, 'learning_rate': 6.490940766550521e-07, 'epoch': 249.23}

 39%|███▉      | 22580/57600 [3:57:21<5:59:05,  1.63it/s]
 39%|███▉      | 22581/57600 [3:57:22<6:01:10,  1.62it/s]
 39%|███▉      | 22582/57600 [3:57:22<6:01:34,  1.61it/s]
 39%|███▉      | 22583/57600 [3:57:23<5:54:13,  1.65it/s]
 39%|███▉      | 22584/57600 [3:57:23<5:50:39,  1.66it/s]
 39%|███▉      | 22585/57600 [3:57:24<5:47:36,  1.68it/s]
 39%|███▉      | 22586/57600 [3:57:25<5:50:05,  1.67it/s]
 39%|███▉      | 22587/57600 [3:57:25<5:50:51,  1.66it/s]
 39%|███▉      | 22588/57600 [3:57:26<6:01:24,  1.61it/s]
 39%|███▉      | 22589/57600 [3:57:26<5:50:50,  1.66it/s]
 39%|███▉      | 22590/57600 [3:57:27<5:45:05,  1.69it/s]
 39%|███▉      | 22591/57600 [3:57:28<5:59:26,  1.62it/s]
 39%|███▉      | 22592/57600 [3:57:28<5:57:54,  1.63it/s]
 39%|███▉      | 22593/57600 [3:57:29<5:52:45,  1.65it/s]
 39%|███▉      | 22594/57600 [3:57:30<5:54:36,  1.65it/s]
 39%|███▉      | 22595/57600 [3:57:30<6:00:14,  1.62it/s]
 39%|███▉      | 22596/57600 [3:57:31<6:00:40,  1.62it/s]
 39%|███▉      | 22597/57600 [3:57:31<6:02:33,  1.61it/s]
 39%|███▉      | 22598/57600 [3:57:32<5:57:36,  1.63it/s]
 39%|███▉      | 22599/57600 [3:57:33<5:58:20,  1.63it/s]
 39%|███▉      | 22600/57600 [3:57:33<5:55:07,  1.64it/s]
                                                         
{'loss': 1.2283, 'learning_rate': 6.48780487804878e-07, 'epoch': 249.45}

 39%|███▉      | 22600/57600 [3:57:33<5:55:07,  1.64it/s]
 39%|███▉      | 22601/57600 [3:57:34<6:16:22,  1.55it/s]
 39%|███▉      | 22602/57600 [3:57:35<6:12:35,  1.57it/s]
 39%|███▉      | 22603/57600 [3:57:35<6:01:18,  1.61it/s]
 39%|███▉      | 22604/57600 [3:57:36<5:57:36,  1.63it/s]
 39%|███▉      | 22605/57600 [3:57:36<5:54:49,  1.64it/s]
 39%|███▉      | 22606/57600 [3:57:37<5:54:30,  1.65it/s]
 39%|███▉      | 22607/57600 [3:57:38<5:57:42,  1.63it/s]
 39%|███▉      | 22608/57600 [3:57:38<5:50:35,  1.66it/s]
 39%|███▉      | 22609/57600 [3:57:39<5:48:53,  1.67it/s]
 39%|███▉      | 22610/57600 [3:57:39<5:56:00,  1.64it/s]
 39%|███▉      | 22611/57600 [3:57:40<5:56:49,  1.63it/s]
 39%|███▉      | 22612/57600 [3:57:41<5:57:08,  1.63it/s]
 39%|███▉      | 22613/57600 [3:57:41<5:53:28,  1.65it/s]
 39%|███▉      | 22614/57600 [3:57:42<5:51:14,  1.66it/s]
 39%|███▉      | 22615/57600 [3:57:42<5:53:55,  1.65it/s]
 39%|███▉      | 22616/57600 [3:57:43<5:55:46,  1.64it/s]
 39%|███▉      | 22617/57600 [3:57:44<5:57:38,  1.63it/s]
 39%|███▉      | 22618/57600 [3:57:44<5:58:40,  1.63it/s]
 39%|███▉      | 22619/57600 [3:57:45<6:23:20,  1.52it/s]
 39%|███▉      | 22620/57600 [3:57:46<6:13:42,  1.56it/s]
                                                         
{'loss': 1.2114, 'learning_rate': 6.484668989547039e-07, 'epoch': 249.67}

 39%|███▉      | 22620/57600 [3:57:46<6:13:42,  1.56it/s]
 39%|███▉      | 22621/57600 [3:57:46<6:11:16,  1.57it/s]
 39%|███▉      | 22622/57600 [3:57:47<6:03:40,  1.60it/s]
 39%|███▉      | 22623/57600 [3:57:47<5:58:01,  1.63it/s]
 39%|███▉      | 22624/57600 [3:57:48<6:03:22,  1.60it/s]
 39%|███▉      | 22625/57600 [3:57:49<6:09:52,  1.58it/s]
 39%|███▉      | 22626/57600 [3:57:49<6:09:40,  1.58it/s]
 39%|███▉      | 22627/57600 [3:57:50<6:09:31,  1.58it/s]
 39%|███▉      | 22628/57600 [3:57:51<6:14:45,  1.56it/s]
 39%|███▉      | 22629/57600 [3:57:51<6:08:24,  1.58it/s]
 39%|███▉      | 22630/57600 [3:57:52<5:58:49,  1.62it/s]
 39%|███▉      | 22631/57600 [3:57:52<5:55:05,  1.64it/s]
 39%|███▉      | 22632/57600 [3:57:53<6:02:24,  1.61it/s]
 39%|███▉      | 22633/57600 [3:57:54<6:16:26,  1.55it/s]
 39%|███▉      | 22634/57600 [3:57:55<6:27:17,  1.50it/s]
 39%|███▉      | 22635/57600 [3:57:55<6:33:47,  1.48it/s]
 39%|███▉      | 22636/57600 [3:57:56<6:11:38,  1.57it/s]
 39%|███▉      | 22637/57600 [3:57:56<6:16:53,  1.55it/s]
 39%|███▉      | 22638/57600 [3:57:57<6:10:22,  1.57it/s]
 39%|███▉      | 22639/57600 [3:57:58<6:16:48,  1.55it/s]
 39%|███▉      | 22640/57600 [3:57:58<6:12:00,  1.57it/s]
                                                         
{'loss': 1.2301, 'learning_rate': 6.481533101045295e-07, 'epoch': 249.89}

 39%|███▉      | 22640/57600 [3:57:58<6:12:00,  1.57it/s]
 39%|███▉      | 22641/57600 [3:57:59<6:01:15,  1.61it/s]
 39%|███▉      | 22642/57600 [3:57:59<5:55:08,  1.64it/s]
 39%|███▉      | 22643/57600 [3:58:00<5:52:28,  1.65it/s]
 39%|███▉      | 22644/57600 [3:58:01<5:47:57,  1.67it/s]
 39%|███▉      | 22645/57600 [3:58:01<5:57:11,  1.63it/s]
 39%|███▉      | 22646/57600 [3:58:02<5:55:30,  1.64it/s]
 39%|███▉      | 22647/57600 [3:58:03<5:55:03,  1.64it/s]
 39%|███▉      | 22648/57600 [3:58:03<5:55:49,  1.64it/s]
 39%|███▉      | 22649/57600 [3:58:04<5:58:06,  1.63it/s]
 39%|███▉      | 22650/57600 [3:58:04<6:12:17,  1.56it/s]
 39%|███▉      | 22651/57600 [3:58:05<6:08:29,  1.58it/s]
 39%|███▉      | 22652/57600 [3:58:06<6:15:44,  1.55it/s]
 39%|███▉      | 22653/57600 [3:58:06<6:06:04,  1.59it/s]
 39%|███▉      | 22654/57600 [3:58:07<6:00:04,  1.62it/s]
 39%|███▉      | 22655/57600 [3:58:08<5:56:48,  1.63it/s]
 39%|███▉      | 22656/57600 [3:58:08<6:01:37,  1.61it/s]
 39%|███▉      | 22657/57600 [3:58:09<6:01:20,  1.61it/s]
 39%|███▉      | 22658/57600 [3:58:09<5:53:02,  1.65it/s]
 39%|███▉      | 22659/57600 [3:58:10<5:44:55,  1.69it/s]
 39%|███▉      | 22660/57600 [3:58:11<5:57:04,  1.63it/s]
                                                         
{'loss': 1.2607, 'learning_rate': 6.478397212543554e-07, 'epoch': 250.11}

 39%|███▉      | 22660/57600 [3:58:11<5:57:04,  1.63it/s]
 39%|███▉      | 22661/57600 [3:58:11<6:00:52,  1.61it/s]
 39%|███▉      | 22662/57600 [3:58:12<5:57:19,  1.63it/s]
 39%|███▉      | 22663/57600 [3:58:12<5:55:10,  1.64it/s]
 39%|███▉      | 22664/57600 [3:58:13<5:59:22,  1.62it/s]
 39%|███▉      | 22665/57600 [3:58:14<5:59:21,  1.62it/s]
 39%|███▉      | 22666/57600 [3:58:14<6:13:13,  1.56it/s]
 39%|███▉      | 22667/57600 [3:58:15<6:24:00,  1.52it/s]
 39%|███▉      | 22668/57600 [3:58:16<6:23:28,  1.52it/s]
 39%|███▉      | 22669/57600 [3:58:16<6:20:13,  1.53it/s]
 39%|███▉      | 22670/57600 [3:58:17<6:14:46,  1.55it/s]
 39%|███▉      | 22671/57600 [3:58:18<6:00:24,  1.62it/s]
 39%|███▉      | 22672/57600 [3:58:18<5:57:00,  1.63it/s]
 39%|███▉      | 22673/57600 [3:58:19<5:54:08,  1.64it/s]
 39%|███▉      | 22674/57600 [3:58:19<5:57:05,  1.63it/s]
 39%|███▉      | 22675/57600 [3:58:20<6:11:53,  1.57it/s]
 39%|███▉      | 22676/57600 [3:58:21<6:00:32,  1.61it/s]
 39%|███▉      | 22677/57600 [3:58:21<5:57:37,  1.63it/s]
 39%|███▉      | 22678/57600 [3:58:22<5:56:10,  1.63it/s]
 39%|███▉      | 22679/57600 [3:58:22<5:53:06,  1.65it/s]
 39%|███▉      | 22680/57600 [3:58:23<5:54:36,  1.64it/s]
                                                         
{'loss': 1.2013, 'learning_rate': 6.475261324041812e-07, 'epoch': 250.33}

 39%|███▉      | 22680/57600 [3:58:23<5:54:36,  1.64it/s]
 39%|███▉      | 22681/57600 [3:58:24<5:59:52,  1.62it/s]
 39%|███▉      | 22682/57600 [3:58:24<6:01:06,  1.61it/s]
 39%|███▉      | 22683/57600 [3:58:25<6:07:12,  1.58it/s]
 39%|███▉      | 22684/57600 [3:58:26<6:29:02,  1.50it/s]
 39%|███▉      | 22685/57600 [3:58:26<6:27:48,  1.50it/s]
 39%|███▉      | 22686/57600 [3:58:27<6:32:35,  1.48it/s]
 39%|███▉      | 22687/57600 [3:58:28<6:15:24,  1.55it/s]
 39%|███▉      | 22688/57600 [3:58:28<6:27:26,  1.50it/s]
 39%|███▉      | 22689/57600 [3:58:29<6:13:26,  1.56it/s]
 39%|███▉      | 22690/57600 [3:58:30<6:18:32,  1.54it/s]
 39%|███▉      | 22691/57600 [3:58:30<6:07:41,  1.58it/s]
 39%|███▉      | 22692/57600 [3:58:31<6:04:25,  1.60it/s]
 39%|███▉      | 22693/57600 [3:58:31<5:53:50,  1.64it/s]
 39%|███▉      | 22694/57600 [3:58:32<6:02:45,  1.60it/s]
 39%|███▉      | 22695/57600 [3:58:33<5:53:29,  1.65it/s]
 39%|███▉      | 22696/57600 [3:58:33<6:06:09,  1.59it/s]
 39%|███▉      | 22697/57600 [3:58:34<6:01:51,  1.61it/s]
 39%|███▉      | 22698/57600 [3:58:34<5:48:26,  1.67it/s]
 39%|███▉      | 22699/57600 [3:58:35<5:57:24,  1.63it/s]
 39%|███▉      | 22700/57600 [3:58:36<5:51:53,  1.65it/s]
                                                         
{'loss': 1.2215, 'learning_rate': 6.47212543554007e-07, 'epoch': 250.55}

 39%|███▉      | 22700/57600 [3:58:36<5:51:53,  1.65it/s]
 39%|███▉      | 22701/57600 [3:58:36<5:53:39,  1.64it/s]
 39%|███▉      | 22702/57600 [3:58:37<5:50:28,  1.66it/s]
 39%|███▉      | 22703/57600 [3:58:37<5:38:26,  1.72it/s]
 39%|███▉      | 22704/57600 [3:58:38<5:40:50,  1.71it/s]
 39%|███▉      | 22705/57600 [3:58:39<5:39:20,  1.71it/s]
 39%|███▉      | 22706/57600 [3:58:39<5:50:42,  1.66it/s]
 39%|███▉      | 22707/57600 [3:58:40<5:44:39,  1.69it/s]
 39%|███▉      | 22708/57600 [3:58:40<5:39:03,  1.72it/s]
 39%|███▉      | 22709/57600 [3:58:41<5:49:10,  1.67it/s]
 39%|███▉      | 22710/57600 [3:58:42<5:47:02,  1.68it/s]
 39%|███▉      | 22711/57600 [3:58:42<5:45:45,  1.68it/s]
 39%|███▉      | 22712/57600 [3:58:43<6:08:32,  1.58it/s]
 39%|███▉      | 22713/57600 [3:58:44<6:02:01,  1.61it/s]
 39%|███▉      | 22714/57600 [3:58:44<5:54:31,  1.64it/s]
 39%|███▉      | 22715/57600 [3:58:45<6:06:42,  1.59it/s]
 39%|███▉      | 22716/57600 [3:58:45<6:00:06,  1.61it/s]
 39%|███▉      | 22717/57600 [3:58:46<5:56:15,  1.63it/s]
 39%|███▉      | 22718/57600 [3:58:47<5:56:07,  1.63it/s]
 39%|███▉      | 22719/57600 [3:58:47<6:18:59,  1.53it/s]
 39%|███▉      | 22720/57600 [3:58:48<6:03:14,  1.60it/s]
                                                         
{'loss': 1.2495, 'learning_rate': 6.468989547038326e-07, 'epoch': 250.77}

 39%|███▉      | 22720/57600 [3:58:48<6:03:14,  1.60it/s]
 39%|███▉      | 22721/57600 [3:58:49<5:57:20,  1.63it/s]
 39%|███▉      | 22722/57600 [3:58:49<6:10:10,  1.57it/s]
 39%|███▉      | 22723/57600 [3:58:50<6:12:14,  1.56it/s]
 39%|███▉      | 22724/57600 [3:58:50<5:55:35,  1.63it/s]
 39%|███▉      | 22725/57600 [3:58:51<5:51:12,  1.65it/s]
 39%|███▉      | 22726/57600 [3:58:52<5:58:20,  1.62it/s]
 39%|███▉      | 22727/57600 [3:58:52<5:56:13,  1.63it/s]
 39%|███▉      | 22728/57600 [3:58:53<6:00:20,  1.61it/s]
 39%|███▉      | 22729/57600 [3:58:53<6:01:03,  1.61it/s]
 39%|███▉      | 22730/57600 [3:58:54<6:11:24,  1.56it/s]
 39%|███▉      | 22731/57600 [3:58:55<6:04:25,  1.59it/s]
 39%|███▉      | 22732/57600 [3:58:55<6:01:53,  1.61it/s]
 39%|███▉      | 22733/57600 [3:58:56<6:01:26,  1.61it/s]
 39%|███▉      | 22734/57600 [3:58:57<5:58:38,  1.62it/s]
 39%|███▉      | 22735/57600 [3:58:57<6:00:15,  1.61it/s]
 39%|███▉      | 22736/57600 [3:58:58<6:03:33,  1.60it/s]
 39%|███▉      | 22737/57600 [3:58:58<6:03:31,  1.60it/s]
 39%|███▉      | 22738/57600 [3:58:59<5:58:27,  1.62it/s]
 39%|███▉      | 22739/57600 [3:59:00<5:55:53,  1.63it/s]
 39%|███▉      | 22740/57600 [3:59:00<6:01:17,  1.61it/s]
                                                         
{'loss': 1.2359, 'learning_rate': 6.465853658536585e-07, 'epoch': 250.99}

 39%|███▉      | 22740/57600 [3:59:00<6:01:17,  1.61it/s]
 39%|███▉      | 22741/57600 [3:59:01<6:11:38,  1.56it/s]
 39%|███▉      | 22742/57600 [3:59:02<5:58:49,  1.62it/s]
 39%|███▉      | 22743/57600 [3:59:02<5:54:02,  1.64it/s]
 39%|███▉      | 22744/57600 [3:59:03<5:48:18,  1.67it/s]
 39%|███▉      | 22745/57600 [3:59:03<5:44:33,  1.69it/s]
 39%|███▉      | 22746/57600 [3:59:04<5:45:55,  1.68it/s]
 39%|███▉      | 22747/57600 [3:59:05<5:50:47,  1.66it/s]
 39%|███▉      | 22748/57600 [3:59:05<5:49:23,  1.66it/s]
 39%|███▉      | 22749/57600 [3:59:06<5:58:35,  1.62it/s]
 39%|███▉      | 22750/57600 [3:59:06<5:54:41,  1.64it/s]
 39%|███▉      | 22751/57600 [3:59:07<5:53:38,  1.64it/s]
 40%|███▉      | 22752/57600 [3:59:08<5:55:40,  1.63it/s]
 40%|███▉      | 22753/57600 [3:59:08<5:50:52,  1.66it/s]
 40%|███▉      | 22754/57600 [3:59:09<6:06:28,  1.58it/s]
 40%|███▉      | 22755/57600 [3:59:09<6:00:32,  1.61it/s]
 40%|███▉      | 22756/57600 [3:59:10<6:20:43,  1.53it/s]
 40%|███▉      | 22757/57600 [3:59:11<6:14:52,  1.55it/s]
 40%|███▉      | 22758/57600 [3:59:11<6:10:57,  1.57it/s]
 40%|███▉      | 22759/57600 [3:59:12<6:13:20,  1.56it/s]
 40%|███▉      | 22760/57600 [3:59:13<6:15:17,  1.55it/s]
                                                         
{'loss': 1.2297, 'learning_rate': 6.462717770034843e-07, 'epoch': 251.21}

 40%|███▉      | 22760/57600 [3:59:13<6:15:17,  1.55it/s]
 40%|███▉      | 22761/57600 [3:59:13<6:02:29,  1.60it/s]
 40%|███▉      | 22762/57600 [3:59:14<5:54:13,  1.64it/s]
 40%|███▉      | 22763/57600 [3:59:15<5:51:33,  1.65it/s]
 40%|███▉      | 22764/57600 [3:59:15<5:48:39,  1.67it/s]
 40%|███▉      | 22765/57600 [3:59:16<5:51:11,  1.65it/s]
 40%|███▉      | 22766/57600 [3:59:16<5:55:46,  1.63it/s]
 40%|███▉      | 22767/57600 [3:59:17<5:55:05,  1.63it/s]
 40%|███▉      | 22768/57600 [3:59:18<6:20:27,  1.53it/s]
 40%|███▉      | 22769/57600 [3:59:18<6:13:11,  1.56it/s]
 40%|███▉      | 22770/57600 [3:59:19<6:13:03,  1.56it/s]
 40%|███▉      | 22771/57600 [3:59:20<5:56:50,  1.63it/s]
 40%|███▉      | 22772/57600 [3:59:20<5:54:19,  1.64it/s]
 40%|███▉      | 22773/57600 [3:59:21<5:56:03,  1.63it/s]
 40%|███▉      | 22774/57600 [3:59:21<6:07:54,  1.58it/s]
 40%|███▉      | 22775/57600 [3:59:22<6:18:31,  1.53it/s]
 40%|███▉      | 22776/57600 [3:59:23<6:11:12,  1.56it/s]
 40%|███▉      | 22777/57600 [3:59:23<6:10:37,  1.57it/s]
 40%|███▉      | 22778/57600 [3:59:24<6:04:12,  1.59it/s]
 40%|███▉      | 22779/57600 [3:59:25<6:16:06,  1.54it/s]
 40%|███▉      | 22780/57600 [3:59:25<6:08:45,  1.57it/s]
                                                         
{'loss': 1.2304, 'learning_rate': 6.459581881533101e-07, 'epoch': 251.43}

 40%|███▉      | 22780/57600 [3:59:25<6:08:45,  1.57it/s]
 40%|███▉      | 22781/57600 [3:59:26<6:04:38,  1.59it/s]
 40%|███▉      | 22782/57600 [3:59:26<5:59:54,  1.61it/s]
 40%|███▉      | 22783/57600 [3:59:27<5:52:55,  1.64it/s]
 40%|███▉      | 22784/57600 [3:59:28<5:57:53,  1.62it/s]
 40%|███▉      | 22785/57600 [3:59:28<6:03:37,  1.60it/s]
 40%|███▉      | 22786/57600 [3:59:29<6:10:48,  1.56it/s]
 40%|███▉      | 22787/57600 [3:59:30<6:09:11,  1.57it/s]
 40%|███▉      | 22788/57600 [3:59:30<6:05:01,  1.59it/s]
 40%|███▉      | 22789/57600 [3:59:31<6:04:28,  1.59it/s]
 40%|███▉      | 22790/57600 [3:59:32<6:05:09,  1.59it/s]
 40%|███▉      | 22791/57600 [3:59:32<6:09:44,  1.57it/s]
 40%|███▉      | 22792/57600 [3:59:33<6:11:12,  1.56it/s]
 40%|███▉      | 22793/57600 [3:59:33<6:02:14,  1.60it/s]
 40%|███▉      | 22794/57600 [3:59:34<5:59:41,  1.61it/s]
 40%|███▉      | 22795/57600 [3:59:35<5:55:48,  1.63it/s]
 40%|███▉      | 22796/57600 [3:59:35<6:07:49,  1.58it/s]
 40%|███▉      | 22797/57600 [3:59:36<6:05:02,  1.59it/s]
 40%|███▉      | 22798/57600 [3:59:37<5:55:18,  1.63it/s]
 40%|███▉      | 22799/57600 [3:59:37<6:05:47,  1.59it/s]
 40%|███▉      | 22800/57600 [3:59:38<6:19:31,  1.53it/s]
                                                         
{'loss': 1.2113, 'learning_rate': 6.456445993031358e-07, 'epoch': 251.66}

 40%|███▉      | 22800/57600 [3:59:38<6:19:31,  1.53it/s]
 40%|███▉      | 22801/57600 [3:59:38<6:11:24,  1.56it/s]
 40%|███▉      | 22802/57600 [3:59:39<6:03:18,  1.60it/s]
 40%|███▉      | 22803/57600 [3:59:40<5:44:25,  1.68it/s]
 40%|███▉      | 22804/57600 [3:59:40<5:50:11,  1.66it/s]
 40%|███▉      | 22805/57600 [3:59:41<5:45:14,  1.68it/s]
 40%|███▉      | 22806/57600 [3:59:41<5:41:25,  1.70it/s]
 40%|███▉      | 22807/57600 [3:59:42<5:40:47,  1.70it/s]
 40%|███▉      | 22808/57600 [3:59:43<5:44:45,  1.68it/s]
 40%|███▉      | 22809/57600 [3:59:43<6:09:54,  1.57it/s]
 40%|███▉      | 22810/57600 [3:59:44<6:08:51,  1.57it/s]
 40%|███▉      | 22811/57600 [3:59:45<6:01:17,  1.60it/s]
 40%|███▉      | 22812/57600 [3:59:45<5:53:01,  1.64it/s]
 40%|███▉      | 22813/57600 [3:59:46<6:02:18,  1.60it/s]
 40%|███▉      | 22814/57600 [3:59:46<6:09:06,  1.57it/s]
 40%|███▉      | 22815/57600 [3:59:47<6:09:02,  1.57it/s]
 40%|███▉      | 22816/57600 [3:59:48<5:54:37,  1.63it/s]
 40%|███▉      | 22817/57600 [3:59:48<5:54:20,  1.64it/s]
 40%|███▉      | 22818/57600 [3:59:49<5:54:16,  1.64it/s]
 40%|███▉      | 22819/57600 [3:59:49<5:55:01,  1.63it/s]
 40%|███▉      | 22820/57600 [3:59:50<5:58:57,  1.61it/s]
                                                         
{'loss': 1.2395, 'learning_rate': 6.453310104529617e-07, 'epoch': 251.88}

 40%|███▉      | 22820/57600 [3:59:50<5:58:57,  1.61it/s]
 40%|███▉      | 22821/57600 [3:59:51<6:00:58,  1.61it/s]
 40%|███▉      | 22822/57600 [3:59:51<6:02:11,  1.60it/s]
 40%|███▉      | 22823/57600 [3:59:52<5:48:05,  1.67it/s]
 40%|███▉      | 22824/57600 [3:59:53<5:49:57,  1.66it/s]
 40%|███▉      | 22825/57600 [3:59:53<5:59:01,  1.61it/s]
 40%|███▉      | 22826/57600 [3:59:54<6:04:47,  1.59it/s]
 40%|███▉      | 22827/57600 [3:59:54<6:00:39,  1.61it/s]
 40%|███▉      | 22828/57600 [3:59:55<5:55:59,  1.63it/s]
 40%|███▉      | 22829/57600 [3:59:56<5:54:52,  1.63it/s]
 40%|███▉      | 22830/57600 [3:59:56<5:47:02,  1.67it/s]
 40%|███▉      | 22831/57600 [3:59:57<5:51:19,  1.65it/s]
 40%|███▉      | 22832/57600 [3:59:58<6:14:00,  1.55it/s]
 40%|███▉      | 22833/57600 [3:59:58<6:03:21,  1.59it/s]
 40%|███▉      | 22834/57600 [3:59:59<6:07:12,  1.58it/s]
 40%|███▉      | 22835/57600 [3:59:59<6:06:22,  1.58it/s]
 40%|███▉      | 22836/57600 [4:00:00<6:07:58,  1.57it/s]
 40%|███▉      | 22837/57600 [4:00:01<6:18:57,  1.53it/s]
 40%|███▉      | 22838/57600 [4:00:01<6:10:42,  1.56it/s]
 40%|███▉      | 22839/57600 [4:00:02<6:03:40,  1.59it/s]
 40%|███▉      | 22840/57600 [4:00:03<6:03:24,  1.59it/s]
                                                         
{'loss': 1.2217, 'learning_rate': 6.450174216027875e-07, 'epoch': 252.1}

 40%|███▉      | 22840/57600 [4:00:03<6:03:24,  1.59it/s]
 40%|███▉      | 22841/57600 [4:00:03<6:02:59,  1.60it/s]
 40%|███▉      | 22842/57600 [4:00:04<5:56:54,  1.62it/s]
 40%|███▉      | 22843/57600 [4:00:04<6:07:38,  1.58it/s]
 40%|███▉      | 22844/57600 [4:00:05<6:01:13,  1.60it/s]
 40%|███▉      | 22845/57600 [4:00:06<5:52:06,  1.65it/s]
 40%|███▉      | 22846/57600 [4:00:06<6:01:37,  1.60it/s]
 40%|███▉      | 22847/57600 [4:00:07<5:51:57,  1.65it/s]
 40%|███▉      | 22848/57600 [4:00:08<5:56:54,  1.62it/s]
 40%|███▉      | 22849/57600 [4:00:08<5:50:52,  1.65it/s]
 40%|███▉      | 22850/57600 [4:00:09<5:49:53,  1.66it/s]
 40%|███▉      | 22851/57600 [4:00:09<5:53:27,  1.64it/s]
 40%|███▉      | 22852/57600 [4:00:10<6:12:08,  1.56it/s]
 40%|███▉      | 22853/57600 [4:00:11<5:56:31,  1.62it/s]
 40%|███▉      | 22854/57600 [4:00:11<5:54:11,  1.64it/s]
 40%|███▉      | 22855/57600 [4:00:12<5:55:18,  1.63it/s]
 40%|███▉      | 22856/57600 [4:00:12<5:57:20,  1.62it/s]
 40%|███▉      | 22857/57600 [4:00:13<5:55:51,  1.63it/s]
 40%|███▉      | 22858/57600 [4:00:14<6:08:36,  1.57it/s]
 40%|███▉      | 22859/57600 [4:00:14<6:06:24,  1.58it/s]
 40%|███▉      | 22860/57600 [4:00:15<5:57:17,  1.62it/s]
                                                         
{'loss': 1.2416, 'learning_rate': 6.447038327526132e-07, 'epoch': 252.32}

 40%|███▉      | 22860/57600 [4:00:15<5:57:17,  1.62it/s]
 40%|███▉      | 22861/57600 [4:00:16<6:11:49,  1.56it/s]
 40%|███▉      | 22862/57600 [4:00:16<6:02:10,  1.60it/s]
 40%|███▉      | 22863/57600 [4:00:17<5:51:22,  1.65it/s]
 40%|███▉      | 22864/57600 [4:00:17<6:03:42,  1.59it/s]
 40%|███▉      | 22865/57600 [4:00:18<6:00:28,  1.61it/s]
 40%|███▉      | 22866/57600 [4:00:19<6:07:53,  1.57it/s]
 40%|███▉      | 22867/57600 [4:00:19<6:07:01,  1.58it/s]
 40%|███▉      | 22868/57600 [4:00:20<5:56:08,  1.63it/s]
 40%|███▉      | 22869/57600 [4:00:21<5:51:44,  1.65it/s]
 40%|███▉      | 22870/57600 [4:00:21<5:44:41,  1.68it/s]
 40%|███▉      | 22871/57600 [4:00:22<5:44:16,  1.68it/s]
 40%|███▉      | 22872/57600 [4:00:22<5:46:56,  1.67it/s]
 40%|███▉      | 22873/57600 [4:00:23<5:48:09,  1.66it/s]
 40%|███▉      | 22874/57600 [4:00:24<6:00:49,  1.60it/s]
 40%|███▉      | 22875/57600 [4:00:24<6:05:43,  1.58it/s]
 40%|███▉      | 22876/57600 [4:00:25<5:57:42,  1.62it/s]
 40%|███▉      | 22877/57600 [4:00:26<6:04:52,  1.59it/s]
 40%|███▉      | 22878/57600 [4:00:26<6:05:31,  1.58it/s]
 40%|███▉      | 22879/57600 [4:00:27<6:12:21,  1.55it/s]
 40%|███▉      | 22880/57600 [4:00:27<5:56:02,  1.63it/s]
                                                         
{'loss': 1.2418, 'learning_rate': 6.443902439024391e-07, 'epoch': 252.54}

 40%|███▉      | 22880/57600 [4:00:27<5:56:02,  1.63it/s]
 40%|███▉      | 22881/57600 [4:00:28<6:00:29,  1.61it/s]
 40%|███▉      | 22882/57600 [4:00:29<5:51:08,  1.65it/s]
 40%|███▉      | 22883/57600 [4:00:29<5:50:38,  1.65it/s]
 40%|███▉      | 22884/57600 [4:00:30<5:49:50,  1.65it/s]
 40%|███▉      | 22885/57600 [4:00:30<6:00:25,  1.61it/s]
 40%|███▉      | 22886/57600 [4:00:31<5:56:01,  1.63it/s]
 40%|███▉      | 22887/57600 [4:00:32<5:51:39,  1.65it/s]
 40%|███▉      | 22888/57600 [4:00:32<5:55:41,  1.63it/s]
 40%|███▉      | 22889/57600 [4:00:33<5:58:40,  1.61it/s]
 40%|███▉      | 22890/57600 [4:00:34<5:58:03,  1.62it/s]
 40%|███▉      | 22891/57600 [4:00:34<6:06:26,  1.58it/s]
 40%|███▉      | 22892/57600 [4:00:35<6:02:29,  1.60it/s]
 40%|███▉      | 22893/57600 [4:00:35<5:51:41,  1.64it/s]
 40%|███▉      | 22894/57600 [4:00:36<6:07:17,  1.57it/s]
 40%|███▉      | 22895/57600 [4:00:37<6:09:47,  1.56it/s]
 40%|███▉      | 22896/57600 [4:00:37<6:03:29,  1.59it/s]
 40%|███▉      | 22897/57600 [4:00:38<6:03:02,  1.59it/s]
 40%|███▉      | 22898/57600 [4:00:39<6:00:56,  1.60it/s]
 40%|███▉      | 22899/57600 [4:00:39<5:57:24,  1.62it/s]
 40%|███▉      | 22900/57600 [4:00:40<6:09:53,  1.56it/s]
                                                         
{'loss': 1.2268, 'learning_rate': 6.440766550522648e-07, 'epoch': 252.76}

 40%|███▉      | 22900/57600 [4:00:40<6:09:53,  1.56it/s]
 40%|███▉      | 22901/57600 [4:00:40<6:07:45,  1.57it/s]
 40%|███▉      | 22902/57600 [4:00:41<6:19:42,  1.52it/s]
 40%|███▉      | 22903/57600 [4:00:42<6:08:16,  1.57it/s]
 40%|███▉      | 22904/57600 [4:00:42<6:09:28,  1.57it/s]
 40%|███▉      | 22905/57600 [4:00:43<6:04:45,  1.59it/s]
 40%|███▉      | 22906/57600 [4:00:44<6:06:51,  1.58it/s]
 40%|███▉      | 22907/57600 [4:00:44<5:52:39,  1.64it/s]
 40%|███▉      | 22908/57600 [4:00:45<5:50:57,  1.65it/s]
 40%|███▉      | 22909/57600 [4:00:46<6:06:21,  1.58it/s]
 40%|███▉      | 22910/57600 [4:00:46<5:55:11,  1.63it/s]
 40%|███▉      | 22911/57600 [4:00:47<5:48:40,  1.66it/s]
 40%|███▉      | 22912/57600 [4:00:47<5:55:46,  1.63it/s]
 40%|███▉      | 22913/57600 [4:00:48<6:02:04,  1.60it/s]
 40%|███▉      | 22914/57600 [4:00:49<6:06:06,  1.58it/s]
 40%|███▉      | 22915/57600 [4:00:49<6:19:08,  1.52it/s]
 40%|███▉      | 22916/57600 [4:00:50<6:13:31,  1.55it/s]
 40%|███▉      | 22917/57600 [4:00:51<6:17:24,  1.53it/s]
 40%|███▉      | 22918/57600 [4:00:51<6:05:24,  1.58it/s]
 40%|███▉      | 22919/57600 [4:00:52<5:51:35,  1.64it/s]
 40%|███▉      | 22920/57600 [4:00:52<5:47:39,  1.66it/s]
                                                         
{'loss': 1.2491, 'learning_rate': 6.437630662020906e-07, 'epoch': 252.98}

 40%|███▉      | 22920/57600 [4:00:52<5:47:39,  1.66it/s]
 40%|███▉      | 22921/57600 [4:00:53<5:44:40,  1.68it/s]
 40%|███▉      | 22922/57600 [4:00:54<6:06:28,  1.58it/s]
 40%|███▉      | 22923/57600 [4:00:54<6:02:19,  1.60it/s]
 40%|███▉      | 22924/57600 [4:00:55<6:03:49,  1.59it/s]
 40%|███▉      | 22925/57600 [4:00:56<6:05:54,  1.58it/s]
 40%|███▉      | 22926/57600 [4:00:56<6:08:41,  1.57it/s]
 40%|███▉      | 22927/57600 [4:00:57<6:07:35,  1.57it/s]
 40%|███▉      | 22928/57600 [4:00:57<5:59:20,  1.61it/s]
 40%|███▉      | 22929/57600 [4:00:58<5:52:07,  1.64it/s]
 40%|███▉      | 22930/57600 [4:00:59<5:48:27,  1.66it/s]
 40%|███▉      | 22931/57600 [4:00:59<6:04:39,  1.58it/s]
 40%|███▉      | 22932/57600 [4:01:00<6:04:30,  1.59it/s]
 40%|███▉      | 22933/57600 [4:01:01<6:03:10,  1.59it/s]
 40%|███▉      | 22934/57600 [4:01:01<6:02:38,  1.59it/s]
 40%|███▉      | 22935/57600 [4:01:02<5:58:47,  1.61it/s]
 40%|███▉      | 22936/57600 [4:01:02<6:04:59,  1.58it/s]
 40%|███▉      | 22937/57600 [4:01:03<6:08:13,  1.57it/s]
 40%|███▉      | 22938/57600 [4:01:04<6:16:15,  1.54it/s]
 40%|███▉      | 22939/57600 [4:01:04<6:09:19,  1.56it/s]
 40%|███▉      | 22940/57600 [4:01:05<6:10:25,  1.56it/s]
                                                         
{'loss': 1.2296, 'learning_rate': 6.434494773519163e-07, 'epoch': 253.2}

 40%|███▉      | 22940/57600 [4:01:05<6:10:25,  1.56it/s]
 40%|███▉      | 22941/57600 [4:01:06<6:20:04,  1.52it/s]
 40%|███▉      | 22942/57600 [4:01:06<6:10:51,  1.56it/s]
 40%|███▉      | 22943/57600 [4:01:07<6:06:53,  1.57it/s]
 40%|███▉      | 22944/57600 [4:01:08<6:02:16,  1.59it/s]
 40%|███▉      | 22945/57600 [4:01:08<5:58:23,  1.61it/s]
 40%|███▉      | 22946/57600 [4:01:09<6:04:53,  1.58it/s]
 40%|███▉      | 22947/57600 [4:01:09<6:10:17,  1.56it/s]
 40%|███▉      | 22948/57600 [4:01:10<6:05:56,  1.58it/s]
 40%|███▉      | 22949/57600 [4:01:11<6:02:04,  1.59it/s]
 40%|███▉      | 22950/57600 [4:01:11<5:57:59,  1.61it/s]
 40%|███▉      | 22951/57600 [4:01:12<6:05:15,  1.58it/s]
 40%|███▉      | 22952/57600 [4:01:13<6:07:15,  1.57it/s]
 40%|███▉      | 22953/57600 [4:01:13<6:01:40,  1.60it/s]
 40%|███▉      | 22954/57600 [4:01:14<5:56:58,  1.62it/s]
 40%|███▉      | 22955/57600 [4:01:14<6:01:21,  1.60it/s]
 40%|███▉      | 22956/57600 [4:01:15<6:03:54,  1.59it/s]
 40%|███▉      | 22957/57600 [4:01:16<6:11:01,  1.56it/s]
 40%|███▉      | 22958/57600 [4:01:16<6:09:36,  1.56it/s]
 40%|███▉      | 22959/57600 [4:01:17<5:53:34,  1.63it/s]
 40%|███▉      | 22960/57600 [4:01:18<5:58:01,  1.61it/s]
                                                         
{'loss': 1.2027, 'learning_rate': 6.431358885017422e-07, 'epoch': 253.42}

 40%|███▉      | 22960/57600 [4:01:18<5:58:01,  1.61it/s]
 40%|███▉      | 22961/57600 [4:01:18<5:54:51,  1.63it/s]
 40%|███▉      | 22962/57600 [4:01:19<5:57:36,  1.61it/s]
 40%|███▉      | 22963/57600 [4:01:19<5:56:32,  1.62it/s]
 40%|███▉      | 22964/57600 [4:01:20<5:57:03,  1.62it/s]
 40%|███▉      | 22965/57600 [4:01:21<6:03:38,  1.59it/s]
 40%|███▉      | 22966/57600 [4:01:21<6:08:42,  1.57it/s]
 40%|███▉      | 22967/57600 [4:01:22<5:55:14,  1.62it/s]
 40%|███▉      | 22968/57600 [4:01:22<5:49:43,  1.65it/s]
 40%|███▉      | 22969/57600 [4:01:23<5:57:04,  1.62it/s]
 40%|███▉      | 22970/57600 [4:01:24<5:54:45,  1.63it/s]
 40%|███▉      | 22971/57600 [4:01:24<6:05:44,  1.58it/s]
 40%|███▉      | 22972/57600 [4:01:25<5:56:31,  1.62it/s]
 40%|███▉      | 22973/57600 [4:01:26<5:50:42,  1.65it/s]
 40%|███▉      | 22974/57600 [4:01:26<5:54:26,  1.63it/s]
 40%|███▉      | 22975/57600 [4:01:27<5:59:04,  1.61it/s]
 40%|███▉      | 22976/57600 [4:01:28<6:08:44,  1.56it/s]
 40%|███▉      | 22977/57600 [4:01:28<6:05:00,  1.58it/s]
 40%|███▉      | 22978/57600 [4:01:29<5:57:23,  1.61it/s]
 40%|███▉      | 22979/57600 [4:01:29<5:47:44,  1.66it/s]
 40%|███▉      | 22980/57600 [4:01:30<6:00:23,  1.60it/s]
                                                         
{'loss': 1.2225, 'learning_rate': 6.428222996515679e-07, 'epoch': 253.64}

 40%|███▉      | 22980/57600 [4:01:30<6:00:23,  1.60it/s]
 40%|███▉      | 22981/57600 [4:01:31<6:00:33,  1.60it/s]
 40%|███▉      | 22982/57600 [4:01:31<6:08:31,  1.57it/s]
 40%|███▉      | 22983/57600 [4:01:32<6:12:39,  1.55it/s]
 40%|███▉      | 22984/57600 [4:01:32<5:56:02,  1.62it/s]
 40%|███▉      | 22985/57600 [4:01:33<5:58:56,  1.61it/s]
 40%|███▉      | 22986/57600 [4:01:34<6:08:15,  1.57it/s]
 40%|███▉      | 22987/57600 [4:01:34<6:06:10,  1.58it/s]
 40%|███▉      | 22988/57600 [4:01:35<5:51:48,  1.64it/s]
 40%|███▉      | 22989/57600 [4:01:36<5:47:24,  1.66it/s]
 40%|███▉      | 22990/57600 [4:01:36<5:47:55,  1.66it/s]
 40%|███▉      | 22991/57600 [4:01:37<5:37:13,  1.71it/s]
 40%|███▉      | 22992/57600 [4:01:37<5:34:40,  1.72it/s]
 40%|███▉      | 22993/57600 [4:01:38<5:46:14,  1.67it/s]
 40%|███▉      | 22994/57600 [4:01:39<5:45:16,  1.67it/s]
 40%|███▉      | 22995/57600 [4:01:39<6:01:32,  1.60it/s]
 40%|███▉      | 22996/57600 [4:01:40<6:06:46,  1.57it/s]
 40%|███▉      | 22997/57600 [4:01:40<6:07:15,  1.57it/s]
 40%|███▉      | 22998/57600 [4:01:41<6:06:58,  1.57it/s]
 40%|███▉      | 22999/57600 [4:01:42<6:00:19,  1.60it/s]
 40%|███▉      | 23000/57600 [4:01:42<6:03:04,  1.59it/s]
                                                         
{'loss': 1.2255, 'learning_rate': 6.425087108013937e-07, 'epoch': 253.86}

 40%|███▉      | 23000/57600 [4:01:42<6:03:04,  1.59it/s]
 40%|███▉      | 23001/57600 [4:01:43<5:56:05,  1.62it/s]
 40%|███▉      | 23002/57600 [4:01:44<5:57:15,  1.61it/s]
 40%|███▉      | 23003/57600 [4:01:44<5:49:33,  1.65it/s]
 40%|███▉      | 23004/57600 [4:01:45<5:49:00,  1.65it/s]
 40%|███▉      | 23005/57600 [4:01:45<5:51:04,  1.64it/s]
 40%|███▉      | 23006/57600 [4:01:46<5:50:42,  1.64it/s]
 40%|███▉      | 23007/57600 [4:01:47<5:49:07,  1.65it/s]
 40%|███▉      | 23008/57600 [4:01:47<5:51:06,  1.64it/s]
 40%|███▉      | 23009/57600 [4:01:48<5:53:43,  1.63it/s]
 40%|███▉      | 23010/57600 [4:01:48<5:52:43,  1.63it/s]
 40%|███▉      | 23011/57600 [4:01:49<5:42:23,  1.68it/s]
 40%|███▉      | 23012/57600 [4:01:50<5:46:43,  1.66it/s]
 40%|███▉      | 23013/57600 [4:01:50<5:54:22,  1.63it/s]
 40%|███▉      | 23014/57600 [4:01:51<6:01:02,  1.60it/s]
 40%|███▉      | 23015/57600 [4:01:52<5:56:25,  1.62it/s]
 40%|███▉      | 23016/57600 [4:01:52<6:18:29,  1.52it/s]
 40%|███▉      | 23017/57600 [4:01:53<6:17:26,  1.53it/s]
 40%|███▉      | 23018/57600 [4:01:54<6:18:32,  1.52it/s]
 40%|███▉      | 23019/57600 [4:01:54<6:15:44,  1.53it/s]
 40%|███▉      | 23020/57600 [4:01:55<6:10:59,  1.55it/s]
                                                         
{'loss': 1.1998, 'learning_rate': 6.421951219512194e-07, 'epoch': 254.08}

 40%|███▉      | 23020/57600 [4:01:55<6:10:59,  1.55it/s]
 40%|███▉      | 23021/57600 [4:01:55<5:54:45,  1.62it/s]
 40%|███▉      | 23022/57600 [4:01:56<5:50:58,  1.64it/s]
 40%|███▉      | 23023/57600 [4:01:57<5:42:40,  1.68it/s]
 40%|███▉      | 23024/57600 [4:01:57<5:48:26,  1.65it/s]
 40%|███▉      | 23025/57600 [4:01:58<5:51:43,  1.64it/s]
 40%|███▉      | 23026/57600 [4:01:58<5:58:30,  1.61it/s]
 40%|███▉      | 23027/57600 [4:01:59<5:51:49,  1.64it/s]
 40%|███▉      | 23028/57600 [4:02:00<6:00:51,  1.60it/s]
 40%|███▉      | 23029/57600 [4:02:00<6:12:07,  1.55it/s]
 40%|███▉      | 23030/57600 [4:02:01<6:03:31,  1.58it/s]
 40%|███▉      | 23031/57600 [4:02:02<6:01:04,  1.60it/s]
 40%|███▉      | 23032/57600 [4:02:02<5:55:37,  1.62it/s]
 40%|███▉      | 23033/57600 [4:02:03<5:51:57,  1.64it/s]
 40%|███▉      | 23034/57600 [4:02:03<5:50:07,  1.65it/s]
 40%|███▉      | 23035/57600 [4:02:04<6:14:29,  1.54it/s]
 40%|███▉      | 23036/57600 [4:02:05<6:26:37,  1.49it/s]
 40%|███▉      | 23037/57600 [4:02:05<6:22:33,  1.51it/s]
 40%|███▉      | 23038/57600 [4:02:06<6:22:11,  1.51it/s]
 40%|███▉      | 23039/57600 [4:02:07<6:16:39,  1.53it/s]
 40%|████      | 23040/57600 [4:02:07<6:18:16,  1.52it/s]
                                                         
{'loss': 1.1963, 'learning_rate': 6.418815331010453e-07, 'epoch': 254.3}

 40%|████      | 23040/57600 [4:02:07<6:18:16,  1.52it/s]
 40%|████      | 23041/57600 [4:02:08<6:00:17,  1.60it/s]
 40%|████      | 23042/57600 [4:02:09<6:02:42,  1.59it/s]
 40%|████      | 23043/57600 [4:02:09<5:46:16,  1.66it/s]
 40%|████      | 23044/57600 [4:02:10<5:48:34,  1.65it/s]
 40%|████      | 23045/57600 [4:02:10<5:41:13,  1.69it/s]
 40%|████      | 23046/57600 [4:02:11<5:47:34,  1.66it/s]
 40%|████      | 23047/57600 [4:02:12<5:44:43,  1.67it/s]
 40%|████      | 23048/57600 [4:02:12<5:53:00,  1.63it/s]
 40%|████      | 23049/57600 [4:02:13<5:46:00,  1.66it/s]
 40%|████      | 23050/57600 [4:02:13<5:51:18,  1.64it/s]
 40%|████      | 23051/57600 [4:02:14<5:37:48,  1.70it/s]
 40%|████      | 23052/57600 [4:02:15<5:53:16,  1.63it/s]
 40%|████      | 23053/57600 [4:02:15<5:45:59,  1.66it/s]
 40%|████      | 23054/57600 [4:02:16<6:04:46,  1.58it/s]
 40%|████      | 23055/57600 [4:02:17<5:58:54,  1.60it/s]
 40%|████      | 23056/57600 [4:02:17<5:56:40,  1.61it/s]
 40%|████      | 23057/57600 [4:02:18<6:08:59,  1.56it/s]
 40%|████      | 23058/57600 [4:02:18<5:55:37,  1.62it/s]
 40%|████      | 23059/57600 [4:02:19<5:49:31,  1.65it/s]
 40%|████      | 23060/57600 [4:02:20<5:45:22,  1.67it/s]
                                                         
{'loss': 1.2718, 'learning_rate': 6.41567944250871e-07, 'epoch': 254.53}

 40%|████      | 23060/57600 [4:02:20<5:45:22,  1.67it/s]
 40%|████      | 23061/57600 [4:02:20<5:36:14,  1.71it/s]
 40%|████      | 23062/57600 [4:02:21<5:49:04,  1.65it/s]
 40%|████      | 23063/57600 [4:02:21<5:57:19,  1.61it/s]
 40%|████      | 23064/57600 [4:02:22<5:46:25,  1.66it/s]
 40%|████      | 23065/57600 [4:02:23<5:46:17,  1.66it/s]
 40%|████      | 23066/57600 [4:02:23<5:44:10,  1.67it/s]
 40%|████      | 23067/57600 [4:02:24<5:55:44,  1.62it/s]
 40%|████      | 23068/57600 [4:02:24<6:02:01,  1.59it/s]
 40%|████      | 23069/57600 [4:02:25<6:06:05,  1.57it/s]
 40%|████      | 23070/57600 [4:02:26<5:52:59,  1.63it/s]
 40%|████      | 23071/57600 [4:02:26<6:01:53,  1.59it/s]
 40%|████      | 23072/57600 [4:02:27<5:53:04,  1.63it/s]
 40%|████      | 23073/57600 [4:02:28<5:53:07,  1.63it/s]
 40%|████      | 23074/57600 [4:02:28<6:02:36,  1.59it/s]
 40%|████      | 23075/57600 [4:02:29<5:54:13,  1.62it/s]
 40%|████      | 23076/57600 [4:02:29<6:01:38,  1.59it/s]
 40%|████      | 23077/57600 [4:02:30<5:54:35,  1.62it/s]
 40%|████      | 23078/57600 [4:02:31<5:42:17,  1.68it/s]
 40%|████      | 23079/57600 [4:02:31<5:45:18,  1.67it/s]
 40%|████      | 23080/57600 [4:02:32<5:46:20,  1.66it/s]
                                                         
{'loss': 1.2729, 'learning_rate': 6.412543554006968e-07, 'epoch': 254.75}

 40%|████      | 23080/57600 [4:02:32<5:46:20,  1.66it/s]
 40%|████      | 23081/57600 [4:02:32<5:51:17,  1.64it/s]
 40%|████      | 23082/57600 [4:02:33<5:46:08,  1.66it/s]
 40%|████      | 23083/57600 [4:02:34<5:36:45,  1.71it/s]
 40%|████      | 23084/57600 [4:02:34<5:36:28,  1.71it/s]
 40%|████      | 23085/57600 [4:02:35<5:45:57,  1.66it/s]
 40%|████      | 23086/57600 [4:02:35<5:41:03,  1.69it/s]
 40%|████      | 23087/57600 [4:02:36<5:57:27,  1.61it/s]
 40%|████      | 23088/57600 [4:02:37<6:02:12,  1.59it/s]
 40%|████      | 23089/57600 [4:02:37<6:00:51,  1.59it/s]
 40%|████      | 23090/57600 [4:02:38<6:03:39,  1.58it/s]
 40%|████      | 23091/57600 [4:02:39<6:05:29,  1.57it/s]
 40%|████      | 23092/57600 [4:02:39<5:58:21,  1.60it/s]
 40%|████      | 23093/57600 [4:02:40<6:02:53,  1.58it/s]
 40%|████      | 23094/57600 [4:02:41<6:10:36,  1.55it/s]
 40%|████      | 23095/57600 [4:02:41<6:17:15,  1.52it/s]
 40%|████      | 23096/57600 [4:02:42<6:11:31,  1.55it/s]
 40%|████      | 23097/57600 [4:02:42<6:00:21,  1.60it/s]
 40%|████      | 23098/57600 [4:02:43<5:56:30,  1.61it/s]
 40%|████      | 23099/57600 [4:02:44<5:44:38,  1.67it/s]
 40%|████      | 23100/57600 [4:02:44<5:43:06,  1.68it/s]
                                                         
{'loss': 1.2323, 'learning_rate': 6.409407665505227e-07, 'epoch': 254.97}

 40%|████      | 23100/57600 [4:02:44<5:43:06,  1.68it/s]
 40%|████      | 23101/57600 [4:02:45<5:54:42,  1.62it/s]
 40%|████      | 23102/57600 [4:02:45<5:53:57,  1.62it/s]
 40%|████      | 23103/57600 [4:02:46<5:57:18,  1.61it/s]
 40%|████      | 23104/57600 [4:02:47<6:04:49,  1.58it/s]
 40%|████      | 23105/57600 [4:02:47<5:59:57,  1.60it/s]
 40%|████      | 23106/57600 [4:02:48<6:02:41,  1.59it/s]
 40%|████      | 23107/57600 [4:02:49<5:51:55,  1.63it/s]
 40%|████      | 23108/57600 [4:02:49<5:51:35,  1.64it/s]
 40%|████      | 23109/57600 [4:02:50<5:49:44,  1.64it/s]
 40%|████      | 23110/57600 [4:02:50<5:59:16,  1.60it/s]
 40%|████      | 23111/57600 [4:02:51<5:52:25,  1.63it/s]
 40%|████      | 23112/57600 [4:02:52<5:52:10,  1.63it/s]
 40%|████      | 23113/57600 [4:02:52<5:57:45,  1.61it/s]
 40%|████      | 23114/57600 [4:02:53<5:53:28,  1.63it/s]
 40%|████      | 23115/57600 [4:02:53<5:52:21,  1.63it/s]
 40%|████      | 23116/57600 [4:02:54<5:49:48,  1.64it/s]
 40%|████      | 23117/57600 [4:02:55<5:51:29,  1.64it/s]
 40%|████      | 23118/57600 [4:02:55<5:43:01,  1.68it/s]
 40%|████      | 23119/57600 [4:02:56<6:01:53,  1.59it/s]
 40%|████      | 23120/57600 [4:02:57<6:00:28,  1.59it/s]
                                                         
{'loss': 1.1998, 'learning_rate': 6.406271777003484e-07, 'epoch': 255.19}

 40%|████      | 23120/57600 [4:02:57<6:00:28,  1.59it/s]
 40%|████      | 23121/57600 [4:02:57<6:09:47,  1.55it/s]
 40%|████      | 23122/57600 [4:02:58<6:17:14,  1.52it/s]
 40%|████      | 23123/57600 [4:02:59<6:20:08,  1.51it/s]
 40%|████      | 23124/57600 [4:02:59<6:09:50,  1.55it/s]
 40%|████      | 23125/57600 [4:03:00<6:04:29,  1.58it/s]
 40%|████      | 23126/57600 [4:03:00<6:04:47,  1.58it/s]
 40%|████      | 23127/57600 [4:03:01<5:55:34,  1.62it/s]
 40%|████      | 23128/57600 [4:03:02<5:58:32,  1.60it/s]
 40%|████      | 23129/57600 [4:03:02<5:58:55,  1.60it/s]
 40%|████      | 23130/57600 [4:03:03<5:59:29,  1.60it/s]
 40%|████      | 23131/57600 [4:03:04<6:04:10,  1.58it/s]
 40%|████      | 23132/57600 [4:03:04<5:53:43,  1.62it/s]
 40%|████      | 23133/57600 [4:03:05<5:51:13,  1.64it/s]
 40%|████      | 23134/57600 [4:03:05<5:50:13,  1.64it/s]
 40%|████      | 23135/57600 [4:03:06<5:45:37,  1.66it/s]
 40%|████      | 23136/57600 [4:03:07<5:50:08,  1.64it/s]
 40%|████      | 23137/57600 [4:03:07<5:47:57,  1.65it/s]
 40%|████      | 23138/57600 [4:03:08<5:43:00,  1.67it/s]
 40%|████      | 23139/57600 [4:03:08<5:57:59,  1.60it/s]
 40%|████      | 23140/57600 [4:03:09<5:55:24,  1.62it/s]
                                                         
{'loss': 1.2034, 'learning_rate': 6.403135888501742e-07, 'epoch': 255.41}

 40%|████      | 23140/57600 [4:03:09<5:55:24,  1.62it/s]
 40%|████      | 23141/57600 [4:03:10<5:46:06,  1.66it/s]
 40%|████      | 23142/57600 [4:03:10<5:50:07,  1.64it/s]
 40%|████      | 23143/57600 [4:03:11<5:41:32,  1.68it/s]
 40%|████      | 23144/57600 [4:03:11<5:41:00,  1.68it/s]
 40%|████      | 23145/57600 [4:03:12<5:43:10,  1.67it/s]
 40%|████      | 23146/57600 [4:03:13<5:37:51,  1.70it/s]
 40%|████      | 23147/57600 [4:03:13<5:31:59,  1.73it/s]
 40%|████      | 23148/57600 [4:03:14<5:40:37,  1.69it/s]
 40%|████      | 23149/57600 [4:03:14<5:36:37,  1.71it/s]
 40%|████      | 23150/57600 [4:03:15<5:51:52,  1.63it/s]
 40%|████      | 23151/57600 [4:03:16<5:42:16,  1.68it/s]
 40%|████      | 23152/57600 [4:03:16<5:41:38,  1.68it/s]
 40%|████      | 23153/57600 [4:03:17<6:00:01,  1.59it/s]
 40%|████      | 23154/57600 [4:03:18<6:06:50,  1.56it/s]
 40%|████      | 23155/57600 [4:03:18<5:59:59,  1.59it/s]
 40%|████      | 23156/57600 [4:03:19<6:01:16,  1.59it/s]
 40%|████      | 23157/57600 [4:03:19<6:05:12,  1.57it/s]
 40%|████      | 23158/57600 [4:03:20<6:08:13,  1.56it/s]
 40%|████      | 23159/57600 [4:03:21<5:56:31,  1.61it/s]
 40%|████      | 23160/57600 [4:03:21<5:46:37,  1.66it/s]
                                                         
{'loss': 1.255, 'learning_rate': 6.399999999999999e-07, 'epoch': 255.63}

 40%|████      | 23160/57600 [4:03:21<5:46:37,  1.66it/s]
 40%|████      | 23161/57600 [4:03:22<5:55:00,  1.62it/s]
 40%|████      | 23162/57600 [4:03:22<5:47:01,  1.65it/s]
 40%|████      | 23163/57600 [4:03:23<6:09:31,  1.55it/s]
 40%|████      | 23164/57600 [4:03:24<6:02:38,  1.58it/s]
 40%|████      | 23165/57600 [4:03:24<5:55:41,  1.61it/s]
 40%|████      | 23166/57600 [4:03:25<5:56:08,  1.61it/s]
 40%|████      | 23167/57600 [4:03:26<5:56:00,  1.61it/s]
 40%|████      | 23168/57600 [4:03:26<5:58:37,  1.60it/s]
 40%|████      | 23169/57600 [4:03:27<5:47:17,  1.65it/s]
 40%|████      | 23170/57600 [4:03:27<5:47:24,  1.65it/s]
 40%|████      | 23171/57600 [4:03:28<5:43:11,  1.67it/s]
 40%|████      | 23172/57600 [4:03:29<5:45:49,  1.66it/s]
 40%|████      | 23173/57600 [4:03:29<5:48:38,  1.65it/s]
 40%|████      | 23174/57600 [4:03:30<5:46:14,  1.66it/s]
 40%|████      | 23175/57600 [4:03:30<5:51:12,  1.63it/s]
 40%|████      | 23176/57600 [4:03:31<5:40:15,  1.69it/s]
 40%|████      | 23177/57600 [4:03:32<5:41:34,  1.68it/s]
 40%|████      | 23178/57600 [4:03:32<5:43:42,  1.67it/s]
 40%|████      | 23179/57600 [4:03:33<5:54:38,  1.62it/s]
 40%|████      | 23180/57600 [4:03:33<5:55:53,  1.61it/s]
                                                         
{'loss': 1.2207, 'learning_rate': 6.396864111498258e-07, 'epoch': 255.85}

 40%|████      | 23180/57600 [4:03:33<5:55:53,  1.61it/s]
 40%|████      | 23181/57600 [4:03:34<6:00:37,  1.59it/s]
 40%|████      | 23182/57600 [4:03:35<5:55:24,  1.61it/s]
 40%|████      | 23183/57600 [4:03:35<5:46:29,  1.66it/s]
 40%|████      | 23184/57600 [4:03:36<5:51:36,  1.63it/s]
 40%|████      | 23185/57600 [4:03:37<5:58:42,  1.60it/s]
 40%|████      | 23186/57600 [4:03:37<5:48:35,  1.65it/s]
 40%|████      | 23187/57600 [4:03:38<5:47:34,  1.65it/s]
 40%|████      | 23188/57600 [4:03:38<6:00:08,  1.59it/s]
 40%|████      | 23189/57600 [4:03:39<6:00:34,  1.59it/s]
 40%|████      | 23190/57600 [4:03:40<6:03:14,  1.58it/s]
 40%|████      | 23191/57600 [4:03:40<6:04:40,  1.57it/s]
 40%|████      | 23192/57600 [4:03:41<6:21:21,  1.50it/s]
 40%|████      | 23193/57600 [4:03:42<6:14:34,  1.53it/s]
 40%|████      | 23194/57600 [4:03:42<6:19:35,  1.51it/s]
 40%|████      | 23195/57600 [4:03:43<6:16:10,  1.52it/s]
 40%|████      | 23196/57600 [4:03:44<6:14:34,  1.53it/s]
 40%|████      | 23197/57600 [4:03:44<6:15:59,  1.53it/s]
 40%|████      | 23198/57600 [4:03:45<6:19:48,  1.51it/s]
 40%|████      | 23199/57600 [4:03:46<6:10:59,  1.55it/s]
 40%|████      | 23200/57600 [4:03:46<6:08:24,  1.56it/s]
                                                         
{'loss': 1.202, 'learning_rate': 6.393728222996515e-07, 'epoch': 256.07}

 40%|████      | 23200/57600 [4:03:46<6:08:24,  1.56it/s]
 40%|████      | 23201/57600 [4:03:47<6:22:01,  1.50it/s]
 40%|████      | 23202/57600 [4:03:48<6:21:31,  1.50it/s]
 40%|████      | 23203/57600 [4:03:48<6:11:45,  1.54it/s]
 40%|████      | 23204/57600 [4:03:49<6:04:49,  1.57it/s]
 40%|████      | 23205/57600 [4:03:50<6:10:49,  1.55it/s]
 40%|████      | 23206/57600 [4:03:50<5:56:18,  1.61it/s]
 40%|████      | 23207/57600 [4:03:51<5:54:44,  1.62it/s]
 40%|████      | 23208/57600 [4:03:51<5:46:34,  1.65it/s]
 40%|████      | 23209/57600 [4:03:52<5:52:57,  1.62it/s]
 40%|████      | 23210/57600 [4:03:53<5:55:10,  1.61it/s]
 40%|████      | 23211/57600 [4:03:53<5:46:42,  1.65it/s]
 40%|████      | 23212/57600 [4:03:54<5:43:43,  1.67it/s]
 40%|████      | 23213/57600 [4:03:54<5:53:22,  1.62it/s]
 40%|████      | 23214/57600 [4:03:55<5:52:34,  1.63it/s]
 40%|████      | 23215/57600 [4:03:56<6:08:11,  1.56it/s]
 40%|████      | 23216/57600 [4:03:56<6:01:41,  1.58it/s]
 40%|████      | 23217/57600 [4:03:57<5:51:05,  1.63it/s]
 40%|████      | 23218/57600 [4:03:58<5:58:21,  1.60it/s]
 40%|████      | 23219/57600 [4:03:58<5:58:05,  1.60it/s]
 40%|████      | 23220/57600 [4:03:59<5:50:33,  1.63it/s]
                                                         
{'loss': 1.2386, 'learning_rate': 6.390592334494773e-07, 'epoch': 256.29}

 40%|████      | 23220/57600 [4:03:59<5:50:33,  1.63it/s]
 40%|████      | 23221/57600 [4:03:59<5:46:02,  1.66it/s]
 40%|████      | 23222/57600 [4:04:00<5:56:21,  1.61it/s]
 40%|████      | 23223/57600 [4:04:01<5:50:23,  1.64it/s]
 40%|████      | 23224/57600 [4:04:01<5:56:14,  1.61it/s]
 40%|████      | 23225/57600 [4:04:02<6:03:13,  1.58it/s]
 40%|████      | 23226/57600 [4:04:02<6:03:23,  1.58it/s]
 40%|████      | 23227/57600 [4:04:03<5:57:43,  1.60it/s]
 40%|████      | 23228/57600 [4:04:04<5:50:14,  1.64it/s]
 40%|████      | 23229/57600 [4:04:04<5:50:13,  1.64it/s]
 40%|████      | 23230/57600 [4:04:05<5:39:29,  1.69it/s]
 40%|████      | 23231/57600 [4:04:05<5:38:24,  1.69it/s]
 40%|████      | 23232/57600 [4:04:06<5:43:51,  1.67it/s]
 40%|████      | 23233/57600 [4:04:07<5:46:46,  1.65it/s]
 40%|████      | 23234/57600 [4:04:07<5:47:16,  1.65it/s]
 40%|████      | 23235/57600 [4:04:08<5:53:54,  1.62it/s]
 40%|████      | 23236/57600 [4:04:09<5:58:07,  1.60it/s]
 40%|████      | 23237/57600 [4:04:09<5:55:19,  1.61it/s]
 40%|████      | 23238/57600 [4:04:10<5:55:26,  1.61it/s]
 40%|████      | 23239/57600 [4:04:10<5:59:07,  1.59it/s]
 40%|████      | 23240/57600 [4:04:11<6:12:11,  1.54it/s]
                                                         
{'loss': 1.2212, 'learning_rate': 6.387456445993031e-07, 'epoch': 256.51}

 40%|████      | 23240/57600 [4:04:11<6:12:11,  1.54it/s]
 40%|████      | 23241/57600 [4:04:12<6:05:42,  1.57it/s]
 40%|████      | 23242/57600 [4:04:12<5:59:41,  1.59it/s]
 40%|████      | 23243/57600 [4:04:13<5:49:59,  1.64it/s]
 40%|████      | 23244/57600 [4:04:14<5:54:04,  1.62it/s]
 40%|████      | 23245/57600 [4:04:14<5:51:40,  1.63it/s]
 40%|████      | 23246/57600 [4:04:15<5:42:28,  1.67it/s]
 40%|████      | 23247/57600 [4:04:15<5:44:00,  1.66it/s]
 40%|████      | 23248/57600 [4:04:16<5:47:55,  1.65it/s]
 40%|████      | 23249/57600 [4:04:17<5:41:40,  1.68it/s]
 40%|████      | 23250/57600 [4:04:17<5:33:06,  1.72it/s]
 40%|████      | 23251/57600 [4:04:18<5:36:32,  1.70it/s]
 40%|████      | 23252/57600 [4:04:18<5:42:01,  1.67it/s]
 40%|████      | 23253/57600 [4:04:19<5:43:42,  1.67it/s]
 40%|████      | 23254/57600 [4:04:19<5:40:34,  1.68it/s]
 40%|████      | 23255/57600 [4:04:20<5:35:21,  1.71it/s]
 40%|████      | 23256/57600 [4:04:21<5:53:38,  1.62it/s]
 40%|████      | 23257/57600 [4:04:21<5:44:06,  1.66it/s]
 40%|████      | 23258/57600 [4:04:22<5:37:20,  1.70it/s]
 40%|████      | 23259/57600 [4:04:23<5:52:00,  1.63it/s]
 40%|████      | 23260/57600 [4:04:23<6:13:10,  1.53it/s]
                                                         
{'loss': 1.2496, 'learning_rate': 6.384320557491289e-07, 'epoch': 256.73}

 40%|████      | 23260/57600 [4:04:23<6:13:10,  1.53it/s]
 40%|████      | 23261/57600 [4:04:24<6:01:58,  1.58it/s]
 40%|████      | 23262/57600 [4:04:24<5:51:17,  1.63it/s]
 40%|████      | 23263/57600 [4:04:25<5:54:09,  1.62it/s]
 40%|████      | 23264/57600 [4:04:26<5:55:52,  1.61it/s]
 40%|████      | 23265/57600 [4:04:26<6:04:30,  1.57it/s]
 40%|████      | 23266/57600 [4:04:27<5:57:00,  1.60it/s]
 40%|████      | 23267/57600 [4:04:28<5:52:53,  1.62it/s]
 40%|████      | 23268/57600 [4:04:28<5:55:11,  1.61it/s]
 40%|████      | 23269/57600 [4:04:29<5:58:04,  1.60it/s]
 40%|████      | 23270/57600 [4:04:29<5:44:41,  1.66it/s]
 40%|████      | 23271/57600 [4:04:30<5:47:00,  1.65it/s]
 40%|████      | 23272/57600 [4:04:31<5:57:25,  1.60it/s]
 40%|████      | 23273/57600 [4:04:31<5:49:33,  1.64it/s]
 40%|████      | 23274/57600 [4:04:32<5:45:43,  1.65it/s]
 40%|████      | 23275/57600 [4:04:32<5:42:30,  1.67it/s]
 40%|████      | 23276/57600 [4:04:33<5:54:30,  1.61it/s]
 40%|████      | 23277/57600 [4:04:34<5:50:45,  1.63it/s]
 40%|████      | 23278/57600 [4:04:34<6:04:08,  1.57it/s]
 40%|████      | 23279/57600 [4:04:35<6:10:06,  1.55it/s]
 40%|████      | 23280/57600 [4:04:36<6:02:53,  1.58it/s]
                                                         
{'loss': 1.2011, 'learning_rate': 6.381184668989546e-07, 'epoch': 256.95}

 40%|████      | 23280/57600 [4:04:36<6:02:53,  1.58it/s]
 40%|████      | 23281/57600 [4:04:36<5:58:08,  1.60it/s]
 40%|████      | 23282/57600 [4:04:37<5:48:07,  1.64it/s]
 40%|████      | 23283/57600 [4:04:37<5:52:19,  1.62it/s]
 40%|████      | 23284/57600 [4:04:38<5:47:55,  1.64it/s]
 40%|████      | 23285/57600 [4:04:39<5:56:40,  1.60it/s]
 40%|████      | 23286/57600 [4:04:39<5:59:08,  1.59it/s]
 40%|████      | 23287/57600 [4:04:40<6:03:15,  1.57it/s]
 40%|████      | 23288/57600 [4:04:41<5:54:22,  1.61it/s]
 40%|████      | 23289/57600 [4:04:41<5:57:55,  1.60it/s]
 40%|████      | 23290/57600 [4:04:42<6:02:30,  1.58it/s]
 40%|████      | 23291/57600 [4:04:43<6:06:38,  1.56it/s]
 40%|████      | 23292/57600 [4:04:43<6:12:33,  1.53it/s]
 40%|████      | 23293/57600 [4:04:44<6:11:30,  1.54it/s]
 40%|████      | 23294/57600 [4:04:44<5:54:47,  1.61it/s]
 40%|████      | 23295/57600 [4:04:45<5:53:50,  1.62it/s]
 40%|████      | 23296/57600 [4:04:46<5:51:33,  1.63it/s]
 40%|████      | 23297/57600 [4:04:46<5:53:56,  1.62it/s]
 40%|████      | 23298/57600 [4:04:47<5:45:34,  1.65it/s]
 40%|████      | 23299/57600 [4:04:47<5:46:21,  1.65it/s]
 40%|████      | 23300/57600 [4:04:48<5:55:46,  1.61it/s]
                                                         
{'loss': 1.2317, 'learning_rate': 6.378048780487805e-07, 'epoch': 257.17}

 40%|████      | 23300/57600 [4:04:48<5:55:46,  1.61it/s]
 40%|████      | 23301/57600 [4:04:49<5:53:46,  1.62it/s]
 40%|████      | 23302/57600 [4:04:49<5:46:25,  1.65it/s]
 40%|████      | 23303/57600 [4:04:50<5:55:58,  1.61it/s]
 40%|████      | 23304/57600 [4:04:51<5:59:44,  1.59it/s]
 40%|████      | 23305/57600 [4:04:51<5:47:58,  1.64it/s]
 40%|████      | 23306/57600 [4:04:52<5:44:43,  1.66it/s]
 40%|████      | 23307/57600 [4:04:52<6:07:16,  1.56it/s]
 40%|████      | 23308/57600 [4:04:53<6:10:31,  1.54it/s]
 40%|████      | 23309/57600 [4:04:54<6:03:31,  1.57it/s]
 40%|████      | 23310/57600 [4:04:54<5:52:25,  1.62it/s]
 40%|████      | 23311/57600 [4:04:55<5:58:43,  1.59it/s]
 40%|████      | 23312/57600 [4:04:56<6:02:31,  1.58it/s]
 40%|████      | 23313/57600 [4:04:56<5:54:04,  1.61it/s]
 40%|████      | 23314/57600 [4:04:57<5:47:07,  1.65it/s]
 40%|████      | 23315/57600 [4:04:57<5:39:55,  1.68it/s]
 40%|████      | 23316/57600 [4:04:58<5:51:00,  1.63it/s]
 40%|████      | 23317/57600 [4:04:59<5:43:38,  1.66it/s]
 40%|████      | 23318/57600 [4:04:59<5:35:37,  1.70it/s]
 40%|████      | 23319/57600 [4:05:00<5:36:07,  1.70it/s]
 40%|████      | 23320/57600 [4:05:00<5:40:50,  1.68it/s]
                                                         
{'loss': 1.2106, 'learning_rate': 6.374912891986062e-07, 'epoch': 257.4}

 40%|████      | 23320/57600 [4:05:00<5:40:50,  1.68it/s]
 40%|████      | 23321/57600 [4:05:01<5:50:44,  1.63it/s]
 40%|████      | 23322/57600 [4:05:02<5:54:33,  1.61it/s]
 40%|████      | 23323/57600 [4:05:02<5:51:00,  1.63it/s]
 40%|████      | 23324/57600 [4:05:03<5:59:23,  1.59it/s]
 40%|████      | 23325/57600 [4:05:03<5:44:02,  1.66it/s]
 40%|████      | 23326/57600 [4:05:04<5:37:31,  1.69it/s]
 40%|████      | 23327/57600 [4:05:05<5:54:39,  1.61it/s]
 40%|████      | 23328/57600 [4:05:05<5:52:46,  1.62it/s]
 41%|████      | 23329/57600 [4:05:06<6:02:03,  1.58it/s]
 41%|████      | 23330/57600 [4:05:07<5:57:02,  1.60it/s]
 41%|████      | 23331/57600 [4:05:07<6:05:18,  1.56it/s]
 41%|████      | 23332/57600 [4:05:08<5:52:55,  1.62it/s]
 41%|████      | 23333/57600 [4:05:08<5:55:28,  1.61it/s]
 41%|████      | 23334/57600 [4:05:09<5:54:17,  1.61it/s]
 41%|████      | 23335/57600 [4:05:10<5:49:19,  1.63it/s]
 41%|████      | 23336/57600 [4:05:10<5:53:19,  1.62it/s]
 41%|████      | 23337/57600 [4:05:11<6:00:17,  1.58it/s]
 41%|████      | 23338/57600 [4:05:12<5:54:03,  1.61it/s]
 41%|████      | 23339/57600 [4:05:12<6:01:08,  1.58it/s]
 41%|████      | 23340/57600 [4:05:13<5:44:34,  1.66it/s]
                                                         
{'loss': 1.2412, 'learning_rate': 6.37177700348432e-07, 'epoch': 257.62}

 41%|████      | 23340/57600 [4:05:13<5:44:34,  1.66it/s]
 41%|████      | 23341/57600 [4:05:13<5:53:45,  1.61it/s]
 41%|████      | 23342/57600 [4:05:14<5:47:49,  1.64it/s]
 41%|████      | 23343/57600 [4:05:15<5:48:56,  1.64it/s]
 41%|████      | 23344/57600 [4:05:15<5:43:08,  1.66it/s]
 41%|████      | 23345/57600 [4:05:16<5:43:34,  1.66it/s]
 41%|████      | 23346/57600 [4:05:16<5:38:20,  1.69it/s]
 41%|████      | 23347/57600 [4:05:17<5:38:33,  1.69it/s]
 41%|████      | 23348/57600 [4:05:18<6:03:12,  1.57it/s]
 41%|████      | 23349/57600 [4:05:18<5:58:42,  1.59it/s]
 41%|████      | 23350/57600 [4:05:19<5:58:15,  1.59it/s]
 41%|████      | 23351/57600 [4:05:19<5:47:40,  1.64it/s]
 41%|████      | 23352/57600 [4:05:20<5:51:58,  1.62it/s]
 41%|████      | 23353/57600 [4:05:21<6:06:59,  1.56it/s]
 41%|████      | 23354/57600 [4:05:21<6:05:35,  1.56it/s]
 41%|████      | 23355/57600 [4:05:22<6:01:58,  1.58it/s]
 41%|████      | 23356/57600 [4:05:23<5:52:23,  1.62it/s]
 41%|████      | 23357/57600 [4:05:23<5:47:05,  1.64it/s]
 41%|████      | 23358/57600 [4:05:24<5:41:03,  1.67it/s]
 41%|████      | 23359/57600 [4:05:24<5:50:57,  1.63it/s]
 41%|████      | 23360/57600 [4:05:25<5:48:12,  1.64it/s]
                                                         
{'loss': 1.2499, 'learning_rate': 6.368641114982579e-07, 'epoch': 257.84}

 41%|████      | 23360/57600 [4:05:25<5:48:12,  1.64it/s]
 41%|████      | 23361/57600 [4:05:26<5:53:44,  1.61it/s]
 41%|████      | 23362/57600 [4:05:26<5:53:14,  1.62it/s]
 41%|████      | 23363/57600 [4:05:27<5:58:39,  1.59it/s]
 41%|████      | 23364/57600 [4:05:28<6:09:59,  1.54it/s]
 41%|████      | 23365/57600 [4:05:28<5:53:38,  1.61it/s]
 41%|████      | 23366/57600 [4:05:29<5:47:58,  1.64it/s]
 41%|████      | 23367/57600 [4:05:29<5:41:02,  1.67it/s]
 41%|████      | 23368/57600 [4:05:30<5:48:46,  1.64it/s]
 41%|████      | 23369/57600 [4:05:31<5:43:51,  1.66it/s]
 41%|████      | 23370/57600 [4:05:31<5:45:08,  1.65it/s]
 41%|████      | 23371/57600 [4:05:32<5:57:03,  1.60it/s]
 41%|████      | 23372/57600 [4:05:32<5:50:40,  1.63it/s]
 41%|████      | 23373/57600 [4:05:33<6:02:13,  1.57it/s]
 41%|████      | 23374/57600 [4:05:34<6:14:23,  1.52it/s]
 41%|████      | 23375/57600 [4:05:35<6:20:59,  1.50it/s]
 41%|████      | 23376/57600 [4:05:35<6:05:18,  1.56it/s]
 41%|████      | 23377/57600 [4:05:36<6:01:26,  1.58it/s]
 41%|████      | 23378/57600 [4:05:36<5:56:59,  1.60it/s]
 41%|████      | 23379/57600 [4:05:37<5:44:59,  1.65it/s]
 41%|████      | 23380/57600 [4:05:38<5:47:23,  1.64it/s]
                                                         
{'loss': 1.2144, 'learning_rate': 6.365505226480836e-07, 'epoch': 258.06}

 41%|████      | 23380/57600 [4:05:38<5:47:23,  1.64it/s]
 41%|████      | 23381/57600 [4:05:38<5:42:41,  1.66it/s]
 41%|████      | 23382/57600 [4:05:39<5:58:48,  1.59it/s]
 41%|████      | 23383/57600 [4:05:39<6:06:03,  1.56it/s]
 41%|████      | 23384/57600 [4:05:40<5:54:34,  1.61it/s]
 41%|████      | 23385/57600 [4:05:41<5:58:18,  1.59it/s]
 41%|████      | 23386/57600 [4:05:41<5:43:12,  1.66it/s]
 41%|████      | 23387/57600 [4:05:42<5:34:59,  1.70it/s]
 41%|████      | 23388/57600 [4:05:42<5:46:47,  1.64it/s]
 41%|████      | 23389/57600 [4:05:43<5:41:50,  1.67it/s]
 41%|████      | 23390/57600 [4:05:44<5:49:57,  1.63it/s]
 41%|████      | 23391/57600 [4:05:44<6:02:42,  1.57it/s]
 41%|████      | 23392/57600 [4:05:45<6:02:26,  1.57it/s]
 41%|████      | 23393/57600 [4:05:46<5:53:45,  1.61it/s]
 41%|████      | 23394/57600 [4:05:46<5:59:14,  1.59it/s]
 41%|████      | 23395/57600 [4:05:47<5:55:35,  1.60it/s]
 41%|████      | 23396/57600 [4:05:47<5:49:16,  1.63it/s]
 41%|████      | 23397/57600 [4:05:48<5:53:00,  1.61it/s]
 41%|████      | 23398/57600 [4:05:49<5:47:24,  1.64it/s]
 41%|████      | 23399/57600 [4:05:49<5:40:05,  1.68it/s]
 41%|████      | 23400/57600 [4:05:50<5:37:23,  1.69it/s]
                                                         
{'loss': 1.2171, 'learning_rate': 6.362369337979094e-07, 'epoch': 258.28}

 41%|████      | 23400/57600 [4:05:50<5:37:23,  1.69it/s]
 41%|████      | 23401/57600 [4:05:50<5:45:51,  1.65it/s]
 41%|████      | 23402/57600 [4:05:51<5:41:54,  1.67it/s]
 41%|████      | 23403/57600 [4:05:52<5:45:10,  1.65it/s]
 41%|████      | 23404/57600 [4:05:52<5:43:11,  1.66it/s]
 41%|████      | 23405/57600 [4:05:53<5:43:30,  1.66it/s]
 41%|████      | 23406/57600 [4:05:53<5:41:52,  1.67it/s]
 41%|████      | 23407/57600 [4:05:54<5:54:28,  1.61it/s]
 41%|████      | 23408/57600 [4:05:55<6:06:08,  1.56it/s]
 41%|████      | 23409/57600 [4:05:55<5:57:16,  1.59it/s]
 41%|████      | 23410/57600 [4:05:56<6:03:42,  1.57it/s]
 41%|████      | 23411/57600 [4:05:57<5:51:13,  1.62it/s]
 41%|████      | 23412/57600 [4:05:57<6:01:51,  1.57it/s]
 41%|████      | 23413/57600 [4:05:58<6:02:05,  1.57it/s]
 41%|████      | 23414/57600 [4:05:58<5:47:53,  1.64it/s]
 41%|████      | 23415/57600 [4:05:59<5:57:40,  1.59it/s]
 41%|████      | 23416/57600 [4:06:00<6:20:41,  1.50it/s]
 41%|████      | 23417/57600 [4:06:01<6:14:16,  1.52it/s]
 41%|████      | 23418/57600 [4:06:01<6:09:11,  1.54it/s]
 41%|████      | 23419/57600 [4:06:02<5:55:54,  1.60it/s]
 41%|████      | 23420/57600 [4:06:02<5:44:35,  1.65it/s]
                                                         
{'loss': 1.2023, 'learning_rate': 6.359233449477351e-07, 'epoch': 258.5}

 41%|████      | 23420/57600 [4:06:02<5:44:35,  1.65it/s]
 41%|████      | 23421/57600 [4:06:03<5:48:12,  1.64it/s]
 41%|████      | 23422/57600 [4:06:04<5:54:32,  1.61it/s]
 41%|████      | 23423/57600 [4:06:04<5:54:10,  1.61it/s]
 41%|████      | 23424/57600 [4:06:05<5:46:03,  1.65it/s]
 41%|████      | 23425/57600 [4:06:05<5:39:18,  1.68it/s]
 41%|████      | 23426/57600 [4:06:06<5:36:51,  1.69it/s]
 41%|████      | 23427/57600 [4:06:07<5:50:21,  1.63it/s]
 41%|████      | 23428/57600 [4:06:07<5:44:46,  1.65it/s]
 41%|████      | 23429/57600 [4:06:08<5:41:15,  1.67it/s]
 41%|████      | 23430/57600 [4:06:08<5:50:35,  1.62it/s]
 41%|████      | 23431/57600 [4:06:09<5:41:56,  1.67it/s]
 41%|████      | 23432/57600 [4:06:10<5:41:26,  1.67it/s]
 41%|████      | 23433/57600 [4:06:10<5:35:29,  1.70it/s]
 41%|████      | 23434/57600 [4:06:11<5:42:27,  1.66it/s]
 41%|████      | 23435/57600 [4:06:11<5:48:49,  1.63it/s]
 41%|████      | 23436/57600 [4:06:12<5:47:56,  1.64it/s]
 41%|████      | 23437/57600 [4:06:13<5:51:22,  1.62it/s]
 41%|████      | 23438/57600 [4:06:13<6:11:41,  1.53it/s]
 41%|████      | 23439/57600 [4:06:14<6:05:26,  1.56it/s]
 41%|████      | 23440/57600 [4:06:15<6:14:19,  1.52it/s]
                                                         
{'loss': 1.2195, 'learning_rate': 6.35609756097561e-07, 'epoch': 258.72}

 41%|████      | 23440/57600 [4:06:15<6:14:19,  1.52it/s]
 41%|████      | 23441/57600 [4:06:15<6:08:17,  1.55it/s]
 41%|████      | 23442/57600 [4:06:16<6:17:52,  1.51it/s]
 41%|████      | 23443/57600 [4:06:17<6:07:11,  1.55it/s]
 41%|████      | 23444/57600 [4:06:17<6:09:27,  1.54it/s]
 41%|████      | 23445/57600 [4:06:18<5:57:05,  1.59it/s]
 41%|████      | 23446/57600 [4:06:19<6:00:14,  1.58it/s]
 41%|████      | 23447/57600 [4:06:19<6:04:01,  1.56it/s]
 41%|████      | 23448/57600 [4:06:20<5:51:52,  1.62it/s]
 41%|████      | 23449/57600 [4:06:20<5:46:14,  1.64it/s]
 41%|████      | 23450/57600 [4:06:21<5:41:26,  1.67it/s]
 41%|████      | 23451/57600 [4:06:22<5:41:21,  1.67it/s]
 41%|████      | 23452/57600 [4:06:22<5:31:20,  1.72it/s]
 41%|████      | 23453/57600 [4:06:23<5:32:26,  1.71it/s]
 41%|████      | 23454/57600 [4:06:23<5:34:16,  1.70it/s]
 41%|████      | 23455/57600 [4:06:24<5:43:56,  1.65it/s]
 41%|████      | 23456/57600 [4:06:25<5:51:01,  1.62it/s]
 41%|████      | 23457/57600 [4:06:25<6:02:36,  1.57it/s]
 41%|████      | 23458/57600 [4:06:26<5:54:12,  1.61it/s]
 41%|████      | 23459/57600 [4:06:26<6:06:07,  1.55it/s]
 41%|████      | 23460/57600 [4:06:27<6:12:54,  1.53it/s]
                                                         
{'loss': 1.2402, 'learning_rate': 6.352961672473866e-07, 'epoch': 258.94}

 41%|████      | 23460/57600 [4:06:27<6:12:54,  1.53it/s]
 41%|████      | 23461/57600 [4:06:28<6:04:06,  1.56it/s]
 41%|████      | 23462/57600 [4:06:28<5:54:32,  1.60it/s]
 41%|████      | 23463/57600 [4:06:29<5:51:17,  1.62it/s]
 41%|████      | 23464/57600 [4:06:30<5:59:17,  1.58it/s]
 41%|████      | 23465/57600 [4:06:30<5:53:45,  1.61it/s]
 41%|████      | 23466/57600 [4:06:31<6:24:23,  1.48it/s]
 41%|████      | 23467/57600 [4:06:32<6:13:03,  1.52it/s]
 41%|████      | 23468/57600 [4:06:32<6:10:47,  1.53it/s]
 41%|████      | 23469/57600 [4:06:33<6:01:36,  1.57it/s]
 41%|████      | 23470/57600 [4:06:33<5:58:55,  1.58it/s]
 41%|████      | 23471/57600 [4:06:34<5:54:13,  1.61it/s]
 41%|████      | 23472/57600 [4:06:35<5:53:00,  1.61it/s]
 41%|████      | 23473/57600 [4:06:35<5:48:17,  1.63it/s]
 41%|████      | 23474/57600 [4:06:36<5:48:39,  1.63it/s]
 41%|████      | 23475/57600 [4:06:37<5:56:38,  1.59it/s]
 41%|████      | 23476/57600 [4:06:37<5:56:49,  1.59it/s]
 41%|████      | 23477/57600 [4:06:38<5:58:30,  1.59it/s]
 41%|████      | 23478/57600 [4:06:38<6:00:34,  1.58it/s]
 41%|████      | 23479/57600 [4:06:39<6:16:00,  1.51it/s]
 41%|████      | 23480/57600 [4:06:40<6:05:09,  1.56it/s]
                                                         
{'loss': 1.2099, 'learning_rate': 6.349825783972125e-07, 'epoch': 259.16}

 41%|████      | 23480/57600 [4:06:40<6:05:09,  1.56it/s]
 41%|████      | 23481/57600 [4:06:40<5:55:40,  1.60it/s]
 41%|████      | 23482/57600 [4:06:41<5:55:45,  1.60it/s]
 41%|████      | 23483/57600 [4:06:42<6:05:53,  1.55it/s]
 41%|████      | 23484/57600 [4:06:42<5:51:44,  1.62it/s]
 41%|████      | 23485/57600 [4:06:43<5:43:22,  1.66it/s]
 41%|████      | 23486/57600 [4:06:43<5:34:13,  1.70it/s]
 41%|████      | 23487/57600 [4:06:44<6:01:15,  1.57it/s]
 41%|████      | 23488/57600 [4:06:45<5:58:44,  1.58it/s]
 41%|████      | 23489/57600 [4:06:45<6:02:57,  1.57it/s]
 41%|████      | 23490/57600 [4:06:46<6:10:43,  1.53it/s]
 41%|████      | 23491/57600 [4:06:47<6:02:03,  1.57it/s]
 41%|████      | 23492/57600 [4:06:47<5:55:31,  1.60it/s]
 41%|████      | 23493/57600 [4:06:48<6:11:32,  1.53it/s]
 41%|████      | 23494/57600 [4:06:49<6:01:40,  1.57it/s]
 41%|████      | 23495/57600 [4:06:49<5:52:13,  1.61it/s]
 41%|████      | 23496/57600 [4:06:50<5:45:59,  1.64it/s]
 41%|████      | 23497/57600 [4:06:50<5:45:03,  1.65it/s]
 41%|████      | 23498/57600 [4:06:51<5:40:23,  1.67it/s]
 41%|████      | 23499/57600 [4:06:52<5:40:05,  1.67it/s]
 41%|████      | 23500/57600 [4:06:52<6:01:57,  1.57it/s]
                                                         
{'loss': 1.2101, 'learning_rate': 6.346689895470383e-07, 'epoch': 259.38}

 41%|████      | 23500/57600 [4:06:52<6:01:57,  1.57it/s]
 41%|████      | 23501/57600 [4:06:53<5:47:13,  1.64it/s]
 41%|████      | 23502/57600 [4:06:54<5:57:50,  1.59it/s]
 41%|████      | 23503/57600 [4:06:54<6:00:11,  1.58it/s]
 41%|████      | 23504/57600 [4:06:55<6:00:49,  1.57it/s]
 41%|████      | 23505/57600 [4:06:55<6:02:10,  1.57it/s]
 41%|████      | 23506/57600 [4:06:56<6:08:16,  1.54it/s]
 41%|████      | 23507/57600 [4:06:57<6:05:17,  1.56it/s]
 41%|████      | 23508/57600 [4:06:57<6:01:09,  1.57it/s]
 41%|████      | 23509/57600 [4:06:58<5:58:58,  1.58it/s]
 41%|████      | 23510/57600 [4:06:59<5:46:25,  1.64it/s]
 41%|████      | 23511/57600 [4:06:59<5:49:48,  1.62it/s]
 41%|████      | 23512/57600 [4:07:00<5:44:41,  1.65it/s]
 41%|████      | 23513/57600 [4:07:00<5:39:56,  1.67it/s]
 41%|████      | 23514/57600 [4:07:01<5:34:59,  1.70it/s]
 41%|████      | 23515/57600 [4:07:01<5:31:32,  1.71it/s]
 41%|████      | 23516/57600 [4:07:02<5:30:33,  1.72it/s]
 41%|████      | 23517/57600 [4:07:03<5:44:49,  1.65it/s]
 41%|████      | 23518/57600 [4:07:03<5:50:54,  1.62it/s]
 41%|████      | 23519/57600 [4:07:04<5:44:37,  1.65it/s]
 41%|████      | 23520/57600 [4:07:05<5:50:50,  1.62it/s]
                                                         
{'loss': 1.2063, 'learning_rate': 6.343554006968641e-07, 'epoch': 259.6}

 41%|████      | 23520/57600 [4:07:05<5:50:50,  1.62it/s]
 41%|████      | 23521/57600 [4:07:05<5:54:01,  1.60it/s]
 41%|████      | 23522/57600 [4:07:06<5:57:35,  1.59it/s]
 41%|████      | 23523/57600 [4:07:06<5:52:11,  1.61it/s]
 41%|████      | 23524/57600 [4:07:07<5:38:38,  1.68it/s]
 41%|████      | 23525/57600 [4:07:08<5:32:41,  1.71it/s]
 41%|████      | 23526/57600 [4:07:08<5:44:34,  1.65it/s]
 41%|████      | 23527/57600 [4:07:09<5:34:23,  1.70it/s]
 41%|████      | 23528/57600 [4:07:09<5:36:49,  1.69it/s]
 41%|████      | 23529/57600 [4:07:10<5:39:38,  1.67it/s]
 41%|████      | 23530/57600 [4:07:11<5:30:05,  1.72it/s]
 41%|████      | 23531/57600 [4:07:11<5:42:57,  1.66it/s]
 41%|████      | 23532/57600 [4:07:12<5:37:37,  1.68it/s]
 41%|████      | 23533/57600 [4:07:12<5:35:07,  1.69it/s]
 41%|████      | 23534/57600 [4:07:13<5:42:55,  1.66it/s]
 41%|████      | 23535/57600 [4:07:14<5:31:56,  1.71it/s]
 41%|████      | 23536/57600 [4:07:14<5:45:55,  1.64it/s]
 41%|████      | 23537/57600 [4:07:15<5:47:09,  1.64it/s]
 41%|████      | 23538/57600 [4:07:15<5:42:20,  1.66it/s]
 41%|████      | 23539/57600 [4:07:16<5:43:15,  1.65it/s]
 41%|████      | 23540/57600 [4:07:17<5:45:05,  1.64it/s]
                                                         
{'loss': 1.2622, 'learning_rate': 6.340418118466898e-07, 'epoch': 259.82}

 41%|████      | 23540/57600 [4:07:17<5:45:05,  1.64it/s]
 41%|████      | 23541/57600 [4:07:17<5:42:44,  1.66it/s]
 41%|████      | 23542/57600 [4:07:18<5:39:25,  1.67it/s]
 41%|████      | 23543/57600 [4:07:18<5:49:05,  1.63it/s]
 41%|████      | 23544/57600 [4:07:19<5:48:56,  1.63it/s]
 41%|████      | 23545/57600 [4:07:20<5:51:11,  1.62it/s]
 41%|████      | 23546/57600 [4:07:20<5:56:01,  1.59it/s]
 41%|████      | 23547/57600 [4:07:21<6:04:11,  1.56it/s]
 41%|████      | 23548/57600 [4:07:22<5:59:23,  1.58it/s]
 41%|████      | 23549/57600 [4:07:22<5:52:28,  1.61it/s]
 41%|████      | 23550/57600 [4:07:23<5:43:45,  1.65it/s]
 41%|████      | 23551/57600 [4:07:23<5:40:59,  1.66it/s]
 41%|████      | 23552/57600 [4:07:24<5:52:04,  1.61it/s]
 41%|████      | 23553/57600 [4:07:25<5:49:35,  1.62it/s]
 41%|████      | 23554/57600 [4:07:25<5:37:35,  1.68it/s]
 41%|████      | 23555/57600 [4:07:26<5:42:49,  1.66it/s]
 41%|████      | 23556/57600 [4:07:26<5:46:37,  1.64it/s]
 41%|████      | 23557/57600 [4:07:27<5:53:24,  1.61it/s]
 41%|████      | 23558/57600 [4:07:28<5:44:17,  1.65it/s]
 41%|████      | 23559/57600 [4:07:28<5:39:11,  1.67it/s]
 41%|████      | 23560/57600 [4:07:29<5:45:30,  1.64it/s]
                                                         
{'loss': 1.2606, 'learning_rate': 6.337282229965156e-07, 'epoch': 260.04}

 41%|████      | 23560/57600 [4:07:29<5:45:30,  1.64it/s]
 41%|████      | 23561/57600 [4:07:30<5:54:20,  1.60it/s]
 41%|████      | 23562/57600 [4:07:30<5:57:25,  1.59it/s]
 41%|████      | 23563/57600 [4:07:31<5:54:21,  1.60it/s]
 41%|████      | 23564/57600 [4:07:31<5:46:01,  1.64it/s]
 41%|████      | 23565/57600 [4:07:32<5:39:16,  1.67it/s]
 41%|████      | 23566/57600 [4:07:33<5:55:02,  1.60it/s]
 41%|████      | 23567/57600 [4:07:33<5:45:10,  1.64it/s]
 41%|████      | 23568/57600 [4:07:34<5:58:56,  1.58it/s]
 41%|████      | 23569/57600 [4:07:34<5:53:12,  1.61it/s]
 41%|████      | 23570/57600 [4:07:35<5:57:23,  1.59it/s]
 41%|████      | 23571/57600 [4:07:36<5:52:02,  1.61it/s]
 41%|████      | 23572/57600 [4:07:36<5:59:45,  1.58it/s]
 41%|████      | 23573/57600 [4:07:37<6:00:53,  1.57it/s]
 41%|████      | 23574/57600 [4:07:38<5:51:54,  1.61it/s]
 41%|████      | 23575/57600 [4:07:38<5:47:44,  1.63it/s]
 41%|████      | 23576/57600 [4:07:39<5:41:47,  1.66it/s]
 41%|████      | 23577/57600 [4:07:39<5:42:50,  1.65it/s]
 41%|████      | 23578/57600 [4:07:40<5:43:18,  1.65it/s]
 41%|████      | 23579/57600 [4:07:41<5:37:34,  1.68it/s]
 41%|████      | 23580/57600 [4:07:41<5:34:17,  1.70it/s]
                                                         
{'loss': 1.2232, 'learning_rate': 6.334146341463415e-07, 'epoch': 260.26}

 41%|████      | 23580/57600 [4:07:41<5:34:17,  1.70it/s]
 41%|████      | 23581/57600 [4:07:42<5:34:59,  1.69it/s]
 41%|████      | 23582/57600 [4:07:42<5:33:48,  1.70it/s]
 41%|████      | 23583/57600 [4:07:43<5:28:12,  1.73it/s]
 41%|████      | 23584/57600 [4:07:43<5:33:56,  1.70it/s]
 41%|████      | 23585/57600 [4:07:44<5:40:34,  1.66it/s]
 41%|████      | 23586/57600 [4:07:45<5:58:56,  1.58it/s]
 41%|████      | 23587/57600 [4:07:45<5:57:44,  1.58it/s]
 41%|████      | 23588/57600 [4:07:46<6:07:17,  1.54it/s]
 41%|████      | 23589/57600 [4:07:47<5:56:48,  1.59it/s]
 41%|████      | 23590/57600 [4:07:47<5:50:15,  1.62it/s]
 41%|████      | 23591/57600 [4:07:48<5:49:25,  1.62it/s]
 41%|████      | 23592/57600 [4:07:49<5:43:11,  1.65it/s]
 41%|████      | 23593/57600 [4:07:49<5:42:53,  1.65it/s]
 41%|████      | 23594/57600 [4:07:50<5:52:29,  1.61it/s]
 41%|████      | 23595/57600 [4:07:50<6:03:09,  1.56it/s]
 41%|████      | 23596/57600 [4:07:51<6:01:49,  1.57it/s]
 41%|████      | 23597/57600 [4:07:52<5:51:42,  1.61it/s]
 41%|████      | 23598/57600 [4:07:52<5:41:01,  1.66it/s]
 41%|████      | 23599/57600 [4:07:53<5:42:04,  1.66it/s]
 41%|████      | 23600/57600 [4:07:53<5:41:22,  1.66it/s]
                                                         
{'loss': 1.247, 'learning_rate': 6.331010452961672e-07, 'epoch': 260.49}

 41%|████      | 23600/57600 [4:07:53<5:41:22,  1.66it/s]
 41%|████      | 23601/57600 [4:07:54<6:05:06,  1.55it/s]
 41%|████      | 23602/57600 [4:07:55<5:53:15,  1.60it/s]
 41%|████      | 23603/57600 [4:07:55<6:06:59,  1.54it/s]
 41%|████      | 23604/57600 [4:07:56<6:08:28,  1.54it/s]
 41%|████      | 23605/57600 [4:07:57<6:18:48,  1.50it/s]
 41%|████      | 23606/57600 [4:07:57<6:11:00,  1.53it/s]
 41%|████      | 23607/57600 [4:07:58<6:03:11,  1.56it/s]
 41%|████      | 23608/57600 [4:07:59<5:46:05,  1.64it/s]
 41%|████      | 23609/57600 [4:07:59<5:48:16,  1.63it/s]
 41%|████      | 23610/57600 [4:08:00<5:36:07,  1.69it/s]
 41%|████      | 23611/57600 [4:08:00<5:34:29,  1.69it/s]
 41%|████      | 23612/57600 [4:08:01<5:43:31,  1.65it/s]
 41%|████      | 23613/57600 [4:08:02<5:40:11,  1.67it/s]
 41%|████      | 23614/57600 [4:08:02<5:45:40,  1.64it/s]
 41%|████      | 23615/57600 [4:08:03<5:39:08,  1.67it/s]
 41%|████      | 23616/57600 [4:08:03<5:34:15,  1.69it/s]
 41%|████      | 23617/57600 [4:08:04<5:32:04,  1.71it/s]
 41%|████      | 23618/57600 [4:08:05<5:32:40,  1.70it/s]
 41%|████      | 23619/57600 [4:08:05<5:30:47,  1.71it/s]
 41%|████      | 23620/57600 [4:08:06<5:48:49,  1.62it/s]
                                                         
{'loss': 1.1941, 'learning_rate': 6.327874564459929e-07, 'epoch': 260.71}

 41%|████      | 23620/57600 [4:08:06<5:48:49,  1.62it/s]
 41%|████      | 23621/57600 [4:08:06<6:00:49,  1.57it/s]
 41%|████      | 23622/57600 [4:08:07<5:47:09,  1.63it/s]
 41%|████      | 23623/57600 [4:08:08<5:41:39,  1.66it/s]
 41%|████      | 23624/57600 [4:08:08<5:44:32,  1.64it/s]
 41%|████      | 23625/57600 [4:08:09<5:57:14,  1.59it/s]
 41%|████      | 23626/57600 [4:08:10<5:55:39,  1.59it/s]
 41%|████      | 23627/57600 [4:08:10<5:57:36,  1.58it/s]
 41%|████      | 23628/57600 [4:08:11<5:59:24,  1.58it/s]
 41%|████      | 23629/57600 [4:08:11<5:54:41,  1.60it/s]
 41%|████      | 23630/57600 [4:08:12<5:59:12,  1.58it/s]
 41%|████      | 23631/57600 [4:08:13<5:47:06,  1.63it/s]
 41%|████      | 23632/57600 [4:08:13<5:58:07,  1.58it/s]
 41%|████      | 23633/57600 [4:08:14<6:16:14,  1.50it/s]
 41%|████      | 23634/57600 [4:08:15<6:12:54,  1.52it/s]
 41%|████      | 23635/57600 [4:08:15<6:16:13,  1.50it/s]
 41%|████      | 23636/57600 [4:08:16<6:24:04,  1.47it/s]
 41%|████      | 23637/57600 [4:08:17<6:11:23,  1.52it/s]
 41%|████      | 23638/57600 [4:08:17<6:03:23,  1.56it/s]
 41%|████      | 23639/57600 [4:08:18<6:16:28,  1.50it/s]
 41%|████      | 23640/57600 [4:08:19<6:04:28,  1.55it/s]
                                                         
{'loss': 1.1894, 'learning_rate': 6.324738675958188e-07, 'epoch': 260.93}

 41%|████      | 23640/57600 [4:08:19<6:04:28,  1.55it/s]
 41%|████      | 23641/57600 [4:08:19<5:47:12,  1.63it/s]
 41%|████      | 23642/57600 [4:08:20<5:45:26,  1.64it/s]
 41%|████      | 23643/57600 [4:08:20<5:48:17,  1.62it/s]
 41%|████      | 23644/57600 [4:08:21<5:39:46,  1.67it/s]
 41%|████      | 23645/57600 [4:08:22<5:50:29,  1.61it/s]
 41%|████      | 23646/57600 [4:08:22<5:55:33,  1.59it/s]
 41%|████      | 23647/57600 [4:08:23<6:00:54,  1.57it/s]
 41%|████      | 23648/57600 [4:08:23<5:43:39,  1.65it/s]
 41%|████      | 23649/57600 [4:08:24<5:53:11,  1.60it/s]
 41%|████      | 23650/57600 [4:08:25<5:43:36,  1.65it/s]
 41%|████      | 23651/57600 [4:08:25<5:52:49,  1.60it/s]
 41%|████      | 23652/57600 [4:08:26<5:46:44,  1.63it/s]
 41%|████      | 23653/57600 [4:08:27<5:47:26,  1.63it/s]
 41%|████      | 23654/57600 [4:08:27<5:38:52,  1.67it/s]
 41%|████      | 23655/57600 [4:08:28<5:40:36,  1.66it/s]
 41%|████      | 23656/57600 [4:08:28<5:44:25,  1.64it/s]
 41%|████      | 23657/57600 [4:08:29<5:42:14,  1.65it/s]
 41%|████      | 23658/57600 [4:08:30<5:54:44,  1.59it/s]
 41%|████      | 23659/57600 [4:08:30<5:42:06,  1.65it/s]
 41%|████      | 23660/57600 [4:08:31<5:41:31,  1.66it/s]
                                                         
{'loss': 1.2888, 'learning_rate': 6.321602787456447e-07, 'epoch': 261.15}

 41%|████      | 23660/57600 [4:08:31<5:41:31,  1.66it/s]
 41%|████      | 23661/57600 [4:08:31<5:41:24,  1.66it/s]
 41%|████      | 23662/57600 [4:08:32<5:36:48,  1.68it/s]
 41%|████      | 23663/57600 [4:08:33<5:49:39,  1.62it/s]
 41%|████      | 23664/57600 [4:08:33<5:53:23,  1.60it/s]
 41%|████      | 23665/57600 [4:08:34<6:00:37,  1.57it/s]
 41%|████      | 23666/57600 [4:08:35<5:55:33,  1.59it/s]
 41%|████      | 23667/57600 [4:08:35<5:45:07,  1.64it/s]
 41%|████      | 23668/57600 [4:08:36<5:44:15,  1.64it/s]
 41%|████      | 23669/57600 [4:08:36<5:48:27,  1.62it/s]
 41%|████      | 23670/57600 [4:08:37<5:43:06,  1.65it/s]
 41%|████      | 23671/57600 [4:08:38<5:48:27,  1.62it/s]
 41%|████      | 23672/57600 [4:08:38<5:50:18,  1.61it/s]
 41%|████      | 23673/57600 [4:08:39<5:53:19,  1.60it/s]
 41%|████      | 23674/57600 [4:08:40<5:59:29,  1.57it/s]
 41%|████      | 23675/57600 [4:08:40<6:02:34,  1.56it/s]
 41%|████      | 23676/57600 [4:08:41<5:50:34,  1.61it/s]
 41%|████      | 23677/57600 [4:08:41<5:50:09,  1.61it/s]
 41%|████      | 23678/57600 [4:08:42<6:00:54,  1.57it/s]
 41%|████      | 23679/57600 [4:08:43<5:59:26,  1.57it/s]
 41%|████      | 23680/57600 [4:08:43<5:46:53,  1.63it/s]
                                                         
{'loss': 1.1849, 'learning_rate': 6.318466898954703e-07, 'epoch': 261.37}

 41%|████      | 23680/57600 [4:08:43<5:46:53,  1.63it/s]
 41%|████      | 23681/57600 [4:08:44<5:41:38,  1.65it/s]
 41%|████      | 23682/57600 [4:08:44<5:49:13,  1.62it/s]
 41%|████      | 23683/57600 [4:08:45<5:51:12,  1.61it/s]
 41%|████      | 23684/57600 [4:08:46<5:36:31,  1.68it/s]
 41%|████      | 23685/57600 [4:08:46<5:43:29,  1.65it/s]
 41%|████      | 23686/57600 [4:08:47<5:36:12,  1.68it/s]
 41%|████      | 23687/57600 [4:08:47<5:39:45,  1.66it/s]
 41%|████      | 23688/57600 [4:08:48<5:38:00,  1.67it/s]
 41%|████      | 23689/57600 [4:08:49<5:39:16,  1.67it/s]
 41%|████      | 23690/57600 [4:08:49<5:46:55,  1.63it/s]
 41%|████      | 23691/57600 [4:08:50<5:42:40,  1.65it/s]
 41%|████      | 23692/57600 [4:08:51<6:02:45,  1.56it/s]
 41%|████      | 23693/57600 [4:08:51<6:09:21,  1.53it/s]
 41%|████      | 23694/57600 [4:08:52<6:17:05,  1.50it/s]
 41%|████      | 23695/57600 [4:08:53<6:05:24,  1.55it/s]
 41%|████      | 23696/57600 [4:08:53<6:12:00,  1.52it/s]
 41%|████      | 23697/57600 [4:08:54<6:08:24,  1.53it/s]
 41%|████      | 23698/57600 [4:08:55<6:00:26,  1.57it/s]
 41%|████      | 23699/57600 [4:08:55<5:50:33,  1.61it/s]
 41%|████      | 23700/57600 [4:08:56<5:54:26,  1.59it/s]
                                                         
{'loss': 1.1739, 'learning_rate': 6.31533101045296e-07, 'epoch': 261.59}

 41%|████      | 23700/57600 [4:08:56<5:54:26,  1.59it/s]
 41%|████      | 23701/57600 [4:08:56<5:55:48,  1.59it/s]
 41%|████      | 23702/57600 [4:08:57<5:52:17,  1.60it/s]
 41%|████      | 23703/57600 [4:08:58<5:50:56,  1.61it/s]
 41%|████      | 23704/57600 [4:08:58<5:41:33,  1.65it/s]
 41%|████      | 23705/57600 [4:08:59<5:41:59,  1.65it/s]
 41%|████      | 23706/57600 [4:08:59<5:53:00,  1.60it/s]
 41%|████      | 23707/57600 [4:09:00<5:58:46,  1.57it/s]
 41%|████      | 23708/57600 [4:09:01<5:43:06,  1.65it/s]
 41%|████      | 23709/57600 [4:09:01<5:45:15,  1.64it/s]
 41%|████      | 23710/57600 [4:09:02<5:54:07,  1.59it/s]
 41%|████      | 23711/57600 [4:09:03<5:55:03,  1.59it/s]
 41%|████      | 23712/57600 [4:09:03<5:47:04,  1.63it/s]
 41%|████      | 23713/57600 [4:09:04<5:41:08,  1.66it/s]
 41%|████      | 23714/57600 [4:09:04<6:01:27,  1.56it/s]
 41%|████      | 23715/57600 [4:09:05<5:51:08,  1.61it/s]
 41%|████      | 23716/57600 [4:09:06<6:03:22,  1.55it/s]
 41%|████      | 23717/57600 [4:09:06<6:05:27,  1.55it/s]
 41%|████      | 23718/57600 [4:09:07<5:50:45,  1.61it/s]
 41%|████      | 23719/57600 [4:09:08<5:44:57,  1.64it/s]
 41%|████      | 23720/57600 [4:09:08<5:49:57,  1.61it/s]
                                                         
{'loss': 1.2167, 'learning_rate': 6.31219512195122e-07, 'epoch': 261.81}

 41%|████      | 23720/57600 [4:09:08<5:49:57,  1.61it/s]
 41%|████      | 23721/57600 [4:09:09<5:50:54,  1.61it/s]
 41%|████      | 23722/57600 [4:09:09<5:47:13,  1.63it/s]
 41%|████      | 23723/57600 [4:09:10<5:50:09,  1.61it/s]
 41%|████      | 23724/57600 [4:09:11<5:43:30,  1.64it/s]
 41%|████      | 23725/57600 [4:09:11<5:44:54,  1.64it/s]
 41%|████      | 23726/57600 [4:09:12<5:42:20,  1.65it/s]
 41%|████      | 23727/57600 [4:09:12<5:43:09,  1.65it/s]
 41%|████      | 23728/57600 [4:09:13<5:40:41,  1.66it/s]
 41%|████      | 23729/57600 [4:09:14<5:44:18,  1.64it/s]
 41%|████      | 23730/57600 [4:09:14<5:53:13,  1.60it/s]
 41%|████      | 23731/57600 [4:09:15<5:41:22,  1.65it/s]
 41%|████      | 23732/57600 [4:09:16<6:04:51,  1.55it/s]
 41%|████      | 23733/57600 [4:09:16<5:59:20,  1.57it/s]
 41%|████      | 23734/57600 [4:09:17<5:56:45,  1.58it/s]
 41%|████      | 23735/57600 [4:09:17<5:54:00,  1.59it/s]
 41%|████      | 23736/57600 [4:09:18<5:48:45,  1.62it/s]
 41%|████      | 23737/57600 [4:09:19<5:39:39,  1.66it/s]
 41%|████      | 23738/57600 [4:09:19<6:05:24,  1.54it/s]
 41%|████      | 23739/57600 [4:09:20<5:59:39,  1.57it/s]
 41%|████      | 23740/57600 [4:09:21<5:56:28,  1.58it/s]
                                                         
{'loss': 1.2133, 'learning_rate': 6.309059233449478e-07, 'epoch': 262.03}

 41%|████      | 23740/57600 [4:09:21<5:56:28,  1.58it/s]
 41%|████      | 23741/57600 [4:09:21<6:04:14,  1.55it/s]
 41%|████      | 23742/57600 [4:09:22<5:57:23,  1.58it/s]
 41%|████      | 23743/57600 [4:09:22<5:55:16,  1.59it/s]
 41%|████      | 23744/57600 [4:09:23<5:57:26,  1.58it/s]
 41%|████      | 23745/57600 [4:09:24<5:53:17,  1.60it/s]
 41%|████      | 23746/57600 [4:09:24<5:57:27,  1.58it/s]
 41%|████      | 23747/57600 [4:09:25<5:49:36,  1.61it/s]
 41%|████      | 23748/57600 [4:09:26<5:42:19,  1.65it/s]
 41%|████      | 23749/57600 [4:09:26<5:40:00,  1.66it/s]
 41%|████      | 23750/57600 [4:09:27<5:42:37,  1.65it/s]
 41%|████      | 23751/57600 [4:09:27<5:38:11,  1.67it/s]
 41%|████      | 23752/57600 [4:09:28<5:40:58,  1.65it/s]
 41%|████      | 23753/57600 [4:09:29<5:39:14,  1.66it/s]
 41%|████      | 23754/57600 [4:09:29<5:50:12,  1.61it/s]
 41%|████      | 23755/57600 [4:09:30<5:41:58,  1.65it/s]
 41%|████      | 23756/57600 [4:09:30<5:44:04,  1.64it/s]
 41%|████      | 23757/57600 [4:09:31<5:47:43,  1.62it/s]
 41%|████      | 23758/57600 [4:09:32<5:40:53,  1.65it/s]
 41%|████      | 23759/57600 [4:09:32<5:48:37,  1.62it/s]
 41%|████▏     | 23760/57600 [4:09:33<5:43:02,  1.64it/s]
                                                         
{'loss': 1.2285, 'learning_rate': 6.305923344947734e-07, 'epoch': 262.25}

 41%|████▏     | 23760/57600 [4:09:33<5:43:02,  1.64it/s]
 41%|████▏     | 23761/57600 [4:09:33<5:32:43,  1.70it/s]
 41%|████▏     | 23762/57600 [4:09:34<5:29:25,  1.71it/s]
 41%|████▏     | 23763/57600 [4:09:35<5:25:39,  1.73it/s]
 41%|████▏     | 23764/57600 [4:09:35<5:33:52,  1.69it/s]
 41%|████▏     | 23765/57600 [4:09:36<5:48:24,  1.62it/s]
 41%|████▏     | 23766/57600 [4:09:37<5:55:00,  1.59it/s]
 41%|████▏     | 23767/57600 [4:09:37<5:54:02,  1.59it/s]
 41%|████▏     | 23768/57600 [4:09:38<5:51:20,  1.60it/s]
 41%|████▏     | 23769/57600 [4:09:38<5:40:21,  1.66it/s]
 41%|████▏     | 23770/57600 [4:09:39<5:37:41,  1.67it/s]
 41%|████▏     | 23771/57600 [4:09:40<5:44:44,  1.64it/s]
 41%|████▏     | 23772/57600 [4:09:40<5:39:37,  1.66it/s]
 41%|████▏     | 23773/57600 [4:09:41<5:45:50,  1.63it/s]
 41%|████▏     | 23774/57600 [4:09:41<5:48:47,  1.62it/s]
 41%|████▏     | 23775/57600 [4:09:42<5:47:12,  1.62it/s]
 41%|████▏     | 23776/57600 [4:09:43<5:46:50,  1.63it/s]
 41%|████▏     | 23777/57600 [4:09:43<5:56:44,  1.58it/s]
 41%|████▏     | 23778/57600 [4:09:44<5:54:42,  1.59it/s]
 41%|████▏     | 23779/57600 [4:09:44<5:42:42,  1.64it/s]
 41%|████▏     | 23780/57600 [4:09:45<5:38:12,  1.67it/s]
                                                         
{'loss': 1.2533, 'learning_rate': 6.302787456445993e-07, 'epoch': 262.47}

 41%|████▏     | 23780/57600 [4:09:45<5:38:12,  1.67it/s]
 41%|████▏     | 23781/57600 [4:09:46<5:32:45,  1.69it/s]
 41%|████▏     | 23782/57600 [4:09:46<5:59:58,  1.57it/s]
 41%|████▏     | 23783/57600 [4:09:47<5:55:38,  1.58it/s]
 41%|████▏     | 23784/57600 [4:09:48<5:51:52,  1.60it/s]
 41%|████▏     | 23785/57600 [4:09:48<5:48:09,  1.62it/s]
 41%|████▏     | 23786/57600 [4:09:49<5:57:04,  1.58it/s]
 41%|████▏     | 23787/57600 [4:09:50<6:03:03,  1.55it/s]
 41%|████▏     | 23788/57600 [4:09:50<5:58:45,  1.57it/s]
 41%|████▏     | 23789/57600 [4:09:51<6:00:37,  1.56it/s]
 41%|████▏     | 23790/57600 [4:09:51<6:03:07,  1.55it/s]
 41%|████▏     | 23791/57600 [4:09:52<6:05:07,  1.54it/s]
 41%|████▏     | 23792/57600 [4:09:53<6:06:53,  1.54it/s]
 41%|████▏     | 23793/57600 [4:09:53<6:06:36,  1.54it/s]
 41%|████▏     | 23794/57600 [4:09:54<6:00:05,  1.56it/s]
 41%|████▏     | 23795/57600 [4:09:55<6:06:44,  1.54it/s]
 41%|████▏     | 23796/57600 [4:09:55<5:51:25,  1.60it/s]
 41%|████▏     | 23797/57600 [4:09:56<6:00:52,  1.56it/s]
 41%|████▏     | 23798/57600 [4:09:57<6:05:42,  1.54it/s]
 41%|████▏     | 23799/57600 [4:09:57<5:56:22,  1.58it/s]
 41%|████▏     | 23800/57600 [4:09:58<5:53:04,  1.60it/s]
                                                         
{'loss': 1.1534, 'learning_rate': 6.29965156794425e-07, 'epoch': 262.69}

 41%|████▏     | 23800/57600 [4:09:58<5:53:04,  1.60it/s]
 41%|████▏     | 23801/57600 [4:09:58<5:52:49,  1.60it/s]
 41%|████▏     | 23802/57600 [4:09:59<5:40:57,  1.65it/s]
 41%|████▏     | 23803/57600 [4:10:00<5:57:20,  1.58it/s]
 41%|████▏     | 23804/57600 [4:10:00<5:57:31,  1.58it/s]
 41%|████▏     | 23805/57600 [4:10:01<5:43:43,  1.64it/s]
 41%|████▏     | 23806/57600 [4:10:01<5:40:43,  1.65it/s]
 41%|████▏     | 23807/57600 [4:10:02<5:37:53,  1.67it/s]
 41%|████▏     | 23808/57600 [4:10:03<5:33:45,  1.69it/s]
 41%|████▏     | 23809/57600 [4:10:03<5:39:18,  1.66it/s]
 41%|████▏     | 23810/57600 [4:10:04<5:36:56,  1.67it/s]
 41%|████▏     | 23811/57600 [4:10:04<5:36:17,  1.67it/s]
 41%|████▏     | 23812/57600 [4:10:05<5:34:03,  1.69it/s]
 41%|████▏     | 23813/57600 [4:10:06<5:47:39,  1.62it/s]
 41%|████▏     | 23814/57600 [4:10:06<5:50:43,  1.61it/s]
 41%|████▏     | 23815/57600 [4:10:07<5:45:17,  1.63it/s]
 41%|████▏     | 23816/57600 [4:10:08<5:53:29,  1.59it/s]
 41%|████▏     | 23817/57600 [4:10:08<6:00:24,  1.56it/s]
 41%|████▏     | 23818/57600 [4:10:09<6:03:51,  1.55it/s]
 41%|████▏     | 23819/57600 [4:10:10<6:07:07,  1.53it/s]
 41%|████▏     | 23820/57600 [4:10:10<5:53:47,  1.59it/s]
                                                         
{'loss': 1.2009, 'learning_rate': 6.296515679442508e-07, 'epoch': 262.91}

 41%|████▏     | 23820/57600 [4:10:10<5:53:47,  1.59it/s]
 41%|████▏     | 23821/57600 [4:10:11<5:50:18,  1.61it/s]
 41%|████▏     | 23822/57600 [4:10:11<5:42:54,  1.64it/s]
 41%|████▏     | 23823/57600 [4:10:12<5:39:21,  1.66it/s]
 41%|████▏     | 23824/57600 [4:10:13<5:33:31,  1.69it/s]
 41%|████▏     | 23825/57600 [4:10:13<5:43:09,  1.64it/s]
 41%|████▏     | 23826/57600 [4:10:14<5:44:27,  1.63it/s]
 41%|████▏     | 23827/57600 [4:10:14<5:42:41,  1.64it/s]
 41%|████▏     | 23828/57600 [4:10:15<6:03:02,  1.55it/s]
 41%|████▏     | 23829/57600 [4:10:16<6:05:40,  1.54it/s]
 41%|████▏     | 23830/57600 [4:10:16<6:02:25,  1.55it/s]
 41%|████▏     | 23831/57600 [4:10:17<5:46:21,  1.62it/s]
 41%|████▏     | 23832/57600 [4:10:18<5:52:15,  1.60it/s]
 41%|████▏     | 23833/57600 [4:10:18<5:55:05,  1.58it/s]
 41%|████▏     | 23834/57600 [4:10:19<5:58:57,  1.57it/s]
 41%|████▏     | 23835/57600 [4:10:19<5:52:19,  1.60it/s]
 41%|████▏     | 23836/57600 [4:10:20<5:42:49,  1.64it/s]
 41%|████▏     | 23837/57600 [4:10:21<5:55:18,  1.58it/s]
 41%|████▏     | 23838/57600 [4:10:21<5:46:13,  1.63it/s]
 41%|████▏     | 23839/57600 [4:10:22<5:54:25,  1.59it/s]
 41%|████▏     | 23840/57600 [4:10:23<5:51:38,  1.60it/s]
                                                         
{'loss': 1.1822, 'learning_rate': 6.293379790940765e-07, 'epoch': 263.13}

 41%|████▏     | 23840/57600 [4:10:23<5:51:38,  1.60it/s]
 41%|████▏     | 23841/57600 [4:10:23<5:53:36,  1.59it/s]
 41%|████▏     | 23842/57600 [4:10:24<5:51:27,  1.60it/s]
 41%|████▏     | 23843/57600 [4:10:24<5:52:37,  1.60it/s]
 41%|████▏     | 23844/57600 [4:10:25<6:06:14,  1.54it/s]
 41%|████▏     | 23845/57600 [4:10:26<5:55:31,  1.58it/s]
 41%|████▏     | 23846/57600 [4:10:26<5:41:15,  1.65it/s]
 41%|████▏     | 23847/57600 [4:10:27<5:40:23,  1.65it/s]
 41%|████▏     | 23848/57600 [4:10:27<5:34:05,  1.68it/s]
 41%|████▏     | 23849/57600 [4:10:28<5:35:44,  1.68it/s]
 41%|████▏     | 23850/57600 [4:10:29<5:28:34,  1.71it/s]
 41%|████▏     | 23851/57600 [4:10:29<5:26:45,  1.72it/s]
 41%|████▏     | 23852/57600 [4:10:30<5:22:27,  1.74it/s]
 41%|████▏     | 23853/57600 [4:10:30<5:40:49,  1.65it/s]
 41%|████▏     | 23854/57600 [4:10:31<5:45:06,  1.63it/s]
 41%|████▏     | 23855/57600 [4:10:32<5:42:20,  1.64it/s]
 41%|████▏     | 23856/57600 [4:10:32<5:45:03,  1.63it/s]
 41%|████▏     | 23857/57600 [4:10:33<5:38:40,  1.66it/s]
 41%|████▏     | 23858/57600 [4:10:34<5:44:33,  1.63it/s]
 41%|████▏     | 23859/57600 [4:10:34<5:51:38,  1.60it/s]
 41%|████▏     | 23860/57600 [4:10:35<5:49:46,  1.61it/s]
                                                         
{'loss': 1.2322, 'learning_rate': 6.290243902439025e-07, 'epoch': 263.36}

 41%|████▏     | 23860/57600 [4:10:35<5:49:46,  1.61it/s]
 41%|████▏     | 23861/57600 [4:10:35<5:41:23,  1.65it/s]
 41%|████▏     | 23862/57600 [4:10:36<5:46:46,  1.62it/s]
 41%|████▏     | 23863/57600 [4:10:37<5:41:18,  1.65it/s]
 41%|████▏     | 23864/57600 [4:10:37<5:34:07,  1.68it/s]
 41%|████▏     | 23865/57600 [4:10:38<5:31:12,  1.70it/s]
 41%|████▏     | 23866/57600 [4:10:38<5:43:47,  1.64it/s]
 41%|████▏     | 23867/57600 [4:10:39<5:43:54,  1.63it/s]
 41%|████▏     | 23868/57600 [4:10:40<5:47:11,  1.62it/s]
 41%|████▏     | 23869/57600 [4:10:40<6:04:49,  1.54it/s]
 41%|████▏     | 23870/57600 [4:10:41<6:02:07,  1.55it/s]
 41%|████▏     | 23871/57600 [4:10:42<5:57:45,  1.57it/s]
 41%|████▏     | 23872/57600 [4:10:42<6:05:16,  1.54it/s]
 41%|████▏     | 23873/57600 [4:10:43<6:15:13,  1.50it/s]
 41%|████▏     | 23874/57600 [4:10:44<6:07:14,  1.53it/s]
 41%|████▏     | 23875/57600 [4:10:44<6:00:42,  1.56it/s]
 41%|████▏     | 23876/57600 [4:10:45<5:50:59,  1.60it/s]
 41%|████▏     | 23877/57600 [4:10:45<5:44:09,  1.63it/s]
 41%|████▏     | 23878/57600 [4:10:46<5:57:46,  1.57it/s]
 41%|████▏     | 23879/57600 [4:10:47<5:54:36,  1.58it/s]
 41%|████▏     | 23880/57600 [4:10:47<5:54:11,  1.59it/s]
                                                         
{'loss': 1.2095, 'learning_rate': 6.287108013937282e-07, 'epoch': 263.58}

 41%|████▏     | 23880/57600 [4:10:47<5:54:11,  1.59it/s]
 41%|████▏     | 23881/57600 [4:10:48<5:53:00,  1.59it/s]
 41%|████▏     | 23882/57600 [4:10:49<5:49:42,  1.61it/s]
 41%|████▏     | 23883/57600 [4:10:49<5:42:09,  1.64it/s]
 41%|████▏     | 23884/57600 [4:10:50<5:35:10,  1.68it/s]
 41%|████▏     | 23885/57600 [4:10:50<5:46:27,  1.62it/s]
 41%|████▏     | 23886/57600 [4:10:51<5:43:39,  1.64it/s]
 41%|████▏     | 23887/57600 [4:10:52<5:51:49,  1.60it/s]
 41%|████▏     | 23888/57600 [4:10:52<5:39:19,  1.66it/s]
 41%|████▏     | 23889/57600 [4:10:53<5:31:10,  1.70it/s]
 41%|████▏     | 23890/57600 [4:10:53<5:39:53,  1.65it/s]
 41%|████▏     | 23891/57600 [4:10:54<5:42:07,  1.64it/s]
 41%|████▏     | 23892/57600 [4:10:55<5:39:13,  1.66it/s]
 41%|████▏     | 23893/57600 [4:10:55<5:41:08,  1.65it/s]
 41%|████▏     | 23894/57600 [4:10:56<5:39:34,  1.65it/s]
 41%|████▏     | 23895/57600 [4:10:56<5:38:09,  1.66it/s]
 41%|████▏     | 23896/57600 [4:10:57<5:32:29,  1.69it/s]
 41%|████▏     | 23897/57600 [4:10:58<5:28:11,  1.71it/s]
 41%|████▏     | 23898/57600 [4:10:58<5:38:32,  1.66it/s]
 41%|████▏     | 23899/57600 [4:10:59<5:49:50,  1.61it/s]
 41%|████▏     | 23900/57600 [4:11:00<5:53:50,  1.59it/s]
                                                         
{'loss': 1.2768, 'learning_rate': 6.283972125435539e-07, 'epoch': 263.8}

 41%|████▏     | 23900/57600 [4:11:00<5:53:50,  1.59it/s]
 41%|████▏     | 23901/57600 [4:11:00<6:11:19,  1.51it/s]
 41%|████▏     | 23902/57600 [4:11:01<6:01:01,  1.56it/s]
 41%|████▏     | 23903/57600 [4:11:02<6:02:19,  1.55it/s]
 42%|████▏     | 23904/57600 [4:11:02<6:04:20,  1.54it/s]
 42%|████▏     | 23905/57600 [4:11:03<6:09:25,  1.52it/s]
 42%|████▏     | 23906/57600 [4:11:03<6:02:53,  1.55it/s]
 42%|████▏     | 23907/57600 [4:11:04<6:01:58,  1.55it/s]
 42%|████▏     | 23908/57600 [4:11:05<5:47:39,  1.62it/s]
 42%|████▏     | 23909/57600 [4:11:05<5:46:06,  1.62it/s]
 42%|████▏     | 23910/57600 [4:11:06<5:54:26,  1.58it/s]
 42%|████▏     | 23911/57600 [4:11:07<5:45:13,  1.63it/s]
 42%|████▏     | 23912/57600 [4:11:07<5:40:58,  1.65it/s]
 42%|████▏     | 23913/57600 [4:11:08<5:39:02,  1.66it/s]
 42%|████▏     | 23914/57600 [4:11:08<5:37:42,  1.66it/s]
 42%|████▏     | 23915/57600 [4:11:09<5:42:45,  1.64it/s]
 42%|████▏     | 23916/57600 [4:11:10<5:43:53,  1.63it/s]
 42%|████▏     | 23917/57600 [4:11:10<5:44:39,  1.63it/s]
 42%|████▏     | 23918/57600 [4:11:11<5:55:43,  1.58it/s]
 42%|████▏     | 23919/57600 [4:11:12<6:20:01,  1.48it/s]
 42%|████▏     | 23920/57600 [4:11:12<6:25:21,  1.46it/s]
                                                         
{'loss': 1.1598, 'learning_rate': 6.280836236933798e-07, 'epoch': 264.02}

 42%|████▏     | 23920/57600 [4:11:12<6:25:21,  1.46it/s]
 42%|████▏     | 23921/57600 [4:11:13<6:17:55,  1.49it/s]
 42%|████▏     | 23922/57600 [4:11:14<6:28:09,  1.45it/s]
 42%|████▏     | 23923/57600 [4:11:14<6:19:11,  1.48it/s]
 42%|████▏     | 23924/57600 [4:11:15<6:02:56,  1.55it/s]
 42%|████▏     | 23925/57600 [4:11:16<5:53:49,  1.59it/s]
 42%|████▏     | 23926/57600 [4:11:16<5:55:23,  1.58it/s]
 42%|████▏     | 23927/57600 [4:11:17<6:00:38,  1.56it/s]
 42%|████▏     | 23928/57600 [4:11:17<5:49:27,  1.61it/s]
 42%|████▏     | 23929/57600 [4:11:18<5:42:25,  1.64it/s]
 42%|████▏     | 23930/57600 [4:11:19<5:34:23,  1.68it/s]
 42%|████▏     | 23931/57600 [4:11:19<5:39:03,  1.66it/s]
 42%|████▏     | 23932/57600 [4:11:20<5:47:54,  1.61it/s]
 42%|████▏     | 23933/57600 [4:11:20<5:45:04,  1.63it/s]
 42%|████▏     | 23934/57600 [4:11:21<5:37:31,  1.66it/s]
 42%|████▏     | 23935/57600 [4:11:22<5:42:26,  1.64it/s]
 42%|████▏     | 23936/57600 [4:11:22<5:56:36,  1.57it/s]
 42%|████▏     | 23937/57600 [4:11:23<5:50:43,  1.60it/s]
 42%|████▏     | 23938/57600 [4:11:24<5:48:12,  1.61it/s]
 42%|████▏     | 23939/57600 [4:11:24<5:43:36,  1.63it/s]
 42%|████▏     | 23940/57600 [4:11:25<5:34:55,  1.68it/s]
                                                         
{'loss': 1.2398, 'learning_rate': 6.277700348432056e-07, 'epoch': 264.24}

 42%|████▏     | 23940/57600 [4:11:25<5:34:55,  1.68it/s]
 42%|████▏     | 23941/57600 [4:11:25<5:36:20,  1.67it/s]
 42%|████▏     | 23942/57600 [4:11:26<5:38:05,  1.66it/s]
 42%|████▏     | 23943/57600 [4:11:27<5:40:38,  1.65it/s]
 42%|████▏     | 23944/57600 [4:11:27<5:44:35,  1.63it/s]
 42%|████▏     | 23945/57600 [4:11:28<5:36:03,  1.67it/s]
 42%|████▏     | 23946/57600 [4:11:28<5:41:07,  1.64it/s]
 42%|████▏     | 23947/57600 [4:11:29<5:42:20,  1.64it/s]
 42%|████▏     | 23948/57600 [4:11:30<5:35:36,  1.67it/s]
 42%|████▏     | 23949/57600 [4:11:30<5:37:04,  1.66it/s]
 42%|████▏     | 23950/57600 [4:11:31<5:38:58,  1.65it/s]
 42%|████▏     | 23951/57600 [4:11:31<5:41:00,  1.64it/s]
 42%|████▏     | 23952/57600 [4:11:32<5:49:54,  1.60it/s]
 42%|████▏     | 23953/57600 [4:11:33<5:48:58,  1.61it/s]
 42%|████▏     | 23954/57600 [4:11:33<5:46:05,  1.62it/s]
 42%|████▏     | 23955/57600 [4:11:34<5:36:43,  1.67it/s]
 42%|████▏     | 23956/57600 [4:11:34<5:46:30,  1.62it/s]
 42%|████▏     | 23957/57600 [4:11:35<5:58:32,  1.56it/s]
 42%|████▏     | 23958/57600 [4:11:36<5:54:48,  1.58it/s]
 42%|████▏     | 23959/57600 [4:11:36<6:01:14,  1.55it/s]
 42%|████▏     | 23960/57600 [4:11:37<5:53:32,  1.59it/s]
                                                         
{'loss': 1.2455, 'learning_rate': 6.274564459930314e-07, 'epoch': 264.46}

 42%|████▏     | 23960/57600 [4:11:37<5:53:32,  1.59it/s]
 42%|████▏     | 23961/57600 [4:11:38<5:43:15,  1.63it/s]
 42%|████▏     | 23962/57600 [4:11:38<5:36:23,  1.67it/s]
 42%|████▏     | 23963/57600 [4:11:39<5:43:00,  1.63it/s]
 42%|████▏     | 23964/57600 [4:11:40<5:55:02,  1.58it/s]
 42%|████▏     | 23965/57600 [4:11:40<5:50:58,  1.60it/s]
 42%|████▏     | 23966/57600 [4:11:41<5:49:35,  1.60it/s]
 42%|████▏     | 23967/57600 [4:11:41<5:39:57,  1.65it/s]
 42%|████▏     | 23968/57600 [4:11:42<5:40:48,  1.64it/s]
 42%|████▏     | 23969/57600 [4:11:43<5:40:23,  1.65it/s]
 42%|████▏     | 23970/57600 [4:11:43<5:43:38,  1.63it/s]
 42%|████▏     | 23971/57600 [4:11:44<5:46:20,  1.62it/s]
 42%|████▏     | 23972/57600 [4:11:44<5:47:46,  1.61it/s]
 42%|████▏     | 23973/57600 [4:11:45<5:41:41,  1.64it/s]
 42%|████▏     | 23974/57600 [4:11:46<5:38:19,  1.66it/s]
 42%|████▏     | 23975/57600 [4:11:46<5:43:56,  1.63it/s]
 42%|████▏     | 23976/57600 [4:11:47<5:42:38,  1.64it/s]
 42%|████▏     | 23977/57600 [4:11:47<5:42:10,  1.64it/s]
 42%|████▏     | 23978/57600 [4:11:48<5:47:44,  1.61it/s]
 42%|████▏     | 23979/57600 [4:11:49<5:43:34,  1.63it/s]
 42%|████▏     | 23980/57600 [4:11:49<5:37:38,  1.66it/s]
                                                         
{'loss': 1.24, 'learning_rate': 6.27142857142857e-07, 'epoch': 264.68}

 42%|████▏     | 23980/57600 [4:11:49<5:37:38,  1.66it/s]
 42%|████▏     | 23981/57600 [4:11:50<5:30:30,  1.70it/s]
 42%|████▏     | 23982/57600 [4:11:50<5:25:26,  1.72it/s]
 42%|████▏     | 23983/57600 [4:11:51<5:24:02,  1.73it/s]
 42%|████▏     | 23984/57600 [4:11:52<5:35:21,  1.67it/s]
 42%|████▏     | 23985/57600 [4:11:52<5:38:50,  1.65it/s]
 42%|████▏     | 23986/57600 [4:11:53<5:45:02,  1.62it/s]
 42%|████▏     | 23987/57600 [4:11:53<5:49:58,  1.60it/s]
 42%|████▏     | 23988/57600 [4:11:54<5:49:45,  1.60it/s]
 42%|████▏     | 23989/57600 [4:11:55<5:50:42,  1.60it/s]
 42%|████▏     | 23990/57600 [4:11:55<5:56:45,  1.57it/s]
 42%|████▏     | 23991/57600 [4:11:56<5:53:37,  1.58it/s]
 42%|████▏     | 23992/57600 [4:11:57<5:55:06,  1.58it/s]
 42%|████▏     | 23993/57600 [4:11:57<5:54:27,  1.58it/s]
 42%|████▏     | 23994/57600 [4:11:58<6:03:00,  1.54it/s]
 42%|████▏     | 23995/57600 [4:11:59<5:56:06,  1.57it/s]
 42%|████▏     | 23996/57600 [4:11:59<5:48:18,  1.61it/s]
 42%|████▏     | 23997/57600 [4:12:00<5:50:46,  1.60it/s]
 42%|████▏     | 23998/57600 [4:12:00<5:48:18,  1.61it/s]
 42%|████▏     | 23999/57600 [4:12:01<5:50:30,  1.60it/s]
 42%|████▏     | 24000/57600 [4:12:02<5:47:51,  1.61it/s]
                                                         
{'loss': 1.2203, 'learning_rate': 6.26829268292683e-07, 'epoch': 264.9}

 42%|████▏     | 24000/57600 [4:12:02<5:47:51,  1.61it/s]
 42%|████▏     | 24001/57600 [4:12:02<5:44:51,  1.62it/s]
 42%|████▏     | 24002/57600 [4:12:03<6:03:52,  1.54it/s]
 42%|████▏     | 24003/57600 [4:12:04<5:51:43,  1.59it/s]
 42%|████▏     | 24004/57600 [4:12:04<5:45:57,  1.62it/s]
 42%|████▏     | 24005/57600 [4:12:05<5:38:52,  1.65it/s]
 42%|████▏     | 24006/57600 [4:12:05<5:41:45,  1.64it/s]
 42%|████▏     | 24007/57600 [4:12:06<5:35:47,  1.67it/s]
 42%|████▏     | 24008/57600 [4:12:07<5:30:16,  1.70it/s]
 42%|████▏     | 24009/57600 [4:12:07<5:37:23,  1.66it/s]
 42%|████▏     | 24010/57600 [4:12:08<5:47:47,  1.61it/s]
 42%|████▏     | 24011/57600 [4:12:08<5:43:03,  1.63it/s]
 42%|████▏     | 24012/57600 [4:12:09<5:43:16,  1.63it/s]
 42%|████▏     | 24013/57600 [4:12:10<5:53:00,  1.59it/s]
 42%|████▏     | 24014/57600 [4:12:10<5:52:40,  1.59it/s]
 42%|████▏     | 24015/57600 [4:12:11<5:47:40,  1.61it/s]
 42%|████▏     | 24016/57600 [4:12:12<5:45:44,  1.62it/s]
 42%|████▏     | 24017/57600 [4:12:12<5:47:00,  1.61it/s]
 42%|████▏     | 24018/57600 [4:12:13<5:54:04,  1.58it/s]
 42%|████▏     | 24019/57600 [4:12:13<5:43:28,  1.63it/s]
 42%|████▏     | 24020/57600 [4:12:14<5:37:16,  1.66it/s]
                                                         
{'loss': 1.2501, 'learning_rate': 6.265156794425087e-07, 'epoch': 265.12}

 42%|████▏     | 24020/57600 [4:12:14<5:37:16,  1.66it/s]
 42%|████▏     | 24021/57600 [4:12:15<5:49:15,  1.60it/s]
 42%|████▏     | 24022/57600 [4:12:15<5:47:12,  1.61it/s]
 42%|████▏     | 24023/57600 [4:12:16<5:39:39,  1.65it/s]
 42%|████▏     | 24024/57600 [4:12:16<5:36:13,  1.66it/s]
 42%|████▏     | 24025/57600 [4:12:17<5:37:41,  1.66it/s]
 42%|████▏     | 24026/57600 [4:12:18<5:40:30,  1.64it/s]
 42%|████▏     | 24027/57600 [4:12:18<5:40:35,  1.64it/s]
 42%|████▏     | 24028/57600 [4:12:19<5:38:09,  1.65it/s]
 42%|████▏     | 24029/57600 [4:12:19<5:28:34,  1.70it/s]
 42%|████▏     | 24030/57600 [4:12:20<5:29:08,  1.70it/s]
 42%|████▏     | 24031/57600 [4:12:21<5:29:25,  1.70it/s]
 42%|████▏     | 24032/57600 [4:12:21<5:27:57,  1.71it/s]
 42%|████▏     | 24033/57600 [4:12:22<5:32:16,  1.68it/s]
 42%|████▏     | 24034/57600 [4:12:22<5:50:31,  1.60it/s]
 42%|████▏     | 24035/57600 [4:12:23<5:35:49,  1.67it/s]
 42%|████▏     | 24036/57600 [4:12:24<5:43:17,  1.63it/s]
 42%|████▏     | 24037/57600 [4:12:24<5:39:40,  1.65it/s]
 42%|████▏     | 24038/57600 [4:12:25<5:44:03,  1.63it/s]
 42%|████▏     | 24039/57600 [4:12:25<5:35:11,  1.67it/s]
 42%|████▏     | 24040/57600 [4:12:26<5:36:46,  1.66it/s]
                                                         
{'loss': 1.2449, 'learning_rate': 6.262020905923344e-07, 'epoch': 265.34}

 42%|████▏     | 24040/57600 [4:12:26<5:36:46,  1.66it/s]
 42%|████▏     | 24041/57600 [4:12:27<5:43:16,  1.63it/s]
 42%|████▏     | 24042/57600 [4:12:27<5:36:51,  1.66it/s]
 42%|████▏     | 24043/57600 [4:12:28<5:39:43,  1.65it/s]
 42%|████▏     | 24044/57600 [4:12:28<5:35:24,  1.67it/s]
 42%|████▏     | 24045/57600 [4:12:29<5:49:00,  1.60it/s]
 42%|████▏     | 24046/57600 [4:12:30<5:47:02,  1.61it/s]
 42%|████▏     | 24047/57600 [4:12:30<5:47:03,  1.61it/s]
 42%|████▏     | 24048/57600 [4:12:31<5:42:57,  1.63it/s]
 42%|████▏     | 24049/57600 [4:12:32<5:50:28,  1.60it/s]
 42%|████▏     | 24050/57600 [4:12:32<5:40:22,  1.64it/s]
 42%|████▏     | 24051/57600 [4:12:33<5:51:59,  1.59it/s]
 42%|████▏     | 24052/57600 [4:12:34<6:04:30,  1.53it/s]
 42%|████▏     | 24053/57600 [4:12:34<6:00:02,  1.55it/s]
 42%|████▏     | 24054/57600 [4:12:35<6:00:59,  1.55it/s]
 42%|████▏     | 24055/57600 [4:12:35<5:53:13,  1.58it/s]
 42%|████▏     | 24056/57600 [4:12:36<5:51:31,  1.59it/s]
 42%|████▏     | 24057/57600 [4:12:37<5:53:32,  1.58it/s]
 42%|████▏     | 24058/57600 [4:12:37<5:46:33,  1.61it/s]
 42%|████▏     | 24059/57600 [4:12:38<5:57:03,  1.57it/s]
 42%|████▏     | 24060/57600 [4:12:39<5:49:02,  1.60it/s]
                                                         
{'loss': 1.1949, 'learning_rate': 6.258885017421602e-07, 'epoch': 265.56}

 42%|████▏     | 24060/57600 [4:12:39<5:49:02,  1.60it/s]
 42%|████▏     | 24061/57600 [4:12:39<5:55:25,  1.57it/s]
 42%|████▏     | 24062/57600 [4:12:40<5:45:43,  1.62it/s]
 42%|████▏     | 24063/57600 [4:12:40<5:43:06,  1.63it/s]
 42%|████▏     | 24064/57600 [4:12:41<5:51:18,  1.59it/s]
 42%|████▏     | 24065/57600 [4:12:42<5:54:32,  1.58it/s]
 42%|████▏     | 24066/57600 [4:12:42<5:56:38,  1.57it/s]
 42%|████▏     | 24067/57600 [4:12:43<5:57:03,  1.57it/s]
 42%|████▏     | 24068/57600 [4:12:44<5:50:06,  1.60it/s]
 42%|████▏     | 24069/57600 [4:12:44<5:43:50,  1.63it/s]
 42%|████▏     | 24070/57600 [4:12:45<5:45:24,  1.62it/s]
 42%|████▏     | 24071/57600 [4:12:45<5:46:10,  1.61it/s]
 42%|████▏     | 24072/57600 [4:12:46<5:41:36,  1.64it/s]
 42%|████▏     | 24073/57600 [4:12:47<5:50:01,  1.60it/s]
 42%|████▏     | 24074/57600 [4:12:47<5:48:24,  1.60it/s]
 42%|████▏     | 24075/57600 [4:12:48<5:51:42,  1.59it/s]
 42%|████▏     | 24076/57600 [4:12:49<5:38:29,  1.65it/s]
 42%|████▏     | 24077/57600 [4:12:49<5:36:53,  1.66it/s]
 42%|████▏     | 24078/57600 [4:12:50<5:47:45,  1.61it/s]
 42%|████▏     | 24079/57600 [4:12:50<5:37:52,  1.65it/s]
 42%|████▏     | 24080/57600 [4:12:51<5:34:53,  1.67it/s]
                                                         
{'loss': 1.2228, 'learning_rate': 6.255749128919861e-07, 'epoch': 265.78}

 42%|████▏     | 24080/57600 [4:12:51<5:34:53,  1.67it/s]
 42%|████▏     | 24081/57600 [4:12:52<5:35:43,  1.66it/s]
 42%|████▏     | 24082/57600 [4:12:52<5:46:58,  1.61it/s]
 42%|████▏     | 24083/57600 [4:12:53<5:53:21,  1.58it/s]
 42%|████▏     | 24084/57600 [4:12:54<5:57:48,  1.56it/s]
 42%|████▏     | 24085/57600 [4:12:54<5:52:47,  1.58it/s]
 42%|████▏     | 24086/57600 [4:12:55<5:45:50,  1.62it/s]
 42%|████▏     | 24087/57600 [4:12:55<5:36:54,  1.66it/s]
 42%|████▏     | 24088/57600 [4:12:56<5:31:19,  1.69it/s]
 42%|████▏     | 24089/57600 [4:12:56<5:31:51,  1.68it/s]
 42%|████▏     | 24090/57600 [4:12:57<5:43:53,  1.62it/s]
 42%|████▏     | 24091/57600 [4:12:58<5:45:50,  1.61it/s]
 42%|████▏     | 24092/57600 [4:12:58<5:42:10,  1.63it/s]
 42%|████▏     | 24093/57600 [4:12:59<5:45:14,  1.62it/s]
 42%|████▏     | 24094/57600 [4:13:00<5:43:29,  1.63it/s]
 42%|████▏     | 24095/57600 [4:13:00<5:55:59,  1.57it/s]
 42%|████▏     | 24096/57600 [4:13:01<5:48:37,  1.60it/s]
 42%|████▏     | 24097/57600 [4:13:02<5:56:56,  1.56it/s]
 42%|████▏     | 24098/57600 [4:13:02<5:59:17,  1.55it/s]
 42%|████▏     | 24099/57600 [4:13:03<6:03:30,  1.54it/s]
 42%|████▏     | 24100/57600 [4:13:04<6:28:57,  1.44it/s]
                                                         
{'loss': 1.2237, 'learning_rate': 6.252613240418118e-07, 'epoch': 266.0}

 42%|████▏     | 24100/57600 [4:13:04<6:28:57,  1.44it/s]
 42%|████▏     | 24101/57600 [4:13:04<6:23:56,  1.45it/s]
 42%|████▏     | 24102/57600 [4:13:05<6:15:57,  1.48it/s]
 42%|████▏     | 24103/57600 [4:13:06<6:07:05,  1.52it/s]
 42%|████▏     | 24104/57600 [4:13:06<6:11:55,  1.50it/s]
 42%|████▏     | 24105/57600 [4:13:07<6:11:10,  1.50it/s]
 42%|████▏     | 24106/57600 [4:13:08<6:09:37,  1.51it/s]
 42%|████▏     | 24107/57600 [4:13:08<6:13:37,  1.49it/s]
 42%|████▏     | 24108/57600 [4:13:09<5:56:58,  1.56it/s]
 42%|████▏     | 24109/57600 [4:13:09<5:40:36,  1.64it/s]
 42%|████▏     | 24110/57600 [4:13:10<5:35:45,  1.66it/s]
 42%|████▏     | 24111/57600 [4:13:11<5:28:36,  1.70it/s]
 42%|████▏     | 24112/57600 [4:13:11<5:29:50,  1.69it/s]
 42%|████▏     | 24113/57600 [4:13:12<5:38:43,  1.65it/s]
 42%|████▏     | 24114/57600 [4:13:12<5:50:36,  1.59it/s]
 42%|████▏     | 24115/57600 [4:13:13<5:44:52,  1.62it/s]
 42%|████▏     | 24116/57600 [4:13:14<5:37:08,  1.66it/s]
 42%|████▏     | 24117/57600 [4:13:14<5:31:23,  1.68it/s]
 42%|████▏     | 24118/57600 [4:13:15<5:38:49,  1.65it/s]
 42%|████▏     | 24119/57600 [4:13:15<5:37:59,  1.65it/s]
 42%|████▏     | 24120/57600 [4:13:16<5:41:18,  1.63it/s]
                                                         
{'loss': 1.2144, 'learning_rate': 6.249477351916376e-07, 'epoch': 266.23}

 42%|████▏     | 24120/57600 [4:13:16<5:41:18,  1.63it/s]
 42%|████▏     | 24121/57600 [4:13:17<5:48:04,  1.60it/s]
 42%|████▏     | 24122/57600 [4:13:17<5:43:45,  1.62it/s]
 42%|████▏     | 24123/57600 [4:13:18<5:36:51,  1.66it/s]
 42%|████▏     | 24124/57600 [4:13:19<5:42:00,  1.63it/s]
 42%|████▏     | 24125/57600 [4:13:19<5:33:21,  1.67it/s]
 42%|████▏     | 24126/57600 [4:13:20<5:43:02,  1.63it/s]
 42%|████▏     | 24127/57600 [4:13:20<5:41:04,  1.64it/s]
 42%|████▏     | 24128/57600 [4:13:21<5:41:32,  1.63it/s]
 42%|████▏     | 24129/57600 [4:13:22<5:37:50,  1.65it/s]
 42%|████▏     | 24130/57600 [4:13:22<5:35:19,  1.66it/s]
 42%|████▏     | 24131/57600 [4:13:23<5:31:56,  1.68it/s]
 42%|████▏     | 24132/57600 [4:13:23<5:31:29,  1.68it/s]
 42%|████▏     | 24133/57600 [4:13:24<5:39:07,  1.64it/s]
 42%|████▏     | 24134/57600 [4:13:25<5:43:52,  1.62it/s]
 42%|████▏     | 24135/57600 [4:13:25<5:40:37,  1.64it/s]
 42%|████▏     | 24136/57600 [4:13:26<5:39:07,  1.64it/s]
 42%|████▏     | 24137/57600 [4:13:26<5:47:24,  1.61it/s]
 42%|████▏     | 24138/57600 [4:13:27<5:48:46,  1.60it/s]
 42%|████▏     | 24139/57600 [4:13:28<5:50:08,  1.59it/s]
 42%|████▏     | 24140/57600 [4:13:28<5:40:25,  1.64it/s]
                                                         
{'loss': 1.2376, 'learning_rate': 6.246341463414634e-07, 'epoch': 266.45}

 42%|████▏     | 24140/57600 [4:13:28<5:40:25,  1.64it/s]
 42%|████▏     | 24141/57600 [4:13:29<5:39:45,  1.64it/s]
 42%|████▏     | 24142/57600 [4:13:29<5:31:34,  1.68it/s]
 42%|████▏     | 24143/57600 [4:13:30<5:29:44,  1.69it/s]
 42%|████▏     | 24144/57600 [4:13:31<5:26:52,  1.71it/s]
 42%|████▏     | 24145/57600 [4:13:31<5:23:39,  1.72it/s]
 42%|████▏     | 24146/57600 [4:13:32<5:24:04,  1.72it/s]
 42%|████▏     | 24147/57600 [4:13:32<5:26:08,  1.71it/s]
 42%|████▏     | 24148/57600 [4:13:33<5:37:40,  1.65it/s]
 42%|████▏     | 24149/57600 [4:13:34<5:39:52,  1.64it/s]
 42%|████▏     | 24150/57600 [4:13:34<5:40:52,  1.64it/s]
 42%|████▏     | 24151/57600 [4:13:35<5:55:27,  1.57it/s]
 42%|████▏     | 24152/57600 [4:13:36<6:05:43,  1.52it/s]
 42%|████▏     | 24153/57600 [4:13:36<5:55:52,  1.57it/s]
 42%|████▏     | 24154/57600 [4:13:37<5:41:16,  1.63it/s]
 42%|████▏     | 24155/57600 [4:13:37<5:48:16,  1.60it/s]
 42%|████▏     | 24156/57600 [4:13:38<5:54:53,  1.57it/s]
 42%|████▏     | 24157/57600 [4:13:39<6:07:31,  1.52it/s]
 42%|████▏     | 24158/57600 [4:13:39<6:01:07,  1.54it/s]
 42%|████▏     | 24159/57600 [4:13:40<5:55:40,  1.57it/s]
 42%|████▏     | 24160/57600 [4:13:41<5:46:26,  1.61it/s]
                                                         
{'loss': 1.2158, 'learning_rate': 6.243205574912892e-07, 'epoch': 266.67}

 42%|████▏     | 24160/57600 [4:13:41<5:46:26,  1.61it/s]
 42%|████▏     | 24161/57600 [4:13:41<5:46:14,  1.61it/s]
 42%|████▏     | 24162/57600 [4:13:42<5:50:17,  1.59it/s]
 42%|████▏     | 24163/57600 [4:13:43<6:02:33,  1.54it/s]
 42%|████▏     | 24164/57600 [4:13:43<5:53:50,  1.57it/s]
 42%|████▏     | 24165/57600 [4:13:44<5:44:39,  1.62it/s]
 42%|████▏     | 24166/57600 [4:13:44<5:35:57,  1.66it/s]
 42%|████▏     | 24167/57600 [4:13:45<5:39:36,  1.64it/s]
 42%|████▏     | 24168/57600 [4:13:46<5:36:42,  1.65it/s]
 42%|████▏     | 24169/57600 [4:13:46<5:44:06,  1.62it/s]
 42%|████▏     | 24170/57600 [4:13:47<5:40:07,  1.64it/s]
 42%|████▏     | 24171/57600 [4:13:47<5:47:11,  1.60it/s]
 42%|████▏     | 24172/57600 [4:13:48<5:40:40,  1.64it/s]
 42%|████▏     | 24173/57600 [4:13:49<5:32:55,  1.67it/s]
 42%|████▏     | 24174/57600 [4:13:49<5:47:21,  1.60it/s]
 42%|████▏     | 24175/57600 [4:13:50<5:35:47,  1.66it/s]
 42%|████▏     | 24176/57600 [4:13:50<5:31:42,  1.68it/s]
 42%|████▏     | 24177/57600 [4:13:51<5:32:31,  1.68it/s]
 42%|████▏     | 24178/57600 [4:13:52<5:43:04,  1.62it/s]
 42%|████▏     | 24179/57600 [4:13:52<6:12:49,  1.49it/s]
 42%|████▏     | 24180/57600 [4:13:53<6:11:21,  1.50it/s]
                                                         
{'loss': 1.2253, 'learning_rate': 6.24006968641115e-07, 'epoch': 266.89}

 42%|████▏     | 24180/57600 [4:13:53<6:11:21,  1.50it/s]
 42%|████▏     | 24181/57600 [4:13:54<5:54:04,  1.57it/s]
 42%|████▏     | 24182/57600 [4:13:54<5:47:47,  1.60it/s]
 42%|████▏     | 24183/57600 [4:13:55<5:43:02,  1.62it/s]
 42%|████▏     | 24184/57600 [4:13:55<5:37:29,  1.65it/s]
 42%|████▏     | 24185/57600 [4:13:56<5:49:09,  1.59it/s]
 42%|████▏     | 24186/57600 [4:13:57<5:41:09,  1.63it/s]
 42%|████▏     | 24187/57600 [4:13:57<5:51:57,  1.58it/s]
 42%|████▏     | 24188/57600 [4:13:58<5:48:39,  1.60it/s]
 42%|████▏     | 24189/57600 [4:13:59<5:40:11,  1.64it/s]
 42%|████▏     | 24190/57600 [4:13:59<5:40:44,  1.63it/s]
 42%|████▏     | 24191/57600 [4:14:00<5:55:38,  1.57it/s]
 42%|████▏     | 24192/57600 [4:14:01<5:55:36,  1.57it/s]
 42%|████▏     | 24193/57600 [4:14:01<5:40:27,  1.64it/s]
 42%|████▏     | 24194/57600 [4:14:02<5:37:04,  1.65it/s]
 42%|████▏     | 24195/57600 [4:14:02<5:51:29,  1.58it/s]
 42%|████▏     | 24196/57600 [4:14:03<5:48:52,  1.60it/s]
 42%|████▏     | 24197/57600 [4:14:04<5:42:24,  1.63it/s]
 42%|████▏     | 24198/57600 [4:14:04<5:37:36,  1.65it/s]
 42%|████▏     | 24199/57600 [4:14:05<5:33:58,  1.67it/s]
 42%|████▏     | 24200/57600 [4:14:05<5:50:39,  1.59it/s]
                                                         
{'loss': 1.229, 'learning_rate': 6.236933797909407e-07, 'epoch': 267.11}

 42%|████▏     | 24200/57600 [4:14:05<5:50:39,  1.59it/s]
 42%|████▏     | 24201/57600 [4:14:06<5:45:56,  1.61it/s]
 42%|████▏     | 24202/57600 [4:14:07<5:46:38,  1.61it/s]
 42%|████▏     | 24203/57600 [4:14:07<5:45:01,  1.61it/s]
 42%|████▏     | 24204/57600 [4:14:08<5:47:59,  1.60it/s]
 42%|████▏     | 24205/57600 [4:14:09<5:44:06,  1.62it/s]
 42%|████▏     | 24206/57600 [4:14:09<5:34:55,  1.66it/s]
 42%|████▏     | 24207/57600 [4:14:10<5:36:33,  1.65it/s]
 42%|████▏     | 24208/57600 [4:14:10<5:33:06,  1.67it/s]
 42%|████▏     | 24209/57600 [4:14:11<5:43:39,  1.62it/s]
 42%|████▏     | 24210/57600 [4:14:12<5:46:26,  1.61it/s]
 42%|████▏     | 24211/57600 [4:14:12<5:49:37,  1.59it/s]
 42%|████▏     | 24212/57600 [4:14:13<5:56:33,  1.56it/s]
 42%|████▏     | 24213/57600 [4:14:14<5:52:49,  1.58it/s]
 42%|████▏     | 24214/57600 [4:14:14<5:42:40,  1.62it/s]
 42%|████▏     | 24215/57600 [4:14:15<5:29:43,  1.69it/s]
 42%|████▏     | 24216/57600 [4:14:15<5:35:41,  1.66it/s]
 42%|████▏     | 24217/57600 [4:14:16<5:42:54,  1.62it/s]
 42%|████▏     | 24218/57600 [4:14:17<5:45:38,  1.61it/s]
 42%|████▏     | 24219/57600 [4:14:17<5:44:51,  1.61it/s]
 42%|████▏     | 24220/57600 [4:14:18<5:56:05,  1.56it/s]
                                                         
{'loss': 1.209, 'learning_rate': 6.233797909407666e-07, 'epoch': 267.33}

 42%|████▏     | 24220/57600 [4:14:18<5:56:05,  1.56it/s]
 42%|████▏     | 24221/57600 [4:14:18<5:56:12,  1.56it/s]
 42%|████▏     | 24222/57600 [4:14:19<5:49:02,  1.59it/s]
 42%|████▏     | 24223/57600 [4:14:20<5:36:25,  1.65it/s]
 42%|████▏     | 24224/57600 [4:14:20<5:27:25,  1.70it/s]
 42%|████▏     | 24225/57600 [4:14:21<5:38:59,  1.64it/s]
 42%|████▏     | 24226/57600 [4:14:21<5:43:35,  1.62it/s]
 42%|████▏     | 24227/57600 [4:14:22<5:50:06,  1.59it/s]
 42%|████▏     | 24228/57600 [4:14:23<5:40:54,  1.63it/s]
 42%|████▏     | 24229/57600 [4:14:23<5:38:11,  1.64it/s]
 42%|████▏     | 24230/57600 [4:14:24<5:34:16,  1.66it/s]
 42%|████▏     | 24231/57600 [4:14:25<5:37:32,  1.65it/s]
 42%|████▏     | 24232/57600 [4:14:25<5:37:26,  1.65it/s]
 42%|████▏     | 24233/57600 [4:14:26<5:47:53,  1.60it/s]
 42%|████▏     | 24234/57600 [4:14:26<5:42:31,  1.62it/s]
 42%|████▏     | 24235/57600 [4:14:27<5:38:07,  1.64it/s]
 42%|████▏     | 24236/57600 [4:14:28<5:27:31,  1.70it/s]
 42%|████▏     | 24237/57600 [4:14:28<5:32:40,  1.67it/s]
 42%|████▏     | 24238/57600 [4:14:29<5:28:00,  1.70it/s]
 42%|████▏     | 24239/57600 [4:14:29<5:36:38,  1.65it/s]
 42%|████▏     | 24240/57600 [4:14:30<5:52:03,  1.58it/s]
                                                         
{'loss': 1.2141, 'learning_rate': 6.230662020905923e-07, 'epoch': 267.55}

 42%|████▏     | 24240/57600 [4:14:30<5:52:03,  1.58it/s]
 42%|████▏     | 24241/57600 [4:14:31<5:51:09,  1.58it/s]
 42%|████▏     | 24242/57600 [4:14:31<5:44:00,  1.62it/s]
 42%|████▏     | 24243/57600 [4:14:32<6:11:14,  1.50it/s]
 42%|████▏     | 24244/57600 [4:14:33<5:54:05,  1.57it/s]
 42%|████▏     | 24245/57600 [4:14:33<5:49:23,  1.59it/s]
 42%|████▏     | 24246/57600 [4:14:34<5:50:37,  1.59it/s]
 42%|████▏     | 24247/57600 [4:14:34<5:41:05,  1.63it/s]
 42%|████▏     | 24248/57600 [4:14:35<5:40:03,  1.63it/s]
 42%|████▏     | 24249/57600 [4:14:36<5:37:12,  1.65it/s]
 42%|████▏     | 24250/57600 [4:14:36<5:42:32,  1.62it/s]
 42%|████▏     | 24251/57600 [4:14:37<5:36:41,  1.65it/s]
 42%|████▏     | 24252/57600 [4:14:38<6:01:00,  1.54it/s]
 42%|████▏     | 24253/57600 [4:14:38<6:09:03,  1.51it/s]
 42%|████▏     | 24254/57600 [4:14:39<6:14:38,  1.48it/s]
 42%|████▏     | 24255/57600 [4:14:40<5:56:06,  1.56it/s]
 42%|████▏     | 24256/57600 [4:14:40<5:55:12,  1.56it/s]
 42%|████▏     | 24257/57600 [4:14:41<5:49:02,  1.59it/s]
 42%|████▏     | 24258/57600 [4:14:41<5:42:50,  1.62it/s]
 42%|████▏     | 24259/57600 [4:14:42<5:44:10,  1.61it/s]
 42%|████▏     | 24260/57600 [4:14:43<5:51:17,  1.58it/s]
                                                         
{'loss': 1.1775, 'learning_rate': 6.227526132404181e-07, 'epoch': 267.77}

 42%|████▏     | 24260/57600 [4:14:43<5:51:17,  1.58it/s]
 42%|████▏     | 24261/57600 [4:14:43<5:45:55,  1.61it/s]
 42%|████▏     | 24262/57600 [4:14:44<5:39:20,  1.64it/s]
 42%|████▏     | 24263/57600 [4:14:44<5:42:01,  1.62it/s]
 42%|████▏     | 24264/57600 [4:14:45<5:32:47,  1.67it/s]
 42%|████▏     | 24265/57600 [4:14:46<5:48:14,  1.60it/s]
 42%|████▏     | 24266/57600 [4:14:46<5:48:00,  1.60it/s]
 42%|████▏     | 24267/57600 [4:14:47<5:40:32,  1.63it/s]
 42%|████▏     | 24268/57600 [4:14:48<5:41:38,  1.63it/s]
 42%|████▏     | 24269/57600 [4:14:48<5:50:43,  1.58it/s]
 42%|████▏     | 24270/57600 [4:14:49<5:41:31,  1.63it/s]
 42%|████▏     | 24271/57600 [4:14:49<5:39:35,  1.64it/s]
 42%|████▏     | 24272/57600 [4:14:50<5:45:55,  1.61it/s]
 42%|████▏     | 24273/57600 [4:14:51<5:55:04,  1.56it/s]
 42%|████▏     | 24274/57600 [4:14:51<6:04:29,  1.52it/s]
 42%|████▏     | 24275/57600 [4:14:52<5:54:16,  1.57it/s]
 42%|████▏     | 24276/57600 [4:14:53<5:45:28,  1.61it/s]
 42%|████▏     | 24277/57600 [4:14:53<5:39:45,  1.63it/s]
 42%|████▏     | 24278/57600 [4:14:54<5:49:10,  1.59it/s]
 42%|████▏     | 24279/57600 [4:14:55<6:02:03,  1.53it/s]
 42%|████▏     | 24280/57600 [4:14:55<6:01:13,  1.54it/s]
                                                         
{'loss': 1.212, 'learning_rate': 6.224390243902439e-07, 'epoch': 267.99}

 42%|████▏     | 24280/57600 [4:14:55<6:01:13,  1.54it/s]
 42%|████▏     | 24281/57600 [4:14:56<6:17:52,  1.47it/s]
 42%|████▏     | 24282/57600 [4:14:57<6:03:32,  1.53it/s]
 42%|████▏     | 24283/57600 [4:14:57<6:01:50,  1.53it/s]
 42%|████▏     | 24284/57600 [4:14:58<6:06:54,  1.51it/s]
 42%|████▏     | 24285/57600 [4:14:58<5:55:35,  1.56it/s]
 42%|████▏     | 24286/57600 [4:14:59<6:05:24,  1.52it/s]
 42%|████▏     | 24287/57600 [4:15:00<6:07:00,  1.51it/s]
 42%|████▏     | 24288/57600 [4:15:00<5:52:33,  1.57it/s]
 42%|████▏     | 24289/57600 [4:15:01<5:45:47,  1.61it/s]
 42%|████▏     | 24290/57600 [4:15:02<5:53:40,  1.57it/s]
 42%|████▏     | 24291/57600 [4:15:02<5:40:08,  1.63it/s]
 42%|████▏     | 24292/57600 [4:15:03<5:38:56,  1.64it/s]
 42%|████▏     | 24293/57600 [4:15:04<5:46:56,  1.60it/s]
 42%|████▏     | 24294/57600 [4:15:04<5:38:16,  1.64it/s]
 42%|████▏     | 24295/57600 [4:15:05<5:36:08,  1.65it/s]
 42%|████▏     | 24296/57600 [4:15:05<5:47:29,  1.60it/s]
 42%|████▏     | 24297/57600 [4:15:06<5:42:03,  1.62it/s]
 42%|████▏     | 24298/57600 [4:15:07<5:48:47,  1.59it/s]
 42%|████▏     | 24299/57600 [4:15:07<5:48:48,  1.59it/s]
 42%|████▏     | 24300/57600 [4:15:08<6:03:03,  1.53it/s]
                                                         
{'loss': 1.1793, 'learning_rate': 6.221254355400697e-07, 'epoch': 268.21}

 42%|████▏     | 24300/57600 [4:15:08<6:03:03,  1.53it/s]
 42%|████▏     | 24301/57600 [4:15:09<5:59:49,  1.54it/s]
 42%|████▏     | 24302/57600 [4:15:09<5:57:40,  1.55it/s]
 42%|████▏     | 24303/57600 [4:15:10<6:14:38,  1.48it/s]
 42%|████▏     | 24304/57600 [4:15:11<6:52:14,  1.35it/s]
 42%|████▏     | 24305/57600 [4:15:12<6:37:33,  1.40it/s]
 42%|████▏     | 24306/57600 [4:15:12<6:16:09,  1.48it/s]
 42%|████▏     | 24307/57600 [4:15:13<6:11:16,  1.49it/s]
 42%|████▏     | 24308/57600 [4:15:13<6:03:39,  1.53it/s]
 42%|████▏     | 24309/57600 [4:15:14<5:53:52,  1.57it/s]
 42%|████▏     | 24310/57600 [4:15:15<5:55:18,  1.56it/s]
 42%|████▏     | 24311/57600 [4:15:15<5:51:42,  1.58it/s]
 42%|████▏     | 24312/57600 [4:15:16<6:03:17,  1.53it/s]
 42%|████▏     | 24313/57600 [4:15:17<5:50:38,  1.58it/s]
 42%|████▏     | 24314/57600 [4:15:17<5:46:28,  1.60it/s]
 42%|████▏     | 24315/57600 [4:15:18<5:41:09,  1.63it/s]
 42%|████▏     | 24316/57600 [4:15:18<5:27:16,  1.70it/s]
 42%|████▏     | 24317/57600 [4:15:19<5:27:43,  1.69it/s]
 42%|████▏     | 24318/57600 [4:15:19<5:36:19,  1.65it/s]
 42%|████▏     | 24319/57600 [4:15:20<5:36:54,  1.65it/s]
 42%|████▏     | 24320/57600 [4:15:21<5:30:56,  1.68it/s]
                                                         
{'loss': 1.2344, 'learning_rate': 6.218118466898954e-07, 'epoch': 268.43}

 42%|████▏     | 24320/57600 [4:15:21<5:30:56,  1.68it/s]
 42%|████▏     | 24321/57600 [4:15:21<5:33:55,  1.66it/s]
 42%|████▏     | 24322/57600 [4:15:22<5:28:00,  1.69it/s]
 42%|████▏     | 24323/57600 [4:15:22<5:29:54,  1.68it/s]
 42%|████▏     | 24324/57600 [4:15:23<5:43:27,  1.61it/s]
 42%|████▏     | 24325/57600 [4:15:24<5:45:52,  1.60it/s]
 42%|████▏     | 24326/57600 [4:15:24<5:36:33,  1.65it/s]
 42%|████▏     | 24327/57600 [4:15:25<5:35:34,  1.65it/s]
 42%|████▏     | 24328/57600 [4:15:26<5:47:07,  1.60it/s]
 42%|████▏     | 24329/57600 [4:15:26<5:43:26,  1.61it/s]
 42%|████▏     | 24330/57600 [4:15:27<5:53:18,  1.57it/s]
 42%|████▏     | 24331/57600 [4:15:27<5:42:20,  1.62it/s]
 42%|████▏     | 24332/57600 [4:15:28<5:46:28,  1.60it/s]
 42%|████▏     | 24333/57600 [4:15:29<5:48:26,  1.59it/s]
 42%|████▏     | 24334/57600 [4:15:29<5:58:29,  1.55it/s]
 42%|████▏     | 24335/57600 [4:15:30<5:54:12,  1.57it/s]
 42%|████▏     | 24336/57600 [4:15:31<5:46:28,  1.60it/s]
 42%|████▏     | 24337/57600 [4:15:31<5:48:03,  1.59it/s]
 42%|████▏     | 24338/57600 [4:15:32<5:41:47,  1.62it/s]
 42%|████▏     | 24339/57600 [4:15:33<5:54:17,  1.56it/s]
 42%|████▏     | 24340/57600 [4:15:33<5:48:03,  1.59it/s]
                                                         
{'loss': 1.225, 'learning_rate': 6.214982578397212e-07, 'epoch': 268.65}

 42%|████▏     | 24340/57600 [4:15:33<5:48:03,  1.59it/s]
 42%|████▏     | 24341/57600 [4:15:34<5:46:07,  1.60it/s]
 42%|████▏     | 24342/57600 [4:15:34<5:49:47,  1.58it/s]
 42%|████▏     | 24343/57600 [4:15:35<5:53:28,  1.57it/s]
 42%|████▏     | 24344/57600 [4:15:36<5:55:19,  1.56it/s]
 42%|████▏     | 24345/57600 [4:15:36<5:45:16,  1.61it/s]
 42%|████▏     | 24346/57600 [4:15:37<5:35:19,  1.65it/s]
 42%|████▏     | 24347/57600 [4:15:37<5:38:00,  1.64it/s]
 42%|████▏     | 24348/57600 [4:15:38<5:36:44,  1.65it/s]
 42%|████▏     | 24349/57600 [4:15:39<5:45:28,  1.60it/s]
 42%|████▏     | 24350/57600 [4:15:39<5:44:12,  1.61it/s]
 42%|████▏     | 24351/57600 [4:15:40<5:42:18,  1.62it/s]
 42%|████▏     | 24352/57600 [4:15:41<5:42:55,  1.62it/s]
 42%|████▏     | 24353/57600 [4:15:41<5:37:55,  1.64it/s]
 42%|████▏     | 24354/57600 [4:15:42<5:41:45,  1.62it/s]
 42%|████▏     | 24355/57600 [4:15:42<5:49:57,  1.58it/s]
 42%|████▏     | 24356/57600 [4:15:43<5:49:36,  1.58it/s]
 42%|████▏     | 24357/57600 [4:15:44<6:00:41,  1.54it/s]
 42%|████▏     | 24358/57600 [4:15:44<5:49:48,  1.58it/s]
 42%|████▏     | 24359/57600 [4:15:45<5:37:39,  1.64it/s]
 42%|████▏     | 24360/57600 [4:15:46<5:32:25,  1.67it/s]
                                                         
{'loss': 1.2174, 'learning_rate': 6.21184668989547e-07, 'epoch': 268.87}

 42%|████▏     | 24360/57600 [4:15:46<5:32:25,  1.67it/s]
 42%|████▏     | 24361/57600 [4:15:46<5:23:20,  1.71it/s]
 42%|████▏     | 24362/57600 [4:15:47<5:24:11,  1.71it/s]
 42%|████▏     | 24363/57600 [4:15:47<5:21:51,  1.72it/s]
 42%|████▏     | 24364/57600 [4:15:48<5:18:46,  1.74it/s]
 42%|████▏     | 24365/57600 [4:15:48<5:34:07,  1.66it/s]
 42%|████▏     | 24366/57600 [4:15:49<5:32:01,  1.67it/s]
 42%|████▏     | 24367/57600 [4:15:50<5:28:55,  1.68it/s]
 42%|████▏     | 24368/57600 [4:15:50<5:29:45,  1.68it/s]
 42%|████▏     | 24369/57600 [4:15:51<5:33:09,  1.66it/s]
 42%|████▏     | 24370/57600 [4:15:52<5:47:17,  1.59it/s]
 42%|████▏     | 24371/57600 [4:15:52<5:50:40,  1.58it/s]
 42%|████▏     | 24372/57600 [4:15:53<6:05:13,  1.52it/s]
 42%|████▏     | 24373/57600 [4:15:54<6:11:19,  1.49it/s]
 42%|████▏     | 24374/57600 [4:15:54<6:01:21,  1.53it/s]
 42%|████▏     | 24375/57600 [4:15:55<6:00:18,  1.54it/s]
 42%|████▏     | 24376/57600 [4:15:55<5:44:25,  1.61it/s]
 42%|████▏     | 24377/57600 [4:15:56<5:38:29,  1.64it/s]
 42%|████▏     | 24378/57600 [4:15:57<5:58:34,  1.54it/s]
 42%|████▏     | 24379/57600 [4:15:57<5:46:01,  1.60it/s]
 42%|████▏     | 24380/57600 [4:15:58<5:55:40,  1.56it/s]
                                                         
{'loss': 1.2349, 'learning_rate': 6.208710801393728e-07, 'epoch': 269.09}

 42%|████▏     | 24380/57600 [4:15:58<5:55:40,  1.56it/s]
 42%|████▏     | 24381/57600 [4:15:59<5:41:16,  1.62it/s]
 42%|████▏     | 24382/57600 [4:15:59<5:38:23,  1.64it/s]
 42%|████▏     | 24383/57600 [4:16:00<5:37:58,  1.64it/s]
 42%|████▏     | 24384/57600 [4:16:00<5:40:40,  1.63it/s]
 42%|████▏     | 24385/57600 [4:16:01<5:37:25,  1.64it/s]
 42%|████▏     | 24386/57600 [4:16:02<5:33:57,  1.66it/s]
 42%|████▏     | 24387/57600 [4:16:02<5:28:51,  1.68it/s]
 42%|████▏     | 24388/57600 [4:16:03<5:29:48,  1.68it/s]
 42%|████▏     | 24389/57600 [4:16:03<5:29:10,  1.68it/s]
 42%|████▏     | 24390/57600 [4:16:04<5:34:00,  1.66it/s]
 42%|████▏     | 24391/57600 [4:16:05<5:40:45,  1.62it/s]
 42%|████▏     | 24392/57600 [4:16:05<5:30:57,  1.67it/s]
 42%|████▏     | 24393/57600 [4:16:06<5:26:35,  1.69it/s]
 42%|████▏     | 24394/57600 [4:16:06<5:34:47,  1.65it/s]
 42%|████▏     | 24395/57600 [4:16:07<5:25:57,  1.70it/s]
 42%|████▏     | 24396/57600 [4:16:08<5:26:28,  1.70it/s]
 42%|████▏     | 24397/57600 [4:16:08<5:21:36,  1.72it/s]
 42%|████▏     | 24398/57600 [4:16:09<5:18:54,  1.74it/s]
 42%|████▏     | 24399/57600 [4:16:09<5:34:38,  1.65it/s]
 42%|████▏     | 24400/57600 [4:16:10<5:33:59,  1.66it/s]
                                                         
{'loss': 1.2278, 'learning_rate': 6.205574912891986e-07, 'epoch': 269.32}

 42%|████▏     | 24400/57600 [4:16:10<5:33:59,  1.66it/s]
 42%|████▏     | 24401/57600 [4:16:10<5:28:18,  1.69it/s]
 42%|████▏     | 24402/57600 [4:16:11<5:37:31,  1.64it/s]
 42%|████▏     | 24403/57600 [4:16:12<5:44:19,  1.61it/s]
 42%|████▏     | 24404/57600 [4:16:13<6:00:18,  1.54it/s]
 42%|████▏     | 24405/57600 [4:16:13<5:50:44,  1.58it/s]
 42%|████▏     | 24406/57600 [4:16:14<5:53:02,  1.57it/s]
 42%|████▏     | 24407/57600 [4:16:14<5:49:42,  1.58it/s]
 42%|████▏     | 24408/57600 [4:16:15<5:54:11,  1.56it/s]
 42%|████▏     | 24409/57600 [4:16:16<5:50:55,  1.58it/s]
 42%|████▏     | 24410/57600 [4:16:16<5:48:21,  1.59it/s]
 42%|████▏     | 24411/57600 [4:16:17<5:56:15,  1.55it/s]
 42%|████▏     | 24412/57600 [4:16:18<5:50:44,  1.58it/s]
 42%|████▏     | 24413/57600 [4:16:18<5:56:50,  1.55it/s]
 42%|████▏     | 24414/57600 [4:16:19<6:00:39,  1.53it/s]
 42%|████▏     | 24415/57600 [4:16:20<5:57:55,  1.55it/s]
 42%|████▏     | 24416/57600 [4:16:20<5:54:30,  1.56it/s]
 42%|████▏     | 24417/57600 [4:16:21<6:15:05,  1.47it/s]
 42%|████▏     | 24418/57600 [4:16:21<5:56:02,  1.55it/s]
 42%|████▏     | 24419/57600 [4:16:22<5:50:48,  1.58it/s]
 42%|████▏     | 24420/57600 [4:16:23<5:41:09,  1.62it/s]
                                                         
{'loss': 1.2107, 'learning_rate': 6.202439024390244e-07, 'epoch': 269.54}

 42%|████▏     | 24420/57600 [4:16:23<5:41:09,  1.62it/s]
 42%|████▏     | 24421/57600 [4:16:23<5:30:26,  1.67it/s]
 42%|████▏     | 24422/57600 [4:16:24<5:24:46,  1.70it/s]
 42%|████▏     | 24423/57600 [4:16:24<5:22:23,  1.72it/s]
 42%|████▏     | 24424/57600 [4:16:25<5:27:28,  1.69it/s]
 42%|████▏     | 24425/57600 [4:16:26<5:41:11,  1.62it/s]
 42%|████▏     | 24426/57600 [4:16:26<5:38:27,  1.63it/s]
 42%|████▏     | 24427/57600 [4:16:27<5:43:05,  1.61it/s]
 42%|████▏     | 24428/57600 [4:16:28<5:47:05,  1.59it/s]
 42%|████▏     | 24429/57600 [4:16:28<5:37:40,  1.64it/s]
 42%|████▏     | 24430/57600 [4:16:29<5:42:42,  1.61it/s]
 42%|████▏     | 24431/57600 [4:16:29<5:41:16,  1.62it/s]
 42%|████▏     | 24432/57600 [4:16:30<5:36:54,  1.64it/s]
 42%|████▏     | 24433/57600 [4:16:31<5:40:48,  1.62it/s]
 42%|████▏     | 24434/57600 [4:16:31<5:43:12,  1.61it/s]
 42%|████▏     | 24435/57600 [4:16:32<5:36:07,  1.64it/s]
 42%|████▏     | 24436/57600 [4:16:32<5:42:48,  1.61it/s]
 42%|████▏     | 24437/57600 [4:16:33<5:40:00,  1.63it/s]
 42%|████▏     | 24438/57600 [4:16:34<5:39:31,  1.63it/s]
 42%|████▏     | 24439/57600 [4:16:34<5:30:29,  1.67it/s]
 42%|████▏     | 24440/57600 [4:16:35<5:44:14,  1.61it/s]
                                                         
{'loss': 1.2683, 'learning_rate': 6.199303135888501e-07, 'epoch': 269.76}

 42%|████▏     | 24440/57600 [4:16:35<5:44:14,  1.61it/s]
 42%|████▏     | 24441/57600 [4:16:36<5:44:03,  1.61it/s]
 42%|████▏     | 24442/57600 [4:16:36<5:48:17,  1.59it/s]
 42%|████▏     | 24443/57600 [4:16:37<5:45:41,  1.60it/s]
 42%|████▏     | 24444/57600 [4:16:37<5:59:22,  1.54it/s]
 42%|████▏     | 24445/57600 [4:16:38<6:01:32,  1.53it/s]
 42%|████▏     | 24446/57600 [4:16:39<6:01:13,  1.53it/s]
 42%|████▏     | 24447/57600 [4:16:39<5:55:48,  1.55it/s]
 42%|████▏     | 24448/57600 [4:16:40<5:52:11,  1.57it/s]
 42%|████▏     | 24449/57600 [4:16:41<5:38:12,  1.63it/s]
 42%|████▏     | 24450/57600 [4:16:41<5:40:45,  1.62it/s]
 42%|████▏     | 24451/57600 [4:16:42<5:44:25,  1.60it/s]
 42%|████▏     | 24452/57600 [4:16:42<5:44:45,  1.60it/s]
 42%|████▏     | 24453/57600 [4:16:43<5:49:34,  1.58it/s]
 42%|████▏     | 24454/57600 [4:16:44<5:43:31,  1.61it/s]
 42%|████▏     | 24455/57600 [4:16:44<5:41:58,  1.62it/s]
 42%|████▏     | 24456/57600 [4:16:45<5:41:40,  1.62it/s]
 42%|████▏     | 24457/57600 [4:16:46<5:50:08,  1.58it/s]
 42%|████▏     | 24458/57600 [4:16:46<5:49:33,  1.58it/s]
 42%|████▏     | 24459/57600 [4:16:47<5:48:45,  1.58it/s]
 42%|████▏     | 24460/57600 [4:16:48<5:57:40,  1.54it/s]
                                                         
{'loss': 1.1847, 'learning_rate': 6.196167247386759e-07, 'epoch': 269.98}

 42%|████▏     | 24460/57600 [4:16:48<5:57:40,  1.54it/s]
 42%|████▏     | 24461/57600 [4:16:48<5:52:07,  1.57it/s]
 42%|████▏     | 24462/57600 [4:16:49<6:03:28,  1.52it/s]
 42%|████▏     | 24463/57600 [4:16:50<6:05:26,  1.51it/s]
 42%|████▏     | 24464/57600 [4:16:50<6:09:56,  1.49it/s]
 42%|████▏     | 24465/57600 [4:16:51<5:56:37,  1.55it/s]
 42%|████▏     | 24466/57600 [4:16:51<5:44:13,  1.60it/s]
 42%|████▏     | 24467/57600 [4:16:52<5:32:24,  1.66it/s]
 42%|████▏     | 24468/57600 [4:16:53<5:36:37,  1.64it/s]
 42%|████▏     | 24469/57600 [4:16:53<5:45:25,  1.60it/s]
 42%|████▏     | 24470/57600 [4:16:54<5:39:22,  1.63it/s]
 42%|████▏     | 24471/57600 [4:16:54<5:33:55,  1.65it/s]
 42%|████▏     | 24472/57600 [4:16:55<5:29:49,  1.67it/s]
 42%|████▏     | 24473/57600 [4:16:56<5:38:02,  1.63it/s]
 42%|████▏     | 24474/57600 [4:16:56<5:38:04,  1.63it/s]
 42%|████▏     | 24475/57600 [4:16:57<5:37:56,  1.63it/s]
 42%|████▏     | 24476/57600 [4:16:57<5:35:29,  1.65it/s]
 42%|████▏     | 24477/57600 [4:16:58<5:27:13,  1.69it/s]
 42%|████▏     | 24478/57600 [4:16:59<5:45:18,  1.60it/s]
 42%|████▏     | 24479/57600 [4:16:59<5:37:31,  1.64it/s]
 42%|████▎     | 24480/57600 [4:17:00<5:41:06,  1.62it/s]
                                                         
{'loss': 1.2206, 'learning_rate': 6.193031358885017e-07, 'epoch': 270.2}

 42%|████▎     | 24480/57600 [4:17:00<5:41:06,  1.62it/s]
 43%|████▎     | 24481/57600 [4:17:01<5:41:06,  1.62it/s]
 43%|████▎     | 24482/57600 [4:17:01<5:52:50,  1.56it/s]
 43%|████▎     | 24483/57600 [4:17:02<5:38:47,  1.63it/s]
 43%|████▎     | 24484/57600 [4:17:02<5:47:24,  1.59it/s]
 43%|████▎     | 24485/57600 [4:17:03<5:42:49,  1.61it/s]
 43%|████▎     | 24486/57600 [4:17:04<5:45:43,  1.60it/s]
 43%|████▎     | 24487/57600 [4:17:04<5:37:32,  1.63it/s]
 43%|████▎     | 24488/57600 [4:17:05<5:36:59,  1.64it/s]
 43%|████▎     | 24489/57600 [4:17:06<5:48:26,  1.58it/s]
 43%|████▎     | 24490/57600 [4:17:06<5:58:08,  1.54it/s]
 43%|████▎     | 24491/57600 [4:17:07<5:50:49,  1.57it/s]
 43%|████▎     | 24492/57600 [4:17:07<5:44:06,  1.60it/s]
 43%|████▎     | 24493/57600 [4:17:08<5:52:28,  1.57it/s]
 43%|████▎     | 24494/57600 [4:17:09<5:53:17,  1.56it/s]
 43%|████▎     | 24495/57600 [4:17:10<6:08:06,  1.50it/s]
 43%|████▎     | 24496/57600 [4:17:10<5:51:07,  1.57it/s]
 43%|████▎     | 24497/57600 [4:17:11<5:53:49,  1.56it/s]
 43%|████▎     | 24498/57600 [4:17:11<5:53:08,  1.56it/s]
 43%|████▎     | 24499/57600 [4:17:12<5:46:32,  1.59it/s]
 43%|████▎     | 24500/57600 [4:17:13<5:50:48,  1.57it/s]
                                                         
{'loss': 1.201, 'learning_rate': 6.189895470383275e-07, 'epoch': 270.42}

 43%|████▎     | 24500/57600 [4:17:13<5:50:48,  1.57it/s]
 43%|████▎     | 24501/57600 [4:17:13<5:37:58,  1.63it/s]
 43%|████▎     | 24502/57600 [4:17:14<5:43:06,  1.61it/s]
 43%|████▎     | 24503/57600 [4:17:14<5:43:18,  1.61it/s]
 43%|████▎     | 24504/57600 [4:17:15<5:43:57,  1.60it/s]
 43%|████▎     | 24505/57600 [4:17:16<5:46:14,  1.59it/s]
 43%|████▎     | 24506/57600 [4:17:16<5:45:26,  1.60it/s]
 43%|████▎     | 24507/57600 [4:17:17<5:44:52,  1.60it/s]
 43%|████▎     | 24508/57600 [4:17:18<5:43:46,  1.60it/s]
 43%|████▎     | 24509/57600 [4:17:18<5:40:06,  1.62it/s]
 43%|████▎     | 24510/57600 [4:17:19<5:41:26,  1.62it/s]
 43%|████▎     | 24511/57600 [4:17:19<5:37:26,  1.63it/s]
 43%|████▎     | 24512/57600 [4:17:20<5:39:38,  1.62it/s]
 43%|████▎     | 24513/57600 [4:17:21<5:41:27,  1.61it/s]
 43%|████▎     | 24514/57600 [4:17:21<5:44:17,  1.60it/s]
 43%|████▎     | 24515/57600 [4:17:22<5:51:31,  1.57it/s]
 43%|████▎     | 24516/57600 [4:17:23<5:45:48,  1.59it/s]
 43%|████▎     | 24517/57600 [4:17:23<5:43:17,  1.61it/s]
 43%|████▎     | 24518/57600 [4:17:24<5:40:20,  1.62it/s]
 43%|████▎     | 24519/57600 [4:17:24<5:40:10,  1.62it/s]
 43%|████▎     | 24520/57600 [4:17:25<5:33:37,  1.65it/s]
                                                         
{'loss': 1.245, 'learning_rate': 6.186759581881533e-07, 'epoch': 270.64}

 43%|████▎     | 24520/57600 [4:17:25<5:33:37,  1.65it/s]
 43%|████▎     | 24521/57600 [4:17:26<5:40:36,  1.62it/s]
 43%|████▎     | 24522/57600 [4:17:26<5:52:39,  1.56it/s]
 43%|████▎     | 24523/57600 [4:17:27<5:57:26,  1.54it/s]
 43%|████▎     | 24524/57600 [4:17:28<5:56:58,  1.54it/s]
 43%|████▎     | 24525/57600 [4:17:28<5:56:36,  1.55it/s]
 43%|████▎     | 24526/57600 [4:17:29<5:53:06,  1.56it/s]
 43%|████▎     | 24527/57600 [4:17:30<5:48:15,  1.58it/s]
 43%|████▎     | 24528/57600 [4:17:30<5:53:52,  1.56it/s]
 43%|████▎     | 24529/57600 [4:17:31<5:39:36,  1.62it/s]
 43%|████▎     | 24530/57600 [4:17:31<5:36:54,  1.64it/s]
 43%|████▎     | 24531/57600 [4:17:32<5:41:08,  1.62it/s]
 43%|████▎     | 24532/57600 [4:17:33<5:37:28,  1.63it/s]
 43%|████▎     | 24533/57600 [4:17:33<5:32:42,  1.66it/s]
 43%|████▎     | 24534/57600 [4:17:34<5:41:14,  1.62it/s]
 43%|████▎     | 24535/57600 [4:17:34<5:33:55,  1.65it/s]
 43%|████▎     | 24536/57600 [4:17:35<5:44:57,  1.60it/s]
 43%|████▎     | 24537/57600 [4:17:36<5:48:29,  1.58it/s]
 43%|████▎     | 24538/57600 [4:17:36<5:55:42,  1.55it/s]
 43%|████▎     | 24539/57600 [4:17:37<5:49:05,  1.58it/s]
 43%|████▎     | 24540/57600 [4:17:38<5:48:13,  1.58it/s]
                                                         
{'loss': 1.1934, 'learning_rate': 6.183623693379791e-07, 'epoch': 270.86}

 43%|████▎     | 24540/57600 [4:17:38<5:48:13,  1.58it/s]
 43%|████▎     | 24541/57600 [4:17:38<5:51:51,  1.57it/s]
 43%|████▎     | 24542/57600 [4:17:39<5:47:08,  1.59it/s]
 43%|████▎     | 24543/57600 [4:17:39<5:30:58,  1.66it/s]
 43%|████▎     | 24544/57600 [4:17:40<5:36:04,  1.64it/s]
 43%|████▎     | 24545/57600 [4:17:41<5:46:46,  1.59it/s]
 43%|████▎     | 24546/57600 [4:17:41<5:42:55,  1.61it/s]
 43%|████▎     | 24547/57600 [4:17:42<5:36:25,  1.64it/s]
 43%|████▎     | 24548/57600 [4:17:43<5:36:36,  1.64it/s]
 43%|████▎     | 24549/57600 [4:17:43<5:37:54,  1.63it/s]
 43%|████▎     | 24550/57600 [4:17:44<5:30:48,  1.67it/s]
 43%|████▎     | 24551/57600 [4:17:44<5:22:23,  1.71it/s]
 43%|████▎     | 24552/57600 [4:17:45<5:34:07,  1.65it/s]
 43%|████▎     | 24553/57600 [4:17:46<5:51:13,  1.57it/s]
 43%|████▎     | 24554/57600 [4:17:46<5:52:58,  1.56it/s]
 43%|████▎     | 24555/57600 [4:17:47<5:42:57,  1.61it/s]
 43%|████▎     | 24556/57600 [4:17:48<5:46:07,  1.59it/s]
 43%|████▎     | 24557/57600 [4:17:48<5:47:04,  1.59it/s]
 43%|████▎     | 24558/57600 [4:17:49<5:42:36,  1.61it/s]
 43%|████▎     | 24559/57600 [4:17:49<5:41:49,  1.61it/s]
 43%|████▎     | 24560/57600 [4:17:50<5:36:23,  1.64it/s]
                                                         
{'loss': 1.2011, 'learning_rate': 6.180487804878049e-07, 'epoch': 271.08}

 43%|████▎     | 24560/57600 [4:17:50<5:36:23,  1.64it/s]
 43%|████▎     | 24561/57600 [4:17:51<5:37:49,  1.63it/s]
 43%|████▎     | 24562/57600 [4:17:51<5:31:09,  1.66it/s]
 43%|████▎     | 24563/57600 [4:17:52<5:24:39,  1.70it/s]
 43%|████▎     | 24564/57600 [4:17:52<5:23:42,  1.70it/s]
 43%|████▎     | 24565/57600 [4:17:53<5:24:24,  1.70it/s]
 43%|████▎     | 24566/57600 [4:17:54<5:32:50,  1.65it/s]
 43%|████▎     | 24567/57600 [4:17:54<5:45:40,  1.59it/s]
 43%|████▎     | 24568/57600 [4:17:55<5:46:54,  1.59it/s]
 43%|████▎     | 24569/57600 [4:17:55<5:40:22,  1.62it/s]
 43%|████▎     | 24570/57600 [4:17:56<5:54:04,  1.55it/s]
 43%|████▎     | 24571/57600 [4:17:57<5:45:12,  1.59it/s]
 43%|████▎     | 24572/57600 [4:17:57<5:38:09,  1.63it/s]
 43%|████▎     | 24573/57600 [4:17:58<5:38:14,  1.63it/s]
 43%|████▎     | 24574/57600 [4:17:59<5:33:17,  1.65it/s]
 43%|████▎     | 24575/57600 [4:17:59<5:39:56,  1.62it/s]
 43%|████▎     | 24576/57600 [4:18:00<5:39:21,  1.62it/s]
 43%|████▎     | 24577/57600 [4:18:00<5:38:40,  1.63it/s]
 43%|████▎     | 24578/57600 [4:18:01<5:37:38,  1.63it/s]
 43%|████▎     | 24579/57600 [4:18:02<5:33:36,  1.65it/s]
 43%|████▎     | 24580/57600 [4:18:02<5:36:08,  1.64it/s]
                                                         
{'loss': 1.2161, 'learning_rate': 6.177351916376306e-07, 'epoch': 271.3}

 43%|████▎     | 24580/57600 [4:18:02<5:36:08,  1.64it/s]
 43%|████▎     | 24581/57600 [4:18:03<5:27:41,  1.68it/s]
 43%|████▎     | 24582/57600 [4:18:03<5:24:02,  1.70it/s]
 43%|████▎     | 24583/57600 [4:18:04<5:22:02,  1.71it/s]
 43%|████▎     | 24584/57600 [4:18:05<5:24:14,  1.70it/s]
 43%|████▎     | 24585/57600 [4:18:05<5:24:34,  1.70it/s]
 43%|████▎     | 24586/57600 [4:18:06<5:24:20,  1.70it/s]
 43%|████▎     | 24587/57600 [4:18:06<5:41:17,  1.61it/s]
 43%|████▎     | 24588/57600 [4:18:07<5:45:36,  1.59it/s]
 43%|████▎     | 24589/57600 [4:18:08<5:36:12,  1.64it/s]
 43%|████▎     | 24590/57600 [4:18:08<5:27:37,  1.68it/s]
 43%|████▎     | 24591/57600 [4:18:09<5:30:39,  1.66it/s]
 43%|████▎     | 24592/57600 [4:18:09<5:49:58,  1.57it/s]
 43%|████▎     | 24593/57600 [4:18:10<5:59:13,  1.53it/s]
 43%|████▎     | 24594/57600 [4:18:11<5:55:39,  1.55it/s]
 43%|████▎     | 24595/57600 [4:18:11<5:49:25,  1.57it/s]
 43%|████▎     | 24596/57600 [4:18:12<5:37:12,  1.63it/s]
 43%|████▎     | 24597/57600 [4:18:13<5:40:48,  1.61it/s]
 43%|████▎     | 24598/57600 [4:18:13<5:37:42,  1.63it/s]
 43%|████▎     | 24599/57600 [4:18:14<5:32:05,  1.66it/s]
 43%|████▎     | 24600/57600 [4:18:14<5:30:28,  1.66it/s]
                                                         
{'loss': 1.2299, 'learning_rate': 6.174216027874564e-07, 'epoch': 271.52}

 43%|████▎     | 24600/57600 [4:18:14<5:30:28,  1.66it/s]
 43%|████▎     | 24601/57600 [4:18:15<5:31:24,  1.66it/s]
 43%|████▎     | 24602/57600 [4:18:16<5:29:06,  1.67it/s]
 43%|████▎     | 24603/57600 [4:18:16<5:41:18,  1.61it/s]
 43%|████▎     | 24604/57600 [4:18:17<5:40:32,  1.61it/s]
 43%|████▎     | 24605/57600 [4:18:18<5:42:50,  1.60it/s]
 43%|████▎     | 24606/57600 [4:18:18<5:50:02,  1.57it/s]
 43%|████▎     | 24607/57600 [4:18:19<5:55:48,  1.55it/s]
 43%|████▎     | 24608/57600 [4:18:19<5:57:08,  1.54it/s]
 43%|████▎     | 24609/57600 [4:18:20<5:52:05,  1.56it/s]
 43%|████▎     | 24610/57600 [4:18:21<5:48:50,  1.58it/s]
 43%|████▎     | 24611/57600 [4:18:21<5:45:53,  1.59it/s]
 43%|████▎     | 24612/57600 [4:18:22<5:35:50,  1.64it/s]
 43%|████▎     | 24613/57600 [4:18:23<5:39:00,  1.62it/s]
 43%|████▎     | 24614/57600 [4:18:23<5:48:14,  1.58it/s]
 43%|████▎     | 24615/57600 [4:18:24<5:38:13,  1.63it/s]
 43%|████▎     | 24616/57600 [4:18:24<5:43:20,  1.60it/s]
 43%|████▎     | 24617/57600 [4:18:25<5:52:34,  1.56it/s]
 43%|████▎     | 24618/57600 [4:18:26<5:46:29,  1.59it/s]
 43%|████▎     | 24619/57600 [4:18:26<5:46:25,  1.59it/s]
 43%|████▎     | 24620/57600 [4:18:27<5:48:16,  1.58it/s]
                                                         
{'loss': 1.1873, 'learning_rate': 6.171080139372821e-07, 'epoch': 271.74}

 43%|████▎     | 24620/57600 [4:18:27<5:48:16,  1.58it/s]
 43%|████▎     | 24621/57600 [4:18:28<5:51:58,  1.56it/s]
 43%|████▎     | 24622/57600 [4:18:28<5:50:35,  1.57it/s]
 43%|████▎     | 24623/57600 [4:18:29<5:49:22,  1.57it/s]
 43%|████▎     | 24624/57600 [4:18:30<5:41:33,  1.61it/s]
 43%|████▎     | 24625/57600 [4:18:30<5:43:15,  1.60it/s]
 43%|████▎     | 24626/57600 [4:18:31<5:46:45,  1.58it/s]
 43%|████▎     | 24627/57600 [4:18:31<5:54:43,  1.55it/s]
 43%|████▎     | 24628/57600 [4:18:32<5:40:39,  1.61it/s]
 43%|████▎     | 24629/57600 [4:18:33<5:44:22,  1.60it/s]
 43%|████▎     | 24630/57600 [4:18:33<5:41:46,  1.61it/s]
 43%|████▎     | 24631/57600 [4:18:34<5:34:42,  1.64it/s]
 43%|████▎     | 24632/57600 [4:18:34<5:33:31,  1.65it/s]
 43%|████▎     | 24633/57600 [4:18:35<5:29:33,  1.67it/s]
 43%|████▎     | 24634/57600 [4:18:36<5:18:24,  1.73it/s]
 43%|████▎     | 24635/57600 [4:18:36<5:22:24,  1.70it/s]
 43%|████▎     | 24636/57600 [4:18:37<5:42:41,  1.60it/s]
 43%|████▎     | 24637/57600 [4:18:38<5:44:58,  1.59it/s]
 43%|████▎     | 24638/57600 [4:18:38<5:43:34,  1.60it/s]
 43%|████▎     | 24639/57600 [4:18:39<5:38:19,  1.62it/s]
 43%|████▎     | 24640/57600 [4:18:39<5:34:27,  1.64it/s]
                                                         
{'loss': 1.2246, 'learning_rate': 6.16794425087108e-07, 'epoch': 271.96}

 43%|████▎     | 24640/57600 [4:18:39<5:34:27,  1.64it/s]
 43%|████▎     | 24641/57600 [4:18:40<5:44:42,  1.59it/s]
 43%|████▎     | 24642/57600 [4:18:41<5:42:37,  1.60it/s]
 43%|████▎     | 24643/57600 [4:18:41<5:36:07,  1.63it/s]
 43%|████▎     | 24644/57600 [4:18:42<5:53:00,  1.56it/s]
 43%|████▎     | 24645/57600 [4:18:43<5:44:47,  1.59it/s]
 43%|████▎     | 24646/57600 [4:18:43<5:42:48,  1.60it/s]
 43%|████▎     | 24647/57600 [4:18:44<5:38:02,  1.62it/s]
 43%|████▎     | 24648/57600 [4:18:44<5:39:48,  1.62it/s]
 43%|████▎     | 24649/57600 [4:18:45<5:30:36,  1.66it/s]
 43%|████▎     | 24650/57600 [4:18:46<5:32:45,  1.65it/s]
 43%|████▎     | 24651/57600 [4:18:46<5:41:29,  1.61it/s]
 43%|████▎     | 24652/57600 [4:18:47<5:37:20,  1.63it/s]
 43%|████▎     | 24653/57600 [4:18:47<5:31:43,  1.66it/s]
 43%|████▎     | 24654/57600 [4:18:48<5:26:02,  1.68it/s]
 43%|████▎     | 24655/57600 [4:18:49<5:37:34,  1.63it/s]
 43%|████▎     | 24656/57600 [4:18:49<5:37:08,  1.63it/s]
 43%|████▎     | 24657/57600 [4:18:50<5:36:56,  1.63it/s]
 43%|████▎     | 24658/57600 [4:18:50<5:45:06,  1.59it/s]
 43%|████▎     | 24659/57600 [4:18:51<5:41:50,  1.61it/s]
 43%|████▎     | 24660/57600 [4:18:52<5:43:51,  1.60it/s]
                                                         
{'loss': 1.251, 'learning_rate': 6.164808362369337e-07, 'epoch': 272.19}

 43%|████▎     | 24660/57600 [4:18:52<5:43:51,  1.60it/s]
 43%|████▎     | 24661/57600 [4:18:52<5:32:44,  1.65it/s]
 43%|████▎     | 24662/57600 [4:18:53<5:35:16,  1.64it/s]
 43%|████▎     | 24663/57600 [4:18:54<5:39:59,  1.61it/s]
 43%|████▎     | 24664/57600 [4:18:54<5:43:35,  1.60it/s]
 43%|████▎     | 24665/57600 [4:18:55<5:32:22,  1.65it/s]
 43%|████▎     | 24666/57600 [4:18:55<5:34:22,  1.64it/s]
 43%|████▎     | 24667/57600 [4:18:56<5:41:49,  1.61it/s]
 43%|████▎     | 24668/57600 [4:18:57<5:31:06,  1.66it/s]
 43%|████▎     | 24669/57600 [4:18:57<5:34:51,  1.64it/s]
 43%|████▎     | 24670/57600 [4:18:58<5:32:18,  1.65it/s]
 43%|████▎     | 24671/57600 [4:18:58<5:41:03,  1.61it/s]
 43%|████▎     | 24672/57600 [4:18:59<5:48:39,  1.57it/s]
 43%|████▎     | 24673/57600 [4:19:00<5:43:06,  1.60it/s]
 43%|████▎     | 24674/57600 [4:19:00<5:50:05,  1.57it/s]
 43%|████▎     | 24675/57600 [4:19:01<5:38:37,  1.62it/s]
 43%|████▎     | 24676/57600 [4:19:02<5:34:03,  1.64it/s]
 43%|████▎     | 24677/57600 [4:19:02<5:35:05,  1.64it/s]
 43%|████▎     | 24678/57600 [4:19:03<5:28:47,  1.67it/s]
 43%|████▎     | 24679/57600 [4:19:03<5:30:30,  1.66it/s]
 43%|████▎     | 24680/57600 [4:19:04<5:45:04,  1.59it/s]
                                                         
{'loss': 1.2046, 'learning_rate': 6.161672473867596e-07, 'epoch': 272.41}

 43%|████▎     | 24680/57600 [4:19:04<5:45:04,  1.59it/s]
 43%|████▎     | 24681/57600 [4:19:05<5:37:00,  1.63it/s]
 43%|████▎     | 24682/57600 [4:19:05<5:45:13,  1.59it/s]
 43%|████▎     | 24683/57600 [4:19:06<5:43:26,  1.60it/s]
 43%|████▎     | 24684/57600 [4:19:06<5:33:06,  1.65it/s]
 43%|████▎     | 24685/57600 [4:19:07<5:31:30,  1.65it/s]
 43%|████▎     | 24686/57600 [4:19:08<5:25:58,  1.68it/s]
 43%|████▎     | 24687/57600 [4:19:08<5:28:36,  1.67it/s]
 43%|████▎     | 24688/57600 [4:19:09<5:31:26,  1.65it/s]
 43%|████▎     | 24689/57600 [4:19:09<5:21:51,  1.70it/s]
 43%|████▎     | 24690/57600 [4:19:10<5:25:43,  1.68it/s]
 43%|████▎     | 24691/57600 [4:19:11<5:28:27,  1.67it/s]
 43%|████▎     | 24692/57600 [4:19:11<5:36:06,  1.63it/s]
 43%|████▎     | 24693/57600 [4:19:12<5:29:52,  1.66it/s]
 43%|████▎     | 24694/57600 [4:19:12<5:32:12,  1.65it/s]
 43%|████▎     | 24695/57600 [4:19:13<5:51:03,  1.56it/s]
 43%|████▎     | 24696/57600 [4:19:14<5:50:00,  1.57it/s]
 43%|████▎     | 24697/57600 [4:19:14<5:42:32,  1.60it/s]
 43%|████▎     | 24698/57600 [4:19:15<5:30:46,  1.66it/s]
 43%|████▎     | 24699/57600 [4:19:16<5:31:52,  1.65it/s]
 43%|████▎     | 24700/57600 [4:19:16<5:39:56,  1.61it/s]
                                                         
{'loss': 1.2391, 'learning_rate': 6.158536585365853e-07, 'epoch': 272.63}

 43%|████▎     | 24700/57600 [4:19:16<5:39:56,  1.61it/s]
 43%|████▎     | 24701/57600 [4:19:17<5:36:16,  1.63it/s]
 43%|████▎     | 24702/57600 [4:19:17<5:32:41,  1.65it/s]
 43%|████▎     | 24703/57600 [4:19:18<5:44:43,  1.59it/s]
 43%|████▎     | 24704/57600 [4:19:19<5:55:54,  1.54it/s]
 43%|████▎     | 24705/57600 [4:19:19<5:38:54,  1.62it/s]
 43%|████▎     | 24706/57600 [4:19:20<5:34:04,  1.64it/s]
 43%|████▎     | 24707/57600 [4:19:21<5:29:57,  1.66it/s]
 43%|████▎     | 24708/57600 [4:19:21<5:27:48,  1.67it/s]
 43%|████▎     | 24709/57600 [4:19:22<5:30:52,  1.66it/s]
 43%|████▎     | 24710/57600 [4:19:22<5:31:37,  1.65it/s]
 43%|████▎     | 24711/57600 [4:19:23<5:39:32,  1.61it/s]
 43%|████▎     | 24712/57600 [4:19:24<5:36:52,  1.63it/s]
 43%|████▎     | 24713/57600 [4:19:24<5:37:51,  1.62it/s]
 43%|████▎     | 24714/57600 [4:19:25<5:51:32,  1.56it/s]
 43%|████▎     | 24715/57600 [4:19:26<5:52:47,  1.55it/s]
 43%|████▎     | 24716/57600 [4:19:26<6:00:38,  1.52it/s]
 43%|████▎     | 24717/57600 [4:19:27<5:58:35,  1.53it/s]
 43%|████▎     | 24718/57600 [4:19:28<5:53:51,  1.55it/s]
 43%|████▎     | 24719/57600 [4:19:28<5:44:55,  1.59it/s]
 43%|████▎     | 24720/57600 [4:19:29<5:37:15,  1.62it/s]
                                                         
{'loss': 1.2197, 'learning_rate': 6.155400696864111e-07, 'epoch': 272.85}

 43%|████▎     | 24720/57600 [4:19:29<5:37:15,  1.62it/s]
 43%|████▎     | 24721/57600 [4:19:29<5:34:45,  1.64it/s]
 43%|████▎     | 24722/57600 [4:19:30<5:24:30,  1.69it/s]
 43%|████▎     | 24723/57600 [4:19:30<5:26:22,  1.68it/s]
 43%|████▎     | 24724/57600 [4:19:31<5:30:55,  1.66it/s]
 43%|████▎     | 24725/57600 [4:19:32<5:39:42,  1.61it/s]
 43%|████▎     | 24726/57600 [4:19:32<5:33:37,  1.64it/s]
 43%|████▎     | 24727/57600 [4:19:33<5:59:36,  1.52it/s]
 43%|████▎     | 24728/57600 [4:19:34<6:04:51,  1.50it/s]
 43%|████▎     | 24729/57600 [4:19:34<5:56:32,  1.54it/s]
 43%|████▎     | 24730/57600 [4:19:35<5:46:19,  1.58it/s]
 43%|████▎     | 24731/57600 [4:19:36<5:40:11,  1.61it/s]
 43%|████▎     | 24732/57600 [4:19:36<5:36:06,  1.63it/s]
 43%|████▎     | 24733/57600 [4:19:37<5:40:05,  1.61it/s]
 43%|████▎     | 24734/57600 [4:19:37<5:45:42,  1.58it/s]
 43%|████▎     | 24735/57600 [4:19:38<5:46:45,  1.58it/s]
 43%|████▎     | 24736/57600 [4:19:39<5:42:33,  1.60it/s]
 43%|████▎     | 24737/57600 [4:19:39<5:41:37,  1.60it/s]
 43%|████▎     | 24738/57600 [4:19:40<5:47:30,  1.58it/s]
 43%|████▎     | 24739/57600 [4:19:41<5:42:24,  1.60it/s]
 43%|████▎     | 24740/57600 [4:19:41<5:42:06,  1.60it/s]
                                                         
{'loss': 1.1918, 'learning_rate': 6.152264808362369e-07, 'epoch': 273.07}

 43%|████▎     | 24740/57600 [4:19:41<5:42:06,  1.60it/s]
 43%|████▎     | 24741/57600 [4:19:42<5:37:56,  1.62it/s]
 43%|████▎     | 24742/57600 [4:19:42<5:31:28,  1.65it/s]
 43%|████▎     | 24743/57600 [4:19:43<5:37:41,  1.62it/s]
 43%|████▎     | 24744/57600 [4:19:44<5:29:24,  1.66it/s]
 43%|████▎     | 24745/57600 [4:19:44<5:32:15,  1.65it/s]
 43%|████▎     | 24746/57600 [4:19:45<5:25:43,  1.68it/s]
 43%|████▎     | 24747/57600 [4:19:45<5:21:30,  1.70it/s]
 43%|████▎     | 24748/57600 [4:19:46<5:41:21,  1.60it/s]
 43%|████▎     | 24749/57600 [4:19:47<5:37:01,  1.62it/s]
 43%|████▎     | 24750/57600 [4:19:47<5:29:59,  1.66it/s]
 43%|████▎     | 24751/57600 [4:19:48<5:38:00,  1.62it/s]
 43%|████▎     | 24752/57600 [4:19:48<5:37:16,  1.62it/s]
 43%|████▎     | 24753/57600 [4:19:49<5:33:37,  1.64it/s]
 43%|████▎     | 24754/57600 [4:19:50<5:37:49,  1.62it/s]
 43%|████▎     | 24755/57600 [4:19:50<5:28:38,  1.67it/s]
 43%|████▎     | 24756/57600 [4:19:51<5:22:53,  1.70it/s]
 43%|████▎     | 24757/57600 [4:19:52<5:41:48,  1.60it/s]
 43%|████▎     | 24758/57600 [4:19:52<5:32:25,  1.65it/s]
 43%|████▎     | 24759/57600 [4:19:53<5:27:07,  1.67it/s]
 43%|████▎     | 24760/57600 [4:19:53<5:42:33,  1.60it/s]
                                                         
{'loss': 1.2409, 'learning_rate': 6.149128919860627e-07, 'epoch': 273.29}

 43%|████▎     | 24760/57600 [4:19:53<5:42:33,  1.60it/s]
 43%|████▎     | 24761/57600 [4:19:54<5:44:02,  1.59it/s]
 43%|████▎     | 24762/57600 [4:19:55<5:41:44,  1.60it/s]
 43%|████▎     | 24763/57600 [4:19:55<5:47:02,  1.58it/s]
 43%|████▎     | 24764/57600 [4:19:56<5:36:57,  1.62it/s]
 43%|████▎     | 24765/57600 [4:19:57<5:41:22,  1.60it/s]
 43%|████▎     | 24766/57600 [4:19:57<5:36:29,  1.63it/s]
 43%|████▎     | 24767/57600 [4:19:58<5:35:38,  1.63it/s]
 43%|████▎     | 24768/57600 [4:19:58<5:36:25,  1.63it/s]
 43%|████▎     | 24769/57600 [4:19:59<5:38:02,  1.62it/s]
 43%|████▎     | 24770/57600 [4:20:00<5:33:56,  1.64it/s]
 43%|████▎     | 24771/57600 [4:20:00<5:30:24,  1.66it/s]
 43%|████▎     | 24772/57600 [4:20:01<5:25:27,  1.68it/s]
 43%|████▎     | 24773/57600 [4:20:01<5:20:55,  1.70it/s]
 43%|████▎     | 24774/57600 [4:20:02<5:18:36,  1.72it/s]
 43%|████▎     | 24775/57600 [4:20:02<5:25:04,  1.68it/s]
 43%|████▎     | 24776/57600 [4:20:03<5:30:09,  1.66it/s]
 43%|████▎     | 24777/57600 [4:20:04<5:43:22,  1.59it/s]
 43%|████▎     | 24778/57600 [4:20:05<5:59:58,  1.52it/s]
 43%|████▎     | 24779/57600 [4:20:05<5:47:15,  1.58it/s]
 43%|████▎     | 24780/57600 [4:20:06<5:44:43,  1.59it/s]
                                                         
{'loss': 1.2091, 'learning_rate': 6.145993031358885e-07, 'epoch': 273.51}

 43%|████▎     | 24780/57600 [4:20:06<5:44:43,  1.59it/s]
 43%|████▎     | 24781/57600 [4:20:06<5:55:15,  1.54it/s]
 43%|████▎     | 24782/57600 [4:20:07<5:48:12,  1.57it/s]
 43%|████▎     | 24783/57600 [4:20:08<5:39:08,  1.61it/s]
 43%|████▎     | 24784/57600 [4:20:08<5:40:58,  1.60it/s]
 43%|████▎     | 24785/57600 [4:20:09<5:48:17,  1.57it/s]
 43%|████▎     | 24786/57600 [4:20:09<5:36:53,  1.62it/s]
 43%|████▎     | 24787/57600 [4:20:10<5:34:54,  1.63it/s]
 43%|████▎     | 24788/57600 [4:20:11<5:36:22,  1.63it/s]
 43%|████▎     | 24789/57600 [4:20:11<5:36:20,  1.63it/s]
 43%|████▎     | 24790/57600 [4:20:12<5:26:40,  1.67it/s]
 43%|████▎     | 24791/57600 [4:20:12<5:25:22,  1.68it/s]
 43%|████▎     | 24792/57600 [4:20:13<5:35:47,  1.63it/s]
 43%|████▎     | 24793/57600 [4:20:14<5:37:23,  1.62it/s]
 43%|████▎     | 24794/57600 [4:20:14<5:41:47,  1.60it/s]
 43%|████▎     | 24795/57600 [4:20:15<5:30:18,  1.66it/s]
 43%|████▎     | 24796/57600 [4:20:16<5:33:16,  1.64it/s]
 43%|████▎     | 24797/57600 [4:20:16<5:32:58,  1.64it/s]
 43%|████▎     | 24798/57600 [4:20:17<5:36:57,  1.62it/s]
 43%|████▎     | 24799/57600 [4:20:17<5:31:18,  1.65it/s]
 43%|████▎     | 24800/57600 [4:20:18<5:41:13,  1.60it/s]
                                                         
{'loss': 1.1942, 'learning_rate': 6.142857142857142e-07, 'epoch': 273.73}

 43%|████▎     | 24800/57600 [4:20:18<5:41:13,  1.60it/s]
 43%|████▎     | 24801/57600 [4:20:19<5:33:26,  1.64it/s]
 43%|████▎     | 24802/57600 [4:20:19<5:24:59,  1.68it/s]
 43%|████▎     | 24803/57600 [4:20:20<5:38:07,  1.62it/s]
 43%|████▎     | 24804/57600 [4:20:20<5:37:40,  1.62it/s]
 43%|████▎     | 24805/57600 [4:20:21<5:40:55,  1.60it/s]
 43%|████▎     | 24806/57600 [4:20:22<5:43:35,  1.59it/s]
 43%|████▎     | 24807/57600 [4:20:22<5:46:31,  1.58it/s]
 43%|████▎     | 24808/57600 [4:20:23<5:32:43,  1.64it/s]
 43%|████▎     | 24809/57600 [4:20:24<5:35:42,  1.63it/s]
 43%|████▎     | 24810/57600 [4:20:24<5:51:15,  1.56it/s]
 43%|████▎     | 24811/57600 [4:20:25<6:00:08,  1.52it/s]
 43%|████▎     | 24812/57600 [4:20:26<5:52:20,  1.55it/s]
 43%|████▎     | 24813/57600 [4:20:26<5:53:46,  1.54it/s]
 43%|████▎     | 24814/57600 [4:20:27<5:45:35,  1.58it/s]
 43%|████▎     | 24815/57600 [4:20:27<5:44:37,  1.59it/s]
 43%|████▎     | 24816/57600 [4:20:28<5:29:49,  1.66it/s]
 43%|████▎     | 24817/57600 [4:20:29<5:30:52,  1.65it/s]
 43%|████▎     | 24818/57600 [4:20:29<5:23:13,  1.69it/s]
 43%|████▎     | 24819/57600 [4:20:30<5:29:33,  1.66it/s]
 43%|████▎     | 24820/57600 [4:20:30<5:33:49,  1.64it/s]
                                                         
{'loss': 1.2063, 'learning_rate': 6.139721254355401e-07, 'epoch': 273.95}

 43%|████▎     | 24820/57600 [4:20:30<5:33:49,  1.64it/s]
 43%|████▎     | 24821/57600 [4:20:31<5:26:41,  1.67it/s]
 43%|████▎     | 24822/57600 [4:20:32<5:30:40,  1.65it/s]
 43%|████▎     | 24823/57600 [4:20:32<5:31:40,  1.65it/s]
 43%|████▎     | 24824/57600 [4:20:33<5:34:49,  1.63it/s]
 43%|████▎     | 24825/57600 [4:20:34<5:45:11,  1.58it/s]
 43%|████▎     | 24826/57600 [4:20:34<5:54:12,  1.54it/s]
 43%|████▎     | 24827/57600 [4:20:35<5:50:46,  1.56it/s]
 43%|████▎     | 24828/57600 [4:20:35<5:50:44,  1.56it/s]
 43%|████▎     | 24829/57600 [4:20:36<5:59:48,  1.52it/s]
 43%|████▎     | 24830/57600 [4:20:37<5:44:45,  1.58it/s]
 43%|████▎     | 24831/57600 [4:20:37<5:55:40,  1.54it/s]
 43%|████▎     | 24832/57600 [4:20:38<5:51:51,  1.55it/s]
 43%|████▎     | 24833/57600 [4:20:39<5:39:46,  1.61it/s]
 43%|████▎     | 24834/57600 [4:20:39<5:34:20,  1.63it/s]
 43%|████▎     | 24835/57600 [4:20:40<5:28:33,  1.66it/s]
 43%|████▎     | 24836/57600 [4:20:40<5:21:32,  1.70it/s]
 43%|████▎     | 24837/57600 [4:20:41<5:20:34,  1.70it/s]
 43%|████▎     | 24838/57600 [4:20:42<5:31:13,  1.65it/s]
 43%|████▎     | 24839/57600 [4:20:42<5:25:04,  1.68it/s]
 43%|████▎     | 24840/57600 [4:20:43<5:23:50,  1.69it/s]
                                                         
{'loss': 1.215, 'learning_rate': 6.136585365853659e-07, 'epoch': 274.17}

 43%|████▎     | 24840/57600 [4:20:43<5:23:50,  1.69it/s]
 43%|████▎     | 24841/57600 [4:20:43<5:31:53,  1.65it/s]
 43%|████▎     | 24842/57600 [4:20:44<5:31:07,  1.65it/s]
 43%|████▎     | 24843/57600 [4:20:45<5:25:30,  1.68it/s]
 43%|████▎     | 24844/57600 [4:20:45<5:26:30,  1.67it/s]
 43%|████▎     | 24845/57600 [4:20:46<5:41:31,  1.60it/s]
 43%|████▎     | 24846/57600 [4:20:46<5:28:21,  1.66it/s]
 43%|████▎     | 24847/57600 [4:20:47<5:26:45,  1.67it/s]
 43%|████▎     | 24848/57600 [4:20:48<5:22:31,  1.69it/s]
 43%|████▎     | 24849/57600 [4:20:48<5:31:05,  1.65it/s]
 43%|████▎     | 24850/57600 [4:20:49<5:24:33,  1.68it/s]
 43%|████▎     | 24851/57600 [4:20:49<5:28:03,  1.66it/s]
 43%|████▎     | 24852/57600 [4:20:50<5:34:03,  1.63it/s]
 43%|████▎     | 24853/57600 [4:20:51<5:33:29,  1.64it/s]
 43%|████▎     | 24854/57600 [4:20:51<5:38:33,  1.61it/s]
 43%|████▎     | 24855/57600 [4:20:52<5:36:18,  1.62it/s]
 43%|████▎     | 24856/57600 [4:20:52<5:31:19,  1.65it/s]
 43%|████▎     | 24857/57600 [4:20:53<5:30:50,  1.65it/s]
 43%|████▎     | 24858/57600 [4:20:54<5:24:44,  1.68it/s]
 43%|████▎     | 24859/57600 [4:20:54<5:34:49,  1.63it/s]
 43%|████▎     | 24860/57600 [4:20:55<5:25:01,  1.68it/s]
                                                         
{'loss': 1.2067, 'learning_rate': 6.133449477351915e-07, 'epoch': 274.39}

 43%|████▎     | 24860/57600 [4:20:55<5:25:01,  1.68it/s]
 43%|████▎     | 24861/57600 [4:20:56<5:29:54,  1.65it/s]
 43%|████▎     | 24862/57600 [4:20:56<5:38:43,  1.61it/s]
 43%|████▎     | 24863/57600 [4:20:57<5:33:16,  1.64it/s]
 43%|████▎     | 24864/57600 [4:20:57<5:44:13,  1.58it/s]
 43%|████▎     | 24865/57600 [4:20:58<5:36:23,  1.62it/s]
 43%|████▎     | 24866/57600 [4:20:59<5:23:43,  1.69it/s]
 43%|████▎     | 24867/57600 [4:20:59<5:27:42,  1.66it/s]
 43%|████▎     | 24868/57600 [4:21:00<5:24:38,  1.68it/s]
 43%|████▎     | 24869/57600 [4:21:00<5:19:47,  1.71it/s]
 43%|████▎     | 24870/57600 [4:21:01<5:16:29,  1.72it/s]
 43%|████▎     | 24871/57600 [4:21:02<5:30:05,  1.65it/s]
 43%|████▎     | 24872/57600 [4:21:02<5:30:55,  1.65it/s]
 43%|████▎     | 24873/57600 [4:21:03<5:46:43,  1.57it/s]
 43%|████▎     | 24874/57600 [4:21:03<5:47:30,  1.57it/s]
 43%|████▎     | 24875/57600 [4:21:04<5:45:32,  1.58it/s]
 43%|████▎     | 24876/57600 [4:21:05<5:55:44,  1.53it/s]
 43%|████▎     | 24877/57600 [4:21:05<5:51:38,  1.55it/s]
 43%|████▎     | 24878/57600 [4:21:06<5:47:17,  1.57it/s]
 43%|████▎     | 24879/57600 [4:21:07<5:46:05,  1.58it/s]
 43%|████▎     | 24880/57600 [4:21:07<5:42:27,  1.59it/s]
                                                         
{'loss': 1.2142, 'learning_rate': 6.130313588850173e-07, 'epoch': 274.61}

 43%|████▎     | 24880/57600 [4:21:07<5:42:27,  1.59it/s]
 43%|████▎     | 24881/57600 [4:21:08<5:47:28,  1.57it/s]
 43%|████▎     | 24882/57600 [4:21:09<5:38:52,  1.61it/s]
 43%|████▎     | 24883/57600 [4:21:09<5:41:59,  1.59it/s]
 43%|████▎     | 24884/57600 [4:21:10<5:35:55,  1.62it/s]
 43%|████▎     | 24885/57600 [4:21:10<5:41:15,  1.60it/s]
 43%|████▎     | 24886/57600 [4:21:11<5:44:10,  1.58it/s]
 43%|████▎     | 24887/57600 [4:21:12<5:28:58,  1.66it/s]
 43%|████▎     | 24888/57600 [4:21:12<5:29:13,  1.66it/s]
 43%|████▎     | 24889/57600 [4:21:13<5:29:59,  1.65it/s]
 43%|████▎     | 24890/57600 [4:21:14<5:47:18,  1.57it/s]
 43%|████▎     | 24891/57600 [4:21:14<5:45:53,  1.58it/s]
 43%|████▎     | 24892/57600 [4:21:15<5:40:49,  1.60it/s]
 43%|████▎     | 24893/57600 [4:21:15<5:36:30,  1.62it/s]
 43%|████▎     | 24894/57600 [4:21:16<5:27:49,  1.66it/s]
 43%|████▎     | 24895/57600 [4:21:17<5:26:43,  1.67it/s]
 43%|████▎     | 24896/57600 [4:21:17<5:19:08,  1.71it/s]
 43%|████▎     | 24897/57600 [4:21:18<5:26:35,  1.67it/s]
 43%|████▎     | 24898/57600 [4:21:18<5:21:18,  1.70it/s]
 43%|████▎     | 24899/57600 [4:21:19<5:27:34,  1.66it/s]
 43%|████▎     | 24900/57600 [4:21:20<5:36:24,  1.62it/s]
                                                         
{'loss': 1.2379, 'learning_rate': 6.127177700348432e-07, 'epoch': 274.83}

 43%|████▎     | 24900/57600 [4:21:20<5:36:24,  1.62it/s]
 43%|████▎     | 24901/57600 [4:21:20<5:36:48,  1.62it/s]
 43%|████▎     | 24902/57600 [4:21:21<5:42:20,  1.59it/s]
 43%|████▎     | 24903/57600 [4:21:21<5:37:10,  1.62it/s]
 43%|████▎     | 24904/57600 [4:21:22<5:48:11,  1.57it/s]
 43%|████▎     | 24905/57600 [4:21:23<5:44:07,  1.58it/s]
 43%|████▎     | 24906/57600 [4:21:23<5:41:48,  1.59it/s]
 43%|████▎     | 24907/57600 [4:21:24<5:47:44,  1.57it/s]
 43%|████▎     | 24908/57600 [4:21:25<5:42:37,  1.59it/s]
 43%|████▎     | 24909/57600 [4:21:25<5:46:04,  1.57it/s]
 43%|████▎     | 24910/57600 [4:21:26<5:49:01,  1.56it/s]
 43%|████▎     | 24911/57600 [4:21:27<5:46:58,  1.57it/s]
 43%|████▎     | 24912/57600 [4:21:27<5:52:09,  1.55it/s]
 43%|████▎     | 24913/57600 [4:21:28<5:54:14,  1.54it/s]
 43%|████▎     | 24914/57600 [4:21:29<5:57:08,  1.53it/s]
 43%|████▎     | 24915/57600 [4:21:29<5:58:37,  1.52it/s]
 43%|████▎     | 24916/57600 [4:21:30<5:56:12,  1.53it/s]
 43%|████▎     | 24917/57600 [4:21:30<5:50:55,  1.55it/s]
 43%|████▎     | 24918/57600 [4:21:31<5:46:37,  1.57it/s]
 43%|████▎     | 24919/57600 [4:21:32<5:37:42,  1.61it/s]
 43%|████▎     | 24920/57600 [4:21:32<5:40:24,  1.60it/s]
                                                         
{'loss': 1.156, 'learning_rate': 6.124041811846689e-07, 'epoch': 275.06}

 43%|████▎     | 24920/57600 [4:21:32<5:40:24,  1.60it/s]
 43%|████▎     | 24921/57600 [4:21:33<5:35:34,  1.62it/s]
 43%|████▎     | 24922/57600 [4:21:34<5:38:04,  1.61it/s]
 43%|████▎     | 24923/57600 [4:21:34<5:31:23,  1.64it/s]
 43%|████▎     | 24924/57600 [4:21:35<5:25:08,  1.67it/s]
 43%|████▎     | 24925/57600 [4:21:35<5:26:10,  1.67it/s]
 43%|████▎     | 24926/57600 [4:21:36<5:22:44,  1.69it/s]
 43%|████▎     | 24927/57600 [4:21:36<5:20:31,  1.70it/s]
 43%|████▎     | 24928/57600 [4:21:37<5:31:29,  1.64it/s]
 43%|████▎     | 24929/57600 [4:21:38<5:27:57,  1.66it/s]
 43%|████▎     | 24930/57600 [4:21:38<5:29:26,  1.65it/s]
 43%|████▎     | 24931/57600 [4:21:39<5:26:29,  1.67it/s]
 43%|████▎     | 24932/57600 [4:21:39<5:20:25,  1.70it/s]
 43%|████▎     | 24933/57600 [4:21:40<5:21:25,  1.69it/s]
 43%|████▎     | 24934/57600 [4:21:41<5:17:27,  1.71it/s]
 43%|████▎     | 24935/57600 [4:21:41<5:32:16,  1.64it/s]
 43%|████▎     | 24936/57600 [4:21:42<5:21:25,  1.69it/s]
 43%|████▎     | 24937/57600 [4:21:42<5:21:21,  1.69it/s]
 43%|████▎     | 24938/57600 [4:21:43<5:24:08,  1.68it/s]
 43%|████▎     | 24939/57600 [4:21:44<5:28:23,  1.66it/s]
 43%|████▎     | 24940/57600 [4:21:44<5:30:37,  1.65it/s]
                                                         
{'loss': 1.2272, 'learning_rate': 6.120905923344947e-07, 'epoch': 275.28}

 43%|████▎     | 24940/57600 [4:21:44<5:30:37,  1.65it/s]
 43%|████▎     | 24941/57600 [4:21:45<5:42:29,  1.59it/s]
 43%|████▎     | 24942/57600 [4:21:46<5:40:47,  1.60it/s]
 43%|████▎     | 24943/57600 [4:21:46<5:41:09,  1.60it/s]
 43%|████▎     | 24944/57600 [4:21:47<5:29:00,  1.65it/s]
 43%|████▎     | 24945/57600 [4:21:47<5:27:09,  1.66it/s]
 43%|████▎     | 24946/57600 [4:21:48<5:35:46,  1.62it/s]
 43%|████▎     | 24947/57600 [4:21:49<5:42:44,  1.59it/s]
 43%|████▎     | 24948/57600 [4:21:49<5:42:51,  1.59it/s]
 43%|████▎     | 24949/57600 [4:21:50<5:42:19,  1.59it/s]
 43%|████▎     | 24950/57600 [4:21:51<5:43:28,  1.58it/s]
 43%|████▎     | 24951/57600 [4:21:51<5:50:50,  1.55it/s]
 43%|████▎     | 24952/57600 [4:21:52<5:51:24,  1.55it/s]
 43%|████▎     | 24953/57600 [4:21:52<5:40:36,  1.60it/s]
 43%|████▎     | 24954/57600 [4:21:53<5:37:35,  1.61it/s]
 43%|████▎     | 24955/57600 [4:21:54<5:46:25,  1.57it/s]
 43%|████▎     | 24956/57600 [4:21:54<5:46:43,  1.57it/s]
 43%|████▎     | 24957/57600 [4:21:55<5:40:27,  1.60it/s]
 43%|████▎     | 24958/57600 [4:21:56<5:42:50,  1.59it/s]
 43%|████▎     | 24959/57600 [4:21:56<5:41:50,  1.59it/s]
 43%|████▎     | 24960/57600 [4:21:57<5:49:25,  1.56it/s]
                                                         
{'loss': 1.1731, 'learning_rate': 6.117770034843205e-07, 'epoch': 275.5}

 43%|████▎     | 24960/57600 [4:21:57<5:49:25,  1.56it/s]
 43%|████▎     | 24961/57600 [4:21:58<5:52:23,  1.54it/s]
 43%|████▎     | 24962/57600 [4:21:58<5:44:29,  1.58it/s]
 43%|████▎     | 24963/57600 [4:21:59<5:50:44,  1.55it/s]
 43%|████▎     | 24964/57600 [4:21:59<5:35:15,  1.62it/s]
 43%|████▎     | 24965/57600 [4:22:00<5:33:49,  1.63it/s]
 43%|████▎     | 24966/57600 [4:22:01<5:43:03,  1.59it/s]
 43%|████▎     | 24967/57600 [4:22:01<5:45:01,  1.58it/s]
 43%|████▎     | 24968/57600 [4:22:02<5:37:33,  1.61it/s]
 43%|████▎     | 24969/57600 [4:22:02<5:32:06,  1.64it/s]
 43%|████▎     | 24970/57600 [4:22:03<5:22:10,  1.69it/s]
 43%|████▎     | 24971/57600 [4:22:04<5:41:11,  1.59it/s]
 43%|████▎     | 24972/57600 [4:22:04<5:29:36,  1.65it/s]
 43%|████▎     | 24973/57600 [4:22:05<5:28:41,  1.65it/s]
 43%|████▎     | 24974/57600 [4:22:05<5:25:43,  1.67it/s]
 43%|████▎     | 24975/57600 [4:22:06<5:28:28,  1.66it/s]
 43%|████▎     | 24976/57600 [4:22:07<5:28:27,  1.66it/s]
 43%|████▎     | 24977/57600 [4:22:07<5:23:22,  1.68it/s]
 43%|████▎     | 24978/57600 [4:22:08<5:28:47,  1.65it/s]
 43%|████▎     | 24979/57600 [4:22:08<5:24:40,  1.67it/s]
 43%|████▎     | 24980/57600 [4:22:09<5:13:06,  1.74it/s]
                                                         
{'loss': 1.2582, 'learning_rate': 6.114634146341464e-07, 'epoch': 275.72}

 43%|████▎     | 24980/57600 [4:22:09<5:13:06,  1.74it/s]
 43%|████▎     | 24981/57600 [4:22:10<5:15:59,  1.72it/s]
 43%|████▎     | 24982/57600 [4:22:10<5:15:00,  1.73it/s]
 43%|████▎     | 24983/57600 [4:22:11<5:33:49,  1.63it/s]
 43%|████▎     | 24984/57600 [4:22:11<5:34:22,  1.63it/s]
 43%|████▎     | 24985/57600 [4:22:12<5:48:12,  1.56it/s]
 43%|████▎     | 24986/57600 [4:22:13<5:44:30,  1.58it/s]
 43%|████▎     | 24987/57600 [4:22:13<5:47:39,  1.56it/s]
 43%|████▎     | 24988/57600 [4:22:14<5:36:14,  1.62it/s]
 43%|████▎     | 24989/57600 [4:22:15<5:31:12,  1.64it/s]
 43%|████▎     | 24990/57600 [4:22:15<5:33:07,  1.63it/s]
 43%|████▎     | 24991/57600 [4:22:16<5:29:49,  1.65it/s]
 43%|████▎     | 24992/57600 [4:22:17<5:39:37,  1.60it/s]
 43%|████▎     | 24993/57600 [4:22:17<5:40:17,  1.60it/s]
 43%|████▎     | 24994/57600 [4:22:18<5:36:46,  1.61it/s]
 43%|████▎     | 24995/57600 [4:22:18<5:37:37,  1.61it/s]
 43%|████▎     | 24996/57600 [4:22:19<5:40:45,  1.59it/s]
 43%|████▎     | 24997/57600 [4:22:20<5:38:10,  1.61it/s]
 43%|████▎     | 24998/57600 [4:22:20<5:25:26,  1.67it/s]
 43%|████▎     | 24999/57600 [4:22:21<5:28:03,  1.66it/s]
 43%|████▎     | 25000/57600 [4:22:21<5:39:21,  1.60it/s]
                                                         
{'loss': 1.2158, 'learning_rate': 6.11149825783972e-07, 'epoch': 275.94}

 43%|████▎     | 25000/57600 [4:22:21<5:39:21,  1.60it/s]
 43%|████▎     | 25001/57600 [4:22:22<5:46:52,  1.57it/s]
 43%|████▎     | 25002/57600 [4:22:23<5:44:25,  1.58it/s]
 43%|████▎     | 25003/57600 [4:22:23<5:43:04,  1.58it/s]
 43%|████▎     | 25004/57600 [4:22:24<5:39:39,  1.60it/s]
 43%|████▎     | 25005/57600 [4:22:25<5:46:44,  1.57it/s]
 43%|████▎     | 25006/57600 [4:22:25<6:00:41,  1.51it/s]
 43%|████▎     | 25007/57600 [4:22:26<5:53:05,  1.54it/s]
 43%|████▎     | 25008/57600 [4:22:27<5:39:22,  1.60it/s]
 43%|████▎     | 25009/57600 [4:22:27<5:33:06,  1.63it/s]
 43%|████▎     | 25010/57600 [4:22:28<5:39:35,  1.60it/s]
 43%|████▎     | 25011/57600 [4:22:28<5:35:16,  1.62it/s]
 43%|████▎     | 25012/57600 [4:22:29<5:32:47,  1.63it/s]
 43%|████▎     | 25013/57600 [4:22:30<5:35:52,  1.62it/s]
 43%|████▎     | 25014/57600 [4:22:30<5:36:54,  1.61it/s]
 43%|████▎     | 25015/57600 [4:22:31<5:31:35,  1.64it/s]
 43%|████▎     | 25016/57600 [4:22:31<5:38:34,  1.60it/s]
 43%|████▎     | 25017/57600 [4:22:32<6:08:04,  1.48it/s]
 43%|████▎     | 25018/57600 [4:22:33<5:52:47,  1.54it/s]
 43%|████▎     | 25019/57600 [4:22:33<5:40:14,  1.60it/s]
 43%|████▎     | 25020/57600 [4:22:34<6:01:38,  1.50it/s]
                                                         
{'loss': 1.2254, 'learning_rate': 6.108362369337978e-07, 'epoch': 276.16}

 43%|████▎     | 25020/57600 [4:22:34<6:01:38,  1.50it/s]
 43%|████▎     | 25021/57600 [4:22:35<5:46:52,  1.57it/s]
 43%|████▎     | 25022/57600 [4:22:35<5:36:45,  1.61it/s]
 43%|████▎     | 25023/57600 [4:22:36<5:51:16,  1.55it/s]
 43%|████▎     | 25024/57600 [4:22:37<5:45:32,  1.57it/s]
 43%|████▎     | 25025/57600 [4:22:37<5:33:33,  1.63it/s]
 43%|████▎     | 25026/57600 [4:22:38<5:34:30,  1.62it/s]
 43%|████▎     | 25027/57600 [4:22:39<5:42:08,  1.59it/s]
 43%|████▎     | 25028/57600 [4:22:39<5:50:34,  1.55it/s]
 43%|████▎     | 25029/57600 [4:22:40<5:40:18,  1.60it/s]
 43%|████▎     | 25030/57600 [4:22:40<5:43:13,  1.58it/s]
 43%|████▎     | 25031/57600 [4:22:41<5:40:54,  1.59it/s]
 43%|████▎     | 25032/57600 [4:22:42<5:35:59,  1.62it/s]
 43%|████▎     | 25033/57600 [4:22:42<5:30:32,  1.64it/s]
 43%|████▎     | 25034/57600 [4:22:43<5:26:31,  1.66it/s]
 43%|████▎     | 25035/57600 [4:22:43<5:31:35,  1.64it/s]
 43%|████▎     | 25036/57600 [4:22:44<5:30:25,  1.64it/s]
 43%|████▎     | 25037/57600 [4:22:45<5:30:38,  1.64it/s]
 43%|████▎     | 25038/57600 [4:22:45<5:50:24,  1.55it/s]
 43%|████▎     | 25039/57600 [4:22:46<5:45:17,  1.57it/s]
 43%|████▎     | 25040/57600 [4:22:47<5:45:54,  1.57it/s]
                                                         
{'loss': 1.2137, 'learning_rate': 6.105226480836237e-07, 'epoch': 276.38}

 43%|████▎     | 25040/57600 [4:22:47<5:45:54,  1.57it/s]
 43%|████▎     | 25041/57600 [4:22:47<5:35:08,  1.62it/s]
 43%|████▎     | 25042/57600 [4:22:48<5:36:10,  1.61it/s]
 43%|████▎     | 25043/57600 [4:22:49<5:41:23,  1.59it/s]
 43%|████▎     | 25044/57600 [4:22:49<5:43:23,  1.58it/s]
 43%|████▎     | 25045/57600 [4:22:50<5:36:43,  1.61it/s]
 43%|████▎     | 25046/57600 [4:22:50<5:35:45,  1.62it/s]
 43%|████▎     | 25047/57600 [4:22:51<5:25:28,  1.67it/s]
 43%|████▎     | 25048/57600 [4:22:52<5:24:58,  1.67it/s]
 43%|████▎     | 25049/57600 [4:22:52<5:19:18,  1.70it/s]
 43%|████▎     | 25050/57600 [4:22:53<5:28:22,  1.65it/s]
 43%|████▎     | 25051/57600 [4:22:53<5:36:34,  1.61it/s]
 43%|████▎     | 25052/57600 [4:22:54<5:33:15,  1.63it/s]
 43%|████▎     | 25053/57600 [4:22:55<5:32:01,  1.63it/s]
 43%|████▎     | 25054/57600 [4:22:55<5:23:53,  1.67it/s]
 43%|████▎     | 25055/57600 [4:22:56<5:27:46,  1.65it/s]
 44%|████▎     | 25056/57600 [4:22:56<5:29:49,  1.64it/s]
 44%|████▎     | 25057/57600 [4:22:57<5:36:04,  1.61it/s]
 44%|████▎     | 25058/57600 [4:22:58<5:45:48,  1.57it/s]
 44%|████▎     | 25059/57600 [4:22:58<5:34:20,  1.62it/s]
 44%|████▎     | 25060/57600 [4:22:59<5:44:15,  1.58it/s]
                                                         
{'loss': 1.171, 'learning_rate': 6.102090592334495e-07, 'epoch': 276.6}

 44%|████▎     | 25060/57600 [4:22:59<5:44:15,  1.58it/s]
 44%|████▎     | 25061/57600 [4:23:00<5:43:05,  1.58it/s]
 44%|████▎     | 25062/57600 [4:23:00<5:37:34,  1.61it/s]
 44%|████▎     | 25063/57600 [4:23:01<5:34:48,  1.62it/s]
 44%|████▎     | 25064/57600 [4:23:01<5:39:29,  1.60it/s]
 44%|████▎     | 25065/57600 [4:23:02<5:40:33,  1.59it/s]
 44%|████▎     | 25066/57600 [4:23:03<5:32:23,  1.63it/s]
 44%|████▎     | 25067/57600 [4:23:03<5:34:04,  1.62it/s]
 44%|████▎     | 25068/57600 [4:23:04<5:32:24,  1.63it/s]
 44%|████▎     | 25069/57600 [4:23:05<5:35:36,  1.62it/s]
 44%|████▎     | 25070/57600 [4:23:05<5:34:46,  1.62it/s]
 44%|████▎     | 25071/57600 [4:23:06<5:35:15,  1.62it/s]
 44%|████▎     | 25072/57600 [4:23:06<5:33:43,  1.62it/s]
 44%|████▎     | 25073/57600 [4:23:07<5:32:28,  1.63it/s]
 44%|████▎     | 25074/57600 [4:23:08<5:37:43,  1.61it/s]
 44%|████▎     | 25075/57600 [4:23:08<5:44:02,  1.58it/s]
 44%|████▎     | 25076/57600 [4:23:09<5:41:32,  1.59it/s]
 44%|████▎     | 25077/57600 [4:23:09<5:31:57,  1.63it/s]
 44%|████▎     | 25078/57600 [4:23:10<5:25:19,  1.67it/s]
 44%|████▎     | 25079/57600 [4:23:11<5:15:32,  1.72it/s]
 44%|████▎     | 25080/57600 [4:23:11<5:13:40,  1.73it/s]
                                                         
{'loss': 1.2115, 'learning_rate': 6.098954703832752e-07, 'epoch': 276.82}

 44%|████▎     | 25080/57600 [4:23:11<5:13:40,  1.73it/s]
 44%|████▎     | 25081/57600 [4:23:12<5:10:05,  1.75it/s]
 44%|████▎     | 25082/57600 [4:23:12<5:17:06,  1.71it/s]
 44%|████▎     | 25083/57600 [4:23:13<5:29:43,  1.64it/s]
 44%|████▎     | 25084/57600 [4:23:14<5:25:59,  1.66it/s]
 44%|████▎     | 25085/57600 [4:23:14<5:36:26,  1.61it/s]
 44%|████▎     | 25086/57600 [4:23:15<5:25:38,  1.66it/s]
 44%|████▎     | 25087/57600 [4:23:15<5:31:23,  1.64it/s]
 44%|████▎     | 25088/57600 [4:23:16<5:31:44,  1.63it/s]
 44%|████▎     | 25089/57600 [4:23:17<5:42:29,  1.58it/s]
 44%|████▎     | 25090/57600 [4:23:17<5:36:50,  1.61it/s]
 44%|████▎     | 25091/57600 [4:23:18<5:43:50,  1.58it/s]
 44%|████▎     | 25092/57600 [4:23:19<5:39:51,  1.59it/s]
 44%|████▎     | 25093/57600 [4:23:19<5:37:14,  1.61it/s]
 44%|████▎     | 25094/57600 [4:23:20<5:24:41,  1.67it/s]
 44%|████▎     | 25095/57600 [4:23:20<5:27:54,  1.65it/s]
 44%|████▎     | 25096/57600 [4:23:21<5:33:18,  1.63it/s]
 44%|████▎     | 25097/57600 [4:23:22<5:42:19,  1.58it/s]
 44%|████▎     | 25098/57600 [4:23:22<5:34:05,  1.62it/s]
 44%|████▎     | 25099/57600 [4:23:23<5:25:30,  1.66it/s]
 44%|████▎     | 25100/57600 [4:23:23<5:23:18,  1.68it/s]
                                                         
{'loss': 1.2124, 'learning_rate': 6.09581881533101e-07, 'epoch': 277.04}

 44%|████▎     | 25100/57600 [4:23:23<5:23:18,  1.68it/s]
 44%|████▎     | 25101/57600 [4:23:24<5:35:21,  1.62it/s]
 44%|████▎     | 25102/57600 [4:23:25<5:38:30,  1.60it/s]
 44%|████▎     | 25103/57600 [4:23:25<5:30:11,  1.64it/s]
 44%|████▎     | 25104/57600 [4:23:26<5:28:26,  1.65it/s]
 44%|████▎     | 25105/57600 [4:23:26<5:27:36,  1.65it/s]
 44%|████▎     | 25106/57600 [4:23:27<5:23:09,  1.68it/s]
 44%|████▎     | 25107/57600 [4:23:28<5:19:33,  1.69it/s]
 44%|████▎     | 25108/57600 [4:23:28<5:29:24,  1.64it/s]
 44%|████▎     | 25109/57600 [4:23:29<5:48:28,  1.55it/s]
 44%|████▎     | 25110/57600 [4:23:30<5:51:40,  1.54it/s]
 44%|████▎     | 25111/57600 [4:23:30<5:36:21,  1.61it/s]
 44%|████▎     | 25112/57600 [4:23:31<5:31:44,  1.63it/s]
 44%|████▎     | 25113/57600 [4:23:31<5:29:27,  1.64it/s]
 44%|████▎     | 25114/57600 [4:23:32<5:32:07,  1.63it/s]
 44%|████▎     | 25115/57600 [4:23:33<5:45:17,  1.57it/s]
 44%|████▎     | 25116/57600 [4:23:33<5:46:30,  1.56it/s]
 44%|████▎     | 25117/57600 [4:23:34<5:56:16,  1.52it/s]
 44%|████▎     | 25118/57600 [4:23:35<5:57:26,  1.51it/s]
 44%|████▎     | 25119/57600 [4:23:35<6:01:45,  1.50it/s]
 44%|████▎     | 25120/57600 [4:23:36<5:47:05,  1.56it/s]
                                                         
{'loss': 1.2222, 'learning_rate': 6.092682926829269e-07, 'epoch': 277.26}

 44%|████▎     | 25120/57600 [4:23:36<5:47:05,  1.56it/s]
 44%|████▎     | 25121/57600 [4:23:37<5:51:53,  1.54it/s]
 44%|████▎     | 25122/57600 [4:23:37<5:47:00,  1.56it/s]
 44%|████▎     | 25123/57600 [4:23:38<5:42:26,  1.58it/s]
 44%|████▎     | 25124/57600 [4:23:39<5:35:40,  1.61it/s]
 44%|████▎     | 25125/57600 [4:23:39<5:25:39,  1.66it/s]
 44%|████▎     | 25126/57600 [4:23:40<5:32:24,  1.63it/s]
 44%|████▎     | 25127/57600 [4:23:40<5:29:11,  1.64it/s]
 44%|████▎     | 25128/57600 [4:23:41<5:27:26,  1.65it/s]
 44%|████▎     | 25129/57600 [4:23:42<5:33:29,  1.62it/s]
 44%|████▎     | 25130/57600 [4:23:42<5:30:51,  1.64it/s]
 44%|████▎     | 25131/57600 [4:23:43<5:27:49,  1.65it/s]
 44%|████▎     | 25132/57600 [4:23:43<5:33:36,  1.62it/s]
 44%|████▎     | 25133/57600 [4:23:44<5:30:48,  1.64it/s]
 44%|████▎     | 25134/57600 [4:23:45<5:34:27,  1.62it/s]
 44%|████▎     | 25135/57600 [4:23:45<5:40:39,  1.59it/s]
 44%|████▎     | 25136/57600 [4:23:46<5:40:09,  1.59it/s]
 44%|████▎     | 25137/57600 [4:23:47<5:39:42,  1.59it/s]
 44%|████▎     | 25138/57600 [4:23:47<5:37:21,  1.60it/s]
 44%|████▎     | 25139/57600 [4:23:48<5:39:21,  1.59it/s]
 44%|████▎     | 25140/57600 [4:23:48<5:35:11,  1.61it/s]
                                                         
{'loss': 1.2309, 'learning_rate': 6.089547038327526e-07, 'epoch': 277.48}

 44%|████▎     | 25140/57600 [4:23:48<5:35:11,  1.61it/s]
 44%|████▎     | 25141/57600 [4:23:49<5:31:57,  1.63it/s]
 44%|████▎     | 25142/57600 [4:23:50<5:30:07,  1.64it/s]
 44%|████▎     | 25143/57600 [4:23:50<5:24:57,  1.66it/s]
 44%|████▎     | 25144/57600 [4:23:51<5:21:50,  1.68it/s]
 44%|████▎     | 25145/57600 [4:23:51<5:19:36,  1.69it/s]
 44%|████▎     | 25146/57600 [4:23:52<5:14:33,  1.72it/s]
 44%|████▎     | 25147/57600 [4:23:53<5:25:21,  1.66it/s]
 44%|████▎     | 25148/57600 [4:23:53<5:31:42,  1.63it/s]
 44%|████▎     | 25149/57600 [4:23:54<5:26:23,  1.66it/s]
 44%|████▎     | 25150/57600 [4:23:54<5:21:15,  1.68it/s]
 44%|████▎     | 25151/57600 [4:23:55<5:36:28,  1.61it/s]
 44%|████▎     | 25152/57600 [4:23:56<5:41:31,  1.58it/s]
 44%|████▎     | 25153/57600 [4:23:56<5:37:14,  1.60it/s]
 44%|████▎     | 25154/57600 [4:23:57<5:38:48,  1.60it/s]
 44%|████▎     | 25155/57600 [4:23:58<5:37:40,  1.60it/s]
 44%|████▎     | 25156/57600 [4:23:58<5:48:58,  1.55it/s]
 44%|████▎     | 25157/57600 [4:23:59<5:36:34,  1.61it/s]
 44%|████▎     | 25158/57600 [4:23:59<5:26:21,  1.66it/s]
 44%|████▎     | 25159/57600 [4:24:00<5:31:25,  1.63it/s]
 44%|████▎     | 25160/57600 [4:24:01<5:40:11,  1.59it/s]
                                                         
{'loss': 1.2246, 'learning_rate': 6.086411149825783e-07, 'epoch': 277.7}

 44%|████▎     | 25160/57600 [4:24:01<5:40:11,  1.59it/s]
 44%|████▎     | 25161/57600 [4:24:01<5:36:12,  1.61it/s]
 44%|████▎     | 25162/57600 [4:24:02<5:40:19,  1.59it/s]
 44%|████▎     | 25163/57600 [4:24:03<5:39:50,  1.59it/s]
 44%|████▎     | 25164/57600 [4:24:03<5:33:49,  1.62it/s]
 44%|████▎     | 25165/57600 [4:24:04<5:24:17,  1.67it/s]
 44%|████▎     | 25166/57600 [4:24:04<5:41:30,  1.58it/s]
 44%|████▎     | 25167/57600 [4:24:05<5:43:15,  1.57it/s]
 44%|████▎     | 25168/57600 [4:24:06<5:49:02,  1.55it/s]
 44%|████▎     | 25169/57600 [4:24:06<5:54:58,  1.52it/s]
 44%|████▎     | 25170/57600 [4:24:07<5:49:40,  1.55it/s]
 44%|████▎     | 25171/57600 [4:24:08<5:45:08,  1.57it/s]
 44%|████▎     | 25172/57600 [4:24:08<5:54:40,  1.52it/s]
 44%|████▎     | 25173/57600 [4:24:09<5:42:33,  1.58it/s]
 44%|████▎     | 25174/57600 [4:24:10<5:38:08,  1.60it/s]
 44%|████▎     | 25175/57600 [4:24:10<5:27:22,  1.65it/s]
 44%|████▎     | 25176/57600 [4:24:11<5:26:01,  1.66it/s]
 44%|████▎     | 25177/57600 [4:24:11<5:31:06,  1.63it/s]
 44%|████▎     | 25178/57600 [4:24:12<5:36:51,  1.60it/s]
 44%|████▎     | 25179/57600 [4:24:13<5:30:24,  1.64it/s]
 44%|████▎     | 25180/57600 [4:24:13<5:29:54,  1.64it/s]
                                                         
{'loss': 1.1875, 'learning_rate': 6.083275261324041e-07, 'epoch': 277.92}

 44%|████▎     | 25180/57600 [4:24:13<5:29:54,  1.64it/s]
 44%|████▎     | 25181/57600 [4:24:14<5:32:49,  1.62it/s]
 44%|████▎     | 25182/57600 [4:24:14<5:33:20,  1.62it/s]
 44%|████▎     | 25183/57600 [4:24:15<5:27:56,  1.65it/s]
 44%|████▎     | 25184/57600 [4:24:16<5:27:50,  1.65it/s]
 44%|████▎     | 25185/57600 [4:24:16<5:32:20,  1.63it/s]
 44%|████▎     | 25186/57600 [4:24:17<5:26:52,  1.65it/s]
 44%|████▎     | 25187/57600 [4:24:17<5:37:33,  1.60it/s]
 44%|████▎     | 25188/57600 [4:24:18<5:29:56,  1.64it/s]
 44%|████▎     | 25189/57600 [4:24:19<5:30:39,  1.63it/s]
 44%|████▎     | 25190/57600 [4:24:19<5:31:14,  1.63it/s]
 44%|████▎     | 25191/57600 [4:24:20<5:34:50,  1.61it/s]
 44%|████▎     | 25192/57600 [4:24:21<5:42:07,  1.58it/s]
 44%|████▎     | 25193/57600 [4:24:21<5:29:57,  1.64it/s]
 44%|████▎     | 25194/57600 [4:24:22<5:26:30,  1.65it/s]
 44%|████▎     | 25195/57600 [4:24:22<5:24:41,  1.66it/s]
 44%|████▎     | 25196/57600 [4:24:23<5:36:03,  1.61it/s]
 44%|████▎     | 25197/57600 [4:24:24<5:36:05,  1.61it/s]
 44%|████▎     | 25198/57600 [4:24:24<5:38:29,  1.60it/s]
 44%|████▎     | 25199/57600 [4:24:25<5:35:22,  1.61it/s]
 44%|████▍     | 25200/57600 [4:24:25<5:29:59,  1.64it/s]
                                                         
{'loss': 1.2339, 'learning_rate': 6.080139372822299e-07, 'epoch': 278.15}

 44%|████▍     | 25200/57600 [4:24:25<5:29:59,  1.64it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.39it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.12it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.78it/s]

100%|██████████| 6/6 [00:01<00:00,  3.16it/s]{'score': 46.56553016096495, 'counts': [142, 92, 62, 44], 'totals': [214, 184, 154, 125], 'precisions': [66.35514018691589, 50.0, 40.25974025974026, 35.2], 'bp': 1.0, 'sys_len': 214, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 1.970467448234558, 'eval_bleu': 46.5655, 'eval_gen_len': 8.5667, 'eval_runtime': 3.2684, 'eval_samples_per_second': 9.179, 'eval_steps_per_second': 1.836, 'epoch': 278.15}

 44%|████▍     | 25200/57600 [4:24:29<5:29:59,  1.64it/s]

100%|██████████| 6/6 [00:02<00:00,  3.16it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 11:18:42,049 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 44%|████▍     | 25201/57600 [4:24:41<45:31:15,  5.06s/it]
 44%|████▍     | 25202/57600 [4:24:41<33:24:12,  3.71s/it]
 44%|████▍     | 25203/57600 [4:24:42<25:13:03,  2.80s/it]
 44%|████▍     | 25204/57600 [4:24:43<19:19:59,  2.15s/it]
 44%|████▍     | 25205/57600 [4:24:43<15:05:27,  1.68s/it]
 44%|████▍     | 25206/57600 [4:24:44<12:20:03,  1.37s/it]
 44%|████▍     | 25207/57600 [4:24:45<10:21:41,  1.15s/it]
 44%|████▍     | 25208/57600 [4:24:45<9:01:09,  1.00s/it] 
 44%|████▍     | 25209/57600 [4:24:46<8:11:59,  1.10it/s]
 44%|████▍     | 25210/57600 [4:24:47<7:34:08,  1.19it/s]
 44%|████▍     | 25211/57600 [4:24:47<7:04:14,  1.27it/s]
 44%|████▍     | 25212/57600 [4:24:48<6:47:05,  1.33it/s]
 44%|████▍     | 25213/57600 [4:24:49<6:28:08,  1.39it/s]
 44%|████▍     | 25214/57600 [4:24:49<6:09:33,  1.46it/s]
 44%|████▍     | 25215/57600 [4:24:50<6:00:32,  1.50it/s]
 44%|████▍     | 25216/57600 [4:24:50<5:50:14,  1.54it/s]
 44%|████▍     | 25217/57600 [4:24:51<5:58:02,  1.51it/s]
 44%|████▍     | 25218/57600 [4:24:52<6:01:17,  1.49it/s]
 44%|████▍     | 25219/57600 [4:24:53<6:07:09,  1.47it/s]
 44%|████▍     | 25220/57600 [4:24:53<6:00:23,  1.50it/s]
                                                         
{'loss': 1.1705, 'learning_rate': 6.077003484320556e-07, 'epoch': 278.37}

 44%|████▍     | 25220/57600 [4:24:53<6:00:23,  1.50it/s]
 44%|████▍     | 25221/57600 [4:24:54<5:59:43,  1.50it/s]
 44%|████▍     | 25222/57600 [4:24:55<5:57:56,  1.51it/s]
 44%|████▍     | 25223/57600 [4:24:55<6:08:16,  1.47it/s]
 44%|████▍     | 25224/57600 [4:24:56<6:13:09,  1.45it/s]
 44%|████▍     | 25225/57600 [4:24:57<6:10:44,  1.46it/s]
 44%|████▍     | 25226/57600 [4:24:57<6:08:26,  1.46it/s]
 44%|████▍     | 25227/57600 [4:24:58<6:07:26,  1.47it/s]
 44%|████▍     | 25228/57600 [4:24:59<5:56:32,  1.51it/s]
 44%|████▍     | 25229/57600 [4:24:59<6:11:52,  1.45it/s]
 44%|████▍     | 25230/57600 [4:25:00<6:04:20,  1.48it/s]
 44%|████▍     | 25231/57600 [4:25:01<5:48:16,  1.55it/s]
 44%|████▍     | 25232/57600 [4:25:01<5:48:58,  1.55it/s]
 44%|████▍     | 25233/57600 [4:25:02<5:43:08,  1.57it/s]
 44%|████▍     | 25234/57600 [4:25:02<5:41:51,  1.58it/s]
 44%|████▍     | 25235/57600 [4:25:03<5:33:37,  1.62it/s]
 44%|████▍     | 25236/57600 [4:25:04<5:40:02,  1.59it/s]
 44%|████▍     | 25237/57600 [4:25:04<5:50:49,  1.54it/s]
 44%|████▍     | 25238/57600 [4:25:05<5:56:14,  1.51it/s]
 44%|████▍     | 25239/57600 [4:25:06<5:58:05,  1.51it/s]
 44%|████▍     | 25240/57600 [4:25:06<6:00:44,  1.50it/s]
                                                         
{'loss': 1.2458, 'learning_rate': 6.073867595818815e-07, 'epoch': 278.59}

 44%|████▍     | 25240/57600 [4:25:06<6:00:44,  1.50it/s]
 44%|████▍     | 25241/57600 [4:25:07<6:11:39,  1.45it/s]
 44%|████▍     | 25242/57600 [4:25:08<6:09:51,  1.46it/s]
 44%|████▍     | 25243/57600 [4:25:09<6:08:58,  1.46it/s]
 44%|████▍     | 25244/57600 [4:25:09<6:00:31,  1.50it/s]
 44%|████▍     | 25245/57600 [4:25:10<5:58:35,  1.50it/s]
 44%|████▍     | 25246/57600 [4:25:11<6:20:30,  1.42it/s]
 44%|████▍     | 25247/57600 [4:25:11<6:12:16,  1.45it/s]
 44%|████▍     | 25248/57600 [4:25:12<6:20:38,  1.42it/s]
 44%|████▍     | 25249/57600 [4:25:13<6:09:43,  1.46it/s]
 44%|████▍     | 25250/57600 [4:25:13<6:12:05,  1.45it/s]
 44%|████▍     | 25251/57600 [4:25:14<6:08:35,  1.46it/s]
 44%|████▍     | 25252/57600 [4:25:15<6:02:23,  1.49it/s]
 44%|████▍     | 25253/57600 [4:25:15<5:51:39,  1.53it/s]
 44%|████▍     | 25254/57600 [4:25:16<5:54:23,  1.52it/s]
 44%|████▍     | 25255/57600 [4:25:17<5:42:39,  1.57it/s]
 44%|████▍     | 25256/57600 [4:25:17<5:45:40,  1.56it/s]
 44%|████▍     | 25257/57600 [4:25:18<5:43:36,  1.57it/s]
 44%|████▍     | 25258/57600 [4:25:18<5:41:41,  1.58it/s]
 44%|████▍     | 25259/57600 [4:25:19<5:47:42,  1.55it/s]
 44%|████▍     | 25260/57600 [4:25:20<5:31:21,  1.63it/s]
                                                         
{'loss': 1.225, 'learning_rate': 6.070731707317074e-07, 'epoch': 278.81}

 44%|████▍     | 25260/57600 [4:25:20<5:31:21,  1.63it/s]
 44%|████▍     | 25261/57600 [4:25:20<5:39:04,  1.59it/s]
 44%|████▍     | 25262/57600 [4:25:21<5:33:53,  1.61it/s]
 44%|████▍     | 25263/57600 [4:25:21<5:28:19,  1.64it/s]
 44%|████▍     | 25264/57600 [4:25:22<5:35:56,  1.60it/s]
 44%|████▍     | 25265/57600 [4:25:23<5:35:33,  1.61it/s]
 44%|████▍     | 25266/57600 [4:25:23<5:32:56,  1.62it/s]
 44%|████▍     | 25267/57600 [4:25:24<5:33:10,  1.62it/s]
 44%|████▍     | 25268/57600 [4:25:25<5:40:27,  1.58it/s]
 44%|████▍     | 25269/57600 [4:25:25<5:39:21,  1.59it/s]
 44%|████▍     | 25270/57600 [4:25:26<5:41:38,  1.58it/s]
 44%|████▍     | 25271/57600 [4:25:27<5:48:19,  1.55it/s]
 44%|████▍     | 25272/57600 [4:25:27<5:52:52,  1.53it/s]
 44%|████▍     | 25273/57600 [4:25:28<5:50:08,  1.54it/s]
 44%|████▍     | 25274/57600 [4:25:29<5:46:29,  1.55it/s]
 44%|████▍     | 25275/57600 [4:25:29<5:46:29,  1.55it/s]
 44%|████▍     | 25276/57600 [4:25:30<5:32:21,  1.62it/s]
 44%|████▍     | 25277/57600 [4:25:30<5:23:01,  1.67it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 44%|████▍     | 25278/57600 [4:25:31<5:45:22,  1.56it/s]
 44%|████▍     | 25279/57600 [4:25:32<5:45:34,  1.56it/s]
 44%|████▍     | 25280/57600 [4:25:32<5:45:48,  1.56it/s]
                                                         
{'loss': 1.2393, 'learning_rate': 6.067595818815331e-07, 'epoch': 279.03}

 44%|████▍     | 25280/57600 [4:25:32<5:45:48,  1.56it/s]
 44%|████▍     | 25281/57600 [4:25:33<5:52:21,  1.53it/s]
 44%|████▍     | 25282/57600 [4:25:34<5:54:28,  1.52it/s]
 44%|████▍     | 25283/57600 [4:25:34<6:12:03,  1.45it/s]
 44%|████▍     | 25284/57600 [4:25:35<5:56:34,  1.51it/s]
 44%|████▍     | 25285/57600 [4:25:36<5:52:28,  1.53it/s]
 44%|████▍     | 25286/57600 [4:25:36<5:58:57,  1.50it/s]
 44%|████▍     | 25287/57600 [4:25:37<6:02:56,  1.48it/s]
 44%|████▍     | 25288/57600 [4:25:38<5:55:40,  1.51it/s]
 44%|████▍     | 25289/57600 [4:25:38<5:54:50,  1.52it/s]
 44%|████▍     | 25290/57600 [4:25:39<5:47:28,  1.55it/s]
 44%|████▍     | 25291/57600 [4:25:40<5:43:03,  1.57it/s]
 44%|████▍     | 25292/57600 [4:25:40<5:48:12,  1.55it/s]
 44%|████▍     | 25293/57600 [4:25:41<5:42:07,  1.57it/s]
 44%|████▍     | 25294/57600 [4:25:42<5:55:03,  1.52it/s]
 44%|████▍     | 25295/57600 [4:25:42<5:55:43,  1.51it/s]
 44%|████▍     | 25296/57600 [4:25:43<5:52:12,  1.53it/s]
 44%|████▍     | 25297/57600 [4:25:43<5:47:17,  1.55it/s]
 44%|████▍     | 25298/57600 [4:25:44<5:55:17,  1.52it/s]
 44%|████▍     | 25299/57600 [4:25:45<5:46:50,  1.55it/s]
 44%|████▍     | 25300/57600 [4:25:45<5:43:42,  1.57it/s]
                                                         
{'loss': 1.1811, 'learning_rate': 6.064459930313588e-07, 'epoch': 279.25}

 44%|████▍     | 25300/57600 [4:25:45<5:43:42,  1.57it/s]
 44%|████▍     | 25301/57600 [4:25:46<5:56:37,  1.51it/s]
 44%|████▍     | 25302/57600 [4:25:47<5:47:45,  1.55it/s]
 44%|████▍     | 25303/57600 [4:25:47<5:44:29,  1.56it/s]
 44%|████▍     | 25304/57600 [4:25:48<5:49:50,  1.54it/s]
 44%|████▍     | 25305/57600 [4:25:49<5:51:59,  1.53it/s]
 44%|████▍     | 25306/57600 [4:25:49<5:49:39,  1.54it/s]
 44%|████▍     | 25307/57600 [4:25:50<5:43:48,  1.57it/s]
 44%|████▍     | 25308/57600 [4:25:51<5:48:08,  1.55it/s]
 44%|████▍     | 25309/57600 [4:25:51<5:56:21,  1.51it/s]
 44%|████▍     | 25310/57600 [4:25:52<5:51:40,  1.53it/s]
 44%|████▍     | 25311/57600 [4:25:53<6:02:21,  1.49it/s]
 44%|████▍     | 25312/57600 [4:25:53<5:58:53,  1.50it/s]
 44%|████▍     | 25313/57600 [4:25:54<5:58:15,  1.50it/s]
 44%|████▍     | 25314/57600 [4:25:55<5:59:29,  1.50it/s]
 44%|████▍     | 25315/57600 [4:25:55<5:48:28,  1.54it/s]
 44%|████▍     | 25316/57600 [4:25:56<5:53:48,  1.52it/s]
 44%|████▍     | 25317/57600 [4:25:57<6:02:52,  1.48it/s]
 44%|████▍     | 25318/57600 [4:25:57<6:07:02,  1.47it/s]
 44%|████▍     | 25319/57600 [4:25:58<6:00:30,  1.49it/s]
 44%|████▍     | 25320/57600 [4:25:59<5:58:20,  1.50it/s]
                                                         
{'loss': 1.1949, 'learning_rate': 6.061324041811846e-07, 'epoch': 279.47}

 44%|████▍     | 25320/57600 [4:25:59<5:58:20,  1.50it/s]
 44%|████▍     | 25321/57600 [4:25:59<5:58:01,  1.50it/s]
 44%|████▍     | 25322/57600 [4:26:00<5:53:48,  1.52it/s]
 44%|████▍     | 25323/57600 [4:26:01<6:06:15,  1.47it/s]
 44%|████▍     | 25324/57600 [4:26:01<6:06:16,  1.47it/s]
 44%|████▍     | 25325/57600 [4:26:02<6:04:51,  1.47it/s]
 44%|████▍     | 25326/57600 [4:26:03<6:12:34,  1.44it/s]
 44%|████▍     | 25327/57600 [4:26:03<6:11:55,  1.45it/s]
 44%|████▍     | 25328/57600 [4:26:04<5:49:53,  1.54it/s]
 44%|████▍     | 25329/57600 [4:26:05<5:45:23,  1.56it/s]
 44%|████▍     | 25330/57600 [4:26:05<5:47:49,  1.55it/s]
 44%|████▍     | 25331/57600 [4:26:06<5:48:38,  1.54it/s]
 44%|████▍     | 25332/57600 [4:26:07<5:45:38,  1.56it/s]
 44%|████▍     | 25333/57600 [4:26:07<5:59:26,  1.50it/s]
 44%|████▍     | 25334/57600 [4:26:08<5:57:13,  1.51it/s]
 44%|████▍     | 25335/57600 [4:26:09<5:53:33,  1.52it/s]
 44%|████▍     | 25336/57600 [4:26:09<5:51:40,  1.53it/s]
 44%|████▍     | 25337/57600 [4:26:10<5:44:54,  1.56it/s]
 44%|████▍     | 25338/57600 [4:26:11<5:48:49,  1.54it/s]
 44%|████▍     | 25339/57600 [4:26:11<6:00:09,  1.49it/s]
 44%|████▍     | 25340/57600 [4:26:12<5:43:13,  1.57it/s]
                                                         
{'loss': 1.2285, 'learning_rate': 6.058188153310105e-07, 'epoch': 279.69}

 44%|████▍     | 25340/57600 [4:26:12<5:43:13,  1.57it/s]
 44%|████▍     | 25341/57600 [4:26:13<5:56:29,  1.51it/s]
 44%|████▍     | 25342/57600 [4:26:13<5:53:41,  1.52it/s]
 44%|████▍     | 25343/57600 [4:26:14<5:56:54,  1.51it/s]
 44%|████▍     | 25344/57600 [4:26:15<5:57:38,  1.50it/s]
 44%|████▍     | 25345/57600 [4:26:15<5:54:59,  1.51it/s]
 44%|████▍     | 25346/57600 [4:26:16<5:39:56,  1.58it/s]
 44%|████▍     | 25347/57600 [4:26:16<5:45:43,  1.55it/s]
 44%|████▍     | 25348/57600 [4:26:17<5:44:45,  1.56it/s]
 44%|████▍     | 25349/57600 [4:26:18<5:36:59,  1.60it/s]
 44%|████▍     | 25350/57600 [4:26:18<5:42:21,  1.57it/s]
 44%|████▍     | 25351/57600 [4:26:19<5:39:14,  1.58it/s]
 44%|████▍     | 25352/57600 [4:26:20<5:38:25,  1.59it/s]
 44%|████▍     | 25353/57600 [4:26:20<5:34:33,  1.61it/s]
 44%|████▍     | 25354/57600 [4:26:21<5:32:56,  1.61it/s]
 44%|████▍     | 25355/57600 [4:26:21<5:32:06,  1.62it/s]
 44%|████▍     | 25356/57600 [4:26:22<5:38:50,  1.59it/s]
 44%|████▍     | 25357/57600 [4:26:23<5:48:26,  1.54it/s]
 44%|████▍     | 25358/57600 [4:26:23<5:58:58,  1.50it/s]
 44%|████▍     | 25359/57600 [4:26:24<5:54:18,  1.52it/s]
 44%|████▍     | 25360/57600 [4:26:25<5:43:49,  1.56it/s]
                                                         
{'loss': 1.2115, 'learning_rate': 6.055052264808362e-07, 'epoch': 279.91}

 44%|████▍     | 25360/57600 [4:26:25<5:43:49,  1.56it/s]
 44%|████▍     | 25361/57600 [4:26:25<5:43:44,  1.56it/s]
 44%|████▍     | 25362/57600 [4:26:26<5:48:55,  1.54it/s]
 44%|████▍     | 25363/57600 [4:26:27<5:56:27,  1.51it/s]
 44%|████▍     | 25364/57600 [4:26:27<5:49:36,  1.54it/s]
 44%|████▍     | 25365/57600 [4:26:28<5:51:50,  1.53it/s]
 44%|████▍     | 25366/57600 [4:26:29<5:51:44,  1.53it/s]
 44%|████▍     | 25367/57600 [4:26:29<5:48:32,  1.54it/s]
 44%|████▍     | 25368/57600 [4:26:30<5:46:07,  1.55it/s]
 44%|████▍     | 25369/57600 [4:26:31<5:56:42,  1.51it/s]
 44%|████▍     | 25370/57600 [4:26:31<5:48:25,  1.54it/s]
 44%|████▍     | 25371/57600 [4:26:32<5:44:04,  1.56it/s]
 44%|████▍     | 25372/57600 [4:26:33<5:59:09,  1.50it/s]
 44%|████▍     | 25373/57600 [4:26:33<6:02:16,  1.48it/s]
 44%|████▍     | 25374/57600 [4:26:34<5:54:18,  1.52it/s]
 44%|████▍     | 25375/57600 [4:26:35<5:52:41,  1.52it/s]
 44%|████▍     | 25376/57600 [4:26:35<5:45:52,  1.55it/s]
 44%|████▍     | 25377/57600 [4:26:36<5:55:37,  1.51it/s]
 44%|████▍     | 25378/57600 [4:26:36<5:48:27,  1.54it/s]
 44%|████▍     | 25379/57600 [4:26:37<5:50:29,  1.53it/s]
 44%|████▍     | 25380/57600 [4:26:38<6:04:18,  1.47it/s]
                                                         
{'loss': 1.2489, 'learning_rate': 6.05191637630662e-07, 'epoch': 280.13}

 44%|████▍     | 25380/57600 [4:26:38<6:04:18,  1.47it/s]
 44%|████▍     | 25381/57600 [4:26:38<5:56:42,  1.51it/s]
 44%|████▍     | 25382/57600 [4:26:39<5:45:56,  1.55it/s]
 44%|████▍     | 25383/57600 [4:26:40<5:52:46,  1.52it/s]
 44%|████▍     | 25384/57600 [4:26:40<5:54:11,  1.52it/s]
 44%|████▍     | 25385/57600 [4:26:41<5:57:20,  1.50it/s]
 44%|████▍     | 25386/57600 [4:26:42<5:58:08,  1.50it/s]
 44%|████▍     | 25387/57600 [4:26:42<5:43:58,  1.56it/s]
 44%|████▍     | 25388/57600 [4:26:43<5:43:39,  1.56it/s]
 44%|████▍     | 25389/57600 [4:26:44<5:48:54,  1.54it/s]
 44%|████▍     | 25390/57600 [4:26:44<5:43:10,  1.56it/s]
 44%|████▍     | 25391/57600 [4:26:45<5:31:00,  1.62it/s]
 44%|████▍     | 25392/57600 [4:26:45<5:32:01,  1.62it/s]
 44%|████▍     | 25393/57600 [4:26:46<5:29:25,  1.63it/s]
 44%|████▍     | 25394/57600 [4:26:47<5:29:51,  1.63it/s]
 44%|████▍     | 25395/57600 [4:26:47<5:34:28,  1.60it/s]
 44%|████▍     | 25396/57600 [4:26:48<5:34:16,  1.61it/s]
 44%|████▍     | 25397/57600 [4:26:49<5:25:09,  1.65it/s]
 44%|████▍     | 25398/57600 [4:26:49<5:19:52,  1.68it/s]
 44%|████▍     | 25399/57600 [4:26:50<5:34:45,  1.60it/s]
 44%|████▍     | 25400/57600 [4:26:50<5:29:02,  1.63it/s]
                                                         
{'loss': 1.2012, 'learning_rate': 6.048780487804878e-07, 'epoch': 280.35}

 44%|████▍     | 25400/57600 [4:26:50<5:29:02,  1.63it/s]
 44%|████▍     | 25401/57600 [4:26:51<5:34:28,  1.60it/s]
 44%|████▍     | 25402/57600 [4:26:52<5:27:41,  1.64it/s]
 44%|████▍     | 25403/57600 [4:26:52<5:23:26,  1.66it/s]
 44%|████▍     | 25404/57600 [4:26:53<5:23:33,  1.66it/s]
 44%|████▍     | 25405/57600 [4:26:53<5:23:08,  1.66it/s]
 44%|████▍     | 25406/57600 [4:26:54<5:26:00,  1.65it/s]
 44%|████▍     | 25407/57600 [4:26:55<5:29:31,  1.63it/s]
 44%|████▍     | 25408/57600 [4:26:55<5:25:36,  1.65it/s]
 44%|████▍     | 25409/57600 [4:26:56<5:22:30,  1.66it/s]
 44%|████▍     | 25410/57600 [4:26:56<5:20:01,  1.68it/s]
 44%|████▍     | 25411/57600 [4:26:57<5:26:00,  1.65it/s]
 44%|████▍     | 25412/57600 [4:26:58<5:25:56,  1.65it/s]
 44%|████▍     | 25413/57600 [4:26:58<5:31:10,  1.62it/s]
 44%|████▍     | 25414/57600 [4:26:59<5:41:48,  1.57it/s]
 44%|████▍     | 25415/57600 [4:27:00<5:38:05,  1.59it/s]
 44%|████▍     | 25416/57600 [4:27:00<5:28:56,  1.63it/s]
 44%|████▍     | 25417/57600 [4:27:01<5:34:43,  1.60it/s]
 44%|████▍     | 25418/57600 [4:27:02<5:44:37,  1.56it/s]
 44%|████▍     | 25419/57600 [4:27:02<5:37:07,  1.59it/s]
 44%|████▍     | 25420/57600 [4:27:03<5:30:49,  1.62it/s]
                                                         
{'loss': 1.1805, 'learning_rate': 6.045644599303136e-07, 'epoch': 280.57}

 44%|████▍     | 25420/57600 [4:27:03<5:30:49,  1.62it/s]
 44%|████▍     | 25421/57600 [4:27:03<5:22:40,  1.66it/s]
 44%|████▍     | 25422/57600 [4:27:04<5:39:58,  1.58it/s]
 44%|████▍     | 25423/57600 [4:27:05<5:36:52,  1.59it/s]
 44%|████▍     | 25424/57600 [4:27:05<5:39:11,  1.58it/s]
 44%|████▍     | 25425/57600 [4:27:06<5:39:52,  1.58it/s]
 44%|████▍     | 25426/57600 [4:27:06<5:34:14,  1.60it/s]
 44%|████▍     | 25427/57600 [4:27:07<5:30:01,  1.62it/s]
 44%|████▍     | 25428/57600 [4:27:08<5:44:42,  1.56it/s]
 44%|████▍     | 25429/57600 [4:27:08<5:36:44,  1.59it/s]
 44%|████▍     | 25430/57600 [4:27:09<5:29:42,  1.63it/s]
 44%|████▍     | 25431/57600 [4:27:10<5:33:46,  1.61it/s]
 44%|████▍     | 25432/57600 [4:27:10<5:40:17,  1.58it/s]
 44%|████▍     | 25433/57600 [4:27:11<5:30:03,  1.62it/s]
 44%|████▍     | 25434/57600 [4:27:11<5:35:41,  1.60it/s]
 44%|████▍     | 25435/57600 [4:27:12<5:33:05,  1.61it/s]
 44%|████▍     | 25436/57600 [4:27:13<5:35:47,  1.60it/s]
 44%|████▍     | 25437/57600 [4:27:13<5:45:39,  1.55it/s]
 44%|████▍     | 25438/57600 [4:27:14<5:41:58,  1.57it/s]
 44%|████▍     | 25439/57600 [4:27:15<5:28:07,  1.63it/s]
 44%|████▍     | 25440/57600 [4:27:15<5:35:17,  1.60it/s]
                                                         
{'loss': 1.2035, 'learning_rate': 6.042508710801392e-07, 'epoch': 280.79}

 44%|████▍     | 25440/57600 [4:27:15<5:35:17,  1.60it/s]
 44%|████▍     | 25441/57600 [4:27:16<5:30:00,  1.62it/s]
 44%|████▍     | 25442/57600 [4:27:16<5:31:05,  1.62it/s]
 44%|████▍     | 25443/57600 [4:27:17<5:43:05,  1.56it/s]
 44%|████▍     | 25444/57600 [4:27:18<5:50:52,  1.53it/s]
 44%|████▍     | 25445/57600 [4:27:18<5:48:05,  1.54it/s]
 44%|████▍     | 25446/57600 [4:27:19<5:37:29,  1.59it/s]
 44%|████▍     | 25447/57600 [4:27:20<5:30:16,  1.62it/s]
 44%|████▍     | 25448/57600 [4:27:20<5:39:38,  1.58it/s]
 44%|████▍     | 25449/57600 [4:27:21<5:55:47,  1.51it/s]
 44%|████▍     | 25450/57600 [4:27:22<5:38:54,  1.58it/s]
 44%|████▍     | 25451/57600 [4:27:22<5:41:47,  1.57it/s]
 44%|████▍     | 25452/57600 [4:27:23<5:33:27,  1.61it/s]
 44%|████▍     | 25453/57600 [4:27:23<5:34:40,  1.60it/s]
 44%|████▍     | 25454/57600 [4:27:24<5:25:05,  1.65it/s]
 44%|████▍     | 25455/57600 [4:27:25<5:25:55,  1.64it/s]
 44%|████▍     | 25456/57600 [4:27:25<5:22:23,  1.66it/s]
 44%|████▍     | 25457/57600 [4:27:26<5:40:56,  1.57it/s]
 44%|████▍     | 25458/57600 [4:27:27<5:44:54,  1.55it/s]
 44%|████▍     | 25459/57600 [4:27:27<5:50:33,  1.53it/s]
 44%|████▍     | 25460/57600 [4:27:28<5:57:48,  1.50it/s]
                                                         
{'loss': 1.2033, 'learning_rate': 6.039372822299651e-07, 'epoch': 281.02}

 44%|████▍     | 25460/57600 [4:27:28<5:57:48,  1.50it/s]
 44%|████▍     | 25461/57600 [4:27:29<6:07:44,  1.46it/s]
 44%|████▍     | 25462/57600 [4:27:29<5:50:40,  1.53it/s]
 44%|████▍     | 25463/57600 [4:27:30<5:37:44,  1.59it/s]
 44%|████▍     | 25464/57600 [4:27:31<5:44:36,  1.55it/s]
 44%|████▍     | 25465/57600 [4:27:31<5:30:41,  1.62it/s]
 44%|████▍     | 25466/57600 [4:27:32<5:32:12,  1.61it/s]
 44%|████▍     | 25467/57600 [4:27:32<5:26:41,  1.64it/s]
 44%|████▍     | 25468/57600 [4:27:33<5:22:44,  1.66it/s]
 44%|████▍     | 25469/57600 [4:27:34<5:22:05,  1.66it/s]
 44%|████▍     | 25470/57600 [4:27:34<5:19:41,  1.68it/s]
 44%|████▍     | 25471/57600 [4:27:35<5:16:58,  1.69it/s]
 44%|████▍     | 25472/57600 [4:27:35<5:31:10,  1.62it/s]
 44%|████▍     | 25473/57600 [4:27:36<5:53:40,  1.51it/s]
 44%|████▍     | 25474/57600 [4:27:37<5:39:47,  1.58it/s]
 44%|████▍     | 25475/57600 [4:27:37<5:32:27,  1.61it/s]
 44%|████▍     | 25476/57600 [4:27:38<5:34:10,  1.60it/s]
 44%|████▍     | 25477/57600 [4:27:39<5:47:55,  1.54it/s]
 44%|████▍     | 25478/57600 [4:27:39<5:43:21,  1.56it/s]
 44%|████▍     | 25479/57600 [4:27:40<5:50:31,  1.53it/s]
 44%|████▍     | 25480/57600 [4:27:40<5:37:25,  1.59it/s]
                                                         
{'loss': 1.1734, 'learning_rate': 6.036236933797909e-07, 'epoch': 281.24}

 44%|████▍     | 25480/57600 [4:27:40<5:37:25,  1.59it/s]
 44%|████▍     | 25481/57600 [4:27:41<5:35:01,  1.60it/s]
 44%|████▍     | 25482/57600 [4:27:42<5:27:11,  1.64it/s]
 44%|████▍     | 25483/57600 [4:27:42<5:27:56,  1.63it/s]
 44%|████▍     | 25484/57600 [4:27:43<5:27:43,  1.63it/s]
 44%|████▍     | 25485/57600 [4:27:44<5:28:24,  1.63it/s]
 44%|████▍     | 25486/57600 [4:27:44<5:26:11,  1.64it/s]
 44%|████▍     | 25487/57600 [4:27:45<5:39:33,  1.58it/s]
 44%|████▍     | 25488/57600 [4:27:45<5:45:55,  1.55it/s]
 44%|████▍     | 25489/57600 [4:27:46<5:46:23,  1.54it/s]
 44%|████▍     | 25490/57600 [4:27:47<5:33:04,  1.61it/s]
 44%|████▍     | 25491/57600 [4:27:47<5:35:16,  1.60it/s]
 44%|████▍     | 25492/57600 [4:27:48<5:40:47,  1.57it/s]
 44%|████▍     | 25493/57600 [4:27:49<5:30:27,  1.62it/s]
 44%|████▍     | 25494/57600 [4:27:49<5:41:48,  1.57it/s]
 44%|████▍     | 25495/57600 [4:27:50<5:36:51,  1.59it/s]
 44%|████▍     | 25496/57600 [4:27:50<5:31:54,  1.61it/s]
 44%|████▍     | 25497/57600 [4:27:51<5:21:27,  1.66it/s]
 44%|████▍     | 25498/57600 [4:27:52<5:30:01,  1.62it/s]
 44%|████▍     | 25499/57600 [4:27:52<5:27:35,  1.63it/s]
 44%|████▍     | 25500/57600 [4:27:53<5:22:33,  1.66it/s]
                                                         
{'loss': 1.2108, 'learning_rate': 6.033101045296167e-07, 'epoch': 281.46}

 44%|████▍     | 25500/57600 [4:27:53<5:22:33,  1.66it/s]
 44%|████▍     | 25501/57600 [4:27:53<5:19:43,  1.67it/s]
 44%|████▍     | 25502/57600 [4:27:54<5:12:55,  1.71it/s]
 44%|████▍     | 25503/57600 [4:27:55<5:31:11,  1.62it/s]
 44%|████▍     | 25504/57600 [4:27:55<5:22:53,  1.66it/s]
 44%|████▍     | 25505/57600 [4:27:56<5:22:20,  1.66it/s]
 44%|████▍     | 25506/57600 [4:27:56<5:23:02,  1.66it/s]
 44%|████▍     | 25507/57600 [4:27:57<5:25:23,  1.64it/s]
 44%|████▍     | 25508/57600 [4:27:58<5:30:39,  1.62it/s]
 44%|████▍     | 25509/57600 [4:27:58<5:36:15,  1.59it/s]
 44%|████▍     | 25510/57600 [4:27:59<5:32:41,  1.61it/s]
 44%|████▍     | 25511/57600 [4:28:00<5:36:49,  1.59it/s]
 44%|████▍     | 25512/57600 [4:28:00<5:43:02,  1.56it/s]
 44%|████▍     | 25513/57600 [4:28:01<5:36:58,  1.59it/s]
 44%|████▍     | 25514/57600 [4:28:02<5:33:00,  1.61it/s]
 44%|████▍     | 25515/57600 [4:28:02<5:30:15,  1.62it/s]
 44%|████▍     | 25516/57600 [4:28:03<5:37:46,  1.58it/s]
 44%|████▍     | 25517/57600 [4:28:03<5:41:47,  1.56it/s]
 44%|████▍     | 25518/57600 [4:28:04<5:40:36,  1.57it/s]
 44%|████▍     | 25519/57600 [4:28:05<5:40:54,  1.57it/s]
 44%|████▍     | 25520/57600 [4:28:05<5:44:37,  1.55it/s]
                                                         
{'loss': 1.1953, 'learning_rate': 6.029965156794424e-07, 'epoch': 281.68}

 44%|████▍     | 25520/57600 [4:28:05<5:44:37,  1.55it/s]
 44%|████▍     | 25521/57600 [4:28:06<5:41:06,  1.57it/s]
 44%|████▍     | 25522/57600 [4:28:07<5:37:02,  1.59it/s]
 44%|████▍     | 25523/57600 [4:28:07<5:49:20,  1.53it/s]
 44%|████▍     | 25524/57600 [4:28:08<5:49:36,  1.53it/s]
 44%|████▍     | 25525/57600 [4:28:09<5:33:45,  1.60it/s]
 44%|████▍     | 25526/57600 [4:28:09<5:30:01,  1.62it/s]
 44%|████▍     | 25527/57600 [4:28:10<5:23:19,  1.65it/s]
 44%|████▍     | 25528/57600 [4:28:10<5:30:55,  1.62it/s]
 44%|████▍     | 25529/57600 [4:28:11<5:24:50,  1.65it/s]
 44%|████▍     | 25530/57600 [4:28:12<5:33:05,  1.60it/s]
 44%|████▍     | 25531/57600 [4:28:12<5:25:04,  1.64it/s]
 44%|████▍     | 25532/57600 [4:28:13<5:16:04,  1.69it/s]
 44%|████▍     | 25533/57600 [4:28:13<5:24:03,  1.65it/s]
 44%|████▍     | 25534/57600 [4:28:14<5:22:02,  1.66it/s]
 44%|████▍     | 25535/57600 [4:28:15<5:28:09,  1.63it/s]
 44%|████▍     | 25536/57600 [4:28:15<5:36:36,  1.59it/s]
 44%|████▍     | 25537/57600 [4:28:16<5:38:10,  1.58it/s]
 44%|████▍     | 25538/57600 [4:28:17<5:40:55,  1.57it/s]
 44%|████▍     | 25539/57600 [4:28:17<5:34:26,  1.60it/s]
 44%|████▍     | 25540/57600 [4:28:18<5:38:59,  1.58it/s]
                                                         
{'loss': 1.2069, 'learning_rate': 6.026829268292683e-07, 'epoch': 281.9}

 44%|████▍     | 25540/57600 [4:28:18<5:38:59,  1.58it/s]
 44%|████▍     | 25541/57600 [4:28:19<5:47:04,  1.54it/s]
 44%|████▍     | 25542/57600 [4:28:19<5:43:21,  1.56it/s]
 44%|████▍     | 25543/57600 [4:28:20<5:43:54,  1.55it/s]
 44%|████▍     | 25544/57600 [4:28:20<5:36:15,  1.59it/s]
 44%|████▍     | 25545/57600 [4:28:21<5:27:06,  1.63it/s]
 44%|████▍     | 25546/57600 [4:28:22<5:29:56,  1.62it/s]
 44%|████▍     | 25547/57600 [4:28:22<5:32:03,  1.61it/s]
 44%|████▍     | 25548/57600 [4:28:23<5:29:58,  1.62it/s]
 44%|████▍     | 25549/57600 [4:28:23<5:34:12,  1.60it/s]
 44%|████▍     | 25550/57600 [4:28:24<5:55:53,  1.50it/s]
 44%|████▍     | 25551/57600 [4:28:25<5:48:52,  1.53it/s]
 44%|████▍     | 25552/57600 [4:28:25<5:46:43,  1.54it/s]
 44%|████▍     | 25553/57600 [4:28:26<5:43:17,  1.56it/s]
 44%|████▍     | 25554/57600 [4:28:27<5:41:20,  1.56it/s]
 44%|████▍     | 25555/57600 [4:28:27<5:33:45,  1.60it/s]
 44%|████▍     | 25556/57600 [4:28:28<5:36:23,  1.59it/s]
 44%|████▍     | 25557/57600 [4:28:29<5:30:39,  1.62it/s]
 44%|████▍     | 25558/57600 [4:28:29<5:28:00,  1.63it/s]
 44%|████▍     | 25559/57600 [4:28:30<5:38:02,  1.58it/s]
 44%|████▍     | 25560/57600 [4:28:30<5:29:23,  1.62it/s]
                                                         
{'loss': 1.2031, 'learning_rate': 6.023693379790941e-07, 'epoch': 282.12}

 44%|████▍     | 25560/57600 [4:28:30<5:29:23,  1.62it/s]
 44%|████▍     | 25561/57600 [4:28:31<5:23:39,  1.65it/s]
 44%|████▍     | 25562/57600 [4:28:32<5:22:02,  1.66it/s]
 44%|████▍     | 25563/57600 [4:28:32<5:18:21,  1.68it/s]
 44%|████▍     | 25564/57600 [4:28:33<5:15:14,  1.69it/s]
 44%|████▍     | 25565/57600 [4:28:33<5:20:47,  1.66it/s]
 44%|████▍     | 25566/57600 [4:28:34<5:24:14,  1.65it/s]
 44%|████▍     | 25567/57600 [4:28:35<5:32:55,  1.60it/s]
 44%|████▍     | 25568/57600 [4:28:35<5:27:50,  1.63it/s]
 44%|████▍     | 25569/57600 [4:28:36<5:36:56,  1.58it/s]
 44%|████▍     | 25570/57600 [4:28:37<5:35:25,  1.59it/s]
 44%|████▍     | 25571/57600 [4:28:37<5:39:40,  1.57it/s]
 44%|████▍     | 25572/57600 [4:28:38<5:33:56,  1.60it/s]
 44%|████▍     | 25573/57600 [4:28:38<5:34:00,  1.60it/s]
 44%|████▍     | 25574/57600 [4:28:39<5:38:07,  1.58it/s]
 44%|████▍     | 25575/57600 [4:28:40<5:29:20,  1.62it/s]
 44%|████▍     | 25576/57600 [4:28:40<5:21:04,  1.66it/s]
 44%|████▍     | 25577/57600 [4:28:41<5:17:11,  1.68it/s]
 44%|████▍     | 25578/57600 [4:28:41<5:18:44,  1.67it/s]
 44%|████▍     | 25579/57600 [4:28:42<5:12:39,  1.71it/s]
 44%|████▍     | 25580/57600 [4:28:43<5:21:32,  1.66it/s]
                                                         
{'loss': 1.2203, 'learning_rate': 6.020557491289198e-07, 'epoch': 282.34}

 44%|████▍     | 25580/57600 [4:28:43<5:21:32,  1.66it/s]
 44%|████▍     | 25581/57600 [4:28:43<5:32:41,  1.60it/s]
 44%|████▍     | 25582/57600 [4:28:44<5:23:12,  1.65it/s]
 44%|████▍     | 25583/57600 [4:28:44<5:29:07,  1.62it/s]
 44%|████▍     | 25584/57600 [4:28:45<5:34:35,  1.59it/s]
 44%|████▍     | 25585/57600 [4:28:46<5:34:04,  1.60it/s]
 44%|████▍     | 25586/57600 [4:28:46<5:46:09,  1.54it/s]
 44%|████▍     | 25587/57600 [4:28:47<5:39:52,  1.57it/s]
 44%|████▍     | 25588/57600 [4:28:48<5:50:32,  1.52it/s]
 44%|████▍     | 25589/57600 [4:28:48<5:37:15,  1.58it/s]
 44%|████▍     | 25590/57600 [4:28:49<5:34:21,  1.60it/s]
 44%|████▍     | 25591/57600 [4:28:50<5:35:24,  1.59it/s]
 44%|████▍     | 25592/57600 [4:28:50<5:26:30,  1.63it/s]
 44%|████▍     | 25593/57600 [4:28:51<5:24:03,  1.65it/s]
 44%|████▍     | 25594/57600 [4:28:51<5:19:05,  1.67it/s]
 44%|████▍     | 25595/57600 [4:28:52<5:20:13,  1.67it/s]
 44%|████▍     | 25596/57600 [4:28:53<5:14:25,  1.70it/s]
 44%|████▍     | 25597/57600 [4:28:53<5:22:39,  1.65it/s]
 44%|████▍     | 25598/57600 [4:28:54<5:21:01,  1.66it/s]
 44%|████▍     | 25599/57600 [4:28:54<5:14:14,  1.70it/s]
 44%|████▍     | 25600/57600 [4:28:55<5:20:11,  1.67it/s]
                                                         
{'loss': 1.232, 'learning_rate': 6.017421602787457e-07, 'epoch': 282.56}

 44%|████▍     | 25600/57600 [4:28:55<5:20:11,  1.67it/s]
 44%|████▍     | 25601/57600 [4:28:56<5:43:30,  1.55it/s]
 44%|████▍     | 25602/57600 [4:28:56<5:32:50,  1.60it/s]
 44%|████▍     | 25603/57600 [4:28:57<5:38:02,  1.58it/s]
 44%|████▍     | 25604/57600 [4:28:58<5:38:19,  1.58it/s]
 44%|████▍     | 25605/57600 [4:28:58<5:34:26,  1.59it/s]
 44%|████▍     | 25606/57600 [4:28:59<5:41:14,  1.56it/s]
 44%|████▍     | 25607/57600 [4:28:59<5:34:36,  1.59it/s]
 44%|████▍     | 25608/57600 [4:29:00<5:36:24,  1.58it/s]
 44%|████▍     | 25609/57600 [4:29:01<5:32:27,  1.60it/s]
 44%|████▍     | 25610/57600 [4:29:01<5:23:03,  1.65it/s]
 44%|████▍     | 25611/57600 [4:29:02<5:28:53,  1.62it/s]
 44%|████▍     | 25612/57600 [4:29:03<5:30:25,  1.61it/s]
 44%|████▍     | 25613/57600 [4:29:03<5:40:04,  1.57it/s]
 44%|████▍     | 25614/57600 [4:29:04<5:41:19,  1.56it/s]
 44%|████▍     | 25615/57600 [4:29:04<5:39:51,  1.57it/s]
 44%|████▍     | 25616/57600 [4:29:05<5:45:39,  1.54it/s]
 44%|████▍     | 25617/57600 [4:29:06<5:46:14,  1.54it/s]
 44%|████▍     | 25618/57600 [4:29:06<5:44:15,  1.55it/s]
 44%|████▍     | 25619/57600 [4:29:07<5:38:02,  1.58it/s]
 44%|████▍     | 25620/57600 [4:29:08<5:26:43,  1.63it/s]
                                                         
{'loss': 1.1678, 'learning_rate': 6.014285714285714e-07, 'epoch': 282.78}

 44%|████▍     | 25620/57600 [4:29:08<5:26:43,  1.63it/s]
 44%|████▍     | 25621/57600 [4:29:08<5:21:49,  1.66it/s]
 44%|████▍     | 25622/57600 [4:29:09<5:25:34,  1.64it/s]
 44%|████▍     | 25623/57600 [4:29:09<5:32:35,  1.60it/s]
 44%|████▍     | 25624/57600 [4:29:10<5:46:31,  1.54it/s]
 44%|████▍     | 25625/57600 [4:29:11<5:44:05,  1.55it/s]
 44%|████▍     | 25626/57600 [4:29:11<5:34:41,  1.59it/s]
 44%|████▍     | 25627/57600 [4:29:12<5:26:11,  1.63it/s]
 44%|████▍     | 25628/57600 [4:29:13<5:25:15,  1.64it/s]
 44%|████▍     | 25629/57600 [4:29:13<5:24:56,  1.64it/s]
 44%|████▍     | 25630/57600 [4:29:14<5:26:30,  1.63it/s]
 44%|████▍     | 25631/57600 [4:29:14<5:32:22,  1.60it/s]
 44%|████▍     | 25632/57600 [4:29:15<5:38:49,  1.57it/s]
 45%|████▍     | 25633/57600 [4:29:16<5:35:02,  1.59it/s]
 45%|████▍     | 25634/57600 [4:29:16<5:27:57,  1.62it/s]
 45%|████▍     | 25635/57600 [4:29:17<5:28:11,  1.62it/s]
 45%|████▍     | 25636/57600 [4:29:18<5:37:30,  1.58it/s]
 45%|████▍     | 25637/57600 [4:29:18<5:36:57,  1.58it/s]
 45%|████▍     | 25638/57600 [4:29:19<5:38:48,  1.57it/s]
 45%|████▍     | 25639/57600 [4:29:20<5:43:54,  1.55it/s]
 45%|████▍     | 25640/57600 [4:29:20<5:43:49,  1.55it/s]
                                                         
{'loss': 1.223, 'learning_rate': 6.011149825783972e-07, 'epoch': 283.0}

 45%|████▍     | 25640/57600 [4:29:20<5:43:49,  1.55it/s]
 45%|████▍     | 25641/57600 [4:29:21<5:35:27,  1.59it/s]
 45%|████▍     | 25642/57600 [4:29:21<5:26:47,  1.63it/s]
 45%|████▍     | 25643/57600 [4:29:22<5:32:49,  1.60it/s]
 45%|████▍     | 25644/57600 [4:29:23<5:32:58,  1.60it/s]
 45%|████▍     | 25645/57600 [4:29:23<5:30:37,  1.61it/s]
 45%|████▍     | 25646/57600 [4:29:24<5:26:50,  1.63it/s]
 45%|████▍     | 25647/57600 [4:29:24<5:25:11,  1.64it/s]
 45%|████▍     | 25648/57600 [4:29:25<5:30:12,  1.61it/s]
 45%|████▍     | 25649/57600 [4:29:26<5:32:57,  1.60it/s]
 45%|████▍     | 25650/57600 [4:29:26<5:36:12,  1.58it/s]
 45%|████▍     | 25651/57600 [4:29:27<5:34:15,  1.59it/s]
 45%|████▍     | 25652/57600 [4:29:28<5:26:49,  1.63it/s]
 45%|████▍     | 25653/57600 [4:29:28<5:27:05,  1.63it/s]
 45%|████▍     | 25654/57600 [4:29:29<5:33:10,  1.60it/s]
 45%|████▍     | 25655/57600 [4:29:30<5:40:40,  1.56it/s]
 45%|████▍     | 25656/57600 [4:29:30<5:36:15,  1.58it/s]
 45%|████▍     | 25657/57600 [4:29:31<5:33:36,  1.60it/s]
 45%|████▍     | 25658/57600 [4:29:31<5:25:10,  1.64it/s]
 45%|████▍     | 25659/57600 [4:29:32<5:25:56,  1.63it/s]
 45%|████▍     | 25660/57600 [4:29:33<5:32:09,  1.60it/s]
                                                         
{'loss': 1.1983, 'learning_rate': 6.008013937282229e-07, 'epoch': 283.22}

 45%|████▍     | 25660/57600 [4:29:33<5:32:09,  1.60it/s]
 45%|████▍     | 25661/57600 [4:29:33<5:27:57,  1.62it/s]
 45%|████▍     | 25662/57600 [4:29:34<5:20:26,  1.66it/s]
 45%|████▍     | 25663/57600 [4:29:34<5:18:03,  1.67it/s]
 45%|████▍     | 25664/57600 [4:29:35<5:13:49,  1.70it/s]
 45%|████▍     | 25665/57600 [4:29:36<5:23:57,  1.64it/s]
 45%|████▍     | 25666/57600 [4:29:36<5:36:02,  1.58it/s]
 45%|████▍     | 25667/57600 [4:29:37<5:34:18,  1.59it/s]
 45%|████▍     | 25668/57600 [4:29:38<5:42:17,  1.55it/s]
 45%|████▍     | 25669/57600 [4:29:38<5:58:01,  1.49it/s]
 45%|████▍     | 25670/57600 [4:29:39<5:42:43,  1.55it/s]
 45%|████▍     | 25671/57600 [4:29:39<5:32:09,  1.60it/s]
 45%|████▍     | 25672/57600 [4:29:40<5:35:03,  1.59it/s]
 45%|████▍     | 25673/57600 [4:29:41<5:35:22,  1.59it/s]
 45%|████▍     | 25674/57600 [4:29:41<5:35:09,  1.59it/s]
 45%|████▍     | 25675/57600 [4:29:42<5:23:43,  1.64it/s]
 45%|████▍     | 25676/57600 [4:29:42<5:18:23,  1.67it/s]
 45%|████▍     | 25677/57600 [4:29:43<5:35:53,  1.58it/s]
 45%|████▍     | 25678/57600 [4:29:44<5:26:03,  1.63it/s]
 45%|████▍     | 25679/57600 [4:29:44<5:20:00,  1.66it/s]
 45%|████▍     | 25680/57600 [4:29:45<5:20:50,  1.66it/s]
                                                         
{'loss': 1.2263, 'learning_rate': 6.004878048780488e-07, 'epoch': 283.44}

 45%|████▍     | 25680/57600 [4:29:45<5:20:50,  1.66it/s]
 45%|████▍     | 25681/57600 [4:29:46<5:31:14,  1.61it/s]
 45%|████▍     | 25682/57600 [4:29:46<5:28:50,  1.62it/s]
 45%|████▍     | 25683/57600 [4:29:47<5:54:25,  1.50it/s]
 45%|████▍     | 25684/57600 [4:29:48<5:51:03,  1.52it/s]
 45%|████▍     | 25685/57600 [4:29:48<5:48:45,  1.53it/s]
 45%|████▍     | 25686/57600 [4:29:49<5:46:04,  1.54it/s]
 45%|████▍     | 25687/57600 [4:29:49<5:32:15,  1.60it/s]
 45%|████▍     | 25688/57600 [4:29:50<5:44:17,  1.54it/s]
 45%|████▍     | 25689/57600 [4:29:51<5:35:17,  1.59it/s]
 45%|████▍     | 25690/57600 [4:29:51<5:33:24,  1.60it/s]
 45%|████▍     | 25691/57600 [4:29:52<5:32:41,  1.60it/s]
 45%|████▍     | 25692/57600 [4:29:53<5:40:24,  1.56it/s]
 45%|████▍     | 25693/57600 [4:29:53<5:40:53,  1.56it/s]
 45%|████▍     | 25694/57600 [4:29:54<5:38:02,  1.57it/s]
 45%|████▍     | 25695/57600 [4:29:55<5:30:22,  1.61it/s]
 45%|████▍     | 25696/57600 [4:29:55<5:29:09,  1.62it/s]
 45%|████▍     | 25697/57600 [4:29:56<5:28:14,  1.62it/s]
 45%|████▍     | 25698/57600 [4:29:56<5:22:03,  1.65it/s]
 45%|████▍     | 25699/57600 [4:29:57<5:20:17,  1.66it/s]
 45%|████▍     | 25700/57600 [4:29:58<5:26:40,  1.63it/s]
                                                         
{'loss': 1.1873, 'learning_rate': 6.001742160278745e-07, 'epoch': 283.66}

 45%|████▍     | 25700/57600 [4:29:58<5:26:40,  1.63it/s]
 45%|████▍     | 25701/57600 [4:29:58<5:31:18,  1.60it/s]
 45%|████▍     | 25702/57600 [4:29:59<5:28:37,  1.62it/s]
 45%|████▍     | 25703/57600 [4:29:59<5:27:41,  1.62it/s]
 45%|████▍     | 25704/57600 [4:30:00<5:17:07,  1.68it/s]
 45%|████▍     | 25705/57600 [4:30:01<5:19:44,  1.66it/s]
 45%|████▍     | 25706/57600 [4:30:01<5:28:31,  1.62it/s]
 45%|████▍     | 25707/57600 [4:30:02<5:26:31,  1.63it/s]
 45%|████▍     | 25708/57600 [4:30:03<5:26:44,  1.63it/s]
 45%|████▍     | 25709/57600 [4:30:03<5:18:57,  1.67it/s]
 45%|████▍     | 25710/57600 [4:30:04<5:25:00,  1.64it/s]
 45%|████▍     | 25711/57600 [4:30:04<5:22:43,  1.65it/s]
 45%|████▍     | 25712/57600 [4:30:05<5:35:41,  1.58it/s]
 45%|████▍     | 25713/57600 [4:30:06<5:40:28,  1.56it/s]
 45%|████▍     | 25714/57600 [4:30:06<5:35:49,  1.58it/s]
 45%|████▍     | 25715/57600 [4:30:07<5:52:19,  1.51it/s]
 45%|████▍     | 25716/57600 [4:30:08<5:53:34,  1.50it/s]
 45%|████▍     | 25717/57600 [4:30:08<5:35:52,  1.58it/s]
 45%|████▍     | 25718/57600 [4:30:09<5:22:31,  1.65it/s]
 45%|████▍     | 25719/57600 [4:30:09<5:23:20,  1.64it/s]
 45%|████▍     | 25720/57600 [4:30:10<5:15:10,  1.69it/s]
                                                         
{'loss': 1.1983, 'learning_rate': 5.998606271777003e-07, 'epoch': 283.89}

 45%|████▍     | 25720/57600 [4:30:10<5:15:10,  1.69it/s]
 45%|████▍     | 25721/57600 [4:30:11<5:14:48,  1.69it/s]
 45%|████▍     | 25722/57600 [4:30:11<5:09:11,  1.72it/s]
 45%|████▍     | 25723/57600 [4:30:12<5:27:03,  1.62it/s]
 45%|████▍     | 25724/57600 [4:30:12<5:22:05,  1.65it/s]
 45%|████▍     | 25725/57600 [4:30:13<5:15:36,  1.68it/s]
 45%|████▍     | 25726/57600 [4:30:14<5:12:04,  1.70it/s]
 45%|████▍     | 25727/57600 [4:30:14<5:13:10,  1.70it/s]
 45%|████▍     | 25728/57600 [4:30:15<5:11:55,  1.70it/s]
 45%|████▍     | 25729/57600 [4:30:15<5:16:34,  1.68it/s]
 45%|████▍     | 25730/57600 [4:30:16<5:17:46,  1.67it/s]
 45%|████▍     | 25731/57600 [4:30:17<5:31:11,  1.60it/s]
 45%|████▍     | 25732/57600 [4:30:17<5:24:02,  1.64it/s]
 45%|████▍     | 25733/57600 [4:30:18<5:27:58,  1.62it/s]
 45%|████▍     | 25734/57600 [4:30:18<5:31:59,  1.60it/s]
 45%|████▍     | 25735/57600 [4:30:19<5:32:04,  1.60it/s]
 45%|████▍     | 25736/57600 [4:30:20<5:32:22,  1.60it/s]
 45%|████▍     | 25737/57600 [4:30:20<5:34:58,  1.59it/s]
 45%|████▍     | 25738/57600 [4:30:21<5:31:12,  1.60it/s]
 45%|████▍     | 25739/57600 [4:30:22<5:45:47,  1.54it/s]
 45%|████▍     | 25740/57600 [4:30:22<5:47:23,  1.53it/s]
                                                         
{'loss': 1.2363, 'learning_rate': 5.995470383275261e-07, 'epoch': 284.11}

 45%|████▍     | 25740/57600 [4:30:22<5:47:23,  1.53it/s]
 45%|████▍     | 25741/57600 [4:30:23<5:35:58,  1.58it/s]
 45%|████▍     | 25742/57600 [4:30:23<5:29:18,  1.61it/s]
 45%|████▍     | 25743/57600 [4:30:24<5:33:03,  1.59it/s]
 45%|████▍     | 25744/57600 [4:30:25<5:24:52,  1.63it/s]
 45%|████▍     | 25745/57600 [4:30:25<5:17:09,  1.67it/s]
 45%|████▍     | 25746/57600 [4:30:26<5:20:45,  1.66it/s]
 45%|████▍     | 25747/57600 [4:30:26<5:16:38,  1.68it/s]
 45%|████▍     | 25748/57600 [4:30:27<5:11:22,  1.70it/s]
 45%|████▍     | 25749/57600 [4:30:28<5:10:37,  1.71it/s]
 45%|████▍     | 25750/57600 [4:30:28<5:04:13,  1.74it/s]
 45%|████▍     | 25751/57600 [4:30:29<5:06:58,  1.73it/s]
 45%|████▍     | 25752/57600 [4:30:29<5:19:38,  1.66it/s]
 45%|████▍     | 25753/57600 [4:30:30<5:22:27,  1.65it/s]
 45%|████▍     | 25754/57600 [4:30:31<5:11:59,  1.70it/s]
 45%|████▍     | 25755/57600 [4:30:31<5:23:28,  1.64it/s]
 45%|████▍     | 25756/57600 [4:30:32<5:34:04,  1.59it/s]
 45%|████▍     | 25757/57600 [4:30:33<5:33:39,  1.59it/s]
 45%|████▍     | 25758/57600 [4:30:33<5:42:09,  1.55it/s]
 45%|████▍     | 25759/57600 [4:30:34<5:42:26,  1.55it/s]
 45%|████▍     | 25760/57600 [4:30:34<5:38:32,  1.57it/s]
                                                         
{'loss': 1.2258, 'learning_rate': 5.992334494773519e-07, 'epoch': 284.33}

 45%|████▍     | 25760/57600 [4:30:34<5:38:32,  1.57it/s]
 45%|████▍     | 25761/57600 [4:30:35<5:40:14,  1.56it/s]
 45%|████▍     | 25762/57600 [4:30:36<5:30:48,  1.60it/s]
 45%|████▍     | 25763/57600 [4:30:36<5:22:52,  1.64it/s]
 45%|████▍     | 25764/57600 [4:30:37<5:25:50,  1.63it/s]
 45%|████▍     | 25765/57600 [4:30:38<5:26:45,  1.62it/s]
 45%|████▍     | 25766/57600 [4:30:38<5:24:38,  1.63it/s]
 45%|████▍     | 25767/57600 [4:30:39<5:22:33,  1.64it/s]
 45%|████▍     | 25768/57600 [4:30:39<5:20:14,  1.66it/s]
 45%|████▍     | 25769/57600 [4:30:40<5:19:09,  1.66it/s]
 45%|████▍     | 25770/57600 [4:30:41<5:18:36,  1.67it/s]
 45%|████▍     | 25771/57600 [4:30:41<5:17:01,  1.67it/s]
 45%|████▍     | 25772/57600 [4:30:42<5:19:39,  1.66it/s]
 45%|████▍     | 25773/57600 [4:30:42<5:21:49,  1.65it/s]
 45%|████▍     | 25774/57600 [4:30:43<5:15:45,  1.68it/s]
 45%|████▍     | 25775/57600 [4:30:44<5:25:27,  1.63it/s]
 45%|████▍     | 25776/57600 [4:30:44<5:20:08,  1.66it/s]
 45%|████▍     | 25777/57600 [4:30:45<5:33:07,  1.59it/s]
 45%|████▍     | 25778/57600 [4:30:45<5:28:09,  1.62it/s]
 45%|████▍     | 25779/57600 [4:30:46<5:26:05,  1.63it/s]
 45%|████▍     | 25780/57600 [4:30:47<5:20:11,  1.66it/s]
                                                         
{'loss': 1.2215, 'learning_rate': 5.989198606271776e-07, 'epoch': 284.55}

 45%|████▍     | 25780/57600 [4:30:47<5:20:11,  1.66it/s]
 45%|████▍     | 25781/57600 [4:30:47<5:27:15,  1.62it/s]
 45%|████▍     | 25782/57600 [4:30:48<5:25:09,  1.63it/s]
 45%|████▍     | 25783/57600 [4:30:49<5:30:26,  1.60it/s]
 45%|████▍     | 25784/57600 [4:30:49<5:32:38,  1.59it/s]
 45%|████▍     | 25785/57600 [4:30:50<5:33:11,  1.59it/s]
 45%|████▍     | 25786/57600 [4:30:50<5:29:43,  1.61it/s]
 45%|████▍     | 25787/57600 [4:30:51<5:40:18,  1.56it/s]
 45%|████▍     | 25788/57600 [4:30:52<5:44:32,  1.54it/s]
 45%|████▍     | 25789/57600 [4:30:52<5:31:26,  1.60it/s]
 45%|████▍     | 25790/57600 [4:30:53<5:47:25,  1.53it/s]
 45%|████▍     | 25791/57600 [4:30:54<5:50:12,  1.51it/s]
 45%|████▍     | 25792/57600 [4:30:54<5:59:46,  1.47it/s]
 45%|████▍     | 25793/57600 [4:30:55<6:05:39,  1.45it/s]
 45%|████▍     | 25794/57600 [4:30:56<5:53:24,  1.50it/s]
 45%|████▍     | 25795/57600 [4:30:56<5:41:45,  1.55it/s]
 45%|████▍     | 25796/57600 [4:30:57<5:49:20,  1.52it/s]
 45%|████▍     | 25797/57600 [4:30:58<5:44:36,  1.54it/s]
 45%|████▍     | 25798/57600 [4:30:58<5:45:29,  1.53it/s]
 45%|████▍     | 25799/57600 [4:30:59<5:42:01,  1.55it/s]
 45%|████▍     | 25800/57600 [4:31:00<5:30:33,  1.60it/s]
                                                         
{'loss': 1.1816, 'learning_rate': 5.986062717770035e-07, 'epoch': 284.77}

 45%|████▍     | 25800/57600 [4:31:00<5:30:33,  1.60it/s]
 45%|████▍     | 25801/57600 [4:31:00<5:34:26,  1.58it/s]
 45%|████▍     | 25802/57600 [4:31:01<5:26:47,  1.62it/s]
 45%|████▍     | 25803/57600 [4:31:01<5:27:22,  1.62it/s]
 45%|████▍     | 25804/57600 [4:31:02<5:19:08,  1.66it/s]
 45%|████▍     | 25805/57600 [4:31:03<5:28:22,  1.61it/s]
 45%|████▍     | 25806/57600 [4:31:03<5:38:30,  1.57it/s]
 45%|████▍     | 25807/57600 [4:31:04<5:33:30,  1.59it/s]
 45%|████▍     | 25808/57600 [4:31:05<5:30:51,  1.60it/s]
 45%|████▍     | 25809/57600 [4:31:05<5:31:25,  1.60it/s]
 45%|████▍     | 25810/57600 [4:31:06<5:33:14,  1.59it/s]
 45%|████▍     | 25811/57600 [4:31:06<5:33:28,  1.59it/s]
 45%|████▍     | 25812/57600 [4:31:07<5:36:08,  1.58it/s]
 45%|████▍     | 25813/57600 [4:31:08<5:25:09,  1.63it/s]
 45%|████▍     | 25814/57600 [4:31:08<5:31:09,  1.60it/s]
 45%|████▍     | 25815/57600 [4:31:09<5:22:24,  1.64it/s]
 45%|████▍     | 25816/57600 [4:31:10<5:33:55,  1.59it/s]
 45%|████▍     | 25817/57600 [4:31:10<5:29:51,  1.61it/s]
 45%|████▍     | 25818/57600 [4:31:11<5:26:25,  1.62it/s]
 45%|████▍     | 25819/57600 [4:31:11<5:16:19,  1.67it/s]
 45%|████▍     | 25820/57600 [4:31:12<5:20:55,  1.65it/s]
                                                         
{'loss': 1.2286, 'learning_rate': 5.982926829268293e-07, 'epoch': 284.99}

 45%|████▍     | 25820/57600 [4:31:12<5:20:55,  1.65it/s]
 45%|████▍     | 25821/57600 [4:31:13<5:33:46,  1.59it/s]
 45%|████▍     | 25822/57600 [4:31:13<5:39:48,  1.56it/s]
 45%|████▍     | 25823/57600 [4:31:14<5:29:52,  1.61it/s]
 45%|████▍     | 25824/57600 [4:31:14<5:30:44,  1.60it/s]
 45%|████▍     | 25825/57600 [4:31:15<5:23:37,  1.64it/s]
 45%|████▍     | 25826/57600 [4:31:16<5:38:50,  1.56it/s]
 45%|████▍     | 25827/57600 [4:31:16<5:36:02,  1.58it/s]
 45%|████▍     | 25828/57600 [4:31:17<5:32:23,  1.59it/s]
 45%|████▍     | 25829/57600 [4:31:18<5:29:28,  1.61it/s]
 45%|████▍     | 25830/57600 [4:31:18<5:23:30,  1.64it/s]
 45%|████▍     | 25831/57600 [4:31:19<5:21:22,  1.65it/s]
 45%|████▍     | 25832/57600 [4:31:19<5:21:17,  1.65it/s]
 45%|████▍     | 25833/57600 [4:31:20<5:17:10,  1.67it/s]
 45%|████▍     | 25834/57600 [4:31:21<5:16:59,  1.67it/s]
 45%|████▍     | 25835/57600 [4:31:21<5:28:37,  1.61it/s]
 45%|████▍     | 25836/57600 [4:31:22<5:33:49,  1.59it/s]
 45%|████▍     | 25837/57600 [4:31:22<5:26:40,  1.62it/s]
 45%|████▍     | 25838/57600 [4:31:23<5:23:55,  1.63it/s]
 45%|████▍     | 25839/57600 [4:31:24<5:38:26,  1.56it/s]
 45%|████▍     | 25840/57600 [4:31:24<5:32:26,  1.59it/s]
                                                         
{'loss': 1.2205, 'learning_rate': 5.97979094076655e-07, 'epoch': 285.21}

 45%|████▍     | 25840/57600 [4:31:24<5:32:26,  1.59it/s]
 45%|████▍     | 25841/57600 [4:31:25<5:43:51,  1.54it/s]
 45%|████▍     | 25842/57600 [4:31:26<5:55:51,  1.49it/s]
 45%|████▍     | 25843/57600 [4:31:27<6:00:59,  1.47it/s]
 45%|████▍     | 25844/57600 [4:31:27<5:52:10,  1.50it/s]
 45%|████▍     | 25845/57600 [4:31:28<5:36:06,  1.57it/s]
 45%|████▍     | 25846/57600 [4:31:28<5:30:06,  1.60it/s]
 45%|████▍     | 25847/57600 [4:31:29<5:40:37,  1.55it/s]
 45%|████▍     | 25848/57600 [4:31:30<5:29:36,  1.61it/s]
 45%|████▍     | 25849/57600 [4:31:30<5:26:25,  1.62it/s]
 45%|████▍     | 25850/57600 [4:31:31<5:15:11,  1.68it/s]
 45%|████▍     | 25851/57600 [4:31:31<5:23:17,  1.64it/s]
 45%|████▍     | 25852/57600 [4:31:32<5:16:33,  1.67it/s]
 45%|████▍     | 25853/57600 [4:31:33<5:19:05,  1.66it/s]
 45%|████▍     | 25854/57600 [4:31:33<5:40:16,  1.55it/s]
 45%|████▍     | 25855/57600 [4:31:34<5:36:33,  1.57it/s]
 45%|████▍     | 25856/57600 [4:31:35<5:41:47,  1.55it/s]
 45%|████▍     | 25857/57600 [4:31:35<5:34:18,  1.58it/s]
 45%|████▍     | 25858/57600 [4:31:36<5:21:34,  1.65it/s]
 45%|████▍     | 25859/57600 [4:31:36<5:27:30,  1.62it/s]
 45%|████▍     | 25860/57600 [4:31:37<5:23:25,  1.64it/s]
                                                         
{'loss': 1.2523, 'learning_rate': 5.976655052264808e-07, 'epoch': 285.43}

 45%|████▍     | 25860/57600 [4:31:37<5:23:25,  1.64it/s]
 45%|████▍     | 25861/57600 [4:31:38<5:28:42,  1.61it/s]
 45%|████▍     | 25862/57600 [4:31:38<5:29:54,  1.60it/s]
 45%|████▍     | 25863/57600 [4:31:39<5:28:49,  1.61it/s]
 45%|████▍     | 25864/57600 [4:31:39<5:27:32,  1.61it/s]
 45%|████▍     | 25865/57600 [4:31:40<5:24:20,  1.63it/s]
 45%|████▍     | 25866/57600 [4:31:41<5:17:26,  1.67it/s]
 45%|████▍     | 25867/57600 [4:31:41<5:22:53,  1.64it/s]
 45%|████▍     | 25868/57600 [4:31:42<5:28:05,  1.61it/s]
 45%|████▍     | 25869/57600 [4:31:43<5:23:13,  1.64it/s]
 45%|████▍     | 25870/57600 [4:31:43<5:14:24,  1.68it/s]
 45%|████▍     | 25871/57600 [4:31:44<5:30:54,  1.60it/s]
 45%|████▍     | 25872/57600 [4:31:44<5:29:46,  1.60it/s]
 45%|████▍     | 25873/57600 [4:31:45<5:36:49,  1.57it/s]
 45%|████▍     | 25874/57600 [4:31:46<5:32:57,  1.59it/s]
 45%|████▍     | 25875/57600 [4:31:46<5:29:11,  1.61it/s]
 45%|████▍     | 25876/57600 [4:31:47<5:33:36,  1.58it/s]
 45%|████▍     | 25877/57600 [4:31:47<5:23:51,  1.63it/s]
 45%|████▍     | 25878/57600 [4:31:48<5:29:10,  1.61it/s]
 45%|████▍     | 25879/57600 [4:31:49<5:22:03,  1.64it/s]
 45%|████▍     | 25880/57600 [4:31:49<5:23:34,  1.63it/s]
                                                         
{'loss': 1.195, 'learning_rate': 5.973519163763066e-07, 'epoch': 285.65}

 45%|████▍     | 25880/57600 [4:31:49<5:23:34,  1.63it/s]
 45%|████▍     | 25881/57600 [4:31:50<5:23:37,  1.63it/s]
 45%|████▍     | 25882/57600 [4:31:51<5:23:17,  1.64it/s]
 45%|████▍     | 25883/57600 [4:31:51<5:35:39,  1.57it/s]
 45%|████▍     | 25884/57600 [4:31:52<5:41:32,  1.55it/s]
 45%|████▍     | 25885/57600 [4:31:53<5:33:35,  1.58it/s]
 45%|████▍     | 25886/57600 [4:31:53<5:24:05,  1.63it/s]
 45%|████▍     | 25887/57600 [4:31:54<5:26:50,  1.62it/s]
 45%|████▍     | 25888/57600 [4:31:54<5:30:48,  1.60it/s]
 45%|████▍     | 25889/57600 [4:31:55<5:19:42,  1.65it/s]
 45%|████▍     | 25890/57600 [4:31:56<5:16:19,  1.67it/s]
 45%|████▍     | 25891/57600 [4:31:56<5:16:58,  1.67it/s]
 45%|████▍     | 25892/57600 [4:31:57<5:20:38,  1.65it/s]
 45%|████▍     | 25893/57600 [4:31:57<5:20:41,  1.65it/s]
 45%|████▍     | 25894/57600 [4:31:58<5:26:02,  1.62it/s]
 45%|████▍     | 25895/57600 [4:31:59<5:28:54,  1.61it/s]
 45%|████▍     | 25896/57600 [4:31:59<5:24:32,  1.63it/s]
 45%|████▍     | 25897/57600 [4:32:00<5:30:38,  1.60it/s]
 45%|████▍     | 25898/57600 [4:32:00<5:25:32,  1.62it/s]
 45%|████▍     | 25899/57600 [4:32:01<5:29:36,  1.60it/s]
 45%|████▍     | 25900/57600 [4:32:02<5:30:37,  1.60it/s]
                                                         
{'loss': 1.2195, 'learning_rate': 5.970383275261324e-07, 'epoch': 285.87}

 45%|████▍     | 25900/57600 [4:32:02<5:30:37,  1.60it/s]
 45%|████▍     | 25901/57600 [4:32:02<5:21:37,  1.64it/s]
 45%|████▍     | 25902/57600 [4:32:03<5:15:14,  1.68it/s]
 45%|████▍     | 25903/57600 [4:32:04<5:30:30,  1.60it/s]
 45%|████▍     | 25904/57600 [4:32:04<5:28:34,  1.61it/s]
 45%|████▍     | 25905/57600 [4:32:05<5:33:53,  1.58it/s]
 45%|████▍     | 25906/57600 [4:32:05<5:31:46,  1.59it/s]
 45%|████▍     | 25907/57600 [4:32:06<5:29:21,  1.60it/s]
 45%|████▍     | 25908/57600 [4:32:07<5:35:45,  1.57it/s]
 45%|████▍     | 25909/57600 [4:32:07<5:29:53,  1.60it/s]
 45%|████▍     | 25910/57600 [4:32:08<5:21:59,  1.64it/s]
 45%|████▍     | 25911/57600 [4:32:09<5:22:08,  1.64it/s]
 45%|████▍     | 25912/57600 [4:32:09<5:38:51,  1.56it/s]
 45%|████▍     | 25913/57600 [4:32:10<5:38:04,  1.56it/s]
 45%|████▍     | 25914/57600 [4:32:10<5:29:22,  1.60it/s]
 45%|████▍     | 25915/57600 [4:32:11<5:38:47,  1.56it/s]
 45%|████▍     | 25916/57600 [4:32:12<5:34:47,  1.58it/s]
 45%|████▍     | 25917/57600 [4:32:12<5:31:20,  1.59it/s]
 45%|████▍     | 25918/57600 [4:32:13<5:30:04,  1.60it/s]
 45%|████▍     | 25919/57600 [4:32:14<5:27:11,  1.61it/s]
 45%|████▌     | 25920/57600 [4:32:14<5:21:24,  1.64it/s]
                                                         
{'loss': 1.211, 'learning_rate': 5.967247386759581e-07, 'epoch': 286.09}

 45%|████▌     | 25920/57600 [4:32:14<5:21:24,  1.64it/s]
 45%|████▌     | 25921/57600 [4:32:15<5:19:04,  1.65it/s]
 45%|████▌     | 25922/57600 [4:32:15<5:15:14,  1.67it/s]
 45%|████▌     | 25923/57600 [4:32:16<5:23:10,  1.63it/s]
 45%|████▌     | 25924/57600 [4:32:17<5:38:10,  1.56it/s]
 45%|████▌     | 25925/57600 [4:32:17<5:33:13,  1.58it/s]
 45%|████▌     | 25926/57600 [4:32:18<5:32:27,  1.59it/s]
 45%|████▌     | 25927/57600 [4:32:19<5:29:24,  1.60it/s]
 45%|████▌     | 25928/57600 [4:32:19<5:22:59,  1.63it/s]
 45%|████▌     | 25929/57600 [4:32:20<5:32:30,  1.59it/s]
 45%|████▌     | 25930/57600 [4:32:20<5:41:47,  1.54it/s]
 45%|████▌     | 25931/57600 [4:32:21<5:37:59,  1.56it/s]
 45%|████▌     | 25932/57600 [4:32:22<5:39:30,  1.55it/s]
 45%|████▌     | 25933/57600 [4:32:22<5:30:27,  1.60it/s]
 45%|████▌     | 25934/57600 [4:32:23<5:25:08,  1.62it/s]
 45%|████▌     | 25935/57600 [4:32:24<5:20:16,  1.65it/s]
 45%|████▌     | 25936/57600 [4:32:24<5:31:34,  1.59it/s]
 45%|████▌     | 25937/57600 [4:32:25<5:27:13,  1.61it/s]
 45%|████▌     | 25938/57600 [4:32:25<5:15:49,  1.67it/s]
 45%|████▌     | 25939/57600 [4:32:26<5:17:01,  1.66it/s]
 45%|████▌     | 25940/57600 [4:32:27<5:19:20,  1.65it/s]
                                                         
{'loss': 1.2293, 'learning_rate': 5.96411149825784e-07, 'epoch': 286.31}

 45%|████▌     | 25940/57600 [4:32:27<5:19:20,  1.65it/s]
 45%|████▌     | 25941/57600 [4:32:27<5:16:41,  1.67it/s]
 45%|████▌     | 25942/57600 [4:32:28<5:20:58,  1.64it/s]
 45%|████▌     | 25943/57600 [4:32:28<5:27:27,  1.61it/s]
 45%|████▌     | 25944/57600 [4:32:29<5:31:40,  1.59it/s]
 45%|████▌     | 25945/57600 [4:32:30<5:29:34,  1.60it/s]
 45%|████▌     | 25946/57600 [4:32:30<5:28:36,  1.61it/s]
 45%|████▌     | 25947/57600 [4:32:31<5:31:17,  1.59it/s]
 45%|████▌     | 25948/57600 [4:32:32<5:29:44,  1.60it/s]
 45%|████▌     | 25949/57600 [4:32:32<5:30:36,  1.60it/s]
 45%|████▌     | 25950/57600 [4:32:33<5:31:35,  1.59it/s]
 45%|████▌     | 25951/57600 [4:32:33<5:32:43,  1.59it/s]
 45%|████▌     | 25952/57600 [4:32:34<5:23:27,  1.63it/s]
 45%|████▌     | 25953/57600 [4:32:35<5:17:12,  1.66it/s]
 45%|████▌     | 25954/57600 [4:32:35<5:24:53,  1.62it/s]
 45%|████▌     | 25955/57600 [4:32:36<5:32:02,  1.59it/s]
 45%|████▌     | 25956/57600 [4:32:37<5:22:40,  1.63it/s]
 45%|████▌     | 25957/57600 [4:32:37<5:27:53,  1.61it/s]
 45%|████▌     | 25958/57600 [4:32:38<5:27:03,  1.61it/s]
 45%|████▌     | 25959/57600 [4:32:38<5:24:16,  1.63it/s]
 45%|████▌     | 25960/57600 [4:32:39<5:20:41,  1.64it/s]
                                                         
{'loss': 1.2403, 'learning_rate': 5.960975609756097e-07, 'epoch': 286.53}

 45%|████▌     | 25960/57600 [4:32:39<5:20:41,  1.64it/s]
 45%|████▌     | 25961/57600 [4:32:40<5:24:03,  1.63it/s]
 45%|████▌     | 25962/57600 [4:32:40<5:25:04,  1.62it/s]
 45%|████▌     | 25963/57600 [4:32:41<5:17:42,  1.66it/s]
 45%|████▌     | 25964/57600 [4:32:41<5:21:43,  1.64it/s]
 45%|████▌     | 25965/57600 [4:32:42<5:33:09,  1.58it/s]
 45%|████▌     | 25966/57600 [4:32:43<5:34:03,  1.58it/s]
 45%|████▌     | 25967/57600 [4:32:43<5:28:38,  1.60it/s]
 45%|████▌     | 25968/57600 [4:32:44<5:20:35,  1.64it/s]
 45%|████▌     | 25969/57600 [4:32:44<5:18:33,  1.65it/s]
 45%|████▌     | 25970/57600 [4:32:45<5:11:43,  1.69it/s]
 45%|████▌     | 25971/57600 [4:32:46<5:21:36,  1.64it/s]
 45%|████▌     | 25972/57600 [4:32:46<5:31:12,  1.59it/s]
 45%|████▌     | 25973/57600 [4:32:47<5:31:18,  1.59it/s]
 45%|████▌     | 25974/57600 [4:32:48<5:22:29,  1.63it/s]
 45%|████▌     | 25975/57600 [4:32:48<5:31:50,  1.59it/s]
 45%|████▌     | 25976/57600 [4:32:49<5:20:12,  1.65it/s]
 45%|████▌     | 25977/57600 [4:32:49<5:26:01,  1.62it/s]
 45%|████▌     | 25978/57600 [4:32:50<5:25:57,  1.62it/s]
 45%|████▌     | 25979/57600 [4:32:51<5:21:11,  1.64it/s]
 45%|████▌     | 25980/57600 [4:32:51<5:34:12,  1.58it/s]
                                                         
{'loss': 1.1658, 'learning_rate': 5.957839721254355e-07, 'epoch': 286.75}

 45%|████▌     | 25980/57600 [4:32:51<5:34:12,  1.58it/s]
 45%|████▌     | 25981/57600 [4:32:52<5:32:34,  1.58it/s]
 45%|████▌     | 25982/57600 [4:32:53<5:24:57,  1.62it/s]
 45%|████▌     | 25983/57600 [4:32:53<5:16:37,  1.66it/s]
 45%|████▌     | 25984/57600 [4:32:54<5:18:38,  1.65it/s]
 45%|████▌     | 25985/57600 [4:32:54<5:15:45,  1.67it/s]
 45%|████▌     | 25986/57600 [4:32:55<5:27:32,  1.61it/s]
 45%|████▌     | 25987/57600 [4:32:56<5:27:26,  1.61it/s]
 45%|████▌     | 25988/57600 [4:32:56<5:35:25,  1.57it/s]
 45%|████▌     | 25989/57600 [4:32:57<5:26:05,  1.62it/s]
 45%|████▌     | 25990/57600 [4:32:57<5:26:45,  1.61it/s]
 45%|████▌     | 25991/57600 [4:32:58<5:24:51,  1.62it/s]
 45%|████▌     | 25992/57600 [4:32:59<5:24:32,  1.62it/s]
 45%|████▌     | 25993/57600 [4:32:59<5:26:20,  1.61it/s]
 45%|████▌     | 25994/57600 [4:33:00<5:39:43,  1.55it/s]
 45%|████▌     | 25995/57600 [4:33:01<5:36:16,  1.57it/s]
 45%|████▌     | 25996/57600 [4:33:01<5:31:48,  1.59it/s]
 45%|████▌     | 25997/57600 [4:33:02<5:26:27,  1.61it/s]
 45%|████▌     | 25998/57600 [4:33:03<5:28:11,  1.60it/s]
 45%|████▌     | 25999/57600 [4:33:03<5:41:08,  1.54it/s]
 45%|████▌     | 26000/57600 [4:33:04<5:38:58,  1.55it/s]
                                                         
{'loss': 1.1995, 'learning_rate': 5.954703832752612e-07, 'epoch': 286.98}

 45%|████▌     | 26000/57600 [4:33:04<5:38:58,  1.55it/s]
 45%|████▌     | 26001/57600 [4:33:04<5:32:31,  1.58it/s]
 45%|████▌     | 26002/57600 [4:33:05<5:32:59,  1.58it/s]
 45%|████▌     | 26003/57600 [4:33:06<5:42:46,  1.54it/s]
 45%|████▌     | 26004/57600 [4:33:06<5:28:46,  1.60it/s]
 45%|████▌     | 26005/57600 [4:33:07<5:31:18,  1.59it/s]
 45%|████▌     | 26006/57600 [4:33:08<5:20:07,  1.64it/s]
 45%|████▌     | 26007/57600 [4:33:08<5:22:14,  1.63it/s]
 45%|████▌     | 26008/57600 [4:33:09<5:31:07,  1.59it/s]
 45%|████▌     | 26009/57600 [4:33:09<5:35:57,  1.57it/s]
 45%|████▌     | 26010/57600 [4:33:10<5:43:41,  1.53it/s]
 45%|████▌     | 26011/57600 [4:33:11<5:32:49,  1.58it/s]
 45%|████▌     | 26012/57600 [4:33:11<5:28:19,  1.60it/s]
 45%|████▌     | 26013/57600 [4:33:12<5:36:34,  1.56it/s]
 45%|████▌     | 26014/57600 [4:33:13<5:43:56,  1.53it/s]
 45%|████▌     | 26015/57600 [4:33:13<5:30:28,  1.59it/s]
 45%|████▌     | 26016/57600 [4:33:14<5:22:51,  1.63it/s]
 45%|████▌     | 26017/57600 [4:33:14<5:18:36,  1.65it/s]
 45%|████▌     | 26018/57600 [4:33:15<5:24:21,  1.62it/s]
 45%|████▌     | 26019/57600 [4:33:16<5:17:27,  1.66it/s]
 45%|████▌     | 26020/57600 [4:33:16<5:30:07,  1.59it/s]
                                                         
{'loss': 1.2052, 'learning_rate': 5.951567944250872e-07, 'epoch': 287.2}

 45%|████▌     | 26020/57600 [4:33:16<5:30:07,  1.59it/s]
 45%|████▌     | 26021/57600 [4:33:17<5:36:28,  1.56it/s]
 45%|████▌     | 26022/57600 [4:33:18<5:23:16,  1.63it/s]
 45%|████▌     | 26023/57600 [4:33:18<5:28:57,  1.60it/s]
 45%|████▌     | 26024/57600 [4:33:19<5:27:08,  1.61it/s]
 45%|████▌     | 26025/57600 [4:33:19<5:19:59,  1.64it/s]
 45%|████▌     | 26026/57600 [4:33:20<5:30:58,  1.59it/s]
 45%|████▌     | 26027/57600 [4:33:21<5:21:55,  1.63it/s]
 45%|████▌     | 26028/57600 [4:33:21<5:16:34,  1.66it/s]
 45%|████▌     | 26029/57600 [4:33:22<5:20:12,  1.64it/s]
 45%|████▌     | 26030/57600 [4:33:22<5:13:19,  1.68it/s]
 45%|████▌     | 26031/57600 [4:33:23<5:25:29,  1.62it/s]
 45%|████▌     | 26032/57600 [4:33:24<5:22:18,  1.63it/s]
 45%|████▌     | 26033/57600 [4:33:24<5:26:18,  1.61it/s]
 45%|████▌     | 26034/57600 [4:33:25<5:28:12,  1.60it/s]
 45%|████▌     | 26035/57600 [4:33:26<5:23:52,  1.62it/s]
 45%|████▌     | 26036/57600 [4:33:26<5:23:30,  1.63it/s]
 45%|████▌     | 26037/57600 [4:33:27<5:32:43,  1.58it/s]
 45%|████▌     | 26038/57600 [4:33:27<5:27:14,  1.61it/s]
 45%|████▌     | 26039/57600 [4:33:28<5:36:08,  1.56it/s]
 45%|████▌     | 26040/57600 [4:33:29<5:35:48,  1.57it/s]
                                                         
{'loss': 1.2132, 'learning_rate': 5.948432055749128e-07, 'epoch': 287.42}

 45%|████▌     | 26040/57600 [4:33:29<5:35:48,  1.57it/s]
 45%|████▌     | 26041/57600 [4:33:29<5:27:27,  1.61it/s]
 45%|████▌     | 26042/57600 [4:33:30<5:19:12,  1.65it/s]
 45%|████▌     | 26043/57600 [4:33:31<5:28:02,  1.60it/s]
 45%|████▌     | 26044/57600 [4:33:31<5:27:41,  1.60it/s]
 45%|████▌     | 26045/57600 [4:33:32<5:26:20,  1.61it/s]
 45%|████▌     | 26046/57600 [4:33:33<5:36:58,  1.56it/s]
 45%|████▌     | 26047/57600 [4:33:33<5:33:49,  1.58it/s]
 45%|████▌     | 26048/57600 [4:33:34<5:29:09,  1.60it/s]
 45%|████▌     | 26049/57600 [4:33:34<5:23:02,  1.63it/s]
 45%|████▌     | 26050/57600 [4:33:35<5:19:17,  1.65it/s]
 45%|████▌     | 26051/57600 [4:33:36<5:26:39,  1.61it/s]
 45%|████▌     | 26052/57600 [4:33:36<5:23:11,  1.63it/s]
 45%|████▌     | 26053/57600 [4:33:37<5:29:52,  1.59it/s]
 45%|████▌     | 26054/57600 [4:33:37<5:18:59,  1.65it/s]
 45%|████▌     | 26055/57600 [4:33:38<5:25:30,  1.62it/s]
 45%|████▌     | 26056/57600 [4:33:39<5:36:26,  1.56it/s]
 45%|████▌     | 26057/57600 [4:33:39<5:28:14,  1.60it/s]
 45%|████▌     | 26058/57600 [4:33:40<5:23:52,  1.62it/s]
 45%|████▌     | 26059/57600 [4:33:41<5:27:22,  1.61it/s]
 45%|████▌     | 26060/57600 [4:33:41<5:26:31,  1.61it/s]
                                                         
{'loss': 1.2423, 'learning_rate': 5.945296167247386e-07, 'epoch': 287.64}

 45%|████▌     | 26060/57600 [4:33:41<5:26:31,  1.61it/s]
 45%|████▌     | 26061/57600 [4:33:42<5:24:46,  1.62it/s]
 45%|████▌     | 26062/57600 [4:33:42<5:23:47,  1.62it/s]
 45%|████▌     | 26063/57600 [4:33:43<5:24:01,  1.62it/s]
 45%|████▌     | 26064/57600 [4:33:44<5:15:20,  1.67it/s]
 45%|████▌     | 26065/57600 [4:33:44<5:16:41,  1.66it/s]
 45%|████▌     | 26066/57600 [4:33:45<5:23:45,  1.62it/s]
 45%|████▌     | 26067/57600 [4:33:45<5:26:57,  1.61it/s]
 45%|████▌     | 26068/57600 [4:33:46<5:33:38,  1.58it/s]
 45%|████▌     | 26069/57600 [4:33:47<5:35:23,  1.57it/s]
 45%|████▌     | 26070/57600 [4:33:47<5:22:52,  1.63it/s]
 45%|████▌     | 26071/57600 [4:33:48<5:22:57,  1.63it/s]
 45%|████▌     | 26072/57600 [4:33:49<5:24:20,  1.62it/s]
 45%|████▌     | 26073/57600 [4:33:49<5:13:49,  1.67it/s]
 45%|████▌     | 26074/57600 [4:33:50<5:17:05,  1.66it/s]
 45%|████▌     | 26075/57600 [4:33:50<5:17:07,  1.66it/s]
 45%|████▌     | 26076/57600 [4:33:51<5:23:27,  1.62it/s]
 45%|████▌     | 26077/57600 [4:33:52<5:31:16,  1.59it/s]
 45%|████▌     | 26078/57600 [4:33:52<5:24:13,  1.62it/s]
 45%|████▌     | 26079/57600 [4:33:53<5:19:49,  1.64it/s]
 45%|████▌     | 26080/57600 [4:33:53<5:14:10,  1.67it/s]
                                                         
{'loss': 1.2359, 'learning_rate': 5.942160278745645e-07, 'epoch': 287.86}

 45%|████▌     | 26080/57600 [4:33:53<5:14:10,  1.67it/s]
 45%|████▌     | 26081/57600 [4:33:54<5:19:50,  1.64it/s]
 45%|████▌     | 26082/57600 [4:33:55<5:30:52,  1.59it/s]
 45%|████▌     | 26083/57600 [4:33:55<5:22:30,  1.63it/s]
 45%|████▌     | 26084/57600 [4:33:56<5:24:59,  1.62it/s]
 45%|████▌     | 26085/57600 [4:33:56<5:14:54,  1.67it/s]
 45%|████▌     | 26086/57600 [4:33:57<5:15:55,  1.66it/s]
 45%|████▌     | 26087/57600 [4:33:58<5:22:09,  1.63it/s]
 45%|████▌     | 26088/57600 [4:33:58<5:30:34,  1.59it/s]
 45%|████▌     | 26089/57600 [4:33:59<5:28:28,  1.60it/s]
 45%|████▌     | 26090/57600 [4:34:00<5:38:24,  1.55it/s]
 45%|████▌     | 26091/57600 [4:34:00<5:33:26,  1.57it/s]
 45%|████▌     | 26092/57600 [4:34:01<5:27:55,  1.60it/s]
 45%|████▌     | 26093/57600 [4:34:02<5:37:51,  1.55it/s]
 45%|████▌     | 26094/57600 [4:34:02<5:39:28,  1.55it/s]
 45%|████▌     | 26095/57600 [4:34:03<5:39:23,  1.55it/s]
 45%|████▌     | 26096/57600 [4:34:04<5:40:48,  1.54it/s]
 45%|████▌     | 26097/57600 [4:34:04<5:48:14,  1.51it/s]
 45%|████▌     | 26098/57600 [4:34:05<5:34:47,  1.57it/s]
 45%|████▌     | 26099/57600 [4:34:05<5:31:36,  1.58it/s]
 45%|████▌     | 26100/57600 [4:34:06<5:27:09,  1.60it/s]
                                                         
{'loss': 1.1798, 'learning_rate': 5.939024390243902e-07, 'epoch': 288.08}

 45%|████▌     | 26100/57600 [4:34:06<5:27:09,  1.60it/s]
 45%|████▌     | 26101/57600 [4:34:07<5:20:14,  1.64it/s]
 45%|████▌     | 26102/57600 [4:34:07<5:17:58,  1.65it/s]
 45%|████▌     | 26103/57600 [4:34:08<5:27:17,  1.60it/s]
 45%|████▌     | 26104/57600 [4:34:09<5:34:28,  1.57it/s]
 45%|████▌     | 26105/57600 [4:34:09<5:42:30,  1.53it/s]
 45%|████▌     | 26106/57600 [4:34:10<5:47:17,  1.51it/s]
 45%|████▌     | 26107/57600 [4:34:11<5:34:30,  1.57it/s]
 45%|████▌     | 26108/57600 [4:34:11<5:38:43,  1.55it/s]
 45%|████▌     | 26109/57600 [4:34:12<5:25:48,  1.61it/s]
 45%|████▌     | 26110/57600 [4:34:12<5:16:48,  1.66it/s]
 45%|████▌     | 26111/57600 [4:34:13<5:11:13,  1.69it/s]
 45%|████▌     | 26112/57600 [4:34:14<5:23:48,  1.62it/s]
 45%|████▌     | 26113/57600 [4:34:14<5:24:29,  1.62it/s]
 45%|████▌     | 26114/57600 [4:34:15<5:25:33,  1.61it/s]
 45%|████▌     | 26115/57600 [4:34:15<5:20:33,  1.64it/s]
 45%|████▌     | 26116/57600 [4:34:16<5:36:19,  1.56it/s]
 45%|████▌     | 26117/57600 [4:34:17<5:28:54,  1.60it/s]
 45%|████▌     | 26118/57600 [4:34:17<5:31:15,  1.58it/s]
 45%|████▌     | 26119/57600 [4:34:18<5:34:25,  1.57it/s]
 45%|████▌     | 26120/57600 [4:34:19<5:24:12,  1.62it/s]
                                                         
{'loss': 1.1791, 'learning_rate': 5.93588850174216e-07, 'epoch': 288.3}

 45%|████▌     | 26120/57600 [4:34:19<5:24:12,  1.62it/s]
 45%|████▌     | 26121/57600 [4:34:19<5:23:07,  1.62it/s]
 45%|████▌     | 26122/57600 [4:34:20<5:30:32,  1.59it/s]
 45%|████▌     | 26123/57600 [4:34:21<5:42:01,  1.53it/s]
 45%|████▌     | 26124/57600 [4:34:21<5:32:39,  1.58it/s]
 45%|████▌     | 26125/57600 [4:34:22<5:28:30,  1.60it/s]
 45%|████▌     | 26126/57600 [4:34:22<5:23:12,  1.62it/s]
 45%|████▌     | 26127/57600 [4:34:23<5:19:18,  1.64it/s]
 45%|████▌     | 26128/57600 [4:34:23<5:15:55,  1.66it/s]
 45%|████▌     | 26129/57600 [4:34:24<5:15:26,  1.66it/s]
 45%|████▌     | 26130/57600 [4:34:25<5:14:24,  1.67it/s]
 45%|████▌     | 26131/57600 [4:34:25<5:21:39,  1.63it/s]
 45%|████▌     | 26132/57600 [4:34:26<5:26:24,  1.61it/s]
 45%|████▌     | 26133/57600 [4:34:27<5:31:52,  1.58it/s]
 45%|████▌     | 26134/57600 [4:34:27<5:24:50,  1.61it/s]
 45%|████▌     | 26135/57600 [4:34:28<5:23:31,  1.62it/s]
 45%|████▌     | 26136/57600 [4:34:29<5:32:22,  1.58it/s]
 45%|████▌     | 26137/57600 [4:34:29<5:28:11,  1.60it/s]
 45%|████▌     | 26138/57600 [4:34:30<5:26:33,  1.61it/s]
 45%|████▌     | 26139/57600 [4:34:30<5:26:48,  1.60it/s]
 45%|████▌     | 26140/57600 [4:34:31<5:28:54,  1.59it/s]
                                                         
{'loss': 1.1888, 'learning_rate': 5.932752613240418e-07, 'epoch': 288.52}

 45%|████▌     | 26140/57600 [4:34:31<5:28:54,  1.59it/s]
 45%|████▌     | 26141/57600 [4:34:32<5:21:28,  1.63it/s]
 45%|████▌     | 26142/57600 [4:34:32<5:16:48,  1.65it/s]
 45%|████▌     | 26143/57600 [4:34:33<5:22:52,  1.62it/s]
 45%|████▌     | 26144/57600 [4:34:33<5:32:57,  1.57it/s]
 45%|████▌     | 26145/57600 [4:34:34<5:26:39,  1.60it/s]
 45%|████▌     | 26146/57600 [4:34:35<5:20:05,  1.64it/s]
 45%|████▌     | 26147/57600 [4:34:35<5:29:14,  1.59it/s]
 45%|████▌     | 26148/57600 [4:34:36<5:33:44,  1.57it/s]
 45%|████▌     | 26149/57600 [4:34:37<5:27:46,  1.60it/s]
 45%|████▌     | 26150/57600 [4:34:37<5:32:55,  1.57it/s]
 45%|████▌     | 26151/57600 [4:34:38<5:25:54,  1.61it/s]
 45%|████▌     | 26152/57600 [4:34:38<5:30:03,  1.59it/s]
 45%|████▌     | 26153/57600 [4:34:39<5:30:27,  1.59it/s]
 45%|████▌     | 26154/57600 [4:34:40<5:30:45,  1.58it/s]
 45%|████▌     | 26155/57600 [4:34:40<5:31:34,  1.58it/s]
 45%|████▌     | 26156/57600 [4:34:41<5:26:14,  1.61it/s]
 45%|████▌     | 26157/57600 [4:34:42<5:30:31,  1.59it/s]
 45%|████▌     | 26158/57600 [4:34:42<5:22:01,  1.63it/s]
 45%|████▌     | 26159/57600 [4:34:43<5:21:40,  1.63it/s]
 45%|████▌     | 26160/57600 [4:34:43<5:31:49,  1.58it/s]
                                                         
{'loss': 1.1584, 'learning_rate': 5.929616724738677e-07, 'epoch': 288.74}

 45%|████▌     | 26160/57600 [4:34:43<5:31:49,  1.58it/s]
 45%|████▌     | 26161/57600 [4:34:44<5:25:00,  1.61it/s]
 45%|████▌     | 26162/57600 [4:34:45<5:25:11,  1.61it/s]
 45%|████▌     | 26163/57600 [4:34:45<5:23:25,  1.62it/s]
 45%|████▌     | 26164/57600 [4:34:46<5:24:12,  1.62it/s]
 45%|████▌     | 26165/57600 [4:34:47<5:17:28,  1.65it/s]
 45%|████▌     | 26166/57600 [4:34:47<5:31:07,  1.58it/s]
 45%|████▌     | 26167/57600 [4:34:48<5:20:21,  1.64it/s]
 45%|████▌     | 26168/57600 [4:34:48<5:25:30,  1.61it/s]
 45%|████▌     | 26169/57600 [4:34:49<5:28:36,  1.59it/s]
 45%|████▌     | 26170/57600 [4:34:50<5:42:29,  1.53it/s]
 45%|████▌     | 26171/57600 [4:34:50<5:34:15,  1.57it/s]
 45%|████▌     | 26172/57600 [4:34:51<5:26:19,  1.61it/s]
 45%|████▌     | 26173/57600 [4:34:52<5:18:37,  1.64it/s]
 45%|████▌     | 26174/57600 [4:34:52<5:10:16,  1.69it/s]
 45%|████▌     | 26175/57600 [4:34:53<5:08:39,  1.70it/s]
 45%|████▌     | 26176/57600 [4:34:53<5:18:20,  1.65it/s]
 45%|████▌     | 26177/57600 [4:34:54<5:26:16,  1.61it/s]
 45%|████▌     | 26178/57600 [4:34:55<5:18:09,  1.65it/s]
 45%|████▌     | 26179/57600 [4:34:55<5:18:58,  1.64it/s]
 45%|████▌     | 26180/57600 [4:34:56<5:09:56,  1.69it/s]
                                                         
{'loss': 1.2086, 'learning_rate': 5.926480836236933e-07, 'epoch': 288.96}

 45%|████▌     | 26180/57600 [4:34:56<5:09:56,  1.69it/s]
 45%|████▌     | 26181/57600 [4:34:56<5:09:47,  1.69it/s]
 45%|████▌     | 26182/57600 [4:34:57<5:15:37,  1.66it/s]
 45%|████▌     | 26183/57600 [4:34:58<5:27:20,  1.60it/s]
 45%|████▌     | 26184/57600 [4:34:58<5:42:31,  1.53it/s]
 45%|████▌     | 26185/57600 [4:34:59<5:37:16,  1.55it/s]
 45%|████▌     | 26186/57600 [4:35:00<5:27:51,  1.60it/s]
 45%|████▌     | 26187/57600 [4:35:00<5:33:18,  1.57it/s]
 45%|████▌     | 26188/57600 [4:35:01<5:25:51,  1.61it/s]
 45%|████▌     | 26189/57600 [4:35:01<5:27:17,  1.60it/s]
 45%|████▌     | 26190/57600 [4:35:02<5:28:43,  1.59it/s]
 45%|████▌     | 26191/57600 [4:35:03<5:26:01,  1.61it/s]
 45%|████▌     | 26192/57600 [4:35:03<5:36:02,  1.56it/s]
 45%|████▌     | 26193/57600 [4:35:04<5:40:44,  1.54it/s]
 45%|████▌     | 26194/57600 [4:35:05<5:32:26,  1.57it/s]
 45%|████▌     | 26195/57600 [4:35:05<5:33:38,  1.57it/s]
 45%|████▌     | 26196/57600 [4:35:06<5:38:39,  1.55it/s]
 45%|████▌     | 26197/57600 [4:35:07<5:41:11,  1.53it/s]
 45%|████▌     | 26198/57600 [4:35:07<5:29:20,  1.59it/s]
 45%|████▌     | 26199/57600 [4:35:08<5:21:09,  1.63it/s]
 45%|████▌     | 26200/57600 [4:35:08<5:18:27,  1.64it/s]
                                                         
{'loss': 1.2015, 'learning_rate': 5.923344947735191e-07, 'epoch': 289.18}

 45%|████▌     | 26200/57600 [4:35:08<5:18:27,  1.64it/s]
 45%|████▌     | 26201/57600 [4:35:09<5:31:57,  1.58it/s]
 45%|████▌     | 26202/57600 [4:35:10<5:23:21,  1.62it/s]
 45%|████▌     | 26203/57600 [4:35:10<5:36:08,  1.56it/s]
 45%|████▌     | 26204/57600 [4:35:11<5:30:07,  1.59it/s]
 45%|████▌     | 26205/57600 [4:35:11<5:20:10,  1.63it/s]
 45%|████▌     | 26206/57600 [4:35:12<5:22:37,  1.62it/s]
 45%|████▌     | 26207/57600 [4:35:13<5:21:43,  1.63it/s]
 46%|████▌     | 26208/57600 [4:35:13<5:25:09,  1.61it/s]
 46%|████▌     | 26209/57600 [4:35:14<5:19:13,  1.64it/s]
 46%|████▌     | 26210/57600 [4:35:15<5:16:09,  1.65it/s]
 46%|████▌     | 26211/57600 [4:35:15<5:24:12,  1.61it/s]
 46%|████▌     | 26212/57600 [4:35:16<5:32:01,  1.58it/s]
 46%|████▌     | 26213/57600 [4:35:16<5:22:44,  1.62it/s]
 46%|████▌     | 26214/57600 [4:35:17<5:32:06,  1.58it/s]
 46%|████▌     | 26215/57600 [4:35:18<5:27:27,  1.60it/s]
 46%|████▌     | 26216/57600 [4:35:18<5:27:39,  1.60it/s]
 46%|████▌     | 26217/57600 [4:35:19<5:27:24,  1.60it/s]
 46%|████▌     | 26218/57600 [4:35:20<5:18:02,  1.64it/s]
 46%|████▌     | 26219/57600 [4:35:20<5:17:57,  1.64it/s]
 46%|████▌     | 26220/57600 [4:35:21<5:26:07,  1.60it/s]
                                                         
{'loss': 1.1905, 'learning_rate': 5.920209059233449e-07, 'epoch': 289.4}

 46%|████▌     | 26220/57600 [4:35:21<5:26:07,  1.60it/s]
 46%|████▌     | 26221/57600 [4:35:21<5:32:22,  1.57it/s]
 46%|████▌     | 26222/57600 [4:35:22<5:25:06,  1.61it/s]
 46%|████▌     | 26223/57600 [4:35:23<5:28:44,  1.59it/s]
 46%|████▌     | 26224/57600 [4:35:23<5:30:18,  1.58it/s]
 46%|████▌     | 26225/57600 [4:35:24<5:34:37,  1.56it/s]
 46%|████▌     | 26226/57600 [4:35:25<5:27:16,  1.60it/s]
 46%|████▌     | 26227/57600 [4:35:25<5:29:18,  1.59it/s]
 46%|████▌     | 26228/57600 [4:35:26<5:17:55,  1.64it/s]
 46%|████▌     | 26229/57600 [4:35:26<5:18:17,  1.64it/s]
 46%|████▌     | 26230/57600 [4:35:27<5:23:57,  1.61it/s]
 46%|████▌     | 26231/57600 [4:35:28<5:26:19,  1.60it/s]
 46%|████▌     | 26232/57600 [4:35:28<5:30:23,  1.58it/s]
 46%|████▌     | 26233/57600 [4:35:29<5:19:40,  1.64it/s]
 46%|████▌     | 26234/57600 [4:35:29<5:14:37,  1.66it/s]
 46%|████▌     | 26235/57600 [4:35:30<5:09:26,  1.69it/s]
 46%|████▌     | 26236/57600 [4:35:31<5:11:02,  1.68it/s]
 46%|████▌     | 26237/57600 [4:35:31<5:08:24,  1.69it/s]
 46%|████▌     | 26238/57600 [4:35:32<5:05:45,  1.71it/s]
 46%|████▌     | 26239/57600 [4:35:32<5:06:21,  1.71it/s]
 46%|████▌     | 26240/57600 [4:35:33<5:08:05,  1.70it/s]
                                                         
{'loss': 1.181, 'learning_rate': 5.917073170731708e-07, 'epoch': 289.62}

 46%|████▌     | 26240/57600 [4:35:33<5:08:05,  1.70it/s]
 46%|████▌     | 26241/57600 [4:35:34<5:14:45,  1.66it/s]
 46%|████▌     | 26242/57600 [4:35:34<5:14:59,  1.66it/s]
 46%|████▌     | 26243/57600 [4:35:35<5:10:03,  1.69it/s]
 46%|████▌     | 26244/57600 [4:35:35<5:18:53,  1.64it/s]
 46%|████▌     | 26245/57600 [4:35:36<5:22:18,  1.62it/s]
 46%|████▌     | 26246/57600 [4:35:37<5:27:45,  1.59it/s]
 46%|████▌     | 26247/57600 [4:35:37<5:24:07,  1.61it/s]
 46%|████▌     | 26248/57600 [4:35:38<5:19:19,  1.64it/s]
 46%|████▌     | 26249/57600 [4:35:39<5:16:58,  1.65it/s]
 46%|████▌     | 26250/57600 [4:35:39<5:31:35,  1.58it/s]
 46%|████▌     | 26251/57600 [4:35:40<5:27:23,  1.60it/s]
 46%|████▌     | 26252/57600 [4:35:40<5:29:25,  1.59it/s]
 46%|████▌     | 26253/57600 [4:35:41<5:35:10,  1.56it/s]
 46%|████▌     | 26254/57600 [4:35:42<5:30:49,  1.58it/s]
 46%|████▌     | 26255/57600 [4:35:42<5:30:01,  1.58it/s]
 46%|████▌     | 26256/57600 [4:35:43<5:29:55,  1.58it/s]
 46%|████▌     | 26257/57600 [4:35:44<5:20:49,  1.63it/s]
 46%|████▌     | 26258/57600 [4:35:44<5:23:07,  1.62it/s]
 46%|████▌     | 26259/57600 [4:35:45<5:29:59,  1.58it/s]
 46%|████▌     | 26260/57600 [4:35:45<5:23:18,  1.62it/s]
                                                         
{'loss': 1.1961, 'learning_rate': 5.913937282229964e-07, 'epoch': 289.85}

 46%|████▌     | 26260/57600 [4:35:45<5:23:18,  1.62it/s]
 46%|████▌     | 26261/57600 [4:35:46<5:15:38,  1.65it/s]
 46%|████▌     | 26262/57600 [4:35:47<5:11:15,  1.68it/s]
 46%|████▌     | 26263/57600 [4:35:47<5:07:36,  1.70it/s]
 46%|████▌     | 26264/57600 [4:35:48<5:08:42,  1.69it/s]
 46%|████▌     | 26265/57600 [4:35:48<5:20:39,  1.63it/s]
 46%|████▌     | 26266/57600 [4:35:49<5:18:56,  1.64it/s]
 46%|████▌     | 26267/57600 [4:35:50<5:13:54,  1.66it/s]
 46%|████▌     | 26268/57600 [4:35:50<5:11:15,  1.68it/s]
 46%|████▌     | 26269/57600 [4:35:51<5:22:56,  1.62it/s]
 46%|████▌     | 26270/57600 [4:35:52<5:30:09,  1.58it/s]
 46%|████▌     | 26271/57600 [4:35:52<5:43:18,  1.52it/s]
 46%|████▌     | 26272/57600 [4:35:53<5:36:56,  1.55it/s]
 46%|████▌     | 26273/57600 [4:35:53<5:30:57,  1.58it/s]
 46%|████▌     | 26274/57600 [4:35:54<5:36:27,  1.55it/s]
 46%|████▌     | 26275/57600 [4:35:55<5:36:05,  1.55it/s]
 46%|████▌     | 26276/57600 [4:35:55<5:30:23,  1.58it/s]
 46%|████▌     | 26277/57600 [4:35:56<5:27:51,  1.59it/s]
 46%|████▌     | 26278/57600 [4:35:57<5:26:44,  1.60it/s]
 46%|████▌     | 26279/57600 [4:35:57<5:37:21,  1.55it/s]
 46%|████▌     | 26280/57600 [4:35:58<5:39:03,  1.54it/s]
                                                         
{'loss': 1.2372, 'learning_rate': 5.910801393728223e-07, 'epoch': 290.07}

 46%|████▌     | 26280/57600 [4:35:58<5:39:03,  1.54it/s]
 46%|████▌     | 26281/57600 [4:35:59<5:30:00,  1.58it/s]
 46%|████▌     | 26282/57600 [4:35:59<5:36:55,  1.55it/s]
 46%|████▌     | 26283/57600 [4:36:00<5:22:43,  1.62it/s]
 46%|████▌     | 26284/57600 [4:36:00<5:18:23,  1.64it/s]
 46%|████▌     | 26285/57600 [4:36:01<5:20:16,  1.63it/s]
 46%|████▌     | 26286/57600 [4:36:02<5:25:41,  1.60it/s]
 46%|████▌     | 26287/57600 [4:36:02<5:17:51,  1.64it/s]
 46%|████▌     | 26288/57600 [4:36:03<5:10:41,  1.68it/s]
 46%|████▌     | 26289/57600 [4:36:03<5:18:37,  1.64it/s]
 46%|████▌     | 26290/57600 [4:36:04<5:17:51,  1.64it/s]
 46%|████▌     | 26291/57600 [4:36:05<5:17:36,  1.64it/s]
 46%|████▌     | 26292/57600 [4:36:05<5:26:44,  1.60it/s]
 46%|████▌     | 26293/57600 [4:36:06<5:24:24,  1.61it/s]
 46%|████▌     | 26294/57600 [4:36:07<5:23:34,  1.61it/s]
 46%|████▌     | 26295/57600 [4:36:07<5:19:36,  1.63it/s]
 46%|████▌     | 26296/57600 [4:36:08<5:25:06,  1.60it/s]
 46%|████▌     | 26297/57600 [4:36:08<5:17:21,  1.64it/s]
 46%|████▌     | 26298/57600 [4:36:09<5:13:49,  1.66it/s]
 46%|████▌     | 26299/57600 [4:36:10<5:20:35,  1.63it/s]
 46%|████▌     | 26300/57600 [4:36:10<5:16:52,  1.65it/s]
                                                         
{'loss': 1.2319, 'learning_rate': 5.907665505226481e-07, 'epoch': 290.29}

 46%|████▌     | 26300/57600 [4:36:10<5:16:52,  1.65it/s]
 46%|████▌     | 26301/57600 [4:36:11<5:21:58,  1.62it/s]
 46%|████▌     | 26302/57600 [4:36:11<5:21:07,  1.62it/s]
 46%|████▌     | 26303/57600 [4:36:12<5:26:45,  1.60it/s]
 46%|████▌     | 26304/57600 [4:36:13<5:26:55,  1.60it/s]
 46%|████▌     | 26305/57600 [4:36:13<5:25:07,  1.60it/s]
 46%|████▌     | 26306/57600 [4:36:14<5:22:55,  1.62it/s]
 46%|████▌     | 26307/57600 [4:36:15<5:17:34,  1.64it/s]
 46%|████▌     | 26308/57600 [4:36:15<5:12:30,  1.67it/s]
 46%|████▌     | 26309/57600 [4:36:16<5:13:49,  1.66it/s]
 46%|████▌     | 26310/57600 [4:36:16<5:12:06,  1.67it/s]
 46%|████▌     | 26311/57600 [4:36:17<5:09:54,  1.68it/s]
 46%|████▌     | 26312/57600 [4:36:18<5:19:58,  1.63it/s]
 46%|████▌     | 26313/57600 [4:36:18<5:32:22,  1.57it/s]
 46%|████▌     | 26314/57600 [4:36:19<5:29:31,  1.58it/s]
 46%|████▌     | 26315/57600 [4:36:19<5:23:10,  1.61it/s]
 46%|████▌     | 26316/57600 [4:36:20<5:22:19,  1.62it/s]
 46%|████▌     | 26317/57600 [4:36:21<5:31:56,  1.57it/s]
 46%|████▌     | 26318/57600 [4:36:21<5:37:19,  1.55it/s]
 46%|████▌     | 26319/57600 [4:36:22<5:36:15,  1.55it/s]
 46%|████▌     | 26320/57600 [4:36:23<5:34:11,  1.56it/s]
                                                         
{'loss': 1.1856, 'learning_rate': 5.904529616724739e-07, 'epoch': 290.51}

 46%|████▌     | 26320/57600 [4:36:23<5:34:11,  1.56it/s]
 46%|████▌     | 26321/57600 [4:36:23<5:28:54,  1.59it/s]
 46%|████▌     | 26322/57600 [4:36:24<5:20:39,  1.63it/s]
 46%|████▌     | 26323/57600 [4:36:25<5:24:16,  1.61it/s]
 46%|████▌     | 26324/57600 [4:36:25<5:18:05,  1.64it/s]
 46%|████▌     | 26325/57600 [4:36:26<5:10:12,  1.68it/s]
 46%|████▌     | 26326/57600 [4:36:26<5:22:24,  1.62it/s]
 46%|████▌     | 26327/57600 [4:36:27<5:21:42,  1.62it/s]
 46%|████▌     | 26328/57600 [4:36:28<5:16:53,  1.64it/s]
 46%|████▌     | 26329/57600 [4:36:28<5:28:28,  1.59it/s]
 46%|████▌     | 26330/57600 [4:36:29<5:29:02,  1.58it/s]
 46%|████▌     | 26331/57600 [4:36:29<5:17:38,  1.64it/s]
 46%|████▌     | 26332/57600 [4:36:30<5:22:59,  1.61it/s]
 46%|████▌     | 26333/57600 [4:36:31<5:21:59,  1.62it/s]
 46%|████▌     | 26334/57600 [4:36:31<5:24:56,  1.60it/s]
 46%|████▌     | 26335/57600 [4:36:32<5:33:01,  1.56it/s]
 46%|████▌     | 26336/57600 [4:36:33<5:24:12,  1.61it/s]
 46%|████▌     | 26337/57600 [4:36:33<5:19:12,  1.63it/s]
 46%|████▌     | 26338/57600 [4:36:34<5:13:20,  1.66it/s]
 46%|████▌     | 26339/57600 [4:36:34<5:29:05,  1.58it/s]
 46%|████▌     | 26340/57600 [4:36:35<5:20:04,  1.63it/s]
                                                         
{'loss': 1.2184, 'learning_rate': 5.901393728222995e-07, 'epoch': 290.73}

 46%|████▌     | 26340/57600 [4:36:35<5:20:04,  1.63it/s]
 46%|████▌     | 26341/57600 [4:36:36<5:15:34,  1.65it/s]
 46%|████▌     | 26342/57600 [4:36:36<5:24:32,  1.61it/s]
 46%|████▌     | 26343/57600 [4:36:37<5:19:36,  1.63it/s]
 46%|████▌     | 26344/57600 [4:36:38<5:29:30,  1.58it/s]
 46%|████▌     | 26345/57600 [4:36:38<5:38:30,  1.54it/s]
 46%|████▌     | 26346/57600 [4:36:39<5:28:56,  1.58it/s]
 46%|████▌     | 26347/57600 [4:36:39<5:30:02,  1.58it/s]
 46%|████▌     | 26348/57600 [4:36:40<5:27:46,  1.59it/s]
 46%|████▌     | 26349/57600 [4:36:41<5:20:39,  1.62it/s]
 46%|████▌     | 26350/57600 [4:36:41<5:30:09,  1.58it/s]
 46%|████▌     | 26351/57600 [4:36:42<5:27:59,  1.59it/s]
 46%|████▌     | 26352/57600 [4:36:43<5:24:19,  1.61it/s]
 46%|████▌     | 26353/57600 [4:36:43<5:23:31,  1.61it/s]
 46%|████▌     | 26354/57600 [4:36:44<5:22:53,  1.61it/s]
 46%|████▌     | 26355/57600 [4:36:44<5:18:10,  1.64it/s]
 46%|████▌     | 26356/57600 [4:36:45<5:19:23,  1.63it/s]
 46%|████▌     | 26357/57600 [4:36:46<5:22:35,  1.61it/s]
 46%|████▌     | 26358/57600 [4:36:46<5:17:39,  1.64it/s]
 46%|████▌     | 26359/57600 [4:36:47<5:15:12,  1.65it/s]
 46%|████▌     | 26360/57600 [4:36:47<5:12:28,  1.67it/s]
                                                         
{'loss': 1.2286, 'learning_rate': 5.898257839721254e-07, 'epoch': 290.95}

 46%|████▌     | 26360/57600 [4:36:47<5:12:28,  1.67it/s]
 46%|████▌     | 26361/57600 [4:36:48<5:21:31,  1.62it/s]
 46%|████▌     | 26362/57600 [4:36:49<5:28:20,  1.59it/s]
 46%|████▌     | 26363/57600 [4:36:49<5:34:33,  1.56it/s]
 46%|████▌     | 26364/57600 [4:36:50<5:29:51,  1.58it/s]
 46%|████▌     | 26365/57600 [4:36:51<5:39:23,  1.53it/s]
 46%|████▌     | 26366/57600 [4:36:51<5:38:06,  1.54it/s]
 46%|████▌     | 26367/57600 [4:36:52<5:38:17,  1.54it/s]
 46%|████▌     | 26368/57600 [4:36:53<5:31:07,  1.57it/s]
 46%|████▌     | 26369/57600 [4:36:53<5:28:26,  1.58it/s]
 46%|████▌     | 26370/57600 [4:36:54<5:18:49,  1.63it/s]
 46%|████▌     | 26371/57600 [4:36:54<5:25:24,  1.60it/s]
 46%|████▌     | 26372/57600 [4:36:55<5:19:41,  1.63it/s]
 46%|████▌     | 26373/57600 [4:36:56<5:28:56,  1.58it/s]
 46%|████▌     | 26374/57600 [4:36:56<5:30:54,  1.57it/s]
 46%|████▌     | 26375/57600 [4:36:57<5:28:36,  1.58it/s]
 46%|████▌     | 26376/57600 [4:36:58<5:33:31,  1.56it/s]
 46%|████▌     | 26377/57600 [4:36:58<5:19:25,  1.63it/s]
 46%|████▌     | 26378/57600 [4:36:59<5:15:27,  1.65it/s]
 46%|████▌     | 26379/57600 [4:36:59<5:18:22,  1.63it/s]
 46%|████▌     | 26380/57600 [4:37:00<5:09:18,  1.68it/s]
                                                         
{'loss': 1.2022, 'learning_rate': 5.895121951219513e-07, 'epoch': 291.17}

 46%|████▌     | 26380/57600 [4:37:00<5:09:18,  1.68it/s]
 46%|████▌     | 26381/57600 [4:37:01<5:13:30,  1.66it/s]
 46%|████▌     | 26382/57600 [4:37:01<5:12:13,  1.67it/s]
 46%|████▌     | 26383/57600 [4:37:02<5:23:31,  1.61it/s]
 46%|████▌     | 26384/57600 [4:37:02<5:16:07,  1.65it/s]
 46%|████▌     | 26385/57600 [4:37:03<5:34:55,  1.55it/s]
 46%|████▌     | 26386/57600 [4:37:04<5:36:57,  1.54it/s]
 46%|████▌     | 26387/57600 [4:37:04<5:26:56,  1.59it/s]
 46%|████▌     | 26388/57600 [4:37:05<5:24:05,  1.61it/s]
 46%|████▌     | 26389/57600 [4:37:06<5:21:16,  1.62it/s]
 46%|████▌     | 26390/57600 [4:37:06<5:20:09,  1.62it/s]
 46%|████▌     | 26391/57600 [4:37:07<5:18:14,  1.63it/s]
 46%|████▌     | 26392/57600 [4:37:07<5:11:16,  1.67it/s]
 46%|████▌     | 26393/57600 [4:37:08<5:20:46,  1.62it/s]
 46%|████▌     | 26394/57600 [4:37:09<5:15:37,  1.65it/s]
 46%|████▌     | 26395/57600 [4:37:09<5:37:07,  1.54it/s]
 46%|████▌     | 26396/57600 [4:37:10<5:36:12,  1.55it/s]
 46%|████▌     | 26397/57600 [4:37:11<5:36:41,  1.54it/s]
 46%|████▌     | 26398/57600 [4:37:11<6:00:47,  1.44it/s]
 46%|████▌     | 26399/57600 [4:37:12<5:48:21,  1.49it/s]
 46%|████▌     | 26400/57600 [4:37:13<5:40:36,  1.53it/s]
                                                         
{'loss': 1.1817, 'learning_rate': 5.891986062717769e-07, 'epoch': 291.39}

 46%|████▌     | 26400/57600 [4:37:13<5:40:36,  1.53it/s]
 46%|████▌     | 26401/57600 [4:37:13<5:44:26,  1.51it/s]
 46%|████▌     | 26402/57600 [4:37:14<5:34:47,  1.55it/s]
 46%|████▌     | 26403/57600 [4:37:15<5:31:34,  1.57it/s]
 46%|████▌     | 26404/57600 [4:37:15<5:35:46,  1.55it/s]
 46%|████▌     | 26405/57600 [4:37:16<5:33:49,  1.56it/s]
 46%|████▌     | 26406/57600 [4:37:17<5:37:48,  1.54it/s]
 46%|████▌     | 26407/57600 [4:37:17<5:35:50,  1.55it/s]
 46%|████▌     | 26408/57600 [4:37:18<5:30:47,  1.57it/s]
 46%|████▌     | 26409/57600 [4:37:18<5:29:46,  1.58it/s]
 46%|████▌     | 26410/57600 [4:37:19<5:24:29,  1.60it/s]
 46%|████▌     | 26411/57600 [4:37:20<5:29:35,  1.58it/s]
 46%|████▌     | 26412/57600 [4:37:20<5:36:23,  1.55it/s]
 46%|████▌     | 26413/57600 [4:37:21<5:36:29,  1.54it/s]
 46%|████▌     | 26414/57600 [4:37:22<5:27:13,  1.59it/s]
 46%|████▌     | 26415/57600 [4:37:22<5:22:48,  1.61it/s]
 46%|████▌     | 26416/57600 [4:37:23<5:37:25,  1.54it/s]
 46%|████▌     | 26417/57600 [4:37:24<5:35:19,  1.55it/s]
 46%|████▌     | 26418/57600 [4:37:24<5:40:16,  1.53it/s]
 46%|████▌     | 26419/57600 [4:37:25<5:36:26,  1.54it/s]
 46%|████▌     | 26420/57600 [4:37:25<5:29:53,  1.58it/s]
                                                         
{'loss': 1.1717, 'learning_rate': 5.888850174216028e-07, 'epoch': 291.61}

 46%|████▌     | 26420/57600 [4:37:25<5:29:53,  1.58it/s]
 46%|████▌     | 26421/57600 [4:37:26<5:32:34,  1.56it/s]
 46%|████▌     | 26422/57600 [4:37:27<5:37:59,  1.54it/s]
 46%|████▌     | 26423/57600 [4:37:27<5:24:34,  1.60it/s]
 46%|████▌     | 26424/57600 [4:37:28<5:18:52,  1.63it/s]
 46%|████▌     | 26425/57600 [4:37:29<5:24:23,  1.60it/s]
 46%|████▌     | 26426/57600 [4:37:29<5:19:10,  1.63it/s]
 46%|████▌     | 26427/57600 [4:37:30<5:07:54,  1.69it/s]
 46%|████▌     | 26428/57600 [4:37:30<5:06:54,  1.69it/s]
 46%|████▌     | 26429/57600 [4:37:31<5:11:09,  1.67it/s]
 46%|████▌     | 26430/57600 [4:37:32<5:16:39,  1.64it/s]
 46%|████▌     | 26431/57600 [4:37:32<5:20:35,  1.62it/s]
 46%|████▌     | 26432/57600 [4:37:33<5:21:20,  1.62it/s]
 46%|████▌     | 26433/57600 [4:37:33<5:15:36,  1.65it/s]
 46%|████▌     | 26434/57600 [4:37:34<5:15:38,  1.65it/s]
 46%|████▌     | 26435/57600 [4:37:35<5:15:32,  1.65it/s]
 46%|████▌     | 26436/57600 [4:37:35<5:09:06,  1.68it/s]
 46%|████▌     | 26437/57600 [4:37:36<5:16:17,  1.64it/s]
 46%|████▌     | 26438/57600 [4:37:36<5:19:32,  1.63it/s]
 46%|████▌     | 26439/57600 [4:37:37<5:12:47,  1.66it/s]
 46%|████▌     | 26440/57600 [4:37:38<5:04:12,  1.71it/s]
                                                         
{'loss': 1.2329, 'learning_rate': 5.885714285714286e-07, 'epoch': 291.83}

 46%|████▌     | 26440/57600 [4:37:38<5:04:12,  1.71it/s]
 46%|████▌     | 26441/57600 [4:37:38<5:15:59,  1.64it/s]
 46%|████▌     | 26442/57600 [4:37:39<5:24:09,  1.60it/s]
 46%|████▌     | 26443/57600 [4:37:39<5:09:56,  1.68it/s]
 46%|████▌     | 26444/57600 [4:37:40<5:17:44,  1.63it/s]
 46%|████▌     | 26445/57600 [4:37:41<5:12:25,  1.66it/s]
 46%|████▌     | 26446/57600 [4:37:41<5:08:17,  1.68it/s]
 46%|████▌     | 26447/57600 [4:37:42<5:06:25,  1.69it/s]
 46%|████▌     | 26448/57600 [4:37:42<5:00:31,  1.73it/s]
 46%|████▌     | 26449/57600 [4:37:43<5:02:36,  1.72it/s]
 46%|████▌     | 26450/57600 [4:37:44<5:08:29,  1.68it/s]
 46%|████▌     | 26451/57600 [4:37:44<5:10:26,  1.67it/s]
 46%|████▌     | 26452/57600 [4:37:45<5:11:39,  1.67it/s]
 46%|████▌     | 26453/57600 [4:37:45<5:12:06,  1.66it/s]
 46%|████▌     | 26454/57600 [4:37:46<5:17:51,  1.63it/s]
 46%|████▌     | 26455/57600 [4:37:47<5:20:35,  1.62it/s]
 46%|████▌     | 26456/57600 [4:37:47<5:35:35,  1.55it/s]
 46%|████▌     | 26457/57600 [4:37:48<5:26:09,  1.59it/s]
 46%|████▌     | 26458/57600 [4:37:49<5:23:08,  1.61it/s]
 46%|████▌     | 26459/57600 [4:37:49<5:18:41,  1.63it/s]
 46%|████▌     | 26460/57600 [4:37:50<5:12:18,  1.66it/s]
                                                         
{'loss': 1.2172, 'learning_rate': 5.882578397212544e-07, 'epoch': 292.05}

 46%|████▌     | 26460/57600 [4:37:50<5:12:18,  1.66it/s]
 46%|████▌     | 26461/57600 [4:37:50<5:12:37,  1.66it/s]
 46%|████▌     | 26462/57600 [4:37:51<5:19:38,  1.62it/s]
 46%|████▌     | 26463/57600 [4:37:52<5:13:08,  1.66it/s]
 46%|████▌     | 26464/57600 [4:37:52<5:10:34,  1.67it/s]
 46%|████▌     | 26465/57600 [4:37:53<5:06:10,  1.69it/s]
 46%|████▌     | 26466/57600 [4:37:53<5:07:57,  1.68it/s]
 46%|████▌     | 26467/57600 [4:37:54<5:22:29,  1.61it/s]
 46%|████▌     | 26468/57600 [4:37:55<5:22:05,  1.61it/s]
 46%|████▌     | 26469/57600 [4:37:55<5:16:26,  1.64it/s]
 46%|████▌     | 26470/57600 [4:37:56<5:33:21,  1.56it/s]
 46%|████▌     | 26471/57600 [4:37:57<5:34:58,  1.55it/s]
 46%|████▌     | 26472/57600 [4:37:57<5:36:48,  1.54it/s]
 46%|████▌     | 26473/57600 [4:37:58<5:30:55,  1.57it/s]
 46%|████▌     | 26474/57600 [4:37:59<5:30:34,  1.57it/s]
 46%|████▌     | 26475/57600 [4:37:59<5:33:36,  1.55it/s]
 46%|████▌     | 26476/57600 [4:38:00<5:24:20,  1.60it/s]
 46%|████▌     | 26477/57600 [4:38:00<5:19:27,  1.62it/s]
 46%|████▌     | 26478/57600 [4:38:01<5:23:33,  1.60it/s]
 46%|████▌     | 26479/57600 [4:38:02<5:17:13,  1.64it/s]
 46%|████▌     | 26480/57600 [4:38:02<5:30:46,  1.57it/s]
                                                         
{'loss': 1.1863, 'learning_rate': 5.8794425087108e-07, 'epoch': 292.27}

 46%|████▌     | 26480/57600 [4:38:02<5:30:46,  1.57it/s]
 46%|████▌     | 26481/57600 [4:38:03<5:23:50,  1.60it/s]
 46%|████▌     | 26482/57600 [4:38:03<5:25:27,  1.59it/s]
 46%|████▌     | 26483/57600 [4:38:04<5:22:42,  1.61it/s]
 46%|████▌     | 26484/57600 [4:38:05<5:30:26,  1.57it/s]
 46%|████▌     | 26485/57600 [4:38:06<5:46:08,  1.50it/s]
 46%|████▌     | 26486/57600 [4:38:06<5:51:33,  1.48it/s]
 46%|████▌     | 26487/57600 [4:38:07<5:38:09,  1.53it/s]
 46%|████▌     | 26488/57600 [4:38:07<5:35:50,  1.54it/s]
 46%|████▌     | 26489/57600 [4:38:08<5:35:55,  1.54it/s]
 46%|████▌     | 26490/57600 [4:38:09<5:29:24,  1.57it/s]
 46%|████▌     | 26491/57600 [4:38:09<5:21:54,  1.61it/s]
 46%|████▌     | 26492/57600 [4:38:10<5:08:54,  1.68it/s]
 46%|████▌     | 26493/57600 [4:38:10<5:18:35,  1.63it/s]
 46%|████▌     | 26494/57600 [4:38:11<5:15:46,  1.64it/s]
 46%|████▌     | 26495/57600 [4:38:12<5:25:39,  1.59it/s]
 46%|████▌     | 26496/57600 [4:38:12<5:17:45,  1.63it/s]
 46%|████▌     | 26497/57600 [4:38:13<5:21:46,  1.61it/s]
 46%|████▌     | 26498/57600 [4:38:14<5:24:47,  1.60it/s]
 46%|████▌     | 26499/57600 [4:38:14<5:27:56,  1.58it/s]
 46%|████▌     | 26500/57600 [4:38:15<5:31:56,  1.56it/s]
                                                         
{'loss': 1.1673, 'learning_rate': 5.876306620209059e-07, 'epoch': 292.49}

 46%|████▌     | 26500/57600 [4:38:15<5:31:56,  1.56it/s]
 46%|████▌     | 26501/57600 [4:38:16<5:35:28,  1.55it/s]
 46%|████▌     | 26502/57600 [4:38:16<5:42:51,  1.51it/s]
 46%|████▌     | 26503/57600 [4:38:17<5:33:58,  1.55it/s]
 46%|████▌     | 26504/57600 [4:38:18<5:32:10,  1.56it/s]
 46%|████▌     | 26505/57600 [4:38:18<5:25:51,  1.59it/s]
 46%|████▌     | 26506/57600 [4:38:19<5:17:22,  1.63it/s]
 46%|████▌     | 26507/57600 [4:38:19<5:22:35,  1.61it/s]
 46%|████▌     | 26508/57600 [4:38:20<5:13:00,  1.66it/s]
 46%|████▌     | 26509/57600 [4:38:20<5:10:59,  1.67it/s]
 46%|████▌     | 26510/57600 [4:38:21<5:10:31,  1.67it/s]
 46%|████▌     | 26511/57600 [4:38:22<5:18:52,  1.62it/s]
 46%|████▌     | 26512/57600 [4:38:22<5:24:56,  1.59it/s]
 46%|████▌     | 26513/57600 [4:38:23<5:13:21,  1.65it/s]
 46%|████▌     | 26514/57600 [4:38:24<5:23:36,  1.60it/s]
 46%|████▌     | 26515/57600 [4:38:24<5:28:24,  1.58it/s]
 46%|████▌     | 26516/57600 [4:38:25<5:25:25,  1.59it/s]
 46%|████▌     | 26517/57600 [4:38:25<5:16:23,  1.64it/s]
 46%|████▌     | 26518/57600 [4:38:26<5:18:54,  1.62it/s]
 46%|████▌     | 26519/57600 [4:38:27<5:26:35,  1.59it/s]
 46%|████▌     | 26520/57600 [4:38:27<5:24:05,  1.60it/s]
                                                         
{'loss': 1.207, 'learning_rate': 5.873170731707317e-07, 'epoch': 292.72}

 46%|████▌     | 26520/57600 [4:38:27<5:24:05,  1.60it/s]
 46%|████▌     | 26521/57600 [4:38:28<5:16:51,  1.63it/s]
 46%|████▌     | 26522/57600 [4:38:29<5:27:26,  1.58it/s]
 46%|████▌     | 26523/57600 [4:38:29<5:24:50,  1.59it/s]
 46%|████▌     | 26524/57600 [4:38:30<5:25:32,  1.59it/s]
 46%|████▌     | 26525/57600 [4:38:30<5:17:58,  1.63it/s]
 46%|████▌     | 26526/57600 [4:38:31<5:22:07,  1.61it/s]
 46%|████▌     | 26527/57600 [4:38:32<5:24:22,  1.60it/s]
 46%|████▌     | 26528/57600 [4:38:32<5:16:21,  1.64it/s]
 46%|████▌     | 26529/57600 [4:38:33<5:20:28,  1.62it/s]
 46%|████▌     | 26530/57600 [4:38:34<5:17:16,  1.63it/s]
 46%|████▌     | 26531/57600 [4:38:34<5:19:40,  1.62it/s]
 46%|████▌     | 26532/57600 [4:38:35<5:17:43,  1.63it/s]
 46%|████▌     | 26533/57600 [4:38:35<5:25:43,  1.59it/s]
 46%|████▌     | 26534/57600 [4:38:36<5:18:16,  1.63it/s]
 46%|████▌     | 26535/57600 [4:38:37<5:22:55,  1.60it/s]
 46%|████▌     | 26536/57600 [4:38:37<5:23:03,  1.60it/s]
 46%|████▌     | 26537/57600 [4:38:38<5:20:45,  1.61it/s]
 46%|████▌     | 26538/57600 [4:38:38<5:18:37,  1.62it/s]
 46%|████▌     | 26539/57600 [4:38:39<5:28:18,  1.58it/s]
 46%|████▌     | 26540/57600 [4:38:40<5:32:25,  1.56it/s]
                                                         
{'loss': 1.2263, 'learning_rate': 5.870034843205575e-07, 'epoch': 292.94}

 46%|████▌     | 26540/57600 [4:38:40<5:32:25,  1.56it/s]
 46%|████▌     | 26541/57600 [4:38:40<5:29:09,  1.57it/s]
 46%|████▌     | 26542/57600 [4:38:41<5:31:01,  1.56it/s]
 46%|████▌     | 26543/57600 [4:38:42<5:32:03,  1.56it/s]
 46%|████▌     | 26544/57600 [4:38:42<5:26:20,  1.59it/s]
 46%|████▌     | 26545/57600 [4:38:43<5:30:13,  1.57it/s]
 46%|████▌     | 26546/57600 [4:38:44<5:34:16,  1.55it/s]
 46%|████▌     | 26547/57600 [4:38:44<5:30:00,  1.57it/s]
 46%|████▌     | 26548/57600 [4:38:45<5:37:18,  1.53it/s]
 46%|████▌     | 26549/57600 [4:38:46<5:25:44,  1.59it/s]
 46%|████▌     | 26550/57600 [4:38:46<5:26:41,  1.58it/s]
 46%|████▌     | 26551/57600 [4:38:47<5:26:08,  1.59it/s]
 46%|████▌     | 26552/57600 [4:38:47<5:26:03,  1.59it/s]
 46%|████▌     | 26553/57600 [4:38:48<5:25:49,  1.59it/s]
 46%|████▌     | 26554/57600 [4:38:49<5:17:29,  1.63it/s]
 46%|████▌     | 26555/57600 [4:38:49<5:16:17,  1.64it/s]
 46%|████▌     | 26556/57600 [4:38:50<5:32:20,  1.56it/s]
 46%|████▌     | 26557/57600 [4:38:51<5:30:25,  1.57it/s]
 46%|████▌     | 26558/57600 [4:38:51<5:28:45,  1.57it/s]
 46%|████▌     | 26559/57600 [4:38:52<5:33:08,  1.55it/s]
 46%|████▌     | 26560/57600 [4:38:53<5:42:48,  1.51it/s]
                                                         
{'loss': 1.1734, 'learning_rate': 5.866898954703832e-07, 'epoch': 293.16}

 46%|████▌     | 26560/57600 [4:38:53<5:42:48,  1.51it/s]
 46%|████▌     | 26561/57600 [4:38:53<5:25:05,  1.59it/s]
 46%|████▌     | 26562/57600 [4:38:54<5:28:43,  1.57it/s]
 46%|████▌     | 26563/57600 [4:38:54<5:29:07,  1.57it/s]
 46%|████▌     | 26564/57600 [4:38:55<5:39:40,  1.52it/s]
 46%|████▌     | 26565/57600 [4:38:56<5:32:22,  1.56it/s]
 46%|████▌     | 26566/57600 [4:38:56<5:20:20,  1.61it/s]
 46%|████▌     | 26567/57600 [4:38:57<5:18:46,  1.62it/s]
 46%|████▌     | 26568/57600 [4:38:58<5:23:22,  1.60it/s]
 46%|████▌     | 26569/57600 [4:38:58<5:35:03,  1.54it/s]
 46%|████▌     | 26570/57600 [4:38:59<5:29:00,  1.57it/s]
 46%|████▌     | 26571/57600 [4:39:00<5:28:24,  1.57it/s]
 46%|████▌     | 26572/57600 [4:39:00<5:32:24,  1.56it/s]
 46%|████▌     | 26573/57600 [4:39:01<5:34:42,  1.54it/s]
 46%|████▌     | 26574/57600 [4:39:01<5:28:44,  1.57it/s]
 46%|████▌     | 26575/57600 [4:39:02<5:31:33,  1.56it/s]
 46%|████▌     | 26576/57600 [4:39:03<5:26:48,  1.58it/s]
 46%|████▌     | 26577/57600 [4:39:03<5:25:24,  1.59it/s]
 46%|████▌     | 26578/57600 [4:39:04<5:24:05,  1.60it/s]
 46%|████▌     | 26579/57600 [4:39:05<5:14:09,  1.65it/s]
 46%|████▌     | 26580/57600 [4:39:05<5:11:34,  1.66it/s]
                                                         
{'loss': 1.1811, 'learning_rate': 5.863763066202091e-07, 'epoch': 293.38}

 46%|████▌     | 26580/57600 [4:39:05<5:11:34,  1.66it/s]
 46%|████▌     | 26581/57600 [4:39:06<5:12:08,  1.66it/s]
 46%|████▌     | 26582/57600 [4:39:06<5:16:24,  1.63it/s]
 46%|████▌     | 26583/57600 [4:39:07<5:15:20,  1.64it/s]
 46%|████▌     | 26584/57600 [4:39:08<5:15:37,  1.64it/s]
 46%|████▌     | 26585/57600 [4:39:08<5:25:45,  1.59it/s]
 46%|████▌     | 26586/57600 [4:39:09<5:28:57,  1.57it/s]
 46%|████▌     | 26587/57600 [4:39:09<5:21:51,  1.61it/s]
 46%|████▌     | 26588/57600 [4:39:10<5:19:45,  1.62it/s]
 46%|████▌     | 26589/57600 [4:39:11<5:14:10,  1.65it/s]
 46%|████▌     | 26590/57600 [4:39:11<5:18:01,  1.63it/s]
 46%|████▌     | 26591/57600 [4:39:12<5:20:45,  1.61it/s]
 46%|████▌     | 26592/57600 [4:39:13<5:13:18,  1.65it/s]
 46%|████▌     | 26593/57600 [4:39:13<5:11:18,  1.66it/s]
 46%|████▌     | 26594/57600 [4:39:14<5:14:55,  1.64it/s]
 46%|████▌     | 26595/57600 [4:39:14<5:27:22,  1.58it/s]
 46%|████▌     | 26596/57600 [4:39:15<5:25:33,  1.59it/s]
 46%|████▌     | 26597/57600 [4:39:16<5:33:53,  1.55it/s]
 46%|████▌     | 26598/57600 [4:39:16<5:51:40,  1.47it/s]
 46%|████▌     | 26599/57600 [4:39:17<5:43:38,  1.50it/s]
 46%|████▌     | 26600/57600 [4:39:18<5:26:25,  1.58it/s]
                                                         
{'loss': 1.1802, 'learning_rate': 5.860627177700349e-07, 'epoch': 293.6}

 46%|████▌     | 26600/57600 [4:39:18<5:26:25,  1.58it/s]
 46%|████▌     | 26601/57600 [4:39:18<5:29:24,  1.57it/s]
 46%|████▌     | 26602/57600 [4:39:19<5:26:20,  1.58it/s]
 46%|████▌     | 26603/57600 [4:39:20<5:20:26,  1.61it/s]
 46%|████▌     | 26604/57600 [4:39:20<5:26:26,  1.58it/s]
 46%|████▌     | 26605/57600 [4:39:21<5:24:38,  1.59it/s]
 46%|████▌     | 26606/57600 [4:39:21<5:30:07,  1.56it/s]
 46%|████▌     | 26607/57600 [4:39:22<5:22:57,  1.60it/s]
 46%|████▌     | 26608/57600 [4:39:23<5:16:27,  1.63it/s]
 46%|████▌     | 26609/57600 [4:39:23<5:14:02,  1.64it/s]
 46%|████▌     | 26610/57600 [4:39:24<5:23:58,  1.59it/s]
 46%|████▌     | 26611/57600 [4:39:25<5:22:49,  1.60it/s]
 46%|████▌     | 26612/57600 [4:39:25<5:26:21,  1.58it/s]
 46%|████▌     | 26613/57600 [4:39:26<5:33:58,  1.55it/s]
 46%|████▌     | 26614/57600 [4:39:26<5:23:07,  1.60it/s]
 46%|████▌     | 26615/57600 [4:39:27<5:32:20,  1.55it/s]
 46%|████▌     | 26616/57600 [4:39:28<5:32:04,  1.56it/s]
 46%|████▌     | 26617/57600 [4:39:28<5:20:58,  1.61it/s]
 46%|████▌     | 26618/57600 [4:39:29<5:19:26,  1.62it/s]
 46%|████▌     | 26619/57600 [4:39:30<5:17:31,  1.63it/s]
 46%|████▌     | 26620/57600 [4:39:30<5:11:43,  1.66it/s]
                                                         
{'loss': 1.1793, 'learning_rate': 5.857491289198605e-07, 'epoch': 293.82}

 46%|████▌     | 26620/57600 [4:39:30<5:11:43,  1.66it/s]
 46%|████▌     | 26621/57600 [4:39:31<5:31:40,  1.56it/s]
 46%|████▌     | 26622/57600 [4:39:31<5:23:42,  1.59it/s]
 46%|████▌     | 26623/57600 [4:39:32<5:23:31,  1.60it/s]
 46%|████▌     | 26624/57600 [4:39:33<5:19:21,  1.62it/s]
 46%|████▌     | 26625/57600 [4:39:33<5:21:56,  1.60it/s]
 46%|████▌     | 26626/57600 [4:39:34<5:24:59,  1.59it/s]
 46%|████▌     | 26627/57600 [4:39:35<5:32:01,  1.55it/s]
 46%|████▌     | 26628/57600 [4:39:35<5:26:41,  1.58it/s]
 46%|████▌     | 26629/57600 [4:39:36<5:23:52,  1.59it/s]
 46%|████▌     | 26630/57600 [4:39:36<5:20:36,  1.61it/s]
 46%|████▌     | 26631/57600 [4:39:37<5:20:04,  1.61it/s]
 46%|████▌     | 26632/57600 [4:39:38<5:19:52,  1.61it/s]
 46%|████▌     | 26633/57600 [4:39:38<5:18:49,  1.62it/s]
 46%|████▌     | 26634/57600 [4:39:39<5:17:12,  1.63it/s]
 46%|████▌     | 26635/57600 [4:39:40<5:12:35,  1.65it/s]
 46%|████▌     | 26636/57600 [4:39:40<5:06:14,  1.69it/s]
 46%|████▌     | 26637/57600 [4:39:41<5:17:56,  1.62it/s]
 46%|████▌     | 26638/57600 [4:39:41<5:27:40,  1.57it/s]
 46%|████▌     | 26639/57600 [4:39:42<5:24:33,  1.59it/s]
 46%|████▋     | 26640/57600 [4:39:43<5:23:21,  1.60it/s]
                                                         
{'loss': 1.183, 'learning_rate': 5.854355400696864e-07, 'epoch': 294.04}

 46%|████▋     | 26640/57600 [4:39:43<5:23:21,  1.60it/s]
 46%|████▋     | 26641/57600 [4:39:43<5:27:48,  1.57it/s]
 46%|████▋     | 26642/57600 [4:39:44<5:18:22,  1.62it/s]
 46%|████▋     | 26643/57600 [4:39:44<5:12:59,  1.65it/s]
 46%|████▋     | 26644/57600 [4:39:45<5:11:26,  1.66it/s]
 46%|████▋     | 26645/57600 [4:39:46<5:30:33,  1.56it/s]
 46%|████▋     | 26646/57600 [4:39:46<5:21:50,  1.60it/s]
 46%|████▋     | 26647/57600 [4:39:47<5:29:23,  1.57it/s]
 46%|████▋     | 26648/57600 [4:39:48<5:36:57,  1.53it/s]
 46%|████▋     | 26649/57600 [4:39:48<5:31:52,  1.55it/s]
 46%|████▋     | 26650/57600 [4:39:49<5:27:36,  1.57it/s]
 46%|████▋     | 26651/57600 [4:39:50<5:16:25,  1.63it/s]
 46%|████▋     | 26652/57600 [4:39:50<5:25:37,  1.58it/s]
 46%|████▋     | 26653/57600 [4:39:51<5:24:35,  1.59it/s]
 46%|████▋     | 26654/57600 [4:39:51<5:14:29,  1.64it/s]
 46%|████▋     | 26655/57600 [4:39:52<5:17:53,  1.62it/s]
 46%|████▋     | 26656/57600 [4:39:53<5:17:59,  1.62it/s]
 46%|████▋     | 26657/57600 [4:39:53<5:13:53,  1.64it/s]
 46%|████▋     | 26658/57600 [4:39:54<5:12:54,  1.65it/s]
 46%|████▋     | 26659/57600 [4:39:54<5:13:27,  1.65it/s]
 46%|████▋     | 26660/57600 [4:39:55<5:23:18,  1.59it/s]
                                                         
{'loss': 1.2072, 'learning_rate': 5.851219512195122e-07, 'epoch': 294.26}

 46%|████▋     | 26660/57600 [4:39:55<5:23:18,  1.59it/s]
 46%|████▋     | 26661/57600 [4:39:56<5:22:07,  1.60it/s]
 46%|████▋     | 26662/57600 [4:39:56<5:19:14,  1.62it/s]
 46%|████▋     | 26663/57600 [4:39:57<5:23:01,  1.60it/s]
 46%|████▋     | 26664/57600 [4:39:58<5:13:30,  1.64it/s]
 46%|████▋     | 26665/57600 [4:39:58<5:39:13,  1.52it/s]
 46%|████▋     | 26666/57600 [4:39:59<5:23:26,  1.59it/s]
 46%|████▋     | 26667/57600 [4:40:00<5:31:08,  1.56it/s]
 46%|████▋     | 26668/57600 [4:40:00<5:40:10,  1.52it/s]
 46%|████▋     | 26669/57600 [4:40:01<5:32:00,  1.55it/s]
 46%|████▋     | 26670/57600 [4:40:01<5:22:20,  1.60it/s]
 46%|████▋     | 26671/57600 [4:40:02<5:15:39,  1.63it/s]
 46%|████▋     | 26672/57600 [4:40:03<5:19:04,  1.62it/s]
 46%|████▋     | 26673/57600 [4:40:03<5:17:10,  1.63it/s]
 46%|████▋     | 26674/57600 [4:40:04<5:14:05,  1.64it/s]
 46%|████▋     | 26675/57600 [4:40:04<5:09:23,  1.67it/s]
 46%|████▋     | 26676/57600 [4:40:05<5:09:44,  1.66it/s]
 46%|████▋     | 26677/57600 [4:40:06<5:12:11,  1.65it/s]
 46%|████▋     | 26678/57600 [4:40:06<5:15:28,  1.63it/s]
 46%|████▋     | 26679/57600 [4:40:07<5:32:28,  1.55it/s]
 46%|████▋     | 26680/57600 [4:40:08<5:24:30,  1.59it/s]
                                                         
{'loss': 1.1929, 'learning_rate': 5.84808362369338e-07, 'epoch': 294.48}

 46%|████▋     | 26680/57600 [4:40:08<5:24:30,  1.59it/s]
 46%|████▋     | 26681/57600 [4:40:08<5:28:50,  1.57it/s]
 46%|████▋     | 26682/57600 [4:40:09<5:28:54,  1.57it/s]
 46%|████▋     | 26683/57600 [4:40:10<5:25:45,  1.58it/s]
 46%|████▋     | 26684/57600 [4:40:10<5:15:54,  1.63it/s]
 46%|████▋     | 26685/57600 [4:40:11<5:17:26,  1.62it/s]
 46%|████▋     | 26686/57600 [4:40:11<5:14:15,  1.64it/s]
 46%|████▋     | 26687/57600 [4:40:12<5:14:17,  1.64it/s]
 46%|████▋     | 26688/57600 [4:40:13<5:24:24,  1.59it/s]
 46%|████▋     | 26689/57600 [4:40:13<5:21:26,  1.60it/s]
 46%|████▋     | 26690/57600 [4:40:14<5:25:18,  1.58it/s]
 46%|████▋     | 26691/57600 [4:40:15<5:27:46,  1.57it/s]
 46%|████▋     | 26692/57600 [4:40:15<5:21:41,  1.60it/s]
 46%|████▋     | 26693/57600 [4:40:16<5:31:28,  1.55it/s]
 46%|████▋     | 26694/57600 [4:40:16<5:31:11,  1.56it/s]
 46%|████▋     | 26695/57600 [4:40:17<5:25:51,  1.58it/s]
 46%|████▋     | 26696/57600 [4:40:18<5:24:25,  1.59it/s]
 46%|████▋     | 26697/57600 [4:40:18<5:29:15,  1.56it/s]
 46%|████▋     | 26698/57600 [4:40:19<5:28:18,  1.57it/s]
 46%|████▋     | 26699/57600 [4:40:20<5:16:47,  1.63it/s]
 46%|████▋     | 26700/57600 [4:40:20<5:18:49,  1.62it/s]
                                                         
{'loss': 1.1652, 'learning_rate': 5.844947735191637e-07, 'epoch': 294.7}

 46%|████▋     | 26700/57600 [4:40:20<5:18:49,  1.62it/s]
 46%|████▋     | 26701/57600 [4:40:21<5:18:59,  1.61it/s]
 46%|████▋     | 26702/57600 [4:40:21<5:12:38,  1.65it/s]
 46%|████▋     | 26703/57600 [4:40:22<5:24:17,  1.59it/s]
 46%|████▋     | 26704/57600 [4:40:23<5:16:54,  1.62it/s]
 46%|████▋     | 26705/57600 [4:40:23<5:19:01,  1.61it/s]
 46%|████▋     | 26706/57600 [4:40:24<5:23:12,  1.59it/s]
 46%|████▋     | 26707/57600 [4:40:25<5:20:10,  1.61it/s]
 46%|████▋     | 26708/57600 [4:40:25<5:29:26,  1.56it/s]
 46%|████▋     | 26709/57600 [4:40:26<5:24:17,  1.59it/s]
 46%|████▋     | 26710/57600 [4:40:26<5:22:19,  1.60it/s]
 46%|████▋     | 26711/57600 [4:40:27<5:24:07,  1.59it/s]
 46%|████▋     | 26712/57600 [4:40:28<5:23:21,  1.59it/s]
 46%|████▋     | 26713/57600 [4:40:28<5:16:18,  1.63it/s]
 46%|████▋     | 26714/57600 [4:40:29<5:29:08,  1.56it/s]
 46%|████▋     | 26715/57600 [4:40:30<5:26:11,  1.58it/s]
 46%|████▋     | 26716/57600 [4:40:30<5:37:42,  1.52it/s]
 46%|████▋     | 26717/57600 [4:40:31<5:33:21,  1.54it/s]
 46%|████▋     | 26718/57600 [4:40:31<5:19:23,  1.61it/s]
 46%|████▋     | 26719/57600 [4:40:32<5:18:56,  1.61it/s]
 46%|████▋     | 26720/57600 [4:40:33<5:21:34,  1.60it/s]
                                                         
{'loss': 1.1923, 'learning_rate': 5.841811846689896e-07, 'epoch': 294.92}

 46%|████▋     | 26720/57600 [4:40:33<5:21:34,  1.60it/s]
 46%|████▋     | 26721/57600 [4:40:33<5:14:31,  1.64it/s]
 46%|████▋     | 26722/57600 [4:40:34<5:21:33,  1.60it/s]
 46%|████▋     | 26723/57600 [4:40:35<5:17:31,  1.62it/s]
 46%|████▋     | 26724/57600 [4:40:35<5:18:30,  1.62it/s]
 46%|████▋     | 26725/57600 [4:40:36<5:16:57,  1.62it/s]
 46%|████▋     | 26726/57600 [4:40:36<5:14:42,  1.64it/s]
 46%|████▋     | 26727/57600 [4:40:37<5:18:50,  1.61it/s]
 46%|████▋     | 26728/57600 [4:40:38<5:31:09,  1.55it/s]
 46%|████▋     | 26729/57600 [4:40:38<5:29:42,  1.56it/s]
 46%|████▋     | 26730/57600 [4:40:39<5:34:52,  1.54it/s]
 46%|████▋     | 26731/57600 [4:40:40<5:35:25,  1.53it/s]
 46%|████▋     | 26732/57600 [4:40:40<5:30:40,  1.56it/s]
 46%|████▋     | 26733/57600 [4:40:41<5:21:20,  1.60it/s]
 46%|████▋     | 26734/57600 [4:40:42<5:24:50,  1.58it/s]
 46%|████▋     | 26735/57600 [4:40:42<5:18:58,  1.61it/s]
 46%|████▋     | 26736/57600 [4:40:43<5:24:28,  1.59it/s]
 46%|████▋     | 26737/57600 [4:40:44<5:40:22,  1.51it/s]
 46%|████▋     | 26738/57600 [4:40:44<5:37:46,  1.52it/s]
 46%|████▋     | 26739/57600 [4:40:45<5:38:43,  1.52it/s]
 46%|████▋     | 26740/57600 [4:40:45<5:38:54,  1.52it/s]
                                                         
{'loss': 1.1919, 'learning_rate': 5.838675958188153e-07, 'epoch': 295.14}

 46%|████▋     | 26740/57600 [4:40:45<5:38:54,  1.52it/s]
 46%|████▋     | 26741/57600 [4:40:46<5:33:01,  1.54it/s]
 46%|████▋     | 26742/57600 [4:40:47<5:38:49,  1.52it/s]
 46%|████▋     | 26743/57600 [4:40:47<5:44:45,  1.49it/s]
 46%|████▋     | 26744/57600 [4:40:48<5:28:46,  1.56it/s]
 46%|████▋     | 26745/57600 [4:40:49<5:19:48,  1.61it/s]
 46%|████▋     | 26746/57600 [4:40:49<5:21:28,  1.60it/s]
 46%|████▋     | 26747/57600 [4:40:50<5:29:47,  1.56it/s]
 46%|████▋     | 26748/57600 [4:40:51<5:19:11,  1.61it/s]
 46%|████▋     | 26749/57600 [4:40:51<5:15:09,  1.63it/s]
 46%|████▋     | 26750/57600 [4:40:52<5:20:01,  1.61it/s]
 46%|████▋     | 26751/57600 [4:40:52<5:16:23,  1.63it/s]
 46%|████▋     | 26752/57600 [4:40:53<5:14:27,  1.63it/s]
 46%|████▋     | 26753/57600 [4:40:54<5:06:34,  1.68it/s]
 46%|████▋     | 26754/57600 [4:40:54<5:09:05,  1.66it/s]
 46%|████▋     | 26755/57600 [4:40:55<5:02:49,  1.70it/s]
 46%|████▋     | 26756/57600 [4:40:55<5:01:59,  1.70it/s]
 46%|████▋     | 26757/57600 [4:40:56<5:09:32,  1.66it/s]
 46%|████▋     | 26758/57600 [4:40:57<5:17:28,  1.62it/s]
 46%|████▋     | 26759/57600 [4:40:57<5:14:36,  1.63it/s]
 46%|████▋     | 26760/57600 [4:40:58<5:31:04,  1.55it/s]
                                                         
{'loss': 1.1995, 'learning_rate': 5.835540069686411e-07, 'epoch': 295.36}

 46%|████▋     | 26760/57600 [4:40:58<5:31:04,  1.55it/s]
 46%|████▋     | 26761/57600 [4:40:59<5:24:33,  1.58it/s]
 46%|████▋     | 26762/57600 [4:40:59<5:11:21,  1.65it/s]
 46%|████▋     | 26763/57600 [4:41:00<5:09:58,  1.66it/s]
 46%|████▋     | 26764/57600 [4:41:00<5:09:01,  1.66it/s]
 46%|████▋     | 26765/57600 [4:41:01<5:07:48,  1.67it/s]
 46%|████▋     | 26766/57600 [4:41:01<5:04:08,  1.69it/s]
 46%|████▋     | 26767/57600 [4:41:02<5:01:54,  1.70it/s]
 46%|████▋     | 26768/57600 [4:41:03<5:19:11,  1.61it/s]
 46%|████▋     | 26769/57600 [4:41:03<5:23:31,  1.59it/s]
 46%|████▋     | 26770/57600 [4:41:04<5:22:23,  1.59it/s]
 46%|████▋     | 26771/57600 [4:41:05<5:19:18,  1.61it/s]
 46%|████▋     | 26772/57600 [4:41:05<5:19:50,  1.61it/s]
 46%|████▋     | 26773/57600 [4:41:06<5:23:42,  1.59it/s]
 46%|████▋     | 26774/57600 [4:41:06<5:18:13,  1.61it/s]
 46%|████▋     | 26775/57600 [4:41:07<5:20:07,  1.60it/s]
 46%|████▋     | 26776/57600 [4:41:08<5:16:17,  1.62it/s]
 46%|████▋     | 26777/57600 [4:41:08<5:12:33,  1.64it/s]
 46%|████▋     | 26778/57600 [4:41:09<5:17:44,  1.62it/s]
 46%|████▋     | 26779/57600 [4:41:10<5:31:06,  1.55it/s]
 46%|████▋     | 26780/57600 [4:41:10<5:24:52,  1.58it/s]
                                                         
{'loss': 1.2217, 'learning_rate': 5.832404181184668e-07, 'epoch': 295.58}

 46%|████▋     | 26780/57600 [4:41:10<5:24:52,  1.58it/s]
 46%|████▋     | 26781/57600 [4:41:11<5:32:30,  1.54it/s]
 46%|████▋     | 26782/57600 [4:41:11<5:19:38,  1.61it/s]
 46%|████▋     | 26783/57600 [4:41:12<5:30:39,  1.55it/s]
 46%|████▋     | 26784/57600 [4:41:13<5:21:28,  1.60it/s]
 47%|████▋     | 26785/57600 [4:41:13<5:24:06,  1.58it/s]
 47%|████▋     | 26786/57600 [4:41:14<5:17:24,  1.62it/s]
 47%|████▋     | 26787/57600 [4:41:15<5:20:29,  1.60it/s]
 47%|████▋     | 26788/57600 [4:41:15<5:15:30,  1.63it/s]
 47%|████▋     | 26789/57600 [4:41:16<5:12:02,  1.65it/s]
 47%|████▋     | 26790/57600 [4:41:16<5:13:22,  1.64it/s]
 47%|████▋     | 26791/57600 [4:41:17<5:21:40,  1.60it/s]
 47%|████▋     | 26792/57600 [4:41:18<5:16:46,  1.62it/s]
 47%|████▋     | 26793/57600 [4:41:18<5:16:58,  1.62it/s]
 47%|████▋     | 26794/57600 [4:41:19<5:20:44,  1.60it/s]
 47%|████▋     | 26795/57600 [4:41:20<5:32:45,  1.54it/s]
 47%|████▋     | 26796/57600 [4:41:20<5:25:21,  1.58it/s]
 47%|████▋     | 26797/57600 [4:41:21<5:19:35,  1.61it/s]
 47%|████▋     | 26798/57600 [4:41:21<5:23:21,  1.59it/s]
 47%|████▋     | 26799/57600 [4:41:22<5:24:22,  1.58it/s]
 47%|████▋     | 26800/57600 [4:41:23<5:18:09,  1.61it/s]
                                                         
{'loss': 1.2089, 'learning_rate': 5.829268292682927e-07, 'epoch': 295.81}

 47%|████▋     | 26800/57600 [4:41:23<5:18:09,  1.61it/s]
 47%|████▋     | 26801/57600 [4:41:23<5:22:33,  1.59it/s]
 47%|████▋     | 26802/57600 [4:41:24<5:17:15,  1.62it/s]
 47%|████▋     | 26803/57600 [4:41:25<5:15:28,  1.63it/s]
 47%|████▋     | 26804/57600 [4:41:25<5:13:51,  1.64it/s]
 47%|████▋     | 26805/57600 [4:41:26<5:13:42,  1.64it/s]
 47%|████▋     | 26806/57600 [4:41:26<5:07:22,  1.67it/s]
 47%|████▋     | 26807/57600 [4:41:27<4:59:37,  1.71it/s]
 47%|████▋     | 26808/57600 [4:41:28<5:09:08,  1.66it/s]
 47%|████▋     | 26809/57600 [4:41:28<5:13:09,  1.64it/s]
 47%|████▋     | 26810/57600 [4:41:29<5:11:19,  1.65it/s]
 47%|████▋     | 26811/57600 [4:41:29<5:10:36,  1.65it/s]
 47%|████▋     | 26812/57600 [4:41:30<5:10:40,  1.65it/s]
 47%|████▋     | 26813/57600 [4:41:31<5:18:19,  1.61it/s]
 47%|████▋     | 26814/57600 [4:41:31<5:17:47,  1.61it/s]
 47%|████▋     | 26815/57600 [4:41:32<5:16:03,  1.62it/s]
 47%|████▋     | 26816/57600 [4:41:32<5:20:20,  1.60it/s]
 47%|████▋     | 26817/57600 [4:41:33<5:19:51,  1.60it/s]
 47%|████▋     | 26818/57600 [4:41:34<5:28:44,  1.56it/s]
 47%|████▋     | 26819/57600 [4:41:34<5:24:23,  1.58it/s]
 47%|████▋     | 26820/57600 [4:41:35<5:20:30,  1.60it/s]
                                                         
{'loss': 1.2007, 'learning_rate': 5.826132404181184e-07, 'epoch': 296.03}

 47%|████▋     | 26820/57600 [4:41:35<5:20:30,  1.60it/s]
 47%|████▋     | 26821/57600 [4:41:36<5:21:29,  1.60it/s]
 47%|████▋     | 26822/57600 [4:41:36<5:25:04,  1.58it/s]
 47%|████▋     | 26823/57600 [4:41:37<5:20:27,  1.60it/s]
 47%|████▋     | 26824/57600 [4:41:37<5:10:32,  1.65it/s]
 47%|████▋     | 26825/57600 [4:41:38<5:21:55,  1.59it/s]
 47%|████▋     | 26826/57600 [4:41:39<5:17:03,  1.62it/s]
 47%|████▋     | 26827/57600 [4:41:39<5:18:38,  1.61it/s]
 47%|████▋     | 26828/57600 [4:41:40<5:25:07,  1.58it/s]
 47%|████▋     | 26829/57600 [4:41:41<5:37:57,  1.52it/s]
 47%|████▋     | 26830/57600 [4:41:41<5:41:30,  1.50it/s]
 47%|████▋     | 26831/57600 [4:41:42<5:31:52,  1.55it/s]
 47%|████▋     | 26832/57600 [4:41:43<5:26:22,  1.57it/s]
 47%|████▋     | 26833/57600 [4:41:43<5:20:35,  1.60it/s]
 47%|████▋     | 26834/57600 [4:41:44<5:14:00,  1.63it/s]
 47%|████▋     | 26835/57600 [4:41:44<5:13:03,  1.64it/s]
 47%|████▋     | 26836/57600 [4:41:45<5:16:36,  1.62it/s]
 47%|████▋     | 26837/57600 [4:41:46<5:21:55,  1.59it/s]
 47%|████▋     | 26838/57600 [4:41:46<5:25:56,  1.57it/s]
 47%|████▋     | 26839/57600 [4:41:47<5:29:27,  1.56it/s]
 47%|████▋     | 26840/57600 [4:41:48<5:25:30,  1.58it/s]
                                                         
{'loss': 1.1839, 'learning_rate': 5.822996515679442e-07, 'epoch': 296.25}

 47%|████▋     | 26840/57600 [4:41:48<5:25:30,  1.58it/s]
 47%|████▋     | 26841/57600 [4:41:48<5:20:27,  1.60it/s]
 47%|████▋     | 26842/57600 [4:41:49<5:13:51,  1.63it/s]
 47%|████▋     | 26843/57600 [4:41:49<5:03:59,  1.69it/s]
 47%|████▋     | 26844/57600 [4:41:50<5:09:26,  1.66it/s]
 47%|████▋     | 26845/57600 [4:41:51<5:19:48,  1.60it/s]
 47%|████▋     | 26846/57600 [4:41:51<5:16:53,  1.62it/s]
 47%|████▋     | 26847/57600 [4:41:52<5:11:03,  1.65it/s]
 47%|████▋     | 26848/57600 [4:41:53<5:32:39,  1.54it/s]
 47%|████▋     | 26849/57600 [4:41:53<5:35:04,  1.53it/s]
 47%|████▋     | 26850/57600 [4:41:54<5:31:15,  1.55it/s]
 47%|████▋     | 26851/57600 [4:41:55<5:36:24,  1.52it/s]
 47%|████▋     | 26852/57600 [4:41:55<5:33:43,  1.54it/s]
 47%|████▋     | 26853/57600 [4:41:56<5:28:32,  1.56it/s]
 47%|████▋     | 26854/57600 [4:41:56<5:22:12,  1.59it/s]
 47%|████▋     | 26855/57600 [4:41:57<5:35:56,  1.53it/s]
 47%|████▋     | 26856/57600 [4:41:58<5:21:17,  1.59it/s]
 47%|████▋     | 26857/57600 [4:41:58<5:18:59,  1.61it/s]
 47%|████▋     | 26858/57600 [4:41:59<5:19:27,  1.60it/s]
 47%|████▋     | 26859/57600 [4:41:59<5:08:43,  1.66it/s]
 47%|████▋     | 26860/57600 [4:42:00<5:04:51,  1.68it/s]
                                                         
{'loss': 1.1946, 'learning_rate': 5.8198606271777e-07, 'epoch': 296.47}

 47%|████▋     | 26860/57600 [4:42:00<5:04:51,  1.68it/s]
 47%|████▋     | 26861/57600 [4:42:01<5:09:39,  1.65it/s]
 47%|████▋     | 26862/57600 [4:42:01<5:14:53,  1.63it/s]
 47%|████▋     | 26863/57600 [4:42:02<5:25:42,  1.57it/s]
 47%|████▋     | 26864/57600 [4:42:03<5:21:01,  1.60it/s]
 47%|████▋     | 26865/57600 [4:42:03<5:18:41,  1.61it/s]
 47%|████▋     | 26866/57600 [4:42:04<5:27:54,  1.56it/s]
 47%|████▋     | 26867/57600 [4:42:05<5:18:27,  1.61it/s]
 47%|████▋     | 26868/57600 [4:42:05<5:12:29,  1.64it/s]
 47%|████▋     | 26869/57600 [4:42:06<5:17:47,  1.61it/s]
 47%|████▋     | 26870/57600 [4:42:06<5:33:56,  1.53it/s]
 47%|████▋     | 26871/57600 [4:42:07<5:34:00,  1.53it/s]
 47%|████▋     | 26872/57600 [4:42:08<5:29:58,  1.55it/s]
 47%|████▋     | 26873/57600 [4:42:08<5:30:49,  1.55it/s]
 47%|████▋     | 26874/57600 [4:42:09<5:31:17,  1.55it/s]
 47%|████▋     | 26875/57600 [4:42:10<5:28:58,  1.56it/s]
 47%|████▋     | 26876/57600 [4:42:10<5:23:50,  1.58it/s]
 47%|████▋     | 26877/57600 [4:42:11<5:23:16,  1.58it/s]
 47%|████▋     | 26878/57600 [4:42:12<5:24:47,  1.58it/s]
 47%|████▋     | 26879/57600 [4:42:12<5:24:06,  1.58it/s]
 47%|████▋     | 26880/57600 [4:42:13<5:15:22,  1.62it/s]
                                                         
{'loss': 1.2003, 'learning_rate': 5.816724738675958e-07, 'epoch': 296.69}

 47%|████▋     | 26880/57600 [4:42:13<5:15:22,  1.62it/s]
 47%|████▋     | 26881/57600 [4:42:13<5:10:46,  1.65it/s]
 47%|████▋     | 26882/57600 [4:42:14<5:18:30,  1.61it/s]
 47%|████▋     | 26883/57600 [4:42:15<5:13:20,  1.63it/s]
 47%|████▋     | 26884/57600 [4:42:15<5:05:09,  1.68it/s]
 47%|████▋     | 26885/57600 [4:42:16<5:16:22,  1.62it/s]
 47%|████▋     | 26886/57600 [4:42:16<5:16:56,  1.62it/s]
 47%|████▋     | 26887/57600 [4:42:17<5:12:46,  1.64it/s]
 47%|████▋     | 26888/57600 [4:42:18<5:09:05,  1.66it/s]
 47%|████▋     | 26889/57600 [4:42:18<5:10:52,  1.65it/s]
 47%|████▋     | 26890/57600 [4:42:19<5:09:30,  1.65it/s]
 47%|████▋     | 26891/57600 [4:42:19<5:04:40,  1.68it/s]
 47%|████▋     | 26892/57600 [4:42:20<5:04:18,  1.68it/s]
 47%|████▋     | 26893/57600 [4:42:21<5:03:32,  1.69it/s]
 47%|████▋     | 26894/57600 [4:42:21<5:14:32,  1.63it/s]
 47%|████▋     | 26895/57600 [4:42:22<5:15:59,  1.62it/s]
 47%|████▋     | 26896/57600 [4:42:22<5:07:23,  1.66it/s]
 47%|████▋     | 26897/57600 [4:42:23<5:14:08,  1.63it/s]
 47%|████▋     | 26898/57600 [4:42:24<5:11:17,  1.64it/s]
 47%|████▋     | 26899/57600 [4:42:24<5:15:25,  1.62it/s]
 47%|████▋     | 26900/57600 [4:42:25<5:21:37,  1.59it/s]
                                                         
{'loss': 1.2044, 'learning_rate': 5.813588850174216e-07, 'epoch': 296.91}

 47%|████▋     | 26900/57600 [4:42:25<5:21:37,  1.59it/s]
 47%|████▋     | 26901/57600 [4:42:26<5:16:38,  1.62it/s]
 47%|████▋     | 26902/57600 [4:42:26<5:18:20,  1.61it/s]
 47%|████▋     | 26903/57600 [4:42:27<5:22:20,  1.59it/s]
 47%|████▋     | 26904/57600 [4:42:27<5:20:37,  1.60it/s]
 47%|████▋     | 26905/57600 [4:42:28<5:20:53,  1.59it/s]
 47%|████▋     | 26906/57600 [4:42:29<5:21:23,  1.59it/s]
 47%|████▋     | 26907/57600 [4:42:29<5:21:40,  1.59it/s]
 47%|████▋     | 26908/57600 [4:42:30<5:16:03,  1.62it/s]
 47%|████▋     | 26909/57600 [4:42:31<5:22:37,  1.59it/s]
 47%|████▋     | 26910/57600 [4:42:31<5:18:38,  1.61it/s]
 47%|████▋     | 26911/57600 [4:42:32<5:16:17,  1.62it/s]
 47%|████▋     | 26912/57600 [4:42:32<5:11:24,  1.64it/s]
 47%|████▋     | 26913/57600 [4:42:33<5:13:46,  1.63it/s]
 47%|████▋     | 26914/57600 [4:42:34<5:09:15,  1.65it/s]
 47%|████▋     | 26915/57600 [4:42:34<5:20:30,  1.60it/s]
 47%|████▋     | 26916/57600 [4:42:35<5:17:37,  1.61it/s]
 47%|████▋     | 26917/57600 [4:42:36<5:15:45,  1.62it/s]
 47%|████▋     | 26918/57600 [4:42:36<5:12:16,  1.64it/s]
 47%|████▋     | 26919/57600 [4:42:37<5:12:48,  1.63it/s]
 47%|████▋     | 26920/57600 [4:42:37<5:18:54,  1.60it/s]
                                                         
{'loss': 1.2163, 'learning_rate': 5.810452961672473e-07, 'epoch': 297.13}

 47%|████▋     | 26920/57600 [4:42:37<5:18:54,  1.60it/s]
 47%|████▋     | 26921/57600 [4:42:38<5:23:31,  1.58it/s]
 47%|████▋     | 26922/57600 [4:42:39<5:16:10,  1.62it/s]
 47%|████▋     | 26923/57600 [4:42:39<5:13:42,  1.63it/s]
 47%|████▋     | 26924/57600 [4:42:40<5:21:25,  1.59it/s]
 47%|████▋     | 26925/57600 [4:42:41<5:26:20,  1.57it/s]
 47%|████▋     | 26926/57600 [4:42:41<5:15:25,  1.62it/s]
 47%|████▋     | 26927/57600 [4:42:42<5:20:23,  1.60it/s]
 47%|████▋     | 26928/57600 [4:42:42<5:17:13,  1.61it/s]
 47%|████▋     | 26929/57600 [4:42:43<5:22:50,  1.58it/s]
 47%|████▋     | 26930/57600 [4:42:44<5:14:34,  1.62it/s]
 47%|████▋     | 26931/57600 [4:42:44<5:16:10,  1.62it/s]
 47%|████▋     | 26932/57600 [4:42:45<5:18:57,  1.60it/s]
 47%|████▋     | 26933/57600 [4:42:46<5:24:33,  1.57it/s]
 47%|████▋     | 26934/57600 [4:42:46<5:22:49,  1.58it/s]
 47%|████▋     | 26935/57600 [4:42:47<5:11:10,  1.64it/s]
 47%|████▋     | 26936/57600 [4:42:47<5:13:15,  1.63it/s]
 47%|████▋     | 26937/57600 [4:42:48<5:20:19,  1.60it/s]
 47%|████▋     | 26938/57600 [4:42:49<5:18:14,  1.61it/s]
 47%|████▋     | 26939/57600 [4:42:49<5:16:35,  1.61it/s]
 47%|████▋     | 26940/57600 [4:42:50<5:27:47,  1.56it/s]
                                                         
{'loss': 1.1956, 'learning_rate': 5.807317073170733e-07, 'epoch': 297.35}

 47%|████▋     | 26940/57600 [4:42:50<5:27:47,  1.56it/s]
 47%|████▋     | 26941/57600 [4:42:50<5:17:51,  1.61it/s]
 47%|████▋     | 26942/57600 [4:42:51<5:22:11,  1.59it/s]
 47%|████▋     | 26943/57600 [4:42:52<5:21:08,  1.59it/s]
 47%|████▋     | 26944/57600 [4:42:52<5:19:45,  1.60it/s]
 47%|████▋     | 26945/57600 [4:42:53<5:29:22,  1.55it/s]
 47%|████▋     | 26946/57600 [4:42:54<5:27:09,  1.56it/s]
 47%|████▋     | 26947/57600 [4:42:54<5:26:43,  1.56it/s]
 47%|████▋     | 26948/57600 [4:42:55<5:16:08,  1.62it/s]
 47%|████▋     | 26949/57600 [4:42:56<5:19:27,  1.60it/s]
 47%|████▋     | 26950/57600 [4:42:56<5:20:56,  1.59it/s]
 47%|████▋     | 26951/57600 [4:42:57<5:27:24,  1.56it/s]
 47%|████▋     | 26952/57600 [4:42:57<5:26:23,  1.57it/s]
 47%|████▋     | 26953/57600 [4:42:58<5:19:37,  1.60it/s]
 47%|████▋     | 26954/57600 [4:42:59<5:30:28,  1.55it/s]
 47%|████▋     | 26955/57600 [4:42:59<5:23:09,  1.58it/s]
 47%|████▋     | 26956/57600 [4:43:00<5:14:38,  1.62it/s]
 47%|████▋     | 26957/57600 [4:43:00<5:05:24,  1.67it/s]
 47%|████▋     | 26958/57600 [4:43:01<5:06:01,  1.67it/s]
 47%|████▋     | 26959/57600 [4:43:02<5:02:51,  1.69it/s]
 47%|████▋     | 26960/57600 [4:43:02<5:12:44,  1.63it/s]
                                                         
{'loss': 1.2227, 'learning_rate': 5.804181184668989e-07, 'epoch': 297.57}

 47%|████▋     | 26960/57600 [4:43:02<5:12:44,  1.63it/s]
 47%|████▋     | 26961/57600 [4:43:03<5:14:12,  1.63it/s]
 47%|████▋     | 26962/57600 [4:43:04<5:06:46,  1.66it/s]
 47%|████▋     | 26963/57600 [4:43:04<5:10:46,  1.64it/s]
 47%|████▋     | 26964/57600 [4:43:05<5:16:23,  1.61it/s]
 47%|████▋     | 26965/57600 [4:43:05<5:08:52,  1.65it/s]
 47%|████▋     | 26966/57600 [4:43:06<5:08:37,  1.65it/s]
 47%|████▋     | 26967/57600 [4:43:07<5:17:29,  1.61it/s]
 47%|████▋     | 26968/57600 [4:43:07<5:13:56,  1.63it/s]
 47%|████▋     | 26969/57600 [4:43:08<5:09:20,  1.65it/s]
 47%|████▋     | 26970/57600 [4:43:08<5:04:26,  1.68it/s]
 47%|████▋     | 26971/57600 [4:43:09<5:02:02,  1.69it/s]
 47%|████▋     | 26972/57600 [4:43:10<5:06:36,  1.66it/s]
 47%|████▋     | 26973/57600 [4:43:10<5:06:03,  1.67it/s]
 47%|████▋     | 26974/57600 [4:43:11<5:08:38,  1.65it/s]
 47%|████▋     | 26975/57600 [4:43:11<5:02:22,  1.69it/s]
 47%|████▋     | 26976/57600 [4:43:12<5:11:04,  1.64it/s]
 47%|████▋     | 26977/57600 [4:43:13<5:17:33,  1.61it/s]
 47%|████▋     | 26978/57600 [4:43:13<5:21:44,  1.59it/s]
 47%|████▋     | 26979/57600 [4:43:14<5:16:23,  1.61it/s]
 47%|████▋     | 26980/57600 [4:43:15<5:25:20,  1.57it/s]
                                                         
{'loss': 1.216, 'learning_rate': 5.801045296167248e-07, 'epoch': 297.79}

 47%|████▋     | 26980/57600 [4:43:15<5:25:20,  1.57it/s]
 47%|████▋     | 26981/57600 [4:43:15<5:25:49,  1.57it/s]
 47%|████▋     | 26982/57600 [4:43:16<5:19:15,  1.60it/s]
 47%|████▋     | 26983/57600 [4:43:16<5:13:20,  1.63it/s]
 47%|████▋     | 26984/57600 [4:43:17<5:19:19,  1.60it/s]
 47%|████▋     | 26985/57600 [4:43:18<5:29:01,  1.55it/s]
 47%|████▋     | 26986/57600 [4:43:18<5:20:40,  1.59it/s]
 47%|████▋     | 26987/57600 [4:43:19<5:29:09,  1.55it/s]
 47%|████▋     | 26988/57600 [4:43:20<5:24:43,  1.57it/s]
 47%|████▋     | 26989/57600 [4:43:20<5:24:49,  1.57it/s]
 47%|████▋     | 26990/57600 [4:43:21<5:20:20,  1.59it/s]
 47%|████▋     | 26991/57600 [4:43:22<5:24:11,  1.57it/s]
 47%|████▋     | 26992/57600 [4:43:22<5:24:07,  1.57it/s]
 47%|████▋     | 26993/57600 [4:43:23<5:16:00,  1.61it/s]
 47%|████▋     | 26994/57600 [4:43:23<5:18:39,  1.60it/s]
 47%|████▋     | 26995/57600 [4:43:24<5:14:13,  1.62it/s]
 47%|████▋     | 26996/57600 [4:43:25<5:15:28,  1.62it/s]
 47%|████▋     | 26997/57600 [4:43:25<5:19:31,  1.60it/s]
 47%|████▋     | 26998/57600 [4:43:26<5:18:46,  1.60it/s]
 47%|████▋     | 26999/57600 [4:43:27<5:22:59,  1.58it/s]
 47%|████▋     | 27000/57600 [4:43:27<5:23:36,  1.58it/s]
                                                         
{'loss': 1.2001, 'learning_rate': 5.797909407665505e-07, 'epoch': 298.01}

 47%|████▋     | 27000/57600 [4:43:27<5:23:36,  1.58it/s]
 47%|████▋     | 27001/57600 [4:43:28<5:25:06,  1.57it/s]
 47%|████▋     | 27002/57600 [4:43:28<5:25:34,  1.57it/s]
 47%|████▋     | 27003/57600 [4:43:29<5:21:55,  1.58it/s]
 47%|████▋     | 27004/57600 [4:43:30<5:38:35,  1.51it/s]
 47%|████▋     | 27005/57600 [4:43:31<5:50:12,  1.46it/s]
 47%|████▋     | 27006/57600 [4:43:31<5:37:27,  1.51it/s]
 47%|████▋     | 27007/57600 [4:43:32<5:27:39,  1.56it/s]
 47%|████▋     | 27008/57600 [4:43:32<5:19:21,  1.60it/s]
 47%|████▋     | 27009/57600 [4:43:33<5:16:14,  1.61it/s]
 47%|████▋     | 27010/57600 [4:43:34<5:19:09,  1.60it/s]
 47%|████▋     | 27011/57600 [4:43:34<5:13:46,  1.62it/s]
 47%|████▋     | 27012/57600 [4:43:35<5:11:40,  1.64it/s]
 47%|████▋     | 27013/57600 [4:43:35<5:09:33,  1.65it/s]
 47%|████▋     | 27014/57600 [4:43:36<5:13:54,  1.62it/s]
 47%|████▋     | 27015/57600 [4:43:37<5:08:35,  1.65it/s]
 47%|████▋     | 27016/57600 [4:43:37<5:13:10,  1.63it/s]
 47%|████▋     | 27017/57600 [4:43:38<5:27:09,  1.56it/s]
 47%|████▋     | 27018/57600 [4:43:39<5:15:02,  1.62it/s]
 47%|████▋     | 27019/57600 [4:43:39<5:11:32,  1.64it/s]
 47%|████▋     | 27020/57600 [4:43:40<5:21:48,  1.58it/s]
                                                         
{'loss': 1.1819, 'learning_rate': 5.794773519163763e-07, 'epoch': 298.23}

 47%|████▋     | 27020/57600 [4:43:40<5:21:48,  1.58it/s]
 47%|████▋     | 27021/57600 [4:43:40<5:26:51,  1.56it/s]
 47%|████▋     | 27022/57600 [4:43:41<5:22:29,  1.58it/s]
 47%|████▋     | 27023/57600 [4:43:42<5:17:41,  1.60it/s]
 47%|████▋     | 27024/57600 [4:43:42<5:16:28,  1.61it/s]
 47%|████▋     | 27025/57600 [4:43:43<5:19:47,  1.59it/s]
 47%|████▋     | 27026/57600 [4:43:44<5:25:56,  1.56it/s]
 47%|████▋     | 27027/57600 [4:43:44<5:18:50,  1.60it/s]
 47%|████▋     | 27028/57600 [4:43:45<5:12:40,  1.63it/s]
 47%|████▋     | 27029/57600 [4:43:45<5:21:15,  1.59it/s]
 47%|████▋     | 27030/57600 [4:43:46<5:14:53,  1.62it/s]
 47%|████▋     | 27031/57600 [4:43:47<5:09:25,  1.65it/s]
 47%|████▋     | 27032/57600 [4:43:47<5:07:40,  1.66it/s]
 47%|████▋     | 27033/57600 [4:43:48<5:05:08,  1.67it/s]
 47%|████▋     | 27034/57600 [4:43:48<5:21:11,  1.59it/s]
 47%|████▋     | 27035/57600 [4:43:49<5:24:57,  1.57it/s]
 47%|████▋     | 27036/57600 [4:43:50<5:25:01,  1.57it/s]
 47%|████▋     | 27037/57600 [4:43:50<5:18:33,  1.60it/s]
 47%|████▋     | 27038/57600 [4:43:51<5:20:50,  1.59it/s]
 47%|████▋     | 27039/57600 [4:43:52<5:16:03,  1.61it/s]
 47%|████▋     | 27040/57600 [4:43:52<5:11:27,  1.64it/s]
                                                         
{'loss': 1.172, 'learning_rate': 5.79163763066202e-07, 'epoch': 298.45}

 47%|████▋     | 27040/57600 [4:43:52<5:11:27,  1.64it/s]
 47%|████▋     | 27041/57600 [4:43:53<5:09:34,  1.65it/s]
 47%|████▋     | 27042/57600 [4:43:53<5:10:09,  1.64it/s]
 47%|████▋     | 27043/57600 [4:43:54<5:05:15,  1.67it/s]
 47%|████▋     | 27044/57600 [4:43:55<5:16:08,  1.61it/s]
 47%|████▋     | 27045/57600 [4:43:55<5:11:55,  1.63it/s]
 47%|████▋     | 27046/57600 [4:43:56<5:18:13,  1.60it/s]
 47%|████▋     | 27047/57600 [4:43:57<5:19:05,  1.60it/s]
 47%|████▋     | 27048/57600 [4:43:57<5:11:00,  1.64it/s]
 47%|████▋     | 27049/57600 [4:43:58<5:05:54,  1.66it/s]
 47%|████▋     | 27050/57600 [4:43:58<5:22:20,  1.58it/s]
 47%|████▋     | 27051/57600 [4:43:59<5:24:34,  1.57it/s]
 47%|████▋     | 27052/57600 [4:44:00<5:20:21,  1.59it/s]
 47%|████▋     | 27053/57600 [4:44:00<5:26:21,  1.56it/s]
 47%|████▋     | 27054/57600 [4:44:01<5:17:31,  1.60it/s]
 47%|████▋     | 27055/57600 [4:44:02<5:29:00,  1.55it/s]
 47%|████▋     | 27056/57600 [4:44:02<5:22:40,  1.58it/s]
 47%|████▋     | 27057/57600 [4:44:03<5:29:14,  1.55it/s]
 47%|████▋     | 27058/57600 [4:44:03<5:11:45,  1.63it/s]
 47%|████▋     | 27059/57600 [4:44:04<5:06:35,  1.66it/s]
 47%|████▋     | 27060/57600 [4:44:05<5:20:23,  1.59it/s]
                                                         
{'loss': 1.1822, 'learning_rate': 5.788501742160278e-07, 'epoch': 298.68}

 47%|████▋     | 27060/57600 [4:44:05<5:20:23,  1.59it/s]
 47%|████▋     | 27061/57600 [4:44:05<5:11:07,  1.64it/s]
 47%|████▋     | 27062/57600 [4:44:06<5:03:21,  1.68it/s]
 47%|████▋     | 27063/57600 [4:44:06<5:03:24,  1.68it/s]
 47%|████▋     | 27064/57600 [4:44:07<5:03:09,  1.68it/s]
 47%|████▋     | 27065/57600 [4:44:08<5:03:46,  1.68it/s]
 47%|████▋     | 27066/57600 [4:44:08<5:08:45,  1.65it/s]
 47%|████▋     | 27067/57600 [4:44:09<5:03:21,  1.68it/s]
 47%|████▋     | 27068/57600 [4:44:09<5:05:58,  1.66it/s]
 47%|████▋     | 27069/57600 [4:44:10<4:57:47,  1.71it/s]
 47%|████▋     | 27070/57600 [4:44:11<5:01:09,  1.69it/s]
 47%|████▋     | 27071/57600 [4:44:11<4:57:27,  1.71it/s]
 47%|████▋     | 27072/57600 [4:44:12<5:01:14,  1.69it/s]
 47%|████▋     | 27073/57600 [4:44:12<5:06:07,  1.66it/s]
 47%|████▋     | 27074/57600 [4:44:13<5:10:35,  1.64it/s]
 47%|████▋     | 27075/57600 [4:44:14<5:12:06,  1.63it/s]
 47%|████▋     | 27076/57600 [4:44:14<5:11:31,  1.63it/s]
 47%|████▋     | 27077/57600 [4:44:15<5:20:18,  1.59it/s]
 47%|████▋     | 27078/57600 [4:44:16<5:16:31,  1.61it/s]
 47%|████▋     | 27079/57600 [4:44:16<5:20:39,  1.59it/s]
 47%|████▋     | 27080/57600 [4:44:17<5:13:39,  1.62it/s]
                                                         
{'loss': 1.2188, 'learning_rate': 5.785365853658536e-07, 'epoch': 298.9}

 47%|████▋     | 27080/57600 [4:44:17<5:13:39,  1.62it/s]
 47%|████▋     | 27081/57600 [4:44:17<5:08:02,  1.65it/s]
 47%|████▋     | 27082/57600 [4:44:18<5:07:31,  1.65it/s]
 47%|████▋     | 27083/57600 [4:44:19<5:14:51,  1.62it/s]
 47%|████▋     | 27084/57600 [4:44:19<5:06:57,  1.66it/s]
 47%|████▋     | 27085/57600 [4:44:20<5:06:02,  1.66it/s]
 47%|████▋     | 27086/57600 [4:44:20<5:07:22,  1.65it/s]
 47%|████▋     | 27087/57600 [4:44:21<5:10:24,  1.64it/s]
 47%|████▋     | 27088/57600 [4:44:22<5:19:30,  1.59it/s]
 47%|████▋     | 27089/57600 [4:44:22<5:26:15,  1.56it/s]
 47%|████▋     | 27090/57600 [4:44:23<5:30:55,  1.54it/s]
 47%|████▋     | 27091/57600 [4:44:24<5:26:51,  1.56it/s]
 47%|████▋     | 27092/57600 [4:44:24<5:17:19,  1.60it/s]
 47%|████▋     | 27093/57600 [4:44:25<5:17:01,  1.60it/s]
 47%|████▋     | 27094/57600 [4:44:25<5:20:38,  1.59it/s]
 47%|████▋     | 27095/57600 [4:44:26<5:26:15,  1.56it/s]
 47%|████▋     | 27096/57600 [4:44:27<5:13:56,  1.62it/s]
 47%|████▋     | 27097/57600 [4:44:27<5:10:58,  1.63it/s]
 47%|████▋     | 27098/57600 [4:44:28<5:10:14,  1.64it/s]
 47%|████▋     | 27099/57600 [4:44:29<5:27:33,  1.55it/s]
 47%|████▋     | 27100/57600 [4:44:29<5:14:44,  1.62it/s]
                                                         
{'loss': 1.2073, 'learning_rate': 5.782229965156794e-07, 'epoch': 299.12}

 47%|████▋     | 27100/57600 [4:44:29<5:14:44,  1.62it/s]
 47%|████▋     | 27101/57600 [4:44:30<5:24:19,  1.57it/s]
 47%|████▋     | 27102/57600 [4:44:31<5:24:54,  1.56it/s]
 47%|████▋     | 27103/57600 [4:44:31<5:25:11,  1.56it/s]
 47%|████▋     | 27104/57600 [4:44:32<5:20:33,  1.59it/s]
 47%|████▋     | 27105/57600 [4:44:32<5:13:25,  1.62it/s]
 47%|████▋     | 27106/57600 [4:44:33<5:15:14,  1.61it/s]
 47%|████▋     | 27107/57600 [4:44:34<5:16:58,  1.60it/s]
 47%|████▋     | 27108/57600 [4:44:34<5:28:25,  1.55it/s]
 47%|████▋     | 27109/57600 [4:44:35<5:19:18,  1.59it/s]
 47%|████▋     | 27110/57600 [4:44:35<5:08:48,  1.65it/s]
 47%|████▋     | 27111/57600 [4:44:36<5:10:29,  1.64it/s]
 47%|████▋     | 27112/57600 [4:44:37<5:08:30,  1.65it/s]
 47%|████▋     | 27113/57600 [4:44:37<5:19:30,  1.59it/s]
 47%|████▋     | 27114/57600 [4:44:38<5:20:45,  1.58it/s]
 47%|████▋     | 27115/57600 [4:44:39<5:12:27,  1.63it/s]
 47%|████▋     | 27116/57600 [4:44:39<5:02:54,  1.68it/s]
 47%|████▋     | 27117/57600 [4:44:40<5:13:06,  1.62it/s]
 47%|████▋     | 27118/57600 [4:44:40<5:08:31,  1.65it/s]
 47%|████▋     | 27119/57600 [4:44:41<5:03:35,  1.67it/s]
 47%|████▋     | 27120/57600 [4:44:42<5:02:21,  1.68it/s]
                                                         
{'loss': 1.2013, 'learning_rate': 5.779094076655052e-07, 'epoch': 299.34}

 47%|████▋     | 27120/57600 [4:44:42<5:02:21,  1.68it/s]
 47%|████▋     | 27121/57600 [4:44:42<5:00:17,  1.69it/s]
 47%|████▋     | 27122/57600 [4:44:43<5:05:14,  1.66it/s]
 47%|████▋     | 27123/57600 [4:44:43<5:06:45,  1.66it/s]
 47%|████▋     | 27124/57600 [4:44:44<4:56:22,  1.71it/s]
 47%|████▋     | 27125/57600 [4:44:45<5:00:07,  1.69it/s]
 47%|████▋     | 27126/57600 [4:44:45<5:10:19,  1.64it/s]
 47%|████▋     | 27127/57600 [4:44:46<5:05:09,  1.66it/s]
 47%|████▋     | 27128/57600 [4:44:46<5:03:18,  1.67it/s]
 47%|████▋     | 27129/57600 [4:44:47<5:14:36,  1.61it/s]
 47%|████▋     | 27130/57600 [4:44:48<5:18:10,  1.60it/s]
 47%|████▋     | 27131/57600 [4:44:48<5:15:54,  1.61it/s]
 47%|████▋     | 27132/57600 [4:44:49<5:18:21,  1.60it/s]
 47%|████▋     | 27133/57600 [4:44:50<5:19:20,  1.59it/s]
 47%|████▋     | 27134/57600 [4:44:50<5:18:01,  1.60it/s]
 47%|████▋     | 27135/57600 [4:44:51<5:11:17,  1.63it/s]
 47%|████▋     | 27136/57600 [4:44:51<5:04:05,  1.67it/s]
 47%|████▋     | 27137/57600 [4:44:52<5:12:34,  1.62it/s]
 47%|████▋     | 27138/57600 [4:44:53<5:10:07,  1.64it/s]
 47%|████▋     | 27139/57600 [4:44:53<5:03:37,  1.67it/s]
 47%|████▋     | 27140/57600 [4:44:54<5:05:03,  1.66it/s]
                                                         
{'loss': 1.2272, 'learning_rate': 5.77595818815331e-07, 'epoch': 299.56}

 47%|████▋     | 27140/57600 [4:44:54<5:05:03,  1.66it/s]
 47%|████▋     | 27141/57600 [4:44:54<5:18:39,  1.59it/s]
 47%|████▋     | 27142/57600 [4:44:55<5:16:12,  1.61it/s]
 47%|████▋     | 27143/57600 [4:44:56<5:20:17,  1.58it/s]
 47%|████▋     | 27144/57600 [4:44:56<5:20:26,  1.58it/s]
 47%|████▋     | 27145/57600 [4:44:57<5:24:28,  1.56it/s]
 47%|████▋     | 27146/57600 [4:44:58<5:14:06,  1.62it/s]
 47%|████▋     | 27147/57600 [4:44:58<5:04:28,  1.67it/s]
 47%|████▋     | 27148/57600 [4:44:59<5:01:01,  1.69it/s]
 47%|████▋     | 27149/57600 [4:44:59<5:01:18,  1.68it/s]
 47%|████▋     | 27150/57600 [4:45:00<5:12:41,  1.62it/s]
 47%|████▋     | 27151/57600 [4:45:01<5:12:33,  1.62it/s]
 47%|████▋     | 27152/57600 [4:45:01<5:25:20,  1.56it/s]
 47%|████▋     | 27153/57600 [4:45:02<5:40:57,  1.49it/s]
 47%|████▋     | 27154/57600 [4:45:03<5:42:31,  1.48it/s]
 47%|████▋     | 27155/57600 [4:45:03<5:47:27,  1.46it/s]
 47%|████▋     | 27156/57600 [4:45:04<5:35:41,  1.51it/s]
 47%|████▋     | 27157/57600 [4:45:05<5:26:07,  1.56it/s]
 47%|████▋     | 27158/57600 [4:45:05<5:18:26,  1.59it/s]
 47%|████▋     | 27159/57600 [4:45:06<5:20:09,  1.58it/s]
 47%|████▋     | 27160/57600 [4:45:07<5:31:39,  1.53it/s]
                                                         
{'loss': 1.1641, 'learning_rate': 5.772822299651568e-07, 'epoch': 299.78}

 47%|████▋     | 27160/57600 [4:45:07<5:31:39,  1.53it/s]
 47%|████▋     | 27161/57600 [4:45:07<5:21:17,  1.58it/s]
 47%|████▋     | 27162/57600 [4:45:08<5:23:34,  1.57it/s]
 47%|████▋     | 27163/57600 [4:45:08<5:18:16,  1.59it/s]
 47%|████▋     | 27164/57600 [4:45:09<5:19:29,  1.59it/s]
 47%|████▋     | 27165/57600 [4:45:10<5:23:21,  1.57it/s]
 47%|████▋     | 27166/57600 [4:45:10<5:27:55,  1.55it/s]
 47%|████▋     | 27167/57600 [4:45:11<5:37:12,  1.50it/s]
 47%|████▋     | 27168/57600 [4:45:12<5:31:13,  1.53it/s]
 47%|████▋     | 27169/57600 [4:45:12<5:24:37,  1.56it/s]
 47%|████▋     | 27170/57600 [4:45:13<5:20:47,  1.58it/s]
 47%|████▋     | 27171/57600 [4:45:13<5:10:28,  1.63it/s]
 47%|████▋     | 27172/57600 [4:45:14<5:11:17,  1.63it/s]
 47%|████▋     | 27173/57600 [4:45:15<5:15:43,  1.61it/s]
 47%|████▋     | 27174/57600 [4:45:15<5:25:06,  1.56it/s]
 47%|████▋     | 27175/57600 [4:45:16<5:28:26,  1.54it/s]
 47%|████▋     | 27176/57600 [4:45:17<5:35:32,  1.51it/s]
 47%|████▋     | 27177/57600 [4:45:17<5:31:22,  1.53it/s]
 47%|████▋     | 27178/57600 [4:45:18<5:23:47,  1.57it/s]
 47%|████▋     | 27179/57600 [4:45:19<5:26:24,  1.55it/s]
 47%|████▋     | 27180/57600 [4:45:19<5:33:23,  1.52it/s]
                                                         
{'loss': 1.1675, 'learning_rate': 5.769686411149826e-07, 'epoch': 300.0}

 47%|████▋     | 27180/57600 [4:45:19<5:33:23,  1.52it/s]
 47%|████▋     | 27181/57600 [4:45:20<5:38:08,  1.50it/s]
 47%|████▋     | 27182/57600 [4:45:21<5:36:05,  1.51it/s]
 47%|████▋     | 27183/57600 [4:45:21<5:23:37,  1.57it/s]
 47%|████▋     | 27184/57600 [4:45:22<5:25:54,  1.56it/s]
 47%|████▋     | 27185/57600 [4:45:23<5:19:09,  1.59it/s]
 47%|████▋     | 27186/57600 [4:45:23<5:16:17,  1.60it/s]
 47%|████▋     | 27187/57600 [4:45:24<5:04:48,  1.66it/s]
 47%|████▋     | 27188/57600 [4:45:24<5:02:19,  1.68it/s]
 47%|████▋     | 27189/57600 [4:45:25<5:18:22,  1.59it/s]
 47%|████▋     | 27190/57600 [4:45:26<5:06:49,  1.65it/s]
 47%|████▋     | 27191/57600 [4:45:26<5:07:32,  1.65it/s]
 47%|████▋     | 27192/57600 [4:45:27<5:10:15,  1.63it/s]
 47%|████▋     | 27193/57600 [4:45:27<5:23:12,  1.57it/s]
 47%|████▋     | 27194/57600 [4:45:28<5:20:22,  1.58it/s]
 47%|████▋     | 27195/57600 [4:45:29<5:17:08,  1.60it/s]
 47%|████▋     | 27196/57600 [4:45:29<5:05:33,  1.66it/s]
 47%|████▋     | 27197/57600 [4:45:30<5:12:15,  1.62it/s]
 47%|████▋     | 27198/57600 [4:45:30<5:08:28,  1.64it/s]
 47%|████▋     | 27199/57600 [4:45:31<5:12:40,  1.62it/s]
 47%|████▋     | 27200/57600 [4:45:32<5:16:22,  1.60it/s]
                                                         
{'loss': 1.2051, 'learning_rate': 5.766550522648083e-07, 'epoch': 300.22}

 47%|████▋     | 27200/57600 [4:45:32<5:16:22,  1.60it/s]
 47%|████▋     | 27201/57600 [4:45:32<5:21:04,  1.58it/s]
 47%|████▋     | 27202/57600 [4:45:33<5:27:10,  1.55it/s]
 47%|████▋     | 27203/57600 [4:45:34<5:37:37,  1.50it/s]
 47%|████▋     | 27204/57600 [4:45:34<5:31:46,  1.53it/s]
 47%|████▋     | 27205/57600 [4:45:35<5:33:50,  1.52it/s]
 47%|████▋     | 27206/57600 [4:45:36<5:29:35,  1.54it/s]
 47%|████▋     | 27207/57600 [4:45:36<5:31:15,  1.53it/s]
 47%|████▋     | 27208/57600 [4:45:37<5:36:00,  1.51it/s]
 47%|████▋     | 27209/57600 [4:45:38<5:31:02,  1.53it/s]
 47%|████▋     | 27210/57600 [4:45:38<5:18:42,  1.59it/s]
 47%|████▋     | 27211/57600 [4:45:39<5:13:14,  1.62it/s]
 47%|████▋     | 27212/57600 [4:45:39<5:18:14,  1.59it/s]
 47%|████▋     | 27213/57600 [4:45:40<5:05:31,  1.66it/s]
 47%|████▋     | 27214/57600 [4:45:41<5:20:01,  1.58it/s]
 47%|████▋     | 27215/57600 [4:45:41<5:33:22,  1.52it/s]
 47%|████▋     | 27216/57600 [4:45:42<5:26:41,  1.55it/s]
 47%|████▋     | 27217/57600 [4:45:43<5:18:11,  1.59it/s]
 47%|████▋     | 27218/57600 [4:45:43<5:12:16,  1.62it/s]
 47%|████▋     | 27219/57600 [4:45:44<5:17:13,  1.60it/s]
 47%|████▋     | 27220/57600 [4:45:45<5:18:35,  1.59it/s]
                                                         
{'loss': 1.1936, 'learning_rate': 5.763414634146341e-07, 'epoch': 300.44}

 47%|████▋     | 27220/57600 [4:45:45<5:18:35,  1.59it/s]
 47%|████▋     | 27221/57600 [4:45:45<5:17:14,  1.60it/s]
 47%|████▋     | 27222/57600 [4:45:46<5:12:58,  1.62it/s]
 47%|████▋     | 27223/57600 [4:45:46<5:18:38,  1.59it/s]
 47%|████▋     | 27224/57600 [4:45:47<5:11:58,  1.62it/s]
 47%|████▋     | 27225/57600 [4:45:48<5:10:39,  1.63it/s]
 47%|████▋     | 27226/57600 [4:45:48<5:10:36,  1.63it/s]
 47%|████▋     | 27227/57600 [4:45:49<5:21:50,  1.57it/s]
 47%|████▋     | 27228/57600 [4:45:50<5:16:36,  1.60it/s]
 47%|████▋     | 27229/57600 [4:45:50<5:09:33,  1.64it/s]
 47%|████▋     | 27230/57600 [4:45:51<5:01:17,  1.68it/s]
 47%|████▋     | 27231/57600 [4:45:51<5:02:30,  1.67it/s]
 47%|████▋     | 27232/57600 [4:45:52<5:02:14,  1.67it/s]
 47%|████▋     | 27233/57600 [4:45:52<5:03:07,  1.67it/s]
 47%|████▋     | 27234/57600 [4:45:53<5:06:44,  1.65it/s]
 47%|████▋     | 27235/57600 [4:45:54<5:08:31,  1.64it/s]
 47%|████▋     | 27236/57600 [4:45:54<5:09:21,  1.64it/s]
 47%|████▋     | 27237/57600 [4:45:55<5:14:59,  1.61it/s]
 47%|████▋     | 27238/57600 [4:45:56<5:21:23,  1.57it/s]
 47%|████▋     | 27239/57600 [4:45:56<5:27:33,  1.54it/s]
 47%|████▋     | 27240/57600 [4:45:57<5:16:58,  1.60it/s]
                                                         
{'loss': 1.2252, 'learning_rate': 5.760278745644599e-07, 'epoch': 300.66}

 47%|████▋     | 27240/57600 [4:45:57<5:16:58,  1.60it/s]
 47%|████▋     | 27241/57600 [4:45:58<5:28:28,  1.54it/s]
 47%|████▋     | 27242/57600 [4:45:58<5:35:33,  1.51it/s]
 47%|████▋     | 27243/57600 [4:45:59<5:25:18,  1.56it/s]
 47%|████▋     | 27244/57600 [4:45:59<5:13:51,  1.61it/s]
 47%|████▋     | 27245/57600 [4:46:00<5:15:37,  1.60it/s]
 47%|████▋     | 27246/57600 [4:46:01<5:08:56,  1.64it/s]
 47%|████▋     | 27247/57600 [4:46:01<5:05:37,  1.66it/s]
 47%|████▋     | 27248/57600 [4:46:02<4:59:33,  1.69it/s]
 47%|████▋     | 27249/57600 [4:46:02<5:12:47,  1.62it/s]
 47%|████▋     | 27250/57600 [4:46:03<5:29:10,  1.54it/s]
 47%|████▋     | 27251/57600 [4:46:04<5:26:09,  1.55it/s]
 47%|████▋     | 27252/57600 [4:46:05<5:35:39,  1.51it/s]
 47%|████▋     | 27253/57600 [4:46:05<5:21:05,  1.58it/s]
 47%|████▋     | 27254/57600 [4:46:06<5:24:15,  1.56it/s]
 47%|████▋     | 27255/57600 [4:46:06<5:29:45,  1.53it/s]
 47%|████▋     | 27256/57600 [4:46:07<5:23:31,  1.56it/s]
 47%|████▋     | 27257/57600 [4:46:08<5:19:05,  1.58it/s]
 47%|████▋     | 27258/57600 [4:46:08<5:22:52,  1.57it/s]
 47%|████▋     | 27259/57600 [4:46:09<5:18:19,  1.59it/s]
 47%|████▋     | 27260/57600 [4:46:09<5:06:56,  1.65it/s]
                                                         
{'loss': 1.1681, 'learning_rate': 5.757142857142857e-07, 'epoch': 300.88}

 47%|████▋     | 27260/57600 [4:46:09<5:06:56,  1.65it/s]
 47%|████▋     | 27261/57600 [4:46:10<5:06:37,  1.65it/s]
 47%|████▋     | 27262/57600 [4:46:11<5:08:55,  1.64it/s]
 47%|████▋     | 27263/57600 [4:46:11<5:09:40,  1.63it/s]
 47%|████▋     | 27264/57600 [4:46:12<5:11:10,  1.62it/s]
 47%|████▋     | 27265/57600 [4:46:13<5:05:17,  1.66it/s]
 47%|████▋     | 27266/57600 [4:46:13<5:02:21,  1.67it/s]
 47%|████▋     | 27267/57600 [4:46:14<5:01:12,  1.68it/s]
 47%|████▋     | 27268/57600 [4:46:14<5:02:48,  1.67it/s]
 47%|████▋     | 27269/57600 [4:46:15<4:59:19,  1.69it/s]
 47%|████▋     | 27270/57600 [4:46:15<4:57:44,  1.70it/s]
 47%|████▋     | 27271/57600 [4:46:16<5:14:45,  1.61it/s]
 47%|████▋     | 27272/57600 [4:46:17<5:11:33,  1.62it/s]
 47%|████▋     | 27273/57600 [4:46:17<5:14:28,  1.61it/s]
 47%|████▋     | 27274/57600 [4:46:18<5:13:15,  1.61it/s]
 47%|████▋     | 27275/57600 [4:46:19<5:24:21,  1.56it/s]
 47%|████▋     | 27276/57600 [4:46:19<5:29:05,  1.54it/s]
 47%|████▋     | 27277/57600 [4:46:20<5:20:02,  1.58it/s]
 47%|████▋     | 27278/57600 [4:46:21<5:16:39,  1.60it/s]
 47%|████▋     | 27279/57600 [4:46:21<5:12:47,  1.62it/s]
 47%|████▋     | 27280/57600 [4:46:22<5:09:37,  1.63it/s]
                                                         
{'loss': 1.2009, 'learning_rate': 5.754006968641115e-07, 'epoch': 301.1}

 47%|████▋     | 27280/57600 [4:46:22<5:09:37,  1.63it/s]
 47%|████▋     | 27281/57600 [4:46:22<5:10:11,  1.63it/s]
 47%|████▋     | 27282/57600 [4:46:23<5:25:00,  1.55it/s]
 47%|████▋     | 27283/57600 [4:46:24<5:23:54,  1.56it/s]
 47%|████▋     | 27284/57600 [4:46:24<5:16:30,  1.60it/s]
 47%|████▋     | 27285/57600 [4:46:25<5:21:20,  1.57it/s]
 47%|████▋     | 27286/57600 [4:46:26<5:22:12,  1.57it/s]
 47%|████▋     | 27287/57600 [4:46:26<5:13:27,  1.61it/s]
 47%|████▋     | 27288/57600 [4:46:27<5:16:15,  1.60it/s]
 47%|████▋     | 27289/57600 [4:46:27<5:04:23,  1.66it/s]
 47%|████▋     | 27290/57600 [4:46:28<5:01:44,  1.67it/s]
 47%|████▋     | 27291/57600 [4:46:29<5:04:31,  1.66it/s]
 47%|████▋     | 27292/57600 [4:46:29<5:11:58,  1.62it/s]
 47%|████▋     | 27293/57600 [4:46:30<5:19:02,  1.58it/s]
 47%|████▋     | 27294/57600 [4:46:30<5:08:54,  1.64it/s]
 47%|████▋     | 27295/57600 [4:46:31<5:02:26,  1.67it/s]
 47%|████▋     | 27296/57600 [4:46:32<4:59:33,  1.69it/s]
 47%|████▋     | 27297/57600 [4:46:32<5:13:13,  1.61it/s]
 47%|████▋     | 27298/57600 [4:46:33<5:04:03,  1.66it/s]
 47%|████▋     | 27299/57600 [4:46:33<4:58:49,  1.69it/s]
 47%|████▋     | 27300/57600 [4:46:34<4:56:31,  1.70it/s]
                                                         
{'loss': 1.2106, 'learning_rate': 5.750871080139372e-07, 'epoch': 301.32}

 47%|████▋     | 27300/57600 [4:46:34<4:56:31,  1.70it/s]
 47%|████▋     | 27301/57600 [4:46:35<5:07:03,  1.64it/s]
 47%|████▋     | 27302/57600 [4:46:35<5:01:43,  1.67it/s]
 47%|████▋     | 27303/57600 [4:46:36<5:15:16,  1.60it/s]
 47%|████▋     | 27304/57600 [4:46:37<5:18:05,  1.59it/s]
 47%|████▋     | 27305/57600 [4:46:37<5:19:37,  1.58it/s]
 47%|████▋     | 27306/57600 [4:46:38<5:13:01,  1.61it/s]
 47%|████▋     | 27307/57600 [4:46:38<5:04:35,  1.66it/s]
 47%|████▋     | 27308/57600 [4:46:39<5:16:55,  1.59it/s]
 47%|████▋     | 27309/57600 [4:46:40<5:15:11,  1.60it/s]
 47%|████▋     | 27310/57600 [4:46:40<5:17:00,  1.59it/s]
 47%|████▋     | 27311/57600 [4:46:41<5:17:37,  1.59it/s]
 47%|████▋     | 27312/57600 [4:46:42<5:24:34,  1.56it/s]
 47%|████▋     | 27313/57600 [4:46:42<5:17:16,  1.59it/s]
 47%|████▋     | 27314/57600 [4:46:43<5:12:09,  1.62it/s]
 47%|████▋     | 27315/57600 [4:46:43<5:08:21,  1.64it/s]
 47%|████▋     | 27316/57600 [4:46:44<5:09:11,  1.63it/s]
 47%|████▋     | 27317/57600 [4:46:45<5:10:50,  1.62it/s]
 47%|████▋     | 27318/57600 [4:46:45<5:08:34,  1.64it/s]
 47%|████▋     | 27319/57600 [4:46:46<5:14:55,  1.60it/s]
 47%|████▋     | 27320/57600 [4:46:47<5:12:00,  1.62it/s]
                                                         
{'loss': 1.1752, 'learning_rate': 5.74773519163763e-07, 'epoch': 301.55}

 47%|████▋     | 27320/57600 [4:46:47<5:12:00,  1.62it/s]
 47%|████▋     | 27321/57600 [4:46:47<5:03:11,  1.66it/s]
 47%|████▋     | 27322/57600 [4:46:48<5:09:17,  1.63it/s]
 47%|████▋     | 27323/57600 [4:46:48<5:23:16,  1.56it/s]
 47%|████▋     | 27324/57600 [4:46:49<5:24:24,  1.56it/s]
 47%|████▋     | 27325/57600 [4:46:50<5:23:24,  1.56it/s]
 47%|████▋     | 27326/57600 [4:46:50<5:11:11,  1.62it/s]
 47%|████▋     | 27327/57600 [4:46:51<5:07:56,  1.64it/s]
 47%|████▋     | 27328/57600 [4:46:51<5:04:59,  1.65it/s]
 47%|████▋     | 27329/57600 [4:46:52<5:06:09,  1.65it/s]
 47%|████▋     | 27330/57600 [4:46:53<5:14:07,  1.61it/s]
 47%|████▋     | 27331/57600 [4:46:53<5:20:33,  1.57it/s]
 47%|████▋     | 27332/57600 [4:46:54<5:09:08,  1.63it/s]
 47%|████▋     | 27333/57600 [4:46:55<5:08:25,  1.64it/s]
 47%|████▋     | 27334/57600 [4:46:55<5:04:25,  1.66it/s]
 47%|████▋     | 27335/57600 [4:46:56<5:13:08,  1.61it/s]
 47%|████▋     | 27336/57600 [4:46:56<5:06:56,  1.64it/s]
 47%|████▋     | 27337/57600 [4:46:57<5:15:03,  1.60it/s]
 47%|████▋     | 27338/57600 [4:46:58<5:11:06,  1.62it/s]
 47%|████▋     | 27339/57600 [4:46:58<5:09:18,  1.63it/s]
 47%|████▋     | 27340/57600 [4:46:59<5:11:11,  1.62it/s]
                                                         
{'loss': 1.1914, 'learning_rate': 5.744599303135888e-07, 'epoch': 301.77}

 47%|████▋     | 27340/57600 [4:46:59<5:11:11,  1.62it/s]
 47%|████▋     | 27341/57600 [4:47:00<5:15:59,  1.60it/s]
 47%|████▋     | 27342/57600 [4:47:00<5:18:10,  1.58it/s]
 47%|████▋     | 27343/57600 [4:47:01<5:25:50,  1.55it/s]
 47%|████▋     | 27344/57600 [4:47:01<5:19:01,  1.58it/s]
 47%|████▋     | 27345/57600 [4:47:02<5:14:00,  1.61it/s]
 47%|████▋     | 27346/57600 [4:47:03<5:16:42,  1.59it/s]
 47%|████▋     | 27347/57600 [4:47:03<5:14:32,  1.60it/s]
 47%|████▋     | 27348/57600 [4:47:04<5:13:50,  1.61it/s]
 47%|████▋     | 27349/57600 [4:47:04<5:05:44,  1.65it/s]
 47%|████▋     | 27350/57600 [4:47:05<5:01:33,  1.67it/s]
 47%|████▋     | 27351/57600 [4:47:06<5:02:53,  1.66it/s]
 47%|████▋     | 27352/57600 [4:47:06<5:07:54,  1.64it/s]
 47%|████▋     | 27353/57600 [4:47:07<5:21:57,  1.57it/s]
 47%|████▋     | 27354/57600 [4:47:08<5:22:59,  1.56it/s]
 47%|████▋     | 27355/57600 [4:47:08<5:20:19,  1.57it/s]
 47%|████▋     | 27356/57600 [4:47:09<5:14:19,  1.60it/s]
 47%|████▋     | 27357/57600 [4:47:10<5:25:03,  1.55it/s]
 47%|████▋     | 27358/57600 [4:47:10<5:18:12,  1.58it/s]
 47%|████▋     | 27359/57600 [4:47:11<5:12:21,  1.61it/s]
 48%|████▊     | 27360/57600 [4:47:11<5:16:06,  1.59it/s]
                                                         
{'loss': 1.2181, 'learning_rate': 5.741463414634147e-07, 'epoch': 301.99}

 48%|████▊     | 27360/57600 [4:47:11<5:16:06,  1.59it/s]
 48%|████▊     | 27361/57600 [4:47:12<5:10:45,  1.62it/s]
 48%|████▊     | 27362/57600 [4:47:13<5:39:28,  1.48it/s]
 48%|████▊     | 27363/57600 [4:47:13<5:39:34,  1.48it/s]
 48%|████▊     | 27364/57600 [4:47:14<5:38:35,  1.49it/s]
 48%|████▊     | 27365/57600 [4:47:15<5:36:40,  1.50it/s]
 48%|████▊     | 27366/57600 [4:47:15<5:30:50,  1.52it/s]
 48%|████▊     | 27367/57600 [4:47:16<5:31:40,  1.52it/s]
 48%|████▊     | 27368/57600 [4:47:17<5:24:53,  1.55it/s]
 48%|████▊     | 27369/57600 [4:47:17<5:16:19,  1.59it/s]
 48%|████▊     | 27370/57600 [4:47:18<5:17:12,  1.59it/s]
 48%|████▊     | 27371/57600 [4:47:19<5:16:18,  1.59it/s]
 48%|████▊     | 27372/57600 [4:47:19<5:01:36,  1.67it/s]
 48%|████▊     | 27373/57600 [4:47:20<5:16:32,  1.59it/s]
 48%|████▊     | 27374/57600 [4:47:20<5:14:29,  1.60it/s]
 48%|████▊     | 27375/57600 [4:47:21<5:19:33,  1.58it/s]
 48%|████▊     | 27376/57600 [4:47:22<5:15:55,  1.59it/s]
 48%|████▊     | 27377/57600 [4:47:22<5:11:15,  1.62it/s]
 48%|████▊     | 27378/57600 [4:47:23<5:06:14,  1.64it/s]
 48%|████▊     | 27379/57600 [4:47:23<4:57:23,  1.69it/s]
 48%|████▊     | 27380/57600 [4:47:24<4:59:40,  1.68it/s]
                                                         
{'loss': 1.1858, 'learning_rate': 5.738327526132403e-07, 'epoch': 302.21}

 48%|████▊     | 27380/57600 [4:47:24<4:59:40,  1.68it/s]
 48%|████▊     | 27381/57600 [4:47:25<5:01:11,  1.67it/s]
 48%|████▊     | 27382/57600 [4:47:25<5:10:59,  1.62it/s]
 48%|████▊     | 27383/57600 [4:47:26<5:25:45,  1.55it/s]
 48%|████▊     | 27384/57600 [4:47:27<5:17:38,  1.59it/s]
 48%|████▊     | 27385/57600 [4:47:27<5:12:12,  1.61it/s]
 48%|████▊     | 27386/57600 [4:47:28<5:16:12,  1.59it/s]
 48%|████▊     | 27387/57600 [4:47:29<5:34:49,  1.50it/s]
 48%|████▊     | 27388/57600 [4:47:29<5:21:54,  1.56it/s]
 48%|████▊     | 27389/57600 [4:47:30<5:14:35,  1.60it/s]
 48%|████▊     | 27390/57600 [4:47:30<5:06:09,  1.64it/s]
 48%|████▊     | 27391/57600 [4:47:31<4:58:06,  1.69it/s]
 48%|████▊     | 27392/57600 [4:47:31<4:57:14,  1.69it/s]
 48%|████▊     | 27393/57600 [4:47:32<5:00:20,  1.68it/s]
 48%|████▊     | 27394/57600 [4:47:33<5:07:22,  1.64it/s]
 48%|████▊     | 27395/57600 [4:47:33<5:03:53,  1.66it/s]
 48%|████▊     | 27396/57600 [4:47:34<5:09:00,  1.63it/s]
 48%|████▊     | 27397/57600 [4:47:35<5:05:08,  1.65it/s]
 48%|████▊     | 27398/57600 [4:47:35<5:09:53,  1.62it/s]
 48%|████▊     | 27399/57600 [4:47:36<5:07:23,  1.64it/s]
 48%|████▊     | 27400/57600 [4:47:36<5:06:17,  1.64it/s]
                                                         
{'loss': 1.2108, 'learning_rate': 5.735191637630662e-07, 'epoch': 302.43}

 48%|████▊     | 27400/57600 [4:47:36<5:06:17,  1.64it/s]
 48%|████▊     | 27401/57600 [4:47:37<5:04:16,  1.65it/s]
 48%|████▊     | 27402/57600 [4:47:37<4:51:56,  1.72it/s]
 48%|████▊     | 27403/57600 [4:47:38<5:07:32,  1.64it/s]
 48%|████▊     | 27404/57600 [4:47:39<5:09:36,  1.63it/s]
 48%|████▊     | 27405/57600 [4:47:39<5:01:10,  1.67it/s]
 48%|████▊     | 27406/57600 [4:47:40<4:54:39,  1.71it/s]
 48%|████▊     | 27407/57600 [4:47:41<4:59:13,  1.68it/s]
 48%|████▊     | 27408/57600 [4:47:41<5:08:01,  1.63it/s]
 48%|████▊     | 27409/57600 [4:47:42<5:06:31,  1.64it/s]
 48%|████▊     | 27410/57600 [4:47:42<4:56:27,  1.70it/s]
 48%|████▊     | 27411/57600 [4:47:43<5:08:56,  1.63it/s]
 48%|████▊     | 27412/57600 [4:47:44<5:21:31,  1.56it/s]
 48%|████▊     | 27413/57600 [4:47:44<5:21:45,  1.56it/s]
 48%|████▊     | 27414/57600 [4:47:45<5:16:27,  1.59it/s]
 48%|████▊     | 27415/57600 [4:47:46<5:25:44,  1.54it/s]
 48%|████▊     | 27416/57600 [4:47:46<5:30:42,  1.52it/s]
 48%|████▊     | 27417/57600 [4:47:47<5:21:33,  1.56it/s]
 48%|████▊     | 27418/57600 [4:47:48<5:23:30,  1.55it/s]
 48%|████▊     | 27419/57600 [4:47:48<5:21:57,  1.56it/s]
 48%|████▊     | 27420/57600 [4:47:49<5:11:22,  1.62it/s]
                                                         
{'loss': 1.2267, 'learning_rate': 5.732055749128921e-07, 'epoch': 302.65}

 48%|████▊     | 27420/57600 [4:47:49<5:11:22,  1.62it/s]
 48%|████▊     | 27421/57600 [4:47:49<5:06:36,  1.64it/s]
 48%|████▊     | 27422/57600 [4:47:50<5:02:53,  1.66it/s]
 48%|████▊     | 27423/57600 [4:47:50<4:54:35,  1.71it/s]
 48%|████▊     | 27424/57600 [4:47:51<4:58:22,  1.69it/s]
 48%|████▊     | 27425/57600 [4:47:52<5:02:02,  1.67it/s]
 48%|████▊     | 27426/57600 [4:47:52<5:08:01,  1.63it/s]
 48%|████▊     | 27427/57600 [4:47:53<5:07:17,  1.64it/s]
 48%|████▊     | 27428/57600 [4:47:54<5:03:37,  1.66it/s]
 48%|████▊     | 27429/57600 [4:47:54<5:08:02,  1.63it/s]
 48%|████▊     | 27430/57600 [4:47:55<5:22:42,  1.56it/s]
 48%|████▊     | 27431/57600 [4:47:56<5:21:14,  1.57it/s]
 48%|████▊     | 27432/57600 [4:47:56<5:21:23,  1.56it/s]
 48%|████▊     | 27433/57600 [4:47:57<5:16:03,  1.59it/s]
 48%|████▊     | 27434/57600 [4:47:57<5:16:05,  1.59it/s]
 48%|████▊     | 27435/57600 [4:47:58<5:09:17,  1.63it/s]
 48%|████▊     | 27436/57600 [4:47:59<5:20:27,  1.57it/s]
 48%|████▊     | 27437/57600 [4:47:59<5:23:26,  1.55it/s]
 48%|████▊     | 27438/57600 [4:48:00<5:21:27,  1.56it/s]
 48%|████▊     | 27439/57600 [4:48:01<5:24:19,  1.55it/s]
 48%|████▊     | 27440/57600 [4:48:01<5:15:11,  1.59it/s]
                                                         
{'loss': 1.1994, 'learning_rate': 5.728919860627177e-07, 'epoch': 302.87}

 48%|████▊     | 27440/57600 [4:48:01<5:15:11,  1.59it/s]
 48%|████▊     | 27441/57600 [4:48:02<5:04:26,  1.65it/s]
 48%|████▊     | 27442/57600 [4:48:02<4:59:31,  1.68it/s]
 48%|████▊     | 27443/57600 [4:48:03<4:58:01,  1.69it/s]
 48%|████▊     | 27444/57600 [4:48:04<5:01:03,  1.67it/s]
 48%|████▊     | 27445/57600 [4:48:04<5:12:46,  1.61it/s]
 48%|████▊     | 27446/57600 [4:48:05<5:09:54,  1.62it/s]
 48%|████▊     | 27447/57600 [4:48:05<5:06:13,  1.64it/s]
 48%|████▊     | 27448/57600 [4:48:06<5:01:07,  1.67it/s]
 48%|████▊     | 27449/57600 [4:48:07<4:55:57,  1.70it/s]
 48%|████▊     | 27450/57600 [4:48:07<5:13:20,  1.60it/s]
 48%|████▊     | 27451/57600 [4:48:08<5:05:37,  1.64it/s]
 48%|████▊     | 27452/57600 [4:48:09<5:22:22,  1.56it/s]
 48%|████▊     | 27453/57600 [4:48:09<5:23:58,  1.55it/s]
 48%|████▊     | 27454/57600 [4:48:10<5:27:01,  1.54it/s]
 48%|████▊     | 27455/57600 [4:48:10<5:19:40,  1.57it/s]
 48%|████▊     | 27456/57600 [4:48:11<5:25:45,  1.54it/s]
 48%|████▊     | 27457/57600 [4:48:12<5:13:17,  1.60it/s]
 48%|████▊     | 27458/57600 [4:48:12<5:11:47,  1.61it/s]
 48%|████▊     | 27459/57600 [4:48:13<5:13:08,  1.60it/s]
 48%|████▊     | 27460/57600 [4:48:13<5:02:57,  1.66it/s]
                                                         
{'loss': 1.2005, 'learning_rate': 5.725783972125435e-07, 'epoch': 303.09}

 48%|████▊     | 27460/57600 [4:48:13<5:02:57,  1.66it/s]
 48%|████▊     | 27461/57600 [4:48:14<5:04:17,  1.65it/s]
 48%|████▊     | 27462/57600 [4:48:15<5:01:35,  1.67it/s]
 48%|████▊     | 27463/57600 [4:48:15<5:01:45,  1.66it/s]
 48%|████▊     | 27464/57600 [4:48:16<5:06:30,  1.64it/s]
 48%|████▊     | 27465/57600 [4:48:17<5:04:35,  1.65it/s]
 48%|████▊     | 27466/57600 [4:48:17<4:59:19,  1.68it/s]
 48%|████▊     | 27467/57600 [4:48:18<4:58:25,  1.68it/s]
 48%|████▊     | 27468/57600 [4:48:18<4:57:18,  1.69it/s]
 48%|████▊     | 27469/57600 [4:48:19<5:09:46,  1.62it/s]
 48%|████▊     | 27470/57600 [4:48:20<5:05:19,  1.64it/s]
 48%|████▊     | 27471/57600 [4:48:20<4:59:59,  1.67it/s]
 48%|████▊     | 27472/57600 [4:48:21<5:06:41,  1.64it/s]
 48%|████▊     | 27473/57600 [4:48:21<5:11:42,  1.61it/s]
 48%|████▊     | 27474/57600 [4:48:22<5:04:29,  1.65it/s]
 48%|████▊     | 27475/57600 [4:48:23<5:05:56,  1.64it/s]
 48%|████▊     | 27476/57600 [4:48:23<5:04:00,  1.65it/s]
 48%|████▊     | 27477/57600 [4:48:24<5:00:21,  1.67it/s]
 48%|████▊     | 27478/57600 [4:48:24<5:04:16,  1.65it/s]
 48%|████▊     | 27479/57600 [4:48:25<5:03:53,  1.65it/s]
 48%|████▊     | 27480/57600 [4:48:26<5:04:43,  1.65it/s]
                                                         
{'loss': 1.1943, 'learning_rate': 5.722648083623693e-07, 'epoch': 303.31}

 48%|████▊     | 27480/57600 [4:48:26<5:04:43,  1.65it/s]
 48%|████▊     | 27481/57600 [4:48:26<5:04:57,  1.65it/s]
 48%|████▊     | 27482/57600 [4:48:27<5:14:29,  1.60it/s]
 48%|████▊     | 27483/57600 [4:48:27<5:09:35,  1.62it/s]
 48%|████▊     | 27484/57600 [4:48:28<5:13:12,  1.60it/s]
 48%|████▊     | 27485/57600 [4:48:29<5:12:40,  1.61it/s]
 48%|████▊     | 27486/57600 [4:48:29<5:10:06,  1.62it/s]
 48%|████▊     | 27487/57600 [4:48:30<5:11:27,  1.61it/s]
 48%|████▊     | 27488/57600 [4:48:31<5:08:31,  1.63it/s]
 48%|████▊     | 27489/57600 [4:48:31<5:13:11,  1.60it/s]
 48%|████▊     | 27490/57600 [4:48:32<5:22:22,  1.56it/s]
 48%|████▊     | 27491/57600 [4:48:33<5:19:29,  1.57it/s]
 48%|████▊     | 27492/57600 [4:48:33<5:09:29,  1.62it/s]
 48%|████▊     | 27493/57600 [4:48:34<5:12:14,  1.61it/s]
 48%|████▊     | 27494/57600 [4:48:34<5:21:40,  1.56it/s]
 48%|████▊     | 27495/57600 [4:48:35<5:12:17,  1.61it/s]
 48%|████▊     | 27496/57600 [4:48:36<5:07:08,  1.63it/s]
 48%|████▊     | 27497/57600 [4:48:36<5:06:56,  1.63it/s]
 48%|████▊     | 27498/57600 [4:48:37<4:59:39,  1.67it/s]
 48%|████▊     | 27499/57600 [4:48:37<5:04:23,  1.65it/s]
 48%|████▊     | 27500/57600 [4:48:38<5:15:46,  1.59it/s]
                                                         
{'loss': 1.1911, 'learning_rate': 5.719512195121951e-07, 'epoch': 303.53}

 48%|████▊     | 27500/57600 [4:48:38<5:15:46,  1.59it/s]
 48%|████▊     | 27501/57600 [4:48:39<5:16:08,  1.59it/s]
 48%|████▊     | 27502/57600 [4:48:39<5:10:05,  1.62it/s]
 48%|████▊     | 27503/57600 [4:48:40<5:04:53,  1.65it/s]
 48%|████▊     | 27504/57600 [4:48:41<5:10:16,  1.62it/s]
 48%|████▊     | 27505/57600 [4:48:41<5:15:10,  1.59it/s]
 48%|████▊     | 27506/57600 [4:48:42<5:15:31,  1.59it/s]
 48%|████▊     | 27507/57600 [4:48:42<5:12:01,  1.61it/s]
 48%|████▊     | 27508/57600 [4:48:43<5:10:37,  1.61it/s]
 48%|████▊     | 27509/57600 [4:48:44<5:04:35,  1.65it/s]
 48%|████▊     | 27510/57600 [4:48:44<5:12:57,  1.60it/s]
 48%|████▊     | 27511/57600 [4:48:45<5:13:48,  1.60it/s]
 48%|████▊     | 27512/57600 [4:48:45<5:11:20,  1.61it/s]
 48%|████▊     | 27513/57600 [4:48:46<5:10:15,  1.62it/s]
 48%|████▊     | 27514/57600 [4:48:47<5:04:43,  1.65it/s]
 48%|████▊     | 27515/57600 [4:48:47<5:05:49,  1.64it/s]
 48%|████▊     | 27516/57600 [4:48:48<5:14:12,  1.60it/s]
 48%|████▊     | 27517/57600 [4:48:49<5:20:26,  1.56it/s]
 48%|████▊     | 27518/57600 [4:48:49<5:19:57,  1.57it/s]
 48%|████▊     | 27519/57600 [4:48:50<5:11:24,  1.61it/s]
 48%|████▊     | 27520/57600 [4:48:50<5:12:51,  1.60it/s]
                                                         
{'loss': 1.1845, 'learning_rate': 5.716376306620208e-07, 'epoch': 303.75}

 48%|████▊     | 27520/57600 [4:48:50<5:12:51,  1.60it/s]
 48%|████▊     | 27521/57600 [4:48:51<5:19:00,  1.57it/s]
 48%|████▊     | 27522/57600 [4:48:52<5:12:53,  1.60it/s]
 48%|████▊     | 27523/57600 [4:48:52<5:15:25,  1.59it/s]
 48%|████▊     | 27524/57600 [4:48:53<5:24:04,  1.55it/s]
 48%|████▊     | 27525/57600 [4:48:54<5:20:35,  1.56it/s]
 48%|████▊     | 27526/57600 [4:48:54<5:08:00,  1.63it/s]
 48%|████▊     | 27527/57600 [4:48:55<5:08:30,  1.62it/s]
 48%|████▊     | 27528/57600 [4:48:56<5:12:27,  1.60it/s]
 48%|████▊     | 27529/57600 [4:48:56<5:06:59,  1.63it/s]
 48%|████▊     | 27530/57600 [4:48:57<5:05:31,  1.64it/s]
 48%|████▊     | 27531/57600 [4:48:57<5:10:36,  1.61it/s]
 48%|████▊     | 27532/57600 [4:48:58<5:07:17,  1.63it/s]
 48%|████▊     | 27533/57600 [4:48:59<5:04:51,  1.64it/s]
 48%|████▊     | 27534/57600 [4:48:59<5:09:04,  1.62it/s]
 48%|████▊     | 27535/57600 [4:49:00<5:13:55,  1.60it/s]
 48%|████▊     | 27536/57600 [4:49:00<5:16:20,  1.58it/s]
 48%|████▊     | 27537/57600 [4:49:01<5:16:01,  1.59it/s]
 48%|████▊     | 27538/57600 [4:49:02<5:13:36,  1.60it/s]
 48%|████▊     | 27539/57600 [4:49:02<5:20:50,  1.56it/s]
 48%|████▊     | 27540/57600 [4:49:03<5:25:07,  1.54it/s]
                                                         
{'loss': 1.1822, 'learning_rate': 5.713240418118467e-07, 'epoch': 303.97}

 48%|████▊     | 27540/57600 [4:49:03<5:25:07,  1.54it/s]
 48%|████▊     | 27541/57600 [4:49:04<5:15:53,  1.59it/s]
 48%|████▊     | 27542/57600 [4:49:04<5:18:40,  1.57it/s]
 48%|████▊     | 27543/57600 [4:49:05<5:27:46,  1.53it/s]
 48%|████▊     | 27544/57600 [4:49:06<5:20:50,  1.56it/s]
 48%|████▊     | 27545/57600 [4:49:06<5:23:44,  1.55it/s]
 48%|████▊     | 27546/57600 [4:49:07<5:24:14,  1.54it/s]
 48%|████▊     | 27547/57600 [4:49:07<5:14:05,  1.59it/s]
 48%|████▊     | 27548/57600 [4:49:08<5:15:14,  1.59it/s]
 48%|████▊     | 27549/57600 [4:49:09<5:02:40,  1.65it/s]
 48%|████▊     | 27550/57600 [4:49:09<4:59:07,  1.67it/s]
 48%|████▊     | 27551/57600 [4:49:10<4:50:31,  1.72it/s]
 48%|████▊     | 27552/57600 [4:49:10<4:47:32,  1.74it/s]
 48%|████▊     | 27553/57600 [4:49:11<4:56:00,  1.69it/s]
 48%|████▊     | 27554/57600 [4:49:12<4:58:04,  1.68it/s]
 48%|████▊     | 27555/57600 [4:49:12<5:09:41,  1.62it/s]
 48%|████▊     | 27556/57600 [4:49:13<5:10:13,  1.61it/s]
 48%|████▊     | 27557/57600 [4:49:13<5:07:34,  1.63it/s]
 48%|████▊     | 27558/57600 [4:49:14<5:12:13,  1.60it/s]
 48%|████▊     | 27559/57600 [4:49:15<5:07:39,  1.63it/s]
 48%|████▊     | 27560/57600 [4:49:15<5:18:35,  1.57it/s]
                                                         
{'loss': 1.2154, 'learning_rate': 5.710104529616724e-07, 'epoch': 304.19}

 48%|████▊     | 27560/57600 [4:49:15<5:18:35,  1.57it/s]
 48%|████▊     | 27561/57600 [4:49:16<5:23:46,  1.55it/s]
 48%|████▊     | 27562/57600 [4:49:17<5:20:47,  1.56it/s]
 48%|████▊     | 27563/57600 [4:49:17<5:19:36,  1.57it/s]
 48%|████▊     | 27564/57600 [4:49:18<5:18:15,  1.57it/s]
 48%|████▊     | 27565/57600 [4:49:19<5:08:38,  1.62it/s]
 48%|████▊     | 27566/57600 [4:49:19<5:17:52,  1.57it/s]
 48%|████▊     | 27567/57600 [4:49:20<5:12:58,  1.60it/s]
 48%|████▊     | 27568/57600 [4:49:21<5:21:56,  1.55it/s]
 48%|████▊     | 27569/57600 [4:49:21<5:23:49,  1.55it/s]
 48%|████▊     | 27570/57600 [4:49:22<5:25:41,  1.54it/s]
 48%|████▊     | 27571/57600 [4:49:22<5:28:49,  1.52it/s]
 48%|████▊     | 27572/57600 [4:49:23<5:14:42,  1.59it/s]
 48%|████▊     | 27573/57600 [4:49:24<5:14:32,  1.59it/s]
 48%|████▊     | 27574/57600 [4:49:24<5:17:15,  1.58it/s]
 48%|████▊     | 27575/57600 [4:49:25<5:15:16,  1.59it/s]
 48%|████▊     | 27576/57600 [4:49:26<5:11:42,  1.61it/s]
 48%|████▊     | 27577/57600 [4:49:26<5:22:50,  1.55it/s]
 48%|████▊     | 27578/57600 [4:49:27<5:22:59,  1.55it/s]
 48%|████▊     | 27579/57600 [4:49:27<5:14:07,  1.59it/s]
 48%|████▊     | 27580/57600 [4:49:28<5:14:50,  1.59it/s]
                                                         
{'loss': 1.1526, 'learning_rate': 5.706968641114983e-07, 'epoch': 304.42}

 48%|████▊     | 27580/57600 [4:49:28<5:14:50,  1.59it/s]
 48%|████▊     | 27581/57600 [4:49:29<5:13:11,  1.60it/s]
 48%|████▊     | 27582/57600 [4:49:29<5:07:37,  1.63it/s]
 48%|████▊     | 27583/57600 [4:49:30<5:12:29,  1.60it/s]
 48%|████▊     | 27584/57600 [4:49:31<5:03:30,  1.65it/s]
 48%|████▊     | 27585/57600 [4:49:31<5:06:09,  1.63it/s]
 48%|████▊     | 27586/57600 [4:49:32<5:15:19,  1.59it/s]
 48%|████▊     | 27587/57600 [4:49:32<5:11:34,  1.61it/s]
 48%|████▊     | 27588/57600 [4:49:33<5:36:24,  1.49it/s]
 48%|████▊     | 27589/57600 [4:49:34<5:27:05,  1.53it/s]
 48%|████▊     | 27590/57600 [4:49:34<5:24:39,  1.54it/s]
 48%|████▊     | 27591/57600 [4:49:35<5:16:28,  1.58it/s]
 48%|████▊     | 27592/57600 [4:49:36<5:16:48,  1.58it/s]
 48%|████▊     | 27593/57600 [4:49:36<5:18:06,  1.57it/s]
 48%|████▊     | 27594/57600 [4:49:37<5:18:49,  1.57it/s]
 48%|████▊     | 27595/57600 [4:49:38<5:12:16,  1.60it/s]
 48%|████▊     | 27596/57600 [4:49:38<5:09:21,  1.62it/s]
 48%|████▊     | 27597/57600 [4:49:39<5:01:42,  1.66it/s]
 48%|████▊     | 27598/57600 [4:49:39<4:55:47,  1.69it/s]
 48%|████▊     | 27599/57600 [4:49:40<5:09:11,  1.62it/s]
 48%|████▊     | 27600/57600 [4:49:41<5:14:27,  1.59it/s]
                                                         
{'loss': 1.1992, 'learning_rate': 5.703832752613239e-07, 'epoch': 304.64}

 48%|████▊     | 27600/57600 [4:49:41<5:14:27,  1.59it/s]
 48%|████▊     | 27601/57600 [4:49:41<5:19:38,  1.56it/s]
 48%|████▊     | 27602/57600 [4:49:42<5:20:28,  1.56it/s]
 48%|████▊     | 27603/57600 [4:49:43<5:14:12,  1.59it/s]
 48%|████▊     | 27604/57600 [4:49:43<5:13:44,  1.59it/s]
 48%|████▊     | 27605/57600 [4:49:44<5:08:21,  1.62it/s]
 48%|████▊     | 27606/57600 [4:49:44<5:13:58,  1.59it/s]
 48%|████▊     | 27607/57600 [4:49:45<5:03:43,  1.65it/s]
 48%|████▊     | 27608/57600 [4:49:46<5:01:50,  1.66it/s]
 48%|████▊     | 27609/57600 [4:49:46<5:02:01,  1.66it/s]
 48%|████▊     | 27610/57600 [4:49:47<5:08:56,  1.62it/s]
 48%|████▊     | 27611/57600 [4:49:47<5:09:58,  1.61it/s]
 48%|████▊     | 27612/57600 [4:49:48<5:10:14,  1.61it/s]
 48%|████▊     | 27613/57600 [4:49:49<5:04:22,  1.64it/s]
 48%|████▊     | 27614/57600 [4:49:49<5:02:50,  1.65it/s]
 48%|████▊     | 27615/57600 [4:49:50<5:12:53,  1.60it/s]
 48%|████▊     | 27616/57600 [4:49:51<5:10:11,  1.61it/s]
 48%|████▊     | 27617/57600 [4:49:51<5:09:02,  1.62it/s]
 48%|████▊     | 27618/57600 [4:49:52<4:59:32,  1.67it/s]
 48%|████▊     | 27619/57600 [4:49:52<4:55:29,  1.69it/s]
 48%|████▊     | 27620/57600 [4:49:53<4:51:00,  1.72it/s]
                                                         
{'loss': 1.1996, 'learning_rate': 5.700696864111499e-07, 'epoch': 304.86}

 48%|████▊     | 27620/57600 [4:49:53<4:51:00,  1.72it/s]
 48%|████▊     | 27621/57600 [4:49:54<5:09:46,  1.61it/s]
 48%|████▊     | 27622/57600 [4:49:54<5:01:52,  1.66it/s]
 48%|████▊     | 27623/57600 [4:49:55<4:52:36,  1.71it/s]
 48%|████▊     | 27624/57600 [4:49:55<4:47:56,  1.74it/s]
 48%|████▊     | 27625/57600 [4:49:56<4:57:20,  1.68it/s]
 48%|████▊     | 27626/57600 [4:49:56<4:59:13,  1.67it/s]
 48%|████▊     | 27627/57600 [4:49:57<5:04:36,  1.64it/s]
 48%|████▊     | 27628/57600 [4:49:58<4:55:54,  1.69it/s]
 48%|████▊     | 27629/57600 [4:49:58<5:03:20,  1.65it/s]
 48%|████▊     | 27630/57600 [4:49:59<5:07:35,  1.62it/s]
 48%|████▊     | 27631/57600 [4:50:00<5:04:00,  1.64it/s]
 48%|████▊     | 27632/57600 [4:50:00<5:06:12,  1.63it/s]
 48%|████▊     | 27633/57600 [4:50:01<5:01:29,  1.66it/s]
 48%|████▊     | 27634/57600 [4:50:01<5:13:55,  1.59it/s]
 48%|████▊     | 27635/57600 [4:50:02<5:09:04,  1.62it/s]
 48%|████▊     | 27636/57600 [4:50:03<5:05:31,  1.63it/s]
 48%|████▊     | 27637/57600 [4:50:03<5:07:01,  1.63it/s]
 48%|████▊     | 27638/57600 [4:50:04<5:11:40,  1.60it/s]
 48%|████▊     | 27639/57600 [4:50:05<5:12:39,  1.60it/s]
 48%|████▊     | 27640/57600 [4:50:05<5:10:28,  1.61it/s]
                                                         
{'loss': 1.2453, 'learning_rate': 5.697560975609756e-07, 'epoch': 305.08}

 48%|████▊     | 27640/57600 [4:50:05<5:10:28,  1.61it/s]
 48%|████▊     | 27641/57600 [4:50:06<5:16:15,  1.58it/s]
 48%|████▊     | 27642/57600 [4:50:06<5:14:20,  1.59it/s]
 48%|████▊     | 27643/57600 [4:50:07<5:15:02,  1.58it/s]
 48%|████▊     | 27644/57600 [4:50:08<5:07:14,  1.62it/s]
 48%|████▊     | 27645/57600 [4:50:08<5:18:12,  1.57it/s]
 48%|████▊     | 27646/57600 [4:50:09<5:34:23,  1.49it/s]
 48%|████▊     | 27647/57600 [4:50:10<5:31:07,  1.51it/s]
 48%|████▊     | 27648/57600 [4:50:10<5:25:32,  1.53it/s]
 48%|████▊     | 27649/57600 [4:50:11<5:11:16,  1.60it/s]
 48%|████▊     | 27650/57600 [4:50:11<5:06:21,  1.63it/s]
 48%|████▊     | 27651/57600 [4:50:12<5:02:31,  1.65it/s]
 48%|████▊     | 27652/57600 [4:50:13<4:56:41,  1.68it/s]
 48%|████▊     | 27653/57600 [4:50:13<4:57:58,  1.68it/s]
 48%|████▊     | 27654/57600 [4:50:14<4:52:02,  1.71it/s]
 48%|████▊     | 27655/57600 [4:50:14<5:01:07,  1.66it/s]
 48%|████▊     | 27656/57600 [4:50:15<5:05:43,  1.63it/s]
 48%|████▊     | 27657/57600 [4:50:16<5:09:58,  1.61it/s]
 48%|████▊     | 27658/57600 [4:50:16<5:12:34,  1.60it/s]
 48%|████▊     | 27659/57600 [4:50:17<5:18:19,  1.57it/s]
 48%|████▊     | 27660/57600 [4:50:18<5:13:43,  1.59it/s]
                                                         
{'loss': 1.1897, 'learning_rate': 5.694425087108013e-07, 'epoch': 305.3}

 48%|████▊     | 27660/57600 [4:50:18<5:13:43,  1.59it/s]
 48%|████▊     | 27661/57600 [4:50:18<5:12:55,  1.59it/s]
 48%|████▊     | 27662/57600 [4:50:19<5:14:09,  1.59it/s]
 48%|████▊     | 27663/57600 [4:50:20<5:15:32,  1.58it/s]
 48%|████▊     | 27664/57600 [4:50:20<5:03:56,  1.64it/s]
 48%|████▊     | 27665/57600 [4:50:21<5:11:37,  1.60it/s]
 48%|████▊     | 27666/57600 [4:50:21<5:15:02,  1.58it/s]
 48%|████▊     | 27667/57600 [4:50:22<5:13:28,  1.59it/s]
 48%|████▊     | 27668/57600 [4:50:23<5:13:20,  1.59it/s]
 48%|████▊     | 27669/57600 [4:50:23<5:28:37,  1.52it/s]
 48%|████▊     | 27670/57600 [4:50:24<5:15:16,  1.58it/s]
 48%|████▊     | 27671/57600 [4:50:25<5:09:38,  1.61it/s]
 48%|████▊     | 27672/57600 [4:50:25<5:09:40,  1.61it/s]
 48%|████▊     | 27673/57600 [4:50:26<5:06:02,  1.63it/s]
 48%|████▊     | 27674/57600 [4:50:26<5:06:28,  1.63it/s]
 48%|████▊     | 27675/57600 [4:50:27<5:06:33,  1.63it/s]
 48%|████▊     | 27676/57600 [4:50:28<5:05:46,  1.63it/s]
 48%|████▊     | 27677/57600 [4:50:28<5:11:46,  1.60it/s]
 48%|████▊     | 27678/57600 [4:50:29<5:10:15,  1.61it/s]
 48%|████▊     | 27679/57600 [4:50:29<5:09:00,  1.61it/s]
 48%|████▊     | 27680/57600 [4:50:30<5:07:28,  1.62it/s]
                                                         
{'loss': 1.1674, 'learning_rate': 5.691289198606271e-07, 'epoch': 305.52}

 48%|████▊     | 27680/57600 [4:50:30<5:07:28,  1.62it/s]
 48%|████▊     | 27681/57600 [4:50:31<5:02:11,  1.65it/s]
 48%|████▊     | 27682/57600 [4:50:31<4:57:15,  1.68it/s]
 48%|████▊     | 27683/57600 [4:50:32<4:57:01,  1.68it/s]
 48%|████▊     | 27684/57600 [4:50:33<5:16:20,  1.58it/s]
 48%|████▊     | 27685/57600 [4:50:33<5:07:38,  1.62it/s]
 48%|████▊     | 27686/57600 [4:50:34<5:05:49,  1.63it/s]
 48%|████▊     | 27687/57600 [4:50:34<5:00:30,  1.66it/s]
 48%|████▊     | 27688/57600 [4:50:35<5:03:34,  1.64it/s]
 48%|████▊     | 27689/57600 [4:50:36<5:04:26,  1.64it/s]
 48%|████▊     | 27690/57600 [4:50:36<5:11:05,  1.60it/s]
 48%|████▊     | 27691/57600 [4:50:37<5:01:52,  1.65it/s]
 48%|████▊     | 27692/57600 [4:50:37<5:09:31,  1.61it/s]
 48%|████▊     | 27693/57600 [4:50:38<5:11:21,  1.60it/s]
 48%|████▊     | 27694/57600 [4:50:39<5:06:01,  1.63it/s]
 48%|████▊     | 27695/57600 [4:50:39<5:14:35,  1.58it/s]
 48%|████▊     | 27696/57600 [4:50:40<5:06:08,  1.63it/s]
 48%|████▊     | 27697/57600 [4:50:41<5:10:01,  1.61it/s]
 48%|████▊     | 27698/57600 [4:50:41<5:10:16,  1.61it/s]
 48%|████▊     | 27699/57600 [4:50:42<5:08:54,  1.61it/s]
 48%|████▊     | 27700/57600 [4:50:42<5:10:39,  1.60it/s]
                                                         
{'loss': 1.1978, 'learning_rate': 5.68815331010453e-07, 'epoch': 305.74}

 48%|████▊     | 27700/57600 [4:50:42<5:10:39,  1.60it/s]
 48%|████▊     | 27701/57600 [4:50:43<5:09:51,  1.61it/s]
 48%|████▊     | 27702/57600 [4:50:44<5:03:01,  1.64it/s]
 48%|████▊     | 27703/57600 [4:50:44<4:55:51,  1.68it/s]
 48%|████▊     | 27704/57600 [4:50:45<5:00:08,  1.66it/s]
 48%|████▊     | 27705/57600 [4:50:45<5:09:44,  1.61it/s]
 48%|████▊     | 27706/57600 [4:50:46<5:15:35,  1.58it/s]
 48%|████▊     | 27707/57600 [4:50:47<5:05:48,  1.63it/s]
 48%|████▊     | 27708/57600 [4:50:47<5:19:04,  1.56it/s]
 48%|████▊     | 27709/57600 [4:50:48<5:13:41,  1.59it/s]
 48%|████▊     | 27710/57600 [4:50:49<5:13:34,  1.59it/s]
 48%|████▊     | 27711/57600 [4:50:49<5:13:21,  1.59it/s]
 48%|████▊     | 27712/57600 [4:50:50<5:05:25,  1.63it/s]
 48%|████▊     | 27713/57600 [4:50:50<5:07:57,  1.62it/s]
 48%|████▊     | 27714/57600 [4:50:51<5:02:17,  1.65it/s]
 48%|████▊     | 27715/57600 [4:50:52<5:04:45,  1.63it/s]
 48%|████▊     | 27716/57600 [4:50:52<5:02:47,  1.64it/s]
 48%|████▊     | 27717/57600 [4:50:53<5:01:23,  1.65it/s]
 48%|████▊     | 27718/57600 [4:50:53<5:04:49,  1.63it/s]
 48%|████▊     | 27719/57600 [4:50:54<5:04:33,  1.64it/s]
 48%|████▊     | 27720/57600 [4:50:55<4:59:59,  1.66it/s]
                                                         
{'loss': 1.2132, 'learning_rate': 5.685017421602787e-07, 'epoch': 305.96}

 48%|████▊     | 27720/57600 [4:50:55<4:59:59,  1.66it/s]
 48%|████▊     | 27721/57600 [4:50:55<5:08:34,  1.61it/s]
 48%|████▊     | 27722/57600 [4:50:56<5:02:57,  1.64it/s]
 48%|████▊     | 27723/57600 [4:50:57<5:12:00,  1.60it/s]
 48%|████▊     | 27724/57600 [4:50:57<5:22:47,  1.54it/s]
 48%|████▊     | 27725/57600 [4:50:58<5:30:36,  1.51it/s]
 48%|████▊     | 27726/57600 [4:50:59<5:35:12,  1.49it/s]
 48%|████▊     | 27727/57600 [4:50:59<5:30:41,  1.51it/s]
 48%|████▊     | 27728/57600 [4:51:00<5:30:35,  1.51it/s]
 48%|████▊     | 27729/57600 [4:51:01<5:25:05,  1.53it/s]
 48%|████▊     | 27730/57600 [4:51:01<5:14:25,  1.58it/s]
 48%|████▊     | 27731/57600 [4:51:02<5:26:06,  1.53it/s]
 48%|████▊     | 27732/57600 [4:51:03<5:38:16,  1.47it/s]
 48%|████▊     | 27733/57600 [4:51:03<5:25:52,  1.53it/s]
 48%|████▊     | 27734/57600 [4:51:04<5:26:42,  1.52it/s]
 48%|████▊     | 27735/57600 [4:51:04<5:11:00,  1.60it/s]
 48%|████▊     | 27736/57600 [4:51:05<5:01:36,  1.65it/s]
 48%|████▊     | 27737/57600 [4:51:06<5:08:11,  1.61it/s]
 48%|████▊     | 27738/57600 [4:51:06<5:08:52,  1.61it/s]
 48%|████▊     | 27739/57600 [4:51:07<5:12:42,  1.59it/s]
 48%|████▊     | 27740/57600 [4:51:08<5:10:36,  1.60it/s]
                                                         
{'loss': 1.1438, 'learning_rate': 5.681881533101045e-07, 'epoch': 306.18}

 48%|████▊     | 27740/57600 [4:51:08<5:10:36,  1.60it/s]
 48%|████▊     | 27741/57600 [4:51:08<5:12:32,  1.59it/s]
 48%|████▊     | 27742/57600 [4:51:09<5:06:54,  1.62it/s]
 48%|████▊     | 27743/57600 [4:51:09<5:13:00,  1.59it/s]
 48%|████▊     | 27744/57600 [4:51:10<5:12:14,  1.59it/s]
 48%|████▊     | 27745/57600 [4:51:11<5:08:42,  1.61it/s]
 48%|████▊     | 27746/57600 [4:51:11<5:07:09,  1.62it/s]
 48%|████▊     | 27747/57600 [4:51:12<5:05:25,  1.63it/s]
 48%|████▊     | 27748/57600 [4:51:12<5:05:34,  1.63it/s]
 48%|████▊     | 27749/57600 [4:51:13<5:11:18,  1.60it/s]
 48%|████▊     | 27750/57600 [4:51:14<5:07:00,  1.62it/s]
 48%|████▊     | 27751/57600 [4:51:14<4:59:33,  1.66it/s]
 48%|████▊     | 27752/57600 [4:51:15<4:56:30,  1.68it/s]
 48%|████▊     | 27753/57600 [4:51:16<5:09:12,  1.61it/s]
 48%|████▊     | 27754/57600 [4:51:16<5:06:57,  1.62it/s]
 48%|████▊     | 27755/57600 [4:51:17<5:03:42,  1.64it/s]
 48%|████▊     | 27756/57600 [4:51:17<5:07:34,  1.62it/s]
 48%|████▊     | 27757/57600 [4:51:18<5:02:19,  1.65it/s]
 48%|████▊     | 27758/57600 [4:51:19<5:06:08,  1.62it/s]
 48%|████▊     | 27759/57600 [4:51:19<5:04:36,  1.63it/s]
 48%|████▊     | 27760/57600 [4:51:20<5:01:59,  1.65it/s]
                                                         
{'loss': 1.2112, 'learning_rate': 5.678745644599304e-07, 'epoch': 306.4}

 48%|████▊     | 27760/57600 [4:51:20<5:01:59,  1.65it/s]
 48%|████▊     | 27761/57600 [4:51:20<5:04:49,  1.63it/s]
 48%|████▊     | 27762/57600 [4:51:21<5:12:35,  1.59it/s]
 48%|████▊     | 27763/57600 [4:51:22<5:06:38,  1.62it/s]
 48%|████▊     | 27764/57600 [4:51:22<5:00:12,  1.66it/s]
 48%|████▊     | 27765/57600 [4:51:23<4:58:58,  1.66it/s]
 48%|████▊     | 27766/57600 [4:51:24<5:11:50,  1.59it/s]
 48%|████▊     | 27767/57600 [4:51:24<5:20:03,  1.55it/s]
 48%|████▊     | 27768/57600 [4:51:25<5:11:01,  1.60it/s]
 48%|████▊     | 27769/57600 [4:51:25<5:13:46,  1.58it/s]
 48%|████▊     | 27770/57600 [4:51:26<5:16:49,  1.57it/s]
 48%|████▊     | 27771/57600 [4:51:27<5:13:41,  1.58it/s]
 48%|████▊     | 27772/57600 [4:51:27<5:16:58,  1.57it/s]
 48%|████▊     | 27773/57600 [4:51:28<5:22:32,  1.54it/s]
 48%|████▊     | 27774/57600 [4:51:29<5:08:46,  1.61it/s]
 48%|████▊     | 27775/57600 [4:51:29<4:59:28,  1.66it/s]
 48%|████▊     | 27776/57600 [4:51:30<4:58:55,  1.66it/s]
 48%|████▊     | 27777/57600 [4:51:30<5:02:50,  1.64it/s]
 48%|████▊     | 27778/57600 [4:51:31<4:53:52,  1.69it/s]
 48%|████▊     | 27779/57600 [4:51:32<5:02:59,  1.64it/s]
 48%|████▊     | 27780/57600 [4:51:32<5:03:49,  1.64it/s]
                                                         
{'loss': 1.2042, 'learning_rate': 5.67560975609756e-07, 'epoch': 306.62}

 48%|████▊     | 27780/57600 [4:51:32<5:03:49,  1.64it/s]
 48%|████▊     | 27781/57600 [4:51:33<5:01:29,  1.65it/s]
 48%|████▊     | 27782/57600 [4:51:33<5:08:44,  1.61it/s]
 48%|████▊     | 27783/57600 [4:51:34<5:05:09,  1.63it/s]
 48%|████▊     | 27784/57600 [4:51:35<5:09:27,  1.61it/s]
 48%|████▊     | 27785/57600 [4:51:35<5:15:49,  1.57it/s]
 48%|████▊     | 27786/57600 [4:51:36<5:08:13,  1.61it/s]
 48%|████▊     | 27787/57600 [4:51:37<5:15:16,  1.58it/s]
 48%|████▊     | 27788/57600 [4:51:37<5:16:01,  1.57it/s]
 48%|████▊     | 27789/57600 [4:51:38<5:13:40,  1.58it/s]
 48%|████▊     | 27790/57600 [4:51:38<5:06:02,  1.62it/s]
 48%|████▊     | 27791/57600 [4:51:39<4:58:08,  1.67it/s]
 48%|████▊     | 27792/57600 [4:51:40<5:04:37,  1.63it/s]
 48%|████▊     | 27793/57600 [4:51:40<5:08:47,  1.61it/s]
 48%|████▊     | 27794/57600 [4:51:41<5:21:23,  1.55it/s]
 48%|████▊     | 27795/57600 [4:51:42<5:20:16,  1.55it/s]
 48%|████▊     | 27796/57600 [4:51:42<5:15:48,  1.57it/s]
 48%|████▊     | 27797/57600 [4:51:43<5:18:46,  1.56it/s]
 48%|████▊     | 27798/57600 [4:51:43<5:04:30,  1.63it/s]
 48%|████▊     | 27799/57600 [4:51:44<5:11:52,  1.59it/s]
 48%|████▊     | 27800/57600 [4:51:45<5:07:21,  1.62it/s]
                                                         
{'loss': 1.1631, 'learning_rate': 5.672473867595819e-07, 'epoch': 306.84}

 48%|████▊     | 27800/57600 [4:51:45<5:07:21,  1.62it/s]
 48%|████▊     | 27801/57600 [4:51:45<5:01:23,  1.65it/s]
 48%|████▊     | 27802/57600 [4:51:46<5:00:00,  1.66it/s]
 48%|████▊     | 27803/57600 [4:51:46<4:56:22,  1.68it/s]
 48%|████▊     | 27804/57600 [4:51:47<5:06:41,  1.62it/s]
 48%|████▊     | 27805/57600 [4:51:48<5:02:46,  1.64it/s]
 48%|████▊     | 27806/57600 [4:51:48<4:53:27,  1.69it/s]
 48%|████▊     | 27807/57600 [4:51:49<5:01:43,  1.65it/s]
 48%|████▊     | 27808/57600 [4:51:50<5:04:07,  1.63it/s]
 48%|████▊     | 27809/57600 [4:51:50<5:14:41,  1.58it/s]
 48%|████▊     | 27810/57600 [4:51:51<5:11:13,  1.60it/s]
 48%|████▊     | 27811/57600 [4:51:51<5:04:23,  1.63it/s]
 48%|████▊     | 27812/57600 [4:51:52<5:06:23,  1.62it/s]
 48%|████▊     | 27813/57600 [4:51:53<4:58:44,  1.66it/s]
 48%|████▊     | 27814/57600 [4:51:53<5:03:14,  1.64it/s]
 48%|████▊     | 27815/57600 [4:51:54<5:22:58,  1.54it/s]
 48%|████▊     | 27816/57600 [4:51:55<5:27:08,  1.52it/s]
 48%|████▊     | 27817/57600 [4:51:55<5:20:04,  1.55it/s]
 48%|████▊     | 27818/57600 [4:51:56<5:15:20,  1.57it/s]
 48%|████▊     | 27819/57600 [4:51:56<5:03:40,  1.63it/s]
 48%|████▊     | 27820/57600 [4:51:57<4:51:34,  1.70it/s]
                                                         
{'loss': 1.2175, 'learning_rate': 5.669337979094076e-07, 'epoch': 307.06}

 48%|████▊     | 27820/57600 [4:51:57<4:51:34,  1.70it/s]
 48%|████▊     | 27821/57600 [4:51:58<5:00:10,  1.65it/s]
 48%|████▊     | 27822/57600 [4:51:58<5:10:01,  1.60it/s]
 48%|████▊     | 27823/57600 [4:51:59<5:06:09,  1.62it/s]
 48%|████▊     | 27824/57600 [4:52:00<5:09:49,  1.60it/s]
 48%|████▊     | 27825/57600 [4:52:00<5:08:41,  1.61it/s]
 48%|████▊     | 27826/57600 [4:52:01<5:03:33,  1.63it/s]
 48%|████▊     | 27827/57600 [4:52:01<5:05:42,  1.62it/s]
 48%|████▊     | 27828/57600 [4:52:02<5:09:27,  1.60it/s]
 48%|████▊     | 27829/57600 [4:52:03<5:03:35,  1.63it/s]
 48%|████▊     | 27830/57600 [4:52:03<5:09:02,  1.61it/s]
 48%|████▊     | 27831/57600 [4:52:04<5:06:16,  1.62it/s]
 48%|████▊     | 27832/57600 [4:52:04<4:59:57,  1.65it/s]
 48%|████▊     | 27833/57600 [4:52:05<5:08:01,  1.61it/s]
 48%|████▊     | 27834/57600 [4:52:06<5:20:34,  1.55it/s]
 48%|████▊     | 27835/57600 [4:52:06<5:15:57,  1.57it/s]
 48%|████▊     | 27836/57600 [4:52:07<5:31:09,  1.50it/s]
 48%|████▊     | 27837/57600 [4:52:08<5:27:46,  1.51it/s]
 48%|████▊     | 27838/57600 [4:52:08<5:17:54,  1.56it/s]
 48%|████▊     | 27839/57600 [4:52:09<5:13:05,  1.58it/s]
 48%|████▊     | 27840/57600 [4:52:10<5:06:12,  1.62it/s]
                                                         
{'loss': 1.1607, 'learning_rate': 5.666202090592335e-07, 'epoch': 307.28}

 48%|████▊     | 27840/57600 [4:52:10<5:06:12,  1.62it/s]
 48%|████▊     | 27841/57600 [4:52:10<5:16:32,  1.57it/s]
 48%|████▊     | 27842/57600 [4:52:11<5:07:18,  1.61it/s]
 48%|████▊     | 27843/57600 [4:52:11<5:10:21,  1.60it/s]
 48%|████▊     | 27844/57600 [4:52:12<4:59:39,  1.65it/s]
 48%|████▊     | 27845/57600 [4:52:13<5:03:52,  1.63it/s]
 48%|████▊     | 27846/57600 [4:52:13<4:56:17,  1.67it/s]
 48%|████▊     | 27847/57600 [4:52:14<4:51:44,  1.70it/s]
 48%|████▊     | 27848/57600 [4:52:14<4:53:19,  1.69it/s]
 48%|████▊     | 27849/57600 [4:52:15<4:59:54,  1.65it/s]
 48%|████▊     | 27850/57600 [4:52:16<5:10:54,  1.59it/s]
 48%|████▊     | 27851/57600 [4:52:16<5:26:27,  1.52it/s]
 48%|████▊     | 27852/57600 [4:52:17<5:14:43,  1.58it/s]
 48%|████▊     | 27853/57600 [4:52:18<5:07:17,  1.61it/s]
 48%|████▊     | 27854/57600 [4:52:18<5:05:59,  1.62it/s]
 48%|████▊     | 27855/57600 [4:52:19<5:07:29,  1.61it/s]
 48%|████▊     | 27856/57600 [4:52:19<4:57:34,  1.67it/s]
 48%|████▊     | 27857/57600 [4:52:20<5:07:57,  1.61it/s]
 48%|████▊     | 27858/57600 [4:52:21<5:08:20,  1.61it/s]
 48%|████▊     | 27859/57600 [4:52:21<5:02:17,  1.64it/s]
 48%|████▊     | 27860/57600 [4:52:22<5:01:49,  1.64it/s]
                                                         
{'loss': 1.1965, 'learning_rate': 5.663066202090592e-07, 'epoch': 307.51}

 48%|████▊     | 27860/57600 [4:52:22<5:01:49,  1.64it/s]
 48%|████▊     | 27861/57600 [4:52:23<5:12:11,  1.59it/s]
 48%|████▊     | 27862/57600 [4:52:23<5:05:07,  1.62it/s]
 48%|████▊     | 27863/57600 [4:52:24<5:02:21,  1.64it/s]
 48%|████▊     | 27864/57600 [4:52:24<5:02:57,  1.64it/s]
 48%|████▊     | 27865/57600 [4:52:25<5:01:49,  1.64it/s]
 48%|████▊     | 27866/57600 [4:52:26<5:04:58,  1.62it/s]
 48%|████▊     | 27867/57600 [4:52:26<5:05:58,  1.62it/s]
 48%|████▊     | 27868/57600 [4:52:27<5:09:04,  1.60it/s]
 48%|████▊     | 27869/57600 [4:52:28<5:13:46,  1.58it/s]
 48%|████▊     | 27870/57600 [4:52:28<5:15:06,  1.57it/s]
 48%|████▊     | 27871/57600 [4:52:29<5:11:59,  1.59it/s]
 48%|████▊     | 27872/57600 [4:52:29<5:10:21,  1.60it/s]
 48%|████▊     | 27873/57600 [4:52:30<5:08:36,  1.61it/s]
 48%|████▊     | 27874/57600 [4:52:31<4:58:17,  1.66it/s]
 48%|████▊     | 27875/57600 [4:52:31<5:07:45,  1.61it/s]
 48%|████▊     | 27876/57600 [4:52:32<5:05:26,  1.62it/s]
 48%|████▊     | 27877/57600 [4:52:32<5:04:40,  1.63it/s]
 48%|████▊     | 27878/57600 [4:52:33<4:59:42,  1.65it/s]
 48%|████▊     | 27879/57600 [4:52:34<5:08:43,  1.60it/s]
 48%|████▊     | 27880/57600 [4:52:34<5:04:40,  1.63it/s]
                                                         
{'loss': 1.2026, 'learning_rate': 5.659930313588849e-07, 'epoch': 307.73}

 48%|████▊     | 27880/57600 [4:52:34<5:04:40,  1.63it/s]
 48%|████▊     | 27881/57600 [4:52:35<5:01:01,  1.65it/s]
 48%|████▊     | 27882/57600 [4:52:36<5:11:12,  1.59it/s]
 48%|████▊     | 27883/57600 [4:52:36<5:02:33,  1.64it/s]
 48%|████▊     | 27884/57600 [4:52:37<4:51:56,  1.70it/s]
 48%|████▊     | 27885/57600 [4:52:37<4:50:19,  1.71it/s]
 48%|████▊     | 27886/57600 [4:52:38<4:56:41,  1.67it/s]
 48%|████▊     | 27887/57600 [4:52:38<4:52:51,  1.69it/s]
 48%|████▊     | 27888/57600 [4:52:39<4:55:35,  1.68it/s]
 48%|████▊     | 27889/57600 [4:52:40<5:12:07,  1.59it/s]
 48%|████▊     | 27890/57600 [4:52:40<5:20:09,  1.55it/s]
 48%|████▊     | 27891/57600 [4:52:41<5:25:07,  1.52it/s]
 48%|████▊     | 27892/57600 [4:52:42<5:20:09,  1.55it/s]
 48%|████▊     | 27893/57600 [4:52:42<5:26:31,  1.52it/s]
 48%|████▊     | 27894/57600 [4:52:43<5:13:13,  1.58it/s]
 48%|████▊     | 27895/57600 [4:52:44<5:12:54,  1.58it/s]
 48%|████▊     | 27896/57600 [4:52:44<5:14:47,  1.57it/s]
 48%|████▊     | 27897/57600 [4:52:45<5:15:05,  1.57it/s]
 48%|████▊     | 27898/57600 [4:52:46<5:18:23,  1.55it/s]
 48%|████▊     | 27899/57600 [4:52:46<5:09:35,  1.60it/s]
 48%|████▊     | 27900/57600 [4:52:47<5:00:40,  1.65it/s]
                                                         
{'loss': 1.2316, 'learning_rate': 5.656794425087108e-07, 'epoch': 307.95}

 48%|████▊     | 27900/57600 [4:52:47<5:00:40,  1.65it/s]
 48%|████▊     | 27901/57600 [4:52:47<4:56:48,  1.67it/s]
 48%|████▊     | 27902/57600 [4:52:48<4:58:17,  1.66it/s]
 48%|████▊     | 27903/57600 [4:52:49<5:00:28,  1.65it/s]
 48%|████▊     | 27904/57600 [4:52:49<5:08:29,  1.60it/s]
 48%|████▊     | 27905/57600 [4:52:50<5:17:33,  1.56it/s]
 48%|████▊     | 27906/57600 [4:52:51<5:19:42,  1.55it/s]
 48%|████▊     | 27907/57600 [4:52:51<5:14:52,  1.57it/s]
 48%|████▊     | 27908/57600 [4:52:52<5:23:12,  1.53it/s]
 48%|████▊     | 27909/57600 [4:52:52<5:22:11,  1.54it/s]
 48%|████▊     | 27910/57600 [4:52:53<5:29:04,  1.50it/s]
 48%|████▊     | 27911/57600 [4:52:54<5:37:36,  1.47it/s]
 48%|████▊     | 27912/57600 [4:52:55<5:36:46,  1.47it/s]
 48%|████▊     | 27913/57600 [4:52:55<5:27:51,  1.51it/s]
 48%|████▊     | 27914/57600 [4:52:56<5:16:27,  1.56it/s]
 48%|████▊     | 27915/57600 [4:52:56<5:05:44,  1.62it/s]
 48%|████▊     | 27916/57600 [4:52:57<5:05:22,  1.62it/s]
 48%|████▊     | 27917/57600 [4:52:58<4:55:09,  1.68it/s]
 48%|████▊     | 27918/57600 [4:52:58<5:03:51,  1.63it/s]
 48%|████▊     | 27919/57600 [4:52:59<4:58:58,  1.65it/s]
 48%|████▊     | 27920/57600 [4:52:59<4:59:12,  1.65it/s]
                                                         
{'loss': 1.163, 'learning_rate': 5.653658536585366e-07, 'epoch': 308.17}

 48%|████▊     | 27920/57600 [4:52:59<4:59:12,  1.65it/s]
 48%|████▊     | 27921/57600 [4:53:00<5:05:45,  1.62it/s]
 48%|████▊     | 27922/57600 [4:53:01<5:03:17,  1.63it/s]
 48%|████▊     | 27923/57600 [4:53:01<4:58:53,  1.65it/s]
 48%|████▊     | 27924/57600 [4:53:02<4:58:20,  1.66it/s]
 48%|████▊     | 27925/57600 [4:53:02<5:03:10,  1.63it/s]
 48%|████▊     | 27926/57600 [4:53:03<5:16:34,  1.56it/s]
 48%|████▊     | 27927/57600 [4:53:04<5:10:24,  1.59it/s]
 48%|████▊     | 27928/57600 [4:53:04<5:06:41,  1.61it/s]
 48%|████▊     | 27929/57600 [4:53:05<5:07:52,  1.61it/s]
 48%|████▊     | 27930/57600 [4:53:06<5:03:36,  1.63it/s]
 48%|████▊     | 27931/57600 [4:53:06<5:09:59,  1.60it/s]
 48%|████▊     | 27932/57600 [4:53:07<5:02:48,  1.63it/s]
 48%|████▊     | 27933/57600 [4:53:07<5:00:53,  1.64it/s]
 48%|████▊     | 27934/57600 [4:53:08<5:01:31,  1.64it/s]
 48%|████▊     | 27935/57600 [4:53:09<5:04:55,  1.62it/s]
 48%|████▊     | 27936/57600 [4:53:09<5:04:52,  1.62it/s]
 49%|████▊     | 27937/57600 [4:53:10<5:01:48,  1.64it/s]
 49%|████▊     | 27938/57600 [4:53:11<5:07:46,  1.61it/s]
 49%|████▊     | 27939/57600 [4:53:11<4:58:00,  1.66it/s]
 49%|████▊     | 27940/57600 [4:53:12<5:07:02,  1.61it/s]
                                                         
{'loss': 1.2085, 'learning_rate': 5.650522648083622e-07, 'epoch': 308.39}

 49%|████▊     | 27940/57600 [4:53:12<5:07:02,  1.61it/s]
 49%|████▊     | 27941/57600 [4:53:12<5:14:55,  1.57it/s]
 49%|████▊     | 27942/57600 [4:53:13<5:16:04,  1.56it/s]
 49%|████▊     | 27943/57600 [4:53:14<5:10:51,  1.59it/s]
 49%|████▊     | 27944/57600 [4:53:14<5:07:34,  1.61it/s]
 49%|████▊     | 27945/57600 [4:53:15<5:05:55,  1.62it/s]
 49%|████▊     | 27946/57600 [4:53:15<4:59:08,  1.65it/s]
 49%|████▊     | 27947/57600 [4:53:16<4:52:15,  1.69it/s]
 49%|████▊     | 27948/57600 [4:53:17<4:59:35,  1.65it/s]
 49%|████▊     | 27949/57600 [4:53:17<4:59:22,  1.65it/s]
 49%|████▊     | 27950/57600 [4:53:18<4:56:28,  1.67it/s]
 49%|████▊     | 27951/57600 [4:53:18<5:00:55,  1.64it/s]
 49%|████▊     | 27952/57600 [4:53:19<4:57:52,  1.66it/s]
 49%|████▊     | 27953/57600 [4:53:20<5:09:07,  1.60it/s]
 49%|████▊     | 27954/57600 [4:53:20<5:08:55,  1.60it/s]
 49%|████▊     | 27955/57600 [4:53:21<5:03:57,  1.63it/s]
 49%|████▊     | 27956/57600 [4:53:22<5:01:31,  1.64it/s]
 49%|████▊     | 27957/57600 [4:53:22<4:55:31,  1.67it/s]
 49%|████▊     | 27958/57600 [4:53:23<5:00:23,  1.64it/s]
 49%|████▊     | 27959/57600 [4:53:23<5:01:00,  1.64it/s]
 49%|████▊     | 27960/57600 [4:53:24<5:14:44,  1.57it/s]
                                                         
{'loss': 1.2146, 'learning_rate': 5.647386759581881e-07, 'epoch': 308.61}

 49%|████▊     | 27960/57600 [4:53:24<5:14:44,  1.57it/s]
 49%|████▊     | 27961/57600 [4:53:25<5:07:00,  1.61it/s]
 49%|████▊     | 27962/57600 [4:53:25<4:58:44,  1.65it/s]
 49%|████▊     | 27963/57600 [4:53:26<5:01:29,  1.64it/s]
 49%|████▊     | 27964/57600 [4:53:26<4:59:25,  1.65it/s]
 49%|████▊     | 27965/57600 [4:53:27<4:53:36,  1.68it/s]
 49%|████▊     | 27966/57600 [4:53:28<4:52:47,  1.69it/s]
 49%|████▊     | 27967/57600 [4:53:28<4:54:20,  1.68it/s]
 49%|████▊     | 27968/57600 [4:53:29<4:58:56,  1.65it/s]
 49%|████▊     | 27969/57600 [4:53:29<5:04:26,  1.62it/s]
 49%|████▊     | 27970/57600 [4:53:30<5:03:37,  1.63it/s]
 49%|████▊     | 27971/57600 [4:53:31<5:01:38,  1.64it/s]
 49%|████▊     | 27972/57600 [4:53:31<5:20:08,  1.54it/s]
 49%|████▊     | 27973/57600 [4:53:32<5:08:35,  1.60it/s]
 49%|████▊     | 27974/57600 [4:53:33<5:08:17,  1.60it/s]
 49%|████▊     | 27975/57600 [4:53:33<5:11:32,  1.58it/s]
 49%|████▊     | 27976/57600 [4:53:34<5:02:10,  1.63it/s]
 49%|████▊     | 27977/57600 [4:53:34<5:00:10,  1.64it/s]
 49%|████▊     | 27978/57600 [4:53:35<5:09:16,  1.60it/s]
 49%|████▊     | 27979/57600 [4:53:36<5:04:33,  1.62it/s]
 49%|████▊     | 27980/57600 [4:53:36<5:11:14,  1.59it/s]
                                                         
{'loss': 1.2172, 'learning_rate': 5.64425087108014e-07, 'epoch': 308.83}

 49%|████▊     | 27980/57600 [4:53:36<5:11:14,  1.59it/s]
 49%|████▊     | 27981/57600 [4:53:37<5:10:42,  1.59it/s]
 49%|████▊     | 27982/57600 [4:53:38<5:12:10,  1.58it/s]
 49%|████▊     | 27983/57600 [4:53:38<5:12:15,  1.58it/s]
 49%|████▊     | 27984/57600 [4:53:39<5:17:37,  1.55it/s]
 49%|████▊     | 27985/57600 [4:53:40<5:20:20,  1.54it/s]
 49%|████▊     | 27986/57600 [4:53:40<5:05:11,  1.62it/s]
 49%|████▊     | 27987/57600 [4:53:41<5:04:47,  1.62it/s]
 49%|████▊     | 27988/57600 [4:53:41<5:03:54,  1.62it/s]
 49%|████▊     | 27989/57600 [4:53:42<4:56:56,  1.66it/s]
 49%|████▊     | 27990/57600 [4:53:43<5:06:49,  1.61it/s]
 49%|████▊     | 27991/57600 [4:53:43<5:17:43,  1.55it/s]
 49%|████▊     | 27992/57600 [4:53:44<5:05:58,  1.61it/s]
 49%|████▊     | 27993/57600 [4:53:44<5:05:49,  1.61it/s]
 49%|████▊     | 27994/57600 [4:53:45<5:05:59,  1.61it/s]
 49%|████▊     | 27995/57600 [4:53:46<5:06:35,  1.61it/s]
 49%|████▊     | 27996/57600 [4:53:47<5:30:51,  1.49it/s]
 49%|████▊     | 27997/57600 [4:53:47<5:37:58,  1.46it/s]
 49%|████▊     | 27998/57600 [4:53:48<5:35:31,  1.47it/s]
 49%|████▊     | 27999/57600 [4:53:48<5:20:59,  1.54it/s]
 49%|████▊     | 28000/57600 [4:53:49<5:25:16,  1.52it/s]
                                                         
{'loss': 1.1308, 'learning_rate': 5.641114982578397e-07, 'epoch': 309.05}

 49%|████▊     | 28000/57600 [4:53:49<5:25:16,  1.52it/s]
 49%|████▊     | 28001/57600 [4:53:50<5:19:27,  1.54it/s]
 49%|████▊     | 28002/57600 [4:53:50<5:19:15,  1.55it/s]
 49%|████▊     | 28003/57600 [4:53:51<5:17:44,  1.55it/s]
 49%|████▊     | 28004/57600 [4:53:52<5:15:40,  1.56it/s]
 49%|████▊     | 28005/57600 [4:53:52<5:18:18,  1.55it/s]
 49%|████▊     | 28006/57600 [4:53:53<5:15:19,  1.56it/s]
 49%|████▊     | 28007/57600 [4:53:54<5:09:13,  1.60it/s]
 49%|████▊     | 28008/57600 [4:53:54<5:14:02,  1.57it/s]
 49%|████▊     | 28009/57600 [4:53:55<5:10:18,  1.59it/s]
 49%|████▊     | 28010/57600 [4:53:55<5:04:54,  1.62it/s]
 49%|████▊     | 28011/57600 [4:53:56<5:05:21,  1.61it/s]
 49%|████▊     | 28012/57600 [4:53:57<5:08:51,  1.60it/s]
 49%|████▊     | 28013/57600 [4:53:57<5:00:41,  1.64it/s]
 49%|████▊     | 28014/57600 [4:53:58<5:01:14,  1.64it/s]
 49%|████▊     | 28015/57600 [4:53:58<4:56:34,  1.66it/s]
 49%|████▊     | 28016/57600 [4:53:59<5:06:24,  1.61it/s]
 49%|████▊     | 28017/57600 [4:54:00<5:02:23,  1.63it/s]
 49%|████▊     | 28018/57600 [4:54:00<5:03:25,  1.62it/s]
 49%|████▊     | 28019/57600 [4:54:01<5:05:02,  1.62it/s]
 49%|████▊     | 28020/57600 [4:54:02<5:00:03,  1.64it/s]
                                                         
{'loss': 1.1976, 'learning_rate': 5.637979094076655e-07, 'epoch': 309.27}

 49%|████▊     | 28020/57600 [4:54:02<5:00:03,  1.64it/s]
 49%|████▊     | 28021/57600 [4:54:02<5:05:47,  1.61it/s]
 49%|████▊     | 28022/57600 [4:54:03<5:06:12,  1.61it/s]
 49%|████▊     | 28023/57600 [4:54:03<4:58:16,  1.65it/s]
 49%|████▊     | 28024/57600 [4:54:04<4:57:22,  1.66it/s]
 49%|████▊     | 28025/57600 [4:54:05<4:57:38,  1.66it/s]
 49%|████▊     | 28026/57600 [4:54:05<5:01:24,  1.64it/s]
 49%|████▊     | 28027/57600 [4:54:06<4:57:26,  1.66it/s]
 49%|████▊     | 28028/57600 [4:54:06<4:57:20,  1.66it/s]
 49%|████▊     | 28029/57600 [4:54:07<4:59:00,  1.65it/s]
 49%|████▊     | 28030/57600 [4:54:08<4:52:06,  1.69it/s]
 49%|████▊     | 28031/57600 [4:54:08<5:03:09,  1.63it/s]
 49%|████▊     | 28032/57600 [4:54:09<5:06:08,  1.61it/s]
 49%|████▊     | 28033/57600 [4:54:09<5:02:32,  1.63it/s]
 49%|████▊     | 28034/57600 [4:54:10<4:57:55,  1.65it/s]
 49%|████▊     | 28035/57600 [4:54:11<5:01:49,  1.63it/s]
 49%|████▊     | 28036/57600 [4:54:11<5:06:33,  1.61it/s]
 49%|████▊     | 28037/57600 [4:54:12<5:10:17,  1.59it/s]
 49%|████▊     | 28038/57600 [4:54:13<5:07:31,  1.60it/s]
 49%|████▊     | 28039/57600 [4:54:13<4:57:33,  1.66it/s]
 49%|████▊     | 28040/57600 [4:54:14<5:03:01,  1.63it/s]
                                                         
{'loss': 1.2266, 'learning_rate': 5.634843205574913e-07, 'epoch': 309.49}

 49%|████▊     | 28040/57600 [4:54:14<5:03:01,  1.63it/s]
 49%|████▊     | 28041/57600 [4:54:14<4:57:41,  1.65it/s]
 49%|████▊     | 28042/57600 [4:54:15<5:12:16,  1.58it/s]
 49%|████▊     | 28043/57600 [4:54:16<5:21:46,  1.53it/s]
 49%|████▊     | 28044/57600 [4:54:16<5:07:13,  1.60it/s]
 49%|████▊     | 28045/57600 [4:54:17<5:11:28,  1.58it/s]
 49%|████▊     | 28046/57600 [4:54:18<5:07:14,  1.60it/s]
 49%|████▊     | 28047/57600 [4:54:18<5:06:29,  1.61it/s]
 49%|████▊     | 28048/57600 [4:54:19<5:17:05,  1.55it/s]
 49%|████▊     | 28049/57600 [4:54:19<5:08:23,  1.60it/s]
 49%|████▊     | 28050/57600 [4:54:20<5:05:46,  1.61it/s]
 49%|████▊     | 28051/57600 [4:54:21<4:59:38,  1.64it/s]
 49%|████▊     | 28052/57600 [4:54:21<4:48:03,  1.71it/s]
 49%|████▊     | 28053/57600 [4:54:22<4:46:18,  1.72it/s]
 49%|████▊     | 28054/57600 [4:54:22<4:54:09,  1.67it/s]
 49%|████▊     | 28055/57600 [4:54:23<4:51:28,  1.69it/s]
 49%|████▊     | 28056/57600 [4:54:24<4:58:56,  1.65it/s]
 49%|████▊     | 28057/57600 [4:54:24<5:09:29,  1.59it/s]
 49%|████▊     | 28058/57600 [4:54:25<5:00:10,  1.64it/s]
 49%|████▊     | 28059/57600 [4:54:25<4:54:56,  1.67it/s]
 49%|████▊     | 28060/57600 [4:54:26<4:52:39,  1.68it/s]
                                                         
{'loss': 1.2106, 'learning_rate': 5.631707317073171e-07, 'epoch': 309.71}

 49%|████▊     | 28060/57600 [4:54:26<4:52:39,  1.68it/s]
 49%|████▊     | 28061/57600 [4:54:27<4:57:11,  1.66it/s]
 49%|████▊     | 28062/57600 [4:54:27<5:00:46,  1.64it/s]
 49%|████▊     | 28063/57600 [4:54:28<5:03:29,  1.62it/s]
 49%|████▊     | 28064/57600 [4:54:29<5:03:50,  1.62it/s]
 49%|████▊     | 28065/57600 [4:54:29<5:09:24,  1.59it/s]
 49%|████▊     | 28066/57600 [4:54:30<5:06:53,  1.60it/s]
 49%|████▊     | 28067/57600 [4:54:30<5:12:21,  1.58it/s]
 49%|████▊     | 28068/57600 [4:54:31<5:10:52,  1.58it/s]
 49%|████▊     | 28069/57600 [4:54:32<5:05:14,  1.61it/s]
 49%|████▊     | 28070/57600 [4:54:32<5:06:17,  1.61it/s]
 49%|████▊     | 28071/57600 [4:54:33<5:07:08,  1.60it/s]
 49%|████▊     | 28072/57600 [4:54:34<4:58:55,  1.65it/s]
 49%|████▊     | 28073/57600 [4:54:34<5:07:41,  1.60it/s]
 49%|████▊     | 28074/57600 [4:54:35<5:03:50,  1.62it/s]
 49%|████▊     | 28075/57600 [4:54:35<5:04:40,  1.62it/s]
 49%|████▊     | 28076/57600 [4:54:36<5:03:16,  1.62it/s]
 49%|████▊     | 28077/57600 [4:54:37<5:04:34,  1.62it/s]
 49%|████▊     | 28078/57600 [4:54:37<5:05:59,  1.61it/s]
 49%|████▊     | 28079/57600 [4:54:38<5:05:56,  1.61it/s]
 49%|████▉     | 28080/57600 [4:54:38<5:02:16,  1.63it/s]
                                                         
{'loss': 1.1707, 'learning_rate': 5.628571428571428e-07, 'epoch': 309.93}

 49%|████▉     | 28080/57600 [4:54:38<5:02:16,  1.63it/s]
 49%|████▉     | 28081/57600 [4:54:39<5:13:58,  1.57it/s]
 49%|████▉     | 28082/57600 [4:54:40<5:02:56,  1.62it/s]
 49%|████▉     | 28083/57600 [4:54:40<5:14:09,  1.57it/s]
 49%|████▉     | 28084/57600 [4:54:41<5:16:32,  1.55it/s]
 49%|████▉     | 28085/57600 [4:54:42<5:24:45,  1.51it/s]
 49%|████▉     | 28086/57600 [4:54:42<5:13:12,  1.57it/s]
 49%|████▉     | 28087/57600 [4:54:43<5:20:44,  1.53it/s]
 49%|████▉     | 28088/57600 [4:54:44<5:18:21,  1.54it/s]
 49%|████▉     | 28089/57600 [4:54:44<5:05:38,  1.61it/s]
 49%|████▉     | 28090/57600 [4:54:45<4:58:55,  1.65it/s]
 49%|████▉     | 28091/57600 [4:54:45<5:04:29,  1.62it/s]
 49%|████▉     | 28092/57600 [4:54:46<5:04:37,  1.61it/s]
 49%|████▉     | 28093/57600 [4:54:47<5:01:24,  1.63it/s]
 49%|████▉     | 28094/57600 [4:54:47<5:08:23,  1.59it/s]
 49%|████▉     | 28095/57600 [4:54:48<5:06:47,  1.60it/s]
 49%|████▉     | 28096/57600 [4:54:49<5:07:01,  1.60it/s]
 49%|████▉     | 28097/57600 [4:54:49<5:11:33,  1.58it/s]
 49%|████▉     | 28098/57600 [4:54:50<5:05:06,  1.61it/s]
 49%|████▉     | 28099/57600 [4:54:51<5:15:27,  1.56it/s]
 49%|████▉     | 28100/57600 [4:54:51<5:13:38,  1.57it/s]
                                                         
{'loss': 1.149, 'learning_rate': 5.625435540069688e-07, 'epoch': 310.15}

 49%|████▉     | 28100/57600 [4:54:51<5:13:38,  1.57it/s]
 49%|████▉     | 28101/57600 [4:54:52<5:15:53,  1.56it/s]
 49%|████▉     | 28102/57600 [4:54:52<5:10:52,  1.58it/s]
 49%|████▉     | 28103/57600 [4:54:53<5:05:45,  1.61it/s]
 49%|████▉     | 28104/57600 [4:54:54<5:04:27,  1.61it/s]
 49%|████▉     | 28105/57600 [4:54:54<4:58:24,  1.65it/s]
 49%|████▉     | 28106/57600 [4:54:55<4:55:00,  1.67it/s]
 49%|████▉     | 28107/57600 [4:54:55<4:56:28,  1.66it/s]
 49%|████▉     | 28108/57600 [4:54:56<5:07:04,  1.60it/s]
 49%|████▉     | 28109/57600 [4:54:57<4:57:40,  1.65it/s]
 49%|████▉     | 28110/57600 [4:54:57<4:59:47,  1.64it/s]
 49%|████▉     | 28111/57600 [4:54:58<5:15:32,  1.56it/s]
 49%|████▉     | 28112/57600 [4:54:59<5:12:32,  1.57it/s]
 49%|████▉     | 28113/57600 [4:54:59<5:19:11,  1.54it/s]
 49%|████▉     | 28114/57600 [4:55:00<5:04:03,  1.62it/s]
 49%|████▉     | 28115/57600 [4:55:00<4:57:45,  1.65it/s]
 49%|████▉     | 28116/57600 [4:55:01<5:06:45,  1.60it/s]
 49%|████▉     | 28117/57600 [4:55:02<5:21:08,  1.53it/s]
 49%|████▉     | 28118/57600 [4:55:02<5:19:23,  1.54it/s]
 49%|████▉     | 28119/57600 [4:55:03<5:23:38,  1.52it/s]
 49%|████▉     | 28120/57600 [4:55:04<5:24:48,  1.51it/s]
                                                         
{'loss': 1.1601, 'learning_rate': 5.622299651567944e-07, 'epoch': 310.38}

 49%|████▉     | 28120/57600 [4:55:04<5:24:48,  1.51it/s]
 49%|████▉     | 28121/57600 [4:55:04<5:27:40,  1.50it/s]
 49%|████▉     | 28122/57600 [4:55:05<5:12:29,  1.57it/s]
 49%|████▉     | 28123/57600 [4:55:06<5:14:36,  1.56it/s]
 49%|████▉     | 28124/57600 [4:55:06<5:20:11,  1.53it/s]
 49%|████▉     | 28125/57600 [4:55:07<5:08:30,  1.59it/s]
 49%|████▉     | 28126/57600 [4:55:08<5:15:27,  1.56it/s]
 49%|████▉     | 28127/57600 [4:55:08<5:06:16,  1.60it/s]
 49%|████▉     | 28128/57600 [4:55:09<4:56:00,  1.66it/s]
 49%|████▉     | 28129/57600 [4:55:09<4:57:52,  1.65it/s]
 49%|████▉     | 28130/57600 [4:55:10<4:49:23,  1.70it/s]
 49%|████▉     | 28131/57600 [4:55:10<4:50:48,  1.69it/s]
 49%|████▉     | 28132/57600 [4:55:11<4:52:47,  1.68it/s]
 49%|████▉     | 28133/57600 [4:55:12<4:58:01,  1.65it/s]
 49%|████▉     | 28134/57600 [4:55:12<4:51:32,  1.68it/s]
 49%|████▉     | 28135/57600 [4:55:13<4:44:58,  1.72it/s]
 49%|████▉     | 28136/57600 [4:55:13<4:52:54,  1.68it/s]
 49%|████▉     | 28137/57600 [4:55:14<4:53:20,  1.67it/s]
 49%|████▉     | 28138/57600 [4:55:15<5:00:33,  1.63it/s]
 49%|████▉     | 28139/57600 [4:55:15<4:56:23,  1.66it/s]
 49%|████▉     | 28140/57600 [4:55:16<5:04:13,  1.61it/s]
                                                         
{'loss': 1.1933, 'learning_rate': 5.619163763066202e-07, 'epoch': 310.6}

 49%|████▉     | 28140/57600 [4:55:16<5:04:13,  1.61it/s]
 49%|████▉     | 28141/57600 [4:55:17<4:56:06,  1.66it/s]
 49%|████▉     | 28142/57600 [4:55:17<4:55:41,  1.66it/s]
 49%|████▉     | 28143/57600 [4:55:18<5:07:33,  1.60it/s]
 49%|████▉     | 28144/57600 [4:55:18<5:07:14,  1.60it/s]
 49%|████▉     | 28145/57600 [4:55:19<5:09:14,  1.59it/s]
 49%|████▉     | 28146/57600 [4:55:20<5:05:51,  1.61it/s]
 49%|████▉     | 28147/57600 [4:55:20<4:54:33,  1.67it/s]
 49%|████▉     | 28148/57600 [4:55:21<5:02:12,  1.62it/s]
 49%|████▉     | 28149/57600 [4:55:22<5:16:31,  1.55it/s]
 49%|████▉     | 28150/57600 [4:55:22<5:07:10,  1.60it/s]
 49%|████▉     | 28151/57600 [4:55:23<5:03:00,  1.62it/s]
 49%|████▉     | 28152/57600 [4:55:23<5:05:21,  1.61it/s]
 49%|████▉     | 28153/57600 [4:55:24<5:02:49,  1.62it/s]
 49%|████▉     | 28154/57600 [4:55:25<5:10:39,  1.58it/s]
 49%|████▉     | 28155/57600 [4:55:25<5:20:24,  1.53it/s]
 49%|████▉     | 28156/57600 [4:55:26<5:12:28,  1.57it/s]
 49%|████▉     | 28157/57600 [4:55:27<5:11:36,  1.57it/s]
 49%|████▉     | 28158/57600 [4:55:27<5:04:39,  1.61it/s]
 49%|████▉     | 28159/57600 [4:55:28<4:59:24,  1.64it/s]
 49%|████▉     | 28160/57600 [4:55:28<4:58:52,  1.64it/s]
                                                         
{'loss': 1.2091, 'learning_rate': 5.61602787456446e-07, 'epoch': 310.82}

 49%|████▉     | 28160/57600 [4:55:28<4:58:52,  1.64it/s]
 49%|████▉     | 28161/57600 [4:55:29<5:03:45,  1.62it/s]
 49%|████▉     | 28162/57600 [4:55:30<5:06:07,  1.60it/s]
 49%|████▉     | 28163/57600 [4:55:30<4:57:16,  1.65it/s]
 49%|████▉     | 28164/57600 [4:55:31<4:51:11,  1.68it/s]
 49%|████▉     | 28165/57600 [4:55:31<4:49:05,  1.70it/s]
 49%|████▉     | 28166/57600 [4:55:32<4:53:20,  1.67it/s]
 49%|████▉     | 28167/57600 [4:55:33<4:49:21,  1.70it/s]
 49%|████▉     | 28168/57600 [4:55:33<4:49:23,  1.70it/s]
 49%|████▉     | 28169/57600 [4:55:34<4:54:43,  1.66it/s]
 49%|████▉     | 28170/57600 [4:55:34<5:04:20,  1.61it/s]
 49%|████▉     | 28171/57600 [4:55:35<5:02:59,  1.62it/s]
 49%|████▉     | 28172/57600 [4:55:36<5:10:17,  1.58it/s]
 49%|████▉     | 28173/57600 [4:55:36<5:03:47,  1.61it/s]
 49%|████▉     | 28174/57600 [4:55:37<5:03:58,  1.61it/s]
 49%|████▉     | 28175/57600 [4:55:38<5:06:39,  1.60it/s]
 49%|████▉     | 28176/57600 [4:55:38<5:15:59,  1.55it/s]
 49%|████▉     | 28177/57600 [4:55:39<5:20:19,  1.53it/s]
 49%|████▉     | 28178/57600 [4:55:40<5:25:51,  1.50it/s]
 49%|████▉     | 28179/57600 [4:55:40<5:17:32,  1.54it/s]
 49%|████▉     | 28180/57600 [4:55:41<5:10:44,  1.58it/s]
                                                         
{'loss': 1.2123, 'learning_rate': 5.612891986062718e-07, 'epoch': 311.04}

 49%|████▉     | 28180/57600 [4:55:41<5:10:44,  1.58it/s]
 49%|████▉     | 28181/57600 [4:55:41<5:08:37,  1.59it/s]
 49%|████▉     | 28182/57600 [4:55:42<5:03:42,  1.61it/s]
 49%|████▉     | 28183/57600 [4:55:43<5:05:01,  1.61it/s]
 49%|████▉     | 28184/57600 [4:55:43<4:54:30,  1.66it/s]
 49%|████▉     | 28185/57600 [4:55:44<5:09:28,  1.58it/s]
 49%|████▉     | 28186/57600 [4:55:45<5:09:19,  1.58it/s]
 49%|████▉     | 28187/57600 [4:55:45<5:04:03,  1.61it/s]
 49%|████▉     | 28188/57600 [4:55:46<5:09:33,  1.58it/s]
 49%|████▉     | 28189/57600 [4:55:46<5:04:53,  1.61it/s]
 49%|████▉     | 28190/57600 [4:55:47<5:00:48,  1.63it/s]
 49%|████▉     | 28191/57600 [4:55:48<4:58:52,  1.64it/s]
 49%|████▉     | 28192/57600 [4:55:48<5:12:45,  1.57it/s]
 49%|████▉     | 28193/57600 [4:55:49<5:17:23,  1.54it/s]
 49%|████▉     | 28194/57600 [4:55:50<5:23:26,  1.52it/s]
 49%|████▉     | 28195/57600 [4:55:50<5:06:16,  1.60it/s]
 49%|████▉     | 28196/57600 [4:55:51<5:01:48,  1.62it/s]
 49%|████▉     | 28197/57600 [4:55:51<4:57:39,  1.65it/s]
 49%|████▉     | 28198/57600 [4:55:52<4:55:18,  1.66it/s]
 49%|████▉     | 28199/57600 [4:55:53<4:56:17,  1.65it/s]
 49%|████▉     | 28200/57600 [4:55:53<4:53:57,  1.67it/s]
                                                         
{'loss': 1.1963, 'learning_rate': 5.609756097560975e-07, 'epoch': 311.26}

 49%|████▉     | 28200/57600 [4:55:53<4:53:57,  1.67it/s]
 49%|████▉     | 28201/57600 [4:55:54<5:09:47,  1.58it/s]
 49%|████▉     | 28202/57600 [4:55:54<4:56:26,  1.65it/s]
 49%|████▉     | 28203/57600 [4:55:55<4:52:41,  1.67it/s]
 49%|████▉     | 28204/57600 [4:55:56<5:01:43,  1.62it/s]
 49%|████▉     | 28205/57600 [4:55:56<5:09:52,  1.58it/s]
 49%|████▉     | 28206/57600 [4:55:57<4:59:19,  1.64it/s]
 49%|████▉     | 28207/57600 [4:55:58<5:03:16,  1.62it/s]
 49%|████▉     | 28208/57600 [4:55:58<5:00:47,  1.63it/s]
 49%|████▉     | 28209/57600 [4:55:59<5:01:59,  1.62it/s]
 49%|████▉     | 28210/57600 [4:55:59<5:13:23,  1.56it/s]
 49%|████▉     | 28211/57600 [4:56:00<5:06:27,  1.60it/s]
 49%|████▉     | 28212/57600 [4:56:01<5:10:08,  1.58it/s]
 49%|████▉     | 28213/57600 [4:56:01<5:16:47,  1.55it/s]
 49%|████▉     | 28214/57600 [4:56:02<5:16:54,  1.55it/s]
 49%|████▉     | 28215/57600 [4:56:03<5:15:41,  1.55it/s]
 49%|████▉     | 28216/57600 [4:56:03<5:01:01,  1.63it/s]
 49%|████▉     | 28217/57600 [4:56:04<5:00:29,  1.63it/s]
 49%|████▉     | 28218/57600 [4:56:04<4:57:24,  1.65it/s]
 49%|████▉     | 28219/57600 [4:56:05<4:52:19,  1.68it/s]
 49%|████▉     | 28220/57600 [4:56:06<4:58:34,  1.64it/s]
                                                         
{'loss': 1.1684, 'learning_rate': 5.606620209059233e-07, 'epoch': 311.48}

 49%|████▉     | 28220/57600 [4:56:06<4:58:34,  1.64it/s]
 49%|████▉     | 28221/57600 [4:56:06<5:02:53,  1.62it/s]
 49%|████▉     | 28222/57600 [4:56:07<4:56:35,  1.65it/s]
 49%|████▉     | 28223/57600 [4:56:07<4:50:46,  1.68it/s]
 49%|████▉     | 28224/57600 [4:56:08<4:49:24,  1.69it/s]
 49%|████▉     | 28225/57600 [4:56:09<4:45:45,  1.71it/s]
 49%|████▉     | 28226/57600 [4:56:09<4:52:47,  1.67it/s]
 49%|████▉     | 28227/57600 [4:56:10<4:48:35,  1.70it/s]
 49%|████▉     | 28228/57600 [4:56:10<4:51:49,  1.68it/s]
 49%|████▉     | 28229/57600 [4:56:11<4:58:37,  1.64it/s]
 49%|████▉     | 28230/57600 [4:56:12<4:55:03,  1.66it/s]
 49%|████▉     | 28231/57600 [4:56:12<5:01:05,  1.63it/s]
 49%|████▉     | 28232/57600 [4:56:13<5:05:48,  1.60it/s]
 49%|████▉     | 28233/57600 [4:56:14<5:01:30,  1.62it/s]
 49%|████▉     | 28234/57600 [4:56:14<4:56:39,  1.65it/s]
 49%|████▉     | 28235/57600 [4:56:15<4:56:19,  1.65it/s]
 49%|████▉     | 28236/57600 [4:56:15<4:58:29,  1.64it/s]
 49%|████▉     | 28237/57600 [4:56:16<4:56:13,  1.65it/s]
 49%|████▉     | 28238/57600 [4:56:16<4:47:42,  1.70it/s]
 49%|████▉     | 28239/57600 [4:56:17<4:59:04,  1.64it/s]
 49%|████▉     | 28240/57600 [4:56:18<4:55:41,  1.65it/s]
                                                         
{'loss': 1.2162, 'learning_rate': 5.60348432055749e-07, 'epoch': 311.7}

 49%|████▉     | 28240/57600 [4:56:18<4:55:41,  1.65it/s]
 49%|████▉     | 28241/57600 [4:56:18<5:11:35,  1.57it/s]
 49%|████▉     | 28242/57600 [4:56:19<5:03:38,  1.61it/s]
 49%|████▉     | 28243/57600 [4:56:20<5:10:32,  1.58it/s]
 49%|████▉     | 28244/57600 [4:56:20<5:06:30,  1.60it/s]
 49%|████▉     | 28245/57600 [4:56:21<5:08:15,  1.59it/s]
 49%|████▉     | 28246/57600 [4:56:22<5:02:33,  1.62it/s]
 49%|████▉     | 28247/57600 [4:56:22<4:53:44,  1.67it/s]
 49%|████▉     | 28248/57600 [4:56:23<4:49:48,  1.69it/s]
 49%|████▉     | 28249/57600 [4:56:23<5:01:34,  1.62it/s]
 49%|████▉     | 28250/57600 [4:56:24<4:51:52,  1.68it/s]
 49%|████▉     | 28251/57600 [4:56:25<5:02:47,  1.62it/s]
 49%|████▉     | 28252/57600 [4:56:25<5:06:34,  1.60it/s]
 49%|████▉     | 28253/57600 [4:56:26<5:09:05,  1.58it/s]
 49%|████▉     | 28254/57600 [4:56:26<5:01:06,  1.62it/s]
 49%|████▉     | 28255/57600 [4:56:27<4:59:46,  1.63it/s]
 49%|████▉     | 28256/57600 [4:56:28<4:59:42,  1.63it/s]
 49%|████▉     | 28257/57600 [4:56:28<5:07:04,  1.59it/s]
 49%|████▉     | 28258/57600 [4:56:29<5:15:15,  1.55it/s]
 49%|████▉     | 28259/57600 [4:56:30<5:10:38,  1.57it/s]
 49%|████▉     | 28260/57600 [4:56:30<5:16:07,  1.55it/s]
                                                         
{'loss': 1.1923, 'learning_rate': 5.600348432055749e-07, 'epoch': 311.92}

 49%|████▉     | 28260/57600 [4:56:30<5:16:07,  1.55it/s]
 49%|████▉     | 28261/57600 [4:56:31<5:08:11,  1.59it/s]
 49%|████▉     | 28262/57600 [4:56:31<5:02:48,  1.61it/s]
 49%|████▉     | 28263/57600 [4:56:32<5:08:36,  1.58it/s]
 49%|████▉     | 28264/57600 [4:56:33<5:03:49,  1.61it/s]
 49%|████▉     | 28265/57600 [4:56:33<5:01:31,  1.62it/s]
 49%|████▉     | 28266/57600 [4:56:34<4:56:46,  1.65it/s]
 49%|████▉     | 28267/57600 [4:56:35<4:58:48,  1.64it/s]
 49%|████▉     | 28268/57600 [4:56:35<5:19:36,  1.53it/s]
 49%|████▉     | 28269/57600 [4:56:36<5:08:50,  1.58it/s]
 49%|████▉     | 28270/57600 [4:56:37<5:13:56,  1.56it/s]
 49%|████▉     | 28271/57600 [4:56:37<5:01:48,  1.62it/s]
 49%|████▉     | 28272/57600 [4:56:38<5:01:47,  1.62it/s]
 49%|████▉     | 28273/57600 [4:56:38<4:59:27,  1.63it/s]
 49%|████▉     | 28274/57600 [4:56:39<5:07:29,  1.59it/s]
 49%|████▉     | 28275/57600 [4:56:40<5:01:58,  1.62it/s]
 49%|████▉     | 28276/57600 [4:56:40<4:57:47,  1.64it/s]
 49%|████▉     | 28277/57600 [4:56:41<5:06:23,  1.60it/s]
 49%|████▉     | 28278/57600 [4:56:41<5:06:35,  1.59it/s]
 49%|████▉     | 28279/57600 [4:56:42<5:02:08,  1.62it/s]
 49%|████▉     | 28280/57600 [4:56:43<5:10:14,  1.58it/s]
                                                         
{'loss': 1.2096, 'learning_rate': 5.597212543554007e-07, 'epoch': 312.14}

 49%|████▉     | 28280/57600 [4:56:43<5:10:14,  1.58it/s]
 49%|████▉     | 28281/57600 [4:56:43<5:06:55,  1.59it/s]
 49%|████▉     | 28282/57600 [4:56:44<5:01:41,  1.62it/s]
 49%|████▉     | 28283/57600 [4:56:45<5:00:18,  1.63it/s]
 49%|████▉     | 28284/57600 [4:56:45<4:59:55,  1.63it/s]
 49%|████▉     | 28285/57600 [4:56:46<5:04:11,  1.61it/s]
 49%|████▉     | 28286/57600 [4:56:46<5:07:11,  1.59it/s]
 49%|████▉     | 28287/57600 [4:56:47<5:00:56,  1.62it/s]
 49%|████▉     | 28288/57600 [4:56:48<4:56:40,  1.65it/s]
 49%|████▉     | 28289/57600 [4:56:48<4:56:48,  1.65it/s]
 49%|████▉     | 28290/57600 [4:56:49<5:03:44,  1.61it/s]
 49%|████▉     | 28291/57600 [4:56:49<5:02:17,  1.62it/s]
 49%|████▉     | 28292/57600 [4:56:50<5:29:46,  1.48it/s]
 49%|████▉     | 28293/57600 [4:56:51<5:17:39,  1.54it/s]
 49%|████▉     | 28294/57600 [4:56:52<5:23:27,  1.51it/s]
 49%|████▉     | 28295/57600 [4:56:52<5:14:54,  1.55it/s]
 49%|████▉     | 28296/57600 [4:56:53<5:07:03,  1.59it/s]
 49%|████▉     | 28297/57600 [4:56:53<4:58:53,  1.63it/s]
 49%|████▉     | 28298/57600 [4:56:54<5:08:47,  1.58it/s]
 49%|████▉     | 28299/57600 [4:56:55<5:02:00,  1.62it/s]
 49%|████▉     | 28300/57600 [4:56:55<5:00:58,  1.62it/s]
                                                         
{'loss': 1.1683, 'learning_rate': 5.594076655052264e-07, 'epoch': 312.36}

 49%|████▉     | 28300/57600 [4:56:55<5:00:58,  1.62it/s]
 49%|████▉     | 28301/57600 [4:56:56<5:21:22,  1.52it/s]
 49%|████▉     | 28302/57600 [4:56:57<5:17:48,  1.54it/s]
 49%|████▉     | 28303/57600 [4:56:57<5:07:04,  1.59it/s]
 49%|████▉     | 28304/57600 [4:56:58<5:09:35,  1.58it/s]
 49%|████▉     | 28305/57600 [4:56:58<5:02:55,  1.61it/s]
 49%|████▉     | 28306/57600 [4:56:59<4:59:05,  1.63it/s]
 49%|████▉     | 28307/57600 [4:57:00<4:57:32,  1.64it/s]
 49%|████▉     | 28308/57600 [4:57:00<4:58:08,  1.64it/s]
 49%|████▉     | 28309/57600 [4:57:01<5:06:57,  1.59it/s]
 49%|████▉     | 28310/57600 [4:57:01<5:03:39,  1.61it/s]
 49%|████▉     | 28311/57600 [4:57:02<5:09:12,  1.58it/s]
 49%|████▉     | 28312/57600 [4:57:03<5:23:00,  1.51it/s]
 49%|████▉     | 28313/57600 [4:57:04<5:19:04,  1.53it/s]
 49%|████▉     | 28314/57600 [4:57:04<5:06:54,  1.59it/s]
 49%|████▉     | 28315/57600 [4:57:05<5:05:11,  1.60it/s]
 49%|████▉     | 28316/57600 [4:57:05<5:02:27,  1.61it/s]
 49%|████▉     | 28317/57600 [4:57:06<5:06:17,  1.59it/s]
 49%|████▉     | 28318/57600 [4:57:07<4:56:09,  1.65it/s]
 49%|████▉     | 28319/57600 [4:57:07<4:56:54,  1.64it/s]
 49%|████▉     | 28320/57600 [4:57:08<5:09:32,  1.58it/s]
                                                         
{'loss': 1.1773, 'learning_rate': 5.590940766550523e-07, 'epoch': 312.58}

 49%|████▉     | 28320/57600 [4:57:08<5:09:32,  1.58it/s]
 49%|████▉     | 28321/57600 [4:57:08<4:58:51,  1.63it/s]
 49%|████▉     | 28322/57600 [4:57:09<4:57:10,  1.64it/s]
 49%|████▉     | 28323/57600 [4:57:10<4:59:42,  1.63it/s]
 49%|████▉     | 28324/57600 [4:57:10<5:04:39,  1.60it/s]
 49%|████▉     | 28325/57600 [4:57:11<4:54:26,  1.66it/s]
 49%|████▉     | 28326/57600 [4:57:11<4:53:13,  1.66it/s]
 49%|████▉     | 28327/57600 [4:57:12<4:51:37,  1.67it/s]
 49%|████▉     | 28328/57600 [4:57:13<4:52:24,  1.67it/s]
 49%|████▉     | 28329/57600 [4:57:13<4:47:42,  1.70it/s]
 49%|████▉     | 28330/57600 [4:57:14<4:50:22,  1.68it/s]
 49%|████▉     | 28331/57600 [4:57:14<4:56:10,  1.65it/s]
 49%|████▉     | 28332/57600 [4:57:15<4:58:19,  1.64it/s]
 49%|████▉     | 28333/57600 [4:57:16<5:06:29,  1.59it/s]
 49%|████▉     | 28334/57600 [4:57:16<5:04:58,  1.60it/s]
 49%|████▉     | 28335/57600 [4:57:17<5:05:21,  1.60it/s]
 49%|████▉     | 28336/57600 [4:57:18<5:06:16,  1.59it/s]
 49%|████▉     | 28337/57600 [4:57:18<5:04:57,  1.60it/s]
 49%|████▉     | 28338/57600 [4:57:19<5:01:34,  1.62it/s]
 49%|████▉     | 28339/57600 [4:57:19<5:09:45,  1.57it/s]
 49%|████▉     | 28340/57600 [4:57:20<5:02:27,  1.61it/s]
                                                         
{'loss': 1.2004, 'learning_rate': 5.587804878048781e-07, 'epoch': 312.8}

 49%|████▉     | 28340/57600 [4:57:20<5:02:27,  1.61it/s]
 49%|████▉     | 28341/57600 [4:57:21<5:05:47,  1.59it/s]
 49%|████▉     | 28342/57600 [4:57:21<5:02:34,  1.61it/s]
 49%|████▉     | 28343/57600 [4:57:22<5:04:35,  1.60it/s]
 49%|████▉     | 28344/57600 [4:57:23<4:59:02,  1.63it/s]
 49%|████▉     | 28345/57600 [4:57:23<5:06:26,  1.59it/s]
 49%|████▉     | 28346/57600 [4:57:24<5:00:00,  1.63it/s]
 49%|████▉     | 28347/57600 [4:57:24<4:53:40,  1.66it/s]
 49%|████▉     | 28348/57600 [4:57:25<4:51:14,  1.67it/s]
 49%|████▉     | 28349/57600 [4:57:26<4:56:15,  1.65it/s]
 49%|████▉     | 28350/57600 [4:57:26<5:09:51,  1.57it/s]
 49%|████▉     | 28351/57600 [4:57:27<5:21:01,  1.52it/s]
 49%|████▉     | 28352/57600 [4:57:28<5:21:04,  1.52it/s]
 49%|████▉     | 28353/57600 [4:57:28<5:12:26,  1.56it/s]
 49%|████▉     | 28354/57600 [4:57:29<4:58:11,  1.63it/s]
 49%|████▉     | 28355/57600 [4:57:29<4:58:53,  1.63it/s]
 49%|████▉     | 28356/57600 [4:57:30<5:00:00,  1.62it/s]
 49%|████▉     | 28357/57600 [4:57:31<4:52:40,  1.67it/s]
 49%|████▉     | 28358/57600 [4:57:31<5:01:14,  1.62it/s]
 49%|████▉     | 28359/57600 [4:57:32<4:52:30,  1.67it/s]
 49%|████▉     | 28360/57600 [4:57:32<4:57:48,  1.64it/s]
                                                         
{'loss': 1.1871, 'learning_rate': 5.584668989547038e-07, 'epoch': 313.02}

 49%|████▉     | 28360/57600 [4:57:32<4:57:48,  1.64it/s]
 49%|████▉     | 28361/57600 [4:57:33<5:04:24,  1.60it/s]
 49%|████▉     | 28362/57600 [4:57:34<5:05:54,  1.59it/s]
 49%|████▉     | 28363/57600 [4:57:34<5:03:46,  1.60it/s]
 49%|████▉     | 28364/57600 [4:57:35<5:09:42,  1.57it/s]
 49%|████▉     | 28365/57600 [4:57:36<5:10:08,  1.57it/s]
 49%|████▉     | 28366/57600 [4:57:36<5:17:11,  1.54it/s]
 49%|████▉     | 28367/57600 [4:57:37<5:07:19,  1.59it/s]
 49%|████▉     | 28368/57600 [4:57:38<5:02:19,  1.61it/s]
 49%|████▉     | 28369/57600 [4:57:38<5:14:05,  1.55it/s]
 49%|████▉     | 28370/57600 [4:57:39<5:16:20,  1.54it/s]
 49%|████▉     | 28371/57600 [4:57:40<5:19:45,  1.52it/s]
 49%|████▉     | 28372/57600 [4:57:40<5:04:09,  1.60it/s]
 49%|████▉     | 28373/57600 [4:57:41<4:54:36,  1.65it/s]
 49%|████▉     | 28374/57600 [4:57:41<4:53:35,  1.66it/s]
 49%|████▉     | 28375/57600 [4:57:42<4:51:33,  1.67it/s]
 49%|████▉     | 28376/57600 [4:57:43<5:01:59,  1.61it/s]
 49%|████▉     | 28377/57600 [4:57:43<4:52:06,  1.67it/s]
 49%|████▉     | 28378/57600 [4:57:44<5:02:28,  1.61it/s]
 49%|████▉     | 28379/57600 [4:57:44<5:04:52,  1.60it/s]
 49%|████▉     | 28380/57600 [4:57:45<5:06:41,  1.59it/s]
                                                         
{'loss': 1.1895, 'learning_rate': 5.581533101045296e-07, 'epoch': 313.25}

 49%|████▉     | 28380/57600 [4:57:45<5:06:41,  1.59it/s]
 49%|████▉     | 28381/57600 [4:57:46<5:05:38,  1.59it/s]
 49%|████▉     | 28382/57600 [4:57:46<5:03:47,  1.60it/s]
 49%|████▉     | 28383/57600 [4:57:47<5:05:59,  1.59it/s]
 49%|████▉     | 28384/57600 [4:57:48<5:08:22,  1.58it/s]
 49%|████▉     | 28385/57600 [4:57:48<4:58:12,  1.63it/s]
 49%|████▉     | 28386/57600 [4:57:49<4:59:03,  1.63it/s]
 49%|████▉     | 28387/57600 [4:57:49<5:03:04,  1.61it/s]
 49%|████▉     | 28388/57600 [4:57:50<4:58:36,  1.63it/s]
 49%|████▉     | 28389/57600 [4:57:51<5:05:39,  1.59it/s]
 49%|████▉     | 28390/57600 [4:57:51<4:55:57,  1.64it/s]
 49%|████▉     | 28391/57600 [4:57:52<5:04:54,  1.60it/s]
 49%|████▉     | 28392/57600 [4:57:52<5:06:48,  1.59it/s]
 49%|████▉     | 28393/57600 [4:57:53<5:08:21,  1.58it/s]
 49%|████▉     | 28394/57600 [4:57:54<5:07:57,  1.58it/s]
 49%|████▉     | 28395/57600 [4:57:54<5:05:52,  1.59it/s]
 49%|████▉     | 28396/57600 [4:57:55<5:08:20,  1.58it/s]
 49%|████▉     | 28397/57600 [4:57:56<5:03:05,  1.61it/s]
 49%|████▉     | 28398/57600 [4:57:56<5:11:03,  1.56it/s]
 49%|████▉     | 28399/57600 [4:57:57<5:08:50,  1.58it/s]
 49%|████▉     | 28400/57600 [4:57:57<5:01:02,  1.62it/s]
                                                         
{'loss': 1.1981, 'learning_rate': 5.578397212543555e-07, 'epoch': 313.47}

 49%|████▉     | 28400/57600 [4:57:57<5:01:02,  1.62it/s]
 49%|████▉     | 28401/57600 [4:57:58<5:07:15,  1.58it/s]
 49%|████▉     | 28402/57600 [4:57:59<5:10:49,  1.57it/s]
 49%|████▉     | 28403/57600 [4:57:59<5:00:16,  1.62it/s]
 49%|████▉     | 28404/57600 [4:58:00<5:05:10,  1.59it/s]
 49%|████▉     | 28405/57600 [4:58:01<4:56:07,  1.64it/s]
 49%|████▉     | 28406/57600 [4:58:01<4:55:58,  1.64it/s]
 49%|████▉     | 28407/57600 [4:58:02<4:52:52,  1.66it/s]
 49%|████▉     | 28408/57600 [4:58:02<4:50:34,  1.67it/s]
 49%|████▉     | 28409/57600 [4:58:03<4:52:55,  1.66it/s]
 49%|████▉     | 28410/57600 [4:58:04<4:52:38,  1.66it/s]
 49%|████▉     | 28411/57600 [4:58:04<4:56:47,  1.64it/s]
 49%|████▉     | 28412/57600 [4:58:05<4:57:24,  1.64it/s]
 49%|████▉     | 28413/57600 [4:58:05<4:48:13,  1.69it/s]
 49%|████▉     | 28414/57600 [4:58:06<4:51:57,  1.67it/s]
 49%|████▉     | 28415/57600 [4:58:07<5:01:45,  1.61it/s]
 49%|████▉     | 28416/57600 [4:58:07<5:14:44,  1.55it/s]
 49%|████▉     | 28417/57600 [4:58:08<5:27:55,  1.48it/s]
 49%|████▉     | 28418/57600 [4:58:09<5:23:03,  1.51it/s]
 49%|████▉     | 28419/57600 [4:58:09<5:14:18,  1.55it/s]
 49%|████▉     | 28420/57600 [4:58:10<5:07:03,  1.58it/s]
                                                         
{'loss': 1.2169, 'learning_rate': 5.575261324041811e-07, 'epoch': 313.69}

 49%|████▉     | 28420/57600 [4:58:10<5:07:03,  1.58it/s]
 49%|████▉     | 28421/57600 [4:58:11<5:14:33,  1.55it/s]
 49%|████▉     | 28422/57600 [4:58:11<5:14:07,  1.55it/s]
 49%|████▉     | 28423/57600 [4:58:12<5:13:19,  1.55it/s]
 49%|████▉     | 28424/57600 [4:58:13<5:18:35,  1.53it/s]
 49%|████▉     | 28425/57600 [4:58:13<5:11:22,  1.56it/s]
 49%|████▉     | 28426/57600 [4:58:14<5:18:18,  1.53it/s]
 49%|████▉     | 28427/57600 [4:58:14<5:07:18,  1.58it/s]
 49%|████▉     | 28428/57600 [4:58:15<5:12:16,  1.56it/s]
 49%|████▉     | 28429/57600 [4:58:16<5:10:40,  1.56it/s]
 49%|████▉     | 28430/57600 [4:58:16<5:13:54,  1.55it/s]
 49%|████▉     | 28431/57600 [4:58:17<5:02:45,  1.61it/s]
 49%|████▉     | 28432/57600 [4:58:18<5:03:50,  1.60it/s]
 49%|████▉     | 28433/57600 [4:58:18<4:59:40,  1.62it/s]
 49%|████▉     | 28434/57600 [4:58:19<4:51:28,  1.67it/s]
 49%|████▉     | 28435/57600 [4:58:19<4:56:22,  1.64it/s]
 49%|████▉     | 28436/57600 [4:58:20<5:03:34,  1.60it/s]
 49%|████▉     | 28437/57600 [4:58:21<4:58:47,  1.63it/s]
 49%|████▉     | 28438/57600 [4:58:21<4:54:04,  1.65it/s]
 49%|████▉     | 28439/57600 [4:58:22<4:44:44,  1.71it/s]
 49%|████▉     | 28440/57600 [4:58:22<4:44:18,  1.71it/s]
                                                         
{'loss': 1.1895, 'learning_rate': 5.57212543554007e-07, 'epoch': 313.91}

 49%|████▉     | 28440/57600 [4:58:22<4:44:18,  1.71it/s]
 49%|████▉     | 28441/57600 [4:58:23<4:51:04,  1.67it/s]
 49%|████▉     | 28442/57600 [4:58:24<4:49:27,  1.68it/s]
 49%|████▉     | 28443/57600 [4:58:24<4:51:50,  1.67it/s]
 49%|████▉     | 28444/57600 [4:58:25<4:54:17,  1.65it/s]
 49%|████▉     | 28445/57600 [4:58:25<4:52:36,  1.66it/s]
 49%|████▉     | 28446/57600 [4:58:26<5:01:37,  1.61it/s]
 49%|████▉     | 28447/57600 [4:58:27<4:59:08,  1.62it/s]
 49%|████▉     | 28448/57600 [4:58:27<5:06:30,  1.59it/s]
 49%|████▉     | 28449/57600 [4:58:28<5:11:28,  1.56it/s]
 49%|████▉     | 28450/57600 [4:58:29<5:06:30,  1.59it/s]
 49%|████▉     | 28451/57600 [4:58:29<5:00:01,  1.62it/s]
 49%|████▉     | 28452/57600 [4:58:30<4:55:38,  1.64it/s]
 49%|████▉     | 28453/57600 [4:58:30<5:00:24,  1.62it/s]
 49%|████▉     | 28454/57600 [4:58:31<4:59:43,  1.62it/s]
 49%|████▉     | 28455/57600 [4:58:32<4:50:22,  1.67it/s]
 49%|████▉     | 28456/57600 [4:58:32<4:53:30,  1.65it/s]
 49%|████▉     | 28457/57600 [4:58:33<4:53:29,  1.65it/s]
 49%|████▉     | 28458/57600 [4:58:33<4:56:25,  1.64it/s]
 49%|████▉     | 28459/57600 [4:58:34<4:56:10,  1.64it/s]
 49%|████▉     | 28460/57600 [4:58:35<4:58:54,  1.62it/s]
                                                         
{'loss': 1.2034, 'learning_rate': 5.568989547038329e-07, 'epoch': 314.13}

 49%|████▉     | 28460/57600 [4:58:35<4:58:54,  1.62it/s]
 49%|████▉     | 28461/57600 [4:58:35<4:53:09,  1.66it/s]
 49%|████▉     | 28462/57600 [4:58:36<4:54:54,  1.65it/s]
 49%|████▉     | 28463/57600 [4:58:36<4:47:08,  1.69it/s]
 49%|████▉     | 28464/57600 [4:58:37<5:09:07,  1.57it/s]
 49%|████▉     | 28465/57600 [4:58:38<5:12:10,  1.56it/s]
 49%|████▉     | 28466/57600 [4:58:39<5:15:53,  1.54it/s]
 49%|████▉     | 28467/57600 [4:58:39<5:06:44,  1.58it/s]
 49%|████▉     | 28468/57600 [4:58:40<5:06:27,  1.58it/s]
 49%|████▉     | 28469/57600 [4:58:40<5:12:15,  1.55it/s]
 49%|████▉     | 28470/57600 [4:58:41<5:03:50,  1.60it/s]
 49%|████▉     | 28471/57600 [4:58:42<4:58:56,  1.62it/s]
 49%|████▉     | 28472/57600 [4:58:42<4:57:10,  1.63it/s]
 49%|████▉     | 28473/57600 [4:58:43<4:50:06,  1.67it/s]
 49%|████▉     | 28474/57600 [4:58:43<5:06:45,  1.58it/s]
 49%|████▉     | 28475/57600 [4:58:44<5:17:37,  1.53it/s]
 49%|████▉     | 28476/57600 [4:58:45<5:18:42,  1.52it/s]
 49%|████▉     | 28477/57600 [4:58:45<5:04:08,  1.60it/s]
 49%|████▉     | 28478/57600 [4:58:46<5:01:41,  1.61it/s]
 49%|████▉     | 28479/57600 [4:58:47<4:59:06,  1.62it/s]
 49%|████▉     | 28480/57600 [4:58:47<4:55:02,  1.64it/s]
                                                         
{'loss': 1.1766, 'learning_rate': 5.565853658536585e-07, 'epoch': 314.35}

 49%|████▉     | 28480/57600 [4:58:47<4:55:02,  1.64it/s]
 49%|████▉     | 28481/57600 [4:58:48<4:55:53,  1.64it/s]
 49%|████▉     | 28482/57600 [4:58:48<4:57:22,  1.63it/s]
 49%|████▉     | 28483/57600 [4:58:49<4:55:05,  1.64it/s]
 49%|████▉     | 28484/57600 [4:58:50<4:47:18,  1.69it/s]
 49%|████▉     | 28485/57600 [4:58:50<4:43:29,  1.71it/s]
 49%|████▉     | 28486/57600 [4:58:51<4:50:59,  1.67it/s]
 49%|████▉     | 28487/57600 [4:58:51<4:58:53,  1.62it/s]
 49%|████▉     | 28488/57600 [4:58:52<4:57:24,  1.63it/s]
 49%|████▉     | 28489/57600 [4:58:53<4:53:54,  1.65it/s]
 49%|████▉     | 28490/57600 [4:58:53<5:00:49,  1.61it/s]
 49%|████▉     | 28491/57600 [4:58:54<4:56:24,  1.64it/s]
 49%|████▉     | 28492/57600 [4:58:54<4:49:34,  1.68it/s]
 49%|████▉     | 28493/57600 [4:58:55<4:58:20,  1.63it/s]
 49%|████▉     | 28494/57600 [4:58:56<5:09:01,  1.57it/s]
 49%|████▉     | 28495/57600 [4:58:56<5:01:23,  1.61it/s]
 49%|████▉     | 28496/57600 [4:58:57<4:57:54,  1.63it/s]
 49%|████▉     | 28497/57600 [4:58:58<4:55:27,  1.64it/s]
 49%|████▉     | 28498/57600 [4:58:58<5:02:25,  1.60it/s]
 49%|████▉     | 28499/57600 [4:58:59<5:00:02,  1.62it/s]
 49%|████▉     | 28500/57600 [4:58:59<4:56:46,  1.63it/s]
                                                         
{'loss': 1.204, 'learning_rate': 5.562717770034842e-07, 'epoch': 314.57}

 49%|████▉     | 28500/57600 [4:58:59<4:56:46,  1.63it/s]
 49%|████▉     | 28501/57600 [4:59:00<4:49:03,  1.68it/s]
 49%|████▉     | 28502/57600 [4:59:01<4:47:16,  1.69it/s]
 49%|████▉     | 28503/57600 [4:59:01<4:59:54,  1.62it/s]
 49%|████▉     | 28504/57600 [4:59:02<5:07:52,  1.58it/s]
 49%|████▉     | 28505/57600 [4:59:03<5:09:07,  1.57it/s]
 49%|████▉     | 28506/57600 [4:59:03<5:05:58,  1.58it/s]
 49%|████▉     | 28507/57600 [4:59:04<5:00:35,  1.61it/s]
 49%|████▉     | 28508/57600 [4:59:04<5:00:02,  1.62it/s]
 49%|████▉     | 28509/57600 [4:59:05<5:09:24,  1.57it/s]
 49%|████▉     | 28510/57600 [4:59:06<5:28:32,  1.48it/s]
 49%|████▉     | 28511/57600 [4:59:06<5:22:12,  1.50it/s]
 50%|████▉     | 28512/57600 [4:59:07<5:10:24,  1.56it/s]
 50%|████▉     | 28513/57600 [4:59:08<5:11:31,  1.56it/s]
 50%|████▉     | 28514/57600 [4:59:08<5:06:03,  1.58it/s]
 50%|████▉     | 28515/57600 [4:59:09<5:08:59,  1.57it/s]
 50%|████▉     | 28516/57600 [4:59:10<5:02:35,  1.60it/s]
 50%|████▉     | 28517/57600 [4:59:10<5:03:49,  1.60it/s]
 50%|████▉     | 28518/57600 [4:59:11<4:59:41,  1.62it/s]
 50%|████▉     | 28519/57600 [4:59:11<4:54:51,  1.64it/s]
 50%|████▉     | 28520/57600 [4:59:12<5:02:19,  1.60it/s]
                                                         
{'loss': 1.1877, 'learning_rate': 5.5595818815331e-07, 'epoch': 314.79}

 50%|████▉     | 28520/57600 [4:59:12<5:02:19,  1.60it/s]
 50%|████▉     | 28521/57600 [4:59:13<4:55:41,  1.64it/s]
 50%|████▉     | 28522/57600 [4:59:13<4:57:49,  1.63it/s]
 50%|████▉     | 28523/57600 [4:59:14<4:50:50,  1.67it/s]
 50%|████▉     | 28524/57600 [4:59:14<4:55:55,  1.64it/s]
 50%|████▉     | 28525/57600 [4:59:15<5:14:08,  1.54it/s]
 50%|████▉     | 28526/57600 [4:59:16<5:15:39,  1.54it/s]
 50%|████▉     | 28527/57600 [4:59:16<5:12:52,  1.55it/s]
 50%|████▉     | 28528/57600 [4:59:17<5:04:48,  1.59it/s]
 50%|████▉     | 28529/57600 [4:59:18<5:13:17,  1.55it/s]
 50%|████▉     | 28530/57600 [4:59:18<5:05:31,  1.59it/s]
 50%|████▉     | 28531/57600 [4:59:19<4:56:39,  1.63it/s]
 50%|████▉     | 28532/57600 [4:59:19<4:51:04,  1.66it/s]
 50%|████▉     | 28533/57600 [4:59:20<4:50:54,  1.67it/s]
 50%|████▉     | 28534/57600 [4:59:21<4:54:16,  1.65it/s]
 50%|████▉     | 28535/57600 [4:59:21<4:55:07,  1.64it/s]
 50%|████▉     | 28536/57600 [4:59:22<4:54:39,  1.64it/s]
 50%|████▉     | 28537/57600 [4:59:23<4:58:06,  1.62it/s]
 50%|████▉     | 28538/57600 [4:59:23<5:01:04,  1.61it/s]
 50%|████▉     | 28539/57600 [4:59:24<5:08:04,  1.57it/s]
 50%|████▉     | 28540/57600 [4:59:25<5:25:31,  1.49it/s]
                                                         
{'loss': 1.1443, 'learning_rate': 5.556445993031359e-07, 'epoch': 315.01}

 50%|████▉     | 28540/57600 [4:59:25<5:25:31,  1.49it/s]
 50%|████▉     | 28541/57600 [4:59:25<5:16:52,  1.53it/s]
 50%|████▉     | 28542/57600 [4:59:26<5:09:13,  1.57it/s]
 50%|████▉     | 28543/57600 [4:59:26<5:02:27,  1.60it/s]
 50%|████▉     | 28544/57600 [4:59:27<5:10:33,  1.56it/s]
 50%|████▉     | 28545/57600 [4:59:28<5:04:26,  1.59it/s]
 50%|████▉     | 28546/57600 [4:59:28<5:03:08,  1.60it/s]
 50%|████▉     | 28547/57600 [4:59:29<4:58:53,  1.62it/s]
 50%|████▉     | 28548/57600 [4:59:30<4:55:53,  1.64it/s]
 50%|████▉     | 28549/57600 [4:59:30<4:48:03,  1.68it/s]
 50%|████▉     | 28550/57600 [4:59:31<4:57:02,  1.63it/s]
 50%|████▉     | 28551/57600 [4:59:31<4:56:03,  1.64it/s]
 50%|████▉     | 28552/57600 [4:59:32<4:53:48,  1.65it/s]
 50%|████▉     | 28553/57600 [4:59:33<5:04:30,  1.59it/s]
 50%|████▉     | 28554/57600 [4:59:33<5:00:16,  1.61it/s]
 50%|████▉     | 28555/57600 [4:59:34<5:01:06,  1.61it/s]
 50%|████▉     | 28556/57600 [4:59:34<5:06:09,  1.58it/s]
 50%|████▉     | 28557/57600 [4:59:35<4:56:43,  1.63it/s]
 50%|████▉     | 28558/57600 [4:59:36<5:06:18,  1.58it/s]
 50%|████▉     | 28559/57600 [4:59:36<5:08:39,  1.57it/s]
 50%|████▉     | 28560/57600 [4:59:37<5:16:01,  1.53it/s]
                                                         
{'loss': 1.1559, 'learning_rate': 5.553310104529616e-07, 'epoch': 315.23}

 50%|████▉     | 28560/57600 [4:59:37<5:16:01,  1.53it/s]
 50%|████▉     | 28561/57600 [4:59:38<4:59:33,  1.62it/s]
 50%|████▉     | 28562/57600 [4:59:38<4:56:41,  1.63it/s]
 50%|████▉     | 28563/57600 [4:59:39<4:54:30,  1.64it/s]
 50%|████▉     | 28564/57600 [4:59:39<4:52:38,  1.65it/s]
 50%|████▉     | 28565/57600 [4:59:40<4:55:35,  1.64it/s]
 50%|████▉     | 28566/57600 [4:59:41<4:55:33,  1.64it/s]
 50%|████▉     | 28567/57600 [4:59:41<4:59:41,  1.61it/s]
 50%|████▉     | 28568/57600 [4:59:42<4:48:53,  1.67it/s]
 50%|████▉     | 28569/57600 [4:59:42<4:50:54,  1.66it/s]
 50%|████▉     | 28570/57600 [4:59:43<4:49:17,  1.67it/s]
 50%|████▉     | 28571/57600 [4:59:44<4:57:52,  1.62it/s]
 50%|████▉     | 28572/57600 [4:59:44<5:02:24,  1.60it/s]
 50%|████▉     | 28573/57600 [4:59:45<5:02:26,  1.60it/s]
 50%|████▉     | 28574/57600 [4:59:46<5:13:34,  1.54it/s]
 50%|████▉     | 28575/57600 [4:59:46<5:12:50,  1.55it/s]
 50%|████▉     | 28576/57600 [4:59:47<5:08:02,  1.57it/s]
 50%|████▉     | 28577/57600 [4:59:48<5:16:37,  1.53it/s]
 50%|████▉     | 28578/57600 [4:59:48<5:09:27,  1.56it/s]
 50%|████▉     | 28579/57600 [4:59:49<5:04:01,  1.59it/s]
 50%|████▉     | 28580/57600 [4:59:50<5:13:38,  1.54it/s]
                                                         
{'loss': 1.1696, 'learning_rate': 5.550174216027875e-07, 'epoch': 315.45}

 50%|████▉     | 28580/57600 [4:59:50<5:13:38,  1.54it/s]
 50%|████▉     | 28581/57600 [4:59:50<5:06:58,  1.58it/s]
 50%|████▉     | 28582/57600 [4:59:51<5:00:06,  1.61it/s]
 50%|████▉     | 28583/57600 [4:59:51<5:05:20,  1.58it/s]
 50%|████▉     | 28584/57600 [4:59:52<5:08:08,  1.57it/s]
 50%|████▉     | 28585/57600 [4:59:53<5:04:37,  1.59it/s]
 50%|████▉     | 28586/57600 [4:59:53<4:57:18,  1.63it/s]
 50%|████▉     | 28587/57600 [4:59:54<4:56:40,  1.63it/s]
 50%|████▉     | 28588/57600 [4:59:54<4:52:52,  1.65it/s]
 50%|████▉     | 28589/57600 [4:59:55<4:57:42,  1.62it/s]
 50%|████▉     | 28590/57600 [4:59:56<5:09:30,  1.56it/s]
 50%|████▉     | 28591/57600 [4:59:56<5:02:23,  1.60it/s]
 50%|████▉     | 28592/57600 [4:59:57<4:54:23,  1.64it/s]
 50%|████▉     | 28593/57600 [4:59:58<4:56:32,  1.63it/s]
 50%|████▉     | 28594/57600 [4:59:58<4:55:54,  1.63it/s]
 50%|████▉     | 28595/57600 [4:59:59<4:53:02,  1.65it/s]
 50%|████▉     | 28596/57600 [4:59:59<4:52:45,  1.65it/s]
 50%|████▉     | 28597/57600 [5:00:00<4:55:27,  1.64it/s]
 50%|████▉     | 28598/57600 [5:00:01<4:49:57,  1.67it/s]
 50%|████▉     | 28599/57600 [5:00:01<4:57:32,  1.62it/s]
 50%|████▉     | 28600/57600 [5:00:02<4:59:07,  1.62it/s]
                                                         
{'loss': 1.1773, 'learning_rate': 5.547038327526132e-07, 'epoch': 315.67}

 50%|████▉     | 28600/57600 [5:00:02<4:59:07,  1.62it/s]
 50%|████▉     | 28601/57600 [5:00:02<4:58:25,  1.62it/s]
 50%|████▉     | 28602/57600 [5:00:03<4:48:08,  1.68it/s]
 50%|████▉     | 28603/57600 [5:00:04<4:44:36,  1.70it/s]
 50%|████▉     | 28604/57600 [5:00:04<4:54:39,  1.64it/s]
 50%|████▉     | 28605/57600 [5:00:05<4:53:35,  1.65it/s]
 50%|████▉     | 28606/57600 [5:00:05<4:52:41,  1.65it/s]
 50%|████▉     | 28607/57600 [5:00:06<4:56:18,  1.63it/s]
 50%|████▉     | 28608/57600 [5:00:07<4:55:01,  1.64it/s]
 50%|████▉     | 28609/57600 [5:00:07<4:50:51,  1.66it/s]
 50%|████▉     | 28610/57600 [5:00:08<4:47:12,  1.68it/s]
 50%|████▉     | 28611/57600 [5:00:08<4:44:13,  1.70it/s]
 50%|████▉     | 28612/57600 [5:00:09<4:52:23,  1.65it/s]
 50%|████▉     | 28613/57600 [5:00:10<5:00:17,  1.61it/s]
 50%|████▉     | 28614/57600 [5:00:10<5:08:32,  1.57it/s]
 50%|████▉     | 28615/57600 [5:00:11<5:02:07,  1.60it/s]
 50%|████▉     | 28616/57600 [5:00:12<4:59:49,  1.61it/s]
 50%|████▉     | 28617/57600 [5:00:12<4:58:54,  1.62it/s]
 50%|████▉     | 28618/57600 [5:00:13<5:06:47,  1.57it/s]
 50%|████▉     | 28619/57600 [5:00:14<5:14:45,  1.53it/s]
 50%|████▉     | 28620/57600 [5:00:14<5:06:15,  1.58it/s]
                                                         
{'loss': 1.1586, 'learning_rate': 5.543902439024391e-07, 'epoch': 315.89}

 50%|████▉     | 28620/57600 [5:00:14<5:06:15,  1.58it/s]
 50%|████▉     | 28621/57600 [5:00:15<5:04:47,  1.58it/s]
 50%|████▉     | 28622/57600 [5:00:15<5:09:23,  1.56it/s]
 50%|████▉     | 28623/57600 [5:00:16<5:21:19,  1.50it/s]
 50%|████▉     | 28624/57600 [5:00:17<5:15:52,  1.53it/s]
 50%|████▉     | 28625/57600 [5:00:17<5:13:03,  1.54it/s]
 50%|████▉     | 28626/57600 [5:00:18<5:12:57,  1.54it/s]
 50%|████▉     | 28627/57600 [5:00:19<5:02:10,  1.60it/s]
 50%|████▉     | 28628/57600 [5:00:19<5:15:32,  1.53it/s]
 50%|████▉     | 28629/57600 [5:00:20<5:04:07,  1.59it/s]
 50%|████▉     | 28630/57600 [5:00:21<5:18:11,  1.52it/s]
 50%|████▉     | 28631/57600 [5:00:21<5:13:41,  1.54it/s]
 50%|████▉     | 28632/57600 [5:00:22<5:12:30,  1.54it/s]
 50%|████▉     | 28633/57600 [5:00:22<5:04:40,  1.58it/s]
 50%|████▉     | 28634/57600 [5:00:23<5:07:31,  1.57it/s]
 50%|████▉     | 28635/57600 [5:00:24<5:03:17,  1.59it/s]
 50%|████▉     | 28636/57600 [5:00:24<5:01:29,  1.60it/s]
 50%|████▉     | 28637/57600 [5:00:25<5:02:54,  1.59it/s]
 50%|████▉     | 28638/57600 [5:00:26<5:08:56,  1.56it/s]
 50%|████▉     | 28639/57600 [5:00:26<5:06:00,  1.58it/s]
 50%|████▉     | 28640/57600 [5:00:27<5:08:45,  1.56it/s]
                                                         
{'loss': 1.1868, 'learning_rate': 5.540766550522647e-07, 'epoch': 316.11}

 50%|████▉     | 28640/57600 [5:00:27<5:08:45,  1.56it/s]
 50%|████▉     | 28641/57600 [5:00:28<4:57:39,  1.62it/s]
 50%|████▉     | 28642/57600 [5:00:28<4:55:55,  1.63it/s]
 50%|████▉     | 28643/57600 [5:00:29<4:57:44,  1.62it/s]
 50%|████▉     | 28644/57600 [5:00:29<5:04:00,  1.59it/s]
 50%|████▉     | 28645/57600 [5:00:30<4:54:53,  1.64it/s]
 50%|████▉     | 28646/57600 [5:00:31<4:50:02,  1.66it/s]
 50%|████▉     | 28647/57600 [5:00:31<4:47:31,  1.68it/s]
 50%|████▉     | 28648/57600 [5:00:32<4:53:33,  1.64it/s]
 50%|████▉     | 28649/57600 [5:00:32<4:55:56,  1.63it/s]
 50%|████▉     | 28650/57600 [5:00:33<4:55:12,  1.63it/s]
 50%|████▉     | 28651/57600 [5:00:34<4:50:02,  1.66it/s]
 50%|████▉     | 28652/57600 [5:00:34<4:45:52,  1.69it/s]
 50%|████▉     | 28653/57600 [5:00:35<4:48:39,  1.67it/s]
 50%|████▉     | 28654/57600 [5:00:35<4:55:46,  1.63it/s]
 50%|████▉     | 28655/57600 [5:00:36<4:49:42,  1.67it/s]
 50%|████▉     | 28656/57600 [5:00:37<5:03:34,  1.59it/s]
 50%|████▉     | 28657/57600 [5:00:37<5:08:02,  1.57it/s]
 50%|████▉     | 28658/57600 [5:00:38<5:03:47,  1.59it/s]
 50%|████▉     | 28659/57600 [5:00:39<5:06:17,  1.57it/s]
 50%|████▉     | 28660/57600 [5:00:39<5:00:08,  1.61it/s]
                                                         
{'loss': 1.1764, 'learning_rate': 5.537630662020906e-07, 'epoch': 316.34}

 50%|████▉     | 28660/57600 [5:00:39<5:00:08,  1.61it/s]
 50%|████▉     | 28661/57600 [5:00:40<4:54:32,  1.64it/s]
 50%|████▉     | 28662/57600 [5:00:40<4:56:54,  1.62it/s]
 50%|████▉     | 28663/57600 [5:00:41<4:53:00,  1.65it/s]
 50%|████▉     | 28664/57600 [5:00:42<4:52:10,  1.65it/s]
 50%|████▉     | 28665/57600 [5:00:42<4:59:10,  1.61it/s]
 50%|████▉     | 28666/57600 [5:00:43<4:49:59,  1.66it/s]
 50%|████▉     | 28667/57600 [5:00:43<4:59:07,  1.61it/s]
 50%|████▉     | 28668/57600 [5:00:44<5:06:20,  1.57it/s]
 50%|████▉     | 28669/57600 [5:00:45<5:03:53,  1.59it/s]
 50%|████▉     | 28670/57600 [5:00:45<4:59:21,  1.61it/s]
 50%|████▉     | 28671/57600 [5:00:46<5:05:00,  1.58it/s]
 50%|████▉     | 28672/57600 [5:00:47<5:06:34,  1.57it/s]
 50%|████▉     | 28673/57600 [5:00:47<5:04:23,  1.58it/s]
 50%|████▉     | 28674/57600 [5:00:48<5:06:59,  1.57it/s]
 50%|████▉     | 28675/57600 [5:00:48<4:57:47,  1.62it/s]
 50%|████▉     | 28676/57600 [5:00:49<4:58:41,  1.61it/s]
 50%|████▉     | 28677/57600 [5:00:50<5:05:38,  1.58it/s]
 50%|████▉     | 28678/57600 [5:00:50<5:14:32,  1.53it/s]
 50%|████▉     | 28679/57600 [5:00:51<5:14:25,  1.53it/s]
 50%|████▉     | 28680/57600 [5:00:52<5:12:34,  1.54it/s]
                                                         
{'loss': 1.1469, 'learning_rate': 5.534494773519165e-07, 'epoch': 316.56}

 50%|████▉     | 28680/57600 [5:00:52<5:12:34,  1.54it/s]
 50%|████▉     | 28681/57600 [5:00:52<5:02:30,  1.59it/s]
 50%|████▉     | 28682/57600 [5:00:53<5:11:17,  1.55it/s]
 50%|████▉     | 28683/57600 [5:00:54<5:07:28,  1.57it/s]
 50%|████▉     | 28684/57600 [5:00:54<5:06:28,  1.57it/s]
 50%|████▉     | 28685/57600 [5:00:55<5:08:42,  1.56it/s]
 50%|████▉     | 28686/57600 [5:00:56<5:02:44,  1.59it/s]
 50%|████▉     | 28687/57600 [5:00:56<4:55:51,  1.63it/s]
 50%|████▉     | 28688/57600 [5:00:57<4:49:22,  1.67it/s]
 50%|████▉     | 28689/57600 [5:00:57<4:48:39,  1.67it/s]
 50%|████▉     | 28690/57600 [5:00:58<4:49:06,  1.67it/s]
 50%|████▉     | 28691/57600 [5:00:59<4:59:29,  1.61it/s]
 50%|████▉     | 28692/57600 [5:00:59<5:01:29,  1.60it/s]
 50%|████▉     | 28693/57600 [5:01:00<5:04:47,  1.58it/s]
 50%|████▉     | 28694/57600 [5:01:00<5:03:07,  1.59it/s]
 50%|████▉     | 28695/57600 [5:01:01<4:53:17,  1.64it/s]
 50%|████▉     | 28696/57600 [5:01:02<4:58:19,  1.61it/s]
 50%|████▉     | 28697/57600 [5:01:02<5:02:20,  1.59it/s]
 50%|████▉     | 28698/57600 [5:01:03<4:54:33,  1.64it/s]
 50%|████▉     | 28699/57600 [5:01:04<4:58:10,  1.62it/s]
 50%|████▉     | 28700/57600 [5:01:04<4:52:56,  1.64it/s]
                                                         
{'loss': 1.1953, 'learning_rate': 5.531358885017421e-07, 'epoch': 316.78}

 50%|████▉     | 28700/57600 [5:01:04<4:52:56,  1.64it/s]
 50%|████▉     | 28701/57600 [5:01:05<5:03:43,  1.59it/s]
 50%|████▉     | 28702/57600 [5:01:05<5:01:08,  1.60it/s]
 50%|████▉     | 28703/57600 [5:01:06<5:10:16,  1.55it/s]
 50%|████▉     | 28704/57600 [5:01:07<5:03:54,  1.58it/s]
 50%|████▉     | 28705/57600 [5:01:07<5:05:53,  1.57it/s]
 50%|████▉     | 28706/57600 [5:01:08<4:58:23,  1.61it/s]
 50%|████▉     | 28707/57600 [5:01:09<4:56:30,  1.62it/s]
 50%|████▉     | 28708/57600 [5:01:09<4:55:16,  1.63it/s]
 50%|████▉     | 28709/57600 [5:01:10<4:47:40,  1.67it/s]
 50%|████▉     | 28710/57600 [5:01:10<4:45:05,  1.69it/s]
 50%|████▉     | 28711/57600 [5:01:11<5:10:56,  1.55it/s]
 50%|████▉     | 28712/57600 [5:01:12<5:04:11,  1.58it/s]
 50%|████▉     | 28713/57600 [5:01:12<5:10:42,  1.55it/s]
 50%|████▉     | 28714/57600 [5:01:13<5:10:44,  1.55it/s]
 50%|████▉     | 28715/57600 [5:01:14<5:16:20,  1.52it/s]
 50%|████▉     | 28716/57600 [5:01:14<5:11:34,  1.55it/s]
 50%|████▉     | 28717/57600 [5:01:15<4:59:44,  1.61it/s]
 50%|████▉     | 28718/57600 [5:01:15<4:57:04,  1.62it/s]
 50%|████▉     | 28719/57600 [5:01:16<4:51:02,  1.65it/s]
 50%|████▉     | 28720/57600 [5:01:17<4:50:58,  1.65it/s]
                                                         
{'loss': 1.1843, 'learning_rate': 5.528222996515679e-07, 'epoch': 317.0}

 50%|████▉     | 28720/57600 [5:01:17<4:50:58,  1.65it/s]
 50%|████▉     | 28721/57600 [5:01:17<5:04:12,  1.58it/s]
 50%|████▉     | 28722/57600 [5:01:18<4:56:29,  1.62it/s]
 50%|████▉     | 28723/57600 [5:01:19<4:59:05,  1.61it/s]
 50%|████▉     | 28724/57600 [5:01:19<4:56:15,  1.62it/s]
 50%|████▉     | 28725/57600 [5:01:20<5:00:59,  1.60it/s]
 50%|████▉     | 28726/57600 [5:01:20<4:58:05,  1.61it/s]
 50%|████▉     | 28727/57600 [5:01:21<4:50:58,  1.65it/s]
 50%|████▉     | 28728/57600 [5:01:22<4:46:30,  1.68it/s]
 50%|████▉     | 28729/57600 [5:01:22<4:43:32,  1.70it/s]
 50%|████▉     | 28730/57600 [5:01:23<4:46:17,  1.68it/s]
 50%|████▉     | 28731/57600 [5:01:23<4:41:51,  1.71it/s]
 50%|████▉     | 28732/57600 [5:01:24<4:50:48,  1.65it/s]
 50%|████▉     | 28733/57600 [5:01:25<4:49:42,  1.66it/s]
 50%|████▉     | 28734/57600 [5:01:25<5:04:15,  1.58it/s]
 50%|████▉     | 28735/57600 [5:01:26<5:02:20,  1.59it/s]
 50%|████▉     | 28736/57600 [5:01:26<5:02:20,  1.59it/s]
 50%|████▉     | 28737/57600 [5:01:27<4:58:50,  1.61it/s]
 50%|████▉     | 28738/57600 [5:01:28<4:58:57,  1.61it/s]
 50%|████▉     | 28739/57600 [5:01:28<4:53:20,  1.64it/s]
 50%|████▉     | 28740/57600 [5:01:29<4:54:26,  1.63it/s]
                                                         
{'loss': 1.1964, 'learning_rate': 5.525087108013938e-07, 'epoch': 317.22}

 50%|████▉     | 28740/57600 [5:01:29<4:54:26,  1.63it/s]
 50%|████▉     | 28741/57600 [5:01:30<4:51:45,  1.65it/s]
 50%|████▉     | 28742/57600 [5:01:30<4:57:03,  1.62it/s]
 50%|████▉     | 28743/57600 [5:01:31<5:13:39,  1.53it/s]
 50%|████▉     | 28744/57600 [5:01:31<4:59:42,  1.60it/s]
 50%|████▉     | 28745/57600 [5:01:32<5:02:57,  1.59it/s]
 50%|████▉     | 28746/57600 [5:01:33<4:53:16,  1.64it/s]
 50%|████▉     | 28747/57600 [5:01:33<4:54:53,  1.63it/s]
 50%|████▉     | 28748/57600 [5:01:34<4:54:01,  1.64it/s]
 50%|████▉     | 28749/57600 [5:01:34<4:49:23,  1.66it/s]
 50%|████▉     | 28750/57600 [5:01:35<4:45:52,  1.68it/s]
 50%|████▉     | 28751/57600 [5:01:36<4:44:34,  1.69it/s]
 50%|████▉     | 28752/57600 [5:01:36<4:59:35,  1.60it/s]
 50%|████▉     | 28753/57600 [5:01:37<4:52:43,  1.64it/s]
 50%|████▉     | 28754/57600 [5:01:37<4:51:13,  1.65it/s]
 50%|████▉     | 28755/57600 [5:01:38<4:44:08,  1.69it/s]
 50%|████▉     | 28756/57600 [5:01:39<4:48:19,  1.67it/s]
 50%|████▉     | 28757/57600 [5:01:39<5:02:50,  1.59it/s]
 50%|████▉     | 28758/57600 [5:01:40<5:25:25,  1.48it/s]
 50%|████▉     | 28759/57600 [5:01:41<5:11:45,  1.54it/s]
 50%|████▉     | 28760/57600 [5:01:41<5:07:13,  1.56it/s]
                                                         
{'loss': 1.203, 'learning_rate': 5.521951219512194e-07, 'epoch': 317.44}

 50%|████▉     | 28760/57600 [5:01:41<5:07:13,  1.56it/s]
 50%|████▉     | 28761/57600 [5:01:42<5:16:29,  1.52it/s]
 50%|████▉     | 28762/57600 [5:01:43<5:06:31,  1.57it/s]
 50%|████▉     | 28763/57600 [5:01:43<5:07:46,  1.56it/s]
 50%|████▉     | 28764/57600 [5:01:44<5:01:35,  1.59it/s]
 50%|████▉     | 28765/57600 [5:01:44<4:59:07,  1.61it/s]
 50%|████▉     | 28766/57600 [5:01:45<4:59:31,  1.60it/s]
 50%|████▉     | 28767/57600 [5:01:46<5:07:02,  1.57it/s]
 50%|████▉     | 28768/57600 [5:01:46<5:03:36,  1.58it/s]
 50%|████▉     | 28769/57600 [5:01:47<5:00:40,  1.60it/s]
 50%|████▉     | 28770/57600 [5:01:48<4:48:34,  1.67it/s]
 50%|████▉     | 28771/57600 [5:01:48<4:48:19,  1.67it/s]
 50%|████▉     | 28772/57600 [5:01:49<4:57:19,  1.62it/s]
 50%|████▉     | 28773/57600 [5:01:49<4:53:52,  1.63it/s]
 50%|████▉     | 28774/57600 [5:01:50<4:53:39,  1.64it/s]
 50%|████▉     | 28775/57600 [5:01:51<4:59:40,  1.60it/s]
 50%|████▉     | 28776/57600 [5:01:51<5:08:14,  1.56it/s]
 50%|████▉     | 28777/57600 [5:01:52<5:08:26,  1.56it/s]
 50%|████▉     | 28778/57600 [5:01:53<4:56:17,  1.62it/s]
 50%|████▉     | 28779/57600 [5:01:53<4:49:29,  1.66it/s]
 50%|████▉     | 28780/57600 [5:01:54<4:46:21,  1.68it/s]
                                                         
{'loss': 1.18, 'learning_rate': 5.518815331010452e-07, 'epoch': 317.66}

 50%|████▉     | 28780/57600 [5:01:54<4:46:21,  1.68it/s]
 50%|████▉     | 28781/57600 [5:01:54<4:52:46,  1.64it/s]
 50%|████▉     | 28782/57600 [5:01:55<5:02:19,  1.59it/s]
 50%|████▉     | 28783/57600 [5:01:56<5:05:27,  1.57it/s]
 50%|████▉     | 28784/57600 [5:01:56<5:16:54,  1.52it/s]
 50%|████▉     | 28785/57600 [5:01:57<5:14:09,  1.53it/s]
 50%|████▉     | 28786/57600 [5:01:58<5:15:23,  1.52it/s]
 50%|████▉     | 28787/57600 [5:01:58<5:05:33,  1.57it/s]
 50%|████▉     | 28788/57600 [5:01:59<5:03:33,  1.58it/s]
 50%|████▉     | 28789/57600 [5:02:00<5:03:55,  1.58it/s]
 50%|████▉     | 28790/57600 [5:02:00<5:08:04,  1.56it/s]
 50%|████▉     | 28791/57600 [5:02:01<4:57:43,  1.61it/s]
 50%|████▉     | 28792/57600 [5:02:01<4:53:24,  1.64it/s]
 50%|████▉     | 28793/57600 [5:02:02<4:52:11,  1.64it/s]
 50%|████▉     | 28794/57600 [5:02:03<5:01:29,  1.59it/s]
 50%|████▉     | 28795/57600 [5:02:03<5:13:05,  1.53it/s]
 50%|████▉     | 28796/57600 [5:02:04<5:01:08,  1.59it/s]
 50%|████▉     | 28797/57600 [5:02:05<4:55:49,  1.62it/s]
 50%|████▉     | 28798/57600 [5:02:05<4:44:26,  1.69it/s]
 50%|████▉     | 28799/57600 [5:02:06<4:42:25,  1.70it/s]
 50%|█████     | 28800/57600 [5:02:06<4:49:53,  1.66it/s]
                                                         
{'loss': 1.194, 'learning_rate': 5.515679442508711e-07, 'epoch': 317.88}

 50%|█████     | 28800/57600 [5:02:06<4:49:53,  1.66it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 11.32it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.28it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.82it/s]

100%|██████████| 6/6 [00:01<00:00,  3.22it/s]{'score': 51.40659903712194, 'counts': [149, 100, 69, 49], 'totals': [212, 182, 152, 123], 'precisions': [70.28301886792453, 54.94505494505494, 45.39473684210526, 39.83739837398374], 'bp': 1.0, 'sys_len': 212, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 1.9817793369293213, 'eval_bleu': 51.4066, 'eval_gen_len': 8.5, 'eval_runtime': 3.2253, 'eval_samples_per_second': 9.302, 'eval_steps_per_second': 1.86, 'epoch': 317.88}

 50%|█████     | 28800/57600 [5:02:10<4:49:53,  1.66it/s]

100%|██████████| 6/6 [00:02<00:00,  3.22it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 11:56:22,847 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 50%|█████     | 28801/57600 [5:02:41<86:45:20, 10.84s/it]
 50%|█████     | 28802/57600 [5:02:42<62:32:05,  7.82s/it]
 50%|█████     | 28803/57600 [5:02:42<45:14:56,  5.66s/it]
 50%|█████     | 28804/57600 [5:02:43<33:10:52,  4.15s/it]
 50%|█████     | 28805/57600 [5:02:44<24:42:39,  3.09s/it]
 50%|█████     | 28806/57600 [5:02:44<18:39:09,  2.33s/it]
 50%|█████     | 28807/57600 [5:02:45<14:35:22,  1.82s/it]
 50%|█████     | 28808/57600 [5:02:45<11:43:31,  1.47s/it]
 50%|█████     | 28809/57600 [5:02:46<9:40:20,  1.21s/it] 
 50%|█████     | 28810/57600 [5:02:47<8:11:47,  1.02s/it]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 50%|█████     | 28811/57600 [5:02:47<7:28:25,  1.07it/s]
 50%|█████     | 28812/57600 [5:02:48<6:53:33,  1.16it/s]
 50%|█████     | 28813/57600 [5:02:49<6:11:31,  1.29it/s]
 50%|█████     | 28814/57600 [5:02:49<5:58:47,  1.34it/s]
 50%|█████     | 28815/57600 [5:02:50<5:50:12,  1.37it/s]
 50%|█████     | 28816/57600 [5:02:51<5:39:09,  1.41it/s]
 50%|█████     | 28817/57600 [5:02:51<5:43:09,  1.40it/s]
 50%|█████     | 28818/57600 [5:02:52<5:35:57,  1.43it/s]
 50%|█████     | 28819/57600 [5:02:53<5:30:25,  1.45it/s]
 50%|█████     | 28820/57600 [5:02:53<5:17:08,  1.51it/s]
                                                         
{'loss': 1.234, 'learning_rate': 5.512543554006968e-07, 'epoch': 318.1}

 50%|█████     | 28820/57600 [5:02:53<5:17:08,  1.51it/s]
 50%|█████     | 28821/57600 [5:02:54<5:20:31,  1.50it/s]
 50%|█████     | 28822/57600 [5:02:55<5:10:26,  1.55it/s]
 50%|█████     | 28823/57600 [5:02:55<5:10:42,  1.54it/s]
 50%|█████     | 28824/57600 [5:02:56<5:11:57,  1.54it/s]
 50%|█████     | 28825/57600 [5:02:57<5:11:53,  1.54it/s]
 50%|█████     | 28826/57600 [5:02:57<5:19:45,  1.50it/s]
 50%|█████     | 28827/57600 [5:02:58<5:21:37,  1.49it/s]
 50%|█████     | 28828/57600 [5:02:59<5:10:05,  1.55it/s]
 50%|█████     | 28829/57600 [5:02:59<5:16:08,  1.52it/s]
 50%|█████     | 28830/57600 [5:03:00<5:17:45,  1.51it/s]
 50%|█████     | 28831/57600 [5:03:01<5:10:05,  1.55it/s]
 50%|█████     | 28832/57600 [5:03:01<5:11:33,  1.54it/s]
 50%|█████     | 28833/57600 [5:03:02<5:15:12,  1.52it/s]
 50%|█████     | 28834/57600 [5:03:02<5:06:51,  1.56it/s]
 50%|█████     | 28835/57600 [5:03:03<5:21:40,  1.49it/s]
 50%|█████     | 28836/57600 [5:03:04<5:35:40,  1.43it/s]
 50%|█████     | 28837/57600 [5:03:05<5:35:14,  1.43it/s]
 50%|█████     | 28838/57600 [5:03:05<5:28:35,  1.46it/s]
 50%|█████     | 28839/57600 [5:03:06<5:25:28,  1.47it/s]
 50%|█████     | 28840/57600 [5:03:07<5:23:07,  1.48it/s]
                                                         
{'loss': 1.1729, 'learning_rate': 5.509407665505227e-07, 'epoch': 318.32}

 50%|█████     | 28840/57600 [5:03:07<5:23:07,  1.48it/s]
 50%|█████     | 28841/57600 [5:03:07<5:24:16,  1.48it/s]
 50%|█████     | 28842/57600 [5:03:08<5:18:11,  1.51it/s]
 50%|█████     | 28843/57600 [5:03:09<5:14:57,  1.52it/s]
 50%|█████     | 28844/57600 [5:03:09<5:21:39,  1.49it/s]
 50%|█████     | 28845/57600 [5:03:10<5:15:40,  1.52it/s]
 50%|█████     | 28846/57600 [5:03:11<5:17:06,  1.51it/s]
 50%|█████     | 28847/57600 [5:03:11<5:25:01,  1.47it/s]
 50%|█████     | 28848/57600 [5:03:12<5:30:28,  1.45it/s]
 50%|█████     | 28849/57600 [5:03:13<5:28:16,  1.46it/s]
 50%|█████     | 28850/57600 [5:03:13<5:19:12,  1.50it/s]
 50%|█████     | 28851/57600 [5:03:14<5:13:52,  1.53it/s]
 50%|█████     | 28852/57600 [5:03:15<5:20:52,  1.49it/s]
 50%|█████     | 28853/57600 [5:03:15<5:18:21,  1.50it/s]
 50%|█████     | 28854/57600 [5:03:16<5:22:54,  1.48it/s]
 50%|█████     | 28855/57600 [5:03:17<5:21:59,  1.49it/s]
 50%|█████     | 28856/57600 [5:03:17<5:31:13,  1.45it/s]
 50%|█████     | 28857/57600 [5:03:18<5:31:13,  1.45it/s]
 50%|█████     | 28858/57600 [5:03:19<5:24:05,  1.48it/s]
 50%|█████     | 28859/57600 [5:03:19<5:22:29,  1.49it/s]
 50%|█████     | 28860/57600 [5:03:20<5:32:10,  1.44it/s]
                                                         
{'loss': 1.2175, 'learning_rate': 5.506271777003484e-07, 'epoch': 318.54}

 50%|█████     | 28860/57600 [5:03:20<5:32:10,  1.44it/s]
 50%|█████     | 28861/57600 [5:03:21<5:32:25,  1.44it/s]
 50%|█████     | 28862/57600 [5:03:22<5:35:09,  1.43it/s]
 50%|█████     | 28863/57600 [5:03:22<5:28:41,  1.46it/s]
 50%|█████     | 28864/57600 [5:03:23<5:22:01,  1.49it/s]
 50%|█████     | 28865/57600 [5:03:24<5:17:35,  1.51it/s]
 50%|█████     | 28866/57600 [5:03:24<5:11:28,  1.54it/s]
 50%|█████     | 28867/57600 [5:03:25<5:07:48,  1.56it/s]
 50%|█████     | 28868/57600 [5:03:25<5:08:38,  1.55it/s]
 50%|█████     | 28869/57600 [5:03:26<5:06:39,  1.56it/s]
 50%|█████     | 28870/57600 [5:03:27<5:07:10,  1.56it/s]
 50%|█████     | 28871/57600 [5:03:27<5:06:18,  1.56it/s]
 50%|█████     | 28872/57600 [5:03:28<5:10:17,  1.54it/s]
 50%|█████     | 28873/57600 [5:03:29<5:07:45,  1.56it/s]
 50%|█████     | 28874/57600 [5:03:29<5:03:42,  1.58it/s]
 50%|█████     | 28875/57600 [5:03:30<5:19:30,  1.50it/s]
 50%|█████     | 28876/57600 [5:03:31<5:23:54,  1.48it/s]
 50%|█████     | 28877/57600 [5:03:31<5:07:29,  1.56it/s]
 50%|█████     | 28878/57600 [5:03:32<5:03:44,  1.58it/s]
 50%|█████     | 28879/57600 [5:03:33<5:09:13,  1.55it/s]
 50%|█████     | 28880/57600 [5:03:33<5:07:11,  1.56it/s]
                                                         
{'loss': 1.2113, 'learning_rate': 5.503135888501742e-07, 'epoch': 318.76}

 50%|█████     | 28880/57600 [5:03:33<5:07:11,  1.56it/s]
 50%|█████     | 28881/57600 [5:03:34<5:11:33,  1.54it/s]
 50%|█████     | 28882/57600 [5:03:34<4:59:04,  1.60it/s]
 50%|█████     | 28883/57600 [5:03:35<4:53:57,  1.63it/s]
 50%|█████     | 28884/57600 [5:03:36<4:50:11,  1.65it/s]
 50%|█████     | 28885/57600 [5:03:36<4:58:32,  1.60it/s]
 50%|█████     | 28886/57600 [5:03:37<5:06:15,  1.56it/s]
 50%|█████     | 28887/57600 [5:03:38<5:03:10,  1.58it/s]
 50%|█████     | 28888/57600 [5:03:38<4:57:19,  1.61it/s]
 50%|█████     | 28889/57600 [5:03:39<5:00:32,  1.59it/s]
 50%|█████     | 28890/57600 [5:03:39<4:51:53,  1.64it/s]
 50%|█████     | 28891/57600 [5:03:40<4:51:57,  1.64it/s]
 50%|█████     | 28892/57600 [5:03:41<4:56:42,  1.61it/s]
 50%|█████     | 28893/57600 [5:03:41<5:00:49,  1.59it/s]
 50%|█████     | 28894/57600 [5:03:42<5:05:09,  1.57it/s]
 50%|█████     | 28895/57600 [5:03:43<5:03:57,  1.57it/s]
 50%|█████     | 28896/57600 [5:03:43<5:13:17,  1.53it/s]
 50%|█████     | 28897/57600 [5:03:44<5:10:38,  1.54it/s]
 50%|█████     | 28898/57600 [5:03:45<5:11:49,  1.53it/s]
 50%|█████     | 28899/57600 [5:03:45<5:15:53,  1.51it/s]
 50%|█████     | 28900/57600 [5:03:46<5:17:36,  1.51it/s]
                                                         
{'loss': 1.1887, 'learning_rate': 5.5e-07, 'epoch': 318.98}

 50%|█████     | 28900/57600 [5:03:46<5:17:36,  1.51it/s]
 50%|█████     | 28901/57600 [5:03:46<5:12:11,  1.53it/s]
 50%|█████     | 28902/57600 [5:03:47<5:24:21,  1.47it/s]
 50%|█████     | 28903/57600 [5:03:48<5:22:39,  1.48it/s]
 50%|█████     | 28904/57600 [5:03:49<5:23:34,  1.48it/s]
 50%|█████     | 28905/57600 [5:03:49<5:20:46,  1.49it/s]
 50%|█████     | 28906/57600 [5:03:50<5:25:43,  1.47it/s]
 50%|█████     | 28907/57600 [5:03:51<5:24:20,  1.47it/s]
 50%|█████     | 28908/57600 [5:03:51<5:22:27,  1.48it/s]
 50%|█████     | 28909/57600 [5:03:52<5:14:51,  1.52it/s]
 50%|█████     | 28910/57600 [5:03:53<5:08:36,  1.55it/s]
 50%|█████     | 28911/57600 [5:03:53<5:12:57,  1.53it/s]
 50%|█████     | 28912/57600 [5:03:54<5:16:11,  1.51it/s]
 50%|█████     | 28913/57600 [5:03:54<5:11:49,  1.53it/s]
 50%|█████     | 28914/57600 [5:03:55<5:20:55,  1.49it/s]
 50%|█████     | 28915/57600 [5:03:56<5:09:45,  1.54it/s]
 50%|█████     | 28916/57600 [5:03:56<5:10:31,  1.54it/s]
 50%|█████     | 28917/57600 [5:03:57<5:07:22,  1.56it/s]
 50%|█████     | 28918/57600 [5:03:58<5:04:57,  1.57it/s]
 50%|█████     | 28919/57600 [5:03:58<5:06:46,  1.56it/s]
 50%|█████     | 28920/57600 [5:03:59<5:15:20,  1.52it/s]
                                                         
{'loss': 1.1669, 'learning_rate': 5.496864111498259e-07, 'epoch': 319.21}

 50%|█████     | 28920/57600 [5:03:59<5:15:20,  1.52it/s]
 50%|█████     | 28921/57600 [5:04:00<5:06:07,  1.56it/s]
 50%|█████     | 28922/57600 [5:04:00<5:08:57,  1.55it/s]
 50%|█████     | 28923/57600 [5:04:01<5:02:01,  1.58it/s]
 50%|█████     | 28924/57600 [5:04:02<5:07:44,  1.55it/s]
 50%|█████     | 28925/57600 [5:04:02<5:16:16,  1.51it/s]
 50%|█████     | 28926/57600 [5:04:03<5:21:57,  1.48it/s]
 50%|█████     | 28927/57600 [5:04:04<5:26:38,  1.46it/s]
 50%|█████     | 28928/57600 [5:04:04<5:23:51,  1.48it/s]
 50%|█████     | 28929/57600 [5:04:05<5:19:23,  1.50it/s]
 50%|█████     | 28930/57600 [5:04:06<5:14:35,  1.52it/s]
 50%|█████     | 28931/57600 [5:04:06<5:24:52,  1.47it/s]
 50%|█████     | 28932/57600 [5:04:07<5:20:00,  1.49it/s]
 50%|█████     | 28933/57600 [5:04:08<5:16:34,  1.51it/s]
 50%|█████     | 28934/57600 [5:04:08<5:13:14,  1.53it/s]
 50%|█████     | 28935/57600 [5:04:09<5:07:54,  1.55it/s]
 50%|█████     | 28936/57600 [5:04:10<5:04:29,  1.57it/s]
 50%|█████     | 28937/57600 [5:04:10<5:06:56,  1.56it/s]
 50%|█████     | 28938/57600 [5:04:11<5:01:26,  1.58it/s]
 50%|█████     | 28939/57600 [5:04:11<4:59:27,  1.60it/s]
 50%|█████     | 28940/57600 [5:04:12<5:17:41,  1.50it/s]
                                                         
{'loss': 1.1865, 'learning_rate': 5.493728222996515e-07, 'epoch': 319.43}

 50%|█████     | 28940/57600 [5:04:12<5:17:41,  1.50it/s]
 50%|█████     | 28941/57600 [5:04:13<5:19:54,  1.49it/s]
 50%|█████     | 28942/57600 [5:04:13<5:10:50,  1.54it/s]
 50%|█████     | 28943/57600 [5:04:14<5:20:07,  1.49it/s]
 50%|█████     | 28944/57600 [5:04:15<5:20:21,  1.49it/s]
 50%|█████     | 28945/57600 [5:04:16<5:28:41,  1.45it/s]
 50%|█████     | 28946/57600 [5:04:16<5:23:58,  1.47it/s]
 50%|█████     | 28947/57600 [5:04:17<5:17:05,  1.51it/s]
 50%|█████     | 28948/57600 [5:04:18<5:20:55,  1.49it/s]
 50%|█████     | 28949/57600 [5:04:18<5:27:45,  1.46it/s]
 50%|█████     | 28950/57600 [5:04:19<5:30:49,  1.44it/s]
 50%|█████     | 28951/57600 [5:04:20<5:16:29,  1.51it/s]
 50%|█████     | 28952/57600 [5:04:20<5:04:18,  1.57it/s]
 50%|█████     | 28953/57600 [5:04:21<5:03:19,  1.57it/s]
 50%|█████     | 28954/57600 [5:04:21<5:11:21,  1.53it/s]
 50%|█████     | 28955/57600 [5:04:22<5:09:51,  1.54it/s]
 50%|█████     | 28956/57600 [5:04:23<5:08:08,  1.55it/s]
 50%|█████     | 28957/57600 [5:04:23<5:08:58,  1.55it/s]
 50%|█████     | 28958/57600 [5:04:24<5:10:21,  1.54it/s]
 50%|█████     | 28959/57600 [5:04:25<5:01:22,  1.58it/s]
 50%|█████     | 28960/57600 [5:04:25<4:56:16,  1.61it/s]
                                                         
{'loss': 1.2081, 'learning_rate': 5.490592334494774e-07, 'epoch': 319.65}

 50%|█████     | 28960/57600 [5:04:25<4:56:16,  1.61it/s]
 50%|█████     | 28961/57600 [5:04:26<5:06:55,  1.56it/s]
 50%|█████     | 28962/57600 [5:04:27<5:13:58,  1.52it/s]
 50%|█████     | 28963/57600 [5:04:27<5:13:29,  1.52it/s]
 50%|█████     | 28964/57600 [5:04:28<5:10:13,  1.54it/s]
 50%|█████     | 28965/57600 [5:04:29<5:09:11,  1.54it/s]
 50%|█████     | 28966/57600 [5:04:29<4:59:02,  1.60it/s]
 50%|█████     | 28967/57600 [5:04:30<5:01:11,  1.58it/s]
 50%|█████     | 28968/57600 [5:04:30<5:10:57,  1.53it/s]
 50%|█████     | 28969/57600 [5:04:31<4:57:54,  1.60it/s]
 50%|█████     | 28970/57600 [5:04:32<5:00:19,  1.59it/s]
 50%|█████     | 28971/57600 [5:04:32<4:58:39,  1.60it/s]
 50%|█████     | 28972/57600 [5:04:33<4:57:19,  1.60it/s]
 50%|█████     | 28973/57600 [5:04:34<5:06:36,  1.56it/s]
 50%|█████     | 28974/57600 [5:04:34<5:13:55,  1.52it/s]
 50%|█████     | 28975/57600 [5:04:35<5:18:48,  1.50it/s]
 50%|█████     | 28976/57600 [5:04:36<5:18:20,  1.50it/s]
 50%|█████     | 28977/57600 [5:04:36<5:18:19,  1.50it/s]
 50%|█████     | 28978/57600 [5:04:37<5:10:21,  1.54it/s]
 50%|█████     | 28979/57600 [5:04:38<5:09:43,  1.54it/s]
 50%|█████     | 28980/57600 [5:04:38<5:09:57,  1.54it/s]
                                                         
{'loss': 1.19, 'learning_rate': 5.48745644599303e-07, 'epoch': 319.87}

 50%|█████     | 28980/57600 [5:04:38<5:09:57,  1.54it/s]
 50%|█████     | 28981/57600 [5:04:39<5:13:05,  1.52it/s]
 50%|█████     | 28982/57600 [5:04:40<5:21:50,  1.48it/s]
 50%|█████     | 28983/57600 [5:04:40<5:16:05,  1.51it/s]
 50%|█████     | 28984/57600 [5:04:41<5:14:04,  1.52it/s]
 50%|█████     | 28985/57600 [5:04:42<5:09:57,  1.54it/s]
 50%|█████     | 28986/57600 [5:04:42<5:07:05,  1.55it/s]
 50%|█████     | 28987/57600 [5:04:43<5:09:27,  1.54it/s]
 50%|█████     | 28988/57600 [5:04:43<5:09:52,  1.54it/s]
 50%|█████     | 28989/57600 [5:04:44<4:59:12,  1.59it/s]
 50%|█████     | 28990/57600 [5:04:45<4:56:21,  1.61it/s]
 50%|█████     | 28991/57600 [5:04:45<4:59:32,  1.59it/s]
 50%|█████     | 28992/57600 [5:04:46<5:04:38,  1.57it/s]
 50%|█████     | 28993/57600 [5:04:47<5:26:54,  1.46it/s]
 50%|█████     | 28994/57600 [5:04:47<5:23:25,  1.47it/s]
 50%|█████     | 28995/57600 [5:04:48<5:12:03,  1.53it/s]
 50%|█████     | 28996/57600 [5:04:49<5:04:50,  1.56it/s]
 50%|█████     | 28997/57600 [5:04:49<5:05:54,  1.56it/s]
 50%|█████     | 28998/57600 [5:04:50<5:04:06,  1.57it/s]
 50%|█████     | 28999/57600 [5:04:51<5:12:22,  1.53it/s]
 50%|█████     | 29000/57600 [5:04:51<5:01:56,  1.58it/s]
                                                         
{'loss': 1.1859, 'learning_rate': 5.484320557491289e-07, 'epoch': 320.09}

 50%|█████     | 29000/57600 [5:04:51<5:01:56,  1.58it/s]
 50%|█████     | 29001/57600 [5:04:52<5:02:04,  1.58it/s]
 50%|█████     | 29002/57600 [5:04:52<5:06:06,  1.56it/s]
 50%|█████     | 29003/57600 [5:04:53<4:59:36,  1.59it/s]
 50%|█████     | 29004/57600 [5:04:54<4:54:30,  1.62it/s]
 50%|█████     | 29005/57600 [5:04:54<4:53:56,  1.62it/s]
 50%|█████     | 29006/57600 [5:04:55<4:59:14,  1.59it/s]
 50%|█████     | 29007/57600 [5:04:56<5:13:37,  1.52it/s]
 50%|█████     | 29008/57600 [5:04:56<5:24:32,  1.47it/s]
 50%|█████     | 29009/57600 [5:04:57<5:17:45,  1.50it/s]
 50%|█████     | 29010/57600 [5:04:58<5:12:54,  1.52it/s]
 50%|█████     | 29011/57600 [5:04:58<5:02:22,  1.58it/s]
 50%|█████     | 29012/57600 [5:04:59<5:02:26,  1.58it/s]
 50%|█████     | 29013/57600 [5:04:59<4:55:54,  1.61it/s]
 50%|█████     | 29014/57600 [5:05:00<4:56:02,  1.61it/s]
 50%|█████     | 29015/57600 [5:05:01<4:51:02,  1.64it/s]
 50%|█████     | 29016/57600 [5:05:01<4:58:30,  1.60it/s]
 50%|█████     | 29017/57600 [5:05:02<5:06:18,  1.56it/s]
 50%|█████     | 29018/57600 [5:05:03<4:56:24,  1.61it/s]
 50%|█████     | 29019/57600 [5:05:03<4:57:07,  1.60it/s]
 50%|█████     | 29020/57600 [5:05:04<4:49:03,  1.65it/s]
                                                         
{'loss': 1.1067, 'learning_rate': 5.481184668989546e-07, 'epoch': 320.31}

 50%|█████     | 29020/57600 [5:05:04<4:49:03,  1.65it/s]
 50%|█████     | 29021/57600 [5:05:04<5:01:08,  1.58it/s]
 50%|█████     | 29022/57600 [5:05:05<5:03:33,  1.57it/s]
 50%|█████     | 29023/57600 [5:05:06<5:02:43,  1.57it/s]
 50%|█████     | 29024/57600 [5:05:06<5:01:09,  1.58it/s]
 50%|█████     | 29025/57600 [5:05:07<4:51:34,  1.63it/s]
 50%|█████     | 29026/57600 [5:05:08<4:42:55,  1.68it/s]
 50%|█████     | 29027/57600 [5:05:08<4:46:59,  1.66it/s]
 50%|█████     | 29028/57600 [5:05:09<4:43:15,  1.68it/s]
 50%|█████     | 29029/57600 [5:05:09<4:48:40,  1.65it/s]
 50%|█████     | 29030/57600 [5:05:10<4:41:32,  1.69it/s]
 50%|█████     | 29031/57600 [5:05:10<4:38:13,  1.71it/s]
 50%|█████     | 29032/57600 [5:05:11<4:38:42,  1.71it/s]
 50%|█████     | 29033/57600 [5:05:12<4:42:47,  1.68it/s]
 50%|█████     | 29034/57600 [5:05:12<4:53:01,  1.62it/s]
 50%|█████     | 29035/57600 [5:05:13<5:02:15,  1.58it/s]
 50%|█████     | 29036/57600 [5:05:14<4:59:23,  1.59it/s]
 50%|█████     | 29037/57600 [5:05:14<4:53:46,  1.62it/s]
 50%|█████     | 29038/57600 [5:05:15<4:49:09,  1.65it/s]
 50%|█████     | 29039/57600 [5:05:15<5:00:22,  1.58it/s]
 50%|█████     | 29040/57600 [5:05:16<5:08:12,  1.54it/s]
                                                         
{'loss': 1.1809, 'learning_rate': 5.478048780487804e-07, 'epoch': 320.53}

 50%|█████     | 29040/57600 [5:05:16<5:08:12,  1.54it/s]
 50%|█████     | 29041/57600 [5:05:17<5:05:16,  1.56it/s]
 50%|█████     | 29042/57600 [5:05:17<4:58:09,  1.60it/s]
 50%|█████     | 29043/57600 [5:05:18<4:51:59,  1.63it/s]
 50%|█████     | 29044/57600 [5:05:19<4:51:05,  1.63it/s]
 50%|█████     | 29045/57600 [5:05:19<4:43:29,  1.68it/s]
 50%|█████     | 29046/57600 [5:05:20<4:40:24,  1.70it/s]
 50%|█████     | 29047/57600 [5:05:20<4:42:54,  1.68it/s]
 50%|█████     | 29048/57600 [5:05:21<4:49:57,  1.64it/s]
 50%|█████     | 29049/57600 [5:05:22<4:43:35,  1.68it/s]
 50%|█████     | 29050/57600 [5:05:22<4:44:05,  1.67it/s]
 50%|█████     | 29051/57600 [5:05:23<4:46:33,  1.66it/s]
 50%|█████     | 29052/57600 [5:05:23<4:48:41,  1.65it/s]
 50%|█████     | 29053/57600 [5:05:24<4:57:12,  1.60it/s]
 50%|█████     | 29054/57600 [5:05:25<4:57:32,  1.60it/s]
 50%|█████     | 29055/57600 [5:05:25<5:03:19,  1.57it/s]
 50%|█████     | 29056/57600 [5:05:26<5:02:20,  1.57it/s]
 50%|█████     | 29057/57600 [5:05:27<5:01:29,  1.58it/s]
 50%|█████     | 29058/57600 [5:05:27<5:06:24,  1.55it/s]
 50%|█████     | 29059/57600 [5:05:28<5:18:12,  1.49it/s]
 50%|█████     | 29060/57600 [5:05:29<5:20:47,  1.48it/s]
                                                         
{'loss': 1.1919, 'learning_rate': 5.474912891986063e-07, 'epoch': 320.75}

 50%|█████     | 29060/57600 [5:05:29<5:20:47,  1.48it/s]
 50%|█████     | 29061/57600 [5:05:29<5:08:43,  1.54it/s]
 50%|█████     | 29062/57600 [5:05:30<5:05:10,  1.56it/s]
 50%|█████     | 29063/57600 [5:05:30<4:55:16,  1.61it/s]
 50%|█████     | 29064/57600 [5:05:31<4:49:25,  1.64it/s]
 50%|█████     | 29065/57600 [5:05:32<4:46:47,  1.66it/s]
 50%|█████     | 29066/57600 [5:05:32<4:51:01,  1.63it/s]
 50%|█████     | 29067/57600 [5:05:33<4:47:46,  1.65it/s]
 50%|█████     | 29068/57600 [5:05:33<4:46:07,  1.66it/s]
 50%|█████     | 29069/57600 [5:05:34<4:50:05,  1.64it/s]
 50%|█████     | 29070/57600 [5:05:35<4:54:56,  1.61it/s]
 50%|█████     | 29071/57600 [5:05:35<4:54:31,  1.61it/s]
 50%|█████     | 29072/57600 [5:05:36<4:59:49,  1.59it/s]
 50%|█████     | 29073/57600 [5:05:37<4:52:09,  1.63it/s]
 50%|█████     | 29074/57600 [5:05:37<4:44:12,  1.67it/s]
 50%|█████     | 29075/57600 [5:05:38<4:46:31,  1.66it/s]
 50%|█████     | 29076/57600 [5:05:38<4:45:28,  1.67it/s]
 50%|█████     | 29077/57600 [5:05:39<4:49:37,  1.64it/s]
 50%|█████     | 29078/57600 [5:05:40<4:49:23,  1.64it/s]
 50%|█████     | 29079/57600 [5:05:40<4:52:15,  1.63it/s]
 50%|█████     | 29080/57600 [5:05:41<5:05:06,  1.56it/s]
                                                         
{'loss': 1.2178, 'learning_rate': 5.47177700348432e-07, 'epoch': 320.97}

 50%|█████     | 29080/57600 [5:05:41<5:05:06,  1.56it/s]
 50%|█████     | 29081/57600 [5:05:42<5:08:30,  1.54it/s]
 50%|█████     | 29082/57600 [5:05:42<4:58:14,  1.59it/s]
 50%|█████     | 29083/57600 [5:05:43<5:07:37,  1.55it/s]
 50%|█████     | 29084/57600 [5:05:43<4:54:37,  1.61it/s]
 50%|█████     | 29085/57600 [5:05:44<4:48:47,  1.65it/s]
 50%|█████     | 29086/57600 [5:05:45<4:48:14,  1.65it/s]
 50%|█████     | 29087/57600 [5:05:45<4:53:45,  1.62it/s]
 50%|█████     | 29088/57600 [5:05:46<5:00:27,  1.58it/s]
 51%|█████     | 29089/57600 [5:05:46<4:52:40,  1.62it/s]
 51%|█████     | 29090/57600 [5:05:47<5:01:57,  1.57it/s]
 51%|█████     | 29091/57600 [5:05:48<5:08:00,  1.54it/s]
 51%|█████     | 29092/57600 [5:05:48<5:00:43,  1.58it/s]
 51%|█████     | 29093/57600 [5:05:49<4:53:23,  1.62it/s]
 51%|█████     | 29094/57600 [5:05:50<4:56:04,  1.60it/s]
 51%|█████     | 29095/57600 [5:05:50<4:59:10,  1.59it/s]
 51%|█████     | 29096/57600 [5:05:51<5:00:39,  1.58it/s]
 51%|█████     | 29097/57600 [5:05:51<4:48:32,  1.65it/s]
 51%|█████     | 29098/57600 [5:05:52<4:59:52,  1.58it/s]
 51%|█████     | 29099/57600 [5:05:53<5:02:07,  1.57it/s]
 51%|█████     | 29100/57600 [5:05:53<5:07:46,  1.54it/s]
                                                         
{'loss': 1.1705, 'learning_rate': 5.468641114982579e-07, 'epoch': 321.19}

 51%|█████     | 29100/57600 [5:05:53<5:07:46,  1.54it/s]
 51%|█████     | 29101/57600 [5:05:54<5:01:49,  1.57it/s]
 51%|█████     | 29102/57600 [5:05:55<5:02:54,  1.57it/s]
 51%|█████     | 29103/57600 [5:05:55<5:03:39,  1.56it/s]
 51%|█████     | 29104/57600 [5:05:56<4:57:51,  1.59it/s]
 51%|█████     | 29105/57600 [5:05:57<5:01:07,  1.58it/s]
 51%|█████     | 29106/57600 [5:05:57<4:53:49,  1.62it/s]
 51%|█████     | 29107/57600 [5:05:58<4:44:54,  1.67it/s]
 51%|█████     | 29108/57600 [5:05:58<4:45:04,  1.67it/s]
 51%|█████     | 29109/57600 [5:05:59<4:49:44,  1.64it/s]
 51%|█████     | 29110/57600 [5:06:00<4:51:01,  1.63it/s]
 51%|█████     | 29111/57600 [5:06:00<5:05:13,  1.56it/s]
 51%|█████     | 29112/57600 [5:06:01<5:12:05,  1.52it/s]
 51%|█████     | 29113/57600 [5:06:02<5:06:36,  1.55it/s]
 51%|█████     | 29114/57600 [5:06:02<4:56:17,  1.60it/s]
 51%|█████     | 29115/57600 [5:06:03<5:01:20,  1.58it/s]
 51%|█████     | 29116/57600 [5:06:04<5:08:52,  1.54it/s]
 51%|█████     | 29117/57600 [5:06:04<5:02:41,  1.57it/s]
 51%|█████     | 29118/57600 [5:06:05<5:00:12,  1.58it/s]
 51%|█████     | 29119/57600 [5:06:05<4:58:37,  1.59it/s]
 51%|█████     | 29120/57600 [5:06:06<4:53:49,  1.62it/s]
                                                         
{'loss': 1.1619, 'learning_rate': 5.465505226480836e-07, 'epoch': 321.41}

 51%|█████     | 29120/57600 [5:06:06<4:53:49,  1.62it/s]
 51%|█████     | 29121/57600 [5:06:07<4:57:30,  1.60it/s]
 51%|█████     | 29122/57600 [5:06:07<4:56:17,  1.60it/s]
 51%|█████     | 29123/57600 [5:06:08<4:50:19,  1.63it/s]
 51%|█████     | 29124/57600 [5:06:08<4:46:39,  1.66it/s]
 51%|█████     | 29125/57600 [5:06:09<4:50:06,  1.64it/s]
 51%|█████     | 29126/57600 [5:06:10<4:54:04,  1.61it/s]
 51%|█████     | 29127/57600 [5:06:10<4:51:44,  1.63it/s]
 51%|█████     | 29128/57600 [5:06:11<4:40:13,  1.69it/s]
 51%|█████     | 29129/57600 [5:06:11<4:44:11,  1.67it/s]
 51%|█████     | 29130/57600 [5:06:12<4:42:09,  1.68it/s]
 51%|█████     | 29131/57600 [5:06:13<4:39:20,  1.70it/s]
 51%|█████     | 29132/57600 [5:06:13<4:44:58,  1.66it/s]
 51%|█████     | 29133/57600 [5:06:14<4:52:26,  1.62it/s]
 51%|█████     | 29134/57600 [5:06:14<4:46:06,  1.66it/s]
 51%|█████     | 29135/57600 [5:06:15<4:47:11,  1.65it/s]
 51%|█████     | 29136/57600 [5:06:16<4:41:12,  1.69it/s]
 51%|█████     | 29137/57600 [5:06:16<4:48:59,  1.64it/s]
 51%|█████     | 29138/57600 [5:06:17<4:51:05,  1.63it/s]
 51%|█████     | 29139/57600 [5:06:18<4:51:40,  1.63it/s]
 51%|█████     | 29140/57600 [5:06:18<4:47:05,  1.65it/s]
                                                         
{'loss': 1.1919, 'learning_rate': 5.462369337979094e-07, 'epoch': 321.63}

 51%|█████     | 29140/57600 [5:06:18<4:47:05,  1.65it/s]
 51%|█████     | 29141/57600 [5:06:19<4:56:32,  1.60it/s]
 51%|█████     | 29142/57600 [5:06:19<4:51:57,  1.62it/s]
 51%|█████     | 29143/57600 [5:06:20<4:49:00,  1.64it/s]
 51%|█████     | 29144/57600 [5:06:21<4:48:19,  1.64it/s]
 51%|█████     | 29145/57600 [5:06:21<4:45:30,  1.66it/s]
 51%|█████     | 29146/57600 [5:06:22<4:55:10,  1.61it/s]
 51%|█████     | 29147/57600 [5:06:22<4:52:00,  1.62it/s]
 51%|█████     | 29148/57600 [5:06:23<4:50:25,  1.63it/s]
 51%|█████     | 29149/57600 [5:06:24<4:47:17,  1.65it/s]
 51%|█████     | 29150/57600 [5:06:24<4:48:08,  1.65it/s]
 51%|█████     | 29151/57600 [5:06:25<4:40:32,  1.69it/s]
 51%|█████     | 29152/57600 [5:06:25<4:50:32,  1.63it/s]
 51%|█████     | 29153/57600 [5:06:26<4:57:52,  1.59it/s]
 51%|█████     | 29154/57600 [5:06:27<4:55:46,  1.60it/s]
 51%|█████     | 29155/57600 [5:06:27<4:58:23,  1.59it/s]
 51%|█████     | 29156/57600 [5:06:28<5:07:02,  1.54it/s]
 51%|█████     | 29157/57600 [5:06:29<5:00:43,  1.58it/s]
 51%|█████     | 29158/57600 [5:06:29<5:04:23,  1.56it/s]
 51%|█████     | 29159/57600 [5:06:30<5:10:08,  1.53it/s]
 51%|█████     | 29160/57600 [5:06:31<5:05:43,  1.55it/s]
                                                         
{'loss': 1.1679, 'learning_rate': 5.459233449477352e-07, 'epoch': 321.85}

 51%|█████     | 29160/57600 [5:06:31<5:05:43,  1.55it/s]
 51%|█████     | 29161/57600 [5:06:31<4:59:04,  1.58it/s]
 51%|█████     | 29162/57600 [5:06:32<4:53:19,  1.62it/s]
 51%|█████     | 29163/57600 [5:06:33<4:58:55,  1.59it/s]
 51%|█████     | 29164/57600 [5:06:33<5:05:53,  1.55it/s]
 51%|█████     | 29165/57600 [5:06:34<5:02:18,  1.57it/s]
 51%|█████     | 29166/57600 [5:06:34<4:56:08,  1.60it/s]
 51%|█████     | 29167/57600 [5:06:35<4:50:29,  1.63it/s]
 51%|█████     | 29168/57600 [5:06:36<4:46:37,  1.65it/s]
 51%|█████     | 29169/57600 [5:06:36<4:56:45,  1.60it/s]
 51%|█████     | 29170/57600 [5:06:37<4:55:57,  1.60it/s]
 51%|█████     | 29171/57600 [5:06:37<4:57:03,  1.60it/s]
 51%|█████     | 29172/57600 [5:06:38<5:00:24,  1.58it/s]
 51%|█████     | 29173/57600 [5:06:39<4:48:18,  1.64it/s]
 51%|█████     | 29174/57600 [5:06:39<5:03:23,  1.56it/s]
 51%|█████     | 29175/57600 [5:06:40<5:04:40,  1.55it/s]
 51%|█████     | 29176/57600 [5:06:41<4:58:51,  1.59it/s]
 51%|█████     | 29177/57600 [5:06:41<4:49:44,  1.63it/s]
 51%|█████     | 29178/57600 [5:06:42<4:50:25,  1.63it/s]
 51%|█████     | 29179/57600 [5:06:42<4:54:04,  1.61it/s]
 51%|█████     | 29180/57600 [5:06:43<4:58:40,  1.59it/s]
                                                         
{'loss': 1.1742, 'learning_rate': 5.45609756097561e-07, 'epoch': 322.08}

 51%|█████     | 29180/57600 [5:06:43<4:58:40,  1.59it/s]
 51%|█████     | 29181/57600 [5:06:44<4:48:53,  1.64it/s]
 51%|█████     | 29182/57600 [5:06:44<4:42:36,  1.68it/s]
 51%|█████     | 29183/57600 [5:06:45<4:40:54,  1.69it/s]
 51%|█████     | 29184/57600 [5:06:45<4:46:43,  1.65it/s]
 51%|█████     | 29185/57600 [5:06:46<4:52:26,  1.62it/s]
 51%|█████     | 29186/57600 [5:06:47<4:57:49,  1.59it/s]
 51%|█████     | 29187/57600 [5:06:47<5:06:08,  1.55it/s]
 51%|█████     | 29188/57600 [5:06:48<5:10:49,  1.52it/s]
 51%|█████     | 29189/57600 [5:06:49<5:09:16,  1.53it/s]
 51%|█████     | 29190/57600 [5:06:49<5:08:44,  1.53it/s]
 51%|█████     | 29191/57600 [5:06:50<5:09:39,  1.53it/s]
 51%|█████     | 29192/57600 [5:06:51<5:00:08,  1.58it/s]
 51%|█████     | 29193/57600 [5:06:51<4:54:20,  1.61it/s]
 51%|█████     | 29194/57600 [5:06:52<5:01:30,  1.57it/s]
 51%|█████     | 29195/57600 [5:06:53<4:56:27,  1.60it/s]
 51%|█████     | 29196/57600 [5:06:53<4:55:08,  1.60it/s]
 51%|█████     | 29197/57600 [5:06:54<4:58:20,  1.59it/s]
 51%|█████     | 29198/57600 [5:06:54<4:59:53,  1.58it/s]
 51%|█████     | 29199/57600 [5:06:55<4:54:16,  1.61it/s]
 51%|█████     | 29200/57600 [5:06:56<4:50:45,  1.63it/s]
                                                         
{'loss': 1.1394, 'learning_rate': 5.452961672473868e-07, 'epoch': 322.3}

 51%|█████     | 29200/57600 [5:06:56<4:50:45,  1.63it/s]
 51%|█████     | 29201/57600 [5:06:56<4:50:01,  1.63it/s]
 51%|█████     | 29202/57600 [5:06:57<4:56:14,  1.60it/s]
 51%|█████     | 29203/57600 [5:06:58<5:03:39,  1.56it/s]
 51%|█████     | 29204/57600 [5:06:58<4:57:39,  1.59it/s]
 51%|█████     | 29205/57600 [5:06:59<4:59:55,  1.58it/s]
 51%|█████     | 29206/57600 [5:06:59<4:50:22,  1.63it/s]
 51%|█████     | 29207/57600 [5:07:00<4:49:22,  1.64it/s]
 51%|█████     | 29208/57600 [5:07:01<4:42:17,  1.68it/s]
 51%|█████     | 29209/57600 [5:07:01<4:47:17,  1.65it/s]
 51%|█████     | 29210/57600 [5:07:02<4:48:59,  1.64it/s]
 51%|█████     | 29211/57600 [5:07:02<4:44:47,  1.66it/s]
 51%|█████     | 29212/57600 [5:07:03<4:44:03,  1.67it/s]
 51%|█████     | 29213/57600 [5:07:04<4:44:27,  1.66it/s]
 51%|█████     | 29214/57600 [5:07:04<4:42:25,  1.68it/s]
 51%|█████     | 29215/57600 [5:07:05<4:39:44,  1.69it/s]
 51%|█████     | 29216/57600 [5:07:05<4:38:06,  1.70it/s]
 51%|█████     | 29217/57600 [5:07:06<4:48:07,  1.64it/s]
 51%|█████     | 29218/57600 [5:07:07<4:49:13,  1.64it/s]
 51%|█████     | 29219/57600 [5:07:07<4:50:54,  1.63it/s]
 51%|█████     | 29220/57600 [5:07:08<4:51:38,  1.62it/s]
                                                         
{'loss': 1.1978, 'learning_rate': 5.449825783972125e-07, 'epoch': 322.52}

 51%|█████     | 29220/57600 [5:07:08<4:51:38,  1.62it/s]
 51%|█████     | 29221/57600 [5:07:08<4:51:26,  1.62it/s]
 51%|█████     | 29222/57600 [5:07:09<4:45:57,  1.65it/s]
 51%|█████     | 29223/57600 [5:07:10<4:50:20,  1.63it/s]
 51%|█████     | 29224/57600 [5:07:10<4:44:08,  1.66it/s]
 51%|█████     | 29225/57600 [5:07:11<4:42:58,  1.67it/s]
 51%|█████     | 29226/57600 [5:07:11<4:40:16,  1.69it/s]
 51%|█████     | 29227/57600 [5:07:12<4:40:10,  1.69it/s]
 51%|█████     | 29228/57600 [5:07:13<4:40:08,  1.69it/s]
 51%|█████     | 29229/57600 [5:07:13<4:37:59,  1.70it/s]
 51%|█████     | 29230/57600 [5:07:14<4:53:25,  1.61it/s]
 51%|█████     | 29231/57600 [5:07:15<4:55:15,  1.60it/s]
 51%|█████     | 29232/57600 [5:07:15<4:56:45,  1.59it/s]
 51%|█████     | 29233/57600 [5:07:16<4:52:44,  1.62it/s]
 51%|█████     | 29234/57600 [5:07:16<4:50:12,  1.63it/s]
 51%|█████     | 29235/57600 [5:07:17<4:52:08,  1.62it/s]
 51%|█████     | 29236/57600 [5:07:18<4:58:04,  1.59it/s]
 51%|█████     | 29237/57600 [5:07:18<5:08:23,  1.53it/s]
 51%|█████     | 29238/57600 [5:07:19<5:06:49,  1.54it/s]
 51%|█████     | 29239/57600 [5:07:20<5:05:54,  1.55it/s]
 51%|█████     | 29240/57600 [5:07:20<5:21:29,  1.47it/s]
                                                         
{'loss': 1.1737, 'learning_rate': 5.446689895470383e-07, 'epoch': 322.74}

 51%|█████     | 29240/57600 [5:07:20<5:21:29,  1.47it/s]
 51%|█████     | 29241/57600 [5:07:21<5:17:57,  1.49it/s]
 51%|█████     | 29242/57600 [5:07:22<5:04:41,  1.55it/s]
 51%|█████     | 29243/57600 [5:07:22<5:03:07,  1.56it/s]
 51%|█████     | 29244/57600 [5:07:23<4:58:19,  1.58it/s]
 51%|█████     | 29245/57600 [5:07:24<5:12:27,  1.51it/s]
 51%|█████     | 29246/57600 [5:07:24<5:09:19,  1.53it/s]
 51%|█████     | 29247/57600 [5:07:25<5:06:52,  1.54it/s]
 51%|█████     | 29248/57600 [5:07:26<5:06:54,  1.54it/s]
 51%|█████     | 29249/57600 [5:07:26<5:03:02,  1.56it/s]
 51%|█████     | 29250/57600 [5:07:27<4:59:20,  1.58it/s]
 51%|█████     | 29251/57600 [5:07:27<4:58:43,  1.58it/s]
 51%|█████     | 29252/57600 [5:07:28<5:01:37,  1.57it/s]
 51%|█████     | 29253/57600 [5:07:29<4:58:29,  1.58it/s]
 51%|█████     | 29254/57600 [5:07:29<4:55:17,  1.60it/s]
 51%|█████     | 29255/57600 [5:07:30<4:55:31,  1.60it/s]
 51%|█████     | 29256/57600 [5:07:31<4:54:54,  1.60it/s]
 51%|█████     | 29257/57600 [5:07:31<4:54:19,  1.60it/s]
 51%|█████     | 29258/57600 [5:07:32<4:46:03,  1.65it/s]
 51%|█████     | 29259/57600 [5:07:32<4:46:26,  1.65it/s]
 51%|█████     | 29260/57600 [5:07:33<4:54:38,  1.60it/s]
                                                         
{'loss': 1.1663, 'learning_rate': 5.44355400696864e-07, 'epoch': 322.96}

 51%|█████     | 29260/57600 [5:07:33<4:54:38,  1.60it/s]
 51%|█████     | 29261/57600 [5:07:34<4:54:25,  1.60it/s]
 51%|█████     | 29262/57600 [5:07:34<4:55:06,  1.60it/s]
 51%|█████     | 29263/57600 [5:07:35<5:00:40,  1.57it/s]
 51%|█████     | 29264/57600 [5:07:36<5:07:33,  1.54it/s]
 51%|█████     | 29265/57600 [5:07:36<4:57:12,  1.59it/s]
 51%|█████     | 29266/57600 [5:07:37<4:45:32,  1.65it/s]
 51%|█████     | 29267/57600 [5:07:37<4:49:28,  1.63it/s]
 51%|█████     | 29268/57600 [5:07:38<4:41:38,  1.68it/s]
 51%|█████     | 29269/57600 [5:07:38<4:39:59,  1.69it/s]
 51%|█████     | 29270/57600 [5:07:39<4:40:46,  1.68it/s]
 51%|█████     | 29271/57600 [5:07:40<4:37:24,  1.70it/s]
 51%|█████     | 29272/57600 [5:07:40<4:33:46,  1.72it/s]
 51%|█████     | 29273/57600 [5:07:41<4:48:24,  1.64it/s]
 51%|█████     | 29274/57600 [5:07:42<4:57:50,  1.59it/s]
 51%|█████     | 29275/57600 [5:07:42<4:47:52,  1.64it/s]
 51%|█████     | 29276/57600 [5:07:43<4:45:48,  1.65it/s]
 51%|█████     | 29277/57600 [5:07:43<4:52:41,  1.61it/s]
 51%|█████     | 29278/57600 [5:07:44<4:55:42,  1.60it/s]
 51%|█████     | 29279/57600 [5:07:45<4:56:42,  1.59it/s]
 51%|█████     | 29280/57600 [5:07:45<4:54:37,  1.60it/s]
                                                         
{'loss': 1.1925, 'learning_rate': 5.440418118466898e-07, 'epoch': 323.18}

 51%|█████     | 29280/57600 [5:07:45<4:54:37,  1.60it/s]
 51%|█████     | 29281/57600 [5:07:46<4:57:37,  1.59it/s]
 51%|█████     | 29282/57600 [5:07:47<5:04:38,  1.55it/s]
 51%|█████     | 29283/57600 [5:07:47<5:01:40,  1.56it/s]
 51%|█████     | 29284/57600 [5:07:48<4:50:50,  1.62it/s]
 51%|█████     | 29285/57600 [5:07:48<4:55:27,  1.60it/s]
 51%|█████     | 29286/57600 [5:07:49<5:04:05,  1.55it/s]
 51%|█████     | 29287/57600 [5:07:50<5:02:27,  1.56it/s]
 51%|█████     | 29288/57600 [5:07:50<4:58:40,  1.58it/s]
 51%|█████     | 29289/57600 [5:07:51<4:57:50,  1.58it/s]
 51%|█████     | 29290/57600 [5:07:52<4:55:05,  1.60it/s]
 51%|█████     | 29291/57600 [5:07:52<4:55:37,  1.60it/s]
 51%|█████     | 29292/57600 [5:07:53<4:58:48,  1.58it/s]
 51%|█████     | 29293/57600 [5:07:54<5:01:28,  1.56it/s]
 51%|█████     | 29294/57600 [5:07:54<4:55:10,  1.60it/s]
 51%|█████     | 29295/57600 [5:07:55<5:00:36,  1.57it/s]
 51%|█████     | 29296/57600 [5:07:55<5:01:50,  1.56it/s]
 51%|█████     | 29297/57600 [5:07:56<4:51:46,  1.62it/s]
 51%|█████     | 29298/57600 [5:07:57<4:52:55,  1.61it/s]
 51%|█████     | 29299/57600 [5:07:57<4:45:47,  1.65it/s]
 51%|█████     | 29300/57600 [5:07:58<4:39:51,  1.69it/s]
                                                         
{'loss': 1.1958, 'learning_rate': 5.437282229965156e-07, 'epoch': 323.4}

 51%|█████     | 29300/57600 [5:07:58<4:39:51,  1.69it/s]
 51%|█████     | 29301/57600 [5:07:58<4:38:52,  1.69it/s]
 51%|█████     | 29302/57600 [5:07:59<4:39:09,  1.69it/s]
 51%|█████     | 29303/57600 [5:08:00<4:40:13,  1.68it/s]
 51%|█████     | 29304/57600 [5:08:00<4:35:26,  1.71it/s]
 51%|█████     | 29305/57600 [5:08:01<4:31:34,  1.74it/s]
 51%|█████     | 29306/57600 [5:08:01<4:41:08,  1.68it/s]
 51%|█████     | 29307/57600 [5:08:02<4:53:22,  1.61it/s]
 51%|█████     | 29308/57600 [5:08:03<4:48:49,  1.63it/s]
 51%|█████     | 29309/57600 [5:08:03<4:48:42,  1.63it/s]
 51%|█████     | 29310/57600 [5:08:04<4:48:26,  1.63it/s]
 51%|█████     | 29311/57600 [5:08:04<4:55:05,  1.60it/s]
 51%|█████     | 29312/57600 [5:08:05<4:52:47,  1.61it/s]
 51%|█████     | 29313/57600 [5:08:06<4:46:04,  1.65it/s]
 51%|█████     | 29314/57600 [5:08:06<4:50:26,  1.62it/s]
 51%|█████     | 29315/57600 [5:08:07<4:44:51,  1.65it/s]
 51%|█████     | 29316/57600 [5:08:07<4:43:20,  1.66it/s]
 51%|█████     | 29317/57600 [5:08:08<4:42:24,  1.67it/s]
 51%|█████     | 29318/57600 [5:08:09<4:38:06,  1.69it/s]
 51%|█████     | 29319/57600 [5:08:09<4:47:55,  1.64it/s]
 51%|█████     | 29320/57600 [5:08:10<4:51:35,  1.62it/s]
                                                         
{'loss': 1.2169, 'learning_rate': 5.434146341463415e-07, 'epoch': 323.62}

 51%|█████     | 29320/57600 [5:08:10<4:51:35,  1.62it/s]
 51%|█████     | 29321/57600 [5:08:11<5:01:03,  1.57it/s]
 51%|█████     | 29322/57600 [5:08:11<4:57:46,  1.58it/s]
 51%|█████     | 29323/57600 [5:08:12<4:59:06,  1.58it/s]
 51%|█████     | 29324/57600 [5:08:12<4:53:23,  1.61it/s]
 51%|█████     | 29325/57600 [5:08:13<4:49:32,  1.63it/s]
 51%|█████     | 29326/57600 [5:08:14<5:02:27,  1.56it/s]
 51%|█████     | 29327/57600 [5:08:14<5:03:46,  1.55it/s]
 51%|█████     | 29328/57600 [5:08:15<5:01:03,  1.57it/s]
 51%|█████     | 29329/57600 [5:08:16<4:56:37,  1.59it/s]
 51%|█████     | 29330/57600 [5:08:16<5:00:11,  1.57it/s]
 51%|█████     | 29331/57600 [5:08:17<5:05:36,  1.54it/s]
 51%|█████     | 29332/57600 [5:08:18<4:57:26,  1.58it/s]
 51%|█████     | 29333/57600 [5:08:18<4:55:01,  1.60it/s]
 51%|█████     | 29334/57600 [5:08:19<4:52:55,  1.61it/s]
 51%|█████     | 29335/57600 [5:08:19<4:55:17,  1.60it/s]
 51%|█████     | 29336/57600 [5:08:20<4:50:24,  1.62it/s]
 51%|█████     | 29337/57600 [5:08:21<5:00:24,  1.57it/s]
 51%|█████     | 29338/57600 [5:08:21<5:04:35,  1.55it/s]
 51%|█████     | 29339/57600 [5:08:22<5:02:38,  1.56it/s]
 51%|█████     | 29340/57600 [5:08:23<5:04:44,  1.55it/s]
                                                         
{'loss': 1.161, 'learning_rate': 5.431010452961672e-07, 'epoch': 323.84}

 51%|█████     | 29340/57600 [5:08:23<5:04:44,  1.55it/s]
 51%|█████     | 29341/57600 [5:08:23<4:54:12,  1.60it/s]
 51%|█████     | 29342/57600 [5:08:24<5:06:08,  1.54it/s]
 51%|█████     | 29343/57600 [5:08:25<5:09:03,  1.52it/s]
 51%|█████     | 29344/57600 [5:08:25<4:56:08,  1.59it/s]
 51%|█████     | 29345/57600 [5:08:26<5:00:57,  1.56it/s]
 51%|█████     | 29346/57600 [5:08:26<4:59:52,  1.57it/s]
 51%|█████     | 29347/57600 [5:08:27<5:07:44,  1.53it/s]
 51%|█████     | 29348/57600 [5:08:28<5:03:19,  1.55it/s]
 51%|█████     | 29349/57600 [5:08:28<4:59:04,  1.57it/s]
 51%|█████     | 29350/57600 [5:08:29<4:47:44,  1.64it/s]
 51%|█████     | 29351/57600 [5:08:30<4:42:19,  1.67it/s]
 51%|█████     | 29352/57600 [5:08:30<4:44:35,  1.65it/s]
 51%|█████     | 29353/57600 [5:08:31<4:55:41,  1.59it/s]
 51%|█████     | 29354/57600 [5:08:32<5:00:31,  1.57it/s]
 51%|█████     | 29355/57600 [5:08:32<5:01:14,  1.56it/s]
 51%|█████     | 29356/57600 [5:08:33<4:59:32,  1.57it/s]
 51%|█████     | 29357/57600 [5:08:33<4:57:36,  1.58it/s]
 51%|█████     | 29358/57600 [5:08:34<4:51:07,  1.62it/s]
 51%|█████     | 29359/57600 [5:08:35<4:43:12,  1.66it/s]
 51%|█████     | 29360/57600 [5:08:35<4:54:51,  1.60it/s]
                                                         
{'loss': 1.1456, 'learning_rate': 5.427874564459931e-07, 'epoch': 324.06}

 51%|█████     | 29360/57600 [5:08:35<4:54:51,  1.60it/s]
 51%|█████     | 29361/57600 [5:08:36<5:01:48,  1.56it/s]
 51%|█████     | 29362/57600 [5:08:37<5:13:19,  1.50it/s]
 51%|█████     | 29363/57600 [5:08:37<5:05:26,  1.54it/s]
 51%|█████     | 29364/57600 [5:08:38<4:55:52,  1.59it/s]
 51%|█████     | 29365/57600 [5:08:38<4:53:40,  1.60it/s]
 51%|█████     | 29366/57600 [5:08:39<5:00:07,  1.57it/s]
 51%|█████     | 29367/57600 [5:08:40<4:54:00,  1.60it/s]
 51%|█████     | 29368/57600 [5:08:40<4:55:34,  1.59it/s]
 51%|█████     | 29369/57600 [5:08:41<4:52:13,  1.61it/s]
 51%|█████     | 29370/57600 [5:08:42<4:54:42,  1.60it/s]
 51%|█████     | 29371/57600 [5:08:42<4:54:19,  1.60it/s]
 51%|█████     | 29372/57600 [5:08:43<4:54:51,  1.60it/s]
 51%|█████     | 29373/57600 [5:08:44<5:01:51,  1.56it/s]
 51%|█████     | 29374/57600 [5:08:44<5:04:36,  1.54it/s]
 51%|█████     | 29375/57600 [5:08:45<5:10:48,  1.51it/s]
 51%|█████     | 29376/57600 [5:08:45<5:01:16,  1.56it/s]
 51%|█████     | 29377/57600 [5:08:46<5:14:06,  1.50it/s]
 51%|█████     | 29378/57600 [5:08:47<5:08:25,  1.53it/s]
 51%|█████     | 29379/57600 [5:08:47<4:54:48,  1.60it/s]
 51%|█████     | 29380/57600 [5:08:48<4:53:40,  1.60it/s]
                                                         
{'loss': 1.1658, 'learning_rate': 5.424738675958188e-07, 'epoch': 324.28}

 51%|█████     | 29380/57600 [5:08:48<4:53:40,  1.60it/s]
 51%|█████     | 29381/57600 [5:08:49<4:52:33,  1.61it/s]
 51%|█████     | 29382/57600 [5:08:49<4:52:25,  1.61it/s]
 51%|█████     | 29383/57600 [5:08:50<4:43:10,  1.66it/s]
 51%|█████     | 29384/57600 [5:08:50<4:38:14,  1.69it/s]
 51%|█████     | 29385/57600 [5:08:51<4:45:52,  1.64it/s]
 51%|█████     | 29386/57600 [5:08:52<4:47:29,  1.64it/s]
 51%|█████     | 29387/57600 [5:08:52<4:50:14,  1.62it/s]
 51%|█████     | 29388/57600 [5:08:53<4:48:37,  1.63it/s]
 51%|█████     | 29389/57600 [5:08:53<4:45:47,  1.65it/s]
 51%|█████     | 29390/57600 [5:08:54<4:53:47,  1.60it/s]
 51%|█████     | 29391/57600 [5:08:55<4:54:21,  1.60it/s]
 51%|█████     | 29392/57600 [5:08:55<4:56:59,  1.58it/s]
 51%|█████     | 29393/57600 [5:08:56<4:48:02,  1.63it/s]
 51%|█████     | 29394/57600 [5:08:57<4:54:07,  1.60it/s]
 51%|█████     | 29395/57600 [5:08:57<4:52:40,  1.61it/s]
 51%|█████     | 29396/57600 [5:08:58<4:51:47,  1.61it/s]
 51%|█████     | 29397/57600 [5:08:59<4:59:39,  1.57it/s]
 51%|█████     | 29398/57600 [5:08:59<4:53:18,  1.60it/s]
 51%|█████     | 29399/57600 [5:09:00<4:53:07,  1.60it/s]
 51%|█████     | 29400/57600 [5:09:00<4:46:48,  1.64it/s]
                                                         
{'loss': 1.1708, 'learning_rate': 5.421602787456446e-07, 'epoch': 324.5}

 51%|█████     | 29400/57600 [5:09:00<4:46:48,  1.64it/s]
 51%|█████     | 29401/57600 [5:09:01<4:44:39,  1.65it/s]
 51%|█████     | 29402/57600 [5:09:01<4:37:59,  1.69it/s]
 51%|█████     | 29403/57600 [5:09:02<4:40:01,  1.68it/s]
 51%|█████     | 29404/57600 [5:09:03<4:40:05,  1.68it/s]
 51%|█████     | 29405/57600 [5:09:03<4:46:24,  1.64it/s]
 51%|█████     | 29406/57600 [5:09:04<4:45:47,  1.64it/s]
 51%|█████     | 29407/57600 [5:09:05<4:51:53,  1.61it/s]
 51%|█████     | 29408/57600 [5:09:05<4:47:45,  1.63it/s]
 51%|█████     | 29409/57600 [5:09:06<4:53:22,  1.60it/s]
 51%|█████     | 29410/57600 [5:09:06<4:54:55,  1.59it/s]
 51%|█████     | 29411/57600 [5:09:07<5:06:17,  1.53it/s]
 51%|█████     | 29412/57600 [5:09:08<5:10:13,  1.51it/s]
 51%|█████     | 29413/57600 [5:09:08<5:01:32,  1.56it/s]
 51%|█████     | 29414/57600 [5:09:09<4:54:32,  1.59it/s]
 51%|█████     | 29415/57600 [5:09:10<4:51:16,  1.61it/s]
 51%|█████     | 29416/57600 [5:09:10<4:42:36,  1.66it/s]
 51%|█████     | 29417/57600 [5:09:11<4:37:46,  1.69it/s]
 51%|█████     | 29418/57600 [5:09:11<4:37:25,  1.69it/s]
 51%|█████     | 29419/57600 [5:09:12<4:31:55,  1.73it/s]
 51%|█████     | 29420/57600 [5:09:13<4:36:22,  1.70it/s]
                                                         
{'loss': 1.1884, 'learning_rate': 5.418466898954704e-07, 'epoch': 324.72}

 51%|█████     | 29420/57600 [5:09:13<4:36:22,  1.70it/s]
 51%|█████     | 29421/57600 [5:09:13<4:32:36,  1.72it/s]
 51%|█████     | 29422/57600 [5:09:14<4:42:17,  1.66it/s]
 51%|█████     | 29423/57600 [5:09:14<4:42:22,  1.66it/s]
 51%|█████     | 29424/57600 [5:09:15<4:43:52,  1.65it/s]
 51%|█████     | 29425/57600 [5:09:16<4:45:39,  1.64it/s]
 51%|█████     | 29426/57600 [5:09:16<4:46:34,  1.64it/s]
 51%|█████     | 29427/57600 [5:09:17<4:39:57,  1.68it/s]
 51%|█████     | 29428/57600 [5:09:17<4:42:58,  1.66it/s]
 51%|█████     | 29429/57600 [5:09:18<4:57:00,  1.58it/s]
 51%|█████     | 29430/57600 [5:09:19<5:02:37,  1.55it/s]
 51%|█████     | 29431/57600 [5:09:19<4:56:35,  1.58it/s]
 51%|█████     | 29432/57600 [5:09:20<5:03:00,  1.55it/s]
 51%|█████     | 29433/57600 [5:09:21<5:00:53,  1.56it/s]
 51%|█████     | 29434/57600 [5:09:21<4:56:13,  1.58it/s]
 51%|█████     | 29435/57600 [5:09:22<4:51:10,  1.61it/s]
 51%|█████     | 29436/57600 [5:09:22<4:48:00,  1.63it/s]
 51%|█████     | 29437/57600 [5:09:23<4:40:34,  1.67it/s]
 51%|█████     | 29438/57600 [5:09:24<4:39:28,  1.68it/s]
 51%|█████     | 29439/57600 [5:09:24<4:46:51,  1.64it/s]
 51%|█████     | 29440/57600 [5:09:25<4:47:28,  1.63it/s]
                                                         
{'loss': 1.195, 'learning_rate': 5.415331010452962e-07, 'epoch': 324.94}

 51%|█████     | 29440/57600 [5:09:25<4:47:28,  1.63it/s]
 51%|█████     | 29441/57600 [5:09:25<4:40:45,  1.67it/s]
 51%|█████     | 29442/57600 [5:09:26<4:49:09,  1.62it/s]
 51%|█████     | 29443/57600 [5:09:27<4:38:16,  1.69it/s]
 51%|█████     | 29444/57600 [5:09:27<4:49:03,  1.62it/s]
 51%|█████     | 29445/57600 [5:09:28<4:47:45,  1.63it/s]
 51%|█████     | 29446/57600 [5:09:29<5:06:48,  1.53it/s]
 51%|█████     | 29447/57600 [5:09:29<5:06:48,  1.53it/s]
 51%|█████     | 29448/57600 [5:09:30<4:59:24,  1.57it/s]
 51%|█████     | 29449/57600 [5:09:30<4:48:13,  1.63it/s]
 51%|█████     | 29450/57600 [5:09:31<4:51:38,  1.61it/s]
 51%|█████     | 29451/57600 [5:09:32<4:48:26,  1.63it/s]
 51%|█████     | 29452/57600 [5:09:32<4:41:32,  1.67it/s]
 51%|█████     | 29453/57600 [5:09:33<5:04:27,  1.54it/s]
 51%|█████     | 29454/57600 [5:09:34<4:52:57,  1.60it/s]
 51%|█████     | 29455/57600 [5:09:34<4:51:39,  1.61it/s]
 51%|█████     | 29456/57600 [5:09:35<4:56:57,  1.58it/s]
 51%|█████     | 29457/57600 [5:09:35<4:43:09,  1.66it/s]
 51%|█████     | 29458/57600 [5:09:36<4:46:22,  1.64it/s]
 51%|█████     | 29459/57600 [5:09:37<4:46:54,  1.63it/s]
 51%|█████     | 29460/57600 [5:09:37<4:47:40,  1.63it/s]
                                                         
{'loss': 1.2413, 'learning_rate': 5.412195121951219e-07, 'epoch': 325.17}

 51%|█████     | 29460/57600 [5:09:37<4:47:40,  1.63it/s]
 51%|█████     | 29461/57600 [5:09:38<4:51:59,  1.61it/s]
 51%|█████     | 29462/57600 [5:09:39<4:56:52,  1.58it/s]
 51%|█████     | 29463/57600 [5:09:39<4:52:06,  1.61it/s]
 51%|█████     | 29464/57600 [5:09:40<5:02:06,  1.55it/s]
 51%|█████     | 29465/57600 [5:09:40<4:59:50,  1.56it/s]
 51%|█████     | 29466/57600 [5:09:41<4:53:50,  1.60it/s]
 51%|█████     | 29467/57600 [5:09:42<4:49:09,  1.62it/s]
 51%|█████     | 29468/57600 [5:09:42<4:43:21,  1.65it/s]
 51%|█████     | 29469/57600 [5:09:43<4:49:39,  1.62it/s]
 51%|█████     | 29470/57600 [5:09:43<4:44:11,  1.65it/s]
 51%|█████     | 29471/57600 [5:09:44<4:41:32,  1.67it/s]
 51%|█████     | 29472/57600 [5:09:45<4:41:26,  1.67it/s]
 51%|█████     | 29473/57600 [5:09:45<4:43:24,  1.65it/s]
 51%|█████     | 29474/57600 [5:09:46<4:49:55,  1.62it/s]
 51%|█████     | 29475/57600 [5:09:47<4:45:25,  1.64it/s]
 51%|█████     | 29476/57600 [5:09:47<4:43:25,  1.65it/s]
 51%|█████     | 29477/57600 [5:09:48<4:46:16,  1.64it/s]
 51%|█████     | 29478/57600 [5:09:48<4:52:18,  1.60it/s]
 51%|█████     | 29479/57600 [5:09:49<4:41:01,  1.67it/s]
 51%|█████     | 29480/57600 [5:09:49<4:36:11,  1.70it/s]
                                                         
{'loss': 1.178, 'learning_rate': 5.409059233449478e-07, 'epoch': 325.39}

 51%|█████     | 29480/57600 [5:09:49<4:36:11,  1.70it/s]
 51%|█████     | 29481/57600 [5:09:50<4:36:30,  1.69it/s]
 51%|█████     | 29482/57600 [5:09:51<4:38:08,  1.68it/s]
 51%|█████     | 29483/57600 [5:09:51<4:48:19,  1.63it/s]
 51%|█████     | 29484/57600 [5:09:52<4:46:10,  1.64it/s]
 51%|█████     | 29485/57600 [5:09:53<4:43:59,  1.65it/s]
 51%|█████     | 29486/57600 [5:09:53<4:49:45,  1.62it/s]
 51%|█████     | 29487/57600 [5:09:54<4:51:38,  1.61it/s]
 51%|█████     | 29488/57600 [5:09:54<4:41:49,  1.66it/s]
 51%|█████     | 29489/57600 [5:09:55<4:40:42,  1.67it/s]
 51%|█████     | 29490/57600 [5:09:56<4:45:20,  1.64it/s]
 51%|█████     | 29491/57600 [5:09:56<4:40:39,  1.67it/s]
 51%|█████     | 29492/57600 [5:09:57<4:41:40,  1.66it/s]
 51%|█████     | 29493/57600 [5:09:57<4:51:14,  1.61it/s]
 51%|█████     | 29494/57600 [5:09:58<4:45:38,  1.64it/s]
 51%|█████     | 29495/57600 [5:09:59<4:44:42,  1.65it/s]
 51%|█████     | 29496/57600 [5:09:59<4:44:09,  1.65it/s]
 51%|█████     | 29497/57600 [5:10:00<4:59:09,  1.57it/s]
 51%|█████     | 29498/57600 [5:10:01<5:01:49,  1.55it/s]
 51%|█████     | 29499/57600 [5:10:01<5:06:53,  1.53it/s]
 51%|█████     | 29500/57600 [5:10:02<4:50:53,  1.61it/s]
                                                         
{'loss': 1.1932, 'learning_rate': 5.405923344947734e-07, 'epoch': 325.61}

 51%|█████     | 29500/57600 [5:10:02<4:50:53,  1.61it/s]
 51%|█████     | 29501/57600 [5:10:02<4:52:16,  1.60it/s]
 51%|█████     | 29502/57600 [5:10:03<4:40:11,  1.67it/s]
 51%|█████     | 29503/57600 [5:10:04<4:45:38,  1.64it/s]
 51%|█████     | 29504/57600 [5:10:04<4:56:41,  1.58it/s]
 51%|█████     | 29505/57600 [5:10:05<5:06:58,  1.53it/s]
 51%|█████     | 29506/57600 [5:10:06<5:04:50,  1.54it/s]
 51%|█████     | 29507/57600 [5:10:06<4:59:29,  1.56it/s]
 51%|█████     | 29508/57600 [5:10:07<5:03:00,  1.55it/s]
 51%|█████     | 29509/57600 [5:10:08<5:09:40,  1.51it/s]
 51%|█████     | 29510/57600 [5:10:08<5:01:03,  1.56it/s]
 51%|█████     | 29511/57600 [5:10:09<4:55:42,  1.58it/s]
 51%|█████     | 29512/57600 [5:10:09<4:52:35,  1.60it/s]
 51%|█████     | 29513/57600 [5:10:10<4:45:48,  1.64it/s]
 51%|█████     | 29514/57600 [5:10:11<4:59:31,  1.56it/s]
 51%|█████     | 29515/57600 [5:10:11<5:00:42,  1.56it/s]
 51%|█████     | 29516/57600 [5:10:12<4:52:40,  1.60it/s]
 51%|█████     | 29517/57600 [5:10:13<4:46:26,  1.63it/s]
 51%|█████     | 29518/57600 [5:10:13<4:40:41,  1.67it/s]
 51%|█████     | 29519/57600 [5:10:14<4:46:23,  1.63it/s]
 51%|█████▏    | 29520/57600 [5:10:14<4:44:20,  1.65it/s]
                                                         
{'loss': 1.1841, 'learning_rate': 5.402787456445993e-07, 'epoch': 325.83}

 51%|█████▏    | 29520/57600 [5:10:14<4:44:20,  1.65it/s]
 51%|█████▏    | 29521/57600 [5:10:15<4:39:59,  1.67it/s]
 51%|█████▏    | 29522/57600 [5:10:16<4:44:38,  1.64it/s]
 51%|█████▏    | 29523/57600 [5:10:16<4:44:31,  1.64it/s]
 51%|█████▏    | 29524/57600 [5:10:17<4:42:19,  1.66it/s]
 51%|█████▏    | 29525/57600 [5:10:17<4:42:46,  1.65it/s]
 51%|█████▏    | 29526/57600 [5:10:18<4:45:44,  1.64it/s]
 51%|█████▏    | 29527/57600 [5:10:19<4:52:47,  1.60it/s]
 51%|█████▏    | 29528/57600 [5:10:19<4:51:57,  1.60it/s]
 51%|█████▏    | 29529/57600 [5:10:20<4:52:01,  1.60it/s]
 51%|█████▏    | 29530/57600 [5:10:20<4:44:52,  1.64it/s]
 51%|█████▏    | 29531/57600 [5:10:21<4:45:05,  1.64it/s]
 51%|█████▏    | 29532/57600 [5:10:22<4:44:07,  1.65it/s]
 51%|█████▏    | 29533/57600 [5:10:22<4:44:38,  1.64it/s]
 51%|█████▏    | 29534/57600 [5:10:23<4:45:53,  1.64it/s]
 51%|█████▏    | 29535/57600 [5:10:24<4:50:09,  1.61it/s]
 51%|█████▏    | 29536/57600 [5:10:24<5:09:28,  1.51it/s]
 51%|█████▏    | 29537/57600 [5:10:25<5:05:44,  1.53it/s]
 51%|█████▏    | 29538/57600 [5:10:26<5:04:42,  1.53it/s]
 51%|█████▏    | 29539/57600 [5:10:26<4:56:55,  1.58it/s]
 51%|█████▏    | 29540/57600 [5:10:27<4:55:09,  1.58it/s]
                                                         
{'loss': 1.1766, 'learning_rate': 5.39965156794425e-07, 'epoch': 326.05}

 51%|█████▏    | 29540/57600 [5:10:27<4:55:09,  1.58it/s]
 51%|█████▏    | 29541/57600 [5:10:27<4:54:32,  1.59it/s]
 51%|█████▏    | 29542/57600 [5:10:28<4:59:17,  1.56it/s]
 51%|█████▏    | 29543/57600 [5:10:29<4:51:10,  1.61it/s]
 51%|█████▏    | 29544/57600 [5:10:29<4:49:08,  1.62it/s]
 51%|█████▏    | 29545/57600 [5:10:30<4:48:41,  1.62it/s]
 51%|█████▏    | 29546/57600 [5:10:31<4:55:13,  1.58it/s]
 51%|█████▏    | 29547/57600 [5:10:31<4:59:19,  1.56it/s]
 51%|█████▏    | 29548/57600 [5:10:32<4:50:35,  1.61it/s]
 51%|█████▏    | 29549/57600 [5:10:32<4:50:46,  1.61it/s]
 51%|█████▏    | 29550/57600 [5:10:33<4:54:11,  1.59it/s]
 51%|█████▏    | 29551/57600 [5:10:34<4:55:24,  1.58it/s]
 51%|█████▏    | 29552/57600 [5:10:34<4:57:32,  1.57it/s]
 51%|█████▏    | 29553/57600 [5:10:35<4:59:41,  1.56it/s]
 51%|█████▏    | 29554/57600 [5:10:36<4:56:36,  1.58it/s]
 51%|█████▏    | 29555/57600 [5:10:36<5:04:21,  1.54it/s]
 51%|█████▏    | 29556/57600 [5:10:37<4:49:22,  1.62it/s]
 51%|█████▏    | 29557/57600 [5:10:37<4:47:19,  1.63it/s]
 51%|█████▏    | 29558/57600 [5:10:38<4:59:47,  1.56it/s]
 51%|█████▏    | 29559/57600 [5:10:39<4:55:58,  1.58it/s]
 51%|█████▏    | 29560/57600 [5:10:39<4:48:32,  1.62it/s]
                                                         
{'loss': 1.1359, 'learning_rate': 5.396515679442508e-07, 'epoch': 326.27}

 51%|█████▏    | 29560/57600 [5:10:39<4:48:32,  1.62it/s]
 51%|█████▏    | 29561/57600 [5:10:40<4:52:53,  1.60it/s]
 51%|█████▏    | 29562/57600 [5:10:41<4:46:37,  1.63it/s]
 51%|█████▏    | 29563/57600 [5:10:41<4:54:28,  1.59it/s]
 51%|█████▏    | 29564/57600 [5:10:42<4:49:02,  1.62it/s]
 51%|█████▏    | 29565/57600 [5:10:43<4:54:02,  1.59it/s]
 51%|█████▏    | 29566/57600 [5:10:43<4:53:55,  1.59it/s]
 51%|█████▏    | 29567/57600 [5:10:44<4:50:45,  1.61it/s]
 51%|█████▏    | 29568/57600 [5:10:44<4:45:50,  1.63it/s]
 51%|█████▏    | 29569/57600 [5:10:45<4:42:33,  1.65it/s]
 51%|█████▏    | 29570/57600 [5:10:46<4:46:05,  1.63it/s]
 51%|█████▏    | 29571/57600 [5:10:46<4:48:53,  1.62it/s]
 51%|█████▏    | 29572/57600 [5:10:47<4:53:34,  1.59it/s]
 51%|█████▏    | 29573/57600 [5:10:48<4:54:19,  1.59it/s]
 51%|█████▏    | 29574/57600 [5:10:48<4:49:40,  1.61it/s]
 51%|█████▏    | 29575/57600 [5:10:49<4:47:00,  1.63it/s]
 51%|█████▏    | 29576/57600 [5:10:49<4:41:30,  1.66it/s]
 51%|█████▏    | 29577/57600 [5:10:50<4:40:21,  1.67it/s]
 51%|█████▏    | 29578/57600 [5:10:50<4:43:41,  1.65it/s]
 51%|█████▏    | 29579/57600 [5:10:51<4:47:57,  1.62it/s]
 51%|█████▏    | 29580/57600 [5:10:52<4:46:18,  1.63it/s]
                                                         
{'loss': 1.1609, 'learning_rate': 5.393379790940767e-07, 'epoch': 326.49}

 51%|█████▏    | 29580/57600 [5:10:52<4:46:18,  1.63it/s]
 51%|█████▏    | 29581/57600 [5:10:52<4:41:18,  1.66it/s]
 51%|█████▏    | 29582/57600 [5:10:53<4:40:36,  1.66it/s]
 51%|█████▏    | 29583/57600 [5:10:53<4:38:58,  1.67it/s]
 51%|█████▏    | 29584/57600 [5:10:54<4:45:36,  1.63it/s]
 51%|█████▏    | 29585/57600 [5:10:55<4:57:24,  1.57it/s]
 51%|█████▏    | 29586/57600 [5:10:55<4:51:17,  1.60it/s]
 51%|█████▏    | 29587/57600 [5:10:56<5:04:00,  1.54it/s]
 51%|█████▏    | 29588/57600 [5:10:57<4:55:43,  1.58it/s]
 51%|█████▏    | 29589/57600 [5:10:57<5:00:39,  1.55it/s]
 51%|█████▏    | 29590/57600 [5:10:58<4:50:01,  1.61it/s]
 51%|█████▏    | 29591/57600 [5:10:59<4:52:50,  1.59it/s]
 51%|█████▏    | 29592/57600 [5:10:59<4:51:39,  1.60it/s]
 51%|█████▏    | 29593/57600 [5:11:00<4:50:10,  1.61it/s]
 51%|█████▏    | 29594/57600 [5:11:00<4:52:12,  1.60it/s]
 51%|█████▏    | 29595/57600 [5:11:01<4:47:08,  1.63it/s]
 51%|█████▏    | 29596/57600 [5:11:02<4:52:20,  1.60it/s]
 51%|█████▏    | 29597/57600 [5:11:02<4:46:33,  1.63it/s]
 51%|█████▏    | 29598/57600 [5:11:03<4:49:43,  1.61it/s]
 51%|█████▏    | 29599/57600 [5:11:04<4:48:07,  1.62it/s]
 51%|█████▏    | 29600/57600 [5:11:04<4:47:52,  1.62it/s]
                                                         
{'loss': 1.1551, 'learning_rate': 5.390243902439024e-07, 'epoch': 326.71}

 51%|█████▏    | 29600/57600 [5:11:04<4:47:52,  1.62it/s]
 51%|█████▏    | 29601/57600 [5:11:05<4:55:15,  1.58it/s]
 51%|█████▏    | 29602/57600 [5:11:05<4:55:01,  1.58it/s]
 51%|█████▏    | 29603/57600 [5:11:06<4:52:48,  1.59it/s]
 51%|█████▏    | 29604/57600 [5:11:07<4:53:34,  1.59it/s]
 51%|█████▏    | 29605/57600 [5:11:07<4:46:04,  1.63it/s]
 51%|█████▏    | 29606/57600 [5:11:08<4:44:22,  1.64it/s]
 51%|█████▏    | 29607/57600 [5:11:09<4:44:54,  1.64it/s]
 51%|█████▏    | 29608/57600 [5:11:09<4:48:26,  1.62it/s]
 51%|█████▏    | 29609/57600 [5:11:10<4:41:41,  1.66it/s]
 51%|█████▏    | 29610/57600 [5:11:10<4:36:14,  1.69it/s]
 51%|█████▏    | 29611/57600 [5:11:11<4:44:57,  1.64it/s]
 51%|█████▏    | 29612/57600 [5:11:11<4:35:39,  1.69it/s]
 51%|█████▏    | 29613/57600 [5:11:12<4:36:01,  1.69it/s]
 51%|█████▏    | 29614/57600 [5:11:13<4:52:47,  1.59it/s]
 51%|█████▏    | 29615/57600 [5:11:13<4:47:29,  1.62it/s]
 51%|█████▏    | 29616/57600 [5:11:14<4:52:09,  1.60it/s]
 51%|█████▏    | 29617/57600 [5:11:15<4:49:51,  1.61it/s]
 51%|█████▏    | 29618/57600 [5:11:15<4:49:12,  1.61it/s]
 51%|█████▏    | 29619/57600 [5:11:16<4:51:23,  1.60it/s]
 51%|█████▏    | 29620/57600 [5:11:16<4:46:37,  1.63it/s]
                                                         
{'loss': 1.2131, 'learning_rate': 5.387108013937282e-07, 'epoch': 326.93}

 51%|█████▏    | 29620/57600 [5:11:16<4:46:37,  1.63it/s]
 51%|█████▏    | 29621/57600 [5:11:17<4:39:26,  1.67it/s]
 51%|█████▏    | 29622/57600 [5:11:18<4:51:03,  1.60it/s]
 51%|█████▏    | 29623/57600 [5:11:18<4:57:03,  1.57it/s]
 51%|█████▏    | 29624/57600 [5:11:19<4:59:53,  1.55it/s]
 51%|█████▏    | 29625/57600 [5:11:20<4:48:28,  1.62it/s]
 51%|█████▏    | 29626/57600 [5:11:20<4:45:05,  1.64it/s]
 51%|█████▏    | 29627/57600 [5:11:21<4:59:19,  1.56it/s]
 51%|█████▏    | 29628/57600 [5:11:21<4:49:30,  1.61it/s]
 51%|█████▏    | 29629/57600 [5:11:22<4:50:08,  1.61it/s]
 51%|█████▏    | 29630/57600 [5:11:23<4:49:28,  1.61it/s]
 51%|█████▏    | 29631/57600 [5:11:23<4:44:10,  1.64it/s]
 51%|█████▏    | 29632/57600 [5:11:24<4:41:44,  1.65it/s]
 51%|█████▏    | 29633/57600 [5:11:25<4:58:46,  1.56it/s]
 51%|█████▏    | 29634/57600 [5:11:25<4:52:20,  1.59it/s]
 51%|█████▏    | 29635/57600 [5:11:26<4:58:03,  1.56it/s]
 51%|█████▏    | 29636/57600 [5:11:27<4:56:54,  1.57it/s]
 51%|█████▏    | 29637/57600 [5:11:27<4:46:08,  1.63it/s]
 51%|█████▏    | 29638/57600 [5:11:28<4:43:52,  1.64it/s]
 51%|█████▏    | 29639/57600 [5:11:28<4:35:09,  1.69it/s]
 51%|█████▏    | 29640/57600 [5:11:29<4:35:12,  1.69it/s]
                                                         
{'loss': 1.2387, 'learning_rate': 5.38397212543554e-07, 'epoch': 327.15}

 51%|█████▏    | 29640/57600 [5:11:29<4:35:12,  1.69it/s]
 51%|█████▏    | 29641/57600 [5:11:30<4:46:11,  1.63it/s]
 51%|█████▏    | 29642/57600 [5:11:30<4:53:06,  1.59it/s]
 51%|█████▏    | 29643/57600 [5:11:31<4:51:36,  1.60it/s]
 51%|█████▏    | 29644/57600 [5:11:31<4:57:06,  1.57it/s]
 51%|█████▏    | 29645/57600 [5:11:32<5:10:50,  1.50it/s]
 51%|█████▏    | 29646/57600 [5:11:33<5:12:54,  1.49it/s]
 51%|█████▏    | 29647/57600 [5:11:33<5:03:24,  1.54it/s]
 51%|█████▏    | 29648/57600 [5:11:34<5:00:07,  1.55it/s]
 51%|█████▏    | 29649/57600 [5:11:35<5:00:26,  1.55it/s]
 51%|█████▏    | 29650/57600 [5:11:35<5:03:27,  1.54it/s]
 51%|█████▏    | 29651/57600 [5:11:36<5:05:02,  1.53it/s]
 51%|█████▏    | 29652/57600 [5:11:37<5:03:02,  1.54it/s]
 51%|█████▏    | 29653/57600 [5:11:37<4:52:51,  1.59it/s]
 51%|█████▏    | 29654/57600 [5:11:38<4:51:54,  1.60it/s]
 51%|█████▏    | 29655/57600 [5:11:39<4:56:50,  1.57it/s]
 51%|█████▏    | 29656/57600 [5:11:39<4:51:47,  1.60it/s]
 51%|█████▏    | 29657/57600 [5:11:40<4:52:58,  1.59it/s]
 51%|█████▏    | 29658/57600 [5:11:40<4:46:52,  1.62it/s]
 51%|█████▏    | 29659/57600 [5:11:41<4:47:38,  1.62it/s]
 51%|█████▏    | 29660/57600 [5:11:42<4:43:25,  1.64it/s]
                                                         
{'loss': 1.1454, 'learning_rate': 5.380836236933798e-07, 'epoch': 327.37}

 51%|█████▏    | 29660/57600 [5:11:42<4:43:25,  1.64it/s]
 51%|█████▏    | 29661/57600 [5:11:42<4:47:42,  1.62it/s]
 51%|█████▏    | 29662/57600 [5:11:43<4:43:07,  1.64it/s]
 51%|█████▏    | 29663/57600 [5:11:44<4:55:51,  1.57it/s]
 52%|█████▏    | 29664/57600 [5:11:44<4:53:27,  1.59it/s]
 52%|█████▏    | 29665/57600 [5:11:45<4:49:10,  1.61it/s]
 52%|█████▏    | 29666/57600 [5:11:45<4:57:08,  1.57it/s]
 52%|█████▏    | 29667/57600 [5:11:46<4:54:23,  1.58it/s]
 52%|█████▏    | 29668/57600 [5:11:47<4:59:55,  1.55it/s]
 52%|█████▏    | 29669/57600 [5:11:47<4:51:02,  1.60it/s]
 52%|█████▏    | 29670/57600 [5:11:48<5:00:22,  1.55it/s]
 52%|█████▏    | 29671/57600 [5:11:49<4:56:32,  1.57it/s]
 52%|█████▏    | 29672/57600 [5:11:49<5:02:19,  1.54it/s]
 52%|█████▏    | 29673/57600 [5:11:50<4:52:57,  1.59it/s]
 52%|█████▏    | 29674/57600 [5:11:51<4:54:53,  1.58it/s]
 52%|█████▏    | 29675/57600 [5:11:51<4:48:55,  1.61it/s]
 52%|█████▏    | 29676/57600 [5:11:52<4:52:05,  1.59it/s]
 52%|█████▏    | 29677/57600 [5:11:52<4:41:45,  1.65it/s]
 52%|█████▏    | 29678/57600 [5:11:53<4:39:43,  1.66it/s]
 52%|█████▏    | 29679/57600 [5:11:54<4:43:58,  1.64it/s]
 52%|█████▏    | 29680/57600 [5:11:54<4:51:49,  1.59it/s]
                                                         
{'loss': 1.1845, 'learning_rate': 5.377700348432055e-07, 'epoch': 327.59}

 52%|█████▏    | 29680/57600 [5:11:54<4:51:49,  1.59it/s]
 52%|█████▏    | 29681/57600 [5:11:55<4:43:15,  1.64it/s]
 52%|█████▏    | 29682/57600 [5:11:55<4:39:35,  1.66it/s]
 52%|█████▏    | 29683/57600 [5:11:56<4:53:56,  1.58it/s]
 52%|█████▏    | 29684/57600 [5:11:57<4:52:36,  1.59it/s]
 52%|█████▏    | 29685/57600 [5:11:57<4:51:26,  1.60it/s]
 52%|█████▏    | 29686/57600 [5:11:58<4:46:21,  1.62it/s]
 52%|█████▏    | 29687/57600 [5:11:58<4:46:07,  1.63it/s]
 52%|█████▏    | 29688/57600 [5:11:59<4:41:04,  1.66it/s]
 52%|█████▏    | 29689/57600 [5:12:00<4:44:10,  1.64it/s]
 52%|█████▏    | 29690/57600 [5:12:00<4:47:24,  1.62it/s]
 52%|█████▏    | 29691/57600 [5:12:01<4:48:53,  1.61it/s]
 52%|█████▏    | 29692/57600 [5:12:02<4:47:12,  1.62it/s]
 52%|█████▏    | 29693/57600 [5:12:02<4:42:21,  1.65it/s]
 52%|█████▏    | 29694/57600 [5:12:03<4:36:49,  1.68it/s]
 52%|█████▏    | 29695/57600 [5:12:03<4:36:14,  1.68it/s]
 52%|█████▏    | 29696/57600 [5:12:04<4:39:22,  1.66it/s]
 52%|█████▏    | 29697/57600 [5:12:05<4:37:19,  1.68it/s]
 52%|█████▏    | 29698/57600 [5:12:05<4:47:35,  1.62it/s]
 52%|█████▏    | 29699/57600 [5:12:06<4:46:36,  1.62it/s]
 52%|█████▏    | 29700/57600 [5:12:06<4:48:54,  1.61it/s]
                                                         
{'loss': 1.1905, 'learning_rate': 5.374564459930314e-07, 'epoch': 327.81}

 52%|█████▏    | 29700/57600 [5:12:06<4:48:54,  1.61it/s]
 52%|█████▏    | 29701/57600 [5:12:07<4:41:22,  1.65it/s]
 52%|█████▏    | 29702/57600 [5:12:08<4:54:15,  1.58it/s]
 52%|█████▏    | 29703/57600 [5:12:08<4:48:52,  1.61it/s]
 52%|█████▏    | 29704/57600 [5:12:09<4:47:10,  1.62it/s]
 52%|█████▏    | 29705/57600 [5:12:10<4:52:45,  1.59it/s]
 52%|█████▏    | 29706/57600 [5:12:10<4:57:36,  1.56it/s]
 52%|█████▏    | 29707/57600 [5:12:11<4:59:12,  1.55it/s]
 52%|█████▏    | 29708/57600 [5:12:11<4:46:08,  1.62it/s]
 52%|█████▏    | 29709/57600 [5:12:12<4:42:46,  1.64it/s]
 52%|█████▏    | 29710/57600 [5:12:13<4:40:38,  1.66it/s]
 52%|█████▏    | 29711/57600 [5:12:13<4:51:24,  1.60it/s]
 52%|█████▏    | 29712/57600 [5:12:14<4:51:01,  1.60it/s]
 52%|█████▏    | 29713/57600 [5:12:15<4:52:08,  1.59it/s]
 52%|█████▏    | 29714/57600 [5:12:15<4:49:44,  1.60it/s]
 52%|█████▏    | 29715/57600 [5:12:16<4:40:59,  1.65it/s]
 52%|█████▏    | 29716/57600 [5:12:16<4:48:25,  1.61it/s]
 52%|█████▏    | 29717/57600 [5:12:17<4:58:57,  1.55it/s]
 52%|█████▏    | 29718/57600 [5:12:18<4:53:55,  1.58it/s]
 52%|█████▏    | 29719/57600 [5:12:18<4:46:33,  1.62it/s]
 52%|█████▏    | 29720/57600 [5:12:19<4:42:16,  1.65it/s]
                                                         
{'loss': 1.1777, 'learning_rate': 5.371428571428572e-07, 'epoch': 328.04}

 52%|█████▏    | 29720/57600 [5:12:19<4:42:16,  1.65it/s]
 52%|█████▏    | 29721/57600 [5:12:20<4:50:01,  1.60it/s]
 52%|█████▏    | 29722/57600 [5:12:20<4:46:48,  1.62it/s]
 52%|█████▏    | 29723/57600 [5:12:21<4:40:24,  1.66it/s]
 52%|█████▏    | 29724/57600 [5:12:21<4:40:32,  1.66it/s]
 52%|█████▏    | 29725/57600 [5:12:22<4:47:15,  1.62it/s]
 52%|█████▏    | 29726/57600 [5:12:22<4:37:21,  1.68it/s]
 52%|█████▏    | 29727/57600 [5:12:23<4:49:34,  1.60it/s]
 52%|█████▏    | 29728/57600 [5:12:24<4:49:35,  1.60it/s]
 52%|█████▏    | 29729/57600 [5:12:24<4:53:22,  1.58it/s]
 52%|█████▏    | 29730/57600 [5:12:25<4:47:15,  1.62it/s]
 52%|█████▏    | 29731/57600 [5:12:26<4:48:37,  1.61it/s]
 52%|█████▏    | 29732/57600 [5:12:26<4:51:38,  1.59it/s]
 52%|█████▏    | 29733/57600 [5:12:27<4:53:51,  1.58it/s]
 52%|█████▏    | 29734/57600 [5:12:28<4:58:26,  1.56it/s]
 52%|█████▏    | 29735/57600 [5:12:28<4:44:02,  1.64it/s]
 52%|█████▏    | 29736/57600 [5:12:29<4:47:17,  1.62it/s]
 52%|█████▏    | 29737/57600 [5:12:29<4:45:49,  1.62it/s]
 52%|█████▏    | 29738/57600 [5:12:30<4:38:50,  1.67it/s]
 52%|█████▏    | 29739/57600 [5:12:31<4:41:38,  1.65it/s]
 52%|█████▏    | 29740/57600 [5:12:31<4:38:16,  1.67it/s]
                                                         
{'loss': 1.176, 'learning_rate': 5.368292682926828e-07, 'epoch': 328.26}

 52%|█████▏    | 29740/57600 [5:12:31<4:38:16,  1.67it/s]
 52%|█████▏    | 29741/57600 [5:12:32<4:42:49,  1.64it/s]
 52%|█████▏    | 29742/57600 [5:12:32<4:42:03,  1.65it/s]
 52%|█████▏    | 29743/57600 [5:12:33<4:44:48,  1.63it/s]
 52%|█████▏    | 29744/57600 [5:12:34<4:44:17,  1.63it/s]
 52%|█████▏    | 29745/57600 [5:12:34<4:46:43,  1.62it/s]
 52%|█████▏    | 29746/57600 [5:12:35<4:46:48,  1.62it/s]
 52%|█████▏    | 29747/57600 [5:12:36<4:48:03,  1.61it/s]
 52%|█████▏    | 29748/57600 [5:12:36<4:55:36,  1.57it/s]
 52%|█████▏    | 29749/57600 [5:12:37<5:09:04,  1.50it/s]
 52%|█████▏    | 29750/57600 [5:12:38<4:59:46,  1.55it/s]
 52%|█████▏    | 29751/57600 [5:12:38<4:57:35,  1.56it/s]
 52%|█████▏    | 29752/57600 [5:12:39<4:53:22,  1.58it/s]
 52%|█████▏    | 29753/57600 [5:12:39<5:01:30,  1.54it/s]
 52%|█████▏    | 29754/57600 [5:12:40<4:57:54,  1.56it/s]
 52%|█████▏    | 29755/57600 [5:12:41<4:53:28,  1.58it/s]
 52%|█████▏    | 29756/57600 [5:12:41<4:51:48,  1.59it/s]
 52%|█████▏    | 29757/57600 [5:12:42<4:54:20,  1.58it/s]
 52%|█████▏    | 29758/57600 [5:12:43<4:50:52,  1.60it/s]
 52%|█████▏    | 29759/57600 [5:12:43<4:46:52,  1.62it/s]
 52%|█████▏    | 29760/57600 [5:12:44<4:48:00,  1.61it/s]
                                                         
{'loss': 1.1587, 'learning_rate': 5.365156794425087e-07, 'epoch': 328.48}

 52%|█████▏    | 29760/57600 [5:12:44<4:48:00,  1.61it/s]
 52%|█████▏    | 29761/57600 [5:12:44<4:52:46,  1.58it/s]
 52%|█████▏    | 29762/57600 [5:12:45<5:02:08,  1.54it/s]
 52%|█████▏    | 29763/57600 [5:12:46<4:54:58,  1.57it/s]
 52%|█████▏    | 29764/57600 [5:12:46<4:50:57,  1.59it/s]
 52%|█████▏    | 29765/57600 [5:12:47<4:56:08,  1.57it/s]
 52%|█████▏    | 29766/57600 [5:12:48<4:55:09,  1.57it/s]
 52%|█████▏    | 29767/57600 [5:12:48<4:57:30,  1.56it/s]
 52%|█████▏    | 29768/57600 [5:12:49<4:49:51,  1.60it/s]
 52%|█████▏    | 29769/57600 [5:12:50<4:49:31,  1.60it/s]
 52%|█████▏    | 29770/57600 [5:12:50<4:44:08,  1.63it/s]
 52%|█████▏    | 29771/57600 [5:12:51<4:43:50,  1.63it/s]
 52%|█████▏    | 29772/57600 [5:12:51<4:39:51,  1.66it/s]
 52%|█████▏    | 29773/57600 [5:12:52<4:35:26,  1.68it/s]
 52%|█████▏    | 29774/57600 [5:12:53<4:48:56,  1.61it/s]
 52%|█████▏    | 29775/57600 [5:12:53<4:40:22,  1.65it/s]
 52%|█████▏    | 29776/57600 [5:12:54<4:45:31,  1.62it/s]
 52%|█████▏    | 29777/57600 [5:12:54<4:42:15,  1.64it/s]
 52%|█████▏    | 29778/57600 [5:12:55<4:37:35,  1.67it/s]
 52%|█████▏    | 29779/57600 [5:12:55<4:34:41,  1.69it/s]
 52%|█████▏    | 29780/57600 [5:12:56<4:42:12,  1.64it/s]
                                                         
{'loss': 1.189, 'learning_rate': 5.362020905923344e-07, 'epoch': 328.7}

 52%|█████▏    | 29780/57600 [5:12:56<4:42:12,  1.64it/s]
 52%|█████▏    | 29781/57600 [5:12:57<4:38:09,  1.67it/s]
 52%|█████▏    | 29782/57600 [5:12:57<4:39:18,  1.66it/s]
 52%|█████▏    | 29783/57600 [5:12:58<4:34:31,  1.69it/s]
 52%|█████▏    | 29784/57600 [5:12:59<4:36:38,  1.68it/s]
 52%|█████▏    | 29785/57600 [5:12:59<4:57:10,  1.56it/s]
 52%|█████▏    | 29786/57600 [5:13:00<4:57:32,  1.56it/s]
 52%|█████▏    | 29787/57600 [5:13:00<4:47:38,  1.61it/s]
 52%|█████▏    | 29788/57600 [5:13:01<4:51:25,  1.59it/s]
 52%|█████▏    | 29789/57600 [5:13:02<4:43:34,  1.63it/s]
 52%|█████▏    | 29790/57600 [5:13:02<4:47:02,  1.61it/s]
 52%|█████▏    | 29791/57600 [5:13:03<4:41:54,  1.64it/s]
 52%|█████▏    | 29792/57600 [5:13:04<4:48:44,  1.61it/s]
 52%|█████▏    | 29793/57600 [5:13:04<4:40:46,  1.65it/s]
 52%|█████▏    | 29794/57600 [5:13:05<4:38:51,  1.66it/s]
 52%|█████▏    | 29795/57600 [5:13:05<4:35:38,  1.68it/s]
 52%|█████▏    | 29796/57600 [5:13:06<4:38:02,  1.67it/s]
 52%|█████▏    | 29797/57600 [5:13:07<4:46:49,  1.62it/s]
 52%|█████▏    | 29798/57600 [5:13:07<4:39:46,  1.66it/s]
 52%|█████▏    | 29799/57600 [5:13:08<4:46:39,  1.62it/s]
 52%|█████▏    | 29800/57600 [5:13:08<4:49:22,  1.60it/s]
                                                         
{'loss': 1.1826, 'learning_rate': 5.358885017421602e-07, 'epoch': 328.92}

 52%|█████▏    | 29800/57600 [5:13:08<4:49:22,  1.60it/s]
 52%|█████▏    | 29801/57600 [5:13:09<4:48:14,  1.61it/s]
 52%|█████▏    | 29802/57600 [5:13:10<5:06:10,  1.51it/s]
 52%|█████▏    | 29803/57600 [5:13:10<4:58:18,  1.55it/s]
 52%|█████▏    | 29804/57600 [5:13:11<5:01:45,  1.54it/s]
 52%|█████▏    | 29805/57600 [5:13:12<4:56:54,  1.56it/s]
 52%|█████▏    | 29806/57600 [5:13:12<4:48:31,  1.61it/s]
 52%|█████▏    | 29807/57600 [5:13:13<4:55:28,  1.57it/s]
 52%|█████▏    | 29808/57600 [5:13:14<5:01:28,  1.54it/s]
 52%|█████▏    | 29809/57600 [5:13:14<4:57:38,  1.56it/s]
 52%|█████▏    | 29810/57600 [5:13:15<4:48:18,  1.61it/s]
 52%|█████▏    | 29811/57600 [5:13:15<4:45:55,  1.62it/s]
 52%|█████▏    | 29812/57600 [5:13:16<4:44:03,  1.63it/s]
 52%|█████▏    | 29813/57600 [5:13:17<4:41:11,  1.65it/s]
 52%|█████▏    | 29814/57600 [5:13:17<4:40:29,  1.65it/s]
 52%|█████▏    | 29815/57600 [5:13:18<4:44:15,  1.63it/s]
 52%|█████▏    | 29816/57600 [5:13:18<4:39:16,  1.66it/s]
 52%|█████▏    | 29817/57600 [5:13:19<4:45:59,  1.62it/s]
 52%|█████▏    | 29818/57600 [5:13:20<4:47:26,  1.61it/s]
 52%|█████▏    | 29819/57600 [5:13:20<4:45:03,  1.62it/s]
 52%|█████▏    | 29820/57600 [5:13:21<4:36:03,  1.68it/s]
                                                         
{'loss': 1.182, 'learning_rate': 5.35574912891986e-07, 'epoch': 329.14}

 52%|█████▏    | 29820/57600 [5:13:21<4:36:03,  1.68it/s]
 52%|█████▏    | 29821/57600 [5:13:21<4:35:40,  1.68it/s]
 52%|█████▏    | 29822/57600 [5:13:22<4:40:52,  1.65it/s]
 52%|█████▏    | 29823/57600 [5:13:23<4:39:19,  1.66it/s]
 52%|█████▏    | 29824/57600 [5:13:23<4:43:29,  1.63it/s]
 52%|█████▏    | 29825/57600 [5:13:24<4:42:31,  1.64it/s]
 52%|█████▏    | 29826/57600 [5:13:25<4:46:26,  1.62it/s]
 52%|█████▏    | 29827/57600 [5:13:25<4:47:24,  1.61it/s]
 52%|█████▏    | 29828/57600 [5:13:26<4:36:47,  1.67it/s]
 52%|█████▏    | 29829/57600 [5:13:26<4:43:27,  1.63it/s]
 52%|█████▏    | 29830/57600 [5:13:27<4:52:09,  1.58it/s]
 52%|█████▏    | 29831/57600 [5:13:28<4:55:18,  1.57it/s]
 52%|█████▏    | 29832/57600 [5:13:28<4:51:20,  1.59it/s]
 52%|█████▏    | 29833/57600 [5:13:29<4:47:42,  1.61it/s]
 52%|█████▏    | 29834/57600 [5:13:30<4:45:49,  1.62it/s]
 52%|█████▏    | 29835/57600 [5:13:30<4:49:21,  1.60it/s]
 52%|█████▏    | 29836/57600 [5:13:31<4:48:57,  1.60it/s]
 52%|█████▏    | 29837/57600 [5:13:31<4:52:37,  1.58it/s]
 52%|█████▏    | 29838/57600 [5:13:32<4:45:31,  1.62it/s]
 52%|█████▏    | 29839/57600 [5:13:33<4:38:33,  1.66it/s]
 52%|█████▏    | 29840/57600 [5:13:33<4:35:19,  1.68it/s]
                                                         
{'loss': 1.1905, 'learning_rate': 5.352613240418117e-07, 'epoch': 329.36}

 52%|█████▏    | 29840/57600 [5:13:33<4:35:19,  1.68it/s]
 52%|█████▏    | 29841/57600 [5:13:34<4:42:17,  1.64it/s]
 52%|█████▏    | 29842/57600 [5:13:34<4:41:56,  1.64it/s]
 52%|█████▏    | 29843/57600 [5:13:35<4:41:11,  1.65it/s]
 52%|█████▏    | 29844/57600 [5:13:36<4:42:29,  1.64it/s]
 52%|█████▏    | 29845/57600 [5:13:36<4:50:50,  1.59it/s]
 52%|█████▏    | 29846/57600 [5:13:37<5:03:49,  1.52it/s]
 52%|█████▏    | 29847/57600 [5:13:38<4:56:27,  1.56it/s]
 52%|█████▏    | 29848/57600 [5:13:38<4:59:23,  1.54it/s]
 52%|█████▏    | 29849/57600 [5:13:39<4:57:17,  1.56it/s]
 52%|█████▏    | 29850/57600 [5:13:40<4:44:52,  1.62it/s]
 52%|█████▏    | 29851/57600 [5:13:40<4:40:45,  1.65it/s]
 52%|█████▏    | 29852/57600 [5:13:41<4:51:39,  1.59it/s]
 52%|█████▏    | 29853/57600 [5:13:41<4:45:19,  1.62it/s]
 52%|█████▏    | 29854/57600 [5:13:42<4:42:29,  1.64it/s]
 52%|█████▏    | 29855/57600 [5:13:43<4:43:45,  1.63it/s]
 52%|█████▏    | 29856/57600 [5:13:43<4:52:10,  1.58it/s]
 52%|█████▏    | 29857/57600 [5:13:44<4:47:37,  1.61it/s]
 52%|█████▏    | 29858/57600 [5:13:44<4:47:03,  1.61it/s]
 52%|█████▏    | 29859/57600 [5:13:45<4:45:52,  1.62it/s]
 52%|█████▏    | 29860/57600 [5:13:46<4:45:55,  1.62it/s]
                                                         
{'loss': 1.1627, 'learning_rate': 5.349477351916376e-07, 'epoch': 329.58}

 52%|█████▏    | 29860/57600 [5:13:46<4:45:55,  1.62it/s]
 52%|█████▏    | 29861/57600 [5:13:46<4:52:33,  1.58it/s]
 52%|█████▏    | 29862/57600 [5:13:47<4:50:42,  1.59it/s]
 52%|█████▏    | 29863/57600 [5:13:48<4:54:13,  1.57it/s]
 52%|█████▏    | 29864/57600 [5:13:48<4:49:21,  1.60it/s]
 52%|█████▏    | 29865/57600 [5:13:49<4:51:39,  1.58it/s]
 52%|█████▏    | 29866/57600 [5:13:50<4:52:15,  1.58it/s]
 52%|█████▏    | 29867/57600 [5:13:50<4:50:08,  1.59it/s]
 52%|█████▏    | 29868/57600 [5:13:51<4:58:38,  1.55it/s]
 52%|█████▏    | 29869/57600 [5:13:51<4:59:03,  1.55it/s]
 52%|█████▏    | 29870/57600 [5:13:52<4:57:29,  1.55it/s]
 52%|█████▏    | 29871/57600 [5:13:53<4:45:54,  1.62it/s]
 52%|█████▏    | 29872/57600 [5:13:53<4:49:49,  1.59it/s]
 52%|█████▏    | 29873/57600 [5:13:54<4:47:20,  1.61it/s]
 52%|█████▏    | 29874/57600 [5:13:55<4:47:26,  1.61it/s]
 52%|█████▏    | 29875/57600 [5:13:55<4:44:53,  1.62it/s]
 52%|█████▏    | 29876/57600 [5:13:56<4:36:13,  1.67it/s]
 52%|█████▏    | 29877/57600 [5:13:56<4:51:24,  1.59it/s]
 52%|█████▏    | 29878/57600 [5:13:57<4:52:33,  1.58it/s]
 52%|█████▏    | 29879/57600 [5:13:58<4:41:58,  1.64it/s]
 52%|█████▏    | 29880/57600 [5:13:58<4:48:10,  1.60it/s]
                                                         
{'loss': 1.1429, 'learning_rate': 5.346341463414634e-07, 'epoch': 329.8}

 52%|█████▏    | 29880/57600 [5:13:58<4:48:10,  1.60it/s]
 52%|█████▏    | 29881/57600 [5:13:59<4:42:37,  1.63it/s]
 52%|█████▏    | 29882/57600 [5:13:59<4:40:57,  1.64it/s]
 52%|█████▏    | 29883/57600 [5:14:00<4:35:31,  1.68it/s]
 52%|█████▏    | 29884/57600 [5:14:01<4:49:39,  1.59it/s]
 52%|█████▏    | 29885/57600 [5:14:01<4:42:36,  1.63it/s]
 52%|█████▏    | 29886/57600 [5:14:02<4:49:07,  1.60it/s]
 52%|█████▏    | 29887/57600 [5:14:03<4:51:42,  1.58it/s]
 52%|█████▏    | 29888/57600 [5:14:03<5:08:06,  1.50it/s]
 52%|█████▏    | 29889/57600 [5:14:04<4:59:44,  1.54it/s]
 52%|█████▏    | 29890/57600 [5:14:05<4:52:45,  1.58it/s]
 52%|█████▏    | 29891/57600 [5:14:05<4:47:02,  1.61it/s]
 52%|█████▏    | 29892/57600 [5:14:06<4:51:13,  1.59it/s]
 52%|█████▏    | 29893/57600 [5:14:06<4:49:38,  1.59it/s]
 52%|█████▏    | 29894/57600 [5:14:07<4:49:08,  1.60it/s]
 52%|█████▏    | 29895/57600 [5:14:08<4:46:58,  1.61it/s]
 52%|█████▏    | 29896/57600 [5:14:08<4:43:39,  1.63it/s]
 52%|█████▏    | 29897/57600 [5:14:09<4:39:02,  1.65it/s]
 52%|█████▏    | 29898/57600 [5:14:09<4:48:10,  1.60it/s]
 52%|█████▏    | 29899/57600 [5:14:10<5:07:26,  1.50it/s]
 52%|█████▏    | 29900/57600 [5:14:11<4:57:06,  1.55it/s]
                                                         
{'loss': 1.1788, 'learning_rate': 5.343205574912892e-07, 'epoch': 330.02}

 52%|█████▏    | 29900/57600 [5:14:11<4:57:06,  1.55it/s]
 52%|█████▏    | 29901/57600 [5:14:11<4:50:16,  1.59it/s]
 52%|█████▏    | 29902/57600 [5:14:12<4:57:37,  1.55it/s]
 52%|█████▏    | 29903/57600 [5:14:13<4:50:33,  1.59it/s]
 52%|█████▏    | 29904/57600 [5:14:13<4:39:37,  1.65it/s]
 52%|█████▏    | 29905/57600 [5:14:14<4:49:05,  1.60it/s]
 52%|█████▏    | 29906/57600 [5:14:15<4:49:09,  1.60it/s]
 52%|█████▏    | 29907/57600 [5:14:15<4:49:19,  1.60it/s]
 52%|█████▏    | 29908/57600 [5:14:16<4:50:01,  1.59it/s]
 52%|█████▏    | 29909/57600 [5:14:16<4:49:44,  1.59it/s]
 52%|█████▏    | 29910/57600 [5:14:17<4:42:23,  1.63it/s]
 52%|█████▏    | 29911/57600 [5:14:18<4:45:36,  1.62it/s]
 52%|█████▏    | 29912/57600 [5:14:18<4:47:27,  1.61it/s]
 52%|█████▏    | 29913/57600 [5:14:19<4:55:24,  1.56it/s]
 52%|█████▏    | 29914/57600 [5:14:20<4:57:36,  1.55it/s]
 52%|█████▏    | 29915/57600 [5:14:20<4:57:15,  1.55it/s]
 52%|█████▏    | 29916/57600 [5:14:21<4:54:43,  1.57it/s]
 52%|█████▏    | 29917/57600 [5:14:22<4:49:01,  1.60it/s]
 52%|█████▏    | 29918/57600 [5:14:22<5:00:15,  1.54it/s]
 52%|█████▏    | 29919/57600 [5:14:23<4:56:28,  1.56it/s]
 52%|█████▏    | 29920/57600 [5:14:24<5:01:28,  1.53it/s]
                                                         
{'loss': 1.139, 'learning_rate': 5.34006968641115e-07, 'epoch': 330.24}

 52%|█████▏    | 29920/57600 [5:14:24<5:01:28,  1.53it/s]
 52%|█████▏    | 29921/57600 [5:14:24<4:54:44,  1.57it/s]
 52%|█████▏    | 29922/57600 [5:14:25<4:46:36,  1.61it/s]
 52%|█████▏    | 29923/57600 [5:14:25<4:40:34,  1.64it/s]
 52%|█████▏    | 29924/57600 [5:14:26<4:34:18,  1.68it/s]
 52%|█████▏    | 29925/57600 [5:14:26<4:39:20,  1.65it/s]
 52%|█████▏    | 29926/57600 [5:14:27<4:39:09,  1.65it/s]
 52%|█████▏    | 29927/57600 [5:14:28<4:37:03,  1.66it/s]
 52%|█████▏    | 29928/57600 [5:14:28<4:33:54,  1.68it/s]
 52%|█████▏    | 29929/57600 [5:14:29<4:36:53,  1.67it/s]
 52%|█████▏    | 29930/57600 [5:14:29<4:39:22,  1.65it/s]
 52%|█████▏    | 29931/57600 [5:14:30<4:45:22,  1.62it/s]
 52%|█████▏    | 29932/57600 [5:14:31<4:45:35,  1.61it/s]
 52%|█████▏    | 29933/57600 [5:14:31<4:47:32,  1.60it/s]
 52%|█████▏    | 29934/57600 [5:14:32<4:41:10,  1.64it/s]
 52%|█████▏    | 29935/57600 [5:14:33<4:48:25,  1.60it/s]
 52%|█████▏    | 29936/57600 [5:14:33<4:44:36,  1.62it/s]
 52%|█████▏    | 29937/57600 [5:14:34<4:37:31,  1.66it/s]
 52%|█████▏    | 29938/57600 [5:14:34<4:37:02,  1.66it/s]
 52%|█████▏    | 29939/57600 [5:14:35<4:40:16,  1.64it/s]
 52%|█████▏    | 29940/57600 [5:14:36<4:39:06,  1.65it/s]
                                                         
{'loss': 1.195, 'learning_rate': 5.336933797909408e-07, 'epoch': 330.46}

 52%|█████▏    | 29940/57600 [5:14:36<4:39:06,  1.65it/s]
 52%|█████▏    | 29941/57600 [5:14:36<4:47:11,  1.61it/s]
 52%|█████▏    | 29942/57600 [5:14:37<4:40:47,  1.64it/s]
 52%|█████▏    | 29943/57600 [5:14:37<4:46:21,  1.61it/s]
 52%|█████▏    | 29944/57600 [5:14:38<4:47:51,  1.60it/s]
 52%|█████▏    | 29945/57600 [5:14:39<4:38:51,  1.65it/s]
 52%|█████▏    | 29946/57600 [5:14:39<4:35:19,  1.67it/s]
 52%|█████▏    | 29947/57600 [5:14:40<4:39:19,  1.65it/s]
 52%|█████▏    | 29948/57600 [5:14:40<4:35:25,  1.67it/s]
 52%|█████▏    | 29949/57600 [5:14:41<4:32:46,  1.69it/s]
 52%|█████▏    | 29950/57600 [5:14:42<4:37:29,  1.66it/s]
 52%|█████▏    | 29951/57600 [5:14:42<4:38:21,  1.66it/s]
 52%|█████▏    | 29952/57600 [5:14:43<4:42:31,  1.63it/s]
 52%|█████▏    | 29953/57600 [5:14:44<4:40:30,  1.64it/s]
 52%|█████▏    | 29954/57600 [5:14:44<4:47:11,  1.60it/s]
 52%|█████▏    | 29955/57600 [5:14:45<4:52:21,  1.58it/s]
 52%|█████▏    | 29956/57600 [5:14:45<4:49:49,  1.59it/s]
 52%|█████▏    | 29957/57600 [5:14:46<4:54:10,  1.57it/s]
 52%|█████▏    | 29958/57600 [5:14:47<4:58:33,  1.54it/s]
 52%|█████▏    | 29959/57600 [5:14:47<5:05:48,  1.51it/s]
 52%|█████▏    | 29960/57600 [5:14:48<4:58:45,  1.54it/s]
                                                         
{'loss': 1.1667, 'learning_rate': 5.333797909407665e-07, 'epoch': 330.68}

 52%|█████▏    | 29960/57600 [5:14:48<4:58:45,  1.54it/s]
 52%|█████▏    | 29961/57600 [5:14:49<4:53:52,  1.57it/s]
 52%|█████▏    | 29962/57600 [5:14:49<4:58:33,  1.54it/s]
 52%|█████▏    | 29963/57600 [5:14:50<4:47:17,  1.60it/s]
 52%|█████▏    | 29964/57600 [5:14:51<4:47:44,  1.60it/s]
 52%|█████▏    | 29965/57600 [5:14:51<5:04:26,  1.51it/s]
 52%|█████▏    | 29966/57600 [5:14:52<4:51:08,  1.58it/s]
 52%|█████▏    | 29967/57600 [5:14:52<4:39:45,  1.65it/s]
 52%|█████▏    | 29968/57600 [5:14:53<4:52:04,  1.58it/s]
 52%|█████▏    | 29969/57600 [5:14:54<4:44:48,  1.62it/s]
 52%|█████▏    | 29970/57600 [5:14:54<4:44:17,  1.62it/s]
 52%|█████▏    | 29971/57600 [5:14:55<4:38:24,  1.65it/s]
 52%|█████▏    | 29972/57600 [5:14:56<5:02:24,  1.52it/s]
 52%|█████▏    | 29973/57600 [5:14:56<4:55:29,  1.56it/s]
 52%|█████▏    | 29974/57600 [5:14:57<4:43:46,  1.62it/s]
 52%|█████▏    | 29975/57600 [5:14:57<4:43:25,  1.62it/s]
 52%|█████▏    | 29976/57600 [5:14:58<4:33:36,  1.68it/s]
 52%|█████▏    | 29977/57600 [5:14:59<4:43:55,  1.62it/s]
 52%|█████▏    | 29978/57600 [5:14:59<4:57:19,  1.55it/s]
 52%|█████▏    | 29979/57600 [5:15:00<4:48:33,  1.60it/s]
 52%|█████▏    | 29980/57600 [5:15:01<4:51:58,  1.58it/s]
                                                         
{'loss': 1.2169, 'learning_rate': 5.330662020905923e-07, 'epoch': 330.91}

 52%|█████▏    | 29980/57600 [5:15:01<4:51:58,  1.58it/s]
 52%|█████▏    | 29981/57600 [5:15:01<4:43:37,  1.62it/s]
 52%|█████▏    | 29982/57600 [5:15:02<4:44:03,  1.62it/s]
 52%|█████▏    | 29983/57600 [5:15:02<4:42:56,  1.63it/s]
 52%|█████▏    | 29984/57600 [5:15:03<4:38:19,  1.65it/s]
 52%|█████▏    | 29985/57600 [5:15:04<4:30:08,  1.70it/s]
 52%|█████▏    | 29986/57600 [5:15:04<4:27:48,  1.72it/s]
 52%|█████▏    | 29987/57600 [5:15:05<4:37:13,  1.66it/s]
 52%|█████▏    | 29988/57600 [5:15:05<4:37:08,  1.66it/s]
 52%|█████▏    | 29989/57600 [5:15:06<4:53:25,  1.57it/s]
 52%|█████▏    | 29990/57600 [5:15:07<4:44:06,  1.62it/s]
 52%|█████▏    | 29991/57600 [5:15:07<4:38:30,  1.65it/s]
 52%|█████▏    | 29992/57600 [5:15:08<4:32:08,  1.69it/s]
 52%|█████▏    | 29993/57600 [5:15:08<4:36:37,  1.66it/s]
 52%|█████▏    | 29994/57600 [5:15:09<4:33:46,  1.68it/s]
 52%|█████▏    | 29995/57600 [5:15:10<4:33:23,  1.68it/s]
 52%|█████▏    | 29996/57600 [5:15:10<4:34:13,  1.68it/s]
 52%|█████▏    | 29997/57600 [5:15:11<4:38:09,  1.65it/s]
 52%|█████▏    | 29998/57600 [5:15:11<4:39:59,  1.64it/s]
 52%|█████▏    | 29999/57600 [5:15:12<4:45:09,  1.61it/s]
 52%|█████▏    | 30000/57600 [5:15:13<4:37:51,  1.66it/s]
                                                         
{'loss': 1.2115, 'learning_rate': 5.327526132404182e-07, 'epoch': 331.13}

 52%|█████▏    | 30000/57600 [5:15:13<4:37:51,  1.66it/s]
 52%|█████▏    | 30001/57600 [5:15:13<4:39:11,  1.65it/s]
 52%|█████▏    | 30002/57600 [5:15:14<4:44:10,  1.62it/s]
 52%|█████▏    | 30003/57600 [5:15:15<5:00:00,  1.53it/s]
 52%|█████▏    | 30004/57600 [5:15:15<5:02:31,  1.52it/s]
 52%|█████▏    | 30005/57600 [5:15:16<4:53:44,  1.57it/s]
 52%|█████▏    | 30006/57600 [5:15:16<4:44:30,  1.62it/s]
 52%|█████▏    | 30007/57600 [5:15:17<4:39:35,  1.64it/s]
 52%|█████▏    | 30008/57600 [5:15:18<4:43:46,  1.62it/s]
 52%|█████▏    | 30009/57600 [5:15:18<4:49:06,  1.59it/s]
 52%|█████▏    | 30010/57600 [5:15:19<4:50:49,  1.58it/s]
 52%|█████▏    | 30011/57600 [5:15:20<4:57:48,  1.54it/s]
 52%|█████▏    | 30012/57600 [5:15:20<4:49:47,  1.59it/s]
 52%|█████▏    | 30013/57600 [5:15:21<4:47:46,  1.60it/s]
 52%|█████▏    | 30014/57600 [5:15:22<4:52:02,  1.57it/s]
 52%|█████▏    | 30015/57600 [5:15:22<4:45:42,  1.61it/s]
 52%|█████▏    | 30016/57600 [5:15:23<4:39:11,  1.65it/s]
 52%|█████▏    | 30017/57600 [5:15:23<4:46:06,  1.61it/s]
 52%|█████▏    | 30018/57600 [5:15:24<4:39:34,  1.64it/s]
 52%|█████▏    | 30019/57600 [5:15:25<4:44:10,  1.62it/s]
 52%|█████▏    | 30020/57600 [5:15:25<4:44:06,  1.62it/s]
                                                         
{'loss': 1.1799, 'learning_rate': 5.324390243902438e-07, 'epoch': 331.35}

 52%|█████▏    | 30020/57600 [5:15:25<4:44:06,  1.62it/s]
 52%|█████▏    | 30021/57600 [5:15:26<4:45:54,  1.61it/s]
 52%|█████▏    | 30022/57600 [5:15:26<4:49:44,  1.59it/s]
 52%|█████▏    | 30023/57600 [5:15:27<4:46:52,  1.60it/s]
 52%|█████▏    | 30024/57600 [5:15:28<4:48:48,  1.59it/s]
 52%|█████▏    | 30025/57600 [5:15:28<4:44:12,  1.62it/s]
 52%|█████▏    | 30026/57600 [5:15:29<4:45:15,  1.61it/s]
 52%|█████▏    | 30027/57600 [5:15:30<4:53:41,  1.56it/s]
 52%|█████▏    | 30028/57600 [5:15:30<4:55:16,  1.56it/s]
 52%|█████▏    | 30029/57600 [5:15:31<4:49:00,  1.59it/s]
 52%|█████▏    | 30030/57600 [5:15:32<4:52:04,  1.57it/s]
 52%|█████▏    | 30031/57600 [5:15:32<4:57:16,  1.55it/s]
 52%|█████▏    | 30032/57600 [5:15:33<4:58:02,  1.54it/s]
 52%|█████▏    | 30033/57600 [5:15:33<4:47:10,  1.60it/s]
 52%|█████▏    | 30034/57600 [5:15:34<4:51:04,  1.58it/s]
 52%|█████▏    | 30035/57600 [5:15:35<4:54:39,  1.56it/s]
 52%|█████▏    | 30036/57600 [5:15:35<4:53:48,  1.56it/s]
 52%|█████▏    | 30037/57600 [5:15:36<4:59:02,  1.54it/s]
 52%|█████▏    | 30038/57600 [5:15:37<4:58:26,  1.54it/s]
 52%|█████▏    | 30039/57600 [5:15:37<4:49:56,  1.58it/s]
 52%|█████▏    | 30040/57600 [5:15:38<4:45:54,  1.61it/s]
                                                         
{'loss': 1.1713, 'learning_rate': 5.321254355400697e-07, 'epoch': 331.57}

 52%|█████▏    | 30040/57600 [5:15:38<4:45:54,  1.61it/s]
 52%|█████▏    | 30041/57600 [5:15:39<4:47:05,  1.60it/s]
 52%|█████▏    | 30042/57600 [5:15:39<4:45:45,  1.61it/s]
 52%|█████▏    | 30043/57600 [5:15:40<4:49:16,  1.59it/s]
 52%|█████▏    | 30044/57600 [5:15:40<4:39:25,  1.64it/s]
 52%|█████▏    | 30045/57600 [5:15:41<4:41:06,  1.63it/s]
 52%|█████▏    | 30046/57600 [5:15:42<4:52:03,  1.57it/s]
 52%|█████▏    | 30047/57600 [5:15:42<4:42:00,  1.63it/s]
 52%|█████▏    | 30048/57600 [5:15:43<4:35:24,  1.67it/s]
 52%|█████▏    | 30049/57600 [5:15:43<4:38:50,  1.65it/s]
 52%|█████▏    | 30050/57600 [5:15:44<4:46:09,  1.60it/s]
 52%|█████▏    | 30051/57600 [5:15:45<4:52:28,  1.57it/s]
 52%|█████▏    | 30052/57600 [5:15:45<4:59:50,  1.53it/s]
 52%|█████▏    | 30053/57600 [5:15:46<5:02:30,  1.52it/s]
 52%|█████▏    | 30054/57600 [5:15:47<4:54:26,  1.56it/s]
 52%|█████▏    | 30055/57600 [5:15:47<4:49:00,  1.59it/s]
 52%|█████▏    | 30056/57600 [5:15:48<4:45:57,  1.61it/s]
 52%|█████▏    | 30057/57600 [5:15:49<4:52:42,  1.57it/s]
 52%|█████▏    | 30058/57600 [5:15:49<4:56:46,  1.55it/s]
 52%|█████▏    | 30059/57600 [5:15:50<4:48:12,  1.59it/s]
 52%|█████▏    | 30060/57600 [5:15:50<4:48:17,  1.59it/s]
                                                         
{'loss': 1.1347, 'learning_rate': 5.318118466898954e-07, 'epoch': 331.79}

 52%|█████▏    | 30060/57600 [5:15:50<4:48:17,  1.59it/s]
 52%|█████▏    | 30061/57600 [5:15:51<4:50:32,  1.58it/s]
 52%|█████▏    | 30062/57600 [5:15:52<5:08:57,  1.49it/s]
 52%|█████▏    | 30063/57600 [5:15:53<5:04:37,  1.51it/s]
 52%|█████▏    | 30064/57600 [5:15:53<5:01:46,  1.52it/s]
 52%|█████▏    | 30065/57600 [5:15:54<4:53:25,  1.56it/s]
 52%|█████▏    | 30066/57600 [5:15:54<4:44:45,  1.61it/s]
 52%|█████▏    | 30067/57600 [5:15:55<4:46:59,  1.60it/s]
 52%|█████▏    | 30068/57600 [5:15:56<4:45:57,  1.60it/s]
 52%|█████▏    | 30069/57600 [5:15:56<4:50:31,  1.58it/s]
 52%|█████▏    | 30070/57600 [5:15:57<4:50:30,  1.58it/s]
 52%|█████▏    | 30071/57600 [5:15:57<4:43:48,  1.62it/s]
 52%|█████▏    | 30072/57600 [5:15:58<4:45:45,  1.61it/s]
 52%|█████▏    | 30073/57600 [5:15:59<4:40:13,  1.64it/s]
 52%|█████▏    | 30074/57600 [5:15:59<4:47:13,  1.60it/s]
 52%|█████▏    | 30075/57600 [5:16:00<4:47:37,  1.59it/s]
 52%|█████▏    | 30076/57600 [5:16:01<4:50:53,  1.58it/s]
 52%|█████▏    | 30077/57600 [5:16:01<4:42:10,  1.63it/s]
 52%|█████▏    | 30078/57600 [5:16:02<4:44:15,  1.61it/s]
 52%|█████▏    | 30079/57600 [5:16:02<4:45:22,  1.61it/s]
 52%|█████▏    | 30080/57600 [5:16:03<4:51:53,  1.57it/s]
                                                         
{'loss': 1.1641, 'learning_rate': 5.314982578397212e-07, 'epoch': 332.01}

 52%|█████▏    | 30080/57600 [5:16:03<4:51:53,  1.57it/s]
 52%|█████▏    | 30081/57600 [5:16:04<4:46:40,  1.60it/s]
 52%|█████▏    | 30082/57600 [5:16:04<4:44:30,  1.61it/s]
 52%|█████▏    | 30083/57600 [5:16:05<4:47:27,  1.60it/s]
 52%|█████▏    | 30084/57600 [5:16:06<4:45:30,  1.61it/s]
 52%|█████▏    | 30085/57600 [5:16:06<4:46:55,  1.60it/s]
 52%|█████▏    | 30086/57600 [5:16:07<4:50:23,  1.58it/s]
 52%|█████▏    | 30087/57600 [5:16:07<4:50:01,  1.58it/s]
 52%|█████▏    | 30088/57600 [5:16:08<4:53:59,  1.56it/s]
 52%|█████▏    | 30089/57600 [5:16:09<4:54:35,  1.56it/s]
 52%|█████▏    | 30090/57600 [5:16:09<4:50:24,  1.58it/s]
 52%|█████▏    | 30091/57600 [5:16:10<4:48:28,  1.59it/s]
 52%|█████▏    | 30092/57600 [5:16:11<4:57:53,  1.54it/s]
 52%|█████▏    | 30093/57600 [5:16:11<4:52:51,  1.57it/s]
 52%|█████▏    | 30094/57600 [5:16:12<4:46:13,  1.60it/s]
 52%|█████▏    | 30095/57600 [5:16:13<4:56:59,  1.54it/s]
 52%|█████▏    | 30096/57600 [5:16:13<4:52:03,  1.57it/s]
 52%|█████▏    | 30097/57600 [5:16:14<4:59:04,  1.53it/s]
 52%|█████▏    | 30098/57600 [5:16:15<4:58:48,  1.53it/s]
 52%|█████▏    | 30099/57600 [5:16:15<4:57:45,  1.54it/s]
 52%|█████▏    | 30100/57600 [5:16:16<4:50:54,  1.58it/s]
                                                         
{'loss': 1.2001, 'learning_rate': 5.311846689895469e-07, 'epoch': 332.23}

 52%|█████▏    | 30100/57600 [5:16:16<4:50:54,  1.58it/s]
 52%|█████▏    | 30101/57600 [5:16:16<4:53:33,  1.56it/s]
 52%|█████▏    | 30102/57600 [5:16:17<4:55:42,  1.55it/s]
 52%|█████▏    | 30103/57600 [5:16:18<4:52:54,  1.56it/s]
 52%|█████▏    | 30104/57600 [5:16:18<4:45:15,  1.61it/s]
 52%|█████▏    | 30105/57600 [5:16:19<4:38:54,  1.64it/s]
 52%|█████▏    | 30106/57600 [5:16:20<4:37:05,  1.65it/s]
 52%|█████▏    | 30107/57600 [5:16:20<4:43:31,  1.62it/s]
 52%|█████▏    | 30108/57600 [5:16:21<4:41:37,  1.63it/s]
 52%|█████▏    | 30109/57600 [5:16:21<4:36:57,  1.65it/s]
 52%|█████▏    | 30110/57600 [5:16:22<4:36:41,  1.66it/s]
 52%|█████▏    | 30111/57600 [5:16:23<4:37:29,  1.65it/s]
 52%|█████▏    | 30112/57600 [5:16:23<4:38:22,  1.65it/s]
 52%|█████▏    | 30113/57600 [5:16:24<4:49:01,  1.59it/s]
 52%|█████▏    | 30114/57600 [5:16:25<4:55:23,  1.55it/s]
 52%|█████▏    | 30115/57600 [5:16:25<5:02:49,  1.51it/s]
 52%|█████▏    | 30116/57600 [5:16:26<4:54:13,  1.56it/s]
 52%|█████▏    | 30117/57600 [5:16:26<4:47:36,  1.59it/s]
 52%|█████▏    | 30118/57600 [5:16:27<4:44:43,  1.61it/s]
 52%|█████▏    | 30119/57600 [5:16:28<4:59:03,  1.53it/s]
 52%|█████▏    | 30120/57600 [5:16:29<5:14:43,  1.46it/s]
                                                         
{'loss': 1.1617, 'learning_rate': 5.308710801393728e-07, 'epoch': 332.45}

 52%|█████▏    | 30120/57600 [5:16:29<5:14:43,  1.46it/s]
 52%|█████▏    | 30121/57600 [5:16:29<5:13:16,  1.46it/s]
 52%|█████▏    | 30122/57600 [5:16:30<4:59:16,  1.53it/s]
 52%|█████▏    | 30123/57600 [5:16:30<4:56:12,  1.55it/s]
 52%|█████▏    | 30124/57600 [5:16:31<4:49:02,  1.58it/s]
 52%|█████▏    | 30125/57600 [5:16:32<4:42:26,  1.62it/s]
 52%|█████▏    | 30126/57600 [5:16:32<4:42:21,  1.62it/s]
 52%|█████▏    | 30127/57600 [5:16:33<4:41:30,  1.63it/s]
 52%|█████▏    | 30128/57600 [5:16:34<4:51:26,  1.57it/s]
 52%|█████▏    | 30129/57600 [5:16:34<4:50:07,  1.58it/s]
 52%|█████▏    | 30130/57600 [5:16:35<4:53:23,  1.56it/s]
 52%|█████▏    | 30131/57600 [5:16:36<5:04:20,  1.50it/s]
 52%|█████▏    | 30132/57600 [5:16:36<5:02:24,  1.51it/s]
 52%|█████▏    | 30133/57600 [5:16:37<4:51:08,  1.57it/s]
 52%|█████▏    | 30134/57600 [5:16:37<4:52:28,  1.57it/s]
 52%|█████▏    | 30135/57600 [5:16:38<4:56:07,  1.55it/s]
 52%|█████▏    | 30136/57600 [5:16:39<4:55:49,  1.55it/s]
 52%|█████▏    | 30137/57600 [5:16:39<4:49:27,  1.58it/s]
 52%|█████▏    | 30138/57600 [5:16:40<4:55:09,  1.55it/s]
 52%|█████▏    | 30139/57600 [5:16:41<4:52:08,  1.57it/s]
 52%|█████▏    | 30140/57600 [5:16:41<4:53:39,  1.56it/s]
                                                         
{'loss': 1.1591, 'learning_rate': 5.305574912891986e-07, 'epoch': 332.67}

 52%|█████▏    | 30140/57600 [5:16:41<4:53:39,  1.56it/s]
 52%|█████▏    | 30141/57600 [5:16:42<4:46:14,  1.60it/s]
 52%|█████▏    | 30142/57600 [5:16:42<4:43:23,  1.61it/s]
 52%|█████▏    | 30143/57600 [5:16:43<4:56:13,  1.54it/s]
 52%|█████▏    | 30144/57600 [5:16:44<4:54:01,  1.56it/s]
 52%|█████▏    | 30145/57600 [5:16:44<4:56:25,  1.54it/s]
 52%|█████▏    | 30146/57600 [5:16:45<4:48:14,  1.59it/s]
 52%|█████▏    | 30147/57600 [5:16:46<4:56:42,  1.54it/s]
 52%|█████▏    | 30148/57600 [5:16:46<4:47:40,  1.59it/s]
 52%|█████▏    | 30149/57600 [5:16:47<4:42:04,  1.62it/s]
 52%|█████▏    | 30150/57600 [5:16:48<4:46:56,  1.59it/s]
 52%|█████▏    | 30151/57600 [5:16:48<4:50:12,  1.58it/s]
 52%|█████▏    | 30152/57600 [5:16:49<4:57:32,  1.54it/s]
 52%|█████▏    | 30153/57600 [5:16:50<4:55:00,  1.55it/s]
 52%|█████▏    | 30154/57600 [5:16:50<4:44:48,  1.61it/s]
 52%|█████▏    | 30155/57600 [5:16:51<4:41:15,  1.63it/s]
 52%|█████▏    | 30156/57600 [5:16:51<4:36:06,  1.66it/s]
 52%|█████▏    | 30157/57600 [5:16:52<4:43:44,  1.61it/s]
 52%|█████▏    | 30158/57600 [5:16:53<4:37:36,  1.65it/s]
 52%|█████▏    | 30159/57600 [5:16:53<4:36:08,  1.66it/s]
 52%|█████▏    | 30160/57600 [5:16:54<4:54:06,  1.55it/s]
                                                         
{'loss': 1.1553, 'learning_rate': 5.302439024390244e-07, 'epoch': 332.89}

 52%|█████▏    | 30160/57600 [5:16:54<4:54:06,  1.55it/s]
 52%|█████▏    | 30161/57600 [5:16:54<4:43:47,  1.61it/s]
 52%|█████▏    | 30162/57600 [5:16:55<4:42:29,  1.62it/s]
 52%|█████▏    | 30163/57600 [5:16:56<4:43:08,  1.61it/s]
 52%|█████▏    | 30164/57600 [5:16:56<4:42:21,  1.62it/s]
 52%|█████▏    | 30165/57600 [5:16:57<4:49:18,  1.58it/s]
 52%|█████▏    | 30166/57600 [5:16:58<4:47:54,  1.59it/s]
 52%|█████▏    | 30167/57600 [5:16:58<4:48:45,  1.58it/s]
 52%|█████▏    | 30168/57600 [5:16:59<4:56:29,  1.54it/s]
 52%|█████▏    | 30169/57600 [5:17:00<5:01:26,  1.52it/s]
 52%|█████▏    | 30170/57600 [5:17:00<5:08:40,  1.48it/s]
 52%|█████▏    | 30171/57600 [5:17:01<5:15:56,  1.45it/s]
 52%|█████▏    | 30172/57600 [5:17:02<5:06:56,  1.49it/s]
 52%|█████▏    | 30173/57600 [5:17:02<5:08:27,  1.48it/s]
 52%|█████▏    | 30174/57600 [5:17:03<5:03:52,  1.50it/s]
 52%|█████▏    | 30175/57600 [5:17:04<4:56:03,  1.54it/s]
 52%|█████▏    | 30176/57600 [5:17:04<4:53:52,  1.56it/s]
 52%|█████▏    | 30177/57600 [5:17:05<4:47:01,  1.59it/s]
 52%|█████▏    | 30178/57600 [5:17:05<4:36:52,  1.65it/s]
 52%|█████▏    | 30179/57600 [5:17:06<4:37:22,  1.65it/s]
 52%|█████▏    | 30180/57600 [5:17:07<4:35:46,  1.66it/s]
                                                         
{'loss': 1.1895, 'learning_rate': 5.299303135888502e-07, 'epoch': 333.11}

 52%|█████▏    | 30180/57600 [5:17:07<4:35:46,  1.66it/s]
 52%|█████▏    | 30181/57600 [5:17:07<4:36:52,  1.65it/s]
 52%|█████▏    | 30182/57600 [5:17:08<4:43:42,  1.61it/s]
 52%|█████▏    | 30183/57600 [5:17:08<4:44:33,  1.61it/s]
 52%|█████▏    | 30184/57600 [5:17:09<4:43:00,  1.61it/s]
 52%|█████▏    | 30185/57600 [5:17:10<4:45:20,  1.60it/s]
 52%|█████▏    | 30186/57600 [5:17:10<4:50:21,  1.57it/s]
 52%|█████▏    | 30187/57600 [5:17:11<4:54:38,  1.55it/s]
 52%|█████▏    | 30188/57600 [5:17:12<4:53:02,  1.56it/s]
 52%|█████▏    | 30189/57600 [5:17:12<4:54:28,  1.55it/s]
 52%|█████▏    | 30190/57600 [5:17:13<4:51:09,  1.57it/s]
 52%|█████▏    | 30191/57600 [5:17:14<4:46:32,  1.59it/s]
 52%|█████▏    | 30192/57600 [5:17:14<4:45:33,  1.60it/s]
 52%|█████▏    | 30193/57600 [5:17:15<4:51:21,  1.57it/s]
 52%|█████▏    | 30194/57600 [5:17:15<4:52:11,  1.56it/s]
 52%|█████▏    | 30195/57600 [5:17:16<4:47:49,  1.59it/s]
 52%|█████▏    | 30196/57600 [5:17:17<4:49:54,  1.58it/s]
 52%|█████▏    | 30197/57600 [5:17:17<4:56:42,  1.54it/s]
 52%|█████▏    | 30198/57600 [5:17:18<4:48:31,  1.58it/s]
 52%|█████▏    | 30199/57600 [5:17:19<4:46:51,  1.59it/s]
 52%|█████▏    | 30200/57600 [5:17:19<4:39:12,  1.64it/s]
                                                         
{'loss': 1.1721, 'learning_rate': 5.296167247386759e-07, 'epoch': 333.33}

 52%|█████▏    | 30200/57600 [5:17:19<4:39:12,  1.64it/s]
 52%|█████▏    | 30201/57600 [5:17:20<4:45:01,  1.60it/s]
 52%|█████▏    | 30202/57600 [5:17:20<4:43:44,  1.61it/s]
 52%|█████▏    | 30203/57600 [5:17:21<4:39:48,  1.63it/s]
 52%|█████▏    | 30204/57600 [5:17:22<4:32:23,  1.68it/s]
 52%|█████▏    | 30205/57600 [5:17:22<4:34:26,  1.66it/s]
 52%|█████▏    | 30206/57600 [5:17:23<4:33:13,  1.67it/s]
 52%|█████▏    | 30207/57600 [5:17:23<4:32:18,  1.68it/s]
 52%|█████▏    | 30208/57600 [5:17:24<4:39:29,  1.63it/s]
 52%|█████▏    | 30209/57600 [5:17:25<4:46:18,  1.59it/s]
 52%|█████▏    | 30210/57600 [5:17:25<4:48:00,  1.58it/s]
 52%|█████▏    | 30211/57600 [5:17:26<4:52:16,  1.56it/s]
 52%|█████▏    | 30212/57600 [5:17:27<4:57:27,  1.53it/s]
 52%|█████▏    | 30213/57600 [5:17:27<5:05:58,  1.49it/s]
 52%|█████▏    | 30214/57600 [5:17:28<4:59:36,  1.52it/s]
 52%|█████▏    | 30215/57600 [5:17:29<4:50:33,  1.57it/s]
 52%|█████▏    | 30216/57600 [5:17:29<4:44:12,  1.61it/s]
 52%|█████▏    | 30217/57600 [5:17:30<4:40:56,  1.62it/s]
 52%|█████▏    | 30218/57600 [5:17:30<4:41:24,  1.62it/s]
 52%|█████▏    | 30219/57600 [5:17:31<4:44:26,  1.60it/s]
 52%|█████▏    | 30220/57600 [5:17:32<4:50:28,  1.57it/s]
                                                         
{'loss': 1.1746, 'learning_rate': 5.293031358885018e-07, 'epoch': 333.55}

 52%|█████▏    | 30220/57600 [5:17:32<4:50:28,  1.57it/s]
 52%|█████▏    | 30221/57600 [5:17:32<4:47:53,  1.59it/s]
 52%|█████▏    | 30222/57600 [5:17:33<4:48:26,  1.58it/s]
 52%|█████▏    | 30223/57600 [5:17:34<4:45:48,  1.60it/s]
 52%|█████▏    | 30224/57600 [5:17:34<4:44:10,  1.61it/s]
 52%|█████▏    | 30225/57600 [5:17:35<4:43:33,  1.61it/s]
 52%|█████▏    | 30226/57600 [5:17:36<4:52:33,  1.56it/s]
 52%|█████▏    | 30227/57600 [5:17:36<4:54:31,  1.55it/s]
 52%|█████▏    | 30228/57600 [5:17:37<4:50:42,  1.57it/s]
 52%|█████▏    | 30229/57600 [5:17:37<4:58:49,  1.53it/s]
 52%|█████▏    | 30230/57600 [5:17:38<4:55:16,  1.54it/s]
 52%|█████▏    | 30231/57600 [5:17:39<4:48:20,  1.58it/s]
 52%|█████▏    | 30232/57600 [5:17:39<4:50:07,  1.57it/s]
 52%|█████▏    | 30233/57600 [5:17:40<4:39:00,  1.63it/s]
 52%|█████▏    | 30234/57600 [5:17:41<4:40:10,  1.63it/s]
 52%|█████▏    | 30235/57600 [5:17:41<4:37:23,  1.64it/s]
 52%|█████▏    | 30236/57600 [5:17:42<4:42:05,  1.62it/s]
 52%|█████▏    | 30237/57600 [5:17:42<4:50:44,  1.57it/s]
 52%|█████▏    | 30238/57600 [5:17:43<4:44:11,  1.60it/s]
 52%|█████▏    | 30239/57600 [5:17:44<4:50:22,  1.57it/s]
 52%|█████▎    | 30240/57600 [5:17:44<4:43:46,  1.61it/s]
                                                         
{'loss': 1.1505, 'learning_rate': 5.289895470383274e-07, 'epoch': 333.77}

 52%|█████▎    | 30240/57600 [5:17:44<4:43:46,  1.61it/s]
 53%|█████▎    | 30241/57600 [5:17:45<4:46:03,  1.59it/s]
 53%|█████▎    | 30242/57600 [5:17:46<4:41:38,  1.62it/s]
 53%|█████▎    | 30243/57600 [5:17:46<4:42:15,  1.62it/s]
 53%|█████▎    | 30244/57600 [5:17:47<4:44:43,  1.60it/s]
 53%|█████▎    | 30245/57600 [5:17:47<4:53:37,  1.55it/s]
 53%|█████▎    | 30246/57600 [5:17:48<4:50:17,  1.57it/s]
 53%|█████▎    | 30247/57600 [5:17:49<4:50:40,  1.57it/s]
 53%|█████▎    | 30248/57600 [5:17:49<4:43:22,  1.61it/s]
 53%|█████▎    | 30249/57600 [5:17:50<4:43:47,  1.61it/s]
 53%|█████▎    | 30250/57600 [5:17:51<4:47:45,  1.58it/s]
 53%|█████▎    | 30251/57600 [5:17:51<4:56:54,  1.54it/s]
 53%|█████▎    | 30252/57600 [5:17:52<4:51:23,  1.56it/s]
 53%|█████▎    | 30253/57600 [5:17:53<4:48:26,  1.58it/s]
 53%|█████▎    | 30254/57600 [5:17:53<4:48:08,  1.58it/s]
 53%|█████▎    | 30255/57600 [5:17:54<4:42:44,  1.61it/s]
 53%|█████▎    | 30256/57600 [5:17:54<4:55:50,  1.54it/s]
 53%|█████▎    | 30257/57600 [5:17:55<4:49:42,  1.57it/s]
 53%|█████▎    | 30258/57600 [5:17:56<4:39:42,  1.63it/s]
 53%|█████▎    | 30259/57600 [5:17:56<4:44:21,  1.60it/s]
 53%|█████▎    | 30260/57600 [5:17:57<4:51:34,  1.56it/s]
                                                         
{'loss': 1.1609, 'learning_rate': 5.286759581881533e-07, 'epoch': 334.0}

 53%|█████▎    | 30260/57600 [5:17:57<4:51:34,  1.56it/s]
 53%|█████▎    | 30261/57600 [5:17:58<5:03:55,  1.50it/s]
 53%|█████▎    | 30262/57600 [5:17:58<5:16:33,  1.44it/s]
 53%|█████▎    | 30263/57600 [5:17:59<5:14:11,  1.45it/s]
 53%|█████▎    | 30264/57600 [5:18:00<5:17:52,  1.43it/s]
 53%|█████▎    | 30265/57600 [5:18:00<5:01:32,  1.51it/s]
 53%|█████▎    | 30266/57600 [5:18:01<4:51:38,  1.56it/s]
 53%|█████▎    | 30267/57600 [5:18:02<4:57:11,  1.53it/s]
 53%|█████▎    | 30268/57600 [5:18:02<4:57:20,  1.53it/s]
 53%|█████▎    | 30269/57600 [5:18:03<4:57:22,  1.53it/s]
 53%|█████▎    | 30270/57600 [5:18:04<5:02:30,  1.51it/s]
 53%|█████▎    | 30271/57600 [5:18:04<4:55:11,  1.54it/s]
 53%|█████▎    | 30272/57600 [5:18:05<4:45:49,  1.59it/s]
 53%|█████▎    | 30273/57600 [5:18:06<4:47:58,  1.58it/s]
 53%|█████▎    | 30274/57600 [5:18:06<4:54:55,  1.54it/s]
 53%|█████▎    | 30275/57600 [5:18:07<4:54:22,  1.55it/s]
 53%|█████▎    | 30276/57600 [5:18:07<4:54:42,  1.55it/s]
 53%|█████▎    | 30277/57600 [5:18:08<4:51:23,  1.56it/s]
 53%|█████▎    | 30278/57600 [5:18:09<4:45:55,  1.59it/s]
 53%|█████▎    | 30279/57600 [5:18:09<4:45:23,  1.60it/s]
 53%|█████▎    | 30280/57600 [5:18:10<4:46:09,  1.59it/s]
                                                         
{'loss': 1.1453, 'learning_rate': 5.283623693379791e-07, 'epoch': 334.22}

 53%|█████▎    | 30280/57600 [5:18:10<4:46:09,  1.59it/s]
 53%|█████▎    | 30281/57600 [5:18:11<4:49:42,  1.57it/s]
 53%|█████▎    | 30282/57600 [5:18:11<4:46:26,  1.59it/s]
 53%|█████▎    | 30283/57600 [5:18:12<4:52:42,  1.56it/s]
 53%|█████▎    | 30284/57600 [5:18:13<4:50:41,  1.57it/s]
 53%|█████▎    | 30285/57600 [5:18:13<4:47:45,  1.58it/s]
 53%|█████▎    | 30286/57600 [5:18:14<4:48:08,  1.58it/s]
 53%|█████▎    | 30287/57600 [5:18:14<4:42:55,  1.61it/s]
 53%|█████▎    | 30288/57600 [5:18:15<4:46:31,  1.59it/s]
 53%|█████▎    | 30289/57600 [5:18:16<4:55:21,  1.54it/s]
 53%|█████▎    | 30290/57600 [5:18:16<5:00:08,  1.52it/s]
 53%|█████▎    | 30291/57600 [5:18:17<4:47:26,  1.58it/s]
 53%|█████▎    | 30292/57600 [5:18:18<4:40:04,  1.63it/s]
 53%|█████▎    | 30293/57600 [5:18:18<4:39:29,  1.63it/s]
 53%|█████▎    | 30294/57600 [5:18:19<4:35:31,  1.65it/s]
 53%|█████▎    | 30295/57600 [5:18:19<4:40:15,  1.62it/s]
 53%|█████▎    | 30296/57600 [5:18:20<4:46:11,  1.59it/s]
 53%|█████▎    | 30297/57600 [5:18:21<4:41:37,  1.62it/s]
 53%|█████▎    | 30298/57600 [5:18:21<4:46:19,  1.59it/s]
 53%|█████▎    | 30299/57600 [5:18:22<4:46:46,  1.59it/s]
 53%|█████▎    | 30300/57600 [5:18:23<4:38:25,  1.63it/s]
                                                         
{'loss': 1.1834, 'learning_rate': 5.280487804878048e-07, 'epoch': 334.44}

 53%|█████▎    | 30300/57600 [5:18:23<4:38:25,  1.63it/s]
 53%|█████▎    | 30301/57600 [5:18:23<4:38:06,  1.64it/s]
 53%|█████▎    | 30302/57600 [5:18:24<4:36:52,  1.64it/s]
 53%|█████▎    | 30303/57600 [5:18:24<4:39:30,  1.63it/s]
 53%|█████▎    | 30304/57600 [5:18:25<4:39:30,  1.63it/s]
 53%|█████▎    | 30305/57600 [5:18:26<4:39:48,  1.63it/s]
 53%|█████▎    | 30306/57600 [5:18:26<4:40:41,  1.62it/s]
 53%|█████▎    | 30307/57600 [5:18:27<4:43:44,  1.60it/s]
 53%|█████▎    | 30308/57600 [5:18:27<4:44:00,  1.60it/s]
 53%|█████▎    | 30309/57600 [5:18:28<4:33:26,  1.66it/s]
 53%|█████▎    | 30310/57600 [5:18:29<4:40:00,  1.62it/s]
 53%|█████▎    | 30311/57600 [5:18:29<4:33:29,  1.66it/s]
 53%|█████▎    | 30312/57600 [5:18:30<4:28:29,  1.69it/s]
 53%|█████▎    | 30313/57600 [5:18:30<4:30:44,  1.68it/s]
 53%|█████▎    | 30314/57600 [5:18:31<4:44:26,  1.60it/s]
 53%|█████▎    | 30315/57600 [5:18:32<4:45:29,  1.59it/s]
 53%|█████▎    | 30316/57600 [5:18:32<4:49:47,  1.57it/s]
 53%|█████▎    | 30317/57600 [5:18:33<4:44:52,  1.60it/s]
 53%|█████▎    | 30318/57600 [5:18:34<4:50:38,  1.56it/s]
 53%|█████▎    | 30319/57600 [5:18:34<4:48:07,  1.58it/s]
 53%|█████▎    | 30320/57600 [5:18:35<4:45:28,  1.59it/s]
                                                         
{'loss': 1.2259, 'learning_rate': 5.277351916376305e-07, 'epoch': 334.66}

 53%|█████▎    | 30320/57600 [5:18:35<4:45:28,  1.59it/s]
 53%|█████▎    | 30321/57600 [5:18:36<4:46:18,  1.59it/s]
 53%|█████▎    | 30322/57600 [5:18:36<4:53:41,  1.55it/s]
 53%|█████▎    | 30323/57600 [5:18:37<4:57:22,  1.53it/s]
 53%|█████▎    | 30324/57600 [5:18:37<4:48:48,  1.57it/s]
 53%|█████▎    | 30325/57600 [5:18:38<4:48:55,  1.57it/s]
 53%|█████▎    | 30326/57600 [5:18:39<4:44:28,  1.60it/s]
 53%|█████▎    | 30327/57600 [5:18:39<4:49:32,  1.57it/s]
 53%|█████▎    | 30328/57600 [5:18:40<4:47:01,  1.58it/s]
 53%|█████▎    | 30329/57600 [5:18:41<4:47:11,  1.58it/s]
 53%|█████▎    | 30330/57600 [5:18:41<4:40:33,  1.62it/s]
 53%|█████▎    | 30331/57600 [5:18:42<4:40:41,  1.62it/s]
 53%|█████▎    | 30332/57600 [5:18:42<4:33:20,  1.66it/s]
 53%|█████▎    | 30333/57600 [5:18:43<4:35:24,  1.65it/s]
 53%|█████▎    | 30334/57600 [5:18:44<4:38:28,  1.63it/s]
 53%|█████▎    | 30335/57600 [5:18:44<4:49:34,  1.57it/s]
 53%|█████▎    | 30336/57600 [5:18:45<4:43:18,  1.60it/s]
 53%|█████▎    | 30337/57600 [5:18:46<4:47:41,  1.58it/s]
 53%|█████▎    | 30338/57600 [5:18:46<4:41:53,  1.61it/s]
 53%|█████▎    | 30339/57600 [5:18:47<4:40:21,  1.62it/s]
 53%|█████▎    | 30340/57600 [5:18:47<4:42:24,  1.61it/s]
                                                         
{'loss': 1.1974, 'learning_rate': 5.274216027874564e-07, 'epoch': 334.88}

 53%|█████▎    | 30340/57600 [5:18:47<4:42:24,  1.61it/s]
 53%|█████▎    | 30341/57600 [5:18:48<4:29:49,  1.68it/s]
 53%|█████▎    | 30342/57600 [5:18:49<4:28:50,  1.69it/s]
 53%|█████▎    | 30343/57600 [5:18:49<4:31:54,  1.67it/s]
 53%|█████▎    | 30344/57600 [5:18:50<4:35:01,  1.65it/s]
 53%|█████▎    | 30345/57600 [5:18:50<4:41:43,  1.61it/s]
 53%|█████▎    | 30346/57600 [5:18:51<4:48:26,  1.57it/s]
 53%|█████▎    | 30347/57600 [5:18:52<4:48:22,  1.58it/s]
 53%|█████▎    | 30348/57600 [5:18:52<4:42:15,  1.61it/s]
 53%|█████▎    | 30349/57600 [5:18:53<4:48:27,  1.57it/s]
 53%|█████▎    | 30350/57600 [5:18:54<4:57:37,  1.53it/s]
 53%|█████▎    | 30351/57600 [5:18:54<4:54:42,  1.54it/s]
 53%|█████▎    | 30352/57600 [5:18:55<5:04:11,  1.49it/s]
 53%|█████▎    | 30353/57600 [5:18:56<4:54:19,  1.54it/s]
 53%|█████▎    | 30354/57600 [5:18:56<4:56:32,  1.53it/s]
 53%|█████▎    | 30355/57600 [5:18:57<4:57:01,  1.53it/s]
 53%|█████▎    | 30356/57600 [5:18:58<4:51:23,  1.56it/s]
 53%|█████▎    | 30357/57600 [5:18:58<4:54:14,  1.54it/s]
 53%|█████▎    | 30358/57600 [5:18:59<5:00:12,  1.51it/s]
 53%|█████▎    | 30359/57600 [5:19:00<5:02:26,  1.50it/s]
 53%|█████▎    | 30360/57600 [5:19:00<4:47:48,  1.58it/s]
                                                         
{'loss': 1.1794, 'learning_rate': 5.271080139372821e-07, 'epoch': 335.1}

 53%|█████▎    | 30360/57600 [5:19:00<4:47:48,  1.58it/s]
 53%|█████▎    | 30361/57600 [5:19:01<4:41:07,  1.61it/s]
 53%|█████▎    | 30362/57600 [5:19:01<4:44:26,  1.60it/s]
 53%|█████▎    | 30363/57600 [5:19:02<4:56:45,  1.53it/s]
 53%|█████▎    | 30364/57600 [5:19:03<4:47:59,  1.58it/s]
 53%|█████▎    | 30365/57600 [5:19:03<4:46:39,  1.58it/s]
 53%|█████▎    | 30366/57600 [5:19:04<4:48:41,  1.57it/s]
 53%|█████▎    | 30367/57600 [5:19:05<4:59:37,  1.51it/s]
 53%|█████▎    | 30368/57600 [5:19:05<4:58:28,  1.52it/s]
 53%|█████▎    | 30369/57600 [5:19:06<4:54:37,  1.54it/s]
 53%|█████▎    | 30370/57600 [5:19:07<4:49:08,  1.57it/s]
 53%|█████▎    | 30371/57600 [5:19:07<4:49:24,  1.57it/s]
 53%|█████▎    | 30372/57600 [5:19:08<4:51:48,  1.56it/s]
 53%|█████▎    | 30373/57600 [5:19:09<5:02:34,  1.50it/s]
 53%|█████▎    | 30374/57600 [5:19:09<4:48:14,  1.57it/s]
 53%|█████▎    | 30375/57600 [5:19:10<4:46:57,  1.58it/s]
 53%|█████▎    | 30376/57600 [5:19:10<4:50:36,  1.56it/s]
 53%|█████▎    | 30377/57600 [5:19:11<4:55:56,  1.53it/s]
 53%|█████▎    | 30378/57600 [5:19:12<4:57:50,  1.52it/s]
 53%|█████▎    | 30379/57600 [5:19:12<4:49:11,  1.57it/s]
 53%|█████▎    | 30380/57600 [5:19:13<4:51:00,  1.56it/s]
                                                         
{'loss': 1.1433, 'learning_rate': 5.26794425087108e-07, 'epoch': 335.32}

 53%|█████▎    | 30380/57600 [5:19:13<4:51:00,  1.56it/s]
 53%|█████▎    | 30381/57600 [5:19:14<4:52:19,  1.55it/s]
 53%|█████▎    | 30382/57600 [5:19:14<4:52:57,  1.55it/s]
 53%|█████▎    | 30383/57600 [5:19:15<4:44:52,  1.59it/s]
 53%|█████▎    | 30384/57600 [5:19:16<4:44:46,  1.59it/s]
 53%|█████▎    | 30385/57600 [5:19:16<4:42:04,  1.61it/s]
 53%|█████▎    | 30386/57600 [5:19:17<4:37:51,  1.63it/s]
 53%|█████▎    | 30387/57600 [5:19:17<4:40:31,  1.62it/s]
 53%|█████▎    | 30388/57600 [5:19:18<4:46:43,  1.58it/s]
 53%|█████▎    | 30389/57600 [5:19:19<4:42:08,  1.61it/s]
 53%|█████▎    | 30390/57600 [5:19:19<4:51:33,  1.56it/s]
 53%|█████▎    | 30391/57600 [5:19:20<4:51:44,  1.55it/s]
 53%|█████▎    | 30392/57600 [5:19:21<4:54:54,  1.54it/s]
 53%|█████▎    | 30393/57600 [5:19:21<5:10:08,  1.46it/s]
 53%|█████▎    | 30394/57600 [5:19:22<5:01:51,  1.50it/s]
 53%|█████▎    | 30395/57600 [5:19:23<4:52:33,  1.55it/s]
 53%|█████▎    | 30396/57600 [5:19:23<4:47:54,  1.57it/s]
 53%|█████▎    | 30397/57600 [5:19:24<4:40:52,  1.61it/s]
 53%|█████▎    | 30398/57600 [5:19:24<4:43:44,  1.60it/s]
 53%|█████▎    | 30399/57600 [5:19:25<4:50:59,  1.56it/s]
 53%|█████▎    | 30400/57600 [5:19:26<4:47:30,  1.58it/s]
                                                         
{'loss': 1.1405, 'learning_rate': 5.264808362369338e-07, 'epoch': 335.54}

 53%|█████▎    | 30400/57600 [5:19:26<4:47:30,  1.58it/s]
 53%|█████▎    | 30401/57600 [5:19:26<4:42:19,  1.61it/s]
 53%|█████▎    | 30402/57600 [5:19:27<4:34:55,  1.65it/s]
 53%|█████▎    | 30403/57600 [5:19:28<4:34:15,  1.65it/s]
 53%|█████▎    | 30404/57600 [5:19:28<4:34:32,  1.65it/s]
 53%|█████▎    | 30405/57600 [5:19:29<4:41:45,  1.61it/s]
 53%|█████▎    | 30406/57600 [5:19:29<4:46:42,  1.58it/s]
 53%|█████▎    | 30407/57600 [5:19:30<4:49:09,  1.57it/s]
 53%|█████▎    | 30408/57600 [5:19:31<4:43:11,  1.60it/s]
 53%|█████▎    | 30409/57600 [5:19:31<4:39:49,  1.62it/s]
 53%|█████▎    | 30410/57600 [5:19:32<4:35:18,  1.65it/s]
 53%|█████▎    | 30411/57600 [5:19:32<4:31:03,  1.67it/s]
 53%|█████▎    | 30412/57600 [5:19:33<4:34:14,  1.65it/s]
 53%|█████▎    | 30413/57600 [5:19:34<4:34:34,  1.65it/s]
 53%|█████▎    | 30414/57600 [5:19:34<4:40:22,  1.62it/s]
 53%|█████▎    | 30415/57600 [5:19:35<4:40:53,  1.61it/s]
 53%|█████▎    | 30416/57600 [5:19:36<4:39:36,  1.62it/s]
 53%|█████▎    | 30417/57600 [5:19:36<4:41:47,  1.61it/s]
 53%|█████▎    | 30418/57600 [5:19:37<4:40:53,  1.61it/s]
 53%|█████▎    | 30419/57600 [5:19:37<4:37:50,  1.63it/s]
 53%|█████▎    | 30420/57600 [5:19:38<4:44:37,  1.59it/s]
                                                         
{'loss': 1.2012, 'learning_rate': 5.261672473867596e-07, 'epoch': 335.76}

 53%|█████▎    | 30420/57600 [5:19:38<4:44:37,  1.59it/s]
 53%|█████▎    | 30421/57600 [5:19:39<4:51:05,  1.56it/s]
 53%|█████▎    | 30422/57600 [5:19:39<4:49:30,  1.56it/s]
 53%|█████▎    | 30423/57600 [5:19:40<4:45:48,  1.58it/s]
 53%|█████▎    | 30424/57600 [5:19:41<4:39:40,  1.62it/s]
 53%|█████▎    | 30425/57600 [5:19:41<4:43:17,  1.60it/s]
 53%|█████▎    | 30426/57600 [5:19:42<4:48:46,  1.57it/s]
 53%|█████▎    | 30427/57600 [5:19:42<4:45:11,  1.59it/s]
 53%|█████▎    | 30428/57600 [5:19:43<4:45:18,  1.59it/s]
 53%|█████▎    | 30429/57600 [5:19:44<4:51:21,  1.55it/s]
 53%|█████▎    | 30430/57600 [5:19:44<4:41:28,  1.61it/s]
 53%|█████▎    | 30431/57600 [5:19:45<4:42:37,  1.60it/s]
 53%|█████▎    | 30432/57600 [5:19:46<4:50:11,  1.56it/s]
 53%|█████▎    | 30433/57600 [5:19:46<5:01:37,  1.50it/s]
 53%|█████▎    | 30434/57600 [5:19:47<4:55:34,  1.53it/s]
 53%|█████▎    | 30435/57600 [5:19:48<4:46:59,  1.58it/s]
 53%|█████▎    | 30436/57600 [5:19:48<4:44:15,  1.59it/s]
 53%|█████▎    | 30437/57600 [5:19:49<4:41:47,  1.61it/s]
 53%|█████▎    | 30438/57600 [5:19:49<4:42:54,  1.60it/s]
 53%|█████▎    | 30439/57600 [5:19:50<4:43:03,  1.60it/s]
 53%|█████▎    | 30440/57600 [5:19:51<4:40:10,  1.62it/s]
                                                         
{'loss': 1.1916, 'learning_rate': 5.258536585365854e-07, 'epoch': 335.98}

 53%|█████▎    | 30440/57600 [5:19:51<4:40:10,  1.62it/s]
 53%|█████▎    | 30441/57600 [5:19:51<4:43:20,  1.60it/s]
 53%|█████▎    | 30442/57600 [5:19:52<4:46:31,  1.58it/s]
 53%|█████▎    | 30443/57600 [5:19:53<4:40:03,  1.62it/s]
 53%|█████▎    | 30444/57600 [5:19:53<4:37:45,  1.63it/s]
 53%|█████▎    | 30445/57600 [5:19:54<4:32:29,  1.66it/s]
 53%|█████▎    | 30446/57600 [5:19:54<4:31:14,  1.67it/s]
 53%|█████▎    | 30447/57600 [5:19:55<4:38:22,  1.63it/s]
 53%|█████▎    | 30448/57600 [5:19:56<4:36:29,  1.64it/s]
 53%|█████▎    | 30449/57600 [5:19:56<4:37:33,  1.63it/s]
 53%|█████▎    | 30450/57600 [5:19:57<4:45:04,  1.59it/s]
 53%|█████▎    | 30451/57600 [5:19:58<4:52:30,  1.55it/s]
 53%|█████▎    | 30452/57600 [5:19:58<4:45:53,  1.58it/s]
 53%|█████▎    | 30453/57600 [5:19:59<4:35:17,  1.64it/s]
 53%|█████▎    | 30454/57600 [5:19:59<4:29:45,  1.68it/s]
 53%|█████▎    | 30455/57600 [5:20:00<4:32:52,  1.66it/s]
 53%|█████▎    | 30456/57600 [5:20:01<4:32:50,  1.66it/s]
 53%|█████▎    | 30457/57600 [5:20:01<4:41:38,  1.61it/s]
 53%|█████▎    | 30458/57600 [5:20:02<4:38:38,  1.62it/s]
 53%|█████▎    | 30459/57600 [5:20:02<4:40:12,  1.61it/s]
 53%|█████▎    | 30460/57600 [5:20:03<4:32:58,  1.66it/s]
                                                         
{'loss': 1.1924, 'learning_rate': 5.255400696864112e-07, 'epoch': 336.2}

 53%|█████▎    | 30460/57600 [5:20:03<4:32:58,  1.66it/s]
 53%|█████▎    | 30461/57600 [5:20:04<4:32:16,  1.66it/s]
 53%|█████▎    | 30462/57600 [5:20:04<4:30:25,  1.67it/s]
 53%|█████▎    | 30463/57600 [5:20:05<4:27:40,  1.69it/s]
 53%|█████▎    | 30464/57600 [5:20:05<4:46:00,  1.58it/s]
 53%|█████▎    | 30465/57600 [5:20:06<4:54:22,  1.54it/s]
 53%|█████▎    | 30466/57600 [5:20:07<4:56:28,  1.53it/s]
 53%|█████▎    | 30467/57600 [5:20:08<5:06:13,  1.48it/s]
 53%|█████▎    | 30468/57600 [5:20:08<5:08:28,  1.47it/s]
 53%|█████▎    | 30469/57600 [5:20:09<5:02:02,  1.50it/s]
 53%|█████▎    | 30470/57600 [5:20:10<5:03:03,  1.49it/s]
 53%|█████▎    | 30471/57600 [5:20:10<5:00:25,  1.51it/s]
 53%|█████▎    | 30472/57600 [5:20:11<4:53:12,  1.54it/s]
 53%|█████▎    | 30473/57600 [5:20:11<4:48:36,  1.57it/s]
 53%|█████▎    | 30474/57600 [5:20:12<4:43:34,  1.59it/s]
 53%|█████▎    | 30475/57600 [5:20:13<4:38:57,  1.62it/s]
 53%|█████▎    | 30476/57600 [5:20:13<4:46:26,  1.58it/s]
 53%|█████▎    | 30477/57600 [5:20:14<4:44:10,  1.59it/s]
 53%|█████▎    | 30478/57600 [5:20:15<4:39:57,  1.61it/s]
 53%|█████▎    | 30479/57600 [5:20:15<4:51:56,  1.55it/s]
 53%|█████▎    | 30480/57600 [5:20:16<4:49:50,  1.56it/s]
                                                         
{'loss': 1.1476, 'learning_rate': 5.252264808362369e-07, 'epoch': 336.42}

 53%|█████▎    | 30480/57600 [5:20:16<4:49:50,  1.56it/s]
 53%|█████▎    | 30481/57600 [5:20:16<4:44:58,  1.59it/s]
 53%|█████▎    | 30482/57600 [5:20:17<4:41:21,  1.61it/s]
 53%|█████▎    | 30483/57600 [5:20:18<4:40:48,  1.61it/s]
 53%|█████▎    | 30484/57600 [5:20:18<4:39:35,  1.62it/s]
 53%|█████▎    | 30485/57600 [5:20:19<4:45:18,  1.58it/s]
 53%|█████▎    | 30486/57600 [5:20:20<4:41:58,  1.60it/s]
 53%|█████▎    | 30487/57600 [5:20:20<4:38:40,  1.62it/s]
 53%|█████▎    | 30488/57600 [5:20:21<4:51:48,  1.55it/s]
 53%|█████▎    | 30489/57600 [5:20:21<4:48:35,  1.57it/s]
 53%|█████▎    | 30490/57600 [5:20:22<4:50:36,  1.55it/s]
 53%|█████▎    | 30491/57600 [5:20:23<4:54:29,  1.53it/s]
 53%|█████▎    | 30492/57600 [5:20:23<4:51:41,  1.55it/s]
 53%|█████▎    | 30493/57600 [5:20:24<4:53:22,  1.54it/s]
 53%|█████▎    | 30494/57600 [5:20:25<4:56:27,  1.52it/s]
 53%|█████▎    | 30495/57600 [5:20:25<4:48:40,  1.56it/s]
 53%|█████▎    | 30496/57600 [5:20:26<4:49:33,  1.56it/s]
 53%|█████▎    | 30497/57600 [5:20:27<4:50:09,  1.56it/s]
 53%|█████▎    | 30498/57600 [5:20:27<4:41:02,  1.61it/s]
 53%|█████▎    | 30499/57600 [5:20:28<4:51:15,  1.55it/s]
 53%|█████▎    | 30500/57600 [5:20:29<4:58:41,  1.51it/s]
                                                         
{'loss': 1.158, 'learning_rate': 5.249128919860627e-07, 'epoch': 336.64}

 53%|█████▎    | 30500/57600 [5:20:29<4:58:41,  1.51it/s]
 53%|█████▎    | 30501/57600 [5:20:29<4:55:59,  1.53it/s]
 53%|█████▎    | 30502/57600 [5:20:30<4:56:40,  1.52it/s]
 53%|█████▎    | 30503/57600 [5:20:31<4:56:06,  1.53it/s]
 53%|█████▎    | 30504/57600 [5:20:31<4:51:38,  1.55it/s]
 53%|█████▎    | 30505/57600 [5:20:32<4:43:51,  1.59it/s]
 53%|█████▎    | 30506/57600 [5:20:32<4:42:35,  1.60it/s]
 53%|█████▎    | 30507/57600 [5:20:33<4:41:38,  1.60it/s]
 53%|█████▎    | 30508/57600 [5:20:34<4:31:43,  1.66it/s]
 53%|█████▎    | 30509/57600 [5:20:34<4:32:16,  1.66it/s]
 53%|█████▎    | 30510/57600 [5:20:35<4:39:59,  1.61it/s]
 53%|█████▎    | 30511/57600 [5:20:36<4:43:37,  1.59it/s]
 53%|█████▎    | 30512/57600 [5:20:36<4:39:36,  1.61it/s]
 53%|█████▎    | 30513/57600 [5:20:37<4:44:41,  1.59it/s]
 53%|█████▎    | 30514/57600 [5:20:37<4:41:42,  1.60it/s]
 53%|█████▎    | 30515/57600 [5:20:38<4:34:52,  1.64it/s]
 53%|█████▎    | 30516/57600 [5:20:39<4:34:30,  1.64it/s]
 53%|█████▎    | 30517/57600 [5:20:39<4:44:03,  1.59it/s]
 53%|█████▎    | 30518/57600 [5:20:40<4:54:21,  1.53it/s]
 53%|█████▎    | 30519/57600 [5:20:41<4:53:53,  1.54it/s]
 53%|█████▎    | 30520/57600 [5:20:41<4:48:34,  1.56it/s]
                                                         
{'loss': 1.1524, 'learning_rate': 5.245993031358886e-07, 'epoch': 336.87}

 53%|█████▎    | 30520/57600 [5:20:41<4:48:34,  1.56it/s]
 53%|█████▎    | 30521/57600 [5:20:42<4:45:48,  1.58it/s]
 53%|█████▎    | 30522/57600 [5:20:42<4:40:44,  1.61it/s]
 53%|█████▎    | 30523/57600 [5:20:43<4:39:32,  1.61it/s]
 53%|█████▎    | 30524/57600 [5:20:44<4:40:43,  1.61it/s]
 53%|█████▎    | 30525/57600 [5:20:44<4:42:01,  1.60it/s]
 53%|█████▎    | 30526/57600 [5:20:45<4:34:24,  1.64it/s]
 53%|█████▎    | 30527/57600 [5:20:45<4:38:23,  1.62it/s]
 53%|█████▎    | 30528/57600 [5:20:46<4:41:11,  1.60it/s]
 53%|█████▎    | 30529/57600 [5:20:47<4:49:58,  1.56it/s]
 53%|█████▎    | 30530/57600 [5:20:47<4:41:38,  1.60it/s]
 53%|█████▎    | 30531/57600 [5:20:48<4:48:47,  1.56it/s]
 53%|█████▎    | 30532/57600 [5:20:49<4:40:36,  1.61it/s]
 53%|█████▎    | 30533/57600 [5:20:49<5:03:31,  1.49it/s]
 53%|█████▎    | 30534/57600 [5:20:50<4:50:56,  1.55it/s]
 53%|█████▎    | 30535/57600 [5:20:51<4:44:27,  1.59it/s]
 53%|█████▎    | 30536/57600 [5:20:51<4:43:19,  1.59it/s]
 53%|█████▎    | 30537/57600 [5:20:52<4:50:41,  1.55it/s]
 53%|█████▎    | 30538/57600 [5:20:53<4:54:30,  1.53it/s]
 53%|█████▎    | 30539/57600 [5:20:53<4:53:24,  1.54it/s]
 53%|█████▎    | 30540/57600 [5:20:54<4:56:09,  1.52it/s]
                                                         
{'loss': 1.1872, 'learning_rate': 5.242857142857142e-07, 'epoch': 337.09}

 53%|█████▎    | 30540/57600 [5:20:54<4:56:09,  1.52it/s]
 53%|█████▎    | 30541/57600 [5:20:55<4:59:04,  1.51it/s]
 53%|█████▎    | 30542/57600 [5:20:55<4:49:56,  1.56it/s]
 53%|█████▎    | 30543/57600 [5:20:56<4:44:02,  1.59it/s]
 53%|█████▎    | 30544/57600 [5:20:56<4:46:47,  1.57it/s]
 53%|█████▎    | 30545/57600 [5:20:57<4:38:14,  1.62it/s]
 53%|█████▎    | 30546/57600 [5:20:58<4:34:08,  1.64it/s]
 53%|█████▎    | 30547/57600 [5:20:58<4:43:19,  1.59it/s]
 53%|█████▎    | 30548/57600 [5:20:59<4:48:16,  1.56it/s]
 53%|█████▎    | 30549/57600 [5:21:00<4:46:57,  1.57it/s]
 53%|█████▎    | 30550/57600 [5:21:00<4:46:10,  1.58it/s]
 53%|█████▎    | 30551/57600 [5:21:01<4:50:02,  1.55it/s]
 53%|█████▎    | 30552/57600 [5:21:01<4:45:30,  1.58it/s]
 53%|█████▎    | 30553/57600 [5:21:02<4:40:32,  1.61it/s]
 53%|█████▎    | 30554/57600 [5:21:03<4:39:12,  1.61it/s]
 53%|█████▎    | 30555/57600 [5:21:03<4:42:39,  1.59it/s]
 53%|█████▎    | 30556/57600 [5:21:04<4:34:58,  1.64it/s]
 53%|█████▎    | 30557/57600 [5:21:05<4:33:54,  1.65it/s]
 53%|█████▎    | 30558/57600 [5:21:05<4:31:38,  1.66it/s]
 53%|█████▎    | 30559/57600 [5:21:06<4:36:07,  1.63it/s]
 53%|█████▎    | 30560/57600 [5:21:06<4:42:51,  1.59it/s]
                                                         
{'loss': 1.1946, 'learning_rate': 5.239721254355401e-07, 'epoch': 337.31}

 53%|█████▎    | 30560/57600 [5:21:06<4:42:51,  1.59it/s]
 53%|█████▎    | 30561/57600 [5:21:07<4:45:00,  1.58it/s]
 53%|█████▎    | 30562/57600 [5:21:08<4:34:51,  1.64it/s]
 53%|█████▎    | 30563/57600 [5:21:08<4:44:19,  1.58it/s]
 53%|█████▎    | 30564/57600 [5:21:09<4:34:04,  1.64it/s]
 53%|█████▎    | 30565/57600 [5:21:10<4:47:25,  1.57it/s]
 53%|█████▎    | 30566/57600 [5:21:10<4:44:53,  1.58it/s]
 53%|█████▎    | 30567/57600 [5:21:11<4:41:38,  1.60it/s]
 53%|█████▎    | 30568/57600 [5:21:11<4:44:13,  1.59it/s]
 53%|█████▎    | 30569/57600 [5:21:12<4:42:41,  1.59it/s]
 53%|█████▎    | 30570/57600 [5:21:13<4:39:37,  1.61it/s]
 53%|█████▎    | 30571/57600 [5:21:13<4:38:37,  1.62it/s]
 53%|█████▎    | 30572/57600 [5:21:14<4:43:45,  1.59it/s]
 53%|█████▎    | 30573/57600 [5:21:14<4:36:52,  1.63it/s]
 53%|█████▎    | 30574/57600 [5:21:15<4:33:02,  1.65it/s]
 53%|█████▎    | 30575/57600 [5:21:16<4:32:36,  1.65it/s]
 53%|█████▎    | 30576/57600 [5:21:16<4:35:58,  1.63it/s]
 53%|█████▎    | 30577/57600 [5:21:17<4:39:30,  1.61it/s]
 53%|█████▎    | 30578/57600 [5:21:18<4:39:01,  1.61it/s]
 53%|█████▎    | 30579/57600 [5:21:18<4:43:57,  1.59it/s]
 53%|█████▎    | 30580/57600 [5:21:19<4:41:09,  1.60it/s]
                                                         
{'loss': 1.2015, 'learning_rate': 5.236585365853657e-07, 'epoch': 337.53}

 53%|█████▎    | 30580/57600 [5:21:19<4:41:09,  1.60it/s]
 53%|█████▎    | 30581/57600 [5:21:19<4:36:17,  1.63it/s]
 53%|█████▎    | 30582/57600 [5:21:20<4:32:14,  1.65it/s]
 53%|█████▎    | 30583/57600 [5:21:21<4:33:44,  1.64it/s]
 53%|█████▎    | 30584/57600 [5:21:21<4:40:21,  1.61it/s]
 53%|█████▎    | 30585/57600 [5:21:22<4:31:02,  1.66it/s]
 53%|█████▎    | 30586/57600 [5:21:22<4:28:07,  1.68it/s]
 53%|█████▎    | 30587/57600 [5:21:23<4:30:01,  1.67it/s]
 53%|█████▎    | 30588/57600 [5:21:24<4:35:54,  1.63it/s]
 53%|█████▎    | 30589/57600 [5:21:24<4:38:14,  1.62it/s]
 53%|█████▎    | 30590/57600 [5:21:25<4:40:36,  1.60it/s]
 53%|█████▎    | 30591/57600 [5:21:26<4:40:06,  1.61it/s]
 53%|█████▎    | 30592/57600 [5:21:26<4:42:54,  1.59it/s]
 53%|█████▎    | 30593/57600 [5:21:27<4:49:40,  1.55it/s]
 53%|█████▎    | 30594/57600 [5:21:27<4:39:46,  1.61it/s]
 53%|█████▎    | 30595/57600 [5:21:28<4:37:26,  1.62it/s]
 53%|█████▎    | 30596/57600 [5:21:29<4:36:59,  1.62it/s]
 53%|█████▎    | 30597/57600 [5:21:29<4:44:07,  1.58it/s]
 53%|█████▎    | 30598/57600 [5:21:30<4:47:12,  1.57it/s]
 53%|█████▎    | 30599/57600 [5:21:31<4:55:33,  1.52it/s]
 53%|█████▎    | 30600/57600 [5:21:31<4:45:56,  1.57it/s]
                                                         
{'loss': 1.1733, 'learning_rate': 5.233449477351916e-07, 'epoch': 337.75}

 53%|█████▎    | 30600/57600 [5:21:31<4:45:56,  1.57it/s]
 53%|█████▎    | 30601/57600 [5:21:32<4:45:45,  1.57it/s]
 53%|█████▎    | 30602/57600 [5:21:32<4:36:16,  1.63it/s]
 53%|█████▎    | 30603/57600 [5:21:33<4:32:52,  1.65it/s]
 53%|█████▎    | 30604/57600 [5:21:34<4:43:22,  1.59it/s]
 53%|█████▎    | 30605/57600 [5:21:34<4:37:24,  1.62it/s]
 53%|█████▎    | 30606/57600 [5:21:35<4:36:55,  1.62it/s]
 53%|█████▎    | 30607/57600 [5:21:36<4:37:07,  1.62it/s]
 53%|█████▎    | 30608/57600 [5:21:36<4:38:30,  1.62it/s]
 53%|█████▎    | 30609/57600 [5:21:37<4:38:35,  1.61it/s]
 53%|█████▎    | 30610/57600 [5:21:37<4:46:21,  1.57it/s]
 53%|█████▎    | 30611/57600 [5:21:38<4:45:05,  1.58it/s]
 53%|█████▎    | 30612/57600 [5:21:39<4:45:14,  1.58it/s]
 53%|█████▎    | 30613/57600 [5:21:39<4:45:54,  1.57it/s]
 53%|█████▎    | 30614/57600 [5:21:40<4:41:37,  1.60it/s]
 53%|█████▎    | 30615/57600 [5:21:41<4:51:20,  1.54it/s]
 53%|█████▎    | 30616/57600 [5:21:41<4:43:06,  1.59it/s]
 53%|█████▎    | 30617/57600 [5:21:42<4:44:26,  1.58it/s]
 53%|█████▎    | 30618/57600 [5:21:43<4:59:41,  1.50it/s]
 53%|█████▎    | 30619/57600 [5:21:43<4:54:56,  1.52it/s]
 53%|█████▎    | 30620/57600 [5:21:44<4:42:26,  1.59it/s]
                                                         
{'loss': 1.1593, 'learning_rate': 5.230313588850173e-07, 'epoch': 337.97}

 53%|█████▎    | 30620/57600 [5:21:44<4:42:26,  1.59it/s]
 53%|█████▎    | 30621/57600 [5:21:44<4:39:58,  1.61it/s]
 53%|█████▎    | 30622/57600 [5:21:45<4:42:12,  1.59it/s]
 53%|█████▎    | 30623/57600 [5:21:46<4:44:42,  1.58it/s]
 53%|█████▎    | 30624/57600 [5:21:46<4:45:03,  1.58it/s]
 53%|█████▎    | 30625/57600 [5:21:47<4:40:59,  1.60it/s]
 53%|█████▎    | 30626/57600 [5:21:48<4:43:30,  1.59it/s]
 53%|█████▎    | 30627/57600 [5:21:48<4:49:45,  1.55it/s]
 53%|█████▎    | 30628/57600 [5:21:49<4:48:48,  1.56it/s]
 53%|█████▎    | 30629/57600 [5:21:50<4:45:41,  1.57it/s]
 53%|█████▎    | 30630/57600 [5:21:50<4:44:45,  1.58it/s]
 53%|█████▎    | 30631/57600 [5:21:51<4:39:56,  1.61it/s]
 53%|█████▎    | 30632/57600 [5:21:51<4:41:37,  1.60it/s]
 53%|█████▎    | 30633/57600 [5:21:52<4:43:22,  1.59it/s]
 53%|█████▎    | 30634/57600 [5:21:53<4:36:51,  1.62it/s]
 53%|█████▎    | 30635/57600 [5:21:53<4:33:32,  1.64it/s]
 53%|█████▎    | 30636/57600 [5:21:54<4:40:31,  1.60it/s]
 53%|█████▎    | 30637/57600 [5:21:54<4:35:49,  1.63it/s]
 53%|█████▎    | 30638/57600 [5:21:55<4:39:17,  1.61it/s]
 53%|█████▎    | 30639/57600 [5:21:56<4:46:21,  1.57it/s]
 53%|█████▎    | 30640/57600 [5:21:56<4:37:55,  1.62it/s]
                                                         
{'loss': 1.1967, 'learning_rate': 5.227177700348432e-07, 'epoch': 338.19}

 53%|█████▎    | 30640/57600 [5:21:56<4:37:55,  1.62it/s]
 53%|█████▎    | 30641/57600 [5:21:57<4:35:40,  1.63it/s]
 53%|█████▎    | 30642/57600 [5:21:58<4:57:49,  1.51it/s]
 53%|█████▎    | 30643/57600 [5:21:58<4:50:43,  1.55it/s]
 53%|█████▎    | 30644/57600 [5:21:59<4:47:28,  1.56it/s]
 53%|█████▎    | 30645/57600 [5:22:00<4:40:42,  1.60it/s]
 53%|█████▎    | 30646/57600 [5:22:00<4:36:46,  1.62it/s]
 53%|█████▎    | 30647/57600 [5:22:01<4:51:31,  1.54it/s]
 53%|█████▎    | 30648/57600 [5:22:01<4:41:20,  1.60it/s]
 53%|█████▎    | 30649/57600 [5:22:02<4:35:15,  1.63it/s]
 53%|█████▎    | 30650/57600 [5:22:03<4:32:31,  1.65it/s]
 53%|█████▎    | 30651/57600 [5:22:03<4:41:14,  1.60it/s]
 53%|█████▎    | 30652/57600 [5:22:04<4:41:15,  1.60it/s]
 53%|█████▎    | 30653/57600 [5:22:05<4:50:11,  1.55it/s]
 53%|█████▎    | 30654/57600 [5:22:05<4:46:50,  1.57it/s]
 53%|█████▎    | 30655/57600 [5:22:06<4:42:01,  1.59it/s]
 53%|█████▎    | 30656/57600 [5:22:06<4:39:35,  1.61it/s]
 53%|█████▎    | 30657/57600 [5:22:07<4:35:56,  1.63it/s]
 53%|█████▎    | 30658/57600 [5:22:08<4:29:45,  1.66it/s]
 53%|█████▎    | 30659/57600 [5:22:08<4:25:12,  1.69it/s]
 53%|█████▎    | 30660/57600 [5:22:09<4:32:15,  1.65it/s]
                                                         
{'loss': 1.1877, 'learning_rate': 5.22404181184669e-07, 'epoch': 338.41}

 53%|█████▎    | 30660/57600 [5:22:09<4:32:15,  1.65it/s]
 53%|█████▎    | 30661/57600 [5:22:09<4:31:11,  1.66it/s]
 53%|█████▎    | 30662/57600 [5:22:10<4:40:33,  1.60it/s]
 53%|█████▎    | 30663/57600 [5:22:11<4:30:47,  1.66it/s]
 53%|█████▎    | 30664/57600 [5:22:11<4:31:27,  1.65it/s]
 53%|█████▎    | 30665/57600 [5:22:12<4:31:33,  1.65it/s]
 53%|█████▎    | 30666/57600 [5:22:13<4:33:18,  1.64it/s]
 53%|█████▎    | 30667/57600 [5:22:13<4:36:54,  1.62it/s]
 53%|█████▎    | 30668/57600 [5:22:14<4:45:52,  1.57it/s]
 53%|█████▎    | 30669/57600 [5:22:14<4:44:14,  1.58it/s]
 53%|█████▎    | 30670/57600 [5:22:15<4:42:18,  1.59it/s]
 53%|█████▎    | 30671/57600 [5:22:16<4:43:57,  1.58it/s]
 53%|█████▎    | 30672/57600 [5:22:16<4:39:10,  1.61it/s]
 53%|█████▎    | 30673/57600 [5:22:17<4:38:11,  1.61it/s]
 53%|█████▎    | 30674/57600 [5:22:18<4:37:39,  1.62it/s]
 53%|█████▎    | 30675/57600 [5:22:18<4:43:00,  1.59it/s]
 53%|█████▎    | 30676/57600 [5:22:19<4:45:52,  1.57it/s]
 53%|█████▎    | 30677/57600 [5:22:19<4:45:00,  1.57it/s]
 53%|█████▎    | 30678/57600 [5:22:20<4:42:18,  1.59it/s]
 53%|█████▎    | 30679/57600 [5:22:21<4:43:11,  1.58it/s]
 53%|█████▎    | 30680/57600 [5:22:21<4:56:46,  1.51it/s]
                                                         
{'loss': 1.142, 'learning_rate': 5.220905923344948e-07, 'epoch': 338.63}

 53%|█████▎    | 30680/57600 [5:22:21<4:56:46,  1.51it/s]
 53%|█████▎    | 30681/57600 [5:22:22<4:53:16,  1.53it/s]
 53%|█████▎    | 30682/57600 [5:22:23<4:46:57,  1.56it/s]
 53%|█████▎    | 30683/57600 [5:22:23<4:38:49,  1.61it/s]
 53%|█████▎    | 30684/57600 [5:22:24<4:35:42,  1.63it/s]
 53%|█████▎    | 30685/57600 [5:22:25<4:50:26,  1.54it/s]
 53%|█████▎    | 30686/57600 [5:22:25<4:39:52,  1.60it/s]
 53%|█████▎    | 30687/57600 [5:22:26<4:47:26,  1.56it/s]
 53%|█████▎    | 30688/57600 [5:22:26<4:43:19,  1.58it/s]
 53%|█████▎    | 30689/57600 [5:22:27<4:36:59,  1.62it/s]
 53%|█████▎    | 30690/57600 [5:22:28<4:49:28,  1.55it/s]
 53%|█████▎    | 30691/57600 [5:22:28<4:43:41,  1.58it/s]
 53%|█████▎    | 30692/57600 [5:22:29<4:35:32,  1.63it/s]
 53%|█████▎    | 30693/57600 [5:22:30<4:38:09,  1.61it/s]
 53%|█████▎    | 30694/57600 [5:22:30<4:50:11,  1.55it/s]
 53%|█████▎    | 30695/57600 [5:22:31<4:44:01,  1.58it/s]
 53%|█████▎    | 30696/57600 [5:22:32<4:45:19,  1.57it/s]
 53%|█████▎    | 30697/57600 [5:22:32<4:40:19,  1.60it/s]
 53%|█████▎    | 30698/57600 [5:22:33<4:34:23,  1.63it/s]
 53%|█████▎    | 30699/57600 [5:22:33<4:42:31,  1.59it/s]
 53%|█████▎    | 30700/57600 [5:22:34<4:41:51,  1.59it/s]
                                                         
{'loss': 1.1526, 'learning_rate': 5.217770034843206e-07, 'epoch': 338.85}

 53%|█████▎    | 30700/57600 [5:22:34<4:41:51,  1.59it/s]
 53%|█████▎    | 30701/57600 [5:22:35<4:46:10,  1.57it/s]
 53%|█████▎    | 30702/57600 [5:22:35<4:42:58,  1.58it/s]
 53%|█████▎    | 30703/57600 [5:22:36<4:36:44,  1.62it/s]
 53%|█████▎    | 30704/57600 [5:22:37<4:43:23,  1.58it/s]
 53%|█████▎    | 30705/57600 [5:22:37<4:39:58,  1.60it/s]
 53%|█████▎    | 30706/57600 [5:22:38<4:46:25,  1.56it/s]
 53%|█████▎    | 30707/57600 [5:22:38<4:37:29,  1.62it/s]
 53%|█████▎    | 30708/57600 [5:22:39<4:37:25,  1.62it/s]
 53%|█████▎    | 30709/57600 [5:22:40<4:29:34,  1.66it/s]
 53%|█████▎    | 30710/57600 [5:22:40<4:32:11,  1.65it/s]
 53%|█████▎    | 30711/57600 [5:22:41<4:30:57,  1.65it/s]
 53%|█████▎    | 30712/57600 [5:22:41<4:32:43,  1.64it/s]
 53%|█████▎    | 30713/57600 [5:22:42<4:31:46,  1.65it/s]
 53%|█████▎    | 30714/57600 [5:22:43<4:39:21,  1.60it/s]
 53%|█████▎    | 30715/57600 [5:22:43<4:35:53,  1.62it/s]
 53%|█████▎    | 30716/57600 [5:22:44<4:33:53,  1.64it/s]
 53%|█████▎    | 30717/57600 [5:22:44<4:33:18,  1.64it/s]
 53%|█████▎    | 30718/57600 [5:22:45<4:36:24,  1.62it/s]
 53%|█████▎    | 30719/57600 [5:22:46<4:35:47,  1.62it/s]
 53%|█████▎    | 30720/57600 [5:22:46<4:34:46,  1.63it/s]
                                                         
{'loss': 1.1642, 'learning_rate': 5.214634146341463e-07, 'epoch': 339.07}

 53%|█████▎    | 30720/57600 [5:22:46<4:34:46,  1.63it/s]
 53%|█████▎    | 30721/57600 [5:22:47<4:33:12,  1.64it/s]
 53%|█████▎    | 30722/57600 [5:22:48<4:31:34,  1.65it/s]
 53%|█████▎    | 30723/57600 [5:22:48<4:37:47,  1.61it/s]
 53%|█████▎    | 30724/57600 [5:22:49<4:41:04,  1.59it/s]
 53%|█████▎    | 30725/57600 [5:22:49<4:43:30,  1.58it/s]
 53%|█████▎    | 30726/57600 [5:22:50<4:37:06,  1.62it/s]
 53%|█████▎    | 30727/57600 [5:22:51<4:43:00,  1.58it/s]
 53%|█████▎    | 30728/57600 [5:22:51<4:44:25,  1.57it/s]
 53%|█████▎    | 30729/57600 [5:22:52<4:48:15,  1.55it/s]
 53%|█████▎    | 30730/57600 [5:22:53<4:45:13,  1.57it/s]
 53%|█████▎    | 30731/57600 [5:22:53<4:44:14,  1.58it/s]
 53%|█████▎    | 30732/57600 [5:22:54<4:38:08,  1.61it/s]
 53%|█████▎    | 30733/57600 [5:22:55<4:45:01,  1.57it/s]
 53%|█████▎    | 30734/57600 [5:22:55<4:44:43,  1.57it/s]
 53%|█████▎    | 30735/57600 [5:22:56<4:40:32,  1.60it/s]
 53%|█████▎    | 30736/57600 [5:22:56<4:34:11,  1.63it/s]
 53%|█████▎    | 30737/57600 [5:22:57<4:49:51,  1.54it/s]
 53%|█████▎    | 30738/57600 [5:22:58<4:47:25,  1.56it/s]
 53%|█████▎    | 30739/57600 [5:22:58<4:40:25,  1.60it/s]
 53%|█████▎    | 30740/57600 [5:22:59<4:43:37,  1.58it/s]
                                                         
{'loss': 1.1686, 'learning_rate': 5.211498257839722e-07, 'epoch': 339.29}

 53%|█████▎    | 30740/57600 [5:22:59<4:43:37,  1.58it/s]
 53%|█████▎    | 30741/57600 [5:23:00<4:39:01,  1.60it/s]
 53%|█████▎    | 30742/57600 [5:23:00<4:38:41,  1.61it/s]
 53%|█████▎    | 30743/57600 [5:23:01<4:36:41,  1.62it/s]
 53%|█████▎    | 30744/57600 [5:23:01<4:32:35,  1.64it/s]
 53%|█████▎    | 30745/57600 [5:23:02<4:30:23,  1.66it/s]
 53%|█████▎    | 30746/57600 [5:23:03<4:32:14,  1.64it/s]
 53%|█████▎    | 30747/57600 [5:23:03<4:48:17,  1.55it/s]
 53%|█████▎    | 30748/57600 [5:23:04<4:49:23,  1.55it/s]
 53%|█████▎    | 30749/57600 [5:23:05<4:48:20,  1.55it/s]
 53%|█████▎    | 30750/57600 [5:23:05<4:38:11,  1.61it/s]
 53%|█████▎    | 30751/57600 [5:23:06<4:48:30,  1.55it/s]
 53%|█████▎    | 30752/57600 [5:23:06<4:40:04,  1.60it/s]
 53%|█████▎    | 30753/57600 [5:23:07<4:45:13,  1.57it/s]
 53%|█████▎    | 30754/57600 [5:23:08<4:52:31,  1.53it/s]
 53%|█████▎    | 30755/57600 [5:23:08<4:39:47,  1.60it/s]
 53%|█████▎    | 30756/57600 [5:23:09<4:45:30,  1.57it/s]
 53%|█████▎    | 30757/57600 [5:23:10<4:44:11,  1.57it/s]
 53%|█████▎    | 30758/57600 [5:23:10<4:38:19,  1.61it/s]
 53%|█████▎    | 30759/57600 [5:23:11<4:39:41,  1.60it/s]
 53%|█████▎    | 30760/57600 [5:23:12<4:41:19,  1.59it/s]
                                                         
{'loss': 1.1572, 'learning_rate': 5.208362369337978e-07, 'epoch': 339.51}

 53%|█████▎    | 30760/57600 [5:23:12<4:41:19,  1.59it/s]
 53%|█████▎    | 30761/57600 [5:23:12<4:40:48,  1.59it/s]
 53%|█████▎    | 30762/57600 [5:23:13<4:43:06,  1.58it/s]
 53%|█████▎    | 30763/57600 [5:23:13<4:33:59,  1.63it/s]
 53%|█████▎    | 30764/57600 [5:23:14<4:38:05,  1.61it/s]
 53%|█████▎    | 30765/57600 [5:23:15<4:34:00,  1.63it/s]
 53%|█████▎    | 30766/57600 [5:23:15<4:28:49,  1.66it/s]
 53%|█████▎    | 30767/57600 [5:23:16<4:40:02,  1.60it/s]
 53%|█████▎    | 30768/57600 [5:23:17<4:45:36,  1.57it/s]
 53%|█████▎    | 30769/57600 [5:23:17<4:46:52,  1.56it/s]
 53%|█████▎    | 30770/57600 [5:23:18<4:53:45,  1.52it/s]
 53%|█████▎    | 30771/57600 [5:23:19<4:54:57,  1.52it/s]
 53%|█████▎    | 30772/57600 [5:23:19<4:55:38,  1.51it/s]
 53%|█████▎    | 30773/57600 [5:23:20<4:47:09,  1.56it/s]
 53%|█████▎    | 30774/57600 [5:23:20<4:40:35,  1.59it/s]
 53%|█████▎    | 30775/57600 [5:23:21<4:37:54,  1.61it/s]
 53%|█████▎    | 30776/57600 [5:23:22<4:36:19,  1.62it/s]
 53%|█████▎    | 30777/57600 [5:23:22<4:36:16,  1.62it/s]
 53%|█████▎    | 30778/57600 [5:23:23<4:37:42,  1.61it/s]
 53%|█████▎    | 30779/57600 [5:23:23<4:33:27,  1.63it/s]
 53%|█████▎    | 30780/57600 [5:23:24<4:30:00,  1.66it/s]
                                                         
{'loss': 1.1538, 'learning_rate': 5.205226480836237e-07, 'epoch': 339.74}

 53%|█████▎    | 30780/57600 [5:23:24<4:30:00,  1.66it/s]
 53%|█████▎    | 30781/57600 [5:23:25<4:37:47,  1.61it/s]
 53%|█████▎    | 30782/57600 [5:23:25<4:37:54,  1.61it/s]
 53%|█████▎    | 30783/57600 [5:23:26<4:42:51,  1.58it/s]
 53%|█████▎    | 30784/57600 [5:23:27<4:39:32,  1.60it/s]
 53%|█████▎    | 30785/57600 [5:23:27<4:48:02,  1.55it/s]
 53%|█████▎    | 30786/57600 [5:23:28<4:45:01,  1.57it/s]
 53%|█████▎    | 30787/57600 [5:23:29<4:46:37,  1.56it/s]
 53%|█████▎    | 30788/57600 [5:23:29<4:36:39,  1.62it/s]
 53%|█████▎    | 30789/57600 [5:23:30<4:33:03,  1.64it/s]
 53%|█████▎    | 30790/57600 [5:23:30<4:33:52,  1.63it/s]
 53%|█████▎    | 30791/57600 [5:23:31<4:54:33,  1.52it/s]
 53%|█████▎    | 30792/57600 [5:23:32<4:44:22,  1.57it/s]
 53%|█████▎    | 30793/57600 [5:23:32<4:44:17,  1.57it/s]
 53%|█████▎    | 30794/57600 [5:23:33<4:45:06,  1.57it/s]
 53%|█████▎    | 30795/57600 [5:23:34<4:46:54,  1.56it/s]
 53%|█████▎    | 30796/57600 [5:23:34<4:41:13,  1.59it/s]
 53%|█████▎    | 30797/57600 [5:23:35<4:36:31,  1.62it/s]
 53%|█████▎    | 30798/57600 [5:23:35<4:40:10,  1.59it/s]
 53%|█████▎    | 30799/57600 [5:23:36<4:39:22,  1.60it/s]
 53%|█████▎    | 30800/57600 [5:23:37<4:41:34,  1.59it/s]
                                                         
{'loss': 1.1739, 'learning_rate': 5.202090592334495e-07, 'epoch': 339.96}

 53%|█████▎    | 30800/57600 [5:23:37<4:41:34,  1.59it/s]
 53%|█████▎    | 30801/57600 [5:23:37<4:35:48,  1.62it/s]
 53%|█████▎    | 30802/57600 [5:23:38<4:36:48,  1.61it/s]
 53%|█████▎    | 30803/57600 [5:23:38<4:32:27,  1.64it/s]
 53%|█████▎    | 30804/57600 [5:23:39<4:28:21,  1.66it/s]
 53%|█████▎    | 30805/57600 [5:23:40<4:39:11,  1.60it/s]
 53%|█████▎    | 30806/57600 [5:23:40<4:37:17,  1.61it/s]
 53%|█████▎    | 30807/57600 [5:23:41<4:33:37,  1.63it/s]
 53%|█████▎    | 30808/57600 [5:23:42<4:34:28,  1.63it/s]
 53%|█████▎    | 30809/57600 [5:23:42<4:36:56,  1.61it/s]
 53%|█████▎    | 30810/57600 [5:23:43<4:36:44,  1.61it/s]
 53%|█████▎    | 30811/57600 [5:23:43<4:36:05,  1.62it/s]
 53%|█████▎    | 30812/57600 [5:23:44<4:30:48,  1.65it/s]
 53%|█████▎    | 30813/57600 [5:23:45<4:27:29,  1.67it/s]
 53%|█████▎    | 30814/57600 [5:23:45<4:29:49,  1.65it/s]
 53%|█████▎    | 30815/57600 [5:23:46<4:26:01,  1.68it/s]
 54%|█████▎    | 30816/57600 [5:23:46<4:29:56,  1.65it/s]
 54%|█████▎    | 30817/57600 [5:23:47<4:32:14,  1.64it/s]
 54%|█████▎    | 30818/57600 [5:23:48<4:25:40,  1.68it/s]
 54%|█████▎    | 30819/57600 [5:23:48<4:36:32,  1.61it/s]
 54%|█████▎    | 30820/57600 [5:23:49<4:33:58,  1.63it/s]
                                                         
{'loss': 1.2046, 'learning_rate': 5.198954703832752e-07, 'epoch': 340.18}

 54%|█████▎    | 30820/57600 [5:23:49<4:33:58,  1.63it/s]
 54%|█████▎    | 30821/57600 [5:23:50<4:37:29,  1.61it/s]
 54%|█████▎    | 30822/57600 [5:23:50<4:31:42,  1.64it/s]
 54%|█████▎    | 30823/57600 [5:23:51<4:25:26,  1.68it/s]
 54%|█████▎    | 30824/57600 [5:23:51<4:31:41,  1.64it/s]
 54%|█████▎    | 30825/57600 [5:23:52<4:33:39,  1.63it/s]
 54%|█████▎    | 30826/57600 [5:23:53<4:32:17,  1.64it/s]
 54%|█████▎    | 30827/57600 [5:23:53<4:32:42,  1.64it/s]
 54%|█████▎    | 30828/57600 [5:23:54<4:37:14,  1.61it/s]
 54%|█████▎    | 30829/57600 [5:23:54<4:34:04,  1.63it/s]
 54%|█████▎    | 30830/57600 [5:23:55<4:50:09,  1.54it/s]
 54%|█████▎    | 30831/57600 [5:23:56<4:50:39,  1.53it/s]
 54%|█████▎    | 30832/57600 [5:23:56<4:40:45,  1.59it/s]
 54%|█████▎    | 30833/57600 [5:23:57<4:44:16,  1.57it/s]
 54%|█████▎    | 30834/57600 [5:23:58<4:46:09,  1.56it/s]
 54%|█████▎    | 30835/57600 [5:23:58<4:35:22,  1.62it/s]
 54%|█████▎    | 30836/57600 [5:23:59<4:43:42,  1.57it/s]
 54%|█████▎    | 30837/57600 [5:24:00<4:49:02,  1.54it/s]
 54%|█████▎    | 30838/57600 [5:24:00<4:46:23,  1.56it/s]
 54%|█████▎    | 30839/57600 [5:24:01<4:41:54,  1.58it/s]
 54%|█████▎    | 30840/57600 [5:24:01<4:42:15,  1.58it/s]
                                                         
{'loss': 1.1681, 'learning_rate': 5.19581881533101e-07, 'epoch': 340.4}

 54%|█████▎    | 30840/57600 [5:24:01<4:42:15,  1.58it/s]
 54%|█████▎    | 30841/57600 [5:24:02<4:39:49,  1.59it/s]
 54%|█████▎    | 30842/57600 [5:24:03<4:39:21,  1.60it/s]
 54%|█████▎    | 30843/57600 [5:24:03<4:41:52,  1.58it/s]
 54%|█████▎    | 30844/57600 [5:24:04<4:32:07,  1.64it/s]
 54%|█████▎    | 30845/57600 [5:24:04<4:30:45,  1.65it/s]
 54%|█████▎    | 30846/57600 [5:24:05<4:37:59,  1.60it/s]
 54%|█████▎    | 30847/57600 [5:24:06<4:48:43,  1.54it/s]
 54%|█████▎    | 30848/57600 [5:24:07<4:51:34,  1.53it/s]
 54%|█████▎    | 30849/57600 [5:24:07<4:41:08,  1.59it/s]
 54%|█████▎    | 30850/57600 [5:24:08<4:38:18,  1.60it/s]
 54%|█████▎    | 30851/57600 [5:24:08<4:34:30,  1.62it/s]
 54%|█████▎    | 30852/57600 [5:24:09<4:40:42,  1.59it/s]
 54%|█████▎    | 30853/57600 [5:24:10<4:46:17,  1.56it/s]
 54%|█████▎    | 30854/57600 [5:24:10<4:41:17,  1.58it/s]
 54%|█████▎    | 30855/57600 [5:24:11<4:40:09,  1.59it/s]
 54%|█████▎    | 30856/57600 [5:24:11<4:40:05,  1.59it/s]
 54%|█████▎    | 30857/57600 [5:24:12<4:44:35,  1.57it/s]
 54%|█████▎    | 30858/57600 [5:24:13<4:48:29,  1.54it/s]
 54%|█████▎    | 30859/57600 [5:24:13<4:41:24,  1.58it/s]
 54%|█████▎    | 30860/57600 [5:24:14<4:32:52,  1.63it/s]
                                                         
{'loss': 1.1633, 'learning_rate': 5.192682926829268e-07, 'epoch': 340.62}

 54%|█████▎    | 30860/57600 [5:24:14<4:32:52,  1.63it/s]
 54%|█████▎    | 30861/57600 [5:24:15<4:35:48,  1.62it/s]
 54%|█████▎    | 30862/57600 [5:24:15<4:38:36,  1.60it/s]
 54%|█████▎    | 30863/57600 [5:24:16<4:47:25,  1.55it/s]
 54%|█████▎    | 30864/57600 [5:24:17<4:39:43,  1.59it/s]
 54%|█████▎    | 30865/57600 [5:24:17<4:37:06,  1.61it/s]
 54%|█████▎    | 30866/57600 [5:24:18<4:31:33,  1.64it/s]
 54%|█████▎    | 30867/57600 [5:24:18<4:52:30,  1.52it/s]
 54%|█████▎    | 30868/57600 [5:24:19<4:44:26,  1.57it/s]
 54%|█████▎    | 30869/57600 [5:24:20<4:41:57,  1.58it/s]
 54%|█████▎    | 30870/57600 [5:24:20<4:41:31,  1.58it/s]
 54%|█████▎    | 30871/57600 [5:24:21<4:34:38,  1.62it/s]
 54%|█████▎    | 30872/57600 [5:24:22<4:36:53,  1.61it/s]
 54%|█████▎    | 30873/57600 [5:24:22<4:42:20,  1.58it/s]
 54%|█████▎    | 30874/57600 [5:24:23<4:43:03,  1.57it/s]
 54%|█████▎    | 30875/57600 [5:24:23<4:33:31,  1.63it/s]
 54%|█████▎    | 30876/57600 [5:24:24<4:37:29,  1.61it/s]
 54%|█████▎    | 30877/57600 [5:24:25<4:34:11,  1.62it/s]
 54%|█████▎    | 30878/57600 [5:24:25<4:42:18,  1.58it/s]
 54%|█████▎    | 30879/57600 [5:24:26<4:44:07,  1.57it/s]
 54%|█████▎    | 30880/57600 [5:24:27<4:36:05,  1.61it/s]
                                                         
{'loss': 1.1735, 'learning_rate': 5.189547038327525e-07, 'epoch': 340.84}

 54%|█████▎    | 30880/57600 [5:24:27<4:36:05,  1.61it/s]
 54%|█████▎    | 30881/57600 [5:24:27<4:37:03,  1.61it/s]
 54%|█████▎    | 30882/57600 [5:24:28<4:38:05,  1.60it/s]
 54%|█████▎    | 30883/57600 [5:24:28<4:32:55,  1.63it/s]
 54%|█████▎    | 30884/57600 [5:24:29<4:27:20,  1.67it/s]
 54%|█████▎    | 30885/57600 [5:24:30<4:28:57,  1.66it/s]
 54%|█████▎    | 30886/57600 [5:24:30<4:28:08,  1.66it/s]
 54%|█████▎    | 30887/57600 [5:24:31<4:29:26,  1.65it/s]
 54%|█████▎    | 30888/57600 [5:24:31<4:33:13,  1.63it/s]
 54%|█████▎    | 30889/57600 [5:24:32<4:37:38,  1.60it/s]
 54%|█████▎    | 30890/57600 [5:24:33<4:28:06,  1.66it/s]
 54%|█████▎    | 30891/57600 [5:24:33<4:37:04,  1.61it/s]
 54%|█████▎    | 30892/57600 [5:24:34<4:40:10,  1.59it/s]
 54%|█████▎    | 30893/57600 [5:24:35<4:34:09,  1.62it/s]
 54%|█████▎    | 30894/57600 [5:24:35<4:33:07,  1.63it/s]
 54%|█████▎    | 30895/57600 [5:24:36<4:50:42,  1.53it/s]
 54%|█████▎    | 30896/57600 [5:24:36<4:39:56,  1.59it/s]
 54%|█████▎    | 30897/57600 [5:24:37<4:50:11,  1.53it/s]
 54%|█████▎    | 30898/57600 [5:24:38<4:56:43,  1.50it/s]
 54%|█████▎    | 30899/57600 [5:24:38<4:49:26,  1.54it/s]
 54%|█████▎    | 30900/57600 [5:24:39<4:46:35,  1.55it/s]
                                                         
{'loss': 1.1636, 'learning_rate': 5.186411149825783e-07, 'epoch': 341.06}

 54%|█████▎    | 30900/57600 [5:24:39<4:46:35,  1.55it/s]
 54%|█████▎    | 30901/57600 [5:24:40<4:48:12,  1.54it/s]
 54%|█████▎    | 30902/57600 [5:24:40<4:56:19,  1.50it/s]
 54%|█████▎    | 30903/57600 [5:24:41<4:46:16,  1.55it/s]
 54%|█████▎    | 30904/57600 [5:24:42<4:42:14,  1.58it/s]
 54%|█████▎    | 30905/57600 [5:24:42<4:34:47,  1.62it/s]
 54%|█████▎    | 30906/57600 [5:24:43<4:42:11,  1.58it/s]
 54%|█████▎    | 30907/57600 [5:24:44<4:45:14,  1.56it/s]
 54%|█████▎    | 30908/57600 [5:24:44<4:40:25,  1.59it/s]
 54%|█████▎    | 30909/57600 [5:24:45<4:35:13,  1.62it/s]
 54%|█████▎    | 30910/57600 [5:24:45<4:35:22,  1.62it/s]
 54%|█████▎    | 30911/57600 [5:24:46<4:45:25,  1.56it/s]
 54%|█████▎    | 30912/57600 [5:24:47<4:39:13,  1.59it/s]
 54%|█████▎    | 30913/57600 [5:24:47<4:38:51,  1.60it/s]
 54%|█████▎    | 30914/57600 [5:24:48<4:34:33,  1.62it/s]
 54%|█████▎    | 30915/57600 [5:24:49<4:33:02,  1.63it/s]
 54%|█████▎    | 30916/57600 [5:24:49<4:43:03,  1.57it/s]
 54%|█████▎    | 30917/57600 [5:24:50<4:46:14,  1.55it/s]
 54%|█████▎    | 30918/57600 [5:24:50<4:43:05,  1.57it/s]
 54%|█████▎    | 30919/57600 [5:24:51<4:46:35,  1.55it/s]
 54%|█████▎    | 30920/57600 [5:24:52<4:34:04,  1.62it/s]
                                                         
{'loss': 1.1792, 'learning_rate': 5.183275261324041e-07, 'epoch': 341.28}

 54%|█████▎    | 30920/57600 [5:24:52<4:34:04,  1.62it/s]
 54%|█████▎    | 30921/57600 [5:24:52<4:38:31,  1.60it/s]
 54%|█████▎    | 30922/57600 [5:24:53<4:46:50,  1.55it/s]
 54%|█████▎    | 30923/57600 [5:24:54<4:37:35,  1.60it/s]
 54%|█████▎    | 30924/57600 [5:24:54<4:31:17,  1.64it/s]
 54%|█████▎    | 30925/57600 [5:24:55<4:33:16,  1.63it/s]
 54%|█████▎    | 30926/57600 [5:24:55<4:26:24,  1.67it/s]
 54%|█████▎    | 30927/57600 [5:24:56<4:25:58,  1.67it/s]
 54%|█████▎    | 30928/57600 [5:24:57<4:24:00,  1.68it/s]
 54%|█████▎    | 30929/57600 [5:24:57<4:23:24,  1.69it/s]
 54%|█████▎    | 30930/57600 [5:24:58<4:27:43,  1.66it/s]
 54%|█████▎    | 30931/57600 [5:24:58<4:27:20,  1.66it/s]
 54%|█████▎    | 30932/57600 [5:24:59<4:26:16,  1.67it/s]
 54%|█████▎    | 30933/57600 [5:25:00<4:20:35,  1.71it/s]
 54%|█████▎    | 30934/57600 [5:25:00<4:23:45,  1.68it/s]
 54%|█████▎    | 30935/57600 [5:25:01<4:22:54,  1.69it/s]
 54%|█████▎    | 30936/57600 [5:25:01<4:22:34,  1.69it/s]
 54%|█████▎    | 30937/57600 [5:25:02<4:34:28,  1.62it/s]
 54%|█████▎    | 30938/57600 [5:25:03<4:39:23,  1.59it/s]
 54%|█████▎    | 30939/57600 [5:25:03<4:34:48,  1.62it/s]
 54%|█████▎    | 30940/57600 [5:25:04<4:35:09,  1.61it/s]
                                                         
{'loss': 1.195, 'learning_rate': 5.1801393728223e-07, 'epoch': 341.5}

 54%|█████▎    | 30940/57600 [5:25:04<4:35:09,  1.61it/s]
 54%|█████▎    | 30941/57600 [5:25:04<4:30:40,  1.64it/s]
 54%|█████▎    | 30942/57600 [5:25:05<4:31:07,  1.64it/s]
 54%|█████▎    | 30943/57600 [5:25:06<4:33:35,  1.62it/s]
 54%|█████▎    | 30944/57600 [5:25:06<4:38:14,  1.60it/s]
 54%|█████▎    | 30945/57600 [5:25:07<4:34:18,  1.62it/s]
 54%|█████▎    | 30946/57600 [5:25:08<4:39:49,  1.59it/s]
 54%|█████▎    | 30947/57600 [5:25:08<4:32:33,  1.63it/s]
 54%|█████▎    | 30948/57600 [5:25:09<4:48:13,  1.54it/s]
 54%|█████▎    | 30949/57600 [5:25:09<4:40:25,  1.58it/s]
 54%|█████▎    | 30950/57600 [5:25:10<4:34:44,  1.62it/s]
 54%|█████▎    | 30951/57600 [5:25:11<4:49:59,  1.53it/s]
 54%|█████▎    | 30952/57600 [5:25:11<4:47:50,  1.54it/s]
 54%|█████▎    | 30953/57600 [5:25:12<4:38:15,  1.60it/s]
 54%|█████▎    | 30954/57600 [5:25:13<4:40:16,  1.58it/s]
 54%|█████▎    | 30955/57600 [5:25:13<4:37:36,  1.60it/s]
 54%|█████▎    | 30956/57600 [5:25:14<4:38:10,  1.60it/s]
 54%|█████▎    | 30957/57600 [5:25:15<4:38:59,  1.59it/s]
 54%|█████▎    | 30958/57600 [5:25:15<4:39:25,  1.59it/s]
 54%|█████▎    | 30959/57600 [5:25:16<4:44:47,  1.56it/s]
 54%|█████▍    | 30960/57600 [5:25:16<4:40:22,  1.58it/s]
                                                         
{'loss': 1.1563, 'learning_rate': 5.177003484320558e-07, 'epoch': 341.72}

 54%|█████▍    | 30960/57600 [5:25:16<4:40:22,  1.58it/s]
 54%|█████▍    | 30961/57600 [5:25:17<4:33:17,  1.62it/s]
 54%|█████▍    | 30962/57600 [5:25:18<4:39:17,  1.59it/s]
 54%|█████▍    | 30963/57600 [5:25:18<4:45:15,  1.56it/s]
 54%|█████▍    | 30964/57600 [5:25:19<4:47:00,  1.55it/s]
 54%|█████▍    | 30965/57600 [5:25:20<4:48:51,  1.54it/s]
 54%|█████▍    | 30966/57600 [5:25:20<4:46:11,  1.55it/s]
 54%|█████▍    | 30967/57600 [5:25:21<4:39:56,  1.59it/s]
 54%|█████▍    | 30968/57600 [5:25:21<4:33:19,  1.62it/s]
 54%|█████▍    | 30969/57600 [5:25:22<4:39:01,  1.59it/s]
 54%|█████▍    | 30970/57600 [5:25:23<4:33:32,  1.62it/s]
 54%|█████▍    | 30971/57600 [5:25:23<4:39:39,  1.59it/s]
 54%|█████▍    | 30972/57600 [5:25:24<4:46:14,  1.55it/s]
 54%|█████▍    | 30973/57600 [5:25:25<4:45:03,  1.56it/s]
 54%|█████▍    | 30974/57600 [5:25:25<4:43:59,  1.56it/s]
 54%|█████▍    | 30975/57600 [5:25:26<4:46:48,  1.55it/s]
 54%|█████▍    | 30976/57600 [5:25:27<4:43:06,  1.57it/s]
 54%|█████▍    | 30977/57600 [5:25:27<4:40:05,  1.58it/s]
 54%|█████▍    | 30978/57600 [5:25:28<4:33:56,  1.62it/s]
 54%|█████▍    | 30979/57600 [5:25:28<4:25:17,  1.67it/s]
 54%|█████▍    | 30980/57600 [5:25:29<4:22:42,  1.69it/s]
                                                         
{'loss': 1.1721, 'learning_rate': 5.173867595818816e-07, 'epoch': 341.94}

 54%|█████▍    | 30980/57600 [5:25:29<4:22:42,  1.69it/s]
 54%|█████▍    | 30981/57600 [5:25:30<4:26:22,  1.67it/s]
 54%|█████▍    | 30982/57600 [5:25:30<4:22:11,  1.69it/s]
 54%|█████▍    | 30983/57600 [5:25:31<4:21:36,  1.70it/s]
 54%|█████▍    | 30984/57600 [5:25:31<4:27:23,  1.66it/s]
 54%|█████▍    | 30985/57600 [5:25:32<4:31:40,  1.63it/s]
 54%|█████▍    | 30986/57600 [5:25:33<4:41:45,  1.57it/s]
 54%|█████▍    | 30987/57600 [5:25:33<4:41:50,  1.57it/s]
 54%|█████▍    | 30988/57600 [5:25:34<4:38:53,  1.59it/s]
 54%|█████▍    | 30989/57600 [5:25:35<4:40:38,  1.58it/s]
 54%|█████▍    | 30990/57600 [5:25:35<4:36:47,  1.60it/s]
 54%|█████▍    | 30991/57600 [5:25:36<4:36:14,  1.61it/s]
 54%|█████▍    | 30992/57600 [5:25:37<4:47:12,  1.54it/s]
 54%|█████▍    | 30993/57600 [5:25:37<4:37:38,  1.60it/s]
 54%|█████▍    | 30994/57600 [5:25:38<4:37:40,  1.60it/s]
 54%|█████▍    | 30995/57600 [5:25:38<4:35:44,  1.61it/s]
 54%|█████▍    | 30996/57600 [5:25:39<4:47:55,  1.54it/s]
 54%|█████▍    | 30997/57600 [5:25:40<4:42:04,  1.57it/s]
 54%|█████▍    | 30998/57600 [5:25:40<4:36:24,  1.60it/s]
 54%|█████▍    | 30999/57600 [5:25:41<4:32:49,  1.62it/s]
 54%|█████▍    | 31000/57600 [5:25:41<4:33:01,  1.62it/s]
                                                         
{'loss': 1.1566, 'learning_rate': 5.170731707317073e-07, 'epoch': 342.16}

 54%|█████▍    | 31000/57600 [5:25:41<4:33:01,  1.62it/s]
 54%|█████▍    | 31001/57600 [5:25:42<4:28:53,  1.65it/s]
 54%|█████▍    | 31002/57600 [5:25:43<4:35:10,  1.61it/s]
 54%|█████▍    | 31003/57600 [5:25:43<4:34:07,  1.62it/s]
 54%|█████▍    | 31004/57600 [5:25:44<4:33:26,  1.62it/s]
 54%|█████▍    | 31005/57600 [5:25:44<4:27:36,  1.66it/s]
 54%|█████▍    | 31006/57600 [5:25:45<4:27:49,  1.65it/s]
 54%|█████▍    | 31007/57600 [5:25:46<4:37:52,  1.60it/s]
 54%|█████▍    | 31008/57600 [5:25:46<4:40:11,  1.58it/s]
 54%|█████▍    | 31009/57600 [5:25:47<4:38:07,  1.59it/s]
 54%|█████▍    | 31010/57600 [5:25:48<4:35:18,  1.61it/s]
 54%|█████▍    | 31011/57600 [5:25:48<4:33:12,  1.62it/s]
 54%|█████▍    | 31012/57600 [5:25:49<4:33:43,  1.62it/s]
 54%|█████▍    | 31013/57600 [5:25:50<4:35:28,  1.61it/s]
 54%|█████▍    | 31014/57600 [5:25:50<4:36:20,  1.60it/s]
 54%|█████▍    | 31015/57600 [5:25:51<4:36:17,  1.60it/s]
 54%|█████▍    | 31016/57600 [5:25:51<4:41:41,  1.57it/s]
 54%|█████▍    | 31017/57600 [5:25:52<4:45:01,  1.55it/s]
 54%|█████▍    | 31018/57600 [5:25:53<4:50:16,  1.53it/s]
 54%|█████▍    | 31019/57600 [5:25:53<4:41:36,  1.57it/s]
 54%|█████▍    | 31020/57600 [5:25:54<4:38:23,  1.59it/s]
                                                         
{'loss': 1.1617, 'learning_rate': 5.167595818815331e-07, 'epoch': 342.38}

 54%|█████▍    | 31020/57600 [5:25:54<4:38:23,  1.59it/s]
 54%|█████▍    | 31021/57600 [5:25:55<4:40:40,  1.58it/s]
 54%|█████▍    | 31022/57600 [5:25:55<4:31:37,  1.63it/s]
 54%|█████▍    | 31023/57600 [5:25:56<4:32:00,  1.63it/s]
 54%|█████▍    | 31024/57600 [5:25:57<4:45:59,  1.55it/s]
 54%|█████▍    | 31025/57600 [5:25:57<4:42:03,  1.57it/s]
 54%|█████▍    | 31026/57600 [5:25:58<4:43:08,  1.56it/s]
 54%|█████▍    | 31027/57600 [5:25:58<4:43:55,  1.56it/s]
 54%|█████▍    | 31028/57600 [5:25:59<4:34:55,  1.61it/s]
 54%|█████▍    | 31029/57600 [5:26:00<4:37:48,  1.59it/s]
 54%|█████▍    | 31030/57600 [5:26:00<4:57:03,  1.49it/s]
 54%|█████▍    | 31031/57600 [5:26:01<4:47:46,  1.54it/s]
 54%|█████▍    | 31032/57600 [5:26:02<4:39:33,  1.58it/s]
 54%|█████▍    | 31033/57600 [5:26:02<4:43:22,  1.56it/s]
 54%|█████▍    | 31034/57600 [5:26:03<4:36:08,  1.60it/s]
 54%|█████▍    | 31035/57600 [5:26:03<4:34:22,  1.61it/s]
 54%|█████▍    | 31036/57600 [5:26:04<4:31:42,  1.63it/s]
 54%|█████▍    | 31037/57600 [5:26:05<4:29:57,  1.64it/s]
 54%|█████▍    | 31038/57600 [5:26:05<4:42:37,  1.57it/s]
 54%|█████▍    | 31039/57600 [5:26:06<4:37:11,  1.60it/s]
 54%|█████▍    | 31040/57600 [5:26:07<4:33:38,  1.62it/s]
                                                         
{'loss': 1.146, 'learning_rate': 5.164459930313588e-07, 'epoch': 342.6}

 54%|█████▍    | 31040/57600 [5:26:07<4:33:38,  1.62it/s]
 54%|█████▍    | 31041/57600 [5:26:07<4:32:20,  1.63it/s]
 54%|█████▍    | 31042/57600 [5:26:08<4:26:44,  1.66it/s]
 54%|█████▍    | 31043/57600 [5:26:08<4:29:35,  1.64it/s]
 54%|█████▍    | 31044/57600 [5:26:09<4:41:50,  1.57it/s]
 54%|█████▍    | 31045/57600 [5:26:10<4:43:40,  1.56it/s]
 54%|█████▍    | 31046/57600 [5:26:10<4:51:17,  1.52it/s]
 54%|█████▍    | 31047/57600 [5:26:11<4:49:16,  1.53it/s]
 54%|█████▍    | 31048/57600 [5:26:12<4:55:19,  1.50it/s]
 54%|█████▍    | 31049/57600 [5:26:12<4:44:52,  1.55it/s]
 54%|█████▍    | 31050/57600 [5:26:13<4:40:20,  1.58it/s]
 54%|█████▍    | 31051/57600 [5:26:14<4:30:29,  1.64it/s]
 54%|█████▍    | 31052/57600 [5:26:14<4:33:57,  1.62it/s]
 54%|█████▍    | 31053/57600 [5:26:15<4:29:29,  1.64it/s]
 54%|█████▍    | 31054/57600 [5:26:15<4:23:12,  1.68it/s]
 54%|█████▍    | 31055/57600 [5:26:16<4:26:26,  1.66it/s]
 54%|█████▍    | 31056/57600 [5:26:17<4:34:14,  1.61it/s]
 54%|█████▍    | 31057/57600 [5:26:17<4:30:25,  1.64it/s]
 54%|█████▍    | 31058/57600 [5:26:18<4:34:21,  1.61it/s]
 54%|█████▍    | 31059/57600 [5:26:18<4:37:37,  1.59it/s]
 54%|█████▍    | 31060/57600 [5:26:19<4:37:44,  1.59it/s]
                                                         
{'loss': 1.1685, 'learning_rate': 5.161324041811846e-07, 'epoch': 342.83}

 54%|█████▍    | 31060/57600 [5:26:19<4:37:44,  1.59it/s]
 54%|█████▍    | 31061/57600 [5:26:20<4:33:03,  1.62it/s]
 54%|█████▍    | 31062/57600 [5:26:20<4:25:17,  1.67it/s]
 54%|█████▍    | 31063/57600 [5:26:21<4:34:48,  1.61it/s]
 54%|█████▍    | 31064/57600 [5:26:22<4:38:56,  1.59it/s]
 54%|█████▍    | 31065/57600 [5:26:22<4:41:42,  1.57it/s]
 54%|█████▍    | 31066/57600 [5:26:23<4:36:31,  1.60it/s]
 54%|█████▍    | 31067/57600 [5:26:23<4:34:46,  1.61it/s]
 54%|█████▍    | 31068/57600 [5:26:24<4:35:09,  1.61it/s]
 54%|█████▍    | 31069/57600 [5:26:25<4:28:40,  1.65it/s]
 54%|█████▍    | 31070/57600 [5:26:25<4:32:43,  1.62it/s]
 54%|█████▍    | 31071/57600 [5:26:26<4:29:38,  1.64it/s]
 54%|█████▍    | 31072/57600 [5:26:27<4:42:58,  1.56it/s]
 54%|█████▍    | 31073/57600 [5:26:27<4:36:54,  1.60it/s]
 54%|█████▍    | 31074/57600 [5:26:28<4:41:50,  1.57it/s]
 54%|█████▍    | 31075/57600 [5:26:28<4:36:31,  1.60it/s]
 54%|█████▍    | 31076/57600 [5:26:29<4:42:02,  1.57it/s]
 54%|█████▍    | 31077/57600 [5:26:30<4:33:20,  1.62it/s]
 54%|█████▍    | 31078/57600 [5:26:30<4:31:13,  1.63it/s]
 54%|█████▍    | 31079/57600 [5:26:31<4:27:21,  1.65it/s]
 54%|█████▍    | 31080/57600 [5:26:31<4:23:07,  1.68it/s]
                                                         
{'loss': 1.1861, 'learning_rate': 5.158188153310105e-07, 'epoch': 343.05}

 54%|█████▍    | 31080/57600 [5:26:31<4:23:07,  1.68it/s]
 54%|█████▍    | 31081/57600 [5:26:32<4:20:35,  1.70it/s]
 54%|█████▍    | 31082/57600 [5:26:33<4:19:39,  1.70it/s]
 54%|█████▍    | 31083/57600 [5:26:33<4:24:37,  1.67it/s]
 54%|█████▍    | 31084/57600 [5:26:34<4:38:48,  1.59it/s]
 54%|█████▍    | 31085/57600 [5:26:35<4:48:20,  1.53it/s]
 54%|█████▍    | 31086/57600 [5:26:35<4:50:45,  1.52it/s]
 54%|█████▍    | 31087/57600 [5:26:36<4:49:45,  1.53it/s]
 54%|█████▍    | 31088/57600 [5:26:37<4:52:11,  1.51it/s]
 54%|█████▍    | 31089/57600 [5:26:37<4:49:42,  1.53it/s]
 54%|█████▍    | 31090/57600 [5:26:38<4:50:48,  1.52it/s]
 54%|█████▍    | 31091/57600 [5:26:39<4:42:15,  1.57it/s]
 54%|█████▍    | 31092/57600 [5:26:39<4:36:48,  1.60it/s]
 54%|█████▍    | 31093/57600 [5:26:40<4:33:38,  1.61it/s]
 54%|█████▍    | 31094/57600 [5:26:40<4:38:37,  1.59it/s]
 54%|█████▍    | 31095/57600 [5:26:41<4:42:25,  1.56it/s]
 54%|█████▍    | 31096/57600 [5:26:42<4:45:29,  1.55it/s]
 54%|█████▍    | 31097/57600 [5:26:42<4:49:23,  1.53it/s]
 54%|█████▍    | 31098/57600 [5:26:43<4:35:17,  1.60it/s]
 54%|█████▍    | 31099/57600 [5:26:44<4:39:40,  1.58it/s]
 54%|█████▍    | 31100/57600 [5:26:44<4:40:58,  1.57it/s]
                                                         
{'loss': 1.1599, 'learning_rate': 5.155052264808361e-07, 'epoch': 343.27}

 54%|█████▍    | 31100/57600 [5:26:44<4:40:58,  1.57it/s]
 54%|█████▍    | 31101/57600 [5:26:45<4:33:25,  1.62it/s]
 54%|█████▍    | 31102/57600 [5:26:45<4:32:32,  1.62it/s]
 54%|█████▍    | 31103/57600 [5:26:46<4:33:53,  1.61it/s]
 54%|█████▍    | 31104/57600 [5:26:47<4:25:41,  1.66it/s]
 54%|█████▍    | 31105/57600 [5:26:47<4:27:50,  1.65it/s]
 54%|█████▍    | 31106/57600 [5:26:48<4:23:00,  1.68it/s]
 54%|█████▍    | 31107/57600 [5:26:48<4:25:54,  1.66it/s]
 54%|█████▍    | 31108/57600 [5:26:49<4:31:42,  1.62it/s]
 54%|█████▍    | 31109/57600 [5:26:50<4:21:40,  1.69it/s]
 54%|█████▍    | 31110/57600 [5:26:50<4:26:22,  1.66it/s]
 54%|█████▍    | 31111/57600 [5:26:51<4:25:56,  1.66it/s]
 54%|█████▍    | 31112/57600 [5:26:51<4:26:35,  1.66it/s]
 54%|█████▍    | 31113/57600 [5:26:52<4:23:39,  1.67it/s]
 54%|█████▍    | 31114/57600 [5:26:53<4:25:19,  1.66it/s]
 54%|█████▍    | 31115/57600 [5:26:53<4:36:47,  1.59it/s]
 54%|█████▍    | 31116/57600 [5:26:54<4:50:03,  1.52it/s]
 54%|█████▍    | 31117/57600 [5:26:55<4:52:56,  1.51it/s]
 54%|█████▍    | 31118/57600 [5:26:55<4:45:09,  1.55it/s]
 54%|█████▍    | 31119/57600 [5:26:56<4:41:59,  1.57it/s]
 54%|█████▍    | 31120/57600 [5:26:57<4:38:07,  1.59it/s]
                                                         
{'loss': 1.1844, 'learning_rate': 5.15191637630662e-07, 'epoch': 343.49}

 54%|█████▍    | 31120/57600 [5:26:57<4:38:07,  1.59it/s]
 54%|█████▍    | 31121/57600 [5:26:57<4:40:02,  1.58it/s]
 54%|█████▍    | 31122/57600 [5:26:58<4:39:58,  1.58it/s]
 54%|█████▍    | 31123/57600 [5:26:58<4:40:42,  1.57it/s]
 54%|█████▍    | 31124/57600 [5:26:59<4:46:43,  1.54it/s]
 54%|█████▍    | 31125/57600 [5:27:00<4:40:56,  1.57it/s]
 54%|█████▍    | 31126/57600 [5:27:00<4:38:43,  1.58it/s]
 54%|█████▍    | 31127/57600 [5:27:01<4:33:01,  1.62it/s]
 54%|█████▍    | 31128/57600 [5:27:02<4:44:49,  1.55it/s]
 54%|█████▍    | 31129/57600 [5:27:02<4:38:39,  1.58it/s]
 54%|█████▍    | 31130/57600 [5:27:03<4:37:48,  1.59it/s]
 54%|█████▍    | 31131/57600 [5:27:03<4:29:25,  1.64it/s]
 54%|█████▍    | 31132/57600 [5:27:04<4:26:22,  1.66it/s]
 54%|█████▍    | 31133/57600 [5:27:05<4:24:43,  1.67it/s]
 54%|█████▍    | 31134/57600 [5:27:05<4:25:59,  1.66it/s]
 54%|█████▍    | 31135/57600 [5:27:06<4:27:47,  1.65it/s]
 54%|█████▍    | 31136/57600 [5:27:06<4:20:50,  1.69it/s]
 54%|█████▍    | 31137/57600 [5:27:07<4:23:12,  1.68it/s]
 54%|█████▍    | 31138/57600 [5:27:08<4:37:24,  1.59it/s]
 54%|█████▍    | 31139/57600 [5:27:08<4:34:01,  1.61it/s]
 54%|█████▍    | 31140/57600 [5:27:09<4:36:54,  1.59it/s]
                                                         
{'loss': 1.1672, 'learning_rate': 5.148780487804876e-07, 'epoch': 343.71}

 54%|█████▍    | 31140/57600 [5:27:09<4:36:54,  1.59it/s]
 54%|█████▍    | 31141/57600 [5:27:10<4:39:59,  1.57it/s]
 54%|█████▍    | 31142/57600 [5:27:10<4:35:17,  1.60it/s]
 54%|█████▍    | 31143/57600 [5:27:11<4:30:52,  1.63it/s]
 54%|█████▍    | 31144/57600 [5:27:11<4:38:21,  1.58it/s]
 54%|█████▍    | 31145/57600 [5:27:12<4:27:52,  1.65it/s]
 54%|█████▍    | 31146/57600 [5:27:13<4:30:45,  1.63it/s]
 54%|█████▍    | 31147/57600 [5:27:13<4:31:02,  1.63it/s]
 54%|█████▍    | 31148/57600 [5:27:14<4:46:55,  1.54it/s]
 54%|█████▍    | 31149/57600 [5:27:15<4:42:26,  1.56it/s]
 54%|█████▍    | 31150/57600 [5:27:15<4:37:09,  1.59it/s]
 54%|█████▍    | 31151/57600 [5:27:16<4:38:31,  1.58it/s]
 54%|█████▍    | 31152/57600 [5:27:16<4:35:54,  1.60it/s]
 54%|█████▍    | 31153/57600 [5:27:17<4:41:57,  1.56it/s]
 54%|█████▍    | 31154/57600 [5:27:18<4:42:05,  1.56it/s]
 54%|█████▍    | 31155/57600 [5:27:18<4:38:21,  1.58it/s]
 54%|█████▍    | 31156/57600 [5:27:19<4:32:24,  1.62it/s]
 54%|█████▍    | 31157/57600 [5:27:20<4:30:39,  1.63it/s]
 54%|█████▍    | 31158/57600 [5:27:20<4:29:36,  1.63it/s]
 54%|█████▍    | 31159/57600 [5:27:21<4:29:45,  1.63it/s]
 54%|█████▍    | 31160/57600 [5:27:21<4:29:13,  1.64it/s]
                                                         
{'loss': 1.1302, 'learning_rate': 5.145644599303136e-07, 'epoch': 343.93}

 54%|█████▍    | 31160/57600 [5:27:21<4:29:13,  1.64it/s]
 54%|█████▍    | 31161/57600 [5:27:22<4:22:31,  1.68it/s]
 54%|█████▍    | 31162/57600 [5:27:23<4:36:29,  1.59it/s]
 54%|█████▍    | 31163/57600 [5:27:23<4:46:47,  1.54it/s]
 54%|█████▍    | 31164/57600 [5:27:24<4:37:55,  1.59it/s]
 54%|█████▍    | 31165/57600 [5:27:25<4:30:45,  1.63it/s]
 54%|█████▍    | 31166/57600 [5:27:25<4:29:25,  1.64it/s]
 54%|█████▍    | 31167/57600 [5:27:26<4:34:39,  1.60it/s]
 54%|█████▍    | 31168/57600 [5:27:26<4:35:44,  1.60it/s]
 54%|█████▍    | 31169/57600 [5:27:27<4:29:16,  1.64it/s]
 54%|█████▍    | 31170/57600 [5:27:28<4:40:14,  1.57it/s]
 54%|█████▍    | 31171/57600 [5:27:28<4:48:48,  1.53it/s]
 54%|█████▍    | 31172/57600 [5:27:29<4:55:52,  1.49it/s]
 54%|█████▍    | 31173/57600 [5:27:30<5:01:09,  1.46it/s]
 54%|█████▍    | 31174/57600 [5:27:30<4:51:36,  1.51it/s]
 54%|█████▍    | 31175/57600 [5:27:31<4:36:26,  1.59it/s]
 54%|█████▍    | 31176/57600 [5:27:32<4:29:15,  1.64it/s]
 54%|█████▍    | 31177/57600 [5:27:32<4:26:36,  1.65it/s]
 54%|█████▍    | 31178/57600 [5:27:33<4:30:37,  1.63it/s]
 54%|█████▍    | 31179/57600 [5:27:33<4:21:19,  1.69it/s]
 54%|█████▍    | 31180/57600 [5:27:34<4:26:44,  1.65it/s]
                                                         
{'loss': 1.2002, 'learning_rate': 5.142508710801393e-07, 'epoch': 344.15}

 54%|█████▍    | 31180/57600 [5:27:34<4:26:44,  1.65it/s]
 54%|█████▍    | 31181/57600 [5:27:35<4:24:26,  1.67it/s]
 54%|█████▍    | 31182/57600 [5:27:35<4:26:57,  1.65it/s]
 54%|█████▍    | 31183/57600 [5:27:36<4:33:35,  1.61it/s]
 54%|█████▍    | 31184/57600 [5:27:36<4:32:14,  1.62it/s]
 54%|█████▍    | 31185/57600 [5:27:37<4:26:43,  1.65it/s]
 54%|█████▍    | 31186/57600 [5:27:38<4:27:05,  1.65it/s]
 54%|█████▍    | 31187/57600 [5:27:38<4:34:09,  1.61it/s]
 54%|█████▍    | 31188/57600 [5:27:39<4:27:56,  1.64it/s]
 54%|█████▍    | 31189/57600 [5:27:40<4:39:23,  1.58it/s]
 54%|█████▍    | 31190/57600 [5:27:40<4:42:52,  1.56it/s]
 54%|█████▍    | 31191/57600 [5:27:41<4:30:07,  1.63it/s]
 54%|█████▍    | 31192/57600 [5:27:41<4:32:59,  1.61it/s]
 54%|█████▍    | 31193/57600 [5:27:42<4:33:55,  1.61it/s]
 54%|█████▍    | 31194/57600 [5:27:43<4:28:04,  1.64it/s]
 54%|█████▍    | 31195/57600 [5:27:43<4:37:54,  1.58it/s]
 54%|█████▍    | 31196/57600 [5:27:44<4:35:40,  1.60it/s]
 54%|█████▍    | 31197/57600 [5:27:45<4:31:34,  1.62it/s]
 54%|█████▍    | 31198/57600 [5:27:45<4:28:37,  1.64it/s]
 54%|█████▍    | 31199/57600 [5:27:46<4:32:54,  1.61it/s]
 54%|█████▍    | 31200/57600 [5:27:46<4:26:52,  1.65it/s]
                                                         
{'loss': 1.191, 'learning_rate': 5.139372822299652e-07, 'epoch': 344.37}

 54%|█████▍    | 31200/57600 [5:27:46<4:26:52,  1.65it/s]
 54%|█████▍    | 31201/57600 [5:27:47<4:24:39,  1.66it/s]
 54%|█████▍    | 31202/57600 [5:27:48<4:28:47,  1.64it/s]
 54%|█████▍    | 31203/57600 [5:27:48<4:22:26,  1.68it/s]
 54%|█████▍    | 31204/57600 [5:27:49<4:23:50,  1.67it/s]
 54%|█████▍    | 31205/57600 [5:27:49<4:27:34,  1.64it/s]
 54%|█████▍    | 31206/57600 [5:27:50<4:25:52,  1.65it/s]
 54%|█████▍    | 31207/57600 [5:27:51<4:20:37,  1.69it/s]
 54%|█████▍    | 31208/57600 [5:27:51<4:19:51,  1.69it/s]
 54%|█████▍    | 31209/57600 [5:27:52<4:20:58,  1.69it/s]
 54%|█████▍    | 31210/57600 [5:27:52<4:22:32,  1.68it/s]
 54%|█████▍    | 31211/57600 [5:27:53<4:35:53,  1.59it/s]
 54%|█████▍    | 31212/57600 [5:27:54<4:39:46,  1.57it/s]
 54%|█████▍    | 31213/57600 [5:27:54<4:44:20,  1.55it/s]
 54%|█████▍    | 31214/57600 [5:27:55<4:45:14,  1.54it/s]
 54%|█████▍    | 31215/57600 [5:27:56<4:38:31,  1.58it/s]
 54%|█████▍    | 31216/57600 [5:27:56<4:37:28,  1.58it/s]
 54%|█████▍    | 31217/57600 [5:27:57<4:36:42,  1.59it/s]
 54%|█████▍    | 31218/57600 [5:27:57<4:34:04,  1.60it/s]
 54%|█████▍    | 31219/57600 [5:27:58<4:32:45,  1.61it/s]
 54%|█████▍    | 31220/57600 [5:27:59<4:33:31,  1.61it/s]
                                                         
{'loss': 1.1869, 'learning_rate': 5.13623693379791e-07, 'epoch': 344.59}

 54%|█████▍    | 31220/57600 [5:27:59<4:33:31,  1.61it/s]
 54%|█████▍    | 31221/57600 [5:27:59<4:37:42,  1.58it/s]
 54%|█████▍    | 31222/57600 [5:28:00<4:47:51,  1.53it/s]
 54%|█████▍    | 31223/57600 [5:28:01<4:46:06,  1.54it/s]
 54%|█████▍    | 31224/57600 [5:28:01<4:37:20,  1.59it/s]
 54%|█████▍    | 31225/57600 [5:28:02<4:35:49,  1.59it/s]
 54%|█████▍    | 31226/57600 [5:28:02<4:32:42,  1.61it/s]
 54%|█████▍    | 31227/57600 [5:28:03<4:26:40,  1.65it/s]
 54%|█████▍    | 31228/57600 [5:28:04<4:31:20,  1.62it/s]
 54%|█████▍    | 31229/57600 [5:28:04<4:30:17,  1.63it/s]
 54%|█████▍    | 31230/57600 [5:28:05<4:28:19,  1.64it/s]
 54%|█████▍    | 31231/57600 [5:28:06<4:29:01,  1.63it/s]
 54%|█████▍    | 31232/57600 [5:28:06<4:42:50,  1.55it/s]
 54%|█████▍    | 31233/57600 [5:28:07<4:32:28,  1.61it/s]
 54%|█████▍    | 31234/57600 [5:28:08<4:46:54,  1.53it/s]
 54%|█████▍    | 31235/57600 [5:28:08<4:41:38,  1.56it/s]
 54%|█████▍    | 31236/57600 [5:28:09<4:47:17,  1.53it/s]
 54%|█████▍    | 31237/57600 [5:28:09<4:32:57,  1.61it/s]
 54%|█████▍    | 31238/57600 [5:28:10<4:28:03,  1.64it/s]
 54%|█████▍    | 31239/57600 [5:28:11<4:40:46,  1.56it/s]
 54%|█████▍    | 31240/57600 [5:28:11<4:35:23,  1.60it/s]
                                                         
{'loss': 1.1655, 'learning_rate': 5.133101045296167e-07, 'epoch': 344.81}

 54%|█████▍    | 31240/57600 [5:28:11<4:35:23,  1.60it/s]
 54%|█████▍    | 31241/57600 [5:28:12<4:31:45,  1.62it/s]
 54%|█████▍    | 31242/57600 [5:28:13<4:35:59,  1.59it/s]
 54%|█████▍    | 31243/57600 [5:28:13<4:38:08,  1.58it/s]
 54%|█████▍    | 31244/57600 [5:28:14<4:39:34,  1.57it/s]
 54%|█████▍    | 31245/57600 [5:28:14<4:32:02,  1.61it/s]
 54%|█████▍    | 31246/57600 [5:28:15<4:44:52,  1.54it/s]
 54%|█████▍    | 31247/57600 [5:28:16<4:38:57,  1.57it/s]
 54%|█████▍    | 31248/57600 [5:28:16<4:40:31,  1.57it/s]
 54%|█████▍    | 31249/57600 [5:28:17<4:32:58,  1.61it/s]
 54%|█████▍    | 31250/57600 [5:28:18<4:37:57,  1.58it/s]
 54%|█████▍    | 31251/57600 [5:28:18<4:38:41,  1.58it/s]
 54%|█████▍    | 31252/57600 [5:28:19<4:43:00,  1.55it/s]
 54%|█████▍    | 31253/57600 [5:28:20<4:47:23,  1.53it/s]
 54%|█████▍    | 31254/57600 [5:28:20<4:51:22,  1.51it/s]
 54%|█████▍    | 31255/57600 [5:28:21<4:42:01,  1.56it/s]
 54%|█████▍    | 31256/57600 [5:28:21<4:31:39,  1.62it/s]
 54%|█████▍    | 31257/57600 [5:28:22<4:34:36,  1.60it/s]
 54%|█████▍    | 31258/57600 [5:28:23<4:42:12,  1.56it/s]
 54%|█████▍    | 31259/57600 [5:28:23<4:36:27,  1.59it/s]
 54%|█████▍    | 31260/57600 [5:28:24<4:39:11,  1.57it/s]
                                                         
{'loss': 1.1354, 'learning_rate': 5.129965156794426e-07, 'epoch': 345.03}

 54%|█████▍    | 31260/57600 [5:28:24<4:39:11,  1.57it/s]
 54%|█████▍    | 31261/57600 [5:28:25<4:38:49,  1.57it/s]
 54%|█████▍    | 31262/57600 [5:28:25<4:44:22,  1.54it/s]
 54%|█████▍    | 31263/57600 [5:28:26<4:47:56,  1.52it/s]
 54%|█████▍    | 31264/57600 [5:28:27<4:45:33,  1.54it/s]
 54%|█████▍    | 31265/57600 [5:28:27<4:34:05,  1.60it/s]
 54%|█████▍    | 31266/57600 [5:28:28<4:41:26,  1.56it/s]
 54%|█████▍    | 31267/57600 [5:28:29<4:45:05,  1.54it/s]
 54%|█████▍    | 31268/57600 [5:28:29<4:37:36,  1.58it/s]
 54%|█████▍    | 31269/57600 [5:28:30<4:35:53,  1.59it/s]
 54%|█████▍    | 31270/57600 [5:28:30<4:30:14,  1.62it/s]
 54%|█████▍    | 31271/57600 [5:28:31<4:30:24,  1.62it/s]
 54%|█████▍    | 31272/57600 [5:28:32<4:37:57,  1.58it/s]
 54%|█████▍    | 31273/57600 [5:28:32<4:45:02,  1.54it/s]
 54%|█████▍    | 31274/57600 [5:28:33<4:41:00,  1.56it/s]
 54%|█████▍    | 31275/57600 [5:28:34<4:36:29,  1.59it/s]
 54%|█████▍    | 31276/57600 [5:28:34<4:33:16,  1.61it/s]
 54%|█████▍    | 31277/57600 [5:28:35<4:46:18,  1.53it/s]
 54%|█████▍    | 31278/57600 [5:28:36<4:46:35,  1.53it/s]
 54%|█████▍    | 31279/57600 [5:28:36<4:42:57,  1.55it/s]
 54%|█████▍    | 31280/57600 [5:28:37<4:36:07,  1.59it/s]
                                                         
{'loss': 1.1772, 'learning_rate': 5.126829268292682e-07, 'epoch': 345.25}

 54%|█████▍    | 31280/57600 [5:28:37<4:36:07,  1.59it/s]
 54%|█████▍    | 31281/57600 [5:28:37<4:36:21,  1.59it/s]
 54%|█████▍    | 31282/57600 [5:28:38<4:45:57,  1.53it/s]
 54%|█████▍    | 31283/57600 [5:28:39<4:38:20,  1.58it/s]
 54%|█████▍    | 31284/57600 [5:28:39<4:37:47,  1.58it/s]
 54%|█████▍    | 31285/57600 [5:28:40<4:47:34,  1.53it/s]
 54%|█████▍    | 31286/57600 [5:28:41<4:43:16,  1.55it/s]
 54%|█████▍    | 31287/57600 [5:28:41<4:37:33,  1.58it/s]
 54%|█████▍    | 31288/57600 [5:28:42<4:30:13,  1.62it/s]
 54%|█████▍    | 31289/57600 [5:28:42<4:26:01,  1.65it/s]
 54%|█████▍    | 31290/57600 [5:28:43<4:36:05,  1.59it/s]
 54%|█████▍    | 31291/57600 [5:28:44<4:29:23,  1.63it/s]
 54%|█████▍    | 31292/57600 [5:28:44<4:37:05,  1.58it/s]
 54%|█████▍    | 31293/57600 [5:28:45<4:37:34,  1.58it/s]
 54%|█████▍    | 31294/57600 [5:28:46<4:29:10,  1.63it/s]
 54%|█████▍    | 31295/57600 [5:28:46<4:35:58,  1.59it/s]
 54%|█████▍    | 31296/57600 [5:28:47<4:41:26,  1.56it/s]
 54%|█████▍    | 31297/57600 [5:28:47<4:31:52,  1.61it/s]
 54%|█████▍    | 31298/57600 [5:28:48<4:30:00,  1.62it/s]
 54%|█████▍    | 31299/57600 [5:28:49<4:31:02,  1.62it/s]
 54%|█████▍    | 31300/57600 [5:28:49<4:31:14,  1.62it/s]
                                                         
{'loss': 1.1738, 'learning_rate': 5.123693379790941e-07, 'epoch': 345.47}

 54%|█████▍    | 31300/57600 [5:28:49<4:31:14,  1.62it/s]
 54%|█████▍    | 31301/57600 [5:28:50<4:29:21,  1.63it/s]
 54%|█████▍    | 31302/57600 [5:28:51<4:36:33,  1.58it/s]
 54%|█████▍    | 31303/57600 [5:28:51<4:30:17,  1.62it/s]
 54%|█████▍    | 31304/57600 [5:28:52<4:38:06,  1.58it/s]
 54%|█████▍    | 31305/57600 [5:28:52<4:32:14,  1.61it/s]
 54%|█████▍    | 31306/57600 [5:28:53<4:40:29,  1.56it/s]
 54%|█████▍    | 31307/57600 [5:28:54<4:34:53,  1.59it/s]
 54%|█████▍    | 31308/57600 [5:28:54<4:29:17,  1.63it/s]
 54%|█████▍    | 31309/57600 [5:28:55<4:34:02,  1.60it/s]
 54%|█████▍    | 31310/57600 [5:28:56<4:35:01,  1.59it/s]
 54%|█████▍    | 31311/57600 [5:28:56<4:29:48,  1.62it/s]
 54%|█████▍    | 31312/57600 [5:28:57<4:23:41,  1.66it/s]
 54%|█████▍    | 31313/57600 [5:28:57<4:18:22,  1.70it/s]
 54%|█████▍    | 31314/57600 [5:28:58<4:23:27,  1.66it/s]
 54%|█████▍    | 31315/57600 [5:28:59<4:26:04,  1.65it/s]
 54%|█████▍    | 31316/57600 [5:28:59<4:27:53,  1.64it/s]
 54%|█████▍    | 31317/57600 [5:29:00<4:29:22,  1.63it/s]
 54%|█████▍    | 31318/57600 [5:29:00<4:31:13,  1.62it/s]
 54%|█████▍    | 31319/57600 [5:29:01<4:27:04,  1.64it/s]
 54%|█████▍    | 31320/57600 [5:29:02<4:30:56,  1.62it/s]
                                                         
{'loss': 1.1995, 'learning_rate': 5.120557491289197e-07, 'epoch': 345.7}

 54%|█████▍    | 31320/57600 [5:29:02<4:30:56,  1.62it/s]
 54%|█████▍    | 31321/57600 [5:29:02<4:27:19,  1.64it/s]
 54%|█████▍    | 31322/57600 [5:29:03<4:34:48,  1.59it/s]
 54%|█████▍    | 31323/57600 [5:29:03<4:28:43,  1.63it/s]
 54%|█████▍    | 31324/57600 [5:29:04<4:27:46,  1.64it/s]
 54%|█████▍    | 31325/57600 [5:29:05<4:24:03,  1.66it/s]
 54%|█████▍    | 31326/57600 [5:29:05<4:27:21,  1.64it/s]
 54%|█████▍    | 31327/57600 [5:29:06<4:26:08,  1.65it/s]
 54%|█████▍    | 31328/57600 [5:29:06<4:24:11,  1.66it/s]
 54%|█████▍    | 31329/57600 [5:29:07<4:25:21,  1.65it/s]
 54%|█████▍    | 31330/57600 [5:29:08<4:28:31,  1.63it/s]
 54%|█████▍    | 31331/57600 [5:29:08<4:29:32,  1.62it/s]
 54%|█████▍    | 31332/57600 [5:29:09<4:34:08,  1.60it/s]
 54%|█████▍    | 31333/57600 [5:29:10<4:35:37,  1.59it/s]
 54%|█████▍    | 31334/57600 [5:29:10<4:28:35,  1.63it/s]
 54%|█████▍    | 31335/57600 [5:29:11<4:34:27,  1.59it/s]
 54%|█████▍    | 31336/57600 [5:29:11<4:29:41,  1.62it/s]
 54%|█████▍    | 31337/57600 [5:29:12<4:29:59,  1.62it/s]
 54%|█████▍    | 31338/57600 [5:29:13<4:22:46,  1.67it/s]
 54%|█████▍    | 31339/57600 [5:29:13<4:21:56,  1.67it/s]
 54%|█████▍    | 31340/57600 [5:29:14<4:23:26,  1.66it/s]
                                                         
{'loss': 1.1945, 'learning_rate': 5.117421602787456e-07, 'epoch': 345.92}

 54%|█████▍    | 31340/57600 [5:29:14<4:23:26,  1.66it/s]
 54%|█████▍    | 31341/57600 [5:29:14<4:27:19,  1.64it/s]
 54%|█████▍    | 31342/57600 [5:29:15<4:23:51,  1.66it/s]
 54%|█████▍    | 31343/57600 [5:29:16<4:24:16,  1.66it/s]
 54%|█████▍    | 31344/57600 [5:29:16<4:29:01,  1.63it/s]
 54%|█████▍    | 31345/57600 [5:29:17<4:32:55,  1.60it/s]
 54%|█████▍    | 31346/57600 [5:29:18<4:34:06,  1.60it/s]
 54%|█████▍    | 31347/57600 [5:29:18<4:32:52,  1.60it/s]
 54%|█████▍    | 31348/57600 [5:29:19<4:53:55,  1.49it/s]
 54%|█████▍    | 31349/57600 [5:29:20<4:41:40,  1.55it/s]
 54%|█████▍    | 31350/57600 [5:29:20<4:41:55,  1.55it/s]
 54%|█████▍    | 31351/57600 [5:29:21<4:34:58,  1.59it/s]
 54%|█████▍    | 31352/57600 [5:29:21<4:40:49,  1.56it/s]
 54%|█████▍    | 31353/57600 [5:29:22<4:42:37,  1.55it/s]
 54%|█████▍    | 31354/57600 [5:29:23<4:46:02,  1.53it/s]
 54%|█████▍    | 31355/57600 [5:29:23<4:36:17,  1.58it/s]
 54%|█████▍    | 31356/57600 [5:29:24<4:33:38,  1.60it/s]
 54%|█████▍    | 31357/57600 [5:29:25<4:33:00,  1.60it/s]
 54%|█████▍    | 31358/57600 [5:29:25<4:32:32,  1.60it/s]
 54%|█████▍    | 31359/57600 [5:29:26<4:32:49,  1.60it/s]
 54%|█████▍    | 31360/57600 [5:29:26<4:24:54,  1.65it/s]
                                                         
{'loss': 1.1692, 'learning_rate': 5.114285714285714e-07, 'epoch': 346.14}

 54%|█████▍    | 31360/57600 [5:29:26<4:24:54,  1.65it/s]
 54%|█████▍    | 31361/57600 [5:29:27<4:20:22,  1.68it/s]
 54%|█████▍    | 31362/57600 [5:29:28<4:13:54,  1.72it/s]
 54%|█████▍    | 31363/57600 [5:29:28<4:12:55,  1.73it/s]
 54%|█████▍    | 31364/57600 [5:29:29<4:24:47,  1.65it/s]
 54%|█████▍    | 31365/57600 [5:29:29<4:23:33,  1.66it/s]
 54%|█████▍    | 31366/57600 [5:29:30<4:29:40,  1.62it/s]
 54%|█████▍    | 31367/57600 [5:29:31<4:25:46,  1.65it/s]
 54%|█████▍    | 31368/57600 [5:29:31<4:25:27,  1.65it/s]
 54%|█████▍    | 31369/57600 [5:29:32<4:18:08,  1.69it/s]
 54%|█████▍    | 31370/57600 [5:29:32<4:19:29,  1.68it/s]
 54%|█████▍    | 31371/57600 [5:29:33<4:25:00,  1.65it/s]
 54%|█████▍    | 31372/57600 [5:29:34<4:27:20,  1.64it/s]
 54%|█████▍    | 31373/57600 [5:29:34<4:36:19,  1.58it/s]
 54%|█████▍    | 31374/57600 [5:29:35<4:33:14,  1.60it/s]
 54%|█████▍    | 31375/57600 [5:29:36<4:34:05,  1.59it/s]
 54%|█████▍    | 31376/57600 [5:29:36<4:26:33,  1.64it/s]
 54%|█████▍    | 31377/57600 [5:29:37<4:27:59,  1.63it/s]
 54%|█████▍    | 31378/57600 [5:29:37<4:37:30,  1.57it/s]
 54%|█████▍    | 31379/57600 [5:29:38<4:42:09,  1.55it/s]
 54%|█████▍    | 31380/57600 [5:29:39<4:34:02,  1.59it/s]
                                                         
{'loss': 1.2119, 'learning_rate': 5.111149825783972e-07, 'epoch': 346.36}

 54%|█████▍    | 31380/57600 [5:29:39<4:34:02,  1.59it/s]
 54%|█████▍    | 31381/57600 [5:29:39<4:33:31,  1.60it/s]
 54%|█████▍    | 31382/57600 [5:29:40<4:25:36,  1.65it/s]
 54%|█████▍    | 31383/57600 [5:29:41<4:32:03,  1.61it/s]
 54%|█████▍    | 31384/57600 [5:29:41<4:29:12,  1.62it/s]
 54%|█████▍    | 31385/57600 [5:29:42<4:25:43,  1.64it/s]
 54%|█████▍    | 31386/57600 [5:29:42<4:32:14,  1.60it/s]
 54%|█████▍    | 31387/57600 [5:29:43<4:27:00,  1.64it/s]
 54%|█████▍    | 31388/57600 [5:29:44<4:33:36,  1.60it/s]
 54%|█████▍    | 31389/57600 [5:29:44<4:27:48,  1.63it/s]
 54%|█████▍    | 31390/57600 [5:29:45<4:32:03,  1.61it/s]
 54%|█████▍    | 31391/57600 [5:29:45<4:28:15,  1.63it/s]
 55%|█████▍    | 31392/57600 [5:29:46<4:29:42,  1.62it/s]
 55%|█████▍    | 31393/57600 [5:29:47<4:28:56,  1.62it/s]
 55%|█████▍    | 31394/57600 [5:29:47<4:31:25,  1.61it/s]
 55%|█████▍    | 31395/57600 [5:29:48<4:34:30,  1.59it/s]
 55%|█████▍    | 31396/57600 [5:29:49<4:42:06,  1.55it/s]
 55%|█████▍    | 31397/57600 [5:29:49<4:39:14,  1.56it/s]
 55%|█████▍    | 31398/57600 [5:29:50<4:33:44,  1.60it/s]
 55%|█████▍    | 31399/57600 [5:29:50<4:33:10,  1.60it/s]
 55%|█████▍    | 31400/57600 [5:29:51<4:29:15,  1.62it/s]
                                                         
{'loss': 1.1656, 'learning_rate': 5.108013937282229e-07, 'epoch': 346.58}

 55%|█████▍    | 31400/57600 [5:29:51<4:29:15,  1.62it/s]
 55%|█████▍    | 31401/57600 [5:29:52<4:26:23,  1.64it/s]
 55%|█████▍    | 31402/57600 [5:29:52<4:29:16,  1.62it/s]
 55%|█████▍    | 31403/57600 [5:29:53<4:23:21,  1.66it/s]
 55%|█████▍    | 31404/57600 [5:29:53<4:20:18,  1.68it/s]
 55%|█████▍    | 31405/57600 [5:29:54<4:21:48,  1.67it/s]
 55%|█████▍    | 31406/57600 [5:29:55<4:28:14,  1.63it/s]
 55%|█████▍    | 31407/57600 [5:29:55<4:31:58,  1.61it/s]
 55%|█████▍    | 31408/57600 [5:29:56<4:35:33,  1.58it/s]
 55%|█████▍    | 31409/57600 [5:29:57<4:27:47,  1.63it/s]
 55%|█████▍    | 31410/57600 [5:29:57<4:28:43,  1.62it/s]
 55%|█████▍    | 31411/57600 [5:29:58<4:27:35,  1.63it/s]
 55%|█████▍    | 31412/57600 [5:29:58<4:27:53,  1.63it/s]
 55%|█████▍    | 31413/57600 [5:29:59<4:31:23,  1.61it/s]
 55%|█████▍    | 31414/57600 [5:30:00<4:23:30,  1.66it/s]
 55%|█████▍    | 31415/57600 [5:30:00<4:25:49,  1.64it/s]
 55%|█████▍    | 31416/57600 [5:30:01<4:35:51,  1.58it/s]
 55%|█████▍    | 31417/57600 [5:30:02<4:41:03,  1.55it/s]
 55%|█████▍    | 31418/57600 [5:30:02<4:40:01,  1.56it/s]
 55%|█████▍    | 31419/57600 [5:30:03<4:33:10,  1.60it/s]
 55%|█████▍    | 31420/57600 [5:30:04<4:38:29,  1.57it/s]
                                                         
{'loss': 1.1491, 'learning_rate': 5.104878048780488e-07, 'epoch': 346.8}

 55%|█████▍    | 31420/57600 [5:30:04<4:38:29,  1.57it/s]
 55%|█████▍    | 31421/57600 [5:30:04<4:36:33,  1.58it/s]
 55%|█████▍    | 31422/57600 [5:30:05<4:39:01,  1.56it/s]
 55%|█████▍    | 31423/57600 [5:30:05<4:42:22,  1.55it/s]
 55%|█████▍    | 31424/57600 [5:30:06<4:42:40,  1.54it/s]
 55%|█████▍    | 31425/57600 [5:30:07<4:36:58,  1.58it/s]
 55%|█████▍    | 31426/57600 [5:30:07<4:37:53,  1.57it/s]
 55%|█████▍    | 31427/57600 [5:30:08<4:33:50,  1.59it/s]
 55%|█████▍    | 31428/57600 [5:30:09<4:35:22,  1.58it/s]
 55%|█████▍    | 31429/57600 [5:30:09<4:32:25,  1.60it/s]
 55%|█████▍    | 31430/57600 [5:30:10<4:37:02,  1.57it/s]
 55%|█████▍    | 31431/57600 [5:30:10<4:32:40,  1.60it/s]
 55%|█████▍    | 31432/57600 [5:30:11<4:36:23,  1.58it/s]
 55%|█████▍    | 31433/57600 [5:30:12<4:35:02,  1.59it/s]
 55%|█████▍    | 31434/57600 [5:30:12<4:41:53,  1.55it/s]
 55%|█████▍    | 31435/57600 [5:30:13<4:43:25,  1.54it/s]
 55%|█████▍    | 31436/57600 [5:30:14<4:47:58,  1.51it/s]
 55%|█████▍    | 31437/57600 [5:30:14<4:43:08,  1.54it/s]
 55%|█████▍    | 31438/57600 [5:30:15<4:46:48,  1.52it/s]
 55%|█████▍    | 31439/57600 [5:30:16<4:58:53,  1.46it/s]
 55%|█████▍    | 31440/57600 [5:30:16<4:50:09,  1.50it/s]
                                                         
{'loss': 1.1632, 'learning_rate': 5.101742160278745e-07, 'epoch': 347.02}

 55%|█████▍    | 31440/57600 [5:30:16<4:50:09,  1.50it/s]
 55%|█████▍    | 31441/57600 [5:30:17<4:41:17,  1.55it/s]
 55%|█████▍    | 31442/57600 [5:30:18<4:50:11,  1.50it/s]
 55%|█████▍    | 31443/57600 [5:30:18<4:40:52,  1.55it/s]
 55%|█████▍    | 31444/57600 [5:30:19<4:42:11,  1.54it/s]
 55%|█████▍    | 31445/57600 [5:30:20<4:32:26,  1.60it/s]
 55%|█████▍    | 31446/57600 [5:30:20<4:36:07,  1.58it/s]
 55%|█████▍    | 31447/57600 [5:30:21<4:28:50,  1.62it/s]
 55%|█████▍    | 31448/57600 [5:30:21<4:35:28,  1.58it/s]
 55%|█████▍    | 31449/57600 [5:30:22<4:28:53,  1.62it/s]
 55%|█████▍    | 31450/57600 [5:30:23<4:27:10,  1.63it/s]
 55%|█████▍    | 31451/57600 [5:30:23<4:19:41,  1.68it/s]
 55%|█████▍    | 31452/57600 [5:30:24<4:20:36,  1.67it/s]
 55%|█████▍    | 31453/57600 [5:30:24<4:23:35,  1.65it/s]
 55%|█████▍    | 31454/57600 [5:30:25<4:17:45,  1.69it/s]
 55%|█████▍    | 31455/57600 [5:30:26<4:22:04,  1.66it/s]
 55%|█████▍    | 31456/57600 [5:30:26<4:22:15,  1.66it/s]
 55%|█████▍    | 31457/57600 [5:30:27<4:16:07,  1.70it/s]
 55%|█████▍    | 31458/57600 [5:30:27<4:26:26,  1.64it/s]
 55%|█████▍    | 31459/57600 [5:30:28<4:19:06,  1.68it/s]
 55%|█████▍    | 31460/57600 [5:30:29<4:23:15,  1.65it/s]
                                                         
{'loss': 1.1851, 'learning_rate': 5.098606271777003e-07, 'epoch': 347.24}

 55%|█████▍    | 31460/57600 [5:30:29<4:23:15,  1.65it/s]
 55%|█████▍    | 31461/57600 [5:30:29<4:20:42,  1.67it/s]
 55%|█████▍    | 31462/57600 [5:30:30<4:30:40,  1.61it/s]
 55%|█████▍    | 31463/57600 [5:30:30<4:24:56,  1.64it/s]
 55%|█████▍    | 31464/57600 [5:30:31<4:22:55,  1.66it/s]
 55%|█████▍    | 31465/57600 [5:30:32<4:17:15,  1.69it/s]
 55%|█████▍    | 31466/57600 [5:30:32<4:28:26,  1.62it/s]
 55%|█████▍    | 31467/57600 [5:30:33<4:31:23,  1.60it/s]
 55%|█████▍    | 31468/57600 [5:30:34<4:26:45,  1.63it/s]
 55%|█████▍    | 31469/57600 [5:30:34<4:22:08,  1.66it/s]
 55%|█████▍    | 31470/57600 [5:30:35<4:20:52,  1.67it/s]
 55%|█████▍    | 31471/57600 [5:30:35<4:28:11,  1.62it/s]
 55%|█████▍    | 31472/57600 [5:30:36<4:36:24,  1.58it/s]
 55%|█████▍    | 31473/57600 [5:30:37<4:38:25,  1.56it/s]
 55%|█████▍    | 31474/57600 [5:30:37<4:41:28,  1.55it/s]
 55%|█████▍    | 31475/57600 [5:30:38<4:37:31,  1.57it/s]
 55%|█████▍    | 31476/57600 [5:30:39<4:34:17,  1.59it/s]
 55%|█████▍    | 31477/57600 [5:30:39<4:26:37,  1.63it/s]
 55%|█████▍    | 31478/57600 [5:30:40<4:28:30,  1.62it/s]
 55%|█████▍    | 31479/57600 [5:30:40<4:27:03,  1.63it/s]
 55%|█████▍    | 31480/57600 [5:30:41<4:27:47,  1.63it/s]
                                                         
{'loss': 1.1948, 'learning_rate': 5.09547038327526e-07, 'epoch': 347.46}

 55%|█████▍    | 31480/57600 [5:30:41<4:27:47,  1.63it/s]
 55%|█████▍    | 31481/57600 [5:30:42<4:33:01,  1.59it/s]
 55%|█████▍    | 31482/57600 [5:30:42<4:26:08,  1.64it/s]
 55%|█████▍    | 31483/57600 [5:30:43<4:24:57,  1.64it/s]
 55%|█████▍    | 31484/57600 [5:30:43<4:25:06,  1.64it/s]
 55%|█████▍    | 31485/57600 [5:30:44<4:34:16,  1.59it/s]
 55%|█████▍    | 31486/57600 [5:30:45<4:27:43,  1.63it/s]
 55%|█████▍    | 31487/57600 [5:30:45<4:25:34,  1.64it/s]
 55%|█████▍    | 31488/57600 [5:30:46<4:26:32,  1.63it/s]
 55%|█████▍    | 31489/57600 [5:30:47<4:32:32,  1.60it/s]
 55%|█████▍    | 31490/57600 [5:30:47<4:34:47,  1.58it/s]
 55%|█████▍    | 31491/57600 [5:30:48<4:37:37,  1.57it/s]
 55%|█████▍    | 31492/57600 [5:30:48<4:35:42,  1.58it/s]
 55%|█████▍    | 31493/57600 [5:30:49<4:49:53,  1.50it/s]
 55%|█████▍    | 31494/57600 [5:30:50<4:48:13,  1.51it/s]
 55%|█████▍    | 31495/57600 [5:30:51<4:45:24,  1.52it/s]
 55%|█████▍    | 31496/57600 [5:30:51<4:38:40,  1.56it/s]
 55%|█████▍    | 31497/57600 [5:30:52<4:33:12,  1.59it/s]
 55%|█████▍    | 31498/57600 [5:30:52<4:33:18,  1.59it/s]
 55%|█████▍    | 31499/57600 [5:30:53<4:41:05,  1.55it/s]
 55%|█████▍    | 31500/57600 [5:30:54<4:44:14,  1.53it/s]
                                                         
{'loss': 1.1337, 'learning_rate': 5.092334494773519e-07, 'epoch': 347.68}

 55%|█████▍    | 31500/57600 [5:30:54<4:44:14,  1.53it/s]
 55%|█████▍    | 31501/57600 [5:30:54<4:46:11,  1.52it/s]
 55%|█████▍    | 31502/57600 [5:30:55<4:38:16,  1.56it/s]
 55%|█████▍    | 31503/57600 [5:30:56<4:34:58,  1.58it/s]
 55%|█████▍    | 31504/57600 [5:30:56<4:43:41,  1.53it/s]
 55%|█████▍    | 31505/57600 [5:30:57<4:42:07,  1.54it/s]
 55%|█████▍    | 31506/57600 [5:30:58<4:51:16,  1.49it/s]
 55%|█████▍    | 31507/57600 [5:30:58<4:39:27,  1.56it/s]
 55%|█████▍    | 31508/57600 [5:30:59<4:28:29,  1.62it/s]
 55%|█████▍    | 31509/57600 [5:30:59<4:30:06,  1.61it/s]
 55%|█████▍    | 31510/57600 [5:31:00<4:41:21,  1.55it/s]
 55%|█████▍    | 31511/57600 [5:31:01<4:35:03,  1.58it/s]
 55%|█████▍    | 31512/57600 [5:31:01<4:36:15,  1.57it/s]
 55%|█████▍    | 31513/57600 [5:31:02<4:28:48,  1.62it/s]
 55%|█████▍    | 31514/57600 [5:31:03<4:26:27,  1.63it/s]
 55%|█████▍    | 31515/57600 [5:31:03<4:21:32,  1.66it/s]
 55%|█████▍    | 31516/57600 [5:31:04<4:24:41,  1.64it/s]
 55%|█████▍    | 31517/57600 [5:31:04<4:27:31,  1.62it/s]
 55%|█████▍    | 31518/57600 [5:31:05<4:27:36,  1.62it/s]
 55%|█████▍    | 31519/57600 [5:31:06<4:31:48,  1.60it/s]
 55%|█████▍    | 31520/57600 [5:31:06<4:29:44,  1.61it/s]
                                                         
{'loss': 1.1976, 'learning_rate': 5.089198606271777e-07, 'epoch': 347.9}

 55%|█████▍    | 31520/57600 [5:31:06<4:29:44,  1.61it/s]
 55%|█████▍    | 31521/57600 [5:31:07<4:29:38,  1.61it/s]
 55%|█████▍    | 31522/57600 [5:31:08<4:33:02,  1.59it/s]
 55%|█████▍    | 31523/57600 [5:31:08<4:37:14,  1.57it/s]
 55%|█████▍    | 31524/57600 [5:31:09<4:38:35,  1.56it/s]
 55%|█████▍    | 31525/57600 [5:31:09<4:34:28,  1.58it/s]
 55%|█████▍    | 31526/57600 [5:31:10<4:26:22,  1.63it/s]
 55%|█████▍    | 31527/57600 [5:31:11<4:27:54,  1.62it/s]
 55%|█████▍    | 31528/57600 [5:31:11<4:24:02,  1.65it/s]
 55%|█████▍    | 31529/57600 [5:31:12<4:37:39,  1.56it/s]
 55%|█████▍    | 31530/57600 [5:31:13<4:38:53,  1.56it/s]
 55%|█████▍    | 31531/57600 [5:31:13<4:36:33,  1.57it/s]
 55%|█████▍    | 31532/57600 [5:31:14<4:29:02,  1.61it/s]
 55%|█████▍    | 31533/57600 [5:31:14<4:29:25,  1.61it/s]
 55%|█████▍    | 31534/57600 [5:31:15<4:32:34,  1.59it/s]
 55%|█████▍    | 31535/57600 [5:31:16<4:31:41,  1.60it/s]
 55%|█████▍    | 31536/57600 [5:31:16<4:30:58,  1.60it/s]
 55%|█████▍    | 31537/57600 [5:31:17<4:37:11,  1.57it/s]
 55%|█████▍    | 31538/57600 [5:31:18<4:34:56,  1.58it/s]
 55%|█████▍    | 31539/57600 [5:31:18<4:29:10,  1.61it/s]
 55%|█████▍    | 31540/57600 [5:31:19<4:31:19,  1.60it/s]
                                                         
{'loss': 1.2112, 'learning_rate': 5.086062717770035e-07, 'epoch': 348.12}

 55%|█████▍    | 31540/57600 [5:31:19<4:31:19,  1.60it/s]
 55%|█████▍    | 31541/57600 [5:31:19<4:30:01,  1.61it/s]
 55%|█████▍    | 31542/57600 [5:31:20<4:26:21,  1.63it/s]
 55%|█████▍    | 31543/57600 [5:31:21<4:31:12,  1.60it/s]
 55%|█████▍    | 31544/57600 [5:31:21<4:27:14,  1.63it/s]
 55%|█████▍    | 31545/57600 [5:31:22<4:22:56,  1.65it/s]
 55%|█████▍    | 31546/57600 [5:31:22<4:22:44,  1.65it/s]
 55%|█████▍    | 31547/57600 [5:31:23<4:28:57,  1.61it/s]
 55%|█████▍    | 31548/57600 [5:31:24<4:27:30,  1.62it/s]
 55%|█████▍    | 31549/57600 [5:31:24<4:34:36,  1.58it/s]
 55%|█████▍    | 31550/57600 [5:31:25<4:37:53,  1.56it/s]
 55%|█████▍    | 31551/57600 [5:31:26<4:42:14,  1.54it/s]
 55%|█████▍    | 31552/57600 [5:31:26<4:42:28,  1.54it/s]
 55%|█████▍    | 31553/57600 [5:31:27<4:40:33,  1.55it/s]
 55%|█████▍    | 31554/57600 [5:31:28<4:49:41,  1.50it/s]
 55%|█████▍    | 31555/57600 [5:31:28<4:52:12,  1.49it/s]
 55%|█████▍    | 31556/57600 [5:31:29<4:44:27,  1.53it/s]
 55%|█████▍    | 31557/57600 [5:31:30<4:31:08,  1.60it/s]
 55%|█████▍    | 31558/57600 [5:31:30<4:20:43,  1.66it/s]
 55%|█████▍    | 31559/57600 [5:31:31<4:35:37,  1.57it/s]
 55%|█████▍    | 31560/57600 [5:31:31<4:38:15,  1.56it/s]
                                                         
{'loss': 1.1144, 'learning_rate': 5.082926829268292e-07, 'epoch': 348.34}

 55%|█████▍    | 31560/57600 [5:31:31<4:38:15,  1.56it/s]
 55%|█████▍    | 31561/57600 [5:31:32<4:47:07,  1.51it/s]
 55%|█████▍    | 31562/57600 [5:31:33<4:41:44,  1.54it/s]
 55%|█████▍    | 31563/57600 [5:31:33<4:29:29,  1.61it/s]
 55%|█████▍    | 31564/57600 [5:31:34<4:32:51,  1.59it/s]
 55%|█████▍    | 31565/57600 [5:31:35<4:35:34,  1.57it/s]
 55%|█████▍    | 31566/57600 [5:31:35<4:28:24,  1.62it/s]
 55%|█████▍    | 31567/57600 [5:31:36<4:27:15,  1.62it/s]
 55%|█████▍    | 31568/57600 [5:31:36<4:28:59,  1.61it/s]
 55%|█████▍    | 31569/57600 [5:31:37<4:32:13,  1.59it/s]
 55%|█████▍    | 31570/57600 [5:31:38<4:25:22,  1.63it/s]
 55%|█████▍    | 31571/57600 [5:31:38<4:44:20,  1.53it/s]
 55%|█████▍    | 31572/57600 [5:31:39<4:34:29,  1.58it/s]
 55%|█████▍    | 31573/57600 [5:31:40<4:34:37,  1.58it/s]
 55%|█████▍    | 31574/57600 [5:31:40<4:31:56,  1.60it/s]
 55%|█████▍    | 31575/57600 [5:31:41<4:29:52,  1.61it/s]
 55%|█████▍    | 31576/57600 [5:31:41<4:27:48,  1.62it/s]
 55%|█████▍    | 31577/57600 [5:31:42<4:22:55,  1.65it/s]
 55%|█████▍    | 31578/57600 [5:31:43<4:22:55,  1.65it/s]
 55%|█████▍    | 31579/57600 [5:31:43<4:36:18,  1.57it/s]
 55%|█████▍    | 31580/57600 [5:31:44<4:29:59,  1.61it/s]
                                                         
{'loss': 1.1663, 'learning_rate': 5.07979094076655e-07, 'epoch': 348.57}

 55%|█████▍    | 31580/57600 [5:31:44<4:29:59,  1.61it/s]
 55%|█████▍    | 31581/57600 [5:31:45<4:26:52,  1.62it/s]
 55%|█████▍    | 31582/57600 [5:31:45<4:32:44,  1.59it/s]
 55%|█████▍    | 31583/57600 [5:31:46<4:32:29,  1.59it/s]
 55%|█████▍    | 31584/57600 [5:31:47<4:36:27,  1.57it/s]
 55%|█████▍    | 31585/57600 [5:31:47<4:27:36,  1.62it/s]
 55%|█████▍    | 31586/57600 [5:31:48<4:28:55,  1.61it/s]
 55%|█████▍    | 31587/57600 [5:31:48<4:29:56,  1.61it/s]
 55%|█████▍    | 31588/57600 [5:31:49<4:31:38,  1.60it/s]
 55%|█████▍    | 31589/57600 [5:31:50<4:24:14,  1.64it/s]
 55%|█████▍    | 31590/57600 [5:31:50<4:26:13,  1.63it/s]
 55%|█████▍    | 31591/57600 [5:31:51<4:29:04,  1.61it/s]
 55%|█████▍    | 31592/57600 [5:31:52<4:41:17,  1.54it/s]
 55%|█████▍    | 31593/57600 [5:31:52<4:32:25,  1.59it/s]
 55%|█████▍    | 31594/57600 [5:31:53<4:36:02,  1.57it/s]
 55%|█████▍    | 31595/57600 [5:31:53<4:32:42,  1.59it/s]
 55%|█████▍    | 31596/57600 [5:31:54<4:33:09,  1.59it/s]
 55%|█████▍    | 31597/57600 [5:31:55<4:30:11,  1.60it/s]
 55%|█████▍    | 31598/57600 [5:31:55<4:21:21,  1.66it/s]
 55%|█████▍    | 31599/57600 [5:31:56<4:20:24,  1.66it/s]
 55%|█████▍    | 31600/57600 [5:31:56<4:19:25,  1.67it/s]
                                                         
{'loss': 1.1801, 'learning_rate': 5.076655052264809e-07, 'epoch': 348.79}

 55%|█████▍    | 31600/57600 [5:31:56<4:19:25,  1.67it/s]
 55%|█████▍    | 31601/57600 [5:31:57<4:22:49,  1.65it/s]
 55%|█████▍    | 31602/57600 [5:31:58<4:19:25,  1.67it/s]
 55%|█████▍    | 31603/57600 [5:31:58<4:19:39,  1.67it/s]
 55%|█████▍    | 31604/57600 [5:31:59<4:28:16,  1.61it/s]
 55%|█████▍    | 31605/57600 [5:31:59<4:25:48,  1.63it/s]
 55%|█████▍    | 31606/57600 [5:32:00<4:26:57,  1.62it/s]
 55%|█████▍    | 31607/57600 [5:32:01<4:27:06,  1.62it/s]
 55%|█████▍    | 31608/57600 [5:32:01<4:31:14,  1.60it/s]
 55%|█████▍    | 31609/57600 [5:32:02<4:29:55,  1.60it/s]
 55%|█████▍    | 31610/57600 [5:32:03<4:23:22,  1.64it/s]
 55%|█████▍    | 31611/57600 [5:32:03<4:19:44,  1.67it/s]
 55%|█████▍    | 31612/57600 [5:32:04<4:28:39,  1.61it/s]
 55%|█████▍    | 31613/57600 [5:32:04<4:34:24,  1.58it/s]
 55%|█████▍    | 31614/57600 [5:32:05<4:35:32,  1.57it/s]
 55%|█████▍    | 31615/57600 [5:32:06<4:39:02,  1.55it/s]
 55%|█████▍    | 31616/57600 [5:32:06<4:32:01,  1.59it/s]
 55%|█████▍    | 31617/57600 [5:32:07<4:32:59,  1.59it/s]
 55%|█████▍    | 31618/57600 [5:32:08<4:36:57,  1.56it/s]
 55%|█████▍    | 31619/57600 [5:32:08<4:36:58,  1.56it/s]
 55%|█████▍    | 31620/57600 [5:32:09<4:42:42,  1.53it/s]
                                                         
{'loss': 1.1764, 'learning_rate': 5.073519163763065e-07, 'epoch': 349.01}

 55%|█████▍    | 31620/57600 [5:32:09<4:42:42,  1.53it/s]
 55%|█████▍    | 31621/57600 [5:32:10<4:42:05,  1.53it/s]
 55%|█████▍    | 31622/57600 [5:32:10<4:40:06,  1.55it/s]
 55%|█████▍    | 31623/57600 [5:32:11<4:32:12,  1.59it/s]
 55%|█████▍    | 31624/57600 [5:32:11<4:36:41,  1.56it/s]
 55%|█████▍    | 31625/57600 [5:32:12<4:35:08,  1.57it/s]
 55%|█████▍    | 31626/57600 [5:32:13<4:32:07,  1.59it/s]
 55%|█████▍    | 31627/57600 [5:32:13<4:29:55,  1.60it/s]
 55%|█████▍    | 31628/57600 [5:32:14<4:24:17,  1.64it/s]
 55%|█████▍    | 31629/57600 [5:32:15<4:24:11,  1.64it/s]
 55%|█████▍    | 31630/57600 [5:32:15<4:15:23,  1.69it/s]
 55%|█████▍    | 31631/57600 [5:32:16<4:24:28,  1.64it/s]
 55%|█████▍    | 31632/57600 [5:32:16<4:28:51,  1.61it/s]
 55%|█████▍    | 31633/57600 [5:32:17<4:26:32,  1.62it/s]
 55%|█████▍    | 31634/57600 [5:32:18<4:19:02,  1.67it/s]
 55%|█████▍    | 31635/57600 [5:32:18<4:18:46,  1.67it/s]
 55%|█████▍    | 31636/57600 [5:32:19<4:33:00,  1.59it/s]
 55%|█████▍    | 31637/57600 [5:32:19<4:27:11,  1.62it/s]
 55%|█████▍    | 31638/57600 [5:32:20<4:41:48,  1.54it/s]
 55%|█████▍    | 31639/57600 [5:32:21<4:39:03,  1.55it/s]
 55%|█████▍    | 31640/57600 [5:32:21<4:41:00,  1.54it/s]
                                                         
{'loss': 1.1734, 'learning_rate': 5.070383275261324e-07, 'epoch': 349.23}

 55%|█████▍    | 31640/57600 [5:32:21<4:41:00,  1.54it/s]
 55%|█████▍    | 31641/57600 [5:32:22<4:41:20,  1.54it/s]
 55%|█████▍    | 31642/57600 [5:32:23<4:44:19,  1.52it/s]
 55%|█████▍    | 31643/57600 [5:32:23<4:35:34,  1.57it/s]
 55%|█████▍    | 31644/57600 [5:32:24<4:30:39,  1.60it/s]
 55%|█████▍    | 31645/57600 [5:32:25<4:29:56,  1.60it/s]
 55%|█████▍    | 31646/57600 [5:32:25<4:32:39,  1.59it/s]
 55%|█████▍    | 31647/57600 [5:32:26<4:37:24,  1.56it/s]
 55%|█████▍    | 31648/57600 [5:32:26<4:27:12,  1.62it/s]
 55%|█████▍    | 31649/57600 [5:32:27<4:24:51,  1.63it/s]
 55%|█████▍    | 31650/57600 [5:32:28<4:20:15,  1.66it/s]
 55%|█████▍    | 31651/57600 [5:32:28<4:36:03,  1.57it/s]
 55%|█████▍    | 31652/57600 [5:32:29<4:50:29,  1.49it/s]
 55%|█████▍    | 31653/57600 [5:32:30<4:42:30,  1.53it/s]
 55%|█████▍    | 31654/57600 [5:32:30<4:32:58,  1.58it/s]
 55%|█████▍    | 31655/57600 [5:32:31<4:32:21,  1.59it/s]
 55%|█████▍    | 31656/57600 [5:32:32<4:31:58,  1.59it/s]
 55%|█████▍    | 31657/57600 [5:32:32<4:34:48,  1.57it/s]
 55%|█████▍    | 31658/57600 [5:32:33<4:29:16,  1.61it/s]
 55%|█████▍    | 31659/57600 [5:32:33<4:28:20,  1.61it/s]
 55%|█████▍    | 31660/57600 [5:32:34<4:20:23,  1.66it/s]
                                                         
{'loss': 1.1605, 'learning_rate': 5.067247386759581e-07, 'epoch': 349.45}

 55%|█████▍    | 31660/57600 [5:32:34<4:20:23,  1.66it/s]
 55%|█████▍    | 31661/57600 [5:32:35<4:23:53,  1.64it/s]
 55%|█████▍    | 31662/57600 [5:32:35<4:16:03,  1.69it/s]
 55%|█████▍    | 31663/57600 [5:32:36<4:29:37,  1.60it/s]
 55%|█████▍    | 31664/57600 [5:32:36<4:33:14,  1.58it/s]
 55%|█████▍    | 31665/57600 [5:32:37<4:28:41,  1.61it/s]
 55%|█████▍    | 31666/57600 [5:32:38<4:30:09,  1.60it/s]
 55%|█████▍    | 31667/57600 [5:32:38<4:22:33,  1.65it/s]
 55%|█████▍    | 31668/57600 [5:32:39<4:21:25,  1.65it/s]
 55%|█████▍    | 31669/57600 [5:32:40<4:27:04,  1.62it/s]
 55%|█████▍    | 31670/57600 [5:32:40<4:40:00,  1.54it/s]
 55%|█████▍    | 31671/57600 [5:32:41<4:35:09,  1.57it/s]
 55%|█████▍    | 31672/57600 [5:32:41<4:33:28,  1.58it/s]
 55%|█████▍    | 31673/57600 [5:32:42<4:29:13,  1.61it/s]
 55%|█████▍    | 31674/57600 [5:32:43<4:28:34,  1.61it/s]
 55%|█████▍    | 31675/57600 [5:32:43<4:23:45,  1.64it/s]
 55%|█████▍    | 31676/57600 [5:32:44<4:20:25,  1.66it/s]
 55%|█████▍    | 31677/57600 [5:32:45<4:24:25,  1.63it/s]
 55%|█████▍    | 31678/57600 [5:32:45<4:22:03,  1.65it/s]
 55%|█████▍    | 31679/57600 [5:32:46<4:22:29,  1.65it/s]
 55%|█████▌    | 31680/57600 [5:32:46<4:26:31,  1.62it/s]
                                                         
{'loss': 1.2098, 'learning_rate': 5.06411149825784e-07, 'epoch': 349.67}

 55%|█████▌    | 31680/57600 [5:32:46<4:26:31,  1.62it/s]
 55%|█████▌    | 31681/57600 [5:32:47<4:25:12,  1.63it/s]
 55%|█████▌    | 31682/57600 [5:32:48<4:29:31,  1.60it/s]
 55%|█████▌    | 31683/57600 [5:32:48<4:23:54,  1.64it/s]
 55%|█████▌    | 31684/57600 [5:32:49<4:20:32,  1.66it/s]
 55%|█████▌    | 31685/57600 [5:32:49<4:33:22,  1.58it/s]
 55%|█████▌    | 31686/57600 [5:32:50<4:27:13,  1.62it/s]
 55%|█████▌    | 31687/57600 [5:32:51<4:22:07,  1.65it/s]
 55%|█████▌    | 31688/57600 [5:32:51<4:23:54,  1.64it/s]
 55%|█████▌    | 31689/57600 [5:32:52<4:19:13,  1.67it/s]
 55%|█████▌    | 31690/57600 [5:32:52<4:16:17,  1.68it/s]
 55%|█████▌    | 31691/57600 [5:32:53<4:22:21,  1.65it/s]
 55%|█████▌    | 31692/57600 [5:32:54<4:27:32,  1.61it/s]
 55%|█████▌    | 31693/57600 [5:32:54<4:25:35,  1.63it/s]
 55%|█████▌    | 31694/57600 [5:32:55<4:30:58,  1.59it/s]
 55%|█████▌    | 31695/57600 [5:32:56<4:31:38,  1.59it/s]
 55%|█████▌    | 31696/57600 [5:32:56<4:26:18,  1.62it/s]
 55%|█████▌    | 31697/57600 [5:32:57<4:25:51,  1.62it/s]
 55%|█████▌    | 31698/57600 [5:32:58<4:37:54,  1.55it/s]
 55%|█████▌    | 31699/57600 [5:32:58<4:34:43,  1.57it/s]
 55%|█████▌    | 31700/57600 [5:32:59<4:40:06,  1.54it/s]
                                                         
{'loss': 1.1533, 'learning_rate': 5.060975609756097e-07, 'epoch': 349.89}

 55%|█████▌    | 31700/57600 [5:32:59<4:40:06,  1.54it/s]
 55%|█████▌    | 31701/57600 [5:32:59<4:38:41,  1.55it/s]
 55%|█████▌    | 31702/57600 [5:33:00<4:33:56,  1.58it/s]
 55%|█████▌    | 31703/57600 [5:33:01<4:33:21,  1.58it/s]
 55%|█████▌    | 31704/57600 [5:33:01<4:25:18,  1.63it/s]
 55%|█████▌    | 31705/57600 [5:33:02<4:24:35,  1.63it/s]
 55%|█████▌    | 31706/57600 [5:33:03<4:36:05,  1.56it/s]
 55%|█████▌    | 31707/57600 [5:33:03<4:32:08,  1.59it/s]
 55%|█████▌    | 31708/57600 [5:33:04<4:32:03,  1.59it/s]
 55%|█████▌    | 31709/57600 [5:33:04<4:35:15,  1.57it/s]
 55%|█████▌    | 31710/57600 [5:33:05<4:35:15,  1.57it/s]
 55%|█████▌    | 31711/57600 [5:33:06<4:45:47,  1.51it/s]
 55%|█████▌    | 31712/57600 [5:33:06<4:34:13,  1.57it/s]
 55%|█████▌    | 31713/57600 [5:33:07<4:38:26,  1.55it/s]
 55%|█████▌    | 31714/57600 [5:33:08<4:27:54,  1.61it/s]
 55%|█████▌    | 31715/57600 [5:33:08<4:24:49,  1.63it/s]
 55%|█████▌    | 31716/57600 [5:33:09<4:25:54,  1.62it/s]
 55%|█████▌    | 31717/57600 [5:33:10<4:33:27,  1.58it/s]
 55%|█████▌    | 31718/57600 [5:33:10<4:42:02,  1.53it/s]
 55%|█████▌    | 31719/57600 [5:33:11<4:37:50,  1.55it/s]
 55%|█████▌    | 31720/57600 [5:33:11<4:38:29,  1.55it/s]
                                                         
{'loss': 1.1666, 'learning_rate': 5.057839721254354e-07, 'epoch': 350.11}

 55%|█████▌    | 31720/57600 [5:33:11<4:38:29,  1.55it/s]
 55%|█████▌    | 31721/57600 [5:33:12<4:34:38,  1.57it/s]
 55%|█████▌    | 31722/57600 [5:33:13<4:36:04,  1.56it/s]
 55%|█████▌    | 31723/57600 [5:33:13<4:35:52,  1.56it/s]
 55%|█████▌    | 31724/57600 [5:33:14<4:37:52,  1.55it/s]
 55%|█████▌    | 31725/57600 [5:33:15<4:42:09,  1.53it/s]
 55%|█████▌    | 31726/57600 [5:33:15<4:36:12,  1.56it/s]
 55%|█████▌    | 31727/57600 [5:33:16<4:43:22,  1.52it/s]
 55%|█████▌    | 31728/57600 [5:33:17<4:45:17,  1.51it/s]
 55%|█████▌    | 31729/57600 [5:33:17<4:41:56,  1.53it/s]
 55%|█████▌    | 31730/57600 [5:33:18<4:35:58,  1.56it/s]
 55%|█████▌    | 31731/57600 [5:33:19<4:40:20,  1.54it/s]
 55%|█████▌    | 31732/57600 [5:33:19<4:34:38,  1.57it/s]
 55%|█████▌    | 31733/57600 [5:33:20<4:30:02,  1.60it/s]
 55%|█████▌    | 31734/57600 [5:33:21<4:44:42,  1.51it/s]
 55%|█████▌    | 31735/57600 [5:33:21<4:38:08,  1.55it/s]
 55%|█████▌    | 31736/57600 [5:33:22<4:39:10,  1.54it/s]
 55%|█████▌    | 31737/57600 [5:33:22<4:28:43,  1.60it/s]
 55%|█████▌    | 31738/57600 [5:33:23<4:19:45,  1.66it/s]
 55%|█████▌    | 31739/57600 [5:33:24<4:20:29,  1.65it/s]
 55%|█████▌    | 31740/57600 [5:33:24<4:18:57,  1.66it/s]
                                                         
{'loss': 1.1604, 'learning_rate': 5.054703832752614e-07, 'epoch': 350.33}

 55%|█████▌    | 31740/57600 [5:33:24<4:18:57,  1.66it/s]
 55%|█████▌    | 31741/57600 [5:33:25<4:17:52,  1.67it/s]
 55%|█████▌    | 31742/57600 [5:33:25<4:18:57,  1.66it/s]
 55%|█████▌    | 31743/57600 [5:33:26<4:31:25,  1.59it/s]
 55%|█████▌    | 31744/57600 [5:33:27<4:26:17,  1.62it/s]
 55%|█████▌    | 31745/57600 [5:33:27<4:34:33,  1.57it/s]
 55%|█████▌    | 31746/57600 [5:33:28<4:42:47,  1.52it/s]
 55%|█████▌    | 31747/57600 [5:33:29<4:35:33,  1.56it/s]
 55%|█████▌    | 31748/57600 [5:33:29<4:33:44,  1.57it/s]
 55%|█████▌    | 31749/57600 [5:33:30<4:28:32,  1.60it/s]
 55%|█████▌    | 31750/57600 [5:33:31<4:35:30,  1.56it/s]
 55%|█████▌    | 31751/57600 [5:33:31<4:31:19,  1.59it/s]
 55%|█████▌    | 31752/57600 [5:33:32<4:24:18,  1.63it/s]
 55%|█████▌    | 31753/57600 [5:33:32<4:27:39,  1.61it/s]
 55%|█████▌    | 31754/57600 [5:33:33<4:31:50,  1.58it/s]
 55%|█████▌    | 31755/57600 [5:33:34<4:37:57,  1.55it/s]
 55%|█████▌    | 31756/57600 [5:33:34<4:31:50,  1.58it/s]
 55%|█████▌    | 31757/57600 [5:33:35<4:27:20,  1.61it/s]
 55%|█████▌    | 31758/57600 [5:33:35<4:21:52,  1.64it/s]
 55%|█████▌    | 31759/57600 [5:33:36<4:30:35,  1.59it/s]
 55%|█████▌    | 31760/57600 [5:33:37<4:22:09,  1.64it/s]
                                                         
{'loss': 1.1899, 'learning_rate': 5.051567944250871e-07, 'epoch': 350.55}

 55%|█████▌    | 31760/57600 [5:33:37<4:22:09,  1.64it/s]
 55%|█████▌    | 31761/57600 [5:33:37<4:16:54,  1.68it/s]
 55%|█████▌    | 31762/57600 [5:33:38<4:20:55,  1.65it/s]
 55%|█████▌    | 31763/57600 [5:33:38<4:20:08,  1.66it/s]
 55%|█████▌    | 31764/57600 [5:33:39<4:29:30,  1.60it/s]
 55%|█████▌    | 31765/57600 [5:33:40<4:39:18,  1.54it/s]
 55%|█████▌    | 31766/57600 [5:33:40<4:32:26,  1.58it/s]
 55%|█████▌    | 31767/57600 [5:33:41<4:37:10,  1.55it/s]
 55%|█████▌    | 31768/57600 [5:33:42<4:37:01,  1.55it/s]
 55%|█████▌    | 31769/57600 [5:33:42<4:35:59,  1.56it/s]
 55%|█████▌    | 31770/57600 [5:33:43<4:32:42,  1.58it/s]
 55%|█████▌    | 31771/57600 [5:33:44<4:38:21,  1.55it/s]
 55%|█████▌    | 31772/57600 [5:33:44<4:29:25,  1.60it/s]
 55%|█████▌    | 31773/57600 [5:33:45<4:27:42,  1.61it/s]
 55%|█████▌    | 31774/57600 [5:33:46<4:28:56,  1.60it/s]
 55%|█████▌    | 31775/57600 [5:33:46<4:29:00,  1.60it/s]
 55%|█████▌    | 31776/57600 [5:33:47<4:35:24,  1.56it/s]
 55%|█████▌    | 31777/57600 [5:33:47<4:33:17,  1.57it/s]
 55%|█████▌    | 31778/57600 [5:33:48<4:38:36,  1.54it/s]
 55%|█████▌    | 31779/57600 [5:33:49<4:30:44,  1.59it/s]
 55%|█████▌    | 31780/57600 [5:33:49<4:23:40,  1.63it/s]
                                                         
{'loss': 1.1404, 'learning_rate': 5.04843205574913e-07, 'epoch': 350.77}

 55%|█████▌    | 31780/57600 [5:33:49<4:23:40,  1.63it/s]
 55%|█████▌    | 31781/57600 [5:33:50<4:18:10,  1.67it/s]
 55%|█████▌    | 31782/57600 [5:33:50<4:15:48,  1.68it/s]
 55%|█████▌    | 31783/57600 [5:33:51<4:19:37,  1.66it/s]
 55%|█████▌    | 31784/57600 [5:33:52<4:17:29,  1.67it/s]
 55%|█████▌    | 31785/57600 [5:33:52<4:12:09,  1.71it/s]
 55%|█████▌    | 31786/57600 [5:33:53<4:14:54,  1.69it/s]
 55%|█████▌    | 31787/57600 [5:33:53<4:22:12,  1.64it/s]
 55%|█████▌    | 31788/57600 [5:33:54<4:28:36,  1.60it/s]
 55%|█████▌    | 31789/57600 [5:33:55<4:34:25,  1.57it/s]
 55%|█████▌    | 31790/57600 [5:33:55<4:26:05,  1.62it/s]
 55%|█████▌    | 31791/57600 [5:33:56<4:30:26,  1.59it/s]
 55%|█████▌    | 31792/57600 [5:33:57<4:27:59,  1.61it/s]
 55%|█████▌    | 31793/57600 [5:33:57<4:29:11,  1.60it/s]
 55%|█████▌    | 31794/57600 [5:33:58<4:29:34,  1.60it/s]
 55%|█████▌    | 31795/57600 [5:33:59<4:31:36,  1.58it/s]
 55%|█████▌    | 31796/57600 [5:33:59<4:24:39,  1.62it/s]
 55%|█████▌    | 31797/57600 [5:34:00<4:25:24,  1.62it/s]
 55%|█████▌    | 31798/57600 [5:34:00<4:23:52,  1.63it/s]
 55%|█████▌    | 31799/57600 [5:34:01<4:25:21,  1.62it/s]
 55%|█████▌    | 31800/57600 [5:34:02<4:22:22,  1.64it/s]
                                                         
{'loss': 1.16, 'learning_rate': 5.045296167247386e-07, 'epoch': 350.99}

 55%|█████▌    | 31800/57600 [5:34:02<4:22:22,  1.64it/s]
 55%|█████▌    | 31801/57600 [5:34:02<4:34:48,  1.56it/s]
 55%|█████▌    | 31802/57600 [5:34:03<4:38:53,  1.54it/s]
 55%|█████▌    | 31803/57600 [5:34:04<4:43:02,  1.52it/s]
 55%|█████▌    | 31804/57600 [5:34:04<4:36:14,  1.56it/s]
 55%|█████▌    | 31805/57600 [5:34:05<4:33:02,  1.57it/s]
 55%|█████▌    | 31806/57600 [5:34:05<4:34:59,  1.56it/s]
 55%|█████▌    | 31807/57600 [5:34:06<4:38:40,  1.54it/s]
 55%|█████▌    | 31808/57600 [5:34:07<4:43:15,  1.52it/s]
 55%|█████▌    | 31809/57600 [5:34:08<4:46:27,  1.50it/s]
 55%|█████▌    | 31810/57600 [5:34:08<4:30:22,  1.59it/s]
 55%|█████▌    | 31811/57600 [5:34:09<4:23:38,  1.63it/s]
 55%|█████▌    | 31812/57600 [5:34:09<4:19:05,  1.66it/s]
 55%|█████▌    | 31813/57600 [5:34:10<4:24:54,  1.62it/s]
 55%|█████▌    | 31814/57600 [5:34:11<4:33:38,  1.57it/s]
 55%|█████▌    | 31815/57600 [5:34:11<4:32:36,  1.58it/s]
 55%|█████▌    | 31816/57600 [5:34:12<4:33:50,  1.57it/s]
 55%|█████▌    | 31817/57600 [5:34:12<4:31:15,  1.58it/s]
 55%|█████▌    | 31818/57600 [5:34:13<4:24:11,  1.63it/s]
 55%|█████▌    | 31819/57600 [5:34:14<4:20:47,  1.65it/s]
 55%|█████▌    | 31820/57600 [5:34:14<4:17:24,  1.67it/s]
                                                         
{'loss': 1.1792, 'learning_rate': 5.042160278745645e-07, 'epoch': 351.21}

 55%|█████▌    | 31820/57600 [5:34:14<4:17:24,  1.67it/s]
 55%|█████▌    | 31821/57600 [5:34:15<4:12:42,  1.70it/s]
 55%|█████▌    | 31822/57600 [5:34:15<4:14:34,  1.69it/s]
 55%|█████▌    | 31823/57600 [5:34:16<4:21:34,  1.64it/s]
 55%|█████▌    | 31824/57600 [5:34:17<4:21:09,  1.64it/s]
 55%|█████▌    | 31825/57600 [5:34:17<4:25:10,  1.62it/s]
 55%|█████▌    | 31826/57600 [5:34:18<4:27:37,  1.61it/s]
 55%|█████▌    | 31827/57600 [5:34:19<4:28:49,  1.60it/s]
 55%|█████▌    | 31828/57600 [5:34:19<4:29:22,  1.59it/s]
 55%|█████▌    | 31829/57600 [5:34:20<4:30:10,  1.59it/s]
 55%|█████▌    | 31830/57600 [5:34:20<4:30:16,  1.59it/s]
 55%|█████▌    | 31831/57600 [5:34:21<4:24:15,  1.63it/s]
 55%|█████▌    | 31832/57600 [5:34:22<4:28:38,  1.60it/s]
 55%|█████▌    | 31833/57600 [5:34:22<4:32:33,  1.58it/s]
 55%|█████▌    | 31834/57600 [5:34:23<4:31:32,  1.58it/s]
 55%|█████▌    | 31835/57600 [5:34:23<4:22:37,  1.64it/s]
 55%|█████▌    | 31836/57600 [5:34:24<4:26:38,  1.61it/s]
 55%|█████▌    | 31837/57600 [5:34:25<4:19:40,  1.65it/s]
 55%|█████▌    | 31838/57600 [5:34:25<4:22:03,  1.64it/s]
 55%|█████▌    | 31839/57600 [5:34:26<4:22:32,  1.64it/s]
 55%|█████▌    | 31840/57600 [5:34:26<4:15:32,  1.68it/s]
                                                         
{'loss': 1.2048, 'learning_rate': 5.039024390243901e-07, 'epoch': 351.43}

 55%|█████▌    | 31840/57600 [5:34:26<4:15:32,  1.68it/s]
 55%|█████▌    | 31841/57600 [5:34:27<4:20:08,  1.65it/s]
 55%|█████▌    | 31842/57600 [5:34:28<4:22:13,  1.64it/s]
 55%|█████▌    | 31843/57600 [5:34:28<4:27:21,  1.61it/s]
 55%|█████▌    | 31844/57600 [5:34:29<4:22:14,  1.64it/s]
 55%|█████▌    | 31845/57600 [5:34:30<4:21:52,  1.64it/s]
 55%|█████▌    | 31846/57600 [5:34:30<4:22:37,  1.63it/s]
 55%|█████▌    | 31847/57600 [5:34:31<4:24:27,  1.62it/s]
 55%|█████▌    | 31848/57600 [5:34:32<4:36:35,  1.55it/s]
 55%|█████▌    | 31849/57600 [5:34:32<4:25:10,  1.62it/s]
 55%|█████▌    | 31850/57600 [5:34:33<4:27:28,  1.60it/s]
 55%|█████▌    | 31851/57600 [5:34:33<4:32:18,  1.58it/s]
 55%|█████▌    | 31852/57600 [5:34:34<4:24:56,  1.62it/s]
 55%|█████▌    | 31853/57600 [5:34:35<4:24:20,  1.62it/s]
 55%|█████▌    | 31854/57600 [5:34:35<4:31:51,  1.58it/s]
 55%|█████▌    | 31855/57600 [5:34:36<4:36:02,  1.55it/s]
 55%|█████▌    | 31856/57600 [5:34:37<4:34:48,  1.56it/s]
 55%|█████▌    | 31857/57600 [5:34:37<4:28:43,  1.60it/s]
 55%|█████▌    | 31858/57600 [5:34:38<4:23:11,  1.63it/s]
 55%|█████▌    | 31859/57600 [5:34:38<4:19:50,  1.65it/s]
 55%|█████▌    | 31860/57600 [5:34:39<4:22:03,  1.64it/s]
                                                         
{'loss': 1.1659, 'learning_rate': 5.03588850174216e-07, 'epoch': 351.66}

 55%|█████▌    | 31860/57600 [5:34:39<4:22:03,  1.64it/s]
 55%|█████▌    | 31861/57600 [5:34:40<4:25:59,  1.61it/s]
 55%|█████▌    | 31862/57600 [5:34:40<4:26:06,  1.61it/s]
 55%|█████▌    | 31863/57600 [5:34:41<4:22:51,  1.63it/s]
 55%|█████▌    | 31864/57600 [5:34:41<4:27:23,  1.60it/s]
 55%|█████▌    | 31865/57600 [5:34:42<4:32:00,  1.58it/s]
 55%|█████▌    | 31866/57600 [5:34:43<4:31:54,  1.58it/s]
 55%|█████▌    | 31867/57600 [5:34:43<4:40:33,  1.53it/s]
 55%|█████▌    | 31868/57600 [5:34:44<4:41:58,  1.52it/s]
 55%|█████▌    | 31869/57600 [5:34:45<4:32:55,  1.57it/s]
 55%|█████▌    | 31870/57600 [5:34:45<4:29:55,  1.59it/s]
 55%|█████▌    | 31871/57600 [5:34:46<4:26:38,  1.61it/s]
 55%|█████▌    | 31872/57600 [5:34:47<4:29:36,  1.59it/s]
 55%|█████▌    | 31873/57600 [5:34:47<4:26:51,  1.61it/s]
 55%|█████▌    | 31874/57600 [5:34:48<4:28:42,  1.60it/s]
 55%|█████▌    | 31875/57600 [5:34:48<4:28:48,  1.59it/s]
 55%|█████▌    | 31876/57600 [5:34:49<4:34:50,  1.56it/s]
 55%|█████▌    | 31877/57600 [5:34:50<4:26:50,  1.61it/s]
 55%|█████▌    | 31878/57600 [5:34:50<4:33:23,  1.57it/s]
 55%|█████▌    | 31879/57600 [5:34:51<4:29:59,  1.59it/s]
 55%|█████▌    | 31880/57600 [5:34:52<4:23:23,  1.63it/s]
                                                         
{'loss': 1.1488, 'learning_rate': 5.032752613240418e-07, 'epoch': 351.88}

 55%|█████▌    | 31880/57600 [5:34:52<4:23:23,  1.63it/s]
 55%|█████▌    | 31881/57600 [5:34:52<4:26:32,  1.61it/s]
 55%|█████▌    | 31882/57600 [5:34:53<4:41:15,  1.52it/s]
 55%|█████▌    | 31883/57600 [5:34:53<4:31:19,  1.58it/s]
 55%|█████▌    | 31884/57600 [5:34:54<4:36:27,  1.55it/s]
 55%|█████▌    | 31885/57600 [5:34:55<4:25:03,  1.62it/s]
 55%|█████▌    | 31886/57600 [5:34:55<4:23:21,  1.63it/s]
 55%|█████▌    | 31887/57600 [5:34:56<4:29:12,  1.59it/s]
 55%|█████▌    | 31888/57600 [5:34:57<4:35:21,  1.56it/s]
 55%|█████▌    | 31889/57600 [5:34:57<4:37:28,  1.54it/s]
 55%|█████▌    | 31890/57600 [5:34:58<4:38:17,  1.54it/s]
 55%|█████▌    | 31891/57600 [5:34:59<4:31:48,  1.58it/s]
 55%|█████▌    | 31892/57600 [5:34:59<4:43:36,  1.51it/s]
 55%|█████▌    | 31893/57600 [5:35:00<4:38:38,  1.54it/s]
 55%|█████▌    | 31894/57600 [5:35:01<4:32:28,  1.57it/s]
 55%|█████▌    | 31895/57600 [5:35:01<4:23:34,  1.63it/s]
 55%|█████▌    | 31896/57600 [5:35:02<4:32:18,  1.57it/s]
 55%|█████▌    | 31897/57600 [5:35:02<4:37:36,  1.54it/s]
 55%|█████▌    | 31898/57600 [5:35:03<4:33:29,  1.57it/s]
 55%|█████▌    | 31899/57600 [5:35:04<4:29:10,  1.59it/s]
 55%|█████▌    | 31900/57600 [5:35:04<4:26:25,  1.61it/s]
                                                         
{'loss': 1.1646, 'learning_rate': 5.029616724738676e-07, 'epoch': 352.1}

 55%|█████▌    | 31900/57600 [5:35:04<4:26:25,  1.61it/s]
 55%|█████▌    | 31901/57600 [5:35:05<4:25:38,  1.61it/s]
 55%|█████▌    | 31902/57600 [5:35:06<4:30:03,  1.59it/s]
 55%|█████▌    | 31903/57600 [5:35:06<4:24:18,  1.62it/s]
 55%|█████▌    | 31904/57600 [5:35:07<4:17:50,  1.66it/s]
 55%|█████▌    | 31905/57600 [5:35:07<4:16:42,  1.67it/s]
 55%|█████▌    | 31906/57600 [5:35:08<4:15:09,  1.68it/s]
 55%|█████▌    | 31907/57600 [5:35:09<4:18:43,  1.66it/s]
 55%|█████▌    | 31908/57600 [5:35:09<4:20:43,  1.64it/s]
 55%|█████▌    | 31909/57600 [5:35:10<4:20:53,  1.64it/s]
 55%|█████▌    | 31910/57600 [5:35:10<4:18:56,  1.65it/s]
 55%|█████▌    | 31911/57600 [5:35:11<4:25:40,  1.61it/s]
 55%|█████▌    | 31912/57600 [5:35:12<4:26:46,  1.60it/s]
 55%|█████▌    | 31913/57600 [5:35:12<4:26:51,  1.60it/s]
 55%|█████▌    | 31914/57600 [5:35:13<4:27:39,  1.60it/s]
 55%|█████▌    | 31915/57600 [5:35:13<4:20:18,  1.64it/s]
 55%|█████▌    | 31916/57600 [5:35:14<4:27:25,  1.60it/s]
 55%|█████▌    | 31917/57600 [5:35:15<4:24:02,  1.62it/s]
 55%|█████▌    | 31918/57600 [5:35:15<4:25:21,  1.61it/s]
 55%|█████▌    | 31919/57600 [5:35:16<4:28:18,  1.60it/s]
 55%|█████▌    | 31920/57600 [5:35:17<4:29:25,  1.59it/s]
                                                         
{'loss': 1.1681, 'learning_rate': 5.026480836236933e-07, 'epoch': 352.32}

 55%|█████▌    | 31920/57600 [5:35:17<4:29:25,  1.59it/s]
 55%|█████▌    | 31921/57600 [5:35:17<4:36:39,  1.55it/s]
 55%|█████▌    | 31922/57600 [5:35:18<4:41:27,  1.52it/s]
 55%|█████▌    | 31923/57600 [5:35:19<4:42:03,  1.52it/s]
 55%|█████▌    | 31924/57600 [5:35:19<4:35:30,  1.55it/s]
 55%|█████▌    | 31925/57600 [5:35:20<4:43:28,  1.51it/s]
 55%|█████▌    | 31926/57600 [5:35:21<4:32:28,  1.57it/s]
 55%|█████▌    | 31927/57600 [5:35:21<4:28:20,  1.59it/s]
 55%|█████▌    | 31928/57600 [5:35:22<4:23:25,  1.62it/s]
 55%|█████▌    | 31929/57600 [5:35:22<4:20:30,  1.64it/s]
 55%|█████▌    | 31930/57600 [5:35:23<4:21:30,  1.64it/s]
 55%|█████▌    | 31931/57600 [5:35:24<4:17:21,  1.66it/s]
 55%|█████▌    | 31932/57600 [5:35:24<4:15:40,  1.67it/s]
 55%|█████▌    | 31933/57600 [5:35:25<4:14:03,  1.68it/s]
 55%|█████▌    | 31934/57600 [5:35:25<4:32:22,  1.57it/s]
 55%|█████▌    | 31935/57600 [5:35:26<4:30:00,  1.58it/s]
 55%|█████▌    | 31936/57600 [5:35:27<4:24:09,  1.62it/s]
 55%|█████▌    | 31937/57600 [5:35:27<4:20:47,  1.64it/s]
 55%|█████▌    | 31938/57600 [5:35:28<4:21:06,  1.64it/s]
 55%|█████▌    | 31939/57600 [5:35:28<4:17:03,  1.66it/s]
 55%|█████▌    | 31940/57600 [5:35:29<4:27:00,  1.60it/s]
                                                         
{'loss': 1.1924, 'learning_rate': 5.023344947735192e-07, 'epoch': 352.54}

 55%|█████▌    | 31940/57600 [5:35:29<4:27:00,  1.60it/s]
 55%|█████▌    | 31941/57600 [5:35:30<4:25:19,  1.61it/s]
 55%|█████▌    | 31942/57600 [5:35:30<4:22:35,  1.63it/s]
 55%|█████▌    | 31943/57600 [5:35:31<4:21:46,  1.63it/s]
 55%|█████▌    | 31944/57600 [5:35:32<4:19:42,  1.65it/s]
 55%|█████▌    | 31945/57600 [5:35:32<4:35:10,  1.55it/s]
 55%|█████▌    | 31946/57600 [5:35:33<4:29:10,  1.59it/s]
 55%|█████▌    | 31947/57600 [5:35:33<4:19:46,  1.65it/s]
 55%|█████▌    | 31948/57600 [5:35:34<4:19:30,  1.65it/s]
 55%|█████▌    | 31949/57600 [5:35:35<4:22:12,  1.63it/s]
 55%|█████▌    | 31950/57600 [5:35:35<4:19:17,  1.65it/s]
 55%|█████▌    | 31951/57600 [5:35:36<4:22:15,  1.63it/s]
 55%|█████▌    | 31952/57600 [5:35:37<4:29:24,  1.59it/s]
 55%|█████▌    | 31953/57600 [5:35:37<4:27:53,  1.60it/s]
 55%|█████▌    | 31954/57600 [5:35:38<4:21:36,  1.63it/s]
 55%|█████▌    | 31955/57600 [5:35:38<4:22:28,  1.63it/s]
 55%|█████▌    | 31956/57600 [5:35:39<4:16:09,  1.67it/s]
 55%|█████▌    | 31957/57600 [5:35:40<4:25:41,  1.61it/s]
 55%|█████▌    | 31958/57600 [5:35:40<4:24:04,  1.62it/s]
 55%|█████▌    | 31959/57600 [5:35:41<4:20:59,  1.64it/s]
 55%|█████▌    | 31960/57600 [5:35:41<4:18:57,  1.65it/s]
                                                         
{'loss': 1.1631, 'learning_rate': 5.020209059233449e-07, 'epoch': 352.76}

 55%|█████▌    | 31960/57600 [5:35:41<4:18:57,  1.65it/s]
 55%|█████▌    | 31961/57600 [5:35:42<4:18:48,  1.65it/s]
 55%|█████▌    | 31962/57600 [5:35:43<4:32:30,  1.57it/s]
 55%|█████▌    | 31963/57600 [5:35:43<4:40:42,  1.52it/s]
 55%|█████▌    | 31964/57600 [5:35:44<4:38:54,  1.53it/s]
 55%|█████▌    | 31965/57600 [5:35:45<4:41:48,  1.52it/s]
 55%|█████▌    | 31966/57600 [5:35:45<4:39:09,  1.53it/s]
 55%|█████▌    | 31967/57600 [5:35:46<4:34:45,  1.55it/s]
 56%|█████▌    | 31968/57600 [5:35:47<4:28:45,  1.59it/s]
 56%|█████▌    | 31969/57600 [5:35:47<4:32:53,  1.57it/s]
 56%|█████▌    | 31970/57600 [5:35:48<4:28:54,  1.59it/s]
 56%|█████▌    | 31971/57600 [5:35:49<4:36:17,  1.55it/s]
 56%|█████▌    | 31972/57600 [5:35:49<4:36:23,  1.55it/s]
 56%|█████▌    | 31973/57600 [5:35:50<4:38:53,  1.53it/s]
 56%|█████▌    | 31974/57600 [5:35:50<4:25:15,  1.61it/s]
 56%|█████▌    | 31975/57600 [5:35:51<4:27:56,  1.59it/s]
 56%|█████▌    | 31976/57600 [5:35:52<4:25:23,  1.61it/s]
 56%|█████▌    | 31977/57600 [5:35:52<4:29:15,  1.59it/s]
 56%|█████▌    | 31978/57600 [5:35:53<4:26:58,  1.60it/s]
 56%|█████▌    | 31979/57600 [5:35:54<4:32:59,  1.56it/s]
 56%|█████▌    | 31980/57600 [5:35:54<4:32:02,  1.57it/s]
                                                         
{'loss': 1.1437, 'learning_rate': 5.017073170731707e-07, 'epoch': 352.98}

 56%|█████▌    | 31980/57600 [5:35:54<4:32:02,  1.57it/s]
 56%|█████▌    | 31981/57600 [5:35:55<4:40:24,  1.52it/s]
 56%|█████▌    | 31982/57600 [5:35:56<5:00:01,  1.42it/s]
 56%|█████▌    | 31983/57600 [5:35:56<4:43:56,  1.50it/s]
 56%|█████▌    | 31984/57600 [5:35:57<4:46:20,  1.49it/s]
 56%|█████▌    | 31985/57600 [5:35:58<4:37:27,  1.54it/s]
 56%|█████▌    | 31986/57600 [5:35:58<4:35:03,  1.55it/s]
 56%|█████▌    | 31987/57600 [5:35:59<4:29:41,  1.58it/s]
 56%|█████▌    | 31988/57600 [5:35:59<4:24:03,  1.62it/s]
 56%|█████▌    | 31989/57600 [5:36:00<4:16:36,  1.66it/s]
 56%|█████▌    | 31990/57600 [5:36:01<4:36:08,  1.55it/s]
 56%|█████▌    | 31991/57600 [5:36:01<4:31:09,  1.57it/s]
 56%|█████▌    | 31992/57600 [5:36:02<4:35:23,  1.55it/s]
 56%|█████▌    | 31993/57600 [5:36:03<4:28:47,  1.59it/s]
 56%|█████▌    | 31994/57600 [5:36:03<4:30:34,  1.58it/s]
 56%|█████▌    | 31995/57600 [5:36:04<4:27:40,  1.59it/s]
 56%|█████▌    | 31996/57600 [5:36:05<4:37:42,  1.54it/s]
 56%|█████▌    | 31997/57600 [5:36:05<4:31:43,  1.57it/s]
 56%|█████▌    | 31998/57600 [5:36:06<4:27:38,  1.59it/s]
 56%|█████▌    | 31999/57600 [5:36:06<4:24:12,  1.61it/s]
 56%|█████▌    | 32000/57600 [5:36:07<4:18:59,  1.65it/s]
                                                         
{'loss': 1.1479, 'learning_rate': 5.013937282229966e-07, 'epoch': 353.2}

 56%|█████▌    | 32000/57600 [5:36:07<4:18:59,  1.65it/s]
 56%|█████▌    | 32001/57600 [5:36:08<4:19:06,  1.65it/s]
 56%|█████▌    | 32002/57600 [5:36:08<4:15:38,  1.67it/s]
 56%|█████▌    | 32003/57600 [5:36:09<4:24:53,  1.61it/s]
 56%|█████▌    | 32004/57600 [5:36:09<4:19:38,  1.64it/s]
 56%|█████▌    | 32005/57600 [5:36:10<4:20:06,  1.64it/s]
 56%|█████▌    | 32006/57600 [5:36:11<4:27:05,  1.60it/s]
 56%|█████▌    | 32007/57600 [5:36:11<4:18:25,  1.65it/s]
 56%|█████▌    | 32008/57600 [5:36:12<4:15:59,  1.67it/s]
 56%|█████▌    | 32009/57600 [5:36:12<4:15:08,  1.67it/s]
 56%|█████▌    | 32010/57600 [5:36:13<4:27:56,  1.59it/s]
 56%|█████▌    | 32011/57600 [5:36:14<4:29:50,  1.58it/s]
 56%|█████▌    | 32012/57600 [5:36:14<4:26:14,  1.60it/s]
 56%|█████▌    | 32013/57600 [5:36:15<4:25:22,  1.61it/s]
 56%|█████▌    | 32014/57600 [5:36:16<4:27:19,  1.60it/s]
 56%|█████▌    | 32015/57600 [5:36:16<4:29:57,  1.58it/s]
 56%|█████▌    | 32016/57600 [5:36:17<4:34:29,  1.55it/s]
 56%|█████▌    | 32017/57600 [5:36:18<4:38:47,  1.53it/s]
 56%|█████▌    | 32018/57600 [5:36:18<4:28:55,  1.59it/s]
 56%|█████▌    | 32019/57600 [5:36:19<4:23:25,  1.62it/s]
 56%|█████▌    | 32020/57600 [5:36:19<4:21:44,  1.63it/s]
                                                         
{'loss': 1.1799, 'learning_rate': 5.010801393728223e-07, 'epoch': 353.42}

 56%|█████▌    | 32020/57600 [5:36:19<4:21:44,  1.63it/s]
 56%|█████▌    | 32021/57600 [5:36:20<4:22:18,  1.63it/s]
 56%|█████▌    | 32022/57600 [5:36:21<4:14:59,  1.67it/s]
 56%|█████▌    | 32023/57600 [5:36:21<4:22:21,  1.62it/s]
 56%|█████▌    | 32024/57600 [5:36:22<4:26:25,  1.60it/s]
 56%|█████▌    | 32025/57600 [5:36:22<4:28:50,  1.59it/s]
 56%|█████▌    | 32026/57600 [5:36:23<4:36:04,  1.54it/s]
 56%|█████▌    | 32027/57600 [5:36:24<4:31:45,  1.57it/s]
 56%|█████▌    | 32028/57600 [5:36:24<4:25:04,  1.61it/s]
 56%|█████▌    | 32029/57600 [5:36:25<4:22:09,  1.63it/s]
 56%|█████▌    | 32030/57600 [5:36:26<4:31:39,  1.57it/s]
 56%|█████▌    | 32031/57600 [5:36:26<4:32:21,  1.56it/s]
 56%|█████▌    | 32032/57600 [5:36:27<4:22:25,  1.62it/s]
 56%|█████▌    | 32033/57600 [5:36:27<4:16:10,  1.66it/s]
 56%|█████▌    | 32034/57600 [5:36:28<4:09:43,  1.71it/s]
 56%|█████▌    | 32035/57600 [5:36:29<4:22:33,  1.62it/s]
 56%|█████▌    | 32036/57600 [5:36:29<4:18:12,  1.65it/s]
 56%|█████▌    | 32037/57600 [5:36:30<4:17:36,  1.65it/s]
 56%|█████▌    | 32038/57600 [5:36:30<4:15:52,  1.66it/s]
 56%|█████▌    | 32039/57600 [5:36:31<4:24:18,  1.61it/s]
 56%|█████▌    | 32040/57600 [5:36:32<4:38:51,  1.53it/s]
                                                         
{'loss': 1.1763, 'learning_rate': 5.007665505226481e-07, 'epoch': 353.64}

 56%|█████▌    | 32040/57600 [5:36:32<4:38:51,  1.53it/s]
 56%|█████▌    | 32041/57600 [5:36:32<4:29:14,  1.58it/s]
 56%|█████▌    | 32042/57600 [5:36:33<4:26:11,  1.60it/s]
 56%|█████▌    | 32043/57600 [5:36:34<4:18:46,  1.65it/s]
 56%|█████▌    | 32044/57600 [5:36:34<4:20:12,  1.64it/s]
 56%|█████▌    | 32045/57600 [5:36:35<4:20:16,  1.64it/s]
 56%|█████▌    | 32046/57600 [5:36:35<4:28:36,  1.59it/s]
 56%|█████▌    | 32047/57600 [5:36:36<4:30:34,  1.57it/s]
 56%|█████▌    | 32048/57600 [5:36:37<4:31:06,  1.57it/s]
 56%|█████▌    | 32049/57600 [5:36:37<4:23:49,  1.61it/s]
 56%|█████▌    | 32050/57600 [5:36:38<4:26:03,  1.60it/s]
 56%|█████▌    | 32051/57600 [5:36:39<4:26:32,  1.60it/s]
 56%|█████▌    | 32052/57600 [5:36:39<4:24:40,  1.61it/s]
 56%|█████▌    | 32053/57600 [5:36:40<4:24:40,  1.61it/s]
 56%|█████▌    | 32054/57600 [5:36:40<4:20:40,  1.63it/s]
 56%|█████▌    | 32055/57600 [5:36:41<4:26:09,  1.60it/s]
 56%|█████▌    | 32056/57600 [5:36:42<4:27:05,  1.59it/s]
 56%|█████▌    | 32057/57600 [5:36:42<4:24:05,  1.61it/s]
 56%|█████▌    | 32058/57600 [5:36:43<4:16:58,  1.66it/s]
 56%|█████▌    | 32059/57600 [5:36:43<4:14:33,  1.67it/s]
 56%|█████▌    | 32060/57600 [5:36:44<4:22:38,  1.62it/s]
                                                         
{'loss': 1.216, 'learning_rate': 5.004529616724738e-07, 'epoch': 353.86}

 56%|█████▌    | 32060/57600 [5:36:44<4:22:38,  1.62it/s]
 56%|█████▌    | 32061/57600 [5:36:45<4:24:18,  1.61it/s]
 56%|█████▌    | 32062/57600 [5:36:45<4:32:35,  1.56it/s]
 56%|█████▌    | 32063/57600 [5:36:46<4:41:38,  1.51it/s]
 56%|█████▌    | 32064/57600 [5:36:47<4:34:31,  1.55it/s]
 56%|█████▌    | 32065/57600 [5:36:47<4:28:38,  1.58it/s]
 56%|█████▌    | 32066/57600 [5:36:48<4:27:18,  1.59it/s]
 56%|█████▌    | 32067/57600 [5:36:49<4:30:29,  1.57it/s]
 56%|█████▌    | 32068/57600 [5:36:49<4:22:46,  1.62it/s]
 56%|█████▌    | 32069/57600 [5:36:50<4:25:06,  1.61it/s]
 56%|█████▌    | 32070/57600 [5:36:50<4:26:14,  1.60it/s]
 56%|█████▌    | 32071/57600 [5:36:51<4:21:19,  1.63it/s]
 56%|█████▌    | 32072/57600 [5:36:52<4:20:45,  1.63it/s]
 56%|█████▌    | 32073/57600 [5:36:52<4:33:34,  1.56it/s]
 56%|█████▌    | 32074/57600 [5:36:53<4:31:52,  1.56it/s]
 56%|█████▌    | 32075/57600 [5:36:54<4:40:06,  1.52it/s]
 56%|█████▌    | 32076/57600 [5:36:54<4:31:26,  1.57it/s]
 56%|█████▌    | 32077/57600 [5:36:55<4:34:05,  1.55it/s]
 56%|█████▌    | 32078/57600 [5:36:56<4:27:36,  1.59it/s]
 56%|█████▌    | 32079/57600 [5:36:56<4:27:49,  1.59it/s]
 56%|█████▌    | 32080/57600 [5:36:57<4:27:31,  1.59it/s]
                                                         
{'loss': 1.1665, 'learning_rate': 5.001393728222996e-07, 'epoch': 354.08}

 56%|█████▌    | 32080/57600 [5:36:57<4:27:31,  1.59it/s]
 56%|█████▌    | 32081/57600 [5:36:57<4:30:48,  1.57it/s]
 56%|█████▌    | 32082/57600 [5:36:58<4:32:06,  1.56it/s]
 56%|█████▌    | 32083/57600 [5:36:59<4:27:35,  1.59it/s]
 56%|█████▌    | 32084/57600 [5:36:59<4:28:37,  1.58it/s]
 56%|█████▌    | 32085/57600 [5:37:00<4:30:44,  1.57it/s]
 56%|█████▌    | 32086/57600 [5:37:01<4:24:24,  1.61it/s]
 56%|█████▌    | 32087/57600 [5:37:01<4:17:54,  1.65it/s]
 56%|█████▌    | 32088/57600 [5:37:02<4:28:19,  1.58it/s]
 56%|█████▌    | 32089/57600 [5:37:02<4:23:59,  1.61it/s]
 56%|█████▌    | 32090/57600 [5:37:03<4:18:35,  1.64it/s]
 56%|█████▌    | 32091/57600 [5:37:04<4:21:49,  1.62it/s]
 56%|█████▌    | 32092/57600 [5:37:04<4:24:12,  1.61it/s]
 56%|█████▌    | 32093/57600 [5:37:05<4:16:54,  1.65it/s]
 56%|█████▌    | 32094/57600 [5:37:06<4:18:57,  1.64it/s]
 56%|█████▌    | 32095/57600 [5:37:06<4:29:19,  1.58it/s]
 56%|█████▌    | 32096/57600 [5:37:07<4:26:36,  1.59it/s]
 56%|█████▌    | 32097/57600 [5:37:07<4:28:45,  1.58it/s]
 56%|█████▌    | 32098/57600 [5:37:08<4:27:18,  1.59it/s]
 56%|█████▌    | 32099/57600 [5:37:09<4:23:29,  1.61it/s]
 56%|█████▌    | 32100/57600 [5:37:09<4:27:13,  1.59it/s]
                                                         
{'loss': 1.1589, 'learning_rate': 4.998257839721254e-07, 'epoch': 354.3}

 56%|█████▌    | 32100/57600 [5:37:09<4:27:13,  1.59it/s]
 56%|█████▌    | 32101/57600 [5:37:10<4:33:12,  1.56it/s]
 56%|█████▌    | 32102/57600 [5:37:11<4:24:09,  1.61it/s]
 56%|█████▌    | 32103/57600 [5:37:11<4:30:47,  1.57it/s]
 56%|█████▌    | 32104/57600 [5:37:12<4:25:40,  1.60it/s]
 56%|█████▌    | 32105/57600 [5:37:13<4:43:39,  1.50it/s]
 56%|█████▌    | 32106/57600 [5:37:13<4:42:04,  1.51it/s]
 56%|█████▌    | 32107/57600 [5:37:14<4:30:59,  1.57it/s]
 56%|█████▌    | 32108/57600 [5:37:14<4:25:43,  1.60it/s]
 56%|█████▌    | 32109/57600 [5:37:15<4:19:36,  1.64it/s]
 56%|█████▌    | 32110/57600 [5:37:16<4:17:43,  1.65it/s]
 56%|█████▌    | 32111/57600 [5:37:16<4:21:07,  1.63it/s]
 56%|█████▌    | 32112/57600 [5:37:17<4:19:30,  1.64it/s]
 56%|█████▌    | 32113/57600 [5:37:18<4:34:01,  1.55it/s]
 56%|█████▌    | 32114/57600 [5:37:18<4:36:54,  1.53it/s]
 56%|█████▌    | 32115/57600 [5:37:19<4:29:35,  1.58it/s]
 56%|█████▌    | 32116/57600 [5:37:19<4:28:16,  1.58it/s]
 56%|█████▌    | 32117/57600 [5:37:20<4:21:15,  1.63it/s]
 56%|█████▌    | 32118/57600 [5:37:21<4:18:52,  1.64it/s]
 56%|█████▌    | 32119/57600 [5:37:21<4:21:25,  1.62it/s]
 56%|█████▌    | 32120/57600 [5:37:22<4:33:40,  1.55it/s]
                                                         
{'loss': 1.1646, 'learning_rate': 4.995121951219512e-07, 'epoch': 354.53}

 56%|█████▌    | 32120/57600 [5:37:22<4:33:40,  1.55it/s]
 56%|█████▌    | 32121/57600 [5:37:23<4:26:45,  1.59it/s]
 56%|█████▌    | 32122/57600 [5:37:23<4:31:44,  1.56it/s]
 56%|█████▌    | 32123/57600 [5:37:24<4:34:58,  1.54it/s]
 56%|█████▌    | 32124/57600 [5:37:25<4:40:31,  1.51it/s]
 56%|█████▌    | 32125/57600 [5:37:25<4:32:26,  1.56it/s]
 56%|█████▌    | 32126/57600 [5:37:26<4:30:31,  1.57it/s]
 56%|█████▌    | 32127/57600 [5:37:26<4:34:46,  1.55it/s]
 56%|█████▌    | 32128/57600 [5:37:27<4:31:28,  1.56it/s]
 56%|█████▌    | 32129/57600 [5:37:28<4:41:59,  1.51it/s]
 56%|█████▌    | 32130/57600 [5:37:29<4:44:38,  1.49it/s]
 56%|█████▌    | 32131/57600 [5:37:29<4:35:58,  1.54it/s]
 56%|█████▌    | 32132/57600 [5:37:30<4:29:37,  1.57it/s]
 56%|█████▌    | 32133/57600 [5:37:30<4:34:19,  1.55it/s]
 56%|█████▌    | 32134/57600 [5:37:31<4:27:30,  1.59it/s]
 56%|█████▌    | 32135/57600 [5:37:32<4:33:32,  1.55it/s]
 56%|█████▌    | 32136/57600 [5:37:32<4:35:33,  1.54it/s]
 56%|█████▌    | 32137/57600 [5:37:33<4:31:21,  1.56it/s]
 56%|█████▌    | 32138/57600 [5:37:34<4:32:22,  1.56it/s]
 56%|█████▌    | 32139/57600 [5:37:34<4:24:02,  1.61it/s]
 56%|█████▌    | 32140/57600 [5:37:35<4:27:13,  1.59it/s]
                                                         
{'loss': 1.1749, 'learning_rate': 4.991986062717769e-07, 'epoch': 354.75}

 56%|█████▌    | 32140/57600 [5:37:35<4:27:13,  1.59it/s]
 56%|█████▌    | 32141/57600 [5:37:35<4:21:20,  1.62it/s]
 56%|█████▌    | 32142/57600 [5:37:36<4:22:20,  1.62it/s]
 56%|█████▌    | 32143/57600 [5:37:37<4:16:24,  1.65it/s]
 56%|█████▌    | 32144/57600 [5:37:37<4:13:45,  1.67it/s]
 56%|█████▌    | 32145/57600 [5:37:38<4:12:44,  1.68it/s]
 56%|█████▌    | 32146/57600 [5:37:38<4:12:32,  1.68it/s]
 56%|█████▌    | 32147/57600 [5:37:39<4:11:35,  1.69it/s]
 56%|█████▌    | 32148/57600 [5:37:39<4:07:33,  1.71it/s]
 56%|█████▌    | 32149/57600 [5:37:40<4:10:17,  1.69it/s]
 56%|█████▌    | 32150/57600 [5:37:41<4:08:19,  1.71it/s]
 56%|█████▌    | 32151/57600 [5:37:41<4:09:01,  1.70it/s]
 56%|█████▌    | 32152/57600 [5:37:42<4:06:39,  1.72it/s]
 56%|█████▌    | 32153/57600 [5:37:42<4:11:44,  1.68it/s]
 56%|█████▌    | 32154/57600 [5:37:43<4:08:04,  1.71it/s]
 56%|█████▌    | 32155/57600 [5:37:44<4:09:17,  1.70it/s]
 56%|█████▌    | 32156/57600 [5:37:44<4:09:46,  1.70it/s]
 56%|█████▌    | 32157/57600 [5:37:45<4:04:12,  1.74it/s]
 56%|█████▌    | 32158/57600 [5:37:45<4:12:09,  1.68it/s]
 56%|█████▌    | 32159/57600 [5:37:46<4:14:30,  1.67it/s]
 56%|█████▌    | 32160/57600 [5:37:47<4:23:01,  1.61it/s]
                                                         
{'loss': 1.2224, 'learning_rate': 4.988850174216028e-07, 'epoch': 354.97}

 56%|█████▌    | 32160/57600 [5:37:47<4:23:01,  1.61it/s]
 56%|█████▌    | 32161/57600 [5:37:47<4:28:00,  1.58it/s]
 56%|█████▌    | 32162/57600 [5:37:48<4:29:19,  1.57it/s]
 56%|█████▌    | 32163/57600 [5:37:49<4:31:10,  1.56it/s]
 56%|█████▌    | 32164/57600 [5:37:49<4:39:05,  1.52it/s]
 56%|█████▌    | 32165/57600 [5:37:50<4:36:58,  1.53it/s]
 56%|█████▌    | 32166/57600 [5:37:51<4:38:33,  1.52it/s]
 56%|█████▌    | 32167/57600 [5:37:51<4:38:07,  1.52it/s]
 56%|█████▌    | 32168/57600 [5:37:52<4:32:23,  1.56it/s]
 56%|█████▌    | 32169/57600 [5:37:53<4:27:28,  1.58it/s]
 56%|█████▌    | 32170/57600 [5:37:53<4:31:22,  1.56it/s]
 56%|█████▌    | 32171/57600 [5:37:54<4:34:41,  1.54it/s]
 56%|█████▌    | 32172/57600 [5:37:54<4:34:27,  1.54it/s]
 56%|█████▌    | 32173/57600 [5:37:55<4:31:13,  1.56it/s]
 56%|█████▌    | 32174/57600 [5:37:56<4:39:07,  1.52it/s]
 56%|█████▌    | 32175/57600 [5:37:56<4:34:15,  1.55it/s]
 56%|█████▌    | 32176/57600 [5:37:57<4:37:00,  1.53it/s]
 56%|█████▌    | 32177/57600 [5:37:58<4:35:01,  1.54it/s]
 56%|█████▌    | 32178/57600 [5:37:58<4:29:50,  1.57it/s]
 56%|█████▌    | 32179/57600 [5:37:59<4:27:07,  1.59it/s]
 56%|█████▌    | 32180/57600 [5:38:00<4:23:42,  1.61it/s]
                                                         
{'loss': 1.1945, 'learning_rate': 4.985714285714285e-07, 'epoch': 355.19}

 56%|█████▌    | 32180/57600 [5:38:00<4:23:42,  1.61it/s]
 56%|█████▌    | 32181/57600 [5:38:00<4:29:54,  1.57it/s]
 56%|█████▌    | 32182/57600 [5:38:01<4:36:35,  1.53it/s]
 56%|█████▌    | 32183/57600 [5:38:02<4:30:15,  1.57it/s]
 56%|█████▌    | 32184/57600 [5:38:02<4:24:48,  1.60it/s]
 56%|█████▌    | 32185/57600 [5:38:03<4:29:29,  1.57it/s]
 56%|█████▌    | 32186/57600 [5:38:03<4:22:14,  1.62it/s]
 56%|█████▌    | 32187/57600 [5:38:04<4:20:48,  1.62it/s]
 56%|█████▌    | 32188/57600 [5:38:05<4:14:46,  1.66it/s]
 56%|█████▌    | 32189/57600 [5:38:05<4:19:18,  1.63it/s]
 56%|█████▌    | 32190/57600 [5:38:06<4:12:47,  1.68it/s]
 56%|█████▌    | 32191/57600 [5:38:06<4:22:18,  1.61it/s]
 56%|█████▌    | 32192/57600 [5:38:07<4:19:02,  1.63it/s]
 56%|█████▌    | 32193/57600 [5:38:08<4:15:00,  1.66it/s]
 56%|█████▌    | 32194/57600 [5:38:08<4:10:50,  1.69it/s]
 56%|█████▌    | 32195/57600 [5:38:09<4:19:27,  1.63it/s]
 56%|█████▌    | 32196/57600 [5:38:09<4:22:22,  1.61it/s]
 56%|█████▌    | 32197/57600 [5:38:10<4:24:57,  1.60it/s]
 56%|█████▌    | 32198/57600 [5:38:11<4:27:04,  1.59it/s]
 56%|█████▌    | 32199/57600 [5:38:11<4:17:35,  1.64it/s]
 56%|█████▌    | 32200/57600 [5:38:12<4:29:21,  1.57it/s]
                                                         
{'loss': 1.1612, 'learning_rate': 4.982578397212543e-07, 'epoch': 355.41}

 56%|█████▌    | 32200/57600 [5:38:12<4:29:21,  1.57it/s]
 56%|█████▌    | 32201/57600 [5:38:13<4:30:43,  1.56it/s]
 56%|█████▌    | 32202/57600 [5:38:13<4:26:23,  1.59it/s]
 56%|█████▌    | 32203/57600 [5:38:14<4:21:32,  1.62it/s]
 56%|█████▌    | 32204/57600 [5:38:14<4:22:13,  1.61it/s]
 56%|█████▌    | 32205/57600 [5:38:15<4:19:38,  1.63it/s]
 56%|█████▌    | 32206/57600 [5:38:16<4:15:10,  1.66it/s]
 56%|█████▌    | 32207/57600 [5:38:16<4:15:20,  1.66it/s]
 56%|█████▌    | 32208/57600 [5:38:17<4:24:57,  1.60it/s]
 56%|█████▌    | 32209/57600 [5:38:18<4:24:52,  1.60it/s]
 56%|█████▌    | 32210/57600 [5:38:18<4:30:37,  1.56it/s]
 56%|█████▌    | 32211/57600 [5:38:19<4:22:18,  1.61it/s]
 56%|█████▌    | 32212/57600 [5:38:19<4:25:55,  1.59it/s]
 56%|█████▌    | 32213/57600 [5:38:20<4:24:55,  1.60it/s]
 56%|█████▌    | 32214/57600 [5:38:21<4:25:03,  1.60it/s]
 56%|█████▌    | 32215/57600 [5:38:21<4:26:42,  1.59it/s]
 56%|█████▌    | 32216/57600 [5:38:22<4:29:50,  1.57it/s]
 56%|█████▌    | 32217/57600 [5:38:23<4:32:42,  1.55it/s]
 56%|█████▌    | 32218/57600 [5:38:23<4:24:33,  1.60it/s]
 56%|█████▌    | 32219/57600 [5:38:24<4:23:50,  1.60it/s]
 56%|█████▌    | 32220/57600 [5:38:24<4:20:40,  1.62it/s]
                                                         
{'loss': 1.156, 'learning_rate': 4.979442508710801e-07, 'epoch': 355.63}

 56%|█████▌    | 32220/57600 [5:38:24<4:20:40,  1.62it/s]
 56%|█████▌    | 32221/57600 [5:38:25<4:19:59,  1.63it/s]
 56%|█████▌    | 32222/57600 [5:38:26<4:25:28,  1.59it/s]
 56%|█████▌    | 32223/57600 [5:38:26<4:28:39,  1.57it/s]
 56%|█████▌    | 32224/57600 [5:38:27<4:31:25,  1.56it/s]
 56%|█████▌    | 32225/57600 [5:38:28<4:23:55,  1.60it/s]
 56%|█████▌    | 32226/57600 [5:38:28<4:23:34,  1.60it/s]
 56%|█████▌    | 32227/57600 [5:38:29<4:31:09,  1.56it/s]
 56%|█████▌    | 32228/57600 [5:38:30<4:36:27,  1.53it/s]
 56%|█████▌    | 32229/57600 [5:38:30<4:40:58,  1.50it/s]
 56%|█████▌    | 32230/57600 [5:38:31<4:30:10,  1.57it/s]
 56%|█████▌    | 32231/57600 [5:38:31<4:26:41,  1.59it/s]
 56%|█████▌    | 32232/57600 [5:38:32<4:23:27,  1.60it/s]
 56%|█████▌    | 32233/57600 [5:38:33<4:19:15,  1.63it/s]
 56%|█████▌    | 32234/57600 [5:38:33<4:22:02,  1.61it/s]
 56%|█████▌    | 32235/57600 [5:38:34<4:18:28,  1.64it/s]
 56%|█████▌    | 32236/57600 [5:38:34<4:17:19,  1.64it/s]
 56%|█████▌    | 32237/57600 [5:38:35<4:13:10,  1.67it/s]
 56%|█████▌    | 32238/57600 [5:38:36<4:17:57,  1.64it/s]
 56%|█████▌    | 32239/57600 [5:38:36<4:21:34,  1.62it/s]
 56%|█████▌    | 32240/57600 [5:38:37<4:21:07,  1.62it/s]
                                                         
{'loss': 1.2042, 'learning_rate': 4.976306620209059e-07, 'epoch': 355.85}

 56%|█████▌    | 32240/57600 [5:38:37<4:21:07,  1.62it/s]
 56%|█████▌    | 32241/57600 [5:38:38<4:15:31,  1.65it/s]
 56%|█████▌    | 32242/57600 [5:38:38<4:10:11,  1.69it/s]
 56%|█████▌    | 32243/57600 [5:38:39<4:12:34,  1.67it/s]
 56%|█████▌    | 32244/57600 [5:38:39<4:15:46,  1.65it/s]
 56%|█████▌    | 32245/57600 [5:38:40<4:11:13,  1.68it/s]
 56%|█████▌    | 32246/57600 [5:38:40<4:09:35,  1.69it/s]
 56%|█████▌    | 32247/57600 [5:38:41<4:24:43,  1.60it/s]
 56%|█████▌    | 32248/57600 [5:38:42<4:24:09,  1.60it/s]
 56%|█████▌    | 32249/57600 [5:38:42<4:28:39,  1.57it/s]
 56%|█████▌    | 32250/57600 [5:38:43<4:26:18,  1.59it/s]
 56%|█████▌    | 32251/57600 [5:38:44<4:20:40,  1.62it/s]
 56%|█████▌    | 32252/57600 [5:38:45<5:39:48,  1.24it/s]
 56%|█████▌    | 32253/57600 [5:38:45<5:09:34,  1.36it/s]
 56%|█████▌    | 32254/57600 [5:38:46<5:09:33,  1.36it/s]
 56%|█████▌    | 32255/57600 [5:38:47<4:50:16,  1.46it/s]
 56%|█████▌    | 32256/57600 [5:38:47<4:37:57,  1.52it/s]
 56%|█████▌    | 32257/57600 [5:38:48<4:32:33,  1.55it/s]
 56%|█████▌    | 32258/57600 [5:38:49<4:28:44,  1.57it/s]
 56%|█████▌    | 32259/57600 [5:38:49<4:24:39,  1.60it/s]
 56%|█████▌    | 32260/57600 [5:38:50<4:17:49,  1.64it/s]
                                                         
{'loss': 1.1951, 'learning_rate': 4.973170731707316e-07, 'epoch': 356.07}

 56%|█████▌    | 32260/57600 [5:38:50<4:17:49,  1.64it/s]
 56%|█████▌    | 32261/57600 [5:38:50<4:18:26,  1.63it/s]
 56%|█████▌    | 32262/57600 [5:38:51<4:17:11,  1.64it/s]
 56%|█████▌    | 32263/57600 [5:38:52<4:18:12,  1.64it/s]
 56%|█████▌    | 32264/57600 [5:38:52<4:28:21,  1.57it/s]
 56%|█████▌    | 32265/57600 [5:38:53<4:20:15,  1.62it/s]
 56%|█████▌    | 32266/57600 [5:38:53<4:15:17,  1.65it/s]
 56%|█████▌    | 32267/57600 [5:38:54<4:18:30,  1.63it/s]
 56%|█████▌    | 32268/57600 [5:38:55<4:24:02,  1.60it/s]
 56%|█████▌    | 32269/57600 [5:38:55<4:24:03,  1.60it/s]
 56%|█████▌    | 32270/57600 [5:38:56<4:20:43,  1.62it/s]
 56%|█████▌    | 32271/57600 [5:38:57<4:19:04,  1.63it/s]
 56%|█████▌    | 32272/57600 [5:38:57<4:20:27,  1.62it/s]
 56%|█████▌    | 32273/57600 [5:38:58<4:27:53,  1.58it/s]
 56%|█████▌    | 32274/57600 [5:38:59<4:27:32,  1.58it/s]
 56%|█████▌    | 32275/57600 [5:38:59<4:21:44,  1.61it/s]
 56%|█████▌    | 32276/57600 [5:39:00<4:20:11,  1.62it/s]
 56%|█████▌    | 32277/57600 [5:39:00<4:20:47,  1.62it/s]
 56%|█████▌    | 32278/57600 [5:39:01<4:29:57,  1.56it/s]
 56%|█████▌    | 32279/57600 [5:39:02<4:30:20,  1.56it/s]
 56%|█████▌    | 32280/57600 [5:39:02<4:28:00,  1.57it/s]
                                                         
{'loss': 1.1731, 'learning_rate': 4.970034843205575e-07, 'epoch': 356.29}

 56%|█████▌    | 32280/57600 [5:39:02<4:28:00,  1.57it/s]
 56%|█████▌    | 32281/57600 [5:39:03<4:21:17,  1.62it/s]
 56%|█████▌    | 32282/57600 [5:39:04<4:23:41,  1.60it/s]
 56%|█████▌    | 32283/57600 [5:39:04<4:31:43,  1.55it/s]
 56%|█████▌    | 32284/57600 [5:39:05<4:44:21,  1.48it/s]
 56%|█████▌    | 32285/57600 [5:39:06<4:42:09,  1.50it/s]
 56%|█████▌    | 32286/57600 [5:39:06<4:46:45,  1.47it/s]
 56%|█████▌    | 32287/57600 [5:39:07<4:35:12,  1.53it/s]
 56%|█████▌    | 32288/57600 [5:39:08<4:38:43,  1.51it/s]
 56%|█████▌    | 32289/57600 [5:39:08<4:30:10,  1.56it/s]
 56%|█████▌    | 32290/57600 [5:39:09<4:30:09,  1.56it/s]
 56%|█████▌    | 32291/57600 [5:39:09<4:25:47,  1.59it/s]
 56%|█████▌    | 32292/57600 [5:39:10<4:15:49,  1.65it/s]
 56%|█████▌    | 32293/57600 [5:39:11<4:14:39,  1.66it/s]
 56%|█████▌    | 32294/57600 [5:39:11<4:10:33,  1.68it/s]
 56%|█████▌    | 32295/57600 [5:39:12<4:24:22,  1.60it/s]
 56%|█████▌    | 32296/57600 [5:39:12<4:26:22,  1.58it/s]
 56%|█████▌    | 32297/57600 [5:39:13<4:34:13,  1.54it/s]
 56%|█████▌    | 32298/57600 [5:39:14<4:23:36,  1.60it/s]
 56%|█████▌    | 32299/57600 [5:39:14<4:24:57,  1.59it/s]
 56%|█████▌    | 32300/57600 [5:39:15<4:21:13,  1.61it/s]
                                                         
{'loss': 1.1627, 'learning_rate': 4.966898954703834e-07, 'epoch': 356.51}

 56%|█████▌    | 32300/57600 [5:39:15<4:21:13,  1.61it/s]
 56%|█████▌    | 32301/57600 [5:39:16<4:17:43,  1.64it/s]
 56%|█████▌    | 32302/57600 [5:39:16<4:22:36,  1.61it/s]
 56%|█████▌    | 32303/57600 [5:39:17<4:18:07,  1.63it/s]
 56%|█████▌    | 32304/57600 [5:39:17<4:25:22,  1.59it/s]
 56%|█████▌    | 32305/57600 [5:39:18<4:27:27,  1.58it/s]
 56%|█████▌    | 32306/57600 [5:39:19<4:24:05,  1.60it/s]
 56%|█████▌    | 32307/57600 [5:39:19<4:27:31,  1.58it/s]
 56%|█████▌    | 32308/57600 [5:39:20<4:25:08,  1.59it/s]
 56%|█████▌    | 32309/57600 [5:39:21<4:34:06,  1.54it/s]
 56%|█████▌    | 32310/57600 [5:39:21<4:26:12,  1.58it/s]
 56%|█████▌    | 32311/57600 [5:39:22<4:28:38,  1.57it/s]
 56%|█████▌    | 32312/57600 [5:39:23<4:27:34,  1.58it/s]
 56%|█████▌    | 32313/57600 [5:39:23<4:24:37,  1.59it/s]
 56%|█████▌    | 32314/57600 [5:39:24<4:23:50,  1.60it/s]
 56%|█████▌    | 32315/57600 [5:39:24<4:23:10,  1.60it/s]
 56%|█████▌    | 32316/57600 [5:39:25<4:20:09,  1.62it/s]
 56%|█████▌    | 32317/57600 [5:39:26<4:25:19,  1.59it/s]
 56%|█████▌    | 32318/57600 [5:39:26<4:34:01,  1.54it/s]
 56%|█████▌    | 32319/57600 [5:39:27<4:32:35,  1.55it/s]
 56%|█████▌    | 32320/57600 [5:39:28<4:27:55,  1.57it/s]
                                                         
{'loss': 1.1532, 'learning_rate': 4.96376306620209e-07, 'epoch': 356.73}

 56%|█████▌    | 32320/57600 [5:39:28<4:27:55,  1.57it/s]
 56%|█████▌    | 32321/57600 [5:39:28<4:25:41,  1.59it/s]
 56%|█████▌    | 32322/57600 [5:39:29<4:20:58,  1.61it/s]
 56%|█████▌    | 32323/57600 [5:39:29<4:18:07,  1.63it/s]
 56%|█████▌    | 32324/57600 [5:39:30<4:20:57,  1.61it/s]
 56%|█████▌    | 32325/57600 [5:39:31<4:27:29,  1.57it/s]
 56%|█████▌    | 32326/57600 [5:39:31<4:23:59,  1.60it/s]
 56%|█████▌    | 32327/57600 [5:39:32<4:19:49,  1.62it/s]
 56%|█████▌    | 32328/57600 [5:39:33<4:25:26,  1.59it/s]
 56%|█████▌    | 32329/57600 [5:39:33<4:23:43,  1.60it/s]
 56%|█████▌    | 32330/57600 [5:39:34<4:26:37,  1.58it/s]
 56%|█████▌    | 32331/57600 [5:39:34<4:26:38,  1.58it/s]
 56%|█████▌    | 32332/57600 [5:39:35<4:24:57,  1.59it/s]
 56%|█████▌    | 32333/57600 [5:39:36<4:16:42,  1.64it/s]
 56%|█████▌    | 32334/57600 [5:39:36<4:18:30,  1.63it/s]
 56%|█████▌    | 32335/57600 [5:39:37<4:19:02,  1.63it/s]
 56%|█████▌    | 32336/57600 [5:39:38<4:26:02,  1.58it/s]
 56%|█████▌    | 32337/57600 [5:39:38<4:31:35,  1.55it/s]
 56%|█████▌    | 32338/57600 [5:39:39<4:29:09,  1.56it/s]
 56%|█████▌    | 32339/57600 [5:39:40<4:33:22,  1.54it/s]
 56%|█████▌    | 32340/57600 [5:39:40<4:29:13,  1.56it/s]
                                                         
{'loss': 1.2106, 'learning_rate': 4.960627177700349e-07, 'epoch': 356.95}

 56%|█████▌    | 32340/57600 [5:39:40<4:29:13,  1.56it/s]
 56%|█████▌    | 32341/57600 [5:39:41<4:34:58,  1.53it/s]
 56%|█████▌    | 32342/57600 [5:39:42<4:35:56,  1.53it/s]
 56%|█████▌    | 32343/57600 [5:39:42<4:29:07,  1.56it/s]
 56%|█████▌    | 32344/57600 [5:39:43<4:24:01,  1.59it/s]
 56%|█████▌    | 32345/57600 [5:39:43<4:35:53,  1.53it/s]
 56%|█████▌    | 32346/57600 [5:39:44<4:25:45,  1.58it/s]
 56%|█████▌    | 32347/57600 [5:39:45<4:35:06,  1.53it/s]
 56%|█████▌    | 32348/57600 [5:39:45<4:30:13,  1.56it/s]
 56%|█████▌    | 32349/57600 [5:39:46<4:34:34,  1.53it/s]
 56%|█████▌    | 32350/57600 [5:39:47<4:30:15,  1.56it/s]
 56%|█████▌    | 32351/57600 [5:39:47<4:26:00,  1.58it/s]
 56%|█████▌    | 32352/57600 [5:39:48<4:27:16,  1.57it/s]
 56%|█████▌    | 32353/57600 [5:39:48<4:20:46,  1.61it/s]
 56%|█████▌    | 32354/57600 [5:39:49<4:23:46,  1.60it/s]
 56%|█████▌    | 32355/57600 [5:39:50<4:23:08,  1.60it/s]
 56%|█████▌    | 32356/57600 [5:39:51<4:45:32,  1.47it/s]
 56%|█████▌    | 32357/57600 [5:39:51<4:41:05,  1.50it/s]
 56%|█████▌    | 32358/57600 [5:39:52<4:36:11,  1.52it/s]
 56%|█████▌    | 32359/57600 [5:39:52<4:29:42,  1.56it/s]
 56%|█████▌    | 32360/57600 [5:39:53<4:25:36,  1.58it/s]
                                                         
{'loss': 1.1187, 'learning_rate': 4.957491289198605e-07, 'epoch': 357.17}

 56%|█████▌    | 32360/57600 [5:39:53<4:25:36,  1.58it/s]
 56%|█████▌    | 32361/57600 [5:39:54<4:15:17,  1.65it/s]
 56%|█████▌    | 32362/57600 [5:39:54<4:14:10,  1.65it/s]
 56%|█████▌    | 32363/57600 [5:39:55<4:19:39,  1.62it/s]
 56%|█████▌    | 32364/57600 [5:39:55<4:13:02,  1.66it/s]
 56%|█████▌    | 32365/57600 [5:39:56<4:19:00,  1.62it/s]
 56%|█████▌    | 32366/57600 [5:39:57<4:27:48,  1.57it/s]
 56%|█████▌    | 32367/57600 [5:39:57<4:19:02,  1.62it/s]
 56%|█████▌    | 32368/57600 [5:39:58<4:17:43,  1.63it/s]
 56%|█████▌    | 32369/57600 [5:39:59<4:15:49,  1.64it/s]
 56%|█████▌    | 32370/57600 [5:39:59<4:12:34,  1.66it/s]
 56%|█████▌    | 32371/57600 [5:40:00<4:12:49,  1.66it/s]
 56%|█████▌    | 32372/57600 [5:40:00<4:10:07,  1.68it/s]
 56%|█████▌    | 32373/57600 [5:40:01<4:14:15,  1.65it/s]
 56%|█████▌    | 32374/57600 [5:40:02<4:14:50,  1.65it/s]
 56%|█████▌    | 32375/57600 [5:40:02<4:09:16,  1.69it/s]
 56%|█████▌    | 32376/57600 [5:40:03<4:06:32,  1.71it/s]
 56%|█████▌    | 32377/57600 [5:40:03<4:09:36,  1.68it/s]
 56%|█████▌    | 32378/57600 [5:40:04<4:13:12,  1.66it/s]
 56%|█████▌    | 32379/57600 [5:40:04<4:13:01,  1.66it/s]
 56%|█████▌    | 32380/57600 [5:40:05<4:13:27,  1.66it/s]
                                                         
{'loss': 1.2261, 'learning_rate': 4.954355400696864e-07, 'epoch': 357.4}

 56%|█████▌    | 32380/57600 [5:40:05<4:13:27,  1.66it/s]
 56%|█████▌    | 32381/57600 [5:40:06<4:10:28,  1.68it/s]
 56%|█████▌    | 32382/57600 [5:40:06<4:15:43,  1.64it/s]
 56%|█████▌    | 32383/57600 [5:40:07<4:18:14,  1.63it/s]
 56%|█████▌    | 32384/57600 [5:40:08<4:20:00,  1.62it/s]
 56%|█████▌    | 32385/57600 [5:40:08<4:24:47,  1.59it/s]
 56%|█████▌    | 32386/57600 [5:40:09<4:28:16,  1.57it/s]
 56%|█████▌    | 32387/57600 [5:40:10<4:27:54,  1.57it/s]
 56%|█████▌    | 32388/57600 [5:40:10<4:33:08,  1.54it/s]
 56%|█████▌    | 32389/57600 [5:40:11<4:45:00,  1.47it/s]
 56%|█████▌    | 32390/57600 [5:40:12<4:41:54,  1.49it/s]
 56%|█████▌    | 32391/57600 [5:40:12<4:36:29,  1.52it/s]
 56%|█████▌    | 32392/57600 [5:40:13<4:44:30,  1.48it/s]
 56%|█████▌    | 32393/57600 [5:40:14<4:34:05,  1.53it/s]
 56%|█████▌    | 32394/57600 [5:40:14<4:24:49,  1.59it/s]
 56%|█████▌    | 32395/57600 [5:40:15<4:20:06,  1.62it/s]
 56%|█████▌    | 32396/57600 [5:40:15<4:19:50,  1.62it/s]
 56%|█████▌    | 32397/57600 [5:40:16<4:24:43,  1.59it/s]
 56%|█████▌    | 32398/57600 [5:40:17<4:18:57,  1.62it/s]
 56%|█████▌    | 32399/57600 [5:40:17<4:18:06,  1.63it/s]
 56%|█████▋    | 32400/57600 [5:40:18<4:14:37,  1.65it/s]
                                                         
{'loss': 1.1416, 'learning_rate': 4.951219512195121e-07, 'epoch': 357.62}

 56%|█████▋    | 32400/57600 [5:40:18<4:14:37,  1.65it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.99it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  6.95it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.72it/s]

100%|██████████| 6/6 [00:01<00:00,  3.34it/s]{'score': 45.70224195796069, 'counts': [140, 87, 60, 42], 'totals': [211, 181, 151, 122], 'precisions': [66.35071090047393, 48.06629834254144, 39.735099337748345, 34.42622950819672], 'bp': 1.0, 'sys_len': 211, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 1.9698816537857056, 'eval_bleu': 45.7022, 'eval_gen_len': 8.4333, 'eval_runtime': 3.174, 'eval_samples_per_second': 9.452, 'eval_steps_per_second': 1.89, 'epoch': 357.62}

 56%|█████▋    | 32400/57600 [5:40:21<4:14:37,  1.65it/s]

100%|██████████| 6/6 [00:02<00:00,  3.34it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 12:34:34,271 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 56%|█████▋    | 32401/57600 [5:40:40<48:41:02,  6.96s/it]
 56%|█████▋    | 32402/57600 [5:40:40<35:27:28,  5.07s/it]
 56%|█████▋    | 32403/57600 [5:40:41<26:10:21,  3.74s/it]
 56%|█████▋    | 32404/57600 [5:40:42<19:49:17,  2.83s/it]
 56%|█████▋    | 32405/57600 [5:40:42<15:25:09,  2.20s/it]
 56%|█████▋    | 32406/57600 [5:40:43<12:18:58,  1.76s/it]
 56%|█████▋    | 32407/57600 [5:40:44<10:02:48,  1.44s/it]
 56%|█████▋    | 32408/57600 [5:40:44<8:37:50,  1.23s/it] 
 56%|█████▋    | 32409/57600 [5:40:45<7:24:02,  1.06s/it]
 56%|█████▋    | 32410/57600 [5:40:46<6:30:02,  1.08it/s]
 56%|█████▋    | 32411/57600 [5:40:46<5:57:58,  1.17it/s]
 56%|█████▋    | 32412/57600 [5:40:47<5:29:03,  1.28it/s]
 56%|█████▋    | 32413/57600 [5:40:48<5:05:52,  1.37it/s]
 56%|█████▋    | 32414/57600 [5:40:48<4:53:58,  1.43it/s]
 56%|█████▋    | 32415/57600 [5:40:49<4:47:09,  1.46it/s]
 56%|█████▋    | 32416/57600 [5:40:50<4:48:41,  1.45it/s]
 56%|█████▋    | 32417/57600 [5:40:50<4:38:12,  1.51it/s]
 56%|█████▋    | 32418/57600 [5:40:51<4:45:15,  1.47it/s]
 56%|█████▋    | 32419/57600 [5:40:52<4:44:10,  1.48it/s]
 56%|█████▋    | 32420/57600 [5:40:52<4:37:45,  1.51it/s]
                                                         
{'loss': 1.1481, 'learning_rate': 4.948083623693379e-07, 'epoch': 357.84}

 56%|█████▋    | 32420/57600 [5:40:52<4:37:45,  1.51it/s]
 56%|█████▋    | 32421/57600 [5:40:53<4:30:07,  1.55it/s]
 56%|█████▋    | 32422/57600 [5:40:54<4:37:03,  1.51it/s]
 56%|█████▋    | 32423/57600 [5:40:54<4:29:00,  1.56it/s]
 56%|█████▋    | 32424/57600 [5:40:55<4:35:08,  1.53it/s]
 56%|█████▋    | 32425/57600 [5:40:55<4:38:34,  1.51it/s]
 56%|█████▋    | 32426/57600 [5:40:56<4:39:25,  1.50it/s]
 56%|█████▋    | 32427/57600 [5:40:57<4:49:27,  1.45it/s]
 56%|█████▋    | 32428/57600 [5:40:58<4:40:13,  1.50it/s]
 56%|█████▋    | 32429/57600 [5:40:58<4:44:08,  1.48it/s]
 56%|█████▋    | 32430/57600 [5:40:59<4:37:10,  1.51it/s]
 56%|█████▋    | 32431/57600 [5:40:59<4:29:24,  1.56it/s]
 56%|█████▋    | 32432/57600 [5:41:00<4:26:53,  1.57it/s]
 56%|█████▋    | 32433/57600 [5:41:01<4:29:51,  1.55it/s]
 56%|█████▋    | 32434/57600 [5:41:01<4:36:06,  1.52it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 56%|█████▋    | 32435/57600 [5:41:02<4:56:00,  1.42it/s]
 56%|█████▋    | 32436/57600 [5:41:03<4:51:59,  1.44it/s]
 56%|█████▋    | 32437/57600 [5:41:04<4:50:53,  1.44it/s]
 56%|█████▋    | 32438/57600 [5:41:04<4:49:28,  1.45it/s]
 56%|█████▋    | 32439/57600 [5:41:05<4:48:47,  1.45it/s]
 56%|█████▋    | 32440/57600 [5:41:06<4:53:56,  1.43it/s]
                                                         
{'loss': 1.1564, 'learning_rate': 4.944947735191637e-07, 'epoch': 358.06}

 56%|█████▋    | 32440/57600 [5:41:06<4:53:56,  1.43it/s]
 56%|█████▋    | 32441/57600 [5:41:06<5:00:20,  1.40it/s]
 56%|█████▋    | 32442/57600 [5:41:07<4:48:24,  1.45it/s]
 56%|█████▋    | 32443/57600 [5:41:08<4:44:44,  1.47it/s]
 56%|█████▋    | 32444/57600 [5:41:08<4:39:35,  1.50it/s]
 56%|█████▋    | 32445/57600 [5:41:09<4:39:28,  1.50it/s]
 56%|█████▋    | 32446/57600 [5:41:10<4:40:01,  1.50it/s]
 56%|█████▋    | 32447/57600 [5:41:10<4:37:14,  1.51it/s]
 56%|█████▋    | 32448/57600 [5:41:11<4:37:13,  1.51it/s]
 56%|█████▋    | 32449/57600 [5:41:12<4:35:03,  1.52it/s]
 56%|█████▋    | 32450/57600 [5:41:12<4:28:06,  1.56it/s]
 56%|█████▋    | 32451/57600 [5:41:13<4:30:25,  1.55it/s]
 56%|█████▋    | 32452/57600 [5:41:14<4:30:25,  1.55it/s]
 56%|█████▋    | 32453/57600 [5:41:14<4:37:18,  1.51it/s]
 56%|█████▋    | 32454/57600 [5:41:15<4:41:23,  1.49it/s]
 56%|█████▋    | 32455/57600 [5:41:16<4:43:44,  1.48it/s]
 56%|█████▋    | 32456/57600 [5:41:16<4:41:49,  1.49it/s]
 56%|█████▋    | 32457/57600 [5:41:17<4:37:08,  1.51it/s]
 56%|█████▋    | 32458/57600 [5:41:18<4:32:07,  1.54it/s]
 56%|█████▋    | 32459/57600 [5:41:18<4:29:14,  1.56it/s]
 56%|█████▋    | 32460/57600 [5:41:19<4:29:55,  1.55it/s]
                                                         
{'loss': 1.1771, 'learning_rate': 4.941811846689895e-07, 'epoch': 358.28}

 56%|█████▋    | 32460/57600 [5:41:19<4:29:55,  1.55it/s]
 56%|█████▋    | 32461/57600 [5:41:19<4:29:43,  1.55it/s]
 56%|█████▋    | 32462/57600 [5:41:20<4:37:52,  1.51it/s]
 56%|█████▋    | 32463/57600 [5:41:21<4:46:45,  1.46it/s]
 56%|█████▋    | 32464/57600 [5:41:22<4:46:41,  1.46it/s]
 56%|█████▋    | 32465/57600 [5:41:22<4:45:46,  1.47it/s]
 56%|█████▋    | 32466/57600 [5:41:23<4:38:26,  1.50it/s]
 56%|█████▋    | 32467/57600 [5:41:24<4:38:04,  1.51it/s]
 56%|█████▋    | 32468/57600 [5:41:24<4:27:57,  1.56it/s]
 56%|█████▋    | 32469/57600 [5:41:25<4:29:47,  1.55it/s]
 56%|█████▋    | 32470/57600 [5:41:25<4:33:15,  1.53it/s]
 56%|█████▋    | 32471/57600 [5:41:26<4:24:01,  1.59it/s]
 56%|█████▋    | 32472/57600 [5:41:27<4:28:01,  1.56it/s]
 56%|█████▋    | 32473/57600 [5:41:27<4:32:00,  1.54it/s]
 56%|█████▋    | 32474/57600 [5:41:28<4:30:49,  1.55it/s]
 56%|█████▋    | 32475/57600 [5:41:29<4:37:39,  1.51it/s]
 56%|█████▋    | 32476/57600 [5:41:29<4:36:24,  1.51it/s]
 56%|█████▋    | 32477/57600 [5:41:30<4:29:28,  1.55it/s]
 56%|█████▋    | 32478/57600 [5:41:31<4:19:12,  1.62it/s]
 56%|█████▋    | 32479/57600 [5:41:31<4:20:48,  1.61it/s]
 56%|█████▋    | 32480/57600 [5:41:32<4:27:18,  1.57it/s]
                                                         
{'loss': 1.1402, 'learning_rate': 4.938675958188153e-07, 'epoch': 358.5}

 56%|█████▋    | 32480/57600 [5:41:32<4:27:18,  1.57it/s]
 56%|█████▋    | 32481/57600 [5:41:33<4:29:41,  1.55it/s]
 56%|█████▋    | 32482/57600 [5:41:33<4:25:21,  1.58it/s]
 56%|█████▋    | 32483/57600 [5:41:34<4:24:17,  1.58it/s]
 56%|█████▋    | 32484/57600 [5:41:34<4:21:39,  1.60it/s]
 56%|█████▋    | 32485/57600 [5:41:35<4:14:43,  1.64it/s]
 56%|█████▋    | 32486/57600 [5:41:36<4:21:48,  1.60it/s]
 56%|█████▋    | 32487/57600 [5:41:36<4:25:50,  1.57it/s]
 56%|█████▋    | 32488/57600 [5:41:37<4:36:03,  1.52it/s]
 56%|█████▋    | 32489/57600 [5:41:38<4:39:04,  1.50it/s]
 56%|█████▋    | 32490/57600 [5:41:38<4:41:52,  1.48it/s]
 56%|█████▋    | 32491/57600 [5:41:39<4:39:23,  1.50it/s]
 56%|█████▋    | 32492/57600 [5:41:40<4:31:54,  1.54it/s]
 56%|█████▋    | 32493/57600 [5:41:40<4:26:46,  1.57it/s]
 56%|█████▋    | 32494/57600 [5:41:41<4:26:14,  1.57it/s]
 56%|█████▋    | 32495/57600 [5:41:41<4:22:34,  1.59it/s]
 56%|█████▋    | 32496/57600 [5:41:42<4:28:28,  1.56it/s]
 56%|█████▋    | 32497/57600 [5:41:43<4:18:32,  1.62it/s]
 56%|█████▋    | 32498/57600 [5:41:43<4:16:33,  1.63it/s]
 56%|█████▋    | 32499/57600 [5:41:44<4:25:18,  1.58it/s]
 56%|█████▋    | 32500/57600 [5:41:45<4:39:21,  1.50it/s]
                                                         
{'loss': 1.1897, 'learning_rate': 4.935540069686411e-07, 'epoch': 358.72}

 56%|█████▋    | 32500/57600 [5:41:45<4:39:21,  1.50it/s]
 56%|█████▋    | 32501/57600 [5:41:45<4:38:56,  1.50it/s]
 56%|█████▋    | 32502/57600 [5:41:46<4:36:23,  1.51it/s]
 56%|█████▋    | 32503/57600 [5:41:47<4:29:35,  1.55it/s]
 56%|█████▋    | 32504/57600 [5:41:47<4:30:29,  1.55it/s]
 56%|█████▋    | 32505/57600 [5:41:48<4:49:18,  1.45it/s]
 56%|█████▋    | 32506/57600 [5:41:49<4:50:30,  1.44it/s]
 56%|█████▋    | 32507/57600 [5:41:49<4:47:01,  1.46it/s]
 56%|█████▋    | 32508/57600 [5:41:50<4:44:50,  1.47it/s]
 56%|█████▋    | 32509/57600 [5:41:51<4:48:37,  1.45it/s]
 56%|█████▋    | 32510/57600 [5:41:52<4:47:31,  1.45it/s]
 56%|█████▋    | 32511/57600 [5:41:52<4:41:38,  1.48it/s]
 56%|█████▋    | 32512/57600 [5:41:53<4:34:17,  1.52it/s]
 56%|█████▋    | 32513/57600 [5:41:53<4:27:43,  1.56it/s]
 56%|█████▋    | 32514/57600 [5:41:54<4:23:47,  1.58it/s]
 56%|█████▋    | 32515/57600 [5:41:55<4:21:16,  1.60it/s]
 56%|█████▋    | 32516/57600 [5:41:55<4:26:29,  1.57it/s]
 56%|█████▋    | 32517/57600 [5:41:56<4:20:22,  1.61it/s]
 56%|█████▋    | 32518/57600 [5:41:56<4:14:36,  1.64it/s]
 56%|█████▋    | 32519/57600 [5:41:57<4:10:23,  1.67it/s]
 56%|█████▋    | 32520/57600 [5:41:58<4:30:42,  1.54it/s]
                                                         
{'loss': 1.2065, 'learning_rate': 4.93240418118467e-07, 'epoch': 358.94}

 56%|█████▋    | 32520/57600 [5:41:58<4:30:42,  1.54it/s]
 56%|█████▋    | 32521/57600 [5:41:58<4:36:54,  1.51it/s]
 56%|█████▋    | 32522/57600 [5:41:59<4:41:54,  1.48it/s]
 56%|█████▋    | 32523/57600 [5:42:00<4:38:41,  1.50it/s]
 56%|█████▋    | 32524/57600 [5:42:00<4:38:45,  1.50it/s]
 56%|█████▋    | 32525/57600 [5:42:01<4:30:35,  1.54it/s]
 56%|█████▋    | 32526/57600 [5:42:02<4:42:21,  1.48it/s]
 56%|█████▋    | 32527/57600 [5:42:03<4:43:35,  1.47it/s]
 56%|█████▋    | 32528/57600 [5:42:03<4:38:18,  1.50it/s]
 56%|█████▋    | 32529/57600 [5:42:04<4:36:33,  1.51it/s]
 56%|█████▋    | 32530/57600 [5:42:04<4:24:44,  1.58it/s]
 56%|█████▋    | 32531/57600 [5:42:05<4:29:47,  1.55it/s]
 56%|█████▋    | 32532/57600 [5:42:06<4:41:03,  1.49it/s]
 56%|█████▋    | 32533/57600 [5:42:06<4:27:46,  1.56it/s]
 56%|█████▋    | 32534/57600 [5:42:07<4:25:54,  1.57it/s]
 56%|█████▋    | 32535/57600 [5:42:08<4:34:22,  1.52it/s]
 56%|█████▋    | 32536/57600 [5:42:08<4:33:17,  1.53it/s]
 56%|█████▋    | 32537/57600 [5:42:09<4:36:20,  1.51it/s]
 56%|█████▋    | 32538/57600 [5:42:10<4:44:29,  1.47it/s]
 56%|█████▋    | 32539/57600 [5:42:10<4:43:18,  1.47it/s]
 56%|█████▋    | 32540/57600 [5:42:11<4:43:43,  1.47it/s]
                                                         
{'loss': 1.1553, 'learning_rate': 4.929268292682927e-07, 'epoch': 359.16}

 56%|█████▋    | 32540/57600 [5:42:11<4:43:43,  1.47it/s]
 56%|█████▋    | 32541/57600 [5:42:12<4:40:32,  1.49it/s]
 56%|█████▋    | 32542/57600 [5:42:12<4:37:16,  1.51it/s]
 56%|█████▋    | 32543/57600 [5:42:13<4:42:07,  1.48it/s]
 56%|█████▋    | 32544/57600 [5:42:14<4:34:33,  1.52it/s]
 57%|█████▋    | 32545/57600 [5:42:14<4:34:19,  1.52it/s]
 57%|█████▋    | 32546/57600 [5:42:15<4:31:28,  1.54it/s]
 57%|█████▋    | 32547/57600 [5:42:16<4:23:56,  1.58it/s]
 57%|█████▋    | 32548/57600 [5:42:16<4:19:39,  1.61it/s]
 57%|█████▋    | 32549/57600 [5:42:17<4:22:42,  1.59it/s]
 57%|█████▋    | 32550/57600 [5:42:17<4:27:58,  1.56it/s]
 57%|█████▋    | 32551/57600 [5:42:18<4:28:12,  1.56it/s]
 57%|█████▋    | 32552/57600 [5:42:19<4:27:09,  1.56it/s]
 57%|█████▋    | 32553/57600 [5:42:19<4:26:48,  1.56it/s]
 57%|█████▋    | 32554/57600 [5:42:20<4:23:42,  1.58it/s]
 57%|█████▋    | 32555/57600 [5:42:21<4:23:51,  1.58it/s]
 57%|█████▋    | 32556/57600 [5:42:21<4:28:48,  1.55it/s]
 57%|█████▋    | 32557/57600 [5:42:22<4:23:55,  1.58it/s]
 57%|█████▋    | 32558/57600 [5:42:23<4:30:07,  1.55it/s]
 57%|█████▋    | 32559/57600 [5:42:23<4:28:53,  1.55it/s]
 57%|█████▋    | 32560/57600 [5:42:24<4:42:06,  1.48it/s]
                                                         
{'loss': 1.224, 'learning_rate': 4.926132404181185e-07, 'epoch': 359.38}

 57%|█████▋    | 32560/57600 [5:42:24<4:42:06,  1.48it/s]
 57%|█████▋    | 32561/57600 [5:42:25<4:39:31,  1.49it/s]
 57%|█████▋    | 32562/57600 [5:42:25<4:36:44,  1.51it/s]
 57%|█████▋    | 32563/57600 [5:42:26<4:33:25,  1.53it/s]
 57%|█████▋    | 32564/57600 [5:42:27<4:38:45,  1.50it/s]
 57%|█████▋    | 32565/57600 [5:42:27<4:28:51,  1.55it/s]
 57%|█████▋    | 32566/57600 [5:42:28<4:24:12,  1.58it/s]
 57%|█████▋    | 32567/57600 [5:42:29<4:33:04,  1.53it/s]
 57%|█████▋    | 32568/57600 [5:42:29<4:24:35,  1.58it/s]
 57%|█████▋    | 32569/57600 [5:42:30<4:14:27,  1.64it/s]
 57%|█████▋    | 32570/57600 [5:42:30<4:22:21,  1.59it/s]
 57%|█████▋    | 32571/57600 [5:42:31<4:20:51,  1.60it/s]
 57%|█████▋    | 32572/57600 [5:42:32<4:24:40,  1.58it/s]
 57%|█████▋    | 32573/57600 [5:42:32<4:35:39,  1.51it/s]
 57%|█████▋    | 32574/57600 [5:42:33<4:31:33,  1.54it/s]
 57%|█████▋    | 32575/57600 [5:42:34<4:26:26,  1.57it/s]
 57%|█████▋    | 32576/57600 [5:42:34<4:35:00,  1.52it/s]
 57%|█████▋    | 32577/57600 [5:42:35<4:43:44,  1.47it/s]
 57%|█████▋    | 32578/57600 [5:42:36<4:41:18,  1.48it/s]
 57%|█████▋    | 32579/57600 [5:42:36<4:35:23,  1.51it/s]
 57%|█████▋    | 32580/57600 [5:42:37<4:30:03,  1.54it/s]
                                                         
{'loss': 1.1704, 'learning_rate': 4.922996515679443e-07, 'epoch': 359.6}

 57%|█████▋    | 32580/57600 [5:42:37<4:30:03,  1.54it/s]
 57%|█████▋    | 32581/57600 [5:42:38<4:36:48,  1.51it/s]
 57%|█████▋    | 32582/57600 [5:42:38<4:25:52,  1.57it/s]
 57%|█████▋    | 32583/57600 [5:42:39<4:22:32,  1.59it/s]
 57%|█████▋    | 32584/57600 [5:42:39<4:22:10,  1.59it/s]
 57%|█████▋    | 32585/57600 [5:42:40<4:16:33,  1.62it/s]
 57%|█████▋    | 32586/57600 [5:42:41<4:23:51,  1.58it/s]
 57%|█████▋    | 32587/57600 [5:42:41<4:31:11,  1.54it/s]
 57%|█████▋    | 32588/57600 [5:42:42<4:33:33,  1.52it/s]
 57%|█████▋    | 32589/57600 [5:42:43<4:41:17,  1.48it/s]
 57%|█████▋    | 32590/57600 [5:42:43<4:45:31,  1.46it/s]
 57%|█████▋    | 32591/57600 [5:42:44<4:42:07,  1.48it/s]
 57%|█████▋    | 32592/57600 [5:42:45<4:39:12,  1.49it/s]
 57%|█████▋    | 32593/57600 [5:42:45<4:38:15,  1.50it/s]
 57%|█████▋    | 32594/57600 [5:42:46<4:40:06,  1.49it/s]
 57%|█████▋    | 32595/57600 [5:42:47<4:33:02,  1.53it/s]
 57%|█████▋    | 32596/57600 [5:42:47<4:34:06,  1.52it/s]
 57%|█████▋    | 32597/57600 [5:42:48<4:29:58,  1.54it/s]
 57%|█████▋    | 32598/57600 [5:42:49<4:24:45,  1.57it/s]
 57%|█████▋    | 32599/57600 [5:42:49<4:29:43,  1.54it/s]
 57%|█████▋    | 32600/57600 [5:42:50<4:22:43,  1.59it/s]
                                                         
{'loss': 1.1194, 'learning_rate': 4.9198606271777e-07, 'epoch': 359.82}

 57%|█████▋    | 32600/57600 [5:42:50<4:22:43,  1.59it/s]
 57%|█████▋    | 32601/57600 [5:42:51<4:22:06,  1.59it/s]
 57%|█████▋    | 32602/57600 [5:42:51<4:30:13,  1.54it/s]
 57%|█████▋    | 32603/57600 [5:42:52<4:32:18,  1.53it/s]
 57%|█████▋    | 32604/57600 [5:42:53<4:34:25,  1.52it/s]
 57%|█████▋    | 32605/57600 [5:42:53<4:31:30,  1.53it/s]
 57%|█████▋    | 32606/57600 [5:42:54<4:25:10,  1.57it/s]
 57%|█████▋    | 32607/57600 [5:42:54<4:28:27,  1.55it/s]
 57%|█████▋    | 32608/57600 [5:42:55<4:26:22,  1.56it/s]
 57%|█████▋    | 32609/57600 [5:42:56<4:28:27,  1.55it/s]
 57%|█████▋    | 32610/57600 [5:42:56<4:24:55,  1.57it/s]
 57%|█████▋    | 32611/57600 [5:42:57<4:21:13,  1.59it/s]
 57%|█████▋    | 32612/57600 [5:42:58<4:19:17,  1.61it/s]
 57%|█████▋    | 32613/57600 [5:42:58<4:25:27,  1.57it/s]
 57%|█████▋    | 32614/57600 [5:42:59<4:24:06,  1.58it/s]
 57%|█████▋    | 32615/57600 [5:43:00<4:23:43,  1.58it/s]
 57%|█████▋    | 32616/57600 [5:43:00<4:29:13,  1.55it/s]
 57%|█████▋    | 32617/57600 [5:43:01<4:43:49,  1.47it/s]
 57%|█████▋    | 32618/57600 [5:43:02<4:29:07,  1.55it/s]
 57%|█████▋    | 32619/57600 [5:43:02<4:20:36,  1.60it/s]
 57%|█████▋    | 32620/57600 [5:43:03<4:22:54,  1.58it/s]
                                                         
{'loss': 1.1772, 'learning_rate': 4.916724738675958e-07, 'epoch': 360.04}

 57%|█████▋    | 32620/57600 [5:43:03<4:22:54,  1.58it/s]
 57%|█████▋    | 32621/57600 [5:43:03<4:16:52,  1.62it/s]
 57%|█████▋    | 32622/57600 [5:43:04<4:17:28,  1.62it/s]
 57%|█████▋    | 32623/57600 [5:43:05<4:22:33,  1.59it/s]
 57%|█████▋    | 32624/57600 [5:43:05<4:22:05,  1.59it/s]
 57%|█████▋    | 32625/57600 [5:43:06<4:22:45,  1.58it/s]
 57%|█████▋    | 32626/57600 [5:43:06<4:19:07,  1.61it/s]
 57%|█████▋    | 32627/57600 [5:43:07<4:17:41,  1.62it/s]
 57%|█████▋    | 32628/57600 [5:43:08<4:19:28,  1.60it/s]
 57%|█████▋    | 32629/57600 [5:43:08<4:25:45,  1.57it/s]
 57%|█████▋    | 32630/57600 [5:43:09<4:30:33,  1.54it/s]
 57%|█████▋    | 32631/57600 [5:43:10<4:23:55,  1.58it/s]
 57%|█████▋    | 32632/57600 [5:43:10<4:20:21,  1.60it/s]
 57%|█████▋    | 32633/57600 [5:43:11<4:19:31,  1.60it/s]
 57%|█████▋    | 32634/57600 [5:43:11<4:13:55,  1.64it/s]
 57%|█████▋    | 32635/57600 [5:43:12<4:23:42,  1.58it/s]
 57%|█████▋    | 32636/57600 [5:43:13<4:27:53,  1.55it/s]
 57%|█████▋    | 32637/57600 [5:43:13<4:21:44,  1.59it/s]
 57%|█████▋    | 32638/57600 [5:43:14<4:23:36,  1.58it/s]
 57%|█████▋    | 32639/57600 [5:43:15<4:19:39,  1.60it/s]
 57%|█████▋    | 32640/57600 [5:43:15<4:20:48,  1.60it/s]
                                                         
{'loss': 1.1531, 'learning_rate': 4.913588850174216e-07, 'epoch': 360.26}

 57%|█████▋    | 32640/57600 [5:43:15<4:20:48,  1.60it/s]
 57%|█████▋    | 32641/57600 [5:43:16<4:25:30,  1.57it/s]
 57%|█████▋    | 32642/57600 [5:43:17<4:21:37,  1.59it/s]
 57%|█████▋    | 32643/57600 [5:43:17<4:18:19,  1.61it/s]
 57%|█████▋    | 32644/57600 [5:43:18<4:12:25,  1.65it/s]
 57%|█████▋    | 32645/57600 [5:43:18<4:24:58,  1.57it/s]
 57%|█████▋    | 32646/57600 [5:43:19<4:15:31,  1.63it/s]
 57%|█████▋    | 32647/57600 [5:43:20<4:18:05,  1.61it/s]
 57%|█████▋    | 32648/57600 [5:43:20<4:15:05,  1.63it/s]
 57%|█████▋    | 32649/57600 [5:43:21<4:12:06,  1.65it/s]
 57%|█████▋    | 32650/57600 [5:43:21<4:09:15,  1.67it/s]
 57%|█████▋    | 32651/57600 [5:43:22<4:12:01,  1.65it/s]
 57%|█████▋    | 32652/57600 [5:43:23<4:09:31,  1.67it/s]
 57%|█████▋    | 32653/57600 [5:43:23<4:17:40,  1.61it/s]
 57%|█████▋    | 32654/57600 [5:43:24<4:22:37,  1.58it/s]
 57%|█████▋    | 32655/57600 [5:43:25<4:22:49,  1.58it/s]
 57%|█████▋    | 32656/57600 [5:43:25<4:23:57,  1.58it/s]
 57%|█████▋    | 32657/57600 [5:43:26<4:36:35,  1.50it/s]
 57%|█████▋    | 32658/57600 [5:43:27<4:29:19,  1.54it/s]
 57%|█████▋    | 32659/57600 [5:43:27<4:24:24,  1.57it/s]
 57%|█████▋    | 32660/57600 [5:43:28<4:21:38,  1.59it/s]
                                                         
{'loss': 1.1752, 'learning_rate': 4.910452961672473e-07, 'epoch': 360.49}

 57%|█████▋    | 32660/57600 [5:43:28<4:21:38,  1.59it/s]
 57%|█████▋    | 32661/57600 [5:43:29<4:30:31,  1.54it/s]
 57%|█████▋    | 32662/57600 [5:43:29<4:27:20,  1.55it/s]
 57%|█████▋    | 32663/57600 [5:43:30<4:20:29,  1.60it/s]
 57%|█████▋    | 32664/57600 [5:43:30<4:23:23,  1.58it/s]
 57%|█████▋    | 32665/57600 [5:43:31<4:22:18,  1.58it/s]
 57%|█████▋    | 32666/57600 [5:43:32<4:17:52,  1.61it/s]
 57%|█████▋    | 32667/57600 [5:43:32<4:20:35,  1.59it/s]
 57%|█████▋    | 32668/57600 [5:43:33<4:20:55,  1.59it/s]
 57%|█████▋    | 32669/57600 [5:43:33<4:20:29,  1.60it/s]
 57%|█████▋    | 32670/57600 [5:43:34<4:18:03,  1.61it/s]
 57%|█████▋    | 32671/57600 [5:43:35<4:22:15,  1.58it/s]
 57%|█████▋    | 32672/57600 [5:43:35<4:28:16,  1.55it/s]
 57%|█████▋    | 32673/57600 [5:43:36<4:26:12,  1.56it/s]
 57%|█████▋    | 32674/57600 [5:43:37<4:20:04,  1.60it/s]
 57%|█████▋    | 32675/57600 [5:43:37<4:22:40,  1.58it/s]
 57%|█████▋    | 32676/57600 [5:43:38<4:22:36,  1.58it/s]
 57%|█████▋    | 32677/57600 [5:43:39<4:23:59,  1.57it/s]
 57%|█████▋    | 32678/57600 [5:43:39<4:19:35,  1.60it/s]
 57%|█████▋    | 32679/57600 [5:43:40<4:22:15,  1.58it/s]
 57%|█████▋    | 32680/57600 [5:43:40<4:19:08,  1.60it/s]
                                                         
{'loss': 1.1692, 'learning_rate': 4.907317073170732e-07, 'epoch': 360.71}

 57%|█████▋    | 32680/57600 [5:43:40<4:19:08,  1.60it/s]
 57%|█████▋    | 32681/57600 [5:43:41<4:24:23,  1.57it/s]
 57%|█████▋    | 32682/57600 [5:43:42<4:30:31,  1.54it/s]
 57%|█████▋    | 32683/57600 [5:43:42<4:25:09,  1.57it/s]
 57%|█████▋    | 32684/57600 [5:43:43<4:23:43,  1.57it/s]
 57%|█████▋    | 32685/57600 [5:43:44<4:17:36,  1.61it/s]
 57%|█████▋    | 32686/57600 [5:43:44<4:20:44,  1.59it/s]
 57%|█████▋    | 32687/57600 [5:43:45<4:20:20,  1.59it/s]
 57%|█████▋    | 32688/57600 [5:43:45<4:19:52,  1.60it/s]
 57%|█████▋    | 32689/57600 [5:43:46<4:25:48,  1.56it/s]
 57%|█████▋    | 32690/57600 [5:43:47<4:28:00,  1.55it/s]
 57%|█████▋    | 32691/57600 [5:43:48<4:34:06,  1.51it/s]
 57%|█████▋    | 32692/57600 [5:43:48<4:37:12,  1.50it/s]
 57%|█████▋    | 32693/57600 [5:43:49<4:27:47,  1.55it/s]
 57%|█████▋    | 32694/57600 [5:43:49<4:20:15,  1.59it/s]
 57%|█████▋    | 32695/57600 [5:43:50<4:28:43,  1.54it/s]
 57%|█████▋    | 32696/57600 [5:43:51<4:36:20,  1.50it/s]
 57%|█████▋    | 32697/57600 [5:43:51<4:28:43,  1.54it/s]
 57%|█████▋    | 32698/57600 [5:43:52<4:20:30,  1.59it/s]
 57%|█████▋    | 32699/57600 [5:43:53<4:25:34,  1.56it/s]
 57%|█████▋    | 32700/57600 [5:43:53<4:28:23,  1.55it/s]
                                                         
{'loss': 1.1234, 'learning_rate': 4.904181184668989e-07, 'epoch': 360.93}

 57%|█████▋    | 32700/57600 [5:43:53<4:28:23,  1.55it/s]
 57%|█████▋    | 32701/57600 [5:43:54<4:25:25,  1.56it/s]
 57%|█████▋    | 32702/57600 [5:43:55<4:29:07,  1.54it/s]
 57%|█████▋    | 32703/57600 [5:43:55<4:21:41,  1.59it/s]
 57%|█████▋    | 32704/57600 [5:43:56<4:18:13,  1.61it/s]
 57%|█████▋    | 32705/57600 [5:43:56<4:24:30,  1.57it/s]
 57%|█████▋    | 32706/57600 [5:43:57<4:27:14,  1.55it/s]
 57%|█████▋    | 32707/57600 [5:43:58<4:26:55,  1.55it/s]
 57%|█████▋    | 32708/57600 [5:43:58<4:27:51,  1.55it/s]
 57%|█████▋    | 32709/57600 [5:43:59<4:23:52,  1.57it/s]
 57%|█████▋    | 32710/57600 [5:44:00<4:24:02,  1.57it/s]
 57%|█████▋    | 32711/57600 [5:44:00<4:37:52,  1.49it/s]
 57%|█████▋    | 32712/57600 [5:44:01<4:29:29,  1.54it/s]
 57%|█████▋    | 32713/57600 [5:44:02<4:24:44,  1.57it/s]
 57%|█████▋    | 32714/57600 [5:44:02<4:21:01,  1.59it/s]
 57%|█████▋    | 32715/57600 [5:44:03<4:25:05,  1.56it/s]
 57%|█████▋    | 32716/57600 [5:44:04<4:24:52,  1.57it/s]
 57%|█████▋    | 32717/57600 [5:44:04<4:26:11,  1.56it/s]
 57%|█████▋    | 32718/57600 [5:44:05<4:31:05,  1.53it/s]
 57%|█████▋    | 32719/57600 [5:44:05<4:20:56,  1.59it/s]
 57%|█████▋    | 32720/57600 [5:44:06<4:21:47,  1.58it/s]
                                                         
{'loss': 1.1295, 'learning_rate': 4.901045296167247e-07, 'epoch': 361.15}

 57%|█████▋    | 32720/57600 [5:44:06<4:21:47,  1.58it/s]
 57%|█████▋    | 32721/57600 [5:44:07<4:20:08,  1.59it/s]
 57%|█████▋    | 32722/57600 [5:44:07<4:22:44,  1.58it/s]
 57%|█████▋    | 32723/57600 [5:44:08<4:23:42,  1.57it/s]
 57%|█████▋    | 32724/57600 [5:44:09<4:18:32,  1.60it/s]
 57%|█████▋    | 32725/57600 [5:44:09<4:18:19,  1.60it/s]
 57%|█████▋    | 32726/57600 [5:44:10<4:14:19,  1.63it/s]
 57%|█████▋    | 32727/57600 [5:44:10<4:13:00,  1.64it/s]
 57%|█████▋    | 32728/57600 [5:44:11<4:09:39,  1.66it/s]
 57%|█████▋    | 32729/57600 [5:44:12<4:11:11,  1.65it/s]
 57%|█████▋    | 32730/57600 [5:44:12<4:11:29,  1.65it/s]
 57%|█████▋    | 32731/57600 [5:44:13<4:16:32,  1.62it/s]
 57%|█████▋    | 32732/57600 [5:44:13<4:19:42,  1.60it/s]
 57%|█████▋    | 32733/57600 [5:44:14<4:11:13,  1.65it/s]
 57%|█████▋    | 32734/57600 [5:44:15<4:20:15,  1.59it/s]
 57%|█████▋    | 32735/57600 [5:44:15<4:20:26,  1.59it/s]
 57%|█████▋    | 32736/57600 [5:44:16<4:22:01,  1.58it/s]
 57%|█████▋    | 32737/57600 [5:44:17<4:25:26,  1.56it/s]
 57%|█████▋    | 32738/57600 [5:44:17<4:34:56,  1.51it/s]
 57%|█████▋    | 32739/57600 [5:44:18<4:30:13,  1.53it/s]
 57%|█████▋    | 32740/57600 [5:44:19<4:27:39,  1.55it/s]
                                                         
{'loss': 1.1615, 'learning_rate': 4.897909407665505e-07, 'epoch': 361.37}

 57%|█████▋    | 32740/57600 [5:44:19<4:27:39,  1.55it/s]
 57%|█████▋    | 32741/57600 [5:44:19<4:30:18,  1.53it/s]
 57%|█████▋    | 32742/57600 [5:44:20<4:24:17,  1.57it/s]
 57%|█████▋    | 32743/57600 [5:44:21<4:27:34,  1.55it/s]
 57%|█████▋    | 32744/57600 [5:44:21<4:33:34,  1.51it/s]
 57%|█████▋    | 32745/57600 [5:44:22<4:22:53,  1.58it/s]
 57%|█████▋    | 32746/57600 [5:44:22<4:24:25,  1.57it/s]
 57%|█████▋    | 32747/57600 [5:44:23<4:28:09,  1.54it/s]
 57%|█████▋    | 32748/57600 [5:44:24<4:32:16,  1.52it/s]
 57%|█████▋    | 32749/57600 [5:44:24<4:23:53,  1.57it/s]
 57%|█████▋    | 32750/57600 [5:44:25<4:20:54,  1.59it/s]
 57%|█████▋    | 32751/57600 [5:44:26<4:17:29,  1.61it/s]
 57%|█████▋    | 32752/57600 [5:44:26<4:14:38,  1.63it/s]
 57%|█████▋    | 32753/57600 [5:44:27<4:15:48,  1.62it/s]
 57%|█████▋    | 32754/57600 [5:44:28<4:21:07,  1.59it/s]
 57%|█████▋    | 32755/57600 [5:44:28<4:18:16,  1.60it/s]
 57%|█████▋    | 32756/57600 [5:44:29<4:21:02,  1.59it/s]
 57%|█████▋    | 32757/57600 [5:44:29<4:19:29,  1.60it/s]
 57%|█████▋    | 32758/57600 [5:44:30<4:17:57,  1.61it/s]
 57%|█████▋    | 32759/57600 [5:44:31<4:22:04,  1.58it/s]
 57%|█████▋    | 32760/57600 [5:44:31<4:26:51,  1.55it/s]
                                                         
{'loss': 1.1748, 'learning_rate': 4.894773519163763e-07, 'epoch': 361.59}

 57%|█████▋    | 32760/57600 [5:44:31<4:26:51,  1.55it/s]
 57%|█████▋    | 32761/57600 [5:44:32<4:28:38,  1.54it/s]
 57%|█████▋    | 32762/57600 [5:44:33<4:26:16,  1.55it/s]
 57%|█████▋    | 32763/57600 [5:44:33<4:22:08,  1.58it/s]
 57%|█████▋    | 32764/57600 [5:44:34<4:16:50,  1.61it/s]
 57%|█████▋    | 32765/57600 [5:44:35<4:25:16,  1.56it/s]
 57%|█████▋    | 32766/57600 [5:44:35<4:30:46,  1.53it/s]
 57%|█████▋    | 32767/57600 [5:44:36<4:38:46,  1.48it/s]
 57%|█████▋    | 32768/57600 [5:44:37<4:39:13,  1.48it/s]
 57%|█████▋    | 32769/57600 [5:44:37<4:37:00,  1.49it/s]
 57%|█████▋    | 32770/57600 [5:44:38<4:34:27,  1.51it/s]
 57%|█████▋    | 32771/57600 [5:44:39<4:31:43,  1.52it/s]
 57%|█████▋    | 32772/57600 [5:44:39<4:23:42,  1.57it/s]
 57%|█████▋    | 32773/57600 [5:44:40<4:23:05,  1.57it/s]
 57%|█████▋    | 32774/57600 [5:44:40<4:17:43,  1.61it/s]
 57%|█████▋    | 32775/57600 [5:44:41<4:18:02,  1.60it/s]
 57%|█████▋    | 32776/57600 [5:44:42<4:24:07,  1.57it/s]
 57%|█████▋    | 32777/57600 [5:44:42<4:22:59,  1.57it/s]
 57%|█████▋    | 32778/57600 [5:44:43<4:18:50,  1.60it/s]
 57%|█████▋    | 32779/57600 [5:44:44<4:24:23,  1.56it/s]
 57%|█████▋    | 32780/57600 [5:44:44<4:22:14,  1.58it/s]
                                                         
{'loss': 1.1254, 'learning_rate': 4.89163763066202e-07, 'epoch': 361.81}

 57%|█████▋    | 32780/57600 [5:44:44<4:22:14,  1.58it/s]
 57%|█████▋    | 32781/57600 [5:44:45<4:23:42,  1.57it/s]
 57%|█████▋    | 32782/57600 [5:44:45<4:22:22,  1.58it/s]
 57%|█████▋    | 32783/57600 [5:44:46<4:29:36,  1.53it/s]
 57%|█████▋    | 32784/57600 [5:44:47<4:25:50,  1.56it/s]
 57%|█████▋    | 32785/57600 [5:44:47<4:21:45,  1.58it/s]
 57%|█████▋    | 32786/57600 [5:44:48<4:26:22,  1.55it/s]
 57%|█████▋    | 32787/57600 [5:44:49<4:26:34,  1.55it/s]
 57%|█████▋    | 32788/57600 [5:44:49<4:21:29,  1.58it/s]
 57%|█████▋    | 32789/57600 [5:44:50<4:18:09,  1.60it/s]
 57%|█████▋    | 32790/57600 [5:44:50<4:10:51,  1.65it/s]
 57%|█████▋    | 32791/57600 [5:44:51<4:21:50,  1.58it/s]
 57%|█████▋    | 32792/57600 [5:44:52<4:21:23,  1.58it/s]
 57%|█████▋    | 32793/57600 [5:44:52<4:22:05,  1.58it/s]
 57%|█████▋    | 32794/57600 [5:44:53<4:16:28,  1.61it/s]
 57%|█████▋    | 32795/57600 [5:44:54<4:15:19,  1.62it/s]
 57%|█████▋    | 32796/57600 [5:44:54<4:10:52,  1.65it/s]
 57%|█████▋    | 32797/57600 [5:44:55<4:10:46,  1.65it/s]
 57%|█████▋    | 32798/57600 [5:44:56<4:22:00,  1.58it/s]
 57%|█████▋    | 32799/57600 [5:44:56<4:19:46,  1.59it/s]
 57%|█████▋    | 32800/57600 [5:44:57<4:32:39,  1.52it/s]
                                                         
{'loss': 1.165, 'learning_rate': 4.888501742160279e-07, 'epoch': 362.03}

 57%|█████▋    | 32800/57600 [5:44:57<4:32:39,  1.52it/s]
 57%|█████▋    | 32801/57600 [5:44:58<4:46:38,  1.44it/s]
 57%|█████▋    | 32802/57600 [5:44:58<4:34:42,  1.50it/s]
 57%|█████▋    | 32803/57600 [5:44:59<4:23:12,  1.57it/s]
 57%|█████▋    | 32804/57600 [5:44:59<4:15:11,  1.62it/s]
 57%|█████▋    | 32805/57600 [5:45:00<4:10:55,  1.65it/s]
 57%|█████▋    | 32806/57600 [5:45:01<4:09:38,  1.66it/s]
 57%|█████▋    | 32807/57600 [5:45:01<4:07:04,  1.67it/s]
 57%|█████▋    | 32808/57600 [5:45:02<4:11:43,  1.64it/s]
 57%|█████▋    | 32809/57600 [5:45:02<4:13:40,  1.63it/s]
 57%|█████▋    | 32810/57600 [5:45:03<4:11:58,  1.64it/s]
 57%|█████▋    | 32811/57600 [5:45:04<4:15:49,  1.61it/s]
 57%|█████▋    | 32812/57600 [5:45:04<4:09:45,  1.65it/s]
 57%|█████▋    | 32813/57600 [5:45:05<4:14:35,  1.62it/s]
 57%|█████▋    | 32814/57600 [5:45:05<4:17:04,  1.61it/s]
 57%|█████▋    | 32815/57600 [5:45:06<4:18:34,  1.60it/s]
 57%|█████▋    | 32816/57600 [5:45:07<4:20:49,  1.58it/s]
 57%|█████▋    | 32817/57600 [5:45:07<4:17:13,  1.61it/s]
 57%|█████▋    | 32818/57600 [5:45:08<4:15:17,  1.62it/s]
 57%|█████▋    | 32819/57600 [5:45:09<4:14:41,  1.62it/s]
 57%|█████▋    | 32820/57600 [5:45:09<4:14:17,  1.62it/s]
                                                         
{'loss': 1.1824, 'learning_rate': 4.885365853658538e-07, 'epoch': 362.25}

 57%|█████▋    | 32820/57600 [5:45:09<4:14:17,  1.62it/s]
 57%|█████▋    | 32821/57600 [5:45:10<4:12:20,  1.64it/s]
 57%|█████▋    | 32822/57600 [5:45:11<4:23:15,  1.57it/s]
 57%|█████▋    | 32823/57600 [5:45:11<4:18:45,  1.60it/s]
 57%|█████▋    | 32824/57600 [5:45:12<4:16:46,  1.61it/s]
 57%|█████▋    | 32825/57600 [5:45:12<4:13:21,  1.63it/s]
 57%|█████▋    | 32826/57600 [5:45:13<4:10:20,  1.65it/s]
 57%|█████▋    | 32827/57600 [5:45:14<4:11:43,  1.64it/s]
 57%|█████▋    | 32828/57600 [5:45:14<4:07:02,  1.67it/s]
 57%|█████▋    | 32829/57600 [5:45:15<4:16:06,  1.61it/s]
 57%|█████▋    | 32830/57600 [5:45:15<4:23:36,  1.57it/s]
 57%|█████▋    | 32831/57600 [5:45:16<4:19:09,  1.59it/s]
 57%|█████▋    | 32832/57600 [5:45:17<4:19:19,  1.59it/s]
 57%|█████▋    | 32833/57600 [5:45:17<4:22:49,  1.57it/s]
 57%|█████▋    | 32834/57600 [5:45:18<4:32:24,  1.52it/s]
 57%|█████▋    | 32835/57600 [5:45:19<4:32:20,  1.52it/s]
 57%|█████▋    | 32836/57600 [5:45:19<4:23:04,  1.57it/s]
 57%|█████▋    | 32837/57600 [5:45:20<4:15:54,  1.61it/s]
 57%|█████▋    | 32838/57600 [5:45:21<4:25:52,  1.55it/s]
 57%|█████▋    | 32839/57600 [5:45:21<4:28:26,  1.54it/s]
 57%|█████▋    | 32840/57600 [5:45:22<4:31:37,  1.52it/s]
                                                         
{'loss': 1.1703, 'learning_rate': 4.882229965156794e-07, 'epoch': 362.47}

 57%|█████▋    | 32840/57600 [5:45:22<4:31:37,  1.52it/s]
 57%|█████▋    | 32841/57600 [5:45:23<4:27:05,  1.54it/s]
 57%|█████▋    | 32842/57600 [5:45:23<4:19:31,  1.59it/s]
 57%|█████▋    | 32843/57600 [5:45:24<4:28:59,  1.53it/s]
 57%|█████▋    | 32844/57600 [5:45:24<4:23:39,  1.56it/s]
 57%|█████▋    | 32845/57600 [5:45:25<4:19:49,  1.59it/s]
 57%|█████▋    | 32846/57600 [5:45:26<4:21:19,  1.58it/s]
 57%|█████▋    | 32847/57600 [5:45:26<4:24:01,  1.56it/s]
 57%|█████▋    | 32848/57600 [5:45:27<4:15:27,  1.61it/s]
 57%|█████▋    | 32849/57600 [5:45:28<4:16:49,  1.61it/s]
 57%|█████▋    | 32850/57600 [5:45:28<4:24:50,  1.56it/s]
 57%|█████▋    | 32851/57600 [5:45:29<4:15:55,  1.61it/s]
 57%|█████▋    | 32852/57600 [5:45:30<4:25:53,  1.55it/s]
 57%|█████▋    | 32853/57600 [5:45:30<4:25:57,  1.55it/s]
 57%|█████▋    | 32854/57600 [5:45:31<4:20:37,  1.58it/s]
 57%|█████▋    | 32855/57600 [5:45:31<4:21:11,  1.58it/s]
 57%|█████▋    | 32856/57600 [5:45:32<4:23:47,  1.56it/s]
 57%|█████▋    | 32857/57600 [5:45:33<4:13:55,  1.62it/s]
 57%|█████▋    | 32858/57600 [5:45:33<4:21:31,  1.58it/s]
 57%|█████▋    | 32859/57600 [5:45:34<4:14:46,  1.62it/s]
 57%|█████▋    | 32860/57600 [5:45:34<4:14:27,  1.62it/s]
                                                         
{'loss': 1.1826, 'learning_rate': 4.879094076655053e-07, 'epoch': 362.69}

 57%|█████▋    | 32860/57600 [5:45:34<4:14:27,  1.62it/s]
 57%|█████▋    | 32861/57600 [5:45:35<4:18:25,  1.60it/s]
 57%|█████▋    | 32862/57600 [5:45:36<4:19:39,  1.59it/s]
 57%|█████▋    | 32863/57600 [5:45:36<4:20:11,  1.58it/s]
 57%|█████▋    | 32864/57600 [5:45:37<4:16:52,  1.60it/s]
 57%|█████▋    | 32865/57600 [5:45:38<4:21:25,  1.58it/s]
 57%|█████▋    | 32866/57600 [5:45:38<4:24:25,  1.56it/s]
 57%|█████▋    | 32867/57600 [5:45:39<4:22:31,  1.57it/s]
 57%|█████▋    | 32868/57600 [5:45:40<4:19:08,  1.59it/s]
 57%|█████▋    | 32869/57600 [5:45:40<4:12:24,  1.63it/s]
 57%|█████▋    | 32870/57600 [5:45:41<4:11:50,  1.64it/s]
 57%|█████▋    | 32871/57600 [5:45:41<4:11:52,  1.64it/s]
 57%|█████▋    | 32872/57600 [5:45:42<4:10:24,  1.65it/s]
 57%|█████▋    | 32873/57600 [5:45:43<4:18:21,  1.60it/s]
 57%|█████▋    | 32874/57600 [5:45:43<4:20:58,  1.58it/s]
 57%|█████▋    | 32875/57600 [5:45:44<4:14:41,  1.62it/s]
 57%|█████▋    | 32876/57600 [5:45:44<4:13:37,  1.62it/s]
 57%|█████▋    | 32877/57600 [5:45:45<4:17:02,  1.60it/s]
 57%|█████▋    | 32878/57600 [5:45:46<4:16:29,  1.61it/s]
 57%|█████▋    | 32879/57600 [5:45:46<4:16:19,  1.61it/s]
 57%|█████▋    | 32880/57600 [5:45:47<4:17:11,  1.60it/s]
                                                         
{'loss': 1.1704, 'learning_rate': 4.875958188153309e-07, 'epoch': 362.91}

 57%|█████▋    | 32880/57600 [5:45:47<4:17:11,  1.60it/s]
 57%|█████▋    | 32881/57600 [5:45:48<4:27:11,  1.54it/s]
 57%|█████▋    | 32882/57600 [5:45:48<4:24:16,  1.56it/s]
 57%|█████▋    | 32883/57600 [5:45:49<4:32:20,  1.51it/s]
 57%|█████▋    | 32884/57600 [5:45:50<4:25:34,  1.55it/s]
 57%|█████▋    | 32885/57600 [5:45:50<4:27:54,  1.54it/s]
 57%|█████▋    | 32886/57600 [5:45:51<4:26:12,  1.55it/s]
 57%|█████▋    | 32887/57600 [5:45:52<4:20:39,  1.58it/s]
 57%|█████▋    | 32888/57600 [5:45:52<4:29:29,  1.53it/s]
 57%|█████▋    | 32889/57600 [5:45:53<4:23:13,  1.56it/s]
 57%|█████▋    | 32890/57600 [5:45:53<4:23:30,  1.56it/s]
 57%|█████▋    | 32891/57600 [5:45:54<4:36:45,  1.49it/s]
 57%|█████▋    | 32892/57600 [5:45:55<4:30:50,  1.52it/s]
 57%|█████▋    | 32893/57600 [5:45:56<4:40:53,  1.47it/s]
 57%|█████▋    | 32894/57600 [5:45:56<4:32:08,  1.51it/s]
 57%|█████▋    | 32895/57600 [5:45:57<4:22:09,  1.57it/s]
 57%|█████▋    | 32896/57600 [5:45:57<4:16:11,  1.61it/s]
 57%|█████▋    | 32897/57600 [5:45:58<4:08:26,  1.66it/s]
 57%|█████▋    | 32898/57600 [5:45:58<4:01:51,  1.70it/s]
 57%|█████▋    | 32899/57600 [5:45:59<4:06:24,  1.67it/s]
 57%|█████▋    | 32900/57600 [5:46:00<4:06:54,  1.67it/s]
                                                         
{'loss': 1.1456, 'learning_rate': 4.872822299651568e-07, 'epoch': 363.13}

 57%|█████▋    | 32900/57600 [5:46:00<4:06:54,  1.67it/s]
 57%|█████▋    | 32901/57600 [5:46:00<4:05:47,  1.67it/s]
 57%|█████▋    | 32902/57600 [5:46:01<4:22:33,  1.57it/s]
 57%|█████▋    | 32903/57600 [5:46:02<4:11:03,  1.64it/s]
 57%|█████▋    | 32904/57600 [5:46:02<4:10:27,  1.64it/s]
 57%|█████▋    | 32905/57600 [5:46:03<4:16:01,  1.61it/s]
 57%|█████▋    | 32906/57600 [5:46:03<4:10:24,  1.64it/s]
 57%|█████▋    | 32907/57600 [5:46:04<4:10:12,  1.64it/s]
 57%|█████▋    | 32908/57600 [5:46:05<4:16:23,  1.61it/s]
 57%|█████▋    | 32909/57600 [5:46:05<4:14:02,  1.62it/s]
 57%|█████▋    | 32910/57600 [5:46:06<4:16:59,  1.60it/s]
 57%|█████▋    | 32911/57600 [5:46:06<4:10:22,  1.64it/s]
 57%|█████▋    | 32912/57600 [5:46:07<4:12:23,  1.63it/s]
 57%|█████▋    | 32913/57600 [5:46:08<4:19:05,  1.59it/s]
 57%|█████▋    | 32914/57600 [5:46:08<4:19:38,  1.58it/s]
 57%|█████▋    | 32915/57600 [5:46:09<4:27:39,  1.54it/s]
 57%|█████▋    | 32916/57600 [5:46:10<4:18:13,  1.59it/s]
 57%|█████▋    | 32917/57600 [5:46:10<4:22:51,  1.57it/s]
 57%|█████▋    | 32918/57600 [5:46:11<4:24:31,  1.56it/s]
 57%|█████▋    | 32919/57600 [5:46:12<4:25:06,  1.55it/s]
 57%|█████▋    | 32920/57600 [5:46:12<4:24:45,  1.55it/s]
                                                         
{'loss': 1.1702, 'learning_rate': 4.869686411149825e-07, 'epoch': 363.36}

 57%|█████▋    | 32920/57600 [5:46:12<4:24:45,  1.55it/s]
 57%|█████▋    | 32921/57600 [5:46:13<4:18:24,  1.59it/s]
 57%|█████▋    | 32922/57600 [5:46:13<4:13:58,  1.62it/s]
 57%|█████▋    | 32923/57600 [5:46:14<4:11:42,  1.63it/s]
 57%|█████▋    | 32924/57600 [5:46:15<4:11:44,  1.63it/s]
 57%|█████▋    | 32925/57600 [5:46:15<4:16:40,  1.60it/s]
 57%|█████▋    | 32926/57600 [5:46:16<4:20:31,  1.58it/s]
 57%|█████▋    | 32927/57600 [5:46:17<4:22:35,  1.57it/s]
 57%|█████▋    | 32928/57600 [5:46:17<4:16:49,  1.60it/s]
 57%|█████▋    | 32929/57600 [5:46:18<4:17:19,  1.60it/s]
 57%|█████▋    | 32930/57600 [5:46:18<4:18:05,  1.59it/s]
 57%|█████▋    | 32931/57600 [5:46:19<4:24:22,  1.56it/s]
 57%|█████▋    | 32932/57600 [5:46:20<4:23:17,  1.56it/s]
 57%|█████▋    | 32933/57600 [5:46:20<4:19:14,  1.59it/s]
 57%|█████▋    | 32934/57600 [5:46:21<4:19:48,  1.58it/s]
 57%|█████▋    | 32935/57600 [5:46:22<4:19:31,  1.58it/s]
 57%|█████▋    | 32936/57600 [5:46:22<4:19:46,  1.58it/s]
 57%|█████▋    | 32937/57600 [5:46:23<4:23:55,  1.56it/s]
 57%|█████▋    | 32938/57600 [5:46:24<4:17:44,  1.59it/s]
 57%|█████▋    | 32939/57600 [5:46:24<4:18:34,  1.59it/s]
 57%|█████▋    | 32940/57600 [5:46:25<4:17:49,  1.59it/s]
                                                         
{'loss': 1.1534, 'learning_rate': 4.866550522648083e-07, 'epoch': 363.58}

 57%|█████▋    | 32940/57600 [5:46:25<4:17:49,  1.59it/s]
 57%|█████▋    | 32941/57600 [5:46:25<4:09:10,  1.65it/s]
 57%|█████▋    | 32942/57600 [5:46:26<4:05:44,  1.67it/s]
 57%|█████▋    | 32943/57600 [5:46:27<4:11:35,  1.63it/s]
 57%|█████▋    | 32944/57600 [5:46:27<4:13:58,  1.62it/s]
 57%|█████▋    | 32945/57600 [5:46:28<4:08:31,  1.65it/s]
 57%|█████▋    | 32946/57600 [5:46:28<4:06:55,  1.66it/s]
 57%|█████▋    | 32947/57600 [5:46:29<4:17:00,  1.60it/s]
 57%|█████▋    | 32948/57600 [5:46:30<4:13:30,  1.62it/s]
 57%|█████▋    | 32949/57600 [5:46:30<4:07:47,  1.66it/s]
 57%|█████▋    | 32950/57600 [5:46:31<4:05:56,  1.67it/s]
 57%|█████▋    | 32951/57600 [5:46:31<4:05:40,  1.67it/s]
 57%|█████▋    | 32952/57600 [5:46:32<4:13:59,  1.62it/s]
 57%|█████▋    | 32953/57600 [5:46:33<4:10:36,  1.64it/s]
 57%|█████▋    | 32954/57600 [5:46:33<4:04:35,  1.68it/s]
 57%|█████▋    | 32955/57600 [5:46:34<4:02:14,  1.70it/s]
 57%|█████▋    | 32956/57600 [5:46:34<4:04:46,  1.68it/s]
 57%|█████▋    | 32957/57600 [5:46:35<4:09:05,  1.65it/s]
 57%|█████▋    | 32958/57600 [5:46:36<4:12:17,  1.63it/s]
 57%|█████▋    | 32959/57600 [5:46:36<4:15:30,  1.61it/s]
 57%|█████▋    | 32960/57600 [5:46:37<4:09:13,  1.65it/s]
                                                         
{'loss': 1.155, 'learning_rate': 4.863414634146341e-07, 'epoch': 363.8}

 57%|█████▋    | 32960/57600 [5:46:37<4:09:13,  1.65it/s]
 57%|█████▋    | 32961/57600 [5:46:37<4:05:41,  1.67it/s]
 57%|█████▋    | 32962/57600 [5:46:38<4:10:13,  1.64it/s]
 57%|█████▋    | 32963/57600 [5:46:39<4:08:16,  1.65it/s]
 57%|█████▋    | 32964/57600 [5:46:39<4:11:27,  1.63it/s]
 57%|█████▋    | 32965/57600 [5:46:40<4:11:17,  1.63it/s]
 57%|█████▋    | 32966/57600 [5:46:41<4:21:33,  1.57it/s]
 57%|█████▋    | 32967/57600 [5:46:41<4:19:12,  1.58it/s]
 57%|█████▋    | 32968/57600 [5:46:42<4:18:31,  1.59it/s]
 57%|█████▋    | 32969/57600 [5:46:43<4:20:02,  1.58it/s]
 57%|█████▋    | 32970/57600 [5:46:43<4:19:38,  1.58it/s]
 57%|█████▋    | 32971/57600 [5:46:44<4:07:23,  1.66it/s]
 57%|█████▋    | 32972/57600 [5:46:44<4:07:19,  1.66it/s]
 57%|█████▋    | 32973/57600 [5:46:45<4:08:58,  1.65it/s]
 57%|█████▋    | 32974/57600 [5:46:46<4:06:40,  1.66it/s]
 57%|█████▋    | 32975/57600 [5:46:46<4:15:38,  1.61it/s]
 57%|█████▋    | 32976/57600 [5:46:47<4:12:23,  1.63it/s]
 57%|█████▋    | 32977/57600 [5:46:47<4:15:18,  1.61it/s]
 57%|█████▋    | 32978/57600 [5:46:48<4:15:38,  1.61it/s]
 57%|█████▋    | 32979/57600 [5:46:49<4:30:56,  1.51it/s]
 57%|█████▋    | 32980/57600 [5:46:49<4:34:41,  1.49it/s]
                                                         
{'loss': 1.169, 'learning_rate': 4.860278745644599e-07, 'epoch': 364.02}

 57%|█████▋    | 32980/57600 [5:46:49<4:34:41,  1.49it/s]
 57%|█████▋    | 32981/57600 [5:46:50<4:26:13,  1.54it/s]
 57%|█████▋    | 32982/57600 [5:46:51<4:15:24,  1.61it/s]
 57%|█████▋    | 32983/57600 [5:46:51<4:15:49,  1.60it/s]
 57%|█████▋    | 32984/57600 [5:46:52<4:15:44,  1.60it/s]
 57%|█████▋    | 32985/57600 [5:46:53<4:16:23,  1.60it/s]
 57%|█████▋    | 32986/57600 [5:46:53<4:15:56,  1.60it/s]
 57%|█████▋    | 32987/57600 [5:46:54<4:17:54,  1.59it/s]
 57%|█████▋    | 32988/57600 [5:46:54<4:16:03,  1.60it/s]
 57%|█████▋    | 32989/57600 [5:46:55<4:17:13,  1.59it/s]
 57%|█████▋    | 32990/57600 [5:46:56<4:16:34,  1.60it/s]
 57%|█████▋    | 32991/57600 [5:46:56<4:14:20,  1.61it/s]
 57%|█████▋    | 32992/57600 [5:46:57<4:15:26,  1.61it/s]
 57%|█████▋    | 32993/57600 [5:46:58<4:14:24,  1.61it/s]
 57%|█████▋    | 32994/57600 [5:46:58<4:18:25,  1.59it/s]
 57%|█████▋    | 32995/57600 [5:46:59<4:16:35,  1.60it/s]
 57%|█████▋    | 32996/57600 [5:46:59<4:10:31,  1.64it/s]
 57%|█████▋    | 32997/57600 [5:47:00<4:15:41,  1.60it/s]
 57%|█████▋    | 32998/57600 [5:47:01<4:14:05,  1.61it/s]
 57%|█████▋    | 32999/57600 [5:47:01<4:13:16,  1.62it/s]
 57%|█████▋    | 33000/57600 [5:47:02<4:12:17,  1.63it/s]
                                                         
{'loss': 1.1725, 'learning_rate': 4.857142857142857e-07, 'epoch': 364.24}

 57%|█████▋    | 33000/57600 [5:47:02<4:12:17,  1.63it/s]
 57%|█████▋    | 33001/57600 [5:47:02<4:14:58,  1.61it/s]
 57%|█████▋    | 33002/57600 [5:47:03<4:17:01,  1.60it/s]
 57%|█████▋    | 33003/57600 [5:47:04<4:18:21,  1.59it/s]
 57%|█████▋    | 33004/57600 [5:47:04<4:19:30,  1.58it/s]
 57%|█████▋    | 33005/57600 [5:47:05<4:16:39,  1.60it/s]
 57%|█████▋    | 33006/57600 [5:47:06<4:14:56,  1.61it/s]
 57%|█████▋    | 33007/57600 [5:47:06<4:13:45,  1.62it/s]
 57%|█████▋    | 33008/57600 [5:47:07<4:25:16,  1.55it/s]
 57%|█████▋    | 33009/57600 [5:47:08<4:18:26,  1.59it/s]
 57%|█████▋    | 33010/57600 [5:47:08<4:08:17,  1.65it/s]
 57%|█████▋    | 33011/57600 [5:47:09<4:10:28,  1.64it/s]
 57%|█████▋    | 33012/57600 [5:47:09<4:20:21,  1.57it/s]
 57%|█████▋    | 33013/57600 [5:47:10<4:15:09,  1.61it/s]
 57%|█████▋    | 33014/57600 [5:47:11<4:27:34,  1.53it/s]
 57%|█████▋    | 33015/57600 [5:47:11<4:23:36,  1.55it/s]
 57%|█████▋    | 33016/57600 [5:47:12<4:16:40,  1.60it/s]
 57%|█████▋    | 33017/57600 [5:47:13<4:28:27,  1.53it/s]
 57%|█████▋    | 33018/57600 [5:47:13<4:20:46,  1.57it/s]
 57%|█████▋    | 33019/57600 [5:47:14<4:13:57,  1.61it/s]
 57%|█████▋    | 33020/57600 [5:47:14<4:13:45,  1.61it/s]
                                                         
{'loss': 1.1441, 'learning_rate': 4.854006968641115e-07, 'epoch': 364.46}

 57%|█████▋    | 33020/57600 [5:47:14<4:13:45,  1.61it/s]
 57%|█████▋    | 33021/57600 [5:47:15<4:13:41,  1.61it/s]
 57%|█████▋    | 33022/57600 [5:47:16<4:12:54,  1.62it/s]
 57%|█████▋    | 33023/57600 [5:47:16<4:12:40,  1.62it/s]
 57%|█████▋    | 33024/57600 [5:47:17<4:22:18,  1.56it/s]
 57%|█████▋    | 33025/57600 [5:47:18<4:21:41,  1.57it/s]
 57%|█████▋    | 33026/57600 [5:47:18<4:22:11,  1.56it/s]
 57%|█████▋    | 33027/57600 [5:47:19<4:19:04,  1.58it/s]
 57%|█████▋    | 33028/57600 [5:47:20<4:23:38,  1.55it/s]
 57%|█████▋    | 33029/57600 [5:47:20<4:16:49,  1.59it/s]
 57%|█████▋    | 33030/57600 [5:47:21<4:25:47,  1.54it/s]
 57%|█████▋    | 33031/57600 [5:47:21<4:23:25,  1.55it/s]
 57%|█████▋    | 33032/57600 [5:47:22<4:23:54,  1.55it/s]
 57%|█████▋    | 33033/57600 [5:47:23<4:21:55,  1.56it/s]
 57%|█████▋    | 33034/57600 [5:47:23<4:32:25,  1.50it/s]
 57%|█████▋    | 33035/57600 [5:47:24<4:22:14,  1.56it/s]
 57%|█████▋    | 33036/57600 [5:47:25<4:14:41,  1.61it/s]
 57%|█████▋    | 33037/57600 [5:47:25<4:09:15,  1.64it/s]
 57%|█████▋    | 33038/57600 [5:47:26<4:19:41,  1.58it/s]
 57%|█████▋    | 33039/57600 [5:47:27<4:21:23,  1.57it/s]
 57%|█████▋    | 33040/57600 [5:47:27<4:26:12,  1.54it/s]
                                                         
{'loss': 1.1205, 'learning_rate': 4.850871080139373e-07, 'epoch': 364.68}

 57%|█████▋    | 33040/57600 [5:47:27<4:26:12,  1.54it/s]
 57%|█████▋    | 33041/57600 [5:47:28<4:27:44,  1.53it/s]
 57%|█████▋    | 33042/57600 [5:47:29<4:30:37,  1.51it/s]
 57%|█████▋    | 33043/57600 [5:47:29<4:30:04,  1.52it/s]
 57%|█████▋    | 33044/57600 [5:47:30<4:27:03,  1.53it/s]
 57%|█████▋    | 33045/57600 [5:47:31<4:41:42,  1.45it/s]
 57%|█████▋    | 33046/57600 [5:47:31<4:37:13,  1.48it/s]
 57%|█████▋    | 33047/57600 [5:47:32<4:32:31,  1.50it/s]
 57%|█████▋    | 33048/57600 [5:47:33<4:32:28,  1.50it/s]
 57%|█████▋    | 33049/57600 [5:47:33<4:27:45,  1.53it/s]
 57%|█████▋    | 33050/57600 [5:47:34<4:22:28,  1.56it/s]
 57%|█████▋    | 33051/57600 [5:47:34<4:18:35,  1.58it/s]
 57%|█████▋    | 33052/57600 [5:47:35<4:11:22,  1.63it/s]
 57%|█████▋    | 33053/57600 [5:47:36<4:11:15,  1.63it/s]
 57%|█████▋    | 33054/57600 [5:47:36<4:19:41,  1.58it/s]
 57%|█████▋    | 33055/57600 [5:47:37<4:17:51,  1.59it/s]
 57%|█████▋    | 33056/57600 [5:47:38<4:11:26,  1.63it/s]
 57%|█████▋    | 33057/57600 [5:47:38<4:08:08,  1.65it/s]
 57%|█████▋    | 33058/57600 [5:47:39<4:07:03,  1.66it/s]
 57%|█████▋    | 33059/57600 [5:47:39<4:05:37,  1.67it/s]
 57%|█████▋    | 33060/57600 [5:47:40<4:06:39,  1.66it/s]
                                                         
{'loss': 1.1632, 'learning_rate': 4.84773519163763e-07, 'epoch': 364.9}

 57%|█████▋    | 33060/57600 [5:47:40<4:06:39,  1.66it/s]
 57%|█████▋    | 33061/57600 [5:47:40<4:05:10,  1.67it/s]
 57%|█████▋    | 33062/57600 [5:47:41<4:03:44,  1.68it/s]
 57%|█████▋    | 33063/57600 [5:47:42<4:03:24,  1.68it/s]
 57%|█████▋    | 33064/57600 [5:47:42<4:09:26,  1.64it/s]
 57%|█████▋    | 33065/57600 [5:47:43<4:11:57,  1.62it/s]
 57%|█████▋    | 33066/57600 [5:47:44<4:09:39,  1.64it/s]
 57%|█████▋    | 33067/57600 [5:47:44<4:04:28,  1.67it/s]
 57%|█████▋    | 33068/57600 [5:47:45<4:02:16,  1.69it/s]
 57%|█████▋    | 33069/57600 [5:47:45<4:09:50,  1.64it/s]
 57%|█████▋    | 33070/57600 [5:47:46<4:19:40,  1.57it/s]
 57%|█████▋    | 33071/57600 [5:47:47<4:11:26,  1.63it/s]
 57%|█████▋    | 33072/57600 [5:47:47<4:17:10,  1.59it/s]
 57%|█████▋    | 33073/57600 [5:47:48<4:13:38,  1.61it/s]
 57%|█████▋    | 33074/57600 [5:47:49<4:23:46,  1.55it/s]
 57%|█████▋    | 33075/57600 [5:47:49<4:14:10,  1.61it/s]
 57%|█████▋    | 33076/57600 [5:47:50<4:17:22,  1.59it/s]
 57%|█████▋    | 33077/57600 [5:47:50<4:20:14,  1.57it/s]
 57%|█████▋    | 33078/57600 [5:47:51<4:13:40,  1.61it/s]
 57%|█████▋    | 33079/57600 [5:47:52<4:18:50,  1.58it/s]
 57%|█████▋    | 33080/57600 [5:47:52<4:27:15,  1.53it/s]
                                                         
{'loss': 1.1767, 'learning_rate': 4.844599303135889e-07, 'epoch': 365.12}

 57%|█████▋    | 33080/57600 [5:47:52<4:27:15,  1.53it/s]
 57%|█████▋    | 33081/57600 [5:47:53<4:22:54,  1.55it/s]
 57%|█████▋    | 33082/57600 [5:47:54<4:20:03,  1.57it/s]
 57%|█████▋    | 33083/57600 [5:47:54<4:20:18,  1.57it/s]
 57%|█████▋    | 33084/57600 [5:47:55<4:26:52,  1.53it/s]
 57%|█████▋    | 33085/57600 [5:47:56<4:40:10,  1.46it/s]
 57%|█████▋    | 33086/57600 [5:47:56<4:34:28,  1.49it/s]
 57%|█████▋    | 33087/57600 [5:47:57<4:40:41,  1.46it/s]
 57%|█████▋    | 33088/57600 [5:47:58<4:31:01,  1.51it/s]
 57%|█████▋    | 33089/57600 [5:47:58<4:31:15,  1.51it/s]
 57%|█████▋    | 33090/57600 [5:47:59<4:21:38,  1.56it/s]
 57%|█████▋    | 33091/57600 [5:47:59<4:12:44,  1.62it/s]
 57%|█████▋    | 33092/57600 [5:48:00<4:13:58,  1.61it/s]
 57%|█████▋    | 33093/57600 [5:48:01<4:14:13,  1.61it/s]
 57%|█████▋    | 33094/57600 [5:48:01<4:12:18,  1.62it/s]
 57%|█████▋    | 33095/57600 [5:48:02<4:09:07,  1.64it/s]
 57%|█████▋    | 33096/57600 [5:48:03<4:02:57,  1.68it/s]
 57%|█████▋    | 33097/57600 [5:48:03<4:00:33,  1.70it/s]
 57%|█████▋    | 33098/57600 [5:48:04<4:04:27,  1.67it/s]
 57%|█████▋    | 33099/57600 [5:48:04<4:06:42,  1.66it/s]
 57%|█████▋    | 33100/57600 [5:48:05<4:02:36,  1.68it/s]
                                                         
{'loss': 1.1543, 'learning_rate': 4.841463414634147e-07, 'epoch': 365.34}

 57%|█████▋    | 33100/57600 [5:48:05<4:02:36,  1.68it/s]
 57%|█████▋    | 33101/57600 [5:48:05<4:02:14,  1.69it/s]
 57%|█████▋    | 33102/57600 [5:48:06<4:04:00,  1.67it/s]
 57%|█████▋    | 33103/57600 [5:48:07<4:06:04,  1.66it/s]
 57%|█████▋    | 33104/57600 [5:48:07<4:15:31,  1.60it/s]
 57%|█████▋    | 33105/57600 [5:48:08<4:17:16,  1.59it/s]
 57%|█████▋    | 33106/57600 [5:48:09<4:23:40,  1.55it/s]
 57%|█████▋    | 33107/57600 [5:48:09<4:23:05,  1.55it/s]
 57%|█████▋    | 33108/57600 [5:48:10<4:30:41,  1.51it/s]
 57%|█████▋    | 33109/57600 [5:48:11<4:22:07,  1.56it/s]
 57%|█████▋    | 33110/57600 [5:48:11<4:13:05,  1.61it/s]
 57%|█████▋    | 33111/57600 [5:48:12<4:11:35,  1.62it/s]
 57%|█████▋    | 33112/57600 [5:48:12<4:08:47,  1.64it/s]
 57%|█████▋    | 33113/57600 [5:48:13<4:13:28,  1.61it/s]
 57%|█████▋    | 33114/57600 [5:48:14<4:13:48,  1.61it/s]
 57%|█████▋    | 33115/57600 [5:48:14<4:12:45,  1.61it/s]
 57%|█████▋    | 33116/57600 [5:48:15<4:11:17,  1.62it/s]
 57%|█████▋    | 33117/57600 [5:48:16<4:17:16,  1.59it/s]
 57%|█████▋    | 33118/57600 [5:48:16<4:19:10,  1.57it/s]
 57%|█████▋    | 33119/57600 [5:48:17<4:22:40,  1.55it/s]
 57%|█████▊    | 33120/57600 [5:48:17<4:15:46,  1.60it/s]
                                                         
{'loss': 1.2035, 'learning_rate': 4.838327526132404e-07, 'epoch': 365.56}

 57%|█████▊    | 33120/57600 [5:48:17<4:15:46,  1.60it/s]
 58%|█████▊    | 33121/57600 [5:48:18<4:18:33,  1.58it/s]
 58%|█████▊    | 33122/57600 [5:48:19<4:14:38,  1.60it/s]
 58%|█████▊    | 33123/57600 [5:48:19<4:26:12,  1.53it/s]
 58%|█████▊    | 33124/57600 [5:48:20<4:19:47,  1.57it/s]
 58%|█████▊    | 33125/57600 [5:48:21<4:13:53,  1.61it/s]
 58%|█████▊    | 33126/57600 [5:48:21<4:21:35,  1.56it/s]
 58%|█████▊    | 33127/57600 [5:48:22<4:23:26,  1.55it/s]
 58%|█████▊    | 33128/57600 [5:48:23<4:16:56,  1.59it/s]
 58%|█████▊    | 33129/57600 [5:48:23<4:21:39,  1.56it/s]
 58%|█████▊    | 33130/57600 [5:48:24<4:23:48,  1.55it/s]
 58%|█████▊    | 33131/57600 [5:48:24<4:13:38,  1.61it/s]
 58%|█████▊    | 33132/57600 [5:48:25<4:16:27,  1.59it/s]
 58%|█████▊    | 33133/57600 [5:48:26<4:04:36,  1.67it/s]
 58%|█████▊    | 33134/57600 [5:48:26<4:15:34,  1.60it/s]
 58%|█████▊    | 33135/57600 [5:48:27<4:19:55,  1.57it/s]
 58%|█████▊    | 33136/57600 [5:48:28<4:34:39,  1.48it/s]
 58%|█████▊    | 33137/57600 [5:48:28<4:24:29,  1.54it/s]
 58%|█████▊    | 33138/57600 [5:48:29<4:14:05,  1.60it/s]
 58%|█████▊    | 33139/57600 [5:48:30<4:18:28,  1.58it/s]
 58%|█████▊    | 33140/57600 [5:48:30<4:12:34,  1.61it/s]
                                                         
{'loss': 1.1284, 'learning_rate': 4.835191637630662e-07, 'epoch': 365.78}

 58%|█████▊    | 33140/57600 [5:48:30<4:12:34,  1.61it/s]
 58%|█████▊    | 33141/57600 [5:48:31<4:05:58,  1.66it/s]
 58%|█████▊    | 33142/57600 [5:48:31<4:14:10,  1.60it/s]
 58%|█████▊    | 33143/57600 [5:48:32<4:13:59,  1.60it/s]
 58%|█████▊    | 33144/57600 [5:48:33<4:11:43,  1.62it/s]
 58%|█████▊    | 33145/57600 [5:48:33<4:07:32,  1.65it/s]
 58%|█████▊    | 33146/57600 [5:48:34<4:06:25,  1.65it/s]
 58%|█████▊    | 33147/57600 [5:48:34<4:12:03,  1.62it/s]
 58%|█████▊    | 33148/57600 [5:48:35<4:09:00,  1.64it/s]
 58%|█████▊    | 33149/57600 [5:48:36<4:09:18,  1.63it/s]
 58%|█████▊    | 33150/57600 [5:48:36<4:18:11,  1.58it/s]
 58%|█████▊    | 33151/57600 [5:48:37<4:13:44,  1.61it/s]
 58%|█████▊    | 33152/57600 [5:48:38<4:17:32,  1.58it/s]
 58%|█████▊    | 33153/57600 [5:48:38<4:09:47,  1.63it/s]
 58%|█████▊    | 33154/57600 [5:48:39<4:14:54,  1.60it/s]
 58%|█████▊    | 33155/57600 [5:48:39<4:12:48,  1.61it/s]
 58%|█████▊    | 33156/57600 [5:48:40<4:10:01,  1.63it/s]
 58%|█████▊    | 33157/57600 [5:48:41<4:13:06,  1.61it/s]
 58%|█████▊    | 33158/57600 [5:48:41<4:12:52,  1.61it/s]
 58%|█████▊    | 33159/57600 [5:48:42<4:16:05,  1.59it/s]
 58%|█████▊    | 33160/57600 [5:48:43<4:23:05,  1.55it/s]
                                                         
{'loss': 1.1924, 'learning_rate': 4.832055749128919e-07, 'epoch': 366.0}

 58%|█████▊    | 33160/57600 [5:48:43<4:23:05,  1.55it/s]
 58%|█████▊    | 33161/57600 [5:48:43<4:24:33,  1.54it/s]
 58%|█████▊    | 33162/57600 [5:48:44<4:30:45,  1.50it/s]
 58%|█████▊    | 33163/57600 [5:48:45<4:21:44,  1.56it/s]
 58%|█████▊    | 33164/57600 [5:48:45<4:16:14,  1.59it/s]
 58%|█████▊    | 33165/57600 [5:48:46<4:16:41,  1.59it/s]
 58%|█████▊    | 33166/57600 [5:48:46<4:06:35,  1.65it/s]
 58%|█████▊    | 33167/57600 [5:48:47<4:05:50,  1.66it/s]
 58%|█████▊    | 33168/57600 [5:48:48<4:06:55,  1.65it/s]
 58%|█████▊    | 33169/57600 [5:48:48<4:11:43,  1.62it/s]
 58%|█████▊    | 33170/57600 [5:48:49<4:15:07,  1.60it/s]
 58%|█████▊    | 33171/57600 [5:48:49<4:15:22,  1.59it/s]
 58%|█████▊    | 33172/57600 [5:48:50<4:14:55,  1.60it/s]
 58%|█████▊    | 33173/57600 [5:48:51<4:12:22,  1.61it/s]
 58%|█████▊    | 33174/57600 [5:48:51<4:12:57,  1.61it/s]
 58%|█████▊    | 33175/57600 [5:48:52<4:15:59,  1.59it/s]
 58%|█████▊    | 33176/57600 [5:48:53<4:14:30,  1.60it/s]
 58%|█████▊    | 33177/57600 [5:48:53<4:14:53,  1.60it/s]
 58%|█████▊    | 33178/57600 [5:48:54<4:10:30,  1.62it/s]
 58%|█████▊    | 33179/57600 [5:48:54<4:07:58,  1.64it/s]
 58%|█████▊    | 33180/57600 [5:48:55<4:16:05,  1.59it/s]
                                                         
{'loss': 1.1987, 'learning_rate': 4.828919860627177e-07, 'epoch': 366.23}

 58%|█████▊    | 33180/57600 [5:48:55<4:16:05,  1.59it/s]
 58%|█████▊    | 33181/57600 [5:48:56<4:15:27,  1.59it/s]
 58%|█████▊    | 33182/57600 [5:48:56<4:13:30,  1.61it/s]
 58%|█████▊    | 33183/57600 [5:48:57<4:14:05,  1.60it/s]
 58%|█████▊    | 33184/57600 [5:48:58<4:11:35,  1.62it/s]
 58%|█████▊    | 33185/57600 [5:48:58<4:17:52,  1.58it/s]
 58%|█████▊    | 33186/57600 [5:48:59<4:18:17,  1.58it/s]
 58%|█████▊    | 33187/57600 [5:49:00<4:22:32,  1.55it/s]
 58%|█████▊    | 33188/57600 [5:49:00<4:20:42,  1.56it/s]
 58%|█████▊    | 33189/57600 [5:49:01<4:22:44,  1.55it/s]
 58%|█████▊    | 33190/57600 [5:49:01<4:20:53,  1.56it/s]
 58%|█████▊    | 33191/57600 [5:49:02<4:16:03,  1.59it/s]
 58%|█████▊    | 33192/57600 [5:49:03<4:31:08,  1.50it/s]
 58%|█████▊    | 33193/57600 [5:49:03<4:29:05,  1.51it/s]
 58%|█████▊    | 33194/57600 [5:49:04<4:30:11,  1.51it/s]
 58%|█████▊    | 33195/57600 [5:49:05<4:25:29,  1.53it/s]
 58%|█████▊    | 33196/57600 [5:49:05<4:19:29,  1.57it/s]
 58%|█████▊    | 33197/57600 [5:49:06<4:20:01,  1.56it/s]
 58%|█████▊    | 33198/57600 [5:49:07<4:21:09,  1.56it/s]
 58%|█████▊    | 33199/57600 [5:49:07<4:44:29,  1.43it/s]
 58%|█████▊    | 33200/57600 [5:49:08<4:35:03,  1.48it/s]
                                                         
{'loss': 1.1411, 'learning_rate': 4.825783972125435e-07, 'epoch': 366.45}

 58%|█████▊    | 33200/57600 [5:49:08<4:35:03,  1.48it/s]
 58%|█████▊    | 33201/57600 [5:49:09<4:27:13,  1.52it/s]
 58%|█████▊    | 33202/57600 [5:49:09<4:16:02,  1.59it/s]
 58%|█████▊    | 33203/57600 [5:49:10<4:13:31,  1.60it/s]
 58%|█████▊    | 33204/57600 [5:49:11<4:21:49,  1.55it/s]
 58%|█████▊    | 33205/57600 [5:49:11<4:15:18,  1.59it/s]
 58%|█████▊    | 33206/57600 [5:49:12<4:13:12,  1.61it/s]
 58%|█████▊    | 33207/57600 [5:49:12<4:22:14,  1.55it/s]
 58%|█████▊    | 33208/57600 [5:49:13<4:18:52,  1.57it/s]
 58%|█████▊    | 33209/57600 [5:49:14<4:10:38,  1.62it/s]
 58%|█████▊    | 33210/57600 [5:49:14<4:05:05,  1.66it/s]
 58%|█████▊    | 33211/57600 [5:49:15<4:04:37,  1.66it/s]
 58%|█████▊    | 33212/57600 [5:49:15<4:10:30,  1.62it/s]
 58%|█████▊    | 33213/57600 [5:49:16<4:11:40,  1.61it/s]
 58%|█████▊    | 33214/57600 [5:49:17<4:11:21,  1.62it/s]
 58%|█████▊    | 33215/57600 [5:49:17<4:13:04,  1.61it/s]
 58%|█████▊    | 33216/57600 [5:49:18<4:25:22,  1.53it/s]
 58%|█████▊    | 33217/57600 [5:49:19<4:23:48,  1.54it/s]
 58%|█████▊    | 33218/57600 [5:49:19<4:22:30,  1.55it/s]
 58%|█████▊    | 33219/57600 [5:49:20<4:16:37,  1.58it/s]
 58%|█████▊    | 33220/57600 [5:49:21<4:11:12,  1.62it/s]
                                                         
{'loss': 1.1467, 'learning_rate': 4.822648083623693e-07, 'epoch': 366.67}

 58%|█████▊    | 33220/57600 [5:49:21<4:11:12,  1.62it/s]
 58%|█████▊    | 33221/57600 [5:49:21<4:07:20,  1.64it/s]
 58%|█████▊    | 33222/57600 [5:49:22<4:05:59,  1.65it/s]
 58%|█████▊    | 33223/57600 [5:49:22<4:04:15,  1.66it/s]
 58%|█████▊    | 33224/57600 [5:49:23<4:03:41,  1.67it/s]
 58%|█████▊    | 33225/57600 [5:49:24<4:10:16,  1.62it/s]
 58%|█████▊    | 33226/57600 [5:49:24<4:15:53,  1.59it/s]
 58%|█████▊    | 33227/57600 [5:49:25<4:15:36,  1.59it/s]
 58%|█████▊    | 33228/57600 [5:49:26<4:18:54,  1.57it/s]
 58%|█████▊    | 33229/57600 [5:49:26<4:20:36,  1.56it/s]
 58%|█████▊    | 33230/57600 [5:49:27<4:23:14,  1.54it/s]
 58%|█████▊    | 33231/57600 [5:49:27<4:18:53,  1.57it/s]
 58%|█████▊    | 33232/57600 [5:49:28<4:15:05,  1.59it/s]
 58%|█████▊    | 33233/57600 [5:49:29<4:06:33,  1.65it/s]
 58%|█████▊    | 33234/57600 [5:49:29<4:07:05,  1.64it/s]
 58%|█████▊    | 33235/57600 [5:49:30<4:03:34,  1.67it/s]
 58%|█████▊    | 33236/57600 [5:49:30<4:04:03,  1.66it/s]
 58%|█████▊    | 33237/57600 [5:49:31<4:04:49,  1.66it/s]
 58%|█████▊    | 33238/57600 [5:49:32<4:04:48,  1.66it/s]
 58%|█████▊    | 33239/57600 [5:49:32<4:11:59,  1.61it/s]
 58%|█████▊    | 33240/57600 [5:49:33<4:04:38,  1.66it/s]
                                                         
{'loss': 1.1609, 'learning_rate': 4.819512195121951e-07, 'epoch': 366.89}

 58%|█████▊    | 33240/57600 [5:49:33<4:04:38,  1.66it/s]
 58%|█████▊    | 33241/57600 [5:49:33<4:04:27,  1.66it/s]
 58%|█████▊    | 33242/57600 [5:49:34<4:06:20,  1.65it/s]
 58%|█████▊    | 33243/57600 [5:49:35<4:06:46,  1.65it/s]
 58%|█████▊    | 33244/57600 [5:49:35<4:13:15,  1.60it/s]
 58%|█████▊    | 33245/57600 [5:49:36<4:16:12,  1.58it/s]
 58%|█████▊    | 33246/57600 [5:49:37<4:15:33,  1.59it/s]
 58%|█████▊    | 33247/57600 [5:49:37<4:18:28,  1.57it/s]
 58%|█████▊    | 33248/57600 [5:49:38<4:10:05,  1.62it/s]
 58%|█████▊    | 33249/57600 [5:49:38<4:06:18,  1.65it/s]
 58%|█████▊    | 33250/57600 [5:49:39<3:59:20,  1.70it/s]
 58%|█████▊    | 33251/57600 [5:49:40<4:18:27,  1.57it/s]
 58%|█████▊    | 33252/57600 [5:49:40<4:11:00,  1.62it/s]
 58%|█████▊    | 33253/57600 [5:49:41<4:08:36,  1.63it/s]
 58%|█████▊    | 33254/57600 [5:49:41<4:07:21,  1.64it/s]
 58%|█████▊    | 33255/57600 [5:49:42<4:01:03,  1.68it/s]
 58%|█████▊    | 33256/57600 [5:49:43<3:58:39,  1.70it/s]
 58%|█████▊    | 33257/57600 [5:49:43<4:02:30,  1.67it/s]
 58%|█████▊    | 33258/57600 [5:49:44<4:09:57,  1.62it/s]
 58%|█████▊    | 33259/57600 [5:49:45<4:09:49,  1.62it/s]
 58%|█████▊    | 33260/57600 [5:49:45<4:21:19,  1.55it/s]
                                                         
{'loss': 1.138, 'learning_rate': 4.816376306620209e-07, 'epoch': 367.11}

 58%|█████▊    | 33260/57600 [5:49:45<4:21:19,  1.55it/s]
 58%|█████▊    | 33261/57600 [5:49:46<4:14:04,  1.60it/s]
 58%|█████▊    | 33262/57600 [5:49:46<4:15:13,  1.59it/s]
 58%|█████▊    | 33263/57600 [5:49:47<4:13:07,  1.60it/s]
 58%|█████▊    | 33264/57600 [5:49:48<4:15:33,  1.59it/s]
 58%|█████▊    | 33265/57600 [5:49:48<4:13:04,  1.60it/s]
 58%|█████▊    | 33266/57600 [5:49:49<4:07:12,  1.64it/s]
 58%|█████▊    | 33267/57600 [5:49:50<4:14:54,  1.59it/s]
 58%|█████▊    | 33268/57600 [5:49:50<4:12:09,  1.61it/s]
 58%|█████▊    | 33269/57600 [5:49:51<4:15:19,  1.59it/s]
 58%|█████▊    | 33270/57600 [5:49:52<4:25:31,  1.53it/s]
 58%|█████▊    | 33271/57600 [5:49:52<4:19:31,  1.56it/s]
 58%|█████▊    | 33272/57600 [5:49:53<4:18:00,  1.57it/s]
 58%|█████▊    | 33273/57600 [5:49:53<4:15:07,  1.59it/s]
 58%|█████▊    | 33274/57600 [5:49:54<4:11:08,  1.61it/s]
 58%|█████▊    | 33275/57600 [5:49:55<4:20:11,  1.56it/s]
 58%|█████▊    | 33276/57600 [5:49:55<4:09:20,  1.63it/s]
 58%|█████▊    | 33277/57600 [5:49:56<4:04:41,  1.66it/s]
 58%|█████▊    | 33278/57600 [5:49:56<4:00:15,  1.69it/s]
 58%|█████▊    | 33279/57600 [5:49:57<4:02:01,  1.67it/s]
 58%|█████▊    | 33280/57600 [5:49:58<4:02:25,  1.67it/s]
                                                         
{'loss': 1.1967, 'learning_rate': 4.813240418118467e-07, 'epoch': 367.33}

 58%|█████▊    | 33280/57600 [5:49:58<4:02:25,  1.67it/s]
 58%|█████▊    | 33281/57600 [5:49:58<4:01:27,  1.68it/s]
 58%|█████▊    | 33282/57600 [5:49:59<4:02:07,  1.67it/s]
 58%|█████▊    | 33283/57600 [5:49:59<4:04:33,  1.66it/s]
 58%|█████▊    | 33284/57600 [5:50:00<4:06:23,  1.64it/s]
 58%|█████▊    | 33285/57600 [5:50:01<4:11:16,  1.61it/s]
 58%|█████▊    | 33286/57600 [5:50:01<4:16:40,  1.58it/s]
 58%|█████▊    | 33287/57600 [5:50:02<4:12:07,  1.61it/s]
 58%|█████▊    | 33288/57600 [5:50:02<4:07:59,  1.63it/s]
 58%|█████▊    | 33289/57600 [5:50:03<4:09:53,  1.62it/s]
 58%|█████▊    | 33290/57600 [5:50:04<4:08:55,  1.63it/s]
 58%|█████▊    | 33291/57600 [5:50:04<4:14:02,  1.59it/s]
 58%|█████▊    | 33292/57600 [5:50:05<4:19:53,  1.56it/s]
 58%|█████▊    | 33293/57600 [5:50:06<4:27:28,  1.51it/s]
 58%|█████▊    | 33294/57600 [5:50:06<4:24:39,  1.53it/s]
 58%|█████▊    | 33295/57600 [5:50:07<4:20:18,  1.56it/s]
 58%|█████▊    | 33296/57600 [5:50:08<4:16:33,  1.58it/s]
 58%|█████▊    | 33297/57600 [5:50:08<4:25:00,  1.53it/s]
 58%|█████▊    | 33298/57600 [5:50:09<4:21:15,  1.55it/s]
 58%|█████▊    | 33299/57600 [5:50:10<4:20:38,  1.55it/s]
 58%|█████▊    | 33300/57600 [5:50:10<4:16:21,  1.58it/s]
                                                         
{'loss': 1.1784, 'learning_rate': 4.810104529616724e-07, 'epoch': 367.55}

 58%|█████▊    | 33300/57600 [5:50:10<4:16:21,  1.58it/s]
 58%|█████▊    | 33301/57600 [5:50:11<4:16:27,  1.58it/s]
 58%|█████▊    | 33302/57600 [5:50:11<4:12:32,  1.60it/s]
 58%|█████▊    | 33303/57600 [5:50:12<4:16:17,  1.58it/s]
 58%|█████▊    | 33304/57600 [5:50:13<4:13:16,  1.60it/s]
 58%|█████▊    | 33305/57600 [5:50:13<4:12:23,  1.60it/s]
 58%|█████▊    | 33306/57600 [5:50:14<4:16:47,  1.58it/s]
 58%|█████▊    | 33307/57600 [5:50:15<4:14:59,  1.59it/s]
 58%|█████▊    | 33308/57600 [5:50:15<4:13:49,  1.60it/s]
 58%|█████▊    | 33309/57600 [5:50:16<4:09:26,  1.62it/s]
 58%|█████▊    | 33310/57600 [5:50:16<4:06:20,  1.64it/s]
 58%|█████▊    | 33311/57600 [5:50:17<4:06:09,  1.64it/s]
 58%|█████▊    | 33312/57600 [5:50:18<4:10:38,  1.62it/s]
 58%|█████▊    | 33313/57600 [5:50:18<4:11:54,  1.61it/s]
 58%|█████▊    | 33314/57600 [5:50:19<4:10:46,  1.61it/s]
 58%|█████▊    | 33315/57600 [5:50:20<4:17:19,  1.57it/s]
 58%|█████▊    | 33316/57600 [5:50:20<4:19:01,  1.56it/s]
 58%|█████▊    | 33317/57600 [5:50:21<4:22:48,  1.54it/s]
 58%|█████▊    | 33318/57600 [5:50:21<4:12:31,  1.60it/s]
 58%|█████▊    | 33319/57600 [5:50:22<4:15:15,  1.59it/s]
 58%|█████▊    | 33320/57600 [5:50:23<4:22:29,  1.54it/s]
                                                         
{'loss': 1.1341, 'learning_rate': 4.806968641114983e-07, 'epoch': 367.77}

 58%|█████▊    | 33320/57600 [5:50:23<4:22:29,  1.54it/s]
 58%|█████▊    | 33321/57600 [5:50:23<4:20:21,  1.55it/s]
 58%|█████▊    | 33322/57600 [5:50:24<4:21:24,  1.55it/s]
 58%|█████▊    | 33323/57600 [5:50:25<4:18:06,  1.57it/s]
 58%|█████▊    | 33324/57600 [5:50:25<4:09:08,  1.62it/s]
 58%|█████▊    | 33325/57600 [5:50:26<4:11:14,  1.61it/s]
 58%|█████▊    | 33326/57600 [5:50:27<4:18:16,  1.57it/s]
 58%|█████▊    | 33327/57600 [5:50:27<4:15:50,  1.58it/s]
 58%|█████▊    | 33328/57600 [5:50:28<4:14:55,  1.59it/s]
 58%|█████▊    | 33329/57600 [5:50:28<4:14:51,  1.59it/s]
 58%|█████▊    | 33330/57600 [5:50:29<4:16:33,  1.58it/s]
 58%|█████▊    | 33331/57600 [5:50:30<4:12:08,  1.60it/s]
 58%|█████▊    | 33332/57600 [5:50:30<4:03:53,  1.66it/s]
 58%|█████▊    | 33333/57600 [5:50:31<4:12:38,  1.60it/s]
 58%|█████▊    | 33334/57600 [5:50:32<4:10:33,  1.61it/s]
 58%|█████▊    | 33335/57600 [5:50:32<4:11:17,  1.61it/s]
 58%|█████▊    | 33336/57600 [5:50:33<4:16:29,  1.58it/s]
 58%|█████▊    | 33337/57600 [5:50:33<4:12:53,  1.60it/s]
 58%|█████▊    | 33338/57600 [5:50:34<4:15:57,  1.58it/s]
 58%|█████▊    | 33339/57600 [5:50:35<4:15:55,  1.58it/s]
 58%|█████▊    | 33340/57600 [5:50:35<4:07:59,  1.63it/s]
                                                         
{'loss': 1.163, 'learning_rate': 4.803832752613239e-07, 'epoch': 367.99}

 58%|█████▊    | 33340/57600 [5:50:35<4:07:59,  1.63it/s]
 58%|█████▊    | 33341/57600 [5:50:36<4:19:21,  1.56it/s]
 58%|█████▊    | 33342/57600 [5:50:37<4:21:11,  1.55it/s]
 58%|█████▊    | 33343/57600 [5:50:37<4:23:16,  1.54it/s]
 58%|█████▊    | 33344/57600 [5:50:38<4:19:03,  1.56it/s]
 58%|█████▊    | 33345/57600 [5:50:39<4:17:04,  1.57it/s]
 58%|█████▊    | 33346/57600 [5:50:39<4:25:36,  1.52it/s]
 58%|█████▊    | 33347/57600 [5:50:40<4:22:13,  1.54it/s]
 58%|█████▊    | 33348/57600 [5:50:41<4:24:57,  1.53it/s]
 58%|█████▊    | 33349/57600 [5:50:41<4:26:22,  1.52it/s]
 58%|█████▊    | 33350/57600 [5:50:42<4:18:12,  1.57it/s]
 58%|█████▊    | 33351/57600 [5:50:42<4:15:43,  1.58it/s]
 58%|█████▊    | 33352/57600 [5:50:43<4:16:13,  1.58it/s]
 58%|█████▊    | 33353/57600 [5:50:44<4:11:07,  1.61it/s]
 58%|█████▊    | 33354/57600 [5:50:44<4:04:20,  1.65it/s]
 58%|█████▊    | 33355/57600 [5:50:45<4:11:38,  1.61it/s]
 58%|█████▊    | 33356/57600 [5:50:45<4:10:55,  1.61it/s]
 58%|█████▊    | 33357/57600 [5:50:46<4:11:52,  1.60it/s]
 58%|█████▊    | 33358/57600 [5:50:47<4:06:40,  1.64it/s]
 58%|█████▊    | 33359/57600 [5:50:47<4:08:03,  1.63it/s]
 58%|█████▊    | 33360/57600 [5:50:48<4:12:20,  1.60it/s]
                                                         
{'loss': 1.1603, 'learning_rate': 4.800696864111498e-07, 'epoch': 368.21}

 58%|█████▊    | 33360/57600 [5:50:48<4:12:20,  1.60it/s]
 58%|█████▊    | 33361/57600 [5:50:49<4:14:24,  1.59it/s]
 58%|█████▊    | 33362/57600 [5:50:49<4:12:28,  1.60it/s]
 58%|█████▊    | 33363/57600 [5:50:50<4:18:41,  1.56it/s]
 58%|█████▊    | 33364/57600 [5:50:51<4:14:24,  1.59it/s]
 58%|█████▊    | 33365/57600 [5:50:51<4:17:45,  1.57it/s]
 58%|█████▊    | 33366/57600 [5:50:52<4:10:47,  1.61it/s]
 58%|█████▊    | 33367/57600 [5:50:52<4:11:53,  1.60it/s]
 58%|█████▊    | 33368/57600 [5:50:53<4:05:06,  1.65it/s]
 58%|█████▊    | 33369/57600 [5:50:54<4:01:52,  1.67it/s]
 58%|█████▊    | 33370/57600 [5:50:54<4:14:02,  1.59it/s]
 58%|█████▊    | 33371/57600 [5:50:55<4:22:44,  1.54it/s]
 58%|█████▊    | 33372/57600 [5:50:56<4:20:02,  1.55it/s]
 58%|█████▊    | 33373/57600 [5:50:56<4:19:08,  1.56it/s]
 58%|█████▊    | 33374/57600 [5:50:57<4:15:04,  1.58it/s]
 58%|█████▊    | 33375/57600 [5:50:57<4:11:46,  1.60it/s]
 58%|█████▊    | 33376/57600 [5:50:58<4:06:57,  1.63it/s]
 58%|█████▊    | 33377/57600 [5:50:59<4:10:48,  1.61it/s]
 58%|█████▊    | 33378/57600 [5:50:59<4:14:07,  1.59it/s]
 58%|█████▊    | 33379/57600 [5:51:00<4:17:24,  1.57it/s]
 58%|█████▊    | 33380/57600 [5:51:01<4:21:38,  1.54it/s]
                                                         
{'loss': 1.1226, 'learning_rate': 4.797560975609757e-07, 'epoch': 368.43}

 58%|█████▊    | 33380/57600 [5:51:01<4:21:38,  1.54it/s]
 58%|█████▊    | 33381/57600 [5:51:01<4:20:20,  1.55it/s]
 58%|█████▊    | 33382/57600 [5:51:02<4:16:09,  1.58it/s]
 58%|█████▊    | 33383/57600 [5:51:02<4:14:13,  1.59it/s]
 58%|█████▊    | 33384/57600 [5:51:03<4:17:05,  1.57it/s]
 58%|█████▊    | 33385/57600 [5:51:04<4:16:47,  1.57it/s]
 58%|█████▊    | 33386/57600 [5:51:04<4:19:45,  1.55it/s]
 58%|█████▊    | 33387/57600 [5:51:05<4:16:40,  1.57it/s]
 58%|█████▊    | 33388/57600 [5:51:06<4:09:25,  1.62it/s]
 58%|█████▊    | 33389/57600 [5:51:06<4:11:08,  1.61it/s]
 58%|█████▊    | 33390/57600 [5:51:07<4:09:29,  1.62it/s]
 58%|█████▊    | 33391/57600 [5:51:07<4:03:59,  1.65it/s]
 58%|█████▊    | 33392/57600 [5:51:08<4:11:21,  1.61it/s]
 58%|█████▊    | 33393/57600 [5:51:09<4:05:05,  1.65it/s]
 58%|█████▊    | 33394/57600 [5:51:09<4:02:32,  1.66it/s]
 58%|█████▊    | 33395/57600 [5:51:10<4:06:54,  1.63it/s]
 58%|█████▊    | 33396/57600 [5:51:11<4:11:55,  1.60it/s]
 58%|█████▊    | 33397/57600 [5:51:11<4:09:42,  1.62it/s]
 58%|█████▊    | 33398/57600 [5:51:12<4:11:30,  1.60it/s]
 58%|█████▊    | 33399/57600 [5:51:12<4:13:45,  1.59it/s]
 58%|█████▊    | 33400/57600 [5:51:13<4:17:59,  1.56it/s]
                                                         
{'loss': 1.1896, 'learning_rate': 4.794425087108013e-07, 'epoch': 368.65}

 58%|█████▊    | 33400/57600 [5:51:13<4:17:59,  1.56it/s]
 58%|█████▊    | 33401/57600 [5:51:14<4:12:02,  1.60it/s]
 58%|█████▊    | 33402/57600 [5:51:14<4:11:09,  1.61it/s]
 58%|█████▊    | 33403/57600 [5:51:15<4:10:12,  1.61it/s]
 58%|█████▊    | 33404/57600 [5:51:16<4:10:52,  1.61it/s]
 58%|█████▊    | 33405/57600 [5:51:16<4:04:35,  1.65it/s]
 58%|█████▊    | 33406/57600 [5:51:17<4:08:47,  1.62it/s]
 58%|█████▊    | 33407/57600 [5:51:17<4:03:41,  1.65it/s]
 58%|█████▊    | 33408/57600 [5:51:18<4:03:49,  1.65it/s]
 58%|█████▊    | 33409/57600 [5:51:19<3:59:30,  1.68it/s]
 58%|█████▊    | 33410/57600 [5:51:19<4:02:28,  1.66it/s]
 58%|█████▊    | 33411/57600 [5:51:20<4:16:31,  1.57it/s]
 58%|█████▊    | 33412/57600 [5:51:20<4:10:40,  1.61it/s]
 58%|█████▊    | 33413/57600 [5:51:21<4:09:33,  1.62it/s]
 58%|█████▊    | 33414/57600 [5:51:22<4:05:33,  1.64it/s]
 58%|█████▊    | 33415/57600 [5:51:22<4:06:41,  1.63it/s]
 58%|█████▊    | 33416/57600 [5:51:23<4:08:43,  1.62it/s]
 58%|█████▊    | 33417/57600 [5:51:23<4:02:41,  1.66it/s]
 58%|█████▊    | 33418/57600 [5:51:24<4:10:33,  1.61it/s]
 58%|█████▊    | 33419/57600 [5:51:25<4:06:13,  1.64it/s]
 58%|█████▊    | 33420/57600 [5:51:25<4:00:57,  1.67it/s]
                                                         
{'loss': 1.1895, 'learning_rate': 4.791289198606272e-07, 'epoch': 368.87}

 58%|█████▊    | 33420/57600 [5:51:25<4:00:57,  1.67it/s]
 58%|█████▊    | 33421/57600 [5:51:26<4:03:03,  1.66it/s]
 58%|█████▊    | 33422/57600 [5:51:26<3:59:36,  1.68it/s]
 58%|█████▊    | 33423/57600 [5:51:27<3:55:05,  1.71it/s]
 58%|█████▊    | 33424/57600 [5:51:28<3:56:12,  1.71it/s]
 58%|█████▊    | 33425/57600 [5:51:28<3:56:56,  1.70it/s]
 58%|█████▊    | 33426/57600 [5:51:29<4:00:00,  1.68it/s]
 58%|█████▊    | 33427/57600 [5:51:29<4:08:21,  1.62it/s]
 58%|█████▊    | 33428/57600 [5:51:30<4:26:54,  1.51it/s]
 58%|█████▊    | 33429/57600 [5:51:31<4:18:26,  1.56it/s]
 58%|█████▊    | 33430/57600 [5:51:31<4:16:16,  1.57it/s]
 58%|█████▊    | 33431/57600 [5:51:32<4:21:25,  1.54it/s]
 58%|█████▊    | 33432/57600 [5:51:33<4:27:44,  1.50it/s]
 58%|█████▊    | 33433/57600 [5:51:33<4:26:15,  1.51it/s]
 58%|█████▊    | 33434/57600 [5:51:34<4:18:27,  1.56it/s]
 58%|█████▊    | 33435/57600 [5:51:35<4:14:53,  1.58it/s]
 58%|█████▊    | 33436/57600 [5:51:35<4:14:26,  1.58it/s]
 58%|█████▊    | 33437/57600 [5:51:36<4:15:27,  1.58it/s]
 58%|█████▊    | 33438/57600 [5:51:37<4:12:53,  1.59it/s]
 58%|█████▊    | 33439/57600 [5:51:37<4:12:38,  1.59it/s]
 58%|█████▊    | 33440/57600 [5:51:38<4:08:46,  1.62it/s]
                                                         
{'loss': 1.1875, 'learning_rate': 4.788153310104529e-07, 'epoch': 369.09}

 58%|█████▊    | 33440/57600 [5:51:38<4:08:46,  1.62it/s]
 58%|█████▊    | 33441/57600 [5:51:38<4:03:22,  1.65it/s]
 58%|█████▊    | 33442/57600 [5:51:39<4:00:34,  1.67it/s]
 58%|█████▊    | 33443/57600 [5:51:40<4:00:40,  1.67it/s]
 58%|█████▊    | 33444/57600 [5:51:40<3:55:35,  1.71it/s]
 58%|█████▊    | 33445/57600 [5:51:41<3:52:48,  1.73it/s]
 58%|█████▊    | 33446/57600 [5:51:41<3:56:08,  1.70it/s]
 58%|█████▊    | 33447/57600 [5:51:42<4:02:14,  1.66it/s]
 58%|█████▊    | 33448/57600 [5:51:43<4:17:13,  1.56it/s]
 58%|█████▊    | 33449/57600 [5:51:43<4:30:47,  1.49it/s]
 58%|█████▊    | 33450/57600 [5:51:44<4:28:08,  1.50it/s]
 58%|█████▊    | 33451/57600 [5:51:45<4:23:15,  1.53it/s]
 58%|█████▊    | 33452/57600 [5:51:45<4:18:09,  1.56it/s]
 58%|█████▊    | 33453/57600 [5:51:46<4:19:08,  1.55it/s]
 58%|█████▊    | 33454/57600 [5:51:47<4:20:45,  1.54it/s]
 58%|█████▊    | 33455/57600 [5:51:47<4:14:00,  1.58it/s]
 58%|█████▊    | 33456/57600 [5:51:48<4:18:09,  1.56it/s]
 58%|█████▊    | 33457/57600 [5:51:48<4:17:19,  1.56it/s]
 58%|█████▊    | 33458/57600 [5:51:49<4:14:04,  1.58it/s]
 58%|█████▊    | 33459/57600 [5:51:50<4:10:30,  1.61it/s]
 58%|█████▊    | 33460/57600 [5:51:50<4:15:00,  1.58it/s]
                                                         
{'loss': 1.1469, 'learning_rate': 4.785017421602787e-07, 'epoch': 369.32}

 58%|█████▊    | 33460/57600 [5:51:50<4:15:00,  1.58it/s]
 58%|█████▊    | 33461/57600 [5:51:51<4:09:24,  1.61it/s]
 58%|█████▊    | 33462/57600 [5:51:52<4:13:00,  1.59it/s]
 58%|█████▊    | 33463/57600 [5:51:52<4:08:40,  1.62it/s]
 58%|█████▊    | 33464/57600 [5:51:53<4:03:11,  1.65it/s]
 58%|█████▊    | 33465/57600 [5:51:53<4:11:17,  1.60it/s]
 58%|█████▊    | 33466/57600 [5:51:54<4:18:46,  1.55it/s]
 58%|█████▊    | 33467/57600 [5:51:55<4:15:05,  1.58it/s]
 58%|█████▊    | 33468/57600 [5:51:55<4:10:58,  1.60it/s]
 58%|█████▊    | 33469/57600 [5:51:56<4:06:59,  1.63it/s]
 58%|█████▊    | 33470/57600 [5:51:57<4:13:34,  1.59it/s]
 58%|█████▊    | 33471/57600 [5:51:57<4:19:45,  1.55it/s]
 58%|█████▊    | 33472/57600 [5:51:58<4:22:31,  1.53it/s]
 58%|█████▊    | 33473/57600 [5:51:59<4:18:31,  1.56it/s]
 58%|█████▊    | 33474/57600 [5:51:59<4:14:29,  1.58it/s]
 58%|█████▊    | 33475/57600 [5:52:00<4:12:29,  1.59it/s]
 58%|█████▊    | 33476/57600 [5:52:00<4:06:39,  1.63it/s]
 58%|█████▊    | 33477/57600 [5:52:01<4:15:03,  1.58it/s]
 58%|█████▊    | 33478/57600 [5:52:02<4:05:32,  1.64it/s]
 58%|█████▊    | 33479/57600 [5:52:02<4:09:10,  1.61it/s]
 58%|█████▊    | 33480/57600 [5:52:03<4:16:34,  1.57it/s]
                                                         
{'loss': 1.1542, 'learning_rate': 4.781881533101045e-07, 'epoch': 369.54}

 58%|█████▊    | 33480/57600 [5:52:03<4:16:34,  1.57it/s]
 58%|█████▊    | 33481/57600 [5:52:04<4:17:49,  1.56it/s]
 58%|█████▊    | 33482/57600 [5:52:04<4:18:56,  1.55it/s]
 58%|█████▊    | 33483/57600 [5:52:05<4:14:25,  1.58it/s]
 58%|█████▊    | 33484/57600 [5:52:05<4:14:21,  1.58it/s]
 58%|█████▊    | 33485/57600 [5:52:06<4:11:43,  1.60it/s]
 58%|█████▊    | 33486/57600 [5:52:07<4:15:45,  1.57it/s]
 58%|█████▊    | 33487/57600 [5:52:07<4:19:32,  1.55it/s]
 58%|█████▊    | 33488/57600 [5:52:08<4:19:30,  1.55it/s]
 58%|█████▊    | 33489/57600 [5:52:09<4:15:00,  1.58it/s]
 58%|█████▊    | 33490/57600 [5:52:09<4:03:55,  1.65it/s]
 58%|█████▊    | 33491/57600 [5:52:10<4:06:59,  1.63it/s]
 58%|█████▊    | 33492/57600 [5:52:10<4:04:54,  1.64it/s]
 58%|█████▊    | 33493/57600 [5:52:11<4:08:46,  1.61it/s]
 58%|█████▊    | 33494/57600 [5:52:12<4:13:51,  1.58it/s]
 58%|█████▊    | 33495/57600 [5:52:12<4:03:49,  1.65it/s]
 58%|█████▊    | 33496/57600 [5:52:13<4:02:42,  1.66it/s]
 58%|█████▊    | 33497/57600 [5:52:13<4:01:54,  1.66it/s]
 58%|█████▊    | 33498/57600 [5:52:14<3:56:48,  1.70it/s]
 58%|█████▊    | 33499/57600 [5:52:15<3:57:15,  1.69it/s]
 58%|█████▊    | 33500/57600 [5:52:15<4:05:31,  1.64it/s]
                                                         
{'loss': 1.219, 'learning_rate': 4.778745644599303e-07, 'epoch': 369.76}

 58%|█████▊    | 33500/57600 [5:52:15<4:05:31,  1.64it/s]
 58%|█████▊    | 33501/57600 [5:52:16<4:15:44,  1.57it/s]
 58%|█████▊    | 33502/57600 [5:52:17<4:15:51,  1.57it/s]
 58%|█████▊    | 33503/57600 [5:52:17<4:28:51,  1.49it/s]
 58%|█████▊    | 33504/57600 [5:52:18<4:23:44,  1.52it/s]
 58%|█████▊    | 33505/57600 [5:52:19<4:15:10,  1.57it/s]
 58%|█████▊    | 33506/57600 [5:52:19<4:12:22,  1.59it/s]
 58%|█████▊    | 33507/57600 [5:52:20<4:16:27,  1.57it/s]
 58%|█████▊    | 33508/57600 [5:52:20<4:10:34,  1.60it/s]
 58%|█████▊    | 33509/57600 [5:52:21<4:03:04,  1.65it/s]
 58%|█████▊    | 33510/57600 [5:52:22<3:59:40,  1.68it/s]
 58%|█████▊    | 33511/57600 [5:52:22<4:06:55,  1.63it/s]
 58%|█████▊    | 33512/57600 [5:52:23<4:03:30,  1.65it/s]
 58%|█████▊    | 33513/57600 [5:52:23<4:03:34,  1.65it/s]
 58%|█████▊    | 33514/57600 [5:52:24<4:04:53,  1.64it/s]
 58%|█████▊    | 33515/57600 [5:52:25<4:04:23,  1.64it/s]
 58%|█████▊    | 33516/57600 [5:52:25<4:02:11,  1.66it/s]
 58%|█████▊    | 33517/57600 [5:52:26<4:09:24,  1.61it/s]
 58%|█████▊    | 33518/57600 [5:52:27<4:16:06,  1.57it/s]
 58%|█████▊    | 33519/57600 [5:52:27<4:08:48,  1.61it/s]
 58%|█████▊    | 33520/57600 [5:52:28<4:09:34,  1.61it/s]
                                                         
{'loss': 1.1547, 'learning_rate': 4.775609756097561e-07, 'epoch': 369.98}

 58%|█████▊    | 33520/57600 [5:52:28<4:09:34,  1.61it/s]
 58%|█████▊    | 33521/57600 [5:52:29<4:22:51,  1.53it/s]
 58%|█████▊    | 33522/57600 [5:52:29<4:20:12,  1.54it/s]
 58%|█████▊    | 33523/57600 [5:52:30<4:20:47,  1.54it/s]
 58%|█████▊    | 33524/57600 [5:52:31<4:28:25,  1.49it/s]
 58%|█████▊    | 33525/57600 [5:52:31<4:27:58,  1.50it/s]
 58%|█████▊    | 33526/57600 [5:52:32<4:21:15,  1.54it/s]
 58%|█████▊    | 33527/57600 [5:52:32<4:15:37,  1.57it/s]
 58%|█████▊    | 33528/57600 [5:52:33<4:22:10,  1.53it/s]
 58%|█████▊    | 33529/57600 [5:52:34<4:18:26,  1.55it/s]
 58%|█████▊    | 33530/57600 [5:52:34<4:20:33,  1.54it/s]
 58%|█████▊    | 33531/57600 [5:52:35<4:14:20,  1.58it/s]
 58%|█████▊    | 33532/57600 [5:52:36<4:11:10,  1.60it/s]
 58%|█████▊    | 33533/57600 [5:52:36<4:11:25,  1.60it/s]
 58%|█████▊    | 33534/57600 [5:52:37<4:11:14,  1.60it/s]
 58%|█████▊    | 33535/57600 [5:52:37<4:12:36,  1.59it/s]
 58%|█████▊    | 33536/57600 [5:52:38<4:24:58,  1.51it/s]
 58%|█████▊    | 33537/57600 [5:52:39<4:21:50,  1.53it/s]
 58%|█████▊    | 33538/57600 [5:52:39<4:13:20,  1.58it/s]
 58%|█████▊    | 33539/57600 [5:52:40<4:05:19,  1.63it/s]
 58%|█████▊    | 33540/57600 [5:52:41<3:58:25,  1.68it/s]
                                                         
{'loss': 1.1719, 'learning_rate': 4.772473867595819e-07, 'epoch': 370.2}

 58%|█████▊    | 33540/57600 [5:52:41<3:58:25,  1.68it/s]
 58%|█████▊    | 33541/57600 [5:52:41<4:06:51,  1.62it/s]
 58%|█████▊    | 33542/57600 [5:52:42<4:13:32,  1.58it/s]
 58%|█████▊    | 33543/57600 [5:52:42<4:09:08,  1.61it/s]
 58%|█████▊    | 33544/57600 [5:52:43<4:06:32,  1.63it/s]
 58%|█████▊    | 33545/57600 [5:52:44<3:59:25,  1.67it/s]
 58%|█████▊    | 33546/57600 [5:52:44<3:58:43,  1.68it/s]
 58%|█████▊    | 33547/57600 [5:52:45<3:59:34,  1.67it/s]
 58%|█████▊    | 33548/57600 [5:52:45<4:01:14,  1.66it/s]
 58%|█████▊    | 33549/57600 [5:52:46<4:08:57,  1.61it/s]
 58%|█████▊    | 33550/57600 [5:52:47<4:13:54,  1.58it/s]
 58%|█████▊    | 33551/57600 [5:52:47<4:13:15,  1.58it/s]
 58%|█████▊    | 33552/57600 [5:52:48<4:08:54,  1.61it/s]
 58%|█████▊    | 33553/57600 [5:52:49<4:14:43,  1.57it/s]
 58%|█████▊    | 33554/57600 [5:52:49<4:05:38,  1.63it/s]
 58%|█████▊    | 33555/57600 [5:52:50<4:11:23,  1.59it/s]
 58%|█████▊    | 33556/57600 [5:52:51<4:11:45,  1.59it/s]
 58%|█████▊    | 33557/57600 [5:52:51<4:12:07,  1.59it/s]
 58%|█████▊    | 33558/57600 [5:52:52<4:09:58,  1.60it/s]
 58%|█████▊    | 33559/57600 [5:52:52<4:11:07,  1.60it/s]
 58%|█████▊    | 33560/57600 [5:52:53<4:22:25,  1.53it/s]
                                                         
{'loss': 1.123, 'learning_rate': 4.769337979094076e-07, 'epoch': 370.42}

 58%|█████▊    | 33560/57600 [5:52:53<4:22:25,  1.53it/s]
 58%|█████▊    | 33561/57600 [5:52:54<4:17:50,  1.55it/s]
 58%|█████▊    | 33562/57600 [5:52:54<4:11:49,  1.59it/s]
 58%|█████▊    | 33563/57600 [5:52:55<4:05:34,  1.63it/s]
 58%|█████▊    | 33564/57600 [5:52:56<4:09:37,  1.60it/s]
 58%|█████▊    | 33565/57600 [5:52:56<4:16:42,  1.56it/s]
 58%|█████▊    | 33566/57600 [5:52:57<4:07:52,  1.62it/s]
 58%|█████▊    | 33567/57600 [5:52:57<4:03:08,  1.65it/s]
 58%|█████▊    | 33568/57600 [5:52:58<4:08:00,  1.61it/s]
 58%|█████▊    | 33569/57600 [5:52:59<4:06:04,  1.63it/s]
 58%|█████▊    | 33570/57600 [5:52:59<4:07:33,  1.62it/s]
 58%|█████▊    | 33571/57600 [5:53:00<4:04:57,  1.63it/s]
 58%|█████▊    | 33572/57600 [5:53:00<4:02:56,  1.65it/s]
 58%|█████▊    | 33573/57600 [5:53:01<4:06:59,  1.62it/s]
 58%|█████▊    | 33574/57600 [5:53:02<4:15:41,  1.57it/s]
 58%|█████▊    | 33575/57600 [5:53:02<4:22:49,  1.52it/s]
 58%|█████▊    | 33576/57600 [5:53:03<4:19:10,  1.54it/s]
 58%|█████▊    | 33577/57600 [5:53:04<4:09:24,  1.61it/s]
 58%|█████▊    | 33578/57600 [5:53:04<4:12:39,  1.58it/s]
 58%|█████▊    | 33579/57600 [5:53:05<4:07:47,  1.62it/s]
 58%|█████▊    | 33580/57600 [5:53:06<4:05:08,  1.63it/s]
                                                         
{'loss': 1.1784, 'learning_rate': 4.766202090592334e-07, 'epoch': 370.64}

 58%|█████▊    | 33580/57600 [5:53:06<4:05:08,  1.63it/s]
 58%|█████▊    | 33581/57600 [5:53:06<4:16:49,  1.56it/s]
 58%|█████▊    | 33582/57600 [5:53:07<4:16:54,  1.56it/s]
 58%|█████▊    | 33583/57600 [5:53:08<4:17:57,  1.55it/s]
 58%|█████▊    | 33584/57600 [5:53:08<4:17:51,  1.55it/s]
 58%|█████▊    | 33585/57600 [5:53:09<4:16:00,  1.56it/s]
 58%|█████▊    | 33586/57600 [5:53:09<4:12:14,  1.59it/s]
 58%|█████▊    | 33587/57600 [5:53:10<4:12:36,  1.58it/s]
 58%|█████▊    | 33588/57600 [5:53:11<4:06:21,  1.62it/s]
 58%|█████▊    | 33589/57600 [5:53:11<4:00:43,  1.66it/s]
 58%|█████▊    | 33590/57600 [5:53:12<4:00:21,  1.66it/s]
 58%|█████▊    | 33591/57600 [5:53:12<3:57:38,  1.68it/s]
 58%|█████▊    | 33592/57600 [5:53:13<4:02:28,  1.65it/s]
 58%|█████▊    | 33593/57600 [5:53:14<3:57:51,  1.68it/s]
 58%|█████▊    | 33594/57600 [5:53:14<4:03:23,  1.64it/s]
 58%|█████▊    | 33595/57600 [5:53:15<4:03:36,  1.64it/s]
 58%|█████▊    | 33596/57600 [5:53:15<3:59:06,  1.67it/s]
 58%|█████▊    | 33597/57600 [5:53:16<4:01:51,  1.65it/s]
 58%|█████▊    | 33598/57600 [5:53:17<4:01:06,  1.66it/s]
 58%|█████▊    | 33599/57600 [5:53:17<3:59:42,  1.67it/s]
 58%|█████▊    | 33600/57600 [5:53:18<4:11:09,  1.59it/s]
                                                         
{'loss': 1.1852, 'learning_rate': 4.763066202090592e-07, 'epoch': 370.86}

 58%|█████▊    | 33600/57600 [5:53:18<4:11:09,  1.59it/s]
 58%|█████▊    | 33601/57600 [5:53:19<4:24:36,  1.51it/s]
 58%|█████▊    | 33602/57600 [5:53:19<4:22:12,  1.53it/s]
 58%|█████▊    | 33603/57600 [5:53:20<4:18:33,  1.55it/s]
 58%|█████▊    | 33604/57600 [5:53:20<4:12:51,  1.58it/s]
 58%|█████▊    | 33605/57600 [5:53:21<4:10:43,  1.60it/s]
 58%|█████▊    | 33606/57600 [5:53:22<4:06:58,  1.62it/s]
 58%|█████▊    | 33607/57600 [5:53:22<4:10:52,  1.59it/s]
 58%|█████▊    | 33608/57600 [5:53:23<4:22:14,  1.52it/s]
 58%|█████▊    | 33609/57600 [5:53:24<4:16:29,  1.56it/s]
 58%|█████▊    | 33610/57600 [5:53:24<4:07:01,  1.62it/s]
 58%|█████▊    | 33611/57600 [5:53:25<4:08:39,  1.61it/s]
 58%|█████▊    | 33612/57600 [5:53:26<4:18:10,  1.55it/s]
 58%|█████▊    | 33613/57600 [5:53:26<4:31:39,  1.47it/s]
 58%|█████▊    | 33614/57600 [5:53:27<4:34:26,  1.46it/s]
 58%|█████▊    | 33615/57600 [5:53:28<4:21:11,  1.53it/s]
 58%|█████▊    | 33616/57600 [5:53:28<4:16:16,  1.56it/s]
 58%|█████▊    | 33617/57600 [5:53:29<4:12:07,  1.59it/s]
 58%|█████▊    | 33618/57600 [5:53:30<4:18:03,  1.55it/s]
 58%|█████▊    | 33619/57600 [5:53:30<4:21:09,  1.53it/s]
 58%|█████▊    | 33620/57600 [5:53:31<4:15:27,  1.56it/s]
                                                         
{'loss': 1.1725, 'learning_rate': 4.7599303135888505e-07, 'epoch': 371.08}

 58%|█████▊    | 33620/57600 [5:53:31<4:15:27,  1.56it/s]
 58%|█████▊    | 33621/57600 [5:53:31<4:03:39,  1.64it/s]
 58%|█████▊    | 33622/57600 [5:53:32<4:04:26,  1.63it/s]
 58%|█████▊    | 33623/57600 [5:53:33<4:00:41,  1.66it/s]
 58%|█████▊    | 33624/57600 [5:53:33<4:05:29,  1.63it/s]
 58%|█████▊    | 33625/57600 [5:53:34<4:06:47,  1.62it/s]
 58%|█████▊    | 33626/57600 [5:53:34<4:06:39,  1.62it/s]
 58%|█████▊    | 33627/57600 [5:53:35<4:12:33,  1.58it/s]
 58%|█████▊    | 33628/57600 [5:53:36<4:25:32,  1.50it/s]
 58%|█████▊    | 33629/57600 [5:53:36<4:22:37,  1.52it/s]
 58%|█████▊    | 33630/57600 [5:53:37<4:15:45,  1.56it/s]
 58%|█████▊    | 33631/57600 [5:53:38<4:11:30,  1.59it/s]
 58%|█████▊    | 33632/57600 [5:53:38<4:20:41,  1.53it/s]
 58%|█████▊    | 33633/57600 [5:53:39<4:15:58,  1.56it/s]
 58%|█████▊    | 33634/57600 [5:53:40<4:10:54,  1.59it/s]
 58%|█████▊    | 33635/57600 [5:53:40<4:13:34,  1.58it/s]
 58%|█████▊    | 33636/57600 [5:53:41<4:19:58,  1.54it/s]
 58%|█████▊    | 33637/57600 [5:53:42<4:27:29,  1.49it/s]
 58%|█████▊    | 33638/57600 [5:53:42<4:19:02,  1.54it/s]
 58%|█████▊    | 33639/57600 [5:53:43<4:11:48,  1.59it/s]
 58%|█████▊    | 33640/57600 [5:53:43<4:06:46,  1.62it/s]
                                                         
{'loss': 1.1537, 'learning_rate': 4.7567944250871075e-07, 'epoch': 371.3}

 58%|█████▊    | 33640/57600 [5:53:43<4:06:46,  1.62it/s]
 58%|█████▊    | 33641/57600 [5:53:44<4:03:03,  1.64it/s]
 58%|█████▊    | 33642/57600 [5:53:45<3:57:17,  1.68it/s]
 58%|█████▊    | 33643/57600 [5:53:45<4:06:08,  1.62it/s]
 58%|█████▊    | 33644/57600 [5:53:46<4:05:19,  1.63it/s]
 58%|█████▊    | 33645/57600 [5:53:46<4:04:37,  1.63it/s]
 58%|█████▊    | 33646/57600 [5:53:47<4:02:08,  1.65it/s]
 58%|█████▊    | 33647/57600 [5:53:48<3:59:14,  1.67it/s]
 58%|█████▊    | 33648/57600 [5:53:48<4:03:42,  1.64it/s]
 58%|█████▊    | 33649/57600 [5:53:49<3:59:11,  1.67it/s]
 58%|█████▊    | 33650/57600 [5:53:50<4:10:46,  1.59it/s]
 58%|█████▊    | 33651/57600 [5:53:50<4:12:48,  1.58it/s]
 58%|█████▊    | 33652/57600 [5:53:51<4:02:06,  1.65it/s]
 58%|█████▊    | 33653/57600 [5:53:51<4:05:47,  1.62it/s]
 58%|█████▊    | 33654/57600 [5:53:52<4:14:52,  1.57it/s]
 58%|█████▊    | 33655/57600 [5:53:53<4:15:49,  1.56it/s]
 58%|█████▊    | 33656/57600 [5:53:53<4:14:55,  1.57it/s]
 58%|█████▊    | 33657/57600 [5:53:54<4:12:51,  1.58it/s]
 58%|█████▊    | 33658/57600 [5:53:55<4:12:17,  1.58it/s]
 58%|█████▊    | 33659/57600 [5:53:55<4:04:43,  1.63it/s]
 58%|█████▊    | 33660/57600 [5:53:56<4:09:58,  1.60it/s]
                                                         
{'loss': 1.1854, 'learning_rate': 4.753658536585366e-07, 'epoch': 371.52}

 58%|█████▊    | 33660/57600 [5:53:56<4:09:58,  1.60it/s]
 58%|█████▊    | 33661/57600 [5:53:56<4:07:30,  1.61it/s]
 58%|█████▊    | 33662/57600 [5:53:57<4:06:49,  1.62it/s]
 58%|█████▊    | 33663/57600 [5:53:58<4:15:55,  1.56it/s]
 58%|█████▊    | 33664/57600 [5:53:58<4:18:27,  1.54it/s]
 58%|█████▊    | 33665/57600 [5:53:59<4:16:59,  1.55it/s]
 58%|█████▊    | 33666/57600 [5:54:00<4:08:22,  1.61it/s]
 58%|█████▊    | 33667/57600 [5:54:00<4:23:49,  1.51it/s]
 58%|█████▊    | 33668/57600 [5:54:01<4:18:34,  1.54it/s]
 58%|█████▊    | 33669/57600 [5:54:02<4:18:05,  1.55it/s]
 58%|█████▊    | 33670/57600 [5:54:02<4:25:25,  1.50it/s]
 58%|█████▊    | 33671/57600 [5:54:03<4:24:17,  1.51it/s]
 58%|█████▊    | 33672/57600 [5:54:04<4:19:11,  1.54it/s]
 58%|█████▊    | 33673/57600 [5:54:04<4:07:36,  1.61it/s]
 58%|█████▊    | 33674/57600 [5:54:05<4:09:38,  1.60it/s]
 58%|█████▊    | 33675/57600 [5:54:05<4:16:59,  1.55it/s]
 58%|█████▊    | 33676/57600 [5:54:06<4:20:03,  1.53it/s]
 58%|█████▊    | 33677/57600 [5:54:07<4:12:41,  1.58it/s]
 58%|█████▊    | 33678/57600 [5:54:07<4:06:22,  1.62it/s]
 58%|█████▊    | 33679/57600 [5:54:08<4:08:05,  1.61it/s]
 58%|█████▊    | 33680/57600 [5:54:09<4:06:42,  1.62it/s]
                                                         
{'loss': 1.1336, 'learning_rate': 4.750522648083623e-07, 'epoch': 371.74}

 58%|█████▊    | 33680/57600 [5:54:09<4:06:42,  1.62it/s]
 58%|█████▊    | 33681/57600 [5:54:09<4:06:41,  1.62it/s]
 58%|█████▊    | 33682/57600 [5:54:10<4:01:14,  1.65it/s]
 58%|█████▊    | 33683/57600 [5:54:10<3:58:17,  1.67it/s]
 58%|█████▊    | 33684/57600 [5:54:11<3:56:28,  1.69it/s]
 58%|█████▊    | 33685/57600 [5:54:12<4:02:38,  1.64it/s]
 58%|█████▊    | 33686/57600 [5:54:12<4:01:16,  1.65it/s]
 58%|█████▊    | 33687/57600 [5:54:13<4:04:36,  1.63it/s]
 58%|█████▊    | 33688/57600 [5:54:13<4:02:39,  1.64it/s]
 58%|█████▊    | 33689/57600 [5:54:14<4:02:49,  1.64it/s]
 58%|█████▊    | 33690/57600 [5:54:15<4:02:19,  1.64it/s]
 58%|█████▊    | 33691/57600 [5:54:15<3:55:23,  1.69it/s]
 58%|█████▊    | 33692/57600 [5:54:16<4:07:02,  1.61it/s]
 58%|█████▊    | 33693/57600 [5:54:16<4:08:00,  1.61it/s]
 58%|█████▊    | 33694/57600 [5:54:17<4:04:59,  1.63it/s]
 58%|█████▊    | 33695/57600 [5:54:18<4:08:03,  1.61it/s]
 58%|█████▊    | 33696/57600 [5:54:18<4:05:44,  1.62it/s]
 59%|█████▊    | 33697/57600 [5:54:19<4:08:10,  1.61it/s]
 59%|█████▊    | 33698/57600 [5:54:20<4:10:45,  1.59it/s]
 59%|█████▊    | 33699/57600 [5:54:20<4:03:00,  1.64it/s]
 59%|█████▊    | 33700/57600 [5:54:21<3:58:44,  1.67it/s]
                                                         
{'loss': 1.2089, 'learning_rate': 4.7473867595818817e-07, 'epoch': 371.96}

 59%|█████▊    | 33700/57600 [5:54:21<3:58:44,  1.67it/s]
 59%|█████▊    | 33701/57600 [5:54:21<3:52:47,  1.71it/s]
 59%|█████▊    | 33702/57600 [5:54:22<3:58:15,  1.67it/s]
 59%|█████▊    | 33703/57600 [5:54:23<4:02:28,  1.64it/s]
 59%|█████▊    | 33704/57600 [5:54:23<4:12:28,  1.58it/s]
 59%|█████▊    | 33705/57600 [5:54:24<4:06:49,  1.61it/s]
 59%|█████▊    | 33706/57600 [5:54:25<4:21:16,  1.52it/s]
 59%|█████▊    | 33707/57600 [5:54:25<4:11:47,  1.58it/s]
 59%|█████▊    | 33708/57600 [5:54:26<4:03:03,  1.64it/s]
 59%|█████▊    | 33709/57600 [5:54:26<4:10:05,  1.59it/s]
 59%|█████▊    | 33710/57600 [5:54:27<4:12:14,  1.58it/s]
 59%|█████▊    | 33711/57600 [5:54:28<4:10:09,  1.59it/s]
 59%|█████▊    | 33712/57600 [5:54:28<4:01:11,  1.65it/s]
 59%|█████▊    | 33713/57600 [5:54:29<4:05:37,  1.62it/s]
 59%|█████▊    | 33714/57600 [5:54:29<4:04:41,  1.63it/s]
 59%|█████▊    | 33715/57600 [5:54:30<3:59:51,  1.66it/s]
 59%|█████▊    | 33716/57600 [5:54:31<4:05:34,  1.62it/s]
 59%|█████▊    | 33717/57600 [5:54:31<4:01:00,  1.65it/s]
 59%|█████▊    | 33718/57600 [5:54:32<4:00:44,  1.65it/s]
 59%|█████▊    | 33719/57600 [5:54:32<4:00:15,  1.66it/s]
 59%|█████▊    | 33720/57600 [5:54:33<4:03:02,  1.64it/s]
                                                         
{'loss': 1.1628, 'learning_rate': 4.7442508710801387e-07, 'epoch': 372.19}

 59%|█████▊    | 33720/57600 [5:54:33<4:03:02,  1.64it/s]
 59%|█████▊    | 33721/57600 [5:54:34<4:09:02,  1.60it/s]
 59%|█████▊    | 33722/57600 [5:54:34<4:13:10,  1.57it/s]
 59%|█████▊    | 33723/57600 [5:54:35<4:11:00,  1.59it/s]
 59%|█████▊    | 33724/57600 [5:54:36<4:10:46,  1.59it/s]
 59%|█████▊    | 33725/57600 [5:54:36<4:18:43,  1.54it/s]
 59%|█████▊    | 33726/57600 [5:54:37<4:22:36,  1.52it/s]
 59%|█████▊    | 33727/57600 [5:54:38<4:22:30,  1.52it/s]
 59%|█████▊    | 33728/57600 [5:54:38<4:26:18,  1.49it/s]
 59%|█████▊    | 33729/57600 [5:54:39<4:13:52,  1.57it/s]
 59%|█████▊    | 33730/57600 [5:54:40<4:09:15,  1.60it/s]
 59%|█████▊    | 33731/57600 [5:54:40<4:08:45,  1.60it/s]
 59%|█████▊    | 33732/57600 [5:54:41<4:12:51,  1.57it/s]
 59%|█████▊    | 33733/57600 [5:54:41<4:10:46,  1.59it/s]
 59%|█████▊    | 33734/57600 [5:54:42<4:15:03,  1.56it/s]
 59%|█████▊    | 33735/57600 [5:54:43<4:13:54,  1.57it/s]
 59%|█████▊    | 33736/57600 [5:54:43<4:07:52,  1.60it/s]
 59%|█████▊    | 33737/57600 [5:54:44<4:07:46,  1.61it/s]
 59%|█████▊    | 33738/57600 [5:54:45<4:09:59,  1.59it/s]
 59%|█████▊    | 33739/57600 [5:54:45<4:13:04,  1.57it/s]
 59%|█████▊    | 33740/57600 [5:54:46<4:11:32,  1.58it/s]
                                                         
{'loss': 1.1535, 'learning_rate': 4.741114982578397e-07, 'epoch': 372.41}

 59%|█████▊    | 33740/57600 [5:54:46<4:11:32,  1.58it/s]
 59%|█████▊    | 33741/57600 [5:54:47<4:13:47,  1.57it/s]
 59%|█████▊    | 33742/57600 [5:54:47<4:12:40,  1.57it/s]
 59%|█████▊    | 33743/57600 [5:54:48<4:04:29,  1.63it/s]
 59%|█████▊    | 33744/57600 [5:54:48<4:04:33,  1.63it/s]
 59%|█████▊    | 33745/57600 [5:54:49<4:07:22,  1.61it/s]
 59%|█████▊    | 33746/57600 [5:54:50<4:04:55,  1.62it/s]
 59%|█████▊    | 33747/57600 [5:54:50<4:08:58,  1.60it/s]
 59%|█████▊    | 33748/57600 [5:54:51<4:08:08,  1.60it/s]
 59%|█████▊    | 33749/57600 [5:54:51<4:05:07,  1.62it/s]
 59%|█████▊    | 33750/57600 [5:54:52<3:58:38,  1.67it/s]
 59%|█████▊    | 33751/57600 [5:54:53<3:57:13,  1.68it/s]
 59%|█████▊    | 33752/57600 [5:54:53<3:52:49,  1.71it/s]
 59%|█████▊    | 33753/57600 [5:54:54<3:58:10,  1.67it/s]
 59%|█████▊    | 33754/57600 [5:54:54<4:09:09,  1.60it/s]
 59%|█████▊    | 33755/57600 [5:54:55<4:09:41,  1.59it/s]
 59%|█████▊    | 33756/57600 [5:54:56<4:03:50,  1.63it/s]
 59%|█████▊    | 33757/57600 [5:54:56<4:06:37,  1.61it/s]
 59%|█████▊    | 33758/57600 [5:54:57<3:59:50,  1.66it/s]
 59%|█████▊    | 33759/57600 [5:54:57<3:59:28,  1.66it/s]
 59%|█████▊    | 33760/57600 [5:54:58<3:57:16,  1.67it/s]
                                                         
{'loss': 1.2004, 'learning_rate': 4.7379790940766553e-07, 'epoch': 372.63}

 59%|█████▊    | 33760/57600 [5:54:58<3:57:16,  1.67it/s]
 59%|█████▊    | 33761/57600 [5:54:59<4:13:51,  1.57it/s]
 59%|█████▊    | 33762/57600 [5:54:59<4:09:49,  1.59it/s]
 59%|█████▊    | 33763/57600 [5:55:00<4:08:18,  1.60it/s]
 59%|█████▊    | 33764/57600 [5:55:01<4:01:58,  1.64it/s]
 59%|█████▊    | 33765/57600 [5:55:01<4:01:46,  1.64it/s]
 59%|█████▊    | 33766/57600 [5:55:02<4:07:28,  1.61it/s]
 59%|█████▊    | 33767/57600 [5:55:02<4:05:42,  1.62it/s]
 59%|█████▊    | 33768/57600 [5:55:03<4:01:07,  1.65it/s]
 59%|█████▊    | 33769/57600 [5:55:04<4:12:49,  1.57it/s]
 59%|█████▊    | 33770/57600 [5:55:04<4:04:33,  1.62it/s]
 59%|█████▊    | 33771/57600 [5:55:05<4:03:15,  1.63it/s]
 59%|█████▊    | 33772/57600 [5:55:06<4:09:25,  1.59it/s]
 59%|█████▊    | 33773/57600 [5:55:06<4:20:07,  1.53it/s]
 59%|█████▊    | 33774/57600 [5:55:07<4:20:43,  1.52it/s]
 59%|█████▊    | 33775/57600 [5:55:08<4:19:17,  1.53it/s]
 59%|█████▊    | 33776/57600 [5:55:08<4:15:15,  1.56it/s]
 59%|█████▊    | 33777/57600 [5:55:09<4:11:49,  1.58it/s]
 59%|█████▊    | 33778/57600 [5:55:09<4:03:23,  1.63it/s]
 59%|█████▊    | 33779/57600 [5:55:10<3:59:39,  1.66it/s]
 59%|█████▊    | 33780/57600 [5:55:11<4:07:08,  1.61it/s]
                                                         
{'loss': 1.1668, 'learning_rate': 4.734843205574913e-07, 'epoch': 372.85}

 59%|█████▊    | 33780/57600 [5:55:11<4:07:08,  1.61it/s]
 59%|█████▊    | 33781/57600 [5:55:11<4:15:05,  1.56it/s]
 59%|█████▊    | 33782/57600 [5:55:12<4:17:36,  1.54it/s]
 59%|█████▊    | 33783/57600 [5:55:13<4:12:23,  1.57it/s]
 59%|█████▊    | 33784/57600 [5:55:13<4:12:03,  1.57it/s]
 59%|█████▊    | 33785/57600 [5:55:14<4:08:21,  1.60it/s]
 59%|█████▊    | 33786/57600 [5:55:15<4:21:52,  1.52it/s]
 59%|█████▊    | 33787/57600 [5:55:15<4:12:48,  1.57it/s]
 59%|█████▊    | 33788/57600 [5:55:16<4:21:58,  1.51it/s]
 59%|█████▊    | 33789/57600 [5:55:16<4:15:18,  1.55it/s]
 59%|█████▊    | 33790/57600 [5:55:17<4:11:12,  1.58it/s]
 59%|█████▊    | 33791/57600 [5:55:18<4:16:27,  1.55it/s]
 59%|█████▊    | 33792/57600 [5:55:18<4:12:48,  1.57it/s]
 59%|█████▊    | 33793/57600 [5:55:19<4:09:00,  1.59it/s]
 59%|█████▊    | 33794/57600 [5:55:20<4:19:33,  1.53it/s]
 59%|█████▊    | 33795/57600 [5:55:20<4:16:54,  1.54it/s]
 59%|█████▊    | 33796/57600 [5:55:21<4:13:28,  1.57it/s]
 59%|█████▊    | 33797/57600 [5:55:22<4:11:39,  1.58it/s]
 59%|█████▊    | 33798/57600 [5:55:22<4:07:06,  1.61it/s]
 59%|█████▊    | 33799/57600 [5:55:23<4:04:32,  1.62it/s]
 59%|█████▊    | 33800/57600 [5:55:23<4:02:01,  1.64it/s]
                                                         
{'loss': 1.1721, 'learning_rate': 4.731707317073171e-07, 'epoch': 373.07}

 59%|█████▊    | 33800/57600 [5:55:23<4:02:01,  1.64it/s]
 59%|█████▊    | 33801/57600 [5:55:24<4:03:43,  1.63it/s]
 59%|█████▊    | 33802/57600 [5:55:25<4:16:05,  1.55it/s]
 59%|█████▊    | 33803/57600 [5:55:25<4:21:41,  1.52it/s]
 59%|█████▊    | 33804/57600 [5:55:26<4:21:38,  1.52it/s]
 59%|█████▊    | 33805/57600 [5:55:27<4:10:34,  1.58it/s]
 59%|█████▊    | 33806/57600 [5:55:27<4:02:46,  1.63it/s]
 59%|█████▊    | 33807/57600 [5:55:28<4:00:02,  1.65it/s]
 59%|█████▊    | 33808/57600 [5:55:28<4:08:56,  1.59it/s]
 59%|█████▊    | 33809/57600 [5:55:29<4:02:24,  1.64it/s]
 59%|█████▊    | 33810/57600 [5:55:30<3:55:08,  1.69it/s]
 59%|█████▊    | 33811/57600 [5:55:30<3:57:08,  1.67it/s]
 59%|█████▊    | 33812/57600 [5:55:31<4:03:27,  1.63it/s]
 59%|█████▊    | 33813/57600 [5:55:31<4:05:40,  1.61it/s]
 59%|█████▊    | 33814/57600 [5:55:32<4:01:38,  1.64it/s]
 59%|█████▊    | 33815/57600 [5:55:33<4:02:36,  1.63it/s]
 59%|█████▊    | 33816/57600 [5:55:33<4:00:35,  1.65it/s]
 59%|█████▊    | 33817/57600 [5:55:34<4:06:38,  1.61it/s]
 59%|█████▊    | 33818/57600 [5:55:35<4:03:05,  1.63it/s]
 59%|█████▊    | 33819/57600 [5:55:35<4:01:14,  1.64it/s]
 59%|█████▊    | 33820/57600 [5:55:36<4:06:42,  1.61it/s]
                                                         
{'loss': 1.1719, 'learning_rate': 4.728571428571428e-07, 'epoch': 373.29}

 59%|█████▊    | 33820/57600 [5:55:36<4:06:42,  1.61it/s]
 59%|█████▊    | 33821/57600 [5:55:36<4:02:57,  1.63it/s]
 59%|█████▊    | 33822/57600 [5:55:37<4:07:02,  1.60it/s]
 59%|█████▊    | 33823/57600 [5:55:38<4:11:06,  1.58it/s]
 59%|█████▊    | 33824/57600 [5:55:38<4:15:08,  1.55it/s]
 59%|█████▊    | 33825/57600 [5:55:39<4:11:33,  1.58it/s]
 59%|█████▊    | 33826/57600 [5:55:40<4:04:39,  1.62it/s]
 59%|█████▊    | 33827/57600 [5:55:40<4:16:39,  1.54it/s]
 59%|█████▊    | 33828/57600 [5:55:41<4:09:59,  1.58it/s]
 59%|█████▊    | 33829/57600 [5:55:41<4:05:17,  1.62it/s]
 59%|█████▊    | 33830/57600 [5:55:42<4:08:40,  1.59it/s]
 59%|█████▊    | 33831/57600 [5:55:43<4:03:57,  1.62it/s]
 59%|█████▊    | 33832/57600 [5:55:43<3:57:06,  1.67it/s]
 59%|█████▊    | 33833/57600 [5:55:44<3:59:26,  1.65it/s]
 59%|█████▊    | 33834/57600 [5:55:45<4:06:43,  1.61it/s]
 59%|█████▊    | 33835/57600 [5:55:45<4:13:20,  1.56it/s]
 59%|█████▊    | 33836/57600 [5:55:46<4:13:51,  1.56it/s]
 59%|█████▊    | 33837/57600 [5:55:46<4:12:21,  1.57it/s]
 59%|█████▊    | 33838/57600 [5:55:47<4:11:41,  1.57it/s]
 59%|█████▊    | 33839/57600 [5:55:48<4:05:46,  1.61it/s]
 59%|█████▉    | 33840/57600 [5:55:48<4:08:19,  1.59it/s]
                                                         
{'loss': 1.1815, 'learning_rate': 4.7254355400696864e-07, 'epoch': 373.51}

 59%|█████▉    | 33840/57600 [5:55:48<4:08:19,  1.59it/s]
 59%|█████▉    | 33841/57600 [5:55:49<4:09:17,  1.59it/s]
 59%|█████▉    | 33842/57600 [5:55:50<4:04:27,  1.62it/s]
 59%|█████▉    | 33843/57600 [5:55:50<3:57:59,  1.66it/s]
 59%|█████▉    | 33844/57600 [5:55:51<3:54:28,  1.69it/s]
 59%|█████▉    | 33845/57600 [5:55:51<4:00:28,  1.65it/s]
 59%|█████▉    | 33846/57600 [5:55:52<4:07:50,  1.60it/s]
 59%|█████▉    | 33847/57600 [5:55:53<4:07:27,  1.60it/s]
 59%|█████▉    | 33848/57600 [5:55:53<4:15:27,  1.55it/s]
 59%|█████▉    | 33849/57600 [5:55:54<4:14:37,  1.55it/s]
 59%|█████▉    | 33850/57600 [5:55:55<4:12:46,  1.57it/s]
 59%|█████▉    | 33851/57600 [5:55:55<4:11:55,  1.57it/s]
 59%|█████▉    | 33852/57600 [5:55:56<4:15:53,  1.55it/s]
 59%|█████▉    | 33853/57600 [5:55:57<4:13:46,  1.56it/s]
 59%|█████▉    | 33854/57600 [5:55:57<4:19:20,  1.53it/s]
 59%|█████▉    | 33855/57600 [5:55:58<4:10:27,  1.58it/s]
 59%|█████▉    | 33856/57600 [5:55:58<4:06:47,  1.60it/s]
 59%|█████▉    | 33857/57600 [5:55:59<4:08:53,  1.59it/s]
 59%|█████▉    | 33858/57600 [5:56:00<4:04:35,  1.62it/s]
 59%|█████▉    | 33859/57600 [5:56:00<4:02:58,  1.63it/s]
 59%|█████▉    | 33860/57600 [5:56:01<4:11:18,  1.57it/s]
                                                         
{'loss': 1.1809, 'learning_rate': 4.7222996515679434e-07, 'epoch': 373.73}

 59%|█████▉    | 33860/57600 [5:56:01<4:11:18,  1.57it/s]
 59%|█████▉    | 33861/57600 [5:56:02<4:11:23,  1.57it/s]
 59%|█████▉    | 33862/57600 [5:56:02<4:15:16,  1.55it/s]
 59%|█████▉    | 33863/57600 [5:56:03<4:13:33,  1.56it/s]
 59%|█████▉    | 33864/57600 [5:56:04<4:14:45,  1.55it/s]
 59%|█████▉    | 33865/57600 [5:56:04<4:17:58,  1.53it/s]
 59%|█████▉    | 33866/57600 [5:56:05<4:09:00,  1.59it/s]
 59%|█████▉    | 33867/57600 [5:56:05<4:13:13,  1.56it/s]
 59%|█████▉    | 33868/57600 [5:56:06<4:09:51,  1.58it/s]
 59%|█████▉    | 33869/57600 [5:56:07<4:05:43,  1.61it/s]
 59%|█████▉    | 33870/57600 [5:56:07<4:02:33,  1.63it/s]
 59%|█████▉    | 33871/57600 [5:56:08<4:03:46,  1.62it/s]
 59%|█████▉    | 33872/57600 [5:56:08<3:56:22,  1.67it/s]
 59%|█████▉    | 33873/57600 [5:56:09<4:01:09,  1.64it/s]
 59%|█████▉    | 33874/57600 [5:56:10<4:00:42,  1.64it/s]
 59%|█████▉    | 33875/57600 [5:56:10<3:58:02,  1.66it/s]
 59%|█████▉    | 33876/57600 [5:56:11<3:56:45,  1.67it/s]
 59%|█████▉    | 33877/57600 [5:56:11<3:53:36,  1.69it/s]
 59%|█████▉    | 33878/57600 [5:56:12<4:01:24,  1.64it/s]
 59%|█████▉    | 33879/57600 [5:56:13<4:03:55,  1.62it/s]
 59%|█████▉    | 33880/57600 [5:56:13<4:12:15,  1.57it/s]
                                                         
{'loss': 1.1849, 'learning_rate': 4.719163763066202e-07, 'epoch': 373.95}

 59%|█████▉    | 33880/57600 [5:56:13<4:12:15,  1.57it/s]
 59%|█████▉    | 33881/57600 [5:56:14<4:16:41,  1.54it/s]
 59%|█████▉    | 33882/57600 [5:56:15<4:13:37,  1.56it/s]
 59%|█████▉    | 33883/57600 [5:56:15<4:10:38,  1.58it/s]
 59%|█████▉    | 33884/57600 [5:56:16<4:06:44,  1.60it/s]
 59%|█████▉    | 33885/57600 [5:56:17<4:13:31,  1.56it/s]
 59%|█████▉    | 33886/57600 [5:56:17<4:21:20,  1.51it/s]
 59%|█████▉    | 33887/57600 [5:56:18<4:14:53,  1.55it/s]
 59%|█████▉    | 33888/57600 [5:56:19<4:12:21,  1.57it/s]
 59%|█████▉    | 33889/57600 [5:56:19<4:22:19,  1.51it/s]
 59%|█████▉    | 33890/57600 [5:56:20<4:11:44,  1.57it/s]
 59%|█████▉    | 33891/57600 [5:56:20<4:11:45,  1.57it/s]
 59%|█████▉    | 33892/57600 [5:56:21<4:02:17,  1.63it/s]
 59%|█████▉    | 33893/57600 [5:56:22<4:11:17,  1.57it/s]
 59%|█████▉    | 33894/57600 [5:56:22<4:07:54,  1.59it/s]
 59%|█████▉    | 33895/57600 [5:56:23<4:03:09,  1.62it/s]
 59%|█████▉    | 33896/57600 [5:56:23<3:59:11,  1.65it/s]
 59%|█████▉    | 33897/57600 [5:56:24<4:08:51,  1.59it/s]
 59%|█████▉    | 33898/57600 [5:56:25<4:06:17,  1.60it/s]
 59%|█████▉    | 33899/57600 [5:56:25<4:01:58,  1.63it/s]
 59%|█████▉    | 33900/57600 [5:56:26<4:04:40,  1.61it/s]
                                                         
{'loss': 1.179, 'learning_rate': 4.71602787456446e-07, 'epoch': 374.17}

 59%|█████▉    | 33900/57600 [5:56:26<4:04:40,  1.61it/s]
 59%|█████▉    | 33901/57600 [5:56:27<4:08:05,  1.59it/s]
 59%|█████▉    | 33902/57600 [5:56:27<4:17:05,  1.54it/s]
 59%|█████▉    | 33903/57600 [5:56:28<4:14:19,  1.55it/s]
 59%|█████▉    | 33904/57600 [5:56:29<4:02:48,  1.63it/s]
 59%|█████▉    | 33905/57600 [5:56:29<4:02:03,  1.63it/s]
 59%|█████▉    | 33906/57600 [5:56:30<4:06:28,  1.60it/s]
 59%|█████▉    | 33907/57600 [5:56:30<4:12:52,  1.56it/s]
 59%|█████▉    | 33908/57600 [5:56:31<4:10:18,  1.58it/s]
 59%|█████▉    | 33909/57600 [5:56:32<4:16:24,  1.54it/s]
 59%|█████▉    | 33910/57600 [5:56:32<4:20:53,  1.51it/s]
 59%|█████▉    | 33911/57600 [5:56:33<4:11:46,  1.57it/s]
 59%|█████▉    | 33912/57600 [5:56:34<4:00:03,  1.64it/s]
 59%|█████▉    | 33913/57600 [5:56:34<4:00:14,  1.64it/s]
 59%|█████▉    | 33914/57600 [5:56:35<3:59:01,  1.65it/s]
 59%|█████▉    | 33915/57600 [5:56:35<4:04:12,  1.62it/s]
 59%|█████▉    | 33916/57600 [5:56:36<4:04:31,  1.61it/s]
 59%|█████▉    | 33917/57600 [5:56:37<4:01:04,  1.64it/s]
 59%|█████▉    | 33918/57600 [5:56:37<3:58:09,  1.66it/s]
 59%|█████▉    | 33919/57600 [5:56:38<4:03:05,  1.62it/s]
 59%|█████▉    | 33920/57600 [5:56:38<4:02:09,  1.63it/s]
                                                         
{'loss': 1.1572, 'learning_rate': 4.7128919860627176e-07, 'epoch': 374.39}

 59%|█████▉    | 33920/57600 [5:56:38<4:02:09,  1.63it/s]
 59%|█████▉    | 33921/57600 [5:56:39<4:05:02,  1.61it/s]
 59%|█████▉    | 33922/57600 [5:56:40<4:03:52,  1.62it/s]
 59%|█████▉    | 33923/57600 [5:56:40<4:09:44,  1.58it/s]
 59%|█████▉    | 33924/57600 [5:56:41<4:06:52,  1.60it/s]
 59%|█████▉    | 33925/57600 [5:56:42<4:13:51,  1.55it/s]
 59%|█████▉    | 33926/57600 [5:56:42<4:09:41,  1.58it/s]
 59%|█████▉    | 33927/57600 [5:56:43<4:02:09,  1.63it/s]
 59%|█████▉    | 33928/57600 [5:56:44<4:06:44,  1.60it/s]
 59%|█████▉    | 33929/57600 [5:56:44<4:05:34,  1.61it/s]
 59%|█████▉    | 33930/57600 [5:56:45<4:11:23,  1.57it/s]
 59%|█████▉    | 33931/57600 [5:56:45<4:16:22,  1.54it/s]
 59%|█████▉    | 33932/57600 [5:56:46<4:16:58,  1.54it/s]
 59%|█████▉    | 33933/57600 [5:56:47<4:07:36,  1.59it/s]
 59%|█████▉    | 33934/57600 [5:56:47<4:04:08,  1.62it/s]
 59%|█████▉    | 33935/57600 [5:56:48<4:01:32,  1.63it/s]
 59%|█████▉    | 33936/57600 [5:56:49<4:04:38,  1.61it/s]
 59%|█████▉    | 33937/57600 [5:56:49<4:03:32,  1.62it/s]
 59%|█████▉    | 33938/57600 [5:56:50<4:11:49,  1.57it/s]
 59%|█████▉    | 33939/57600 [5:56:50<4:07:14,  1.60it/s]
 59%|█████▉    | 33940/57600 [5:56:51<4:01:40,  1.63it/s]
                                                         
{'loss': 1.1734, 'learning_rate': 4.7097560975609756e-07, 'epoch': 374.61}

 59%|█████▉    | 33940/57600 [5:56:51<4:01:40,  1.63it/s]
 59%|█████▉    | 33941/57600 [5:56:52<4:09:57,  1.58it/s]
 59%|█████▉    | 33942/57600 [5:56:52<4:12:28,  1.56it/s]
 59%|█████▉    | 33943/57600 [5:56:53<4:12:33,  1.56it/s]
 59%|█████▉    | 33944/57600 [5:56:54<4:09:10,  1.58it/s]
 59%|█████▉    | 33945/57600 [5:56:54<4:06:16,  1.60it/s]
 59%|█████▉    | 33946/57600 [5:56:55<4:11:53,  1.57it/s]
 59%|█████▉    | 33947/57600 [5:56:55<4:08:30,  1.59it/s]
 59%|█████▉    | 33948/57600 [5:56:56<4:16:30,  1.54it/s]
 59%|█████▉    | 33949/57600 [5:56:57<4:11:29,  1.57it/s]
 59%|█████▉    | 33950/57600 [5:56:57<4:09:31,  1.58it/s]
 59%|█████▉    | 33951/57600 [5:56:58<4:11:10,  1.57it/s]
 59%|█████▉    | 33952/57600 [5:56:59<4:03:29,  1.62it/s]
 59%|█████▉    | 33953/57600 [5:56:59<4:10:47,  1.57it/s]
 59%|█████▉    | 33954/57600 [5:57:00<4:05:34,  1.60it/s]
 59%|█████▉    | 33955/57600 [5:57:01<4:06:49,  1.60it/s]
 59%|█████▉    | 33956/57600 [5:57:01<4:02:05,  1.63it/s]
 59%|█████▉    | 33957/57600 [5:57:02<4:00:53,  1.64it/s]
 59%|█████▉    | 33958/57600 [5:57:02<3:58:14,  1.65it/s]
 59%|█████▉    | 33959/57600 [5:57:03<3:58:45,  1.65it/s]
 59%|█████▉    | 33960/57600 [5:57:04<3:56:16,  1.67it/s]
                                                         
{'loss': 1.1608, 'learning_rate': 4.706620209059233e-07, 'epoch': 374.83}

 59%|█████▉    | 33960/57600 [5:57:04<3:56:16,  1.67it/s]
 59%|█████▉    | 33961/57600 [5:57:04<3:58:37,  1.65it/s]
 59%|█████▉    | 33962/57600 [5:57:05<4:01:51,  1.63it/s]
 59%|█████▉    | 33963/57600 [5:57:05<4:01:14,  1.63it/s]
 59%|█████▉    | 33964/57600 [5:57:06<4:05:29,  1.60it/s]
 59%|█████▉    | 33965/57600 [5:57:07<4:07:23,  1.59it/s]
 59%|█████▉    | 33966/57600 [5:57:07<4:11:56,  1.56it/s]
 59%|█████▉    | 33967/57600 [5:57:08<4:19:43,  1.52it/s]
 59%|█████▉    | 33968/57600 [5:57:09<4:24:40,  1.49it/s]
 59%|█████▉    | 33969/57600 [5:57:09<4:19:35,  1.52it/s]
 59%|█████▉    | 33970/57600 [5:57:10<4:17:47,  1.53it/s]
 59%|█████▉    | 33971/57600 [5:57:11<4:06:37,  1.60it/s]
 59%|█████▉    | 33972/57600 [5:57:11<4:03:56,  1.61it/s]
 59%|█████▉    | 33973/57600 [5:57:12<3:59:48,  1.64it/s]
 59%|█████▉    | 33974/57600 [5:57:12<3:59:53,  1.64it/s]
 59%|█████▉    | 33975/57600 [5:57:13<4:00:37,  1.64it/s]
 59%|█████▉    | 33976/57600 [5:57:14<4:08:58,  1.58it/s]
 59%|█████▉    | 33977/57600 [5:57:14<4:09:14,  1.58it/s]
 59%|█████▉    | 33978/57600 [5:57:15<4:08:06,  1.59it/s]
 59%|█████▉    | 33979/57600 [5:57:16<4:09:35,  1.58it/s]
 59%|█████▉    | 33980/57600 [5:57:16<4:13:13,  1.55it/s]
                                                         
{'loss': 1.1355, 'learning_rate': 4.7034843205574917e-07, 'epoch': 375.06}

 59%|█████▉    | 33980/57600 [5:57:16<4:13:13,  1.55it/s]
 59%|█████▉    | 33981/57600 [5:57:17<4:11:26,  1.57it/s]
 59%|█████▉    | 33982/57600 [5:57:17<4:06:26,  1.60it/s]
 59%|█████▉    | 33983/57600 [5:57:18<4:11:54,  1.56it/s]
 59%|█████▉    | 33984/57600 [5:57:19<4:05:26,  1.60it/s]
 59%|█████▉    | 33985/57600 [5:57:19<4:07:55,  1.59it/s]
 59%|█████▉    | 33986/57600 [5:57:20<4:27:27,  1.47it/s]
 59%|█████▉    | 33987/57600 [5:57:21<4:23:34,  1.49it/s]
 59%|█████▉    | 33988/57600 [5:57:21<4:25:07,  1.48it/s]
 59%|█████▉    | 33989/57600 [5:57:22<4:19:38,  1.52it/s]
 59%|█████▉    | 33990/57600 [5:57:23<4:18:19,  1.52it/s]
 59%|█████▉    | 33991/57600 [5:57:23<4:14:00,  1.55it/s]
 59%|█████▉    | 33992/57600 [5:57:24<4:10:52,  1.57it/s]
 59%|█████▉    | 33993/57600 [5:57:25<4:08:26,  1.58it/s]
 59%|█████▉    | 33994/57600 [5:57:25<4:15:20,  1.54it/s]
 59%|█████▉    | 33995/57600 [5:57:26<4:11:36,  1.56it/s]
 59%|█████▉    | 33996/57600 [5:57:27<4:11:46,  1.56it/s]
 59%|█████▉    | 33997/57600 [5:57:27<4:18:32,  1.52it/s]
 59%|█████▉    | 33998/57600 [5:57:28<4:09:37,  1.58it/s]
 59%|█████▉    | 33999/57600 [5:57:28<4:09:27,  1.58it/s]
 59%|█████▉    | 34000/57600 [5:57:29<4:08:15,  1.58it/s]
                                                         
{'loss': 1.1185, 'learning_rate': 4.7003484320557487e-07, 'epoch': 375.28}

 59%|█████▉    | 34000/57600 [5:57:29<4:08:15,  1.58it/s]
 59%|█████▉    | 34001/57600 [5:57:30<4:06:42,  1.59it/s]
 59%|█████▉    | 34002/57600 [5:57:30<4:01:54,  1.63it/s]
 59%|█████▉    | 34003/57600 [5:57:31<4:12:11,  1.56it/s]
 59%|█████▉    | 34004/57600 [5:57:32<4:09:35,  1.58it/s]
 59%|█████▉    | 34005/57600 [5:57:32<4:06:55,  1.59it/s]
 59%|█████▉    | 34006/57600 [5:57:33<4:06:13,  1.60it/s]
 59%|█████▉    | 34007/57600 [5:57:33<4:04:51,  1.61it/s]
 59%|█████▉    | 34008/57600 [5:57:34<4:03:25,  1.62it/s]
 59%|█████▉    | 34009/57600 [5:57:35<4:05:11,  1.60it/s]
 59%|█████▉    | 34010/57600 [5:57:35<4:04:57,  1.61it/s]
 59%|█████▉    | 34011/57600 [5:57:36<4:12:16,  1.56it/s]
 59%|█████▉    | 34012/57600 [5:57:37<4:28:56,  1.46it/s]
 59%|█████▉    | 34013/57600 [5:57:37<4:20:26,  1.51it/s]
 59%|█████▉    | 34014/57600 [5:57:38<4:12:59,  1.55it/s]
 59%|█████▉    | 34015/57600 [5:57:39<4:07:20,  1.59it/s]
 59%|█████▉    | 34016/57600 [5:57:39<4:04:08,  1.61it/s]
 59%|█████▉    | 34017/57600 [5:57:40<3:58:03,  1.65it/s]
 59%|█████▉    | 34018/57600 [5:57:40<4:00:49,  1.63it/s]
 59%|█████▉    | 34019/57600 [5:57:41<3:52:36,  1.69it/s]
 59%|█████▉    | 34020/57600 [5:57:42<4:01:25,  1.63it/s]
                                                         
{'loss': 1.1525, 'learning_rate': 4.697212543554007e-07, 'epoch': 375.5}

 59%|█████▉    | 34020/57600 [5:57:42<4:01:25,  1.63it/s]
 59%|█████▉    | 34021/57600 [5:57:42<3:56:44,  1.66it/s]
 59%|█████▉    | 34022/57600 [5:57:43<3:57:57,  1.65it/s]
 59%|█████▉    | 34023/57600 [5:57:43<3:57:23,  1.66it/s]
 59%|█████▉    | 34024/57600 [5:57:44<3:58:55,  1.64it/s]
 59%|█████▉    | 34025/57600 [5:57:45<3:59:48,  1.64it/s]
 59%|█████▉    | 34026/57600 [5:57:45<4:03:19,  1.61it/s]
 59%|█████▉    | 34027/57600 [5:57:46<4:10:39,  1.57it/s]
 59%|█████▉    | 34028/57600 [5:57:47<4:20:44,  1.51it/s]
 59%|█████▉    | 34029/57600 [5:57:47<4:17:14,  1.53it/s]
 59%|█████▉    | 34030/57600 [5:57:48<4:09:44,  1.57it/s]
 59%|█████▉    | 34031/57600 [5:57:49<4:07:26,  1.59it/s]
 59%|█████▉    | 34032/57600 [5:57:49<4:02:22,  1.62it/s]
 59%|█████▉    | 34033/57600 [5:57:50<4:09:47,  1.57it/s]
 59%|█████▉    | 34034/57600 [5:57:51<4:21:51,  1.50it/s]
 59%|█████▉    | 34035/57600 [5:57:51<4:17:30,  1.53it/s]
 59%|█████▉    | 34036/57600 [5:57:52<4:21:51,  1.50it/s]
 59%|█████▉    | 34037/57600 [5:57:53<4:23:05,  1.49it/s]
 59%|█████▉    | 34038/57600 [5:57:53<4:28:30,  1.46it/s]
 59%|█████▉    | 34039/57600 [5:57:54<4:20:48,  1.51it/s]
 59%|█████▉    | 34040/57600 [5:57:55<4:24:02,  1.49it/s]
                                                         
{'loss': 1.1526, 'learning_rate': 4.694076655052265e-07, 'epoch': 375.72}

 59%|█████▉    | 34040/57600 [5:57:55<4:24:02,  1.49it/s]
 59%|█████▉    | 34041/57600 [5:57:55<4:15:09,  1.54it/s]
 59%|█████▉    | 34042/57600 [5:57:56<4:04:03,  1.61it/s]
 59%|█████▉    | 34043/57600 [5:57:56<4:08:05,  1.58it/s]
 59%|█████▉    | 34044/57600 [5:57:57<4:04:02,  1.61it/s]
 59%|█████▉    | 34045/57600 [5:57:58<4:06:52,  1.59it/s]
 59%|█████▉    | 34046/57600 [5:57:58<4:00:10,  1.63it/s]
 59%|█████▉    | 34047/57600 [5:57:59<4:02:17,  1.62it/s]
 59%|█████▉    | 34048/57600 [5:57:59<4:05:53,  1.60it/s]
 59%|█████▉    | 34049/57600 [5:58:00<4:00:49,  1.63it/s]
 59%|█████▉    | 34050/57600 [5:58:01<4:05:18,  1.60it/s]
 59%|█████▉    | 34051/57600 [5:58:01<4:03:22,  1.61it/s]
 59%|█████▉    | 34052/57600 [5:58:02<4:07:48,  1.58it/s]
 59%|█████▉    | 34053/57600 [5:58:03<4:06:17,  1.59it/s]
 59%|█████▉    | 34054/57600 [5:58:03<4:14:16,  1.54it/s]
 59%|█████▉    | 34055/57600 [5:58:04<4:07:01,  1.59it/s]
 59%|█████▉    | 34056/57600 [5:58:05<4:08:10,  1.58it/s]
 59%|█████▉    | 34057/57600 [5:58:05<4:06:57,  1.59it/s]
 59%|█████▉    | 34058/57600 [5:58:06<4:04:45,  1.60it/s]
 59%|█████▉    | 34059/57600 [5:58:06<4:08:36,  1.58it/s]
 59%|█████▉    | 34060/57600 [5:58:07<4:12:19,  1.55it/s]
                                                         
{'loss': 1.1603, 'learning_rate': 4.6909407665505223e-07, 'epoch': 375.94}

 59%|█████▉    | 34060/57600 [5:58:07<4:12:19,  1.55it/s]
 59%|█████▉    | 34061/57600 [5:58:08<4:16:27,  1.53it/s]
 59%|█████▉    | 34062/57600 [5:58:08<4:12:53,  1.55it/s]
 59%|█████▉    | 34063/57600 [5:58:09<4:09:55,  1.57it/s]
 59%|█████▉    | 34064/57600 [5:58:10<4:06:30,  1.59it/s]
 59%|█████▉    | 34065/57600 [5:58:10<4:00:08,  1.63it/s]
 59%|█████▉    | 34066/57600 [5:58:11<4:02:58,  1.61it/s]
 59%|█████▉    | 34067/57600 [5:58:11<4:02:19,  1.62it/s]
 59%|█████▉    | 34068/57600 [5:58:12<4:01:33,  1.62it/s]
 59%|█████▉    | 34069/57600 [5:58:13<4:15:08,  1.54it/s]
 59%|█████▉    | 34070/57600 [5:58:13<4:07:39,  1.58it/s]
 59%|█████▉    | 34071/57600 [5:58:14<4:11:58,  1.56it/s]
 59%|█████▉    | 34072/57600 [5:58:15<4:04:24,  1.60it/s]
 59%|█████▉    | 34073/57600 [5:58:15<4:04:17,  1.61it/s]
 59%|█████▉    | 34074/57600 [5:58:16<4:05:22,  1.60it/s]
 59%|█████▉    | 34075/57600 [5:58:16<4:06:17,  1.59it/s]
 59%|█████▉    | 34076/57600 [5:58:17<4:05:02,  1.60it/s]
 59%|█████▉    | 34077/57600 [5:58:18<4:10:40,  1.56it/s]
 59%|█████▉    | 34078/57600 [5:58:18<4:14:11,  1.54it/s]
 59%|█████▉    | 34079/57600 [5:58:19<4:10:28,  1.57it/s]
 59%|█████▉    | 34080/57600 [5:58:20<4:08:04,  1.58it/s]
                                                         
{'loss': 1.1153, 'learning_rate': 4.6878048780487804e-07, 'epoch': 376.16}

 59%|█████▉    | 34080/57600 [5:58:20<4:08:04,  1.58it/s]
 59%|█████▉    | 34081/57600 [5:58:20<4:04:42,  1.60it/s]
 59%|█████▉    | 34082/57600 [5:58:21<4:09:03,  1.57it/s]
 59%|█████▉    | 34083/57600 [5:58:22<3:59:52,  1.63it/s]
 59%|█████▉    | 34084/57600 [5:58:22<3:55:10,  1.67it/s]
 59%|█████▉    | 34085/57600 [5:58:23<4:00:12,  1.63it/s]
 59%|█████▉    | 34086/57600 [5:58:23<3:58:39,  1.64it/s]
 59%|█████▉    | 34087/57600 [5:58:24<3:58:42,  1.64it/s]
 59%|█████▉    | 34088/57600 [5:58:25<3:58:36,  1.64it/s]
 59%|█████▉    | 34089/57600 [5:58:25<4:02:18,  1.62it/s]
 59%|█████▉    | 34090/57600 [5:58:26<4:09:44,  1.57it/s]
 59%|█████▉    | 34091/57600 [5:58:27<4:17:29,  1.52it/s]
 59%|█████▉    | 34092/57600 [5:58:27<4:11:04,  1.56it/s]
 59%|█████▉    | 34093/57600 [5:58:28<4:16:40,  1.53it/s]
 59%|█████▉    | 34094/57600 [5:58:28<4:07:46,  1.58it/s]
 59%|█████▉    | 34095/57600 [5:58:29<4:07:48,  1.58it/s]
 59%|█████▉    | 34096/57600 [5:58:30<4:01:14,  1.62it/s]
 59%|█████▉    | 34097/57600 [5:58:30<4:01:49,  1.62it/s]
 59%|█████▉    | 34098/57600 [5:58:31<3:56:58,  1.65it/s]
 59%|█████▉    | 34099/57600 [5:58:31<3:58:26,  1.64it/s]
 59%|█████▉    | 34100/57600 [5:58:32<4:05:59,  1.59it/s]
                                                         
{'loss': 1.1728, 'learning_rate': 4.6846689895470384e-07, 'epoch': 376.38}

 59%|█████▉    | 34100/57600 [5:58:32<4:05:59,  1.59it/s]
 59%|█████▉    | 34101/57600 [5:58:33<4:09:17,  1.57it/s]
 59%|█████▉    | 34102/57600 [5:58:33<4:01:26,  1.62it/s]
 59%|█████▉    | 34103/57600 [5:58:34<4:01:13,  1.62it/s]
 59%|█████▉    | 34104/57600 [5:58:35<4:05:16,  1.60it/s]
 59%|█████▉    | 34105/57600 [5:58:35<4:04:38,  1.60it/s]
 59%|█████▉    | 34106/57600 [5:58:36<4:07:54,  1.58it/s]
 59%|█████▉    | 34107/57600 [5:58:37<4:08:40,  1.57it/s]
 59%|█████▉    | 34108/57600 [5:58:37<4:05:59,  1.59it/s]
 59%|█████▉    | 34109/57600 [5:58:38<4:06:27,  1.59it/s]
 59%|█████▉    | 34110/57600 [5:58:38<4:08:20,  1.58it/s]
 59%|█████▉    | 34111/57600 [5:58:39<4:00:19,  1.63it/s]
 59%|█████▉    | 34112/57600 [5:58:40<3:58:35,  1.64it/s]
 59%|█████▉    | 34113/57600 [5:58:40<3:54:50,  1.67it/s]
 59%|█████▉    | 34114/57600 [5:58:41<3:51:16,  1.69it/s]
 59%|█████▉    | 34115/57600 [5:58:41<3:59:16,  1.64it/s]
 59%|█████▉    | 34116/57600 [5:58:42<3:58:31,  1.64it/s]
 59%|█████▉    | 34117/57600 [5:58:43<4:03:06,  1.61it/s]
 59%|█████▉    | 34118/57600 [5:58:43<3:59:41,  1.63it/s]
 59%|█████▉    | 34119/57600 [5:58:44<4:03:13,  1.61it/s]
 59%|█████▉    | 34120/57600 [5:58:44<3:57:44,  1.65it/s]
                                                         
{'loss': 1.1574, 'learning_rate': 4.681533101045296e-07, 'epoch': 376.6}

 59%|█████▉    | 34120/57600 [5:58:44<3:57:44,  1.65it/s]
 59%|█████▉    | 34121/57600 [5:58:45<4:01:26,  1.62it/s]
 59%|█████▉    | 34122/57600 [5:58:46<4:05:38,  1.59it/s]
 59%|█████▉    | 34123/57600 [5:58:46<4:04:46,  1.60it/s]
 59%|█████▉    | 34124/57600 [5:58:47<4:00:11,  1.63it/s]
 59%|█████▉    | 34125/57600 [5:58:48<4:04:21,  1.60it/s]
 59%|█████▉    | 34126/57600 [5:58:48<4:07:17,  1.58it/s]
 59%|█████▉    | 34127/57600 [5:58:49<4:17:28,  1.52it/s]
 59%|█████▉    | 34128/57600 [5:58:50<4:15:03,  1.53it/s]
 59%|█████▉    | 34129/57600 [5:58:50<4:13:15,  1.54it/s]
 59%|█████▉    | 34130/57600 [5:58:51<4:08:55,  1.57it/s]
 59%|█████▉    | 34131/57600 [5:58:51<4:05:15,  1.59it/s]
 59%|█████▉    | 34132/57600 [5:58:52<4:07:41,  1.58it/s]
 59%|█████▉    | 34133/57600 [5:58:53<4:14:42,  1.54it/s]
 59%|█████▉    | 34134/57600 [5:58:53<4:11:07,  1.56it/s]
 59%|█████▉    | 34135/57600 [5:58:54<4:05:52,  1.59it/s]
 59%|█████▉    | 34136/57600 [5:58:55<4:09:22,  1.57it/s]
 59%|█████▉    | 34137/57600 [5:58:55<4:11:01,  1.56it/s]
 59%|█████▉    | 34138/57600 [5:58:56<4:14:03,  1.54it/s]
 59%|█████▉    | 34139/57600 [5:58:57<4:07:55,  1.58it/s]
 59%|█████▉    | 34140/57600 [5:58:57<4:05:05,  1.60it/s]
                                                         
{'loss': 1.1542, 'learning_rate': 4.6783972125435534e-07, 'epoch': 376.82}

 59%|█████▉    | 34140/57600 [5:58:57<4:05:05,  1.60it/s]
 59%|█████▉    | 34141/57600 [5:58:58<4:04:00,  1.60it/s]
 59%|█████▉    | 34142/57600 [5:58:58<4:01:02,  1.62it/s]
 59%|█████▉    | 34143/57600 [5:58:59<4:02:35,  1.61it/s]
 59%|█████▉    | 34144/57600 [5:59:00<4:06:44,  1.58it/s]
 59%|█████▉    | 34145/57600 [5:59:00<4:05:30,  1.59it/s]
 59%|█████▉    | 34146/57600 [5:59:01<3:58:13,  1.64it/s]
 59%|█████▉    | 34147/57600 [5:59:02<4:02:35,  1.61it/s]
 59%|█████▉    | 34148/57600 [5:59:02<4:12:24,  1.55it/s]
 59%|█████▉    | 34149/57600 [5:59:03<4:13:34,  1.54it/s]
 59%|█████▉    | 34150/57600 [5:59:04<4:10:58,  1.56it/s]
 59%|█████▉    | 34151/57600 [5:59:04<4:11:16,  1.56it/s]
 59%|█████▉    | 34152/57600 [5:59:05<4:17:31,  1.52it/s]
 59%|█████▉    | 34153/57600 [5:59:06<4:13:58,  1.54it/s]
 59%|█████▉    | 34154/57600 [5:59:06<4:14:04,  1.54it/s]
 59%|█████▉    | 34155/57600 [5:59:07<4:13:19,  1.54it/s]
 59%|█████▉    | 34156/57600 [5:59:07<4:04:10,  1.60it/s]
 59%|█████▉    | 34157/57600 [5:59:08<4:17:00,  1.52it/s]
 59%|█████▉    | 34158/57600 [5:59:09<4:10:57,  1.56it/s]
 59%|█████▉    | 34159/57600 [5:59:09<4:05:43,  1.59it/s]
 59%|█████▉    | 34160/57600 [5:59:10<4:03:47,  1.60it/s]
                                                         
{'loss': 1.1492, 'learning_rate': 4.6752613240418115e-07, 'epoch': 377.04}

 59%|█████▉    | 34160/57600 [5:59:10<4:03:47,  1.60it/s]
 59%|█████▉    | 34161/57600 [5:59:11<3:58:33,  1.64it/s]
 59%|█████▉    | 34162/57600 [5:59:11<3:50:49,  1.69it/s]
 59%|█████▉    | 34163/57600 [5:59:12<3:55:36,  1.66it/s]
 59%|█████▉    | 34164/57600 [5:59:12<3:54:42,  1.66it/s]
 59%|█████▉    | 34165/57600 [5:59:13<3:53:31,  1.67it/s]
 59%|█████▉    | 34166/57600 [5:59:13<3:51:19,  1.69it/s]
 59%|█████▉    | 34167/57600 [5:59:14<4:01:44,  1.62it/s]
 59%|█████▉    | 34168/57600 [5:59:15<4:01:06,  1.62it/s]
 59%|█████▉    | 34169/57600 [5:59:15<4:07:31,  1.58it/s]
 59%|█████▉    | 34170/57600 [5:59:16<4:06:39,  1.58it/s]
 59%|█████▉    | 34171/57600 [5:59:17<4:03:31,  1.60it/s]
 59%|█████▉    | 34172/57600 [5:59:17<3:59:49,  1.63it/s]
 59%|█████▉    | 34173/57600 [5:59:18<3:54:38,  1.66it/s]
 59%|█████▉    | 34174/57600 [5:59:18<3:58:52,  1.63it/s]
 59%|█████▉    | 34175/57600 [5:59:19<3:55:54,  1.65it/s]
 59%|█████▉    | 34176/57600 [5:59:20<4:00:58,  1.62it/s]
 59%|█████▉    | 34177/57600 [5:59:20<4:03:16,  1.60it/s]
 59%|█████▉    | 34178/57600 [5:59:21<4:01:48,  1.61it/s]
 59%|█████▉    | 34179/57600 [5:59:22<4:04:31,  1.60it/s]
 59%|█████▉    | 34180/57600 [5:59:22<4:04:44,  1.59it/s]
                                                         
{'loss': 1.1756, 'learning_rate': 4.67212543554007e-07, 'epoch': 377.26}

 59%|█████▉    | 34180/57600 [5:59:22<4:04:44,  1.59it/s]
 59%|█████▉    | 34181/57600 [5:59:23<4:14:32,  1.53it/s]
 59%|█████▉    | 34182/57600 [5:59:24<4:11:13,  1.55it/s]
 59%|█████▉    | 34183/57600 [5:59:24<4:07:59,  1.57it/s]
 59%|█████▉    | 34184/57600 [5:59:25<4:07:50,  1.57it/s]
 59%|█████▉    | 34185/57600 [5:59:25<4:08:04,  1.57it/s]
 59%|█████▉    | 34186/57600 [5:59:26<4:05:08,  1.59it/s]
 59%|█████▉    | 34187/57600 [5:59:27<4:11:43,  1.55it/s]
 59%|█████▉    | 34188/57600 [5:59:27<4:11:09,  1.55it/s]
 59%|█████▉    | 34189/57600 [5:59:28<4:04:29,  1.60it/s]
 59%|█████▉    | 34190/57600 [5:59:29<4:01:23,  1.62it/s]
 59%|█████▉    | 34191/57600 [5:59:29<4:07:07,  1.58it/s]
 59%|█████▉    | 34192/57600 [5:59:30<4:08:22,  1.57it/s]
 59%|█████▉    | 34193/57600 [5:59:30<4:07:52,  1.57it/s]
 59%|█████▉    | 34194/57600 [5:59:31<3:59:58,  1.63it/s]
 59%|█████▉    | 34195/57600 [5:59:32<4:06:31,  1.58it/s]
 59%|█████▉    | 34196/57600 [5:59:32<4:05:23,  1.59it/s]
 59%|█████▉    | 34197/57600 [5:59:33<4:08:11,  1.57it/s]
 59%|█████▉    | 34198/57600 [5:59:34<4:05:48,  1.59it/s]
 59%|█████▉    | 34199/57600 [5:59:34<4:06:15,  1.58it/s]
 59%|█████▉    | 34200/57600 [5:59:35<4:07:01,  1.58it/s]
                                                         
{'loss': 1.1558, 'learning_rate': 4.668989547038327e-07, 'epoch': 377.48}

 59%|█████▉    | 34200/57600 [5:59:35<4:07:01,  1.58it/s]
 59%|█████▉    | 34201/57600 [5:59:36<4:04:53,  1.59it/s]
 59%|█████▉    | 34202/57600 [5:59:36<4:09:00,  1.57it/s]
 59%|█████▉    | 34203/57600 [5:59:37<4:08:01,  1.57it/s]
 59%|█████▉    | 34204/57600 [5:59:37<4:04:50,  1.59it/s]
 59%|█████▉    | 34205/57600 [5:59:38<4:08:25,  1.57it/s]
 59%|█████▉    | 34206/57600 [5:59:39<4:12:49,  1.54it/s]
 59%|█████▉    | 34207/57600 [5:59:39<4:02:54,  1.61it/s]
 59%|█████▉    | 34208/57600 [5:59:40<3:56:37,  1.65it/s]
 59%|█████▉    | 34209/57600 [5:59:41<4:07:23,  1.58it/s]
 59%|█████▉    | 34210/57600 [5:59:41<4:03:40,  1.60it/s]
 59%|█████▉    | 34211/57600 [5:59:42<4:07:31,  1.57it/s]
 59%|█████▉    | 34212/57600 [5:59:43<4:13:02,  1.54it/s]
 59%|█████▉    | 34213/57600 [5:59:43<4:08:21,  1.57it/s]
 59%|█████▉    | 34214/57600 [5:59:44<4:09:42,  1.56it/s]
 59%|█████▉    | 34215/57600 [5:59:44<3:58:12,  1.64it/s]
 59%|█████▉    | 34216/57600 [5:59:45<4:10:38,  1.55it/s]
 59%|█████▉    | 34217/57600 [5:59:46<4:02:54,  1.60it/s]
 59%|█████▉    | 34218/57600 [5:59:46<4:03:07,  1.60it/s]
 59%|█████▉    | 34219/57600 [5:59:47<4:08:10,  1.57it/s]
 59%|█████▉    | 34220/57600 [5:59:48<4:06:20,  1.58it/s]
                                                         
{'loss': 1.1589, 'learning_rate': 4.6658536585365856e-07, 'epoch': 377.7}

 59%|█████▉    | 34220/57600 [5:59:48<4:06:20,  1.58it/s]
 59%|█████▉    | 34221/57600 [5:59:48<4:05:51,  1.58it/s]
 59%|█████▉    | 34222/57600 [5:59:49<4:02:31,  1.61it/s]
 59%|█████▉    | 34223/57600 [5:59:49<4:12:20,  1.54it/s]
 59%|█████▉    | 34224/57600 [5:59:50<4:08:44,  1.57it/s]
 59%|█████▉    | 34225/57600 [5:59:51<3:58:25,  1.63it/s]
 59%|█████▉    | 34226/57600 [5:59:51<4:04:51,  1.59it/s]
 59%|█████▉    | 34227/57600 [5:59:52<3:58:29,  1.63it/s]
 59%|█████▉    | 34228/57600 [5:59:53<4:11:44,  1.55it/s]
 59%|█████▉    | 34229/57600 [5:59:53<4:01:54,  1.61it/s]
 59%|█████▉    | 34230/57600 [5:59:54<4:03:09,  1.60it/s]
 59%|█████▉    | 34231/57600 [5:59:55<4:15:49,  1.52it/s]
 59%|█████▉    | 34232/57600 [5:59:55<4:06:12,  1.58it/s]
 59%|█████▉    | 34233/57600 [5:59:56<4:10:04,  1.56it/s]
 59%|█████▉    | 34234/57600 [5:59:56<4:11:19,  1.55it/s]
 59%|█████▉    | 34235/57600 [5:59:57<4:03:24,  1.60it/s]
 59%|█████▉    | 34236/57600 [5:59:58<3:59:08,  1.63it/s]
 59%|█████▉    | 34237/57600 [5:59:58<4:06:40,  1.58it/s]
 59%|█████▉    | 34238/57600 [5:59:59<4:06:14,  1.58it/s]
 59%|█████▉    | 34239/57600 [5:59:59<4:00:33,  1.62it/s]
 59%|█████▉    | 34240/57600 [6:00:00<4:03:03,  1.60it/s]
                                                         
{'loss': 1.1709, 'learning_rate': 4.6627177700348426e-07, 'epoch': 377.92}

 59%|█████▉    | 34240/57600 [6:00:00<4:03:03,  1.60it/s]
 59%|█████▉    | 34241/57600 [6:00:01<4:03:09,  1.60it/s]
 59%|█████▉    | 34242/57600 [6:00:01<4:03:43,  1.60it/s]
 59%|█████▉    | 34243/57600 [6:00:02<4:01:07,  1.61it/s]
 59%|█████▉    | 34244/57600 [6:00:03<4:03:38,  1.60it/s]
 59%|█████▉    | 34245/57600 [6:00:03<4:07:09,  1.57it/s]
 59%|█████▉    | 34246/57600 [6:00:04<4:13:46,  1.53it/s]
 59%|█████▉    | 34247/57600 [6:00:05<4:16:47,  1.52it/s]
 59%|█████▉    | 34248/57600 [6:00:05<4:12:21,  1.54it/s]
 59%|█████▉    | 34249/57600 [6:00:06<4:15:41,  1.52it/s]
 59%|█████▉    | 34250/57600 [6:00:07<4:15:31,  1.52it/s]
 59%|█████▉    | 34251/57600 [6:00:07<4:14:18,  1.53it/s]
 59%|█████▉    | 34252/57600 [6:00:08<4:20:07,  1.50it/s]
 59%|█████▉    | 34253/57600 [6:00:09<4:14:04,  1.53it/s]
 59%|█████▉    | 34254/57600 [6:00:09<4:15:02,  1.53it/s]
 59%|█████▉    | 34255/57600 [6:00:10<4:12:57,  1.54it/s]
 59%|█████▉    | 34256/57600 [6:00:10<4:04:03,  1.59it/s]
 59%|█████▉    | 34257/57600 [6:00:11<4:01:23,  1.61it/s]
 59%|█████▉    | 34258/57600 [6:00:12<4:01:15,  1.61it/s]
 59%|█████▉    | 34259/57600 [6:00:12<4:00:29,  1.62it/s]
 59%|█████▉    | 34260/57600 [6:00:13<3:59:10,  1.63it/s]
                                                         
{'loss': 1.1598, 'learning_rate': 4.659581881533101e-07, 'epoch': 378.15}

 59%|█████▉    | 34260/57600 [6:00:13<3:59:10,  1.63it/s]
 59%|█████▉    | 34261/57600 [6:00:13<3:54:40,  1.66it/s]
 59%|█████▉    | 34262/57600 [6:00:14<3:58:45,  1.63it/s]
 59%|█████▉    | 34263/57600 [6:00:15<3:55:27,  1.65it/s]
 59%|█████▉    | 34264/57600 [6:00:15<3:54:47,  1.66it/s]
 59%|█████▉    | 34265/57600 [6:00:16<4:00:02,  1.62it/s]
 59%|█████▉    | 34266/57600 [6:00:17<4:01:23,  1.61it/s]
 59%|█████▉    | 34267/57600 [6:00:17<4:07:21,  1.57it/s]
 59%|█████▉    | 34268/57600 [6:00:18<4:01:50,  1.61it/s]
 59%|█████▉    | 34269/57600 [6:00:18<4:03:13,  1.60it/s]
 59%|█████▉    | 34270/57600 [6:00:19<4:05:04,  1.59it/s]
 59%|█████▉    | 34271/57600 [6:00:20<3:59:31,  1.62it/s]
 60%|█████▉    | 34272/57600 [6:00:20<4:01:40,  1.61it/s]
 60%|█████▉    | 34273/57600 [6:00:21<4:03:44,  1.60it/s]
 60%|█████▉    | 34274/57600 [6:00:22<4:02:41,  1.60it/s]
 60%|█████▉    | 34275/57600 [6:00:22<4:00:27,  1.62it/s]
 60%|█████▉    | 34276/57600 [6:00:23<4:00:09,  1.62it/s]
 60%|█████▉    | 34277/57600 [6:00:23<4:01:29,  1.61it/s]
 60%|█████▉    | 34278/57600 [6:00:24<3:54:33,  1.66it/s]
 60%|█████▉    | 34279/57600 [6:00:25<3:57:04,  1.64it/s]
 60%|█████▉    | 34280/57600 [6:00:25<3:54:14,  1.66it/s]
                                                         
{'loss': 1.165, 'learning_rate': 4.656445993031358e-07, 'epoch': 378.37}

 60%|█████▉    | 34280/57600 [6:00:25<3:54:14,  1.66it/s]
 60%|█████▉    | 34281/57600 [6:00:26<3:52:13,  1.67it/s]
 60%|█████▉    | 34282/57600 [6:00:26<3:53:14,  1.67it/s]
 60%|█████▉    | 34283/57600 [6:00:27<3:58:17,  1.63it/s]
 60%|█████▉    | 34284/57600 [6:00:28<3:58:11,  1.63it/s]
 60%|█████▉    | 34285/57600 [6:00:28<4:03:51,  1.59it/s]
 60%|█████▉    | 34286/57600 [6:00:29<4:00:53,  1.61it/s]
 60%|█████▉    | 34287/57600 [6:00:30<4:03:31,  1.60it/s]
 60%|█████▉    | 34288/57600 [6:00:30<3:59:50,  1.62it/s]
 60%|█████▉    | 34289/57600 [6:00:31<3:58:31,  1.63it/s]
 60%|█████▉    | 34290/57600 [6:00:31<3:52:51,  1.67it/s]
 60%|█████▉    | 34291/57600 [6:00:32<3:56:17,  1.64it/s]
 60%|█████▉    | 34292/57600 [6:00:33<4:03:05,  1.60it/s]
 60%|█████▉    | 34293/57600 [6:00:33<3:56:52,  1.64it/s]
 60%|█████▉    | 34294/57600 [6:00:34<3:57:59,  1.63it/s]
 60%|█████▉    | 34295/57600 [6:00:34<4:03:18,  1.60it/s]
 60%|█████▉    | 34296/57600 [6:00:35<4:08:06,  1.57it/s]
 60%|█████▉    | 34297/57600 [6:00:36<4:05:32,  1.58it/s]
 60%|█████▉    | 34298/57600 [6:00:36<4:02:29,  1.60it/s]
 60%|█████▉    | 34299/57600 [6:00:37<3:58:22,  1.63it/s]
 60%|█████▉    | 34300/57600 [6:00:38<4:02:48,  1.60it/s]
                                                         
{'loss': 1.1712, 'learning_rate': 4.653310104529616e-07, 'epoch': 378.59}

 60%|█████▉    | 34300/57600 [6:00:38<4:02:48,  1.60it/s]
 60%|█████▉    | 34301/57600 [6:00:38<4:00:31,  1.61it/s]
 60%|█████▉    | 34302/57600 [6:00:39<4:03:33,  1.59it/s]
 60%|█████▉    | 34303/57600 [6:00:40<4:13:27,  1.53it/s]
 60%|█████▉    | 34304/57600 [6:00:40<4:01:58,  1.60it/s]
 60%|█████▉    | 34305/57600 [6:00:41<4:06:33,  1.57it/s]
 60%|█████▉    | 34306/57600 [6:00:42<4:24:12,  1.47it/s]
 60%|█████▉    | 34307/57600 [6:00:42<4:15:03,  1.52it/s]
 60%|█████▉    | 34308/57600 [6:00:43<4:03:26,  1.59it/s]
 60%|█████▉    | 34309/57600 [6:00:43<4:04:35,  1.59it/s]
 60%|█████▉    | 34310/57600 [6:00:44<4:10:02,  1.55it/s]
 60%|█████▉    | 34311/57600 [6:00:45<4:09:19,  1.56it/s]
 60%|█████▉    | 34312/57600 [6:00:45<3:57:51,  1.63it/s]
 60%|█████▉    | 34313/57600 [6:00:46<3:57:55,  1.63it/s]
 60%|█████▉    | 34314/57600 [6:00:46<3:55:23,  1.65it/s]
 60%|█████▉    | 34315/57600 [6:00:47<3:53:02,  1.67it/s]
 60%|█████▉    | 34316/57600 [6:00:48<3:56:30,  1.64it/s]
 60%|█████▉    | 34317/57600 [6:00:48<3:56:35,  1.64it/s]
 60%|█████▉    | 34318/57600 [6:00:49<3:59:38,  1.62it/s]
 60%|█████▉    | 34319/57600 [6:00:50<4:05:07,  1.58it/s]
 60%|█████▉    | 34320/57600 [6:00:50<3:55:28,  1.65it/s]
                                                         
{'loss': 1.1503, 'learning_rate': 4.650174216027875e-07, 'epoch': 378.81}

 60%|█████▉    | 34320/57600 [6:00:50<3:55:28,  1.65it/s]
 60%|█████▉    | 34321/57600 [6:00:51<3:54:12,  1.66it/s]
 60%|█████▉    | 34322/57600 [6:00:51<4:08:59,  1.56it/s]
 60%|█████▉    | 34323/57600 [6:00:52<4:09:58,  1.55it/s]
 60%|█████▉    | 34324/57600 [6:00:53<4:18:01,  1.50it/s]
 60%|█████▉    | 34325/57600 [6:00:53<4:14:16,  1.53it/s]
 60%|█████▉    | 34326/57600 [6:00:54<4:06:14,  1.58it/s]
 60%|█████▉    | 34327/57600 [6:00:55<4:07:05,  1.57it/s]
 60%|█████▉    | 34328/57600 [6:00:55<4:05:54,  1.58it/s]
 60%|█████▉    | 34329/57600 [6:00:56<4:01:58,  1.60it/s]
 60%|█████▉    | 34330/57600 [6:00:56<3:54:05,  1.66it/s]
 60%|█████▉    | 34331/57600 [6:00:57<3:59:07,  1.62it/s]
 60%|█████▉    | 34332/57600 [6:00:58<3:58:26,  1.63it/s]
 60%|█████▉    | 34333/57600 [6:00:58<3:52:05,  1.67it/s]
 60%|█████▉    | 34334/57600 [6:00:59<3:59:19,  1.62it/s]
 60%|█████▉    | 34335/57600 [6:01:00<3:58:24,  1.63it/s]
 60%|█████▉    | 34336/57600 [6:01:00<3:59:07,  1.62it/s]
 60%|█████▉    | 34337/57600 [6:01:01<4:03:43,  1.59it/s]
 60%|█████▉    | 34338/57600 [6:01:02<4:15:58,  1.51it/s]
 60%|█████▉    | 34339/57600 [6:01:02<4:11:59,  1.54it/s]
 60%|█████▉    | 34340/57600 [6:01:03<4:09:11,  1.56it/s]
                                                         
{'loss': 1.1694, 'learning_rate': 4.647038327526132e-07, 'epoch': 379.03}

 60%|█████▉    | 34340/57600 [6:01:03<4:09:11,  1.56it/s]
 60%|█████▉    | 34341/57600 [6:01:03<4:13:13,  1.53it/s]
 60%|█████▉    | 34342/57600 [6:01:04<4:09:43,  1.55it/s]
 60%|█████▉    | 34343/57600 [6:01:05<4:10:43,  1.55it/s]
 60%|█████▉    | 34344/57600 [6:01:05<4:12:34,  1.53it/s]
 60%|█████▉    | 34345/57600 [6:01:06<4:06:49,  1.57it/s]
 60%|█████▉    | 34346/57600 [6:01:07<3:58:51,  1.62it/s]
 60%|█████▉    | 34347/57600 [6:01:07<4:04:36,  1.58it/s]
 60%|█████▉    | 34348/57600 [6:01:08<4:10:47,  1.55it/s]
 60%|█████▉    | 34349/57600 [6:01:09<4:04:33,  1.58it/s]
 60%|█████▉    | 34350/57600 [6:01:09<4:03:31,  1.59it/s]
 60%|█████▉    | 34351/57600 [6:01:10<4:06:16,  1.57it/s]
 60%|█████▉    | 34352/57600 [6:01:10<4:05:17,  1.58it/s]
 60%|█████▉    | 34353/57600 [6:01:11<4:07:49,  1.56it/s]
 60%|█████▉    | 34354/57600 [6:01:12<4:02:01,  1.60it/s]
 60%|█████▉    | 34355/57600 [6:01:12<4:03:05,  1.59it/s]
 60%|█████▉    | 34356/57600 [6:01:13<4:03:11,  1.59it/s]
 60%|█████▉    | 34357/57600 [6:01:14<4:03:49,  1.59it/s]
 60%|█████▉    | 34358/57600 [6:01:14<4:13:11,  1.53it/s]
 60%|█████▉    | 34359/57600 [6:01:15<4:08:06,  1.56it/s]
 60%|█████▉    | 34360/57600 [6:01:16<4:15:36,  1.52it/s]
                                                         
{'loss': 1.1221, 'learning_rate': 4.6439024390243904e-07, 'epoch': 379.25}

 60%|█████▉    | 34360/57600 [6:01:16<4:15:36,  1.52it/s]
 60%|█████▉    | 34361/57600 [6:01:16<4:18:34,  1.50it/s]
 60%|█████▉    | 34362/57600 [6:01:17<4:08:40,  1.56it/s]
 60%|█████▉    | 34363/57600 [6:01:17<4:08:26,  1.56it/s]
 60%|█████▉    | 34364/57600 [6:01:18<4:07:37,  1.56it/s]
 60%|█████▉    | 34365/57600 [6:01:19<3:53:56,  1.66it/s]
 60%|█████▉    | 34366/57600 [6:01:19<4:05:40,  1.58it/s]
 60%|█████▉    | 34367/57600 [6:01:20<4:11:56,  1.54it/s]
 60%|█████▉    | 34368/57600 [6:01:21<4:04:54,  1.58it/s]
 60%|█████▉    | 34369/57600 [6:01:21<4:09:22,  1.55it/s]
 60%|█████▉    | 34370/57600 [6:01:22<4:03:08,  1.59it/s]
 60%|█████▉    | 34371/57600 [6:01:23<4:02:35,  1.60it/s]
 60%|█████▉    | 34372/57600 [6:01:23<3:57:19,  1.63it/s]
 60%|█████▉    | 34373/57600 [6:01:24<3:56:00,  1.64it/s]
 60%|█████▉    | 34374/57600 [6:01:24<3:56:39,  1.64it/s]
 60%|█████▉    | 34375/57600 [6:01:25<3:58:16,  1.62it/s]
 60%|█████▉    | 34376/57600 [6:01:26<4:07:03,  1.57it/s]
 60%|█████▉    | 34377/57600 [6:01:26<4:00:55,  1.61it/s]
 60%|█████▉    | 34378/57600 [6:01:27<4:00:26,  1.61it/s]
 60%|█████▉    | 34379/57600 [6:01:27<3:59:04,  1.62it/s]
 60%|█████▉    | 34380/57600 [6:01:28<4:01:27,  1.60it/s]
                                                         
{'loss': 1.1639, 'learning_rate': 4.6407665505226474e-07, 'epoch': 379.47}

 60%|█████▉    | 34380/57600 [6:01:28<4:01:27,  1.60it/s]
 60%|█████▉    | 34381/57600 [6:01:29<3:58:20,  1.62it/s]
 60%|█████▉    | 34382/57600 [6:01:29<3:53:17,  1.66it/s]
 60%|█████▉    | 34383/57600 [6:01:30<3:44:49,  1.72it/s]
 60%|█████▉    | 34384/57600 [6:01:30<3:48:49,  1.69it/s]
 60%|█████▉    | 34385/57600 [6:01:31<3:49:00,  1.69it/s]
 60%|█████▉    | 34386/57600 [6:01:32<3:46:21,  1.71it/s]
 60%|█████▉    | 34387/57600 [6:01:32<3:50:24,  1.68it/s]
 60%|█████▉    | 34388/57600 [6:01:33<3:47:28,  1.70it/s]
 60%|█████▉    | 34389/57600 [6:01:33<3:50:10,  1.68it/s]
 60%|█████▉    | 34390/57600 [6:01:34<3:52:22,  1.66it/s]
 60%|█████▉    | 34391/57600 [6:01:35<3:54:40,  1.65it/s]
 60%|█████▉    | 34392/57600 [6:01:35<4:08:35,  1.56it/s]
 60%|█████▉    | 34393/57600 [6:01:36<4:04:24,  1.58it/s]
 60%|█████▉    | 34394/57600 [6:01:37<4:11:47,  1.54it/s]
 60%|█████▉    | 34395/57600 [6:01:37<4:15:02,  1.52it/s]
 60%|█████▉    | 34396/57600 [6:01:38<4:10:27,  1.54it/s]
 60%|█████▉    | 34397/57600 [6:01:39<4:01:23,  1.60it/s]
 60%|█████▉    | 34398/57600 [6:01:39<4:00:29,  1.61it/s]
 60%|█████▉    | 34399/57600 [6:01:40<4:11:59,  1.53it/s]
 60%|█████▉    | 34400/57600 [6:01:40<4:01:35,  1.60it/s]
                                                         
{'loss': 1.2062, 'learning_rate': 4.637630662020906e-07, 'epoch': 379.69}

 60%|█████▉    | 34400/57600 [6:01:40<4:01:35,  1.60it/s]
 60%|█████▉    | 34401/57600 [6:01:41<3:59:17,  1.62it/s]
 60%|█████▉    | 34402/57600 [6:01:42<3:54:43,  1.65it/s]
 60%|█████▉    | 34403/57600 [6:01:42<3:57:39,  1.63it/s]
 60%|█████▉    | 34404/57600 [6:01:43<3:58:55,  1.62it/s]
 60%|█████▉    | 34405/57600 [6:01:43<4:03:20,  1.59it/s]
 60%|█████▉    | 34406/57600 [6:01:44<4:04:02,  1.58it/s]
 60%|█████▉    | 34407/57600 [6:01:45<3:58:09,  1.62it/s]
 60%|█████▉    | 34408/57600 [6:01:45<3:56:36,  1.63it/s]
 60%|█████▉    | 34409/57600 [6:01:46<3:55:37,  1.64it/s]
 60%|█████▉    | 34410/57600 [6:01:47<3:53:12,  1.66it/s]
 60%|█████▉    | 34411/57600 [6:01:47<3:51:43,  1.67it/s]
 60%|█████▉    | 34412/57600 [6:01:48<3:46:37,  1.71it/s]
 60%|█████▉    | 34413/57600 [6:01:48<3:51:08,  1.67it/s]
 60%|█████▉    | 34414/57600 [6:01:49<3:50:18,  1.68it/s]
 60%|█████▉    | 34415/57600 [6:01:50<3:56:01,  1.64it/s]
 60%|█████▉    | 34416/57600 [6:01:50<3:56:45,  1.63it/s]
 60%|█████▉    | 34417/57600 [6:01:51<3:50:04,  1.68it/s]
 60%|█████▉    | 34418/57600 [6:01:51<3:55:40,  1.64it/s]
 60%|█████▉    | 34419/57600 [6:01:52<3:58:25,  1.62it/s]
 60%|█████▉    | 34420/57600 [6:01:53<4:01:05,  1.60it/s]
                                                         
{'loss': 1.1965, 'learning_rate': 4.634494773519163e-07, 'epoch': 379.91}

 60%|█████▉    | 34420/57600 [6:01:53<4:01:05,  1.60it/s]
 60%|█████▉    | 34421/57600 [6:01:53<4:02:06,  1.60it/s]
 60%|█████▉    | 34422/57600 [6:01:54<4:03:28,  1.59it/s]
 60%|█████▉    | 34423/57600 [6:01:54<3:58:08,  1.62it/s]
 60%|█████▉    | 34424/57600 [6:01:55<3:55:49,  1.64it/s]
 60%|█████▉    | 34425/57600 [6:01:56<3:56:40,  1.63it/s]
 60%|█████▉    | 34426/57600 [6:01:56<3:59:40,  1.61it/s]
 60%|█████▉    | 34427/57600 [6:01:57<4:00:48,  1.60it/s]
 60%|█████▉    | 34428/57600 [6:01:58<4:04:41,  1.58it/s]
 60%|█████▉    | 34429/57600 [6:01:58<4:07:27,  1.56it/s]
 60%|█████▉    | 34430/57600 [6:01:59<4:02:28,  1.59it/s]
 60%|█████▉    | 34431/57600 [6:01:59<4:00:29,  1.61it/s]
 60%|█████▉    | 34432/57600 [6:02:00<3:57:54,  1.62it/s]
 60%|█████▉    | 34433/57600 [6:02:01<4:01:07,  1.60it/s]
 60%|█████▉    | 34434/57600 [6:02:01<4:02:45,  1.59it/s]
 60%|█████▉    | 34435/57600 [6:02:02<4:01:10,  1.60it/s]
 60%|█████▉    | 34436/57600 [6:02:03<4:04:56,  1.58it/s]
 60%|█████▉    | 34437/57600 [6:02:03<4:11:02,  1.54it/s]
 60%|█████▉    | 34438/57600 [6:02:04<4:03:08,  1.59it/s]
 60%|█████▉    | 34439/57600 [6:02:05<4:02:52,  1.59it/s]
 60%|█████▉    | 34440/57600 [6:02:05<4:06:17,  1.57it/s]
                                                         
{'loss': 1.1416, 'learning_rate': 4.6313588850174215e-07, 'epoch': 380.13}

 60%|█████▉    | 34440/57600 [6:02:05<4:06:17,  1.57it/s]
 60%|█████▉    | 34441/57600 [6:02:06<4:04:52,  1.58it/s]
 60%|█████▉    | 34442/57600 [6:02:06<4:01:36,  1.60it/s]
 60%|█████▉    | 34443/57600 [6:02:07<3:54:48,  1.64it/s]
 60%|█████▉    | 34444/57600 [6:02:08<4:01:01,  1.60it/s]
 60%|█████▉    | 34445/57600 [6:02:08<4:01:25,  1.60it/s]
 60%|█████▉    | 34446/57600 [6:02:09<4:15:14,  1.51it/s]
 60%|█████▉    | 34447/57600 [6:02:10<4:09:26,  1.55it/s]
 60%|█████▉    | 34448/57600 [6:02:10<4:04:51,  1.58it/s]
 60%|█████▉    | 34449/57600 [6:02:11<4:04:17,  1.58it/s]
 60%|█████▉    | 34450/57600 [6:02:12<4:07:00,  1.56it/s]
 60%|█████▉    | 34451/57600 [6:02:12<4:00:24,  1.60it/s]
 60%|█████▉    | 34452/57600 [6:02:13<3:51:49,  1.66it/s]
 60%|█████▉    | 34453/57600 [6:02:13<3:52:57,  1.66it/s]
 60%|█████▉    | 34454/57600 [6:02:14<4:03:52,  1.58it/s]
 60%|█████▉    | 34455/57600 [6:02:15<4:02:11,  1.59it/s]
 60%|█████▉    | 34456/57600 [6:02:15<4:02:32,  1.59it/s]
 60%|█████▉    | 34457/57600 [6:02:16<4:03:55,  1.58it/s]
 60%|█████▉    | 34458/57600 [6:02:16<4:00:40,  1.60it/s]
 60%|█████▉    | 34459/57600 [6:02:17<4:04:18,  1.58it/s]
 60%|█████▉    | 34460/57600 [6:02:18<4:03:34,  1.58it/s]
                                                         
{'loss': 1.1331, 'learning_rate': 4.6282229965156796e-07, 'epoch': 380.35}

 60%|█████▉    | 34460/57600 [6:02:18<4:03:34,  1.58it/s]
 60%|█████▉    | 34461/57600 [6:02:18<4:02:02,  1.59it/s]
 60%|█████▉    | 34462/57600 [6:02:19<4:08:45,  1.55it/s]
 60%|█████▉    | 34463/57600 [6:02:20<4:01:13,  1.60it/s]
 60%|█████▉    | 34464/57600 [6:02:20<3:58:22,  1.62it/s]
 60%|█████▉    | 34465/57600 [6:02:21<3:53:41,  1.65it/s]
 60%|█████▉    | 34466/57600 [6:02:21<4:02:09,  1.59it/s]
 60%|█████▉    | 34467/57600 [6:02:22<3:59:19,  1.61it/s]
 60%|█████▉    | 34468/57600 [6:02:23<3:57:06,  1.63it/s]
 60%|█████▉    | 34469/57600 [6:02:23<3:56:23,  1.63it/s]
 60%|█████▉    | 34470/57600 [6:02:24<4:04:55,  1.57it/s]
 60%|█████▉    | 34471/57600 [6:02:25<4:06:55,  1.56it/s]
 60%|█████▉    | 34472/57600 [6:02:25<3:58:29,  1.62it/s]
 60%|█████▉    | 34473/57600 [6:02:26<3:58:15,  1.62it/s]
 60%|█████▉    | 34474/57600 [6:02:27<4:05:02,  1.57it/s]
 60%|█████▉    | 34475/57600 [6:02:27<3:59:01,  1.61it/s]
 60%|█████▉    | 34476/57600 [6:02:28<4:09:28,  1.54it/s]
 60%|█████▉    | 34477/57600 [6:02:28<4:02:32,  1.59it/s]
 60%|█████▉    | 34478/57600 [6:02:29<4:05:49,  1.57it/s]
 60%|█████▉    | 34479/57600 [6:02:30<4:03:03,  1.59it/s]
 60%|█████▉    | 34480/57600 [6:02:30<3:57:14,  1.62it/s]
                                                         
{'loss': 1.1529, 'learning_rate': 4.625087108013937e-07, 'epoch': 380.57}

 60%|█████▉    | 34480/57600 [6:02:30<3:57:14,  1.62it/s]
 60%|█████▉    | 34481/57600 [6:02:31<3:52:34,  1.66it/s]
 60%|█████▉    | 34482/57600 [6:02:31<3:55:36,  1.64it/s]
 60%|█████▉    | 34483/57600 [6:02:32<4:05:36,  1.57it/s]
 60%|█████▉    | 34484/57600 [6:02:33<3:59:37,  1.61it/s]
 60%|█████▉    | 34485/57600 [6:02:33<3:55:57,  1.63it/s]
 60%|█████▉    | 34486/57600 [6:02:34<3:49:43,  1.68it/s]
 60%|█████▉    | 34487/57600 [6:02:34<3:49:44,  1.68it/s]
 60%|█████▉    | 34488/57600 [6:02:35<3:49:27,  1.68it/s]
 60%|█████▉    | 34489/57600 [6:02:36<3:50:40,  1.67it/s]
 60%|█████▉    | 34490/57600 [6:02:36<4:01:41,  1.59it/s]
 60%|█████▉    | 34491/57600 [6:02:37<3:58:48,  1.61it/s]
 60%|█████▉    | 34492/57600 [6:02:38<4:05:58,  1.57it/s]
 60%|█████▉    | 34493/57600 [6:02:38<4:05:04,  1.57it/s]
 60%|█████▉    | 34494/57600 [6:02:39<3:56:25,  1.63it/s]
 60%|█████▉    | 34495/57600 [6:02:39<3:51:30,  1.66it/s]
 60%|█████▉    | 34496/57600 [6:02:40<3:46:51,  1.70it/s]
 60%|█████▉    | 34497/57600 [6:02:41<3:51:07,  1.67it/s]
 60%|█████▉    | 34498/57600 [6:02:41<4:00:00,  1.60it/s]
 60%|█████▉    | 34499/57600 [6:02:42<3:58:45,  1.61it/s]
 60%|█████▉    | 34500/57600 [6:02:42<3:53:22,  1.65it/s]
                                                         
{'loss': 1.1931, 'learning_rate': 4.621951219512195e-07, 'epoch': 380.79}

 60%|█████▉    | 34500/57600 [6:02:42<3:53:22,  1.65it/s]
 60%|█████▉    | 34501/57600 [6:02:43<3:49:28,  1.68it/s]
 60%|█████▉    | 34502/57600 [6:02:44<3:56:22,  1.63it/s]
 60%|█████▉    | 34503/57600 [6:02:44<3:58:37,  1.61it/s]
 60%|█████▉    | 34504/57600 [6:02:45<4:09:22,  1.54it/s]
 60%|█████▉    | 34505/57600 [6:02:46<4:03:10,  1.58it/s]
 60%|█████▉    | 34506/57600 [6:02:46<4:05:31,  1.57it/s]
 60%|█████▉    | 34507/57600 [6:02:47<4:04:24,  1.57it/s]
 60%|█████▉    | 34508/57600 [6:02:48<4:05:37,  1.57it/s]
 60%|█████▉    | 34509/57600 [6:02:48<4:02:22,  1.59it/s]
 60%|█████▉    | 34510/57600 [6:02:49<4:03:05,  1.58it/s]
 60%|█████▉    | 34511/57600 [6:02:49<3:53:48,  1.65it/s]
 60%|█████▉    | 34512/57600 [6:02:50<4:06:59,  1.56it/s]
 60%|█████▉    | 34513/57600 [6:02:51<4:14:52,  1.51it/s]
 60%|█████▉    | 34514/57600 [6:02:51<4:05:26,  1.57it/s]
 60%|█████▉    | 34515/57600 [6:02:52<4:03:10,  1.58it/s]
 60%|█████▉    | 34516/57600 [6:02:53<3:58:54,  1.61it/s]
 60%|█████▉    | 34517/57600 [6:02:53<3:58:21,  1.61it/s]
 60%|█████▉    | 34518/57600 [6:02:54<4:04:15,  1.57it/s]
 60%|█████▉    | 34519/57600 [6:02:55<4:13:08,  1.52it/s]
 60%|█████▉    | 34520/57600 [6:02:55<4:13:32,  1.52it/s]
                                                         
{'loss': 1.1638, 'learning_rate': 4.618815331010452e-07, 'epoch': 381.02}

 60%|█████▉    | 34520/57600 [6:02:55<4:13:32,  1.52it/s]
 60%|█████▉    | 34521/57600 [6:02:56<4:16:10,  1.50it/s]
 60%|█████▉    | 34522/57600 [6:02:57<4:07:52,  1.55it/s]
 60%|█████▉    | 34523/57600 [6:02:57<3:59:28,  1.61it/s]
 60%|█████▉    | 34524/57600 [6:02:58<4:10:01,  1.54it/s]
 60%|█████▉    | 34525/57600 [6:02:58<4:08:58,  1.54it/s]
 60%|█████▉    | 34526/57600 [6:02:59<4:04:02,  1.58it/s]
 60%|█████▉    | 34527/57600 [6:03:00<4:00:42,  1.60it/s]
 60%|█████▉    | 34528/57600 [6:03:00<3:58:08,  1.61it/s]
 60%|█████▉    | 34529/57600 [6:03:01<3:58:48,  1.61it/s]
 60%|█████▉    | 34530/57600 [6:03:01<3:51:52,  1.66it/s]
 60%|█████▉    | 34531/57600 [6:03:02<3:54:58,  1.64it/s]
 60%|█████▉    | 34532/57600 [6:03:03<3:54:10,  1.64it/s]
 60%|█████▉    | 34533/57600 [6:03:03<3:49:08,  1.68it/s]
 60%|█████▉    | 34534/57600 [6:03:04<3:47:00,  1.69it/s]
 60%|█████▉    | 34535/57600 [6:03:04<3:52:32,  1.65it/s]
 60%|█████▉    | 34536/57600 [6:03:05<3:51:56,  1.66it/s]
 60%|█████▉    | 34537/57600 [6:03:06<3:47:44,  1.69it/s]
 60%|█████▉    | 34538/57600 [6:03:06<3:55:09,  1.63it/s]
 60%|█████▉    | 34539/57600 [6:03:07<3:55:34,  1.63it/s]
 60%|█████▉    | 34540/57600 [6:03:08<3:56:35,  1.62it/s]
                                                         
{'loss': 1.1293, 'learning_rate': 4.6156794425087107e-07, 'epoch': 381.24}

 60%|█████▉    | 34540/57600 [6:03:08<3:56:35,  1.62it/s]
 60%|█████▉    | 34541/57600 [6:03:08<3:48:33,  1.68it/s]
 60%|█████▉    | 34542/57600 [6:03:09<3:52:11,  1.66it/s]
 60%|█████▉    | 34543/57600 [6:03:09<3:57:10,  1.62it/s]
 60%|█████▉    | 34544/57600 [6:03:10<4:01:39,  1.59it/s]
 60%|█████▉    | 34545/57600 [6:03:11<3:59:51,  1.60it/s]
 60%|█████▉    | 34546/57600 [6:03:11<3:57:15,  1.62it/s]
 60%|█████▉    | 34547/57600 [6:03:12<3:55:18,  1.63it/s]
 60%|█████▉    | 34548/57600 [6:03:12<3:59:06,  1.61it/s]
 60%|█████▉    | 34549/57600 [6:03:13<4:02:15,  1.59it/s]
 60%|█████▉    | 34550/57600 [6:03:14<3:56:29,  1.62it/s]
 60%|█████▉    | 34551/57600 [6:03:14<3:55:11,  1.63it/s]
 60%|█████▉    | 34552/57600 [6:03:15<4:03:15,  1.58it/s]
 60%|█████▉    | 34553/57600 [6:03:16<4:16:32,  1.50it/s]
 60%|█████▉    | 34554/57600 [6:03:16<4:19:43,  1.48it/s]
 60%|█████▉    | 34555/57600 [6:03:17<4:10:06,  1.54it/s]
 60%|█████▉    | 34556/57600 [6:03:18<4:12:59,  1.52it/s]
 60%|█████▉    | 34557/57600 [6:03:18<4:10:24,  1.53it/s]
 60%|█████▉    | 34558/57600 [6:03:19<4:07:32,  1.55it/s]
 60%|█████▉    | 34559/57600 [6:03:20<3:58:03,  1.61it/s]
 60%|██████    | 34560/57600 [6:03:20<4:01:16,  1.59it/s]
                                                         
{'loss': 1.1728, 'learning_rate': 4.612543554006968e-07, 'epoch': 381.46}

 60%|██████    | 34560/57600 [6:03:20<4:01:16,  1.59it/s]
 60%|██████    | 34561/57600 [6:03:21<4:03:38,  1.58it/s]
 60%|██████    | 34562/57600 [6:03:21<3:57:01,  1.62it/s]
 60%|██████    | 34563/57600 [6:03:22<4:00:17,  1.60it/s]
 60%|██████    | 34564/57600 [6:03:23<3:57:26,  1.62it/s]
 60%|██████    | 34565/57600 [6:03:23<3:56:26,  1.62it/s]
 60%|██████    | 34566/57600 [6:03:24<3:54:28,  1.64it/s]
 60%|██████    | 34567/57600 [6:03:24<3:48:36,  1.68it/s]
 60%|██████    | 34568/57600 [6:03:25<3:49:32,  1.67it/s]
 60%|██████    | 34569/57600 [6:03:26<3:55:08,  1.63it/s]
 60%|██████    | 34570/57600 [6:03:26<3:54:03,  1.64it/s]
 60%|██████    | 34571/57600 [6:03:27<3:56:38,  1.62it/s]
 60%|██████    | 34572/57600 [6:03:28<3:55:39,  1.63it/s]
 60%|██████    | 34573/57600 [6:03:28<3:57:17,  1.62it/s]
 60%|██████    | 34574/57600 [6:03:29<3:57:58,  1.61it/s]
 60%|██████    | 34575/57600 [6:03:29<4:00:21,  1.60it/s]
 60%|██████    | 34576/57600 [6:03:30<3:55:52,  1.63it/s]
 60%|██████    | 34577/57600 [6:03:31<4:03:55,  1.57it/s]
 60%|██████    | 34578/57600 [6:03:31<4:00:06,  1.60it/s]
 60%|██████    | 34579/57600 [6:03:32<3:50:40,  1.66it/s]
 60%|██████    | 34580/57600 [6:03:32<3:45:59,  1.70it/s]
                                                         
{'loss': 1.1847, 'learning_rate': 4.6094076655052263e-07, 'epoch': 381.68}

 60%|██████    | 34580/57600 [6:03:32<3:45:59,  1.70it/s]
 60%|██████    | 34581/57600 [6:03:33<3:51:36,  1.66it/s]
 60%|██████    | 34582/57600 [6:03:34<3:55:13,  1.63it/s]
 60%|██████    | 34583/57600 [6:03:34<3:54:25,  1.64it/s]
 60%|██████    | 34584/57600 [6:03:35<3:49:50,  1.67it/s]
 60%|██████    | 34585/57600 [6:03:35<3:47:22,  1.69it/s]
 60%|██████    | 34586/57600 [6:03:36<3:50:43,  1.66it/s]
 60%|██████    | 34587/57600 [6:03:37<3:51:36,  1.66it/s]
 60%|██████    | 34588/57600 [6:03:37<3:50:08,  1.67it/s]
 60%|██████    | 34589/57600 [6:03:38<4:03:43,  1.57it/s]
 60%|██████    | 34590/57600 [6:03:39<4:02:20,  1.58it/s]
 60%|██████    | 34591/57600 [6:03:39<4:01:06,  1.59it/s]
 60%|██████    | 34592/57600 [6:03:40<4:04:05,  1.57it/s]
 60%|██████    | 34593/57600 [6:03:40<4:02:09,  1.58it/s]
 60%|██████    | 34594/57600 [6:03:41<3:59:16,  1.60it/s]
 60%|██████    | 34595/57600 [6:03:42<3:58:06,  1.61it/s]
 60%|██████    | 34596/57600 [6:03:42<4:04:21,  1.57it/s]
 60%|██████    | 34597/57600 [6:03:43<4:06:13,  1.56it/s]
 60%|██████    | 34598/57600 [6:03:44<4:03:00,  1.58it/s]
 60%|██████    | 34599/57600 [6:03:44<3:56:40,  1.62it/s]
 60%|██████    | 34600/57600 [6:03:45<3:54:42,  1.63it/s]
                                                         
{'loss': 1.1777, 'learning_rate': 4.6062717770034843e-07, 'epoch': 381.9}

 60%|██████    | 34600/57600 [6:03:45<3:54:42,  1.63it/s]
 60%|██████    | 34601/57600 [6:03:45<4:00:39,  1.59it/s]
 60%|██████    | 34602/57600 [6:03:46<3:58:59,  1.60it/s]
 60%|██████    | 34603/57600 [6:03:47<3:58:33,  1.61it/s]
 60%|██████    | 34604/57600 [6:03:47<3:55:48,  1.63it/s]
 60%|██████    | 34605/57600 [6:03:48<4:00:27,  1.59it/s]
 60%|██████    | 34606/57600 [6:03:49<4:06:22,  1.56it/s]
 60%|██████    | 34607/57600 [6:03:49<3:58:02,  1.61it/s]
 60%|██████    | 34608/57600 [6:03:50<4:04:41,  1.57it/s]
 60%|██████    | 34609/57600 [6:03:50<4:00:50,  1.59it/s]
 60%|██████    | 34610/57600 [6:03:51<4:09:51,  1.53it/s]
 60%|██████    | 34611/57600 [6:03:52<4:06:03,  1.56it/s]
 60%|██████    | 34612/57600 [6:03:52<4:00:23,  1.59it/s]
 60%|██████    | 34613/57600 [6:03:53<3:59:11,  1.60it/s]
 60%|██████    | 34614/57600 [6:03:54<3:56:32,  1.62it/s]
 60%|██████    | 34615/57600 [6:03:54<3:59:58,  1.60it/s]
 60%|██████    | 34616/57600 [6:03:55<4:01:43,  1.58it/s]
 60%|██████    | 34617/57600 [6:03:56<3:56:20,  1.62it/s]
 60%|██████    | 34618/57600 [6:03:56<3:53:21,  1.64it/s]
 60%|██████    | 34619/57600 [6:03:57<3:51:45,  1.65it/s]
 60%|██████    | 34620/57600 [6:03:57<4:02:41,  1.58it/s]
                                                         
{'loss': 1.167, 'learning_rate': 4.603135888501742e-07, 'epoch': 382.12}

 60%|██████    | 34620/57600 [6:03:57<4:02:41,  1.58it/s]
 60%|██████    | 34621/57600 [6:03:58<4:09:38,  1.53it/s]
 60%|██████    | 34622/57600 [6:03:59<4:17:03,  1.49it/s]
 60%|██████    | 34623/57600 [6:03:59<4:09:19,  1.54it/s]
 60%|██████    | 34624/57600 [6:04:00<4:03:29,  1.57it/s]
 60%|██████    | 34625/57600 [6:04:01<4:05:41,  1.56it/s]
 60%|██████    | 34626/57600 [6:04:01<4:01:54,  1.58it/s]
 60%|██████    | 34627/57600 [6:04:02<3:56:51,  1.62it/s]
 60%|██████    | 34628/57600 [6:04:02<3:51:13,  1.66it/s]
 60%|██████    | 34629/57600 [6:04:03<3:50:44,  1.66it/s]
 60%|██████    | 34630/57600 [6:04:04<3:50:28,  1.66it/s]
 60%|██████    | 34631/57600 [6:04:04<3:46:03,  1.69it/s]
 60%|██████    | 34632/57600 [6:04:05<3:49:36,  1.67it/s]
 60%|██████    | 34633/57600 [6:04:05<3:56:59,  1.62it/s]
 60%|██████    | 34634/57600 [6:04:06<3:54:43,  1.63it/s]
 60%|██████    | 34635/57600 [6:04:07<3:53:37,  1.64it/s]
 60%|██████    | 34636/57600 [6:04:07<4:03:09,  1.57it/s]
 60%|██████    | 34637/57600 [6:04:08<3:58:00,  1.61it/s]
 60%|██████    | 34638/57600 [6:04:09<3:51:36,  1.65it/s]
 60%|██████    | 34639/57600 [6:04:09<3:54:19,  1.63it/s]
 60%|██████    | 34640/57600 [6:04:10<3:50:25,  1.66it/s]
                                                         
{'loss': 1.1808, 'learning_rate': 4.6e-07, 'epoch': 382.34}

 60%|██████    | 34640/57600 [6:04:10<3:50:25,  1.66it/s]
 60%|██████    | 34641/57600 [6:04:10<3:45:50,  1.69it/s]
 60%|██████    | 34642/57600 [6:04:11<4:04:33,  1.56it/s]
 60%|██████    | 34643/57600 [6:04:12<3:57:48,  1.61it/s]
 60%|██████    | 34644/57600 [6:04:12<3:58:39,  1.60it/s]
 60%|██████    | 34645/57600 [6:04:13<3:52:24,  1.65it/s]
 60%|██████    | 34646/57600 [6:04:13<3:48:25,  1.67it/s]
 60%|██████    | 34647/57600 [6:04:14<4:00:19,  1.59it/s]
 60%|██████    | 34648/57600 [6:04:15<4:00:36,  1.59it/s]
 60%|██████    | 34649/57600 [6:04:15<3:55:14,  1.63it/s]
 60%|██████    | 34650/57600 [6:04:16<3:58:58,  1.60it/s]
 60%|██████    | 34651/57600 [6:04:17<4:02:06,  1.58it/s]
 60%|██████    | 34652/57600 [6:04:17<4:00:46,  1.59it/s]
 60%|██████    | 34653/57600 [6:04:18<3:58:38,  1.60it/s]
 60%|██████    | 34654/57600 [6:04:18<4:00:54,  1.59it/s]
 60%|██████    | 34655/57600 [6:04:19<4:03:38,  1.57it/s]
 60%|██████    | 34656/57600 [6:04:20<4:04:24,  1.56it/s]
 60%|██████    | 34657/57600 [6:04:20<4:06:20,  1.55it/s]
 60%|██████    | 34658/57600 [6:04:21<4:12:31,  1.51it/s]
 60%|██████    | 34659/57600 [6:04:22<4:06:29,  1.55it/s]
 60%|██████    | 34660/57600 [6:04:22<4:07:18,  1.55it/s]
                                                         
{'loss': 1.116, 'learning_rate': 4.5968641114982574e-07, 'epoch': 382.56}

 60%|██████    | 34660/57600 [6:04:22<4:07:18,  1.55it/s]
 60%|██████    | 34661/57600 [6:04:23<4:03:21,  1.57it/s]
 60%|██████    | 34662/57600 [6:04:24<4:04:26,  1.56it/s]
 60%|██████    | 34663/57600 [6:04:24<4:03:46,  1.57it/s]
 60%|██████    | 34664/57600 [6:04:25<4:11:30,  1.52it/s]
 60%|██████    | 34665/57600 [6:04:26<3:59:24,  1.60it/s]
 60%|██████    | 34666/57600 [6:04:26<4:03:26,  1.57it/s]
 60%|██████    | 34667/57600 [6:04:27<4:00:51,  1.59it/s]
 60%|██████    | 34668/57600 [6:04:28<4:12:47,  1.51it/s]
 60%|██████    | 34669/57600 [6:04:28<4:12:37,  1.51it/s]
 60%|██████    | 34670/57600 [6:04:29<4:10:15,  1.53it/s]
 60%|██████    | 34671/57600 [6:04:30<4:07:45,  1.54it/s]
 60%|██████    | 34672/57600 [6:04:30<3:59:21,  1.60it/s]
 60%|██████    | 34673/57600 [6:04:31<4:02:03,  1.58it/s]
 60%|██████    | 34674/57600 [6:04:31<3:58:25,  1.60it/s]
 60%|██████    | 34675/57600 [6:04:32<4:11:50,  1.52it/s]
 60%|██████    | 34676/57600 [6:04:33<4:09:03,  1.53it/s]
 60%|██████    | 34677/57600 [6:04:33<4:10:05,  1.53it/s]
 60%|██████    | 34678/57600 [6:04:34<4:05:57,  1.55it/s]
 60%|██████    | 34679/57600 [6:04:35<4:08:44,  1.54it/s]
 60%|██████    | 34680/57600 [6:04:35<4:03:34,  1.57it/s]
                                                         
{'loss': 1.1357, 'learning_rate': 4.593728222996515e-07, 'epoch': 382.78}

 60%|██████    | 34680/57600 [6:04:35<4:03:34,  1.57it/s]
 60%|██████    | 34681/57600 [6:04:36<4:04:46,  1.56it/s]
 60%|██████    | 34682/57600 [6:04:37<4:04:46,  1.56it/s]
 60%|██████    | 34683/57600 [6:04:37<4:01:24,  1.58it/s]
 60%|██████    | 34684/57600 [6:04:38<3:54:03,  1.63it/s]
 60%|██████    | 34685/57600 [6:04:38<4:00:29,  1.59it/s]
 60%|██████    | 34686/57600 [6:04:39<3:58:58,  1.60it/s]
 60%|██████    | 34687/57600 [6:04:40<4:01:13,  1.58it/s]
 60%|██████    | 34688/57600 [6:04:40<4:05:43,  1.55it/s]
 60%|██████    | 34689/57600 [6:04:41<4:00:10,  1.59it/s]
 60%|██████    | 34690/57600 [6:04:42<3:57:17,  1.61it/s]
 60%|██████    | 34691/57600 [6:04:42<4:03:52,  1.57it/s]
 60%|██████    | 34692/57600 [6:04:43<3:59:16,  1.60it/s]
 60%|██████    | 34693/57600 [6:04:43<3:53:07,  1.64it/s]
 60%|██████    | 34694/57600 [6:04:44<4:01:53,  1.58it/s]
 60%|██████    | 34695/57600 [6:04:45<3:56:04,  1.62it/s]
 60%|██████    | 34696/57600 [6:04:45<3:58:24,  1.60it/s]
 60%|██████    | 34697/57600 [6:04:46<4:01:32,  1.58it/s]
 60%|██████    | 34698/57600 [6:04:47<4:04:55,  1.56it/s]
 60%|██████    | 34699/57600 [6:04:47<4:13:52,  1.50it/s]
 60%|██████    | 34700/57600 [6:04:48<4:12:13,  1.51it/s]
                                                         
{'loss': 1.1878, 'learning_rate': 4.590592334494774e-07, 'epoch': 383.0}

 60%|██████    | 34700/57600 [6:04:48<4:12:13,  1.51it/s]
 60%|██████    | 34701/57600 [6:04:49<4:12:43,  1.51it/s]
 60%|██████    | 34702/57600 [6:04:49<4:01:16,  1.58it/s]
 60%|██████    | 34703/57600 [6:04:50<4:01:45,  1.58it/s]
 60%|██████    | 34704/57600 [6:04:50<3:55:52,  1.62it/s]
 60%|██████    | 34705/57600 [6:04:51<3:55:26,  1.62it/s]
 60%|██████    | 34706/57600 [6:04:52<4:05:25,  1.55it/s]
 60%|██████    | 34707/57600 [6:04:52<3:59:47,  1.59it/s]
 60%|██████    | 34708/57600 [6:04:53<4:00:48,  1.58it/s]
 60%|██████    | 34709/57600 [6:04:54<3:50:13,  1.66it/s]
 60%|██████    | 34710/57600 [6:04:54<3:53:34,  1.63it/s]
 60%|██████    | 34711/57600 [6:04:55<3:49:44,  1.66it/s]
 60%|██████    | 34712/57600 [6:04:55<3:47:45,  1.67it/s]
 60%|██████    | 34713/57600 [6:04:56<3:47:28,  1.68it/s]
 60%|██████    | 34714/57600 [6:04:57<3:59:00,  1.60it/s]
 60%|██████    | 34715/57600 [6:04:57<3:57:30,  1.61it/s]
 60%|██████    | 34716/57600 [6:04:58<4:00:12,  1.59it/s]
 60%|██████    | 34717/57600 [6:04:58<3:59:17,  1.59it/s]
 60%|██████    | 34718/57600 [6:04:59<4:00:34,  1.59it/s]
 60%|██████    | 34719/57600 [6:05:00<4:00:10,  1.59it/s]
 60%|██████    | 34720/57600 [6:05:00<4:01:55,  1.58it/s]
                                                         
{'loss': 1.1284, 'learning_rate': 4.587456445993031e-07, 'epoch': 383.22}

 60%|██████    | 34720/57600 [6:05:00<4:01:55,  1.58it/s]
 60%|██████    | 34721/57600 [6:05:01<4:13:18,  1.51it/s]
 60%|██████    | 34722/57600 [6:05:02<4:03:08,  1.57it/s]
 60%|██████    | 34723/57600 [6:05:02<4:00:45,  1.58it/s]
 60%|██████    | 34724/57600 [6:05:03<4:01:57,  1.58it/s]
 60%|██████    | 34725/57600 [6:05:04<4:02:16,  1.57it/s]
 60%|██████    | 34726/57600 [6:05:04<3:56:42,  1.61it/s]
 60%|██████    | 34727/57600 [6:05:05<3:56:05,  1.61it/s]
 60%|██████    | 34728/57600 [6:05:05<3:55:21,  1.62it/s]
 60%|██████    | 34729/57600 [6:05:06<4:05:51,  1.55it/s]
 60%|██████    | 34730/57600 [6:05:07<4:00:43,  1.58it/s]
 60%|██████    | 34731/57600 [6:05:07<4:02:00,  1.57it/s]
 60%|██████    | 34732/57600 [6:05:08<4:06:04,  1.55it/s]
 60%|██████    | 34733/57600 [6:05:09<4:06:10,  1.55it/s]
 60%|██████    | 34734/57600 [6:05:09<4:00:04,  1.59it/s]
 60%|██████    | 34735/57600 [6:05:10<4:00:52,  1.58it/s]
 60%|██████    | 34736/57600 [6:05:10<3:55:09,  1.62it/s]
 60%|██████    | 34737/57600 [6:05:11<3:47:59,  1.67it/s]
 60%|██████    | 34738/57600 [6:05:12<3:54:31,  1.62it/s]
 60%|██████    | 34739/57600 [6:05:12<3:57:39,  1.60it/s]
 60%|██████    | 34740/57600 [6:05:13<4:01:24,  1.58it/s]
                                                         
{'loss': 1.1819, 'learning_rate': 4.584320557491289e-07, 'epoch': 383.44}

 60%|██████    | 34740/57600 [6:05:13<4:01:24,  1.58it/s]
 60%|██████    | 34741/57600 [6:05:14<3:59:32,  1.59it/s]
 60%|██████    | 34742/57600 [6:05:14<4:01:16,  1.58it/s]
 60%|██████    | 34743/57600 [6:05:15<3:58:34,  1.60it/s]
 60%|██████    | 34744/57600 [6:05:16<4:03:11,  1.57it/s]
 60%|██████    | 34745/57600 [6:05:16<4:05:46,  1.55it/s]
 60%|██████    | 34746/57600 [6:05:17<4:12:02,  1.51it/s]
 60%|██████    | 34747/57600 [6:05:18<4:07:23,  1.54it/s]
 60%|██████    | 34748/57600 [6:05:18<4:00:54,  1.58it/s]
 60%|██████    | 34749/57600 [6:05:19<4:01:54,  1.57it/s]
 60%|██████    | 34750/57600 [6:05:19<3:59:19,  1.59it/s]
 60%|██████    | 34751/57600 [6:05:20<3:55:25,  1.62it/s]
 60%|██████    | 34752/57600 [6:05:21<3:58:32,  1.60it/s]
 60%|██████    | 34753/57600 [6:05:21<3:58:20,  1.60it/s]
 60%|██████    | 34754/57600 [6:05:22<3:56:10,  1.61it/s]
 60%|██████    | 34755/57600 [6:05:22<3:55:03,  1.62it/s]
 60%|██████    | 34756/57600 [6:05:23<3:53:29,  1.63it/s]
 60%|██████    | 34757/57600 [6:05:24<4:14:07,  1.50it/s]
 60%|██████    | 34758/57600 [6:05:24<4:09:58,  1.52it/s]
 60%|██████    | 34759/57600 [6:05:25<4:07:48,  1.54it/s]
 60%|██████    | 34760/57600 [6:05:26<4:12:22,  1.51it/s]
                                                         
{'loss': 1.1144, 'learning_rate': 4.5811846689895466e-07, 'epoch': 383.66}

 60%|██████    | 34760/57600 [6:05:26<4:12:22,  1.51it/s]
 60%|██████    | 34761/57600 [6:05:26<4:10:51,  1.52it/s]
 60%|██████    | 34762/57600 [6:05:27<4:06:21,  1.55it/s]
 60%|██████    | 34763/57600 [6:05:28<4:07:32,  1.54it/s]
 60%|██████    | 34764/57600 [6:05:28<3:58:48,  1.59it/s]
 60%|██████    | 34765/57600 [6:05:29<3:57:23,  1.60it/s]
 60%|██████    | 34766/57600 [6:05:30<4:09:15,  1.53it/s]
 60%|██████    | 34767/57600 [6:05:30<4:06:05,  1.55it/s]
 60%|██████    | 34768/57600 [6:05:31<3:58:46,  1.59it/s]
 60%|██████    | 34769/57600 [6:05:31<3:58:08,  1.60it/s]
 60%|██████    | 34770/57600 [6:05:32<3:51:28,  1.64it/s]
 60%|██████    | 34771/57600 [6:05:33<3:49:07,  1.66it/s]
 60%|██████    | 34772/57600 [6:05:33<3:47:35,  1.67it/s]
 60%|██████    | 34773/57600 [6:05:34<3:49:59,  1.65it/s]
 60%|██████    | 34774/57600 [6:05:34<3:53:55,  1.63it/s]
 60%|██████    | 34775/57600 [6:05:35<3:59:11,  1.59it/s]
 60%|██████    | 34776/57600 [6:05:36<3:56:40,  1.61it/s]
 60%|██████    | 34777/57600 [6:05:36<3:54:25,  1.62it/s]
 60%|██████    | 34778/57600 [6:05:37<3:52:49,  1.63it/s]
 60%|██████    | 34779/57600 [6:05:38<4:00:58,  1.58it/s]
 60%|██████    | 34780/57600 [6:05:38<3:57:52,  1.60it/s]
                                                         
{'loss': 1.1786, 'learning_rate': 4.5780487804878047e-07, 'epoch': 383.89}

 60%|██████    | 34780/57600 [6:05:38<3:57:52,  1.60it/s]
 60%|██████    | 34781/57600 [6:05:39<4:02:58,  1.57it/s]
 60%|██████    | 34782/57600 [6:05:40<4:04:54,  1.55it/s]
 60%|██████    | 34783/57600 [6:05:40<4:01:56,  1.57it/s]
 60%|██████    | 34784/57600 [6:05:41<3:56:31,  1.61it/s]
 60%|██████    | 34785/57600 [6:05:41<3:53:01,  1.63it/s]
 60%|██████    | 34786/57600 [6:05:42<3:55:26,  1.61it/s]
 60%|██████    | 34787/57600 [6:05:43<3:57:19,  1.60it/s]
 60%|██████    | 34788/57600 [6:05:43<3:54:22,  1.62it/s]
 60%|██████    | 34789/57600 [6:05:44<3:54:39,  1.62it/s]
 60%|██████    | 34790/57600 [6:05:45<4:13:51,  1.50it/s]
 60%|██████    | 34791/57600 [6:05:45<4:16:08,  1.48it/s]
 60%|██████    | 34792/57600 [6:05:46<4:11:36,  1.51it/s]
 60%|██████    | 34793/57600 [6:05:47<4:09:03,  1.53it/s]
 60%|██████    | 34794/57600 [6:05:47<4:05:30,  1.55it/s]
 60%|██████    | 34795/57600 [6:05:48<3:57:47,  1.60it/s]
 60%|██████    | 34796/57600 [6:05:48<3:58:29,  1.59it/s]
 60%|██████    | 34797/57600 [6:05:49<3:57:44,  1.60it/s]
 60%|██████    | 34798/57600 [6:05:50<3:53:22,  1.63it/s]
 60%|██████    | 34799/57600 [6:05:50<3:58:30,  1.59it/s]
 60%|██████    | 34800/57600 [6:05:51<3:57:17,  1.60it/s]
                                                         
{'loss': 1.1793, 'learning_rate': 4.5749128919860616e-07, 'epoch': 384.11}

 60%|██████    | 34800/57600 [6:05:51<3:57:17,  1.60it/s]
 60%|██████    | 34801/57600 [6:05:52<3:53:43,  1.63it/s]
 60%|██████    | 34802/57600 [6:05:52<3:54:07,  1.62it/s]
 60%|██████    | 34803/57600 [6:05:53<3:53:34,  1.63it/s]
 60%|██████    | 34804/57600 [6:05:53<3:51:24,  1.64it/s]
 60%|██████    | 34805/57600 [6:05:54<3:52:40,  1.63it/s]
 60%|██████    | 34806/57600 [6:05:55<3:58:21,  1.59it/s]
 60%|██████    | 34807/57600 [6:05:55<3:52:40,  1.63it/s]
 60%|██████    | 34808/57600 [6:05:56<3:52:57,  1.63it/s]
 60%|██████    | 34809/57600 [6:05:56<3:48:43,  1.66it/s]
 60%|██████    | 34810/57600 [6:05:57<3:57:28,  1.60it/s]
 60%|██████    | 34811/57600 [6:05:58<4:00:53,  1.58it/s]
 60%|██████    | 34812/57600 [6:05:58<4:08:13,  1.53it/s]
 60%|██████    | 34813/57600 [6:05:59<4:00:31,  1.58it/s]
 60%|██████    | 34814/57600 [6:06:00<3:57:03,  1.60it/s]
 60%|██████    | 34815/57600 [6:06:00<3:51:54,  1.64it/s]
 60%|██████    | 34816/57600 [6:06:01<3:55:29,  1.61it/s]
 60%|██████    | 34817/57600 [6:06:01<3:53:54,  1.62it/s]
 60%|██████    | 34818/57600 [6:06:02<3:51:04,  1.64it/s]
 60%|██████    | 34819/57600 [6:06:03<3:59:38,  1.58it/s]
 60%|██████    | 34820/57600 [6:06:03<3:56:48,  1.60it/s]
                                                         
{'loss': 1.1671, 'learning_rate': 4.57177700348432e-07, 'epoch': 384.33}

 60%|██████    | 34820/57600 [6:06:03<3:56:48,  1.60it/s]
 60%|██████    | 34821/57600 [6:06:04<3:56:08,  1.61it/s]
 60%|██████    | 34822/57600 [6:06:05<3:58:46,  1.59it/s]
 60%|██████    | 34823/57600 [6:06:05<3:56:09,  1.61it/s]
 60%|██████    | 34824/57600 [6:06:06<3:58:41,  1.59it/s]
 60%|██████    | 34825/57600 [6:06:07<4:01:40,  1.57it/s]
 60%|██████    | 34826/57600 [6:06:07<4:05:45,  1.54it/s]
 60%|██████    | 34827/57600 [6:06:08<4:01:06,  1.57it/s]
 60%|██████    | 34828/57600 [6:06:08<3:55:53,  1.61it/s]
 60%|██████    | 34829/57600 [6:06:09<3:54:36,  1.62it/s]
 60%|██████    | 34830/57600 [6:06:10<3:52:27,  1.63it/s]
 60%|██████    | 34831/57600 [6:06:10<3:46:57,  1.67it/s]
 60%|██████    | 34832/57600 [6:06:11<3:43:26,  1.70it/s]
 60%|██████    | 34833/57600 [6:06:11<3:51:10,  1.64it/s]
 60%|██████    | 34834/57600 [6:06:12<3:52:37,  1.63it/s]
 60%|██████    | 34835/57600 [6:06:13<3:50:29,  1.65it/s]
 60%|██████    | 34836/57600 [6:06:13<3:50:27,  1.65it/s]
 60%|██████    | 34837/57600 [6:06:14<3:53:24,  1.63it/s]
 60%|██████    | 34838/57600 [6:06:14<3:57:01,  1.60it/s]
 60%|██████    | 34839/57600 [6:06:15<4:04:33,  1.55it/s]
 60%|██████    | 34840/57600 [6:06:16<4:02:12,  1.57it/s]
                                                         
{'loss': 1.1962, 'learning_rate': 4.568641114982579e-07, 'epoch': 384.55}

 60%|██████    | 34840/57600 [6:06:16<4:02:12,  1.57it/s]
 60%|██████    | 34841/57600 [6:06:16<3:58:49,  1.59it/s]
 60%|██████    | 34842/57600 [6:06:17<4:11:01,  1.51it/s]
 60%|██████    | 34843/57600 [6:06:18<4:07:40,  1.53it/s]
 60%|██████    | 34844/57600 [6:06:18<4:03:48,  1.56it/s]
 60%|██████    | 34845/57600 [6:06:19<4:00:06,  1.58it/s]
 60%|██████    | 34846/57600 [6:06:20<3:59:44,  1.58it/s]
 60%|██████    | 34847/57600 [6:06:20<4:00:45,  1.58it/s]
 60%|██████    | 34848/57600 [6:06:21<3:59:02,  1.59it/s]
 61%|██████    | 34849/57600 [6:06:21<3:55:07,  1.61it/s]
 61%|██████    | 34850/57600 [6:06:22<3:54:13,  1.62it/s]
 61%|██████    | 34851/57600 [6:06:23<3:53:15,  1.63it/s]
 61%|██████    | 34852/57600 [6:06:23<3:52:25,  1.63it/s]
 61%|██████    | 34853/57600 [6:06:24<3:56:46,  1.60it/s]
 61%|██████    | 34854/57600 [6:06:25<3:58:23,  1.59it/s]
 61%|██████    | 34855/57600 [6:06:25<3:54:02,  1.62it/s]
 61%|██████    | 34856/57600 [6:06:26<4:01:09,  1.57it/s]
 61%|██████    | 34857/57600 [6:06:26<3:56:16,  1.60it/s]
 61%|██████    | 34858/57600 [6:06:27<3:54:26,  1.62it/s]
 61%|██████    | 34859/57600 [6:06:28<3:56:35,  1.60it/s]
 61%|██████    | 34860/57600 [6:06:28<4:05:24,  1.54it/s]
                                                         
{'loss': 1.1392, 'learning_rate': 4.565505226480836e-07, 'epoch': 384.77}

 61%|██████    | 34860/57600 [6:06:28<4:05:24,  1.54it/s]
 61%|██████    | 34861/57600 [6:06:29<4:02:15,  1.56it/s]
 61%|██████    | 34862/57600 [6:06:30<3:55:21,  1.61it/s]
 61%|██████    | 34863/57600 [6:06:30<3:58:13,  1.59it/s]
 61%|██████    | 34864/57600 [6:06:31<4:05:22,  1.54it/s]
 61%|██████    | 34865/57600 [6:06:32<3:58:19,  1.59it/s]
 61%|██████    | 34866/57600 [6:06:32<4:02:45,  1.56it/s]
 61%|██████    | 34867/57600 [6:06:33<3:58:53,  1.59it/s]
 61%|██████    | 34868/57600 [6:06:33<4:00:32,  1.58it/s]
 61%|██████    | 34869/57600 [6:06:34<3:55:15,  1.61it/s]
 61%|██████    | 34870/57600 [6:06:35<3:56:19,  1.60it/s]
 61%|██████    | 34871/57600 [6:06:35<4:03:25,  1.56it/s]
 61%|██████    | 34872/57600 [6:06:36<4:05:39,  1.54it/s]
 61%|██████    | 34873/57600 [6:06:37<4:09:53,  1.52it/s]
 61%|██████    | 34874/57600 [6:06:37<4:12:56,  1.50it/s]
 61%|██████    | 34875/57600 [6:06:38<4:07:22,  1.53it/s]
 61%|██████    | 34876/57600 [6:06:39<4:11:28,  1.51it/s]
 61%|██████    | 34877/57600 [6:06:39<4:07:31,  1.53it/s]
 61%|██████    | 34878/57600 [6:06:40<3:59:27,  1.58it/s]
 61%|██████    | 34879/57600 [6:06:41<4:09:36,  1.52it/s]
 61%|██████    | 34880/57600 [6:06:41<4:01:51,  1.57it/s]
                                                         
{'loss': 1.1296, 'learning_rate': 4.5623693379790944e-07, 'epoch': 384.99}

 61%|██████    | 34880/57600 [6:06:41<4:01:51,  1.57it/s]
 61%|██████    | 34881/57600 [6:06:42<4:07:25,  1.53it/s]
 61%|██████    | 34882/57600 [6:06:43<4:11:20,  1.51it/s]
 61%|██████    | 34883/57600 [6:06:43<4:10:04,  1.51it/s]
 61%|██████    | 34884/57600 [6:06:44<4:02:53,  1.56it/s]
 61%|██████    | 34885/57600 [6:06:45<4:03:26,  1.56it/s]
 61%|██████    | 34886/57600 [6:06:45<4:00:43,  1.57it/s]
 61%|██████    | 34887/57600 [6:06:46<4:15:07,  1.48it/s]
 61%|██████    | 34888/57600 [6:06:47<4:27:47,  1.41it/s]
 61%|██████    | 34889/57600 [6:06:47<4:29:54,  1.40it/s]
 61%|██████    | 34890/57600 [6:06:48<4:19:56,  1.46it/s]
 61%|██████    | 34891/57600 [6:06:49<4:19:13,  1.46it/s]
 61%|██████    | 34892/57600 [6:06:49<4:12:56,  1.50it/s]
 61%|██████    | 34893/57600 [6:06:50<4:08:11,  1.52it/s]
 61%|██████    | 34894/57600 [6:06:51<4:09:22,  1.52it/s]
 61%|██████    | 34895/57600 [6:06:51<4:03:44,  1.55it/s]
 61%|██████    | 34896/57600 [6:06:52<4:01:54,  1.56it/s]
 61%|██████    | 34897/57600 [6:06:52<3:59:27,  1.58it/s]
 61%|██████    | 34898/57600 [6:06:53<4:01:05,  1.57it/s]
 61%|██████    | 34899/57600 [6:06:54<4:02:03,  1.56it/s]
 61%|██████    | 34900/57600 [6:06:54<3:59:48,  1.58it/s]
                                                         
{'loss': 1.1262, 'learning_rate': 4.5592334494773514e-07, 'epoch': 385.21}

 61%|██████    | 34900/57600 [6:06:54<3:59:48,  1.58it/s]
 61%|██████    | 34901/57600 [6:06:55<4:00:38,  1.57it/s]
 61%|██████    | 34902/57600 [6:06:56<3:57:42,  1.59it/s]
 61%|██████    | 34903/57600 [6:06:56<3:52:17,  1.63it/s]
 61%|██████    | 34904/57600 [6:06:57<3:49:40,  1.65it/s]
 61%|██████    | 34905/57600 [6:06:57<3:46:54,  1.67it/s]
 61%|██████    | 34906/57600 [6:06:58<3:56:28,  1.60it/s]
 61%|██████    | 34907/57600 [6:06:59<3:57:42,  1.59it/s]
 61%|██████    | 34908/57600 [6:06:59<3:59:40,  1.58it/s]
 61%|██████    | 34909/57600 [6:07:00<4:00:05,  1.58it/s]
 61%|██████    | 34910/57600 [6:07:01<3:52:16,  1.63it/s]
 61%|██████    | 34911/57600 [6:07:01<3:47:38,  1.66it/s]
 61%|██████    | 34912/57600 [6:07:02<3:56:48,  1.60it/s]
 61%|██████    | 34913/57600 [6:07:03<4:08:11,  1.52it/s]
 61%|██████    | 34914/57600 [6:07:03<4:08:39,  1.52it/s]
 61%|██████    | 34915/57600 [6:07:04<3:58:22,  1.59it/s]
 61%|██████    | 34916/57600 [6:07:04<3:58:08,  1.59it/s]
 61%|██████    | 34917/57600 [6:07:05<3:58:34,  1.58it/s]
 61%|██████    | 34918/57600 [6:07:06<3:51:07,  1.64it/s]
 61%|██████    | 34919/57600 [6:07:06<3:55:07,  1.61it/s]
 61%|██████    | 34920/57600 [6:07:07<3:50:18,  1.64it/s]
                                                         
{'loss': 1.1584, 'learning_rate': 4.55609756097561e-07, 'epoch': 385.43}

 61%|██████    | 34920/57600 [6:07:07<3:50:18,  1.64it/s]
 61%|██████    | 34921/57600 [6:07:08<4:04:05,  1.55it/s]
 61%|██████    | 34922/57600 [6:07:08<4:00:06,  1.57it/s]
 61%|██████    | 34923/57600 [6:07:09<3:59:09,  1.58it/s]
 61%|██████    | 34924/57600 [6:07:09<4:01:46,  1.56it/s]
 61%|██████    | 34925/57600 [6:07:10<4:08:25,  1.52it/s]
 61%|██████    | 34926/57600 [6:07:11<3:59:01,  1.58it/s]
 61%|██████    | 34927/57600 [6:07:11<3:53:55,  1.62it/s]
 61%|██████    | 34928/57600 [6:07:12<3:56:45,  1.60it/s]
 61%|██████    | 34929/57600 [6:07:13<4:06:32,  1.53it/s]
 61%|██████    | 34930/57600 [6:07:13<3:57:20,  1.59it/s]
 61%|██████    | 34931/57600 [6:07:14<3:51:01,  1.64it/s]
 61%|██████    | 34932/57600 [6:07:14<3:46:33,  1.67it/s]
 61%|██████    | 34933/57600 [6:07:15<3:48:24,  1.65it/s]
 61%|██████    | 34934/57600 [6:07:16<3:54:36,  1.61it/s]
 61%|██████    | 34935/57600 [6:07:16<3:52:10,  1.63it/s]
 61%|██████    | 34936/57600 [6:07:17<3:57:29,  1.59it/s]
 61%|██████    | 34937/57600 [6:07:18<4:00:55,  1.57it/s]
 61%|██████    | 34938/57600 [6:07:18<3:55:55,  1.60it/s]
 61%|██████    | 34939/57600 [6:07:19<3:56:08,  1.60it/s]
 61%|██████    | 34940/57600 [6:07:19<3:51:55,  1.63it/s]
                                                         
{'loss': 1.1438, 'learning_rate': 4.552961672473867e-07, 'epoch': 385.65}

 61%|██████    | 34940/57600 [6:07:19<3:51:55,  1.63it/s]
 61%|██████    | 34941/57600 [6:07:20<3:53:30,  1.62it/s]
 61%|██████    | 34942/57600 [6:07:21<3:52:49,  1.62it/s]
 61%|██████    | 34943/57600 [6:07:21<3:59:28,  1.58it/s]
 61%|██████    | 34944/57600 [6:07:22<4:04:06,  1.55it/s]
 61%|██████    | 34945/57600 [6:07:23<4:00:21,  1.57it/s]
 61%|██████    | 34946/57600 [6:07:23<4:02:48,  1.56it/s]
 61%|██████    | 34947/57600 [6:07:24<3:58:06,  1.59it/s]
 61%|██████    | 34948/57600 [6:07:24<3:51:58,  1.63it/s]
 61%|██████    | 34949/57600 [6:07:25<3:50:06,  1.64it/s]
 61%|██████    | 34950/57600 [6:07:26<3:53:48,  1.61it/s]
 61%|██████    | 34951/57600 [6:07:26<3:57:03,  1.59it/s]
 61%|██████    | 34952/57600 [6:07:27<4:00:02,  1.57it/s]
 61%|██████    | 34953/57600 [6:07:28<3:55:37,  1.60it/s]
 61%|██████    | 34954/57600 [6:07:28<3:55:26,  1.60it/s]
 61%|██████    | 34955/57600 [6:07:29<3:50:01,  1.64it/s]
 61%|██████    | 34956/57600 [6:07:29<3:55:47,  1.60it/s]
 61%|██████    | 34957/57600 [6:07:30<3:58:41,  1.58it/s]
 61%|██████    | 34958/57600 [6:07:31<3:55:24,  1.60it/s]
 61%|██████    | 34959/57600 [6:07:31<4:02:38,  1.56it/s]
 61%|██████    | 34960/57600 [6:07:32<4:06:45,  1.53it/s]
                                                         
{'loss': 1.1533, 'learning_rate': 4.5498257839721255e-07, 'epoch': 385.87}

 61%|██████    | 34960/57600 [6:07:32<4:06:45,  1.53it/s]
 61%|██████    | 34961/57600 [6:07:33<3:56:25,  1.60it/s]
 61%|██████    | 34962/57600 [6:07:33<3:51:39,  1.63it/s]
 61%|██████    | 34963/57600 [6:07:34<3:50:12,  1.64it/s]
 61%|██████    | 34964/57600 [6:07:34<3:43:46,  1.69it/s]
 61%|██████    | 34965/57600 [6:07:35<3:44:37,  1.68it/s]
 61%|██████    | 34966/57600 [6:07:36<3:48:08,  1.65it/s]
 61%|██████    | 34967/57600 [6:07:36<3:58:27,  1.58it/s]
 61%|██████    | 34968/57600 [6:07:37<4:07:30,  1.52it/s]
 61%|██████    | 34969/57600 [6:07:38<4:04:03,  1.55it/s]
 61%|██████    | 34970/57600 [6:07:38<4:04:31,  1.54it/s]
 61%|██████    | 34971/57600 [6:07:39<4:05:00,  1.54it/s]
 61%|██████    | 34972/57600 [6:07:40<4:11:13,  1.50it/s]
 61%|██████    | 34973/57600 [6:07:40<4:09:25,  1.51it/s]
 61%|██████    | 34974/57600 [6:07:41<4:09:07,  1.51it/s]
 61%|██████    | 34975/57600 [6:07:42<3:59:03,  1.58it/s]
 61%|██████    | 34976/57600 [6:07:42<4:01:16,  1.56it/s]
 61%|██████    | 34977/57600 [6:07:43<3:55:46,  1.60it/s]
 61%|██████    | 34978/57600 [6:07:43<3:55:09,  1.60it/s]
 61%|██████    | 34979/57600 [6:07:44<4:00:03,  1.57it/s]
 61%|██████    | 34980/57600 [6:07:45<3:58:35,  1.58it/s]
                                                         
{'loss': 1.1437, 'learning_rate': 4.5466898954703835e-07, 'epoch': 386.09}

 61%|██████    | 34980/57600 [6:07:45<3:58:35,  1.58it/s]
 61%|██████    | 34981/57600 [6:07:45<4:04:44,  1.54it/s]
 61%|██████    | 34982/57600 [6:07:46<4:00:59,  1.56it/s]
 61%|██████    | 34983/57600 [6:07:47<4:00:39,  1.57it/s]
 61%|██████    | 34984/57600 [6:07:47<4:00:41,  1.57it/s]
 61%|██████    | 34985/57600 [6:07:48<3:56:24,  1.59it/s]
 61%|██████    | 34986/57600 [6:07:48<3:58:32,  1.58it/s]
 61%|██████    | 34987/57600 [6:07:49<3:56:47,  1.59it/s]
 61%|██████    | 34988/57600 [6:07:50<3:58:43,  1.58it/s]
 61%|██████    | 34989/57600 [6:07:50<3:59:05,  1.58it/s]
 61%|██████    | 34990/57600 [6:07:51<4:03:38,  1.55it/s]
 61%|██████    | 34991/57600 [6:07:52<4:03:05,  1.55it/s]
 61%|██████    | 34992/57600 [6:07:52<4:00:24,  1.57it/s]
 61%|██████    | 34993/57600 [6:07:53<4:03:19,  1.55it/s]
 61%|██████    | 34994/57600 [6:07:54<4:05:20,  1.54it/s]
 61%|██████    | 34995/57600 [6:07:54<3:54:37,  1.61it/s]
 61%|██████    | 34996/57600 [6:07:55<3:50:20,  1.64it/s]
 61%|██████    | 34997/57600 [6:07:55<3:54:01,  1.61it/s]
 61%|██████    | 34998/57600 [6:07:56<3:53:15,  1.61it/s]
 61%|██████    | 34999/57600 [6:07:57<3:54:58,  1.60it/s]
 61%|██████    | 35000/57600 [6:07:57<3:53:53,  1.61it/s]
                                                         
{'loss': 1.1541, 'learning_rate': 4.5435540069686405e-07, 'epoch': 386.31}

 61%|██████    | 35000/57600 [6:07:57<3:53:53,  1.61it/s]
 61%|██████    | 35001/57600 [6:07:58<3:52:42,  1.62it/s]
 61%|██████    | 35002/57600 [6:07:59<3:54:31,  1.61it/s]
 61%|██████    | 35003/57600 [6:07:59<3:48:09,  1.65it/s]
 61%|██████    | 35004/57600 [6:08:00<3:44:17,  1.68it/s]
 61%|██████    | 35005/57600 [6:08:00<3:42:51,  1.69it/s]
 61%|██████    | 35006/57600 [6:08:01<3:41:16,  1.70it/s]
 61%|██████    | 35007/57600 [6:08:01<3:41:03,  1.70it/s]
 61%|██████    | 35008/57600 [6:08:02<3:50:28,  1.63it/s]
 61%|██████    | 35009/57600 [6:08:03<3:45:41,  1.67it/s]
 61%|██████    | 35010/57600 [6:08:03<3:44:55,  1.67it/s]
 61%|██████    | 35011/57600 [6:08:04<3:49:56,  1.64it/s]
 61%|██████    | 35012/57600 [6:08:04<3:44:24,  1.68it/s]
 61%|██████    | 35013/57600 [6:08:05<3:47:07,  1.66it/s]
 61%|██████    | 35014/57600 [6:08:06<3:46:08,  1.66it/s]
 61%|██████    | 35015/57600 [6:08:06<3:52:22,  1.62it/s]
 61%|██████    | 35016/57600 [6:08:07<3:59:23,  1.57it/s]
 61%|██████    | 35017/57600 [6:08:08<4:01:14,  1.56it/s]
 61%|██████    | 35018/57600 [6:08:08<3:51:55,  1.62it/s]
 61%|██████    | 35019/57600 [6:08:09<4:02:46,  1.55it/s]
 61%|██████    | 35020/57600 [6:08:10<4:04:18,  1.54it/s]
                                                         
{'loss': 1.1999, 'learning_rate': 4.540418118466899e-07, 'epoch': 386.53}

 61%|██████    | 35020/57600 [6:08:10<4:04:18,  1.54it/s]
 61%|██████    | 35021/57600 [6:08:10<3:56:19,  1.59it/s]
 61%|██████    | 35022/57600 [6:08:11<3:58:40,  1.58it/s]
 61%|██████    | 35023/57600 [6:08:11<3:51:48,  1.62it/s]
 61%|██████    | 35024/57600 [6:08:12<3:46:44,  1.66it/s]
 61%|██████    | 35025/57600 [6:08:13<3:49:59,  1.64it/s]
 61%|██████    | 35026/57600 [6:08:13<3:53:13,  1.61it/s]
 61%|██████    | 35027/57600 [6:08:14<3:58:25,  1.58it/s]
 61%|██████    | 35028/57600 [6:08:15<3:55:45,  1.60it/s]
 61%|██████    | 35029/57600 [6:08:15<3:47:56,  1.65it/s]
 61%|██████    | 35030/57600 [6:08:16<3:45:40,  1.67it/s]
 61%|██████    | 35031/57600 [6:08:16<3:58:09,  1.58it/s]
 61%|██████    | 35032/57600 [6:08:17<4:00:25,  1.56it/s]
 61%|██████    | 35033/57600 [6:08:18<3:58:03,  1.58it/s]
 61%|██████    | 35034/57600 [6:08:18<3:51:38,  1.62it/s]
 61%|██████    | 35035/57600 [6:08:19<3:54:21,  1.60it/s]
 61%|██████    | 35036/57600 [6:08:20<3:57:25,  1.58it/s]
 61%|██████    | 35037/57600 [6:08:20<3:59:25,  1.57it/s]
 61%|██████    | 35038/57600 [6:08:21<3:59:37,  1.57it/s]
 61%|██████    | 35039/57600 [6:08:21<3:57:10,  1.59it/s]
 61%|██████    | 35040/57600 [6:08:22<3:56:26,  1.59it/s]
                                                         
{'loss': 1.1495, 'learning_rate': 4.537282229965156e-07, 'epoch': 386.75}

 61%|██████    | 35040/57600 [6:08:22<3:56:26,  1.59it/s]
 61%|██████    | 35041/57600 [6:08:23<4:08:37,  1.51it/s]
 61%|██████    | 35042/57600 [6:08:23<3:59:15,  1.57it/s]
 61%|██████    | 35043/57600 [6:08:24<3:53:41,  1.61it/s]
 61%|██████    | 35044/57600 [6:08:25<3:57:20,  1.58it/s]
 61%|██████    | 35045/57600 [6:08:25<3:52:00,  1.62it/s]
 61%|██████    | 35046/57600 [6:08:26<3:50:09,  1.63it/s]
 61%|██████    | 35047/57600 [6:08:26<3:54:44,  1.60it/s]
 61%|██████    | 35048/57600 [6:08:27<3:58:18,  1.58it/s]
 61%|██████    | 35049/57600 [6:08:28<3:55:40,  1.59it/s]
 61%|██████    | 35050/57600 [6:08:28<3:56:43,  1.59it/s]
 61%|██████    | 35051/57600 [6:08:29<4:00:53,  1.56it/s]
 61%|██████    | 35052/57600 [6:08:30<3:56:27,  1.59it/s]
 61%|██████    | 35053/57600 [6:08:30<3:54:03,  1.61it/s]
 61%|██████    | 35054/57600 [6:08:31<3:57:39,  1.58it/s]
 61%|██████    | 35055/57600 [6:08:32<3:57:53,  1.58it/s]
 61%|██████    | 35056/57600 [6:08:32<3:53:43,  1.61it/s]
 61%|██████    | 35057/57600 [6:08:33<3:59:37,  1.57it/s]
 61%|██████    | 35058/57600 [6:08:33<3:54:47,  1.60it/s]
 61%|██████    | 35059/57600 [6:08:34<4:06:37,  1.52it/s]
 61%|██████    | 35060/57600 [6:08:35<3:58:39,  1.57it/s]
                                                         
{'loss': 1.1571, 'learning_rate': 4.5341463414634147e-07, 'epoch': 386.98}

 61%|██████    | 35060/57600 [6:08:35<3:58:39,  1.57it/s]
 61%|██████    | 35061/57600 [6:08:35<4:12:30,  1.49it/s]
 61%|██████    | 35062/57600 [6:08:36<4:03:23,  1.54it/s]
 61%|██████    | 35063/57600 [6:08:37<4:14:46,  1.47it/s]
 61%|██████    | 35064/57600 [6:08:37<4:08:55,  1.51it/s]
 61%|██████    | 35065/57600 [6:08:38<4:03:49,  1.54it/s]
 61%|██████    | 35066/57600 [6:08:39<3:54:39,  1.60it/s]
 61%|██████    | 35067/57600 [6:08:39<3:51:25,  1.62it/s]
 61%|██████    | 35068/57600 [6:08:40<3:47:59,  1.65it/s]
 61%|██████    | 35069/57600 [6:08:40<3:47:48,  1.65it/s]
 61%|██████    | 35070/57600 [6:08:41<3:48:14,  1.65it/s]
 61%|██████    | 35071/57600 [6:08:42<3:46:13,  1.66it/s]
 61%|██████    | 35072/57600 [6:08:42<3:44:51,  1.67it/s]
 61%|██████    | 35073/57600 [6:08:43<3:44:56,  1.67it/s]
 61%|██████    | 35074/57600 [6:08:43<3:40:50,  1.70it/s]
 61%|██████    | 35075/57600 [6:08:44<3:47:14,  1.65it/s]
 61%|██████    | 35076/57600 [6:08:45<3:51:36,  1.62it/s]
 61%|██████    | 35077/57600 [6:08:45<4:02:08,  1.55it/s]
 61%|██████    | 35078/57600 [6:08:46<3:55:26,  1.59it/s]
 61%|██████    | 35079/57600 [6:08:47<3:57:24,  1.58it/s]
 61%|██████    | 35080/57600 [6:08:47<3:50:15,  1.63it/s]
                                                         
{'loss': 1.178, 'learning_rate': 4.5310104529616717e-07, 'epoch': 387.2}

 61%|██████    | 35080/57600 [6:08:47<3:50:15,  1.63it/s]
 61%|██████    | 35081/57600 [6:08:48<3:52:25,  1.61it/s]
 61%|██████    | 35082/57600 [6:08:48<3:44:52,  1.67it/s]
 61%|██████    | 35083/57600 [6:08:49<3:55:00,  1.60it/s]
 61%|██████    | 35084/57600 [6:08:50<3:56:02,  1.59it/s]
 61%|██████    | 35085/57600 [6:08:50<3:51:07,  1.62it/s]
 61%|██████    | 35086/57600 [6:08:51<3:48:56,  1.64it/s]
 61%|██████    | 35087/57600 [6:08:51<3:44:19,  1.67it/s]
 61%|██████    | 35088/57600 [6:08:52<3:52:38,  1.61it/s]
 61%|██████    | 35089/57600 [6:08:53<3:48:18,  1.64it/s]
 61%|██████    | 35090/57600 [6:08:53<3:56:42,  1.58it/s]
 61%|██████    | 35091/57600 [6:08:54<3:58:18,  1.57it/s]
 61%|██████    | 35092/57600 [6:08:55<4:00:15,  1.56it/s]
 61%|██████    | 35093/57600 [6:08:55<3:59:45,  1.56it/s]
 61%|██████    | 35094/57600 [6:08:56<4:00:35,  1.56it/s]
 61%|██████    | 35095/57600 [6:08:57<4:01:38,  1.55it/s]
 61%|██████    | 35096/57600 [6:08:57<4:02:24,  1.55it/s]
 61%|██████    | 35097/57600 [6:08:58<3:58:13,  1.57it/s]
 61%|██████    | 35098/57600 [6:08:58<3:59:07,  1.57it/s]
 61%|██████    | 35099/57600 [6:08:59<3:52:16,  1.61it/s]
 61%|██████    | 35100/57600 [6:09:00<3:57:00,  1.58it/s]
                                                         
{'loss': 1.1715, 'learning_rate': 4.52787456445993e-07, 'epoch': 387.42}

 61%|██████    | 35100/57600 [6:09:00<3:57:00,  1.58it/s]
 61%|██████    | 35101/57600 [6:09:00<4:00:01,  1.56it/s]
 61%|██████    | 35102/57600 [6:09:01<4:03:33,  1.54it/s]
 61%|██████    | 35103/57600 [6:09:02<3:54:03,  1.60it/s]
 61%|██████    | 35104/57600 [6:09:02<3:49:26,  1.63it/s]
 61%|██████    | 35105/57600 [6:09:03<4:02:47,  1.54it/s]
 61%|██████    | 35106/57600 [6:09:04<3:58:31,  1.57it/s]
 61%|██████    | 35107/57600 [6:09:04<3:53:05,  1.61it/s]
 61%|██████    | 35108/57600 [6:09:05<4:05:29,  1.53it/s]
 61%|██████    | 35109/57600 [6:09:05<3:54:36,  1.60it/s]
 61%|██████    | 35110/57600 [6:09:06<3:53:32,  1.60it/s]
 61%|██████    | 35111/57600 [6:09:07<3:58:23,  1.57it/s]
 61%|██████    | 35112/57600 [6:09:07<3:56:05,  1.59it/s]
 61%|██████    | 35113/57600 [6:09:08<3:56:43,  1.58it/s]
 61%|██████    | 35114/57600 [6:09:09<3:52:51,  1.61it/s]
 61%|██████    | 35115/57600 [6:09:09<3:59:33,  1.56it/s]
 61%|██████    | 35116/57600 [6:09:10<3:57:47,  1.58it/s]
 61%|██████    | 35117/57600 [6:09:10<3:49:35,  1.63it/s]
 61%|██████    | 35118/57600 [6:09:11<3:54:07,  1.60it/s]
 61%|██████    | 35119/57600 [6:09:12<3:58:20,  1.57it/s]
 61%|██████    | 35120/57600 [6:09:12<3:54:38,  1.60it/s]
                                                         
{'loss': 1.1834, 'learning_rate': 4.5247386759581883e-07, 'epoch': 387.64}

 61%|██████    | 35120/57600 [6:09:12<3:54:38,  1.60it/s]
 61%|██████    | 35121/57600 [6:09:13<3:55:20,  1.59it/s]
 61%|██████    | 35122/57600 [6:09:14<4:03:27,  1.54it/s]
 61%|██████    | 35123/57600 [6:09:14<3:58:44,  1.57it/s]
 61%|██████    | 35124/57600 [6:09:15<4:01:18,  1.55it/s]
 61%|██████    | 35125/57600 [6:09:16<4:10:00,  1.50it/s]
 61%|██████    | 35126/57600 [6:09:16<4:06:13,  1.52it/s]
 61%|██████    | 35127/57600 [6:09:17<3:55:33,  1.59it/s]
 61%|██████    | 35128/57600 [6:09:18<4:00:46,  1.56it/s]
 61%|██████    | 35129/57600 [6:09:18<3:54:22,  1.60it/s]
 61%|██████    | 35130/57600 [6:09:19<4:04:02,  1.53it/s]
 61%|██████    | 35131/57600 [6:09:19<3:59:48,  1.56it/s]
 61%|██████    | 35132/57600 [6:09:20<3:54:16,  1.60it/s]
 61%|██████    | 35133/57600 [6:09:21<3:49:20,  1.63it/s]
 61%|██████    | 35134/57600 [6:09:21<3:53:39,  1.60it/s]
 61%|██████    | 35135/57600 [6:09:22<3:52:31,  1.61it/s]
 61%|██████    | 35136/57600 [6:09:22<3:49:28,  1.63it/s]
 61%|██████    | 35137/57600 [6:09:23<3:48:47,  1.64it/s]
 61%|██████    | 35138/57600 [6:09:24<3:52:26,  1.61it/s]
 61%|██████    | 35139/57600 [6:09:24<4:01:13,  1.55it/s]
 61%|██████    | 35140/57600 [6:09:25<4:01:35,  1.55it/s]
                                                         
{'loss': 1.1213, 'learning_rate': 4.521602787456446e-07, 'epoch': 387.86}

 61%|██████    | 35140/57600 [6:09:25<4:01:35,  1.55it/s]
 61%|██████    | 35141/57600 [6:09:26<3:50:00,  1.63it/s]
 61%|██████    | 35142/57600 [6:09:26<3:53:44,  1.60it/s]
 61%|██████    | 35143/57600 [6:09:27<3:49:25,  1.63it/s]
 61%|██████    | 35144/57600 [6:09:27<3:48:12,  1.64it/s]
 61%|██████    | 35145/57600 [6:09:28<3:51:29,  1.62it/s]
 61%|██████    | 35146/57600 [6:09:29<3:56:51,  1.58it/s]
 61%|██████    | 35147/57600 [6:09:29<3:57:28,  1.58it/s]
 61%|██████    | 35148/57600 [6:09:30<3:55:17,  1.59it/s]
 61%|██████    | 35149/57600 [6:09:31<4:02:22,  1.54it/s]
 61%|██████    | 35150/57600 [6:09:31<3:58:50,  1.57it/s]
 61%|██████    | 35151/57600 [6:09:32<3:55:19,  1.59it/s]
 61%|██████    | 35152/57600 [6:09:33<3:53:13,  1.60it/s]
 61%|██████    | 35153/57600 [6:09:33<4:06:19,  1.52it/s]
 61%|██████    | 35154/57600 [6:09:34<4:03:07,  1.54it/s]
 61%|██████    | 35155/57600 [6:09:35<4:00:42,  1.55it/s]
 61%|██████    | 35156/57600 [6:09:35<4:00:46,  1.55it/s]
 61%|██████    | 35157/57600 [6:09:36<3:56:09,  1.58it/s]
 61%|██████    | 35158/57600 [6:09:36<3:48:49,  1.63it/s]
 61%|██████    | 35159/57600 [6:09:37<3:46:39,  1.65it/s]
 61%|██████    | 35160/57600 [6:09:38<3:47:48,  1.64it/s]
                                                         
{'loss': 1.179, 'learning_rate': 4.518466898954704e-07, 'epoch': 388.08}

 61%|██████    | 35160/57600 [6:09:38<3:47:48,  1.64it/s]
 61%|██████    | 35161/57600 [6:09:38<3:50:11,  1.62it/s]
 61%|██████    | 35162/57600 [6:09:39<3:44:22,  1.67it/s]
 61%|██████    | 35163/57600 [6:09:39<3:45:36,  1.66it/s]
 61%|██████    | 35164/57600 [6:09:40<3:43:37,  1.67it/s]
 61%|██████    | 35165/57600 [6:09:41<3:46:16,  1.65it/s]
 61%|██████    | 35166/57600 [6:09:41<3:58:02,  1.57it/s]
 61%|██████    | 35167/57600 [6:09:42<4:02:38,  1.54it/s]
 61%|██████    | 35168/57600 [6:09:43<3:56:08,  1.58it/s]
 61%|██████    | 35169/57600 [6:09:43<4:05:21,  1.52it/s]
 61%|██████    | 35170/57600 [6:09:44<3:55:58,  1.58it/s]
 61%|██████    | 35171/57600 [6:09:44<3:51:15,  1.62it/s]
 61%|██████    | 35172/57600 [6:09:45<3:50:51,  1.62it/s]
 61%|██████    | 35173/57600 [6:09:46<3:51:23,  1.62it/s]
 61%|██████    | 35174/57600 [6:09:46<4:00:17,  1.56it/s]
 61%|██████    | 35175/57600 [6:09:47<3:55:56,  1.58it/s]
 61%|██████    | 35176/57600 [6:09:48<3:54:34,  1.59it/s]
 61%|██████    | 35177/57600 [6:09:48<3:52:59,  1.60it/s]
 61%|██████    | 35178/57600 [6:09:49<3:47:49,  1.64it/s]
 61%|██████    | 35179/57600 [6:09:49<3:55:01,  1.59it/s]
 61%|██████    | 35180/57600 [6:09:50<3:59:41,  1.56it/s]
                                                         
{'loss': 1.1465, 'learning_rate': 4.5153310104529614e-07, 'epoch': 388.3}

 61%|██████    | 35180/57600 [6:09:50<3:59:41,  1.56it/s]
 61%|██████    | 35181/57600 [6:09:51<4:04:11,  1.53it/s]
 61%|██████    | 35182/57600 [6:09:51<4:02:45,  1.54it/s]
 61%|██████    | 35183/57600 [6:09:52<4:02:51,  1.54it/s]
 61%|██████    | 35184/57600 [6:09:53<3:56:08,  1.58it/s]
 61%|██████    | 35185/57600 [6:09:53<3:53:53,  1.60it/s]
 61%|██████    | 35186/57600 [6:09:54<3:53:06,  1.60it/s]
 61%|██████    | 35187/57600 [6:09:55<3:52:52,  1.60it/s]
 61%|██████    | 35188/57600 [6:09:55<3:52:26,  1.61it/s]
 61%|██████    | 35189/57600 [6:09:56<3:48:48,  1.63it/s]
 61%|██████    | 35190/57600 [6:09:56<3:49:55,  1.62it/s]
 61%|██████    | 35191/57600 [6:09:57<3:56:35,  1.58it/s]
 61%|██████    | 35192/57600 [6:09:58<4:02:10,  1.54it/s]
 61%|██████    | 35193/57600 [6:09:58<4:03:30,  1.53it/s]
 61%|██████    | 35194/57600 [6:09:59<4:04:28,  1.53it/s]
 61%|██████    | 35195/57600 [6:10:00<4:02:53,  1.54it/s]
 61%|██████    | 35196/57600 [6:10:00<3:58:23,  1.57it/s]
 61%|██████    | 35197/57600 [6:10:01<3:52:07,  1.61it/s]
 61%|██████    | 35198/57600 [6:10:02<3:53:51,  1.60it/s]
 61%|██████    | 35199/57600 [6:10:02<3:48:14,  1.64it/s]
 61%|██████    | 35200/57600 [6:10:03<3:51:26,  1.61it/s]
                                                         
{'loss': 1.1355, 'learning_rate': 4.5121951219512194e-07, 'epoch': 388.52}

 61%|██████    | 35200/57600 [6:10:03<3:51:26,  1.61it/s]
 61%|██████    | 35201/57600 [6:10:03<3:57:34,  1.57it/s]
 61%|██████    | 35202/57600 [6:10:04<3:54:03,  1.59it/s]
 61%|██████    | 35203/57600 [6:10:05<3:51:09,  1.61it/s]
 61%|██████    | 35204/57600 [6:10:05<3:45:07,  1.66it/s]
 61%|██████    | 35205/57600 [6:10:06<3:48:08,  1.64it/s]
 61%|██████    | 35206/57600 [6:10:06<3:47:26,  1.64it/s]
 61%|██████    | 35207/57600 [6:10:07<3:50:44,  1.62it/s]
 61%|██████    | 35208/57600 [6:10:08<3:50:08,  1.62it/s]
 61%|██████    | 35209/57600 [6:10:08<3:52:18,  1.61it/s]
 61%|██████    | 35210/57600 [6:10:09<3:54:54,  1.59it/s]
 61%|██████    | 35211/57600 [6:10:10<4:01:18,  1.55it/s]
 61%|██████    | 35212/57600 [6:10:10<3:56:06,  1.58it/s]
 61%|██████    | 35213/57600 [6:10:11<3:52:19,  1.61it/s]
 61%|██████    | 35214/57600 [6:10:11<3:54:08,  1.59it/s]
 61%|██████    | 35215/57600 [6:10:12<3:52:15,  1.61it/s]
 61%|██████    | 35216/57600 [6:10:13<3:43:50,  1.67it/s]
 61%|██████    | 35217/57600 [6:10:13<3:39:43,  1.70it/s]
 61%|██████    | 35218/57600 [6:10:14<3:39:30,  1.70it/s]
 61%|██████    | 35219/57600 [6:10:14<3:43:53,  1.67it/s]
 61%|██████    | 35220/57600 [6:10:15<3:47:39,  1.64it/s]
                                                         
{'loss': 1.1686, 'learning_rate': 4.509059233449477e-07, 'epoch': 388.74}

 61%|██████    | 35220/57600 [6:10:15<3:47:39,  1.64it/s]
 61%|██████    | 35221/57600 [6:10:16<3:53:50,  1.59it/s]
 61%|██████    | 35222/57600 [6:10:16<3:52:46,  1.60it/s]
 61%|██████    | 35223/57600 [6:10:17<4:00:37,  1.55it/s]
 61%|██████    | 35224/57600 [6:10:18<3:55:18,  1.58it/s]
 61%|██████    | 35225/57600 [6:10:18<3:58:46,  1.56it/s]
 61%|██████    | 35226/57600 [6:10:19<3:53:48,  1.59it/s]
 61%|██████    | 35227/57600 [6:10:19<3:46:57,  1.64it/s]
 61%|██████    | 35228/57600 [6:10:20<3:46:14,  1.65it/s]
 61%|██████    | 35229/57600 [6:10:21<3:56:48,  1.57it/s]
 61%|██████    | 35230/57600 [6:10:21<3:53:40,  1.60it/s]
 61%|██████    | 35231/57600 [6:10:22<3:52:07,  1.61it/s]
 61%|██████    | 35232/57600 [6:10:23<3:49:36,  1.62it/s]
 61%|██████    | 35233/57600 [6:10:23<3:46:48,  1.64it/s]
 61%|██████    | 35234/57600 [6:10:24<3:49:51,  1.62it/s]
 61%|██████    | 35235/57600 [6:10:24<3:54:30,  1.59it/s]
 61%|██████    | 35236/57600 [6:10:25<3:50:58,  1.61it/s]
 61%|██████    | 35237/57600 [6:10:26<3:59:07,  1.56it/s]
 61%|██████    | 35238/57600 [6:10:26<4:03:54,  1.53it/s]
 61%|██████    | 35239/57600 [6:10:27<4:05:42,  1.52it/s]
 61%|██████    | 35240/57600 [6:10:28<3:57:18,  1.57it/s]
                                                         
{'loss': 1.1378, 'learning_rate': 4.505923344947735e-07, 'epoch': 388.96}

 61%|██████    | 35240/57600 [6:10:28<3:57:18,  1.57it/s]
 61%|██████    | 35241/57600 [6:10:28<3:52:55,  1.60it/s]
 61%|██████    | 35242/57600 [6:10:29<3:55:55,  1.58it/s]
 61%|██████    | 35243/57600 [6:10:30<4:02:41,  1.54it/s]
 61%|██████    | 35244/57600 [6:10:30<4:05:14,  1.52it/s]
 61%|██████    | 35245/57600 [6:10:31<4:04:33,  1.52it/s]
 61%|██████    | 35246/57600 [6:10:32<4:00:58,  1.55it/s]
 61%|██████    | 35247/57600 [6:10:32<3:57:51,  1.57it/s]
 61%|██████    | 35248/57600 [6:10:33<3:48:40,  1.63it/s]
 61%|██████    | 35249/57600 [6:10:33<3:48:44,  1.63it/s]
 61%|██████    | 35250/57600 [6:10:34<3:49:28,  1.62it/s]
 61%|██████    | 35251/57600 [6:10:35<3:55:00,  1.59it/s]
 61%|██████    | 35252/57600 [6:10:35<3:55:20,  1.58it/s]
 61%|██████    | 35253/57600 [6:10:36<3:54:44,  1.59it/s]
 61%|██████    | 35254/57600 [6:10:37<3:58:21,  1.56it/s]
 61%|██████    | 35255/57600 [6:10:37<3:54:38,  1.59it/s]
 61%|██████    | 35256/57600 [6:10:38<3:56:22,  1.58it/s]
 61%|██████    | 35257/57600 [6:10:38<3:52:19,  1.60it/s]
 61%|██████    | 35258/57600 [6:10:39<3:59:34,  1.55it/s]
 61%|██████    | 35259/57600 [6:10:40<3:59:46,  1.55it/s]
 61%|██████    | 35260/57600 [6:10:40<4:00:11,  1.55it/s]
                                                         
{'loss': 1.1601, 'learning_rate': 4.5027874564459925e-07, 'epoch': 389.18}

 61%|██████    | 35260/57600 [6:10:40<4:00:11,  1.55it/s]
 61%|██████    | 35261/57600 [6:10:41<3:59:09,  1.56it/s]
 61%|██████    | 35262/57600 [6:10:42<3:53:43,  1.59it/s]
 61%|██████    | 35263/57600 [6:10:42<3:51:19,  1.61it/s]
 61%|██████    | 35264/57600 [6:10:43<3:53:35,  1.59it/s]
 61%|██████    | 35265/57600 [6:10:44<3:54:15,  1.59it/s]
 61%|██████    | 35266/57600 [6:10:44<3:54:24,  1.59it/s]
 61%|██████    | 35267/57600 [6:10:45<3:53:17,  1.60it/s]
 61%|██████    | 35268/57600 [6:10:45<3:50:53,  1.61it/s]
 61%|██████    | 35269/57600 [6:10:46<3:56:17,  1.58it/s]
 61%|██████    | 35270/57600 [6:10:47<4:04:10,  1.52it/s]
 61%|██████    | 35271/57600 [6:10:47<4:04:01,  1.53it/s]
 61%|██████    | 35272/57600 [6:10:48<4:05:57,  1.51it/s]
 61%|██████    | 35273/57600 [6:10:49<3:51:37,  1.61it/s]
 61%|██████    | 35274/57600 [6:10:49<3:45:47,  1.65it/s]
 61%|██████    | 35275/57600 [6:10:50<3:51:03,  1.61it/s]
 61%|██████    | 35276/57600 [6:10:50<3:49:06,  1.62it/s]
 61%|██████    | 35277/57600 [6:10:51<3:46:33,  1.64it/s]
 61%|██████    | 35278/57600 [6:10:52<3:45:31,  1.65it/s]
 61%|██████    | 35279/57600 [6:10:52<3:49:59,  1.62it/s]
 61%|██████▏   | 35280/57600 [6:10:53<3:48:04,  1.63it/s]
                                                         
{'loss': 1.1491, 'learning_rate': 4.4996515679442506e-07, 'epoch': 389.4}

 61%|██████▏   | 35280/57600 [6:10:53<3:48:04,  1.63it/s]
 61%|██████▏   | 35281/57600 [6:10:53<3:44:36,  1.66it/s]
 61%|██████▏   | 35282/57600 [6:10:54<3:47:22,  1.64it/s]
 61%|██████▏   | 35283/57600 [6:10:55<3:55:53,  1.58it/s]
 61%|██████▏   | 35284/57600 [6:10:55<4:04:10,  1.52it/s]
 61%|██████▏   | 35285/57600 [6:10:56<4:03:16,  1.53it/s]
 61%|██████▏   | 35286/57600 [6:10:57<3:56:56,  1.57it/s]
 61%|██████▏   | 35287/57600 [6:10:57<3:54:27,  1.59it/s]
 61%|██████▏   | 35288/57600 [6:10:58<4:05:10,  1.52it/s]
 61%|██████▏   | 35289/57600 [6:10:59<4:06:04,  1.51it/s]
 61%|██████▏   | 35290/57600 [6:10:59<4:05:05,  1.52it/s]
 61%|██████▏   | 35291/57600 [6:11:00<4:02:21,  1.53it/s]
 61%|██████▏   | 35292/57600 [6:11:01<4:05:46,  1.51it/s]
 61%|██████▏   | 35293/57600 [6:11:01<3:56:40,  1.57it/s]
 61%|██████▏   | 35294/57600 [6:11:02<3:57:24,  1.57it/s]
 61%|██████▏   | 35295/57600 [6:11:03<3:57:19,  1.57it/s]
 61%|██████▏   | 35296/57600 [6:11:03<3:51:16,  1.61it/s]
 61%|██████▏   | 35297/57600 [6:11:04<3:58:33,  1.56it/s]
 61%|██████▏   | 35298/57600 [6:11:05<4:02:25,  1.53it/s]
 61%|██████▏   | 35299/57600 [6:11:05<4:02:02,  1.54it/s]
 61%|██████▏   | 35300/57600 [6:11:06<4:08:08,  1.50it/s]
                                                         
{'loss': 1.1138, 'learning_rate': 4.4965156794425086e-07, 'epoch': 389.62}

 61%|██████▏   | 35300/57600 [6:11:06<4:08:08,  1.50it/s]
 61%|██████▏   | 35301/57600 [6:11:06<4:01:25,  1.54it/s]
 61%|██████▏   | 35302/57600 [6:11:07<4:03:15,  1.53it/s]
 61%|██████▏   | 35303/57600 [6:11:08<3:55:57,  1.57it/s]
 61%|██████▏   | 35304/57600 [6:11:08<3:51:32,  1.60it/s]
 61%|██████▏   | 35305/57600 [6:11:09<3:46:09,  1.64it/s]
 61%|██████▏   | 35306/57600 [6:11:10<3:47:34,  1.63it/s]
 61%|██████▏   | 35307/57600 [6:11:10<3:53:46,  1.59it/s]
 61%|██████▏   | 35308/57600 [6:11:11<3:47:05,  1.64it/s]
 61%|██████▏   | 35309/57600 [6:11:11<3:42:16,  1.67it/s]
 61%|██████▏   | 35310/57600 [6:11:12<3:52:55,  1.59it/s]
 61%|██████▏   | 35311/57600 [6:11:13<3:55:03,  1.58it/s]
 61%|██████▏   | 35312/57600 [6:11:13<3:58:51,  1.56it/s]
 61%|██████▏   | 35313/57600 [6:11:14<3:56:32,  1.57it/s]
 61%|██████▏   | 35314/57600 [6:11:15<3:53:04,  1.59it/s]
 61%|██████▏   | 35315/57600 [6:11:15<4:05:32,  1.51it/s]
 61%|██████▏   | 35316/57600 [6:11:16<4:03:13,  1.53it/s]
 61%|██████▏   | 35317/57600 [6:11:17<4:03:36,  1.52it/s]
 61%|██████▏   | 35318/57600 [6:11:17<4:00:08,  1.55it/s]
 61%|██████▏   | 35319/57600 [6:11:18<3:50:22,  1.61it/s]
 61%|██████▏   | 35320/57600 [6:11:18<3:52:47,  1.60it/s]
                                                         
{'loss': 1.1747, 'learning_rate': 4.493379790940766e-07, 'epoch': 389.85}

 61%|██████▏   | 35320/57600 [6:11:18<3:52:47,  1.60it/s]
 61%|██████▏   | 35321/57600 [6:11:19<3:47:59,  1.63it/s]
 61%|██████▏   | 35322/57600 [6:11:20<3:45:38,  1.65it/s]
 61%|██████▏   | 35323/57600 [6:11:20<3:51:28,  1.60it/s]
 61%|██████▏   | 35324/57600 [6:11:21<3:53:42,  1.59it/s]
 61%|██████▏   | 35325/57600 [6:11:22<3:59:10,  1.55it/s]
 61%|██████▏   | 35326/57600 [6:11:22<3:55:03,  1.58it/s]
 61%|██████▏   | 35327/57600 [6:11:23<3:51:40,  1.60it/s]
 61%|██████▏   | 35328/57600 [6:11:23<3:51:52,  1.60it/s]
 61%|██████▏   | 35329/57600 [6:11:24<3:45:55,  1.64it/s]
 61%|██████▏   | 35330/57600 [6:11:25<3:50:28,  1.61it/s]
 61%|██████▏   | 35331/57600 [6:11:25<3:50:51,  1.61it/s]
 61%|██████▏   | 35332/57600 [6:11:26<3:55:50,  1.57it/s]
 61%|██████▏   | 35333/57600 [6:11:27<3:52:23,  1.60it/s]
 61%|██████▏   | 35334/57600 [6:11:27<3:58:03,  1.56it/s]
 61%|██████▏   | 35335/57600 [6:11:28<4:12:24,  1.47it/s]
 61%|██████▏   | 35336/57600 [6:11:29<3:59:43,  1.55it/s]
 61%|██████▏   | 35337/57600 [6:11:29<3:59:36,  1.55it/s]
 61%|██████▏   | 35338/57600 [6:11:30<3:54:37,  1.58it/s]
 61%|██████▏   | 35339/57600 [6:11:30<4:00:33,  1.54it/s]
 61%|██████▏   | 35340/57600 [6:11:31<4:02:37,  1.53it/s]
                                                         
{'loss': 1.1572, 'learning_rate': 4.490243902439024e-07, 'epoch': 390.07}

 61%|██████▏   | 35340/57600 [6:11:31<4:02:37,  1.53it/s]
 61%|██████▏   | 35341/57600 [6:11:32<3:56:43,  1.57it/s]
 61%|██████▏   | 35342/57600 [6:11:32<3:55:09,  1.58it/s]
 61%|██████▏   | 35343/57600 [6:11:33<3:50:13,  1.61it/s]
 61%|██████▏   | 35344/57600 [6:11:34<3:58:21,  1.56it/s]
 61%|██████▏   | 35345/57600 [6:11:34<3:57:53,  1.56it/s]
 61%|██████▏   | 35346/57600 [6:11:35<4:03:24,  1.52it/s]
 61%|██████▏   | 35347/57600 [6:11:36<4:01:26,  1.54it/s]
 61%|██████▏   | 35348/57600 [6:11:36<3:58:51,  1.55it/s]
 61%|██████▏   | 35349/57600 [6:11:37<3:54:06,  1.58it/s]
 61%|██████▏   | 35350/57600 [6:11:37<3:49:47,  1.61it/s]
 61%|██████▏   | 35351/57600 [6:11:38<3:53:14,  1.59it/s]
 61%|██████▏   | 35352/57600 [6:11:39<3:57:40,  1.56it/s]
 61%|██████▏   | 35353/57600 [6:11:39<3:58:41,  1.55it/s]
 61%|██████▏   | 35354/57600 [6:11:40<3:55:16,  1.58it/s]
 61%|██████▏   | 35355/57600 [6:11:41<3:58:24,  1.56it/s]
 61%|██████▏   | 35356/57600 [6:11:41<4:03:05,  1.53it/s]
 61%|██████▏   | 35357/57600 [6:11:42<4:05:49,  1.51it/s]
 61%|██████▏   | 35358/57600 [6:11:43<4:01:09,  1.54it/s]
 61%|██████▏   | 35359/57600 [6:11:43<3:59:32,  1.55it/s]
 61%|██████▏   | 35360/57600 [6:11:44<3:56:21,  1.57it/s]
                                                         
{'loss': 1.1155, 'learning_rate': 4.4871080139372817e-07, 'epoch': 390.29}

 61%|██████▏   | 35360/57600 [6:11:44<3:56:21,  1.57it/s]
 61%|██████▏   | 35361/57600 [6:11:45<4:02:57,  1.53it/s]
 61%|██████▏   | 35362/57600 [6:11:45<3:55:53,  1.57it/s]
 61%|██████▏   | 35363/57600 [6:11:46<4:03:46,  1.52it/s]
 61%|██████▏   | 35364/57600 [6:11:47<3:57:04,  1.56it/s]
 61%|██████▏   | 35365/57600 [6:11:47<3:53:16,  1.59it/s]
 61%|██████▏   | 35366/57600 [6:11:48<3:50:39,  1.61it/s]
 61%|██████▏   | 35367/57600 [6:11:48<3:52:40,  1.59it/s]
 61%|██████▏   | 35368/57600 [6:11:49<3:50:27,  1.61it/s]
 61%|██████▏   | 35369/57600 [6:11:50<3:50:31,  1.61it/s]
 61%|██████▏   | 35370/57600 [6:11:50<3:51:36,  1.60it/s]
 61%|██████▏   | 35371/57600 [6:11:51<3:56:12,  1.57it/s]
 61%|██████▏   | 35372/57600 [6:11:52<3:54:25,  1.58it/s]
 61%|██████▏   | 35373/57600 [6:11:52<4:00:09,  1.54it/s]
 61%|██████▏   | 35374/57600 [6:11:53<4:00:20,  1.54it/s]
 61%|██████▏   | 35375/57600 [6:11:54<4:00:34,  1.54it/s]
 61%|██████▏   | 35376/57600 [6:11:54<4:04:32,  1.51it/s]
 61%|██████▏   | 35377/57600 [6:11:55<4:04:51,  1.51it/s]
 61%|██████▏   | 35378/57600 [6:11:55<3:59:59,  1.54it/s]
 61%|██████▏   | 35379/57600 [6:11:56<3:58:09,  1.56it/s]
 61%|██████▏   | 35380/57600 [6:11:57<3:53:17,  1.59it/s]
                                                         
{'loss': 1.1676, 'learning_rate': 4.483972125435539e-07, 'epoch': 390.51}

 61%|██████▏   | 35380/57600 [6:11:57<3:53:17,  1.59it/s]
 61%|██████▏   | 35381/57600 [6:11:57<3:52:32,  1.59it/s]
 61%|██████▏   | 35382/57600 [6:11:58<3:51:58,  1.60it/s]
 61%|██████▏   | 35383/57600 [6:11:59<3:50:10,  1.61it/s]
 61%|██████▏   | 35384/57600 [6:11:59<3:46:55,  1.63it/s]
 61%|██████▏   | 35385/57600 [6:12:00<3:45:37,  1.64it/s]
 61%|██████▏   | 35386/57600 [6:12:00<3:48:57,  1.62it/s]
 61%|██████▏   | 35387/57600 [6:12:01<3:54:21,  1.58it/s]
 61%|██████▏   | 35388/57600 [6:12:02<3:56:25,  1.57it/s]
 61%|██████▏   | 35389/57600 [6:12:02<3:52:36,  1.59it/s]
 61%|██████▏   | 35390/57600 [6:12:03<4:00:57,  1.54it/s]
 61%|██████▏   | 35391/57600 [6:12:04<3:54:33,  1.58it/s]
 61%|██████▏   | 35392/57600 [6:12:04<3:52:43,  1.59it/s]
 61%|██████▏   | 35393/57600 [6:12:05<3:56:58,  1.56it/s]
 61%|██████▏   | 35394/57600 [6:12:06<3:51:07,  1.60it/s]
 61%|██████▏   | 35395/57600 [6:12:06<3:48:38,  1.62it/s]
 61%|██████▏   | 35396/57600 [6:12:07<3:50:16,  1.61it/s]
 61%|██████▏   | 35397/57600 [6:12:07<3:50:54,  1.60it/s]
 61%|██████▏   | 35398/57600 [6:12:08<3:58:35,  1.55it/s]
 61%|██████▏   | 35399/57600 [6:12:09<3:59:51,  1.54it/s]
 61%|██████▏   | 35400/57600 [6:12:09<4:00:28,  1.54it/s]
                                                         
{'loss': 1.1616, 'learning_rate': 4.4808362369337983e-07, 'epoch': 390.73}

 61%|██████▏   | 35400/57600 [6:12:09<4:00:28,  1.54it/s]
 61%|██████▏   | 35401/57600 [6:12:10<3:57:50,  1.56it/s]
 61%|██████▏   | 35402/57600 [6:12:11<4:03:04,  1.52it/s]
 61%|██████▏   | 35403/57600 [6:12:11<3:55:14,  1.57it/s]
 61%|██████▏   | 35404/57600 [6:12:12<3:51:29,  1.60it/s]
 61%|██████▏   | 35405/57600 [6:12:12<3:46:20,  1.63it/s]
 61%|██████▏   | 35406/57600 [6:12:13<3:49:29,  1.61it/s]
 61%|██████▏   | 35407/57600 [6:12:14<3:48:13,  1.62it/s]
 61%|██████▏   | 35408/57600 [6:12:14<3:48:07,  1.62it/s]
 61%|██████▏   | 35409/57600 [6:12:15<3:41:36,  1.67it/s]
 61%|██████▏   | 35410/57600 [6:12:16<3:50:59,  1.60it/s]
 61%|██████▏   | 35411/57600 [6:12:16<3:49:00,  1.61it/s]
 61%|██████▏   | 35412/57600 [6:12:17<3:46:32,  1.63it/s]
 61%|██████▏   | 35413/57600 [6:12:17<3:44:24,  1.65it/s]
 61%|██████▏   | 35414/57600 [6:12:18<3:50:58,  1.60it/s]
 61%|██████▏   | 35415/57600 [6:12:19<3:52:40,  1.59it/s]
 61%|██████▏   | 35416/57600 [6:12:19<3:50:11,  1.61it/s]
 61%|██████▏   | 35417/57600 [6:12:20<3:55:55,  1.57it/s]
 61%|██████▏   | 35418/57600 [6:12:21<3:59:10,  1.55it/s]
 61%|██████▏   | 35419/57600 [6:12:21<3:57:01,  1.56it/s]
 61%|██████▏   | 35420/57600 [6:12:22<4:00:35,  1.54it/s]
                                                         
{'loss': 1.1607, 'learning_rate': 4.4777003484320553e-07, 'epoch': 390.95}

 61%|██████▏   | 35420/57600 [6:12:22<4:00:35,  1.54it/s]
 61%|██████▏   | 35421/57600 [6:12:23<4:00:41,  1.54it/s]
 61%|██████▏   | 35422/57600 [6:12:23<3:58:01,  1.55it/s]
 61%|██████▏   | 35423/57600 [6:12:24<3:49:19,  1.61it/s]
 62%|██████▏   | 35424/57600 [6:12:24<3:48:09,  1.62it/s]
 62%|██████▏   | 35425/57600 [6:12:25<3:58:33,  1.55it/s]
 62%|██████▏   | 35426/57600 [6:12:26<3:57:07,  1.56it/s]
 62%|██████▏   | 35427/57600 [6:12:26<3:51:30,  1.60it/s]
 62%|██████▏   | 35428/57600 [6:12:27<3:54:02,  1.58it/s]
 62%|██████▏   | 35429/57600 [6:12:28<3:52:30,  1.59it/s]
 62%|██████▏   | 35430/57600 [6:12:28<3:51:30,  1.60it/s]
 62%|██████▏   | 35431/57600 [6:12:29<3:48:07,  1.62it/s]
 62%|██████▏   | 35432/57600 [6:12:29<3:46:25,  1.63it/s]
 62%|██████▏   | 35433/57600 [6:12:30<3:52:46,  1.59it/s]
 62%|██████▏   | 35434/57600 [6:12:31<3:51:43,  1.59it/s]
 62%|██████▏   | 35435/57600 [6:12:31<3:54:38,  1.57it/s]
 62%|██████▏   | 35436/57600 [6:12:32<3:57:15,  1.56it/s]
 62%|██████▏   | 35437/57600 [6:12:33<3:52:21,  1.59it/s]
 62%|██████▏   | 35438/57600 [6:12:33<3:51:58,  1.59it/s]
 62%|██████▏   | 35439/57600 [6:12:34<4:08:21,  1.49it/s]
 62%|██████▏   | 35440/57600 [6:12:35<4:00:55,  1.53it/s]
                                                         
{'loss': 1.1482, 'learning_rate': 4.4745644599303134e-07, 'epoch': 391.17}

 62%|██████▏   | 35440/57600 [6:12:35<4:00:55,  1.53it/s]
 62%|██████▏   | 35441/57600 [6:12:35<4:00:40,  1.53it/s]
 62%|██████▏   | 35442/57600 [6:12:36<3:58:39,  1.55it/s]
 62%|██████▏   | 35443/57600 [6:12:37<3:58:32,  1.55it/s]
 62%|██████▏   | 35444/57600 [6:12:37<4:02:41,  1.52it/s]
 62%|██████▏   | 35445/57600 [6:12:38<3:58:46,  1.55it/s]
 62%|██████▏   | 35446/57600 [6:12:39<4:00:45,  1.53it/s]
 62%|██████▏   | 35447/57600 [6:12:39<3:54:59,  1.57it/s]
 62%|██████▏   | 35448/57600 [6:12:40<3:56:11,  1.56it/s]
 62%|██████▏   | 35449/57600 [6:12:40<3:57:37,  1.55it/s]
 62%|██████▏   | 35450/57600 [6:12:41<4:08:29,  1.49it/s]
 62%|██████▏   | 35451/57600 [6:12:42<4:06:20,  1.50it/s]
 62%|██████▏   | 35452/57600 [6:12:42<4:04:20,  1.51it/s]
 62%|██████▏   | 35453/57600 [6:12:43<3:56:29,  1.56it/s]
 62%|██████▏   | 35454/57600 [6:12:44<3:51:19,  1.60it/s]
 62%|██████▏   | 35455/57600 [6:12:44<3:47:42,  1.62it/s]
 62%|██████▏   | 35456/57600 [6:12:45<3:48:08,  1.62it/s]
 62%|██████▏   | 35457/57600 [6:12:45<3:49:55,  1.61it/s]
 62%|██████▏   | 35458/57600 [6:12:46<3:54:17,  1.58it/s]
 62%|██████▏   | 35459/57600 [6:12:47<3:56:59,  1.56it/s]
 62%|██████▏   | 35460/57600 [6:12:48<4:04:02,  1.51it/s]
                                                         
{'loss': 1.1485, 'learning_rate': 4.471428571428571e-07, 'epoch': 391.39}

 62%|██████▏   | 35460/57600 [6:12:48<4:04:02,  1.51it/s]
 62%|██████▏   | 35461/57600 [6:12:48<3:56:01,  1.56it/s]
 62%|██████▏   | 35462/57600 [6:12:49<3:51:01,  1.60it/s]
 62%|██████▏   | 35463/57600 [6:12:49<3:52:57,  1.58it/s]
 62%|██████▏   | 35464/57600 [6:12:50<3:55:23,  1.57it/s]
 62%|██████▏   | 35465/57600 [6:12:51<3:50:33,  1.60it/s]
 62%|██████▏   | 35466/57600 [6:12:51<3:50:39,  1.60it/s]
 62%|██████▏   | 35467/57600 [6:12:52<3:43:09,  1.65it/s]
 62%|██████▏   | 35468/57600 [6:12:52<3:47:25,  1.62it/s]
 62%|██████▏   | 35469/57600 [6:12:53<3:44:28,  1.64it/s]
 62%|██████▏   | 35470/57600 [6:12:54<3:42:22,  1.66it/s]
 62%|██████▏   | 35471/57600 [6:12:54<3:58:30,  1.55it/s]
 62%|██████▏   | 35472/57600 [6:12:55<4:01:48,  1.53it/s]
 62%|██████▏   | 35473/57600 [6:12:56<3:57:36,  1.55it/s]
 62%|██████▏   | 35474/57600 [6:12:56<3:53:46,  1.58it/s]
 62%|██████▏   | 35475/57600 [6:12:57<4:07:36,  1.49it/s]
 62%|██████▏   | 35476/57600 [6:12:58<3:55:25,  1.57it/s]
 62%|██████▏   | 35477/57600 [6:12:58<3:47:55,  1.62it/s]
 62%|██████▏   | 35478/57600 [6:12:59<3:44:45,  1.64it/s]
 62%|██████▏   | 35479/57600 [6:12:59<3:44:58,  1.64it/s]
 62%|██████▏   | 35480/57600 [6:13:00<3:50:12,  1.60it/s]
                                                         
{'loss': 1.1441, 'learning_rate': 4.468292682926829e-07, 'epoch': 391.61}

 62%|██████▏   | 35480/57600 [6:13:00<3:50:12,  1.60it/s]
 62%|██████▏   | 35481/57600 [6:13:01<3:48:04,  1.62it/s]
 62%|██████▏   | 35482/57600 [6:13:01<3:44:26,  1.64it/s]
 62%|██████▏   | 35483/57600 [6:13:02<3:50:09,  1.60it/s]
 62%|██████▏   | 35484/57600 [6:13:02<3:43:04,  1.65it/s]
 62%|██████▏   | 35485/57600 [6:13:03<3:52:06,  1.59it/s]
 62%|██████▏   | 35486/57600 [6:13:04<4:00:55,  1.53it/s]
 62%|██████▏   | 35487/57600 [6:13:04<3:53:58,  1.58it/s]
 62%|██████▏   | 35488/57600 [6:13:05<3:49:34,  1.61it/s]
 62%|██████▏   | 35489/57600 [6:13:06<3:45:17,  1.64it/s]
 62%|██████▏   | 35490/57600 [6:13:06<3:50:59,  1.60it/s]
 62%|██████▏   | 35491/57600 [6:13:07<3:53:36,  1.58it/s]
 62%|██████▏   | 35492/57600 [6:13:07<3:43:59,  1.65it/s]
 62%|██████▏   | 35493/57600 [6:13:08<3:45:54,  1.63it/s]
 62%|██████▏   | 35494/57600 [6:13:09<3:51:13,  1.59it/s]
 62%|██████▏   | 35495/57600 [6:13:09<3:46:50,  1.62it/s]
 62%|██████▏   | 35496/57600 [6:13:10<3:47:13,  1.62it/s]
 62%|██████▏   | 35497/57600 [6:13:11<3:43:38,  1.65it/s]
 62%|██████▏   | 35498/57600 [6:13:11<3:43:48,  1.65it/s]
 62%|██████▏   | 35499/57600 [6:13:12<3:41:55,  1.66it/s]
 62%|██████▏   | 35500/57600 [6:13:12<3:42:48,  1.65it/s]
                                                         
{'loss': 1.2112, 'learning_rate': 4.465156794425086e-07, 'epoch': 391.83}

 62%|██████▏   | 35500/57600 [6:13:12<3:42:48,  1.65it/s]
 62%|██████▏   | 35501/57600 [6:13:13<3:50:43,  1.60it/s]
 62%|██████▏   | 35502/57600 [6:13:14<3:48:59,  1.61it/s]
 62%|██████▏   | 35503/57600 [6:13:14<3:50:50,  1.60it/s]
 62%|██████▏   | 35504/57600 [6:13:15<3:52:47,  1.58it/s]
 62%|██████▏   | 35505/57600 [6:13:16<3:50:41,  1.60it/s]
 62%|██████▏   | 35506/57600 [6:13:16<3:48:47,  1.61it/s]
 62%|██████▏   | 35507/57600 [6:13:17<3:49:18,  1.61it/s]
 62%|██████▏   | 35508/57600 [6:13:17<3:50:03,  1.60it/s]
 62%|██████▏   | 35509/57600 [6:13:18<3:49:35,  1.60it/s]
 62%|██████▏   | 35510/57600 [6:13:19<3:47:09,  1.62it/s]
 62%|██████▏   | 35511/57600 [6:13:19<3:46:16,  1.63it/s]
 62%|██████▏   | 35512/57600 [6:13:20<3:49:12,  1.61it/s]
 62%|██████▏   | 35513/57600 [6:13:21<3:56:17,  1.56it/s]
 62%|██████▏   | 35514/57600 [6:13:21<3:58:10,  1.55it/s]
 62%|██████▏   | 35515/57600 [6:13:22<3:54:27,  1.57it/s]
 62%|██████▏   | 35516/57600 [6:13:22<3:57:25,  1.55it/s]
 62%|██████▏   | 35517/57600 [6:13:23<3:50:24,  1.60it/s]
 62%|██████▏   | 35518/57600 [6:13:24<3:51:10,  1.59it/s]
 62%|██████▏   | 35519/57600 [6:13:24<3:54:35,  1.57it/s]
 62%|██████▏   | 35520/57600 [6:13:25<3:52:31,  1.58it/s]
                                                         
{'loss': 1.1937, 'learning_rate': 4.4620209059233445e-07, 'epoch': 392.05}

 62%|██████▏   | 35520/57600 [6:13:25<3:52:31,  1.58it/s]
 62%|██████▏   | 35521/57600 [6:13:26<3:53:15,  1.58it/s]
 62%|██████▏   | 35522/57600 [6:13:26<3:55:00,  1.57it/s]
 62%|██████▏   | 35523/57600 [6:13:27<3:57:40,  1.55it/s]
 62%|██████▏   | 35524/57600 [6:13:28<3:53:58,  1.57it/s]
 62%|██████▏   | 35525/57600 [6:13:28<3:53:16,  1.58it/s]
 62%|██████▏   | 35526/57600 [6:13:29<3:51:37,  1.59it/s]
 62%|██████▏   | 35527/57600 [6:13:29<3:51:05,  1.59it/s]
 62%|██████▏   | 35528/57600 [6:13:30<4:05:13,  1.50it/s]
 62%|██████▏   | 35529/57600 [6:13:31<3:51:58,  1.59it/s]
 62%|██████▏   | 35530/57600 [6:13:31<3:49:36,  1.60it/s]
 62%|██████▏   | 35531/57600 [6:13:32<3:49:50,  1.60it/s]
 62%|██████▏   | 35532/57600 [6:13:33<3:48:12,  1.61it/s]
 62%|██████▏   | 35533/57600 [6:13:33<3:47:59,  1.61it/s]
 62%|██████▏   | 35534/57600 [6:13:34<3:56:12,  1.56it/s]
 62%|██████▏   | 35535/57600 [6:13:34<3:54:50,  1.57it/s]
 62%|██████▏   | 35536/57600 [6:13:35<3:58:58,  1.54it/s]
 62%|██████▏   | 35537/57600 [6:13:36<3:54:43,  1.57it/s]
 62%|██████▏   | 35538/57600 [6:13:36<3:52:34,  1.58it/s]
 62%|██████▏   | 35539/57600 [6:13:37<3:55:38,  1.56it/s]
 62%|██████▏   | 35540/57600 [6:13:38<4:02:00,  1.52it/s]
                                                         
{'loss': 1.1341, 'learning_rate': 4.458885017421603e-07, 'epoch': 392.27}

 62%|██████▏   | 35540/57600 [6:13:38<4:02:00,  1.52it/s]
 62%|██████▏   | 35541/57600 [6:13:38<3:55:11,  1.56it/s]
 62%|██████▏   | 35542/57600 [6:13:39<3:45:41,  1.63it/s]
 62%|██████▏   | 35543/57600 [6:13:40<3:52:41,  1.58it/s]
 62%|██████▏   | 35544/57600 [6:13:40<3:53:57,  1.57it/s]
 62%|██████▏   | 35545/57600 [6:13:41<3:54:56,  1.56it/s]
 62%|██████▏   | 35546/57600 [6:13:42<3:55:47,  1.56it/s]
 62%|██████▏   | 35547/57600 [6:13:42<3:46:37,  1.62it/s]
 62%|██████▏   | 35548/57600 [6:13:43<3:43:20,  1.65it/s]
 62%|██████▏   | 35549/57600 [6:13:43<3:44:49,  1.63it/s]
 62%|██████▏   | 35550/57600 [6:13:44<3:48:41,  1.61it/s]
 62%|██████▏   | 35551/57600 [6:13:45<3:42:37,  1.65it/s]
 62%|██████▏   | 35552/57600 [6:13:45<3:47:19,  1.62it/s]
 62%|██████▏   | 35553/57600 [6:13:46<3:51:32,  1.59it/s]
 62%|██████▏   | 35554/57600 [6:13:46<3:51:21,  1.59it/s]
 62%|██████▏   | 35555/57600 [6:13:47<3:44:55,  1.63it/s]
 62%|██████▏   | 35556/57600 [6:13:48<3:46:33,  1.62it/s]
 62%|██████▏   | 35557/57600 [6:13:48<3:51:58,  1.58it/s]
 62%|██████▏   | 35558/57600 [6:13:49<3:56:00,  1.56it/s]
 62%|██████▏   | 35559/57600 [6:13:50<3:55:47,  1.56it/s]
 62%|██████▏   | 35560/57600 [6:13:50<4:05:34,  1.50it/s]
                                                         
{'loss': 1.1756, 'learning_rate': 4.45574912891986e-07, 'epoch': 392.49}

 62%|██████▏   | 35560/57600 [6:13:50<4:05:34,  1.50it/s]
 62%|██████▏   | 35561/57600 [6:13:51<3:59:31,  1.53it/s]
 62%|██████▏   | 35562/57600 [6:13:52<4:00:45,  1.53it/s]
 62%|██████▏   | 35563/57600 [6:13:52<4:00:52,  1.52it/s]
 62%|██████▏   | 35564/57600 [6:13:53<4:04:23,  1.50it/s]
 62%|██████▏   | 35565/57600 [6:13:54<3:58:52,  1.54it/s]
 62%|██████▏   | 35566/57600 [6:13:54<3:52:32,  1.58it/s]
 62%|██████▏   | 35567/57600 [6:13:55<3:48:29,  1.61it/s]
 62%|██████▏   | 35568/57600 [6:13:55<3:44:11,  1.64it/s]
 62%|██████▏   | 35569/57600 [6:13:56<3:43:02,  1.65it/s]
 62%|██████▏   | 35570/57600 [6:13:57<3:38:45,  1.68it/s]
 62%|██████▏   | 35571/57600 [6:13:57<3:48:25,  1.61it/s]
 62%|██████▏   | 35572/57600 [6:13:58<3:56:28,  1.55it/s]
 62%|██████▏   | 35573/57600 [6:13:59<3:55:51,  1.56it/s]
 62%|██████▏   | 35574/57600 [6:13:59<3:48:59,  1.60it/s]
 62%|██████▏   | 35575/57600 [6:14:00<3:58:18,  1.54it/s]
 62%|██████▏   | 35576/57600 [6:14:00<4:00:19,  1.53it/s]
 62%|██████▏   | 35577/57600 [6:14:01<3:59:10,  1.53it/s]
 62%|██████▏   | 35578/57600 [6:14:02<3:56:12,  1.55it/s]
 62%|██████▏   | 35579/57600 [6:14:02<3:54:22,  1.57it/s]
 62%|██████▏   | 35580/57600 [6:14:03<3:48:38,  1.61it/s]
                                                         
{'loss': 1.1754, 'learning_rate': 4.4526132404181187e-07, 'epoch': 392.72}

 62%|██████▏   | 35580/57600 [6:14:03<3:48:38,  1.61it/s]
 62%|██████▏   | 35581/57600 [6:14:04<3:49:28,  1.60it/s]
 62%|██████▏   | 35582/57600 [6:14:04<3:46:30,  1.62it/s]
 62%|██████▏   | 35583/57600 [6:14:05<3:43:41,  1.64it/s]
 62%|██████▏   | 35584/57600 [6:14:05<3:49:20,  1.60it/s]
 62%|██████▏   | 35585/57600 [6:14:06<4:00:05,  1.53it/s]
 62%|██████▏   | 35586/57600 [6:14:07<4:07:58,  1.48it/s]
 62%|██████▏   | 35587/57600 [6:14:07<3:59:01,  1.53it/s]
 62%|██████▏   | 35588/57600 [6:14:08<4:03:44,  1.51it/s]
 62%|██████▏   | 35589/57600 [6:14:09<3:57:54,  1.54it/s]
 62%|██████▏   | 35590/57600 [6:14:09<3:53:43,  1.57it/s]
 62%|██████▏   | 35591/57600 [6:14:10<3:51:04,  1.59it/s]
 62%|██████▏   | 35592/57600 [6:14:11<3:47:25,  1.61it/s]
 62%|██████▏   | 35593/57600 [6:14:11<3:49:09,  1.60it/s]
 62%|██████▏   | 35594/57600 [6:14:12<3:45:21,  1.63it/s]
 62%|██████▏   | 35595/57600 [6:14:12<3:43:33,  1.64it/s]
 62%|██████▏   | 35596/57600 [6:14:13<3:39:04,  1.67it/s]
 62%|██████▏   | 35597/57600 [6:14:14<3:39:48,  1.67it/s]
 62%|██████▏   | 35598/57600 [6:14:14<3:41:10,  1.66it/s]
 62%|██████▏   | 35599/57600 [6:14:15<3:42:14,  1.65it/s]
 62%|██████▏   | 35600/57600 [6:14:15<3:41:45,  1.65it/s]
                                                         
{'loss': 1.1678, 'learning_rate': 4.4494773519163756e-07, 'epoch': 392.94}

 62%|██████▏   | 35600/57600 [6:14:15<3:41:45,  1.65it/s]
 62%|██████▏   | 35601/57600 [6:14:16<3:45:44,  1.62it/s]
 62%|██████▏   | 35602/57600 [6:14:17<3:49:03,  1.60it/s]
 62%|██████▏   | 35603/57600 [6:14:17<3:57:35,  1.54it/s]
 62%|██████▏   | 35604/57600 [6:14:18<4:00:02,  1.53it/s]
 62%|██████▏   | 35605/57600 [6:14:19<3:52:19,  1.58it/s]
 62%|██████▏   | 35606/57600 [6:14:19<4:00:58,  1.52it/s]
 62%|██████▏   | 35607/57600 [6:14:20<3:56:20,  1.55it/s]
 62%|██████▏   | 35608/57600 [6:14:21<3:51:34,  1.58it/s]
 62%|██████▏   | 35609/57600 [6:14:21<3:54:44,  1.56it/s]
 62%|██████▏   | 35610/57600 [6:14:22<3:48:04,  1.61it/s]
 62%|██████▏   | 35611/57600 [6:14:23<3:52:21,  1.58it/s]
 62%|██████▏   | 35612/57600 [6:14:23<3:52:03,  1.58it/s]
 62%|██████▏   | 35613/57600 [6:14:24<3:46:47,  1.62it/s]
 62%|██████▏   | 35614/57600 [6:14:24<4:01:17,  1.52it/s]
 62%|██████▏   | 35615/57600 [6:14:25<3:54:19,  1.56it/s]
 62%|██████▏   | 35616/57600 [6:14:26<3:49:35,  1.60it/s]
 62%|██████▏   | 35617/57600 [6:14:26<3:52:44,  1.57it/s]
 62%|██████▏   | 35618/57600 [6:14:27<3:50:23,  1.59it/s]
 62%|██████▏   | 35619/57600 [6:14:28<3:46:02,  1.62it/s]
 62%|██████▏   | 35620/57600 [6:14:28<3:43:09,  1.64it/s]
                                                         
{'loss': 1.1252, 'learning_rate': 4.446341463414634e-07, 'epoch': 393.16}

 62%|██████▏   | 35620/57600 [6:14:28<3:43:09,  1.64it/s]
 62%|██████▏   | 35621/57600 [6:14:29<3:47:15,  1.61it/s]
 62%|██████▏   | 35622/57600 [6:14:29<3:54:35,  1.56it/s]
 62%|██████▏   | 35623/57600 [6:14:30<3:53:37,  1.57it/s]
 62%|██████▏   | 35624/57600 [6:14:31<3:49:01,  1.60it/s]
 62%|██████▏   | 35625/57600 [6:14:31<3:42:47,  1.64it/s]
 62%|██████▏   | 35626/57600 [6:14:32<3:45:32,  1.62it/s]
 62%|██████▏   | 35627/57600 [6:14:32<3:43:46,  1.64it/s]
 62%|██████▏   | 35628/57600 [6:14:33<3:44:08,  1.63it/s]
 62%|██████▏   | 35629/57600 [6:14:34<3:52:14,  1.58it/s]
 62%|██████▏   | 35630/57600 [6:14:34<3:51:22,  1.58it/s]
 62%|██████▏   | 35631/57600 [6:14:35<3:55:06,  1.56it/s]
 62%|██████▏   | 35632/57600 [6:14:36<3:54:34,  1.56it/s]
 62%|██████▏   | 35633/57600 [6:14:36<3:50:29,  1.59it/s]
 62%|██████▏   | 35634/57600 [6:14:37<3:50:21,  1.59it/s]
 62%|██████▏   | 35635/57600 [6:14:38<3:48:36,  1.60it/s]
 62%|██████▏   | 35636/57600 [6:14:38<3:45:45,  1.62it/s]
 62%|██████▏   | 35637/57600 [6:14:39<3:48:28,  1.60it/s]
 62%|██████▏   | 35638/57600 [6:14:39<3:51:01,  1.58it/s]
 62%|██████▏   | 35639/57600 [6:14:40<3:57:17,  1.54it/s]
 62%|██████▏   | 35640/57600 [6:14:41<3:51:07,  1.58it/s]
                                                         
{'loss': 1.1646, 'learning_rate': 4.4432055749128923e-07, 'epoch': 393.38}

 62%|██████▏   | 35640/57600 [6:14:41<3:51:07,  1.58it/s]
 62%|██████▏   | 35641/57600 [6:14:41<3:48:20,  1.60it/s]
 62%|██████▏   | 35642/57600 [6:14:42<3:46:36,  1.62it/s]
 62%|██████▏   | 35643/57600 [6:14:43<3:40:26,  1.66it/s]
 62%|██████▏   | 35644/57600 [6:14:43<3:35:58,  1.69it/s]
 62%|██████▏   | 35645/57600 [6:14:44<3:40:01,  1.66it/s]
 62%|██████▏   | 35646/57600 [6:14:44<3:48:21,  1.60it/s]
 62%|██████▏   | 35647/57600 [6:14:45<3:44:38,  1.63it/s]
 62%|██████▏   | 35648/57600 [6:14:46<3:49:53,  1.59it/s]
 62%|██████▏   | 35649/57600 [6:14:46<4:06:29,  1.48it/s]
 62%|██████▏   | 35650/57600 [6:14:47<4:03:16,  1.50it/s]
 62%|██████▏   | 35651/57600 [6:14:48<3:53:18,  1.57it/s]
 62%|██████▏   | 35652/57600 [6:14:48<3:57:48,  1.54it/s]
 62%|██████▏   | 35653/57600 [6:14:49<3:53:16,  1.57it/s]
 62%|██████▏   | 35654/57600 [6:14:50<3:52:34,  1.57it/s]
 62%|██████▏   | 35655/57600 [6:14:50<3:50:25,  1.59it/s]
 62%|██████▏   | 35656/57600 [6:14:51<3:53:29,  1.57it/s]
 62%|██████▏   | 35657/57600 [6:14:51<3:48:53,  1.60it/s]
 62%|██████▏   | 35658/57600 [6:14:52<3:46:19,  1.62it/s]
 62%|██████▏   | 35659/57600 [6:14:53<3:44:04,  1.63it/s]
 62%|██████▏   | 35660/57600 [6:14:53<3:47:14,  1.61it/s]
                                                         
{'loss': 1.1361, 'learning_rate': 4.44006968641115e-07, 'epoch': 393.6}

 62%|██████▏   | 35660/57600 [6:14:53<3:47:14,  1.61it/s]
 62%|██████▏   | 35661/57600 [6:14:54<3:49:04,  1.60it/s]
 62%|██████▏   | 35662/57600 [6:14:55<3:51:53,  1.58it/s]
 62%|██████▏   | 35663/57600 [6:14:55<3:53:37,  1.57it/s]
 62%|██████▏   | 35664/57600 [6:14:56<3:49:32,  1.59it/s]
 62%|██████▏   | 35665/57600 [6:14:56<3:46:29,  1.61it/s]
 62%|██████▏   | 35666/57600 [6:14:57<3:42:32,  1.64it/s]
 62%|██████▏   | 35667/57600 [6:14:58<3:49:41,  1.59it/s]
 62%|██████▏   | 35668/57600 [6:14:58<3:50:08,  1.59it/s]
 62%|██████▏   | 35669/57600 [6:14:59<3:47:32,  1.61it/s]
 62%|██████▏   | 35670/57600 [6:14:59<3:44:05,  1.63it/s]
 62%|██████▏   | 35671/57600 [6:15:00<3:40:41,  1.66it/s]
 62%|██████▏   | 35672/57600 [6:15:01<3:40:48,  1.66it/s]
 62%|██████▏   | 35673/57600 [6:15:01<3:46:56,  1.61it/s]
 62%|██████▏   | 35674/57600 [6:15:02<3:47:00,  1.61it/s]
 62%|██████▏   | 35675/57600 [6:15:03<3:42:10,  1.64it/s]
 62%|██████▏   | 35676/57600 [6:15:03<3:46:33,  1.61it/s]
 62%|██████▏   | 35677/57600 [6:15:04<3:54:57,  1.56it/s]
 62%|██████▏   | 35678/57600 [6:15:05<3:53:50,  1.56it/s]
 62%|██████▏   | 35679/57600 [6:15:05<3:56:10,  1.55it/s]
 62%|██████▏   | 35680/57600 [6:15:06<4:06:10,  1.48it/s]
                                                         
{'loss': 1.1557, 'learning_rate': 4.436933797909408e-07, 'epoch': 393.82}

 62%|██████▏   | 35680/57600 [6:15:06<4:06:10,  1.48it/s]
 62%|██████▏   | 35681/57600 [6:15:07<4:00:20,  1.52it/s]
 62%|██████▏   | 35682/57600 [6:15:07<3:54:34,  1.56it/s]
 62%|██████▏   | 35683/57600 [6:15:08<3:48:42,  1.60it/s]
 62%|██████▏   | 35684/57600 [6:15:08<3:56:53,  1.54it/s]
 62%|██████▏   | 35685/57600 [6:15:09<3:57:23,  1.54it/s]
 62%|██████▏   | 35686/57600 [6:15:10<3:57:39,  1.54it/s]
 62%|██████▏   | 35687/57600 [6:15:10<3:53:32,  1.56it/s]
 62%|██████▏   | 35688/57600 [6:15:11<3:54:37,  1.56it/s]
 62%|██████▏   | 35689/57600 [6:15:12<3:49:29,  1.59it/s]
 62%|██████▏   | 35690/57600 [6:15:12<3:46:45,  1.61it/s]
 62%|██████▏   | 35691/57600 [6:15:13<3:50:57,  1.58it/s]
 62%|██████▏   | 35692/57600 [6:15:13<3:48:00,  1.60it/s]
 62%|██████▏   | 35693/57600 [6:15:14<3:44:32,  1.63it/s]
 62%|██████▏   | 35694/57600 [6:15:15<3:49:23,  1.59it/s]
 62%|██████▏   | 35695/57600 [6:15:15<3:53:23,  1.56it/s]
 62%|██████▏   | 35696/57600 [6:15:16<3:48:31,  1.60it/s]
 62%|██████▏   | 35697/57600 [6:15:17<3:54:25,  1.56it/s]
 62%|██████▏   | 35698/57600 [6:15:17<3:56:33,  1.54it/s]
 62%|██████▏   | 35699/57600 [6:15:18<4:03:40,  1.50it/s]
 62%|██████▏   | 35700/57600 [6:15:19<4:04:31,  1.49it/s]
                                                         
{'loss': 1.1226, 'learning_rate': 4.433797909407665e-07, 'epoch': 394.04}

 62%|██████▏   | 35700/57600 [6:15:19<4:04:31,  1.49it/s]
 62%|██████▏   | 35701/57600 [6:15:19<4:05:33,  1.49it/s]
 62%|██████▏   | 35702/57600 [6:15:20<4:01:41,  1.51it/s]
 62%|██████▏   | 35703/57600 [6:15:21<3:52:22,  1.57it/s]
 62%|██████▏   | 35704/57600 [6:15:21<3:51:16,  1.58it/s]
 62%|██████▏   | 35705/57600 [6:15:22<3:51:15,  1.58it/s]
 62%|██████▏   | 35706/57600 [6:15:23<3:53:32,  1.56it/s]
 62%|██████▏   | 35707/57600 [6:15:23<3:46:39,  1.61it/s]
 62%|██████▏   | 35708/57600 [6:15:24<3:50:46,  1.58it/s]
 62%|██████▏   | 35709/57600 [6:15:24<3:56:25,  1.54it/s]
 62%|██████▏   | 35710/57600 [6:15:25<3:53:20,  1.56it/s]
 62%|██████▏   | 35711/57600 [6:15:26<3:55:31,  1.55it/s]
 62%|██████▏   | 35712/57600 [6:15:26<3:49:29,  1.59it/s]
 62%|██████▏   | 35713/57600 [6:15:27<3:41:32,  1.65it/s]
 62%|██████▏   | 35714/57600 [6:15:28<3:47:00,  1.61it/s]
 62%|██████▏   | 35715/57600 [6:15:28<3:51:52,  1.57it/s]
 62%|██████▏   | 35716/57600 [6:15:29<3:48:17,  1.60it/s]
 62%|██████▏   | 35717/57600 [6:15:30<3:58:11,  1.53it/s]
 62%|██████▏   | 35718/57600 [6:15:30<3:56:06,  1.54it/s]
 62%|██████▏   | 35719/57600 [6:15:31<3:49:07,  1.59it/s]
 62%|██████▏   | 35720/57600 [6:15:31<3:46:43,  1.61it/s]
                                                         
{'loss': 1.1205, 'learning_rate': 4.4306620209059234e-07, 'epoch': 394.26}

 62%|██████▏   | 35720/57600 [6:15:31<3:46:43,  1.61it/s]
 62%|██████▏   | 35721/57600 [6:15:32<3:42:52,  1.64it/s]
 62%|██████▏   | 35722/57600 [6:15:33<3:48:19,  1.60it/s]
 62%|██████▏   | 35723/57600 [6:15:33<3:51:31,  1.57it/s]
 62%|██████▏   | 35724/57600 [6:15:34<3:53:25,  1.56it/s]
 62%|██████▏   | 35725/57600 [6:15:34<3:47:28,  1.60it/s]
 62%|██████▏   | 35726/57600 [6:15:35<3:46:43,  1.61it/s]
 62%|██████▏   | 35727/57600 [6:15:36<3:45:01,  1.62it/s]
 62%|██████▏   | 35728/57600 [6:15:36<3:43:07,  1.63it/s]
 62%|██████▏   | 35729/57600 [6:15:37<3:41:12,  1.65it/s]
 62%|██████▏   | 35730/57600 [6:15:38<3:46:43,  1.61it/s]
 62%|██████▏   | 35731/57600 [6:15:38<3:49:51,  1.59it/s]
 62%|██████▏   | 35732/57600 [6:15:39<3:52:16,  1.57it/s]
 62%|██████▏   | 35733/57600 [6:15:39<3:46:45,  1.61it/s]
 62%|██████▏   | 35734/57600 [6:15:40<4:00:05,  1.52it/s]
 62%|██████▏   | 35735/57600 [6:15:41<4:16:10,  1.42it/s]
 62%|██████▏   | 35736/57600 [6:15:42<4:15:04,  1.43it/s]
 62%|██████▏   | 35737/57600 [6:15:42<4:07:39,  1.47it/s]
 62%|██████▏   | 35738/57600 [6:15:43<3:58:07,  1.53it/s]
 62%|██████▏   | 35739/57600 [6:15:44<3:53:10,  1.56it/s]
 62%|██████▏   | 35740/57600 [6:15:44<3:51:14,  1.58it/s]
                                                         
{'loss': 1.1669, 'learning_rate': 4.4275261324041804e-07, 'epoch': 394.48}

 62%|██████▏   | 35740/57600 [6:15:44<3:51:14,  1.58it/s]
 62%|██████▏   | 35741/57600 [6:15:45<3:47:51,  1.60it/s]
 62%|██████▏   | 35742/57600 [6:15:45<3:45:39,  1.61it/s]
 62%|██████▏   | 35743/57600 [6:15:46<3:47:41,  1.60it/s]
 62%|██████▏   | 35744/57600 [6:15:47<3:55:25,  1.55it/s]
 62%|██████▏   | 35745/57600 [6:15:47<3:57:56,  1.53it/s]
 62%|██████▏   | 35746/57600 [6:15:48<3:54:46,  1.55it/s]
 62%|██████▏   | 35747/57600 [6:15:49<4:07:11,  1.47it/s]
 62%|██████▏   | 35748/57600 [6:15:49<3:58:41,  1.53it/s]
 62%|██████▏   | 35749/57600 [6:15:50<3:49:53,  1.58it/s]
 62%|██████▏   | 35750/57600 [6:15:51<3:45:50,  1.61it/s]
 62%|██████▏   | 35751/57600 [6:15:51<3:45:20,  1.62it/s]
 62%|██████▏   | 35752/57600 [6:15:52<3:50:12,  1.58it/s]
 62%|██████▏   | 35753/57600 [6:15:52<3:46:43,  1.61it/s]
 62%|██████▏   | 35754/57600 [6:15:53<3:43:26,  1.63it/s]
 62%|██████▏   | 35755/57600 [6:15:54<3:45:36,  1.61it/s]
 62%|██████▏   | 35756/57600 [6:15:54<3:49:53,  1.58it/s]
 62%|██████▏   | 35757/57600 [6:15:55<3:48:57,  1.59it/s]
 62%|██████▏   | 35758/57600 [6:15:55<3:44:17,  1.62it/s]
 62%|██████▏   | 35759/57600 [6:15:56<3:50:05,  1.58it/s]
 62%|██████▏   | 35760/57600 [6:15:57<3:48:07,  1.60it/s]
                                                         
{'loss': 1.1618, 'learning_rate': 4.424390243902439e-07, 'epoch': 394.7}

 62%|██████▏   | 35760/57600 [6:15:57<3:48:07,  1.60it/s]
 62%|██████▏   | 35761/57600 [6:15:57<3:48:00,  1.60it/s]
 62%|██████▏   | 35762/57600 [6:15:58<3:47:45,  1.60it/s]
 62%|██████▏   | 35763/57600 [6:15:59<3:52:14,  1.57it/s]
 62%|██████▏   | 35764/57600 [6:15:59<3:46:19,  1.61it/s]
 62%|██████▏   | 35765/57600 [6:16:00<3:45:33,  1.61it/s]
 62%|██████▏   | 35766/57600 [6:16:01<3:48:31,  1.59it/s]
 62%|██████▏   | 35767/57600 [6:16:01<3:50:53,  1.58it/s]
 62%|██████▏   | 35768/57600 [6:16:02<3:58:02,  1.53it/s]
 62%|██████▏   | 35769/57600 [6:16:02<3:53:16,  1.56it/s]
 62%|██████▏   | 35770/57600 [6:16:03<3:50:50,  1.58it/s]
 62%|██████▏   | 35771/57600 [6:16:04<3:54:35,  1.55it/s]
 62%|██████▏   | 35772/57600 [6:16:04<3:49:28,  1.59it/s]
 62%|██████▏   | 35773/57600 [6:16:05<3:45:49,  1.61it/s]
 62%|██████▏   | 35774/57600 [6:16:06<3:47:48,  1.60it/s]
 62%|██████▏   | 35775/57600 [6:16:06<3:48:08,  1.59it/s]
 62%|██████▏   | 35776/57600 [6:16:07<3:56:35,  1.54it/s]
 62%|██████▏   | 35777/57600 [6:16:08<3:50:58,  1.57it/s]
 62%|██████▏   | 35778/57600 [6:16:08<3:49:14,  1.59it/s]
 62%|██████▏   | 35779/57600 [6:16:09<3:40:18,  1.65it/s]
 62%|██████▏   | 35780/57600 [6:16:09<3:47:48,  1.60it/s]
                                                         
{'loss': 1.1301, 'learning_rate': 4.421254355400697e-07, 'epoch': 394.92}

 62%|██████▏   | 35780/57600 [6:16:09<3:47:48,  1.60it/s]
 62%|██████▏   | 35781/57600 [6:16:10<3:43:29,  1.63it/s]
 62%|██████▏   | 35782/57600 [6:16:11<3:44:43,  1.62it/s]
 62%|██████▏   | 35783/57600 [6:16:11<3:40:56,  1.65it/s]
 62%|██████▏   | 35784/57600 [6:16:12<3:47:03,  1.60it/s]
 62%|██████▏   | 35785/57600 [6:16:12<3:45:37,  1.61it/s]
 62%|██████▏   | 35786/57600 [6:16:13<3:56:06,  1.54it/s]
 62%|██████▏   | 35787/57600 [6:16:14<3:51:56,  1.57it/s]
 62%|██████▏   | 35788/57600 [6:16:14<3:55:30,  1.54it/s]
 62%|██████▏   | 35789/57600 [6:16:15<3:47:02,  1.60it/s]
 62%|██████▏   | 35790/57600 [6:16:16<3:44:30,  1.62it/s]
 62%|██████▏   | 35791/57600 [6:16:16<3:45:43,  1.61it/s]
 62%|██████▏   | 35792/57600 [6:16:17<3:47:36,  1.60it/s]
 62%|██████▏   | 35793/57600 [6:16:18<3:53:04,  1.56it/s]
 62%|██████▏   | 35794/57600 [6:16:18<3:48:11,  1.59it/s]
 62%|██████▏   | 35795/57600 [6:16:19<3:44:33,  1.62it/s]
 62%|██████▏   | 35796/57600 [6:16:19<3:41:01,  1.64it/s]
 62%|██████▏   | 35797/57600 [6:16:20<3:38:15,  1.66it/s]
 62%|██████▏   | 35798/57600 [6:16:21<3:41:09,  1.64it/s]
 62%|██████▏   | 35799/57600 [6:16:21<3:51:58,  1.57it/s]
 62%|██████▏   | 35800/57600 [6:16:22<3:57:25,  1.53it/s]
                                                         
{'loss': 1.171, 'learning_rate': 4.4181184668989545e-07, 'epoch': 395.14}

 62%|██████▏   | 35800/57600 [6:16:22<3:57:25,  1.53it/s]
 62%|██████▏   | 35801/57600 [6:16:23<3:57:42,  1.53it/s]
 62%|██████▏   | 35802/57600 [6:16:23<3:55:27,  1.54it/s]
 62%|██████▏   | 35803/57600 [6:16:24<3:50:50,  1.57it/s]
 62%|██████▏   | 35804/57600 [6:16:25<3:53:05,  1.56it/s]
 62%|██████▏   | 35805/57600 [6:16:25<3:57:38,  1.53it/s]
 62%|██████▏   | 35806/57600 [6:16:26<3:54:11,  1.55it/s]
 62%|██████▏   | 35807/57600 [6:16:26<3:53:26,  1.56it/s]
 62%|██████▏   | 35808/57600 [6:16:27<3:48:11,  1.59it/s]
 62%|██████▏   | 35809/57600 [6:16:28<3:51:24,  1.57it/s]
 62%|██████▏   | 35810/57600 [6:16:28<3:52:51,  1.56it/s]
 62%|██████▏   | 35811/57600 [6:16:29<3:51:44,  1.57it/s]
 62%|██████▏   | 35812/57600 [6:16:30<3:45:17,  1.61it/s]
 62%|██████▏   | 35813/57600 [6:16:30<4:00:20,  1.51it/s]
 62%|██████▏   | 35814/57600 [6:16:31<3:59:11,  1.52it/s]
 62%|██████▏   | 35815/57600 [6:16:32<3:57:17,  1.53it/s]
 62%|██████▏   | 35816/57600 [6:16:32<3:49:08,  1.58it/s]
 62%|██████▏   | 35817/57600 [6:16:33<3:49:32,  1.58it/s]
 62%|██████▏   | 35818/57600 [6:16:33<3:53:02,  1.56it/s]
 62%|██████▏   | 35819/57600 [6:16:34<3:47:26,  1.60it/s]
 62%|██████▏   | 35820/57600 [6:16:35<3:47:26,  1.60it/s]
                                                         
{'loss': 1.1389, 'learning_rate': 4.4149825783972126e-07, 'epoch': 395.36}

 62%|██████▏   | 35820/57600 [6:16:35<3:47:26,  1.60it/s]
 62%|██████▏   | 35821/57600 [6:16:35<3:46:03,  1.61it/s]
 62%|██████▏   | 35822/57600 [6:16:36<3:43:05,  1.63it/s]
 62%|██████▏   | 35823/57600 [6:16:37<3:42:09,  1.63it/s]
 62%|██████▏   | 35824/57600 [6:16:37<3:50:45,  1.57it/s]
 62%|██████▏   | 35825/57600 [6:16:38<4:02:21,  1.50it/s]
 62%|██████▏   | 35826/57600 [6:16:39<4:02:21,  1.50it/s]
 62%|██████▏   | 35827/57600 [6:16:39<3:57:18,  1.53it/s]
 62%|██████▏   | 35828/57600 [6:16:40<3:58:35,  1.52it/s]
 62%|██████▏   | 35829/57600 [6:16:41<3:50:56,  1.57it/s]
 62%|██████▏   | 35830/57600 [6:16:41<3:49:20,  1.58it/s]
 62%|██████▏   | 35831/57600 [6:16:42<3:48:20,  1.59it/s]
 62%|██████▏   | 35832/57600 [6:16:42<3:43:32,  1.62it/s]
 62%|██████▏   | 35833/57600 [6:16:43<3:52:28,  1.56it/s]
 62%|██████▏   | 35834/57600 [6:16:44<3:50:57,  1.57it/s]
 62%|██████▏   | 35835/57600 [6:16:44<3:48:39,  1.59it/s]
 62%|██████▏   | 35836/57600 [6:16:45<3:47:12,  1.60it/s]
 62%|██████▏   | 35837/57600 [6:16:45<3:43:35,  1.62it/s]
 62%|██████▏   | 35838/57600 [6:16:46<3:46:28,  1.60it/s]
 62%|██████▏   | 35839/57600 [6:16:47<3:43:05,  1.63it/s]
 62%|██████▏   | 35840/57600 [6:16:47<3:52:10,  1.56it/s]
                                                         
{'loss': 1.1758, 'learning_rate': 4.41184668989547e-07, 'epoch': 395.58}

 62%|██████▏   | 35840/57600 [6:16:47<3:52:10,  1.56it/s]
 62%|██████▏   | 35841/57600 [6:16:48<3:50:13,  1.58it/s]
 62%|██████▏   | 35842/57600 [6:16:49<3:54:47,  1.54it/s]
 62%|██████▏   | 35843/57600 [6:16:49<3:48:51,  1.58it/s]
 62%|██████▏   | 35844/57600 [6:16:50<3:45:34,  1.61it/s]
 62%|██████▏   | 35845/57600 [6:16:51<3:51:16,  1.57it/s]
 62%|██████▏   | 35846/57600 [6:16:51<3:59:54,  1.51it/s]
 62%|██████▏   | 35847/57600 [6:16:52<3:53:26,  1.55it/s]
 62%|██████▏   | 35848/57600 [6:16:53<3:49:20,  1.58it/s]
 62%|██████▏   | 35849/57600 [6:16:53<3:50:18,  1.57it/s]
 62%|██████▏   | 35850/57600 [6:16:54<3:44:31,  1.61it/s]
 62%|██████▏   | 35851/57600 [6:16:54<3:44:21,  1.62it/s]
 62%|██████▏   | 35852/57600 [6:16:55<3:43:27,  1.62it/s]
 62%|██████▏   | 35853/57600 [6:16:56<3:41:45,  1.63it/s]
 62%|██████▏   | 35854/57600 [6:16:56<3:47:11,  1.60it/s]
 62%|██████▏   | 35855/57600 [6:16:57<3:56:37,  1.53it/s]
 62%|██████▏   | 35856/57600 [6:16:58<3:51:50,  1.56it/s]
 62%|██████▏   | 35857/57600 [6:16:58<3:46:51,  1.60it/s]
 62%|██████▏   | 35858/57600 [6:16:59<3:39:09,  1.65it/s]
 62%|██████▏   | 35859/57600 [6:16:59<3:36:39,  1.67it/s]
 62%|██████▏   | 35860/57600 [6:17:00<3:42:32,  1.63it/s]
                                                         
{'loss': 1.148, 'learning_rate': 4.408710801393728e-07, 'epoch': 395.81}

 62%|██████▏   | 35860/57600 [6:17:00<3:42:32,  1.63it/s]
 62%|██████▏   | 35861/57600 [6:17:01<3:40:29,  1.64it/s]
 62%|██████▏   | 35862/57600 [6:17:01<3:44:38,  1.61it/s]
 62%|██████▏   | 35863/57600 [6:17:02<3:46:53,  1.60it/s]
 62%|██████▏   | 35864/57600 [6:17:02<3:48:37,  1.58it/s]
 62%|██████▏   | 35865/57600 [6:17:03<3:53:38,  1.55it/s]
 62%|██████▏   | 35866/57600 [6:17:04<3:48:49,  1.58it/s]
 62%|██████▏   | 35867/57600 [6:17:04<3:45:11,  1.61it/s]
 62%|██████▏   | 35868/57600 [6:17:05<3:47:37,  1.59it/s]
 62%|██████▏   | 35869/57600 [6:17:06<3:47:34,  1.59it/s]
 62%|██████▏   | 35870/57600 [6:17:06<3:41:16,  1.64it/s]
 62%|██████▏   | 35871/57600 [6:17:07<3:53:18,  1.55it/s]
 62%|██████▏   | 35872/57600 [6:17:08<3:47:51,  1.59it/s]
 62%|██████▏   | 35873/57600 [6:17:08<3:44:39,  1.61it/s]
 62%|██████▏   | 35874/57600 [6:17:09<3:43:57,  1.62it/s]
 62%|██████▏   | 35875/57600 [6:17:09<3:50:06,  1.57it/s]
 62%|██████▏   | 35876/57600 [6:17:10<3:52:38,  1.56it/s]
 62%|██████▏   | 35877/57600 [6:17:11<3:48:17,  1.59it/s]
 62%|██████▏   | 35878/57600 [6:17:11<3:58:36,  1.52it/s]
 62%|██████▏   | 35879/57600 [6:17:12<3:49:51,  1.57it/s]
 62%|██████▏   | 35880/57600 [6:17:13<3:48:46,  1.58it/s]
                                                         
{'loss': 1.1375, 'learning_rate': 4.4055749128919857e-07, 'epoch': 396.03}

 62%|██████▏   | 35880/57600 [6:17:13<3:48:46,  1.58it/s]
 62%|██████▏   | 35881/57600 [6:17:13<3:45:36,  1.60it/s]
 62%|██████▏   | 35882/57600 [6:17:14<3:48:29,  1.58it/s]
 62%|██████▏   | 35883/57600 [6:17:14<3:49:20,  1.58it/s]
 62%|██████▏   | 35884/57600 [6:17:15<3:57:01,  1.53it/s]
 62%|██████▏   | 35885/57600 [6:17:16<3:53:13,  1.55it/s]
 62%|██████▏   | 35886/57600 [6:17:16<3:53:22,  1.55it/s]
 62%|██████▏   | 35887/57600 [6:17:17<3:53:40,  1.55it/s]
 62%|██████▏   | 35888/57600 [6:17:18<3:54:29,  1.54it/s]
 62%|██████▏   | 35889/57600 [6:17:18<3:57:21,  1.52it/s]
 62%|██████▏   | 35890/57600 [6:17:19<3:57:51,  1.52it/s]
 62%|██████▏   | 35891/57600 [6:17:20<3:49:48,  1.57it/s]
 62%|██████▏   | 35892/57600 [6:17:20<3:48:47,  1.58it/s]
 62%|██████▏   | 35893/57600 [6:17:21<3:41:32,  1.63it/s]
 62%|██████▏   | 35894/57600 [6:17:21<3:37:49,  1.66it/s]
 62%|██████▏   | 35895/57600 [6:17:22<3:43:19,  1.62it/s]
 62%|██████▏   | 35896/57600 [6:17:23<3:46:25,  1.60it/s]
 62%|██████▏   | 35897/57600 [6:17:23<3:46:31,  1.60it/s]
 62%|██████▏   | 35898/57600 [6:17:24<3:43:50,  1.62it/s]
 62%|██████▏   | 35899/57600 [6:17:25<3:41:39,  1.63it/s]
 62%|██████▏   | 35900/57600 [6:17:25<3:44:23,  1.61it/s]
                                                         
{'loss': 1.1157, 'learning_rate': 4.4024390243902437e-07, 'epoch': 396.25}

 62%|██████▏   | 35900/57600 [6:17:25<3:44:23,  1.61it/s]
 62%|██████▏   | 35901/57600 [6:17:26<3:41:00,  1.64it/s]
 62%|██████▏   | 35902/57600 [6:17:26<3:38:08,  1.66it/s]
 62%|██████▏   | 35903/57600 [6:17:27<3:38:13,  1.66it/s]
 62%|██████▏   | 35904/57600 [6:17:28<3:41:50,  1.63it/s]
 62%|██████▏   | 35905/57600 [6:17:28<3:52:13,  1.56it/s]
 62%|██████▏   | 35906/57600 [6:17:29<3:48:25,  1.58it/s]
 62%|██████▏   | 35907/57600 [6:17:30<3:49:24,  1.58it/s]
 62%|██████▏   | 35908/57600 [6:17:30<3:48:57,  1.58it/s]
 62%|██████▏   | 35909/57600 [6:17:31<3:42:43,  1.62it/s]
 62%|██████▏   | 35910/57600 [6:17:31<3:39:03,  1.65it/s]
 62%|██████▏   | 35911/57600 [6:17:32<3:37:54,  1.66it/s]
 62%|██████▏   | 35912/57600 [6:17:33<3:39:51,  1.64it/s]
 62%|██████▏   | 35913/57600 [6:17:33<3:39:12,  1.65it/s]
 62%|██████▏   | 35914/57600 [6:17:34<3:38:40,  1.65it/s]
 62%|██████▏   | 35915/57600 [6:17:34<3:51:06,  1.56it/s]
 62%|██████▏   | 35916/57600 [6:17:35<3:59:03,  1.51it/s]
 62%|██████▏   | 35917/57600 [6:17:36<3:56:57,  1.53it/s]
 62%|██████▏   | 35918/57600 [6:17:36<3:50:33,  1.57it/s]
 62%|██████▏   | 35919/57600 [6:17:37<3:54:57,  1.54it/s]
 62%|██████▏   | 35920/57600 [6:17:38<3:57:13,  1.52it/s]
                                                         
{'loss': 1.1181, 'learning_rate': 4.399303135888502e-07, 'epoch': 396.47}

 62%|██████▏   | 35920/57600 [6:17:38<3:57:13,  1.52it/s]
 62%|██████▏   | 35921/57600 [6:17:38<3:57:04,  1.52it/s]
 62%|██████▏   | 35922/57600 [6:17:39<3:58:42,  1.51it/s]
 62%|██████▏   | 35923/57600 [6:17:40<3:56:54,  1.52it/s]
 62%|██████▏   | 35924/57600 [6:17:40<3:54:36,  1.54it/s]
 62%|██████▏   | 35925/57600 [6:17:41<4:02:10,  1.49it/s]
 62%|██████▏   | 35926/57600 [6:17:42<3:56:07,  1.53it/s]
 62%|██████▏   | 35927/57600 [6:17:42<3:54:58,  1.54it/s]
 62%|██████▏   | 35928/57600 [6:17:43<3:48:27,  1.58it/s]
 62%|██████▏   | 35929/57600 [6:17:44<3:51:59,  1.56it/s]
 62%|██████▏   | 35930/57600 [6:17:44<3:48:17,  1.58it/s]
 62%|██████▏   | 35931/57600 [6:17:45<3:44:05,  1.61it/s]
 62%|██████▏   | 35932/57600 [6:17:45<3:46:07,  1.60it/s]
 62%|██████▏   | 35933/57600 [6:17:46<3:52:40,  1.55it/s]
 62%|██████▏   | 35934/57600 [6:17:47<3:52:54,  1.55it/s]
 62%|██████▏   | 35935/57600 [6:17:47<3:44:29,  1.61it/s]
 62%|██████▏   | 35936/57600 [6:17:48<3:44:01,  1.61it/s]
 62%|██████▏   | 35937/57600 [6:17:49<3:44:54,  1.61it/s]
 62%|██████▏   | 35938/57600 [6:17:49<3:41:03,  1.63it/s]
 62%|██████▏   | 35939/57600 [6:17:50<3:35:06,  1.68it/s]
 62%|██████▏   | 35940/57600 [6:17:50<3:43:08,  1.62it/s]
                                                         
{'loss': 1.1487, 'learning_rate': 4.3961672473867593e-07, 'epoch': 396.69}

 62%|██████▏   | 35940/57600 [6:17:50<3:43:08,  1.62it/s]
 62%|██████▏   | 35941/57600 [6:17:51<3:54:15,  1.54it/s]
 62%|██████▏   | 35942/57600 [6:17:52<3:50:40,  1.56it/s]
 62%|██████▏   | 35943/57600 [6:17:52<3:46:57,  1.59it/s]
 62%|██████▏   | 35944/57600 [6:17:53<3:53:26,  1.55it/s]
 62%|██████▏   | 35945/57600 [6:17:54<3:51:12,  1.56it/s]
 62%|██████▏   | 35946/57600 [6:17:54<3:55:15,  1.53it/s]
 62%|██████▏   | 35947/57600 [6:17:55<3:50:18,  1.57it/s]
 62%|██████▏   | 35948/57600 [6:17:56<3:48:28,  1.58it/s]
 62%|██████▏   | 35949/57600 [6:17:56<3:50:25,  1.57it/s]
 62%|██████▏   | 35950/57600 [6:17:57<3:45:50,  1.60it/s]
 62%|██████▏   | 35951/57600 [6:17:58<3:48:50,  1.58it/s]
 62%|██████▏   | 35952/57600 [6:17:58<3:44:11,  1.61it/s]
 62%|██████▏   | 35953/57600 [6:17:59<3:44:02,  1.61it/s]
 62%|██████▏   | 35954/57600 [6:17:59<3:42:49,  1.62it/s]
 62%|██████▏   | 35955/57600 [6:18:00<3:47:16,  1.59it/s]
 62%|██████▏   | 35956/57600 [6:18:01<3:47:17,  1.59it/s]
 62%|██████▏   | 35957/57600 [6:18:01<3:42:35,  1.62it/s]
 62%|██████▏   | 35958/57600 [6:18:02<3:51:23,  1.56it/s]
 62%|██████▏   | 35959/57600 [6:18:03<3:54:30,  1.54it/s]
 62%|██████▏   | 35960/57600 [6:18:03<3:51:39,  1.56it/s]
                                                         
{'loss': 1.1366, 'learning_rate': 4.393031358885017e-07, 'epoch': 396.91}

 62%|██████▏   | 35960/57600 [6:18:03<3:51:39,  1.56it/s]
 62%|██████▏   | 35961/57600 [6:18:04<3:52:50,  1.55it/s]
 62%|██████▏   | 35962/57600 [6:18:04<3:46:22,  1.59it/s]
 62%|██████▏   | 35963/57600 [6:18:05<3:37:57,  1.65it/s]
 62%|██████▏   | 35964/57600 [6:18:06<3:40:37,  1.63it/s]
 62%|██████▏   | 35965/57600 [6:18:06<3:44:44,  1.60it/s]
 62%|██████▏   | 35966/57600 [6:18:07<3:52:26,  1.55it/s]
 62%|██████▏   | 35967/57600 [6:18:08<3:53:29,  1.54it/s]
 62%|██████▏   | 35968/57600 [6:18:08<3:43:39,  1.61it/s]
 62%|██████▏   | 35969/57600 [6:18:09<3:55:26,  1.53it/s]
 62%|██████▏   | 35970/57600 [6:18:09<3:49:51,  1.57it/s]
 62%|██████▏   | 35971/57600 [6:18:10<3:51:39,  1.56it/s]
 62%|██████▏   | 35972/57600 [6:18:11<3:54:10,  1.54it/s]
 62%|██████▏   | 35973/57600 [6:18:11<3:49:12,  1.57it/s]
 62%|██████▏   | 35974/57600 [6:18:12<3:41:03,  1.63it/s]
 62%|██████▏   | 35975/57600 [6:18:13<3:54:25,  1.54it/s]
 62%|██████▏   | 35976/57600 [6:18:13<3:56:10,  1.53it/s]
 62%|██████▏   | 35977/57600 [6:18:14<3:53:44,  1.54it/s]
 62%|██████▏   | 35978/57600 [6:18:15<3:54:41,  1.54it/s]
 62%|██████▏   | 35979/57600 [6:18:15<3:50:07,  1.57it/s]
 62%|██████▏   | 35980/57600 [6:18:16<3:48:32,  1.58it/s]
                                                         
{'loss': 1.1268, 'learning_rate': 4.389895470383275e-07, 'epoch': 397.13}

 62%|██████▏   | 35980/57600 [6:18:16<3:48:32,  1.58it/s]
 62%|██████▏   | 35981/57600 [6:18:17<3:49:16,  1.57it/s]
 62%|██████▏   | 35982/57600 [6:18:17<3:45:14,  1.60it/s]
 62%|██████▏   | 35983/57600 [6:18:18<3:49:34,  1.57it/s]
 62%|██████▏   | 35984/57600 [6:18:18<3:52:48,  1.55it/s]
 62%|██████▏   | 35985/57600 [6:18:19<3:55:42,  1.53it/s]
 62%|██████▏   | 35986/57600 [6:18:20<3:50:26,  1.56it/s]
 62%|██████▏   | 35987/57600 [6:18:20<3:55:12,  1.53it/s]
 62%|██████▏   | 35988/57600 [6:18:21<3:50:28,  1.56it/s]
 62%|██████▏   | 35989/57600 [6:18:22<3:50:01,  1.57it/s]
 62%|██████▏   | 35990/57600 [6:18:22<3:37:53,  1.65it/s]
 62%|██████▏   | 35991/57600 [6:18:23<3:42:51,  1.62it/s]
 62%|██████▏   | 35992/57600 [6:18:23<3:40:22,  1.63it/s]
 62%|██████▏   | 35993/57600 [6:18:24<3:47:32,  1.58it/s]
 62%|██████▏   | 35994/57600 [6:18:25<3:41:28,  1.63it/s]
 62%|██████▏   | 35995/57600 [6:18:25<3:45:30,  1.60it/s]
 62%|██████▏   | 35996/57600 [6:18:26<3:46:26,  1.59it/s]
 62%|██████▏   | 35997/57600 [6:18:27<3:39:57,  1.64it/s]
 62%|██████▏   | 35998/57600 [6:18:27<3:38:32,  1.65it/s]
 62%|██████▏   | 35999/57600 [6:18:28<3:41:57,  1.62it/s]
 62%|██████▎   | 36000/57600 [6:18:28<3:43:59,  1.61it/s]
                                                         
{'loss': 1.1437, 'learning_rate': 4.386759581881533e-07, 'epoch': 397.35}

 62%|██████▎   | 36000/57600 [6:18:28<3:43:59,  1.61it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.99it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.15it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.82it/s]

100%|██████████| 6/6 [00:01<00:00,  3.48it/s]{'score': 46.87261082110182, 'counts': [138, 88, 59, 42], 'totals': [204, 174, 144, 115], 'precisions': [67.6470588235294, 50.57471264367816, 40.97222222222222, 36.52173913043478], 'bp': 0.9854017210216538, 'sys_len': 204, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 1.9691740274429321, 'eval_bleu': 46.8726, 'eval_gen_len': 8.2, 'eval_runtime': 3.1722, 'eval_samples_per_second': 9.457, 'eval_steps_per_second': 1.891, 'epoch': 397.35}

 62%|██████▎   | 36000/57600 [6:18:32<3:43:59,  1.61it/s]

100%|██████████| 6/6 [00:02<00:00,  3.48it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 13:12:44,966 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 63%|██████▎   | 36001/57600 [6:19:03<64:17:49, 10.72s/it]
 63%|██████▎   | 36002/57600 [6:19:03<46:04:16,  7.68s/it]
 63%|██████▎   | 36003/57600 [6:19:04<33:21:56,  5.56s/it]
 63%|██████▎   | 36004/57600 [6:19:05<24:48:41,  4.14s/it]
 63%|██████▎   | 36005/57600 [6:19:06<18:44:04,  3.12s/it]
 63%|██████▎   | 36006/57600 [6:19:06<14:23:19,  2.40s/it]
 63%|██████▎   | 36007/57600 [6:19:07<11:24:35,  1.90s/it]
 63%|██████▎   | 36008/57600 [6:19:08<9:11:07,  1.53s/it] 
 63%|██████▎   | 36009/57600 [6:19:08<7:33:18,  1.26s/it]
 63%|██████▎   | 36010/57600 [6:19:09<6:30:44,  1.09s/it]
 63%|██████▎   | 36011/57600 [6:19:10<5:51:24,  1.02it/s]
 63%|██████▎   | 36012/57600 [6:19:10<5:23:34,  1.11it/s]
 63%|██████▎   | 36013/57600 [6:19:11<4:56:13,  1.21it/s]
 63%|██████▎   | 36014/57600 [6:19:12<4:42:20,  1.27it/s]
 63%|██████▎   | 36015/57600 [6:19:12<4:20:11,  1.38it/s]
 63%|██████▎   | 36016/57600 [6:19:13<4:16:03,  1.40it/s]
 63%|██████▎   | 36017/57600 [6:19:14<4:13:40,  1.42it/s]
 63%|██████▎   | 36018/57600 [6:19:14<4:03:12,  1.48it/s]
 63%|██████▎   | 36019/57600 [6:19:15<4:06:32,  1.46it/s]
 63%|██████▎   | 36020/57600 [6:19:16<3:57:29,  1.51it/s]
                                                         
{'loss': 1.1699, 'learning_rate': 4.3836236933797904e-07, 'epoch': 397.57}

 63%|██████▎   | 36020/57600 [6:19:16<3:57:29,  1.51it/s]
 63%|██████▎   | 36021/57600 [6:19:16<3:55:29,  1.53it/s]
 63%|██████▎   | 36022/57600 [6:19:17<3:53:43,  1.54it/s]
 63%|██████▎   | 36023/57600 [6:19:18<3:59:17,  1.50it/s]
 63%|██████▎   | 36024/57600 [6:19:18<3:59:04,  1.50it/s]
 63%|██████▎   | 36025/57600 [6:19:19<3:55:25,  1.53it/s]
 63%|██████▎   | 36026/57600 [6:19:19<3:53:29,  1.54it/s]
 63%|██████▎   | 36027/57600 [6:19:20<3:56:52,  1.52it/s]
 63%|██████▎   | 36028/57600 [6:19:21<3:55:26,  1.53it/s]
 63%|██████▎   | 36029/57600 [6:19:22<4:02:38,  1.48it/s]
 63%|██████▎   | 36030/57600 [6:19:22<4:04:27,  1.47it/s]
 63%|██████▎   | 36031/57600 [6:19:23<3:59:11,  1.50it/s]
 63%|██████▎   | 36032/57600 [6:19:24<3:58:08,  1.51it/s]
 63%|██████▎   | 36033/57600 [6:19:24<4:01:09,  1.49it/s]
 63%|██████▎   | 36034/57600 [6:19:25<4:00:27,  1.49it/s]
 63%|██████▎   | 36035/57600 [6:19:25<3:54:23,  1.53it/s]
 63%|██████▎   | 36036/57600 [6:19:26<3:54:55,  1.53it/s]
 63%|██████▎   | 36037/57600 [6:19:27<3:54:08,  1.53it/s]
 63%|██████▎   | 36038/57600 [6:19:27<3:52:34,  1.55it/s]
 63%|██████▎   | 36039/57600 [6:19:28<4:04:46,  1.47it/s]
 63%|██████▎   | 36040/57600 [6:19:29<4:02:11,  1.48it/s]
                                                         
{'loss': 1.1739, 'learning_rate': 4.3804878048780485e-07, 'epoch': 397.79}

 63%|██████▎   | 36040/57600 [6:19:29<4:02:11,  1.48it/s]
 63%|██████▎   | 36041/57600 [6:19:29<3:53:49,  1.54it/s]
 63%|██████▎   | 36042/57600 [6:19:30<3:59:06,  1.50it/s]
 63%|██████▎   | 36043/57600 [6:19:31<3:57:03,  1.52it/s]
 63%|██████▎   | 36044/57600 [6:19:31<3:57:36,  1.51it/s]
 63%|██████▎   | 36045/57600 [6:19:32<3:54:37,  1.53it/s]
 63%|██████▎   | 36046/57600 [6:19:33<4:00:05,  1.50it/s]
 63%|██████▎   | 36047/57600 [6:19:33<3:53:00,  1.54it/s]
 63%|██████▎   | 36048/57600 [6:19:34<3:49:10,  1.57it/s]
 63%|██████▎   | 36049/57600 [6:19:35<3:51:47,  1.55it/s]
 63%|██████▎   | 36050/57600 [6:19:35<3:52:53,  1.54it/s]
 63%|██████▎   | 36051/57600 [6:19:36<3:56:52,  1.52it/s]
 63%|██████▎   | 36052/57600 [6:19:37<3:58:43,  1.50it/s]
 63%|██████▎   | 36053/57600 [6:19:37<3:50:58,  1.55it/s]
 63%|██████▎   | 36054/57600 [6:19:38<3:51:34,  1.55it/s]
 63%|██████▎   | 36055/57600 [6:19:39<3:56:47,  1.52it/s]
 63%|██████▎   | 36056/57600 [6:19:39<3:57:28,  1.51it/s]
 63%|██████▎   | 36057/57600 [6:19:40<3:52:09,  1.55it/s]
 63%|██████▎   | 36058/57600 [6:19:41<3:56:41,  1.52it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 63%|██████▎   | 36059/57600 [6:19:41<4:08:52,  1.44it/s]
 63%|██████▎   | 36060/57600 [6:19:42<4:01:59,  1.48it/s]
                                                         
{'loss': 1.1427, 'learning_rate': 4.377351916376307e-07, 'epoch': 398.01}

 63%|██████▎   | 36060/57600 [6:19:42<4:01:59,  1.48it/s]
 63%|██████▎   | 36061/57600 [6:19:43<3:52:10,  1.55it/s]
 63%|██████▎   | 36062/57600 [6:19:43<3:53:50,  1.54it/s]
 63%|██████▎   | 36063/57600 [6:19:44<4:01:46,  1.48it/s]
 63%|██████▎   | 36064/57600 [6:19:45<4:00:20,  1.49it/s]
 63%|██████▎   | 36065/57600 [6:19:45<3:56:21,  1.52it/s]
 63%|██████▎   | 36066/57600 [6:19:46<4:04:29,  1.47it/s]
 63%|██████▎   | 36067/57600 [6:19:47<4:11:30,  1.43it/s]
 63%|██████▎   | 36068/57600 [6:19:47<4:06:04,  1.46it/s]
 63%|██████▎   | 36069/57600 [6:19:48<3:59:54,  1.50it/s]
 63%|██████▎   | 36070/57600 [6:19:49<3:49:42,  1.56it/s]
 63%|██████▎   | 36071/57600 [6:19:49<3:48:12,  1.57it/s]
 63%|██████▎   | 36072/57600 [6:19:50<3:51:16,  1.55it/s]
 63%|██████▎   | 36073/57600 [6:19:51<3:52:50,  1.54it/s]
 63%|██████▎   | 36074/57600 [6:19:51<3:51:45,  1.55it/s]
 63%|██████▎   | 36075/57600 [6:19:52<4:02:32,  1.48it/s]
 63%|██████▎   | 36076/57600 [6:19:53<4:03:35,  1.47it/s]
 63%|██████▎   | 36077/57600 [6:19:53<4:02:34,  1.48it/s]
 63%|██████▎   | 36078/57600 [6:19:54<4:00:40,  1.49it/s]
 63%|██████▎   | 36079/57600 [6:19:55<4:03:05,  1.48it/s]
 63%|██████▎   | 36080/57600 [6:19:55<3:59:17,  1.50it/s]
                                                         
{'loss': 1.1355, 'learning_rate': 4.374216027874564e-07, 'epoch': 398.23}

 63%|██████▎   | 36080/57600 [6:19:55<3:59:17,  1.50it/s]
 63%|██████▎   | 36081/57600 [6:19:56<3:54:46,  1.53it/s]
 63%|██████▎   | 36082/57600 [6:19:57<3:56:26,  1.52it/s]
 63%|██████▎   | 36083/57600 [6:19:57<3:55:24,  1.52it/s]
 63%|██████▎   | 36084/57600 [6:19:58<3:51:10,  1.55it/s]
 63%|██████▎   | 36085/57600 [6:19:58<3:48:16,  1.57it/s]
 63%|██████▎   | 36086/57600 [6:19:59<3:43:39,  1.60it/s]
 63%|██████▎   | 36087/57600 [6:20:00<3:45:39,  1.59it/s]
 63%|██████▎   | 36088/57600 [6:20:00<3:46:57,  1.58it/s]
 63%|██████▎   | 36089/57600 [6:20:01<3:42:13,  1.61it/s]
 63%|██████▎   | 36090/57600 [6:20:02<3:44:05,  1.60it/s]
 63%|██████▎   | 36091/57600 [6:20:02<3:42:05,  1.61it/s]
 63%|██████▎   | 36092/57600 [6:20:03<3:40:52,  1.62it/s]
 63%|██████▎   | 36093/57600 [6:20:03<3:40:10,  1.63it/s]
 63%|██████▎   | 36094/57600 [6:20:04<3:33:53,  1.68it/s]
 63%|██████▎   | 36095/57600 [6:20:05<3:35:31,  1.66it/s]
 63%|██████▎   | 36096/57600 [6:20:05<3:47:35,  1.57it/s]
 63%|██████▎   | 36097/57600 [6:20:06<3:52:01,  1.54it/s]
 63%|██████▎   | 36098/57600 [6:20:07<3:47:53,  1.57it/s]
 63%|██████▎   | 36099/57600 [6:20:07<3:50:27,  1.55it/s]
 63%|██████▎   | 36100/57600 [6:20:08<3:47:08,  1.58it/s]
                                                         
{'loss': 1.1802, 'learning_rate': 4.3710801393728226e-07, 'epoch': 398.45}

 63%|██████▎   | 36100/57600 [6:20:08<3:47:08,  1.58it/s]
 63%|██████▎   | 36101/57600 [6:20:08<3:42:05,  1.61it/s]
 63%|██████▎   | 36102/57600 [6:20:09<3:43:04,  1.61it/s]
 63%|██████▎   | 36103/57600 [6:20:10<3:42:29,  1.61it/s]
 63%|██████▎   | 36104/57600 [6:20:10<3:40:31,  1.62it/s]
 63%|██████▎   | 36105/57600 [6:20:11<3:42:54,  1.61it/s]
 63%|██████▎   | 36106/57600 [6:20:11<3:37:53,  1.64it/s]
 63%|██████▎   | 36107/57600 [6:20:12<3:38:34,  1.64it/s]
 63%|██████▎   | 36108/57600 [6:20:13<4:00:21,  1.49it/s]
 63%|██████▎   | 36109/57600 [6:20:14<4:01:35,  1.48it/s]
 63%|██████▎   | 36110/57600 [6:20:14<4:05:04,  1.46it/s]
 63%|██████▎   | 36111/57600 [6:20:15<3:56:02,  1.52it/s]
 63%|██████▎   | 36112/57600 [6:20:16<3:59:36,  1.49it/s]
 63%|██████▎   | 36113/57600 [6:20:16<3:55:09,  1.52it/s]
 63%|██████▎   | 36114/57600 [6:20:17<3:54:10,  1.53it/s]
 63%|██████▎   | 36115/57600 [6:20:18<3:53:20,  1.53it/s]
 63%|██████▎   | 36116/57600 [6:20:18<3:57:20,  1.51it/s]
 63%|██████▎   | 36117/57600 [6:20:19<3:58:25,  1.50it/s]
 63%|██████▎   | 36118/57600 [6:20:20<3:59:10,  1.50it/s]
 63%|██████▎   | 36119/57600 [6:20:20<3:56:32,  1.51it/s]
 63%|██████▎   | 36120/57600 [6:20:21<3:50:40,  1.55it/s]
                                                         
{'loss': 1.171, 'learning_rate': 4.3679442508710796e-07, 'epoch': 398.68}

 63%|██████▎   | 36120/57600 [6:20:21<3:50:40,  1.55it/s]
 63%|██████▎   | 36121/57600 [6:20:22<3:58:57,  1.50it/s]
 63%|██████▎   | 36122/57600 [6:20:22<3:51:15,  1.55it/s]
 63%|██████▎   | 36123/57600 [6:20:23<3:50:04,  1.56it/s]
 63%|██████▎   | 36124/57600 [6:20:23<3:52:26,  1.54it/s]
 63%|██████▎   | 36125/57600 [6:20:24<3:56:46,  1.51it/s]
 63%|██████▎   | 36126/57600 [6:20:25<3:58:13,  1.50it/s]
 63%|██████▎   | 36127/57600 [6:20:25<3:55:46,  1.52it/s]
 63%|██████▎   | 36128/57600 [6:20:26<3:54:13,  1.53it/s]
 63%|██████▎   | 36129/57600 [6:20:27<3:52:03,  1.54it/s]
 63%|██████▎   | 36130/57600 [6:20:27<3:54:33,  1.53it/s]
 63%|██████▎   | 36131/57600 [6:20:28<3:51:08,  1.55it/s]
 63%|██████▎   | 36132/57600 [6:20:29<3:47:04,  1.58it/s]
 63%|██████▎   | 36133/57600 [6:20:29<3:38:24,  1.64it/s]
 63%|██████▎   | 36134/57600 [6:20:30<3:39:42,  1.63it/s]
 63%|██████▎   | 36135/57600 [6:20:30<3:50:30,  1.55it/s]
 63%|██████▎   | 36136/57600 [6:20:31<3:56:20,  1.51it/s]
 63%|██████▎   | 36137/57600 [6:20:32<3:51:24,  1.55it/s]
 63%|██████▎   | 36138/57600 [6:20:32<3:50:09,  1.55it/s]
 63%|██████▎   | 36139/57600 [6:20:33<4:03:06,  1.47it/s]
 63%|██████▎   | 36140/57600 [6:20:34<3:57:00,  1.51it/s]
                                                         
{'loss': 1.1463, 'learning_rate': 4.3648083623693377e-07, 'epoch': 398.9}

 63%|██████▎   | 36140/57600 [6:20:34<3:57:00,  1.51it/s]
 63%|██████▎   | 36141/57600 [6:20:34<3:52:37,  1.54it/s]
 63%|██████▎   | 36142/57600 [6:20:35<3:53:48,  1.53it/s]
 63%|██████▎   | 36143/57600 [6:20:36<4:00:40,  1.49it/s]
 63%|██████▎   | 36144/57600 [6:20:37<4:02:52,  1.47it/s]
 63%|██████▎   | 36145/57600 [6:20:37<4:11:24,  1.42it/s]
 63%|██████▎   | 36146/57600 [6:20:38<4:07:34,  1.44it/s]
 63%|██████▎   | 36147/57600 [6:20:39<4:13:24,  1.41it/s]
 63%|██████▎   | 36148/57600 [6:20:39<4:05:51,  1.45it/s]
 63%|██████▎   | 36149/57600 [6:20:40<4:05:14,  1.46it/s]
 63%|██████▎   | 36150/57600 [6:20:41<4:16:07,  1.40it/s]
 63%|██████▎   | 36151/57600 [6:20:41<4:03:17,  1.47it/s]
 63%|██████▎   | 36152/57600 [6:20:42<4:03:25,  1.47it/s]
 63%|██████▎   | 36153/57600 [6:20:43<3:57:46,  1.50it/s]
 63%|██████▎   | 36154/57600 [6:20:43<3:56:04,  1.51it/s]
 63%|██████▎   | 36155/57600 [6:20:44<3:51:35,  1.54it/s]
 63%|██████▎   | 36156/57600 [6:20:45<3:51:29,  1.54it/s]
 63%|██████▎   | 36157/57600 [6:20:45<3:55:22,  1.52it/s]
 63%|██████▎   | 36158/57600 [6:20:46<4:00:46,  1.48it/s]
 63%|██████▎   | 36159/57600 [6:20:47<3:56:09,  1.51it/s]
 63%|██████▎   | 36160/57600 [6:20:47<3:52:10,  1.54it/s]
                                                         
{'loss': 1.1102, 'learning_rate': 4.361672473867595e-07, 'epoch': 399.12}

 63%|██████▎   | 36160/57600 [6:20:47<3:52:10,  1.54it/s]
 63%|██████▎   | 36161/57600 [6:20:48<3:50:04,  1.55it/s]
 63%|██████▎   | 36162/57600 [6:20:49<3:47:05,  1.57it/s]
 63%|██████▎   | 36163/57600 [6:20:49<3:52:13,  1.54it/s]
 63%|██████▎   | 36164/57600 [6:20:50<3:50:10,  1.55it/s]
 63%|██████▎   | 36165/57600 [6:20:50<3:47:47,  1.57it/s]
 63%|██████▎   | 36166/57600 [6:20:51<3:48:03,  1.57it/s]
 63%|██████▎   | 36167/57600 [6:20:52<3:44:17,  1.59it/s]
 63%|██████▎   | 36168/57600 [6:20:52<3:45:38,  1.58it/s]
 63%|██████▎   | 36169/57600 [6:20:53<3:51:12,  1.54it/s]
 63%|██████▎   | 36170/57600 [6:20:54<3:54:28,  1.52it/s]
 63%|██████▎   | 36171/57600 [6:20:54<3:49:32,  1.56it/s]
 63%|██████▎   | 36172/57600 [6:20:55<3:59:43,  1.49it/s]
 63%|██████▎   | 36173/57600 [6:20:56<4:01:32,  1.48it/s]
 63%|██████▎   | 36174/57600 [6:20:56<4:02:14,  1.47it/s]
 63%|██████▎   | 36175/57600 [6:20:57<3:58:23,  1.50it/s]
 63%|██████▎   | 36176/57600 [6:20:58<3:57:08,  1.51it/s]
 63%|██████▎   | 36177/57600 [6:20:58<3:53:56,  1.53it/s]
 63%|██████▎   | 36178/57600 [6:20:59<3:56:31,  1.51it/s]
 63%|██████▎   | 36179/57600 [6:21:00<3:55:27,  1.52it/s]
 63%|██████▎   | 36180/57600 [6:21:00<3:53:47,  1.53it/s]
                                                         
{'loss': 1.1136, 'learning_rate': 4.358536585365853e-07, 'epoch': 399.34}

 63%|██████▎   | 36180/57600 [6:21:00<3:53:47,  1.53it/s]
 63%|██████▎   | 36181/57600 [6:21:01<3:53:05,  1.53it/s]
 63%|██████▎   | 36182/57600 [6:21:02<3:49:37,  1.55it/s]
 63%|██████▎   | 36183/57600 [6:21:02<3:43:49,  1.59it/s]
 63%|██████▎   | 36184/57600 [6:21:03<3:38:28,  1.63it/s]
 63%|██████▎   | 36185/57600 [6:21:03<3:49:33,  1.55it/s]
 63%|██████▎   | 36186/57600 [6:21:04<3:58:38,  1.50it/s]
 63%|██████▎   | 36187/57600 [6:21:05<3:52:28,  1.54it/s]
 63%|██████▎   | 36188/57600 [6:21:05<3:50:16,  1.55it/s]
 63%|██████▎   | 36189/57600 [6:21:06<3:55:19,  1.52it/s]
 63%|██████▎   | 36190/57600 [6:21:07<3:47:44,  1.57it/s]
 63%|██████▎   | 36191/57600 [6:21:07<3:46:27,  1.58it/s]
 63%|██████▎   | 36192/57600 [6:21:08<3:52:43,  1.53it/s]
 63%|██████▎   | 36193/57600 [6:21:09<3:46:34,  1.57it/s]
 63%|██████▎   | 36194/57600 [6:21:09<4:01:23,  1.48it/s]
 63%|██████▎   | 36195/57600 [6:21:10<3:56:49,  1.51it/s]
 63%|██████▎   | 36196/57600 [6:21:11<3:56:28,  1.51it/s]
 63%|██████▎   | 36197/57600 [6:21:11<3:50:29,  1.55it/s]
 63%|██████▎   | 36198/57600 [6:21:12<3:53:05,  1.53it/s]
 63%|██████▎   | 36199/57600 [6:21:13<3:52:58,  1.53it/s]
 63%|██████▎   | 36200/57600 [6:21:13<3:58:22,  1.50it/s]
                                                         
{'loss': 1.1909, 'learning_rate': 4.355400696864112e-07, 'epoch': 399.56}

 63%|██████▎   | 36200/57600 [6:21:13<3:58:22,  1.50it/s]
 63%|██████▎   | 36201/57600 [6:21:14<3:54:22,  1.52it/s]
 63%|██████▎   | 36202/57600 [6:21:15<3:51:57,  1.54it/s]
 63%|██████▎   | 36203/57600 [6:21:15<4:05:26,  1.45it/s]
 63%|██████▎   | 36204/57600 [6:21:16<4:01:09,  1.48it/s]
 63%|██████▎   | 36205/57600 [6:21:17<3:59:22,  1.49it/s]
 63%|██████▎   | 36206/57600 [6:21:17<4:03:34,  1.46it/s]
 63%|██████▎   | 36207/57600 [6:21:18<3:58:44,  1.49it/s]
 63%|██████▎   | 36208/57600 [6:21:19<4:00:31,  1.48it/s]
 63%|██████▎   | 36209/57600 [6:21:19<3:50:38,  1.55it/s]
 63%|██████▎   | 36210/57600 [6:21:20<3:50:28,  1.55it/s]
 63%|██████▎   | 36211/57600 [6:21:21<4:13:32,  1.41it/s]
 63%|██████▎   | 36212/57600 [6:21:22<4:16:29,  1.39it/s]
 63%|██████▎   | 36213/57600 [6:21:22<4:06:58,  1.44it/s]
 63%|██████▎   | 36214/57600 [6:21:23<3:58:00,  1.50it/s]
 63%|██████▎   | 36215/57600 [6:21:23<3:53:39,  1.53it/s]
 63%|██████▎   | 36216/57600 [6:21:24<3:48:59,  1.56it/s]
 63%|██████▎   | 36217/57600 [6:21:25<3:45:59,  1.58it/s]
 63%|██████▎   | 36218/57600 [6:21:25<3:50:10,  1.55it/s]
 63%|██████▎   | 36219/57600 [6:21:26<3:58:08,  1.50it/s]
 63%|██████▎   | 36220/57600 [6:21:27<4:08:22,  1.43it/s]
                                                         
{'loss': 1.1672, 'learning_rate': 4.352264808362369e-07, 'epoch': 399.78}

 63%|██████▎   | 36220/57600 [6:21:27<4:08:22,  1.43it/s]
 63%|██████▎   | 36221/57600 [6:21:27<4:04:38,  1.46it/s]
 63%|██████▎   | 36222/57600 [6:21:28<4:01:38,  1.47it/s]
 63%|██████▎   | 36223/57600 [6:21:29<4:04:16,  1.46it/s]
 63%|██████▎   | 36224/57600 [6:21:30<4:03:50,  1.46it/s]
 63%|██████▎   | 36225/57600 [6:21:30<4:03:44,  1.46it/s]
 63%|██████▎   | 36226/57600 [6:21:31<3:55:01,  1.52it/s]
 63%|██████▎   | 36227/57600 [6:21:31<3:55:21,  1.51it/s]
 63%|██████▎   | 36228/57600 [6:21:32<3:55:05,  1.52it/s]
 63%|██████▎   | 36229/57600 [6:21:33<3:53:14,  1.53it/s]
 63%|██████▎   | 36230/57600 [6:21:33<3:55:50,  1.51it/s]
 63%|██████▎   | 36231/57600 [6:21:34<3:48:08,  1.56it/s]
 63%|██████▎   | 36232/57600 [6:21:35<3:47:39,  1.56it/s]
 63%|██████▎   | 36233/57600 [6:21:35<3:48:05,  1.56it/s]
 63%|██████▎   | 36234/57600 [6:21:36<3:54:28,  1.52it/s]
 63%|██████▎   | 36235/57600 [6:21:37<3:49:47,  1.55it/s]
 63%|██████▎   | 36236/57600 [6:21:37<3:51:35,  1.54it/s]
 63%|██████▎   | 36237/57600 [6:21:38<3:52:59,  1.53it/s]
 63%|██████▎   | 36238/57600 [6:21:39<3:47:57,  1.56it/s]
 63%|██████▎   | 36239/57600 [6:21:39<3:45:54,  1.58it/s]
 63%|██████▎   | 36240/57600 [6:21:40<3:41:49,  1.60it/s]
                                                         
{'loss': 1.0953, 'learning_rate': 4.3491289198606274e-07, 'epoch': 400.0}

 63%|██████▎   | 36240/57600 [6:21:40<3:41:49,  1.60it/s]
 63%|██████▎   | 36241/57600 [6:21:40<3:47:25,  1.57it/s]
 63%|██████▎   | 36242/57600 [6:21:41<3:52:32,  1.53it/s]
 63%|██████▎   | 36243/57600 [6:21:42<3:48:48,  1.56it/s]
 63%|██████▎   | 36244/57600 [6:21:42<3:43:12,  1.59it/s]
 63%|██████▎   | 36245/57600 [6:21:43<3:46:13,  1.57it/s]
 63%|██████▎   | 36246/57600 [6:21:44<3:49:26,  1.55it/s]
 63%|██████▎   | 36247/57600 [6:21:44<3:50:26,  1.54it/s]
 63%|██████▎   | 36248/57600 [6:21:45<3:48:13,  1.56it/s]
 63%|██████▎   | 36249/57600 [6:21:46<3:44:43,  1.58it/s]
 63%|██████▎   | 36250/57600 [6:21:46<3:48:54,  1.55it/s]
 63%|██████▎   | 36251/57600 [6:21:47<3:50:08,  1.55it/s]
 63%|██████▎   | 36252/57600 [6:21:48<3:47:51,  1.56it/s]
 63%|██████▎   | 36253/57600 [6:21:48<3:42:58,  1.60it/s]
 63%|██████▎   | 36254/57600 [6:21:49<3:46:06,  1.57it/s]
 63%|██████▎   | 36255/57600 [6:21:49<3:40:34,  1.61it/s]
 63%|██████▎   | 36256/57600 [6:21:50<3:35:43,  1.65it/s]
 63%|██████▎   | 36257/57600 [6:21:51<3:39:54,  1.62it/s]
 63%|██████▎   | 36258/57600 [6:21:51<3:35:48,  1.65it/s]
 63%|██████▎   | 36259/57600 [6:21:52<3:42:17,  1.60it/s]
 63%|██████▎   | 36260/57600 [6:21:52<3:44:50,  1.58it/s]
                                                         
{'loss': 1.1247, 'learning_rate': 4.3459930313588844e-07, 'epoch': 400.22}

 63%|██████▎   | 36260/57600 [6:21:52<3:44:50,  1.58it/s]
 63%|██████▎   | 36261/57600 [6:21:53<3:41:38,  1.60it/s]
 63%|██████▎   | 36262/57600 [6:21:54<3:42:28,  1.60it/s]
 63%|██████▎   | 36263/57600 [6:21:54<3:41:24,  1.61it/s]
 63%|██████▎   | 36264/57600 [6:21:55<3:47:12,  1.57it/s]
 63%|██████▎   | 36265/57600 [6:21:56<3:50:48,  1.54it/s]
 63%|██████▎   | 36266/57600 [6:21:56<3:55:56,  1.51it/s]
 63%|██████▎   | 36267/57600 [6:21:57<3:53:16,  1.52it/s]
 63%|██████▎   | 36268/57600 [6:21:58<3:53:19,  1.52it/s]
 63%|██████▎   | 36269/57600 [6:21:58<3:48:54,  1.55it/s]
 63%|██████▎   | 36270/57600 [6:21:59<3:47:37,  1.56it/s]
 63%|██████▎   | 36271/57600 [6:22:00<3:48:30,  1.56it/s]
 63%|██████▎   | 36272/57600 [6:22:00<3:42:42,  1.60it/s]
 63%|██████▎   | 36273/57600 [6:22:01<3:40:51,  1.61it/s]
 63%|██████▎   | 36274/57600 [6:22:01<3:39:51,  1.62it/s]
 63%|██████▎   | 36275/57600 [6:22:02<3:46:30,  1.57it/s]
 63%|██████▎   | 36276/57600 [6:22:03<3:40:41,  1.61it/s]
 63%|██████▎   | 36277/57600 [6:22:03<3:41:20,  1.61it/s]
 63%|██████▎   | 36278/57600 [6:22:04<3:44:36,  1.58it/s]
 63%|██████▎   | 36279/57600 [6:22:05<3:44:52,  1.58it/s]
 63%|██████▎   | 36280/57600 [6:22:05<3:38:38,  1.63it/s]
                                                         
{'loss': 1.169, 'learning_rate': 4.342857142857143e-07, 'epoch': 400.44}

 63%|██████▎   | 36280/57600 [6:22:05<3:38:38,  1.63it/s]
 63%|██████▎   | 36281/57600 [6:22:06<3:35:32,  1.65it/s]
 63%|██████▎   | 36282/57600 [6:22:06<3:43:53,  1.59it/s]
 63%|██████▎   | 36283/57600 [6:22:07<3:40:20,  1.61it/s]
 63%|██████▎   | 36284/57600 [6:22:08<3:47:57,  1.56it/s]
 63%|██████▎   | 36285/57600 [6:22:08<3:44:12,  1.58it/s]
 63%|██████▎   | 36286/57600 [6:22:09<3:38:44,  1.62it/s]
 63%|██████▎   | 36287/57600 [6:22:09<3:36:03,  1.64it/s]
 63%|██████▎   | 36288/57600 [6:22:10<3:31:48,  1.68it/s]
 63%|██████▎   | 36289/57600 [6:22:11<3:33:24,  1.66it/s]
 63%|██████▎   | 36290/57600 [6:22:11<3:46:28,  1.57it/s]
 63%|██████▎   | 36291/57600 [6:22:12<3:38:19,  1.63it/s]
 63%|██████▎   | 36292/57600 [6:22:13<3:43:49,  1.59it/s]
 63%|██████▎   | 36293/57600 [6:22:13<3:46:34,  1.57it/s]
 63%|██████▎   | 36294/57600 [6:22:14<3:46:35,  1.57it/s]
 63%|██████▎   | 36295/57600 [6:22:14<3:40:26,  1.61it/s]
 63%|██████▎   | 36296/57600 [6:22:15<3:41:25,  1.60it/s]
 63%|██████▎   | 36297/57600 [6:22:16<3:46:33,  1.57it/s]
 63%|██████▎   | 36298/57600 [6:22:16<3:49:55,  1.54it/s]
 63%|██████▎   | 36299/57600 [6:22:17<3:43:45,  1.59it/s]
 63%|██████▎   | 36300/57600 [6:22:18<3:42:16,  1.60it/s]
                                                         
{'loss': 1.1571, 'learning_rate': 4.3397212543554e-07, 'epoch': 400.66}

 63%|██████▎   | 36300/57600 [6:22:18<3:42:16,  1.60it/s]
 63%|██████▎   | 36301/57600 [6:22:18<3:46:25,  1.57it/s]
 63%|██████▎   | 36302/57600 [6:22:19<3:57:17,  1.50it/s]
 63%|██████▎   | 36303/57600 [6:22:20<3:50:30,  1.54it/s]
 63%|██████▎   | 36304/57600 [6:22:20<3:46:19,  1.57it/s]
 63%|██████▎   | 36305/57600 [6:22:21<3:46:32,  1.57it/s]
 63%|██████▎   | 36306/57600 [6:22:22<3:43:16,  1.59it/s]
 63%|██████▎   | 36307/57600 [6:22:22<3:40:36,  1.61it/s]
 63%|██████▎   | 36308/57600 [6:22:23<3:37:56,  1.63it/s]
 63%|██████▎   | 36309/57600 [6:22:23<3:37:47,  1.63it/s]
 63%|██████▎   | 36310/57600 [6:22:24<3:36:27,  1.64it/s]
 63%|██████▎   | 36311/57600 [6:22:25<3:35:51,  1.64it/s]
 63%|██████▎   | 36312/57600 [6:22:25<3:38:05,  1.63it/s]
 63%|██████▎   | 36313/57600 [6:22:26<3:37:11,  1.63it/s]
 63%|██████▎   | 36314/57600 [6:22:26<3:35:27,  1.65it/s]
 63%|██████▎   | 36315/57600 [6:22:27<3:40:53,  1.61it/s]
 63%|██████▎   | 36316/57600 [6:22:28<3:43:44,  1.59it/s]
 63%|██████▎   | 36317/57600 [6:22:28<3:34:33,  1.65it/s]
 63%|██████▎   | 36318/57600 [6:22:29<3:55:15,  1.51it/s]
 63%|██████▎   | 36319/57600 [6:22:30<3:47:51,  1.56it/s]
 63%|██████▎   | 36320/57600 [6:22:30<3:42:40,  1.59it/s]
                                                         
{'loss': 1.2385, 'learning_rate': 4.3365853658536585e-07, 'epoch': 400.88}

 63%|██████▎   | 36320/57600 [6:22:30<3:42:40,  1.59it/s]
 63%|██████▎   | 36321/57600 [6:22:31<3:46:12,  1.57it/s]
 63%|██████▎   | 36322/57600 [6:22:32<3:49:05,  1.55it/s]
 63%|██████▎   | 36323/57600 [6:22:32<3:49:26,  1.55it/s]
 63%|██████▎   | 36324/57600 [6:22:33<3:46:50,  1.56it/s]
 63%|██████▎   | 36325/57600 [6:22:33<3:44:41,  1.58it/s]
 63%|██████▎   | 36326/57600 [6:22:34<3:45:08,  1.57it/s]
 63%|██████▎   | 36327/57600 [6:22:35<3:44:19,  1.58it/s]
 63%|██████▎   | 36328/57600 [6:22:35<3:47:30,  1.56it/s]
 63%|██████▎   | 36329/57600 [6:22:36<3:54:24,  1.51it/s]
 63%|██████▎   | 36330/57600 [6:22:37<3:53:53,  1.52it/s]
 63%|██████▎   | 36331/57600 [6:22:37<3:59:35,  1.48it/s]
 63%|██████▎   | 36332/57600 [6:22:38<3:55:04,  1.51it/s]
 63%|██████▎   | 36333/57600 [6:22:39<3:48:48,  1.55it/s]
 63%|██████▎   | 36334/57600 [6:22:39<3:43:09,  1.59it/s]
 63%|██████▎   | 36335/57600 [6:22:40<3:43:46,  1.58it/s]
 63%|██████▎   | 36336/57600 [6:22:40<3:38:58,  1.62it/s]
 63%|██████▎   | 36337/57600 [6:22:41<3:38:57,  1.62it/s]
 63%|██████▎   | 36338/57600 [6:22:42<3:42:14,  1.59it/s]
 63%|██████▎   | 36339/57600 [6:22:42<3:41:15,  1.60it/s]
 63%|██████▎   | 36340/57600 [6:22:43<3:43:49,  1.58it/s]
                                                         
{'loss': 1.1616, 'learning_rate': 4.3334494773519166e-07, 'epoch': 401.1}

 63%|██████▎   | 36340/57600 [6:22:43<3:43:49,  1.58it/s]
 63%|██████▎   | 36341/57600 [6:22:44<3:41:34,  1.60it/s]
 63%|██████▎   | 36342/57600 [6:22:44<3:40:05,  1.61it/s]
 63%|██████▎   | 36343/57600 [6:22:45<3:36:36,  1.64it/s]
 63%|██████▎   | 36344/57600 [6:22:45<3:41:45,  1.60it/s]
 63%|██████▎   | 36345/57600 [6:22:46<3:45:22,  1.57it/s]
 63%|██████▎   | 36346/57600 [6:22:47<3:57:01,  1.49it/s]
 63%|██████▎   | 36347/57600 [6:22:47<3:51:01,  1.53it/s]
 63%|██████▎   | 36348/57600 [6:22:48<3:45:11,  1.57it/s]
 63%|██████▎   | 36349/57600 [6:22:49<3:44:14,  1.58it/s]
 63%|██████▎   | 36350/57600 [6:22:49<3:43:40,  1.58it/s]
 63%|██████▎   | 36351/57600 [6:22:50<3:42:05,  1.59it/s]
 63%|██████▎   | 36352/57600 [6:22:51<3:35:12,  1.65it/s]
 63%|██████▎   | 36353/57600 [6:22:51<3:30:10,  1.68it/s]
 63%|██████▎   | 36354/57600 [6:22:52<3:38:51,  1.62it/s]
 63%|██████▎   | 36355/57600 [6:22:52<3:42:33,  1.59it/s]
 63%|██████▎   | 36356/57600 [6:22:53<3:39:44,  1.61it/s]
 63%|██████▎   | 36357/57600 [6:22:54<3:44:48,  1.57it/s]
 63%|██████▎   | 36358/57600 [6:22:54<3:44:49,  1.57it/s]
 63%|██████▎   | 36359/57600 [6:22:55<3:38:59,  1.62it/s]
 63%|██████▎   | 36360/57600 [6:22:56<3:41:17,  1.60it/s]
                                                         
{'loss': 1.1949, 'learning_rate': 4.330313588850174e-07, 'epoch': 401.32}

 63%|██████▎   | 36360/57600 [6:22:56<3:41:17,  1.60it/s]
 63%|██████▎   | 36361/57600 [6:22:56<3:43:32,  1.58it/s]
 63%|██████▎   | 36362/57600 [6:22:57<3:42:53,  1.59it/s]
 63%|██████▎   | 36363/57600 [6:22:57<3:45:19,  1.57it/s]
 63%|██████▎   | 36364/57600 [6:22:58<3:45:22,  1.57it/s]
 63%|██████▎   | 36365/57600 [6:22:59<3:47:25,  1.56it/s]
 63%|██████▎   | 36366/57600 [6:22:59<3:44:39,  1.58it/s]
 63%|██████▎   | 36367/57600 [6:23:00<3:55:46,  1.50it/s]
 63%|██████▎   | 36368/57600 [6:23:01<4:02:17,  1.46it/s]
 63%|██████▎   | 36369/57600 [6:23:02<4:06:05,  1.44it/s]
 63%|██████▎   | 36370/57600 [6:23:02<4:06:18,  1.44it/s]
 63%|██████▎   | 36371/57600 [6:23:03<3:53:19,  1.52it/s]
 63%|██████▎   | 36372/57600 [6:23:03<3:48:03,  1.55it/s]
 63%|██████▎   | 36373/57600 [6:23:04<3:47:23,  1.56it/s]
 63%|██████▎   | 36374/57600 [6:23:05<3:42:14,  1.59it/s]
 63%|██████▎   | 36375/57600 [6:23:05<3:35:03,  1.64it/s]
 63%|██████▎   | 36376/57600 [6:23:06<3:47:03,  1.56it/s]
 63%|██████▎   | 36377/57600 [6:23:07<3:43:45,  1.58it/s]
 63%|██████▎   | 36378/57600 [6:23:07<3:45:08,  1.57it/s]
 63%|██████▎   | 36379/57600 [6:23:08<3:38:14,  1.62it/s]
 63%|██████▎   | 36380/57600 [6:23:08<3:45:08,  1.57it/s]
                                                         
{'loss': 1.185, 'learning_rate': 4.327177700348432e-07, 'epoch': 401.55}

 63%|██████▎   | 36380/57600 [6:23:08<3:45:08,  1.57it/s]
 63%|██████▎   | 36381/57600 [6:23:09<3:43:28,  1.58it/s]
 63%|██████▎   | 36382/57600 [6:23:10<3:44:04,  1.58it/s]
 63%|██████▎   | 36383/57600 [6:23:10<3:45:16,  1.57it/s]
 63%|██████▎   | 36384/57600 [6:23:11<3:45:32,  1.57it/s]
 63%|██████▎   | 36385/57600 [6:23:12<3:42:00,  1.59it/s]
 63%|██████▎   | 36386/57600 [6:23:12<3:44:02,  1.58it/s]
 63%|██████▎   | 36387/57600 [6:23:13<3:39:29,  1.61it/s]
 63%|██████▎   | 36388/57600 [6:23:13<3:33:56,  1.65it/s]
 63%|██████▎   | 36389/57600 [6:23:14<3:34:36,  1.65it/s]
 63%|██████▎   | 36390/57600 [6:23:15<3:36:50,  1.63it/s]
 63%|██████▎   | 36391/57600 [6:23:15<3:34:19,  1.65it/s]
 63%|██████▎   | 36392/57600 [6:23:16<3:46:17,  1.56it/s]
 63%|██████▎   | 36393/57600 [6:23:17<3:43:47,  1.58it/s]
 63%|██████▎   | 36394/57600 [6:23:17<3:42:15,  1.59it/s]
 63%|██████▎   | 36395/57600 [6:23:18<3:46:02,  1.56it/s]
 63%|██████▎   | 36396/57600 [6:23:19<3:48:38,  1.55it/s]
 63%|██████▎   | 36397/57600 [6:23:19<3:42:35,  1.59it/s]
 63%|██████▎   | 36398/57600 [6:23:20<3:36:31,  1.63it/s]
 63%|██████▎   | 36399/57600 [6:23:20<3:34:48,  1.65it/s]
 63%|██████▎   | 36400/57600 [6:23:21<3:47:52,  1.55it/s]
                                                         
{'loss': 1.1708, 'learning_rate': 4.324041811846689e-07, 'epoch': 401.77}

 63%|██████▎   | 36400/57600 [6:23:21<3:47:52,  1.55it/s]
 63%|██████▎   | 36401/57600 [6:23:22<3:46:47,  1.56it/s]
 63%|██████▎   | 36402/57600 [6:23:22<3:40:48,  1.60it/s]
 63%|██████▎   | 36403/57600 [6:23:23<3:42:32,  1.59it/s]
 63%|██████▎   | 36404/57600 [6:23:24<3:44:24,  1.57it/s]
 63%|██████▎   | 36405/57600 [6:23:24<3:39:35,  1.61it/s]
 63%|██████▎   | 36406/57600 [6:23:25<3:43:54,  1.58it/s]
 63%|██████▎   | 36407/57600 [6:23:25<3:47:59,  1.55it/s]
 63%|██████▎   | 36408/57600 [6:23:26<3:45:44,  1.56it/s]
 63%|██████▎   | 36409/57600 [6:23:27<3:44:31,  1.57it/s]
 63%|██████▎   | 36410/57600 [6:23:27<3:47:58,  1.55it/s]
 63%|██████▎   | 36411/57600 [6:23:28<3:44:47,  1.57it/s]
 63%|██████▎   | 36412/57600 [6:23:29<3:42:58,  1.58it/s]
 63%|██████▎   | 36413/57600 [6:23:29<3:44:42,  1.57it/s]
 63%|██████▎   | 36414/57600 [6:23:30<3:46:41,  1.56it/s]
 63%|██████▎   | 36415/57600 [6:23:31<3:52:39,  1.52it/s]
 63%|██████▎   | 36416/57600 [6:23:31<3:50:20,  1.53it/s]
 63%|██████▎   | 36417/57600 [6:23:32<3:44:55,  1.57it/s]
 63%|██████▎   | 36418/57600 [6:23:33<3:53:30,  1.51it/s]
 63%|██████▎   | 36419/57600 [6:23:33<3:47:49,  1.55it/s]
 63%|██████▎   | 36420/57600 [6:23:34<3:45:11,  1.57it/s]
                                                         
{'loss': 1.1252, 'learning_rate': 4.320905923344948e-07, 'epoch': 401.99}

 63%|██████▎   | 36420/57600 [6:23:34<3:45:11,  1.57it/s]
 63%|██████▎   | 36421/57600 [6:23:34<3:45:30,  1.57it/s]
 63%|██████▎   | 36422/57600 [6:23:35<3:54:25,  1.51it/s]
 63%|██████▎   | 36423/57600 [6:23:36<3:54:24,  1.51it/s]
 63%|██████▎   | 36424/57600 [6:23:36<3:48:51,  1.54it/s]
 63%|██████▎   | 36425/57600 [6:23:37<3:41:19,  1.59it/s]
 63%|██████▎   | 36426/57600 [6:23:38<3:41:01,  1.60it/s]
 63%|██████▎   | 36427/57600 [6:23:38<3:42:27,  1.59it/s]
 63%|██████▎   | 36428/57600 [6:23:39<3:35:50,  1.63it/s]
 63%|██████▎   | 36429/57600 [6:23:39<3:35:12,  1.64it/s]
 63%|██████▎   | 36430/57600 [6:23:40<3:43:15,  1.58it/s]
 63%|██████▎   | 36431/57600 [6:23:41<3:39:34,  1.61it/s]
 63%|██████▎   | 36432/57600 [6:23:41<3:39:16,  1.61it/s]
 63%|██████▎   | 36433/57600 [6:23:42<3:45:33,  1.56it/s]
 63%|██████▎   | 36434/57600 [6:23:43<3:45:06,  1.57it/s]
 63%|██████▎   | 36435/57600 [6:23:43<3:39:39,  1.61it/s]
 63%|██████▎   | 36436/57600 [6:23:44<3:38:55,  1.61it/s]
 63%|██████▎   | 36437/57600 [6:23:45<3:42:18,  1.59it/s]
 63%|██████▎   | 36438/57600 [6:23:45<3:40:07,  1.60it/s]
 63%|██████▎   | 36439/57600 [6:23:46<3:40:41,  1.60it/s]
 63%|██████▎   | 36440/57600 [6:23:46<3:41:25,  1.59it/s]
                                                         
{'loss': 1.1517, 'learning_rate': 4.3177700348432047e-07, 'epoch': 402.21}

 63%|██████▎   | 36440/57600 [6:23:46<3:41:25,  1.59it/s]
 63%|██████▎   | 36441/57600 [6:23:47<3:41:50,  1.59it/s]
 63%|██████▎   | 36442/57600 [6:23:48<3:42:46,  1.58it/s]
 63%|██████▎   | 36443/57600 [6:23:48<3:49:00,  1.54it/s]
 63%|██████▎   | 36444/57600 [6:23:49<3:48:28,  1.54it/s]
 63%|██████▎   | 36445/57600 [6:23:50<3:47:03,  1.55it/s]
 63%|██████▎   | 36446/57600 [6:23:50<3:50:57,  1.53it/s]
 63%|██████▎   | 36447/57600 [6:23:51<3:44:53,  1.57it/s]
 63%|██████▎   | 36448/57600 [6:23:52<3:49:22,  1.54it/s]
 63%|██████▎   | 36449/57600 [6:23:52<3:48:25,  1.54it/s]
 63%|██████▎   | 36450/57600 [6:23:53<3:42:49,  1.58it/s]
 63%|██████▎   | 36451/57600 [6:23:53<3:43:32,  1.58it/s]
 63%|██████▎   | 36452/57600 [6:23:54<3:40:41,  1.60it/s]
 63%|██████▎   | 36453/57600 [6:23:55<3:45:58,  1.56it/s]
 63%|██████▎   | 36454/57600 [6:23:55<3:47:34,  1.55it/s]
 63%|██████▎   | 36455/57600 [6:23:56<3:46:18,  1.56it/s]
 63%|██████▎   | 36456/57600 [6:23:57<3:43:16,  1.58it/s]
 63%|██████▎   | 36457/57600 [6:23:57<3:45:57,  1.56it/s]
 63%|██████▎   | 36458/57600 [6:23:58<3:42:29,  1.58it/s]
 63%|██████▎   | 36459/57600 [6:23:59<3:42:43,  1.58it/s]
 63%|██████▎   | 36460/57600 [6:23:59<3:37:59,  1.62it/s]
                                                         
{'loss': 1.1446, 'learning_rate': 4.3146341463414633e-07, 'epoch': 402.43}

 63%|██████▎   | 36460/57600 [6:23:59<3:37:59,  1.62it/s]
 63%|██████▎   | 36461/57600 [6:24:00<3:35:03,  1.64it/s]
 63%|██████▎   | 36462/57600 [6:24:01<3:52:13,  1.52it/s]
 63%|██████▎   | 36463/57600 [6:24:01<3:42:34,  1.58it/s]
 63%|██████▎   | 36464/57600 [6:24:02<3:44:56,  1.57it/s]
 63%|██████▎   | 36465/57600 [6:24:02<3:45:53,  1.56it/s]
 63%|██████▎   | 36466/57600 [6:24:03<3:40:13,  1.60it/s]
 63%|██████▎   | 36467/57600 [6:24:04<3:42:46,  1.58it/s]
 63%|██████▎   | 36468/57600 [6:24:04<3:44:29,  1.57it/s]
 63%|██████▎   | 36469/57600 [6:24:05<3:43:09,  1.58it/s]
 63%|██████▎   | 36470/57600 [6:24:05<3:35:14,  1.64it/s]
 63%|██████▎   | 36471/57600 [6:24:06<3:37:03,  1.62it/s]
 63%|██████▎   | 36472/57600 [6:24:07<3:48:25,  1.54it/s]
 63%|██████▎   | 36473/57600 [6:24:07<3:45:45,  1.56it/s]
 63%|██████▎   | 36474/57600 [6:24:08<3:42:14,  1.58it/s]
 63%|██████▎   | 36475/57600 [6:24:09<3:41:13,  1.59it/s]
 63%|██████▎   | 36476/57600 [6:24:09<3:49:33,  1.53it/s]
 63%|██████▎   | 36477/57600 [6:24:10<3:52:25,  1.51it/s]
 63%|██████▎   | 36478/57600 [6:24:11<3:46:55,  1.55it/s]
 63%|██████▎   | 36479/57600 [6:24:11<3:39:16,  1.61it/s]
 63%|██████▎   | 36480/57600 [6:24:12<3:35:31,  1.63it/s]
                                                         
{'loss': 1.1321, 'learning_rate': 4.3114982578397213e-07, 'epoch': 402.65}

 63%|██████▎   | 36480/57600 [6:24:12<3:35:31,  1.63it/s]
 63%|██████▎   | 36481/57600 [6:24:12<3:33:48,  1.65it/s]
 63%|██████▎   | 36482/57600 [6:24:13<3:36:51,  1.62it/s]
 63%|██████▎   | 36483/57600 [6:24:14<3:38:38,  1.61it/s]
 63%|██████▎   | 36484/57600 [6:24:14<3:40:25,  1.60it/s]
 63%|██████▎   | 36485/57600 [6:24:15<3:38:36,  1.61it/s]
 63%|██████▎   | 36486/57600 [6:24:16<3:37:39,  1.62it/s]
 63%|██████▎   | 36487/57600 [6:24:16<3:48:01,  1.54it/s]
 63%|██████▎   | 36488/57600 [6:24:17<3:49:07,  1.54it/s]
 63%|██████▎   | 36489/57600 [6:24:18<3:45:34,  1.56it/s]
 63%|██████▎   | 36490/57600 [6:24:18<3:43:13,  1.58it/s]
 63%|██████▎   | 36491/57600 [6:24:19<3:39:58,  1.60it/s]
 63%|██████▎   | 36492/57600 [6:24:19<3:38:41,  1.61it/s]
 63%|██████▎   | 36493/57600 [6:24:20<3:37:55,  1.61it/s]
 63%|██████▎   | 36494/57600 [6:24:21<3:37:38,  1.62it/s]
 63%|██████▎   | 36495/57600 [6:24:21<3:40:24,  1.60it/s]
 63%|██████▎   | 36496/57600 [6:24:22<3:43:21,  1.57it/s]
 63%|██████▎   | 36497/57600 [6:24:23<3:44:18,  1.57it/s]
 63%|██████▎   | 36498/57600 [6:24:23<3:41:08,  1.59it/s]
 63%|██████▎   | 36499/57600 [6:24:24<3:42:27,  1.58it/s]
 63%|██████▎   | 36500/57600 [6:24:24<3:38:02,  1.61it/s]
                                                         
{'loss': 1.1393, 'learning_rate': 4.308362369337979e-07, 'epoch': 402.87}

 63%|██████▎   | 36500/57600 [6:24:24<3:38:02,  1.61it/s]
 63%|██████▎   | 36501/57600 [6:24:25<3:39:36,  1.60it/s]
 63%|██████▎   | 36502/57600 [6:24:26<3:38:28,  1.61it/s]
 63%|██████▎   | 36503/57600 [6:24:26<3:39:00,  1.61it/s]
 63%|██████▎   | 36504/57600 [6:24:27<3:32:18,  1.66it/s]
 63%|██████▎   | 36505/57600 [6:24:27<3:29:45,  1.68it/s]
 63%|██████▎   | 36506/57600 [6:24:28<3:34:14,  1.64it/s]
 63%|██████▎   | 36507/57600 [6:24:29<3:39:21,  1.60it/s]
 63%|██████▎   | 36508/57600 [6:24:29<3:47:06,  1.55it/s]
 63%|██████▎   | 36509/57600 [6:24:30<3:44:55,  1.56it/s]
 63%|██████▎   | 36510/57600 [6:24:31<3:38:00,  1.61it/s]
 63%|██████▎   | 36511/57600 [6:24:31<3:35:36,  1.63it/s]
 63%|██████▎   | 36512/57600 [6:24:32<3:51:10,  1.52it/s]
 63%|██████▎   | 36513/57600 [6:24:33<3:48:13,  1.54it/s]
 63%|██████▎   | 36514/57600 [6:24:33<3:46:39,  1.55it/s]
 63%|██████▎   | 36515/57600 [6:24:34<3:42:36,  1.58it/s]
 63%|██████▎   | 36516/57600 [6:24:34<3:39:28,  1.60it/s]
 63%|██████▎   | 36517/57600 [6:24:35<3:37:03,  1.62it/s]
 63%|██████▎   | 36518/57600 [6:24:36<3:39:04,  1.60it/s]
 63%|██████▎   | 36519/57600 [6:24:36<3:39:08,  1.60it/s]
 63%|██████▎   | 36520/57600 [6:24:37<3:38:16,  1.61it/s]
                                                         
{'loss': 1.1481, 'learning_rate': 4.305226480836237e-07, 'epoch': 403.09}

 63%|██████▎   | 36520/57600 [6:24:37<3:38:16,  1.61it/s]
 63%|██████▎   | 36521/57600 [6:24:38<3:41:11,  1.59it/s]
 63%|██████▎   | 36522/57600 [6:24:38<3:39:23,  1.60it/s]
 63%|██████▎   | 36523/57600 [6:24:39<3:43:11,  1.57it/s]
 63%|██████▎   | 36524/57600 [6:24:39<3:43:04,  1.57it/s]
 63%|██████▎   | 36525/57600 [6:24:40<3:44:27,  1.56it/s]
 63%|██████▎   | 36526/57600 [6:24:41<3:41:54,  1.58it/s]
 63%|██████▎   | 36527/57600 [6:24:41<3:42:04,  1.58it/s]
 63%|██████▎   | 36528/57600 [6:24:42<3:49:35,  1.53it/s]
 63%|██████▎   | 36529/57600 [6:24:43<3:43:32,  1.57it/s]
 63%|██████▎   | 36530/57600 [6:24:43<3:48:17,  1.54it/s]
 63%|██████▎   | 36531/57600 [6:24:44<3:43:58,  1.57it/s]
 63%|██████▎   | 36532/57600 [6:24:45<3:41:02,  1.59it/s]
 63%|██████▎   | 36533/57600 [6:24:45<3:34:48,  1.63it/s]
 63%|██████▎   | 36534/57600 [6:24:46<3:29:43,  1.67it/s]
 63%|██████▎   | 36535/57600 [6:24:46<3:30:26,  1.67it/s]
 63%|██████▎   | 36536/57600 [6:24:47<3:30:26,  1.67it/s]
 63%|██████▎   | 36537/57600 [6:24:47<3:29:20,  1.68it/s]
 63%|██████▎   | 36538/57600 [6:24:48<3:36:39,  1.62it/s]
 63%|██████▎   | 36539/57600 [6:24:49<3:42:37,  1.58it/s]
 63%|██████▎   | 36540/57600 [6:24:50<3:51:56,  1.51it/s]
                                                         
{'loss': 1.1189, 'learning_rate': 4.302090592334495e-07, 'epoch': 403.31}

 63%|██████▎   | 36540/57600 [6:24:50<3:51:56,  1.51it/s]
 63%|██████▎   | 36541/57600 [6:24:50<3:48:53,  1.53it/s]
 63%|██████▎   | 36542/57600 [6:24:51<3:42:35,  1.58it/s]
 63%|██████▎   | 36543/57600 [6:24:52<3:51:35,  1.52it/s]
 63%|██████▎   | 36544/57600 [6:24:52<3:44:06,  1.57it/s]
 63%|██████▎   | 36545/57600 [6:24:53<3:40:56,  1.59it/s]
 63%|██████▎   | 36546/57600 [6:24:53<3:54:14,  1.50it/s]
 63%|██████▎   | 36547/57600 [6:24:54<3:44:22,  1.56it/s]
 63%|██████▎   | 36548/57600 [6:24:55<3:40:40,  1.59it/s]
 63%|██████▎   | 36549/57600 [6:24:55<3:35:44,  1.63it/s]
 63%|██████▎   | 36550/57600 [6:24:56<3:37:22,  1.61it/s]
 63%|██████▎   | 36551/57600 [6:24:56<3:33:02,  1.65it/s]
 63%|██████▎   | 36552/57600 [6:24:57<3:31:56,  1.66it/s]
 63%|██████▎   | 36553/57600 [6:24:58<3:36:09,  1.62it/s]
 63%|██████▎   | 36554/57600 [6:24:58<3:44:15,  1.56it/s]
 63%|██████▎   | 36555/57600 [6:24:59<3:48:42,  1.53it/s]
 63%|██████▎   | 36556/57600 [6:25:00<3:39:14,  1.60it/s]
 63%|██████▎   | 36557/57600 [6:25:00<3:35:17,  1.63it/s]
 63%|██████▎   | 36558/57600 [6:25:01<3:37:00,  1.62it/s]
 63%|██████▎   | 36559/57600 [6:25:01<3:38:53,  1.60it/s]
 63%|██████▎   | 36560/57600 [6:25:02<3:39:14,  1.60it/s]
                                                         
{'loss': 1.1586, 'learning_rate': 4.2989547038327525e-07, 'epoch': 403.53}

 63%|██████▎   | 36560/57600 [6:25:02<3:39:14,  1.60it/s]
 63%|██████▎   | 36561/57600 [6:25:03<3:41:07,  1.59it/s]
 63%|██████▎   | 36562/57600 [6:25:03<3:39:39,  1.60it/s]
 63%|██████▎   | 36563/57600 [6:25:04<3:40:21,  1.59it/s]
 63%|██████▎   | 36564/57600 [6:25:05<3:37:26,  1.61it/s]
 63%|██████▎   | 36565/57600 [6:25:05<3:33:38,  1.64it/s]
 63%|██████▎   | 36566/57600 [6:25:06<3:32:25,  1.65it/s]
 63%|██████▎   | 36567/57600 [6:25:06<3:29:59,  1.67it/s]
 63%|██████▎   | 36568/57600 [6:25:07<3:29:01,  1.68it/s]
 63%|██████▎   | 36569/57600 [6:25:08<3:38:01,  1.61it/s]
 63%|██████▎   | 36570/57600 [6:25:08<3:41:41,  1.58it/s]
 63%|██████▎   | 36571/57600 [6:25:09<3:44:49,  1.56it/s]
 63%|██████▎   | 36572/57600 [6:25:09<3:34:59,  1.63it/s]
 63%|██████▎   | 36573/57600 [6:25:10<3:41:03,  1.59it/s]
 63%|██████▎   | 36574/57600 [6:25:11<3:38:18,  1.61it/s]
 63%|██████▎   | 36575/57600 [6:25:11<3:38:20,  1.60it/s]
 64%|██████▎   | 36576/57600 [6:25:12<3:31:17,  1.66it/s]
 64%|██████▎   | 36577/57600 [6:25:13<3:36:26,  1.62it/s]
 64%|██████▎   | 36578/57600 [6:25:13<3:38:01,  1.61it/s]
 64%|██████▎   | 36579/57600 [6:25:14<3:34:27,  1.63it/s]
 64%|██████▎   | 36580/57600 [6:25:14<3:33:53,  1.64it/s]
                                                         
{'loss': 1.184, 'learning_rate': 4.29581881533101e-07, 'epoch': 403.75}

 64%|██████▎   | 36580/57600 [6:25:14<3:33:53,  1.64it/s]
 64%|██████▎   | 36581/57600 [6:25:15<3:37:09,  1.61it/s]
 64%|██████▎   | 36582/57600 [6:25:16<3:42:33,  1.57it/s]
 64%|██████▎   | 36583/57600 [6:25:16<3:46:34,  1.55it/s]
 64%|██████▎   | 36584/57600 [6:25:17<3:40:22,  1.59it/s]
 64%|██████▎   | 36585/57600 [6:25:18<3:38:35,  1.60it/s]
 64%|██████▎   | 36586/57600 [6:25:18<3:31:35,  1.66it/s]
 64%|██████▎   | 36587/57600 [6:25:19<3:33:51,  1.64it/s]
 64%|██████▎   | 36588/57600 [6:25:19<3:41:46,  1.58it/s]
 64%|██████▎   | 36589/57600 [6:25:20<3:38:39,  1.60it/s]
 64%|██████▎   | 36590/57600 [6:25:21<3:45:13,  1.55it/s]
 64%|██████▎   | 36591/57600 [6:25:21<3:42:21,  1.57it/s]
 64%|██████▎   | 36592/57600 [6:25:22<3:36:43,  1.62it/s]
 64%|██████▎   | 36593/57600 [6:25:23<3:35:16,  1.63it/s]
 64%|██████▎   | 36594/57600 [6:25:23<3:45:47,  1.55it/s]
 64%|██████▎   | 36595/57600 [6:25:24<3:54:22,  1.49it/s]
 64%|██████▎   | 36596/57600 [6:25:25<3:47:21,  1.54it/s]
 64%|██████▎   | 36597/57600 [6:25:25<3:45:26,  1.55it/s]
 64%|██████▎   | 36598/57600 [6:25:26<3:43:29,  1.57it/s]
 64%|██████▎   | 36599/57600 [6:25:26<3:36:16,  1.62it/s]
 64%|██████▎   | 36600/57600 [6:25:27<3:37:38,  1.61it/s]
                                                         
{'loss': 1.1367, 'learning_rate': 4.292682926829268e-07, 'epoch': 403.97}

 64%|██████▎   | 36600/57600 [6:25:27<3:37:38,  1.61it/s]
 64%|██████▎   | 36601/57600 [6:25:28<3:36:10,  1.62it/s]
 64%|██████▎   | 36602/57600 [6:25:28<3:31:32,  1.65it/s]
 64%|██████▎   | 36603/57600 [6:25:29<3:40:54,  1.58it/s]
 64%|██████▎   | 36604/57600 [6:25:30<3:35:30,  1.62it/s]
 64%|██████▎   | 36605/57600 [6:25:30<3:32:03,  1.65it/s]
 64%|██████▎   | 36606/57600 [6:25:31<3:38:43,  1.60it/s]
 64%|██████▎   | 36607/57600 [6:25:31<3:31:06,  1.66it/s]
 64%|██████▎   | 36608/57600 [6:25:32<3:36:59,  1.61it/s]
 64%|██████▎   | 36609/57600 [6:25:33<3:36:27,  1.62it/s]
 64%|██████▎   | 36610/57600 [6:25:33<3:30:40,  1.66it/s]
 64%|██████▎   | 36611/57600 [6:25:34<3:33:42,  1.64it/s]
 64%|██████▎   | 36612/57600 [6:25:34<3:34:19,  1.63it/s]
 64%|██████▎   | 36613/57600 [6:25:35<3:31:10,  1.66it/s]
 64%|██████▎   | 36614/57600 [6:25:36<3:31:54,  1.65it/s]
 64%|██████▎   | 36615/57600 [6:25:36<3:35:06,  1.63it/s]
 64%|██████▎   | 36616/57600 [6:25:37<3:35:04,  1.63it/s]
 64%|██████▎   | 36617/57600 [6:25:37<3:34:37,  1.63it/s]
 64%|██████▎   | 36618/57600 [6:25:38<3:30:18,  1.66it/s]
 64%|██████▎   | 36619/57600 [6:25:39<3:43:48,  1.56it/s]
 64%|██████▎   | 36620/57600 [6:25:39<3:42:45,  1.57it/s]
                                                         
{'loss': 1.1961, 'learning_rate': 4.289547038327526e-07, 'epoch': 404.19}

 64%|██████▎   | 36620/57600 [6:25:39<3:42:45,  1.57it/s]
 64%|██████▎   | 36621/57600 [6:25:40<3:32:14,  1.65it/s]
 64%|██████▎   | 36622/57600 [6:25:41<3:29:40,  1.67it/s]
 64%|██████▎   | 36623/57600 [6:25:41<3:31:14,  1.65it/s]
 64%|██████▎   | 36624/57600 [6:25:42<3:30:27,  1.66it/s]
 64%|██████▎   | 36625/57600 [6:25:42<3:27:42,  1.68it/s]
 64%|██████▎   | 36626/57600 [6:25:43<3:31:08,  1.66it/s]
 64%|██████▎   | 36627/57600 [6:25:44<3:27:06,  1.69it/s]
 64%|██████▎   | 36628/57600 [6:25:44<3:24:09,  1.71it/s]
 64%|██████▎   | 36629/57600 [6:25:45<3:32:36,  1.64it/s]
 64%|██████▎   | 36630/57600 [6:25:45<3:28:10,  1.68it/s]
 64%|██████▎   | 36631/57600 [6:25:46<3:27:34,  1.68it/s]
 64%|██████▎   | 36632/57600 [6:25:47<3:34:52,  1.63it/s]
 64%|██████▎   | 36633/57600 [6:25:47<3:40:47,  1.58it/s]
 64%|██████▎   | 36634/57600 [6:25:48<3:39:44,  1.59it/s]
 64%|██████▎   | 36635/57600 [6:25:49<3:46:56,  1.54it/s]
 64%|██████▎   | 36636/57600 [6:25:49<3:59:27,  1.46it/s]
 64%|██████▎   | 36637/57600 [6:25:50<3:54:46,  1.49it/s]
 64%|██████▎   | 36638/57600 [6:25:51<3:55:19,  1.48it/s]
 64%|██████▎   | 36639/57600 [6:25:51<3:46:32,  1.54it/s]
 64%|██████▎   | 36640/57600 [6:25:52<3:38:05,  1.60it/s]
                                                         
{'loss': 1.1672, 'learning_rate': 4.2864111498257836e-07, 'epoch': 404.42}

 64%|██████▎   | 36640/57600 [6:25:52<3:38:05,  1.60it/s]
 64%|██████▎   | 36641/57600 [6:25:52<3:39:03,  1.59it/s]
 64%|██████▎   | 36642/57600 [6:25:53<3:31:59,  1.65it/s]
 64%|██████▎   | 36643/57600 [6:25:54<3:30:12,  1.66it/s]
 64%|██████▎   | 36644/57600 [6:25:54<3:26:51,  1.69it/s]
 64%|██████▎   | 36645/57600 [6:25:55<3:39:37,  1.59it/s]
 64%|██████▎   | 36646/57600 [6:25:56<3:47:34,  1.53it/s]
 64%|██████▎   | 36647/57600 [6:25:56<3:48:40,  1.53it/s]
 64%|██████▎   | 36648/57600 [6:25:57<3:47:41,  1.53it/s]
 64%|██████▎   | 36649/57600 [6:25:58<3:47:14,  1.54it/s]
 64%|██████▎   | 36650/57600 [6:25:58<3:43:33,  1.56it/s]
 64%|██████▎   | 36651/57600 [6:25:59<3:38:28,  1.60it/s]
 64%|██████▎   | 36652/57600 [6:25:59<3:40:45,  1.58it/s]
 64%|██████▎   | 36653/57600 [6:26:00<3:33:07,  1.64it/s]
 64%|██████▎   | 36654/57600 [6:26:01<3:39:48,  1.59it/s]
 64%|██████▎   | 36655/57600 [6:26:01<3:34:38,  1.63it/s]
 64%|██████▎   | 36656/57600 [6:26:02<3:39:14,  1.59it/s]
 64%|██████▎   | 36657/57600 [6:26:02<3:37:22,  1.61it/s]
 64%|██████▎   | 36658/57600 [6:26:03<3:37:49,  1.60it/s]
 64%|██████▎   | 36659/57600 [6:26:04<3:29:57,  1.66it/s]
 64%|██████▎   | 36660/57600 [6:26:04<3:25:51,  1.70it/s]
                                                         
{'loss': 1.128, 'learning_rate': 4.2832752613240416e-07, 'epoch': 404.64}

 64%|██████▎   | 36660/57600 [6:26:04<3:25:51,  1.70it/s]
 64%|██████▎   | 36661/57600 [6:26:05<3:29:36,  1.66it/s]
 64%|██████▎   | 36662/57600 [6:26:05<3:36:49,  1.61it/s]
 64%|██████▎   | 36663/57600 [6:26:06<3:39:39,  1.59it/s]
 64%|██████▎   | 36664/57600 [6:26:07<3:30:51,  1.65it/s]
 64%|██████▎   | 36665/57600 [6:26:07<3:34:21,  1.63it/s]
 64%|██████▎   | 36666/57600 [6:26:08<3:37:55,  1.60it/s]
 64%|██████▎   | 36667/57600 [6:26:09<3:34:00,  1.63it/s]
 64%|██████▎   | 36668/57600 [6:26:09<3:36:52,  1.61it/s]
 64%|██████▎   | 36669/57600 [6:26:10<3:43:55,  1.56it/s]
 64%|██████▎   | 36670/57600 [6:26:10<3:37:54,  1.60it/s]
 64%|██████▎   | 36671/57600 [6:26:11<3:37:47,  1.60it/s]
 64%|██████▎   | 36672/57600 [6:26:12<3:32:50,  1.64it/s]
 64%|██████▎   | 36673/57600 [6:26:12<3:36:48,  1.61it/s]
 64%|██████▎   | 36674/57600 [6:26:13<3:33:05,  1.64it/s]
 64%|██████▎   | 36675/57600 [6:26:13<3:29:34,  1.66it/s]
 64%|██████▎   | 36676/57600 [6:26:14<3:40:23,  1.58it/s]
 64%|██████▎   | 36677/57600 [6:26:15<3:38:09,  1.60it/s]
 64%|██████▎   | 36678/57600 [6:26:15<3:35:04,  1.62it/s]
 64%|██████▎   | 36679/57600 [6:26:16<3:42:03,  1.57it/s]
 64%|██████▎   | 36680/57600 [6:26:17<3:40:53,  1.58it/s]
                                                         
{'loss': 1.1529, 'learning_rate': 4.280139372822299e-07, 'epoch': 404.86}

 64%|██████▎   | 36680/57600 [6:26:17<3:40:53,  1.58it/s]
 64%|██████▎   | 36681/57600 [6:26:17<3:38:11,  1.60it/s]
 64%|██████▎   | 36682/57600 [6:26:18<3:36:00,  1.61it/s]
 64%|██████▎   | 36683/57600 [6:26:19<3:42:39,  1.57it/s]
 64%|██████▎   | 36684/57600 [6:26:19<3:40:55,  1.58it/s]
 64%|██████▎   | 36685/57600 [6:26:20<3:37:01,  1.61it/s]
 64%|██████▎   | 36686/57600 [6:26:20<3:37:52,  1.60it/s]
 64%|██████▎   | 36687/57600 [6:26:21<3:45:37,  1.54it/s]
 64%|██████▎   | 36688/57600 [6:26:22<3:42:41,  1.57it/s]
 64%|██████▎   | 36689/57600 [6:26:22<3:44:41,  1.55it/s]
 64%|██████▎   | 36690/57600 [6:26:23<3:50:47,  1.51it/s]
 64%|██████▎   | 36691/57600 [6:26:24<3:49:49,  1.52it/s]
 64%|██████▎   | 36692/57600 [6:26:24<3:46:36,  1.54it/s]
 64%|██████▎   | 36693/57600 [6:26:25<3:47:24,  1.53it/s]
 64%|██████▎   | 36694/57600 [6:26:26<3:57:41,  1.47it/s]
 64%|██████▎   | 36695/57600 [6:26:26<3:49:58,  1.52it/s]
 64%|██████▎   | 36696/57600 [6:26:27<3:42:38,  1.56it/s]
 64%|██████▎   | 36697/57600 [6:26:28<3:37:02,  1.61it/s]
 64%|██████▎   | 36698/57600 [6:26:28<3:32:29,  1.64it/s]
 64%|██████▎   | 36699/57600 [6:26:29<3:35:18,  1.62it/s]
 64%|██████▎   | 36700/57600 [6:26:29<3:34:53,  1.62it/s]
                                                         
{'loss': 1.1188, 'learning_rate': 4.277003484320557e-07, 'epoch': 405.08}

 64%|██████▎   | 36700/57600 [6:26:29<3:34:53,  1.62it/s]
 64%|██████▎   | 36701/57600 [6:26:30<3:42:10,  1.57it/s]
 64%|██████▎   | 36702/57600 [6:26:31<3:40:30,  1.58it/s]
 64%|██████▎   | 36703/57600 [6:26:31<3:33:59,  1.63it/s]
 64%|██████▎   | 36704/57600 [6:26:32<3:28:11,  1.67it/s]
 64%|██████▎   | 36705/57600 [6:26:33<3:30:52,  1.65it/s]
 64%|██████▎   | 36706/57600 [6:26:33<3:32:44,  1.64it/s]
 64%|██████▎   | 36707/57600 [6:26:34<3:35:40,  1.61it/s]
 64%|██████▎   | 36708/57600 [6:26:34<3:30:55,  1.65it/s]
 64%|██████▎   | 36709/57600 [6:26:35<3:34:43,  1.62it/s]
 64%|██████▎   | 36710/57600 [6:26:36<3:27:15,  1.68it/s]
 64%|██████▎   | 36711/57600 [6:26:36<3:38:00,  1.60it/s]
 64%|██████▎   | 36712/57600 [6:26:37<3:35:59,  1.61it/s]
 64%|██████▎   | 36713/57600 [6:26:37<3:39:23,  1.59it/s]
 64%|██████▎   | 36714/57600 [6:26:38<3:37:47,  1.60it/s]
 64%|██████▎   | 36715/57600 [6:26:39<3:34:59,  1.62it/s]
 64%|██████▎   | 36716/57600 [6:26:39<3:28:19,  1.67it/s]
 64%|██████▎   | 36717/57600 [6:26:40<3:33:05,  1.63it/s]
 64%|██████▎   | 36718/57600 [6:26:40<3:30:17,  1.65it/s]
 64%|██████▎   | 36719/57600 [6:26:41<3:35:50,  1.61it/s]
 64%|██████▍   | 36720/57600 [6:26:42<3:40:11,  1.58it/s]
                                                         
{'loss': 1.1708, 'learning_rate': 4.273867595818816e-07, 'epoch': 405.3}

 64%|██████▍   | 36720/57600 [6:26:42<3:40:11,  1.58it/s]
 64%|██████▍   | 36721/57600 [6:26:42<3:41:29,  1.57it/s]
 64%|██████▍   | 36722/57600 [6:26:43<3:42:37,  1.56it/s]
 64%|██████▍   | 36723/57600 [6:26:44<3:38:35,  1.59it/s]
 64%|██████▍   | 36724/57600 [6:26:44<3:35:02,  1.62it/s]
 64%|██████▍   | 36725/57600 [6:26:45<3:34:12,  1.62it/s]
 64%|██████▍   | 36726/57600 [6:26:46<3:40:02,  1.58it/s]
 64%|██████▍   | 36727/57600 [6:26:46<3:37:06,  1.60it/s]
 64%|██████▍   | 36728/57600 [6:26:47<3:32:53,  1.63it/s]
 64%|██████▍   | 36729/57600 [6:26:47<3:37:33,  1.60it/s]
 64%|██████▍   | 36730/57600 [6:26:48<3:39:15,  1.59it/s]
 64%|██████▍   | 36731/57600 [6:26:49<3:39:52,  1.58it/s]
 64%|██████▍   | 36732/57600 [6:26:49<3:32:41,  1.64it/s]
 64%|██████▍   | 36733/57600 [6:26:50<3:29:47,  1.66it/s]
 64%|██████▍   | 36734/57600 [6:26:50<3:30:09,  1.65it/s]
 64%|██████▍   | 36735/57600 [6:26:51<3:36:18,  1.61it/s]
 64%|██████▍   | 36736/57600 [6:26:52<3:33:16,  1.63it/s]
 64%|██████▍   | 36737/57600 [6:26:52<3:38:03,  1.59it/s]
 64%|██████▍   | 36738/57600 [6:26:53<3:34:16,  1.62it/s]
 64%|██████▍   | 36739/57600 [6:26:54<3:36:31,  1.61it/s]
 64%|██████▍   | 36740/57600 [6:26:54<3:43:56,  1.55it/s]
                                                         
{'loss': 1.1476, 'learning_rate': 4.270731707317073e-07, 'epoch': 405.52}

 64%|██████▍   | 36740/57600 [6:26:54<3:43:56,  1.55it/s]
 64%|██████▍   | 36741/57600 [6:26:55<3:48:54,  1.52it/s]
 64%|██████▍   | 36742/57600 [6:26:56<3:47:56,  1.53it/s]
 64%|██████▍   | 36743/57600 [6:26:56<3:44:29,  1.55it/s]
 64%|██████▍   | 36744/57600 [6:26:57<3:38:41,  1.59it/s]
 64%|██████▍   | 36745/57600 [6:26:58<3:42:04,  1.57it/s]
 64%|██████▍   | 36746/57600 [6:26:58<3:47:21,  1.53it/s]
 64%|██████▍   | 36747/57600 [6:26:59<3:44:14,  1.55it/s]
 64%|██████▍   | 36748/57600 [6:27:00<3:49:23,  1.51it/s]
 64%|██████▍   | 36749/57600 [6:27:00<3:43:51,  1.55it/s]
 64%|██████▍   | 36750/57600 [6:27:01<3:48:34,  1.52it/s]
 64%|██████▍   | 36751/57600 [6:27:01<3:48:20,  1.52it/s]
 64%|██████▍   | 36752/57600 [6:27:02<3:45:28,  1.54it/s]
 64%|██████▍   | 36753/57600 [6:27:03<3:40:34,  1.58it/s]
 64%|██████▍   | 36754/57600 [6:27:03<3:37:56,  1.59it/s]
 64%|██████▍   | 36755/57600 [6:27:04<3:41:35,  1.57it/s]
 64%|██████▍   | 36756/57600 [6:27:05<3:33:20,  1.63it/s]
 64%|██████▍   | 36757/57600 [6:27:05<3:41:02,  1.57it/s]
 64%|██████▍   | 36758/57600 [6:27:06<3:47:16,  1.53it/s]
 64%|██████▍   | 36759/57600 [6:27:07<3:47:35,  1.53it/s]
 64%|██████▍   | 36760/57600 [6:27:07<3:46:01,  1.54it/s]
                                                         
{'loss': 1.1487, 'learning_rate': 4.2675958188153314e-07, 'epoch': 405.74}

 64%|██████▍   | 36760/57600 [6:27:07<3:46:01,  1.54it/s]
 64%|██████▍   | 36761/57600 [6:27:08<3:43:16,  1.56it/s]
 64%|██████▍   | 36762/57600 [6:27:08<3:41:08,  1.57it/s]
 64%|██████▍   | 36763/57600 [6:27:09<3:36:10,  1.61it/s]
 64%|██████▍   | 36764/57600 [6:27:10<3:32:51,  1.63it/s]
 64%|██████▍   | 36765/57600 [6:27:10<3:32:52,  1.63it/s]
 64%|██████▍   | 36766/57600 [6:27:11<3:29:35,  1.66it/s]
 64%|██████▍   | 36767/57600 [6:27:12<3:44:01,  1.55it/s]
 64%|██████▍   | 36768/57600 [6:27:12<3:44:44,  1.54it/s]
 64%|██████▍   | 36769/57600 [6:27:13<3:47:22,  1.53it/s]
 64%|██████▍   | 36770/57600 [6:27:14<3:45:34,  1.54it/s]
 64%|██████▍   | 36771/57600 [6:27:14<3:43:41,  1.55it/s]
 64%|██████▍   | 36772/57600 [6:27:15<3:40:46,  1.57it/s]
 64%|██████▍   | 36773/57600 [6:27:15<3:35:13,  1.61it/s]
 64%|██████▍   | 36774/57600 [6:27:16<3:37:44,  1.59it/s]
 64%|██████▍   | 36775/57600 [6:27:17<3:40:02,  1.58it/s]
 64%|██████▍   | 36776/57600 [6:27:17<3:48:10,  1.52it/s]
 64%|██████▍   | 36777/57600 [6:27:18<3:47:42,  1.52it/s]
 64%|██████▍   | 36778/57600 [6:27:19<3:46:26,  1.53it/s]
 64%|██████▍   | 36779/57600 [6:27:19<3:36:27,  1.60it/s]
 64%|██████▍   | 36780/57600 [6:27:20<3:32:54,  1.63it/s]
                                                         
{'loss': 1.1542, 'learning_rate': 4.2644599303135883e-07, 'epoch': 405.96}

 64%|██████▍   | 36780/57600 [6:27:20<3:32:54,  1.63it/s]
 64%|██████▍   | 36781/57600 [6:27:20<3:29:58,  1.65it/s]
 64%|██████▍   | 36782/57600 [6:27:21<3:34:40,  1.62it/s]
 64%|██████▍   | 36783/57600 [6:27:22<3:39:37,  1.58it/s]
 64%|██████▍   | 36784/57600 [6:27:22<3:51:11,  1.50it/s]
 64%|██████▍   | 36785/57600 [6:27:23<3:48:52,  1.52it/s]
 64%|██████▍   | 36786/57600 [6:27:24<3:49:31,  1.51it/s]
 64%|██████▍   | 36787/57600 [6:27:24<3:50:44,  1.50it/s]
 64%|██████▍   | 36788/57600 [6:27:25<3:46:14,  1.53it/s]
 64%|██████▍   | 36789/57600 [6:27:26<3:37:06,  1.60it/s]
 64%|██████▍   | 36790/57600 [6:27:26<3:33:23,  1.63it/s]
 64%|██████▍   | 36791/57600 [6:27:27<3:34:31,  1.62it/s]
 64%|██████▍   | 36792/57600 [6:27:27<3:35:55,  1.61it/s]
 64%|██████▍   | 36793/57600 [6:27:28<3:38:07,  1.59it/s]
 64%|██████▍   | 36794/57600 [6:27:29<3:39:13,  1.58it/s]
 64%|██████▍   | 36795/57600 [6:27:29<3:37:56,  1.59it/s]
 64%|██████▍   | 36796/57600 [6:27:30<3:35:53,  1.61it/s]
 64%|██████▍   | 36797/57600 [6:27:31<3:38:47,  1.58it/s]
 64%|██████▍   | 36798/57600 [6:27:31<3:48:00,  1.52it/s]
 64%|██████▍   | 36799/57600 [6:27:32<3:44:51,  1.54it/s]
 64%|██████▍   | 36800/57600 [6:27:33<3:44:18,  1.55it/s]
                                                         
{'loss': 1.1383, 'learning_rate': 4.261324041811847e-07, 'epoch': 406.18}

 64%|██████▍   | 36800/57600 [6:27:33<3:44:18,  1.55it/s]
 64%|██████▍   | 36801/57600 [6:27:33<3:39:49,  1.58it/s]
 64%|██████▍   | 36802/57600 [6:27:34<3:36:08,  1.60it/s]
 64%|██████▍   | 36803/57600 [6:27:34<3:37:27,  1.59it/s]
 64%|██████▍   | 36804/57600 [6:27:35<3:31:27,  1.64it/s]
 64%|██████▍   | 36805/57600 [6:27:36<3:31:14,  1.64it/s]
 64%|██████▍   | 36806/57600 [6:27:36<3:32:33,  1.63it/s]
 64%|██████▍   | 36807/57600 [6:27:37<3:38:02,  1.59it/s]
 64%|██████▍   | 36808/57600 [6:27:38<3:35:41,  1.61it/s]
 64%|██████▍   | 36809/57600 [6:27:38<3:30:52,  1.64it/s]
 64%|██████▍   | 36810/57600 [6:27:39<3:29:14,  1.66it/s]
 64%|██████▍   | 36811/57600 [6:27:39<3:26:03,  1.68it/s]
 64%|██████▍   | 36812/57600 [6:27:40<3:23:48,  1.70it/s]
 64%|██████▍   | 36813/57600 [6:27:41<3:28:36,  1.66it/s]
 64%|██████▍   | 36814/57600 [6:27:41<3:31:30,  1.64it/s]
 64%|██████▍   | 36815/57600 [6:27:42<3:37:21,  1.59it/s]
 64%|██████▍   | 36816/57600 [6:27:42<3:30:55,  1.64it/s]
 64%|██████▍   | 36817/57600 [6:27:43<3:29:38,  1.65it/s]
 64%|██████▍   | 36818/57600 [6:27:44<3:29:16,  1.66it/s]
 64%|██████▍   | 36819/57600 [6:27:44<3:45:09,  1.54it/s]
 64%|██████▍   | 36820/57600 [6:27:45<3:39:51,  1.58it/s]
                                                         
{'loss': 1.1552, 'learning_rate': 4.258188153310104e-07, 'epoch': 406.4}

 64%|██████▍   | 36820/57600 [6:27:45<3:39:51,  1.58it/s]
 64%|██████▍   | 36821/57600 [6:27:46<3:41:39,  1.56it/s]
 64%|██████▍   | 36822/57600 [6:27:46<3:35:15,  1.61it/s]
 64%|██████▍   | 36823/57600 [6:27:47<3:35:59,  1.60it/s]
 64%|██████▍   | 36824/57600 [6:27:47<3:31:01,  1.64it/s]
 64%|██████▍   | 36825/57600 [6:27:48<3:35:55,  1.60it/s]
 64%|██████▍   | 36826/57600 [6:27:49<3:36:06,  1.60it/s]
 64%|██████▍   | 36827/57600 [6:27:49<3:40:29,  1.57it/s]
 64%|██████▍   | 36828/57600 [6:27:50<3:34:35,  1.61it/s]
 64%|██████▍   | 36829/57600 [6:27:51<3:35:20,  1.61it/s]
 64%|██████▍   | 36830/57600 [6:27:51<3:37:33,  1.59it/s]
 64%|██████▍   | 36831/57600 [6:27:52<3:34:21,  1.61it/s]
 64%|██████▍   | 36832/57600 [6:27:52<3:42:07,  1.56it/s]
 64%|██████▍   | 36833/57600 [6:27:53<3:42:04,  1.56it/s]
 64%|██████▍   | 36834/57600 [6:27:54<3:36:35,  1.60it/s]
 64%|██████▍   | 36835/57600 [6:27:54<3:45:04,  1.54it/s]
 64%|██████▍   | 36836/57600 [6:27:55<3:45:36,  1.53it/s]
 64%|██████▍   | 36837/57600 [6:27:56<3:38:28,  1.58it/s]
 64%|██████▍   | 36838/57600 [6:27:56<3:39:23,  1.58it/s]
 64%|██████▍   | 36839/57600 [6:27:57<3:40:27,  1.57it/s]
 64%|██████▍   | 36840/57600 [6:27:58<3:38:43,  1.58it/s]
                                                         
{'loss': 1.1357, 'learning_rate': 4.255052264808362e-07, 'epoch': 406.62}

 64%|██████▍   | 36840/57600 [6:27:58<3:38:43,  1.58it/s]
 64%|██████▍   | 36841/57600 [6:27:58<3:45:14,  1.54it/s]
 64%|██████▍   | 36842/57600 [6:27:59<3:40:07,  1.57it/s]
 64%|██████▍   | 36843/57600 [6:27:59<3:32:24,  1.63it/s]
 64%|██████▍   | 36844/57600 [6:28:00<3:32:24,  1.63it/s]
 64%|██████▍   | 36845/57600 [6:28:01<3:29:57,  1.65it/s]
 64%|██████▍   | 36846/57600 [6:28:01<3:34:12,  1.61it/s]
 64%|██████▍   | 36847/57600 [6:28:02<3:35:13,  1.61it/s]
 64%|██████▍   | 36848/57600 [6:28:03<3:38:40,  1.58it/s]
 64%|██████▍   | 36849/57600 [6:28:03<3:35:47,  1.60it/s]
 64%|██████▍   | 36850/57600 [6:28:04<3:37:14,  1.59it/s]
 64%|██████▍   | 36851/57600 [6:28:04<3:36:06,  1.60it/s]
 64%|██████▍   | 36852/57600 [6:28:05<3:33:54,  1.62it/s]
 64%|██████▍   | 36853/57600 [6:28:06<3:48:40,  1.51it/s]
 64%|██████▍   | 36854/57600 [6:28:06<3:39:07,  1.58it/s]
 64%|██████▍   | 36855/57600 [6:28:07<3:52:55,  1.48it/s]
 64%|██████▍   | 36856/57600 [6:28:08<3:45:55,  1.53it/s]
 64%|██████▍   | 36857/57600 [6:28:08<3:39:48,  1.57it/s]
 64%|██████▍   | 36858/57600 [6:28:09<3:46:17,  1.53it/s]
 64%|██████▍   | 36859/57600 [6:28:10<3:43:05,  1.55it/s]
 64%|██████▍   | 36860/57600 [6:28:10<3:47:42,  1.52it/s]
                                                         
{'loss': 1.1506, 'learning_rate': 4.2519163763066205e-07, 'epoch': 406.84}

 64%|██████▍   | 36860/57600 [6:28:10<3:47:42,  1.52it/s]
 64%|██████▍   | 36861/57600 [6:28:11<3:41:19,  1.56it/s]
 64%|██████▍   | 36862/57600 [6:28:12<3:43:25,  1.55it/s]
 64%|██████▍   | 36863/57600 [6:28:12<3:44:57,  1.54it/s]
 64%|██████▍   | 36864/57600 [6:28:13<3:39:57,  1.57it/s]
 64%|██████▍   | 36865/57600 [6:28:13<3:36:52,  1.59it/s]
 64%|██████▍   | 36866/57600 [6:28:14<3:35:47,  1.60it/s]
 64%|██████▍   | 36867/57600 [6:28:15<3:28:59,  1.65it/s]
 64%|██████▍   | 36868/57600 [6:28:15<3:31:21,  1.63it/s]
 64%|██████▍   | 36869/57600 [6:28:16<3:38:12,  1.58it/s]
 64%|██████▍   | 36870/57600 [6:28:17<3:38:00,  1.58it/s]
 64%|██████▍   | 36871/57600 [6:28:17<3:32:50,  1.62it/s]
 64%|██████▍   | 36872/57600 [6:28:18<3:30:00,  1.65it/s]
 64%|██████▍   | 36873/57600 [6:28:18<3:27:10,  1.67it/s]
 64%|██████▍   | 36874/57600 [6:28:19<3:24:23,  1.69it/s]
 64%|██████▍   | 36875/57600 [6:28:20<3:33:37,  1.62it/s]
 64%|██████▍   | 36876/57600 [6:28:20<3:28:19,  1.66it/s]
 64%|██████▍   | 36877/57600 [6:28:21<3:35:14,  1.60it/s]
 64%|██████▍   | 36878/57600 [6:28:21<3:36:02,  1.60it/s]
 64%|██████▍   | 36879/57600 [6:28:22<3:29:56,  1.64it/s]
 64%|██████▍   | 36880/57600 [6:28:23<3:33:08,  1.62it/s]
                                                         
{'loss': 1.1682, 'learning_rate': 4.2487804878048775e-07, 'epoch': 407.06}

 64%|██████▍   | 36880/57600 [6:28:23<3:33:08,  1.62it/s]
 64%|██████▍   | 36881/57600 [6:28:23<3:29:19,  1.65it/s]
 64%|██████▍   | 36882/57600 [6:28:24<3:25:48,  1.68it/s]
 64%|██████▍   | 36883/57600 [6:28:24<3:33:38,  1.62it/s]
 64%|██████▍   | 36884/57600 [6:28:25<3:29:31,  1.65it/s]
 64%|██████▍   | 36885/57600 [6:28:26<3:32:24,  1.63it/s]
 64%|██████▍   | 36886/57600 [6:28:26<3:32:41,  1.62it/s]
 64%|██████▍   | 36887/57600 [6:28:27<3:33:31,  1.62it/s]
 64%|██████▍   | 36888/57600 [6:28:28<3:32:03,  1.63it/s]
 64%|██████▍   | 36889/57600 [6:28:28<3:26:35,  1.67it/s]
 64%|██████▍   | 36890/57600 [6:28:29<3:23:56,  1.69it/s]
 64%|██████▍   | 36891/57600 [6:28:29<3:30:25,  1.64it/s]
 64%|██████▍   | 36892/57600 [6:28:30<3:28:03,  1.66it/s]
 64%|██████▍   | 36893/57600 [6:28:30<3:27:31,  1.66it/s]
 64%|██████▍   | 36894/57600 [6:28:31<3:32:30,  1.62it/s]
 64%|██████▍   | 36895/57600 [6:28:32<3:40:20,  1.57it/s]
 64%|██████▍   | 36896/57600 [6:28:32<3:38:18,  1.58it/s]
 64%|██████▍   | 36897/57600 [6:28:33<3:37:44,  1.58it/s]
 64%|██████▍   | 36898/57600 [6:28:34<3:33:28,  1.62it/s]
 64%|██████▍   | 36899/57600 [6:28:34<3:38:12,  1.58it/s]
 64%|██████▍   | 36900/57600 [6:28:35<3:43:47,  1.54it/s]
                                                         
{'loss': 1.1692, 'learning_rate': 4.245644599303136e-07, 'epoch': 407.28}

 64%|██████▍   | 36900/57600 [6:28:35<3:43:47,  1.54it/s]
 64%|██████▍   | 36901/57600 [6:28:36<3:43:10,  1.55it/s]
 64%|██████▍   | 36902/57600 [6:28:36<3:42:49,  1.55it/s]
 64%|██████▍   | 36903/57600 [6:28:37<3:51:35,  1.49it/s]
 64%|██████▍   | 36904/57600 [6:28:38<3:48:16,  1.51it/s]
 64%|██████▍   | 36905/57600 [6:28:38<3:44:53,  1.53it/s]
 64%|██████▍   | 36906/57600 [6:28:39<3:50:06,  1.50it/s]
 64%|██████▍   | 36907/57600 [6:28:40<3:45:51,  1.53it/s]
 64%|██████▍   | 36908/57600 [6:28:40<3:38:12,  1.58it/s]
 64%|██████▍   | 36909/57600 [6:28:41<3:40:28,  1.56it/s]
 64%|██████▍   | 36910/57600 [6:28:41<3:40:18,  1.57it/s]
 64%|██████▍   | 36911/57600 [6:28:42<3:32:05,  1.63it/s]
 64%|██████▍   | 36912/57600 [6:28:43<3:36:31,  1.59it/s]
 64%|██████▍   | 36913/57600 [6:28:43<3:33:35,  1.61it/s]
 64%|██████▍   | 36914/57600 [6:28:44<3:34:22,  1.61it/s]
 64%|██████▍   | 36915/57600 [6:28:45<3:30:00,  1.64it/s]
 64%|██████▍   | 36916/57600 [6:28:45<3:41:55,  1.55it/s]
 64%|██████▍   | 36917/57600 [6:28:46<3:37:02,  1.59it/s]
 64%|██████▍   | 36918/57600 [6:28:47<3:44:29,  1.54it/s]
 64%|██████▍   | 36919/57600 [6:28:47<3:53:46,  1.47it/s]
 64%|██████▍   | 36920/57600 [6:28:48<3:45:42,  1.53it/s]
                                                         
{'loss': 1.1206, 'learning_rate': 4.242508710801393e-07, 'epoch': 407.51}

 64%|██████▍   | 36920/57600 [6:28:48<3:45:42,  1.53it/s]
 64%|██████▍   | 36921/57600 [6:28:48<3:36:40,  1.59it/s]
 64%|██████▍   | 36922/57600 [6:28:49<3:39:25,  1.57it/s]
 64%|██████▍   | 36923/57600 [6:28:50<3:38:15,  1.58it/s]
 64%|██████▍   | 36924/57600 [6:28:50<3:38:05,  1.58it/s]
 64%|██████▍   | 36925/57600 [6:28:51<3:39:24,  1.57it/s]
 64%|██████▍   | 36926/57600 [6:28:52<3:34:47,  1.60it/s]
 64%|██████▍   | 36927/57600 [6:28:52<3:31:12,  1.63it/s]
 64%|██████▍   | 36928/57600 [6:28:53<3:32:08,  1.62it/s]
 64%|██████▍   | 36929/57600 [6:28:53<3:29:26,  1.64it/s]
 64%|██████▍   | 36930/57600 [6:28:54<3:31:06,  1.63it/s]
 64%|██████▍   | 36931/57600 [6:28:55<3:31:50,  1.63it/s]
 64%|██████▍   | 36932/57600 [6:28:55<3:32:01,  1.62it/s]
 64%|██████▍   | 36933/57600 [6:28:56<3:33:32,  1.61it/s]
 64%|██████▍   | 36934/57600 [6:28:57<3:32:18,  1.62it/s]
 64%|██████▍   | 36935/57600 [6:28:57<3:31:32,  1.63it/s]
 64%|██████▍   | 36936/57600 [6:28:58<3:36:18,  1.59it/s]
 64%|██████▍   | 36937/57600 [6:28:58<3:32:03,  1.62it/s]
 64%|██████▍   | 36938/57600 [6:28:59<3:32:15,  1.62it/s]
 64%|██████▍   | 36939/57600 [6:29:00<3:27:30,  1.66it/s]
 64%|██████▍   | 36940/57600 [6:29:00<3:29:33,  1.64it/s]
                                                         
{'loss': 1.1806, 'learning_rate': 4.2393728222996517e-07, 'epoch': 407.73}

 64%|██████▍   | 36940/57600 [6:29:00<3:29:33,  1.64it/s]
 64%|██████▍   | 36941/57600 [6:29:01<3:33:14,  1.61it/s]
 64%|██████▍   | 36942/57600 [6:29:01<3:29:59,  1.64it/s]
 64%|██████▍   | 36943/57600 [6:29:02<3:37:15,  1.58it/s]
 64%|██████▍   | 36944/57600 [6:29:03<3:37:27,  1.58it/s]
 64%|██████▍   | 36945/57600 [6:29:03<3:33:08,  1.62it/s]
 64%|██████▍   | 36946/57600 [6:29:04<3:29:13,  1.65it/s]
 64%|██████▍   | 36947/57600 [6:29:04<3:26:45,  1.66it/s]
 64%|██████▍   | 36948/57600 [6:29:05<3:25:01,  1.68it/s]
 64%|██████▍   | 36949/57600 [6:29:06<3:24:11,  1.69it/s]
 64%|██████▍   | 36950/57600 [6:29:06<3:29:50,  1.64it/s]
 64%|██████▍   | 36951/57600 [6:29:07<3:28:47,  1.65it/s]
 64%|██████▍   | 36952/57600 [6:29:08<3:31:31,  1.63it/s]
 64%|██████▍   | 36953/57600 [6:29:08<3:33:19,  1.61it/s]
 64%|██████▍   | 36954/57600 [6:29:09<3:29:45,  1.64it/s]
 64%|██████▍   | 36955/57600 [6:29:09<3:29:26,  1.64it/s]
 64%|██████▍   | 36956/57600 [6:29:10<3:33:31,  1.61it/s]
 64%|██████▍   | 36957/57600 [6:29:11<3:36:50,  1.59it/s]
 64%|██████▍   | 36958/57600 [6:29:11<3:36:25,  1.59it/s]
 64%|██████▍   | 36959/57600 [6:29:12<3:45:10,  1.53it/s]
 64%|██████▍   | 36960/57600 [6:29:13<3:44:51,  1.53it/s]
                                                         
{'loss': 1.1506, 'learning_rate': 4.2362369337979087e-07, 'epoch': 407.95}

 64%|██████▍   | 36960/57600 [6:29:13<3:44:51,  1.53it/s]
 64%|██████▍   | 36961/57600 [6:29:13<3:41:07,  1.56it/s]
 64%|██████▍   | 36962/57600 [6:29:14<3:47:42,  1.51it/s]
 64%|██████▍   | 36963/57600 [6:29:15<3:40:06,  1.56it/s]
 64%|██████▍   | 36964/57600 [6:29:15<3:43:40,  1.54it/s]
 64%|██████▍   | 36965/57600 [6:29:16<3:51:11,  1.49it/s]
 64%|██████▍   | 36966/57600 [6:29:17<3:49:21,  1.50it/s]
 64%|██████▍   | 36967/57600 [6:29:17<3:41:32,  1.55it/s]
 64%|██████▍   | 36968/57600 [6:29:18<3:38:42,  1.57it/s]
 64%|██████▍   | 36969/57600 [6:29:18<3:39:06,  1.57it/s]
 64%|██████▍   | 36970/57600 [6:29:19<3:35:13,  1.60it/s]
 64%|██████▍   | 36971/57600 [6:29:20<3:34:24,  1.60it/s]
 64%|██████▍   | 36972/57600 [6:29:20<3:36:03,  1.59it/s]
 64%|██████▍   | 36973/57600 [6:29:21<3:33:05,  1.61it/s]
 64%|██████▍   | 36974/57600 [6:29:22<3:34:28,  1.60it/s]
 64%|██████▍   | 36975/57600 [6:29:22<3:33:58,  1.61it/s]
 64%|██████▍   | 36976/57600 [6:29:23<3:39:00,  1.57it/s]
 64%|██████▍   | 36977/57600 [6:29:23<3:31:42,  1.62it/s]
 64%|██████▍   | 36978/57600 [6:29:24<3:30:14,  1.63it/s]
 64%|██████▍   | 36979/57600 [6:29:25<3:27:58,  1.65it/s]
 64%|██████▍   | 36980/57600 [6:29:25<3:26:16,  1.67it/s]
                                                         
{'loss': 1.1418, 'learning_rate': 4.233101045296167e-07, 'epoch': 408.17}

 64%|██████▍   | 36980/57600 [6:29:25<3:26:16,  1.67it/s]
 64%|██████▍   | 36981/57600 [6:29:26<3:24:02,  1.68it/s]
 64%|██████▍   | 36982/57600 [6:29:26<3:24:47,  1.68it/s]
 64%|██████▍   | 36983/57600 [6:29:27<3:29:59,  1.64it/s]
 64%|██████▍   | 36984/57600 [6:29:28<3:27:31,  1.66it/s]
 64%|██████▍   | 36985/57600 [6:29:28<3:33:19,  1.61it/s]
 64%|██████▍   | 36986/57600 [6:29:29<3:34:50,  1.60it/s]
 64%|██████▍   | 36987/57600 [6:29:29<3:29:20,  1.64it/s]
 64%|██████▍   | 36988/57600 [6:29:30<3:28:51,  1.64it/s]
 64%|██████▍   | 36989/57600 [6:29:31<3:23:18,  1.69it/s]
 64%|██████▍   | 36990/57600 [6:29:31<3:31:54,  1.62it/s]
 64%|██████▍   | 36991/57600 [6:29:32<3:34:03,  1.60it/s]
 64%|██████▍   | 36992/57600 [6:29:33<3:35:52,  1.59it/s]
 64%|██████▍   | 36993/57600 [6:29:33<3:47:42,  1.51it/s]
 64%|██████▍   | 36994/57600 [6:29:34<3:41:40,  1.55it/s]
 64%|██████▍   | 36995/57600 [6:29:35<3:37:25,  1.58it/s]
 64%|██████▍   | 36996/57600 [6:29:35<3:42:09,  1.55it/s]
 64%|██████▍   | 36997/57600 [6:29:36<3:42:11,  1.55it/s]
 64%|██████▍   | 36998/57600 [6:29:37<3:49:16,  1.50it/s]
 64%|██████▍   | 36999/57600 [6:29:37<3:41:48,  1.55it/s]
 64%|██████▍   | 37000/57600 [6:29:38<3:39:34,  1.56it/s]
                                                         
{'loss': 1.1389, 'learning_rate': 4.229965156794426e-07, 'epoch': 408.39}

 64%|██████▍   | 37000/57600 [6:29:38<3:39:34,  1.56it/s]
 64%|██████▍   | 37001/57600 [6:29:38<3:37:38,  1.58it/s]
 64%|██████▍   | 37002/57600 [6:29:39<3:30:47,  1.63it/s]
 64%|██████▍   | 37003/57600 [6:29:40<3:30:40,  1.63it/s]
 64%|██████▍   | 37004/57600 [6:29:40<3:30:29,  1.63it/s]
 64%|██████▍   | 37005/57600 [6:29:41<3:26:16,  1.66it/s]
 64%|██████▍   | 37006/57600 [6:29:41<3:24:30,  1.68it/s]
 64%|██████▍   | 37007/57600 [6:29:42<3:35:26,  1.59it/s]
 64%|██████▍   | 37008/57600 [6:29:43<3:39:35,  1.56it/s]
 64%|██████▍   | 37009/57600 [6:29:43<3:38:00,  1.57it/s]
 64%|██████▍   | 37010/57600 [6:29:44<3:44:17,  1.53it/s]
 64%|██████▍   | 37011/57600 [6:29:45<3:48:35,  1.50it/s]
 64%|██████▍   | 37012/57600 [6:29:45<3:44:57,  1.53it/s]
 64%|██████▍   | 37013/57600 [6:29:46<3:45:09,  1.52it/s]
 64%|██████▍   | 37014/57600 [6:29:47<3:38:52,  1.57it/s]
 64%|██████▍   | 37015/57600 [6:29:47<3:40:56,  1.55it/s]
 64%|██████▍   | 37016/57600 [6:29:48<3:38:38,  1.57it/s]
 64%|██████▍   | 37017/57600 [6:29:49<3:44:37,  1.53it/s]
 64%|██████▍   | 37018/57600 [6:29:49<3:38:51,  1.57it/s]
 64%|██████▍   | 37019/57600 [6:29:50<3:33:11,  1.61it/s]
 64%|██████▍   | 37020/57600 [6:29:50<3:33:12,  1.61it/s]
                                                         
{'loss': 1.1643, 'learning_rate': 4.226829268292683e-07, 'epoch': 408.61}

 64%|██████▍   | 37020/57600 [6:29:50<3:33:12,  1.61it/s]
 64%|██████▍   | 37021/57600 [6:29:51<3:37:46,  1.57it/s]
 64%|██████▍   | 37022/57600 [6:29:52<3:39:16,  1.56it/s]
 64%|██████▍   | 37023/57600 [6:29:52<3:42:07,  1.54it/s]
 64%|██████▍   | 37024/57600 [6:29:53<3:39:10,  1.56it/s]
 64%|██████▍   | 37025/57600 [6:29:54<3:37:02,  1.58it/s]
 64%|██████▍   | 37026/57600 [6:29:54<3:33:27,  1.61it/s]
 64%|██████▍   | 37027/57600 [6:29:55<3:26:06,  1.66it/s]
 64%|██████▍   | 37028/57600 [6:29:55<3:30:08,  1.63it/s]
 64%|██████▍   | 37029/57600 [6:29:56<3:31:27,  1.62it/s]
 64%|██████▍   | 37030/57600 [6:29:57<3:36:14,  1.59it/s]
 64%|██████▍   | 37031/57600 [6:29:57<3:36:59,  1.58it/s]
 64%|██████▍   | 37032/57600 [6:29:58<3:36:28,  1.58it/s]
 64%|██████▍   | 37033/57600 [6:29:59<3:33:15,  1.61it/s]
 64%|██████▍   | 37034/57600 [6:29:59<3:32:34,  1.61it/s]
 64%|██████▍   | 37035/57600 [6:30:00<3:49:47,  1.49it/s]
 64%|██████▍   | 37036/57600 [6:30:01<3:42:37,  1.54it/s]
 64%|██████▍   | 37037/57600 [6:30:01<3:40:32,  1.55it/s]
 64%|██████▍   | 37038/57600 [6:30:02<3:36:00,  1.59it/s]
 64%|██████▍   | 37039/57600 [6:30:02<3:40:22,  1.56it/s]
 64%|██████▍   | 37040/57600 [6:30:03<3:47:35,  1.51it/s]
                                                         
{'loss': 1.1332, 'learning_rate': 4.223693379790941e-07, 'epoch': 408.83}

 64%|██████▍   | 37040/57600 [6:30:03<3:47:35,  1.51it/s]
 64%|██████▍   | 37041/57600 [6:30:04<3:42:25,  1.54it/s]
 64%|██████▍   | 37042/57600 [6:30:04<3:38:11,  1.57it/s]
 64%|██████▍   | 37043/57600 [6:30:05<3:44:04,  1.53it/s]
 64%|██████▍   | 37044/57600 [6:30:06<3:47:30,  1.51it/s]
 64%|██████▍   | 37045/57600 [6:30:06<3:45:35,  1.52it/s]
 64%|██████▍   | 37046/57600 [6:30:07<3:49:26,  1.49it/s]
 64%|██████▍   | 37047/57600 [6:30:08<3:39:40,  1.56it/s]
 64%|██████▍   | 37048/57600 [6:30:08<3:44:54,  1.52it/s]
 64%|██████▍   | 37049/57600 [6:30:09<3:37:23,  1.58it/s]
 64%|██████▍   | 37050/57600 [6:30:10<3:31:43,  1.62it/s]
 64%|██████▍   | 37051/57600 [6:30:10<3:27:25,  1.65it/s]
 64%|██████▍   | 37052/57600 [6:30:11<3:33:21,  1.61it/s]
 64%|██████▍   | 37053/57600 [6:30:11<3:31:24,  1.62it/s]
 64%|██████▍   | 37054/57600 [6:30:12<3:28:58,  1.64it/s]
 64%|██████▍   | 37055/57600 [6:30:13<3:34:36,  1.60it/s]
 64%|██████▍   | 37056/57600 [6:30:13<3:39:10,  1.56it/s]
 64%|██████▍   | 37057/57600 [6:30:14<3:39:02,  1.56it/s]
 64%|██████▍   | 37058/57600 [6:30:15<3:39:05,  1.56it/s]
 64%|██████▍   | 37059/57600 [6:30:15<3:42:13,  1.54it/s]
 64%|██████▍   | 37060/57600 [6:30:16<3:37:59,  1.57it/s]
                                                         
{'loss': 1.1497, 'learning_rate': 4.2205574912891984e-07, 'epoch': 409.05}

 64%|██████▍   | 37060/57600 [6:30:16<3:37:59,  1.57it/s]
 64%|██████▍   | 37061/57600 [6:30:17<3:36:15,  1.58it/s]
 64%|██████▍   | 37062/57600 [6:30:17<3:41:36,  1.54it/s]
 64%|██████▍   | 37063/57600 [6:30:18<3:38:47,  1.56it/s]
 64%|██████▍   | 37064/57600 [6:30:18<3:38:11,  1.57it/s]
 64%|██████▍   | 37065/57600 [6:30:19<3:40:01,  1.56it/s]
 64%|██████▍   | 37066/57600 [6:30:20<3:39:40,  1.56it/s]
 64%|██████▍   | 37067/57600 [6:30:20<3:37:06,  1.58it/s]
 64%|██████▍   | 37068/57600 [6:30:21<3:39:47,  1.56it/s]
 64%|██████▍   | 37069/57600 [6:30:22<3:35:43,  1.59it/s]
 64%|██████▍   | 37070/57600 [6:30:22<3:33:55,  1.60it/s]
 64%|██████▍   | 37071/57600 [6:30:23<3:37:51,  1.57it/s]
 64%|██████▍   | 37072/57600 [6:30:24<3:34:28,  1.60it/s]
 64%|██████▍   | 37073/57600 [6:30:24<3:37:21,  1.57it/s]
 64%|██████▍   | 37074/57600 [6:30:25<3:39:50,  1.56it/s]
 64%|██████▍   | 37075/57600 [6:30:26<3:46:42,  1.51it/s]
 64%|██████▍   | 37076/57600 [6:30:26<3:44:35,  1.52it/s]
 64%|██████▍   | 37077/57600 [6:30:27<3:40:39,  1.55it/s]
 64%|██████▍   | 37078/57600 [6:30:27<3:41:00,  1.55it/s]
 64%|██████▍   | 37079/57600 [6:30:28<3:29:50,  1.63it/s]
 64%|██████▍   | 37080/57600 [6:30:29<3:32:10,  1.61it/s]
                                                         
{'loss': 1.1002, 'learning_rate': 4.2174216027874564e-07, 'epoch': 409.27}

 64%|██████▍   | 37080/57600 [6:30:29<3:32:10,  1.61it/s]
 64%|██████▍   | 37081/57600 [6:30:29<3:35:52,  1.58it/s]
 64%|██████▍   | 37082/57600 [6:30:30<3:41:47,  1.54it/s]
 64%|██████▍   | 37083/57600 [6:30:31<3:37:25,  1.57it/s]
 64%|██████▍   | 37084/57600 [6:30:31<3:47:17,  1.50it/s]
 64%|██████▍   | 37085/57600 [6:30:32<3:41:59,  1.54it/s]
 64%|██████▍   | 37086/57600 [6:30:32<3:33:26,  1.60it/s]
 64%|██████▍   | 37087/57600 [6:30:33<3:29:21,  1.63it/s]
 64%|██████▍   | 37088/57600 [6:30:34<3:23:26,  1.68it/s]
 64%|██████▍   | 37089/57600 [6:30:34<3:24:32,  1.67it/s]
 64%|██████▍   | 37090/57600 [6:30:35<3:21:14,  1.70it/s]
 64%|██████▍   | 37091/57600 [6:30:35<3:18:41,  1.72it/s]
 64%|██████▍   | 37092/57600 [6:30:36<3:21:21,  1.70it/s]
 64%|██████▍   | 37093/57600 [6:30:37<3:30:09,  1.63it/s]
 64%|██████▍   | 37094/57600 [6:30:37<3:36:37,  1.58it/s]
 64%|██████▍   | 37095/57600 [6:30:38<3:36:39,  1.58it/s]
 64%|██████▍   | 37096/57600 [6:30:39<3:32:02,  1.61it/s]
 64%|██████▍   | 37097/57600 [6:30:39<3:28:27,  1.64it/s]
 64%|██████▍   | 37098/57600 [6:30:40<3:28:38,  1.64it/s]
 64%|██████▍   | 37099/57600 [6:30:40<3:26:32,  1.65it/s]
 64%|██████▍   | 37100/57600 [6:30:41<3:23:42,  1.68it/s]
                                                         
{'loss': 1.1924, 'learning_rate': 4.2142857142857134e-07, 'epoch': 409.49}

 64%|██████▍   | 37100/57600 [6:30:41<3:23:42,  1.68it/s]
 64%|██████▍   | 37101/57600 [6:30:42<3:27:03,  1.65it/s]
 64%|██████▍   | 37102/57600 [6:30:42<3:27:57,  1.64it/s]
 64%|██████▍   | 37103/57600 [6:30:43<3:34:45,  1.59it/s]
 64%|██████▍   | 37104/57600 [6:30:43<3:34:01,  1.60it/s]
 64%|██████▍   | 37105/57600 [6:30:44<3:35:41,  1.58it/s]
 64%|██████▍   | 37106/57600 [6:30:45<3:29:47,  1.63it/s]
 64%|██████▍   | 37107/57600 [6:30:45<3:32:21,  1.61it/s]
 64%|██████▍   | 37108/57600 [6:30:46<3:31:50,  1.61it/s]
 64%|██████▍   | 37109/57600 [6:30:46<3:26:39,  1.65it/s]
 64%|██████▍   | 37110/57600 [6:30:47<3:26:44,  1.65it/s]
 64%|██████▍   | 37111/57600 [6:30:48<3:27:41,  1.64it/s]
 64%|██████▍   | 37112/57600 [6:30:48<3:33:56,  1.60it/s]
 64%|██████▍   | 37113/57600 [6:30:49<3:38:11,  1.56it/s]
 64%|██████▍   | 37114/57600 [6:30:50<3:33:12,  1.60it/s]
 64%|██████▍   | 37115/57600 [6:30:50<3:36:47,  1.57it/s]
 64%|██████▍   | 37116/57600 [6:30:51<3:41:34,  1.54it/s]
 64%|██████▍   | 37117/57600 [6:30:52<3:40:21,  1.55it/s]
 64%|██████▍   | 37118/57600 [6:30:52<3:40:47,  1.55it/s]
 64%|██████▍   | 37119/57600 [6:30:53<3:44:44,  1.52it/s]
 64%|██████▍   | 37120/57600 [6:30:54<3:41:03,  1.54it/s]
                                                         
{'loss': 1.1697, 'learning_rate': 4.2111498257839725e-07, 'epoch': 409.71}

 64%|██████▍   | 37120/57600 [6:30:54<3:41:03,  1.54it/s]
 64%|██████▍   | 37121/57600 [6:30:54<3:38:09,  1.56it/s]
 64%|██████▍   | 37122/57600 [6:30:55<3:37:59,  1.57it/s]
 64%|██████▍   | 37123/57600 [6:30:56<3:41:50,  1.54it/s]
 64%|██████▍   | 37124/57600 [6:30:56<3:41:28,  1.54it/s]
 64%|██████▍   | 37125/57600 [6:30:57<3:32:58,  1.60it/s]
 64%|██████▍   | 37126/57600 [6:30:57<3:42:38,  1.53it/s]
 64%|██████▍   | 37127/57600 [6:30:58<3:40:20,  1.55it/s]
 64%|██████▍   | 37128/57600 [6:30:59<3:40:38,  1.55it/s]
 64%|██████▍   | 37129/57600 [6:30:59<3:34:51,  1.59it/s]
 64%|██████▍   | 37130/57600 [6:31:00<3:38:00,  1.56it/s]
 64%|██████▍   | 37131/57600 [6:31:01<3:34:36,  1.59it/s]
 64%|██████▍   | 37132/57600 [6:31:01<3:28:46,  1.63it/s]
 64%|██████▍   | 37133/57600 [6:31:02<3:29:48,  1.63it/s]
 64%|██████▍   | 37134/57600 [6:31:02<3:25:19,  1.66it/s]
 64%|██████▍   | 37135/57600 [6:31:03<3:25:00,  1.66it/s]
 64%|██████▍   | 37136/57600 [6:31:04<3:30:45,  1.62it/s]
 64%|██████▍   | 37137/57600 [6:31:04<3:30:18,  1.62it/s]
 64%|██████▍   | 37138/57600 [6:31:05<3:32:40,  1.60it/s]
 64%|██████▍   | 37139/57600 [6:31:05<3:33:40,  1.60it/s]
 64%|██████▍   | 37140/57600 [6:31:06<3:39:33,  1.55it/s]
                                                         
{'loss': 1.1467, 'learning_rate': 4.20801393728223e-07, 'epoch': 409.93}

 64%|██████▍   | 37140/57600 [6:31:06<3:39:33,  1.55it/s]
 64%|██████▍   | 37141/57600 [6:31:07<3:39:41,  1.55it/s]
 64%|██████▍   | 37142/57600 [6:31:07<3:34:13,  1.59it/s]
 64%|██████▍   | 37143/57600 [6:31:08<3:35:45,  1.58it/s]
 64%|██████▍   | 37144/57600 [6:31:09<3:42:07,  1.53it/s]
 64%|██████▍   | 37145/57600 [6:31:09<3:37:22,  1.57it/s]
 64%|██████▍   | 37146/57600 [6:31:10<3:42:54,  1.53it/s]
 64%|██████▍   | 37147/57600 [6:31:11<3:48:07,  1.49it/s]
 64%|██████▍   | 37148/57600 [6:31:11<3:48:39,  1.49it/s]
 64%|██████▍   | 37149/57600 [6:31:12<3:43:58,  1.52it/s]
 64%|██████▍   | 37150/57600 [6:31:13<3:34:44,  1.59it/s]
 64%|██████▍   | 37151/57600 [6:31:13<3:36:22,  1.58it/s]
 64%|██████▍   | 37152/57600 [6:31:14<3:34:22,  1.59it/s]
 65%|██████▍   | 37153/57600 [6:31:14<3:27:57,  1.64it/s]
 65%|██████▍   | 37154/57600 [6:31:15<3:24:33,  1.67it/s]
 65%|██████▍   | 37155/57600 [6:31:16<3:27:44,  1.64it/s]
 65%|██████▍   | 37156/57600 [6:31:16<3:28:43,  1.63it/s]
 65%|██████▍   | 37157/57600 [6:31:17<3:23:17,  1.68it/s]
 65%|██████▍   | 37158/57600 [6:31:17<3:28:26,  1.63it/s]
 65%|██████▍   | 37159/57600 [6:31:18<3:27:38,  1.64it/s]
 65%|██████▍   | 37160/57600 [6:31:19<3:26:40,  1.65it/s]
                                                         
{'loss': 1.1527, 'learning_rate': 4.2048780487804876e-07, 'epoch': 410.15}

 65%|██████▍   | 37160/57600 [6:31:19<3:26:40,  1.65it/s]
 65%|██████▍   | 37161/57600 [6:31:19<3:32:56,  1.60it/s]
 65%|██████▍   | 37162/57600 [6:31:20<3:28:55,  1.63it/s]
 65%|██████▍   | 37163/57600 [6:31:21<3:27:15,  1.64it/s]
 65%|██████▍   | 37164/57600 [6:31:21<3:30:18,  1.62it/s]
 65%|██████▍   | 37165/57600 [6:31:22<3:41:24,  1.54it/s]
 65%|██████▍   | 37166/57600 [6:31:23<3:37:57,  1.56it/s]
 65%|██████▍   | 37167/57600 [6:31:23<3:34:00,  1.59it/s]
 65%|██████▍   | 37168/57600 [6:31:24<3:34:23,  1.59it/s]
 65%|██████▍   | 37169/57600 [6:31:25<3:48:51,  1.49it/s]
 65%|██████▍   | 37170/57600 [6:31:25<3:53:25,  1.46it/s]
 65%|██████▍   | 37171/57600 [6:31:26<3:56:13,  1.44it/s]
 65%|██████▍   | 37172/57600 [6:31:27<3:47:44,  1.50it/s]
 65%|██████▍   | 37173/57600 [6:31:27<3:39:50,  1.55it/s]
 65%|██████▍   | 37174/57600 [6:31:28<3:40:24,  1.54it/s]
 65%|██████▍   | 37175/57600 [6:31:28<3:35:34,  1.58it/s]
 65%|██████▍   | 37176/57600 [6:31:29<3:33:27,  1.59it/s]
 65%|██████▍   | 37177/57600 [6:31:30<3:44:34,  1.52it/s]
 65%|██████▍   | 37178/57600 [6:31:30<3:39:31,  1.55it/s]
 65%|██████▍   | 37179/57600 [6:31:31<3:33:58,  1.59it/s]
 65%|██████▍   | 37180/57600 [6:31:32<3:35:38,  1.58it/s]
                                                         
{'loss': 1.1282, 'learning_rate': 4.2017421602787456e-07, 'epoch': 410.38}

 65%|██████▍   | 37180/57600 [6:31:32<3:35:38,  1.58it/s]
 65%|██████▍   | 37181/57600 [6:31:32<3:34:24,  1.59it/s]
 65%|██████▍   | 37182/57600 [6:31:33<3:32:12,  1.60it/s]
 65%|██████▍   | 37183/57600 [6:31:33<3:31:26,  1.61it/s]
 65%|██████▍   | 37184/57600 [6:31:34<3:28:42,  1.63it/s]
 65%|██████▍   | 37185/57600 [6:31:35<3:23:53,  1.67it/s]
 65%|██████▍   | 37186/57600 [6:31:35<3:20:15,  1.70it/s]
 65%|██████▍   | 37187/57600 [6:31:36<3:23:28,  1.67it/s]
 65%|██████▍   | 37188/57600 [6:31:36<3:29:48,  1.62it/s]
 65%|██████▍   | 37189/57600 [6:31:37<3:29:00,  1.63it/s]
 65%|██████▍   | 37190/57600 [6:31:38<3:31:40,  1.61it/s]
 65%|██████▍   | 37191/57600 [6:31:38<3:28:24,  1.63it/s]
 65%|██████▍   | 37192/57600 [6:31:39<3:30:38,  1.61it/s]
 65%|██████▍   | 37193/57600 [6:31:40<3:31:23,  1.61it/s]
 65%|██████▍   | 37194/57600 [6:31:40<3:36:24,  1.57it/s]
 65%|██████▍   | 37195/57600 [6:31:41<3:32:00,  1.60it/s]
 65%|██████▍   | 37196/57600 [6:31:41<3:30:46,  1.61it/s]
 65%|██████▍   | 37197/57600 [6:31:42<3:34:05,  1.59it/s]
 65%|██████▍   | 37198/57600 [6:31:43<3:33:13,  1.59it/s]
 65%|██████▍   | 37199/57600 [6:31:43<3:26:10,  1.65it/s]
 65%|██████▍   | 37200/57600 [6:31:44<3:34:40,  1.58it/s]
                                                         
{'loss': 1.1604, 'learning_rate': 4.198606271777003e-07, 'epoch': 410.6}

 65%|██████▍   | 37200/57600 [6:31:44<3:34:40,  1.58it/s]
 65%|██████▍   | 37201/57600 [6:31:45<3:30:18,  1.62it/s]
 65%|██████▍   | 37202/57600 [6:31:45<3:30:21,  1.62it/s]
 65%|██████▍   | 37203/57600 [6:31:46<3:35:46,  1.58it/s]
 65%|██████▍   | 37204/57600 [6:31:46<3:38:50,  1.55it/s]
 65%|██████▍   | 37205/57600 [6:31:47<3:33:53,  1.59it/s]
 65%|██████▍   | 37206/57600 [6:31:48<3:33:21,  1.59it/s]
 65%|██████▍   | 37207/57600 [6:31:48<3:32:35,  1.60it/s]
 65%|██████▍   | 37208/57600 [6:31:49<3:32:14,  1.60it/s]
 65%|██████▍   | 37209/57600 [6:31:50<3:35:40,  1.58it/s]
 65%|██████▍   | 37210/57600 [6:31:50<3:43:13,  1.52it/s]
 65%|██████▍   | 37211/57600 [6:31:51<3:42:22,  1.53it/s]
 65%|██████▍   | 37212/57600 [6:31:52<3:37:06,  1.57it/s]
 65%|██████▍   | 37213/57600 [6:31:52<3:44:06,  1.52it/s]
 65%|██████▍   | 37214/57600 [6:31:53<3:37:49,  1.56it/s]
 65%|██████▍   | 37215/57600 [6:31:53<3:33:04,  1.59it/s]
 65%|██████▍   | 37216/57600 [6:31:54<3:42:52,  1.52it/s]
 65%|██████▍   | 37217/57600 [6:31:55<3:32:51,  1.60it/s]
 65%|██████▍   | 37218/57600 [6:31:55<3:27:28,  1.64it/s]
 65%|██████▍   | 37219/57600 [6:31:56<3:40:09,  1.54it/s]
 65%|██████▍   | 37220/57600 [6:31:57<3:48:34,  1.49it/s]
                                                         
{'loss': 1.1222, 'learning_rate': 4.195470383275261e-07, 'epoch': 410.82}

 65%|██████▍   | 37220/57600 [6:31:57<3:48:34,  1.49it/s]
 65%|██████▍   | 37221/57600 [6:31:57<3:44:06,  1.52it/s]
 65%|██████▍   | 37222/57600 [6:31:58<3:41:09,  1.54it/s]
 65%|██████▍   | 37223/57600 [6:31:59<3:37:04,  1.56it/s]
 65%|██████▍   | 37224/57600 [6:31:59<3:34:15,  1.58it/s]
 65%|██████▍   | 37225/57600 [6:32:00<3:38:54,  1.55it/s]
 65%|██████▍   | 37226/57600 [6:32:01<3:38:22,  1.56it/s]
 65%|██████▍   | 37227/57600 [6:32:01<3:36:22,  1.57it/s]
 65%|██████▍   | 37228/57600 [6:32:02<3:35:37,  1.57it/s]
 65%|██████▍   | 37229/57600 [6:32:03<3:39:29,  1.55it/s]
 65%|██████▍   | 37230/57600 [6:32:03<3:43:16,  1.52it/s]
 65%|██████▍   | 37231/57600 [6:32:04<3:38:24,  1.55it/s]
 65%|██████▍   | 37232/57600 [6:32:04<3:36:58,  1.56it/s]
 65%|██████▍   | 37233/57600 [6:32:05<3:35:11,  1.58it/s]
 65%|██████▍   | 37234/57600 [6:32:06<3:34:51,  1.58it/s]
 65%|██████▍   | 37235/57600 [6:32:06<3:34:24,  1.58it/s]
 65%|██████▍   | 37236/57600 [6:32:07<3:31:25,  1.61it/s]
 65%|██████▍   | 37237/57600 [6:32:08<3:40:12,  1.54it/s]
 65%|██████▍   | 37238/57600 [6:32:08<3:37:23,  1.56it/s]
 65%|██████▍   | 37239/57600 [6:32:09<3:33:08,  1.59it/s]
 65%|██████▍   | 37240/57600 [6:32:10<3:39:56,  1.54it/s]
                                                         
{'loss': 1.1339, 'learning_rate': 4.192334494773519e-07, 'epoch': 411.04}

 65%|██████▍   | 37240/57600 [6:32:10<3:39:56,  1.54it/s]
 65%|██████▍   | 37241/57600 [6:32:10<3:42:17,  1.53it/s]
 65%|██████▍   | 37242/57600 [6:32:11<3:47:09,  1.49it/s]
 65%|██████▍   | 37243/57600 [6:32:12<3:42:39,  1.52it/s]
 65%|██████▍   | 37244/57600 [6:32:12<3:38:25,  1.55it/s]
 65%|██████▍   | 37245/57600 [6:32:13<3:34:20,  1.58it/s]
 65%|██████▍   | 37246/57600 [6:32:13<3:32:59,  1.59it/s]
 65%|██████▍   | 37247/57600 [6:32:14<3:28:49,  1.62it/s]
 65%|██████▍   | 37248/57600 [6:32:15<3:35:28,  1.57it/s]
 65%|██████▍   | 37249/57600 [6:32:15<3:31:34,  1.60it/s]
 65%|██████▍   | 37250/57600 [6:32:16<3:40:03,  1.54it/s]
 65%|██████▍   | 37251/57600 [6:32:17<3:35:42,  1.57it/s]
 65%|██████▍   | 37252/57600 [6:32:17<3:30:24,  1.61it/s]
 65%|██████▍   | 37253/57600 [6:32:18<3:27:04,  1.64it/s]
 65%|██████▍   | 37254/57600 [6:32:18<3:25:08,  1.65it/s]
 65%|██████▍   | 37255/57600 [6:32:19<3:24:29,  1.66it/s]
 65%|██████▍   | 37256/57600 [6:32:20<3:28:52,  1.62it/s]
 65%|██████▍   | 37257/57600 [6:32:20<3:29:37,  1.62it/s]
 65%|██████▍   | 37258/57600 [6:32:21<3:29:25,  1.62it/s]
 65%|██████▍   | 37259/57600 [6:32:21<3:22:45,  1.67it/s]
 65%|██████▍   | 37260/57600 [6:32:22<3:26:28,  1.64it/s]
                                                         
{'loss': 1.1465, 'learning_rate': 4.189198606271777e-07, 'epoch': 411.26}

 65%|██████▍   | 37260/57600 [6:32:22<3:26:28,  1.64it/s]
 65%|██████▍   | 37261/57600 [6:32:23<3:24:12,  1.66it/s]
 65%|██████▍   | 37262/57600 [6:32:23<3:26:48,  1.64it/s]
 65%|██████▍   | 37263/57600 [6:32:24<3:23:58,  1.66it/s]
 65%|██████▍   | 37264/57600 [6:32:24<3:25:21,  1.65it/s]
 65%|██████▍   | 37265/57600 [6:32:25<3:21:14,  1.68it/s]
 65%|██████▍   | 37266/57600 [6:32:26<3:24:24,  1.66it/s]
 65%|██████▍   | 37267/57600 [6:32:26<3:31:47,  1.60it/s]
 65%|██████▍   | 37268/57600 [6:32:27<3:34:57,  1.58it/s]
 65%|██████▍   | 37269/57600 [6:32:28<3:33:03,  1.59it/s]
 65%|██████▍   | 37270/57600 [6:32:28<3:27:05,  1.64it/s]
 65%|██████▍   | 37271/57600 [6:32:29<3:30:16,  1.61it/s]
 65%|██████▍   | 37272/57600 [6:32:29<3:25:49,  1.65it/s]
 65%|██████▍   | 37273/57600 [6:32:30<3:34:00,  1.58it/s]
 65%|██████▍   | 37274/57600 [6:32:31<3:30:30,  1.61it/s]
 65%|██████▍   | 37275/57600 [6:32:31<3:28:24,  1.63it/s]
 65%|██████▍   | 37276/57600 [6:32:32<3:35:43,  1.57it/s]
 65%|██████▍   | 37277/57600 [6:32:33<3:36:10,  1.57it/s]
 65%|██████▍   | 37278/57600 [6:32:33<3:28:37,  1.62it/s]
 65%|██████▍   | 37279/57600 [6:32:34<3:29:20,  1.62it/s]
 65%|██████▍   | 37280/57600 [6:32:34<3:32:08,  1.60it/s]
                                                         
{'loss': 1.1561, 'learning_rate': 4.186062717770035e-07, 'epoch': 411.48}

 65%|██████▍   | 37280/57600 [6:32:34<3:32:08,  1.60it/s]
 65%|██████▍   | 37281/57600 [6:32:35<3:31:58,  1.60it/s]
 65%|██████▍   | 37282/57600 [6:32:36<3:36:21,  1.57it/s]
 65%|██████▍   | 37283/57600 [6:32:36<3:37:16,  1.56it/s]
 65%|██████▍   | 37284/57600 [6:32:37<3:37:31,  1.56it/s]
 65%|██████▍   | 37285/57600 [6:32:38<3:31:20,  1.60it/s]
 65%|██████▍   | 37286/57600 [6:32:38<3:35:12,  1.57it/s]
 65%|██████▍   | 37287/57600 [6:32:39<3:31:12,  1.60it/s]
 65%|██████▍   | 37288/57600 [6:32:39<3:30:07,  1.61it/s]
 65%|██████▍   | 37289/57600 [6:32:40<3:45:24,  1.50it/s]
 65%|██████▍   | 37290/57600 [6:32:41<3:37:09,  1.56it/s]
 65%|██████▍   | 37291/57600 [6:32:41<3:32:51,  1.59it/s]
 65%|██████▍   | 37292/57600 [6:32:42<3:30:39,  1.61it/s]
 65%|██████▍   | 37293/57600 [6:32:43<3:25:25,  1.65it/s]
 65%|██████▍   | 37294/57600 [6:32:43<3:26:45,  1.64it/s]
 65%|██████▍   | 37295/57600 [6:32:44<3:30:38,  1.61it/s]
 65%|██████▍   | 37296/57600 [6:32:44<3:27:20,  1.63it/s]
 65%|██████▍   | 37297/57600 [6:32:45<3:23:35,  1.66it/s]
 65%|██████▍   | 37298/57600 [6:32:46<3:23:55,  1.66it/s]
 65%|██████▍   | 37299/57600 [6:32:46<3:34:21,  1.58it/s]
 65%|██████▍   | 37300/57600 [6:32:47<3:32:29,  1.59it/s]
                                                         
{'loss': 1.1597, 'learning_rate': 4.1829268292682923e-07, 'epoch': 411.7}

 65%|██████▍   | 37300/57600 [6:32:47<3:32:29,  1.59it/s]
 65%|██████▍   | 37301/57600 [6:32:48<3:38:38,  1.55it/s]
 65%|██████▍   | 37302/57600 [6:32:48<3:35:34,  1.57it/s]
 65%|██████▍   | 37303/57600 [6:32:49<3:32:34,  1.59it/s]
 65%|██████▍   | 37304/57600 [6:32:49<3:31:49,  1.60it/s]
 65%|██████▍   | 37305/57600 [6:32:50<3:28:01,  1.63it/s]
 65%|██████▍   | 37306/57600 [6:32:51<3:28:12,  1.62it/s]
 65%|██████▍   | 37307/57600 [6:32:51<3:29:00,  1.62it/s]
 65%|██████▍   | 37308/57600 [6:32:52<3:24:46,  1.65it/s]
 65%|██████▍   | 37309/57600 [6:32:52<3:23:07,  1.66it/s]
 65%|██████▍   | 37310/57600 [6:32:53<3:20:03,  1.69it/s]
 65%|██████▍   | 37311/57600 [6:32:54<3:21:37,  1.68it/s]
 65%|██████▍   | 37312/57600 [6:32:54<3:17:13,  1.71it/s]
 65%|██████▍   | 37313/57600 [6:32:55<3:20:38,  1.69it/s]
 65%|██████▍   | 37314/57600 [6:32:55<3:24:04,  1.66it/s]
 65%|██████▍   | 37315/57600 [6:32:56<3:20:27,  1.69it/s]
 65%|██████▍   | 37316/57600 [6:32:57<3:21:12,  1.68it/s]
 65%|██████▍   | 37317/57600 [6:32:57<3:29:36,  1.61it/s]
 65%|██████▍   | 37318/57600 [6:32:58<3:33:57,  1.58it/s]
 65%|██████▍   | 37319/57600 [6:32:59<3:40:04,  1.54it/s]
 65%|██████▍   | 37320/57600 [6:32:59<3:36:50,  1.56it/s]
                                                         
{'loss': 1.1627, 'learning_rate': 4.1797909407665504e-07, 'epoch': 411.92}

 65%|██████▍   | 37320/57600 [6:32:59<3:36:50,  1.56it/s]
 65%|██████▍   | 37321/57600 [6:33:00<3:38:48,  1.54it/s]
 65%|██████▍   | 37322/57600 [6:33:01<3:35:51,  1.57it/s]
 65%|██████▍   | 37323/57600 [6:33:01<3:31:41,  1.60it/s]
 65%|██████▍   | 37324/57600 [6:33:02<3:38:26,  1.55it/s]
 65%|██████▍   | 37325/57600 [6:33:03<3:46:24,  1.49it/s]
 65%|██████▍   | 37326/57600 [6:33:03<3:38:29,  1.55it/s]
 65%|██████▍   | 37327/57600 [6:33:04<3:38:09,  1.55it/s]
 65%|██████▍   | 37328/57600 [6:33:05<3:55:17,  1.44it/s]
 65%|██████▍   | 37329/57600 [6:33:05<3:48:06,  1.48it/s]
 65%|██████▍   | 37330/57600 [6:33:06<3:43:48,  1.51it/s]
 65%|██████▍   | 37331/57600 [6:33:06<3:38:55,  1.54it/s]
 65%|██████▍   | 37332/57600 [6:33:07<3:37:07,  1.56it/s]
 65%|██████▍   | 37333/57600 [6:33:08<3:32:02,  1.59it/s]
 65%|██████▍   | 37334/57600 [6:33:08<3:30:24,  1.61it/s]
 65%|██████▍   | 37335/57600 [6:33:09<3:38:48,  1.54it/s]
 65%|██████▍   | 37336/57600 [6:33:10<3:31:38,  1.60it/s]
 65%|██████▍   | 37337/57600 [6:33:10<3:33:03,  1.59it/s]
 65%|██████▍   | 37338/57600 [6:33:11<3:32:36,  1.59it/s]
 65%|██████▍   | 37339/57600 [6:33:11<3:29:07,  1.61it/s]
 65%|██████▍   | 37340/57600 [6:33:12<3:27:57,  1.62it/s]
                                                         
{'loss': 1.1128, 'learning_rate': 4.176655052264808e-07, 'epoch': 412.14}

 65%|██████▍   | 37340/57600 [6:33:12<3:27:57,  1.62it/s]
 65%|██████▍   | 37341/57600 [6:33:13<3:26:35,  1.63it/s]
 65%|██████▍   | 37342/57600 [6:33:13<3:22:53,  1.66it/s]
 65%|██████▍   | 37343/57600 [6:33:14<3:24:49,  1.65it/s]
 65%|██████▍   | 37344/57600 [6:33:14<3:25:37,  1.64it/s]
 65%|██████▍   | 37345/57600 [6:33:15<3:34:48,  1.57it/s]
 65%|██████▍   | 37346/57600 [6:33:16<3:36:30,  1.56it/s]
 65%|██████▍   | 37347/57600 [6:33:16<3:33:33,  1.58it/s]
 65%|██████▍   | 37348/57600 [6:33:17<3:35:21,  1.57it/s]
 65%|██████▍   | 37349/57600 [6:33:18<3:36:19,  1.56it/s]
 65%|██████▍   | 37350/57600 [6:33:18<3:38:41,  1.54it/s]
 65%|██████▍   | 37351/57600 [6:33:19<3:34:48,  1.57it/s]
 65%|██████▍   | 37352/57600 [6:33:20<3:44:28,  1.50it/s]
 65%|██████▍   | 37353/57600 [6:33:20<3:41:19,  1.52it/s]
 65%|██████▍   | 37354/57600 [6:33:21<3:38:04,  1.55it/s]
 65%|██████▍   | 37355/57600 [6:33:22<3:36:26,  1.56it/s]
 65%|██████▍   | 37356/57600 [6:33:22<3:34:20,  1.57it/s]
 65%|██████▍   | 37357/57600 [6:33:23<3:36:07,  1.56it/s]
 65%|██████▍   | 37358/57600 [6:33:24<3:37:36,  1.55it/s]
 65%|██████▍   | 37359/57600 [6:33:24<3:33:55,  1.58it/s]
 65%|██████▍   | 37360/57600 [6:33:25<3:35:37,  1.56it/s]
                                                         
{'loss': 1.1165, 'learning_rate': 4.173519163763066e-07, 'epoch': 412.36}

 65%|██████▍   | 37360/57600 [6:33:25<3:35:37,  1.56it/s]
 65%|██████▍   | 37361/57600 [6:33:26<3:39:55,  1.53it/s]
 65%|██████▍   | 37362/57600 [6:33:26<3:38:12,  1.55it/s]
 65%|██████▍   | 37363/57600 [6:33:27<3:31:35,  1.59it/s]
 65%|██████▍   | 37364/57600 [6:33:27<3:33:23,  1.58it/s]
 65%|██████▍   | 37365/57600 [6:33:28<3:37:44,  1.55it/s]
 65%|██████▍   | 37366/57600 [6:33:29<3:35:55,  1.56it/s]
 65%|██████▍   | 37367/57600 [6:33:29<3:33:24,  1.58it/s]
 65%|██████▍   | 37368/57600 [6:33:30<3:34:05,  1.58it/s]
 65%|██████▍   | 37369/57600 [6:33:31<3:40:37,  1.53it/s]
 65%|██████▍   | 37370/57600 [6:33:31<3:36:57,  1.55it/s]
 65%|██████▍   | 37371/57600 [6:33:32<3:39:33,  1.54it/s]
 65%|██████▍   | 37372/57600 [6:33:33<3:40:54,  1.53it/s]
 65%|██████▍   | 37373/57600 [6:33:33<3:34:18,  1.57it/s]
 65%|██████▍   | 37374/57600 [6:33:34<3:30:45,  1.60it/s]
 65%|██████▍   | 37375/57600 [6:33:34<3:28:26,  1.62it/s]
 65%|██████▍   | 37376/57600 [6:33:35<3:26:30,  1.63it/s]
 65%|██████▍   | 37377/57600 [6:33:36<3:31:50,  1.59it/s]
 65%|██████▍   | 37378/57600 [6:33:36<3:36:23,  1.56it/s]
 65%|██████▍   | 37379/57600 [6:33:37<3:37:30,  1.55it/s]
 65%|██████▍   | 37380/57600 [6:33:38<3:32:13,  1.59it/s]
                                                         
{'loss': 1.1412, 'learning_rate': 4.1703832752613234e-07, 'epoch': 412.58}

 65%|██████▍   | 37380/57600 [6:33:38<3:32:13,  1.59it/s]
 65%|██████▍   | 37381/57600 [6:33:38<3:30:23,  1.60it/s]
 65%|██████▍   | 37382/57600 [6:33:39<3:21:19,  1.67it/s]
 65%|██████▍   | 37383/57600 [6:33:39<3:21:29,  1.67it/s]
 65%|██████▍   | 37384/57600 [6:33:40<3:28:37,  1.61it/s]
 65%|██████▍   | 37385/57600 [6:33:41<3:26:51,  1.63it/s]
 65%|██████▍   | 37386/57600 [6:33:41<3:28:56,  1.61it/s]
 65%|██████▍   | 37387/57600 [6:33:42<3:30:27,  1.60it/s]
 65%|██████▍   | 37388/57600 [6:33:42<3:30:45,  1.60it/s]
 65%|██████▍   | 37389/57600 [6:33:43<3:31:42,  1.59it/s]
 65%|██████▍   | 37390/57600 [6:33:44<3:27:58,  1.62it/s]
 65%|██████▍   | 37391/57600 [6:33:44<3:23:32,  1.65it/s]
 65%|██████▍   | 37392/57600 [6:33:45<3:24:35,  1.65it/s]
 65%|██████▍   | 37393/57600 [6:33:46<3:27:14,  1.63it/s]
 65%|██████▍   | 37394/57600 [6:33:46<3:31:38,  1.59it/s]
 65%|██████▍   | 37395/57600 [6:33:47<3:23:54,  1.65it/s]
 65%|██████▍   | 37396/57600 [6:33:47<3:22:56,  1.66it/s]
 65%|██████▍   | 37397/57600 [6:33:48<3:24:17,  1.65it/s]
 65%|██████▍   | 37398/57600 [6:33:49<3:19:52,  1.68it/s]
 65%|██████▍   | 37399/57600 [6:33:49<3:19:23,  1.69it/s]
 65%|██████▍   | 37400/57600 [6:33:50<3:19:28,  1.69it/s]
                                                         
{'loss': 1.1862, 'learning_rate': 4.1672473867595815e-07, 'epoch': 412.8}

 65%|██████▍   | 37400/57600 [6:33:50<3:19:28,  1.69it/s]
 65%|██████▍   | 37401/57600 [6:33:50<3:26:54,  1.63it/s]
 65%|██████▍   | 37402/57600 [6:33:51<3:32:03,  1.59it/s]
 65%|██████▍   | 37403/57600 [6:33:52<3:26:42,  1.63it/s]
 65%|██████▍   | 37404/57600 [6:33:52<3:21:32,  1.67it/s]
 65%|██████▍   | 37405/57600 [6:33:53<3:24:45,  1.64it/s]
 65%|██████▍   | 37406/57600 [6:33:53<3:27:51,  1.62it/s]
 65%|██████▍   | 37407/57600 [6:33:54<3:27:45,  1.62it/s]
 65%|██████▍   | 37408/57600 [6:33:55<3:27:56,  1.62it/s]
 65%|██████▍   | 37409/57600 [6:33:55<3:31:52,  1.59it/s]
 65%|██████▍   | 37410/57600 [6:33:56<3:34:09,  1.57it/s]
 65%|██████▍   | 37411/57600 [6:33:57<3:31:22,  1.59it/s]
 65%|██████▍   | 37412/57600 [6:33:57<3:32:27,  1.58it/s]
 65%|██████▍   | 37413/57600 [6:33:58<3:30:04,  1.60it/s]
 65%|██████▍   | 37414/57600 [6:33:58<3:27:41,  1.62it/s]
 65%|██████▍   | 37415/57600 [6:33:59<3:38:03,  1.54it/s]
 65%|██████▍   | 37416/57600 [6:34:00<3:35:38,  1.56it/s]
 65%|██████▍   | 37417/57600 [6:34:00<3:32:32,  1.58it/s]
 65%|██████▍   | 37418/57600 [6:34:01<3:42:57,  1.51it/s]
 65%|██████▍   | 37419/57600 [6:34:02<3:37:48,  1.54it/s]
 65%|██████▍   | 37420/57600 [6:34:02<3:34:31,  1.57it/s]
                                                         
{'loss': 1.1466, 'learning_rate': 4.16411149825784e-07, 'epoch': 413.02}

 65%|██████▍   | 37420/57600 [6:34:02<3:34:31,  1.57it/s]
 65%|██████▍   | 37421/57600 [6:34:03<3:30:47,  1.60it/s]
 65%|██████▍   | 37422/57600 [6:34:04<3:32:23,  1.58it/s]
 65%|██████▍   | 37423/57600 [6:34:04<3:34:29,  1.57it/s]
 65%|██████▍   | 37424/57600 [6:34:05<3:33:48,  1.57it/s]
 65%|██████▍   | 37425/57600 [6:34:06<3:33:59,  1.57it/s]
 65%|██████▍   | 37426/57600 [6:34:06<3:34:27,  1.57it/s]
 65%|██████▍   | 37427/57600 [6:34:07<3:38:24,  1.54it/s]
 65%|██████▍   | 37428/57600 [6:34:07<3:35:03,  1.56it/s]
 65%|██████▍   | 37429/57600 [6:34:08<3:31:39,  1.59it/s]
 65%|██████▍   | 37430/57600 [6:34:09<3:25:57,  1.63it/s]
 65%|██████▍   | 37431/57600 [6:34:09<3:30:56,  1.59it/s]
 65%|██████▍   | 37432/57600 [6:34:10<3:35:03,  1.56it/s]
 65%|██████▍   | 37433/57600 [6:34:11<3:37:48,  1.54it/s]
 65%|██████▍   | 37434/57600 [6:34:11<3:43:21,  1.50it/s]
 65%|██████▍   | 37435/57600 [6:34:12<3:40:16,  1.53it/s]
 65%|██████▍   | 37436/57600 [6:34:13<3:33:12,  1.58it/s]
 65%|██████▍   | 37437/57600 [6:34:13<3:28:45,  1.61it/s]
 65%|██████▍   | 37438/57600 [6:34:14<3:34:08,  1.57it/s]
 65%|██████▍   | 37439/57600 [6:34:14<3:35:43,  1.56it/s]
 65%|██████▌   | 37440/57600 [6:34:15<3:29:05,  1.61it/s]
                                                         
{'loss': 1.1462, 'learning_rate': 4.160975609756097e-07, 'epoch': 413.25}

 65%|██████▌   | 37440/57600 [6:34:15<3:29:05,  1.61it/s]
 65%|██████▌   | 37441/57600 [6:34:16<3:32:24,  1.58it/s]
 65%|██████▌   | 37442/57600 [6:34:16<3:32:01,  1.58it/s]
 65%|██████▌   | 37443/57600 [6:34:17<3:26:57,  1.62it/s]
 65%|██████▌   | 37444/57600 [6:34:18<3:25:59,  1.63it/s]
 65%|██████▌   | 37445/57600 [6:34:18<3:30:48,  1.59it/s]
 65%|██████▌   | 37446/57600 [6:34:19<3:30:03,  1.60it/s]
 65%|██████▌   | 37447/57600 [6:34:19<3:28:55,  1.61it/s]
 65%|██████▌   | 37448/57600 [6:34:20<3:24:05,  1.65it/s]
 65%|██████▌   | 37449/57600 [6:34:21<3:23:41,  1.65it/s]
 65%|██████▌   | 37450/57600 [6:34:21<3:31:01,  1.59it/s]
 65%|██████▌   | 37451/57600 [6:34:22<3:34:08,  1.57it/s]
 65%|██████▌   | 37452/57600 [6:34:23<3:39:28,  1.53it/s]
 65%|██████▌   | 37453/57600 [6:34:23<3:31:26,  1.59it/s]
 65%|██████▌   | 37454/57600 [6:34:24<3:30:53,  1.59it/s]
 65%|██████▌   | 37455/57600 [6:34:24<3:31:58,  1.58it/s]
 65%|██████▌   | 37456/57600 [6:34:25<3:28:11,  1.61it/s]
 65%|██████▌   | 37457/57600 [6:34:26<3:27:21,  1.62it/s]
 65%|██████▌   | 37458/57600 [6:34:26<3:37:44,  1.54it/s]
 65%|██████▌   | 37459/57600 [6:34:27<3:33:21,  1.57it/s]
 65%|██████▌   | 37460/57600 [6:34:28<3:30:11,  1.60it/s]
                                                         
{'loss': 1.1418, 'learning_rate': 4.1578397212543556e-07, 'epoch': 413.47}

 65%|██████▌   | 37460/57600 [6:34:28<3:30:11,  1.60it/s]
 65%|██████▌   | 37461/57600 [6:34:28<3:24:34,  1.64it/s]
 65%|██████▌   | 37462/57600 [6:34:29<3:27:13,  1.62it/s]
 65%|██████▌   | 37463/57600 [6:34:29<3:32:58,  1.58it/s]
 65%|██████▌   | 37464/57600 [6:34:30<3:33:27,  1.57it/s]
 65%|██████▌   | 37465/57600 [6:34:31<3:31:13,  1.59it/s]
 65%|██████▌   | 37466/57600 [6:34:31<3:26:41,  1.62it/s]
 65%|██████▌   | 37467/57600 [6:34:32<3:28:08,  1.61it/s]
 65%|██████▌   | 37468/57600 [6:34:33<3:27:17,  1.62it/s]
 65%|██████▌   | 37469/57600 [6:34:33<3:26:35,  1.62it/s]
 65%|██████▌   | 37470/57600 [6:34:34<3:30:10,  1.60it/s]
 65%|██████▌   | 37471/57600 [6:34:34<3:35:48,  1.55it/s]
 65%|██████▌   | 37472/57600 [6:34:35<3:33:06,  1.57it/s]
 65%|██████▌   | 37473/57600 [6:34:36<3:37:39,  1.54it/s]
 65%|██████▌   | 37474/57600 [6:34:36<3:40:58,  1.52it/s]
 65%|██████▌   | 37475/57600 [6:34:37<3:41:51,  1.51it/s]
 65%|██████▌   | 37476/57600 [6:34:38<3:36:58,  1.55it/s]
 65%|██████▌   | 37477/57600 [6:34:38<3:29:55,  1.60it/s]
 65%|██████▌   | 37478/57600 [6:34:39<3:28:48,  1.61it/s]
 65%|██████▌   | 37479/57600 [6:34:40<3:37:55,  1.54it/s]
 65%|██████▌   | 37480/57600 [6:34:40<3:37:28,  1.54it/s]
                                                         
{'loss': 1.1285, 'learning_rate': 4.1547038327526126e-07, 'epoch': 413.69}

 65%|██████▌   | 37480/57600 [6:34:40<3:37:28,  1.54it/s]
 65%|██████▌   | 37481/57600 [6:34:41<3:31:23,  1.59it/s]
 65%|██████▌   | 37482/57600 [6:34:41<3:25:46,  1.63it/s]
 65%|██████▌   | 37483/57600 [6:34:42<3:28:25,  1.61it/s]
 65%|██████▌   | 37484/57600 [6:34:43<3:27:22,  1.62it/s]
 65%|██████▌   | 37485/57600 [6:34:43<3:32:24,  1.58it/s]
 65%|██████▌   | 37486/57600 [6:34:44<3:29:58,  1.60it/s]
 65%|██████▌   | 37487/57600 [6:34:45<3:32:47,  1.58it/s]
 65%|██████▌   | 37488/57600 [6:34:45<3:29:22,  1.60it/s]
 65%|██████▌   | 37489/57600 [6:34:46<3:31:51,  1.58it/s]
 65%|██████▌   | 37490/57600 [6:34:46<3:27:07,  1.62it/s]
 65%|██████▌   | 37491/57600 [6:34:47<3:30:04,  1.60it/s]
 65%|██████▌   | 37492/57600 [6:34:48<3:28:15,  1.61it/s]
 65%|██████▌   | 37493/57600 [6:34:48<3:30:33,  1.59it/s]
 65%|██████▌   | 37494/57600 [6:34:49<3:27:13,  1.62it/s]
 65%|██████▌   | 37495/57600 [6:34:50<3:28:23,  1.61it/s]
 65%|██████▌   | 37496/57600 [6:34:50<3:35:10,  1.56it/s]
 65%|██████▌   | 37497/57600 [6:34:51<3:30:52,  1.59it/s]
 65%|██████▌   | 37498/57600 [6:34:52<3:30:51,  1.59it/s]
 65%|██████▌   | 37499/57600 [6:34:52<3:29:02,  1.60it/s]
 65%|██████▌   | 37500/57600 [6:34:53<3:25:44,  1.63it/s]
                                                         
{'loss': 1.1471, 'learning_rate': 4.151567944250871e-07, 'epoch': 413.91}

 65%|██████▌   | 37500/57600 [6:34:53<3:25:44,  1.63it/s]
 65%|██████▌   | 37501/57600 [6:34:53<3:26:46,  1.62it/s]
 65%|██████▌   | 37502/57600 [6:34:54<3:25:09,  1.63it/s]
 65%|██████▌   | 37503/57600 [6:34:55<3:26:49,  1.62it/s]
 65%|██████▌   | 37504/57600 [6:34:55<3:25:22,  1.63it/s]
 65%|██████▌   | 37505/57600 [6:34:56<3:23:57,  1.64it/s]
 65%|██████▌   | 37506/57600 [6:34:56<3:28:53,  1.60it/s]
 65%|██████▌   | 37507/57600 [6:34:57<3:32:04,  1.58it/s]
 65%|██████▌   | 37508/57600 [6:34:58<3:28:15,  1.61it/s]
 65%|██████▌   | 37509/57600 [6:34:58<3:36:22,  1.55it/s]
 65%|██████▌   | 37510/57600 [6:34:59<3:30:44,  1.59it/s]
 65%|██████▌   | 37511/57600 [6:35:00<3:25:21,  1.63it/s]
 65%|██████▌   | 37512/57600 [6:35:00<3:27:13,  1.62it/s]
 65%|██████▌   | 37513/57600 [6:35:01<3:22:21,  1.65it/s]
 65%|██████▌   | 37514/57600 [6:35:01<3:21:26,  1.66it/s]
 65%|██████▌   | 37515/57600 [6:35:02<3:24:30,  1.64it/s]
 65%|██████▌   | 37516/57600 [6:35:03<3:24:29,  1.64it/s]
 65%|██████▌   | 37517/57600 [6:35:03<3:25:46,  1.63it/s]
 65%|██████▌   | 37518/57600 [6:35:04<3:25:58,  1.62it/s]
 65%|██████▌   | 37519/57600 [6:35:04<3:23:49,  1.64it/s]
 65%|██████▌   | 37520/57600 [6:35:05<3:23:26,  1.65it/s]
                                                         
{'loss': 1.1541, 'learning_rate': 4.148432055749128e-07, 'epoch': 414.13}

 65%|██████▌   | 37520/57600 [6:35:05<3:23:26,  1.65it/s]
 65%|██████▌   | 37521/57600 [6:35:06<3:33:09,  1.57it/s]
 65%|██████▌   | 37522/57600 [6:35:06<3:38:24,  1.53it/s]
 65%|██████▌   | 37523/57600 [6:35:07<3:37:45,  1.54it/s]
 65%|██████▌   | 37524/57600 [6:35:08<3:35:59,  1.55it/s]
 65%|██████▌   | 37525/57600 [6:35:08<3:36:40,  1.54it/s]
 65%|██████▌   | 37526/57600 [6:35:09<3:26:02,  1.62it/s]
 65%|██████▌   | 37527/57600 [6:35:10<3:23:50,  1.64it/s]
 65%|██████▌   | 37528/57600 [6:35:10<3:27:05,  1.62it/s]
 65%|██████▌   | 37529/57600 [6:35:11<3:27:43,  1.61it/s]
 65%|██████▌   | 37530/57600 [6:35:11<3:23:16,  1.65it/s]
 65%|██████▌   | 37531/57600 [6:35:12<3:31:04,  1.58it/s]
 65%|██████▌   | 37532/57600 [6:35:13<3:23:43,  1.64it/s]
 65%|██████▌   | 37533/57600 [6:35:13<3:23:48,  1.64it/s]
 65%|██████▌   | 37534/57600 [6:35:14<3:33:12,  1.57it/s]
 65%|██████▌   | 37535/57600 [6:35:15<3:30:45,  1.59it/s]
 65%|██████▌   | 37536/57600 [6:35:15<3:24:54,  1.63it/s]
 65%|██████▌   | 37537/57600 [6:35:16<3:25:08,  1.63it/s]
 65%|██████▌   | 37538/57600 [6:35:16<3:27:23,  1.61it/s]
 65%|██████▌   | 37539/57600 [6:35:17<3:30:04,  1.59it/s]
 65%|██████▌   | 37540/57600 [6:35:18<3:33:31,  1.57it/s]
                                                         
{'loss': 1.1447, 'learning_rate': 4.145296167247386e-07, 'epoch': 414.35}

 65%|██████▌   | 37540/57600 [6:35:18<3:33:31,  1.57it/s]
 65%|██████▌   | 37541/57600 [6:35:18<3:31:24,  1.58it/s]
 65%|██████▌   | 37542/57600 [6:35:19<3:29:19,  1.60it/s]
 65%|██████▌   | 37543/57600 [6:35:20<3:28:46,  1.60it/s]
 65%|██████▌   | 37544/57600 [6:35:20<3:37:48,  1.53it/s]
 65%|██████▌   | 37545/57600 [6:35:21<3:32:08,  1.58it/s]
 65%|██████▌   | 37546/57600 [6:35:22<3:44:09,  1.49it/s]
 65%|██████▌   | 37547/57600 [6:35:22<3:35:53,  1.55it/s]
 65%|██████▌   | 37548/57600 [6:35:23<3:34:17,  1.56it/s]
 65%|██████▌   | 37549/57600 [6:35:23<3:35:08,  1.55it/s]
 65%|██████▌   | 37550/57600 [6:35:24<3:30:15,  1.59it/s]
 65%|██████▌   | 37551/57600 [6:35:25<3:25:04,  1.63it/s]
 65%|██████▌   | 37552/57600 [6:35:25<3:26:18,  1.62it/s]
 65%|██████▌   | 37553/57600 [6:35:26<3:30:43,  1.59it/s]
 65%|██████▌   | 37554/57600 [6:35:26<3:26:07,  1.62it/s]
 65%|██████▌   | 37555/57600 [6:35:27<3:24:23,  1.63it/s]
 65%|██████▌   | 37556/57600 [6:35:28<3:23:42,  1.64it/s]
 65%|██████▌   | 37557/57600 [6:35:28<3:26:00,  1.62it/s]
 65%|██████▌   | 37558/57600 [6:35:29<3:28:11,  1.60it/s]
 65%|██████▌   | 37559/57600 [6:35:30<3:35:05,  1.55it/s]
 65%|██████▌   | 37560/57600 [6:35:30<3:28:25,  1.60it/s]
                                                         
{'loss': 1.1477, 'learning_rate': 4.142160278745645e-07, 'epoch': 414.57}

 65%|██████▌   | 37560/57600 [6:35:30<3:28:25,  1.60it/s]
 65%|██████▌   | 37561/57600 [6:35:31<3:23:34,  1.64it/s]
 65%|██████▌   | 37562/57600 [6:35:31<3:23:57,  1.64it/s]
 65%|██████▌   | 37563/57600 [6:35:32<3:24:06,  1.64it/s]
 65%|██████▌   | 37564/57600 [6:35:33<3:30:10,  1.59it/s]
 65%|██████▌   | 37565/57600 [6:35:33<3:26:57,  1.61it/s]
 65%|██████▌   | 37566/57600 [6:35:34<3:23:28,  1.64it/s]
 65%|██████▌   | 37567/57600 [6:35:35<3:28:03,  1.60it/s]
 65%|██████▌   | 37568/57600 [6:35:35<3:28:28,  1.60it/s]
 65%|██████▌   | 37569/57600 [6:35:36<3:32:59,  1.57it/s]
 65%|██████▌   | 37570/57600 [6:35:36<3:32:37,  1.57it/s]
 65%|██████▌   | 37571/57600 [6:35:37<3:28:35,  1.60it/s]
 65%|██████▌   | 37572/57600 [6:35:38<3:35:02,  1.55it/s]
 65%|██████▌   | 37573/57600 [6:35:38<3:34:08,  1.56it/s]
 65%|██████▌   | 37574/57600 [6:35:39<3:28:47,  1.60it/s]
 65%|██████▌   | 37575/57600 [6:35:40<3:30:16,  1.59it/s]
 65%|██████▌   | 37576/57600 [6:35:40<3:36:54,  1.54it/s]
 65%|██████▌   | 37577/57600 [6:35:41<3:40:40,  1.51it/s]
 65%|██████▌   | 37578/57600 [6:35:42<3:42:15,  1.50it/s]
 65%|██████▌   | 37579/57600 [6:35:42<3:40:51,  1.51it/s]
 65%|██████▌   | 37580/57600 [6:35:43<3:38:56,  1.52it/s]
                                                         
{'loss': 1.1384, 'learning_rate': 4.139024390243902e-07, 'epoch': 414.79}

 65%|██████▌   | 37580/57600 [6:35:43<3:38:56,  1.52it/s]
 65%|██████▌   | 37581/57600 [6:35:44<3:35:37,  1.55it/s]
 65%|██████▌   | 37582/57600 [6:35:44<3:27:59,  1.60it/s]
 65%|██████▌   | 37583/57600 [6:35:45<3:25:58,  1.62it/s]
 65%|██████▌   | 37584/57600 [6:35:45<3:22:12,  1.65it/s]
 65%|██████▌   | 37585/57600 [6:35:46<3:24:51,  1.63it/s]
 65%|██████▌   | 37586/57600 [6:35:47<3:24:23,  1.63it/s]
 65%|██████▌   | 37587/57600 [6:35:47<3:26:55,  1.61it/s]
 65%|██████▌   | 37588/57600 [6:35:48<3:30:21,  1.59it/s]
 65%|██████▌   | 37589/57600 [6:35:49<3:30:08,  1.59it/s]
 65%|██████▌   | 37590/57600 [6:35:49<3:23:34,  1.64it/s]
 65%|██████▌   | 37591/57600 [6:35:50<3:23:02,  1.64it/s]
 65%|██████▌   | 37592/57600 [6:35:50<3:24:32,  1.63it/s]
 65%|██████▌   | 37593/57600 [6:35:51<3:25:08,  1.63it/s]
 65%|██████▌   | 37594/57600 [6:35:52<3:24:06,  1.63it/s]
 65%|██████▌   | 37595/57600 [6:35:52<3:27:34,  1.61it/s]
 65%|██████▌   | 37596/57600 [6:35:53<3:30:01,  1.59it/s]
 65%|██████▌   | 37597/57600 [6:35:54<3:34:25,  1.55it/s]
 65%|██████▌   | 37598/57600 [6:35:54<3:36:51,  1.54it/s]
 65%|██████▌   | 37599/57600 [6:35:55<3:40:46,  1.51it/s]
 65%|██████▌   | 37600/57600 [6:35:56<3:46:32,  1.47it/s]
                                                         
{'loss': 1.1892, 'learning_rate': 4.1358885017421604e-07, 'epoch': 415.01}

 65%|██████▌   | 37600/57600 [6:35:56<3:46:32,  1.47it/s]
 65%|██████▌   | 37601/57600 [6:35:56<3:43:12,  1.49it/s]
 65%|██████▌   | 37602/57600 [6:35:57<3:36:22,  1.54it/s]
 65%|██████▌   | 37603/57600 [6:35:57<3:27:53,  1.60it/s]
 65%|██████▌   | 37604/57600 [6:35:58<3:24:45,  1.63it/s]
 65%|██████▌   | 37605/57600 [6:35:59<3:20:48,  1.66it/s]
 65%|██████▌   | 37606/57600 [6:35:59<3:23:52,  1.63it/s]
 65%|██████▌   | 37607/57600 [6:36:00<3:21:34,  1.65it/s]
 65%|██████▌   | 37608/57600 [6:36:00<3:26:40,  1.61it/s]
 65%|██████▌   | 37609/57600 [6:36:01<3:30:39,  1.58it/s]
 65%|██████▌   | 37610/57600 [6:36:02<3:25:14,  1.62it/s]
 65%|██████▌   | 37611/57600 [6:36:02<3:33:45,  1.56it/s]
 65%|██████▌   | 37612/57600 [6:36:03<3:28:32,  1.60it/s]
 65%|██████▌   | 37613/57600 [6:36:04<3:29:01,  1.59it/s]
 65%|██████▌   | 37614/57600 [6:36:04<3:26:19,  1.61it/s]
 65%|██████▌   | 37615/57600 [6:36:05<3:30:09,  1.58it/s]
 65%|██████▌   | 37616/57600 [6:36:05<3:26:44,  1.61it/s]
 65%|██████▌   | 37617/57600 [6:36:06<3:39:15,  1.52it/s]
 65%|██████▌   | 37618/57600 [6:36:07<3:40:13,  1.51it/s]
 65%|██████▌   | 37619/57600 [6:36:07<3:35:24,  1.55it/s]
 65%|██████▌   | 37620/57600 [6:36:08<3:39:01,  1.52it/s]
                                                         
{'loss': 1.128, 'learning_rate': 4.1327526132404174e-07, 'epoch': 415.23}

 65%|██████▌   | 37620/57600 [6:36:08<3:39:01,  1.52it/s]
 65%|██████▌   | 37621/57600 [6:36:09<3:39:52,  1.51it/s]
 65%|██████▌   | 37622/57600 [6:36:09<3:32:40,  1.57it/s]
 65%|██████▌   | 37623/57600 [6:36:10<3:30:36,  1.58it/s]
 65%|██████▌   | 37624/57600 [6:36:11<3:26:54,  1.61it/s]
 65%|██████▌   | 37625/57600 [6:36:11<3:29:59,  1.59it/s]
 65%|██████▌   | 37626/57600 [6:36:12<3:36:01,  1.54it/s]
 65%|██████▌   | 37627/57600 [6:36:13<3:28:57,  1.59it/s]
 65%|██████▌   | 37628/57600 [6:36:13<3:28:45,  1.59it/s]
 65%|██████▌   | 37629/57600 [6:36:14<3:26:47,  1.61it/s]
 65%|██████▌   | 37630/57600 [6:36:14<3:29:24,  1.59it/s]
 65%|██████▌   | 37631/57600 [6:36:15<3:28:47,  1.59it/s]
 65%|██████▌   | 37632/57600 [6:36:16<3:31:20,  1.57it/s]
 65%|██████▌   | 37633/57600 [6:36:16<3:36:24,  1.54it/s]
 65%|██████▌   | 37634/57600 [6:36:17<3:34:38,  1.55it/s]
 65%|██████▌   | 37635/57600 [6:36:18<3:37:50,  1.53it/s]
 65%|██████▌   | 37636/57600 [6:36:18<3:33:01,  1.56it/s]
 65%|██████▌   | 37637/57600 [6:36:19<3:28:11,  1.60it/s]
 65%|██████▌   | 37638/57600 [6:36:19<3:23:05,  1.64it/s]
 65%|██████▌   | 37639/57600 [6:36:20<3:28:07,  1.60it/s]
 65%|██████▌   | 37640/57600 [6:36:21<3:26:12,  1.61it/s]
                                                         
{'loss': 1.1521, 'learning_rate': 4.129616724738676e-07, 'epoch': 415.45}

 65%|██████▌   | 37640/57600 [6:36:21<3:26:12,  1.61it/s]
 65%|██████▌   | 37641/57600 [6:36:21<3:30:45,  1.58it/s]
 65%|██████▌   | 37642/57600 [6:36:22<3:24:07,  1.63it/s]
 65%|██████▌   | 37643/57600 [6:36:23<3:23:21,  1.64it/s]
 65%|██████▌   | 37644/57600 [6:36:23<3:28:33,  1.59it/s]
 65%|██████▌   | 37645/57600 [6:36:24<3:25:36,  1.62it/s]
 65%|██████▌   | 37646/57600 [6:36:24<3:26:46,  1.61it/s]
 65%|██████▌   | 37647/57600 [6:36:25<3:35:59,  1.54it/s]
 65%|██████▌   | 37648/57600 [6:36:26<3:35:46,  1.54it/s]
 65%|██████▌   | 37649/57600 [6:36:26<3:34:30,  1.55it/s]
 65%|██████▌   | 37650/57600 [6:36:27<3:38:07,  1.52it/s]
 65%|██████▌   | 37651/57600 [6:36:28<3:33:04,  1.56it/s]
 65%|██████▌   | 37652/57600 [6:36:28<3:33:32,  1.56it/s]
 65%|██████▌   | 37653/57600 [6:36:29<3:27:35,  1.60it/s]
 65%|██████▌   | 37654/57600 [6:36:30<3:20:41,  1.66it/s]
 65%|██████▌   | 37655/57600 [6:36:30<3:18:01,  1.68it/s]
 65%|██████▌   | 37656/57600 [6:36:31<3:21:12,  1.65it/s]
 65%|██████▌   | 37657/57600 [6:36:31<3:30:41,  1.58it/s]
 65%|██████▌   | 37658/57600 [6:36:32<3:29:16,  1.59it/s]
 65%|██████▌   | 37659/57600 [6:36:33<3:26:14,  1.61it/s]
 65%|██████▌   | 37660/57600 [6:36:33<3:27:26,  1.60it/s]
                                                         
{'loss': 1.127, 'learning_rate': 4.126480836236934e-07, 'epoch': 415.67}

 65%|██████▌   | 37660/57600 [6:36:33<3:27:26,  1.60it/s]
 65%|██████▌   | 37661/57600 [6:36:34<3:25:37,  1.62it/s]
 65%|██████▌   | 37662/57600 [6:36:35<3:26:31,  1.61it/s]
 65%|██████▌   | 37663/57600 [6:36:35<3:21:54,  1.65it/s]
 65%|██████▌   | 37664/57600 [6:36:36<3:28:29,  1.59it/s]
 65%|██████▌   | 37665/57600 [6:36:36<3:29:06,  1.59it/s]
 65%|██████▌   | 37666/57600 [6:36:37<3:28:39,  1.59it/s]
 65%|██████▌   | 37667/57600 [6:36:38<3:25:23,  1.62it/s]
 65%|██████▌   | 37668/57600 [6:36:38<3:31:27,  1.57it/s]
 65%|██████▌   | 37669/57600 [6:36:39<3:29:24,  1.59it/s]
 65%|██████▌   | 37670/57600 [6:36:40<3:23:01,  1.64it/s]
 65%|██████▌   | 37671/57600 [6:36:40<3:28:00,  1.60it/s]
 65%|██████▌   | 37672/57600 [6:36:41<3:28:21,  1.59it/s]
 65%|██████▌   | 37673/57600 [6:36:41<3:24:13,  1.63it/s]
 65%|██████▌   | 37674/57600 [6:36:42<3:23:01,  1.64it/s]
 65%|██████▌   | 37675/57600 [6:36:43<3:28:33,  1.59it/s]
 65%|██████▌   | 37676/57600 [6:36:43<3:26:49,  1.61it/s]
 65%|██████▌   | 37677/57600 [6:36:44<3:34:00,  1.55it/s]
 65%|██████▌   | 37678/57600 [6:36:45<3:33:43,  1.55it/s]
 65%|██████▌   | 37679/57600 [6:36:45<3:28:59,  1.59it/s]
 65%|██████▌   | 37680/57600 [6:36:46<3:29:46,  1.58it/s]
                                                         
{'loss': 1.1564, 'learning_rate': 4.1233449477351915e-07, 'epoch': 415.89}

 65%|██████▌   | 37680/57600 [6:36:46<3:29:46,  1.58it/s]
 65%|██████▌   | 37681/57600 [6:36:46<3:30:00,  1.58it/s]
 65%|██████▌   | 37682/57600 [6:36:47<3:23:42,  1.63it/s]
 65%|██████▌   | 37683/57600 [6:36:48<3:23:53,  1.63it/s]
 65%|██████▌   | 37684/57600 [6:36:48<3:21:59,  1.64it/s]
 65%|██████▌   | 37685/57600 [6:36:49<3:25:41,  1.61it/s]
 65%|██████▌   | 37686/57600 [6:36:50<3:29:31,  1.58it/s]
 65%|██████▌   | 37687/57600 [6:36:50<3:30:16,  1.58it/s]
 65%|██████▌   | 37688/57600 [6:36:51<3:25:39,  1.61it/s]
 65%|██████▌   | 37689/57600 [6:36:51<3:25:46,  1.61it/s]
 65%|██████▌   | 37690/57600 [6:36:52<3:30:07,  1.58it/s]
 65%|██████▌   | 37691/57600 [6:36:53<3:26:07,  1.61it/s]
 65%|██████▌   | 37692/57600 [6:36:53<3:21:56,  1.64it/s]
 65%|██████▌   | 37693/57600 [6:36:54<3:27:43,  1.60it/s]
 65%|██████▌   | 37694/57600 [6:36:54<3:21:20,  1.65it/s]
 65%|██████▌   | 37695/57600 [6:36:55<3:23:57,  1.63it/s]
 65%|██████▌   | 37696/57600 [6:36:56<3:24:51,  1.62it/s]
 65%|██████▌   | 37697/57600 [6:36:56<3:24:10,  1.62it/s]
 65%|██████▌   | 37698/57600 [6:36:57<3:26:16,  1.61it/s]
 65%|██████▌   | 37699/57600 [6:36:58<3:19:54,  1.66it/s]
 65%|██████▌   | 37700/57600 [6:36:58<3:23:02,  1.63it/s]
                                                         
{'loss': 1.1432, 'learning_rate': 4.12020905923345e-07, 'epoch': 416.11}

 65%|██████▌   | 37700/57600 [6:36:58<3:23:02,  1.63it/s]
 65%|██████▌   | 37701/57600 [6:36:59<3:21:35,  1.65it/s]
 65%|██████▌   | 37702/57600 [6:36:59<3:31:16,  1.57it/s]
 65%|██████▌   | 37703/57600 [6:37:00<3:26:53,  1.60it/s]
 65%|██████▌   | 37704/57600 [6:37:01<3:25:03,  1.62it/s]
 65%|██████▌   | 37705/57600 [6:37:01<3:25:43,  1.61it/s]
 65%|██████▌   | 37706/57600 [6:37:02<3:25:29,  1.61it/s]
 65%|██████▌   | 37707/57600 [6:37:03<3:23:24,  1.63it/s]
 65%|██████▌   | 37708/57600 [6:37:03<3:28:23,  1.59it/s]
 65%|██████▌   | 37709/57600 [6:37:04<3:25:57,  1.61it/s]
 65%|██████▌   | 37710/57600 [6:37:04<3:25:36,  1.61it/s]
 65%|██████▌   | 37711/57600 [6:37:05<3:23:41,  1.63it/s]
 65%|██████▌   | 37712/57600 [6:37:06<3:21:43,  1.64it/s]
 65%|██████▌   | 37713/57600 [6:37:06<3:22:19,  1.64it/s]
 65%|██████▌   | 37714/57600 [6:37:07<3:25:30,  1.61it/s]
 65%|██████▌   | 37715/57600 [6:37:07<3:28:26,  1.59it/s]
 65%|██████▌   | 37716/57600 [6:37:08<3:23:36,  1.63it/s]
 65%|██████▌   | 37717/57600 [6:37:09<3:21:44,  1.64it/s]
 65%|██████▌   | 37718/57600 [6:37:09<3:17:52,  1.67it/s]
 65%|██████▌   | 37719/57600 [6:37:10<3:19:20,  1.66it/s]
 65%|██████▌   | 37720/57600 [6:37:11<3:24:31,  1.62it/s]
                                                         
{'loss': 1.1652, 'learning_rate': 4.117073170731707e-07, 'epoch': 416.34}

 65%|██████▌   | 37720/57600 [6:37:11<3:24:31,  1.62it/s]
 65%|██████▌   | 37721/57600 [6:37:11<3:19:14,  1.66it/s]
 65%|██████▌   | 37722/57600 [6:37:12<3:20:16,  1.65it/s]
 65%|██████▌   | 37723/57600 [6:37:12<3:21:43,  1.64it/s]
 65%|██████▌   | 37724/57600 [6:37:13<3:20:31,  1.65it/s]
 65%|██████▌   | 37725/57600 [6:37:14<3:21:09,  1.65it/s]
 65%|██████▌   | 37726/57600 [6:37:14<3:28:00,  1.59it/s]
 65%|██████▌   | 37727/57600 [6:37:15<3:27:20,  1.60it/s]
 66%|██████▌   | 37728/57600 [6:37:15<3:27:25,  1.60it/s]
 66%|██████▌   | 37729/57600 [6:37:16<3:27:29,  1.60it/s]
 66%|██████▌   | 37730/57600 [6:37:17<3:21:44,  1.64it/s]
 66%|██████▌   | 37731/57600 [6:37:17<3:18:47,  1.67it/s]
 66%|██████▌   | 37732/57600 [6:37:18<3:22:28,  1.64it/s]
 66%|██████▌   | 37733/57600 [6:37:18<3:19:35,  1.66it/s]
 66%|██████▌   | 37734/57600 [6:37:19<3:21:59,  1.64it/s]
 66%|██████▌   | 37735/57600 [6:37:20<3:24:10,  1.62it/s]
 66%|██████▌   | 37736/57600 [6:37:20<3:31:19,  1.57it/s]
 66%|██████▌   | 37737/57600 [6:37:21<3:29:21,  1.58it/s]
 66%|██████▌   | 37738/57600 [6:37:22<3:43:12,  1.48it/s]
 66%|██████▌   | 37739/57600 [6:37:22<3:39:43,  1.51it/s]
 66%|██████▌   | 37740/57600 [6:37:23<3:35:38,  1.53it/s]
                                                         
{'loss': 1.1644, 'learning_rate': 4.113937282229965e-07, 'epoch': 416.56}

 66%|██████▌   | 37740/57600 [6:37:23<3:35:38,  1.53it/s]
 66%|██████▌   | 37741/57600 [6:37:24<3:34:16,  1.54it/s]
 66%|██████▌   | 37742/57600 [6:37:24<3:28:55,  1.58it/s]
 66%|██████▌   | 37743/57600 [6:37:25<3:37:17,  1.52it/s]
 66%|██████▌   | 37744/57600 [6:37:26<3:32:35,  1.56it/s]
 66%|██████▌   | 37745/57600 [6:37:26<3:28:23,  1.59it/s]
 66%|██████▌   | 37746/57600 [6:37:27<3:28:38,  1.59it/s]
 66%|██████▌   | 37747/57600 [6:37:27<3:29:20,  1.58it/s]
 66%|██████▌   | 37748/57600 [6:37:28<3:25:11,  1.61it/s]
 66%|██████▌   | 37749/57600 [6:37:29<3:26:12,  1.60it/s]
 66%|██████▌   | 37750/57600 [6:37:29<3:24:24,  1.62it/s]
 66%|██████▌   | 37751/57600 [6:37:30<3:27:06,  1.60it/s]
 66%|██████▌   | 37752/57600 [6:37:31<3:24:45,  1.62it/s]
 66%|██████▌   | 37753/57600 [6:37:31<3:22:48,  1.63it/s]
 66%|██████▌   | 37754/57600 [6:37:32<3:17:14,  1.68it/s]
 66%|██████▌   | 37755/57600 [6:37:32<3:17:30,  1.67it/s]
 66%|██████▌   | 37756/57600 [6:37:33<3:27:59,  1.59it/s]
 66%|██████▌   | 37757/57600 [6:37:34<3:26:45,  1.60it/s]
 66%|██████▌   | 37758/57600 [6:37:34<3:24:58,  1.61it/s]
 66%|██████▌   | 37759/57600 [6:37:35<3:27:46,  1.59it/s]
 66%|██████▌   | 37760/57600 [6:37:35<3:22:05,  1.64it/s]
                                                         
{'loss': 1.1459, 'learning_rate': 4.1108013937282227e-07, 'epoch': 416.78}

 66%|██████▌   | 37760/57600 [6:37:35<3:22:05,  1.64it/s]
 66%|██████▌   | 37761/57600 [6:37:36<3:33:23,  1.55it/s]
 66%|██████▌   | 37762/57600 [6:37:37<3:31:56,  1.56it/s]
 66%|██████▌   | 37763/57600 [6:37:37<3:30:33,  1.57it/s]
 66%|██████▌   | 37764/57600 [6:37:38<3:28:35,  1.58it/s]
 66%|██████▌   | 37765/57600 [6:37:39<3:27:55,  1.59it/s]
 66%|██████▌   | 37766/57600 [6:37:39<3:26:19,  1.60it/s]
 66%|██████▌   | 37767/57600 [6:37:40<3:20:52,  1.65it/s]
 66%|██████▌   | 37768/57600 [6:37:41<3:29:48,  1.58it/s]
 66%|██████▌   | 37769/57600 [6:37:41<3:29:57,  1.57it/s]
 66%|██████▌   | 37770/57600 [6:37:42<3:29:11,  1.58it/s]
 66%|██████▌   | 37771/57600 [6:37:42<3:28:15,  1.59it/s]
 66%|██████▌   | 37772/57600 [6:37:43<3:34:42,  1.54it/s]
 66%|██████▌   | 37773/57600 [6:37:44<3:33:40,  1.55it/s]
 66%|██████▌   | 37774/57600 [6:37:44<3:32:13,  1.56it/s]
 66%|██████▌   | 37775/57600 [6:37:45<3:29:07,  1.58it/s]
 66%|██████▌   | 37776/57600 [6:37:46<3:30:57,  1.57it/s]
 66%|██████▌   | 37777/57600 [6:37:46<3:28:55,  1.58it/s]
 66%|██████▌   | 37778/57600 [6:37:47<3:25:17,  1.61it/s]
 66%|██████▌   | 37779/57600 [6:37:47<3:25:16,  1.61it/s]
 66%|██████▌   | 37780/57600 [6:37:48<3:21:51,  1.64it/s]
                                                         
{'loss': 1.148, 'learning_rate': 4.1076655052264807e-07, 'epoch': 417.0}

 66%|██████▌   | 37780/57600 [6:37:48<3:21:51,  1.64it/s]
 66%|██████▌   | 37781/57600 [6:37:49<3:33:21,  1.55it/s]
 66%|██████▌   | 37782/57600 [6:37:49<3:32:13,  1.56it/s]
 66%|██████▌   | 37783/57600 [6:37:50<3:28:41,  1.58it/s]
 66%|██████▌   | 37784/57600 [6:37:51<3:23:37,  1.62it/s]
 66%|██████▌   | 37785/57600 [6:37:51<3:25:46,  1.60it/s]
 66%|██████▌   | 37786/57600 [6:37:52<3:29:06,  1.58it/s]
 66%|██████▌   | 37787/57600 [6:37:53<3:28:23,  1.58it/s]
 66%|██████▌   | 37788/57600 [6:37:53<3:20:57,  1.64it/s]
 66%|██████▌   | 37789/57600 [6:37:54<3:20:06,  1.65it/s]
 66%|██████▌   | 37790/57600 [6:37:54<3:17:22,  1.67it/s]
 66%|██████▌   | 37791/57600 [6:37:55<3:12:55,  1.71it/s]
 66%|██████▌   | 37792/57600 [6:37:55<3:13:39,  1.70it/s]
 66%|██████▌   | 37793/57600 [6:37:56<3:12:47,  1.71it/s]
 66%|██████▌   | 37794/57600 [6:37:57<3:14:20,  1.70it/s]
 66%|██████▌   | 37795/57600 [6:37:57<3:12:49,  1.71it/s]
 66%|██████▌   | 37796/57600 [6:37:58<3:11:41,  1.72it/s]
 66%|██████▌   | 37797/57600 [6:37:58<3:14:42,  1.70it/s]
 66%|██████▌   | 37798/57600 [6:37:59<3:18:28,  1.66it/s]
 66%|██████▌   | 37799/57600 [6:38:00<3:21:25,  1.64it/s]
 66%|██████▌   | 37800/57600 [6:38:00<3:21:34,  1.64it/s]
                                                         
{'loss': 1.1711, 'learning_rate': 4.104529616724739e-07, 'epoch': 417.22}

 66%|██████▌   | 37800/57600 [6:38:00<3:21:34,  1.64it/s]
 66%|██████▌   | 37801/57600 [6:38:01<3:19:02,  1.66it/s]
 66%|██████▌   | 37802/57600 [6:38:01<3:20:25,  1.65it/s]
 66%|██████▌   | 37803/57600 [6:38:02<3:20:06,  1.65it/s]
 66%|██████▌   | 37804/57600 [6:38:03<3:28:40,  1.58it/s]
 66%|██████▌   | 37805/57600 [6:38:03<3:38:48,  1.51it/s]
 66%|██████▌   | 37806/57600 [6:38:04<3:30:16,  1.57it/s]
 66%|██████▌   | 37807/57600 [6:38:05<3:27:59,  1.59it/s]
 66%|██████▌   | 37808/57600 [6:38:05<3:31:20,  1.56it/s]
 66%|██████▌   | 37809/57600 [6:38:06<3:30:15,  1.57it/s]
 66%|██████▌   | 37810/57600 [6:38:07<3:29:38,  1.57it/s]
 66%|██████▌   | 37811/57600 [6:38:07<3:25:26,  1.61it/s]
 66%|██████▌   | 37812/57600 [6:38:08<3:28:24,  1.58it/s]
 66%|██████▌   | 37813/57600 [6:38:08<3:23:00,  1.62it/s]
 66%|██████▌   | 37814/57600 [6:38:09<3:23:58,  1.62it/s]
 66%|██████▌   | 37815/57600 [6:38:10<3:33:53,  1.54it/s]
 66%|██████▌   | 37816/57600 [6:38:11<3:45:26,  1.46it/s]
 66%|██████▌   | 37817/57600 [6:38:11<3:36:42,  1.52it/s]
 66%|██████▌   | 37818/57600 [6:38:12<3:31:42,  1.56it/s]
 66%|██████▌   | 37819/57600 [6:38:12<3:29:32,  1.57it/s]
 66%|██████▌   | 37820/57600 [6:38:13<3:29:41,  1.57it/s]
                                                         
{'loss': 1.142, 'learning_rate': 4.101393728222996e-07, 'epoch': 417.44}

 66%|██████▌   | 37820/57600 [6:38:13<3:29:41,  1.57it/s]
 66%|██████▌   | 37821/57600 [6:38:14<3:31:08,  1.56it/s]
 66%|██████▌   | 37822/57600 [6:38:14<3:34:20,  1.54it/s]
 66%|██████▌   | 37823/57600 [6:38:15<3:32:05,  1.55it/s]
 66%|██████▌   | 37824/57600 [6:38:16<3:27:41,  1.59it/s]
 66%|██████▌   | 37825/57600 [6:38:16<3:29:41,  1.57it/s]
 66%|██████▌   | 37826/57600 [6:38:17<3:27:25,  1.59it/s]
 66%|██████▌   | 37827/57600 [6:38:17<3:24:00,  1.62it/s]
 66%|██████▌   | 37828/57600 [6:38:18<3:25:56,  1.60it/s]
 66%|██████▌   | 37829/57600 [6:38:19<3:19:34,  1.65it/s]
 66%|██████▌   | 37830/57600 [6:38:19<3:19:59,  1.65it/s]
 66%|██████▌   | 37831/57600 [6:38:20<3:16:44,  1.67it/s]
 66%|██████▌   | 37832/57600 [6:38:20<3:19:23,  1.65it/s]
 66%|██████▌   | 37833/57600 [6:38:21<3:21:58,  1.63it/s]
 66%|██████▌   | 37834/57600 [6:38:22<3:30:12,  1.57it/s]
 66%|██████▌   | 37835/57600 [6:38:22<3:24:27,  1.61it/s]
 66%|██████▌   | 37836/57600 [6:38:23<3:18:40,  1.66it/s]
 66%|██████▌   | 37837/57600 [6:38:24<3:21:48,  1.63it/s]
 66%|██████▌   | 37838/57600 [6:38:24<3:21:44,  1.63it/s]
 66%|██████▌   | 37839/57600 [6:38:25<3:20:40,  1.64it/s]
 66%|██████▌   | 37840/57600 [6:38:25<3:17:32,  1.67it/s]
                                                         
{'loss': 1.1569, 'learning_rate': 4.0982578397212543e-07, 'epoch': 417.66}

 66%|██████▌   | 37840/57600 [6:38:25<3:17:32,  1.67it/s]
 66%|██████▌   | 37841/57600 [6:38:26<3:26:58,  1.59it/s]
 66%|██████▌   | 37842/57600 [6:38:27<3:29:42,  1.57it/s]
 66%|██████▌   | 37843/57600 [6:38:27<3:25:38,  1.60it/s]
 66%|██████▌   | 37844/57600 [6:38:28<3:28:21,  1.58it/s]
 66%|██████▌   | 37845/57600 [6:38:29<3:26:08,  1.60it/s]
 66%|██████▌   | 37846/57600 [6:38:29<3:33:40,  1.54it/s]
 66%|██████▌   | 37847/57600 [6:38:30<3:26:09,  1.60it/s]
 66%|██████▌   | 37848/57600 [6:38:30<3:24:50,  1.61it/s]
 66%|██████▌   | 37849/57600 [6:38:31<3:34:31,  1.53it/s]
 66%|██████▌   | 37850/57600 [6:38:32<3:29:00,  1.57it/s]
 66%|██████▌   | 37851/57600 [6:38:32<3:23:46,  1.62it/s]
 66%|██████▌   | 37852/57600 [6:38:33<3:17:07,  1.67it/s]
 66%|██████▌   | 37853/57600 [6:38:33<3:20:15,  1.64it/s]
 66%|██████▌   | 37854/57600 [6:38:34<3:18:50,  1.66it/s]
 66%|██████▌   | 37855/57600 [6:38:35<3:19:17,  1.65it/s]
 66%|██████▌   | 37856/57600 [6:38:35<3:24:20,  1.61it/s]
 66%|██████▌   | 37857/57600 [6:38:36<3:23:09,  1.62it/s]
 66%|██████▌   | 37858/57600 [6:38:37<3:21:39,  1.63it/s]
 66%|██████▌   | 37859/57600 [6:38:37<3:27:16,  1.59it/s]
 66%|██████▌   | 37860/57600 [6:38:38<3:29:43,  1.57it/s]
                                                         
{'loss': 1.1337, 'learning_rate': 4.095121951219512e-07, 'epoch': 417.88}

 66%|██████▌   | 37860/57600 [6:38:38<3:29:43,  1.57it/s]
 66%|██████▌   | 37861/57600 [6:38:38<3:22:55,  1.62it/s]
 66%|██████▌   | 37862/57600 [6:38:39<3:34:37,  1.53it/s]
 66%|██████▌   | 37863/57600 [6:38:40<3:33:11,  1.54it/s]
 66%|██████▌   | 37864/57600 [6:38:40<3:24:43,  1.61it/s]
 66%|██████▌   | 37865/57600 [6:38:41<3:22:23,  1.63it/s]
 66%|██████▌   | 37866/57600 [6:38:42<3:29:10,  1.57it/s]
 66%|██████▌   | 37867/57600 [6:38:42<3:30:23,  1.56it/s]
 66%|██████▌   | 37868/57600 [6:38:43<3:28:36,  1.58it/s]
 66%|██████▌   | 37869/57600 [6:38:44<3:26:47,  1.59it/s]
 66%|██████▌   | 37870/57600 [6:38:44<3:36:17,  1.52it/s]
 66%|██████▌   | 37871/57600 [6:38:45<3:42:17,  1.48it/s]
 66%|██████▌   | 37872/57600 [6:38:46<3:39:54,  1.50it/s]
 66%|██████▌   | 37873/57600 [6:38:46<3:31:55,  1.55it/s]
 66%|██████▌   | 37874/57600 [6:38:47<3:32:42,  1.55it/s]
 66%|██████▌   | 37875/57600 [6:38:48<3:37:30,  1.51it/s]
 66%|██████▌   | 37876/57600 [6:38:48<3:30:04,  1.56it/s]
 66%|██████▌   | 37877/57600 [6:38:49<3:26:22,  1.59it/s]
 66%|██████▌   | 37878/57600 [6:38:49<3:26:09,  1.59it/s]
 66%|██████▌   | 37879/57600 [6:38:50<3:22:47,  1.62it/s]
 66%|██████▌   | 37880/57600 [6:38:51<3:22:03,  1.63it/s]
                                                         
{'loss': 1.1481, 'learning_rate': 4.09198606271777e-07, 'epoch': 418.1}

 66%|██████▌   | 37880/57600 [6:38:51<3:22:03,  1.63it/s]
 66%|██████▌   | 37881/57600 [6:38:51<3:19:27,  1.65it/s]
 66%|██████▌   | 37882/57600 [6:38:52<3:28:56,  1.57it/s]
 66%|██████▌   | 37883/57600 [6:38:53<3:27:32,  1.58it/s]
 66%|██████▌   | 37884/57600 [6:38:53<3:31:04,  1.56it/s]
 66%|██████▌   | 37885/57600 [6:38:54<3:27:19,  1.58it/s]
 66%|██████▌   | 37886/57600 [6:38:54<3:26:59,  1.59it/s]
 66%|██████▌   | 37887/57600 [6:38:55<3:25:59,  1.59it/s]
 66%|██████▌   | 37888/57600 [6:38:56<3:19:49,  1.64it/s]
 66%|██████▌   | 37889/57600 [6:38:56<3:25:16,  1.60it/s]
 66%|██████▌   | 37890/57600 [6:38:57<3:33:09,  1.54it/s]
 66%|██████▌   | 37891/57600 [6:38:58<3:30:48,  1.56it/s]
 66%|██████▌   | 37892/57600 [6:38:58<3:33:23,  1.54it/s]
 66%|██████▌   | 37893/57600 [6:38:59<3:29:54,  1.56it/s]
 66%|██████▌   | 37894/57600 [6:39:00<3:29:46,  1.57it/s]
 66%|██████▌   | 37895/57600 [6:39:00<3:26:37,  1.59it/s]
 66%|██████▌   | 37896/57600 [6:39:01<3:25:19,  1.60it/s]
 66%|██████▌   | 37897/57600 [6:39:01<3:22:53,  1.62it/s]
 66%|██████▌   | 37898/57600 [6:39:02<3:27:12,  1.58it/s]
 66%|██████▌   | 37899/57600 [6:39:03<3:22:46,  1.62it/s]
 66%|██████▌   | 37900/57600 [6:39:03<3:20:00,  1.64it/s]
                                                         
{'loss': 1.1402, 'learning_rate': 4.0888501742160274e-07, 'epoch': 418.32}

 66%|██████▌   | 37900/57600 [6:39:03<3:20:00,  1.64it/s]
 66%|██████▌   | 37901/57600 [6:39:04<3:17:13,  1.66it/s]
 66%|██████▌   | 37902/57600 [6:39:04<3:15:42,  1.68it/s]
 66%|██████▌   | 37903/57600 [6:39:05<3:15:12,  1.68it/s]
 66%|██████▌   | 37904/57600 [6:39:06<3:19:44,  1.64it/s]
 66%|██████▌   | 37905/57600 [6:39:06<3:18:07,  1.66it/s]
 66%|██████▌   | 37906/57600 [6:39:07<3:26:31,  1.59it/s]
 66%|██████▌   | 37907/57600 [6:39:07<3:28:09,  1.58it/s]
 66%|██████▌   | 37908/57600 [6:39:08<3:28:42,  1.57it/s]
 66%|██████▌   | 37909/57600 [6:39:09<3:27:49,  1.58it/s]
 66%|██████▌   | 37910/57600 [6:39:09<3:23:07,  1.62it/s]
 66%|██████▌   | 37911/57600 [6:39:10<3:31:34,  1.55it/s]
 66%|██████▌   | 37912/57600 [6:39:11<3:25:05,  1.60it/s]
 66%|██████▌   | 37913/57600 [6:39:11<3:22:39,  1.62it/s]
 66%|██████▌   | 37914/57600 [6:39:12<3:26:38,  1.59it/s]
 66%|██████▌   | 37915/57600 [6:39:12<3:20:15,  1.64it/s]
 66%|██████▌   | 37916/57600 [6:39:13<3:18:40,  1.65it/s]
 66%|██████▌   | 37917/57600 [6:39:14<3:17:44,  1.66it/s]
 66%|██████▌   | 37918/57600 [6:39:14<3:23:00,  1.62it/s]
 66%|██████▌   | 37919/57600 [6:39:15<3:22:01,  1.62it/s]
 66%|██████▌   | 37920/57600 [6:39:16<3:35:57,  1.52it/s]
                                                         
{'loss': 1.143, 'learning_rate': 4.0857142857142855e-07, 'epoch': 418.54}

 66%|██████▌   | 37920/57600 [6:39:16<3:35:57,  1.52it/s]
 66%|██████▌   | 37921/57600 [6:39:16<3:45:29,  1.45it/s]
 66%|██████▌   | 37922/57600 [6:39:17<3:44:17,  1.46it/s]
 66%|██████▌   | 37923/57600 [6:39:18<3:35:20,  1.52it/s]
 66%|██████▌   | 37924/57600 [6:39:18<3:32:08,  1.55it/s]
 66%|██████▌   | 37925/57600 [6:39:19<3:30:34,  1.56it/s]
 66%|██████▌   | 37926/57600 [6:39:20<3:26:19,  1.59it/s]
 66%|██████▌   | 37927/57600 [6:39:20<3:31:26,  1.55it/s]
 66%|██████▌   | 37928/57600 [6:39:21<3:32:13,  1.54it/s]
 66%|██████▌   | 37929/57600 [6:39:21<3:28:41,  1.57it/s]
 66%|██████▌   | 37930/57600 [6:39:22<3:31:17,  1.55it/s]
 66%|██████▌   | 37931/57600 [6:39:23<3:26:45,  1.59it/s]
 66%|██████▌   | 37932/57600 [6:39:23<3:24:18,  1.60it/s]
 66%|██████▌   | 37933/57600 [6:39:24<3:22:36,  1.62it/s]
 66%|██████▌   | 37934/57600 [6:39:25<3:23:13,  1.61it/s]
 66%|██████▌   | 37935/57600 [6:39:25<3:22:20,  1.62it/s]
 66%|██████▌   | 37936/57600 [6:39:26<3:30:38,  1.56it/s]
 66%|██████▌   | 37937/57600 [6:39:27<3:35:12,  1.52it/s]
 66%|██████▌   | 37938/57600 [6:39:27<3:37:31,  1.51it/s]
 66%|██████▌   | 37939/57600 [6:39:28<3:36:30,  1.51it/s]
 66%|██████▌   | 37940/57600 [6:39:29<3:30:33,  1.56it/s]
                                                         
{'loss': 1.1103, 'learning_rate': 4.082578397212544e-07, 'epoch': 418.76}

 66%|██████▌   | 37940/57600 [6:39:29<3:30:33,  1.56it/s]
 66%|██████▌   | 37941/57600 [6:39:29<3:25:52,  1.59it/s]
 66%|██████▌   | 37942/57600 [6:39:30<3:26:15,  1.59it/s]
 66%|██████▌   | 37943/57600 [6:39:30<3:23:50,  1.61it/s]
 66%|██████▌   | 37944/57600 [6:39:31<3:21:05,  1.63it/s]
 66%|██████▌   | 37945/57600 [6:39:32<3:20:30,  1.63it/s]
 66%|██████▌   | 37946/57600 [6:39:32<3:19:29,  1.64it/s]
 66%|██████▌   | 37947/57600 [6:39:33<3:28:31,  1.57it/s]
 66%|██████▌   | 37948/57600 [6:39:33<3:27:19,  1.58it/s]
 66%|██████▌   | 37949/57600 [6:39:34<3:38:44,  1.50it/s]
 66%|██████▌   | 37950/57600 [6:39:35<3:33:26,  1.53it/s]
 66%|██████▌   | 37951/57600 [6:39:35<3:30:50,  1.55it/s]
 66%|██████▌   | 37952/57600 [6:39:36<3:34:25,  1.53it/s]
 66%|██████▌   | 37953/57600 [6:39:37<3:25:36,  1.59it/s]
 66%|██████▌   | 37954/57600 [6:39:37<3:22:43,  1.62it/s]
 66%|██████▌   | 37955/57600 [6:39:38<3:21:48,  1.62it/s]
 66%|██████▌   | 37956/57600 [6:39:39<3:22:17,  1.62it/s]
 66%|██████▌   | 37957/57600 [6:39:39<3:21:30,  1.62it/s]
 66%|██████▌   | 37958/57600 [6:39:40<3:20:10,  1.64it/s]
 66%|██████▌   | 37959/57600 [6:39:40<3:22:36,  1.62it/s]
 66%|██████▌   | 37960/57600 [6:39:41<3:17:43,  1.66it/s]
                                                         
{'loss': 1.1221, 'learning_rate': 4.079442508710801e-07, 'epoch': 418.98}

 66%|██████▌   | 37960/57600 [6:39:41<3:17:43,  1.66it/s]
 66%|██████▌   | 37961/57600 [6:39:42<3:17:21,  1.66it/s]
 66%|██████▌   | 37962/57600 [6:39:42<3:25:51,  1.59it/s]
 66%|██████▌   | 37963/57600 [6:39:43<3:31:14,  1.55it/s]
 66%|██████▌   | 37964/57600 [6:39:44<3:28:35,  1.57it/s]
 66%|██████▌   | 37965/57600 [6:39:44<3:27:15,  1.58it/s]
 66%|██████▌   | 37966/57600 [6:39:45<3:27:23,  1.58it/s]
 66%|██████▌   | 37967/57600 [6:39:45<3:25:27,  1.59it/s]
 66%|██████▌   | 37968/57600 [6:39:46<3:29:13,  1.56it/s]
 66%|██████▌   | 37969/57600 [6:39:47<3:25:36,  1.59it/s]
 66%|██████▌   | 37970/57600 [6:39:47<3:36:48,  1.51it/s]
 66%|██████▌   | 37971/57600 [6:39:48<3:34:40,  1.52it/s]
 66%|██████▌   | 37972/57600 [6:39:49<3:28:28,  1.57it/s]
 66%|██████▌   | 37973/57600 [6:39:49<3:28:30,  1.57it/s]
 66%|██████▌   | 37974/57600 [6:39:50<3:25:30,  1.59it/s]
 66%|██████▌   | 37975/57600 [6:39:51<3:21:32,  1.62it/s]
 66%|██████▌   | 37976/57600 [6:39:51<3:23:37,  1.61it/s]
 66%|██████▌   | 37977/57600 [6:39:52<3:22:54,  1.61it/s]
 66%|██████▌   | 37978/57600 [6:39:52<3:18:39,  1.65it/s]
 66%|██████▌   | 37979/57600 [6:39:53<3:18:34,  1.65it/s]
 66%|██████▌   | 37980/57600 [6:39:54<3:15:25,  1.67it/s]
                                                         
{'loss': 1.1496, 'learning_rate': 4.0763066202090596e-07, 'epoch': 419.21}

 66%|██████▌   | 37980/57600 [6:39:54<3:15:25,  1.67it/s]
 66%|██████▌   | 37981/57600 [6:39:54<3:12:59,  1.69it/s]
 66%|██████▌   | 37982/57600 [6:39:55<3:12:01,  1.70it/s]
 66%|██████▌   | 37983/57600 [6:39:55<3:13:13,  1.69it/s]
 66%|██████▌   | 37984/57600 [6:39:56<3:23:11,  1.61it/s]
 66%|██████▌   | 37985/57600 [6:39:57<3:16:40,  1.66it/s]
 66%|██████▌   | 37986/57600 [6:39:57<3:15:20,  1.67it/s]
 66%|██████▌   | 37987/57600 [6:39:58<3:21:44,  1.62it/s]
 66%|██████▌   | 37988/57600 [6:39:58<3:22:22,  1.62it/s]
 66%|██████▌   | 37989/57600 [6:39:59<3:17:52,  1.65it/s]
 66%|██████▌   | 37990/57600 [6:40:00<3:18:29,  1.65it/s]
 66%|██████▌   | 37991/57600 [6:40:00<3:17:16,  1.66it/s]
 66%|██████▌   | 37992/57600 [6:40:01<3:14:24,  1.68it/s]
 66%|██████▌   | 37993/57600 [6:40:01<3:14:07,  1.68it/s]
 66%|██████▌   | 37994/57600 [6:40:02<3:15:00,  1.68it/s]
 66%|██████▌   | 37995/57600 [6:40:03<3:12:44,  1.70it/s]
 66%|██████▌   | 37996/57600 [6:40:03<3:13:55,  1.68it/s]
 66%|██████▌   | 37997/57600 [6:40:04<3:15:52,  1.67it/s]
 66%|██████▌   | 37998/57600 [6:40:04<3:19:53,  1.63it/s]
 66%|██████▌   | 37999/57600 [6:40:05<3:20:39,  1.63it/s]
 66%|██████▌   | 38000/57600 [6:40:06<3:25:50,  1.59it/s]
                                                         
{'loss': 1.1512, 'learning_rate': 4.0731707317073166e-07, 'epoch': 419.43}

 66%|██████▌   | 38000/57600 [6:40:06<3:25:50,  1.59it/s]
 66%|██████▌   | 38001/57600 [6:40:06<3:23:28,  1.61it/s]
 66%|██████▌   | 38002/57600 [6:40:07<3:26:18,  1.58it/s]
 66%|██████▌   | 38003/57600 [6:40:08<3:29:10,  1.56it/s]
 66%|██████▌   | 38004/57600 [6:40:08<3:30:38,  1.55it/s]
 66%|██████▌   | 38005/57600 [6:40:09<3:26:46,  1.58it/s]
 66%|██████▌   | 38006/57600 [6:40:09<3:24:45,  1.59it/s]
 66%|██████▌   | 38007/57600 [6:40:10<3:34:11,  1.52it/s]
 66%|██████▌   | 38008/57600 [6:40:11<3:32:13,  1.54it/s]
 66%|██████▌   | 38009/57600 [6:40:11<3:28:35,  1.57it/s]
 66%|██████▌   | 38010/57600 [6:40:12<3:29:40,  1.56it/s]
 66%|██████▌   | 38011/57600 [6:40:13<3:24:50,  1.59it/s]
 66%|██████▌   | 38012/57600 [6:40:13<3:27:35,  1.57it/s]
 66%|██████▌   | 38013/57600 [6:40:14<3:20:45,  1.63it/s]
 66%|██████▌   | 38014/57600 [6:40:14<3:15:53,  1.67it/s]
 66%|██████▌   | 38015/57600 [6:40:15<3:17:20,  1.65it/s]
 66%|██████▌   | 38016/57600 [6:40:16<3:19:41,  1.63it/s]
 66%|██████▌   | 38017/57600 [6:40:16<3:17:17,  1.65it/s]
 66%|██████▌   | 38018/57600 [6:40:17<3:19:51,  1.63it/s]
 66%|██████▌   | 38019/57600 [6:40:18<3:22:01,  1.62it/s]
 66%|██████▌   | 38020/57600 [6:40:18<3:20:50,  1.62it/s]
                                                         
{'loss': 1.1456, 'learning_rate': 4.0700348432055747e-07, 'epoch': 419.65}

 66%|██████▌   | 38020/57600 [6:40:18<3:20:50,  1.62it/s]
 66%|██████▌   | 38021/57600 [6:40:19<3:21:58,  1.62it/s]
 66%|██████▌   | 38022/57600 [6:40:19<3:28:50,  1.56it/s]
 66%|██████▌   | 38023/57600 [6:40:20<3:27:43,  1.57it/s]
 66%|██████▌   | 38024/57600 [6:40:21<3:22:37,  1.61it/s]
 66%|██████▌   | 38025/57600 [6:40:21<3:24:03,  1.60it/s]
 66%|██████▌   | 38026/57600 [6:40:22<3:30:12,  1.55it/s]
 66%|██████▌   | 38027/57600 [6:40:23<3:31:16,  1.54it/s]
 66%|██████▌   | 38028/57600 [6:40:23<3:37:55,  1.50it/s]
 66%|██████▌   | 38029/57600 [6:40:24<3:43:25,  1.46it/s]
 66%|██████▌   | 38030/57600 [6:40:25<3:33:29,  1.53it/s]
 66%|██████▌   | 38031/57600 [6:40:25<3:34:28,  1.52it/s]
 66%|██████▌   | 38032/57600 [6:40:26<3:34:33,  1.52it/s]
 66%|██████▌   | 38033/57600 [6:40:27<3:29:10,  1.56it/s]
 66%|██████▌   | 38034/57600 [6:40:27<3:18:46,  1.64it/s]
 66%|██████▌   | 38035/57600 [6:40:28<3:21:21,  1.62it/s]
 66%|██████▌   | 38036/57600 [6:40:28<3:23:39,  1.60it/s]
 66%|██████▌   | 38037/57600 [6:40:29<3:29:55,  1.55it/s]
 66%|██████▌   | 38038/57600 [6:40:30<3:23:28,  1.60it/s]
 66%|██████▌   | 38039/57600 [6:40:30<3:21:23,  1.62it/s]
 66%|██████▌   | 38040/57600 [6:40:31<3:26:27,  1.58it/s]
                                                         
{'loss': 1.1294, 'learning_rate': 4.066898954703832e-07, 'epoch': 419.87}

 66%|██████▌   | 38040/57600 [6:40:31<3:26:27,  1.58it/s]
 66%|██████▌   | 38041/57600 [6:40:32<3:30:05,  1.55it/s]
 66%|██████▌   | 38042/57600 [6:40:32<3:23:44,  1.60it/s]
 66%|██████▌   | 38043/57600 [6:40:33<3:25:00,  1.59it/s]
 66%|██████▌   | 38044/57600 [6:40:34<3:37:24,  1.50it/s]
 66%|██████▌   | 38045/57600 [6:40:34<3:35:50,  1.51it/s]
 66%|██████▌   | 38046/57600 [6:40:35<3:28:40,  1.56it/s]
 66%|██████▌   | 38047/57600 [6:40:35<3:24:56,  1.59it/s]
 66%|██████▌   | 38048/57600 [6:40:36<3:24:00,  1.60it/s]
 66%|██████▌   | 38049/57600 [6:40:37<3:27:22,  1.57it/s]
 66%|██████▌   | 38050/57600 [6:40:37<3:31:45,  1.54it/s]
 66%|██████▌   | 38051/57600 [6:40:38<3:24:04,  1.60it/s]
 66%|██████▌   | 38052/57600 [6:40:39<3:26:02,  1.58it/s]
 66%|██████▌   | 38053/57600 [6:40:39<3:31:57,  1.54it/s]
 66%|██████▌   | 38054/57600 [6:40:40<3:26:49,  1.58it/s]
 66%|██████▌   | 38055/57600 [6:40:41<3:25:05,  1.59it/s]
 66%|██████▌   | 38056/57600 [6:40:41<3:23:35,  1.60it/s]
 66%|██████▌   | 38057/57600 [6:40:42<3:17:31,  1.65it/s]
 66%|██████▌   | 38058/57600 [6:40:42<3:17:43,  1.65it/s]
 66%|██████▌   | 38059/57600 [6:40:43<3:23:12,  1.60it/s]
 66%|██████▌   | 38060/57600 [6:40:44<3:23:02,  1.60it/s]
                                                         
{'loss': 1.1663, 'learning_rate': 4.06376306620209e-07, 'epoch': 420.09}

 66%|██████▌   | 38060/57600 [6:40:44<3:23:02,  1.60it/s]
 66%|██████▌   | 38061/57600 [6:40:44<3:37:07,  1.50it/s]
 66%|██████▌   | 38062/57600 [6:40:45<3:29:43,  1.55it/s]
 66%|██████▌   | 38063/57600 [6:40:46<3:27:24,  1.57it/s]
 66%|██████▌   | 38064/57600 [6:40:46<3:34:01,  1.52it/s]
 66%|██████▌   | 38065/57600 [6:40:47<3:33:59,  1.52it/s]
 66%|██████▌   | 38066/57600 [6:40:48<3:27:54,  1.57it/s]
 66%|██████▌   | 38067/57600 [6:40:48<3:26:54,  1.57it/s]
 66%|██████▌   | 38068/57600 [6:40:49<3:23:59,  1.60it/s]
 66%|██████▌   | 38069/57600 [6:40:49<3:26:57,  1.57it/s]
 66%|██████▌   | 38070/57600 [6:40:50<3:26:51,  1.57it/s]
 66%|██████▌   | 38071/57600 [6:40:51<3:25:39,  1.58it/s]
 66%|██████▌   | 38072/57600 [6:40:51<3:30:24,  1.55it/s]
 66%|██████▌   | 38073/57600 [6:40:52<3:30:32,  1.55it/s]
 66%|██████▌   | 38074/57600 [6:40:53<3:27:15,  1.57it/s]
 66%|██████▌   | 38075/57600 [6:40:53<3:25:40,  1.58it/s]
 66%|██████▌   | 38076/57600 [6:40:54<3:24:41,  1.59it/s]
 66%|██████▌   | 38077/57600 [6:40:54<3:18:35,  1.64it/s]
 66%|██████▌   | 38078/57600 [6:40:55<3:19:53,  1.63it/s]
 66%|██████▌   | 38079/57600 [6:40:56<3:24:35,  1.59it/s]
 66%|██████▌   | 38080/57600 [6:40:56<3:23:28,  1.60it/s]
                                                         
{'loss': 1.1684, 'learning_rate': 4.060627177700349e-07, 'epoch': 420.31}

 66%|██████▌   | 38080/57600 [6:40:56<3:23:28,  1.60it/s]
 66%|██████▌   | 38081/57600 [6:40:57<3:20:04,  1.63it/s]
 66%|██████▌   | 38082/57600 [6:40:58<3:23:11,  1.60it/s]
 66%|██████▌   | 38083/57600 [6:40:58<3:23:35,  1.60it/s]
 66%|██████▌   | 38084/57600 [6:40:59<3:31:39,  1.54it/s]
 66%|██████▌   | 38085/57600 [6:41:00<3:26:05,  1.58it/s]
 66%|██████▌   | 38086/57600 [6:41:00<3:25:47,  1.58it/s]
 66%|██████▌   | 38087/57600 [6:41:01<3:24:49,  1.59it/s]
 66%|██████▌   | 38088/57600 [6:41:01<3:21:19,  1.62it/s]
 66%|██████▌   | 38089/57600 [6:41:02<3:22:11,  1.61it/s]
 66%|██████▌   | 38090/57600 [6:41:03<3:21:12,  1.62it/s]
 66%|██████▌   | 38091/57600 [6:41:03<3:23:17,  1.60it/s]
 66%|██████▌   | 38092/57600 [6:41:04<3:24:40,  1.59it/s]
 66%|██████▌   | 38093/57600 [6:41:05<3:23:31,  1.60it/s]
 66%|██████▌   | 38094/57600 [6:41:05<3:20:53,  1.62it/s]
 66%|██████▌   | 38095/57600 [6:41:06<3:21:27,  1.61it/s]
 66%|██████▌   | 38096/57600 [6:41:06<3:23:24,  1.60it/s]
 66%|██████▌   | 38097/57600 [6:41:07<3:19:37,  1.63it/s]
 66%|██████▌   | 38098/57600 [6:41:08<3:21:29,  1.61it/s]
 66%|██████▌   | 38099/57600 [6:41:08<3:19:49,  1.63it/s]
 66%|██████▌   | 38100/57600 [6:41:09<3:16:19,  1.66it/s]
                                                         
{'loss': 1.1241, 'learning_rate': 4.057491289198606e-07, 'epoch': 420.53}

 66%|██████▌   | 38100/57600 [6:41:09<3:16:19,  1.66it/s]
 66%|██████▌   | 38101/57600 [6:41:09<3:20:37,  1.62it/s]
 66%|██████▌   | 38102/57600 [6:41:10<3:18:36,  1.64it/s]
 66%|██████▌   | 38103/57600 [6:41:11<3:23:23,  1.60it/s]
 66%|██████▌   | 38104/57600 [6:41:11<3:24:15,  1.59it/s]
 66%|██████▌   | 38105/57600 [6:41:12<3:22:17,  1.61it/s]
 66%|██████▌   | 38106/57600 [6:41:13<3:18:24,  1.64it/s]
 66%|██████▌   | 38107/57600 [6:41:13<3:15:01,  1.67it/s]
 66%|██████▌   | 38108/57600 [6:41:14<3:16:51,  1.65it/s]
 66%|██████▌   | 38109/57600 [6:41:14<3:17:58,  1.64it/s]
 66%|██████▌   | 38110/57600 [6:41:15<3:20:49,  1.62it/s]
 66%|██████▌   | 38111/57600 [6:41:16<3:24:48,  1.59it/s]
 66%|██████▌   | 38112/57600 [6:41:16<3:19:33,  1.63it/s]
 66%|██████▌   | 38113/57600 [6:41:17<3:24:18,  1.59it/s]
 66%|██████▌   | 38114/57600 [6:41:17<3:23:12,  1.60it/s]
 66%|██████▌   | 38115/57600 [6:41:18<3:24:06,  1.59it/s]
 66%|██████▌   | 38116/57600 [6:41:19<3:20:04,  1.62it/s]
 66%|██████▌   | 38117/57600 [6:41:19<3:33:35,  1.52it/s]
 66%|██████▌   | 38118/57600 [6:41:20<3:26:20,  1.57it/s]
 66%|██████▌   | 38119/57600 [6:41:21<3:21:47,  1.61it/s]
 66%|██████▌   | 38120/57600 [6:41:21<3:20:39,  1.62it/s]
                                                         
{'loss': 1.1597, 'learning_rate': 4.0543554006968644e-07, 'epoch': 420.75}

 66%|██████▌   | 38120/57600 [6:41:21<3:20:39,  1.62it/s]
 66%|██████▌   | 38121/57600 [6:41:22<3:33:52,  1.52it/s]
 66%|██████▌   | 38122/57600 [6:41:23<3:28:14,  1.56it/s]
 66%|██████▌   | 38123/57600 [6:41:23<3:34:34,  1.51it/s]
 66%|██████▌   | 38124/57600 [6:41:24<3:40:15,  1.47it/s]
 66%|██████▌   | 38125/57600 [6:41:25<3:30:29,  1.54it/s]
 66%|██████▌   | 38126/57600 [6:41:25<3:30:03,  1.55it/s]
 66%|██████▌   | 38127/57600 [6:41:26<3:25:57,  1.58it/s]
 66%|██████▌   | 38128/57600 [6:41:26<3:22:47,  1.60it/s]
 66%|██████▌   | 38129/57600 [6:41:27<3:22:45,  1.60it/s]
 66%|██████▌   | 38130/57600 [6:41:28<3:18:18,  1.64it/s]
 66%|██████▌   | 38131/57600 [6:41:28<3:17:38,  1.64it/s]
 66%|██████▌   | 38132/57600 [6:41:29<3:22:04,  1.61it/s]
 66%|██████▌   | 38133/57600 [6:41:29<3:16:27,  1.65it/s]
 66%|██████▌   | 38134/57600 [6:41:30<3:16:47,  1.65it/s]
 66%|██████▌   | 38135/57600 [6:41:31<3:22:13,  1.60it/s]
 66%|██████▌   | 38136/57600 [6:41:31<3:18:29,  1.63it/s]
 66%|██████▌   | 38137/57600 [6:41:32<3:18:02,  1.64it/s]
 66%|██████▌   | 38138/57600 [6:41:33<3:22:46,  1.60it/s]
 66%|██████▌   | 38139/57600 [6:41:33<3:27:53,  1.56it/s]
 66%|██████▌   | 38140/57600 [6:41:34<3:27:27,  1.56it/s]
                                                         
{'loss': 1.1643, 'learning_rate': 4.0512195121951214e-07, 'epoch': 420.97}

 66%|██████▌   | 38140/57600 [6:41:34<3:27:27,  1.56it/s]
 66%|██████▌   | 38141/57600 [6:41:35<3:22:41,  1.60it/s]
 66%|██████▌   | 38142/57600 [6:41:35<3:21:37,  1.61it/s]
 66%|██████▌   | 38143/57600 [6:41:36<3:29:38,  1.55it/s]
 66%|██████▌   | 38144/57600 [6:41:36<3:24:03,  1.59it/s]
 66%|██████▌   | 38145/57600 [6:41:37<3:18:22,  1.63it/s]
 66%|██████▌   | 38146/57600 [6:41:38<3:16:34,  1.65it/s]
 66%|██████▌   | 38147/57600 [6:41:38<3:13:51,  1.67it/s]
 66%|██████▌   | 38148/57600 [6:41:39<3:23:48,  1.59it/s]
 66%|██████▌   | 38149/57600 [6:41:40<3:30:40,  1.54it/s]
 66%|██████▌   | 38150/57600 [6:41:40<3:27:35,  1.56it/s]
 66%|██████▌   | 38151/57600 [6:41:41<3:19:32,  1.62it/s]
 66%|██████▌   | 38152/57600 [6:41:41<3:21:35,  1.61it/s]
 66%|██████▌   | 38153/57600 [6:41:42<3:24:45,  1.58it/s]
 66%|██████▌   | 38154/57600 [6:41:43<3:27:56,  1.56it/s]
 66%|██████▌   | 38155/57600 [6:41:43<3:23:25,  1.59it/s]
 66%|██████▌   | 38156/57600 [6:41:44<3:27:51,  1.56it/s]
 66%|██████▌   | 38157/57600 [6:41:45<3:21:21,  1.61it/s]
 66%|██████▌   | 38158/57600 [6:41:45<3:20:54,  1.61it/s]
 66%|██████▌   | 38159/57600 [6:41:46<3:26:54,  1.57it/s]
 66%|██████▋   | 38160/57600 [6:41:46<3:26:29,  1.57it/s]
                                                         
{'loss': 1.1592, 'learning_rate': 4.04808362369338e-07, 'epoch': 421.19}

 66%|██████▋   | 38160/57600 [6:41:46<3:26:29,  1.57it/s]
 66%|██████▋   | 38161/57600 [6:41:47<3:26:39,  1.57it/s]
 66%|██████▋   | 38162/57600 [6:41:48<3:25:31,  1.58it/s]
 66%|██████▋   | 38163/57600 [6:41:48<3:26:18,  1.57it/s]
 66%|██████▋   | 38164/57600 [6:41:49<3:23:32,  1.59it/s]
 66%|██████▋   | 38165/57600 [6:41:50<3:16:55,  1.64it/s]
 66%|██████▋   | 38166/57600 [6:41:50<3:17:41,  1.64it/s]
 66%|██████▋   | 38167/57600 [6:41:51<3:25:21,  1.58it/s]
 66%|██████▋   | 38168/57600 [6:41:51<3:19:26,  1.62it/s]
 66%|██████▋   | 38169/57600 [6:41:52<3:19:35,  1.62it/s]
 66%|██████▋   | 38170/57600 [6:41:53<3:20:29,  1.62it/s]
 66%|██████▋   | 38171/57600 [6:41:53<3:24:45,  1.58it/s]
 66%|██████▋   | 38172/57600 [6:41:54<3:26:31,  1.57it/s]
 66%|██████▋   | 38173/57600 [6:41:55<3:26:06,  1.57it/s]
 66%|██████▋   | 38174/57600 [6:41:55<3:20:23,  1.62it/s]
 66%|██████▋   | 38175/57600 [6:41:56<3:24:38,  1.58it/s]
 66%|██████▋   | 38176/57600 [6:41:57<3:26:14,  1.57it/s]
 66%|██████▋   | 38177/57600 [6:41:57<3:26:53,  1.56it/s]
 66%|██████▋   | 38178/57600 [6:41:58<3:24:20,  1.58it/s]
 66%|██████▋   | 38179/57600 [6:41:58<3:29:37,  1.54it/s]
 66%|██████▋   | 38180/57600 [6:41:59<3:27:10,  1.56it/s]
                                                         
{'loss': 1.1483, 'learning_rate': 4.044947735191637e-07, 'epoch': 421.41}

 66%|██████▋   | 38180/57600 [6:41:59<3:27:10,  1.56it/s]
 66%|██████▋   | 38181/57600 [6:42:00<3:24:29,  1.58it/s]
 66%|██████▋   | 38182/57600 [6:42:00<3:26:23,  1.57it/s]
 66%|██████▋   | 38183/57600 [6:42:01<3:21:03,  1.61it/s]
 66%|██████▋   | 38184/57600 [6:42:02<3:18:41,  1.63it/s]
 66%|██████▋   | 38185/57600 [6:42:02<3:14:50,  1.66it/s]
 66%|██████▋   | 38186/57600 [6:42:03<3:31:29,  1.53it/s]
 66%|██████▋   | 38187/57600 [6:42:04<3:29:46,  1.54it/s]
 66%|██████▋   | 38188/57600 [6:42:04<3:28:05,  1.55it/s]
 66%|██████▋   | 38189/57600 [6:42:05<3:28:55,  1.55it/s]
 66%|██████▋   | 38190/57600 [6:42:05<3:23:29,  1.59it/s]
 66%|██████▋   | 38191/57600 [6:42:06<3:28:16,  1.55it/s]
 66%|██████▋   | 38192/57600 [6:42:07<3:20:29,  1.61it/s]
 66%|██████▋   | 38193/57600 [6:42:07<3:17:07,  1.64it/s]
 66%|██████▋   | 38194/57600 [6:42:08<3:20:31,  1.61it/s]
 66%|██████▋   | 38195/57600 [6:42:08<3:14:56,  1.66it/s]
 66%|██████▋   | 38196/57600 [6:42:09<3:17:03,  1.64it/s]
 66%|██████▋   | 38197/57600 [6:42:10<3:17:13,  1.64it/s]
 66%|██████▋   | 38198/57600 [6:42:10<3:23:33,  1.59it/s]
 66%|██████▋   | 38199/57600 [6:42:11<3:28:11,  1.55it/s]
 66%|██████▋   | 38200/57600 [6:42:12<3:25:02,  1.58it/s]
                                                         
{'loss': 1.1539, 'learning_rate': 4.0418118466898955e-07, 'epoch': 421.63}

 66%|██████▋   | 38200/57600 [6:42:12<3:25:02,  1.58it/s]
 66%|██████▋   | 38201/57600 [6:42:12<3:25:50,  1.57it/s]
 66%|██████▋   | 38202/57600 [6:42:13<3:23:13,  1.59it/s]
 66%|██████▋   | 38203/57600 [6:42:13<3:22:14,  1.60it/s]
 66%|██████▋   | 38204/57600 [6:42:14<3:22:12,  1.60it/s]
 66%|██████▋   | 38205/57600 [6:42:15<3:18:39,  1.63it/s]
 66%|██████▋   | 38206/57600 [6:42:15<3:18:55,  1.62it/s]
 66%|██████▋   | 38207/57600 [6:42:16<3:19:55,  1.62it/s]
 66%|██████▋   | 38208/57600 [6:42:17<3:25:37,  1.57it/s]
 66%|██████▋   | 38209/57600 [6:42:17<3:22:38,  1.59it/s]
 66%|██████▋   | 38210/57600 [6:42:18<3:17:21,  1.64it/s]
 66%|██████▋   | 38211/57600 [6:42:18<3:16:31,  1.64it/s]
 66%|██████▋   | 38212/57600 [6:42:19<3:22:53,  1.59it/s]
 66%|██████▋   | 38213/57600 [6:42:20<3:22:37,  1.59it/s]
 66%|██████▋   | 38214/57600 [6:42:20<3:19:31,  1.62it/s]
 66%|██████▋   | 38215/57600 [6:42:21<3:19:20,  1.62it/s]
 66%|██████▋   | 38216/57600 [6:42:22<3:19:14,  1.62it/s]
 66%|██████▋   | 38217/57600 [6:42:22<3:18:06,  1.63it/s]
 66%|██████▋   | 38218/57600 [6:42:23<3:20:18,  1.61it/s]
 66%|██████▋   | 38219/57600 [6:42:23<3:28:11,  1.55it/s]
 66%|██████▋   | 38220/57600 [6:42:24<3:35:02,  1.50it/s]
                                                         
{'loss': 1.1445, 'learning_rate': 4.0386759581881536e-07, 'epoch': 421.85}

 66%|██████▋   | 38220/57600 [6:42:24<3:35:02,  1.50it/s]
 66%|██████▋   | 38221/57600 [6:42:25<3:34:41,  1.50it/s]
 66%|██████▋   | 38222/57600 [6:42:25<3:28:33,  1.55it/s]
 66%|██████▋   | 38223/57600 [6:42:26<3:26:29,  1.56it/s]
 66%|██████▋   | 38224/57600 [6:42:27<3:25:20,  1.57it/s]
 66%|██████▋   | 38225/57600 [6:42:27<3:23:23,  1.59it/s]
 66%|██████▋   | 38226/57600 [6:42:28<3:24:17,  1.58it/s]
 66%|██████▋   | 38227/57600 [6:42:29<3:24:30,  1.58it/s]
 66%|██████▋   | 38228/57600 [6:42:29<3:21:58,  1.60it/s]
 66%|██████▋   | 38229/57600 [6:42:30<3:23:14,  1.59it/s]
 66%|██████▋   | 38230/57600 [6:42:30<3:20:54,  1.61it/s]
 66%|██████▋   | 38231/57600 [6:42:31<3:18:00,  1.63it/s]
 66%|██████▋   | 38232/57600 [6:42:32<3:19:16,  1.62it/s]
 66%|██████▋   | 38233/57600 [6:42:32<3:19:27,  1.62it/s]
 66%|██████▋   | 38234/57600 [6:42:33<3:28:01,  1.55it/s]
 66%|██████▋   | 38235/57600 [6:42:34<3:25:33,  1.57it/s]
 66%|██████▋   | 38236/57600 [6:42:34<3:19:01,  1.62it/s]
 66%|██████▋   | 38237/57600 [6:42:35<3:19:05,  1.62it/s]
 66%|██████▋   | 38238/57600 [6:42:35<3:22:05,  1.60it/s]
 66%|██████▋   | 38239/57600 [6:42:36<3:23:50,  1.58it/s]
 66%|██████▋   | 38240/57600 [6:42:37<3:26:38,  1.56it/s]
                                                         
{'loss': 1.1763, 'learning_rate': 4.035540069686411e-07, 'epoch': 422.08}

 66%|██████▋   | 38240/57600 [6:42:37<3:26:38,  1.56it/s]
 66%|██████▋   | 38241/57600 [6:42:37<3:30:14,  1.53it/s]
 66%|██████▋   | 38242/57600 [6:42:38<3:28:52,  1.54it/s]
 66%|██████▋   | 38243/57600 [6:42:39<3:24:37,  1.58it/s]
 66%|██████▋   | 38244/57600 [6:42:39<3:28:26,  1.55it/s]
 66%|██████▋   | 38245/57600 [6:42:40<3:23:39,  1.58it/s]
 66%|██████▋   | 38246/57600 [6:42:41<3:24:53,  1.57it/s]
 66%|██████▋   | 38247/57600 [6:42:41<3:30:28,  1.53it/s]
 66%|██████▋   | 38248/57600 [6:42:42<3:26:02,  1.57it/s]
 66%|██████▋   | 38249/57600 [6:42:42<3:22:49,  1.59it/s]
 66%|██████▋   | 38250/57600 [6:42:43<3:22:24,  1.59it/s]
 66%|██████▋   | 38251/57600 [6:42:44<3:20:26,  1.61it/s]
 66%|██████▋   | 38252/57600 [6:42:44<3:25:33,  1.57it/s]
 66%|██████▋   | 38253/57600 [6:42:45<3:21:17,  1.60it/s]
 66%|██████▋   | 38254/57600 [6:42:46<3:21:06,  1.60it/s]
 66%|██████▋   | 38255/57600 [6:42:46<3:26:08,  1.56it/s]
 66%|██████▋   | 38256/57600 [6:42:47<3:25:48,  1.57it/s]
 66%|██████▋   | 38257/57600 [6:42:48<3:25:42,  1.57it/s]
 66%|██████▋   | 38258/57600 [6:42:48<3:29:26,  1.54it/s]
 66%|██████▋   | 38259/57600 [6:42:49<3:25:25,  1.57it/s]
 66%|██████▋   | 38260/57600 [6:42:49<3:20:45,  1.61it/s]
                                                         
{'loss': 1.1422, 'learning_rate': 4.032404181184669e-07, 'epoch': 422.3}

 66%|██████▋   | 38260/57600 [6:42:49<3:20:45,  1.61it/s]
 66%|██████▋   | 38261/57600 [6:42:50<3:16:58,  1.64it/s]
 66%|██████▋   | 38262/57600 [6:42:51<3:18:31,  1.62it/s]
 66%|██████▋   | 38263/57600 [6:42:51<3:13:26,  1.67it/s]
 66%|██████▋   | 38264/57600 [6:42:52<3:19:14,  1.62it/s]
 66%|██████▋   | 38265/57600 [6:42:53<3:21:33,  1.60it/s]
 66%|██████▋   | 38266/57600 [6:42:53<3:30:11,  1.53it/s]
 66%|██████▋   | 38267/57600 [6:42:54<3:20:02,  1.61it/s]
 66%|██████▋   | 38268/57600 [6:42:54<3:20:30,  1.61it/s]
 66%|██████▋   | 38269/57600 [6:42:55<3:18:11,  1.63it/s]
 66%|██████▋   | 38270/57600 [6:42:56<3:17:40,  1.63it/s]
 66%|██████▋   | 38271/57600 [6:42:56<3:25:13,  1.57it/s]
 66%|██████▋   | 38272/57600 [6:42:57<3:20:49,  1.60it/s]
 66%|██████▋   | 38273/57600 [6:42:58<3:24:58,  1.57it/s]
 66%|██████▋   | 38274/57600 [6:42:58<3:21:35,  1.60it/s]
 66%|██████▋   | 38275/57600 [6:42:59<3:16:48,  1.64it/s]
 66%|██████▋   | 38276/57600 [6:42:59<3:20:30,  1.61it/s]
 66%|██████▋   | 38277/57600 [6:43:00<3:19:55,  1.61it/s]
 66%|██████▋   | 38278/57600 [6:43:01<3:29:34,  1.54it/s]
 66%|██████▋   | 38279/57600 [6:43:01<3:32:08,  1.52it/s]
 66%|██████▋   | 38280/57600 [6:43:02<3:30:43,  1.53it/s]
                                                         
{'loss': 1.1585, 'learning_rate': 4.029268292682926e-07, 'epoch': 422.52}

 66%|██████▋   | 38280/57600 [6:43:02<3:30:43,  1.53it/s]
 66%|██████▋   | 38281/57600 [6:43:03<3:26:06,  1.56it/s]
 66%|██████▋   | 38282/57600 [6:43:03<3:28:31,  1.54it/s]
 66%|██████▋   | 38283/57600 [6:43:04<3:33:37,  1.51it/s]
 66%|██████▋   | 38284/57600 [6:43:05<3:26:44,  1.56it/s]
 66%|██████▋   | 38285/57600 [6:43:05<3:24:23,  1.57it/s]
 66%|██████▋   | 38286/57600 [6:43:06<3:26:15,  1.56it/s]
 66%|██████▋   | 38287/57600 [6:43:06<3:24:14,  1.58it/s]
 66%|██████▋   | 38288/57600 [6:43:07<3:20:29,  1.61it/s]
 66%|██████▋   | 38289/57600 [6:43:08<3:22:08,  1.59it/s]
 66%|██████▋   | 38290/57600 [6:43:08<3:20:09,  1.61it/s]
 66%|██████▋   | 38291/57600 [6:43:09<3:17:01,  1.63it/s]
 66%|██████▋   | 38292/57600 [6:43:10<3:18:23,  1.62it/s]
 66%|██████▋   | 38293/57600 [6:43:10<3:14:13,  1.66it/s]
 66%|██████▋   | 38294/57600 [6:43:11<3:13:51,  1.66it/s]
 66%|██████▋   | 38295/57600 [6:43:11<3:15:28,  1.65it/s]
 66%|██████▋   | 38296/57600 [6:43:12<3:30:20,  1.53it/s]
 66%|██████▋   | 38297/57600 [6:43:13<3:29:34,  1.54it/s]
 66%|██████▋   | 38298/57600 [6:43:13<3:25:50,  1.56it/s]
 66%|██████▋   | 38299/57600 [6:43:14<3:23:15,  1.58it/s]
 66%|██████▋   | 38300/57600 [6:43:15<3:24:08,  1.58it/s]
                                                         
{'loss': 1.1285, 'learning_rate': 4.0261324041811847e-07, 'epoch': 422.74}

 66%|██████▋   | 38300/57600 [6:43:15<3:24:08,  1.58it/s]
 66%|██████▋   | 38301/57600 [6:43:15<3:21:51,  1.59it/s]
 66%|██████▋   | 38302/57600 [6:43:16<3:23:06,  1.58it/s]
 66%|██████▋   | 38303/57600 [6:43:17<3:23:25,  1.58it/s]
 66%|██████▋   | 38304/57600 [6:43:17<3:26:38,  1.56it/s]
 67%|██████▋   | 38305/57600 [6:43:18<3:23:23,  1.58it/s]
 67%|██████▋   | 38306/57600 [6:43:18<3:19:07,  1.61it/s]
 67%|██████▋   | 38307/57600 [6:43:19<3:17:14,  1.63it/s]
 67%|██████▋   | 38308/57600 [6:43:20<3:17:15,  1.63it/s]
 67%|██████▋   | 38309/57600 [6:43:20<3:19:45,  1.61it/s]
 67%|██████▋   | 38310/57600 [6:43:21<3:25:41,  1.56it/s]
 67%|██████▋   | 38311/57600 [6:43:21<3:19:40,  1.61it/s]
 67%|██████▋   | 38312/57600 [6:43:22<3:18:06,  1.62it/s]
 67%|██████▋   | 38313/57600 [6:43:23<3:20:20,  1.60it/s]
 67%|██████▋   | 38314/57600 [6:43:23<3:17:47,  1.63it/s]
 67%|██████▋   | 38315/57600 [6:43:24<3:15:47,  1.64it/s]
 67%|██████▋   | 38316/57600 [6:43:25<3:18:44,  1.62it/s]
 67%|██████▋   | 38317/57600 [6:43:25<3:19:14,  1.61it/s]
 67%|██████▋   | 38318/57600 [6:43:26<3:20:10,  1.61it/s]
 67%|██████▋   | 38319/57600 [6:43:27<3:26:44,  1.55it/s]
 67%|██████▋   | 38320/57600 [6:43:27<3:27:07,  1.55it/s]
                                                         
{'loss': 1.1413, 'learning_rate': 4.0229965156794417e-07, 'epoch': 422.96}

 67%|██████▋   | 38320/57600 [6:43:27<3:27:07,  1.55it/s]
 67%|██████▋   | 38321/57600 [6:43:28<3:38:26,  1.47it/s]
 67%|██████▋   | 38322/57600 [6:43:29<3:40:13,  1.46it/s]
 67%|██████▋   | 38323/57600 [6:43:29<3:33:33,  1.50it/s]
 67%|██████▋   | 38324/57600 [6:43:30<3:36:54,  1.48it/s]
 67%|██████▋   | 38325/57600 [6:43:31<3:28:30,  1.54it/s]
 67%|██████▋   | 38326/57600 [6:43:31<3:31:25,  1.52it/s]
 67%|██████▋   | 38327/57600 [6:43:32<3:23:25,  1.58it/s]
 67%|██████▋   | 38328/57600 [6:43:32<3:25:11,  1.57it/s]
 67%|██████▋   | 38329/57600 [6:43:33<3:26:05,  1.56it/s]
 67%|██████▋   | 38330/57600 [6:43:34<3:28:46,  1.54it/s]
 67%|██████▋   | 38331/57600 [6:43:34<3:30:40,  1.52it/s]
 67%|██████▋   | 38332/57600 [6:43:35<3:25:33,  1.56it/s]
 67%|██████▋   | 38333/57600 [6:43:36<3:21:22,  1.59it/s]
 67%|██████▋   | 38334/57600 [6:43:36<3:21:54,  1.59it/s]
 67%|██████▋   | 38335/57600 [6:43:37<3:23:04,  1.58it/s]
 67%|██████▋   | 38336/57600 [6:43:37<3:20:14,  1.60it/s]
 67%|██████▋   | 38337/57600 [6:43:38<3:20:52,  1.60it/s]
 67%|██████▋   | 38338/57600 [6:43:39<3:23:43,  1.58it/s]
 67%|██████▋   | 38339/57600 [6:43:39<3:20:40,  1.60it/s]
 67%|██████▋   | 38340/57600 [6:43:40<3:16:40,  1.63it/s]
                                                         
{'loss': 1.1166, 'learning_rate': 4.0198606271777e-07, 'epoch': 423.18}

 67%|██████▋   | 38340/57600 [6:43:40<3:16:40,  1.63it/s]
 67%|██████▋   | 38341/57600 [6:43:41<3:19:09,  1.61it/s]
 67%|██████▋   | 38342/57600 [6:43:41<3:13:38,  1.66it/s]
 67%|██████▋   | 38343/57600 [6:43:42<3:12:36,  1.67it/s]
 67%|██████▋   | 38344/57600 [6:43:42<3:14:18,  1.65it/s]
 67%|██████▋   | 38345/57600 [6:43:43<3:16:38,  1.63it/s]
 67%|██████▋   | 38346/57600 [6:43:44<3:15:42,  1.64it/s]
 67%|██████▋   | 38347/57600 [6:43:44<3:17:16,  1.63it/s]
 67%|██████▋   | 38348/57600 [6:43:45<3:18:20,  1.62it/s]
 67%|██████▋   | 38349/57600 [6:43:45<3:20:15,  1.60it/s]
 67%|██████▋   | 38350/57600 [6:43:46<3:25:38,  1.56it/s]
 67%|██████▋   | 38351/57600 [6:43:47<3:25:39,  1.56it/s]
 67%|██████▋   | 38352/57600 [6:43:47<3:23:31,  1.58it/s]
 67%|██████▋   | 38353/57600 [6:43:48<3:19:14,  1.61it/s]
 67%|██████▋   | 38354/57600 [6:43:49<3:17:18,  1.63it/s]
 67%|██████▋   | 38355/57600 [6:43:49<3:11:47,  1.67it/s]
 67%|██████▋   | 38356/57600 [6:43:50<3:14:45,  1.65it/s]
 67%|██████▋   | 38357/57600 [6:43:50<3:20:42,  1.60it/s]
 67%|██████▋   | 38358/57600 [6:43:51<3:17:03,  1.63it/s]
 67%|██████▋   | 38359/57600 [6:43:52<3:17:24,  1.62it/s]
 67%|██████▋   | 38360/57600 [6:43:52<3:19:16,  1.61it/s]
                                                         
{'loss': 1.1441, 'learning_rate': 4.0167247386759583e-07, 'epoch': 423.4}

 67%|██████▋   | 38360/57600 [6:43:52<3:19:16,  1.61it/s]
 67%|██████▋   | 38361/57600 [6:43:53<3:17:06,  1.63it/s]
 67%|██████▋   | 38362/57600 [6:43:54<3:16:18,  1.63it/s]
 67%|██████▋   | 38363/57600 [6:43:54<3:19:04,  1.61it/s]
 67%|██████▋   | 38364/57600 [6:43:55<3:14:16,  1.65it/s]
 67%|██████▋   | 38365/57600 [6:43:55<3:08:05,  1.70it/s]
 67%|██████▋   | 38366/57600 [6:43:56<3:08:23,  1.70it/s]
 67%|██████▋   | 38367/57600 [6:43:56<3:07:51,  1.71it/s]
 67%|██████▋   | 38368/57600 [6:43:57<3:15:10,  1.64it/s]
 67%|██████▋   | 38369/57600 [6:43:58<3:16:23,  1.63it/s]
 67%|██████▋   | 38370/57600 [6:43:58<3:20:36,  1.60it/s]
 67%|██████▋   | 38371/57600 [6:43:59<3:17:56,  1.62it/s]
 67%|██████▋   | 38372/57600 [6:44:00<3:23:14,  1.58it/s]
 67%|██████▋   | 38373/57600 [6:44:00<3:21:19,  1.59it/s]
 67%|██████▋   | 38374/57600 [6:44:01<3:18:19,  1.62it/s]
 67%|██████▋   | 38375/57600 [6:44:02<3:23:24,  1.58it/s]
 67%|██████▋   | 38376/57600 [6:44:02<3:15:54,  1.64it/s]
 67%|██████▋   | 38377/57600 [6:44:03<3:13:47,  1.65it/s]
 67%|██████▋   | 38378/57600 [6:44:03<3:14:31,  1.65it/s]
 67%|██████▋   | 38379/57600 [6:44:04<3:10:46,  1.68it/s]
 67%|██████▋   | 38380/57600 [6:44:05<3:15:00,  1.64it/s]
                                                         
{'loss': 1.1839, 'learning_rate': 4.013588850174216e-07, 'epoch': 423.62}

 67%|██████▋   | 38380/57600 [6:44:05<3:15:00,  1.64it/s]
 67%|██████▋   | 38381/57600 [6:44:05<3:16:21,  1.63it/s]
 67%|██████▋   | 38382/57600 [6:44:06<3:21:17,  1.59it/s]
 67%|██████▋   | 38383/57600 [6:44:06<3:22:09,  1.58it/s]
 67%|██████▋   | 38384/57600 [6:44:07<3:25:24,  1.56it/s]
 67%|██████▋   | 38385/57600 [6:44:08<3:19:40,  1.60it/s]
 67%|██████▋   | 38386/57600 [6:44:08<3:23:27,  1.57it/s]
 67%|██████▋   | 38387/57600 [6:44:09<3:19:20,  1.61it/s]
 67%|██████▋   | 38388/57600 [6:44:10<3:19:15,  1.61it/s]
 67%|██████▋   | 38389/57600 [6:44:10<3:24:25,  1.57it/s]
 67%|██████▋   | 38390/57600 [6:44:11<3:18:52,  1.61it/s]
 67%|██████▋   | 38391/57600 [6:44:12<3:24:42,  1.56it/s]
 67%|██████▋   | 38392/57600 [6:44:12<3:18:56,  1.61it/s]
 67%|██████▋   | 38393/57600 [6:44:13<3:20:37,  1.60it/s]
 67%|██████▋   | 38394/57600 [6:44:13<3:24:59,  1.56it/s]
 67%|██████▋   | 38395/57600 [6:44:14<3:21:54,  1.59it/s]
 67%|██████▋   | 38396/57600 [6:44:15<3:23:28,  1.57it/s]
 67%|██████▋   | 38397/57600 [6:44:15<3:24:03,  1.57it/s]
 67%|██████▋   | 38398/57600 [6:44:16<3:34:06,  1.49it/s]
 67%|██████▋   | 38399/57600 [6:44:17<3:29:04,  1.53it/s]
 67%|██████▋   | 38400/57600 [6:44:17<3:26:26,  1.55it/s]
                                                         
{'loss': 1.1659, 'learning_rate': 4.0104529616724733e-07, 'epoch': 423.84}

 67%|██████▋   | 38400/57600 [6:44:17<3:26:26,  1.55it/s]
 67%|██████▋   | 38401/57600 [6:44:18<3:36:12,  1.48it/s]
 67%|██████▋   | 38402/57600 [6:44:19<3:31:39,  1.51it/s]
 67%|██████▋   | 38403/57600 [6:44:19<3:25:22,  1.56it/s]
 67%|██████▋   | 38404/57600 [6:44:20<3:26:07,  1.55it/s]
 67%|██████▋   | 38405/57600 [6:44:21<3:33:23,  1.50it/s]
 67%|██████▋   | 38406/57600 [6:44:21<3:26:23,  1.55it/s]
 67%|██████▋   | 38407/57600 [6:44:22<3:20:05,  1.60it/s]
 67%|██████▋   | 38408/57600 [6:44:22<3:21:10,  1.59it/s]
 67%|██████▋   | 38409/57600 [6:44:23<3:23:02,  1.58it/s]
 67%|██████▋   | 38410/57600 [6:44:24<3:17:34,  1.62it/s]
 67%|██████▋   | 38411/57600 [6:44:24<3:21:32,  1.59it/s]
 67%|██████▋   | 38412/57600 [6:44:25<3:24:28,  1.56it/s]
 67%|██████▋   | 38413/57600 [6:44:26<3:19:44,  1.60it/s]
 67%|██████▋   | 38414/57600 [6:44:26<3:21:37,  1.59it/s]
 67%|██████▋   | 38415/57600 [6:44:27<3:25:26,  1.56it/s]
 67%|██████▋   | 38416/57600 [6:44:27<3:20:23,  1.60it/s]
 67%|██████▋   | 38417/57600 [6:44:28<3:26:30,  1.55it/s]
 67%|██████▋   | 38418/57600 [6:44:29<3:24:00,  1.57it/s]
 67%|██████▋   | 38419/57600 [6:44:29<3:26:16,  1.55it/s]
 67%|██████▋   | 38420/57600 [6:44:30<3:32:00,  1.51it/s]
                                                         
{'loss': 1.1344, 'learning_rate': 4.0073170731707314e-07, 'epoch': 424.06}

 67%|██████▋   | 38420/57600 [6:44:30<3:32:00,  1.51it/s]
 67%|██████▋   | 38421/57600 [6:44:31<3:29:34,  1.53it/s]
 67%|██████▋   | 38422/57600 [6:44:31<3:26:49,  1.55it/s]
 67%|██████▋   | 38423/57600 [6:44:32<3:21:42,  1.58it/s]
 67%|██████▋   | 38424/57600 [6:44:33<3:17:35,  1.62it/s]
 67%|██████▋   | 38425/57600 [6:44:33<3:18:46,  1.61it/s]
 67%|██████▋   | 38426/57600 [6:44:34<3:13:52,  1.65it/s]
 67%|██████▋   | 38427/57600 [6:44:34<3:13:27,  1.65it/s]
 67%|██████▋   | 38428/57600 [6:44:35<3:13:33,  1.65it/s]
 67%|██████▋   | 38429/57600 [6:44:36<3:12:14,  1.66it/s]
 67%|██████▋   | 38430/57600 [6:44:36<3:16:49,  1.62it/s]
 67%|██████▋   | 38431/57600 [6:44:37<3:15:21,  1.64it/s]
 67%|██████▋   | 38432/57600 [6:44:38<3:22:19,  1.58it/s]
 67%|██████▋   | 38433/57600 [6:44:38<3:17:37,  1.62it/s]
 67%|██████▋   | 38434/57600 [6:44:39<3:19:22,  1.60it/s]
 67%|██████▋   | 38435/57600 [6:44:39<3:22:33,  1.58it/s]
 67%|██████▋   | 38436/57600 [6:44:40<3:19:35,  1.60it/s]
 67%|██████▋   | 38437/57600 [6:44:41<3:16:51,  1.62it/s]
 67%|██████▋   | 38438/57600 [6:44:41<3:14:24,  1.64it/s]
 67%|██████▋   | 38439/57600 [6:44:42<3:14:23,  1.64it/s]
 67%|██████▋   | 38440/57600 [6:44:42<3:20:05,  1.60it/s]
                                                         
{'loss': 1.1552, 'learning_rate': 4.0041811846689894e-07, 'epoch': 424.28}

 67%|██████▋   | 38440/57600 [6:44:42<3:20:05,  1.60it/s]
 67%|██████▋   | 38441/57600 [6:44:43<3:24:48,  1.56it/s]
 67%|██████▋   | 38442/57600 [6:44:44<3:23:23,  1.57it/s]
 67%|██████▋   | 38443/57600 [6:44:44<3:19:47,  1.60it/s]
 67%|██████▋   | 38444/57600 [6:44:45<3:16:57,  1.62it/s]
 67%|██████▋   | 38445/57600 [6:44:46<3:16:12,  1.63it/s]
 67%|██████▋   | 38446/57600 [6:44:46<3:20:18,  1.59it/s]
 67%|██████▋   | 38447/57600 [6:44:47<3:18:40,  1.61it/s]
 67%|██████▋   | 38448/57600 [6:44:47<3:13:55,  1.65it/s]
 67%|██████▋   | 38449/57600 [6:44:48<3:19:25,  1.60it/s]
 67%|██████▋   | 38450/57600 [6:44:49<3:16:24,  1.63it/s]
 67%|██████▋   | 38451/57600 [6:44:49<3:19:04,  1.60it/s]
 67%|██████▋   | 38452/57600 [6:44:50<3:23:54,  1.57it/s]
 67%|██████▋   | 38453/57600 [6:44:51<3:24:45,  1.56it/s]
 67%|██████▋   | 38454/57600 [6:44:51<3:21:46,  1.58it/s]
 67%|██████▋   | 38455/57600 [6:44:52<3:19:47,  1.60it/s]
 67%|██████▋   | 38456/57600 [6:44:52<3:13:30,  1.65it/s]
 67%|██████▋   | 38457/57600 [6:44:53<3:12:57,  1.65it/s]
 67%|██████▋   | 38458/57600 [6:44:54<3:13:44,  1.65it/s]
 67%|██████▋   | 38459/57600 [6:44:54<3:16:58,  1.62it/s]
 67%|██████▋   | 38460/57600 [6:44:55<3:16:07,  1.63it/s]
                                                         
{'loss': 1.134, 'learning_rate': 4.001045296167247e-07, 'epoch': 424.5}

 67%|██████▋   | 38460/57600 [6:44:55<3:16:07,  1.63it/s]
 67%|██████▋   | 38461/57600 [6:44:56<3:14:45,  1.64it/s]
 67%|██████▋   | 38462/57600 [6:44:56<3:17:22,  1.62it/s]
 67%|██████▋   | 38463/57600 [6:44:57<3:23:07,  1.57it/s]
 67%|██████▋   | 38464/57600 [6:44:58<3:29:06,  1.53it/s]
 67%|██████▋   | 38465/57600 [6:44:58<3:24:01,  1.56it/s]
 67%|██████▋   | 38466/57600 [6:44:59<3:21:04,  1.59it/s]
 67%|██████▋   | 38467/57600 [6:44:59<3:26:39,  1.54it/s]
 67%|██████▋   | 38468/57600 [6:45:00<3:24:07,  1.56it/s]
 67%|██████▋   | 38469/57600 [6:45:01<3:20:26,  1.59it/s]
 67%|██████▋   | 38470/57600 [6:45:01<3:24:59,  1.56it/s]
 67%|██████▋   | 38471/57600 [6:45:02<3:19:47,  1.60it/s]
 67%|██████▋   | 38472/57600 [6:45:02<3:16:00,  1.63it/s]
 67%|██████▋   | 38473/57600 [6:45:03<3:16:23,  1.62it/s]
 67%|██████▋   | 38474/57600 [6:45:04<3:22:50,  1.57it/s]
 67%|██████▋   | 38475/57600 [6:45:04<3:27:00,  1.54it/s]
 67%|██████▋   | 38476/57600 [6:45:05<3:20:29,  1.59it/s]
 67%|██████▋   | 38477/57600 [6:45:06<3:21:43,  1.58it/s]
 67%|██████▋   | 38478/57600 [6:45:06<3:20:17,  1.59it/s]
 67%|██████▋   | 38479/57600 [6:45:07<3:27:18,  1.54it/s]
 67%|██████▋   | 38480/57600 [6:45:08<3:25:43,  1.55it/s]
                                                         
{'loss': 1.1405, 'learning_rate': 3.997909407665505e-07, 'epoch': 424.72}

 67%|██████▋   | 38480/57600 [6:45:08<3:25:43,  1.55it/s]
 67%|██████▋   | 38481/57600 [6:45:08<3:17:07,  1.62it/s]
 67%|██████▋   | 38482/57600 [6:45:09<3:15:42,  1.63it/s]
 67%|██████▋   | 38483/57600 [6:45:09<3:15:32,  1.63it/s]
 67%|██████▋   | 38484/57600 [6:45:10<3:14:33,  1.64it/s]
 67%|██████▋   | 38485/57600 [6:45:11<3:19:49,  1.59it/s]
 67%|██████▋   | 38486/57600 [6:45:11<3:21:20,  1.58it/s]
 67%|██████▋   | 38487/57600 [6:45:12<3:18:17,  1.61it/s]
 67%|██████▋   | 38488/57600 [6:45:13<3:29:10,  1.52it/s]
 67%|██████▋   | 38489/57600 [6:45:13<3:22:00,  1.58it/s]
 67%|██████▋   | 38490/57600 [6:45:14<3:25:43,  1.55it/s]
 67%|██████▋   | 38491/57600 [6:45:15<3:29:31,  1.52it/s]
 67%|██████▋   | 38492/57600 [6:45:15<3:27:46,  1.53it/s]
 67%|██████▋   | 38493/57600 [6:45:16<3:25:41,  1.55it/s]
 67%|██████▋   | 38494/57600 [6:45:16<3:17:20,  1.61it/s]
 67%|██████▋   | 38495/57600 [6:45:17<3:17:46,  1.61it/s]
 67%|██████▋   | 38496/57600 [6:45:18<3:14:51,  1.63it/s]
 67%|██████▋   | 38497/57600 [6:45:18<3:12:43,  1.65it/s]
 67%|██████▋   | 38498/57600 [6:45:19<3:20:38,  1.59it/s]
 67%|██████▋   | 38499/57600 [6:45:20<3:17:55,  1.61it/s]
 67%|██████▋   | 38500/57600 [6:45:20<3:18:44,  1.60it/s]
                                                         
{'loss': 1.1448, 'learning_rate': 3.994773519163763e-07, 'epoch': 424.94}

 67%|██████▋   | 38500/57600 [6:45:20<3:18:44,  1.60it/s]
 67%|██████▋   | 38501/57600 [6:45:21<3:22:58,  1.57it/s]
 67%|██████▋   | 38502/57600 [6:45:21<3:21:00,  1.58it/s]
 67%|██████▋   | 38503/57600 [6:45:22<3:21:42,  1.58it/s]
 67%|██████▋   | 38504/57600 [6:45:23<3:20:23,  1.59it/s]
 67%|██████▋   | 38505/57600 [6:45:23<3:26:11,  1.54it/s]
 67%|██████▋   | 38506/57600 [6:45:24<3:31:36,  1.50it/s]
 67%|██████▋   | 38507/57600 [6:45:25<3:37:45,  1.46it/s]
 67%|██████▋   | 38508/57600 [6:45:25<3:29:58,  1.52it/s]
 67%|██████▋   | 38509/57600 [6:45:26<3:32:59,  1.49it/s]
 67%|██████▋   | 38510/57600 [6:45:27<3:28:26,  1.53it/s]
 67%|██████▋   | 38511/57600 [6:45:27<3:20:51,  1.58it/s]
 67%|██████▋   | 38512/57600 [6:45:28<3:23:23,  1.56it/s]
 67%|██████▋   | 38513/57600 [6:45:29<3:23:10,  1.57it/s]
 67%|██████▋   | 38514/57600 [6:45:29<3:19:09,  1.60it/s]
 67%|██████▋   | 38515/57600 [6:45:30<3:15:23,  1.63it/s]
 67%|██████▋   | 38516/57600 [6:45:30<3:14:08,  1.64it/s]
 67%|██████▋   | 38517/57600 [6:45:31<3:11:24,  1.66it/s]
 67%|██████▋   | 38518/57600 [6:45:32<3:13:33,  1.64it/s]
 67%|██████▋   | 38519/57600 [6:45:32<3:12:15,  1.65it/s]
 67%|██████▋   | 38520/57600 [6:45:33<3:17:19,  1.61it/s]
                                                         
{'loss': 1.1329, 'learning_rate': 3.99163763066202e-07, 'epoch': 425.17}

 67%|██████▋   | 38520/57600 [6:45:33<3:17:19,  1.61it/s]
 67%|██████▋   | 38521/57600 [6:45:34<3:20:00,  1.59it/s]
 67%|██████▋   | 38522/57600 [6:45:34<3:24:24,  1.56it/s]
 67%|██████▋   | 38523/57600 [6:45:35<3:23:04,  1.57it/s]
 67%|██████▋   | 38524/57600 [6:45:35<3:20:41,  1.58it/s]
 67%|██████▋   | 38525/57600 [6:45:36<3:24:38,  1.55it/s]
 67%|██████▋   | 38526/57600 [6:45:37<3:23:21,  1.56it/s]
 67%|██████▋   | 38527/57600 [6:45:37<3:24:03,  1.56it/s]
 67%|██████▋   | 38528/57600 [6:45:38<3:19:19,  1.59it/s]
 67%|██████▋   | 38529/57600 [6:45:39<3:20:36,  1.58it/s]
 67%|██████▋   | 38530/57600 [6:45:39<3:22:39,  1.57it/s]
 67%|██████▋   | 38531/57600 [6:45:40<3:17:30,  1.61it/s]
 67%|██████▋   | 38532/57600 [6:45:41<3:21:06,  1.58it/s]
 67%|██████▋   | 38533/57600 [6:45:41<3:20:54,  1.58it/s]
 67%|██████▋   | 38534/57600 [6:45:42<3:26:35,  1.54it/s]
 67%|██████▋   | 38535/57600 [6:45:43<3:31:26,  1.50it/s]
 67%|██████▋   | 38536/57600 [6:45:43<3:35:10,  1.48it/s]
 67%|██████▋   | 38537/57600 [6:45:44<3:29:53,  1.51it/s]
 67%|██████▋   | 38538/57600 [6:45:44<3:25:24,  1.55it/s]
 67%|██████▋   | 38539/57600 [6:45:45<3:20:30,  1.58it/s]
 67%|██████▋   | 38540/57600 [6:45:46<3:17:21,  1.61it/s]
                                                         
{'loss': 1.1272, 'learning_rate': 3.9885017421602786e-07, 'epoch': 425.39}

 67%|██████▋   | 38540/57600 [6:45:46<3:17:21,  1.61it/s]
 67%|██████▋   | 38541/57600 [6:45:46<3:26:30,  1.54it/s]
 67%|██████▋   | 38542/57600 [6:45:47<3:24:08,  1.56it/s]
 67%|██████▋   | 38543/57600 [6:45:48<3:26:09,  1.54it/s]
 67%|██████▋   | 38544/57600 [6:45:48<3:25:21,  1.55it/s]
 67%|██████▋   | 38545/57600 [6:45:49<3:26:46,  1.54it/s]
 67%|██████▋   | 38546/57600 [6:45:50<3:26:01,  1.54it/s]
 67%|██████▋   | 38547/57600 [6:45:50<3:20:34,  1.58it/s]
 67%|██████▋   | 38548/57600 [6:45:51<3:19:45,  1.59it/s]
 67%|██████▋   | 38549/57600 [6:45:51<3:17:03,  1.61it/s]
 67%|██████▋   | 38550/57600 [6:45:52<3:21:44,  1.57it/s]
 67%|██████▋   | 38551/57600 [6:45:53<3:18:14,  1.60it/s]
 67%|██████▋   | 38552/57600 [6:45:53<3:20:18,  1.58it/s]
 67%|██████▋   | 38553/57600 [6:45:54<3:16:19,  1.62it/s]
 67%|██████▋   | 38554/57600 [6:45:55<3:20:16,  1.59it/s]
 67%|██████▋   | 38555/57600 [6:45:55<3:18:19,  1.60it/s]
 67%|██████▋   | 38556/57600 [6:45:56<3:13:47,  1.64it/s]
 67%|██████▋   | 38557/57600 [6:45:56<3:08:52,  1.68it/s]
 67%|██████▋   | 38558/57600 [6:45:57<3:08:28,  1.68it/s]
 67%|██████▋   | 38559/57600 [6:45:58<3:11:42,  1.66it/s]
 67%|██████▋   | 38560/57600 [6:45:58<3:14:58,  1.63it/s]
                                                         
{'loss': 1.1722, 'learning_rate': 3.985365853658536e-07, 'epoch': 425.61}

 67%|██████▋   | 38560/57600 [6:45:58<3:14:58,  1.63it/s]
 67%|██████▋   | 38561/57600 [6:45:59<3:21:06,  1.58it/s]
 67%|██████▋   | 38562/57600 [6:46:00<3:25:11,  1.55it/s]
 67%|██████▋   | 38563/57600 [6:46:00<3:26:21,  1.54it/s]
 67%|██████▋   | 38564/57600 [6:46:01<3:22:46,  1.56it/s]
 67%|██████▋   | 38565/57600 [6:46:01<3:22:01,  1.57it/s]
 67%|██████▋   | 38566/57600 [6:46:02<3:26:34,  1.54it/s]
 67%|██████▋   | 38567/57600 [6:46:03<3:21:18,  1.58it/s]
 67%|██████▋   | 38568/57600 [6:46:03<3:19:08,  1.59it/s]
 67%|██████▋   | 38569/57600 [6:46:04<3:20:49,  1.58it/s]
 67%|██████▋   | 38570/57600 [6:46:05<3:29:56,  1.51it/s]
 67%|██████▋   | 38571/57600 [6:46:05<3:29:31,  1.51it/s]
 67%|██████▋   | 38572/57600 [6:46:06<3:33:16,  1.49it/s]
 67%|██████▋   | 38573/57600 [6:46:07<3:28:43,  1.52it/s]
 67%|██████▋   | 38574/57600 [6:46:07<3:19:37,  1.59it/s]
 67%|██████▋   | 38575/57600 [6:46:08<3:14:47,  1.63it/s]
 67%|██████▋   | 38576/57600 [6:46:08<3:13:01,  1.64it/s]
 67%|██████▋   | 38577/57600 [6:46:09<3:14:40,  1.63it/s]
 67%|██████▋   | 38578/57600 [6:46:10<3:15:02,  1.63it/s]
 67%|██████▋   | 38579/57600 [6:46:10<3:17:11,  1.61it/s]
 67%|██████▋   | 38580/57600 [6:46:11<3:14:01,  1.63it/s]
                                                         
{'loss': 1.1337, 'learning_rate': 3.982229965156794e-07, 'epoch': 425.83}

 67%|██████▋   | 38580/57600 [6:46:11<3:14:01,  1.63it/s]
 67%|██████▋   | 38581/57600 [6:46:12<3:12:33,  1.65it/s]
 67%|██████▋   | 38582/57600 [6:46:12<3:13:31,  1.64it/s]
 67%|██████▋   | 38583/57600 [6:46:13<3:14:56,  1.63it/s]
 67%|██████▋   | 38584/57600 [6:46:13<3:11:03,  1.66it/s]
 67%|██████▋   | 38585/57600 [6:46:14<3:09:08,  1.68it/s]
 67%|██████▋   | 38586/57600 [6:46:15<3:09:57,  1.67it/s]
 67%|██████▋   | 38587/57600 [6:46:15<3:07:40,  1.69it/s]
 67%|██████▋   | 38588/57600 [6:46:16<3:09:46,  1.67it/s]
 67%|██████▋   | 38589/57600 [6:46:16<3:16:11,  1.62it/s]
 67%|██████▋   | 38590/57600 [6:46:17<3:15:54,  1.62it/s]
 67%|██████▋   | 38591/57600 [6:46:18<3:17:22,  1.61it/s]
 67%|██████▋   | 38592/57600 [6:46:18<3:12:32,  1.65it/s]
 67%|██████▋   | 38593/57600 [6:46:19<3:12:41,  1.64it/s]
 67%|██████▋   | 38594/57600 [6:46:19<3:15:54,  1.62it/s]
 67%|██████▋   | 38595/57600 [6:46:20<3:14:58,  1.62it/s]
 67%|██████▋   | 38596/57600 [6:46:21<3:24:38,  1.55it/s]
 67%|██████▋   | 38597/57600 [6:46:21<3:29:51,  1.51it/s]
 67%|██████▋   | 38598/57600 [6:46:22<3:24:46,  1.55it/s]
 67%|██████▋   | 38599/57600 [6:46:23<3:21:01,  1.58it/s]
 67%|██████▋   | 38600/57600 [6:46:23<3:20:38,  1.58it/s]
                                                         
{'loss': 1.1551, 'learning_rate': 3.9790940766550517e-07, 'epoch': 426.05}

 67%|██████▋   | 38600/57600 [6:46:23<3:20:38,  1.58it/s]
 67%|██████▋   | 38601/57600 [6:46:24<3:22:36,  1.56it/s]
 67%|██████▋   | 38602/57600 [6:46:25<3:22:43,  1.56it/s]
 67%|██████▋   | 38603/57600 [6:46:25<3:18:28,  1.60it/s]
 67%|██████▋   | 38604/57600 [6:46:26<3:17:48,  1.60it/s]
 67%|██████▋   | 38605/57600 [6:46:26<3:18:13,  1.60it/s]
 67%|██████▋   | 38606/57600 [6:46:27<3:19:46,  1.58it/s]
 67%|██████▋   | 38607/57600 [6:46:28<3:21:18,  1.57it/s]
 67%|██████▋   | 38608/57600 [6:46:28<3:22:31,  1.56it/s]
 67%|██████▋   | 38609/57600 [6:46:29<3:17:24,  1.60it/s]
 67%|██████▋   | 38610/57600 [6:46:30<3:15:53,  1.62it/s]
 67%|██████▋   | 38611/57600 [6:46:30<3:18:20,  1.60it/s]
 67%|██████▋   | 38612/57600 [6:46:31<3:16:45,  1.61it/s]
 67%|██████▋   | 38613/57600 [6:46:31<3:12:45,  1.64it/s]
 67%|██████▋   | 38614/57600 [6:46:32<3:14:34,  1.63it/s]
 67%|██████▋   | 38615/57600 [6:46:33<3:15:43,  1.62it/s]
 67%|██████▋   | 38616/57600 [6:46:33<3:17:27,  1.60it/s]
 67%|██████▋   | 38617/57600 [6:46:34<3:16:14,  1.61it/s]
 67%|██████▋   | 38618/57600 [6:46:35<3:16:46,  1.61it/s]
 67%|██████▋   | 38619/57600 [6:46:35<3:19:20,  1.59it/s]
 67%|██████▋   | 38620/57600 [6:46:36<3:21:22,  1.57it/s]
                                                         
{'loss': 1.1655, 'learning_rate': 3.97595818815331e-07, 'epoch': 426.27}

 67%|██████▋   | 38620/57600 [6:46:36<3:21:22,  1.57it/s]
 67%|██████▋   | 38621/57600 [6:46:36<3:17:30,  1.60it/s]
 67%|██████▋   | 38622/57600 [6:46:37<3:15:47,  1.62it/s]
 67%|██████▋   | 38623/57600 [6:46:38<3:13:29,  1.63it/s]
 67%|██████▋   | 38624/57600 [6:46:38<3:12:41,  1.64it/s]
 67%|██████▋   | 38625/57600 [6:46:39<3:06:58,  1.69it/s]
 67%|██████▋   | 38626/57600 [6:46:39<3:11:14,  1.65it/s]
 67%|██████▋   | 38627/57600 [6:46:40<3:13:04,  1.64it/s]
 67%|██████▋   | 38628/57600 [6:46:41<3:11:07,  1.65it/s]
 67%|██████▋   | 38629/57600 [6:46:41<3:21:46,  1.57it/s]
 67%|██████▋   | 38630/57600 [6:46:42<3:24:47,  1.54it/s]
 67%|██████▋   | 38631/57600 [6:46:43<3:21:35,  1.57it/s]
 67%|██████▋   | 38632/57600 [6:46:43<3:20:07,  1.58it/s]
 67%|██████▋   | 38633/57600 [6:46:44<3:17:24,  1.60it/s]
 67%|██████▋   | 38634/57600 [6:46:45<3:18:45,  1.59it/s]
 67%|██████▋   | 38635/57600 [6:46:45<3:16:06,  1.61it/s]
 67%|██████▋   | 38636/57600 [6:46:46<3:16:50,  1.61it/s]
 67%|██████▋   | 38637/57600 [6:46:46<3:22:10,  1.56it/s]
 67%|██████▋   | 38638/57600 [6:46:47<3:15:12,  1.62it/s]
 67%|██████▋   | 38639/57600 [6:46:48<3:10:09,  1.66it/s]
 67%|██████▋   | 38640/57600 [6:46:48<3:08:25,  1.68it/s]
                                                         
{'loss': 1.1145, 'learning_rate': 3.9728222996515683e-07, 'epoch': 426.49}

 67%|██████▋   | 38640/57600 [6:46:48<3:08:25,  1.68it/s]
 67%|██████▋   | 38641/57600 [6:46:49<3:15:44,  1.61it/s]
 67%|██████▋   | 38642/57600 [6:46:50<3:19:52,  1.58it/s]
 67%|██████▋   | 38643/57600 [6:46:50<3:18:34,  1.59it/s]
 67%|██████▋   | 38644/57600 [6:46:51<3:13:46,  1.63it/s]
 67%|██████▋   | 38645/57600 [6:46:51<3:18:26,  1.59it/s]
 67%|██████▋   | 38646/57600 [6:46:52<3:13:08,  1.64it/s]
 67%|██████▋   | 38647/57600 [6:46:53<3:11:33,  1.65it/s]
 67%|██████▋   | 38648/57600 [6:46:53<3:08:46,  1.67it/s]
 67%|██████▋   | 38649/57600 [6:46:54<3:07:57,  1.68it/s]
 67%|██████▋   | 38650/57600 [6:46:54<3:05:03,  1.71it/s]
 67%|██████▋   | 38651/57600 [6:46:55<3:12:54,  1.64it/s]
 67%|██████▋   | 38652/57600 [6:46:56<3:19:33,  1.58it/s]
 67%|██████▋   | 38653/57600 [6:46:56<3:14:30,  1.62it/s]
 67%|██████▋   | 38654/57600 [6:46:57<3:17:24,  1.60it/s]
 67%|██████▋   | 38655/57600 [6:46:57<3:12:23,  1.64it/s]
 67%|██████▋   | 38656/57600 [6:46:58<3:10:36,  1.66it/s]
 67%|██████▋   | 38657/57600 [6:46:59<3:13:09,  1.63it/s]
 67%|██████▋   | 38658/57600 [6:46:59<3:12:16,  1.64it/s]
 67%|██████▋   | 38659/57600 [6:47:00<3:14:46,  1.62it/s]
 67%|██████▋   | 38660/57600 [6:47:01<3:17:01,  1.60it/s]
                                                         
{'loss': 1.1747, 'learning_rate': 3.9696864111498253e-07, 'epoch': 426.71}

 67%|██████▋   | 38660/57600 [6:47:01<3:17:01,  1.60it/s]
 67%|██████▋   | 38661/57600 [6:47:01<3:18:50,  1.59it/s]
 67%|██████▋   | 38662/57600 [6:47:02<3:19:12,  1.58it/s]
 67%|██████▋   | 38663/57600 [6:47:02<3:17:34,  1.60it/s]
 67%|██████▋   | 38664/57600 [6:47:03<3:25:08,  1.54it/s]
 67%|██████▋   | 38665/57600 [6:47:04<3:20:59,  1.57it/s]
 67%|██████▋   | 38666/57600 [6:47:04<3:17:49,  1.60it/s]
 67%|██████▋   | 38667/57600 [6:47:05<3:15:02,  1.62it/s]
 67%|██████▋   | 38668/57600 [6:47:06<3:17:56,  1.59it/s]
 67%|██████▋   | 38669/57600 [6:47:06<3:24:34,  1.54it/s]
 67%|██████▋   | 38670/57600 [6:47:07<3:29:39,  1.50it/s]
 67%|██████▋   | 38671/57600 [6:47:08<3:40:05,  1.43it/s]
 67%|██████▋   | 38672/57600 [6:47:08<3:40:28,  1.43it/s]
 67%|██████▋   | 38673/57600 [6:47:09<3:38:31,  1.44it/s]
 67%|██████▋   | 38674/57600 [6:47:10<3:33:37,  1.48it/s]
 67%|██████▋   | 38675/57600 [6:47:10<3:30:01,  1.50it/s]
 67%|██████▋   | 38676/57600 [6:47:11<3:32:04,  1.49it/s]
 67%|██████▋   | 38677/57600 [6:47:12<3:26:07,  1.53it/s]
 67%|██████▋   | 38678/57600 [6:47:12<3:27:05,  1.52it/s]
 67%|██████▋   | 38679/57600 [6:47:13<3:26:26,  1.53it/s]
 67%|██████▋   | 38680/57600 [6:47:14<3:23:57,  1.55it/s]
                                                         
{'loss': 1.1222, 'learning_rate': 3.966550522648084e-07, 'epoch': 426.93}

 67%|██████▋   | 38680/57600 [6:47:14<3:23:57,  1.55it/s]
 67%|██████▋   | 38681/57600 [6:47:14<3:23:27,  1.55it/s]
 67%|██████▋   | 38682/57600 [6:47:15<3:17:27,  1.60it/s]
 67%|██████▋   | 38683/57600 [6:47:15<3:16:07,  1.61it/s]
 67%|██████▋   | 38684/57600 [6:47:16<3:21:09,  1.57it/s]
 67%|██████▋   | 38685/57600 [6:47:17<3:25:22,  1.53it/s]
 67%|██████▋   | 38686/57600 [6:47:17<3:23:47,  1.55it/s]
 67%|██████▋   | 38687/57600 [6:47:18<3:25:45,  1.53it/s]
 67%|██████▋   | 38688/57600 [6:47:19<3:19:52,  1.58it/s]
 67%|██████▋   | 38689/57600 [6:47:19<3:16:48,  1.60it/s]
 67%|██████▋   | 38690/57600 [6:47:20<3:19:46,  1.58it/s]
 67%|██████▋   | 38691/57600 [6:47:21<3:17:50,  1.59it/s]
 67%|██████▋   | 38692/57600 [6:47:21<3:19:29,  1.58it/s]
 67%|██████▋   | 38693/57600 [6:47:22<3:14:21,  1.62it/s]
 67%|██████▋   | 38694/57600 [6:47:22<3:14:51,  1.62it/s]
 67%|██████▋   | 38695/57600 [6:47:23<3:09:39,  1.66it/s]
 67%|██████▋   | 38696/57600 [6:47:24<3:08:39,  1.67it/s]
 67%|██████▋   | 38697/57600 [6:47:24<3:07:55,  1.68it/s]
 67%|██████▋   | 38698/57600 [6:47:25<3:24:21,  1.54it/s]
 67%|██████▋   | 38699/57600 [6:47:26<3:18:19,  1.59it/s]
 67%|██████▋   | 38700/57600 [6:47:26<3:15:48,  1.61it/s]
                                                         
{'loss': 1.1597, 'learning_rate': 3.963414634146341e-07, 'epoch': 427.15}

 67%|██████▋   | 38700/57600 [6:47:26<3:15:48,  1.61it/s]
 67%|██████▋   | 38701/57600 [6:47:27<3:17:14,  1.60it/s]
 67%|██████▋   | 38702/57600 [6:47:27<3:21:47,  1.56it/s]
 67%|██████▋   | 38703/57600 [6:47:28<3:17:13,  1.60it/s]
 67%|██████▋   | 38704/57600 [6:47:29<3:15:44,  1.61it/s]
 67%|██████▋   | 38705/57600 [6:47:29<3:14:24,  1.62it/s]
 67%|██████▋   | 38706/57600 [6:47:30<3:11:22,  1.65it/s]
 67%|██████▋   | 38707/57600 [6:47:30<3:10:56,  1.65it/s]
 67%|██████▋   | 38708/57600 [6:47:31<3:13:15,  1.63it/s]
 67%|██████▋   | 38709/57600 [6:47:32<3:08:18,  1.67it/s]
 67%|██████▋   | 38710/57600 [6:47:32<3:07:38,  1.68it/s]
 67%|██████▋   | 38711/57600 [6:47:33<3:13:40,  1.63it/s]
 67%|██████▋   | 38712/57600 [6:47:34<3:14:53,  1.62it/s]
 67%|██████▋   | 38713/57600 [6:47:34<3:16:09,  1.60it/s]
 67%|██████▋   | 38714/57600 [6:47:35<3:13:10,  1.63it/s]
 67%|██████▋   | 38715/57600 [6:47:35<3:21:00,  1.57it/s]
 67%|██████▋   | 38716/57600 [6:47:36<3:21:23,  1.56it/s]
 67%|██████▋   | 38717/57600 [6:47:37<3:27:57,  1.51it/s]
 67%|██████▋   | 38718/57600 [6:47:38<3:35:30,  1.46it/s]
 67%|██████▋   | 38719/57600 [6:47:38<3:29:13,  1.50it/s]
 67%|██████▋   | 38720/57600 [6:47:39<3:30:15,  1.50it/s]
                                                         
{'loss': 1.1525, 'learning_rate': 3.960278745644599e-07, 'epoch': 427.37}

 67%|██████▋   | 38720/57600 [6:47:39<3:30:15,  1.50it/s]
 67%|██████▋   | 38721/57600 [6:47:40<3:34:29,  1.47it/s]
 67%|██████▋   | 38722/57600 [6:47:40<3:31:50,  1.49it/s]
 67%|██████▋   | 38723/57600 [6:47:41<3:27:38,  1.52it/s]
 67%|██████▋   | 38724/57600 [6:47:41<3:27:12,  1.52it/s]
 67%|██████▋   | 38725/57600 [6:47:42<3:18:44,  1.58it/s]
 67%|██████▋   | 38726/57600 [6:47:43<3:19:26,  1.58it/s]
 67%|██████▋   | 38727/57600 [6:47:43<3:17:49,  1.59it/s]
 67%|██████▋   | 38728/57600 [6:47:44<3:15:55,  1.61it/s]
 67%|██████▋   | 38729/57600 [6:47:45<3:19:21,  1.58it/s]
 67%|██████▋   | 38730/57600 [6:47:45<3:22:10,  1.56it/s]
 67%|██████▋   | 38731/57600 [6:47:46<3:18:31,  1.58it/s]
 67%|██████▋   | 38732/57600 [6:47:46<3:17:52,  1.59it/s]
 67%|██████▋   | 38733/57600 [6:47:47<3:14:40,  1.62it/s]
 67%|██████▋   | 38734/57600 [6:47:48<3:24:43,  1.54it/s]
 67%|██████▋   | 38735/57600 [6:47:48<3:19:23,  1.58it/s]
 67%|██████▋   | 38736/57600 [6:47:49<3:22:37,  1.55it/s]
 67%|██████▋   | 38737/57600 [6:47:50<3:19:53,  1.57it/s]
 67%|██████▋   | 38738/57600 [6:47:50<3:21:22,  1.56it/s]
 67%|██████▋   | 38739/57600 [6:47:51<3:21:04,  1.56it/s]
 67%|██████▋   | 38740/57600 [6:47:52<3:20:02,  1.57it/s]
                                                         
{'loss': 1.1365, 'learning_rate': 3.9571428571428575e-07, 'epoch': 427.59}

 67%|██████▋   | 38740/57600 [6:47:52<3:20:02,  1.57it/s]
 67%|██████▋   | 38741/57600 [6:47:52<3:12:49,  1.63it/s]
 67%|██████▋   | 38742/57600 [6:47:53<3:07:36,  1.68it/s]
 67%|██████▋   | 38743/57600 [6:47:53<3:05:48,  1.69it/s]
 67%|██████▋   | 38744/57600 [6:47:54<3:06:08,  1.69it/s]
 67%|██████▋   | 38745/57600 [6:47:54<3:06:50,  1.68it/s]
 67%|██████▋   | 38746/57600 [6:47:55<3:16:40,  1.60it/s]
 67%|██████▋   | 38747/57600 [6:47:56<3:10:17,  1.65it/s]
 67%|██████▋   | 38748/57600 [6:47:56<3:09:28,  1.66it/s]
 67%|██████▋   | 38749/57600 [6:47:57<3:10:32,  1.65it/s]
 67%|██████▋   | 38750/57600 [6:47:58<3:10:39,  1.65it/s]
 67%|██████▋   | 38751/57600 [6:47:58<3:12:36,  1.63it/s]
 67%|██████▋   | 38752/57600 [6:47:59<3:10:12,  1.65it/s]
 67%|██████▋   | 38753/57600 [6:47:59<3:10:35,  1.65it/s]
 67%|██████▋   | 38754/57600 [6:48:00<3:13:58,  1.62it/s]
 67%|██████▋   | 38755/57600 [6:48:01<3:22:28,  1.55it/s]
 67%|██████▋   | 38756/57600 [6:48:01<3:27:53,  1.51it/s]
 67%|██████▋   | 38757/57600 [6:48:02<3:21:48,  1.56it/s]
 67%|██████▋   | 38758/57600 [6:48:03<3:20:09,  1.57it/s]
 67%|██████▋   | 38759/57600 [6:48:03<3:17:12,  1.59it/s]
 67%|██████▋   | 38760/57600 [6:48:04<3:14:25,  1.61it/s]
                                                         
{'loss': 1.144, 'learning_rate': 3.9540069686411145e-07, 'epoch': 427.81}

 67%|██████▋   | 38760/57600 [6:48:04<3:14:25,  1.61it/s]
 67%|██████▋   | 38761/57600 [6:48:04<3:11:48,  1.64it/s]
 67%|██████▋   | 38762/57600 [6:48:05<3:12:12,  1.63it/s]
 67%|██████▋   | 38763/57600 [6:48:06<3:19:27,  1.57it/s]
 67%|██████▋   | 38764/57600 [6:48:06<3:22:40,  1.55it/s]
 67%|██████▋   | 38765/57600 [6:48:07<3:25:10,  1.53it/s]
 67%|██████▋   | 38766/57600 [6:48:08<3:26:02,  1.52it/s]
 67%|██████▋   | 38767/57600 [6:48:08<3:21:17,  1.56it/s]
 67%|██████▋   | 38768/57600 [6:48:09<3:15:09,  1.61it/s]
 67%|██████▋   | 38769/57600 [6:48:10<3:20:10,  1.57it/s]
 67%|██████▋   | 38770/57600 [6:48:10<3:29:09,  1.50it/s]
 67%|██████▋   | 38771/57600 [6:48:11<3:29:12,  1.50it/s]
 67%|██████▋   | 38772/57600 [6:48:12<3:23:29,  1.54it/s]
 67%|██████▋   | 38773/57600 [6:48:12<3:26:32,  1.52it/s]
 67%|██████▋   | 38774/57600 [6:48:13<3:21:42,  1.56it/s]
 67%|██████▋   | 38775/57600 [6:48:14<3:20:54,  1.56it/s]
 67%|██████▋   | 38776/57600 [6:48:14<3:21:12,  1.56it/s]
 67%|██████▋   | 38777/57600 [6:48:15<3:32:04,  1.48it/s]
 67%|██████▋   | 38778/57600 [6:48:16<3:33:10,  1.47it/s]
 67%|██████▋   | 38779/57600 [6:48:16<3:32:02,  1.48it/s]
 67%|██████▋   | 38780/57600 [6:48:17<3:32:20,  1.48it/s]
                                                         
{'loss': 1.117, 'learning_rate': 3.950871080139373e-07, 'epoch': 428.04}

 67%|██████▋   | 38780/57600 [6:48:17<3:32:20,  1.48it/s]
 67%|██████▋   | 38781/57600 [6:48:18<3:28:52,  1.50it/s]
 67%|██████▋   | 38782/57600 [6:48:18<3:22:13,  1.55it/s]
 67%|██████▋   | 38783/57600 [6:48:19<3:22:44,  1.55it/s]
 67%|██████▋   | 38784/57600 [6:48:20<3:21:20,  1.56it/s]
 67%|██████▋   | 38785/57600 [6:48:20<3:20:57,  1.56it/s]
 67%|██████▋   | 38786/57600 [6:48:21<3:20:10,  1.57it/s]
 67%|██████▋   | 38787/57600 [6:48:21<3:23:35,  1.54it/s]
 67%|██████▋   | 38788/57600 [6:48:22<3:17:07,  1.59it/s]
 67%|██████▋   | 38789/57600 [6:48:23<3:22:42,  1.55it/s]
 67%|██████▋   | 38790/57600 [6:48:23<3:22:00,  1.55it/s]
 67%|██████▋   | 38791/57600 [6:48:24<3:21:55,  1.55it/s]
 67%|██████▋   | 38792/57600 [6:48:25<3:19:40,  1.57it/s]
 67%|██████▋   | 38793/57600 [6:48:25<3:19:48,  1.57it/s]
 67%|██████▋   | 38794/57600 [6:48:26<3:16:34,  1.59it/s]
 67%|██████▋   | 38795/57600 [6:48:27<3:17:32,  1.59it/s]
 67%|██████▋   | 38796/57600 [6:48:27<3:12:51,  1.63it/s]
 67%|██████▋   | 38797/57600 [6:48:28<3:11:49,  1.63it/s]
 67%|██████▋   | 38798/57600 [6:48:28<3:11:33,  1.64it/s]
 67%|██████▋   | 38799/57600 [6:48:29<3:12:15,  1.63it/s]
 67%|██████▋   | 38800/57600 [6:48:30<3:15:40,  1.60it/s]
                                                         
{'loss': 1.1474, 'learning_rate': 3.94773519163763e-07, 'epoch': 428.26}

 67%|██████▋   | 38800/57600 [6:48:30<3:15:40,  1.60it/s]
 67%|██████▋   | 38801/57600 [6:48:30<3:20:38,  1.56it/s]
 67%|██████▋   | 38802/57600 [6:48:31<3:16:49,  1.59it/s]
 67%|██████▋   | 38803/57600 [6:48:32<3:23:44,  1.54it/s]
 67%|██████▋   | 38804/57600 [6:48:32<3:23:18,  1.54it/s]
 67%|██████▋   | 38805/57600 [6:48:33<3:26:05,  1.52it/s]
 67%|██████▋   | 38806/57600 [6:48:33<3:20:58,  1.56it/s]
 67%|██████▋   | 38807/57600 [6:48:34<3:22:03,  1.55it/s]
 67%|██████▋   | 38808/57600 [6:48:35<3:23:05,  1.54it/s]
 67%|██████▋   | 38809/57600 [6:48:35<3:22:00,  1.55it/s]
 67%|██████▋   | 38810/57600 [6:48:36<3:22:25,  1.55it/s]
 67%|██████▋   | 38811/57600 [6:48:37<3:22:47,  1.54it/s]
 67%|██████▋   | 38812/57600 [6:48:37<3:18:24,  1.58it/s]
 67%|██████▋   | 38813/57600 [6:48:38<3:14:41,  1.61it/s]
 67%|██████▋   | 38814/57600 [6:48:39<3:13:44,  1.62it/s]
 67%|██████▋   | 38815/57600 [6:48:39<3:13:30,  1.62it/s]
 67%|██████▋   | 38816/57600 [6:48:40<3:13:17,  1.62it/s]
 67%|██████▋   | 38817/57600 [6:48:40<3:20:16,  1.56it/s]
 67%|██████▋   | 38818/57600 [6:48:41<3:22:55,  1.54it/s]
 67%|██████▋   | 38819/57600 [6:48:42<3:22:00,  1.55it/s]
 67%|██████▋   | 38820/57600 [6:48:42<3:21:51,  1.55it/s]
                                                         
{'loss': 1.1054, 'learning_rate': 3.9445993031358887e-07, 'epoch': 428.48}

 67%|██████▋   | 38820/57600 [6:48:42<3:21:51,  1.55it/s]
 67%|██████▋   | 38821/57600 [6:48:43<3:22:40,  1.54it/s]
 67%|██████▋   | 38822/57600 [6:48:44<3:16:44,  1.59it/s]
 67%|██████▋   | 38823/57600 [6:48:44<3:19:03,  1.57it/s]
 67%|██████▋   | 38824/57600 [6:48:45<3:23:07,  1.54it/s]
 67%|██████▋   | 38825/57600 [6:48:46<3:15:54,  1.60it/s]
 67%|██████▋   | 38826/57600 [6:48:46<3:25:23,  1.52it/s]
 67%|██████▋   | 38827/57600 [6:48:47<3:27:56,  1.50it/s]
 67%|██████▋   | 38828/57600 [6:48:48<3:19:09,  1.57it/s]
 67%|██████▋   | 38829/57600 [6:48:48<3:14:38,  1.61it/s]
 67%|██████▋   | 38830/57600 [6:48:49<3:13:04,  1.62it/s]
 67%|██████▋   | 38831/57600 [6:48:49<3:14:53,  1.61it/s]
 67%|██████▋   | 38832/57600 [6:48:50<3:11:17,  1.64it/s]
 67%|██████▋   | 38833/57600 [6:48:51<3:09:58,  1.65it/s]
 67%|██████▋   | 38834/57600 [6:48:51<3:18:02,  1.58it/s]
 67%|██████▋   | 38835/57600 [6:48:52<3:16:39,  1.59it/s]
 67%|██████▋   | 38836/57600 [6:48:52<3:13:36,  1.62it/s]
 67%|██████▋   | 38837/57600 [6:48:53<3:09:57,  1.65it/s]
 67%|██████▋   | 38838/57600 [6:48:54<3:08:50,  1.66it/s]
 67%|██████▋   | 38839/57600 [6:48:54<3:06:00,  1.68it/s]
 67%|██████▋   | 38840/57600 [6:48:55<3:04:46,  1.69it/s]
                                                         
{'loss': 1.1707, 'learning_rate': 3.9414634146341456e-07, 'epoch': 428.7}

 67%|██████▋   | 38840/57600 [6:48:55<3:04:46,  1.69it/s]
 67%|██████▋   | 38841/57600 [6:48:55<3:06:39,  1.68it/s]
 67%|██████▋   | 38842/57600 [6:48:56<3:12:05,  1.63it/s]
 67%|██████▋   | 38843/57600 [6:48:57<3:11:01,  1.64it/s]
 67%|██████▋   | 38844/57600 [6:48:57<3:20:23,  1.56it/s]
 67%|██████▋   | 38845/57600 [6:48:58<3:18:39,  1.57it/s]
 67%|██████▋   | 38846/57600 [6:48:59<3:13:29,  1.62it/s]
 67%|██████▋   | 38847/57600 [6:48:59<3:12:27,  1.62it/s]
 67%|██████▋   | 38848/57600 [6:49:00<3:11:50,  1.63it/s]
 67%|██████▋   | 38849/57600 [6:49:00<3:11:03,  1.64it/s]
 67%|██████▋   | 38850/57600 [6:49:01<3:16:02,  1.59it/s]
 67%|██████▋   | 38851/57600 [6:49:02<3:14:21,  1.61it/s]
 67%|██████▋   | 38852/57600 [6:49:02<3:11:06,  1.64it/s]
 67%|██████▋   | 38853/57600 [6:49:03<3:09:38,  1.65it/s]
 67%|██████▋   | 38854/57600 [6:49:03<3:11:40,  1.63it/s]
 67%|██████▋   | 38855/57600 [6:49:04<3:14:02,  1.61it/s]
 67%|██████▋   | 38856/57600 [6:49:05<3:13:06,  1.62it/s]
 67%|██████▋   | 38857/57600 [6:49:05<3:12:19,  1.62it/s]
 67%|██████▋   | 38858/57600 [6:49:06<3:15:45,  1.60it/s]
 67%|██████▋   | 38859/57600 [6:49:07<3:17:28,  1.58it/s]
 67%|██████▋   | 38860/57600 [6:49:07<3:22:18,  1.54it/s]
                                                         
{'loss': 1.1234, 'learning_rate': 3.938327526132404e-07, 'epoch': 428.92}

 67%|██████▋   | 38860/57600 [6:49:07<3:22:18,  1.54it/s]
 67%|██████▋   | 38861/57600 [6:49:08<3:15:47,  1.60it/s]
 67%|██████▋   | 38862/57600 [6:49:09<3:19:06,  1.57it/s]
 67%|██████▋   | 38863/57600 [6:49:09<3:11:49,  1.63it/s]
 67%|██████▋   | 38864/57600 [6:49:10<3:20:37,  1.56it/s]
 67%|██████▋   | 38865/57600 [6:49:10<3:14:46,  1.60it/s]
 67%|██████▋   | 38866/57600 [6:49:11<3:12:06,  1.63it/s]
 67%|██████▋   | 38867/57600 [6:49:12<3:11:01,  1.63it/s]
 67%|██████▋   | 38868/57600 [6:49:12<3:14:42,  1.60it/s]
 67%|██████▋   | 38869/57600 [6:49:13<3:18:06,  1.58it/s]
 67%|██████▋   | 38870/57600 [6:49:14<3:14:35,  1.60it/s]
 67%|██████▋   | 38871/57600 [6:49:14<3:14:26,  1.61it/s]
 67%|██████▋   | 38872/57600 [6:49:15<3:11:16,  1.63it/s]
 67%|██████▋   | 38873/57600 [6:49:15<3:10:26,  1.64it/s]
 67%|██████▋   | 38874/57600 [6:49:16<3:09:57,  1.64it/s]
 67%|██████▋   | 38875/57600 [6:49:17<3:09:49,  1.64it/s]
 67%|██████▋   | 38876/57600 [6:49:17<3:10:45,  1.64it/s]
 67%|██████▋   | 38877/57600 [6:49:18<3:09:33,  1.65it/s]
 67%|██████▋   | 38878/57600 [6:49:18<3:08:27,  1.66it/s]
 67%|██████▋   | 38879/57600 [6:49:19<3:15:18,  1.60it/s]
 68%|██████▊   | 38880/57600 [6:49:20<3:11:16,  1.63it/s]
                                                         
{'loss': 1.1648, 'learning_rate': 3.9351916376306623e-07, 'epoch': 429.14}

 68%|██████▊   | 38880/57600 [6:49:20<3:11:16,  1.63it/s]
 68%|██████▊   | 38881/57600 [6:49:20<3:11:42,  1.63it/s]
 68%|██████▊   | 38882/57600 [6:49:21<3:16:44,  1.59it/s]
 68%|██████▊   | 38883/57600 [6:49:22<3:20:29,  1.56it/s]
 68%|██████▊   | 38884/57600 [6:49:22<3:26:53,  1.51it/s]
 68%|██████▊   | 38885/57600 [6:49:23<3:23:41,  1.53it/s]
 68%|██████▊   | 38886/57600 [6:49:24<3:21:08,  1.55it/s]
 68%|██████▊   | 38887/57600 [6:49:24<3:25:41,  1.52it/s]
 68%|██████▊   | 38888/57600 [6:49:25<3:19:27,  1.56it/s]
 68%|██████▊   | 38889/57600 [6:49:26<3:23:56,  1.53it/s]
 68%|██████▊   | 38890/57600 [6:49:26<3:22:47,  1.54it/s]
 68%|██████▊   | 38891/57600 [6:49:27<3:20:49,  1.55it/s]
 68%|██████▊   | 38892/57600 [6:49:27<3:23:29,  1.53it/s]
 68%|██████▊   | 38893/57600 [6:49:28<3:14:06,  1.61it/s]
 68%|██████▊   | 38894/57600 [6:49:29<3:12:00,  1.62it/s]
 68%|██████▊   | 38895/57600 [6:49:29<3:14:31,  1.60it/s]
 68%|██████▊   | 38896/57600 [6:49:30<3:25:02,  1.52it/s]
 68%|██████▊   | 38897/57600 [6:49:31<3:16:56,  1.58it/s]
 68%|██████▊   | 38898/57600 [6:49:31<3:18:55,  1.57it/s]
 68%|██████▊   | 38899/57600 [6:49:32<3:10:02,  1.64it/s]
 68%|██████▊   | 38900/57600 [6:49:32<3:15:49,  1.59it/s]
                                                         
{'loss': 1.1243, 'learning_rate': 3.93205574912892e-07, 'epoch': 429.36}

 68%|██████▊   | 38900/57600 [6:49:32<3:15:49,  1.59it/s]
 68%|██████▊   | 38901/57600 [6:49:33<3:20:08,  1.56it/s]
 68%|██████▊   | 38902/57600 [6:49:34<3:17:05,  1.58it/s]
 68%|██████▊   | 38903/57600 [6:49:34<3:12:55,  1.62it/s]
 68%|██████▊   | 38904/57600 [6:49:35<3:08:34,  1.65it/s]
 68%|██████▊   | 38905/57600 [6:49:36<3:11:12,  1.63it/s]
 68%|██████▊   | 38906/57600 [6:49:36<3:12:56,  1.61it/s]
 68%|██████▊   | 38907/57600 [6:49:37<3:13:40,  1.61it/s]
 68%|██████▊   | 38908/57600 [6:49:37<3:14:48,  1.60it/s]
 68%|██████▊   | 38909/57600 [6:49:38<3:15:40,  1.59it/s]
 68%|██████▊   | 38910/57600 [6:49:39<3:11:42,  1.62it/s]
 68%|██████▊   | 38911/57600 [6:49:39<3:15:57,  1.59it/s]
 68%|██████▊   | 38912/57600 [6:49:40<3:19:02,  1.56it/s]
 68%|██████▊   | 38913/57600 [6:49:41<3:21:22,  1.55it/s]
 68%|██████▊   | 38914/57600 [6:49:41<3:19:28,  1.56it/s]
 68%|██████▊   | 38915/57600 [6:49:42<3:14:50,  1.60it/s]
 68%|██████▊   | 38916/57600 [6:49:42<3:11:01,  1.63it/s]
 68%|██████▊   | 38917/57600 [6:49:43<3:08:53,  1.65it/s]
 68%|██████▊   | 38918/57600 [6:49:44<3:11:52,  1.62it/s]
 68%|██████▊   | 38919/57600 [6:49:44<3:12:35,  1.62it/s]
 68%|██████▊   | 38920/57600 [6:49:45<3:14:40,  1.60it/s]
                                                         
{'loss': 1.1617, 'learning_rate': 3.928919860627178e-07, 'epoch': 429.58}

 68%|██████▊   | 38920/57600 [6:49:45<3:14:40,  1.60it/s]
 68%|██████▊   | 38921/57600 [6:49:46<3:22:21,  1.54it/s]
 68%|██████▊   | 38922/57600 [6:49:46<3:26:42,  1.51it/s]
 68%|██████▊   | 38923/57600 [6:49:47<3:21:35,  1.54it/s]
 68%|██████▊   | 38924/57600 [6:49:48<3:15:45,  1.59it/s]
 68%|██████▊   | 38925/57600 [6:49:48<3:19:33,  1.56it/s]
 68%|██████▊   | 38926/57600 [6:49:49<3:17:26,  1.58it/s]
 68%|██████▊   | 38927/57600 [6:49:49<3:18:58,  1.56it/s]
 68%|██████▊   | 38928/57600 [6:49:50<3:16:34,  1.58it/s]
 68%|██████▊   | 38929/57600 [6:49:51<3:13:12,  1.61it/s]
 68%|██████▊   | 38930/57600 [6:49:51<3:15:35,  1.59it/s]
 68%|██████▊   | 38931/57600 [6:49:52<3:11:39,  1.62it/s]
 68%|██████▊   | 38932/57600 [6:49:53<3:17:36,  1.57it/s]
 68%|██████▊   | 38933/57600 [6:49:53<3:17:51,  1.57it/s]
 68%|██████▊   | 38934/57600 [6:49:54<3:17:38,  1.57it/s]
 68%|██████▊   | 38935/57600 [6:49:55<3:23:10,  1.53it/s]
 68%|██████▊   | 38936/57600 [6:49:55<3:18:01,  1.57it/s]
 68%|██████▊   | 38937/57600 [6:49:56<3:20:34,  1.55it/s]
 68%|██████▊   | 38938/57600 [6:49:56<3:20:42,  1.55it/s]
 68%|██████▊   | 38939/57600 [6:49:57<3:17:25,  1.58it/s]
 68%|██████▊   | 38940/57600 [6:49:58<3:11:23,  1.62it/s]
                                                         
{'loss': 1.1192, 'learning_rate': 3.9257839721254354e-07, 'epoch': 429.8}

 68%|██████▊   | 38940/57600 [6:49:58<3:11:23,  1.62it/s]
 68%|██████▊   | 38941/57600 [6:49:58<3:08:38,  1.65it/s]
 68%|██████▊   | 38942/57600 [6:49:59<3:17:59,  1.57it/s]
 68%|██████▊   | 38943/57600 [6:50:00<3:17:42,  1.57it/s]
 68%|██████▊   | 38944/57600 [6:50:00<3:18:29,  1.57it/s]
 68%|██████▊   | 38945/57600 [6:50:01<3:14:16,  1.60it/s]
 68%|██████▊   | 38946/57600 [6:50:01<3:14:23,  1.60it/s]
 68%|██████▊   | 38947/57600 [6:50:02<3:16:38,  1.58it/s]
 68%|██████▊   | 38948/57600 [6:50:03<3:17:07,  1.58it/s]
 68%|██████▊   | 38949/57600 [6:50:03<3:20:06,  1.55it/s]
 68%|██████▊   | 38950/57600 [6:50:04<3:18:17,  1.57it/s]
 68%|██████▊   | 38951/57600 [6:50:05<3:15:14,  1.59it/s]
 68%|██████▊   | 38952/57600 [6:50:05<3:12:29,  1.61it/s]
 68%|██████▊   | 38953/57600 [6:50:06<3:17:44,  1.57it/s]
 68%|██████▊   | 38954/57600 [6:50:06<3:16:09,  1.58it/s]
 68%|██████▊   | 38955/57600 [6:50:07<3:13:35,  1.61it/s]
 68%|██████▊   | 38956/57600 [6:50:08<3:12:39,  1.61it/s]
 68%|██████▊   | 38957/57600 [6:50:08<3:10:41,  1.63it/s]
 68%|██████▊   | 38958/57600 [6:50:09<3:09:09,  1.64it/s]
 68%|██████▊   | 38959/57600 [6:50:10<3:22:54,  1.53it/s]
 68%|██████▊   | 38960/57600 [6:50:10<3:15:11,  1.59it/s]
                                                         
{'loss': 1.159, 'learning_rate': 3.9226480836236934e-07, 'epoch': 430.02}

 68%|██████▊   | 38960/57600 [6:50:10<3:15:11,  1.59it/s]
 68%|██████▊   | 38961/57600 [6:50:11<3:13:28,  1.61it/s]
 68%|██████▊   | 38962/57600 [6:50:12<3:18:56,  1.56it/s]
 68%|██████▊   | 38963/57600 [6:50:12<3:14:56,  1.59it/s]
 68%|██████▊   | 38964/57600 [6:50:13<3:10:10,  1.63it/s]
 68%|██████▊   | 38965/57600 [6:50:13<3:11:18,  1.62it/s]
 68%|██████▊   | 38966/57600 [6:50:14<3:10:03,  1.63it/s]
 68%|██████▊   | 38967/57600 [6:50:15<3:11:09,  1.62it/s]
 68%|██████▊   | 38968/57600 [6:50:15<3:15:17,  1.59it/s]
 68%|██████▊   | 38969/57600 [6:50:16<3:18:34,  1.56it/s]
 68%|██████▊   | 38970/57600 [6:50:17<3:19:15,  1.56it/s]
 68%|██████▊   | 38971/57600 [6:50:17<3:15:51,  1.59it/s]
 68%|██████▊   | 38972/57600 [6:50:18<3:15:42,  1.59it/s]
 68%|██████▊   | 38973/57600 [6:50:18<3:14:06,  1.60it/s]
 68%|██████▊   | 38974/57600 [6:50:19<3:14:54,  1.59it/s]
 68%|██████▊   | 38975/57600 [6:50:20<3:15:06,  1.59it/s]
 68%|██████▊   | 38976/57600 [6:50:20<3:11:42,  1.62it/s]
 68%|██████▊   | 38977/57600 [6:50:21<3:15:23,  1.59it/s]
 68%|██████▊   | 38978/57600 [6:50:21<3:10:18,  1.63it/s]
 68%|██████▊   | 38979/57600 [6:50:22<3:12:38,  1.61it/s]
 68%|██████▊   | 38980/57600 [6:50:23<3:16:16,  1.58it/s]
                                                         
{'loss': 1.1673, 'learning_rate': 3.9195121951219504e-07, 'epoch': 430.24}

 68%|██████▊   | 38980/57600 [6:50:23<3:16:16,  1.58it/s]
 68%|██████▊   | 38981/57600 [6:50:23<3:13:11,  1.61it/s]
 68%|██████▊   | 38982/57600 [6:50:24<3:16:27,  1.58it/s]
 68%|██████▊   | 38983/57600 [6:50:25<3:11:59,  1.62it/s]
 68%|██████▊   | 38984/57600 [6:50:25<3:09:28,  1.64it/s]
 68%|██████▊   | 38985/57600 [6:50:26<3:12:29,  1.61it/s]
 68%|██████▊   | 38986/57600 [6:50:26<3:08:47,  1.64it/s]
 68%|██████▊   | 38987/57600 [6:50:27<3:09:32,  1.64it/s]
 68%|██████▊   | 38988/57600 [6:50:28<3:15:40,  1.59it/s]
 68%|██████▊   | 38989/57600 [6:50:28<3:13:50,  1.60it/s]
 68%|██████▊   | 38990/57600 [6:50:29<3:13:41,  1.60it/s]
 68%|██████▊   | 38991/57600 [6:50:30<3:15:15,  1.59it/s]
 68%|██████▊   | 38992/57600 [6:50:30<3:12:11,  1.61it/s]
 68%|██████▊   | 38993/57600 [6:50:31<3:08:12,  1.65it/s]
 68%|██████▊   | 38994/57600 [6:50:31<3:11:23,  1.62it/s]
 68%|██████▊   | 38995/57600 [6:50:32<3:07:18,  1.66it/s]
 68%|██████▊   | 38996/57600 [6:50:33<3:18:22,  1.56it/s]
 68%|██████▊   | 38997/57600 [6:50:33<3:10:35,  1.63it/s]
 68%|██████▊   | 38998/57600 [6:50:34<3:10:43,  1.63it/s]
 68%|██████▊   | 38999/57600 [6:50:35<3:12:38,  1.61it/s]
 68%|██████▊   | 39000/57600 [6:50:35<3:08:58,  1.64it/s]
                                                         
{'loss': 1.1815, 'learning_rate': 3.916376306620209e-07, 'epoch': 430.46}

 68%|██████▊   | 39000/57600 [6:50:35<3:08:58,  1.64it/s]
 68%|██████▊   | 39001/57600 [6:50:36<3:14:10,  1.60it/s]
 68%|██████▊   | 39002/57600 [6:50:36<3:09:41,  1.63it/s]
 68%|██████▊   | 39003/57600 [6:50:37<3:17:13,  1.57it/s]
 68%|██████▊   | 39004/57600 [6:50:38<3:16:03,  1.58it/s]
 68%|██████▊   | 39005/57600 [6:50:38<3:15:59,  1.58it/s]
 68%|██████▊   | 39006/57600 [6:50:39<3:11:56,  1.61it/s]
 68%|██████▊   | 39007/57600 [6:50:39<3:11:38,  1.62it/s]
 68%|██████▊   | 39008/57600 [6:50:40<3:12:07,  1.61it/s]
 68%|██████▊   | 39009/57600 [6:50:41<3:08:42,  1.64it/s]
 68%|██████▊   | 39010/57600 [6:50:41<3:13:46,  1.60it/s]
 68%|██████▊   | 39011/57600 [6:50:42<3:14:12,  1.60it/s]
 68%|██████▊   | 39012/57600 [6:50:43<3:16:41,  1.58it/s]
 68%|██████▊   | 39013/57600 [6:50:43<3:19:47,  1.55it/s]
 68%|██████▊   | 39014/57600 [6:50:44<3:21:13,  1.54it/s]
 68%|██████▊   | 39015/57600 [6:50:45<3:22:07,  1.53it/s]
 68%|██████▊   | 39016/57600 [6:50:45<3:21:08,  1.54it/s]
 68%|██████▊   | 39017/57600 [6:50:46<3:24:28,  1.51it/s]
 68%|██████▊   | 39018/57600 [6:50:47<3:19:57,  1.55it/s]
 68%|██████▊   | 39019/57600 [6:50:47<3:25:09,  1.51it/s]
 68%|██████▊   | 39020/57600 [6:50:48<3:21:51,  1.53it/s]
                                                         
{'loss': 1.1173, 'learning_rate': 3.913240418118467e-07, 'epoch': 430.68}

 68%|██████▊   | 39020/57600 [6:50:48<3:21:51,  1.53it/s]
 68%|██████▊   | 39021/57600 [6:50:49<3:23:52,  1.52it/s]
 68%|██████▊   | 39022/57600 [6:50:49<3:20:39,  1.54it/s]
 68%|██████▊   | 39023/57600 [6:50:50<3:20:31,  1.54it/s]
 68%|██████▊   | 39024/57600 [6:50:50<3:21:06,  1.54it/s]
 68%|██████▊   | 39025/57600 [6:50:51<3:28:49,  1.48it/s]
 68%|██████▊   | 39026/57600 [6:50:52<3:32:57,  1.45it/s]
 68%|██████▊   | 39027/57600 [6:50:53<3:24:20,  1.51it/s]
 68%|██████▊   | 39028/57600 [6:50:53<3:22:02,  1.53it/s]
 68%|██████▊   | 39029/57600 [6:50:54<3:15:59,  1.58it/s]
 68%|██████▊   | 39030/57600 [6:50:54<3:11:27,  1.62it/s]
 68%|██████▊   | 39031/57600 [6:50:55<3:12:48,  1.61it/s]
 68%|██████▊   | 39032/57600 [6:50:56<3:09:04,  1.64it/s]
 68%|██████▊   | 39033/57600 [6:50:56<3:09:16,  1.63it/s]
 68%|██████▊   | 39034/57600 [6:50:57<3:07:59,  1.65it/s]
 68%|██████▊   | 39035/57600 [6:50:57<3:06:00,  1.66it/s]
 68%|██████▊   | 39036/57600 [6:50:58<3:04:50,  1.67it/s]
 68%|██████▊   | 39037/57600 [6:50:59<3:04:22,  1.68it/s]
 68%|██████▊   | 39038/57600 [6:50:59<3:05:03,  1.67it/s]
 68%|██████▊   | 39039/57600 [6:51:00<3:02:18,  1.70it/s]
 68%|██████▊   | 39040/57600 [6:51:00<3:01:14,  1.71it/s]
                                                         
{'loss': 1.1484, 'learning_rate': 3.9101045296167245e-07, 'epoch': 430.91}

 68%|██████▊   | 39040/57600 [6:51:00<3:01:14,  1.71it/s]
 68%|██████▊   | 39041/57600 [6:51:01<3:04:27,  1.68it/s]
 68%|██████▊   | 39042/57600 [6:51:02<3:12:16,  1.61it/s]
 68%|██████▊   | 39043/57600 [6:51:02<3:07:53,  1.65it/s]
 68%|██████▊   | 39044/57600 [6:51:03<3:11:37,  1.61it/s]
 68%|██████▊   | 39045/57600 [6:51:03<3:16:31,  1.57it/s]
 68%|██████▊   | 39046/57600 [6:51:04<3:18:13,  1.56it/s]
 68%|██████▊   | 39047/57600 [6:51:05<3:18:07,  1.56it/s]
 68%|██████▊   | 39048/57600 [6:51:05<3:12:50,  1.60it/s]
 68%|██████▊   | 39049/57600 [6:51:06<3:23:47,  1.52it/s]
 68%|██████▊   | 39050/57600 [6:51:07<3:20:28,  1.54it/s]
 68%|██████▊   | 39051/57600 [6:51:07<3:20:19,  1.54it/s]
 68%|██████▊   | 39052/57600 [6:51:08<3:18:31,  1.56it/s]
 68%|██████▊   | 39053/57600 [6:51:09<3:18:10,  1.56it/s]
 68%|██████▊   | 39054/57600 [6:51:09<3:10:09,  1.63it/s]
 68%|██████▊   | 39055/57600 [6:51:10<3:11:31,  1.61it/s]
 68%|██████▊   | 39056/57600 [6:51:10<3:11:26,  1.61it/s]
 68%|██████▊   | 39057/57600 [6:51:11<3:11:23,  1.61it/s]
 68%|██████▊   | 39058/57600 [6:51:12<3:10:20,  1.62it/s]
 68%|██████▊   | 39059/57600 [6:51:12<3:09:01,  1.63it/s]
 68%|██████▊   | 39060/57600 [6:51:13<3:07:08,  1.65it/s]
                                                         
{'loss': 1.1731, 'learning_rate': 3.9069686411149826e-07, 'epoch': 431.13}

 68%|██████▊   | 39060/57600 [6:51:13<3:07:08,  1.65it/s]
 68%|██████▊   | 39061/57600 [6:51:14<3:13:58,  1.59it/s]
 68%|██████▊   | 39062/57600 [6:51:14<3:16:26,  1.57it/s]
 68%|██████▊   | 39063/57600 [6:51:15<3:20:35,  1.54it/s]
 68%|██████▊   | 39064/57600 [6:51:15<3:14:11,  1.59it/s]
 68%|██████▊   | 39065/57600 [6:51:16<3:12:58,  1.60it/s]
 68%|██████▊   | 39066/57600 [6:51:17<3:12:35,  1.60it/s]
 68%|██████▊   | 39067/57600 [6:51:17<3:09:43,  1.63it/s]
 68%|██████▊   | 39068/57600 [6:51:18<3:07:46,  1.64it/s]
 68%|██████▊   | 39069/57600 [6:51:19<3:13:50,  1.59it/s]
 68%|██████▊   | 39070/57600 [6:51:19<3:18:07,  1.56it/s]
 68%|██████▊   | 39071/57600 [6:51:20<3:12:09,  1.61it/s]
 68%|██████▊   | 39072/57600 [6:51:20<3:15:57,  1.58it/s]
 68%|██████▊   | 39073/57600 [6:51:21<3:23:16,  1.52it/s]
 68%|██████▊   | 39074/57600 [6:51:22<3:21:31,  1.53it/s]
 68%|██████▊   | 39075/57600 [6:51:22<3:21:31,  1.53it/s]
 68%|██████▊   | 39076/57600 [6:51:23<3:17:21,  1.56it/s]
 68%|██████▊   | 39077/57600 [6:51:24<3:20:33,  1.54it/s]
 68%|██████▊   | 39078/57600 [6:51:24<3:19:04,  1.55it/s]
 68%|██████▊   | 39079/57600 [6:51:25<3:18:12,  1.56it/s]
 68%|██████▊   | 39080/57600 [6:51:26<3:16:00,  1.57it/s]
                                                         
{'loss': 1.1409, 'learning_rate': 3.90383275261324e-07, 'epoch': 431.35}

 68%|██████▊   | 39080/57600 [6:51:26<3:16:00,  1.57it/s]
 68%|██████▊   | 39081/57600 [6:51:26<3:18:16,  1.56it/s]
 68%|██████▊   | 39082/57600 [6:51:27<3:13:01,  1.60it/s]
 68%|██████▊   | 39083/57600 [6:51:28<3:12:18,  1.60it/s]
 68%|██████▊   | 39084/57600 [6:51:28<3:11:51,  1.61it/s]
 68%|██████▊   | 39085/57600 [6:51:29<3:15:56,  1.57it/s]
 68%|██████▊   | 39086/57600 [6:51:29<3:11:21,  1.61it/s]
 68%|██████▊   | 39087/57600 [6:51:30<3:05:38,  1.66it/s]
 68%|██████▊   | 39088/57600 [6:51:31<3:06:58,  1.65it/s]
 68%|██████▊   | 39089/57600 [6:51:31<3:17:22,  1.56it/s]
 68%|██████▊   | 39090/57600 [6:51:32<3:20:18,  1.54it/s]
 68%|██████▊   | 39091/57600 [6:51:33<3:16:38,  1.57it/s]
 68%|██████▊   | 39092/57600 [6:51:33<3:14:43,  1.58it/s]
 68%|██████▊   | 39093/57600 [6:51:34<3:13:02,  1.60it/s]
 68%|██████▊   | 39094/57600 [6:51:34<3:11:08,  1.61it/s]
 68%|██████▊   | 39095/57600 [6:51:35<3:13:13,  1.60it/s]
 68%|██████▊   | 39096/57600 [6:51:36<3:12:21,  1.60it/s]
 68%|██████▊   | 39097/57600 [6:51:36<3:18:47,  1.55it/s]
 68%|██████▊   | 39098/57600 [6:51:37<3:13:55,  1.59it/s]
 68%|██████▊   | 39099/57600 [6:51:38<3:13:27,  1.59it/s]
 68%|██████▊   | 39100/57600 [6:51:38<3:17:38,  1.56it/s]
                                                         
{'loss': 1.1594, 'learning_rate': 3.9006968641114976e-07, 'epoch': 431.57}

 68%|██████▊   | 39100/57600 [6:51:38<3:17:38,  1.56it/s]
 68%|██████▊   | 39101/57600 [6:51:39<3:16:23,  1.57it/s]
 68%|██████▊   | 39102/57600 [6:51:39<3:07:17,  1.65it/s]
 68%|██████▊   | 39103/57600 [6:51:40<3:07:54,  1.64it/s]
 68%|██████▊   | 39104/57600 [6:51:41<3:07:01,  1.65it/s]
 68%|██████▊   | 39105/57600 [6:51:41<3:08:44,  1.63it/s]
 68%|██████▊   | 39106/57600 [6:51:42<3:05:45,  1.66it/s]
 68%|██████▊   | 39107/57600 [6:51:42<3:10:07,  1.62it/s]
 68%|██████▊   | 39108/57600 [6:51:43<3:06:21,  1.65it/s]
 68%|██████▊   | 39109/57600 [6:51:44<3:02:56,  1.68it/s]
 68%|██████▊   | 39110/57600 [6:51:44<3:02:42,  1.69it/s]
 68%|██████▊   | 39111/57600 [6:51:45<3:02:21,  1.69it/s]
 68%|██████▊   | 39112/57600 [6:51:45<3:10:16,  1.62it/s]
 68%|██████▊   | 39113/57600 [6:51:46<3:15:40,  1.57it/s]
 68%|██████▊   | 39114/57600 [6:51:47<3:17:57,  1.56it/s]
 68%|██████▊   | 39115/57600 [6:51:47<3:16:31,  1.57it/s]
 68%|██████▊   | 39116/57600 [6:51:48<3:20:05,  1.54it/s]
 68%|██████▊   | 39117/57600 [6:51:49<3:21:12,  1.53it/s]
 68%|██████▊   | 39118/57600 [6:51:49<3:20:07,  1.54it/s]
 68%|██████▊   | 39119/57600 [6:51:50<3:21:21,  1.53it/s]
 68%|██████▊   | 39120/57600 [6:51:51<3:14:59,  1.58it/s]
                                                         
{'loss': 1.1579, 'learning_rate': 3.8975609756097557e-07, 'epoch': 431.79}

 68%|██████▊   | 39120/57600 [6:51:51<3:14:59,  1.58it/s]
 68%|██████▊   | 39121/57600 [6:51:51<3:12:19,  1.60it/s]
 68%|██████▊   | 39122/57600 [6:51:52<3:16:20,  1.57it/s]
 68%|██████▊   | 39123/57600 [6:51:53<3:20:35,  1.54it/s]
 68%|██████▊   | 39124/57600 [6:51:53<3:18:09,  1.55it/s]
 68%|██████▊   | 39125/57600 [6:51:54<3:13:30,  1.59it/s]
 68%|██████▊   | 39126/57600 [6:51:54<3:13:42,  1.59it/s]
 68%|██████▊   | 39127/57600 [6:51:55<3:19:37,  1.54it/s]
 68%|██████▊   | 39128/57600 [6:51:56<3:16:48,  1.56it/s]
 68%|██████▊   | 39129/57600 [6:51:56<3:09:50,  1.62it/s]
 68%|██████▊   | 39130/57600 [6:51:57<3:06:17,  1.65it/s]
 68%|██████▊   | 39131/57600 [6:51:58<3:03:53,  1.67it/s]
 68%|██████▊   | 39132/57600 [6:51:58<3:08:18,  1.63it/s]
 68%|██████▊   | 39133/57600 [6:51:59<3:15:37,  1.57it/s]
 68%|██████▊   | 39134/57600 [6:51:59<3:12:48,  1.60it/s]
 68%|██████▊   | 39135/57600 [6:52:00<3:09:35,  1.62it/s]
 68%|██████▊   | 39136/57600 [6:52:01<3:11:25,  1.61it/s]
 68%|██████▊   | 39137/57600 [6:52:01<3:13:05,  1.59it/s]
 68%|██████▊   | 39138/57600 [6:52:02<3:14:22,  1.58it/s]
 68%|██████▊   | 39139/57600 [6:52:03<3:15:35,  1.57it/s]
 68%|██████▊   | 39140/57600 [6:52:03<3:22:07,  1.52it/s]
                                                         
{'loss': 1.1521, 'learning_rate': 3.8944250871080137e-07, 'epoch': 432.01}

 68%|██████▊   | 39140/57600 [6:52:03<3:22:07,  1.52it/s]
 68%|██████▊   | 39141/57600 [6:52:04<3:13:20,  1.59it/s]
 68%|██████▊   | 39142/57600 [6:52:05<3:21:20,  1.53it/s]
 68%|██████▊   | 39143/57600 [6:52:05<3:19:08,  1.54it/s]
 68%|██████▊   | 39144/57600 [6:52:06<3:17:07,  1.56it/s]
 68%|██████▊   | 39145/57600 [6:52:06<3:14:39,  1.58it/s]
 68%|██████▊   | 39146/57600 [6:52:07<3:13:47,  1.59it/s]
 68%|██████▊   | 39147/57600 [6:52:08<3:15:33,  1.57it/s]
 68%|██████▊   | 39148/57600 [6:52:08<3:20:31,  1.53it/s]
 68%|██████▊   | 39149/57600 [6:52:09<3:24:33,  1.50it/s]
 68%|██████▊   | 39150/57600 [6:52:10<3:20:51,  1.53it/s]
 68%|██████▊   | 39151/57600 [6:52:10<3:19:08,  1.54it/s]
 68%|██████▊   | 39152/57600 [6:52:11<3:21:11,  1.53it/s]
 68%|██████▊   | 39153/57600 [6:52:12<3:13:51,  1.59it/s]
 68%|██████▊   | 39154/57600 [6:52:12<3:11:15,  1.61it/s]
 68%|██████▊   | 39155/57600 [6:52:13<3:07:43,  1.64it/s]
 68%|██████▊   | 39156/57600 [6:52:14<3:16:43,  1.56it/s]
 68%|██████▊   | 39157/57600 [6:52:14<3:12:15,  1.60it/s]
 68%|██████▊   | 39158/57600 [6:52:15<3:08:33,  1.63it/s]
 68%|██████▊   | 39159/57600 [6:52:15<3:08:44,  1.63it/s]
 68%|██████▊   | 39160/57600 [6:52:16<3:16:23,  1.56it/s]
                                                         
{'loss': 1.1229, 'learning_rate': 3.891289198606272e-07, 'epoch': 432.23}

 68%|██████▊   | 39160/57600 [6:52:16<3:16:23,  1.56it/s]
 68%|██████▊   | 39161/57600 [6:52:17<3:12:31,  1.60it/s]
 68%|██████▊   | 39162/57600 [6:52:17<3:06:51,  1.64it/s]
 68%|██████▊   | 39163/57600 [6:52:18<3:05:08,  1.66it/s]
 68%|██████▊   | 39164/57600 [6:52:18<3:05:09,  1.66it/s]
 68%|██████▊   | 39165/57600 [6:52:19<3:03:12,  1.68it/s]
 68%|██████▊   | 39166/57600 [6:52:20<3:05:39,  1.65it/s]
 68%|██████▊   | 39167/57600 [6:52:20<3:05:00,  1.66it/s]
 68%|██████▊   | 39168/57600 [6:52:21<3:00:28,  1.70it/s]
 68%|██████▊   | 39169/57600 [6:52:21<3:05:57,  1.65it/s]
 68%|██████▊   | 39170/57600 [6:52:22<3:03:27,  1.67it/s]
 68%|██████▊   | 39171/57600 [6:52:23<3:13:37,  1.59it/s]
 68%|██████▊   | 39172/57600 [6:52:23<3:09:19,  1.62it/s]
 68%|██████▊   | 39173/57600 [6:52:24<3:06:30,  1.65it/s]
 68%|██████▊   | 39174/57600 [6:52:24<3:09:39,  1.62it/s]
 68%|██████▊   | 39175/57600 [6:52:25<3:11:38,  1.60it/s]
 68%|██████▊   | 39176/57600 [6:52:26<3:08:10,  1.63it/s]
 68%|██████▊   | 39177/57600 [6:52:26<3:07:00,  1.64it/s]
 68%|██████▊   | 39178/57600 [6:52:27<3:12:08,  1.60it/s]
 68%|██████▊   | 39179/57600 [6:52:28<3:12:06,  1.60it/s]
 68%|██████▊   | 39180/57600 [6:52:28<3:17:09,  1.56it/s]
                                                         
{'loss': 1.1652, 'learning_rate': 3.8881533101045293e-07, 'epoch': 432.45}

 68%|██████▊   | 39180/57600 [6:52:28<3:17:09,  1.56it/s]
 68%|██████▊   | 39181/57600 [6:52:29<3:21:48,  1.52it/s]
 68%|██████▊   | 39182/57600 [6:52:30<3:19:11,  1.54it/s]
 68%|██████▊   | 39183/57600 [6:52:30<3:16:27,  1.56it/s]
 68%|██████▊   | 39184/57600 [6:52:31<3:11:35,  1.60it/s]
 68%|██████▊   | 39185/57600 [6:52:31<3:11:29,  1.60it/s]
 68%|██████▊   | 39186/57600 [6:52:32<3:04:55,  1.66it/s]
 68%|██████▊   | 39187/57600 [6:52:33<3:03:46,  1.67it/s]
 68%|██████▊   | 39188/57600 [6:52:33<3:01:07,  1.69it/s]
 68%|██████▊   | 39189/57600 [6:52:34<3:05:03,  1.66it/s]
 68%|██████▊   | 39190/57600 [6:52:34<3:03:57,  1.67it/s]
 68%|██████▊   | 39191/57600 [6:52:35<3:12:51,  1.59it/s]
 68%|██████▊   | 39192/57600 [6:52:36<3:10:42,  1.61it/s]
 68%|██████▊   | 39193/57600 [6:52:36<3:13:55,  1.58it/s]
 68%|██████▊   | 39194/57600 [6:52:37<3:13:10,  1.59it/s]
 68%|██████▊   | 39195/57600 [6:52:38<3:10:18,  1.61it/s]
 68%|██████▊   | 39196/57600 [6:52:38<3:05:11,  1.66it/s]
 68%|██████▊   | 39197/57600 [6:52:39<3:05:30,  1.65it/s]
 68%|██████▊   | 39198/57600 [6:52:39<3:03:26,  1.67it/s]
 68%|██████▊   | 39199/57600 [6:52:40<3:15:10,  1.57it/s]
 68%|██████▊   | 39200/57600 [6:52:41<3:13:03,  1.59it/s]
                                                         
{'loss': 1.1542, 'learning_rate': 3.8850174216027873e-07, 'epoch': 432.67}

 68%|██████▊   | 39200/57600 [6:52:41<3:13:03,  1.59it/s]
 68%|██████▊   | 39201/57600 [6:52:41<3:13:49,  1.58it/s]
 68%|██████▊   | 39202/57600 [6:52:42<3:14:13,  1.58it/s]
 68%|██████▊   | 39203/57600 [6:52:43<3:13:17,  1.59it/s]
 68%|██████▊   | 39204/57600 [6:52:43<3:12:31,  1.59it/s]
 68%|██████▊   | 39205/57600 [6:52:44<3:12:24,  1.59it/s]
 68%|██████▊   | 39206/57600 [6:52:44<3:21:41,  1.52it/s]
 68%|██████▊   | 39207/57600 [6:52:45<3:25:01,  1.50it/s]
 68%|██████▊   | 39208/57600 [6:52:46<3:24:01,  1.50it/s]
 68%|██████▊   | 39209/57600 [6:52:46<3:20:27,  1.53it/s]
 68%|██████▊   | 39210/57600 [6:52:47<3:17:31,  1.55it/s]
 68%|██████▊   | 39211/57600 [6:52:48<3:13:18,  1.59it/s]
 68%|██████▊   | 39212/57600 [6:52:48<3:19:16,  1.54it/s]
 68%|██████▊   | 39213/57600 [6:52:49<3:18:04,  1.55it/s]
 68%|██████▊   | 39214/57600 [6:52:50<3:19:13,  1.54it/s]
 68%|██████▊   | 39215/57600 [6:52:50<3:14:33,  1.57it/s]
 68%|██████▊   | 39216/57600 [6:52:51<3:15:33,  1.57it/s]
 68%|██████▊   | 39217/57600 [6:52:52<3:15:24,  1.57it/s]
 68%|██████▊   | 39218/57600 [6:52:52<3:24:17,  1.50it/s]
 68%|██████▊   | 39219/57600 [6:52:53<3:26:12,  1.49it/s]
 68%|██████▊   | 39220/57600 [6:52:54<3:25:53,  1.49it/s]
                                                         
{'loss': 1.088, 'learning_rate': 3.8818815331010443e-07, 'epoch': 432.89}

 68%|██████▊   | 39220/57600 [6:52:54<3:25:53,  1.49it/s]
 68%|██████▊   | 39221/57600 [6:52:54<3:31:13,  1.45it/s]
 68%|██████▊   | 39222/57600 [6:52:55<3:24:28,  1.50it/s]
 68%|██████▊   | 39223/57600 [6:52:56<3:15:34,  1.57it/s]
 68%|██████▊   | 39224/57600 [6:52:56<3:12:11,  1.59it/s]
 68%|██████▊   | 39225/57600 [6:52:57<3:06:19,  1.64it/s]
 68%|██████▊   | 39226/57600 [6:52:57<3:04:55,  1.66it/s]
 68%|██████▊   | 39227/57600 [6:52:58<3:04:07,  1.66it/s]
 68%|██████▊   | 39228/57600 [6:52:59<3:03:09,  1.67it/s]
 68%|██████▊   | 39229/57600 [6:52:59<3:05:59,  1.65it/s]
 68%|██████▊   | 39230/57600 [6:53:00<3:16:29,  1.56it/s]
 68%|██████▊   | 39231/57600 [6:53:01<3:19:11,  1.54it/s]
 68%|██████▊   | 39232/57600 [6:53:01<3:17:39,  1.55it/s]
 68%|██████▊   | 39233/57600 [6:53:02<3:17:17,  1.55it/s]
 68%|██████▊   | 39234/57600 [6:53:02<3:14:35,  1.57it/s]
 68%|██████▊   | 39235/57600 [6:53:03<3:15:06,  1.57it/s]
 68%|██████▊   | 39236/57600 [6:53:04<3:14:56,  1.57it/s]
 68%|██████▊   | 39237/57600 [6:53:04<3:16:14,  1.56it/s]
 68%|██████▊   | 39238/57600 [6:53:05<3:13:02,  1.59it/s]
 68%|██████▊   | 39239/57600 [6:53:06<3:11:15,  1.60it/s]
 68%|██████▊   | 39240/57600 [6:53:06<3:12:57,  1.59it/s]
                                                         
{'loss': 1.1239, 'learning_rate': 3.878745644599303e-07, 'epoch': 433.11}

 68%|██████▊   | 39240/57600 [6:53:06<3:12:57,  1.59it/s]
 68%|██████▊   | 39241/57600 [6:53:07<3:08:23,  1.62it/s]
 68%|██████▊   | 39242/57600 [6:53:08<3:16:49,  1.55it/s]
 68%|██████▊   | 39243/57600 [6:53:08<3:16:28,  1.56it/s]
 68%|██████▊   | 39244/57600 [6:53:09<3:12:29,  1.59it/s]
 68%|██████▊   | 39245/57600 [6:53:09<3:12:25,  1.59it/s]
 68%|██████▊   | 39246/57600 [6:53:10<3:12:49,  1.59it/s]
 68%|██████▊   | 39247/57600 [6:53:11<3:07:06,  1.63it/s]
 68%|██████▊   | 39248/57600 [6:53:11<3:08:31,  1.62it/s]
 68%|██████▊   | 39249/57600 [6:53:12<3:08:19,  1.62it/s]
 68%|██████▊   | 39250/57600 [6:53:12<3:07:21,  1.63it/s]
 68%|██████▊   | 39251/57600 [6:53:13<3:07:00,  1.64it/s]
 68%|██████▊   | 39252/57600 [6:53:14<3:17:53,  1.55it/s]
 68%|██████▊   | 39253/57600 [6:53:14<3:20:56,  1.52it/s]
 68%|██████▊   | 39254/57600 [6:53:15<3:22:53,  1.51it/s]
 68%|██████▊   | 39255/57600 [6:53:16<3:16:12,  1.56it/s]
 68%|██████▊   | 39256/57600 [6:53:16<3:14:29,  1.57it/s]
 68%|██████▊   | 39257/57600 [6:53:17<3:17:39,  1.55it/s]
 68%|██████▊   | 39258/57600 [6:53:18<3:25:15,  1.49it/s]
 68%|██████▊   | 39259/57600 [6:53:18<3:30:12,  1.45it/s]
 68%|██████▊   | 39260/57600 [6:53:19<3:26:17,  1.48it/s]
                                                         
{'loss': 1.1119, 'learning_rate': 3.8756097560975604e-07, 'epoch': 433.33}

 68%|██████▊   | 39260/57600 [6:53:19<3:26:17,  1.48it/s]
 68%|██████▊   | 39261/57600 [6:53:20<3:19:28,  1.53it/s]
 68%|██████▊   | 39262/57600 [6:53:20<3:09:08,  1.62it/s]
 68%|██████▊   | 39263/57600 [6:53:21<3:14:29,  1.57it/s]
 68%|██████▊   | 39264/57600 [6:53:22<3:14:57,  1.57it/s]
 68%|██████▊   | 39265/57600 [6:53:22<3:13:40,  1.58it/s]
 68%|██████▊   | 39266/57600 [6:53:23<3:15:10,  1.57it/s]
 68%|██████▊   | 39267/57600 [6:53:23<3:12:25,  1.59it/s]
 68%|██████▊   | 39268/57600 [6:53:24<3:20:49,  1.52it/s]
 68%|██████▊   | 39269/57600 [6:53:25<3:15:41,  1.56it/s]
 68%|██████▊   | 39270/57600 [6:53:25<3:13:03,  1.58it/s]
 68%|██████▊   | 39271/57600 [6:53:26<3:12:49,  1.58it/s]
 68%|██████▊   | 39272/57600 [6:53:27<3:16:49,  1.55it/s]
 68%|██████▊   | 39273/57600 [6:53:27<3:13:06,  1.58it/s]
 68%|██████▊   | 39274/57600 [6:53:28<3:10:39,  1.60it/s]
 68%|██████▊   | 39275/57600 [6:53:29<3:09:49,  1.61it/s]
 68%|██████▊   | 39276/57600 [6:53:29<3:06:09,  1.64it/s]
 68%|██████▊   | 39277/57600 [6:53:30<3:08:08,  1.62it/s]
 68%|██████▊   | 39278/57600 [6:53:30<3:06:09,  1.64it/s]
 68%|██████▊   | 39279/57600 [6:53:31<3:15:58,  1.56it/s]
 68%|██████▊   | 39280/57600 [6:53:32<3:13:46,  1.58it/s]
                                                         
{'loss': 1.1393, 'learning_rate': 3.8724738675958185e-07, 'epoch': 433.55}

 68%|██████▊   | 39280/57600 [6:53:32<3:13:46,  1.58it/s]
 68%|██████▊   | 39281/57600 [6:53:32<3:14:42,  1.57it/s]
 68%|██████▊   | 39282/57600 [6:53:33<3:11:32,  1.59it/s]
 68%|██████▊   | 39283/57600 [6:53:33<3:07:05,  1.63it/s]
 68%|██████▊   | 39284/57600 [6:53:34<3:05:55,  1.64it/s]
 68%|██████▊   | 39285/57600 [6:53:35<3:08:45,  1.62it/s]
 68%|██████▊   | 39286/57600 [6:53:35<3:11:01,  1.60it/s]
 68%|██████▊   | 39287/57600 [6:53:36<3:14:05,  1.57it/s]
 68%|██████▊   | 39288/57600 [6:53:37<3:14:45,  1.57it/s]
 68%|██████▊   | 39289/57600 [6:53:37<3:13:20,  1.58it/s]
 68%|██████▊   | 39290/57600 [6:53:38<3:09:29,  1.61it/s]
 68%|██████▊   | 39291/57600 [6:53:39<3:08:53,  1.62it/s]
 68%|██████▊   | 39292/57600 [6:53:39<3:10:33,  1.60it/s]
 68%|██████▊   | 39293/57600 [6:53:40<3:07:16,  1.63it/s]
 68%|██████▊   | 39294/57600 [6:53:40<3:03:27,  1.66it/s]
 68%|██████▊   | 39295/57600 [6:53:41<3:01:50,  1.68it/s]
 68%|██████▊   | 39296/57600 [6:53:41<3:02:57,  1.67it/s]
 68%|██████▊   | 39297/57600 [6:53:42<3:02:06,  1.68it/s]
 68%|██████▊   | 39298/57600 [6:53:43<3:06:46,  1.63it/s]
 68%|██████▊   | 39299/57600 [6:53:43<3:04:23,  1.65it/s]
 68%|██████▊   | 39300/57600 [6:53:44<3:00:38,  1.69it/s]
                                                         
{'loss': 1.1361, 'learning_rate': 3.869337979094077e-07, 'epoch': 433.77}

 68%|██████▊   | 39300/57600 [6:53:44<3:00:38,  1.69it/s]
 68%|██████▊   | 39301/57600 [6:53:44<3:01:36,  1.68it/s]
 68%|██████▊   | 39302/57600 [6:53:45<2:59:53,  1.70it/s]
 68%|██████▊   | 39303/57600 [6:53:46<2:57:46,  1.72it/s]
 68%|██████▊   | 39304/57600 [6:53:46<2:59:57,  1.69it/s]
 68%|██████▊   | 39305/57600 [6:53:47<3:01:37,  1.68it/s]
 68%|██████▊   | 39306/57600 [6:53:47<3:06:46,  1.63it/s]
 68%|██████▊   | 39307/57600 [6:53:48<3:12:06,  1.59it/s]
 68%|██████▊   | 39308/57600 [6:53:49<3:12:33,  1.58it/s]
 68%|██████▊   | 39309/57600 [6:53:49<3:13:24,  1.58it/s]
 68%|██████▊   | 39310/57600 [6:53:50<3:10:59,  1.60it/s]
 68%|██████▊   | 39311/57600 [6:53:51<3:09:26,  1.61it/s]
 68%|██████▊   | 39312/57600 [6:53:51<3:16:02,  1.55it/s]
 68%|██████▊   | 39313/57600 [6:53:52<3:17:20,  1.54it/s]
 68%|██████▊   | 39314/57600 [6:53:53<3:18:20,  1.54it/s]
 68%|██████▊   | 39315/57600 [6:53:53<3:16:07,  1.55it/s]
 68%|██████▊   | 39316/57600 [6:53:54<3:09:53,  1.60it/s]
 68%|██████▊   | 39317/57600 [6:53:54<3:04:44,  1.65it/s]
 68%|██████▊   | 39318/57600 [6:53:55<3:09:28,  1.61it/s]
 68%|██████▊   | 39319/57600 [6:53:56<3:19:19,  1.53it/s]
 68%|██████▊   | 39320/57600 [6:53:56<3:13:34,  1.57it/s]
                                                         
{'loss': 1.1372, 'learning_rate': 3.866202090592334e-07, 'epoch': 434.0}

 68%|██████▊   | 39320/57600 [6:53:56<3:13:34,  1.57it/s]
 68%|██████▊   | 39321/57600 [6:53:57<3:20:51,  1.52it/s]
 68%|██████▊   | 39322/57600 [6:53:58<3:13:42,  1.57it/s]
 68%|██████▊   | 39323/57600 [6:53:58<3:12:51,  1.58it/s]
 68%|██████▊   | 39324/57600 [6:53:59<3:09:11,  1.61it/s]
 68%|██████▊   | 39325/57600 [6:54:00<3:11:29,  1.59it/s]
 68%|██████▊   | 39326/57600 [6:54:00<3:09:27,  1.61it/s]
 68%|██████▊   | 39327/57600 [6:54:01<3:09:53,  1.60it/s]
 68%|██████▊   | 39328/57600 [6:54:01<3:06:09,  1.64it/s]
 68%|██████▊   | 39329/57600 [6:54:02<3:13:37,  1.57it/s]
 68%|██████▊   | 39330/57600 [6:54:03<3:12:35,  1.58it/s]
 68%|██████▊   | 39331/57600 [6:54:03<3:14:20,  1.57it/s]
 68%|██████▊   | 39332/57600 [6:54:04<3:11:42,  1.59it/s]
 68%|██████▊   | 39333/57600 [6:54:05<3:08:43,  1.61it/s]
 68%|██████▊   | 39334/57600 [6:54:05<3:05:04,  1.64it/s]
 68%|██████▊   | 39335/57600 [6:54:06<3:03:02,  1.66it/s]
 68%|██████▊   | 39336/57600 [6:54:06<3:04:21,  1.65it/s]
 68%|██████▊   | 39337/57600 [6:54:07<3:10:57,  1.59it/s]
 68%|██████▊   | 39338/57600 [6:54:08<3:07:02,  1.63it/s]
 68%|██████▊   | 39339/57600 [6:54:08<3:06:45,  1.63it/s]
 68%|██████▊   | 39340/57600 [6:54:09<3:07:34,  1.62it/s]
                                                         
{'loss': 1.1554, 'learning_rate': 3.8630662020905926e-07, 'epoch': 434.22}

 68%|██████▊   | 39340/57600 [6:54:09<3:07:34,  1.62it/s]
 68%|██████▊   | 39341/57600 [6:54:10<3:16:48,  1.55it/s]
 68%|██████▊   | 39342/57600 [6:54:10<3:12:51,  1.58it/s]
 68%|██████▊   | 39343/57600 [6:54:11<3:11:15,  1.59it/s]
 68%|██████▊   | 39344/57600 [6:54:11<3:12:41,  1.58it/s]
 68%|██████▊   | 39345/57600 [6:54:12<3:09:15,  1.61it/s]
 68%|██████▊   | 39346/57600 [6:54:13<3:04:34,  1.65it/s]
 68%|██████▊   | 39347/57600 [6:54:13<3:08:23,  1.61it/s]
 68%|██████▊   | 39348/57600 [6:54:14<3:14:46,  1.56it/s]
 68%|██████▊   | 39349/57600 [6:54:15<3:12:53,  1.58it/s]
 68%|██████▊   | 39350/57600 [6:54:15<3:10:52,  1.59it/s]
 68%|██████▊   | 39351/57600 [6:54:16<3:17:41,  1.54it/s]
 68%|██████▊   | 39352/57600 [6:54:16<3:15:20,  1.56it/s]
 68%|██████▊   | 39353/57600 [6:54:17<3:11:38,  1.59it/s]
 68%|██████▊   | 39354/57600 [6:54:18<3:12:48,  1.58it/s]
 68%|██████▊   | 39355/57600 [6:54:18<3:11:57,  1.58it/s]
 68%|██████▊   | 39356/57600 [6:54:19<3:10:01,  1.60it/s]
 68%|██████▊   | 39357/57600 [6:54:20<3:10:34,  1.60it/s]
 68%|██████▊   | 39358/57600 [6:54:20<3:07:52,  1.62it/s]
 68%|██████▊   | 39359/57600 [6:54:21<3:07:18,  1.62it/s]
 68%|██████▊   | 39360/57600 [6:54:21<3:11:12,  1.59it/s]
                                                         
{'loss': 1.1433, 'learning_rate': 3.8599303135888496e-07, 'epoch': 434.44}

 68%|██████▊   | 39360/57600 [6:54:21<3:11:12,  1.59it/s]
 68%|██████▊   | 39361/57600 [6:54:22<3:17:23,  1.54it/s]
 68%|██████▊   | 39362/57600 [6:54:23<3:18:59,  1.53it/s]
 68%|██████▊   | 39363/57600 [6:54:23<3:15:45,  1.55it/s]
 68%|██████▊   | 39364/57600 [6:54:24<3:20:43,  1.51it/s]
 68%|██████▊   | 39365/57600 [6:54:25<3:26:27,  1.47it/s]
 68%|██████▊   | 39366/57600 [6:54:26<3:22:00,  1.50it/s]
 68%|██████▊   | 39367/57600 [6:54:26<3:23:05,  1.50it/s]
 68%|██████▊   | 39368/57600 [6:54:27<3:20:19,  1.52it/s]
 68%|██████▊   | 39369/57600 [6:54:27<3:17:10,  1.54it/s]
 68%|██████▊   | 39370/57600 [6:54:28<3:16:10,  1.55it/s]
 68%|██████▊   | 39371/57600 [6:54:29<3:14:01,  1.57it/s]
 68%|██████▊   | 39372/57600 [6:54:29<3:18:59,  1.53it/s]
 68%|██████▊   | 39373/57600 [6:54:30<3:15:45,  1.55it/s]
 68%|██████▊   | 39374/57600 [6:54:31<3:09:39,  1.60it/s]
 68%|██████▊   | 39375/57600 [6:54:31<3:04:40,  1.64it/s]
 68%|██████▊   | 39376/57600 [6:54:32<3:04:33,  1.65it/s]
 68%|██████▊   | 39377/57600 [6:54:32<3:08:28,  1.61it/s]
 68%|██████▊   | 39378/57600 [6:54:33<3:12:00,  1.58it/s]
 68%|██████▊   | 39379/57600 [6:54:34<3:12:44,  1.58it/s]
 68%|██████▊   | 39380/57600 [6:54:34<3:05:21,  1.64it/s]
                                                         
{'loss': 1.1224, 'learning_rate': 3.856794425087108e-07, 'epoch': 434.66}

 68%|██████▊   | 39380/57600 [6:54:34<3:05:21,  1.64it/s]
 68%|██████▊   | 39381/57600 [6:54:35<3:01:35,  1.67it/s]
 68%|██████▊   | 39382/57600 [6:54:35<3:00:25,  1.68it/s]
 68%|██████▊   | 39383/57600 [6:54:36<3:13:58,  1.57it/s]
 68%|██████▊   | 39384/57600 [6:54:37<3:17:21,  1.54it/s]
 68%|██████▊   | 39385/57600 [6:54:38<3:21:23,  1.51it/s]
 68%|██████▊   | 39386/57600 [6:54:38<3:12:50,  1.57it/s]
 68%|██████▊   | 39387/57600 [6:54:39<3:16:08,  1.55it/s]
 68%|██████▊   | 39388/57600 [6:54:39<3:17:29,  1.54it/s]
 68%|██████▊   | 39389/57600 [6:54:40<3:12:46,  1.57it/s]
 68%|██████▊   | 39390/57600 [6:54:41<3:13:28,  1.57it/s]
 68%|██████▊   | 39391/57600 [6:54:41<3:09:31,  1.60it/s]
 68%|██████▊   | 39392/57600 [6:54:42<3:09:01,  1.61it/s]
 68%|██████▊   | 39393/57600 [6:54:42<3:05:19,  1.64it/s]
 68%|██████▊   | 39394/57600 [6:54:43<3:09:32,  1.60it/s]
 68%|██████▊   | 39395/57600 [6:54:44<3:08:19,  1.61it/s]
 68%|██████▊   | 39396/57600 [6:54:44<3:09:34,  1.60it/s]
 68%|██████▊   | 39397/57600 [6:54:45<3:06:54,  1.62it/s]
 68%|██████▊   | 39398/57600 [6:54:46<3:10:28,  1.59it/s]
 68%|██████▊   | 39399/57600 [6:54:46<3:12:58,  1.57it/s]
 68%|██████▊   | 39400/57600 [6:54:47<3:18:15,  1.53it/s]
                                                         
{'loss': 1.1458, 'learning_rate': 3.853658536585365e-07, 'epoch': 434.88}

 68%|██████▊   | 39400/57600 [6:54:47<3:18:15,  1.53it/s]
 68%|██████▊   | 39401/57600 [6:54:48<3:12:46,  1.57it/s]
 68%|██████▊   | 39402/57600 [6:54:48<3:05:01,  1.64it/s]
 68%|██████▊   | 39403/57600 [6:54:49<3:04:04,  1.65it/s]
 68%|██████▊   | 39404/57600 [6:54:49<3:06:04,  1.63it/s]
 68%|██████▊   | 39405/57600 [6:54:50<3:09:24,  1.60it/s]
 68%|██████▊   | 39406/57600 [6:54:51<3:07:17,  1.62it/s]
 68%|██████▊   | 39407/57600 [6:54:51<3:09:32,  1.60it/s]
 68%|██████▊   | 39408/57600 [6:54:52<3:08:39,  1.61it/s]
 68%|██████▊   | 39409/57600 [6:54:53<3:14:43,  1.56it/s]
 68%|██████▊   | 39410/57600 [6:54:53<3:11:37,  1.58it/s]
 68%|██████▊   | 39411/57600 [6:54:54<3:09:23,  1.60it/s]
 68%|██████▊   | 39412/57600 [6:54:55<3:25:07,  1.48it/s]
 68%|██████▊   | 39413/57600 [6:54:55<3:21:24,  1.51it/s]
 68%|██████▊   | 39414/57600 [6:54:56<3:18:43,  1.53it/s]
 68%|██████▊   | 39415/57600 [6:54:56<3:16:23,  1.54it/s]
 68%|██████▊   | 39416/57600 [6:54:57<3:18:05,  1.53it/s]
 68%|██████▊   | 39417/57600 [6:54:58<3:22:13,  1.50it/s]
 68%|██████▊   | 39418/57600 [6:54:59<3:25:34,  1.47it/s]
 68%|██████▊   | 39419/57600 [6:54:59<3:22:55,  1.49it/s]
 68%|██████▊   | 39420/57600 [6:55:00<3:26:12,  1.47it/s]
                                                         
{'loss': 1.0863, 'learning_rate': 3.850522648083623e-07, 'epoch': 435.1}

 68%|██████▊   | 39420/57600 [6:55:00<3:26:12,  1.47it/s]
 68%|██████▊   | 39421/57600 [6:55:01<3:25:01,  1.48it/s]
 68%|██████▊   | 39422/57600 [6:55:01<3:17:58,  1.53it/s]
 68%|██████▊   | 39423/57600 [6:55:02<3:15:21,  1.55it/s]
 68%|██████▊   | 39424/57600 [6:55:02<3:13:23,  1.57it/s]
 68%|██████▊   | 39425/57600 [6:55:03<3:10:15,  1.59it/s]
 68%|██████▊   | 39426/57600 [6:55:04<3:16:49,  1.54it/s]
 68%|██████▊   | 39427/57600 [6:55:04<3:09:05,  1.60it/s]
 68%|██████▊   | 39428/57600 [6:55:05<3:05:43,  1.63it/s]
 68%|██████▊   | 39429/57600 [6:55:06<3:09:21,  1.60it/s]
 68%|██████▊   | 39430/57600 [6:55:06<3:17:48,  1.53it/s]
 68%|██████▊   | 39431/57600 [6:55:07<3:11:25,  1.58it/s]
 68%|██████▊   | 39432/57600 [6:55:07<3:08:47,  1.60it/s]
 68%|██████▊   | 39433/57600 [6:55:08<3:06:37,  1.62it/s]
 68%|██████▊   | 39434/57600 [6:55:09<3:10:26,  1.59it/s]
 68%|██████▊   | 39435/57600 [6:55:09<3:07:43,  1.61it/s]
 68%|██████▊   | 39436/57600 [6:55:10<3:05:56,  1.63it/s]
 68%|██████▊   | 39437/57600 [6:55:11<3:07:07,  1.62it/s]
 68%|██████▊   | 39438/57600 [6:55:11<3:05:31,  1.63it/s]
 68%|██████▊   | 39439/57600 [6:55:12<3:12:32,  1.57it/s]
 68%|██████▊   | 39440/57600 [6:55:12<3:15:41,  1.55it/s]
                                                         
{'loss': 1.1512, 'learning_rate': 3.847386759581882e-07, 'epoch': 435.32}

 68%|██████▊   | 39440/57600 [6:55:12<3:15:41,  1.55it/s]
 68%|██████▊   | 39441/57600 [6:55:13<3:15:18,  1.55it/s]
 68%|██████▊   | 39442/57600 [6:55:14<3:11:11,  1.58it/s]
 68%|██████▊   | 39443/57600 [6:55:14<3:11:27,  1.58it/s]
 68%|██████▊   | 39444/57600 [6:55:15<3:08:19,  1.61it/s]
 68%|██████▊   | 39445/57600 [6:55:16<3:01:59,  1.66it/s]
 68%|██████▊   | 39446/57600 [6:55:16<3:02:19,  1.66it/s]
 68%|██████▊   | 39447/57600 [6:55:17<2:59:41,  1.68it/s]
 68%|██████▊   | 39448/57600 [6:55:17<2:58:13,  1.70it/s]
 68%|██████▊   | 39449/57600 [6:55:18<2:59:45,  1.68it/s]
 68%|██████▊   | 39450/57600 [6:55:19<3:04:38,  1.64it/s]
 68%|██████▊   | 39451/57600 [6:55:19<3:03:26,  1.65it/s]
 68%|██████▊   | 39452/57600 [6:55:20<3:03:02,  1.65it/s]
 68%|██████▊   | 39453/57600 [6:55:20<3:02:35,  1.66it/s]
 68%|██████▊   | 39454/57600 [6:55:21<3:05:21,  1.63it/s]
 68%|██████▊   | 39455/57600 [6:55:22<3:02:07,  1.66it/s]
 68%|██████▊   | 39456/57600 [6:55:22<3:06:46,  1.62it/s]
 69%|██████▊   | 39457/57600 [6:55:23<3:04:52,  1.64it/s]
 69%|██████▊   | 39458/57600 [6:55:23<3:09:02,  1.60it/s]
 69%|██████▊   | 39459/57600 [6:55:24<3:04:43,  1.64it/s]
 69%|██████▊   | 39460/57600 [6:55:25<3:07:44,  1.61it/s]
                                                         
{'loss': 1.147, 'learning_rate': 3.844250871080139e-07, 'epoch': 435.54}

 69%|██████▊   | 39460/57600 [6:55:25<3:07:44,  1.61it/s]
 69%|██████▊   | 39461/57600 [6:55:25<3:07:13,  1.61it/s]
 69%|██████▊   | 39462/57600 [6:55:26<3:07:52,  1.61it/s]
 69%|██████▊   | 39463/57600 [6:55:27<3:07:42,  1.61it/s]
 69%|██████▊   | 39464/57600 [6:55:27<3:17:45,  1.53it/s]
 69%|██████▊   | 39465/57600 [6:55:28<3:16:14,  1.54it/s]
 69%|██████▊   | 39466/57600 [6:55:29<3:17:08,  1.53it/s]
 69%|██████▊   | 39467/57600 [6:55:29<3:11:49,  1.58it/s]
 69%|██████▊   | 39468/57600 [6:55:30<3:16:22,  1.54it/s]
 69%|██████▊   | 39469/57600 [6:55:30<3:16:12,  1.54it/s]
 69%|██████▊   | 39470/57600 [6:55:31<3:24:30,  1.48it/s]
 69%|██████▊   | 39471/57600 [6:55:32<3:19:35,  1.51it/s]
 69%|██████▊   | 39472/57600 [6:55:32<3:15:24,  1.55it/s]
 69%|██████▊   | 39473/57600 [6:55:33<3:10:14,  1.59it/s]
 69%|██████▊   | 39474/57600 [6:55:34<3:13:39,  1.56it/s]
 69%|██████▊   | 39475/57600 [6:55:34<3:08:18,  1.60it/s]
 69%|██████▊   | 39476/57600 [6:55:35<3:08:24,  1.60it/s]
 69%|██████▊   | 39477/57600 [6:55:36<3:07:41,  1.61it/s]
 69%|██████▊   | 39478/57600 [6:55:36<3:08:50,  1.60it/s]
 69%|██████▊   | 39479/57600 [6:55:37<3:06:04,  1.62it/s]
 69%|██████▊   | 39480/57600 [6:55:37<3:04:07,  1.64it/s]
                                                         
{'loss': 1.1392, 'learning_rate': 3.8411149825783974e-07, 'epoch': 435.76}

 69%|██████▊   | 39480/57600 [6:55:37<3:04:07,  1.64it/s]
 69%|██████▊   | 39481/57600 [6:55:38<3:03:42,  1.64it/s]
 69%|██████▊   | 39482/57600 [6:55:39<3:10:00,  1.59it/s]
 69%|██████▊   | 39483/57600 [6:55:39<3:11:58,  1.57it/s]
 69%|██████▊   | 39484/57600 [6:55:40<3:09:42,  1.59it/s]
 69%|██████▊   | 39485/57600 [6:55:40<3:04:16,  1.64it/s]
 69%|██████▊   | 39486/57600 [6:55:41<3:06:02,  1.62it/s]
 69%|██████▊   | 39487/57600 [6:55:42<3:06:49,  1.62it/s]
 69%|██████▊   | 39488/57600 [6:55:42<3:11:02,  1.58it/s]
 69%|██████▊   | 39489/57600 [6:55:43<3:07:20,  1.61it/s]
 69%|██████▊   | 39490/57600 [6:55:44<3:05:04,  1.63it/s]
 69%|██████▊   | 39491/57600 [6:55:44<3:13:27,  1.56it/s]
 69%|██████▊   | 39492/57600 [6:55:45<3:12:50,  1.57it/s]
 69%|██████▊   | 39493/57600 [6:55:46<3:13:04,  1.56it/s]
 69%|██████▊   | 39494/57600 [6:55:46<3:08:24,  1.60it/s]
 69%|██████▊   | 39495/57600 [6:55:47<3:10:10,  1.59it/s]
 69%|██████▊   | 39496/57600 [6:55:47<3:07:21,  1.61it/s]
 69%|██████▊   | 39497/57600 [6:55:48<3:04:16,  1.64it/s]
 69%|██████▊   | 39498/57600 [6:55:49<3:07:41,  1.61it/s]
 69%|██████▊   | 39499/57600 [6:55:49<3:03:48,  1.64it/s]
 69%|██████▊   | 39500/57600 [6:55:50<3:06:45,  1.62it/s]
                                                         
{'loss': 1.1789, 'learning_rate': 3.8379790940766544e-07, 'epoch': 435.98}

 69%|██████▊   | 39500/57600 [6:55:50<3:06:45,  1.62it/s]
 69%|██████▊   | 39501/57600 [6:55:51<3:09:11,  1.59it/s]
 69%|██████▊   | 39502/57600 [6:55:51<3:17:58,  1.52it/s]
 69%|██████▊   | 39503/57600 [6:55:52<3:19:04,  1.52it/s]
 69%|██████▊   | 39504/57600 [6:55:53<3:15:02,  1.55it/s]
 69%|██████▊   | 39505/57600 [6:55:53<3:13:34,  1.56it/s]
 69%|██████▊   | 39506/57600 [6:55:54<3:10:30,  1.58it/s]
 69%|██████▊   | 39507/57600 [6:55:54<3:09:44,  1.59it/s]
 69%|██████▊   | 39508/57600 [6:55:55<3:08:19,  1.60it/s]
 69%|██████▊   | 39509/57600 [6:55:56<3:04:36,  1.63it/s]
 69%|██████▊   | 39510/57600 [6:55:56<3:06:24,  1.62it/s]
 69%|██████▊   | 39511/57600 [6:55:57<3:09:09,  1.59it/s]
 69%|██████▊   | 39512/57600 [6:55:57<3:09:37,  1.59it/s]
 69%|██████▊   | 39513/57600 [6:55:58<3:10:30,  1.58it/s]
 69%|██████▊   | 39514/57600 [6:55:59<3:07:55,  1.60it/s]
 69%|██████▊   | 39515/57600 [6:55:59<3:02:37,  1.65it/s]
 69%|██████▊   | 39516/57600 [6:56:00<3:10:08,  1.59it/s]
 69%|██████▊   | 39517/57600 [6:56:01<3:10:51,  1.58it/s]
 69%|██████▊   | 39518/57600 [6:56:01<3:12:21,  1.57it/s]
 69%|██████▊   | 39519/57600 [6:56:02<3:09:29,  1.59it/s]
 69%|██████▊   | 39520/57600 [6:56:03<3:12:50,  1.56it/s]
                                                         
{'loss': 1.1395, 'learning_rate': 3.834843205574913e-07, 'epoch': 436.2}

 69%|██████▊   | 39520/57600 [6:56:03<3:12:50,  1.56it/s]
 69%|██████▊   | 39521/57600 [6:56:03<3:14:11,  1.55it/s]
 69%|██████▊   | 39522/57600 [6:56:04<3:15:51,  1.54it/s]
 69%|██████▊   | 39523/57600 [6:56:04<3:14:25,  1.55it/s]
 69%|██████▊   | 39524/57600 [6:56:05<3:13:27,  1.56it/s]
 69%|██████▊   | 39525/57600 [6:56:06<3:15:22,  1.54it/s]
 69%|██████▊   | 39526/57600 [6:56:06<3:12:42,  1.56it/s]
 69%|██████▊   | 39527/57600 [6:56:07<3:17:51,  1.52it/s]
 69%|██████▊   | 39528/57600 [6:56:08<3:17:44,  1.52it/s]
 69%|██████▊   | 39529/57600 [6:56:08<3:15:14,  1.54it/s]
 69%|██████▊   | 39530/57600 [6:56:09<3:13:17,  1.56it/s]
 69%|██████▊   | 39531/57600 [6:56:10<3:11:16,  1.57it/s]
 69%|██████▊   | 39532/57600 [6:56:10<3:05:18,  1.63it/s]
 69%|██████▊   | 39533/57600 [6:56:11<3:06:40,  1.61it/s]
 69%|██████▊   | 39534/57600 [6:56:11<3:05:34,  1.62it/s]
 69%|██████▊   | 39535/57600 [6:56:12<3:05:54,  1.62it/s]
 69%|██████▊   | 39536/57600 [6:56:13<3:07:10,  1.61it/s]
 69%|██████▊   | 39537/57600 [6:56:13<3:07:32,  1.61it/s]
 69%|██████▊   | 39538/57600 [6:56:14<3:12:16,  1.57it/s]
 69%|██████▊   | 39539/57600 [6:56:15<3:11:10,  1.57it/s]
 69%|██████▊   | 39540/57600 [6:56:15<3:07:22,  1.61it/s]
                                                         
{'loss': 1.1263, 'learning_rate': 3.83170731707317e-07, 'epoch': 436.42}

 69%|██████▊   | 39540/57600 [6:56:15<3:07:22,  1.61it/s]
 69%|██████▊   | 39541/57600 [6:56:16<3:20:39,  1.50it/s]
 69%|██████▊   | 39542/57600 [6:56:17<3:14:34,  1.55it/s]
 69%|██████▊   | 39543/57600 [6:56:17<3:15:19,  1.54it/s]
 69%|██████▊   | 39544/57600 [6:56:18<3:11:28,  1.57it/s]
 69%|██████▊   | 39545/57600 [6:56:19<3:12:44,  1.56it/s]
 69%|██████▊   | 39546/57600 [6:56:19<3:11:32,  1.57it/s]
 69%|██████▊   | 39547/57600 [6:56:20<3:09:53,  1.58it/s]
 69%|██████▊   | 39548/57600 [6:56:20<3:09:09,  1.59it/s]
 69%|██████▊   | 39549/57600 [6:56:21<3:13:21,  1.56it/s]
 69%|██████▊   | 39550/57600 [6:56:22<3:10:32,  1.58it/s]
 69%|██████▊   | 39551/57600 [6:56:22<3:09:22,  1.59it/s]
 69%|██████▊   | 39552/57600 [6:56:23<3:02:43,  1.65it/s]
 69%|██████▊   | 39553/57600 [6:56:23<2:58:18,  1.69it/s]
 69%|██████▊   | 39554/57600 [6:56:24<2:59:31,  1.68it/s]
 69%|██████▊   | 39555/57600 [6:56:25<3:09:17,  1.59it/s]
 69%|██████▊   | 39556/57600 [6:56:25<3:07:13,  1.61it/s]
 69%|██████▊   | 39557/57600 [6:56:26<3:06:55,  1.61it/s]
 69%|██████▊   | 39558/57600 [6:56:27<3:04:50,  1.63it/s]
 69%|██████▊   | 39559/57600 [6:56:27<3:03:27,  1.64it/s]
 69%|██████▊   | 39560/57600 [6:56:28<3:18:41,  1.51it/s]
                                                         
{'loss': 1.13, 'learning_rate': 3.828571428571429e-07, 'epoch': 436.64}

 69%|██████▊   | 39560/57600 [6:56:28<3:18:41,  1.51it/s]
 69%|██████▊   | 39561/57600 [6:56:29<3:15:55,  1.53it/s]
 69%|██████▊   | 39562/57600 [6:56:29<3:13:44,  1.55it/s]
 69%|██████▊   | 39563/57600 [6:56:30<3:11:45,  1.57it/s]
 69%|██████▊   | 39564/57600 [6:56:30<3:13:24,  1.55it/s]
 69%|██████▊   | 39565/57600 [6:56:31<3:09:26,  1.59it/s]
 69%|██████▊   | 39566/57600 [6:56:32<3:08:45,  1.59it/s]
 69%|██████▊   | 39567/57600 [6:56:32<3:10:14,  1.58it/s]
 69%|██████▊   | 39568/57600 [6:56:33<3:10:33,  1.58it/s]
 69%|██████▊   | 39569/57600 [6:56:34<3:07:12,  1.61it/s]
 69%|██████▊   | 39570/57600 [6:56:34<3:04:18,  1.63it/s]
 69%|██████▊   | 39571/57600 [6:56:35<3:10:01,  1.58it/s]
 69%|██████▊   | 39572/57600 [6:56:35<3:07:30,  1.60it/s]
 69%|██████▊   | 39573/57600 [6:56:36<3:05:28,  1.62it/s]
 69%|██████▊   | 39574/57600 [6:56:37<3:09:07,  1.59it/s]
 69%|██████▊   | 39575/57600 [6:56:37<3:14:27,  1.54it/s]
 69%|██████▊   | 39576/57600 [6:56:38<3:16:52,  1.53it/s]
 69%|██████▊   | 39577/57600 [6:56:39<3:11:28,  1.57it/s]
 69%|██████▊   | 39578/57600 [6:56:39<3:06:02,  1.61it/s]
 69%|██████▊   | 39579/57600 [6:56:40<3:11:16,  1.57it/s]
 69%|██████▊   | 39580/57600 [6:56:41<3:09:59,  1.58it/s]
                                                         
{'loss': 1.1497, 'learning_rate': 3.8254355400696866e-07, 'epoch': 436.87}

 69%|██████▊   | 39580/57600 [6:56:41<3:09:59,  1.58it/s]
 69%|██████▊   | 39581/57600 [6:56:41<3:08:48,  1.59it/s]
 69%|██████▊   | 39582/57600 [6:56:42<3:09:34,  1.58it/s]
 69%|██████▊   | 39583/57600 [6:56:42<3:07:49,  1.60it/s]
 69%|██████▊   | 39584/57600 [6:56:43<3:02:16,  1.65it/s]
 69%|██████▊   | 39585/57600 [6:56:44<3:05:56,  1.61it/s]
 69%|██████▊   | 39586/57600 [6:56:44<3:02:46,  1.64it/s]
 69%|██████▊   | 39587/57600 [6:56:45<3:05:20,  1.62it/s]
 69%|██████▊   | 39588/57600 [6:56:45<3:02:34,  1.64it/s]
 69%|██████▊   | 39589/57600 [6:56:46<3:05:40,  1.62it/s]
 69%|██████▊   | 39590/57600 [6:56:47<3:09:20,  1.59it/s]
 69%|██████▊   | 39591/57600 [6:56:47<3:06:24,  1.61it/s]
 69%|██████▊   | 39592/57600 [6:56:48<3:05:36,  1.62it/s]
 69%|██████▊   | 39593/57600 [6:56:49<3:11:12,  1.57it/s]
 69%|██████▊   | 39594/57600 [6:56:49<3:08:35,  1.59it/s]
 69%|██████▊   | 39595/57600 [6:56:50<3:11:09,  1.57it/s]
 69%|██████▊   | 39596/57600 [6:56:51<3:13:46,  1.55it/s]
 69%|██████▊   | 39597/57600 [6:56:51<3:13:17,  1.55it/s]
 69%|██████▊   | 39598/57600 [6:56:52<3:10:16,  1.58it/s]
 69%|██████▊   | 39599/57600 [6:56:52<3:08:42,  1.59it/s]
 69%|██████▉   | 39600/57600 [6:56:53<3:04:58,  1.62it/s]
                                                         
{'loss': 1.156, 'learning_rate': 3.822299651567944e-07, 'epoch': 437.09}

 69%|██████▉   | 39600/57600 [6:56:53<3:04:58,  1.62it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 11.24it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.18it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.76it/s]

100%|██████████| 6/6 [00:01<00:00,  3.15it/s]{'score': 48.73856487544334, 'counts': [145, 93, 64, 46], 'totals': [211, 181, 151, 122], 'precisions': [68.72037914691943, 51.38121546961326, 42.384105960264904, 37.704918032786885], 'bp': 1.0, 'sys_len': 211, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 1.9549425840377808, 'eval_bleu': 48.7386, 'eval_gen_len': 8.4333, 'eval_runtime': 3.2851, 'eval_samples_per_second': 9.132, 'eval_steps_per_second': 1.826, 'epoch': 437.09}

 69%|██████▉   | 39600/57600 [6:56:56<3:04:58,  1.62it/s]

100%|██████████| 6/6 [00:03<00:00,  3.15it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 13:51:09,615 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 69%|██████▉   | 39601/57600 [6:57:25<49:56:05,  9.99s/it]
 69%|██████▉   | 39602/57600 [6:57:25<35:52:52,  7.18s/it]
 69%|██████▉   | 39603/57600 [6:57:26<26:08:24,  5.23s/it]
 69%|██████▉   | 39604/57600 [6:57:27<19:25:18,  3.89s/it]
 69%|██████▉   | 39605/57600 [6:57:28<14:43:00,  2.94s/it]
 69%|██████▉   | 39606/57600 [6:57:28<11:22:16,  2.28s/it]
 69%|██████▉   | 39607/57600 [6:57:29<8:59:05,  1.80s/it] 
 69%|██████▉   | 39608/57600 [6:57:30<7:15:55,  1.45s/it]
 69%|██████▉   | 39609/57600 [6:57:30<5:58:33,  1.20s/it]
 69%|██████▉   | 39610/57600 [6:57:31<5:08:12,  1.03s/it]
 69%|██████▉   | 39611/57600 [6:57:32<4:30:51,  1.11it/s]
 69%|██████▉   | 39612/57600 [6:57:32<4:06:36,  1.22it/s]
 69%|██████▉   | 39613/57600 [6:57:33<3:55:18,  1.27it/s]
 69%|██████▉   | 39614/57600 [6:57:34<3:44:15,  1.34it/s]
 69%|██████▉   | 39615/57600 [6:57:34<3:31:56,  1.41it/s]
 69%|██████▉   | 39616/57600 [6:57:35<3:20:12,  1.50it/s]
 69%|██████▉   | 39617/57600 [6:57:35<3:18:33,  1.51it/s]
 69%|██████▉   | 39618/57600 [6:57:36<3:29:29,  1.43it/s]
 69%|██████▉   | 39619/57600 [6:57:37<3:27:57,  1.44it/s]
 69%|██████▉   | 39620/57600 [6:57:37<3:24:47,  1.46it/s]
                                                         
{'loss': 1.177, 'learning_rate': 3.819163763066202e-07, 'epoch': 437.31}

 69%|██████▉   | 39620/57600 [6:57:37<3:24:47,  1.46it/s]
 69%|██████▉   | 39621/57600 [6:57:38<3:24:36,  1.46it/s]
 69%|██████▉   | 39622/57600 [6:57:39<3:22:43,  1.48it/s]
 69%|██████▉   | 39623/57600 [6:57:39<3:19:31,  1.50it/s]
 69%|██████▉   | 39624/57600 [6:57:40<3:20:09,  1.50it/s]
 69%|██████▉   | 39625/57600 [6:57:41<3:15:45,  1.53it/s]
 69%|██████▉   | 39626/57600 [6:57:41<3:18:17,  1.51it/s]
 69%|██████▉   | 39627/57600 [6:57:42<3:19:38,  1.50it/s]
 69%|██████▉   | 39628/57600 [6:57:43<3:15:06,  1.54it/s]
 69%|██████▉   | 39629/57600 [6:57:43<3:18:43,  1.51it/s]
 69%|██████▉   | 39630/57600 [6:57:44<3:28:24,  1.44it/s]
 69%|██████▉   | 39631/57600 [6:57:45<3:28:48,  1.43it/s]
 69%|██████▉   | 39632/57600 [6:57:46<3:21:09,  1.49it/s]
 69%|██████▉   | 39633/57600 [6:57:46<3:26:16,  1.45it/s]
 69%|██████▉   | 39634/57600 [6:57:47<3:23:51,  1.47it/s]
 69%|██████▉   | 39635/57600 [6:57:48<3:18:22,  1.51it/s]
 69%|██████▉   | 39636/57600 [6:57:48<3:17:37,  1.52it/s]
 69%|██████▉   | 39637/57600 [6:57:49<3:20:17,  1.49it/s]
 69%|██████▉   | 39638/57600 [6:57:49<3:13:29,  1.55it/s]
 69%|██████▉   | 39639/57600 [6:57:50<3:16:57,  1.52it/s]
 69%|██████▉   | 39640/57600 [6:57:51<3:11:48,  1.56it/s]
                                                         
{'loss': 1.1015, 'learning_rate': 3.8160278745644597e-07, 'epoch': 437.53}

 69%|██████▉   | 39640/57600 [6:57:51<3:11:48,  1.56it/s]
 69%|██████▉   | 39641/57600 [6:57:51<3:13:28,  1.55it/s]
 69%|██████▉   | 39642/57600 [6:57:52<3:10:17,  1.57it/s]
 69%|██████▉   | 39643/57600 [6:57:53<3:09:02,  1.58it/s]
 69%|██████▉   | 39644/57600 [6:57:53<3:11:29,  1.56it/s]
 69%|██████▉   | 39645/57600 [6:57:54<3:12:53,  1.55it/s]
 69%|██████▉   | 39646/57600 [6:57:55<3:12:25,  1.56it/s]
 69%|██████▉   | 39647/57600 [6:57:55<3:15:40,  1.53it/s]
 69%|██████▉   | 39648/57600 [6:57:56<3:16:24,  1.52it/s]
 69%|██████▉   | 39649/57600 [6:57:57<3:18:12,  1.51it/s]
 69%|██████▉   | 39650/57600 [6:57:57<3:13:00,  1.55it/s]
 69%|██████▉   | 39651/57600 [6:57:58<3:08:33,  1.59it/s]
 69%|██████▉   | 39652/57600 [6:57:58<3:12:17,  1.56it/s]
 69%|██████▉   | 39653/57600 [6:57:59<3:08:52,  1.58it/s]
 69%|██████▉   | 39654/57600 [6:58:00<3:19:14,  1.50it/s]
 69%|██████▉   | 39655/57600 [6:58:01<3:19:12,  1.50it/s]
 69%|██████▉   | 39656/57600 [6:58:01<3:18:09,  1.51it/s]
 69%|██████▉   | 39657/57600 [6:58:02<3:23:29,  1.47it/s]
 69%|██████▉   | 39658/57600 [6:58:03<3:23:03,  1.47it/s]
 69%|██████▉   | 39659/57600 [6:58:03<3:20:57,  1.49it/s]
 69%|██████▉   | 39660/57600 [6:58:04<3:19:19,  1.50it/s]
                                                         
{'loss': 1.1403, 'learning_rate': 3.8128919860627177e-07, 'epoch': 437.75}

 69%|██████▉   | 39660/57600 [6:58:04<3:19:19,  1.50it/s]
 69%|██████▉   | 39661/57600 [6:58:04<3:14:12,  1.54it/s]
 69%|██████▉   | 39662/57600 [6:58:05<3:10:12,  1.57it/s]
 69%|██████▉   | 39663/57600 [6:58:06<3:13:22,  1.55it/s]
 69%|██████▉   | 39664/57600 [6:58:06<3:09:17,  1.58it/s]
 69%|██████▉   | 39665/57600 [6:58:07<3:07:46,  1.59it/s]
 69%|██████▉   | 39666/57600 [6:58:08<3:05:24,  1.61it/s]
 69%|██████▉   | 39667/57600 [6:58:08<3:07:08,  1.60it/s]
 69%|██████▉   | 39668/57600 [6:58:09<3:12:27,  1.55it/s]
 69%|██████▉   | 39669/57600 [6:58:10<3:19:24,  1.50it/s]
 69%|██████▉   | 39670/57600 [6:58:10<3:16:47,  1.52it/s]
 69%|██████▉   | 39671/57600 [6:58:11<3:18:22,  1.51it/s]
 69%|██████▉   | 39672/57600 [6:58:12<3:10:52,  1.57it/s]
 69%|██████▉   | 39673/57600 [6:58:12<3:11:31,  1.56it/s]
 69%|██████▉   | 39674/57600 [6:58:13<3:06:10,  1.60it/s]
 69%|██████▉   | 39675/57600 [6:58:13<3:08:51,  1.58it/s]
 69%|██████▉   | 39676/57600 [6:58:14<3:11:09,  1.56it/s]
 69%|██████▉   | 39677/57600 [6:58:15<3:11:45,  1.56it/s]
 69%|██████▉   | 39678/57600 [6:58:15<3:16:12,  1.52it/s]
 69%|██████▉   | 39679/57600 [6:58:16<3:16:04,  1.52it/s]
 69%|██████▉   | 39680/57600 [6:58:17<3:17:35,  1.51it/s]
                                                         
{'loss': 1.144, 'learning_rate': 3.809756097560976e-07, 'epoch': 437.97}

 69%|██████▉   | 39680/57600 [6:58:17<3:17:35,  1.51it/s]
 69%|██████▉   | 39681/57600 [6:58:17<3:18:04,  1.51it/s]
 69%|██████▉   | 39682/57600 [6:58:18<3:20:55,  1.49it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 69%|██████▉   | 39683/57600 [6:58:19<3:27:04,  1.44it/s]
 69%|██████▉   | 39684/57600 [6:58:19<3:19:29,  1.50it/s]
 69%|██████▉   | 39685/57600 [6:58:20<3:13:04,  1.55it/s]
 69%|██████▉   | 39686/57600 [6:58:21<3:12:14,  1.55it/s]
 69%|██████▉   | 39687/57600 [6:58:21<3:06:04,  1.60it/s]
 69%|██████▉   | 39688/57600 [6:58:22<3:15:27,  1.53it/s]
 69%|██████▉   | 39689/57600 [6:58:23<3:18:27,  1.50it/s]
 69%|██████▉   | 39690/57600 [6:58:23<3:15:18,  1.53it/s]
 69%|██████▉   | 39691/57600 [6:58:24<3:13:15,  1.54it/s]
 69%|██████▉   | 39692/57600 [6:58:25<3:13:57,  1.54it/s]
 69%|██████▉   | 39693/57600 [6:58:25<3:11:56,  1.55it/s]
 69%|██████▉   | 39694/57600 [6:58:26<3:14:34,  1.53it/s]
 69%|██████▉   | 39695/57600 [6:58:27<3:15:56,  1.52it/s]
 69%|██████▉   | 39696/57600 [6:58:27<3:20:07,  1.49it/s]
 69%|██████▉   | 39697/57600 [6:58:28<3:17:53,  1.51it/s]
 69%|██████▉   | 39698/57600 [6:58:29<3:15:42,  1.52it/s]
 69%|██████▉   | 39699/57600 [6:58:29<3:11:42,  1.56it/s]
 69%|██████▉   | 39700/57600 [6:58:30<3:12:54,  1.55it/s]
                                                         
{'loss': 1.1744, 'learning_rate': 3.8066202090592333e-07, 'epoch': 438.19}

 69%|██████▉   | 39700/57600 [6:58:30<3:12:54,  1.55it/s]
 69%|██████▉   | 39701/57600 [6:58:31<3:29:15,  1.43it/s]
 69%|██████▉   | 39702/57600 [6:58:31<3:21:09,  1.48it/s]
 69%|██████▉   | 39703/57600 [6:58:32<3:19:28,  1.50it/s]
 69%|██████▉   | 39704/57600 [6:58:33<3:20:46,  1.49it/s]
 69%|██████▉   | 39705/57600 [6:58:33<3:18:56,  1.50it/s]
 69%|██████▉   | 39706/57600 [6:58:34<3:11:42,  1.56it/s]
 69%|██████▉   | 39707/57600 [6:58:35<3:17:21,  1.51it/s]
 69%|██████▉   | 39708/57600 [6:58:35<3:19:47,  1.49it/s]
 69%|██████▉   | 39709/57600 [6:58:36<3:24:22,  1.46it/s]
 69%|██████▉   | 39710/57600 [6:58:37<3:30:05,  1.42it/s]
 69%|██████▉   | 39711/57600 [6:58:37<3:24:37,  1.46it/s]
 69%|██████▉   | 39712/57600 [6:58:38<3:25:25,  1.45it/s]
 69%|██████▉   | 39713/57600 [6:58:39<3:22:41,  1.47it/s]
 69%|██████▉   | 39714/57600 [6:58:39<3:21:13,  1.48it/s]
 69%|██████▉   | 39715/57600 [6:58:40<3:16:25,  1.52it/s]
 69%|██████▉   | 39716/57600 [6:58:41<3:18:13,  1.50it/s]
 69%|██████▉   | 39717/57600 [6:58:41<3:12:22,  1.55it/s]
 69%|██████▉   | 39718/57600 [6:58:42<3:14:06,  1.54it/s]
 69%|██████▉   | 39719/57600 [6:58:43<3:18:54,  1.50it/s]
 69%|██████▉   | 39720/57600 [6:58:43<3:13:37,  1.54it/s]
                                                         
{'loss': 1.1481, 'learning_rate': 3.8034843205574913e-07, 'epoch': 438.41}

 69%|██████▉   | 39720/57600 [6:58:43<3:13:37,  1.54it/s]
 69%|██████▉   | 39721/57600 [6:58:44<3:10:11,  1.57it/s]
 69%|██████▉   | 39722/57600 [6:58:45<3:15:57,  1.52it/s]
 69%|██████▉   | 39723/57600 [6:58:45<3:13:35,  1.54it/s]
 69%|██████▉   | 39724/57600 [6:58:46<3:17:08,  1.51it/s]
 69%|██████▉   | 39725/57600 [6:58:47<3:15:45,  1.52it/s]
 69%|██████▉   | 39726/57600 [6:58:47<3:12:34,  1.55it/s]
 69%|██████▉   | 39727/57600 [6:58:48<3:10:12,  1.57it/s]
 69%|██████▉   | 39728/57600 [6:58:48<3:15:06,  1.53it/s]
 69%|██████▉   | 39729/57600 [6:58:49<3:12:46,  1.55it/s]
 69%|██████▉   | 39730/57600 [6:58:50<3:11:48,  1.55it/s]
 69%|██████▉   | 39731/57600 [6:58:50<3:17:10,  1.51it/s]
 69%|██████▉   | 39732/57600 [6:58:51<3:16:13,  1.52it/s]
 69%|██████▉   | 39733/57600 [6:58:52<3:08:00,  1.58it/s]
 69%|██████▉   | 39734/57600 [6:58:52<3:06:07,  1.60it/s]
 69%|██████▉   | 39735/57600 [6:58:53<3:06:39,  1.60it/s]
 69%|██████▉   | 39736/57600 [6:58:53<3:05:03,  1.61it/s]
 69%|██████▉   | 39737/57600 [6:58:54<3:06:10,  1.60it/s]
 69%|██████▉   | 39738/57600 [6:58:55<3:04:04,  1.62it/s]
 69%|██████▉   | 39739/57600 [6:58:55<3:04:53,  1.61it/s]
 69%|██████▉   | 39740/57600 [6:58:56<3:09:43,  1.57it/s]
                                                         
{'loss': 1.1002, 'learning_rate': 3.800348432055749e-07, 'epoch': 438.63}

 69%|██████▉   | 39740/57600 [6:58:56<3:09:43,  1.57it/s]
 69%|██████▉   | 39741/57600 [6:58:57<3:09:38,  1.57it/s]
 69%|██████▉   | 39742/57600 [6:58:57<3:09:33,  1.57it/s]
 69%|██████▉   | 39743/57600 [6:58:58<3:12:43,  1.54it/s]
 69%|██████▉   | 39744/57600 [6:58:59<3:11:52,  1.55it/s]
 69%|██████▉   | 39745/57600 [6:58:59<3:11:11,  1.56it/s]
 69%|██████▉   | 39746/57600 [6:59:00<3:15:14,  1.52it/s]
 69%|██████▉   | 39747/57600 [6:59:00<3:07:56,  1.58it/s]
 69%|██████▉   | 39748/57600 [6:59:01<3:05:09,  1.61it/s]
 69%|██████▉   | 39749/57600 [6:59:02<3:10:08,  1.56it/s]
 69%|██████▉   | 39750/57600 [6:59:02<3:11:52,  1.55it/s]
 69%|██████▉   | 39751/57600 [6:59:03<3:15:54,  1.52it/s]
 69%|██████▉   | 39752/57600 [6:59:04<3:15:05,  1.52it/s]
 69%|██████▉   | 39753/57600 [6:59:04<3:17:20,  1.51it/s]
 69%|██████▉   | 39754/57600 [6:59:05<3:17:29,  1.51it/s]
 69%|██████▉   | 39755/57600 [6:59:06<3:19:42,  1.49it/s]
 69%|██████▉   | 39756/57600 [6:59:06<3:10:15,  1.56it/s]
 69%|██████▉   | 39757/57600 [6:59:07<3:10:33,  1.56it/s]
 69%|██████▉   | 39758/57600 [6:59:08<3:13:21,  1.54it/s]
 69%|██████▉   | 39759/57600 [6:59:08<3:14:32,  1.53it/s]
 69%|██████▉   | 39760/57600 [6:59:09<3:13:08,  1.54it/s]
                                                         
{'loss': 1.1463, 'learning_rate': 3.797212543554007e-07, 'epoch': 438.85}

 69%|██████▉   | 39760/57600 [6:59:09<3:13:08,  1.54it/s]
 69%|██████▉   | 39761/57600 [6:59:10<3:15:50,  1.52it/s]
 69%|██████▉   | 39762/57600 [6:59:10<3:23:13,  1.46it/s]
 69%|██████▉   | 39763/57600 [6:59:11<3:18:56,  1.49it/s]
 69%|██████▉   | 39764/57600 [6:59:12<3:22:39,  1.47it/s]
 69%|██████▉   | 39765/57600 [6:59:13<3:30:22,  1.41it/s]
 69%|██████▉   | 39766/57600 [6:59:13<3:20:29,  1.48it/s]
 69%|██████▉   | 39767/57600 [6:59:14<3:17:51,  1.50it/s]
 69%|██████▉   | 39768/57600 [6:59:14<3:16:20,  1.51it/s]
 69%|██████▉   | 39769/57600 [6:59:15<3:24:03,  1.46it/s]
 69%|██████▉   | 39770/57600 [6:59:16<3:25:57,  1.44it/s]
 69%|██████▉   | 39771/57600 [6:59:17<3:24:00,  1.46it/s]
 69%|██████▉   | 39772/57600 [6:59:17<3:25:00,  1.45it/s]
 69%|██████▉   | 39773/57600 [6:59:18<3:19:30,  1.49it/s]
 69%|██████▉   | 39774/57600 [6:59:19<3:31:33,  1.40it/s]
 69%|██████▉   | 39775/57600 [6:59:19<3:23:28,  1.46it/s]
 69%|██████▉   | 39776/57600 [6:59:20<3:21:30,  1.47it/s]
 69%|██████▉   | 39777/57600 [6:59:21<3:20:14,  1.48it/s]
 69%|██████▉   | 39778/57600 [6:59:21<3:18:15,  1.50it/s]
 69%|██████▉   | 39779/57600 [6:59:22<3:14:45,  1.53it/s]
 69%|██████▉   | 39780/57600 [6:59:23<3:14:01,  1.53it/s]
                                                         
{'loss': 1.1197, 'learning_rate': 3.7940766550522644e-07, 'epoch': 439.07}

 69%|██████▉   | 39780/57600 [6:59:23<3:14:01,  1.53it/s]
 69%|██████▉   | 39781/57600 [6:59:23<3:15:54,  1.52it/s]
 69%|██████▉   | 39782/57600 [6:59:24<3:19:32,  1.49it/s]
 69%|██████▉   | 39783/57600 [6:59:25<3:16:35,  1.51it/s]
 69%|██████▉   | 39784/57600 [6:59:25<3:13:42,  1.53it/s]
 69%|██████▉   | 39785/57600 [6:59:26<3:11:42,  1.55it/s]
 69%|██████▉   | 39786/57600 [6:59:26<3:08:55,  1.57it/s]
 69%|██████▉   | 39787/57600 [6:59:27<3:10:47,  1.56it/s]
 69%|██████▉   | 39788/57600 [6:59:28<3:11:09,  1.55it/s]
 69%|██████▉   | 39789/57600 [6:59:29<3:22:04,  1.47it/s]
 69%|██████▉   | 39790/57600 [6:59:29<3:18:48,  1.49it/s]
 69%|██████▉   | 39791/57600 [6:59:30<3:16:33,  1.51it/s]
 69%|██████▉   | 39792/57600 [6:59:30<3:14:22,  1.53it/s]
 69%|██████▉   | 39793/57600 [6:59:31<3:16:55,  1.51it/s]
 69%|██████▉   | 39794/57600 [6:59:32<3:13:37,  1.53it/s]
 69%|██████▉   | 39795/57600 [6:59:32<3:15:56,  1.51it/s]
 69%|██████▉   | 39796/57600 [6:59:33<3:15:27,  1.52it/s]
 69%|██████▉   | 39797/57600 [6:59:34<3:12:55,  1.54it/s]
 69%|██████▉   | 39798/57600 [6:59:34<3:08:55,  1.57it/s]
 69%|██████▉   | 39799/57600 [6:59:35<3:13:52,  1.53it/s]
 69%|██████▉   | 39800/57600 [6:59:36<3:19:23,  1.49it/s]
                                                         
{'loss': 1.1338, 'learning_rate': 3.7909407665505225e-07, 'epoch': 439.29}

 69%|██████▉   | 39800/57600 [6:59:36<3:19:23,  1.49it/s]
 69%|██████▉   | 39801/57600 [6:59:36<3:18:27,  1.49it/s]
 69%|██████▉   | 39802/57600 [6:59:37<3:14:13,  1.53it/s]
 69%|██████▉   | 39803/57600 [6:59:38<3:09:28,  1.57it/s]
 69%|██████▉   | 39804/57600 [6:59:38<3:07:47,  1.58it/s]
 69%|██████▉   | 39805/57600 [6:59:39<3:08:02,  1.58it/s]
 69%|██████▉   | 39806/57600 [6:59:39<3:04:29,  1.61it/s]
 69%|██████▉   | 39807/57600 [6:59:40<3:11:49,  1.55it/s]
 69%|██████▉   | 39808/57600 [6:59:41<3:15:17,  1.52it/s]
 69%|██████▉   | 39809/57600 [6:59:41<3:11:48,  1.55it/s]
 69%|██████▉   | 39810/57600 [6:59:42<3:23:13,  1.46it/s]
 69%|██████▉   | 39811/57600 [6:59:43<3:23:24,  1.46it/s]
 69%|██████▉   | 39812/57600 [6:59:44<3:26:16,  1.44it/s]
 69%|██████▉   | 39813/57600 [6:59:44<3:23:10,  1.46it/s]
 69%|██████▉   | 39814/57600 [6:59:45<3:13:42,  1.53it/s]
 69%|██████▉   | 39815/57600 [6:59:45<3:06:20,  1.59it/s]
 69%|██████▉   | 39816/57600 [6:59:46<3:06:07,  1.59it/s]
 69%|██████▉   | 39817/57600 [6:59:47<3:06:16,  1.59it/s]
 69%|██████▉   | 39818/57600 [6:59:47<3:12:27,  1.54it/s]
 69%|██████▉   | 39819/57600 [6:59:48<3:05:35,  1.60it/s]
 69%|██████▉   | 39820/57600 [6:59:49<3:09:44,  1.56it/s]
                                                         
{'loss': 1.174, 'learning_rate': 3.787804878048781e-07, 'epoch': 439.51}

 69%|██████▉   | 39820/57600 [6:59:49<3:09:44,  1.56it/s]
 69%|██████▉   | 39821/57600 [6:59:49<3:10:48,  1.55it/s]
 69%|██████▉   | 39822/57600 [6:59:50<3:06:00,  1.59it/s]
 69%|██████▉   | 39823/57600 [6:59:51<3:06:35,  1.59it/s]
 69%|██████▉   | 39824/57600 [6:59:51<3:13:05,  1.53it/s]
 69%|██████▉   | 39825/57600 [6:59:52<3:05:52,  1.59it/s]
 69%|██████▉   | 39826/57600 [6:59:52<3:00:16,  1.64it/s]
 69%|██████▉   | 39827/57600 [6:59:53<2:53:52,  1.70it/s]
 69%|██████▉   | 39828/57600 [6:59:54<3:00:30,  1.64it/s]
 69%|██████▉   | 39829/57600 [6:59:54<2:59:17,  1.65it/s]
 69%|██████▉   | 39830/57600 [6:59:55<2:56:31,  1.68it/s]
 69%|██████▉   | 39831/57600 [6:59:55<2:54:55,  1.69it/s]
 69%|██████▉   | 39832/57600 [6:59:56<2:56:40,  1.68it/s]
 69%|██████▉   | 39833/57600 [6:59:57<2:58:12,  1.66it/s]
 69%|██████▉   | 39834/57600 [6:59:57<3:00:13,  1.64it/s]
 69%|██████▉   | 39835/57600 [6:59:58<3:05:19,  1.60it/s]
 69%|██████▉   | 39836/57600 [6:59:58<3:06:30,  1.59it/s]
 69%|██████▉   | 39837/57600 [6:59:59<3:09:52,  1.56it/s]
 69%|██████▉   | 39838/57600 [7:00:00<3:06:03,  1.59it/s]
 69%|██████▉   | 39839/57600 [7:00:00<3:08:46,  1.57it/s]
 69%|██████▉   | 39840/57600 [7:00:01<3:05:03,  1.60it/s]
                                                         
{'loss': 1.1651, 'learning_rate': 3.784668989547038e-07, 'epoch': 439.74}

 69%|██████▉   | 39840/57600 [7:00:01<3:05:03,  1.60it/s]
 69%|██████▉   | 39841/57600 [7:00:02<3:04:17,  1.61it/s]
 69%|██████▉   | 39842/57600 [7:00:02<3:06:19,  1.59it/s]
 69%|██████▉   | 39843/57600 [7:00:03<3:06:25,  1.59it/s]
 69%|██████▉   | 39844/57600 [7:00:04<3:04:30,  1.60it/s]
 69%|██████▉   | 39845/57600 [7:00:04<3:00:19,  1.64it/s]
 69%|██████▉   | 39846/57600 [7:00:05<2:58:47,  1.66it/s]
 69%|██████▉   | 39847/57600 [7:00:05<3:00:10,  1.64it/s]
 69%|██████▉   | 39848/57600 [7:00:06<3:02:56,  1.62it/s]
 69%|██████▉   | 39849/57600 [7:00:07<3:09:23,  1.56it/s]
 69%|██████▉   | 39850/57600 [7:00:07<3:04:34,  1.60it/s]
 69%|██████▉   | 39851/57600 [7:00:08<2:58:20,  1.66it/s]
 69%|██████▉   | 39852/57600 [7:00:08<2:58:27,  1.66it/s]
 69%|██████▉   | 39853/57600 [7:00:09<3:04:55,  1.60it/s]
 69%|██████▉   | 39854/57600 [7:00:10<3:06:19,  1.59it/s]
 69%|██████▉   | 39855/57600 [7:00:10<3:07:00,  1.58it/s]
 69%|██████▉   | 39856/57600 [7:00:11<3:11:49,  1.54it/s]
 69%|██████▉   | 39857/57600 [7:00:12<3:09:53,  1.56it/s]
 69%|██████▉   | 39858/57600 [7:00:12<3:17:05,  1.50it/s]
 69%|██████▉   | 39859/57600 [7:00:13<3:09:23,  1.56it/s]
 69%|██████▉   | 39860/57600 [7:00:14<3:06:51,  1.58it/s]
                                                         
{'loss': 1.1388, 'learning_rate': 3.781533101045296e-07, 'epoch': 439.96}

 69%|██████▉   | 39860/57600 [7:00:14<3:06:51,  1.58it/s]
 69%|██████▉   | 39861/57600 [7:00:14<3:08:37,  1.57it/s]
 69%|██████▉   | 39862/57600 [7:00:15<3:12:39,  1.53it/s]
 69%|██████▉   | 39863/57600 [7:00:15<3:06:47,  1.58it/s]
 69%|██████▉   | 39864/57600 [7:00:16<3:11:12,  1.55it/s]
 69%|██████▉   | 39865/57600 [7:00:17<3:12:59,  1.53it/s]
 69%|██████▉   | 39866/57600 [7:00:17<3:10:57,  1.55it/s]
 69%|██████▉   | 39867/57600 [7:00:18<3:09:02,  1.56it/s]
 69%|██████▉   | 39868/57600 [7:00:19<3:10:08,  1.55it/s]
 69%|██████▉   | 39869/57600 [7:00:19<3:08:54,  1.56it/s]
 69%|██████▉   | 39870/57600 [7:00:20<3:06:17,  1.59it/s]
 69%|██████▉   | 39871/57600 [7:00:21<3:03:24,  1.61it/s]
 69%|██████▉   | 39872/57600 [7:00:21<3:00:33,  1.64it/s]
 69%|██████▉   | 39873/57600 [7:00:22<2:58:28,  1.66it/s]
 69%|██████▉   | 39874/57600 [7:00:22<2:55:33,  1.68it/s]
 69%|██████▉   | 39875/57600 [7:00:23<2:59:38,  1.64it/s]
 69%|██████▉   | 39876/57600 [7:00:24<3:03:07,  1.61it/s]
 69%|██████▉   | 39877/57600 [7:00:24<3:09:00,  1.56it/s]
 69%|██████▉   | 39878/57600 [7:00:25<3:06:40,  1.58it/s]
 69%|██████▉   | 39879/57600 [7:00:26<3:11:21,  1.54it/s]
 69%|██████▉   | 39880/57600 [7:00:26<3:16:29,  1.50it/s]
                                                         
{'loss': 1.1651, 'learning_rate': 3.7783972125435536e-07, 'epoch': 440.18}

 69%|██████▉   | 39880/57600 [7:00:26<3:16:29,  1.50it/s]
 69%|██████▉   | 39881/57600 [7:00:27<3:12:55,  1.53it/s]
 69%|██████▉   | 39882/57600 [7:00:28<3:07:33,  1.57it/s]
 69%|██████▉   | 39883/57600 [7:00:28<2:59:40,  1.64it/s]
 69%|██████▉   | 39884/57600 [7:00:29<3:00:10,  1.64it/s]
 69%|██████▉   | 39885/57600 [7:00:29<3:02:27,  1.62it/s]
 69%|██████▉   | 39886/57600 [7:00:30<3:01:50,  1.62it/s]
 69%|██████▉   | 39887/57600 [7:00:31<3:08:37,  1.57it/s]
 69%|██████▉   | 39888/57600 [7:00:31<3:02:43,  1.62it/s]
 69%|██████▉   | 39889/57600 [7:00:32<3:01:35,  1.63it/s]
 69%|██████▉   | 39890/57600 [7:00:32<3:00:05,  1.64it/s]
 69%|██████▉   | 39891/57600 [7:00:33<3:01:51,  1.62it/s]
 69%|██████▉   | 39892/57600 [7:00:34<3:04:45,  1.60it/s]
 69%|██████▉   | 39893/57600 [7:00:34<3:09:26,  1.56it/s]
 69%|██████▉   | 39894/57600 [7:00:35<3:05:47,  1.59it/s]
 69%|██████▉   | 39895/57600 [7:00:36<3:04:18,  1.60it/s]
 69%|██████▉   | 39896/57600 [7:00:36<3:02:04,  1.62it/s]
 69%|██████▉   | 39897/57600 [7:00:37<2:58:49,  1.65it/s]
 69%|██████▉   | 39898/57600 [7:00:37<3:04:12,  1.60it/s]
 69%|██████▉   | 39899/57600 [7:00:38<3:06:29,  1.58it/s]
 69%|██████▉   | 39900/57600 [7:00:39<3:07:30,  1.57it/s]
                                                         
{'loss': 1.1577, 'learning_rate': 3.7752613240418116e-07, 'epoch': 440.4}

 69%|██████▉   | 39900/57600 [7:00:39<3:07:30,  1.57it/s]
 69%|██████▉   | 39901/57600 [7:00:39<3:08:11,  1.57it/s]
 69%|██████▉   | 39902/57600 [7:00:40<3:04:02,  1.60it/s]
 69%|██████▉   | 39903/57600 [7:00:41<3:05:30,  1.59it/s]
 69%|██████▉   | 39904/57600 [7:00:41<2:59:47,  1.64it/s]
 69%|██████▉   | 39905/57600 [7:00:42<3:01:50,  1.62it/s]
 69%|██████▉   | 39906/57600 [7:00:42<3:06:58,  1.58it/s]
 69%|██████▉   | 39907/57600 [7:00:43<3:06:53,  1.58it/s]
 69%|██████▉   | 39908/57600 [7:00:44<3:04:41,  1.60it/s]
 69%|██████▉   | 39909/57600 [7:00:44<3:08:11,  1.57it/s]
 69%|██████▉   | 39910/57600 [7:00:45<3:03:41,  1.61it/s]
 69%|██████▉   | 39911/57600 [7:00:46<3:02:51,  1.61it/s]
 69%|██████▉   | 39912/57600 [7:00:46<3:04:31,  1.60it/s]
 69%|██████▉   | 39913/57600 [7:00:47<3:02:41,  1.61it/s]
 69%|██████▉   | 39914/57600 [7:00:47<3:03:39,  1.60it/s]
 69%|██████▉   | 39915/57600 [7:00:48<3:02:34,  1.61it/s]
 69%|██████▉   | 39916/57600 [7:00:49<3:01:21,  1.63it/s]
 69%|██████▉   | 39917/57600 [7:00:49<3:04:13,  1.60it/s]
 69%|██████▉   | 39918/57600 [7:00:50<3:09:57,  1.55it/s]
 69%|██████▉   | 39919/57600 [7:00:51<3:10:17,  1.55it/s]
 69%|██████▉   | 39920/57600 [7:00:51<3:08:31,  1.56it/s]
                                                         
{'loss': 1.1453, 'learning_rate': 3.772125435540069e-07, 'epoch': 440.62}

 69%|██████▉   | 39920/57600 [7:00:51<3:08:31,  1.56it/s]
 69%|██████▉   | 39921/57600 [7:00:52<3:16:37,  1.50it/s]
 69%|██████▉   | 39922/57600 [7:00:53<3:13:56,  1.52it/s]
 69%|██████▉   | 39923/57600 [7:00:53<3:10:23,  1.55it/s]
 69%|██████▉   | 39924/57600 [7:00:54<3:08:24,  1.56it/s]
 69%|██████▉   | 39925/57600 [7:00:55<3:10:48,  1.54it/s]
 69%|██████▉   | 39926/57600 [7:00:55<3:03:05,  1.61it/s]
 69%|██████▉   | 39927/57600 [7:00:56<3:03:29,  1.61it/s]
 69%|██████▉   | 39928/57600 [7:00:56<3:01:42,  1.62it/s]
 69%|██████▉   | 39929/57600 [7:00:57<3:03:42,  1.60it/s]
 69%|██████▉   | 39930/57600 [7:00:58<2:59:28,  1.64it/s]
 69%|██████▉   | 39931/57600 [7:00:58<2:56:37,  1.67it/s]
 69%|██████▉   | 39932/57600 [7:00:59<3:00:28,  1.63it/s]
 69%|██████▉   | 39933/57600 [7:00:59<2:54:26,  1.69it/s]
 69%|██████▉   | 39934/57600 [7:01:00<2:58:06,  1.65it/s]
 69%|██████▉   | 39935/57600 [7:01:01<3:04:23,  1.60it/s]
 69%|██████▉   | 39936/57600 [7:01:01<3:03:41,  1.60it/s]
 69%|██████▉   | 39937/57600 [7:01:02<3:02:57,  1.61it/s]
 69%|██████▉   | 39938/57600 [7:01:03<3:05:25,  1.59it/s]
 69%|██████▉   | 39939/57600 [7:01:03<3:06:13,  1.58it/s]
 69%|██████▉   | 39940/57600 [7:01:04<3:02:51,  1.61it/s]
                                                         
{'loss': 1.1037, 'learning_rate': 3.768989547038327e-07, 'epoch': 440.84}

 69%|██████▉   | 39940/57600 [7:01:04<3:02:51,  1.61it/s]
 69%|██████▉   | 39941/57600 [7:01:04<2:58:35,  1.65it/s]
 69%|██████▉   | 39942/57600 [7:01:05<3:08:23,  1.56it/s]
 69%|██████▉   | 39943/57600 [7:01:06<3:08:13,  1.56it/s]
 69%|██████▉   | 39944/57600 [7:01:06<3:09:34,  1.55it/s]
 69%|██████▉   | 39945/57600 [7:01:07<3:13:09,  1.52it/s]
 69%|██████▉   | 39946/57600 [7:01:08<3:14:17,  1.51it/s]
 69%|██████▉   | 39947/57600 [7:01:08<3:08:04,  1.56it/s]
 69%|██████▉   | 39948/57600 [7:01:09<3:04:52,  1.59it/s]
 69%|██████▉   | 39949/57600 [7:01:10<3:07:32,  1.57it/s]
 69%|██████▉   | 39950/57600 [7:01:10<3:12:20,  1.53it/s]
 69%|██████▉   | 39951/57600 [7:01:11<3:08:35,  1.56it/s]
 69%|██████▉   | 39952/57600 [7:01:11<3:02:29,  1.61it/s]
 69%|██████▉   | 39953/57600 [7:01:12<2:59:38,  1.64it/s]
 69%|██████▉   | 39954/57600 [7:01:13<3:01:34,  1.62it/s]
 69%|██████▉   | 39955/57600 [7:01:13<3:05:29,  1.59it/s]
 69%|██████▉   | 39956/57600 [7:01:14<3:11:15,  1.54it/s]
 69%|██████▉   | 39957/57600 [7:01:15<3:09:35,  1.55it/s]
 69%|██████▉   | 39958/57600 [7:01:15<3:13:41,  1.52it/s]
 69%|██████▉   | 39959/57600 [7:01:16<3:12:07,  1.53it/s]
 69%|██████▉   | 39960/57600 [7:01:17<3:14:38,  1.51it/s]
                                                         
{'loss': 1.1393, 'learning_rate': 3.765853658536586e-07, 'epoch': 441.06}

 69%|██████▉   | 39960/57600 [7:01:17<3:14:38,  1.51it/s]
 69%|██████▉   | 39961/57600 [7:01:17<3:13:49,  1.52it/s]
 69%|██████▉   | 39962/57600 [7:01:18<3:06:56,  1.57it/s]
 69%|██████▉   | 39963/57600 [7:01:18<3:00:37,  1.63it/s]
 69%|██████▉   | 39964/57600 [7:01:19<3:06:45,  1.57it/s]
 69%|██████▉   | 39965/57600 [7:01:20<3:07:01,  1.57it/s]
 69%|██████▉   | 39966/57600 [7:01:20<3:05:15,  1.59it/s]
 69%|██████▉   | 39967/57600 [7:01:21<3:01:07,  1.62it/s]
 69%|██████▉   | 39968/57600 [7:01:22<3:04:58,  1.59it/s]
 69%|██████▉   | 39969/57600 [7:01:22<3:02:25,  1.61it/s]
 69%|██████▉   | 39970/57600 [7:01:23<2:58:57,  1.64it/s]
 69%|██████▉   | 39971/57600 [7:01:23<3:06:47,  1.57it/s]
 69%|██████▉   | 39972/57600 [7:01:24<3:10:13,  1.54it/s]
 69%|██████▉   | 39973/57600 [7:01:25<3:10:41,  1.54it/s]
 69%|██████▉   | 39974/57600 [7:01:25<3:12:04,  1.53it/s]
 69%|██████▉   | 39975/57600 [7:01:26<3:12:48,  1.52it/s]
 69%|██████▉   | 39976/57600 [7:01:27<3:07:22,  1.57it/s]
 69%|██████▉   | 39977/57600 [7:01:27<3:10:28,  1.54it/s]
 69%|██████▉   | 39978/57600 [7:01:28<3:06:02,  1.58it/s]
 69%|██████▉   | 39979/57600 [7:01:29<3:02:21,  1.61it/s]
 69%|██████▉   | 39980/57600 [7:01:29<2:57:36,  1.65it/s]
                                                         
{'loss': 1.1566, 'learning_rate': 3.762717770034843e-07, 'epoch': 441.28}

 69%|██████▉   | 39980/57600 [7:01:29<2:57:36,  1.65it/s]
 69%|██████▉   | 39981/57600 [7:01:30<2:55:06,  1.68it/s]
 69%|██████▉   | 39982/57600 [7:01:30<2:54:19,  1.68it/s]
 69%|██████▉   | 39983/57600 [7:01:31<2:56:13,  1.67it/s]
 69%|██████▉   | 39984/57600 [7:01:32<2:59:41,  1.63it/s]
 69%|██████▉   | 39985/57600 [7:01:32<3:02:39,  1.61it/s]
 69%|██████▉   | 39986/57600 [7:01:33<3:00:09,  1.63it/s]
 69%|██████▉   | 39987/57600 [7:01:34<3:04:32,  1.59it/s]
 69%|██████▉   | 39988/57600 [7:01:34<3:08:31,  1.56it/s]
 69%|██████▉   | 39989/57600 [7:01:35<3:13:28,  1.52it/s]
 69%|██████▉   | 39990/57600 [7:01:36<3:15:02,  1.50it/s]
 69%|██████▉   | 39991/57600 [7:01:36<3:12:44,  1.52it/s]
 69%|██████▉   | 39992/57600 [7:01:37<3:07:26,  1.57it/s]
 69%|██████▉   | 39993/57600 [7:01:37<3:02:24,  1.61it/s]
 69%|██████▉   | 39994/57600 [7:01:38<3:01:08,  1.62it/s]
 69%|██████▉   | 39995/57600 [7:01:39<3:01:21,  1.62it/s]
 69%|██████▉   | 39996/57600 [7:01:39<3:04:04,  1.59it/s]
 69%|██████▉   | 39997/57600 [7:01:40<3:04:55,  1.59it/s]
 69%|██████▉   | 39998/57600 [7:01:41<3:11:05,  1.54it/s]
 69%|██████▉   | 39999/57600 [7:01:41<3:08:37,  1.56it/s]
 69%|██████▉   | 40000/57600 [7:01:42<3:11:34,  1.53it/s]
                                                         
{'loss': 1.0984, 'learning_rate': 3.7595818815331014e-07, 'epoch': 441.5}

 69%|██████▉   | 40000/57600 [7:01:42<3:11:34,  1.53it/s]
 69%|██████▉   | 40001/57600 [7:01:43<3:09:21,  1.55it/s]
 69%|██████▉   | 40002/57600 [7:01:43<3:06:01,  1.58it/s]
 69%|██████▉   | 40003/57600 [7:01:44<3:05:52,  1.58it/s]
 69%|██████▉   | 40004/57600 [7:01:44<3:13:49,  1.51it/s]
 69%|██████▉   | 40005/57600 [7:01:45<3:10:36,  1.54it/s]
 69%|██████▉   | 40006/57600 [7:01:46<3:05:58,  1.58it/s]
 69%|██████▉   | 40007/57600 [7:01:46<3:06:56,  1.57it/s]
 69%|██████▉   | 40008/57600 [7:01:47<3:06:24,  1.57it/s]
 69%|██████▉   | 40009/57600 [7:01:48<3:10:43,  1.54it/s]
 69%|██████▉   | 40010/57600 [7:01:48<3:11:55,  1.53it/s]
 69%|██████▉   | 40011/57600 [7:01:49<3:19:05,  1.47it/s]
 69%|██████▉   | 40012/57600 [7:01:50<3:13:32,  1.51it/s]
 69%|██████▉   | 40013/57600 [7:01:50<3:06:10,  1.57it/s]
 69%|██████▉   | 40014/57600 [7:01:51<3:05:33,  1.58it/s]
 69%|██████▉   | 40015/57600 [7:01:52<3:08:05,  1.56it/s]
 69%|██████▉   | 40016/57600 [7:01:52<3:07:09,  1.57it/s]
 69%|██████▉   | 40017/57600 [7:01:53<3:03:12,  1.60it/s]
 69%|██████▉   | 40018/57600 [7:01:53<2:59:11,  1.64it/s]
 69%|██████▉   | 40019/57600 [7:01:54<3:01:23,  1.62it/s]
 69%|██████▉   | 40020/57600 [7:01:55<2:58:01,  1.65it/s]
                                                         
{'loss': 1.1659, 'learning_rate': 3.7564459930313583e-07, 'epoch': 441.72}

 69%|██████▉   | 40020/57600 [7:01:55<2:58:01,  1.65it/s]
 69%|██████▉   | 40021/57600 [7:01:55<3:06:06,  1.57it/s]
 69%|██████▉   | 40022/57600 [7:01:56<3:07:03,  1.57it/s]
 69%|██████▉   | 40023/57600 [7:01:57<3:10:09,  1.54it/s]
 69%|██████▉   | 40024/57600 [7:01:57<3:07:23,  1.56it/s]
 69%|██████▉   | 40025/57600 [7:01:58<3:09:06,  1.55it/s]
 69%|██████▉   | 40026/57600 [7:01:58<3:06:43,  1.57it/s]
 69%|██████▉   | 40027/57600 [7:01:59<3:07:24,  1.56it/s]
 69%|██████▉   | 40028/57600 [7:02:00<3:06:16,  1.57it/s]
 69%|██████▉   | 40029/57600 [7:02:00<3:07:04,  1.57it/s]
 69%|██████▉   | 40030/57600 [7:02:01<3:08:51,  1.55it/s]
 69%|██████▉   | 40031/57600 [7:02:02<3:12:29,  1.52it/s]
 70%|██████▉   | 40032/57600 [7:02:02<3:03:20,  1.60it/s]
 70%|██████▉   | 40033/57600 [7:02:03<3:02:44,  1.60it/s]
 70%|██████▉   | 40034/57600 [7:02:04<2:59:57,  1.63it/s]
 70%|██████▉   | 40035/57600 [7:02:04<3:01:24,  1.61it/s]
 70%|██████▉   | 40036/57600 [7:02:05<2:56:40,  1.66it/s]
 70%|██████▉   | 40037/57600 [7:02:05<3:06:02,  1.57it/s]
 70%|██████▉   | 40038/57600 [7:02:06<3:07:56,  1.56it/s]
 70%|██████▉   | 40039/57600 [7:02:07<3:04:45,  1.58it/s]
 70%|██████▉   | 40040/57600 [7:02:07<2:57:17,  1.65it/s]
                                                         
{'loss': 1.1299, 'learning_rate': 3.753310104529617e-07, 'epoch': 441.94}

 70%|██████▉   | 40040/57600 [7:02:07<2:57:17,  1.65it/s]
 70%|██████▉   | 40041/57600 [7:02:08<3:01:32,  1.61it/s]
 70%|██████▉   | 40042/57600 [7:02:08<2:57:29,  1.65it/s]
 70%|██████▉   | 40043/57600 [7:02:09<2:59:23,  1.63it/s]
 70%|██████▉   | 40044/57600 [7:02:10<3:03:19,  1.60it/s]
 70%|██████▉   | 40045/57600 [7:02:10<3:03:38,  1.59it/s]
 70%|██████▉   | 40046/57600 [7:02:11<3:07:25,  1.56it/s]
 70%|██████▉   | 40047/57600 [7:02:12<3:10:34,  1.54it/s]
 70%|██████▉   | 40048/57600 [7:02:12<3:05:49,  1.57it/s]
 70%|██████▉   | 40049/57600 [7:02:13<3:07:22,  1.56it/s]
 70%|██████▉   | 40050/57600 [7:02:14<3:10:30,  1.54it/s]
 70%|██████▉   | 40051/57600 [7:02:14<3:07:50,  1.56it/s]
 70%|██████▉   | 40052/57600 [7:02:15<3:06:59,  1.56it/s]
 70%|██████▉   | 40053/57600 [7:02:16<3:06:10,  1.57it/s]
 70%|██████▉   | 40054/57600 [7:02:16<3:06:49,  1.57it/s]
 70%|██████▉   | 40055/57600 [7:02:17<3:01:51,  1.61it/s]
 70%|██████▉   | 40056/57600 [7:02:17<2:57:46,  1.64it/s]
 70%|██████▉   | 40057/57600 [7:02:18<2:59:21,  1.63it/s]
 70%|██████▉   | 40058/57600 [7:02:19<2:57:36,  1.65it/s]
 70%|██████▉   | 40059/57600 [7:02:19<2:57:13,  1.65it/s]
 70%|██████▉   | 40060/57600 [7:02:20<3:04:56,  1.58it/s]
                                                         
{'loss': 1.1503, 'learning_rate': 3.750174216027874e-07, 'epoch': 442.16}

 70%|██████▉   | 40060/57600 [7:02:20<3:04:56,  1.58it/s]
 70%|██████▉   | 40061/57600 [7:02:21<3:09:32,  1.54it/s]
 70%|██████▉   | 40062/57600 [7:02:21<3:08:56,  1.55it/s]
 70%|██████▉   | 40063/57600 [7:02:22<3:07:03,  1.56it/s]
 70%|██████▉   | 40064/57600 [7:02:22<3:04:32,  1.58it/s]
 70%|██████▉   | 40065/57600 [7:02:23<3:09:47,  1.54it/s]
 70%|██████▉   | 40066/57600 [7:02:24<3:05:58,  1.57it/s]
 70%|██████▉   | 40067/57600 [7:02:24<3:08:46,  1.55it/s]
 70%|██████▉   | 40068/57600 [7:02:25<3:05:26,  1.58it/s]
 70%|██████▉   | 40069/57600 [7:02:26<3:02:42,  1.60it/s]
 70%|██████▉   | 40070/57600 [7:02:26<3:06:48,  1.56it/s]
 70%|██████▉   | 40071/57600 [7:02:27<3:06:23,  1.57it/s]
 70%|██████▉   | 40072/57600 [7:02:28<3:03:39,  1.59it/s]
 70%|██████▉   | 40073/57600 [7:02:28<3:02:26,  1.60it/s]
 70%|██████▉   | 40074/57600 [7:02:29<3:03:01,  1.60it/s]
 70%|██████▉   | 40075/57600 [7:02:29<3:05:25,  1.58it/s]
 70%|██████▉   | 40076/57600 [7:02:30<3:11:52,  1.52it/s]
 70%|██████▉   | 40077/57600 [7:02:31<3:06:05,  1.57it/s]
 70%|██████▉   | 40078/57600 [7:02:31<3:05:21,  1.58it/s]
 70%|██████▉   | 40079/57600 [7:02:32<3:01:46,  1.61it/s]
 70%|██████▉   | 40080/57600 [7:02:33<2:58:30,  1.64it/s]
                                                         
{'loss': 1.1451, 'learning_rate': 3.7470383275261325e-07, 'epoch': 442.38}

 70%|██████▉   | 40080/57600 [7:02:33<2:58:30,  1.64it/s]
 70%|██████▉   | 40081/57600 [7:02:33<2:58:38,  1.63it/s]
 70%|██████▉   | 40082/57600 [7:02:34<2:58:05,  1.64it/s]
 70%|██████▉   | 40083/57600 [7:02:34<2:57:26,  1.65it/s]
 70%|██████▉   | 40084/57600 [7:02:35<3:03:05,  1.59it/s]
 70%|██████▉   | 40085/57600 [7:02:36<2:56:25,  1.65it/s]
 70%|██████▉   | 40086/57600 [7:02:36<2:58:51,  1.63it/s]
 70%|██████▉   | 40087/57600 [7:02:37<2:57:16,  1.65it/s]
 70%|██████▉   | 40088/57600 [7:02:37<2:55:41,  1.66it/s]
 70%|██████▉   | 40089/57600 [7:02:38<2:56:03,  1.66it/s]
 70%|██████▉   | 40090/57600 [7:02:39<2:57:24,  1.65it/s]
 70%|██████▉   | 40091/57600 [7:02:39<2:57:38,  1.64it/s]
 70%|██████▉   | 40092/57600 [7:02:40<2:55:49,  1.66it/s]
 70%|██████▉   | 40093/57600 [7:02:40<2:51:19,  1.70it/s]
 70%|██████▉   | 40094/57600 [7:02:41<2:55:39,  1.66it/s]
 70%|██████▉   | 40095/57600 [7:02:42<2:57:22,  1.64it/s]
 70%|██████▉   | 40096/57600 [7:02:42<2:59:22,  1.63it/s]
 70%|██████▉   | 40097/57600 [7:02:43<2:58:44,  1.63it/s]
 70%|██████▉   | 40098/57600 [7:02:44<3:04:02,  1.58it/s]
 70%|██████▉   | 40099/57600 [7:02:44<3:05:34,  1.57it/s]
 70%|██████▉   | 40100/57600 [7:02:45<3:06:33,  1.56it/s]
                                                         
{'loss': 1.1444, 'learning_rate': 3.7439024390243905e-07, 'epoch': 442.6}

 70%|██████▉   | 40100/57600 [7:02:45<3:06:33,  1.56it/s]
 70%|██████▉   | 40101/57600 [7:02:45<3:05:53,  1.57it/s]
 70%|██████▉   | 40102/57600 [7:02:46<3:11:20,  1.52it/s]
 70%|██████▉   | 40103/57600 [7:02:47<3:11:07,  1.53it/s]
 70%|██████▉   | 40104/57600 [7:02:47<3:11:46,  1.52it/s]
 70%|██████▉   | 40105/57600 [7:02:48<3:10:27,  1.53it/s]
 70%|██████▉   | 40106/57600 [7:02:49<3:07:55,  1.55it/s]
 70%|██████▉   | 40107/57600 [7:02:49<3:07:41,  1.55it/s]
 70%|██████▉   | 40108/57600 [7:02:50<3:08:26,  1.55it/s]
 70%|██████▉   | 40109/57600 [7:02:51<3:03:22,  1.59it/s]
 70%|██████▉   | 40110/57600 [7:02:51<3:11:34,  1.52it/s]
 70%|██████▉   | 40111/57600 [7:02:52<3:13:13,  1.51it/s]
 70%|██████▉   | 40112/57600 [7:02:53<3:08:37,  1.55it/s]
 70%|██████▉   | 40113/57600 [7:02:53<3:07:05,  1.56it/s]
 70%|██████▉   | 40114/57600 [7:02:54<3:05:59,  1.57it/s]
 70%|██████▉   | 40115/57600 [7:02:55<3:04:38,  1.58it/s]
 70%|██████▉   | 40116/57600 [7:02:55<3:06:00,  1.57it/s]
 70%|██████▉   | 40117/57600 [7:02:56<3:04:27,  1.58it/s]
 70%|██████▉   | 40118/57600 [7:02:56<3:02:28,  1.60it/s]
 70%|██████▉   | 40119/57600 [7:02:57<3:00:33,  1.61it/s]
 70%|██████▉   | 40120/57600 [7:02:58<3:04:02,  1.58it/s]
                                                         
{'loss': 1.1223, 'learning_rate': 3.7407665505226475e-07, 'epoch': 442.83}

 70%|██████▉   | 40120/57600 [7:02:58<3:04:02,  1.58it/s]
 70%|██████▉   | 40121/57600 [7:02:58<3:00:46,  1.61it/s]
 70%|██████▉   | 40122/57600 [7:02:59<2:57:45,  1.64it/s]
 70%|██████▉   | 40123/57600 [7:02:59<2:55:13,  1.66it/s]
 70%|██████▉   | 40124/57600 [7:03:00<2:56:41,  1.65it/s]
 70%|██████▉   | 40125/57600 [7:03:01<3:04:21,  1.58it/s]
 70%|██████▉   | 40126/57600 [7:03:01<3:02:57,  1.59it/s]
 70%|██████▉   | 40127/57600 [7:03:02<3:01:19,  1.61it/s]
 70%|██████▉   | 40128/57600 [7:03:03<2:59:39,  1.62it/s]
 70%|██████▉   | 40129/57600 [7:03:03<3:02:28,  1.60it/s]
 70%|██████▉   | 40130/57600 [7:03:04<3:05:13,  1.57it/s]
 70%|██████▉   | 40131/57600 [7:03:04<3:01:39,  1.60it/s]
 70%|██████▉   | 40132/57600 [7:03:05<3:03:35,  1.59it/s]
 70%|██████▉   | 40133/57600 [7:03:06<3:06:45,  1.56it/s]
 70%|██████▉   | 40134/57600 [7:03:06<3:03:55,  1.58it/s]
 70%|██████▉   | 40135/57600 [7:03:07<3:08:24,  1.54it/s]
 70%|██████▉   | 40136/57600 [7:03:08<3:12:37,  1.51it/s]
 70%|██████▉   | 40137/57600 [7:03:08<3:07:15,  1.55it/s]
 70%|██████▉   | 40138/57600 [7:03:09<3:10:03,  1.53it/s]
 70%|██████▉   | 40139/57600 [7:03:10<3:11:29,  1.52it/s]
 70%|██████▉   | 40140/57600 [7:03:10<3:07:27,  1.55it/s]
                                                         
{'loss': 1.1695, 'learning_rate': 3.7376306620209066e-07, 'epoch': 443.05}

 70%|██████▉   | 40140/57600 [7:03:10<3:07:27,  1.55it/s]
 70%|██████▉   | 40141/57600 [7:03:11<3:03:33,  1.59it/s]
 70%|██████▉   | 40142/57600 [7:03:11<2:56:42,  1.65it/s]
 70%|██████▉   | 40143/57600 [7:03:12<2:56:38,  1.65it/s]
 70%|██████▉   | 40144/57600 [7:03:13<2:58:57,  1.63it/s]
 70%|██████▉   | 40145/57600 [7:03:13<2:56:39,  1.65it/s]
 70%|██████▉   | 40146/57600 [7:03:14<2:55:05,  1.66it/s]
 70%|██████▉   | 40147/57600 [7:03:15<3:03:17,  1.59it/s]
 70%|██████▉   | 40148/57600 [7:03:15<3:00:42,  1.61it/s]
 70%|██████▉   | 40149/57600 [7:03:16<3:04:02,  1.58it/s]
 70%|██████▉   | 40150/57600 [7:03:16<2:58:03,  1.63it/s]
 70%|██████▉   | 40151/57600 [7:03:17<2:58:43,  1.63it/s]
 70%|██████▉   | 40152/57600 [7:03:18<2:58:59,  1.62it/s]
 70%|██████▉   | 40153/57600 [7:03:18<2:57:59,  1.63it/s]
 70%|██████▉   | 40154/57600 [7:03:19<3:03:12,  1.59it/s]
 70%|██████▉   | 40155/57600 [7:03:20<2:59:41,  1.62it/s]
 70%|██████▉   | 40156/57600 [7:03:20<2:55:39,  1.66it/s]
 70%|██████▉   | 40157/57600 [7:03:21<2:51:11,  1.70it/s]
 70%|██████▉   | 40158/57600 [7:03:21<2:58:20,  1.63it/s]
 70%|██████▉   | 40159/57600 [7:03:22<3:00:41,  1.61it/s]
 70%|██████▉   | 40160/57600 [7:03:23<3:09:54,  1.53it/s]
                                                         
{'loss': 1.1616, 'learning_rate': 3.734494773519163e-07, 'epoch': 443.27}

 70%|██████▉   | 40160/57600 [7:03:23<3:09:54,  1.53it/s]
 70%|██████▉   | 40161/57600 [7:03:23<3:11:13,  1.52it/s]
 70%|██████▉   | 40162/57600 [7:03:24<3:09:18,  1.54it/s]
 70%|██████▉   | 40163/57600 [7:03:25<3:09:23,  1.53it/s]
 70%|██████▉   | 40164/57600 [7:03:25<3:03:02,  1.59it/s]
 70%|██████▉   | 40165/57600 [7:03:26<3:05:49,  1.56it/s]
 70%|██████▉   | 40166/57600 [7:03:26<2:58:20,  1.63it/s]
 70%|██████▉   | 40167/57600 [7:03:27<3:01:14,  1.60it/s]
 70%|██████▉   | 40168/57600 [7:03:28<2:57:33,  1.64it/s]
 70%|██████▉   | 40169/57600 [7:03:28<2:56:40,  1.64it/s]
 70%|██████▉   | 40170/57600 [7:03:29<2:55:19,  1.66it/s]
 70%|██████▉   | 40171/57600 [7:03:29<2:58:07,  1.63it/s]
 70%|██████▉   | 40172/57600 [7:03:30<3:01:15,  1.60it/s]
 70%|██████▉   | 40173/57600 [7:03:31<3:08:07,  1.54it/s]
 70%|██████▉   | 40174/57600 [7:03:31<3:07:50,  1.55it/s]
 70%|██████▉   | 40175/57600 [7:03:32<3:11:10,  1.52it/s]
 70%|██████▉   | 40176/57600 [7:03:33<3:06:25,  1.56it/s]
 70%|██████▉   | 40177/57600 [7:03:33<3:12:02,  1.51it/s]
 70%|██████▉   | 40178/57600 [7:03:34<3:04:32,  1.57it/s]
 70%|██████▉   | 40179/57600 [7:03:35<3:01:13,  1.60it/s]
 70%|██████▉   | 40180/57600 [7:03:35<2:57:13,  1.64it/s]
                                                         
{'loss': 1.1511, 'learning_rate': 3.7313588850174217e-07, 'epoch': 443.49}

 70%|██████▉   | 40180/57600 [7:03:35<2:57:13,  1.64it/s]
 70%|██████▉   | 40181/57600 [7:03:36<2:57:01,  1.64it/s]
 70%|██████▉   | 40182/57600 [7:03:36<3:00:39,  1.61it/s]
 70%|██████▉   | 40183/57600 [7:03:37<3:01:37,  1.60it/s]
 70%|██████▉   | 40184/57600 [7:03:38<2:58:43,  1.62it/s]
 70%|██████▉   | 40185/57600 [7:03:38<3:03:30,  1.58it/s]
 70%|██████▉   | 40186/57600 [7:03:39<2:57:57,  1.63it/s]
 70%|██████▉   | 40187/57600 [7:03:40<2:59:51,  1.61it/s]
 70%|██████▉   | 40188/57600 [7:03:40<3:07:46,  1.55it/s]
 70%|██████▉   | 40189/57600 [7:03:41<3:07:13,  1.55it/s]
 70%|██████▉   | 40190/57600 [7:03:42<3:03:46,  1.58it/s]
 70%|██████▉   | 40191/57600 [7:03:42<3:07:46,  1.55it/s]
 70%|██████▉   | 40192/57600 [7:03:43<3:09:14,  1.53it/s]
 70%|██████▉   | 40193/57600 [7:03:44<3:14:44,  1.49it/s]
 70%|██████▉   | 40194/57600 [7:03:44<3:11:11,  1.52it/s]
 70%|██████▉   | 40195/57600 [7:03:45<3:10:21,  1.52it/s]
 70%|██████▉   | 40196/57600 [7:03:45<3:03:45,  1.58it/s]
 70%|██████▉   | 40197/57600 [7:03:46<3:03:02,  1.58it/s]
 70%|██████▉   | 40198/57600 [7:03:47<3:02:16,  1.59it/s]
 70%|██████▉   | 40199/57600 [7:03:47<2:59:15,  1.62it/s]
 70%|██████▉   | 40200/57600 [7:03:48<3:01:31,  1.60it/s]
                                                         
{'loss': 1.1121, 'learning_rate': 3.7282229965156787e-07, 'epoch': 443.71}

 70%|██████▉   | 40200/57600 [7:03:48<3:01:31,  1.60it/s]
 70%|██████▉   | 40201/57600 [7:03:49<2:59:24,  1.62it/s]
 70%|██████▉   | 40202/57600 [7:03:49<3:01:55,  1.59it/s]
 70%|██████▉   | 40203/57600 [7:03:50<2:58:14,  1.63it/s]
 70%|██████▉   | 40204/57600 [7:03:50<3:01:29,  1.60it/s]
 70%|██████▉   | 40205/57600 [7:03:51<2:59:36,  1.61it/s]
 70%|██████▉   | 40206/57600 [7:03:52<3:01:26,  1.60it/s]
 70%|██████▉   | 40207/57600 [7:03:52<3:00:45,  1.60it/s]
 70%|██████▉   | 40208/57600 [7:03:53<3:00:44,  1.60it/s]
 70%|██████▉   | 40209/57600 [7:03:54<2:58:58,  1.62it/s]
 70%|██████▉   | 40210/57600 [7:03:54<3:11:17,  1.52it/s]
 70%|██████▉   | 40211/57600 [7:03:55<3:11:42,  1.51it/s]
 70%|██████▉   | 40212/57600 [7:03:56<3:16:25,  1.48it/s]
 70%|██████▉   | 40213/57600 [7:03:56<3:17:19,  1.47it/s]
 70%|██████▉   | 40214/57600 [7:03:57<3:08:49,  1.53it/s]
 70%|██████▉   | 40215/57600 [7:03:58<3:07:27,  1.55it/s]
 70%|██████▉   | 40216/57600 [7:03:58<3:02:43,  1.59it/s]
 70%|██████▉   | 40217/57600 [7:03:59<3:00:31,  1.60it/s]
 70%|██████▉   | 40218/57600 [7:03:59<2:59:10,  1.62it/s]
 70%|██████▉   | 40219/57600 [7:04:00<3:05:14,  1.56it/s]
 70%|██████▉   | 40220/57600 [7:04:01<3:01:22,  1.60it/s]
                                                         
{'loss': 1.121, 'learning_rate': 3.725087108013937e-07, 'epoch': 443.93}

 70%|██████▉   | 40220/57600 [7:04:01<3:01:22,  1.60it/s]
 70%|██████▉   | 40221/57600 [7:04:01<3:02:32,  1.59it/s]
 70%|██████▉   | 40222/57600 [7:04:02<2:58:30,  1.62it/s]
 70%|██████▉   | 40223/57600 [7:04:02<2:57:41,  1.63it/s]
 70%|██████▉   | 40224/57600 [7:04:03<3:02:29,  1.59it/s]
 70%|██████▉   | 40225/57600 [7:04:04<2:59:48,  1.61it/s]
 70%|██████▉   | 40226/57600 [7:04:04<2:58:36,  1.62it/s]
 70%|██████▉   | 40227/57600 [7:04:05<3:08:54,  1.53it/s]
 70%|██████▉   | 40228/57600 [7:04:06<3:07:13,  1.55it/s]
 70%|██████▉   | 40229/57600 [7:04:06<3:04:44,  1.57it/s]
 70%|██████▉   | 40230/57600 [7:04:07<3:11:55,  1.51it/s]
 70%|██████▉   | 40231/57600 [7:04:08<3:13:39,  1.49it/s]
 70%|██████▉   | 40232/57600 [7:04:08<3:05:37,  1.56it/s]
 70%|██████▉   | 40233/57600 [7:04:09<3:05:46,  1.56it/s]
 70%|██████▉   | 40234/57600 [7:04:10<3:02:15,  1.59it/s]
 70%|██████▉   | 40235/57600 [7:04:10<2:59:01,  1.62it/s]
 70%|██████▉   | 40236/57600 [7:04:11<2:59:04,  1.62it/s]
 70%|██████▉   | 40237/57600 [7:04:12<3:06:43,  1.55it/s]
 70%|██████▉   | 40238/57600 [7:04:12<3:00:43,  1.60it/s]
 70%|██████▉   | 40239/57600 [7:04:13<2:58:35,  1.62it/s]
 70%|██████▉   | 40240/57600 [7:04:13<2:58:05,  1.62it/s]
                                                         
{'loss': 1.1332, 'learning_rate': 3.7219512195121953e-07, 'epoch': 444.15}

 70%|██████▉   | 40240/57600 [7:04:13<2:58:05,  1.62it/s]
 70%|██████▉   | 40241/57600 [7:04:14<2:56:33,  1.64it/s]
 70%|██████▉   | 40242/57600 [7:04:15<3:01:20,  1.60it/s]
 70%|██████▉   | 40243/57600 [7:04:15<3:03:14,  1.58it/s]
 70%|██████▉   | 40244/57600 [7:04:16<3:13:23,  1.50it/s]
 70%|██████▉   | 40245/57600 [7:04:17<3:13:22,  1.50it/s]
 70%|██████▉   | 40246/57600 [7:04:17<3:08:38,  1.53it/s]
 70%|██████▉   | 40247/57600 [7:04:18<3:05:04,  1.56it/s]
 70%|██████▉   | 40248/57600 [7:04:18<3:03:00,  1.58it/s]
 70%|██████▉   | 40249/57600 [7:04:19<2:59:37,  1.61it/s]
 70%|██████▉   | 40250/57600 [7:04:20<3:05:18,  1.56it/s]
 70%|██████▉   | 40251/57600 [7:04:20<3:00:52,  1.60it/s]
 70%|██████▉   | 40252/57600 [7:04:21<2:58:59,  1.62it/s]
 70%|██████▉   | 40253/57600 [7:04:22<2:58:57,  1.62it/s]
 70%|██████▉   | 40254/57600 [7:04:22<3:04:09,  1.57it/s]
 70%|██████▉   | 40255/57600 [7:04:23<3:07:01,  1.55it/s]
 70%|██████▉   | 40256/57600 [7:04:24<3:08:37,  1.53it/s]
 70%|██████▉   | 40257/57600 [7:04:24<3:02:32,  1.58it/s]
 70%|██████▉   | 40258/57600 [7:04:25<3:04:49,  1.56it/s]
 70%|██████▉   | 40259/57600 [7:04:25<3:08:00,  1.54it/s]
 70%|██████▉   | 40260/57600 [7:04:26<3:06:03,  1.55it/s]
                                                         
{'loss': 1.1323, 'learning_rate': 3.7188153310104533e-07, 'epoch': 444.37}

 70%|██████▉   | 40260/57600 [7:04:26<3:06:03,  1.55it/s]
 70%|██████▉   | 40261/57600 [7:04:27<3:09:46,  1.52it/s]
 70%|██████▉   | 40262/57600 [7:04:27<3:05:39,  1.56it/s]
 70%|██████▉   | 40263/57600 [7:04:28<3:05:21,  1.56it/s]
 70%|██████▉   | 40264/57600 [7:04:29<3:03:17,  1.58it/s]
 70%|██████▉   | 40265/57600 [7:04:29<2:56:51,  1.63it/s]
 70%|██████▉   | 40266/57600 [7:04:30<3:02:59,  1.58it/s]
 70%|██████▉   | 40267/57600 [7:04:31<3:04:39,  1.56it/s]
 70%|██████▉   | 40268/57600 [7:04:31<3:09:19,  1.53it/s]
 70%|██████▉   | 40269/57600 [7:04:32<3:05:01,  1.56it/s]
 70%|██████▉   | 40270/57600 [7:04:32<2:59:30,  1.61it/s]
 70%|██████▉   | 40271/57600 [7:04:33<3:00:50,  1.60it/s]
 70%|██████▉   | 40272/57600 [7:04:34<3:02:48,  1.58it/s]
 70%|██████▉   | 40273/57600 [7:04:34<2:58:49,  1.61it/s]
 70%|██████▉   | 40274/57600 [7:04:35<2:53:59,  1.66it/s]
 70%|██████▉   | 40275/57600 [7:04:35<2:54:23,  1.66it/s]
 70%|██████▉   | 40276/57600 [7:04:36<2:55:22,  1.65it/s]
 70%|██████▉   | 40277/57600 [7:04:37<2:53:15,  1.67it/s]
 70%|██████▉   | 40278/57600 [7:04:37<2:54:41,  1.65it/s]
 70%|██████▉   | 40279/57600 [7:04:38<2:58:17,  1.62it/s]
 70%|██████▉   | 40280/57600 [7:04:39<2:53:06,  1.67it/s]
                                                         
{'loss': 1.1534, 'learning_rate': 3.715679442508711e-07, 'epoch': 444.59}

 70%|██████▉   | 40280/57600 [7:04:39<2:53:06,  1.67it/s]
 70%|██████▉   | 40281/57600 [7:04:39<2:50:29,  1.69it/s]
 70%|██████▉   | 40282/57600 [7:04:40<2:56:07,  1.64it/s]
 70%|██████▉   | 40283/57600 [7:04:40<2:58:27,  1.62it/s]
 70%|██████▉   | 40284/57600 [7:04:41<3:04:20,  1.57it/s]
 70%|██████▉   | 40285/57600 [7:04:42<3:10:37,  1.51it/s]
 70%|██████▉   | 40286/57600 [7:04:42<3:04:04,  1.57it/s]
 70%|██████▉   | 40287/57600 [7:04:43<3:02:32,  1.58it/s]
 70%|██████▉   | 40288/57600 [7:04:44<2:59:39,  1.61it/s]
 70%|██████▉   | 40289/57600 [7:04:44<3:03:16,  1.57it/s]
 70%|██████▉   | 40290/57600 [7:04:45<2:58:26,  1.62it/s]
 70%|██████▉   | 40291/57600 [7:04:45<2:53:13,  1.67it/s]
 70%|██████▉   | 40292/57600 [7:04:46<2:58:49,  1.61it/s]
 70%|██████▉   | 40293/57600 [7:04:47<2:55:42,  1.64it/s]
 70%|██████▉   | 40294/57600 [7:04:47<2:59:16,  1.61it/s]
 70%|██████▉   | 40295/57600 [7:04:48<2:56:36,  1.63it/s]
 70%|██████▉   | 40296/57600 [7:04:49<3:00:58,  1.59it/s]
 70%|██████▉   | 40297/57600 [7:04:49<3:05:12,  1.56it/s]
 70%|██████▉   | 40298/57600 [7:04:50<3:07:21,  1.54it/s]
 70%|██████▉   | 40299/57600 [7:04:51<3:07:08,  1.54it/s]
 70%|██████▉   | 40300/57600 [7:04:51<3:03:52,  1.57it/s]
                                                         
{'loss': 1.1098, 'learning_rate': 3.7125435540069684e-07, 'epoch': 444.81}

 70%|██████▉   | 40300/57600 [7:04:51<3:03:52,  1.57it/s]
 70%|██████▉   | 40301/57600 [7:04:52<2:57:53,  1.62it/s]
 70%|██████▉   | 40302/57600 [7:04:52<2:57:13,  1.63it/s]
 70%|██████▉   | 40303/57600 [7:04:53<2:52:23,  1.67it/s]
 70%|██████▉   | 40304/57600 [7:04:53<2:52:51,  1.67it/s]
 70%|██████▉   | 40305/57600 [7:04:54<2:54:23,  1.65it/s]
 70%|██████▉   | 40306/57600 [7:04:55<2:50:19,  1.69it/s]
 70%|██████▉   | 40307/57600 [7:04:55<2:50:29,  1.69it/s]
 70%|██████▉   | 40308/57600 [7:04:56<3:00:53,  1.59it/s]
 70%|██████▉   | 40309/57600 [7:04:57<3:03:34,  1.57it/s]
 70%|██████▉   | 40310/57600 [7:04:57<3:04:57,  1.56it/s]
 70%|██████▉   | 40311/57600 [7:04:58<3:06:25,  1.55it/s]
 70%|██████▉   | 40312/57600 [7:04:59<3:04:10,  1.56it/s]
 70%|██████▉   | 40313/57600 [7:04:59<3:05:39,  1.55it/s]
 70%|██████▉   | 40314/57600 [7:05:00<3:07:47,  1.53it/s]
 70%|██████▉   | 40315/57600 [7:05:01<3:08:02,  1.53it/s]
 70%|██████▉   | 40316/57600 [7:05:01<3:00:30,  1.60it/s]
 70%|██████▉   | 40317/57600 [7:05:02<2:58:20,  1.62it/s]
 70%|██████▉   | 40318/57600 [7:05:02<3:01:34,  1.59it/s]
 70%|██████▉   | 40319/57600 [7:05:03<2:57:52,  1.62it/s]
 70%|███████   | 40320/57600 [7:05:04<2:57:53,  1.62it/s]
                                                         
{'loss': 1.1334, 'learning_rate': 3.7094076655052264e-07, 'epoch': 445.03}

 70%|███████   | 40320/57600 [7:05:04<2:57:53,  1.62it/s]
 70%|███████   | 40321/57600 [7:05:04<2:55:30,  1.64it/s]
 70%|███████   | 40322/57600 [7:05:05<3:00:47,  1.59it/s]
 70%|███████   | 40323/57600 [7:05:05<2:59:26,  1.60it/s]
 70%|███████   | 40324/57600 [7:05:06<3:03:01,  1.57it/s]
 70%|███████   | 40325/57600 [7:05:07<3:01:32,  1.59it/s]
 70%|███████   | 40326/57600 [7:05:07<3:05:13,  1.55it/s]
 70%|███████   | 40327/57600 [7:05:08<2:57:56,  1.62it/s]
 70%|███████   | 40328/57600 [7:05:09<2:53:43,  1.66it/s]
 70%|███████   | 40329/57600 [7:05:09<2:52:01,  1.67it/s]
 70%|███████   | 40330/57600 [7:05:10<2:50:09,  1.69it/s]
 70%|███████   | 40331/57600 [7:05:10<2:52:08,  1.67it/s]
 70%|███████   | 40332/57600 [7:05:11<2:49:04,  1.70it/s]
 70%|███████   | 40333/57600 [7:05:11<2:51:40,  1.68it/s]
 70%|███████   | 40334/57600 [7:05:12<2:52:04,  1.67it/s]
 70%|███████   | 40335/57600 [7:05:13<2:56:55,  1.63it/s]
 70%|███████   | 40336/57600 [7:05:13<2:57:37,  1.62it/s]
 70%|███████   | 40337/57600 [7:05:14<3:00:09,  1.60it/s]
 70%|███████   | 40338/57600 [7:05:15<3:00:54,  1.59it/s]
 70%|███████   | 40339/57600 [7:05:15<2:58:00,  1.62it/s]
 70%|███████   | 40340/57600 [7:05:16<3:03:34,  1.57it/s]
                                                         
{'loss': 1.1431, 'learning_rate': 3.706271777003484e-07, 'epoch': 445.25}

 70%|███████   | 40340/57600 [7:05:16<3:03:34,  1.57it/s]
 70%|███████   | 40341/57600 [7:05:17<3:00:41,  1.59it/s]
 70%|███████   | 40342/57600 [7:05:17<2:58:55,  1.61it/s]
 70%|███████   | 40343/57600 [7:05:18<3:01:15,  1.59it/s]
 70%|███████   | 40344/57600 [7:05:18<2:59:30,  1.60it/s]
 70%|███████   | 40345/57600 [7:05:19<2:56:58,  1.63it/s]
 70%|███████   | 40346/57600 [7:05:20<3:01:33,  1.58it/s]
 70%|███████   | 40347/57600 [7:05:20<3:01:17,  1.59it/s]
 70%|███████   | 40348/57600 [7:05:21<3:03:01,  1.57it/s]
 70%|███████   | 40349/57600 [7:05:22<3:07:20,  1.53it/s]
 70%|███████   | 40350/57600 [7:05:22<3:02:38,  1.57it/s]
 70%|███████   | 40351/57600 [7:05:23<2:59:29,  1.60it/s]
 70%|███████   | 40352/57600 [7:05:23<2:58:42,  1.61it/s]
 70%|███████   | 40353/57600 [7:05:24<3:02:05,  1.58it/s]
 70%|███████   | 40354/57600 [7:05:25<3:01:45,  1.58it/s]
 70%|███████   | 40355/57600 [7:05:25<2:58:45,  1.61it/s]
 70%|███████   | 40356/57600 [7:05:26<3:07:50,  1.53it/s]
 70%|███████   | 40357/57600 [7:05:27<3:14:05,  1.48it/s]
 70%|███████   | 40358/57600 [7:05:27<3:06:42,  1.54it/s]
 70%|███████   | 40359/57600 [7:05:28<3:01:18,  1.58it/s]
 70%|███████   | 40360/57600 [7:05:29<3:05:38,  1.55it/s]
                                                         
{'loss': 1.1335, 'learning_rate': 3.703135888501742e-07, 'epoch': 445.47}

 70%|███████   | 40360/57600 [7:05:29<3:05:38,  1.55it/s]
 70%|███████   | 40361/57600 [7:05:29<3:08:49,  1.52it/s]
 70%|███████   | 40362/57600 [7:05:30<3:10:54,  1.50it/s]
 70%|███████   | 40363/57600 [7:05:31<3:03:34,  1.56it/s]
 70%|███████   | 40364/57600 [7:05:31<3:02:47,  1.57it/s]
 70%|███████   | 40365/57600 [7:05:32<3:00:53,  1.59it/s]
 70%|███████   | 40366/57600 [7:05:32<3:01:27,  1.58it/s]
 70%|███████   | 40367/57600 [7:05:33<3:05:45,  1.55it/s]
 70%|███████   | 40368/57600 [7:05:34<2:58:19,  1.61it/s]
 70%|███████   | 40369/57600 [7:05:34<2:54:45,  1.64it/s]
 70%|███████   | 40370/57600 [7:05:35<2:54:02,  1.65it/s]
 70%|███████   | 40371/57600 [7:05:35<2:55:44,  1.63it/s]
 70%|███████   | 40372/57600 [7:05:36<3:00:39,  1.59it/s]
 70%|███████   | 40373/57600 [7:05:37<3:00:07,  1.59it/s]
 70%|███████   | 40374/57600 [7:05:37<3:05:19,  1.55it/s]
 70%|███████   | 40375/57600 [7:05:38<3:01:05,  1.59it/s]
 70%|███████   | 40376/57600 [7:05:39<2:59:05,  1.60it/s]
 70%|███████   | 40377/57600 [7:05:39<2:57:50,  1.61it/s]
 70%|███████   | 40378/57600 [7:05:40<2:59:07,  1.60it/s]
 70%|███████   | 40379/57600 [7:05:41<2:59:07,  1.60it/s]
 70%|███████   | 40380/57600 [7:05:41<2:55:57,  1.63it/s]
                                                         
{'loss': 1.1261, 'learning_rate': 3.7e-07, 'epoch': 445.7}

 70%|███████   | 40380/57600 [7:05:41<2:55:57,  1.63it/s]
 70%|███████   | 40381/57600 [7:05:42<2:56:28,  1.63it/s]
 70%|███████   | 40382/57600 [7:05:42<2:59:33,  1.60it/s]
 70%|███████   | 40383/57600 [7:05:43<3:00:17,  1.59it/s]
 70%|███████   | 40384/57600 [7:05:44<3:01:12,  1.58it/s]
 70%|███████   | 40385/57600 [7:05:44<2:56:39,  1.62it/s]
 70%|███████   | 40386/57600 [7:05:45<2:55:48,  1.63it/s]
 70%|███████   | 40387/57600 [7:05:46<3:02:32,  1.57it/s]
 70%|███████   | 40388/57600 [7:05:46<3:00:02,  1.59it/s]
 70%|███████   | 40389/57600 [7:05:47<3:00:37,  1.59it/s]
 70%|███████   | 40390/57600 [7:05:47<3:00:17,  1.59it/s]
 70%|███████   | 40391/57600 [7:05:48<3:00:50,  1.59it/s]
 70%|███████   | 40392/57600 [7:05:49<3:02:32,  1.57it/s]
 70%|███████   | 40393/57600 [7:05:49<2:58:08,  1.61it/s]
 70%|███████   | 40394/57600 [7:05:50<3:00:02,  1.59it/s]
 70%|███████   | 40395/57600 [7:05:51<2:58:40,  1.60it/s]
 70%|███████   | 40396/57600 [7:05:51<3:01:01,  1.58it/s]
 70%|███████   | 40397/57600 [7:05:52<3:07:39,  1.53it/s]
 70%|███████   | 40398/57600 [7:05:53<3:09:10,  1.52it/s]
 70%|███████   | 40399/57600 [7:05:53<3:00:31,  1.59it/s]
 70%|███████   | 40400/57600 [7:05:54<3:00:31,  1.59it/s]
                                                         
{'loss': 1.115, 'learning_rate': 3.6968641114982576e-07, 'epoch': 445.92}

 70%|███████   | 40400/57600 [7:05:54<3:00:31,  1.59it/s]
 70%|███████   | 40401/57600 [7:05:54<3:00:11,  1.59it/s]
 70%|███████   | 40402/57600 [7:05:55<3:09:19,  1.51it/s]
 70%|███████   | 40403/57600 [7:05:56<3:08:12,  1.52it/s]
 70%|███████   | 40404/57600 [7:05:56<3:02:42,  1.57it/s]
 70%|███████   | 40405/57600 [7:05:57<3:05:43,  1.54it/s]
 70%|███████   | 40406/57600 [7:05:58<3:01:41,  1.58it/s]
 70%|███████   | 40407/57600 [7:05:58<3:02:36,  1.57it/s]
 70%|███████   | 40408/57600 [7:05:59<3:05:52,  1.54it/s]
 70%|███████   | 40409/57600 [7:06:00<3:07:02,  1.53it/s]
 70%|███████   | 40410/57600 [7:06:00<3:05:52,  1.54it/s]
 70%|███████   | 40411/57600 [7:06:01<3:03:40,  1.56it/s]
 70%|███████   | 40412/57600 [7:06:01<2:59:21,  1.60it/s]
 70%|███████   | 40413/57600 [7:06:02<2:57:40,  1.61it/s]
 70%|███████   | 40414/57600 [7:06:03<2:53:23,  1.65it/s]
 70%|███████   | 40415/57600 [7:06:03<2:55:21,  1.63it/s]
 70%|███████   | 40416/57600 [7:06:04<2:59:24,  1.60it/s]
 70%|███████   | 40417/57600 [7:06:05<2:59:35,  1.59it/s]
 70%|███████   | 40418/57600 [7:06:05<3:04:50,  1.55it/s]
 70%|███████   | 40419/57600 [7:06:06<3:04:46,  1.55it/s]
 70%|███████   | 40420/57600 [7:06:07<3:05:06,  1.55it/s]
                                                         
{'loss': 1.1489, 'learning_rate': 3.6937282229965156e-07, 'epoch': 446.14}

 70%|███████   | 40420/57600 [7:06:07<3:05:06,  1.55it/s]
 70%|███████   | 40421/57600 [7:06:07<3:01:59,  1.57it/s]
 70%|███████   | 40422/57600 [7:06:08<2:54:14,  1.64it/s]
 70%|███████   | 40423/57600 [7:06:08<2:57:54,  1.61it/s]
 70%|███████   | 40424/57600 [7:06:09<2:54:05,  1.64it/s]
 70%|███████   | 40425/57600 [7:06:10<3:01:16,  1.58it/s]
 70%|███████   | 40426/57600 [7:06:10<2:55:46,  1.63it/s]
 70%|███████   | 40427/57600 [7:06:11<2:56:18,  1.62it/s]
 70%|███████   | 40428/57600 [7:06:11<2:53:37,  1.65it/s]
 70%|███████   | 40429/57600 [7:06:12<2:53:21,  1.65it/s]
 70%|███████   | 40430/57600 [7:06:13<2:52:45,  1.66it/s]
 70%|███████   | 40431/57600 [7:06:13<2:53:59,  1.64it/s]
 70%|███████   | 40432/57600 [7:06:14<2:55:53,  1.63it/s]
 70%|███████   | 40433/57600 [7:06:15<2:59:00,  1.60it/s]
 70%|███████   | 40434/57600 [7:06:15<2:57:18,  1.61it/s]
 70%|███████   | 40435/57600 [7:06:16<2:55:43,  1.63it/s]
 70%|███████   | 40436/57600 [7:06:16<2:55:42,  1.63it/s]
 70%|███████   | 40437/57600 [7:06:17<2:53:00,  1.65it/s]
 70%|███████   | 40438/57600 [7:06:18<2:54:31,  1.64it/s]
 70%|███████   | 40439/57600 [7:06:18<2:59:52,  1.59it/s]
 70%|███████   | 40440/57600 [7:06:19<2:59:41,  1.59it/s]
                                                         
{'loss': 1.1683, 'learning_rate': 3.690592334494773e-07, 'epoch': 446.36}

 70%|███████   | 40440/57600 [7:06:19<2:59:41,  1.59it/s]
 70%|███████   | 40441/57600 [7:06:19<2:58:44,  1.60it/s]
 70%|███████   | 40442/57600 [7:06:20<2:56:10,  1.62it/s]
 70%|███████   | 40443/57600 [7:06:21<2:51:59,  1.66it/s]
 70%|███████   | 40444/57600 [7:06:21<2:52:54,  1.65it/s]
 70%|███████   | 40445/57600 [7:06:22<2:53:16,  1.65it/s]
 70%|███████   | 40446/57600 [7:06:22<2:57:25,  1.61it/s]
 70%|███████   | 40447/57600 [7:06:23<3:02:16,  1.57it/s]
 70%|███████   | 40448/57600 [7:06:24<3:08:26,  1.52it/s]
 70%|███████   | 40449/57600 [7:06:25<3:06:09,  1.54it/s]
 70%|███████   | 40450/57600 [7:06:25<3:01:30,  1.57it/s]
 70%|███████   | 40451/57600 [7:06:26<2:58:09,  1.60it/s]
 70%|███████   | 40452/57600 [7:06:26<2:57:06,  1.61it/s]
 70%|███████   | 40453/57600 [7:06:27<2:56:21,  1.62it/s]
 70%|███████   | 40454/57600 [7:06:28<3:03:54,  1.55it/s]
 70%|███████   | 40455/57600 [7:06:28<3:01:35,  1.57it/s]
 70%|███████   | 40456/57600 [7:06:29<2:59:52,  1.59it/s]
 70%|███████   | 40457/57600 [7:06:29<2:58:33,  1.60it/s]
 70%|███████   | 40458/57600 [7:06:30<2:59:42,  1.59it/s]
 70%|███████   | 40459/57600 [7:06:31<3:09:06,  1.51it/s]
 70%|███████   | 40460/57600 [7:06:32<3:13:22,  1.48it/s]
                                                         
{'loss': 1.1336, 'learning_rate': 3.687456445993031e-07, 'epoch': 446.58}

 70%|███████   | 40460/57600 [7:06:32<3:13:22,  1.48it/s]
 70%|███████   | 40461/57600 [7:06:32<3:08:55,  1.51it/s]
 70%|███████   | 40462/57600 [7:06:33<3:07:26,  1.52it/s]
 70%|███████   | 40463/57600 [7:06:33<3:03:55,  1.55it/s]
 70%|███████   | 40464/57600 [7:06:34<2:58:06,  1.60it/s]
 70%|███████   | 40465/57600 [7:06:35<2:59:54,  1.59it/s]
 70%|███████   | 40466/57600 [7:06:35<2:55:56,  1.62it/s]
 70%|███████   | 40467/57600 [7:06:36<2:57:21,  1.61it/s]
 70%|███████   | 40468/57600 [7:06:37<2:59:35,  1.59it/s]
 70%|███████   | 40469/57600 [7:06:37<2:58:45,  1.60it/s]
 70%|███████   | 40470/57600 [7:06:38<3:04:35,  1.55it/s]
 70%|███████   | 40471/57600 [7:06:39<3:05:11,  1.54it/s]
 70%|███████   | 40472/57600 [7:06:39<3:03:14,  1.56it/s]
 70%|███████   | 40473/57600 [7:06:40<2:58:26,  1.60it/s]
 70%|███████   | 40474/57600 [7:06:40<3:05:44,  1.54it/s]
 70%|███████   | 40475/57600 [7:06:41<3:04:41,  1.55it/s]
 70%|███████   | 40476/57600 [7:06:42<3:01:08,  1.58it/s]
 70%|███████   | 40477/57600 [7:06:42<3:03:58,  1.55it/s]
 70%|███████   | 40478/57600 [7:06:43<3:02:20,  1.57it/s]
 70%|███████   | 40479/57600 [7:06:44<3:03:27,  1.56it/s]
 70%|███████   | 40480/57600 [7:06:44<2:58:13,  1.60it/s]
                                                         
{'loss': 1.1252, 'learning_rate': 3.6843205574912887e-07, 'epoch': 446.8}

 70%|███████   | 40480/57600 [7:06:44<2:58:13,  1.60it/s]
 70%|███████   | 40481/57600 [7:06:45<3:03:24,  1.56it/s]
 70%|███████   | 40482/57600 [7:06:45<2:59:22,  1.59it/s]
 70%|███████   | 40483/57600 [7:06:46<3:04:54,  1.54it/s]
 70%|███████   | 40484/57600 [7:06:47<3:06:08,  1.53it/s]
 70%|███████   | 40485/57600 [7:06:47<3:03:16,  1.56it/s]
 70%|███████   | 40486/57600 [7:06:48<3:01:23,  1.57it/s]
 70%|███████   | 40487/57600 [7:06:49<2:59:27,  1.59it/s]
 70%|███████   | 40488/57600 [7:06:49<3:05:01,  1.54it/s]
 70%|███████   | 40489/57600 [7:06:50<3:03:07,  1.56it/s]
 70%|███████   | 40490/57600 [7:06:51<3:00:19,  1.58it/s]
 70%|███████   | 40491/57600 [7:06:51<2:58:11,  1.60it/s]
 70%|███████   | 40492/57600 [7:06:52<3:02:54,  1.56it/s]
 70%|███████   | 40493/57600 [7:06:53<3:00:37,  1.58it/s]
 70%|███████   | 40494/57600 [7:06:53<2:58:26,  1.60it/s]
 70%|███████   | 40495/57600 [7:06:54<2:55:23,  1.63it/s]
 70%|███████   | 40496/57600 [7:06:54<2:53:19,  1.64it/s]
 70%|███████   | 40497/57600 [7:06:55<2:54:03,  1.64it/s]
 70%|███████   | 40498/57600 [7:06:56<2:56:50,  1.61it/s]
 70%|███████   | 40499/57600 [7:06:56<3:06:37,  1.53it/s]
 70%|███████   | 40500/57600 [7:06:57<3:05:01,  1.54it/s]
                                                         
{'loss': 1.1317, 'learning_rate': 3.681184668989547e-07, 'epoch': 447.02}

 70%|███████   | 40500/57600 [7:06:57<3:05:01,  1.54it/s]
 70%|███████   | 40501/57600 [7:06:58<3:00:09,  1.58it/s]
 70%|███████   | 40502/57600 [7:06:58<3:02:15,  1.56it/s]
 70%|███████   | 40503/57600 [7:06:59<3:06:10,  1.53it/s]
 70%|███████   | 40504/57600 [7:06:59<3:01:47,  1.57it/s]
 70%|███████   | 40505/57600 [7:07:00<3:04:44,  1.54it/s]
 70%|███████   | 40506/57600 [7:07:01<3:00:29,  1.58it/s]
 70%|███████   | 40507/57600 [7:07:01<3:03:49,  1.55it/s]
 70%|███████   | 40508/57600 [7:07:02<3:05:19,  1.54it/s]
 70%|███████   | 40509/57600 [7:07:03<3:07:13,  1.52it/s]
 70%|███████   | 40510/57600 [7:07:03<3:12:46,  1.48it/s]
 70%|███████   | 40511/57600 [7:07:04<3:17:32,  1.44it/s]
 70%|███████   | 40512/57600 [7:07:05<3:13:00,  1.48it/s]
 70%|███████   | 40513/57600 [7:07:05<3:06:04,  1.53it/s]
 70%|███████   | 40514/57600 [7:07:06<3:11:34,  1.49it/s]
 70%|███████   | 40515/57600 [7:07:07<3:08:35,  1.51it/s]
 70%|███████   | 40516/57600 [7:07:07<3:03:30,  1.55it/s]
 70%|███████   | 40517/57600 [7:07:08<2:56:40,  1.61it/s]
 70%|███████   | 40518/57600 [7:07:09<3:01:06,  1.57it/s]
 70%|███████   | 40519/57600 [7:07:09<2:58:15,  1.60it/s]
 70%|███████   | 40520/57600 [7:07:10<2:59:52,  1.58it/s]
                                                         
{'loss': 1.1273, 'learning_rate': 3.6780487804878053e-07, 'epoch': 447.24}

 70%|███████   | 40520/57600 [7:07:10<2:59:52,  1.58it/s]
 70%|███████   | 40521/57600 [7:07:10<2:55:54,  1.62it/s]
 70%|███████   | 40522/57600 [7:07:11<2:57:14,  1.61it/s]
 70%|███████   | 40523/57600 [7:07:12<2:56:36,  1.61it/s]
 70%|███████   | 40524/57600 [7:07:12<2:59:25,  1.59it/s]
 70%|███████   | 40525/57600 [7:07:13<2:56:30,  1.61it/s]
 70%|███████   | 40526/57600 [7:07:14<2:58:27,  1.59it/s]
 70%|███████   | 40527/57600 [7:07:14<3:00:05,  1.58it/s]
 70%|███████   | 40528/57600 [7:07:15<2:53:10,  1.64it/s]
 70%|███████   | 40529/57600 [7:07:15<2:56:19,  1.61it/s]
 70%|███████   | 40530/57600 [7:07:16<2:57:39,  1.60it/s]
 70%|███████   | 40531/57600 [7:07:17<3:00:47,  1.57it/s]
 70%|███████   | 40532/57600 [7:07:17<2:59:42,  1.58it/s]
 70%|███████   | 40533/57600 [7:07:18<2:56:22,  1.61it/s]
 70%|███████   | 40534/57600 [7:07:19<2:57:12,  1.61it/s]
 70%|███████   | 40535/57600 [7:07:19<3:01:27,  1.57it/s]
 70%|███████   | 40536/57600 [7:07:20<2:58:54,  1.59it/s]
 70%|███████   | 40537/57600 [7:07:20<2:53:57,  1.63it/s]
 70%|███████   | 40538/57600 [7:07:21<2:55:16,  1.62it/s]
 70%|███████   | 40539/57600 [7:07:22<2:56:55,  1.61it/s]
 70%|███████   | 40540/57600 [7:07:22<2:55:35,  1.62it/s]
                                                         
{'loss': 1.1509, 'learning_rate': 3.6749128919860623e-07, 'epoch': 447.46}

 70%|███████   | 40540/57600 [7:07:22<2:55:35,  1.62it/s]
 70%|███████   | 40541/57600 [7:07:23<2:56:41,  1.61it/s]
 70%|███████   | 40542/57600 [7:07:24<2:54:36,  1.63it/s]
 70%|███████   | 40543/57600 [7:07:24<2:59:34,  1.58it/s]
 70%|███████   | 40544/57600 [7:07:25<2:54:30,  1.63it/s]
 70%|███████   | 40545/57600 [7:07:25<2:52:58,  1.64it/s]
 70%|███████   | 40546/57600 [7:07:26<2:58:10,  1.60it/s]
 70%|███████   | 40547/57600 [7:07:27<2:54:37,  1.63it/s]
 70%|███████   | 40548/57600 [7:07:27<3:09:31,  1.50it/s]
 70%|███████   | 40549/57600 [7:07:28<3:09:46,  1.50it/s]
 70%|███████   | 40550/57600 [7:07:29<3:05:01,  1.54it/s]
 70%|███████   | 40551/57600 [7:07:29<3:01:26,  1.57it/s]
 70%|███████   | 40552/57600 [7:07:30<2:55:35,  1.62it/s]
 70%|███████   | 40553/57600 [7:07:30<2:52:09,  1.65it/s]
 70%|███████   | 40554/57600 [7:07:31<2:47:37,  1.69it/s]
 70%|███████   | 40555/57600 [7:07:32<2:57:07,  1.60it/s]
 70%|███████   | 40556/57600 [7:07:32<2:56:40,  1.61it/s]
 70%|███████   | 40557/57600 [7:07:33<2:57:43,  1.60it/s]
 70%|███████   | 40558/57600 [7:07:34<2:56:56,  1.61it/s]
 70%|███████   | 40559/57600 [7:07:34<2:55:09,  1.62it/s]
 70%|███████   | 40560/57600 [7:07:35<2:53:31,  1.64it/s]
                                                         
{'loss': 1.1495, 'learning_rate': 3.6717770034843204e-07, 'epoch': 447.68}

 70%|███████   | 40560/57600 [7:07:35<2:53:31,  1.64it/s]
 70%|███████   | 40561/57600 [7:07:35<2:58:20,  1.59it/s]
 70%|███████   | 40562/57600 [7:07:36<3:00:05,  1.58it/s]
 70%|███████   | 40563/57600 [7:07:37<3:02:50,  1.55it/s]
 70%|███████   | 40564/57600 [7:07:37<3:00:17,  1.57it/s]
 70%|███████   | 40565/57600 [7:07:38<2:54:44,  1.62it/s]
 70%|███████   | 40566/57600 [7:07:39<2:52:39,  1.64it/s]
 70%|███████   | 40567/57600 [7:07:39<2:57:25,  1.60it/s]
 70%|███████   | 40568/57600 [7:07:40<2:57:06,  1.60it/s]
 70%|███████   | 40569/57600 [7:07:40<2:53:53,  1.63it/s]
 70%|███████   | 40570/57600 [7:07:41<2:58:52,  1.59it/s]
 70%|███████   | 40571/57600 [7:07:42<2:58:50,  1.59it/s]
 70%|███████   | 40572/57600 [7:07:42<2:59:07,  1.58it/s]
 70%|███████   | 40573/57600 [7:07:43<2:59:12,  1.58it/s]
 70%|███████   | 40574/57600 [7:07:44<2:55:21,  1.62it/s]
 70%|███████   | 40575/57600 [7:07:44<2:51:52,  1.65it/s]
 70%|███████   | 40576/57600 [7:07:45<2:56:06,  1.61it/s]
 70%|███████   | 40577/57600 [7:07:45<2:58:28,  1.59it/s]
 70%|███████   | 40578/57600 [7:07:46<2:58:27,  1.59it/s]
 70%|███████   | 40579/57600 [7:07:47<3:02:41,  1.55it/s]
 70%|███████   | 40580/57600 [7:07:47<3:02:37,  1.55it/s]
                                                         
{'loss': 1.1304, 'learning_rate': 3.668641114982578e-07, 'epoch': 447.9}

 70%|███████   | 40580/57600 [7:07:47<3:02:37,  1.55it/s]
 70%|███████   | 40581/57600 [7:07:48<3:00:13,  1.57it/s]
 70%|███████   | 40582/57600 [7:07:49<3:05:23,  1.53it/s]
 70%|███████   | 40583/57600 [7:07:49<3:00:20,  1.57it/s]
 70%|███████   | 40584/57600 [7:07:50<3:02:19,  1.56it/s]
 70%|███████   | 40585/57600 [7:07:51<2:59:20,  1.58it/s]
 70%|███████   | 40586/57600 [7:07:51<2:53:04,  1.64it/s]
 70%|███████   | 40587/57600 [7:07:52<2:55:59,  1.61it/s]
 70%|███████   | 40588/57600 [7:07:52<2:51:41,  1.65it/s]
 70%|███████   | 40589/57600 [7:07:53<3:02:50,  1.55it/s]
 70%|███████   | 40590/57600 [7:07:54<3:01:25,  1.56it/s]
 70%|███████   | 40591/57600 [7:07:54<3:00:36,  1.57it/s]
 70%|███████   | 40592/57600 [7:07:55<2:54:59,  1.62it/s]
 70%|███████   | 40593/57600 [7:07:56<2:57:56,  1.59it/s]
 70%|███████   | 40594/57600 [7:07:56<2:55:57,  1.61it/s]
 70%|███████   | 40595/57600 [7:07:57<2:59:10,  1.58it/s]
 70%|███████   | 40596/57600 [7:07:57<3:00:12,  1.57it/s]
 70%|███████   | 40597/57600 [7:07:58<3:05:17,  1.53it/s]
 70%|███████   | 40598/57600 [7:07:59<3:04:35,  1.54it/s]
 70%|███████   | 40599/57600 [7:07:59<2:58:56,  1.58it/s]
 70%|███████   | 40600/57600 [7:08:00<2:57:05,  1.60it/s]
                                                         
{'loss': 1.1187, 'learning_rate': 3.665505226480836e-07, 'epoch': 448.12}

 70%|███████   | 40600/57600 [7:08:00<2:57:05,  1.60it/s]
 70%|███████   | 40601/57600 [7:08:01<2:58:47,  1.58it/s]
 70%|███████   | 40602/57600 [7:08:01<3:05:02,  1.53it/s]
 70%|███████   | 40603/57600 [7:08:02<3:06:57,  1.52it/s]
 70%|███████   | 40604/57600 [7:08:03<3:03:01,  1.55it/s]
 70%|███████   | 40605/57600 [7:08:03<3:07:17,  1.51it/s]
 70%|███████   | 40606/57600 [7:08:04<3:03:45,  1.54it/s]
 70%|███████   | 40607/57600 [7:08:05<3:03:33,  1.54it/s]
 70%|███████   | 40608/57600 [7:08:05<2:57:19,  1.60it/s]
 71%|███████   | 40609/57600 [7:08:06<2:56:38,  1.60it/s]
 71%|███████   | 40610/57600 [7:08:06<2:59:15,  1.58it/s]
 71%|███████   | 40611/57600 [7:08:07<2:54:51,  1.62it/s]
 71%|███████   | 40612/57600 [7:08:08<2:53:20,  1.63it/s]
 71%|███████   | 40613/57600 [7:08:08<2:53:19,  1.63it/s]
 71%|███████   | 40614/57600 [7:08:09<2:53:25,  1.63it/s]
 71%|███████   | 40615/57600 [7:08:10<3:02:26,  1.55it/s]
 71%|███████   | 40616/57600 [7:08:10<2:59:02,  1.58it/s]
 71%|███████   | 40617/57600 [7:08:11<3:02:53,  1.55it/s]
 71%|███████   | 40618/57600 [7:08:11<2:58:27,  1.59it/s]
 71%|███████   | 40619/57600 [7:08:12<2:57:15,  1.60it/s]
 71%|███████   | 40620/57600 [7:08:13<2:57:54,  1.59it/s]
                                                         
{'loss': 1.1221, 'learning_rate': 3.6623693379790935e-07, 'epoch': 448.34}

 71%|███████   | 40620/57600 [7:08:13<2:57:54,  1.59it/s]
 71%|███████   | 40621/57600 [7:08:13<2:59:59,  1.57it/s]
 71%|███████   | 40622/57600 [7:08:14<2:59:58,  1.57it/s]
 71%|███████   | 40623/57600 [7:08:15<2:58:08,  1.59it/s]
 71%|███████   | 40624/57600 [7:08:15<3:02:38,  1.55it/s]
 71%|███████   | 40625/57600 [7:08:16<3:05:09,  1.53it/s]
 71%|███████   | 40626/57600 [7:08:17<3:00:20,  1.57it/s]
 71%|███████   | 40627/57600 [7:08:17<2:56:23,  1.60it/s]
 71%|███████   | 40628/57600 [7:08:18<2:49:44,  1.67it/s]
 71%|███████   | 40629/57600 [7:08:18<2:51:36,  1.65it/s]
 71%|███████   | 40630/57600 [7:08:19<2:47:57,  1.68it/s]
 71%|███████   | 40631/57600 [7:08:20<2:56:14,  1.60it/s]
 71%|███████   | 40632/57600 [7:08:20<2:55:22,  1.61it/s]
 71%|███████   | 40633/57600 [7:08:21<2:54:58,  1.62it/s]
 71%|███████   | 40634/57600 [7:08:21<2:56:50,  1.60it/s]
 71%|███████   | 40635/57600 [7:08:22<2:57:22,  1.59it/s]
 71%|███████   | 40636/57600 [7:08:23<2:59:39,  1.57it/s]
 71%|███████   | 40637/57600 [7:08:23<2:56:52,  1.60it/s]
 71%|███████   | 40638/57600 [7:08:24<2:58:55,  1.58it/s]
 71%|███████   | 40639/57600 [7:08:25<2:52:55,  1.63it/s]
 71%|███████   | 40640/57600 [7:08:25<2:54:46,  1.62it/s]
                                                         
{'loss': 1.1638, 'learning_rate': 3.6592334494773515e-07, 'epoch': 448.57}

 71%|███████   | 40640/57600 [7:08:25<2:54:46,  1.62it/s]
 71%|███████   | 40641/57600 [7:08:26<3:04:27,  1.53it/s]
 71%|███████   | 40642/57600 [7:08:27<2:59:30,  1.57it/s]
 71%|███████   | 40643/57600 [7:08:27<3:02:24,  1.55it/s]
 71%|███████   | 40644/57600 [7:08:28<2:59:21,  1.58it/s]
 71%|███████   | 40645/57600 [7:08:28<2:58:15,  1.59it/s]
 71%|███████   | 40646/57600 [7:08:29<2:55:15,  1.61it/s]
 71%|███████   | 40647/57600 [7:08:30<3:00:25,  1.57it/s]
 71%|███████   | 40648/57600 [7:08:30<2:57:43,  1.59it/s]
 71%|███████   | 40649/57600 [7:08:31<2:54:42,  1.62it/s]
 71%|███████   | 40650/57600 [7:08:32<2:58:47,  1.58it/s]
 71%|███████   | 40651/57600 [7:08:32<2:55:04,  1.61it/s]
 71%|███████   | 40652/57600 [7:08:33<3:00:53,  1.56it/s]
 71%|███████   | 40653/57600 [7:08:33<2:57:31,  1.59it/s]
 71%|███████   | 40654/57600 [7:08:34<2:53:42,  1.63it/s]
 71%|███████   | 40655/57600 [7:08:35<2:53:38,  1.63it/s]
 71%|███████   | 40656/57600 [7:08:35<2:54:19,  1.62it/s]
 71%|███████   | 40657/57600 [7:08:36<2:56:30,  1.60it/s]
 71%|███████   | 40658/57600 [7:08:37<2:59:02,  1.58it/s]
 71%|███████   | 40659/57600 [7:08:37<2:58:05,  1.59it/s]
 71%|███████   | 40660/57600 [7:08:38<3:02:00,  1.55it/s]
                                                         
{'loss': 1.1179, 'learning_rate': 3.65609756097561e-07, 'epoch': 448.79}

 71%|███████   | 40660/57600 [7:08:38<3:02:00,  1.55it/s]
 71%|███████   | 40661/57600 [7:08:39<3:06:07,  1.52it/s]
 71%|███████   | 40662/57600 [7:08:39<3:04:20,  1.53it/s]
 71%|███████   | 40663/57600 [7:08:40<2:58:07,  1.58it/s]
 71%|███████   | 40664/57600 [7:08:40<3:00:57,  1.56it/s]
 71%|███████   | 40665/57600 [7:08:41<2:57:00,  1.59it/s]
 71%|███████   | 40666/57600 [7:08:42<2:53:20,  1.63it/s]
 71%|███████   | 40667/57600 [7:08:42<2:54:58,  1.61it/s]
 71%|███████   | 40668/57600 [7:08:43<3:00:46,  1.56it/s]
 71%|███████   | 40669/57600 [7:08:44<2:58:58,  1.58it/s]
 71%|███████   | 40670/57600 [7:08:44<2:58:32,  1.58it/s]
 71%|███████   | 40671/57600 [7:08:45<2:52:21,  1.64it/s]
 71%|███████   | 40672/57600 [7:08:45<2:49:16,  1.67it/s]
 71%|███████   | 40673/57600 [7:08:46<2:59:20,  1.57it/s]
 71%|███████   | 40674/57600 [7:08:47<2:54:06,  1.62it/s]
 71%|███████   | 40675/57600 [7:08:47<2:51:47,  1.64it/s]
 71%|███████   | 40676/57600 [7:08:48<2:49:44,  1.66it/s]
 71%|███████   | 40677/57600 [7:08:48<2:52:00,  1.64it/s]
 71%|███████   | 40678/57600 [7:08:49<2:50:34,  1.65it/s]
 71%|███████   | 40679/57600 [7:08:50<2:47:28,  1.68it/s]
 71%|███████   | 40680/57600 [7:08:50<2:59:19,  1.57it/s]
                                                         
{'loss': 1.131, 'learning_rate': 3.652961672473867e-07, 'epoch': 449.01}

 71%|███████   | 40680/57600 [7:08:50<2:59:19,  1.57it/s]
 71%|███████   | 40681/57600 [7:08:51<2:57:20,  1.59it/s]
 71%|███████   | 40682/57600 [7:08:52<2:55:56,  1.60it/s]
 71%|███████   | 40683/57600 [7:08:52<3:05:41,  1.52it/s]
 71%|███████   | 40684/57600 [7:08:53<3:03:06,  1.54it/s]
 71%|███████   | 40685/57600 [7:08:54<3:04:09,  1.53it/s]
 71%|███████   | 40686/57600 [7:08:54<3:02:33,  1.54it/s]
 71%|███████   | 40687/57600 [7:08:55<2:55:12,  1.61it/s]
 71%|███████   | 40688/57600 [7:08:55<2:50:47,  1.65it/s]
 71%|███████   | 40689/57600 [7:08:56<2:47:57,  1.68it/s]
 71%|███████   | 40690/57600 [7:08:57<2:51:11,  1.65it/s]
 71%|███████   | 40691/57600 [7:08:57<2:50:13,  1.66it/s]
 71%|███████   | 40692/57600 [7:08:58<2:51:36,  1.64it/s]
 71%|███████   | 40693/57600 [7:08:58<2:58:36,  1.58it/s]
 71%|███████   | 40694/57600 [7:08:59<2:59:36,  1.57it/s]
 71%|███████   | 40695/57600 [7:09:00<2:56:18,  1.60it/s]
 71%|███████   | 40696/57600 [7:09:00<2:56:34,  1.60it/s]
 71%|███████   | 40697/57600 [7:09:01<2:50:58,  1.65it/s]
 71%|███████   | 40698/57600 [7:09:02<2:50:30,  1.65it/s]
 71%|███████   | 40699/57600 [7:09:02<2:50:26,  1.65it/s]
 71%|███████   | 40700/57600 [7:09:03<2:52:58,  1.63it/s]
                                                         
{'loss': 1.1289, 'learning_rate': 3.6498257839721256e-07, 'epoch': 449.23}

 71%|███████   | 40700/57600 [7:09:03<2:52:58,  1.63it/s]
 71%|███████   | 40701/57600 [7:09:03<2:55:33,  1.60it/s]
 71%|███████   | 40702/57600 [7:09:04<2:51:53,  1.64it/s]
 71%|███████   | 40703/57600 [7:09:05<2:49:19,  1.66it/s]
 71%|███████   | 40704/57600 [7:09:05<2:49:56,  1.66it/s]
 71%|███████   | 40705/57600 [7:09:06<2:51:17,  1.64it/s]
 71%|███████   | 40706/57600 [7:09:06<2:56:21,  1.60it/s]
 71%|███████   | 40707/57600 [7:09:07<2:58:39,  1.58it/s]
 71%|███████   | 40708/57600 [7:09:08<2:58:39,  1.58it/s]
 71%|███████   | 40709/57600 [7:09:08<3:06:29,  1.51it/s]
 71%|███████   | 40710/57600 [7:09:09<3:09:15,  1.49it/s]
 71%|███████   | 40711/57600 [7:09:10<3:11:51,  1.47it/s]
 71%|███████   | 40712/57600 [7:09:10<3:05:57,  1.51it/s]
 71%|███████   | 40713/57600 [7:09:11<3:03:19,  1.54it/s]
 71%|███████   | 40714/57600 [7:09:12<3:11:00,  1.47it/s]
 71%|███████   | 40715/57600 [7:09:12<3:04:44,  1.52it/s]
 71%|███████   | 40716/57600 [7:09:13<2:57:26,  1.59it/s]
 71%|███████   | 40717/57600 [7:09:14<2:53:59,  1.62it/s]
 71%|███████   | 40718/57600 [7:09:14<3:00:23,  1.56it/s]
 71%|███████   | 40719/57600 [7:09:15<2:53:42,  1.62it/s]
 71%|███████   | 40720/57600 [7:09:16<2:56:31,  1.59it/s]
                                                         
{'loss': 1.1436, 'learning_rate': 3.6466898954703826e-07, 'epoch': 449.45}

 71%|███████   | 40720/57600 [7:09:16<2:56:31,  1.59it/s]
 71%|███████   | 40721/57600 [7:09:16<2:55:04,  1.61it/s]
 71%|███████   | 40722/57600 [7:09:17<2:53:00,  1.63it/s]
 71%|███████   | 40723/57600 [7:09:17<2:53:10,  1.62it/s]
 71%|███████   | 40724/57600 [7:09:18<2:56:21,  1.59it/s]
 71%|███████   | 40725/57600 [7:09:19<3:04:42,  1.52it/s]
 71%|███████   | 40726/57600 [7:09:19<3:03:15,  1.53it/s]
 71%|███████   | 40727/57600 [7:09:20<3:00:50,  1.56it/s]
 71%|███████   | 40728/57600 [7:09:21<3:02:08,  1.54it/s]
 71%|███████   | 40729/57600 [7:09:21<3:04:02,  1.53it/s]
 71%|███████   | 40730/57600 [7:09:22<3:00:04,  1.56it/s]
 71%|███████   | 40731/57600 [7:09:23<3:01:15,  1.55it/s]
 71%|███████   | 40732/57600 [7:09:23<3:00:06,  1.56it/s]
 71%|███████   | 40733/57600 [7:09:24<3:03:04,  1.54it/s]
 71%|███████   | 40734/57600 [7:09:25<3:06:29,  1.51it/s]
 71%|███████   | 40735/57600 [7:09:25<3:03:52,  1.53it/s]
 71%|███████   | 40736/57600 [7:09:26<2:59:54,  1.56it/s]
 71%|███████   | 40737/57600 [7:09:26<3:00:47,  1.55it/s]
 71%|███████   | 40738/57600 [7:09:27<3:00:11,  1.56it/s]
 71%|███████   | 40739/57600 [7:09:28<2:57:06,  1.59it/s]
 71%|███████   | 40740/57600 [7:09:28<2:54:36,  1.61it/s]
                                                         
{'loss': 1.1178, 'learning_rate': 3.643554006968641e-07, 'epoch': 449.67}

 71%|███████   | 40740/57600 [7:09:28<2:54:36,  1.61it/s]
 71%|███████   | 40741/57600 [7:09:29<2:53:00,  1.62it/s]
 71%|███████   | 40742/57600 [7:09:30<2:54:00,  1.61it/s]
 71%|███████   | 40743/57600 [7:09:30<2:51:50,  1.64it/s]
 71%|███████   | 40744/57600 [7:09:31<2:54:48,  1.61it/s]
 71%|███████   | 40745/57600 [7:09:31<2:55:11,  1.60it/s]
 71%|███████   | 40746/57600 [7:09:32<2:55:23,  1.60it/s]
 71%|███████   | 40747/57600 [7:09:33<2:49:39,  1.66it/s]
 71%|███████   | 40748/57600 [7:09:33<2:57:01,  1.59it/s]
 71%|███████   | 40749/57600 [7:09:34<2:57:54,  1.58it/s]
 71%|███████   | 40750/57600 [7:09:35<2:56:22,  1.59it/s]
 71%|███████   | 40751/57600 [7:09:35<2:51:37,  1.64it/s]
 71%|███████   | 40752/57600 [7:09:36<3:00:12,  1.56it/s]
 71%|███████   | 40753/57600 [7:09:36<2:56:17,  1.59it/s]
 71%|███████   | 40754/57600 [7:09:37<2:58:34,  1.57it/s]
 71%|███████   | 40755/57600 [7:09:38<2:59:31,  1.56it/s]
 71%|███████   | 40756/57600 [7:09:38<2:58:11,  1.58it/s]
 71%|███████   | 40757/57600 [7:09:39<2:56:41,  1.59it/s]
 71%|███████   | 40758/57600 [7:09:40<2:54:15,  1.61it/s]
 71%|███████   | 40759/57600 [7:09:40<2:59:41,  1.56it/s]
 71%|███████   | 40760/57600 [7:09:41<2:57:56,  1.58it/s]
                                                         
{'loss': 1.1459, 'learning_rate': 3.640418118466899e-07, 'epoch': 449.89}

 71%|███████   | 40760/57600 [7:09:41<2:57:56,  1.58it/s]
 71%|███████   | 40761/57600 [7:09:41<2:56:18,  1.59it/s]
 71%|███████   | 40762/57600 [7:09:42<2:52:34,  1.63it/s]
 71%|███████   | 40763/57600 [7:09:43<2:54:03,  1.61it/s]
 71%|███████   | 40764/57600 [7:09:43<2:53:17,  1.62it/s]
 71%|███████   | 40765/57600 [7:09:44<2:51:23,  1.64it/s]
 71%|███████   | 40766/57600 [7:09:44<2:48:17,  1.67it/s]
 71%|███████   | 40767/57600 [7:09:45<2:54:31,  1.61it/s]
 71%|███████   | 40768/57600 [7:09:46<2:51:04,  1.64it/s]
 71%|███████   | 40769/57600 [7:09:46<2:53:42,  1.61it/s]
 71%|███████   | 40770/57600 [7:09:47<2:52:08,  1.63it/s]
 71%|███████   | 40771/57600 [7:09:48<2:55:48,  1.60it/s]
 71%|███████   | 40772/57600 [7:09:48<3:01:47,  1.54it/s]
 71%|███████   | 40773/57600 [7:09:49<2:58:37,  1.57it/s]
 71%|███████   | 40774/57600 [7:09:50<2:59:02,  1.57it/s]
 71%|███████   | 40775/57600 [7:09:50<2:57:14,  1.58it/s]
 71%|███████   | 40776/57600 [7:09:51<2:54:36,  1.61it/s]
 71%|███████   | 40777/57600 [7:09:52<3:01:00,  1.55it/s]
 71%|███████   | 40778/57600 [7:09:52<3:01:42,  1.54it/s]
 71%|███████   | 40779/57600 [7:09:53<3:02:51,  1.53it/s]
 71%|███████   | 40780/57600 [7:09:53<2:56:55,  1.58it/s]
                                                         
{'loss': 1.1443, 'learning_rate': 3.637282229965157e-07, 'epoch': 450.11}

 71%|███████   | 40780/57600 [7:09:53<2:56:55,  1.58it/s]
 71%|███████   | 40781/57600 [7:09:54<2:57:25,  1.58it/s]
 71%|███████   | 40782/57600 [7:09:55<2:53:21,  1.62it/s]
 71%|███████   | 40783/57600 [7:09:55<2:53:05,  1.62it/s]
 71%|███████   | 40784/57600 [7:09:56<2:59:12,  1.56it/s]
 71%|███████   | 40785/57600 [7:09:57<3:00:29,  1.55it/s]
 71%|███████   | 40786/57600 [7:09:57<3:02:43,  1.53it/s]
 71%|███████   | 40787/57600 [7:09:58<2:57:18,  1.58it/s]
 71%|███████   | 40788/57600 [7:09:58<2:53:20,  1.62it/s]
 71%|███████   | 40789/57600 [7:09:59<2:53:56,  1.61it/s]
 71%|███████   | 40790/57600 [7:10:00<2:46:34,  1.68it/s]
 71%|███████   | 40791/57600 [7:10:00<2:57:10,  1.58it/s]
 71%|███████   | 40792/57600 [7:10:01<2:55:06,  1.60it/s]
 71%|███████   | 40793/57600 [7:10:02<2:59:14,  1.56it/s]
 71%|███████   | 40794/57600 [7:10:02<2:59:12,  1.56it/s]
 71%|███████   | 40795/57600 [7:10:03<3:03:42,  1.52it/s]
 71%|███████   | 40796/57600 [7:10:04<3:02:04,  1.54it/s]
 71%|███████   | 40797/57600 [7:10:04<3:03:15,  1.53it/s]
 71%|███████   | 40798/57600 [7:10:05<2:58:53,  1.57it/s]
 71%|███████   | 40799/57600 [7:10:05<3:00:45,  1.55it/s]
 71%|███████   | 40800/57600 [7:10:06<3:02:15,  1.54it/s]
                                                         
{'loss': 1.1279, 'learning_rate': 3.634146341463415e-07, 'epoch': 450.33}

 71%|███████   | 40800/57600 [7:10:06<3:02:15,  1.54it/s]
 71%|███████   | 40801/57600 [7:10:07<3:06:31,  1.50it/s]
 71%|███████   | 40802/57600 [7:10:07<3:03:17,  1.53it/s]
 71%|███████   | 40803/57600 [7:10:08<3:01:13,  1.54it/s]
 71%|███████   | 40804/57600 [7:10:09<3:03:17,  1.53it/s]
 71%|███████   | 40805/57600 [7:10:09<3:00:47,  1.55it/s]
 71%|███████   | 40806/57600 [7:10:10<2:53:55,  1.61it/s]
 71%|███████   | 40807/57600 [7:10:11<2:55:12,  1.60it/s]
 71%|███████   | 40808/57600 [7:10:11<2:51:42,  1.63it/s]
 71%|███████   | 40809/57600 [7:10:12<2:55:10,  1.60it/s]
 71%|███████   | 40810/57600 [7:10:12<2:55:31,  1.59it/s]
 71%|███████   | 40811/57600 [7:10:13<2:50:07,  1.64it/s]
 71%|███████   | 40812/57600 [7:10:14<2:50:13,  1.64it/s]
 71%|███████   | 40813/57600 [7:10:14<2:52:29,  1.62it/s]
 71%|███████   | 40814/57600 [7:10:15<2:55:46,  1.59it/s]
 71%|███████   | 40815/57600 [7:10:16<2:58:36,  1.57it/s]
 71%|███████   | 40816/57600 [7:10:16<2:56:03,  1.59it/s]
 71%|███████   | 40817/57600 [7:10:17<2:55:14,  1.60it/s]
 71%|███████   | 40818/57600 [7:10:17<2:51:41,  1.63it/s]
 71%|███████   | 40819/57600 [7:10:18<2:53:51,  1.61it/s]
 71%|███████   | 40820/57600 [7:10:19<2:51:54,  1.63it/s]
                                                         
{'loss': 1.1468, 'learning_rate': 3.631010452961672e-07, 'epoch': 450.55}

 71%|███████   | 40820/57600 [7:10:19<2:51:54,  1.63it/s]
 71%|███████   | 40821/57600 [7:10:19<2:47:33,  1.67it/s]
 71%|███████   | 40822/57600 [7:10:20<2:55:36,  1.59it/s]
 71%|███████   | 40823/57600 [7:10:21<2:56:24,  1.59it/s]
 71%|███████   | 40824/57600 [7:10:21<2:58:31,  1.57it/s]
 71%|███████   | 40825/57600 [7:10:22<2:55:34,  1.59it/s]
 71%|███████   | 40826/57600 [7:10:22<2:58:54,  1.56it/s]
 71%|███████   | 40827/57600 [7:10:23<2:56:39,  1.58it/s]
 71%|███████   | 40828/57600 [7:10:24<2:53:52,  1.61it/s]
 71%|███████   | 40829/57600 [7:10:24<2:51:44,  1.63it/s]
 71%|███████   | 40830/57600 [7:10:25<2:50:45,  1.64it/s]
 71%|███████   | 40831/57600 [7:10:26<2:54:02,  1.61it/s]
 71%|███████   | 40832/57600 [7:10:26<2:51:52,  1.63it/s]
 71%|███████   | 40833/57600 [7:10:27<2:52:20,  1.62it/s]
 71%|███████   | 40834/57600 [7:10:27<2:50:27,  1.64it/s]
 71%|███████   | 40835/57600 [7:10:28<2:50:38,  1.64it/s]
 71%|███████   | 40836/57600 [7:10:29<2:54:39,  1.60it/s]
 71%|███████   | 40837/57600 [7:10:29<2:52:13,  1.62it/s]
 71%|███████   | 40838/57600 [7:10:30<2:47:22,  1.67it/s]
 71%|███████   | 40839/57600 [7:10:30<2:54:47,  1.60it/s]
 71%|███████   | 40840/57600 [7:10:31<2:54:43,  1.60it/s]
                                                         
{'loss': 1.1435, 'learning_rate': 3.627874564459931e-07, 'epoch': 450.77}

 71%|███████   | 40840/57600 [7:10:31<2:54:43,  1.60it/s]
 71%|███████   | 40841/57600 [7:10:32<2:55:09,  1.59it/s]
 71%|███████   | 40842/57600 [7:10:32<2:54:23,  1.60it/s]
 71%|███████   | 40843/57600 [7:10:33<2:56:50,  1.58it/s]
 71%|███████   | 40844/57600 [7:10:34<2:55:50,  1.59it/s]
 71%|███████   | 40845/57600 [7:10:34<2:52:03,  1.62it/s]
 71%|███████   | 40846/57600 [7:10:35<2:50:44,  1.64it/s]
 71%|███████   | 40847/57600 [7:10:35<2:48:13,  1.66it/s]
 71%|███████   | 40848/57600 [7:10:36<2:53:31,  1.61it/s]
 71%|███████   | 40849/57600 [7:10:37<2:47:55,  1.66it/s]
 71%|███████   | 40850/57600 [7:10:37<2:49:48,  1.64it/s]
 71%|███████   | 40851/57600 [7:10:38<2:47:20,  1.67it/s]
 71%|███████   | 40852/57600 [7:10:38<2:49:01,  1.65it/s]
 71%|███████   | 40853/57600 [7:10:39<2:46:43,  1.67it/s]
 71%|███████   | 40854/57600 [7:10:40<2:51:30,  1.63it/s]
 71%|███████   | 40855/57600 [7:10:40<2:52:15,  1.62it/s]
 71%|███████   | 40856/57600 [7:10:41<2:51:04,  1.63it/s]
 71%|███████   | 40857/57600 [7:10:42<2:53:04,  1.61it/s]
 71%|███████   | 40858/57600 [7:10:42<2:51:13,  1.63it/s]
 71%|███████   | 40859/57600 [7:10:43<2:50:08,  1.64it/s]
 71%|███████   | 40860/57600 [7:10:43<2:52:41,  1.62it/s]
                                                         
{'loss': 1.189, 'learning_rate': 3.6247386759581874e-07, 'epoch': 450.99}

 71%|███████   | 40860/57600 [7:10:43<2:52:41,  1.62it/s]
 71%|███████   | 40861/57600 [7:10:44<3:07:14,  1.49it/s]
 71%|███████   | 40862/57600 [7:10:45<3:04:08,  1.51it/s]
 71%|███████   | 40863/57600 [7:10:45<2:57:00,  1.58it/s]
 71%|███████   | 40864/57600 [7:10:46<2:53:08,  1.61it/s]
 71%|███████   | 40865/57600 [7:10:47<2:50:07,  1.64it/s]
 71%|███████   | 40866/57600 [7:10:47<2:51:36,  1.63it/s]
 71%|███████   | 40867/57600 [7:10:48<2:51:32,  1.63it/s]
 71%|███████   | 40868/57600 [7:10:48<2:54:13,  1.60it/s]
 71%|███████   | 40869/57600 [7:10:49<2:53:40,  1.61it/s]
 71%|███████   | 40870/57600 [7:10:50<2:57:08,  1.57it/s]
 71%|███████   | 40871/57600 [7:10:50<3:03:56,  1.52it/s]
 71%|███████   | 40872/57600 [7:10:51<3:00:15,  1.55it/s]
 71%|███████   | 40873/57600 [7:10:52<2:56:34,  1.58it/s]
 71%|███████   | 40874/57600 [7:10:52<2:54:47,  1.59it/s]
 71%|███████   | 40875/57600 [7:10:53<2:49:56,  1.64it/s]
 71%|███████   | 40876/57600 [7:10:53<2:54:55,  1.59it/s]
 71%|███████   | 40877/57600 [7:10:54<2:50:36,  1.63it/s]
 71%|███████   | 40878/57600 [7:10:55<2:55:27,  1.59it/s]
 71%|███████   | 40879/57600 [7:10:55<2:51:59,  1.62it/s]
 71%|███████   | 40880/57600 [7:10:56<2:51:52,  1.62it/s]
                                                         
{'loss': 1.1308, 'learning_rate': 3.621602787456446e-07, 'epoch': 451.21}

 71%|███████   | 40880/57600 [7:10:56<2:51:52,  1.62it/s]
 71%|███████   | 40881/57600 [7:10:57<2:52:08,  1.62it/s]
 71%|███████   | 40882/57600 [7:10:57<2:55:53,  1.58it/s]
 71%|███████   | 40883/57600 [7:10:58<2:51:45,  1.62it/s]
 71%|███████   | 40884/57600 [7:10:58<2:49:30,  1.64it/s]
 71%|███████   | 40885/57600 [7:10:59<2:49:18,  1.65it/s]
 71%|███████   | 40886/57600 [7:11:00<2:48:38,  1.65it/s]
 71%|███████   | 40887/57600 [7:11:00<2:55:09,  1.59it/s]
 71%|███████   | 40888/57600 [7:11:01<2:52:31,  1.61it/s]
 71%|███████   | 40889/57600 [7:11:01<2:50:27,  1.63it/s]
 71%|███████   | 40890/57600 [7:11:02<2:50:57,  1.63it/s]
 71%|███████   | 40891/57600 [7:11:03<2:52:52,  1.61it/s]
 71%|███████   | 40892/57600 [7:11:03<2:51:57,  1.62it/s]
 71%|███████   | 40893/57600 [7:11:04<2:53:49,  1.60it/s]
 71%|███████   | 40894/57600 [7:11:05<2:54:50,  1.59it/s]
 71%|███████   | 40895/57600 [7:11:05<2:56:49,  1.57it/s]
 71%|███████   | 40896/57600 [7:11:06<2:58:43,  1.56it/s]
 71%|███████   | 40897/57600 [7:11:07<2:56:42,  1.58it/s]
 71%|███████   | 40898/57600 [7:11:07<2:57:16,  1.57it/s]
 71%|███████   | 40899/57600 [7:11:08<2:59:29,  1.55it/s]
 71%|███████   | 40900/57600 [7:11:08<2:54:51,  1.59it/s]
                                                         
{'loss': 1.1471, 'learning_rate': 3.618466898954704e-07, 'epoch': 451.43}

 71%|███████   | 40900/57600 [7:11:08<2:54:51,  1.59it/s]
 71%|███████   | 40901/57600 [7:11:09<2:58:19,  1.56it/s]
 71%|███████   | 40902/57600 [7:11:10<2:58:46,  1.56it/s]
 71%|███████   | 40903/57600 [7:11:10<2:58:24,  1.56it/s]
 71%|███████   | 40904/57600 [7:11:11<2:52:27,  1.61it/s]
 71%|███████   | 40905/57600 [7:11:12<2:54:18,  1.60it/s]
 71%|███████   | 40906/57600 [7:11:12<2:52:53,  1.61it/s]
 71%|███████   | 40907/57600 [7:11:13<2:51:57,  1.62it/s]
 71%|███████   | 40908/57600 [7:11:13<2:48:29,  1.65it/s]
 71%|███████   | 40909/57600 [7:11:14<2:50:37,  1.63it/s]
 71%|███████   | 40910/57600 [7:11:15<2:57:16,  1.57it/s]
 71%|███████   | 40911/57600 [7:11:15<2:55:35,  1.58it/s]
 71%|███████   | 40912/57600 [7:11:16<3:00:13,  1.54it/s]
 71%|███████   | 40913/57600 [7:11:17<2:58:21,  1.56it/s]
 71%|███████   | 40914/57600 [7:11:17<2:54:42,  1.59it/s]
 71%|███████   | 40915/57600 [7:11:18<2:58:19,  1.56it/s]
 71%|███████   | 40916/57600 [7:11:19<2:59:14,  1.55it/s]
 71%|███████   | 40917/57600 [7:11:19<3:08:18,  1.48it/s]
 71%|███████   | 40918/57600 [7:11:20<3:03:11,  1.52it/s]
 71%|███████   | 40919/57600 [7:11:21<3:01:48,  1.53it/s]
 71%|███████   | 40920/57600 [7:11:21<2:56:59,  1.57it/s]
                                                         
{'loss': 1.1316, 'learning_rate': 3.6153310104529615e-07, 'epoch': 451.66}

 71%|███████   | 40920/57600 [7:11:21<2:56:59,  1.57it/s]
 71%|███████   | 40921/57600 [7:11:22<2:56:56,  1.57it/s]
 71%|███████   | 40922/57600 [7:11:22<2:52:41,  1.61it/s]
 71%|███████   | 40923/57600 [7:11:23<2:52:33,  1.61it/s]
 71%|███████   | 40924/57600 [7:11:24<2:47:04,  1.66it/s]
 71%|███████   | 40925/57600 [7:11:24<2:55:58,  1.58it/s]
 71%|███████   | 40926/57600 [7:11:25<2:57:42,  1.56it/s]
 71%|███████   | 40927/57600 [7:11:26<2:57:17,  1.57it/s]
 71%|███████   | 40928/57600 [7:11:26<2:55:14,  1.59it/s]
 71%|███████   | 40929/57600 [7:11:27<2:49:17,  1.64it/s]
 71%|███████   | 40930/57600 [7:11:27<2:46:27,  1.67it/s]
 71%|███████   | 40931/57600 [7:11:28<2:52:15,  1.61it/s]
 71%|███████   | 40932/57600 [7:11:29<2:51:03,  1.62it/s]
 71%|███████   | 40933/57600 [7:11:29<2:46:01,  1.67it/s]
 71%|███████   | 40934/57600 [7:11:30<2:47:26,  1.66it/s]
 71%|███████   | 40935/57600 [7:11:30<2:55:16,  1.58it/s]
 71%|███████   | 40936/57600 [7:11:31<2:50:46,  1.63it/s]
 71%|███████   | 40937/57600 [7:11:32<2:59:14,  1.55it/s]
 71%|███████   | 40938/57600 [7:11:32<2:56:12,  1.58it/s]
 71%|███████   | 40939/57600 [7:11:33<2:53:06,  1.60it/s]
 71%|███████   | 40940/57600 [7:11:34<2:50:10,  1.63it/s]
                                                         
{'loss': 1.1592, 'learning_rate': 3.6121951219512196e-07, 'epoch': 451.88}

 71%|███████   | 40940/57600 [7:11:34<2:50:10,  1.63it/s]
 71%|███████   | 40941/57600 [7:11:34<2:55:35,  1.58it/s]
 71%|███████   | 40942/57600 [7:11:35<2:56:38,  1.57it/s]
 71%|███████   | 40943/57600 [7:11:36<2:58:34,  1.55it/s]
 71%|███████   | 40944/57600 [7:11:36<2:54:17,  1.59it/s]
 71%|███████   | 40945/57600 [7:11:37<2:59:13,  1.55it/s]
 71%|███████   | 40946/57600 [7:11:38<3:05:44,  1.49it/s]
 71%|███████   | 40947/57600 [7:11:38<3:04:21,  1.51it/s]
 71%|███████   | 40948/57600 [7:11:39<3:09:02,  1.47it/s]
 71%|███████   | 40949/57600 [7:11:40<3:03:11,  1.51it/s]
 71%|███████   | 40950/57600 [7:11:40<2:56:25,  1.57it/s]
 71%|███████   | 40951/57600 [7:11:41<2:54:20,  1.59it/s]
 71%|███████   | 40952/57600 [7:11:41<3:00:49,  1.53it/s]
 71%|███████   | 40953/57600 [7:11:42<2:54:07,  1.59it/s]
 71%|███████   | 40954/57600 [7:11:43<2:53:33,  1.60it/s]
 71%|███████   | 40955/57600 [7:11:43<2:52:33,  1.61it/s]
 71%|███████   | 40956/57600 [7:11:44<2:49:38,  1.64it/s]
 71%|███████   | 40957/57600 [7:11:44<2:53:21,  1.60it/s]
 71%|███████   | 40958/57600 [7:11:45<2:55:53,  1.58it/s]
 71%|███████   | 40959/57600 [7:11:46<3:00:25,  1.54it/s]
 71%|███████   | 40960/57600 [7:11:46<2:58:51,  1.55it/s]
                                                         
{'loss': 1.1262, 'learning_rate': 3.6090592334494766e-07, 'epoch': 452.1}

 71%|███████   | 40960/57600 [7:11:46<2:58:51,  1.55it/s]
 71%|███████   | 40961/57600 [7:11:47<2:51:39,  1.62it/s]
 71%|███████   | 40962/57600 [7:11:48<2:52:20,  1.61it/s]
 71%|███████   | 40963/57600 [7:11:48<2:55:34,  1.58it/s]
 71%|███████   | 40964/57600 [7:11:49<2:59:36,  1.54it/s]
 71%|███████   | 40965/57600 [7:11:50<2:54:48,  1.59it/s]
 71%|███████   | 40966/57600 [7:11:50<2:53:58,  1.59it/s]
 71%|███████   | 40967/57600 [7:11:51<2:50:57,  1.62it/s]
 71%|███████   | 40968/57600 [7:11:51<2:52:19,  1.61it/s]
 71%|███████   | 40969/57600 [7:11:52<2:57:02,  1.57it/s]
 71%|███████   | 40970/57600 [7:11:53<2:58:08,  1.56it/s]
 71%|███████   | 40971/57600 [7:11:53<2:52:36,  1.61it/s]
 71%|███████   | 40972/57600 [7:11:54<2:53:43,  1.60it/s]
 71%|███████   | 40973/57600 [7:11:55<2:48:48,  1.64it/s]
 71%|███████   | 40974/57600 [7:11:55<2:53:58,  1.59it/s]
 71%|███████   | 40975/57600 [7:11:56<2:51:14,  1.62it/s]
 71%|███████   | 40976/57600 [7:11:57<3:01:07,  1.53it/s]
 71%|███████   | 40977/57600 [7:11:57<2:55:17,  1.58it/s]
 71%|███████   | 40978/57600 [7:11:58<2:56:52,  1.57it/s]
 71%|███████   | 40979/57600 [7:11:58<2:51:18,  1.62it/s]
 71%|███████   | 40980/57600 [7:11:59<2:47:59,  1.65it/s]
                                                         
{'loss': 1.1274, 'learning_rate': 3.605923344947735e-07, 'epoch': 452.32}

 71%|███████   | 40980/57600 [7:11:59<2:47:59,  1.65it/s]
 71%|███████   | 40981/57600 [7:12:00<2:46:01,  1.67it/s]
 71%|███████   | 40982/57600 [7:12:00<2:46:47,  1.66it/s]
 71%|███████   | 40983/57600 [7:12:01<2:46:55,  1.66it/s]
 71%|███████   | 40984/57600 [7:12:01<2:47:17,  1.66it/s]
 71%|███████   | 40985/57600 [7:12:02<2:44:55,  1.68it/s]
 71%|███████   | 40986/57600 [7:12:02<2:41:58,  1.71it/s]
 71%|███████   | 40987/57600 [7:12:03<2:47:50,  1.65it/s]
 71%|███████   | 40988/57600 [7:12:04<2:48:01,  1.65it/s]
 71%|███████   | 40989/57600 [7:12:04<2:48:11,  1.65it/s]
 71%|███████   | 40990/57600 [7:12:05<2:50:46,  1.62it/s]
 71%|███████   | 40991/57600 [7:12:06<2:50:16,  1.63it/s]
 71%|███████   | 40992/57600 [7:12:06<2:52:49,  1.60it/s]
 71%|███████   | 40993/57600 [7:12:07<2:52:11,  1.61it/s]
 71%|███████   | 40994/57600 [7:12:08<2:54:51,  1.58it/s]
 71%|███████   | 40995/57600 [7:12:08<2:57:51,  1.56it/s]
 71%|███████   | 40996/57600 [7:12:09<2:55:10,  1.58it/s]
 71%|███████   | 40997/57600 [7:12:09<2:54:10,  1.59it/s]
 71%|███████   | 40998/57600 [7:12:10<2:55:05,  1.58it/s]
 71%|███████   | 40999/57600 [7:12:11<2:54:09,  1.59it/s]
 71%|███████   | 41000/57600 [7:12:11<3:01:08,  1.53it/s]
                                                         
{'loss': 1.1403, 'learning_rate': 3.6027874564459927e-07, 'epoch': 452.54}

 71%|███████   | 41000/57600 [7:12:11<3:01:08,  1.53it/s]
 71%|███████   | 41001/57600 [7:12:12<2:58:05,  1.55it/s]
 71%|███████   | 41002/57600 [7:12:13<2:52:03,  1.61it/s]
 71%|███████   | 41003/57600 [7:12:13<2:51:30,  1.61it/s]
 71%|███████   | 41004/57600 [7:12:14<2:51:38,  1.61it/s]
 71%|███████   | 41005/57600 [7:12:14<2:54:18,  1.59it/s]
 71%|███████   | 41006/57600 [7:12:15<2:50:44,  1.62it/s]
 71%|███████   | 41007/57600 [7:12:16<2:52:34,  1.60it/s]
 71%|███████   | 41008/57600 [7:12:16<2:57:22,  1.56it/s]
 71%|███████   | 41009/57600 [7:12:17<2:53:03,  1.60it/s]
 71%|███████   | 41010/57600 [7:12:18<2:55:15,  1.58it/s]
 71%|███████   | 41011/57600 [7:12:18<2:56:59,  1.56it/s]
 71%|███████   | 41012/57600 [7:12:19<2:55:24,  1.58it/s]
 71%|███████   | 41013/57600 [7:12:19<2:48:56,  1.64it/s]
 71%|███████   | 41014/57600 [7:12:20<2:46:52,  1.66it/s]
 71%|███████   | 41015/57600 [7:12:21<2:56:17,  1.57it/s]
 71%|███████   | 41016/57600 [7:12:21<3:04:05,  1.50it/s]
 71%|███████   | 41017/57600 [7:12:22<3:01:02,  1.53it/s]
 71%|███████   | 41018/57600 [7:12:23<3:01:42,  1.52it/s]
 71%|███████   | 41019/57600 [7:12:23<2:58:57,  1.54it/s]
 71%|███████   | 41020/57600 [7:12:24<2:54:51,  1.58it/s]
                                                         
{'loss': 1.1721, 'learning_rate': 3.5996515679442507e-07, 'epoch': 452.76}

 71%|███████   | 41020/57600 [7:12:24<2:54:51,  1.58it/s]
 71%|███████   | 41021/57600 [7:12:25<2:51:41,  1.61it/s]
 71%|███████   | 41022/57600 [7:12:25<2:55:24,  1.58it/s]
 71%|███████   | 41023/57600 [7:12:26<2:53:21,  1.59it/s]
 71%|███████   | 41024/57600 [7:12:26<2:49:27,  1.63it/s]
 71%|███████   | 41025/57600 [7:12:27<2:47:08,  1.65it/s]
 71%|███████   | 41026/57600 [7:12:28<2:46:57,  1.65it/s]
 71%|███████   | 41027/57600 [7:12:28<2:54:04,  1.59it/s]
 71%|███████   | 41028/57600 [7:12:29<2:49:46,  1.63it/s]
 71%|███████   | 41029/57600 [7:12:30<2:50:11,  1.62it/s]
 71%|███████   | 41030/57600 [7:12:30<2:49:46,  1.63it/s]
 71%|███████   | 41031/57600 [7:12:31<2:56:41,  1.56it/s]
 71%|███████   | 41032/57600 [7:12:31<2:54:50,  1.58it/s]
 71%|███████   | 41033/57600 [7:12:32<3:01:50,  1.52it/s]
 71%|███████   | 41034/57600 [7:12:33<2:56:27,  1.56it/s]
 71%|███████   | 41035/57600 [7:12:33<2:54:59,  1.58it/s]
 71%|███████   | 41036/57600 [7:12:34<2:52:12,  1.60it/s]
 71%|███████   | 41037/57600 [7:12:35<2:56:06,  1.57it/s]
 71%|███████   | 41038/57600 [7:12:35<2:57:46,  1.55it/s]
 71%|███████   | 41039/57600 [7:12:36<2:57:19,  1.56it/s]
 71%|███████▏  | 41040/57600 [7:12:37<2:56:38,  1.56it/s]
                                                         
{'loss': 1.1051, 'learning_rate': 3.596515679442509e-07, 'epoch': 452.98}

 71%|███████▏  | 41040/57600 [7:12:37<2:56:38,  1.56it/s]
 71%|███████▏  | 41041/57600 [7:12:37<2:56:44,  1.56it/s]
 71%|███████▏  | 41042/57600 [7:12:38<2:59:35,  1.54it/s]
 71%|███████▏  | 41043/57600 [7:12:38<2:55:14,  1.57it/s]
 71%|███████▏  | 41044/57600 [7:12:39<2:51:02,  1.61it/s]
 71%|███████▏  | 41045/57600 [7:12:40<2:54:09,  1.58it/s]
 71%|███████▏  | 41046/57600 [7:12:40<2:50:29,  1.62it/s]
 71%|███████▏  | 41047/57600 [7:12:41<2:54:53,  1.58it/s]
 71%|███████▏  | 41048/57600 [7:12:42<2:53:17,  1.59it/s]
 71%|███████▏  | 41049/57600 [7:12:42<2:50:31,  1.62it/s]
 71%|███████▏  | 41050/57600 [7:12:43<2:49:11,  1.63it/s]
 71%|███████▏  | 41051/57600 [7:12:44<2:56:11,  1.57it/s]
 71%|███████▏  | 41052/57600 [7:12:44<3:03:23,  1.50it/s]
 71%|███████▏  | 41053/57600 [7:12:45<2:55:25,  1.57it/s]
 71%|███████▏  | 41054/57600 [7:12:46<3:01:08,  1.52it/s]
 71%|███████▏  | 41055/57600 [7:12:46<2:59:07,  1.54it/s]
 71%|███████▏  | 41056/57600 [7:12:47<2:54:26,  1.58it/s]
 71%|███████▏  | 41057/57600 [7:12:47<2:52:19,  1.60it/s]
 71%|███████▏  | 41058/57600 [7:12:48<2:50:47,  1.61it/s]
 71%|███████▏  | 41059/57600 [7:12:49<2:50:51,  1.61it/s]
 71%|███████▏  | 41060/57600 [7:12:49<2:54:24,  1.58it/s]
                                                         
{'loss': 1.1413, 'learning_rate': 3.5933797909407663e-07, 'epoch': 453.2}

 71%|███████▏  | 41060/57600 [7:12:49<2:54:24,  1.58it/s]
 71%|███████▏  | 41061/57600 [7:12:50<2:57:49,  1.55it/s]
 71%|███████▏  | 41062/57600 [7:12:51<3:00:15,  1.53it/s]
 71%|███████▏  | 41063/57600 [7:12:51<2:55:33,  1.57it/s]
 71%|███████▏  | 41064/57600 [7:12:52<2:55:25,  1.57it/s]
 71%|███████▏  | 41065/57600 [7:12:52<2:57:24,  1.55it/s]
 71%|███████▏  | 41066/57600 [7:12:53<2:53:10,  1.59it/s]
 71%|███████▏  | 41067/57600 [7:12:54<2:55:36,  1.57it/s]
 71%|███████▏  | 41068/57600 [7:12:54<2:53:24,  1.59it/s]
 71%|███████▏  | 41069/57600 [7:12:55<2:50:10,  1.62it/s]
 71%|███████▏  | 41070/57600 [7:12:56<2:47:18,  1.65it/s]
 71%|███████▏  | 41071/57600 [7:12:56<3:00:18,  1.53it/s]
 71%|███████▏  | 41072/57600 [7:12:57<3:05:01,  1.49it/s]
 71%|███████▏  | 41073/57600 [7:12:58<3:02:00,  1.51it/s]
 71%|███████▏  | 41074/57600 [7:12:58<2:58:05,  1.55it/s]
 71%|███████▏  | 41075/57600 [7:12:59<2:54:36,  1.58it/s]
 71%|███████▏  | 41076/57600 [7:13:00<3:02:08,  1.51it/s]
 71%|███████▏  | 41077/57600 [7:13:00<2:53:59,  1.58it/s]
 71%|███████▏  | 41078/57600 [7:13:01<2:52:46,  1.59it/s]
 71%|███████▏  | 41079/57600 [7:13:01<2:50:12,  1.62it/s]
 71%|███████▏  | 41080/57600 [7:13:02<2:46:24,  1.65it/s]
                                                         
{'loss': 1.1231, 'learning_rate': 3.5902439024390243e-07, 'epoch': 453.42}

 71%|███████▏  | 41080/57600 [7:13:02<2:46:24,  1.65it/s]
 71%|███████▏  | 41081/57600 [7:13:03<2:46:31,  1.65it/s]
 71%|███████▏  | 41082/57600 [7:13:03<2:46:12,  1.66it/s]
 71%|███████▏  | 41083/57600 [7:13:04<2:48:46,  1.63it/s]
 71%|███████▏  | 41084/57600 [7:13:04<2:49:23,  1.62it/s]
 71%|███████▏  | 41085/57600 [7:13:05<2:48:17,  1.64it/s]
 71%|███████▏  | 41086/57600 [7:13:06<2:47:12,  1.65it/s]
 71%|███████▏  | 41087/57600 [7:13:06<2:49:14,  1.63it/s]
 71%|███████▏  | 41088/57600 [7:13:07<2:59:05,  1.54it/s]
 71%|███████▏  | 41089/57600 [7:13:08<2:55:41,  1.57it/s]
 71%|███████▏  | 41090/57600 [7:13:08<2:50:47,  1.61it/s]
 71%|███████▏  | 41091/57600 [7:13:09<2:51:29,  1.60it/s]
 71%|███████▏  | 41092/57600 [7:13:09<2:50:31,  1.61it/s]
 71%|███████▏  | 41093/57600 [7:13:10<2:51:45,  1.60it/s]
 71%|███████▏  | 41094/57600 [7:13:11<2:58:00,  1.55it/s]
 71%|███████▏  | 41095/57600 [7:13:11<2:54:11,  1.58it/s]
 71%|███████▏  | 41096/57600 [7:13:12<2:48:02,  1.64it/s]
 71%|███████▏  | 41097/57600 [7:13:12<2:42:39,  1.69it/s]
 71%|███████▏  | 41098/57600 [7:13:13<2:44:30,  1.67it/s]
 71%|███████▏  | 41099/57600 [7:13:14<2:47:09,  1.65it/s]
 71%|███████▏  | 41100/57600 [7:13:14<2:45:37,  1.66it/s]
                                                         
{'loss': 1.1572, 'learning_rate': 3.587108013937282e-07, 'epoch': 453.64}

 71%|███████▏  | 41100/57600 [7:13:14<2:45:37,  1.66it/s]
 71%|███████▏  | 41101/57600 [7:13:15<2:46:38,  1.65it/s]
 71%|███████▏  | 41102/57600 [7:13:16<2:50:16,  1.61it/s]
 71%|███████▏  | 41103/57600 [7:13:16<2:57:02,  1.55it/s]
 71%|███████▏  | 41104/57600 [7:13:17<2:56:33,  1.56it/s]
 71%|███████▏  | 41105/57600 [7:13:18<2:57:38,  1.55it/s]
 71%|███████▏  | 41106/57600 [7:13:18<2:57:30,  1.55it/s]
 71%|███████▏  | 41107/57600 [7:13:19<2:55:51,  1.56it/s]
 71%|███████▏  | 41108/57600 [7:13:19<2:55:49,  1.56it/s]
 71%|███████▏  | 41109/57600 [7:13:20<2:55:05,  1.57it/s]
 71%|███████▏  | 41110/57600 [7:13:21<2:55:11,  1.57it/s]
 71%|███████▏  | 41111/57600 [7:13:21<2:56:10,  1.56it/s]
 71%|███████▏  | 41112/57600 [7:13:22<2:53:23,  1.58it/s]
 71%|███████▏  | 41113/57600 [7:13:23<2:57:56,  1.54it/s]
 71%|███████▏  | 41114/57600 [7:13:23<2:53:54,  1.58it/s]
 71%|███████▏  | 41115/57600 [7:13:24<2:58:15,  1.54it/s]
 71%|███████▏  | 41116/57600 [7:13:25<2:53:23,  1.58it/s]
 71%|███████▏  | 41117/57600 [7:13:25<2:48:29,  1.63it/s]
 71%|███████▏  | 41118/57600 [7:13:26<2:47:00,  1.64it/s]
 71%|███████▏  | 41119/57600 [7:13:26<2:51:57,  1.60it/s]
 71%|███████▏  | 41120/57600 [7:13:27<2:54:47,  1.57it/s]
                                                         
{'loss': 1.121, 'learning_rate': 3.58397212543554e-07, 'epoch': 453.86}

 71%|███████▏  | 41120/57600 [7:13:27<2:54:47,  1.57it/s]
 71%|███████▏  | 41121/57600 [7:13:28<2:58:52,  1.54it/s]
 71%|███████▏  | 41122/57600 [7:13:28<2:56:54,  1.55it/s]
 71%|███████▏  | 41123/57600 [7:13:29<2:52:59,  1.59it/s]
 71%|███████▏  | 41124/57600 [7:13:30<2:51:26,  1.60it/s]
 71%|███████▏  | 41125/57600 [7:13:30<2:51:23,  1.60it/s]
 71%|███████▏  | 41126/57600 [7:13:31<2:52:49,  1.59it/s]
 71%|███████▏  | 41127/57600 [7:13:31<2:51:29,  1.60it/s]
 71%|███████▏  | 41128/57600 [7:13:32<2:50:09,  1.61it/s]
 71%|███████▏  | 41129/57600 [7:13:33<2:46:31,  1.65it/s]
 71%|███████▏  | 41130/57600 [7:13:33<2:51:04,  1.60it/s]
 71%|███████▏  | 41131/57600 [7:13:34<2:50:32,  1.61it/s]
 71%|███████▏  | 41132/57600 [7:13:34<2:49:10,  1.62it/s]
 71%|███████▏  | 41133/57600 [7:13:35<3:01:00,  1.52it/s]
 71%|███████▏  | 41134/57600 [7:13:36<3:01:49,  1.51it/s]
 71%|███████▏  | 41135/57600 [7:13:37<3:01:05,  1.52it/s]
 71%|███████▏  | 41136/57600 [7:13:37<3:00:04,  1.52it/s]
 71%|███████▏  | 41137/57600 [7:13:38<2:56:39,  1.55it/s]
 71%|███████▏  | 41138/57600 [7:13:38<2:50:16,  1.61it/s]
 71%|███████▏  | 41139/57600 [7:13:39<2:47:44,  1.64it/s]
 71%|███████▏  | 41140/57600 [7:13:40<2:47:49,  1.63it/s]
                                                         
{'loss': 1.1234, 'learning_rate': 3.5808362369337974e-07, 'epoch': 454.08}

 71%|███████▏  | 41140/57600 [7:13:40<2:47:49,  1.63it/s]
 71%|███████▏  | 41141/57600 [7:13:40<2:48:24,  1.63it/s]
 71%|███████▏  | 41142/57600 [7:13:41<2:46:05,  1.65it/s]
 71%|███████▏  | 41143/57600 [7:13:41<2:48:25,  1.63it/s]
 71%|███████▏  | 41144/57600 [7:13:42<2:46:21,  1.65it/s]
 71%|███████▏  | 41145/57600 [7:13:43<2:45:50,  1.65it/s]
 71%|███████▏  | 41146/57600 [7:13:43<2:51:54,  1.60it/s]
 71%|███████▏  | 41147/57600 [7:13:44<2:55:30,  1.56it/s]
 71%|███████▏  | 41148/57600 [7:13:45<2:51:21,  1.60it/s]
 71%|███████▏  | 41149/57600 [7:13:45<2:47:41,  1.64it/s]
 71%|███████▏  | 41150/57600 [7:13:46<2:50:11,  1.61it/s]
 71%|███████▏  | 41151/57600 [7:13:46<2:48:08,  1.63it/s]
 71%|███████▏  | 41152/57600 [7:13:47<2:53:38,  1.58it/s]
 71%|███████▏  | 41153/57600 [7:13:48<2:48:11,  1.63it/s]
 71%|███████▏  | 41154/57600 [7:13:48<2:54:19,  1.57it/s]
 71%|███████▏  | 41155/57600 [7:13:49<2:51:55,  1.59it/s]
 71%|███████▏  | 41156/57600 [7:13:50<2:52:57,  1.58it/s]
 71%|███████▏  | 41157/57600 [7:13:50<2:56:31,  1.55it/s]
 71%|███████▏  | 41158/57600 [7:13:51<3:03:12,  1.50it/s]
 71%|███████▏  | 41159/57600 [7:13:52<3:01:04,  1.51it/s]
 71%|███████▏  | 41160/57600 [7:13:52<3:06:23,  1.47it/s]
                                                         
{'loss': 1.1248, 'learning_rate': 3.5777003484320555e-07, 'epoch': 454.3}

 71%|███████▏  | 41160/57600 [7:13:52<3:06:23,  1.47it/s]
 71%|███████▏  | 41161/57600 [7:13:53<3:06:36,  1.47it/s]
 71%|███████▏  | 41162/57600 [7:13:54<3:02:13,  1.50it/s]
 71%|███████▏  | 41163/57600 [7:13:54<3:04:43,  1.48it/s]
 71%|███████▏  | 41164/57600 [7:13:55<3:04:18,  1.49it/s]
 71%|███████▏  | 41165/57600 [7:13:56<3:01:46,  1.51it/s]
 71%|███████▏  | 41166/57600 [7:13:56<3:00:51,  1.51it/s]
 71%|███████▏  | 41167/57600 [7:13:57<2:58:57,  1.53it/s]
 71%|███████▏  | 41168/57600 [7:13:58<2:57:29,  1.54it/s]
 71%|███████▏  | 41169/57600 [7:13:58<2:53:59,  1.57it/s]
 71%|███████▏  | 41170/57600 [7:13:59<2:50:43,  1.60it/s]
 71%|███████▏  | 41171/57600 [7:13:59<2:45:20,  1.66it/s]
 71%|███████▏  | 41172/57600 [7:14:00<2:51:30,  1.60it/s]
 71%|███████▏  | 41173/57600 [7:14:01<2:58:34,  1.53it/s]
 71%|███████▏  | 41174/57600 [7:14:01<2:56:03,  1.56it/s]
 71%|███████▏  | 41175/57600 [7:14:02<2:50:51,  1.60it/s]
 71%|███████▏  | 41176/57600 [7:14:03<2:49:48,  1.61it/s]
 71%|███████▏  | 41177/57600 [7:14:03<2:50:17,  1.61it/s]
 71%|███████▏  | 41178/57600 [7:14:04<2:48:03,  1.63it/s]
 71%|███████▏  | 41179/57600 [7:14:04<2:46:22,  1.64it/s]
 71%|███████▏  | 41180/57600 [7:14:05<2:47:18,  1.64it/s]
                                                         
{'loss': 1.1286, 'learning_rate': 3.574564459930314e-07, 'epoch': 454.53}

 71%|███████▏  | 41180/57600 [7:14:05<2:47:18,  1.64it/s]
 71%|███████▏  | 41181/57600 [7:14:06<2:46:36,  1.64it/s]
 71%|███████▏  | 41182/57600 [7:14:06<2:49:03,  1.62it/s]
 71%|███████▏  | 41183/57600 [7:14:07<2:48:32,  1.62it/s]
 72%|███████▏  | 41184/57600 [7:14:07<2:53:03,  1.58it/s]
 72%|███████▏  | 41185/57600 [7:14:08<2:53:40,  1.58it/s]
 72%|███████▏  | 41186/57600 [7:14:09<2:50:24,  1.61it/s]
 72%|███████▏  | 41187/57600 [7:14:09<2:50:24,  1.61it/s]
 72%|███████▏  | 41188/57600 [7:14:10<2:48:40,  1.62it/s]
 72%|███████▏  | 41189/57600 [7:14:11<2:49:55,  1.61it/s]
 72%|███████▏  | 41190/57600 [7:14:11<2:46:44,  1.64it/s]
 72%|███████▏  | 41191/57600 [7:14:12<2:45:12,  1.66it/s]
 72%|███████▏  | 41192/57600 [7:14:12<2:46:06,  1.65it/s]
 72%|███████▏  | 41193/57600 [7:14:13<2:43:35,  1.67it/s]
 72%|███████▏  | 41194/57600 [7:14:14<2:42:11,  1.69it/s]
 72%|███████▏  | 41195/57600 [7:14:14<2:47:55,  1.63it/s]
 72%|███████▏  | 41196/57600 [7:14:15<2:44:38,  1.66it/s]
 72%|███████▏  | 41197/57600 [7:14:15<2:47:55,  1.63it/s]
 72%|███████▏  | 41198/57600 [7:14:16<2:46:54,  1.64it/s]
 72%|███████▏  | 41199/57600 [7:14:17<2:47:02,  1.64it/s]
 72%|███████▏  | 41200/57600 [7:14:17<2:48:54,  1.62it/s]
                                                         
{'loss': 1.1519, 'learning_rate': 3.571428571428571e-07, 'epoch': 454.75}

 72%|███████▏  | 41200/57600 [7:14:17<2:48:54,  1.62it/s]
 72%|███████▏  | 41201/57600 [7:14:18<2:47:05,  1.64it/s]
 72%|███████▏  | 41202/57600 [7:14:18<2:48:27,  1.62it/s]
 72%|███████▏  | 41203/57600 [7:14:19<2:53:40,  1.57it/s]
 72%|███████▏  | 41204/57600 [7:14:20<2:55:20,  1.56it/s]
 72%|███████▏  | 41205/57600 [7:14:20<2:51:47,  1.59it/s]
 72%|███████▏  | 41206/57600 [7:14:21<2:50:48,  1.60it/s]
 72%|███████▏  | 41207/57600 [7:14:22<2:54:08,  1.57it/s]
 72%|███████▏  | 41208/57600 [7:14:22<2:47:39,  1.63it/s]
 72%|███████▏  | 41209/57600 [7:14:23<2:51:59,  1.59it/s]
 72%|███████▏  | 41210/57600 [7:14:24<2:54:18,  1.57it/s]
 72%|███████▏  | 41211/57600 [7:14:24<2:59:08,  1.52it/s]
 72%|███████▏  | 41212/57600 [7:14:25<3:03:48,  1.49it/s]
 72%|███████▏  | 41213/57600 [7:14:26<3:05:31,  1.47it/s]
 72%|███████▏  | 41214/57600 [7:14:26<3:07:14,  1.46it/s]
 72%|███████▏  | 41215/57600 [7:14:27<3:03:26,  1.49it/s]
 72%|███████▏  | 41216/57600 [7:14:28<2:59:38,  1.52it/s]
 72%|███████▏  | 41217/57600 [7:14:28<3:02:29,  1.50it/s]
 72%|███████▏  | 41218/57600 [7:14:29<3:00:10,  1.52it/s]
 72%|███████▏  | 41219/57600 [7:14:30<2:56:33,  1.55it/s]
 72%|███████▏  | 41220/57600 [7:14:30<2:54:19,  1.57it/s]
                                                         
{'loss': 1.1209, 'learning_rate': 3.5682926829268296e-07, 'epoch': 454.97}

 72%|███████▏  | 41220/57600 [7:14:30<2:54:19,  1.57it/s]
 72%|███████▏  | 41221/57600 [7:14:31<2:50:06,  1.60it/s]
 72%|███████▏  | 41222/57600 [7:14:31<2:52:27,  1.58it/s]
 72%|███████▏  | 41223/57600 [7:14:32<2:51:53,  1.59it/s]
 72%|███████▏  | 41224/57600 [7:14:33<2:59:08,  1.52it/s]
 72%|███████▏  | 41225/57600 [7:14:33<3:00:33,  1.51it/s]
 72%|███████▏  | 41226/57600 [7:14:34<2:54:44,  1.56it/s]
 72%|███████▏  | 41227/57600 [7:14:35<2:55:37,  1.55it/s]
 72%|███████▏  | 41228/57600 [7:14:35<2:58:45,  1.53it/s]
 72%|███████▏  | 41229/57600 [7:14:36<2:55:51,  1.55it/s]
 72%|███████▏  | 41230/57600 [7:14:37<2:57:53,  1.53it/s]
 72%|███████▏  | 41231/57600 [7:14:37<3:04:21,  1.48it/s]
 72%|███████▏  | 41232/57600 [7:14:38<2:59:41,  1.52it/s]
 72%|███████▏  | 41233/57600 [7:14:39<2:57:04,  1.54it/s]
 72%|███████▏  | 41234/57600 [7:14:39<3:00:57,  1.51it/s]
 72%|███████▏  | 41235/57600 [7:14:40<3:00:18,  1.51it/s]
 72%|███████▏  | 41236/57600 [7:14:41<2:58:46,  1.53it/s]
 72%|███████▏  | 41237/57600 [7:14:41<2:59:15,  1.52it/s]
 72%|███████▏  | 41238/57600 [7:14:42<2:54:51,  1.56it/s]
 72%|███████▏  | 41239/57600 [7:14:42<2:49:10,  1.61it/s]
 72%|███████▏  | 41240/57600 [7:14:43<2:49:35,  1.61it/s]
                                                         
{'loss': 1.1182, 'learning_rate': 3.5651567944250866e-07, 'epoch': 455.19}

 72%|███████▏  | 41240/57600 [7:14:43<2:49:35,  1.61it/s]
 72%|███████▏  | 41241/57600 [7:14:44<2:56:13,  1.55it/s]
 72%|███████▏  | 41242/57600 [7:14:44<2:53:51,  1.57it/s]
 72%|███████▏  | 41243/57600 [7:14:45<2:51:44,  1.59it/s]
 72%|███████▏  | 41244/57600 [7:14:46<2:48:36,  1.62it/s]
 72%|███████▏  | 41245/57600 [7:14:46<2:58:48,  1.52it/s]
 72%|███████▏  | 41246/57600 [7:14:47<2:53:01,  1.58it/s]
 72%|███████▏  | 41247/57600 [7:14:48<2:50:27,  1.60it/s]
 72%|███████▏  | 41248/57600 [7:14:48<2:47:33,  1.63it/s]
 72%|███████▏  | 41249/57600 [7:14:49<2:49:16,  1.61it/s]
 72%|███████▏  | 41250/57600 [7:14:49<2:45:55,  1.64it/s]
 72%|███████▏  | 41251/57600 [7:14:50<2:50:37,  1.60it/s]
 72%|███████▏  | 41252/57600 [7:14:51<2:48:46,  1.61it/s]
 72%|███████▏  | 41253/57600 [7:14:51<2:49:08,  1.61it/s]
 72%|███████▏  | 41254/57600 [7:14:52<2:49:17,  1.61it/s]
 72%|███████▏  | 41255/57600 [7:14:53<2:48:38,  1.62it/s]
 72%|███████▏  | 41256/57600 [7:14:53<2:51:05,  1.59it/s]
 72%|███████▏  | 41257/57600 [7:14:54<2:48:37,  1.62it/s]
 72%|███████▏  | 41258/57600 [7:14:54<2:55:38,  1.55it/s]
 72%|███████▏  | 41259/57600 [7:14:55<2:55:16,  1.55it/s]
 72%|███████▏  | 41260/57600 [7:14:56<2:59:00,  1.52it/s]
                                                         
{'loss': 1.1495, 'learning_rate': 3.5620209059233447e-07, 'epoch': 455.41}

 72%|███████▏  | 41260/57600 [7:14:56<2:59:00,  1.52it/s]
 72%|███████▏  | 41261/57600 [7:14:56<2:56:05,  1.55it/s]
 72%|███████▏  | 41262/57600 [7:14:57<2:53:42,  1.57it/s]
 72%|███████▏  | 41263/57600 [7:14:58<2:52:49,  1.58it/s]
 72%|███████▏  | 41264/57600 [7:14:58<2:54:57,  1.56it/s]
 72%|███████▏  | 41265/57600 [7:14:59<2:52:23,  1.58it/s]
 72%|███████▏  | 41266/57600 [7:15:00<2:48:28,  1.62it/s]
 72%|███████▏  | 41267/57600 [7:15:00<2:49:02,  1.61it/s]
 72%|███████▏  | 41268/57600 [7:15:01<2:52:25,  1.58it/s]
 72%|███████▏  | 41269/57600 [7:15:01<2:49:59,  1.60it/s]
 72%|███████▏  | 41270/57600 [7:15:02<2:47:57,  1.62it/s]
 72%|███████▏  | 41271/57600 [7:15:03<2:50:46,  1.59it/s]
 72%|███████▏  | 41272/57600 [7:15:03<2:48:47,  1.61it/s]
 72%|███████▏  | 41273/57600 [7:15:04<2:48:09,  1.62it/s]
 72%|███████▏  | 41274/57600 [7:15:05<2:50:22,  1.60it/s]
 72%|███████▏  | 41275/57600 [7:15:05<2:44:28,  1.65it/s]
 72%|███████▏  | 41276/57600 [7:15:06<2:42:03,  1.68it/s]
 72%|███████▏  | 41277/57600 [7:15:06<2:43:23,  1.67it/s]
 72%|███████▏  | 41278/57600 [7:15:07<2:53:32,  1.57it/s]
 72%|███████▏  | 41279/57600 [7:15:08<2:55:29,  1.55it/s]
 72%|███████▏  | 41280/57600 [7:15:08<2:54:58,  1.55it/s]
                                                         
{'loss': 1.1124, 'learning_rate': 3.558885017421602e-07, 'epoch': 455.63}

 72%|███████▏  | 41280/57600 [7:15:08<2:54:58,  1.55it/s]
 72%|███████▏  | 41281/57600 [7:15:09<2:50:26,  1.60it/s]
 72%|███████▏  | 41282/57600 [7:15:10<2:54:01,  1.56it/s]
 72%|███████▏  | 41283/57600 [7:15:10<2:50:21,  1.60it/s]
 72%|███████▏  | 41284/57600 [7:15:11<2:54:00,  1.56it/s]
 72%|███████▏  | 41285/57600 [7:15:11<2:54:24,  1.56it/s]
 72%|███████▏  | 41286/57600 [7:15:12<2:50:56,  1.59it/s]
 72%|███████▏  | 41287/57600 [7:15:13<2:49:46,  1.60it/s]
 72%|███████▏  | 41288/57600 [7:15:13<2:52:06,  1.58it/s]
 72%|███████▏  | 41289/57600 [7:15:14<2:52:05,  1.58it/s]
 72%|███████▏  | 41290/57600 [7:15:15<2:45:58,  1.64it/s]
 72%|███████▏  | 41291/57600 [7:15:15<2:44:10,  1.66it/s]
 72%|███████▏  | 41292/57600 [7:15:16<2:48:18,  1.61it/s]
 72%|███████▏  | 41293/57600 [7:15:16<2:49:36,  1.60it/s]
 72%|███████▏  | 41294/57600 [7:15:17<2:49:25,  1.60it/s]
 72%|███████▏  | 41295/57600 [7:15:18<3:01:02,  1.50it/s]
 72%|███████▏  | 41296/57600 [7:15:18<2:56:36,  1.54it/s]
 72%|███████▏  | 41297/57600 [7:15:19<2:51:35,  1.58it/s]
 72%|███████▏  | 41298/57600 [7:15:20<2:46:23,  1.63it/s]
 72%|███████▏  | 41299/57600 [7:15:20<2:44:23,  1.65it/s]
 72%|███████▏  | 41300/57600 [7:15:21<2:48:03,  1.62it/s]
                                                         
{'loss': 1.1193, 'learning_rate': 3.55574912891986e-07, 'epoch': 455.85}

 72%|███████▏  | 41300/57600 [7:15:21<2:48:03,  1.62it/s]
 72%|███████▏  | 41301/57600 [7:15:21<2:50:24,  1.59it/s]
 72%|███████▏  | 41302/57600 [7:15:22<2:50:03,  1.60it/s]
 72%|███████▏  | 41303/57600 [7:15:23<2:48:14,  1.61it/s]
 72%|███████▏  | 41304/57600 [7:15:23<2:54:07,  1.56it/s]
 72%|███████▏  | 41305/57600 [7:15:24<2:53:52,  1.56it/s]
 72%|███████▏  | 41306/57600 [7:15:25<2:50:41,  1.59it/s]
 72%|███████▏  | 41307/57600 [7:15:25<2:53:38,  1.56it/s]
 72%|███████▏  | 41308/57600 [7:15:26<2:54:06,  1.56it/s]
 72%|███████▏  | 41309/57600 [7:15:27<2:56:04,  1.54it/s]
 72%|███████▏  | 41310/57600 [7:15:27<2:54:13,  1.56it/s]
 72%|███████▏  | 41311/57600 [7:15:28<2:49:12,  1.60it/s]
 72%|███████▏  | 41312/57600 [7:15:28<2:54:48,  1.55it/s]
 72%|███████▏  | 41313/57600 [7:15:29<2:51:15,  1.59it/s]
 72%|███████▏  | 41314/57600 [7:15:30<2:53:44,  1.56it/s]
 72%|███████▏  | 41315/57600 [7:15:30<2:53:02,  1.57it/s]
 72%|███████▏  | 41316/57600 [7:15:31<2:51:12,  1.59it/s]
 72%|███████▏  | 41317/57600 [7:15:32<2:49:05,  1.60it/s]
 72%|███████▏  | 41318/57600 [7:15:32<2:54:40,  1.55it/s]
 72%|███████▏  | 41319/57600 [7:15:33<2:52:17,  1.57it/s]
 72%|███████▏  | 41320/57600 [7:15:33<2:47:43,  1.62it/s]
                                                         
{'loss': 1.1411, 'learning_rate': 3.552613240418119e-07, 'epoch': 456.07}

 72%|███████▏  | 41320/57600 [7:15:33<2:47:43,  1.62it/s]
 72%|███████▏  | 41321/57600 [7:15:34<2:54:44,  1.55it/s]
 72%|███████▏  | 41322/57600 [7:15:35<2:50:02,  1.60it/s]
 72%|███████▏  | 41323/57600 [7:15:35<2:48:07,  1.61it/s]
 72%|███████▏  | 41324/57600 [7:15:36<2:47:33,  1.62it/s]
 72%|███████▏  | 41325/57600 [7:15:37<2:53:44,  1.56it/s]
 72%|███████▏  | 41326/57600 [7:15:37<2:53:57,  1.56it/s]
 72%|███████▏  | 41327/57600 [7:15:38<2:55:41,  1.54it/s]
 72%|███████▏  | 41328/57600 [7:15:39<2:51:36,  1.58it/s]
 72%|███████▏  | 41329/57600 [7:15:39<2:51:08,  1.58it/s]
 72%|███████▏  | 41330/57600 [7:15:40<2:48:41,  1.61it/s]
 72%|███████▏  | 41331/57600 [7:15:40<2:46:07,  1.63it/s]
 72%|███████▏  | 41332/57600 [7:15:41<2:57:07,  1.53it/s]
 72%|███████▏  | 41333/57600 [7:15:42<2:54:45,  1.55it/s]
 72%|███████▏  | 41334/57600 [7:15:42<2:53:35,  1.56it/s]
 72%|███████▏  | 41335/57600 [7:15:43<2:54:33,  1.55it/s]
 72%|███████▏  | 41336/57600 [7:15:44<2:51:46,  1.58it/s]
 72%|███████▏  | 41337/57600 [7:15:44<2:49:14,  1.60it/s]
 72%|███████▏  | 41338/57600 [7:15:45<2:59:18,  1.51it/s]
 72%|███████▏  | 41339/57600 [7:15:46<3:00:11,  1.50it/s]
 72%|███████▏  | 41340/57600 [7:15:46<2:58:23,  1.52it/s]
                                                         
{'loss': 1.1061, 'learning_rate': 3.549477351916376e-07, 'epoch': 456.29}

 72%|███████▏  | 41340/57600 [7:15:46<2:58:23,  1.52it/s]
 72%|███████▏  | 41341/57600 [7:15:47<2:53:44,  1.56it/s]
 72%|███████▏  | 41342/57600 [7:15:48<2:50:44,  1.59it/s]
 72%|███████▏  | 41343/57600 [7:15:48<2:50:54,  1.59it/s]
 72%|███████▏  | 41344/57600 [7:15:49<2:54:17,  1.55it/s]
 72%|███████▏  | 41345/57600 [7:15:49<2:50:30,  1.59it/s]
 72%|███████▏  | 41346/57600 [7:15:50<2:47:38,  1.62it/s]
 72%|███████▏  | 41347/57600 [7:15:51<2:50:30,  1.59it/s]
 72%|███████▏  | 41348/57600 [7:15:51<2:44:04,  1.65it/s]
 72%|███████▏  | 41349/57600 [7:15:52<2:46:00,  1.63it/s]
 72%|███████▏  | 41350/57600 [7:15:52<2:42:43,  1.66it/s]
 72%|███████▏  | 41351/57600 [7:15:53<2:50:09,  1.59it/s]
 72%|███████▏  | 41352/57600 [7:15:54<2:51:47,  1.58it/s]
 72%|███████▏  | 41353/57600 [7:15:54<2:51:38,  1.58it/s]
 72%|███████▏  | 41354/57600 [7:15:55<2:50:37,  1.59it/s]
 72%|███████▏  | 41355/57600 [7:15:56<2:49:50,  1.59it/s]
 72%|███████▏  | 41356/57600 [7:15:56<2:46:59,  1.62it/s]
 72%|███████▏  | 41357/57600 [7:15:57<2:43:30,  1.66it/s]
 72%|███████▏  | 41358/57600 [7:15:58<2:51:20,  1.58it/s]
 72%|███████▏  | 41359/57600 [7:15:58<2:51:45,  1.58it/s]
 72%|███████▏  | 41360/57600 [7:15:59<2:47:51,  1.61it/s]
                                                         
{'loss': 1.1603, 'learning_rate': 3.5463414634146344e-07, 'epoch': 456.51}

 72%|███████▏  | 41360/57600 [7:15:59<2:47:51,  1.61it/s]
 72%|███████▏  | 41361/57600 [7:15:59<2:48:45,  1.60it/s]
 72%|███████▏  | 41362/57600 [7:16:00<2:50:31,  1.59it/s]
 72%|███████▏  | 41363/57600 [7:16:01<2:46:55,  1.62it/s]
 72%|███████▏  | 41364/57600 [7:16:01<2:45:29,  1.64it/s]
 72%|███████▏  | 41365/57600 [7:16:02<2:49:06,  1.60it/s]
 72%|███████▏  | 41366/57600 [7:16:02<2:45:33,  1.63it/s]
 72%|███████▏  | 41367/57600 [7:16:03<2:53:31,  1.56it/s]
 72%|███████▏  | 41368/57600 [7:16:04<2:52:35,  1.57it/s]
 72%|███████▏  | 41369/57600 [7:16:04<2:50:20,  1.59it/s]
 72%|███████▏  | 41370/57600 [7:16:05<2:52:50,  1.56it/s]
 72%|███████▏  | 41371/57600 [7:16:06<2:55:29,  1.54it/s]
 72%|███████▏  | 41372/57600 [7:16:06<2:57:24,  1.52it/s]
 72%|███████▏  | 41373/57600 [7:16:07<2:55:41,  1.54it/s]
 72%|███████▏  | 41374/57600 [7:16:08<2:55:08,  1.54it/s]
 72%|███████▏  | 41375/57600 [7:16:08<2:56:48,  1.53it/s]
 72%|███████▏  | 41376/57600 [7:16:09<2:54:20,  1.55it/s]
 72%|███████▏  | 41377/57600 [7:16:10<2:54:37,  1.55it/s]
 72%|███████▏  | 41378/57600 [7:16:10<2:58:56,  1.51it/s]
 72%|███████▏  | 41379/57600 [7:16:11<2:57:51,  1.52it/s]
 72%|███████▏  | 41380/57600 [7:16:12<2:52:01,  1.57it/s]
                                                         
{'loss': 1.0956, 'learning_rate': 3.5432055749128914e-07, 'epoch': 456.73}

 72%|███████▏  | 41380/57600 [7:16:12<2:52:01,  1.57it/s]
 72%|███████▏  | 41381/57600 [7:16:12<2:48:21,  1.61it/s]
 72%|███████▏  | 41382/57600 [7:16:13<2:48:16,  1.61it/s]
 72%|███████▏  | 41383/57600 [7:16:13<2:48:00,  1.61it/s]
 72%|███████▏  | 41384/57600 [7:16:14<2:44:38,  1.64it/s]
 72%|███████▏  | 41385/57600 [7:16:15<2:42:02,  1.67it/s]
 72%|███████▏  | 41386/57600 [7:16:15<2:42:39,  1.66it/s]
 72%|███████▏  | 41387/57600 [7:16:16<2:41:30,  1.67it/s]
 72%|███████▏  | 41388/57600 [7:16:16<2:42:59,  1.66it/s]
 72%|███████▏  | 41389/57600 [7:16:17<2:45:40,  1.63it/s]
 72%|███████▏  | 41390/57600 [7:16:18<2:48:53,  1.60it/s]
 72%|███████▏  | 41391/57600 [7:16:18<2:52:05,  1.57it/s]
 72%|███████▏  | 41392/57600 [7:16:19<2:53:57,  1.55it/s]
 72%|███████▏  | 41393/57600 [7:16:20<2:48:03,  1.61it/s]
 72%|███████▏  | 41394/57600 [7:16:20<2:50:48,  1.58it/s]
 72%|███████▏  | 41395/57600 [7:16:21<2:46:45,  1.62it/s]
 72%|███████▏  | 41396/57600 [7:16:21<2:46:33,  1.62it/s]
 72%|███████▏  | 41397/57600 [7:16:22<2:46:09,  1.63it/s]
 72%|███████▏  | 41398/57600 [7:16:23<2:55:14,  1.54it/s]
 72%|███████▏  | 41399/57600 [7:16:23<2:47:08,  1.62it/s]
 72%|███████▏  | 41400/57600 [7:16:24<2:48:28,  1.60it/s]
                                                         
{'loss': 1.1584, 'learning_rate': 3.54006968641115e-07, 'epoch': 456.95}

 72%|███████▏  | 41400/57600 [7:16:24<2:48:28,  1.60it/s]
 72%|███████▏  | 41401/57600 [7:16:24<2:45:10,  1.63it/s]
 72%|███████▏  | 41402/57600 [7:16:25<2:43:34,  1.65it/s]
 72%|███████▏  | 41403/57600 [7:16:26<2:47:05,  1.62it/s]
 72%|███████▏  | 41404/57600 [7:16:26<2:44:34,  1.64it/s]
 72%|███████▏  | 41405/57600 [7:16:27<2:57:18,  1.52it/s]
 72%|███████▏  | 41406/57600 [7:16:28<2:54:31,  1.55it/s]
 72%|███████▏  | 41407/57600 [7:16:28<2:51:12,  1.58it/s]
 72%|███████▏  | 41408/57600 [7:16:29<3:00:33,  1.49it/s]
 72%|███████▏  | 41409/57600 [7:16:30<2:58:40,  1.51it/s]
 72%|███████▏  | 41410/57600 [7:16:30<2:56:48,  1.53it/s]
 72%|███████▏  | 41411/57600 [7:16:31<2:55:04,  1.54it/s]
 72%|███████▏  | 41412/57600 [7:16:32<2:56:33,  1.53it/s]
 72%|███████▏  | 41413/57600 [7:16:32<2:54:27,  1.55it/s]
 72%|███████▏  | 41414/57600 [7:16:33<2:55:06,  1.54it/s]
 72%|███████▏  | 41415/57600 [7:16:34<2:55:44,  1.53it/s]
 72%|███████▏  | 41416/57600 [7:16:34<2:55:27,  1.54it/s]
 72%|███████▏  | 41417/57600 [7:16:35<2:53:39,  1.55it/s]
 72%|███████▏  | 41418/57600 [7:16:35<2:48:40,  1.60it/s]
 72%|███████▏  | 41419/57600 [7:16:36<2:53:50,  1.55it/s]
 72%|███████▏  | 41420/57600 [7:16:37<2:52:10,  1.57it/s]
                                                         
{'loss': 1.1137, 'learning_rate': 3.536933797909407e-07, 'epoch': 457.17}

 72%|███████▏  | 41420/57600 [7:16:37<2:52:10,  1.57it/s]
 72%|███████▏  | 41421/57600 [7:16:37<2:51:10,  1.58it/s]
 72%|███████▏  | 41422/57600 [7:16:38<2:47:32,  1.61it/s]
 72%|███████▏  | 41423/57600 [7:16:39<2:48:33,  1.60it/s]
 72%|███████▏  | 41424/57600 [7:16:39<2:43:31,  1.65it/s]
 72%|███████▏  | 41425/57600 [7:16:40<2:40:51,  1.68it/s]
 72%|███████▏  | 41426/57600 [7:16:40<2:41:31,  1.67it/s]
 72%|███████▏  | 41427/57600 [7:16:41<2:40:09,  1.68it/s]
 72%|███████▏  | 41428/57600 [7:16:42<2:43:20,  1.65it/s]
 72%|███████▏  | 41429/57600 [7:16:42<2:45:23,  1.63it/s]
 72%|███████▏  | 41430/57600 [7:16:43<2:39:11,  1.69it/s]
 72%|███████▏  | 41431/57600 [7:16:43<2:48:47,  1.60it/s]
 72%|███████▏  | 41432/57600 [7:16:44<2:43:52,  1.64it/s]
 72%|███████▏  | 41433/57600 [7:16:45<2:51:25,  1.57it/s]
 72%|███████▏  | 41434/57600 [7:16:45<2:49:12,  1.59it/s]
 72%|███████▏  | 41435/57600 [7:16:46<2:46:13,  1.62it/s]
 72%|███████▏  | 41436/57600 [7:16:47<2:45:50,  1.62it/s]
 72%|███████▏  | 41437/57600 [7:16:47<2:43:10,  1.65it/s]
 72%|███████▏  | 41438/57600 [7:16:48<2:45:47,  1.62it/s]
 72%|███████▏  | 41439/57600 [7:16:48<2:43:26,  1.65it/s]
 72%|███████▏  | 41440/57600 [7:16:49<2:43:36,  1.65it/s]
                                                         
{'loss': 1.1808, 'learning_rate': 3.5337979094076655e-07, 'epoch': 457.4}

 72%|███████▏  | 41440/57600 [7:16:49<2:43:36,  1.65it/s]
 72%|███████▏  | 41441/57600 [7:16:50<2:45:42,  1.63it/s]
 72%|███████▏  | 41442/57600 [7:16:50<2:45:11,  1.63it/s]
 72%|███████▏  | 41443/57600 [7:16:51<2:44:41,  1.64it/s]
 72%|███████▏  | 41444/57600 [7:16:51<2:48:30,  1.60it/s]
 72%|███████▏  | 41445/57600 [7:16:52<2:49:49,  1.59it/s]
 72%|███████▏  | 41446/57600 [7:16:53<2:48:04,  1.60it/s]
 72%|███████▏  | 41447/57600 [7:16:53<2:52:07,  1.56it/s]
 72%|███████▏  | 41448/57600 [7:16:54<2:48:38,  1.60it/s]
 72%|███████▏  | 41449/57600 [7:16:55<2:47:21,  1.61it/s]
 72%|███████▏  | 41450/57600 [7:16:55<2:46:53,  1.61it/s]
 72%|███████▏  | 41451/57600 [7:16:56<2:48:27,  1.60it/s]
 72%|███████▏  | 41452/57600 [7:16:56<2:49:54,  1.58it/s]
 72%|███████▏  | 41453/57600 [7:16:57<2:47:51,  1.60it/s]
 72%|███████▏  | 41454/57600 [7:16:58<2:48:25,  1.60it/s]
 72%|███████▏  | 41455/57600 [7:16:58<2:48:18,  1.60it/s]
 72%|███████▏  | 41456/57600 [7:16:59<2:41:39,  1.66it/s]
 72%|███████▏  | 41457/57600 [7:16:59<2:40:25,  1.68it/s]
 72%|███████▏  | 41458/57600 [7:17:00<2:42:52,  1.65it/s]
 72%|███████▏  | 41459/57600 [7:17:01<2:40:17,  1.68it/s]
 72%|███████▏  | 41460/57600 [7:17:01<2:45:48,  1.62it/s]
                                                         
{'loss': 1.1562, 'learning_rate': 3.5306620209059236e-07, 'epoch': 457.62}

 72%|███████▏  | 41460/57600 [7:17:01<2:45:48,  1.62it/s]
 72%|███████▏  | 41461/57600 [7:17:02<2:41:06,  1.67it/s]
 72%|███████▏  | 41462/57600 [7:17:03<2:41:37,  1.66it/s]
 72%|███████▏  | 41463/57600 [7:17:03<2:43:41,  1.64it/s]
 72%|███████▏  | 41464/57600 [7:17:04<2:43:42,  1.64it/s]
 72%|███████▏  | 41465/57600 [7:17:04<2:49:40,  1.58it/s]
 72%|███████▏  | 41466/57600 [7:17:05<2:50:27,  1.58it/s]
 72%|███████▏  | 41467/57600 [7:17:06<2:56:51,  1.52it/s]
 72%|███████▏  | 41468/57600 [7:17:06<2:55:13,  1.53it/s]
 72%|███████▏  | 41469/57600 [7:17:07<2:55:29,  1.53it/s]
 72%|███████▏  | 41470/57600 [7:17:08<2:57:30,  1.51it/s]
 72%|███████▏  | 41471/57600 [7:17:08<2:52:46,  1.56it/s]
 72%|███████▏  | 41472/57600 [7:17:09<2:54:25,  1.54it/s]
 72%|███████▏  | 41473/57600 [7:17:10<2:55:28,  1.53it/s]
 72%|███████▏  | 41474/57600 [7:17:10<2:56:44,  1.52it/s]
 72%|███████▏  | 41475/57600 [7:17:11<2:53:00,  1.55it/s]
 72%|███████▏  | 41476/57600 [7:17:12<2:52:14,  1.56it/s]
 72%|███████▏  | 41477/57600 [7:17:12<2:54:15,  1.54it/s]
 72%|███████▏  | 41478/57600 [7:17:13<2:58:04,  1.51it/s]
 72%|███████▏  | 41479/57600 [7:17:14<2:55:56,  1.53it/s]
 72%|███████▏  | 41480/57600 [7:17:14<2:57:05,  1.52it/s]
                                                         
{'loss': 1.0854, 'learning_rate': 3.527526132404181e-07, 'epoch': 457.84}

 72%|███████▏  | 41480/57600 [7:17:14<2:57:05,  1.52it/s]
 72%|███████▏  | 41481/57600 [7:17:15<2:50:01,  1.58it/s]
 72%|███████▏  | 41482/57600 [7:17:16<2:56:30,  1.52it/s]
 72%|███████▏  | 41483/57600 [7:17:16<2:56:46,  1.52it/s]
 72%|███████▏  | 41484/57600 [7:17:17<2:50:57,  1.57it/s]
 72%|███████▏  | 41485/57600 [7:17:17<2:47:52,  1.60it/s]
 72%|███████▏  | 41486/57600 [7:17:18<2:49:08,  1.59it/s]
 72%|███████▏  | 41487/57600 [7:17:19<2:52:11,  1.56it/s]
 72%|███████▏  | 41488/57600 [7:17:19<2:47:05,  1.61it/s]
 72%|███████▏  | 41489/57600 [7:17:20<2:46:23,  1.61it/s]
 72%|███████▏  | 41490/57600 [7:17:21<2:44:53,  1.63it/s]
 72%|███████▏  | 41491/57600 [7:17:21<2:48:25,  1.59it/s]
 72%|███████▏  | 41492/57600 [7:17:22<2:48:41,  1.59it/s]
 72%|███████▏  | 41493/57600 [7:17:22<2:52:23,  1.56it/s]
 72%|███████▏  | 41494/57600 [7:17:23<2:48:51,  1.59it/s]
 72%|███████▏  | 41495/57600 [7:17:24<3:00:03,  1.49it/s]
 72%|███████▏  | 41496/57600 [7:17:24<2:55:30,  1.53it/s]
 72%|███████▏  | 41497/57600 [7:17:25<2:52:11,  1.56it/s]
 72%|███████▏  | 41498/57600 [7:17:26<2:50:21,  1.58it/s]
 72%|███████▏  | 41499/57600 [7:17:26<2:54:12,  1.54it/s]
 72%|███████▏  | 41500/57600 [7:17:27<2:49:08,  1.59it/s]
                                                         
{'loss': 1.1344, 'learning_rate': 3.524390243902439e-07, 'epoch': 458.06}

 72%|███████▏  | 41500/57600 [7:17:27<2:49:08,  1.59it/s]
 72%|███████▏  | 41501/57600 [7:17:28<2:49:41,  1.58it/s]
 72%|███████▏  | 41502/57600 [7:17:28<2:46:54,  1.61it/s]
 72%|███████▏  | 41503/57600 [7:17:29<2:40:34,  1.67it/s]
 72%|███████▏  | 41504/57600 [7:17:29<2:44:13,  1.63it/s]
 72%|███████▏  | 41505/57600 [7:17:30<2:41:42,  1.66it/s]
 72%|███████▏  | 41506/57600 [7:17:31<2:43:36,  1.64it/s]
 72%|███████▏  | 41507/57600 [7:17:31<2:50:28,  1.57it/s]
 72%|███████▏  | 41508/57600 [7:17:32<2:50:12,  1.58it/s]
 72%|███████▏  | 41509/57600 [7:17:33<2:52:02,  1.56it/s]
 72%|███████▏  | 41510/57600 [7:17:33<2:56:10,  1.52it/s]
 72%|███████▏  | 41511/57600 [7:17:34<2:52:05,  1.56it/s]
 72%|███████▏  | 41512/57600 [7:17:34<2:49:39,  1.58it/s]
 72%|███████▏  | 41513/57600 [7:17:35<2:46:03,  1.61it/s]
 72%|███████▏  | 41514/57600 [7:17:36<2:45:40,  1.62it/s]
 72%|███████▏  | 41515/57600 [7:17:36<2:49:22,  1.58it/s]
 72%|███████▏  | 41516/57600 [7:17:37<2:49:13,  1.58it/s]
 72%|███████▏  | 41517/57600 [7:17:38<2:52:28,  1.55it/s]
 72%|███████▏  | 41518/57600 [7:17:38<2:49:09,  1.58it/s]
 72%|███████▏  | 41519/57600 [7:17:39<2:54:07,  1.54it/s]
 72%|███████▏  | 41520/57600 [7:17:40<2:51:23,  1.56it/s]
                                                         
{'loss': 1.154, 'learning_rate': 3.521254355400696e-07, 'epoch': 458.28}

 72%|███████▏  | 41520/57600 [7:17:40<2:51:23,  1.56it/s]
 72%|███████▏  | 41521/57600 [7:17:40<2:47:56,  1.60it/s]
 72%|███████▏  | 41522/57600 [7:17:41<2:54:19,  1.54it/s]
 72%|███████▏  | 41523/57600 [7:17:41<2:49:47,  1.58it/s]
 72%|███████▏  | 41524/57600 [7:17:42<2:48:50,  1.59it/s]
 72%|███████▏  | 41525/57600 [7:17:43<2:47:09,  1.60it/s]
 72%|███████▏  | 41526/57600 [7:17:43<2:44:56,  1.62it/s]
 72%|███████▏  | 41527/57600 [7:17:44<2:42:16,  1.65it/s]
 72%|███████▏  | 41528/57600 [7:17:44<2:44:32,  1.63it/s]
 72%|███████▏  | 41529/57600 [7:17:45<2:47:51,  1.60it/s]
 72%|███████▏  | 41530/57600 [7:17:46<2:52:50,  1.55it/s]
 72%|███████▏  | 41531/57600 [7:17:46<2:53:39,  1.54it/s]
 72%|███████▏  | 41532/57600 [7:17:47<2:49:42,  1.58it/s]
 72%|███████▏  | 41533/57600 [7:17:48<2:48:22,  1.59it/s]
 72%|███████▏  | 41534/57600 [7:17:48<2:43:09,  1.64it/s]
 72%|███████▏  | 41535/57600 [7:17:49<2:42:35,  1.65it/s]
 72%|███████▏  | 41536/57600 [7:17:49<2:43:06,  1.64it/s]
 72%|███████▏  | 41537/57600 [7:17:50<2:46:43,  1.61it/s]
 72%|███████▏  | 41538/57600 [7:17:51<2:41:50,  1.65it/s]
 72%|███████▏  | 41539/57600 [7:17:51<2:47:59,  1.59it/s]
 72%|███████▏  | 41540/57600 [7:17:52<2:49:59,  1.57it/s]
                                                         
{'loss': 1.1108, 'learning_rate': 3.518118466898954e-07, 'epoch': 458.5}

 72%|███████▏  | 41540/57600 [7:17:52<2:49:59,  1.57it/s]
 72%|███████▏  | 41541/57600 [7:17:53<2:48:58,  1.58it/s]
 72%|███████▏  | 41542/57600 [7:17:53<2:52:52,  1.55it/s]
 72%|███████▏  | 41543/57600 [7:17:54<2:49:31,  1.58it/s]
 72%|███████▏  | 41544/57600 [7:17:55<2:50:33,  1.57it/s]
 72%|███████▏  | 41545/57600 [7:17:55<2:53:01,  1.55it/s]
 72%|███████▏  | 41546/57600 [7:17:56<2:52:54,  1.55it/s]
 72%|███████▏  | 41547/57600 [7:17:57<2:53:36,  1.54it/s]
 72%|███████▏  | 41548/57600 [7:17:57<2:51:56,  1.56it/s]
 72%|███████▏  | 41549/57600 [7:17:58<2:45:45,  1.61it/s]
 72%|███████▏  | 41550/57600 [7:17:58<2:47:39,  1.60it/s]
 72%|███████▏  | 41551/57600 [7:17:59<2:50:22,  1.57it/s]
 72%|███████▏  | 41552/57600 [7:18:00<2:50:05,  1.57it/s]
 72%|███████▏  | 41553/57600 [7:18:00<2:49:24,  1.58it/s]
 72%|███████▏  | 41554/57600 [7:18:01<2:49:59,  1.57it/s]
 72%|███████▏  | 41555/57600 [7:18:02<2:46:14,  1.61it/s]
 72%|███████▏  | 41556/57600 [7:18:02<2:51:00,  1.56it/s]
 72%|███████▏  | 41557/57600 [7:18:03<2:48:18,  1.59it/s]
 72%|███████▏  | 41558/57600 [7:18:03<2:48:02,  1.59it/s]
 72%|███████▏  | 41559/57600 [7:18:04<2:47:11,  1.60it/s]
 72%|███████▏  | 41560/57600 [7:18:05<2:49:08,  1.58it/s]
                                                         
{'loss': 1.1306, 'learning_rate': 3.5149825783972117e-07, 'epoch': 458.72}

 72%|███████▏  | 41560/57600 [7:18:05<2:49:08,  1.58it/s]
 72%|███████▏  | 41561/57600 [7:18:05<2:56:47,  1.51it/s]
 72%|███████▏  | 41562/57600 [7:18:06<2:54:04,  1.54it/s]
 72%|███████▏  | 41563/57600 [7:18:07<2:50:15,  1.57it/s]
 72%|███████▏  | 41564/57600 [7:18:07<2:55:39,  1.52it/s]
 72%|███████▏  | 41565/57600 [7:18:08<2:52:14,  1.55it/s]
 72%|███████▏  | 41566/57600 [7:18:09<2:48:36,  1.58it/s]
 72%|███████▏  | 41567/57600 [7:18:09<2:43:56,  1.63it/s]
 72%|███████▏  | 41568/57600 [7:18:10<2:41:42,  1.65it/s]
 72%|███████▏  | 41569/57600 [7:18:10<2:43:20,  1.64it/s]
 72%|███████▏  | 41570/57600 [7:18:11<2:41:05,  1.66it/s]
 72%|███████▏  | 41571/57600 [7:18:12<2:46:46,  1.60it/s]
 72%|███████▏  | 41572/57600 [7:18:12<2:44:18,  1.63it/s]
 72%|███████▏  | 41573/57600 [7:18:13<2:41:46,  1.65it/s]
 72%|███████▏  | 41574/57600 [7:18:13<2:39:31,  1.67it/s]
 72%|███████▏  | 41575/57600 [7:18:14<2:46:47,  1.60it/s]
 72%|███████▏  | 41576/57600 [7:18:15<2:46:37,  1.60it/s]
 72%|███████▏  | 41577/57600 [7:18:16<2:59:15,  1.49it/s]
 72%|███████▏  | 41578/57600 [7:18:16<2:59:02,  1.49it/s]
 72%|███████▏  | 41579/57600 [7:18:17<2:56:28,  1.51it/s]
 72%|███████▏  | 41580/57600 [7:18:17<2:48:43,  1.58it/s]
                                                         
{'loss': 1.1684, 'learning_rate': 3.51184668989547e-07, 'epoch': 458.94}

 72%|███████▏  | 41580/57600 [7:18:17<2:48:43,  1.58it/s]
 72%|███████▏  | 41581/57600 [7:18:18<2:50:12,  1.57it/s]
 72%|███████▏  | 41582/57600 [7:18:19<2:50:54,  1.56it/s]
 72%|███████▏  | 41583/57600 [7:18:19<2:52:40,  1.55it/s]
 72%|███████▏  | 41584/57600 [7:18:20<2:51:49,  1.55it/s]
 72%|███████▏  | 41585/57600 [7:18:21<2:50:23,  1.57it/s]
 72%|███████▏  | 41586/57600 [7:18:21<2:57:43,  1.50it/s]
 72%|███████▏  | 41587/57600 [7:18:22<2:51:08,  1.56it/s]
 72%|███████▏  | 41588/57600 [7:18:23<2:52:56,  1.54it/s]
 72%|███████▏  | 41589/57600 [7:18:23<2:53:52,  1.53it/s]
 72%|███████▏  | 41590/57600 [7:18:24<2:51:49,  1.55it/s]
 72%|███████▏  | 41591/57600 [7:18:24<2:49:09,  1.58it/s]
 72%|███████▏  | 41592/57600 [7:18:25<2:51:32,  1.56it/s]
 72%|███████▏  | 41593/57600 [7:18:26<2:54:27,  1.53it/s]
 72%|███████▏  | 41594/57600 [7:18:26<2:54:03,  1.53it/s]
 72%|███████▏  | 41595/57600 [7:18:27<2:54:29,  1.53it/s]
 72%|███████▏  | 41596/57600 [7:18:28<2:52:47,  1.54it/s]
 72%|███████▏  | 41597/57600 [7:18:28<2:49:25,  1.57it/s]
 72%|███████▏  | 41598/57600 [7:18:29<2:48:25,  1.58it/s]
 72%|███████▏  | 41599/57600 [7:18:30<2:48:40,  1.58it/s]
 72%|███████▏  | 41600/57600 [7:18:30<2:47:10,  1.60it/s]
                                                         
{'loss': 1.1056, 'learning_rate': 3.5087108013937283e-07, 'epoch': 459.16}

 72%|███████▏  | 41600/57600 [7:18:30<2:47:10,  1.60it/s]
 72%|███████▏  | 41601/57600 [7:18:31<2:47:52,  1.59it/s]
 72%|███████▏  | 41602/57600 [7:18:31<2:45:20,  1.61it/s]
 72%|███████▏  | 41603/57600 [7:18:32<2:45:38,  1.61it/s]
 72%|███████▏  | 41604/57600 [7:18:33<2:48:22,  1.58it/s]
 72%|███████▏  | 41605/57600 [7:18:33<2:45:36,  1.61it/s]
 72%|███████▏  | 41606/57600 [7:18:34<2:44:51,  1.62it/s]
 72%|███████▏  | 41607/57600 [7:18:35<2:49:32,  1.57it/s]
 72%|███████▏  | 41608/57600 [7:18:35<2:46:15,  1.60it/s]
 72%|███████▏  | 41609/57600 [7:18:36<2:49:09,  1.58it/s]
 72%|███████▏  | 41610/57600 [7:18:36<2:46:53,  1.60it/s]
 72%|███████▏  | 41611/57600 [7:18:37<2:47:11,  1.59it/s]
 72%|███████▏  | 41612/57600 [7:18:38<2:47:53,  1.59it/s]
 72%|███████▏  | 41613/57600 [7:18:38<2:42:09,  1.64it/s]
 72%|███████▏  | 41614/57600 [7:18:39<2:43:45,  1.63it/s]
 72%|███████▏  | 41615/57600 [7:18:40<2:48:37,  1.58it/s]
 72%|███████▏  | 41616/57600 [7:18:40<2:47:09,  1.59it/s]
 72%|███████▏  | 41617/57600 [7:18:41<2:48:24,  1.58it/s]
 72%|███████▏  | 41618/57600 [7:18:42<2:48:32,  1.58it/s]
 72%|███████▏  | 41619/57600 [7:18:42<2:47:38,  1.59it/s]
 72%|███████▏  | 41620/57600 [7:18:43<2:52:48,  1.54it/s]
                                                         
{'loss': 1.125, 'learning_rate': 3.505574912891986e-07, 'epoch': 459.38}

 72%|███████▏  | 41620/57600 [7:18:43<2:52:48,  1.54it/s]
 72%|███████▏  | 41621/57600 [7:18:43<2:53:17,  1.54it/s]
 72%|███████▏  | 41622/57600 [7:18:44<2:49:31,  1.57it/s]
 72%|███████▏  | 41623/57600 [7:18:45<2:45:51,  1.61it/s]
 72%|███████▏  | 41624/57600 [7:18:45<2:57:17,  1.50it/s]
 72%|███████▏  | 41625/57600 [7:18:46<2:51:45,  1.55it/s]
 72%|███████▏  | 41626/57600 [7:18:47<2:48:16,  1.58it/s]
 72%|███████▏  | 41627/57600 [7:18:47<2:45:16,  1.61it/s]
 72%|███████▏  | 41628/57600 [7:18:48<2:48:40,  1.58it/s]
 72%|███████▏  | 41629/57600 [7:18:48<2:45:24,  1.61it/s]
 72%|███████▏  | 41630/57600 [7:18:49<2:41:29,  1.65it/s]
 72%|███████▏  | 41631/57600 [7:18:50<2:44:50,  1.61it/s]
 72%|███████▏  | 41632/57600 [7:18:50<2:46:34,  1.60it/s]
 72%|███████▏  | 41633/57600 [7:18:51<2:48:02,  1.58it/s]
 72%|███████▏  | 41634/57600 [7:18:52<2:46:10,  1.60it/s]
 72%|███████▏  | 41635/57600 [7:18:52<2:45:40,  1.61it/s]
 72%|███████▏  | 41636/57600 [7:18:53<2:46:24,  1.60it/s]
 72%|███████▏  | 41637/57600 [7:18:53<2:47:24,  1.59it/s]
 72%|███████▏  | 41638/57600 [7:18:54<2:46:05,  1.60it/s]
 72%|███████▏  | 41639/57600 [7:18:55<2:45:15,  1.61it/s]
 72%|███████▏  | 41640/57600 [7:18:55<2:43:15,  1.63it/s]
                                                         
{'loss': 1.1251, 'learning_rate': 3.502439024390244e-07, 'epoch': 459.6}

 72%|███████▏  | 41640/57600 [7:18:55<2:43:15,  1.63it/s]
 72%|███████▏  | 41641/57600 [7:18:56<2:41:40,  1.65it/s]
 72%|███████▏  | 41642/57600 [7:18:57<2:44:12,  1.62it/s]
 72%|███████▏  | 41643/57600 [7:18:57<2:50:36,  1.56it/s]
 72%|███████▏  | 41644/57600 [7:18:58<2:52:01,  1.55it/s]
 72%|███████▏  | 41645/57600 [7:18:59<2:57:07,  1.50it/s]
 72%|███████▏  | 41646/57600 [7:18:59<2:50:05,  1.56it/s]
 72%|███████▏  | 41647/57600 [7:19:00<2:50:17,  1.56it/s]
 72%|███████▏  | 41648/57600 [7:19:00<2:49:01,  1.57it/s]
 72%|███████▏  | 41649/57600 [7:19:01<2:46:57,  1.59it/s]
 72%|███████▏  | 41650/57600 [7:19:02<2:51:49,  1.55it/s]
 72%|███████▏  | 41651/57600 [7:19:02<2:46:05,  1.60it/s]
 72%|███████▏  | 41652/57600 [7:19:03<2:43:35,  1.62it/s]
 72%|███████▏  | 41653/57600 [7:19:04<2:42:26,  1.64it/s]
 72%|███████▏  | 41654/57600 [7:19:04<2:40:46,  1.65it/s]
 72%|███████▏  | 41655/57600 [7:19:05<2:37:18,  1.69it/s]
 72%|███████▏  | 41656/57600 [7:19:05<2:42:13,  1.64it/s]
 72%|███████▏  | 41657/57600 [7:19:06<2:46:17,  1.60it/s]
 72%|███████▏  | 41658/57600 [7:19:07<2:43:21,  1.63it/s]
 72%|███████▏  | 41659/57600 [7:19:07<2:52:40,  1.54it/s]
 72%|███████▏  | 41660/57600 [7:19:08<2:50:40,  1.56it/s]
                                                         
{'loss': 1.1147, 'learning_rate': 3.499303135888501e-07, 'epoch': 459.82}

 72%|███████▏  | 41660/57600 [7:19:08<2:50:40,  1.56it/s]
 72%|███████▏  | 41661/57600 [7:19:09<2:50:51,  1.55it/s]
 72%|███████▏  | 41662/57600 [7:19:09<2:47:43,  1.58it/s]
 72%|███████▏  | 41663/57600 [7:19:10<2:51:02,  1.55it/s]
 72%|███████▏  | 41664/57600 [7:19:10<2:46:25,  1.60it/s]
 72%|███████▏  | 41665/57600 [7:19:11<2:42:54,  1.63it/s]
 72%|███████▏  | 41666/57600 [7:19:12<2:40:05,  1.66it/s]
 72%|███████▏  | 41667/57600 [7:19:12<2:43:47,  1.62it/s]
 72%|███████▏  | 41668/57600 [7:19:13<2:40:20,  1.66it/s]
 72%|███████▏  | 41669/57600 [7:19:13<2:37:35,  1.68it/s]
 72%|███████▏  | 41670/57600 [7:19:14<2:49:46,  1.56it/s]
 72%|███████▏  | 41671/57600 [7:19:15<2:52:02,  1.54it/s]
 72%|███████▏  | 41672/57600 [7:19:15<2:50:21,  1.56it/s]
 72%|███████▏  | 41673/57600 [7:19:16<2:52:33,  1.54it/s]
 72%|███████▏  | 41674/57600 [7:19:17<2:52:11,  1.54it/s]
 72%|███████▏  | 41675/57600 [7:19:18<2:58:51,  1.48it/s]
 72%|███████▏  | 41676/57600 [7:19:18<2:50:58,  1.55it/s]
 72%|███████▏  | 41677/57600 [7:19:19<2:52:43,  1.54it/s]
 72%|███████▏  | 41678/57600 [7:19:19<2:49:08,  1.57it/s]
 72%|███████▏  | 41679/57600 [7:19:20<2:51:11,  1.55it/s]
 72%|███████▏  | 41680/57600 [7:19:21<2:47:13,  1.59it/s]
                                                         
{'loss': 1.1571, 'learning_rate': 3.4961672473867594e-07, 'epoch': 460.04}

 72%|███████▏  | 41680/57600 [7:19:21<2:47:13,  1.59it/s]
 72%|███████▏  | 41681/57600 [7:19:21<2:48:05,  1.58it/s]
 72%|███████▏  | 41682/57600 [7:19:22<2:45:52,  1.60it/s]
 72%|███████▏  | 41683/57600 [7:19:22<2:41:53,  1.64it/s]
 72%|███████▏  | 41684/57600 [7:19:23<2:38:08,  1.68it/s]
 72%|███████▏  | 41685/57600 [7:19:24<2:40:59,  1.65it/s]
 72%|███████▏  | 41686/57600 [7:19:24<2:46:37,  1.59it/s]
 72%|███████▏  | 41687/57600 [7:19:25<2:47:09,  1.59it/s]
 72%|███████▏  | 41688/57600 [7:19:26<2:45:30,  1.60it/s]
 72%|███████▏  | 41689/57600 [7:19:26<2:45:23,  1.60it/s]
 72%|███████▏  | 41690/57600 [7:19:27<2:46:34,  1.59it/s]
 72%|███████▏  | 41691/57600 [7:19:27<2:43:17,  1.62it/s]
 72%|███████▏  | 41692/57600 [7:19:28<2:45:59,  1.60it/s]
 72%|███████▏  | 41693/57600 [7:19:29<2:47:59,  1.58it/s]
 72%|███████▏  | 41694/57600 [7:19:29<2:45:44,  1.60it/s]
 72%|███████▏  | 41695/57600 [7:19:30<2:47:41,  1.58it/s]
 72%|███████▏  | 41696/57600 [7:19:31<2:45:31,  1.60it/s]
 72%|███████▏  | 41697/57600 [7:19:31<2:46:38,  1.59it/s]
 72%|███████▏  | 41698/57600 [7:19:32<2:46:37,  1.59it/s]
 72%|███████▏  | 41699/57600 [7:19:32<2:46:05,  1.60it/s]
 72%|███████▏  | 41700/57600 [7:19:33<2:44:48,  1.61it/s]
                                                         
{'loss': 1.1576, 'learning_rate': 3.493031358885017e-07, 'epoch': 460.26}

 72%|███████▏  | 41700/57600 [7:19:33<2:44:48,  1.61it/s]
 72%|███████▏  | 41701/57600 [7:19:34<2:44:32,  1.61it/s]
 72%|███████▏  | 41702/57600 [7:19:34<2:45:10,  1.60it/s]
 72%|███████▏  | 41703/57600 [7:19:35<2:50:35,  1.55it/s]
 72%|███████▏  | 41704/57600 [7:19:36<2:50:41,  1.55it/s]
 72%|███████▏  | 41705/57600 [7:19:36<2:45:18,  1.60it/s]
 72%|███████▏  | 41706/57600 [7:19:37<2:42:20,  1.63it/s]
 72%|███████▏  | 41707/57600 [7:19:37<2:48:16,  1.57it/s]
 72%|███████▏  | 41708/57600 [7:19:38<2:47:25,  1.58it/s]
 72%|███████▏  | 41709/57600 [7:19:39<2:51:10,  1.55it/s]
 72%|███████▏  | 41710/57600 [7:19:39<2:48:45,  1.57it/s]
 72%|███████▏  | 41711/57600 [7:19:40<2:44:04,  1.61it/s]
 72%|███████▏  | 41712/57600 [7:19:41<2:40:42,  1.65it/s]
 72%|███████▏  | 41713/57600 [7:19:41<2:42:19,  1.63it/s]
 72%|███████▏  | 41714/57600 [7:19:42<2:40:34,  1.65it/s]
 72%|███████▏  | 41715/57600 [7:19:42<2:37:22,  1.68it/s]
 72%|███████▏  | 41716/57600 [7:19:43<2:36:01,  1.70it/s]
 72%|███████▏  | 41717/57600 [7:19:44<2:39:43,  1.66it/s]
 72%|███████▏  | 41718/57600 [7:19:44<2:46:21,  1.59it/s]
 72%|███████▏  | 41719/57600 [7:19:45<2:47:45,  1.58it/s]
 72%|███████▏  | 41720/57600 [7:19:45<2:43:22,  1.62it/s]
                                                         
{'loss': 1.1273, 'learning_rate': 3.489895470383275e-07, 'epoch': 460.49}

 72%|███████▏  | 41720/57600 [7:19:45<2:43:22,  1.62it/s]
 72%|███████▏  | 41721/57600 [7:19:46<2:52:12,  1.54it/s]
 72%|███████▏  | 41722/57600 [7:19:47<2:52:18,  1.54it/s]
 72%|███████▏  | 41723/57600 [7:19:47<2:47:07,  1.58it/s]
 72%|███████▏  | 41724/57600 [7:19:48<2:51:13,  1.55it/s]
 72%|███████▏  | 41725/57600 [7:19:49<2:46:50,  1.59it/s]
 72%|███████▏  | 41726/57600 [7:19:49<2:48:38,  1.57it/s]
 72%|███████▏  | 41727/57600 [7:19:50<2:44:16,  1.61it/s]
 72%|███████▏  | 41728/57600 [7:19:51<2:42:58,  1.62it/s]
 72%|███████▏  | 41729/57600 [7:19:51<2:43:12,  1.62it/s]
 72%|███████▏  | 41730/57600 [7:19:52<2:46:58,  1.58it/s]
 72%|███████▏  | 41731/57600 [7:19:52<2:41:11,  1.64it/s]
 72%|███████▏  | 41732/57600 [7:19:53<2:51:21,  1.54it/s]
 72%|███████▏  | 41733/57600 [7:19:54<2:51:40,  1.54it/s]
 72%|███████▏  | 41734/57600 [7:19:54<2:46:07,  1.59it/s]
 72%|███████▏  | 41735/57600 [7:19:55<2:41:39,  1.64it/s]
 72%|███████▏  | 41736/57600 [7:19:56<2:40:57,  1.64it/s]
 72%|███████▏  | 41737/57600 [7:19:56<2:46:27,  1.59it/s]
 72%|███████▏  | 41738/57600 [7:19:57<2:46:57,  1.58it/s]
 72%|███████▏  | 41739/57600 [7:19:58<2:49:14,  1.56it/s]
 72%|███████▏  | 41740/57600 [7:19:58<2:47:37,  1.58it/s]
                                                         
{'loss': 1.1376, 'learning_rate': 3.486759581881533e-07, 'epoch': 460.71}

 72%|███████▏  | 41740/57600 [7:19:58<2:47:37,  1.58it/s]
 72%|███████▏  | 41741/57600 [7:19:59<2:59:20,  1.47it/s]
 72%|███████▏  | 41742/57600 [7:20:00<2:57:51,  1.49it/s]
 72%|███████▏  | 41743/57600 [7:20:00<2:50:52,  1.55it/s]
 72%|███████▏  | 41744/57600 [7:20:01<2:50:13,  1.55it/s]
 72%|███████▏  | 41745/57600 [7:20:01<2:44:26,  1.61it/s]
 72%|███████▏  | 41746/57600 [7:20:02<2:47:48,  1.57it/s]
 72%|███████▏  | 41747/57600 [7:20:03<2:41:48,  1.63it/s]
 72%|███████▏  | 41748/57600 [7:20:03<2:42:59,  1.62it/s]
 72%|███████▏  | 41749/57600 [7:20:04<2:42:42,  1.62it/s]
 72%|███████▏  | 41750/57600 [7:20:04<2:44:02,  1.61it/s]
 72%|███████▏  | 41751/57600 [7:20:05<2:45:17,  1.60it/s]
 72%|███████▏  | 41752/57600 [7:20:06<2:46:49,  1.58it/s]
 72%|███████▏  | 41753/57600 [7:20:06<2:51:01,  1.54it/s]
 72%|███████▏  | 41754/57600 [7:20:07<2:48:44,  1.57it/s]
 72%|███████▏  | 41755/57600 [7:20:08<2:55:33,  1.50it/s]
 72%|███████▏  | 41756/57600 [7:20:08<2:51:08,  1.54it/s]
 72%|███████▏  | 41757/57600 [7:20:09<2:50:23,  1.55it/s]
 72%|███████▏  | 41758/57600 [7:20:10<2:46:30,  1.59it/s]
 72%|███████▏  | 41759/57600 [7:20:10<2:47:08,  1.58it/s]
 72%|███████▎  | 41760/57600 [7:20:11<2:46:34,  1.58it/s]
                                                         
{'loss': 1.1215, 'learning_rate': 3.4836236933797906e-07, 'epoch': 460.93}

 72%|███████▎  | 41760/57600 [7:20:11<2:46:34,  1.58it/s]
 73%|███████▎  | 41761/57600 [7:20:11<2:43:50,  1.61it/s]
 73%|███████▎  | 41762/57600 [7:20:12<2:47:57,  1.57it/s]
 73%|███████▎  | 41763/57600 [7:20:13<2:52:50,  1.53it/s]
 73%|███████▎  | 41764/57600 [7:20:14<2:52:32,  1.53it/s]
 73%|███████▎  | 41765/57600 [7:20:14<2:48:04,  1.57it/s]
 73%|███████▎  | 41766/57600 [7:20:15<2:48:34,  1.57it/s]
 73%|███████▎  | 41767/57600 [7:20:16<3:01:49,  1.45it/s]
 73%|███████▎  | 41768/57600 [7:20:16<2:54:06,  1.52it/s]
 73%|███████▎  | 41769/57600 [7:20:17<2:49:17,  1.56it/s]
 73%|███████▎  | 41770/57600 [7:20:17<2:47:04,  1.58it/s]
 73%|███████▎  | 41771/57600 [7:20:18<2:48:46,  1.56it/s]
 73%|███████▎  | 41772/57600 [7:20:19<2:53:27,  1.52it/s]
 73%|███████▎  | 41773/57600 [7:20:19<2:50:55,  1.54it/s]
 73%|███████▎  | 41774/57600 [7:20:20<2:51:19,  1.54it/s]
 73%|███████▎  | 41775/57600 [7:20:21<2:52:14,  1.53it/s]
 73%|███████▎  | 41776/57600 [7:20:21<2:51:00,  1.54it/s]
 73%|███████▎  | 41777/57600 [7:20:22<2:45:36,  1.59it/s]
 73%|███████▎  | 41778/57600 [7:20:23<2:47:56,  1.57it/s]
 73%|███████▎  | 41779/57600 [7:20:23<2:47:16,  1.58it/s]
 73%|███████▎  | 41780/57600 [7:20:24<2:47:12,  1.58it/s]
                                                         
{'loss': 1.1083, 'learning_rate': 3.4804878048780486e-07, 'epoch': 461.15}

 73%|███████▎  | 41780/57600 [7:20:24<2:47:12,  1.58it/s]
 73%|███████▎  | 41781/57600 [7:20:24<2:45:49,  1.59it/s]
 73%|███████▎  | 41782/57600 [7:20:25<2:44:42,  1.60it/s]
 73%|███████▎  | 41783/57600 [7:20:26<2:41:12,  1.64it/s]
 73%|███████▎  | 41784/57600 [7:20:26<2:45:38,  1.59it/s]
 73%|███████▎  | 41785/57600 [7:20:27<2:42:24,  1.62it/s]
 73%|███████▎  | 41786/57600 [7:20:28<2:49:07,  1.56it/s]
 73%|███████▎  | 41787/57600 [7:20:28<2:46:40,  1.58it/s]
 73%|███████▎  | 41788/57600 [7:20:29<2:49:21,  1.56it/s]
 73%|███████▎  | 41789/57600 [7:20:29<2:45:28,  1.59it/s]
 73%|███████▎  | 41790/57600 [7:20:30<2:42:09,  1.62it/s]
 73%|███████▎  | 41791/57600 [7:20:31<2:43:48,  1.61it/s]
 73%|███████▎  | 41792/57600 [7:20:31<2:42:02,  1.63it/s]
 73%|███████▎  | 41793/57600 [7:20:32<2:44:47,  1.60it/s]
 73%|███████▎  | 41794/57600 [7:20:32<2:41:23,  1.63it/s]
 73%|███████▎  | 41795/57600 [7:20:33<2:40:16,  1.64it/s]
 73%|███████▎  | 41796/57600 [7:20:34<2:39:34,  1.65it/s]
 73%|███████▎  | 41797/57600 [7:20:34<2:37:36,  1.67it/s]
 73%|███████▎  | 41798/57600 [7:20:35<2:33:45,  1.71it/s]
 73%|███████▎  | 41799/57600 [7:20:36<2:42:29,  1.62it/s]
 73%|███████▎  | 41800/57600 [7:20:36<2:42:05,  1.62it/s]
                                                         
{'loss': 1.1667, 'learning_rate': 3.477351916376306e-07, 'epoch': 461.37}

 73%|███████▎  | 41800/57600 [7:20:36<2:42:05,  1.62it/s]
 73%|███████▎  | 41801/57600 [7:20:37<2:37:58,  1.67it/s]
 73%|███████▎  | 41802/57600 [7:20:37<2:40:18,  1.64it/s]
 73%|███████▎  | 41803/57600 [7:20:38<2:41:00,  1.64it/s]
 73%|███████▎  | 41804/57600 [7:20:39<2:39:51,  1.65it/s]
 73%|███████▎  | 41805/57600 [7:20:39<2:39:09,  1.65it/s]
 73%|███████▎  | 41806/57600 [7:20:40<2:37:04,  1.68it/s]
 73%|███████▎  | 41807/57600 [7:20:40<2:39:33,  1.65it/s]
 73%|███████▎  | 41808/57600 [7:20:41<2:50:49,  1.54it/s]
 73%|███████▎  | 41809/57600 [7:20:42<2:47:26,  1.57it/s]
 73%|███████▎  | 41810/57600 [7:20:42<2:45:25,  1.59it/s]
 73%|███████▎  | 41811/57600 [7:20:43<2:47:35,  1.57it/s]
 73%|███████▎  | 41812/57600 [7:20:44<2:49:08,  1.56it/s]
 73%|███████▎  | 41813/57600 [7:20:44<2:44:33,  1.60it/s]
 73%|███████▎  | 41814/57600 [7:20:45<2:42:44,  1.62it/s]
 73%|███████▎  | 41815/57600 [7:20:46<2:51:09,  1.54it/s]
 73%|███████▎  | 41816/57600 [7:20:46<2:51:32,  1.53it/s]
 73%|███████▎  | 41817/57600 [7:20:47<2:51:44,  1.53it/s]
 73%|███████▎  | 41818/57600 [7:20:48<2:52:58,  1.52it/s]
 73%|███████▎  | 41819/57600 [7:20:48<2:45:53,  1.59it/s]
 73%|███████▎  | 41820/57600 [7:20:49<2:42:43,  1.62it/s]
                                                         
{'loss': 1.1311, 'learning_rate': 3.474216027874564e-07, 'epoch': 461.59}

 73%|███████▎  | 41820/57600 [7:20:49<2:42:43,  1.62it/s]
 73%|███████▎  | 41821/57600 [7:20:49<2:44:49,  1.60it/s]
 73%|███████▎  | 41822/57600 [7:20:50<2:48:02,  1.56it/s]
 73%|███████▎  | 41823/57600 [7:20:51<2:48:47,  1.56it/s]
 73%|███████▎  | 41824/57600 [7:20:51<2:43:09,  1.61it/s]
 73%|███████▎  | 41825/57600 [7:20:52<2:48:25,  1.56it/s]
 73%|███████▎  | 41826/57600 [7:20:53<2:49:08,  1.55it/s]
 73%|███████▎  | 41827/57600 [7:20:53<2:44:12,  1.60it/s]
 73%|███████▎  | 41828/57600 [7:20:54<2:41:30,  1.63it/s]
 73%|███████▎  | 41829/57600 [7:20:54<2:39:45,  1.65it/s]
 73%|███████▎  | 41830/57600 [7:20:55<2:36:50,  1.68it/s]
 73%|███████▎  | 41831/57600 [7:20:56<2:39:01,  1.65it/s]
 73%|███████▎  | 41832/57600 [7:20:56<2:40:26,  1.64it/s]
 73%|███████▎  | 41833/57600 [7:20:57<2:44:59,  1.59it/s]
 73%|███████▎  | 41834/57600 [7:20:57<2:45:46,  1.59it/s]
 73%|███████▎  | 41835/57600 [7:20:58<2:45:38,  1.59it/s]
 73%|███████▎  | 41836/57600 [7:20:59<2:50:11,  1.54it/s]
 73%|███████▎  | 41837/57600 [7:20:59<2:49:18,  1.55it/s]
 73%|███████▎  | 41838/57600 [7:21:00<2:53:56,  1.51it/s]
 73%|███████▎  | 41839/57600 [7:21:01<2:49:33,  1.55it/s]
 73%|███████▎  | 41840/57600 [7:21:01<2:47:01,  1.57it/s]
                                                         
{'loss': 1.1249, 'learning_rate': 3.471080139372823e-07, 'epoch': 461.81}

 73%|███████▎  | 41840/57600 [7:21:01<2:47:01,  1.57it/s]
 73%|███████▎  | 41841/57600 [7:21:02<2:45:55,  1.58it/s]
 73%|███████▎  | 41842/57600 [7:21:03<2:44:29,  1.60it/s]
 73%|███████▎  | 41843/57600 [7:21:03<2:47:00,  1.57it/s]
 73%|███████▎  | 41844/57600 [7:21:04<2:49:08,  1.55it/s]
 73%|███████▎  | 41845/57600 [7:21:04<2:46:51,  1.57it/s]
 73%|███████▎  | 41846/57600 [7:21:05<2:42:19,  1.62it/s]
 73%|███████▎  | 41847/57600 [7:21:06<2:40:34,  1.64it/s]
 73%|███████▎  | 41848/57600 [7:21:06<2:41:38,  1.62it/s]
 73%|███████▎  | 41849/57600 [7:21:07<2:42:35,  1.61it/s]
 73%|███████▎  | 41850/57600 [7:21:08<2:42:24,  1.62it/s]
 73%|███████▎  | 41851/57600 [7:21:08<2:40:29,  1.64it/s]
 73%|███████▎  | 41852/57600 [7:21:09<2:42:17,  1.62it/s]
 73%|███████▎  | 41853/57600 [7:21:09<2:38:54,  1.65it/s]
 73%|███████▎  | 41854/57600 [7:21:10<2:38:19,  1.66it/s]
 73%|███████▎  | 41855/57600 [7:21:11<2:43:25,  1.61it/s]
 73%|███████▎  | 41856/57600 [7:21:11<2:51:04,  1.53it/s]
 73%|███████▎  | 41857/57600 [7:21:12<2:50:59,  1.53it/s]
 73%|███████▎  | 41858/57600 [7:21:13<3:09:30,  1.38it/s]
 73%|███████▎  | 41859/57600 [7:21:14<3:08:29,  1.39it/s]
 73%|███████▎  | 41860/57600 [7:21:14<3:01:46,  1.44it/s]
                                                         
{'loss': 1.103, 'learning_rate': 3.46794425087108e-07, 'epoch': 462.03}

 73%|███████▎  | 41860/57600 [7:21:14<3:01:46,  1.44it/s]
 73%|███████▎  | 41861/57600 [7:21:15<2:57:16,  1.48it/s]
 73%|███████▎  | 41862/57600 [7:21:15<2:52:45,  1.52it/s]
 73%|███████▎  | 41863/57600 [7:21:16<2:48:02,  1.56it/s]
 73%|███████▎  | 41864/57600 [7:21:17<2:49:10,  1.55it/s]
 73%|███████▎  | 41865/57600 [7:21:17<2:48:53,  1.55it/s]
 73%|███████▎  | 41866/57600 [7:21:18<2:48:10,  1.56it/s]
 73%|███████▎  | 41867/57600 [7:21:19<2:48:19,  1.56it/s]
 73%|███████▎  | 41868/57600 [7:21:19<2:45:34,  1.58it/s]
 73%|███████▎  | 41869/57600 [7:21:20<2:47:44,  1.56it/s]
 73%|███████▎  | 41870/57600 [7:21:21<2:45:15,  1.59it/s]
 73%|███████▎  | 41871/57600 [7:21:21<2:41:00,  1.63it/s]
 73%|███████▎  | 41872/57600 [7:21:22<2:47:35,  1.56it/s]
 73%|███████▎  | 41873/57600 [7:21:22<2:46:02,  1.58it/s]
 73%|███████▎  | 41874/57600 [7:21:23<2:40:44,  1.63it/s]
 73%|███████▎  | 41875/57600 [7:21:24<2:45:25,  1.58it/s]
 73%|███████▎  | 41876/57600 [7:21:24<2:44:58,  1.59it/s]
 73%|███████▎  | 41877/57600 [7:21:25<2:38:36,  1.65it/s]
 73%|███████▎  | 41878/57600 [7:21:25<2:33:57,  1.70it/s]
 73%|███████▎  | 41879/57600 [7:21:26<2:36:05,  1.68it/s]
 73%|███████▎  | 41880/57600 [7:21:27<2:37:21,  1.66it/s]
                                                         
{'loss': 1.1352, 'learning_rate': 3.4648083623693383e-07, 'epoch': 462.25}

 73%|███████▎  | 41880/57600 [7:21:27<2:37:21,  1.66it/s]
 73%|███████▎  | 41881/57600 [7:21:27<2:35:46,  1.68it/s]
 73%|███████▎  | 41882/57600 [7:21:28<2:32:28,  1.72it/s]
 73%|███████▎  | 41883/57600 [7:21:28<2:36:27,  1.67it/s]
 73%|███████▎  | 41884/57600 [7:21:29<2:41:38,  1.62it/s]
 73%|███████▎  | 41885/57600 [7:21:30<2:44:49,  1.59it/s]
 73%|███████▎  | 41886/57600 [7:21:30<2:41:55,  1.62it/s]
 73%|███████▎  | 41887/57600 [7:21:31<2:47:31,  1.56it/s]
 73%|███████▎  | 41888/57600 [7:21:32<2:44:23,  1.59it/s]
 73%|███████▎  | 41889/57600 [7:21:32<2:40:06,  1.64it/s]
 73%|███████▎  | 41890/57600 [7:21:33<2:38:22,  1.65it/s]
 73%|███████▎  | 41891/57600 [7:21:33<2:39:56,  1.64it/s]
 73%|███████▎  | 41892/57600 [7:21:34<2:44:16,  1.59it/s]
 73%|███████▎  | 41893/57600 [7:21:35<2:46:36,  1.57it/s]
 73%|███████▎  | 41894/57600 [7:21:35<2:46:22,  1.57it/s]
 73%|███████▎  | 41895/57600 [7:21:36<2:46:34,  1.57it/s]
 73%|███████▎  | 41896/57600 [7:21:37<2:41:14,  1.62it/s]
 73%|███████▎  | 41897/57600 [7:21:37<2:40:16,  1.63it/s]
 73%|███████▎  | 41898/57600 [7:21:38<2:37:44,  1.66it/s]
 73%|███████▎  | 41899/57600 [7:21:38<2:42:01,  1.62it/s]
 73%|███████▎  | 41900/57600 [7:21:39<2:40:20,  1.63it/s]
                                                         
{'loss': 1.1752, 'learning_rate': 3.4616724738675953e-07, 'epoch': 462.47}

 73%|███████▎  | 41900/57600 [7:21:39<2:40:20,  1.63it/s]
 73%|███████▎  | 41901/57600 [7:21:40<2:38:33,  1.65it/s]
 73%|███████▎  | 41902/57600 [7:21:40<2:39:15,  1.64it/s]
 73%|███████▎  | 41903/57600 [7:21:41<2:44:20,  1.59it/s]
 73%|███████▎  | 41904/57600 [7:21:41<2:45:34,  1.58it/s]
 73%|███████▎  | 41905/57600 [7:21:42<2:44:01,  1.59it/s]
 73%|███████▎  | 41906/57600 [7:21:43<2:47:52,  1.56it/s]
 73%|███████▎  | 41907/57600 [7:21:43<2:49:52,  1.54it/s]
 73%|███████▎  | 41908/57600 [7:21:44<2:50:15,  1.54it/s]
 73%|███████▎  | 41909/57600 [7:21:45<2:46:34,  1.57it/s]
 73%|███████▎  | 41910/57600 [7:21:45<2:44:23,  1.59it/s]
 73%|███████▎  | 41911/57600 [7:21:46<2:44:09,  1.59it/s]
 73%|███████▎  | 41912/57600 [7:21:47<2:42:43,  1.61it/s]
 73%|███████▎  | 41913/57600 [7:21:47<2:42:59,  1.60it/s]
 73%|███████▎  | 41914/57600 [7:21:48<2:39:02,  1.64it/s]
 73%|███████▎  | 41915/57600 [7:21:48<2:35:57,  1.68it/s]
 73%|███████▎  | 41916/57600 [7:21:49<2:40:41,  1.63it/s]
 73%|███████▎  | 41917/57600 [7:21:50<2:45:09,  1.58it/s]
 73%|███████▎  | 41918/57600 [7:21:50<2:43:12,  1.60it/s]
 73%|███████▎  | 41919/57600 [7:21:51<2:42:54,  1.60it/s]
 73%|███████▎  | 41920/57600 [7:21:51<2:42:47,  1.61it/s]
                                                         
{'loss': 1.1267, 'learning_rate': 3.458536585365854e-07, 'epoch': 462.69}

 73%|███████▎  | 41920/57600 [7:21:51<2:42:47,  1.61it/s]
 73%|███████▎  | 41921/57600 [7:21:52<2:40:16,  1.63it/s]
 73%|███████▎  | 41922/57600 [7:21:53<2:39:46,  1.64it/s]
 73%|███████▎  | 41923/57600 [7:21:53<2:43:01,  1.60it/s]
 73%|███████▎  | 41924/57600 [7:21:54<2:42:32,  1.61it/s]
 73%|███████▎  | 41925/57600 [7:21:55<2:46:29,  1.57it/s]
 73%|███████▎  | 41926/57600 [7:21:55<2:41:16,  1.62it/s]
 73%|███████▎  | 41927/57600 [7:21:56<2:42:46,  1.60it/s]
 73%|███████▎  | 41928/57600 [7:21:56<2:40:08,  1.63it/s]
 73%|███████▎  | 41929/57600 [7:21:57<2:38:05,  1.65it/s]
 73%|███████▎  | 41930/57600 [7:21:58<2:39:33,  1.64it/s]
 73%|███████▎  | 41931/57600 [7:21:58<2:40:53,  1.62it/s]
 73%|███████▎  | 41932/57600 [7:21:59<2:38:22,  1.65it/s]
 73%|███████▎  | 41933/57600 [7:21:59<2:38:04,  1.65it/s]
 73%|███████▎  | 41934/57600 [7:22:00<2:40:24,  1.63it/s]
 73%|███████▎  | 41935/57600 [7:22:01<2:45:36,  1.58it/s]
 73%|███████▎  | 41936/57600 [7:22:01<2:51:33,  1.52it/s]
 73%|███████▎  | 41937/57600 [7:22:02<2:52:18,  1.52it/s]
 73%|███████▎  | 41938/57600 [7:22:03<2:58:43,  1.46it/s]
 73%|███████▎  | 41939/57600 [7:22:03<2:52:45,  1.51it/s]
 73%|███████▎  | 41940/57600 [7:22:04<2:55:12,  1.49it/s]
                                                         
{'loss': 1.0625, 'learning_rate': 3.455400696864111e-07, 'epoch': 462.91}

 73%|███████▎  | 41940/57600 [7:22:04<2:55:12,  1.49it/s]
 73%|███████▎  | 41941/57600 [7:22:05<2:48:40,  1.55it/s]
 73%|███████▎  | 41942/57600 [7:22:05<2:47:39,  1.56it/s]
 73%|███████▎  | 41943/57600 [7:22:06<2:50:00,  1.53it/s]
 73%|███████▎  | 41944/57600 [7:22:07<2:46:44,  1.56it/s]
 73%|███████▎  | 41945/57600 [7:22:07<2:46:16,  1.57it/s]
 73%|███████▎  | 41946/57600 [7:22:08<2:46:19,  1.57it/s]
 73%|███████▎  | 41947/57600 [7:22:09<2:42:39,  1.60it/s]
 73%|███████▎  | 41948/57600 [7:22:09<2:49:11,  1.54it/s]
 73%|███████▎  | 41949/57600 [7:22:10<2:51:52,  1.52it/s]
 73%|███████▎  | 41950/57600 [7:22:11<2:50:23,  1.53it/s]
 73%|███████▎  | 41951/57600 [7:22:11<2:49:32,  1.54it/s]
 73%|███████▎  | 41952/57600 [7:22:12<2:52:50,  1.51it/s]
 73%|███████▎  | 41953/57600 [7:22:13<2:56:05,  1.48it/s]
 73%|███████▎  | 41954/57600 [7:22:13<2:48:30,  1.55it/s]
 73%|███████▎  | 41955/57600 [7:22:14<2:45:08,  1.58it/s]
 73%|███████▎  | 41956/57600 [7:22:14<2:46:07,  1.57it/s]
 73%|███████▎  | 41957/57600 [7:22:15<2:45:02,  1.58it/s]
 73%|███████▎  | 41958/57600 [7:22:16<2:40:23,  1.63it/s]
 73%|███████▎  | 41959/57600 [7:22:16<2:44:09,  1.59it/s]
 73%|███████▎  | 41960/57600 [7:22:17<2:41:43,  1.61it/s]
                                                         
{'loss': 1.1038, 'learning_rate': 3.4522648083623695e-07, 'epoch': 463.13}

 73%|███████▎  | 41960/57600 [7:22:17<2:41:43,  1.61it/s]
 73%|███████▎  | 41961/57600 [7:22:17<2:40:10,  1.63it/s]
 73%|███████▎  | 41962/57600 [7:22:18<2:43:55,  1.59it/s]
 73%|███████▎  | 41963/57600 [7:22:19<2:40:18,  1.63it/s]
 73%|███████▎  | 41964/57600 [7:22:19<2:46:04,  1.57it/s]
 73%|███████▎  | 41965/57600 [7:22:20<2:40:45,  1.62it/s]
 73%|███████▎  | 41966/57600 [7:22:21<2:38:17,  1.65it/s]
 73%|███████▎  | 41967/57600 [7:22:21<2:44:01,  1.59it/s]
 73%|███████▎  | 41968/57600 [7:22:22<2:44:12,  1.59it/s]
 73%|███████▎  | 41969/57600 [7:22:22<2:39:24,  1.63it/s]
 73%|███████▎  | 41970/57600 [7:22:23<2:42:59,  1.60it/s]
 73%|███████▎  | 41971/57600 [7:22:24<2:42:08,  1.61it/s]
 73%|███████▎  | 41972/57600 [7:22:24<2:38:48,  1.64it/s]
 73%|███████▎  | 41973/57600 [7:22:25<2:45:37,  1.57it/s]
 73%|███████▎  | 41974/57600 [7:22:26<2:47:27,  1.56it/s]
 73%|███████▎  | 41975/57600 [7:22:26<2:51:55,  1.51it/s]
 73%|███████▎  | 41976/57600 [7:22:27<2:51:51,  1.52it/s]
 73%|███████▎  | 41977/57600 [7:22:28<2:45:57,  1.57it/s]
 73%|███████▎  | 41978/57600 [7:22:28<2:43:36,  1.59it/s]
 73%|███████▎  | 41979/57600 [7:22:29<2:39:25,  1.63it/s]
 73%|███████▎  | 41980/57600 [7:22:30<2:47:43,  1.55it/s]
                                                         
{'loss': 1.1499, 'learning_rate': 3.4491289198606275e-07, 'epoch': 463.36}

 73%|███████▎  | 41980/57600 [7:22:30<2:47:43,  1.55it/s]
 73%|███████▎  | 41981/57600 [7:22:30<2:50:45,  1.52it/s]
 73%|███████▎  | 41982/57600 [7:22:31<2:49:57,  1.53it/s]
 73%|███████▎  | 41983/57600 [7:22:31<2:45:40,  1.57it/s]
 73%|███████▎  | 41984/57600 [7:22:32<2:46:13,  1.57it/s]
 73%|███████▎  | 41985/57600 [7:22:33<2:43:54,  1.59it/s]
 73%|███████▎  | 41986/57600 [7:22:33<2:43:19,  1.59it/s]
 73%|███████▎  | 41987/57600 [7:22:34<2:40:24,  1.62it/s]
 73%|███████▎  | 41988/57600 [7:22:34<2:36:59,  1.66it/s]
 73%|███████▎  | 41989/57600 [7:22:35<2:37:57,  1.65it/s]
 73%|███████▎  | 41990/57600 [7:22:36<2:37:21,  1.65it/s]
 73%|███████▎  | 41991/57600 [7:22:36<2:35:47,  1.67it/s]
 73%|███████▎  | 41992/57600 [7:22:37<2:34:32,  1.68it/s]
 73%|███████▎  | 41993/57600 [7:22:38<2:43:00,  1.60it/s]
 73%|███████▎  | 41994/57600 [7:22:38<2:45:35,  1.57it/s]
 73%|███████▎  | 41995/57600 [7:22:39<2:47:24,  1.55it/s]
 73%|███████▎  | 41996/57600 [7:22:40<2:44:16,  1.58it/s]
 73%|███████▎  | 41997/57600 [7:22:40<2:41:42,  1.61it/s]
 73%|███████▎  | 41998/57600 [7:22:41<2:43:05,  1.59it/s]
 73%|███████▎  | 41999/57600 [7:22:41<2:46:09,  1.56it/s]
 73%|███████▎  | 42000/57600 [7:22:42<2:40:36,  1.62it/s]
                                                         
{'loss': 1.1417, 'learning_rate': 3.4459930313588845e-07, 'epoch': 463.58}

 73%|███████▎  | 42000/57600 [7:22:42<2:40:36,  1.62it/s]
 73%|███████▎  | 42001/57600 [7:22:43<2:40:00,  1.62it/s]
 73%|███████▎  | 42002/57600 [7:22:43<2:35:14,  1.67it/s]
 73%|███████▎  | 42003/57600 [7:22:44<2:38:12,  1.64it/s]
 73%|███████▎  | 42004/57600 [7:22:44<2:42:06,  1.60it/s]
 73%|███████▎  | 42005/57600 [7:22:45<2:39:54,  1.63it/s]
 73%|███████▎  | 42006/57600 [7:22:46<2:47:49,  1.55it/s]
 73%|███████▎  | 42007/57600 [7:22:46<2:49:14,  1.54it/s]
 73%|███████▎  | 42008/57600 [7:22:47<2:46:11,  1.56it/s]
 73%|███████▎  | 42009/57600 [7:22:48<2:44:47,  1.58it/s]
 73%|███████▎  | 42010/57600 [7:22:48<2:46:50,  1.56it/s]
 73%|███████▎  | 42011/57600 [7:22:49<2:41:45,  1.61it/s]
 73%|███████▎  | 42012/57600 [7:22:49<2:40:40,  1.62it/s]
 73%|███████▎  | 42013/57600 [7:22:50<2:39:43,  1.63it/s]
 73%|███████▎  | 42014/57600 [7:22:51<2:38:30,  1.64it/s]
 73%|███████▎  | 42015/57600 [7:22:51<2:45:49,  1.57it/s]
 73%|███████▎  | 42016/57600 [7:22:52<2:42:49,  1.60it/s]
 73%|███████▎  | 42017/57600 [7:22:53<2:46:35,  1.56it/s]
 73%|███████▎  | 42018/57600 [7:22:53<2:44:23,  1.58it/s]
 73%|███████▎  | 42019/57600 [7:22:54<2:41:49,  1.60it/s]
 73%|███████▎  | 42020/57600 [7:22:54<2:40:23,  1.62it/s]
                                                         
{'loss': 1.1291, 'learning_rate': 3.442857142857143e-07, 'epoch': 463.8}

 73%|███████▎  | 42020/57600 [7:22:54<2:40:23,  1.62it/s]
 73%|███████▎  | 42021/57600 [7:22:55<2:43:44,  1.59it/s]
 73%|███████▎  | 42022/57600 [7:22:56<2:49:01,  1.54it/s]
 73%|███████▎  | 42023/57600 [7:22:56<2:46:39,  1.56it/s]
 73%|███████▎  | 42024/57600 [7:22:57<2:44:53,  1.57it/s]
 73%|███████▎  | 42025/57600 [7:22:58<2:40:48,  1.61it/s]
 73%|███████▎  | 42026/57600 [7:22:58<2:38:49,  1.63it/s]
 73%|███████▎  | 42027/57600 [7:22:59<2:35:40,  1.67it/s]
 73%|███████▎  | 42028/57600 [7:22:59<2:35:47,  1.67it/s]
 73%|███████▎  | 42029/57600 [7:23:00<2:33:25,  1.69it/s]
 73%|███████▎  | 42030/57600 [7:23:01<2:35:03,  1.67it/s]
 73%|███████▎  | 42031/57600 [7:23:01<2:36:09,  1.66it/s]
 73%|███████▎  | 42032/57600 [7:23:02<2:35:17,  1.67it/s]
 73%|███████▎  | 42033/57600 [7:23:02<2:35:45,  1.67it/s]
 73%|███████▎  | 42034/57600 [7:23:03<2:35:05,  1.67it/s]
 73%|███████▎  | 42035/57600 [7:23:04<2:35:05,  1.67it/s]
 73%|███████▎  | 42036/57600 [7:23:04<2:44:03,  1.58it/s]
 73%|███████▎  | 42037/57600 [7:23:05<2:52:19,  1.51it/s]
 73%|███████▎  | 42038/57600 [7:23:06<2:49:27,  1.53it/s]
 73%|███████▎  | 42039/57600 [7:23:06<2:56:15,  1.47it/s]
 73%|███████▎  | 42040/57600 [7:23:07<2:50:36,  1.52it/s]
                                                         
{'loss': 1.142, 'learning_rate': 3.4397212543554e-07, 'epoch': 464.02}

 73%|███████▎  | 42040/57600 [7:23:07<2:50:36,  1.52it/s]
 73%|███████▎  | 42041/57600 [7:23:08<2:50:24,  1.52it/s]
 73%|███████▎  | 42042/57600 [7:23:08<2:47:48,  1.55it/s]
 73%|███████▎  | 42043/57600 [7:23:09<2:52:45,  1.50it/s]
 73%|███████▎  | 42044/57600 [7:23:10<2:47:02,  1.55it/s]
 73%|███████▎  | 42045/57600 [7:23:10<2:46:56,  1.55it/s]
 73%|███████▎  | 42046/57600 [7:23:11<2:46:12,  1.56it/s]
 73%|███████▎  | 42047/57600 [7:23:12<2:42:33,  1.59it/s]
 73%|███████▎  | 42048/57600 [7:23:12<2:43:05,  1.59it/s]
 73%|███████▎  | 42049/57600 [7:23:13<2:41:15,  1.61it/s]
 73%|███████▎  | 42050/57600 [7:23:13<2:41:42,  1.60it/s]
 73%|███████▎  | 42051/57600 [7:23:14<2:46:16,  1.56it/s]
 73%|███████▎  | 42052/57600 [7:23:15<2:40:19,  1.62it/s]
 73%|███████▎  | 42053/57600 [7:23:15<2:40:42,  1.61it/s]
 73%|███████▎  | 42054/57600 [7:23:16<2:42:00,  1.60it/s]
 73%|███████▎  | 42055/57600 [7:23:16<2:40:08,  1.62it/s]
 73%|███████▎  | 42056/57600 [7:23:17<2:39:37,  1.62it/s]
 73%|███████▎  | 42057/57600 [7:23:18<2:45:10,  1.57it/s]
 73%|███████▎  | 42058/57600 [7:23:18<2:47:06,  1.55it/s]
 73%|███████▎  | 42059/57600 [7:23:19<2:43:01,  1.59it/s]
 73%|███████▎  | 42060/57600 [7:23:20<2:39:29,  1.62it/s]
                                                         
{'loss': 1.0993, 'learning_rate': 3.4365853658536587e-07, 'epoch': 464.24}

 73%|███████▎  | 42060/57600 [7:23:20<2:39:29,  1.62it/s]
 73%|███████▎  | 42061/57600 [7:23:20<2:39:42,  1.62it/s]
 73%|███████▎  | 42062/57600 [7:23:21<2:44:16,  1.58it/s]
 73%|███████▎  | 42063/57600 [7:23:22<2:42:56,  1.59it/s]
 73%|███████▎  | 42064/57600 [7:23:22<2:39:52,  1.62it/s]
 73%|███████▎  | 42065/57600 [7:23:23<2:37:58,  1.64it/s]
 73%|███████▎  | 42066/57600 [7:23:23<2:38:21,  1.63it/s]
 73%|███████▎  | 42067/57600 [7:23:24<2:35:56,  1.66it/s]
 73%|███████▎  | 42068/57600 [7:23:25<2:36:26,  1.65it/s]
 73%|███████▎  | 42069/57600 [7:23:25<2:36:04,  1.66it/s]
 73%|███████▎  | 42070/57600 [7:23:26<2:35:56,  1.66it/s]
 73%|███████▎  | 42071/57600 [7:23:26<2:40:06,  1.62it/s]
 73%|███████▎  | 42072/57600 [7:23:27<2:42:48,  1.59it/s]
 73%|███████▎  | 42073/57600 [7:23:28<2:40:58,  1.61it/s]
 73%|███████▎  | 42074/57600 [7:23:28<2:39:36,  1.62it/s]
 73%|███████▎  | 42075/57600 [7:23:29<2:38:18,  1.63it/s]
 73%|███████▎  | 42076/57600 [7:23:29<2:38:21,  1.63it/s]
 73%|███████▎  | 42077/57600 [7:23:30<2:39:15,  1.62it/s]
 73%|███████▎  | 42078/57600 [7:23:31<2:39:25,  1.62it/s]
 73%|███████▎  | 42079/57600 [7:23:31<2:44:19,  1.57it/s]
 73%|███████▎  | 42080/57600 [7:23:32<2:44:57,  1.57it/s]
                                                         
{'loss': 1.1713, 'learning_rate': 3.4334494773519157e-07, 'epoch': 464.46}

 73%|███████▎  | 42080/57600 [7:23:32<2:44:57,  1.57it/s]
 73%|███████▎  | 42081/57600 [7:23:33<2:39:23,  1.62it/s]
 73%|███████▎  | 42082/57600 [7:23:33<2:38:38,  1.63it/s]
 73%|███████▎  | 42083/57600 [7:23:34<2:42:57,  1.59it/s]
 73%|███████▎  | 42084/57600 [7:23:35<2:48:12,  1.54it/s]
 73%|███████▎  | 42085/57600 [7:23:35<2:41:51,  1.60it/s]
 73%|███████▎  | 42086/57600 [7:23:36<2:42:40,  1.59it/s]
 73%|███████▎  | 42087/57600 [7:23:36<2:43:05,  1.59it/s]
 73%|███████▎  | 42088/57600 [7:23:37<2:40:02,  1.62it/s]
 73%|███████▎  | 42089/57600 [7:23:38<2:44:36,  1.57it/s]
 73%|███████▎  | 42090/57600 [7:23:38<2:44:09,  1.57it/s]
 73%|███████▎  | 42091/57600 [7:23:39<2:42:45,  1.59it/s]
 73%|███████▎  | 42092/57600 [7:23:40<2:41:46,  1.60it/s]
 73%|███████▎  | 42093/57600 [7:23:40<2:41:11,  1.60it/s]
 73%|███████▎  | 42094/57600 [7:23:41<2:45:13,  1.56it/s]
 73%|███████▎  | 42095/57600 [7:23:42<2:48:10,  1.54it/s]
 73%|███████▎  | 42096/57600 [7:23:42<2:48:11,  1.54it/s]
 73%|███████▎  | 42097/57600 [7:23:43<2:43:08,  1.58it/s]
 73%|███████▎  | 42098/57600 [7:23:43<2:42:23,  1.59it/s]
 73%|███████▎  | 42099/57600 [7:23:44<2:40:46,  1.61it/s]
 73%|███████▎  | 42100/57600 [7:23:45<2:42:36,  1.59it/s]
                                                         
{'loss': 1.1404, 'learning_rate': 3.430313588850174e-07, 'epoch': 464.68}

 73%|███████▎  | 42100/57600 [7:23:45<2:42:36,  1.59it/s]
 73%|███████▎  | 42101/57600 [7:23:45<2:49:26,  1.52it/s]
 73%|███████▎  | 42102/57600 [7:23:46<2:47:04,  1.55it/s]
 73%|███████▎  | 42103/57600 [7:23:47<2:42:02,  1.59it/s]
 73%|███████▎  | 42104/57600 [7:23:47<2:38:03,  1.63it/s]
 73%|███████▎  | 42105/57600 [7:23:48<2:39:44,  1.62it/s]
 73%|███████▎  | 42106/57600 [7:23:48<2:41:11,  1.60it/s]
 73%|███████▎  | 42107/57600 [7:23:49<2:42:31,  1.59it/s]
 73%|███████▎  | 42108/57600 [7:23:50<2:42:03,  1.59it/s]
 73%|███████▎  | 42109/57600 [7:23:50<2:48:05,  1.54it/s]
 73%|███████▎  | 42110/57600 [7:23:51<2:41:16,  1.60it/s]
 73%|███████▎  | 42111/57600 [7:23:52<2:39:18,  1.62it/s]
 73%|███████▎  | 42112/57600 [7:23:52<2:44:25,  1.57it/s]
 73%|███████▎  | 42113/57600 [7:23:53<2:44:21,  1.57it/s]
 73%|███████▎  | 42114/57600 [7:23:53<2:41:08,  1.60it/s]
 73%|███████▎  | 42115/57600 [7:23:54<2:42:45,  1.59it/s]
 73%|███████▎  | 42116/57600 [7:23:55<2:41:39,  1.60it/s]
 73%|███████▎  | 42117/57600 [7:23:55<2:41:07,  1.60it/s]
 73%|███████▎  | 42118/57600 [7:23:56<2:38:56,  1.62it/s]
 73%|███████▎  | 42119/57600 [7:23:57<2:38:07,  1.63it/s]
 73%|███████▎  | 42120/57600 [7:23:57<2:43:13,  1.58it/s]
                                                         
{'loss': 1.1187, 'learning_rate': 3.427177700348432e-07, 'epoch': 464.9}

 73%|███████▎  | 42120/57600 [7:23:57<2:43:13,  1.58it/s]
 73%|███████▎  | 42121/57600 [7:23:58<2:45:59,  1.55it/s]
 73%|███████▎  | 42122/57600 [7:23:58<2:42:09,  1.59it/s]
 73%|███████▎  | 42123/57600 [7:23:59<2:43:00,  1.58it/s]
 73%|███████▎  | 42124/57600 [7:24:00<2:45:45,  1.56it/s]
 73%|███████▎  | 42125/57600 [7:24:00<2:43:09,  1.58it/s]
 73%|███████▎  | 42126/57600 [7:24:01<2:42:15,  1.59it/s]
 73%|███████▎  | 42127/57600 [7:24:02<2:37:29,  1.64it/s]
 73%|███████▎  | 42128/57600 [7:24:02<2:37:08,  1.64it/s]
 73%|███████▎  | 42129/57600 [7:24:03<2:38:29,  1.63it/s]
 73%|███████▎  | 42130/57600 [7:24:04<2:48:04,  1.53it/s]
 73%|███████▎  | 42131/57600 [7:24:04<2:50:19,  1.51it/s]
 73%|███████▎  | 42132/57600 [7:24:05<2:44:02,  1.57it/s]
 73%|███████▎  | 42133/57600 [7:24:05<2:39:29,  1.62it/s]
 73%|███████▎  | 42134/57600 [7:24:06<2:42:32,  1.59it/s]
 73%|███████▎  | 42135/57600 [7:24:07<2:38:39,  1.62it/s]
 73%|███████▎  | 42136/57600 [7:24:07<2:41:18,  1.60it/s]
 73%|███████▎  | 42137/57600 [7:24:08<2:41:32,  1.60it/s]
 73%|███████▎  | 42138/57600 [7:24:09<2:40:26,  1.61it/s]
 73%|███████▎  | 42139/57600 [7:24:09<2:41:11,  1.60it/s]
 73%|███████▎  | 42140/57600 [7:24:10<2:39:39,  1.61it/s]
                                                         
{'loss': 1.1665, 'learning_rate': 3.42404181184669e-07, 'epoch': 465.12}

 73%|███████▎  | 42140/57600 [7:24:10<2:39:39,  1.61it/s]
 73%|███████▎  | 42141/57600 [7:24:10<2:40:25,  1.61it/s]
 73%|███████▎  | 42142/57600 [7:24:11<2:41:57,  1.59it/s]
 73%|███████▎  | 42143/57600 [7:24:12<2:43:33,  1.58it/s]
 73%|███████▎  | 42144/57600 [7:24:12<2:41:14,  1.60it/s]
 73%|███████▎  | 42145/57600 [7:24:13<2:34:45,  1.66it/s]
 73%|███████▎  | 42146/57600 [7:24:13<2:34:59,  1.66it/s]
 73%|███████▎  | 42147/57600 [7:24:14<2:34:45,  1.66it/s]
 73%|███████▎  | 42148/57600 [7:24:15<2:37:17,  1.64it/s]
 73%|███████▎  | 42149/57600 [7:24:15<2:37:55,  1.63it/s]
 73%|███████▎  | 42150/57600 [7:24:16<2:35:07,  1.66it/s]
 73%|███████▎  | 42151/57600 [7:24:17<2:42:03,  1.59it/s]
 73%|███████▎  | 42152/57600 [7:24:17<2:46:15,  1.55it/s]
 73%|███████▎  | 42153/57600 [7:24:18<2:43:34,  1.57it/s]
 73%|███████▎  | 42154/57600 [7:24:18<2:40:22,  1.61it/s]
 73%|███████▎  | 42155/57600 [7:24:19<2:40:11,  1.61it/s]
 73%|███████▎  | 42156/57600 [7:24:20<2:39:10,  1.62it/s]
 73%|███████▎  | 42157/57600 [7:24:20<2:40:19,  1.61it/s]
 73%|███████▎  | 42158/57600 [7:24:21<2:42:48,  1.58it/s]
 73%|███████▎  | 42159/57600 [7:24:22<2:40:50,  1.60it/s]
 73%|███████▎  | 42160/57600 [7:24:22<2:45:17,  1.56it/s]
                                                         
{'loss': 1.1548, 'learning_rate': 3.420905923344948e-07, 'epoch': 465.34}

 73%|███████▎  | 42160/57600 [7:24:22<2:45:17,  1.56it/s]
 73%|███████▎  | 42161/57600 [7:24:23<2:43:04,  1.58it/s]
 73%|███████▎  | 42162/57600 [7:24:23<2:37:27,  1.63it/s]
 73%|███████▎  | 42163/57600 [7:24:24<2:36:57,  1.64it/s]
 73%|███████▎  | 42164/57600 [7:24:25<2:39:51,  1.61it/s]
 73%|███████▎  | 42165/57600 [7:24:25<2:43:59,  1.57it/s]
 73%|███████▎  | 42166/57600 [7:24:26<2:44:47,  1.56it/s]
 73%|███████▎  | 42167/57600 [7:24:27<2:42:29,  1.58it/s]
 73%|███████▎  | 42168/57600 [7:24:27<2:44:09,  1.57it/s]
 73%|███████▎  | 42169/57600 [7:24:28<2:38:56,  1.62it/s]
 73%|███████▎  | 42170/57600 [7:24:28<2:41:25,  1.59it/s]
 73%|███████▎  | 42171/57600 [7:24:29<2:36:57,  1.64it/s]
 73%|███████▎  | 42172/57600 [7:24:30<2:40:28,  1.60it/s]
 73%|███████▎  | 42173/57600 [7:24:30<2:44:00,  1.57it/s]
 73%|███████▎  | 42174/57600 [7:24:31<2:45:54,  1.55it/s]
 73%|███████▎  | 42175/57600 [7:24:32<2:44:57,  1.56it/s]
 73%|███████▎  | 42176/57600 [7:24:32<2:43:52,  1.57it/s]
 73%|███████▎  | 42177/57600 [7:24:33<2:43:05,  1.58it/s]
 73%|███████▎  | 42178/57600 [7:24:34<2:44:14,  1.57it/s]
 73%|███████▎  | 42179/57600 [7:24:34<2:45:27,  1.55it/s]
 73%|███████▎  | 42180/57600 [7:24:35<2:41:42,  1.59it/s]
                                                         
{'loss': 1.1313, 'learning_rate': 3.4177700348432054e-07, 'epoch': 465.56}

 73%|███████▎  | 42180/57600 [7:24:35<2:41:42,  1.59it/s]
 73%|███████▎  | 42181/57600 [7:24:35<2:38:48,  1.62it/s]
 73%|███████▎  | 42182/57600 [7:24:36<2:39:07,  1.61it/s]
 73%|███████▎  | 42183/57600 [7:24:37<2:38:49,  1.62it/s]
 73%|███████▎  | 42184/57600 [7:24:37<2:39:10,  1.61it/s]
 73%|███████▎  | 42185/57600 [7:24:38<2:43:09,  1.57it/s]
 73%|███████▎  | 42186/57600 [7:24:39<2:45:24,  1.55it/s]
 73%|███████▎  | 42187/57600 [7:24:39<2:42:50,  1.58it/s]
 73%|███████▎  | 42188/57600 [7:24:40<2:39:29,  1.61it/s]
 73%|███████▎  | 42189/57600 [7:24:40<2:38:46,  1.62it/s]
 73%|███████▎  | 42190/57600 [7:24:41<2:41:53,  1.59it/s]
 73%|███████▎  | 42191/57600 [7:24:42<2:39:38,  1.61it/s]
 73%|███████▎  | 42192/57600 [7:24:42<2:37:44,  1.63it/s]
 73%|███████▎  | 42193/57600 [7:24:43<2:44:04,  1.56it/s]
 73%|███████▎  | 42194/57600 [7:24:44<2:40:59,  1.59it/s]
 73%|███████▎  | 42195/57600 [7:24:44<2:41:28,  1.59it/s]
 73%|███████▎  | 42196/57600 [7:24:45<2:39:18,  1.61it/s]
 73%|███████▎  | 42197/57600 [7:24:46<2:45:26,  1.55it/s]
 73%|███████▎  | 42198/57600 [7:24:46<2:48:46,  1.52it/s]
 73%|███████▎  | 42199/57600 [7:24:47<2:44:49,  1.56it/s]
 73%|███████▎  | 42200/57600 [7:24:47<2:44:51,  1.56it/s]
                                                         
{'loss': 1.1037, 'learning_rate': 3.4146341463414634e-07, 'epoch': 465.78}

 73%|███████▎  | 42200/57600 [7:24:47<2:44:51,  1.56it/s]
 73%|███████▎  | 42201/57600 [7:24:48<2:39:40,  1.61it/s]
 73%|███████▎  | 42202/57600 [7:24:49<2:41:57,  1.58it/s]
 73%|███████▎  | 42203/57600 [7:24:49<2:41:16,  1.59it/s]
 73%|███████▎  | 42204/57600 [7:24:50<2:43:12,  1.57it/s]
 73%|███████▎  | 42205/57600 [7:24:51<2:37:52,  1.63it/s]
 73%|███████▎  | 42206/57600 [7:24:51<2:38:03,  1.62it/s]
 73%|███████▎  | 42207/57600 [7:24:52<2:37:12,  1.63it/s]
 73%|███████▎  | 42208/57600 [7:24:52<2:36:52,  1.64it/s]
 73%|███████▎  | 42209/57600 [7:24:53<2:35:49,  1.65it/s]
 73%|███████▎  | 42210/57600 [7:24:54<2:42:01,  1.58it/s]
 73%|███████▎  | 42211/57600 [7:24:54<2:41:09,  1.59it/s]
 73%|███████▎  | 42212/57600 [7:24:55<2:43:40,  1.57it/s]
 73%|███████▎  | 42213/57600 [7:24:56<2:47:12,  1.53it/s]
 73%|███████▎  | 42214/57600 [7:24:56<2:50:28,  1.50it/s]
 73%|███████▎  | 42215/57600 [7:24:57<2:47:15,  1.53it/s]
 73%|███████▎  | 42216/57600 [7:24:58<2:45:31,  1.55it/s]
 73%|███████▎  | 42217/57600 [7:24:58<2:41:19,  1.59it/s]
 73%|███████▎  | 42218/57600 [7:24:59<2:42:11,  1.58it/s]
 73%|███████▎  | 42219/57600 [7:24:59<2:43:10,  1.57it/s]
 73%|███████▎  | 42220/57600 [7:25:00<2:44:35,  1.56it/s]
                                                         
{'loss': 1.1544, 'learning_rate': 3.411498257839721e-07, 'epoch': 466.0}

 73%|███████▎  | 42220/57600 [7:25:00<2:44:35,  1.56it/s]
 73%|███████▎  | 42221/57600 [7:25:01<2:41:51,  1.58it/s]
 73%|███████▎  | 42222/57600 [7:25:01<2:37:54,  1.62it/s]
 73%|███████▎  | 42223/57600 [7:25:02<2:42:40,  1.58it/s]
 73%|███████▎  | 42224/57600 [7:25:03<2:41:21,  1.59it/s]
 73%|███████▎  | 42225/57600 [7:25:03<2:43:36,  1.57it/s]
 73%|███████▎  | 42226/57600 [7:25:04<2:39:40,  1.60it/s]
 73%|███████▎  | 42227/57600 [7:25:05<2:44:34,  1.56it/s]
 73%|███████▎  | 42228/57600 [7:25:05<2:44:00,  1.56it/s]
 73%|███████▎  | 42229/57600 [7:25:06<2:42:32,  1.58it/s]
 73%|███████▎  | 42230/57600 [7:25:06<2:42:52,  1.57it/s]
 73%|███████▎  | 42231/57600 [7:25:07<2:41:59,  1.58it/s]
 73%|███████▎  | 42232/57600 [7:25:08<2:42:13,  1.58it/s]
 73%|███████▎  | 42233/57600 [7:25:08<2:41:32,  1.59it/s]
 73%|███████▎  | 42234/57600 [7:25:09<2:40:47,  1.59it/s]
 73%|███████▎  | 42235/57600 [7:25:09<2:37:38,  1.62it/s]
 73%|███████▎  | 42236/57600 [7:25:10<2:40:59,  1.59it/s]
 73%|███████▎  | 42237/57600 [7:25:11<2:41:04,  1.59it/s]
 73%|███████▎  | 42238/57600 [7:25:11<2:40:48,  1.59it/s]
 73%|███████▎  | 42239/57600 [7:25:12<2:41:21,  1.59it/s]
 73%|███████▎  | 42240/57600 [7:25:13<2:37:52,  1.62it/s]
                                                         
{'loss': 1.1605, 'learning_rate': 3.4083623693379785e-07, 'epoch': 466.23}

 73%|███████▎  | 42240/57600 [7:25:13<2:37:52,  1.62it/s]
 73%|███████▎  | 42241/57600 [7:25:13<2:36:50,  1.63it/s]
 73%|███████▎  | 42242/57600 [7:25:14<2:34:09,  1.66it/s]
 73%|███████▎  | 42243/57600 [7:25:14<2:32:35,  1.68it/s]
 73%|███████▎  | 42244/57600 [7:25:15<2:45:45,  1.54it/s]
 73%|███████▎  | 42245/57600 [7:25:16<2:56:00,  1.45it/s]
 73%|███████▎  | 42246/57600 [7:25:17<2:49:42,  1.51it/s]
 73%|███████▎  | 42247/57600 [7:25:17<2:44:13,  1.56it/s]
 73%|███████▎  | 42248/57600 [7:25:18<2:47:38,  1.53it/s]
 73%|███████▎  | 42249/57600 [7:25:18<2:42:05,  1.58it/s]
 73%|███████▎  | 42250/57600 [7:25:19<2:45:01,  1.55it/s]
 73%|███████▎  | 42251/57600 [7:25:20<2:37:57,  1.62it/s]
 73%|███████▎  | 42252/57600 [7:25:20<2:41:21,  1.59it/s]
 73%|███████▎  | 42253/57600 [7:25:21<2:36:04,  1.64it/s]
 73%|███████▎  | 42254/57600 [7:25:21<2:35:06,  1.65it/s]
 73%|███████▎  | 42255/57600 [7:25:22<2:34:08,  1.66it/s]
 73%|███████▎  | 42256/57600 [7:25:23<2:36:14,  1.64it/s]
 73%|███████▎  | 42257/57600 [7:25:23<2:38:47,  1.61it/s]
 73%|███████▎  | 42258/57600 [7:25:24<2:37:46,  1.62it/s]
 73%|███████▎  | 42259/57600 [7:25:25<2:41:10,  1.59it/s]
 73%|███████▎  | 42260/57600 [7:25:25<2:45:10,  1.55it/s]
                                                         
{'loss': 1.1331, 'learning_rate': 3.405226480836237e-07, 'epoch': 466.45}

 73%|███████▎  | 42260/57600 [7:25:25<2:45:10,  1.55it/s]
 73%|███████▎  | 42261/57600 [7:25:26<2:44:29,  1.55it/s]
 73%|███████▎  | 42262/57600 [7:25:26<2:39:20,  1.60it/s]
 73%|███████▎  | 42263/57600 [7:25:27<2:37:52,  1.62it/s]
 73%|███████▎  | 42264/57600 [7:25:28<2:38:25,  1.61it/s]
 73%|███████▎  | 42265/57600 [7:25:28<2:42:40,  1.57it/s]
 73%|███████▎  | 42266/57600 [7:25:29<2:45:00,  1.55it/s]
 73%|███████▎  | 42267/57600 [7:25:30<2:47:00,  1.53it/s]
 73%|███████▎  | 42268/57600 [7:25:30<2:47:29,  1.53it/s]
 73%|███████▎  | 42269/57600 [7:25:31<2:43:53,  1.56it/s]
 73%|███████▎  | 42270/57600 [7:25:32<2:45:46,  1.54it/s]
 73%|███████▎  | 42271/57600 [7:25:32<2:43:32,  1.56it/s]
 73%|███████▎  | 42272/57600 [7:25:33<2:41:11,  1.58it/s]
 73%|███████▎  | 42273/57600 [7:25:33<2:38:05,  1.62it/s]
 73%|███████▎  | 42274/57600 [7:25:34<2:37:37,  1.62it/s]
 73%|███████▎  | 42275/57600 [7:25:35<2:39:11,  1.60it/s]
 73%|███████▎  | 42276/57600 [7:25:35<2:35:21,  1.64it/s]
 73%|███████▎  | 42277/57600 [7:25:36<2:38:08,  1.61it/s]
 73%|███████▎  | 42278/57600 [7:25:37<2:40:45,  1.59it/s]
 73%|███████▎  | 42279/57600 [7:25:37<2:38:05,  1.62it/s]
 73%|███████▎  | 42280/57600 [7:25:38<2:40:55,  1.59it/s]
                                                         
{'loss': 1.1138, 'learning_rate': 3.4020905923344946e-07, 'epoch': 466.67}

 73%|███████▎  | 42280/57600 [7:25:38<2:40:55,  1.59it/s]
 73%|███████▎  | 42281/57600 [7:25:39<2:43:22,  1.56it/s]
 73%|███████▎  | 42282/57600 [7:25:39<2:48:33,  1.51it/s]
 73%|███████▎  | 42283/57600 [7:25:40<2:45:37,  1.54it/s]
 73%|███████▎  | 42284/57600 [7:25:40<2:41:34,  1.58it/s]
 73%|███████▎  | 42285/57600 [7:25:41<2:40:23,  1.59it/s]
 73%|███████▎  | 42286/57600 [7:25:42<2:39:18,  1.60it/s]
 73%|███████▎  | 42287/57600 [7:25:42<2:40:58,  1.59it/s]
 73%|███████▎  | 42288/57600 [7:25:43<2:37:53,  1.62it/s]
 73%|███████▎  | 42289/57600 [7:25:44<2:36:20,  1.63it/s]
 73%|███████▎  | 42290/57600 [7:25:44<2:38:31,  1.61it/s]
 73%|███████▎  | 42291/57600 [7:25:45<2:37:20,  1.62it/s]
 73%|███████▎  | 42292/57600 [7:25:45<2:45:07,  1.55it/s]
 73%|███████▎  | 42293/57600 [7:25:46<2:43:20,  1.56it/s]
 73%|███████▎  | 42294/57600 [7:25:47<2:45:54,  1.54it/s]
 73%|███████▎  | 42295/57600 [7:25:47<2:43:27,  1.56it/s]
 73%|███████▎  | 42296/57600 [7:25:48<2:40:10,  1.59it/s]
 73%|███████▎  | 42297/57600 [7:25:49<2:41:58,  1.57it/s]
 73%|███████▎  | 42298/57600 [7:25:49<2:37:52,  1.62it/s]
 73%|███████▎  | 42299/57600 [7:25:50<2:35:38,  1.64it/s]
 73%|███████▎  | 42300/57600 [7:25:50<2:38:41,  1.61it/s]
                                                         
{'loss': 1.1152, 'learning_rate': 3.3989547038327526e-07, 'epoch': 466.89}

 73%|███████▎  | 42300/57600 [7:25:50<2:38:41,  1.61it/s]
 73%|███████▎  | 42301/57600 [7:25:51<2:41:27,  1.58it/s]
 73%|███████▎  | 42302/57600 [7:25:52<2:39:31,  1.60it/s]
 73%|███████▎  | 42303/57600 [7:25:52<2:37:08,  1.62it/s]
 73%|███████▎  | 42304/57600 [7:25:53<2:33:24,  1.66it/s]
 73%|███████▎  | 42305/57600 [7:25:53<2:30:32,  1.69it/s]
 73%|███████▎  | 42306/57600 [7:25:54<2:38:45,  1.61it/s]
 73%|███████▎  | 42307/57600 [7:25:55<2:42:49,  1.57it/s]
 73%|███████▎  | 42308/57600 [7:25:55<2:43:47,  1.56it/s]
 73%|███████▎  | 42309/57600 [7:25:56<2:43:28,  1.56it/s]
 73%|███████▎  | 42310/57600 [7:25:57<2:42:17,  1.57it/s]
 73%|███████▎  | 42311/57600 [7:25:57<2:46:54,  1.53it/s]
 73%|███████▎  | 42312/57600 [7:25:58<2:45:27,  1.54it/s]
 73%|███████▎  | 42313/57600 [7:25:59<2:43:34,  1.56it/s]
 73%|███████▎  | 42314/57600 [7:25:59<2:40:30,  1.59it/s]
 73%|███████▎  | 42315/57600 [7:26:00<2:38:30,  1.61it/s]
 73%|███████▎  | 42316/57600 [7:26:01<2:44:58,  1.54it/s]
 73%|███████▎  | 42317/57600 [7:26:01<2:42:01,  1.57it/s]
 73%|███████▎  | 42318/57600 [7:26:02<2:42:12,  1.57it/s]
 73%|███████▎  | 42319/57600 [7:26:02<2:41:02,  1.58it/s]
 73%|███████▎  | 42320/57600 [7:26:03<2:38:25,  1.61it/s]
                                                         
{'loss': 1.1406, 'learning_rate': 3.39581881533101e-07, 'epoch': 467.11}

 73%|███████▎  | 42320/57600 [7:26:03<2:38:25,  1.61it/s]
 73%|███████▎  | 42321/57600 [7:26:04<2:33:35,  1.66it/s]
 73%|███████▎  | 42322/57600 [7:26:04<2:31:19,  1.68it/s]
 73%|███████▎  | 42323/57600 [7:26:05<2:38:39,  1.60it/s]
 73%|███████▎  | 42324/57600 [7:26:05<2:33:55,  1.65it/s]
 73%|███████▎  | 42325/57600 [7:26:06<2:39:07,  1.60it/s]
 73%|███████▎  | 42326/57600 [7:26:07<2:36:12,  1.63it/s]
 73%|███████▎  | 42327/57600 [7:26:07<2:36:44,  1.62it/s]
 73%|███████▎  | 42328/57600 [7:26:08<2:38:30,  1.61it/s]
 73%|███████▎  | 42329/57600 [7:26:09<2:36:19,  1.63it/s]
 73%|███████▎  | 42330/57600 [7:26:09<2:37:12,  1.62it/s]
 73%|███████▎  | 42331/57600 [7:26:10<2:34:40,  1.65it/s]
 73%|███████▎  | 42332/57600 [7:26:10<2:35:59,  1.63it/s]
 73%|███████▎  | 42333/57600 [7:26:11<2:33:17,  1.66it/s]
 73%|███████▎  | 42334/57600 [7:26:12<2:38:27,  1.61it/s]
 73%|███████▎  | 42335/57600 [7:26:12<2:47:21,  1.52it/s]
 74%|███████▎  | 42336/57600 [7:26:13<2:44:34,  1.55it/s]
 74%|███████▎  | 42337/57600 [7:26:14<2:40:55,  1.58it/s]
 74%|███████▎  | 42338/57600 [7:26:14<2:41:51,  1.57it/s]
 74%|███████▎  | 42339/57600 [7:26:15<2:45:20,  1.54it/s]
 74%|███████▎  | 42340/57600 [7:26:16<2:44:50,  1.54it/s]
                                                         
{'loss': 1.1333, 'learning_rate': 3.392682926829268e-07, 'epoch': 467.33}

 74%|███████▎  | 42340/57600 [7:26:16<2:44:50,  1.54it/s]
 74%|███████▎  | 42341/57600 [7:26:16<2:46:46,  1.52it/s]
 74%|███████▎  | 42342/57600 [7:26:17<2:43:41,  1.55it/s]
 74%|███████▎  | 42343/57600 [7:26:18<2:45:22,  1.54it/s]
 74%|███████▎  | 42344/57600 [7:26:18<2:45:47,  1.53it/s]
 74%|███████▎  | 42345/57600 [7:26:19<2:39:08,  1.60it/s]
 74%|███████▎  | 42346/57600 [7:26:19<2:40:08,  1.59it/s]
 74%|███████▎  | 42347/57600 [7:26:20<2:39:46,  1.59it/s]
 74%|███████▎  | 42348/57600 [7:26:21<2:46:01,  1.53it/s]
 74%|███████▎  | 42349/57600 [7:26:21<2:43:56,  1.55it/s]
 74%|███████▎  | 42350/57600 [7:26:22<2:41:15,  1.58it/s]
 74%|███████▎  | 42351/57600 [7:26:23<2:38:34,  1.60it/s]
 74%|███████▎  | 42352/57600 [7:26:23<2:35:54,  1.63it/s]
 74%|███████▎  | 42353/57600 [7:26:24<2:36:55,  1.62it/s]
 74%|███████▎  | 42354/57600 [7:26:24<2:34:22,  1.65it/s]
 74%|███████▎  | 42355/57600 [7:26:25<2:31:37,  1.68it/s]
 74%|███████▎  | 42356/57600 [7:26:26<2:35:03,  1.64it/s]
 74%|███████▎  | 42357/57600 [7:26:26<2:38:22,  1.60it/s]
 74%|███████▎  | 42358/57600 [7:26:27<2:33:24,  1.66it/s]
 74%|███████▎  | 42359/57600 [7:26:27<2:36:21,  1.62it/s]
 74%|███████▎  | 42360/57600 [7:26:28<2:45:41,  1.53it/s]
                                                         
{'loss': 1.1324, 'learning_rate': 3.389547038327525e-07, 'epoch': 467.55}

 74%|███████▎  | 42360/57600 [7:26:28<2:45:41,  1.53it/s]
 74%|███████▎  | 42361/57600 [7:26:29<2:42:57,  1.56it/s]
 74%|███████▎  | 42362/57600 [7:26:29<2:39:42,  1.59it/s]
 74%|███████▎  | 42363/57600 [7:26:30<2:37:18,  1.61it/s]
 74%|███████▎  | 42364/57600 [7:26:31<2:40:00,  1.59it/s]
 74%|███████▎  | 42365/57600 [7:26:31<2:39:00,  1.60it/s]
 74%|███████▎  | 42366/57600 [7:26:32<2:45:18,  1.54it/s]
 74%|███████▎  | 42367/57600 [7:26:33<2:41:03,  1.58it/s]
 74%|███████▎  | 42368/57600 [7:26:33<2:44:33,  1.54it/s]
 74%|███████▎  | 42369/57600 [7:26:34<2:38:46,  1.60it/s]
 74%|███████▎  | 42370/57600 [7:26:34<2:39:15,  1.59it/s]
 74%|███████▎  | 42371/57600 [7:26:35<2:37:03,  1.62it/s]
 74%|███████▎  | 42372/57600 [7:26:36<2:35:05,  1.64it/s]
 74%|███████▎  | 42373/57600 [7:26:36<2:32:32,  1.66it/s]
 74%|███████▎  | 42374/57600 [7:26:37<2:32:36,  1.66it/s]
 74%|███████▎  | 42375/57600 [7:26:38<2:38:02,  1.61it/s]
 74%|███████▎  | 42376/57600 [7:26:38<2:38:29,  1.60it/s]
 74%|███████▎  | 42377/57600 [7:26:39<2:38:35,  1.60it/s]
 74%|███████▎  | 42378/57600 [7:26:39<2:38:50,  1.60it/s]
 74%|███████▎  | 42379/57600 [7:26:40<2:42:32,  1.56it/s]
 74%|███████▎  | 42380/57600 [7:26:41<2:41:10,  1.57it/s]
                                                         
{'loss': 1.1196, 'learning_rate': 3.386411149825784e-07, 'epoch': 467.77}

 74%|███████▎  | 42380/57600 [7:26:41<2:41:10,  1.57it/s]
 74%|███████▎  | 42381/57600 [7:26:41<2:49:40,  1.49it/s]
 74%|███████▎  | 42382/57600 [7:26:42<2:41:06,  1.57it/s]
 74%|███████▎  | 42383/57600 [7:26:43<2:38:55,  1.60it/s]
 74%|███████▎  | 42384/57600 [7:26:43<2:39:13,  1.59it/s]
 74%|███████▎  | 42385/57600 [7:26:44<2:39:14,  1.59it/s]
 74%|███████▎  | 42386/57600 [7:26:44<2:33:18,  1.65it/s]
 74%|███████▎  | 42387/57600 [7:26:45<2:35:27,  1.63it/s]
 74%|███████▎  | 42388/57600 [7:26:46<2:34:31,  1.64it/s]
 74%|███████▎  | 42389/57600 [7:26:46<2:33:18,  1.65it/s]
 74%|███████▎  | 42390/57600 [7:26:47<2:36:26,  1.62it/s]
 74%|███████▎  | 42391/57600 [7:26:48<2:43:02,  1.55it/s]
 74%|███████▎  | 42392/57600 [7:26:48<2:46:58,  1.52it/s]
 74%|███████▎  | 42393/57600 [7:26:49<2:47:43,  1.51it/s]
 74%|███████▎  | 42394/57600 [7:26:50<2:49:27,  1.50it/s]
 74%|███████▎  | 42395/57600 [7:26:50<2:45:07,  1.53it/s]
 74%|███████▎  | 42396/57600 [7:26:51<2:42:18,  1.56it/s]
 74%|███████▎  | 42397/57600 [7:26:51<2:40:42,  1.58it/s]
 74%|███████▎  | 42398/57600 [7:26:52<2:40:47,  1.58it/s]
 74%|███████▎  | 42399/57600 [7:26:53<2:37:45,  1.61it/s]
 74%|███████▎  | 42400/57600 [7:26:53<2:37:55,  1.60it/s]
                                                         
{'loss': 1.1067, 'learning_rate': 3.383275261324042e-07, 'epoch': 467.99}

 74%|███████▎  | 42400/57600 [7:26:53<2:37:55,  1.60it/s]
 74%|███████▎  | 42401/57600 [7:26:54<2:44:50,  1.54it/s]
 74%|███████▎  | 42402/57600 [7:26:55<2:42:33,  1.56it/s]
 74%|███████▎  | 42403/57600 [7:26:55<2:40:55,  1.57it/s]
 74%|███████▎  | 42404/57600 [7:26:56<2:43:52,  1.55it/s]
 74%|███████▎  | 42405/57600 [7:26:57<2:43:15,  1.55it/s]
 74%|███████▎  | 42406/57600 [7:26:57<2:42:52,  1.55it/s]
 74%|███████▎  | 42407/57600 [7:26:58<2:44:20,  1.54it/s]
 74%|███████▎  | 42408/57600 [7:26:59<2:41:00,  1.57it/s]
 74%|███████▎  | 42409/57600 [7:26:59<2:42:02,  1.56it/s]
 74%|███████▎  | 42410/57600 [7:27:00<2:41:38,  1.57it/s]
 74%|███████▎  | 42411/57600 [7:27:00<2:41:57,  1.56it/s]
 74%|███████▎  | 42412/57600 [7:27:01<2:37:46,  1.60it/s]
 74%|███████▎  | 42413/57600 [7:27:02<2:41:33,  1.57it/s]
 74%|███████▎  | 42414/57600 [7:27:02<2:41:05,  1.57it/s]
 74%|███████▎  | 42415/57600 [7:27:03<2:37:19,  1.61it/s]
 74%|███████▎  | 42416/57600 [7:27:04<2:36:44,  1.61it/s]
 74%|███████▎  | 42417/57600 [7:27:04<2:33:07,  1.65it/s]
 74%|███████▎  | 42418/57600 [7:27:05<2:38:11,  1.60it/s]
 74%|███████▎  | 42419/57600 [7:27:05<2:37:06,  1.61it/s]
 74%|███████▎  | 42420/57600 [7:27:06<2:36:34,  1.62it/s]
                                                         
{'loss': 1.1315, 'learning_rate': 3.3801393728222993e-07, 'epoch': 468.21}

 74%|███████▎  | 42420/57600 [7:27:06<2:36:34,  1.62it/s]
 74%|███████▎  | 42421/57600 [7:27:07<2:32:47,  1.66it/s]
 74%|███████▎  | 42422/57600 [7:27:07<2:32:09,  1.66it/s]
 74%|███████▎  | 42423/57600 [7:27:08<2:34:05,  1.64it/s]
 74%|███████▎  | 42424/57600 [7:27:08<2:36:15,  1.62it/s]
 74%|███████▎  | 42425/57600 [7:27:09<2:32:04,  1.66it/s]
 74%|███████▎  | 42426/57600 [7:27:10<2:28:49,  1.70it/s]
 74%|███████▎  | 42427/57600 [7:27:10<2:28:35,  1.70it/s]
 74%|███████▎  | 42428/57600 [7:27:11<2:27:55,  1.71it/s]
 74%|███████▎  | 42429/57600 [7:27:11<2:28:16,  1.71it/s]
 74%|███████▎  | 42430/57600 [7:27:12<2:32:03,  1.66it/s]
 74%|███████▎  | 42431/57600 [7:27:13<2:32:47,  1.65it/s]
 74%|███████▎  | 42432/57600 [7:27:13<2:34:24,  1.64it/s]
 74%|███████▎  | 42433/57600 [7:27:14<2:34:27,  1.64it/s]
 74%|███████▎  | 42434/57600 [7:27:14<2:38:22,  1.60it/s]
 74%|███████▎  | 42435/57600 [7:27:15<2:34:44,  1.63it/s]
 74%|███████▎  | 42436/57600 [7:27:16<2:35:53,  1.62it/s]
 74%|███████▎  | 42437/57600 [7:27:16<2:40:55,  1.57it/s]
 74%|███████▎  | 42438/57600 [7:27:17<2:38:33,  1.59it/s]
 74%|███████▎  | 42439/57600 [7:27:18<2:37:58,  1.60it/s]
 74%|███████▎  | 42440/57600 [7:27:18<2:35:59,  1.62it/s]
                                                         
{'loss': 1.1629, 'learning_rate': 3.377003484320558e-07, 'epoch': 468.43}

 74%|███████▎  | 42440/57600 [7:27:18<2:35:59,  1.62it/s]
 74%|███████▎  | 42441/57600 [7:27:19<2:36:42,  1.61it/s]
 74%|███████▎  | 42442/57600 [7:27:19<2:33:08,  1.65it/s]
 74%|███████▎  | 42443/57600 [7:27:20<2:39:42,  1.58it/s]
 74%|███████▎  | 42444/57600 [7:27:21<2:37:37,  1.60it/s]
 74%|███████▎  | 42445/57600 [7:27:21<2:36:11,  1.62it/s]
 74%|███████▎  | 42446/57600 [7:27:22<2:38:49,  1.59it/s]
 74%|███████▎  | 42447/57600 [7:27:23<2:35:01,  1.63it/s]
 74%|███████▎  | 42448/57600 [7:27:23<2:36:15,  1.62it/s]
 74%|███████▎  | 42449/57600 [7:27:24<2:38:17,  1.60it/s]
 74%|███████▎  | 42450/57600 [7:27:24<2:39:08,  1.59it/s]
 74%|███████▎  | 42451/57600 [7:27:25<2:38:04,  1.60it/s]
 74%|███████▎  | 42452/57600 [7:27:26<2:37:42,  1.60it/s]
 74%|███████▎  | 42453/57600 [7:27:26<2:39:54,  1.58it/s]
 74%|███████▎  | 42454/57600 [7:27:27<2:38:18,  1.59it/s]
 74%|███████▎  | 42455/57600 [7:27:28<2:40:54,  1.57it/s]
 74%|███████▎  | 42456/57600 [7:27:28<2:46:02,  1.52it/s]
 74%|███████▎  | 42457/57600 [7:27:29<2:49:46,  1.49it/s]
 74%|███████▎  | 42458/57600 [7:27:30<2:52:31,  1.46it/s]
 74%|███████▎  | 42459/57600 [7:27:30<2:48:54,  1.49it/s]
 74%|███████▎  | 42460/57600 [7:27:31<2:44:44,  1.53it/s]
                                                         
{'loss': 1.1046, 'learning_rate': 3.373867595818815e-07, 'epoch': 468.65}

 74%|███████▎  | 42460/57600 [7:27:31<2:44:44,  1.53it/s]
 74%|███████▎  | 42461/57600 [7:27:32<2:42:45,  1.55it/s]
 74%|███████▎  | 42462/57600 [7:27:32<2:46:08,  1.52it/s]
 74%|███████▎  | 42463/57600 [7:27:33<2:44:05,  1.54it/s]
 74%|███████▎  | 42464/57600 [7:27:34<2:43:30,  1.54it/s]
 74%|███████▎  | 42465/57600 [7:27:34<2:41:03,  1.57it/s]
 74%|███████▎  | 42466/57600 [7:27:35<2:43:03,  1.55it/s]
 74%|███████▎  | 42467/57600 [7:27:36<2:48:52,  1.49it/s]
 74%|███████▎  | 42468/57600 [7:27:36<2:45:08,  1.53it/s]
 74%|███████▎  | 42469/57600 [7:27:37<2:38:59,  1.59it/s]
 74%|███████▎  | 42470/57600 [7:27:37<2:40:52,  1.57it/s]
 74%|███████▎  | 42471/57600 [7:27:38<2:41:11,  1.56it/s]
 74%|███████▎  | 42472/57600 [7:27:39<2:37:40,  1.60it/s]
 74%|███████▎  | 42473/57600 [7:27:39<2:37:20,  1.60it/s]
 74%|███████▎  | 42474/57600 [7:27:40<2:38:14,  1.59it/s]
 74%|███████▎  | 42475/57600 [7:27:41<2:37:35,  1.60it/s]
 74%|███████▎  | 42476/57600 [7:27:41<2:48:26,  1.50it/s]
 74%|███████▎  | 42477/57600 [7:27:42<2:43:36,  1.54it/s]
 74%|███████▎  | 42478/57600 [7:27:43<2:40:36,  1.57it/s]
 74%|███████▎  | 42479/57600 [7:27:43<2:40:15,  1.57it/s]
 74%|███████▍  | 42480/57600 [7:27:44<2:36:45,  1.61it/s]
                                                         
{'loss': 1.1401, 'learning_rate': 3.370731707317073e-07, 'epoch': 468.87}

 74%|███████▍  | 42480/57600 [7:27:44<2:36:45,  1.61it/s]
 74%|███████▍  | 42481/57600 [7:27:44<2:35:00,  1.63it/s]
 74%|███████▍  | 42482/57600 [7:27:45<2:36:15,  1.61it/s]
 74%|███████▍  | 42483/57600 [7:27:46<2:36:29,  1.61it/s]
 74%|███████▍  | 42484/57600 [7:27:46<2:46:04,  1.52it/s]
 74%|███████▍  | 42485/57600 [7:27:47<2:41:32,  1.56it/s]
 74%|███████▍  | 42486/57600 [7:27:48<2:47:32,  1.50it/s]
 74%|███████▍  | 42487/57600 [7:27:48<2:43:51,  1.54it/s]
 74%|███████▍  | 42488/57600 [7:27:49<2:44:40,  1.53it/s]
 74%|███████▍  | 42489/57600 [7:27:50<2:43:26,  1.54it/s]
 74%|███████▍  | 42490/57600 [7:27:50<2:41:24,  1.56it/s]
 74%|███████▍  | 42491/57600 [7:27:51<2:34:36,  1.63it/s]
 74%|███████▍  | 42492/57600 [7:27:51<2:42:30,  1.55it/s]
 74%|███████▍  | 42493/57600 [7:27:52<2:39:58,  1.57it/s]
 74%|███████▍  | 42494/57600 [7:27:53<2:42:06,  1.55it/s]
 74%|███████▍  | 42495/57600 [7:27:53<2:37:12,  1.60it/s]
 74%|███████▍  | 42496/57600 [7:27:54<2:32:01,  1.66it/s]
 74%|███████▍  | 42497/57600 [7:27:55<2:35:20,  1.62it/s]
 74%|███████▍  | 42498/57600 [7:27:55<2:33:43,  1.64it/s]
 74%|███████▍  | 42499/57600 [7:27:56<2:39:00,  1.58it/s]
 74%|███████▍  | 42500/57600 [7:27:56<2:40:35,  1.57it/s]
                                                         
{'loss': 1.1215, 'learning_rate': 3.3675958188153304e-07, 'epoch': 469.09}

 74%|███████▍  | 42500/57600 [7:27:56<2:40:35,  1.57it/s]
 74%|███████▍  | 42501/57600 [7:27:57<2:36:20,  1.61it/s]
 74%|███████▍  | 42502/57600 [7:27:58<2:34:06,  1.63it/s]
 74%|███████▍  | 42503/57600 [7:27:58<2:35:16,  1.62it/s]
 74%|███████▍  | 42504/57600 [7:27:59<2:38:25,  1.59it/s]
 74%|███████▍  | 42505/57600 [7:28:00<2:43:55,  1.53it/s]
 74%|███████▍  | 42506/57600 [7:28:00<2:39:39,  1.58it/s]
 74%|███████▍  | 42507/57600 [7:28:01<2:45:45,  1.52it/s]
 74%|███████▍  | 42508/57600 [7:28:02<2:53:02,  1.45it/s]
 74%|███████▍  | 42509/57600 [7:28:02<2:45:46,  1.52it/s]
 74%|███████▍  | 42510/57600 [7:28:03<2:45:06,  1.52it/s]
 74%|███████▍  | 42511/57600 [7:28:04<2:45:24,  1.52it/s]
 74%|███████▍  | 42512/57600 [7:28:04<2:41:37,  1.56it/s]
 74%|███████▍  | 42513/57600 [7:28:05<2:39:45,  1.57it/s]
 74%|███████▍  | 42514/57600 [7:28:05<2:36:27,  1.61it/s]
 74%|███████▍  | 42515/57600 [7:28:06<2:39:34,  1.58it/s]
 74%|███████▍  | 42516/57600 [7:28:07<2:36:42,  1.60it/s]
 74%|███████▍  | 42517/57600 [7:28:07<2:33:51,  1.63it/s]
 74%|███████▍  | 42518/57600 [7:28:08<2:37:32,  1.60it/s]
 74%|███████▍  | 42519/57600 [7:28:08<2:31:56,  1.65it/s]
 74%|███████▍  | 42520/57600 [7:28:09<2:30:44,  1.67it/s]
                                                         
{'loss': 1.1688, 'learning_rate': 3.364459930313589e-07, 'epoch': 469.32}

 74%|███████▍  | 42520/57600 [7:28:09<2:30:44,  1.67it/s]
 74%|███████▍  | 42521/57600 [7:28:10<2:37:10,  1.60it/s]
 74%|███████▍  | 42522/57600 [7:28:10<2:44:19,  1.53it/s]
 74%|███████▍  | 42523/57600 [7:28:11<2:44:33,  1.53it/s]
 74%|███████▍  | 42524/57600 [7:28:12<2:36:30,  1.61it/s]
 74%|███████▍  | 42525/57600 [7:28:12<2:38:56,  1.58it/s]
 74%|███████▍  | 42526/57600 [7:28:13<2:41:19,  1.56it/s]
 74%|███████▍  | 42527/57600 [7:28:14<2:41:12,  1.56it/s]
 74%|███████▍  | 42528/57600 [7:28:14<2:36:41,  1.60it/s]
 74%|███████▍  | 42529/57600 [7:28:15<2:37:22,  1.60it/s]
 74%|███████▍  | 42530/57600 [7:28:15<2:36:00,  1.61it/s]
 74%|███████▍  | 42531/57600 [7:28:16<2:36:40,  1.60it/s]
 74%|███████▍  | 42532/57600 [7:28:17<2:35:15,  1.62it/s]
 74%|███████▍  | 42533/57600 [7:28:17<2:35:50,  1.61it/s]
 74%|███████▍  | 42534/57600 [7:28:18<2:37:35,  1.59it/s]
 74%|███████▍  | 42535/57600 [7:28:19<2:42:11,  1.55it/s]
 74%|███████▍  | 42536/57600 [7:28:19<2:39:35,  1.57it/s]
 74%|███████▍  | 42537/57600 [7:28:20<2:38:10,  1.59it/s]
 74%|███████▍  | 42538/57600 [7:28:20<2:32:36,  1.64it/s]
 74%|███████▍  | 42539/57600 [7:28:21<2:29:57,  1.67it/s]
 74%|███████▍  | 42540/57600 [7:28:22<2:36:44,  1.60it/s]
                                                         
{'loss': 1.1017, 'learning_rate': 3.3613240418118465e-07, 'epoch': 469.54}

 74%|███████▍  | 42540/57600 [7:28:22<2:36:44,  1.60it/s]
 74%|███████▍  | 42541/57600 [7:28:22<2:39:00,  1.58it/s]
 74%|███████▍  | 42542/57600 [7:28:23<2:38:39,  1.58it/s]
 74%|███████▍  | 42543/57600 [7:28:24<2:36:45,  1.60it/s]
 74%|███████▍  | 42544/57600 [7:28:24<2:33:38,  1.63it/s]
 74%|███████▍  | 42545/57600 [7:28:25<2:34:30,  1.62it/s]
 74%|███████▍  | 42546/57600 [7:28:25<2:32:37,  1.64it/s]
 74%|███████▍  | 42547/57600 [7:28:26<2:33:54,  1.63it/s]
 74%|███████▍  | 42548/57600 [7:28:27<2:34:03,  1.63it/s]
 74%|███████▍  | 42549/57600 [7:28:27<2:33:52,  1.63it/s]
 74%|███████▍  | 42550/57600 [7:28:28<2:28:46,  1.69it/s]
 74%|███████▍  | 42551/57600 [7:28:28<2:36:14,  1.61it/s]
 74%|███████▍  | 42552/57600 [7:28:29<2:35:58,  1.61it/s]
 74%|███████▍  | 42553/57600 [7:28:30<2:33:27,  1.63it/s]
 74%|███████▍  | 42554/57600 [7:28:30<2:33:47,  1.63it/s]
 74%|███████▍  | 42555/57600 [7:28:31<2:35:20,  1.61it/s]
 74%|███████▍  | 42556/57600 [7:28:32<2:36:06,  1.61it/s]
 74%|███████▍  | 42557/57600 [7:28:32<2:38:33,  1.58it/s]
 74%|███████▍  | 42558/57600 [7:28:33<2:41:44,  1.55it/s]
 74%|███████▍  | 42559/57600 [7:28:34<2:50:52,  1.47it/s]
 74%|███████▍  | 42560/57600 [7:28:34<2:54:39,  1.44it/s]
                                                         
{'loss': 1.1356, 'learning_rate': 3.358188153310104e-07, 'epoch': 469.76}

 74%|███████▍  | 42560/57600 [7:28:34<2:54:39,  1.44it/s]
 74%|███████▍  | 42561/57600 [7:28:35<2:50:11,  1.47it/s]
 74%|███████▍  | 42562/57600 [7:28:36<2:48:20,  1.49it/s]
 74%|███████▍  | 42563/57600 [7:28:36<2:46:38,  1.50it/s]
 74%|███████▍  | 42564/57600 [7:28:37<2:45:26,  1.51it/s]
 74%|███████▍  | 42565/57600 [7:28:38<2:45:59,  1.51it/s]
 74%|███████▍  | 42566/57600 [7:28:38<2:44:02,  1.53it/s]
 74%|███████▍  | 42567/57600 [7:28:39<2:46:52,  1.50it/s]
 74%|███████▍  | 42568/57600 [7:28:40<2:43:54,  1.53it/s]
 74%|███████▍  | 42569/57600 [7:28:40<2:42:00,  1.55it/s]
 74%|███████▍  | 42570/57600 [7:28:41<2:37:15,  1.59it/s]
 74%|███████▍  | 42571/57600 [7:28:41<2:32:18,  1.64it/s]
 74%|███████▍  | 42572/57600 [7:28:42<2:32:41,  1.64it/s]
 74%|███████▍  | 42573/57600 [7:28:43<2:31:25,  1.65it/s]
 74%|███████▍  | 42574/57600 [7:28:43<2:31:43,  1.65it/s]
 74%|███████▍  | 42575/57600 [7:28:44<2:36:02,  1.60it/s]
 74%|███████▍  | 42576/57600 [7:28:45<2:40:22,  1.56it/s]
 74%|███████▍  | 42577/57600 [7:28:45<2:35:56,  1.61it/s]
 74%|███████▍  | 42578/57600 [7:28:46<2:35:40,  1.61it/s]
 74%|███████▍  | 42579/57600 [7:28:46<2:33:05,  1.64it/s]
 74%|███████▍  | 42580/57600 [7:28:47<2:32:39,  1.64it/s]
                                                         
{'loss': 1.1307, 'learning_rate': 3.3550522648083626e-07, 'epoch': 469.98}

 74%|███████▍  | 42580/57600 [7:28:47<2:32:39,  1.64it/s]
 74%|███████▍  | 42581/57600 [7:28:48<2:33:26,  1.63it/s]
 74%|███████▍  | 42582/57600 [7:28:48<2:37:40,  1.59it/s]
 74%|███████▍  | 42583/57600 [7:28:49<2:39:05,  1.57it/s]
 74%|███████▍  | 42584/57600 [7:28:50<2:41:00,  1.55it/s]
 74%|███████▍  | 42585/57600 [7:28:50<2:37:59,  1.58it/s]
 74%|███████▍  | 42586/57600 [7:28:51<2:32:42,  1.64it/s]
 74%|███████▍  | 42587/57600 [7:28:51<2:32:00,  1.65it/s]
 74%|███████▍  | 42588/57600 [7:28:52<2:37:13,  1.59it/s]
 74%|███████▍  | 42589/57600 [7:28:53<2:37:36,  1.59it/s]
 74%|███████▍  | 42590/57600 [7:28:53<2:34:34,  1.62it/s]
 74%|███████▍  | 42591/57600 [7:28:54<2:31:46,  1.65it/s]
 74%|███████▍  | 42592/57600 [7:28:54<2:31:43,  1.65it/s]
 74%|███████▍  | 42593/57600 [7:28:55<2:29:35,  1.67it/s]
 74%|███████▍  | 42594/57600 [7:28:56<2:27:33,  1.69it/s]
 74%|███████▍  | 42595/57600 [7:28:56<2:35:09,  1.61it/s]
 74%|███████▍  | 42596/57600 [7:28:57<2:32:02,  1.64it/s]
 74%|███████▍  | 42597/57600 [7:28:57<2:32:51,  1.64it/s]
 74%|███████▍  | 42598/57600 [7:28:58<2:33:19,  1.63it/s]
 74%|███████▍  | 42599/57600 [7:28:59<2:50:16,  1.47it/s]
 74%|███████▍  | 42600/57600 [7:29:00<2:48:56,  1.48it/s]
                                                         
{'loss': 1.1366, 'learning_rate': 3.3519163763066196e-07, 'epoch': 470.2}

 74%|███████▍  | 42600/57600 [7:29:00<2:48:56,  1.48it/s]
 74%|███████▍  | 42601/57600 [7:29:00<2:42:22,  1.54it/s]
 74%|███████▍  | 42602/57600 [7:29:01<2:40:23,  1.56it/s]
 74%|███████▍  | 42603/57600 [7:29:01<2:36:57,  1.59it/s]
 74%|███████▍  | 42604/57600 [7:29:02<2:34:59,  1.61it/s]
 74%|███████▍  | 42605/57600 [7:29:03<2:31:34,  1.65it/s]
 74%|███████▍  | 42606/57600 [7:29:03<2:32:32,  1.64it/s]
 74%|███████▍  | 42607/57600 [7:29:04<2:35:11,  1.61it/s]
 74%|███████▍  | 42608/57600 [7:29:04<2:33:12,  1.63it/s]
 74%|███████▍  | 42609/57600 [7:29:05<2:33:27,  1.63it/s]
 74%|███████▍  | 42610/57600 [7:29:06<2:32:46,  1.64it/s]
 74%|███████▍  | 42611/57600 [7:29:06<2:36:39,  1.59it/s]
 74%|███████▍  | 42612/57600 [7:29:07<2:33:01,  1.63it/s]
 74%|███████▍  | 42613/57600 [7:29:08<2:39:22,  1.57it/s]
 74%|███████▍  | 42614/57600 [7:29:08<2:39:38,  1.56it/s]
 74%|███████▍  | 42615/57600 [7:29:09<2:38:35,  1.57it/s]
 74%|███████▍  | 42616/57600 [7:29:09<2:35:02,  1.61it/s]
 74%|███████▍  | 42617/57600 [7:29:10<2:36:11,  1.60it/s]
 74%|███████▍  | 42618/57600 [7:29:11<2:38:14,  1.58it/s]
 74%|███████▍  | 42619/57600 [7:29:11<2:38:55,  1.57it/s]
 74%|███████▍  | 42620/57600 [7:29:12<2:37:18,  1.59it/s]
                                                         
{'loss': 1.1425, 'learning_rate': 3.3487804878048777e-07, 'epoch': 470.42}

 74%|███████▍  | 42620/57600 [7:29:12<2:37:18,  1.59it/s]
 74%|███████▍  | 42621/57600 [7:29:13<2:34:25,  1.62it/s]
 74%|███████▍  | 42622/57600 [7:29:13<2:35:37,  1.60it/s]
 74%|███████▍  | 42623/57600 [7:29:14<2:33:15,  1.63it/s]
 74%|███████▍  | 42624/57600 [7:29:14<2:33:26,  1.63it/s]
 74%|███████▍  | 42625/57600 [7:29:15<2:35:27,  1.61it/s]
 74%|███████▍  | 42626/57600 [7:29:16<2:32:10,  1.64it/s]
 74%|███████▍  | 42627/57600 [7:29:16<2:31:58,  1.64it/s]
 74%|███████▍  | 42628/57600 [7:29:17<2:35:02,  1.61it/s]
 74%|███████▍  | 42629/57600 [7:29:18<2:38:45,  1.57it/s]
 74%|███████▍  | 42630/57600 [7:29:18<2:36:59,  1.59it/s]
 74%|███████▍  | 42631/57600 [7:29:19<2:34:38,  1.61it/s]
 74%|███████▍  | 42632/57600 [7:29:19<2:33:52,  1.62it/s]
 74%|███████▍  | 42633/57600 [7:29:20<2:31:55,  1.64it/s]
 74%|███████▍  | 42634/57600 [7:29:21<2:30:48,  1.65it/s]
 74%|███████▍  | 42635/57600 [7:29:21<2:30:10,  1.66it/s]
 74%|███████▍  | 42636/57600 [7:29:22<2:32:04,  1.64it/s]
 74%|███████▍  | 42637/57600 [7:29:22<2:32:58,  1.63it/s]
 74%|███████▍  | 42638/57600 [7:29:23<2:32:07,  1.64it/s]
 74%|███████▍  | 42639/57600 [7:29:24<2:32:14,  1.64it/s]
 74%|███████▍  | 42640/57600 [7:29:24<2:35:23,  1.60it/s]
                                                         
{'loss': 1.1551, 'learning_rate': 3.345644599303135e-07, 'epoch': 470.64}

 74%|███████▍  | 42640/57600 [7:29:24<2:35:23,  1.60it/s]
 74%|███████▍  | 42641/57600 [7:29:25<2:45:31,  1.51it/s]
 74%|███████▍  | 42642/57600 [7:29:26<2:37:17,  1.58it/s]
 74%|███████▍  | 42643/57600 [7:29:26<2:34:24,  1.61it/s]
 74%|███████▍  | 42644/57600 [7:29:27<2:30:47,  1.65it/s]
 74%|███████▍  | 42645/57600 [7:29:27<2:30:08,  1.66it/s]
 74%|███████▍  | 42646/57600 [7:29:28<2:32:05,  1.64it/s]
 74%|███████▍  | 42647/57600 [7:29:29<2:37:05,  1.59it/s]
 74%|███████▍  | 42648/57600 [7:29:29<2:41:14,  1.55it/s]
 74%|███████▍  | 42649/57600 [7:29:30<2:34:38,  1.61it/s]
 74%|███████▍  | 42650/57600 [7:29:30<2:35:26,  1.60it/s]
 74%|███████▍  | 42651/57600 [7:29:31<2:31:28,  1.64it/s]
 74%|███████▍  | 42652/57600 [7:29:32<2:30:45,  1.65it/s]
 74%|███████▍  | 42653/57600 [7:29:32<2:32:22,  1.63it/s]
 74%|███████▍  | 42654/57600 [7:29:33<2:29:45,  1.66it/s]
 74%|███████▍  | 42655/57600 [7:29:34<2:34:42,  1.61it/s]
 74%|███████▍  | 42656/57600 [7:29:34<2:31:32,  1.64it/s]
 74%|███████▍  | 42657/57600 [7:29:35<2:36:50,  1.59it/s]
 74%|███████▍  | 42658/57600 [7:29:35<2:38:09,  1.57it/s]
 74%|███████▍  | 42659/57600 [7:29:36<2:39:19,  1.56it/s]
 74%|███████▍  | 42660/57600 [7:29:37<2:41:55,  1.54it/s]
                                                         
{'loss': 1.1276, 'learning_rate': 3.342508710801394e-07, 'epoch': 470.86}

 74%|███████▍  | 42660/57600 [7:29:37<2:41:55,  1.54it/s]
 74%|███████▍  | 42661/57600 [7:29:37<2:39:07,  1.56it/s]
 74%|███████▍  | 42662/57600 [7:29:38<2:38:19,  1.57it/s]
 74%|███████▍  | 42663/57600 [7:29:39<2:39:03,  1.57it/s]
 74%|███████▍  | 42664/57600 [7:29:39<2:39:14,  1.56it/s]
 74%|███████▍  | 42665/57600 [7:29:40<2:32:30,  1.63it/s]
 74%|███████▍  | 42666/57600 [7:29:41<2:37:09,  1.58it/s]
 74%|███████▍  | 42667/57600 [7:29:41<2:41:20,  1.54it/s]
 74%|███████▍  | 42668/57600 [7:29:42<2:44:42,  1.51it/s]
 74%|███████▍  | 42669/57600 [7:29:43<2:43:01,  1.53it/s]
 74%|███████▍  | 42670/57600 [7:29:43<2:39:42,  1.56it/s]
 74%|███████▍  | 42671/57600 [7:29:44<2:39:43,  1.56it/s]
 74%|███████▍  | 42672/57600 [7:29:44<2:41:48,  1.54it/s]
 74%|███████▍  | 42673/57600 [7:29:45<2:49:26,  1.47it/s]
 74%|███████▍  | 42674/57600 [7:29:46<2:47:21,  1.49it/s]
 74%|███████▍  | 42675/57600 [7:29:46<2:42:04,  1.53it/s]
 74%|███████▍  | 42676/57600 [7:29:47<2:36:44,  1.59it/s]
 74%|███████▍  | 42677/57600 [7:29:48<2:35:16,  1.60it/s]
 74%|███████▍  | 42678/57600 [7:29:48<2:34:06,  1.61it/s]
 74%|███████▍  | 42679/57600 [7:29:49<2:33:02,  1.62it/s]
 74%|███████▍  | 42680/57600 [7:29:49<2:33:13,  1.62it/s]
                                                         
{'loss': 1.1544, 'learning_rate': 3.339372822299652e-07, 'epoch': 471.08}

 74%|███████▍  | 42680/57600 [7:29:50<2:33:13,  1.62it/s]
 74%|███████▍  | 42681/57600 [7:29:50<2:34:31,  1.61it/s]
 74%|███████▍  | 42682/57600 [7:29:51<2:36:43,  1.59it/s]
 74%|███████▍  | 42683/57600 [7:29:51<2:33:36,  1.62it/s]
 74%|███████▍  | 42684/57600 [7:29:52<2:33:58,  1.61it/s]
 74%|███████▍  | 42685/57600 [7:29:53<2:30:29,  1.65it/s]
 74%|███████▍  | 42686/57600 [7:29:53<2:27:57,  1.68it/s]
 74%|███████▍  | 42687/57600 [7:29:54<2:29:09,  1.67it/s]
 74%|███████▍  | 42688/57600 [7:29:54<2:28:05,  1.68it/s]
 74%|███████▍  | 42689/57600 [7:29:55<2:32:51,  1.63it/s]
 74%|███████▍  | 42690/57600 [7:29:56<2:33:35,  1.62it/s]
 74%|███████▍  | 42691/57600 [7:29:56<2:32:58,  1.62it/s]
 74%|███████▍  | 42692/57600 [7:29:57<2:33:49,  1.62it/s]
 74%|███████▍  | 42693/57600 [7:29:57<2:34:41,  1.61it/s]
 74%|███████▍  | 42694/57600 [7:29:58<2:32:58,  1.62it/s]
 74%|███████▍  | 42695/57600 [7:29:59<2:29:15,  1.66it/s]
 74%|███████▍  | 42696/57600 [7:29:59<2:33:35,  1.62it/s]
 74%|███████▍  | 42697/57600 [7:30:00<2:36:25,  1.59it/s]
 74%|███████▍  | 42698/57600 [7:30:01<2:36:55,  1.58it/s]
 74%|███████▍  | 42699/57600 [7:30:01<2:36:35,  1.59it/s]
 74%|███████▍  | 42700/57600 [7:30:02<2:35:15,  1.60it/s]
                                                         
{'loss': 1.1279, 'learning_rate': 3.336236933797909e-07, 'epoch': 471.3}

 74%|███████▍  | 42700/57600 [7:30:02<2:35:15,  1.60it/s]
 74%|███████▍  | 42701/57600 [7:30:02<2:36:23,  1.59it/s]
 74%|███████▍  | 42702/57600 [7:30:03<2:35:57,  1.59it/s]
 74%|███████▍  | 42703/57600 [7:30:04<2:39:08,  1.56it/s]
 74%|███████▍  | 42704/57600 [7:30:04<2:41:24,  1.54it/s]
 74%|███████▍  | 42705/57600 [7:30:05<2:39:32,  1.56it/s]
 74%|███████▍  | 42706/57600 [7:30:06<2:37:01,  1.58it/s]
 74%|███████▍  | 42707/57600 [7:30:06<2:36:09,  1.59it/s]
 74%|███████▍  | 42708/57600 [7:30:07<2:33:06,  1.62it/s]
 74%|███████▍  | 42709/57600 [7:30:08<2:34:07,  1.61it/s]
 74%|███████▍  | 42710/57600 [7:30:08<2:35:56,  1.59it/s]
 74%|███████▍  | 42711/57600 [7:30:09<2:35:45,  1.59it/s]
 74%|███████▍  | 42712/57600 [7:30:09<2:34:56,  1.60it/s]
 74%|███████▍  | 42713/57600 [7:30:10<2:34:33,  1.61it/s]
 74%|███████▍  | 42714/57600 [7:30:11<2:40:16,  1.55it/s]
 74%|███████▍  | 42715/57600 [7:30:11<2:43:25,  1.52it/s]
 74%|███████▍  | 42716/57600 [7:30:12<2:39:00,  1.56it/s]
 74%|███████▍  | 42717/57600 [7:30:13<2:33:19,  1.62it/s]
 74%|███████▍  | 42718/57600 [7:30:13<2:36:06,  1.59it/s]
 74%|███████▍  | 42719/57600 [7:30:14<2:33:39,  1.61it/s]
 74%|███████▍  | 42720/57600 [7:30:15<2:37:56,  1.57it/s]
                                                         
{'loss': 1.1445, 'learning_rate': 3.3331010452961674e-07, 'epoch': 471.52}

 74%|███████▍  | 42720/57600 [7:30:15<2:37:56,  1.57it/s]
 74%|███████▍  | 42721/57600 [7:30:15<2:33:31,  1.62it/s]
 74%|███████▍  | 42722/57600 [7:30:16<2:32:22,  1.63it/s]
 74%|███████▍  | 42723/57600 [7:30:16<2:33:44,  1.61it/s]
 74%|███████▍  | 42724/57600 [7:30:17<2:36:47,  1.58it/s]
 74%|███████▍  | 42725/57600 [7:30:18<2:33:18,  1.62it/s]
 74%|███████▍  | 42726/57600 [7:30:18<2:31:38,  1.63it/s]
 74%|███████▍  | 42727/57600 [7:30:19<2:33:17,  1.62it/s]
 74%|███████▍  | 42728/57600 [7:30:19<2:28:31,  1.67it/s]
 74%|███████▍  | 42729/57600 [7:30:20<2:28:05,  1.67it/s]
 74%|███████▍  | 42730/57600 [7:30:21<2:32:55,  1.62it/s]
 74%|███████▍  | 42731/57600 [7:30:21<2:34:07,  1.61it/s]
 74%|███████▍  | 42732/57600 [7:30:22<2:31:31,  1.64it/s]
 74%|███████▍  | 42733/57600 [7:30:23<2:37:16,  1.58it/s]
 74%|███████▍  | 42734/57600 [7:30:23<2:33:45,  1.61it/s]
 74%|███████▍  | 42735/57600 [7:30:24<2:31:46,  1.63it/s]
 74%|███████▍  | 42736/57600 [7:30:24<2:37:31,  1.57it/s]
 74%|███████▍  | 42737/57600 [7:30:25<2:38:20,  1.56it/s]
 74%|███████▍  | 42738/57600 [7:30:26<2:35:10,  1.60it/s]
 74%|███████▍  | 42739/57600 [7:30:26<2:31:34,  1.63it/s]
 74%|███████▍  | 42740/57600 [7:30:27<2:31:51,  1.63it/s]
                                                         
{'loss': 1.1409, 'learning_rate': 3.329965156794425e-07, 'epoch': 471.74}

 74%|███████▍  | 42740/57600 [7:30:27<2:31:51,  1.63it/s]
 74%|███████▍  | 42741/57600 [7:30:28<2:37:27,  1.57it/s]
 74%|███████▍  | 42742/57600 [7:30:28<2:36:33,  1.58it/s]
 74%|███████▍  | 42743/57600 [7:30:29<2:32:07,  1.63it/s]
 74%|███████▍  | 42744/57600 [7:30:29<2:30:22,  1.65it/s]
 74%|███████▍  | 42745/57600 [7:30:30<2:29:55,  1.65it/s]
 74%|███████▍  | 42746/57600 [7:30:31<2:35:42,  1.59it/s]
 74%|███████▍  | 42747/57600 [7:30:31<2:36:58,  1.58it/s]
 74%|███████▍  | 42748/57600 [7:30:32<2:37:47,  1.57it/s]
 74%|███████▍  | 42749/57600 [7:30:32<2:31:29,  1.63it/s]
 74%|███████▍  | 42750/57600 [7:30:33<2:31:43,  1.63it/s]
 74%|███████▍  | 42751/57600 [7:30:34<2:35:27,  1.59it/s]
 74%|███████▍  | 42752/57600 [7:30:34<2:37:25,  1.57it/s]
 74%|███████▍  | 42753/57600 [7:30:35<2:33:06,  1.62it/s]
 74%|███████▍  | 42754/57600 [7:30:36<2:37:33,  1.57it/s]
 74%|███████▍  | 42755/57600 [7:30:36<2:35:33,  1.59it/s]
 74%|███████▍  | 42756/57600 [7:30:37<2:35:39,  1.59it/s]
 74%|███████▍  | 42757/57600 [7:30:38<2:43:28,  1.51it/s]
 74%|███████▍  | 42758/57600 [7:30:38<2:40:57,  1.54it/s]
 74%|███████▍  | 42759/57600 [7:30:39<2:43:11,  1.52it/s]
 74%|███████▍  | 42760/57600 [7:30:40<2:41:10,  1.53it/s]
                                                         
{'loss': 1.1386, 'learning_rate': 3.326829268292683e-07, 'epoch': 471.96}

 74%|███████▍  | 42760/57600 [7:30:40<2:41:10,  1.53it/s]
 74%|███████▍  | 42761/57600 [7:30:40<2:38:04,  1.56it/s]
 74%|███████▍  | 42762/57600 [7:30:41<2:38:07,  1.56it/s]
 74%|███████▍  | 42763/57600 [7:30:41<2:36:28,  1.58it/s]
 74%|███████▍  | 42764/57600 [7:30:42<2:50:53,  1.45it/s]
 74%|███████▍  | 42765/57600 [7:30:43<2:43:44,  1.51it/s]
 74%|███████▍  | 42766/57600 [7:30:44<2:45:35,  1.49it/s]
 74%|███████▍  | 42767/57600 [7:30:44<2:41:23,  1.53it/s]
 74%|███████▍  | 42768/57600 [7:30:45<2:36:28,  1.58it/s]
 74%|███████▍  | 42769/57600 [7:30:45<2:34:28,  1.60it/s]
 74%|███████▍  | 42770/57600 [7:30:46<2:42:17,  1.52it/s]
 74%|███████▍  | 42771/57600 [7:30:47<2:42:38,  1.52it/s]
 74%|███████▍  | 42772/57600 [7:30:47<2:38:28,  1.56it/s]
 74%|███████▍  | 42773/57600 [7:30:48<2:41:30,  1.53it/s]
 74%|███████▍  | 42774/57600 [7:30:49<2:38:07,  1.56it/s]
 74%|███████▍  | 42775/57600 [7:30:49<2:38:42,  1.56it/s]
 74%|███████▍  | 42776/57600 [7:30:50<2:42:00,  1.53it/s]
 74%|███████▍  | 42777/57600 [7:30:51<2:39:15,  1.55it/s]
 74%|███████▍  | 42778/57600 [7:30:51<2:37:04,  1.57it/s]
 74%|███████▍  | 42779/57600 [7:30:52<2:35:21,  1.59it/s]
 74%|███████▍  | 42780/57600 [7:30:52<2:33:34,  1.61it/s]
                                                         
{'loss': 1.1302, 'learning_rate': 3.323693379790941e-07, 'epoch': 472.19}

 74%|███████▍  | 42780/57600 [7:30:52<2:33:34,  1.61it/s]
 74%|███████▍  | 42781/57600 [7:30:53<2:32:24,  1.62it/s]
 74%|███████▍  | 42782/57600 [7:30:54<2:30:04,  1.65it/s]
 74%|███████▍  | 42783/57600 [7:30:54<2:30:15,  1.64it/s]
 74%|███████▍  | 42784/57600 [7:30:55<2:30:19,  1.64it/s]
 74%|███████▍  | 42785/57600 [7:30:55<2:30:38,  1.64it/s]
 74%|███████▍  | 42786/57600 [7:30:56<2:36:10,  1.58it/s]
 74%|███████▍  | 42787/57600 [7:30:57<2:35:17,  1.59it/s]
 74%|███████▍  | 42788/57600 [7:30:57<2:35:19,  1.59it/s]
 74%|███████▍  | 42789/57600 [7:30:58<2:34:31,  1.60it/s]
 74%|███████▍  | 42790/57600 [7:30:59<2:40:31,  1.54it/s]
 74%|███████▍  | 42791/57600 [7:30:59<2:41:09,  1.53it/s]
 74%|███████▍  | 42792/57600 [7:31:00<2:34:54,  1.59it/s]
 74%|███████▍  | 42793/57600 [7:31:01<2:31:32,  1.63it/s]
 74%|███████▍  | 42794/57600 [7:31:01<2:33:37,  1.61it/s]
 74%|███████▍  | 42795/57600 [7:31:02<2:35:05,  1.59it/s]
 74%|███████▍  | 42796/57600 [7:31:02<2:35:32,  1.59it/s]
 74%|███████▍  | 42797/57600 [7:31:03<2:33:25,  1.61it/s]
 74%|███████▍  | 42798/57600 [7:31:04<2:29:39,  1.65it/s]
 74%|███████▍  | 42799/57600 [7:31:04<2:27:35,  1.67it/s]
 74%|███████▍  | 42800/57600 [7:31:05<2:34:34,  1.60it/s]
                                                         
{'loss': 1.1509, 'learning_rate': 3.3205574912891985e-07, 'epoch': 472.41}

 74%|███████▍  | 42800/57600 [7:31:05<2:34:34,  1.60it/s]
 74%|███████▍  | 42801/57600 [7:31:06<2:35:30,  1.59it/s]
 74%|███████▍  | 42802/57600 [7:31:06<2:34:50,  1.59it/s]
 74%|███████▍  | 42803/57600 [7:31:07<2:32:56,  1.61it/s]
 74%|███████▍  | 42804/57600 [7:31:07<2:29:12,  1.65it/s]
 74%|███████▍  | 42805/57600 [7:31:08<2:34:05,  1.60it/s]
 74%|███████▍  | 42806/57600 [7:31:09<2:31:15,  1.63it/s]
 74%|███████▍  | 42807/57600 [7:31:09<2:36:36,  1.57it/s]
 74%|███████▍  | 42808/57600 [7:31:10<2:40:52,  1.53it/s]
 74%|███████▍  | 42809/57600 [7:31:11<2:38:51,  1.55it/s]
 74%|███████▍  | 42810/57600 [7:31:11<2:37:20,  1.57it/s]
 74%|███████▍  | 42811/57600 [7:31:12<2:33:48,  1.60it/s]
 74%|███████▍  | 42812/57600 [7:31:12<2:36:59,  1.57it/s]
 74%|███████▍  | 42813/57600 [7:31:13<2:34:01,  1.60it/s]
 74%|███████▍  | 42814/57600 [7:31:14<2:31:19,  1.63it/s]
 74%|███████▍  | 42815/57600 [7:31:14<2:31:53,  1.62it/s]
 74%|███████▍  | 42816/57600 [7:31:15<2:29:14,  1.65it/s]
 74%|███████▍  | 42817/57600 [7:31:15<2:32:28,  1.62it/s]
 74%|███████▍  | 42818/57600 [7:31:16<2:34:51,  1.59it/s]
 74%|███████▍  | 42819/57600 [7:31:17<2:37:00,  1.57it/s]
 74%|███████▍  | 42820/57600 [7:31:17<2:37:36,  1.56it/s]
                                                         
{'loss': 1.1168, 'learning_rate': 3.3174216027874566e-07, 'epoch': 472.63}

 74%|███████▍  | 42820/57600 [7:31:17<2:37:36,  1.56it/s]
 74%|███████▍  | 42821/57600 [7:31:18<2:36:23,  1.58it/s]
 74%|███████▍  | 42822/57600 [7:31:19<2:34:40,  1.59it/s]
 74%|███████▍  | 42823/57600 [7:31:19<2:33:34,  1.60it/s]
 74%|███████▍  | 42824/57600 [7:31:20<2:38:55,  1.55it/s]
 74%|███████▍  | 42825/57600 [7:31:21<2:32:18,  1.62it/s]
 74%|███████▍  | 42826/57600 [7:31:21<2:40:13,  1.54it/s]
 74%|███████▍  | 42827/57600 [7:31:22<2:31:37,  1.62it/s]
 74%|███████▍  | 42828/57600 [7:31:22<2:31:39,  1.62it/s]
 74%|███████▍  | 42829/57600 [7:31:23<2:36:42,  1.57it/s]
 74%|███████▍  | 42830/57600 [7:31:24<2:32:25,  1.61it/s]
 74%|███████▍  | 42831/57600 [7:31:24<2:29:29,  1.65it/s]
 74%|███████▍  | 42832/57600 [7:31:25<2:31:40,  1.62it/s]
 74%|███████▍  | 42833/57600 [7:31:26<2:36:14,  1.58it/s]
 74%|███████▍  | 42834/57600 [7:31:26<2:38:17,  1.55it/s]
 74%|███████▍  | 42835/57600 [7:31:27<2:40:58,  1.53it/s]
 74%|███████▍  | 42836/57600 [7:31:28<2:39:14,  1.55it/s]
 74%|███████▍  | 42837/57600 [7:31:28<2:42:13,  1.52it/s]
 74%|███████▍  | 42838/57600 [7:31:29<2:40:52,  1.53it/s]
 74%|███████▍  | 42839/57600 [7:31:30<2:39:47,  1.54it/s]
 74%|███████▍  | 42840/57600 [7:31:30<2:40:30,  1.53it/s]
                                                         
{'loss': 1.095, 'learning_rate': 3.3142857142857136e-07, 'epoch': 472.85}

 74%|███████▍  | 42840/57600 [7:31:30<2:40:30,  1.53it/s]
 74%|███████▍  | 42841/57600 [7:31:31<2:35:00,  1.59it/s]
 74%|███████▍  | 42842/57600 [7:31:31<2:33:32,  1.60it/s]
 74%|███████▍  | 42843/57600 [7:31:32<2:38:36,  1.55it/s]
 74%|███████▍  | 42844/57600 [7:31:33<2:37:12,  1.56it/s]
 74%|███████▍  | 42845/57600 [7:31:33<2:35:49,  1.58it/s]
 74%|███████▍  | 42846/57600 [7:31:34<2:32:27,  1.61it/s]
 74%|███████▍  | 42847/57600 [7:31:34<2:30:27,  1.63it/s]
 74%|███████▍  | 42848/57600 [7:31:35<2:31:32,  1.62it/s]
 74%|███████▍  | 42849/57600 [7:31:36<2:30:24,  1.63it/s]
 74%|███████▍  | 42850/57600 [7:31:36<2:28:47,  1.65it/s]
 74%|███████▍  | 42851/57600 [7:31:37<2:28:49,  1.65it/s]
 74%|███████▍  | 42852/57600 [7:31:38<2:28:30,  1.66it/s]
 74%|███████▍  | 42853/57600 [7:31:38<2:33:40,  1.60it/s]
 74%|███████▍  | 42854/57600 [7:31:39<2:38:58,  1.55it/s]
 74%|███████▍  | 42855/57600 [7:31:39<2:36:05,  1.57it/s]
 74%|███████▍  | 42856/57600 [7:31:40<2:34:46,  1.59it/s]
 74%|███████▍  | 42857/57600 [7:31:41<2:31:36,  1.62it/s]
 74%|███████▍  | 42858/57600 [7:31:41<2:32:44,  1.61it/s]
 74%|███████▍  | 42859/57600 [7:31:42<2:28:05,  1.66it/s]
 74%|███████▍  | 42860/57600 [7:31:42<2:27:41,  1.66it/s]
                                                         
{'loss': 1.1584, 'learning_rate': 3.311149825783972e-07, 'epoch': 473.07}

 74%|███████▍  | 42860/57600 [7:31:42<2:27:41,  1.66it/s]
 74%|███████▍  | 42861/57600 [7:31:43<2:27:30,  1.67it/s]
 74%|███████▍  | 42862/57600 [7:31:44<2:28:47,  1.65it/s]
 74%|███████▍  | 42863/57600 [7:31:44<2:26:39,  1.67it/s]
 74%|███████▍  | 42864/57600 [7:31:45<2:24:45,  1.70it/s]
 74%|███████▍  | 42865/57600 [7:31:46<2:31:59,  1.62it/s]
 74%|███████▍  | 42866/57600 [7:31:46<2:29:50,  1.64it/s]
 74%|███████▍  | 42867/57600 [7:31:47<2:32:16,  1.61it/s]
 74%|███████▍  | 42868/57600 [7:31:47<2:30:08,  1.64it/s]
 74%|███████▍  | 42869/57600 [7:31:48<2:36:22,  1.57it/s]
 74%|███████▍  | 42870/57600 [7:31:49<2:35:52,  1.58it/s]
 74%|███████▍  | 42871/57600 [7:31:49<2:30:12,  1.63it/s]
 74%|███████▍  | 42872/57600 [7:31:50<2:33:23,  1.60it/s]
 74%|███████▍  | 42873/57600 [7:31:50<2:31:22,  1.62it/s]
 74%|███████▍  | 42874/57600 [7:31:51<2:30:32,  1.63it/s]
 74%|███████▍  | 42875/57600 [7:31:52<2:35:42,  1.58it/s]
 74%|███████▍  | 42876/57600 [7:31:52<2:31:58,  1.61it/s]
 74%|███████▍  | 42877/57600 [7:31:53<2:31:38,  1.62it/s]
 74%|███████▍  | 42878/57600 [7:31:54<2:32:18,  1.61it/s]
 74%|███████▍  | 42879/57600 [7:31:54<2:35:30,  1.58it/s]
 74%|███████▍  | 42880/57600 [7:31:55<2:31:33,  1.62it/s]
                                                         
{'loss': 1.1508, 'learning_rate': 3.3080139372822297e-07, 'epoch': 473.29}

 74%|███████▍  | 42880/57600 [7:31:55<2:31:33,  1.62it/s]
 74%|███████▍  | 42881/57600 [7:31:55<2:29:46,  1.64it/s]
 74%|███████▍  | 42882/57600 [7:31:56<2:32:03,  1.61it/s]
 74%|███████▍  | 42883/57600 [7:31:57<2:40:03,  1.53it/s]
 74%|███████▍  | 42884/57600 [7:31:57<2:38:54,  1.54it/s]
 74%|███████▍  | 42885/57600 [7:31:58<2:35:41,  1.58it/s]
 74%|███████▍  | 42886/57600 [7:31:59<2:36:52,  1.56it/s]
 74%|███████▍  | 42887/57600 [7:31:59<2:31:41,  1.62it/s]
 74%|███████▍  | 42888/57600 [7:32:00<2:30:20,  1.63it/s]
 74%|███████▍  | 42889/57600 [7:32:01<2:32:21,  1.61it/s]
 74%|███████▍  | 42890/57600 [7:32:01<2:34:13,  1.59it/s]
 74%|███████▍  | 42891/57600 [7:32:02<2:34:08,  1.59it/s]
 74%|███████▍  | 42892/57600 [7:32:02<2:31:52,  1.61it/s]
 74%|███████▍  | 42893/57600 [7:32:03<2:29:49,  1.64it/s]
 74%|███████▍  | 42894/57600 [7:32:04<2:30:29,  1.63it/s]
 74%|███████▍  | 42895/57600 [7:32:04<2:31:02,  1.62it/s]
 74%|███████▍  | 42896/57600 [7:32:05<2:31:27,  1.62it/s]
 74%|███████▍  | 42897/57600 [7:32:05<2:31:48,  1.61it/s]
 74%|███████▍  | 42898/57600 [7:32:06<2:33:13,  1.60it/s]
 74%|███████▍  | 42899/57600 [7:32:07<2:34:16,  1.59it/s]
 74%|███████▍  | 42900/57600 [7:32:07<2:35:19,  1.58it/s]
                                                         
{'loss': 1.1147, 'learning_rate': 3.3048780487804877e-07, 'epoch': 473.51}

 74%|███████▍  | 42900/57600 [7:32:07<2:35:19,  1.58it/s]
 74%|███████▍  | 42901/57600 [7:32:08<2:34:50,  1.58it/s]
 74%|███████▍  | 42902/57600 [7:32:09<2:32:54,  1.60it/s]
 74%|███████▍  | 42903/57600 [7:32:09<2:40:37,  1.52it/s]
 74%|███████▍  | 42904/57600 [7:32:10<2:36:43,  1.56it/s]
 74%|███████▍  | 42905/57600 [7:32:11<2:31:42,  1.61it/s]
 74%|███████▍  | 42906/57600 [7:32:11<2:27:48,  1.66it/s]
 74%|███████▍  | 42907/57600 [7:32:12<2:30:12,  1.63it/s]
 74%|███████▍  | 42908/57600 [7:32:12<2:36:47,  1.56it/s]
 74%|███████▍  | 42909/57600 [7:32:13<2:38:23,  1.55it/s]
 74%|███████▍  | 42910/57600 [7:32:14<2:33:29,  1.60it/s]
 74%|███████▍  | 42911/57600 [7:32:14<2:32:08,  1.61it/s]
 74%|███████▍  | 42912/57600 [7:32:15<2:33:35,  1.59it/s]
 75%|███████▍  | 42913/57600 [7:32:16<2:36:53,  1.56it/s]
 75%|███████▍  | 42914/57600 [7:32:16<2:33:56,  1.59it/s]
 75%|███████▍  | 42915/57600 [7:32:17<2:34:28,  1.58it/s]
 75%|███████▍  | 42916/57600 [7:32:17<2:31:24,  1.62it/s]
 75%|███████▍  | 42917/57600 [7:32:18<2:35:41,  1.57it/s]
 75%|███████▍  | 42918/57600 [7:32:19<2:33:18,  1.60it/s]
 75%|███████▍  | 42919/57600 [7:32:19<2:34:00,  1.59it/s]
 75%|███████▍  | 42920/57600 [7:32:20<2:36:36,  1.56it/s]
                                                         
{'loss': 1.1217, 'learning_rate': 3.301742160278746e-07, 'epoch': 473.73}

 75%|███████▍  | 42920/57600 [7:32:20<2:36:36,  1.56it/s]
 75%|███████▍  | 42921/57600 [7:32:21<2:33:12,  1.60it/s]
 75%|███████▍  | 42922/57600 [7:32:21<2:34:56,  1.58it/s]
 75%|███████▍  | 42923/57600 [7:32:22<2:35:30,  1.57it/s]
 75%|███████▍  | 42924/57600 [7:32:23<2:35:54,  1.57it/s]
 75%|███████▍  | 42925/57600 [7:32:23<2:38:26,  1.54it/s]
 75%|███████▍  | 42926/57600 [7:32:24<2:36:03,  1.57it/s]
 75%|███████▍  | 42927/57600 [7:32:24<2:37:02,  1.56it/s]
 75%|███████▍  | 42928/57600 [7:32:25<2:36:07,  1.57it/s]
 75%|███████▍  | 42929/57600 [7:32:26<2:36:37,  1.56it/s]
 75%|███████▍  | 42930/57600 [7:32:26<2:36:17,  1.56it/s]
 75%|███████▍  | 42931/57600 [7:32:27<2:39:26,  1.53it/s]
 75%|███████▍  | 42932/57600 [7:32:28<2:40:15,  1.53it/s]
 75%|███████▍  | 42933/57600 [7:32:28<2:38:03,  1.55it/s]
 75%|███████▍  | 42934/57600 [7:32:29<2:40:46,  1.52it/s]
 75%|███████▍  | 42935/57600 [7:32:30<2:38:08,  1.55it/s]
 75%|███████▍  | 42936/57600 [7:32:30<2:36:21,  1.56it/s]
 75%|███████▍  | 42937/57600 [7:32:31<2:32:31,  1.60it/s]
 75%|███████▍  | 42938/57600 [7:32:32<2:33:52,  1.59it/s]
 75%|███████▍  | 42939/57600 [7:32:32<2:33:34,  1.59it/s]
 75%|███████▍  | 42940/57600 [7:32:33<2:31:20,  1.61it/s]
                                                         
{'loss': 1.1099, 'learning_rate': 3.2986062717770033e-07, 'epoch': 473.95}

 75%|███████▍  | 42940/57600 [7:32:33<2:31:20,  1.61it/s]
 75%|███████▍  | 42941/57600 [7:32:33<2:29:00,  1.64it/s]
 75%|███████▍  | 42942/57600 [7:32:34<2:33:05,  1.60it/s]
 75%|███████▍  | 42943/57600 [7:32:35<2:30:14,  1.63it/s]
 75%|███████▍  | 42944/57600 [7:32:35<2:37:00,  1.56it/s]
 75%|███████▍  | 42945/57600 [7:32:36<2:45:59,  1.47it/s]
 75%|███████▍  | 42946/57600 [7:32:37<2:40:17,  1.52it/s]
 75%|███████▍  | 42947/57600 [7:32:37<2:36:30,  1.56it/s]
 75%|███████▍  | 42948/57600 [7:32:38<2:36:43,  1.56it/s]
 75%|███████▍  | 42949/57600 [7:32:39<2:33:19,  1.59it/s]
 75%|███████▍  | 42950/57600 [7:32:39<2:30:49,  1.62it/s]
 75%|███████▍  | 42951/57600 [7:32:40<2:33:27,  1.59it/s]
 75%|███████▍  | 42952/57600 [7:32:40<2:33:34,  1.59it/s]
 75%|███████▍  | 42953/57600 [7:32:41<2:31:12,  1.61it/s]
 75%|███████▍  | 42954/57600 [7:32:42<2:25:53,  1.67it/s]
 75%|███████▍  | 42955/57600 [7:32:42<2:24:29,  1.69it/s]
 75%|███████▍  | 42956/57600 [7:32:43<2:26:30,  1.67it/s]
 75%|███████▍  | 42957/57600 [7:32:43<2:27:04,  1.66it/s]
 75%|███████▍  | 42958/57600 [7:32:44<2:33:10,  1.59it/s]
 75%|███████▍  | 42959/57600 [7:32:45<2:31:55,  1.61it/s]
 75%|███████▍  | 42960/57600 [7:32:45<2:28:49,  1.64it/s]
                                                         
{'loss': 1.1578, 'learning_rate': 3.295470383275262e-07, 'epoch': 474.17}

 75%|███████▍  | 42960/57600 [7:32:45<2:28:49,  1.64it/s]
 75%|███████▍  | 42961/57600 [7:32:46<2:32:11,  1.60it/s]
 75%|███████▍  | 42962/57600 [7:32:46<2:28:06,  1.65it/s]
 75%|███████▍  | 42963/57600 [7:32:47<2:28:11,  1.65it/s]
 75%|███████▍  | 42964/57600 [7:32:48<2:29:09,  1.64it/s]
 75%|███████▍  | 42965/57600 [7:32:48<2:32:46,  1.60it/s]
 75%|███████▍  | 42966/57600 [7:32:49<2:31:45,  1.61it/s]
 75%|███████▍  | 42967/57600 [7:32:50<2:38:00,  1.54it/s]
 75%|███████▍  | 42968/57600 [7:32:50<2:32:38,  1.60it/s]
 75%|███████▍  | 42969/57600 [7:32:51<2:32:33,  1.60it/s]
 75%|███████▍  | 42970/57600 [7:32:51<2:30:30,  1.62it/s]
 75%|███████▍  | 42971/57600 [7:32:52<2:28:36,  1.64it/s]
 75%|███████▍  | 42972/57600 [7:32:53<2:28:57,  1.64it/s]
 75%|███████▍  | 42973/57600 [7:32:53<2:26:39,  1.66it/s]
 75%|███████▍  | 42974/57600 [7:32:54<2:28:35,  1.64it/s]
 75%|███████▍  | 42975/57600 [7:32:54<2:28:29,  1.64it/s]
 75%|███████▍  | 42976/57600 [7:32:55<2:29:04,  1.64it/s]
 75%|███████▍  | 42977/57600 [7:32:56<2:34:18,  1.58it/s]
 75%|███████▍  | 42978/57600 [7:32:56<2:34:37,  1.58it/s]
 75%|███████▍  | 42979/57600 [7:32:57<2:35:52,  1.56it/s]
 75%|███████▍  | 42980/57600 [7:32:58<2:33:00,  1.59it/s]
                                                         
{'loss': 1.1245, 'learning_rate': 3.292334494773519e-07, 'epoch': 474.39}

 75%|███████▍  | 42980/57600 [7:32:58<2:33:00,  1.59it/s]
 75%|███████▍  | 42981/57600 [7:32:58<2:34:17,  1.58it/s]
 75%|███████▍  | 42982/57600 [7:32:59<2:30:28,  1.62it/s]
 75%|███████▍  | 42983/57600 [7:33:00<2:34:04,  1.58it/s]
 75%|███████▍  | 42984/57600 [7:33:00<2:32:41,  1.60it/s]
 75%|███████▍  | 42985/57600 [7:33:01<2:31:45,  1.61it/s]
 75%|███████▍  | 42986/57600 [7:33:01<2:32:55,  1.59it/s]
 75%|███████▍  | 42987/57600 [7:33:02<2:36:56,  1.55it/s]
 75%|███████▍  | 42988/57600 [7:33:03<2:33:40,  1.58it/s]
 75%|███████▍  | 42989/57600 [7:33:03<2:34:58,  1.57it/s]
 75%|███████▍  | 42990/57600 [7:33:04<2:41:21,  1.51it/s]
 75%|███████▍  | 42991/57600 [7:33:05<2:41:12,  1.51it/s]
 75%|███████▍  | 42992/57600 [7:33:05<2:36:00,  1.56it/s]
 75%|███████▍  | 42993/57600 [7:33:06<2:36:37,  1.55it/s]
 75%|███████▍  | 42994/57600 [7:33:07<2:33:31,  1.59it/s]
 75%|███████▍  | 42995/57600 [7:33:07<2:35:00,  1.57it/s]
 75%|███████▍  | 42996/57600 [7:33:08<2:36:08,  1.56it/s]
 75%|███████▍  | 42997/57600 [7:33:08<2:33:51,  1.58it/s]
 75%|███████▍  | 42998/57600 [7:33:09<2:34:34,  1.57it/s]
 75%|███████▍  | 42999/57600 [7:33:10<2:39:56,  1.52it/s]
 75%|███████▍  | 43000/57600 [7:33:10<2:37:55,  1.54it/s]
                                                         
{'loss': 1.1166, 'learning_rate': 3.289198606271777e-07, 'epoch': 474.61}

 75%|███████▍  | 43000/57600 [7:33:10<2:37:55,  1.54it/s]
 75%|███████▍  | 43001/57600 [7:33:11<2:43:06,  1.49it/s]
 75%|███████▍  | 43002/57600 [7:33:12<2:40:54,  1.51it/s]
 75%|███████▍  | 43003/57600 [7:33:12<2:40:38,  1.51it/s]
 75%|███████▍  | 43004/57600 [7:33:13<2:41:00,  1.51it/s]
 75%|███████▍  | 43005/57600 [7:33:14<2:34:17,  1.58it/s]
 75%|███████▍  | 43006/57600 [7:33:14<2:32:44,  1.59it/s]
 75%|███████▍  | 43007/57600 [7:33:15<2:33:28,  1.58it/s]
 75%|███████▍  | 43008/57600 [7:33:16<2:35:31,  1.56it/s]
 75%|███████▍  | 43009/57600 [7:33:16<2:41:24,  1.51it/s]
 75%|███████▍  | 43010/57600 [7:33:17<2:36:40,  1.55it/s]
 75%|███████▍  | 43011/57600 [7:33:18<2:38:31,  1.53it/s]
 75%|███████▍  | 43012/57600 [7:33:18<2:37:45,  1.54it/s]
 75%|███████▍  | 43013/57600 [7:33:19<2:36:19,  1.56it/s]
 75%|███████▍  | 43014/57600 [7:33:20<2:34:07,  1.58it/s]
 75%|███████▍  | 43015/57600 [7:33:20<2:33:04,  1.59it/s]
 75%|███████▍  | 43016/57600 [7:33:21<2:36:19,  1.55it/s]
 75%|███████▍  | 43017/57600 [7:33:21<2:32:21,  1.60it/s]
 75%|███████▍  | 43018/57600 [7:33:22<2:35:57,  1.56it/s]
 75%|███████▍  | 43019/57600 [7:33:23<2:37:25,  1.54it/s]
 75%|███████▍  | 43020/57600 [7:33:23<2:33:16,  1.59it/s]
                                                         
{'loss': 1.1015, 'learning_rate': 3.2860627177700344e-07, 'epoch': 474.83}

 75%|███████▍  | 43020/57600 [7:33:23<2:33:16,  1.59it/s]
 75%|███████▍  | 43021/57600 [7:33:24<2:38:13,  1.54it/s]
 75%|███████▍  | 43022/57600 [7:33:25<2:37:32,  1.54it/s]
 75%|███████▍  | 43023/57600 [7:33:25<2:32:22,  1.59it/s]
 75%|███████▍  | 43024/57600 [7:33:26<2:30:31,  1.61it/s]
 75%|███████▍  | 43025/57600 [7:33:26<2:30:49,  1.61it/s]
 75%|███████▍  | 43026/57600 [7:33:27<2:27:19,  1.65it/s]
 75%|███████▍  | 43027/57600 [7:33:28<2:34:47,  1.57it/s]
 75%|███████▍  | 43028/57600 [7:33:28<2:33:56,  1.58it/s]
 75%|███████▍  | 43029/57600 [7:33:29<2:31:31,  1.60it/s]
 75%|███████▍  | 43030/57600 [7:33:30<2:29:34,  1.62it/s]
 75%|███████▍  | 43031/57600 [7:33:30<2:28:12,  1.64it/s]
 75%|███████▍  | 43032/57600 [7:33:31<2:27:31,  1.65it/s]
 75%|███████▍  | 43033/57600 [7:33:31<2:30:54,  1.61it/s]
 75%|███████▍  | 43034/57600 [7:33:32<2:29:04,  1.63it/s]
 75%|███████▍  | 43035/57600 [7:33:33<2:30:43,  1.61it/s]
 75%|███████▍  | 43036/57600 [7:33:33<2:34:09,  1.57it/s]
 75%|███████▍  | 43037/57600 [7:33:34<2:32:14,  1.59it/s]
 75%|███████▍  | 43038/57600 [7:33:35<2:31:09,  1.61it/s]
 75%|███████▍  | 43039/57600 [7:33:35<2:28:39,  1.63it/s]
 75%|███████▍  | 43040/57600 [7:33:36<2:29:59,  1.62it/s]
                                                         
{'loss': 1.1511, 'learning_rate': 3.2829268292682925e-07, 'epoch': 475.06}

 75%|███████▍  | 43040/57600 [7:33:36<2:29:59,  1.62it/s]
 75%|███████▍  | 43041/57600 [7:33:36<2:29:06,  1.63it/s]
 75%|███████▍  | 43042/57600 [7:33:37<2:33:10,  1.58it/s]
 75%|███████▍  | 43043/57600 [7:33:38<2:30:19,  1.61it/s]
 75%|███████▍  | 43044/57600 [7:33:38<2:24:51,  1.67it/s]
 75%|███████▍  | 43045/57600 [7:33:39<2:26:11,  1.66it/s]
 75%|███████▍  | 43046/57600 [7:33:39<2:24:12,  1.68it/s]
 75%|███████▍  | 43047/57600 [7:33:40<2:27:49,  1.64it/s]
 75%|███████▍  | 43048/57600 [7:33:41<2:32:38,  1.59it/s]
 75%|███████▍  | 43049/57600 [7:33:41<2:36:39,  1.55it/s]
 75%|███████▍  | 43050/57600 [7:33:42<2:35:45,  1.56it/s]
 75%|███████▍  | 43051/57600 [7:33:43<2:34:40,  1.57it/s]
 75%|███████▍  | 43052/57600 [7:33:43<2:33:40,  1.58it/s]
 75%|███████▍  | 43053/57600 [7:33:44<2:40:39,  1.51it/s]
 75%|███████▍  | 43054/57600 [7:33:45<2:38:04,  1.53it/s]
 75%|███████▍  | 43055/57600 [7:33:45<2:35:13,  1.56it/s]
 75%|███████▍  | 43056/57600 [7:33:46<2:35:29,  1.56it/s]
 75%|███████▍  | 43057/57600 [7:33:47<2:38:40,  1.53it/s]
 75%|███████▍  | 43058/57600 [7:33:47<2:38:35,  1.53it/s]
 75%|███████▍  | 43059/57600 [7:33:48<2:33:07,  1.58it/s]
 75%|███████▍  | 43060/57600 [7:33:48<2:35:06,  1.56it/s]
                                                         
{'loss': 1.139, 'learning_rate': 3.2797909407665505e-07, 'epoch': 475.28}

 75%|███████▍  | 43060/57600 [7:33:48<2:35:06,  1.56it/s]
 75%|███████▍  | 43061/57600 [7:33:49<2:33:01,  1.58it/s]
 75%|███████▍  | 43062/57600 [7:33:50<2:33:02,  1.58it/s]
 75%|███████▍  | 43063/57600 [7:33:50<2:33:05,  1.58it/s]
 75%|███████▍  | 43064/57600 [7:33:51<2:31:07,  1.60it/s]
 75%|███████▍  | 43065/57600 [7:33:52<2:28:01,  1.64it/s]
 75%|███████▍  | 43066/57600 [7:33:52<2:25:20,  1.67it/s]
 75%|███████▍  | 43067/57600 [7:33:53<2:30:51,  1.61it/s]
 75%|███████▍  | 43068/57600 [7:33:53<2:33:11,  1.58it/s]
 75%|███████▍  | 43069/57600 [7:33:54<2:31:29,  1.60it/s]
 75%|███████▍  | 43070/57600 [7:33:55<2:33:55,  1.57it/s]
 75%|███████▍  | 43071/57600 [7:33:55<2:28:00,  1.64it/s]
 75%|███████▍  | 43072/57600 [7:33:56<2:27:05,  1.65it/s]
 75%|███████▍  | 43073/57600 [7:33:56<2:30:20,  1.61it/s]
 75%|███████▍  | 43074/57600 [7:33:57<2:30:12,  1.61it/s]
 75%|███████▍  | 43075/57600 [7:33:58<2:28:02,  1.64it/s]
 75%|███████▍  | 43076/57600 [7:33:58<2:25:06,  1.67it/s]
 75%|███████▍  | 43077/57600 [7:33:59<2:22:05,  1.70it/s]
 75%|███████▍  | 43078/57600 [7:33:59<2:22:51,  1.69it/s]
 75%|███████▍  | 43079/57600 [7:34:00<2:25:32,  1.66it/s]
 75%|███████▍  | 43080/57600 [7:34:01<2:28:38,  1.63it/s]
                                                         
{'loss': 1.1502, 'learning_rate': 3.276655052264808e-07, 'epoch': 475.5}

 75%|███████▍  | 43080/57600 [7:34:01<2:28:38,  1.63it/s]
 75%|███████▍  | 43081/57600 [7:34:01<2:33:45,  1.57it/s]
 75%|███████▍  | 43082/57600 [7:34:02<2:29:50,  1.61it/s]
 75%|███████▍  | 43083/57600 [7:34:03<2:32:45,  1.58it/s]
 75%|███████▍  | 43084/57600 [7:34:03<2:31:13,  1.60it/s]
 75%|███████▍  | 43085/57600 [7:34:04<2:30:00,  1.61it/s]
 75%|███████▍  | 43086/57600 [7:34:04<2:30:49,  1.60it/s]
 75%|███████▍  | 43087/57600 [7:34:05<2:27:51,  1.64it/s]
 75%|███████▍  | 43088/57600 [7:34:06<2:32:29,  1.59it/s]
 75%|███████▍  | 43089/57600 [7:34:06<2:39:10,  1.52it/s]
 75%|███████▍  | 43090/57600 [7:34:07<2:34:12,  1.57it/s]
 75%|███████▍  | 43091/57600 [7:34:08<2:33:58,  1.57it/s]
 75%|███████▍  | 43092/57600 [7:34:08<2:39:33,  1.52it/s]
 75%|███████▍  | 43093/57600 [7:34:09<2:38:49,  1.52it/s]
 75%|███████▍  | 43094/57600 [7:34:10<2:32:45,  1.58it/s]
 75%|███████▍  | 43095/57600 [7:34:10<2:31:55,  1.59it/s]
 75%|███████▍  | 43096/57600 [7:34:11<2:29:30,  1.62it/s]
 75%|███████▍  | 43097/57600 [7:34:11<2:29:18,  1.62it/s]
 75%|███████▍  | 43098/57600 [7:34:12<2:32:40,  1.58it/s]
 75%|███████▍  | 43099/57600 [7:34:13<2:31:21,  1.60it/s]
 75%|███████▍  | 43100/57600 [7:34:13<2:35:24,  1.55it/s]
                                                         
{'loss': 1.1129, 'learning_rate': 3.2735191637630666e-07, 'epoch': 475.72}

 75%|███████▍  | 43100/57600 [7:34:13<2:35:24,  1.55it/s]
 75%|███████▍  | 43101/57600 [7:34:14<2:32:13,  1.59it/s]
 75%|███████▍  | 43102/57600 [7:34:15<2:27:00,  1.64it/s]
 75%|███████▍  | 43103/57600 [7:34:15<2:28:40,  1.63it/s]
 75%|███████▍  | 43104/57600 [7:34:16<2:31:46,  1.59it/s]
 75%|███████▍  | 43105/57600 [7:34:16<2:30:30,  1.61it/s]
 75%|███████▍  | 43106/57600 [7:34:17<2:30:42,  1.60it/s]
 75%|███████▍  | 43107/57600 [7:34:18<2:38:44,  1.52it/s]
 75%|███████▍  | 43108/57600 [7:34:19<2:45:40,  1.46it/s]
 75%|███████▍  | 43109/57600 [7:34:19<2:40:37,  1.50it/s]
 75%|███████▍  | 43110/57600 [7:34:20<2:34:18,  1.56it/s]
 75%|███████▍  | 43111/57600 [7:34:20<2:34:09,  1.57it/s]
 75%|███████▍  | 43112/57600 [7:34:21<2:31:35,  1.59it/s]
 75%|███████▍  | 43113/57600 [7:34:22<2:32:51,  1.58it/s]
 75%|███████▍  | 43114/57600 [7:34:22<2:30:56,  1.60it/s]
 75%|███████▍  | 43115/57600 [7:34:23<2:29:23,  1.62it/s]
 75%|███████▍  | 43116/57600 [7:34:23<2:28:12,  1.63it/s]
 75%|███████▍  | 43117/57600 [7:34:24<2:29:41,  1.61it/s]
 75%|███████▍  | 43118/57600 [7:34:25<2:27:00,  1.64it/s]
 75%|███████▍  | 43119/57600 [7:34:25<2:25:26,  1.66it/s]
 75%|███████▍  | 43120/57600 [7:34:26<2:24:50,  1.67it/s]
                                                         
{'loss': 1.1405, 'learning_rate': 3.2703832752613236e-07, 'epoch': 475.94}

 75%|███████▍  | 43120/57600 [7:34:26<2:24:50,  1.67it/s]
 75%|███████▍  | 43121/57600 [7:34:27<2:29:54,  1.61it/s]
 75%|███████▍  | 43122/57600 [7:34:27<2:29:48,  1.61it/s]
 75%|███████▍  | 43123/57600 [7:34:28<2:36:00,  1.55it/s]
 75%|███████▍  | 43124/57600 [7:34:28<2:31:40,  1.59it/s]
 75%|███████▍  | 43125/57600 [7:34:29<2:31:43,  1.59it/s]
 75%|███████▍  | 43126/57600 [7:34:30<2:37:11,  1.53it/s]
 75%|███████▍  | 43127/57600 [7:34:30<2:30:55,  1.60it/s]
 75%|███████▍  | 43128/57600 [7:34:31<2:27:10,  1.64it/s]
 75%|███████▍  | 43129/57600 [7:34:32<2:26:08,  1.65it/s]
 75%|███████▍  | 43130/57600 [7:34:32<2:23:13,  1.68it/s]
 75%|███████▍  | 43131/57600 [7:34:33<2:24:37,  1.67it/s]
 75%|███████▍  | 43132/57600 [7:34:33<2:30:28,  1.60it/s]
 75%|███████▍  | 43133/57600 [7:34:34<2:35:12,  1.55it/s]
 75%|███████▍  | 43134/57600 [7:34:35<2:32:22,  1.58it/s]
 75%|███████▍  | 43135/57600 [7:34:35<2:36:41,  1.54it/s]
 75%|███████▍  | 43136/57600 [7:34:36<2:32:13,  1.58it/s]
 75%|███████▍  | 43137/57600 [7:34:37<2:34:59,  1.56it/s]
 75%|███████▍  | 43138/57600 [7:34:37<2:29:31,  1.61it/s]
 75%|███████▍  | 43139/57600 [7:34:38<2:26:45,  1.64it/s]
 75%|███████▍  | 43140/57600 [7:34:38<2:27:42,  1.63it/s]
                                                         
{'loss': 1.1517, 'learning_rate': 3.2672473867595816e-07, 'epoch': 476.16}

 75%|███████▍  | 43140/57600 [7:34:38<2:27:42,  1.63it/s]
 75%|███████▍  | 43141/57600 [7:34:39<2:33:22,  1.57it/s]
 75%|███████▍  | 43142/57600 [7:34:40<2:30:27,  1.60it/s]
 75%|███████▍  | 43143/57600 [7:34:40<2:32:03,  1.58it/s]
 75%|███████▍  | 43144/57600 [7:34:41<2:36:03,  1.54it/s]
 75%|███████▍  | 43145/57600 [7:34:42<2:31:54,  1.59it/s]
 75%|███████▍  | 43146/57600 [7:34:42<2:27:46,  1.63it/s]
 75%|███████▍  | 43147/57600 [7:34:43<2:27:02,  1.64it/s]
 75%|███████▍  | 43148/57600 [7:34:43<2:31:21,  1.59it/s]
 75%|███████▍  | 43149/57600 [7:34:44<2:32:00,  1.58it/s]
 75%|███████▍  | 43150/57600 [7:34:45<2:38:37,  1.52it/s]
 75%|███████▍  | 43151/57600 [7:34:45<2:33:34,  1.57it/s]
 75%|███████▍  | 43152/57600 [7:34:46<2:30:00,  1.61it/s]
 75%|███████▍  | 43153/57600 [7:34:47<2:37:00,  1.53it/s]
 75%|███████▍  | 43154/57600 [7:34:47<2:39:12,  1.51it/s]
 75%|███████▍  | 43155/57600 [7:34:48<2:30:23,  1.60it/s]
 75%|███████▍  | 43156/57600 [7:34:49<2:30:15,  1.60it/s]
 75%|███████▍  | 43157/57600 [7:34:49<2:33:42,  1.57it/s]
 75%|███████▍  | 43158/57600 [7:34:50<2:37:53,  1.52it/s]
 75%|███████▍  | 43159/57600 [7:34:51<2:41:38,  1.49it/s]
 75%|███████▍  | 43160/57600 [7:34:51<2:41:15,  1.49it/s]
                                                         
{'loss': 1.1224, 'learning_rate': 3.264111498257839e-07, 'epoch': 476.38}

 75%|███████▍  | 43160/57600 [7:34:51<2:41:15,  1.49it/s]
 75%|███████▍  | 43161/57600 [7:34:52<2:37:07,  1.53it/s]
 75%|███████▍  | 43162/57600 [7:34:53<2:33:31,  1.57it/s]
 75%|███████▍  | 43163/57600 [7:34:53<2:33:30,  1.57it/s]
 75%|███████▍  | 43164/57600 [7:34:54<2:32:52,  1.57it/s]
 75%|███████▍  | 43165/57600 [7:34:54<2:27:43,  1.63it/s]
 75%|███████▍  | 43166/57600 [7:34:55<2:32:29,  1.58it/s]
 75%|███████▍  | 43167/57600 [7:34:56<2:30:27,  1.60it/s]
 75%|███████▍  | 43168/57600 [7:34:56<2:30:25,  1.60it/s]
 75%|███████▍  | 43169/57600 [7:34:57<2:27:42,  1.63it/s]
 75%|███████▍  | 43170/57600 [7:34:58<2:30:53,  1.59it/s]
 75%|███████▍  | 43171/57600 [7:34:58<2:30:46,  1.59it/s]
 75%|███████▍  | 43172/57600 [7:34:59<2:33:14,  1.57it/s]
 75%|███████▍  | 43173/57600 [7:34:59<2:33:53,  1.56it/s]
 75%|███████▍  | 43174/57600 [7:35:00<2:32:13,  1.58it/s]
 75%|███████▍  | 43175/57600 [7:35:01<2:34:16,  1.56it/s]
 75%|███████▍  | 43176/57600 [7:35:01<2:29:54,  1.60it/s]
 75%|███████▍  | 43177/57600 [7:35:02<2:29:44,  1.61it/s]
 75%|███████▍  | 43178/57600 [7:35:03<2:30:35,  1.60it/s]
 75%|███████▍  | 43179/57600 [7:35:03<2:28:05,  1.62it/s]
 75%|███████▍  | 43180/57600 [7:35:04<2:27:51,  1.63it/s]
                                                         
{'loss': 1.1472, 'learning_rate': 3.260975609756098e-07, 'epoch': 476.6}

 75%|███████▍  | 43180/57600 [7:35:04<2:27:51,  1.63it/s]
 75%|███████▍  | 43181/57600 [7:35:04<2:29:28,  1.61it/s]
 75%|███████▍  | 43182/57600 [7:35:05<2:27:25,  1.63it/s]
 75%|███████▍  | 43183/57600 [7:35:06<2:27:36,  1.63it/s]
 75%|███████▍  | 43184/57600 [7:35:06<2:30:55,  1.59it/s]
 75%|███████▍  | 43185/57600 [7:35:07<2:32:34,  1.57it/s]
 75%|███████▍  | 43186/57600 [7:35:08<2:27:55,  1.62it/s]
 75%|███████▍  | 43187/57600 [7:35:08<2:24:16,  1.66it/s]
 75%|███████▍  | 43188/57600 [7:35:09<2:29:55,  1.60it/s]
 75%|███████▍  | 43189/57600 [7:35:09<2:26:02,  1.64it/s]
 75%|███████▍  | 43190/57600 [7:35:10<2:24:37,  1.66it/s]
 75%|███████▍  | 43191/57600 [7:35:11<2:25:44,  1.65it/s]
 75%|███████▍  | 43192/57600 [7:35:11<2:29:15,  1.61it/s]
 75%|███████▍  | 43193/57600 [7:35:12<2:32:15,  1.58it/s]
 75%|███████▍  | 43194/57600 [7:35:12<2:33:04,  1.57it/s]
 75%|███████▍  | 43195/57600 [7:35:13<2:31:58,  1.58it/s]
 75%|███████▍  | 43196/57600 [7:35:14<2:34:39,  1.55it/s]
 75%|███████▍  | 43197/57600 [7:35:14<2:32:06,  1.58it/s]
 75%|███████▍  | 43198/57600 [7:35:15<2:32:51,  1.57it/s]
 75%|███████▍  | 43199/57600 [7:35:16<2:35:23,  1.54it/s]
 75%|███████▌  | 43200/57600 [7:35:16<2:36:38,  1.53it/s]
                                                         
{'loss': 1.1355, 'learning_rate': 3.257839721254356e-07, 'epoch': 476.82}

 75%|███████▌  | 43200/57600 [7:35:16<2:36:38,  1.53it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 11.09it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.20it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.59it/s]

100%|██████████| 6/6 [00:01<00:00,  3.03it/s]{'score': 48.392857263226055, 'counts': [146, 93, 65, 47], 'totals': [213, 183, 154, 126], 'precisions': [68.54460093896714, 50.81967213114754, 42.20779220779221, 37.301587301587304], 'bp': 1.0, 'sys_len': 213, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 1.9725987911224365, 'eval_bleu': 48.3929, 'eval_gen_len': 8.5667, 'eval_runtime': 3.2649, 'eval_samples_per_second': 9.189, 'eval_steps_per_second': 1.838, 'epoch': 476.82}

 75%|███████▌  | 43200/57600 [7:35:20<2:36:38,  1.53it/s]

100%|██████████| 6/6 [00:03<00:00,  3.03it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 14:29:32,982 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 75%|███████▌  | 43201/57600 [7:35:40<30:36:18,  7.65s/it]
 75%|███████▌  | 43202/57600 [7:35:41<22:12:05,  5.55s/it]
 75%|███████▌  | 43203/57600 [7:35:42<16:21:47,  4.09s/it]
 75%|███████▌  | 43204/57600 [7:35:42<12:21:43,  3.09s/it]
 75%|███████▌  | 43205/57600 [7:35:43<9:35:48,  2.40s/it] 
 75%|███████▌  | 43206/57600 [7:35:44<7:38:28,  1.91s/it]
 75%|███████▌  | 43207/57600 [7:35:45<6:10:22,  1.54s/it]
 75%|███████▌  | 43208/57600 [7:35:45<5:06:29,  1.28s/it]
 75%|███████▌  | 43209/57600 [7:35:46<4:21:45,  1.09s/it]
 75%|███████▌  | 43210/57600 [7:35:47<3:50:28,  1.04it/s]
 75%|███████▌  | 43211/57600 [7:35:47<3:29:22,  1.15it/s]
 75%|███████▌  | 43212/57600 [7:35:48<3:15:58,  1.22it/s]
 75%|███████▌  | 43213/57600 [7:35:49<3:02:13,  1.32it/s]
 75%|███████▌  | 43214/57600 [7:35:49<2:56:10,  1.36it/s]
 75%|███████▌  | 43215/57600 [7:35:50<2:51:23,  1.40it/s]
 75%|███████▌  | 43216/57600 [7:35:51<2:46:12,  1.44it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 75%|███████▌  | 43217/57600 [7:35:51<2:49:51,  1.41it/s]
 75%|███████▌  | 43218/57600 [7:35:52<2:45:34,  1.45it/s]
 75%|███████▌  | 43219/57600 [7:35:53<2:48:04,  1.43it/s]
 75%|███████▌  | 43220/57600 [7:35:53<2:48:39,  1.42it/s]
                                                         
{'loss': 1.1215, 'learning_rate': 3.254703832752613e-07, 'epoch': 477.04}

 75%|███████▌  | 43220/57600 [7:35:53<2:48:39,  1.42it/s]
 75%|███████▌  | 43221/57600 [7:35:54<2:45:27,  1.45it/s]
 75%|███████▌  | 43222/57600 [7:35:55<2:39:45,  1.50it/s]
 75%|███████▌  | 43223/57600 [7:35:55<2:32:34,  1.57it/s]
 75%|███████▌  | 43224/57600 [7:35:56<2:36:07,  1.53it/s]
 75%|███████▌  | 43225/57600 [7:35:57<2:41:47,  1.48it/s]
 75%|███████▌  | 43226/57600 [7:35:57<2:44:36,  1.46it/s]
 75%|███████▌  | 43227/57600 [7:35:58<2:41:58,  1.48it/s]
 75%|███████▌  | 43228/57600 [7:35:59<2:44:09,  1.46it/s]
 75%|███████▌  | 43229/57600 [7:35:59<2:39:40,  1.50it/s]
 75%|███████▌  | 43230/57600 [7:36:00<2:37:34,  1.52it/s]
 75%|███████▌  | 43231/57600 [7:36:01<2:37:12,  1.52it/s]
 75%|███████▌  | 43232/57600 [7:36:01<2:41:15,  1.48it/s]
 75%|███████▌  | 43233/57600 [7:36:02<2:40:46,  1.49it/s]
 75%|███████▌  | 43234/57600 [7:36:03<2:39:41,  1.50it/s]
 75%|███████▌  | 43235/57600 [7:36:03<2:38:37,  1.51it/s]
 75%|███████▌  | 43236/57600 [7:36:04<2:38:16,  1.51it/s]
 75%|███████▌  | 43237/57600 [7:36:05<2:38:17,  1.51it/s]
 75%|███████▌  | 43238/57600 [7:36:05<2:35:04,  1.54it/s]
 75%|███████▌  | 43239/57600 [7:36:06<2:41:43,  1.48it/s]
 75%|███████▌  | 43240/57600 [7:36:07<2:38:15,  1.51it/s]
                                                         
{'loss': 1.0938, 'learning_rate': 3.2515679442508714e-07, 'epoch': 477.26}

 75%|███████▌  | 43240/57600 [7:36:07<2:38:15,  1.51it/s]
 75%|███████▌  | 43241/57600 [7:36:07<2:41:03,  1.49it/s]
 75%|███████▌  | 43242/57600 [7:36:08<2:41:24,  1.48it/s]
 75%|███████▌  | 43243/57600 [7:36:09<2:35:48,  1.54it/s]
 75%|███████▌  | 43244/57600 [7:36:09<2:36:10,  1.53it/s]
 75%|███████▌  | 43245/57600 [7:36:10<2:32:04,  1.57it/s]
 75%|███████▌  | 43246/57600 [7:36:11<2:28:57,  1.61it/s]
 75%|███████▌  | 43247/57600 [7:36:11<2:26:05,  1.64it/s]
 75%|███████▌  | 43248/57600 [7:36:12<2:26:45,  1.63it/s]
 75%|███████▌  | 43249/57600 [7:36:12<2:28:06,  1.61it/s]
 75%|███████▌  | 43250/57600 [7:36:13<2:27:23,  1.62it/s]
 75%|███████▌  | 43251/57600 [7:36:14<2:36:50,  1.52it/s]
 75%|███████▌  | 43252/57600 [7:36:14<2:36:00,  1.53it/s]
 75%|███████▌  | 43253/57600 [7:36:15<2:39:20,  1.50it/s]
 75%|███████▌  | 43254/57600 [7:36:16<2:36:16,  1.53it/s]
 75%|███████▌  | 43255/57600 [7:36:16<2:43:25,  1.46it/s]
 75%|███████▌  | 43256/57600 [7:36:17<2:44:07,  1.46it/s]
 75%|███████▌  | 43257/57600 [7:36:18<2:45:12,  1.45it/s]
 75%|███████▌  | 43258/57600 [7:36:19<2:51:52,  1.39it/s]
 75%|███████▌  | 43259/57600 [7:36:19<2:48:01,  1.42it/s]
 75%|███████▌  | 43260/57600 [7:36:20<2:44:07,  1.46it/s]
                                                         
{'loss': 1.1255, 'learning_rate': 3.248432055749129e-07, 'epoch': 477.48}

 75%|███████▌  | 43260/57600 [7:36:20<2:44:07,  1.46it/s]
 75%|███████▌  | 43261/57600 [7:36:21<2:42:17,  1.47it/s]
 75%|███████▌  | 43262/57600 [7:36:21<2:39:36,  1.50it/s]
 75%|███████▌  | 43263/57600 [7:36:22<2:37:12,  1.52it/s]
 75%|███████▌  | 43264/57600 [7:36:23<2:37:41,  1.52it/s]
 75%|███████▌  | 43265/57600 [7:36:23<2:36:19,  1.53it/s]
 75%|███████▌  | 43266/57600 [7:36:24<2:38:21,  1.51it/s]
 75%|███████▌  | 43267/57600 [7:36:24<2:36:34,  1.53it/s]
 75%|███████▌  | 43268/57600 [7:36:25<2:34:37,  1.54it/s]
 75%|███████▌  | 43269/57600 [7:36:26<2:35:15,  1.54it/s]
 75%|███████▌  | 43270/57600 [7:36:26<2:32:50,  1.56it/s]
 75%|███████▌  | 43271/57600 [7:36:27<2:34:19,  1.55it/s]
 75%|███████▌  | 43272/57600 [7:36:28<2:33:53,  1.55it/s]
 75%|███████▌  | 43273/57600 [7:36:28<2:37:13,  1.52it/s]
 75%|███████▌  | 43274/57600 [7:36:29<2:33:18,  1.56it/s]
 75%|███████▌  | 43275/57600 [7:36:30<2:27:58,  1.61it/s]
 75%|███████▌  | 43276/57600 [7:36:30<2:29:24,  1.60it/s]
 75%|███████▌  | 43277/57600 [7:36:31<2:32:20,  1.57it/s]
 75%|███████▌  | 43278/57600 [7:36:31<2:29:47,  1.59it/s]
 75%|███████▌  | 43279/57600 [7:36:32<2:29:20,  1.60it/s]
 75%|███████▌  | 43280/57600 [7:36:33<2:29:24,  1.60it/s]
                                                         
{'loss': 1.1423, 'learning_rate': 3.2452961672473864e-07, 'epoch': 477.7}

 75%|███████▌  | 43280/57600 [7:36:33<2:29:24,  1.60it/s]
 75%|███████▌  | 43281/57600 [7:36:33<2:28:42,  1.60it/s]
 75%|███████▌  | 43282/57600 [7:36:34<2:26:40,  1.63it/s]
 75%|███████▌  | 43283/57600 [7:36:35<2:24:49,  1.65it/s]
 75%|███████▌  | 43284/57600 [7:36:35<2:25:06,  1.64it/s]
 75%|███████▌  | 43285/57600 [7:36:36<2:27:26,  1.62it/s]
 75%|███████▌  | 43286/57600 [7:36:36<2:27:49,  1.61it/s]
 75%|███████▌  | 43287/57600 [7:36:37<2:28:49,  1.60it/s]
 75%|███████▌  | 43288/57600 [7:36:38<2:27:57,  1.61it/s]
 75%|███████▌  | 43289/57600 [7:36:38<2:31:36,  1.57it/s]
 75%|███████▌  | 43290/57600 [7:36:39<2:30:22,  1.59it/s]
 75%|███████▌  | 43291/57600 [7:36:40<2:28:19,  1.61it/s]
 75%|███████▌  | 43292/57600 [7:36:40<2:32:44,  1.56it/s]
 75%|███████▌  | 43293/57600 [7:36:41<2:38:13,  1.51it/s]
 75%|███████▌  | 43294/57600 [7:36:42<2:33:35,  1.55it/s]
 75%|███████▌  | 43295/57600 [7:36:42<2:38:09,  1.51it/s]
 75%|███████▌  | 43296/57600 [7:36:43<2:41:58,  1.47it/s]
 75%|███████▌  | 43297/57600 [7:36:44<2:36:39,  1.52it/s]
 75%|███████▌  | 43298/57600 [7:36:44<2:34:30,  1.54it/s]
 75%|███████▌  | 43299/57600 [7:36:45<2:36:34,  1.52it/s]
 75%|███████▌  | 43300/57600 [7:36:46<2:35:49,  1.53it/s]
                                                         
{'loss': 1.1531, 'learning_rate': 3.242160278745644e-07, 'epoch': 477.92}

 75%|███████▌  | 43300/57600 [7:36:46<2:35:49,  1.53it/s]
 75%|███████▌  | 43301/57600 [7:36:46<2:39:18,  1.50it/s]
 75%|███████▌  | 43302/57600 [7:36:47<2:38:50,  1.50it/s]
 75%|███████▌  | 43303/57600 [7:36:48<2:36:48,  1.52it/s]
 75%|███████▌  | 43304/57600 [7:36:48<2:34:47,  1.54it/s]
 75%|███████▌  | 43305/57600 [7:36:49<2:32:52,  1.56it/s]
 75%|███████▌  | 43306/57600 [7:36:49<2:31:30,  1.57it/s]
 75%|███████▌  | 43307/57600 [7:36:50<2:43:23,  1.46it/s]
 75%|███████▌  | 43308/57600 [7:36:51<2:46:54,  1.43it/s]
 75%|███████▌  | 43309/57600 [7:36:52<2:45:47,  1.44it/s]
 75%|███████▌  | 43310/57600 [7:36:52<2:44:29,  1.45it/s]
 75%|███████▌  | 43311/57600 [7:36:53<2:48:43,  1.41it/s]
 75%|███████▌  | 43312/57600 [7:36:54<2:47:38,  1.42it/s]
 75%|███████▌  | 43313/57600 [7:36:54<2:40:07,  1.49it/s]
 75%|███████▌  | 43314/57600 [7:36:55<2:38:43,  1.50it/s]
 75%|███████▌  | 43315/57600 [7:36:56<2:36:07,  1.52it/s]
 75%|███████▌  | 43316/57600 [7:36:56<2:46:00,  1.43it/s]
 75%|███████▌  | 43317/57600 [7:36:57<2:46:27,  1.43it/s]
 75%|███████▌  | 43318/57600 [7:36:58<2:40:45,  1.48it/s]
 75%|███████▌  | 43319/57600 [7:36:58<2:45:10,  1.44it/s]
 75%|███████▌  | 43320/57600 [7:36:59<2:43:33,  1.46it/s]
                                                         
{'loss': 1.1217, 'learning_rate': 3.2390243902439025e-07, 'epoch': 478.15}

 75%|███████▌  | 43320/57600 [7:36:59<2:43:33,  1.46it/s]
 75%|███████▌  | 43321/57600 [7:37:00<2:40:14,  1.49it/s]
 75%|███████▌  | 43322/57600 [7:37:00<2:34:58,  1.54it/s]
 75%|███████▌  | 43323/57600 [7:37:01<2:36:55,  1.52it/s]
 75%|███████▌  | 43324/57600 [7:37:02<2:36:36,  1.52it/s]
 75%|███████▌  | 43325/57600 [7:37:02<2:34:22,  1.54it/s]
 75%|███████▌  | 43326/57600 [7:37:03<2:35:37,  1.53it/s]
 75%|███████▌  | 43327/57600 [7:37:04<2:32:50,  1.56it/s]
 75%|███████▌  | 43328/57600 [7:37:04<2:32:08,  1.56it/s]
 75%|███████▌  | 43329/57600 [7:37:05<2:31:37,  1.57it/s]
 75%|███████▌  | 43330/57600 [7:37:06<2:31:14,  1.57it/s]
 75%|███████▌  | 43331/57600 [7:37:06<2:32:41,  1.56it/s]
 75%|███████▌  | 43332/57600 [7:37:07<2:32:16,  1.56it/s]
 75%|███████▌  | 43333/57600 [7:37:07<2:35:26,  1.53it/s]
 75%|███████▌  | 43334/57600 [7:37:08<2:29:12,  1.59it/s]
 75%|███████▌  | 43335/57600 [7:37:09<2:30:35,  1.58it/s]
 75%|███████▌  | 43336/57600 [7:37:09<2:30:22,  1.58it/s]
 75%|███████▌  | 43337/57600 [7:37:10<2:28:40,  1.60it/s]
 75%|███████▌  | 43338/57600 [7:37:11<2:30:18,  1.58it/s]
 75%|███████▌  | 43339/57600 [7:37:11<2:31:50,  1.57it/s]
 75%|███████▌  | 43340/57600 [7:37:12<2:34:16,  1.54it/s]
                                                         
{'loss': 1.1308, 'learning_rate': 3.2358885017421605e-07, 'epoch': 478.37}

 75%|███████▌  | 43340/57600 [7:37:12<2:34:16,  1.54it/s]
 75%|███████▌  | 43341/57600 [7:37:13<2:38:41,  1.50it/s]
 75%|███████▌  | 43342/57600 [7:37:13<2:37:43,  1.51it/s]
 75%|███████▌  | 43343/57600 [7:37:14<2:31:59,  1.56it/s]
 75%|███████▌  | 43344/57600 [7:37:15<2:34:24,  1.54it/s]
 75%|███████▌  | 43345/57600 [7:37:15<2:37:12,  1.51it/s]
 75%|███████▌  | 43346/57600 [7:37:16<2:37:47,  1.51it/s]
 75%|███████▌  | 43347/57600 [7:37:17<2:43:20,  1.45it/s]
 75%|███████▌  | 43348/57600 [7:37:17<2:40:49,  1.48it/s]
 75%|███████▌  | 43349/57600 [7:37:18<2:39:06,  1.49it/s]
 75%|███████▌  | 43350/57600 [7:37:19<2:34:52,  1.53it/s]
 75%|███████▌  | 43351/57600 [7:37:19<2:31:04,  1.57it/s]
 75%|███████▌  | 43352/57600 [7:37:20<2:33:23,  1.55it/s]
 75%|███████▌  | 43353/57600 [7:37:20<2:30:57,  1.57it/s]
 75%|███████▌  | 43354/57600 [7:37:21<2:36:01,  1.52it/s]
 75%|███████▌  | 43355/57600 [7:37:22<2:35:14,  1.53it/s]
 75%|███████▌  | 43356/57600 [7:37:22<2:34:33,  1.54it/s]
 75%|███████▌  | 43357/57600 [7:37:23<2:32:09,  1.56it/s]
 75%|███████▌  | 43358/57600 [7:37:24<2:32:03,  1.56it/s]
 75%|███████▌  | 43359/57600 [7:37:24<2:37:29,  1.51it/s]
 75%|███████▌  | 43360/57600 [7:37:25<2:41:57,  1.47it/s]
                                                         
{'loss': 1.1318, 'learning_rate': 3.2327526132404175e-07, 'epoch': 478.59}

 75%|███████▌  | 43360/57600 [7:37:25<2:41:57,  1.47it/s]
 75%|███████▌  | 43361/57600 [7:37:26<2:42:38,  1.46it/s]
 75%|███████▌  | 43362/57600 [7:37:26<2:36:56,  1.51it/s]
 75%|███████▌  | 43363/57600 [7:37:27<2:44:43,  1.44it/s]
 75%|███████▌  | 43364/57600 [7:37:28<2:53:01,  1.37it/s]
 75%|███████▌  | 43365/57600 [7:37:29<2:50:55,  1.39it/s]
 75%|███████▌  | 43366/57600 [7:37:29<2:40:58,  1.47it/s]
 75%|███████▌  | 43367/57600 [7:37:30<2:38:59,  1.49it/s]
 75%|███████▌  | 43368/57600 [7:37:31<2:33:34,  1.54it/s]
 75%|███████▌  | 43369/57600 [7:37:31<2:33:40,  1.54it/s]
 75%|███████▌  | 43370/57600 [7:37:32<2:34:51,  1.53it/s]
 75%|███████▌  | 43371/57600 [7:37:33<2:34:19,  1.54it/s]
 75%|███████▌  | 43372/57600 [7:37:33<2:31:23,  1.57it/s]
 75%|███████▌  | 43373/57600 [7:37:34<2:39:33,  1.49it/s]
 75%|███████▌  | 43374/57600 [7:37:35<2:37:47,  1.50it/s]
 75%|███████▌  | 43375/57600 [7:37:35<2:44:46,  1.44it/s]
 75%|███████▌  | 43376/57600 [7:37:36<2:46:59,  1.42it/s]
 75%|███████▌  | 43377/57600 [7:37:37<2:45:40,  1.43it/s]
 75%|███████▌  | 43378/57600 [7:37:37<2:42:49,  1.46it/s]
 75%|███████▌  | 43379/57600 [7:37:38<2:40:19,  1.48it/s]
 75%|███████▌  | 43380/57600 [7:37:39<2:36:08,  1.52it/s]
                                                         
{'loss': 1.1465, 'learning_rate': 3.229616724738676e-07, 'epoch': 478.81}

 75%|███████▌  | 43380/57600 [7:37:39<2:36:08,  1.52it/s]
 75%|███████▌  | 43381/57600 [7:37:39<2:34:12,  1.54it/s]
 75%|███████▌  | 43382/57600 [7:37:40<2:35:49,  1.52it/s]
 75%|███████▌  | 43383/57600 [7:37:41<2:35:28,  1.52it/s]
 75%|███████▌  | 43384/57600 [7:37:41<2:38:23,  1.50it/s]
 75%|███████▌  | 43385/57600 [7:37:42<2:38:28,  1.49it/s]
 75%|███████▌  | 43386/57600 [7:37:43<2:42:50,  1.45it/s]
 75%|███████▌  | 43387/57600 [7:37:43<2:47:22,  1.42it/s]
 75%|███████▌  | 43388/57600 [7:37:44<2:41:40,  1.47it/s]
 75%|███████▌  | 43389/57600 [7:37:45<2:36:41,  1.51it/s]
 75%|███████▌  | 43390/57600 [7:37:45<2:40:53,  1.47it/s]
 75%|███████▌  | 43391/57600 [7:37:46<2:37:50,  1.50it/s]
 75%|███████▌  | 43392/57600 [7:37:47<2:36:50,  1.51it/s]
 75%|███████▌  | 43393/57600 [7:37:47<2:40:18,  1.48it/s]
 75%|███████▌  | 43394/57600 [7:37:48<2:36:57,  1.51it/s]
 75%|███████▌  | 43395/57600 [7:37:49<2:31:55,  1.56it/s]
 75%|███████▌  | 43396/57600 [7:37:49<2:28:12,  1.60it/s]
 75%|███████▌  | 43397/57600 [7:37:50<2:30:27,  1.57it/s]
 75%|███████▌  | 43398/57600 [7:37:51<2:39:21,  1.49it/s]
 75%|███████▌  | 43399/57600 [7:37:51<2:32:16,  1.55it/s]
 75%|███████▌  | 43400/57600 [7:37:52<2:41:29,  1.47it/s]
                                                         
{'loss': 1.1182, 'learning_rate': 3.226480836236934e-07, 'epoch': 479.03}

 75%|███████▌  | 43400/57600 [7:37:52<2:41:29,  1.47it/s]
 75%|███████▌  | 43401/57600 [7:37:53<2:35:50,  1.52it/s]
 75%|███████▌  | 43402/57600 [7:37:53<2:35:41,  1.52it/s]
 75%|███████▌  | 43403/57600 [7:37:54<2:40:54,  1.47it/s]
 75%|███████▌  | 43404/57600 [7:37:55<2:40:25,  1.47it/s]
 75%|███████▌  | 43405/57600 [7:37:55<2:37:47,  1.50it/s]
 75%|███████▌  | 43406/57600 [7:37:56<2:42:01,  1.46it/s]
 75%|███████▌  | 43407/57600 [7:37:57<2:35:09,  1.52it/s]
 75%|███████▌  | 43408/57600 [7:37:57<2:32:20,  1.55it/s]
 75%|███████▌  | 43409/57600 [7:37:58<2:32:52,  1.55it/s]
 75%|███████▌  | 43410/57600 [7:37:58<2:32:03,  1.56it/s]
 75%|███████▌  | 43411/57600 [7:37:59<2:37:40,  1.50it/s]
 75%|███████▌  | 43412/57600 [7:38:00<2:42:12,  1.46it/s]
 75%|███████▌  | 43413/57600 [7:38:01<2:35:37,  1.52it/s]
 75%|███████▌  | 43414/57600 [7:38:01<2:34:43,  1.53it/s]
 75%|███████▌  | 43415/57600 [7:38:02<2:32:46,  1.55it/s]
 75%|███████▌  | 43416/57600 [7:38:02<2:32:47,  1.55it/s]
 75%|███████▌  | 43417/57600 [7:38:03<2:27:51,  1.60it/s]
 75%|███████▌  | 43418/57600 [7:38:04<2:29:02,  1.59it/s]
 75%|███████▌  | 43419/57600 [7:38:04<2:28:33,  1.59it/s]
 75%|███████▌  | 43420/57600 [7:38:05<2:26:10,  1.62it/s]
                                                         
{'loss': 1.106, 'learning_rate': 3.2233449477351917e-07, 'epoch': 479.25}

 75%|███████▌  | 43420/57600 [7:38:05<2:26:10,  1.62it/s]
 75%|███████▌  | 43421/57600 [7:38:06<2:25:31,  1.62it/s]
 75%|███████▌  | 43422/57600 [7:38:06<2:25:19,  1.63it/s]
 75%|███████▌  | 43423/57600 [7:38:07<2:25:20,  1.63it/s]
 75%|███████▌  | 43424/57600 [7:38:07<2:25:56,  1.62it/s]
 75%|███████▌  | 43425/57600 [7:38:08<2:23:32,  1.65it/s]
 75%|███████▌  | 43426/57600 [7:38:09<2:22:21,  1.66it/s]
 75%|███████▌  | 43427/57600 [7:38:09<2:25:53,  1.62it/s]
 75%|███████▌  | 43428/57600 [7:38:10<2:22:17,  1.66it/s]
 75%|███████▌  | 43429/57600 [7:38:10<2:21:59,  1.66it/s]
 75%|███████▌  | 43430/57600 [7:38:11<2:26:00,  1.62it/s]
 75%|███████▌  | 43431/57600 [7:38:12<2:26:23,  1.61it/s]
 75%|███████▌  | 43432/57600 [7:38:12<2:26:14,  1.61it/s]
 75%|███████▌  | 43433/57600 [7:38:13<2:26:33,  1.61it/s]
 75%|███████▌  | 43434/57600 [7:38:13<2:26:44,  1.61it/s]
 75%|███████▌  | 43435/57600 [7:38:14<2:26:12,  1.61it/s]
 75%|███████▌  | 43436/57600 [7:38:15<2:26:55,  1.61it/s]
 75%|███████▌  | 43437/57600 [7:38:15<2:25:48,  1.62it/s]
 75%|███████▌  | 43438/57600 [7:38:16<2:25:07,  1.63it/s]
 75%|███████▌  | 43439/57600 [7:38:17<2:25:19,  1.62it/s]
 75%|███████▌  | 43440/57600 [7:38:17<2:27:24,  1.60it/s]
                                                         
{'loss': 1.1445, 'learning_rate': 3.2202090592334487e-07, 'epoch': 479.47}

 75%|███████▌  | 43440/57600 [7:38:17<2:27:24,  1.60it/s]
 75%|███████▌  | 43441/57600 [7:38:18<2:23:54,  1.64it/s]
 75%|███████▌  | 43442/57600 [7:38:18<2:21:37,  1.67it/s]
 75%|███████▌  | 43443/57600 [7:38:19<2:26:18,  1.61it/s]
 75%|███████▌  | 43444/57600 [7:38:20<2:24:58,  1.63it/s]
 75%|███████▌  | 43445/57600 [7:38:20<2:27:07,  1.60it/s]
 75%|███████▌  | 43446/57600 [7:38:21<2:29:47,  1.57it/s]
 75%|███████▌  | 43447/57600 [7:38:22<2:30:46,  1.56it/s]
 75%|███████▌  | 43448/57600 [7:38:22<2:31:17,  1.56it/s]
 75%|███████▌  | 43449/57600 [7:38:23<2:29:47,  1.57it/s]
 75%|███████▌  | 43450/57600 [7:38:23<2:27:39,  1.60it/s]
 75%|███████▌  | 43451/57600 [7:38:24<2:31:37,  1.56it/s]
 75%|███████▌  | 43452/57600 [7:38:25<2:30:43,  1.56it/s]
 75%|███████▌  | 43453/57600 [7:38:25<2:25:47,  1.62it/s]
 75%|███████▌  | 43454/57600 [7:38:26<2:29:26,  1.58it/s]
 75%|███████▌  | 43455/57600 [7:38:27<2:33:50,  1.53it/s]
 75%|███████▌  | 43456/57600 [7:38:27<2:32:42,  1.54it/s]
 75%|███████▌  | 43457/57600 [7:38:28<2:30:57,  1.56it/s]
 75%|███████▌  | 43458/57600 [7:38:29<2:32:43,  1.54it/s]
 75%|███████▌  | 43459/57600 [7:38:29<2:35:41,  1.51it/s]
 75%|███████▌  | 43460/57600 [7:38:30<2:27:12,  1.60it/s]
                                                         
{'loss': 1.1517, 'learning_rate': 3.217073170731707e-07, 'epoch': 479.69}

 75%|███████▌  | 43460/57600 [7:38:30<2:27:12,  1.60it/s]
 75%|███████▌  | 43461/57600 [7:38:31<2:31:22,  1.56it/s]
 75%|███████▌  | 43462/57600 [7:38:31<2:29:41,  1.57it/s]
 75%|███████▌  | 43463/57600 [7:38:32<2:30:38,  1.56it/s]
 75%|███████▌  | 43464/57600 [7:38:32<2:26:55,  1.60it/s]
 75%|███████▌  | 43465/57600 [7:38:33<2:24:36,  1.63it/s]
 75%|███████▌  | 43466/57600 [7:38:34<2:23:40,  1.64it/s]
 75%|███████▌  | 43467/57600 [7:38:34<2:27:54,  1.59it/s]
 75%|███████▌  | 43468/57600 [7:38:35<2:29:44,  1.57it/s]
 75%|███████▌  | 43469/57600 [7:38:36<2:29:36,  1.57it/s]
 75%|███████▌  | 43470/57600 [7:38:36<2:31:49,  1.55it/s]
 75%|███████▌  | 43471/57600 [7:38:37<2:28:18,  1.59it/s]
 75%|███████▌  | 43472/57600 [7:38:37<2:24:30,  1.63it/s]
 75%|███████▌  | 43473/57600 [7:38:38<2:23:03,  1.65it/s]
 75%|███████▌  | 43474/57600 [7:38:39<2:23:43,  1.64it/s]
 75%|███████▌  | 43475/57600 [7:38:39<2:22:24,  1.65it/s]
 75%|███████▌  | 43476/57600 [7:38:40<2:22:30,  1.65it/s]
 75%|███████▌  | 43477/57600 [7:38:40<2:21:09,  1.67it/s]
 75%|███████▌  | 43478/57600 [7:38:41<2:20:48,  1.67it/s]
 75%|███████▌  | 43479/57600 [7:38:42<2:23:28,  1.64it/s]
 75%|███████▌  | 43480/57600 [7:38:42<2:24:56,  1.62it/s]
                                                         
{'loss': 1.1624, 'learning_rate': 3.2139372822299653e-07, 'epoch': 479.91}

 75%|███████▌  | 43480/57600 [7:38:42<2:24:56,  1.62it/s]
 75%|███████▌  | 43481/57600 [7:38:43<2:21:02,  1.67it/s]
 75%|███████▌  | 43482/57600 [7:38:43<2:22:42,  1.65it/s]
 75%|███████▌  | 43483/57600 [7:38:44<2:27:26,  1.60it/s]
 75%|███████▌  | 43484/57600 [7:38:45<2:28:23,  1.59it/s]
 75%|███████▌  | 43485/57600 [7:38:45<2:36:14,  1.51it/s]
 75%|███████▌  | 43486/57600 [7:38:46<2:38:32,  1.48it/s]
 75%|███████▌  | 43487/57600 [7:38:47<2:34:04,  1.53it/s]
 76%|███████▌  | 43488/57600 [7:38:47<2:34:34,  1.52it/s]
 76%|███████▌  | 43489/57600 [7:38:48<2:34:40,  1.52it/s]
 76%|███████▌  | 43490/57600 [7:38:49<2:32:14,  1.54it/s]
 76%|███████▌  | 43491/57600 [7:38:49<2:37:17,  1.50it/s]
 76%|███████▌  | 43492/57600 [7:38:50<2:39:23,  1.48it/s]
 76%|███████▌  | 43493/57600 [7:38:51<2:30:39,  1.56it/s]
 76%|███████▌  | 43494/57600 [7:38:51<2:31:46,  1.55it/s]
 76%|███████▌  | 43495/57600 [7:38:52<2:27:35,  1.59it/s]
 76%|███████▌  | 43496/57600 [7:38:53<2:28:58,  1.58it/s]
 76%|███████▌  | 43497/57600 [7:38:53<2:24:58,  1.62it/s]
 76%|███████▌  | 43498/57600 [7:38:54<2:24:50,  1.62it/s]
 76%|███████▌  | 43499/57600 [7:38:54<2:28:13,  1.59it/s]
 76%|███████▌  | 43500/57600 [7:38:55<2:25:03,  1.62it/s]
                                                         
{'loss': 1.1148, 'learning_rate': 3.2108013937282223e-07, 'epoch': 480.13}

 76%|███████▌  | 43500/57600 [7:38:55<2:25:03,  1.62it/s]
 76%|███████▌  | 43501/57600 [7:38:56<2:25:20,  1.62it/s]
 76%|███████▌  | 43502/57600 [7:38:56<2:24:07,  1.63it/s]
 76%|███████▌  | 43503/57600 [7:38:57<2:25:59,  1.61it/s]
 76%|███████▌  | 43504/57600 [7:38:58<2:26:18,  1.61it/s]
 76%|███████▌  | 43505/57600 [7:38:58<2:25:58,  1.61it/s]
 76%|███████▌  | 43506/57600 [7:38:59<2:27:59,  1.59it/s]
 76%|███████▌  | 43507/57600 [7:38:59<2:30:06,  1.56it/s]
 76%|███████▌  | 43508/57600 [7:39:00<2:31:44,  1.55it/s]
 76%|███████▌  | 43509/57600 [7:39:01<2:27:48,  1.59it/s]
 76%|███████▌  | 43510/57600 [7:39:01<2:23:38,  1.63it/s]
 76%|███████▌  | 43511/57600 [7:39:02<2:29:43,  1.57it/s]
 76%|███████▌  | 43512/57600 [7:39:03<2:32:30,  1.54it/s]
 76%|███████▌  | 43513/57600 [7:39:03<2:26:11,  1.61it/s]
 76%|███████▌  | 43514/57600 [7:39:04<2:23:16,  1.64it/s]
 76%|███████▌  | 43515/57600 [7:39:04<2:23:15,  1.64it/s]
 76%|███████▌  | 43516/57600 [7:39:05<2:25:06,  1.62it/s]
 76%|███████▌  | 43517/57600 [7:39:06<2:30:25,  1.56it/s]
 76%|███████▌  | 43518/57600 [7:39:06<2:34:56,  1.51it/s]
 76%|███████▌  | 43519/57600 [7:39:07<2:32:49,  1.54it/s]
 76%|███████▌  | 43520/57600 [7:39:08<2:30:22,  1.56it/s]
                                                         
{'loss': 1.1493, 'learning_rate': 3.207665505226481e-07, 'epoch': 480.35}

 76%|███████▌  | 43520/57600 [7:39:08<2:30:22,  1.56it/s]
 76%|███████▌  | 43521/57600 [7:39:08<2:31:03,  1.55it/s]
 76%|███████▌  | 43522/57600 [7:39:09<2:29:57,  1.56it/s]
 76%|███████▌  | 43523/57600 [7:39:10<2:35:42,  1.51it/s]
 76%|███████▌  | 43524/57600 [7:39:10<2:35:04,  1.51it/s]
 76%|███████▌  | 43525/57600 [7:39:11<2:36:02,  1.50it/s]
 76%|███████▌  | 43526/57600 [7:39:12<2:40:00,  1.47it/s]
 76%|███████▌  | 43527/57600 [7:39:12<2:33:50,  1.52it/s]
 76%|███████▌  | 43528/57600 [7:39:13<2:34:01,  1.52it/s]
 76%|███████▌  | 43529/57600 [7:39:14<2:34:26,  1.52it/s]
 76%|███████▌  | 43530/57600 [7:39:14<2:28:46,  1.58it/s]
 76%|███████▌  | 43531/57600 [7:39:15<2:25:18,  1.61it/s]
 76%|███████▌  | 43532/57600 [7:39:15<2:22:14,  1.65it/s]
 76%|███████▌  | 43533/57600 [7:39:16<2:23:14,  1.64it/s]
 76%|███████▌  | 43534/57600 [7:39:17<2:21:56,  1.65it/s]
 76%|███████▌  | 43535/57600 [7:39:17<2:22:00,  1.65it/s]
 76%|███████▌  | 43536/57600 [7:39:18<2:26:08,  1.60it/s]
 76%|███████▌  | 43537/57600 [7:39:18<2:23:31,  1.63it/s]
 76%|███████▌  | 43538/57600 [7:39:19<2:21:31,  1.66it/s]
 76%|███████▌  | 43539/57600 [7:39:20<2:19:53,  1.68it/s]
 76%|███████▌  | 43540/57600 [7:39:20<2:21:00,  1.66it/s]
                                                         
{'loss': 1.1442, 'learning_rate': 3.2045296167247384e-07, 'epoch': 480.57}

 76%|███████▌  | 43540/57600 [7:39:20<2:21:00,  1.66it/s]
 76%|███████▌  | 43541/57600 [7:39:21<2:25:30,  1.61it/s]
 76%|███████▌  | 43542/57600 [7:39:22<2:23:28,  1.63it/s]
 76%|███████▌  | 43543/57600 [7:39:22<2:24:27,  1.62it/s]
 76%|███████▌  | 43544/57600 [7:39:23<2:23:19,  1.63it/s]
 76%|███████▌  | 43545/57600 [7:39:23<2:24:02,  1.63it/s]
 76%|███████▌  | 43546/57600 [7:39:24<2:22:01,  1.65it/s]
 76%|███████▌  | 43547/57600 [7:39:25<2:20:43,  1.66it/s]
 76%|███████▌  | 43548/57600 [7:39:25<2:22:07,  1.65it/s]
 76%|███████▌  | 43549/57600 [7:39:26<2:21:41,  1.65it/s]
 76%|███████▌  | 43550/57600 [7:39:26<2:20:50,  1.66it/s]
 76%|███████▌  | 43551/57600 [7:39:27<2:18:25,  1.69it/s]
 76%|███████▌  | 43552/57600 [7:39:28<2:23:09,  1.64it/s]
 76%|███████▌  | 43553/57600 [7:39:28<2:25:45,  1.61it/s]
 76%|███████▌  | 43554/57600 [7:39:29<2:25:00,  1.61it/s]
 76%|███████▌  | 43555/57600 [7:39:30<2:30:09,  1.56it/s]
 76%|███████▌  | 43556/57600 [7:39:30<2:25:32,  1.61it/s]
 76%|███████▌  | 43557/57600 [7:39:31<2:25:27,  1.61it/s]
 76%|███████▌  | 43558/57600 [7:39:31<2:25:21,  1.61it/s]
 76%|███████▌  | 43559/57600 [7:39:32<2:25:28,  1.61it/s]
 76%|███████▌  | 43560/57600 [7:39:33<2:26:11,  1.60it/s]
                                                         
{'loss': 1.1218, 'learning_rate': 3.2013937282229964e-07, 'epoch': 480.79}

 76%|███████▌  | 43560/57600 [7:39:33<2:26:11,  1.60it/s]
 76%|███████▌  | 43561/57600 [7:39:33<2:26:57,  1.59it/s]
 76%|███████▌  | 43562/57600 [7:39:34<2:28:24,  1.58it/s]
 76%|███████▌  | 43563/57600 [7:39:34<2:25:56,  1.60it/s]
 76%|███████▌  | 43564/57600 [7:39:35<2:28:11,  1.58it/s]
 76%|███████▌  | 43565/57600 [7:39:36<2:31:18,  1.55it/s]
 76%|███████▌  | 43566/57600 [7:39:36<2:26:29,  1.60it/s]
 76%|███████▌  | 43567/57600 [7:39:37<2:27:27,  1.59it/s]
 76%|███████▌  | 43568/57600 [7:39:38<2:23:57,  1.62it/s]
 76%|███████▌  | 43569/57600 [7:39:38<2:23:04,  1.63it/s]
 76%|███████▌  | 43570/57600 [7:39:39<2:24:51,  1.61it/s]
 76%|███████▌  | 43571/57600 [7:39:39<2:24:16,  1.62it/s]
 76%|███████▌  | 43572/57600 [7:39:40<2:21:06,  1.66it/s]
 76%|███████▌  | 43573/57600 [7:39:41<2:23:05,  1.63it/s]
 76%|███████▌  | 43574/57600 [7:39:41<2:25:07,  1.61it/s]
 76%|███████▌  | 43575/57600 [7:39:42<2:24:08,  1.62it/s]
 76%|███████▌  | 43576/57600 [7:39:43<2:34:47,  1.51it/s]
 76%|███████▌  | 43577/57600 [7:39:43<2:38:05,  1.48it/s]
 76%|███████▌  | 43578/57600 [7:39:44<2:35:29,  1.50it/s]
 76%|███████▌  | 43579/57600 [7:39:45<2:39:25,  1.47it/s]
 76%|███████▌  | 43580/57600 [7:39:45<2:34:29,  1.51it/s]
                                                         
{'loss': 1.1261, 'learning_rate': 3.1982578397212534e-07, 'epoch': 481.02}

 76%|███████▌  | 43580/57600 [7:39:45<2:34:29,  1.51it/s]
 76%|███████▌  | 43581/57600 [7:39:46<2:37:00,  1.49it/s]
 76%|███████▌  | 43582/57600 [7:39:47<2:34:10,  1.52it/s]
 76%|███████▌  | 43583/57600 [7:39:47<2:42:27,  1.44it/s]
 76%|███████▌  | 43584/57600 [7:39:48<2:38:18,  1.48it/s]
 76%|███████▌  | 43585/57600 [7:39:49<2:31:54,  1.54it/s]
 76%|███████▌  | 43586/57600 [7:39:49<2:30:30,  1.55it/s]
 76%|███████▌  | 43587/57600 [7:39:50<2:29:44,  1.56it/s]
 76%|███████▌  | 43588/57600 [7:39:51<2:30:58,  1.55it/s]
 76%|███████▌  | 43589/57600 [7:39:51<2:27:42,  1.58it/s]
 76%|███████▌  | 43590/57600 [7:39:52<2:29:11,  1.57it/s]
 76%|███████▌  | 43591/57600 [7:39:52<2:26:51,  1.59it/s]
 76%|███████▌  | 43592/57600 [7:39:53<2:26:29,  1.59it/s]
 76%|███████▌  | 43593/57600 [7:39:54<2:29:37,  1.56it/s]
 76%|███████▌  | 43594/57600 [7:39:54<2:30:59,  1.55it/s]
 76%|███████▌  | 43595/57600 [7:39:55<2:25:39,  1.60it/s]
 76%|███████▌  | 43596/57600 [7:39:56<2:28:12,  1.57it/s]
 76%|███████▌  | 43597/57600 [7:39:56<2:27:13,  1.59it/s]
 76%|███████▌  | 43598/57600 [7:39:57<2:27:50,  1.58it/s]
 76%|███████▌  | 43599/57600 [7:39:58<2:26:37,  1.59it/s]
 76%|███████▌  | 43600/57600 [7:39:58<2:23:57,  1.62it/s]
                                                         
{'loss': 1.1063, 'learning_rate': 3.195121951219512e-07, 'epoch': 481.24}

 76%|███████▌  | 43600/57600 [7:39:58<2:23:57,  1.62it/s]
 76%|███████▌  | 43601/57600 [7:39:59<2:25:20,  1.61it/s]
 76%|███████▌  | 43602/57600 [7:39:59<2:22:37,  1.64it/s]
 76%|███████▌  | 43603/57600 [7:40:00<2:33:36,  1.52it/s]
 76%|███████▌  | 43604/57600 [7:40:01<2:33:15,  1.52it/s]
 76%|███████▌  | 43605/57600 [7:40:01<2:28:12,  1.57it/s]
 76%|███████▌  | 43606/57600 [7:40:02<2:25:33,  1.60it/s]
 76%|███████▌  | 43607/57600 [7:40:03<2:21:26,  1.65it/s]
 76%|███████▌  | 43608/57600 [7:40:03<2:18:35,  1.68it/s]
 76%|███████▌  | 43609/57600 [7:40:04<2:20:05,  1.66it/s]
 76%|███████▌  | 43610/57600 [7:40:04<2:22:29,  1.64it/s]
 76%|███████▌  | 43611/57600 [7:40:05<2:25:18,  1.60it/s]
 76%|███████▌  | 43612/57600 [7:40:06<2:23:02,  1.63it/s]
 76%|███████▌  | 43613/57600 [7:40:06<2:22:08,  1.64it/s]
 76%|███████▌  | 43614/57600 [7:40:07<2:26:18,  1.59it/s]
 76%|███████▌  | 43615/57600 [7:40:07<2:23:58,  1.62it/s]
 76%|███████▌  | 43616/57600 [7:40:08<2:23:15,  1.63it/s]
 76%|███████▌  | 43617/57600 [7:40:09<2:24:17,  1.62it/s]
 76%|███████▌  | 43618/57600 [7:40:09<2:21:51,  1.64it/s]
 76%|███████▌  | 43619/57600 [7:40:10<2:22:22,  1.64it/s]
 76%|███████▌  | 43620/57600 [7:40:10<2:21:03,  1.65it/s]
                                                         
{'loss': 1.1305, 'learning_rate': 3.1919860627177706e-07, 'epoch': 481.46}

 76%|███████▌  | 43620/57600 [7:40:10<2:21:03,  1.65it/s]
 76%|███████▌  | 43621/57600 [7:40:11<2:19:01,  1.68it/s]
 76%|███████▌  | 43622/57600 [7:40:12<2:20:02,  1.66it/s]
 76%|███████▌  | 43623/57600 [7:40:12<2:19:35,  1.67it/s]
 76%|███████▌  | 43624/57600 [7:40:13<2:23:59,  1.62it/s]
 76%|███████▌  | 43625/57600 [7:40:13<2:18:45,  1.68it/s]
 76%|███████▌  | 43626/57600 [7:40:14<2:18:30,  1.68it/s]
 76%|███████▌  | 43627/57600 [7:40:15<2:19:02,  1.67it/s]
 76%|███████▌  | 43628/57600 [7:40:15<2:25:48,  1.60it/s]
 76%|███████▌  | 43629/57600 [7:40:16<2:28:39,  1.57it/s]
 76%|███████▌  | 43630/57600 [7:40:17<2:34:35,  1.51it/s]
 76%|███████▌  | 43631/57600 [7:40:17<2:35:39,  1.50it/s]
 76%|███████▌  | 43632/57600 [7:40:18<2:30:41,  1.54it/s]
 76%|███████▌  | 43633/57600 [7:40:19<2:25:14,  1.60it/s]
 76%|███████▌  | 43634/57600 [7:40:19<2:27:24,  1.58it/s]
 76%|███████▌  | 43635/57600 [7:40:20<2:32:22,  1.53it/s]
 76%|███████▌  | 43636/57600 [7:40:21<2:29:30,  1.56it/s]
 76%|███████▌  | 43637/57600 [7:40:21<2:28:47,  1.56it/s]
 76%|███████▌  | 43638/57600 [7:40:22<2:30:52,  1.54it/s]
 76%|███████▌  | 43639/57600 [7:40:22<2:27:49,  1.57it/s]
 76%|███████▌  | 43640/57600 [7:40:23<2:24:26,  1.61it/s]
                                                         
{'loss': 1.1276, 'learning_rate': 3.1888501742160276e-07, 'epoch': 481.68}

 76%|███████▌  | 43640/57600 [7:40:23<2:24:26,  1.61it/s]
 76%|███████▌  | 43641/57600 [7:40:24<2:29:34,  1.56it/s]
 76%|███████▌  | 43642/57600 [7:40:24<2:30:29,  1.55it/s]
 76%|███████▌  | 43643/57600 [7:40:25<2:33:21,  1.52it/s]
 76%|███████▌  | 43644/57600 [7:40:26<2:31:05,  1.54it/s]
 76%|███████▌  | 43645/57600 [7:40:26<2:27:49,  1.57it/s]
 76%|███████▌  | 43646/57600 [7:40:27<2:25:06,  1.60it/s]
 76%|███████▌  | 43647/57600 [7:40:28<2:22:37,  1.63it/s]
 76%|███████▌  | 43648/57600 [7:40:28<2:24:16,  1.61it/s]
 76%|███████▌  | 43649/57600 [7:40:29<2:23:03,  1.63it/s]
 76%|███████▌  | 43650/57600 [7:40:29<2:21:44,  1.64it/s]
 76%|███████▌  | 43651/57600 [7:40:30<2:22:47,  1.63it/s]
 76%|███████▌  | 43652/57600 [7:40:31<2:19:02,  1.67it/s]
 76%|███████▌  | 43653/57600 [7:40:31<2:22:27,  1.63it/s]
 76%|███████▌  | 43654/57600 [7:40:32<2:26:42,  1.58it/s]
 76%|███████▌  | 43655/57600 [7:40:33<2:28:19,  1.57it/s]
 76%|███████▌  | 43656/57600 [7:40:33<2:24:22,  1.61it/s]
 76%|███████▌  | 43657/57600 [7:40:34<2:26:45,  1.58it/s]
 76%|███████▌  | 43658/57600 [7:40:34<2:25:08,  1.60it/s]
 76%|███████▌  | 43659/57600 [7:40:35<2:23:02,  1.62it/s]
 76%|███████▌  | 43660/57600 [7:40:36<2:27:30,  1.58it/s]
                                                         
{'loss': 1.1197, 'learning_rate': 3.1857142857142856e-07, 'epoch': 481.9}

 76%|███████▌  | 43660/57600 [7:40:36<2:27:30,  1.58it/s]
 76%|███████▌  | 43661/57600 [7:40:36<2:26:54,  1.58it/s]
 76%|███████▌  | 43662/57600 [7:40:37<2:29:52,  1.55it/s]
 76%|███████▌  | 43663/57600 [7:40:38<2:28:18,  1.57it/s]
 76%|███████▌  | 43664/57600 [7:40:38<2:22:37,  1.63it/s]
 76%|███████▌  | 43665/57600 [7:40:39<2:20:02,  1.66it/s]
 76%|███████▌  | 43666/57600 [7:40:39<2:21:15,  1.64it/s]
 76%|███████▌  | 43667/57600 [7:40:40<2:22:59,  1.62it/s]
 76%|███████▌  | 43668/57600 [7:40:41<2:26:52,  1.58it/s]
 76%|███████▌  | 43669/57600 [7:40:41<2:35:20,  1.49it/s]
 76%|███████▌  | 43670/57600 [7:40:42<2:40:43,  1.44it/s]
 76%|███████▌  | 43671/57600 [7:40:43<2:36:41,  1.48it/s]
 76%|███████▌  | 43672/57600 [7:40:43<2:30:10,  1.55it/s]
 76%|███████▌  | 43673/57600 [7:40:44<2:28:52,  1.56it/s]
 76%|███████▌  | 43674/57600 [7:40:45<2:33:40,  1.51it/s]
 76%|███████▌  | 43675/57600 [7:40:45<2:26:09,  1.59it/s]
 76%|███████▌  | 43676/57600 [7:40:46<2:26:06,  1.59it/s]
 76%|███████▌  | 43677/57600 [7:40:46<2:24:30,  1.61it/s]
 76%|███████▌  | 43678/57600 [7:40:47<2:24:14,  1.61it/s]
 76%|███████▌  | 43679/57600 [7:40:48<2:25:23,  1.60it/s]
 76%|███████▌  | 43680/57600 [7:40:48<2:21:32,  1.64it/s]
                                                         
{'loss': 1.1389, 'learning_rate': 3.182578397212543e-07, 'epoch': 482.12}

 76%|███████▌  | 43680/57600 [7:40:48<2:21:32,  1.64it/s]
 76%|███████▌  | 43681/57600 [7:40:49<2:21:33,  1.64it/s]
 76%|███████▌  | 43682/57600 [7:40:50<2:24:11,  1.61it/s]
 76%|███████▌  | 43683/57600 [7:40:50<2:24:57,  1.60it/s]
 76%|███████▌  | 43684/57600 [7:40:51<2:26:13,  1.59it/s]
 76%|███████▌  | 43685/57600 [7:40:51<2:27:24,  1.57it/s]
 76%|███████▌  | 43686/57600 [7:40:52<2:26:29,  1.58it/s]
 76%|███████▌  | 43687/57600 [7:40:53<2:21:01,  1.64it/s]
 76%|███████▌  | 43688/57600 [7:40:53<2:24:39,  1.60it/s]
 76%|███████▌  | 43689/57600 [7:40:54<2:20:25,  1.65it/s]
 76%|███████▌  | 43690/57600 [7:40:55<2:23:29,  1.62it/s]
 76%|███████▌  | 43691/57600 [7:40:55<2:24:40,  1.60it/s]
 76%|███████▌  | 43692/57600 [7:40:56<2:22:16,  1.63it/s]
 76%|███████▌  | 43693/57600 [7:40:56<2:19:07,  1.67it/s]
 76%|███████▌  | 43694/57600 [7:40:57<2:19:15,  1.66it/s]
 76%|███████▌  | 43695/57600 [7:40:58<2:20:44,  1.65it/s]
 76%|███████▌  | 43696/57600 [7:40:58<2:18:59,  1.67it/s]
 76%|███████▌  | 43697/57600 [7:40:59<2:19:47,  1.66it/s]
 76%|███████▌  | 43698/57600 [7:40:59<2:23:03,  1.62it/s]
 76%|███████▌  | 43699/57600 [7:41:00<2:21:32,  1.64it/s]
 76%|███████▌  | 43700/57600 [7:41:01<2:30:04,  1.54it/s]
                                                         
{'loss': 1.1509, 'learning_rate': 3.1794425087108017e-07, 'epoch': 482.34}

 76%|███████▌  | 43700/57600 [7:41:01<2:30:04,  1.54it/s]
 76%|███████▌  | 43701/57600 [7:41:01<2:31:33,  1.53it/s]
 76%|███████▌  | 43702/57600 [7:41:02<2:30:26,  1.54it/s]
 76%|███████▌  | 43703/57600 [7:41:03<2:27:16,  1.57it/s]
 76%|███████▌  | 43704/57600 [7:41:03<2:28:00,  1.56it/s]
 76%|███████▌  | 43705/57600 [7:41:04<2:32:08,  1.52it/s]
 76%|███████▌  | 43706/57600 [7:41:05<2:28:16,  1.56it/s]
 76%|███████▌  | 43707/57600 [7:41:05<2:25:56,  1.59it/s]
 76%|███████▌  | 43708/57600 [7:41:06<2:28:46,  1.56it/s]
 76%|███████▌  | 43709/57600 [7:41:06<2:24:08,  1.61it/s]
 76%|███████▌  | 43710/57600 [7:41:07<2:24:08,  1.61it/s]
 76%|███████▌  | 43711/57600 [7:41:08<2:24:50,  1.60it/s]
 76%|███████▌  | 43712/57600 [7:41:08<2:27:34,  1.57it/s]
 76%|███████▌  | 43713/57600 [7:41:09<2:31:56,  1.52it/s]
 76%|███████▌  | 43714/57600 [7:41:10<2:29:10,  1.55it/s]
 76%|███████▌  | 43715/57600 [7:41:10<2:28:34,  1.56it/s]
 76%|███████▌  | 43716/57600 [7:41:11<2:25:25,  1.59it/s]
 76%|███████▌  | 43717/57600 [7:41:12<2:29:03,  1.55it/s]
 76%|███████▌  | 43718/57600 [7:41:12<2:27:45,  1.57it/s]
 76%|███████▌  | 43719/57600 [7:41:13<2:24:09,  1.60it/s]
 76%|███████▌  | 43720/57600 [7:41:13<2:25:24,  1.59it/s]
                                                         
{'loss': 1.1369, 'learning_rate': 3.1763066202090587e-07, 'epoch': 482.56}

 76%|███████▌  | 43720/57600 [7:41:13<2:25:24,  1.59it/s]
 76%|███████▌  | 43721/57600 [7:41:14<2:23:10,  1.62it/s]
 76%|███████▌  | 43722/57600 [7:41:15<2:20:37,  1.64it/s]
 76%|███████▌  | 43723/57600 [7:41:15<2:18:00,  1.68it/s]
 76%|███████▌  | 43724/57600 [7:41:16<2:23:03,  1.62it/s]
 76%|███████▌  | 43725/57600 [7:41:16<2:19:41,  1.66it/s]
 76%|███████▌  | 43726/57600 [7:41:17<2:19:21,  1.66it/s]
 76%|███████▌  | 43727/57600 [7:41:18<2:24:26,  1.60it/s]
 76%|███████▌  | 43728/57600 [7:41:18<2:27:07,  1.57it/s]
 76%|███████▌  | 43729/57600 [7:41:19<2:33:08,  1.51it/s]
 76%|███████▌  | 43730/57600 [7:41:20<2:29:26,  1.55it/s]
 76%|███████▌  | 43731/57600 [7:41:20<2:25:52,  1.58it/s]
 76%|███████▌  | 43732/57600 [7:41:21<2:20:13,  1.65it/s]
 76%|███████▌  | 43733/57600 [7:41:21<2:21:59,  1.63it/s]
 76%|███████▌  | 43734/57600 [7:41:22<2:21:28,  1.63it/s]
 76%|███████▌  | 43735/57600 [7:41:23<2:21:46,  1.63it/s]
 76%|███████▌  | 43736/57600 [7:41:23<2:21:07,  1.64it/s]
 76%|███████▌  | 43737/57600 [7:41:24<2:19:34,  1.66it/s]
 76%|███████▌  | 43738/57600 [7:41:25<2:20:00,  1.65it/s]
 76%|███████▌  | 43739/57600 [7:41:25<2:25:10,  1.59it/s]
 76%|███████▌  | 43740/57600 [7:41:26<2:29:54,  1.54it/s]
                                                         
{'loss': 1.1159, 'learning_rate': 3.173170731707317e-07, 'epoch': 482.78}

 76%|███████▌  | 43740/57600 [7:41:26<2:29:54,  1.54it/s]
 76%|███████▌  | 43741/57600 [7:41:27<2:28:21,  1.56it/s]
 76%|███████▌  | 43742/57600 [7:41:27<2:28:01,  1.56it/s]
 76%|███████▌  | 43743/57600 [7:41:28<2:23:21,  1.61it/s]
 76%|███████▌  | 43744/57600 [7:41:28<2:23:34,  1.61it/s]
 76%|███████▌  | 43745/57600 [7:41:29<2:27:03,  1.57it/s]
 76%|███████▌  | 43746/57600 [7:41:30<2:24:19,  1.60it/s]
 76%|███████▌  | 43747/57600 [7:41:30<2:28:08,  1.56it/s]
 76%|███████▌  | 43748/57600 [7:41:31<2:29:58,  1.54it/s]
 76%|███████▌  | 43749/57600 [7:41:32<2:34:33,  1.49it/s]
 76%|███████▌  | 43750/57600 [7:41:32<2:31:31,  1.52it/s]
 76%|███████▌  | 43751/57600 [7:41:33<2:31:05,  1.53it/s]
 76%|███████▌  | 43752/57600 [7:41:34<2:32:25,  1.51it/s]
 76%|███████▌  | 43753/57600 [7:41:34<2:30:55,  1.53it/s]
 76%|███████▌  | 43754/57600 [7:41:35<2:27:56,  1.56it/s]
 76%|███████▌  | 43755/57600 [7:41:35<2:24:50,  1.59it/s]
 76%|███████▌  | 43756/57600 [7:41:36<2:22:29,  1.62it/s]
 76%|███████▌  | 43757/57600 [7:41:37<2:22:41,  1.62it/s]
 76%|███████▌  | 43758/57600 [7:41:37<2:24:20,  1.60it/s]
 76%|███████▌  | 43759/57600 [7:41:38<2:23:27,  1.61it/s]
 76%|███████▌  | 43760/57600 [7:41:39<2:32:04,  1.52it/s]
                                                         
{'loss': 1.1181, 'learning_rate': 3.1700348432055753e-07, 'epoch': 483.0}

 76%|███████▌  | 43760/57600 [7:41:39<2:32:04,  1.52it/s]
 76%|███████▌  | 43761/57600 [7:41:39<2:32:39,  1.51it/s]
 76%|███████▌  | 43762/57600 [7:41:40<2:35:28,  1.48it/s]
 76%|███████▌  | 43763/57600 [7:41:41<2:28:17,  1.56it/s]
 76%|███████▌  | 43764/57600 [7:41:41<2:27:51,  1.56it/s]
 76%|███████▌  | 43765/57600 [7:41:42<2:25:03,  1.59it/s]
 76%|███████▌  | 43766/57600 [7:41:43<2:27:26,  1.56it/s]
 76%|███████▌  | 43767/57600 [7:41:43<2:28:53,  1.55it/s]
 76%|███████▌  | 43768/57600 [7:41:44<2:23:23,  1.61it/s]
 76%|███████▌  | 43769/57600 [7:41:44<2:20:28,  1.64it/s]
 76%|███████▌  | 43770/57600 [7:41:45<2:20:35,  1.64it/s]
 76%|███████▌  | 43771/57600 [7:41:46<2:22:56,  1.61it/s]
 76%|███████▌  | 43772/57600 [7:41:46<2:28:34,  1.55it/s]
 76%|███████▌  | 43773/57600 [7:41:47<2:28:20,  1.55it/s]
 76%|███████▌  | 43774/57600 [7:41:48<2:27:15,  1.56it/s]
 76%|███████▌  | 43775/57600 [7:41:48<2:25:49,  1.58it/s]
 76%|███████▌  | 43776/57600 [7:41:49<2:24:20,  1.60it/s]
 76%|███████▌  | 43777/57600 [7:41:49<2:22:02,  1.62it/s]
 76%|███████▌  | 43778/57600 [7:41:50<2:20:13,  1.64it/s]
 76%|███████▌  | 43779/57600 [7:41:51<2:19:33,  1.65it/s]
 76%|███████▌  | 43780/57600 [7:41:51<2:24:24,  1.59it/s]
                                                         
{'loss': 1.1249, 'learning_rate': 3.1668989547038323e-07, 'epoch': 483.22}

 76%|███████▌  | 43780/57600 [7:41:51<2:24:24,  1.59it/s]
 76%|███████▌  | 43781/57600 [7:41:52<2:22:50,  1.61it/s]
 76%|███████▌  | 43782/57600 [7:41:53<2:23:51,  1.60it/s]
 76%|███████▌  | 43783/57600 [7:41:53<2:28:26,  1.55it/s]
 76%|███████▌  | 43784/57600 [7:41:54<2:27:44,  1.56it/s]
 76%|███████▌  | 43785/57600 [7:41:54<2:23:34,  1.60it/s]
 76%|███████▌  | 43786/57600 [7:41:55<2:22:15,  1.62it/s]
 76%|███████▌  | 43787/57600 [7:41:56<2:22:52,  1.61it/s]
 76%|███████▌  | 43788/57600 [7:41:56<2:22:24,  1.62it/s]
 76%|███████▌  | 43789/57600 [7:41:57<2:20:25,  1.64it/s]
 76%|███████▌  | 43790/57600 [7:41:57<2:21:05,  1.63it/s]
 76%|███████▌  | 43791/57600 [7:41:58<2:19:40,  1.65it/s]
 76%|███████▌  | 43792/57600 [7:41:59<2:25:25,  1.58it/s]
 76%|███████▌  | 43793/57600 [7:41:59<2:25:18,  1.58it/s]
 76%|███████▌  | 43794/57600 [7:42:00<2:25:51,  1.58it/s]
 76%|███████▌  | 43795/57600 [7:42:01<2:26:12,  1.57it/s]
 76%|███████▌  | 43796/57600 [7:42:01<2:25:43,  1.58it/s]
 76%|███████▌  | 43797/57600 [7:42:02<2:24:29,  1.59it/s]
 76%|███████▌  | 43798/57600 [7:42:03<2:28:08,  1.55it/s]
 76%|███████▌  | 43799/57600 [7:42:03<2:28:47,  1.55it/s]
 76%|███████▌  | 43800/57600 [7:42:04<2:26:58,  1.56it/s]
                                                         
{'loss': 1.1342, 'learning_rate': 3.1637630662020904e-07, 'epoch': 483.44}

 76%|███████▌  | 43800/57600 [7:42:04<2:26:58,  1.56it/s]
 76%|███████▌  | 43801/57600 [7:42:05<2:27:08,  1.56it/s]
 76%|███████▌  | 43802/57600 [7:42:05<2:24:45,  1.59it/s]
 76%|███████▌  | 43803/57600 [7:42:06<2:21:51,  1.62it/s]
 76%|███████▌  | 43804/57600 [7:42:06<2:21:56,  1.62it/s]
 76%|███████▌  | 43805/57600 [7:42:07<2:17:13,  1.68it/s]
 76%|███████▌  | 43806/57600 [7:42:08<2:24:56,  1.59it/s]
 76%|███████▌  | 43807/57600 [7:42:08<2:22:32,  1.61it/s]
 76%|███████▌  | 43808/57600 [7:42:09<2:19:02,  1.65it/s]
 76%|███████▌  | 43809/57600 [7:42:09<2:22:04,  1.62it/s]
 76%|███████▌  | 43810/57600 [7:42:10<2:26:20,  1.57it/s]
 76%|███████▌  | 43811/57600 [7:42:11<2:28:13,  1.55it/s]
 76%|███████▌  | 43812/57600 [7:42:11<2:26:49,  1.57it/s]
 76%|███████▌  | 43813/57600 [7:42:12<2:34:26,  1.49it/s]
 76%|███████▌  | 43814/57600 [7:42:13<2:33:03,  1.50it/s]
 76%|███████▌  | 43815/57600 [7:42:13<2:29:12,  1.54it/s]
 76%|███████▌  | 43816/57600 [7:42:14<2:28:05,  1.55it/s]
 76%|███████▌  | 43817/57600 [7:42:15<2:23:13,  1.60it/s]
 76%|███████▌  | 43818/57600 [7:42:15<2:24:06,  1.59it/s]
 76%|███████▌  | 43819/57600 [7:42:16<2:22:40,  1.61it/s]
 76%|███████▌  | 43820/57600 [7:42:16<2:23:13,  1.60it/s]
                                                         
{'loss': 1.1113, 'learning_rate': 3.160627177700348e-07, 'epoch': 483.66}

 76%|███████▌  | 43820/57600 [7:42:16<2:23:13,  1.60it/s]
 76%|███████▌  | 43821/57600 [7:42:17<2:20:46,  1.63it/s]
 76%|███████▌  | 43822/57600 [7:42:18<2:18:41,  1.66it/s]
 76%|███████▌  | 43823/57600 [7:42:18<2:23:11,  1.60it/s]
 76%|███████▌  | 43824/57600 [7:42:19<2:21:21,  1.62it/s]
 76%|███████▌  | 43825/57600 [7:42:20<2:22:27,  1.61it/s]
 76%|███████▌  | 43826/57600 [7:42:20<2:26:25,  1.57it/s]
 76%|███████▌  | 43827/57600 [7:42:21<2:25:22,  1.58it/s]
 76%|███████▌  | 43828/57600 [7:42:21<2:27:21,  1.56it/s]
 76%|███████▌  | 43829/57600 [7:42:22<2:27:38,  1.55it/s]
 76%|███████▌  | 43830/57600 [7:42:23<2:24:30,  1.59it/s]
 76%|███████▌  | 43831/57600 [7:42:23<2:20:26,  1.63it/s]
 76%|███████▌  | 43832/57600 [7:42:24<2:25:15,  1.58it/s]
 76%|███████▌  | 43833/57600 [7:42:25<2:30:20,  1.53it/s]
 76%|███████▌  | 43834/57600 [7:42:25<2:27:14,  1.56it/s]
 76%|███████▌  | 43835/57600 [7:42:26<2:26:49,  1.56it/s]
 76%|███████▌  | 43836/57600 [7:42:27<2:22:32,  1.61it/s]
 76%|███████▌  | 43837/57600 [7:42:27<2:19:15,  1.65it/s]
 76%|███████▌  | 43838/57600 [7:42:28<2:21:56,  1.62it/s]
 76%|███████▌  | 43839/57600 [7:42:28<2:22:03,  1.61it/s]
 76%|███████▌  | 43840/57600 [7:42:29<2:22:20,  1.61it/s]
                                                         
{'loss': 1.1048, 'learning_rate': 3.1574912891986065e-07, 'epoch': 483.89}

 76%|███████▌  | 43840/57600 [7:42:29<2:22:20,  1.61it/s]
 76%|███████▌  | 43841/57600 [7:42:30<2:26:19,  1.57it/s]
 76%|███████▌  | 43842/57600 [7:42:30<2:23:24,  1.60it/s]
 76%|███████▌  | 43843/57600 [7:42:31<2:27:37,  1.55it/s]
 76%|███████▌  | 43844/57600 [7:42:32<2:23:26,  1.60it/s]
 76%|███████▌  | 43845/57600 [7:42:32<2:19:59,  1.64it/s]
 76%|███████▌  | 43846/57600 [7:42:33<2:20:02,  1.64it/s]
 76%|███████▌  | 43847/57600 [7:42:33<2:17:42,  1.66it/s]
 76%|███████▌  | 43848/57600 [7:42:34<2:21:03,  1.62it/s]
 76%|███████▌  | 43849/57600 [7:42:35<2:20:53,  1.63it/s]
 76%|███████▌  | 43850/57600 [7:42:35<2:22:04,  1.61it/s]
 76%|███████▌  | 43851/57600 [7:42:36<2:31:05,  1.52it/s]
 76%|███████▌  | 43852/57600 [7:42:37<2:28:19,  1.54it/s]
 76%|███████▌  | 43853/57600 [7:42:37<2:24:16,  1.59it/s]
 76%|███████▌  | 43854/57600 [7:42:38<2:20:23,  1.63it/s]
 76%|███████▌  | 43855/57600 [7:42:38<2:23:13,  1.60it/s]
 76%|███████▌  | 43856/57600 [7:42:39<2:28:33,  1.54it/s]
 76%|███████▌  | 43857/57600 [7:42:40<2:25:40,  1.57it/s]
 76%|███████▌  | 43858/57600 [7:42:40<2:21:03,  1.62it/s]
 76%|███████▌  | 43859/57600 [7:42:41<2:22:32,  1.61it/s]
 76%|███████▌  | 43860/57600 [7:42:42<2:28:24,  1.54it/s]
                                                         
{'loss': 1.1291, 'learning_rate': 3.154355400696865e-07, 'epoch': 484.11}

 76%|███████▌  | 43860/57600 [7:42:42<2:28:24,  1.54it/s]
 76%|███████▌  | 43861/57600 [7:42:42<2:23:16,  1.60it/s]
 76%|███████▌  | 43862/57600 [7:42:43<2:25:43,  1.57it/s]
 76%|███████▌  | 43863/57600 [7:42:43<2:22:18,  1.61it/s]
 76%|███████▌  | 43864/57600 [7:42:44<2:21:11,  1.62it/s]
 76%|███████▌  | 43865/57600 [7:42:45<2:23:49,  1.59it/s]
 76%|███████▌  | 43866/57600 [7:42:45<2:24:08,  1.59it/s]
 76%|███████▌  | 43867/57600 [7:42:46<2:24:50,  1.58it/s]
 76%|███████▌  | 43868/57600 [7:42:47<2:22:32,  1.61it/s]
 76%|███████▌  | 43869/57600 [7:42:47<2:23:11,  1.60it/s]
 76%|███████▌  | 43870/57600 [7:42:48<2:22:07,  1.61it/s]
 76%|███████▌  | 43871/57600 [7:42:48<2:22:32,  1.61it/s]
 76%|███████▌  | 43872/57600 [7:42:49<2:22:48,  1.60it/s]
 76%|███████▌  | 43873/57600 [7:42:50<2:20:42,  1.63it/s]
 76%|███████▌  | 43874/57600 [7:42:50<2:23:45,  1.59it/s]
 76%|███████▌  | 43875/57600 [7:42:51<2:26:36,  1.56it/s]
 76%|███████▌  | 43876/57600 [7:42:52<2:23:45,  1.59it/s]
 76%|███████▌  | 43877/57600 [7:42:52<2:29:51,  1.53it/s]
 76%|███████▌  | 43878/57600 [7:42:53<2:27:15,  1.55it/s]
 76%|███████▌  | 43879/57600 [7:42:53<2:20:33,  1.63it/s]
 76%|███████▌  | 43880/57600 [7:42:54<2:22:16,  1.61it/s]
                                                         
{'loss': 1.1107, 'learning_rate': 3.1512195121951215e-07, 'epoch': 484.33}

 76%|███████▌  | 43880/57600 [7:42:54<2:22:16,  1.61it/s]
 76%|███████▌  | 43881/57600 [7:42:55<2:22:45,  1.60it/s]
 76%|███████▌  | 43882/57600 [7:42:55<2:25:11,  1.57it/s]
 76%|███████▌  | 43883/57600 [7:42:56<2:22:40,  1.60it/s]
 76%|███████▌  | 43884/57600 [7:42:57<2:17:33,  1.66it/s]
 76%|███████▌  | 43885/57600 [7:42:57<2:19:58,  1.63it/s]
 76%|███████▌  | 43886/57600 [7:42:58<2:21:11,  1.62it/s]
 76%|███████▌  | 43887/57600 [7:42:58<2:23:26,  1.59it/s]
 76%|███████▌  | 43888/57600 [7:42:59<2:21:06,  1.62it/s]
 76%|███████▌  | 43889/57600 [7:43:00<2:21:35,  1.61it/s]
 76%|███████▌  | 43890/57600 [7:43:00<2:25:15,  1.57it/s]
 76%|███████▌  | 43891/57600 [7:43:01<2:25:04,  1.57it/s]
 76%|███████▌  | 43892/57600 [7:43:02<2:20:22,  1.63it/s]
 76%|███████▌  | 43893/57600 [7:43:02<2:21:35,  1.61it/s]
 76%|███████▌  | 43894/57600 [7:43:03<2:20:48,  1.62it/s]
 76%|███████▌  | 43895/57600 [7:43:03<2:25:58,  1.56it/s]
 76%|███████▌  | 43896/57600 [7:43:04<2:23:28,  1.59it/s]
 76%|███████▌  | 43897/57600 [7:43:05<2:27:04,  1.55it/s]
 76%|███████▌  | 43898/57600 [7:43:05<2:27:27,  1.55it/s]
 76%|███████▌  | 43899/57600 [7:43:06<2:27:31,  1.55it/s]
 76%|███████▌  | 43900/57600 [7:43:07<2:28:44,  1.54it/s]
                                                         
{'loss': 1.1534, 'learning_rate': 3.14808362369338e-07, 'epoch': 484.55}

 76%|███████▌  | 43900/57600 [7:43:07<2:28:44,  1.54it/s]
 76%|███████▌  | 43901/57600 [7:43:07<2:27:54,  1.54it/s]
 76%|███████▌  | 43902/57600 [7:43:08<2:26:33,  1.56it/s]
 76%|███████▌  | 43903/57600 [7:43:09<2:26:24,  1.56it/s]
 76%|███████▌  | 43904/57600 [7:43:09<2:25:57,  1.56it/s]
 76%|███████▌  | 43905/57600 [7:43:10<2:26:51,  1.55it/s]
 76%|███████▌  | 43906/57600 [7:43:10<2:22:27,  1.60it/s]
 76%|███████▌  | 43907/57600 [7:43:11<2:24:08,  1.58it/s]
 76%|███████▌  | 43908/57600 [7:43:12<2:20:24,  1.63it/s]
 76%|███████▌  | 43909/57600 [7:43:12<2:23:24,  1.59it/s]
 76%|███████▌  | 43910/57600 [7:43:13<2:28:49,  1.53it/s]
 76%|███████▌  | 43911/57600 [7:43:14<2:32:04,  1.50it/s]
 76%|███████▌  | 43912/57600 [7:43:14<2:26:38,  1.56it/s]
 76%|███████▌  | 43913/57600 [7:43:15<2:24:52,  1.57it/s]
 76%|███████▌  | 43914/57600 [7:43:16<2:26:19,  1.56it/s]
 76%|███████▌  | 43915/57600 [7:43:16<2:22:51,  1.60it/s]
 76%|███████▌  | 43916/57600 [7:43:17<2:20:03,  1.63it/s]
 76%|███████▌  | 43917/57600 [7:43:17<2:19:03,  1.64it/s]
 76%|███████▌  | 43918/57600 [7:43:18<2:22:12,  1.60it/s]
 76%|███████▌  | 43919/57600 [7:43:19<2:28:16,  1.54it/s]
 76%|███████▋  | 43920/57600 [7:43:19<2:26:19,  1.56it/s]
                                                         
{'loss': 1.116, 'learning_rate': 3.1449477351916376e-07, 'epoch': 484.77}

 76%|███████▋  | 43920/57600 [7:43:19<2:26:19,  1.56it/s]
 76%|███████▋  | 43921/57600 [7:43:20<2:24:40,  1.58it/s]
 76%|███████▋  | 43922/57600 [7:43:21<2:18:31,  1.65it/s]
 76%|███████▋  | 43923/57600 [7:43:21<2:21:34,  1.61it/s]
 76%|███████▋  | 43924/57600 [7:43:22<2:23:26,  1.59it/s]
 76%|███████▋  | 43925/57600 [7:43:23<2:30:08,  1.52it/s]
 76%|███████▋  | 43926/57600 [7:43:23<2:24:23,  1.58it/s]
 76%|███████▋  | 43927/57600 [7:43:24<2:25:12,  1.57it/s]
 76%|███████▋  | 43928/57600 [7:43:24<2:24:32,  1.58it/s]
 76%|███████▋  | 43929/57600 [7:43:25<2:22:36,  1.60it/s]
 76%|███████▋  | 43930/57600 [7:43:26<2:25:18,  1.57it/s]
 76%|███████▋  | 43931/57600 [7:43:26<2:24:14,  1.58it/s]
 76%|███████▋  | 43932/57600 [7:43:27<2:21:56,  1.60it/s]
 76%|███████▋  | 43933/57600 [7:43:28<2:20:37,  1.62it/s]
 76%|███████▋  | 43934/57600 [7:43:28<2:19:01,  1.64it/s]
 76%|███████▋  | 43935/57600 [7:43:29<2:19:59,  1.63it/s]
 76%|███████▋  | 43936/57600 [7:43:29<2:19:24,  1.63it/s]
 76%|███████▋  | 43937/57600 [7:43:30<2:17:49,  1.65it/s]
 76%|███████▋  | 43938/57600 [7:43:31<2:21:30,  1.61it/s]
 76%|███████▋  | 43939/57600 [7:43:31<2:22:37,  1.60it/s]
 76%|███████▋  | 43940/57600 [7:43:32<2:19:13,  1.64it/s]
                                                         
{'loss': 1.147, 'learning_rate': 3.1418118466898956e-07, 'epoch': 484.99}

 76%|███████▋  | 43940/57600 [7:43:32<2:19:13,  1.64it/s]
 76%|███████▋  | 43941/57600 [7:43:32<2:22:58,  1.59it/s]
 76%|███████▋  | 43942/57600 [7:43:33<2:29:19,  1.52it/s]
 76%|███████▋  | 43943/57600 [7:43:34<2:31:05,  1.51it/s]
 76%|███████▋  | 43944/57600 [7:43:34<2:23:54,  1.58it/s]
 76%|███████▋  | 43945/57600 [7:43:35<2:28:57,  1.53it/s]
 76%|███████▋  | 43946/57600 [7:43:36<2:26:15,  1.56it/s]
 76%|███████▋  | 43947/57600 [7:43:36<2:24:50,  1.57it/s]
 76%|███████▋  | 43948/57600 [7:43:37<2:20:11,  1.62it/s]
 76%|███████▋  | 43949/57600 [7:43:38<2:20:11,  1.62it/s]
 76%|███████▋  | 43950/57600 [7:43:38<2:19:30,  1.63it/s]
 76%|███████▋  | 43951/57600 [7:43:39<2:15:53,  1.67it/s]
 76%|███████▋  | 43952/57600 [7:43:39<2:18:11,  1.65it/s]
 76%|███████▋  | 43953/57600 [7:43:40<2:19:34,  1.63it/s]
 76%|███████▋  | 43954/57600 [7:43:41<2:23:52,  1.58it/s]
 76%|███████▋  | 43955/57600 [7:43:41<2:24:57,  1.57it/s]
 76%|███████▋  | 43956/57600 [7:43:42<2:27:26,  1.54it/s]
 76%|███████▋  | 43957/57600 [7:43:43<2:28:40,  1.53it/s]
 76%|███████▋  | 43958/57600 [7:43:43<2:24:11,  1.58it/s]
 76%|███████▋  | 43959/57600 [7:43:44<2:25:09,  1.57it/s]
 76%|███████▋  | 43960/57600 [7:43:45<2:24:20,  1.57it/s]
                                                         
{'loss': 1.1347, 'learning_rate': 3.1386759581881526e-07, 'epoch': 485.21}

 76%|███████▋  | 43960/57600 [7:43:45<2:24:20,  1.57it/s]
 76%|███████▋  | 43961/57600 [7:43:45<2:28:53,  1.53it/s]
 76%|███████▋  | 43962/57600 [7:43:46<2:24:20,  1.57it/s]
 76%|███████▋  | 43963/57600 [7:43:47<2:27:09,  1.54it/s]
 76%|███████▋  | 43964/57600 [7:43:47<2:24:40,  1.57it/s]
 76%|███████▋  | 43965/57600 [7:43:48<2:20:40,  1.62it/s]
 76%|███████▋  | 43966/57600 [7:43:48<2:19:09,  1.63it/s]
 76%|███████▋  | 43967/57600 [7:43:49<2:20:54,  1.61it/s]
 76%|███████▋  | 43968/57600 [7:43:50<2:19:56,  1.62it/s]
 76%|███████▋  | 43969/57600 [7:43:50<2:16:27,  1.66it/s]
 76%|███████▋  | 43970/57600 [7:43:51<2:16:49,  1.66it/s]
 76%|███████▋  | 43971/57600 [7:43:51<2:17:27,  1.65it/s]
 76%|███████▋  | 43972/57600 [7:43:52<2:15:12,  1.68it/s]
 76%|███████▋  | 43973/57600 [7:43:52<2:14:53,  1.68it/s]
 76%|███████▋  | 43974/57600 [7:43:53<2:21:40,  1.60it/s]
 76%|███████▋  | 43975/57600 [7:43:54<2:28:33,  1.53it/s]
 76%|███████▋  | 43976/57600 [7:43:55<2:29:14,  1.52it/s]
 76%|███████▋  | 43977/57600 [7:43:55<2:22:58,  1.59it/s]
 76%|███████▋  | 43978/57600 [7:43:56<2:23:08,  1.59it/s]
 76%|███████▋  | 43979/57600 [7:43:56<2:25:41,  1.56it/s]
 76%|███████▋  | 43980/57600 [7:43:57<2:25:38,  1.56it/s]
                                                         
{'loss': 1.1253, 'learning_rate': 3.135540069686412e-07, 'epoch': 485.43}

 76%|███████▋  | 43980/57600 [7:43:57<2:25:38,  1.56it/s]
 76%|███████▋  | 43981/57600 [7:43:58<2:27:37,  1.54it/s]
 76%|███████▋  | 43982/57600 [7:43:58<2:27:50,  1.54it/s]
 76%|███████▋  | 43983/57600 [7:43:59<2:24:44,  1.57it/s]
 76%|███████▋  | 43984/57600 [7:44:00<2:21:46,  1.60it/s]
 76%|███████▋  | 43985/57600 [7:44:00<2:18:43,  1.64it/s]
 76%|███████▋  | 43986/57600 [7:44:01<2:24:39,  1.57it/s]
 76%|███████▋  | 43987/57600 [7:44:01<2:23:25,  1.58it/s]
 76%|███████▋  | 43988/57600 [7:44:02<2:20:27,  1.62it/s]
 76%|███████▋  | 43989/57600 [7:44:03<2:25:18,  1.56it/s]
 76%|███████▋  | 43990/57600 [7:44:03<2:24:10,  1.57it/s]
 76%|███████▋  | 43991/57600 [7:44:04<2:29:10,  1.52it/s]
 76%|███████▋  | 43992/57600 [7:44:05<2:23:50,  1.58it/s]
 76%|███████▋  | 43993/57600 [7:44:05<2:24:26,  1.57it/s]
 76%|███████▋  | 43994/57600 [7:44:06<2:26:28,  1.55it/s]
 76%|███████▋  | 43995/57600 [7:44:07<2:27:30,  1.54it/s]
 76%|███████▋  | 43996/57600 [7:44:07<2:21:41,  1.60it/s]
 76%|███████▋  | 43997/57600 [7:44:08<2:20:16,  1.62it/s]
 76%|███████▋  | 43998/57600 [7:44:08<2:22:05,  1.60it/s]
 76%|███████▋  | 43999/57600 [7:44:09<2:20:06,  1.62it/s]
 76%|███████▋  | 44000/57600 [7:44:10<2:20:02,  1.62it/s]
                                                         
{'loss': 1.1149, 'learning_rate': 3.1324041811846693e-07, 'epoch': 485.65}

 76%|███████▋  | 44000/57600 [7:44:10<2:20:02,  1.62it/s]
 76%|███████▋  | 44001/57600 [7:44:10<2:17:05,  1.65it/s]
 76%|███████▋  | 44002/57600 [7:44:11<2:16:16,  1.66it/s]
 76%|███████▋  | 44003/57600 [7:44:11<2:16:52,  1.66it/s]
 76%|███████▋  | 44004/57600 [7:44:12<2:16:17,  1.66it/s]
 76%|███████▋  | 44005/57600 [7:44:13<2:19:03,  1.63it/s]
 76%|███████▋  | 44006/57600 [7:44:13<2:23:50,  1.58it/s]
 76%|███████▋  | 44007/57600 [7:44:14<2:23:03,  1.58it/s]
 76%|███████▋  | 44008/57600 [7:44:15<2:20:00,  1.62it/s]
 76%|███████▋  | 44009/57600 [7:44:15<2:18:51,  1.63it/s]
 76%|███████▋  | 44010/57600 [7:44:16<2:26:40,  1.54it/s]
 76%|███████▋  | 44011/57600 [7:44:17<2:23:31,  1.58it/s]
 76%|███████▋  | 44012/57600 [7:44:17<2:25:01,  1.56it/s]
 76%|███████▋  | 44013/57600 [7:44:18<2:24:30,  1.57it/s]
 76%|███████▋  | 44014/57600 [7:44:18<2:23:33,  1.58it/s]
 76%|███████▋  | 44015/57600 [7:44:19<2:27:20,  1.54it/s]
 76%|███████▋  | 44016/57600 [7:44:20<2:24:12,  1.57it/s]
 76%|███████▋  | 44017/57600 [7:44:20<2:23:21,  1.58it/s]
 76%|███████▋  | 44018/57600 [7:44:21<2:24:24,  1.57it/s]
 76%|███████▋  | 44019/57600 [7:44:22<2:24:33,  1.57it/s]
 76%|███████▋  | 44020/57600 [7:44:22<2:18:12,  1.64it/s]
                                                         
{'loss': 1.1594, 'learning_rate': 3.129268292682926e-07, 'epoch': 485.87}

 76%|███████▋  | 44020/57600 [7:44:22<2:18:12,  1.64it/s]
 76%|███████▋  | 44021/57600 [7:44:23<2:19:11,  1.63it/s]
 76%|███████▋  | 44022/57600 [7:44:23<2:20:24,  1.61it/s]
 76%|███████▋  | 44023/57600 [7:44:24<2:16:59,  1.65it/s]
 76%|███████▋  | 44024/57600 [7:44:25<2:18:44,  1.63it/s]
 76%|███████▋  | 44025/57600 [7:44:25<2:22:21,  1.59it/s]
 76%|███████▋  | 44026/57600 [7:44:26<2:22:27,  1.59it/s]
 76%|███████▋  | 44027/57600 [7:44:27<2:20:30,  1.61it/s]
 76%|███████▋  | 44028/57600 [7:44:27<2:20:44,  1.61it/s]
 76%|███████▋  | 44029/57600 [7:44:28<2:18:48,  1.63it/s]
 76%|███████▋  | 44030/57600 [7:44:29<2:28:17,  1.53it/s]
 76%|███████▋  | 44031/57600 [7:44:29<2:23:42,  1.57it/s]
 76%|███████▋  | 44032/57600 [7:44:30<2:26:46,  1.54it/s]
 76%|███████▋  | 44033/57600 [7:44:30<2:22:47,  1.58it/s]
 76%|███████▋  | 44034/57600 [7:44:31<2:19:31,  1.62it/s]
 76%|███████▋  | 44035/57600 [7:44:32<2:18:54,  1.63it/s]
 76%|███████▋  | 44036/57600 [7:44:32<2:17:12,  1.65it/s]
 76%|███████▋  | 44037/57600 [7:44:33<2:17:30,  1.64it/s]
 76%|███████▋  | 44038/57600 [7:44:33<2:20:06,  1.61it/s]
 76%|███████▋  | 44039/57600 [7:44:34<2:17:14,  1.65it/s]
 76%|███████▋  | 44040/57600 [7:44:35<2:15:40,  1.67it/s]
                                                         
{'loss': 1.1279, 'learning_rate': 3.126132404181185e-07, 'epoch': 486.09}

 76%|███████▋  | 44040/57600 [7:44:35<2:15:40,  1.67it/s]
 76%|███████▋  | 44041/57600 [7:44:35<2:19:36,  1.62it/s]
 76%|███████▋  | 44042/57600 [7:44:36<2:17:26,  1.64it/s]
 76%|███████▋  | 44043/57600 [7:44:37<2:22:55,  1.58it/s]
 76%|███████▋  | 44044/57600 [7:44:37<2:21:29,  1.60it/s]
 76%|███████▋  | 44045/57600 [7:44:38<2:18:50,  1.63it/s]
 76%|███████▋  | 44046/57600 [7:44:38<2:16:14,  1.66it/s]
 76%|███████▋  | 44047/57600 [7:44:39<2:17:36,  1.64it/s]
 76%|███████▋  | 44048/57600 [7:44:39<2:15:25,  1.67it/s]
 76%|███████▋  | 44049/57600 [7:44:40<2:16:11,  1.66it/s]
 76%|███████▋  | 44050/57600 [7:44:41<2:20:18,  1.61it/s]
 76%|███████▋  | 44051/57600 [7:44:41<2:22:09,  1.59it/s]
 76%|███████▋  | 44052/57600 [7:44:42<2:22:02,  1.59it/s]
 76%|███████▋  | 44053/57600 [7:44:43<2:19:42,  1.62it/s]
 76%|███████▋  | 44054/57600 [7:44:43<2:24:35,  1.56it/s]
 76%|███████▋  | 44055/57600 [7:44:44<2:27:55,  1.53it/s]
 76%|███████▋  | 44056/57600 [7:44:45<2:24:18,  1.56it/s]
 76%|███████▋  | 44057/57600 [7:44:45<2:24:28,  1.56it/s]
 76%|███████▋  | 44058/57600 [7:44:46<2:24:51,  1.56it/s]
 76%|███████▋  | 44059/57600 [7:44:47<2:23:10,  1.58it/s]
 76%|███████▋  | 44060/57600 [7:44:47<2:21:29,  1.59it/s]
                                                         
{'loss': 1.1097, 'learning_rate': 3.1229965156794424e-07, 'epoch': 486.31}

 76%|███████▋  | 44060/57600 [7:44:47<2:21:29,  1.59it/s]
 76%|███████▋  | 44061/57600 [7:44:48<2:23:47,  1.57it/s]
 76%|███████▋  | 44062/57600 [7:44:48<2:23:26,  1.57it/s]
 76%|███████▋  | 44063/57600 [7:44:49<2:26:10,  1.54it/s]
 76%|███████▋  | 44064/57600 [7:44:50<2:25:53,  1.55it/s]
 77%|███████▋  | 44065/57600 [7:44:50<2:25:26,  1.55it/s]
 77%|███████▋  | 44066/57600 [7:44:51<2:29:45,  1.51it/s]
 77%|███████▋  | 44067/57600 [7:44:52<2:24:45,  1.56it/s]
 77%|███████▋  | 44068/57600 [7:44:52<2:25:22,  1.55it/s]
 77%|███████▋  | 44069/57600 [7:44:53<2:25:09,  1.55it/s]
 77%|███████▋  | 44070/57600 [7:44:54<2:27:03,  1.53it/s]
 77%|███████▋  | 44071/57600 [7:44:54<2:29:04,  1.51it/s]
 77%|███████▋  | 44072/57600 [7:44:55<2:25:55,  1.55it/s]
 77%|███████▋  | 44073/57600 [7:44:56<2:24:33,  1.56it/s]
 77%|███████▋  | 44074/57600 [7:44:56<2:21:02,  1.60it/s]
 77%|███████▋  | 44075/57600 [7:44:57<2:20:32,  1.60it/s]
 77%|███████▋  | 44076/57600 [7:44:57<2:18:26,  1.63it/s]
 77%|███████▋  | 44077/57600 [7:44:58<2:19:48,  1.61it/s]
 77%|███████▋  | 44078/57600 [7:44:59<2:22:11,  1.58it/s]
 77%|███████▋  | 44079/57600 [7:44:59<2:18:38,  1.63it/s]
 77%|███████▋  | 44080/57600 [7:45:00<2:19:55,  1.61it/s]
                                                         
{'loss': 1.0929, 'learning_rate': 3.1198606271777004e-07, 'epoch': 486.53}

 77%|███████▋  | 44080/57600 [7:45:00<2:19:55,  1.61it/s]
 77%|███████▋  | 44081/57600 [7:45:00<2:18:28,  1.63it/s]
 77%|███████▋  | 44082/57600 [7:45:01<2:20:58,  1.60it/s]
 77%|███████▋  | 44083/57600 [7:45:02<2:18:23,  1.63it/s]
 77%|███████▋  | 44084/57600 [7:45:02<2:21:03,  1.60it/s]
 77%|███████▋  | 44085/57600 [7:45:03<2:24:29,  1.56it/s]
 77%|███████▋  | 44086/57600 [7:45:04<2:20:23,  1.60it/s]
 77%|███████▋  | 44087/57600 [7:45:04<2:18:10,  1.63it/s]
 77%|███████▋  | 44088/57600 [7:45:05<2:18:04,  1.63it/s]
 77%|███████▋  | 44089/57600 [7:45:05<2:20:59,  1.60it/s]
 77%|███████▋  | 44090/57600 [7:45:06<2:20:12,  1.61it/s]
 77%|███████▋  | 44091/57600 [7:45:07<2:22:39,  1.58it/s]
 77%|███████▋  | 44092/57600 [7:45:07<2:24:13,  1.56it/s]
 77%|███████▋  | 44093/57600 [7:45:08<2:23:13,  1.57it/s]
 77%|███████▋  | 44094/57600 [7:45:09<2:30:19,  1.50it/s]
 77%|███████▋  | 44095/57600 [7:45:10<2:32:51,  1.47it/s]
 77%|███████▋  | 44096/57600 [7:45:10<2:29:28,  1.51it/s]
 77%|███████▋  | 44097/57600 [7:45:11<2:26:29,  1.54it/s]
 77%|███████▋  | 44098/57600 [7:45:11<2:25:37,  1.55it/s]
 77%|███████▋  | 44099/57600 [7:45:12<2:26:48,  1.53it/s]
 77%|███████▋  | 44100/57600 [7:45:13<2:24:45,  1.55it/s]
                                                         
{'loss': 1.1549, 'learning_rate': 3.1167247386759574e-07, 'epoch': 486.75}

 77%|███████▋  | 44100/57600 [7:45:13<2:24:45,  1.55it/s]
 77%|███████▋  | 44101/57600 [7:45:13<2:21:35,  1.59it/s]
 77%|███████▋  | 44102/57600 [7:45:14<2:19:57,  1.61it/s]
 77%|███████▋  | 44103/57600 [7:45:15<2:21:35,  1.59it/s]
 77%|███████▋  | 44104/57600 [7:45:15<2:20:16,  1.60it/s]
 77%|███████▋  | 44105/57600 [7:45:16<2:28:27,  1.52it/s]
 77%|███████▋  | 44106/57600 [7:45:16<2:25:43,  1.54it/s]
 77%|███████▋  | 44107/57600 [7:45:17<2:22:27,  1.58it/s]
 77%|███████▋  | 44108/57600 [7:45:18<2:25:49,  1.54it/s]
 77%|███████▋  | 44109/57600 [7:45:18<2:22:52,  1.57it/s]
 77%|███████▋  | 44110/57600 [7:45:19<2:21:52,  1.58it/s]
 77%|███████▋  | 44111/57600 [7:45:20<2:24:25,  1.56it/s]
 77%|███████▋  | 44112/57600 [7:45:20<2:22:36,  1.58it/s]
 77%|███████▋  | 44113/57600 [7:45:21<2:21:10,  1.59it/s]
 77%|███████▋  | 44114/57600 [7:45:22<2:23:23,  1.57it/s]
 77%|███████▋  | 44115/57600 [7:45:22<2:29:43,  1.50it/s]
 77%|███████▋  | 44116/57600 [7:45:23<2:23:50,  1.56it/s]
 77%|███████▋  | 44117/57600 [7:45:24<2:23:56,  1.56it/s]
 77%|███████▋  | 44118/57600 [7:45:24<2:24:50,  1.55it/s]
 77%|███████▋  | 44119/57600 [7:45:25<2:22:21,  1.58it/s]
 77%|███████▋  | 44120/57600 [7:45:25<2:18:57,  1.62it/s]
                                                         
{'loss': 1.1118, 'learning_rate': 3.113588850174216e-07, 'epoch': 486.98}

 77%|███████▋  | 44120/57600 [7:45:25<2:18:57,  1.62it/s]
 77%|███████▋  | 44121/57600 [7:45:26<2:18:30,  1.62it/s]
 77%|███████▋  | 44122/57600 [7:45:27<2:18:42,  1.62it/s]
 77%|███████▋  | 44123/57600 [7:45:27<2:22:32,  1.58it/s]
 77%|███████▋  | 44124/57600 [7:45:28<2:25:08,  1.55it/s]
 77%|███████▋  | 44125/57600 [7:45:29<2:24:49,  1.55it/s]
 77%|███████▋  | 44126/57600 [7:45:29<2:24:46,  1.55it/s]
 77%|███████▋  | 44127/57600 [7:45:30<2:29:39,  1.50it/s]
 77%|███████▋  | 44128/57600 [7:45:31<2:25:12,  1.55it/s]
 77%|███████▋  | 44129/57600 [7:45:31<2:26:19,  1.53it/s]
 77%|███████▋  | 44130/57600 [7:45:32<2:23:53,  1.56it/s]
 77%|███████▋  | 44131/57600 [7:45:33<2:28:04,  1.52it/s]
 77%|███████▋  | 44132/57600 [7:45:33<2:28:14,  1.51it/s]
 77%|███████▋  | 44133/57600 [7:45:34<2:26:00,  1.54it/s]
 77%|███████▋  | 44134/57600 [7:45:34<2:23:07,  1.57it/s]
 77%|███████▋  | 44135/57600 [7:45:35<2:24:44,  1.55it/s]
 77%|███████▋  | 44136/57600 [7:45:36<2:26:50,  1.53it/s]
 77%|███████▋  | 44137/57600 [7:45:36<2:23:56,  1.56it/s]
 77%|███████▋  | 44138/57600 [7:45:37<2:26:14,  1.53it/s]
 77%|███████▋  | 44139/57600 [7:45:38<2:21:18,  1.59it/s]
 77%|███████▋  | 44140/57600 [7:45:38<2:17:42,  1.63it/s]
                                                         
{'loss': 1.1265, 'learning_rate': 3.1104529616724745e-07, 'epoch': 487.2}

 77%|███████▋  | 44140/57600 [7:45:38<2:17:42,  1.63it/s]
 77%|███████▋  | 44141/57600 [7:45:39<2:18:31,  1.62it/s]
 77%|███████▋  | 44142/57600 [7:45:39<2:19:05,  1.61it/s]
 77%|███████▋  | 44143/57600 [7:45:40<2:19:04,  1.61it/s]
 77%|███████▋  | 44144/57600 [7:45:41<2:17:47,  1.63it/s]
 77%|███████▋  | 44145/57600 [7:45:41<2:16:30,  1.64it/s]
 77%|███████▋  | 44146/57600 [7:45:42<2:15:50,  1.65it/s]
 77%|███████▋  | 44147/57600 [7:45:43<2:18:30,  1.62it/s]
 77%|███████▋  | 44148/57600 [7:45:43<2:22:04,  1.58it/s]
 77%|███████▋  | 44149/57600 [7:45:44<2:17:50,  1.63it/s]
 77%|███████▋  | 44150/57600 [7:45:44<2:20:29,  1.60it/s]
 77%|███████▋  | 44151/57600 [7:45:45<2:17:57,  1.62it/s]
 77%|███████▋  | 44152/57600 [7:45:46<2:16:56,  1.64it/s]
 77%|███████▋  | 44153/57600 [7:45:46<2:21:08,  1.59it/s]
 77%|███████▋  | 44154/57600 [7:45:47<2:19:25,  1.61it/s]
 77%|███████▋  | 44155/57600 [7:45:47<2:17:49,  1.63it/s]
 77%|███████▋  | 44156/57600 [7:45:48<2:24:49,  1.55it/s]
 77%|███████▋  | 44157/57600 [7:45:49<2:18:30,  1.62it/s]
 77%|███████▋  | 44158/57600 [7:45:49<2:20:05,  1.60it/s]
 77%|███████▋  | 44159/57600 [7:45:50<2:16:48,  1.64it/s]
 77%|███████▋  | 44160/57600 [7:45:51<2:21:30,  1.58it/s]
                                                         
{'loss': 1.1465, 'learning_rate': 3.1073170731707315e-07, 'epoch': 487.42}

 77%|███████▋  | 44160/57600 [7:45:51<2:21:30,  1.58it/s]
 77%|███████▋  | 44161/57600 [7:45:51<2:23:12,  1.56it/s]
 77%|███████▋  | 44162/57600 [7:45:52<2:20:14,  1.60it/s]
 77%|███████▋  | 44163/57600 [7:45:53<2:20:13,  1.60it/s]
 77%|███████▋  | 44164/57600 [7:45:53<2:23:24,  1.56it/s]
 77%|███████▋  | 44165/57600 [7:45:54<2:19:48,  1.60it/s]
 77%|███████▋  | 44166/57600 [7:45:54<2:18:27,  1.62it/s]
 77%|███████▋  | 44167/57600 [7:45:55<2:19:37,  1.60it/s]
 77%|███████▋  | 44168/57600 [7:45:56<2:18:24,  1.62it/s]
 77%|███████▋  | 44169/57600 [7:45:56<2:18:29,  1.62it/s]
 77%|███████▋  | 44170/57600 [7:45:57<2:21:51,  1.58it/s]
 77%|███████▋  | 44171/57600 [7:45:58<2:18:59,  1.61it/s]
 77%|███████▋  | 44172/57600 [7:45:58<2:17:43,  1.62it/s]
 77%|███████▋  | 44173/57600 [7:45:59<2:16:56,  1.63it/s]
 77%|███████▋  | 44174/57600 [7:45:59<2:17:48,  1.62it/s]
 77%|███████▋  | 44175/57600 [7:46:00<2:17:55,  1.62it/s]
 77%|███████▋  | 44176/57600 [7:46:01<2:22:26,  1.57it/s]
 77%|███████▋  | 44177/57600 [7:46:01<2:20:13,  1.60it/s]
 77%|███████▋  | 44178/57600 [7:46:02<2:23:45,  1.56it/s]
 77%|███████▋  | 44179/57600 [7:46:03<2:21:08,  1.58it/s]
 77%|███████▋  | 44180/57600 [7:46:03<2:20:49,  1.59it/s]
                                                         
{'loss': 1.1336, 'learning_rate': 3.1041811846689896e-07, 'epoch': 487.64}

 77%|███████▋  | 44180/57600 [7:46:03<2:20:49,  1.59it/s]
 77%|███████▋  | 44181/57600 [7:46:04<2:15:08,  1.66it/s]
 77%|███████▋  | 44182/57600 [7:46:04<2:16:17,  1.64it/s]
 77%|███████▋  | 44183/57600 [7:46:05<2:15:41,  1.65it/s]
 77%|███████▋  | 44184/57600 [7:46:06<2:17:01,  1.63it/s]
 77%|███████▋  | 44185/57600 [7:46:06<2:17:08,  1.63it/s]
 77%|███████▋  | 44186/57600 [7:46:07<2:21:24,  1.58it/s]
 77%|███████▋  | 44187/57600 [7:46:07<2:20:08,  1.60it/s]
 77%|███████▋  | 44188/57600 [7:46:08<2:17:56,  1.62it/s]
 77%|███████▋  | 44189/57600 [7:46:09<2:21:27,  1.58it/s]
 77%|███████▋  | 44190/57600 [7:46:09<2:18:35,  1.61it/s]
 77%|███████▋  | 44191/57600 [7:46:10<2:16:14,  1.64it/s]
 77%|███████▋  | 44192/57600 [7:46:11<2:15:28,  1.65it/s]
 77%|███████▋  | 44193/57600 [7:46:11<2:14:48,  1.66it/s]
 77%|███████▋  | 44194/57600 [7:46:12<2:17:27,  1.63it/s]
 77%|███████▋  | 44195/57600 [7:46:12<2:20:09,  1.59it/s]
 77%|███████▋  | 44196/57600 [7:46:13<2:23:24,  1.56it/s]
 77%|███████▋  | 44197/57600 [7:46:14<2:24:32,  1.55it/s]
 77%|███████▋  | 44198/57600 [7:46:14<2:23:06,  1.56it/s]
 77%|███████▋  | 44199/57600 [7:46:15<2:20:15,  1.59it/s]
 77%|███████▋  | 44200/57600 [7:46:16<2:19:44,  1.60it/s]
                                                         
{'loss': 1.1667, 'learning_rate': 3.101045296167247e-07, 'epoch': 487.86}

 77%|███████▋  | 44200/57600 [7:46:16<2:19:44,  1.60it/s]
 77%|███████▋  | 44201/57600 [7:46:16<2:20:08,  1.59it/s]
 77%|███████▋  | 44202/57600 [7:46:17<2:19:52,  1.60it/s]
 77%|███████▋  | 44203/57600 [7:46:17<2:17:52,  1.62it/s]
 77%|███████▋  | 44204/57600 [7:46:18<2:20:15,  1.59it/s]
 77%|███████▋  | 44205/57600 [7:46:19<2:19:20,  1.60it/s]
 77%|███████▋  | 44206/57600 [7:46:19<2:23:46,  1.55it/s]
 77%|███████▋  | 44207/57600 [7:46:20<2:22:04,  1.57it/s]
 77%|███████▋  | 44208/57600 [7:46:21<2:23:50,  1.55it/s]
 77%|███████▋  | 44209/57600 [7:46:21<2:21:24,  1.58it/s]
 77%|███████▋  | 44210/57600 [7:46:22<2:19:53,  1.60it/s]
 77%|███████▋  | 44211/57600 [7:46:23<2:22:47,  1.56it/s]
 77%|███████▋  | 44212/57600 [7:46:23<2:19:00,  1.61it/s]
 77%|███████▋  | 44213/57600 [7:46:24<2:23:54,  1.55it/s]
 77%|███████▋  | 44214/57600 [7:46:24<2:21:25,  1.58it/s]
 77%|███████▋  | 44215/57600 [7:46:25<2:17:23,  1.62it/s]
 77%|███████▋  | 44216/57600 [7:46:26<2:19:13,  1.60it/s]
 77%|███████▋  | 44217/57600 [7:46:26<2:21:14,  1.58it/s]
 77%|███████▋  | 44218/57600 [7:46:27<2:14:40,  1.66it/s]
 77%|███████▋  | 44219/57600 [7:46:27<2:11:58,  1.69it/s]
 77%|███████▋  | 44220/57600 [7:46:28<2:16:02,  1.64it/s]
                                                         
{'loss': 1.1588, 'learning_rate': 3.097909407665505e-07, 'epoch': 488.08}

 77%|███████▋  | 44220/57600 [7:46:28<2:16:02,  1.64it/s]
 77%|███████▋  | 44221/57600 [7:46:29<2:21:27,  1.58it/s]
 77%|███████▋  | 44222/57600 [7:46:30<2:29:35,  1.49it/s]
 77%|███████▋  | 44223/57600 [7:46:30<2:24:04,  1.55it/s]
 77%|███████▋  | 44224/57600 [7:46:31<2:22:59,  1.56it/s]
 77%|███████▋  | 44225/57600 [7:46:31<2:23:33,  1.55it/s]
 77%|███████▋  | 44226/57600 [7:46:32<2:25:53,  1.53it/s]
 77%|███████▋  | 44227/57600 [7:46:33<2:21:39,  1.57it/s]
 77%|███████▋  | 44228/57600 [7:46:33<2:21:02,  1.58it/s]
 77%|███████▋  | 44229/57600 [7:46:34<2:20:17,  1.59it/s]
 77%|███████▋  | 44230/57600 [7:46:35<2:19:39,  1.60it/s]
 77%|███████▋  | 44231/57600 [7:46:35<2:25:05,  1.54it/s]
 77%|███████▋  | 44232/57600 [7:46:36<2:23:52,  1.55it/s]
 77%|███████▋  | 44233/57600 [7:46:37<2:26:57,  1.52it/s]
 77%|███████▋  | 44234/57600 [7:46:37<2:23:14,  1.56it/s]
 77%|███████▋  | 44235/57600 [7:46:38<2:24:48,  1.54it/s]
 77%|███████▋  | 44236/57600 [7:46:38<2:23:12,  1.56it/s]
 77%|███████▋  | 44237/57600 [7:46:39<2:21:31,  1.57it/s]
 77%|███████▋  | 44238/57600 [7:46:40<2:17:46,  1.62it/s]
 77%|███████▋  | 44239/57600 [7:46:40<2:17:18,  1.62it/s]
 77%|███████▋  | 44240/57600 [7:46:41<2:20:32,  1.58it/s]
                                                         
{'loss': 1.096, 'learning_rate': 3.094773519163762e-07, 'epoch': 488.3}

 77%|███████▋  | 44240/57600 [7:46:41<2:20:32,  1.58it/s]
 77%|███████▋  | 44241/57600 [7:46:42<2:17:33,  1.62it/s]
 77%|███████▋  | 44242/57600 [7:46:42<2:14:17,  1.66it/s]
 77%|███████▋  | 44243/57600 [7:46:43<2:13:50,  1.66it/s]
 77%|███████▋  | 44244/57600 [7:46:43<2:13:25,  1.67it/s]
 77%|███████▋  | 44245/57600 [7:46:44<2:18:22,  1.61it/s]
 77%|███████▋  | 44246/57600 [7:46:45<2:24:00,  1.55it/s]
 77%|███████▋  | 44247/57600 [7:46:45<2:22:09,  1.57it/s]
 77%|███████▋  | 44248/57600 [7:46:46<2:20:33,  1.58it/s]
 77%|███████▋  | 44249/57600 [7:46:47<2:19:03,  1.60it/s]
 77%|███████▋  | 44250/57600 [7:46:47<2:17:29,  1.62it/s]
 77%|███████▋  | 44251/57600 [7:46:48<2:12:59,  1.67it/s]
 77%|███████▋  | 44252/57600 [7:46:48<2:13:39,  1.66it/s]
 77%|███████▋  | 44253/57600 [7:46:49<2:14:07,  1.66it/s]
 77%|███████▋  | 44254/57600 [7:46:50<2:21:20,  1.57it/s]
 77%|███████▋  | 44255/57600 [7:46:50<2:20:05,  1.59it/s]
 77%|███████▋  | 44256/57600 [7:46:51<2:19:56,  1.59it/s]
 77%|███████▋  | 44257/57600 [7:46:51<2:18:12,  1.61it/s]
 77%|███████▋  | 44258/57600 [7:46:52<2:17:14,  1.62it/s]
 77%|███████▋  | 44259/57600 [7:46:53<2:20:45,  1.58it/s]
 77%|███████▋  | 44260/57600 [7:46:53<2:19:30,  1.59it/s]
                                                         
{'loss': 1.1389, 'learning_rate': 3.0916376306620207e-07, 'epoch': 488.52}

 77%|███████▋  | 44260/57600 [7:46:53<2:19:30,  1.59it/s]
 77%|███████▋  | 44261/57600 [7:46:54<2:23:14,  1.55it/s]
 77%|███████▋  | 44262/57600 [7:46:55<2:20:22,  1.58it/s]
 77%|███████▋  | 44263/57600 [7:46:55<2:19:48,  1.59it/s]
 77%|███████▋  | 44264/57600 [7:46:56<2:24:27,  1.54it/s]
 77%|███████▋  | 44265/57600 [7:46:57<2:22:32,  1.56it/s]
 77%|███████▋  | 44266/57600 [7:46:57<2:23:21,  1.55it/s]
 77%|███████▋  | 44267/57600 [7:46:58<2:27:01,  1.51it/s]
 77%|███████▋  | 44268/57600 [7:46:59<2:26:38,  1.52it/s]
 77%|███████▋  | 44269/57600 [7:46:59<2:23:09,  1.55it/s]
 77%|███████▋  | 44270/57600 [7:47:00<2:24:17,  1.54it/s]
 77%|███████▋  | 44271/57600 [7:47:00<2:21:21,  1.57it/s]
 77%|███████▋  | 44272/57600 [7:47:01<2:19:22,  1.59it/s]
 77%|███████▋  | 44273/57600 [7:47:02<2:20:49,  1.58it/s]
 77%|███████▋  | 44274/57600 [7:47:02<2:22:19,  1.56it/s]
 77%|███████▋  | 44275/57600 [7:47:03<2:19:02,  1.60it/s]
 77%|███████▋  | 44276/57600 [7:47:04<2:15:47,  1.64it/s]
 77%|███████▋  | 44277/57600 [7:47:04<2:17:17,  1.62it/s]
 77%|███████▋  | 44278/57600 [7:47:05<2:18:01,  1.61it/s]
 77%|███████▋  | 44279/57600 [7:47:05<2:18:55,  1.60it/s]
 77%|███████▋  | 44280/57600 [7:47:06<2:18:56,  1.60it/s]
                                                         
{'loss': 1.1224, 'learning_rate': 3.0885017421602793e-07, 'epoch': 488.74}

 77%|███████▋  | 44280/57600 [7:47:06<2:18:56,  1.60it/s]
 77%|███████▋  | 44281/57600 [7:47:07<2:18:12,  1.61it/s]
 77%|███████▋  | 44282/57600 [7:47:07<2:20:35,  1.58it/s]
 77%|███████▋  | 44283/57600 [7:47:08<2:18:59,  1.60it/s]
 77%|███████▋  | 44284/57600 [7:47:09<2:19:57,  1.59it/s]
 77%|███████▋  | 44285/57600 [7:47:09<2:19:31,  1.59it/s]
 77%|███████▋  | 44286/57600 [7:47:10<2:19:27,  1.59it/s]
 77%|███████▋  | 44287/57600 [7:47:10<2:15:37,  1.64it/s]
 77%|███████▋  | 44288/57600 [7:47:11<2:17:09,  1.62it/s]
 77%|███████▋  | 44289/57600 [7:47:12<2:13:41,  1.66it/s]
 77%|███████▋  | 44290/57600 [7:47:12<2:16:25,  1.63it/s]
 77%|███████▋  | 44291/57600 [7:47:13<2:13:32,  1.66it/s]
 77%|███████▋  | 44292/57600 [7:47:13<2:14:19,  1.65it/s]
 77%|███████▋  | 44293/57600 [7:47:14<2:17:31,  1.61it/s]
 77%|███████▋  | 44294/57600 [7:47:15<2:12:57,  1.67it/s]
 77%|███████▋  | 44295/57600 [7:47:15<2:20:52,  1.57it/s]
 77%|███████▋  | 44296/57600 [7:47:16<2:21:54,  1.56it/s]
 77%|███████▋  | 44297/57600 [7:47:17<2:17:55,  1.61it/s]
 77%|███████▋  | 44298/57600 [7:47:17<2:14:46,  1.64it/s]
 77%|███████▋  | 44299/57600 [7:47:18<2:15:17,  1.64it/s]
 77%|███████▋  | 44300/57600 [7:47:18<2:12:22,  1.67it/s]
                                                         
{'loss': 1.1364, 'learning_rate': 3.0853658536585363e-07, 'epoch': 488.96}

 77%|███████▋  | 44300/57600 [7:47:18<2:12:22,  1.67it/s]
 77%|███████▋  | 44301/57600 [7:47:19<2:15:40,  1.63it/s]
 77%|███████▋  | 44302/57600 [7:47:20<2:12:41,  1.67it/s]
 77%|███████▋  | 44303/57600 [7:47:20<2:16:39,  1.62it/s]
 77%|███████▋  | 44304/57600 [7:47:21<2:23:42,  1.54it/s]
 77%|███████▋  | 44305/57600 [7:47:22<2:21:07,  1.57it/s]
 77%|███████▋  | 44306/57600 [7:47:22<2:19:34,  1.59it/s]
 77%|███████▋  | 44307/57600 [7:47:23<2:20:32,  1.58it/s]
 77%|███████▋  | 44308/57600 [7:47:23<2:17:04,  1.62it/s]
 77%|███████▋  | 44309/57600 [7:47:24<2:13:38,  1.66it/s]
 77%|███████▋  | 44310/57600 [7:47:25<2:12:26,  1.67it/s]
 77%|███████▋  | 44311/57600 [7:47:25<2:15:39,  1.63it/s]
 77%|███████▋  | 44312/57600 [7:47:26<2:12:03,  1.68it/s]
 77%|███████▋  | 44313/57600 [7:47:26<2:14:02,  1.65it/s]
 77%|███████▋  | 44314/57600 [7:47:27<2:17:04,  1.62it/s]
 77%|███████▋  | 44315/57600 [7:47:28<2:17:22,  1.61it/s]
 77%|███████▋  | 44316/57600 [7:47:28<2:16:53,  1.62it/s]
 77%|███████▋  | 44317/57600 [7:47:29<2:16:12,  1.63it/s]
 77%|███████▋  | 44318/57600 [7:47:29<2:17:43,  1.61it/s]
 77%|███████▋  | 44319/57600 [7:47:30<2:15:19,  1.64it/s]
 77%|███████▋  | 44320/57600 [7:47:31<2:13:30,  1.66it/s]
                                                         
{'loss': 1.1456, 'learning_rate': 3.0822299651567943e-07, 'epoch': 489.18}

 77%|███████▋  | 44320/57600 [7:47:31<2:13:30,  1.66it/s]
 77%|███████▋  | 44321/57600 [7:47:31<2:14:05,  1.65it/s]
 77%|███████▋  | 44322/57600 [7:47:32<2:21:54,  1.56it/s]
 77%|███████▋  | 44323/57600 [7:47:33<2:22:38,  1.55it/s]
 77%|███████▋  | 44324/57600 [7:47:33<2:19:49,  1.58it/s]
 77%|███████▋  | 44325/57600 [7:47:34<2:22:08,  1.56it/s]
 77%|███████▋  | 44326/57600 [7:47:35<2:21:46,  1.56it/s]
 77%|███████▋  | 44327/57600 [7:47:35<2:20:10,  1.58it/s]
 77%|███████▋  | 44328/57600 [7:47:36<2:20:44,  1.57it/s]
 77%|███████▋  | 44329/57600 [7:47:36<2:20:24,  1.58it/s]
 77%|███████▋  | 44330/57600 [7:47:37<2:19:46,  1.58it/s]
 77%|███████▋  | 44331/57600 [7:47:38<2:24:34,  1.53it/s]
 77%|███████▋  | 44332/57600 [7:47:38<2:22:09,  1.56it/s]
 77%|███████▋  | 44333/57600 [7:47:39<2:18:19,  1.60it/s]
 77%|███████▋  | 44334/57600 [7:47:40<2:19:06,  1.59it/s]
 77%|███████▋  | 44335/57600 [7:47:40<2:21:01,  1.57it/s]
 77%|███████▋  | 44336/57600 [7:47:41<2:20:38,  1.57it/s]
 77%|███████▋  | 44337/57600 [7:47:42<2:20:31,  1.57it/s]
 77%|███████▋  | 44338/57600 [7:47:42<2:19:43,  1.58it/s]
 77%|███████▋  | 44339/57600 [7:47:43<2:19:44,  1.58it/s]
 77%|███████▋  | 44340/57600 [7:47:43<2:20:32,  1.57it/s]
                                                         
{'loss': 1.1101, 'learning_rate': 3.079094076655052e-07, 'epoch': 489.4}

 77%|███████▋  | 44340/57600 [7:47:43<2:20:32,  1.57it/s]
 77%|███████▋  | 44341/57600 [7:47:44<2:21:08,  1.57it/s]
 77%|███████▋  | 44342/57600 [7:47:45<2:22:13,  1.55it/s]
 77%|███████▋  | 44343/57600 [7:47:45<2:24:24,  1.53it/s]
 77%|███████▋  | 44344/57600 [7:47:46<2:26:26,  1.51it/s]
 77%|███████▋  | 44345/57600 [7:47:47<2:22:36,  1.55it/s]
 77%|███████▋  | 44346/57600 [7:47:47<2:18:18,  1.60it/s]
 77%|███████▋  | 44347/57600 [7:47:48<2:18:30,  1.59it/s]
 77%|███████▋  | 44348/57600 [7:47:48<2:13:59,  1.65it/s]
 77%|███████▋  | 44349/57600 [7:47:49<2:13:01,  1.66it/s]
 77%|███████▋  | 44350/57600 [7:47:50<2:13:26,  1.65it/s]
 77%|███████▋  | 44351/57600 [7:47:50<2:14:26,  1.64it/s]
 77%|███████▋  | 44352/57600 [7:47:51<2:17:02,  1.61it/s]
 77%|███████▋  | 44353/57600 [7:47:52<2:17:14,  1.61it/s]
 77%|███████▋  | 44354/57600 [7:47:52<2:15:36,  1.63it/s]
 77%|███████▋  | 44355/57600 [7:47:53<2:15:51,  1.62it/s]
 77%|███████▋  | 44356/57600 [7:47:53<2:14:16,  1.64it/s]
 77%|███████▋  | 44357/57600 [7:47:54<2:15:35,  1.63it/s]
 77%|███████▋  | 44358/57600 [7:47:55<2:15:54,  1.62it/s]
 77%|███████▋  | 44359/57600 [7:47:55<2:19:07,  1.59it/s]
 77%|███████▋  | 44360/57600 [7:47:56<2:19:29,  1.58it/s]
                                                         
{'loss': 1.1395, 'learning_rate': 3.0759581881533104e-07, 'epoch': 489.62}

 77%|███████▋  | 44360/57600 [7:47:56<2:19:29,  1.58it/s]
 77%|███████▋  | 44361/57600 [7:47:57<2:22:47,  1.55it/s]
 77%|███████▋  | 44362/57600 [7:47:57<2:21:28,  1.56it/s]
 77%|███████▋  | 44363/57600 [7:47:58<2:18:06,  1.60it/s]
 77%|███████▋  | 44364/57600 [7:47:58<2:16:50,  1.61it/s]
 77%|███████▋  | 44365/57600 [7:47:59<2:16:22,  1.62it/s]
 77%|███████▋  | 44366/57600 [7:48:00<2:18:56,  1.59it/s]
 77%|███████▋  | 44367/57600 [7:48:00<2:19:52,  1.58it/s]
 77%|███████▋  | 44368/57600 [7:48:01<2:19:00,  1.59it/s]
 77%|███████▋  | 44369/57600 [7:48:02<2:20:48,  1.57it/s]
 77%|███████▋  | 44370/57600 [7:48:02<2:18:58,  1.59it/s]
 77%|███████▋  | 44371/57600 [7:48:03<2:22:14,  1.55it/s]
 77%|███████▋  | 44372/57600 [7:48:04<2:20:38,  1.57it/s]
 77%|███████▋  | 44373/57600 [7:48:04<2:20:23,  1.57it/s]
 77%|███████▋  | 44374/57600 [7:48:05<2:18:12,  1.59it/s]
 77%|███████▋  | 44375/57600 [7:48:05<2:17:20,  1.60it/s]
 77%|███████▋  | 44376/57600 [7:48:06<2:17:53,  1.60it/s]
 77%|███████▋  | 44377/57600 [7:48:07<2:16:29,  1.61it/s]
 77%|███████▋  | 44378/57600 [7:48:07<2:13:54,  1.65it/s]
 77%|███████▋  | 44379/57600 [7:48:08<2:15:15,  1.63it/s]
 77%|███████▋  | 44380/57600 [7:48:08<2:17:01,  1.61it/s]
                                                         
{'loss': 1.1361, 'learning_rate': 3.0728222996515674e-07, 'epoch': 489.85}

 77%|███████▋  | 44380/57600 [7:48:08<2:17:01,  1.61it/s]
 77%|███████▋  | 44381/57600 [7:48:09<2:17:32,  1.60it/s]
 77%|███████▋  | 44382/57600 [7:48:10<2:15:07,  1.63it/s]
 77%|███████▋  | 44383/57600 [7:48:10<2:17:57,  1.60it/s]
 77%|███████▋  | 44384/57600 [7:48:11<2:19:40,  1.58it/s]
 77%|███████▋  | 44385/57600 [7:48:12<2:16:37,  1.61it/s]
 77%|███████▋  | 44386/57600 [7:48:12<2:15:02,  1.63it/s]
 77%|███████▋  | 44387/57600 [7:48:13<2:15:33,  1.62it/s]
 77%|███████▋  | 44388/57600 [7:48:13<2:17:07,  1.61it/s]
 77%|███████▋  | 44389/57600 [7:48:14<2:18:46,  1.59it/s]
 77%|███████▋  | 44390/57600 [7:48:15<2:21:47,  1.55it/s]
 77%|███████▋  | 44391/57600 [7:48:15<2:23:19,  1.54it/s]
 77%|███████▋  | 44392/57600 [7:48:16<2:19:54,  1.57it/s]
 77%|███████▋  | 44393/57600 [7:48:17<2:21:46,  1.55it/s]
 77%|███████▋  | 44394/57600 [7:48:17<2:18:43,  1.59it/s]
 77%|███████▋  | 44395/57600 [7:48:18<2:20:32,  1.57it/s]
 77%|███████▋  | 44396/57600 [7:48:19<2:18:17,  1.59it/s]
 77%|███████▋  | 44397/57600 [7:48:19<2:17:06,  1.60it/s]
 77%|███████▋  | 44398/57600 [7:48:20<2:17:53,  1.60it/s]
 77%|███████▋  | 44399/57600 [7:48:20<2:17:10,  1.60it/s]
 77%|███████▋  | 44400/57600 [7:48:21<2:18:09,  1.59it/s]
                                                         
{'loss': 1.1494, 'learning_rate': 3.0696864111498255e-07, 'epoch': 490.07}

 77%|███████▋  | 44400/57600 [7:48:21<2:18:09,  1.59it/s]
 77%|███████▋  | 44401/57600 [7:48:22<2:18:21,  1.59it/s]
 77%|███████▋  | 44402/57600 [7:48:22<2:19:29,  1.58it/s]
 77%|███████▋  | 44403/57600 [7:48:23<2:17:29,  1.60it/s]
 77%|███████▋  | 44404/57600 [7:48:24<2:20:03,  1.57it/s]
 77%|███████▋  | 44405/57600 [7:48:24<2:16:09,  1.62it/s]
 77%|███████▋  | 44406/57600 [7:48:25<2:15:10,  1.63it/s]
 77%|███████▋  | 44407/57600 [7:48:25<2:17:54,  1.59it/s]
 77%|███████▋  | 44408/57600 [7:48:26<2:17:56,  1.59it/s]
 77%|███████▋  | 44409/57600 [7:48:27<2:21:27,  1.55it/s]
 77%|███████▋  | 44410/57600 [7:48:27<2:19:44,  1.57it/s]
 77%|███████▋  | 44411/57600 [7:48:28<2:22:04,  1.55it/s]
 77%|███████▋  | 44412/57600 [7:48:29<2:22:50,  1.54it/s]
 77%|███████▋  | 44413/57600 [7:48:29<2:21:23,  1.55it/s]
 77%|███████▋  | 44414/57600 [7:48:30<2:17:51,  1.59it/s]
 77%|███████▋  | 44415/57600 [7:48:31<2:13:58,  1.64it/s]
 77%|███████▋  | 44416/57600 [7:48:31<2:15:10,  1.63it/s]
 77%|███████▋  | 44417/57600 [7:48:32<2:17:50,  1.59it/s]
 77%|███████▋  | 44418/57600 [7:48:32<2:18:59,  1.58it/s]
 77%|███████▋  | 44419/57600 [7:48:33<2:17:04,  1.60it/s]
 77%|███████▋  | 44420/57600 [7:48:34<2:16:15,  1.61it/s]
                                                         
{'loss': 1.1222, 'learning_rate': 3.066550522648084e-07, 'epoch': 490.29}

 77%|███████▋  | 44420/57600 [7:48:34<2:16:15,  1.61it/s]
 77%|███████▋  | 44421/57600 [7:48:34<2:17:41,  1.60it/s]
 77%|███████▋  | 44422/57600 [7:48:35<2:16:04,  1.61it/s]
 77%|███████▋  | 44423/57600 [7:48:36<2:16:02,  1.61it/s]
 77%|███████▋  | 44424/57600 [7:48:36<2:15:39,  1.62it/s]
 77%|███████▋  | 44425/57600 [7:48:37<2:18:21,  1.59it/s]
 77%|███████▋  | 44426/57600 [7:48:37<2:13:27,  1.65it/s]
 77%|███████▋  | 44427/57600 [7:48:38<2:14:31,  1.63it/s]
 77%|███████▋  | 44428/57600 [7:48:39<2:16:30,  1.61it/s]
 77%|███████▋  | 44429/57600 [7:48:39<2:13:43,  1.64it/s]
 77%|███████▋  | 44430/57600 [7:48:40<2:20:53,  1.56it/s]
 77%|███████▋  | 44431/57600 [7:48:40<2:17:52,  1.59it/s]
 77%|███████▋  | 44432/57600 [7:48:41<2:17:30,  1.60it/s]
 77%|███████▋  | 44433/57600 [7:48:42<2:19:05,  1.58it/s]
 77%|███████▋  | 44434/57600 [7:48:42<2:17:20,  1.60it/s]
 77%|███████▋  | 44435/57600 [7:48:43<2:20:07,  1.57it/s]
 77%|███████▋  | 44436/57600 [7:48:44<2:16:58,  1.60it/s]
 77%|███████▋  | 44437/57600 [7:48:44<2:17:53,  1.59it/s]
 77%|███████▋  | 44438/57600 [7:48:45<2:19:19,  1.57it/s]
 77%|███████▋  | 44439/57600 [7:48:46<2:17:14,  1.60it/s]
 77%|███████▋  | 44440/57600 [7:48:46<2:15:00,  1.62it/s]
                                                         
{'loss': 1.1303, 'learning_rate': 3.063414634146341e-07, 'epoch': 490.51}

 77%|███████▋  | 44440/57600 [7:48:46<2:15:00,  1.62it/s]
 77%|███████▋  | 44441/57600 [7:48:47<2:14:56,  1.63it/s]
 77%|███████▋  | 44442/57600 [7:48:47<2:22:41,  1.54it/s]
 77%|███████▋  | 44443/57600 [7:48:48<2:24:48,  1.51it/s]
 77%|███████▋  | 44444/57600 [7:48:49<2:22:15,  1.54it/s]
 77%|███████▋  | 44445/57600 [7:48:49<2:22:40,  1.54it/s]
 77%|███████▋  | 44446/57600 [7:48:50<2:22:56,  1.53it/s]
 77%|███████▋  | 44447/57600 [7:48:51<2:27:15,  1.49it/s]
 77%|███████▋  | 44448/57600 [7:48:51<2:24:50,  1.51it/s]
 77%|███████▋  | 44449/57600 [7:48:52<2:23:30,  1.53it/s]
 77%|███████▋  | 44450/57600 [7:48:53<2:21:58,  1.54it/s]
 77%|███████▋  | 44451/57600 [7:48:53<2:20:49,  1.56it/s]
 77%|███████▋  | 44452/57600 [7:48:54<2:19:34,  1.57it/s]
 77%|███████▋  | 44453/57600 [7:48:55<2:19:45,  1.57it/s]
 77%|███████▋  | 44454/57600 [7:48:55<2:24:16,  1.52it/s]
 77%|███████▋  | 44455/57600 [7:48:56<2:24:01,  1.52it/s]
 77%|███████▋  | 44456/57600 [7:48:57<2:21:08,  1.55it/s]
 77%|███████▋  | 44457/57600 [7:48:57<2:20:58,  1.55it/s]
 77%|███████▋  | 44458/57600 [7:48:58<2:28:16,  1.48it/s]
 77%|███████▋  | 44459/57600 [7:48:59<2:23:47,  1.52it/s]
 77%|███████▋  | 44460/57600 [7:48:59<2:25:43,  1.50it/s]
                                                         
{'loss': 1.095, 'learning_rate': 3.060278745644599e-07, 'epoch': 490.73}

 77%|███████▋  | 44460/57600 [7:48:59<2:25:43,  1.50it/s]
 77%|███████▋  | 44461/57600 [7:49:00<2:22:00,  1.54it/s]
 77%|███████▋  | 44462/57600 [7:49:01<2:26:02,  1.50it/s]
 77%|███████▋  | 44463/57600 [7:49:01<2:28:03,  1.48it/s]
 77%|███████▋  | 44464/57600 [7:49:02<2:26:33,  1.49it/s]
 77%|███████▋  | 44465/57600 [7:49:03<2:25:01,  1.51it/s]
 77%|███████▋  | 44466/57600 [7:49:03<2:22:14,  1.54it/s]
 77%|███████▋  | 44467/57600 [7:49:04<2:18:20,  1.58it/s]
 77%|███████▋  | 44468/57600 [7:49:04<2:16:15,  1.61it/s]
 77%|███████▋  | 44469/57600 [7:49:05<2:14:21,  1.63it/s]
 77%|███████▋  | 44470/57600 [7:49:06<2:10:46,  1.67it/s]
 77%|███████▋  | 44471/57600 [7:49:06<2:14:18,  1.63it/s]
 77%|███████▋  | 44472/57600 [7:49:07<2:12:26,  1.65it/s]
 77%|███████▋  | 44473/57600 [7:49:07<2:10:58,  1.67it/s]
 77%|███████▋  | 44474/57600 [7:49:08<2:10:27,  1.68it/s]
 77%|███████▋  | 44475/57600 [7:49:09<2:12:23,  1.65it/s]
 77%|███████▋  | 44476/57600 [7:49:09<2:12:45,  1.65it/s]
 77%|███████▋  | 44477/57600 [7:49:10<2:13:02,  1.64it/s]
 77%|███████▋  | 44478/57600 [7:49:10<2:13:28,  1.64it/s]
 77%|███████▋  | 44479/57600 [7:49:11<2:12:02,  1.66it/s]
 77%|███████▋  | 44480/57600 [7:49:12<2:12:24,  1.65it/s]
                                                         
{'loss': 1.1407, 'learning_rate': 3.0571428571428566e-07, 'epoch': 490.95}

 77%|███████▋  | 44480/57600 [7:49:12<2:12:24,  1.65it/s]
 77%|███████▋  | 44481/57600 [7:49:12<2:13:05,  1.64it/s]
 77%|███████▋  | 44482/57600 [7:49:13<2:13:32,  1.64it/s]
 77%|███████▋  | 44483/57600 [7:49:13<2:12:48,  1.65it/s]
 77%|███████▋  | 44484/57600 [7:49:14<2:13:42,  1.63it/s]
 77%|███████▋  | 44485/57600 [7:49:15<2:17:18,  1.59it/s]
 77%|███████▋  | 44486/57600 [7:49:15<2:18:51,  1.57it/s]
 77%|███████▋  | 44487/57600 [7:49:16<2:18:30,  1.58it/s]
 77%|███████▋  | 44488/57600 [7:49:17<2:15:43,  1.61it/s]
 77%|███████▋  | 44489/57600 [7:49:17<2:12:30,  1.65it/s]
 77%|███████▋  | 44490/57600 [7:49:18<2:10:56,  1.67it/s]
 77%|███████▋  | 44491/57600 [7:49:18<2:08:38,  1.70it/s]
 77%|███████▋  | 44492/57600 [7:49:19<2:06:28,  1.73it/s]
 77%|███████▋  | 44493/57600 [7:49:20<2:09:29,  1.69it/s]
 77%|███████▋  | 44494/57600 [7:49:20<2:13:27,  1.64it/s]
 77%|███████▋  | 44495/57600 [7:49:21<2:13:05,  1.64it/s]
 77%|███████▋  | 44496/57600 [7:49:21<2:16:39,  1.60it/s]
 77%|███████▋  | 44497/57600 [7:49:22<2:17:21,  1.59it/s]
 77%|███████▋  | 44498/57600 [7:49:23<2:15:16,  1.61it/s]
 77%|███████▋  | 44499/57600 [7:49:23<2:16:48,  1.60it/s]
 77%|███████▋  | 44500/57600 [7:49:24<2:23:07,  1.53it/s]
                                                         
{'loss': 1.132, 'learning_rate': 3.054006968641115e-07, 'epoch': 491.17}

 77%|███████▋  | 44500/57600 [7:49:24<2:23:07,  1.53it/s]
 77%|███████▋  | 44501/57600 [7:49:25<2:21:55,  1.54it/s]
 77%|███████▋  | 44502/57600 [7:49:25<2:23:05,  1.53it/s]
 77%|███████▋  | 44503/57600 [7:49:26<2:22:40,  1.53it/s]
 77%|███████▋  | 44504/57600 [7:49:27<2:26:18,  1.49it/s]
 77%|███████▋  | 44505/57600 [7:49:27<2:22:10,  1.54it/s]
 77%|███████▋  | 44506/57600 [7:49:28<2:26:33,  1.49it/s]
 77%|███████▋  | 44507/57600 [7:49:29<2:22:33,  1.53it/s]
 77%|███████▋  | 44508/57600 [7:49:29<2:22:19,  1.53it/s]
 77%|███████▋  | 44509/57600 [7:49:30<2:23:11,  1.52it/s]
 77%|███████▋  | 44510/57600 [7:49:31<2:21:43,  1.54it/s]
 77%|███████▋  | 44511/57600 [7:49:31<2:24:32,  1.51it/s]
 77%|███████▋  | 44512/57600 [7:49:32<2:20:23,  1.55it/s]
 77%|███████▋  | 44513/57600 [7:49:32<2:17:24,  1.59it/s]
 77%|███████▋  | 44514/57600 [7:49:33<2:17:45,  1.58it/s]
 77%|███████▋  | 44515/57600 [7:49:34<2:22:52,  1.53it/s]
 77%|███████▋  | 44516/57600 [7:49:34<2:23:54,  1.52it/s]
 77%|███████▋  | 44517/57600 [7:49:35<2:26:00,  1.49it/s]
 77%|███████▋  | 44518/57600 [7:49:36<2:19:51,  1.56it/s]
 77%|███████▋  | 44519/57600 [7:49:36<2:19:40,  1.56it/s]
 77%|███████▋  | 44520/57600 [7:49:37<2:21:02,  1.55it/s]
                                                         
{'loss': 1.104, 'learning_rate': 3.050871080139372e-07, 'epoch': 491.39}

 77%|███████▋  | 44520/57600 [7:49:37<2:21:02,  1.55it/s]
 77%|███████▋  | 44521/57600 [7:49:38<2:17:19,  1.59it/s]
 77%|███████▋  | 44522/57600 [7:49:38<2:15:11,  1.61it/s]
 77%|███████▋  | 44523/57600 [7:49:39<2:13:13,  1.64it/s]
 77%|███████▋  | 44524/57600 [7:49:39<2:08:21,  1.70it/s]
 77%|███████▋  | 44525/57600 [7:49:40<2:06:13,  1.73it/s]
 77%|███████▋  | 44526/57600 [7:49:41<2:09:36,  1.68it/s]
 77%|███████▋  | 44527/57600 [7:49:41<2:16:06,  1.60it/s]
 77%|███████▋  | 44528/57600 [7:49:42<2:14:13,  1.62it/s]
 77%|███████▋  | 44529/57600 [7:49:42<2:12:03,  1.65it/s]
 77%|███████▋  | 44530/57600 [7:49:43<2:14:49,  1.62it/s]
 77%|███████▋  | 44531/57600 [7:49:44<2:16:56,  1.59it/s]
 77%|███████▋  | 44532/57600 [7:49:44<2:14:53,  1.61it/s]
 77%|███████▋  | 44533/57600 [7:49:45<2:17:22,  1.59it/s]
 77%|███████▋  | 44534/57600 [7:49:46<2:17:50,  1.58it/s]
 77%|███████▋  | 44535/57600 [7:49:46<2:20:08,  1.55it/s]
 77%|███████▋  | 44536/57600 [7:49:47<2:18:58,  1.57it/s]
 77%|███████▋  | 44537/57600 [7:49:48<2:17:15,  1.59it/s]
 77%|███████▋  | 44538/57600 [7:49:48<2:13:49,  1.63it/s]
 77%|███████▋  | 44539/57600 [7:49:49<2:18:06,  1.58it/s]
 77%|███████▋  | 44540/57600 [7:49:49<2:20:42,  1.55it/s]
                                                         
{'loss': 1.121, 'learning_rate': 3.04773519163763e-07, 'epoch': 491.61}

 77%|███████▋  | 44540/57600 [7:49:49<2:20:42,  1.55it/s]
 77%|███████▋  | 44541/57600 [7:49:50<2:20:29,  1.55it/s]
 77%|███████▋  | 44542/57600 [7:49:51<2:22:53,  1.52it/s]
 77%|███████▋  | 44543/57600 [7:49:51<2:17:26,  1.58it/s]
 77%|███████▋  | 44544/57600 [7:49:52<2:16:46,  1.59it/s]
 77%|███████▋  | 44545/57600 [7:49:53<2:22:34,  1.53it/s]
 77%|███████▋  | 44546/57600 [7:49:53<2:17:00,  1.59it/s]
 77%|███████▋  | 44547/57600 [7:49:54<2:18:06,  1.58it/s]
 77%|███████▋  | 44548/57600 [7:49:55<2:16:13,  1.60it/s]
 77%|███████▋  | 44549/57600 [7:49:55<2:16:22,  1.59it/s]
 77%|███████▋  | 44550/57600 [7:49:56<2:15:32,  1.60it/s]
 77%|███████▋  | 44551/57600 [7:49:56<2:12:29,  1.64it/s]
 77%|███████▋  | 44552/57600 [7:49:57<2:16:53,  1.59it/s]
 77%|███████▋  | 44553/57600 [7:49:58<2:16:52,  1.59it/s]
 77%|███████▋  | 44554/57600 [7:49:58<2:16:46,  1.59it/s]
 77%|███████▋  | 44555/57600 [7:49:59<2:14:28,  1.62it/s]
 77%|███████▋  | 44556/57600 [7:49:59<2:13:55,  1.62it/s]
 77%|███████▋  | 44557/57600 [7:50:00<2:11:13,  1.66it/s]
 77%|███████▋  | 44558/57600 [7:50:01<2:11:04,  1.66it/s]
 77%|███████▋  | 44559/57600 [7:50:01<2:12:32,  1.64it/s]
 77%|███████▋  | 44560/57600 [7:50:02<2:15:01,  1.61it/s]
                                                         
{'loss': 1.1607, 'learning_rate': 3.0445993031358883e-07, 'epoch': 491.83}

 77%|███████▋  | 44560/57600 [7:50:02<2:15:01,  1.61it/s]
 77%|███████▋  | 44561/57600 [7:50:03<2:18:02,  1.57it/s]
 77%|███████▋  | 44562/57600 [7:50:03<2:21:53,  1.53it/s]
 77%|███████▋  | 44563/57600 [7:50:04<2:21:28,  1.54it/s]
 77%|███████▋  | 44564/57600 [7:50:05<2:20:39,  1.54it/s]
 77%|███████▋  | 44565/57600 [7:50:05<2:16:09,  1.60it/s]
 77%|███████▋  | 44566/57600 [7:50:06<2:15:41,  1.60it/s]
 77%|███████▋  | 44567/57600 [7:50:06<2:16:08,  1.60it/s]
 77%|███████▋  | 44568/57600 [7:50:07<2:18:05,  1.57it/s]
 77%|███████▋  | 44569/57600 [7:50:08<2:15:31,  1.60it/s]
 77%|███████▋  | 44570/57600 [7:50:08<2:14:42,  1.61it/s]
 77%|███████▋  | 44571/57600 [7:50:09<2:12:50,  1.63it/s]
 77%|███████▋  | 44572/57600 [7:50:09<2:11:36,  1.65it/s]
 77%|███████▋  | 44573/57600 [7:50:10<2:13:47,  1.62it/s]
 77%|███████▋  | 44574/57600 [7:50:11<2:16:05,  1.60it/s]
 77%|███████▋  | 44575/57600 [7:50:11<2:21:08,  1.54it/s]
 77%|███████▋  | 44576/57600 [7:50:12<2:26:42,  1.48it/s]
 77%|███████▋  | 44577/57600 [7:50:13<2:22:10,  1.53it/s]
 77%|███████▋  | 44578/57600 [7:50:13<2:24:03,  1.51it/s]
 77%|███████▋  | 44579/57600 [7:50:14<2:22:44,  1.52it/s]
 77%|███████▋  | 44580/57600 [7:50:15<2:21:27,  1.53it/s]
                                                         
{'loss': 1.0907, 'learning_rate': 3.0414634146341463e-07, 'epoch': 492.05}

 77%|███████▋  | 44580/57600 [7:50:15<2:21:27,  1.53it/s]
 77%|███████▋  | 44581/57600 [7:50:15<2:20:44,  1.54it/s]
 77%|███████▋  | 44582/57600 [7:50:16<2:19:26,  1.56it/s]
 77%|███████▋  | 44583/57600 [7:50:17<2:19:00,  1.56it/s]
 77%|███████▋  | 44584/57600 [7:50:17<2:20:24,  1.55it/s]
 77%|███████▋  | 44585/57600 [7:50:18<2:15:26,  1.60it/s]
 77%|███████▋  | 44586/57600 [7:50:19<2:15:47,  1.60it/s]
 77%|███████▋  | 44587/57600 [7:50:19<2:15:10,  1.60it/s]
 77%|███████▋  | 44588/57600 [7:50:20<2:14:48,  1.61it/s]
 77%|███████▋  | 44589/57600 [7:50:20<2:19:32,  1.55it/s]
 77%|███████▋  | 44590/57600 [7:50:21<2:17:51,  1.57it/s]
 77%|███████▋  | 44591/57600 [7:50:22<2:14:00,  1.62it/s]
 77%|███████▋  | 44592/57600 [7:50:22<2:16:32,  1.59it/s]
 77%|███████▋  | 44593/57600 [7:50:23<2:17:04,  1.58it/s]
 77%|███████▋  | 44594/57600 [7:50:24<2:17:12,  1.58it/s]
 77%|███████▋  | 44595/57600 [7:50:24<2:21:21,  1.53it/s]
 77%|███████▋  | 44596/57600 [7:50:25<2:20:24,  1.54it/s]
 77%|███████▋  | 44597/57600 [7:50:26<2:19:35,  1.55it/s]
 77%|███████▋  | 44598/57600 [7:50:26<2:16:30,  1.59it/s]
 77%|███████▋  | 44599/57600 [7:50:27<2:17:10,  1.58it/s]
 77%|███████▋  | 44600/57600 [7:50:27<2:17:17,  1.58it/s]
                                                         
{'loss': 1.116, 'learning_rate': 3.0383275261324044e-07, 'epoch': 492.27}

 77%|███████▋  | 44600/57600 [7:50:27<2:17:17,  1.58it/s]
 77%|███████▋  | 44601/57600 [7:50:28<2:15:01,  1.60it/s]
 77%|███████▋  | 44602/57600 [7:50:29<2:12:33,  1.63it/s]
 77%|███████▋  | 44603/57600 [7:50:29<2:12:25,  1.64it/s]
 77%|███████▋  | 44604/57600 [7:50:30<2:11:04,  1.65it/s]
 77%|███████▋  | 44605/57600 [7:50:30<2:11:06,  1.65it/s]
 77%|███████▋  | 44606/57600 [7:50:31<2:16:43,  1.58it/s]
 77%|███████▋  | 44607/57600 [7:50:32<2:15:04,  1.60it/s]
 77%|███████▋  | 44608/57600 [7:50:32<2:19:18,  1.55it/s]
 77%|███████▋  | 44609/57600 [7:50:33<2:20:31,  1.54it/s]
 77%|███████▋  | 44610/57600 [7:50:34<2:26:18,  1.48it/s]
 77%|███████▋  | 44611/57600 [7:50:34<2:21:50,  1.53it/s]
 77%|███████▋  | 44612/57600 [7:50:35<2:19:53,  1.55it/s]
 77%|███████▋  | 44613/57600 [7:50:36<2:18:24,  1.56it/s]
 77%|███████▋  | 44614/57600 [7:50:36<2:16:14,  1.59it/s]
 77%|███████▋  | 44615/57600 [7:50:37<2:13:01,  1.63it/s]
 77%|███████▋  | 44616/57600 [7:50:38<2:15:40,  1.60it/s]
 77%|███████▋  | 44617/57600 [7:50:38<2:19:00,  1.56it/s]
 77%|███████▋  | 44618/57600 [7:50:39<2:15:46,  1.59it/s]
 77%|███████▋  | 44619/57600 [7:50:39<2:14:38,  1.61it/s]
 77%|███████▋  | 44620/57600 [7:50:40<2:16:22,  1.59it/s]
                                                         
{'loss': 1.1573, 'learning_rate': 3.0351916376306614e-07, 'epoch': 492.49}

 77%|███████▋  | 44620/57600 [7:50:40<2:16:22,  1.59it/s]
 77%|███████▋  | 44621/57600 [7:50:41<2:16:40,  1.58it/s]
 77%|███████▋  | 44622/57600 [7:50:41<2:15:56,  1.59it/s]
 77%|███████▋  | 44623/57600 [7:50:42<2:12:46,  1.63it/s]
 77%|███████▋  | 44624/57600 [7:50:43<2:13:32,  1.62it/s]
 77%|███████▋  | 44625/57600 [7:50:43<2:12:46,  1.63it/s]
 77%|███████▋  | 44626/57600 [7:50:44<2:15:23,  1.60it/s]
 77%|███████▋  | 44627/57600 [7:50:44<2:13:17,  1.62it/s]
 77%|███████▋  | 44628/57600 [7:50:45<2:12:43,  1.63it/s]
 77%|███████▋  | 44629/57600 [7:50:46<2:10:33,  1.66it/s]
 77%|███████▋  | 44630/57600 [7:50:46<2:17:24,  1.57it/s]
 77%|███████▋  | 44631/57600 [7:50:47<2:15:25,  1.60it/s]
 77%|███████▋  | 44632/57600 [7:50:47<2:12:09,  1.64it/s]
 77%|███████▋  | 44633/57600 [7:50:48<2:14:36,  1.61it/s]
 77%|███████▋  | 44634/57600 [7:50:49<2:16:59,  1.58it/s]
 77%|███████▋  | 44635/57600 [7:50:49<2:17:16,  1.57it/s]
 77%|███████▋  | 44636/57600 [7:50:50<2:18:34,  1.56it/s]
 77%|███████▋  | 44637/57600 [7:50:51<2:17:57,  1.57it/s]
 77%|███████▋  | 44638/57600 [7:50:51<2:18:30,  1.56it/s]
 77%|███████▋  | 44639/57600 [7:50:52<2:15:13,  1.60it/s]
 78%|███████▊  | 44640/57600 [7:50:53<2:19:05,  1.55it/s]
                                                         
{'loss': 1.112, 'learning_rate': 3.03205574912892e-07, 'epoch': 492.72}

 78%|███████▊  | 44640/57600 [7:50:53<2:19:05,  1.55it/s]
 78%|███████▊  | 44641/57600 [7:50:53<2:13:25,  1.62it/s]
 78%|███████▊  | 44642/57600 [7:50:54<2:12:52,  1.63it/s]
 78%|███████▊  | 44643/57600 [7:50:54<2:17:22,  1.57it/s]
 78%|███████▊  | 44644/57600 [7:50:55<2:22:10,  1.52it/s]
 78%|███████▊  | 44645/57600 [7:50:56<2:20:42,  1.53it/s]
 78%|███████▊  | 44646/57600 [7:50:56<2:19:44,  1.54it/s]
 78%|███████▊  | 44647/57600 [7:50:57<2:18:57,  1.55it/s]
 78%|███████▊  | 44648/57600 [7:50:58<2:14:13,  1.61it/s]
 78%|███████▊  | 44649/57600 [7:50:58<2:16:26,  1.58it/s]
 78%|███████▊  | 44650/57600 [7:50:59<2:19:10,  1.55it/s]
 78%|███████▊  | 44651/57600 [7:51:00<2:12:40,  1.63it/s]
 78%|███████▊  | 44652/57600 [7:51:00<2:14:22,  1.61it/s]
 78%|███████▊  | 44653/57600 [7:51:01<2:11:25,  1.64it/s]
 78%|███████▊  | 44654/57600 [7:51:01<2:14:48,  1.60it/s]
 78%|███████▊  | 44655/57600 [7:51:02<2:14:54,  1.60it/s]
 78%|███████▊  | 44656/57600 [7:51:03<2:15:56,  1.59it/s]
 78%|███████▊  | 44657/57600 [7:51:03<2:18:10,  1.56it/s]
 78%|███████▊  | 44658/57600 [7:51:04<2:16:18,  1.58it/s]
 78%|███████▊  | 44659/57600 [7:51:05<2:16:15,  1.58it/s]
 78%|███████▊  | 44660/57600 [7:51:05<2:16:49,  1.58it/s]
                                                         
{'loss': 1.1136, 'learning_rate': 3.0289198606271775e-07, 'epoch': 492.94}

 78%|███████▊  | 44660/57600 [7:51:05<2:16:49,  1.58it/s]
 78%|███████▊  | 44661/57600 [7:51:06<2:19:22,  1.55it/s]
 78%|███████▊  | 44662/57600 [7:51:07<2:21:18,  1.53it/s]
 78%|███████▊  | 44663/57600 [7:51:07<2:21:28,  1.52it/s]
 78%|███████▊  | 44664/57600 [7:51:08<2:16:18,  1.58it/s]
 78%|███████▊  | 44665/57600 [7:51:08<2:15:27,  1.59it/s]
 78%|███████▊  | 44666/57600 [7:51:09<2:20:25,  1.54it/s]
 78%|███████▊  | 44667/57600 [7:51:10<2:15:03,  1.60it/s]
 78%|███████▊  | 44668/57600 [7:51:10<2:12:09,  1.63it/s]
 78%|███████▊  | 44669/57600 [7:51:11<2:10:42,  1.65it/s]
 78%|███████▊  | 44670/57600 [7:51:12<2:13:30,  1.61it/s]
 78%|███████▊  | 44671/57600 [7:51:12<2:12:58,  1.62it/s]
 78%|███████▊  | 44672/57600 [7:51:13<2:09:35,  1.66it/s]
 78%|███████▊  | 44673/57600 [7:51:13<2:15:07,  1.59it/s]
 78%|███████▊  | 44674/57600 [7:51:14<2:17:09,  1.57it/s]
 78%|███████▊  | 44675/57600 [7:51:15<2:22:06,  1.52it/s]
 78%|███████▊  | 44676/57600 [7:51:15<2:20:37,  1.53it/s]
 78%|███████▊  | 44677/57600 [7:51:16<2:18:10,  1.56it/s]
 78%|███████▊  | 44678/57600 [7:51:17<2:17:55,  1.56it/s]
 78%|███████▊  | 44679/57600 [7:51:17<2:16:36,  1.58it/s]
 78%|███████▊  | 44680/57600 [7:51:18<2:16:51,  1.57it/s]
                                                         
{'loss': 1.1287, 'learning_rate': 3.025783972125435e-07, 'epoch': 493.16}

 78%|███████▊  | 44680/57600 [7:51:18<2:16:51,  1.57it/s]
 78%|███████▊  | 44681/57600 [7:51:18<2:13:41,  1.61it/s]
 78%|███████▊  | 44682/57600 [7:51:19<2:11:50,  1.63it/s]
 78%|███████▊  | 44683/57600 [7:51:20<2:13:54,  1.61it/s]
 78%|███████▊  | 44684/57600 [7:51:20<2:12:40,  1.62it/s]
 78%|███████▊  | 44685/57600 [7:51:21<2:08:35,  1.67it/s]
 78%|███████▊  | 44686/57600 [7:51:22<2:11:44,  1.63it/s]
 78%|███████▊  | 44687/57600 [7:51:22<2:16:35,  1.58it/s]
 78%|███████▊  | 44688/57600 [7:51:23<2:14:07,  1.60it/s]
 78%|███████▊  | 44689/57600 [7:51:23<2:11:46,  1.63it/s]
 78%|███████▊  | 44690/57600 [7:51:24<2:13:31,  1.61it/s]
 78%|███████▊  | 44691/57600 [7:51:25<2:12:49,  1.62it/s]
 78%|███████▊  | 44692/57600 [7:51:25<2:14:03,  1.60it/s]
 78%|███████▊  | 44693/57600 [7:51:26<2:14:22,  1.60it/s]
 78%|███████▊  | 44694/57600 [7:51:26<2:10:27,  1.65it/s]
 78%|███████▊  | 44695/57600 [7:51:27<2:10:24,  1.65it/s]
 78%|███████▊  | 44696/57600 [7:51:28<2:09:01,  1.67it/s]
 78%|███████▊  | 44697/57600 [7:51:28<2:06:29,  1.70it/s]
 78%|███████▊  | 44698/57600 [7:51:29<2:13:55,  1.61it/s]
 78%|███████▊  | 44699/57600 [7:51:30<2:15:33,  1.59it/s]
 78%|███████▊  | 44700/57600 [7:51:30<2:14:13,  1.60it/s]
                                                         
{'loss': 1.1367, 'learning_rate': 3.0226480836236936e-07, 'epoch': 493.38}

 78%|███████▊  | 44700/57600 [7:51:30<2:14:13,  1.60it/s]
 78%|███████▊  | 44701/57600 [7:51:31<2:14:25,  1.60it/s]
 78%|███████▊  | 44702/57600 [7:51:31<2:16:48,  1.57it/s]
 78%|███████▊  | 44703/57600 [7:51:32<2:19:02,  1.55it/s]
 78%|███████▊  | 44704/57600 [7:51:33<2:17:12,  1.57it/s]
 78%|███████▊  | 44705/57600 [7:51:33<2:14:12,  1.60it/s]
 78%|███████▊  | 44706/57600 [7:51:34<2:19:52,  1.54it/s]
 78%|███████▊  | 44707/57600 [7:51:35<2:20:35,  1.53it/s]
 78%|███████▊  | 44708/57600 [7:51:35<2:21:04,  1.52it/s]
 78%|███████▊  | 44709/57600 [7:51:36<2:17:32,  1.56it/s]
 78%|███████▊  | 44710/57600 [7:51:37<2:18:57,  1.55it/s]
 78%|███████▊  | 44711/57600 [7:51:37<2:17:07,  1.57it/s]
 78%|███████▊  | 44712/57600 [7:51:38<2:15:23,  1.59it/s]
 78%|███████▊  | 44713/57600 [7:51:39<2:15:38,  1.58it/s]
 78%|███████▊  | 44714/57600 [7:51:39<2:12:03,  1.63it/s]
 78%|███████▊  | 44715/57600 [7:51:40<2:13:38,  1.61it/s]
 78%|███████▊  | 44716/57600 [7:51:40<2:17:30,  1.56it/s]
 78%|███████▊  | 44717/57600 [7:51:41<2:17:15,  1.56it/s]
 78%|███████▊  | 44718/57600 [7:51:42<2:22:23,  1.51it/s]
 78%|███████▊  | 44719/57600 [7:51:42<2:21:40,  1.52it/s]
 78%|███████▊  | 44720/57600 [7:51:43<2:19:27,  1.54it/s]
                                                         
{'loss': 1.134, 'learning_rate': 3.019512195121951e-07, 'epoch': 493.6}

 78%|███████▊  | 44720/57600 [7:51:43<2:19:27,  1.54it/s]
 78%|███████▊  | 44721/57600 [7:51:44<2:19:10,  1.54it/s]
 78%|███████▊  | 44722/57600 [7:51:44<2:18:57,  1.54it/s]
 78%|███████▊  | 44723/57600 [7:51:45<2:17:52,  1.56it/s]
 78%|███████▊  | 44724/57600 [7:51:46<2:16:53,  1.57it/s]
 78%|███████▊  | 44725/57600 [7:51:46<2:16:52,  1.57it/s]
 78%|███████▊  | 44726/57600 [7:51:47<2:13:41,  1.60it/s]
 78%|███████▊  | 44727/57600 [7:51:47<2:15:32,  1.58it/s]
 78%|███████▊  | 44728/57600 [7:51:48<2:12:32,  1.62it/s]
 78%|███████▊  | 44729/57600 [7:51:49<2:15:45,  1.58it/s]
 78%|███████▊  | 44730/57600 [7:51:49<2:13:17,  1.61it/s]
 78%|███████▊  | 44731/57600 [7:51:50<2:16:55,  1.57it/s]
 78%|███████▊  | 44732/57600 [7:51:51<2:14:17,  1.60it/s]
 78%|███████▊  | 44733/57600 [7:51:51<2:13:00,  1.61it/s]
 78%|███████▊  | 44734/57600 [7:51:52<2:15:17,  1.58it/s]
 78%|███████▊  | 44735/57600 [7:51:52<2:12:50,  1.61it/s]
 78%|███████▊  | 44736/57600 [7:51:53<2:13:45,  1.60it/s]
 78%|███████▊  | 44737/57600 [7:51:54<2:18:34,  1.55it/s]
 78%|███████▊  | 44738/57600 [7:51:54<2:14:45,  1.59it/s]
 78%|███████▊  | 44739/57600 [7:51:55<2:15:45,  1.58it/s]
 78%|███████▊  | 44740/57600 [7:51:56<2:20:28,  1.53it/s]
                                                         
{'loss': 1.1078, 'learning_rate': 3.016376306620209e-07, 'epoch': 493.82}

 78%|███████▊  | 44740/57600 [7:51:56<2:20:28,  1.53it/s]
 78%|███████▊  | 44741/57600 [7:51:56<2:18:31,  1.55it/s]
 78%|███████▊  | 44742/57600 [7:51:57<2:20:00,  1.53it/s]
 78%|███████▊  | 44743/57600 [7:51:58<2:17:48,  1.55it/s]
 78%|███████▊  | 44744/57600 [7:51:58<2:15:29,  1.58it/s]
 78%|███████▊  | 44745/57600 [7:51:59<2:17:52,  1.55it/s]
 78%|███████▊  | 44746/57600 [7:52:00<2:15:56,  1.58it/s]
 78%|███████▊  | 44747/57600 [7:52:00<2:13:54,  1.60it/s]
 78%|███████▊  | 44748/57600 [7:52:01<2:11:12,  1.63it/s]
 78%|███████▊  | 44749/57600 [7:52:01<2:12:54,  1.61it/s]
 78%|███████▊  | 44750/57600 [7:52:02<2:16:20,  1.57it/s]
 78%|███████▊  | 44751/57600 [7:52:03<2:22:00,  1.51it/s]
 78%|███████▊  | 44752/57600 [7:52:03<2:16:43,  1.57it/s]
 78%|███████▊  | 44753/57600 [7:52:04<2:14:00,  1.60it/s]
 78%|███████▊  | 44754/57600 [7:52:05<2:14:46,  1.59it/s]
 78%|███████▊  | 44755/57600 [7:52:05<2:13:07,  1.61it/s]
 78%|███████▊  | 44756/57600 [7:52:06<2:11:52,  1.62it/s]
 78%|███████▊  | 44757/57600 [7:52:07<2:25:13,  1.47it/s]
 78%|███████▊  | 44758/57600 [7:52:07<2:18:48,  1.54it/s]
 78%|███████▊  | 44759/57600 [7:52:08<2:15:22,  1.58it/s]
 78%|███████▊  | 44760/57600 [7:52:08<2:15:23,  1.58it/s]
                                                         
{'loss': 1.1159, 'learning_rate': 3.013240418118466e-07, 'epoch': 494.04}

 78%|███████▊  | 44760/57600 [7:52:08<2:15:23,  1.58it/s]
 78%|███████▊  | 44761/57600 [7:52:09<2:15:05,  1.58it/s]
 78%|███████▊  | 44762/57600 [7:52:10<2:12:31,  1.61it/s]
 78%|███████▊  | 44763/57600 [7:52:10<2:08:27,  1.67it/s]
 78%|███████▊  | 44764/57600 [7:52:11<2:07:51,  1.67it/s]
 78%|███████▊  | 44765/57600 [7:52:11<2:08:10,  1.67it/s]
 78%|███████▊  | 44766/57600 [7:52:12<2:09:39,  1.65it/s]
 78%|███████▊  | 44767/57600 [7:52:13<2:09:39,  1.65it/s]
 78%|███████▊  | 44768/57600 [7:52:13<2:10:05,  1.64it/s]
 78%|███████▊  | 44769/57600 [7:52:14<2:08:14,  1.67it/s]
 78%|███████▊  | 44770/57600 [7:52:14<2:09:50,  1.65it/s]
 78%|███████▊  | 44771/57600 [7:52:15<2:08:36,  1.66it/s]
 78%|███████▊  | 44772/57600 [7:52:16<2:13:26,  1.60it/s]
 78%|███████▊  | 44773/57600 [7:52:16<2:19:25,  1.53it/s]
 78%|███████▊  | 44774/57600 [7:52:17<2:17:41,  1.55it/s]
 78%|███████▊  | 44775/57600 [7:52:18<2:15:02,  1.58it/s]
 78%|███████▊  | 44776/57600 [7:52:18<2:18:16,  1.55it/s]
 78%|███████▊  | 44777/57600 [7:52:19<2:14:32,  1.59it/s]
 78%|███████▊  | 44778/57600 [7:52:20<2:15:32,  1.58it/s]
 78%|███████▊  | 44779/57600 [7:52:20<2:11:40,  1.62it/s]
 78%|███████▊  | 44780/57600 [7:52:21<2:13:04,  1.61it/s]
                                                         
{'loss': 1.1747, 'learning_rate': 3.0101045296167247e-07, 'epoch': 494.26}

 78%|███████▊  | 44780/57600 [7:52:21<2:13:04,  1.61it/s]
 78%|███████▊  | 44781/57600 [7:52:21<2:10:47,  1.63it/s]
 78%|███████▊  | 44782/57600 [7:52:22<2:09:24,  1.65it/s]
 78%|███████▊  | 44783/57600 [7:52:23<2:09:50,  1.65it/s]
 78%|███████▊  | 44784/57600 [7:52:23<2:11:07,  1.63it/s]
 78%|███████▊  | 44785/57600 [7:52:24<2:09:24,  1.65it/s]
 78%|███████▊  | 44786/57600 [7:52:24<2:14:22,  1.59it/s]
 78%|███████▊  | 44787/57600 [7:52:25<2:20:33,  1.52it/s]
 78%|███████▊  | 44788/57600 [7:52:26<2:24:57,  1.47it/s]
 78%|███████▊  | 44789/57600 [7:52:27<2:24:38,  1.48it/s]
 78%|███████▊  | 44790/57600 [7:52:27<2:21:59,  1.50it/s]
 78%|███████▊  | 44791/57600 [7:52:28<2:27:53,  1.44it/s]
 78%|███████▊  | 44792/57600 [7:52:29<2:30:02,  1.42it/s]
 78%|███████▊  | 44793/57600 [7:52:29<2:23:34,  1.49it/s]
 78%|███████▊  | 44794/57600 [7:52:30<2:22:01,  1.50it/s]
 78%|███████▊  | 44795/57600 [7:52:31<2:17:50,  1.55it/s]
 78%|███████▊  | 44796/57600 [7:52:31<2:20:28,  1.52it/s]
 78%|███████▊  | 44797/57600 [7:52:32<2:18:26,  1.54it/s]
 78%|███████▊  | 44798/57600 [7:52:32<2:13:53,  1.59it/s]
 78%|███████▊  | 44799/57600 [7:52:33<2:14:37,  1.58it/s]
 78%|███████▊  | 44800/57600 [7:52:34<2:14:04,  1.59it/s]
                                                         
{'loss': 1.1123, 'learning_rate': 3.0069686411149833e-07, 'epoch': 494.48}

 78%|███████▊  | 44800/57600 [7:52:34<2:14:04,  1.59it/s]
 78%|███████▊  | 44801/57600 [7:52:34<2:10:30,  1.63it/s]
 78%|███████▊  | 44802/57600 [7:52:35<2:05:27,  1.70it/s]
 78%|███████▊  | 44803/57600 [7:52:35<2:08:13,  1.66it/s]
 78%|███████▊  | 44804/57600 [7:52:36<2:14:24,  1.59it/s]
 78%|███████▊  | 44805/57600 [7:52:37<2:12:32,  1.61it/s]
 78%|███████▊  | 44806/57600 [7:52:37<2:08:59,  1.65it/s]
 78%|███████▊  | 44807/57600 [7:52:38<2:10:12,  1.64it/s]
 78%|███████▊  | 44808/57600 [7:52:39<2:12:11,  1.61it/s]
 78%|███████▊  | 44809/57600 [7:52:39<2:16:54,  1.56it/s]
 78%|███████▊  | 44810/57600 [7:52:40<2:14:59,  1.58it/s]
 78%|███████▊  | 44811/57600 [7:52:41<2:16:07,  1.57it/s]
 78%|███████▊  | 44812/57600 [7:52:41<2:18:40,  1.54it/s]
 78%|███████▊  | 44813/57600 [7:52:42<2:16:00,  1.57it/s]
 78%|███████▊  | 44814/57600 [7:52:43<2:18:34,  1.54it/s]
 78%|███████▊  | 44815/57600 [7:52:43<2:20:53,  1.51it/s]
 78%|███████▊  | 44816/57600 [7:52:44<2:17:53,  1.55it/s]
 78%|███████▊  | 44817/57600 [7:52:44<2:19:08,  1.53it/s]
 78%|███████▊  | 44818/57600 [7:52:45<2:16:35,  1.56it/s]
 78%|███████▊  | 44819/57600 [7:52:46<2:18:06,  1.54it/s]
 78%|███████▊  | 44820/57600 [7:52:46<2:16:33,  1.56it/s]
                                                         
{'loss': 1.1273, 'learning_rate': 3.00383275261324e-07, 'epoch': 494.7}

 78%|███████▊  | 44820/57600 [7:52:46<2:16:33,  1.56it/s]
 78%|███████▊  | 44821/57600 [7:52:47<2:12:23,  1.61it/s]
 78%|███████▊  | 44822/57600 [7:52:48<2:12:10,  1.61it/s]
 78%|███████▊  | 44823/57600 [7:52:48<2:10:27,  1.63it/s]
 78%|███████▊  | 44824/57600 [7:52:49<2:11:25,  1.62it/s]
 78%|███████▊  | 44825/57600 [7:52:49<2:11:10,  1.62it/s]
 78%|███████▊  | 44826/57600 [7:52:50<2:09:33,  1.64it/s]
 78%|███████▊  | 44827/57600 [7:52:51<2:10:25,  1.63it/s]
 78%|███████▊  | 44828/57600 [7:52:51<2:14:04,  1.59it/s]
 78%|███████▊  | 44829/57600 [7:52:52<2:14:32,  1.58it/s]
 78%|███████▊  | 44830/57600 [7:52:53<2:18:08,  1.54it/s]
 78%|███████▊  | 44831/57600 [7:52:53<2:14:38,  1.58it/s]
 78%|███████▊  | 44832/57600 [7:52:54<2:12:45,  1.60it/s]
 78%|███████▊  | 44833/57600 [7:52:54<2:08:40,  1.65it/s]
 78%|███████▊  | 44834/57600 [7:52:55<2:10:38,  1.63it/s]
 78%|███████▊  | 44835/57600 [7:52:56<2:10:04,  1.64it/s]
 78%|███████▊  | 44836/57600 [7:52:56<2:12:16,  1.61it/s]
 78%|███████▊  | 44837/57600 [7:52:57<2:09:25,  1.64it/s]
 78%|███████▊  | 44838/57600 [7:52:57<2:09:35,  1.64it/s]
 78%|███████▊  | 44839/57600 [7:52:58<2:08:52,  1.65it/s]
 78%|███████▊  | 44840/57600 [7:52:59<2:06:57,  1.68it/s]
                                                         
{'loss': 1.1231, 'learning_rate': 3.0006968641114983e-07, 'epoch': 494.92}

 78%|███████▊  | 44840/57600 [7:52:59<2:06:57,  1.68it/s]
 78%|███████▊  | 44841/57600 [7:52:59<2:08:49,  1.65it/s]
 78%|███████▊  | 44842/57600 [7:53:00<2:16:24,  1.56it/s]
 78%|███████▊  | 44843/57600 [7:53:01<2:16:55,  1.55it/s]
 78%|███████▊  | 44844/57600 [7:53:01<2:15:40,  1.57it/s]
 78%|███████▊  | 44845/57600 [7:53:02<2:11:27,  1.62it/s]
 78%|███████▊  | 44846/57600 [7:53:02<2:13:25,  1.59it/s]
 78%|███████▊  | 44847/57600 [7:53:03<2:11:08,  1.62it/s]
 78%|███████▊  | 44848/57600 [7:53:04<2:14:43,  1.58it/s]
 78%|███████▊  | 44849/57600 [7:53:04<2:14:29,  1.58it/s]
 78%|███████▊  | 44850/57600 [7:53:05<2:14:09,  1.58it/s]
 78%|███████▊  | 44851/57600 [7:53:06<2:15:02,  1.57it/s]
 78%|███████▊  | 44852/57600 [7:53:06<2:17:27,  1.55it/s]
 78%|███████▊  | 44853/57600 [7:53:07<2:14:04,  1.58it/s]
 78%|███████▊  | 44854/57600 [7:53:08<2:13:59,  1.59it/s]
 78%|███████▊  | 44855/57600 [7:53:08<2:15:24,  1.57it/s]
 78%|███████▊  | 44856/57600 [7:53:09<2:17:44,  1.54it/s]
 78%|███████▊  | 44857/57600 [7:53:09<2:15:20,  1.57it/s]
 78%|███████▊  | 44858/57600 [7:53:10<2:11:43,  1.61it/s]
 78%|███████▊  | 44859/57600 [7:53:11<2:16:02,  1.56it/s]
 78%|███████▊  | 44860/57600 [7:53:11<2:18:53,  1.53it/s]
                                                         
{'loss': 1.1174, 'learning_rate': 2.997560975609756e-07, 'epoch': 495.14}

 78%|███████▊  | 44860/57600 [7:53:11<2:18:53,  1.53it/s]
 78%|███████▊  | 44861/57600 [7:53:12<2:13:50,  1.59it/s]
 78%|███████▊  | 44862/57600 [7:53:13<2:14:43,  1.58it/s]
 78%|███████▊  | 44863/57600 [7:53:13<2:15:41,  1.56it/s]
 78%|███████▊  | 44864/57600 [7:53:14<2:11:10,  1.62it/s]
 78%|███████▊  | 44865/57600 [7:53:14<2:11:19,  1.62it/s]
 78%|███████▊  | 44866/57600 [7:53:15<2:10:26,  1.63it/s]
 78%|███████▊  | 44867/57600 [7:53:16<2:10:09,  1.63it/s]
 78%|███████▊  | 44868/57600 [7:53:16<2:11:12,  1.62it/s]
 78%|███████▊  | 44869/57600 [7:53:17<2:11:40,  1.61it/s]
 78%|███████▊  | 44870/57600 [7:53:18<2:10:43,  1.62it/s]
 78%|███████▊  | 44871/57600 [7:53:18<2:09:28,  1.64it/s]
 78%|███████▊  | 44872/57600 [7:53:19<2:09:43,  1.64it/s]
 78%|███████▊  | 44873/57600 [7:53:19<2:06:21,  1.68it/s]
 78%|███████▊  | 44874/57600 [7:53:20<2:13:03,  1.59it/s]
 78%|███████▊  | 44875/57600 [7:53:21<2:17:01,  1.55it/s]
 78%|███████▊  | 44876/57600 [7:53:21<2:15:49,  1.56it/s]
 78%|███████▊  | 44877/57600 [7:53:22<2:12:27,  1.60it/s]
 78%|███████▊  | 44878/57600 [7:53:23<2:11:15,  1.62it/s]
 78%|███████▊  | 44879/57600 [7:53:23<2:17:00,  1.55it/s]
 78%|███████▊  | 44880/57600 [7:53:24<2:14:23,  1.58it/s]
                                                         
{'loss': 1.1085, 'learning_rate': 2.994425087108014e-07, 'epoch': 495.36}

 78%|███████▊  | 44880/57600 [7:53:24<2:14:23,  1.58it/s]
 78%|███████▊  | 44881/57600 [7:53:25<2:14:50,  1.57it/s]
 78%|███████▊  | 44882/57600 [7:53:25<2:13:26,  1.59it/s]
 78%|███████▊  | 44883/57600 [7:53:26<2:15:18,  1.57it/s]
 78%|███████▊  | 44884/57600 [7:53:26<2:17:58,  1.54it/s]
 78%|███████▊  | 44885/57600 [7:53:27<2:14:51,  1.57it/s]
 78%|███████▊  | 44886/57600 [7:53:28<2:13:12,  1.59it/s]
 78%|███████▊  | 44887/57600 [7:53:28<2:14:18,  1.58it/s]
 78%|███████▊  | 44888/57600 [7:53:29<2:13:21,  1.59it/s]
 78%|███████▊  | 44889/57600 [7:53:30<2:09:48,  1.63it/s]
 78%|███████▊  | 44890/57600 [7:53:30<2:09:32,  1.64it/s]
 78%|███████▊  | 44891/57600 [7:53:31<2:13:29,  1.59it/s]
 78%|███████▊  | 44892/57600 [7:53:31<2:15:09,  1.57it/s]
 78%|███████▊  | 44893/57600 [7:53:32<2:10:43,  1.62it/s]
 78%|███████▊  | 44894/57600 [7:53:33<2:08:59,  1.64it/s]
 78%|███████▊  | 44895/57600 [7:53:33<2:07:31,  1.66it/s]
 78%|███████▊  | 44896/57600 [7:53:34<2:11:14,  1.61it/s]
 78%|███████▊  | 44897/57600 [7:53:35<2:12:50,  1.59it/s]
 78%|███████▊  | 44898/57600 [7:53:35<2:11:45,  1.61it/s]
 78%|███████▊  | 44899/57600 [7:53:36<2:14:53,  1.57it/s]
 78%|███████▊  | 44900/57600 [7:53:36<2:11:56,  1.60it/s]
                                                         
{'loss': 1.1319, 'learning_rate': 2.9912891986062714e-07, 'epoch': 495.58}

 78%|███████▊  | 44900/57600 [7:53:36<2:11:56,  1.60it/s]
 78%|███████▊  | 44901/57600 [7:53:37<2:10:36,  1.62it/s]
 78%|███████▊  | 44902/57600 [7:53:38<2:09:14,  1.64it/s]
 78%|███████▊  | 44903/57600 [7:53:38<2:11:03,  1.61it/s]
 78%|███████▊  | 44904/57600 [7:53:39<2:13:33,  1.58it/s]
 78%|███████▊  | 44905/57600 [7:53:40<2:16:42,  1.55it/s]
 78%|███████▊  | 44906/57600 [7:53:40<2:14:41,  1.57it/s]
 78%|███████▊  | 44907/57600 [7:53:41<2:12:07,  1.60it/s]
 78%|███████▊  | 44908/57600 [7:53:41<2:10:39,  1.62it/s]
 78%|███████▊  | 44909/57600 [7:53:42<2:10:17,  1.62it/s]
 78%|███████▊  | 44910/57600 [7:53:43<2:11:59,  1.60it/s]
 78%|███████▊  | 44911/57600 [7:53:43<2:10:19,  1.62it/s]
 78%|███████▊  | 44912/57600 [7:53:44<2:14:13,  1.58it/s]
 78%|███████▊  | 44913/57600 [7:53:45<2:21:52,  1.49it/s]
 78%|███████▊  | 44914/57600 [7:53:45<2:16:20,  1.55it/s]
 78%|███████▊  | 44915/57600 [7:53:46<2:16:09,  1.55it/s]
 78%|███████▊  | 44916/57600 [7:53:47<2:16:31,  1.55it/s]
 78%|███████▊  | 44917/57600 [7:53:47<2:17:39,  1.54it/s]
 78%|███████▊  | 44918/57600 [7:53:48<2:15:43,  1.56it/s]
 78%|███████▊  | 44919/57600 [7:53:48<2:15:46,  1.56it/s]
 78%|███████▊  | 44920/57600 [7:53:49<2:14:51,  1.57it/s]
                                                         
{'loss': 1.138, 'learning_rate': 2.9881533101045294e-07, 'epoch': 495.81}

 78%|███████▊  | 44920/57600 [7:53:49<2:14:51,  1.57it/s]
 78%|███████▊  | 44921/57600 [7:53:50<2:16:32,  1.55it/s]
 78%|███████▊  | 44922/57600 [7:53:50<2:12:49,  1.59it/s]
 78%|███████▊  | 44923/57600 [7:53:51<2:12:42,  1.59it/s]
 78%|███████▊  | 44924/57600 [7:53:52<2:09:41,  1.63it/s]
 78%|███████▊  | 44925/57600 [7:53:52<2:13:41,  1.58it/s]
 78%|███████▊  | 44926/57600 [7:53:53<2:13:41,  1.58it/s]
 78%|███████▊  | 44927/57600 [7:53:53<2:09:48,  1.63it/s]
 78%|███████▊  | 44928/57600 [7:53:54<2:11:41,  1.60it/s]
 78%|███████▊  | 44929/57600 [7:53:55<2:09:32,  1.63it/s]
 78%|███████▊  | 44930/57600 [7:53:55<2:09:23,  1.63it/s]
 78%|███████▊  | 44931/57600 [7:53:56<2:12:33,  1.59it/s]
 78%|███████▊  | 44932/57600 [7:53:57<2:13:45,  1.58it/s]
 78%|███████▊  | 44933/57600 [7:53:57<2:16:07,  1.55it/s]
 78%|███████▊  | 44934/57600 [7:53:58<2:22:17,  1.48it/s]
 78%|███████▊  | 44935/57600 [7:53:59<2:18:25,  1.52it/s]
 78%|███████▊  | 44936/57600 [7:53:59<2:22:08,  1.48it/s]
 78%|███████▊  | 44937/57600 [7:54:00<2:15:53,  1.55it/s]
 78%|███████▊  | 44938/57600 [7:54:01<2:17:06,  1.54it/s]
 78%|███████▊  | 44939/57600 [7:54:01<2:16:08,  1.55it/s]
 78%|███████▊  | 44940/57600 [7:54:02<2:14:41,  1.57it/s]
                                                         
{'loss': 1.1056, 'learning_rate': 2.985017421602788e-07, 'epoch': 496.03}

 78%|███████▊  | 44940/57600 [7:54:02<2:14:41,  1.57it/s]
 78%|███████▊  | 44941/57600 [7:54:03<2:17:54,  1.53it/s]
 78%|███████▊  | 44942/57600 [7:54:03<2:15:47,  1.55it/s]
 78%|███████▊  | 44943/57600 [7:54:04<2:16:49,  1.54it/s]
 78%|███████▊  | 44944/57600 [7:54:04<2:18:32,  1.52it/s]
 78%|███████▊  | 44945/57600 [7:54:05<2:16:45,  1.54it/s]
 78%|███████▊  | 44946/57600 [7:54:06<2:17:19,  1.54it/s]
 78%|███████▊  | 44947/57600 [7:54:06<2:19:36,  1.51it/s]
 78%|███████▊  | 44948/57600 [7:54:07<2:16:52,  1.54it/s]
 78%|███████▊  | 44949/57600 [7:54:08<2:12:10,  1.60it/s]
 78%|███████▊  | 44950/57600 [7:54:08<2:16:05,  1.55it/s]
 78%|███████▊  | 44951/57600 [7:54:09<2:18:33,  1.52it/s]
 78%|███████▊  | 44952/57600 [7:54:10<2:17:39,  1.53it/s]
 78%|███████▊  | 44953/57600 [7:54:10<2:15:35,  1.55it/s]
 78%|███████▊  | 44954/57600 [7:54:11<2:14:44,  1.56it/s]
 78%|███████▊  | 44955/57600 [7:54:12<2:12:50,  1.59it/s]
 78%|███████▊  | 44956/57600 [7:54:12<2:12:40,  1.59it/s]
 78%|███████▊  | 44957/57600 [7:54:13<2:17:52,  1.53it/s]
 78%|███████▊  | 44958/57600 [7:54:13<2:17:21,  1.53it/s]
 78%|███████▊  | 44959/57600 [7:54:14<2:16:09,  1.55it/s]
 78%|███████▊  | 44960/57600 [7:54:15<2:16:14,  1.55it/s]
                                                         
{'loss': 1.0901, 'learning_rate': 2.981881533101045e-07, 'epoch': 496.25}

 78%|███████▊  | 44960/57600 [7:54:15<2:16:14,  1.55it/s]
 78%|███████▊  | 44961/57600 [7:54:15<2:13:08,  1.58it/s]
 78%|███████▊  | 44962/57600 [7:54:16<2:14:52,  1.56it/s]
 78%|███████▊  | 44963/57600 [7:54:17<2:15:18,  1.56it/s]
 78%|███████▊  | 44964/57600 [7:54:17<2:16:33,  1.54it/s]
 78%|███████▊  | 44965/57600 [7:54:18<2:19:40,  1.51it/s]
 78%|███████▊  | 44966/57600 [7:54:19<2:15:31,  1.55it/s]
 78%|███████▊  | 44967/57600 [7:54:19<2:13:35,  1.58it/s]
 78%|███████▊  | 44968/57600 [7:54:20<2:16:18,  1.54it/s]
 78%|███████▊  | 44969/57600 [7:54:21<2:17:39,  1.53it/s]
 78%|███████▊  | 44970/57600 [7:54:21<2:17:03,  1.54it/s]
 78%|███████▊  | 44971/57600 [7:54:22<2:14:18,  1.57it/s]
 78%|███████▊  | 44972/57600 [7:54:23<2:16:32,  1.54it/s]
 78%|███████▊  | 44973/57600 [7:54:23<2:11:58,  1.59it/s]
 78%|███████▊  | 44974/57600 [7:54:24<2:17:28,  1.53it/s]
 78%|███████▊  | 44975/57600 [7:54:24<2:13:38,  1.57it/s]
 78%|███████▊  | 44976/57600 [7:54:25<2:11:33,  1.60it/s]
 78%|███████▊  | 44977/57600 [7:54:26<2:14:24,  1.57it/s]
 78%|███████▊  | 44978/57600 [7:54:26<2:16:10,  1.54it/s]
 78%|███████▊  | 44979/57600 [7:54:27<2:14:56,  1.56it/s]
 78%|███████▊  | 44980/57600 [7:54:28<2:13:43,  1.57it/s]
                                                         
{'loss': 1.11, 'learning_rate': 2.978745644599303e-07, 'epoch': 496.47}

 78%|███████▊  | 44980/57600 [7:54:28<2:13:43,  1.57it/s]
 78%|███████▊  | 44981/57600 [7:54:28<2:09:35,  1.62it/s]
 78%|███████▊  | 44982/57600 [7:54:29<2:09:42,  1.62it/s]
 78%|███████▊  | 44983/57600 [7:54:29<2:06:14,  1.67it/s]
 78%|███████▊  | 44984/57600 [7:54:30<2:04:29,  1.69it/s]
 78%|███████▊  | 44985/57600 [7:54:31<2:04:14,  1.69it/s]
 78%|███████▊  | 44986/57600 [7:54:31<2:10:51,  1.61it/s]
 78%|███████▊  | 44987/57600 [7:54:32<2:08:35,  1.63it/s]
 78%|███████▊  | 44988/57600 [7:54:32<2:08:37,  1.63it/s]
 78%|███████▊  | 44989/57600 [7:54:33<2:10:20,  1.61it/s]
 78%|███████▊  | 44990/57600 [7:54:34<2:12:18,  1.59it/s]
 78%|███████▊  | 44991/57600 [7:54:34<2:10:27,  1.61it/s]
 78%|███████▊  | 44992/57600 [7:54:35<2:10:25,  1.61it/s]
 78%|███████▊  | 44993/57600 [7:54:36<2:12:34,  1.58it/s]
 78%|███████▊  | 44994/57600 [7:54:36<2:16:33,  1.54it/s]
 78%|███████▊  | 44995/57600 [7:54:37<2:15:33,  1.55it/s]
 78%|███████▊  | 44996/57600 [7:54:37<2:12:30,  1.59it/s]
 78%|███████▊  | 44997/57600 [7:54:38<2:13:28,  1.57it/s]
 78%|███████▊  | 44998/57600 [7:54:39<2:11:11,  1.60it/s]
 78%|███████▊  | 44999/57600 [7:54:39<2:11:59,  1.59it/s]
 78%|███████▊  | 45000/57600 [7:54:40<2:11:42,  1.59it/s]
                                                         
{'loss': 1.1398, 'learning_rate': 2.9756097560975606e-07, 'epoch': 496.69}

 78%|███████▊  | 45000/57600 [7:54:40<2:11:42,  1.59it/s]
 78%|███████▊  | 45001/57600 [7:54:41<2:10:01,  1.61it/s]
 78%|███████▊  | 45002/57600 [7:54:41<2:09:36,  1.62it/s]
 78%|███████▊  | 45003/57600 [7:54:42<2:07:34,  1.65it/s]
 78%|███████▊  | 45004/57600 [7:54:42<2:08:51,  1.63it/s]
 78%|███████▊  | 45005/57600 [7:54:43<2:09:04,  1.63it/s]
 78%|███████▊  | 45006/57600 [7:54:44<2:07:16,  1.65it/s]
 78%|███████▊  | 45007/57600 [7:54:44<2:05:23,  1.67it/s]
 78%|███████▊  | 45008/57600 [7:54:45<2:05:45,  1.67it/s]
 78%|███████▊  | 45009/57600 [7:54:46<2:11:23,  1.60it/s]
 78%|███████▊  | 45010/57600 [7:54:46<2:09:24,  1.62it/s]
 78%|███████▊  | 45011/57600 [7:54:47<2:10:40,  1.61it/s]
 78%|███████▊  | 45012/57600 [7:54:47<2:13:55,  1.57it/s]
 78%|███████▊  | 45013/57600 [7:54:48<2:10:34,  1.61it/s]
 78%|███████▊  | 45014/57600 [7:54:49<2:10:02,  1.61it/s]
 78%|███████▊  | 45015/57600 [7:54:49<2:07:05,  1.65it/s]
 78%|███████▊  | 45016/57600 [7:54:50<2:08:39,  1.63it/s]
 78%|███████▊  | 45017/57600 [7:54:50<2:09:02,  1.63it/s]
 78%|███████▊  | 45018/57600 [7:54:51<2:12:25,  1.58it/s]
 78%|███████▊  | 45019/57600 [7:54:52<2:12:07,  1.59it/s]
 78%|███████▊  | 45020/57600 [7:54:52<2:11:23,  1.60it/s]
                                                         
{'loss': 1.1342, 'learning_rate': 2.972473867595819e-07, 'epoch': 496.91}

 78%|███████▊  | 45020/57600 [7:54:52<2:11:23,  1.60it/s]
 78%|███████▊  | 45021/57600 [7:54:53<2:12:27,  1.58it/s]
 78%|███████▊  | 45022/57600 [7:54:54<2:12:55,  1.58it/s]
 78%|███████▊  | 45023/57600 [7:54:54<2:12:58,  1.58it/s]
 78%|███████▊  | 45024/57600 [7:54:55<2:11:28,  1.59it/s]
 78%|███████▊  | 45025/57600 [7:54:56<2:13:39,  1.57it/s]
 78%|███████▊  | 45026/57600 [7:54:56<2:13:14,  1.57it/s]
 78%|███████▊  | 45027/57600 [7:54:57<2:13:32,  1.57it/s]
 78%|███████▊  | 45028/57600 [7:54:57<2:12:04,  1.59it/s]
 78%|███████▊  | 45029/57600 [7:54:58<2:16:59,  1.53it/s]
 78%|███████▊  | 45030/57600 [7:54:59<2:13:28,  1.57it/s]
 78%|███████▊  | 45031/57600 [7:54:59<2:11:23,  1.59it/s]
 78%|███████▊  | 45032/57600 [7:55:00<2:09:54,  1.61it/s]
 78%|███████▊  | 45033/57600 [7:55:01<2:08:28,  1.63it/s]
 78%|███████▊  | 45034/57600 [7:55:01<2:06:01,  1.66it/s]
 78%|███████▊  | 45035/57600 [7:55:02<2:05:59,  1.66it/s]
 78%|███████▊  | 45036/57600 [7:55:02<2:03:48,  1.69it/s]
 78%|███████▊  | 45037/57600 [7:55:03<2:07:15,  1.65it/s]
 78%|███████▊  | 45038/57600 [7:55:04<2:11:13,  1.60it/s]
 78%|███████▊  | 45039/57600 [7:55:04<2:06:57,  1.65it/s]
 78%|███████▊  | 45040/57600 [7:55:05<2:03:54,  1.69it/s]
                                                         
{'loss': 1.1409, 'learning_rate': 2.969337979094076e-07, 'epoch': 497.13}

 78%|███████▊  | 45040/57600 [7:55:05<2:03:54,  1.69it/s]
 78%|███████▊  | 45041/57600 [7:55:05<2:03:11,  1.70it/s]
 78%|███████▊  | 45042/57600 [7:55:06<2:10:23,  1.61it/s]
 78%|███████▊  | 45043/57600 [7:55:07<2:14:30,  1.56it/s]
 78%|███████▊  | 45044/57600 [7:55:07<2:16:52,  1.53it/s]
 78%|███████▊  | 45045/57600 [7:55:08<2:18:56,  1.51it/s]
 78%|███████▊  | 45046/57600 [7:55:09<2:17:33,  1.52it/s]
 78%|███████▊  | 45047/57600 [7:55:09<2:17:55,  1.52it/s]
 78%|███████▊  | 45048/57600 [7:55:10<2:18:06,  1.51it/s]
 78%|███████▊  | 45049/57600 [7:55:11<2:16:26,  1.53it/s]
 78%|███████▊  | 45050/57600 [7:55:11<2:12:44,  1.58it/s]
 78%|███████▊  | 45051/57600 [7:55:12<2:16:04,  1.54it/s]
 78%|███████▊  | 45052/57600 [7:55:13<2:14:46,  1.55it/s]
 78%|███████▊  | 45053/57600 [7:55:13<2:13:21,  1.57it/s]
 78%|███████▊  | 45054/57600 [7:55:14<2:10:50,  1.60it/s]
 78%|███████▊  | 45055/57600 [7:55:14<2:10:43,  1.60it/s]
 78%|███████▊  | 45056/57600 [7:55:15<2:16:28,  1.53it/s]
 78%|███████▊  | 45057/57600 [7:55:16<2:14:23,  1.56it/s]
 78%|███████▊  | 45058/57600 [7:55:16<2:20:03,  1.49it/s]
 78%|███████▊  | 45059/57600 [7:55:17<2:17:49,  1.52it/s]
 78%|███████▊  | 45060/57600 [7:55:18<2:15:41,  1.54it/s]
                                                         
{'loss': 1.0931, 'learning_rate': 2.966202090592334e-07, 'epoch': 497.35}

 78%|███████▊  | 45060/57600 [7:55:18<2:15:41,  1.54it/s]
 78%|███████▊  | 45061/57600 [7:55:18<2:19:02,  1.50it/s]
 78%|███████▊  | 45062/57600 [7:55:19<2:16:23,  1.53it/s]
 78%|███████▊  | 45063/57600 [7:55:20<2:16:16,  1.53it/s]
 78%|███████▊  | 45064/57600 [7:55:20<2:12:20,  1.58it/s]
 78%|███████▊  | 45065/57600 [7:55:21<2:08:09,  1.63it/s]
 78%|███████▊  | 45066/57600 [7:55:21<2:07:04,  1.64it/s]
 78%|███████▊  | 45067/57600 [7:55:22<2:08:19,  1.63it/s]
 78%|███████▊  | 45068/57600 [7:55:23<2:08:44,  1.62it/s]
 78%|███████▊  | 45069/57600 [7:55:23<2:09:45,  1.61it/s]
 78%|███████▊  | 45070/57600 [7:55:24<2:07:49,  1.63it/s]
 78%|███████▊  | 45071/57600 [7:55:25<2:07:38,  1.64it/s]
 78%|███████▊  | 45072/57600 [7:55:25<2:04:46,  1.67it/s]
 78%|███████▊  | 45073/57600 [7:55:26<2:02:26,  1.71it/s]
 78%|███████▊  | 45074/57600 [7:55:26<2:03:10,  1.69it/s]
 78%|███████▊  | 45075/57600 [7:55:27<2:08:16,  1.63it/s]
 78%|███████▊  | 45076/57600 [7:55:28<2:07:11,  1.64it/s]
 78%|███████▊  | 45077/57600 [7:55:28<2:10:56,  1.59it/s]
 78%|███████▊  | 45078/57600 [7:55:29<2:16:25,  1.53it/s]
 78%|███████▊  | 45079/57600 [7:55:29<2:10:15,  1.60it/s]
 78%|███████▊  | 45080/57600 [7:55:30<2:10:31,  1.60it/s]
                                                         
{'loss': 1.1652, 'learning_rate': 2.963066202090593e-07, 'epoch': 497.57}

 78%|███████▊  | 45080/57600 [7:55:30<2:10:31,  1.60it/s]
 78%|███████▊  | 45081/57600 [7:55:31<2:09:18,  1.61it/s]
 78%|███████▊  | 45082/57600 [7:55:31<2:06:10,  1.65it/s]
 78%|███████▊  | 45083/57600 [7:55:32<2:09:50,  1.61it/s]
 78%|███████▊  | 45084/57600 [7:55:33<2:11:37,  1.58it/s]
 78%|███████▊  | 45085/57600 [7:55:33<2:11:22,  1.59it/s]
 78%|███████▊  | 45086/57600 [7:55:34<2:15:30,  1.54it/s]
 78%|███████▊  | 45087/57600 [7:55:35<2:12:27,  1.57it/s]
 78%|███████▊  | 45088/57600 [7:55:35<2:09:49,  1.61it/s]
 78%|███████▊  | 45089/57600 [7:55:36<2:07:45,  1.63it/s]
 78%|███████▊  | 45090/57600 [7:55:36<2:06:44,  1.65it/s]
 78%|███████▊  | 45091/57600 [7:55:37<2:07:52,  1.63it/s]
 78%|███████▊  | 45092/57600 [7:55:38<2:13:35,  1.56it/s]
 78%|███████▊  | 45093/57600 [7:55:38<2:16:17,  1.53it/s]
 78%|███████▊  | 45094/57600 [7:55:39<2:16:52,  1.52it/s]
 78%|███████▊  | 45095/57600 [7:55:40<2:13:49,  1.56it/s]
 78%|███████▊  | 45096/57600 [7:55:40<2:08:44,  1.62it/s]
 78%|███████▊  | 45097/57600 [7:55:41<2:05:49,  1.66it/s]
 78%|███████▊  | 45098/57600 [7:55:41<2:07:53,  1.63it/s]
 78%|███████▊  | 45099/57600 [7:55:42<2:10:04,  1.60it/s]
 78%|███████▊  | 45100/57600 [7:55:43<2:08:44,  1.62it/s]
                                                         
{'loss': 1.1286, 'learning_rate': 2.9599303135888503e-07, 'epoch': 497.79}

 78%|███████▊  | 45100/57600 [7:55:43<2:08:44,  1.62it/s]
 78%|███████▊  | 45101/57600 [7:55:43<2:09:18,  1.61it/s]
 78%|███████▊  | 45102/57600 [7:55:44<2:10:40,  1.59it/s]
 78%|███████▊  | 45103/57600 [7:55:44<2:08:12,  1.62it/s]
 78%|███████▊  | 45104/57600 [7:55:45<2:05:39,  1.66it/s]
 78%|███████▊  | 45105/57600 [7:55:46<2:09:45,  1.60it/s]
 78%|███████▊  | 45106/57600 [7:55:46<2:08:13,  1.62it/s]
 78%|███████▊  | 45107/57600 [7:55:47<2:08:37,  1.62it/s]
 78%|███████▊  | 45108/57600 [7:55:48<2:04:52,  1.67it/s]
 78%|███████▊  | 45109/57600 [7:55:48<2:09:22,  1.61it/s]
 78%|███████▊  | 45110/57600 [7:55:49<2:12:02,  1.58it/s]
 78%|███████▊  | 45111/57600 [7:55:49<2:11:38,  1.58it/s]
 78%|███████▊  | 45112/57600 [7:55:50<2:14:56,  1.54it/s]
 78%|███████▊  | 45113/57600 [7:55:51<2:09:18,  1.61it/s]
 78%|███████▊  | 45114/57600 [7:55:51<2:09:32,  1.61it/s]
 78%|███████▊  | 45115/57600 [7:55:52<2:05:16,  1.66it/s]
 78%|███████▊  | 45116/57600 [7:55:52<2:05:36,  1.66it/s]
 78%|███████▊  | 45117/57600 [7:55:53<2:12:47,  1.57it/s]
 78%|███████▊  | 45118/57600 [7:55:54<2:12:33,  1.57it/s]
 78%|███████▊  | 45119/57600 [7:55:55<2:19:21,  1.49it/s]
 78%|███████▊  | 45120/57600 [7:55:55<2:11:38,  1.58it/s]
                                                         
{'loss': 1.1267, 'learning_rate': 2.956794425087108e-07, 'epoch': 498.01}

 78%|███████▊  | 45120/57600 [7:55:55<2:11:38,  1.58it/s]
 78%|███████▊  | 45121/57600 [7:55:56<2:12:09,  1.57it/s]
 78%|███████▊  | 45122/57600 [7:55:56<2:12:33,  1.57it/s]
 78%|███████▊  | 45123/57600 [7:55:57<2:14:22,  1.55it/s]
 78%|███████▊  | 45124/57600 [7:55:58<2:11:04,  1.59it/s]
 78%|███████▊  | 45125/57600 [7:55:58<2:09:01,  1.61it/s]
 78%|███████▊  | 45126/57600 [7:55:59<2:08:27,  1.62it/s]
 78%|███████▊  | 45127/57600 [7:56:00<2:09:28,  1.61it/s]
 78%|███████▊  | 45128/57600 [7:56:00<2:08:46,  1.61it/s]
 78%|███████▊  | 45129/57600 [7:56:01<2:07:49,  1.63it/s]
 78%|███████▊  | 45130/57600 [7:56:01<2:15:12,  1.54it/s]
 78%|███████▊  | 45131/57600 [7:56:02<2:12:35,  1.57it/s]
 78%|███████▊  | 45132/57600 [7:56:03<2:13:34,  1.56it/s]
 78%|███████▊  | 45133/57600 [7:56:03<2:12:38,  1.57it/s]
 78%|███████▊  | 45134/57600 [7:56:04<2:10:18,  1.59it/s]
 78%|███████▊  | 45135/57600 [7:56:05<2:12:54,  1.56it/s]
 78%|███████▊  | 45136/57600 [7:56:05<2:15:32,  1.53it/s]
 78%|███████▊  | 45137/57600 [7:56:06<2:17:37,  1.51it/s]
 78%|███████▊  | 45138/57600 [7:56:07<2:14:06,  1.55it/s]
 78%|███████▊  | 45139/57600 [7:56:07<2:13:45,  1.55it/s]
 78%|███████▊  | 45140/57600 [7:56:08<2:14:02,  1.55it/s]
                                                         
{'loss': 1.1027, 'learning_rate': 2.9536585365853653e-07, 'epoch': 498.23}

 78%|███████▊  | 45140/57600 [7:56:08<2:14:02,  1.55it/s]
 78%|███████▊  | 45141/57600 [7:56:08<2:10:16,  1.59it/s]
 78%|███████▊  | 45142/57600 [7:56:09<2:06:25,  1.64it/s]
 78%|███████▊  | 45143/57600 [7:56:10<2:07:23,  1.63it/s]
 78%|███████▊  | 45144/57600 [7:56:10<2:05:34,  1.65it/s]
 78%|███████▊  | 45145/57600 [7:56:11<2:05:36,  1.65it/s]
 78%|███████▊  | 45146/57600 [7:56:12<2:07:20,  1.63it/s]
 78%|███████▊  | 45147/57600 [7:56:12<2:06:55,  1.64it/s]
 78%|███████▊  | 45148/57600 [7:56:13<2:04:32,  1.67it/s]
 78%|███████▊  | 45149/57600 [7:56:13<2:04:23,  1.67it/s]
 78%|███████▊  | 45150/57600 [7:56:14<2:10:19,  1.59it/s]
 78%|███████▊  | 45151/57600 [7:56:15<2:07:03,  1.63it/s]
 78%|███████▊  | 45152/57600 [7:56:15<2:09:37,  1.60it/s]
 78%|███████▊  | 45153/57600 [7:56:16<2:09:49,  1.60it/s]
 78%|███████▊  | 45154/57600 [7:56:16<2:07:17,  1.63it/s]
 78%|███████▊  | 45155/57600 [7:56:17<2:08:35,  1.61it/s]
 78%|███████▊  | 45156/57600 [7:56:18<2:10:41,  1.59it/s]
 78%|███████▊  | 45157/57600 [7:56:18<2:13:54,  1.55it/s]
 78%|███████▊  | 45158/57600 [7:56:19<2:09:28,  1.60it/s]
 78%|███████▊  | 45159/57600 [7:56:20<2:12:24,  1.57it/s]
 78%|███████▊  | 45160/57600 [7:56:20<2:08:24,  1.61it/s]
                                                         
{'loss': 1.1416, 'learning_rate': 2.950522648083624e-07, 'epoch': 498.45}

 78%|███████▊  | 45160/57600 [7:56:20<2:08:24,  1.61it/s]
 78%|███████▊  | 45161/57600 [7:56:21<2:07:27,  1.63it/s]
 78%|███████▊  | 45162/57600 [7:56:21<2:07:31,  1.63it/s]
 78%|███████▊  | 45163/57600 [7:56:22<2:04:37,  1.66it/s]
 78%|███████▊  | 45164/57600 [7:56:23<2:08:22,  1.61it/s]
 78%|███████▊  | 45165/57600 [7:56:23<2:09:01,  1.61it/s]
 78%|███████▊  | 45166/57600 [7:56:24<2:10:20,  1.59it/s]
 78%|███████▊  | 45167/57600 [7:56:25<2:12:29,  1.56it/s]
 78%|███████▊  | 45168/57600 [7:56:25<2:09:35,  1.60it/s]
 78%|███████▊  | 45169/57600 [7:56:26<2:06:05,  1.64it/s]
 78%|███████▊  | 45170/57600 [7:56:26<2:12:03,  1.57it/s]
 78%|███████▊  | 45171/57600 [7:56:27<2:11:59,  1.57it/s]
 78%|███████▊  | 45172/57600 [7:56:28<2:11:33,  1.57it/s]
 78%|███████▊  | 45173/57600 [7:56:28<2:10:32,  1.59it/s]
 78%|███████▊  | 45174/57600 [7:56:29<2:09:02,  1.60it/s]
 78%|███████▊  | 45175/57600 [7:56:30<2:07:12,  1.63it/s]
 78%|███████▊  | 45176/57600 [7:56:30<2:14:34,  1.54it/s]
 78%|███████▊  | 45177/57600 [7:56:31<2:12:06,  1.57it/s]
 78%|███████▊  | 45178/57600 [7:56:32<2:17:48,  1.50it/s]
 78%|███████▊  | 45179/57600 [7:56:32<2:13:06,  1.56it/s]
 78%|███████▊  | 45180/57600 [7:56:33<2:11:56,  1.57it/s]
                                                         
{'loss': 1.0954, 'learning_rate': 2.947386759581881e-07, 'epoch': 498.68}

 78%|███████▊  | 45180/57600 [7:56:33<2:11:56,  1.57it/s]
 78%|███████▊  | 45181/57600 [7:56:33<2:10:28,  1.59it/s]
 78%|███████▊  | 45182/57600 [7:56:34<2:07:34,  1.62it/s]
 78%|███████▊  | 45183/57600 [7:56:35<2:08:13,  1.61it/s]
 78%|███████▊  | 45184/57600 [7:56:35<2:04:32,  1.66it/s]
 78%|███████▊  | 45185/57600 [7:56:36<2:12:08,  1.57it/s]
 78%|███████▊  | 45186/57600 [7:56:37<2:12:44,  1.56it/s]
 78%|███████▊  | 45187/57600 [7:56:37<2:07:33,  1.62it/s]
 78%|███████▊  | 45188/57600 [7:56:38<2:11:07,  1.58it/s]
 78%|███████▊  | 45189/57600 [7:56:38<2:09:34,  1.60it/s]
 78%|███████▊  | 45190/57600 [7:56:39<2:06:18,  1.64it/s]
 78%|███████▊  | 45191/57600 [7:56:40<2:07:23,  1.62it/s]
 78%|███████▊  | 45192/57600 [7:56:40<2:07:14,  1.63it/s]
 78%|███████▊  | 45193/57600 [7:56:41<2:05:07,  1.65it/s]
 78%|███████▊  | 45194/57600 [7:56:41<2:06:51,  1.63it/s]
 78%|███████▊  | 45195/57600 [7:56:42<2:04:26,  1.66it/s]
 78%|███████▊  | 45196/57600 [7:56:43<2:05:17,  1.65it/s]
 78%|███████▊  | 45197/57600 [7:56:43<2:08:47,  1.61it/s]
 78%|███████▊  | 45198/57600 [7:56:44<2:05:42,  1.64it/s]
 78%|███████▊  | 45199/57600 [7:56:45<2:10:22,  1.59it/s]
 78%|███████▊  | 45200/57600 [7:56:45<2:15:21,  1.53it/s]
                                                         
{'loss': 1.1428, 'learning_rate': 2.944250871080139e-07, 'epoch': 498.9}

 78%|███████▊  | 45200/57600 [7:56:45<2:15:21,  1.53it/s]
 78%|███████▊  | 45201/57600 [7:56:46<2:11:52,  1.57it/s]
 78%|███████▊  | 45202/57600 [7:56:47<2:10:54,  1.58it/s]
 78%|███████▊  | 45203/57600 [7:56:47<2:13:38,  1.55it/s]
 78%|███████▊  | 45204/57600 [7:56:48<2:10:43,  1.58it/s]
 78%|███████▊  | 45205/57600 [7:56:48<2:08:51,  1.60it/s]
 78%|███████▊  | 45206/57600 [7:56:49<2:10:41,  1.58it/s]
 78%|███████▊  | 45207/57600 [7:56:50<2:14:48,  1.53it/s]
 78%|███████▊  | 45208/57600 [7:56:50<2:15:49,  1.52it/s]
 78%|███████▊  | 45209/57600 [7:56:51<2:16:01,  1.52it/s]
 78%|███████▊  | 45210/57600 [7:56:52<2:17:57,  1.50it/s]
 78%|███████▊  | 45211/57600 [7:56:52<2:13:33,  1.55it/s]
 78%|███████▊  | 45212/57600 [7:56:53<2:10:27,  1.58it/s]
 78%|███████▊  | 45213/57600 [7:56:54<2:10:31,  1.58it/s]
 78%|███████▊  | 45214/57600 [7:56:54<2:11:00,  1.58it/s]
 78%|███████▊  | 45215/57600 [7:56:55<2:07:46,  1.62it/s]
 78%|███████▊  | 45216/57600 [7:56:55<2:09:29,  1.59it/s]
 79%|███████▊  | 45217/57600 [7:56:56<2:11:45,  1.57it/s]
 79%|███████▊  | 45218/57600 [7:56:57<2:12:01,  1.56it/s]
 79%|███████▊  | 45219/57600 [7:56:57<2:09:56,  1.59it/s]
 79%|███████▊  | 45220/57600 [7:56:58<2:16:54,  1.51it/s]
                                                         
{'loss': 1.1246, 'learning_rate': 2.9411149825783975e-07, 'epoch': 499.12}

 79%|███████▊  | 45220/57600 [7:56:58<2:16:54,  1.51it/s]
 79%|███████▊  | 45221/57600 [7:56:59<2:13:23,  1.55it/s]
 79%|███████▊  | 45222/57600 [7:56:59<2:11:19,  1.57it/s]
 79%|███████▊  | 45223/57600 [7:57:00<2:11:03,  1.57it/s]
 79%|███████▊  | 45224/57600 [7:57:01<2:11:05,  1.57it/s]
 79%|███████▊  | 45225/57600 [7:57:01<2:08:30,  1.61it/s]
 79%|███████▊  | 45226/57600 [7:57:02<2:07:18,  1.62it/s]
 79%|███████▊  | 45227/57600 [7:57:02<2:06:36,  1.63it/s]
 79%|███████▊  | 45228/57600 [7:57:03<2:10:09,  1.58it/s]
 79%|███████▊  | 45229/57600 [7:57:04<2:07:35,  1.62it/s]
 79%|███████▊  | 45230/57600 [7:57:04<2:09:42,  1.59it/s]
 79%|███████▊  | 45231/57600 [7:57:05<2:10:16,  1.58it/s]
 79%|███████▊  | 45232/57600 [7:57:06<2:07:57,  1.61it/s]
 79%|███████▊  | 45233/57600 [7:57:06<2:06:09,  1.63it/s]
 79%|███████▊  | 45234/57600 [7:57:07<2:07:48,  1.61it/s]
 79%|███████▊  | 45235/57600 [7:57:07<2:07:05,  1.62it/s]
 79%|███████▊  | 45236/57600 [7:57:08<2:08:14,  1.61it/s]
 79%|███████▊  | 45237/57600 [7:57:09<2:11:23,  1.57it/s]
 79%|███████▊  | 45238/57600 [7:57:09<2:08:02,  1.61it/s]
 79%|███████▊  | 45239/57600 [7:57:10<2:07:24,  1.62it/s]
 79%|███████▊  | 45240/57600 [7:57:11<2:06:24,  1.63it/s]
                                                         
{'loss': 1.1236, 'learning_rate': 2.937979094076655e-07, 'epoch': 499.34}

 79%|███████▊  | 45240/57600 [7:57:11<2:06:24,  1.63it/s]
 79%|███████▊  | 45241/57600 [7:57:11<2:08:29,  1.60it/s]
 79%|███████▊  | 45242/57600 [7:57:12<2:08:14,  1.61it/s]
 79%|███████▊  | 45243/57600 [7:57:12<2:07:02,  1.62it/s]
 79%|███████▊  | 45244/57600 [7:57:13<2:09:13,  1.59it/s]
 79%|███████▊  | 45245/57600 [7:57:14<2:14:40,  1.53it/s]
 79%|███████▊  | 45246/57600 [7:57:14<2:15:19,  1.52it/s]
 79%|███████▊  | 45247/57600 [7:57:15<2:18:06,  1.49it/s]
 79%|███████▊  | 45248/57600 [7:57:16<2:14:11,  1.53it/s]
 79%|███████▊  | 45249/57600 [7:57:16<2:10:36,  1.58it/s]
 79%|███████▊  | 45250/57600 [7:57:17<2:08:52,  1.60it/s]
 79%|███████▊  | 45251/57600 [7:57:18<2:07:44,  1.61it/s]
 79%|███████▊  | 45252/57600 [7:57:18<2:04:41,  1.65it/s]
 79%|███████▊  | 45253/57600 [7:57:19<2:07:29,  1.61it/s]
 79%|███████▊  | 45254/57600 [7:57:19<2:06:01,  1.63it/s]
 79%|███████▊  | 45255/57600 [7:57:20<2:09:37,  1.59it/s]
 79%|███████▊  | 45256/57600 [7:57:21<2:07:07,  1.62it/s]
 79%|███████▊  | 45257/57600 [7:57:21<2:07:38,  1.61it/s]
 79%|███████▊  | 45258/57600 [7:57:22<2:09:01,  1.59it/s]
 79%|███████▊  | 45259/57600 [7:57:22<2:07:39,  1.61it/s]
 79%|███████▊  | 45260/57600 [7:57:23<2:17:37,  1.49it/s]
                                                         
{'loss': 1.1216, 'learning_rate': 2.9348432055749126e-07, 'epoch': 499.56}

 79%|███████▊  | 45260/57600 [7:57:23<2:17:37,  1.49it/s]
 79%|███████▊  | 45261/57600 [7:57:24<2:18:12,  1.49it/s]
 79%|███████▊  | 45262/57600 [7:57:25<2:14:38,  1.53it/s]
 79%|███████▊  | 45263/57600 [7:57:25<2:10:29,  1.58it/s]
 79%|███████▊  | 45264/57600 [7:57:26<2:10:52,  1.57it/s]
 79%|███████▊  | 45265/57600 [7:57:26<2:10:17,  1.58it/s]
 79%|███████▊  | 45266/57600 [7:57:27<2:09:07,  1.59it/s]
 79%|███████▊  | 45267/57600 [7:57:28<2:09:42,  1.58it/s]
 79%|███████▊  | 45268/57600 [7:57:28<2:10:12,  1.58it/s]
 79%|███████▊  | 45269/57600 [7:57:29<2:15:01,  1.52it/s]
 79%|███████▊  | 45270/57600 [7:57:30<2:14:43,  1.53it/s]
 79%|███████▊  | 45271/57600 [7:57:30<2:09:17,  1.59it/s]
 79%|███████▊  | 45272/57600 [7:57:31<2:06:20,  1.63it/s]
 79%|███████▊  | 45273/57600 [7:57:32<2:11:20,  1.56it/s]
 79%|███████▊  | 45274/57600 [7:57:32<2:08:02,  1.60it/s]
 79%|███████▊  | 45275/57600 [7:57:33<2:08:31,  1.60it/s]
 79%|███████▊  | 45276/57600 [7:57:33<2:14:23,  1.53it/s]
 79%|███████▊  | 45277/57600 [7:57:34<2:09:15,  1.59it/s]
 79%|███████▊  | 45278/57600 [7:57:35<2:10:00,  1.58it/s]
 79%|███████▊  | 45279/57600 [7:57:35<2:06:14,  1.63it/s]
 79%|███████▊  | 45280/57600 [7:57:36<2:09:31,  1.59it/s]
                                                         
{'loss': 1.1215, 'learning_rate': 2.93170731707317e-07, 'epoch': 499.78}

 79%|███████▊  | 45280/57600 [7:57:36<2:09:31,  1.59it/s]
 79%|███████▊  | 45281/57600 [7:57:37<2:08:11,  1.60it/s]
 79%|███████▊  | 45282/57600 [7:57:37<2:07:02,  1.62it/s]
 79%|███████▊  | 45283/57600 [7:57:38<2:04:55,  1.64it/s]
 79%|███████▊  | 45284/57600 [7:57:38<2:06:30,  1.62it/s]
 79%|███████▊  | 45285/57600 [7:57:39<2:08:23,  1.60it/s]
 79%|███████▊  | 45286/57600 [7:57:40<2:05:06,  1.64it/s]
 79%|███████▊  | 45287/57600 [7:57:40<2:05:05,  1.64it/s]
 79%|███████▊  | 45288/57600 [7:57:41<2:08:17,  1.60it/s]
 79%|███████▊  | 45289/57600 [7:57:41<2:07:38,  1.61it/s]
 79%|███████▊  | 45290/57600 [7:57:42<2:06:08,  1.63it/s]
 79%|███████▊  | 45291/57600 [7:57:43<2:07:52,  1.60it/s]
 79%|███████▊  | 45292/57600 [7:57:43<2:08:18,  1.60it/s]
 79%|███████▊  | 45293/57600 [7:57:44<2:10:00,  1.58it/s]
 79%|███████▊  | 45294/57600 [7:57:45<2:07:31,  1.61it/s]
 79%|███████▊  | 45295/57600 [7:57:45<2:07:14,  1.61it/s]
 79%|███████▊  | 45296/57600 [7:57:46<2:06:11,  1.62it/s]
 79%|███████▊  | 45297/57600 [7:57:46<2:04:19,  1.65it/s]
 79%|███████▊  | 45298/57600 [7:57:47<2:07:11,  1.61it/s]
 79%|███████▊  | 45299/57600 [7:57:48<2:12:14,  1.55it/s]
 79%|███████▊  | 45300/57600 [7:57:48<2:10:16,  1.57it/s]
                                                         
{'loss': 1.1316, 'learning_rate': 2.9285714285714287e-07, 'epoch': 500.0}

 79%|███████▊  | 45300/57600 [7:57:48<2:10:16,  1.57it/s]
 79%|███████▊  | 45301/57600 [7:57:49<2:19:59,  1.46it/s]
 79%|███████▊  | 45302/57600 [7:57:50<2:15:35,  1.51it/s]
 79%|███████▊  | 45303/57600 [7:57:50<2:14:27,  1.52it/s]
 79%|███████▊  | 45304/57600 [7:57:51<2:09:16,  1.59it/s]
 79%|███████▊  | 45305/57600 [7:57:52<2:08:19,  1.60it/s]
 79%|███████▊  | 45306/57600 [7:57:52<2:09:31,  1.58it/s]
 79%|███████▊  | 45307/57600 [7:57:53<2:07:14,  1.61it/s]
 79%|███████▊  | 45308/57600 [7:57:53<2:03:58,  1.65it/s]
 79%|███████▊  | 45309/57600 [7:57:54<2:06:22,  1.62it/s]
 79%|███████▊  | 45310/57600 [7:57:55<2:03:51,  1.65it/s]
 79%|███████▊  | 45311/57600 [7:57:55<2:05:52,  1.63it/s]
 79%|███████▊  | 45312/57600 [7:57:56<2:03:49,  1.65it/s]
 79%|███████▊  | 45313/57600 [7:57:56<2:07:26,  1.61it/s]
 79%|███████▊  | 45314/57600 [7:57:57<2:08:46,  1.59it/s]
 79%|███████▊  | 45315/57600 [7:57:58<2:07:11,  1.61it/s]
 79%|███████▊  | 45316/57600 [7:57:58<2:06:42,  1.62it/s]
 79%|███████▊  | 45317/57600 [7:57:59<2:14:10,  1.53it/s]
 79%|███████▊  | 45318/57600 [7:58:00<2:14:58,  1.52it/s]
 79%|███████▊  | 45319/57600 [7:58:00<2:12:04,  1.55it/s]
 79%|███████▊  | 45320/57600 [7:58:01<2:11:01,  1.56it/s]
                                                         
{'loss': 1.1448, 'learning_rate': 2.925435540069686e-07, 'epoch': 500.22}

 79%|███████▊  | 45320/57600 [7:58:01<2:11:01,  1.56it/s]
 79%|███████▊  | 45321/57600 [7:58:02<2:08:04,  1.60it/s]
 79%|███████▊  | 45322/57600 [7:58:02<2:07:18,  1.61it/s]
 79%|███████▊  | 45323/57600 [7:58:03<2:04:44,  1.64it/s]
 79%|███████▊  | 45324/57600 [7:58:03<2:05:16,  1.63it/s]
 79%|███████▊  | 45325/57600 [7:58:04<2:02:38,  1.67it/s]
 79%|███████▊  | 45326/57600 [7:58:05<2:03:44,  1.65it/s]
 79%|███████▊  | 45327/57600 [7:58:05<2:06:01,  1.62it/s]
 79%|███████▊  | 45328/57600 [7:58:06<2:06:32,  1.62it/s]
 79%|███████▊  | 45329/57600 [7:58:06<2:05:10,  1.63it/s]
 79%|███████▊  | 45330/57600 [7:58:07<2:06:33,  1.62it/s]
 79%|███████▊  | 45331/57600 [7:58:08<2:07:38,  1.60it/s]
 79%|███████▊  | 45332/57600 [7:58:08<2:07:31,  1.60it/s]
 79%|███████▊  | 45333/57600 [7:58:09<2:03:57,  1.65it/s]
 79%|███████▊  | 45334/57600 [7:58:10<2:09:50,  1.57it/s]
 79%|███████▊  | 45335/57600 [7:58:10<2:08:21,  1.59it/s]
 79%|███████▊  | 45336/57600 [7:58:11<2:09:26,  1.58it/s]
 79%|███████▊  | 45337/57600 [7:58:12<2:09:52,  1.57it/s]
 79%|███████▊  | 45338/57600 [7:58:12<2:09:16,  1.58it/s]
 79%|███████▊  | 45339/57600 [7:58:13<2:06:24,  1.62it/s]
 79%|███████▊  | 45340/57600 [7:58:13<2:07:31,  1.60it/s]
                                                         
{'loss': 1.1379, 'learning_rate': 2.922299651567944e-07, 'epoch': 500.44}

 79%|███████▊  | 45340/57600 [7:58:13<2:07:31,  1.60it/s]
 79%|███████▊  | 45341/57600 [7:58:14<2:04:25,  1.64it/s]
 79%|███████▊  | 45342/57600 [7:58:15<2:04:37,  1.64it/s]
 79%|███████▊  | 45343/57600 [7:58:15<2:07:45,  1.60it/s]
 79%|███████▊  | 45344/57600 [7:58:16<2:04:57,  1.63it/s]
 79%|███████▊  | 45345/57600 [7:58:16<2:07:24,  1.60it/s]
 79%|███████▊  | 45346/57600 [7:58:17<2:07:10,  1.61it/s]
 79%|███████▊  | 45347/57600 [7:58:18<2:04:13,  1.64it/s]
 79%|███████▊  | 45348/57600 [7:58:18<2:05:09,  1.63it/s]
 79%|███████▊  | 45349/57600 [7:58:19<2:03:24,  1.65it/s]
 79%|███████▊  | 45350/57600 [7:58:20<2:07:05,  1.61it/s]
 79%|███████▊  | 45351/57600 [7:58:20<2:06:17,  1.62it/s]
 79%|███████▊  | 45352/57600 [7:58:21<2:05:40,  1.62it/s]
 79%|███████▊  | 45353/57600 [7:58:21<2:07:36,  1.60it/s]
 79%|███████▊  | 45354/57600 [7:58:22<2:12:16,  1.54it/s]
 79%|███████▊  | 45355/57600 [7:58:23<2:11:32,  1.55it/s]
 79%|███████▊  | 45356/57600 [7:58:23<2:08:31,  1.59it/s]
 79%|███████▊  | 45357/57600 [7:58:24<2:05:36,  1.62it/s]
 79%|███████▊  | 45358/57600 [7:58:25<2:12:59,  1.53it/s]
 79%|███████▊  | 45359/57600 [7:58:25<2:12:07,  1.54it/s]
 79%|███████▉  | 45360/57600 [7:58:26<2:12:01,  1.55it/s]
                                                         
{'loss': 1.1104, 'learning_rate': 2.9191637630662023e-07, 'epoch': 500.66}

 79%|███████▉  | 45360/57600 [7:58:26<2:12:01,  1.55it/s]
 79%|███████▉  | 45361/57600 [7:58:27<2:11:53,  1.55it/s]
 79%|███████▉  | 45362/57600 [7:58:27<2:10:31,  1.56it/s]
 79%|███████▉  | 45363/57600 [7:58:28<2:11:52,  1.55it/s]
 79%|███████▉  | 45364/57600 [7:58:29<2:14:06,  1.52it/s]
 79%|███████▉  | 45365/57600 [7:58:29<2:12:37,  1.54it/s]
 79%|███████▉  | 45366/57600 [7:58:30<2:10:00,  1.57it/s]
 79%|███████▉  | 45367/57600 [7:58:30<2:09:46,  1.57it/s]
 79%|███████▉  | 45368/57600 [7:58:31<2:12:37,  1.54it/s]
 79%|███████▉  | 45369/57600 [7:58:32<2:12:12,  1.54it/s]
 79%|███████▉  | 45370/57600 [7:58:32<2:09:04,  1.58it/s]
 79%|███████▉  | 45371/57600 [7:58:33<2:13:01,  1.53it/s]
 79%|███████▉  | 45372/57600 [7:58:34<2:12:08,  1.54it/s]
 79%|███████▉  | 45373/57600 [7:58:34<2:13:14,  1.53it/s]
 79%|███████▉  | 45374/57600 [7:58:35<2:12:37,  1.54it/s]
 79%|███████▉  | 45375/57600 [7:58:36<2:10:14,  1.56it/s]
 79%|███████▉  | 45376/57600 [7:58:36<2:12:14,  1.54it/s]
 79%|███████▉  | 45377/57600 [7:58:37<2:11:22,  1.55it/s]
 79%|███████▉  | 45378/57600 [7:58:37<2:07:02,  1.60it/s]
 79%|███████▉  | 45379/57600 [7:58:38<2:11:52,  1.54it/s]
 79%|███████▉  | 45380/57600 [7:58:39<2:10:45,  1.56it/s]
                                                         
{'loss': 1.1084, 'learning_rate': 2.9160278745644593e-07, 'epoch': 500.88}

 79%|███████▉  | 45380/57600 [7:58:39<2:10:45,  1.56it/s]
 79%|███████▉  | 45381/57600 [7:58:39<2:07:22,  1.60it/s]
 79%|███████▉  | 45382/57600 [7:58:40<2:09:52,  1.57it/s]
 79%|███████▉  | 45383/57600 [7:58:41<2:07:09,  1.60it/s]
 79%|███████▉  | 45384/57600 [7:58:41<2:10:17,  1.56it/s]
 79%|███████▉  | 45385/57600 [7:58:42<2:07:17,  1.60it/s]
 79%|███████▉  | 45386/57600 [7:58:42<2:04:53,  1.63it/s]
 79%|███████▉  | 45387/57600 [7:58:43<2:04:37,  1.63it/s]
 79%|███████▉  | 45388/57600 [7:58:44<2:07:25,  1.60it/s]
 79%|███████▉  | 45389/57600 [7:58:44<2:09:51,  1.57it/s]
 79%|███████▉  | 45390/57600 [7:58:45<2:09:52,  1.57it/s]
 79%|███████▉  | 45391/57600 [7:58:46<2:17:33,  1.48it/s]
 79%|███████▉  | 45392/57600 [7:58:46<2:14:31,  1.51it/s]
 79%|███████▉  | 45393/57600 [7:58:47<2:10:22,  1.56it/s]
 79%|███████▉  | 45394/57600 [7:58:48<2:11:29,  1.55it/s]
 79%|███████▉  | 45395/57600 [7:58:48<2:11:08,  1.55it/s]
 79%|███████▉  | 45396/57600 [7:58:49<2:08:56,  1.58it/s]
 79%|███████▉  | 45397/57600 [7:58:50<2:09:41,  1.57it/s]
 79%|███████▉  | 45398/57600 [7:58:50<2:07:35,  1.59it/s]
 79%|███████▉  | 45399/57600 [7:58:51<2:05:45,  1.62it/s]
 79%|███████▉  | 45400/57600 [7:58:52<2:11:29,  1.55it/s]
                                                         
{'loss': 1.1076, 'learning_rate': 2.912891986062718e-07, 'epoch': 501.1}

 79%|███████▉  | 45400/57600 [7:58:52<2:11:29,  1.55it/s]
 79%|███████▉  | 45401/57600 [7:58:52<2:09:51,  1.57it/s]
 79%|███████▉  | 45402/57600 [7:58:53<2:06:03,  1.61it/s]
 79%|███████▉  | 45403/57600 [7:58:53<2:07:08,  1.60it/s]
 79%|███████▉  | 45404/57600 [7:58:54<2:06:59,  1.60it/s]
 79%|███████▉  | 45405/57600 [7:58:55<2:09:44,  1.57it/s]
 79%|███████▉  | 45406/57600 [7:58:55<2:06:39,  1.60it/s]
 79%|███████▉  | 45407/57600 [7:58:56<2:08:44,  1.58it/s]
 79%|███████▉  | 45408/57600 [7:58:57<2:09:51,  1.56it/s]
 79%|███████▉  | 45409/57600 [7:58:57<2:12:12,  1.54it/s]
 79%|███████▉  | 45410/57600 [7:58:58<2:15:13,  1.50it/s]
 79%|███████▉  | 45411/57600 [7:58:59<2:14:01,  1.52it/s]
 79%|███████▉  | 45412/57600 [7:58:59<2:08:07,  1.59it/s]
 79%|███████▉  | 45413/57600 [7:59:00<2:09:15,  1.57it/s]
 79%|███████▉  | 45414/57600 [7:59:00<2:09:47,  1.56it/s]
 79%|███████▉  | 45415/57600 [7:59:01<2:07:56,  1.59it/s]
 79%|███████▉  | 45416/57600 [7:59:02<2:05:43,  1.62it/s]
 79%|███████▉  | 45417/57600 [7:59:02<2:04:54,  1.63it/s]
 79%|███████▉  | 45418/57600 [7:59:03<2:04:54,  1.63it/s]
 79%|███████▉  | 45419/57600 [7:59:04<2:08:24,  1.58it/s]
 79%|███████▉  | 45420/57600 [7:59:04<2:09:52,  1.56it/s]
                                                         
{'loss': 1.1087, 'learning_rate': 2.909756097560975e-07, 'epoch': 501.32}

 79%|███████▉  | 45420/57600 [7:59:04<2:09:52,  1.56it/s]
 79%|███████▉  | 45421/57600 [7:59:05<2:08:21,  1.58it/s]
 79%|███████▉  | 45422/57600 [7:59:05<2:10:41,  1.55it/s]
 79%|███████▉  | 45423/57600 [7:59:06<2:15:09,  1.50it/s]
 79%|███████▉  | 45424/57600 [7:59:07<2:10:59,  1.55it/s]
 79%|███████▉  | 45425/57600 [7:59:07<2:07:29,  1.59it/s]
 79%|███████▉  | 45426/57600 [7:59:08<2:08:14,  1.58it/s]
 79%|███████▉  | 45427/57600 [7:59:09<2:08:22,  1.58it/s]
 79%|███████▉  | 45428/57600 [7:59:09<2:12:22,  1.53it/s]
 79%|███████▉  | 45429/57600 [7:59:10<2:12:22,  1.53it/s]
 79%|███████▉  | 45430/57600 [7:59:11<2:06:42,  1.60it/s]
 79%|███████▉  | 45431/57600 [7:59:11<2:08:03,  1.58it/s]
 79%|███████▉  | 45432/57600 [7:59:12<2:07:47,  1.59it/s]
 79%|███████▉  | 45433/57600 [7:59:12<2:07:05,  1.60it/s]
 79%|███████▉  | 45434/57600 [7:59:13<2:11:38,  1.54it/s]
 79%|███████▉  | 45435/57600 [7:59:14<2:10:33,  1.55it/s]
 79%|███████▉  | 45436/57600 [7:59:14<2:08:13,  1.58it/s]
 79%|███████▉  | 45437/57600 [7:59:15<2:07:28,  1.59it/s]
 79%|███████▉  | 45438/57600 [7:59:16<2:06:09,  1.61it/s]
 79%|███████▉  | 45439/57600 [7:59:16<2:06:22,  1.60it/s]
 79%|███████▉  | 45440/57600 [7:59:17<2:05:25,  1.62it/s]
                                                         
{'loss': 1.1351, 'learning_rate': 2.9066202090592334e-07, 'epoch': 501.55}

 79%|███████▉  | 45440/57600 [7:59:17<2:05:25,  1.62it/s]
 79%|███████▉  | 45441/57600 [7:59:18<2:10:50,  1.55it/s]
 79%|███████▉  | 45442/57600 [7:59:18<2:10:00,  1.56it/s]
 79%|███████▉  | 45443/57600 [7:59:19<2:09:52,  1.56it/s]
 79%|███████▉  | 45444/57600 [7:59:20<2:12:55,  1.52it/s]
 79%|███████▉  | 45445/57600 [7:59:20<2:11:21,  1.54it/s]
 79%|███████▉  | 45446/57600 [7:59:21<2:14:11,  1.51it/s]
 79%|███████▉  | 45447/57600 [7:59:21<2:13:17,  1.52it/s]
 79%|███████▉  | 45448/57600 [7:59:22<2:09:56,  1.56it/s]
 79%|███████▉  | 45449/57600 [7:59:23<2:07:50,  1.58it/s]
 79%|███████▉  | 45450/57600 [7:59:23<2:06:07,  1.61it/s]
 79%|███████▉  | 45451/57600 [7:59:24<2:06:18,  1.60it/s]
 79%|███████▉  | 45452/57600 [7:59:25<2:07:31,  1.59it/s]
 79%|███████▉  | 45453/57600 [7:59:25<2:06:53,  1.60it/s]
 79%|███████▉  | 45454/57600 [7:59:26<2:05:14,  1.62it/s]
 79%|███████▉  | 45455/57600 [7:59:26<2:03:00,  1.65it/s]
 79%|███████▉  | 45456/57600 [7:59:27<2:03:57,  1.63it/s]
 79%|███████▉  | 45457/57600 [7:59:28<2:03:25,  1.64it/s]
 79%|███████▉  | 45458/57600 [7:59:28<2:04:36,  1.62it/s]
 79%|███████▉  | 45459/57600 [7:59:29<2:04:16,  1.63it/s]
 79%|███████▉  | 45460/57600 [7:59:30<2:09:54,  1.56it/s]
                                                         
{'loss': 1.1006, 'learning_rate': 2.903484320557491e-07, 'epoch': 501.77}

 79%|███████▉  | 45460/57600 [7:59:30<2:09:54,  1.56it/s]
 79%|███████▉  | 45461/57600 [7:59:30<2:06:38,  1.60it/s]
 79%|███████▉  | 45462/57600 [7:59:31<2:06:32,  1.60it/s]
 79%|███████▉  | 45463/57600 [7:59:31<2:08:26,  1.57it/s]
 79%|███████▉  | 45464/57600 [7:59:32<2:11:47,  1.53it/s]
 79%|███████▉  | 45465/57600 [7:59:33<2:06:39,  1.60it/s]
 79%|███████▉  | 45466/57600 [7:59:33<2:07:53,  1.58it/s]
 79%|███████▉  | 45467/57600 [7:59:34<2:09:39,  1.56it/s]
 79%|███████▉  | 45468/57600 [7:59:35<2:07:36,  1.58it/s]
 79%|███████▉  | 45469/57600 [7:59:35<2:03:03,  1.64it/s]
 79%|███████▉  | 45470/57600 [7:59:36<2:02:25,  1.65it/s]
 79%|███████▉  | 45471/57600 [7:59:36<2:05:26,  1.61it/s]
 79%|███████▉  | 45472/57600 [7:59:37<2:01:45,  1.66it/s]
 79%|███████▉  | 45473/57600 [7:59:38<2:03:58,  1.63it/s]
 79%|███████▉  | 45474/57600 [7:59:38<2:02:33,  1.65it/s]
 79%|███████▉  | 45475/57600 [7:59:39<2:05:31,  1.61it/s]
 79%|███████▉  | 45476/57600 [7:59:39<2:06:12,  1.60it/s]
 79%|███████▉  | 45477/57600 [7:59:40<2:07:50,  1.58it/s]
 79%|███████▉  | 45478/57600 [7:59:41<2:06:54,  1.59it/s]
 79%|███████▉  | 45479/57600 [7:59:41<2:06:01,  1.60it/s]
 79%|███████▉  | 45480/57600 [7:59:42<2:08:53,  1.57it/s]
                                                         
{'loss': 1.1596, 'learning_rate': 2.900348432055749e-07, 'epoch': 501.99}

 79%|███████▉  | 45480/57600 [7:59:42<2:08:53,  1.57it/s]
 79%|███████▉  | 45481/57600 [7:59:43<2:10:36,  1.55it/s]
 79%|███████▉  | 45482/57600 [7:59:43<2:14:32,  1.50it/s]
 79%|███████▉  | 45483/57600 [7:59:44<2:13:25,  1.51it/s]
 79%|███████▉  | 45484/57600 [7:59:45<2:16:36,  1.48it/s]
 79%|███████▉  | 45485/57600 [7:59:45<2:10:54,  1.54it/s]
 79%|███████▉  | 45486/57600 [7:59:46<2:11:23,  1.54it/s]
 79%|███████▉  | 45487/57600 [7:59:47<2:08:02,  1.58it/s]
 79%|███████▉  | 45488/57600 [7:59:47<2:09:12,  1.56it/s]
 79%|███████▉  | 45489/57600 [7:59:48<2:10:14,  1.55it/s]
 79%|███████▉  | 45490/57600 [7:59:48<2:05:27,  1.61it/s]
 79%|███████▉  | 45491/57600 [7:59:49<2:02:47,  1.64it/s]
 79%|███████▉  | 45492/57600 [7:59:50<2:01:49,  1.66it/s]
 79%|███████▉  | 45493/57600 [7:59:50<2:03:05,  1.64it/s]
 79%|███████▉  | 45494/57600 [7:59:51<2:01:38,  1.66it/s]
 79%|███████▉  | 45495/57600 [7:59:52<2:03:48,  1.63it/s]
 79%|███████▉  | 45496/57600 [7:59:52<2:03:52,  1.63it/s]
 79%|███████▉  | 45497/57600 [7:59:53<2:04:37,  1.62it/s]
 79%|███████▉  | 45498/57600 [7:59:53<2:08:04,  1.57it/s]
 79%|███████▉  | 45499/57600 [7:59:54<2:08:30,  1.57it/s]
 79%|███████▉  | 45500/57600 [7:59:55<2:07:38,  1.58it/s]
                                                         
{'loss': 1.162, 'learning_rate': 2.897212543554007e-07, 'epoch': 502.21}

 79%|███████▉  | 45500/57600 [7:59:55<2:07:38,  1.58it/s]
 79%|███████▉  | 45501/57600 [7:59:55<2:06:22,  1.60it/s]
 79%|███████▉  | 45502/57600 [7:59:56<2:04:30,  1.62it/s]
 79%|███████▉  | 45503/57600 [7:59:57<2:07:08,  1.59it/s]
 79%|███████▉  | 45504/57600 [7:59:57<2:06:58,  1.59it/s]
 79%|███████▉  | 45505/57600 [7:59:58<2:11:00,  1.54it/s]
 79%|███████▉  | 45506/57600 [7:59:59<2:09:46,  1.55it/s]
 79%|███████▉  | 45507/57600 [7:59:59<2:07:13,  1.58it/s]
 79%|███████▉  | 45508/57600 [8:00:00<2:07:40,  1.58it/s]
 79%|███████▉  | 45509/57600 [8:00:00<2:09:11,  1.56it/s]
 79%|███████▉  | 45510/57600 [8:00:01<2:06:58,  1.59it/s]
 79%|███████▉  | 45511/57600 [8:00:02<2:09:35,  1.55it/s]
 79%|███████▉  | 45512/57600 [8:00:02<2:06:35,  1.59it/s]
 79%|███████▉  | 45513/57600 [8:00:03<2:05:25,  1.61it/s]
 79%|███████▉  | 45514/57600 [8:00:04<2:11:19,  1.53it/s]
 79%|███████▉  | 45515/57600 [8:00:04<2:07:58,  1.57it/s]
 79%|███████▉  | 45516/57600 [8:00:05<2:03:31,  1.63it/s]
 79%|███████▉  | 45517/57600 [8:00:05<2:08:55,  1.56it/s]
 79%|███████▉  | 45518/57600 [8:00:06<2:10:07,  1.55it/s]
 79%|███████▉  | 45519/57600 [8:00:07<2:08:59,  1.56it/s]
 79%|███████▉  | 45520/57600 [8:00:07<2:08:54,  1.56it/s]
                                                         
{'loss': 1.1339, 'learning_rate': 2.8940766550522646e-07, 'epoch': 502.43}

 79%|███████▉  | 45520/57600 [8:00:07<2:08:54,  1.56it/s]
 79%|███████▉  | 45521/57600 [8:00:08<2:07:12,  1.58it/s]
 79%|███████▉  | 45522/57600 [8:00:09<2:10:45,  1.54it/s]
 79%|███████▉  | 45523/57600 [8:00:09<2:10:02,  1.55it/s]
 79%|███████▉  | 45524/57600 [8:00:10<2:06:10,  1.60it/s]
 79%|███████▉  | 45525/57600 [8:00:10<2:02:00,  1.65it/s]
 79%|███████▉  | 45526/57600 [8:00:11<2:00:10,  1.67it/s]
 79%|███████▉  | 45527/57600 [8:00:12<2:00:59,  1.66it/s]
 79%|███████▉  | 45528/57600 [8:00:12<2:03:49,  1.62it/s]
 79%|███████▉  | 45529/57600 [8:00:13<2:07:52,  1.57it/s]
 79%|███████▉  | 45530/57600 [8:00:14<2:06:14,  1.59it/s]
 79%|███████▉  | 45531/57600 [8:00:14<2:02:43,  1.64it/s]
 79%|███████▉  | 45532/57600 [8:00:15<2:05:02,  1.61it/s]
 79%|███████▉  | 45533/57600 [8:00:16<2:08:35,  1.56it/s]
 79%|███████▉  | 45534/57600 [8:00:16<2:13:43,  1.50it/s]
 79%|███████▉  | 45535/57600 [8:00:17<2:09:07,  1.56it/s]
 79%|███████▉  | 45536/57600 [8:00:17<2:08:37,  1.56it/s]
 79%|███████▉  | 45537/57600 [8:00:18<2:05:38,  1.60it/s]
 79%|███████▉  | 45538/57600 [8:00:19<2:04:06,  1.62it/s]
 79%|███████▉  | 45539/57600 [8:00:19<2:13:57,  1.50it/s]
 79%|███████▉  | 45540/57600 [8:00:20<2:11:04,  1.53it/s]
                                                         
{'loss': 1.1219, 'learning_rate': 2.890940766550523e-07, 'epoch': 502.65}

 79%|███████▉  | 45540/57600 [8:00:20<2:11:04,  1.53it/s]
 79%|███████▉  | 45541/57600 [8:00:21<2:06:52,  1.58it/s]
 79%|███████▉  | 45542/57600 [8:00:21<2:08:07,  1.57it/s]
 79%|███████▉  | 45543/57600 [8:00:22<2:06:00,  1.59it/s]
 79%|███████▉  | 45544/57600 [8:00:23<2:08:33,  1.56it/s]
 79%|███████▉  | 45545/57600 [8:00:23<2:13:35,  1.50it/s]
 79%|███████▉  | 45546/57600 [8:00:24<2:11:06,  1.53it/s]
 79%|███████▉  | 45547/57600 [8:00:25<2:11:42,  1.53it/s]
 79%|███████▉  | 45548/57600 [8:00:25<2:12:13,  1.52it/s]
 79%|███████▉  | 45549/57600 [8:00:26<2:10:07,  1.54it/s]
 79%|███████▉  | 45550/57600 [8:00:26<2:07:38,  1.57it/s]
 79%|███████▉  | 45551/57600 [8:00:27<2:03:41,  1.62it/s]
 79%|███████▉  | 45552/57600 [8:00:28<2:01:42,  1.65it/s]
 79%|███████▉  | 45553/57600 [8:00:28<2:01:34,  1.65it/s]
 79%|███████▉  | 45554/57600 [8:00:29<2:01:43,  1.65it/s]
 79%|███████▉  | 45555/57600 [8:00:29<2:00:18,  1.67it/s]
 79%|███████▉  | 45556/57600 [8:00:30<1:59:16,  1.68it/s]
 79%|███████▉  | 45557/57600 [8:00:31<2:02:11,  1.64it/s]
 79%|███████▉  | 45558/57600 [8:00:31<2:08:44,  1.56it/s]
 79%|███████▉  | 45559/57600 [8:00:32<2:10:21,  1.54it/s]
 79%|███████▉  | 45560/57600 [8:00:33<2:12:47,  1.51it/s]
                                                         
{'loss': 1.1373, 'learning_rate': 2.88780487804878e-07, 'epoch': 502.87}

 79%|███████▉  | 45560/57600 [8:00:33<2:12:47,  1.51it/s]
 79%|███████▉  | 45561/57600 [8:00:33<2:08:47,  1.56it/s]
 79%|███████▉  | 45562/57600 [8:00:34<2:06:05,  1.59it/s]
 79%|███████▉  | 45563/57600 [8:00:35<2:06:19,  1.59it/s]
 79%|███████▉  | 45564/57600 [8:00:35<2:05:03,  1.60it/s]
 79%|███████▉  | 45565/57600 [8:00:36<2:04:15,  1.61it/s]
 79%|███████▉  | 45566/57600 [8:00:36<2:01:56,  1.64it/s]
 79%|███████▉  | 45567/57600 [8:00:37<2:00:22,  1.67it/s]
 79%|███████▉  | 45568/57600 [8:00:38<2:01:44,  1.65it/s]
 79%|███████▉  | 45569/57600 [8:00:38<2:02:51,  1.63it/s]
 79%|███████▉  | 45570/57600 [8:00:39<2:02:11,  1.64it/s]
 79%|███████▉  | 45571/57600 [8:00:39<2:01:18,  1.65it/s]
 79%|███████▉  | 45572/57600 [8:00:40<2:08:24,  1.56it/s]
 79%|███████▉  | 45573/57600 [8:00:41<2:11:38,  1.52it/s]
 79%|███████▉  | 45574/57600 [8:00:41<2:07:21,  1.57it/s]
 79%|███████▉  | 45575/57600 [8:00:42<2:05:42,  1.59it/s]
 79%|███████▉  | 45576/57600 [8:00:43<2:06:08,  1.59it/s]
 79%|███████▉  | 45577/57600 [8:00:43<2:08:36,  1.56it/s]
 79%|███████▉  | 45578/57600 [8:00:44<2:07:19,  1.57it/s]
 79%|███████▉  | 45579/57600 [8:00:45<2:06:57,  1.58it/s]
 79%|███████▉  | 45580/57600 [8:00:45<2:06:36,  1.58it/s]
                                                         
{'loss': 1.129, 'learning_rate': 2.884668989547038e-07, 'epoch': 503.09}

 79%|███████▉  | 45580/57600 [8:00:45<2:06:36,  1.58it/s]
 79%|███████▉  | 45581/57600 [8:00:46<2:05:48,  1.59it/s]
 79%|███████▉  | 45582/57600 [8:00:46<2:09:05,  1.55it/s]
 79%|███████▉  | 45583/57600 [8:00:47<2:06:28,  1.58it/s]
 79%|███████▉  | 45584/57600 [8:00:48<2:06:03,  1.59it/s]
 79%|███████▉  | 45585/57600 [8:00:48<2:03:52,  1.62it/s]
 79%|███████▉  | 45586/57600 [8:00:49<2:02:48,  1.63it/s]
 79%|███████▉  | 45587/57600 [8:00:49<2:02:32,  1.63it/s]
 79%|███████▉  | 45588/57600 [8:00:50<2:02:28,  1.63it/s]
 79%|███████▉  | 45589/57600 [8:00:51<2:05:11,  1.60it/s]
 79%|███████▉  | 45590/57600 [8:00:51<2:08:27,  1.56it/s]
 79%|███████▉  | 45591/57600 [8:00:52<2:11:49,  1.52it/s]
 79%|███████▉  | 45592/57600 [8:00:53<2:11:03,  1.53it/s]
 79%|███████▉  | 45593/57600 [8:00:53<2:06:00,  1.59it/s]
 79%|███████▉  | 45594/57600 [8:00:54<2:04:13,  1.61it/s]
 79%|███████▉  | 45595/57600 [8:00:55<2:00:00,  1.67it/s]
 79%|███████▉  | 45596/57600 [8:00:55<1:59:09,  1.68it/s]
 79%|███████▉  | 45597/57600 [8:00:56<2:02:25,  1.63it/s]
 79%|███████▉  | 45598/57600 [8:00:56<2:01:43,  1.64it/s]
 79%|███████▉  | 45599/57600 [8:00:57<2:06:08,  1.59it/s]
 79%|███████▉  | 45600/57600 [8:00:58<2:08:11,  1.56it/s]
                                                         
{'loss': 1.1331, 'learning_rate': 2.8815331010452957e-07, 'epoch': 503.31}

 79%|███████▉  | 45600/57600 [8:00:58<2:08:11,  1.56it/s]
 79%|███████▉  | 45601/57600 [8:00:58<2:06:27,  1.58it/s]
 79%|███████▉  | 45602/57600 [8:00:59<2:05:25,  1.59it/s]
 79%|███████▉  | 45603/57600 [8:01:00<2:04:14,  1.61it/s]
 79%|███████▉  | 45604/57600 [8:01:00<1:59:03,  1.68it/s]
 79%|███████▉  | 45605/57600 [8:01:01<2:03:39,  1.62it/s]
 79%|███████▉  | 45606/57600 [8:01:01<2:08:17,  1.56it/s]
 79%|███████▉  | 45607/57600 [8:01:02<2:04:45,  1.60it/s]
 79%|███████▉  | 45608/57600 [8:01:03<2:06:02,  1.59it/s]
 79%|███████▉  | 45609/57600 [8:01:03<2:07:04,  1.57it/s]
 79%|███████▉  | 45610/57600 [8:01:04<2:06:23,  1.58it/s]
 79%|███████▉  | 45611/57600 [8:01:05<2:04:57,  1.60it/s]
 79%|███████▉  | 45612/57600 [8:01:05<2:05:51,  1.59it/s]
 79%|███████▉  | 45613/57600 [8:01:06<2:08:23,  1.56it/s]
 79%|███████▉  | 45614/57600 [8:01:06<2:05:29,  1.59it/s]
 79%|███████▉  | 45615/57600 [8:01:07<2:05:26,  1.59it/s]
 79%|███████▉  | 45616/57600 [8:01:08<2:04:19,  1.61it/s]
 79%|███████▉  | 45617/57600 [8:01:08<2:02:24,  1.63it/s]
 79%|███████▉  | 45618/57600 [8:01:09<2:00:48,  1.65it/s]
 79%|███████▉  | 45619/57600 [8:01:09<2:01:00,  1.65it/s]
 79%|███████▉  | 45620/57600 [8:01:10<2:02:41,  1.63it/s]
                                                         
{'loss': 1.1526, 'learning_rate': 2.878397212543554e-07, 'epoch': 503.53}

 79%|███████▉  | 45620/57600 [8:01:10<2:02:41,  1.63it/s]
 79%|███████▉  | 45621/57600 [8:01:11<2:07:37,  1.56it/s]
 79%|███████▉  | 45622/57600 [8:01:11<2:06:03,  1.58it/s]
 79%|███████▉  | 45623/57600 [8:01:12<2:09:27,  1.54it/s]
 79%|███████▉  | 45624/57600 [8:01:13<2:07:17,  1.57it/s]
 79%|███████▉  | 45625/57600 [8:01:13<2:06:50,  1.57it/s]
 79%|███████▉  | 45626/57600 [8:01:14<2:07:37,  1.56it/s]
 79%|███████▉  | 45627/57600 [8:01:15<2:07:57,  1.56it/s]
 79%|███████▉  | 45628/57600 [8:01:15<2:05:36,  1.59it/s]
 79%|███████▉  | 45629/57600 [8:01:16<2:06:28,  1.58it/s]
 79%|███████▉  | 45630/57600 [8:01:17<2:14:51,  1.48it/s]
 79%|███████▉  | 45631/57600 [8:01:17<2:08:35,  1.55it/s]
 79%|███████▉  | 45632/57600 [8:01:18<2:08:23,  1.55it/s]
 79%|███████▉  | 45633/57600 [8:01:19<2:09:40,  1.54it/s]
 79%|███████▉  | 45634/57600 [8:01:19<2:07:20,  1.57it/s]
 79%|███████▉  | 45635/57600 [8:01:20<2:12:21,  1.51it/s]
 79%|███████▉  | 45636/57600 [8:01:20<2:07:16,  1.57it/s]
 79%|███████▉  | 45637/57600 [8:01:21<2:04:31,  1.60it/s]
 79%|███████▉  | 45638/57600 [8:01:22<2:05:02,  1.59it/s]
 79%|███████▉  | 45639/57600 [8:01:22<2:03:12,  1.62it/s]
 79%|███████▉  | 45640/57600 [8:01:23<2:07:36,  1.56it/s]
                                                         
{'loss': 1.0721, 'learning_rate': 2.875261324041812e-07, 'epoch': 503.75}

 79%|███████▉  | 45640/57600 [8:01:23<2:07:36,  1.56it/s]
 79%|███████▉  | 45641/57600 [8:01:24<2:07:02,  1.57it/s]
 79%|███████▉  | 45642/57600 [8:01:24<2:07:06,  1.57it/s]
 79%|███████▉  | 45643/57600 [8:01:25<2:08:18,  1.55it/s]
 79%|███████▉  | 45644/57600 [8:01:26<2:09:10,  1.54it/s]
 79%|███████▉  | 45645/57600 [8:01:26<2:10:10,  1.53it/s]
 79%|███████▉  | 45646/57600 [8:01:27<2:07:02,  1.57it/s]
 79%|███████▉  | 45647/57600 [8:01:27<2:05:34,  1.59it/s]
 79%|███████▉  | 45648/57600 [8:01:28<2:06:07,  1.58it/s]
 79%|███████▉  | 45649/57600 [8:01:29<2:07:30,  1.56it/s]
 79%|███████▉  | 45650/57600 [8:01:29<2:06:10,  1.58it/s]
 79%|███████▉  | 45651/57600 [8:01:30<2:04:35,  1.60it/s]
 79%|███████▉  | 45652/57600 [8:01:31<2:05:08,  1.59it/s]
 79%|███████▉  | 45653/57600 [8:01:31<2:05:00,  1.59it/s]
 79%|███████▉  | 45654/57600 [8:01:32<2:05:37,  1.58it/s]
 79%|███████▉  | 45655/57600 [8:01:32<2:02:49,  1.62it/s]
 79%|███████▉  | 45656/57600 [8:01:33<2:07:08,  1.57it/s]
 79%|███████▉  | 45657/57600 [8:01:34<2:11:35,  1.51it/s]
 79%|███████▉  | 45658/57600 [8:01:34<2:10:40,  1.52it/s]
 79%|███████▉  | 45659/57600 [8:01:35<2:06:33,  1.57it/s]
 79%|███████▉  | 45660/57600 [8:01:36<2:04:04,  1.60it/s]
                                                         
{'loss': 1.0899, 'learning_rate': 2.8721254355400693e-07, 'epoch': 503.97}

 79%|███████▉  | 45660/57600 [8:01:36<2:04:04,  1.60it/s]
 79%|███████▉  | 45661/57600 [8:01:36<2:03:54,  1.61it/s]
 79%|███████▉  | 45662/57600 [8:01:37<2:04:55,  1.59it/s]
 79%|███████▉  | 45663/57600 [8:01:38<2:12:18,  1.50it/s]
 79%|███████▉  | 45664/57600 [8:01:38<2:07:10,  1.56it/s]
 79%|███████▉  | 45665/57600 [8:01:39<2:03:52,  1.61it/s]
 79%|███████▉  | 45666/57600 [8:01:39<2:04:11,  1.60it/s]
 79%|███████▉  | 45667/57600 [8:01:40<2:04:16,  1.60it/s]
 79%|███████▉  | 45668/57600 [8:01:41<2:05:12,  1.59it/s]
 79%|███████▉  | 45669/57600 [8:01:41<2:03:53,  1.60it/s]
 79%|███████▉  | 45670/57600 [8:01:42<2:02:00,  1.63it/s]
 79%|███████▉  | 45671/57600 [8:01:43<2:04:00,  1.60it/s]
 79%|███████▉  | 45672/57600 [8:01:43<2:03:42,  1.61it/s]
 79%|███████▉  | 45673/57600 [8:01:44<2:09:03,  1.54it/s]
 79%|███████▉  | 45674/57600 [8:01:45<2:07:04,  1.56it/s]
 79%|███████▉  | 45675/57600 [8:01:45<2:04:35,  1.60it/s]
 79%|███████▉  | 45676/57600 [8:01:46<2:05:13,  1.59it/s]
 79%|███████▉  | 45677/57600 [8:01:46<2:03:52,  1.60it/s]
 79%|███████▉  | 45678/57600 [8:01:47<2:00:38,  1.65it/s]
 79%|███████▉  | 45679/57600 [8:01:48<2:03:42,  1.61it/s]
 79%|███████▉  | 45680/57600 [8:01:48<2:00:08,  1.65it/s]
                                                         
{'loss': 1.1029, 'learning_rate': 2.868989547038328e-07, 'epoch': 504.19}

 79%|███████▉  | 45680/57600 [8:01:48<2:00:08,  1.65it/s]
 79%|███████▉  | 45681/57600 [8:01:49<2:04:45,  1.59it/s]
 79%|███████▉  | 45682/57600 [8:01:49<2:04:55,  1.59it/s]
 79%|███████▉  | 45683/57600 [8:01:50<2:05:54,  1.58it/s]
 79%|███████▉  | 45684/57600 [8:01:51<2:03:55,  1.60it/s]
 79%|███████▉  | 45685/57600 [8:01:51<2:04:59,  1.59it/s]
 79%|███████▉  | 45686/57600 [8:01:52<2:08:05,  1.55it/s]
 79%|███████▉  | 45687/57600 [8:01:53<2:09:44,  1.53it/s]
 79%|███████▉  | 45688/57600 [8:01:53<2:07:13,  1.56it/s]
 79%|███████▉  | 45689/57600 [8:01:54<2:07:48,  1.55it/s]
 79%|███████▉  | 45690/57600 [8:01:55<2:04:23,  1.60it/s]
 79%|███████▉  | 45691/57600 [8:01:55<2:02:05,  1.63it/s]
 79%|███████▉  | 45692/57600 [8:01:56<2:05:30,  1.58it/s]
 79%|███████▉  | 45693/57600 [8:01:56<2:00:54,  1.64it/s]
 79%|███████▉  | 45694/57600 [8:01:57<1:58:37,  1.67it/s]
 79%|███████▉  | 45695/57600 [8:01:58<1:57:45,  1.68it/s]
 79%|███████▉  | 45696/57600 [8:01:58<1:58:26,  1.68it/s]
 79%|███████▉  | 45697/57600 [8:01:59<2:00:17,  1.65it/s]
 79%|███████▉  | 45698/57600 [8:01:59<2:00:02,  1.65it/s]
 79%|███████▉  | 45699/57600 [8:02:00<2:00:29,  1.65it/s]
 79%|███████▉  | 45700/57600 [8:02:01<2:03:12,  1.61it/s]
                                                         
{'loss': 1.1579, 'learning_rate': 2.865853658536585e-07, 'epoch': 504.42}

 79%|███████▉  | 45700/57600 [8:02:01<2:03:12,  1.61it/s]
 79%|███████▉  | 45701/57600 [8:02:01<2:07:08,  1.56it/s]
 79%|███████▉  | 45702/57600 [8:02:02<2:07:30,  1.56it/s]
 79%|███████▉  | 45703/57600 [8:02:03<2:03:24,  1.61it/s]
 79%|███████▉  | 45704/57600 [8:02:03<2:06:47,  1.56it/s]
 79%|███████▉  | 45705/57600 [8:02:04<2:08:02,  1.55it/s]
 79%|███████▉  | 45706/57600 [8:02:05<2:07:03,  1.56it/s]
 79%|███████▉  | 45707/57600 [8:02:05<2:07:09,  1.56it/s]
 79%|███████▉  | 45708/57600 [8:02:06<2:11:19,  1.51it/s]
 79%|███████▉  | 45709/57600 [8:02:06<2:06:43,  1.56it/s]
 79%|███████▉  | 45710/57600 [8:02:07<2:01:55,  1.63it/s]
 79%|███████▉  | 45711/57600 [8:02:08<2:04:54,  1.59it/s]
 79%|███████▉  | 45712/57600 [8:02:08<2:05:08,  1.58it/s]
 79%|███████▉  | 45713/57600 [8:02:09<2:04:05,  1.60it/s]
 79%|███████▉  | 45714/57600 [8:02:10<2:04:08,  1.60it/s]
 79%|███████▉  | 45715/57600 [8:02:10<2:02:49,  1.61it/s]
 79%|███████▉  | 45716/57600 [8:02:11<1:59:39,  1.66it/s]
 79%|███████▉  | 45717/57600 [8:02:11<2:04:07,  1.60it/s]
 79%|███████▉  | 45718/57600 [8:02:12<2:05:54,  1.57it/s]
 79%|███████▉  | 45719/57600 [8:02:13<2:05:07,  1.58it/s]
 79%|███████▉  | 45720/57600 [8:02:13<2:03:42,  1.60it/s]
                                                         
{'loss': 1.1225, 'learning_rate': 2.862717770034843e-07, 'epoch': 504.64}

 79%|███████▉  | 45720/57600 [8:02:13<2:03:42,  1.60it/s]
 79%|███████▉  | 45721/57600 [8:02:14<2:02:50,  1.61it/s]
 79%|███████▉  | 45722/57600 [8:02:15<2:02:16,  1.62it/s]
 79%|███████▉  | 45723/57600 [8:02:15<2:02:37,  1.61it/s]
 79%|███████▉  | 45724/57600 [8:02:16<2:01:10,  1.63it/s]
 79%|███████▉  | 45725/57600 [8:02:16<1:58:57,  1.66it/s]
 79%|███████▉  | 45726/57600 [8:02:17<1:58:41,  1.67it/s]
 79%|███████▉  | 45727/57600 [8:02:18<2:02:08,  1.62it/s]
 79%|███████▉  | 45728/57600 [8:02:18<2:04:04,  1.59it/s]
 79%|███████▉  | 45729/57600 [8:02:19<2:04:38,  1.59it/s]
 79%|███████▉  | 45730/57600 [8:02:20<2:07:41,  1.55it/s]
 79%|███████▉  | 45731/57600 [8:02:20<2:02:58,  1.61it/s]
 79%|███████▉  | 45732/57600 [8:02:21<2:03:18,  1.60it/s]
 79%|███████▉  | 45733/57600 [8:02:21<2:03:54,  1.60it/s]
 79%|███████▉  | 45734/57600 [8:02:22<2:02:33,  1.61it/s]
 79%|███████▉  | 45735/57600 [8:02:23<2:04:01,  1.59it/s]
 79%|███████▉  | 45736/57600 [8:02:23<2:00:29,  1.64it/s]
 79%|███████▉  | 45737/57600 [8:02:24<1:58:29,  1.67it/s]
 79%|███████▉  | 45738/57600 [8:02:24<1:59:46,  1.65it/s]
 79%|███████▉  | 45739/57600 [8:02:25<1:59:39,  1.65it/s]
 79%|███████▉  | 45740/57600 [8:02:26<1:58:43,  1.67it/s]
                                                         
{'loss': 1.1311, 'learning_rate': 2.8595818815331004e-07, 'epoch': 504.86}

 79%|███████▉  | 45740/57600 [8:02:26<1:58:43,  1.67it/s]
 79%|███████▉  | 45741/57600 [8:02:26<2:01:15,  1.63it/s]
 79%|███████▉  | 45742/57600 [8:02:27<2:02:21,  1.62it/s]
 79%|███████▉  | 45743/57600 [8:02:28<2:05:04,  1.58it/s]
 79%|███████▉  | 45744/57600 [8:02:28<2:06:32,  1.56it/s]
 79%|███████▉  | 45745/57600 [8:02:29<2:05:50,  1.57it/s]
 79%|███████▉  | 45746/57600 [8:02:30<2:09:19,  1.53it/s]
 79%|███████▉  | 45747/57600 [8:02:30<2:07:05,  1.55it/s]
 79%|███████▉  | 45748/57600 [8:02:31<2:07:35,  1.55it/s]
 79%|███████▉  | 45749/57600 [8:02:31<2:06:33,  1.56it/s]
 79%|███████▉  | 45750/57600 [8:02:32<2:08:02,  1.54it/s]
 79%|███████▉  | 45751/57600 [8:02:33<2:07:24,  1.55it/s]
 79%|███████▉  | 45752/57600 [8:02:33<2:04:23,  1.59it/s]
 79%|███████▉  | 45753/57600 [8:02:34<2:02:52,  1.61it/s]
 79%|███████▉  | 45754/57600 [8:02:35<2:05:34,  1.57it/s]
 79%|███████▉  | 45755/57600 [8:02:35<2:02:19,  1.61it/s]
 79%|███████▉  | 45756/57600 [8:02:36<2:02:28,  1.61it/s]
 79%|███████▉  | 45757/57600 [8:02:36<2:00:08,  1.64it/s]
 79%|███████▉  | 45758/57600 [8:02:37<2:03:28,  1.60it/s]
 79%|███████▉  | 45759/57600 [8:02:38<2:05:53,  1.57it/s]
 79%|███████▉  | 45760/57600 [8:02:38<2:04:59,  1.58it/s]
                                                         
{'loss': 1.1056, 'learning_rate': 2.856445993031359e-07, 'epoch': 505.08}

 79%|███████▉  | 45760/57600 [8:02:38<2:04:59,  1.58it/s]
 79%|███████▉  | 45761/57600 [8:02:39<2:06:54,  1.55it/s]
 79%|███████▉  | 45762/57600 [8:02:40<2:07:23,  1.55it/s]
 79%|███████▉  | 45763/57600 [8:02:40<2:03:54,  1.59it/s]
 79%|███████▉  | 45764/57600 [8:02:41<2:01:23,  1.63it/s]
 79%|███████▉  | 45765/57600 [8:02:41<2:00:04,  1.64it/s]
 79%|███████▉  | 45766/57600 [8:02:42<2:01:27,  1.62it/s]
 79%|███████▉  | 45767/57600 [8:02:43<2:03:27,  1.60it/s]
 79%|███████▉  | 45768/57600 [8:02:43<2:00:58,  1.63it/s]
 79%|███████▉  | 45769/57600 [8:02:44<2:05:08,  1.58it/s]
 79%|███████▉  | 45770/57600 [8:02:45<2:02:19,  1.61it/s]
 79%|███████▉  | 45771/57600 [8:02:45<2:05:11,  1.57it/s]
 79%|███████▉  | 45772/57600 [8:02:46<2:03:41,  1.59it/s]
 79%|███████▉  | 45773/57600 [8:02:46<2:02:24,  1.61it/s]
 79%|███████▉  | 45774/57600 [8:02:47<1:59:21,  1.65it/s]
 79%|███████▉  | 45775/57600 [8:02:48<2:04:01,  1.59it/s]
 79%|███████▉  | 45776/57600 [8:02:48<2:07:51,  1.54it/s]
 79%|███████▉  | 45777/57600 [8:02:49<2:04:00,  1.59it/s]
 79%|███████▉  | 45778/57600 [8:02:50<2:02:10,  1.61it/s]
 79%|███████▉  | 45779/57600 [8:02:50<1:58:54,  1.66it/s]
 79%|███████▉  | 45780/57600 [8:02:51<1:59:17,  1.65it/s]
                                                         
{'loss': 1.1246, 'learning_rate': 2.853310104529617e-07, 'epoch': 505.3}

 79%|███████▉  | 45780/57600 [8:02:51<1:59:17,  1.65it/s]
 79%|███████▉  | 45781/57600 [8:02:51<1:58:21,  1.66it/s]
 79%|███████▉  | 45782/57600 [8:02:52<1:59:47,  1.64it/s]
 79%|███████▉  | 45783/57600 [8:02:53<2:08:06,  1.54it/s]
 79%|███████▉  | 45784/57600 [8:02:53<2:06:50,  1.55it/s]
 79%|███████▉  | 45785/57600 [8:02:54<2:03:13,  1.60it/s]
 79%|███████▉  | 45786/57600 [8:02:54<1:59:52,  1.64it/s]
 79%|███████▉  | 45787/57600 [8:02:55<2:02:23,  1.61it/s]
 79%|███████▉  | 45788/57600 [8:02:56<2:03:55,  1.59it/s]
 79%|███████▉  | 45789/57600 [8:02:56<2:01:27,  1.62it/s]
 79%|███████▉  | 45790/57600 [8:02:57<2:02:21,  1.61it/s]
 79%|███████▉  | 45791/57600 [8:02:58<2:01:29,  1.62it/s]
 80%|███████▉  | 45792/57600 [8:02:58<2:02:15,  1.61it/s]
 80%|███████▉  | 45793/57600 [8:02:59<2:02:38,  1.60it/s]
 80%|███████▉  | 45794/57600 [8:02:59<2:01:05,  1.62it/s]
 80%|███████▉  | 45795/57600 [8:03:00<2:00:46,  1.63it/s]
 80%|███████▉  | 45796/57600 [8:03:01<1:58:50,  1.66it/s]
 80%|███████▉  | 45797/57600 [8:03:01<2:01:05,  1.62it/s]
 80%|███████▉  | 45798/57600 [8:03:02<2:02:58,  1.60it/s]
 80%|███████▉  | 45799/57600 [8:03:03<2:01:51,  1.61it/s]
 80%|███████▉  | 45800/57600 [8:03:03<2:00:23,  1.63it/s]
                                                         
{'loss': 1.1082, 'learning_rate': 2.850174216027874e-07, 'epoch': 505.52}

 80%|███████▉  | 45800/57600 [8:03:03<2:00:23,  1.63it/s]
 80%|███████▉  | 45801/57600 [8:03:04<1:57:42,  1.67it/s]
 80%|███████▉  | 45802/57600 [8:03:04<2:03:15,  1.60it/s]
 80%|███████▉  | 45803/57600 [8:03:05<2:00:59,  1.63it/s]
 80%|███████▉  | 45804/57600 [8:03:06<1:58:34,  1.66it/s]
 80%|███████▉  | 45805/57600 [8:03:06<2:02:30,  1.60it/s]
 80%|███████▉  | 45806/57600 [8:03:07<2:00:34,  1.63it/s]
 80%|███████▉  | 45807/57600 [8:03:07<2:01:57,  1.61it/s]
 80%|███████▉  | 45808/57600 [8:03:08<2:02:09,  1.61it/s]
 80%|███████▉  | 45809/57600 [8:03:09<2:05:25,  1.57it/s]
 80%|███████▉  | 45810/57600 [8:03:10<2:16:28,  1.44it/s]
 80%|███████▉  | 45811/57600 [8:03:10<2:12:50,  1.48it/s]
 80%|███████▉  | 45812/57600 [8:03:11<2:11:40,  1.49it/s]
 80%|███████▉  | 45813/57600 [8:03:11<2:08:35,  1.53it/s]
 80%|███████▉  | 45814/57600 [8:03:12<2:07:38,  1.54it/s]
 80%|███████▉  | 45815/57600 [8:03:13<2:05:12,  1.57it/s]
 80%|███████▉  | 45816/57600 [8:03:13<2:01:14,  1.62it/s]
 80%|███████▉  | 45817/57600 [8:03:14<2:01:32,  1.62it/s]
 80%|███████▉  | 45818/57600 [8:03:15<2:01:34,  1.62it/s]
 80%|███████▉  | 45819/57600 [8:03:15<2:00:34,  1.63it/s]
 80%|███████▉  | 45820/57600 [8:03:16<2:02:55,  1.60it/s]
                                                         
{'loss': 1.1291, 'learning_rate': 2.8470383275261326e-07, 'epoch': 505.74}

 80%|███████▉  | 45820/57600 [8:03:16<2:02:55,  1.60it/s]
 80%|███████▉  | 45821/57600 [8:03:16<2:05:00,  1.57it/s]
 80%|███████▉  | 45822/57600 [8:03:17<2:04:53,  1.57it/s]
 80%|███████▉  | 45823/57600 [8:03:18<2:04:45,  1.57it/s]
 80%|███████▉  | 45824/57600 [8:03:18<2:03:00,  1.60it/s]
 80%|███████▉  | 45825/57600 [8:03:19<2:03:57,  1.58it/s]
 80%|███████▉  | 45826/57600 [8:03:20<2:05:51,  1.56it/s]
 80%|███████▉  | 45827/57600 [8:03:20<2:07:19,  1.54it/s]
 80%|███████▉  | 45828/57600 [8:03:21<2:03:39,  1.59it/s]
 80%|███████▉  | 45829/57600 [8:03:22<2:05:14,  1.57it/s]
 80%|███████▉  | 45830/57600 [8:03:22<2:06:18,  1.55it/s]
 80%|███████▉  | 45831/57600 [8:03:23<2:05:52,  1.56it/s]
 80%|███████▉  | 45832/57600 [8:03:23<2:03:48,  1.58it/s]
 80%|███████▉  | 45833/57600 [8:03:24<2:03:16,  1.59it/s]
 80%|███████▉  | 45834/57600 [8:03:25<2:07:19,  1.54it/s]
 80%|███████▉  | 45835/57600 [8:03:25<2:04:34,  1.57it/s]
 80%|███████▉  | 45836/57600 [8:03:26<2:09:34,  1.51it/s]
 80%|███████▉  | 45837/57600 [8:03:27<2:05:01,  1.57it/s]
 80%|███████▉  | 45838/57600 [8:03:27<2:05:51,  1.56it/s]
 80%|███████▉  | 45839/57600 [8:03:28<2:09:12,  1.52it/s]
 80%|███████▉  | 45840/57600 [8:03:29<2:05:45,  1.56it/s]
                                                         
{'loss': 1.1112, 'learning_rate': 2.8439024390243896e-07, 'epoch': 505.96}

 80%|███████▉  | 45840/57600 [8:03:29<2:05:45,  1.56it/s]
 80%|███████▉  | 45841/57600 [8:03:29<2:04:15,  1.58it/s]
 80%|███████▉  | 45842/57600 [8:03:30<2:11:05,  1.49it/s]
 80%|███████▉  | 45843/57600 [8:03:31<2:10:00,  1.51it/s]
 80%|███████▉  | 45844/57600 [8:03:31<2:10:34,  1.50it/s]
 80%|███████▉  | 45845/57600 [8:03:32<2:08:26,  1.53it/s]
 80%|███████▉  | 45846/57600 [8:03:33<2:08:30,  1.52it/s]
 80%|███████▉  | 45847/57600 [8:03:33<2:06:28,  1.55it/s]
 80%|███████▉  | 45848/57600 [8:03:34<2:08:48,  1.52it/s]
 80%|███████▉  | 45849/57600 [8:03:35<2:05:20,  1.56it/s]
 80%|███████▉  | 45850/57600 [8:03:35<2:01:06,  1.62it/s]
 80%|███████▉  | 45851/57600 [8:03:36<2:03:44,  1.58it/s]
 80%|███████▉  | 45852/57600 [8:03:36<2:04:45,  1.57it/s]
 80%|███████▉  | 45853/57600 [8:03:37<2:08:03,  1.53it/s]
 80%|███████▉  | 45854/57600 [8:03:38<2:02:22,  1.60it/s]
 80%|███████▉  | 45855/57600 [8:03:38<2:01:39,  1.61it/s]
 80%|███████▉  | 45856/57600 [8:03:39<1:59:31,  1.64it/s]
 80%|███████▉  | 45857/57600 [8:03:39<2:01:27,  1.61it/s]
 80%|███████▉  | 45858/57600 [8:03:40<2:03:53,  1.58it/s]
 80%|███████▉  | 45859/57600 [8:03:41<1:59:42,  1.63it/s]
 80%|███████▉  | 45860/57600 [8:03:41<2:01:53,  1.61it/s]
                                                         
{'loss': 1.118, 'learning_rate': 2.8407665505226477e-07, 'epoch': 506.18}

 80%|███████▉  | 45860/57600 [8:03:41<2:01:53,  1.61it/s]
 80%|███████▉  | 45861/57600 [8:03:42<2:03:30,  1.58it/s]
 80%|███████▉  | 45862/57600 [8:03:43<2:03:19,  1.59it/s]
 80%|███████▉  | 45863/57600 [8:03:43<2:02:05,  1.60it/s]
 80%|███████▉  | 45864/57600 [8:03:44<2:04:01,  1.58it/s]
 80%|███████▉  | 45865/57600 [8:03:44<1:59:31,  1.64it/s]
 80%|███████▉  | 45866/57600 [8:03:45<1:59:25,  1.64it/s]
 80%|███████▉  | 45867/57600 [8:03:46<2:01:53,  1.60it/s]
 80%|███████▉  | 45868/57600 [8:03:46<2:06:44,  1.54it/s]
 80%|███████▉  | 45869/57600 [8:03:47<2:08:44,  1.52it/s]
 80%|███████▉  | 45870/57600 [8:03:48<2:07:16,  1.54it/s]
 80%|███████▉  | 45871/57600 [8:03:48<2:04:23,  1.57it/s]
 80%|███████▉  | 45872/57600 [8:03:49<2:01:47,  1.60it/s]
 80%|███████▉  | 45873/57600 [8:03:50<2:00:32,  1.62it/s]
 80%|███████▉  | 45874/57600 [8:03:50<1:59:20,  1.64it/s]
 80%|███████▉  | 45875/57600 [8:03:51<1:58:03,  1.66it/s]
 80%|███████▉  | 45876/57600 [8:03:51<2:03:36,  1.58it/s]
 80%|███████▉  | 45877/57600 [8:03:52<2:04:08,  1.57it/s]
 80%|███████▉  | 45878/57600 [8:03:53<2:00:21,  1.62it/s]
 80%|███████▉  | 45879/57600 [8:03:53<2:03:01,  1.59it/s]
 80%|███████▉  | 45880/57600 [8:03:54<2:00:54,  1.62it/s]
                                                         
{'loss': 1.1045, 'learning_rate': 2.837630662020906e-07, 'epoch': 506.4}

 80%|███████▉  | 45880/57600 [8:03:54<2:00:54,  1.62it/s]
 80%|███████▉  | 45881/57600 [8:03:55<1:59:48,  1.63it/s]
 80%|███████▉  | 45882/57600 [8:03:55<2:03:43,  1.58it/s]
 80%|███████▉  | 45883/57600 [8:03:56<2:08:20,  1.52it/s]
 80%|███████▉  | 45884/57600 [8:03:57<2:07:28,  1.53it/s]
 80%|███████▉  | 45885/57600 [8:03:57<2:04:25,  1.57it/s]
 80%|███████▉  | 45886/57600 [8:03:58<2:05:27,  1.56it/s]
 80%|███████▉  | 45887/57600 [8:03:58<2:04:10,  1.57it/s]
 80%|███████▉  | 45888/57600 [8:03:59<2:03:18,  1.58it/s]
 80%|███████▉  | 45889/57600 [8:04:00<2:03:16,  1.58it/s]
 80%|███████▉  | 45890/57600 [8:04:00<2:03:42,  1.58it/s]
 80%|███████▉  | 45891/57600 [8:04:01<2:05:30,  1.55it/s]
 80%|███████▉  | 45892/57600 [8:04:02<2:05:42,  1.55it/s]
 80%|███████▉  | 45893/57600 [8:04:02<2:02:12,  1.60it/s]
 80%|███████▉  | 45894/57600 [8:04:03<2:01:36,  1.60it/s]
 80%|███████▉  | 45895/57600 [8:04:03<2:01:44,  1.60it/s]
 80%|███████▉  | 45896/57600 [8:04:04<2:02:15,  1.60it/s]
 80%|███████▉  | 45897/57600 [8:04:05<1:58:51,  1.64it/s]
 80%|███████▉  | 45898/57600 [8:04:05<1:58:16,  1.65it/s]
 80%|███████▉  | 45899/57600 [8:04:06<2:00:59,  1.61it/s]
 80%|███████▉  | 45900/57600 [8:04:07<2:01:51,  1.60it/s]
                                                         
{'loss': 1.1366, 'learning_rate': 2.834494773519164e-07, 'epoch': 506.62}

 80%|███████▉  | 45900/57600 [8:04:07<2:01:51,  1.60it/s]
 80%|███████▉  | 45901/57600 [8:04:07<2:04:58,  1.56it/s]
 80%|███████▉  | 45902/57600 [8:04:08<2:02:06,  1.60it/s]
 80%|███████▉  | 45903/57600 [8:04:08<2:04:28,  1.57it/s]
 80%|███████▉  | 45904/57600 [8:04:09<2:01:59,  1.60it/s]
 80%|███████▉  | 45905/57600 [8:04:10<2:01:43,  1.60it/s]
 80%|███████▉  | 45906/57600 [8:04:10<1:59:07,  1.64it/s]
 80%|███████▉  | 45907/57600 [8:04:11<2:03:20,  1.58it/s]
 80%|███████▉  | 45908/57600 [8:04:12<2:06:40,  1.54it/s]
 80%|███████▉  | 45909/57600 [8:04:12<2:03:43,  1.57it/s]
 80%|███████▉  | 45910/57600 [8:04:13<2:05:43,  1.55it/s]
 80%|███████▉  | 45911/57600 [8:04:13<2:01:59,  1.60it/s]
 80%|███████▉  | 45912/57600 [8:04:14<2:03:34,  1.58it/s]
 80%|███████▉  | 45913/57600 [8:04:15<2:04:49,  1.56it/s]
 80%|███████▉  | 45914/57600 [8:04:15<2:02:04,  1.60it/s]
 80%|███████▉  | 45915/57600 [8:04:16<2:05:18,  1.55it/s]
 80%|███████▉  | 45916/57600 [8:04:17<2:02:14,  1.59it/s]
 80%|███████▉  | 45917/57600 [8:04:17<1:58:50,  1.64it/s]
 80%|███████▉  | 45918/57600 [8:04:18<1:58:49,  1.64it/s]
 80%|███████▉  | 45919/57600 [8:04:18<1:59:57,  1.62it/s]
 80%|███████▉  | 45920/57600 [8:04:19<2:02:14,  1.59it/s]
                                                         
{'loss': 1.1639, 'learning_rate': 2.831358885017422e-07, 'epoch': 506.84}

 80%|███████▉  | 45920/57600 [8:04:19<2:02:14,  1.59it/s]
 80%|███████▉  | 45921/57600 [8:04:20<2:04:48,  1.56it/s]
 80%|███████▉  | 45922/57600 [8:04:20<2:03:48,  1.57it/s]
 80%|███████▉  | 45923/57600 [8:04:21<2:01:44,  1.60it/s]
 80%|███████▉  | 45924/57600 [8:04:22<2:00:21,  1.62it/s]
 80%|███████▉  | 45925/57600 [8:04:22<2:05:21,  1.55it/s]
 80%|███████▉  | 45926/57600 [8:04:23<2:01:27,  1.60it/s]
 80%|███████▉  | 45927/57600 [8:04:24<1:59:56,  1.62it/s]
 80%|███████▉  | 45928/57600 [8:04:24<2:03:51,  1.57it/s]
 80%|███████▉  | 45929/57600 [8:04:25<2:02:53,  1.58it/s]
 80%|███████▉  | 45930/57600 [8:04:25<2:01:13,  1.60it/s]
 80%|███████▉  | 45931/57600 [8:04:26<1:59:19,  1.63it/s]
 80%|███████▉  | 45932/57600 [8:04:27<1:56:42,  1.67it/s]
 80%|███████▉  | 45933/57600 [8:04:27<2:01:13,  1.60it/s]
 80%|███████▉  | 45934/57600 [8:04:28<1:58:38,  1.64it/s]
 80%|███████▉  | 45935/57600 [8:04:29<2:03:06,  1.58it/s]
 80%|███████▉  | 45936/57600 [8:04:29<2:00:26,  1.61it/s]
 80%|███████▉  | 45937/57600 [8:04:30<1:56:29,  1.67it/s]
 80%|███████▉  | 45938/57600 [8:04:30<1:59:50,  1.62it/s]
 80%|███████▉  | 45939/57600 [8:04:31<1:56:25,  1.67it/s]
 80%|███████▉  | 45940/57600 [8:04:32<1:58:45,  1.64it/s]
                                                         
{'loss': 1.1473, 'learning_rate': 2.828222996515679e-07, 'epoch': 507.06}

 80%|███████▉  | 45940/57600 [8:04:32<1:58:45,  1.64it/s]
 80%|███████▉  | 45941/57600 [8:04:32<1:56:44,  1.66it/s]
 80%|███████▉  | 45942/57600 [8:04:33<1:57:08,  1.66it/s]
 80%|███████▉  | 45943/57600 [8:04:33<1:55:18,  1.68it/s]
 80%|███████▉  | 45944/57600 [8:04:34<1:59:02,  1.63it/s]
 80%|███████▉  | 45945/57600 [8:04:35<1:59:06,  1.63it/s]
 80%|███████▉  | 45946/57600 [8:04:35<1:57:26,  1.65it/s]
 80%|███████▉  | 45947/57600 [8:04:36<1:58:46,  1.64it/s]
 80%|███████▉  | 45948/57600 [8:04:36<1:56:43,  1.66it/s]
 80%|███████▉  | 45949/57600 [8:04:37<1:57:11,  1.66it/s]
 80%|███████▉  | 45950/57600 [8:04:38<2:04:31,  1.56it/s]
 80%|███████▉  | 45951/57600 [8:04:38<2:02:40,  1.58it/s]
 80%|███████▉  | 45952/57600 [8:04:39<2:03:26,  1.57it/s]
 80%|███████▉  | 45953/57600 [8:04:39<1:59:10,  1.63it/s]
 80%|███████▉  | 45954/57600 [8:04:40<1:59:29,  1.62it/s]
 80%|███████▉  | 45955/57600 [8:04:41<2:04:00,  1.56it/s]
 80%|███████▉  | 45956/57600 [8:04:41<1:59:20,  1.63it/s]
 80%|███████▉  | 45957/57600 [8:04:42<1:58:26,  1.64it/s]
 80%|███████▉  | 45958/57600 [8:04:43<2:00:49,  1.61it/s]
 80%|███████▉  | 45959/57600 [8:04:43<2:01:23,  1.60it/s]
 80%|███████▉  | 45960/57600 [8:04:44<2:00:03,  1.62it/s]
                                                         
{'loss': 1.1251, 'learning_rate': 2.8250871080139374e-07, 'epoch': 507.28}

 80%|███████▉  | 45960/57600 [8:04:44<2:00:03,  1.62it/s]
 80%|███████▉  | 45961/57600 [8:04:45<2:05:07,  1.55it/s]
 80%|███████▉  | 45962/57600 [8:04:45<2:08:15,  1.51it/s]
 80%|███████▉  | 45963/57600 [8:04:46<2:03:59,  1.56it/s]
 80%|███████▉  | 45964/57600 [8:04:47<2:05:12,  1.55it/s]
 80%|███████▉  | 45965/57600 [8:04:47<2:03:58,  1.56it/s]
 80%|███████▉  | 45966/57600 [8:04:48<2:03:30,  1.57it/s]
 80%|███████▉  | 45967/57600 [8:04:48<2:01:56,  1.59it/s]
 80%|███████▉  | 45968/57600 [8:04:49<2:01:10,  1.60it/s]
 80%|███████▉  | 45969/57600 [8:04:50<2:03:00,  1.58it/s]
 80%|███████▉  | 45970/57600 [8:04:50<2:04:04,  1.56it/s]
 80%|███████▉  | 45971/57600 [8:04:51<2:01:39,  1.59it/s]
 80%|███████▉  | 45972/57600 [8:04:51<1:59:48,  1.62it/s]
 80%|███████▉  | 45973/57600 [8:04:52<2:01:23,  1.60it/s]
 80%|███████▉  | 45974/57600 [8:04:53<1:59:17,  1.62it/s]
 80%|███████▉  | 45975/57600 [8:04:53<2:01:22,  1.60it/s]
 80%|███████▉  | 45976/57600 [8:04:54<2:06:59,  1.53it/s]
 80%|███████▉  | 45977/57600 [8:04:55<2:07:15,  1.52it/s]
 80%|███████▉  | 45978/57600 [8:04:55<2:06:22,  1.53it/s]
 80%|███████▉  | 45979/57600 [8:04:56<2:08:01,  1.51it/s]
 80%|███████▉  | 45980/57600 [8:04:57<2:06:06,  1.54it/s]
                                                         
{'loss': 1.0948, 'learning_rate': 2.821951219512195e-07, 'epoch': 507.51}

 80%|███████▉  | 45980/57600 [8:04:57<2:06:06,  1.54it/s]
 80%|███████▉  | 45981/57600 [8:04:57<2:09:11,  1.50it/s]
 80%|███████▉  | 45982/57600 [8:04:58<2:09:27,  1.50it/s]
 80%|███████▉  | 45983/57600 [8:04:59<2:04:30,  1.56it/s]
 80%|███████▉  | 45984/57600 [8:04:59<2:02:19,  1.58it/s]
 80%|███████▉  | 45985/57600 [8:05:00<2:02:23,  1.58it/s]
 80%|███████▉  | 45986/57600 [8:05:01<2:00:12,  1.61it/s]
 80%|███████▉  | 45987/57600 [8:05:01<1:56:15,  1.66it/s]
 80%|███████▉  | 45988/57600 [8:05:02<2:02:14,  1.58it/s]
 80%|███████▉  | 45989/57600 [8:05:02<1:57:52,  1.64it/s]
 80%|███████▉  | 45990/57600 [8:05:03<2:01:10,  1.60it/s]
 80%|███████▉  | 45991/57600 [8:05:04<2:05:23,  1.54it/s]
 80%|███████▉  | 45992/57600 [8:05:04<2:01:58,  1.59it/s]
 80%|███████▉  | 45993/57600 [8:05:05<1:57:39,  1.64it/s]
 80%|███████▉  | 45994/57600 [8:05:06<2:01:10,  1.60it/s]
 80%|███████▉  | 45995/57600 [8:05:06<2:01:23,  1.59it/s]
 80%|███████▉  | 45996/57600 [8:05:07<1:59:06,  1.62it/s]
 80%|███████▉  | 45997/57600 [8:05:07<2:01:04,  1.60it/s]
 80%|███████▉  | 45998/57600 [8:05:08<1:59:46,  1.61it/s]
 80%|███████▉  | 45999/57600 [8:05:09<2:04:25,  1.55it/s]
 80%|███████▉  | 46000/57600 [8:05:09<1:59:30,  1.62it/s]
                                                         
{'loss': 1.1439, 'learning_rate': 2.818815331010453e-07, 'epoch': 507.73}

 80%|███████▉  | 46000/57600 [8:05:09<1:59:30,  1.62it/s]
 80%|███████▉  | 46001/57600 [8:05:10<1:58:22,  1.63it/s]
 80%|███████▉  | 46002/57600 [8:05:10<1:55:30,  1.67it/s]
 80%|███████▉  | 46003/57600 [8:05:11<1:57:50,  1.64it/s]
 80%|███████▉  | 46004/57600 [8:05:12<2:03:09,  1.57it/s]
 80%|███████▉  | 46005/57600 [8:05:12<2:00:39,  1.60it/s]
 80%|███████▉  | 46006/57600 [8:05:13<1:58:19,  1.63it/s]
 80%|███████▉  | 46007/57600 [8:05:14<1:56:56,  1.65it/s]
 80%|███████▉  | 46008/57600 [8:05:14<1:57:17,  1.65it/s]
 80%|███████▉  | 46009/57600 [8:05:15<1:57:40,  1.64it/s]
 80%|███████▉  | 46010/57600 [8:05:15<1:56:20,  1.66it/s]
 80%|███████▉  | 46011/57600 [8:05:16<1:56:44,  1.65it/s]
 80%|███████▉  | 46012/57600 [8:05:17<1:59:46,  1.61it/s]
 80%|███████▉  | 46013/57600 [8:05:17<2:03:52,  1.56it/s]
 80%|███████▉  | 46014/57600 [8:05:18<2:00:41,  1.60it/s]
 80%|███████▉  | 46015/57600 [8:05:18<1:59:39,  1.61it/s]
 80%|███████▉  | 46016/57600 [8:05:19<1:58:43,  1.63it/s]
 80%|███████▉  | 46017/57600 [8:05:20<2:00:16,  1.61it/s]
 80%|███████▉  | 46018/57600 [8:05:20<1:57:18,  1.65it/s]
 80%|███████▉  | 46019/57600 [8:05:21<2:05:40,  1.54it/s]
 80%|███████▉  | 46020/57600 [8:05:22<2:03:57,  1.56it/s]
                                                         
{'loss': 1.148, 'learning_rate': 2.815679442508711e-07, 'epoch': 507.95}

 80%|███████▉  | 46020/57600 [8:05:22<2:03:57,  1.56it/s]
 80%|███████▉  | 46021/57600 [8:05:22<1:59:04,  1.62it/s]
 80%|███████▉  | 46022/57600 [8:05:23<2:04:23,  1.55it/s]
 80%|███████▉  | 46023/57600 [8:05:24<2:03:26,  1.56it/s]
 80%|███████▉  | 46024/57600 [8:05:24<2:03:39,  1.56it/s]
 80%|███████▉  | 46025/57600 [8:05:25<2:04:59,  1.54it/s]
 80%|███████▉  | 46026/57600 [8:05:26<2:05:15,  1.54it/s]
 80%|███████▉  | 46027/57600 [8:05:26<2:07:16,  1.52it/s]
 80%|███████▉  | 46028/57600 [8:05:27<2:06:53,  1.52it/s]
 80%|███████▉  | 46029/57600 [8:05:27<2:03:52,  1.56it/s]
 80%|███████▉  | 46030/57600 [8:05:28<2:05:55,  1.53it/s]
 80%|███████▉  | 46031/57600 [8:05:29<2:03:13,  1.56it/s]
 80%|███████▉  | 46032/57600 [8:05:29<1:59:55,  1.61it/s]
 80%|███████▉  | 46033/57600 [8:05:30<1:59:24,  1.61it/s]
 80%|███████▉  | 46034/57600 [8:05:31<1:58:42,  1.62it/s]
 80%|███████▉  | 46035/57600 [8:05:31<2:01:36,  1.59it/s]
 80%|███████▉  | 46036/57600 [8:05:32<2:01:17,  1.59it/s]
 80%|███████▉  | 46037/57600 [8:05:32<2:02:01,  1.58it/s]
 80%|███████▉  | 46038/57600 [8:05:33<1:59:27,  1.61it/s]
 80%|███████▉  | 46039/57600 [8:05:34<2:02:55,  1.57it/s]
 80%|███████▉  | 46040/57600 [8:05:34<2:03:40,  1.56it/s]
                                                         
{'loss': 1.1106, 'learning_rate': 2.8125435540069685e-07, 'epoch': 508.17}

 80%|███████▉  | 46040/57600 [8:05:34<2:03:40,  1.56it/s]
 80%|███████▉  | 46041/57600 [8:05:35<2:06:05,  1.53it/s]
 80%|███████▉  | 46042/57600 [8:05:36<2:05:40,  1.53it/s]
 80%|███████▉  | 46043/57600 [8:05:36<2:03:55,  1.55it/s]
 80%|███████▉  | 46044/57600 [8:05:37<2:03:19,  1.56it/s]
 80%|███████▉  | 46045/57600 [8:05:38<2:02:56,  1.57it/s]
 80%|███████▉  | 46046/57600 [8:05:38<2:00:24,  1.60it/s]
 80%|███████▉  | 46047/57600 [8:05:39<1:58:06,  1.63it/s]
 80%|███████▉  | 46048/57600 [8:05:39<1:58:57,  1.62it/s]
 80%|███████▉  | 46049/57600 [8:05:40<2:01:13,  1.59it/s]
 80%|███████▉  | 46050/57600 [8:05:41<1:59:28,  1.61it/s]
 80%|███████▉  | 46051/57600 [8:05:41<2:02:01,  1.58it/s]
 80%|███████▉  | 46052/57600 [8:05:42<2:02:19,  1.57it/s]
 80%|███████▉  | 46053/57600 [8:05:43<2:06:37,  1.52it/s]
 80%|███████▉  | 46054/57600 [8:05:43<2:02:41,  1.57it/s]
 80%|███████▉  | 46055/57600 [8:05:44<2:08:33,  1.50it/s]
 80%|███████▉  | 46056/57600 [8:05:45<2:05:54,  1.53it/s]
 80%|███████▉  | 46057/57600 [8:05:45<1:59:46,  1.61it/s]
 80%|███████▉  | 46058/57600 [8:05:46<1:59:22,  1.61it/s]
 80%|███████▉  | 46059/57600 [8:05:46<1:58:40,  1.62it/s]
 80%|███████▉  | 46060/57600 [8:05:47<1:58:11,  1.63it/s]
                                                         
{'loss': 1.1169, 'learning_rate': 2.8094076655052266e-07, 'epoch': 508.39}

 80%|███████▉  | 46060/57600 [8:05:47<1:58:11,  1.63it/s]
 80%|███████▉  | 46061/57600 [8:05:48<2:00:15,  1.60it/s]
 80%|███████▉  | 46062/57600 [8:05:48<1:58:56,  1.62it/s]
 80%|███████▉  | 46063/57600 [8:05:49<1:57:13,  1.64it/s]
 80%|███████▉  | 46064/57600 [8:05:49<1:54:24,  1.68it/s]
 80%|███████▉  | 46065/57600 [8:05:50<2:03:13,  1.56it/s]
 80%|███████▉  | 46066/57600 [8:05:51<2:00:45,  1.59it/s]
 80%|███████▉  | 46067/57600 [8:05:51<2:01:05,  1.59it/s]
 80%|███████▉  | 46068/57600 [8:05:52<1:59:57,  1.60it/s]
 80%|███████▉  | 46069/57600 [8:05:53<1:56:08,  1.65it/s]
 80%|███████▉  | 46070/57600 [8:05:53<2:01:03,  1.59it/s]
 80%|███████▉  | 46071/57600 [8:05:54<2:02:08,  1.57it/s]
 80%|███████▉  | 46072/57600 [8:05:55<1:58:25,  1.62it/s]
 80%|███████▉  | 46073/57600 [8:05:55<1:57:28,  1.64it/s]
 80%|███████▉  | 46074/57600 [8:05:56<1:56:57,  1.64it/s]
 80%|███████▉  | 46075/57600 [8:05:56<1:58:29,  1.62it/s]
 80%|███████▉  | 46076/57600 [8:05:57<1:58:45,  1.62it/s]
 80%|███████▉  | 46077/57600 [8:05:58<2:02:29,  1.57it/s]
 80%|███████▉  | 46078/57600 [8:05:58<1:59:06,  1.61it/s]
 80%|███████▉  | 46079/57600 [8:05:59<2:00:16,  1.60it/s]
 80%|████████  | 46080/57600 [8:06:00<2:04:34,  1.54it/s]
                                                         
{'loss': 1.1067, 'learning_rate': 2.806271777003484e-07, 'epoch': 508.61}

 80%|████████  | 46080/57600 [8:06:00<2:04:34,  1.54it/s]
 80%|████████  | 46081/57600 [8:06:00<2:06:14,  1.52it/s]
 80%|████████  | 46082/57600 [8:06:01<2:02:13,  1.57it/s]
 80%|████████  | 46083/57600 [8:06:02<2:04:36,  1.54it/s]
 80%|████████  | 46084/57600 [8:06:02<2:00:43,  1.59it/s]
 80%|████████  | 46085/57600 [8:06:03<1:57:06,  1.64it/s]
 80%|████████  | 46086/57600 [8:06:03<2:02:39,  1.56it/s]
 80%|████████  | 46087/57600 [8:06:04<2:02:15,  1.57it/s]
 80%|████████  | 46088/57600 [8:06:05<2:02:52,  1.56it/s]
 80%|████████  | 46089/57600 [8:06:05<2:01:29,  1.58it/s]
 80%|████████  | 46090/57600 [8:06:06<2:01:13,  1.58it/s]
 80%|████████  | 46091/57600 [8:06:07<2:00:06,  1.60it/s]
 80%|████████  | 46092/57600 [8:06:07<1:58:57,  1.61it/s]
 80%|████████  | 46093/57600 [8:06:08<2:00:50,  1.59it/s]
 80%|████████  | 46094/57600 [8:06:08<1:57:03,  1.64it/s]
 80%|████████  | 46095/57600 [8:06:09<1:58:10,  1.62it/s]
 80%|████████  | 46096/57600 [8:06:10<2:04:19,  1.54it/s]
 80%|████████  | 46097/57600 [8:06:10<2:00:30,  1.59it/s]
 80%|████████  | 46098/57600 [8:06:11<2:00:46,  1.59it/s]
 80%|████████  | 46099/57600 [8:06:11<1:58:21,  1.62it/s]
 80%|████████  | 46100/57600 [8:06:12<1:58:24,  1.62it/s]
                                                         
{'loss': 1.1447, 'learning_rate': 2.803135888501742e-07, 'epoch': 508.83}

 80%|████████  | 46100/57600 [8:06:12<1:58:24,  1.62it/s]
 80%|████████  | 46101/57600 [8:06:13<2:00:05,  1.60it/s]
 80%|████████  | 46102/57600 [8:06:13<2:04:40,  1.54it/s]
 80%|████████  | 46103/57600 [8:06:14<2:03:23,  1.55it/s]
 80%|████████  | 46104/57600 [8:06:15<1:58:40,  1.61it/s]
 80%|████████  | 46105/57600 [8:06:15<2:00:25,  1.59it/s]
 80%|████████  | 46106/57600 [8:06:16<2:03:13,  1.55it/s]
 80%|████████  | 46107/57600 [8:06:17<2:01:59,  1.57it/s]
 80%|████████  | 46108/57600 [8:06:17<2:00:57,  1.58it/s]
 80%|████████  | 46109/57600 [8:06:18<2:00:43,  1.59it/s]
 80%|████████  | 46110/57600 [8:06:18<2:00:11,  1.59it/s]
 80%|████████  | 46111/57600 [8:06:19<2:00:12,  1.59it/s]
 80%|████████  | 46112/57600 [8:06:20<1:59:13,  1.61it/s]
 80%|████████  | 46113/57600 [8:06:20<2:00:21,  1.59it/s]
 80%|████████  | 46114/57600 [8:06:21<2:04:40,  1.54it/s]
 80%|████████  | 46115/57600 [8:06:22<2:07:23,  1.50it/s]
 80%|████████  | 46116/57600 [8:06:22<2:10:48,  1.46it/s]
 80%|████████  | 46117/57600 [8:06:23<2:08:35,  1.49it/s]
 80%|████████  | 46118/57600 [8:06:24<2:04:49,  1.53it/s]
 80%|████████  | 46119/57600 [8:06:24<2:00:41,  1.59it/s]
 80%|████████  | 46120/57600 [8:06:25<1:58:54,  1.61it/s]
                                                         
{'loss': 1.121, 'learning_rate': 2.7999999999999997e-07, 'epoch': 509.05}

 80%|████████  | 46120/57600 [8:06:25<1:58:54,  1.61it/s]
 80%|████████  | 46121/57600 [8:06:26<1:59:43,  1.60it/s]
 80%|████████  | 46122/57600 [8:06:26<1:59:01,  1.61it/s]
 80%|████████  | 46123/57600 [8:06:27<1:59:18,  1.60it/s]
 80%|████████  | 46124/57600 [8:06:27<1:59:50,  1.60it/s]
 80%|████████  | 46125/57600 [8:06:28<2:00:37,  1.59it/s]
 80%|████████  | 46126/57600 [8:06:29<1:57:36,  1.63it/s]
 80%|████████  | 46127/57600 [8:06:29<1:57:29,  1.63it/s]
 80%|████████  | 46128/57600 [8:06:30<1:56:15,  1.64it/s]
 80%|████████  | 46129/57600 [8:06:30<1:57:39,  1.62it/s]
 80%|████████  | 46130/57600 [8:06:31<1:56:51,  1.64it/s]
 80%|████████  | 46131/57600 [8:06:32<1:57:30,  1.63it/s]
 80%|████████  | 46132/57600 [8:06:32<1:59:36,  1.60it/s]
 80%|████████  | 46133/57600 [8:06:33<1:58:54,  1.61it/s]
 80%|████████  | 46134/57600 [8:06:34<1:57:27,  1.63it/s]
 80%|████████  | 46135/57600 [8:06:34<1:59:18,  1.60it/s]
 80%|████████  | 46136/57600 [8:06:35<2:01:10,  1.58it/s]
 80%|████████  | 46137/57600 [8:06:36<2:03:26,  1.55it/s]
 80%|████████  | 46138/57600 [8:06:36<2:01:12,  1.58it/s]
 80%|████████  | 46139/57600 [8:06:37<2:00:16,  1.59it/s]
 80%|████████  | 46140/57600 [8:06:37<1:56:36,  1.64it/s]
                                                         
{'loss': 1.1101, 'learning_rate': 2.7968641114982577e-07, 'epoch': 509.27}

 80%|████████  | 46140/57600 [8:06:37<1:56:36,  1.64it/s]
 80%|████████  | 46141/57600 [8:06:38<1:54:17,  1.67it/s]
 80%|████████  | 46142/57600 [8:06:38<1:52:58,  1.69it/s]
 80%|████████  | 46143/57600 [8:06:39<1:55:43,  1.65it/s]
 80%|████████  | 46144/57600 [8:06:40<1:54:56,  1.66it/s]
 80%|████████  | 46145/57600 [8:06:40<1:56:29,  1.64it/s]
 80%|████████  | 46146/57600 [8:06:41<1:57:50,  1.62it/s]
 80%|████████  | 46147/57600 [8:06:42<1:59:21,  1.60it/s]
 80%|████████  | 46148/57600 [8:06:42<1:58:52,  1.61it/s]
 80%|████████  | 46149/57600 [8:06:43<1:58:33,  1.61it/s]
 80%|████████  | 46150/57600 [8:06:44<2:03:48,  1.54it/s]
 80%|████████  | 46151/57600 [8:06:44<2:01:53,  1.57it/s]
 80%|████████  | 46152/57600 [8:06:45<2:02:39,  1.56it/s]
 80%|████████  | 46153/57600 [8:06:45<2:01:02,  1.58it/s]
 80%|████████  | 46154/57600 [8:06:46<1:59:43,  1.59it/s]
 80%|████████  | 46155/57600 [8:06:47<2:03:34,  1.54it/s]
 80%|████████  | 46156/57600 [8:06:47<2:01:26,  1.57it/s]
 80%|████████  | 46157/57600 [8:06:48<1:58:47,  1.61it/s]
 80%|████████  | 46158/57600 [8:06:49<2:02:01,  1.56it/s]
 80%|████████  | 46159/57600 [8:06:49<2:01:28,  1.57it/s]
 80%|████████  | 46160/57600 [8:06:50<2:01:21,  1.57it/s]
                                                         
{'loss': 1.1322, 'learning_rate': 2.793728222996516e-07, 'epoch': 509.49}

 80%|████████  | 46160/57600 [8:06:50<2:01:21,  1.57it/s]
 80%|████████  | 46161/57600 [8:06:51<2:01:52,  1.56it/s]
 80%|████████  | 46162/57600 [8:06:51<2:00:02,  1.59it/s]
 80%|████████  | 46163/57600 [8:06:52<1:59:56,  1.59it/s]
 80%|████████  | 46164/57600 [8:06:52<1:56:47,  1.63it/s]
 80%|████████  | 46165/57600 [8:06:53<1:59:47,  1.59it/s]
 80%|████████  | 46166/57600 [8:06:54<1:59:29,  1.59it/s]
 80%|████████  | 46167/57600 [8:06:54<1:57:42,  1.62it/s]
 80%|████████  | 46168/57600 [8:06:55<1:58:58,  1.60it/s]
 80%|████████  | 46169/57600 [8:06:56<1:58:55,  1.60it/s]
 80%|████████  | 46170/57600 [8:06:56<1:58:34,  1.61it/s]
 80%|████████  | 46171/57600 [8:06:57<1:53:35,  1.68it/s]
 80%|████████  | 46172/57600 [8:06:57<1:53:22,  1.68it/s]
 80%|████████  | 46173/57600 [8:06:58<1:52:07,  1.70it/s]
 80%|████████  | 46174/57600 [8:06:59<1:59:03,  1.60it/s]
 80%|████████  | 46175/57600 [8:06:59<1:57:42,  1.62it/s]
 80%|████████  | 46176/57600 [8:07:00<2:00:50,  1.58it/s]
 80%|████████  | 46177/57600 [8:07:00<2:01:04,  1.57it/s]
 80%|████████  | 46178/57600 [8:07:01<1:58:50,  1.60it/s]
 80%|████████  | 46179/57600 [8:07:02<2:04:24,  1.53it/s]
 80%|████████  | 46180/57600 [8:07:02<2:02:01,  1.56it/s]
                                                         
{'loss': 1.1463, 'learning_rate': 2.7905923344947733e-07, 'epoch': 509.71}

 80%|████████  | 46180/57600 [8:07:02<2:02:01,  1.56it/s]
 80%|████████  | 46181/57600 [8:07:03<2:04:18,  1.53it/s]
 80%|████████  | 46182/57600 [8:07:04<2:04:22,  1.53it/s]
 80%|████████  | 46183/57600 [8:07:04<2:06:26,  1.50it/s]
 80%|████████  | 46184/57600 [8:07:05<2:03:57,  1.53it/s]
 80%|████████  | 46185/57600 [8:07:06<2:05:37,  1.51it/s]
 80%|████████  | 46186/57600 [8:07:06<2:06:17,  1.51it/s]
 80%|████████  | 46187/57600 [8:07:07<2:08:03,  1.49it/s]
 80%|████████  | 46188/57600 [8:07:08<2:05:36,  1.51it/s]
 80%|████████  | 46189/57600 [8:07:08<2:09:15,  1.47it/s]
 80%|████████  | 46190/57600 [8:07:09<2:08:36,  1.48it/s]
 80%|████████  | 46191/57600 [8:07:10<2:10:25,  1.46it/s]
 80%|████████  | 46192/57600 [8:07:10<2:02:16,  1.55it/s]
 80%|████████  | 46193/57600 [8:07:11<1:59:08,  1.60it/s]
 80%|████████  | 46194/57600 [8:07:12<1:55:41,  1.64it/s]
 80%|████████  | 46195/57600 [8:07:12<1:58:25,  1.61it/s]
 80%|████████  | 46196/57600 [8:07:13<1:57:48,  1.61it/s]
 80%|████████  | 46197/57600 [8:07:13<2:00:48,  1.57it/s]
 80%|████████  | 46198/57600 [8:07:14<2:02:52,  1.55it/s]
 80%|████████  | 46199/57600 [8:07:15<2:04:39,  1.52it/s]
 80%|████████  | 46200/57600 [8:07:15<1:59:53,  1.58it/s]
                                                         
{'loss': 1.1159, 'learning_rate': 2.787456445993032e-07, 'epoch': 509.93}

 80%|████████  | 46200/57600 [8:07:15<1:59:53,  1.58it/s]
 80%|████████  | 46201/57600 [8:07:16<2:03:55,  1.53it/s]
 80%|████████  | 46202/57600 [8:07:17<2:03:19,  1.54it/s]
 80%|████████  | 46203/57600 [8:07:17<2:02:02,  1.56it/s]
 80%|████████  | 46204/57600 [8:07:18<1:59:46,  1.59it/s]
 80%|████████  | 46205/57600 [8:07:19<2:00:51,  1.57it/s]
 80%|████████  | 46206/57600 [8:07:19<2:03:11,  1.54it/s]
 80%|████████  | 46207/57600 [8:07:20<2:06:48,  1.50it/s]
 80%|████████  | 46208/57600 [8:07:21<2:04:07,  1.53it/s]
 80%|████████  | 46209/57600 [8:07:21<2:05:06,  1.52it/s]
 80%|████████  | 46210/57600 [8:07:22<2:02:01,  1.56it/s]
 80%|████████  | 46211/57600 [8:07:22<1:59:36,  1.59it/s]
 80%|████████  | 46212/57600 [8:07:23<1:57:41,  1.61it/s]
 80%|████████  | 46213/57600 [8:07:24<1:59:16,  1.59it/s]
 80%|████████  | 46214/57600 [8:07:24<2:06:31,  1.50it/s]
 80%|████████  | 46215/57600 [8:07:25<2:02:04,  1.55it/s]
 80%|████████  | 46216/57600 [8:07:26<1:58:41,  1.60it/s]
 80%|████████  | 46217/57600 [8:07:26<1:58:51,  1.60it/s]
 80%|████████  | 46218/57600 [8:07:27<1:54:15,  1.66it/s]
 80%|████████  | 46219/57600 [8:07:27<1:56:31,  1.63it/s]
 80%|████████  | 46220/57600 [8:07:28<1:59:27,  1.59it/s]
                                                         
{'loss': 1.1214, 'learning_rate': 2.784320557491289e-07, 'epoch': 510.15}

 80%|████████  | 46220/57600 [8:07:28<1:59:27,  1.59it/s]
 80%|████████  | 46221/57600 [8:07:29<1:59:28,  1.59it/s]
 80%|████████  | 46222/57600 [8:07:29<2:01:17,  1.56it/s]
 80%|████████  | 46223/57600 [8:07:30<2:01:18,  1.56it/s]
 80%|████████  | 46224/57600 [8:07:31<2:01:23,  1.56it/s]
 80%|████████  | 46225/57600 [8:07:31<2:00:26,  1.57it/s]
 80%|████████  | 46226/57600 [8:07:32<2:02:33,  1.55it/s]
 80%|████████  | 46227/57600 [8:07:33<1:59:51,  1.58it/s]
 80%|████████  | 46228/57600 [8:07:33<2:00:37,  1.57it/s]
 80%|████████  | 46229/57600 [8:07:34<1:59:59,  1.58it/s]
 80%|████████  | 46230/57600 [8:07:34<1:58:56,  1.59it/s]
 80%|████████  | 46231/57600 [8:07:35<1:57:22,  1.61it/s]
 80%|████████  | 46232/57600 [8:07:36<1:56:16,  1.63it/s]
 80%|████████  | 46233/57600 [8:07:36<2:01:31,  1.56it/s]
 80%|████████  | 46234/57600 [8:07:37<1:57:55,  1.61it/s]
 80%|████████  | 46235/57600 [8:07:38<1:55:53,  1.63it/s]
 80%|████████  | 46236/57600 [8:07:38<2:00:53,  1.57it/s]
 80%|████████  | 46237/57600 [8:07:39<1:56:40,  1.62it/s]
 80%|████████  | 46238/57600 [8:07:39<1:56:07,  1.63it/s]
 80%|████████  | 46239/57600 [8:07:40<1:54:13,  1.66it/s]
 80%|████████  | 46240/57600 [8:07:41<1:54:03,  1.66it/s]
                                                         
{'loss': 1.1087, 'learning_rate': 2.781184668989547e-07, 'epoch': 510.38}

 80%|████████  | 46240/57600 [8:07:41<1:54:03,  1.66it/s]
 80%|████████  | 46241/57600 [8:07:41<1:58:46,  1.59it/s]
 80%|████████  | 46242/57600 [8:07:42<1:59:51,  1.58it/s]
 80%|████████  | 46243/57600 [8:07:43<2:01:29,  1.56it/s]
 80%|████████  | 46244/57600 [8:07:43<2:02:25,  1.55it/s]
 80%|████████  | 46245/57600 [8:07:44<1:59:17,  1.59it/s]
 80%|████████  | 46246/57600 [8:07:44<1:59:12,  1.59it/s]
 80%|████████  | 46247/57600 [8:07:45<2:01:20,  1.56it/s]
 80%|████████  | 46248/57600 [8:07:46<2:01:36,  1.56it/s]
 80%|████████  | 46249/57600 [8:07:47<2:05:19,  1.51it/s]
 80%|████████  | 46250/57600 [8:07:47<2:04:48,  1.52it/s]
 80%|████████  | 46251/57600 [8:07:48<2:08:00,  1.48it/s]
 80%|████████  | 46252/57600 [8:07:48<2:03:52,  1.53it/s]
 80%|████████  | 46253/57600 [8:07:49<1:59:33,  1.58it/s]
 80%|████████  | 46254/57600 [8:07:50<1:59:40,  1.58it/s]
 80%|████████  | 46255/57600 [8:07:50<2:04:40,  1.52it/s]
 80%|████████  | 46256/57600 [8:07:51<2:03:44,  1.53it/s]
 80%|████████  | 46257/57600 [8:07:52<2:01:55,  1.55it/s]
 80%|████████  | 46258/57600 [8:07:52<2:04:26,  1.52it/s]
 80%|████████  | 46259/57600 [8:07:53<2:00:26,  1.57it/s]
 80%|████████  | 46260/57600 [8:07:54<1:57:12,  1.61it/s]
                                                         
{'loss': 1.0912, 'learning_rate': 2.7780487804878044e-07, 'epoch': 510.6}

 80%|████████  | 46260/57600 [8:07:54<1:57:12,  1.61it/s]
 80%|████████  | 46261/57600 [8:07:54<1:58:29,  1.59it/s]
 80%|████████  | 46262/57600 [8:07:55<1:59:03,  1.59it/s]
 80%|████████  | 46263/57600 [8:07:55<2:00:09,  1.57it/s]
 80%|████████  | 46264/57600 [8:07:56<2:01:05,  1.56it/s]
 80%|████████  | 46265/57600 [8:07:57<2:02:25,  1.54it/s]
 80%|████████  | 46266/57600 [8:07:57<2:02:58,  1.54it/s]
 80%|████████  | 46267/57600 [8:07:58<2:03:21,  1.53it/s]
 80%|████████  | 46268/57600 [8:07:59<2:02:20,  1.54it/s]
 80%|████████  | 46269/57600 [8:07:59<2:03:10,  1.53it/s]
 80%|████████  | 46270/57600 [8:08:00<1:57:55,  1.60it/s]
 80%|████████  | 46271/57600 [8:08:01<1:58:17,  1.60it/s]
 80%|████████  | 46272/57600 [8:08:01<1:58:49,  1.59it/s]
 80%|████████  | 46273/57600 [8:08:02<1:59:14,  1.58it/s]
 80%|████████  | 46274/57600 [8:08:02<1:56:33,  1.62it/s]
 80%|████████  | 46275/57600 [8:08:03<1:56:44,  1.62it/s]
 80%|████████  | 46276/57600 [8:08:04<1:58:12,  1.60it/s]
 80%|████████  | 46277/57600 [8:08:04<1:59:34,  1.58it/s]
 80%|████████  | 46278/57600 [8:08:05<1:55:30,  1.63it/s]
 80%|████████  | 46279/57600 [8:08:06<1:56:57,  1.61it/s]
 80%|████████  | 46280/57600 [8:08:06<1:58:16,  1.60it/s]
                                                         
{'loss': 1.1016, 'learning_rate': 2.774912891986063e-07, 'epoch': 510.82}

 80%|████████  | 46280/57600 [8:08:06<1:58:16,  1.60it/s]
 80%|████████  | 46281/57600 [8:08:07<1:53:34,  1.66it/s]
 80%|████████  | 46282/57600 [8:08:07<1:53:34,  1.66it/s]
 80%|████████  | 46283/57600 [8:08:08<1:56:01,  1.63it/s]
 80%|████████  | 46284/57600 [8:08:09<1:55:49,  1.63it/s]
 80%|████████  | 46285/57600 [8:08:09<1:54:56,  1.64it/s]
 80%|████████  | 46286/57600 [8:08:10<1:58:33,  1.59it/s]
 80%|████████  | 46287/57600 [8:08:10<1:55:46,  1.63it/s]
 80%|████████  | 46288/57600 [8:08:11<1:59:28,  1.58it/s]
 80%|████████  | 46289/57600 [8:08:12<1:59:19,  1.58it/s]
 80%|████████  | 46290/57600 [8:08:12<1:58:59,  1.58it/s]
 80%|████████  | 46291/57600 [8:08:13<1:56:42,  1.61it/s]
 80%|████████  | 46292/57600 [8:08:14<1:55:12,  1.64it/s]
 80%|████████  | 46293/57600 [8:08:14<1:54:10,  1.65it/s]
 80%|████████  | 46294/57600 [8:08:15<1:55:54,  1.63it/s]
 80%|████████  | 46295/57600 [8:08:15<1:54:18,  1.65it/s]
 80%|████████  | 46296/57600 [8:08:16<1:55:57,  1.62it/s]
 80%|████████  | 46297/57600 [8:08:17<2:00:30,  1.56it/s]
 80%|████████  | 46298/57600 [8:08:17<1:58:33,  1.59it/s]
 80%|████████  | 46299/57600 [8:08:18<1:57:22,  1.60it/s]
 80%|████████  | 46300/57600 [8:08:19<2:01:18,  1.55it/s]
                                                         
{'loss': 1.1232, 'learning_rate': 2.7717770034843205e-07, 'epoch': 511.04}

 80%|████████  | 46300/57600 [8:08:19<2:01:18,  1.55it/s]
 80%|████████  | 46301/57600 [8:08:19<1:56:35,  1.62it/s]
 80%|████████  | 46302/57600 [8:08:20<1:55:13,  1.63it/s]
 80%|████████  | 46303/57600 [8:08:20<1:53:44,  1.66it/s]
 80%|████████  | 46304/57600 [8:08:21<1:56:02,  1.62it/s]
 80%|████████  | 46305/57600 [8:08:22<2:01:12,  1.55it/s]
 80%|████████  | 46306/57600 [8:08:22<1:58:47,  1.58it/s]
 80%|████████  | 46307/57600 [8:08:23<1:58:11,  1.59it/s]
 80%|████████  | 46308/57600 [8:08:24<1:57:54,  1.60it/s]
 80%|████████  | 46309/57600 [8:08:24<1:59:24,  1.58it/s]
 80%|████████  | 46310/57600 [8:08:25<2:00:36,  1.56it/s]
 80%|████████  | 46311/57600 [8:08:26<2:01:30,  1.55it/s]
 80%|████████  | 46312/57600 [8:08:26<2:00:35,  1.56it/s]
 80%|████████  | 46313/57600 [8:08:27<1:58:20,  1.59it/s]
 80%|████████  | 46314/57600 [8:08:27<1:55:23,  1.63it/s]
 80%|████████  | 46315/57600 [8:08:28<1:53:32,  1.66it/s]
 80%|████████  | 46316/57600 [8:08:29<1:53:20,  1.66it/s]
 80%|████████  | 46317/57600 [8:08:29<1:52:32,  1.67it/s]
 80%|████████  | 46318/57600 [8:08:30<1:56:53,  1.61it/s]
 80%|████████  | 46319/57600 [8:08:30<1:58:45,  1.58it/s]
 80%|████████  | 46320/57600 [8:08:31<1:56:50,  1.61it/s]
                                                         
{'loss': 1.1398, 'learning_rate': 2.768641114982578e-07, 'epoch': 511.26}

 80%|████████  | 46320/57600 [8:08:31<1:56:50,  1.61it/s]
 80%|████████  | 46321/57600 [8:08:32<1:54:16,  1.64it/s]
 80%|████████  | 46322/57600 [8:08:32<1:56:32,  1.61it/s]
 80%|████████  | 46323/57600 [8:08:33<1:56:12,  1.62it/s]
 80%|████████  | 46324/57600 [8:08:34<1:55:40,  1.62it/s]
 80%|████████  | 46325/57600 [8:08:34<1:55:15,  1.63it/s]
 80%|████████  | 46326/57600 [8:08:35<1:53:36,  1.65it/s]
 80%|████████  | 46327/57600 [8:08:35<1:58:04,  1.59it/s]
 80%|████████  | 46328/57600 [8:08:36<1:57:48,  1.59it/s]
 80%|████████  | 46329/57600 [8:08:37<1:58:42,  1.58it/s]
 80%|████████  | 46330/57600 [8:08:37<1:57:26,  1.60it/s]
 80%|████████  | 46331/57600 [8:08:38<1:57:57,  1.59it/s]
 80%|████████  | 46332/57600 [8:08:38<1:55:11,  1.63it/s]
 80%|████████  | 46333/57600 [8:08:39<1:56:08,  1.62it/s]
 80%|████████  | 46334/57600 [8:08:40<1:56:11,  1.62it/s]
 80%|████████  | 46335/57600 [8:08:40<1:52:20,  1.67it/s]
 80%|████████  | 46336/57600 [8:08:41<1:52:25,  1.67it/s]
 80%|████████  | 46337/57600 [8:08:42<1:56:54,  1.61it/s]
 80%|████████  | 46338/57600 [8:08:42<1:58:14,  1.59it/s]
 80%|████████  | 46339/57600 [8:08:43<2:02:23,  1.53it/s]
 80%|████████  | 46340/57600 [8:08:44<2:02:28,  1.53it/s]
                                                         
{'loss': 1.1016, 'learning_rate': 2.7655052264808366e-07, 'epoch': 511.48}

 80%|████████  | 46340/57600 [8:08:44<2:02:28,  1.53it/s]
 80%|████████  | 46341/57600 [8:08:44<1:59:37,  1.57it/s]
 80%|████████  | 46342/57600 [8:08:45<1:59:34,  1.57it/s]
 80%|████████  | 46343/57600 [8:08:45<2:00:09,  1.56it/s]
 80%|████████  | 46344/57600 [8:08:46<1:59:18,  1.57it/s]
 80%|████████  | 46345/57600 [8:08:47<2:05:11,  1.50it/s]
 80%|████████  | 46346/57600 [8:08:47<2:01:00,  1.55it/s]
 80%|████████  | 46347/57600 [8:08:48<2:04:48,  1.50it/s]
 80%|████████  | 46348/57600 [8:08:49<2:01:58,  1.54it/s]
 80%|████████  | 46349/57600 [8:08:49<2:02:32,  1.53it/s]
 80%|████████  | 46350/57600 [8:08:50<2:00:48,  1.55it/s]
 80%|████████  | 46351/57600 [8:08:51<1:56:37,  1.61it/s]
 80%|████████  | 46352/57600 [8:08:51<1:58:37,  1.58it/s]
 80%|████████  | 46353/57600 [8:08:52<1:59:26,  1.57it/s]
 80%|████████  | 46354/57600 [8:08:53<1:58:51,  1.58it/s]
 80%|████████  | 46355/57600 [8:08:53<2:00:19,  1.56it/s]
 80%|████████  | 46356/57600 [8:08:54<1:58:02,  1.59it/s]
 80%|████████  | 46357/57600 [8:08:54<1:58:09,  1.59it/s]
 80%|████████  | 46358/57600 [8:08:55<2:00:12,  1.56it/s]
 80%|████████  | 46359/57600 [8:08:56<1:58:49,  1.58it/s]
 80%|████████  | 46360/57600 [8:08:56<2:02:04,  1.53it/s]
                                                         
{'loss': 1.1341, 'learning_rate': 2.7623693379790936e-07, 'epoch': 511.7}

 80%|████████  | 46360/57600 [8:08:56<2:02:04,  1.53it/s]
 80%|████████  | 46361/57600 [8:08:57<2:04:53,  1.50it/s]
 80%|████████  | 46362/57600 [8:08:58<2:02:00,  1.54it/s]
 80%|████████  | 46363/57600 [8:08:58<2:04:32,  1.50it/s]
 80%|████████  | 46364/57600 [8:08:59<2:03:53,  1.51it/s]
 80%|████████  | 46365/57600 [8:09:00<2:01:06,  1.55it/s]
 80%|████████  | 46366/57600 [8:09:00<1:57:49,  1.59it/s]
 80%|████████  | 46367/57600 [8:09:01<1:55:05,  1.63it/s]
 80%|████████  | 46368/57600 [8:09:01<1:57:20,  1.60it/s]
 81%|████████  | 46369/57600 [8:09:02<1:58:37,  1.58it/s]
 81%|████████  | 46370/57600 [8:09:03<1:56:26,  1.61it/s]
 81%|████████  | 46371/57600 [8:09:03<1:57:07,  1.60it/s]
 81%|████████  | 46372/57600 [8:09:04<1:56:53,  1.60it/s]
 81%|████████  | 46373/57600 [8:09:05<1:55:37,  1.62it/s]
 81%|████████  | 46374/57600 [8:09:05<1:58:47,  1.57it/s]
 81%|████████  | 46375/57600 [8:09:06<1:56:49,  1.60it/s]
 81%|████████  | 46376/57600 [8:09:06<1:55:55,  1.61it/s]
 81%|████████  | 46377/57600 [8:09:07<1:57:41,  1.59it/s]
 81%|████████  | 46378/57600 [8:09:08<1:56:15,  1.61it/s]
 81%|████████  | 46379/57600 [8:09:08<1:56:37,  1.60it/s]
 81%|████████  | 46380/57600 [8:09:09<1:52:30,  1.66it/s]
                                                         
{'loss': 1.1043, 'learning_rate': 2.7592334494773516e-07, 'epoch': 511.92}

 81%|████████  | 46380/57600 [8:09:09<1:52:30,  1.66it/s]
 81%|████████  | 46381/57600 [8:09:10<1:53:23,  1.65it/s]
 81%|████████  | 46382/57600 [8:09:10<1:51:55,  1.67it/s]
 81%|████████  | 46383/57600 [8:09:11<1:52:05,  1.67it/s]
 81%|████████  | 46384/57600 [8:09:11<1:56:17,  1.61it/s]
 81%|████████  | 46385/57600 [8:09:12<1:51:57,  1.67it/s]
 81%|████████  | 46386/57600 [8:09:13<2:00:11,  1.55it/s]
 81%|████████  | 46387/57600 [8:09:13<1:55:55,  1.61it/s]
 81%|████████  | 46388/57600 [8:09:14<2:01:41,  1.54it/s]
 81%|████████  | 46389/57600 [8:09:15<2:00:08,  1.56it/s]
 81%|████████  | 46390/57600 [8:09:15<1:59:32,  1.56it/s]
 81%|████████  | 46391/57600 [8:09:16<2:06:39,  1.47it/s]
 81%|████████  | 46392/57600 [8:09:17<2:03:23,  1.51it/s]
 81%|████████  | 46393/57600 [8:09:17<2:01:25,  1.54it/s]
 81%|████████  | 46394/57600 [8:09:18<2:05:31,  1.49it/s]
 81%|████████  | 46395/57600 [8:09:19<2:00:00,  1.56it/s]
 81%|████████  | 46396/57600 [8:09:19<1:55:22,  1.62it/s]
 81%|████████  | 46397/57600 [8:09:20<1:52:59,  1.65it/s]
 81%|████████  | 46398/57600 [8:09:20<1:52:35,  1.66it/s]
 81%|████████  | 46399/57600 [8:09:21<1:56:22,  1.60it/s]
 81%|████████  | 46400/57600 [8:09:22<1:59:51,  1.56it/s]
                                                         
{'loss': 1.1382, 'learning_rate': 2.756097560975609e-07, 'epoch': 512.14}

 81%|████████  | 46400/57600 [8:09:22<1:59:51,  1.56it/s]
 81%|████████  | 46401/57600 [8:09:22<2:01:10,  1.54it/s]
 81%|████████  | 46402/57600 [8:09:23<2:04:25,  1.50it/s]
 81%|████████  | 46403/57600 [8:09:24<2:01:39,  1.53it/s]
 81%|████████  | 46404/57600 [8:09:24<1:59:58,  1.56it/s]
 81%|████████  | 46405/57600 [8:09:25<1:59:46,  1.56it/s]
 81%|████████  | 46406/57600 [8:09:26<2:00:26,  1.55it/s]
 81%|████████  | 46407/57600 [8:09:26<2:07:05,  1.47it/s]
 81%|████████  | 46408/57600 [8:09:27<2:07:04,  1.47it/s]
 81%|████████  | 46409/57600 [8:09:28<2:01:26,  1.54it/s]
 81%|████████  | 46410/57600 [8:09:28<2:00:10,  1.55it/s]
 81%|████████  | 46411/57600 [8:09:29<2:01:23,  1.54it/s]
 81%|████████  | 46412/57600 [8:09:29<2:00:11,  1.55it/s]
 81%|████████  | 46413/57600 [8:09:30<1:57:00,  1.59it/s]
 81%|████████  | 46414/57600 [8:09:31<1:56:47,  1.60it/s]
 81%|████████  | 46415/57600 [8:09:31<1:54:00,  1.64it/s]
 81%|████████  | 46416/57600 [8:09:32<1:53:23,  1.64it/s]
 81%|████████  | 46417/57600 [8:09:32<1:51:40,  1.67it/s]
 81%|████████  | 46418/57600 [8:09:33<1:51:29,  1.67it/s]
 81%|████████  | 46419/57600 [8:09:34<1:53:03,  1.65it/s]
 81%|████████  | 46420/57600 [8:09:34<1:52:46,  1.65it/s]
                                                         
{'loss': 1.1341, 'learning_rate': 2.7529616724738683e-07, 'epoch': 512.36}

 81%|████████  | 46420/57600 [8:09:34<1:52:46,  1.65it/s]
 81%|████████  | 46421/57600 [8:09:35<1:53:56,  1.64it/s]
 81%|████████  | 46422/57600 [8:09:35<1:49:52,  1.70it/s]
 81%|████████  | 46423/57600 [8:09:36<1:54:08,  1.63it/s]
 81%|████████  | 46424/57600 [8:09:37<1:56:20,  1.60it/s]
 81%|████████  | 46425/57600 [8:09:37<1:56:06,  1.60it/s]
 81%|████████  | 46426/57600 [8:09:38<1:53:08,  1.65it/s]
 81%|████████  | 46427/57600 [8:09:39<1:52:04,  1.66it/s]
 81%|████████  | 46428/57600 [8:09:39<1:54:16,  1.63it/s]
 81%|████████  | 46429/57600 [8:09:40<1:54:37,  1.62it/s]
 81%|████████  | 46430/57600 [8:09:40<1:54:21,  1.63it/s]
 81%|████████  | 46431/57600 [8:09:41<1:59:07,  1.56it/s]
 81%|████████  | 46432/57600 [8:09:42<2:00:08,  1.55it/s]
 81%|████████  | 46433/57600 [8:09:42<2:01:46,  1.53it/s]
 81%|████████  | 46434/57600 [8:09:43<2:02:58,  1.51it/s]
 81%|████████  | 46435/57600 [8:09:44<1:59:20,  1.56it/s]
 81%|████████  | 46436/57600 [8:09:44<1:58:15,  1.57it/s]
 81%|████████  | 46437/57600 [8:09:45<1:58:11,  1.57it/s]
 81%|████████  | 46438/57600 [8:09:46<1:55:00,  1.62it/s]
 81%|████████  | 46439/57600 [8:09:46<1:59:14,  1.56it/s]
 81%|████████  | 46440/57600 [8:09:47<2:00:24,  1.54it/s]
                                                         
{'loss': 1.1054, 'learning_rate': 2.749825783972126e-07, 'epoch': 512.58}

 81%|████████  | 46440/57600 [8:09:47<2:00:24,  1.54it/s]
 81%|████████  | 46441/57600 [8:09:48<2:06:08,  1.47it/s]
 81%|████████  | 46442/57600 [8:09:48<2:01:11,  1.53it/s]
 81%|████████  | 46443/57600 [8:09:49<1:59:13,  1.56it/s]
 81%|████████  | 46444/57600 [8:09:49<1:58:31,  1.57it/s]
 81%|████████  | 46445/57600 [8:09:50<1:55:32,  1.61it/s]
 81%|████████  | 46446/57600 [8:09:51<1:54:02,  1.63it/s]
 81%|████████  | 46447/57600 [8:09:51<1:53:14,  1.64it/s]
 81%|████████  | 46448/57600 [8:09:52<1:52:46,  1.65it/s]
 81%|████████  | 46449/57600 [8:09:52<1:51:06,  1.67it/s]
 81%|████████  | 46450/57600 [8:09:53<1:52:40,  1.65it/s]
 81%|████████  | 46451/57600 [8:09:54<1:56:01,  1.60it/s]
 81%|████████  | 46452/57600 [8:09:54<1:58:36,  1.57it/s]
 81%|████████  | 46453/57600 [8:09:55<1:56:11,  1.60it/s]
 81%|████████  | 46454/57600 [8:09:56<1:55:00,  1.62it/s]
 81%|████████  | 46455/57600 [8:09:56<2:01:19,  1.53it/s]
 81%|████████  | 46456/57600 [8:09:57<1:59:30,  1.55it/s]
 81%|████████  | 46457/57600 [8:09:58<1:58:31,  1.57it/s]
 81%|████████  | 46458/57600 [8:09:58<2:01:23,  1.53it/s]
 81%|████████  | 46459/57600 [8:09:59<1:57:18,  1.58it/s]
 81%|████████  | 46460/57600 [8:09:59<1:57:14,  1.58it/s]
                                                         
{'loss': 1.1304, 'learning_rate': 2.746689895470383e-07, 'epoch': 512.8}

 81%|████████  | 46460/57600 [8:09:59<1:57:14,  1.58it/s]
 81%|████████  | 46461/57600 [8:10:00<1:57:00,  1.59it/s]
 81%|████████  | 46462/57600 [8:10:01<1:58:17,  1.57it/s]
 81%|████████  | 46463/57600 [8:10:01<2:02:12,  1.52it/s]
 81%|████████  | 46464/57600 [8:10:02<1:59:10,  1.56it/s]
 81%|████████  | 46465/57600 [8:10:03<2:01:55,  1.52it/s]
 81%|████████  | 46466/57600 [8:10:03<1:58:01,  1.57it/s]
 81%|████████  | 46467/57600 [8:10:04<1:56:16,  1.60it/s]
 81%|████████  | 46468/57600 [8:10:05<1:55:51,  1.60it/s]
 81%|████████  | 46469/57600 [8:10:05<1:56:21,  1.59it/s]
 81%|████████  | 46470/57600 [8:10:06<1:57:23,  1.58it/s]
 81%|████████  | 46471/57600 [8:10:06<1:53:36,  1.63it/s]
 81%|████████  | 46472/57600 [8:10:07<1:57:04,  1.58it/s]
 81%|████████  | 46473/57600 [8:10:08<1:58:38,  1.56it/s]
 81%|████████  | 46474/57600 [8:10:08<1:59:52,  1.55it/s]
 81%|████████  | 46475/57600 [8:10:09<1:55:38,  1.60it/s]
 81%|████████  | 46476/57600 [8:10:10<1:59:08,  1.56it/s]
 81%|████████  | 46477/57600 [8:10:10<1:57:43,  1.57it/s]
 81%|████████  | 46478/57600 [8:10:11<1:59:50,  1.55it/s]
 81%|████████  | 46479/57600 [8:10:12<1:59:56,  1.55it/s]
 81%|████████  | 46480/57600 [8:10:12<2:00:05,  1.54it/s]
                                                         
{'loss': 1.1042, 'learning_rate': 2.7435540069686414e-07, 'epoch': 513.02}

 81%|████████  | 46480/57600 [8:10:12<2:00:05,  1.54it/s]
 81%|████████  | 46481/57600 [8:10:13<1:59:48,  1.55it/s]
 81%|████████  | 46482/57600 [8:10:14<2:02:50,  1.51it/s]
 81%|████████  | 46483/57600 [8:10:14<2:08:28,  1.44it/s]
 81%|████████  | 46484/57600 [8:10:15<2:04:17,  1.49it/s]
 81%|████████  | 46485/57600 [8:10:16<2:01:21,  1.53it/s]
 81%|████████  | 46486/57600 [8:10:16<2:05:40,  1.47it/s]
 81%|████████  | 46487/57600 [8:10:17<1:59:33,  1.55it/s]
 81%|████████  | 46488/57600 [8:10:18<1:57:52,  1.57it/s]
 81%|████████  | 46489/57600 [8:10:18<1:57:03,  1.58it/s]
 81%|████████  | 46490/57600 [8:10:19<1:53:53,  1.63it/s]
 81%|████████  | 46491/57600 [8:10:19<1:54:11,  1.62it/s]
 81%|████████  | 46492/57600 [8:10:20<1:55:24,  1.60it/s]
 81%|████████  | 46493/57600 [8:10:21<1:58:09,  1.57it/s]
 81%|████████  | 46494/57600 [8:10:21<1:57:09,  1.58it/s]
 81%|████████  | 46495/57600 [8:10:22<1:56:03,  1.59it/s]
 81%|████████  | 46496/57600 [8:10:22<1:53:21,  1.63it/s]
 81%|████████  | 46497/57600 [8:10:23<1:54:51,  1.61it/s]
 81%|████████  | 46498/57600 [8:10:24<1:55:58,  1.60it/s]
 81%|████████  | 46499/57600 [8:10:24<1:57:38,  1.57it/s]
 81%|████████  | 46500/57600 [8:10:25<2:01:52,  1.52it/s]
                                                         
{'loss': 1.1057, 'learning_rate': 2.740418118466899e-07, 'epoch': 513.25}

 81%|████████  | 46500/57600 [8:10:25<2:01:52,  1.52it/s]
 81%|████████  | 46501/57600 [8:10:26<1:59:45,  1.54it/s]
 81%|████████  | 46502/57600 [8:10:26<1:59:10,  1.55it/s]
 81%|████████  | 46503/57600 [8:10:27<1:56:10,  1.59it/s]
 81%|████████  | 46504/57600 [8:10:28<1:56:54,  1.58it/s]
 81%|████████  | 46505/57600 [8:10:28<1:53:48,  1.62it/s]
 81%|████████  | 46506/57600 [8:10:29<1:55:58,  1.59it/s]
 81%|████████  | 46507/57600 [8:10:29<1:54:18,  1.62it/s]
 81%|████████  | 46508/57600 [8:10:30<1:57:58,  1.57it/s]
 81%|████████  | 46509/57600 [8:10:31<1:55:12,  1.60it/s]
 81%|████████  | 46510/57600 [8:10:31<1:53:48,  1.62it/s]
 81%|████████  | 46511/57600 [8:10:32<1:53:07,  1.63it/s]
 81%|████████  | 46512/57600 [8:10:33<1:53:38,  1.63it/s]
 81%|████████  | 46513/57600 [8:10:33<1:56:27,  1.59it/s]
 81%|████████  | 46514/57600 [8:10:34<1:53:26,  1.63it/s]
 81%|████████  | 46515/57600 [8:10:34<1:52:17,  1.65it/s]
 81%|████████  | 46516/57600 [8:10:35<1:50:59,  1.66it/s]
 81%|████████  | 46517/57600 [8:10:36<1:52:57,  1.64it/s]
 81%|████████  | 46518/57600 [8:10:36<1:53:17,  1.63it/s]
 81%|████████  | 46519/57600 [8:10:37<1:54:18,  1.62it/s]
 81%|████████  | 46520/57600 [8:10:37<1:53:08,  1.63it/s]
                                                         
{'loss': 1.1488, 'learning_rate': 2.7372822299651564e-07, 'epoch': 513.47}

 81%|████████  | 46520/57600 [8:10:37<1:53:08,  1.63it/s]
 81%|████████  | 46521/57600 [8:10:38<1:51:36,  1.65it/s]
 81%|████████  | 46522/57600 [8:10:39<1:51:27,  1.66it/s]
 81%|████████  | 46523/57600 [8:10:39<1:52:00,  1.65it/s]
 81%|████████  | 46524/57600 [8:10:40<1:52:02,  1.65it/s]
 81%|████████  | 46525/57600 [8:10:40<1:49:20,  1.69it/s]
 81%|████████  | 46526/57600 [8:10:41<1:52:49,  1.64it/s]
 81%|████████  | 46527/57600 [8:10:42<1:50:57,  1.66it/s]
 81%|████████  | 46528/57600 [8:10:42<1:53:37,  1.62it/s]
 81%|████████  | 46529/57600 [8:10:43<1:52:07,  1.65it/s]
 81%|████████  | 46530/57600 [8:10:43<1:51:59,  1.65it/s]
 81%|████████  | 46531/57600 [8:10:44<1:50:42,  1.67it/s]
 81%|████████  | 46532/57600 [8:10:45<1:52:25,  1.64it/s]
 81%|████████  | 46533/57600 [8:10:45<1:50:43,  1.67it/s]
 81%|████████  | 46534/57600 [8:10:46<1:54:13,  1.61it/s]
 81%|████████  | 46535/57600 [8:10:47<1:53:46,  1.62it/s]
 81%|████████  | 46536/57600 [8:10:47<1:50:56,  1.66it/s]
 81%|████████  | 46537/57600 [8:10:48<1:54:12,  1.61it/s]
 81%|████████  | 46538/57600 [8:10:48<1:51:20,  1.66it/s]
 81%|████████  | 46539/57600 [8:10:49<1:52:48,  1.63it/s]
 81%|████████  | 46540/57600 [8:10:50<1:51:05,  1.66it/s]
                                                         
{'loss': 1.1476, 'learning_rate': 2.734146341463414e-07, 'epoch': 513.69}

 81%|████████  | 46540/57600 [8:10:50<1:51:05,  1.66it/s]
 81%|████████  | 46541/57600 [8:10:50<1:52:36,  1.64it/s]
 81%|████████  | 46542/57600 [8:10:51<1:54:43,  1.61it/s]
 81%|████████  | 46543/57600 [8:10:51<1:52:15,  1.64it/s]
 81%|████████  | 46544/57600 [8:10:52<1:53:14,  1.63it/s]
 81%|████████  | 46545/57600 [8:10:53<1:54:27,  1.61it/s]
 81%|████████  | 46546/57600 [8:10:53<1:53:30,  1.62it/s]
 81%|████████  | 46547/57600 [8:10:54<1:54:39,  1.61it/s]
 81%|████████  | 46548/57600 [8:10:55<1:53:27,  1.62it/s]
 81%|████████  | 46549/57600 [8:10:55<1:58:24,  1.56it/s]
 81%|████████  | 46550/57600 [8:10:56<1:59:10,  1.55it/s]
 81%|████████  | 46551/57600 [8:10:57<2:00:05,  1.53it/s]
 81%|████████  | 46552/57600 [8:10:57<1:56:56,  1.57it/s]
 81%|████████  | 46553/57600 [8:10:58<1:56:26,  1.58it/s]
 81%|████████  | 46554/57600 [8:10:58<1:58:03,  1.56it/s]
 81%|████████  | 46555/57600 [8:10:59<2:00:39,  1.53it/s]
 81%|████████  | 46556/57600 [8:11:00<1:57:36,  1.57it/s]
 81%|████████  | 46557/57600 [8:11:00<1:55:51,  1.59it/s]
 81%|████████  | 46558/57600 [8:11:01<1:54:13,  1.61it/s]
 81%|████████  | 46559/57600 [8:11:02<1:52:41,  1.63it/s]
 81%|████████  | 46560/57600 [8:11:02<1:51:25,  1.65it/s]
                                                         
{'loss': 1.1214, 'learning_rate': 2.7310104529616725e-07, 'epoch': 513.91}

 81%|████████  | 46560/57600 [8:11:02<1:51:25,  1.65it/s]
 81%|████████  | 46561/57600 [8:11:03<1:54:44,  1.60it/s]
 81%|████████  | 46562/57600 [8:11:03<1:59:19,  1.54it/s]
 81%|████████  | 46563/57600 [8:11:04<1:57:40,  1.56it/s]
 81%|████████  | 46564/57600 [8:11:05<2:00:44,  1.52it/s]
 81%|████████  | 46565/57600 [8:11:05<1:56:18,  1.58it/s]
 81%|████████  | 46566/57600 [8:11:06<1:56:53,  1.57it/s]
 81%|████████  | 46567/57600 [8:11:07<1:58:44,  1.55it/s]
 81%|████████  | 46568/57600 [8:11:07<2:02:54,  1.50it/s]
 81%|████████  | 46569/57600 [8:11:08<2:03:36,  1.49it/s]
 81%|████████  | 46570/57600 [8:11:09<2:02:18,  1.50it/s]
 81%|████████  | 46571/57600 [8:11:09<1:59:44,  1.54it/s]
 81%|████████  | 46572/57600 [8:11:10<1:57:42,  1.56it/s]
 81%|████████  | 46573/57600 [8:11:11<1:54:52,  1.60it/s]
 81%|████████  | 46574/57600 [8:11:11<1:54:00,  1.61it/s]
 81%|████████  | 46575/57600 [8:11:12<1:52:36,  1.63it/s]
 81%|████████  | 46576/57600 [8:11:12<1:53:18,  1.62it/s]
 81%|████████  | 46577/57600 [8:11:13<1:51:26,  1.65it/s]
 81%|████████  | 46578/57600 [8:11:14<1:52:45,  1.63it/s]
 81%|████████  | 46579/57600 [8:11:14<1:51:42,  1.64it/s]
 81%|████████  | 46580/57600 [8:11:15<1:51:10,  1.65it/s]
                                                         
{'loss': 1.1173, 'learning_rate': 2.7278745644599305e-07, 'epoch': 514.13}

 81%|████████  | 46580/57600 [8:11:15<1:51:10,  1.65it/s]
 81%|████████  | 46581/57600 [8:11:15<1:51:29,  1.65it/s]
 81%|████████  | 46582/57600 [8:11:16<1:54:27,  1.60it/s]
 81%|████████  | 46583/57600 [8:11:17<1:57:00,  1.57it/s]
 81%|████████  | 46584/57600 [8:11:17<1:57:40,  1.56it/s]
 81%|████████  | 46585/57600 [8:11:18<1:57:06,  1.57it/s]
 81%|████████  | 46586/57600 [8:11:19<1:55:35,  1.59it/s]
 81%|████████  | 46587/57600 [8:11:19<1:54:38,  1.60it/s]
 81%|████████  | 46588/57600 [8:11:20<1:57:28,  1.56it/s]
 81%|████████  | 46589/57600 [8:11:21<1:57:34,  1.56it/s]
 81%|████████  | 46590/57600 [8:11:21<1:56:44,  1.57it/s]
 81%|████████  | 46591/57600 [8:11:22<1:55:18,  1.59it/s]
 81%|████████  | 46592/57600 [8:11:23<2:00:42,  1.52it/s]
 81%|████████  | 46593/57600 [8:11:23<1:57:28,  1.56it/s]
 81%|████████  | 46594/57600 [8:11:24<1:55:07,  1.59it/s]
 81%|████████  | 46595/57600 [8:11:24<1:54:30,  1.60it/s]
 81%|████████  | 46596/57600 [8:11:25<1:52:18,  1.63it/s]
 81%|████████  | 46597/57600 [8:11:26<1:55:31,  1.59it/s]
 81%|████████  | 46598/57600 [8:11:26<1:54:02,  1.61it/s]
 81%|████████  | 46599/57600 [8:11:27<1:51:30,  1.64it/s]
 81%|████████  | 46600/57600 [8:11:27<1:50:10,  1.66it/s]
                                                         
{'loss': 1.1241, 'learning_rate': 2.7247386759581875e-07, 'epoch': 514.35}

 81%|████████  | 46600/57600 [8:11:27<1:50:10,  1.66it/s]
 81%|████████  | 46601/57600 [8:11:28<1:48:12,  1.69it/s]
 81%|████████  | 46602/57600 [8:11:29<1:54:56,  1.59it/s]
 81%|████████  | 46603/57600 [8:11:29<1:56:57,  1.57it/s]
 81%|████████  | 46604/57600 [8:11:30<1:54:51,  1.60it/s]
 81%|████████  | 46605/57600 [8:11:30<1:52:17,  1.63it/s]
 81%|████████  | 46606/57600 [8:11:31<1:52:13,  1.63it/s]
 81%|████████  | 46607/57600 [8:11:32<1:55:25,  1.59it/s]
 81%|████████  | 46608/57600 [8:11:32<1:52:51,  1.62it/s]
 81%|████████  | 46609/57600 [8:11:33<1:54:23,  1.60it/s]
 81%|████████  | 46610/57600 [8:11:34<1:55:19,  1.59it/s]
 81%|████████  | 46611/57600 [8:11:34<1:51:58,  1.64it/s]
 81%|████████  | 46612/57600 [8:11:35<1:49:30,  1.67it/s]
 81%|████████  | 46613/57600 [8:11:35<1:50:54,  1.65it/s]
 81%|████████  | 46614/57600 [8:11:36<1:52:31,  1.63it/s]
 81%|████████  | 46615/57600 [8:11:37<1:54:01,  1.61it/s]
 81%|████████  | 46616/57600 [8:11:37<1:52:57,  1.62it/s]
 81%|████████  | 46617/57600 [8:11:38<1:58:02,  1.55it/s]
 81%|████████  | 46618/57600 [8:11:39<1:55:40,  1.58it/s]
 81%|████████  | 46619/57600 [8:11:39<1:56:16,  1.57it/s]
 81%|████████  | 46620/57600 [8:11:40<1:54:41,  1.60it/s]
                                                         
{'loss': 1.136, 'learning_rate': 2.721602787456446e-07, 'epoch': 514.57}

 81%|████████  | 46620/57600 [8:11:40<1:54:41,  1.60it/s]
 81%|████████  | 46621/57600 [8:11:40<1:51:56,  1.63it/s]
 81%|████████  | 46622/57600 [8:11:41<1:55:49,  1.58it/s]
 81%|████████  | 46623/57600 [8:11:42<1:54:05,  1.60it/s]
 81%|████████  | 46624/57600 [8:11:42<1:51:23,  1.64it/s]
 81%|████████  | 46625/57600 [8:11:43<1:51:13,  1.64it/s]
 81%|████████  | 46626/57600 [8:11:43<1:50:26,  1.66it/s]
 81%|████████  | 46627/57600 [8:11:44<1:53:18,  1.61it/s]
 81%|████████  | 46628/57600 [8:11:45<1:52:55,  1.62it/s]
 81%|████████  | 46629/57600 [8:11:45<1:53:18,  1.61it/s]
 81%|████████  | 46630/57600 [8:11:46<1:55:27,  1.58it/s]
 81%|████████  | 46631/57600 [8:11:47<1:53:37,  1.61it/s]
 81%|████████  | 46632/57600 [8:11:47<1:55:52,  1.58it/s]
 81%|████████  | 46633/57600 [8:11:48<1:54:13,  1.60it/s]
 81%|████████  | 46634/57600 [8:11:48<1:50:57,  1.65it/s]
 81%|████████  | 46635/57600 [8:11:49<1:50:40,  1.65it/s]
 81%|████████  | 46636/57600 [8:11:50<1:52:30,  1.62it/s]
 81%|████████  | 46637/57600 [8:11:50<1:52:31,  1.62it/s]
 81%|████████  | 46638/57600 [8:11:51<1:55:12,  1.59it/s]
 81%|████████  | 46639/57600 [8:11:52<1:53:27,  1.61it/s]
 81%|████████  | 46640/57600 [8:11:52<1:51:55,  1.63it/s]
                                                         
{'loss': 1.1653, 'learning_rate': 2.7184668989547036e-07, 'epoch': 514.79}

 81%|████████  | 46640/57600 [8:11:52<1:51:55,  1.63it/s]
 81%|████████  | 46641/57600 [8:11:53<1:54:33,  1.59it/s]
 81%|████████  | 46642/57600 [8:11:53<1:52:39,  1.62it/s]
 81%|████████  | 46643/57600 [8:11:54<1:51:54,  1.63it/s]
 81%|████████  | 46644/57600 [8:11:55<1:52:11,  1.63it/s]
 81%|████████  | 46645/57600 [8:11:55<1:52:09,  1.63it/s]
 81%|████████  | 46646/57600 [8:11:56<1:54:05,  1.60it/s]
 81%|████████  | 46647/57600 [8:11:57<2:00:27,  1.52it/s]
 81%|████████  | 46648/57600 [8:11:57<1:55:48,  1.58it/s]
 81%|████████  | 46649/57600 [8:11:58<1:56:31,  1.57it/s]
 81%|████████  | 46650/57600 [8:11:59<1:59:36,  1.53it/s]
 81%|████████  | 46651/57600 [8:11:59<1:58:33,  1.54it/s]
 81%|████████  | 46652/57600 [8:12:00<1:55:39,  1.58it/s]
 81%|████████  | 46653/57600 [8:12:00<1:56:24,  1.57it/s]
 81%|████████  | 46654/57600 [8:12:01<1:52:00,  1.63it/s]
 81%|████████  | 46655/57600 [8:12:02<1:54:11,  1.60it/s]
 81%|████████  | 46656/57600 [8:12:02<1:54:25,  1.59it/s]
 81%|████████  | 46657/57600 [8:12:03<1:54:56,  1.59it/s]
 81%|████████  | 46658/57600 [8:12:04<2:02:18,  1.49it/s]
 81%|████████  | 46659/57600 [8:12:04<1:58:32,  1.54it/s]
 81%|████████  | 46660/57600 [8:12:05<2:01:28,  1.50it/s]
                                                         
{'loss': 1.0816, 'learning_rate': 2.7153310104529617e-07, 'epoch': 515.01}

 81%|████████  | 46660/57600 [8:12:05<2:01:28,  1.50it/s]
 81%|████████  | 46661/57600 [8:12:06<2:03:02,  1.48it/s]
 81%|████████  | 46662/57600 [8:12:06<1:58:37,  1.54it/s]
 81%|████████  | 46663/57600 [8:12:07<1:57:17,  1.55it/s]
 81%|████████  | 46664/57600 [8:12:08<1:57:49,  1.55it/s]
 81%|████████  | 46665/57600 [8:12:08<1:57:20,  1.55it/s]
 81%|████████  | 46666/57600 [8:12:09<1:55:18,  1.58it/s]
 81%|████████  | 46667/57600 [8:12:09<1:57:26,  1.55it/s]
 81%|████████  | 46668/57600 [8:12:10<1:57:06,  1.56it/s]
 81%|████████  | 46669/57600 [8:12:11<1:57:10,  1.55it/s]
 81%|████████  | 46670/57600 [8:12:11<1:54:34,  1.59it/s]
 81%|████████  | 46671/57600 [8:12:12<1:53:45,  1.60it/s]
 81%|████████  | 46672/57600 [8:12:13<1:55:54,  1.57it/s]
 81%|████████  | 46673/57600 [8:12:13<1:56:26,  1.56it/s]
 81%|████████  | 46674/57600 [8:12:14<1:58:39,  1.53it/s]
 81%|████████  | 46675/57600 [8:12:15<1:54:56,  1.58it/s]
 81%|████████  | 46676/57600 [8:12:15<1:52:57,  1.61it/s]
 81%|████████  | 46677/57600 [8:12:16<2:01:34,  1.50it/s]
 81%|████████  | 46678/57600 [8:12:17<2:02:14,  1.49it/s]
 81%|████████  | 46679/57600 [8:12:17<1:59:39,  1.52it/s]
 81%|████████  | 46680/57600 [8:12:18<1:56:59,  1.56it/s]
                                                         
{'loss': 1.0901, 'learning_rate': 2.7121951219512187e-07, 'epoch': 515.23}

 81%|████████  | 46680/57600 [8:12:18<1:56:59,  1.56it/s]
 81%|████████  | 46681/57600 [8:12:19<1:57:44,  1.55it/s]
 81%|████████  | 46682/57600 [8:12:19<1:55:24,  1.58it/s]
 81%|████████  | 46683/57600 [8:12:20<1:53:30,  1.60it/s]
 81%|████████  | 46684/57600 [8:12:20<1:55:30,  1.58it/s]
 81%|████████  | 46685/57600 [8:12:21<1:52:02,  1.62it/s]
 81%|████████  | 46686/57600 [8:12:22<1:51:38,  1.63it/s]
 81%|████████  | 46687/57600 [8:12:22<1:52:27,  1.62it/s]
 81%|████████  | 46688/57600 [8:12:23<1:55:54,  1.57it/s]
 81%|████████  | 46689/57600 [8:12:24<1:56:28,  1.56it/s]
 81%|████████  | 46690/57600 [8:12:24<1:58:49,  1.53it/s]
 81%|████████  | 46691/57600 [8:12:25<1:58:50,  1.53it/s]
 81%|████████  | 46692/57600 [8:12:25<1:55:00,  1.58it/s]
 81%|████████  | 46693/57600 [8:12:26<1:54:22,  1.59it/s]
 81%|████████  | 46694/57600 [8:12:27<1:52:27,  1.62it/s]
 81%|████████  | 46695/57600 [8:12:27<1:52:35,  1.61it/s]
 81%|████████  | 46696/57600 [8:12:28<1:54:43,  1.58it/s]
 81%|████████  | 46697/57600 [8:12:29<1:52:35,  1.61it/s]
 81%|████████  | 46698/57600 [8:12:29<1:55:20,  1.58it/s]
 81%|████████  | 46699/57600 [8:12:30<1:56:06,  1.56it/s]
 81%|████████  | 46700/57600 [8:12:30<1:53:03,  1.61it/s]
                                                         
{'loss': 1.1228, 'learning_rate': 2.709059233449477e-07, 'epoch': 515.45}

 81%|████████  | 46700/57600 [8:12:30<1:53:03,  1.61it/s]
 81%|████████  | 46701/57600 [8:12:31<1:55:56,  1.57it/s]
 81%|████████  | 46702/57600 [8:12:32<1:56:48,  1.55it/s]
 81%|████████  | 46703/57600 [8:12:32<1:56:59,  1.55it/s]
 81%|████████  | 46704/57600 [8:12:33<1:55:02,  1.58it/s]
 81%|████████  | 46705/57600 [8:12:34<1:58:18,  1.53it/s]
 81%|████████  | 46706/57600 [8:12:34<1:56:37,  1.56it/s]
 81%|████████  | 46707/57600 [8:12:35<1:56:15,  1.56it/s]
 81%|████████  | 46708/57600 [8:12:36<1:53:09,  1.60it/s]
 81%|████████  | 46709/57600 [8:12:36<1:53:14,  1.60it/s]
 81%|████████  | 46710/57600 [8:12:37<1:51:15,  1.63it/s]
 81%|████████  | 46711/57600 [8:12:37<1:50:20,  1.64it/s]
 81%|████████  | 46712/57600 [8:12:38<1:52:37,  1.61it/s]
 81%|████████  | 46713/57600 [8:12:39<1:50:25,  1.64it/s]
 81%|████████  | 46714/57600 [8:12:39<1:53:18,  1.60it/s]
 81%|████████  | 46715/57600 [8:12:40<1:53:25,  1.60it/s]
 81%|████████  | 46716/57600 [8:12:40<1:53:15,  1.60it/s]
 81%|████████  | 46717/57600 [8:12:41<1:52:58,  1.61it/s]
 81%|████████  | 46718/57600 [8:12:42<1:50:31,  1.64it/s]
 81%|████████  | 46719/57600 [8:12:42<1:50:36,  1.64it/s]
 81%|████████  | 46720/57600 [8:12:43<1:51:58,  1.62it/s]
                                                         
{'loss': 1.1257, 'learning_rate': 2.705923344947736e-07, 'epoch': 515.67}

 81%|████████  | 46720/57600 [8:12:43<1:51:58,  1.62it/s]
 81%|████████  | 46721/57600 [8:12:44<1:53:01,  1.60it/s]
 81%|████████  | 46722/57600 [8:12:44<1:52:46,  1.61it/s]
 81%|████████  | 46723/57600 [8:12:45<1:49:09,  1.66it/s]
 81%|████████  | 46724/57600 [8:12:45<1:48:02,  1.68it/s]
 81%|████████  | 46725/57600 [8:12:46<1:47:55,  1.68it/s]
 81%|████████  | 46726/57600 [8:12:47<1:51:27,  1.63it/s]
 81%|████████  | 46727/57600 [8:12:47<1:51:53,  1.62it/s]
 81%|████████  | 46728/57600 [8:12:48<1:49:30,  1.65it/s]
 81%|████████  | 46729/57600 [8:12:48<1:54:59,  1.58it/s]
 81%|████████  | 46730/57600 [8:12:49<1:51:56,  1.62it/s]
 81%|████████  | 46731/57600 [8:12:50<1:51:44,  1.62it/s]
 81%|████████  | 46732/57600 [8:12:50<1:51:32,  1.62it/s]
 81%|████████  | 46733/57600 [8:12:51<1:50:32,  1.64it/s]
 81%|████████  | 46734/57600 [8:12:52<1:51:32,  1.62it/s]
 81%|████████  | 46735/57600 [8:12:52<1:50:26,  1.64it/s]
 81%|████████  | 46736/57600 [8:12:53<1:53:09,  1.60it/s]
 81%|████████  | 46737/57600 [8:12:53<1:56:46,  1.55it/s]
 81%|████████  | 46738/57600 [8:12:54<1:56:28,  1.55it/s]
 81%|████████  | 46739/57600 [8:12:55<1:55:50,  1.56it/s]
 81%|████████  | 46740/57600 [8:12:55<1:53:11,  1.60it/s]
                                                         
{'loss': 1.1466, 'learning_rate': 2.702787456445993e-07, 'epoch': 515.89}

 81%|████████  | 46740/57600 [8:12:55<1:53:11,  1.60it/s]
 81%|████████  | 46741/57600 [8:12:56<1:53:16,  1.60it/s]
 81%|████████  | 46742/57600 [8:12:57<1:52:31,  1.61it/s]
 81%|████████  | 46743/57600 [8:12:57<1:55:17,  1.57it/s]
 81%|████████  | 46744/57600 [8:12:58<1:53:42,  1.59it/s]
 81%|████████  | 46745/57600 [8:12:58<1:50:57,  1.63it/s]
 81%|████████  | 46746/57600 [8:12:59<1:51:38,  1.62it/s]
 81%|████████  | 46747/57600 [8:13:00<1:54:27,  1.58it/s]
 81%|████████  | 46748/57600 [8:13:00<1:52:22,  1.61it/s]
 81%|████████  | 46749/57600 [8:13:01<1:53:39,  1.59it/s]
 81%|████████  | 46750/57600 [8:13:02<1:56:00,  1.56it/s]
 81%|████████  | 46751/57600 [8:13:02<1:52:09,  1.61it/s]
 81%|████████  | 46752/57600 [8:13:03<1:49:30,  1.65it/s]
 81%|████████  | 46753/57600 [8:13:03<1:50:52,  1.63it/s]
 81%|████████  | 46754/57600 [8:13:04<1:52:50,  1.60it/s]
 81%|████████  | 46755/57600 [8:13:05<1:53:31,  1.59it/s]
 81%|████████  | 46756/57600 [8:13:05<1:56:11,  1.56it/s]
 81%|████████  | 46757/57600 [8:13:06<1:55:18,  1.57it/s]
 81%|████████  | 46758/57600 [8:13:07<1:51:41,  1.62it/s]
 81%|████████  | 46759/57600 [8:13:07<1:51:30,  1.62it/s]
 81%|████████  | 46760/57600 [8:13:08<1:53:43,  1.59it/s]
                                                         
{'loss': 1.135, 'learning_rate': 2.699651567944251e-07, 'epoch': 516.11}

 81%|████████  | 46760/57600 [8:13:08<1:53:43,  1.59it/s]
 81%|████████  | 46761/57600 [8:13:08<1:51:49,  1.62it/s]
 81%|████████  | 46762/57600 [8:13:09<1:52:22,  1.61it/s]
 81%|████████  | 46763/57600 [8:13:10<1:53:50,  1.59it/s]
 81%|████████  | 46764/57600 [8:13:10<1:52:58,  1.60it/s]
 81%|████████  | 46765/57600 [8:13:11<1:50:40,  1.63it/s]
 81%|████████  | 46766/57600 [8:13:12<1:50:15,  1.64it/s]
 81%|████████  | 46767/57600 [8:13:12<1:50:52,  1.63it/s]
 81%|████████  | 46768/57600 [8:13:13<1:50:34,  1.63it/s]
 81%|████████  | 46769/57600 [8:13:13<1:51:14,  1.62it/s]
 81%|████████  | 46770/57600 [8:13:14<1:50:42,  1.63it/s]
 81%|████████  | 46771/57600 [8:13:15<1:54:48,  1.57it/s]
 81%|████████  | 46772/57600 [8:13:15<1:52:41,  1.60it/s]
 81%|████████  | 46773/57600 [8:13:16<1:53:43,  1.59it/s]
 81%|████████  | 46774/57600 [8:13:17<1:55:02,  1.57it/s]
 81%|████████  | 46775/57600 [8:13:17<1:51:35,  1.62it/s]
 81%|████████  | 46776/57600 [8:13:18<1:52:19,  1.61it/s]
 81%|████████  | 46777/57600 [8:13:18<1:53:56,  1.58it/s]
 81%|████████  | 46778/57600 [8:13:19<1:54:20,  1.58it/s]
 81%|████████  | 46779/57600 [8:13:20<1:55:04,  1.57it/s]
 81%|████████  | 46780/57600 [8:13:20<1:52:00,  1.61it/s]
                                                         
{'loss': 1.1148, 'learning_rate': 2.6965156794425084e-07, 'epoch': 516.34}

 81%|████████  | 46780/57600 [8:13:20<1:52:00,  1.61it/s]
 81%|████████  | 46781/57600 [8:13:21<1:53:07,  1.59it/s]
 81%|████████  | 46782/57600 [8:13:22<1:51:09,  1.62it/s]
 81%|████████  | 46783/57600 [8:13:22<1:55:33,  1.56it/s]
 81%|████████  | 46784/57600 [8:13:23<1:53:05,  1.59it/s]
 81%|████████  | 46785/57600 [8:13:23<1:52:05,  1.61it/s]
 81%|████████  | 46786/57600 [8:13:24<1:54:45,  1.57it/s]
 81%|████████  | 46787/57600 [8:13:25<1:58:25,  1.52it/s]
 81%|████████  | 46788/57600 [8:13:25<1:55:46,  1.56it/s]
 81%|████████  | 46789/57600 [8:13:26<1:54:32,  1.57it/s]
 81%|████████  | 46790/57600 [8:13:27<1:52:39,  1.60it/s]
 81%|████████  | 46791/57600 [8:13:27<1:53:31,  1.59it/s]
 81%|████████  | 46792/57600 [8:13:28<1:51:37,  1.61it/s]
 81%|████████  | 46793/57600 [8:13:28<1:49:55,  1.64it/s]
 81%|████████  | 46794/57600 [8:13:29<1:51:34,  1.61it/s]
 81%|████████  | 46795/57600 [8:13:30<1:51:37,  1.61it/s]
 81%|████████  | 46796/57600 [8:13:30<1:52:47,  1.60it/s]
 81%|████████  | 46797/57600 [8:13:31<1:51:08,  1.62it/s]
 81%|████████  | 46798/57600 [8:13:32<1:55:38,  1.56it/s]
 81%|████████  | 46799/57600 [8:13:32<1:54:11,  1.58it/s]
 81%|████████▏ | 46800/57600 [8:13:33<1:55:51,  1.55it/s]
                                                         
{'loss': 1.1246, 'learning_rate': 2.6933797909407664e-07, 'epoch': 516.56}

 81%|████████▏ | 46800/57600 [8:13:33<1:55:51,  1.55it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.89it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.09it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.54it/s]

100%|██████████| 6/6 [00:01<00:00,  3.19it/s]{'score': 47.88968541823464, 'counts': [143, 90, 62, 44], 'totals': [208, 178, 149, 121], 'precisions': [68.75, 50.561797752808985, 41.61073825503356, 36.36363636363637], 'bp': 1.0, 'sys_len': 208, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 1.970095157623291, 'eval_bleu': 47.8897, 'eval_gen_len': 8.4667, 'eval_runtime': 3.2787, 'eval_samples_per_second': 9.15, 'eval_steps_per_second': 1.83, 'epoch': 516.56}

 81%|████████▏ | 46800/57600 [8:13:36<1:55:51,  1.55it/s]

100%|██████████| 6/6 [00:03<00:00,  3.19it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 15:07:49,569 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 81%|████████▏ | 46801/57600 [8:14:00<25:21:44,  8.45s/it]
 81%|████████▏ | 46802/57600 [8:14:00<18:23:37,  6.13s/it]
 81%|████████▏ | 46803/57600 [8:14:01<13:29:29,  4.50s/it]
 81%|████████▏ | 46804/57600 [8:14:02<10:08:22,  3.38s/it]
 81%|████████▏ | 46805/57600 [8:14:03<7:46:35,  2.59s/it] 
 81%|████████▏ | 46806/57600 [8:14:03<6:03:29,  2.02s/it]
 81%|████████▏ | 46807/57600 [8:14:04<4:53:15,  1.63s/it]
 81%|████████▏ | 46808/57600 [8:14:05<4:01:25,  1.34s/it]
 81%|████████▏ | 46809/57600 [8:14:05<3:23:32,  1.13s/it]
 81%|████████▏ | 46810/57600 [8:14:06<2:57:29,  1.01it/s]
 81%|████████▏ | 46811/57600 [8:14:07<2:42:24,  1.11it/s]
 81%|████████▏ | 46812/57600 [8:14:07<2:30:06,  1.20it/s]
 81%|████████▏ | 46813/57600 [8:14:08<2:24:22,  1.25it/s]
 81%|████████▏ | 46814/57600 [8:14:09<2:21:49,  1.27it/s]
 81%|████████▏ | 46815/57600 [8:14:09<2:12:21,  1.36it/s]
 81%|████████▏ | 46816/57600 [8:14:10<2:11:33,  1.37it/s]
 81%|████████▏ | 46817/57600 [8:14:11<2:06:15,  1.42it/s]
 81%|████████▏ | 46818/57600 [8:14:11<2:00:41,  1.49it/s]
 81%|████████▏ | 46819/57600 [8:14:12<2:06:00,  1.43it/s]
 81%|████████▏ | 46820/57600 [8:14:13<2:07:52,  1.40it/s]
                                                         
{'loss': 1.0884, 'learning_rate': 2.6902439024390234e-07, 'epoch': 516.78}

 81%|████████▏ | 46820/57600 [8:14:13<2:07:52,  1.40it/s]
 81%|████████▏ | 46821/57600 [8:14:14<2:04:56,  1.44it/s]
 81%|████████▏ | 46822/57600 [8:14:14<2:01:52,  1.47it/s]
 81%|████████▏ | 46823/57600 [8:14:15<1:59:12,  1.51it/s]
 81%|████████▏ | 46824/57600 [8:14:15<1:53:31,  1.58it/s]
 81%|████████▏ | 46825/57600 [8:14:16<1:54:10,  1.57it/s]
 81%|████████▏ | 46826/57600 [8:14:17<2:00:40,  1.49it/s]
 81%|████████▏ | 46827/57600 [8:14:17<2:02:13,  1.47it/s]
 81%|████████▏ | 46828/57600 [8:14:18<2:04:56,  1.44it/s]
 81%|████████▏ | 46829/57600 [8:14:19<2:05:21,  1.43it/s]
 81%|████████▏ | 46830/57600 [8:14:20<2:08:13,  1.40it/s]
 81%|████████▏ | 46831/57600 [8:14:20<2:03:37,  1.45it/s]
 81%|████████▏ | 46832/57600 [8:14:21<2:02:33,  1.46it/s]
 81%|████████▏ | 46833/57600 [8:14:22<1:58:15,  1.52it/s]
 81%|████████▏ | 46834/57600 [8:14:22<1:55:26,  1.55it/s]
 81%|████████▏ | 46835/57600 [8:14:23<1:58:41,  1.51it/s]
 81%|████████▏ | 46836/57600 [8:14:23<1:53:55,  1.57it/s]
 81%|████████▏ | 46837/57600 [8:14:24<1:56:25,  1.54it/s]
 81%|████████▏ | 46838/57600 [8:14:25<1:54:00,  1.57it/s]
 81%|████████▏ | 46839/57600 [8:14:25<1:51:18,  1.61it/s]
 81%|████████▏ | 46840/57600 [8:14:26<1:51:48,  1.60it/s]
                                                         
{'loss': 1.0961, 'learning_rate': 2.687108013937282e-07, 'epoch': 517.0}

 81%|████████▏ | 46840/57600 [8:14:26<1:51:48,  1.60it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 81%|████████▏ | 46841/57600 [8:14:27<2:00:22,  1.49it/s]
 81%|████████▏ | 46842/57600 [8:14:27<1:59:00,  1.51it/s]
 81%|████████▏ | 46843/57600 [8:14:28<1:59:42,  1.50it/s]
 81%|████████▏ | 46844/57600 [8:14:29<2:00:59,  1.48it/s]
 81%|████████▏ | 46845/57600 [8:14:29<1:59:27,  1.50it/s]
 81%|████████▏ | 46846/57600 [8:14:30<2:01:29,  1.48it/s]
 81%|████████▏ | 46847/57600 [8:14:31<2:00:42,  1.48it/s]
 81%|████████▏ | 46848/57600 [8:14:31<2:01:04,  1.48it/s]
 81%|████████▏ | 46849/57600 [8:14:32<1:59:15,  1.50it/s]
 81%|████████▏ | 46850/57600 [8:14:33<1:58:48,  1.51it/s]
 81%|████████▏ | 46851/57600 [8:14:33<1:59:12,  1.50it/s]
 81%|████████▏ | 46852/57600 [8:14:34<1:57:38,  1.52it/s]
 81%|████████▏ | 46853/57600 [8:14:35<1:57:32,  1.52it/s]
 81%|████████▏ | 46854/57600 [8:14:35<1:59:43,  1.50it/s]
 81%|████████▏ | 46855/57600 [8:14:36<2:00:55,  1.48it/s]
 81%|████████▏ | 46856/57600 [8:14:37<2:03:25,  1.45it/s]
 81%|████████▏ | 46857/57600 [8:14:37<2:02:22,  1.46it/s]
 81%|████████▏ | 46858/57600 [8:14:38<2:03:18,  1.45it/s]
 81%|████████▏ | 46859/57600 [8:14:39<2:04:23,  1.44it/s]
 81%|████████▏ | 46860/57600 [8:14:39<2:00:33,  1.48it/s]
                                                         
{'loss': 1.0813, 'learning_rate': 2.6839721254355406e-07, 'epoch': 517.22}

 81%|████████▏ | 46860/57600 [8:14:39<2:00:33,  1.48it/s]
 81%|████████▏ | 46861/57600 [8:14:40<2:06:26,  1.42it/s]
 81%|████████▏ | 46862/57600 [8:14:41<2:05:01,  1.43it/s]
 81%|████████▏ | 46863/57600 [8:14:42<1:59:14,  1.50it/s]
 81%|████████▏ | 46864/57600 [8:14:42<1:58:01,  1.52it/s]
 81%|████████▏ | 46865/57600 [8:14:43<1:57:58,  1.52it/s]
 81%|████████▏ | 46866/57600 [8:14:43<1:55:12,  1.55it/s]
 81%|████████▏ | 46867/57600 [8:14:44<1:57:40,  1.52it/s]
 81%|████████▏ | 46868/57600 [8:14:45<1:54:11,  1.57it/s]
 81%|████████▏ | 46869/57600 [8:14:45<1:53:12,  1.58it/s]
 81%|████████▏ | 46870/57600 [8:14:46<1:57:12,  1.53it/s]
 81%|████████▏ | 46871/57600 [8:14:47<1:54:06,  1.57it/s]
 81%|████████▏ | 46872/57600 [8:14:47<1:56:26,  1.54it/s]
 81%|████████▏ | 46873/57600 [8:14:48<1:56:39,  1.53it/s]
 81%|████████▏ | 46874/57600 [8:14:49<1:54:45,  1.56it/s]
 81%|████████▏ | 46875/57600 [8:14:49<1:55:48,  1.54it/s]
 81%|████████▏ | 46876/57600 [8:14:50<1:52:00,  1.60it/s]
 81%|████████▏ | 46877/57600 [8:14:50<1:52:30,  1.59it/s]
 81%|████████▏ | 46878/57600 [8:14:51<1:56:40,  1.53it/s]
 81%|████████▏ | 46879/57600 [8:14:52<1:56:52,  1.53it/s]
 81%|████████▏ | 46880/57600 [8:14:52<1:53:02,  1.58it/s]
                                                         
{'loss': 1.1569, 'learning_rate': 2.6808362369337976e-07, 'epoch': 517.44}

 81%|████████▏ | 46880/57600 [8:14:52<1:53:02,  1.58it/s]
 81%|████████▏ | 46881/57600 [8:14:53<1:55:29,  1.55it/s]
 81%|████████▏ | 46882/57600 [8:14:54<1:50:22,  1.62it/s]
 81%|████████▏ | 46883/57600 [8:14:54<1:47:43,  1.66it/s]
 81%|████████▏ | 46884/57600 [8:14:55<1:48:23,  1.65it/s]
 81%|████████▏ | 46885/57600 [8:14:56<1:51:10,  1.61it/s]
 81%|████████▏ | 46886/57600 [8:14:56<1:54:06,  1.56it/s]
 81%|████████▏ | 46887/57600 [8:14:57<1:55:23,  1.55it/s]
 81%|████████▏ | 46888/57600 [8:14:58<1:55:40,  1.54it/s]
 81%|████████▏ | 46889/57600 [8:14:58<1:59:08,  1.50it/s]
 81%|████████▏ | 46890/57600 [8:14:59<1:54:03,  1.56it/s]
 81%|████████▏ | 46891/57600 [8:14:59<1:52:32,  1.59it/s]
 81%|████████▏ | 46892/57600 [8:15:00<1:54:08,  1.56it/s]
 81%|████████▏ | 46893/57600 [8:15:01<1:50:52,  1.61it/s]
 81%|████████▏ | 46894/57600 [8:15:01<1:54:45,  1.55it/s]
 81%|████████▏ | 46895/57600 [8:15:02<1:53:48,  1.57it/s]
 81%|████████▏ | 46896/57600 [8:15:03<1:52:42,  1.58it/s]
 81%|████████▏ | 46897/57600 [8:15:03<1:52:23,  1.59it/s]
 81%|████████▏ | 46898/57600 [8:15:04<1:54:42,  1.56it/s]
 81%|████████▏ | 46899/57600 [8:15:04<1:52:33,  1.58it/s]
 81%|████████▏ | 46900/57600 [8:15:05<1:53:14,  1.57it/s]
                                                         
{'loss': 1.1273, 'learning_rate': 2.6777003484320556e-07, 'epoch': 517.66}

 81%|████████▏ | 46900/57600 [8:15:05<1:53:14,  1.57it/s]
 81%|████████▏ | 46901/57600 [8:15:06<1:54:03,  1.56it/s]
 81%|████████▏ | 46902/57600 [8:15:06<1:52:26,  1.59it/s]
 81%|████████▏ | 46903/57600 [8:15:07<1:51:55,  1.59it/s]
 81%|████████▏ | 46904/57600 [8:15:08<1:53:08,  1.58it/s]
 81%|████████▏ | 46905/57600 [8:15:08<1:54:29,  1.56it/s]
 81%|████████▏ | 46906/57600 [8:15:09<1:54:39,  1.55it/s]
 81%|████████▏ | 46907/57600 [8:15:10<1:54:49,  1.55it/s]
 81%|████████▏ | 46908/57600 [8:15:10<1:56:17,  1.53it/s]
 81%|████████▏ | 46909/57600 [8:15:11<2:03:17,  1.45it/s]
 81%|████████▏ | 46910/57600 [8:15:12<2:10:52,  1.36it/s]
 81%|████████▏ | 46911/57600 [8:15:13<2:11:07,  1.36it/s]
 81%|████████▏ | 46912/57600 [8:15:13<2:03:58,  1.44it/s]
 81%|████████▏ | 46913/57600 [8:15:14<2:00:12,  1.48it/s]
 81%|████████▏ | 46914/57600 [8:15:14<1:56:35,  1.53it/s]
 81%|████████▏ | 46915/57600 [8:15:15<1:58:01,  1.51it/s]
 81%|████████▏ | 46916/57600 [8:15:16<2:00:53,  1.47it/s]
 81%|████████▏ | 46917/57600 [8:15:16<1:56:25,  1.53it/s]
 81%|████████▏ | 46918/57600 [8:15:17<1:55:19,  1.54it/s]
 81%|████████▏ | 46919/57600 [8:15:18<1:55:49,  1.54it/s]
 81%|████████▏ | 46920/57600 [8:15:18<1:57:51,  1.51it/s]
                                                         
{'loss': 1.1095, 'learning_rate': 2.674564459930313e-07, 'epoch': 517.88}

 81%|████████▏ | 46920/57600 [8:15:18<1:57:51,  1.51it/s]
 81%|████████▏ | 46921/57600 [8:15:19<1:56:56,  1.52it/s]
 81%|████████▏ | 46922/57600 [8:15:20<1:55:27,  1.54it/s]
 81%|████████▏ | 46923/57600 [8:15:20<1:56:12,  1.53it/s]
 81%|████████▏ | 46924/57600 [8:15:21<1:52:02,  1.59it/s]
 81%|████████▏ | 46925/57600 [8:15:22<1:52:57,  1.58it/s]
 81%|████████▏ | 46926/57600 [8:15:22<1:53:39,  1.57it/s]
 81%|████████▏ | 46927/57600 [8:15:23<1:52:06,  1.59it/s]
 81%|████████▏ | 46928/57600 [8:15:24<1:52:47,  1.58it/s]
 81%|████████▏ | 46929/57600 [8:15:24<1:52:13,  1.58it/s]
 81%|████████▏ | 46930/57600 [8:15:25<1:57:29,  1.51it/s]
 81%|████████▏ | 46931/57600 [8:15:26<2:05:13,  1.42it/s]
 81%|████████▏ | 46932/57600 [8:15:26<2:04:48,  1.42it/s]
 81%|████████▏ | 46933/57600 [8:15:27<2:02:54,  1.45it/s]
 81%|████████▏ | 46934/57600 [8:15:28<2:05:33,  1.42it/s]
 81%|████████▏ | 46935/57600 [8:15:28<2:02:47,  1.45it/s]
 81%|████████▏ | 46936/57600 [8:15:29<2:01:05,  1.47it/s]
 81%|████████▏ | 46937/57600 [8:15:30<1:58:16,  1.50it/s]
 81%|████████▏ | 46938/57600 [8:15:30<1:56:29,  1.53it/s]
 81%|████████▏ | 46939/57600 [8:15:31<1:54:30,  1.55it/s]
 81%|████████▏ | 46940/57600 [8:15:32<1:54:55,  1.55it/s]
                                                         
{'loss': 1.1044, 'learning_rate': 2.6714285714285717e-07, 'epoch': 518.1}

 81%|████████▏ | 46940/57600 [8:15:32<1:54:55,  1.55it/s]
 81%|████████▏ | 46941/57600 [8:15:32<1:51:00,  1.60it/s]
 81%|████████▏ | 46942/57600 [8:15:33<1:51:09,  1.60it/s]
 81%|████████▏ | 46943/57600 [8:15:33<1:53:48,  1.56it/s]
 82%|████████▏ | 46944/57600 [8:15:34<1:56:23,  1.53it/s]
 82%|████████▏ | 46945/57600 [8:15:35<1:58:19,  1.50it/s]
 82%|████████▏ | 46946/57600 [8:15:35<1:54:23,  1.55it/s]
 82%|████████▏ | 46947/57600 [8:15:36<1:56:52,  1.52it/s]
 82%|████████▏ | 46948/57600 [8:15:37<1:56:16,  1.53it/s]
 82%|████████▏ | 46949/57600 [8:15:37<1:55:05,  1.54it/s]
 82%|████████▏ | 46950/57600 [8:15:38<1:55:39,  1.53it/s]
 82%|████████▏ | 46951/57600 [8:15:39<1:53:28,  1.56it/s]
 82%|████████▏ | 46952/57600 [8:15:39<1:55:02,  1.54it/s]
 82%|████████▏ | 46953/57600 [8:15:40<1:54:13,  1.55it/s]
 82%|████████▏ | 46954/57600 [8:15:41<1:54:17,  1.55it/s]
 82%|████████▏ | 46955/57600 [8:15:41<1:52:59,  1.57it/s]
 82%|████████▏ | 46956/57600 [8:15:42<1:52:46,  1.57it/s]
 82%|████████▏ | 46957/57600 [8:15:43<1:52:01,  1.58it/s]
 82%|████████▏ | 46958/57600 [8:15:43<1:54:25,  1.55it/s]
 82%|████████▏ | 46959/57600 [8:15:44<1:55:00,  1.54it/s]
 82%|████████▏ | 46960/57600 [8:15:45<2:02:45,  1.44it/s]
                                                         
{'loss': 1.123, 'learning_rate': 2.668292682926829e-07, 'epoch': 518.32}

 82%|████████▏ | 46960/57600 [8:15:45<2:02:45,  1.44it/s]
 82%|████████▏ | 46961/57600 [8:15:45<2:06:30,  1.40it/s]
 82%|████████▏ | 46962/57600 [8:15:46<2:06:05,  1.41it/s]
 82%|████████▏ | 46963/57600 [8:15:47<2:03:38,  1.43it/s]
 82%|████████▏ | 46964/57600 [8:15:47<2:03:34,  1.43it/s]
 82%|████████▏ | 46965/57600 [8:15:48<2:07:11,  1.39it/s]
 82%|████████▏ | 46966/57600 [8:15:49<2:04:55,  1.42it/s]
 82%|████████▏ | 46967/57600 [8:15:50<2:03:44,  1.43it/s]
 82%|████████▏ | 46968/57600 [8:15:50<2:02:34,  1.45it/s]
 82%|████████▏ | 46969/57600 [8:15:51<2:01:33,  1.46it/s]
 82%|████████▏ | 46970/57600 [8:15:52<2:00:48,  1.47it/s]
 82%|████████▏ | 46971/57600 [8:15:52<1:58:31,  1.49it/s]
 82%|████████▏ | 46972/57600 [8:15:53<1:59:41,  1.48it/s]
 82%|████████▏ | 46973/57600 [8:15:54<1:55:34,  1.53it/s]
 82%|████████▏ | 46974/57600 [8:15:54<1:56:47,  1.52it/s]
 82%|████████▏ | 46975/57600 [8:15:55<1:57:54,  1.50it/s]
 82%|████████▏ | 46976/57600 [8:15:56<1:56:46,  1.52it/s]
 82%|████████▏ | 46977/57600 [8:15:56<1:57:41,  1.50it/s]
 82%|████████▏ | 46978/57600 [8:15:57<1:54:31,  1.55it/s]
 82%|████████▏ | 46979/57600 [8:15:58<1:58:12,  1.50it/s]
 82%|████████▏ | 46980/57600 [8:15:58<1:59:50,  1.48it/s]
                                                         
{'loss': 1.1064, 'learning_rate': 2.665156794425087e-07, 'epoch': 518.54}

 82%|████████▏ | 46980/57600 [8:15:58<1:59:50,  1.48it/s]
 82%|████████▏ | 46981/57600 [8:15:59<1:54:12,  1.55it/s]
 82%|████████▏ | 46982/57600 [8:16:00<1:55:28,  1.53it/s]
 82%|████████▏ | 46983/57600 [8:16:00<1:57:35,  1.50it/s]
 82%|████████▏ | 46984/57600 [8:16:01<1:57:02,  1.51it/s]
 82%|████████▏ | 46985/57600 [8:16:01<1:51:19,  1.59it/s]
 82%|████████▏ | 46986/57600 [8:16:02<1:51:47,  1.58it/s]
 82%|████████▏ | 46987/57600 [8:16:03<1:54:34,  1.54it/s]
 82%|████████▏ | 46988/57600 [8:16:03<1:54:00,  1.55it/s]
 82%|████████▏ | 46989/57600 [8:16:04<1:55:37,  1.53it/s]
 82%|████████▏ | 46990/57600 [8:16:05<1:54:58,  1.54it/s]
 82%|████████▏ | 46991/57600 [8:16:05<1:57:09,  1.51it/s]
 82%|████████▏ | 46992/57600 [8:16:06<1:57:17,  1.51it/s]
 82%|████████▏ | 46993/57600 [8:16:07<1:56:43,  1.51it/s]
 82%|████████▏ | 46994/57600 [8:16:07<1:56:42,  1.51it/s]
 82%|████████▏ | 46995/57600 [8:16:08<1:54:48,  1.54it/s]
 82%|████████▏ | 46996/57600 [8:16:09<1:50:30,  1.60it/s]
 82%|████████▏ | 46997/57600 [8:16:09<1:48:24,  1.63it/s]
 82%|████████▏ | 46998/57600 [8:16:10<1:49:35,  1.61it/s]
 82%|████████▏ | 46999/57600 [8:16:10<1:50:25,  1.60it/s]
 82%|████████▏ | 47000/57600 [8:16:11<1:57:57,  1.50it/s]
                                                         
{'loss': 1.1221, 'learning_rate': 2.662020905923346e-07, 'epoch': 518.76}

 82%|████████▏ | 47000/57600 [8:16:11<1:57:57,  1.50it/s]
 82%|████████▏ | 47001/57600 [8:16:12<1:53:13,  1.56it/s]
 82%|████████▏ | 47002/57600 [8:16:12<1:58:14,  1.49it/s]
 82%|████████▏ | 47003/57600 [8:16:13<1:55:50,  1.52it/s]
 82%|████████▏ | 47004/57600 [8:16:14<1:51:13,  1.59it/s]
 82%|████████▏ | 47005/57600 [8:16:14<1:50:16,  1.60it/s]
 82%|████████▏ | 47006/57600 [8:16:15<1:52:28,  1.57it/s]
 82%|████████▏ | 47007/57600 [8:16:16<1:50:09,  1.60it/s]
 82%|████████▏ | 47008/57600 [8:16:16<1:47:55,  1.64it/s]
 82%|████████▏ | 47009/57600 [8:16:17<1:48:25,  1.63it/s]
 82%|████████▏ | 47010/57600 [8:16:17<1:46:12,  1.66it/s]
 82%|████████▏ | 47011/57600 [8:16:18<1:47:31,  1.64it/s]
 82%|████████▏ | 47012/57600 [8:16:19<1:48:05,  1.63it/s]
 82%|████████▏ | 47013/57600 [8:16:19<1:51:22,  1.58it/s]
 82%|████████▏ | 47014/57600 [8:16:20<1:49:34,  1.61it/s]
 82%|████████▏ | 47015/57600 [8:16:20<1:46:57,  1.65it/s]
 82%|████████▏ | 47016/57600 [8:16:21<1:50:27,  1.60it/s]
 82%|████████▏ | 47017/57600 [8:16:22<1:52:09,  1.57it/s]
 82%|████████▏ | 47018/57600 [8:16:22<1:50:17,  1.60it/s]
 82%|████████▏ | 47019/57600 [8:16:23<1:56:13,  1.52it/s]
 82%|████████▏ | 47020/57600 [8:16:24<1:51:23,  1.58it/s]
                                                         
{'loss': 1.1345, 'learning_rate': 2.6588850174216023e-07, 'epoch': 518.98}

 82%|████████▏ | 47020/57600 [8:16:24<1:51:23,  1.58it/s]
 82%|████████▏ | 47021/57600 [8:16:24<1:53:40,  1.55it/s]
 82%|████████▏ | 47022/57600 [8:16:25<1:56:28,  1.51it/s]
 82%|████████▏ | 47023/57600 [8:16:26<1:54:46,  1.54it/s]
 82%|████████▏ | 47024/57600 [8:16:26<1:55:16,  1.53it/s]
 82%|████████▏ | 47025/57600 [8:16:27<1:51:28,  1.58it/s]
 82%|████████▏ | 47026/57600 [8:16:28<1:51:59,  1.57it/s]
 82%|████████▏ | 47027/57600 [8:16:28<1:48:05,  1.63it/s]
 82%|████████▏ | 47028/57600 [8:16:29<1:51:40,  1.58it/s]
 82%|████████▏ | 47029/57600 [8:16:29<1:52:30,  1.57it/s]
 82%|████████▏ | 47030/57600 [8:16:30<1:49:09,  1.61it/s]
 82%|████████▏ | 47031/57600 [8:16:31<1:48:48,  1.62it/s]
 82%|████████▏ | 47032/57600 [8:16:31<1:50:56,  1.59it/s]
 82%|████████▏ | 47033/57600 [8:16:32<1:50:48,  1.59it/s]
 82%|████████▏ | 47034/57600 [8:16:32<1:48:34,  1.62it/s]
 82%|████████▏ | 47035/57600 [8:16:33<1:52:04,  1.57it/s]
 82%|████████▏ | 47036/57600 [8:16:34<1:57:42,  1.50it/s]
 82%|████████▏ | 47037/57600 [8:16:35<1:53:45,  1.55it/s]
 82%|████████▏ | 47038/57600 [8:16:35<1:51:17,  1.58it/s]
 82%|████████▏ | 47039/57600 [8:16:36<1:48:57,  1.62it/s]
 82%|████████▏ | 47040/57600 [8:16:36<1:50:25,  1.59it/s]
                                                         
{'loss': 1.1308, 'learning_rate': 2.6557491289198604e-07, 'epoch': 519.21}

 82%|████████▏ | 47040/57600 [8:16:36<1:50:25,  1.59it/s]
 82%|████████▏ | 47041/57600 [8:16:37<1:53:22,  1.55it/s]
 82%|████████▏ | 47042/57600 [8:16:38<1:50:31,  1.59it/s]
 82%|████████▏ | 47043/57600 [8:16:38<1:51:03,  1.58it/s]
 82%|████████▏ | 47044/57600 [8:16:39<1:48:22,  1.62it/s]
 82%|████████▏ | 47045/57600 [8:16:40<1:50:49,  1.59it/s]
 82%|████████▏ | 47046/57600 [8:16:40<1:48:49,  1.62it/s]
 82%|████████▏ | 47047/57600 [8:16:41<1:47:04,  1.64it/s]
 82%|████████▏ | 47048/57600 [8:16:41<1:49:47,  1.60it/s]
 82%|████████▏ | 47049/57600 [8:16:42<1:48:21,  1.62it/s]
 82%|████████▏ | 47050/57600 [8:16:43<1:47:34,  1.63it/s]
 82%|████████▏ | 47051/57600 [8:16:43<1:50:17,  1.59it/s]
 82%|████████▏ | 47052/57600 [8:16:44<1:47:54,  1.63it/s]
 82%|████████▏ | 47053/57600 [8:16:44<1:47:48,  1.63it/s]
 82%|████████▏ | 47054/57600 [8:16:45<1:47:14,  1.64it/s]
 82%|████████▏ | 47055/57600 [8:16:46<1:47:53,  1.63it/s]
 82%|████████▏ | 47056/57600 [8:16:46<1:49:08,  1.61it/s]
 82%|████████▏ | 47057/57600 [8:16:47<1:51:38,  1.57it/s]
 82%|████████▏ | 47058/57600 [8:16:48<1:50:49,  1.59it/s]
 82%|████████▏ | 47059/57600 [8:16:48<1:48:55,  1.61it/s]
 82%|████████▏ | 47060/57600 [8:16:49<1:49:40,  1.60it/s]
                                                         
{'loss': 1.1336, 'learning_rate': 2.652613240418118e-07, 'epoch': 519.43}

 82%|████████▏ | 47060/57600 [8:16:49<1:49:40,  1.60it/s]
 82%|████████▏ | 47061/57600 [8:16:49<1:50:17,  1.59it/s]
 82%|████████▏ | 47062/57600 [8:16:50<1:50:19,  1.59it/s]
 82%|████████▏ | 47063/57600 [8:16:51<1:48:53,  1.61it/s]
 82%|████████▏ | 47064/57600 [8:16:51<1:45:48,  1.66it/s]
 82%|████████▏ | 47065/57600 [8:16:52<1:46:21,  1.65it/s]
 82%|████████▏ | 47066/57600 [8:16:52<1:47:05,  1.64it/s]
 82%|████████▏ | 47067/57600 [8:16:53<1:45:38,  1.66it/s]
 82%|████████▏ | 47068/57600 [8:16:54<1:44:32,  1.68it/s]
 82%|████████▏ | 47069/57600 [8:16:54<1:42:29,  1.71it/s]
 82%|████████▏ | 47070/57600 [8:16:55<1:47:00,  1.64it/s]
 82%|████████▏ | 47071/57600 [8:16:56<1:52:01,  1.57it/s]
 82%|████████▏ | 47072/57600 [8:16:56<1:52:08,  1.56it/s]
 82%|████████▏ | 47073/57600 [8:16:57<1:48:49,  1.61it/s]
 82%|████████▏ | 47074/57600 [8:16:57<1:49:30,  1.60it/s]
 82%|████████▏ | 47075/57600 [8:16:58<1:48:50,  1.61it/s]
 82%|████████▏ | 47076/57600 [8:16:59<1:48:56,  1.61it/s]
 82%|████████▏ | 47077/57600 [8:16:59<1:46:02,  1.65it/s]
 82%|████████▏ | 47078/57600 [8:17:00<1:43:49,  1.69it/s]
 82%|████████▏ | 47079/57600 [8:17:00<1:43:13,  1.70it/s]
 82%|████████▏ | 47080/57600 [8:17:01<1:43:23,  1.70it/s]
                                                         
{'loss': 1.1642, 'learning_rate': 2.6494773519163765e-07, 'epoch': 519.65}

 82%|████████▏ | 47080/57600 [8:17:01<1:43:23,  1.70it/s]
 82%|████████▏ | 47081/57600 [8:17:02<1:44:44,  1.67it/s]
 82%|████████▏ | 47082/57600 [8:17:02<1:45:03,  1.67it/s]
 82%|████████▏ | 47083/57600 [8:17:03<1:51:39,  1.57it/s]
 82%|████████▏ | 47084/57600 [8:17:03<1:48:27,  1.62it/s]
 82%|████████▏ | 47085/57600 [8:17:04<1:48:16,  1.62it/s]
 82%|████████▏ | 47086/57600 [8:17:05<1:50:07,  1.59it/s]
 82%|████████▏ | 47087/57600 [8:17:05<1:49:34,  1.60it/s]
 82%|████████▏ | 47088/57600 [8:17:06<1:50:14,  1.59it/s]
 82%|████████▏ | 47089/57600 [8:17:07<1:48:56,  1.61it/s]
 82%|████████▏ | 47090/57600 [8:17:07<1:46:51,  1.64it/s]
 82%|████████▏ | 47091/57600 [8:17:08<1:47:51,  1.62it/s]
 82%|████████▏ | 47092/57600 [8:17:08<1:49:32,  1.60it/s]
 82%|████████▏ | 47093/57600 [8:17:09<1:51:09,  1.58it/s]
 82%|████████▏ | 47094/57600 [8:17:10<1:51:05,  1.58it/s]
 82%|████████▏ | 47095/57600 [8:17:10<1:55:50,  1.51it/s]
 82%|████████▏ | 47096/57600 [8:17:11<1:51:46,  1.57it/s]
 82%|████████▏ | 47097/57600 [8:17:12<1:51:42,  1.57it/s]
 82%|████████▏ | 47098/57600 [8:17:12<1:53:35,  1.54it/s]
 82%|████████▏ | 47099/57600 [8:17:13<1:54:30,  1.53it/s]
 82%|████████▏ | 47100/57600 [8:17:14<1:56:02,  1.51it/s]
                                                         
{'loss': 1.0879, 'learning_rate': 2.6463414634146345e-07, 'epoch': 519.87}

 82%|████████▏ | 47100/57600 [8:17:14<1:56:02,  1.51it/s]
 82%|████████▏ | 47101/57600 [8:17:14<1:54:54,  1.52it/s]
 82%|████████▏ | 47102/57600 [8:17:15<1:57:03,  1.49it/s]
 82%|████████▏ | 47103/57600 [8:17:16<1:55:04,  1.52it/s]
 82%|████████▏ | 47104/57600 [8:17:16<1:50:20,  1.59it/s]
 82%|████████▏ | 47105/57600 [8:17:17<1:49:36,  1.60it/s]
 82%|████████▏ | 47106/57600 [8:17:18<1:52:20,  1.56it/s]
 82%|████████▏ | 47107/57600 [8:17:18<1:50:24,  1.58it/s]
 82%|████████▏ | 47108/57600 [8:17:19<1:49:41,  1.59it/s]
 82%|████████▏ | 47109/57600 [8:17:19<1:49:55,  1.59it/s]
 82%|████████▏ | 47110/57600 [8:17:20<1:50:32,  1.58it/s]
 82%|████████▏ | 47111/57600 [8:17:21<1:54:55,  1.52it/s]
 82%|████████▏ | 47112/57600 [8:17:21<1:52:49,  1.55it/s]
 82%|████████▏ | 47113/57600 [8:17:22<1:53:25,  1.54it/s]
 82%|████████▏ | 47114/57600 [8:17:23<1:54:57,  1.52it/s]
 82%|████████▏ | 47115/57600 [8:17:23<2:00:37,  1.45it/s]
 82%|████████▏ | 47116/57600 [8:17:24<1:56:45,  1.50it/s]
 82%|████████▏ | 47117/57600 [8:17:25<1:52:56,  1.55it/s]
 82%|████████▏ | 47118/57600 [8:17:25<1:50:17,  1.58it/s]
 82%|████████▏ | 47119/57600 [8:17:26<1:51:12,  1.57it/s]
 82%|████████▏ | 47120/57600 [8:17:27<1:49:33,  1.59it/s]
                                                         
{'loss': 1.1269, 'learning_rate': 2.6432055749128915e-07, 'epoch': 520.09}

 82%|████████▏ | 47120/57600 [8:17:27<1:49:33,  1.59it/s]
 82%|████████▏ | 47121/57600 [8:17:27<1:45:34,  1.65it/s]
 82%|████████▏ | 47122/57600 [8:17:28<1:43:52,  1.68it/s]
 82%|████████▏ | 47123/57600 [8:17:28<1:46:04,  1.65it/s]
 82%|████████▏ | 47124/57600 [8:17:29<1:46:30,  1.64it/s]
 82%|████████▏ | 47125/57600 [8:17:30<1:51:05,  1.57it/s]
 82%|████████▏ | 47126/57600 [8:17:30<1:52:53,  1.55it/s]
 82%|████████▏ | 47127/57600 [8:17:31<1:48:18,  1.61it/s]
 82%|████████▏ | 47128/57600 [8:17:31<1:47:07,  1.63it/s]
 82%|████████▏ | 47129/57600 [8:17:32<1:49:01,  1.60it/s]
 82%|████████▏ | 47130/57600 [8:17:33<1:48:39,  1.61it/s]
 82%|████████▏ | 47131/57600 [8:17:33<1:45:29,  1.65it/s]
 82%|████████▏ | 47132/57600 [8:17:34<1:49:09,  1.60it/s]
 82%|████████▏ | 47133/57600 [8:17:35<1:54:35,  1.52it/s]
 82%|████████▏ | 47134/57600 [8:17:35<1:50:36,  1.58it/s]
 82%|████████▏ | 47135/57600 [8:17:36<1:51:49,  1.56it/s]
 82%|████████▏ | 47136/57600 [8:17:37<1:50:56,  1.57it/s]
 82%|████████▏ | 47137/57600 [8:17:37<1:51:12,  1.57it/s]
 82%|████████▏ | 47138/57600 [8:17:38<1:51:31,  1.56it/s]
 82%|████████▏ | 47139/57600 [8:17:38<1:51:30,  1.56it/s]
 82%|████████▏ | 47140/57600 [8:17:39<1:48:32,  1.61it/s]
                                                         
{'loss': 1.1539, 'learning_rate': 2.64006968641115e-07, 'epoch': 520.31}

 82%|████████▏ | 47140/57600 [8:17:39<1:48:32,  1.61it/s]
 82%|████████▏ | 47141/57600 [8:17:40<1:49:36,  1.59it/s]
 82%|████████▏ | 47142/57600 [8:17:40<1:46:45,  1.63it/s]
 82%|████████▏ | 47143/57600 [8:17:41<1:46:03,  1.64it/s]
 82%|████████▏ | 47144/57600 [8:17:41<1:46:15,  1.64it/s]
 82%|████████▏ | 47145/57600 [8:17:42<1:48:35,  1.60it/s]
 82%|████████▏ | 47146/57600 [8:17:43<1:47:04,  1.63it/s]
 82%|████████▏ | 47147/57600 [8:17:43<1:47:10,  1.63it/s]
 82%|████████▏ | 47148/57600 [8:17:44<1:53:05,  1.54it/s]
 82%|████████▏ | 47149/57600 [8:17:45<1:51:00,  1.57it/s]
 82%|████████▏ | 47150/57600 [8:17:45<1:50:06,  1.58it/s]
 82%|████████▏ | 47151/57600 [8:17:46<1:49:10,  1.60it/s]
 82%|████████▏ | 47152/57600 [8:17:46<1:45:39,  1.65it/s]
 82%|████████▏ | 47153/57600 [8:17:47<1:46:50,  1.63it/s]
 82%|████████▏ | 47154/57600 [8:17:48<1:50:11,  1.58it/s]
 82%|████████▏ | 47155/57600 [8:17:48<1:49:22,  1.59it/s]
 82%|████████▏ | 47156/57600 [8:17:49<1:49:26,  1.59it/s]
 82%|████████▏ | 47157/57600 [8:17:50<1:52:51,  1.54it/s]
 82%|████████▏ | 47158/57600 [8:17:50<1:49:00,  1.60it/s]
 82%|████████▏ | 47159/57600 [8:17:51<1:48:25,  1.61it/s]
 82%|████████▏ | 47160/57600 [8:17:52<1:47:41,  1.62it/s]
                                                         
{'loss': 1.1108, 'learning_rate': 2.6369337979094076e-07, 'epoch': 520.53}

 82%|████████▏ | 47160/57600 [8:17:52<1:47:41,  1.62it/s]
 82%|████████▏ | 47161/57600 [8:17:52<1:47:09,  1.62it/s]
 82%|████████▏ | 47162/57600 [8:17:53<1:51:34,  1.56it/s]
 82%|████████▏ | 47163/57600 [8:17:53<1:50:40,  1.57it/s]
 82%|████████▏ | 47164/57600 [8:17:54<1:48:47,  1.60it/s]
 82%|████████▏ | 47165/57600 [8:17:55<1:51:44,  1.56it/s]
 82%|████████▏ | 47166/57600 [8:17:55<1:50:08,  1.58it/s]
 82%|████████▏ | 47167/57600 [8:17:56<1:48:15,  1.61it/s]
 82%|████████▏ | 47168/57600 [8:17:57<1:47:51,  1.61it/s]
 82%|████████▏ | 47169/57600 [8:17:57<1:46:20,  1.63it/s]
 82%|████████▏ | 47170/57600 [8:17:58<1:44:08,  1.67it/s]
 82%|████████▏ | 47171/57600 [8:17:58<1:42:46,  1.69it/s]
 82%|████████▏ | 47172/57600 [8:17:59<1:45:06,  1.65it/s]
 82%|████████▏ | 47173/57600 [8:17:59<1:43:18,  1.68it/s]
 82%|████████▏ | 47174/57600 [8:18:00<1:48:55,  1.60it/s]
 82%|████████▏ | 47175/57600 [8:18:01<1:45:06,  1.65it/s]
 82%|████████▏ | 47176/57600 [8:18:01<1:48:05,  1.61it/s]
 82%|████████▏ | 47177/57600 [8:18:02<1:49:05,  1.59it/s]
 82%|████████▏ | 47178/57600 [8:18:03<1:49:52,  1.58it/s]
 82%|████████▏ | 47179/57600 [8:18:03<1:50:19,  1.57it/s]
 82%|████████▏ | 47180/57600 [8:18:04<1:50:48,  1.57it/s]
                                                         
{'loss': 1.1258, 'learning_rate': 2.6337979094076657e-07, 'epoch': 520.75}

 82%|████████▏ | 47180/57600 [8:18:04<1:50:48,  1.57it/s]
 82%|████████▏ | 47181/57600 [8:18:05<1:50:17,  1.57it/s]
 82%|████████▏ | 47182/57600 [8:18:05<1:49:04,  1.59it/s]
 82%|████████▏ | 47183/57600 [8:18:06<1:50:52,  1.57it/s]
 82%|████████▏ | 47184/57600 [8:18:06<1:48:17,  1.60it/s]
 82%|████████▏ | 47185/57600 [8:18:07<1:47:31,  1.61it/s]
 82%|████████▏ | 47186/57600 [8:18:08<1:45:34,  1.64it/s]
 82%|████████▏ | 47187/57600 [8:18:08<1:45:27,  1.65it/s]
 82%|████████▏ | 47188/57600 [8:18:09<1:48:56,  1.59it/s]
 82%|████████▏ | 47189/57600 [8:18:10<1:46:31,  1.63it/s]
 82%|████████▏ | 47190/57600 [8:18:10<1:46:41,  1.63it/s]
 82%|████████▏ | 47191/57600 [8:18:11<1:45:29,  1.64it/s]
 82%|████████▏ | 47192/57600 [8:18:11<1:51:03,  1.56it/s]
 82%|████████▏ | 47193/57600 [8:18:12<1:50:55,  1.56it/s]
 82%|████████▏ | 47194/57600 [8:18:13<1:47:51,  1.61it/s]
 82%|████████▏ | 47195/57600 [8:18:13<1:48:32,  1.60it/s]
 82%|████████▏ | 47196/57600 [8:18:14<1:47:24,  1.61it/s]
 82%|████████▏ | 47197/57600 [8:18:15<1:47:08,  1.62it/s]
 82%|████████▏ | 47198/57600 [8:18:15<1:51:58,  1.55it/s]
 82%|████████▏ | 47199/57600 [8:18:16<1:50:34,  1.57it/s]
 82%|████████▏ | 47200/57600 [8:18:16<1:49:57,  1.58it/s]
                                                         
{'loss': 1.1445, 'learning_rate': 2.6306620209059226e-07, 'epoch': 520.97}

 82%|████████▏ | 47200/57600 [8:18:16<1:49:57,  1.58it/s]
 82%|████████▏ | 47201/57600 [8:18:17<1:50:01,  1.58it/s]
 82%|████████▏ | 47202/57600 [8:18:18<1:50:46,  1.56it/s]
 82%|████████▏ | 47203/57600 [8:18:18<1:53:50,  1.52it/s]
 82%|████████▏ | 47204/57600 [8:18:19<1:51:45,  1.55it/s]
 82%|████████▏ | 47205/57600 [8:18:20<1:47:36,  1.61it/s]
 82%|████████▏ | 47206/57600 [8:18:20<1:52:21,  1.54it/s]
 82%|████████▏ | 47207/57600 [8:18:21<1:51:05,  1.56it/s]
 82%|████████▏ | 47208/57600 [8:18:22<1:47:00,  1.62it/s]
 82%|████████▏ | 47209/57600 [8:18:22<1:45:33,  1.64it/s]
 82%|████████▏ | 47210/57600 [8:18:23<1:48:34,  1.59it/s]
 82%|████████▏ | 47211/57600 [8:18:23<1:47:11,  1.62it/s]
 82%|████████▏ | 47212/57600 [8:18:24<1:46:35,  1.62it/s]
 82%|████████▏ | 47213/57600 [8:18:25<1:48:53,  1.59it/s]
 82%|████████▏ | 47214/57600 [8:18:25<1:45:57,  1.63it/s]
 82%|████████▏ | 47215/57600 [8:18:26<1:45:03,  1.65it/s]
 82%|████████▏ | 47216/57600 [8:18:26<1:47:22,  1.61it/s]
 82%|████████▏ | 47217/57600 [8:18:27<1:48:58,  1.59it/s]
 82%|████████▏ | 47218/57600 [8:18:28<1:48:00,  1.60it/s]
 82%|████████▏ | 47219/57600 [8:18:28<1:47:10,  1.61it/s]
 82%|████████▏ | 47220/57600 [8:18:29<1:47:02,  1.62it/s]
                                                         
{'loss': 1.1007, 'learning_rate': 2.627526132404181e-07, 'epoch': 521.19}

 82%|████████▏ | 47220/57600 [8:18:29<1:47:02,  1.62it/s]
 82%|████████▏ | 47221/57600 [8:18:30<1:49:40,  1.58it/s]
 82%|████████▏ | 47222/57600 [8:18:30<1:49:06,  1.59it/s]
 82%|████████▏ | 47223/57600 [8:18:31<1:51:13,  1.56it/s]
 82%|████████▏ | 47224/57600 [8:18:32<1:52:24,  1.54it/s]
 82%|████████▏ | 47225/57600 [8:18:32<1:52:02,  1.54it/s]
 82%|████████▏ | 47226/57600 [8:18:33<1:48:33,  1.59it/s]
 82%|████████▏ | 47227/57600 [8:18:33<1:48:21,  1.60it/s]
 82%|████████▏ | 47228/57600 [8:18:34<1:46:28,  1.62it/s]
 82%|████████▏ | 47229/57600 [8:18:35<1:49:09,  1.58it/s]
 82%|████████▏ | 47230/57600 [8:18:35<1:46:57,  1.62it/s]
 82%|████████▏ | 47231/57600 [8:18:36<1:48:55,  1.59it/s]
 82%|████████▏ | 47232/57600 [8:18:37<1:48:36,  1.59it/s]
 82%|████████▏ | 47233/57600 [8:18:37<1:47:06,  1.61it/s]
 82%|████████▏ | 47234/57600 [8:18:38<1:48:29,  1.59it/s]
 82%|████████▏ | 47235/57600 [8:18:39<1:50:46,  1.56it/s]
 82%|████████▏ | 47236/57600 [8:18:39<1:50:18,  1.57it/s]
 82%|████████▏ | 47237/57600 [8:18:40<1:48:25,  1.59it/s]
 82%|████████▏ | 47238/57600 [8:18:40<1:46:11,  1.63it/s]
 82%|████████▏ | 47239/57600 [8:18:41<1:44:32,  1.65it/s]
 82%|████████▏ | 47240/57600 [8:18:42<1:44:44,  1.65it/s]
                                                         
{'loss': 1.1411, 'learning_rate': 2.6243902439024393e-07, 'epoch': 521.41}

 82%|████████▏ | 47240/57600 [8:18:42<1:44:44,  1.65it/s]
 82%|████████▏ | 47241/57600 [8:18:42<1:44:59,  1.64it/s]
 82%|████████▏ | 47242/57600 [8:18:43<1:48:52,  1.59it/s]
 82%|████████▏ | 47243/57600 [8:18:43<1:47:00,  1.61it/s]
 82%|████████▏ | 47244/57600 [8:18:44<1:44:49,  1.65it/s]
 82%|████████▏ | 47245/57600 [8:18:45<1:47:33,  1.60it/s]
 82%|████████▏ | 47246/57600 [8:18:45<1:47:29,  1.61it/s]
 82%|████████▏ | 47247/57600 [8:18:46<1:49:48,  1.57it/s]
 82%|████████▏ | 47248/57600 [8:18:47<1:47:46,  1.60it/s]
 82%|████████▏ | 47249/57600 [8:18:47<1:49:46,  1.57it/s]
 82%|████████▏ | 47250/57600 [8:18:48<1:46:34,  1.62it/s]
 82%|████████▏ | 47251/57600 [8:18:48<1:45:10,  1.64it/s]
 82%|████████▏ | 47252/57600 [8:18:49<1:43:37,  1.66it/s]
 82%|████████▏ | 47253/57600 [8:18:50<1:42:37,  1.68it/s]
 82%|████████▏ | 47254/57600 [8:18:50<1:49:08,  1.58it/s]
 82%|████████▏ | 47255/57600 [8:18:51<1:51:21,  1.55it/s]
 82%|████████▏ | 47256/57600 [8:18:52<1:51:05,  1.55it/s]
 82%|████████▏ | 47257/57600 [8:18:52<1:51:00,  1.55it/s]
 82%|████████▏ | 47258/57600 [8:18:53<1:56:22,  1.48it/s]
 82%|████████▏ | 47259/57600 [8:18:54<1:53:29,  1.52it/s]
 82%|████████▏ | 47260/57600 [8:18:54<1:48:08,  1.59it/s]
                                                         
{'loss': 1.0919, 'learning_rate': 2.621254355400696e-07, 'epoch': 521.63}

 82%|████████▏ | 47260/57600 [8:18:54<1:48:08,  1.59it/s]
 82%|████████▏ | 47261/57600 [8:18:55<1:45:42,  1.63it/s]
 82%|████████▏ | 47262/57600 [8:18:55<1:45:20,  1.64it/s]
 82%|████████▏ | 47263/57600 [8:18:56<1:47:39,  1.60it/s]
 82%|████████▏ | 47264/57600 [8:18:57<1:49:57,  1.57it/s]
 82%|████████▏ | 47265/57600 [8:18:57<1:49:46,  1.57it/s]
 82%|████████▏ | 47266/57600 [8:18:58<1:49:13,  1.58it/s]
 82%|████████▏ | 47267/57600 [8:18:59<1:48:27,  1.59it/s]
 82%|████████▏ | 47268/57600 [8:18:59<1:46:56,  1.61it/s]
 82%|████████▏ | 47269/57600 [8:19:00<1:45:27,  1.63it/s]
 82%|████████▏ | 47270/57600 [8:19:00<1:47:06,  1.61it/s]
 82%|████████▏ | 47271/57600 [8:19:01<1:44:54,  1.64it/s]
 82%|████████▏ | 47272/57600 [8:19:02<1:47:34,  1.60it/s]
 82%|████████▏ | 47273/57600 [8:19:02<1:45:59,  1.62it/s]
 82%|████████▏ | 47274/57600 [8:19:03<1:44:17,  1.65it/s]
 82%|████████▏ | 47275/57600 [8:19:03<1:45:47,  1.63it/s]
 82%|████████▏ | 47276/57600 [8:19:04<1:48:48,  1.58it/s]
 82%|████████▏ | 47277/57600 [8:19:05<1:45:56,  1.62it/s]
 82%|████████▏ | 47278/57600 [8:19:05<1:46:53,  1.61it/s]
 82%|████████▏ | 47279/57600 [8:19:06<1:48:47,  1.58it/s]
 82%|████████▏ | 47280/57600 [8:19:07<1:51:11,  1.55it/s]
                                                         
{'loss': 1.1141, 'learning_rate': 2.618118466898955e-07, 'epoch': 521.85}

 82%|████████▏ | 47280/57600 [8:19:07<1:51:11,  1.55it/s]
 82%|████████▏ | 47281/57600 [8:19:07<1:50:38,  1.55it/s]
 82%|████████▏ | 47282/57600 [8:19:08<1:52:24,  1.53it/s]
 82%|████████▏ | 47283/57600 [8:19:09<1:49:02,  1.58it/s]
 82%|████████▏ | 47284/57600 [8:19:09<1:50:05,  1.56it/s]
 82%|████████▏ | 47285/57600 [8:19:10<1:52:52,  1.52it/s]
 82%|████████▏ | 47286/57600 [8:19:10<1:49:05,  1.58it/s]
 82%|████████▏ | 47287/57600 [8:19:11<1:51:53,  1.54it/s]
 82%|████████▏ | 47288/57600 [8:19:12<1:49:12,  1.57it/s]
 82%|████████▏ | 47289/57600 [8:19:12<1:49:26,  1.57it/s]
 82%|████████▏ | 47290/57600 [8:19:13<1:46:23,  1.62it/s]
 82%|████████▏ | 47291/57600 [8:19:14<1:49:26,  1.57it/s]
 82%|████████▏ | 47292/57600 [8:19:14<1:45:45,  1.62it/s]
 82%|████████▏ | 47293/57600 [8:19:15<1:45:58,  1.62it/s]
 82%|████████▏ | 47294/57600 [8:19:16<1:55:41,  1.48it/s]
 82%|████████▏ | 47295/57600 [8:19:16<1:52:12,  1.53it/s]
 82%|████████▏ | 47296/57600 [8:19:17<1:54:49,  1.50it/s]
 82%|████████▏ | 47297/57600 [8:19:18<1:53:10,  1.52it/s]
 82%|████████▏ | 47298/57600 [8:19:18<1:49:01,  1.57it/s]
 82%|████████▏ | 47299/57600 [8:19:19<1:51:00,  1.55it/s]
 82%|████████▏ | 47300/57600 [8:19:20<1:52:17,  1.53it/s]
                                                         
{'loss': 1.1354, 'learning_rate': 2.6149825783972124e-07, 'epoch': 522.08}

 82%|████████▏ | 47300/57600 [8:19:20<1:52:17,  1.53it/s]
 82%|████████▏ | 47301/57600 [8:19:20<1:50:09,  1.56it/s]
 82%|████████▏ | 47302/57600 [8:19:21<1:47:29,  1.60it/s]
 82%|████████▏ | 47303/57600 [8:19:21<1:44:21,  1.64it/s]
 82%|████████▏ | 47304/57600 [8:19:22<1:46:08,  1.62it/s]
 82%|████████▏ | 47305/57600 [8:19:23<1:48:23,  1.58it/s]
 82%|████████▏ | 47306/57600 [8:19:23<1:48:31,  1.58it/s]
 82%|████████▏ | 47307/57600 [8:19:24<1:46:15,  1.61it/s]
 82%|████████▏ | 47308/57600 [8:19:25<1:51:10,  1.54it/s]
 82%|████████▏ | 47309/57600 [8:19:25<1:48:33,  1.58it/s]
 82%|████████▏ | 47310/57600 [8:19:26<1:45:24,  1.63it/s]
 82%|████████▏ | 47311/57600 [8:19:26<1:48:19,  1.58it/s]
 82%|████████▏ | 47312/57600 [8:19:27<1:47:15,  1.60it/s]
 82%|████████▏ | 47313/57600 [8:19:28<1:46:19,  1.61it/s]
 82%|████████▏ | 47314/57600 [8:19:28<1:51:14,  1.54it/s]
 82%|████████▏ | 47315/57600 [8:19:29<1:52:39,  1.52it/s]
 82%|████████▏ | 47316/57600 [8:19:30<1:53:23,  1.51it/s]
 82%|████████▏ | 47317/57600 [8:19:30<1:49:43,  1.56it/s]
 82%|████████▏ | 47318/57600 [8:19:31<1:50:27,  1.55it/s]
 82%|████████▏ | 47319/57600 [8:19:31<1:47:35,  1.59it/s]
 82%|████████▏ | 47320/57600 [8:19:32<1:46:05,  1.61it/s]
                                                         
{'loss': 1.1543, 'learning_rate': 2.6118466898954704e-07, 'epoch': 522.3}

 82%|████████▏ | 47320/57600 [8:19:32<1:46:05,  1.61it/s]
 82%|████████▏ | 47321/57600 [8:19:33<1:44:11,  1.64it/s]
 82%|████████▏ | 47322/57600 [8:19:33<1:47:08,  1.60it/s]
 82%|████████▏ | 47323/57600 [8:19:34<1:44:49,  1.63it/s]
 82%|████████▏ | 47324/57600 [8:19:35<1:52:02,  1.53it/s]
 82%|████████▏ | 47325/57600 [8:19:35<1:46:59,  1.60it/s]
 82%|████████▏ | 47326/57600 [8:19:36<1:44:27,  1.64it/s]
 82%|████████▏ | 47327/57600 [8:19:36<1:46:08,  1.61it/s]
 82%|████████▏ | 47328/57600 [8:19:37<1:43:12,  1.66it/s]
 82%|████████▏ | 47329/57600 [8:19:38<1:41:18,  1.69it/s]
 82%|████████▏ | 47330/57600 [8:19:38<1:48:22,  1.58it/s]
 82%|████████▏ | 47331/57600 [8:19:39<1:48:10,  1.58it/s]
 82%|████████▏ | 47332/57600 [8:19:40<1:50:34,  1.55it/s]
 82%|████████▏ | 47333/57600 [8:19:40<1:51:58,  1.53it/s]
 82%|████████▏ | 47334/57600 [8:19:41<1:47:33,  1.59it/s]
 82%|████████▏ | 47335/57600 [8:19:41<1:44:29,  1.64it/s]
 82%|████████▏ | 47336/57600 [8:19:42<1:45:20,  1.62it/s]
 82%|████████▏ | 47337/57600 [8:19:43<1:46:04,  1.61it/s]
 82%|████████▏ | 47338/57600 [8:19:43<1:48:37,  1.57it/s]
 82%|████████▏ | 47339/57600 [8:19:44<1:49:37,  1.56it/s]
 82%|████████▏ | 47340/57600 [8:19:45<1:48:21,  1.58it/s]
                                                         
{'loss': 1.1414, 'learning_rate': 2.6087108013937274e-07, 'epoch': 522.52}

 82%|████████▏ | 47340/57600 [8:19:45<1:48:21,  1.58it/s]
 82%|████████▏ | 47341/57600 [8:19:45<1:46:27,  1.61it/s]
 82%|████████▏ | 47342/57600 [8:19:46<1:49:29,  1.56it/s]
 82%|████████▏ | 47343/57600 [8:19:47<1:49:42,  1.56it/s]
 82%|████████▏ | 47344/57600 [8:19:47<1:51:23,  1.53it/s]
 82%|████████▏ | 47345/57600 [8:19:48<1:47:45,  1.59it/s]
 82%|████████▏ | 47346/57600 [8:19:48<1:46:35,  1.60it/s]
 82%|████████▏ | 47347/57600 [8:19:49<1:45:10,  1.62it/s]
 82%|████████▏ | 47348/57600 [8:19:50<1:48:37,  1.57it/s]
 82%|████████▏ | 47349/57600 [8:19:50<1:47:38,  1.59it/s]
 82%|████████▏ | 47350/57600 [8:19:51<1:46:28,  1.60it/s]
 82%|████████▏ | 47351/57600 [8:19:52<1:44:54,  1.63it/s]
 82%|████████▏ | 47352/57600 [8:19:52<1:44:46,  1.63it/s]
 82%|████████▏ | 47353/57600 [8:19:53<1:44:08,  1.64it/s]
 82%|████████▏ | 47354/57600 [8:19:53<1:44:24,  1.64it/s]
 82%|████████▏ | 47355/57600 [8:19:54<1:43:31,  1.65it/s]
 82%|████████▏ | 47356/57600 [8:19:55<1:47:30,  1.59it/s]
 82%|████████▏ | 47357/57600 [8:19:55<1:49:30,  1.56it/s]
 82%|████████▏ | 47358/57600 [8:19:56<1:49:29,  1.56it/s]
 82%|████████▏ | 47359/57600 [8:19:57<1:47:17,  1.59it/s]
 82%|████████▏ | 47360/57600 [8:19:57<1:44:11,  1.64it/s]
                                                         
{'loss': 1.1354, 'learning_rate': 2.605574912891986e-07, 'epoch': 522.74}

 82%|████████▏ | 47360/57600 [8:19:57<1:44:11,  1.64it/s]
 82%|████████▏ | 47361/57600 [8:19:58<1:42:52,  1.66it/s]
 82%|████████▏ | 47362/57600 [8:19:58<1:41:39,  1.68it/s]
 82%|████████▏ | 47363/57600 [8:19:59<1:42:16,  1.67it/s]
 82%|████████▏ | 47364/57600 [8:19:59<1:41:27,  1.68it/s]
 82%|████████▏ | 47365/57600 [8:20:00<1:44:48,  1.63it/s]
 82%|████████▏ | 47366/57600 [8:20:01<1:45:23,  1.62it/s]
 82%|████████▏ | 47367/57600 [8:20:01<1:45:34,  1.62it/s]
 82%|████████▏ | 47368/57600 [8:20:02<1:45:28,  1.62it/s]
 82%|████████▏ | 47369/57600 [8:20:03<1:45:58,  1.61it/s]
 82%|████████▏ | 47370/57600 [8:20:03<1:44:57,  1.62it/s]
 82%|████████▏ | 47371/57600 [8:20:04<1:44:24,  1.63it/s]
 82%|████████▏ | 47372/57600 [8:20:04<1:45:32,  1.62it/s]
 82%|████████▏ | 47373/57600 [8:20:05<1:45:28,  1.62it/s]
 82%|████████▏ | 47374/57600 [8:20:06<1:42:52,  1.66it/s]
 82%|████████▏ | 47375/57600 [8:20:06<1:44:33,  1.63it/s]
 82%|████████▏ | 47376/57600 [8:20:07<1:43:44,  1.64it/s]
 82%|████████▏ | 47377/57600 [8:20:08<1:45:07,  1.62it/s]
 82%|████████▏ | 47378/57600 [8:20:08<1:44:21,  1.63it/s]
 82%|████████▏ | 47379/57600 [8:20:09<1:43:27,  1.65it/s]
 82%|████████▏ | 47380/57600 [8:20:09<1:43:52,  1.64it/s]
                                                         
{'loss': 1.1349, 'learning_rate': 2.6024390243902446e-07, 'epoch': 522.96}

 82%|████████▏ | 47380/57600 [8:20:09<1:43:52,  1.64it/s]
 82%|████████▏ | 47381/57600 [8:20:10<1:42:28,  1.66it/s]
 82%|████████▏ | 47382/57600 [8:20:11<1:45:33,  1.61it/s]
 82%|████████▏ | 47383/57600 [8:20:11<1:45:39,  1.61it/s]
 82%|████████▏ | 47384/57600 [8:20:12<1:50:24,  1.54it/s]
 82%|████████▏ | 47385/57600 [8:20:12<1:47:18,  1.59it/s]
 82%|████████▏ | 47386/57600 [8:20:13<1:48:13,  1.57it/s]
 82%|████████▏ | 47387/57600 [8:20:14<1:48:26,  1.57it/s]
 82%|████████▏ | 47388/57600 [8:20:14<1:46:56,  1.59it/s]
 82%|████████▏ | 47389/57600 [8:20:15<1:44:39,  1.63it/s]
 82%|████████▏ | 47390/57600 [8:20:16<1:43:48,  1.64it/s]
 82%|████████▏ | 47391/57600 [8:20:16<1:42:24,  1.66it/s]
 82%|████████▏ | 47392/57600 [8:20:17<1:43:14,  1.65it/s]
 82%|████████▏ | 47393/57600 [8:20:17<1:41:05,  1.68it/s]
 82%|████████▏ | 47394/57600 [8:20:18<1:45:36,  1.61it/s]
 82%|████████▏ | 47395/57600 [8:20:19<1:46:58,  1.59it/s]
 82%|████████▏ | 47396/57600 [8:20:19<1:43:26,  1.64it/s]
 82%|████████▏ | 47397/57600 [8:20:20<1:44:51,  1.62it/s]
 82%|████████▏ | 47398/57600 [8:20:21<1:48:31,  1.57it/s]
 82%|████████▏ | 47399/57600 [8:20:21<1:50:31,  1.54it/s]
 82%|████████▏ | 47400/57600 [8:20:22<1:50:26,  1.54it/s]
                                                         
{'loss': 1.0901, 'learning_rate': 2.5993031358885015e-07, 'epoch': 523.18}

 82%|████████▏ | 47400/57600 [8:20:22<1:50:26,  1.54it/s]
 82%|████████▏ | 47401/57600 [8:20:23<1:51:45,  1.52it/s]
 82%|████████▏ | 47402/57600 [8:20:23<1:48:31,  1.57it/s]
 82%|████████▏ | 47403/57600 [8:20:24<1:46:43,  1.59it/s]
 82%|████████▏ | 47404/57600 [8:20:24<1:45:17,  1.61it/s]
 82%|████████▏ | 47405/57600 [8:20:25<1:44:25,  1.63it/s]
 82%|████████▏ | 47406/57600 [8:20:26<1:44:50,  1.62it/s]
 82%|████████▏ | 47407/57600 [8:20:26<1:50:28,  1.54it/s]
 82%|████████▏ | 47408/57600 [8:20:27<1:50:41,  1.53it/s]
 82%|████████▏ | 47409/57600 [8:20:28<1:48:59,  1.56it/s]
 82%|████████▏ | 47410/57600 [8:20:28<1:45:00,  1.62it/s]
 82%|████████▏ | 47411/57600 [8:20:29<1:44:45,  1.62it/s]
 82%|████████▏ | 47412/57600 [8:20:29<1:44:08,  1.63it/s]
 82%|████████▏ | 47413/57600 [8:20:30<1:45:11,  1.61it/s]
 82%|████████▏ | 47414/57600 [8:20:31<1:45:17,  1.61it/s]
 82%|████████▏ | 47415/57600 [8:20:31<1:43:36,  1.64it/s]
 82%|████████▏ | 47416/57600 [8:20:32<1:43:46,  1.64it/s]
 82%|████████▏ | 47417/57600 [8:20:32<1:44:58,  1.62it/s]
 82%|████████▏ | 47418/57600 [8:20:33<1:43:54,  1.63it/s]
 82%|████████▏ | 47419/57600 [8:20:34<1:45:46,  1.60it/s]
 82%|████████▏ | 47420/57600 [8:20:34<1:45:59,  1.60it/s]
                                                         
{'loss': 1.1694, 'learning_rate': 2.5961672473867596e-07, 'epoch': 523.4}

 82%|████████▏ | 47420/57600 [8:20:34<1:45:59,  1.60it/s]
 82%|████████▏ | 47421/57600 [8:20:35<1:46:33,  1.59it/s]
 82%|████████▏ | 47422/57600 [8:20:36<1:51:24,  1.52it/s]
 82%|████████▏ | 47423/57600 [8:20:36<1:55:31,  1.47it/s]
 82%|████████▏ | 47424/57600 [8:20:37<1:52:57,  1.50it/s]
 82%|████████▏ | 47425/57600 [8:20:38<1:51:10,  1.53it/s]
 82%|████████▏ | 47426/57600 [8:20:38<1:47:21,  1.58it/s]
 82%|████████▏ | 47427/57600 [8:20:39<1:46:16,  1.60it/s]
 82%|████████▏ | 47428/57600 [8:20:39<1:46:03,  1.60it/s]
 82%|████████▏ | 47429/57600 [8:20:40<1:48:52,  1.56it/s]
 82%|████████▏ | 47430/57600 [8:20:41<1:47:29,  1.58it/s]
 82%|████████▏ | 47431/57600 [8:20:41<1:46:25,  1.59it/s]
 82%|████████▏ | 47432/57600 [8:20:42<1:43:50,  1.63it/s]
 82%|████████▏ | 47433/57600 [8:20:43<1:45:19,  1.61it/s]
 82%|████████▏ | 47434/57600 [8:20:43<1:44:11,  1.63it/s]
 82%|████████▏ | 47435/57600 [8:20:44<1:45:10,  1.61it/s]
 82%|████████▏ | 47436/57600 [8:20:44<1:44:14,  1.63it/s]
 82%|████████▏ | 47437/57600 [8:20:45<1:46:35,  1.59it/s]
 82%|████████▏ | 47438/57600 [8:20:46<1:45:15,  1.61it/s]
 82%|████████▏ | 47439/57600 [8:20:46<1:47:41,  1.57it/s]
 82%|████████▏ | 47440/57600 [8:20:47<1:45:15,  1.61it/s]
                                                         
{'loss': 1.1072, 'learning_rate': 2.593031358885017e-07, 'epoch': 523.62}

 82%|████████▏ | 47440/57600 [8:20:47<1:45:15,  1.61it/s]
 82%|████████▏ | 47441/57600 [8:20:48<1:45:42,  1.60it/s]
 82%|████████▏ | 47442/57600 [8:20:48<1:48:44,  1.56it/s]
 82%|████████▏ | 47443/57600 [8:20:49<1:46:10,  1.59it/s]
 82%|████████▏ | 47444/57600 [8:20:49<1:44:52,  1.61it/s]
 82%|████████▏ | 47445/57600 [8:20:50<1:42:25,  1.65it/s]
 82%|████████▏ | 47446/57600 [8:20:51<1:42:42,  1.65it/s]
 82%|████████▏ | 47447/57600 [8:20:51<1:45:30,  1.60it/s]
 82%|████████▏ | 47448/57600 [8:20:52<1:46:10,  1.59it/s]
 82%|████████▏ | 47449/57600 [8:20:53<1:42:48,  1.65it/s]
 82%|████████▏ | 47450/57600 [8:20:53<1:42:35,  1.65it/s]
 82%|████████▏ | 47451/57600 [8:20:54<1:43:41,  1.63it/s]
 82%|████████▏ | 47452/57600 [8:20:54<1:47:11,  1.58it/s]
 82%|████████▏ | 47453/57600 [8:20:55<1:49:49,  1.54it/s]
 82%|████████▏ | 47454/57600 [8:20:56<1:48:21,  1.56it/s]
 82%|████████▏ | 47455/57600 [8:20:56<1:47:17,  1.58it/s]
 82%|████████▏ | 47456/57600 [8:20:57<1:48:35,  1.56it/s]
 82%|████████▏ | 47457/57600 [8:20:58<1:54:10,  1.48it/s]
 82%|████████▏ | 47458/57600 [8:20:58<1:51:12,  1.52it/s]
 82%|████████▏ | 47459/57600 [8:20:59<1:53:51,  1.48it/s]
 82%|████████▏ | 47460/57600 [8:21:00<1:51:43,  1.51it/s]
                                                         
{'loss': 1.1324, 'learning_rate': 2.589895470383275e-07, 'epoch': 523.84}

 82%|████████▏ | 47460/57600 [8:21:00<1:51:43,  1.51it/s]
 82%|████████▏ | 47461/57600 [8:21:00<1:52:31,  1.50it/s]
 82%|████████▏ | 47462/57600 [8:21:01<1:48:23,  1.56it/s]
 82%|████████▏ | 47463/57600 [8:21:02<1:48:21,  1.56it/s]
 82%|████████▏ | 47464/57600 [8:21:02<1:45:56,  1.59it/s]
 82%|████████▏ | 47465/57600 [8:21:03<1:50:41,  1.53it/s]
 82%|████████▏ | 47466/57600 [8:21:04<1:47:04,  1.58it/s]
 82%|████████▏ | 47467/57600 [8:21:04<1:47:59,  1.56it/s]
 82%|████████▏ | 47468/57600 [8:21:05<1:47:02,  1.58it/s]
 82%|████████▏ | 47469/57600 [8:21:05<1:44:50,  1.61it/s]
 82%|████████▏ | 47470/57600 [8:21:06<1:46:46,  1.58it/s]
 82%|████████▏ | 47471/57600 [8:21:07<1:47:20,  1.57it/s]
 82%|████████▏ | 47472/57600 [8:21:07<1:45:16,  1.60it/s]
 82%|████████▏ | 47473/57600 [8:21:08<1:43:42,  1.63it/s]
 82%|████████▏ | 47474/57600 [8:21:09<1:43:28,  1.63it/s]
 82%|████████▏ | 47475/57600 [8:21:09<1:47:15,  1.57it/s]
 82%|████████▏ | 47476/57600 [8:21:10<1:45:19,  1.60it/s]
 82%|████████▏ | 47477/57600 [8:21:10<1:43:48,  1.63it/s]
 82%|████████▏ | 47478/57600 [8:21:11<1:43:46,  1.63it/s]
 82%|████████▏ | 47479/57600 [8:21:12<1:41:50,  1.66it/s]
 82%|████████▏ | 47480/57600 [8:21:12<1:40:31,  1.68it/s]
                                                         
{'loss': 1.1341, 'learning_rate': 2.5867595818815316e-07, 'epoch': 524.06}

 82%|████████▏ | 47480/57600 [8:21:12<1:40:31,  1.68it/s]
 82%|████████▏ | 47481/57600 [8:21:13<1:45:04,  1.60it/s]
 82%|████████▏ | 47482/57600 [8:21:13<1:42:27,  1.65it/s]
 82%|████████▏ | 47483/57600 [8:21:14<1:42:50,  1.64it/s]
 82%|████████▏ | 47484/57600 [8:21:15<1:42:28,  1.65it/s]
 82%|████████▏ | 47485/57600 [8:21:15<1:44:25,  1.61it/s]
 82%|████████▏ | 47486/57600 [8:21:16<1:45:23,  1.60it/s]
 82%|████████▏ | 47487/57600 [8:21:17<1:45:27,  1.60it/s]
 82%|████████▏ | 47488/57600 [8:21:17<1:44:01,  1.62it/s]
 82%|████████▏ | 47489/57600 [8:21:18<1:44:46,  1.61it/s]
 82%|████████▏ | 47490/57600 [8:21:18<1:44:37,  1.61it/s]
 82%|████████▏ | 47491/57600 [8:21:19<1:45:13,  1.60it/s]
 82%|████████▏ | 47492/57600 [8:21:20<1:47:29,  1.57it/s]
 82%|████████▏ | 47493/57600 [8:21:20<1:47:20,  1.57it/s]
 82%|████████▏ | 47494/57600 [8:21:21<1:47:06,  1.57it/s]
 82%|████████▏ | 47495/57600 [8:21:22<1:48:45,  1.55it/s]
 82%|████████▏ | 47496/57600 [8:21:22<1:47:35,  1.57it/s]
 82%|████████▏ | 47497/57600 [8:21:23<1:47:53,  1.56it/s]
 82%|████████▏ | 47498/57600 [8:21:24<1:46:29,  1.58it/s]
 82%|████████▏ | 47499/57600 [8:21:24<1:46:42,  1.58it/s]
 82%|████████▏ | 47500/57600 [8:21:25<1:48:54,  1.55it/s]
                                                         
{'loss': 1.1216, 'learning_rate': 2.5836236933797907e-07, 'epoch': 524.28}

 82%|████████▏ | 47500/57600 [8:21:25<1:48:54,  1.55it/s]
 82%|████████▏ | 47501/57600 [8:21:25<1:46:32,  1.58it/s]
 82%|████████▏ | 47502/57600 [8:21:26<1:43:12,  1.63it/s]
 82%|████████▏ | 47503/57600 [8:21:27<1:48:21,  1.55it/s]
 82%|████████▏ | 47504/57600 [8:21:27<1:47:22,  1.57it/s]
 82%|████████▏ | 47505/57600 [8:21:28<1:43:16,  1.63it/s]
 82%|████████▏ | 47506/57600 [8:21:29<1:44:53,  1.60it/s]
 82%|████████▏ | 47507/57600 [8:21:29<1:43:25,  1.63it/s]
 82%|████████▏ | 47508/57600 [8:21:30<1:50:56,  1.52it/s]
 82%|████████▏ | 47509/57600 [8:21:31<1:51:56,  1.50it/s]
 82%|████████▏ | 47510/57600 [8:21:31<1:51:56,  1.50it/s]
 82%|████████▏ | 47511/57600 [8:21:32<1:49:50,  1.53it/s]
 82%|████████▏ | 47512/57600 [8:21:33<1:53:36,  1.48it/s]
 82%|████████▏ | 47513/57600 [8:21:33<1:49:30,  1.54it/s]
 82%|████████▏ | 47514/57600 [8:21:34<1:51:08,  1.51it/s]
 82%|████████▏ | 47515/57600 [8:21:34<1:48:02,  1.56it/s]
 82%|████████▏ | 47516/57600 [8:21:35<1:47:58,  1.56it/s]
 82%|████████▏ | 47517/57600 [8:21:36<1:46:28,  1.58it/s]
 82%|████████▏ | 47518/57600 [8:21:36<1:46:58,  1.57it/s]
 82%|████████▏ | 47519/57600 [8:21:37<1:45:30,  1.59it/s]
 82%|████████▎ | 47520/57600 [8:21:38<1:44:33,  1.61it/s]
                                                         
{'loss': 1.1209, 'learning_rate': 2.5804878048780493e-07, 'epoch': 524.5}

 82%|████████▎ | 47520/57600 [8:21:38<1:44:33,  1.61it/s]
 83%|████████▎ | 47521/57600 [8:21:38<1:44:30,  1.61it/s]
 83%|████████▎ | 47522/57600 [8:21:39<1:44:18,  1.61it/s]
 83%|████████▎ | 47523/57600 [8:21:39<1:44:46,  1.60it/s]
 83%|████████▎ | 47524/57600 [8:21:40<1:46:38,  1.57it/s]
 83%|████████▎ | 47525/57600 [8:21:41<1:45:38,  1.59it/s]
 83%|████████▎ | 47526/57600 [8:21:41<1:47:29,  1.56it/s]
 83%|████████▎ | 47527/57600 [8:21:42<1:48:30,  1.55it/s]
 83%|████████▎ | 47528/57600 [8:21:43<1:45:43,  1.59it/s]
 83%|████████▎ | 47529/57600 [8:21:43<1:45:16,  1.59it/s]
 83%|████████▎ | 47530/57600 [8:21:44<1:44:11,  1.61it/s]
 83%|████████▎ | 47531/57600 [8:21:44<1:42:43,  1.63it/s]
 83%|████████▎ | 47532/57600 [8:21:45<1:45:32,  1.59it/s]
 83%|████████▎ | 47533/57600 [8:21:46<1:41:59,  1.65it/s]
 83%|████████▎ | 47534/57600 [8:21:46<1:41:14,  1.66it/s]
 83%|████████▎ | 47535/57600 [8:21:47<1:43:40,  1.62it/s]
 83%|████████▎ | 47536/57600 [8:21:48<1:44:09,  1.61it/s]
 83%|████████▎ | 47537/57600 [8:21:48<1:43:29,  1.62it/s]
 83%|████████▎ | 47538/57600 [8:21:49<1:43:47,  1.62it/s]
 83%|████████▎ | 47539/57600 [8:21:49<1:42:49,  1.63it/s]
 83%|████████▎ | 47540/57600 [8:21:50<1:41:33,  1.65it/s]
                                                         
{'loss': 1.141, 'learning_rate': 2.5773519163763063e-07, 'epoch': 524.72}

 83%|████████▎ | 47540/57600 [8:21:50<1:41:33,  1.65it/s]
 83%|████████▎ | 47541/57600 [8:21:51<1:44:02,  1.61it/s]
 83%|████████▎ | 47542/57600 [8:21:51<1:43:16,  1.62it/s]
 83%|████████▎ | 47543/57600 [8:21:52<1:45:58,  1.58it/s]
 83%|████████▎ | 47544/57600 [8:21:53<1:43:37,  1.62it/s]
 83%|████████▎ | 47545/57600 [8:21:53<1:44:12,  1.61it/s]
 83%|████████▎ | 47546/57600 [8:21:54<1:45:21,  1.59it/s]
 83%|████████▎ | 47547/57600 [8:21:54<1:47:14,  1.56it/s]
 83%|████████▎ | 47548/57600 [8:21:55<1:47:46,  1.55it/s]
 83%|████████▎ | 47549/57600 [8:21:56<1:45:51,  1.58it/s]
 83%|████████▎ | 47550/57600 [8:21:56<1:44:14,  1.61it/s]
 83%|████████▎ | 47551/57600 [8:21:57<1:44:10,  1.61it/s]
 83%|████████▎ | 47552/57600 [8:21:58<1:44:49,  1.60it/s]
 83%|████████▎ | 47553/57600 [8:21:58<1:42:44,  1.63it/s]
 83%|████████▎ | 47554/57600 [8:21:59<1:42:45,  1.63it/s]
 83%|████████▎ | 47555/57600 [8:21:59<1:43:14,  1.62it/s]
 83%|████████▎ | 47556/57600 [8:22:00<1:49:16,  1.53it/s]
 83%|████████▎ | 47557/57600 [8:22:01<1:47:54,  1.55it/s]
 83%|████████▎ | 47558/57600 [8:22:01<1:48:49,  1.54it/s]
 83%|████████▎ | 47559/57600 [8:22:02<1:45:57,  1.58it/s]
 83%|████████▎ | 47560/57600 [8:22:03<1:47:43,  1.55it/s]
                                                         
{'loss': 1.1072, 'learning_rate': 2.5742160278745643e-07, 'epoch': 524.94}

 83%|████████▎ | 47560/57600 [8:22:03<1:47:43,  1.55it/s]
 83%|████████▎ | 47561/57600 [8:22:03<1:47:23,  1.56it/s]
 83%|████████▎ | 47562/57600 [8:22:04<1:45:45,  1.58it/s]
 83%|████████▎ | 47563/57600 [8:22:05<1:43:26,  1.62it/s]
 83%|████████▎ | 47564/57600 [8:22:05<1:49:57,  1.52it/s]
 83%|████████▎ | 47565/57600 [8:22:06<1:51:27,  1.50it/s]
 83%|████████▎ | 47566/57600 [8:22:07<1:55:26,  1.45it/s]
 83%|████████▎ | 47567/57600 [8:22:07<1:54:40,  1.46it/s]
 83%|████████▎ | 47568/57600 [8:22:08<1:50:55,  1.51it/s]
 83%|████████▎ | 47569/57600 [8:22:09<1:48:56,  1.53it/s]
 83%|████████▎ | 47570/57600 [8:22:09<1:46:14,  1.57it/s]
 83%|████████▎ | 47571/57600 [8:22:10<1:44:46,  1.60it/s]
 83%|████████▎ | 47572/57600 [8:22:10<1:44:14,  1.60it/s]
 83%|████████▎ | 47573/57600 [8:22:11<1:45:39,  1.58it/s]
 83%|████████▎ | 47574/57600 [8:22:12<1:44:26,  1.60it/s]
 83%|████████▎ | 47575/57600 [8:22:12<1:42:46,  1.63it/s]
 83%|████████▎ | 47576/57600 [8:22:13<1:42:32,  1.63it/s]
 83%|████████▎ | 47577/57600 [8:22:14<1:44:22,  1.60it/s]
 83%|████████▎ | 47578/57600 [8:22:14<1:42:29,  1.63it/s]
 83%|████████▎ | 47579/57600 [8:22:15<1:40:01,  1.67it/s]
 83%|████████▎ | 47580/57600 [8:22:15<1:39:54,  1.67it/s]
                                                         
{'loss': 1.1676, 'learning_rate': 2.571080139372822e-07, 'epoch': 525.17}

 83%|████████▎ | 47580/57600 [8:22:15<1:39:54,  1.67it/s]
 83%|████████▎ | 47581/57600 [8:22:16<1:40:26,  1.66it/s]
 83%|████████▎ | 47582/57600 [8:22:17<1:41:04,  1.65it/s]
 83%|████████▎ | 47583/57600 [8:22:17<1:43:25,  1.61it/s]
 83%|████████▎ | 47584/57600 [8:22:18<1:42:24,  1.63it/s]
 83%|████████▎ | 47585/57600 [8:22:18<1:43:09,  1.62it/s]
 83%|████████▎ | 47586/57600 [8:22:19<1:40:08,  1.67it/s]
 83%|████████▎ | 47587/57600 [8:22:20<1:39:48,  1.67it/s]
 83%|████████▎ | 47588/57600 [8:22:20<1:42:55,  1.62it/s]
 83%|████████▎ | 47589/57600 [8:22:21<1:42:08,  1.63it/s]
 83%|████████▎ | 47590/57600 [8:22:21<1:41:11,  1.65it/s]
 83%|████████▎ | 47591/57600 [8:22:22<1:39:07,  1.68it/s]
 83%|████████▎ | 47592/57600 [8:22:23<1:41:33,  1.64it/s]
 83%|████████▎ | 47593/57600 [8:22:23<1:42:55,  1.62it/s]
 83%|████████▎ | 47594/57600 [8:22:24<1:45:46,  1.58it/s]
 83%|████████▎ | 47595/57600 [8:22:24<1:41:52,  1.64it/s]
 83%|████████▎ | 47596/57600 [8:22:25<1:40:41,  1.66it/s]
 83%|████████▎ | 47597/57600 [8:22:26<1:38:55,  1.69it/s]
 83%|████████▎ | 47598/57600 [8:22:26<1:39:49,  1.67it/s]
 83%|████████▎ | 47599/57600 [8:22:27<1:40:52,  1.65it/s]
 83%|████████▎ | 47600/57600 [8:22:27<1:40:50,  1.65it/s]
                                                         
{'loss': 1.1765, 'learning_rate': 2.5679442508710804e-07, 'epoch': 525.39}

 83%|████████▎ | 47600/57600 [8:22:27<1:40:50,  1.65it/s]
 83%|████████▎ | 47601/57600 [8:22:28<1:41:50,  1.64it/s]
 83%|████████▎ | 47602/57600 [8:22:29<1:40:10,  1.66it/s]
 83%|████████▎ | 47603/57600 [8:22:29<1:40:20,  1.66it/s]
 83%|████████▎ | 47604/57600 [8:22:30<1:42:22,  1.63it/s]
 83%|████████▎ | 47605/57600 [8:22:31<1:41:59,  1.63it/s]
 83%|████████▎ | 47606/57600 [8:22:31<1:45:42,  1.58it/s]
 83%|████████▎ | 47607/57600 [8:22:32<1:46:31,  1.56it/s]
 83%|████████▎ | 47608/57600 [8:22:33<1:48:11,  1.54it/s]
 83%|████████▎ | 47609/57600 [8:22:33<1:50:04,  1.51it/s]
 83%|████████▎ | 47610/57600 [8:22:34<1:50:00,  1.51it/s]
 83%|████████▎ | 47611/57600 [8:22:35<1:48:24,  1.54it/s]
 83%|████████▎ | 47612/57600 [8:22:35<1:48:34,  1.53it/s]
 83%|████████▎ | 47613/57600 [8:22:36<1:46:02,  1.57it/s]
 83%|████████▎ | 47614/57600 [8:22:36<1:46:20,  1.57it/s]
 83%|████████▎ | 47615/57600 [8:22:37<1:48:48,  1.53it/s]
 83%|████████▎ | 47616/57600 [8:22:38<1:49:04,  1.53it/s]
 83%|████████▎ | 47617/57600 [8:22:38<1:48:01,  1.54it/s]
 83%|████████▎ | 47618/57600 [8:22:39<1:48:31,  1.53it/s]
 83%|████████▎ | 47619/57600 [8:22:40<1:45:46,  1.57it/s]
 83%|████████▎ | 47620/57600 [8:22:40<1:45:47,  1.57it/s]
                                                         
{'loss': 1.1005, 'learning_rate': 2.5648083623693374e-07, 'epoch': 525.61}

 83%|████████▎ | 47620/57600 [8:22:40<1:45:47,  1.57it/s]
 83%|████████▎ | 47621/57600 [8:22:41<1:50:51,  1.50it/s]
 83%|████████▎ | 47622/57600 [8:22:42<1:50:55,  1.50it/s]
 83%|████████▎ | 47623/57600 [8:22:42<1:47:18,  1.55it/s]
 83%|████████▎ | 47624/57600 [8:22:43<1:49:56,  1.51it/s]
 83%|████████▎ | 47625/57600 [8:22:44<1:48:52,  1.53it/s]
 83%|████████▎ | 47626/57600 [8:22:44<1:45:07,  1.58it/s]
 83%|████████▎ | 47627/57600 [8:22:45<1:44:42,  1.59it/s]
 83%|████████▎ | 47628/57600 [8:22:46<1:47:25,  1.55it/s]
 83%|████████▎ | 47629/57600 [8:22:46<1:46:53,  1.55it/s]
 83%|████████▎ | 47630/57600 [8:22:47<1:47:51,  1.54it/s]
 83%|████████▎ | 47631/57600 [8:22:47<1:43:58,  1.60it/s]
 83%|████████▎ | 47632/57600 [8:22:48<1:41:26,  1.64it/s]
 83%|████████▎ | 47633/57600 [8:22:49<1:40:57,  1.65it/s]
 83%|████████▎ | 47634/57600 [8:22:49<1:43:24,  1.61it/s]
 83%|████████▎ | 47635/57600 [8:22:50<1:41:15,  1.64it/s]
 83%|████████▎ | 47636/57600 [8:22:51<1:47:10,  1.55it/s]
 83%|████████▎ | 47637/57600 [8:22:51<1:47:11,  1.55it/s]
 83%|████████▎ | 47638/57600 [8:22:52<1:44:08,  1.59it/s]
 83%|████████▎ | 47639/57600 [8:22:52<1:41:05,  1.64it/s]
 83%|████████▎ | 47640/57600 [8:22:53<1:42:34,  1.62it/s]
                                                         
{'loss': 1.0937, 'learning_rate': 2.5616724738675955e-07, 'epoch': 525.83}

 83%|████████▎ | 47640/57600 [8:22:53<1:42:34,  1.62it/s]
 83%|████████▎ | 47641/57600 [8:22:54<1:45:11,  1.58it/s]
 83%|████████▎ | 47642/57600 [8:22:54<1:46:39,  1.56it/s]
 83%|████████▎ | 47643/57600 [8:22:55<1:44:29,  1.59it/s]
 83%|████████▎ | 47644/57600 [8:22:56<1:48:39,  1.53it/s]
 83%|████████▎ | 47645/57600 [8:22:56<1:47:09,  1.55it/s]
 83%|████████▎ | 47646/57600 [8:22:57<1:43:46,  1.60it/s]
 83%|████████▎ | 47647/57600 [8:22:57<1:44:34,  1.59it/s]
 83%|████████▎ | 47648/57600 [8:22:58<1:46:22,  1.56it/s]
 83%|████████▎ | 47649/57600 [8:22:59<1:49:38,  1.51it/s]
 83%|████████▎ | 47650/57600 [8:22:59<1:44:06,  1.59it/s]
 83%|████████▎ | 47651/57600 [8:23:00<1:44:55,  1.58it/s]
 83%|████████▎ | 47652/57600 [8:23:01<1:45:51,  1.57it/s]
 83%|████████▎ | 47653/57600 [8:23:01<1:46:36,  1.56it/s]
 83%|████████▎ | 47654/57600 [8:23:02<1:45:39,  1.57it/s]
 83%|████████▎ | 47655/57600 [8:23:03<1:44:56,  1.58it/s]
 83%|████████▎ | 47656/57600 [8:23:03<1:54:07,  1.45it/s]
 83%|████████▎ | 47657/57600 [8:23:04<1:49:58,  1.51it/s]
 83%|████████▎ | 47658/57600 [8:23:05<1:51:42,  1.48it/s]
 83%|████████▎ | 47659/57600 [8:23:05<1:51:42,  1.48it/s]
 83%|████████▎ | 47660/57600 [8:23:06<1:50:09,  1.50it/s]
                                                         
{'loss': 1.0996, 'learning_rate': 2.558536585365854e-07, 'epoch': 526.05}

 83%|████████▎ | 47660/57600 [8:23:06<1:50:09,  1.50it/s]
 83%|████████▎ | 47661/57600 [8:23:07<1:48:15,  1.53it/s]
 83%|████████▎ | 47662/57600 [8:23:07<1:46:47,  1.55it/s]
 83%|████████▎ | 47663/57600 [8:23:08<1:50:52,  1.49it/s]
 83%|████████▎ | 47664/57600 [8:23:09<1:52:20,  1.47it/s]
 83%|████████▎ | 47665/57600 [8:23:09<1:48:56,  1.52it/s]
 83%|████████▎ | 47666/57600 [8:23:10<1:47:41,  1.54it/s]
 83%|████████▎ | 47667/57600 [8:23:11<1:43:43,  1.60it/s]
 83%|████████▎ | 47668/57600 [8:23:11<1:42:40,  1.61it/s]
 83%|████████▎ | 47669/57600 [8:23:12<1:41:53,  1.62it/s]
 83%|████████▎ | 47670/57600 [8:23:12<1:46:20,  1.56it/s]
 83%|████████▎ | 47671/57600 [8:23:13<1:43:44,  1.60it/s]
 83%|████████▎ | 47672/57600 [8:23:14<1:43:06,  1.60it/s]
 83%|████████▎ | 47673/57600 [8:23:14<1:40:47,  1.64it/s]
 83%|████████▎ | 47674/57600 [8:23:15<1:42:10,  1.62it/s]
 83%|████████▎ | 47675/57600 [8:23:15<1:41:12,  1.63it/s]
 83%|████████▎ | 47676/57600 [8:23:16<1:46:19,  1.56it/s]
 83%|████████▎ | 47677/57600 [8:23:17<1:46:31,  1.55it/s]
 83%|████████▎ | 47678/57600 [8:23:17<1:45:14,  1.57it/s]
 83%|████████▎ | 47679/57600 [8:23:18<1:44:26,  1.58it/s]
 83%|████████▎ | 47680/57600 [8:23:19<1:41:19,  1.63it/s]
                                                         
{'loss': 1.1112, 'learning_rate': 2.5554006968641116e-07, 'epoch': 526.27}

 83%|████████▎ | 47680/57600 [8:23:19<1:41:19,  1.63it/s]
 83%|████████▎ | 47681/57600 [8:23:19<1:44:51,  1.58it/s]
 83%|████████▎ | 47682/57600 [8:23:20<1:42:27,  1.61it/s]
 83%|████████▎ | 47683/57600 [8:23:20<1:40:24,  1.65it/s]
 83%|████████▎ | 47684/57600 [8:23:21<1:39:15,  1.66it/s]
 83%|████████▎ | 47685/57600 [8:23:22<1:38:01,  1.69it/s]
 83%|████████▎ | 47686/57600 [8:23:22<1:36:36,  1.71it/s]
 83%|████████▎ | 47687/57600 [8:23:23<1:39:02,  1.67it/s]
 83%|████████▎ | 47688/57600 [8:23:23<1:40:32,  1.64it/s]
 83%|████████▎ | 47689/57600 [8:23:24<1:40:27,  1.64it/s]
 83%|████████▎ | 47690/57600 [8:23:25<1:45:07,  1.57it/s]
 83%|████████▎ | 47691/57600 [8:23:25<1:40:42,  1.64it/s]
 83%|████████▎ | 47692/57600 [8:23:26<1:41:37,  1.62it/s]
 83%|████████▎ | 47693/57600 [8:23:27<1:43:08,  1.60it/s]
 83%|████████▎ | 47694/57600 [8:23:27<1:43:26,  1.60it/s]
 83%|████████▎ | 47695/57600 [8:23:28<1:43:07,  1.60it/s]
 83%|████████▎ | 47696/57600 [8:23:28<1:40:47,  1.64it/s]
 83%|████████▎ | 47697/57600 [8:23:29<1:40:10,  1.65it/s]
 83%|████████▎ | 47698/57600 [8:23:30<1:41:53,  1.62it/s]
 83%|████████▎ | 47699/57600 [8:23:30<1:39:32,  1.66it/s]
 83%|████████▎ | 47700/57600 [8:23:31<1:38:20,  1.68it/s]
                                                         
{'loss': 1.1295, 'learning_rate': 2.552264808362369e-07, 'epoch': 526.49}

 83%|████████▎ | 47700/57600 [8:23:31<1:38:20,  1.68it/s]
 83%|████████▎ | 47701/57600 [8:23:31<1:38:22,  1.68it/s]
 83%|████████▎ | 47702/57600 [8:23:32<1:38:26,  1.68it/s]
 83%|████████▎ | 47703/57600 [8:23:33<1:39:54,  1.65it/s]
 83%|████████▎ | 47704/57600 [8:23:33<1:40:24,  1.64it/s]
 83%|████████▎ | 47705/57600 [8:23:34<1:44:46,  1.57it/s]
 83%|████████▎ | 47706/57600 [8:23:35<1:43:21,  1.60it/s]
 83%|████████▎ | 47707/57600 [8:23:35<1:43:58,  1.59it/s]
 83%|████████▎ | 47708/57600 [8:23:36<1:47:33,  1.53it/s]
 83%|████████▎ | 47709/57600 [8:23:36<1:45:18,  1.57it/s]
 83%|████████▎ | 47710/57600 [8:23:37<1:44:05,  1.58it/s]
 83%|████████▎ | 47711/57600 [8:23:38<1:43:51,  1.59it/s]
 83%|████████▎ | 47712/57600 [8:23:38<1:43:07,  1.60it/s]
 83%|████████▎ | 47713/57600 [8:23:39<1:42:42,  1.60it/s]
 83%|████████▎ | 47714/57600 [8:23:40<1:43:40,  1.59it/s]
 83%|████████▎ | 47715/57600 [8:23:40<1:43:44,  1.59it/s]
 83%|████████▎ | 47716/57600 [8:23:41<1:47:12,  1.54it/s]
 83%|████████▎ | 47717/57600 [8:23:42<1:48:18,  1.52it/s]
 83%|████████▎ | 47718/57600 [8:23:42<1:52:47,  1.46it/s]
 83%|████████▎ | 47719/57600 [8:23:43<1:46:28,  1.55it/s]
 83%|████████▎ | 47720/57600 [8:23:44<1:49:55,  1.50it/s]
                                                         
{'loss': 1.0978, 'learning_rate': 2.5491289198606266e-07, 'epoch': 526.71}

 83%|████████▎ | 47720/57600 [8:23:44<1:49:55,  1.50it/s]
 83%|████████▎ | 47721/57600 [8:23:44<1:48:03,  1.52it/s]
 83%|████████▎ | 47722/57600 [8:23:45<1:48:50,  1.51it/s]
 83%|████████▎ | 47723/57600 [8:23:46<1:46:35,  1.54it/s]
 83%|████████▎ | 47724/57600 [8:23:46<1:44:06,  1.58it/s]
 83%|████████▎ | 47725/57600 [8:23:47<1:42:41,  1.60it/s]
 83%|████████▎ | 47726/57600 [8:23:47<1:45:09,  1.56it/s]
 83%|████████▎ | 47727/57600 [8:23:48<1:46:13,  1.55it/s]
 83%|████████▎ | 47728/57600 [8:23:49<1:48:57,  1.51it/s]
 83%|████████▎ | 47729/57600 [8:23:49<1:48:01,  1.52it/s]
 83%|████████▎ | 47730/57600 [8:23:50<1:52:40,  1.46it/s]
 83%|████████▎ | 47731/57600 [8:23:51<1:46:08,  1.55it/s]
 83%|████████▎ | 47732/57600 [8:23:51<1:43:14,  1.59it/s]
 83%|████████▎ | 47733/57600 [8:23:52<1:46:07,  1.55it/s]
 83%|████████▎ | 47734/57600 [8:23:53<1:47:58,  1.52it/s]
 83%|████████▎ | 47735/57600 [8:23:53<1:44:27,  1.57it/s]
 83%|████████▎ | 47736/57600 [8:23:54<1:45:43,  1.55it/s]
 83%|████████▎ | 47737/57600 [8:23:55<1:45:07,  1.56it/s]
 83%|████████▎ | 47738/57600 [8:23:55<1:44:09,  1.58it/s]
 83%|████████▎ | 47739/57600 [8:23:56<1:44:29,  1.57it/s]
 83%|████████▎ | 47740/57600 [8:23:56<1:44:49,  1.57it/s]
                                                         
{'loss': 1.0924, 'learning_rate': 2.545993031358885e-07, 'epoch': 526.93}

 83%|████████▎ | 47740/57600 [8:23:56<1:44:49,  1.57it/s]
 83%|████████▎ | 47741/57600 [8:23:57<1:45:17,  1.56it/s]
 83%|████████▎ | 47742/57600 [8:23:58<1:43:25,  1.59it/s]
 83%|████████▎ | 47743/57600 [8:23:58<1:41:45,  1.61it/s]
 83%|████████▎ | 47744/57600 [8:23:59<1:41:56,  1.61it/s]
 83%|████████▎ | 47745/57600 [8:24:00<1:38:47,  1.66it/s]
 83%|████████▎ | 47746/57600 [8:24:00<1:39:20,  1.65it/s]
 83%|████████▎ | 47747/57600 [8:24:01<1:43:10,  1.59it/s]
 83%|████████▎ | 47748/57600 [8:24:01<1:42:52,  1.60it/s]
 83%|████████▎ | 47749/57600 [8:24:02<1:41:16,  1.62it/s]
 83%|████████▎ | 47750/57600 [8:24:03<1:39:37,  1.65it/s]
 83%|████████▎ | 47751/57600 [8:24:03<1:40:19,  1.64it/s]
 83%|████████▎ | 47752/57600 [8:24:04<1:40:19,  1.64it/s]
 83%|████████▎ | 47753/57600 [8:24:04<1:39:01,  1.66it/s]
 83%|████████▎ | 47754/57600 [8:24:05<1:37:51,  1.68it/s]
 83%|████████▎ | 47755/57600 [8:24:06<1:36:29,  1.70it/s]
 83%|████████▎ | 47756/57600 [8:24:06<1:39:23,  1.65it/s]
 83%|████████▎ | 47757/57600 [8:24:07<1:46:54,  1.53it/s]
 83%|████████▎ | 47758/57600 [8:24:08<1:42:09,  1.61it/s]
 83%|████████▎ | 47759/57600 [8:24:08<1:39:18,  1.65it/s]
 83%|████████▎ | 47760/57600 [8:24:09<1:39:34,  1.65it/s]
                                                         
{'loss': 1.184, 'learning_rate': 2.542857142857142e-07, 'epoch': 527.15}

 83%|████████▎ | 47760/57600 [8:24:09<1:39:34,  1.65it/s]
 83%|████████▎ | 47761/57600 [8:24:09<1:40:59,  1.62it/s]
 83%|████████▎ | 47762/57600 [8:24:10<1:46:59,  1.53it/s]
 83%|████████▎ | 47763/57600 [8:24:11<1:46:23,  1.54it/s]
 83%|████████▎ | 47764/57600 [8:24:11<1:43:04,  1.59it/s]
 83%|████████▎ | 47765/57600 [8:24:12<1:42:52,  1.59it/s]
 83%|████████▎ | 47766/57600 [8:24:13<1:41:06,  1.62it/s]
 83%|████████▎ | 47767/57600 [8:24:13<1:42:23,  1.60it/s]
 83%|████████▎ | 47768/57600 [8:24:14<1:43:02,  1.59it/s]
 83%|████████▎ | 47769/57600 [8:24:14<1:42:42,  1.60it/s]
 83%|████████▎ | 47770/57600 [8:24:15<1:44:47,  1.56it/s]
 83%|████████▎ | 47771/57600 [8:24:16<1:45:16,  1.56it/s]
 83%|████████▎ | 47772/57600 [8:24:16<1:43:09,  1.59it/s]
 83%|████████▎ | 47773/57600 [8:24:17<1:41:42,  1.61it/s]
 83%|████████▎ | 47774/57600 [8:24:18<1:43:29,  1.58it/s]
 83%|████████▎ | 47775/57600 [8:24:18<1:40:46,  1.62it/s]
 83%|████████▎ | 47776/57600 [8:24:19<1:41:54,  1.61it/s]
 83%|████████▎ | 47777/57600 [8:24:19<1:41:36,  1.61it/s]
 83%|████████▎ | 47778/57600 [8:24:20<1:43:58,  1.57it/s]
 83%|████████▎ | 47779/57600 [8:24:21<1:41:35,  1.61it/s]
 83%|████████▎ | 47780/57600 [8:24:21<1:42:00,  1.60it/s]
                                                         
{'loss': 1.1071, 'learning_rate': 2.5397212543554e-07, 'epoch': 527.37}

 83%|████████▎ | 47780/57600 [8:24:21<1:42:00,  1.60it/s]
 83%|████████▎ | 47781/57600 [8:24:22<1:42:12,  1.60it/s]
 83%|████████▎ | 47782/57600 [8:24:23<1:42:54,  1.59it/s]
 83%|████████▎ | 47783/57600 [8:24:23<1:41:12,  1.62it/s]
 83%|████████▎ | 47784/57600 [8:24:24<1:41:49,  1.61it/s]
 83%|████████▎ | 47785/57600 [8:24:25<1:47:48,  1.52it/s]
 83%|████████▎ | 47786/57600 [8:24:25<1:44:47,  1.56it/s]
 83%|████████▎ | 47787/57600 [8:24:26<1:50:20,  1.48it/s]
 83%|████████▎ | 47788/57600 [8:24:26<1:45:37,  1.55it/s]
 83%|████████▎ | 47789/57600 [8:24:27<1:43:30,  1.58it/s]
 83%|████████▎ | 47790/57600 [8:24:28<1:44:41,  1.56it/s]
 83%|████████▎ | 47791/57600 [8:24:28<1:44:50,  1.56it/s]
 83%|████████▎ | 47792/57600 [8:24:29<1:42:37,  1.59it/s]
 83%|████████▎ | 47793/57600 [8:24:30<1:43:40,  1.58it/s]
 83%|████████▎ | 47794/57600 [8:24:30<1:43:44,  1.58it/s]
 83%|████████▎ | 47795/57600 [8:24:31<1:41:02,  1.62it/s]
 83%|████████▎ | 47796/57600 [8:24:31<1:38:54,  1.65it/s]
 83%|████████▎ | 47797/57600 [8:24:32<1:39:42,  1.64it/s]
 83%|████████▎ | 47798/57600 [8:24:33<1:39:19,  1.64it/s]
 83%|████████▎ | 47799/57600 [8:24:33<1:39:25,  1.64it/s]
 83%|████████▎ | 47800/57600 [8:24:34<1:40:03,  1.63it/s]
                                                         
{'loss': 1.1094, 'learning_rate': 2.536585365853659e-07, 'epoch': 527.59}

 83%|████████▎ | 47800/57600 [8:24:34<1:40:03,  1.63it/s]
 83%|████████▎ | 47801/57600 [8:24:35<1:40:53,  1.62it/s]
 83%|████████▎ | 47802/57600 [8:24:35<1:42:18,  1.60it/s]
 83%|████████▎ | 47803/57600 [8:24:36<1:45:59,  1.54it/s]
 83%|████████▎ | 47804/57600 [8:24:36<1:42:39,  1.59it/s]
 83%|████████▎ | 47805/57600 [8:24:37<1:43:43,  1.57it/s]
 83%|████████▎ | 47806/57600 [8:24:38<1:42:34,  1.59it/s]
 83%|████████▎ | 47807/57600 [8:24:38<1:46:35,  1.53it/s]
 83%|████████▎ | 47808/57600 [8:24:39<1:49:18,  1.49it/s]
 83%|████████▎ | 47809/57600 [8:24:40<1:46:30,  1.53it/s]
 83%|████████▎ | 47810/57600 [8:24:40<1:41:47,  1.60it/s]
 83%|████████▎ | 47811/57600 [8:24:41<1:43:10,  1.58it/s]
 83%|████████▎ | 47812/57600 [8:24:42<1:41:18,  1.61it/s]
 83%|████████▎ | 47813/57600 [8:24:42<1:39:40,  1.64it/s]
 83%|████████▎ | 47814/57600 [8:24:43<1:39:25,  1.64it/s]
 83%|████████▎ | 47815/57600 [8:24:43<1:40:12,  1.63it/s]
 83%|████████▎ | 47816/57600 [8:24:44<1:38:34,  1.65it/s]
 83%|████████▎ | 47817/57600 [8:24:45<1:42:19,  1.59it/s]
 83%|████████▎ | 47818/57600 [8:24:45<1:41:08,  1.61it/s]
 83%|████████▎ | 47819/57600 [8:24:46<1:46:18,  1.53it/s]
 83%|████████▎ | 47820/57600 [8:24:47<1:42:55,  1.58it/s]
                                                         
{'loss': 1.1137, 'learning_rate': 2.533449477351916e-07, 'epoch': 527.81}

 83%|████████▎ | 47820/57600 [8:24:47<1:42:55,  1.58it/s]
 83%|████████▎ | 47821/57600 [8:24:47<1:40:53,  1.62it/s]
 83%|████████▎ | 47822/57600 [8:24:48<1:41:36,  1.60it/s]
 83%|████████▎ | 47823/57600 [8:24:48<1:39:54,  1.63it/s]
 83%|████████▎ | 47824/57600 [8:24:49<1:39:01,  1.65it/s]
 83%|████████▎ | 47825/57600 [8:24:50<1:44:42,  1.56it/s]
 83%|████████▎ | 47826/57600 [8:24:50<1:41:14,  1.61it/s]
 83%|████████▎ | 47827/57600 [8:24:51<1:43:44,  1.57it/s]
 83%|████████▎ | 47828/57600 [8:24:52<1:45:50,  1.54it/s]
 83%|████████▎ | 47829/57600 [8:24:52<1:41:46,  1.60it/s]
 83%|████████▎ | 47830/57600 [8:24:53<1:39:31,  1.64it/s]
 83%|████████▎ | 47831/57600 [8:24:53<1:42:47,  1.58it/s]
 83%|████████▎ | 47832/57600 [8:24:54<1:41:52,  1.60it/s]
 83%|████████▎ | 47833/57600 [8:24:55<1:40:36,  1.62it/s]
 83%|████████▎ | 47834/57600 [8:24:55<1:41:26,  1.60it/s]
 83%|████████▎ | 47835/57600 [8:24:56<1:47:12,  1.52it/s]
 83%|████████▎ | 47836/57600 [8:24:57<1:45:35,  1.54it/s]
 83%|████████▎ | 47837/57600 [8:24:57<1:47:32,  1.51it/s]
 83%|████████▎ | 47838/57600 [8:24:58<1:50:26,  1.47it/s]
 83%|████████▎ | 47839/57600 [8:24:59<1:50:32,  1.47it/s]
 83%|████████▎ | 47840/57600 [8:24:59<1:48:32,  1.50it/s]
                                                         
{'loss': 1.1011, 'learning_rate': 2.5303135888501744e-07, 'epoch': 528.04}

 83%|████████▎ | 47840/57600 [8:24:59<1:48:32,  1.50it/s]
 83%|████████▎ | 47841/57600 [8:25:00<1:47:07,  1.52it/s]
 83%|████████▎ | 47842/57600 [8:25:01<1:48:46,  1.50it/s]
 83%|████████▎ | 47843/57600 [8:25:01<1:46:12,  1.53it/s]
 83%|████████▎ | 47844/57600 [8:25:02<1:44:34,  1.55it/s]
 83%|████████▎ | 47845/57600 [8:25:03<1:43:55,  1.56it/s]
 83%|████████▎ | 47846/57600 [8:25:03<1:43:34,  1.57it/s]
 83%|████████▎ | 47847/57600 [8:25:04<1:42:21,  1.59it/s]
 83%|████████▎ | 47848/57600 [8:25:04<1:39:44,  1.63it/s]
 83%|████████▎ | 47849/57600 [8:25:05<1:40:21,  1.62it/s]
 83%|████████▎ | 47850/57600 [8:25:06<1:39:29,  1.63it/s]
 83%|████████▎ | 47851/57600 [8:25:06<1:40:04,  1.62it/s]
 83%|████████▎ | 47852/57600 [8:25:07<1:42:49,  1.58it/s]
 83%|████████▎ | 47853/57600 [8:25:08<1:40:52,  1.61it/s]
 83%|████████▎ | 47854/57600 [8:25:08<1:39:19,  1.64it/s]
 83%|████████▎ | 47855/57600 [8:25:09<1:38:00,  1.66it/s]
 83%|████████▎ | 47856/57600 [8:25:09<1:41:22,  1.60it/s]
 83%|████████▎ | 47857/57600 [8:25:10<1:42:08,  1.59it/s]
 83%|████████▎ | 47858/57600 [8:25:11<1:42:39,  1.58it/s]
 83%|████████▎ | 47859/57600 [8:25:11<1:42:45,  1.58it/s]
 83%|████████▎ | 47860/57600 [8:25:12<1:39:29,  1.63it/s]
                                                         
{'loss': 1.129, 'learning_rate': 2.5271777003484314e-07, 'epoch': 528.26}

 83%|████████▎ | 47860/57600 [8:25:12<1:39:29,  1.63it/s]
 83%|████████▎ | 47861/57600 [8:25:12<1:38:01,  1.66it/s]
 83%|████████▎ | 47862/57600 [8:25:13<1:39:01,  1.64it/s]
 83%|████████▎ | 47863/57600 [8:25:14<1:39:29,  1.63it/s]
 83%|████████▎ | 47864/57600 [8:25:14<1:37:45,  1.66it/s]
 83%|████████▎ | 47865/57600 [8:25:15<1:38:36,  1.65it/s]
 83%|████████▎ | 47866/57600 [8:25:15<1:37:18,  1.67it/s]
 83%|████████▎ | 47867/57600 [8:25:16<1:38:33,  1.65it/s]
 83%|████████▎ | 47868/57600 [8:25:17<1:37:57,  1.66it/s]
 83%|████████▎ | 47869/57600 [8:25:17<1:35:14,  1.70it/s]
 83%|████████▎ | 47870/57600 [8:25:18<1:39:43,  1.63it/s]
 83%|████████▎ | 47871/57600 [8:25:19<1:45:27,  1.54it/s]
 83%|████████▎ | 47872/57600 [8:25:19<1:43:20,  1.57it/s]
 83%|████████▎ | 47873/57600 [8:25:20<1:40:33,  1.61it/s]
 83%|████████▎ | 47874/57600 [8:25:21<1:45:23,  1.54it/s]
 83%|████████▎ | 47875/57600 [8:25:21<1:45:29,  1.54it/s]
 83%|████████▎ | 47876/57600 [8:25:22<1:47:15,  1.51it/s]
 83%|████████▎ | 47877/57600 [8:25:22<1:45:12,  1.54it/s]
 83%|████████▎ | 47878/57600 [8:25:23<1:40:41,  1.61it/s]
 83%|████████▎ | 47879/57600 [8:25:24<1:37:46,  1.66it/s]
 83%|████████▎ | 47880/57600 [8:25:24<1:37:03,  1.67it/s]
                                                         
{'loss': 1.1166, 'learning_rate': 2.52404181184669e-07, 'epoch': 528.48}

 83%|████████▎ | 47880/57600 [8:25:24<1:37:03,  1.67it/s]
 83%|████████▎ | 47881/57600 [8:25:25<1:43:07,  1.57it/s]
 83%|████████▎ | 47882/57600 [8:25:26<1:41:24,  1.60it/s]
 83%|████████▎ | 47883/57600 [8:25:26<1:41:30,  1.60it/s]
 83%|████████▎ | 47884/57600 [8:25:27<1:38:48,  1.64it/s]
 83%|████████▎ | 47885/57600 [8:25:27<1:42:24,  1.58it/s]
 83%|████████▎ | 47886/57600 [8:25:28<1:42:56,  1.57it/s]
 83%|████████▎ | 47887/57600 [8:25:29<1:40:49,  1.61it/s]
 83%|████████▎ | 47888/57600 [8:25:29<1:39:26,  1.63it/s]
 83%|████████▎ | 47889/57600 [8:25:30<1:41:41,  1.59it/s]
 83%|████████▎ | 47890/57600 [8:25:30<1:40:19,  1.61it/s]
 83%|████████▎ | 47891/57600 [8:25:31<1:38:17,  1.65it/s]
 83%|████████▎ | 47892/57600 [8:25:32<1:38:23,  1.64it/s]
 83%|████████▎ | 47893/57600 [8:25:32<1:39:06,  1.63it/s]
 83%|████████▎ | 47894/57600 [8:25:33<1:37:43,  1.66it/s]
 83%|████████▎ | 47895/57600 [8:25:34<1:38:25,  1.64it/s]
 83%|████████▎ | 47896/57600 [8:25:34<1:36:36,  1.67it/s]
 83%|████████▎ | 47897/57600 [8:25:35<1:36:32,  1.68it/s]
 83%|████████▎ | 47898/57600 [8:25:35<1:35:24,  1.69it/s]
 83%|████████▎ | 47899/57600 [8:25:36<1:39:02,  1.63it/s]
 83%|████████▎ | 47900/57600 [8:25:37<1:38:53,  1.63it/s]
                                                         
{'loss': 1.153, 'learning_rate': 2.520905923344948e-07, 'epoch': 528.7}

 83%|████████▎ | 47900/57600 [8:25:37<1:38:53,  1.63it/s]
 83%|████████▎ | 47901/57600 [8:25:37<1:37:20,  1.66it/s]
 83%|████████▎ | 47902/57600 [8:25:38<1:35:57,  1.68it/s]
 83%|████████▎ | 47903/57600 [8:25:38<1:41:21,  1.59it/s]
 83%|████████▎ | 47904/57600 [8:25:39<1:44:28,  1.55it/s]
 83%|████████▎ | 47905/57600 [8:25:40<1:45:32,  1.53it/s]
 83%|████████▎ | 47906/57600 [8:25:40<1:41:51,  1.59it/s]
 83%|████████▎ | 47907/57600 [8:25:41<1:44:21,  1.55it/s]
 83%|████████▎ | 47908/57600 [8:25:42<1:42:28,  1.58it/s]
 83%|████████▎ | 47909/57600 [8:25:42<1:45:20,  1.53it/s]
 83%|████████▎ | 47910/57600 [8:25:43<1:44:28,  1.55it/s]
 83%|████████▎ | 47911/57600 [8:25:44<1:41:05,  1.60it/s]
 83%|████████▎ | 47912/57600 [8:25:44<1:41:34,  1.59it/s]
 83%|████████▎ | 47913/57600 [8:25:45<1:40:48,  1.60it/s]
 83%|████████▎ | 47914/57600 [8:25:45<1:38:41,  1.64it/s]
 83%|████████▎ | 47915/57600 [8:25:46<1:36:36,  1.67it/s]
 83%|████████▎ | 47916/57600 [8:25:46<1:35:14,  1.69it/s]
 83%|████████▎ | 47917/57600 [8:25:47<1:36:07,  1.68it/s]
 83%|████████▎ | 47918/57600 [8:25:48<1:39:52,  1.62it/s]
 83%|████████▎ | 47919/57600 [8:25:48<1:43:39,  1.56it/s]
 83%|████████▎ | 47920/57600 [8:25:49<1:41:33,  1.59it/s]
                                                         
{'loss': 1.1238, 'learning_rate': 2.5177700348432055e-07, 'epoch': 528.92}

 83%|████████▎ | 47920/57600 [8:25:49<1:41:33,  1.59it/s]
 83%|████████▎ | 47921/57600 [8:25:50<1:40:26,  1.61it/s]
 83%|████████▎ | 47922/57600 [8:25:50<1:39:50,  1.62it/s]
 83%|████████▎ | 47923/57600 [8:25:51<1:37:40,  1.65it/s]
 83%|████████▎ | 47924/57600 [8:25:51<1:38:10,  1.64it/s]
 83%|████████▎ | 47925/57600 [8:25:52<1:38:22,  1.64it/s]
 83%|████████▎ | 47926/57600 [8:25:53<1:40:47,  1.60it/s]
 83%|████████▎ | 47927/57600 [8:25:53<1:42:12,  1.58it/s]
 83%|████████▎ | 47928/57600 [8:25:54<1:46:58,  1.51it/s]
 83%|████████▎ | 47929/57600 [8:25:55<1:45:17,  1.53it/s]
 83%|████████▎ | 47930/57600 [8:25:55<1:42:34,  1.57it/s]
 83%|████████▎ | 47931/57600 [8:25:56<1:42:38,  1.57it/s]
 83%|████████▎ | 47932/57600 [8:25:57<1:41:55,  1.58it/s]
 83%|████████▎ | 47933/57600 [8:25:57<1:42:32,  1.57it/s]
 83%|████████▎ | 47934/57600 [8:25:58<1:42:31,  1.57it/s]
 83%|████████▎ | 47935/57600 [8:25:59<1:43:18,  1.56it/s]
 83%|████████▎ | 47936/57600 [8:25:59<1:41:57,  1.58it/s]
 83%|████████▎ | 47937/57600 [8:26:00<1:40:47,  1.60it/s]
 83%|████████▎ | 47938/57600 [8:26:00<1:40:17,  1.61it/s]
 83%|████████▎ | 47939/57600 [8:26:01<1:41:59,  1.58it/s]
 83%|████████▎ | 47940/57600 [8:26:02<1:41:28,  1.59it/s]
                                                         
{'loss': 1.1209, 'learning_rate': 2.5146341463414636e-07, 'epoch': 529.14}

 83%|████████▎ | 47940/57600 [8:26:02<1:41:28,  1.59it/s]
 83%|████████▎ | 47941/57600 [8:26:02<1:42:21,  1.57it/s]
 83%|████████▎ | 47942/57600 [8:26:03<1:44:03,  1.55it/s]
 83%|████████▎ | 47943/57600 [8:26:04<1:43:13,  1.56it/s]
 83%|████████▎ | 47944/57600 [8:26:04<1:42:23,  1.57it/s]
 83%|████████▎ | 47945/57600 [8:26:05<1:42:23,  1.57it/s]
 83%|████████▎ | 47946/57600 [8:26:06<1:42:30,  1.57it/s]
 83%|████████▎ | 47947/57600 [8:26:06<1:42:25,  1.57it/s]
 83%|████████▎ | 47948/57600 [8:26:07<1:41:25,  1.59it/s]
 83%|████████▎ | 47949/57600 [8:26:07<1:38:25,  1.63it/s]
 83%|████████▎ | 47950/57600 [8:26:08<1:39:16,  1.62it/s]
 83%|████████▎ | 47951/57600 [8:26:09<1:45:45,  1.52it/s]
 83%|████████▎ | 47952/57600 [8:26:09<1:45:54,  1.52it/s]
 83%|████████▎ | 47953/57600 [8:26:10<1:43:26,  1.55it/s]
 83%|████████▎ | 47954/57600 [8:26:11<1:45:53,  1.52it/s]
 83%|████████▎ | 47955/57600 [8:26:11<1:44:44,  1.53it/s]
 83%|████████▎ | 47956/57600 [8:26:12<1:41:28,  1.58it/s]
 83%|████████▎ | 47957/57600 [8:26:13<1:41:25,  1.58it/s]
 83%|████████▎ | 47958/57600 [8:26:13<1:41:02,  1.59it/s]
 83%|████████▎ | 47959/57600 [8:26:14<1:37:59,  1.64it/s]
 83%|████████▎ | 47960/57600 [8:26:14<1:37:55,  1.64it/s]
                                                         
{'loss': 1.1242, 'learning_rate': 2.511498257839721e-07, 'epoch': 529.36}

 83%|████████▎ | 47960/57600 [8:26:14<1:37:55,  1.64it/s]
 83%|████████▎ | 47961/57600 [8:26:15<1:40:08,  1.60it/s]
 83%|████████▎ | 47962/57600 [8:26:16<1:40:30,  1.60it/s]
 83%|████████▎ | 47963/57600 [8:26:16<1:42:49,  1.56it/s]
 83%|████████▎ | 47964/57600 [8:26:17<1:41:09,  1.59it/s]
 83%|████████▎ | 47965/57600 [8:26:18<1:40:21,  1.60it/s]
 83%|████████▎ | 47966/57600 [8:26:18<1:41:06,  1.59it/s]
 83%|████████▎ | 47967/57600 [8:26:19<1:41:47,  1.58it/s]
 83%|████████▎ | 47968/57600 [8:26:19<1:40:29,  1.60it/s]
 83%|████████▎ | 47969/57600 [8:26:20<1:39:01,  1.62it/s]
 83%|████████▎ | 47970/57600 [8:26:21<1:41:14,  1.59it/s]
 83%|████████▎ | 47971/57600 [8:26:21<1:40:07,  1.60it/s]
 83%|████████▎ | 47972/57600 [8:26:22<1:39:43,  1.61it/s]
 83%|████████▎ | 47973/57600 [8:26:23<1:44:41,  1.53it/s]
 83%|████████▎ | 47974/57600 [8:26:23<1:41:41,  1.58it/s]
 83%|████████▎ | 47975/57600 [8:26:24<1:37:51,  1.64it/s]
 83%|████████▎ | 47976/57600 [8:26:24<1:43:42,  1.55it/s]
 83%|████████▎ | 47977/57600 [8:26:25<1:43:28,  1.55it/s]
 83%|████████▎ | 47978/57600 [8:26:26<1:42:15,  1.57it/s]
 83%|████████▎ | 47979/57600 [8:26:26<1:40:17,  1.60it/s]
 83%|████████▎ | 47980/57600 [8:26:27<1:40:41,  1.59it/s]
                                                         
{'loss': 1.1133, 'learning_rate': 2.508362369337979e-07, 'epoch': 529.58}

 83%|████████▎ | 47980/57600 [8:26:27<1:40:41,  1.59it/s]
 83%|████████▎ | 47981/57600 [8:26:28<1:40:42,  1.59it/s]
 83%|████████▎ | 47982/57600 [8:26:28<1:40:06,  1.60it/s]
 83%|████████▎ | 47983/57600 [8:26:29<1:38:54,  1.62it/s]
 83%|████████▎ | 47984/57600 [8:26:29<1:39:35,  1.61it/s]
 83%|████████▎ | 47985/57600 [8:26:30<1:36:40,  1.66it/s]
 83%|████████▎ | 47986/57600 [8:26:31<1:36:29,  1.66it/s]
 83%|████████▎ | 47987/57600 [8:26:31<1:37:05,  1.65it/s]
 83%|████████▎ | 47988/57600 [8:26:32<1:37:00,  1.65it/s]
 83%|████████▎ | 47989/57600 [8:26:33<1:40:18,  1.60it/s]
 83%|████████▎ | 47990/57600 [8:26:33<1:41:05,  1.58it/s]
 83%|████████▎ | 47991/57600 [8:26:34<1:40:15,  1.60it/s]
 83%|████████▎ | 47992/57600 [8:26:34<1:41:41,  1.57it/s]
 83%|████████▎ | 47993/57600 [8:26:35<1:40:45,  1.59it/s]
 83%|████████▎ | 47994/57600 [8:26:36<1:37:44,  1.64it/s]
 83%|████████▎ | 47995/57600 [8:26:36<1:39:53,  1.60it/s]
 83%|████████▎ | 47996/57600 [8:26:37<1:41:03,  1.58it/s]
 83%|████████▎ | 47997/57600 [8:26:38<1:40:36,  1.59it/s]
 83%|████████▎ | 47998/57600 [8:26:38<1:41:18,  1.58it/s]
 83%|████████▎ | 47999/57600 [8:26:39<1:39:26,  1.61it/s]
 83%|████████▎ | 48000/57600 [8:26:39<1:40:27,  1.59it/s]
                                                         
{'loss': 1.13, 'learning_rate': 2.505226480836236e-07, 'epoch': 529.8}

 83%|████████▎ | 48000/57600 [8:26:39<1:40:27,  1.59it/s]
 83%|████████▎ | 48001/57600 [8:26:40<1:41:42,  1.57it/s]
 83%|████████▎ | 48002/57600 [8:26:41<1:37:41,  1.64it/s]
 83%|████████▎ | 48003/57600 [8:26:41<1:39:34,  1.61it/s]
 83%|████████▎ | 48004/57600 [8:26:42<1:39:37,  1.61it/s]
 83%|████████▎ | 48005/57600 [8:26:43<1:39:41,  1.60it/s]
 83%|████████▎ | 48006/57600 [8:26:43<1:37:21,  1.64it/s]
 83%|████████▎ | 48007/57600 [8:26:44<1:36:17,  1.66it/s]
 83%|████████▎ | 48008/57600 [8:26:44<1:35:54,  1.67it/s]
 83%|████████▎ | 48009/57600 [8:26:45<1:38:17,  1.63it/s]
 83%|████████▎ | 48010/57600 [8:26:46<1:39:30,  1.61it/s]
 83%|████████▎ | 48011/57600 [8:26:46<1:38:15,  1.63it/s]
 83%|████████▎ | 48012/57600 [8:26:47<1:38:42,  1.62it/s]
 83%|████████▎ | 48013/57600 [8:26:47<1:38:27,  1.62it/s]
 83%|████████▎ | 48014/57600 [8:26:48<1:37:52,  1.63it/s]
 83%|████████▎ | 48015/57600 [8:26:49<1:36:37,  1.65it/s]
 83%|████████▎ | 48016/57600 [8:26:49<1:36:06,  1.66it/s]
 83%|████████▎ | 48017/57600 [8:26:50<1:34:19,  1.69it/s]
 83%|████████▎ | 48018/57600 [8:26:50<1:35:08,  1.68it/s]
 83%|████████▎ | 48019/57600 [8:26:51<1:41:52,  1.57it/s]
 83%|████████▎ | 48020/57600 [8:26:52<1:43:42,  1.54it/s]
                                                         
{'loss': 1.1395, 'learning_rate': 2.5020905923344947e-07, 'epoch': 530.02}

 83%|████████▎ | 48020/57600 [8:26:52<1:43:42,  1.54it/s]
 83%|████████▎ | 48021/57600 [8:26:52<1:43:53,  1.54it/s]
 83%|████████▎ | 48022/57600 [8:26:53<1:44:06,  1.53it/s]
 83%|████████▎ | 48023/57600 [8:26:54<1:40:56,  1.58it/s]
 83%|████████▎ | 48024/57600 [8:26:54<1:40:51,  1.58it/s]
 83%|████████▎ | 48025/57600 [8:26:55<1:39:40,  1.60it/s]
 83%|████████▎ | 48026/57600 [8:26:56<1:41:12,  1.58it/s]
 83%|████████▎ | 48027/57600 [8:26:56<1:45:49,  1.51it/s]
 83%|████████▎ | 48028/57600 [8:26:57<1:42:55,  1.55it/s]
 83%|████████▎ | 48029/57600 [8:26:58<1:46:17,  1.50it/s]
 83%|████████▎ | 48030/57600 [8:26:58<1:45:09,  1.52it/s]
 83%|████████▎ | 48031/57600 [8:26:59<1:42:21,  1.56it/s]
 83%|████████▎ | 48032/57600 [8:26:59<1:40:57,  1.58it/s]
 83%|████████▎ | 48033/57600 [8:27:00<1:38:00,  1.63it/s]
 83%|████████▎ | 48034/57600 [8:27:01<1:37:17,  1.64it/s]
 83%|████████▎ | 48035/57600 [8:27:01<1:39:51,  1.60it/s]
 83%|████████▎ | 48036/57600 [8:27:02<1:40:18,  1.59it/s]
 83%|████████▎ | 48037/57600 [8:27:03<1:37:54,  1.63it/s]
 83%|████████▎ | 48038/57600 [8:27:03<1:38:30,  1.62it/s]
 83%|████████▎ | 48039/57600 [8:27:04<1:36:33,  1.65it/s]
 83%|████████▎ | 48040/57600 [8:27:04<1:39:58,  1.59it/s]
                                                         
{'loss': 1.0835, 'learning_rate': 2.4989547038327533e-07, 'epoch': 530.24}

 83%|████████▎ | 48040/57600 [8:27:04<1:39:58,  1.59it/s]
 83%|████████▎ | 48041/57600 [8:27:05<1:40:16,  1.59it/s]
 83%|████████▎ | 48042/57600 [8:27:06<1:38:06,  1.62it/s]
 83%|████████▎ | 48043/57600 [8:27:06<1:37:01,  1.64it/s]
 83%|████████▎ | 48044/57600 [8:27:07<1:35:55,  1.66it/s]
 83%|████████▎ | 48045/57600 [8:27:07<1:35:02,  1.68it/s]
 83%|████████▎ | 48046/57600 [8:27:08<1:34:36,  1.68it/s]
 83%|████████▎ | 48047/57600 [8:27:09<1:34:23,  1.69it/s]
 83%|████████▎ | 48048/57600 [8:27:09<1:37:09,  1.64it/s]
 83%|████████▎ | 48049/57600 [8:27:10<1:40:56,  1.58it/s]
 83%|████████▎ | 48050/57600 [8:27:11<1:40:03,  1.59it/s]
 83%|████████▎ | 48051/57600 [8:27:11<1:40:14,  1.59it/s]
 83%|████████▎ | 48052/57600 [8:27:12<1:36:41,  1.65it/s]
 83%|████████▎ | 48053/57600 [8:27:12<1:35:03,  1.67it/s]
 83%|████████▎ | 48054/57600 [8:27:13<1:35:46,  1.66it/s]
 83%|████████▎ | 48055/57600 [8:27:13<1:35:37,  1.66it/s]
 83%|████████▎ | 48056/57600 [8:27:14<1:35:49,  1.66it/s]
 83%|████████▎ | 48057/57600 [8:27:15<1:35:10,  1.67it/s]
 83%|████████▎ | 48058/57600 [8:27:15<1:39:55,  1.59it/s]
 83%|████████▎ | 48059/57600 [8:27:16<1:40:55,  1.58it/s]
 83%|████████▎ | 48060/57600 [8:27:17<1:40:19,  1.58it/s]
                                                         
{'loss': 1.1185, 'learning_rate': 2.4958188153310103e-07, 'epoch': 530.46}

 83%|████████▎ | 48060/57600 [8:27:17<1:40:19,  1.58it/s]
 83%|████████▎ | 48061/57600 [8:27:17<1:40:10,  1.59it/s]
 83%|████████▎ | 48062/57600 [8:27:18<1:45:06,  1.51it/s]
 83%|████████▎ | 48063/57600 [8:27:19<1:44:16,  1.52it/s]
 83%|████████▎ | 48064/57600 [8:27:19<1:44:09,  1.53it/s]
 83%|████████▎ | 48065/57600 [8:27:20<1:44:33,  1.52it/s]
 83%|████████▎ | 48066/57600 [8:27:21<1:38:48,  1.61it/s]
 83%|████████▎ | 48067/57600 [8:27:21<1:36:25,  1.65it/s]
 83%|████████▎ | 48068/57600 [8:27:22<1:35:36,  1.66it/s]
 83%|████████▎ | 48069/57600 [8:27:22<1:37:10,  1.63it/s]
 83%|████████▎ | 48070/57600 [8:27:23<1:37:18,  1.63it/s]
 83%|████████▎ | 48071/57600 [8:27:24<1:38:13,  1.62it/s]
 83%|████████▎ | 48072/57600 [8:27:24<1:37:51,  1.62it/s]
 83%|████████▎ | 48073/57600 [8:27:25<1:39:31,  1.60it/s]
 83%|████████▎ | 48074/57600 [8:27:25<1:37:58,  1.62it/s]
 83%|████████▎ | 48075/57600 [8:27:26<1:37:59,  1.62it/s]
 83%|████████▎ | 48076/57600 [8:27:27<1:36:54,  1.64it/s]
 83%|████████▎ | 48077/57600 [8:27:27<1:37:21,  1.63it/s]
 83%|████████▎ | 48078/57600 [8:27:28<1:36:28,  1.65it/s]
 83%|████████▎ | 48079/57600 [8:27:29<1:39:01,  1.60it/s]
 83%|████████▎ | 48080/57600 [8:27:29<1:36:24,  1.65it/s]
                                                         
{'loss': 1.157, 'learning_rate': 2.4926829268292683e-07, 'epoch': 530.68}

 83%|████████▎ | 48080/57600 [8:27:29<1:36:24,  1.65it/s]
 83%|████████▎ | 48081/57600 [8:27:30<1:36:22,  1.65it/s]
 83%|████████▎ | 48082/57600 [8:27:30<1:36:39,  1.64it/s]
 83%|████████▎ | 48083/57600 [8:27:31<1:37:22,  1.63it/s]
 83%|████████▎ | 48084/57600 [8:27:32<1:43:53,  1.53it/s]
 83%|████████▎ | 48085/57600 [8:27:32<1:41:15,  1.57it/s]
 83%|████████▎ | 48086/57600 [8:27:33<1:41:54,  1.56it/s]
 83%|████████▎ | 48087/57600 [8:27:34<1:40:24,  1.58it/s]
 83%|████████▎ | 48088/57600 [8:27:34<1:40:06,  1.58it/s]
 83%|████████▎ | 48089/57600 [8:27:35<1:41:04,  1.57it/s]
 83%|████████▎ | 48090/57600 [8:27:35<1:38:55,  1.60it/s]
 83%|████████▎ | 48091/57600 [8:27:36<1:39:31,  1.59it/s]
 83%|████████▎ | 48092/57600 [8:27:37<1:41:58,  1.55it/s]
 83%|████████▎ | 48093/57600 [8:27:37<1:39:08,  1.60it/s]
 83%|████████▎ | 48094/57600 [8:27:38<1:38:21,  1.61it/s]
 83%|████████▎ | 48095/57600 [8:27:38<1:35:49,  1.65it/s]
 84%|████████▎ | 48096/57600 [8:27:39<1:37:45,  1.62it/s]
 84%|████████▎ | 48097/57600 [8:27:40<1:35:16,  1.66it/s]
 84%|████████▎ | 48098/57600 [8:27:40<1:36:30,  1.64it/s]
 84%|████████▎ | 48099/57600 [8:27:41<1:35:56,  1.65it/s]
 84%|████████▎ | 48100/57600 [8:27:42<1:35:23,  1.66it/s]
                                                         
{'loss': 1.1264, 'learning_rate': 2.489547038327526e-07, 'epoch': 530.91}

 84%|████████▎ | 48100/57600 [8:27:42<1:35:23,  1.66it/s]
 84%|████████▎ | 48101/57600 [8:27:42<1:41:52,  1.55it/s]
 84%|████████▎ | 48102/57600 [8:27:43<1:43:19,  1.53it/s]
 84%|████████▎ | 48103/57600 [8:27:44<1:43:01,  1.54it/s]
 84%|████████▎ | 48104/57600 [8:27:44<1:45:36,  1.50it/s]
 84%|████████▎ | 48105/57600 [8:27:45<1:43:06,  1.53it/s]
 84%|████████▎ | 48106/57600 [8:27:45<1:40:20,  1.58it/s]
 84%|████████▎ | 48107/57600 [8:27:46<1:38:42,  1.60it/s]
 84%|████████▎ | 48108/57600 [8:27:47<1:39:10,  1.60it/s]
 84%|████████▎ | 48109/57600 [8:27:47<1:44:27,  1.51it/s]
 84%|████████▎ | 48110/57600 [8:27:48<1:41:07,  1.56it/s]
 84%|████████▎ | 48111/57600 [8:27:49<1:42:46,  1.54it/s]
 84%|████████▎ | 48112/57600 [8:27:49<1:40:52,  1.57it/s]
 84%|████████▎ | 48113/57600 [8:27:50<1:43:32,  1.53it/s]
 84%|████████▎ | 48114/57600 [8:27:51<1:47:54,  1.47it/s]
 84%|████████▎ | 48115/57600 [8:27:51<1:45:05,  1.50it/s]
 84%|████████▎ | 48116/57600 [8:27:52<1:43:11,  1.53it/s]
 84%|████████▎ | 48117/57600 [8:27:53<1:44:37,  1.51it/s]
 84%|████████▎ | 48118/57600 [8:27:53<1:43:02,  1.53it/s]
 84%|████████▎ | 48119/57600 [8:27:54<1:39:09,  1.59it/s]
 84%|████████▎ | 48120/57600 [8:27:55<1:43:36,  1.52it/s]
                                                         
{'loss': 1.0726, 'learning_rate': 2.4864111498257844e-07, 'epoch': 531.13}

 84%|████████▎ | 48120/57600 [8:27:55<1:43:36,  1.52it/s]
 84%|████████▎ | 48121/57600 [8:27:55<1:41:17,  1.56it/s]
 84%|████████▎ | 48122/57600 [8:27:56<1:41:10,  1.56it/s]
 84%|████████▎ | 48123/57600 [8:27:56<1:39:05,  1.59it/s]
 84%|████████▎ | 48124/57600 [8:27:57<1:39:15,  1.59it/s]
 84%|████████▎ | 48125/57600 [8:27:58<1:40:24,  1.57it/s]
 84%|████████▎ | 48126/57600 [8:27:58<1:40:00,  1.58it/s]
 84%|████████▎ | 48127/57600 [8:27:59<1:38:37,  1.60it/s]
 84%|████████▎ | 48128/57600 [8:28:00<1:37:40,  1.62it/s]
 84%|████████▎ | 48129/57600 [8:28:00<1:37:22,  1.62it/s]
 84%|████████▎ | 48130/57600 [8:28:01<1:35:16,  1.66it/s]
 84%|████████▎ | 48131/57600 [8:28:01<1:35:14,  1.66it/s]
 84%|████████▎ | 48132/57600 [8:28:02<1:35:11,  1.66it/s]
 84%|████████▎ | 48133/57600 [8:28:03<1:37:55,  1.61it/s]
 84%|████████▎ | 48134/57600 [8:28:03<1:46:11,  1.49it/s]
 84%|████████▎ | 48135/57600 [8:28:04<1:42:46,  1.53it/s]
 84%|████████▎ | 48136/57600 [8:28:05<1:41:18,  1.56it/s]
 84%|████████▎ | 48137/57600 [8:28:05<1:39:34,  1.58it/s]
 84%|████████▎ | 48138/57600 [8:28:06<1:38:43,  1.60it/s]
 84%|████████▎ | 48139/57600 [8:28:06<1:35:50,  1.65it/s]
 84%|████████▎ | 48140/57600 [8:28:07<1:33:32,  1.69it/s]
                                                         
{'loss': 1.1548, 'learning_rate': 2.4832752613240414e-07, 'epoch': 531.35}

 84%|████████▎ | 48140/57600 [8:28:07<1:33:32,  1.69it/s]
 84%|████████▎ | 48141/57600 [8:28:08<1:36:13,  1.64it/s]
 84%|████████▎ | 48142/57600 [8:28:08<1:36:13,  1.64it/s]
 84%|████████▎ | 48143/57600 [8:28:09<1:37:48,  1.61it/s]
 84%|████████▎ | 48144/57600 [8:28:10<1:38:14,  1.60it/s]
 84%|████████▎ | 48145/57600 [8:28:10<1:35:52,  1.64it/s]
 84%|████████▎ | 48146/57600 [8:28:11<1:36:27,  1.63it/s]
 84%|████████▎ | 48147/57600 [8:28:11<1:37:03,  1.62it/s]
 84%|████████▎ | 48148/57600 [8:28:12<1:37:45,  1.61it/s]
 84%|████████▎ | 48149/57600 [8:28:13<1:37:51,  1.61it/s]
 84%|████████▎ | 48150/57600 [8:28:13<1:38:38,  1.60it/s]
 84%|████████▎ | 48151/57600 [8:28:14<1:38:37,  1.60it/s]
 84%|████████▎ | 48152/57600 [8:28:15<1:40:38,  1.56it/s]
 84%|████████▎ | 48153/57600 [8:28:15<1:42:06,  1.54it/s]
 84%|████████▎ | 48154/57600 [8:28:16<1:42:05,  1.54it/s]
 84%|████████▎ | 48155/57600 [8:28:16<1:40:02,  1.57it/s]
 84%|████████▎ | 48156/57600 [8:28:17<1:38:16,  1.60it/s]
 84%|████████▎ | 48157/57600 [8:28:18<1:38:09,  1.60it/s]
 84%|████████▎ | 48158/57600 [8:28:18<1:37:26,  1.62it/s]
 84%|████████▎ | 48159/57600 [8:28:19<1:35:36,  1.65it/s]
 84%|████████▎ | 48160/57600 [8:28:19<1:35:40,  1.64it/s]
                                                         
{'loss': 1.1144, 'learning_rate': 2.4801393728222995e-07, 'epoch': 531.57}

 84%|████████▎ | 48160/57600 [8:28:19<1:35:40,  1.64it/s]
 84%|████████▎ | 48161/57600 [8:28:20<1:37:03,  1.62it/s]
 84%|████████▎ | 48162/57600 [8:28:21<1:37:19,  1.62it/s]
 84%|████████▎ | 48163/57600 [8:28:21<1:41:50,  1.54it/s]
 84%|████████▎ | 48164/57600 [8:28:22<1:37:59,  1.60it/s]
 84%|████████▎ | 48165/57600 [8:28:23<1:34:35,  1.66it/s]
 84%|████████▎ | 48166/57600 [8:28:23<1:37:46,  1.61it/s]
 84%|████████▎ | 48167/57600 [8:28:24<1:35:48,  1.64it/s]
 84%|████████▎ | 48168/57600 [8:28:24<1:37:51,  1.61it/s]
 84%|████████▎ | 48169/57600 [8:28:25<1:41:06,  1.55it/s]
 84%|████████▎ | 48170/57600 [8:28:26<1:43:14,  1.52it/s]
 84%|████████▎ | 48171/57600 [8:28:27<1:44:12,  1.51it/s]
 84%|████████▎ | 48172/57600 [8:28:27<1:40:47,  1.56it/s]
 84%|████████▎ | 48173/57600 [8:28:28<1:38:18,  1.60it/s]
 84%|████████▎ | 48174/57600 [8:28:28<1:38:41,  1.59it/s]
 84%|████████▎ | 48175/57600 [8:28:29<1:38:15,  1.60it/s]
 84%|████████▎ | 48176/57600 [8:28:30<1:43:08,  1.52it/s]
 84%|████████▎ | 48177/57600 [8:28:30<1:39:03,  1.59it/s]
 84%|████████▎ | 48178/57600 [8:28:31<1:36:48,  1.62it/s]
 84%|████████▎ | 48179/57600 [8:28:32<1:38:58,  1.59it/s]
 84%|████████▎ | 48180/57600 [8:28:32<1:40:30,  1.56it/s]
                                                         
{'loss': 1.1134, 'learning_rate': 2.477003484320558e-07, 'epoch': 531.79}

 84%|████████▎ | 48180/57600 [8:28:32<1:40:30,  1.56it/s]
 84%|████████▎ | 48181/57600 [8:28:33<1:39:32,  1.58it/s]
 84%|████████▎ | 48182/57600 [8:28:33<1:39:47,  1.57it/s]
 84%|████████▎ | 48183/57600 [8:28:34<1:38:16,  1.60it/s]
 84%|████████▎ | 48184/57600 [8:28:35<1:40:18,  1.56it/s]
 84%|████████▎ | 48185/57600 [8:28:35<1:41:24,  1.55it/s]
 84%|████████▎ | 48186/57600 [8:28:36<1:40:01,  1.57it/s]
 84%|████████▎ | 48187/57600 [8:28:37<1:38:44,  1.59it/s]
 84%|████████▎ | 48188/57600 [8:28:37<1:40:29,  1.56it/s]
 84%|████████▎ | 48189/57600 [8:28:38<1:43:33,  1.51it/s]
 84%|████████▎ | 48190/57600 [8:28:39<1:41:24,  1.55it/s]
 84%|████████▎ | 48191/57600 [8:28:39<1:43:47,  1.51it/s]
 84%|████████▎ | 48192/57600 [8:28:40<1:40:12,  1.56it/s]
 84%|████████▎ | 48193/57600 [8:28:41<1:40:21,  1.56it/s]
 84%|████████▎ | 48194/57600 [8:28:41<1:39:47,  1.57it/s]
 84%|████████▎ | 48195/57600 [8:28:42<1:40:26,  1.56it/s]
 84%|████████▎ | 48196/57600 [8:28:42<1:40:25,  1.56it/s]
 84%|████████▎ | 48197/57600 [8:28:43<1:37:44,  1.60it/s]
 84%|████████▎ | 48198/57600 [8:28:44<1:38:04,  1.60it/s]
 84%|████████▎ | 48199/57600 [8:28:44<1:37:39,  1.60it/s]
 84%|████████▎ | 48200/57600 [8:28:45<1:42:59,  1.52it/s]
                                                         
{'loss': 1.1017, 'learning_rate': 2.473867595818815e-07, 'epoch': 532.01}

 84%|████████▎ | 48200/57600 [8:28:45<1:42:59,  1.52it/s]
 84%|████████▎ | 48201/57600 [8:28:46<1:39:46,  1.57it/s]
 84%|████████▎ | 48202/57600 [8:28:46<1:40:19,  1.56it/s]
 84%|████████▎ | 48203/57600 [8:28:47<1:37:55,  1.60it/s]
 84%|████████▎ | 48204/57600 [8:28:48<1:43:54,  1.51it/s]
 84%|████████▎ | 48205/57600 [8:28:48<1:44:41,  1.50it/s]
 84%|████████▎ | 48206/57600 [8:28:49<1:43:37,  1.51it/s]
 84%|████████▎ | 48207/57600 [8:28:50<1:39:53,  1.57it/s]
 84%|████████▎ | 48208/57600 [8:28:50<1:36:20,  1.62it/s]
 84%|████████▎ | 48209/57600 [8:28:51<1:36:01,  1.63it/s]
 84%|████████▎ | 48210/57600 [8:28:51<1:35:31,  1.64it/s]
 84%|████████▎ | 48211/57600 [8:28:52<1:37:40,  1.60it/s]
 84%|████████▎ | 48212/57600 [8:28:53<1:39:17,  1.58it/s]
 84%|████████▎ | 48213/57600 [8:28:53<1:37:30,  1.60it/s]
 84%|████████▎ | 48214/57600 [8:28:54<1:38:55,  1.58it/s]
 84%|████████▎ | 48215/57600 [8:28:54<1:39:34,  1.57it/s]
 84%|████████▎ | 48216/57600 [8:28:55<1:37:17,  1.61it/s]
 84%|████████▎ | 48217/57600 [8:28:56<1:38:46,  1.58it/s]
 84%|████████▎ | 48218/57600 [8:28:56<1:43:13,  1.51it/s]
 84%|████████▎ | 48219/57600 [8:28:57<1:40:11,  1.56it/s]
 84%|████████▎ | 48220/57600 [8:28:58<1:40:21,  1.56it/s]
                                                         
{'loss': 1.1188, 'learning_rate': 2.470731707317073e-07, 'epoch': 532.23}

 84%|████████▎ | 48220/57600 [8:28:58<1:40:21,  1.56it/s]
 84%|████████▎ | 48221/57600 [8:28:58<1:40:11,  1.56it/s]
 84%|████████▎ | 48222/57600 [8:28:59<1:38:36,  1.58it/s]
 84%|████████▎ | 48223/57600 [8:29:00<1:40:24,  1.56it/s]
 84%|████████▎ | 48224/57600 [8:29:00<1:42:50,  1.52it/s]
 84%|████████▎ | 48225/57600 [8:29:01<1:39:17,  1.57it/s]
 84%|████████▎ | 48226/57600 [8:29:02<1:38:13,  1.59it/s]
 84%|████████▎ | 48227/57600 [8:29:02<1:41:27,  1.54it/s]
 84%|████████▎ | 48228/57600 [8:29:03<1:39:31,  1.57it/s]
 84%|████████▎ | 48229/57600 [8:29:03<1:37:48,  1.60it/s]
 84%|████████▎ | 48230/57600 [8:29:04<1:37:11,  1.61it/s]
 84%|████████▎ | 48231/57600 [8:29:05<1:39:29,  1.57it/s]
 84%|████████▎ | 48232/57600 [8:29:05<1:41:34,  1.54it/s]
 84%|████████▎ | 48233/57600 [8:29:06<1:39:10,  1.57it/s]
 84%|████████▎ | 48234/57600 [8:29:07<1:36:58,  1.61it/s]
 84%|████████▎ | 48235/57600 [8:29:07<1:34:57,  1.64it/s]
 84%|████████▎ | 48236/57600 [8:29:08<1:34:56,  1.64it/s]
 84%|████████▎ | 48237/57600 [8:29:08<1:36:43,  1.61it/s]
 84%|████████▎ | 48238/57600 [8:29:09<1:37:30,  1.60it/s]
 84%|████████▎ | 48239/57600 [8:29:10<1:37:22,  1.60it/s]
 84%|████████▍ | 48240/57600 [8:29:10<1:39:03,  1.57it/s]
                                                         
{'loss': 1.1032, 'learning_rate': 2.4675958188153306e-07, 'epoch': 532.45}

 84%|████████▍ | 48240/57600 [8:29:10<1:39:03,  1.57it/s]
 84%|████████▍ | 48241/57600 [8:29:11<1:37:39,  1.60it/s]
 84%|████████▍ | 48242/57600 [8:29:12<1:35:55,  1.63it/s]
 84%|████████▍ | 48243/57600 [8:29:12<1:37:07,  1.61it/s]
 84%|████████▍ | 48244/57600 [8:29:13<1:37:34,  1.60it/s]
 84%|████████▍ | 48245/57600 [8:29:13<1:36:18,  1.62it/s]
 84%|████████▍ | 48246/57600 [8:29:14<1:34:22,  1.65it/s]
 84%|████████▍ | 48247/57600 [8:29:15<1:32:03,  1.69it/s]
 84%|████████▍ | 48248/57600 [8:29:15<1:31:15,  1.71it/s]
 84%|████████▍ | 48249/57600 [8:29:16<1:34:59,  1.64it/s]
 84%|████████▍ | 48250/57600 [8:29:16<1:35:04,  1.64it/s]
 84%|████████▍ | 48251/57600 [8:29:17<1:40:50,  1.55it/s]
 84%|████████▍ | 48252/57600 [8:29:18<1:39:42,  1.56it/s]
 84%|████████▍ | 48253/57600 [8:29:18<1:40:13,  1.55it/s]
 84%|████████▍ | 48254/57600 [8:29:19<1:40:22,  1.55it/s]
 84%|████████▍ | 48255/57600 [8:29:20<1:38:02,  1.59it/s]
 84%|████████▍ | 48256/57600 [8:29:20<1:37:35,  1.60it/s]
 84%|████████▍ | 48257/57600 [8:29:21<1:40:36,  1.55it/s]
 84%|████████▍ | 48258/57600 [8:29:22<1:38:21,  1.58it/s]
 84%|████████▍ | 48259/57600 [8:29:22<1:37:42,  1.59it/s]
 84%|████████▍ | 48260/57600 [8:29:23<1:34:41,  1.64it/s]
                                                         
{'loss': 1.1564, 'learning_rate': 2.464459930313589e-07, 'epoch': 532.67}

 84%|████████▍ | 48260/57600 [8:29:23<1:34:41,  1.64it/s]
 84%|████████▍ | 48261/57600 [8:29:23<1:35:26,  1.63it/s]
 84%|████████▍ | 48262/57600 [8:29:24<1:36:12,  1.62it/s]
 84%|████████▍ | 48263/57600 [8:29:25<1:34:13,  1.65it/s]
 84%|████████▍ | 48264/57600 [8:29:25<1:34:57,  1.64it/s]
 84%|████████▍ | 48265/57600 [8:29:26<1:33:19,  1.67it/s]
 84%|████████▍ | 48266/57600 [8:29:26<1:35:03,  1.64it/s]
 84%|████████▍ | 48267/57600 [8:29:27<1:38:28,  1.58it/s]
 84%|████████▍ | 48268/57600 [8:29:28<1:35:56,  1.62it/s]
 84%|████████▍ | 48269/57600 [8:29:28<1:34:48,  1.64it/s]
 84%|████████▍ | 48270/57600 [8:29:29<1:33:59,  1.65it/s]
 84%|████████▍ | 48271/57600 [8:29:29<1:32:27,  1.68it/s]
 84%|████████▍ | 48272/57600 [8:29:30<1:31:48,  1.69it/s]
 84%|████████▍ | 48273/57600 [8:29:31<1:36:57,  1.60it/s]
 84%|████████▍ | 48274/57600 [8:29:31<1:36:00,  1.62it/s]
 84%|████████▍ | 48275/57600 [8:29:32<1:38:29,  1.58it/s]
 84%|████████▍ | 48276/57600 [8:29:33<1:39:38,  1.56it/s]
 84%|████████▍ | 48277/57600 [8:29:33<1:40:51,  1.54it/s]
 84%|████████▍ | 48278/57600 [8:29:34<1:40:50,  1.54it/s]
 84%|████████▍ | 48279/57600 [8:29:35<1:43:15,  1.50it/s]
 84%|████████▍ | 48280/57600 [8:29:35<1:41:13,  1.53it/s]
                                                         
{'loss': 1.1129, 'learning_rate': 2.461324041811846e-07, 'epoch': 532.89}

 84%|████████▍ | 48280/57600 [8:29:35<1:41:13,  1.53it/s]
 84%|████████▍ | 48281/57600 [8:29:36<1:42:11,  1.52it/s]
 84%|████████▍ | 48282/57600 [8:29:37<1:43:26,  1.50it/s]
 84%|████████▍ | 48283/57600 [8:29:37<1:41:09,  1.54it/s]
 84%|████████▍ | 48284/57600 [8:29:38<1:40:33,  1.54it/s]
 84%|████████▍ | 48285/57600 [8:29:38<1:39:44,  1.56it/s]
 84%|████████▍ | 48286/57600 [8:29:39<1:38:45,  1.57it/s]
 84%|████████▍ | 48287/57600 [8:29:40<1:39:06,  1.57it/s]
 84%|████████▍ | 48288/57600 [8:29:40<1:38:04,  1.58it/s]
 84%|████████▍ | 48289/57600 [8:29:41<1:38:04,  1.58it/s]
 84%|████████▍ | 48290/57600 [8:29:42<1:39:02,  1.57it/s]
 84%|████████▍ | 48291/57600 [8:29:42<1:40:20,  1.55it/s]
 84%|████████▍ | 48292/57600 [8:29:43<1:39:35,  1.56it/s]
 84%|████████▍ | 48293/57600 [8:29:44<1:38:02,  1.58it/s]
 84%|████████▍ | 48294/57600 [8:29:44<1:40:18,  1.55it/s]
 84%|████████▍ | 48295/57600 [8:29:45<1:40:34,  1.54it/s]
 84%|████████▍ | 48296/57600 [8:29:45<1:37:37,  1.59it/s]
 84%|████████▍ | 48297/57600 [8:29:46<1:41:17,  1.53it/s]
 84%|████████▍ | 48298/57600 [8:29:47<1:39:10,  1.56it/s]
 84%|████████▍ | 48299/57600 [8:29:47<1:40:42,  1.54it/s]
 84%|████████▍ | 48300/57600 [8:29:48<1:38:44,  1.57it/s]
                                                         
{'loss': 1.0803, 'learning_rate': 2.458188153310104e-07, 'epoch': 533.11}

 84%|████████▍ | 48300/57600 [8:29:48<1:38:44,  1.57it/s]
 84%|████████▍ | 48301/57600 [8:29:49<1:36:17,  1.61it/s]
 84%|████████▍ | 48302/57600 [8:29:49<1:36:02,  1.61it/s]
 84%|████████▍ | 48303/57600 [8:29:50<1:36:15,  1.61it/s]
 84%|████████▍ | 48304/57600 [8:29:51<1:39:18,  1.56it/s]
 84%|████████▍ | 48305/57600 [8:29:51<1:39:47,  1.55it/s]
 84%|████████▍ | 48306/57600 [8:29:52<1:38:26,  1.57it/s]
 84%|████████▍ | 48307/57600 [8:29:52<1:37:12,  1.59it/s]
 84%|████████▍ | 48308/57600 [8:29:53<1:41:31,  1.53it/s]
 84%|████████▍ | 48309/57600 [8:29:54<1:40:05,  1.55it/s]
 84%|████████▍ | 48310/57600 [8:29:54<1:38:04,  1.58it/s]
 84%|████████▍ | 48311/57600 [8:29:55<1:37:29,  1.59it/s]
 84%|████████▍ | 48312/57600 [8:29:56<1:36:45,  1.60it/s]
 84%|████████▍ | 48313/57600 [8:29:56<1:37:15,  1.59it/s]
 84%|████████▍ | 48314/57600 [8:29:57<1:37:41,  1.58it/s]
 84%|████████▍ | 48315/57600 [8:29:58<1:36:38,  1.60it/s]
 84%|████████▍ | 48316/57600 [8:29:58<1:36:27,  1.60it/s]
 84%|████████▍ | 48317/57600 [8:29:59<1:40:55,  1.53it/s]
 84%|████████▍ | 48318/57600 [8:30:00<1:40:13,  1.54it/s]
 84%|████████▍ | 48319/57600 [8:30:00<1:40:18,  1.54it/s]
 84%|████████▍ | 48320/57600 [8:30:01<1:38:55,  1.56it/s]
                                                         
{'loss': 1.1, 'learning_rate': 2.455052264808363e-07, 'epoch': 533.33}

 84%|████████▍ | 48320/57600 [8:30:01<1:38:55,  1.56it/s]
 84%|████████▍ | 48321/57600 [8:30:01<1:38:26,  1.57it/s]
 84%|████████▍ | 48322/57600 [8:30:02<1:38:21,  1.57it/s]
 84%|████████▍ | 48323/57600 [8:30:03<1:34:52,  1.63it/s]
 84%|████████▍ | 48324/57600 [8:30:03<1:34:09,  1.64it/s]
 84%|████████▍ | 48325/57600 [8:30:04<1:38:43,  1.57it/s]
 84%|████████▍ | 48326/57600 [8:30:05<1:38:13,  1.57it/s]
 84%|████████▍ | 48327/57600 [8:30:05<1:36:00,  1.61it/s]
 84%|████████▍ | 48328/57600 [8:30:06<1:35:30,  1.62it/s]
 84%|████████▍ | 48329/57600 [8:30:06<1:34:55,  1.63it/s]
 84%|████████▍ | 48330/57600 [8:30:07<1:34:57,  1.63it/s]
 84%|████████▍ | 48331/57600 [8:30:08<1:34:02,  1.64it/s]
 84%|████████▍ | 48332/57600 [8:30:08<1:33:08,  1.66it/s]
 84%|████████▍ | 48333/57600 [8:30:09<1:33:53,  1.64it/s]
 84%|████████▍ | 48334/57600 [8:30:09<1:36:15,  1.60it/s]
 84%|████████▍ | 48335/57600 [8:30:10<1:33:52,  1.64it/s]
 84%|████████▍ | 48336/57600 [8:30:11<1:33:35,  1.65it/s]
 84%|████████▍ | 48337/57600 [8:30:11<1:39:32,  1.55it/s]
 84%|████████▍ | 48338/57600 [8:30:12<1:39:45,  1.55it/s]
 84%|████████▍ | 48339/57600 [8:30:13<1:39:09,  1.56it/s]
 84%|████████▍ | 48340/57600 [8:30:13<1:36:38,  1.60it/s]
                                                         
{'loss': 1.1149, 'learning_rate': 2.4519163763066203e-07, 'epoch': 533.55}

 84%|████████▍ | 48340/57600 [8:30:13<1:36:38,  1.60it/s]
 84%|████████▍ | 48341/57600 [8:30:14<1:37:39,  1.58it/s]
 84%|████████▍ | 48342/57600 [8:30:14<1:36:04,  1.61it/s]
 84%|████████▍ | 48343/57600 [8:30:15<1:38:10,  1.57it/s]
 84%|████████▍ | 48344/57600 [8:30:16<1:36:09,  1.60it/s]
 84%|████████▍ | 48345/57600 [8:30:16<1:35:36,  1.61it/s]
 84%|████████▍ | 48346/57600 [8:30:17<1:40:41,  1.53it/s]
 84%|████████▍ | 48347/57600 [8:30:18<1:42:50,  1.50it/s]
 84%|████████▍ | 48348/57600 [8:30:18<1:40:14,  1.54it/s]
 84%|████████▍ | 48349/57600 [8:30:19<1:39:40,  1.55it/s]
 84%|████████▍ | 48350/57600 [8:30:20<1:37:43,  1.58it/s]
 84%|████████▍ | 48351/57600 [8:30:20<1:36:23,  1.60it/s]
 84%|████████▍ | 48352/57600 [8:30:21<1:35:56,  1.61it/s]
 84%|████████▍ | 48353/57600 [8:30:21<1:35:40,  1.61it/s]
 84%|████████▍ | 48354/57600 [8:30:22<1:37:53,  1.57it/s]
 84%|████████▍ | 48355/57600 [8:30:23<1:38:21,  1.57it/s]
 84%|████████▍ | 48356/57600 [8:30:23<1:37:05,  1.59it/s]
 84%|████████▍ | 48357/57600 [8:30:24<1:38:58,  1.56it/s]
 84%|████████▍ | 48358/57600 [8:30:25<1:35:18,  1.62it/s]
 84%|████████▍ | 48359/57600 [8:30:25<1:33:07,  1.65it/s]
 84%|████████▍ | 48360/57600 [8:30:26<1:33:05,  1.65it/s]
                                                         
{'loss': 1.1505, 'learning_rate': 2.4487804878048783e-07, 'epoch': 533.77}

 84%|████████▍ | 48360/57600 [8:30:26<1:33:05,  1.65it/s]
 84%|████████▍ | 48361/57600 [8:30:26<1:33:59,  1.64it/s]
 84%|████████▍ | 48362/57600 [8:30:27<1:33:13,  1.65it/s]
 84%|████████▍ | 48363/57600 [8:30:28<1:32:31,  1.66it/s]
 84%|████████▍ | 48364/57600 [8:30:28<1:37:13,  1.58it/s]
 84%|████████▍ | 48365/57600 [8:30:29<1:34:27,  1.63it/s]
 84%|████████▍ | 48366/57600 [8:30:29<1:33:25,  1.65it/s]
 84%|████████▍ | 48367/57600 [8:30:30<1:35:00,  1.62it/s]
 84%|████████▍ | 48368/57600 [8:30:31<1:35:45,  1.61it/s]
 84%|████████▍ | 48369/57600 [8:30:31<1:38:40,  1.56it/s]
 84%|████████▍ | 48370/57600 [8:30:32<1:37:49,  1.57it/s]
 84%|████████▍ | 48371/57600 [8:30:33<1:38:43,  1.56it/s]
 84%|████████▍ | 48372/57600 [8:30:33<1:36:56,  1.59it/s]
 84%|████████▍ | 48373/57600 [8:30:34<1:38:24,  1.56it/s]
 84%|████████▍ | 48374/57600 [8:30:35<1:36:47,  1.59it/s]
 84%|████████▍ | 48375/57600 [8:30:35<1:35:11,  1.62it/s]
 84%|████████▍ | 48376/57600 [8:30:36<1:38:00,  1.57it/s]
 84%|████████▍ | 48377/57600 [8:30:37<1:38:55,  1.55it/s]
 84%|████████▍ | 48378/57600 [8:30:37<1:40:04,  1.54it/s]
 84%|████████▍ | 48379/57600 [8:30:38<1:39:16,  1.55it/s]
 84%|████████▍ | 48380/57600 [8:30:38<1:36:22,  1.59it/s]
                                                         
{'loss': 1.1273, 'learning_rate': 2.4456445993031353e-07, 'epoch': 534.0}

 84%|████████▍ | 48380/57600 [8:30:38<1:36:22,  1.59it/s]
 84%|████████▍ | 48381/57600 [8:30:39<1:39:18,  1.55it/s]
 84%|████████▍ | 48382/57600 [8:30:40<1:37:14,  1.58it/s]
 84%|████████▍ | 48383/57600 [8:30:40<1:35:15,  1.61it/s]
 84%|████████▍ | 48384/57600 [8:30:41<1:35:38,  1.61it/s]
 84%|████████▍ | 48385/57600 [8:30:41<1:32:43,  1.66it/s]
 84%|████████▍ | 48386/57600 [8:30:42<1:31:09,  1.68it/s]
 84%|████████▍ | 48387/57600 [8:30:43<1:36:17,  1.59it/s]
 84%|████████▍ | 48388/57600 [8:30:43<1:37:05,  1.58it/s]
 84%|████████▍ | 48389/57600 [8:30:44<1:38:43,  1.56it/s]
 84%|████████▍ | 48390/57600 [8:30:45<1:35:47,  1.60it/s]
 84%|████████▍ | 48391/57600 [8:30:45<1:33:33,  1.64it/s]
 84%|████████▍ | 48392/57600 [8:30:46<1:34:17,  1.63it/s]
 84%|████████▍ | 48393/57600 [8:30:46<1:33:28,  1.64it/s]
 84%|████████▍ | 48394/57600 [8:30:47<1:31:42,  1.67it/s]
 84%|████████▍ | 48395/57600 [8:30:48<1:32:02,  1.67it/s]
 84%|████████▍ | 48396/57600 [8:30:48<1:32:02,  1.67it/s]
 84%|████████▍ | 48397/57600 [8:30:49<1:37:59,  1.57it/s]
 84%|████████▍ | 48398/57600 [8:30:50<1:38:31,  1.56it/s]
 84%|████████▍ | 48399/57600 [8:30:50<1:38:20,  1.56it/s]
 84%|████████▍ | 48400/57600 [8:30:51<1:39:16,  1.54it/s]
                                                         
{'loss': 1.1458, 'learning_rate': 2.442508710801394e-07, 'epoch': 534.22}

 84%|████████▍ | 48400/57600 [8:30:51<1:39:16,  1.54it/s]
 84%|████████▍ | 48401/57600 [8:30:51<1:37:03,  1.58it/s]
 84%|████████▍ | 48402/57600 [8:30:52<1:38:35,  1.55it/s]
 84%|████████▍ | 48403/57600 [8:30:53<1:37:39,  1.57it/s]
 84%|████████▍ | 48404/57600 [8:30:53<1:36:57,  1.58it/s]
 84%|████████▍ | 48405/57600 [8:30:54<1:36:13,  1.59it/s]
 84%|████████▍ | 48406/57600 [8:30:55<1:36:11,  1.59it/s]
 84%|████████▍ | 48407/57600 [8:30:55<1:35:33,  1.60it/s]
 84%|████████▍ | 48408/57600 [8:30:56<1:36:10,  1.59it/s]
 84%|████████▍ | 48409/57600 [8:30:56<1:34:10,  1.63it/s]
 84%|████████▍ | 48410/57600 [8:30:57<1:36:28,  1.59it/s]
 84%|████████▍ | 48411/57600 [8:30:58<1:36:39,  1.58it/s]
 84%|████████▍ | 48412/57600 [8:30:58<1:34:54,  1.61it/s]
 84%|████████▍ | 48413/57600 [8:30:59<1:36:55,  1.58it/s]
 84%|████████▍ | 48414/57600 [8:31:00<1:38:26,  1.56it/s]
 84%|████████▍ | 48415/57600 [8:31:00<1:38:12,  1.56it/s]
 84%|████████▍ | 48416/57600 [8:31:01<1:38:01,  1.56it/s]
 84%|████████▍ | 48417/57600 [8:31:02<1:37:29,  1.57it/s]
 84%|████████▍ | 48418/57600 [8:31:02<1:36:29,  1.59it/s]
 84%|████████▍ | 48419/57600 [8:31:03<1:35:52,  1.60it/s]
 84%|████████▍ | 48420/57600 [8:31:03<1:34:59,  1.61it/s]
                                                         
{'loss': 1.0934, 'learning_rate': 2.439372822299651e-07, 'epoch': 534.44}

 84%|████████▍ | 48420/57600 [8:31:03<1:34:59,  1.61it/s]
 84%|████████▍ | 48421/57600 [8:31:04<1:36:05,  1.59it/s]
 84%|████████▍ | 48422/57600 [8:31:05<1:37:27,  1.57it/s]
 84%|████████▍ | 48423/57600 [8:31:05<1:40:15,  1.53it/s]
 84%|████████▍ | 48424/57600 [8:31:06<1:40:05,  1.53it/s]
 84%|████████▍ | 48425/57600 [8:31:07<1:38:30,  1.55it/s]
 84%|████████▍ | 48426/57600 [8:31:07<1:40:57,  1.51it/s]
 84%|████████▍ | 48427/57600 [8:31:08<1:42:25,  1.49it/s]
 84%|████████▍ | 48428/57600 [8:31:09<1:38:29,  1.55it/s]
 84%|████████▍ | 48429/57600 [8:31:09<1:34:51,  1.61it/s]
 84%|████████▍ | 48430/57600 [8:31:10<1:34:25,  1.62it/s]
 84%|████████▍ | 48431/57600 [8:31:10<1:32:35,  1.65it/s]
 84%|████████▍ | 48432/57600 [8:31:11<1:33:34,  1.63it/s]
 84%|████████▍ | 48433/57600 [8:31:12<1:33:37,  1.63it/s]
 84%|████████▍ | 48434/57600 [8:31:12<1:33:50,  1.63it/s]
 84%|████████▍ | 48435/57600 [8:31:13<1:33:35,  1.63it/s]
 84%|████████▍ | 48436/57600 [8:31:14<1:35:23,  1.60it/s]
 84%|████████▍ | 48437/57600 [8:31:14<1:36:08,  1.59it/s]
 84%|████████▍ | 48438/57600 [8:31:15<1:34:59,  1.61it/s]
 84%|████████▍ | 48439/57600 [8:31:15<1:34:35,  1.61it/s]
 84%|████████▍ | 48440/57600 [8:31:16<1:35:25,  1.60it/s]
                                                         
{'loss': 1.0883, 'learning_rate': 2.436236933797909e-07, 'epoch': 534.66}

 84%|████████▍ | 48440/57600 [8:31:16<1:35:25,  1.60it/s]
 84%|████████▍ | 48441/57600 [8:31:17<1:39:01,  1.54it/s]
 84%|████████▍ | 48442/57600 [8:31:17<1:37:54,  1.56it/s]
 84%|████████▍ | 48443/57600 [8:31:18<1:37:50,  1.56it/s]
 84%|████████▍ | 48444/57600 [8:31:19<1:37:10,  1.57it/s]
 84%|████████▍ | 48445/57600 [8:31:19<1:37:42,  1.56it/s]
 84%|████████▍ | 48446/57600 [8:31:20<1:38:53,  1.54it/s]
 84%|████████▍ | 48447/57600 [8:31:21<1:38:06,  1.55it/s]
 84%|████████▍ | 48448/57600 [8:31:21<1:35:38,  1.59it/s]
 84%|████████▍ | 48449/57600 [8:31:22<1:36:30,  1.58it/s]
 84%|████████▍ | 48450/57600 [8:31:22<1:34:38,  1.61it/s]
 84%|████████▍ | 48451/57600 [8:31:23<1:37:09,  1.57it/s]
 84%|████████▍ | 48452/57600 [8:31:24<1:36:16,  1.58it/s]
 84%|████████▍ | 48453/57600 [8:31:24<1:36:41,  1.58it/s]
 84%|████████▍ | 48454/57600 [8:31:25<1:36:47,  1.57it/s]
 84%|████████▍ | 48455/57600 [8:31:26<1:34:43,  1.61it/s]
 84%|████████▍ | 48456/57600 [8:31:26<1:35:21,  1.60it/s]
 84%|████████▍ | 48457/57600 [8:31:27<1:32:38,  1.64it/s]
 84%|████████▍ | 48458/57600 [8:31:27<1:35:09,  1.60it/s]
 84%|████████▍ | 48459/57600 [8:31:28<1:34:41,  1.61it/s]
 84%|████████▍ | 48460/57600 [8:31:29<1:35:21,  1.60it/s]
                                                         
{'loss': 1.1175, 'learning_rate': 2.4331010452961675e-07, 'epoch': 534.88}

 84%|████████▍ | 48460/57600 [8:31:29<1:35:21,  1.60it/s]
 84%|████████▍ | 48461/57600 [8:31:29<1:35:19,  1.60it/s]
 84%|████████▍ | 48462/57600 [8:31:30<1:41:57,  1.49it/s]
 84%|████████▍ | 48463/57600 [8:31:31<1:40:03,  1.52it/s]
 84%|████████▍ | 48464/57600 [8:31:31<1:37:28,  1.56it/s]
 84%|████████▍ | 48465/57600 [8:31:32<1:34:57,  1.60it/s]
 84%|████████▍ | 48466/57600 [8:31:32<1:31:07,  1.67it/s]
 84%|████████▍ | 48467/57600 [8:31:33<1:29:34,  1.70it/s]
 84%|████████▍ | 48468/57600 [8:31:34<1:29:41,  1.70it/s]
 84%|████████▍ | 48469/57600 [8:31:34<1:33:16,  1.63it/s]
 84%|████████▍ | 48470/57600 [8:31:35<1:33:00,  1.64it/s]
 84%|████████▍ | 48471/57600 [8:31:36<1:33:14,  1.63it/s]
 84%|████████▍ | 48472/57600 [8:31:36<1:37:45,  1.56it/s]
 84%|████████▍ | 48473/57600 [8:31:37<1:36:06,  1.58it/s]
 84%|████████▍ | 48474/57600 [8:31:37<1:33:53,  1.62it/s]
 84%|████████▍ | 48475/57600 [8:31:38<1:36:29,  1.58it/s]
 84%|████████▍ | 48476/57600 [8:31:39<1:35:38,  1.59it/s]
 84%|████████▍ | 48477/57600 [8:31:39<1:35:07,  1.60it/s]
 84%|████████▍ | 48478/57600 [8:31:40<1:34:58,  1.60it/s]
 84%|████████▍ | 48479/57600 [8:31:41<1:35:21,  1.59it/s]
 84%|████████▍ | 48480/57600 [8:31:41<1:37:43,  1.56it/s]
                                                         
{'loss': 1.1428, 'learning_rate': 2.429965156794425e-07, 'epoch': 535.1}

 84%|████████▍ | 48480/57600 [8:31:41<1:37:43,  1.56it/s]
 84%|████████▍ | 48481/57600 [8:31:42<1:39:42,  1.52it/s]
 84%|████████▍ | 48482/57600 [8:31:43<1:36:46,  1.57it/s]
 84%|████████▍ | 48483/57600 [8:31:43<1:34:56,  1.60it/s]
 84%|████████▍ | 48484/57600 [8:31:44<1:34:23,  1.61it/s]
 84%|████████▍ | 48485/57600 [8:31:44<1:32:35,  1.64it/s]
 84%|████████▍ | 48486/57600 [8:31:45<1:33:46,  1.62it/s]
 84%|████████▍ | 48487/57600 [8:31:46<1:36:39,  1.57it/s]
 84%|████████▍ | 48488/57600 [8:31:46<1:35:23,  1.59it/s]
 84%|████████▍ | 48489/57600 [8:31:47<1:33:09,  1.63it/s]
 84%|████████▍ | 48490/57600 [8:31:47<1:32:03,  1.65it/s]
 84%|████████▍ | 48491/57600 [8:31:48<1:31:54,  1.65it/s]
 84%|████████▍ | 48492/57600 [8:31:49<1:30:24,  1.68it/s]
 84%|████████▍ | 48493/57600 [8:31:49<1:30:40,  1.67it/s]
 84%|████████▍ | 48494/57600 [8:31:50<1:33:25,  1.62it/s]
 84%|████████▍ | 48495/57600 [8:31:50<1:33:01,  1.63it/s]
 84%|████████▍ | 48496/57600 [8:31:51<1:33:03,  1.63it/s]
 84%|████████▍ | 48497/57600 [8:31:52<1:36:00,  1.58it/s]
 84%|████████▍ | 48498/57600 [8:31:52<1:33:22,  1.62it/s]
 84%|████████▍ | 48499/57600 [8:31:53<1:37:56,  1.55it/s]
 84%|████████▍ | 48500/57600 [8:31:54<1:38:47,  1.54it/s]
                                                         
{'loss': 1.1469, 'learning_rate': 2.426829268292683e-07, 'epoch': 535.32}

 84%|████████▍ | 48500/57600 [8:31:54<1:38:47,  1.54it/s]
 84%|████████▍ | 48501/57600 [8:31:54<1:41:44,  1.49it/s]
 84%|████████▍ | 48502/57600 [8:31:55<1:38:22,  1.54it/s]
 84%|████████▍ | 48503/57600 [8:31:56<1:38:37,  1.54it/s]
 84%|████████▍ | 48504/57600 [8:31:56<1:36:33,  1.57it/s]
 84%|████████▍ | 48505/57600 [8:31:57<1:37:29,  1.55it/s]
 84%|████████▍ | 48506/57600 [8:31:58<1:40:00,  1.52it/s]
 84%|████████▍ | 48507/57600 [8:31:58<1:36:53,  1.56it/s]
 84%|████████▍ | 48508/57600 [8:31:59<1:34:35,  1.60it/s]
 84%|████████▍ | 48509/57600 [8:31:59<1:36:15,  1.57it/s]
 84%|████████▍ | 48510/57600 [8:32:00<1:35:10,  1.59it/s]
 84%|████████▍ | 48511/57600 [8:32:01<1:36:01,  1.58it/s]
 84%|████████▍ | 48512/57600 [8:32:01<1:35:43,  1.58it/s]
 84%|████████▍ | 48513/57600 [8:32:02<1:34:26,  1.60it/s]
 84%|████████▍ | 48514/57600 [8:32:03<1:34:17,  1.61it/s]
 84%|████████▍ | 48515/57600 [8:32:03<1:33:40,  1.62it/s]
 84%|████████▍ | 48516/57600 [8:32:04<1:36:05,  1.58it/s]
 84%|████████▍ | 48517/57600 [8:32:04<1:35:14,  1.59it/s]
 84%|████████▍ | 48518/57600 [8:32:05<1:33:13,  1.62it/s]
 84%|████████▍ | 48519/57600 [8:32:06<1:32:31,  1.64it/s]
 84%|████████▍ | 48520/57600 [8:32:06<1:35:38,  1.58it/s]
                                                         
{'loss': 1.0978, 'learning_rate': 2.42369337979094e-07, 'epoch': 535.54}

 84%|████████▍ | 48520/57600 [8:32:06<1:35:38,  1.58it/s]
 84%|████████▍ | 48521/57600 [8:32:07<1:38:03,  1.54it/s]
 84%|████████▍ | 48522/57600 [8:32:08<1:37:11,  1.56it/s]
 84%|████████▍ | 48523/57600 [8:32:08<1:35:47,  1.58it/s]
 84%|████████▍ | 48524/57600 [8:32:09<1:34:53,  1.59it/s]
 84%|████████▍ | 48525/57600 [8:32:09<1:33:13,  1.62it/s]
 84%|████████▍ | 48526/57600 [8:32:10<1:29:50,  1.68it/s]
 84%|████████▍ | 48527/57600 [8:32:11<1:29:52,  1.68it/s]
 84%|████████▍ | 48528/57600 [8:32:11<1:34:28,  1.60it/s]
 84%|████████▍ | 48529/57600 [8:32:12<1:39:30,  1.52it/s]
 84%|████████▍ | 48530/57600 [8:32:13<1:35:17,  1.59it/s]
 84%|████████▍ | 48531/57600 [8:32:13<1:35:39,  1.58it/s]
 84%|████████▍ | 48532/57600 [8:32:14<1:37:20,  1.55it/s]
 84%|████████▍ | 48533/57600 [8:32:15<1:35:16,  1.59it/s]
 84%|████████▍ | 48534/57600 [8:32:15<1:34:30,  1.60it/s]
 84%|████████▍ | 48535/57600 [8:32:16<1:34:25,  1.60it/s]
 84%|████████▍ | 48536/57600 [8:32:16<1:34:57,  1.59it/s]
 84%|████████▍ | 48537/57600 [8:32:17<1:31:49,  1.65it/s]
 84%|████████▍ | 48538/57600 [8:32:18<1:30:51,  1.66it/s]
 84%|████████▍ | 48539/57600 [8:32:18<1:32:06,  1.64it/s]
 84%|████████▍ | 48540/57600 [8:32:19<1:29:54,  1.68it/s]
                                                         
{'loss': 1.1107, 'learning_rate': 2.4205574912891987e-07, 'epoch': 535.76}

 84%|████████▍ | 48540/57600 [8:32:19<1:29:54,  1.68it/s]
 84%|████████▍ | 48541/57600 [8:32:19<1:32:13,  1.64it/s]
 84%|████████▍ | 48542/57600 [8:32:20<1:36:18,  1.57it/s]
 84%|████████▍ | 48543/57600 [8:32:21<1:36:17,  1.57it/s]
 84%|████████▍ | 48544/57600 [8:32:21<1:35:38,  1.58it/s]
 84%|████████▍ | 48545/57600 [8:32:22<1:33:53,  1.61it/s]
 84%|████████▍ | 48546/57600 [8:32:23<1:30:58,  1.66it/s]
 84%|████████▍ | 48547/57600 [8:32:23<1:30:14,  1.67it/s]
 84%|████████▍ | 48548/57600 [8:32:24<1:32:47,  1.63it/s]
 84%|████████▍ | 48549/57600 [8:32:24<1:32:35,  1.63it/s]
 84%|████████▍ | 48550/57600 [8:32:25<1:33:56,  1.61it/s]
 84%|████████▍ | 48551/57600 [8:32:26<1:31:37,  1.65it/s]
 84%|████████▍ | 48552/57600 [8:32:26<1:35:10,  1.58it/s]
 84%|████████▍ | 48553/57600 [8:32:27<1:34:43,  1.59it/s]
 84%|████████▍ | 48554/57600 [8:32:28<1:34:25,  1.60it/s]
 84%|████████▍ | 48555/57600 [8:32:28<1:35:38,  1.58it/s]
 84%|████████▍ | 48556/57600 [8:32:29<1:37:18,  1.55it/s]
 84%|████████▍ | 48557/57600 [8:32:30<1:38:19,  1.53it/s]
 84%|████████▍ | 48558/57600 [8:32:30<1:39:16,  1.52it/s]
 84%|████████▍ | 48559/57600 [8:32:31<1:38:07,  1.54it/s]
 84%|████████▍ | 48560/57600 [8:32:31<1:37:52,  1.54it/s]
                                                         
{'loss': 1.1489, 'learning_rate': 2.417421602787456e-07, 'epoch': 535.98}

 84%|████████▍ | 48560/57600 [8:32:31<1:37:52,  1.54it/s]
 84%|████████▍ | 48561/57600 [8:32:32<1:38:02,  1.54it/s]
 84%|████████▍ | 48562/57600 [8:32:33<1:42:14,  1.47it/s]
 84%|████████▍ | 48563/57600 [8:32:33<1:37:22,  1.55it/s]
 84%|████████▍ | 48564/57600 [8:32:34<1:34:20,  1.60it/s]
 84%|████████▍ | 48565/57600 [8:32:35<1:31:49,  1.64it/s]
 84%|████████▍ | 48566/57600 [8:32:35<1:31:49,  1.64it/s]
 84%|████████▍ | 48567/57600 [8:32:36<1:34:18,  1.60it/s]
 84%|████████▍ | 48568/57600 [8:32:37<1:35:52,  1.57it/s]
 84%|████████▍ | 48569/57600 [8:32:37<1:39:06,  1.52it/s]
 84%|████████▍ | 48570/57600 [8:32:38<1:38:42,  1.52it/s]
 84%|████████▍ | 48571/57600 [8:32:38<1:34:09,  1.60it/s]
 84%|████████▍ | 48572/57600 [8:32:39<1:34:00,  1.60it/s]
 84%|████████▍ | 48573/57600 [8:32:40<1:34:25,  1.59it/s]
 84%|████████▍ | 48574/57600 [8:32:40<1:33:00,  1.62it/s]
 84%|████████▍ | 48575/57600 [8:32:41<1:33:56,  1.60it/s]
 84%|████████▍ | 48576/57600 [8:32:42<1:34:47,  1.59it/s]
 84%|████████▍ | 48577/57600 [8:32:42<1:34:33,  1.59it/s]
 84%|████████▍ | 48578/57600 [8:32:43<1:31:21,  1.65it/s]
 84%|████████▍ | 48579/57600 [8:32:43<1:31:14,  1.65it/s]
 84%|████████▍ | 48580/57600 [8:32:44<1:34:52,  1.58it/s]
                                                         
{'loss': 1.1286, 'learning_rate': 2.414285714285714e-07, 'epoch': 536.2}

 84%|████████▍ | 48580/57600 [8:32:44<1:34:52,  1.58it/s]
 84%|████████▍ | 48581/57600 [8:32:45<1:33:21,  1.61it/s]
 84%|████████▍ | 48582/57600 [8:32:45<1:32:15,  1.63it/s]
 84%|████████▍ | 48583/57600 [8:32:46<1:33:38,  1.61it/s]
 84%|████████▍ | 48584/57600 [8:32:47<1:36:05,  1.56it/s]
 84%|████████▍ | 48585/57600 [8:32:47<1:37:29,  1.54it/s]
 84%|████████▍ | 48586/57600 [8:32:48<1:34:36,  1.59it/s]
 84%|████████▍ | 48587/57600 [8:32:48<1:36:27,  1.56it/s]
 84%|████████▍ | 48588/57600 [8:32:49<1:34:37,  1.59it/s]
 84%|████████▍ | 48589/57600 [8:32:50<1:33:22,  1.61it/s]
 84%|████████▍ | 48590/57600 [8:32:50<1:30:14,  1.66it/s]
 84%|████████▍ | 48591/57600 [8:32:51<1:30:00,  1.67it/s]
 84%|████████▍ | 48592/57600 [8:32:51<1:30:59,  1.65it/s]
 84%|████████▍ | 48593/57600 [8:32:52<1:32:39,  1.62it/s]
 84%|████████▍ | 48594/57600 [8:32:53<1:31:56,  1.63it/s]
 84%|████████▍ | 48595/57600 [8:32:53<1:32:00,  1.63it/s]
 84%|████████▍ | 48596/57600 [8:32:54<1:29:59,  1.67it/s]
 84%|████████▍ | 48597/57600 [8:32:55<1:31:45,  1.64it/s]
 84%|████████▍ | 48598/57600 [8:32:55<1:34:14,  1.59it/s]
 84%|████████▍ | 48599/57600 [8:32:56<1:33:25,  1.61it/s]
 84%|████████▍ | 48600/57600 [8:32:56<1:33:52,  1.60it/s]
                                                         
{'loss': 1.132, 'learning_rate': 2.4111498257839723e-07, 'epoch': 536.42}

 84%|████████▍ | 48600/57600 [8:32:56<1:33:52,  1.60it/s]
 84%|████████▍ | 48601/57600 [8:32:57<1:36:36,  1.55it/s]
 84%|████████▍ | 48602/57600 [8:32:58<1:36:12,  1.56it/s]
 84%|████████▍ | 48603/57600 [8:32:58<1:35:56,  1.56it/s]
 84%|████████▍ | 48604/57600 [8:32:59<1:39:37,  1.51it/s]
 84%|████████▍ | 48605/57600 [8:33:00<1:38:17,  1.53it/s]
 84%|████████▍ | 48606/57600 [8:33:00<1:39:46,  1.50it/s]
 84%|████████▍ | 48607/57600 [8:33:01<1:42:12,  1.47it/s]
 84%|████████▍ | 48608/57600 [8:33:02<1:43:51,  1.44it/s]
 84%|████████▍ | 48609/57600 [8:33:03<1:43:45,  1.44it/s]
 84%|████████▍ | 48610/57600 [8:33:03<1:43:00,  1.45it/s]
 84%|████████▍ | 48611/57600 [8:33:04<1:40:25,  1.49it/s]
 84%|████████▍ | 48612/57600 [8:33:04<1:36:51,  1.55it/s]
 84%|████████▍ | 48613/57600 [8:33:05<1:34:49,  1.58it/s]
 84%|████████▍ | 48614/57600 [8:33:06<1:35:24,  1.57it/s]
 84%|████████▍ | 48615/57600 [8:33:06<1:34:01,  1.59it/s]
 84%|████████▍ | 48616/57600 [8:33:07<1:36:45,  1.55it/s]
 84%|████████▍ | 48617/57600 [8:33:08<1:34:33,  1.58it/s]
 84%|████████▍ | 48618/57600 [8:33:08<1:33:11,  1.61it/s]
 84%|████████▍ | 48619/57600 [8:33:09<1:34:55,  1.58it/s]
 84%|████████▍ | 48620/57600 [8:33:10<1:37:05,  1.54it/s]
                                                         
{'loss': 1.076, 'learning_rate': 2.40801393728223e-07, 'epoch': 536.64}

 84%|████████▍ | 48620/57600 [8:33:10<1:37:05,  1.54it/s]
 84%|████████▍ | 48621/57600 [8:33:10<1:35:24,  1.57it/s]
 84%|████████▍ | 48622/57600 [8:33:11<1:32:13,  1.62it/s]
 84%|████████▍ | 48623/57600 [8:33:11<1:32:28,  1.62it/s]
 84%|████████▍ | 48624/57600 [8:33:12<1:29:58,  1.66it/s]
 84%|████████▍ | 48625/57600 [8:33:13<1:30:16,  1.66it/s]
 84%|████████▍ | 48626/57600 [8:33:13<1:30:28,  1.65it/s]
 84%|████████▍ | 48627/57600 [8:33:14<1:32:36,  1.61it/s]
 84%|████████▍ | 48628/57600 [8:33:14<1:31:21,  1.64it/s]
 84%|████████▍ | 48629/57600 [8:33:15<1:30:04,  1.66it/s]
 84%|████████▍ | 48630/57600 [8:33:16<1:31:53,  1.63it/s]
 84%|████████▍ | 48631/57600 [8:33:16<1:33:10,  1.60it/s]
 84%|████████▍ | 48632/57600 [8:33:17<1:31:52,  1.63it/s]
 84%|████████▍ | 48633/57600 [8:33:17<1:30:39,  1.65it/s]
 84%|████████▍ | 48634/57600 [8:33:18<1:30:53,  1.64it/s]
 84%|████████▍ | 48635/57600 [8:33:19<1:31:19,  1.64it/s]
 84%|████████▍ | 48636/57600 [8:33:19<1:32:40,  1.61it/s]
 84%|████████▍ | 48637/57600 [8:33:20<1:31:20,  1.64it/s]
 84%|████████▍ | 48638/57600 [8:33:21<1:34:30,  1.58it/s]
 84%|████████▍ | 48639/57600 [8:33:21<1:32:47,  1.61it/s]
 84%|████████▍ | 48640/57600 [8:33:22<1:33:11,  1.60it/s]
                                                         
{'loss': 1.1494, 'learning_rate': 2.404878048780488e-07, 'epoch': 536.87}

 84%|████████▍ | 48640/57600 [8:33:22<1:33:11,  1.60it/s]
 84%|████████▍ | 48641/57600 [8:33:22<1:34:04,  1.59it/s]
 84%|████████▍ | 48642/57600 [8:33:23<1:32:29,  1.61it/s]
 84%|████████▍ | 48643/57600 [8:33:24<1:33:03,  1.60it/s]
 84%|████████▍ | 48644/57600 [8:33:24<1:31:01,  1.64it/s]
 84%|████████▍ | 48645/57600 [8:33:25<1:30:59,  1.64it/s]
 84%|████████▍ | 48646/57600 [8:33:25<1:30:47,  1.64it/s]
 84%|████████▍ | 48647/57600 [8:33:26<1:34:58,  1.57it/s]
 84%|████████▍ | 48648/57600 [8:33:27<1:35:17,  1.57it/s]
 84%|████████▍ | 48649/57600 [8:33:27<1:35:20,  1.56it/s]
 84%|████████▍ | 48650/57600 [8:33:28<1:34:15,  1.58it/s]
 84%|████████▍ | 48651/57600 [8:33:29<1:58:12,  1.26it/s]
 84%|████████▍ | 48652/57600 [8:33:30<1:47:16,  1.39it/s]
 84%|████████▍ | 48653/57600 [8:33:31<1:47:54,  1.38it/s]
 84%|████████▍ | 48654/57600 [8:33:31<1:43:46,  1.44it/s]
 84%|████████▍ | 48655/57600 [8:33:32<1:38:09,  1.52it/s]
 84%|████████▍ | 48656/57600 [8:33:32<1:37:29,  1.53it/s]
 84%|████████▍ | 48657/57600 [8:33:33<1:39:24,  1.50it/s]
 84%|████████▍ | 48658/57600 [8:33:34<1:38:00,  1.52it/s]
 84%|████████▍ | 48659/57600 [8:33:34<1:38:00,  1.52it/s]
 84%|████████▍ | 48660/57600 [8:33:35<1:34:58,  1.57it/s]
                                                         
{'loss': 1.1247, 'learning_rate': 2.401742160278745e-07, 'epoch': 537.09}

 84%|████████▍ | 48660/57600 [8:33:35<1:34:58,  1.57it/s]
 84%|████████▍ | 48661/57600 [8:33:36<1:36:01,  1.55it/s]
 84%|████████▍ | 48662/57600 [8:33:36<1:36:22,  1.55it/s]
 84%|████████▍ | 48663/57600 [8:33:37<1:34:23,  1.58it/s]
 84%|████████▍ | 48664/57600 [8:33:37<1:34:42,  1.57it/s]
 84%|████████▍ | 48665/57600 [8:33:38<1:34:13,  1.58it/s]
 84%|████████▍ | 48666/57600 [8:33:39<1:32:32,  1.61it/s]
 84%|████████▍ | 48667/57600 [8:33:39<1:31:13,  1.63it/s]
 84%|████████▍ | 48668/57600 [8:33:40<1:31:41,  1.62it/s]
 84%|████████▍ | 48669/57600 [8:33:41<1:29:44,  1.66it/s]
 84%|████████▍ | 48670/57600 [8:33:41<1:30:34,  1.64it/s]
 84%|████████▍ | 48671/57600 [8:33:42<1:30:37,  1.64it/s]
 84%|████████▍ | 48672/57600 [8:33:42<1:34:58,  1.57it/s]
 85%|████████▍ | 48673/57600 [8:33:43<1:37:20,  1.53it/s]
 85%|████████▍ | 48674/57600 [8:33:44<1:35:37,  1.56it/s]
 85%|████████▍ | 48675/57600 [8:33:44<1:35:06,  1.56it/s]
 85%|████████▍ | 48676/57600 [8:33:45<1:37:06,  1.53it/s]
 85%|████████▍ | 48677/57600 [8:33:46<1:34:53,  1.57it/s]
 85%|████████▍ | 48678/57600 [8:33:46<1:36:53,  1.53it/s]
 85%|████████▍ | 48679/57600 [8:33:47<1:35:14,  1.56it/s]
 85%|████████▍ | 48680/57600 [8:33:48<1:33:24,  1.59it/s]
                                                         
{'loss': 1.1095, 'learning_rate': 2.3986062717770034e-07, 'epoch': 537.31}

 85%|████████▍ | 48680/57600 [8:33:48<1:33:24,  1.59it/s]
 85%|████████▍ | 48681/57600 [8:33:48<1:34:24,  1.57it/s]
 85%|████████▍ | 48682/57600 [8:33:49<1:36:17,  1.54it/s]
 85%|████████▍ | 48683/57600 [8:33:50<1:36:57,  1.53it/s]
 85%|████████▍ | 48684/57600 [8:33:50<1:35:31,  1.56it/s]
 85%|████████▍ | 48685/57600 [8:33:51<1:34:51,  1.57it/s]
 85%|████████▍ | 48686/57600 [8:33:52<1:37:24,  1.53it/s]
 85%|████████▍ | 48687/57600 [8:33:52<1:34:44,  1.57it/s]
 85%|████████▍ | 48688/57600 [8:33:53<1:33:08,  1.59it/s]
 85%|████████▍ | 48689/57600 [8:33:53<1:33:07,  1.59it/s]
 85%|████████▍ | 48690/57600 [8:33:54<1:34:07,  1.58it/s]
 85%|████████▍ | 48691/57600 [8:33:55<1:34:49,  1.57it/s]
 85%|████████▍ | 48692/57600 [8:33:55<1:32:24,  1.61it/s]
 85%|████████▍ | 48693/57600 [8:33:56<1:30:53,  1.63it/s]
 85%|████████▍ | 48694/57600 [8:33:56<1:28:44,  1.67it/s]
 85%|████████▍ | 48695/57600 [8:33:57<1:34:16,  1.57it/s]
 85%|████████▍ | 48696/57600 [8:33:58<1:31:29,  1.62it/s]
 85%|████████▍ | 48697/57600 [8:33:58<1:32:24,  1.61it/s]
 85%|████████▍ | 48698/57600 [8:33:59<1:30:31,  1.64it/s]
 85%|████████▍ | 48699/57600 [8:33:59<1:31:06,  1.63it/s]
 85%|████████▍ | 48700/57600 [8:34:00<1:31:39,  1.62it/s]
                                                         
{'loss': 1.1362, 'learning_rate': 2.395470383275261e-07, 'epoch': 537.53}

 85%|████████▍ | 48700/57600 [8:34:00<1:31:39,  1.62it/s]
 85%|████████▍ | 48701/57600 [8:34:01<1:33:04,  1.59it/s]
 85%|████████▍ | 48702/57600 [8:34:01<1:31:48,  1.62it/s]
 85%|████████▍ | 48703/57600 [8:34:02<1:31:36,  1.62it/s]
 85%|████████▍ | 48704/57600 [8:34:03<1:32:14,  1.61it/s]
 85%|████████▍ | 48705/57600 [8:34:03<1:30:27,  1.64it/s]
 85%|████████▍ | 48706/57600 [8:34:04<1:33:12,  1.59it/s]
 85%|████████▍ | 48707/57600 [8:34:05<1:38:45,  1.50it/s]
 85%|████████▍ | 48708/57600 [8:34:05<1:36:04,  1.54it/s]
 85%|████████▍ | 48709/57600 [8:34:06<1:34:30,  1.57it/s]
 85%|████████▍ | 48710/57600 [8:34:06<1:33:46,  1.58it/s]
 85%|████████▍ | 48711/57600 [8:34:07<1:33:11,  1.59it/s]
 85%|████████▍ | 48712/57600 [8:34:08<1:33:09,  1.59it/s]
 85%|████████▍ | 48713/57600 [8:34:08<1:29:25,  1.66it/s]
 85%|████████▍ | 48714/57600 [8:34:09<1:28:21,  1.68it/s]
 85%|████████▍ | 48715/57600 [8:34:09<1:29:32,  1.65it/s]
 85%|████████▍ | 48716/57600 [8:34:10<1:29:23,  1.66it/s]
 85%|████████▍ | 48717/57600 [8:34:11<1:34:01,  1.57it/s]
 85%|████████▍ | 48718/57600 [8:34:11<1:36:44,  1.53it/s]
 85%|████████▍ | 48719/57600 [8:34:12<1:36:46,  1.53it/s]
 85%|████████▍ | 48720/57600 [8:34:13<1:36:09,  1.54it/s]
                                                         
{'loss': 1.1193, 'learning_rate': 2.392334494773519e-07, 'epoch': 537.75}

 85%|████████▍ | 48720/57600 [8:34:13<1:36:09,  1.54it/s]
 85%|████████▍ | 48721/57600 [8:34:13<1:34:20,  1.57it/s]
 85%|████████▍ | 48722/57600 [8:34:14<1:32:36,  1.60it/s]
 85%|████████▍ | 48723/57600 [8:34:15<1:34:54,  1.56it/s]
 85%|████████▍ | 48724/57600 [8:34:15<1:31:26,  1.62it/s]
 85%|████████▍ | 48725/57600 [8:34:16<1:31:02,  1.62it/s]
 85%|████████▍ | 48726/57600 [8:34:16<1:30:26,  1.64it/s]
 85%|████████▍ | 48727/57600 [8:34:17<1:31:43,  1.61it/s]
 85%|████████▍ | 48728/57600 [8:34:18<1:29:41,  1.65it/s]
 85%|████████▍ | 48729/57600 [8:34:18<1:33:18,  1.58it/s]
 85%|████████▍ | 48730/57600 [8:34:19<1:31:58,  1.61it/s]
 85%|████████▍ | 48731/57600 [8:34:20<1:33:49,  1.58it/s]
 85%|████████▍ | 48732/57600 [8:34:20<1:32:48,  1.59it/s]
 85%|████████▍ | 48733/57600 [8:34:21<1:31:00,  1.62it/s]
 85%|████████▍ | 48734/57600 [8:34:21<1:30:15,  1.64it/s]
 85%|████████▍ | 48735/57600 [8:34:22<1:31:21,  1.62it/s]
 85%|████████▍ | 48736/57600 [8:34:23<1:31:40,  1.61it/s]
 85%|████████▍ | 48737/57600 [8:34:23<1:30:47,  1.63it/s]
 85%|████████▍ | 48738/57600 [8:34:24<1:28:49,  1.66it/s]
 85%|████████▍ | 48739/57600 [8:34:24<1:29:07,  1.66it/s]
 85%|████████▍ | 48740/57600 [8:34:25<1:29:19,  1.65it/s]
                                                         
{'loss': 1.1645, 'learning_rate': 2.389198606271777e-07, 'epoch': 537.97}

 85%|████████▍ | 48740/57600 [8:34:25<1:29:19,  1.65it/s]
 85%|████████▍ | 48741/57600 [8:34:26<1:32:01,  1.60it/s]
 85%|████████▍ | 48742/57600 [8:34:26<1:30:20,  1.63it/s]
 85%|████████▍ | 48743/57600 [8:34:27<1:34:08,  1.57it/s]
 85%|████████▍ | 48744/57600 [8:34:28<1:31:59,  1.60it/s]
 85%|████████▍ | 48745/57600 [8:34:28<1:30:25,  1.63it/s]
 85%|████████▍ | 48746/57600 [8:34:29<1:31:03,  1.62it/s]
 85%|████████▍ | 48747/57600 [8:34:29<1:28:58,  1.66it/s]
 85%|████████▍ | 48748/57600 [8:34:30<1:31:59,  1.60it/s]
 85%|████████▍ | 48749/57600 [8:34:31<1:30:51,  1.62it/s]
 85%|████████▍ | 48750/57600 [8:34:31<1:31:04,  1.62it/s]
 85%|████████▍ | 48751/57600 [8:34:32<1:35:09,  1.55it/s]
 85%|████████▍ | 48752/57600 [8:34:33<1:32:50,  1.59it/s]
 85%|████████▍ | 48753/57600 [8:34:33<1:31:11,  1.62it/s]
 85%|████████▍ | 48754/57600 [8:34:34<1:30:43,  1.63it/s]
 85%|████████▍ | 48755/57600 [8:34:34<1:33:58,  1.57it/s]
 85%|████████▍ | 48756/57600 [8:34:35<1:34:39,  1.56it/s]
 85%|████████▍ | 48757/57600 [8:34:36<1:35:44,  1.54it/s]
 85%|████████▍ | 48758/57600 [8:34:36<1:34:49,  1.55it/s]
 85%|████████▍ | 48759/57600 [8:34:37<1:33:33,  1.58it/s]
 85%|████████▍ | 48760/57600 [8:34:38<1:34:46,  1.55it/s]
                                                         
{'loss': 1.1336, 'learning_rate': 2.3860627177700346e-07, 'epoch': 538.19}

 85%|████████▍ | 48760/57600 [8:34:38<1:34:46,  1.55it/s]
 85%|████████▍ | 48761/57600 [8:34:38<1:30:46,  1.62it/s]
 85%|████████▍ | 48762/57600 [8:34:39<1:31:54,  1.60it/s]
 85%|████████▍ | 48763/57600 [8:34:40<1:34:18,  1.56it/s]
 85%|████████▍ | 48764/57600 [8:34:40<1:32:58,  1.58it/s]
 85%|████████▍ | 48765/57600 [8:34:41<1:32:12,  1.60it/s]
 85%|████████▍ | 48766/57600 [8:34:41<1:31:31,  1.61it/s]
 85%|████████▍ | 48767/57600 [8:34:42<1:30:53,  1.62it/s]
 85%|████████▍ | 48768/57600 [8:34:43<1:28:18,  1.67it/s]
 85%|████████▍ | 48769/57600 [8:34:43<1:28:30,  1.66it/s]
 85%|████████▍ | 48770/57600 [8:34:44<1:28:02,  1.67it/s]
 85%|████████▍ | 48771/57600 [8:34:44<1:29:58,  1.64it/s]
 85%|████████▍ | 48772/57600 [8:34:45<1:29:06,  1.65it/s]
 85%|████████▍ | 48773/57600 [8:34:46<1:29:14,  1.65it/s]
 85%|████████▍ | 48774/57600 [8:34:46<1:30:41,  1.62it/s]
 85%|████████▍ | 48775/57600 [8:34:47<1:31:40,  1.60it/s]
 85%|████████▍ | 48776/57600 [8:34:47<1:30:58,  1.62it/s]
 85%|████████▍ | 48777/57600 [8:34:48<1:36:03,  1.53it/s]
 85%|████████▍ | 48778/57600 [8:34:49<1:37:21,  1.51it/s]
 85%|████████▍ | 48779/57600 [8:34:50<1:37:03,  1.51it/s]
 85%|████████▍ | 48780/57600 [8:34:50<1:34:13,  1.56it/s]
                                                         
{'loss': 1.1218, 'learning_rate': 2.382926829268293e-07, 'epoch': 538.41}

 85%|████████▍ | 48780/57600 [8:34:50<1:34:13,  1.56it/s]
 85%|████████▍ | 48781/57600 [8:34:51<1:31:44,  1.60it/s]
 85%|████████▍ | 48782/57600 [8:34:51<1:31:05,  1.61it/s]
 85%|████████▍ | 48783/57600 [8:34:52<1:29:19,  1.64it/s]
 85%|████████▍ | 48784/57600 [8:34:52<1:27:39,  1.68it/s]
 85%|████████▍ | 48785/57600 [8:34:53<1:31:14,  1.61it/s]
 85%|████████▍ | 48786/57600 [8:34:54<1:30:23,  1.63it/s]
 85%|████████▍ | 48787/57600 [8:34:54<1:34:28,  1.55it/s]
 85%|████████▍ | 48788/57600 [8:34:55<1:33:37,  1.57it/s]
 85%|████████▍ | 48789/57600 [8:34:56<1:35:26,  1.54it/s]
 85%|████████▍ | 48790/57600 [8:34:56<1:33:31,  1.57it/s]
 85%|████████▍ | 48791/57600 [8:34:57<1:35:08,  1.54it/s]
 85%|████████▍ | 48792/57600 [8:34:58<1:32:24,  1.59it/s]
 85%|████████▍ | 48793/57600 [8:34:58<1:33:54,  1.56it/s]
 85%|████████▍ | 48794/57600 [8:34:59<1:31:52,  1.60it/s]
 85%|████████▍ | 48795/57600 [8:35:00<1:32:08,  1.59it/s]
 85%|████████▍ | 48796/57600 [8:35:00<1:30:43,  1.62it/s]
 85%|████████▍ | 48797/57600 [8:35:01<1:33:03,  1.58it/s]
 85%|████████▍ | 48798/57600 [8:35:02<1:38:29,  1.49it/s]
 85%|████████▍ | 48799/57600 [8:35:02<1:34:35,  1.55it/s]
 85%|████████▍ | 48800/57600 [8:35:03<1:30:59,  1.61it/s]
                                                         
{'loss': 1.104, 'learning_rate': 2.37979094076655e-07, 'epoch': 538.63}

 85%|████████▍ | 48800/57600 [8:35:03<1:30:59,  1.61it/s]
 85%|████████▍ | 48801/57600 [8:35:03<1:33:32,  1.57it/s]
 85%|████████▍ | 48802/57600 [8:35:04<1:33:04,  1.58it/s]
 85%|████████▍ | 48803/57600 [8:35:05<1:32:45,  1.58it/s]
 85%|████████▍ | 48804/57600 [8:35:05<1:30:26,  1.62it/s]
 85%|████████▍ | 48805/57600 [8:35:06<1:30:19,  1.62it/s]
 85%|████████▍ | 48806/57600 [8:35:06<1:28:48,  1.65it/s]
 85%|████████▍ | 48807/57600 [8:35:07<1:29:03,  1.65it/s]
 85%|████████▍ | 48808/57600 [8:35:08<1:31:25,  1.60it/s]
 85%|████████▍ | 48809/57600 [8:35:08<1:32:34,  1.58it/s]
 85%|████████▍ | 48810/57600 [8:35:09<1:31:17,  1.60it/s]
 85%|████████▍ | 48811/57600 [8:35:10<1:32:02,  1.59it/s]
 85%|████████▍ | 48812/57600 [8:35:10<1:31:58,  1.59it/s]
 85%|████████▍ | 48813/57600 [8:35:11<1:33:52,  1.56it/s]
 85%|████████▍ | 48814/57600 [8:35:12<1:35:11,  1.54it/s]
 85%|████████▍ | 48815/57600 [8:35:12<1:33:26,  1.57it/s]
 85%|████████▍ | 48816/57600 [8:35:13<1:33:42,  1.56it/s]
 85%|████████▍ | 48817/57600 [8:35:13<1:32:46,  1.58it/s]
 85%|████████▍ | 48818/57600 [8:35:14<1:31:48,  1.59it/s]
 85%|████████▍ | 48819/57600 [8:35:15<1:30:27,  1.62it/s]
 85%|████████▍ | 48820/57600 [8:35:15<1:30:29,  1.62it/s]
                                                         
{'loss': 1.1036, 'learning_rate': 2.3766550522648084e-07, 'epoch': 538.85}

 85%|████████▍ | 48820/57600 [8:35:15<1:30:29,  1.62it/s]
 85%|████████▍ | 48821/57600 [8:35:16<1:31:30,  1.60it/s]
 85%|████████▍ | 48822/57600 [8:35:17<1:31:49,  1.59it/s]
 85%|████████▍ | 48823/57600 [8:35:17<1:29:46,  1.63it/s]
 85%|████████▍ | 48824/57600 [8:35:18<1:34:20,  1.55it/s]
 85%|████████▍ | 48825/57600 [8:35:19<1:36:49,  1.51it/s]
 85%|████████▍ | 48826/57600 [8:35:19<1:36:59,  1.51it/s]
 85%|████████▍ | 48827/57600 [8:35:20<1:35:59,  1.52it/s]
 85%|████████▍ | 48828/57600 [8:35:20<1:34:22,  1.55it/s]
 85%|████████▍ | 48829/57600 [8:35:21<1:33:08,  1.57it/s]
 85%|████████▍ | 48830/57600 [8:35:22<1:32:23,  1.58it/s]
 85%|████████▍ | 48831/57600 [8:35:22<1:33:32,  1.56it/s]
 85%|████████▍ | 48832/57600 [8:35:23<1:32:25,  1.58it/s]
 85%|████████▍ | 48833/57600 [8:35:24<1:32:18,  1.58it/s]
 85%|████████▍ | 48834/57600 [8:35:24<1:35:17,  1.53it/s]
 85%|████████▍ | 48835/57600 [8:35:25<1:32:10,  1.58it/s]
 85%|████████▍ | 48836/57600 [8:35:25<1:29:59,  1.62it/s]
 85%|████████▍ | 48837/57600 [8:35:26<1:33:11,  1.57it/s]
 85%|████████▍ | 48838/57600 [8:35:27<1:30:53,  1.61it/s]
 85%|████████▍ | 48839/57600 [8:35:27<1:29:05,  1.64it/s]
 85%|████████▍ | 48840/57600 [8:35:28<1:28:19,  1.65it/s]
                                                         
{'loss': 1.1054, 'learning_rate': 2.3735191637630657e-07, 'epoch': 539.07}

 85%|████████▍ | 48840/57600 [8:35:28<1:28:19,  1.65it/s]
 85%|████████▍ | 48841/57600 [8:35:28<1:26:16,  1.69it/s]
 85%|████████▍ | 48842/57600 [8:35:29<1:30:12,  1.62it/s]
 85%|████████▍ | 48843/57600 [8:35:30<1:28:37,  1.65it/s]
 85%|████████▍ | 48844/57600 [8:35:30<1:29:31,  1.63it/s]
 85%|████████▍ | 48845/57600 [8:35:31<1:27:46,  1.66it/s]
 85%|████████▍ | 48846/57600 [8:35:32<1:27:02,  1.68it/s]
 85%|████████▍ | 48847/57600 [8:35:32<1:29:28,  1.63it/s]
 85%|████████▍ | 48848/57600 [8:35:33<1:30:46,  1.61it/s]
 85%|████████▍ | 48849/57600 [8:35:33<1:32:28,  1.58it/s]
 85%|████████▍ | 48850/57600 [8:35:34<1:29:54,  1.62it/s]
 85%|████████▍ | 48851/57600 [8:35:35<1:32:05,  1.58it/s]
 85%|████████▍ | 48852/57600 [8:35:35<1:32:10,  1.58it/s]
 85%|████████▍ | 48853/57600 [8:35:36<1:31:52,  1.59it/s]
 85%|████████▍ | 48854/57600 [8:35:37<1:30:33,  1.61it/s]
 85%|████████▍ | 48855/57600 [8:35:37<1:31:02,  1.60it/s]
 85%|████████▍ | 48856/57600 [8:35:38<1:30:07,  1.62it/s]
 85%|████████▍ | 48857/57600 [8:35:38<1:31:14,  1.60it/s]
 85%|████████▍ | 48858/57600 [8:35:39<1:31:34,  1.59it/s]
 85%|████████▍ | 48859/57600 [8:35:40<1:32:01,  1.58it/s]
 85%|████████▍ | 48860/57600 [8:35:40<1:36:03,  1.52it/s]
                                                         
{'loss': 1.1439, 'learning_rate': 2.3703832752613237e-07, 'epoch': 539.29}

 85%|████████▍ | 48860/57600 [8:35:40<1:36:03,  1.52it/s]
 85%|████████▍ | 48861/57600 [8:35:41<1:37:13,  1.50it/s]
 85%|████████▍ | 48862/57600 [8:35:42<1:36:39,  1.51it/s]
 85%|████████▍ | 48863/57600 [8:35:42<1:35:55,  1.52it/s]
 85%|████████▍ | 48864/57600 [8:35:43<1:36:12,  1.51it/s]
 85%|████████▍ | 48865/57600 [8:35:44<1:35:06,  1.53it/s]
 85%|████████▍ | 48866/57600 [8:35:44<1:32:44,  1.57it/s]
 85%|████████▍ | 48867/57600 [8:35:45<1:32:30,  1.57it/s]
 85%|████████▍ | 48868/57600 [8:35:46<1:32:57,  1.57it/s]
 85%|████████▍ | 48869/57600 [8:35:46<1:32:17,  1.58it/s]
 85%|████████▍ | 48870/57600 [8:35:47<1:29:22,  1.63it/s]
 85%|████████▍ | 48871/57600 [8:35:47<1:29:54,  1.62it/s]
 85%|████████▍ | 48872/57600 [8:35:48<1:33:54,  1.55it/s]
 85%|████████▍ | 48873/57600 [8:35:49<1:32:01,  1.58it/s]
 85%|████████▍ | 48874/57600 [8:35:49<1:29:07,  1.63it/s]
 85%|████████▍ | 48875/57600 [8:35:50<1:34:57,  1.53it/s]
 85%|████████▍ | 48876/57600 [8:35:51<1:34:58,  1.53it/s]
 85%|████████▍ | 48877/57600 [8:35:51<1:33:32,  1.55it/s]
 85%|████████▍ | 48878/57600 [8:35:52<1:32:54,  1.56it/s]
 85%|████████▍ | 48879/57600 [8:35:53<1:34:02,  1.55it/s]
 85%|████████▍ | 48880/57600 [8:35:53<1:34:29,  1.54it/s]
                                                         
{'loss': 1.08, 'learning_rate': 2.367247386759582e-07, 'epoch': 539.51}

 85%|████████▍ | 48880/57600 [8:35:53<1:34:29,  1.54it/s]
 85%|████████▍ | 48881/57600 [8:35:54<1:33:39,  1.55it/s]
 85%|████████▍ | 48882/57600 [8:35:55<1:32:03,  1.58it/s]
 85%|████████▍ | 48883/57600 [8:35:55<1:32:01,  1.58it/s]
 85%|████████▍ | 48884/57600 [8:35:56<1:32:34,  1.57it/s]
 85%|████████▍ | 48885/57600 [8:35:56<1:33:52,  1.55it/s]
 85%|████████▍ | 48886/57600 [8:35:57<1:31:22,  1.59it/s]
 85%|████████▍ | 48887/57600 [8:35:58<1:30:23,  1.61it/s]
 85%|████████▍ | 48888/57600 [8:35:58<1:27:38,  1.66it/s]
 85%|████████▍ | 48889/57600 [8:35:59<1:26:08,  1.69it/s]
 85%|████████▍ | 48890/57600 [8:35:59<1:27:56,  1.65it/s]
 85%|████████▍ | 48891/57600 [8:36:00<1:27:35,  1.66it/s]
 85%|████████▍ | 48892/57600 [8:36:01<1:28:01,  1.65it/s]
 85%|████████▍ | 48893/57600 [8:36:01<1:27:19,  1.66it/s]
 85%|████████▍ | 48894/57600 [8:36:02<1:32:21,  1.57it/s]
 85%|████████▍ | 48895/57600 [8:36:03<1:30:07,  1.61it/s]
 85%|████████▍ | 48896/57600 [8:36:03<1:26:38,  1.67it/s]
 85%|████████▍ | 48897/57600 [8:36:04<1:27:26,  1.66it/s]
 85%|████████▍ | 48898/57600 [8:36:04<1:26:16,  1.68it/s]
 85%|████████▍ | 48899/57600 [8:36:05<1:29:33,  1.62it/s]
 85%|████████▍ | 48900/57600 [8:36:06<1:28:29,  1.64it/s]
                                                         
{'loss': 1.1405, 'learning_rate': 2.364111498257839e-07, 'epoch': 539.74}

 85%|████████▍ | 48900/57600 [8:36:06<1:28:29,  1.64it/s]
 85%|████████▍ | 48901/57600 [8:36:06<1:30:27,  1.60it/s]
 85%|████████▍ | 48902/57600 [8:36:07<1:29:12,  1.63it/s]
 85%|████████▍ | 48903/57600 [8:36:07<1:29:45,  1.61it/s]
 85%|████████▍ | 48904/57600 [8:36:08<1:29:30,  1.62it/s]
 85%|████████▍ | 48905/57600 [8:36:09<1:32:09,  1.57it/s]
 85%|████████▍ | 48906/57600 [8:36:09<1:33:15,  1.55it/s]
 85%|████████▍ | 48907/57600 [8:36:10<1:30:58,  1.59it/s]
 85%|████████▍ | 48908/57600 [8:36:11<1:31:46,  1.58it/s]
 85%|████████▍ | 48909/57600 [8:36:11<1:36:08,  1.51it/s]
 85%|████████▍ | 48910/57600 [8:36:12<1:31:43,  1.58it/s]
 85%|████████▍ | 48911/57600 [8:36:13<1:35:54,  1.51it/s]
 85%|████████▍ | 48912/57600 [8:36:13<1:34:52,  1.53it/s]
 85%|████████▍ | 48913/57600 [8:36:14<1:32:43,  1.56it/s]
 85%|████████▍ | 48914/57600 [8:36:14<1:30:48,  1.59it/s]
 85%|████████▍ | 48915/57600 [8:36:15<1:30:52,  1.59it/s]
 85%|████████▍ | 48916/57600 [8:36:16<1:32:13,  1.57it/s]
 85%|████████▍ | 48917/57600 [8:36:16<1:33:30,  1.55it/s]
 85%|████████▍ | 48918/57600 [8:36:17<1:30:51,  1.59it/s]
 85%|████████▍ | 48919/57600 [8:36:18<1:34:14,  1.54it/s]
 85%|████████▍ | 48920/57600 [8:36:18<1:37:33,  1.48it/s]
                                                         
{'loss': 1.0862, 'learning_rate': 2.3609756097560976e-07, 'epoch': 539.96}

 85%|████████▍ | 48920/57600 [8:36:18<1:37:33,  1.48it/s]
 85%|████████▍ | 48921/57600 [8:36:19<1:36:50,  1.49it/s]
 85%|████████▍ | 48922/57600 [8:36:20<1:32:45,  1.56it/s]
 85%|████████▍ | 48923/57600 [8:36:20<1:34:10,  1.54it/s]
 85%|████████▍ | 48924/57600 [8:36:21<1:30:32,  1.60it/s]
 85%|████████▍ | 48925/57600 [8:36:22<1:32:06,  1.57it/s]
 85%|████████▍ | 48926/57600 [8:36:22<1:34:05,  1.54it/s]
 85%|████████▍ | 48927/57600 [8:36:23<1:32:17,  1.57it/s]
 85%|████████▍ | 48928/57600 [8:36:24<1:31:45,  1.58it/s]
 85%|████████▍ | 48929/57600 [8:36:24<1:30:30,  1.60it/s]
 85%|████████▍ | 48930/57600 [8:36:25<1:31:13,  1.58it/s]
 85%|████████▍ | 48931/57600 [8:36:25<1:31:56,  1.57it/s]
 85%|████████▍ | 48932/57600 [8:36:26<1:33:28,  1.55it/s]
 85%|████████▍ | 48933/57600 [8:36:27<1:33:23,  1.55it/s]
 85%|████████▍ | 48934/57600 [8:36:27<1:31:43,  1.57it/s]
 85%|████████▍ | 48935/57600 [8:36:28<1:31:28,  1.58it/s]
 85%|████████▍ | 48936/57600 [8:36:29<1:31:04,  1.59it/s]
 85%|████████▍ | 48937/57600 [8:36:29<1:30:01,  1.60it/s]
 85%|████████▍ | 48938/57600 [8:36:30<1:29:36,  1.61it/s]
 85%|████████▍ | 48939/57600 [8:36:30<1:30:48,  1.59it/s]
 85%|████████▍ | 48940/57600 [8:36:31<1:33:10,  1.55it/s]
                                                         
{'loss': 1.1428, 'learning_rate': 2.357839721254355e-07, 'epoch': 540.18}

 85%|████████▍ | 48940/57600 [8:36:31<1:33:10,  1.55it/s]
 85%|████████▍ | 48941/57600 [8:36:32<1:34:18,  1.53it/s]
 85%|████████▍ | 48942/57600 [8:36:32<1:34:44,  1.52it/s]
 85%|████████▍ | 48943/57600 [8:36:33<1:31:26,  1.58it/s]
 85%|████████▍ | 48944/57600 [8:36:34<1:29:32,  1.61it/s]
 85%|████████▍ | 48945/57600 [8:36:34<1:29:58,  1.60it/s]
 85%|████████▍ | 48946/57600 [8:36:35<1:31:42,  1.57it/s]
 85%|████████▍ | 48947/57600 [8:36:36<1:30:31,  1.59it/s]
 85%|████████▍ | 48948/57600 [8:36:36<1:31:47,  1.57it/s]
 85%|████████▍ | 48949/57600 [8:36:37<1:29:03,  1.62it/s]
 85%|████████▍ | 48950/57600 [8:36:37<1:30:42,  1.59it/s]
 85%|████████▍ | 48951/57600 [8:36:38<1:32:33,  1.56it/s]
 85%|████████▍ | 48952/57600 [8:36:39<1:33:04,  1.55it/s]
 85%|████████▍ | 48953/57600 [8:36:39<1:33:16,  1.55it/s]
 85%|████████▍ | 48954/57600 [8:36:40<1:32:28,  1.56it/s]
 85%|████████▍ | 48955/57600 [8:36:41<1:29:38,  1.61it/s]
 85%|████████▍ | 48956/57600 [8:36:41<1:29:32,  1.61it/s]
 85%|████████▍ | 48957/57600 [8:36:42<1:31:23,  1.58it/s]
 85%|████████▍ | 48958/57600 [8:36:43<1:32:29,  1.56it/s]
 85%|████████▍ | 48959/57600 [8:36:43<1:32:47,  1.55it/s]
 85%|████████▌ | 48960/57600 [8:36:44<1:31:51,  1.57it/s]
                                                         
{'loss': 1.1379, 'learning_rate': 2.3547038327526132e-07, 'epoch': 540.4}

 85%|████████▌ | 48960/57600 [8:36:44<1:31:51,  1.57it/s]
 85%|████████▌ | 48961/57600 [8:36:45<1:34:00,  1.53it/s]
 85%|████████▌ | 48962/57600 [8:36:45<1:32:19,  1.56it/s]
 85%|████████▌ | 48963/57600 [8:36:46<1:30:05,  1.60it/s]
 85%|████████▌ | 48964/57600 [8:36:46<1:32:11,  1.56it/s]
 85%|████████▌ | 48965/57600 [8:36:47<1:28:34,  1.62it/s]
 85%|████████▌ | 48966/57600 [8:36:48<1:29:14,  1.61it/s]
 85%|████████▌ | 48967/57600 [8:36:48<1:29:14,  1.61it/s]
 85%|████████▌ | 48968/57600 [8:36:49<1:32:02,  1.56it/s]
 85%|████████▌ | 48969/57600 [8:36:50<1:36:18,  1.49it/s]
 85%|████████▌ | 48970/57600 [8:36:50<1:33:54,  1.53it/s]
 85%|████████▌ | 48971/57600 [8:36:51<1:29:52,  1.60it/s]
 85%|████████▌ | 48972/57600 [8:36:51<1:28:12,  1.63it/s]
 85%|████████▌ | 48973/57600 [8:36:52<1:32:02,  1.56it/s]
 85%|████████▌ | 48974/57600 [8:36:53<1:31:30,  1.57it/s]
 85%|████████▌ | 48975/57600 [8:36:53<1:31:59,  1.56it/s]
 85%|████████▌ | 48976/57600 [8:36:54<1:29:56,  1.60it/s]
 85%|████████▌ | 48977/57600 [8:36:55<1:34:00,  1.53it/s]
 85%|████████▌ | 48978/57600 [8:36:55<1:31:24,  1.57it/s]
 85%|████████▌ | 48979/57600 [8:36:56<1:29:55,  1.60it/s]
 85%|████████▌ | 48980/57600 [8:36:56<1:28:29,  1.62it/s]
                                                         
{'loss': 1.1155, 'learning_rate': 2.3515679442508715e-07, 'epoch': 540.62}

 85%|████████▌ | 48980/57600 [8:36:56<1:28:29,  1.62it/s]
 85%|████████▌ | 48981/57600 [8:36:57<1:29:02,  1.61it/s]
 85%|████████▌ | 48982/57600 [8:36:58<1:27:41,  1.64it/s]
 85%|████████▌ | 48983/57600 [8:36:58<1:26:39,  1.66it/s]
 85%|████████▌ | 48984/57600 [8:36:59<1:31:34,  1.57it/s]
 85%|████████▌ | 48985/57600 [8:37:00<1:35:37,  1.50it/s]
 85%|████████▌ | 48986/57600 [8:37:00<1:32:17,  1.56it/s]
 85%|████████▌ | 48987/57600 [8:37:01<1:33:29,  1.54it/s]
 85%|████████▌ | 48988/57600 [8:37:02<1:32:25,  1.55it/s]
 85%|████████▌ | 48989/57600 [8:37:02<1:32:18,  1.55it/s]
 85%|████████▌ | 48990/57600 [8:37:03<1:35:18,  1.51it/s]
 85%|████████▌ | 48991/57600 [8:37:04<1:34:02,  1.53it/s]
 85%|████████▌ | 48992/57600 [8:37:04<1:34:30,  1.52it/s]
 85%|████████▌ | 48993/57600 [8:37:05<1:31:31,  1.57it/s]
 85%|████████▌ | 48994/57600 [8:37:05<1:29:11,  1.61it/s]
 85%|████████▌ | 48995/57600 [8:37:06<1:31:58,  1.56it/s]
 85%|████████▌ | 48996/57600 [8:37:07<1:30:25,  1.59it/s]
 85%|████████▌ | 48997/57600 [8:37:07<1:30:25,  1.59it/s]
 85%|████████▌ | 48998/57600 [8:37:08<1:28:39,  1.62it/s]
 85%|████████▌ | 48999/57600 [8:37:09<1:28:59,  1.61it/s]
 85%|████████▌ | 49000/57600 [8:37:09<1:27:58,  1.63it/s]
                                                         
{'loss': 1.0901, 'learning_rate': 2.3484320557491288e-07, 'epoch': 540.84}

 85%|████████▌ | 49000/57600 [8:37:09<1:27:58,  1.63it/s]
 85%|████████▌ | 49001/57600 [8:37:10<1:25:17,  1.68it/s]
 85%|████████▌ | 49002/57600 [8:37:10<1:25:03,  1.68it/s]
 85%|████████▌ | 49003/57600 [8:37:11<1:25:52,  1.67it/s]
 85%|████████▌ | 49004/57600 [8:37:12<1:26:40,  1.65it/s]
 85%|████████▌ | 49005/57600 [8:37:12<1:27:07,  1.64it/s]
 85%|████████▌ | 49006/57600 [8:37:13<1:29:53,  1.59it/s]
 85%|████████▌ | 49007/57600 [8:37:13<1:30:17,  1.59it/s]
 85%|████████▌ | 49008/57600 [8:37:14<1:31:36,  1.56it/s]
 85%|████████▌ | 49009/57600 [8:37:15<1:30:38,  1.58it/s]
 85%|████████▌ | 49010/57600 [8:37:15<1:30:29,  1.58it/s]
 85%|████████▌ | 49011/57600 [8:37:16<1:30:08,  1.59it/s]
 85%|████████▌ | 49012/57600 [8:37:17<1:28:11,  1.62it/s]
 85%|████████▌ | 49013/57600 [8:37:17<1:28:26,  1.62it/s]
 85%|████████▌ | 49014/57600 [8:37:18<1:27:14,  1.64it/s]
 85%|████████▌ | 49015/57600 [8:37:19<1:32:28,  1.55it/s]
 85%|████████▌ | 49016/57600 [8:37:19<1:32:56,  1.54it/s]
 85%|████████▌ | 49017/57600 [8:37:20<1:32:37,  1.54it/s]
 85%|████████▌ | 49018/57600 [8:37:20<1:31:20,  1.57it/s]
 85%|████████▌ | 49019/57600 [8:37:21<1:29:05,  1.61it/s]
 85%|████████▌ | 49020/57600 [8:37:22<1:28:11,  1.62it/s]
                                                         
{'loss': 1.1415, 'learning_rate': 2.345296167247387e-07, 'epoch': 541.06}

 85%|████████▌ | 49020/57600 [8:37:22<1:28:11,  1.62it/s]
 85%|████████▌ | 49021/57600 [8:37:22<1:26:55,  1.64it/s]
 85%|████████▌ | 49022/57600 [8:37:23<1:30:00,  1.59it/s]
 85%|████████▌ | 49023/57600 [8:37:24<1:28:26,  1.62it/s]
 85%|████████▌ | 49024/57600 [8:37:24<1:28:01,  1.62it/s]
 85%|████████▌ | 49025/57600 [8:37:25<1:31:04,  1.57it/s]
 85%|████████▌ | 49026/57600 [8:37:25<1:30:01,  1.59it/s]
 85%|████████▌ | 49027/57600 [8:37:26<1:29:10,  1.60it/s]
 85%|████████▌ | 49028/57600 [8:37:27<1:29:17,  1.60it/s]
 85%|████████▌ | 49029/57600 [8:37:27<1:29:58,  1.59it/s]
 85%|████████▌ | 49030/57600 [8:37:28<1:29:30,  1.60it/s]
 85%|████████▌ | 49031/57600 [8:37:29<1:30:11,  1.58it/s]
 85%|████████▌ | 49032/57600 [8:37:29<1:31:59,  1.55it/s]
 85%|████████▌ | 49033/57600 [8:37:30<1:30:02,  1.59it/s]
 85%|████████▌ | 49034/57600 [8:37:30<1:27:20,  1.63it/s]
 85%|████████▌ | 49035/57600 [8:37:31<1:27:33,  1.63it/s]
 85%|████████▌ | 49036/57600 [8:37:32<1:26:47,  1.64it/s]
 85%|████████▌ | 49037/57600 [8:37:32<1:29:49,  1.59it/s]
 85%|████████▌ | 49038/57600 [8:37:33<1:29:47,  1.59it/s]
 85%|████████▌ | 49039/57600 [8:37:34<1:30:10,  1.58it/s]
 85%|████████▌ | 49040/57600 [8:37:34<1:31:11,  1.56it/s]
                                                         
{'loss': 1.1008, 'learning_rate': 2.3421602787456443e-07, 'epoch': 541.28}

 85%|████████▌ | 49040/57600 [8:37:34<1:31:11,  1.56it/s]
 85%|████████▌ | 49041/57600 [8:37:35<1:32:55,  1.54it/s]
 85%|████████▌ | 49042/57600 [8:37:36<1:31:13,  1.56it/s]
 85%|████████▌ | 49043/57600 [8:37:36<1:32:50,  1.54it/s]
 85%|████████▌ | 49044/57600 [8:37:37<1:30:33,  1.57it/s]
 85%|████████▌ | 49045/57600 [8:37:37<1:30:35,  1.57it/s]
 85%|████████▌ | 49046/57600 [8:37:38<1:34:57,  1.50it/s]
 85%|████████▌ | 49047/57600 [8:37:39<1:33:14,  1.53it/s]
 85%|████████▌ | 49048/57600 [8:37:39<1:31:15,  1.56it/s]
 85%|████████▌ | 49049/57600 [8:37:40<1:32:36,  1.54it/s]
 85%|████████▌ | 49050/57600 [8:37:41<1:34:03,  1.51it/s]
 85%|████████▌ | 49051/57600 [8:37:41<1:31:17,  1.56it/s]
 85%|████████▌ | 49052/57600 [8:37:42<1:33:22,  1.53it/s]
 85%|████████▌ | 49053/57600 [8:37:43<1:31:10,  1.56it/s]
 85%|████████▌ | 49054/57600 [8:37:43<1:30:34,  1.57it/s]
 85%|████████▌ | 49055/57600 [8:37:44<1:29:30,  1.59it/s]
 85%|████████▌ | 49056/57600 [8:37:44<1:28:05,  1.62it/s]
 85%|████████▌ | 49057/57600 [8:37:45<1:28:23,  1.61it/s]
 85%|████████▌ | 49058/57600 [8:37:46<1:30:54,  1.57it/s]
 85%|████████▌ | 49059/57600 [8:37:46<1:29:34,  1.59it/s]
 85%|████████▌ | 49060/57600 [8:37:47<1:28:48,  1.60it/s]
                                                         
{'loss': 1.1034, 'learning_rate': 2.3390243902439026e-07, 'epoch': 541.5}

 85%|████████▌ | 49060/57600 [8:37:47<1:28:48,  1.60it/s]
 85%|████████▌ | 49061/57600 [8:37:48<1:29:25,  1.59it/s]
 85%|████████▌ | 49062/57600 [8:37:48<1:26:18,  1.65it/s]
 85%|████████▌ | 49063/57600 [8:37:49<1:30:27,  1.57it/s]
 85%|████████▌ | 49064/57600 [8:37:50<1:33:00,  1.53it/s]
 85%|████████▌ | 49065/57600 [8:37:50<1:30:28,  1.57it/s]
 85%|████████▌ | 49066/57600 [8:37:51<1:29:18,  1.59it/s]
 85%|████████▌ | 49067/57600 [8:37:51<1:26:53,  1.64it/s]
 85%|████████▌ | 49068/57600 [8:37:52<1:28:03,  1.61it/s]
 85%|████████▌ | 49069/57600 [8:37:53<1:30:56,  1.56it/s]
 85%|████████▌ | 49070/57600 [8:37:53<1:27:53,  1.62it/s]
 85%|████████▌ | 49071/57600 [8:37:54<1:27:38,  1.62it/s]
 85%|████████▌ | 49072/57600 [8:37:54<1:26:44,  1.64it/s]
 85%|████████▌ | 49073/57600 [8:37:55<1:24:48,  1.68it/s]
 85%|████████▌ | 49074/57600 [8:37:56<1:25:58,  1.65it/s]
 85%|████████▌ | 49075/57600 [8:37:56<1:27:07,  1.63it/s]
 85%|████████▌ | 49076/57600 [8:37:57<1:27:14,  1.63it/s]
 85%|████████▌ | 49077/57600 [8:37:58<1:29:52,  1.58it/s]
 85%|████████▌ | 49078/57600 [8:37:58<1:31:58,  1.54it/s]
 85%|████████▌ | 49079/57600 [8:37:59<1:30:30,  1.57it/s]
 85%|████████▌ | 49080/57600 [8:37:59<1:28:06,  1.61it/s]
                                                         
{'loss': 1.0984, 'learning_rate': 2.33588850174216e-07, 'epoch': 541.72}

 85%|████████▌ | 49080/57600 [8:37:59<1:28:06,  1.61it/s]
 85%|████████▌ | 49081/57600 [8:38:00<1:26:52,  1.63it/s]
 85%|████████▌ | 49082/57600 [8:38:01<1:29:29,  1.59it/s]
 85%|████████▌ | 49083/57600 [8:38:01<1:28:19,  1.61it/s]
 85%|████████▌ | 49084/57600 [8:38:02<1:26:05,  1.65it/s]
 85%|████████▌ | 49085/57600 [8:38:03<1:26:45,  1.64it/s]
 85%|████████▌ | 49086/57600 [8:38:03<1:27:10,  1.63it/s]
 85%|████████▌ | 49087/57600 [8:38:04<1:25:15,  1.66it/s]
 85%|████████▌ | 49088/57600 [8:38:04<1:25:50,  1.65it/s]
 85%|████████▌ | 49089/57600 [8:38:05<1:29:55,  1.58it/s]
 85%|████████▌ | 49090/57600 [8:38:06<1:29:49,  1.58it/s]
 85%|████████▌ | 49091/57600 [8:38:06<1:33:50,  1.51it/s]
 85%|████████▌ | 49092/57600 [8:38:07<1:33:32,  1.52it/s]
 85%|████████▌ | 49093/57600 [8:38:08<1:29:55,  1.58it/s]
 85%|████████▌ | 49094/57600 [8:38:08<1:32:17,  1.54it/s]
 85%|████████▌ | 49095/57600 [8:38:09<1:32:17,  1.54it/s]
 85%|████████▌ | 49096/57600 [8:38:10<1:28:26,  1.60it/s]
 85%|████████▌ | 49097/57600 [8:38:10<1:28:01,  1.61it/s]
 85%|████████▌ | 49098/57600 [8:38:11<1:27:56,  1.61it/s]
 85%|████████▌ | 49099/57600 [8:38:11<1:27:30,  1.62it/s]
 85%|████████▌ | 49100/57600 [8:38:12<1:27:12,  1.62it/s]
                                                         
{'loss': 1.1269, 'learning_rate': 2.332752613240418e-07, 'epoch': 541.94}

 85%|████████▌ | 49100/57600 [8:38:12<1:27:12,  1.62it/s]
 85%|████████▌ | 49101/57600 [8:38:13<1:25:47,  1.65it/s]
 85%|████████▌ | 49102/57600 [8:38:13<1:26:50,  1.63it/s]
 85%|████████▌ | 49103/57600 [8:38:14<1:27:24,  1.62it/s]
 85%|████████▌ | 49104/57600 [8:38:14<1:26:42,  1.63it/s]
 85%|████████▌ | 49105/57600 [8:38:15<1:25:23,  1.66it/s]
 85%|████████▌ | 49106/57600 [8:38:16<1:30:25,  1.57it/s]
 85%|████████▌ | 49107/57600 [8:38:16<1:32:12,  1.54it/s]
 85%|████████▌ | 49108/57600 [8:38:17<1:31:10,  1.55it/s]
 85%|████████▌ | 49109/57600 [8:38:18<1:27:59,  1.61it/s]
 85%|████████▌ | 49110/57600 [8:38:18<1:27:34,  1.62it/s]
 85%|████████▌ | 49111/57600 [8:38:19<1:27:26,  1.62it/s]
 85%|████████▌ | 49112/57600 [8:38:19<1:27:34,  1.62it/s]
 85%|████████▌ | 49113/57600 [8:38:20<1:30:38,  1.56it/s]
 85%|████████▌ | 49114/57600 [8:38:21<1:31:06,  1.55it/s]
 85%|████████▌ | 49115/57600 [8:38:21<1:29:48,  1.57it/s]
 85%|████████▌ | 49116/57600 [8:38:22<1:28:02,  1.61it/s]
 85%|████████▌ | 49117/57600 [8:38:23<1:25:32,  1.65it/s]
 85%|████████▌ | 49118/57600 [8:38:23<1:25:25,  1.65it/s]
 85%|████████▌ | 49119/57600 [8:38:24<1:28:05,  1.60it/s]
 85%|████████▌ | 49120/57600 [8:38:24<1:29:07,  1.59it/s]
                                                         
{'loss': 1.1275, 'learning_rate': 2.3296167247386763e-07, 'epoch': 542.16}

 85%|████████▌ | 49120/57600 [8:38:24<1:29:07,  1.59it/s]
 85%|████████▌ | 49121/57600 [8:38:25<1:30:04,  1.57it/s]
 85%|████████▌ | 49122/57600 [8:38:26<1:29:14,  1.58it/s]
 85%|████████▌ | 49123/57600 [8:38:26<1:31:08,  1.55it/s]
 85%|████████▌ | 49124/57600 [8:38:27<1:31:34,  1.54it/s]
 85%|████████▌ | 49125/57600 [8:38:28<1:27:55,  1.61it/s]
 85%|████████▌ | 49126/57600 [8:38:28<1:26:41,  1.63it/s]
 85%|████████▌ | 49127/57600 [8:38:29<1:27:05,  1.62it/s]
 85%|████████▌ | 49128/57600 [8:38:29<1:27:12,  1.62it/s]
 85%|████████▌ | 49129/57600 [8:38:30<1:27:53,  1.61it/s]
 85%|████████▌ | 49130/57600 [8:38:31<1:26:07,  1.64it/s]
 85%|████████▌ | 49131/57600 [8:38:31<1:24:16,  1.67it/s]
 85%|████████▌ | 49132/57600 [8:38:32<1:23:44,  1.69it/s]
 85%|████████▌ | 49133/57600 [8:38:33<1:26:04,  1.64it/s]
 85%|████████▌ | 49134/57600 [8:38:33<1:26:39,  1.63it/s]
 85%|████████▌ | 49135/57600 [8:38:34<1:29:42,  1.57it/s]
 85%|████████▌ | 49136/57600 [8:38:35<1:31:56,  1.53it/s]
 85%|████████▌ | 49137/57600 [8:38:35<1:32:21,  1.53it/s]
 85%|████████▌ | 49138/57600 [8:38:36<1:29:36,  1.57it/s]
 85%|████████▌ | 49139/57600 [8:38:36<1:30:08,  1.56it/s]
 85%|████████▌ | 49140/57600 [8:38:37<1:30:51,  1.55it/s]
                                                         
{'loss': 1.0807, 'learning_rate': 2.3264808362369335e-07, 'epoch': 542.38}

 85%|████████▌ | 49140/57600 [8:38:37<1:30:51,  1.55it/s]
 85%|████████▌ | 49141/57600 [8:38:38<1:29:42,  1.57it/s]
 85%|████████▌ | 49142/57600 [8:38:38<1:28:44,  1.59it/s]
 85%|████████▌ | 49143/57600 [8:38:39<1:29:17,  1.58it/s]
 85%|████████▌ | 49144/57600 [8:38:40<1:29:40,  1.57it/s]
 85%|████████▌ | 49145/57600 [8:38:40<1:27:15,  1.61it/s]
 85%|████████▌ | 49146/57600 [8:38:41<1:27:44,  1.61it/s]
 85%|████████▌ | 49147/57600 [8:38:41<1:28:09,  1.60it/s]
 85%|████████▌ | 49148/57600 [8:38:42<1:25:33,  1.65it/s]
 85%|████████▌ | 49149/57600 [8:38:43<1:24:40,  1.66it/s]
 85%|████████▌ | 49150/57600 [8:38:43<1:24:54,  1.66it/s]
 85%|████████▌ | 49151/57600 [8:38:44<1:25:33,  1.65it/s]
 85%|████████▌ | 49152/57600 [8:38:44<1:28:48,  1.59it/s]
 85%|████████▌ | 49153/57600 [8:38:45<1:31:52,  1.53it/s]
 85%|████████▌ | 49154/57600 [8:38:46<1:28:16,  1.59it/s]
 85%|████████▌ | 49155/57600 [8:38:46<1:29:52,  1.57it/s]
 85%|████████▌ | 49156/57600 [8:38:47<1:28:16,  1.59it/s]
 85%|████████▌ | 49157/57600 [8:38:48<1:30:11,  1.56it/s]
 85%|████████▌ | 49158/57600 [8:38:48<1:30:22,  1.56it/s]
 85%|████████▌ | 49159/57600 [8:38:49<1:33:09,  1.51it/s]
 85%|████████▌ | 49160/57600 [8:38:50<1:34:16,  1.49it/s]
                                                         
{'loss': 1.1037, 'learning_rate': 2.3233449477351918e-07, 'epoch': 542.6}

 85%|████████▌ | 49160/57600 [8:38:50<1:34:16,  1.49it/s]
 85%|████████▌ | 49161/57600 [8:38:50<1:31:11,  1.54it/s]
 85%|████████▌ | 49162/57600 [8:38:51<1:32:23,  1.52it/s]
 85%|████████▌ | 49163/57600 [8:38:52<1:29:56,  1.56it/s]
 85%|████████▌ | 49164/57600 [8:38:52<1:29:56,  1.56it/s]
 85%|████████▌ | 49165/57600 [8:38:53<1:31:27,  1.54it/s]
 85%|████████▌ | 49166/57600 [8:38:54<1:29:00,  1.58it/s]
 85%|████████▌ | 49167/57600 [8:38:54<1:27:10,  1.61it/s]
 85%|████████▌ | 49168/57600 [8:38:55<1:27:10,  1.61it/s]
 85%|████████▌ | 49169/57600 [8:38:55<1:26:05,  1.63it/s]
 85%|████████▌ | 49170/57600 [8:38:56<1:28:11,  1.59it/s]
 85%|████████▌ | 49171/57600 [8:38:57<1:31:36,  1.53it/s]
 85%|████████▌ | 49172/57600 [8:38:57<1:32:50,  1.51it/s]
 85%|████████▌ | 49173/57600 [8:38:58<1:31:19,  1.54it/s]
 85%|████████▌ | 49174/57600 [8:38:59<1:28:58,  1.58it/s]
 85%|████████▌ | 49175/57600 [8:38:59<1:29:00,  1.58it/s]
 85%|████████▌ | 49176/57600 [8:39:00<1:28:56,  1.58it/s]
 85%|████████▌ | 49177/57600 [8:39:00<1:26:31,  1.62it/s]
 85%|████████▌ | 49178/57600 [8:39:01<1:25:36,  1.64it/s]
 85%|████████▌ | 49179/57600 [8:39:02<1:26:08,  1.63it/s]
 85%|████████▌ | 49180/57600 [8:39:02<1:23:41,  1.68it/s]
                                                         
{'loss': 1.1319, 'learning_rate': 2.320209059233449e-07, 'epoch': 542.83}

 85%|████████▌ | 49180/57600 [8:39:02<1:23:41,  1.68it/s]
 85%|████████▌ | 49181/57600 [8:39:03<1:25:17,  1.65it/s]
 85%|████████▌ | 49182/57600 [8:39:03<1:26:33,  1.62it/s]
 85%|████████▌ | 49183/57600 [8:39:04<1:31:40,  1.53it/s]
 85%|████████▌ | 49184/57600 [8:39:05<1:31:35,  1.53it/s]
 85%|████████▌ | 49185/57600 [8:39:06<1:33:15,  1.50it/s]
 85%|████████▌ | 49186/57600 [8:39:06<1:34:58,  1.48it/s]
 85%|████████▌ | 49187/57600 [8:39:07<1:31:15,  1.54it/s]
 85%|████████▌ | 49188/57600 [8:39:07<1:29:29,  1.57it/s]
 85%|████████▌ | 49189/57600 [8:39:08<1:30:03,  1.56it/s]
 85%|████████▌ | 49190/57600 [8:39:09<1:32:27,  1.52it/s]
 85%|████████▌ | 49191/57600 [8:39:09<1:31:46,  1.53it/s]
 85%|████████▌ | 49192/57600 [8:39:10<1:27:58,  1.59it/s]
 85%|████████▌ | 49193/57600 [8:39:11<1:30:04,  1.56it/s]
 85%|████████▌ | 49194/57600 [8:39:11<1:27:46,  1.60it/s]
 85%|████████▌ | 49195/57600 [8:39:12<1:27:44,  1.60it/s]
 85%|████████▌ | 49196/57600 [8:39:13<1:29:37,  1.56it/s]
 85%|████████▌ | 49197/57600 [8:39:13<1:28:44,  1.58it/s]
 85%|████████▌ | 49198/57600 [8:39:14<1:26:03,  1.63it/s]
 85%|████████▌ | 49199/57600 [8:39:14<1:26:32,  1.62it/s]
 85%|████████▌ | 49200/57600 [8:39:15<1:24:27,  1.66it/s]
                                                         
{'loss': 1.1208, 'learning_rate': 2.3170731707317074e-07, 'epoch': 543.05}

 85%|████████▌ | 49200/57600 [8:39:15<1:24:27,  1.66it/s]
 85%|████████▌ | 49201/57600 [8:39:16<1:23:02,  1.69it/s]
 85%|████████▌ | 49202/57600 [8:39:16<1:25:56,  1.63it/s]
 85%|████████▌ | 49203/57600 [8:39:17<1:25:59,  1.63it/s]
 85%|████████▌ | 49204/57600 [8:39:17<1:24:07,  1.66it/s]
 85%|████████▌ | 49205/57600 [8:39:18<1:28:44,  1.58it/s]
 85%|████████▌ | 49206/57600 [8:39:19<1:28:02,  1.59it/s]
 85%|████████▌ | 49207/57600 [8:39:19<1:27:04,  1.61it/s]
 85%|████████▌ | 49208/57600 [8:39:20<1:28:09,  1.59it/s]
 85%|████████▌ | 49209/57600 [8:39:21<1:28:22,  1.58it/s]
 85%|████████▌ | 49210/57600 [8:39:21<1:27:37,  1.60it/s]
 85%|████████▌ | 49211/57600 [8:39:22<1:29:05,  1.57it/s]
 85%|████████▌ | 49212/57600 [8:39:23<1:29:43,  1.56it/s]
 85%|████████▌ | 49213/57600 [8:39:23<1:25:12,  1.64it/s]
 85%|████████▌ | 49214/57600 [8:39:24<1:27:51,  1.59it/s]
 85%|████████▌ | 49215/57600 [8:39:24<1:27:29,  1.60it/s]
 85%|████████▌ | 49216/57600 [8:39:25<1:26:18,  1.62it/s]
 85%|████████▌ | 49217/57600 [8:39:26<1:26:07,  1.62it/s]
 85%|████████▌ | 49218/57600 [8:39:26<1:25:45,  1.63it/s]
 85%|████████▌ | 49219/57600 [8:39:27<1:26:39,  1.61it/s]
 85%|████████▌ | 49220/57600 [8:39:27<1:24:01,  1.66it/s]
                                                         
{'loss': 1.126, 'learning_rate': 2.3139372822299646e-07, 'epoch': 543.27}

 85%|████████▌ | 49220/57600 [8:39:27<1:24:01,  1.66it/s]
 85%|████████▌ | 49221/57600 [8:39:28<1:25:11,  1.64it/s]
 85%|████████▌ | 49222/57600 [8:39:29<1:26:43,  1.61it/s]
 85%|████████▌ | 49223/57600 [8:39:29<1:27:15,  1.60it/s]
 85%|████████▌ | 49224/57600 [8:39:30<1:24:56,  1.64it/s]
 85%|████████▌ | 49225/57600 [8:39:30<1:24:45,  1.65it/s]
 85%|████████▌ | 49226/57600 [8:39:31<1:26:41,  1.61it/s]
 85%|████████▌ | 49227/57600 [8:39:32<1:25:24,  1.63it/s]
 85%|████████▌ | 49228/57600 [8:39:32<1:25:38,  1.63it/s]
 85%|████████▌ | 49229/57600 [8:39:33<1:25:20,  1.63it/s]
 85%|████████▌ | 49230/57600 [8:39:34<1:23:44,  1.67it/s]
 85%|████████▌ | 49231/57600 [8:39:34<1:23:29,  1.67it/s]
 85%|████████▌ | 49232/57600 [8:39:35<1:25:06,  1.64it/s]
 85%|████████▌ | 49233/57600 [8:39:35<1:25:24,  1.63it/s]
 85%|████████▌ | 49234/57600 [8:39:36<1:28:41,  1.57it/s]
 85%|████████▌ | 49235/57600 [8:39:37<1:29:07,  1.56it/s]
 85%|████████▌ | 49236/57600 [8:39:37<1:27:33,  1.59it/s]
 85%|████████▌ | 49237/57600 [8:39:38<1:30:26,  1.54it/s]
 85%|████████▌ | 49238/57600 [8:39:39<1:29:40,  1.55it/s]
 85%|████████▌ | 49239/57600 [8:39:39<1:28:55,  1.57it/s]
 85%|████████▌ | 49240/57600 [8:39:40<1:27:53,  1.59it/s]
                                                         
{'loss': 1.0764, 'learning_rate': 2.310801393728223e-07, 'epoch': 543.49}

 85%|████████▌ | 49240/57600 [8:39:40<1:27:53,  1.59it/s]
 85%|████████▌ | 49241/57600 [8:39:41<1:28:58,  1.57it/s]
 85%|████████▌ | 49242/57600 [8:39:41<1:28:46,  1.57it/s]
 85%|████████▌ | 49243/57600 [8:39:42<1:28:34,  1.57it/s]
 85%|████████▌ | 49244/57600 [8:39:42<1:28:14,  1.58it/s]
 85%|████████▌ | 49245/57600 [8:39:43<1:27:09,  1.60it/s]
 85%|████████▌ | 49246/57600 [8:39:44<1:27:58,  1.58it/s]
 85%|████████▌ | 49247/57600 [8:39:44<1:27:13,  1.60it/s]
 86%|████████▌ | 49248/57600 [8:39:45<1:25:20,  1.63it/s]
 86%|████████▌ | 49249/57600 [8:39:46<1:26:45,  1.60it/s]
 86%|████████▌ | 49250/57600 [8:39:46<1:27:51,  1.58it/s]
 86%|████████▌ | 49251/57600 [8:39:47<1:26:16,  1.61it/s]
 86%|████████▌ | 49252/57600 [8:39:47<1:25:22,  1.63it/s]
 86%|████████▌ | 49253/57600 [8:39:48<1:24:35,  1.64it/s]
 86%|████████▌ | 49254/57600 [8:39:49<1:24:14,  1.65it/s]
 86%|████████▌ | 49255/57600 [8:39:49<1:25:39,  1.62it/s]
 86%|████████▌ | 49256/57600 [8:39:50<1:24:52,  1.64it/s]
 86%|████████▌ | 49257/57600 [8:39:51<1:29:12,  1.56it/s]
 86%|████████▌ | 49258/57600 [8:39:51<1:30:25,  1.54it/s]
 86%|████████▌ | 49259/57600 [8:39:52<1:31:41,  1.52it/s]
 86%|████████▌ | 49260/57600 [8:39:53<1:33:57,  1.48it/s]
                                                         
{'loss': 1.104, 'learning_rate': 2.3076655052264813e-07, 'epoch': 543.71}

 86%|████████▌ | 49260/57600 [8:39:53<1:33:57,  1.48it/s]
 86%|████████▌ | 49261/57600 [8:39:53<1:32:24,  1.50it/s]
 86%|████████▌ | 49262/57600 [8:39:54<1:29:11,  1.56it/s]
 86%|████████▌ | 49263/57600 [8:39:54<1:26:26,  1.61it/s]
 86%|████████▌ | 49264/57600 [8:39:55<1:26:22,  1.61it/s]
 86%|████████▌ | 49265/57600 [8:39:56<1:28:57,  1.56it/s]
 86%|████████▌ | 49266/57600 [8:39:56<1:26:55,  1.60it/s]
 86%|████████▌ | 49267/57600 [8:39:57<1:26:17,  1.61it/s]
 86%|████████▌ | 49268/57600 [8:39:58<1:26:20,  1.61it/s]
 86%|████████▌ | 49269/57600 [8:39:58<1:25:55,  1.62it/s]
 86%|████████▌ | 49270/57600 [8:39:59<1:27:50,  1.58it/s]
 86%|████████▌ | 49271/57600 [8:39:59<1:29:19,  1.55it/s]
 86%|████████▌ | 49272/57600 [8:40:00<1:28:04,  1.58it/s]
 86%|████████▌ | 49273/57600 [8:40:01<1:28:02,  1.58it/s]
 86%|████████▌ | 49274/57600 [8:40:01<1:26:52,  1.60it/s]
 86%|████████▌ | 49275/57600 [8:40:02<1:25:49,  1.62it/s]
 86%|████████▌ | 49276/57600 [8:40:03<1:27:46,  1.58it/s]
 86%|████████▌ | 49277/57600 [8:40:03<1:29:10,  1.56it/s]
 86%|████████▌ | 49278/57600 [8:40:04<1:29:52,  1.54it/s]
 86%|████████▌ | 49279/57600 [8:40:05<1:29:49,  1.54it/s]
 86%|████████▌ | 49280/57600 [8:40:05<1:26:54,  1.60it/s]
                                                         
{'loss': 1.1319, 'learning_rate': 2.3045296167247385e-07, 'epoch': 543.93}

 86%|████████▌ | 49280/57600 [8:40:05<1:26:54,  1.60it/s]
 86%|████████▌ | 49281/57600 [8:40:06<1:32:09,  1.50it/s]
 86%|████████▌ | 49282/57600 [8:40:07<1:31:00,  1.52it/s]
 86%|████████▌ | 49283/57600 [8:40:07<1:30:55,  1.52it/s]
 86%|████████▌ | 49284/57600 [8:40:08<1:29:17,  1.55it/s]
 86%|████████▌ | 49285/57600 [8:40:08<1:27:04,  1.59it/s]
 86%|████████▌ | 49286/57600 [8:40:09<1:27:57,  1.58it/s]
 86%|████████▌ | 49287/57600 [8:40:10<1:31:04,  1.52it/s]
 86%|████████▌ | 49288/57600 [8:40:10<1:28:53,  1.56it/s]
 86%|████████▌ | 49289/57600 [8:40:11<1:28:02,  1.57it/s]
 86%|████████▌ | 49290/57600 [8:40:12<1:29:40,  1.54it/s]
 86%|████████▌ | 49291/57600 [8:40:12<1:27:50,  1.58it/s]
 86%|████████▌ | 49292/57600 [8:40:13<1:27:34,  1.58it/s]
 86%|████████▌ | 49293/57600 [8:40:14<1:29:06,  1.55it/s]
 86%|████████▌ | 49294/57600 [8:40:14<1:25:24,  1.62it/s]
 86%|████████▌ | 49295/57600 [8:40:15<1:24:00,  1.65it/s]
 86%|████████▌ | 49296/57600 [8:40:15<1:22:34,  1.68it/s]
 86%|████████▌ | 49297/57600 [8:40:16<1:25:03,  1.63it/s]
 86%|████████▌ | 49298/57600 [8:40:17<1:24:57,  1.63it/s]
 86%|████████▌ | 49299/57600 [8:40:17<1:25:41,  1.61it/s]
 86%|████████▌ | 49300/57600 [8:40:18<1:25:30,  1.62it/s]
                                                         
{'loss': 1.1423, 'learning_rate': 2.3013937282229968e-07, 'epoch': 544.15}

 86%|████████▌ | 49300/57600 [8:40:18<1:25:30,  1.62it/s]
 86%|████████▌ | 49301/57600 [8:40:18<1:26:47,  1.59it/s]
 86%|████████▌ | 49302/57600 [8:40:19<1:26:43,  1.59it/s]
 86%|████████▌ | 49303/57600 [8:40:20<1:25:57,  1.61it/s]
 86%|████████▌ | 49304/57600 [8:40:20<1:27:37,  1.58it/s]
 86%|████████▌ | 49305/57600 [8:40:21<1:29:53,  1.54it/s]
 86%|████████▌ | 49306/57600 [8:40:22<1:28:39,  1.56it/s]
 86%|████████▌ | 49307/57600 [8:40:22<1:29:32,  1.54it/s]
 86%|████████▌ | 49308/57600 [8:40:23<1:27:26,  1.58it/s]
 86%|████████▌ | 49309/57600 [8:40:23<1:25:17,  1.62it/s]
 86%|████████▌ | 49310/57600 [8:40:24<1:23:50,  1.65it/s]
 86%|████████▌ | 49311/57600 [8:40:25<1:22:55,  1.67it/s]
 86%|████████▌ | 49312/57600 [8:40:25<1:22:16,  1.68it/s]
 86%|████████▌ | 49313/57600 [8:40:26<1:22:59,  1.66it/s]
 86%|████████▌ | 49314/57600 [8:40:26<1:23:01,  1.66it/s]
 86%|████████▌ | 49315/57600 [8:40:27<1:24:53,  1.63it/s]
 86%|████████▌ | 49316/57600 [8:40:28<1:26:26,  1.60it/s]
 86%|████████▌ | 49317/57600 [8:40:28<1:26:17,  1.60it/s]
 86%|████████▌ | 49318/57600 [8:40:29<1:24:57,  1.62it/s]
 86%|████████▌ | 49319/57600 [8:40:30<1:29:52,  1.54it/s]
 86%|████████▌ | 49320/57600 [8:40:30<1:29:21,  1.54it/s]
                                                         
{'loss': 1.1174, 'learning_rate': 2.298257839721254e-07, 'epoch': 544.37}

 86%|████████▌ | 49320/57600 [8:40:30<1:29:21,  1.54it/s]
 86%|████████▌ | 49321/57600 [8:40:31<1:28:48,  1.55it/s]
 86%|████████▌ | 49322/57600 [8:40:32<1:30:59,  1.52it/s]
 86%|████████▌ | 49323/57600 [8:40:32<1:30:42,  1.52it/s]
 86%|████████▌ | 49324/57600 [8:40:33<1:29:20,  1.54it/s]
 86%|████████▌ | 49325/57600 [8:40:34<1:27:29,  1.58it/s]
 86%|████████▌ | 49326/57600 [8:40:34<1:25:34,  1.61it/s]
 86%|████████▌ | 49327/57600 [8:40:35<1:26:04,  1.60it/s]
 86%|████████▌ | 49328/57600 [8:40:35<1:28:17,  1.56it/s]
 86%|████████▌ | 49329/57600 [8:40:36<1:27:14,  1.58it/s]
 86%|████████▌ | 49330/57600 [8:40:37<1:29:10,  1.55it/s]
 86%|████████▌ | 49331/57600 [8:40:37<1:29:35,  1.54it/s]
 86%|████████▌ | 49332/57600 [8:40:38<1:29:40,  1.54it/s]
 86%|████████▌ | 49333/57600 [8:40:39<1:28:14,  1.56it/s]
 86%|████████▌ | 49334/57600 [8:40:39<1:26:51,  1.59it/s]
 86%|████████▌ | 49335/57600 [8:40:40<1:28:37,  1.55it/s]
 86%|████████▌ | 49336/57600 [8:40:41<1:27:02,  1.58it/s]
 86%|████████▌ | 49337/57600 [8:40:41<1:29:20,  1.54it/s]
 86%|████████▌ | 49338/57600 [8:40:42<1:29:32,  1.54it/s]
 86%|████████▌ | 49339/57600 [8:40:42<1:27:29,  1.57it/s]
 86%|████████▌ | 49340/57600 [8:40:43<1:28:07,  1.56it/s]
                                                         
{'loss': 1.0878, 'learning_rate': 2.2951219512195121e-07, 'epoch': 544.59}

 86%|████████▌ | 49340/57600 [8:40:43<1:28:07,  1.56it/s]
 86%|████████▌ | 49341/57600 [8:40:44<1:24:42,  1.62it/s]
 86%|████████▌ | 49342/57600 [8:40:44<1:26:58,  1.58it/s]
 86%|████████▌ | 49343/57600 [8:40:45<1:28:02,  1.56it/s]
 86%|████████▌ | 49344/57600 [8:40:46<1:26:51,  1.58it/s]
 86%|████████▌ | 49345/57600 [8:40:46<1:26:40,  1.59it/s]
 86%|████████▌ | 49346/57600 [8:40:47<1:31:01,  1.51it/s]
 86%|████████▌ | 49347/57600 [8:40:48<1:26:52,  1.58it/s]
 86%|████████▌ | 49348/57600 [8:40:48<1:27:32,  1.57it/s]
 86%|████████▌ | 49349/57600 [8:40:49<1:25:49,  1.60it/s]
 86%|████████▌ | 49350/57600 [8:40:49<1:26:27,  1.59it/s]
 86%|████████▌ | 49351/57600 [8:40:50<1:25:51,  1.60it/s]
 86%|████████▌ | 49352/57600 [8:40:51<1:28:01,  1.56it/s]
 86%|████████▌ | 49353/57600 [8:40:51<1:28:42,  1.55it/s]
 86%|████████▌ | 49354/57600 [8:40:52<1:30:24,  1.52it/s]
 86%|████████▌ | 49355/57600 [8:40:53<1:32:53,  1.48it/s]
 86%|████████▌ | 49356/57600 [8:40:53<1:29:55,  1.53it/s]
 86%|████████▌ | 49357/57600 [8:40:54<1:26:29,  1.59it/s]
 86%|████████▌ | 49358/57600 [8:40:55<1:27:28,  1.57it/s]
 86%|████████▌ | 49359/57600 [8:40:55<1:26:53,  1.58it/s]
 86%|████████▌ | 49360/57600 [8:40:56<1:25:04,  1.61it/s]
                                                         
{'loss': 1.1226, 'learning_rate': 2.2919860627177694e-07, 'epoch': 544.81}

 86%|████████▌ | 49360/57600 [8:40:56<1:25:04,  1.61it/s]
 86%|████████▌ | 49361/57600 [8:40:56<1:24:17,  1.63it/s]
 86%|████████▌ | 49362/57600 [8:40:57<1:23:08,  1.65it/s]
 86%|████████▌ | 49363/57600 [8:40:58<1:24:24,  1.63it/s]
 86%|████████▌ | 49364/57600 [8:40:58<1:24:03,  1.63it/s]
 86%|████████▌ | 49365/57600 [8:40:59<1:25:18,  1.61it/s]
 86%|████████▌ | 49366/57600 [8:41:00<1:25:11,  1.61it/s]
 86%|████████▌ | 49367/57600 [8:41:00<1:24:12,  1.63it/s]
 86%|████████▌ | 49368/57600 [8:41:01<1:24:01,  1.63it/s]
 86%|████████▌ | 49369/57600 [8:41:01<1:25:18,  1.61it/s]
 86%|████████▌ | 49370/57600 [8:41:02<1:24:07,  1.63it/s]
 86%|████████▌ | 49371/57600 [8:41:03<1:24:23,  1.63it/s]
 86%|████████▌ | 49372/57600 [8:41:03<1:22:26,  1.66it/s]
 86%|████████▌ | 49373/57600 [8:41:04<1:23:40,  1.64it/s]
 86%|████████▌ | 49374/57600 [8:41:04<1:24:20,  1.63it/s]
 86%|████████▌ | 49375/57600 [8:41:05<1:24:35,  1.62it/s]
 86%|████████▌ | 49376/57600 [8:41:06<1:23:59,  1.63it/s]
 86%|████████▌ | 49377/57600 [8:41:06<1:28:38,  1.55it/s]
 86%|████████▌ | 49378/57600 [8:41:07<1:29:43,  1.53it/s]
 86%|████████▌ | 49379/57600 [8:41:08<1:27:34,  1.56it/s]
 86%|████████▌ | 49380/57600 [8:41:08<1:29:42,  1.53it/s]
                                                         
{'loss': 1.1167, 'learning_rate': 2.2888501742160277e-07, 'epoch': 545.03}

 86%|████████▌ | 49380/57600 [8:41:08<1:29:42,  1.53it/s]
 86%|████████▌ | 49381/57600 [8:41:09<1:28:50,  1.54it/s]
 86%|████████▌ | 49382/57600 [8:41:10<1:34:20,  1.45it/s]
 86%|████████▌ | 49383/57600 [8:41:10<1:29:53,  1.52it/s]
 86%|████████▌ | 49384/57600 [8:41:11<1:31:51,  1.49it/s]
 86%|████████▌ | 49385/57600 [8:41:12<1:31:40,  1.49it/s]
 86%|████████▌ | 49386/57600 [8:41:12<1:36:00,  1.43it/s]
 86%|████████▌ | 49387/57600 [8:41:13<1:35:10,  1.44it/s]
 86%|████████▌ | 49388/57600 [8:41:14<1:32:13,  1.48it/s]
 86%|████████▌ | 49389/57600 [8:41:14<1:29:24,  1.53it/s]
 86%|████████▌ | 49390/57600 [8:41:15<1:26:50,  1.58it/s]
 86%|████████▌ | 49391/57600 [8:41:16<1:26:18,  1.59it/s]
 86%|████████▌ | 49392/57600 [8:41:16<1:27:38,  1.56it/s]
 86%|████████▌ | 49393/57600 [8:41:17<1:25:53,  1.59it/s]
 86%|████████▌ | 49394/57600 [8:41:18<1:26:59,  1.57it/s]
 86%|████████▌ | 49395/57600 [8:41:18<1:29:13,  1.53it/s]
 86%|████████▌ | 49396/57600 [8:41:19<1:28:03,  1.55it/s]
 86%|████████▌ | 49397/57600 [8:41:19<1:25:52,  1.59it/s]
 86%|████████▌ | 49398/57600 [8:41:20<1:23:55,  1.63it/s]
 86%|████████▌ | 49399/57600 [8:41:21<1:23:49,  1.63it/s]
 86%|████████▌ | 49400/57600 [8:41:21<1:22:37,  1.65it/s]
                                                         
{'loss': 1.074, 'learning_rate': 2.285714285714286e-07, 'epoch': 545.25}

 86%|████████▌ | 49400/57600 [8:41:21<1:22:37,  1.65it/s]
 86%|████████▌ | 49401/57600 [8:41:22<1:24:00,  1.63it/s]
 86%|████████▌ | 49402/57600 [8:41:22<1:22:50,  1.65it/s]
 86%|████████▌ | 49403/57600 [8:41:23<1:24:55,  1.61it/s]
 86%|████████▌ | 49404/57600 [8:41:24<1:26:19,  1.58it/s]
 86%|████████▌ | 49405/57600 [8:41:24<1:27:19,  1.56it/s]
 86%|████████▌ | 49406/57600 [8:41:25<1:25:42,  1.59it/s]
 86%|████████▌ | 49407/57600 [8:41:26<1:28:19,  1.55it/s]
 86%|████████▌ | 49408/57600 [8:41:26<1:27:20,  1.56it/s]
 86%|████████▌ | 49409/57600 [8:41:27<1:26:53,  1.57it/s]
 86%|████████▌ | 49410/57600 [8:41:28<1:25:29,  1.60it/s]
 86%|████████▌ | 49411/57600 [8:41:28<1:25:41,  1.59it/s]
 86%|████████▌ | 49412/57600 [8:41:29<1:26:10,  1.58it/s]
 86%|████████▌ | 49413/57600 [8:41:29<1:25:34,  1.59it/s]
 86%|████████▌ | 49414/57600 [8:41:30<1:25:28,  1.60it/s]
 86%|████████▌ | 49415/57600 [8:41:31<1:23:22,  1.64it/s]
 86%|████████▌ | 49416/57600 [8:41:31<1:24:31,  1.61it/s]
 86%|████████▌ | 49417/57600 [8:41:32<1:22:11,  1.66it/s]
 86%|████████▌ | 49418/57600 [8:41:32<1:21:56,  1.66it/s]
 86%|████████▌ | 49419/57600 [8:41:33<1:25:57,  1.59it/s]
 86%|████████▌ | 49420/57600 [8:41:34<1:25:57,  1.59it/s]
                                                         
{'loss': 1.1233, 'learning_rate': 2.2825783972125435e-07, 'epoch': 545.47}

 86%|████████▌ | 49420/57600 [8:41:34<1:25:57,  1.59it/s]
 86%|████████▌ | 49421/57600 [8:41:34<1:25:25,  1.60it/s]
 86%|████████▌ | 49422/57600 [8:41:35<1:22:34,  1.65it/s]
 86%|████████▌ | 49423/57600 [8:41:36<1:23:53,  1.62it/s]
 86%|████████▌ | 49424/57600 [8:41:36<1:29:06,  1.53it/s]
 86%|████████▌ | 49425/57600 [8:41:37<1:28:06,  1.55it/s]
 86%|████████▌ | 49426/57600 [8:41:38<1:27:31,  1.56it/s]
 86%|████████▌ | 49427/57600 [8:41:38<1:29:43,  1.52it/s]
 86%|████████▌ | 49428/57600 [8:41:39<1:26:45,  1.57it/s]
 86%|████████▌ | 49429/57600 [8:41:40<1:26:27,  1.58it/s]
 86%|████████▌ | 49430/57600 [8:41:40<1:23:48,  1.62it/s]
 86%|████████▌ | 49431/57600 [8:41:41<1:23:32,  1.63it/s]
 86%|████████▌ | 49432/57600 [8:41:41<1:23:36,  1.63it/s]
 86%|████████▌ | 49433/57600 [8:41:42<1:21:51,  1.66it/s]
 86%|████████▌ | 49434/57600 [8:41:43<1:23:01,  1.64it/s]
 86%|████████▌ | 49435/57600 [8:41:43<1:22:03,  1.66it/s]
 86%|████████▌ | 49436/57600 [8:41:44<1:21:02,  1.68it/s]
 86%|████████▌ | 49437/57600 [8:41:44<1:24:16,  1.61it/s]
 86%|████████▌ | 49438/57600 [8:41:45<1:23:44,  1.62it/s]
 86%|████████▌ | 49439/57600 [8:41:46<1:24:25,  1.61it/s]
 86%|████████▌ | 49440/57600 [8:41:46<1:23:58,  1.62it/s]
                                                         
{'loss': 1.1342, 'learning_rate': 2.2794425087108016e-07, 'epoch': 545.7}

 86%|████████▌ | 49440/57600 [8:41:46<1:23:58,  1.62it/s]
 86%|████████▌ | 49441/57600 [8:41:47<1:22:22,  1.65it/s]
 86%|████████▌ | 49442/57600 [8:41:47<1:24:42,  1.61it/s]
 86%|████████▌ | 49443/57600 [8:41:48<1:26:42,  1.57it/s]
 86%|████████▌ | 49444/57600 [8:41:49<1:26:45,  1.57it/s]
 86%|████████▌ | 49445/57600 [8:41:49<1:24:22,  1.61it/s]
 86%|████████▌ | 49446/57600 [8:41:50<1:25:03,  1.60it/s]
 86%|████████▌ | 49447/57600 [8:41:51<1:21:46,  1.66it/s]
 86%|████████▌ | 49448/57600 [8:41:51<1:25:14,  1.59it/s]
 86%|████████▌ | 49449/57600 [8:41:52<1:25:33,  1.59it/s]
 86%|████████▌ | 49450/57600 [8:41:52<1:25:11,  1.59it/s]
 86%|████████▌ | 49451/57600 [8:41:53<1:24:10,  1.61it/s]
 86%|████████▌ | 49452/57600 [8:41:54<1:24:49,  1.60it/s]
 86%|████████▌ | 49453/57600 [8:41:54<1:24:32,  1.61it/s]
 86%|████████▌ | 49454/57600 [8:41:55<1:24:18,  1.61it/s]
 86%|████████▌ | 49455/57600 [8:41:56<1:22:40,  1.64it/s]
 86%|████████▌ | 49456/57600 [8:41:56<1:23:54,  1.62it/s]
 86%|████████▌ | 49457/57600 [8:41:57<1:27:33,  1.55it/s]
 86%|████████▌ | 49458/57600 [8:41:58<1:29:20,  1.52it/s]
 86%|████████▌ | 49459/57600 [8:41:58<1:27:01,  1.56it/s]
 86%|████████▌ | 49460/57600 [8:41:59<1:26:10,  1.57it/s]
                                                         
{'loss': 1.1092, 'learning_rate': 2.2763066202090588e-07, 'epoch': 545.92}

 86%|████████▌ | 49460/57600 [8:41:59<1:26:10,  1.57it/s]
 86%|████████▌ | 49461/57600 [8:41:59<1:27:01,  1.56it/s]
 86%|████████▌ | 49462/57600 [8:42:00<1:26:31,  1.57it/s]
 86%|████████▌ | 49463/57600 [8:42:01<1:24:16,  1.61it/s]
 86%|████████▌ | 49464/57600 [8:42:01<1:22:42,  1.64it/s]
 86%|████████▌ | 49465/57600 [8:42:02<1:20:47,  1.68it/s]
 86%|████████▌ | 49466/57600 [8:42:02<1:20:45,  1.68it/s]
 86%|████████▌ | 49467/57600 [8:42:03<1:21:59,  1.65it/s]
 86%|████████▌ | 49468/57600 [8:42:04<1:22:34,  1.64it/s]
 86%|████████▌ | 49469/57600 [8:42:04<1:22:29,  1.64it/s]
 86%|████████▌ | 49470/57600 [8:42:05<1:23:09,  1.63it/s]
 86%|████████▌ | 49471/57600 [8:42:06<1:27:40,  1.55it/s]
 86%|████████▌ | 49472/57600 [8:42:06<1:27:02,  1.56it/s]
 86%|████████▌ | 49473/57600 [8:42:07<1:25:40,  1.58it/s]
 86%|████████▌ | 49474/57600 [8:42:07<1:22:43,  1.64it/s]
 86%|████████▌ | 49475/57600 [8:42:08<1:24:35,  1.60it/s]
 86%|████████▌ | 49476/57600 [8:42:09<1:24:36,  1.60it/s]
 86%|████████▌ | 49477/57600 [8:42:09<1:21:55,  1.65it/s]
 86%|████████▌ | 49478/57600 [8:42:10<1:21:06,  1.67it/s]
 86%|████████▌ | 49479/57600 [8:42:10<1:21:42,  1.66it/s]
 86%|████████▌ | 49480/57600 [8:42:11<1:21:44,  1.66it/s]
                                                         
{'loss': 1.151, 'learning_rate': 2.2731707317073172e-07, 'epoch': 546.14}

 86%|████████▌ | 49480/57600 [8:42:11<1:21:44,  1.66it/s]
 86%|████████▌ | 49481/57600 [8:42:12<1:22:53,  1.63it/s]
 86%|████████▌ | 49482/57600 [8:42:12<1:27:38,  1.54it/s]
 86%|████████▌ | 49483/57600 [8:42:13<1:30:50,  1.49it/s]
 86%|████████▌ | 49484/57600 [8:42:14<1:29:54,  1.50it/s]
 86%|████████▌ | 49485/57600 [8:42:14<1:28:49,  1.52it/s]
 86%|████████▌ | 49486/57600 [8:42:15<1:26:47,  1.56it/s]
 86%|████████▌ | 49487/57600 [8:42:16<1:24:35,  1.60it/s]
 86%|████████▌ | 49488/57600 [8:42:16<1:24:06,  1.61it/s]
 86%|████████▌ | 49489/57600 [8:42:17<1:24:44,  1.60it/s]
 86%|████████▌ | 49490/57600 [8:42:17<1:24:55,  1.59it/s]
 86%|████████▌ | 49491/57600 [8:42:18<1:23:19,  1.62it/s]
 86%|████████▌ | 49492/57600 [8:42:19<1:23:06,  1.63it/s]
 86%|████████▌ | 49493/57600 [8:42:19<1:21:13,  1.66it/s]
 86%|████████▌ | 49494/57600 [8:42:20<1:19:30,  1.70it/s]
 86%|████████▌ | 49495/57600 [8:42:20<1:18:15,  1.73it/s]
 86%|████████▌ | 49496/57600 [8:42:21<1:21:25,  1.66it/s]
 86%|████████▌ | 49497/57600 [8:42:22<1:19:54,  1.69it/s]
 86%|████████▌ | 49498/57600 [8:42:22<1:21:58,  1.65it/s]
 86%|████████▌ | 49499/57600 [8:42:23<1:23:57,  1.61it/s]
 86%|████████▌ | 49500/57600 [8:42:23<1:22:37,  1.63it/s]
                                                         
{'loss': 1.1341, 'learning_rate': 2.2700348432055744e-07, 'epoch': 546.36}

 86%|████████▌ | 49500/57600 [8:42:23<1:22:37,  1.63it/s]
 86%|████████▌ | 49501/57600 [8:42:24<1:23:04,  1.62it/s]
 86%|████████▌ | 49502/57600 [8:42:25<1:22:42,  1.63it/s]
 86%|████████▌ | 49503/57600 [8:42:25<1:26:18,  1.56it/s]
 86%|████████▌ | 49504/57600 [8:42:26<1:27:25,  1.54it/s]
 86%|████████▌ | 49505/57600 [8:42:27<1:25:03,  1.59it/s]
 86%|████████▌ | 49506/57600 [8:42:27<1:27:42,  1.54it/s]
 86%|████████▌ | 49507/57600 [8:42:28<1:27:42,  1.54it/s]
 86%|████████▌ | 49508/57600 [8:42:29<1:25:25,  1.58it/s]
 86%|████████▌ | 49509/57600 [8:42:29<1:26:11,  1.56it/s]
 86%|████████▌ | 49510/57600 [8:42:30<1:27:11,  1.55it/s]
 86%|████████▌ | 49511/57600 [8:42:31<1:26:00,  1.57it/s]
 86%|████████▌ | 49512/57600 [8:42:31<1:24:54,  1.59it/s]
 86%|████████▌ | 49513/57600 [8:42:32<1:23:45,  1.61it/s]
 86%|████████▌ | 49514/57600 [8:42:32<1:23:10,  1.62it/s]
 86%|████████▌ | 49515/57600 [8:42:33<1:23:19,  1.62it/s]
 86%|████████▌ | 49516/57600 [8:42:34<1:22:39,  1.63it/s]
 86%|████████▌ | 49517/57600 [8:42:34<1:21:21,  1.66it/s]
 86%|████████▌ | 49518/57600 [8:42:35<1:24:10,  1.60it/s]
 86%|████████▌ | 49519/57600 [8:42:35<1:21:36,  1.65it/s]
 86%|████████▌ | 49520/57600 [8:42:36<1:25:05,  1.58it/s]
                                                         
{'loss': 1.1053, 'learning_rate': 2.2668989547038327e-07, 'epoch': 546.58}

 86%|████████▌ | 49520/57600 [8:42:36<1:25:05,  1.58it/s]
 86%|████████▌ | 49521/57600 [8:42:37<1:25:20,  1.58it/s]
 86%|████████▌ | 49522/57600 [8:42:37<1:24:57,  1.58it/s]
 86%|████████▌ | 49523/57600 [8:42:38<1:25:03,  1.58it/s]
 86%|████████▌ | 49524/57600 [8:42:39<1:24:23,  1.59it/s]
 86%|████████▌ | 49525/57600 [8:42:39<1:24:20,  1.60it/s]
 86%|████████▌ | 49526/57600 [8:42:40<1:23:27,  1.61it/s]
 86%|████████▌ | 49527/57600 [8:42:40<1:25:01,  1.58it/s]
 86%|████████▌ | 49528/57600 [8:42:41<1:25:27,  1.57it/s]
 86%|████████▌ | 49529/57600 [8:42:42<1:23:03,  1.62it/s]
 86%|████████▌ | 49530/57600 [8:42:42<1:23:55,  1.60it/s]
 86%|████████▌ | 49531/57600 [8:42:43<1:24:08,  1.60it/s]
 86%|████████▌ | 49532/57600 [8:42:44<1:24:57,  1.58it/s]
 86%|████████▌ | 49533/57600 [8:42:44<1:25:55,  1.56it/s]
 86%|████████▌ | 49534/57600 [8:42:45<1:27:04,  1.54it/s]
 86%|████████▌ | 49535/57600 [8:42:46<1:28:30,  1.52it/s]
 86%|████████▌ | 49536/57600 [8:42:46<1:27:09,  1.54it/s]
 86%|████████▌ | 49537/57600 [8:42:47<1:26:07,  1.56it/s]
 86%|████████▌ | 49538/57600 [8:42:48<1:25:09,  1.58it/s]
 86%|████████▌ | 49539/57600 [8:42:48<1:22:45,  1.62it/s]
 86%|████████▌ | 49540/57600 [8:42:49<1:24:03,  1.60it/s]
                                                         
{'loss': 1.1347, 'learning_rate': 2.2637630662020908e-07, 'epoch': 546.8}

 86%|████████▌ | 49540/57600 [8:42:49<1:24:03,  1.60it/s]
 86%|████████▌ | 49541/57600 [8:42:49<1:23:33,  1.61it/s]
 86%|████████▌ | 49542/57600 [8:42:50<1:24:16,  1.59it/s]
 86%|████████▌ | 49543/57600 [8:42:51<1:25:20,  1.57it/s]
 86%|████████▌ | 49544/57600 [8:42:51<1:23:57,  1.60it/s]
 86%|████████▌ | 49545/57600 [8:42:52<1:24:30,  1.59it/s]
 86%|████████▌ | 49546/57600 [8:42:53<1:24:26,  1.59it/s]
 86%|████████▌ | 49547/57600 [8:42:53<1:23:32,  1.61it/s]
 86%|████████▌ | 49548/57600 [8:42:54<1:23:31,  1.61it/s]
 86%|████████▌ | 49549/57600 [8:42:54<1:25:06,  1.58it/s]
 86%|████████▌ | 49550/57600 [8:42:55<1:23:51,  1.60it/s]
 86%|████████▌ | 49551/57600 [8:42:56<1:24:38,  1.58it/s]
 86%|████████▌ | 49552/57600 [8:42:56<1:28:49,  1.51it/s]
 86%|████████▌ | 49553/57600 [8:42:57<1:26:12,  1.56it/s]
 86%|████████▌ | 49554/57600 [8:42:58<1:25:32,  1.57it/s]
 86%|████████▌ | 49555/57600 [8:42:58<1:24:11,  1.59it/s]
 86%|████████▌ | 49556/57600 [8:42:59<1:25:01,  1.58it/s]
 86%|████████▌ | 49557/57600 [8:42:59<1:22:45,  1.62it/s]
 86%|████████▌ | 49558/57600 [8:43:00<1:26:15,  1.55it/s]
 86%|████████▌ | 49559/57600 [8:43:01<1:29:14,  1.50it/s]
 86%|████████▌ | 49560/57600 [8:43:01<1:27:44,  1.53it/s]
                                                         
{'loss': 1.1326, 'learning_rate': 2.260627177700348e-07, 'epoch': 547.02}

 86%|████████▌ | 49560/57600 [8:43:01<1:27:44,  1.53it/s]
 86%|████████▌ | 49561/57600 [8:43:02<1:25:56,  1.56it/s]
 86%|████████▌ | 49562/57600 [8:43:03<1:25:04,  1.57it/s]
 86%|████████▌ | 49563/57600 [8:43:03<1:24:30,  1.58it/s]
 86%|████████▌ | 49564/57600 [8:43:04<1:24:41,  1.58it/s]
 86%|████████▌ | 49565/57600 [8:43:05<1:24:47,  1.58it/s]
 86%|████████▌ | 49566/57600 [8:43:05<1:27:26,  1.53it/s]
 86%|████████▌ | 49567/57600 [8:43:06<1:25:08,  1.57it/s]
 86%|████████▌ | 49568/57600 [8:43:07<1:26:35,  1.55it/s]
 86%|████████▌ | 49569/57600 [8:43:07<1:25:00,  1.57it/s]
 86%|████████▌ | 49570/57600 [8:43:08<1:24:35,  1.58it/s]
 86%|████████▌ | 49571/57600 [8:43:08<1:25:02,  1.57it/s]
 86%|████████▌ | 49572/57600 [8:43:09<1:23:10,  1.61it/s]
 86%|████████▌ | 49573/57600 [8:43:10<1:24:27,  1.58it/s]
 86%|████████▌ | 49574/57600 [8:43:10<1:27:50,  1.52it/s]
 86%|████████▌ | 49575/57600 [8:43:11<1:26:19,  1.55it/s]
 86%|████████▌ | 49576/57600 [8:43:12<1:30:55,  1.47it/s]
 86%|████████▌ | 49577/57600 [8:43:12<1:27:00,  1.54it/s]
 86%|████████▌ | 49578/57600 [8:43:13<1:28:03,  1.52it/s]
 86%|████████▌ | 49579/57600 [8:43:14<1:24:42,  1.58it/s]
 86%|████████▌ | 49580/57600 [8:43:14<1:25:22,  1.57it/s]
                                                         
{'loss': 1.1167, 'learning_rate': 2.2574912891986063e-07, 'epoch': 547.24}

 86%|████████▌ | 49580/57600 [8:43:14<1:25:22,  1.57it/s]
 86%|████████▌ | 49581/57600 [8:43:15<1:25:14,  1.57it/s]
 86%|████████▌ | 49582/57600 [8:43:15<1:23:01,  1.61it/s]
 86%|████████▌ | 49583/57600 [8:43:16<1:26:10,  1.55it/s]
 86%|████████▌ | 49584/57600 [8:43:17<1:24:33,  1.58it/s]
 86%|████████▌ | 49585/57600 [8:43:17<1:23:56,  1.59it/s]
 86%|████████▌ | 49586/57600 [8:43:18<1:26:01,  1.55it/s]
 86%|████████▌ | 49587/57600 [8:43:19<1:21:46,  1.63it/s]
 86%|████████▌ | 49588/57600 [8:43:19<1:21:55,  1.63it/s]
 86%|████████▌ | 49589/57600 [8:43:20<1:23:48,  1.59it/s]
 86%|████████▌ | 49590/57600 [8:43:20<1:21:47,  1.63it/s]
 86%|████████▌ | 49591/57600 [8:43:21<1:22:59,  1.61it/s]
 86%|████████▌ | 49592/57600 [8:43:22<1:22:56,  1.61it/s]
 86%|████████▌ | 49593/57600 [8:43:22<1:22:39,  1.61it/s]
 86%|████████▌ | 49594/57600 [8:43:23<1:21:58,  1.63it/s]
 86%|████████▌ | 49595/57600 [8:43:24<1:21:10,  1.64it/s]
 86%|████████▌ | 49596/57600 [8:43:24<1:23:59,  1.59it/s]
 86%|████████▌ | 49597/57600 [8:43:25<1:24:23,  1.58it/s]
 86%|████████▌ | 49598/57600 [8:43:25<1:23:34,  1.60it/s]
 86%|████████▌ | 49599/57600 [8:43:26<1:22:46,  1.61it/s]
 86%|████████▌ | 49600/57600 [8:43:27<1:23:26,  1.60it/s]
                                                         
{'loss': 1.1193, 'learning_rate': 2.2543554006968636e-07, 'epoch': 547.46}

 86%|████████▌ | 49600/57600 [8:43:27<1:23:26,  1.60it/s]
 86%|████████▌ | 49601/57600 [8:43:27<1:25:16,  1.56it/s]
 86%|████████▌ | 49602/57600 [8:43:28<1:26:16,  1.55it/s]
 86%|████████▌ | 49603/57600 [8:43:29<1:23:32,  1.60it/s]
 86%|████████▌ | 49604/57600 [8:43:29<1:22:37,  1.61it/s]
 86%|████████▌ | 49605/57600 [8:43:30<1:24:13,  1.58it/s]
 86%|████████▌ | 49606/57600 [8:43:31<1:24:30,  1.58it/s]
 86%|████████▌ | 49607/57600 [8:43:31<1:22:26,  1.62it/s]
 86%|████████▌ | 49608/57600 [8:43:32<1:21:27,  1.64it/s]
 86%|████████▌ | 49609/57600 [8:43:32<1:20:38,  1.65it/s]
 86%|████████▌ | 49610/57600 [8:43:33<1:21:36,  1.63it/s]
 86%|████████▌ | 49611/57600 [8:43:34<1:23:10,  1.60it/s]
 86%|████████▌ | 49612/57600 [8:43:34<1:22:59,  1.60it/s]
 86%|████████▌ | 49613/57600 [8:43:35<1:22:38,  1.61it/s]
 86%|████████▌ | 49614/57600 [8:43:36<1:25:40,  1.55it/s]
 86%|████████▌ | 49615/57600 [8:43:36<1:23:53,  1.59it/s]
 86%|████████▌ | 49616/57600 [8:43:37<1:22:22,  1.62it/s]
 86%|████████▌ | 49617/57600 [8:43:37<1:23:39,  1.59it/s]
 86%|████████▌ | 49618/57600 [8:43:38<1:23:10,  1.60it/s]
 86%|████████▌ | 49619/57600 [8:43:39<1:26:13,  1.54it/s]
 86%|████████▌ | 49620/57600 [8:43:39<1:25:39,  1.55it/s]
                                                         
{'loss': 1.0693, 'learning_rate': 2.251219512195122e-07, 'epoch': 547.68}

 86%|████████▌ | 49620/57600 [8:43:39<1:25:39,  1.55it/s]
 86%|████████▌ | 49621/57600 [8:43:40<1:22:25,  1.61it/s]
 86%|████████▌ | 49622/57600 [8:43:41<1:21:46,  1.63it/s]
 86%|████████▌ | 49623/57600 [8:43:41<1:23:39,  1.59it/s]
 86%|████████▌ | 49624/57600 [8:43:42<1:21:03,  1.64it/s]
 86%|████████▌ | 49625/57600 [8:43:42<1:21:07,  1.64it/s]
 86%|████████▌ | 49626/57600 [8:43:43<1:20:45,  1.65it/s]
 86%|████████▌ | 49627/57600 [8:43:44<1:23:00,  1.60it/s]
 86%|████████▌ | 49628/57600 [8:43:44<1:22:16,  1.62it/s]
 86%|████████▌ | 49629/57600 [8:43:45<1:20:10,  1.66it/s]
 86%|████████▌ | 49630/57600 [8:43:45<1:20:34,  1.65it/s]
 86%|████████▌ | 49631/57600 [8:43:46<1:23:19,  1.59it/s]
 86%|████████▌ | 49632/57600 [8:43:47<1:24:32,  1.57it/s]
 86%|████████▌ | 49633/57600 [8:43:47<1:22:36,  1.61it/s]
 86%|████████▌ | 49634/57600 [8:43:48<1:22:03,  1.62it/s]
 86%|████████▌ | 49635/57600 [8:43:49<1:23:17,  1.59it/s]
 86%|████████▌ | 49636/57600 [8:43:49<1:20:10,  1.66it/s]
 86%|████████▌ | 49637/57600 [8:43:50<1:20:46,  1.64it/s]
 86%|████████▌ | 49638/57600 [8:43:50<1:20:23,  1.65it/s]
 86%|████████▌ | 49639/57600 [8:43:51<1:22:00,  1.62it/s]
 86%|████████▌ | 49640/57600 [8:43:52<1:20:21,  1.65it/s]
                                                         
{'loss': 1.1476, 'learning_rate': 2.2480836236933792e-07, 'epoch': 547.9}

 86%|████████▌ | 49640/57600 [8:43:52<1:20:21,  1.65it/s]
 86%|████████▌ | 49641/57600 [8:43:52<1:22:32,  1.61it/s]
 86%|████████▌ | 49642/57600 [8:43:53<1:21:30,  1.63it/s]
 86%|████████▌ | 49643/57600 [8:43:53<1:22:49,  1.60it/s]
 86%|████████▌ | 49644/57600 [8:43:54<1:22:15,  1.61it/s]
 86%|████████▌ | 49645/57600 [8:43:55<1:25:01,  1.56it/s]
 86%|████████▌ | 49646/57600 [8:43:55<1:25:51,  1.54it/s]
 86%|████████▌ | 49647/57600 [8:43:56<1:25:47,  1.55it/s]
 86%|████████▌ | 49648/57600 [8:43:57<1:25:42,  1.55it/s]
 86%|████████▌ | 49649/57600 [8:43:58<1:30:35,  1.46it/s]
 86%|████████▌ | 49650/57600 [8:43:58<1:28:26,  1.50it/s]
 86%|████████▌ | 49651/57600 [8:43:59<1:27:56,  1.51it/s]
 86%|████████▌ | 49652/57600 [8:43:59<1:29:52,  1.47it/s]
 86%|████████▌ | 49653/57600 [8:44:00<1:28:32,  1.50it/s]
 86%|████████▌ | 49654/57600 [8:44:01<1:27:40,  1.51it/s]
 86%|████████▌ | 49655/57600 [8:44:01<1:25:33,  1.55it/s]
 86%|████████▌ | 49656/57600 [8:44:02<1:26:31,  1.53it/s]
 86%|████████▌ | 49657/57600 [8:44:03<1:25:00,  1.56it/s]
 86%|████████▌ | 49658/57600 [8:44:03<1:27:28,  1.51it/s]
 86%|████████▌ | 49659/57600 [8:44:04<1:28:22,  1.50it/s]
 86%|████████▌ | 49660/57600 [8:44:05<1:25:43,  1.54it/s]
                                                         
{'loss': 1.0626, 'learning_rate': 2.2449477351916375e-07, 'epoch': 548.12}

 86%|████████▌ | 49660/57600 [8:44:05<1:25:43,  1.54it/s]
 86%|████████▌ | 49661/57600 [8:44:05<1:23:38,  1.58it/s]
 86%|████████▌ | 49662/57600 [8:44:06<1:22:17,  1.61it/s]
 86%|████████▌ | 49663/57600 [8:44:06<1:22:30,  1.60it/s]
 86%|████████▌ | 49664/57600 [8:44:07<1:24:52,  1.56it/s]
 86%|████████▌ | 49665/57600 [8:44:08<1:22:15,  1.61it/s]
 86%|████████▌ | 49666/57600 [8:44:08<1:23:14,  1.59it/s]
 86%|████████▌ | 49667/57600 [8:44:09<1:25:30,  1.55it/s]
 86%|████████▌ | 49668/57600 [8:44:10<1:27:58,  1.50it/s]
 86%|████████▌ | 49669/57600 [8:44:10<1:24:36,  1.56it/s]
 86%|████████▌ | 49670/57600 [8:44:11<1:22:03,  1.61it/s]
 86%|████████▌ | 49671/57600 [8:44:12<1:22:29,  1.60it/s]
 86%|████████▌ | 49672/57600 [8:44:12<1:22:13,  1.61it/s]
 86%|████████▌ | 49673/57600 [8:44:13<1:23:05,  1.59it/s]
 86%|████████▌ | 49674/57600 [8:44:13<1:21:19,  1.62it/s]
 86%|████████▌ | 49675/57600 [8:44:14<1:20:58,  1.63it/s]
 86%|████████▌ | 49676/57600 [8:44:15<1:19:57,  1.65it/s]
 86%|████████▌ | 49677/57600 [8:44:15<1:17:55,  1.69it/s]
 86%|████████▌ | 49678/57600 [8:44:16<1:17:45,  1.70it/s]
 86%|████████▌ | 49679/57600 [8:44:16<1:21:31,  1.62it/s]
 86%|████████▋ | 49680/57600 [8:44:17<1:21:52,  1.61it/s]
                                                         
{'loss': 1.116, 'learning_rate': 2.2418118466898958e-07, 'epoch': 548.34}

 86%|████████▋ | 49680/57600 [8:44:17<1:21:52,  1.61it/s]
 86%|████████▋ | 49681/57600 [8:44:18<1:21:19,  1.62it/s]
 86%|████████▋ | 49682/57600 [8:44:18<1:22:19,  1.60it/s]
 86%|████████▋ | 49683/57600 [8:44:19<1:21:31,  1.62it/s]
 86%|████████▋ | 49684/57600 [8:44:20<1:20:48,  1.63it/s]
 86%|████████▋ | 49685/57600 [8:44:20<1:21:04,  1.63it/s]
 86%|████████▋ | 49686/57600 [8:44:21<1:21:32,  1.62it/s]
 86%|████████▋ | 49687/57600 [8:44:21<1:24:45,  1.56it/s]
 86%|████████▋ | 49688/57600 [8:44:22<1:23:19,  1.58it/s]
 86%|████████▋ | 49689/57600 [8:44:23<1:24:23,  1.56it/s]
 86%|████████▋ | 49690/57600 [8:44:23<1:22:12,  1.60it/s]
 86%|████████▋ | 49691/57600 [8:44:24<1:22:21,  1.60it/s]
 86%|████████▋ | 49692/57600 [8:44:25<1:22:18,  1.60it/s]
 86%|████████▋ | 49693/57600 [8:44:25<1:19:47,  1.65it/s]
 86%|████████▋ | 49694/57600 [8:44:26<1:22:18,  1.60it/s]
 86%|████████▋ | 49695/57600 [8:44:26<1:19:52,  1.65it/s]
 86%|████████▋ | 49696/57600 [8:44:27<1:24:49,  1.55it/s]
 86%|████████▋ | 49697/57600 [8:44:28<1:21:59,  1.61it/s]
 86%|████████▋ | 49698/57600 [8:44:28<1:20:16,  1.64it/s]
 86%|████████▋ | 49699/57600 [8:44:29<1:22:22,  1.60it/s]
 86%|████████▋ | 49700/57600 [8:44:30<1:20:39,  1.63it/s]
                                                         
{'loss': 1.1424, 'learning_rate': 2.238675958188153e-07, 'epoch': 548.57}

 86%|████████▋ | 49700/57600 [8:44:30<1:20:39,  1.63it/s]
 86%|████████▋ | 49701/57600 [8:44:30<1:22:13,  1.60it/s]
 86%|████████▋ | 49702/57600 [8:44:31<1:22:42,  1.59it/s]
 86%|████████▋ | 49703/57600 [8:44:31<1:22:08,  1.60it/s]
 86%|████████▋ | 49704/57600 [8:44:32<1:19:15,  1.66it/s]
 86%|████████▋ | 49705/57600 [8:44:33<1:21:42,  1.61it/s]
 86%|████████▋ | 49706/57600 [8:44:33<1:23:21,  1.58it/s]
 86%|████████▋ | 49707/57600 [8:44:34<1:22:59,  1.59it/s]
 86%|████████▋ | 49708/57600 [8:44:35<1:23:02,  1.58it/s]
 86%|████████▋ | 49709/57600 [8:44:35<1:26:18,  1.52it/s]
 86%|████████▋ | 49710/57600 [8:44:36<1:29:20,  1.47it/s]
 86%|████████▋ | 49711/57600 [8:44:37<1:30:07,  1.46it/s]
 86%|████████▋ | 49712/57600 [8:44:37<1:29:29,  1.47it/s]
 86%|████████▋ | 49713/57600 [8:44:38<1:30:09,  1.46it/s]
 86%|████████▋ | 49714/57600 [8:44:39<1:29:37,  1.47it/s]
 86%|████████▋ | 49715/57600 [8:44:39<1:27:00,  1.51it/s]
 86%|████████▋ | 49716/57600 [8:44:40<1:23:47,  1.57it/s]
 86%|████████▋ | 49717/57600 [8:44:41<1:21:54,  1.60it/s]
 86%|████████▋ | 49718/57600 [8:44:41<1:20:05,  1.64it/s]
 86%|████████▋ | 49719/57600 [8:44:42<1:23:43,  1.57it/s]
 86%|████████▋ | 49720/57600 [8:44:42<1:21:23,  1.61it/s]
                                                         
{'loss': 1.1374, 'learning_rate': 2.2355400696864114e-07, 'epoch': 548.79}

 86%|████████▋ | 49720/57600 [8:44:42<1:21:23,  1.61it/s]
 86%|████████▋ | 49721/57600 [8:44:43<1:22:37,  1.59it/s]
 86%|████████▋ | 49722/57600 [8:44:44<1:21:15,  1.62it/s]
 86%|████████▋ | 49723/57600 [8:44:44<1:19:52,  1.64it/s]
 86%|████████▋ | 49724/57600 [8:44:45<1:21:37,  1.61it/s]
 86%|████████▋ | 49725/57600 [8:44:45<1:20:52,  1.62it/s]
 86%|████████▋ | 49726/57600 [8:44:46<1:20:02,  1.64it/s]
 86%|████████▋ | 49727/57600 [8:44:47<1:23:33,  1.57it/s]
 86%|████████▋ | 49728/57600 [8:44:47<1:24:32,  1.55it/s]
 86%|████████▋ | 49729/57600 [8:44:48<1:23:30,  1.57it/s]
 86%|████████▋ | 49730/57600 [8:44:49<1:21:46,  1.60it/s]
 86%|████████▋ | 49731/57600 [8:44:49<1:20:41,  1.63it/s]
 86%|████████▋ | 49732/57600 [8:44:50<1:19:48,  1.64it/s]
 86%|████████▋ | 49733/57600 [8:44:50<1:20:06,  1.64it/s]
 86%|████████▋ | 49734/57600 [8:44:51<1:19:16,  1.65it/s]
 86%|████████▋ | 49735/57600 [8:44:52<1:18:10,  1.68it/s]
 86%|████████▋ | 49736/57600 [8:44:52<1:20:46,  1.62it/s]
 86%|████████▋ | 49737/57600 [8:44:53<1:21:17,  1.61it/s]
 86%|████████▋ | 49738/57600 [8:44:54<1:20:52,  1.62it/s]
 86%|████████▋ | 49739/57600 [8:44:54<1:19:56,  1.64it/s]
 86%|████████▋ | 49740/57600 [8:44:55<1:23:44,  1.56it/s]
                                                         
{'loss': 1.1343, 'learning_rate': 2.2324041811846686e-07, 'epoch': 549.01}

 86%|████████▋ | 49740/57600 [8:44:55<1:23:44,  1.56it/s]
 86%|████████▋ | 49741/57600 [8:44:55<1:22:01,  1.60it/s]
 86%|████████▋ | 49742/57600 [8:44:56<1:19:47,  1.64it/s]
 86%|████████▋ | 49743/57600 [8:44:57<1:19:40,  1.64it/s]
 86%|████████▋ | 49744/57600 [8:44:57<1:21:35,  1.60it/s]
 86%|████████▋ | 49745/57600 [8:44:58<1:24:47,  1.54it/s]
 86%|████████▋ | 49746/57600 [8:44:59<1:23:58,  1.56it/s]
 86%|████████▋ | 49747/57600 [8:44:59<1:24:59,  1.54it/s]
 86%|████████▋ | 49748/57600 [8:45:00<1:22:45,  1.58it/s]
 86%|████████▋ | 49749/57600 [8:45:00<1:21:12,  1.61it/s]
 86%|████████▋ | 49750/57600 [8:45:01<1:20:11,  1.63it/s]
 86%|████████▋ | 49751/57600 [8:45:02<1:19:52,  1.64it/s]
 86%|████████▋ | 49752/57600 [8:45:02<1:21:02,  1.61it/s]
 86%|████████▋ | 49753/57600 [8:45:03<1:18:47,  1.66it/s]
 86%|████████▋ | 49754/57600 [8:45:03<1:19:56,  1.64it/s]
 86%|████████▋ | 49755/57600 [8:45:04<1:21:52,  1.60it/s]
 86%|████████▋ | 49756/57600 [8:45:05<1:23:47,  1.56it/s]
 86%|████████▋ | 49757/57600 [8:45:05<1:24:24,  1.55it/s]
 86%|████████▋ | 49758/57600 [8:45:06<1:24:04,  1.55it/s]
 86%|████████▋ | 49759/57600 [8:45:07<1:22:17,  1.59it/s]
 86%|████████▋ | 49760/57600 [8:45:07<1:22:51,  1.58it/s]
                                                         
{'loss': 1.1125, 'learning_rate': 2.229268292682927e-07, 'epoch': 549.23}

 86%|████████▋ | 49760/57600 [8:45:07<1:22:51,  1.58it/s]
 86%|████████▋ | 49761/57600 [8:45:08<1:27:29,  1.49it/s]
 86%|████████▋ | 49762/57600 [8:45:09<1:28:38,  1.47it/s]
 86%|████████▋ | 49763/57600 [8:45:09<1:27:45,  1.49it/s]
 86%|████████▋ | 49764/57600 [8:45:10<1:28:46,  1.47it/s]
 86%|████████▋ | 49765/57600 [8:45:11<1:26:29,  1.51it/s]
 86%|████████▋ | 49766/57600 [8:45:11<1:24:26,  1.55it/s]
 86%|████████▋ | 49767/57600 [8:45:12<1:21:06,  1.61it/s]
 86%|████████▋ | 49768/57600 [8:45:13<1:20:25,  1.62it/s]
 86%|████████▋ | 49769/57600 [8:45:13<1:19:04,  1.65it/s]
 86%|████████▋ | 49770/57600 [8:45:14<1:18:25,  1.66it/s]
 86%|████████▋ | 49771/57600 [8:45:14<1:18:56,  1.65it/s]
 86%|████████▋ | 49772/57600 [8:45:15<1:19:47,  1.63it/s]
 86%|████████▋ | 49773/57600 [8:45:16<1:17:50,  1.68it/s]
 86%|████████▋ | 49774/57600 [8:45:16<1:19:12,  1.65it/s]
 86%|████████▋ | 49775/57600 [8:45:17<1:20:34,  1.62it/s]
 86%|████████▋ | 49776/57600 [8:45:17<1:23:14,  1.57it/s]
 86%|████████▋ | 49777/57600 [8:45:18<1:24:34,  1.54it/s]
 86%|████████▋ | 49778/57600 [8:45:19<1:22:28,  1.58it/s]
 86%|████████▋ | 49779/57600 [8:45:19<1:25:20,  1.53it/s]
 86%|████████▋ | 49780/57600 [8:45:20<1:23:30,  1.56it/s]
                                                         
{'loss': 1.1081, 'learning_rate': 2.2261324041811842e-07, 'epoch': 549.45}

 86%|████████▋ | 49780/57600 [8:45:20<1:23:30,  1.56it/s]
 86%|████████▋ | 49781/57600 [8:45:21<1:20:59,  1.61it/s]
 86%|████████▋ | 49782/57600 [8:45:21<1:23:43,  1.56it/s]
 86%|████████▋ | 49783/57600 [8:45:22<1:21:40,  1.60it/s]
 86%|████████▋ | 49784/57600 [8:45:23<1:21:39,  1.60it/s]
 86%|████████▋ | 49785/57600 [8:45:23<1:21:01,  1.61it/s]
 86%|████████▋ | 49786/57600 [8:45:24<1:19:00,  1.65it/s]
 86%|████████▋ | 49787/57600 [8:45:24<1:18:21,  1.66it/s]
 86%|████████▋ | 49788/57600 [8:45:25<1:17:35,  1.68it/s]
 86%|████████▋ | 49789/57600 [8:45:26<1:22:07,  1.59it/s]
 86%|████████▋ | 49790/57600 [8:45:26<1:20:53,  1.61it/s]
 86%|████████▋ | 49791/57600 [8:45:27<1:19:37,  1.63it/s]
 86%|████████▋ | 49792/57600 [8:45:27<1:19:04,  1.65it/s]
 86%|████████▋ | 49793/57600 [8:45:28<1:18:50,  1.65it/s]
 86%|████████▋ | 49794/57600 [8:45:29<1:18:57,  1.65it/s]
 86%|████████▋ | 49795/57600 [8:45:29<1:20:54,  1.61it/s]
 86%|████████▋ | 49796/57600 [8:45:30<1:20:37,  1.61it/s]
 86%|████████▋ | 49797/57600 [8:45:31<1:24:25,  1.54it/s]
 86%|████████▋ | 49798/57600 [8:45:31<1:23:57,  1.55it/s]
 86%|████████▋ | 49799/57600 [8:45:32<1:26:17,  1.51it/s]
 86%|████████▋ | 49800/57600 [8:45:33<1:27:32,  1.49it/s]
                                                         
{'loss': 1.1289, 'learning_rate': 2.2229965156794422e-07, 'epoch': 549.67}

 86%|████████▋ | 49800/57600 [8:45:33<1:27:32,  1.49it/s]
 86%|████████▋ | 49801/57600 [8:45:33<1:24:28,  1.54it/s]
 86%|████████▋ | 49802/57600 [8:45:34<1:24:05,  1.55it/s]
 86%|████████▋ | 49803/57600 [8:45:35<1:24:54,  1.53it/s]
 86%|████████▋ | 49804/57600 [8:45:35<1:23:44,  1.55it/s]
 86%|████████▋ | 49805/57600 [8:45:36<1:24:00,  1.55it/s]
 86%|████████▋ | 49806/57600 [8:45:36<1:21:44,  1.59it/s]
 86%|████████▋ | 49807/57600 [8:45:37<1:19:09,  1.64it/s]
 86%|████████▋ | 49808/57600 [8:45:38<1:17:34,  1.67it/s]
 86%|████████▋ | 49809/57600 [8:45:38<1:17:07,  1.68it/s]
 86%|████████▋ | 49810/57600 [8:45:39<1:16:57,  1.69it/s]
 86%|████████▋ | 49811/57600 [8:45:39<1:16:48,  1.69it/s]
 86%|████████▋ | 49812/57600 [8:45:40<1:18:08,  1.66it/s]
 86%|████████▋ | 49813/57600 [8:45:41<1:19:22,  1.63it/s]
 86%|████████▋ | 49814/57600 [8:45:41<1:20:22,  1.61it/s]
 86%|████████▋ | 49815/57600 [8:45:42<1:19:27,  1.63it/s]
 86%|████████▋ | 49816/57600 [8:45:42<1:19:11,  1.64it/s]
 86%|████████▋ | 49817/57600 [8:45:43<1:23:46,  1.55it/s]
 86%|████████▋ | 49818/57600 [8:45:44<1:22:19,  1.58it/s]
 86%|████████▋ | 49819/57600 [8:45:44<1:22:03,  1.58it/s]
 86%|████████▋ | 49820/57600 [8:45:45<1:25:05,  1.52it/s]
                                                         
{'loss': 1.0951, 'learning_rate': 2.2198606271777005e-07, 'epoch': 549.89}

 86%|████████▋ | 49820/57600 [8:45:45<1:25:05,  1.52it/s]
 86%|████████▋ | 49821/57600 [8:45:46<1:25:33,  1.52it/s]
 86%|████████▋ | 49822/57600 [8:45:46<1:23:46,  1.55it/s]
 86%|████████▋ | 49823/57600 [8:45:47<1:23:41,  1.55it/s]
 86%|████████▋ | 49824/57600 [8:45:48<1:23:58,  1.54it/s]
 87%|████████▋ | 49825/57600 [8:45:48<1:21:44,  1.59it/s]
 87%|████████▋ | 49826/57600 [8:45:49<1:23:00,  1.56it/s]
 87%|████████▋ | 49827/57600 [8:45:50<1:25:31,  1.51it/s]
 87%|████████▋ | 49828/57600 [8:45:50<1:25:14,  1.52it/s]
 87%|████████▋ | 49829/57600 [8:45:51<1:23:07,  1.56it/s]
 87%|████████▋ | 49830/57600 [8:45:52<1:25:35,  1.51it/s]
 87%|████████▋ | 49831/57600 [8:45:52<1:28:32,  1.46it/s]
 87%|████████▋ | 49832/57600 [8:45:53<1:23:34,  1.55it/s]
 87%|████████▋ | 49833/57600 [8:45:53<1:20:21,  1.61it/s]
 87%|████████▋ | 49834/57600 [8:45:54<1:18:59,  1.64it/s]
 87%|████████▋ | 49835/57600 [8:45:55<1:19:47,  1.62it/s]
 87%|████████▋ | 49836/57600 [8:45:55<1:20:50,  1.60it/s]
 87%|████████▋ | 49837/57600 [8:45:56<1:23:02,  1.56it/s]
 87%|████████▋ | 49838/57600 [8:45:57<1:23:01,  1.56it/s]
 87%|████████▋ | 49839/57600 [8:45:57<1:21:50,  1.58it/s]
 87%|████████▋ | 49840/57600 [8:45:58<1:20:41,  1.60it/s]
                                                         
{'loss': 1.1194, 'learning_rate': 2.2167247386759578e-07, 'epoch': 550.11}

 87%|████████▋ | 49840/57600 [8:45:58<1:20:41,  1.60it/s]
 87%|████████▋ | 49841/57600 [8:45:58<1:20:38,  1.60it/s]
 87%|████████▋ | 49842/57600 [8:45:59<1:22:49,  1.56it/s]
 87%|████████▋ | 49843/57600 [8:46:00<1:23:51,  1.54it/s]
 87%|████████▋ | 49844/57600 [8:46:00<1:24:54,  1.52it/s]
 87%|████████▋ | 49845/57600 [8:46:01<1:23:37,  1.55it/s]
 87%|████████▋ | 49846/57600 [8:46:02<1:22:15,  1.57it/s]
 87%|████████▋ | 49847/57600 [8:46:02<1:22:28,  1.57it/s]
 87%|████████▋ | 49848/57600 [8:46:03<1:20:54,  1.60it/s]
 87%|████████▋ | 49849/57600 [8:46:04<1:19:51,  1.62it/s]
 87%|████████▋ | 49850/57600 [8:46:04<1:22:52,  1.56it/s]
 87%|████████▋ | 49851/57600 [8:46:05<1:22:14,  1.57it/s]
 87%|████████▋ | 49852/57600 [8:46:05<1:20:12,  1.61it/s]
 87%|████████▋ | 49853/57600 [8:46:06<1:21:24,  1.59it/s]
 87%|████████▋ | 49854/57600 [8:46:07<1:22:53,  1.56it/s]
 87%|████████▋ | 49855/57600 [8:46:07<1:23:42,  1.54it/s]
 87%|████████▋ | 49856/57600 [8:46:08<1:22:50,  1.56it/s]
 87%|████████▋ | 49857/57600 [8:46:09<1:21:10,  1.59it/s]
 87%|████████▋ | 49858/57600 [8:46:09<1:19:03,  1.63it/s]
 87%|████████▋ | 49859/57600 [8:46:10<1:20:24,  1.60it/s]
 87%|████████▋ | 49860/57600 [8:46:11<1:21:49,  1.58it/s]
                                                         
{'loss': 1.0951, 'learning_rate': 2.213588850174216e-07, 'epoch': 550.33}

 87%|████████▋ | 49860/57600 [8:46:11<1:21:49,  1.58it/s]
 87%|████████▋ | 49861/57600 [8:46:11<1:22:02,  1.57it/s]
 87%|████████▋ | 49862/57600 [8:46:12<1:22:25,  1.56it/s]
 87%|████████▋ | 49863/57600 [8:46:13<1:23:50,  1.54it/s]
 87%|████████▋ | 49864/57600 [8:46:13<1:23:23,  1.55it/s]
 87%|████████▋ | 49865/57600 [8:46:14<1:20:08,  1.61it/s]
 87%|████████▋ | 49866/57600 [8:46:14<1:19:23,  1.62it/s]
 87%|████████▋ | 49867/57600 [8:46:15<1:21:57,  1.57it/s]
 87%|████████▋ | 49868/57600 [8:46:16<1:21:20,  1.58it/s]
 87%|████████▋ | 49869/57600 [8:46:16<1:21:57,  1.57it/s]
 87%|████████▋ | 49870/57600 [8:46:17<1:24:47,  1.52it/s]
 87%|████████▋ | 49871/57600 [8:46:18<1:21:54,  1.57it/s]
 87%|████████▋ | 49872/57600 [8:46:18<1:20:42,  1.60it/s]
 87%|████████▋ | 49873/57600 [8:46:19<1:21:22,  1.58it/s]
 87%|████████▋ | 49874/57600 [8:46:20<1:24:02,  1.53it/s]
 87%|████████▋ | 49875/57600 [8:46:20<1:24:38,  1.52it/s]
 87%|████████▋ | 49876/57600 [8:46:21<1:22:39,  1.56it/s]
 87%|████████▋ | 49877/57600 [8:46:21<1:22:05,  1.57it/s]
 87%|████████▋ | 49878/57600 [8:46:22<1:21:23,  1.58it/s]
 87%|████████▋ | 49879/57600 [8:46:23<1:19:55,  1.61it/s]
 87%|████████▋ | 49880/57600 [8:46:23<1:19:51,  1.61it/s]
                                                         
{'loss': 1.103, 'learning_rate': 2.2104529616724734e-07, 'epoch': 550.55}

 87%|████████▋ | 49880/57600 [8:46:23<1:19:51,  1.61it/s]
 87%|████████▋ | 49881/57600 [8:46:24<1:18:47,  1.63it/s]
 87%|████████▋ | 49882/57600 [8:46:24<1:16:41,  1.68it/s]
 87%|████████▋ | 49883/57600 [8:46:25<1:15:35,  1.70it/s]
 87%|████████▋ | 49884/57600 [8:46:26<1:17:33,  1.66it/s]
 87%|████████▋ | 49885/57600 [8:46:26<1:18:31,  1.64it/s]
 87%|████████▋ | 49886/57600 [8:46:27<1:18:11,  1.64it/s]
 87%|████████▋ | 49887/57600 [8:46:27<1:17:56,  1.65it/s]
 87%|████████▋ | 49888/57600 [8:46:28<1:18:37,  1.63it/s]
 87%|████████▋ | 49889/57600 [8:46:29<1:21:01,  1.59it/s]
 87%|████████▋ | 49890/57600 [8:46:29<1:23:56,  1.53it/s]
 87%|████████▋ | 49891/57600 [8:46:30<1:23:16,  1.54it/s]
 87%|████████▋ | 49892/57600 [8:46:31<1:23:02,  1.55it/s]
 87%|████████▋ | 49893/57600 [8:46:31<1:21:56,  1.57it/s]
 87%|████████▋ | 49894/57600 [8:46:32<1:19:23,  1.62it/s]
 87%|████████▋ | 49895/57600 [8:46:33<1:18:30,  1.64it/s]
 87%|████████▋ | 49896/57600 [8:46:33<1:18:24,  1.64it/s]
 87%|████████▋ | 49897/57600 [8:46:34<1:20:39,  1.59it/s]
 87%|████████▋ | 49898/57600 [8:46:34<1:19:37,  1.61it/s]
 87%|████████▋ | 49899/57600 [8:46:35<1:18:09,  1.64it/s]
 87%|████████▋ | 49900/57600 [8:46:36<1:20:05,  1.60it/s]
                                                         
{'loss': 1.1474, 'learning_rate': 2.2073170731707317e-07, 'epoch': 550.77}

 87%|████████▋ | 49900/57600 [8:46:36<1:20:05,  1.60it/s]
 87%|████████▋ | 49901/57600 [8:46:36<1:21:58,  1.57it/s]
 87%|████████▋ | 49902/57600 [8:46:37<1:20:41,  1.59it/s]
 87%|████████▋ | 49903/57600 [8:46:38<1:19:58,  1.60it/s]
 87%|████████▋ | 49904/57600 [8:46:38<1:19:37,  1.61it/s]
 87%|████████▋ | 49905/57600 [8:46:39<1:18:25,  1.64it/s]
 87%|████████▋ | 49906/57600 [8:46:39<1:18:56,  1.62it/s]
 87%|████████▋ | 49907/57600 [8:46:40<1:20:44,  1.59it/s]
 87%|████████▋ | 49908/57600 [8:46:41<1:20:25,  1.59it/s]
 87%|████████▋ | 49909/57600 [8:46:41<1:24:30,  1.52it/s]
 87%|████████▋ | 49910/57600 [8:46:42<1:20:29,  1.59it/s]
 87%|████████▋ | 49911/57600 [8:46:43<1:20:22,  1.59it/s]
 87%|████████▋ | 49912/57600 [8:46:43<1:18:41,  1.63it/s]
 87%|████████▋ | 49913/57600 [8:46:44<1:17:44,  1.65it/s]
 87%|████████▋ | 49914/57600 [8:46:44<1:17:16,  1.66it/s]
 87%|████████▋ | 49915/57600 [8:46:45<1:19:59,  1.60it/s]
 87%|████████▋ | 49916/57600 [8:46:46<1:21:35,  1.57it/s]
 87%|████████▋ | 49917/57600 [8:46:46<1:22:54,  1.54it/s]
 87%|████████▋ | 49918/57600 [8:46:47<1:25:42,  1.49it/s]
 87%|████████▋ | 49919/57600 [8:46:48<1:24:05,  1.52it/s]
 87%|████████▋ | 49920/57600 [8:46:48<1:21:16,  1.57it/s]
                                                         
{'loss': 1.1227, 'learning_rate': 2.20418118466899e-07, 'epoch': 550.99}

 87%|████████▋ | 49920/57600 [8:46:48<1:21:16,  1.57it/s]
 87%|████████▋ | 49921/57600 [8:46:49<1:23:23,  1.53it/s]
 87%|████████▋ | 49922/57600 [8:46:50<1:22:38,  1.55it/s]
 87%|████████▋ | 49923/57600 [8:46:50<1:19:40,  1.61it/s]
 87%|████████▋ | 49924/57600 [8:46:51<1:18:48,  1.62it/s]
 87%|████████▋ | 49925/57600 [8:46:51<1:19:49,  1.60it/s]
 87%|████████▋ | 49926/57600 [8:46:52<1:18:56,  1.62it/s]
 87%|████████▋ | 49927/57600 [8:46:53<1:19:33,  1.61it/s]
 87%|████████▋ | 49928/57600 [8:46:53<1:18:10,  1.64it/s]
 87%|████████▋ | 49929/57600 [8:46:54<1:19:05,  1.62it/s]
 87%|████████▋ | 49930/57600 [8:46:54<1:19:30,  1.61it/s]
 87%|████████▋ | 49931/57600 [8:46:55<1:19:42,  1.60it/s]
 87%|████████▋ | 49932/57600 [8:46:56<1:21:14,  1.57it/s]
 87%|████████▋ | 49933/57600 [8:46:56<1:19:26,  1.61it/s]
 87%|████████▋ | 49934/57600 [8:46:57<1:18:32,  1.63it/s]
 87%|████████▋ | 49935/57600 [8:46:58<1:16:23,  1.67it/s]
 87%|████████▋ | 49936/57600 [8:46:58<1:15:41,  1.69it/s]
 87%|████████▋ | 49937/57600 [8:46:59<1:17:40,  1.64it/s]
 87%|████████▋ | 49938/57600 [8:46:59<1:18:08,  1.63it/s]
 87%|████████▋ | 49939/57600 [8:47:00<1:17:09,  1.65it/s]
 87%|████████▋ | 49940/57600 [8:47:01<1:17:49,  1.64it/s]
                                                         
{'loss': 1.1563, 'learning_rate': 2.2010452961672473e-07, 'epoch': 551.21}

 87%|████████▋ | 49940/57600 [8:47:01<1:17:49,  1.64it/s]
 87%|████████▋ | 49941/57600 [8:47:01<1:18:45,  1.62it/s]
 87%|████████▋ | 49942/57600 [8:47:02<1:17:03,  1.66it/s]
 87%|████████▋ | 49943/57600 [8:47:02<1:17:53,  1.64it/s]
 87%|████████▋ | 49944/57600 [8:47:03<1:18:36,  1.62it/s]
 87%|████████▋ | 49945/57600 [8:47:04<1:17:43,  1.64it/s]
 87%|████████▋ | 49946/57600 [8:47:04<1:17:59,  1.64it/s]
 87%|████████▋ | 49947/57600 [8:47:05<1:19:13,  1.61it/s]
 87%|████████▋ | 49948/57600 [8:47:05<1:18:21,  1.63it/s]
 87%|████████▋ | 49949/57600 [8:47:06<1:21:24,  1.57it/s]
 87%|████████▋ | 49950/57600 [8:47:07<1:20:05,  1.59it/s]
 87%|████████▋ | 49951/57600 [8:47:07<1:18:52,  1.62it/s]
 87%|████████▋ | 49952/57600 [8:47:08<1:20:16,  1.59it/s]
 87%|████████▋ | 49953/57600 [8:47:09<1:22:06,  1.55it/s]
 87%|████████▋ | 49954/57600 [8:47:09<1:22:26,  1.55it/s]
 87%|████████▋ | 49955/57600 [8:47:10<1:22:05,  1.55it/s]
 87%|████████▋ | 49956/57600 [8:47:11<1:21:18,  1.57it/s]
 87%|████████▋ | 49957/57600 [8:47:11<1:21:09,  1.57it/s]
 87%|████████▋ | 49958/57600 [8:47:12<1:19:50,  1.60it/s]
 87%|████████▋ | 49959/57600 [8:47:12<1:19:10,  1.61it/s]
 87%|████████▋ | 49960/57600 [8:47:13<1:19:02,  1.61it/s]
                                                         
{'loss': 1.1112, 'learning_rate': 2.1979094076655056e-07, 'epoch': 551.43}

 87%|████████▋ | 49960/57600 [8:47:13<1:19:02,  1.61it/s]
 87%|████████▋ | 49961/57600 [8:47:14<1:19:49,  1.60it/s]
 87%|████████▋ | 49962/57600 [8:47:14<1:20:57,  1.57it/s]
 87%|████████▋ | 49963/57600 [8:47:15<1:23:29,  1.52it/s]
 87%|████████▋ | 49964/57600 [8:47:16<1:24:19,  1.51it/s]
 87%|████████▋ | 49965/57600 [8:47:16<1:22:36,  1.54it/s]
 87%|████████▋ | 49966/57600 [8:47:17<1:25:07,  1.49it/s]
 87%|████████▋ | 49967/57600 [8:47:18<1:25:30,  1.49it/s]
 87%|████████▋ | 49968/57600 [8:47:18<1:23:05,  1.53it/s]
 87%|████████▋ | 49969/57600 [8:47:19<1:20:39,  1.58it/s]
 87%|████████▋ | 49970/57600 [8:47:20<1:20:55,  1.57it/s]
 87%|████████▋ | 49971/57600 [8:47:20<1:22:29,  1.54it/s]
 87%|████████▋ | 49972/57600 [8:47:21<1:24:56,  1.50it/s]
 87%|████████▋ | 49973/57600 [8:47:22<1:24:55,  1.50it/s]
 87%|████████▋ | 49974/57600 [8:47:22<1:24:52,  1.50it/s]
 87%|████████▋ | 49975/57600 [8:47:23<1:24:41,  1.50it/s]
 87%|████████▋ | 49976/57600 [8:47:24<1:22:48,  1.53it/s]
 87%|████████▋ | 49977/57600 [8:47:24<1:27:42,  1.45it/s]
 87%|████████▋ | 49978/57600 [8:47:25<1:24:32,  1.50it/s]
 87%|████████▋ | 49979/57600 [8:47:26<1:24:52,  1.50it/s]
 87%|████████▋ | 49980/57600 [8:47:26<1:28:18,  1.44it/s]
                                                         
{'loss': 1.0947, 'learning_rate': 2.1947735191637628e-07, 'epoch': 551.66}

 87%|████████▋ | 49980/57600 [8:47:26<1:28:18,  1.44it/s]
 87%|████████▋ | 49981/57600 [8:47:27<1:24:49,  1.50it/s]
 87%|████████▋ | 49982/57600 [8:47:28<1:24:57,  1.49it/s]
 87%|████████▋ | 49983/57600 [8:47:28<1:25:24,  1.49it/s]
 87%|████████▋ | 49984/57600 [8:47:29<1:23:27,  1.52it/s]
 87%|████████▋ | 49985/57600 [8:47:30<1:22:21,  1.54it/s]
 87%|████████▋ | 49986/57600 [8:47:30<1:24:04,  1.51it/s]
 87%|████████▋ | 49987/57600 [8:47:31<1:24:07,  1.51it/s]
 87%|████████▋ | 49988/57600 [8:47:32<1:23:27,  1.52it/s]
 87%|████████▋ | 49989/57600 [8:47:32<1:23:20,  1.52it/s]
 87%|████████▋ | 49990/57600 [8:47:33<1:24:08,  1.51it/s]
 87%|████████▋ | 49991/57600 [8:47:34<1:21:18,  1.56it/s]
 87%|████████▋ | 49992/57600 [8:47:34<1:21:53,  1.55it/s]
 87%|████████▋ | 49993/57600 [8:47:35<1:20:00,  1.58it/s]
 87%|████████▋ | 49994/57600 [8:47:36<1:24:12,  1.51it/s]
 87%|████████▋ | 49995/57600 [8:47:36<1:25:06,  1.49it/s]
 87%|████████▋ | 49996/57600 [8:47:37<1:26:24,  1.47it/s]
 87%|████████▋ | 49997/57600 [8:47:38<1:28:22,  1.43it/s]
 87%|████████▋ | 49998/57600 [8:47:38<1:31:23,  1.39it/s]
 87%|████████▋ | 49999/57600 [8:47:39<1:29:12,  1.42it/s]
 87%|████████▋ | 50000/57600 [8:47:40<1:27:27,  1.45it/s]
                                                         
{'loss': 1.0799, 'learning_rate': 2.1916376306620206e-07, 'epoch': 551.88}

 87%|████████▋ | 50000/57600 [8:47:40<1:27:27,  1.45it/s]
 87%|████████▋ | 50001/57600 [8:47:40<1:25:12,  1.49it/s]
 87%|████████▋ | 50002/57600 [8:47:41<1:25:44,  1.48it/s]
 87%|████████▋ | 50003/57600 [8:47:42<1:23:41,  1.51it/s]
 87%|████████▋ | 50004/57600 [8:47:42<1:21:48,  1.55it/s]
 87%|████████▋ | 50005/57600 [8:47:43<1:21:11,  1.56it/s]
 87%|████████▋ | 50006/57600 [8:47:44<1:21:44,  1.55it/s]
 87%|████████▋ | 50007/57600 [8:47:44<1:22:08,  1.54it/s]
 87%|████████▋ | 50008/57600 [8:47:45<1:21:24,  1.55it/s]
 87%|████████▋ | 50009/57600 [8:47:46<1:24:59,  1.49it/s]
 87%|████████▋ | 50010/57600 [8:47:46<1:26:23,  1.46it/s]
 87%|████████▋ | 50011/57600 [8:47:47<1:26:55,  1.45it/s]
 87%|████████▋ | 50012/57600 [8:47:48<1:27:56,  1.44it/s]
 87%|████████▋ | 50013/57600 [8:47:49<1:30:05,  1.40it/s]
 87%|████████▋ | 50014/57600 [8:47:49<1:26:40,  1.46it/s]
 87%|████████▋ | 50015/57600 [8:47:50<1:24:06,  1.50it/s]
 87%|████████▋ | 50016/57600 [8:47:50<1:23:42,  1.51it/s]
 87%|████████▋ | 50017/57600 [8:47:51<1:22:09,  1.54it/s]
 87%|████████▋ | 50018/57600 [8:47:52<1:25:49,  1.47it/s]
 87%|████████▋ | 50019/57600 [8:47:52<1:25:36,  1.48it/s]
 87%|████████▋ | 50020/57600 [8:47:53<1:25:41,  1.47it/s]
                                                         
{'loss': 1.0955, 'learning_rate': 2.1885017421602784e-07, 'epoch': 552.1}

 87%|████████▋ | 50020/57600 [8:47:53<1:25:41,  1.47it/s]
 87%|████████▋ | 50021/57600 [8:47:54<1:23:55,  1.51it/s]
 87%|████████▋ | 50022/57600 [8:47:54<1:24:33,  1.49it/s]
 87%|████████▋ | 50023/57600 [8:47:55<1:25:44,  1.47it/s]
 87%|████████▋ | 50024/57600 [8:47:56<1:25:17,  1.48it/s]
 87%|████████▋ | 50025/57600 [8:47:56<1:22:55,  1.52it/s]
 87%|████████▋ | 50026/57600 [8:47:57<1:21:12,  1.55it/s]
 87%|████████▋ | 50027/57600 [8:47:58<1:21:42,  1.54it/s]
 87%|████████▋ | 50028/57600 [8:47:58<1:22:26,  1.53it/s]
 87%|████████▋ | 50029/57600 [8:47:59<1:20:36,  1.57it/s]
 87%|████████▋ | 50030/57600 [8:48:00<1:20:18,  1.57it/s]
 87%|████████▋ | 50031/57600 [8:48:00<1:20:02,  1.58it/s]
 87%|████████▋ | 50032/57600 [8:48:01<1:18:50,  1.60it/s]
 87%|████████▋ | 50033/57600 [8:48:02<1:20:41,  1.56it/s]
 87%|████████▋ | 50034/57600 [8:48:02<1:19:48,  1.58it/s]
 87%|████████▋ | 50035/57600 [8:48:03<1:21:00,  1.56it/s]
 87%|████████▋ | 50036/57600 [8:48:03<1:21:08,  1.55it/s]
 87%|████████▋ | 50037/57600 [8:48:04<1:23:39,  1.51it/s]
 87%|████████▋ | 50038/57600 [8:48:05<1:24:52,  1.48it/s]
 87%|████████▋ | 50039/57600 [8:48:06<1:24:31,  1.49it/s]
 87%|████████▋ | 50040/57600 [8:48:06<1:24:40,  1.49it/s]
                                                         
{'loss': 1.1181, 'learning_rate': 2.1853658536585364e-07, 'epoch': 552.32}

 87%|████████▋ | 50040/57600 [8:48:06<1:24:40,  1.49it/s]
 87%|████████▋ | 50041/57600 [8:48:07<1:26:31,  1.46it/s]
 87%|████████▋ | 50042/57600 [8:48:08<1:24:36,  1.49it/s]
 87%|████████▋ | 50043/57600 [8:48:08<1:23:47,  1.50it/s]
 87%|████████▋ | 50044/57600 [8:48:09<1:21:51,  1.54it/s]
 87%|████████▋ | 50045/57600 [8:48:10<1:24:28,  1.49it/s]
 87%|████████▋ | 50046/57600 [8:48:10<1:25:16,  1.48it/s]
 87%|████████▋ | 50047/57600 [8:48:11<1:24:43,  1.49it/s]
 87%|████████▋ | 50048/57600 [8:48:12<1:23:49,  1.50it/s]
 87%|████████▋ | 50049/57600 [8:48:12<1:24:03,  1.50it/s]
 87%|████████▋ | 50050/57600 [8:48:13<1:21:39,  1.54it/s]
 87%|████████▋ | 50051/57600 [8:48:14<1:22:13,  1.53it/s]
 87%|████████▋ | 50052/57600 [8:48:14<1:23:17,  1.51it/s]
 87%|████████▋ | 50053/57600 [8:48:15<1:24:50,  1.48it/s]
 87%|████████▋ | 50054/57600 [8:48:16<1:24:23,  1.49it/s]
 87%|████████▋ | 50055/57600 [8:48:16<1:21:42,  1.54it/s]
 87%|████████▋ | 50056/57600 [8:48:17<1:22:26,  1.53it/s]
 87%|████████▋ | 50057/57600 [8:48:18<1:23:34,  1.50it/s]
 87%|████████▋ | 50058/57600 [8:48:18<1:22:22,  1.53it/s]
 87%|████████▋ | 50059/57600 [8:48:19<1:20:35,  1.56it/s]
 87%|████████▋ | 50060/57600 [8:48:19<1:19:17,  1.58it/s]
                                                         
{'loss': 1.1288, 'learning_rate': 2.1822299651567948e-07, 'epoch': 552.54}

 87%|████████▋ | 50060/57600 [8:48:19<1:19:17,  1.58it/s]
 87%|████████▋ | 50061/57600 [8:48:20<1:22:05,  1.53it/s]
 87%|████████▋ | 50062/57600 [8:48:21<1:21:43,  1.54it/s]
 87%|████████▋ | 50063/57600 [8:48:21<1:19:21,  1.58it/s]
 87%|████████▋ | 50064/57600 [8:48:22<1:21:41,  1.54it/s]
 87%|████████▋ | 50065/57600 [8:48:23<1:21:23,  1.54it/s]
 87%|████████▋ | 50066/57600 [8:48:23<1:21:40,  1.54it/s]
 87%|████████▋ | 50067/57600 [8:48:24<1:19:26,  1.58it/s]
 87%|████████▋ | 50068/57600 [8:48:25<1:20:21,  1.56it/s]
 87%|████████▋ | 50069/57600 [8:48:25<1:19:09,  1.59it/s]
 87%|████████▋ | 50070/57600 [8:48:26<1:18:41,  1.59it/s]
 87%|████████▋ | 50071/57600 [8:48:26<1:18:27,  1.60it/s]
 87%|████████▋ | 50072/57600 [8:48:27<1:19:21,  1.58it/s]
 87%|████████▋ | 50073/57600 [8:48:28<1:18:11,  1.60it/s]
 87%|████████▋ | 50074/57600 [8:48:28<1:17:36,  1.62it/s]
 87%|████████▋ | 50075/57600 [8:48:29<1:16:40,  1.64it/s]
 87%|████████▋ | 50076/57600 [8:48:30<1:18:55,  1.59it/s]
 87%|████████▋ | 50077/57600 [8:48:30<1:18:58,  1.59it/s]
 87%|████████▋ | 50078/57600 [8:48:31<1:19:03,  1.59it/s]
 87%|████████▋ | 50079/57600 [8:48:31<1:18:45,  1.59it/s]
 87%|████████▋ | 50080/57600 [8:48:32<1:19:35,  1.57it/s]
                                                         
{'loss': 1.1118, 'learning_rate': 2.179094076655052e-07, 'epoch': 552.76}

 87%|████████▋ | 50080/57600 [8:48:32<1:19:35,  1.57it/s]
 87%|████████▋ | 50081/57600 [8:48:33<1:22:01,  1.53it/s]
 87%|████████▋ | 50082/57600 [8:48:33<1:22:09,  1.53it/s]
 87%|████████▋ | 50083/57600 [8:48:34<1:24:28,  1.48it/s]
 87%|████████▋ | 50084/57600 [8:48:35<1:21:56,  1.53it/s]
 87%|████████▋ | 50085/57600 [8:48:35<1:20:50,  1.55it/s]
 87%|████████▋ | 50086/57600 [8:48:36<1:21:21,  1.54it/s]
 87%|████████▋ | 50087/57600 [8:48:37<1:21:14,  1.54it/s]
 87%|████████▋ | 50088/57600 [8:48:37<1:21:23,  1.54it/s]
 87%|████████▋ | 50089/57600 [8:48:38<1:21:10,  1.54it/s]
 87%|████████▋ | 50090/57600 [8:48:39<1:22:18,  1.52it/s]
 87%|████████▋ | 50091/57600 [8:48:39<1:23:31,  1.50it/s]
 87%|████████▋ | 50092/57600 [8:48:40<1:24:56,  1.47it/s]
 87%|████████▋ | 50093/57600 [8:48:41<1:22:02,  1.52it/s]
 87%|████████▋ | 50094/57600 [8:48:41<1:21:30,  1.53it/s]
 87%|████████▋ | 50095/57600 [8:48:42<1:21:39,  1.53it/s]
 87%|████████▋ | 50096/57600 [8:48:43<1:20:30,  1.55it/s]
 87%|████████▋ | 50097/57600 [8:48:43<1:18:49,  1.59it/s]
 87%|████████▋ | 50098/57600 [8:48:44<1:18:32,  1.59it/s]
 87%|████████▋ | 50099/57600 [8:48:44<1:17:57,  1.60it/s]
 87%|████████▋ | 50100/57600 [8:48:45<1:17:25,  1.61it/s]
                                                         
{'loss': 1.0934, 'learning_rate': 2.1759581881533103e-07, 'epoch': 552.98}

 87%|████████▋ | 50100/57600 [8:48:45<1:17:25,  1.61it/s]
 87%|████████▋ | 50101/57600 [8:48:46<1:17:17,  1.62it/s]
 87%|████████▋ | 50102/57600 [8:48:46<1:21:23,  1.54it/s]
 87%|████████▋ | 50103/57600 [8:48:47<1:20:14,  1.56it/s]
 87%|████████▋ | 50104/57600 [8:48:48<1:17:54,  1.60it/s]
 87%|████████▋ | 50105/57600 [8:48:48<1:19:25,  1.57it/s]
 87%|████████▋ | 50106/57600 [8:48:49<1:21:39,  1.53it/s]
 87%|████████▋ | 50107/57600 [8:48:50<1:22:28,  1.51it/s]
 87%|████████▋ | 50108/57600 [8:48:50<1:21:56,  1.52it/s]
 87%|████████▋ | 50109/57600 [8:48:51<1:20:27,  1.55it/s]
 87%|████████▋ | 50110/57600 [8:48:52<1:22:31,  1.51it/s]
 87%|████████▋ | 50111/57600 [8:48:52<1:22:34,  1.51it/s]
 87%|████████▋ | 50112/57600 [8:48:53<1:21:52,  1.52it/s]
 87%|████████▋ | 50113/57600 [8:48:53<1:20:19,  1.55it/s]
 87%|████████▋ | 50114/57600 [8:48:54<1:19:48,  1.56it/s]
 87%|████████▋ | 50115/57600 [8:48:55<1:21:26,  1.53it/s]
 87%|████████▋ | 50116/57600 [8:48:55<1:23:18,  1.50it/s]
 87%|████████▋ | 50117/57600 [8:48:56<1:24:08,  1.48it/s]
 87%|████████▋ | 50118/57600 [8:48:57<1:24:56,  1.47it/s]
 87%|████████▋ | 50119/57600 [8:48:58<1:23:35,  1.49it/s]
 87%|████████▋ | 50120/57600 [8:48:58<1:23:17,  1.50it/s]
                                                         
{'loss': 1.0997, 'learning_rate': 2.1728222996515673e-07, 'epoch': 553.2}

 87%|████████▋ | 50120/57600 [8:48:58<1:23:17,  1.50it/s]
 87%|████████▋ | 50121/57600 [8:48:59<1:21:32,  1.53it/s]
 87%|████████▋ | 50122/57600 [8:48:59<1:20:30,  1.55it/s]
 87%|████████▋ | 50123/57600 [8:49:00<1:21:36,  1.53it/s]
 87%|████████▋ | 50124/57600 [8:49:01<1:24:49,  1.47it/s]
 87%|████████▋ | 50125/57600 [8:49:01<1:23:26,  1.49it/s]
 87%|████████▋ | 50126/57600 [8:49:02<1:21:58,  1.52it/s]
 87%|████████▋ | 50127/57600 [8:49:03<1:21:47,  1.52it/s]
 87%|████████▋ | 50128/57600 [8:49:03<1:22:27,  1.51it/s]
 87%|████████▋ | 50129/57600 [8:49:04<1:22:13,  1.51it/s]
 87%|████████▋ | 50130/57600 [8:49:05<1:22:27,  1.51it/s]
 87%|████████▋ | 50131/57600 [8:49:05<1:21:11,  1.53it/s]
 87%|████████▋ | 50132/57600 [8:49:06<1:21:52,  1.52it/s]
 87%|████████▋ | 50133/57600 [8:49:07<1:23:31,  1.49it/s]
 87%|████████▋ | 50134/57600 [8:49:07<1:23:32,  1.49it/s]
 87%|████████▋ | 50135/57600 [8:49:08<1:20:36,  1.54it/s]
 87%|████████▋ | 50136/57600 [8:49:09<1:19:31,  1.56it/s]
 87%|████████▋ | 50137/57600 [8:49:09<1:19:04,  1.57it/s]
 87%|████████▋ | 50138/57600 [8:49:10<1:18:59,  1.57it/s]
 87%|████████▋ | 50139/57600 [8:49:11<1:20:01,  1.55it/s]
 87%|████████▋ | 50140/57600 [8:49:11<1:18:33,  1.58it/s]
                                                         
{'loss': 1.1146, 'learning_rate': 2.169686411149826e-07, 'epoch': 553.42}

 87%|████████▋ | 50140/57600 [8:49:11<1:18:33,  1.58it/s]
 87%|████████▋ | 50141/57600 [8:49:12<1:21:16,  1.53it/s]
 87%|████████▋ | 50142/57600 [8:49:13<1:19:56,  1.55it/s]
 87%|████████▋ | 50143/57600 [8:49:13<1:20:47,  1.54it/s]
 87%|████████▋ | 50144/57600 [8:49:14<1:23:04,  1.50it/s]
 87%|████████▋ | 50145/57600 [8:49:15<1:22:06,  1.51it/s]
 87%|████████▋ | 50146/57600 [8:49:15<1:23:20,  1.49it/s]
 87%|████████▋ | 50147/57600 [8:49:16<1:24:45,  1.47it/s]
 87%|████████▋ | 50148/57600 [8:49:17<1:25:34,  1.45it/s]
 87%|████████▋ | 50149/57600 [8:49:17<1:23:45,  1.48it/s]
 87%|████████▋ | 50150/57600 [8:49:18<1:22:53,  1.50it/s]
 87%|████████▋ | 50151/57600 [8:49:19<1:21:41,  1.52it/s]
 87%|████████▋ | 50152/57600 [8:49:19<1:21:26,  1.52it/s]
 87%|████████▋ | 50153/57600 [8:49:20<1:19:48,  1.56it/s]
 87%|████████▋ | 50154/57600 [8:49:20<1:18:19,  1.58it/s]
 87%|████████▋ | 50155/57600 [8:49:21<1:20:07,  1.55it/s]
 87%|████████▋ | 50156/57600 [8:49:22<1:18:17,  1.58it/s]
 87%|████████▋ | 50157/57600 [8:49:22<1:18:18,  1.58it/s]
 87%|████████▋ | 50158/57600 [8:49:23<1:17:23,  1.60it/s]
 87%|████████▋ | 50159/57600 [8:49:24<1:17:20,  1.60it/s]
 87%|████████▋ | 50160/57600 [8:49:24<1:19:08,  1.57it/s]
                                                         
{'loss': 1.1399, 'learning_rate': 2.1665505226480831e-07, 'epoch': 553.64}

 87%|████████▋ | 50160/57600 [8:49:24<1:19:08,  1.57it/s]
 87%|████████▋ | 50161/57600 [8:49:25<1:17:49,  1.59it/s]
 87%|████████▋ | 50162/57600 [8:49:25<1:18:07,  1.59it/s]
 87%|████████▋ | 50163/57600 [8:49:26<1:20:11,  1.55it/s]
 87%|████████▋ | 50164/57600 [8:49:27<1:20:31,  1.54it/s]
 87%|████████▋ | 50165/57600 [8:49:28<1:21:32,  1.52it/s]
 87%|████████▋ | 50166/57600 [8:49:28<1:20:56,  1.53it/s]
 87%|████████▋ | 50167/57600 [8:49:29<1:19:12,  1.56it/s]
 87%|████████▋ | 50168/57600 [8:49:29<1:17:52,  1.59it/s]
 87%|████████▋ | 50169/57600 [8:49:30<1:16:19,  1.62it/s]
 87%|████████▋ | 50170/57600 [8:49:31<1:18:28,  1.58it/s]
 87%|████████▋ | 50171/57600 [8:49:31<1:22:37,  1.50it/s]
 87%|████████▋ | 50172/57600 [8:49:32<1:21:39,  1.52it/s]
 87%|████████▋ | 50173/57600 [8:49:33<1:23:01,  1.49it/s]
 87%|████████▋ | 50174/57600 [8:49:33<1:22:55,  1.49it/s]
 87%|████████▋ | 50175/57600 [8:49:34<1:23:25,  1.48it/s]
 87%|████████▋ | 50176/57600 [8:49:35<1:22:32,  1.50it/s]
 87%|████████▋ | 50177/57600 [8:49:35<1:21:42,  1.51it/s]
 87%|████████▋ | 50178/57600 [8:49:36<1:21:55,  1.51it/s]
 87%|████████▋ | 50179/57600 [8:49:37<1:22:44,  1.49it/s]
 87%|████████▋ | 50180/57600 [8:49:37<1:24:15,  1.47it/s]
                                                         
{'loss': 1.105, 'learning_rate': 2.1634146341463415e-07, 'epoch': 553.86}

 87%|████████▋ | 50180/57600 [8:49:37<1:24:15,  1.47it/s]
 87%|████████▋ | 50181/57600 [8:49:38<1:20:53,  1.53it/s]
 87%|████████▋ | 50182/57600 [8:49:39<1:19:54,  1.55it/s]
 87%|████████▋ | 50183/57600 [8:49:39<1:19:27,  1.56it/s]
 87%|████████▋ | 50184/57600 [8:49:40<1:17:14,  1.60it/s]
 87%|████████▋ | 50185/57600 [8:49:40<1:17:37,  1.59it/s]
 87%|████████▋ | 50186/57600 [8:49:41<1:17:49,  1.59it/s]
 87%|████████▋ | 50187/57600 [8:49:42<1:16:52,  1.61it/s]
 87%|████████▋ | 50188/57600 [8:49:42<1:16:06,  1.62it/s]
 87%|████████▋ | 50189/57600 [8:49:43<1:19:40,  1.55it/s]
 87%|████████▋ | 50190/57600 [8:49:44<1:21:04,  1.52it/s]
 87%|████████▋ | 50191/57600 [8:49:44<1:20:43,  1.53it/s]
 87%|████████▋ | 50192/57600 [8:49:45<1:20:00,  1.54it/s]
 87%|████████▋ | 50193/57600 [8:49:46<1:23:36,  1.48it/s]
 87%|████████▋ | 50194/57600 [8:49:46<1:23:51,  1.47it/s]
 87%|████████▋ | 50195/57600 [8:49:47<1:21:30,  1.51it/s]
 87%|████████▋ | 50196/57600 [8:49:48<1:20:10,  1.54it/s]
 87%|████████▋ | 50197/57600 [8:49:48<1:19:11,  1.56it/s]
 87%|████████▋ | 50198/57600 [8:49:49<1:18:30,  1.57it/s]
 87%|████████▋ | 50199/57600 [8:49:50<1:17:25,  1.59it/s]
 87%|████████▋ | 50200/57600 [8:49:50<1:20:33,  1.53it/s]
                                                         
{'loss': 1.1155, 'learning_rate': 2.1602787456445998e-07, 'epoch': 554.08}

 87%|████████▋ | 50200/57600 [8:49:50<1:20:33,  1.53it/s]
 87%|████████▋ | 50201/57600 [8:49:51<1:22:33,  1.49it/s]
 87%|████████▋ | 50202/57600 [8:49:52<1:21:48,  1.51it/s]
 87%|████████▋ | 50203/57600 [8:49:52<1:24:17,  1.46it/s]
 87%|████████▋ | 50204/57600 [8:49:53<1:25:10,  1.45it/s]
 87%|████████▋ | 50205/57600 [8:49:54<1:22:52,  1.49it/s]
 87%|████████▋ | 50206/57600 [8:49:54<1:21:26,  1.51it/s]
 87%|████████▋ | 50207/57600 [8:49:55<1:21:03,  1.52it/s]
 87%|████████▋ | 50208/57600 [8:49:56<1:18:46,  1.56it/s]
 87%|████████▋ | 50209/57600 [8:49:56<1:19:22,  1.55it/s]
 87%|████████▋ | 50210/57600 [8:49:57<1:17:44,  1.58it/s]
 87%|████████▋ | 50211/57600 [8:49:57<1:18:28,  1.57it/s]
 87%|████████▋ | 50212/57600 [8:49:58<1:17:16,  1.59it/s]
 87%|████████▋ | 50213/57600 [8:49:59<1:18:16,  1.57it/s]
 87%|████████▋ | 50214/57600 [8:49:59<1:18:56,  1.56it/s]
 87%|████████▋ | 50215/57600 [8:50:00<1:17:45,  1.58it/s]
 87%|████████▋ | 50216/57600 [8:50:01<1:21:23,  1.51it/s]
 87%|████████▋ | 50217/57600 [8:50:01<1:19:51,  1.54it/s]
 87%|████████▋ | 50218/57600 [8:50:02<1:19:19,  1.55it/s]
 87%|████████▋ | 50219/57600 [8:50:03<1:17:21,  1.59it/s]
 87%|████████▋ | 50220/57600 [8:50:03<1:16:01,  1.62it/s]
                                                         
{'loss': 1.1422, 'learning_rate': 2.1571428571428568e-07, 'epoch': 554.3}

 87%|████████▋ | 50220/57600 [8:50:03<1:16:01,  1.62it/s]
 87%|████████▋ | 50221/57600 [8:50:04<1:16:19,  1.61it/s]
 87%|████████▋ | 50222/57600 [8:50:04<1:15:57,  1.62it/s]
 87%|████████▋ | 50223/57600 [8:50:05<1:18:32,  1.57it/s]
 87%|████████▋ | 50224/57600 [8:50:06<1:20:19,  1.53it/s]
 87%|████████▋ | 50225/57600 [8:50:06<1:19:41,  1.54it/s]
 87%|████████▋ | 50226/57600 [8:50:07<1:16:42,  1.60it/s]
 87%|████████▋ | 50227/57600 [8:50:08<1:15:41,  1.62it/s]
 87%|████████▋ | 50228/57600 [8:50:08<1:17:37,  1.58it/s]
 87%|████████▋ | 50229/57600 [8:50:09<1:18:30,  1.56it/s]
 87%|████████▋ | 50230/57600 [8:50:09<1:16:04,  1.61it/s]
 87%|████████▋ | 50231/57600 [8:50:10<1:15:58,  1.62it/s]
 87%|████████▋ | 50232/57600 [8:50:11<1:16:01,  1.62it/s]
 87%|████████▋ | 50233/57600 [8:50:11<1:16:34,  1.60it/s]
 87%|████████▋ | 50234/57600 [8:50:12<1:15:45,  1.62it/s]
 87%|████████▋ | 50235/57600 [8:50:13<1:14:59,  1.64it/s]
 87%|████████▋ | 50236/57600 [8:50:13<1:14:47,  1.64it/s]
 87%|████████▋ | 50237/57600 [8:50:14<1:16:23,  1.61it/s]
 87%|████████▋ | 50238/57600 [8:50:14<1:19:16,  1.55it/s]
 87%|████████▋ | 50239/57600 [8:50:15<1:20:16,  1.53it/s]
 87%|████████▋ | 50240/57600 [8:50:16<1:20:41,  1.52it/s]
                                                         
{'loss': 1.0936, 'learning_rate': 2.1540069686411153e-07, 'epoch': 554.53}

 87%|████████▋ | 50240/57600 [8:50:16<1:20:41,  1.52it/s]
 87%|████████▋ | 50241/57600 [8:50:16<1:20:34,  1.52it/s]
 87%|████████▋ | 50242/57600 [8:50:17<1:20:11,  1.53it/s]
 87%|████████▋ | 50243/57600 [8:50:18<1:18:33,  1.56it/s]
 87%|████████▋ | 50244/57600 [8:50:18<1:17:32,  1.58it/s]
 87%|████████▋ | 50245/57600 [8:50:19<1:17:00,  1.59it/s]
 87%|████████▋ | 50246/57600 [8:50:20<1:17:36,  1.58it/s]
 87%|████████▋ | 50247/57600 [8:50:20<1:18:48,  1.55it/s]
 87%|████████▋ | 50248/57600 [8:50:21<1:17:46,  1.58it/s]
 87%|████████▋ | 50249/57600 [8:50:22<1:18:25,  1.56it/s]
 87%|████████▋ | 50250/57600 [8:50:22<1:20:38,  1.52it/s]
 87%|████████▋ | 50251/57600 [8:50:23<1:21:02,  1.51it/s]
 87%|████████▋ | 50252/57600 [8:50:24<1:19:13,  1.55it/s]
 87%|████████▋ | 50253/57600 [8:50:24<1:21:06,  1.51it/s]
 87%|████████▋ | 50254/57600 [8:50:25<1:21:26,  1.50it/s]
 87%|████████▋ | 50255/57600 [8:50:26<1:20:56,  1.51it/s]
 87%|████████▋ | 50256/57600 [8:50:26<1:21:30,  1.50it/s]
 87%|████████▋ | 50257/57600 [8:50:27<1:21:18,  1.51it/s]
 87%|████████▋ | 50258/57600 [8:50:28<1:20:09,  1.53it/s]
 87%|████████▋ | 50259/57600 [8:50:28<1:19:26,  1.54it/s]
 87%|████████▋ | 50260/57600 [8:50:29<1:19:33,  1.54it/s]
                                                         
{'loss': 1.103, 'learning_rate': 2.1508710801393723e-07, 'epoch': 554.75}

 87%|████████▋ | 50260/57600 [8:50:29<1:19:33,  1.54it/s]
 87%|████████▋ | 50261/57600 [8:50:30<1:21:36,  1.50it/s]
 87%|████████▋ | 50262/57600 [8:50:30<1:23:00,  1.47it/s]
 87%|████████▋ | 50263/57600 [8:50:31<1:21:33,  1.50it/s]
 87%|████████▋ | 50264/57600 [8:50:32<1:23:18,  1.47it/s]
 87%|████████▋ | 50265/57600 [8:50:32<1:20:44,  1.51it/s]
 87%|████████▋ | 50266/57600 [8:50:33<1:20:00,  1.53it/s]
 87%|████████▋ | 50267/57600 [8:50:33<1:18:02,  1.57it/s]
 87%|████████▋ | 50268/57600 [8:50:34<1:16:46,  1.59it/s]
 87%|████████▋ | 50269/57600 [8:50:35<1:15:40,  1.61it/s]
 87%|████████▋ | 50270/57600 [8:50:35<1:16:14,  1.60it/s]
 87%|████████▋ | 50271/57600 [8:50:36<1:16:45,  1.59it/s]
 87%|████████▋ | 50272/57600 [8:50:36<1:15:00,  1.63it/s]
 87%|████████▋ | 50273/57600 [8:50:37<1:17:50,  1.57it/s]
 87%|████████▋ | 50274/57600 [8:50:38<1:15:31,  1.62it/s]
 87%|████████▋ | 50275/57600 [8:50:38<1:14:41,  1.63it/s]
 87%|████████▋ | 50276/57600 [8:50:39<1:17:26,  1.58it/s]
 87%|████████▋ | 50277/57600 [8:50:40<1:17:25,  1.58it/s]
 87%|████████▋ | 50278/57600 [8:50:40<1:16:04,  1.60it/s]
 87%|████████▋ | 50279/57600 [8:50:41<1:16:01,  1.60it/s]
 87%|████████▋ | 50280/57600 [8:50:42<1:16:54,  1.59it/s]
                                                         
{'loss': 1.1244, 'learning_rate': 2.147735191637631e-07, 'epoch': 554.97}

 87%|████████▋ | 50280/57600 [8:50:42<1:16:54,  1.59it/s]
 87%|████████▋ | 50281/57600 [8:50:42<1:16:21,  1.60it/s]
 87%|████████▋ | 50282/57600 [8:50:43<1:16:06,  1.60it/s]
 87%|████████▋ | 50283/57600 [8:50:43<1:16:51,  1.59it/s]
 87%|████████▋ | 50284/57600 [8:50:44<1:21:13,  1.50it/s]
 87%|████████▋ | 50285/57600 [8:50:45<1:21:24,  1.50it/s]
 87%|████████▋ | 50286/57600 [8:50:45<1:20:01,  1.52it/s]
 87%|████████▋ | 50287/57600 [8:50:46<1:18:06,  1.56it/s]
 87%|████████▋ | 50288/57600 [8:50:47<1:16:53,  1.58it/s]
 87%|████████▋ | 50289/57600 [8:50:47<1:17:47,  1.57it/s]
 87%|████████▋ | 50290/57600 [8:50:48<1:18:09,  1.56it/s]
 87%|████████▋ | 50291/57600 [8:50:49<1:15:19,  1.62it/s]
 87%|████████▋ | 50292/57600 [8:50:49<1:16:26,  1.59it/s]
 87%|████████▋ | 50293/57600 [8:50:50<1:16:15,  1.60it/s]
 87%|████████▋ | 50294/57600 [8:50:50<1:15:12,  1.62it/s]
 87%|████████▋ | 50295/57600 [8:50:51<1:16:06,  1.60it/s]
 87%|████████▋ | 50296/57600 [8:50:52<1:18:18,  1.55it/s]
 87%|████████▋ | 50297/57600 [8:50:52<1:17:43,  1.57it/s]
 87%|████████▋ | 50298/57600 [8:50:53<1:18:06,  1.56it/s]
 87%|████████▋ | 50299/57600 [8:50:54<1:18:42,  1.55it/s]
 87%|████████▋ | 50300/57600 [8:50:54<1:19:30,  1.53it/s]
                                                         
{'loss': 1.119, 'learning_rate': 2.144599303135888e-07, 'epoch': 555.19}

 87%|████████▋ | 50300/57600 [8:50:54<1:19:30,  1.53it/s]
 87%|████████▋ | 50301/57600 [8:50:55<1:20:45,  1.51it/s]
 87%|████████▋ | 50302/57600 [8:50:56<1:17:26,  1.57it/s]
 87%|████████▋ | 50303/57600 [8:50:56<1:17:34,  1.57it/s]
 87%|████████▋ | 50304/57600 [8:50:57<1:17:58,  1.56it/s]
 87%|████████▋ | 50305/57600 [8:50:58<1:16:32,  1.59it/s]
 87%|████████▋ | 50306/57600 [8:50:58<1:15:54,  1.60it/s]
 87%|████████▋ | 50307/57600 [8:50:59<1:19:47,  1.52it/s]
 87%|████████▋ | 50308/57600 [8:50:59<1:17:52,  1.56it/s]
 87%|████████▋ | 50309/57600 [8:51:00<1:22:24,  1.47it/s]
 87%|████████▋ | 50310/57600 [8:51:01<1:22:49,  1.47it/s]
 87%|████████▋ | 50311/57600 [8:51:02<1:19:22,  1.53it/s]
 87%|████████▋ | 50312/57600 [8:51:02<1:18:41,  1.54it/s]
 87%|████████▋ | 50313/57600 [8:51:03<1:16:39,  1.58it/s]
 87%|████████▋ | 50314/57600 [8:51:03<1:15:41,  1.60it/s]
 87%|████████▋ | 50315/57600 [8:51:04<1:18:39,  1.54it/s]
 87%|████████▋ | 50316/57600 [8:51:05<1:22:17,  1.48it/s]
 87%|████████▋ | 50317/57600 [8:51:05<1:19:05,  1.53it/s]
 87%|████████▋ | 50318/57600 [8:51:06<1:18:57,  1.54it/s]
 87%|████████▋ | 50319/57600 [8:51:07<1:19:35,  1.52it/s]
 87%|████████▋ | 50320/57600 [8:51:07<1:18:36,  1.54it/s]
                                                         
{'loss': 1.1021, 'learning_rate': 2.1414634146341462e-07, 'epoch': 555.41}

 87%|████████▋ | 50320/57600 [8:51:07<1:18:36,  1.54it/s]
 87%|████████▋ | 50321/57600 [8:51:08<1:16:18,  1.59it/s]
 87%|████████▋ | 50322/57600 [8:51:09<1:14:51,  1.62it/s]
 87%|████████▋ | 50323/57600 [8:51:09<1:13:40,  1.65it/s]
 87%|████████▋ | 50324/57600 [8:51:10<1:17:16,  1.57it/s]
 87%|████████▋ | 50325/57600 [8:51:10<1:15:31,  1.61it/s]
 87%|████████▋ | 50326/57600 [8:51:11<1:14:05,  1.64it/s]
 87%|████████▋ | 50327/57600 [8:51:12<1:13:21,  1.65it/s]
 87%|████████▋ | 50328/57600 [8:51:12<1:16:28,  1.58it/s]
 87%|████████▋ | 50329/57600 [8:51:13<1:16:04,  1.59it/s]
 87%|████████▋ | 50330/57600 [8:51:14<1:16:48,  1.58it/s]
 87%|████████▋ | 50331/57600 [8:51:14<1:14:46,  1.62it/s]
 87%|████████▋ | 50332/57600 [8:51:15<1:14:45,  1.62it/s]
 87%|████████▋ | 50333/57600 [8:51:15<1:15:09,  1.61it/s]
 87%|████████▋ | 50334/57600 [8:51:16<1:16:38,  1.58it/s]
 87%|████████▋ | 50335/57600 [8:51:17<1:16:17,  1.59it/s]
 87%|████████▋ | 50336/57600 [8:51:17<1:17:37,  1.56it/s]
 87%|████████▋ | 50337/57600 [8:51:18<1:16:48,  1.58it/s]
 87%|████████▋ | 50338/57600 [8:51:19<1:19:35,  1.52it/s]
 87%|████████▋ | 50339/57600 [8:51:19<1:17:56,  1.55it/s]
 87%|████████▋ | 50340/57600 [8:51:20<1:17:35,  1.56it/s]
                                                         
{'loss': 1.1232, 'learning_rate': 2.1383275261324045e-07, 'epoch': 555.63}

 87%|████████▋ | 50340/57600 [8:51:20<1:17:35,  1.56it/s]
 87%|████████▋ | 50341/57600 [8:51:21<1:18:26,  1.54it/s]
 87%|████████▋ | 50342/57600 [8:51:21<1:18:12,  1.55it/s]
 87%|████████▋ | 50343/57600 [8:51:22<1:18:13,  1.55it/s]
 87%|████████▋ | 50344/57600 [8:51:23<1:19:41,  1.52it/s]
 87%|████████▋ | 50345/57600 [8:51:23<1:19:03,  1.53it/s]
 87%|████████▋ | 50346/57600 [8:51:24<1:17:38,  1.56it/s]
 87%|████████▋ | 50347/57600 [8:51:24<1:15:35,  1.60it/s]
 87%|████████▋ | 50348/57600 [8:51:25<1:15:14,  1.61it/s]
 87%|████████▋ | 50349/57600 [8:51:26<1:15:03,  1.61it/s]
 87%|████████▋ | 50350/57600 [8:51:26<1:16:22,  1.58it/s]
 87%|████████▋ | 50351/57600 [8:51:27<1:16:07,  1.59it/s]
 87%|████████▋ | 50352/57600 [8:51:28<1:16:12,  1.59it/s]
 87%|████████▋ | 50353/57600 [8:51:28<1:17:10,  1.57it/s]
 87%|████████▋ | 50354/57600 [8:51:29<1:17:47,  1.55it/s]
 87%|████████▋ | 50355/57600 [8:51:29<1:14:55,  1.61it/s]
 87%|████████▋ | 50356/57600 [8:51:30<1:15:42,  1.59it/s]
 87%|████████▋ | 50357/57600 [8:51:31<1:17:29,  1.56it/s]
 87%|████████▋ | 50358/57600 [8:51:31<1:20:11,  1.51it/s]
 87%|████████▋ | 50359/57600 [8:51:32<1:19:28,  1.52it/s]
 87%|████████▋ | 50360/57600 [8:51:33<1:18:33,  1.54it/s]
                                                         
{'loss': 1.0915, 'learning_rate': 2.1351916376306618e-07, 'epoch': 555.85}

 87%|████████▋ | 50360/57600 [8:51:33<1:18:33,  1.54it/s]
 87%|████████▋ | 50361/57600 [8:51:33<1:21:09,  1.49it/s]
 87%|████████▋ | 50362/57600 [8:51:34<1:19:07,  1.52it/s]
 87%|████████▋ | 50363/57600 [8:51:35<1:17:13,  1.56it/s]
 87%|████████▋ | 50364/57600 [8:51:35<1:17:49,  1.55it/s]
 87%|████████▋ | 50365/57600 [8:51:36<1:17:27,  1.56it/s]
 87%|████████▋ | 50366/57600 [8:51:37<1:16:04,  1.58it/s]
 87%|████████▋ | 50367/57600 [8:51:37<1:15:18,  1.60it/s]
 87%|████████▋ | 50368/57600 [8:51:38<1:15:01,  1.61it/s]
 87%|████████▋ | 50369/57600 [8:51:38<1:15:13,  1.60it/s]
 87%|████████▋ | 50370/57600 [8:51:39<1:14:48,  1.61it/s]
 87%|████████▋ | 50371/57600 [8:51:40<1:14:40,  1.61it/s]
 87%|████████▋ | 50372/57600 [8:51:40<1:13:13,  1.65it/s]
 87%|████████▋ | 50373/57600 [8:51:41<1:15:23,  1.60it/s]
 87%|████████▋ | 50374/57600 [8:51:42<1:20:05,  1.50it/s]
 87%|████████▋ | 50375/57600 [8:51:42<1:19:27,  1.52it/s]
 87%|████████▋ | 50376/57600 [8:51:43<1:18:14,  1.54it/s]
 87%|████████▋ | 50377/57600 [8:51:43<1:15:24,  1.60it/s]
 87%|████████▋ | 50378/57600 [8:51:44<1:15:29,  1.59it/s]
 87%|████████▋ | 50379/57600 [8:51:45<1:15:51,  1.59it/s]
 87%|████████▋ | 50380/57600 [8:51:45<1:13:37,  1.63it/s]
                                                         
{'loss': 1.141, 'learning_rate': 2.13205574912892e-07, 'epoch': 556.07}

 87%|████████▋ | 50380/57600 [8:51:45<1:13:37,  1.63it/s]
 87%|████████▋ | 50381/57600 [8:51:46<1:15:50,  1.59it/s]
 87%|████████▋ | 50382/57600 [8:51:47<1:13:36,  1.63it/s]
 87%|████████▋ | 50383/57600 [8:51:47<1:17:13,  1.56it/s]
 87%|████████▋ | 50384/57600 [8:51:48<1:18:28,  1.53it/s]
 87%|████████▋ | 50385/57600 [8:51:49<1:19:25,  1.51it/s]
 87%|████████▋ | 50386/57600 [8:51:49<1:18:38,  1.53it/s]
 87%|████████▋ | 50387/57600 [8:51:50<1:17:01,  1.56it/s]
 87%|████████▋ | 50388/57600 [8:51:50<1:15:58,  1.58it/s]
 87%|████████▋ | 50389/57600 [8:51:51<1:16:32,  1.57it/s]
 87%|████████▋ | 50390/57600 [8:51:52<1:18:51,  1.52it/s]
 87%|████████▋ | 50391/57600 [8:51:52<1:16:32,  1.57it/s]
 87%|████████▋ | 50392/57600 [8:51:53<1:15:57,  1.58it/s]
 87%|████████▋ | 50393/57600 [8:51:54<1:16:12,  1.58it/s]
 87%|████████▋ | 50394/57600 [8:51:54<1:17:19,  1.55it/s]
 87%|████████▋ | 50395/57600 [8:51:55<1:15:13,  1.60it/s]
 87%|████████▋ | 50396/57600 [8:51:56<1:14:33,  1.61it/s]
 87%|████████▋ | 50397/57600 [8:51:56<1:12:56,  1.65it/s]
 87%|████████▋ | 50398/57600 [8:51:57<1:13:09,  1.64it/s]
 87%|████████▋ | 50399/57600 [8:51:57<1:12:22,  1.66it/s]
 88%|████████▊ | 50400/57600 [8:51:58<1:12:35,  1.65it/s]
                                                         
{'loss': 1.1132, 'learning_rate': 2.1289198606271773e-07, 'epoch': 556.29}

 88%|████████▊ | 50400/57600 [8:51:58<1:12:35,  1.65it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.90it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.01it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.48it/s]

100%|██████████| 6/6 [00:01<00:00,  3.07it/s]{'score': 48.90706738579965, 'counts': [145, 90, 63, 45], 'totals': [206, 176, 147, 119], 'precisions': [70.3883495145631, 51.13636363636363, 42.857142857142854, 37.81512605042017], 'bp': 0.9951573944744894, 'sys_len': 206, 'ref_len': 207}

                                                         

                                             
{'eval_loss': 1.9735721349716187, 'eval_bleu': 48.9071, 'eval_gen_len': 8.3667, 'eval_runtime': 3.3922, 'eval_samples_per_second': 8.844, 'eval_steps_per_second': 1.769, 'epoch': 556.29}

 88%|████████▊ | 50400/57600 [8:52:01<1:12:35,  1.65it/s]

100%|██████████| 6/6 [00:03<00:00,  3.07it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 15:46:14,676 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 88%|████████▊ | 50401/57600 [8:52:33<21:37:27, 10.81s/it]
 88%|████████▊ | 50402/57600 [8:52:33<15:35:38,  7.80s/it]
 88%|████████▊ | 50403/57600 [8:52:34<11:21:19,  5.68s/it]
 88%|████████▊ | 50404/57600 [8:52:35<8:22:28,  4.19s/it] 
 88%|████████▊ | 50405/57600 [8:52:36<6:21:00,  3.18s/it]
 88%|████████▊ | 50406/57600 [8:52:36<4:54:36,  2.46s/it]
 88%|████████▊ | 50407/57600 [8:52:37<3:54:43,  1.96s/it]
 88%|████████▊ | 50408/57600 [8:52:38<3:08:53,  1.58s/it]
 88%|████████▊ | 50409/57600 [8:52:39<2:37:45,  1.32s/it]
 88%|████████▊ | 50410/57600 [8:52:39<2:14:15,  1.12s/it]
 88%|████████▊ | 50411/57600 [8:52:40<1:58:55,  1.01it/s]
 88%|████████▊ | 50412/57600 [8:52:41<1:47:06,  1.12it/s]
 88%|████████▊ | 50413/57600 [8:52:41<1:37:38,  1.23it/s]
 88%|████████▊ | 50414/57600 [8:52:42<1:32:59,  1.29it/s]
 88%|████████▊ | 50415/57600 [8:52:43<1:28:11,  1.36it/s]
 88%|████████▊ | 50416/57600 [8:52:43<1:25:40,  1.40it/s]
 88%|████████▊ | 50417/57600 [8:52:44<1:24:08,  1.42it/s]
 88%|████████▊ | 50418/57600 [8:52:45<1:24:48,  1.41it/s]
 88%|████████▊ | 50419/57600 [8:52:45<1:23:18,  1.44it/s]
 88%|████████▊ | 50420/57600 [8:52:46<1:23:53,  1.43it/s]
                                                         
{'loss': 1.0638, 'learning_rate': 2.1257839721254357e-07, 'epoch': 556.51}

 88%|████████▊ | 50420/57600 [8:52:46<1:23:53,  1.43it/s]
 88%|████████▊ | 50421/57600 [8:52:47<1:21:43,  1.46it/s]
 88%|████████▊ | 50422/57600 [8:52:47<1:21:20,  1.47it/s]
 88%|████████▊ | 50423/57600 [8:52:48<1:22:05,  1.46it/s]
 88%|████████▊ | 50424/57600 [8:52:49<1:20:27,  1.49it/s]
 88%|████████▊ | 50425/57600 [8:52:49<1:22:17,  1.45it/s]
 88%|████████▊ | 50426/57600 [8:52:50<1:23:34,  1.43it/s]
 88%|████████▊ | 50427/57600 [8:52:51<1:20:42,  1.48it/s]
 88%|████████▊ | 50428/57600 [8:52:51<1:19:29,  1.50it/s]
 88%|████████▊ | 50429/57600 [8:52:52<1:18:24,  1.52it/s]
 88%|████████▊ | 50430/57600 [8:52:53<1:19:53,  1.50it/s]
 88%|████████▊ | 50431/57600 [8:52:53<1:21:20,  1.47it/s]
 88%|████████▊ | 50432/57600 [8:52:54<1:23:06,  1.44it/s]
 88%|████████▊ | 50433/57600 [8:52:55<1:22:46,  1.44it/s]
 88%|████████▊ | 50434/57600 [8:52:55<1:22:11,  1.45it/s]
 88%|████████▊ | 50435/57600 [8:52:56<1:21:27,  1.47it/s]
 88%|████████▊ | 50436/57600 [8:52:57<1:19:52,  1.49it/s]
 88%|████████▊ | 50437/57600 [8:52:57<1:20:11,  1.49it/s]
 88%|████████▊ | 50438/57600 [8:52:58<1:23:13,  1.43it/s]
 88%|████████▊ | 50439/57600 [8:52:59<1:21:01,  1.47it/s]
 88%|████████▊ | 50440/57600 [8:53:00<1:19:57,  1.49it/s]
                                                         
{'loss': 1.0955, 'learning_rate': 2.122648083623693e-07, 'epoch': 556.73}

 88%|████████▊ | 50440/57600 [8:53:00<1:19:57,  1.49it/s]
 88%|████████▊ | 50441/57600 [8:53:00<1:20:54,  1.47it/s]
 88%|████████▊ | 50442/57600 [8:53:01<1:19:48,  1.49it/s]
 88%|████████▊ | 50443/57600 [8:53:02<1:21:01,  1.47it/s]
 88%|████████▊ | 50444/57600 [8:53:02<1:22:02,  1.45it/s]
 88%|████████▊ | 50445/57600 [8:53:03<1:20:12,  1.49it/s]
 88%|████████▊ | 50446/57600 [8:53:04<1:19:35,  1.50it/s]
 88%|████████▊ | 50447/57600 [8:53:04<1:22:15,  1.45it/s]
 88%|████████▊ | 50448/57600 [8:53:05<1:21:16,  1.47it/s]
 88%|████████▊ | 50449/57600 [8:53:06<1:19:48,  1.49it/s]
 88%|████████▊ | 50450/57600 [8:53:06<1:19:06,  1.51it/s]
 88%|████████▊ | 50451/57600 [8:53:07<1:17:43,  1.53it/s]
 88%|████████▊ | 50452/57600 [8:53:08<1:18:10,  1.52it/s]
 88%|████████▊ | 50453/57600 [8:53:08<1:16:18,  1.56it/s]
 88%|████████▊ | 50454/57600 [8:53:09<1:17:15,  1.54it/s]
 88%|████████▊ | 50455/57600 [8:53:10<1:18:55,  1.51it/s]
 88%|████████▊ | 50456/57600 [8:53:10<1:18:54,  1.51it/s]
 88%|████████▊ | 50457/57600 [8:53:11<1:19:41,  1.49it/s]
 88%|████████▊ | 50458/57600 [8:53:12<1:22:59,  1.43it/s]
 88%|████████▊ | 50459/57600 [8:53:12<1:23:40,  1.42it/s]
 88%|████████▊ | 50460/57600 [8:53:13<1:24:30,  1.41it/s]
                                                         
{'loss': 1.134, 'learning_rate': 2.1195121951219512e-07, 'epoch': 556.95}

 88%|████████▊ | 50460/57600 [8:53:13<1:24:30,  1.41it/s]
 88%|████████▊ | 50461/57600 [8:53:14<1:22:39,  1.44it/s]
 88%|████████▊ | 50462/57600 [8:53:14<1:21:29,  1.46it/s]
 88%|████████▊ | 50463/57600 [8:53:15<1:20:28,  1.48it/s]
 88%|████████▊ | 50464/57600 [8:53:16<1:19:39,  1.49it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 88%|████████▊ | 50465/57600 [8:53:16<1:21:20,  1.46it/s]
 88%|████████▊ | 50466/57600 [8:53:17<1:18:48,  1.51it/s]
 88%|████████▊ | 50467/57600 [8:53:18<1:20:17,  1.48it/s]
 88%|████████▊ | 50468/57600 [8:53:18<1:19:52,  1.49it/s]
 88%|████████▊ | 50469/57600 [8:53:19<1:21:49,  1.45it/s]
 88%|████████▊ | 50470/57600 [8:53:20<1:22:10,  1.45it/s]
 88%|████████▊ | 50471/57600 [8:53:21<1:22:49,  1.43it/s]
 88%|████████▊ | 50472/57600 [8:53:21<1:25:10,  1.39it/s]
 88%|████████▊ | 50473/57600 [8:53:22<1:20:47,  1.47it/s]
 88%|████████▊ | 50474/57600 [8:53:23<1:18:05,  1.52it/s]
 88%|████████▊ | 50475/57600 [8:53:23<1:15:26,  1.57it/s]
 88%|████████▊ | 50476/57600 [8:53:24<1:14:33,  1.59it/s]
 88%|████████▊ | 50477/57600 [8:53:24<1:16:16,  1.56it/s]
 88%|████████▊ | 50478/57600 [8:53:25<1:15:13,  1.58it/s]
 88%|████████▊ | 50479/57600 [8:53:26<1:13:40,  1.61it/s]
 88%|████████▊ | 50480/57600 [8:53:26<1:14:41,  1.59it/s]
                                                         
{'loss': 1.1122, 'learning_rate': 2.1163763066202093e-07, 'epoch': 557.17}

 88%|████████▊ | 50480/57600 [8:53:26<1:14:41,  1.59it/s]
 88%|████████▊ | 50481/57600 [8:53:27<1:14:06,  1.60it/s]
 88%|████████▊ | 50482/57600 [8:53:28<1:15:47,  1.57it/s]
 88%|████████▊ | 50483/57600 [8:53:28<1:15:13,  1.58it/s]
 88%|████████▊ | 50484/57600 [8:53:29<1:14:31,  1.59it/s]
 88%|████████▊ | 50485/57600 [8:53:29<1:15:00,  1.58it/s]
 88%|████████▊ | 50486/57600 [8:53:30<1:16:17,  1.55it/s]
 88%|████████▊ | 50487/57600 [8:53:31<1:17:06,  1.54it/s]
 88%|████████▊ | 50488/57600 [8:53:31<1:17:29,  1.53it/s]
 88%|████████▊ | 50489/57600 [8:53:32<1:18:41,  1.51it/s]
 88%|████████▊ | 50490/57600 [8:53:33<1:20:13,  1.48it/s]
 88%|████████▊ | 50491/57600 [8:53:33<1:19:39,  1.49it/s]
 88%|████████▊ | 50492/57600 [8:53:34<1:19:29,  1.49it/s]
 88%|████████▊ | 50493/57600 [8:53:35<1:18:03,  1.52it/s]
 88%|████████▊ | 50494/57600 [8:53:35<1:18:07,  1.52it/s]
 88%|████████▊ | 50495/57600 [8:53:36<1:17:38,  1.53it/s]
 88%|████████▊ | 50496/57600 [8:53:37<1:18:26,  1.51it/s]
 88%|████████▊ | 50497/57600 [8:53:37<1:17:56,  1.52it/s]
 88%|████████▊ | 50498/57600 [8:53:38<1:18:34,  1.51it/s]
 88%|████████▊ | 50499/57600 [8:53:39<1:17:09,  1.53it/s]
 88%|████████▊ | 50500/57600 [8:53:39<1:16:33,  1.55it/s]
                                                         
{'loss': 1.1212, 'learning_rate': 2.1132404181184668e-07, 'epoch': 557.4}

 88%|████████▊ | 50500/57600 [8:53:39<1:16:33,  1.55it/s]
 88%|████████▊ | 50501/57600 [8:53:40<1:14:56,  1.58it/s]
 88%|████████▊ | 50502/57600 [8:53:41<1:15:56,  1.56it/s]
 88%|████████▊ | 50503/57600 [8:53:41<1:15:47,  1.56it/s]
 88%|████████▊ | 50504/57600 [8:53:42<1:16:18,  1.55it/s]
 88%|████████▊ | 50505/57600 [8:53:43<1:16:02,  1.56it/s]
 88%|████████▊ | 50506/57600 [8:53:43<1:17:30,  1.53it/s]
 88%|████████▊ | 50507/57600 [8:53:44<1:16:59,  1.54it/s]
 88%|████████▊ | 50508/57600 [8:53:45<1:18:03,  1.51it/s]
 88%|████████▊ | 50509/57600 [8:53:45<1:17:51,  1.52it/s]
 88%|████████▊ | 50510/57600 [8:53:46<1:14:29,  1.59it/s]
 88%|████████▊ | 50511/57600 [8:53:46<1:16:25,  1.55it/s]
 88%|████████▊ | 50512/57600 [8:53:47<1:15:53,  1.56it/s]
 88%|████████▊ | 50513/57600 [8:53:48<1:15:08,  1.57it/s]
 88%|████████▊ | 50514/57600 [8:53:48<1:15:24,  1.57it/s]
 88%|████████▊ | 50515/57600 [8:53:49<1:17:16,  1.53it/s]
 88%|████████▊ | 50516/57600 [8:53:50<1:19:27,  1.49it/s]
 88%|████████▊ | 50517/57600 [8:53:50<1:18:10,  1.51it/s]
 88%|████████▊ | 50518/57600 [8:53:51<1:18:49,  1.50it/s]
 88%|████████▊ | 50519/57600 [8:53:52<1:18:09,  1.51it/s]
 88%|████████▊ | 50520/57600 [8:53:52<1:16:21,  1.55it/s]
                                                         
{'loss': 1.121, 'learning_rate': 2.1101045296167248e-07, 'epoch': 557.62}

 88%|████████▊ | 50520/57600 [8:53:52<1:16:21,  1.55it/s]
 88%|████████▊ | 50521/57600 [8:53:53<1:18:37,  1.50it/s]
 88%|████████▊ | 50522/57600 [8:53:54<1:17:54,  1.51it/s]
 88%|████████▊ | 50523/57600 [8:53:54<1:15:47,  1.56it/s]
 88%|████████▊ | 50524/57600 [8:53:55<1:15:05,  1.57it/s]
 88%|████████▊ | 50525/57600 [8:53:56<1:16:00,  1.55it/s]
 88%|████████▊ | 50526/57600 [8:53:56<1:18:35,  1.50it/s]
 88%|████████▊ | 50527/57600 [8:53:57<1:17:27,  1.52it/s]
 88%|████████▊ | 50528/57600 [8:53:58<1:18:35,  1.50it/s]
 88%|████████▊ | 50529/57600 [8:53:58<1:21:36,  1.44it/s]
 88%|████████▊ | 50530/57600 [8:53:59<1:19:16,  1.49it/s]
 88%|████████▊ | 50531/57600 [8:54:00<1:19:16,  1.49it/s]
 88%|████████▊ | 50532/57600 [8:54:00<1:20:58,  1.45it/s]
 88%|████████▊ | 50533/57600 [8:54:01<1:21:01,  1.45it/s]
 88%|████████▊ | 50534/57600 [8:54:02<1:18:58,  1.49it/s]
 88%|████████▊ | 50535/57600 [8:54:02<1:18:05,  1.51it/s]
 88%|████████▊ | 50536/57600 [8:54:03<1:21:47,  1.44it/s]
 88%|████████▊ | 50537/57600 [8:54:04<1:21:08,  1.45it/s]
 88%|████████▊ | 50538/57600 [8:54:04<1:19:07,  1.49it/s]
 88%|████████▊ | 50539/57600 [8:54:05<1:19:38,  1.48it/s]
 88%|████████▊ | 50540/57600 [8:54:06<1:20:55,  1.45it/s]
                                                         
{'loss': 1.0906, 'learning_rate': 2.1069686411149824e-07, 'epoch': 557.84}

 88%|████████▊ | 50540/57600 [8:54:06<1:20:55,  1.45it/s]
 88%|████████▊ | 50541/57600 [8:54:07<1:21:43,  1.44it/s]
 88%|████████▊ | 50542/57600 [8:54:07<1:21:30,  1.44it/s]
 88%|████████▊ | 50543/57600 [8:54:08<1:19:32,  1.48it/s]
 88%|████████▊ | 50544/57600 [8:54:08<1:18:24,  1.50it/s]
 88%|████████▊ | 50545/57600 [8:54:09<1:19:22,  1.48it/s]
 88%|████████▊ | 50546/57600 [8:54:10<1:19:55,  1.47it/s]
 88%|████████▊ | 50547/57600 [8:54:10<1:17:19,  1.52it/s]
 88%|████████▊ | 50548/57600 [8:54:11<1:18:11,  1.50it/s]
 88%|████████▊ | 50549/57600 [8:54:12<1:16:56,  1.53it/s]
 88%|████████▊ | 50550/57600 [8:54:12<1:17:43,  1.51it/s]
 88%|████████▊ | 50551/57600 [8:54:13<1:15:28,  1.56it/s]
 88%|████████▊ | 50552/57600 [8:54:14<1:14:32,  1.58it/s]
 88%|████████▊ | 50553/57600 [8:54:14<1:18:26,  1.50it/s]
 88%|████████▊ | 50554/57600 [8:54:15<1:17:00,  1.52it/s]
 88%|████████▊ | 50555/57600 [8:54:16<1:20:52,  1.45it/s]
 88%|████████▊ | 50556/57600 [8:54:16<1:19:16,  1.48it/s]
 88%|████████▊ | 50557/57600 [8:54:17<1:19:31,  1.48it/s]
 88%|████████▊ | 50558/57600 [8:54:18<1:17:23,  1.52it/s]
 88%|████████▊ | 50559/57600 [8:54:18<1:17:48,  1.51it/s]
 88%|████████▊ | 50560/57600 [8:54:19<1:18:38,  1.49it/s]
                                                         
{'loss': 1.116, 'learning_rate': 2.1038327526132404e-07, 'epoch': 558.06}

 88%|████████▊ | 50560/57600 [8:54:19<1:18:38,  1.49it/s]
 88%|████████▊ | 50561/57600 [8:54:20<1:22:18,  1.43it/s]
 88%|████████▊ | 50562/57600 [8:54:21<1:18:59,  1.48it/s]
 88%|████████▊ | 50563/57600 [8:54:21<1:20:24,  1.46it/s]
 88%|████████▊ | 50564/57600 [8:54:22<1:16:54,  1.52it/s]
 88%|████████▊ | 50565/57600 [8:54:22<1:17:48,  1.51it/s]
 88%|████████▊ | 50566/57600 [8:54:23<1:16:28,  1.53it/s]
 88%|████████▊ | 50567/57600 [8:54:24<1:16:00,  1.54it/s]
 88%|████████▊ | 50568/57600 [8:54:24<1:13:03,  1.60it/s]
 88%|████████▊ | 50569/57600 [8:54:25<1:13:18,  1.60it/s]
 88%|████████▊ | 50570/57600 [8:54:26<1:14:23,  1.58it/s]
 88%|████████▊ | 50571/57600 [8:54:26<1:14:01,  1.58it/s]
 88%|████████▊ | 50572/57600 [8:54:27<1:12:56,  1.61it/s]
 88%|████████▊ | 50573/57600 [8:54:27<1:12:11,  1.62it/s]
 88%|████████▊ | 50574/57600 [8:54:28<1:13:30,  1.59it/s]
 88%|████████▊ | 50575/57600 [8:54:29<1:15:21,  1.55it/s]
 88%|████████▊ | 50576/57600 [8:54:29<1:17:46,  1.51it/s]
 88%|████████▊ | 50577/57600 [8:54:30<1:18:41,  1.49it/s]
 88%|████████▊ | 50578/57600 [8:54:31<1:19:42,  1.47it/s]
 88%|████████▊ | 50579/57600 [8:54:32<1:20:28,  1.45it/s]
 88%|████████▊ | 50580/57600 [8:54:32<1:18:35,  1.49it/s]
                                                         
{'loss': 1.1102, 'learning_rate': 2.1006968641114977e-07, 'epoch': 558.28}

 88%|████████▊ | 50580/57600 [8:54:32<1:18:35,  1.49it/s]
 88%|████████▊ | 50581/57600 [8:54:33<1:17:04,  1.52it/s]
 88%|████████▊ | 50582/57600 [8:54:33<1:16:20,  1.53it/s]
 88%|████████▊ | 50583/57600 [8:54:34<1:17:32,  1.51it/s]
 88%|████████▊ | 50584/57600 [8:54:35<1:17:28,  1.51it/s]
 88%|████████▊ | 50585/57600 [8:54:35<1:17:09,  1.52it/s]
 88%|████████▊ | 50586/57600 [8:54:36<1:20:08,  1.46it/s]
 88%|████████▊ | 50587/57600 [8:54:37<1:20:49,  1.45it/s]
 88%|████████▊ | 50588/57600 [8:54:38<1:18:16,  1.49it/s]
 88%|████████▊ | 50589/57600 [8:54:38<1:19:18,  1.47it/s]
 88%|████████▊ | 50590/57600 [8:54:39<1:18:32,  1.49it/s]
 88%|████████▊ | 50591/57600 [8:54:40<1:19:37,  1.47it/s]
 88%|████████▊ | 50592/57600 [8:54:40<1:22:04,  1.42it/s]
 88%|████████▊ | 50593/57600 [8:54:41<1:20:48,  1.45it/s]
 88%|████████▊ | 50594/57600 [8:54:42<1:18:09,  1.49it/s]
 88%|████████▊ | 50595/57600 [8:54:42<1:16:20,  1.53it/s]
 88%|████████▊ | 50596/57600 [8:54:43<1:18:02,  1.50it/s]
 88%|████████▊ | 50597/57600 [8:54:44<1:15:54,  1.54it/s]
 88%|████████▊ | 50598/57600 [8:54:44<1:16:50,  1.52it/s]
 88%|████████▊ | 50599/57600 [8:54:45<1:16:40,  1.52it/s]
 88%|████████▊ | 50600/57600 [8:54:46<1:14:21,  1.57it/s]
                                                         
{'loss': 1.1231, 'learning_rate': 2.097560975609756e-07, 'epoch': 558.5}

 88%|████████▊ | 50600/57600 [8:54:46<1:14:21,  1.57it/s]
 88%|████████▊ | 50601/57600 [8:54:46<1:14:19,  1.57it/s]
 88%|████████▊ | 50602/57600 [8:54:47<1:18:12,  1.49it/s]
 88%|████████▊ | 50603/57600 [8:54:48<1:17:07,  1.51it/s]
 88%|████████▊ | 50604/57600 [8:54:48<1:15:32,  1.54it/s]
 88%|████████▊ | 50605/57600 [8:54:49<1:19:38,  1.46it/s]
 88%|████████▊ | 50606/57600 [8:54:50<1:16:24,  1.53it/s]
 88%|████████▊ | 50607/57600 [8:54:50<1:16:21,  1.53it/s]
 88%|████████▊ | 50608/57600 [8:54:51<1:14:27,  1.57it/s]
 88%|████████▊ | 50609/57600 [8:54:51<1:12:21,  1.61it/s]
 88%|████████▊ | 50610/57600 [8:54:52<1:12:45,  1.60it/s]
 88%|████████▊ | 50611/57600 [8:54:53<1:10:00,  1.66it/s]
 88%|████████▊ | 50612/57600 [8:54:53<1:12:49,  1.60it/s]
 88%|████████▊ | 50613/57600 [8:54:54<1:12:47,  1.60it/s]
 88%|████████▊ | 50614/57600 [8:54:54<1:11:36,  1.63it/s]
 88%|████████▊ | 50615/57600 [8:54:55<1:11:43,  1.62it/s]
 88%|████████▊ | 50616/57600 [8:54:56<1:10:28,  1.65it/s]
 88%|████████▊ | 50617/57600 [8:54:56<1:13:09,  1.59it/s]
 88%|████████▊ | 50618/57600 [8:54:57<1:14:55,  1.55it/s]
 88%|████████▊ | 50619/57600 [8:54:58<1:14:22,  1.56it/s]
 88%|████████▊ | 50620/57600 [8:54:58<1:14:08,  1.57it/s]
                                                         
{'loss': 1.1344, 'learning_rate': 2.0944250871080143e-07, 'epoch': 558.72}

 88%|████████▊ | 50620/57600 [8:54:58<1:14:08,  1.57it/s]
 88%|████████▊ | 50621/57600 [8:54:59<1:13:26,  1.58it/s]
 88%|████████▊ | 50622/57600 [8:54:59<1:13:00,  1.59it/s]
 88%|████████▊ | 50623/57600 [8:55:00<1:10:52,  1.64it/s]
 88%|████████▊ | 50624/57600 [8:55:01<1:13:40,  1.58it/s]
 88%|████████▊ | 50625/57600 [8:55:01<1:13:29,  1.58it/s]
 88%|████████▊ | 50626/57600 [8:55:02<1:12:10,  1.61it/s]
 88%|████████▊ | 50627/57600 [8:55:03<1:14:28,  1.56it/s]
 88%|████████▊ | 50628/57600 [8:55:03<1:13:18,  1.59it/s]
 88%|████████▊ | 50629/57600 [8:55:04<1:13:16,  1.59it/s]
 88%|████████▊ | 50630/57600 [8:55:04<1:12:04,  1.61it/s]
 88%|████████▊ | 50631/57600 [8:55:05<1:14:24,  1.56it/s]
 88%|████████▊ | 50632/57600 [8:55:06<1:17:19,  1.50it/s]
 88%|████████▊ | 50633/57600 [8:55:06<1:15:19,  1.54it/s]
 88%|████████▊ | 50634/57600 [8:55:07<1:14:46,  1.55it/s]
 88%|████████▊ | 50635/57600 [8:55:08<1:14:03,  1.57it/s]
 88%|████████▊ | 50636/57600 [8:55:08<1:13:41,  1.58it/s]
 88%|████████▊ | 50637/57600 [8:55:09<1:13:18,  1.58it/s]
 88%|████████▊ | 50638/57600 [8:55:10<1:13:45,  1.57it/s]
 88%|████████▊ | 50639/57600 [8:55:10<1:12:22,  1.60it/s]
 88%|████████▊ | 50640/57600 [8:55:11<1:14:01,  1.57it/s]
                                                         
{'loss': 1.1081, 'learning_rate': 2.0912891986062715e-07, 'epoch': 558.94}

 88%|████████▊ | 50640/57600 [8:55:11<1:14:01,  1.57it/s]
 88%|████████▊ | 50641/57600 [8:55:11<1:12:06,  1.61it/s]
 88%|████████▊ | 50642/57600 [8:55:12<1:14:52,  1.55it/s]
 88%|████████▊ | 50643/57600 [8:55:13<1:12:26,  1.60it/s]
 88%|████████▊ | 50644/57600 [8:55:13<1:11:21,  1.62it/s]
 88%|████████▊ | 50645/57600 [8:55:14<1:09:37,  1.67it/s]
 88%|████████▊ | 50646/57600 [8:55:15<1:12:20,  1.60it/s]
 88%|████████▊ | 50647/57600 [8:55:15<1:12:33,  1.60it/s]
 88%|████████▊ | 50648/57600 [8:55:16<1:13:05,  1.59it/s]
 88%|████████▊ | 50649/57600 [8:55:17<1:12:36,  1.60it/s]
 88%|████████▊ | 50650/57600 [8:55:17<1:13:03,  1.59it/s]
 88%|████████▊ | 50651/57600 [8:55:18<1:11:03,  1.63it/s]
 88%|████████▊ | 50652/57600 [8:55:18<1:10:54,  1.63it/s]
 88%|████████▊ | 50653/57600 [8:55:19<1:13:17,  1.58it/s]
 88%|████████▊ | 50654/57600 [8:55:20<1:14:06,  1.56it/s]
 88%|████████▊ | 50655/57600 [8:55:20<1:12:39,  1.59it/s]
 88%|████████▊ | 50656/57600 [8:55:21<1:15:28,  1.53it/s]
 88%|████████▊ | 50657/57600 [8:55:22<1:14:01,  1.56it/s]
 88%|████████▊ | 50658/57600 [8:55:22<1:13:30,  1.57it/s]
 88%|████████▊ | 50659/57600 [8:55:23<1:14:18,  1.56it/s]
 88%|████████▊ | 50660/57600 [8:55:24<1:16:18,  1.52it/s]
                                                         
{'loss': 1.0986, 'learning_rate': 2.0881533101045296e-07, 'epoch': 559.16}

 88%|████████▊ | 50660/57600 [8:55:24<1:16:18,  1.52it/s]
 88%|████████▊ | 50661/57600 [8:55:24<1:14:01,  1.56it/s]
 88%|████████▊ | 50662/57600 [8:55:25<1:14:43,  1.55it/s]
 88%|████████▊ | 50663/57600 [8:55:25<1:13:51,  1.57it/s]
 88%|████████▊ | 50664/57600 [8:55:26<1:14:55,  1.54it/s]
 88%|████████▊ | 50665/57600 [8:55:27<1:14:15,  1.56it/s]
 88%|████████▊ | 50666/57600 [8:55:27<1:14:19,  1.55it/s]
 88%|████████▊ | 50667/57600 [8:55:28<1:14:06,  1.56it/s]
 88%|████████▊ | 50668/57600 [8:55:29<1:13:44,  1.57it/s]
 88%|████████▊ | 50669/57600 [8:55:29<1:12:39,  1.59it/s]
 88%|████████▊ | 50670/57600 [8:55:30<1:16:17,  1.51it/s]
 88%|████████▊ | 50671/57600 [8:55:31<1:13:40,  1.57it/s]
 88%|████████▊ | 50672/57600 [8:55:31<1:12:03,  1.60it/s]
 88%|████████▊ | 50673/57600 [8:55:32<1:11:48,  1.61it/s]
 88%|████████▊ | 50674/57600 [8:55:32<1:10:20,  1.64it/s]
 88%|████████▊ | 50675/57600 [8:55:33<1:10:32,  1.64it/s]
 88%|████████▊ | 50676/57600 [8:55:34<1:09:53,  1.65it/s]
 88%|████████▊ | 50677/57600 [8:55:34<1:10:42,  1.63it/s]
 88%|████████▊ | 50678/57600 [8:55:35<1:11:53,  1.60it/s]
 88%|████████▊ | 50679/57600 [8:55:36<1:12:39,  1.59it/s]
 88%|████████▊ | 50680/57600 [8:55:36<1:11:59,  1.60it/s]
                                                         
{'loss': 1.0925, 'learning_rate': 2.085017421602787e-07, 'epoch': 559.38}

 88%|████████▊ | 50680/57600 [8:55:36<1:11:59,  1.60it/s]
 88%|████████▊ | 50681/57600 [8:55:37<1:10:54,  1.63it/s]
 88%|████████▊ | 50682/57600 [8:55:37<1:12:13,  1.60it/s]
 88%|████████▊ | 50683/57600 [8:55:38<1:11:41,  1.61it/s]
 88%|████████▊ | 50684/57600 [8:55:39<1:15:04,  1.54it/s]
 88%|████████▊ | 50685/57600 [8:55:39<1:13:45,  1.56it/s]
 88%|████████▊ | 50686/57600 [8:55:40<1:12:03,  1.60it/s]
 88%|████████▊ | 50687/57600 [8:55:40<1:10:29,  1.63it/s]
 88%|████████▊ | 50688/57600 [8:55:41<1:11:00,  1.62it/s]
 88%|████████▊ | 50689/57600 [8:55:42<1:12:19,  1.59it/s]
 88%|████████▊ | 50690/57600 [8:55:42<1:13:45,  1.56it/s]
 88%|████████▊ | 50691/57600 [8:55:43<1:12:56,  1.58it/s]
 88%|████████▊ | 50692/57600 [8:55:44<1:13:10,  1.57it/s]
 88%|████████▊ | 50693/57600 [8:55:44<1:13:46,  1.56it/s]
 88%|████████▊ | 50694/57600 [8:55:45<1:14:22,  1.55it/s]
 88%|████████▊ | 50695/57600 [8:55:46<1:14:02,  1.55it/s]
 88%|████████▊ | 50696/57600 [8:55:46<1:11:54,  1.60it/s]
 88%|████████▊ | 50697/57600 [8:55:47<1:11:52,  1.60it/s]
 88%|████████▊ | 50698/57600 [8:55:47<1:11:05,  1.62it/s]
 88%|████████▊ | 50699/57600 [8:55:48<1:11:23,  1.61it/s]
 88%|████████▊ | 50700/57600 [8:55:49<1:10:10,  1.64it/s]
                                                         
{'loss': 1.1139, 'learning_rate': 2.081881533101045e-07, 'epoch': 559.6}

 88%|████████▊ | 50700/57600 [8:55:49<1:10:10,  1.64it/s]
 88%|████████▊ | 50701/57600 [8:55:49<1:10:17,  1.64it/s]
 88%|████████▊ | 50702/57600 [8:55:50<1:11:14,  1.61it/s]
 88%|████████▊ | 50703/57600 [8:55:50<1:10:01,  1.64it/s]
 88%|████████▊ | 50704/57600 [8:55:51<1:09:16,  1.66it/s]
 88%|████████▊ | 50705/57600 [8:55:52<1:10:39,  1.63it/s]
 88%|████████▊ | 50706/57600 [8:55:52<1:10:13,  1.64it/s]
 88%|████████▊ | 50707/57600 [8:55:53<1:11:36,  1.60it/s]
 88%|████████▊ | 50708/57600 [8:55:54<1:10:12,  1.64it/s]
 88%|████████▊ | 50709/57600 [8:55:54<1:10:40,  1.63it/s]
 88%|████████▊ | 50710/57600 [8:55:55<1:11:40,  1.60it/s]
 88%|████████▊ | 50711/57600 [8:55:55<1:12:04,  1.59it/s]
 88%|████████▊ | 50712/57600 [8:55:56<1:16:31,  1.50it/s]
 88%|████████▊ | 50713/57600 [8:55:57<1:13:48,  1.56it/s]
 88%|████████▊ | 50714/57600 [8:55:57<1:12:10,  1.59it/s]
 88%|████████▊ | 50715/57600 [8:55:58<1:12:22,  1.59it/s]
 88%|████████▊ | 50716/57600 [8:55:59<1:12:35,  1.58it/s]
 88%|████████▊ | 50717/57600 [8:55:59<1:10:35,  1.62it/s]
 88%|████████▊ | 50718/57600 [8:56:00<1:10:58,  1.62it/s]
 88%|████████▊ | 50719/57600 [8:56:01<1:13:10,  1.57it/s]
 88%|████████▊ | 50720/57600 [8:56:01<1:09:58,  1.64it/s]
                                                         
{'loss': 1.1226, 'learning_rate': 2.0787456445993027e-07, 'epoch': 559.82}

 88%|████████▊ | 50720/57600 [8:56:01<1:09:58,  1.64it/s]
 88%|████████▊ | 50721/57600 [8:56:02<1:10:08,  1.63it/s]
 88%|████████▊ | 50722/57600 [8:56:02<1:09:33,  1.65it/s]
 88%|████████▊ | 50723/57600 [8:56:03<1:11:03,  1.61it/s]
 88%|████████▊ | 50724/57600 [8:56:04<1:10:51,  1.62it/s]
 88%|████████▊ | 50725/57600 [8:56:04<1:11:40,  1.60it/s]
 88%|████████▊ | 50726/57600 [8:56:05<1:13:41,  1.55it/s]
 88%|████████▊ | 50727/57600 [8:56:06<1:12:05,  1.59it/s]
 88%|████████▊ | 50728/57600 [8:56:06<1:11:46,  1.60it/s]
 88%|████████▊ | 50729/57600 [8:56:07<1:12:34,  1.58it/s]
 88%|████████▊ | 50730/57600 [8:56:07<1:13:29,  1.56it/s]
 88%|████████▊ | 50731/57600 [8:56:08<1:13:26,  1.56it/s]
 88%|████████▊ | 50732/57600 [8:56:09<1:13:23,  1.56it/s]
 88%|████████▊ | 50733/57600 [8:56:09<1:12:53,  1.57it/s]
 88%|████████▊ | 50734/57600 [8:56:10<1:11:14,  1.61it/s]
 88%|████████▊ | 50735/57600 [8:56:11<1:11:39,  1.60it/s]
 88%|████████▊ | 50736/57600 [8:56:11<1:11:09,  1.61it/s]
 88%|████████▊ | 50737/57600 [8:56:12<1:13:23,  1.56it/s]
 88%|████████▊ | 50738/57600 [8:56:12<1:12:45,  1.57it/s]
 88%|████████▊ | 50739/57600 [8:56:13<1:11:35,  1.60it/s]
 88%|████████▊ | 50740/57600 [8:56:14<1:13:20,  1.56it/s]
                                                         
{'loss': 1.1075, 'learning_rate': 2.0756097560975607e-07, 'epoch': 560.04}

 88%|████████▊ | 50740/57600 [8:56:14<1:13:20,  1.56it/s]
 88%|████████▊ | 50741/57600 [8:56:14<1:12:35,  1.57it/s]
 88%|████████▊ | 50742/57600 [8:56:15<1:12:26,  1.58it/s]
 88%|████████▊ | 50743/57600 [8:56:16<1:12:37,  1.57it/s]
 88%|████████▊ | 50744/57600 [8:56:16<1:13:53,  1.55it/s]
 88%|████████▊ | 50745/57600 [8:56:17<1:11:53,  1.59it/s]
 88%|████████▊ | 50746/57600 [8:56:18<1:11:33,  1.60it/s]
 88%|████████▊ | 50747/57600 [8:56:18<1:10:03,  1.63it/s]
 88%|████████▊ | 50748/57600 [8:56:19<1:09:40,  1.64it/s]
 88%|████████▊ | 50749/57600 [8:56:19<1:10:40,  1.62it/s]
 88%|████████▊ | 50750/57600 [8:56:20<1:15:21,  1.52it/s]
 88%|████████▊ | 50751/57600 [8:56:21<1:17:42,  1.47it/s]
 88%|████████▊ | 50752/57600 [8:56:21<1:14:26,  1.53it/s]
 88%|████████▊ | 50753/57600 [8:56:22<1:12:05,  1.58it/s]
 88%|████████▊ | 50754/57600 [8:56:23<1:11:54,  1.59it/s]
 88%|████████▊ | 50755/57600 [8:56:23<1:11:01,  1.61it/s]
 88%|████████▊ | 50756/57600 [8:56:24<1:09:10,  1.65it/s]
 88%|████████▊ | 50757/57600 [8:56:24<1:08:55,  1.65it/s]
 88%|████████▊ | 50758/57600 [8:56:25<1:10:14,  1.62it/s]
 88%|████████▊ | 50759/57600 [8:56:26<1:10:46,  1.61it/s]
 88%|████████▊ | 50760/57600 [8:56:26<1:12:44,  1.57it/s]
                                                         
{'loss': 1.1045, 'learning_rate': 2.072473867595819e-07, 'epoch': 560.26}

 88%|████████▊ | 50760/57600 [8:56:26<1:12:44,  1.57it/s]
 88%|████████▊ | 50761/57600 [8:56:27<1:10:49,  1.61it/s]
 88%|████████▊ | 50762/57600 [8:56:28<1:13:05,  1.56it/s]
 88%|████████▊ | 50763/57600 [8:56:28<1:14:02,  1.54it/s]
 88%|████████▊ | 50764/57600 [8:56:29<1:11:25,  1.60it/s]
 88%|████████▊ | 50765/57600 [8:56:30<1:10:44,  1.61it/s]
 88%|████████▊ | 50766/57600 [8:56:30<1:10:45,  1.61it/s]
 88%|████████▊ | 50767/57600 [8:56:31<1:10:47,  1.61it/s]
 88%|████████▊ | 50768/57600 [8:56:31<1:11:15,  1.60it/s]
 88%|████████▊ | 50769/57600 [8:56:32<1:09:33,  1.64it/s]
 88%|████████▊ | 50770/57600 [8:56:33<1:11:04,  1.60it/s]
 88%|████████▊ | 50771/57600 [8:56:33<1:09:47,  1.63it/s]
 88%|████████▊ | 50772/57600 [8:56:34<1:08:29,  1.66it/s]
 88%|████████▊ | 50773/57600 [8:56:34<1:10:11,  1.62it/s]
 88%|████████▊ | 50774/57600 [8:56:35<1:09:52,  1.63it/s]
 88%|████████▊ | 50775/57600 [8:56:36<1:09:04,  1.65it/s]
 88%|████████▊ | 50776/57600 [8:56:36<1:10:40,  1.61it/s]
 88%|████████▊ | 50777/57600 [8:56:37<1:11:12,  1.60it/s]
 88%|████████▊ | 50778/57600 [8:56:38<1:12:49,  1.56it/s]
 88%|████████▊ | 50779/57600 [8:56:38<1:11:34,  1.59it/s]
 88%|████████▊ | 50780/57600 [8:56:39<1:09:56,  1.63it/s]
                                                         
{'loss': 1.1279, 'learning_rate': 2.0693379790940763e-07, 'epoch': 560.49}

 88%|████████▊ | 50780/57600 [8:56:39<1:09:56,  1.63it/s]
 88%|████████▊ | 50781/57600 [8:56:39<1:12:40,  1.56it/s]
 88%|████████▊ | 50782/57600 [8:56:40<1:14:09,  1.53it/s]
 88%|████████▊ | 50783/57600 [8:56:41<1:14:03,  1.53it/s]
 88%|████████▊ | 50784/57600 [8:56:41<1:14:13,  1.53it/s]
 88%|████████▊ | 50785/57600 [8:56:42<1:15:01,  1.51it/s]
 88%|████████▊ | 50786/57600 [8:56:43<1:12:40,  1.56it/s]
 88%|████████▊ | 50787/57600 [8:56:43<1:12:44,  1.56it/s]
 88%|████████▊ | 50788/57600 [8:56:44<1:12:10,  1.57it/s]
 88%|████████▊ | 50789/57600 [8:56:45<1:14:23,  1.53it/s]
 88%|████████▊ | 50790/57600 [8:56:45<1:13:47,  1.54it/s]
 88%|████████▊ | 50791/57600 [8:56:46<1:14:34,  1.52it/s]
 88%|████████▊ | 50792/57600 [8:56:47<1:15:21,  1.51it/s]
 88%|████████▊ | 50793/57600 [8:56:47<1:14:19,  1.53it/s]
 88%|████████▊ | 50794/57600 [8:56:48<1:12:31,  1.56it/s]
 88%|████████▊ | 50795/57600 [8:56:49<1:13:50,  1.54it/s]
 88%|████████▊ | 50796/57600 [8:56:49<1:14:36,  1.52it/s]
 88%|████████▊ | 50797/57600 [8:56:50<1:13:13,  1.55it/s]
 88%|████████▊ | 50798/57600 [8:56:51<1:13:05,  1.55it/s]
 88%|████████▊ | 50799/57600 [8:56:51<1:12:30,  1.56it/s]
 88%|████████▊ | 50800/57600 [8:56:52<1:12:38,  1.56it/s]
                                                         
{'loss': 1.0664, 'learning_rate': 2.0662020905923346e-07, 'epoch': 560.71}

 88%|████████▊ | 50800/57600 [8:56:52<1:12:38,  1.56it/s]
 88%|████████▊ | 50801/57600 [8:56:52<1:11:08,  1.59it/s]
 88%|████████▊ | 50802/57600 [8:56:53<1:10:52,  1.60it/s]
 88%|████████▊ | 50803/57600 [8:56:54<1:12:18,  1.57it/s]
 88%|████████▊ | 50804/57600 [8:56:54<1:10:27,  1.61it/s]
 88%|████████▊ | 50805/57600 [8:56:55<1:08:32,  1.65it/s]
 88%|████████▊ | 50806/57600 [8:56:55<1:08:27,  1.65it/s]
 88%|████████▊ | 50807/57600 [8:56:56<1:07:46,  1.67it/s]
 88%|████████▊ | 50808/57600 [8:56:57<1:10:27,  1.61it/s]
 88%|████████▊ | 50809/57600 [8:56:57<1:08:56,  1.64it/s]
 88%|████████▊ | 50810/57600 [8:56:58<1:08:56,  1.64it/s]
 88%|████████▊ | 50811/57600 [8:56:58<1:07:49,  1.67it/s]
 88%|████████▊ | 50812/57600 [8:56:59<1:08:26,  1.65it/s]
 88%|████████▊ | 50813/57600 [8:57:00<1:07:21,  1.68it/s]
 88%|████████▊ | 50814/57600 [8:57:00<1:08:18,  1.66it/s]
 88%|████████▊ | 50815/57600 [8:57:01<1:07:45,  1.67it/s]
 88%|████████▊ | 50816/57600 [8:57:01<1:08:10,  1.66it/s]
 88%|████████▊ | 50817/57600 [8:57:02<1:07:00,  1.69it/s]
 88%|████████▊ | 50818/57600 [8:57:03<1:07:25,  1.68it/s]
 88%|████████▊ | 50819/57600 [8:57:03<1:08:27,  1.65it/s]
 88%|████████▊ | 50820/57600 [8:57:04<1:07:52,  1.66it/s]
                                                         
{'loss': 1.1245, 'learning_rate': 2.0630662020905919e-07, 'epoch': 560.93}

 88%|████████▊ | 50820/57600 [8:57:04<1:07:52,  1.66it/s]
 88%|████████▊ | 50821/57600 [8:57:04<1:07:44,  1.67it/s]
 88%|████████▊ | 50822/57600 [8:57:05<1:08:53,  1.64it/s]
 88%|████████▊ | 50823/57600 [8:57:06<1:09:02,  1.64it/s]
 88%|████████▊ | 50824/57600 [8:57:07<1:14:22,  1.52it/s]
 88%|████████▊ | 50825/57600 [8:57:07<1:12:48,  1.55it/s]
 88%|████████▊ | 50826/57600 [8:57:08<1:13:51,  1.53it/s]
 88%|████████▊ | 50827/57600 [8:57:09<1:18:14,  1.44it/s]
 88%|████████▊ | 50828/57600 [8:57:09<1:16:44,  1.47it/s]
 88%|████████▊ | 50829/57600 [8:57:10<1:13:33,  1.53it/s]
 88%|████████▊ | 50830/57600 [8:57:10<1:11:59,  1.57it/s]
 88%|████████▊ | 50831/57600 [8:57:11<1:09:10,  1.63it/s]
 88%|████████▊ | 50832/57600 [8:57:12<1:08:11,  1.65it/s]
 88%|████████▊ | 50833/57600 [8:57:12<1:06:37,  1.69it/s]
 88%|████████▊ | 50834/57600 [8:57:13<1:07:42,  1.67it/s]
 88%|████████▊ | 50835/57600 [8:57:13<1:09:20,  1.63it/s]
 88%|████████▊ | 50836/57600 [8:57:14<1:09:07,  1.63it/s]
 88%|████████▊ | 50837/57600 [8:57:15<1:11:10,  1.58it/s]
 88%|████████▊ | 50838/57600 [8:57:15<1:09:21,  1.62it/s]
 88%|████████▊ | 50839/57600 [8:57:16<1:10:44,  1.59it/s]
 88%|████████▊ | 50840/57600 [8:57:17<1:13:39,  1.53it/s]
                                                         
{'loss': 1.1102, 'learning_rate': 2.0599303135888502e-07, 'epoch': 561.15}

 88%|████████▊ | 50840/57600 [8:57:17<1:13:39,  1.53it/s]
 88%|████████▊ | 50841/57600 [8:57:17<1:12:55,  1.54it/s]
 88%|████████▊ | 50842/57600 [8:57:18<1:14:34,  1.51it/s]
 88%|████████▊ | 50843/57600 [8:57:19<1:11:48,  1.57it/s]
 88%|████████▊ | 50844/57600 [8:57:19<1:10:22,  1.60it/s]
 88%|████████▊ | 50845/57600 [8:57:20<1:09:49,  1.61it/s]
 88%|████████▊ | 50846/57600 [8:57:20<1:11:16,  1.58it/s]
 88%|████████▊ | 50847/57600 [8:57:21<1:10:01,  1.61it/s]
 88%|████████▊ | 50848/57600 [8:57:22<1:08:00,  1.65it/s]
 88%|████████▊ | 50849/57600 [8:57:22<1:07:01,  1.68it/s]
 88%|████████▊ | 50850/57600 [8:57:23<1:07:51,  1.66it/s]
 88%|████████▊ | 50851/57600 [8:57:23<1:09:41,  1.61it/s]
 88%|████████▊ | 50852/57600 [8:57:24<1:08:58,  1.63it/s]
 88%|████████▊ | 50853/57600 [8:57:25<1:09:38,  1.61it/s]
 88%|████████▊ | 50854/57600 [8:57:25<1:07:48,  1.66it/s]
 88%|████████▊ | 50855/57600 [8:57:26<1:10:49,  1.59it/s]
 88%|████████▊ | 50856/57600 [8:57:26<1:09:16,  1.62it/s]
 88%|████████▊ | 50857/57600 [8:57:27<1:10:48,  1.59it/s]
 88%|████████▊ | 50858/57600 [8:57:28<1:12:24,  1.55it/s]
 88%|████████▊ | 50859/57600 [8:57:28<1:10:32,  1.59it/s]
 88%|████████▊ | 50860/57600 [8:57:29<1:13:07,  1.54it/s]
                                                         
{'loss': 1.1089, 'learning_rate': 2.0567944250871074e-07, 'epoch': 561.37}

 88%|████████▊ | 50860/57600 [8:57:29<1:13:07,  1.54it/s]
 88%|████████▊ | 50861/57600 [8:57:30<1:11:23,  1.57it/s]
 88%|████████▊ | 50862/57600 [8:57:30<1:11:13,  1.58it/s]
 88%|████████▊ | 50863/57600 [8:57:31<1:13:13,  1.53it/s]
 88%|████████▊ | 50864/57600 [8:57:32<1:12:03,  1.56it/s]
 88%|████████▊ | 50865/57600 [8:57:32<1:10:04,  1.60it/s]
 88%|████████▊ | 50866/57600 [8:57:33<1:10:40,  1.59it/s]
 88%|████████▊ | 50867/57600 [8:57:34<1:13:03,  1.54it/s]
 88%|████████▊ | 50868/57600 [8:57:34<1:13:48,  1.52it/s]
 88%|████████▊ | 50869/57600 [8:57:35<1:13:02,  1.54it/s]
 88%|████████▊ | 50870/57600 [8:57:36<1:13:22,  1.53it/s]
 88%|████████▊ | 50871/57600 [8:57:36<1:15:28,  1.49it/s]
 88%|████████▊ | 50872/57600 [8:57:37<1:12:32,  1.55it/s]
 88%|████████▊ | 50873/57600 [8:57:37<1:11:20,  1.57it/s]
 88%|████████▊ | 50874/57600 [8:57:38<1:13:29,  1.53it/s]
 88%|████████▊ | 50875/57600 [8:57:39<1:13:51,  1.52it/s]
 88%|████████▊ | 50876/57600 [8:57:39<1:13:21,  1.53it/s]
 88%|████████▊ | 50877/57600 [8:57:40<1:14:49,  1.50it/s]
 88%|████████▊ | 50878/57600 [8:57:41<1:11:47,  1.56it/s]
 88%|████████▊ | 50879/57600 [8:57:41<1:10:22,  1.59it/s]
 88%|████████▊ | 50880/57600 [8:57:42<1:08:21,  1.64it/s]
                                                         
{'loss': 1.092, 'learning_rate': 2.0536585365853657e-07, 'epoch': 561.59}

 88%|████████▊ | 50880/57600 [8:57:42<1:08:21,  1.64it/s]
 88%|████████▊ | 50881/57600 [8:57:43<1:07:56,  1.65it/s]
 88%|████████▊ | 50882/57600 [8:57:43<1:10:01,  1.60it/s]
 88%|████████▊ | 50883/57600 [8:57:44<1:08:47,  1.63it/s]
 88%|████████▊ | 50884/57600 [8:57:44<1:11:40,  1.56it/s]
 88%|████████▊ | 50885/57600 [8:57:45<1:11:25,  1.57it/s]
 88%|████████▊ | 50886/57600 [8:57:46<1:11:31,  1.56it/s]
 88%|████████▊ | 50887/57600 [8:57:46<1:10:16,  1.59it/s]
 88%|████████▊ | 50888/57600 [8:57:47<1:10:18,  1.59it/s]
 88%|████████▊ | 50889/57600 [8:57:48<1:08:57,  1.62it/s]
 88%|████████▊ | 50890/57600 [8:57:48<1:10:11,  1.59it/s]
 88%|████████▊ | 50891/57600 [8:57:49<1:13:38,  1.52it/s]
 88%|████████▊ | 50892/57600 [8:57:50<1:14:49,  1.49it/s]
 88%|████████▊ | 50893/57600 [8:57:50<1:13:00,  1.53it/s]
 88%|████████▊ | 50894/57600 [8:57:51<1:13:46,  1.52it/s]
 88%|████████▊ | 50895/57600 [8:57:52<1:11:08,  1.57it/s]
 88%|████████▊ | 50896/57600 [8:57:52<1:11:25,  1.56it/s]
 88%|████████▊ | 50897/57600 [8:57:53<1:10:47,  1.58it/s]
 88%|████████▊ | 50898/57600 [8:57:53<1:12:12,  1.55it/s]
 88%|████████▊ | 50899/57600 [8:57:54<1:12:13,  1.55it/s]
 88%|████████▊ | 50900/57600 [8:57:55<1:10:46,  1.58it/s]
                                                         
{'loss': 1.1311, 'learning_rate': 2.050522648083624e-07, 'epoch': 561.81}

 88%|████████▊ | 50900/57600 [8:57:55<1:10:46,  1.58it/s]
 88%|████████▊ | 50901/57600 [8:57:55<1:09:51,  1.60it/s]
 88%|████████▊ | 50902/57600 [8:57:56<1:08:59,  1.62it/s]
 88%|████████▊ | 50903/57600 [8:57:57<1:09:21,  1.61it/s]
 88%|████████▊ | 50904/57600 [8:57:57<1:09:18,  1.61it/s]
 88%|████████▊ | 50905/57600 [8:57:58<1:10:17,  1.59it/s]
 88%|████████▊ | 50906/57600 [8:57:58<1:07:44,  1.65it/s]
 88%|████████▊ | 50907/57600 [8:57:59<1:09:42,  1.60it/s]
 88%|████████▊ | 50908/57600 [8:58:00<1:08:51,  1.62it/s]
 88%|████████▊ | 50909/57600 [8:58:00<1:08:57,  1.62it/s]
 88%|████████▊ | 50910/57600 [8:58:01<1:07:21,  1.66it/s]
 88%|████████▊ | 50911/57600 [8:58:01<1:07:52,  1.64it/s]
 88%|████████▊ | 50912/57600 [8:58:02<1:08:50,  1.62it/s]
 88%|████████▊ | 50913/57600 [8:58:03<1:12:07,  1.55it/s]
 88%|████████▊ | 50914/57600 [8:58:03<1:11:41,  1.55it/s]
 88%|████████▊ | 50915/57600 [8:58:04<1:10:57,  1.57it/s]
 88%|████████▊ | 50916/57600 [8:58:05<1:09:17,  1.61it/s]
 88%|████████▊ | 50917/57600 [8:58:05<1:07:50,  1.64it/s]
 88%|████████▊ | 50918/57600 [8:58:06<1:13:55,  1.51it/s]
 88%|████████▊ | 50919/57600 [8:58:07<1:13:59,  1.50it/s]
 88%|████████▊ | 50920/57600 [8:58:07<1:12:09,  1.54it/s]
                                                         
{'loss': 1.1146, 'learning_rate': 2.047386759581881e-07, 'epoch': 562.03}

 88%|████████▊ | 50920/57600 [8:58:07<1:12:09,  1.54it/s]
 88%|████████▊ | 50921/57600 [8:58:08<1:10:32,  1.58it/s]
 88%|████████▊ | 50922/57600 [8:58:09<1:10:26,  1.58it/s]
 88%|████████▊ | 50923/57600 [8:58:09<1:09:52,  1.59it/s]
 88%|████████▊ | 50924/57600 [8:58:10<1:07:43,  1.64it/s]
 88%|████████▊ | 50925/57600 [8:58:10<1:09:12,  1.61it/s]
 88%|████████▊ | 50926/57600 [8:58:11<1:09:59,  1.59it/s]
 88%|████████▊ | 50927/57600 [8:58:12<1:08:41,  1.62it/s]
 88%|████████▊ | 50928/57600 [8:58:12<1:08:36,  1.62it/s]
 88%|████████▊ | 50929/57600 [8:58:13<1:10:34,  1.58it/s]
 88%|████████▊ | 50930/57600 [8:58:14<1:09:32,  1.60it/s]
 88%|████████▊ | 50931/57600 [8:58:14<1:11:28,  1.55it/s]
 88%|████████▊ | 50932/57600 [8:58:15<1:11:55,  1.55it/s]
 88%|████████▊ | 50933/57600 [8:58:15<1:09:56,  1.59it/s]
 88%|████████▊ | 50934/57600 [8:58:16<1:09:16,  1.60it/s]
 88%|████████▊ | 50935/57600 [8:58:17<1:09:37,  1.60it/s]
 88%|████████▊ | 50936/57600 [8:58:17<1:09:06,  1.61it/s]
 88%|████████▊ | 50937/57600 [8:58:18<1:07:49,  1.64it/s]
 88%|████████▊ | 50938/57600 [8:58:18<1:07:59,  1.63it/s]
 88%|████████▊ | 50939/57600 [8:58:19<1:06:32,  1.67it/s]
 88%|████████▊ | 50940/57600 [8:58:20<1:08:03,  1.63it/s]
                                                         
{'loss': 1.1463, 'learning_rate': 2.0442508710801396e-07, 'epoch': 562.25}

 88%|████████▊ | 50940/57600 [8:58:20<1:08:03,  1.63it/s]
 88%|████████▊ | 50941/57600 [8:58:20<1:08:47,  1.61it/s]
 88%|████████▊ | 50942/57600 [8:58:21<1:09:26,  1.60it/s]
 88%|████████▊ | 50943/57600 [8:58:22<1:08:35,  1.62it/s]
 88%|████████▊ | 50944/57600 [8:58:22<1:06:46,  1.66it/s]
 88%|████████▊ | 50945/57600 [8:58:23<1:07:19,  1.65it/s]
 88%|████████▊ | 50946/57600 [8:58:23<1:05:31,  1.69it/s]
 88%|████████▊ | 50947/57600 [8:58:24<1:06:18,  1.67it/s]
 88%|████████▊ | 50948/57600 [8:58:24<1:04:40,  1.71it/s]
 88%|████████▊ | 50949/57600 [8:58:25<1:05:40,  1.69it/s]
 88%|████████▊ | 50950/57600 [8:58:26<1:06:37,  1.66it/s]
 88%|████████▊ | 50951/57600 [8:58:26<1:07:31,  1.64it/s]
 88%|████████▊ | 50952/57600 [8:58:27<1:07:21,  1.65it/s]
 88%|████████▊ | 50953/57600 [8:58:28<1:10:27,  1.57it/s]
 88%|████████▊ | 50954/57600 [8:58:28<1:09:41,  1.59it/s]
 88%|████████▊ | 50955/57600 [8:58:29<1:10:44,  1.57it/s]
 88%|████████▊ | 50956/57600 [8:58:30<1:12:01,  1.54it/s]
 88%|████████▊ | 50957/57600 [8:58:30<1:11:20,  1.55it/s]
 88%|████████▊ | 50958/57600 [8:58:31<1:11:53,  1.54it/s]
 88%|████████▊ | 50959/57600 [8:58:31<1:08:48,  1.61it/s]
 88%|████████▊ | 50960/57600 [8:58:32<1:09:20,  1.60it/s]
                                                         
{'loss': 1.1455, 'learning_rate': 2.0411149825783966e-07, 'epoch': 562.47}

 88%|████████▊ | 50960/57600 [8:58:32<1:09:20,  1.60it/s]
 88%|████████▊ | 50961/57600 [8:58:33<1:08:08,  1.62it/s]
 88%|████████▊ | 50962/57600 [8:58:33<1:09:12,  1.60it/s]
 88%|████████▊ | 50963/57600 [8:58:34<1:09:04,  1.60it/s]
 88%|████████▊ | 50964/57600 [8:58:35<1:09:27,  1.59it/s]
 88%|████████▊ | 50965/57600 [8:58:35<1:10:22,  1.57it/s]
 88%|████████▊ | 50966/57600 [8:58:36<1:13:29,  1.50it/s]
 88%|████████▊ | 50967/57600 [8:58:37<1:13:50,  1.50it/s]
 88%|████████▊ | 50968/57600 [8:58:37<1:11:53,  1.54it/s]
 88%|████████▊ | 50969/57600 [8:58:38<1:12:05,  1.53it/s]
 88%|████████▊ | 50970/57600 [8:58:39<1:10:01,  1.58it/s]
 88%|████████▊ | 50971/57600 [8:58:39<1:10:09,  1.57it/s]
 88%|████████▊ | 50972/57600 [8:58:40<1:09:47,  1.58it/s]
 88%|████████▊ | 50973/57600 [8:58:40<1:08:43,  1.61it/s]
 88%|████████▊ | 50974/57600 [8:58:41<1:08:23,  1.61it/s]
 88%|████████▊ | 50975/57600 [8:58:42<1:06:00,  1.67it/s]
 88%|████████▊ | 50976/57600 [8:58:42<1:07:21,  1.64it/s]
 89%|████████▊ | 50977/57600 [8:58:43<1:08:29,  1.61it/s]
 89%|████████▊ | 50978/57600 [8:58:43<1:10:49,  1.56it/s]
 89%|████████▊ | 50979/57600 [8:58:44<1:11:23,  1.55it/s]
 89%|████████▊ | 50980/57600 [8:58:45<1:10:35,  1.56it/s]
                                                         
{'loss': 1.0795, 'learning_rate': 2.0379790940766552e-07, 'epoch': 562.69}

 89%|████████▊ | 50980/57600 [8:58:45<1:10:35,  1.56it/s]
 89%|████████▊ | 50981/57600 [8:58:45<1:09:01,  1.60it/s]
 89%|████████▊ | 50982/57600 [8:58:46<1:09:31,  1.59it/s]
 89%|████████▊ | 50983/57600 [8:58:47<1:11:37,  1.54it/s]
 89%|████████▊ | 50984/57600 [8:58:47<1:11:03,  1.55it/s]
 89%|████████▊ | 50985/57600 [8:58:48<1:10:54,  1.55it/s]
 89%|████████▊ | 50986/57600 [8:58:49<1:11:56,  1.53it/s]
 89%|████████▊ | 50987/57600 [8:58:49<1:09:39,  1.58it/s]
 89%|████████▊ | 50988/57600 [8:58:50<1:10:48,  1.56it/s]
 89%|████████▊ | 50989/57600 [8:58:51<1:10:05,  1.57it/s]
 89%|████████▊ | 50990/57600 [8:58:51<1:10:24,  1.56it/s]
 89%|████████▊ | 50991/57600 [8:58:52<1:09:37,  1.58it/s]
 89%|████████▊ | 50992/57600 [8:58:52<1:11:40,  1.54it/s]
 89%|████████▊ | 50993/57600 [8:58:53<1:10:39,  1.56it/s]
 89%|████████▊ | 50994/57600 [8:58:54<1:07:59,  1.62it/s]
 89%|████████▊ | 50995/57600 [8:58:54<1:08:47,  1.60it/s]
 89%|████████▊ | 50996/57600 [8:58:55<1:08:54,  1.60it/s]
 89%|████████▊ | 50997/57600 [8:58:56<1:08:34,  1.60it/s]
 89%|████████▊ | 50998/57600 [8:58:56<1:09:11,  1.59it/s]
 89%|████████▊ | 50999/57600 [8:58:57<1:08:21,  1.61it/s]
 89%|████████▊ | 51000/57600 [8:58:57<1:07:15,  1.64it/s]
                                                         
{'loss': 1.1111, 'learning_rate': 2.0348432055749132e-07, 'epoch': 562.91}

 89%|████████▊ | 51000/57600 [8:58:57<1:07:15,  1.64it/s]
 89%|████████▊ | 51001/57600 [8:58:58<1:08:09,  1.61it/s]
 89%|████████▊ | 51002/57600 [8:58:59<1:08:57,  1.59it/s]
 89%|████████▊ | 51003/57600 [8:58:59<1:07:32,  1.63it/s]
 89%|████████▊ | 51004/57600 [8:59:00<1:10:40,  1.56it/s]
 89%|████████▊ | 51005/57600 [8:59:01<1:08:56,  1.59it/s]
 89%|████████▊ | 51006/57600 [8:59:01<1:09:31,  1.58it/s]
 89%|████████▊ | 51007/57600 [8:59:02<1:08:44,  1.60it/s]
 89%|████████▊ | 51008/57600 [8:59:03<1:10:56,  1.55it/s]
 89%|████████▊ | 51009/57600 [8:59:03<1:09:17,  1.59it/s]
 89%|████████▊ | 51010/57600 [8:59:04<1:10:09,  1.57it/s]
 89%|████████▊ | 51011/57600 [8:59:04<1:12:26,  1.52it/s]
 89%|████████▊ | 51012/57600 [8:59:05<1:09:31,  1.58it/s]
 89%|████████▊ | 51013/57600 [8:59:06<1:11:41,  1.53it/s]
 89%|████████▊ | 51014/57600 [8:59:06<1:11:21,  1.54it/s]
 89%|████████▊ | 51015/57600 [8:59:07<1:10:05,  1.57it/s]
 89%|████████▊ | 51016/57600 [8:59:08<1:08:40,  1.60it/s]
 89%|████████▊ | 51017/57600 [8:59:08<1:07:09,  1.63it/s]
 89%|████████▊ | 51018/57600 [8:59:09<1:10:58,  1.55it/s]
 89%|████████▊ | 51019/57600 [8:59:10<1:10:47,  1.55it/s]
 89%|████████▊ | 51020/57600 [8:59:10<1:11:26,  1.54it/s]
                                                         
{'loss': 1.0907, 'learning_rate': 2.0317073170731705e-07, 'epoch': 563.13}

 89%|████████▊ | 51020/57600 [8:59:10<1:11:26,  1.54it/s]
 89%|████████▊ | 51021/57600 [8:59:11<1:08:43,  1.60it/s]
 89%|████████▊ | 51022/57600 [8:59:11<1:06:34,  1.65it/s]
 89%|████████▊ | 51023/57600 [8:59:12<1:08:42,  1.60it/s]
 89%|████████▊ | 51024/57600 [8:59:13<1:06:28,  1.65it/s]
 89%|████████▊ | 51025/57600 [8:59:13<1:05:24,  1.68it/s]
 89%|████████▊ | 51026/57600 [8:59:14<1:03:59,  1.71it/s]
 89%|████████▊ | 51027/57600 [8:59:14<1:03:58,  1.71it/s]
 89%|████████▊ | 51028/57600 [8:59:15<1:08:37,  1.60it/s]
 89%|████████▊ | 51029/57600 [8:59:16<1:08:12,  1.61it/s]
 89%|████████▊ | 51030/57600 [8:59:16<1:07:33,  1.62it/s]
 89%|████████▊ | 51031/57600 [8:59:17<1:07:21,  1.63it/s]
 89%|████████▊ | 51032/57600 [8:59:17<1:08:54,  1.59it/s]
 89%|████████▊ | 51033/57600 [8:59:18<1:10:31,  1.55it/s]
 89%|████████▊ | 51034/57600 [8:59:19<1:11:00,  1.54it/s]
 89%|████████▊ | 51035/57600 [8:59:19<1:08:01,  1.61it/s]
 89%|████████▊ | 51036/57600 [8:59:20<1:07:48,  1.61it/s]
 89%|████████▊ | 51037/57600 [8:59:21<1:07:10,  1.63it/s]
 89%|████████▊ | 51038/57600 [8:59:21<1:06:58,  1.63it/s]
 89%|████████▊ | 51039/57600 [8:59:22<1:06:02,  1.66it/s]
 89%|████████▊ | 51040/57600 [8:59:22<1:06:14,  1.65it/s]
                                                         
{'loss': 1.1696, 'learning_rate': 2.0285714285714288e-07, 'epoch': 563.36}

 89%|████████▊ | 51040/57600 [8:59:22<1:06:14,  1.65it/s]
 89%|████████▊ | 51041/57600 [8:59:23<1:05:44,  1.66it/s]
 89%|████████▊ | 51042/57600 [8:59:24<1:05:45,  1.66it/s]
 89%|████████▊ | 51043/57600 [8:59:24<1:05:18,  1.67it/s]
 89%|████████▊ | 51044/57600 [8:59:25<1:05:46,  1.66it/s]
 89%|████████▊ | 51045/57600 [8:59:25<1:05:52,  1.66it/s]
 89%|████████▊ | 51046/57600 [8:59:26<1:06:35,  1.64it/s]
 89%|████████▊ | 51047/57600 [8:59:27<1:08:36,  1.59it/s]
 89%|████████▊ | 51048/57600 [8:59:27<1:08:41,  1.59it/s]
 89%|████████▊ | 51049/57600 [8:59:28<1:06:59,  1.63it/s]
 89%|████████▊ | 51050/57600 [8:59:28<1:04:53,  1.68it/s]
 89%|████████▊ | 51051/57600 [8:59:29<1:06:37,  1.64it/s]
 89%|████████▊ | 51052/57600 [8:59:30<1:05:16,  1.67it/s]
 89%|████████▊ | 51053/57600 [8:59:30<1:04:51,  1.68it/s]
 89%|████████▊ | 51054/57600 [8:59:31<1:06:49,  1.63it/s]
 89%|████████▊ | 51055/57600 [8:59:32<1:06:02,  1.65it/s]
 89%|████████▊ | 51056/57600 [8:59:32<1:05:45,  1.66it/s]
 89%|████████▊ | 51057/57600 [8:59:33<1:05:29,  1.67it/s]
 89%|████████▊ | 51058/57600 [8:59:33<1:06:01,  1.65it/s]
 89%|████████▊ | 51059/57600 [8:59:34<1:06:21,  1.64it/s]
 89%|████████▊ | 51060/57600 [8:59:35<1:06:54,  1.63it/s]
                                                         
{'loss': 1.1064, 'learning_rate': 2.025435540069686e-07, 'epoch': 563.58}

 89%|████████▊ | 51060/57600 [8:59:35<1:06:54,  1.63it/s]
 89%|████████▊ | 51061/57600 [8:59:35<1:06:36,  1.64it/s]
 89%|████████▊ | 51062/57600 [8:59:36<1:08:09,  1.60it/s]
 89%|████████▊ | 51063/57600 [8:59:36<1:08:04,  1.60it/s]
 89%|████████▊ | 51064/57600 [8:59:37<1:08:46,  1.58it/s]
 89%|████████▊ | 51065/57600 [8:59:38<1:08:19,  1.59it/s]
 89%|████████▊ | 51066/57600 [8:59:38<1:09:37,  1.56it/s]
 89%|████████▊ | 51067/57600 [8:59:39<1:10:05,  1.55it/s]
 89%|████████▊ | 51068/57600 [8:59:40<1:08:00,  1.60it/s]
 89%|████████▊ | 51069/57600 [8:59:40<1:07:41,  1.61it/s]
 89%|████████▊ | 51070/57600 [8:59:41<1:08:20,  1.59it/s]
 89%|████████▊ | 51071/57600 [8:59:41<1:07:15,  1.62it/s]
 89%|████████▊ | 51072/57600 [8:59:42<1:08:09,  1.60it/s]
 89%|████████▊ | 51073/57600 [8:59:43<1:07:27,  1.61it/s]
 89%|████████▊ | 51074/57600 [8:59:43<1:08:17,  1.59it/s]
 89%|████████▊ | 51075/57600 [8:59:44<1:09:09,  1.57it/s]
 89%|████████▊ | 51076/57600 [8:59:45<1:09:23,  1.57it/s]
 89%|████████▊ | 51077/57600 [8:59:45<1:10:49,  1.54it/s]
 89%|████████▊ | 51078/57600 [8:59:46<1:09:25,  1.57it/s]
 89%|████████▊ | 51079/57600 [8:59:47<1:09:22,  1.57it/s]
 89%|████████▊ | 51080/57600 [8:59:47<1:08:58,  1.58it/s]
                                                         
{'loss': 1.0813, 'learning_rate': 2.0222996515679444e-07, 'epoch': 563.8}

 89%|████████▊ | 51080/57600 [8:59:47<1:08:58,  1.58it/s]
 89%|████████▊ | 51081/57600 [8:59:48<1:09:41,  1.56it/s]
 89%|████████▊ | 51082/57600 [8:59:48<1:08:55,  1.58it/s]
 89%|████████▊ | 51083/57600 [8:59:49<1:10:02,  1.55it/s]
 89%|████████▊ | 51084/57600 [8:59:50<1:08:08,  1.59it/s]
 89%|████████▊ | 51085/57600 [8:59:50<1:07:44,  1.60it/s]
 89%|████████▊ | 51086/57600 [8:59:51<1:06:31,  1.63it/s]
 89%|████████▊ | 51087/57600 [8:59:52<1:05:52,  1.65it/s]
 89%|████████▊ | 51088/57600 [8:59:52<1:05:06,  1.67it/s]
 89%|████████▊ | 51089/57600 [8:59:53<1:07:43,  1.60it/s]
 89%|████████▊ | 51090/57600 [8:59:53<1:06:30,  1.63it/s]
 89%|████████▊ | 51091/57600 [8:59:54<1:07:12,  1.61it/s]
 89%|████████▊ | 51092/57600 [8:59:55<1:07:13,  1.61it/s]
 89%|████████▊ | 51093/57600 [8:59:55<1:07:26,  1.61it/s]
 89%|████████▊ | 51094/57600 [8:59:56<1:08:10,  1.59it/s]
 89%|████████▊ | 51095/57600 [8:59:57<1:07:23,  1.61it/s]
 89%|████████▊ | 51096/57600 [8:59:57<1:08:02,  1.59it/s]
 89%|████████▊ | 51097/57600 [8:59:58<1:04:48,  1.67it/s]
 89%|████████▊ | 51098/57600 [8:59:58<1:09:29,  1.56it/s]
 89%|████████▊ | 51099/57600 [8:59:59<1:10:30,  1.54it/s]
 89%|████████▊ | 51100/57600 [9:00:00<1:11:32,  1.51it/s]
                                                         
{'loss': 1.1003, 'learning_rate': 2.0191637630662016e-07, 'epoch': 564.02}

 89%|████████▊ | 51100/57600 [9:00:00<1:11:32,  1.51it/s]
 89%|████████▊ | 51101/57600 [9:00:00<1:10:21,  1.54it/s]
 89%|████████▊ | 51102/57600 [9:00:01<1:07:57,  1.59it/s]
 89%|████████▊ | 51103/57600 [9:00:02<1:06:33,  1.63it/s]
 89%|████████▊ | 51104/57600 [9:00:02<1:07:22,  1.61it/s]
 89%|████████▊ | 51105/57600 [9:00:03<1:09:08,  1.57it/s]
 89%|████████▊ | 51106/57600 [9:00:03<1:07:20,  1.61it/s]
 89%|████████▊ | 51107/57600 [9:00:04<1:06:28,  1.63it/s]
 89%|████████▊ | 51108/57600 [9:00:05<1:05:43,  1.65it/s]
 89%|████████▊ | 51109/57600 [9:00:05<1:05:19,  1.66it/s]
 89%|████████▊ | 51110/57600 [9:00:06<1:06:47,  1.62it/s]
 89%|████████▊ | 51111/57600 [9:00:07<1:08:37,  1.58it/s]
 89%|████████▊ | 51112/57600 [9:00:07<1:07:38,  1.60it/s]
 89%|████████▊ | 51113/57600 [9:00:08<1:08:50,  1.57it/s]
 89%|████████▊ | 51114/57600 [9:00:08<1:08:52,  1.57it/s]
 89%|████████▊ | 51115/57600 [9:00:09<1:10:29,  1.53it/s]
 89%|████████▊ | 51116/57600 [9:00:10<1:10:51,  1.52it/s]
 89%|████████▊ | 51117/57600 [9:00:10<1:07:45,  1.59it/s]
 89%|████████▊ | 51118/57600 [9:00:11<1:07:56,  1.59it/s]
 89%|████████▊ | 51119/57600 [9:00:12<1:09:52,  1.55it/s]
 89%|████████▉ | 51120/57600 [9:00:12<1:08:43,  1.57it/s]
                                                         
{'loss': 1.1258, 'learning_rate': 2.01602787456446e-07, 'epoch': 564.24}

 89%|████████▉ | 51120/57600 [9:00:12<1:08:43,  1.57it/s]
 89%|████████▉ | 51121/57600 [9:00:13<1:07:30,  1.60it/s]
 89%|████████▉ | 51122/57600 [9:00:14<1:10:13,  1.54it/s]
 89%|████████▉ | 51123/57600 [9:00:14<1:08:51,  1.57it/s]
 89%|████████▉ | 51124/57600 [9:00:15<1:08:40,  1.57it/s]
 89%|████████▉ | 51125/57600 [9:00:16<1:09:19,  1.56it/s]
 89%|████████▉ | 51126/57600 [9:00:16<1:07:15,  1.60it/s]
 89%|████████▉ | 51127/57600 [9:00:17<1:06:07,  1.63it/s]
 89%|████████▉ | 51128/57600 [9:00:17<1:05:50,  1.64it/s]
 89%|████████▉ | 51129/57600 [9:00:18<1:06:22,  1.62it/s]
 89%|████████▉ | 51130/57600 [9:00:19<1:07:27,  1.60it/s]
 89%|████████▉ | 51131/57600 [9:00:19<1:07:03,  1.61it/s]
 89%|████████▉ | 51132/57600 [9:00:20<1:05:12,  1.65it/s]
 89%|████████▉ | 51133/57600 [9:00:20<1:05:00,  1.66it/s]
 89%|████████▉ | 51134/57600 [9:00:21<1:06:46,  1.61it/s]
 89%|████████▉ | 51135/57600 [9:00:22<1:08:28,  1.57it/s]
 89%|████████▉ | 51136/57600 [9:00:22<1:07:00,  1.61it/s]
 89%|████████▉ | 51137/57600 [9:00:23<1:08:20,  1.58it/s]
 89%|████████▉ | 51138/57600 [9:00:24<1:08:04,  1.58it/s]
 89%|████████▉ | 51139/57600 [9:00:24<1:06:17,  1.62it/s]
 89%|████████▉ | 51140/57600 [9:00:25<1:06:16,  1.62it/s]
                                                         
{'loss': 1.0982, 'learning_rate': 2.012891986062718e-07, 'epoch': 564.46}

 89%|████████▉ | 51140/57600 [9:00:25<1:06:16,  1.62it/s]
 89%|████████▉ | 51141/57600 [9:00:25<1:06:45,  1.61it/s]
 89%|████████▉ | 51142/57600 [9:00:26<1:06:49,  1.61it/s]
 89%|████████▉ | 51143/57600 [9:00:27<1:08:34,  1.57it/s]
 89%|████████▉ | 51144/57600 [9:00:27<1:08:36,  1.57it/s]
 89%|████████▉ | 51145/57600 [9:00:28<1:07:40,  1.59it/s]
 89%|████████▉ | 51146/57600 [9:00:29<1:07:53,  1.58it/s]
 89%|████████▉ | 51147/57600 [9:00:29<1:07:55,  1.58it/s]
 89%|████████▉ | 51148/57600 [9:00:30<1:07:20,  1.60it/s]
 89%|████████▉ | 51149/57600 [9:00:30<1:04:35,  1.66it/s]
 89%|████████▉ | 51150/57600 [9:00:31<1:03:40,  1.69it/s]
 89%|████████▉ | 51151/57600 [9:00:32<1:02:38,  1.72it/s]
 89%|████████▉ | 51152/57600 [9:00:32<1:00:56,  1.76it/s]
 89%|████████▉ | 51153/57600 [9:00:33<1:03:08,  1.70it/s]
 89%|████████▉ | 51154/57600 [9:00:33<1:04:04,  1.68it/s]
 89%|████████▉ | 51155/57600 [9:00:34<1:04:04,  1.68it/s]
 89%|████████▉ | 51156/57600 [9:00:35<1:04:32,  1.66it/s]
 89%|████████▉ | 51157/57600 [9:00:35<1:06:20,  1.62it/s]
 89%|████████▉ | 51158/57600 [9:00:36<1:08:44,  1.56it/s]
 89%|████████▉ | 51159/57600 [9:00:36<1:06:23,  1.62it/s]
 89%|████████▉ | 51160/57600 [9:00:37<1:05:18,  1.64it/s]
                                                         
{'loss': 1.1347, 'learning_rate': 2.0097560975609755e-07, 'epoch': 564.68}

 89%|████████▉ | 51160/57600 [9:00:37<1:05:18,  1.64it/s]
 89%|████████▉ | 51161/57600 [9:00:38<1:04:49,  1.66it/s]
 89%|████████▉ | 51162/57600 [9:00:38<1:04:42,  1.66it/s]
 89%|████████▉ | 51163/57600 [9:00:39<1:04:45,  1.66it/s]
 89%|████████▉ | 51164/57600 [9:00:39<1:05:24,  1.64it/s]
 89%|████████▉ | 51165/57600 [9:00:40<1:05:29,  1.64it/s]
 89%|████████▉ | 51166/57600 [9:00:41<1:04:58,  1.65it/s]
 89%|████████▉ | 51167/57600 [9:00:41<1:06:44,  1.61it/s]
 89%|████████▉ | 51168/57600 [9:00:42<1:06:00,  1.62it/s]
 89%|████████▉ | 51169/57600 [9:00:43<1:07:17,  1.59it/s]
 89%|████████▉ | 51170/57600 [9:00:43<1:06:34,  1.61it/s]
 89%|████████▉ | 51171/57600 [9:00:44<1:05:49,  1.63it/s]
 89%|████████▉ | 51172/57600 [9:00:44<1:08:48,  1.56it/s]
 89%|████████▉ | 51173/57600 [9:00:45<1:06:25,  1.61it/s]
 89%|████████▉ | 51174/57600 [9:00:46<1:06:38,  1.61it/s]
 89%|████████▉ | 51175/57600 [9:00:46<1:06:07,  1.62it/s]
 89%|████████▉ | 51176/57600 [9:00:47<1:07:09,  1.59it/s]
 89%|████████▉ | 51177/57600 [9:00:48<1:06:57,  1.60it/s]
 89%|████████▉ | 51178/57600 [9:00:48<1:08:17,  1.57it/s]
 89%|████████▉ | 51179/57600 [9:00:49<1:08:02,  1.57it/s]
 89%|████████▉ | 51180/57600 [9:00:49<1:05:38,  1.63it/s]
                                                         
{'loss': 1.1029, 'learning_rate': 2.0066202090592336e-07, 'epoch': 564.9}

 89%|████████▉ | 51180/57600 [9:00:49<1:05:38,  1.63it/s]
 89%|████████▉ | 51181/57600 [9:00:50<1:05:46,  1.63it/s]
 89%|████████▉ | 51182/57600 [9:00:51<1:03:57,  1.67it/s]
 89%|████████▉ | 51183/57600 [9:00:51<1:04:57,  1.65it/s]
 89%|████████▉ | 51184/57600 [9:00:52<1:04:57,  1.65it/s]
 89%|████████▉ | 51185/57600 [9:00:52<1:04:36,  1.65it/s]
 89%|████████▉ | 51186/57600 [9:00:53<1:04:59,  1.64it/s]
 89%|████████▉ | 51187/57600 [9:00:54<1:07:39,  1.58it/s]
 89%|████████▉ | 51188/57600 [9:00:54<1:07:27,  1.58it/s]
 89%|████████▉ | 51189/57600 [9:00:55<1:07:34,  1.58it/s]
 89%|████████▉ | 51190/57600 [9:00:56<1:08:42,  1.55it/s]
 89%|████████▉ | 51191/57600 [9:00:56<1:07:11,  1.59it/s]
 89%|████████▉ | 51192/57600 [9:00:57<1:05:44,  1.62it/s]
 89%|████████▉ | 51193/57600 [9:00:57<1:05:59,  1.62it/s]
 89%|████████▉ | 51194/57600 [9:00:58<1:08:19,  1.56it/s]
 89%|████████▉ | 51195/57600 [9:00:59<1:08:11,  1.57it/s]
 89%|████████▉ | 51196/57600 [9:00:59<1:06:51,  1.60it/s]
 89%|████████▉ | 51197/57600 [9:01:00<1:06:17,  1.61it/s]
 89%|████████▉ | 51198/57600 [9:01:01<1:04:22,  1.66it/s]
 89%|████████▉ | 51199/57600 [9:01:01<1:07:39,  1.58it/s]
 89%|████████▉ | 51200/57600 [9:01:02<1:06:32,  1.60it/s]
                                                         
{'loss': 1.1229, 'learning_rate': 2.003484320557491e-07, 'epoch': 565.12}

 89%|████████▉ | 51200/57600 [9:01:02<1:06:32,  1.60it/s]
 89%|████████▉ | 51201/57600 [9:01:03<1:09:07,  1.54it/s]
 89%|████████▉ | 51202/57600 [9:01:03<1:06:14,  1.61it/s]
 89%|████████▉ | 51203/57600 [9:01:04<1:06:00,  1.62it/s]
 89%|████████▉ | 51204/57600 [9:01:04<1:06:34,  1.60it/s]
 89%|████████▉ | 51205/57600 [9:01:05<1:07:17,  1.58it/s]
 89%|████████▉ | 51206/57600 [9:01:06<1:06:23,  1.60it/s]
 89%|████████▉ | 51207/57600 [9:01:06<1:05:38,  1.62it/s]
 89%|████████▉ | 51208/57600 [9:01:07<1:04:33,  1.65it/s]
 89%|████████▉ | 51209/57600 [9:01:07<1:04:37,  1.65it/s]
 89%|████████▉ | 51210/57600 [9:01:08<1:04:54,  1.64it/s]
 89%|████████▉ | 51211/57600 [9:01:09<1:04:48,  1.64it/s]
 89%|████████▉ | 51212/57600 [9:01:09<1:05:45,  1.62it/s]
 89%|████████▉ | 51213/57600 [9:01:10<1:05:43,  1.62it/s]
 89%|████████▉ | 51214/57600 [9:01:11<1:05:52,  1.62it/s]
 89%|████████▉ | 51215/57600 [9:01:11<1:05:49,  1.62it/s]
 89%|████████▉ | 51216/57600 [9:01:12<1:09:07,  1.54it/s]
 89%|████████▉ | 51217/57600 [9:01:12<1:07:01,  1.59it/s]
 89%|████████▉ | 51218/57600 [9:01:13<1:06:33,  1.60it/s]
 89%|████████▉ | 51219/57600 [9:01:14<1:06:14,  1.61it/s]
 89%|████████▉ | 51220/57600 [9:01:14<1:07:20,  1.58it/s]
                                                         
{'loss': 1.1013, 'learning_rate': 2.0003484320557494e-07, 'epoch': 565.34}

 89%|████████▉ | 51220/57600 [9:01:14<1:07:20,  1.58it/s]
 89%|████████▉ | 51221/57600 [9:01:15<1:04:41,  1.64it/s]
 89%|████████▉ | 51222/57600 [9:01:16<1:05:24,  1.63it/s]
 89%|████████▉ | 51223/57600 [9:01:16<1:06:04,  1.61it/s]
 89%|████████▉ | 51224/57600 [9:01:17<1:04:07,  1.66it/s]
 89%|████████▉ | 51225/57600 [9:01:17<1:04:20,  1.65it/s]
 89%|████████▉ | 51226/57600 [9:01:18<1:04:01,  1.66it/s]
 89%|████████▉ | 51227/57600 [9:01:19<1:04:20,  1.65it/s]
 89%|████████▉ | 51228/57600 [9:01:19<1:05:46,  1.61it/s]
 89%|████████▉ | 51229/57600 [9:01:20<1:07:22,  1.58it/s]
 89%|████████▉ | 51230/57600 [9:01:21<1:08:22,  1.55it/s]
 89%|████████▉ | 51231/57600 [9:01:21<1:07:54,  1.56it/s]
 89%|████████▉ | 51232/57600 [9:01:22<1:07:44,  1.57it/s]
 89%|████████▉ | 51233/57600 [9:01:23<1:11:55,  1.48it/s]
 89%|████████▉ | 51234/57600 [9:01:23<1:10:14,  1.51it/s]
 89%|████████▉ | 51235/57600 [9:01:24<1:09:37,  1.52it/s]
 89%|████████▉ | 51236/57600 [9:01:24<1:08:00,  1.56it/s]
 89%|████████▉ | 51237/57600 [9:01:25<1:05:34,  1.62it/s]
 89%|████████▉ | 51238/57600 [9:01:26<1:04:58,  1.63it/s]
 89%|████████▉ | 51239/57600 [9:01:26<1:04:57,  1.63it/s]
 89%|████████▉ | 51240/57600 [9:01:27<1:06:48,  1.59it/s]
                                                         
{'loss': 1.0951, 'learning_rate': 1.9972125435540067e-07, 'epoch': 565.56}

 89%|████████▉ | 51240/57600 [9:01:27<1:06:48,  1.59it/s]
 89%|████████▉ | 51241/57600 [9:01:27<1:05:24,  1.62it/s]
 89%|████████▉ | 51242/57600 [9:01:28<1:06:52,  1.58it/s]
 89%|████████▉ | 51243/57600 [9:01:29<1:05:41,  1.61it/s]
 89%|████████▉ | 51244/57600 [9:01:29<1:06:11,  1.60it/s]
 89%|████████▉ | 51245/57600 [9:01:30<1:05:40,  1.61it/s]
 89%|████████▉ | 51246/57600 [9:01:31<1:05:51,  1.61it/s]
 89%|████████▉ | 51247/57600 [9:01:31<1:05:18,  1.62it/s]
 89%|████████▉ | 51248/57600 [9:01:32<1:04:11,  1.65it/s]
 89%|████████▉ | 51249/57600 [9:01:32<1:03:52,  1.66it/s]
 89%|████████▉ | 51250/57600 [9:01:33<1:02:54,  1.68it/s]
 89%|████████▉ | 51251/57600 [9:01:34<1:03:48,  1.66it/s]
 89%|████████▉ | 51252/57600 [9:01:34<1:03:56,  1.65it/s]
 89%|████████▉ | 51253/57600 [9:01:35<1:03:42,  1.66it/s]
 89%|████████▉ | 51254/57600 [9:01:35<1:03:55,  1.65it/s]
 89%|████████▉ | 51255/57600 [9:01:36<1:06:45,  1.58it/s]
 89%|████████▉ | 51256/57600 [9:01:37<1:07:27,  1.57it/s]
 89%|████████▉ | 51257/57600 [9:01:37<1:05:55,  1.60it/s]
 89%|████████▉ | 51258/57600 [9:01:38<1:04:22,  1.64it/s]
 89%|████████▉ | 51259/57600 [9:01:39<1:04:54,  1.63it/s]
 89%|████████▉ | 51260/57600 [9:01:39<1:06:41,  1.58it/s]
                                                         
{'loss': 1.1083, 'learning_rate': 1.9940766550522647e-07, 'epoch': 565.78}

 89%|████████▉ | 51260/57600 [9:01:39<1:06:41,  1.58it/s]
 89%|████████▉ | 51261/57600 [9:01:40<1:06:35,  1.59it/s]
 89%|████████▉ | 51262/57600 [9:01:40<1:05:04,  1.62it/s]
 89%|████████▉ | 51263/57600 [9:01:41<1:03:37,  1.66it/s]
 89%|████████▉ | 51264/57600 [9:01:42<1:05:20,  1.62it/s]
 89%|████████▉ | 51265/57600 [9:01:42<1:05:01,  1.62it/s]
 89%|████████▉ | 51266/57600 [9:01:43<1:04:00,  1.65it/s]
 89%|████████▉ | 51267/57600 [9:01:43<1:02:41,  1.68it/s]
 89%|████████▉ | 51268/57600 [9:01:44<1:02:34,  1.69it/s]
 89%|████████▉ | 51269/57600 [9:01:45<1:03:04,  1.67it/s]
 89%|████████▉ | 51270/57600 [9:01:45<1:02:05,  1.70it/s]
 89%|████████▉ | 51271/57600 [9:01:46<1:01:10,  1.72it/s]
 89%|████████▉ | 51272/57600 [9:01:46<1:01:32,  1.71it/s]
 89%|████████▉ | 51273/57600 [9:01:47<1:03:44,  1.65it/s]
 89%|████████▉ | 51274/57600 [9:01:48<1:04:13,  1.64it/s]
 89%|████████▉ | 51275/57600 [9:01:48<1:05:37,  1.61it/s]
 89%|████████▉ | 51276/57600 [9:01:49<1:05:38,  1.61it/s]
 89%|████████▉ | 51277/57600 [9:01:50<1:06:37,  1.58it/s]
 89%|████████▉ | 51278/57600 [9:01:50<1:08:57,  1.53it/s]
 89%|████████▉ | 51279/57600 [9:01:51<1:09:10,  1.52it/s]
 89%|████████▉ | 51280/57600 [9:01:52<1:11:04,  1.48it/s]
                                                         
{'loss': 1.1329, 'learning_rate': 1.990940766550523e-07, 'epoch': 566.0}

 89%|████████▉ | 51280/57600 [9:01:52<1:11:04,  1.48it/s]
 89%|████████▉ | 51281/57600 [9:01:52<1:10:23,  1.50it/s]
 89%|████████▉ | 51282/57600 [9:01:53<1:08:27,  1.54it/s]
 89%|████████▉ | 51283/57600 [9:01:53<1:07:08,  1.57it/s]
 89%|████████▉ | 51284/57600 [9:01:54<1:05:41,  1.60it/s]
 89%|████████▉ | 51285/57600 [9:01:55<1:05:25,  1.61it/s]
 89%|████████▉ | 51286/57600 [9:01:55<1:03:35,  1.66it/s]
 89%|████████▉ | 51287/57600 [9:01:56<1:02:45,  1.68it/s]
 89%|████████▉ | 51288/57600 [9:01:57<1:07:09,  1.57it/s]
 89%|████████▉ | 51289/57600 [9:01:57<1:05:43,  1.60it/s]
 89%|████████▉ | 51290/57600 [9:01:58<1:06:15,  1.59it/s]
 89%|████████▉ | 51291/57600 [9:01:58<1:05:43,  1.60it/s]
 89%|████████▉ | 51292/57600 [9:01:59<1:05:23,  1.61it/s]
 89%|████████▉ | 51293/57600 [9:02:00<1:07:53,  1.55it/s]
 89%|████████▉ | 51294/57600 [9:02:00<1:07:30,  1.56it/s]
 89%|████████▉ | 51295/57600 [9:02:01<1:06:54,  1.57it/s]
 89%|████████▉ | 51296/57600 [9:02:02<1:05:30,  1.60it/s]
 89%|████████▉ | 51297/57600 [9:02:02<1:06:15,  1.59it/s]
 89%|████████▉ | 51298/57600 [9:02:03<1:07:59,  1.54it/s]
 89%|████████▉ | 51299/57600 [9:02:03<1:04:42,  1.62it/s]
 89%|████████▉ | 51300/57600 [9:02:04<1:04:42,  1.62it/s]
                                                         
{'loss': 1.1128, 'learning_rate': 1.9878048780487803e-07, 'epoch': 566.23}

 89%|████████▉ | 51300/57600 [9:02:04<1:04:42,  1.62it/s]
 89%|████████▉ | 51301/57600 [9:02:05<1:05:08,  1.61it/s]
 89%|████████▉ | 51302/57600 [9:02:05<1:03:37,  1.65it/s]
 89%|████████▉ | 51303/57600 [9:02:06<1:05:05,  1.61it/s]
 89%|████████▉ | 51304/57600 [9:02:06<1:04:02,  1.64it/s]
 89%|████████▉ | 51305/57600 [9:02:07<1:04:44,  1.62it/s]
 89%|████████▉ | 51306/57600 [9:02:08<1:04:58,  1.61it/s]
 89%|████████▉ | 51307/57600 [9:02:08<1:05:53,  1.59it/s]
 89%|████████▉ | 51308/57600 [9:02:09<1:05:26,  1.60it/s]
 89%|████████▉ | 51309/57600 [9:02:10<1:04:46,  1.62it/s]
 89%|████████▉ | 51310/57600 [9:02:10<1:04:55,  1.61it/s]
 89%|████████▉ | 51311/57600 [9:02:11<1:03:05,  1.66it/s]
 89%|████████▉ | 51312/57600 [9:02:11<1:02:56,  1.67it/s]
 89%|████████▉ | 51313/57600 [9:02:12<1:03:48,  1.64it/s]
 89%|████████▉ | 51314/57600 [9:02:13<1:06:10,  1.58it/s]
 89%|████████▉ | 51315/57600 [9:02:13<1:05:21,  1.60it/s]
 89%|████████▉ | 51316/57600 [9:02:14<1:07:01,  1.56it/s]
 89%|████████▉ | 51317/57600 [9:02:15<1:05:25,  1.60it/s]
 89%|████████▉ | 51318/57600 [9:02:15<1:04:03,  1.63it/s]
 89%|████████▉ | 51319/57600 [9:02:16<1:03:52,  1.64it/s]
 89%|████████▉ | 51320/57600 [9:02:16<1:03:23,  1.65it/s]
                                                         
{'loss': 1.1237, 'learning_rate': 1.9846689895470386e-07, 'epoch': 566.45}

 89%|████████▉ | 51320/57600 [9:02:16<1:03:23,  1.65it/s]
 89%|████████▉ | 51321/57600 [9:02:17<1:03:38,  1.64it/s]
 89%|████████▉ | 51322/57600 [9:02:18<1:05:24,  1.60it/s]
 89%|████████▉ | 51323/57600 [9:02:18<1:05:26,  1.60it/s]
 89%|████████▉ | 51324/57600 [9:02:19<1:07:19,  1.55it/s]
 89%|████████▉ | 51325/57600 [9:02:20<1:05:37,  1.59it/s]
 89%|████████▉ | 51326/57600 [9:02:20<1:04:17,  1.63it/s]
 89%|████████▉ | 51327/57600 [9:02:21<1:02:56,  1.66it/s]
 89%|████████▉ | 51328/57600 [9:02:21<1:03:01,  1.66it/s]
 89%|████████▉ | 51329/57600 [9:02:22<1:04:37,  1.62it/s]
 89%|████████▉ | 51330/57600 [9:02:23<1:04:55,  1.61it/s]
 89%|████████▉ | 51331/57600 [9:02:23<1:04:51,  1.61it/s]
 89%|████████▉ | 51332/57600 [9:02:24<1:04:28,  1.62it/s]
 89%|████████▉ | 51333/57600 [9:02:24<1:02:32,  1.67it/s]
 89%|████████▉ | 51334/57600 [9:02:25<1:02:57,  1.66it/s]
 89%|████████▉ | 51335/57600 [9:02:26<1:03:54,  1.63it/s]
 89%|████████▉ | 51336/57600 [9:02:26<1:05:47,  1.59it/s]
 89%|████████▉ | 51337/57600 [9:02:27<1:07:32,  1.55it/s]
 89%|████████▉ | 51338/57600 [9:02:28<1:07:32,  1.55it/s]
 89%|████████▉ | 51339/57600 [9:02:28<1:05:26,  1.59it/s]
 89%|████████▉ | 51340/57600 [9:02:29<1:04:33,  1.62it/s]
                                                         
{'loss': 1.1021, 'learning_rate': 1.981533101045296e-07, 'epoch': 566.67}

 89%|████████▉ | 51340/57600 [9:02:29<1:04:33,  1.62it/s]
 89%|████████▉ | 51341/57600 [9:02:29<1:04:25,  1.62it/s]
 89%|████████▉ | 51342/57600 [9:02:30<1:04:39,  1.61it/s]
 89%|████████▉ | 51343/57600 [9:02:31<1:03:40,  1.64it/s]
 89%|████████▉ | 51344/57600 [9:02:31<1:02:32,  1.67it/s]
 89%|████████▉ | 51345/57600 [9:02:32<1:01:51,  1.69it/s]
 89%|████████▉ | 51346/57600 [9:02:32<1:02:19,  1.67it/s]
 89%|████████▉ | 51347/57600 [9:02:33<1:03:42,  1.64it/s]
 89%|████████▉ | 51348/57600 [9:02:34<1:04:54,  1.61it/s]
 89%|████████▉ | 51349/57600 [9:02:34<1:05:27,  1.59it/s]
 89%|████████▉ | 51350/57600 [9:02:35<1:03:50,  1.63it/s]
 89%|████████▉ | 51351/57600 [9:02:36<1:05:24,  1.59it/s]
 89%|████████▉ | 51352/57600 [9:02:36<1:03:42,  1.63it/s]
 89%|████████▉ | 51353/57600 [9:02:37<1:03:17,  1.65it/s]
 89%|████████▉ | 51354/57600 [9:02:37<1:03:30,  1.64it/s]
 89%|████████▉ | 51355/57600 [9:02:38<1:03:49,  1.63it/s]
 89%|████████▉ | 51356/57600 [9:02:39<1:02:50,  1.66it/s]
 89%|████████▉ | 51357/57600 [9:02:39<1:06:18,  1.57it/s]
 89%|████████▉ | 51358/57600 [9:02:40<1:05:20,  1.59it/s]
 89%|████████▉ | 51359/57600 [9:02:41<1:04:50,  1.60it/s]
 89%|████████▉ | 51360/57600 [9:02:41<1:03:45,  1.63it/s]
                                                         
{'loss': 1.1348, 'learning_rate': 1.978397212543554e-07, 'epoch': 566.89}

 89%|████████▉ | 51360/57600 [9:02:41<1:03:45,  1.63it/s]
 89%|████████▉ | 51361/57600 [9:02:42<1:05:10,  1.60it/s]
 89%|████████▉ | 51362/57600 [9:02:42<1:04:04,  1.62it/s]
 89%|████████▉ | 51363/57600 [9:02:43<1:02:35,  1.66it/s]
 89%|████████▉ | 51364/57600 [9:02:43<1:01:57,  1.68it/s]
 89%|████████▉ | 51365/57600 [9:02:44<1:03:36,  1.63it/s]
 89%|████████▉ | 51366/57600 [9:02:45<1:02:47,  1.65it/s]
 89%|████████▉ | 51367/57600 [9:02:45<1:03:41,  1.63it/s]
 89%|████████▉ | 51368/57600 [9:02:46<1:04:47,  1.60it/s]
 89%|████████▉ | 51369/57600 [9:02:47<1:04:07,  1.62it/s]
 89%|████████▉ | 51370/57600 [9:02:47<1:06:19,  1.57it/s]
 89%|████████▉ | 51371/57600 [9:02:48<1:07:55,  1.53it/s]
 89%|████████▉ | 51372/57600 [9:02:49<1:05:36,  1.58it/s]
 89%|████████▉ | 51373/57600 [9:02:49<1:03:33,  1.63it/s]
 89%|████████▉ | 51374/57600 [9:02:50<1:03:51,  1.62it/s]
 89%|████████▉ | 51375/57600 [9:02:50<1:05:33,  1.58it/s]
 89%|████████▉ | 51376/57600 [9:02:51<1:04:58,  1.60it/s]
 89%|████████▉ | 51377/57600 [9:02:52<1:05:12,  1.59it/s]
 89%|████████▉ | 51378/57600 [9:02:52<1:06:34,  1.56it/s]
 89%|████████▉ | 51379/57600 [9:02:53<1:05:08,  1.59it/s]
 89%|████████▉ | 51380/57600 [9:02:54<1:06:12,  1.57it/s]
                                                         
{'loss': 1.0934, 'learning_rate': 1.9752613240418114e-07, 'epoch': 567.11}

 89%|████████▉ | 51380/57600 [9:02:54<1:06:12,  1.57it/s]
 89%|████████▉ | 51381/57600 [9:02:54<1:05:57,  1.57it/s]
 89%|████████▉ | 51382/57600 [9:02:55<1:05:21,  1.59it/s]
 89%|████████▉ | 51383/57600 [9:02:55<1:04:17,  1.61it/s]
 89%|████████▉ | 51384/57600 [9:02:56<1:06:30,  1.56it/s]
 89%|████████▉ | 51385/57600 [9:02:57<1:04:37,  1.60it/s]
 89%|████████▉ | 51386/57600 [9:02:57<1:04:41,  1.60it/s]
 89%|████████▉ | 51387/57600 [9:02:58<1:04:49,  1.60it/s]
 89%|████████▉ | 51388/57600 [9:02:59<1:04:41,  1.60it/s]
 89%|████████▉ | 51389/57600 [9:02:59<1:03:09,  1.64it/s]
 89%|████████▉ | 51390/57600 [9:03:00<1:07:01,  1.54it/s]
 89%|████████▉ | 51391/57600 [9:03:01<1:05:59,  1.57it/s]
 89%|████████▉ | 51392/57600 [9:03:01<1:05:34,  1.58it/s]
 89%|████████▉ | 51393/57600 [9:03:02<1:05:42,  1.57it/s]
 89%|████████▉ | 51394/57600 [9:03:02<1:04:19,  1.61it/s]
 89%|████████▉ | 51395/57600 [9:03:03<1:03:02,  1.64it/s]
 89%|████████▉ | 51396/57600 [9:03:04<1:04:43,  1.60it/s]
 89%|████████▉ | 51397/57600 [9:03:04<1:05:00,  1.59it/s]
 89%|████████▉ | 51398/57600 [9:03:05<1:07:41,  1.53it/s]
 89%|████████▉ | 51399/57600 [9:03:06<1:07:03,  1.54it/s]
 89%|████████▉ | 51400/57600 [9:03:06<1:05:53,  1.57it/s]
                                                         
{'loss': 1.1146, 'learning_rate': 1.9721254355400695e-07, 'epoch': 567.33}

 89%|████████▉ | 51400/57600 [9:03:06<1:05:53,  1.57it/s]
 89%|████████▉ | 51401/57600 [9:03:07<1:06:13,  1.56it/s]
 89%|████████▉ | 51402/57600 [9:03:07<1:05:26,  1.58it/s]
 89%|████████▉ | 51403/57600 [9:03:08<1:04:24,  1.60it/s]
 89%|████████▉ | 51404/57600 [9:03:09<1:03:00,  1.64it/s]
 89%|████████▉ | 51405/57600 [9:03:09<1:02:28,  1.65it/s]
 89%|████████▉ | 51406/57600 [9:03:10<1:00:31,  1.71it/s]
 89%|████████▉ | 51407/57600 [9:03:10<1:03:31,  1.62it/s]
 89%|████████▉ | 51408/57600 [9:03:11<1:03:39,  1.62it/s]
 89%|████████▉ | 51409/57600 [9:03:12<1:01:50,  1.67it/s]
 89%|████████▉ | 51410/57600 [9:03:12<1:01:52,  1.67it/s]
 89%|████████▉ | 51411/57600 [9:03:13<1:00:41,  1.70it/s]
 89%|████████▉ | 51412/57600 [9:03:13<1:01:51,  1.67it/s]
 89%|████████▉ | 51413/57600 [9:03:14<1:01:32,  1.68it/s]
 89%|████████▉ | 51414/57600 [9:03:15<1:01:05,  1.69it/s]
 89%|████████▉ | 51415/57600 [9:03:15<1:00:49,  1.69it/s]
 89%|████████▉ | 51416/57600 [9:03:16<1:00:45,  1.70it/s]
 89%|████████▉ | 51417/57600 [9:03:16<1:02:12,  1.66it/s]
 89%|████████▉ | 51418/57600 [9:03:17<1:02:57,  1.64it/s]
 89%|████████▉ | 51419/57600 [9:03:18<1:03:02,  1.63it/s]
 89%|████████▉ | 51420/57600 [9:03:18<1:06:28,  1.55it/s]
                                                         
{'loss': 1.1459, 'learning_rate': 1.968989547038328e-07, 'epoch': 567.55}

 89%|████████▉ | 51420/57600 [9:03:18<1:06:28,  1.55it/s]
 89%|████████▉ | 51421/57600 [9:03:19<1:06:05,  1.56it/s]
 89%|████████▉ | 51422/57600 [9:03:20<1:03:11,  1.63it/s]
 89%|████████▉ | 51423/57600 [9:03:20<1:02:35,  1.64it/s]
 89%|████████▉ | 51424/57600 [9:03:21<1:02:02,  1.66it/s]
 89%|████████▉ | 51425/57600 [9:03:21<1:01:15,  1.68it/s]
 89%|████████▉ | 51426/57600 [9:03:22<1:01:16,  1.68it/s]
 89%|████████▉ | 51427/57600 [9:03:23<1:02:34,  1.64it/s]
 89%|████████▉ | 51428/57600 [9:03:23<1:03:19,  1.62it/s]
 89%|████████▉ | 51429/57600 [9:03:24<1:04:31,  1.59it/s]
 89%|████████▉ | 51430/57600 [9:03:24<1:04:19,  1.60it/s]
 89%|████████▉ | 51431/57600 [9:03:25<1:06:10,  1.55it/s]
 89%|████████▉ | 51432/57600 [9:03:26<1:04:32,  1.59it/s]
 89%|████████▉ | 51433/57600 [9:03:26<1:04:10,  1.60it/s]
 89%|████████▉ | 51434/57600 [9:03:27<1:03:29,  1.62it/s]
 89%|████████▉ | 51435/57600 [9:03:28<1:03:14,  1.62it/s]
 89%|████████▉ | 51436/57600 [9:03:28<1:01:39,  1.67it/s]
 89%|████████▉ | 51437/57600 [9:03:29<1:03:24,  1.62it/s]
 89%|████████▉ | 51438/57600 [9:03:29<1:03:36,  1.61it/s]
 89%|████████▉ | 51439/57600 [9:03:30<1:07:15,  1.53it/s]
 89%|████████▉ | 51440/57600 [9:03:31<1:10:55,  1.45it/s]
                                                         
{'loss': 1.0666, 'learning_rate': 1.965853658536585e-07, 'epoch': 567.77}

 89%|████████▉ | 51440/57600 [9:03:31<1:10:55,  1.45it/s]
 89%|████████▉ | 51441/57600 [9:03:32<1:08:19,  1.50it/s]
 89%|████████▉ | 51442/57600 [9:03:32<1:05:53,  1.56it/s]
 89%|████████▉ | 51443/57600 [9:03:33<1:03:53,  1.61it/s]
 89%|████████▉ | 51444/57600 [9:03:33<1:03:16,  1.62it/s]
 89%|████████▉ | 51445/57600 [9:03:34<1:04:16,  1.60it/s]
 89%|████████▉ | 51446/57600 [9:03:35<1:04:04,  1.60it/s]
 89%|████████▉ | 51447/57600 [9:03:35<1:04:24,  1.59it/s]
 89%|████████▉ | 51448/57600 [9:03:36<1:05:25,  1.57it/s]
 89%|████████▉ | 51449/57600 [9:03:37<1:08:34,  1.49it/s]
 89%|████████▉ | 51450/57600 [9:03:37<1:07:36,  1.52it/s]
 89%|████████▉ | 51451/57600 [9:03:38<1:07:02,  1.53it/s]
 89%|████████▉ | 51452/57600 [9:03:39<1:06:16,  1.55it/s]
 89%|████████▉ | 51453/57600 [9:03:39<1:04:18,  1.59it/s]
 89%|████████▉ | 51454/57600 [9:03:40<1:03:27,  1.61it/s]
 89%|████████▉ | 51455/57600 [9:03:40<1:02:00,  1.65it/s]
 89%|████████▉ | 51456/57600 [9:03:41<1:02:55,  1.63it/s]
 89%|████████▉ | 51457/57600 [9:03:41<1:00:55,  1.68it/s]
 89%|████████▉ | 51458/57600 [9:03:42<1:02:25,  1.64it/s]
 89%|████████▉ | 51459/57600 [9:03:43<1:04:11,  1.59it/s]
 89%|████████▉ | 51460/57600 [9:03:43<1:04:27,  1.59it/s]
                                                         
{'loss': 1.1011, 'learning_rate': 1.9627177700348436e-07, 'epoch': 567.99}

 89%|████████▉ | 51460/57600 [9:03:43<1:04:27,  1.59it/s]
 89%|████████▉ | 51461/57600 [9:03:44<1:06:22,  1.54it/s]
 89%|████████▉ | 51462/57600 [9:03:45<1:05:09,  1.57it/s]
 89%|████████▉ | 51463/57600 [9:03:45<1:06:05,  1.55it/s]
 89%|████████▉ | 51464/57600 [9:03:46<1:04:44,  1.58it/s]
 89%|████████▉ | 51465/57600 [9:03:47<1:06:31,  1.54it/s]
 89%|████████▉ | 51466/57600 [9:03:47<1:05:47,  1.55it/s]
 89%|████████▉ | 51467/57600 [9:03:48<1:05:13,  1.57it/s]
 89%|████████▉ | 51468/57600 [9:03:49<1:08:18,  1.50it/s]
 89%|████████▉ | 51469/57600 [9:03:49<1:06:12,  1.54it/s]
 89%|████████▉ | 51470/57600 [9:03:50<1:06:03,  1.55it/s]
 89%|████████▉ | 51471/57600 [9:03:51<1:04:33,  1.58it/s]
 89%|████████▉ | 51472/57600 [9:03:51<1:03:38,  1.60it/s]
 89%|████████▉ | 51473/57600 [9:03:52<1:02:04,  1.64it/s]
 89%|████████▉ | 51474/57600 [9:03:52<1:02:20,  1.64it/s]
 89%|████████▉ | 51475/57600 [9:03:53<1:04:11,  1.59it/s]
 89%|████████▉ | 51476/57600 [9:03:54<1:03:08,  1.62it/s]
 89%|████████▉ | 51477/57600 [9:03:54<1:03:00,  1.62it/s]
 89%|████████▉ | 51478/57600 [9:03:55<1:00:41,  1.68it/s]
 89%|████████▉ | 51479/57600 [9:03:55<1:00:01,  1.70it/s]
 89%|████████▉ | 51480/57600 [9:03:56<59:51,  1.70it/s]  
                                                       
{'loss': 1.103, 'learning_rate': 1.9595818815331006e-07, 'epoch': 568.21}

 89%|████████▉ | 51480/57600 [9:03:56<59:51,  1.70it/s]
 89%|████████▉ | 51481/57600 [9:03:57<1:00:11,  1.69it/s]
 89%|████████▉ | 51482/57600 [9:03:57<1:03:30,  1.61it/s]
 89%|████████▉ | 51483/57600 [9:03:58<1:04:46,  1.57it/s]
 89%|████████▉ | 51484/57600 [9:03:59<1:06:07,  1.54it/s]
 89%|████████▉ | 51485/57600 [9:03:59<1:06:09,  1.54it/s]
 89%|████████▉ | 51486/57600 [9:04:00<1:04:38,  1.58it/s]
 89%|████████▉ | 51487/57600 [9:04:00<1:04:11,  1.59it/s]
 89%|████████▉ | 51488/57600 [9:04:01<1:04:02,  1.59it/s]
 89%|████████▉ | 51489/57600 [9:04:02<1:01:57,  1.64it/s]
 89%|████████▉ | 51490/57600 [9:04:02<1:02:12,  1.64it/s]
 89%|████████▉ | 51491/57600 [9:04:03<1:01:35,  1.65it/s]
 89%|████████▉ | 51492/57600 [9:04:03<1:03:09,  1.61it/s]
 89%|████████▉ | 51493/57600 [9:04:04<1:00:56,  1.67it/s]
 89%|████████▉ | 51494/57600 [9:04:05<1:04:03,  1.59it/s]
 89%|████████▉ | 51495/57600 [9:04:05<1:01:57,  1.64it/s]
 89%|████████▉ | 51496/57600 [9:04:06<1:01:18,  1.66it/s]
 89%|████████▉ | 51497/57600 [9:04:07<1:02:46,  1.62it/s]
 89%|████████▉ | 51498/57600 [9:04:07<1:02:10,  1.64it/s]
 89%|████████▉ | 51499/57600 [9:04:08<1:03:42,  1.60it/s]
 89%|████████▉ | 51500/57600 [9:04:08<1:04:11,  1.58it/s]
                                                         
{'loss': 1.0595, 'learning_rate': 1.956445993031359e-07, 'epoch': 568.43}

 89%|████████▉ | 51500/57600 [9:04:08<1:04:11,  1.58it/s]
 89%|████████▉ | 51501/57600 [9:04:09<1:03:29,  1.60it/s]
 89%|████████▉ | 51502/57600 [9:04:10<1:03:20,  1.60it/s]
 89%|████████▉ | 51503/57600 [9:04:10<1:01:35,  1.65it/s]
 89%|████████▉ | 51504/57600 [9:04:11<1:02:50,  1.62it/s]
 89%|████████▉ | 51505/57600 [9:04:11<1:02:08,  1.63it/s]
 89%|████████▉ | 51506/57600 [9:04:12<1:01:00,  1.66it/s]
 89%|████████▉ | 51507/57600 [9:04:13<1:01:58,  1.64it/s]
 89%|████████▉ | 51508/57600 [9:04:13<1:02:11,  1.63it/s]
 89%|████████▉ | 51509/57600 [9:04:14<1:00:04,  1.69it/s]
 89%|████████▉ | 51510/57600 [9:04:14<1:00:32,  1.68it/s]
 89%|████████▉ | 51511/57600 [9:04:15<1:02:05,  1.63it/s]
 89%|████████▉ | 51512/57600 [9:04:16<1:01:23,  1.65it/s]
 89%|████████▉ | 51513/57600 [9:04:16<1:04:14,  1.58it/s]
 89%|████████▉ | 51514/57600 [9:04:17<1:05:40,  1.54it/s]
 89%|████████▉ | 51515/57600 [9:04:18<1:03:35,  1.59it/s]
 89%|████████▉ | 51516/57600 [9:04:18<1:03:36,  1.59it/s]
 89%|████████▉ | 51517/57600 [9:04:19<1:01:42,  1.64it/s]
 89%|████████▉ | 51518/57600 [9:04:19<1:03:32,  1.60it/s]
 89%|████████▉ | 51519/57600 [9:04:20<1:02:22,  1.62it/s]
 89%|████████▉ | 51520/57600 [9:04:21<1:03:47,  1.59it/s]
                                                         
{'loss': 1.1129, 'learning_rate': 1.9533101045296162e-07, 'epoch': 568.65}

 89%|████████▉ | 51520/57600 [9:04:21<1:03:47,  1.59it/s]
 89%|████████▉ | 51521/57600 [9:04:21<1:02:54,  1.61it/s]
 89%|████████▉ | 51522/57600 [9:04:22<1:02:20,  1.62it/s]
 89%|████████▉ | 51523/57600 [9:04:23<1:02:45,  1.61it/s]
 89%|████████▉ | 51524/57600 [9:04:23<1:04:04,  1.58it/s]
 89%|████████▉ | 51525/57600 [9:04:24<1:03:51,  1.59it/s]
 89%|████████▉ | 51526/57600 [9:04:24<1:03:46,  1.59it/s]
 89%|████████▉ | 51527/57600 [9:04:25<1:04:16,  1.57it/s]
 89%|████████▉ | 51528/57600 [9:04:26<1:02:59,  1.61it/s]
 89%|████████▉ | 51529/57600 [9:04:26<1:02:11,  1.63it/s]
 89%|████████▉ | 51530/57600 [9:04:27<1:01:35,  1.64it/s]
 89%|████████▉ | 51531/57600 [9:04:28<1:02:22,  1.62it/s]
 89%|████████▉ | 51532/57600 [9:04:28<1:03:16,  1.60it/s]
 89%|████████▉ | 51533/57600 [9:04:29<1:02:49,  1.61it/s]
 89%|████████▉ | 51534/57600 [9:04:29<1:02:14,  1.62it/s]
 89%|████████▉ | 51535/57600 [9:04:30<1:01:51,  1.63it/s]
 89%|████████▉ | 51536/57600 [9:04:31<1:03:33,  1.59it/s]
 89%|████████▉ | 51537/57600 [9:04:31<1:03:32,  1.59it/s]
 89%|████████▉ | 51538/57600 [9:04:32<1:02:51,  1.61it/s]
 89%|████████▉ | 51539/57600 [9:04:33<1:01:26,  1.64it/s]
 89%|████████▉ | 51540/57600 [9:04:33<1:00:26,  1.67it/s]
                                                         
{'loss': 1.1028, 'learning_rate': 1.9501742160278745e-07, 'epoch': 568.87}

 89%|████████▉ | 51540/57600 [9:04:33<1:00:26,  1.67it/s]
 89%|████████▉ | 51541/57600 [9:04:34<1:02:12,  1.62it/s]
 89%|████████▉ | 51542/57600 [9:04:34<1:01:27,  1.64it/s]
 89%|████████▉ | 51543/57600 [9:04:35<1:02:24,  1.62it/s]
 89%|████████▉ | 51544/57600 [9:04:36<1:04:00,  1.58it/s]
 89%|████████▉ | 51545/57600 [9:04:36<1:04:33,  1.56it/s]
 89%|████████▉ | 51546/57600 [9:04:37<1:03:33,  1.59it/s]
 89%|████████▉ | 51547/57600 [9:04:38<1:03:48,  1.58it/s]
 89%|████████▉ | 51548/57600 [9:04:38<1:03:40,  1.58it/s]
 89%|████████▉ | 51549/57600 [9:04:39<1:02:35,  1.61it/s]
 89%|████████▉ | 51550/57600 [9:04:39<1:03:51,  1.58it/s]
 89%|████████▉ | 51551/57600 [9:04:40<1:03:52,  1.58it/s]
 90%|████████▉ | 51552/57600 [9:04:41<1:04:47,  1.56it/s]
 90%|████████▉ | 51553/57600 [9:04:41<1:03:43,  1.58it/s]
 90%|████████▉ | 51554/57600 [9:04:42<1:01:35,  1.64it/s]
 90%|████████▉ | 51555/57600 [9:04:43<1:02:04,  1.62it/s]
 90%|████████▉ | 51556/57600 [9:04:43<1:04:22,  1.56it/s]
 90%|████████▉ | 51557/57600 [9:04:44<1:04:22,  1.56it/s]
 90%|████████▉ | 51558/57600 [9:04:44<1:01:50,  1.63it/s]
 90%|████████▉ | 51559/57600 [9:04:45<1:01:02,  1.65it/s]
 90%|████████▉ | 51560/57600 [9:04:46<1:04:54,  1.55it/s]
                                                         
{'loss': 1.0938, 'learning_rate': 1.9470383275261328e-07, 'epoch': 569.09}

 90%|████████▉ | 51560/57600 [9:04:46<1:04:54,  1.55it/s]
 90%|████████▉ | 51561/57600 [9:04:46<1:02:48,  1.60it/s]
 90%|████████▉ | 51562/57600 [9:04:47<1:00:50,  1.65it/s]
 90%|████████▉ | 51563/57600 [9:04:47<1:00:09,  1.67it/s]
 90%|████████▉ | 51564/57600 [9:04:48<1:00:28,  1.66it/s]
 90%|████████▉ | 51565/57600 [9:04:49<1:00:00,  1.68it/s]
 90%|████████▉ | 51566/57600 [9:04:49<1:01:05,  1.65it/s]
 90%|████████▉ | 51567/57600 [9:04:50<1:02:15,  1.62it/s]
 90%|████████▉ | 51568/57600 [9:04:51<1:01:29,  1.64it/s]
 90%|████████▉ | 51569/57600 [9:04:51<59:41,  1.68it/s]  
 90%|████████▉ | 51570/57600 [9:04:52<1:02:02,  1.62it/s]
 90%|████████▉ | 51571/57600 [9:04:52<1:02:12,  1.62it/s]
 90%|████████▉ | 51572/57600 [9:04:53<1:02:19,  1.61it/s]
 90%|████████▉ | 51573/57600 [9:04:54<1:01:28,  1.63it/s]
 90%|████████▉ | 51574/57600 [9:04:54<1:03:31,  1.58it/s]
 90%|████████▉ | 51575/57600 [9:04:55<1:05:04,  1.54it/s]
 90%|████████▉ | 51576/57600 [9:04:56<1:03:59,  1.57it/s]
 90%|████████▉ | 51577/57600 [9:04:56<1:03:41,  1.58it/s]
 90%|████████▉ | 51578/57600 [9:04:57<1:02:44,  1.60it/s]
 90%|████████▉ | 51579/57600 [9:04:57<1:03:24,  1.58it/s]
 90%|████████▉ | 51580/57600 [9:04:58<1:03:01,  1.59it/s]
                                                         
{'loss': 1.1198, 'learning_rate': 1.94390243902439e-07, 'epoch': 569.32}

 90%|████████▉ | 51580/57600 [9:04:58<1:03:01,  1.59it/s]
 90%|████████▉ | 51581/57600 [9:04:59<1:03:28,  1.58it/s]
 90%|████████▉ | 51582/57600 [9:04:59<1:01:55,  1.62it/s]
 90%|████████▉ | 51583/57600 [9:05:00<1:01:02,  1.64it/s]
 90%|████████▉ | 51584/57600 [9:05:00<1:01:16,  1.64it/s]
 90%|████████▉ | 51585/57600 [9:05:01<1:01:20,  1.63it/s]
 90%|████████▉ | 51586/57600 [9:05:02<1:01:57,  1.62it/s]
 90%|████████▉ | 51587/57600 [9:05:02<1:02:28,  1.60it/s]
 90%|████████▉ | 51588/57600 [9:05:03<1:02:32,  1.60it/s]
 90%|████████▉ | 51589/57600 [9:05:04<1:02:08,  1.61it/s]
 90%|████████▉ | 51590/57600 [9:05:04<1:02:56,  1.59it/s]
 90%|████████▉ | 51591/57600 [9:05:05<1:01:55,  1.62it/s]
 90%|████████▉ | 51592/57600 [9:05:05<1:00:03,  1.67it/s]
 90%|████████▉ | 51593/57600 [9:05:06<1:00:32,  1.65it/s]
 90%|████████▉ | 51594/57600 [9:05:07<1:00:19,  1.66it/s]
 90%|████████▉ | 51595/57600 [9:05:07<1:00:23,  1.66it/s]
 90%|████████▉ | 51596/57600 [9:05:08<1:00:03,  1.67it/s]
 90%|████████▉ | 51597/57600 [9:05:08<1:00:51,  1.64it/s]
 90%|████████▉ | 51598/57600 [9:05:09<59:48,  1.67it/s]  
 90%|████████▉ | 51599/57600 [9:05:10<1:00:48,  1.64it/s]
 90%|████████▉ | 51600/57600 [9:05:10<1:00:24,  1.66it/s]
                                                         
{'loss': 1.1075, 'learning_rate': 1.9407665505226484e-07, 'epoch': 569.54}

 90%|████████▉ | 51600/57600 [9:05:10<1:00:24,  1.66it/s]
 90%|████████▉ | 51601/57600 [9:05:11<59:38,  1.68it/s]  
 90%|████████▉ | 51602/57600 [9:05:12<1:02:44,  1.59it/s]
 90%|████████▉ | 51603/57600 [9:05:12<1:00:48,  1.64it/s]
 90%|████████▉ | 51604/57600 [9:05:13<59:40,  1.67it/s]  
 90%|████████▉ | 51605/57600 [9:05:13<1:00:28,  1.65it/s]
 90%|████████▉ | 51606/57600 [9:05:14<1:03:32,  1.57it/s]
 90%|████████▉ | 51607/57600 [9:05:15<1:00:55,  1.64it/s]
 90%|████████▉ | 51608/57600 [9:05:15<59:21,  1.68it/s]  
 90%|████████▉ | 51609/57600 [9:05:16<57:50,  1.73it/s]
 90%|████████▉ | 51610/57600 [9:05:16<58:56,  1.69it/s]
 90%|████████▉ | 51611/57600 [9:05:17<59:15,  1.68it/s]
 90%|████████▉ | 51612/57600 [9:05:18<1:01:23,  1.63it/s]
 90%|████████▉ | 51613/57600 [9:05:18<1:01:00,  1.64it/s]
 90%|████████▉ | 51614/57600 [9:05:19<1:00:45,  1.64it/s]
 90%|████████▉ | 51615/57600 [9:05:19<1:03:29,  1.57it/s]
 90%|████████▉ | 51616/57600 [9:05:20<1:03:49,  1.56it/s]
 90%|████████▉ | 51617/57600 [9:05:21<1:03:14,  1.58it/s]
 90%|████████▉ | 51618/57600 [9:05:21<1:04:59,  1.53it/s]
 90%|████████▉ | 51619/57600 [9:05:22<1:03:54,  1.56it/s]
 90%|████████▉ | 51620/57600 [9:05:23<1:04:58,  1.53it/s]
                                                         
{'loss': 1.1129, 'learning_rate': 1.9376306620209053e-07, 'epoch': 569.76}

 90%|████████▉ | 51620/57600 [9:05:23<1:04:58,  1.53it/s]
 90%|████████▉ | 51621/57600 [9:05:23<1:04:06,  1.55it/s]
 90%|████████▉ | 51622/57600 [9:05:24<1:03:49,  1.56it/s]
 90%|████████▉ | 51623/57600 [9:05:25<1:02:52,  1.58it/s]
 90%|████████▉ | 51624/57600 [9:05:25<1:03:54,  1.56it/s]
 90%|████████▉ | 51625/57600 [9:05:26<1:02:33,  1.59it/s]
 90%|████████▉ | 51626/57600 [9:05:26<1:01:50,  1.61it/s]
 90%|████████▉ | 51627/57600 [9:05:27<1:03:38,  1.56it/s]
 90%|████████▉ | 51628/57600 [9:05:28<1:02:17,  1.60it/s]
 90%|████████▉ | 51629/57600 [9:05:28<1:02:34,  1.59it/s]
 90%|████████▉ | 51630/57600 [9:05:29<1:03:31,  1.57it/s]
 90%|████████▉ | 51631/57600 [9:05:30<1:03:37,  1.56it/s]
 90%|████████▉ | 51632/57600 [9:05:30<1:04:31,  1.54it/s]
 90%|████████▉ | 51633/57600 [9:05:31<1:04:56,  1.53it/s]
 90%|████████▉ | 51634/57600 [9:05:32<1:05:22,  1.52it/s]
 90%|████████▉ | 51635/57600 [9:05:32<1:04:58,  1.53it/s]
 90%|████████▉ | 51636/57600 [9:05:33<1:03:45,  1.56it/s]
 90%|████████▉ | 51637/57600 [9:05:34<1:03:17,  1.57it/s]
 90%|████████▉ | 51638/57600 [9:05:34<1:03:55,  1.55it/s]
 90%|████████▉ | 51639/57600 [9:05:35<1:03:01,  1.58it/s]
 90%|████████▉ | 51640/57600 [9:05:35<1:02:10,  1.60it/s]
                                                         
{'loss': 1.0949, 'learning_rate': 1.934494773519164e-07, 'epoch': 569.98}

 90%|████████▉ | 51640/57600 [9:05:35<1:02:10,  1.60it/s]
 90%|████████▉ | 51641/57600 [9:05:36<1:01:09,  1.62it/s]
 90%|████████▉ | 51642/57600 [9:05:37<1:00:31,  1.64it/s]
 90%|████████▉ | 51643/57600 [9:05:37<1:03:05,  1.57it/s]
 90%|████████▉ | 51644/57600 [9:05:38<1:01:59,  1.60it/s]
 90%|████████▉ | 51645/57600 [9:05:38<59:55,  1.66it/s]  
 90%|████████▉ | 51646/57600 [9:05:39<1:03:34,  1.56it/s]
 90%|████████▉ | 51647/57600 [9:05:40<1:01:10,  1.62it/s]
 90%|████████▉ | 51648/57600 [9:05:40<1:00:15,  1.65it/s]
 90%|████████▉ | 51649/57600 [9:05:41<1:01:29,  1.61it/s]
 90%|████████▉ | 51650/57600 [9:05:42<1:03:14,  1.57it/s]
 90%|████████▉ | 51651/57600 [9:05:42<1:01:43,  1.61it/s]
 90%|████████▉ | 51652/57600 [9:05:43<1:02:37,  1.58it/s]
 90%|████████▉ | 51653/57600 [9:05:44<1:03:12,  1.57it/s]
 90%|████████▉ | 51654/57600 [9:05:44<1:03:21,  1.56it/s]
 90%|████████▉ | 51655/57600 [9:05:45<1:00:56,  1.63it/s]
 90%|████████▉ | 51656/57600 [9:05:45<59:11,  1.67it/s]  
 90%|████████▉ | 51657/57600 [9:05:46<1:01:31,  1.61it/s]
 90%|████████▉ | 51658/57600 [9:05:47<1:00:28,  1.64it/s]
 90%|████████▉ | 51659/57600 [9:05:47<1:00:32,  1.64it/s]
 90%|████████▉ | 51660/57600 [9:05:48<59:32,  1.66it/s]  
                                                       
{'loss': 1.1028, 'learning_rate': 1.931358885017421e-07, 'epoch': 570.2}

 90%|████████▉ | 51660/57600 [9:05:48<59:32,  1.66it/s]
 90%|████████▉ | 51661/57600 [9:05:48<59:56,  1.65it/s]
 90%|████████▉ | 51662/57600 [9:05:49<58:13,  1.70it/s]
 90%|████████▉ | 51663/57600 [9:05:49<57:09,  1.73it/s]
 90%|████████▉ | 51664/57600 [9:05:50<57:24,  1.72it/s]
 90%|████████▉ | 51665/57600 [9:05:51<57:32,  1.72it/s]
 90%|████████▉ | 51666/57600 [9:05:51<59:52,  1.65it/s]
 90%|████████▉ | 51667/57600 [9:05:52<1:00:45,  1.63it/s]
 90%|████████▉ | 51668/57600 [9:05:53<1:00:47,  1.63it/s]
 90%|████████▉ | 51669/57600 [9:05:53<1:00:25,  1.64it/s]
 90%|████████▉ | 51670/57600 [9:05:54<1:00:53,  1.62it/s]
 90%|████████▉ | 51671/57600 [9:05:54<1:00:54,  1.62it/s]
 90%|████████▉ | 51672/57600 [9:05:55<1:02:57,  1.57it/s]
 90%|████████▉ | 51673/57600 [9:05:56<1:01:43,  1.60it/s]
 90%|████████▉ | 51674/57600 [9:05:56<1:03:04,  1.57it/s]
 90%|████████▉ | 51675/57600 [9:05:57<1:02:28,  1.58it/s]
 90%|████████▉ | 51676/57600 [9:05:58<1:01:58,  1.59it/s]
 90%|████████▉ | 51677/57600 [9:05:58<1:03:47,  1.55it/s]
 90%|████████▉ | 51678/57600 [9:05:59<1:06:39,  1.48it/s]
 90%|████████▉ | 51679/57600 [9:06:00<1:09:23,  1.42it/s]
 90%|████████▉ | 51680/57600 [9:06:00<1:05:33,  1.51it/s]
                                                         
{'loss': 1.1258, 'learning_rate': 1.9282229965156795e-07, 'epoch': 570.42}

 90%|████████▉ | 51680/57600 [9:06:00<1:05:33,  1.51it/s]
 90%|████████▉ | 51681/57600 [9:06:01<1:07:50,  1.45it/s]
 90%|████████▉ | 51682/57600 [9:06:02<1:08:21,  1.44it/s]
 90%|████████▉ | 51683/57600 [9:06:02<1:03:52,  1.54it/s]
 90%|████████▉ | 51684/57600 [9:06:03<1:03:55,  1.54it/s]
 90%|████████▉ | 51685/57600 [9:06:04<1:02:51,  1.57it/s]
 90%|████████▉ | 51686/57600 [9:06:04<1:00:55,  1.62it/s]
 90%|████████▉ | 51687/57600 [9:06:05<59:14,  1.66it/s]  
 90%|████████▉ | 51688/57600 [9:06:05<1:01:02,  1.61it/s]
 90%|████████▉ | 51689/57600 [9:06:06<1:03:14,  1.56it/s]
 90%|████████▉ | 51690/57600 [9:06:07<1:00:39,  1.62it/s]
 90%|████████▉ | 51691/57600 [9:06:07<59:36,  1.65it/s]  
 90%|████████▉ | 51692/57600 [9:06:08<58:48,  1.67it/s]
 90%|████████▉ | 51693/57600 [9:06:08<1:01:05,  1.61it/s]
 90%|████████▉ | 51694/57600 [9:06:09<59:36,  1.65it/s]  
 90%|████████▉ | 51695/57600 [9:06:10<1:00:36,  1.62it/s]
 90%|████████▉ | 51696/57600 [9:06:10<59:42,  1.65it/s]  
 90%|████████▉ | 51697/57600 [9:06:11<59:47,  1.65it/s]
 90%|████████▉ | 51698/57600 [9:06:12<1:00:43,  1.62it/s]
 90%|████████▉ | 51699/57600 [9:06:12<59:25,  1.65it/s]  
 90%|████████▉ | 51700/57600 [9:06:13<1:00:03,  1.64it/s]
                                                         
{'loss': 1.0951, 'learning_rate': 1.9250871080139375e-07, 'epoch': 570.64}

 90%|████████▉ | 51700/57600 [9:06:13<1:00:03,  1.64it/s]
 90%|████████▉ | 51701/57600 [9:06:13<1:01:19,  1.60it/s]
 90%|████████▉ | 51702/57600 [9:06:14<1:01:33,  1.60it/s]
 90%|████████▉ | 51703/57600 [9:06:15<1:02:12,  1.58it/s]
 90%|████████▉ | 51704/57600 [9:06:15<1:01:26,  1.60it/s]
 90%|████████▉ | 51705/57600 [9:06:16<1:01:03,  1.61it/s]
 90%|████████▉ | 51706/57600 [9:06:16<59:49,  1.64it/s]  
 90%|████████▉ | 51707/57600 [9:06:17<59:05,  1.66it/s]
 90%|████████▉ | 51708/57600 [9:06:18<1:01:04,  1.61it/s]
 90%|████████▉ | 51709/57600 [9:06:18<1:01:45,  1.59it/s]
 90%|████████▉ | 51710/57600 [9:06:19<1:01:17,  1.60it/s]
 90%|████████▉ | 51711/57600 [9:06:20<1:00:54,  1.61it/s]
 90%|████████▉ | 51712/57600 [9:06:20<1:02:13,  1.58it/s]
 90%|████████▉ | 51713/57600 [9:06:21<1:02:30,  1.57it/s]
 90%|████████▉ | 51714/57600 [9:06:22<1:02:37,  1.57it/s]
 90%|████████▉ | 51715/57600 [9:06:22<1:02:02,  1.58it/s]
 90%|████████▉ | 51716/57600 [9:06:23<1:01:59,  1.58it/s]
 90%|████████▉ | 51717/57600 [9:06:23<1:00:55,  1.61it/s]
 90%|████████▉ | 51718/57600 [9:06:24<1:00:40,  1.62it/s]
 90%|████████▉ | 51719/57600 [9:06:25<58:36,  1.67it/s]  
 90%|████████▉ | 51720/57600 [9:06:25<58:17,  1.68it/s]
                                                       
{'loss': 1.1116, 'learning_rate': 1.9219512195121948e-07, 'epoch': 570.86}

 90%|████████▉ | 51720/57600 [9:06:25<58:17,  1.68it/s]
 90%|████████▉ | 51721/57600 [9:06:26<57:31,  1.70it/s]
 90%|████████▉ | 51722/57600 [9:06:26<57:36,  1.70it/s]
 90%|████████▉ | 51723/57600 [9:06:27<58:17,  1.68it/s]
 90%|████████▉ | 51724/57600 [9:06:28<59:02,  1.66it/s]
 90%|████████▉ | 51725/57600 [9:06:28<57:41,  1.70it/s]
 90%|████████▉ | 51726/57600 [9:06:29<58:12,  1.68it/s]
 90%|████████▉ | 51727/57600 [9:06:29<58:10,  1.68it/s]
 90%|████████▉ | 51728/57600 [9:06:30<1:00:36,  1.61it/s]
 90%|████████▉ | 51729/57600 [9:06:31<1:00:38,  1.61it/s]
 90%|████████▉ | 51730/57600 [9:06:31<59:07,  1.65it/s]  
 90%|████████▉ | 51731/57600 [9:06:32<58:28,  1.67it/s]
 90%|████████▉ | 51732/57600 [9:06:32<57:09,  1.71it/s]
 90%|████████▉ | 51733/57600 [9:06:33<1:01:35,  1.59it/s]
 90%|████████▉ | 51734/57600 [9:06:34<1:00:22,  1.62it/s]
 90%|████████▉ | 51735/57600 [9:06:34<59:55,  1.63it/s]  
 90%|████████▉ | 51736/57600 [9:06:35<1:00:01,  1.63it/s]
 90%|████████▉ | 51737/57600 [9:06:35<58:14,  1.68it/s]  
 90%|████████▉ | 51738/57600 [9:06:36<57:35,  1.70it/s]
 90%|████████▉ | 51739/57600 [9:06:37<58:58,  1.66it/s]
 90%|████████▉ | 51740/57600 [9:06:37<57:48,  1.69it/s]
                                                       
{'loss': 1.1649, 'learning_rate': 1.918815331010453e-07, 'epoch': 571.08}

 90%|████████▉ | 51740/57600 [9:06:37<57:48,  1.69it/s]
 90%|████████▉ | 51741/57600 [9:06:38<58:47,  1.66it/s]
 90%|████████▉ | 51742/57600 [9:06:38<57:20,  1.70it/s]
 90%|████████▉ | 51743/57600 [9:06:39<1:01:12,  1.60it/s]
 90%|████████▉ | 51744/57600 [9:06:40<1:02:43,  1.56it/s]
 90%|████████▉ | 51745/57600 [9:06:40<1:00:24,  1.62it/s]
 90%|████████▉ | 51746/57600 [9:06:41<58:48,  1.66it/s]  
 90%|████████▉ | 51747/57600 [9:06:41<58:53,  1.66it/s]
 90%|████████▉ | 51748/57600 [9:06:42<1:00:10,  1.62it/s]
 90%|████████▉ | 51749/57600 [9:06:43<1:01:18,  1.59it/s]
 90%|████████▉ | 51750/57600 [9:06:43<1:01:47,  1.58it/s]
 90%|████████▉ | 51751/57600 [9:06:44<1:00:45,  1.60it/s]
 90%|████████▉ | 51752/57600 [9:06:45<1:01:50,  1.58it/s]
 90%|████████▉ | 51753/57600 [9:06:45<1:01:03,  1.60it/s]
 90%|████████▉ | 51754/57600 [9:06:46<1:01:02,  1.60it/s]
 90%|████████▉ | 51755/57600 [9:06:47<1:00:58,  1.60it/s]
 90%|████████▉ | 51756/57600 [9:06:47<1:01:38,  1.58it/s]
 90%|████████▉ | 51757/57600 [9:06:48<1:01:04,  1.59it/s]
 90%|████████▉ | 51758/57600 [9:06:48<1:01:22,  1.59it/s]
 90%|████████▉ | 51759/57600 [9:06:49<1:01:22,  1.59it/s]
 90%|████████▉ | 51760/57600 [9:06:50<1:00:25,  1.61it/s]
                                                         
{'loss': 1.0871, 'learning_rate': 1.9156794425087104e-07, 'epoch': 571.3}

 90%|████████▉ | 51760/57600 [9:06:50<1:00:25,  1.61it/s]
 90%|████████▉ | 51761/57600 [9:06:50<1:02:06,  1.57it/s]
 90%|████████▉ | 51762/57600 [9:06:51<1:01:10,  1.59it/s]
 90%|████████▉ | 51763/57600 [9:06:52<1:01:27,  1.58it/s]
 90%|████████▉ | 51764/57600 [9:06:52<1:00:03,  1.62it/s]
 90%|████████▉ | 51765/57600 [9:06:53<1:01:58,  1.57it/s]
 90%|████████▉ | 51766/57600 [9:06:53<1:01:32,  1.58it/s]
 90%|████████▉ | 51767/57600 [9:06:54<1:03:53,  1.52it/s]
 90%|████████▉ | 51768/57600 [9:06:55<1:02:43,  1.55it/s]
 90%|████████▉ | 51769/57600 [9:06:56<1:04:20,  1.51it/s]
 90%|████████▉ | 51770/57600 [9:06:56<1:02:45,  1.55it/s]
 90%|████████▉ | 51771/57600 [9:06:57<1:01:35,  1.58it/s]
 90%|████████▉ | 51772/57600 [9:06:57<59:43,  1.63it/s]  
 90%|████████▉ | 51773/57600 [9:06:58<1:00:42,  1.60it/s]
 90%|████████▉ | 51774/57600 [9:06:59<1:02:54,  1.54it/s]
 90%|████████▉ | 51775/57600 [9:06:59<1:02:20,  1.56it/s]
 90%|████████▉ | 51776/57600 [9:07:00<1:01:31,  1.58it/s]
 90%|████████▉ | 51777/57600 [9:07:01<1:03:04,  1.54it/s]
 90%|████████▉ | 51778/57600 [9:07:01<1:01:05,  1.59it/s]
 90%|████████▉ | 51779/57600 [9:07:02<1:01:37,  1.57it/s]
 90%|████████▉ | 51780/57600 [9:07:02<1:00:14,  1.61it/s]
                                                         
{'loss': 1.0808, 'learning_rate': 1.9125435540069687e-07, 'epoch': 571.52}

 90%|████████▉ | 51780/57600 [9:07:02<1:00:14,  1.61it/s]
 90%|████████▉ | 51781/57600 [9:07:03<59:13,  1.64it/s]  
 90%|████████▉ | 51782/57600 [9:07:04<58:33,  1.66it/s]
 90%|████████▉ | 51783/57600 [9:07:04<57:34,  1.68it/s]
 90%|████████▉ | 51784/57600 [9:07:05<57:42,  1.68it/s]
 90%|████████▉ | 51785/57600 [9:07:05<58:25,  1.66it/s]
 90%|████████▉ | 51786/57600 [9:07:06<1:00:15,  1.61it/s]
 90%|████████▉ | 51787/57600 [9:07:07<1:00:02,  1.61it/s]
 90%|████████▉ | 51788/57600 [9:07:07<1:01:38,  1.57it/s]
 90%|████████▉ | 51789/57600 [9:07:08<1:00:32,  1.60it/s]
 90%|████████▉ | 51790/57600 [9:07:08<58:37,  1.65it/s]  
 90%|████████▉ | 51791/57600 [9:07:09<57:35,  1.68it/s]
 90%|████████▉ | 51792/57600 [9:07:10<58:02,  1.67it/s]
 90%|████████▉ | 51793/57600 [9:07:10<57:14,  1.69it/s]
 90%|████████▉ | 51794/57600 [9:07:11<59:19,  1.63it/s]
 90%|████████▉ | 51795/57600 [9:07:12<59:54,  1.61it/s]
 90%|████████▉ | 51796/57600 [9:07:12<1:00:02,  1.61it/s]
 90%|████████▉ | 51797/57600 [9:07:13<1:00:53,  1.59it/s]
 90%|████████▉ | 51798/57600 [9:07:14<1:03:53,  1.51it/s]
 90%|████████▉ | 51799/57600 [9:07:14<1:02:21,  1.55it/s]
 90%|████████▉ | 51800/57600 [9:07:15<1:00:44,  1.59it/s]
                                                         
{'loss': 1.1242, 'learning_rate': 1.909407665505226e-07, 'epoch': 571.74}

 90%|████████▉ | 51800/57600 [9:07:15<1:00:44,  1.59it/s]
 90%|████████▉ | 51801/57600 [9:07:15<59:33,  1.62it/s]  
 90%|████████▉ | 51802/57600 [9:07:16<58:38,  1.65it/s]
 90%|████████▉ | 51803/57600 [9:07:17<58:45,  1.64it/s]
 90%|████████▉ | 51804/57600 [9:07:17<59:45,  1.62it/s]
 90%|████████▉ | 51805/57600 [9:07:18<59:58,  1.61it/s]
 90%|████████▉ | 51806/57600 [9:07:18<1:01:30,  1.57it/s]
 90%|████████▉ | 51807/57600 [9:07:19<1:00:00,  1.61it/s]
 90%|████████▉ | 51808/57600 [9:07:20<58:57,  1.64it/s]  
 90%|████████▉ | 51809/57600 [9:07:20<59:27,  1.62it/s]
 90%|████████▉ | 51810/57600 [9:07:21<58:57,  1.64it/s]
 90%|████████▉ | 51811/57600 [9:07:22<1:00:49,  1.59it/s]
 90%|████████▉ | 51812/57600 [9:07:22<1:01:08,  1.58it/s]
 90%|████████▉ | 51813/57600 [9:07:23<59:22,  1.62it/s]  
 90%|████████▉ | 51814/57600 [9:07:23<58:46,  1.64it/s]
 90%|████████▉ | 51815/57600 [9:07:24<1:00:47,  1.59it/s]
 90%|████████▉ | 51816/57600 [9:07:25<59:48,  1.61it/s]  
 90%|████████▉ | 51817/57600 [9:07:25<1:01:06,  1.58it/s]
 90%|████████▉ | 51818/57600 [9:07:26<1:00:31,  1.59it/s]
 90%|████████▉ | 51819/57600 [9:07:27<59:41,  1.61it/s]  
 90%|████████▉ | 51820/57600 [9:07:27<59:14,  1.63it/s]
                                                       
{'loss': 1.1188, 'learning_rate': 1.9062717770034842e-07, 'epoch': 571.96}

 90%|████████▉ | 51820/57600 [9:07:27<59:14,  1.63it/s]
 90%|████████▉ | 51821/57600 [9:07:28<59:12,  1.63it/s]
 90%|████████▉ | 51822/57600 [9:07:28<58:42,  1.64it/s]
 90%|████████▉ | 51823/57600 [9:07:29<57:48,  1.67it/s]
 90%|████████▉ | 51824/57600 [9:07:30<1:01:45,  1.56it/s]
 90%|████████▉ | 51825/57600 [9:07:30<1:00:22,  1.59it/s]
 90%|████████▉ | 51826/57600 [9:07:31<59:26,  1.62it/s]  
 90%|████████▉ | 51827/57600 [9:07:31<58:41,  1.64it/s]
 90%|████████▉ | 51828/57600 [9:07:32<1:00:44,  1.58it/s]
 90%|████████▉ | 51829/57600 [9:07:33<1:02:09,  1.55it/s]
 90%|████████▉ | 51830/57600 [9:07:33<1:00:23,  1.59it/s]
 90%|████████▉ | 51831/57600 [9:07:34<58:19,  1.65it/s]  
 90%|████████▉ | 51832/57600 [9:07:35<59:58,  1.60it/s]
 90%|████████▉ | 51833/57600 [9:07:35<59:12,  1.62it/s]
 90%|████████▉ | 51834/57600 [9:07:36<59:12,  1.62it/s]
 90%|████████▉ | 51835/57600 [9:07:36<58:53,  1.63it/s]
 90%|████████▉ | 51836/57600 [9:07:37<58:36,  1.64it/s]
 90%|████████▉ | 51837/57600 [9:07:38<57:34,  1.67it/s]
 90%|████████▉ | 51838/57600 [9:07:38<56:57,  1.69it/s]
 90%|████████▉ | 51839/57600 [9:07:39<56:40,  1.69it/s]
 90%|█████████ | 51840/57600 [9:07:39<57:55,  1.66it/s]
                                                       
{'loss': 1.1589, 'learning_rate': 1.9031358885017423e-07, 'epoch': 572.19}

 90%|█████████ | 51840/57600 [9:07:39<57:55,  1.66it/s]
 90%|█████████ | 51841/57600 [9:07:40<59:22,  1.62it/s]
 90%|█████████ | 51842/57600 [9:07:41<58:53,  1.63it/s]
 90%|█████████ | 51843/57600 [9:07:41<58:23,  1.64it/s]
 90%|█████████ | 51844/57600 [9:07:42<1:00:27,  1.59it/s]
 90%|█████████ | 51845/57600 [9:07:43<1:01:30,  1.56it/s]
 90%|█████████ | 51846/57600 [9:07:43<1:02:13,  1.54it/s]
 90%|█████████ | 51847/57600 [9:07:44<1:02:40,  1.53it/s]
 90%|█████████ | 51848/57600 [9:07:45<1:04:54,  1.48it/s]
 90%|█████████ | 51849/57600 [9:07:45<1:02:58,  1.52it/s]
 90%|█████████ | 51850/57600 [9:07:46<1:03:02,  1.52it/s]
 90%|█████████ | 51851/57600 [9:07:47<1:01:53,  1.55it/s]
 90%|█████████ | 51852/57600 [9:07:47<1:00:10,  1.59it/s]
 90%|█████████ | 51853/57600 [9:07:48<59:27,  1.61it/s]  
 90%|█████████ | 51854/57600 [9:07:48<59:34,  1.61it/s]
 90%|█████████ | 51855/57600 [9:07:49<58:51,  1.63it/s]
 90%|█████████ | 51856/57600 [9:07:50<1:00:26,  1.58it/s]
 90%|█████████ | 51857/57600 [9:07:50<59:38,  1.60it/s]  
 90%|█████████ | 51858/57600 [9:07:51<58:56,  1.62it/s]
 90%|█████████ | 51859/57600 [9:07:51<57:51,  1.65it/s]
 90%|█████████ | 51860/57600 [9:07:52<58:57,  1.62it/s]
                                                       
{'loss': 1.1039, 'learning_rate': 1.8999999999999998e-07, 'epoch': 572.41}

 90%|█████████ | 51860/57600 [9:07:52<58:57,  1.62it/s]
 90%|█████████ | 51861/57600 [9:07:53<58:05,  1.65it/s]
 90%|█████████ | 51862/57600 [9:07:53<58:18,  1.64it/s]
 90%|█████████ | 51863/57600 [9:07:54<58:02,  1.65it/s]
 90%|█████████ | 51864/57600 [9:07:54<58:07,  1.64it/s]
 90%|█████████ | 51865/57600 [9:07:55<58:48,  1.63it/s]
 90%|█████████ | 51866/57600 [9:07:56<1:02:14,  1.54it/s]
 90%|█████████ | 51867/57600 [9:07:56<1:00:29,  1.58it/s]
 90%|█████████ | 51868/57600 [9:07:57<58:26,  1.63it/s]  
 90%|█████████ | 51869/57600 [9:07:58<56:34,  1.69it/s]
 90%|█████████ | 51870/57600 [9:07:58<58:12,  1.64it/s]
 90%|█████████ | 51871/57600 [9:07:59<56:38,  1.69it/s]
 90%|█████████ | 51872/57600 [9:07:59<57:21,  1.66it/s]
 90%|█████████ | 51873/57600 [9:08:00<58:37,  1.63it/s]
 90%|█████████ | 51874/57600 [9:08:01<58:42,  1.63it/s]
 90%|█████████ | 51875/57600 [9:08:01<58:18,  1.64it/s]
 90%|█████████ | 51876/57600 [9:08:02<1:00:43,  1.57it/s]
 90%|█████████ | 51877/57600 [9:08:02<59:32,  1.60it/s]  
 90%|█████████ | 51878/57600 [9:08:03<57:43,  1.65it/s]
 90%|█████████ | 51879/57600 [9:08:04<57:53,  1.65it/s]
 90%|█████████ | 51880/57600 [9:08:04<57:53,  1.65it/s]
                                                       
{'loss': 1.1123, 'learning_rate': 1.8968641114982579e-07, 'epoch': 572.63}

 90%|█████████ | 51880/57600 [9:08:04<57:53,  1.65it/s]
 90%|█████████ | 51881/57600 [9:08:05<58:27,  1.63it/s]
 90%|█████████ | 51882/57600 [9:08:06<1:00:27,  1.58it/s]
 90%|█████████ | 51883/57600 [9:08:06<1:00:32,  1.57it/s]
 90%|█████████ | 51884/57600 [9:08:07<59:37,  1.60it/s]  
 90%|█████████ | 51885/57600 [9:08:07<59:51,  1.59it/s]
 90%|█████████ | 51886/57600 [9:08:08<1:00:37,  1.57it/s]
 90%|█████████ | 51887/57600 [9:08:09<1:01:04,  1.56it/s]
 90%|█████████ | 51888/57600 [9:08:09<1:01:52,  1.54it/s]
 90%|█████████ | 51889/57600 [9:08:10<1:01:13,  1.55it/s]
 90%|█████████ | 51890/57600 [9:08:11<59:37,  1.60it/s]  
 90%|█████████ | 51891/57600 [9:08:11<59:34,  1.60it/s]
 90%|█████████ | 51892/57600 [9:08:12<59:58,  1.59it/s]
 90%|█████████ | 51893/57600 [9:08:13<59:08,  1.61it/s]
 90%|█████████ | 51894/57600 [9:08:13<58:51,  1.62it/s]
 90%|█████████ | 51895/57600 [9:08:14<1:00:36,  1.57it/s]
 90%|█████████ | 51896/57600 [9:08:14<58:51,  1.62it/s]  
 90%|█████████ | 51897/57600 [9:08:15<57:24,  1.66it/s]
 90%|█████████ | 51898/57600 [9:08:16<58:37,  1.62it/s]
 90%|█████████ | 51899/57600 [9:08:16<59:45,  1.59it/s]
 90%|█████████ | 51900/57600 [9:08:17<58:06,  1.63it/s]
                                                       
{'loss': 1.1149, 'learning_rate': 1.8937282229965154e-07, 'epoch': 572.85}

 90%|█████████ | 51900/57600 [9:08:17<58:06,  1.63it/s]
 90%|█████████ | 51901/57600 [9:08:17<57:00,  1.67it/s]
 90%|█████████ | 51902/57600 [9:08:18<57:26,  1.65it/s]
 90%|█████████ | 51903/57600 [9:08:19<58:27,  1.62it/s]
 90%|█████████ | 51904/57600 [9:08:19<57:09,  1.66it/s]
 90%|█████████ | 51905/57600 [9:08:20<57:30,  1.65it/s]
 90%|█████████ | 51906/57600 [9:08:21<59:30,  1.59it/s]
 90%|█████████ | 51907/57600 [9:08:21<59:47,  1.59it/s]
 90%|█████████ | 51908/57600 [9:08:22<58:10,  1.63it/s]
 90%|█████████ | 51909/57600 [9:08:22<59:24,  1.60it/s]
 90%|█████████ | 51910/57600 [9:08:23<59:10,  1.60it/s]
 90%|█████████ | 51911/57600 [9:08:24<58:02,  1.63it/s]
 90%|█████████ | 51912/57600 [9:08:24<56:56,  1.67it/s]
 90%|█████████ | 51913/57600 [9:08:25<57:08,  1.66it/s]
 90%|█████████ | 51914/57600 [9:08:25<59:30,  1.59it/s]
 90%|█████████ | 51915/57600 [9:08:26<58:27,  1.62it/s]
 90%|█████████ | 51916/57600 [9:08:27<58:41,  1.61it/s]
 90%|█████████ | 51917/57600 [9:08:27<59:49,  1.58it/s]
 90%|█████████ | 51918/57600 [9:08:28<57:41,  1.64it/s]
 90%|█████████ | 51919/57600 [9:08:28<57:11,  1.66it/s]
 90%|█████████ | 51920/57600 [9:08:29<1:01:26,  1.54it/s]
                                                         
{'loss': 1.1306, 'learning_rate': 1.8905923344947732e-07, 'epoch': 573.07}

 90%|█████████ | 51920/57600 [9:08:29<1:01:26,  1.54it/s]
 90%|█████████ | 51921/57600 [9:08:30<59:07,  1.60it/s]  
 90%|█████████ | 51922/57600 [9:08:30<58:41,  1.61it/s]
 90%|█████████ | 51923/57600 [9:08:31<58:45,  1.61it/s]
 90%|█████████ | 51924/57600 [9:08:32<57:50,  1.64it/s]
 90%|█████████ | 51925/57600 [9:08:32<57:33,  1.64it/s]
 90%|█████████ | 51926/57600 [9:08:33<57:18,  1.65it/s]
 90%|█████████ | 51927/57600 [9:08:33<58:09,  1.63it/s]
 90%|█████████ | 51928/57600 [9:08:34<58:13,  1.62it/s]
 90%|█████████ | 51929/57600 [9:08:35<56:59,  1.66it/s]
 90%|█████████ | 51930/57600 [9:08:35<58:46,  1.61it/s]
 90%|█████████ | 51931/57600 [9:08:36<57:30,  1.64it/s]
 90%|█████████ | 51932/57600 [9:08:37<57:00,  1.66it/s]
 90%|█████████ | 51933/57600 [9:08:37<55:22,  1.71it/s]
 90%|█████████ | 51934/57600 [9:08:38<56:08,  1.68it/s]
 90%|█████████ | 51935/57600 [9:08:38<56:59,  1.66it/s]
 90%|█████████ | 51936/57600 [9:08:39<57:24,  1.64it/s]
 90%|█████████ | 51937/57600 [9:08:40<58:56,  1.60it/s]
 90%|█████████ | 51938/57600 [9:08:40<58:23,  1.62it/s]
 90%|█████████ | 51939/57600 [9:08:41<57:54,  1.63it/s]
 90%|█████████ | 51940/57600 [9:08:41<58:30,  1.61it/s]
                                                       
{'loss': 1.1336, 'learning_rate': 1.887456445993031e-07, 'epoch': 573.29}

 90%|█████████ | 51940/57600 [9:08:41<58:30,  1.61it/s]
 90%|█████████ | 51941/57600 [9:08:42<57:25,  1.64it/s]
 90%|█████████ | 51942/57600 [9:08:43<57:50,  1.63it/s]
 90%|█████████ | 51943/57600 [9:08:43<57:59,  1.63it/s]
 90%|█████████ | 51944/57600 [9:08:44<57:07,  1.65it/s]
 90%|█████████ | 51945/57600 [9:08:44<57:38,  1.63it/s]
 90%|█████████ | 51946/57600 [9:08:45<58:40,  1.61it/s]
 90%|█████████ | 51947/57600 [9:08:46<58:46,  1.60it/s]
 90%|█████████ | 51948/57600 [9:08:46<58:48,  1.60it/s]
 90%|█████████ | 51949/57600 [9:08:47<58:44,  1.60it/s]
 90%|█████████ | 51950/57600 [9:08:48<59:17,  1.59it/s]
 90%|█████████ | 51951/57600 [9:08:48<57:48,  1.63it/s]
 90%|█████████ | 51952/57600 [9:08:49<59:23,  1.58it/s]
 90%|█████████ | 51953/57600 [9:08:49<58:54,  1.60it/s]
 90%|█████████ | 51954/57600 [9:08:50<57:36,  1.63it/s]
 90%|█████████ | 51955/57600 [9:08:51<57:08,  1.65it/s]
 90%|█████████ | 51956/57600 [9:08:51<57:25,  1.64it/s]
 90%|█████████ | 51957/57600 [9:08:52<1:00:27,  1.56it/s]
 90%|█████████ | 51958/57600 [9:08:53<1:04:48,  1.45it/s]
 90%|█████████ | 51959/57600 [9:08:53<1:03:55,  1.47it/s]
 90%|█████████ | 51960/57600 [9:08:54<1:01:37,  1.53it/s]
                                                         
{'loss': 1.101, 'learning_rate': 1.884320557491289e-07, 'epoch': 573.51}

 90%|█████████ | 51960/57600 [9:08:54<1:01:37,  1.53it/s]
 90%|█████████ | 51961/57600 [9:08:55<59:49,  1.57it/s]  
 90%|█████████ | 51962/57600 [9:08:55<58:19,  1.61it/s]
 90%|█████████ | 51963/57600 [9:08:56<59:38,  1.58it/s]
 90%|█████████ | 51964/57600 [9:08:56<57:44,  1.63it/s]
 90%|█████████ | 51965/57600 [9:08:57<57:18,  1.64it/s]
 90%|█████████ | 51966/57600 [9:08:58<56:47,  1.65it/s]
 90%|█████████ | 51967/57600 [9:08:58<55:56,  1.68it/s]
 90%|█████████ | 51968/57600 [9:08:59<55:37,  1.69it/s]
 90%|█████████ | 51969/57600 [9:08:59<56:37,  1.66it/s]
 90%|█████████ | 51970/57600 [9:09:00<59:12,  1.58it/s]
 90%|█████████ | 51971/57600 [9:09:01<57:22,  1.64it/s]
 90%|█████████ | 51972/57600 [9:09:01<56:25,  1.66it/s]
 90%|█████████ | 51973/57600 [9:09:02<58:23,  1.61it/s]
 90%|█████████ | 51974/57600 [9:09:03<58:31,  1.60it/s]
 90%|█████████ | 51975/57600 [9:09:03<57:38,  1.63it/s]
 90%|█████████ | 51976/57600 [9:09:04<56:44,  1.65it/s]
 90%|█████████ | 51977/57600 [9:09:04<56:12,  1.67it/s]
 90%|█████████ | 51978/57600 [9:09:05<55:05,  1.70it/s]
 90%|█████████ | 51979/57600 [9:09:05<55:00,  1.70it/s]
 90%|█████████ | 51980/57600 [9:09:06<55:50,  1.68it/s]
                                                       
{'loss': 1.1317, 'learning_rate': 1.8811846689895473e-07, 'epoch': 573.73}

 90%|█████████ | 51980/57600 [9:09:06<55:50,  1.68it/s]
 90%|█████████ | 51981/57600 [9:09:07<55:56,  1.67it/s]
 90%|█████████ | 51982/57600 [9:09:07<55:22,  1.69it/s]
 90%|█████████ | 51983/57600 [9:09:08<59:32,  1.57it/s]
 90%|█████████ | 51984/57600 [9:09:09<59:32,  1.57it/s]
 90%|█████████ | 51985/57600 [9:09:09<1:00:00,  1.56it/s]
 90%|█████████ | 51986/57600 [9:09:10<1:00:13,  1.55it/s]
 90%|█████████ | 51987/57600 [9:09:11<58:20,  1.60it/s]  
 90%|█████████ | 51988/57600 [9:09:11<1:00:04,  1.56it/s]
 90%|█████████ | 51989/57600 [9:09:12<59:55,  1.56it/s]  
 90%|█████████ | 51990/57600 [9:09:12<57:25,  1.63it/s]
 90%|█████████ | 51991/57600 [9:09:13<58:21,  1.60it/s]
 90%|█████████ | 51992/57600 [9:09:14<59:35,  1.57it/s]
 90%|█████████ | 51993/57600 [9:09:14<58:14,  1.60it/s]
 90%|█████████ | 51994/57600 [9:09:15<58:40,  1.59it/s]
 90%|█████████ | 51995/57600 [9:09:16<58:00,  1.61it/s]
 90%|█████████ | 51996/57600 [9:09:16<57:28,  1.62it/s]
 90%|█████████ | 51997/57600 [9:09:17<59:09,  1.58it/s]
 90%|█████████ | 51998/57600 [9:09:17<59:08,  1.58it/s]
 90%|█████████ | 51999/57600 [9:09:18<58:02,  1.61it/s]
 90%|█████████ | 52000/57600 [9:09:19<57:32,  1.62it/s]
                                                       
{'loss': 1.08, 'learning_rate': 1.8780487804878046e-07, 'epoch': 573.95}

 90%|█████████ | 52000/57600 [9:09:19<57:32,  1.62it/s]
 90%|█████████ | 52001/57600 [9:09:19<58:38,  1.59it/s]
 90%|█████████ | 52002/57600 [9:09:20<59:56,  1.56it/s]
 90%|█████████ | 52003/57600 [9:09:21<59:17,  1.57it/s]
 90%|█████████ | 52004/57600 [9:09:21<59:40,  1.56it/s]
 90%|█████████ | 52005/57600 [9:09:22<1:02:07,  1.50it/s]
 90%|█████████ | 52006/57600 [9:09:23<1:01:01,  1.53it/s]
 90%|█████████ | 52007/57600 [9:09:23<59:28,  1.57it/s]  
 90%|█████████ | 52008/57600 [9:09:24<1:00:14,  1.55it/s]
 90%|█████████ | 52009/57600 [9:09:25<59:11,  1.57it/s]  
 90%|█████████ | 52010/57600 [9:09:25<59:50,  1.56it/s]
 90%|█████████ | 52011/57600 [9:09:26<57:58,  1.61it/s]
 90%|█████████ | 52012/57600 [9:09:26<58:28,  1.59it/s]
 90%|█████████ | 52013/57600 [9:09:27<1:00:25,  1.54it/s]
 90%|█████████ | 52014/57600 [9:09:28<58:52,  1.58it/s]  
 90%|█████████ | 52015/57600 [9:09:28<57:52,  1.61it/s]
 90%|█████████ | 52016/57600 [9:09:29<58:42,  1.59it/s]
 90%|█████████ | 52017/57600 [9:09:30<59:21,  1.57it/s]
 90%|█████████ | 52018/57600 [9:09:30<58:29,  1.59it/s]
 90%|█████████ | 52019/57600 [9:09:31<57:23,  1.62it/s]
 90%|█████████ | 52020/57600 [9:09:31<59:56,  1.55it/s]
                                                       
{'loss': 1.1152, 'learning_rate': 1.874912891986063e-07, 'epoch': 574.17}

 90%|█████████ | 52020/57600 [9:09:31<59:56,  1.55it/s]
 90%|█████████ | 52021/57600 [9:09:32<57:40,  1.61it/s]
 90%|█████████ | 52022/57600 [9:09:33<57:19,  1.62it/s]
 90%|█████████ | 52023/57600 [9:09:33<56:42,  1.64it/s]
 90%|█████████ | 52024/57600 [9:09:34<56:34,  1.64it/s]
 90%|█████████ | 52025/57600 [9:09:34<56:02,  1.66it/s]
 90%|█████████ | 52026/57600 [9:09:35<55:55,  1.66it/s]
 90%|█████████ | 52027/57600 [9:09:36<56:01,  1.66it/s]
 90%|█████████ | 52028/57600 [9:09:36<56:32,  1.64it/s]
 90%|█████████ | 52029/57600 [9:09:37<57:12,  1.62it/s]
 90%|█████████ | 52030/57600 [9:09:38<58:41,  1.58it/s]
 90%|█████████ | 52031/57600 [9:09:38<58:38,  1.58it/s]
 90%|█████████ | 52032/57600 [9:09:39<58:03,  1.60it/s]
 90%|█████████ | 52033/57600 [9:09:39<57:41,  1.61it/s]
 90%|█████████ | 52034/57600 [9:09:40<57:25,  1.62it/s]
 90%|█████████ | 52035/57600 [9:09:41<57:21,  1.62it/s]
 90%|█████████ | 52036/57600 [9:09:41<55:44,  1.66it/s]
 90%|█████████ | 52037/57600 [9:09:42<57:45,  1.61it/s]
 90%|█████████ | 52038/57600 [9:09:43<57:49,  1.60it/s]
 90%|█████████ | 52039/57600 [9:09:43<56:56,  1.63it/s]
 90%|█████████ | 52040/57600 [9:09:44<1:00:11,  1.54it/s]
                                                         
{'loss': 1.0945, 'learning_rate': 1.8717770034843199e-07, 'epoch': 574.39}

 90%|█████████ | 52040/57600 [9:09:44<1:00:11,  1.54it/s]
 90%|█████████ | 52041/57600 [9:09:44<57:51,  1.60it/s]  
 90%|█████████ | 52042/57600 [9:09:45<57:36,  1.61it/s]
 90%|█████████ | 52043/57600 [9:09:46<56:25,  1.64it/s]
 90%|█████████ | 52044/57600 [9:09:46<58:04,  1.59it/s]
 90%|█████████ | 52045/57600 [9:09:47<1:01:56,  1.49it/s]
 90%|█████████ | 52046/57600 [9:09:48<1:02:00,  1.49it/s]
 90%|█████████ | 52047/57600 [9:09:48<59:51,  1.55it/s]  
 90%|█████████ | 52048/57600 [9:09:49<58:58,  1.57it/s]
 90%|█████████ | 52049/57600 [9:09:50<59:58,  1.54it/s]
 90%|█████████ | 52050/57600 [9:09:50<58:32,  1.58it/s]
 90%|█████████ | 52051/57600 [9:09:51<57:43,  1.60it/s]
 90%|█████████ | 52052/57600 [9:09:51<57:03,  1.62it/s]
 90%|█████████ | 52053/57600 [9:09:52<57:49,  1.60it/s]
 90%|█████████ | 52054/57600 [9:09:53<57:10,  1.62it/s]
 90%|█████████ | 52055/57600 [9:09:53<58:28,  1.58it/s]
 90%|█████████ | 52056/57600 [9:09:54<58:04,  1.59it/s]
 90%|█████████ | 52057/57600 [9:09:55<58:20,  1.58it/s]
 90%|█████████ | 52058/57600 [9:09:55<59:02,  1.56it/s]
 90%|█████████ | 52059/57600 [9:09:56<59:11,  1.56it/s]
 90%|█████████ | 52060/57600 [9:09:56<58:51,  1.57it/s]
                                                       
{'loss': 1.0779, 'learning_rate': 1.8686411149825782e-07, 'epoch': 574.61}

 90%|█████████ | 52060/57600 [9:09:56<58:51,  1.57it/s]
 90%|█████████ | 52061/57600 [9:09:57<59:28,  1.55it/s]
 90%|█████████ | 52062/57600 [9:09:58<58:20,  1.58it/s]
 90%|█████████ | 52063/57600 [9:09:58<57:27,  1.61it/s]
 90%|█████████ | 52064/57600 [9:09:59<56:45,  1.63it/s]
 90%|█████████ | 52065/57600 [9:10:00<57:22,  1.61it/s]
 90%|█████████ | 52066/57600 [9:10:00<59:07,  1.56it/s]
 90%|█████████ | 52067/57600 [9:10:01<1:00:58,  1.51it/s]
 90%|█████████ | 52068/57600 [9:10:02<58:58,  1.56it/s]  
 90%|█████████ | 52069/57600 [9:10:02<57:56,  1.59it/s]
 90%|█████████ | 52070/57600 [9:10:03<58:54,  1.56it/s]
 90%|█████████ | 52071/57600 [9:10:04<1:00:04,  1.53it/s]
 90%|█████████ | 52072/57600 [9:10:04<1:00:08,  1.53it/s]
 90%|█████████ | 52073/57600 [9:10:05<57:44,  1.60it/s]  
 90%|█████████ | 52074/57600 [9:10:05<58:46,  1.57it/s]
 90%|█████████ | 52075/57600 [9:10:06<58:45,  1.57it/s]
 90%|█████████ | 52076/57600 [9:10:07<57:45,  1.59it/s]
 90%|█████████ | 52077/57600 [9:10:07<56:09,  1.64it/s]
 90%|█████████ | 52078/57600 [9:10:08<56:36,  1.63it/s]
 90%|█████████ | 52079/57600 [9:10:08<57:32,  1.60it/s]
 90%|█████████ | 52080/57600 [9:10:09<57:00,  1.61it/s]
                                                       
{'loss': 1.1206, 'learning_rate': 1.8655052264808368e-07, 'epoch': 574.83}

 90%|█████████ | 52080/57600 [9:10:09<57:00,  1.61it/s]
 90%|█████████ | 52081/57600 [9:10:10<57:38,  1.60it/s]
 90%|█████████ | 52082/57600 [9:10:10<57:49,  1.59it/s]
 90%|█████████ | 52083/57600 [9:10:11<57:25,  1.60it/s]
 90%|█████████ | 52084/57600 [9:10:12<57:22,  1.60it/s]
 90%|█████████ | 52085/57600 [9:10:12<57:12,  1.61it/s]
 90%|█████████ | 52086/57600 [9:10:13<58:43,  1.56it/s]
 90%|█████████ | 52087/57600 [9:10:14<57:42,  1.59it/s]
 90%|█████████ | 52088/57600 [9:10:14<56:19,  1.63it/s]
 90%|█████████ | 52089/57600 [9:10:15<56:03,  1.64it/s]
 90%|█████████ | 52090/57600 [9:10:15<57:02,  1.61it/s]
 90%|█████████ | 52091/57600 [9:10:16<55:32,  1.65it/s]
 90%|█████████ | 52092/57600 [9:10:17<55:39,  1.65it/s]
 90%|█████████ | 52093/57600 [9:10:17<54:47,  1.68it/s]
 90%|█████████ | 52094/57600 [9:10:18<56:00,  1.64it/s]
 90%|█████████ | 52095/57600 [9:10:18<55:22,  1.66it/s]
 90%|█████████ | 52096/57600 [9:10:19<57:44,  1.59it/s]
 90%|█████████ | 52097/57600 [9:10:20<1:00:38,  1.51it/s]
 90%|█████████ | 52098/57600 [9:10:20<59:05,  1.55it/s]  
 90%|█████████ | 52099/57600 [9:10:21<57:21,  1.60it/s]
 90%|█████████ | 52100/57600 [9:10:22<56:44,  1.62it/s]
                                                       
{'loss': 1.1292, 'learning_rate': 1.8623693379790937e-07, 'epoch': 575.06}

 90%|█████████ | 52100/57600 [9:10:22<56:44,  1.62it/s]
 90%|█████████ | 52101/57600 [9:10:22<1:00:10,  1.52it/s]
 90%|█████████ | 52102/57600 [9:10:23<1:00:52,  1.51it/s]
 90%|█████████ | 52103/57600 [9:10:24<59:45,  1.53it/s]  
 90%|█████████ | 52104/57600 [9:10:24<59:37,  1.54it/s]
 90%|█████████ | 52105/57600 [9:10:25<58:56,  1.55it/s]
 90%|█████████ | 52106/57600 [9:10:25<57:49,  1.58it/s]
 90%|█████████ | 52107/57600 [9:10:26<57:55,  1.58it/s]
 90%|█████████ | 52108/57600 [9:10:27<57:30,  1.59it/s]
 90%|█████████ | 52109/57600 [9:10:27<1:00:22,  1.52it/s]
 90%|█████████ | 52110/57600 [9:10:28<1:01:14,  1.49it/s]
 90%|█████████ | 52111/57600 [9:10:29<1:00:53,  1.50it/s]
 90%|█████████ | 52112/57600 [9:10:29<58:09,  1.57it/s]  
 90%|█████████ | 52113/57600 [9:10:30<58:53,  1.55it/s]
 90%|█████████ | 52114/57600 [9:10:31<58:01,  1.58it/s]
 90%|█████████ | 52115/57600 [9:10:31<56:45,  1.61it/s]
 90%|█████████ | 52116/57600 [9:10:32<56:09,  1.63it/s]
 90%|█████████ | 52117/57600 [9:10:33<58:02,  1.57it/s]
 90%|█████████ | 52118/57600 [9:10:33<57:24,  1.59it/s]
 90%|█████████ | 52119/57600 [9:10:34<57:08,  1.60it/s]
 90%|█████████ | 52120/57600 [9:10:34<56:31,  1.62it/s]
                                                       
{'loss': 1.0637, 'learning_rate': 1.8592334494773523e-07, 'epoch': 575.28}

 90%|█████████ | 52120/57600 [9:10:34<56:31,  1.62it/s]
 90%|█████████ | 52121/57600 [9:10:35<56:22,  1.62it/s]
 90%|█████████ | 52122/57600 [9:10:36<55:36,  1.64it/s]
 90%|█████████ | 52123/57600 [9:10:36<56:32,  1.61it/s]
 90%|█████████ | 52124/57600 [9:10:37<55:18,  1.65it/s]
 90%|█████████ | 52125/57600 [9:10:37<56:03,  1.63it/s]
 90%|█████████ | 52126/57600 [9:10:38<55:46,  1.64it/s]
 90%|█████████ | 52127/57600 [9:10:39<56:28,  1.62it/s]
 90%|█████████ | 52128/57600 [9:10:39<56:27,  1.62it/s]
 91%|█████████ | 52129/57600 [9:10:40<55:31,  1.64it/s]
 91%|█████████ | 52130/57600 [9:10:40<55:45,  1.64it/s]
 91%|█████████ | 52131/57600 [9:10:41<55:09,  1.65it/s]
 91%|█████████ | 52132/57600 [9:10:42<55:18,  1.65it/s]
 91%|█████████ | 52133/57600 [9:10:42<55:08,  1.65it/s]
 91%|█████████ | 52134/57600 [9:10:43<53:46,  1.69it/s]
 91%|█████████ | 52135/57600 [9:10:43<54:24,  1.67it/s]
 91%|█████████ | 52136/57600 [9:10:44<58:33,  1.55it/s]
 91%|█████████ | 52137/57600 [9:10:45<58:40,  1.55it/s]
 91%|█████████ | 52138/57600 [9:10:45<57:18,  1.59it/s]
 91%|█████████ | 52139/57600 [9:10:46<59:14,  1.54it/s]
 91%|█████████ | 52140/57600 [9:10:47<59:10,  1.54it/s]
                                                       
{'loss': 1.124, 'learning_rate': 1.8560975609756093e-07, 'epoch': 575.5}

 91%|█████████ | 52140/57600 [9:10:47<59:10,  1.54it/s]
 91%|█████████ | 52141/57600 [9:10:47<58:07,  1.57it/s]
 91%|█████████ | 52142/57600 [9:10:48<57:40,  1.58it/s]
 91%|█████████ | 52143/57600 [9:10:49<57:31,  1.58it/s]
 91%|█████████ | 52144/57600 [9:10:49<56:10,  1.62it/s]
 91%|█████████ | 52145/57600 [9:10:50<58:17,  1.56it/s]
 91%|█████████ | 52146/57600 [9:10:51<58:05,  1.56it/s]
 91%|█████████ | 52147/57600 [9:10:51<56:35,  1.61it/s]
 91%|█████████ | 52148/57600 [9:10:52<56:24,  1.61it/s]
 91%|█████████ | 52149/57600 [9:10:52<54:51,  1.66it/s]
 91%|█████████ | 52150/57600 [9:10:53<54:49,  1.66it/s]
 91%|█████████ | 52151/57600 [9:10:54<55:34,  1.63it/s]
 91%|█████████ | 52152/57600 [9:10:54<56:03,  1.62it/s]
 91%|█████████ | 52153/57600 [9:10:55<54:54,  1.65it/s]
 91%|█████████ | 52154/57600 [9:10:55<54:38,  1.66it/s]
 91%|█████████ | 52155/57600 [9:10:56<54:46,  1.66it/s]
 91%|█████████ | 52156/57600 [9:10:57<55:09,  1.64it/s]
 91%|█████████ | 52157/57600 [9:10:57<55:22,  1.64it/s]
 91%|█████████ | 52158/57600 [9:10:58<57:40,  1.57it/s]
 91%|█████████ | 52159/57600 [9:10:59<57:05,  1.59it/s]
 91%|█████████ | 52160/57600 [9:10:59<56:48,  1.60it/s]
                                                       
{'loss': 1.1205, 'learning_rate': 1.852961672473868e-07, 'epoch': 575.72}

 91%|█████████ | 52160/57600 [9:10:59<56:48,  1.60it/s]
 91%|█████████ | 52161/57600 [9:11:00<57:38,  1.57it/s]
 91%|█████████ | 52162/57600 [9:11:00<58:02,  1.56it/s]
 91%|█████████ | 52163/57600 [9:11:01<56:33,  1.60it/s]
 91%|█████████ | 52164/57600 [9:11:02<57:16,  1.58it/s]
 91%|█████████ | 52165/57600 [9:11:02<56:58,  1.59it/s]
 91%|█████████ | 52166/57600 [9:11:03<55:34,  1.63it/s]
 91%|█████████ | 52167/57600 [9:11:04<57:41,  1.57it/s]
 91%|█████████ | 52168/57600 [9:11:04<57:52,  1.56it/s]
 91%|█████████ | 52169/57600 [9:11:05<56:53,  1.59it/s]
 91%|█████████ | 52170/57600 [9:11:05<57:34,  1.57it/s]
 91%|█████████ | 52171/57600 [9:11:06<57:23,  1.58it/s]
 91%|█████████ | 52172/57600 [9:11:07<59:35,  1.52it/s]
 91%|█████████ | 52173/57600 [9:11:07<59:33,  1.52it/s]
 91%|█████████ | 52174/57600 [9:11:08<58:10,  1.55it/s]
 91%|█████████ | 52175/57600 [9:11:09<59:55,  1.51it/s]
 91%|█████████ | 52176/57600 [9:11:09<57:57,  1.56it/s]
 91%|█████████ | 52177/57600 [9:11:10<57:22,  1.58it/s]
 91%|█████████ | 52178/57600 [9:11:11<56:59,  1.59it/s]
 91%|█████████ | 52179/57600 [9:11:11<57:18,  1.58it/s]
 91%|█████████ | 52180/57600 [9:11:12<57:41,  1.57it/s]
                                                       
{'loss': 1.0828, 'learning_rate': 1.849825783972125e-07, 'epoch': 575.94}

 91%|█████████ | 52180/57600 [9:11:12<57:41,  1.57it/s]
 91%|█████████ | 52181/57600 [9:11:13<58:23,  1.55it/s]
 91%|█████████ | 52182/57600 [9:11:13<56:47,  1.59it/s]
 91%|█████████ | 52183/57600 [9:11:14<56:23,  1.60it/s]
 91%|█████████ | 52184/57600 [9:11:14<57:04,  1.58it/s]
 91%|█████████ | 52185/57600 [9:11:15<55:58,  1.61it/s]
 91%|█████████ | 52186/57600 [9:11:16<59:11,  1.52it/s]
 91%|█████████ | 52187/57600 [9:11:16<57:36,  1.57it/s]
 91%|█████████ | 52188/57600 [9:11:17<56:11,  1.61it/s]
 91%|█████████ | 52189/57600 [9:11:18<54:55,  1.64it/s]
 91%|█████████ | 52190/57600 [9:11:18<55:44,  1.62it/s]
 91%|█████████ | 52191/57600 [9:11:19<56:46,  1.59it/s]
 91%|█████████ | 52192/57600 [9:11:19<56:45,  1.59it/s]
 91%|█████████ | 52193/57600 [9:11:20<56:45,  1.59it/s]
 91%|█████████ | 52194/57600 [9:11:21<57:03,  1.58it/s]
 91%|█████████ | 52195/57600 [9:11:21<57:57,  1.55it/s]
 91%|█████████ | 52196/57600 [9:11:22<56:56,  1.58it/s]
 91%|█████████ | 52197/57600 [9:11:23<55:48,  1.61it/s]
 91%|█████████ | 52198/57600 [9:11:23<56:20,  1.60it/s]
 91%|█████████ | 52199/57600 [9:11:24<56:23,  1.60it/s]
 91%|█████████ | 52200/57600 [9:11:24<55:53,  1.61it/s]
                                                       
{'loss': 1.119, 'learning_rate': 1.8466898954703832e-07, 'epoch': 576.16}

 91%|█████████ | 52200/57600 [9:11:24<55:53,  1.61it/s]
 91%|█████████ | 52201/57600 [9:11:25<57:23,  1.57it/s]
 91%|█████████ | 52202/57600 [9:11:26<56:19,  1.60it/s]
 91%|█████████ | 52203/57600 [9:11:26<57:22,  1.57it/s]
 91%|█████████ | 52204/57600 [9:11:27<55:05,  1.63it/s]
 91%|█████████ | 52205/57600 [9:11:28<55:22,  1.62it/s]
 91%|█████████ | 52206/57600 [9:11:28<55:07,  1.63it/s]
 91%|█████████ | 52207/57600 [9:11:29<54:15,  1.66it/s]
 91%|█████████ | 52208/57600 [9:11:29<54:55,  1.64it/s]
 91%|█████████ | 52209/57600 [9:11:30<55:39,  1.61it/s]
 91%|█████████ | 52210/57600 [9:11:31<58:03,  1.55it/s]
 91%|█████████ | 52211/57600 [9:11:31<56:26,  1.59it/s]
 91%|█████████ | 52212/57600 [9:11:32<55:36,  1.61it/s]
 91%|█████████ | 52213/57600 [9:11:33<56:41,  1.58it/s]
 91%|█████████ | 52214/57600 [9:11:33<59:02,  1.52it/s]
 91%|█████████ | 52215/57600 [9:11:34<57:08,  1.57it/s]
 91%|█████████ | 52216/57600 [9:11:35<58:42,  1.53it/s]
 91%|█████████ | 52217/57600 [9:11:35<58:44,  1.53it/s]
 91%|█████████ | 52218/57600 [9:11:36<57:33,  1.56it/s]
 91%|█████████ | 52219/57600 [9:11:37<57:47,  1.55it/s]
 91%|█████████ | 52220/57600 [9:11:37<56:41,  1.58it/s]
                                                       
{'loss': 1.082, 'learning_rate': 1.8435540069686415e-07, 'epoch': 576.38}

 91%|█████████ | 52220/57600 [9:11:37<56:41,  1.58it/s]
 91%|█████████ | 52221/57600 [9:11:38<58:53,  1.52it/s]
 91%|█████████ | 52222/57600 [9:11:38<57:22,  1.56it/s]
 91%|█████████ | 52223/57600 [9:11:39<55:12,  1.62it/s]
 91%|█████████ | 52224/57600 [9:11:40<54:09,  1.65it/s]
 91%|█████████ | 52225/57600 [9:11:40<54:57,  1.63it/s]
 91%|█████████ | 52226/57600 [9:11:41<55:24,  1.62it/s]
 91%|█████████ | 52227/57600 [9:11:41<54:40,  1.64it/s]
 91%|█████████ | 52228/57600 [9:11:42<54:59,  1.63it/s]
 91%|█████████ | 52229/57600 [9:11:43<54:44,  1.64it/s]
 91%|█████████ | 52230/57600 [9:11:43<55:39,  1.61it/s]
 91%|█████████ | 52231/57600 [9:11:44<58:16,  1.54it/s]
 91%|█████████ | 52232/57600 [9:11:45<56:44,  1.58it/s]
 91%|█████████ | 52233/57600 [9:11:45<57:01,  1.57it/s]
 91%|█████████ | 52234/57600 [9:11:46<58:13,  1.54it/s]
 91%|█████████ | 52235/57600 [9:11:47<57:09,  1.56it/s]
 91%|█████████ | 52236/57600 [9:11:47<56:44,  1.58it/s]
 91%|█████████ | 52237/57600 [9:11:48<56:06,  1.59it/s]
 91%|█████████ | 52238/57600 [9:11:48<56:11,  1.59it/s]
 91%|█████████ | 52239/57600 [9:11:49<56:47,  1.57it/s]
 91%|█████████ | 52240/57600 [9:11:50<56:13,  1.59it/s]
                                                       
{'loss': 1.093, 'learning_rate': 1.8404181184668988e-07, 'epoch': 576.6}

 91%|█████████ | 52240/57600 [9:11:50<56:13,  1.59it/s]
 91%|█████████ | 52241/57600 [9:11:50<56:41,  1.58it/s]
 91%|█████████ | 52242/57600 [9:11:51<57:04,  1.56it/s]
 91%|█████████ | 52243/57600 [9:11:52<56:19,  1.59it/s]
 91%|█████████ | 52244/57600 [9:11:52<55:30,  1.61it/s]
 91%|█████████ | 52245/57600 [9:11:53<54:36,  1.63it/s]
 91%|█████████ | 52246/57600 [9:11:53<56:12,  1.59it/s]
 91%|█████████ | 52247/57600 [9:11:54<55:59,  1.59it/s]
 91%|█████████ | 52248/57600 [9:11:55<53:51,  1.66it/s]
 91%|█████████ | 52249/57600 [9:11:55<53:25,  1.67it/s]
 91%|█████████ | 52250/57600 [9:11:56<53:09,  1.68it/s]
 91%|█████████ | 52251/57600 [9:11:56<55:43,  1.60it/s]
 91%|█████████ | 52252/57600 [9:11:57<53:55,  1.65it/s]
 91%|█████████ | 52253/57600 [9:11:58<54:21,  1.64it/s]
 91%|█████████ | 52254/57600 [9:11:58<53:38,  1.66it/s]
 91%|█████████ | 52255/57600 [9:11:59<54:07,  1.65it/s]
 91%|█████████ | 52256/57600 [9:11:59<54:05,  1.65it/s]
 91%|█████████ | 52257/57600 [9:12:00<53:10,  1.67it/s]
 91%|█████████ | 52258/57600 [9:12:01<55:04,  1.62it/s]
 91%|█████████ | 52259/57600 [9:12:01<55:21,  1.61it/s]
 91%|█████████ | 52260/57600 [9:12:02<55:25,  1.61it/s]
                                                       
{'loss': 1.1082, 'learning_rate': 1.837282229965157e-07, 'epoch': 576.82}

 91%|█████████ | 52260/57600 [9:12:02<55:25,  1.61it/s]
 91%|█████████ | 52261/57600 [9:12:03<57:30,  1.55it/s]
 91%|█████████ | 52262/57600 [9:12:03<57:07,  1.56it/s]
 91%|█████████ | 52263/57600 [9:12:04<55:18,  1.61it/s]
 91%|█████████ | 52264/57600 [9:12:04<53:54,  1.65it/s]
 91%|█████████ | 52265/57600 [9:12:05<54:11,  1.64it/s]
 91%|█████████ | 52266/57600 [9:12:06<54:56,  1.62it/s]
 91%|█████████ | 52267/57600 [9:12:06<56:51,  1.56it/s]
 91%|█████████ | 52268/57600 [9:12:07<57:44,  1.54it/s]
 91%|█████████ | 52269/57600 [9:12:08<57:17,  1.55it/s]
 91%|█████████ | 52270/57600 [9:12:08<57:40,  1.54it/s]
 91%|█████████ | 52271/57600 [9:12:09<55:24,  1.60it/s]
 91%|█████████ | 52272/57600 [9:12:10<56:50,  1.56it/s]
 91%|█████████ | 52273/57600 [9:12:10<55:41,  1.59it/s]
 91%|█████████ | 52274/57600 [9:12:11<56:21,  1.57it/s]
 91%|█████████ | 52275/57600 [9:12:11<54:43,  1.62it/s]
 91%|█████████ | 52276/57600 [9:12:12<53:12,  1.67it/s]
 91%|█████████ | 52277/57600 [9:12:13<55:38,  1.59it/s]
 91%|█████████ | 52278/57600 [9:12:13<55:10,  1.61it/s]
 91%|█████████ | 52279/57600 [9:12:14<55:04,  1.61it/s]
 91%|█████████ | 52280/57600 [9:12:15<54:09,  1.64it/s]
                                                       
{'loss': 1.1105, 'learning_rate': 1.8341463414634143e-07, 'epoch': 577.04}

 91%|█████████ | 52280/57600 [9:12:15<54:09,  1.64it/s]
 91%|█████████ | 52281/57600 [9:12:15<55:37,  1.59it/s]
 91%|█████████ | 52282/57600 [9:12:16<54:14,  1.63it/s]
 91%|█████████ | 52283/57600 [9:12:16<56:29,  1.57it/s]
 91%|█████████ | 52284/57600 [9:12:17<55:34,  1.59it/s]
 91%|█████████ | 52285/57600 [9:12:18<54:31,  1.62it/s]
 91%|█████████ | 52286/57600 [9:12:18<54:39,  1.62it/s]
 91%|█████████ | 52287/57600 [9:12:19<55:03,  1.61it/s]
 91%|█████████ | 52288/57600 [9:12:19<53:44,  1.65it/s]
 91%|█████████ | 52289/57600 [9:12:20<53:14,  1.66it/s]
 91%|█████████ | 52290/57600 [9:12:21<54:51,  1.61it/s]
 91%|█████████ | 52291/57600 [9:12:21<55:34,  1.59it/s]
 91%|█████████ | 52292/57600 [9:12:22<53:51,  1.64it/s]
 91%|█████████ | 52293/57600 [9:12:22<52:44,  1.68it/s]
 91%|█████████ | 52294/57600 [9:12:23<53:26,  1.65it/s]
 91%|█████████ | 52295/57600 [9:12:24<54:36,  1.62it/s]
 91%|█████████ | 52296/57600 [9:12:24<55:20,  1.60it/s]
 91%|█████████ | 52297/57600 [9:12:25<56:16,  1.57it/s]
 91%|█████████ | 52298/57600 [9:12:26<57:50,  1.53it/s]
 91%|█████████ | 52299/57600 [9:12:26<56:29,  1.56it/s]
 91%|█████████ | 52300/57600 [9:12:27<55:25,  1.59it/s]
                                                       
{'loss': 1.1053, 'learning_rate': 1.8310104529616726e-07, 'epoch': 577.26}

 91%|█████████ | 52300/57600 [9:12:27<55:25,  1.59it/s]
 91%|█████████ | 52301/57600 [9:12:28<55:24,  1.59it/s]
 91%|█████████ | 52302/57600 [9:12:28<56:03,  1.58it/s]
 91%|█████████ | 52303/57600 [9:12:29<55:54,  1.58it/s]
 91%|█████████ | 52304/57600 [9:12:29<55:03,  1.60it/s]
 91%|█████████ | 52305/57600 [9:12:30<54:45,  1.61it/s]
 91%|█████████ | 52306/57600 [9:12:31<53:23,  1.65it/s]
 91%|█████████ | 52307/57600 [9:12:31<52:34,  1.68it/s]
 91%|█████████ | 52308/57600 [9:12:32<52:10,  1.69it/s]
 91%|█████████ | 52309/57600 [9:12:32<52:24,  1.68it/s]
 91%|█████████ | 52310/57600 [9:12:33<52:29,  1.68it/s]
 91%|█████████ | 52311/57600 [9:12:34<55:17,  1.59it/s]
 91%|█████████ | 52312/57600 [9:12:34<56:21,  1.56it/s]
 91%|█████████ | 52313/57600 [9:12:35<55:42,  1.58it/s]
 91%|█████████ | 52314/57600 [9:12:36<55:51,  1.58it/s]
 91%|█████████ | 52315/57600 [9:12:36<55:49,  1.58it/s]
 91%|█████████ | 52316/57600 [9:12:37<55:07,  1.60it/s]
 91%|█████████ | 52317/57600 [9:12:38<57:25,  1.53it/s]
 91%|█████████ | 52318/57600 [9:12:38<56:00,  1.57it/s]
 91%|█████████ | 52319/57600 [9:12:39<53:59,  1.63it/s]
 91%|█████████ | 52320/57600 [9:12:39<53:10,  1.65it/s]
                                                       
{'loss': 1.0868, 'learning_rate': 1.8278745644599296e-07, 'epoch': 577.48}

 91%|█████████ | 52320/57600 [9:12:39<53:10,  1.65it/s]
 91%|█████████ | 52321/57600 [9:12:40<52:59,  1.66it/s]
 91%|█████████ | 52322/57600 [9:12:41<54:58,  1.60it/s]
 91%|█████████ | 52323/57600 [9:12:41<53:14,  1.65it/s]
 91%|█████████ | 52324/57600 [9:12:42<52:36,  1.67it/s]
 91%|█████████ | 52325/57600 [9:12:42<55:28,  1.58it/s]
 91%|█████████ | 52326/57600 [9:12:43<54:41,  1.61it/s]
 91%|█████████ | 52327/57600 [9:12:44<54:36,  1.61it/s]
 91%|█████████ | 52328/57600 [9:12:44<53:10,  1.65it/s]
 91%|█████████ | 52329/57600 [9:12:45<51:42,  1.70it/s]
 91%|█████████ | 52330/57600 [9:12:45<51:01,  1.72it/s]
 91%|█████████ | 52331/57600 [9:12:46<52:52,  1.66it/s]
 91%|█████████ | 52332/57600 [9:12:47<53:08,  1.65it/s]
 91%|█████████ | 52333/57600 [9:12:47<53:38,  1.64it/s]
 91%|█████████ | 52334/57600 [9:12:48<53:57,  1.63it/s]
 91%|█████████ | 52335/57600 [9:12:49<55:22,  1.58it/s]
 91%|█████████ | 52336/57600 [9:12:49<57:06,  1.54it/s]
 91%|█████████ | 52337/57600 [9:12:50<55:04,  1.59it/s]
 91%|█████████ | 52338/57600 [9:12:50<52:56,  1.66it/s]
 91%|█████████ | 52339/57600 [9:12:51<51:55,  1.69it/s]
 91%|█████████ | 52340/57600 [9:12:52<51:46,  1.69it/s]
                                                       
{'loss': 1.1151, 'learning_rate': 1.8247386759581882e-07, 'epoch': 577.7}

 91%|█████████ | 52340/57600 [9:12:52<51:46,  1.69it/s]
 91%|█████████ | 52341/57600 [9:12:52<53:25,  1.64it/s]
 91%|█████████ | 52342/57600 [9:12:53<53:12,  1.65it/s]
 91%|█████████ | 52343/57600 [9:12:53<55:03,  1.59it/s]
 91%|█████████ | 52344/57600 [9:12:54<54:31,  1.61it/s]
 91%|█████████ | 52345/57600 [9:12:55<54:37,  1.60it/s]
 91%|█████████ | 52346/57600 [9:12:55<53:38,  1.63it/s]
 91%|█████████ | 52347/57600 [9:12:56<53:48,  1.63it/s]
 91%|█████████ | 52348/57600 [9:12:57<55:39,  1.57it/s]
 91%|█████████ | 52349/57600 [9:12:57<55:45,  1.57it/s]
 91%|█████████ | 52350/57600 [9:12:58<58:52,  1.49it/s]
 91%|█████████ | 52351/57600 [9:12:59<58:46,  1.49it/s]
 91%|█████████ | 52352/57600 [9:12:59<57:09,  1.53it/s]
 91%|█████████ | 52353/57600 [9:13:00<54:17,  1.61it/s]
 91%|█████████ | 52354/57600 [9:13:00<55:38,  1.57it/s]
 91%|█████████ | 52355/57600 [9:13:01<55:27,  1.58it/s]
 91%|█████████ | 52356/57600 [9:13:02<57:32,  1.52it/s]
 91%|█████████ | 52357/57600 [9:13:02<56:35,  1.54it/s]
 91%|█████████ | 52358/57600 [9:13:03<57:08,  1.53it/s]
 91%|█████████ | 52359/57600 [9:13:04<57:50,  1.51it/s]
 91%|█████████ | 52360/57600 [9:13:04<55:53,  1.56it/s]
                                                       
{'loss': 1.0612, 'learning_rate': 1.8216027874564463e-07, 'epoch': 577.92}

 91%|█████████ | 52360/57600 [9:13:04<55:53,  1.56it/s]
 91%|█████████ | 52361/57600 [9:13:05<55:54,  1.56it/s]
 91%|█████████ | 52362/57600 [9:13:06<55:54,  1.56it/s]
 91%|█████████ | 52363/57600 [9:13:06<55:48,  1.56it/s]
 91%|█████████ | 52364/57600 [9:13:07<54:11,  1.61it/s]
 91%|█████████ | 52365/57600 [9:13:08<54:28,  1.60it/s]
 91%|█████████ | 52366/57600 [9:13:08<53:03,  1.64it/s]
 91%|█████████ | 52367/57600 [9:13:09<54:55,  1.59it/s]
 91%|█████████ | 52368/57600 [9:13:09<53:34,  1.63it/s]
 91%|█████████ | 52369/57600 [9:13:10<54:02,  1.61it/s]
 91%|█████████ | 52370/57600 [9:13:11<54:44,  1.59it/s]
 91%|█████████ | 52371/57600 [9:13:11<54:42,  1.59it/s]
 91%|█████████ | 52372/57600 [9:13:12<54:12,  1.61it/s]
 91%|█████████ | 52373/57600 [9:13:12<54:02,  1.61it/s]
 91%|█████████ | 52374/57600 [9:13:13<55:33,  1.57it/s]
 91%|█████████ | 52375/57600 [9:13:14<55:38,  1.57it/s]
 91%|█████████ | 52376/57600 [9:13:14<54:51,  1.59it/s]
 91%|█████████ | 52377/57600 [9:13:15<55:18,  1.57it/s]
 91%|█████████ | 52378/57600 [9:13:16<54:47,  1.59it/s]
 91%|█████████ | 52379/57600 [9:13:16<54:50,  1.59it/s]
 91%|█████████ | 52380/57600 [9:13:17<53:47,  1.62it/s]
                                                       
{'loss': 1.1311, 'learning_rate': 1.8184668989547038e-07, 'epoch': 578.15}

 91%|█████████ | 52380/57600 [9:13:17<53:47,  1.62it/s]
 91%|█████████ | 52381/57600 [9:13:17<53:45,  1.62it/s]
 91%|█████████ | 52382/57600 [9:13:18<53:03,  1.64it/s]
 91%|█████████ | 52383/57600 [9:13:19<53:17,  1.63it/s]
 91%|█████████ | 52384/57600 [9:13:19<52:04,  1.67it/s]
 91%|█████████ | 52385/57600 [9:13:20<51:32,  1.69it/s]
 91%|█████████ | 52386/57600 [9:13:20<52:12,  1.66it/s]
 91%|█████████ | 52387/57600 [9:13:21<50:37,  1.72it/s]
 91%|█████████ | 52388/57600 [9:13:22<51:12,  1.70it/s]
 91%|█████████ | 52389/57600 [9:13:22<53:56,  1.61it/s]
 91%|█████████ | 52390/57600 [9:13:23<53:53,  1.61it/s]
 91%|█████████ | 52391/57600 [9:13:24<55:03,  1.58it/s]
 91%|█████████ | 52392/57600 [9:13:24<53:59,  1.61it/s]
 91%|█████████ | 52393/57600 [9:13:25<53:24,  1.62it/s]
 91%|█████████ | 52394/57600 [9:13:25<53:13,  1.63it/s]
 91%|█████████ | 52395/57600 [9:13:26<53:19,  1.63it/s]
 91%|█████████ | 52396/57600 [9:13:27<52:39,  1.65it/s]
 91%|█████████ | 52397/57600 [9:13:27<52:07,  1.66it/s]
 91%|█████████ | 52398/57600 [9:13:28<52:12,  1.66it/s]
 91%|█████████ | 52399/57600 [9:13:28<54:02,  1.60it/s]
 91%|█████████ | 52400/57600 [9:13:29<53:52,  1.61it/s]
                                                       
{'loss': 1.1418, 'learning_rate': 1.8153310104529618e-07, 'epoch': 578.37}

 91%|█████████ | 52400/57600 [9:13:29<53:52,  1.61it/s]
 91%|█████████ | 52401/57600 [9:13:30<54:08,  1.60it/s]
 91%|█████████ | 52402/57600 [9:13:30<52:28,  1.65it/s]
 91%|█████████ | 52403/57600 [9:13:31<52:10,  1.66it/s]
 91%|█████████ | 52404/57600 [9:13:32<53:39,  1.61it/s]
 91%|█████████ | 52405/57600 [9:13:32<53:18,  1.62it/s]
 91%|█████████ | 52406/57600 [9:13:33<53:24,  1.62it/s]
 91%|█████████ | 52407/57600 [9:13:33<52:57,  1.63it/s]
 91%|█████████ | 52408/57600 [9:13:34<51:38,  1.68it/s]
 91%|█████████ | 52409/57600 [9:13:35<51:47,  1.67it/s]
 91%|█████████ | 52410/57600 [9:13:35<55:25,  1.56it/s]
 91%|█████████ | 52411/57600 [9:13:36<54:21,  1.59it/s]
 91%|█████████ | 52412/57600 [9:13:36<54:03,  1.60it/s]
 91%|█████████ | 52413/57600 [9:13:37<52:32,  1.65it/s]
 91%|█████████ | 52414/57600 [9:13:38<53:04,  1.63it/s]
 91%|█████████ | 52415/57600 [9:13:38<53:06,  1.63it/s]
 91%|█████████ | 52416/57600 [9:13:39<54:56,  1.57it/s]
 91%|█████████ | 52417/57600 [9:13:40<54:18,  1.59it/s]
 91%|█████████ | 52418/57600 [9:13:40<54:12,  1.59it/s]
 91%|█████████ | 52419/57600 [9:13:41<54:17,  1.59it/s]
 91%|█████████ | 52420/57600 [9:13:42<55:00,  1.57it/s]
                                                       
{'loss': 1.0929, 'learning_rate': 1.8121951219512193e-07, 'epoch': 578.59}

 91%|█████████ | 52420/57600 [9:13:42<55:00,  1.57it/s]
 91%|█████████ | 52421/57600 [9:13:42<53:11,  1.62it/s]
 91%|█████████ | 52422/57600 [9:13:43<53:56,  1.60it/s]
 91%|█████████ | 52423/57600 [9:13:43<52:29,  1.64it/s]
 91%|█████████ | 52424/57600 [9:13:44<54:12,  1.59it/s]
 91%|█████████ | 52425/57600 [9:13:45<54:27,  1.58it/s]
 91%|█████████ | 52426/57600 [9:13:45<52:58,  1.63it/s]
 91%|█████████ | 52427/57600 [9:13:46<53:23,  1.61it/s]
 91%|█████████ | 52428/57600 [9:13:46<52:10,  1.65it/s]
 91%|█████████ | 52429/57600 [9:13:47<51:34,  1.67it/s]
 91%|█████████ | 52430/57600 [9:13:48<50:06,  1.72it/s]
 91%|█████████ | 52431/57600 [9:13:48<51:04,  1.69it/s]
 91%|█████████ | 52432/57600 [9:13:49<50:28,  1.71it/s]
 91%|█████████ | 52433/57600 [9:13:49<52:53,  1.63it/s]
 91%|█████████ | 52434/57600 [9:13:50<55:06,  1.56it/s]
 91%|█████████ | 52435/57600 [9:13:51<54:03,  1.59it/s]
 91%|█████████ | 52436/57600 [9:13:51<52:51,  1.63it/s]
 91%|█████████ | 52437/57600 [9:13:52<52:10,  1.65it/s]
 91%|█████████ | 52438/57600 [9:13:52<51:41,  1.66it/s]
 91%|█████████ | 52439/57600 [9:13:53<53:25,  1.61it/s]
 91%|█████████ | 52440/57600 [9:13:54<53:36,  1.60it/s]
                                                       
{'loss': 1.1356, 'learning_rate': 1.8090592334494777e-07, 'epoch': 578.81}

 91%|█████████ | 52440/57600 [9:13:54<53:36,  1.60it/s]
 91%|█████████ | 52441/57600 [9:13:54<53:34,  1.61it/s]
 91%|█████████ | 52442/57600 [9:13:55<55:02,  1.56it/s]
 91%|█████████ | 52443/57600 [9:13:56<56:39,  1.52it/s]
 91%|█████████ | 52444/57600 [9:13:56<56:42,  1.52it/s]
 91%|█████████ | 52445/57600 [9:13:57<55:26,  1.55it/s]
 91%|█████████ | 52446/57600 [9:13:58<53:19,  1.61it/s]
 91%|█████████ | 52447/57600 [9:13:58<53:36,  1.60it/s]
 91%|█████████ | 52448/57600 [9:13:59<53:15,  1.61it/s]
 91%|█████████ | 52449/57600 [9:13:59<54:09,  1.59it/s]
 91%|█████████ | 52450/57600 [9:14:00<53:02,  1.62it/s]
 91%|█████████ | 52451/57600 [9:14:01<54:42,  1.57it/s]
 91%|█████████ | 52452/57600 [9:14:01<55:03,  1.56it/s]
 91%|█████████ | 52453/57600 [9:14:02<53:55,  1.59it/s]
 91%|█████████ | 52454/57600 [9:14:03<52:45,  1.63it/s]
 91%|█████████ | 52455/57600 [9:14:03<52:00,  1.65it/s]
 91%|█████████ | 52456/57600 [9:14:04<52:04,  1.65it/s]
 91%|█████████ | 52457/57600 [9:14:04<52:43,  1.63it/s]
 91%|█████████ | 52458/57600 [9:14:05<55:13,  1.55it/s]
 91%|█████████ | 52459/57600 [9:14:06<53:29,  1.60it/s]
 91%|█████████ | 52460/57600 [9:14:06<54:09,  1.58it/s]
                                                       
{'loss': 1.0934, 'learning_rate': 1.8059233449477347e-07, 'epoch': 579.03}

 91%|█████████ | 52460/57600 [9:14:06<54:09,  1.58it/s]
 91%|█████████ | 52461/57600 [9:14:07<54:32,  1.57it/s]
 91%|█████████ | 52462/57600 [9:14:08<54:37,  1.57it/s]
 91%|█████████ | 52463/57600 [9:14:08<55:42,  1.54it/s]
 91%|█████████ | 52464/57600 [9:14:09<55:31,  1.54it/s]
 91%|█████████ | 52465/57600 [9:14:10<55:03,  1.55it/s]
 91%|█████████ | 52466/57600 [9:14:10<55:17,  1.55it/s]
 91%|█████████ | 52467/57600 [9:14:11<55:53,  1.53it/s]
 91%|█████████ | 52468/57600 [9:14:12<54:34,  1.57it/s]
 91%|█████████ | 52469/57600 [9:14:12<53:00,  1.61it/s]
 91%|█████████ | 52470/57600 [9:14:13<53:47,  1.59it/s]
 91%|█████████ | 52471/57600 [9:14:13<54:03,  1.58it/s]
 91%|█████████ | 52472/57600 [9:14:14<52:02,  1.64it/s]
 91%|█████████ | 52473/57600 [9:14:14<50:10,  1.70it/s]
 91%|█████████ | 52474/57600 [9:14:15<50:44,  1.68it/s]
 91%|█████████ | 52475/57600 [9:14:16<52:20,  1.63it/s]
 91%|█████████ | 52476/57600 [9:14:16<53:33,  1.59it/s]
 91%|█████████ | 52477/57600 [9:14:17<53:07,  1.61it/s]
 91%|█████████ | 52478/57600 [9:14:18<54:00,  1.58it/s]
 91%|█████████ | 52479/57600 [9:14:18<53:01,  1.61it/s]
 91%|█████████ | 52480/57600 [9:14:19<52:22,  1.63it/s]
                                                       
{'loss': 1.0882, 'learning_rate': 1.802787456445993e-07, 'epoch': 579.25}

 91%|█████████ | 52480/57600 [9:14:19<52:22,  1.63it/s]
 91%|█████████ | 52481/57600 [9:14:20<53:33,  1.59it/s]
 91%|█████████ | 52482/57600 [9:14:20<55:37,  1.53it/s]
 91%|█████████ | 52483/57600 [9:14:21<54:00,  1.58it/s]
 91%|█████████ | 52484/57600 [9:14:21<53:35,  1.59it/s]
 91%|█████████ | 52485/57600 [9:14:22<53:17,  1.60it/s]
 91%|█████████ | 52486/57600 [9:14:23<52:29,  1.62it/s]
 91%|█████████ | 52487/57600 [9:14:23<51:58,  1.64it/s]
 91%|█████████ | 52488/57600 [9:14:24<51:50,  1.64it/s]
 91%|█████████ | 52489/57600 [9:14:24<52:36,  1.62it/s]
 91%|█████████ | 52490/57600 [9:14:25<53:03,  1.61it/s]
 91%|█████████ | 52491/57600 [9:14:26<52:05,  1.63it/s]
 91%|█████████ | 52492/57600 [9:14:26<53:09,  1.60it/s]
 91%|█████████ | 52493/57600 [9:14:27<51:45,  1.64it/s]
 91%|█████████ | 52494/57600 [9:14:28<51:02,  1.67it/s]
 91%|█████████ | 52495/57600 [9:14:28<50:41,  1.68it/s]
 91%|█████████ | 52496/57600 [9:14:29<52:28,  1.62it/s]
 91%|█████████ | 52497/57600 [9:14:29<52:54,  1.61it/s]
 91%|█████████ | 52498/57600 [9:14:30<51:40,  1.65it/s]
 91%|█████████ | 52499/57600 [9:14:31<51:17,  1.66it/s]
 91%|█████████ | 52500/57600 [9:14:31<51:31,  1.65it/s]
                                                       
{'loss': 1.1207, 'learning_rate': 1.7996515679442513e-07, 'epoch': 579.47}

 91%|█████████ | 52500/57600 [9:14:31<51:31,  1.65it/s]
 91%|█████████ | 52501/57600 [9:14:32<51:19,  1.66it/s]
 91%|█████████ | 52502/57600 [9:14:32<51:55,  1.64it/s]
 91%|█████████ | 52503/57600 [9:14:33<51:51,  1.64it/s]
 91%|█████████ | 52504/57600 [9:14:34<50:27,  1.68it/s]
 91%|█████████ | 52505/57600 [9:14:34<50:32,  1.68it/s]
 91%|█████████ | 52506/57600 [9:14:35<50:59,  1.66it/s]
 91%|█████████ | 52507/57600 [9:14:35<51:36,  1.64it/s]
 91%|█████████ | 52508/57600 [9:14:36<52:13,  1.62it/s]
 91%|█████████ | 52509/57600 [9:14:37<52:27,  1.62it/s]
 91%|█████████ | 52510/57600 [9:14:37<51:03,  1.66it/s]
 91%|█████████ | 52511/57600 [9:14:38<50:03,  1.69it/s]
 91%|█████████ | 52512/57600 [9:14:38<50:58,  1.66it/s]
 91%|█████████ | 52513/57600 [9:14:39<51:11,  1.66it/s]
 91%|█████████ | 52514/57600 [9:14:40<53:15,  1.59it/s]
 91%|█████████ | 52515/57600 [9:14:40<53:33,  1.58it/s]
 91%|█████████ | 52516/57600 [9:14:41<53:57,  1.57it/s]
 91%|█████████ | 52517/57600 [9:14:42<54:06,  1.57it/s]
 91%|█████████ | 52518/57600 [9:14:42<53:56,  1.57it/s]
 91%|█████████ | 52519/57600 [9:14:43<53:41,  1.58it/s]
 91%|█████████ | 52520/57600 [9:14:44<57:22,  1.48it/s]
                                                       
{'loss': 1.1195, 'learning_rate': 1.7965156794425085e-07, 'epoch': 579.69}

 91%|█████████ | 52520/57600 [9:14:44<57:22,  1.48it/s]
 91%|█████████ | 52521/57600 [9:14:44<54:53,  1.54it/s]
 91%|█████████ | 52522/57600 [9:14:45<53:06,  1.59it/s]
 91%|█████████ | 52523/57600 [9:14:46<54:35,  1.55it/s]
 91%|█████████ | 52524/57600 [9:14:46<57:00,  1.48it/s]
 91%|█████████ | 52525/57600 [9:14:47<55:00,  1.54it/s]
 91%|█████████ | 52526/57600 [9:14:48<55:02,  1.54it/s]
 91%|█████████ | 52527/57600 [9:14:48<54:02,  1.56it/s]
 91%|█████████ | 52528/57600 [9:14:49<52:47,  1.60it/s]
 91%|█████████ | 52529/57600 [9:14:49<52:47,  1.60it/s]
 91%|█████████ | 52530/57600 [9:14:50<52:29,  1.61it/s]
 91%|█████████ | 52531/57600 [9:14:51<54:54,  1.54it/s]
 91%|█████████ | 52532/57600 [9:14:51<52:38,  1.60it/s]
 91%|█████████ | 52533/57600 [9:14:52<53:10,  1.59it/s]
 91%|█████████ | 52534/57600 [9:14:52<52:53,  1.60it/s]
 91%|█████████ | 52535/57600 [9:14:53<52:28,  1.61it/s]
 91%|█████████ | 52536/57600 [9:14:54<53:33,  1.58it/s]
 91%|█████████ | 52537/57600 [9:14:54<51:38,  1.63it/s]
 91%|█████████ | 52538/57600 [9:14:55<51:20,  1.64it/s]
 91%|█████████ | 52539/57600 [9:14:56<51:59,  1.62it/s]
 91%|█████████ | 52540/57600 [9:14:56<51:59,  1.62it/s]
                                                       
{'loss': 1.1226, 'learning_rate': 1.7933797909407666e-07, 'epoch': 579.91}

 91%|█████████ | 52540/57600 [9:14:56<51:59,  1.62it/s]
 91%|█████████ | 52541/57600 [9:14:57<51:26,  1.64it/s]
 91%|█████████ | 52542/57600 [9:14:57<51:51,  1.63it/s]
 91%|█████████ | 52543/57600 [9:14:58<50:51,  1.66it/s]
 91%|█████████ | 52544/57600 [9:14:59<49:20,  1.71it/s]
 91%|█████████ | 52545/57600 [9:14:59<49:02,  1.72it/s]
 91%|█████████ | 52546/57600 [9:15:00<49:55,  1.69it/s]
 91%|█████████ | 52547/57600 [9:15:00<48:59,  1.72it/s]
 91%|█████████ | 52548/57600 [9:15:01<49:50,  1.69it/s]
 91%|█████████ | 52549/57600 [9:15:02<52:15,  1.61it/s]
 91%|█████████ | 52550/57600 [9:15:02<51:49,  1.62it/s]
 91%|█████████ | 52551/57600 [9:15:03<52:14,  1.61it/s]
 91%|█████████ | 52552/57600 [9:15:03<51:49,  1.62it/s]
 91%|█████████ | 52553/57600 [9:15:04<51:15,  1.64it/s]
 91%|█████████ | 52554/57600 [9:15:05<53:20,  1.58it/s]
 91%|█████████ | 52555/57600 [9:15:05<51:43,  1.63it/s]
 91%|█████████ | 52556/57600 [9:15:06<52:01,  1.62it/s]
 91%|█████████ | 52557/57600 [9:15:07<51:48,  1.62it/s]
 91%|█████████ | 52558/57600 [9:15:07<52:31,  1.60it/s]
 91%|█████████ | 52559/57600 [9:15:08<53:22,  1.57it/s]
 91%|█████████▏| 52560/57600 [9:15:08<53:11,  1.58it/s]
                                                       
{'loss': 1.1015, 'learning_rate': 1.7902439024390244e-07, 'epoch': 580.13}

 91%|█████████▏| 52560/57600 [9:15:08<53:11,  1.58it/s]
 91%|█████████▏| 52561/57600 [9:15:09<52:25,  1.60it/s]
 91%|█████████▏| 52562/57600 [9:15:10<54:04,  1.55it/s]
 91%|█████████▏| 52563/57600 [9:15:10<52:48,  1.59it/s]
 91%|█████████▏| 52564/57600 [9:15:11<51:39,  1.62it/s]
 91%|█████████▏| 52565/57600 [9:15:12<50:57,  1.65it/s]
 91%|█████████▏| 52566/57600 [9:15:12<52:17,  1.60it/s]
 91%|█████████▏| 52567/57600 [9:15:13<51:06,  1.64it/s]
 91%|█████████▏| 52568/57600 [9:15:13<50:12,  1.67it/s]
 91%|█████████▏| 52569/57600 [9:15:14<51:07,  1.64it/s]
 91%|█████████▏| 52570/57600 [9:15:15<51:18,  1.63it/s]
 91%|█████████▏| 52571/57600 [9:15:15<51:23,  1.63it/s]
 91%|█████████▏| 52572/57600 [9:15:16<51:40,  1.62it/s]
 91%|█████████▏| 52573/57600 [9:15:16<50:43,  1.65it/s]
 91%|█████████▏| 52574/57600 [9:15:17<53:18,  1.57it/s]
 91%|█████████▏| 52575/57600 [9:15:18<52:21,  1.60it/s]
 91%|█████████▏| 52576/57600 [9:15:18<51:05,  1.64it/s]
 91%|█████████▏| 52577/57600 [9:15:19<49:42,  1.68it/s]
 91%|█████████▏| 52578/57600 [9:15:19<49:41,  1.68it/s]
 91%|█████████▏| 52579/57600 [9:15:20<49:55,  1.68it/s]
 91%|█████████▏| 52580/57600 [9:15:21<53:09,  1.57it/s]
                                                       
{'loss': 1.1166, 'learning_rate': 1.7871080139372821e-07, 'epoch': 580.35}

 91%|█████████▏| 52580/57600 [9:15:21<53:09,  1.57it/s]
 91%|█████████▏| 52581/57600 [9:15:21<53:24,  1.57it/s]
 91%|█████████▏| 52582/57600 [9:15:22<52:16,  1.60it/s]
 91%|█████████▏| 52583/57600 [9:15:23<52:10,  1.60it/s]
 91%|█████████▏| 52584/57600 [9:15:23<54:03,  1.55it/s]
 91%|█████████▏| 52585/57600 [9:15:24<52:53,  1.58it/s]
 91%|█████████▏| 52586/57600 [9:15:24<50:57,  1.64it/s]
 91%|█████████▏| 52587/57600 [9:15:25<51:33,  1.62it/s]
 91%|█████████▏| 52588/57600 [9:15:26<50:11,  1.66it/s]
 91%|█████████▏| 52589/57600 [9:15:26<51:45,  1.61it/s]
 91%|█████████▏| 52590/57600 [9:15:27<50:47,  1.64it/s]
 91%|█████████▏| 52591/57600 [9:15:28<51:52,  1.61it/s]
 91%|█████████▏| 52592/57600 [9:15:28<50:47,  1.64it/s]
 91%|█████████▏| 52593/57600 [9:15:29<51:18,  1.63it/s]
 91%|█████████▏| 52594/57600 [9:15:29<52:24,  1.59it/s]
 91%|█████████▏| 52595/57600 [9:15:30<52:57,  1.57it/s]
 91%|█████████▏| 52596/57600 [9:15:31<52:00,  1.60it/s]
 91%|█████████▏| 52597/57600 [9:15:31<52:08,  1.60it/s]
 91%|█████████▏| 52598/57600 [9:15:32<51:31,  1.62it/s]
 91%|█████████▏| 52599/57600 [9:15:33<52:10,  1.60it/s]
 91%|█████████▏| 52600/57600 [9:15:33<52:05,  1.60it/s]
                                                       
{'loss': 1.0993, 'learning_rate': 1.7839721254355397e-07, 'epoch': 580.57}

 91%|█████████▏| 52600/57600 [9:15:33<52:05,  1.60it/s]
 91%|█████████▏| 52601/57600 [9:15:34<50:40,  1.64it/s]
 91%|█████████▏| 52602/57600 [9:15:34<49:52,  1.67it/s]
 91%|█████████▏| 52603/57600 [9:15:35<49:04,  1.70it/s]
 91%|█████████▏| 52604/57600 [9:15:36<49:47,  1.67it/s]
 91%|█████████▏| 52605/57600 [9:15:36<50:19,  1.65it/s]
 91%|█████████▏| 52606/57600 [9:15:37<50:02,  1.66it/s]
 91%|█████████▏| 52607/57600 [9:15:37<50:20,  1.65it/s]
 91%|█████████▏| 52608/57600 [9:15:38<50:43,  1.64it/s]
 91%|█████████▏| 52609/57600 [9:15:39<49:12,  1.69it/s]
 91%|█████████▏| 52610/57600 [9:15:39<51:07,  1.63it/s]
 91%|█████████▏| 52611/57600 [9:15:40<51:42,  1.61it/s]
 91%|█████████▏| 52612/57600 [9:15:40<49:55,  1.66it/s]
 91%|█████████▏| 52613/57600 [9:15:41<50:20,  1.65it/s]
 91%|█████████▏| 52614/57600 [9:15:42<50:44,  1.64it/s]
 91%|█████████▏| 52615/57600 [9:15:42<51:19,  1.62it/s]
 91%|█████████▏| 52616/57600 [9:15:43<50:51,  1.63it/s]
 91%|█████████▏| 52617/57600 [9:15:43<51:34,  1.61it/s]
 91%|█████████▏| 52618/57600 [9:15:44<50:47,  1.63it/s]
 91%|█████████▏| 52619/57600 [9:15:45<50:08,  1.66it/s]
 91%|█████████▏| 52620/57600 [9:15:45<51:09,  1.62it/s]
                                                       
{'loss': 1.1292, 'learning_rate': 1.7808362369337977e-07, 'epoch': 580.79}

 91%|█████████▏| 52620/57600 [9:15:45<51:09,  1.62it/s]
 91%|█████████▏| 52621/57600 [9:15:46<51:21,  1.62it/s]
 91%|█████████▏| 52622/57600 [9:15:47<52:19,  1.59it/s]
 91%|█████████▏| 52623/57600 [9:15:47<50:55,  1.63it/s]
 91%|█████████▏| 52624/57600 [9:15:48<51:31,  1.61it/s]
 91%|█████████▏| 52625/57600 [9:15:48<51:11,  1.62it/s]
 91%|█████████▏| 52626/57600 [9:15:49<52:23,  1.58it/s]
 91%|█████████▏| 52627/57600 [9:15:50<52:50,  1.57it/s]
 91%|█████████▏| 52628/57600 [9:15:50<51:48,  1.60it/s]
 91%|█████████▏| 52629/57600 [9:15:51<53:17,  1.55it/s]
 91%|█████████▏| 52630/57600 [9:15:52<51:59,  1.59it/s]
 91%|█████████▏| 52631/57600 [9:15:52<53:22,  1.55it/s]
 91%|█████████▏| 52632/57600 [9:15:53<53:09,  1.56it/s]
 91%|█████████▏| 52633/57600 [9:15:54<55:12,  1.50it/s]
 91%|█████████▏| 52634/57600 [9:15:54<53:39,  1.54it/s]
 91%|█████████▏| 52635/57600 [9:15:55<54:38,  1.51it/s]
 91%|█████████▏| 52636/57600 [9:15:56<52:54,  1.56it/s]
 91%|█████████▏| 52637/57600 [9:15:56<51:37,  1.60it/s]
 91%|█████████▏| 52638/57600 [9:15:57<50:56,  1.62it/s]
 91%|█████████▏| 52639/57600 [9:15:57<52:17,  1.58it/s]
 91%|█████████▏| 52640/57600 [9:15:58<51:12,  1.61it/s]
                                                       
{'loss': 1.1396, 'learning_rate': 1.777700348432056e-07, 'epoch': 581.02}

 91%|█████████▏| 52640/57600 [9:15:58<51:12,  1.61it/s]
 91%|█████████▏| 52641/57600 [9:15:59<52:37,  1.57it/s]
 91%|█████████▏| 52642/57600 [9:15:59<51:28,  1.61it/s]
 91%|█████████▏| 52643/57600 [9:16:00<50:41,  1.63it/s]
 91%|█████████▏| 52644/57600 [9:16:00<50:38,  1.63it/s]
 91%|█████████▏| 52645/57600 [9:16:01<50:58,  1.62it/s]
 91%|█████████▏| 52646/57600 [9:16:02<49:39,  1.66it/s]
 91%|█████████▏| 52647/57600 [9:16:02<49:59,  1.65it/s]
 91%|█████████▏| 52648/57600 [9:16:03<49:29,  1.67it/s]
 91%|█████████▏| 52649/57600 [9:16:03<49:34,  1.66it/s]
 91%|█████████▏| 52650/57600 [9:16:04<49:52,  1.65it/s]
 91%|█████████▏| 52651/57600 [9:16:05<49:35,  1.66it/s]
 91%|█████████▏| 52652/57600 [9:16:05<48:58,  1.68it/s]
 91%|█████████▏| 52653/57600 [9:16:06<51:21,  1.61it/s]
 91%|█████████▏| 52654/57600 [9:16:07<50:59,  1.62it/s]
 91%|█████████▏| 52655/57600 [9:16:07<49:51,  1.65it/s]
 91%|█████████▏| 52656/57600 [9:16:08<49:37,  1.66it/s]
 91%|█████████▏| 52657/57600 [9:16:08<52:26,  1.57it/s]
 91%|█████████▏| 52658/57600 [9:16:09<51:19,  1.60it/s]
 91%|█████████▏| 52659/57600 [9:16:10<49:57,  1.65it/s]
 91%|█████████▏| 52660/57600 [9:16:10<50:36,  1.63it/s]
                                                       
{'loss': 1.1004, 'learning_rate': 1.7745644599303133e-07, 'epoch': 581.24}

 91%|█████████▏| 52660/57600 [9:16:10<50:36,  1.63it/s]
 91%|█████████▏| 52661/57600 [9:16:11<53:23,  1.54it/s]
 91%|█████████▏| 52662/57600 [9:16:12<51:46,  1.59it/s]
 91%|█████████▏| 52663/57600 [9:16:12<51:09,  1.61it/s]
 91%|█████████▏| 52664/57600 [9:16:13<50:24,  1.63it/s]
 91%|█████████▏| 52665/57600 [9:16:13<48:47,  1.69it/s]
 91%|█████████▏| 52666/57600 [9:16:14<50:43,  1.62it/s]
 91%|█████████▏| 52667/57600 [9:16:15<51:13,  1.61it/s]
 91%|█████████▏| 52668/57600 [9:16:15<52:01,  1.58it/s]
 91%|█████████▏| 52669/57600 [9:16:16<53:27,  1.54it/s]
 91%|█████████▏| 52670/57600 [9:16:17<54:11,  1.52it/s]
 91%|█████████▏| 52671/57600 [9:16:17<54:11,  1.52it/s]
 91%|█████████▏| 52672/57600 [9:16:18<53:29,  1.54it/s]
 91%|█████████▏| 52673/57600 [9:16:18<51:44,  1.59it/s]
 91%|█████████▏| 52674/57600 [9:16:19<52:41,  1.56it/s]
 91%|█████████▏| 52675/57600 [9:16:20<53:27,  1.54it/s]
 91%|█████████▏| 52676/57600 [9:16:20<52:07,  1.57it/s]
 91%|█████████▏| 52677/57600 [9:16:21<51:35,  1.59it/s]
 91%|█████████▏| 52678/57600 [9:16:22<52:14,  1.57it/s]
 91%|█████████▏| 52679/57600 [9:16:22<50:48,  1.61it/s]
 91%|█████████▏| 52680/57600 [9:16:23<50:38,  1.62it/s]
                                                       
{'loss': 1.0889, 'learning_rate': 1.7714285714285716e-07, 'epoch': 581.46}

 91%|█████████▏| 52680/57600 [9:16:23<50:38,  1.62it/s]
 91%|█████████▏| 52681/57600 [9:16:23<50:17,  1.63it/s]
 91%|█████████▏| 52682/57600 [9:16:24<50:27,  1.62it/s]
 91%|█████████▏| 52683/57600 [9:16:25<51:21,  1.60it/s]
 91%|█████████▏| 52684/57600 [9:16:25<50:21,  1.63it/s]
 91%|█████████▏| 52685/57600 [9:16:26<50:53,  1.61it/s]
 91%|█████████▏| 52686/57600 [9:16:27<51:11,  1.60it/s]
 91%|█████████▏| 52687/57600 [9:16:27<51:36,  1.59it/s]
 91%|█████████▏| 52688/57600 [9:16:28<50:28,  1.62it/s]
 91%|█████████▏| 52689/57600 [9:16:28<49:43,  1.65it/s]
 91%|█████████▏| 52690/57600 [9:16:29<49:38,  1.65it/s]
 91%|█████████▏| 52691/57600 [9:16:30<47:57,  1.71it/s]
 91%|█████████▏| 52692/57600 [9:16:30<47:51,  1.71it/s]
 91%|█████████▏| 52693/57600 [9:16:31<48:15,  1.69it/s]
 91%|█████████▏| 52694/57600 [9:16:31<48:40,  1.68it/s]
 91%|█████████▏| 52695/57600 [9:16:32<48:56,  1.67it/s]
 91%|█████████▏| 52696/57600 [9:16:33<47:51,  1.71it/s]
 91%|█████████▏| 52697/57600 [9:16:33<48:30,  1.68it/s]
 91%|█████████▏| 52698/57600 [9:16:34<49:00,  1.67it/s]
 91%|█████████▏| 52699/57600 [9:16:34<50:32,  1.62it/s]
 91%|█████████▏| 52700/57600 [9:16:35<51:18,  1.59it/s]
                                                       
{'loss': 1.1348, 'learning_rate': 1.7682926829268289e-07, 'epoch': 581.68}

 91%|█████████▏| 52700/57600 [9:16:35<51:18,  1.59it/s]
 91%|█████████▏| 52701/57600 [9:16:36<50:54,  1.60it/s]
 91%|█████████▏| 52702/57600 [9:16:36<50:43,  1.61it/s]
 91%|█████████▏| 52703/57600 [9:16:37<51:51,  1.57it/s]
 92%|█████████▏| 52704/57600 [9:16:38<51:20,  1.59it/s]
 92%|█████████▏| 52705/57600 [9:16:38<49:34,  1.65it/s]
 92%|█████████▏| 52706/57600 [9:16:39<48:33,  1.68it/s]
 92%|█████████▏| 52707/57600 [9:16:39<51:18,  1.59it/s]
 92%|█████████▏| 52708/57600 [9:16:40<50:28,  1.62it/s]
 92%|█████████▏| 52709/57600 [9:16:41<50:45,  1.61it/s]
 92%|█████████▏| 52710/57600 [9:16:41<51:15,  1.59it/s]
 92%|█████████▏| 52711/57600 [9:16:42<51:39,  1.58it/s]
 92%|█████████▏| 52712/57600 [9:16:42<49:59,  1.63it/s]
 92%|█████████▏| 52713/57600 [9:16:43<52:30,  1.55it/s]
 92%|█████████▏| 52714/57600 [9:16:44<52:04,  1.56it/s]
 92%|█████████▏| 52715/57600 [9:16:44<51:19,  1.59it/s]
 92%|█████████▏| 52716/57600 [9:16:45<50:22,  1.62it/s]
 92%|█████████▏| 52717/57600 [9:16:46<49:41,  1.64it/s]
 92%|█████████▏| 52718/57600 [9:16:46<52:25,  1.55it/s]
 92%|█████████▏| 52719/57600 [9:16:47<52:43,  1.54it/s]
 92%|█████████▏| 52720/57600 [9:16:48<50:41,  1.60it/s]
                                                       
{'loss': 1.112, 'learning_rate': 1.7651567944250872e-07, 'epoch': 581.9}

 92%|█████████▏| 52720/57600 [9:16:48<50:41,  1.60it/s]
 92%|█████████▏| 52721/57600 [9:16:48<51:42,  1.57it/s]
 92%|█████████▏| 52722/57600 [9:16:49<52:22,  1.55it/s]
 92%|█████████▏| 52723/57600 [9:16:49<50:47,  1.60it/s]
 92%|█████████▏| 52724/57600 [9:16:50<50:08,  1.62it/s]
 92%|█████████▏| 52725/57600 [9:16:51<50:48,  1.60it/s]
 92%|█████████▏| 52726/57600 [9:16:51<50:19,  1.61it/s]
 92%|█████████▏| 52727/57600 [9:16:52<52:14,  1.55it/s]
 92%|█████████▏| 52728/57600 [9:16:53<52:23,  1.55it/s]
 92%|█████████▏| 52729/57600 [9:16:53<50:56,  1.59it/s]
 92%|█████████▏| 52730/57600 [9:16:54<52:45,  1.54it/s]
 92%|█████████▏| 52731/57600 [9:16:55<51:40,  1.57it/s]
 92%|█████████▏| 52732/57600 [9:16:55<51:46,  1.57it/s]
 92%|█████████▏| 52733/57600 [9:16:56<50:24,  1.61it/s]
 92%|█████████▏| 52734/57600 [9:16:56<49:32,  1.64it/s]
 92%|█████████▏| 52735/57600 [9:16:57<48:23,  1.68it/s]
 92%|█████████▏| 52736/57600 [9:16:58<48:39,  1.67it/s]
 92%|█████████▏| 52737/57600 [9:16:58<48:28,  1.67it/s]
 92%|█████████▏| 52738/57600 [9:16:59<48:24,  1.67it/s]
 92%|█████████▏| 52739/57600 [9:16:59<47:08,  1.72it/s]
 92%|█████████▏| 52740/57600 [9:17:00<47:16,  1.71it/s]
                                                       
{'loss': 1.0971, 'learning_rate': 1.7620209059233444e-07, 'epoch': 582.12}

 92%|█████████▏| 52740/57600 [9:17:00<47:16,  1.71it/s]
 92%|█████████▏| 52741/57600 [9:17:00<47:36,  1.70it/s]
 92%|█████████▏| 52742/57600 [9:17:01<50:10,  1.61it/s]
 92%|█████████▏| 52743/57600 [9:17:02<49:35,  1.63it/s]
 92%|█████████▏| 52744/57600 [9:17:02<49:07,  1.65it/s]
 92%|█████████▏| 52745/57600 [9:17:03<50:39,  1.60it/s]
 92%|█████████▏| 52746/57600 [9:17:04<49:47,  1.62it/s]
 92%|█████████▏| 52747/57600 [9:17:04<49:26,  1.64it/s]
 92%|█████████▏| 52748/57600 [9:17:05<48:11,  1.68it/s]
 92%|█████████▏| 52749/57600 [9:17:05<48:45,  1.66it/s]
 92%|█████████▏| 52750/57600 [9:17:06<48:50,  1.66it/s]
 92%|█████████▏| 52751/57600 [9:17:07<48:19,  1.67it/s]
 92%|█████████▏| 52752/57600 [9:17:07<48:27,  1.67it/s]
 92%|█████████▏| 52753/57600 [9:17:08<47:38,  1.70it/s]
 92%|█████████▏| 52754/57600 [9:17:08<51:24,  1.57it/s]
 92%|█████████▏| 52755/57600 [9:17:09<50:04,  1.61it/s]
 92%|█████████▏| 52756/57600 [9:17:10<50:57,  1.58it/s]
 92%|█████████▏| 52757/57600 [9:17:10<49:31,  1.63it/s]
 92%|█████████▏| 52758/57600 [9:17:11<49:51,  1.62it/s]
 92%|█████████▏| 52759/57600 [9:17:11<48:06,  1.68it/s]
 92%|█████████▏| 52760/57600 [9:17:12<49:12,  1.64it/s]
                                                       
{'loss': 1.1349, 'learning_rate': 1.7588850174216027e-07, 'epoch': 582.34}

 92%|█████████▏| 52760/57600 [9:17:12<49:12,  1.64it/s]
 92%|█████████▏| 52761/57600 [9:17:13<51:39,  1.56it/s]
 92%|█████████▏| 52762/57600 [9:17:13<51:24,  1.57it/s]
 92%|█████████▏| 52763/57600 [9:17:14<52:19,  1.54it/s]
 92%|█████████▏| 52764/57600 [9:17:15<51:19,  1.57it/s]
 92%|█████████▏| 52765/57600 [9:17:15<51:15,  1.57it/s]
 92%|█████████▏| 52766/57600 [9:17:16<50:18,  1.60it/s]
 92%|█████████▏| 52767/57600 [9:17:17<50:25,  1.60it/s]
 92%|█████████▏| 52768/57600 [9:17:17<50:22,  1.60it/s]
 92%|█████████▏| 52769/57600 [9:17:18<50:40,  1.59it/s]
 92%|█████████▏| 52770/57600 [9:17:18<50:20,  1.60it/s]
 92%|█████████▏| 52771/57600 [9:17:19<49:09,  1.64it/s]
 92%|█████████▏| 52772/57600 [9:17:20<49:16,  1.63it/s]
 92%|█████████▏| 52773/57600 [9:17:20<47:39,  1.69it/s]
 92%|█████████▏| 52774/57600 [9:17:21<47:28,  1.69it/s]
 92%|█████████▏| 52775/57600 [9:17:22<49:57,  1.61it/s]
 92%|█████████▏| 52776/57600 [9:17:22<50:23,  1.60it/s]
 92%|█████████▏| 52777/57600 [9:17:23<49:36,  1.62it/s]
 92%|█████████▏| 52778/57600 [9:17:23<49:22,  1.63it/s]
 92%|█████████▏| 52779/57600 [9:17:24<51:24,  1.56it/s]
 92%|█████████▏| 52780/57600 [9:17:25<51:43,  1.55it/s]
                                                       
{'loss': 1.0906, 'learning_rate': 1.755749128919861e-07, 'epoch': 582.56}

 92%|█████████▏| 52780/57600 [9:17:25<51:43,  1.55it/s]
 92%|█████████▏| 52781/57600 [9:17:25<51:10,  1.57it/s]
 92%|█████████▏| 52782/57600 [9:17:26<52:43,  1.52it/s]
 92%|█████████▏| 52783/57600 [9:17:27<50:56,  1.58it/s]
 92%|█████████▏| 52784/57600 [9:17:27<49:45,  1.61it/s]
 92%|█████████▏| 52785/57600 [9:17:28<49:08,  1.63it/s]
 92%|█████████▏| 52786/57600 [9:17:28<50:44,  1.58it/s]
 92%|█████████▏| 52787/57600 [9:17:29<50:14,  1.60it/s]
 92%|█████████▏| 52788/57600 [9:17:30<51:03,  1.57it/s]
 92%|█████████▏| 52789/57600 [9:17:30<52:00,  1.54it/s]
 92%|█████████▏| 52790/57600 [9:17:31<50:37,  1.58it/s]
 92%|█████████▏| 52791/57600 [9:17:32<50:35,  1.58it/s]
 92%|█████████▏| 52792/57600 [9:17:32<49:50,  1.61it/s]
 92%|█████████▏| 52793/57600 [9:17:33<48:20,  1.66it/s]
 92%|█████████▏| 52794/57600 [9:17:33<48:50,  1.64it/s]
 92%|█████████▏| 52795/57600 [9:17:34<48:10,  1.66it/s]
 92%|█████████▏| 52796/57600 [9:17:35<48:13,  1.66it/s]
 92%|█████████▏| 52797/57600 [9:17:35<47:42,  1.68it/s]
 92%|█████████▏| 52798/57600 [9:17:36<48:15,  1.66it/s]
 92%|█████████▏| 52799/57600 [9:17:36<50:24,  1.59it/s]
 92%|█████████▏| 52800/57600 [9:17:37<50:14,  1.59it/s]
                                                       
{'loss': 1.0945, 'learning_rate': 1.752613240418118e-07, 'epoch': 582.78}

 92%|█████████▏| 52800/57600 [9:17:37<50:14,  1.59it/s]
 92%|█████████▏| 52801/57600 [9:17:38<51:35,  1.55it/s]
 92%|█████████▏| 52802/57600 [9:17:38<51:39,  1.55it/s]
 92%|█████████▏| 52803/57600 [9:17:39<50:36,  1.58it/s]
 92%|█████████▏| 52804/57600 [9:17:40<49:50,  1.60it/s]
 92%|█████████▏| 52805/57600 [9:17:40<48:07,  1.66it/s]
 92%|█████████▏| 52806/57600 [9:17:41<48:33,  1.65it/s]
 92%|█████████▏| 52807/57600 [9:17:41<47:13,  1.69it/s]
 92%|█████████▏| 52808/57600 [9:17:42<49:19,  1.62it/s]
 92%|█████████▏| 52809/57600 [9:17:43<50:52,  1.57it/s]
 92%|█████████▏| 52810/57600 [9:17:43<50:01,  1.60it/s]
 92%|█████████▏| 52811/57600 [9:17:44<50:32,  1.58it/s]
 92%|█████████▏| 52812/57600 [9:17:45<49:26,  1.61it/s]
 92%|█████████▏| 52813/57600 [9:17:45<48:47,  1.64it/s]
 92%|█████████▏| 52814/57600 [9:17:46<48:22,  1.65it/s]
 92%|█████████▏| 52815/57600 [9:17:46<48:48,  1.63it/s]
 92%|█████████▏| 52816/57600 [9:17:47<48:52,  1.63it/s]
 92%|█████████▏| 52817/57600 [9:17:48<48:13,  1.65it/s]
 92%|█████████▏| 52818/57600 [9:17:48<47:53,  1.66it/s]
 92%|█████████▏| 52819/57600 [9:17:49<49:01,  1.63it/s]
 92%|█████████▏| 52820/57600 [9:17:50<50:44,  1.57it/s]
                                                       
{'loss': 1.1592, 'learning_rate': 1.7494773519163766e-07, 'epoch': 583.0}

 92%|█████████▏| 52820/57600 [9:17:50<50:44,  1.57it/s]
 92%|█████████▏| 52821/57600 [9:17:50<50:12,  1.59it/s]
 92%|█████████▏| 52822/57600 [9:17:51<50:06,  1.59it/s]
 92%|█████████▏| 52823/57600 [9:17:51<50:54,  1.56it/s]
 92%|█████████▏| 52824/57600 [9:17:52<50:03,  1.59it/s]
 92%|█████████▏| 52825/57600 [9:17:53<50:03,  1.59it/s]
 92%|█████████▏| 52826/57600 [9:17:53<49:28,  1.61it/s]
 92%|█████████▏| 52827/57600 [9:17:54<49:17,  1.61it/s]
 92%|█████████▏| 52828/57600 [9:17:54<48:58,  1.62it/s]
 92%|█████████▏| 52829/57600 [9:17:55<49:51,  1.59it/s]
 92%|█████████▏| 52830/57600 [9:17:56<50:57,  1.56it/s]
 92%|█████████▏| 52831/57600 [9:17:56<49:50,  1.59it/s]
 92%|█████████▏| 52832/57600 [9:17:57<49:29,  1.61it/s]
 92%|█████████▏| 52833/57600 [9:17:58<50:02,  1.59it/s]
 92%|█████████▏| 52834/57600 [9:17:58<50:40,  1.57it/s]
 92%|█████████▏| 52835/57600 [9:17:59<49:14,  1.61it/s]
 92%|█████████▏| 52836/57600 [9:18:00<48:49,  1.63it/s]
 92%|█████████▏| 52837/57600 [9:18:00<47:50,  1.66it/s]
 92%|█████████▏| 52838/57600 [9:18:01<48:33,  1.63it/s]
 92%|█████████▏| 52839/57600 [9:18:01<50:56,  1.56it/s]
 92%|█████████▏| 52840/57600 [9:18:02<50:03,  1.58it/s]
                                                       
{'loss': 1.1204, 'learning_rate': 1.7463414634146336e-07, 'epoch': 583.22}

 92%|█████████▏| 52840/57600 [9:18:02<50:03,  1.58it/s]
 92%|█████████▏| 52841/57600 [9:18:03<50:47,  1.56it/s]
 92%|█████████▏| 52842/57600 [9:18:03<50:43,  1.56it/s]
 92%|█████████▏| 52843/57600 [9:18:04<49:36,  1.60it/s]
 92%|█████████▏| 52844/57600 [9:18:05<48:40,  1.63it/s]
 92%|█████████▏| 52845/57600 [9:18:05<48:32,  1.63it/s]
 92%|█████████▏| 52846/57600 [9:18:06<48:10,  1.64it/s]
 92%|█████████▏| 52847/57600 [9:18:06<47:35,  1.66it/s]
 92%|█████████▏| 52848/57600 [9:18:07<47:37,  1.66it/s]
 92%|█████████▏| 52849/57600 [9:18:08<47:52,  1.65it/s]
 92%|█████████▏| 52850/57600 [9:18:08<48:10,  1.64it/s]
 92%|█████████▏| 52851/57600 [9:18:09<48:38,  1.63it/s]
 92%|█████████▏| 52852/57600 [9:18:09<47:14,  1.67it/s]
 92%|█████████▏| 52853/57600 [9:18:10<49:30,  1.60it/s]
 92%|█████████▏| 52854/57600 [9:18:11<49:18,  1.60it/s]
 92%|█████████▏| 52855/57600 [9:18:11<51:22,  1.54it/s]
 92%|█████████▏| 52856/57600 [9:18:12<49:37,  1.59it/s]
 92%|█████████▏| 52857/57600 [9:18:13<49:21,  1.60it/s]
 92%|█████████▏| 52858/57600 [9:18:13<49:16,  1.60it/s]
 92%|█████████▏| 52859/57600 [9:18:14<48:13,  1.64it/s]
 92%|█████████▏| 52860/57600 [9:18:14<49:21,  1.60it/s]
                                                       
{'loss': 1.1148, 'learning_rate': 1.7432055749128922e-07, 'epoch': 583.44}

 92%|█████████▏| 52860/57600 [9:18:14<49:21,  1.60it/s]
 92%|█████████▏| 52861/57600 [9:18:15<47:59,  1.65it/s]
 92%|█████████▏| 52862/57600 [9:18:16<48:55,  1.61it/s]
 92%|█████████▏| 52863/57600 [9:18:16<49:20,  1.60it/s]
 92%|█████████▏| 52864/57600 [9:18:17<49:23,  1.60it/s]
 92%|█████████▏| 52865/57600 [9:18:18<49:34,  1.59it/s]
 92%|█████████▏| 52866/57600 [9:18:18<49:12,  1.60it/s]
 92%|█████████▏| 52867/57600 [9:18:19<49:23,  1.60it/s]
 92%|█████████▏| 52868/57600 [9:18:19<50:37,  1.56it/s]
 92%|█████████▏| 52869/57600 [9:18:20<48:49,  1.61it/s]
 92%|█████████▏| 52870/57600 [9:18:21<50:05,  1.57it/s]
 92%|█████████▏| 52871/57600 [9:18:21<50:35,  1.56it/s]
 92%|█████████▏| 52872/57600 [9:18:22<48:42,  1.62it/s]
 92%|█████████▏| 52873/57600 [9:18:23<48:43,  1.62it/s]
 92%|█████████▏| 52874/57600 [9:18:23<47:51,  1.65it/s]
 92%|█████████▏| 52875/57600 [9:18:24<47:33,  1.66it/s]
 92%|█████████▏| 52876/57600 [9:18:24<47:06,  1.67it/s]
 92%|█████████▏| 52877/57600 [9:18:25<46:07,  1.71it/s]
 92%|█████████▏| 52878/57600 [9:18:26<48:20,  1.63it/s]
 92%|█████████▏| 52879/57600 [9:18:26<48:43,  1.62it/s]
 92%|█████████▏| 52880/57600 [9:18:27<49:35,  1.59it/s]
                                                       
{'loss': 1.1213, 'learning_rate': 1.7400696864111492e-07, 'epoch': 583.66}

 92%|█████████▏| 52880/57600 [9:18:27<49:35,  1.59it/s]
 92%|█████████▏| 52881/57600 [9:18:27<48:15,  1.63it/s]
 92%|█████████▏| 52882/57600 [9:18:28<48:53,  1.61it/s]
 92%|█████████▏| 52883/57600 [9:18:29<48:40,  1.62it/s]
 92%|█████████▏| 52884/57600 [9:18:29<49:28,  1.59it/s]
 92%|█████████▏| 52885/57600 [9:18:30<49:14,  1.60it/s]
 92%|█████████▏| 52886/57600 [9:18:30<47:33,  1.65it/s]
 92%|█████████▏| 52887/57600 [9:18:31<47:48,  1.64it/s]
 92%|█████████▏| 52888/57600 [9:18:32<49:11,  1.60it/s]
 92%|█████████▏| 52889/57600 [9:18:32<48:35,  1.62it/s]
 92%|█████████▏| 52890/57600 [9:18:33<48:49,  1.61it/s]
 92%|█████████▏| 52891/57600 [9:18:34<49:43,  1.58it/s]
 92%|█████████▏| 52892/57600 [9:18:34<48:15,  1.63it/s]
 92%|█████████▏| 52893/57600 [9:18:35<47:15,  1.66it/s]
 92%|█████████▏| 52894/57600 [9:18:35<46:32,  1.68it/s]
 92%|█████████▏| 52895/57600 [9:18:36<48:02,  1.63it/s]
 92%|█████████▏| 52896/57600 [9:18:37<47:49,  1.64it/s]
 92%|█████████▏| 52897/57600 [9:18:37<48:22,  1.62it/s]
 92%|█████████▏| 52898/57600 [9:18:38<49:00,  1.60it/s]
 92%|█████████▏| 52899/57600 [9:18:39<48:58,  1.60it/s]
 92%|█████████▏| 52900/57600 [9:18:39<49:45,  1.57it/s]
                                                       
{'loss': 1.1012, 'learning_rate': 1.7369337979094075e-07, 'epoch': 583.89}

 92%|█████████▏| 52900/57600 [9:18:39<49:45,  1.57it/s]
 92%|█████████▏| 52901/57600 [9:18:40<49:21,  1.59it/s]
 92%|█████████▏| 52902/57600 [9:18:40<48:10,  1.63it/s]
 92%|█████████▏| 52903/57600 [9:18:41<47:53,  1.63it/s]
 92%|█████████▏| 52904/57600 [9:18:42<47:53,  1.63it/s]
 92%|█████████▏| 52905/57600 [9:18:42<48:32,  1.61it/s]
 92%|█████████▏| 52906/57600 [9:18:43<49:14,  1.59it/s]
 92%|█████████▏| 52907/57600 [9:18:44<50:04,  1.56it/s]
 92%|█████████▏| 52908/57600 [9:18:44<49:44,  1.57it/s]
 92%|█████████▏| 52909/57600 [9:18:45<50:58,  1.53it/s]
 92%|█████████▏| 52910/57600 [9:18:46<50:41,  1.54it/s]
 92%|█████████▏| 52911/57600 [9:18:46<51:14,  1.52it/s]
 92%|█████████▏| 52912/57600 [9:18:47<51:47,  1.51it/s]
 92%|█████████▏| 52913/57600 [9:18:48<51:34,  1.51it/s]
 92%|█████████▏| 52914/57600 [9:18:48<51:38,  1.51it/s]
 92%|█████████▏| 52915/57600 [9:18:49<51:22,  1.52it/s]
 92%|█████████▏| 52916/57600 [9:18:49<50:30,  1.55it/s]
 92%|█████████▏| 52917/57600 [9:18:50<51:07,  1.53it/s]
 92%|█████████▏| 52918/57600 [9:18:51<50:31,  1.54it/s]
 92%|█████████▏| 52919/57600 [9:18:51<49:15,  1.58it/s]
 92%|█████████▏| 52920/57600 [9:18:52<50:40,  1.54it/s]
                                                       
{'loss': 1.0892, 'learning_rate': 1.7337979094076658e-07, 'epoch': 584.11}

 92%|█████████▏| 52920/57600 [9:18:52<50:40,  1.54it/s]
 92%|█████████▏| 52921/57600 [9:18:53<49:52,  1.56it/s]
 92%|█████████▏| 52922/57600 [9:18:53<49:06,  1.59it/s]
 92%|█████████▏| 52923/57600 [9:18:54<48:55,  1.59it/s]
 92%|█████████▏| 52924/57600 [9:18:54<48:39,  1.60it/s]
 92%|█████████▏| 52925/57600 [9:18:55<48:35,  1.60it/s]
 92%|█████████▏| 52926/57600 [9:18:56<48:49,  1.60it/s]
 92%|█████████▏| 52927/57600 [9:18:56<48:35,  1.60it/s]
 92%|█████████▏| 52928/57600 [9:18:57<48:22,  1.61it/s]
 92%|█████████▏| 52929/57600 [9:18:58<48:40,  1.60it/s]
 92%|█████████▏| 52930/57600 [9:18:58<48:43,  1.60it/s]
 92%|█████████▏| 52931/57600 [9:18:59<47:59,  1.62it/s]
 92%|█████████▏| 52932/57600 [9:18:59<48:00,  1.62it/s]
 92%|█████████▏| 52933/57600 [9:19:00<46:53,  1.66it/s]
 92%|█████████▏| 52934/57600 [9:19:01<45:48,  1.70it/s]
 92%|█████████▏| 52935/57600 [9:19:01<48:53,  1.59it/s]
 92%|█████████▏| 52936/57600 [9:19:02<48:07,  1.62it/s]
 92%|█████████▏| 52937/57600 [9:19:03<48:22,  1.61it/s]
 92%|█████████▏| 52938/57600 [9:19:03<49:13,  1.58it/s]
 92%|█████████▏| 52939/57600 [9:19:04<49:26,  1.57it/s]
 92%|█████████▏| 52940/57600 [9:19:04<48:41,  1.60it/s]
                                                       
{'loss': 1.1212, 'learning_rate': 1.730662020905923e-07, 'epoch': 584.33}

 92%|█████████▏| 52940/57600 [9:19:04<48:41,  1.60it/s]
 92%|█████████▏| 52941/57600 [9:19:05<48:47,  1.59it/s]
 92%|█████████▏| 52942/57600 [9:19:06<49:39,  1.56it/s]
 92%|█████████▏| 52943/57600 [9:19:06<48:49,  1.59it/s]
 92%|█████████▏| 52944/57600 [9:19:07<48:28,  1.60it/s]
 92%|█████████▏| 52945/57600 [9:19:08<49:44,  1.56it/s]
 92%|█████████▏| 52946/57600 [9:19:08<48:47,  1.59it/s]
 92%|█████████▏| 52947/57600 [9:19:09<49:05,  1.58it/s]
 92%|█████████▏| 52948/57600 [9:19:09<48:01,  1.61it/s]
 92%|█████████▏| 52949/57600 [9:19:10<48:02,  1.61it/s]
 92%|█████████▏| 52950/57600 [9:19:11<47:29,  1.63it/s]
 92%|█████████▏| 52951/57600 [9:19:11<46:42,  1.66it/s]
 92%|█████████▏| 52952/57600 [9:19:12<46:42,  1.66it/s]
 92%|█████████▏| 52953/57600 [9:19:12<47:02,  1.65it/s]
 92%|█████████▏| 52954/57600 [9:19:13<47:06,  1.64it/s]
 92%|█████████▏| 52955/57600 [9:19:14<46:14,  1.67it/s]
 92%|█████████▏| 52956/57600 [9:19:14<47:08,  1.64it/s]
 92%|█████████▏| 52957/57600 [9:19:15<46:07,  1.68it/s]
 92%|█████████▏| 52958/57600 [9:19:16<48:16,  1.60it/s]
 92%|█████████▏| 52959/57600 [9:19:16<48:57,  1.58it/s]
 92%|█████████▏| 52960/57600 [9:19:17<50:33,  1.53it/s]
                                                       
{'loss': 1.0909, 'learning_rate': 1.7275261324041814e-07, 'epoch': 584.55}

 92%|█████████▏| 52960/57600 [9:19:17<50:33,  1.53it/s]
 92%|█████████▏| 52961/57600 [9:19:18<50:13,  1.54it/s]
 92%|█████████▏| 52962/57600 [9:19:18<49:13,  1.57it/s]
 92%|█████████▏| 52963/57600 [9:19:19<49:19,  1.57it/s]
 92%|█████████▏| 52964/57600 [9:19:19<49:09,  1.57it/s]
 92%|█████████▏| 52965/57600 [9:19:20<50:07,  1.54it/s]
 92%|█████████▏| 52966/57600 [9:19:21<48:30,  1.59it/s]
 92%|█████████▏| 52967/57600 [9:19:21<47:53,  1.61it/s]
 92%|█████████▏| 52968/57600 [9:19:22<48:30,  1.59it/s]
 92%|█████████▏| 52969/57600 [9:19:23<48:02,  1.61it/s]
 92%|█████████▏| 52970/57600 [9:19:23<48:12,  1.60it/s]
 92%|█████████▏| 52971/57600 [9:19:24<48:03,  1.61it/s]
 92%|█████████▏| 52972/57600 [9:19:24<48:28,  1.59it/s]
 92%|█████████▏| 52973/57600 [9:19:25<49:06,  1.57it/s]
 92%|█████████▏| 52974/57600 [9:19:26<48:46,  1.58it/s]
 92%|█████████▏| 52975/57600 [9:19:26<48:24,  1.59it/s]
 92%|█████████▏| 52976/57600 [9:19:27<46:54,  1.64it/s]
 92%|█████████▏| 52977/57600 [9:19:28<46:38,  1.65it/s]
 92%|█████████▏| 52978/57600 [9:19:28<47:05,  1.64it/s]
 92%|█████████▏| 52979/57600 [9:19:29<48:45,  1.58it/s]
 92%|█████████▏| 52980/57600 [9:19:29<47:22,  1.63it/s]
                                                       
{'loss': 1.1352, 'learning_rate': 1.7243902439024386e-07, 'epoch': 584.77}

 92%|█████████▏| 52980/57600 [9:19:29<47:22,  1.63it/s]
 92%|█████████▏| 52981/57600 [9:19:30<46:46,  1.65it/s]
 92%|█████████▏| 52982/57600 [9:19:31<46:14,  1.66it/s]
 92%|█████████▏| 52983/57600 [9:19:31<45:41,  1.68it/s]
 92%|█████████▏| 52984/57600 [9:19:32<47:03,  1.64it/s]
 92%|█████████▏| 52985/57600 [9:19:32<47:52,  1.61it/s]
 92%|█████████▏| 52986/57600 [9:19:33<46:14,  1.66it/s]
 92%|█████████▏| 52987/57600 [9:19:34<45:50,  1.68it/s]
 92%|█████████▏| 52988/57600 [9:19:34<45:03,  1.71it/s]
 92%|█████████▏| 52989/57600 [9:19:35<45:25,  1.69it/s]
 92%|█████████▏| 52990/57600 [9:19:35<46:25,  1.66it/s]
 92%|█████████▏| 52991/57600 [9:19:36<46:25,  1.65it/s]
 92%|█████████▏| 52992/57600 [9:19:37<46:20,  1.66it/s]
 92%|█████████▏| 52993/57600 [9:19:37<47:14,  1.63it/s]
 92%|█████████▏| 52994/57600 [9:19:38<47:16,  1.62it/s]
 92%|█████████▏| 52995/57600 [9:19:38<47:38,  1.61it/s]
 92%|█████████▏| 52996/57600 [9:19:39<49:28,  1.55it/s]
 92%|█████████▏| 52997/57600 [9:19:40<49:29,  1.55it/s]
 92%|█████████▏| 52998/57600 [9:19:40<47:53,  1.60it/s]
 92%|█████████▏| 52999/57600 [9:19:41<47:38,  1.61it/s]
 92%|█████████▏| 53000/57600 [9:19:42<47:25,  1.62it/s]
                                                       
{'loss': 1.1064, 'learning_rate': 1.721254355400697e-07, 'epoch': 584.99}

 92%|█████████▏| 53000/57600 [9:19:42<47:25,  1.62it/s]
 92%|█████████▏| 53001/57600 [9:19:42<47:00,  1.63it/s]
 92%|█████████▏| 53002/57600 [9:19:43<49:42,  1.54it/s]
 92%|█████████▏| 53003/57600 [9:19:44<47:27,  1.61it/s]
 92%|█████████▏| 53004/57600 [9:19:44<47:47,  1.60it/s]
 92%|█████████▏| 53005/57600 [9:19:45<48:07,  1.59it/s]
 92%|█████████▏| 53006/57600 [9:19:45<49:56,  1.53it/s]
 92%|█████████▏| 53007/57600 [9:19:46<49:37,  1.54it/s]
 92%|█████████▏| 53008/57600 [9:19:47<49:00,  1.56it/s]
 92%|█████████▏| 53009/57600 [9:19:47<48:38,  1.57it/s]
 92%|█████████▏| 53010/57600 [9:19:48<49:15,  1.55it/s]
 92%|█████████▏| 53011/57600 [9:19:49<50:16,  1.52it/s]
 92%|█████████▏| 53012/57600 [9:19:49<48:11,  1.59it/s]
 92%|█████████▏| 53013/57600 [9:19:50<47:09,  1.62it/s]
 92%|█████████▏| 53014/57600 [9:19:51<47:46,  1.60it/s]
 92%|█████████▏| 53015/57600 [9:19:51<46:33,  1.64it/s]
 92%|█████████▏| 53016/57600 [9:19:52<49:09,  1.55it/s]
 92%|█████████▏| 53017/57600 [9:19:52<48:57,  1.56it/s]
 92%|█████████▏| 53018/57600 [9:19:53<50:08,  1.52it/s]
 92%|█████████▏| 53019/57600 [9:19:54<49:07,  1.55it/s]
 92%|█████████▏| 53020/57600 [9:19:54<49:10,  1.55it/s]
                                                       
{'loss': 1.111, 'learning_rate': 1.7181184668989552e-07, 'epoch': 585.21}

 92%|█████████▏| 53020/57600 [9:19:54<49:10,  1.55it/s]
 92%|█████████▏| 53021/57600 [9:19:55<49:42,  1.54it/s]
 92%|█████████▏| 53022/57600 [9:19:56<49:59,  1.53it/s]
 92%|█████████▏| 53023/57600 [9:19:56<50:26,  1.51it/s]
 92%|█████████▏| 53024/57600 [9:19:57<51:37,  1.48it/s]
 92%|█████████▏| 53025/57600 [9:19:58<49:33,  1.54it/s]
 92%|█████████▏| 53026/57600 [9:19:58<48:53,  1.56it/s]
 92%|█████████▏| 53027/57600 [9:19:59<48:38,  1.57it/s]
 92%|█████████▏| 53028/57600 [9:20:00<49:13,  1.55it/s]
 92%|█████████▏| 53029/57600 [9:20:00<49:55,  1.53it/s]
 92%|█████████▏| 53030/57600 [9:20:01<47:38,  1.60it/s]
 92%|█████████▏| 53031/57600 [9:20:01<47:15,  1.61it/s]
 92%|█████████▏| 53032/57600 [9:20:02<48:08,  1.58it/s]
 92%|█████████▏| 53033/57600 [9:20:03<48:08,  1.58it/s]
 92%|█████████▏| 53034/57600 [9:20:03<48:29,  1.57it/s]
 92%|█████████▏| 53035/57600 [9:20:04<47:08,  1.61it/s]
 92%|█████████▏| 53036/57600 [9:20:05<48:01,  1.58it/s]
 92%|█████████▏| 53037/57600 [9:20:05<47:24,  1.60it/s]
 92%|█████████▏| 53038/57600 [9:20:06<47:14,  1.61it/s]
 92%|█████████▏| 53039/57600 [9:20:06<46:13,  1.64it/s]
 92%|█████████▏| 53040/57600 [9:20:07<45:37,  1.67it/s]
                                                       
{'loss': 1.0868, 'learning_rate': 1.7149825783972125e-07, 'epoch': 585.43}

 92%|█████████▏| 53040/57600 [9:20:07<45:37,  1.67it/s]
 92%|█████████▏| 53041/57600 [9:20:08<45:32,  1.67it/s]
 92%|█████████▏| 53042/57600 [9:20:08<45:51,  1.66it/s]
 92%|█████████▏| 53043/57600 [9:20:09<44:56,  1.69it/s]
 92%|█████████▏| 53044/57600 [9:20:09<45:23,  1.67it/s]
 92%|█████████▏| 53045/57600 [9:20:10<45:39,  1.66it/s]
 92%|█████████▏| 53046/57600 [9:20:11<47:31,  1.60it/s]
 92%|█████████▏| 53047/57600 [9:20:11<49:06,  1.55it/s]
 92%|█████████▏| 53048/57600 [9:20:12<48:19,  1.57it/s]
 92%|█████████▏| 53049/57600 [9:20:13<48:32,  1.56it/s]
 92%|█████████▏| 53050/57600 [9:20:13<48:26,  1.57it/s]
 92%|█████████▏| 53051/57600 [9:20:14<48:06,  1.58it/s]
 92%|█████████▏| 53052/57600 [9:20:14<46:00,  1.65it/s]
 92%|█████████▏| 53053/57600 [9:20:15<44:45,  1.69it/s]
 92%|█████████▏| 53054/57600 [9:20:16<45:24,  1.67it/s]
 92%|█████████▏| 53055/57600 [9:20:16<45:09,  1.68it/s]
 92%|█████████▏| 53056/57600 [9:20:17<44:12,  1.71it/s]
 92%|█████████▏| 53057/57600 [9:20:17<44:54,  1.69it/s]
 92%|█████████▏| 53058/57600 [9:20:18<46:10,  1.64it/s]
 92%|█████████▏| 53059/57600 [9:20:19<47:52,  1.58it/s]
 92%|█████████▏| 53060/57600 [9:20:19<47:34,  1.59it/s]
                                                       
{'loss': 1.1096, 'learning_rate': 1.7118466898954706e-07, 'epoch': 585.65}

 92%|█████████▏| 53060/57600 [9:20:19<47:34,  1.59it/s]
 92%|█████████▏| 53061/57600 [9:20:20<47:08,  1.60it/s]
 92%|█████████▏| 53062/57600 [9:20:21<48:05,  1.57it/s]
 92%|█████████▏| 53063/57600 [9:20:21<47:13,  1.60it/s]
 92%|█████████▏| 53064/57600 [9:20:22<47:12,  1.60it/s]
 92%|█████████▏| 53065/57600 [9:20:22<45:21,  1.67it/s]
 92%|█████████▏| 53066/57600 [9:20:23<45:01,  1.68it/s]
 92%|█████████▏| 53067/57600 [9:20:24<46:49,  1.61it/s]
 92%|█████████▏| 53068/57600 [9:20:24<45:22,  1.66it/s]
 92%|█████████▏| 53069/57600 [9:20:25<45:20,  1.67it/s]
 92%|█████████▏| 53070/57600 [9:20:25<45:30,  1.66it/s]
 92%|█████████▏| 53071/57600 [9:20:26<46:59,  1.61it/s]
 92%|█████████▏| 53072/57600 [9:20:27<47:10,  1.60it/s]
 92%|█████████▏| 53073/57600 [9:20:27<46:24,  1.63it/s]
 92%|█████████▏| 53074/57600 [9:20:28<47:51,  1.58it/s]
 92%|█████████▏| 53075/57600 [9:20:29<49:37,  1.52it/s]
 92%|█████████▏| 53076/57600 [9:20:29<50:28,  1.49it/s]
 92%|█████████▏| 53077/57600 [9:20:30<51:17,  1.47it/s]
 92%|█████████▏| 53078/57600 [9:20:31<49:12,  1.53it/s]
 92%|█████████▏| 53079/57600 [9:20:31<48:35,  1.55it/s]
 92%|█████████▏| 53080/57600 [9:20:32<48:02,  1.57it/s]
                                                       
{'loss': 1.1196, 'learning_rate': 1.708710801393728e-07, 'epoch': 585.87}

 92%|█████████▏| 53080/57600 [9:20:32<48:02,  1.57it/s]
 92%|█████████▏| 53081/57600 [9:20:33<46:55,  1.60it/s]
 92%|█████████▏| 53082/57600 [9:20:33<46:08,  1.63it/s]
 92%|█████████▏| 53083/57600 [9:20:34<47:59,  1.57it/s]
 92%|█████████▏| 53084/57600 [9:20:34<47:04,  1.60it/s]
 92%|█████████▏| 53085/57600 [9:20:35<46:50,  1.61it/s]
 92%|█████████▏| 53086/57600 [9:20:36<45:29,  1.65it/s]
 92%|█████████▏| 53087/57600 [9:20:36<47:07,  1.60it/s]
 92%|█████████▏| 53088/57600 [9:20:37<45:44,  1.64it/s]
 92%|█████████▏| 53089/57600 [9:20:37<44:58,  1.67it/s]
 92%|█████████▏| 53090/57600 [9:20:38<45:02,  1.67it/s]
 92%|█████████▏| 53091/57600 [9:20:39<45:58,  1.63it/s]
 92%|█████████▏| 53092/57600 [9:20:39<47:32,  1.58it/s]
 92%|█████████▏| 53093/57600 [9:20:40<46:59,  1.60it/s]
 92%|█████████▏| 53094/57600 [9:20:41<47:29,  1.58it/s]
 92%|█████████▏| 53095/57600 [9:20:41<46:55,  1.60it/s]
 92%|█████████▏| 53096/57600 [9:20:42<46:51,  1.60it/s]
 92%|█████████▏| 53097/57600 [9:20:42<46:42,  1.61it/s]
 92%|█████████▏| 53098/57600 [9:20:43<46:27,  1.62it/s]
 92%|█████████▏| 53099/57600 [9:20:44<48:39,  1.54it/s]
 92%|█████████▏| 53100/57600 [9:20:44<46:59,  1.60it/s]
                                                       
{'loss': 1.0879, 'learning_rate': 1.705574912891986e-07, 'epoch': 586.09}

 92%|█████████▏| 53100/57600 [9:20:44<46:59,  1.60it/s]
 92%|█████████▏| 53101/57600 [9:20:45<47:30,  1.58it/s]
 92%|█████████▏| 53102/57600 [9:20:46<47:19,  1.58it/s]
 92%|█████████▏| 53103/57600 [9:20:46<46:57,  1.60it/s]
 92%|█████████▏| 53104/57600 [9:20:47<47:08,  1.59it/s]
 92%|█████████▏| 53105/57600 [9:20:48<47:27,  1.58it/s]
 92%|█████████▏| 53106/57600 [9:20:48<47:09,  1.59it/s]
 92%|█████████▏| 53107/57600 [9:20:49<47:19,  1.58it/s]
 92%|█████████▏| 53108/57600 [9:20:49<46:14,  1.62it/s]
 92%|█████████▏| 53109/57600 [9:20:50<46:03,  1.63it/s]
 92%|█████████▏| 53110/57600 [9:20:51<46:37,  1.61it/s]
 92%|█████████▏| 53111/57600 [9:20:51<47:30,  1.57it/s]
 92%|█████████▏| 53112/57600 [9:20:52<49:49,  1.50it/s]
 92%|█████████▏| 53113/57600 [9:20:53<47:11,  1.58it/s]
 92%|█████████▏| 53114/57600 [9:20:53<46:10,  1.62it/s]
 92%|█████████▏| 53115/57600 [9:20:54<46:19,  1.61it/s]
 92%|█████████▏| 53116/57600 [9:20:54<45:05,  1.66it/s]
 92%|█████████▏| 53117/57600 [9:20:55<45:26,  1.64it/s]
 92%|█████████▏| 53118/57600 [9:20:56<47:03,  1.59it/s]
 92%|█████████▏| 53119/57600 [9:20:56<48:30,  1.54it/s]
 92%|█████████▏| 53120/57600 [9:20:57<47:38,  1.57it/s]
                                                       
{'loss': 1.0986, 'learning_rate': 1.7024390243902436e-07, 'epoch': 586.31}

 92%|█████████▏| 53120/57600 [9:20:57<47:38,  1.57it/s]
 92%|█████████▏| 53121/57600 [9:20:58<46:38,  1.60it/s]
 92%|█████████▏| 53122/57600 [9:20:58<47:03,  1.59it/s]
 92%|█████████▏| 53123/57600 [9:20:59<46:49,  1.59it/s]
 92%|█████████▏| 53124/57600 [9:20:59<47:10,  1.58it/s]
 92%|█████████▏| 53125/57600 [9:21:00<46:19,  1.61it/s]
 92%|█████████▏| 53126/57600 [9:21:01<47:46,  1.56it/s]
 92%|█████████▏| 53127/57600 [9:21:01<48:55,  1.52it/s]
 92%|█████████▏| 53128/57600 [9:21:02<49:05,  1.52it/s]
 92%|█████████▏| 53129/57600 [9:21:03<48:39,  1.53it/s]
 92%|█████████▏| 53130/57600 [9:21:03<47:56,  1.55it/s]
 92%|█████████▏| 53131/57600 [9:21:04<46:41,  1.60it/s]
 92%|█████████▏| 53132/57600 [9:21:05<46:41,  1.59it/s]
 92%|█████████▏| 53133/57600 [9:21:05<47:03,  1.58it/s]
 92%|█████████▏| 53134/57600 [9:21:06<48:51,  1.52it/s]
 92%|█████████▏| 53135/57600 [9:21:06<47:06,  1.58it/s]
 92%|█████████▏| 53136/57600 [9:21:07<47:28,  1.57it/s]
 92%|█████████▏| 53137/57600 [9:21:08<47:14,  1.57it/s]
 92%|█████████▏| 53138/57600 [9:21:08<47:42,  1.56it/s]
 92%|█████████▏| 53139/57600 [9:21:09<46:37,  1.59it/s]
 92%|█████████▏| 53140/57600 [9:21:10<45:52,  1.62it/s]
                                                       
{'loss': 1.0939, 'learning_rate': 1.699303135888502e-07, 'epoch': 586.53}

 92%|█████████▏| 53140/57600 [9:21:10<45:52,  1.62it/s]
 92%|█████████▏| 53141/57600 [9:21:10<45:40,  1.63it/s]
 92%|█████████▏| 53142/57600 [9:21:11<46:55,  1.58it/s]
 92%|█████████▏| 53143/57600 [9:21:12<48:25,  1.53it/s]
 92%|█████████▏| 53144/57600 [9:21:12<47:51,  1.55it/s]
 92%|█████████▏| 53145/57600 [9:21:13<46:20,  1.60it/s]
 92%|█████████▏| 53146/57600 [9:21:13<45:01,  1.65it/s]
 92%|█████████▏| 53147/57600 [9:21:14<44:00,  1.69it/s]
 92%|█████████▏| 53148/57600 [9:21:14<43:25,  1.71it/s]
 92%|█████████▏| 53149/57600 [9:21:15<43:25,  1.71it/s]
 92%|█████████▏| 53150/57600 [9:21:16<45:54,  1.62it/s]
 92%|█████████▏| 53151/57600 [9:21:16<45:36,  1.63it/s]
 92%|█████████▏| 53152/57600 [9:21:17<45:38,  1.62it/s]
 92%|█████████▏| 53153/57600 [9:21:18<45:00,  1.65it/s]
 92%|█████████▏| 53154/57600 [9:21:18<47:02,  1.58it/s]
 92%|█████████▏| 53155/57600 [9:21:19<47:41,  1.55it/s]
 92%|█████████▏| 53156/57600 [9:21:20<45:54,  1.61it/s]
 92%|█████████▏| 53157/57600 [9:21:20<46:08,  1.60it/s]
 92%|█████████▏| 53158/57600 [9:21:21<45:42,  1.62it/s]
 92%|█████████▏| 53159/57600 [9:21:21<45:48,  1.62it/s]
 92%|█████████▏| 53160/57600 [9:21:22<44:55,  1.65it/s]
                                                       
{'loss': 1.1178, 'learning_rate': 1.69616724738676e-07, 'epoch': 586.75}

 92%|█████████▏| 53160/57600 [9:21:22<44:55,  1.65it/s]
 92%|█████████▏| 53161/57600 [9:21:23<47:10,  1.57it/s]
 92%|█████████▏| 53162/57600 [9:21:23<47:35,  1.55it/s]
 92%|█████████▏| 53163/57600 [9:21:24<45:53,  1.61it/s]
 92%|█████████▏| 53164/57600 [9:21:24<44:10,  1.67it/s]
 92%|█████████▏| 53165/57600 [9:21:25<43:03,  1.72it/s]
 92%|█████████▏| 53166/57600 [9:21:26<45:55,  1.61it/s]
 92%|█████████▏| 53167/57600 [9:21:26<46:34,  1.59it/s]
 92%|█████████▏| 53168/57600 [9:21:27<44:51,  1.65it/s]
 92%|█████████▏| 53169/57600 [9:21:28<45:37,  1.62it/s]
 92%|█████████▏| 53170/57600 [9:21:28<46:43,  1.58it/s]
 92%|█████████▏| 53171/57600 [9:21:29<47:05,  1.57it/s]
 92%|█████████▏| 53172/57600 [9:21:29<46:15,  1.60it/s]
 92%|█████████▏| 53173/57600 [9:21:30<45:14,  1.63it/s]
 92%|█████████▏| 53174/57600 [9:21:31<44:29,  1.66it/s]
 92%|█████████▏| 53175/57600 [9:21:31<47:24,  1.56it/s]
 92%|█████████▏| 53176/57600 [9:21:32<46:51,  1.57it/s]
 92%|█████████▏| 53177/57600 [9:21:33<48:09,  1.53it/s]
 92%|█████████▏| 53178/57600 [9:21:33<48:16,  1.53it/s]
 92%|█████████▏| 53179/57600 [9:21:34<50:09,  1.47it/s]
 92%|█████████▏| 53180/57600 [9:21:35<49:27,  1.49it/s]
                                                       
{'loss': 1.0901, 'learning_rate': 1.6930313588850173e-07, 'epoch': 586.98}

 92%|█████████▏| 53180/57600 [9:21:35<49:27,  1.49it/s]
 92%|█████████▏| 53181/57600 [9:21:35<47:53,  1.54it/s]
 92%|█████████▏| 53182/57600 [9:21:36<46:22,  1.59it/s]
 92%|█████████▏| 53183/57600 [9:21:37<47:50,  1.54it/s]
 92%|█████████▏| 53184/57600 [9:21:37<46:56,  1.57it/s]
 92%|█████████▏| 53185/57600 [9:21:38<47:31,  1.55it/s]
 92%|█████████▏| 53186/57600 [9:21:39<48:50,  1.51it/s]
 92%|█████████▏| 53187/57600 [9:21:39<48:43,  1.51it/s]
 92%|█████████▏| 53188/57600 [9:21:40<48:10,  1.53it/s]
 92%|█████████▏| 53189/57600 [9:21:41<48:54,  1.50it/s]
 92%|█████████▏| 53190/57600 [9:21:41<48:34,  1.51it/s]
 92%|█████████▏| 53191/57600 [9:21:42<47:37,  1.54it/s]
 92%|█████████▏| 53192/57600 [9:21:42<46:18,  1.59it/s]
 92%|█████████▏| 53193/57600 [9:21:43<46:19,  1.59it/s]
 92%|█████████▏| 53194/57600 [9:21:44<46:04,  1.59it/s]
 92%|█████████▏| 53195/57600 [9:21:44<46:05,  1.59it/s]
 92%|█████████▏| 53196/57600 [9:21:45<45:49,  1.60it/s]
 92%|█████████▏| 53197/57600 [9:21:46<45:20,  1.62it/s]
 92%|█████████▏| 53198/57600 [9:21:46<45:49,  1.60it/s]
 92%|█████████▏| 53199/57600 [9:21:47<45:33,  1.61it/s]
 92%|█████████▏| 53200/57600 [9:21:47<45:08,  1.62it/s]
                                                       
{'loss': 1.1083, 'learning_rate': 1.6898954703832756e-07, 'epoch': 587.2}

 92%|█████████▏| 53200/57600 [9:21:47<45:08,  1.62it/s]
 92%|█████████▏| 53201/57600 [9:21:48<46:55,  1.56it/s]
 92%|█████████▏| 53202/57600 [9:21:49<46:30,  1.58it/s]
 92%|█████████▏| 53203/57600 [9:21:49<45:36,  1.61it/s]
 92%|█████████▏| 53204/57600 [9:21:50<44:35,  1.64it/s]
 92%|█████████▏| 53205/57600 [9:21:51<47:20,  1.55it/s]
 92%|█████████▏| 53206/57600 [9:21:51<45:43,  1.60it/s]
 92%|█████████▏| 53207/57600 [9:21:52<44:48,  1.63it/s]
 92%|█████████▏| 53208/57600 [9:21:52<44:47,  1.63it/s]
 92%|█████████▏| 53209/57600 [9:21:53<43:32,  1.68it/s]
 92%|█████████▏| 53210/57600 [9:21:54<43:44,  1.67it/s]
 92%|█████████▏| 53211/57600 [9:21:54<45:25,  1.61it/s]
 92%|█████████▏| 53212/57600 [9:21:55<45:31,  1.61it/s]
 92%|█████████▏| 53213/57600 [9:21:55<44:42,  1.64it/s]
 92%|█████████▏| 53214/57600 [9:21:56<44:05,  1.66it/s]
 92%|█████████▏| 53215/57600 [9:21:57<44:05,  1.66it/s]
 92%|█████████▏| 53216/57600 [9:21:57<44:08,  1.66it/s]
 92%|█████████▏| 53217/57600 [9:21:58<46:26,  1.57it/s]
 92%|█████████▏| 53218/57600 [9:21:59<45:26,  1.61it/s]
 92%|█████████▏| 53219/57600 [9:21:59<45:54,  1.59it/s]
 92%|█████████▏| 53220/57600 [9:22:00<45:16,  1.61it/s]
                                                       
{'loss': 1.1307, 'learning_rate': 1.6867595818815328e-07, 'epoch': 587.42}

 92%|█████████▏| 53220/57600 [9:22:00<45:16,  1.61it/s]
 92%|█████████▏| 53221/57600 [9:22:00<45:22,  1.61it/s]
 92%|█████████▏| 53222/57600 [9:22:01<45:13,  1.61it/s]
 92%|█████████▏| 53223/57600 [9:22:02<45:11,  1.61it/s]
 92%|█████████▏| 53224/57600 [9:22:02<45:50,  1.59it/s]
 92%|█████████▏| 53225/57600 [9:22:03<45:43,  1.59it/s]
 92%|█████████▏| 53226/57600 [9:22:03<45:01,  1.62it/s]
 92%|█████████▏| 53227/57600 [9:22:04<44:45,  1.63it/s]
 92%|█████████▏| 53228/57600 [9:22:05<44:41,  1.63it/s]
 92%|█████████▏| 53229/57600 [9:22:05<45:41,  1.59it/s]
 92%|█████████▏| 53230/57600 [9:22:06<45:49,  1.59it/s]
 92%|█████████▏| 53231/57600 [9:22:07<45:18,  1.61it/s]
 92%|█████████▏| 53232/57600 [9:22:07<44:37,  1.63it/s]
 92%|█████████▏| 53233/57600 [9:22:08<44:01,  1.65it/s]
 92%|█████████▏| 53234/57600 [9:22:08<43:52,  1.66it/s]
 92%|█████████▏| 53235/57600 [9:22:09<43:51,  1.66it/s]
 92%|█████████▏| 53236/57600 [9:22:10<43:14,  1.68it/s]
 92%|█████████▏| 53237/57600 [9:22:10<42:56,  1.69it/s]
 92%|█████████▏| 53238/57600 [9:22:11<41:59,  1.73it/s]
 92%|█████████▏| 53239/57600 [9:22:11<42:59,  1.69it/s]
 92%|█████████▏| 53240/57600 [9:22:12<42:08,  1.72it/s]
                                                       
{'loss': 1.1298, 'learning_rate': 1.683623693379791e-07, 'epoch': 587.64}

 92%|█████████▏| 53240/57600 [9:22:12<42:08,  1.72it/s]
 92%|█████████▏| 53241/57600 [9:22:12<42:07,  1.72it/s]
 92%|█████████▏| 53242/57600 [9:22:13<44:11,  1.64it/s]
 92%|█████████▏| 53243/57600 [9:22:14<44:14,  1.64it/s]
 92%|█████████▏| 53244/57600 [9:22:14<45:34,  1.59it/s]
 92%|█████████▏| 53245/57600 [9:22:15<46:06,  1.57it/s]
 92%|█████████▏| 53246/57600 [9:22:16<47:13,  1.54it/s]
 92%|█████████▏| 53247/57600 [9:22:16<45:49,  1.58it/s]
 92%|█████████▏| 53248/57600 [9:22:17<45:42,  1.59it/s]
 92%|█████████▏| 53249/57600 [9:22:18<44:47,  1.62it/s]
 92%|█████████▏| 53250/57600 [9:22:18<47:04,  1.54it/s]
 92%|█████████▏| 53251/57600 [9:22:19<46:13,  1.57it/s]
 92%|█████████▏| 53252/57600 [9:22:19<45:58,  1.58it/s]
 92%|█████████▏| 53253/57600 [9:22:20<44:37,  1.62it/s]
 92%|█████████▏| 53254/57600 [9:22:21<45:06,  1.61it/s]
 92%|█████████▏| 53255/57600 [9:22:21<44:32,  1.63it/s]
 92%|█████████▏| 53256/57600 [9:22:22<46:33,  1.55it/s]
 92%|█████████▏| 53257/57600 [9:22:23<47:05,  1.54it/s]
 92%|█████████▏| 53258/57600 [9:22:23<46:54,  1.54it/s]
 92%|█████████▏| 53259/57600 [9:22:24<45:44,  1.58it/s]
 92%|█████████▏| 53260/57600 [9:22:25<45:31,  1.59it/s]
                                                       
{'loss': 1.0645, 'learning_rate': 1.680487804878048e-07, 'epoch': 587.86}

 92%|█████████▏| 53260/57600 [9:22:25<45:31,  1.59it/s]
 92%|█████████▏| 53261/57600 [9:22:25<45:51,  1.58it/s]
 92%|█████████▏| 53262/57600 [9:22:26<44:06,  1.64it/s]
 92%|█████████▏| 53263/57600 [9:22:26<44:13,  1.63it/s]
 92%|█████████▏| 53264/57600 [9:22:27<44:04,  1.64it/s]
 92%|█████████▏| 53265/57600 [9:22:28<46:18,  1.56it/s]
 92%|█████████▏| 53266/57600 [9:22:28<46:26,  1.56it/s]
 92%|█████████▏| 53267/57600 [9:22:29<44:28,  1.62it/s]
 92%|█████████▏| 53268/57600 [9:22:29<44:01,  1.64it/s]
 92%|█████████▏| 53269/57600 [9:22:30<43:27,  1.66it/s]
 92%|█████████▏| 53270/57600 [9:22:31<43:00,  1.68it/s]
 92%|█████████▏| 53271/57600 [9:22:31<43:45,  1.65it/s]
 92%|█████████▏| 53272/57600 [9:22:32<45:43,  1.58it/s]
 92%|█████████▏| 53273/57600 [9:22:33<48:39,  1.48it/s]
 92%|█████████▏| 53274/57600 [9:22:33<48:59,  1.47it/s]
 92%|█████████▏| 53275/57600 [9:22:34<47:24,  1.52it/s]
 92%|█████████▏| 53276/57600 [9:22:35<45:50,  1.57it/s]
 92%|█████████▏| 53277/57600 [9:22:35<46:23,  1.55it/s]
 92%|█████████▏| 53278/57600 [9:22:36<46:17,  1.56it/s]
 92%|█████████▏| 53279/57600 [9:22:37<45:50,  1.57it/s]
 92%|█████████▎| 53280/57600 [9:22:37<44:56,  1.60it/s]
                                                       
{'loss': 1.1264, 'learning_rate': 1.6773519163763064e-07, 'epoch': 588.08}

 92%|█████████▎| 53280/57600 [9:22:37<44:56,  1.60it/s]
 93%|█████████▎| 53281/57600 [9:22:38<44:52,  1.60it/s]
 93%|█████████▎| 53282/57600 [9:22:38<45:57,  1.57it/s]
 93%|█████████▎| 53283/57600 [9:22:39<46:15,  1.56it/s]
 93%|█████████▎| 53284/57600 [9:22:40<44:59,  1.60it/s]
 93%|█████████▎| 53285/57600 [9:22:40<44:46,  1.61it/s]
 93%|█████████▎| 53286/57600 [9:22:41<44:21,  1.62it/s]
 93%|█████████▎| 53287/57600 [9:22:41<43:21,  1.66it/s]
 93%|█████████▎| 53288/57600 [9:22:42<43:27,  1.65it/s]
 93%|█████████▎| 53289/57600 [9:22:43<43:12,  1.66it/s]
 93%|█████████▎| 53290/57600 [9:22:43<43:02,  1.67it/s]
 93%|█████████▎| 53291/57600 [9:22:44<45:37,  1.57it/s]
 93%|█████████▎| 53292/57600 [9:22:45<43:59,  1.63it/s]
 93%|█████████▎| 53293/57600 [9:22:45<43:39,  1.64it/s]
 93%|█████████▎| 53294/57600 [9:22:46<43:48,  1.64it/s]
 93%|█████████▎| 53295/57600 [9:22:46<43:07,  1.66it/s]
 93%|█████████▎| 53296/57600 [9:22:47<44:35,  1.61it/s]
 93%|█████████▎| 53297/57600 [9:22:48<43:28,  1.65it/s]
 93%|█████████▎| 53298/57600 [9:22:48<46:09,  1.55it/s]
 93%|█████████▎| 53299/57600 [9:22:49<44:57,  1.59it/s]
 93%|█████████▎| 53300/57600 [9:22:49<44:10,  1.62it/s]
                                                       
{'loss': 1.1088, 'learning_rate': 1.674216027874565e-07, 'epoch': 588.3}

 93%|█████████▎| 53300/57600 [9:22:49<44:10,  1.62it/s]
 93%|█████████▎| 53301/57600 [9:22:50<43:34,  1.64it/s]
 93%|█████████▎| 53302/57600 [9:22:51<42:57,  1.67it/s]
 93%|█████████▎| 53303/57600 [9:22:51<43:18,  1.65it/s]
 93%|█████████▎| 53304/57600 [9:22:52<44:36,  1.60it/s]
 93%|█████████▎| 53305/57600 [9:22:53<45:09,  1.59it/s]
 93%|█████████▎| 53306/57600 [9:22:53<46:32,  1.54it/s]
 93%|█████████▎| 53307/57600 [9:22:54<46:00,  1.56it/s]
 93%|█████████▎| 53308/57600 [9:22:55<45:47,  1.56it/s]
 93%|█████████▎| 53309/57600 [9:22:55<45:43,  1.56it/s]
 93%|█████████▎| 53310/57600 [9:22:56<44:48,  1.60it/s]
 93%|█████████▎| 53311/57600 [9:22:56<43:33,  1.64it/s]
 93%|█████████▎| 53312/57600 [9:22:57<43:17,  1.65it/s]
 93%|█████████▎| 53313/57600 [9:22:58<44:07,  1.62it/s]
 93%|█████████▎| 53314/57600 [9:22:58<43:39,  1.64it/s]
 93%|█████████▎| 53315/57600 [9:22:59<43:13,  1.65it/s]
 93%|█████████▎| 53316/57600 [9:22:59<43:06,  1.66it/s]
 93%|█████████▎| 53317/57600 [9:23:00<43:15,  1.65it/s]
 93%|█████████▎| 53318/57600 [9:23:01<42:55,  1.66it/s]
 93%|█████████▎| 53319/57600 [9:23:01<42:14,  1.69it/s]
 93%|█████████▎| 53320/57600 [9:23:02<43:27,  1.64it/s]
                                                       
{'loss': 1.0877, 'learning_rate': 1.671080139372822e-07, 'epoch': 588.52}

 93%|█████████▎| 53320/57600 [9:23:02<43:27,  1.64it/s]
 93%|█████████▎| 53321/57600 [9:23:02<44:24,  1.61it/s]
 93%|█████████▎| 53322/57600 [9:23:03<44:23,  1.61it/s]
 93%|█████████▎| 53323/57600 [9:23:04<44:16,  1.61it/s]
 93%|█████████▎| 53324/57600 [9:23:04<43:37,  1.63it/s]
 93%|█████████▎| 53325/57600 [9:23:05<42:59,  1.66it/s]
 93%|█████████▎| 53326/57600 [9:23:05<42:33,  1.67it/s]
 93%|█████████▎| 53327/57600 [9:23:06<44:37,  1.60it/s]
 93%|█████████▎| 53328/57600 [9:23:07<43:40,  1.63it/s]
 93%|█████████▎| 53329/57600 [9:23:07<42:34,  1.67it/s]
 93%|█████████▎| 53330/57600 [9:23:08<41:48,  1.70it/s]
 93%|█████████▎| 53331/57600 [9:23:08<42:57,  1.66it/s]
 93%|█████████▎| 53332/57600 [9:23:09<43:51,  1.62it/s]
 93%|█████████▎| 53333/57600 [9:23:10<44:03,  1.61it/s]
 93%|█████████▎| 53334/57600 [9:23:10<42:53,  1.66it/s]
 93%|█████████▎| 53335/57600 [9:23:11<42:35,  1.67it/s]
 93%|█████████▎| 53336/57600 [9:23:12<44:05,  1.61it/s]
 93%|█████████▎| 53337/57600 [9:23:12<43:51,  1.62it/s]
 93%|█████████▎| 53338/57600 [9:23:13<44:01,  1.61it/s]
 93%|█████████▎| 53339/57600 [9:23:13<44:37,  1.59it/s]
 93%|█████████▎| 53340/57600 [9:23:14<44:27,  1.60it/s]
                                                       
{'loss': 1.1103, 'learning_rate': 1.6679442508710803e-07, 'epoch': 588.74}

 93%|█████████▎| 53340/57600 [9:23:14<44:27,  1.60it/s]
 93%|█████████▎| 53341/57600 [9:23:15<45:54,  1.55it/s]
 93%|█████████▎| 53342/57600 [9:23:15<45:27,  1.56it/s]
 93%|█████████▎| 53343/57600 [9:23:16<45:35,  1.56it/s]
 93%|█████████▎| 53344/57600 [9:23:17<44:36,  1.59it/s]
 93%|█████████▎| 53345/57600 [9:23:17<45:00,  1.58it/s]
 93%|█████████▎| 53346/57600 [9:23:18<45:27,  1.56it/s]
 93%|█████████▎| 53347/57600 [9:23:19<44:04,  1.61it/s]
 93%|█████████▎| 53348/57600 [9:23:19<43:51,  1.62it/s]
 93%|█████████▎| 53349/57600 [9:23:20<43:21,  1.63it/s]
 93%|█████████▎| 53350/57600 [9:23:20<43:24,  1.63it/s]
 93%|█████████▎| 53351/57600 [9:23:21<42:38,  1.66it/s]
 93%|█████████▎| 53352/57600 [9:23:22<42:58,  1.65it/s]
 93%|█████████▎| 53353/57600 [9:23:22<42:37,  1.66it/s]
 93%|█████████▎| 53354/57600 [9:23:23<42:31,  1.66it/s]
 93%|█████████▎| 53355/57600 [9:23:23<45:14,  1.56it/s]
 93%|█████████▎| 53356/57600 [9:23:24<47:18,  1.49it/s]
 93%|█████████▎| 53357/57600 [9:23:25<45:34,  1.55it/s]
 93%|█████████▎| 53358/57600 [9:23:26<47:35,  1.49it/s]
 93%|█████████▎| 53359/57600 [9:23:26<47:07,  1.50it/s]
 93%|█████████▎| 53360/57600 [9:23:27<47:39,  1.48it/s]
                                                       
{'loss': 1.0994, 'learning_rate': 1.6648083623693376e-07, 'epoch': 588.96}

 93%|█████████▎| 53360/57600 [9:23:27<47:39,  1.48it/s]
 93%|█████████▎| 53361/57600 [9:23:27<46:35,  1.52it/s]
 93%|█████████▎| 53362/57600 [9:23:28<46:18,  1.53it/s]
 93%|█████████▎| 53363/57600 [9:23:29<45:32,  1.55it/s]
 93%|█████████▎| 53364/57600 [9:23:29<47:02,  1.50it/s]
 93%|█████████▎| 53365/57600 [9:23:30<44:49,  1.57it/s]
 93%|█████████▎| 53366/57600 [9:23:31<44:33,  1.58it/s]
 93%|█████████▎| 53367/57600 [9:23:31<43:49,  1.61it/s]
 93%|█████████▎| 53368/57600 [9:23:32<42:10,  1.67it/s]
 93%|█████████▎| 53369/57600 [9:23:32<42:58,  1.64it/s]
 93%|█████████▎| 53370/57600 [9:23:33<43:00,  1.64it/s]
 93%|█████████▎| 53371/57600 [9:23:34<42:44,  1.65it/s]
 93%|█████████▎| 53372/57600 [9:23:34<42:31,  1.66it/s]
 93%|█████████▎| 53373/57600 [9:23:35<41:42,  1.69it/s]
 93%|█████████▎| 53374/57600 [9:23:35<42:24,  1.66it/s]
 93%|█████████▎| 53375/57600 [9:23:36<43:19,  1.63it/s]
 93%|█████████▎| 53376/57600 [9:23:37<42:22,  1.66it/s]
 93%|█████████▎| 53377/57600 [9:23:37<43:37,  1.61it/s]
 93%|█████████▎| 53378/57600 [9:23:38<43:44,  1.61it/s]
 93%|█████████▎| 53379/57600 [9:23:39<43:23,  1.62it/s]
 93%|█████████▎| 53380/57600 [9:23:39<43:25,  1.62it/s]
                                                       
{'loss': 1.128, 'learning_rate': 1.661672473867596e-07, 'epoch': 589.18}

 93%|█████████▎| 53380/57600 [9:23:39<43:25,  1.62it/s]
 93%|█████████▎| 53381/57600 [9:23:40<43:30,  1.62it/s]
 93%|█████████▎| 53382/57600 [9:23:40<44:25,  1.58it/s]
 93%|█████████▎| 53383/57600 [9:23:41<43:03,  1.63it/s]
 93%|█████████▎| 53384/57600 [9:23:42<45:02,  1.56it/s]
 93%|█████████▎| 53385/57600 [9:23:42<44:04,  1.59it/s]
 93%|█████████▎| 53386/57600 [9:23:43<43:07,  1.63it/s]
 93%|█████████▎| 53387/57600 [9:23:43<42:27,  1.65it/s]
 93%|█████████▎| 53388/57600 [9:23:44<44:15,  1.59it/s]
 93%|█████████▎| 53389/57600 [9:23:45<43:27,  1.61it/s]
 93%|█████████▎| 53390/57600 [9:23:45<42:04,  1.67it/s]
 93%|█████████▎| 53391/57600 [9:23:46<42:18,  1.66it/s]
 93%|█████████▎| 53392/57600 [9:23:47<41:55,  1.67it/s]
 93%|█████████▎| 53393/57600 [9:23:47<42:48,  1.64it/s]
 93%|█████████▎| 53394/57600 [9:23:48<43:55,  1.60it/s]
 93%|█████████▎| 53395/57600 [9:23:48<43:02,  1.63it/s]
 93%|█████████▎| 53396/57600 [9:23:49<43:32,  1.61it/s]
 93%|█████████▎| 53397/57600 [9:23:50<44:15,  1.58it/s]
 93%|█████████▎| 53398/57600 [9:23:50<44:40,  1.57it/s]
 93%|█████████▎| 53399/57600 [9:23:51<45:01,  1.56it/s]
 93%|█████████▎| 53400/57600 [9:23:52<47:45,  1.47it/s]
                                                       
{'loss': 1.0912, 'learning_rate': 1.6585365853658531e-07, 'epoch': 589.4}

 93%|█████████▎| 53400/57600 [9:23:52<47:45,  1.47it/s]
 93%|█████████▎| 53401/57600 [9:23:52<45:21,  1.54it/s]
 93%|█████████▎| 53402/57600 [9:23:53<46:09,  1.52it/s]
 93%|█████████▎| 53403/57600 [9:23:54<46:22,  1.51it/s]
 93%|█████████▎| 53404/57600 [9:23:54<44:58,  1.56it/s]
 93%|█████████▎| 53405/57600 [9:23:55<45:20,  1.54it/s]
 93%|█████████▎| 53406/57600 [9:23:56<46:57,  1.49it/s]
 93%|█████████▎| 53407/57600 [9:23:56<46:03,  1.52it/s]
 93%|█████████▎| 53408/57600 [9:23:57<44:31,  1.57it/s]
 93%|█████████▎| 53409/57600 [9:23:58<44:53,  1.56it/s]
 93%|█████████▎| 53410/57600 [9:23:58<45:21,  1.54it/s]
 93%|█████████▎| 53411/57600 [9:23:59<45:44,  1.53it/s]
 93%|█████████▎| 53412/57600 [9:24:00<45:06,  1.55it/s]
 93%|█████████▎| 53413/57600 [9:24:00<43:56,  1.59it/s]
 93%|█████████▎| 53414/57600 [9:24:01<43:34,  1.60it/s]
 93%|█████████▎| 53415/57600 [9:24:01<44:22,  1.57it/s]
 93%|█████████▎| 53416/57600 [9:24:02<44:24,  1.57it/s]
 93%|█████████▎| 53417/57600 [9:24:03<44:12,  1.58it/s]
 93%|█████████▎| 53418/57600 [9:24:03<42:31,  1.64it/s]
 93%|█████████▎| 53419/57600 [9:24:04<42:59,  1.62it/s]
 93%|█████████▎| 53420/57600 [9:24:04<41:35,  1.68it/s]
                                                       
{'loss': 1.0957, 'learning_rate': 1.6554006968641115e-07, 'epoch': 589.62}

 93%|█████████▎| 53420/57600 [9:24:04<41:35,  1.68it/s]
 93%|█████████▎| 53421/57600 [9:24:05<42:10,  1.65it/s]
 93%|█████████▎| 53422/57600 [9:24:06<42:12,  1.65it/s]
 93%|█████████▎| 53423/57600 [9:24:06<42:04,  1.65it/s]
 93%|█████████▎| 53424/57600 [9:24:07<43:24,  1.60it/s]
 93%|█████████▎| 53425/57600 [9:24:08<44:23,  1.57it/s]
 93%|█████████▎| 53426/57600 [9:24:08<43:26,  1.60it/s]
 93%|█████████▎| 53427/57600 [9:24:09<43:00,  1.62it/s]
 93%|█████████▎| 53428/57600 [9:24:09<44:48,  1.55it/s]
 93%|█████████▎| 53429/57600 [9:24:10<43:36,  1.59it/s]
 93%|█████████▎| 53430/57600 [9:24:11<41:59,  1.66it/s]
 93%|█████████▎| 53431/57600 [9:24:11<42:57,  1.62it/s]
 93%|█████████▎| 53432/57600 [9:24:12<42:08,  1.65it/s]
 93%|█████████▎| 53433/57600 [9:24:12<41:04,  1.69it/s]
 93%|█████████▎| 53434/57600 [9:24:13<41:25,  1.68it/s]
 93%|█████████▎| 53435/57600 [9:24:14<41:41,  1.67it/s]
 93%|█████████▎| 53436/57600 [9:24:14<41:15,  1.68it/s]
 93%|█████████▎| 53437/57600 [9:24:15<43:26,  1.60it/s]
 93%|█████████▎| 53438/57600 [9:24:16<43:05,  1.61it/s]
 93%|█████████▎| 53439/57600 [9:24:16<44:36,  1.55it/s]
 93%|█████████▎| 53440/57600 [9:24:17<45:08,  1.54it/s]
                                                       
{'loss': 1.0978, 'learning_rate': 1.6522648083623698e-07, 'epoch': 589.85}

 93%|█████████▎| 53440/57600 [9:24:17<45:08,  1.54it/s]
 93%|█████████▎| 53441/57600 [9:24:17<43:44,  1.58it/s]
 93%|█████████▎| 53442/57600 [9:24:18<44:12,  1.57it/s]
 93%|█████████▎| 53443/57600 [9:24:19<43:13,  1.60it/s]
 93%|█████████▎| 53444/57600 [9:24:19<42:06,  1.65it/s]
 93%|█████████▎| 53445/57600 [9:24:20<41:22,  1.67it/s]
 93%|█████████▎| 53446/57600 [9:24:20<41:41,  1.66it/s]
 93%|█████████▎| 53447/57600 [9:24:21<41:36,  1.66it/s]
 93%|█████████▎| 53448/57600 [9:24:22<40:31,  1.71it/s]
 93%|█████████▎| 53449/57600 [9:24:22<40:23,  1.71it/s]
 93%|█████████▎| 53450/57600 [9:24:23<41:51,  1.65it/s]
 93%|█████████▎| 53451/57600 [9:24:23<42:10,  1.64it/s]
 93%|█████████▎| 53452/57600 [9:24:24<42:30,  1.63it/s]
 93%|█████████▎| 53453/57600 [9:24:25<42:49,  1.61it/s]
 93%|█████████▎| 53454/57600 [9:24:25<42:45,  1.62it/s]
 93%|█████████▎| 53455/57600 [9:24:26<45:12,  1.53it/s]
 93%|█████████▎| 53456/57600 [9:24:27<45:05,  1.53it/s]
 93%|█████████▎| 53457/57600 [9:24:27<45:50,  1.51it/s]
 93%|█████████▎| 53458/57600 [9:24:28<44:47,  1.54it/s]
 93%|█████████▎| 53459/57600 [9:24:29<43:59,  1.57it/s]
 93%|█████████▎| 53460/57600 [9:24:29<43:17,  1.59it/s]
                                                       
{'loss': 1.1119, 'learning_rate': 1.649128919860627e-07, 'epoch': 590.07}

 93%|█████████▎| 53460/57600 [9:24:29<43:17,  1.59it/s]
 93%|█████████▎| 53461/57600 [9:24:30<44:21,  1.55it/s]
 93%|█████████▎| 53462/57600 [9:24:31<44:05,  1.56it/s]
 93%|█████████▎| 53463/57600 [9:24:31<43:35,  1.58it/s]
 93%|█████████▎| 53464/57600 [9:24:32<44:18,  1.56it/s]
 93%|█████████▎| 53465/57600 [9:24:32<43:34,  1.58it/s]
 93%|█████████▎| 53466/57600 [9:24:33<42:12,  1.63it/s]
 93%|█████████▎| 53467/57600 [9:24:34<41:20,  1.67it/s]
 93%|█████████▎| 53468/57600 [9:24:34<41:30,  1.66it/s]
 93%|█████████▎| 53469/57600 [9:24:35<41:25,  1.66it/s]
 93%|█████████▎| 53470/57600 [9:24:35<42:19,  1.63it/s]
 93%|█████████▎| 53471/57600 [9:24:36<42:32,  1.62it/s]
 93%|█████████▎| 53472/57600 [9:24:37<44:59,  1.53it/s]
 93%|█████████▎| 53473/57600 [9:24:37<44:51,  1.53it/s]
 93%|█████████▎| 53474/57600 [9:24:38<44:17,  1.55it/s]
 93%|█████████▎| 53475/57600 [9:24:39<42:52,  1.60it/s]
 93%|█████████▎| 53476/57600 [9:24:39<43:06,  1.59it/s]
 93%|█████████▎| 53477/57600 [9:24:40<44:46,  1.53it/s]
 93%|█████████▎| 53478/57600 [9:24:41<44:18,  1.55it/s]
 93%|█████████▎| 53479/57600 [9:24:41<42:50,  1.60it/s]
 93%|█████████▎| 53480/57600 [9:24:42<43:59,  1.56it/s]
                                                       
{'loss': 1.1089, 'learning_rate': 1.6459930313588853e-07, 'epoch': 590.29}

 93%|█████████▎| 53480/57600 [9:24:42<43:59,  1.56it/s]
 93%|█████████▎| 53481/57600 [9:24:42<42:25,  1.62it/s]
 93%|█████████▎| 53482/57600 [9:24:43<42:11,  1.63it/s]
 93%|█████████▎| 53483/57600 [9:24:44<42:33,  1.61it/s]
 93%|█████████▎| 53484/57600 [9:24:44<41:40,  1.65it/s]
 93%|█████████▎| 53485/57600 [9:24:45<42:33,  1.61it/s]
 93%|█████████▎| 53486/57600 [9:24:46<42:59,  1.60it/s]
 93%|█████████▎| 53487/57600 [9:24:46<43:25,  1.58it/s]
 93%|█████████▎| 53488/57600 [9:24:47<44:03,  1.56it/s]
 93%|█████████▎| 53489/57600 [9:24:47<42:28,  1.61it/s]
 93%|█████████▎| 53490/57600 [9:24:48<43:00,  1.59it/s]
 93%|█████████▎| 53491/57600 [9:24:49<42:00,  1.63it/s]
 93%|█████████▎| 53492/57600 [9:24:49<41:03,  1.67it/s]
 93%|█████████▎| 53493/57600 [9:24:50<42:09,  1.62it/s]
 93%|█████████▎| 53494/57600 [9:24:50<41:42,  1.64it/s]
 93%|█████████▎| 53495/57600 [9:24:51<40:53,  1.67it/s]
 93%|█████████▎| 53496/57600 [9:24:52<39:53,  1.71it/s]
 93%|█████████▎| 53497/57600 [9:24:52<40:38,  1.68it/s]
 93%|█████████▎| 53498/57600 [9:24:53<41:36,  1.64it/s]
 93%|█████████▎| 53499/57600 [9:24:53<42:21,  1.61it/s]
 93%|█████████▎| 53500/57600 [9:24:54<41:46,  1.64it/s]
                                                       
{'loss': 1.1268, 'learning_rate': 1.6428571428571423e-07, 'epoch': 590.51}

 93%|█████████▎| 53500/57600 [9:24:54<41:46,  1.64it/s]
 93%|█████████▎| 53501/57600 [9:24:55<41:14,  1.66it/s]
 93%|█████████▎| 53502/57600 [9:24:55<40:23,  1.69it/s]
 93%|█████████▎| 53503/57600 [9:24:56<41:18,  1.65it/s]
 93%|█████████▎| 53504/57600 [9:24:56<40:29,  1.69it/s]
 93%|█████████▎| 53505/57600 [9:24:57<41:35,  1.64it/s]
 93%|█████████▎| 53506/57600 [9:24:58<41:52,  1.63it/s]
 93%|█████████▎| 53507/57600 [9:24:58<42:43,  1.60it/s]
 93%|█████████▎| 53508/57600 [9:24:59<41:37,  1.64it/s]
 93%|█████████▎| 53509/57600 [9:25:00<41:57,  1.63it/s]
 93%|█████████▎| 53510/57600 [9:25:00<41:30,  1.64it/s]
 93%|█████████▎| 53511/57600 [9:25:01<42:26,  1.61it/s]
 93%|█████████▎| 53512/57600 [9:25:01<42:57,  1.59it/s]
 93%|█████████▎| 53513/57600 [9:25:02<43:04,  1.58it/s]
 93%|█████████▎| 53514/57600 [9:25:03<43:15,  1.57it/s]
 93%|█████████▎| 53515/57600 [9:25:03<42:52,  1.59it/s]
 93%|█████████▎| 53516/57600 [9:25:04<42:57,  1.58it/s]
 93%|█████████▎| 53517/57600 [9:25:05<41:29,  1.64it/s]
 93%|█████████▎| 53518/57600 [9:25:05<42:18,  1.61it/s]
 93%|█████████▎| 53519/57600 [9:25:06<42:54,  1.59it/s]
 93%|█████████▎| 53520/57600 [9:25:06<41:37,  1.63it/s]
                                                       
{'loss': 1.1326, 'learning_rate': 1.639721254355401e-07, 'epoch': 590.73}

 93%|█████████▎| 53520/57600 [9:25:06<41:37,  1.63it/s]
 93%|█████████▎| 53521/57600 [9:25:07<42:30,  1.60it/s]
 93%|█████████▎| 53522/57600 [9:25:08<44:03,  1.54it/s]
 93%|█████████▎| 53523/57600 [9:25:08<43:51,  1.55it/s]
 93%|█████████▎| 53524/57600 [9:25:09<43:33,  1.56it/s]
 93%|█████████▎| 53525/57600 [9:25:10<44:35,  1.52it/s]
 93%|█████████▎| 53526/57600 [9:25:10<44:18,  1.53it/s]
 93%|█████████▎| 53527/57600 [9:25:11<43:44,  1.55it/s]
 93%|█████████▎| 53528/57600 [9:25:12<42:50,  1.58it/s]
 93%|█████████▎| 53529/57600 [9:25:12<42:41,  1.59it/s]
 93%|█████████▎| 53530/57600 [9:25:13<41:26,  1.64it/s]
 93%|█████████▎| 53531/57600 [9:25:13<41:00,  1.65it/s]
 93%|█████████▎| 53532/57600 [9:25:14<40:30,  1.67it/s]
 93%|█████████▎| 53533/57600 [9:25:15<40:09,  1.69it/s]
 93%|█████████▎| 53534/57600 [9:25:15<41:25,  1.64it/s]
 93%|█████████▎| 53535/57600 [9:25:16<42:05,  1.61it/s]
 93%|█████████▎| 53536/57600 [9:25:16<42:07,  1.61it/s]
 93%|█████████▎| 53537/57600 [9:25:17<41:52,  1.62it/s]
 93%|█████████▎| 53538/57600 [9:25:18<41:07,  1.65it/s]
 93%|█████████▎| 53539/57600 [9:25:18<42:22,  1.60it/s]
 93%|█████████▎| 53540/57600 [9:25:19<42:34,  1.59it/s]
                                                       
{'loss': 1.106, 'learning_rate': 1.636585365853658e-07, 'epoch': 590.95}

 93%|█████████▎| 53540/57600 [9:25:19<42:34,  1.59it/s]
 93%|█████████▎| 53541/57600 [9:25:20<43:11,  1.57it/s]
 93%|█████████▎| 53542/57600 [9:25:20<42:38,  1.59it/s]
 93%|█████████▎| 53543/57600 [9:25:21<42:25,  1.59it/s]
 93%|█████████▎| 53544/57600 [9:25:22<42:55,  1.57it/s]
 93%|█████████▎| 53545/57600 [9:25:22<43:13,  1.56it/s]
 93%|█████████▎| 53546/57600 [9:25:23<42:17,  1.60it/s]
 93%|█████████▎| 53547/57600 [9:25:23<42:45,  1.58it/s]
 93%|█████████▎| 53548/57600 [9:25:24<41:54,  1.61it/s]
 93%|█████████▎| 53549/57600 [9:25:25<42:25,  1.59it/s]
 93%|█████████▎| 53550/57600 [9:25:25<41:56,  1.61it/s]
 93%|█████████▎| 53551/57600 [9:25:26<42:33,  1.59it/s]
 93%|█████████▎| 53552/57600 [9:25:26<41:00,  1.64it/s]
 93%|█████████▎| 53553/57600 [9:25:27<40:43,  1.66it/s]
 93%|█████████▎| 53554/57600 [9:25:28<41:01,  1.64it/s]
 93%|█████████▎| 53555/57600 [9:25:28<41:45,  1.61it/s]
 93%|█████████▎| 53556/57600 [9:25:29<40:25,  1.67it/s]
 93%|█████████▎| 53557/57600 [9:25:30<41:14,  1.63it/s]
 93%|█████████▎| 53558/57600 [9:25:30<40:26,  1.67it/s]
 93%|█████████▎| 53559/57600 [9:25:31<41:51,  1.61it/s]
 93%|█████████▎| 53560/57600 [9:25:31<40:48,  1.65it/s]
                                                       
{'loss': 1.1175, 'learning_rate': 1.6334494773519165e-07, 'epoch': 591.17}

 93%|█████████▎| 53560/57600 [9:25:31<40:48,  1.65it/s]
 93%|█████████▎| 53561/57600 [9:25:32<41:02,  1.64it/s]
 93%|█████████▎| 53562/57600 [9:25:33<41:44,  1.61it/s]
 93%|█████████▎| 53563/57600 [9:25:33<40:20,  1.67it/s]
 93%|█████████▎| 53564/57600 [9:25:34<41:45,  1.61it/s]
 93%|█████████▎| 53565/57600 [9:25:34<41:05,  1.64it/s]
 93%|█████████▎| 53566/57600 [9:25:35<40:05,  1.68it/s]
 93%|█████████▎| 53567/57600 [9:25:36<39:20,  1.71it/s]
 93%|█████████▎| 53568/57600 [9:25:36<39:49,  1.69it/s]
 93%|█████████▎| 53569/57600 [9:25:37<40:56,  1.64it/s]
 93%|█████████▎| 53570/57600 [9:25:38<43:16,  1.55it/s]
 93%|█████████▎| 53571/57600 [9:25:38<42:02,  1.60it/s]
 93%|█████████▎| 53572/57600 [9:25:39<42:06,  1.59it/s]
 93%|█████████▎| 53573/57600 [9:25:39<40:46,  1.65it/s]
 93%|█████████▎| 53574/57600 [9:25:40<40:39,  1.65it/s]
 93%|█████████▎| 53575/57600 [9:25:41<42:36,  1.57it/s]
 93%|█████████▎| 53576/57600 [9:25:41<43:43,  1.53it/s]
 93%|█████████▎| 53577/57600 [9:25:42<43:37,  1.54it/s]
 93%|█████████▎| 53578/57600 [9:25:43<42:58,  1.56it/s]
 93%|█████████▎| 53579/57600 [9:25:43<42:36,  1.57it/s]
 93%|█████████▎| 53580/57600 [9:25:44<44:20,  1.51it/s]
                                                       
{'loss': 1.1013, 'learning_rate': 1.6303135888501745e-07, 'epoch': 591.39}

 93%|█████████▎| 53580/57600 [9:25:44<44:20,  1.51it/s]
 93%|█████████▎| 53581/57600 [9:25:45<43:45,  1.53it/s]
 93%|█████████▎| 53582/57600 [9:25:45<42:41,  1.57it/s]
 93%|█████████▎| 53583/57600 [9:25:46<41:19,  1.62it/s]
 93%|█████████▎| 53584/57600 [9:25:46<40:57,  1.63it/s]
 93%|█████████▎| 53585/57600 [9:25:47<40:15,  1.66it/s]
 93%|█████████▎| 53586/57600 [9:25:47<39:56,  1.68it/s]
 93%|█████████▎| 53587/57600 [9:25:48<41:01,  1.63it/s]
 93%|█████████▎| 53588/57600 [9:25:49<41:17,  1.62it/s]
 93%|█████████▎| 53589/57600 [9:25:49<41:20,  1.62it/s]
 93%|█████████▎| 53590/57600 [9:25:50<40:42,  1.64it/s]
 93%|█████████▎| 53591/57600 [9:25:51<41:23,  1.61it/s]
 93%|█████████▎| 53592/57600 [9:25:51<41:23,  1.61it/s]
 93%|█████████▎| 53593/57600 [9:25:52<42:52,  1.56it/s]
 93%|█████████▎| 53594/57600 [9:25:52<41:34,  1.61it/s]
 93%|█████████▎| 53595/57600 [9:25:53<41:42,  1.60it/s]
 93%|█████████▎| 53596/57600 [9:25:54<42:45,  1.56it/s]
 93%|█████████▎| 53597/57600 [9:25:54<42:44,  1.56it/s]
 93%|█████████▎| 53598/57600 [9:25:55<41:36,  1.60it/s]
 93%|█████████▎| 53599/57600 [9:25:56<41:05,  1.62it/s]
 93%|█████████▎| 53600/57600 [9:25:56<41:22,  1.61it/s]
                                                       
{'loss': 1.1234, 'learning_rate': 1.6271777003484318e-07, 'epoch': 591.61}

 93%|█████████▎| 53600/57600 [9:25:56<41:22,  1.61it/s]
 93%|█████████▎| 53601/57600 [9:25:57<40:59,  1.63it/s]
 93%|█████████▎| 53602/57600 [9:25:57<41:11,  1.62it/s]
 93%|█████████▎| 53603/57600 [9:25:58<44:10,  1.51it/s]
 93%|█████████▎| 53604/57600 [9:25:59<42:02,  1.58it/s]
 93%|█████████▎| 53605/57600 [9:25:59<41:17,  1.61it/s]
 93%|█████████▎| 53606/57600 [9:26:00<40:20,  1.65it/s]
 93%|█████████▎| 53607/57600 [9:26:01<40:22,  1.65it/s]
 93%|█████████▎| 53608/57600 [9:26:01<41:30,  1.60it/s]
 93%|█████████▎| 53609/57600 [9:26:02<42:29,  1.57it/s]
 93%|█████████▎| 53610/57600 [9:26:02<41:03,  1.62it/s]
 93%|█████████▎| 53611/57600 [9:26:03<41:19,  1.61it/s]
 93%|█████████▎| 53612/57600 [9:26:04<41:05,  1.62it/s]
 93%|█████████▎| 53613/57600 [9:26:04<39:44,  1.67it/s]
 93%|█████████▎| 53614/57600 [9:26:05<40:38,  1.63it/s]
 93%|█████████▎| 53615/57600 [9:26:06<40:26,  1.64it/s]
 93%|█████████▎| 53616/57600 [9:26:06<41:49,  1.59it/s]
 93%|█████████▎| 53617/57600 [9:26:07<42:46,  1.55it/s]
 93%|█████████▎| 53618/57600 [9:26:07<41:34,  1.60it/s]
 93%|█████████▎| 53619/57600 [9:26:08<41:42,  1.59it/s]
 93%|█████████▎| 53620/57600 [9:26:09<42:22,  1.57it/s]
                                                       
{'loss': 1.1097, 'learning_rate': 1.62404181184669e-07, 'epoch': 591.83}

 93%|█████████▎| 53620/57600 [9:26:09<42:22,  1.57it/s]
 93%|█████████▎| 53621/57600 [9:26:09<41:40,  1.59it/s]
 93%|█████████▎| 53622/57600 [9:26:10<40:38,  1.63it/s]
 93%|█████████▎| 53623/57600 [9:26:11<41:19,  1.60it/s]
 93%|█████████▎| 53624/57600 [9:26:11<40:52,  1.62it/s]
 93%|█████████▎| 53625/57600 [9:26:12<39:59,  1.66it/s]
 93%|█████████▎| 53626/57600 [9:26:12<41:57,  1.58it/s]
 93%|█████████▎| 53627/57600 [9:26:13<42:56,  1.54it/s]
 93%|█████████▎| 53628/57600 [9:26:14<43:26,  1.52it/s]
 93%|█████████▎| 53629/57600 [9:26:14<42:53,  1.54it/s]
 93%|█████████▎| 53630/57600 [9:26:15<42:22,  1.56it/s]
 93%|█████████▎| 53631/57600 [9:26:16<42:59,  1.54it/s]
 93%|█████████▎| 53632/57600 [9:26:16<44:48,  1.48it/s]
 93%|█████████▎| 53633/57600 [9:26:17<45:20,  1.46it/s]
 93%|█████████▎| 53634/57600 [9:26:18<43:39,  1.51it/s]
 93%|█████████▎| 53635/57600 [9:26:18<42:17,  1.56it/s]
 93%|█████████▎| 53636/57600 [9:26:19<45:43,  1.44it/s]
 93%|█████████▎| 53637/57600 [9:26:20<45:26,  1.45it/s]
 93%|█████████▎| 53638/57600 [9:26:21<44:15,  1.49it/s]
 93%|█████████▎| 53639/57600 [9:26:21<42:41,  1.55it/s]
 93%|█████████▎| 53640/57600 [9:26:22<41:24,  1.59it/s]
                                                       
{'loss': 1.0873, 'learning_rate': 1.6209059233449473e-07, 'epoch': 592.05}

 93%|█████████▎| 53640/57600 [9:26:22<41:24,  1.59it/s]
 93%|█████████▎| 53641/57600 [9:26:22<42:45,  1.54it/s]
 93%|█████████▎| 53642/57600 [9:26:23<42:48,  1.54it/s]
 93%|█████████▎| 53643/57600 [9:26:24<41:53,  1.57it/s]
 93%|█████████▎| 53644/57600 [9:26:24<42:13,  1.56it/s]
 93%|█████████▎| 53645/57600 [9:26:25<41:25,  1.59it/s]
 93%|█████████▎| 53646/57600 [9:26:25<40:36,  1.62it/s]
 93%|█████████▎| 53647/57600 [9:26:26<40:00,  1.65it/s]
 93%|█████████▎| 53648/57600 [9:26:27<41:31,  1.59it/s]
 93%|█████████▎| 53649/57600 [9:26:27<41:49,  1.57it/s]
 93%|█████████▎| 53650/57600 [9:26:28<40:48,  1.61it/s]
 93%|█████████▎| 53651/57600 [9:26:29<40:39,  1.62it/s]
 93%|█████████▎| 53652/57600 [9:26:29<41:31,  1.58it/s]
 93%|█████████▎| 53653/57600 [9:26:30<42:03,  1.56it/s]
 93%|█████████▎| 53654/57600 [9:26:30<40:58,  1.60it/s]
 93%|█████████▎| 53655/57600 [9:26:31<41:10,  1.60it/s]
 93%|█████████▎| 53656/57600 [9:26:32<39:32,  1.66it/s]
 93%|█████████▎| 53657/57600 [9:26:32<39:26,  1.67it/s]
 93%|█████████▎| 53658/57600 [9:26:33<39:26,  1.67it/s]
 93%|█████████▎| 53659/57600 [9:26:33<39:09,  1.68it/s]
 93%|█████████▎| 53660/57600 [9:26:34<38:51,  1.69it/s]
                                                       
{'loss': 1.1358, 'learning_rate': 1.6177700348432057e-07, 'epoch': 592.27}

 93%|█████████▎| 53660/57600 [9:26:34<38:51,  1.69it/s]
 93%|█████████▎| 53661/57600 [9:26:35<39:38,  1.66it/s]
 93%|█████████▎| 53662/57600 [9:26:35<39:53,  1.65it/s]
 93%|█████████▎| 53663/57600 [9:26:36<39:34,  1.66it/s]
 93%|█████████▎| 53664/57600 [9:26:36<38:59,  1.68it/s]
 93%|█████████▎| 53665/57600 [9:26:37<40:18,  1.63it/s]
 93%|█████████▎| 53666/57600 [9:26:38<41:50,  1.57it/s]
 93%|█████████▎| 53667/57600 [9:26:38<41:35,  1.58it/s]
 93%|█████████▎| 53668/57600 [9:26:39<41:02,  1.60it/s]
 93%|█████████▎| 53669/57600 [9:26:40<39:58,  1.64it/s]
 93%|█████████▎| 53670/57600 [9:26:40<40:20,  1.62it/s]
 93%|█████████▎| 53671/57600 [9:26:41<40:20,  1.62it/s]
 93%|█████████▎| 53672/57600 [9:26:42<41:19,  1.58it/s]
 93%|█████████▎| 53673/57600 [9:26:42<40:44,  1.61it/s]
 93%|█████████▎| 53674/57600 [9:26:43<40:40,  1.61it/s]
 93%|█████████▎| 53675/57600 [9:26:43<40:10,  1.63it/s]
 93%|█████████▎| 53676/57600 [9:26:44<39:26,  1.66it/s]
 93%|█████████▎| 53677/57600 [9:26:45<40:36,  1.61it/s]
 93%|█████████▎| 53678/57600 [9:26:45<40:49,  1.60it/s]
 93%|█████████▎| 53679/57600 [9:26:46<41:52,  1.56it/s]
 93%|█████████▎| 53680/57600 [9:26:47<43:26,  1.50it/s]
                                                       
{'loss': 1.099, 'learning_rate': 1.614634146341463e-07, 'epoch': 592.49}

 93%|█████████▎| 53680/57600 [9:26:47<43:26,  1.50it/s]
 93%|█████████▎| 53681/57600 [9:26:47<42:07,  1.55it/s]
 93%|█████████▎| 53682/57600 [9:26:48<42:55,  1.52it/s]
 93%|█████████▎| 53683/57600 [9:26:49<43:41,  1.49it/s]
 93%|█████████▎| 53684/57600 [9:26:49<42:50,  1.52it/s]
 93%|█████████▎| 53685/57600 [9:26:50<42:04,  1.55it/s]
 93%|█████████▎| 53686/57600 [9:26:50<40:39,  1.60it/s]
 93%|█████████▎| 53687/57600 [9:26:51<40:46,  1.60it/s]
 93%|█████████▎| 53688/57600 [9:26:52<41:02,  1.59it/s]
 93%|█████████▎| 53689/57600 [9:26:52<41:27,  1.57it/s]
 93%|█████████▎| 53690/57600 [9:26:53<41:29,  1.57it/s]
 93%|█████████▎| 53691/57600 [9:26:54<42:39,  1.53it/s]
 93%|█████████▎| 53692/57600 [9:26:54<42:09,  1.54it/s]
 93%|█████████▎| 53693/57600 [9:26:55<43:53,  1.48it/s]
 93%|█████████▎| 53694/57600 [9:26:56<43:14,  1.51it/s]
 93%|█████████▎| 53695/57600 [9:26:56<43:27,  1.50it/s]
 93%|█████████▎| 53696/57600 [9:26:57<43:08,  1.51it/s]
 93%|█████████▎| 53697/57600 [9:26:58<42:45,  1.52it/s]
 93%|█████████▎| 53698/57600 [9:26:58<41:41,  1.56it/s]
 93%|█████████▎| 53699/57600 [9:26:59<43:32,  1.49it/s]
 93%|█████████▎| 53700/57600 [9:27:00<42:15,  1.54it/s]
                                                       
{'loss': 1.1032, 'learning_rate': 1.6114982578397212e-07, 'epoch': 592.72}

 93%|█████████▎| 53700/57600 [9:27:00<42:15,  1.54it/s]
 93%|█████████▎| 53701/57600 [9:27:00<40:46,  1.59it/s]
 93%|█████████▎| 53702/57600 [9:27:01<40:26,  1.61it/s]
 93%|█████████▎| 53703/57600 [9:27:01<40:51,  1.59it/s]
 93%|█████████▎| 53704/57600 [9:27:02<40:53,  1.59it/s]
 93%|█████████▎| 53705/57600 [9:27:03<39:58,  1.62it/s]
 93%|█████████▎| 53706/57600 [9:27:03<40:04,  1.62it/s]
 93%|█████████▎| 53707/57600 [9:27:04<40:25,  1.61it/s]
 93%|█████████▎| 53708/57600 [9:27:04<39:43,  1.63it/s]
 93%|█████████▎| 53709/57600 [9:27:05<39:36,  1.64it/s]
 93%|█████████▎| 53710/57600 [9:27:06<42:19,  1.53it/s]
 93%|█████████▎| 53711/57600 [9:27:06<40:54,  1.58it/s]
 93%|█████████▎| 53712/57600 [9:27:07<40:09,  1.61it/s]
 93%|█████████▎| 53713/57600 [9:27:08<41:27,  1.56it/s]
 93%|█████████▎| 53714/57600 [9:27:08<40:12,  1.61it/s]
 93%|█████████▎| 53715/57600 [9:27:09<39:34,  1.64it/s]
 93%|█████████▎| 53716/57600 [9:27:09<39:10,  1.65it/s]
 93%|█████████▎| 53717/57600 [9:27:10<41:11,  1.57it/s]
 93%|█████████▎| 53718/57600 [9:27:11<41:51,  1.55it/s]
 93%|█████████▎| 53719/57600 [9:27:11<41:18,  1.57it/s]
 93%|█████████▎| 53720/57600 [9:27:12<39:45,  1.63it/s]
                                                       
{'loss': 1.148, 'learning_rate': 1.608362369337979e-07, 'epoch': 592.94}

 93%|█████████▎| 53720/57600 [9:27:12<39:45,  1.63it/s]
 93%|█████████▎| 53721/57600 [9:27:13<39:40,  1.63it/s]
 93%|█████████▎| 53722/57600 [9:27:13<41:04,  1.57it/s]
 93%|█████████▎| 53723/57600 [9:27:14<41:08,  1.57it/s]
 93%|█████████▎| 53724/57600 [9:27:15<41:46,  1.55it/s]
 93%|█████████▎| 53725/57600 [9:27:15<41:22,  1.56it/s]
 93%|█████████▎| 53726/57600 [9:27:16<42:57,  1.50it/s]
 93%|█████████▎| 53727/57600 [9:27:17<43:59,  1.47it/s]
 93%|█████████▎| 53728/57600 [9:27:17<42:50,  1.51it/s]
 93%|█████████▎| 53729/57600 [9:27:18<42:31,  1.52it/s]
 93%|█████████▎| 53730/57600 [9:27:19<42:25,  1.52it/s]
 93%|█████████▎| 53731/57600 [9:27:19<42:01,  1.53it/s]
 93%|█████████▎| 53732/57600 [9:27:20<42:41,  1.51it/s]
 93%|█████████▎| 53733/57600 [9:27:21<41:26,  1.56it/s]
 93%|█████████▎| 53734/57600 [9:27:21<41:15,  1.56it/s]
 93%|█████████▎| 53735/57600 [9:27:22<41:27,  1.55it/s]
 93%|█████████▎| 53736/57600 [9:27:22<41:56,  1.54it/s]
 93%|█████████▎| 53737/57600 [9:27:23<41:44,  1.54it/s]
 93%|█████████▎| 53738/57600 [9:27:24<41:28,  1.55it/s]
 93%|█████████▎| 53739/57600 [9:27:24<41:51,  1.54it/s]
 93%|█████████▎| 53740/57600 [9:27:25<41:32,  1.55it/s]
                                                       
{'loss': 1.0725, 'learning_rate': 1.6052264808362368e-07, 'epoch': 593.16}

 93%|█████████▎| 53740/57600 [9:27:25<41:32,  1.55it/s]
 93%|█████████▎| 53741/57600 [9:27:26<42:23,  1.52it/s]
 93%|█████████▎| 53742/57600 [9:27:26<43:22,  1.48it/s]
 93%|█████████▎| 53743/57600 [9:27:27<42:04,  1.53it/s]
 93%|█████████▎| 53744/57600 [9:27:28<41:30,  1.55it/s]
 93%|█████████▎| 53745/57600 [9:27:28<41:43,  1.54it/s]
 93%|█████████▎| 53746/57600 [9:27:29<41:05,  1.56it/s]
 93%|█████████▎| 53747/57600 [9:27:30<40:28,  1.59it/s]
 93%|█████████▎| 53748/57600 [9:27:30<40:13,  1.60it/s]
 93%|█████████▎| 53749/57600 [9:27:31<40:38,  1.58it/s]
 93%|█████████▎| 53750/57600 [9:27:32<41:44,  1.54it/s]
 93%|█████████▎| 53751/57600 [9:27:32<41:50,  1.53it/s]
 93%|█████████▎| 53752/57600 [9:27:33<41:32,  1.54it/s]
 93%|█████████▎| 53753/57600 [9:27:33<40:55,  1.57it/s]
 93%|█████████▎| 53754/57600 [9:27:34<41:27,  1.55it/s]
 93%|█████████▎| 53755/57600 [9:27:35<40:30,  1.58it/s]
 93%|█████████▎| 53756/57600 [9:27:35<39:55,  1.60it/s]
 93%|█████████▎| 53757/57600 [9:27:36<39:33,  1.62it/s]
 93%|█████████▎| 53758/57600 [9:27:37<39:46,  1.61it/s]
 93%|█████████▎| 53759/57600 [9:27:37<41:20,  1.55it/s]
 93%|█████████▎| 53760/57600 [9:27:38<41:02,  1.56it/s]
                                                       
{'loss': 1.1253, 'learning_rate': 1.6020905923344948e-07, 'epoch': 593.38}

 93%|█████████▎| 53760/57600 [9:27:38<41:02,  1.56it/s]
 93%|█████████▎| 53761/57600 [9:27:39<42:04,  1.52it/s]
 93%|█████████▎| 53762/57600 [9:27:39<41:41,  1.53it/s]
 93%|█████████▎| 53763/57600 [9:27:40<40:45,  1.57it/s]
 93%|█████████▎| 53764/57600 [9:27:40<40:49,  1.57it/s]
 93%|█████████▎| 53765/57600 [9:27:41<40:14,  1.59it/s]
 93%|█████████▎| 53766/57600 [9:27:42<39:58,  1.60it/s]
 93%|█████████▎| 53767/57600 [9:27:42<39:58,  1.60it/s]
 93%|█████████▎| 53768/57600 [9:27:43<39:51,  1.60it/s]
 93%|█████████▎| 53769/57600 [9:27:44<40:52,  1.56it/s]
 93%|█████████▎| 53770/57600 [9:27:44<40:17,  1.58it/s]
 93%|█████████▎| 53771/57600 [9:27:45<40:03,  1.59it/s]
 93%|█████████▎| 53772/57600 [9:27:46<41:24,  1.54it/s]
 93%|█████████▎| 53773/57600 [9:27:46<41:34,  1.53it/s]
 93%|█████████▎| 53774/57600 [9:27:47<41:50,  1.52it/s]
 93%|█████████▎| 53775/57600 [9:27:48<43:39,  1.46it/s]
 93%|█████████▎| 53776/57600 [9:27:48<44:03,  1.45it/s]
 93%|█████████▎| 53777/57600 [9:27:49<42:27,  1.50it/s]
 93%|█████████▎| 53778/57600 [9:27:50<42:09,  1.51it/s]
 93%|█████████▎| 53779/57600 [9:27:50<41:54,  1.52it/s]
 93%|█████████▎| 53780/57600 [9:27:51<43:27,  1.46it/s]
                                                       
{'loss': 1.0764, 'learning_rate': 1.5989547038327524e-07, 'epoch': 593.6}

 93%|█████████▎| 53780/57600 [9:27:51<43:27,  1.46it/s]
 93%|█████████▎| 53781/57600 [9:27:52<43:15,  1.47it/s]
 93%|█████████▎| 53782/57600 [9:27:52<42:07,  1.51it/s]
 93%|█████████▎| 53783/57600 [9:27:53<41:36,  1.53it/s]
 93%|█████████▎| 53784/57600 [9:27:54<40:39,  1.56it/s]
 93%|█████████▎| 53785/57600 [9:27:54<41:11,  1.54it/s]
 93%|█████████▎| 53786/57600 [9:27:55<41:30,  1.53it/s]
 93%|█████████▎| 53787/57600 [9:27:55<39:57,  1.59it/s]
 93%|█████████▎| 53788/57600 [9:27:56<41:22,  1.54it/s]
 93%|█████████▎| 53789/57600 [9:27:57<41:21,  1.54it/s]
 93%|█████████▎| 53790/57600 [9:27:57<40:47,  1.56it/s]
 93%|█████████▎| 53791/57600 [9:27:58<40:21,  1.57it/s]
 93%|█████████▎| 53792/57600 [9:27:59<39:52,  1.59it/s]
 93%|█████████▎| 53793/57600 [9:27:59<40:02,  1.58it/s]
 93%|█████████▎| 53794/57600 [9:28:00<40:16,  1.57it/s]
 93%|█████████▎| 53795/57600 [9:28:01<40:52,  1.55it/s]
 93%|█████████▎| 53796/57600 [9:28:01<42:33,  1.49it/s]
 93%|█████████▎| 53797/57600 [9:28:02<41:56,  1.51it/s]
 93%|█████████▎| 53798/57600 [9:28:03<40:31,  1.56it/s]
 93%|█████████▎| 53799/57600 [9:28:03<40:08,  1.58it/s]
 93%|█████████▎| 53800/57600 [9:28:04<40:30,  1.56it/s]
                                                       
{'loss': 1.1276, 'learning_rate': 1.5958188153310104e-07, 'epoch': 593.82}

 93%|█████████▎| 53800/57600 [9:28:04<40:30,  1.56it/s]
 93%|█████████▎| 53801/57600 [9:28:04<40:50,  1.55it/s]
 93%|█████████▎| 53802/57600 [9:28:05<40:22,  1.57it/s]
 93%|█████████▎| 53803/57600 [9:28:06<40:53,  1.55it/s]
 93%|█████████▎| 53804/57600 [9:28:06<39:39,  1.60it/s]
 93%|█████████▎| 53805/57600 [9:28:07<39:47,  1.59it/s]
 93%|█████████▎| 53806/57600 [9:28:08<40:09,  1.57it/s]
 93%|█████████▎| 53807/57600 [9:28:08<40:15,  1.57it/s]
 93%|█████████▎| 53808/57600 [9:28:09<39:30,  1.60it/s]
 93%|█████████▎| 53809/57600 [9:28:09<39:49,  1.59it/s]
 93%|█████████▎| 53810/57600 [9:28:10<39:31,  1.60it/s]
 93%|█████████▎| 53811/57600 [9:28:11<39:41,  1.59it/s]
 93%|█████████▎| 53812/57600 [9:28:11<40:37,  1.55it/s]
 93%|█████████▎| 53813/57600 [9:28:12<40:43,  1.55it/s]
 93%|█████████▎| 53814/57600 [9:28:13<39:38,  1.59it/s]
 93%|█████████▎| 53815/57600 [9:28:13<39:56,  1.58it/s]
 93%|█████████▎| 53816/57600 [9:28:14<38:38,  1.63it/s]
 93%|█████████▎| 53817/57600 [9:28:15<41:11,  1.53it/s]
 93%|█████████▎| 53818/57600 [9:28:15<39:44,  1.59it/s]
 93%|█████████▎| 53819/57600 [9:28:16<40:53,  1.54it/s]
 93%|█████████▎| 53820/57600 [9:28:17<40:13,  1.57it/s]
                                                       
{'loss': 1.143, 'learning_rate': 1.5926829268292677e-07, 'epoch': 594.04}

 93%|█████████▎| 53820/57600 [9:28:17<40:13,  1.57it/s]
 93%|█████████▎| 53821/57600 [9:28:17<40:39,  1.55it/s]
 93%|█████████▎| 53822/57600 [9:28:18<39:45,  1.58it/s]
 93%|█████████▎| 53823/57600 [9:28:18<39:04,  1.61it/s]
 93%|█████████▎| 53824/57600 [9:28:19<40:03,  1.57it/s]
 93%|█████████▎| 53825/57600 [9:28:20<38:57,  1.61it/s]
 93%|█████████▎| 53826/57600 [9:28:20<39:22,  1.60it/s]
 93%|█████████▎| 53827/57600 [9:28:21<38:28,  1.63it/s]
 93%|█████████▎| 53828/57600 [9:28:21<39:05,  1.61it/s]
 93%|█████████▎| 53829/57600 [9:28:22<38:47,  1.62it/s]
 93%|█████████▎| 53830/57600 [9:28:23<39:54,  1.57it/s]
 93%|█████████▎| 53831/57600 [9:28:23<40:25,  1.55it/s]
 93%|█████████▎| 53832/57600 [9:28:24<40:28,  1.55it/s]
 93%|█████████▎| 53833/57600 [9:28:25<41:01,  1.53it/s]
 93%|█████████▎| 53834/57600 [9:28:25<41:29,  1.51it/s]
 93%|█████████▎| 53835/57600 [9:28:26<41:47,  1.50it/s]
 93%|█████████▎| 53836/57600 [9:28:27<41:05,  1.53it/s]
 93%|█████████▎| 53837/57600 [9:28:27<41:04,  1.53it/s]
 93%|█████████▎| 53838/57600 [9:28:28<40:26,  1.55it/s]
 93%|█████████▎| 53839/57600 [9:28:29<39:25,  1.59it/s]
 93%|█████████▎| 53840/57600 [9:28:29<39:10,  1.60it/s]
                                                       
{'loss': 1.1045, 'learning_rate': 1.5895470383275257e-07, 'epoch': 594.26}

 93%|█████████▎| 53840/57600 [9:28:29<39:10,  1.60it/s]
 93%|█████████▎| 53841/57600 [9:28:30<40:19,  1.55it/s]
 93%|█████████▎| 53842/57600 [9:28:31<39:32,  1.58it/s]
 93%|█████████▎| 53843/57600 [9:28:31<39:04,  1.60it/s]
 93%|█████████▎| 53844/57600 [9:28:32<40:35,  1.54it/s]
 93%|█████████▎| 53845/57600 [9:28:32<40:50,  1.53it/s]
 93%|█████████▎| 53846/57600 [9:28:33<41:08,  1.52it/s]
 93%|█████████▎| 53847/57600 [9:28:34<39:44,  1.57it/s]
 93%|█████████▎| 53848/57600 [9:28:34<41:43,  1.50it/s]
 93%|█████████▎| 53849/57600 [9:28:35<41:05,  1.52it/s]
 93%|█████████▎| 53850/57600 [9:28:36<40:58,  1.53it/s]
 93%|█████████▎| 53851/57600 [9:28:36<40:10,  1.56it/s]
 93%|█████████▎| 53852/57600 [9:28:37<40:59,  1.52it/s]
 93%|█████████▎| 53853/57600 [9:28:38<40:26,  1.54it/s]
 93%|█████████▎| 53854/57600 [9:28:38<39:29,  1.58it/s]
 93%|█████████▎| 53855/57600 [9:28:39<40:41,  1.53it/s]
 94%|█████████▎| 53856/57600 [9:28:40<41:20,  1.51it/s]
 94%|█████████▎| 53857/57600 [9:28:40<41:11,  1.51it/s]
 94%|█████████▎| 53858/57600 [9:28:41<40:34,  1.54it/s]
 94%|█████████▎| 53859/57600 [9:28:42<40:28,  1.54it/s]
 94%|█████████▎| 53860/57600 [9:28:42<41:15,  1.51it/s]
                                                       
{'loss': 1.0981, 'learning_rate': 1.5864111498257843e-07, 'epoch': 594.48}

 94%|█████████▎| 53860/57600 [9:28:42<41:15,  1.51it/s]
 94%|█████████▎| 53861/57600 [9:28:43<40:19,  1.55it/s]
 94%|█████████▎| 53862/57600 [9:28:44<40:11,  1.55it/s]
 94%|█████████▎| 53863/57600 [9:28:44<39:48,  1.56it/s]
 94%|█████████▎| 53864/57600 [9:28:45<40:58,  1.52it/s]
 94%|█████████▎| 53865/57600 [9:28:46<40:33,  1.53it/s]
 94%|█████████▎| 53866/57600 [9:28:46<40:53,  1.52it/s]
 94%|█████████▎| 53867/57600 [9:28:47<39:46,  1.56it/s]
 94%|█████████▎| 53868/57600 [9:28:48<41:50,  1.49it/s]
 94%|█████████▎| 53869/57600 [9:28:48<40:47,  1.52it/s]
 94%|█████████▎| 53870/57600 [9:28:49<40:22,  1.54it/s]
 94%|█████████▎| 53871/57600 [9:28:49<39:54,  1.56it/s]
 94%|█████████▎| 53872/57600 [9:28:50<40:10,  1.55it/s]
 94%|█████████▎| 53873/57600 [9:28:51<39:34,  1.57it/s]
 94%|█████████▎| 53874/57600 [9:28:51<38:58,  1.59it/s]
 94%|█████████▎| 53875/57600 [9:28:52<39:25,  1.57it/s]
 94%|█████████▎| 53876/57600 [9:28:53<39:11,  1.58it/s]
 94%|█████████▎| 53877/57600 [9:28:53<40:10,  1.54it/s]
 94%|█████████▎| 53878/57600 [9:28:54<38:44,  1.60it/s]
 94%|█████████▎| 53879/57600 [9:28:54<38:44,  1.60it/s]
 94%|█████████▎| 53880/57600 [9:28:55<39:36,  1.57it/s]
                                                       
{'loss': 1.1159, 'learning_rate': 1.5832752613240415e-07, 'epoch': 594.7}

 94%|█████████▎| 53880/57600 [9:28:55<39:36,  1.57it/s]
 94%|█████████▎| 53881/57600 [9:28:56<39:38,  1.56it/s]
 94%|█████████▎| 53882/57600 [9:28:56<39:20,  1.58it/s]
 94%|█████████▎| 53883/57600 [9:28:57<39:53,  1.55it/s]
 94%|█████████▎| 53884/57600 [9:28:58<39:28,  1.57it/s]
 94%|█████████▎| 53885/57600 [9:28:58<38:50,  1.59it/s]
 94%|█████████▎| 53886/57600 [9:28:59<38:43,  1.60it/s]
 94%|█████████▎| 53887/57600 [9:29:00<38:33,  1.60it/s]
 94%|█████████▎| 53888/57600 [9:29:00<39:06,  1.58it/s]
 94%|█████████▎| 53889/57600 [9:29:01<39:35,  1.56it/s]
 94%|█████████▎| 53890/57600 [9:29:01<39:10,  1.58it/s]
 94%|█████████▎| 53891/57600 [9:29:02<38:07,  1.62it/s]
 94%|█████████▎| 53892/57600 [9:29:03<38:58,  1.59it/s]
 94%|█████████▎| 53893/57600 [9:29:03<39:19,  1.57it/s]
 94%|█████████▎| 53894/57600 [9:29:04<40:06,  1.54it/s]
 94%|█████████▎| 53895/57600 [9:29:05<40:17,  1.53it/s]
 94%|█████████▎| 53896/57600 [9:29:05<39:12,  1.57it/s]
 94%|█████████▎| 53897/57600 [9:29:06<39:26,  1.56it/s]
 94%|█████████▎| 53898/57600 [9:29:07<39:06,  1.58it/s]
 94%|█████████▎| 53899/57600 [9:29:07<39:15,  1.57it/s]
 94%|█████████▎| 53900/57600 [9:29:08<39:36,  1.56it/s]
                                                       
{'loss': 1.1132, 'learning_rate': 1.5801393728222999e-07, 'epoch': 594.92}

 94%|█████████▎| 53900/57600 [9:29:08<39:36,  1.56it/s]
 94%|█████████▎| 53901/57600 [9:29:08<39:38,  1.56it/s]
 94%|█████████▎| 53902/57600 [9:29:09<40:02,  1.54it/s]
 94%|█████████▎| 53903/57600 [9:29:10<38:58,  1.58it/s]
 94%|█████████▎| 53904/57600 [9:29:10<39:03,  1.58it/s]
 94%|█████████▎| 53905/57600 [9:29:11<39:43,  1.55it/s]
 94%|█████████▎| 53906/57600 [9:29:12<39:02,  1.58it/s]
 94%|█████████▎| 53907/57600 [9:29:12<38:47,  1.59it/s]
 94%|█████████▎| 53908/57600 [9:29:13<39:44,  1.55it/s]
 94%|█████████▎| 53909/57600 [9:29:14<38:43,  1.59it/s]
 94%|█████████▎| 53910/57600 [9:29:14<39:50,  1.54it/s]
 94%|█████████▎| 53911/57600 [9:29:15<39:00,  1.58it/s]
 94%|█████████▎| 53912/57600 [9:29:15<38:08,  1.61it/s]
 94%|█████████▎| 53913/57600 [9:29:16<38:58,  1.58it/s]
 94%|█████████▎| 53914/57600 [9:29:17<38:21,  1.60it/s]
 94%|█████████▎| 53915/57600 [9:29:17<37:42,  1.63it/s]
 94%|█████████▎| 53916/57600 [9:29:18<39:15,  1.56it/s]
 94%|█████████▎| 53917/57600 [9:29:19<39:39,  1.55it/s]
 94%|█████████▎| 53918/57600 [9:29:19<39:39,  1.55it/s]
 94%|█████████▎| 53919/57600 [9:29:20<40:10,  1.53it/s]
 94%|█████████▎| 53920/57600 [9:29:21<39:22,  1.56it/s]
                                                       
{'loss': 1.1365, 'learning_rate': 1.577003484320557e-07, 'epoch': 595.14}

 94%|█████████▎| 53920/57600 [9:29:21<39:22,  1.56it/s]
 94%|█████████▎| 53921/57600 [9:29:21<39:14,  1.56it/s]
 94%|█████████▎| 53922/57600 [9:29:22<39:17,  1.56it/s]
 94%|█████████▎| 53923/57600 [9:29:23<40:52,  1.50it/s]
 94%|█████████▎| 53924/57600 [9:29:23<39:05,  1.57it/s]
 94%|█████████▎| 53925/57600 [9:29:24<37:43,  1.62it/s]
 94%|█████████▎| 53926/57600 [9:29:24<37:46,  1.62it/s]
 94%|█████████▎| 53927/57600 [9:29:25<37:34,  1.63it/s]
 94%|█████████▎| 53928/57600 [9:29:26<37:58,  1.61it/s]
 94%|█████████▎| 53929/57600 [9:29:26<38:29,  1.59it/s]
 94%|█████████▎| 53930/57600 [9:29:27<38:23,  1.59it/s]
 94%|█████████▎| 53931/57600 [9:29:28<39:02,  1.57it/s]
 94%|█████████▎| 53932/57600 [9:29:28<38:32,  1.59it/s]
 94%|█████████▎| 53933/57600 [9:29:29<37:17,  1.64it/s]
 94%|█████████▎| 53934/57600 [9:29:29<38:47,  1.57it/s]
 94%|█████████▎| 53935/57600 [9:29:30<38:25,  1.59it/s]
 94%|█████████▎| 53936/57600 [9:29:31<38:20,  1.59it/s]
 94%|█████████▎| 53937/57600 [9:29:31<38:04,  1.60it/s]
 94%|█████████▎| 53938/57600 [9:29:32<38:02,  1.60it/s]
 94%|█████████▎| 53939/57600 [9:29:32<37:56,  1.61it/s]
 94%|█████████▎| 53940/57600 [9:29:33<37:16,  1.64it/s]
                                                       
{'loss': 1.1481, 'learning_rate': 1.5738675958188154e-07, 'epoch': 595.36}

 94%|█████████▎| 53940/57600 [9:29:33<37:16,  1.64it/s]
 94%|█████████▎| 53941/57600 [9:29:34<37:00,  1.65it/s]
 94%|█████████▎| 53942/57600 [9:29:34<37:17,  1.64it/s]
 94%|█████████▎| 53943/57600 [9:29:35<37:51,  1.61it/s]
 94%|█████████▎| 53944/57600 [9:29:36<38:16,  1.59it/s]
 94%|█████████▎| 53945/57600 [9:29:36<39:37,  1.54it/s]
 94%|█████████▎| 53946/57600 [9:29:37<39:28,  1.54it/s]
 94%|█████████▎| 53947/57600 [9:29:38<38:24,  1.59it/s]
 94%|█████████▎| 53948/57600 [9:29:38<37:50,  1.61it/s]
 94%|█████████▎| 53949/57600 [9:29:39<37:30,  1.62it/s]
 94%|█████████▎| 53950/57600 [9:29:39<37:59,  1.60it/s]
 94%|█████████▎| 53951/57600 [9:29:40<37:59,  1.60it/s]
 94%|█████████▎| 53952/57600 [9:29:41<37:50,  1.61it/s]
 94%|█████████▎| 53953/57600 [9:29:41<38:37,  1.57it/s]
 94%|█████████▎| 53954/57600 [9:29:42<38:00,  1.60it/s]
 94%|█████████▎| 53955/57600 [9:29:42<37:24,  1.62it/s]
 94%|█████████▎| 53956/57600 [9:29:43<39:13,  1.55it/s]
 94%|█████████▎| 53957/57600 [9:29:44<39:37,  1.53it/s]
 94%|█████████▎| 53958/57600 [9:29:44<38:57,  1.56it/s]
 94%|█████████▎| 53959/57600 [9:29:45<39:13,  1.55it/s]
 94%|█████████▎| 53960/57600 [9:29:46<38:23,  1.58it/s]
                                                       
{'loss': 1.0957, 'learning_rate': 1.5707317073170727e-07, 'epoch': 595.58}

 94%|█████████▎| 53960/57600 [9:29:46<38:23,  1.58it/s]
 94%|█████████▎| 53961/57600 [9:29:46<38:12,  1.59it/s]
 94%|█████████▎| 53962/57600 [9:29:47<39:15,  1.54it/s]
 94%|█████████▎| 53963/57600 [9:29:48<37:59,  1.60it/s]
 94%|█████████▎| 53964/57600 [9:29:48<39:18,  1.54it/s]
 94%|█████████▎| 53965/57600 [9:29:49<38:54,  1.56it/s]
 94%|█████████▎| 53966/57600 [9:29:50<38:27,  1.57it/s]
 94%|█████████▎| 53967/57600 [9:29:50<38:17,  1.58it/s]
 94%|█████████▎| 53968/57600 [9:29:51<39:44,  1.52it/s]
 94%|█████████▎| 53969/57600 [9:29:52<39:58,  1.51it/s]
 94%|█████████▎| 53970/57600 [9:29:52<39:53,  1.52it/s]
 94%|█████████▎| 53971/57600 [9:29:53<38:48,  1.56it/s]
 94%|█████████▎| 53972/57600 [9:29:53<38:55,  1.55it/s]
 94%|█████████▎| 53973/57600 [9:29:54<37:54,  1.59it/s]
 94%|█████████▎| 53974/57600 [9:29:55<37:04,  1.63it/s]
 94%|█████████▎| 53975/57600 [9:29:55<37:57,  1.59it/s]
 94%|█████████▎| 53976/57600 [9:29:56<41:44,  1.45it/s]
 94%|█████████▎| 53977/57600 [9:29:57<41:21,  1.46it/s]
 94%|█████████▎| 53978/57600 [9:29:57<40:22,  1.50it/s]
 94%|█████████▎| 53979/57600 [9:29:58<39:34,  1.53it/s]
 94%|█████████▎| 53980/57600 [9:29:59<40:30,  1.49it/s]
                                                       
{'loss': 1.1223, 'learning_rate': 1.5675958188153307e-07, 'epoch': 595.81}

 94%|█████████▎| 53980/57600 [9:29:59<40:30,  1.49it/s]
 94%|█████████▎| 53981/57600 [9:29:59<41:11,  1.46it/s]
 94%|█████████▎| 53982/57600 [9:30:00<39:26,  1.53it/s]
 94%|█████████▎| 53983/57600 [9:30:01<39:05,  1.54it/s]
 94%|█████████▎| 53984/57600 [9:30:01<38:08,  1.58it/s]
 94%|█████████▎| 53985/57600 [9:30:02<38:51,  1.55it/s]
 94%|█████████▎| 53986/57600 [9:30:03<37:40,  1.60it/s]
 94%|█████████▎| 53987/57600 [9:30:03<37:54,  1.59it/s]
 94%|█████████▎| 53988/57600 [9:30:04<37:16,  1.62it/s]
 94%|█████████▎| 53989/57600 [9:30:04<37:47,  1.59it/s]
 94%|█████████▎| 53990/57600 [9:30:05<37:24,  1.61it/s]
 94%|█████████▎| 53991/57600 [9:30:06<37:02,  1.62it/s]
 94%|█████████▎| 53992/57600 [9:30:06<38:20,  1.57it/s]
 94%|█████████▎| 53993/57600 [9:30:07<38:48,  1.55it/s]
 94%|█████████▎| 53994/57600 [9:30:08<39:57,  1.50it/s]
 94%|█████████▎| 53995/57600 [9:30:08<39:24,  1.52it/s]
 94%|█████████▎| 53996/57600 [9:30:09<39:11,  1.53it/s]
 94%|█████████▎| 53997/57600 [9:30:10<39:18,  1.53it/s]
 94%|█████████▎| 53998/57600 [9:30:10<41:31,  1.45it/s]
 94%|█████████▎| 53999/57600 [9:30:11<39:52,  1.51it/s]
 94%|█████████▍| 54000/57600 [9:30:12<38:42,  1.55it/s]
                                                       
{'loss': 1.0843, 'learning_rate': 1.564459930313589e-07, 'epoch': 596.03}

 94%|█████████▍| 54000/57600 [9:30:12<38:42,  1.55it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 10.80it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  6.93it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.41it/s]

100%|██████████| 6/6 [00:01<00:00,  3.05it/s]{'score': 49.98969378359193, 'counts': [147, 92, 66, 48], 'totals': [210, 180, 150, 121], 'precisions': [70.0, 51.111111111111114, 44.0, 39.66942148760331], 'bp': 1.0, 'sys_len': 210, 'ref_len': 207}

                                                       

                                             
{'eval_loss': 1.9765293598175049, 'eval_bleu': 49.9897, 'eval_gen_len': 8.4333, 'eval_runtime': 3.3896, 'eval_samples_per_second': 8.851, 'eval_steps_per_second': 1.77, 'epoch': 596.03}

 94%|█████████▍| 54000/57600 [9:30:15<38:42,  1.55it/s]

100%|██████████| 6/6 [00:03<00:00,  3.05it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 16:24:28,365 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}

 94%|█████████▍| 54001/57600 [9:30:34<7:00:52,  7.02s/it]
 94%|█████████▍| 54002/57600 [9:30:34<5:07:42,  5.13s/it]
 94%|█████████▍| 54003/57600 [9:30:35<3:48:27,  3.81s/it]
 94%|█████████▍| 54004/57600 [9:30:36<2:52:01,  2.87s/it]
 94%|█████████▍| 54005/57600 [9:30:36<2:14:32,  2.25s/it]
 94%|█████████▍| 54006/57600 [9:30:37<1:47:51,  1.80s/it]
 94%|█████████▍| 54007/57600 [9:30:38<1:28:59,  1.49s/it]
 94%|█████████▍| 54008/57600 [9:30:39<1:13:54,  1.23s/it]
 94%|█████████▍| 54009/57600 [9:30:39<1:04:24,  1.08s/it]
 94%|█████████▍| 54010/57600 [9:30:40<57:08,  1.05it/s]  
 94%|█████████▍| 54011/57600 [9:30:41<52:20,  1.14it/s]
 94%|█████████▍| 54012/57600 [9:30:41<48:39,  1.23it/s]
 94%|█████████▍| 54013/57600 [9:30:42<45:31,  1.31it/s]
 94%|█████████▍| 54014/57600 [9:30:43<45:00,  1.33it/s]
 94%|█████████▍| 54015/57600 [9:30:43<43:32,  1.37it/s]
 94%|█████████▍| 54016/57600 [9:30:44<41:59,  1.42it/s]
 94%|█████████▍| 54017/57600 [9:30:45<42:09,  1.42it/s]
 94%|█████████▍| 54018/57600 [9:30:45<41:43,  1.43it/s]
 94%|█████████▍| 54019/57600 [9:30:46<41:48,  1.43it/s]
 94%|█████████▍| 54020/57600 [9:30:47<41:57,  1.42it/s]
                                                       
{'loss': 1.0834, 'learning_rate': 1.5613240418118463e-07, 'epoch': 596.25}

 94%|█████████▍| 54020/57600 [9:30:47<41:57,  1.42it/s]
 94%|█████████▍| 54021/57600 [9:30:47<40:58,  1.46it/s]
 94%|█████████▍| 54022/57600 [9:30:48<40:42,  1.46it/s]
 94%|█████████▍| 54023/57600 [9:30:49<40:35,  1.47it/s]
 94%|█████████▍| 54024/57600 [9:30:50<40:41,  1.46it/s]
 94%|█████████▍| 54025/57600 [9:30:50<41:02,  1.45it/s]
 94%|█████████▍| 54026/57600 [9:30:51<40:33,  1.47it/s]
 94%|█████████▍| 54027/57600 [9:30:51<38:58,  1.53it/s]
 94%|█████████▍| 54028/57600 [9:30:52<38:25,  1.55it/s]
 94%|█████████▍| 54029/57600 [9:30:53<40:00,  1.49it/s]
 94%|█████████▍| 54030/57600 [9:30:54<40:02,  1.49it/s]
 94%|█████████▍| 54031/57600 [9:30:54<39:32,  1.50it/s]
 94%|█████████▍| 54032/57600 [9:30:55<39:13,  1.52it/s]
 94%|█████████▍| 54033/57600 [9:30:55<39:23,  1.51it/s]
 94%|█████████▍| 54034/57600 [9:30:56<39:06,  1.52it/s]
 94%|█████████▍| 54035/57600 [9:30:57<40:06,  1.48it/s]
 94%|█████████▍| 54036/57600 [9:30:57<39:42,  1.50it/s]
 94%|█████████▍| 54037/57600 [9:30:58<39:17,  1.51it/s]
 94%|█████████▍| 54038/57600 [9:30:59<38:50,  1.53it/s]
 94%|█████████▍| 54039/57600 [9:30:59<39:48,  1.49it/s]
 94%|█████████▍| 54040/57600 [9:31:00<39:34,  1.50it/s]
                                                       
{'loss': 1.1256, 'learning_rate': 1.5581881533101046e-07, 'epoch': 596.47}

 94%|█████████▍| 54040/57600 [9:31:00<39:34,  1.50it/s]
 94%|█████████▍| 54041/57600 [9:31:01<39:51,  1.49it/s]
 94%|█████████▍| 54042/57600 [9:31:01<39:48,  1.49it/s]
 94%|█████████▍| 54043/57600 [9:31:02<39:24,  1.50it/s]
 94%|█████████▍| 54044/57600 [9:31:03<39:47,  1.49it/s]
 94%|█████████▍| 54045/57600 [9:31:03<39:04,  1.52it/s]
 94%|█████████▍| 54046/57600 [9:31:04<38:35,  1.53it/s]
 94%|█████████▍| 54047/57600 [9:31:05<38:09,  1.55it/s]
 94%|█████████▍| 54048/57600 [9:31:05<38:41,  1.53it/s]
 94%|█████████▍| 54049/57600 [9:31:06<38:28,  1.54it/s]
 94%|█████████▍| 54050/57600 [9:31:07<37:56,  1.56it/s]
 94%|█████████▍| 54051/57600 [9:31:07<37:54,  1.56it/s]
 94%|█████████▍| 54052/57600 [9:31:08<38:25,  1.54it/s]
 94%|█████████▍| 54053/57600 [9:31:09<39:21,  1.50it/s]
 94%|█████████▍| 54054/57600 [9:31:09<38:25,  1.54it/s]
 94%|█████████▍| 54055/57600 [9:31:10<40:13,  1.47it/s]
 94%|█████████▍| 54056/57600 [9:31:11<39:35,  1.49it/s]
 94%|█████████▍| 54057/57600 [9:31:11<39:05,  1.51it/s]
 94%|█████████▍| 54058/57600 [9:31:12<41:32,  1.42it/s]
 94%|█████████▍| 54059/57600 [9:31:13<40:40,  1.45it/s]
 94%|█████████▍| 54060/57600 [9:31:14<41:20,  1.43it/s]
                                                       
{'loss': 1.0986, 'learning_rate': 1.555052264808362e-07, 'epoch': 596.69}

 94%|█████████▍| 54060/57600 [9:31:14<41:20,  1.43it/s]
 94%|█████████▍| 54061/57600 [9:31:14<40:48,  1.45it/s]
 94%|█████████▍| 54062/57600 [9:31:15<40:15,  1.46it/s]
 94%|█████████▍| 54063/57600 [9:31:16<41:36,  1.42it/s]
 94%|█████████▍| 54064/57600 [9:31:16<40:27,  1.46it/s]
 94%|█████████▍| 54065/57600 [9:31:17<38:56,  1.51it/s]
 94%|█████████▍| 54066/57600 [9:31:17<38:33,  1.53it/s]
 94%|█████████▍| 54067/57600 [9:31:18<38:18,  1.54it/s]
 94%|█████████▍| 54068/57600 [9:31:19<38:10,  1.54it/s]
 94%|█████████▍| 54069/57600 [9:31:20<39:50,  1.48it/s]
 94%|█████████▍| 54070/57600 [9:31:20<39:00,  1.51it/s]
 94%|█████████▍| 54071/57600 [9:31:21<40:03,  1.47it/s]
 94%|█████████▍| 54072/57600 [9:31:21<38:50,  1.51it/s]
 94%|█████████▍| 54073/57600 [9:31:22<37:29,  1.57it/s]
 94%|█████████▍| 54074/57600 [9:31:23<39:09,  1.50it/s]
 94%|█████████▍| 54075/57600 [9:31:23<39:23,  1.49it/s]
 94%|█████████▍| 54076/57600 [9:31:24<39:28,  1.49it/s]
 94%|█████████▍| 54077/57600 [9:31:25<38:44,  1.52it/s]
 94%|█████████▍| 54078/57600 [9:31:25<38:33,  1.52it/s]
 94%|█████████▍| 54079/57600 [9:31:26<38:11,  1.54it/s]
 94%|█████████▍| 54080/57600 [9:31:27<37:23,  1.57it/s]
                                                       
{'loss': 1.1141, 'learning_rate': 1.5519163763066202e-07, 'epoch': 596.91}

 94%|█████████▍| 54080/57600 [9:31:27<37:23,  1.57it/s]
 94%|█████████▍| 54081/57600 [9:31:27<37:06,  1.58it/s]
 94%|█████████▍| 54082/57600 [9:31:28<37:13,  1.58it/s]
 94%|█████████▍| 54083/57600 [9:31:29<37:58,  1.54it/s]
 94%|█████████▍| 54084/57600 [9:31:29<36:52,  1.59it/s]
 94%|█████████▍| 54085/57600 [9:31:30<38:02,  1.54it/s]
 94%|█████████▍| 54086/57600 [9:31:31<37:41,  1.55it/s]
 94%|█████████▍| 54087/57600 [9:31:31<37:58,  1.54it/s]
 94%|█████████▍| 54088/57600 [9:31:32<37:17,  1.57it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 94%|█████████▍| 54089/57600 [9:31:33<39:30,  1.48it/s]
 94%|█████████▍| 54090/57600 [9:31:33<39:28,  1.48it/s]
 94%|█████████▍| 54091/57600 [9:31:34<39:07,  1.49it/s]
 94%|█████████▍| 54092/57600 [9:31:35<39:03,  1.50it/s]
 94%|█████████▍| 54093/57600 [9:31:35<38:35,  1.51it/s]
 94%|█████████▍| 54094/57600 [9:31:36<38:35,  1.51it/s]
 94%|█████████▍| 54095/57600 [9:31:37<39:31,  1.48it/s]
 94%|█████████▍| 54096/57600 [9:31:37<39:09,  1.49it/s]
 94%|█████████▍| 54097/57600 [9:31:38<37:58,  1.54it/s]
 94%|█████████▍| 54098/57600 [9:31:39<40:02,  1.46it/s]
 94%|█████████▍| 54099/57600 [9:31:39<39:24,  1.48it/s]
 94%|█████████▍| 54100/57600 [9:31:40<39:28,  1.48it/s]
                                                       
{'loss': 1.1094, 'learning_rate': 1.5487804878048785e-07, 'epoch': 597.13}

 94%|█████████▍| 54100/57600 [9:31:40<39:28,  1.48it/s]
 94%|█████████▍| 54101/57600 [9:31:41<38:29,  1.52it/s]
 94%|█████████▍| 54102/57600 [9:31:41<39:15,  1.48it/s]
 94%|█████████▍| 54103/57600 [9:31:42<39:34,  1.47it/s]
 94%|█████████▍| 54104/57600 [9:31:43<39:44,  1.47it/s]
 94%|█████████▍| 54105/57600 [9:31:43<39:35,  1.47it/s]
 94%|█████████▍| 54106/57600 [9:31:44<40:20,  1.44it/s]
 94%|█████████▍| 54107/57600 [9:31:45<39:58,  1.46it/s]
 94%|█████████▍| 54108/57600 [9:31:45<39:48,  1.46it/s]
 94%|█████████▍| 54109/57600 [9:31:46<40:21,  1.44it/s]
 94%|█████████▍| 54110/57600 [9:31:47<39:06,  1.49it/s]
 94%|█████████▍| 54111/57600 [9:31:47<39:07,  1.49it/s]
 94%|█████████▍| 54112/57600 [9:31:48<39:02,  1.49it/s]
 94%|█████████▍| 54113/57600 [9:31:49<38:51,  1.50it/s]
 94%|█████████▍| 54114/57600 [9:31:49<39:23,  1.48it/s]
 94%|█████████▍| 54115/57600 [9:31:50<38:16,  1.52it/s]
 94%|█████████▍| 54116/57600 [9:31:51<38:30,  1.51it/s]
 94%|█████████▍| 54117/57600 [9:31:51<38:40,  1.50it/s]
 94%|█████████▍| 54118/57600 [9:31:52<37:48,  1.53it/s]
 94%|█████████▍| 54119/57600 [9:31:53<37:33,  1.54it/s]
 94%|█████████▍| 54120/57600 [9:31:53<37:44,  1.54it/s]
                                                       
{'loss': 1.0814, 'learning_rate': 1.5456445993031357e-07, 'epoch': 597.35}

 94%|█████████▍| 54120/57600 [9:31:53<37:44,  1.54it/s]
 94%|█████████▍| 54121/57600 [9:31:54<38:12,  1.52it/s]
 94%|█████████▍| 54122/57600 [9:31:55<37:33,  1.54it/s]
 94%|█████████▍| 54123/57600 [9:31:55<38:20,  1.51it/s]
 94%|█████████▍| 54124/57600 [9:31:56<38:45,  1.49it/s]
 94%|█████████▍| 54125/57600 [9:31:57<39:09,  1.48it/s]
 94%|█████████▍| 54126/57600 [9:31:57<38:02,  1.52it/s]
 94%|█████████▍| 54127/57600 [9:31:58<40:17,  1.44it/s]
 94%|█████████▍| 54128/57600 [9:31:59<40:28,  1.43it/s]
 94%|█████████▍| 54129/57600 [9:31:59<40:00,  1.45it/s]
 94%|█████████▍| 54130/57600 [9:32:00<39:44,  1.46it/s]
 94%|█████████▍| 54131/57600 [9:32:01<38:58,  1.48it/s]
 94%|█████████▍| 54132/57600 [9:32:01<37:58,  1.52it/s]
 94%|█████████▍| 54133/57600 [9:32:02<38:14,  1.51it/s]
 94%|█████████▍| 54134/57600 [9:32:03<37:58,  1.52it/s]
 94%|█████████▍| 54135/57600 [9:32:03<37:45,  1.53it/s]
 94%|█████████▍| 54136/57600 [9:32:04<37:12,  1.55it/s]
 94%|█████████▍| 54137/57600 [9:32:05<38:35,  1.50it/s]
 94%|█████████▍| 54138/57600 [9:32:05<37:45,  1.53it/s]
 94%|█████████▍| 54139/57600 [9:32:06<38:57,  1.48it/s]
 94%|█████████▍| 54140/57600 [9:32:07<39:57,  1.44it/s]
                                                       
{'loss': 1.105, 'learning_rate': 1.542508710801394e-07, 'epoch': 597.57}

 94%|█████████▍| 54140/57600 [9:32:07<39:57,  1.44it/s]
 94%|█████████▍| 54141/57600 [9:32:07<38:55,  1.48it/s]
 94%|█████████▍| 54142/57600 [9:32:08<37:39,  1.53it/s]
 94%|█████████▍| 54143/57600 [9:32:09<37:28,  1.54it/s]
 94%|█████████▍| 54144/57600 [9:32:09<38:11,  1.51it/s]
 94%|█████████▍| 54145/57600 [9:32:10<37:45,  1.53it/s]
 94%|█████████▍| 54146/57600 [9:32:11<37:14,  1.55it/s]
 94%|█████████▍| 54147/57600 [9:32:11<38:42,  1.49it/s]
 94%|█████████▍| 54148/57600 [9:32:12<38:06,  1.51it/s]
 94%|█████████▍| 54149/57600 [9:32:13<38:53,  1.48it/s]
 94%|█████████▍| 54150/57600 [9:32:13<37:56,  1.52it/s]
 94%|█████████▍| 54151/57600 [9:32:14<38:44,  1.48it/s]
 94%|█████████▍| 54152/57600 [9:32:15<38:33,  1.49it/s]
 94%|█████████▍| 54153/57600 [9:32:15<37:38,  1.53it/s]
 94%|█████████▍| 54154/57600 [9:32:16<38:19,  1.50it/s]
 94%|█████████▍| 54155/57600 [9:32:17<38:53,  1.48it/s]
 94%|█████████▍| 54156/57600 [9:32:17<38:52,  1.48it/s]
 94%|█████████▍| 54157/57600 [9:32:18<39:05,  1.47it/s]
 94%|█████████▍| 54158/57600 [9:32:19<39:51,  1.44it/s]
 94%|█████████▍| 54159/57600 [9:32:19<39:14,  1.46it/s]
 94%|█████████▍| 54160/57600 [9:32:20<38:20,  1.50it/s]
                                                       
{'loss': 1.1205, 'learning_rate': 1.5393728222996513e-07, 'epoch': 597.79}

 94%|█████████▍| 54160/57600 [9:32:20<38:20,  1.50it/s]
 94%|█████████▍| 54161/57600 [9:32:21<37:41,  1.52it/s]
 94%|█████████▍| 54162/57600 [9:32:21<38:05,  1.50it/s]
 94%|█████████▍| 54163/57600 [9:32:22<38:14,  1.50it/s]
 94%|█████████▍| 54164/57600 [9:32:23<39:21,  1.45it/s]
 94%|█████████▍| 54165/57600 [9:32:23<39:07,  1.46it/s]
 94%|█████████▍| 54166/57600 [9:32:24<40:06,  1.43it/s]
 94%|█████████▍| 54167/57600 [9:32:25<39:50,  1.44it/s]
 94%|█████████▍| 54168/57600 [9:32:26<40:04,  1.43it/s]
 94%|█████████▍| 54169/57600 [9:32:26<41:41,  1.37it/s]
 94%|█████████▍| 54170/57600 [9:32:27<40:22,  1.42it/s]
 94%|█████████▍| 54171/57600 [9:32:28<39:31,  1.45it/s]
 94%|█████████▍| 54172/57600 [9:32:28<39:18,  1.45it/s]
 94%|█████████▍| 54173/57600 [9:32:29<39:02,  1.46it/s]
 94%|█████████▍| 54174/57600 [9:32:30<37:59,  1.50it/s]
 94%|█████████▍| 54175/57600 [9:32:30<37:34,  1.52it/s]
 94%|█████████▍| 54176/57600 [9:32:31<38:52,  1.47it/s]
 94%|█████████▍| 54177/57600 [9:32:32<38:29,  1.48it/s]
 94%|█████████▍| 54178/57600 [9:32:32<37:48,  1.51it/s]
 94%|█████████▍| 54179/57600 [9:32:33<40:00,  1.42it/s]
 94%|█████████▍| 54180/57600 [9:32:34<39:39,  1.44it/s]
                                                       
{'loss': 1.0908, 'learning_rate': 1.5362369337979096e-07, 'epoch': 598.01}

 94%|█████████▍| 54180/57600 [9:32:34<39:39,  1.44it/s]
 94%|█████████▍| 54181/57600 [9:32:34<38:24,  1.48it/s]
 94%|█████████▍| 54182/57600 [9:32:35<37:16,  1.53it/s]
 94%|█████████▍| 54183/57600 [9:32:36<39:20,  1.45it/s]
 94%|█████████▍| 54184/57600 [9:32:37<40:06,  1.42it/s]
 94%|█████████▍| 54185/57600 [9:32:37<39:52,  1.43it/s]
 94%|█████████▍| 54186/57600 [9:32:38<39:51,  1.43it/s]
 94%|█████████▍| 54187/57600 [9:32:39<38:55,  1.46it/s]
 94%|█████████▍| 54188/57600 [9:32:39<37:57,  1.50it/s]
 94%|█████████▍| 54189/57600 [9:32:40<38:32,  1.48it/s]
 94%|█████████▍| 54190/57600 [9:32:41<37:51,  1.50it/s]
 94%|█████████▍| 54191/57600 [9:32:41<37:08,  1.53it/s]
 94%|█████████▍| 54192/57600 [9:32:42<37:21,  1.52it/s]
 94%|█████████▍| 54193/57600 [9:32:43<36:23,  1.56it/s]
 94%|█████████▍| 54194/57600 [9:32:43<35:31,  1.60it/s]
 94%|█████████▍| 54195/57600 [9:32:44<35:19,  1.61it/s]
 94%|█████████▍| 54196/57600 [9:32:44<35:42,  1.59it/s]
 94%|█████████▍| 54197/57600 [9:32:45<35:12,  1.61it/s]
 94%|█████████▍| 54198/57600 [9:32:46<36:30,  1.55it/s]
 94%|█████████▍| 54199/57600 [9:32:46<36:24,  1.56it/s]
 94%|█████████▍| 54200/57600 [9:32:47<36:16,  1.56it/s]
                                                       
{'loss': 1.0925, 'learning_rate': 1.533101045296167e-07, 'epoch': 598.23}

 94%|█████████▍| 54200/57600 [9:32:47<36:16,  1.56it/s]
 94%|█████████▍| 54201/57600 [9:32:48<35:27,  1.60it/s]
 94%|█████████▍| 54202/57600 [9:32:48<35:12,  1.61it/s]
 94%|█████████▍| 54203/57600 [9:32:49<34:53,  1.62it/s]
 94%|█████████▍| 54204/57600 [9:32:49<35:16,  1.60it/s]
 94%|█████████▍| 54205/57600 [9:32:50<35:07,  1.61it/s]
 94%|█████████▍| 54206/57600 [9:32:51<35:10,  1.61it/s]
 94%|█████████▍| 54207/57600 [9:32:51<34:48,  1.62it/s]
 94%|█████████▍| 54208/57600 [9:32:52<34:41,  1.63it/s]
 94%|█████████▍| 54209/57600 [9:32:52<34:44,  1.63it/s]
 94%|█████████▍| 54210/57600 [9:32:53<34:57,  1.62it/s]
 94%|█████████▍| 54211/57600 [9:32:54<34:33,  1.63it/s]
 94%|█████████▍| 54212/57600 [9:32:54<35:05,  1.61it/s]
 94%|█████████▍| 54213/57600 [9:32:55<36:27,  1.55it/s]
 94%|█████████▍| 54214/57600 [9:32:56<35:59,  1.57it/s]
 94%|█████████▍| 54215/57600 [9:32:56<36:22,  1.55it/s]
 94%|█████████▍| 54216/57600 [9:32:57<35:56,  1.57it/s]
 94%|█████████▍| 54217/57600 [9:32:58<36:09,  1.56it/s]
 94%|█████████▍| 54218/57600 [9:32:58<34:38,  1.63it/s]
 94%|█████████▍| 54219/57600 [9:32:59<35:42,  1.58it/s]
 94%|█████████▍| 54220/57600 [9:32:59<35:02,  1.61it/s]
                                                       
{'loss': 1.1171, 'learning_rate': 1.5299651567944252e-07, 'epoch': 598.45}

 94%|█████████▍| 54220/57600 [9:32:59<35:02,  1.61it/s]
 94%|█████████▍| 54221/57600 [9:33:00<34:40,  1.62it/s]
 94%|█████████▍| 54222/57600 [9:33:01<34:12,  1.65it/s]
 94%|█████████▍| 54223/57600 [9:33:01<34:47,  1.62it/s]
 94%|█████████▍| 54224/57600 [9:33:02<35:13,  1.60it/s]
 94%|█████████▍| 54225/57600 [9:33:03<35:37,  1.58it/s]
 94%|█████████▍| 54226/57600 [9:33:03<35:26,  1.59it/s]
 94%|█████████▍| 54227/57600 [9:33:04<34:56,  1.61it/s]
 94%|█████████▍| 54228/57600 [9:33:04<34:45,  1.62it/s]
 94%|█████████▍| 54229/57600 [9:33:05<35:33,  1.58it/s]
 94%|█████████▍| 54230/57600 [9:33:06<34:25,  1.63it/s]
 94%|█████████▍| 54231/57600 [9:33:06<34:39,  1.62it/s]
 94%|█████████▍| 54232/57600 [9:33:07<35:04,  1.60it/s]
 94%|█████████▍| 54233/57600 [9:33:08<36:31,  1.54it/s]
 94%|█████████▍| 54234/57600 [9:33:08<36:11,  1.55it/s]
 94%|█████████▍| 54235/57600 [9:33:09<37:13,  1.51it/s]
 94%|█████████▍| 54236/57600 [9:33:10<37:08,  1.51it/s]
 94%|█████████▍| 54237/57600 [9:33:10<35:33,  1.58it/s]
 94%|█████████▍| 54238/57600 [9:33:11<35:07,  1.60it/s]
 94%|█████████▍| 54239/57600 [9:33:11<34:38,  1.62it/s]
 94%|█████████▍| 54240/57600 [9:33:12<35:17,  1.59it/s]
                                                       
{'loss': 1.1022, 'learning_rate': 1.5268292682926835e-07, 'epoch': 598.68}

 94%|█████████▍| 54240/57600 [9:33:12<35:17,  1.59it/s]
 94%|█████████▍| 54241/57600 [9:33:13<35:02,  1.60it/s]
 94%|█████████▍| 54242/57600 [9:33:13<34:51,  1.61it/s]
 94%|█████████▍| 54243/57600 [9:33:14<33:48,  1.66it/s]
 94%|█████████▍| 54244/57600 [9:33:14<34:28,  1.62it/s]
 94%|█████████▍| 54245/57600 [9:33:15<34:39,  1.61it/s]
 94%|█████████▍| 54246/57600 [9:33:16<34:52,  1.60it/s]
 94%|█████████▍| 54247/57600 [9:33:16<36:31,  1.53it/s]
 94%|█████████▍| 54248/57600 [9:33:17<35:59,  1.55it/s]
 94%|█████████▍| 54249/57600 [9:33:18<36:06,  1.55it/s]
 94%|█████████▍| 54250/57600 [9:33:18<35:17,  1.58it/s]
 94%|█████████▍| 54251/57600 [9:33:19<34:45,  1.61it/s]
 94%|█████████▍| 54252/57600 [9:33:20<34:47,  1.60it/s]
 94%|█████████▍| 54253/57600 [9:33:20<34:46,  1.60it/s]
 94%|█████████▍| 54254/57600 [9:33:21<34:44,  1.61it/s]
 94%|█████████▍| 54255/57600 [9:33:21<35:43,  1.56it/s]
 94%|█████████▍| 54256/57600 [9:33:22<35:09,  1.59it/s]
 94%|█████████▍| 54257/57600 [9:33:23<35:13,  1.58it/s]
 94%|█████████▍| 54258/57600 [9:33:23<34:45,  1.60it/s]
 94%|█████████▍| 54259/57600 [9:33:24<34:52,  1.60it/s]
 94%|█████████▍| 54260/57600 [9:33:25<34:54,  1.59it/s]
                                                       
{'loss': 1.1215, 'learning_rate': 1.5236933797909405e-07, 'epoch': 598.9}

 94%|█████████▍| 54260/57600 [9:33:25<34:54,  1.59it/s]
 94%|█████████▍| 54261/57600 [9:33:25<34:03,  1.63it/s]
 94%|█████████▍| 54262/57600 [9:33:26<34:26,  1.62it/s]
 94%|█████████▍| 54263/57600 [9:33:26<34:16,  1.62it/s]
 94%|█████████▍| 54264/57600 [9:33:27<35:03,  1.59it/s]
 94%|█████████▍| 54265/57600 [9:33:28<34:37,  1.61it/s]
 94%|█████████▍| 54266/57600 [9:33:28<35:36,  1.56it/s]
 94%|█████████▍| 54267/57600 [9:33:29<35:12,  1.58it/s]
 94%|█████████▍| 54268/57600 [9:33:30<34:30,  1.61it/s]
 94%|█████████▍| 54269/57600 [9:33:30<34:31,  1.61it/s]
 94%|█████████▍| 54270/57600 [9:33:31<36:33,  1.52it/s]
 94%|█████████▍| 54271/57600 [9:33:32<36:25,  1.52it/s]
 94%|█████████▍| 54272/57600 [9:33:32<35:34,  1.56it/s]
 94%|█████████▍| 54273/57600 [9:33:33<36:59,  1.50it/s]
 94%|█████████▍| 54274/57600 [9:33:34<36:11,  1.53it/s]
 94%|█████████▍| 54275/57600 [9:33:34<36:15,  1.53it/s]
 94%|█████████▍| 54276/57600 [9:33:35<37:01,  1.50it/s]
 94%|█████████▍| 54277/57600 [9:33:35<35:30,  1.56it/s]
 94%|█████████▍| 54278/57600 [9:33:36<34:55,  1.59it/s]
 94%|█████████▍| 54279/57600 [9:33:37<35:01,  1.58it/s]
 94%|█████████▍| 54280/57600 [9:33:37<35:29,  1.56it/s]
                                                       
{'loss': 1.0968, 'learning_rate': 1.5205574912891988e-07, 'epoch': 599.12}

 94%|█████████▍| 54280/57600 [9:33:37<35:29,  1.56it/s]
 94%|█████████▍| 54281/57600 [9:33:38<35:03,  1.58it/s]
 94%|█████████▍| 54282/57600 [9:33:39<34:32,  1.60it/s]
 94%|█████████▍| 54283/57600 [9:33:39<34:01,  1.62it/s]
 94%|█████████▍| 54284/57600 [9:33:40<34:47,  1.59it/s]
 94%|█████████▍| 54285/57600 [9:33:41<36:40,  1.51it/s]
 94%|█████████▍| 54286/57600 [9:33:41<35:57,  1.54it/s]
 94%|█████████▍| 54287/57600 [9:33:42<34:03,  1.62it/s]
 94%|█████████▍| 54288/57600 [9:33:42<34:21,  1.61it/s]
 94%|█████████▍| 54289/57600 [9:33:43<34:42,  1.59it/s]
 94%|█████████▍| 54290/57600 [9:33:44<34:51,  1.58it/s]
 94%|█████████▍| 54291/57600 [9:33:44<34:13,  1.61it/s]
 94%|█████████▍| 54292/57600 [9:33:45<33:02,  1.67it/s]
 94%|█████████▍| 54293/57600 [9:33:45<33:52,  1.63it/s]
 94%|█████████▍| 54294/57600 [9:33:46<33:26,  1.65it/s]
 94%|█████████▍| 54295/57600 [9:33:47<34:28,  1.60it/s]
 94%|█████████▍| 54296/57600 [9:33:47<33:39,  1.64it/s]
 94%|█████████▍| 54297/57600 [9:33:48<33:04,  1.66it/s]
 94%|█████████▍| 54298/57600 [9:33:48<32:13,  1.71it/s]
 94%|█████████▍| 54299/57600 [9:33:49<33:21,  1.65it/s]
 94%|█████████▍| 54300/57600 [9:33:50<34:20,  1.60it/s]
                                                       
{'loss': 1.1202, 'learning_rate': 1.517421602787456e-07, 'epoch': 599.34}

 94%|█████████▍| 54300/57600 [9:33:50<34:20,  1.60it/s]
 94%|█████████▍| 54301/57600 [9:33:50<33:24,  1.65it/s]
 94%|█████████▍| 54302/57600 [9:33:51<33:48,  1.63it/s]
 94%|█████████▍| 54303/57600 [9:33:52<34:07,  1.61it/s]
 94%|█████████▍| 54304/57600 [9:33:52<33:29,  1.64it/s]
 94%|█████████▍| 54305/57600 [9:33:53<33:15,  1.65it/s]
 94%|█████████▍| 54306/57600 [9:33:53<32:45,  1.68it/s]
 94%|█████████▍| 54307/57600 [9:33:54<31:56,  1.72it/s]
 94%|█████████▍| 54308/57600 [9:33:55<33:14,  1.65it/s]
 94%|█████████▍| 54309/57600 [9:33:55<32:51,  1.67it/s]
 94%|█████████▍| 54310/57600 [9:33:56<33:42,  1.63it/s]
 94%|█████████▍| 54311/57600 [9:33:56<33:30,  1.64it/s]
 94%|█████████▍| 54312/57600 [9:33:57<33:36,  1.63it/s]
 94%|█████████▍| 54313/57600 [9:33:58<33:26,  1.64it/s]
 94%|█████████▍| 54314/57600 [9:33:58<32:36,  1.68it/s]
 94%|█████████▍| 54315/57600 [9:33:59<32:35,  1.68it/s]
 94%|█████████▍| 54316/57600 [9:33:59<33:11,  1.65it/s]
 94%|█████████▍| 54317/57600 [9:34:00<32:30,  1.68it/s]
 94%|█████████▍| 54318/57600 [9:34:01<32:36,  1.68it/s]
 94%|█████████▍| 54319/57600 [9:34:01<34:11,  1.60it/s]
 94%|█████████▍| 54320/57600 [9:34:02<34:11,  1.60it/s]
                                                       
{'loss': 1.1196, 'learning_rate': 1.5142857142857144e-07, 'epoch': 599.56}

 94%|█████████▍| 54320/57600 [9:34:02<34:11,  1.60it/s]
 94%|█████████▍| 54321/57600 [9:34:03<35:04,  1.56it/s]
 94%|█████████▍| 54322/57600 [9:34:03<34:20,  1.59it/s]
 94%|█████████▍| 54323/57600 [9:34:04<35:26,  1.54it/s]
 94%|█████████▍| 54324/57600 [9:34:04<35:24,  1.54it/s]
 94%|█████████▍| 54325/57600 [9:34:05<35:22,  1.54it/s]
 94%|█████████▍| 54326/57600 [9:34:06<35:45,  1.53it/s]
 94%|█████████▍| 54327/57600 [9:34:06<34:16,  1.59it/s]
 94%|█████████▍| 54328/57600 [9:34:07<34:02,  1.60it/s]
 94%|█████████▍| 54329/57600 [9:34:08<33:45,  1.61it/s]
 94%|█████████▍| 54330/57600 [9:34:08<34:58,  1.56it/s]
 94%|█████████▍| 54331/57600 [9:34:09<34:33,  1.58it/s]
 94%|█████████▍| 54332/57600 [9:34:10<34:55,  1.56it/s]
 94%|█████████▍| 54333/57600 [9:34:10<34:47,  1.57it/s]
 94%|█████████▍| 54334/57600 [9:34:11<35:37,  1.53it/s]
 94%|█████████▍| 54335/57600 [9:34:12<35:46,  1.52it/s]
 94%|█████████▍| 54336/57600 [9:34:12<35:13,  1.54it/s]
 94%|█████████▍| 54337/57600 [9:34:13<34:17,  1.59it/s]
 94%|█████████▍| 54338/57600 [9:34:13<33:35,  1.62it/s]
 94%|█████████▍| 54339/57600 [9:34:14<34:23,  1.58it/s]
 94%|█████████▍| 54340/57600 [9:34:15<35:26,  1.53it/s]
                                                       
{'loss': 1.0487, 'learning_rate': 1.5111498257839716e-07, 'epoch': 599.78}

 94%|█████████▍| 54340/57600 [9:34:15<35:26,  1.53it/s]
 94%|█████████▍| 54341/57600 [9:34:15<34:53,  1.56it/s]
 94%|█████████▍| 54342/57600 [9:34:16<34:10,  1.59it/s]
 94%|█████████▍| 54343/57600 [9:34:16<32:58,  1.65it/s]
 94%|█████████▍| 54344/57600 [9:34:17<32:08,  1.69it/s]
 94%|█████████▍| 54345/57600 [9:34:18<33:54,  1.60it/s]
 94%|█████████▍| 54346/57600 [9:34:18<33:46,  1.61it/s]
 94%|█████████▍| 54347/57600 [9:34:19<35:06,  1.54it/s]
 94%|█████████▍| 54348/57600 [9:34:20<34:25,  1.57it/s]
 94%|█████████▍| 54349/57600 [9:34:20<33:43,  1.61it/s]
 94%|█████████▍| 54350/57600 [9:34:21<33:03,  1.64it/s]
 94%|█████████▍| 54351/57600 [9:34:22<34:10,  1.58it/s]
 94%|█████████▍| 54352/57600 [9:34:22<34:06,  1.59it/s]
 94%|█████████▍| 54353/57600 [9:34:23<34:14,  1.58it/s]
 94%|█████████▍| 54354/57600 [9:34:23<33:56,  1.59it/s]
 94%|█████████▍| 54355/57600 [9:34:24<32:46,  1.65it/s]
 94%|█████████▍| 54356/57600 [9:34:25<31:50,  1.70it/s]
 94%|█████████▍| 54357/57600 [9:34:25<33:07,  1.63it/s]
 94%|█████████▍| 54358/57600 [9:34:26<33:04,  1.63it/s]
 94%|█████████▍| 54359/57600 [9:34:26<32:42,  1.65it/s]
 94%|█████████▍| 54360/57600 [9:34:27<32:56,  1.64it/s]
                                                       
{'loss': 1.115, 'learning_rate': 1.5080139372822302e-07, 'epoch': 600.0}

 94%|█████████▍| 54360/57600 [9:34:27<32:56,  1.64it/s]
 94%|█████████▍| 54361/57600 [9:34:28<34:20,  1.57it/s]
 94%|█████████▍| 54362/57600 [9:34:28<33:13,  1.62it/s]
 94%|█████████▍| 54363/57600 [9:34:29<33:13,  1.62it/s]
 94%|█████████▍| 54364/57600 [9:34:29<32:49,  1.64it/s]
 94%|█████████▍| 54365/57600 [9:34:30<32:45,  1.65it/s]
 94%|█████████▍| 54366/57600 [9:34:31<32:33,  1.66it/s]
 94%|█████████▍| 54367/57600 [9:34:31<33:19,  1.62it/s]
 94%|█████████▍| 54368/57600 [9:34:32<34:17,  1.57it/s]
 94%|█████████▍| 54369/57600 [9:34:33<34:01,  1.58it/s]
 94%|█████████▍| 54370/57600 [9:34:33<33:17,  1.62it/s]
 94%|█████████▍| 54371/57600 [9:34:34<33:51,  1.59it/s]
 94%|█████████▍| 54372/57600 [9:34:35<34:18,  1.57it/s]
 94%|█████████▍| 54373/57600 [9:34:35<34:05,  1.58it/s]
 94%|█████████▍| 54374/57600 [9:34:36<33:30,  1.60it/s]
 94%|█████████▍| 54375/57600 [9:34:36<33:53,  1.59it/s]
 94%|█████████▍| 54376/57600 [9:34:37<34:30,  1.56it/s]
 94%|█████████▍| 54377/57600 [9:34:38<33:16,  1.61it/s]
 94%|█████████▍| 54378/57600 [9:34:38<33:05,  1.62it/s]
 94%|█████████▍| 54379/57600 [9:34:39<33:09,  1.62it/s]
 94%|█████████▍| 54380/57600 [9:34:39<33:05,  1.62it/s]
                                                       
{'loss': 1.112, 'learning_rate': 1.5048780487804883e-07, 'epoch': 600.22}

 94%|█████████▍| 54380/57600 [9:34:39<33:05,  1.62it/s]
 94%|█████████▍| 54381/57600 [9:34:40<32:54,  1.63it/s]
 94%|█████████▍| 54382/57600 [9:34:41<34:15,  1.57it/s]
 94%|█████████▍| 54383/57600 [9:34:41<33:10,  1.62it/s]
 94%|█████████▍| 54384/57600 [9:34:42<33:13,  1.61it/s]
 94%|█████████▍| 54385/57600 [9:34:43<32:54,  1.63it/s]
 94%|█████████▍| 54386/57600 [9:34:43<33:03,  1.62it/s]
 94%|█████████▍| 54387/57600 [9:34:44<33:43,  1.59it/s]
 94%|█████████▍| 54388/57600 [9:34:44<33:28,  1.60it/s]
 94%|█████████▍| 54389/57600 [9:34:45<33:27,  1.60it/s]
 94%|█████████▍| 54390/57600 [9:34:46<34:08,  1.57it/s]
 94%|█████████▍| 54391/57600 [9:34:46<33:43,  1.59it/s]
 94%|█████████▍| 54392/57600 [9:34:47<32:56,  1.62it/s]
 94%|█████████▍| 54393/57600 [9:34:48<32:16,  1.66it/s]
 94%|█████████▍| 54394/57600 [9:34:48<31:52,  1.68it/s]
 94%|█████████▍| 54395/57600 [9:34:49<31:31,  1.69it/s]
 94%|█████████▍| 54396/57600 [9:34:49<32:26,  1.65it/s]
 94%|█████████▍| 54397/57600 [9:34:50<32:59,  1.62it/s]
 94%|█████████▍| 54398/57600 [9:34:51<32:49,  1.63it/s]
 94%|█████████▍| 54399/57600 [9:34:51<32:59,  1.62it/s]
 94%|█████████▍| 54400/57600 [9:34:52<34:22,  1.55it/s]
                                                       
{'loss': 1.107, 'learning_rate': 1.5017421602787455e-07, 'epoch': 600.44}

 94%|█████████▍| 54400/57600 [9:34:52<34:22,  1.55it/s]
 94%|█████████▍| 54401/57600 [9:34:53<34:10,  1.56it/s]
 94%|█████████▍| 54402/57600 [9:34:53<33:30,  1.59it/s]
 94%|█████████▍| 54403/57600 [9:34:54<32:08,  1.66it/s]
 94%|█████████▍| 54404/57600 [9:34:54<32:52,  1.62it/s]
 94%|█████████▍| 54405/57600 [9:34:55<32:10,  1.65it/s]
 94%|█████████▍| 54406/57600 [9:34:56<31:48,  1.67it/s]
 94%|█████████▍| 54407/57600 [9:34:56<33:23,  1.59it/s]
 94%|█████████▍| 54408/57600 [9:34:57<33:11,  1.60it/s]
 94%|█████████▍| 54409/57600 [9:34:57<32:51,  1.62it/s]
 94%|█████████▍| 54410/57600 [9:34:58<35:04,  1.52it/s]
 94%|█████████▍| 54411/57600 [9:34:59<34:50,  1.53it/s]
 94%|█████████▍| 54412/57600 [9:35:00<36:11,  1.47it/s]
 94%|█████████▍| 54413/57600 [9:35:00<35:32,  1.49it/s]
 94%|█████████▍| 54414/57600 [9:35:01<35:17,  1.50it/s]
 94%|█████████▍| 54415/57600 [9:35:02<34:46,  1.53it/s]
 94%|█████████▍| 54416/57600 [9:35:02<34:35,  1.53it/s]
 94%|█████████▍| 54417/57600 [9:35:03<34:14,  1.55it/s]
 94%|█████████▍| 54418/57600 [9:35:03<33:44,  1.57it/s]
 94%|█████████▍| 54419/57600 [9:35:04<32:48,  1.62it/s]
 94%|█████████▍| 54420/57600 [9:35:05<31:51,  1.66it/s]
                                                       
{'loss': 1.0768, 'learning_rate': 1.4986062717770036e-07, 'epoch': 600.66}

 94%|█████████▍| 54420/57600 [9:35:05<31:51,  1.66it/s]
 94%|█████████▍| 54421/57600 [9:35:05<31:18,  1.69it/s]
 94%|█████████▍| 54422/57600 [9:35:06<32:23,  1.64it/s]
 94%|█████████▍| 54423/57600 [9:35:06<32:02,  1.65it/s]
 94%|█████████▍| 54424/57600 [9:35:07<32:00,  1.65it/s]
 94%|█████████▍| 54425/57600 [9:35:08<32:07,  1.65it/s]
 94%|█████████▍| 54426/57600 [9:35:08<35:14,  1.50it/s]
 94%|█████████▍| 54427/57600 [9:35:09<34:50,  1.52it/s]
 94%|█████████▍| 54428/57600 [9:35:10<33:34,  1.57it/s]
 94%|█████████▍| 54429/57600 [9:35:10<33:50,  1.56it/s]
 94%|█████████▍| 54430/57600 [9:35:11<33:15,  1.59it/s]
 94%|█████████▍| 54431/57600 [9:35:11<33:04,  1.60it/s]
 94%|█████████▍| 54432/57600 [9:35:12<32:32,  1.62it/s]
 95%|█████████▍| 54433/57600 [9:35:13<32:12,  1.64it/s]
 95%|█████████▍| 54434/57600 [9:35:13<31:34,  1.67it/s]
 95%|█████████▍| 54435/57600 [9:35:14<31:27,  1.68it/s]
 95%|█████████▍| 54436/57600 [9:35:14<32:09,  1.64it/s]
 95%|█████████▍| 54437/57600 [9:35:15<32:23,  1.63it/s]
 95%|█████████▍| 54438/57600 [9:35:16<32:20,  1.63it/s]
 95%|█████████▍| 54439/57600 [9:35:16<33:06,  1.59it/s]
 95%|█████████▍| 54440/57600 [9:35:17<32:53,  1.60it/s]
                                                       
{'loss': 1.1118, 'learning_rate': 1.495470383275261e-07, 'epoch': 600.88}

 95%|█████████▍| 54440/57600 [9:35:17<32:53,  1.60it/s]
 95%|█████████▍| 54441/57600 [9:35:18<33:39,  1.56it/s]
 95%|█████████▍| 54442/57600 [9:35:18<33:30,  1.57it/s]
 95%|█████████▍| 54443/57600 [9:35:19<32:43,  1.61it/s]
 95%|█████████▍| 54444/57600 [9:35:20<33:05,  1.59it/s]
 95%|█████████▍| 54445/57600 [9:35:20<34:13,  1.54it/s]
 95%|█████████▍| 54446/57600 [9:35:21<34:43,  1.51it/s]
 95%|█████████▍| 54447/57600 [9:35:22<34:00,  1.55it/s]
 95%|█████████▍| 54448/57600 [9:35:22<33:39,  1.56it/s]
 95%|█████████▍| 54449/57600 [9:35:23<32:47,  1.60it/s]
 95%|█████████▍| 54450/57600 [9:35:23<33:35,  1.56it/s]
 95%|█████████▍| 54451/57600 [9:35:24<34:38,  1.51it/s]
 95%|█████████▍| 54452/57600 [9:35:25<34:35,  1.52it/s]
 95%|█████████▍| 54453/57600 [9:35:25<33:43,  1.55it/s]
 95%|█████████▍| 54454/57600 [9:35:26<32:56,  1.59it/s]
 95%|█████████▍| 54455/57600 [9:35:27<32:09,  1.63it/s]
 95%|█████████▍| 54456/57600 [9:35:27<31:47,  1.65it/s]
 95%|█████████▍| 54457/57600 [9:35:28<31:33,  1.66it/s]
 95%|█████████▍| 54458/57600 [9:35:28<32:30,  1.61it/s]
 95%|█████████▍| 54459/57600 [9:35:29<32:28,  1.61it/s]
 95%|█████████▍| 54460/57600 [9:35:30<32:19,  1.62it/s]
                                                       
{'loss': 1.079, 'learning_rate': 1.4923344947735191e-07, 'epoch': 601.1}

 95%|█████████▍| 54460/57600 [9:35:30<32:19,  1.62it/s]
 95%|█████████▍| 54461/57600 [9:35:30<32:40,  1.60it/s]
 95%|█████████▍| 54462/57600 [9:35:31<33:34,  1.56it/s]
 95%|█████████▍| 54463/57600 [9:35:32<33:08,  1.58it/s]
 95%|█████████▍| 54464/57600 [9:35:32<32:34,  1.60it/s]
 95%|█████████▍| 54465/57600 [9:35:33<32:11,  1.62it/s]
 95%|█████████▍| 54466/57600 [9:35:33<32:01,  1.63it/s]
 95%|█████████▍| 54467/57600 [9:35:34<32:22,  1.61it/s]
 95%|█████████▍| 54468/57600 [9:35:35<31:47,  1.64it/s]
 95%|█████████▍| 54469/57600 [9:35:35<32:46,  1.59it/s]
 95%|█████████▍| 54470/57600 [9:35:36<33:21,  1.56it/s]
 95%|█████████▍| 54471/57600 [9:35:37<33:29,  1.56it/s]
 95%|█████████▍| 54472/57600 [9:35:37<32:59,  1.58it/s]
 95%|█████████▍| 54473/57600 [9:35:38<33:29,  1.56it/s]
 95%|█████████▍| 54474/57600 [9:35:39<34:19,  1.52it/s]
 95%|█████████▍| 54475/57600 [9:35:39<34:26,  1.51it/s]
 95%|█████████▍| 54476/57600 [9:35:40<33:32,  1.55it/s]
 95%|█████████▍| 54477/57600 [9:35:40<31:56,  1.63it/s]
 95%|█████████▍| 54478/57600 [9:35:41<33:13,  1.57it/s]
 95%|█████████▍| 54479/57600 [9:35:42<32:21,  1.61it/s]
 95%|█████████▍| 54480/57600 [9:35:42<32:27,  1.60it/s]
                                                       
{'loss': 1.0904, 'learning_rate': 1.489198606271777e-07, 'epoch': 601.32}

 95%|█████████▍| 54480/57600 [9:35:42<32:27,  1.60it/s]
 95%|█████████▍| 54481/57600 [9:35:43<31:58,  1.63it/s]
 95%|█████████▍| 54482/57600 [9:35:43<31:05,  1.67it/s]
 95%|█████████▍| 54483/57600 [9:35:44<32:08,  1.62it/s]
 95%|█████████▍| 54484/57600 [9:35:45<33:02,  1.57it/s]
 95%|█████████▍| 54485/57600 [9:35:45<33:51,  1.53it/s]
 95%|█████████▍| 54486/57600 [9:35:46<34:13,  1.52it/s]
 95%|█████████▍| 54487/57600 [9:35:47<33:25,  1.55it/s]
 95%|█████████▍| 54488/57600 [9:35:47<32:28,  1.60it/s]
 95%|█████████▍| 54489/57600 [9:35:48<31:47,  1.63it/s]
 95%|█████████▍| 54490/57600 [9:35:48<31:12,  1.66it/s]
 95%|█████████▍| 54491/57600 [9:35:49<31:11,  1.66it/s]
 95%|█████████▍| 54492/57600 [9:35:50<31:20,  1.65it/s]
 95%|█████████▍| 54493/57600 [9:35:50<31:28,  1.65it/s]
 95%|█████████▍| 54494/57600 [9:35:51<31:12,  1.66it/s]
 95%|█████████▍| 54495/57600 [9:35:52<32:03,  1.61it/s]
 95%|█████████▍| 54496/57600 [9:35:52<30:54,  1.67it/s]
 95%|█████████▍| 54497/57600 [9:35:53<30:33,  1.69it/s]
 95%|█████████▍| 54498/57600 [9:35:53<30:32,  1.69it/s]
 95%|█████████▍| 54499/57600 [9:35:54<31:29,  1.64it/s]
 95%|█████████▍| 54500/57600 [9:35:55<31:05,  1.66it/s]
                                                       
{'loss': 1.108, 'learning_rate': 1.4860627177700347e-07, 'epoch': 601.55}

 95%|█████████▍| 54500/57600 [9:35:55<31:05,  1.66it/s]
 95%|█████████▍| 54501/57600 [9:35:55<31:14,  1.65it/s]
 95%|█████████▍| 54502/57600 [9:35:56<32:04,  1.61it/s]
 95%|█████████▍| 54503/57600 [9:35:57<34:36,  1.49it/s]
 95%|█████████▍| 54504/57600 [9:35:57<33:30,  1.54it/s]
 95%|█████████▍| 54505/57600 [9:35:58<33:32,  1.54it/s]
 95%|█████████▍| 54506/57600 [9:35:58<33:37,  1.53it/s]
 95%|█████████▍| 54507/57600 [9:35:59<34:06,  1.51it/s]
 95%|█████████▍| 54508/57600 [9:36:00<32:43,  1.57it/s]
 95%|█████████▍| 54509/57600 [9:36:00<31:30,  1.63it/s]
 95%|█████████▍| 54510/57600 [9:36:01<31:45,  1.62it/s]
 95%|█████████▍| 54511/57600 [9:36:02<32:05,  1.60it/s]
 95%|█████████▍| 54512/57600 [9:36:02<32:34,  1.58it/s]
 95%|█████████▍| 54513/57600 [9:36:03<32:06,  1.60it/s]
 95%|█████████▍| 54514/57600 [9:36:03<32:38,  1.58it/s]
 95%|█████████▍| 54515/57600 [9:36:04<31:45,  1.62it/s]
 95%|█████████▍| 54516/57600 [9:36:05<31:52,  1.61it/s]
 95%|█████████▍| 54517/57600 [9:36:05<30:51,  1.67it/s]
 95%|█████████▍| 54518/57600 [9:36:06<31:02,  1.65it/s]
 95%|█████████▍| 54519/57600 [9:36:06<30:40,  1.67it/s]
 95%|█████████▍| 54520/57600 [9:36:07<30:37,  1.68it/s]
                                                       
{'loss': 1.0864, 'learning_rate': 1.482926829268293e-07, 'epoch': 601.77}

 95%|█████████▍| 54520/57600 [9:36:07<30:37,  1.68it/s]
 95%|█████████▍| 54521/57600 [9:36:08<31:36,  1.62it/s]
 95%|█████████▍| 54522/57600 [9:36:08<32:23,  1.58it/s]
 95%|█████████▍| 54523/57600 [9:36:09<32:29,  1.58it/s]
 95%|█████████▍| 54524/57600 [9:36:10<31:29,  1.63it/s]
 95%|█████████▍| 54525/57600 [9:36:10<31:40,  1.62it/s]
 95%|█████████▍| 54526/57600 [9:36:11<30:54,  1.66it/s]
 95%|█████████▍| 54527/57600 [9:36:11<31:24,  1.63it/s]
 95%|█████████▍| 54528/57600 [9:36:12<31:41,  1.62it/s]
 95%|█████████▍| 54529/57600 [9:36:13<31:37,  1.62it/s]
 95%|█████████▍| 54530/57600 [9:36:13<30:33,  1.67it/s]
 95%|█████████▍| 54531/57600 [9:36:14<30:37,  1.67it/s]
 95%|█████████▍| 54532/57600 [9:36:14<31:50,  1.61it/s]
 95%|█████████▍| 54533/57600 [9:36:15<31:37,  1.62it/s]
 95%|█████████▍| 54534/57600 [9:36:16<31:50,  1.61it/s]
 95%|█████████▍| 54535/57600 [9:36:16<31:50,  1.60it/s]
 95%|█████████▍| 54536/57600 [9:36:17<31:47,  1.61it/s]
 95%|█████████▍| 54537/57600 [9:36:18<32:07,  1.59it/s]
 95%|█████████▍| 54538/57600 [9:36:18<32:09,  1.59it/s]
 95%|█████████▍| 54539/57600 [9:36:19<32:41,  1.56it/s]
 95%|█████████▍| 54540/57600 [9:36:19<32:01,  1.59it/s]
                                                       
{'loss': 1.0926, 'learning_rate': 1.4797909407665503e-07, 'epoch': 601.99}

 95%|█████████▍| 54540/57600 [9:36:19<32:01,  1.59it/s]
 95%|█████████▍| 54541/57600 [9:36:20<31:44,  1.61it/s]
 95%|█████████▍| 54542/57600 [9:36:21<33:38,  1.52it/s]
 95%|█████████▍| 54543/57600 [9:36:21<33:02,  1.54it/s]
 95%|█████████▍| 54544/57600 [9:36:22<31:59,  1.59it/s]
 95%|█████████▍| 54545/57600 [9:36:23<32:35,  1.56it/s]
 95%|█████████▍| 54546/57600 [9:36:23<33:03,  1.54it/s]
 95%|█████████▍| 54547/57600 [9:36:24<32:06,  1.58it/s]
 95%|█████████▍| 54548/57600 [9:36:25<32:50,  1.55it/s]
 95%|█████████▍| 54549/57600 [9:36:25<33:14,  1.53it/s]
 95%|█████████▍| 54550/57600 [9:36:26<32:48,  1.55it/s]
 95%|█████████▍| 54551/57600 [9:36:27<32:07,  1.58it/s]
 95%|█████████▍| 54552/57600 [9:36:27<31:20,  1.62it/s]
 95%|█████████▍| 54553/57600 [9:36:28<31:43,  1.60it/s]
 95%|█████████▍| 54554/57600 [9:36:28<31:27,  1.61it/s]
 95%|█████████▍| 54555/57600 [9:36:29<30:55,  1.64it/s]
 95%|█████████▍| 54556/57600 [9:36:30<31:09,  1.63it/s]
 95%|█████████▍| 54557/57600 [9:36:30<33:22,  1.52it/s]
 95%|█████████▍| 54558/57600 [9:36:31<32:43,  1.55it/s]
 95%|█████████▍| 54559/57600 [9:36:32<31:54,  1.59it/s]
 95%|█████████▍| 54560/57600 [9:36:32<31:42,  1.60it/s]
                                                       
{'loss': 1.0962, 'learning_rate': 1.4766550522648086e-07, 'epoch': 602.21}

 95%|█████████▍| 54560/57600 [9:36:32<31:42,  1.60it/s]
 95%|█████████▍| 54561/57600 [9:36:33<31:55,  1.59it/s]
 95%|█████████▍| 54562/57600 [9:36:33<31:23,  1.61it/s]
 95%|█████████▍| 54563/57600 [9:36:34<31:26,  1.61it/s]
 95%|█████████▍| 54564/57600 [9:36:35<30:30,  1.66it/s]
 95%|█████████▍| 54565/57600 [9:36:35<30:35,  1.65it/s]
 95%|█████████▍| 54566/57600 [9:36:36<31:47,  1.59it/s]
 95%|█████████▍| 54567/57600 [9:36:37<31:21,  1.61it/s]
 95%|█████████▍| 54568/57600 [9:36:37<32:14,  1.57it/s]
 95%|█████████▍| 54569/57600 [9:36:38<31:13,  1.62it/s]
 95%|█████████▍| 54570/57600 [9:36:38<31:41,  1.59it/s]
 95%|█████████▍| 54571/57600 [9:36:39<31:23,  1.61it/s]
 95%|█████████▍| 54572/57600 [9:36:40<32:05,  1.57it/s]
 95%|█████████▍| 54573/57600 [9:36:40<31:34,  1.60it/s]
 95%|█████████▍| 54574/57600 [9:36:41<30:47,  1.64it/s]
 95%|█████████▍| 54575/57600 [9:36:41<30:17,  1.66it/s]
 95%|█████████▍| 54576/57600 [9:36:42<29:52,  1.69it/s]
 95%|█████████▍| 54577/57600 [9:36:43<29:21,  1.72it/s]
 95%|█████████▍| 54578/57600 [9:36:43<30:32,  1.65it/s]
 95%|█████████▍| 54579/57600 [9:36:44<31:01,  1.62it/s]
 95%|█████████▍| 54580/57600 [9:36:44<31:09,  1.62it/s]
                                                       
{'loss': 1.1248, 'learning_rate': 1.4735191637630658e-07, 'epoch': 602.43}

 95%|█████████▍| 54580/57600 [9:36:44<31:09,  1.62it/s]
 95%|█████████▍| 54581/57600 [9:36:45<31:36,  1.59it/s]
 95%|█████████▍| 54582/57600 [9:36:46<30:56,  1.63it/s]
 95%|█████████▍| 54583/57600 [9:36:46<31:27,  1.60it/s]
 95%|█████████▍| 54584/57600 [9:36:47<32:24,  1.55it/s]
 95%|█████████▍| 54585/57600 [9:36:48<32:48,  1.53it/s]
 95%|█████████▍| 54586/57600 [9:36:48<31:42,  1.58it/s]
 95%|█████████▍| 54587/57600 [9:36:49<30:29,  1.65it/s]
 95%|█████████▍| 54588/57600 [9:36:49<29:42,  1.69it/s]
 95%|█████████▍| 54589/57600 [9:36:50<29:48,  1.68it/s]
 95%|█████████▍| 54590/57600 [9:36:51<30:36,  1.64it/s]
 95%|█████████▍| 54591/57600 [9:36:51<30:54,  1.62it/s]
 95%|█████████▍| 54592/57600 [9:36:52<31:07,  1.61it/s]
 95%|█████████▍| 54593/57600 [9:36:53<31:38,  1.58it/s]
 95%|█████████▍| 54594/57600 [9:36:53<31:44,  1.58it/s]
 95%|█████████▍| 54595/57600 [9:36:54<32:41,  1.53it/s]
 95%|█████████▍| 54596/57600 [9:36:55<32:24,  1.54it/s]
 95%|█████████▍| 54597/57600 [9:36:55<31:13,  1.60it/s]
 95%|█████████▍| 54598/57600 [9:36:56<30:32,  1.64it/s]
 95%|█████████▍| 54599/57600 [9:36:56<29:55,  1.67it/s]
 95%|█████████▍| 54600/57600 [9:36:57<30:26,  1.64it/s]
                                                       
{'loss': 1.1002, 'learning_rate': 1.4703832752613242e-07, 'epoch': 602.65}

 95%|█████████▍| 54600/57600 [9:36:57<30:26,  1.64it/s]
 95%|█████████▍| 54601/57600 [9:36:57<29:55,  1.67it/s]
 95%|█████████▍| 54602/57600 [9:36:58<29:33,  1.69it/s]
 95%|█████████▍| 54603/57600 [9:36:59<28:57,  1.72it/s]
 95%|█████████▍| 54604/57600 [9:36:59<29:02,  1.72it/s]
 95%|█████████▍| 54605/57600 [9:37:00<29:06,  1.71it/s]
 95%|█████████▍| 54606/57600 [9:37:00<30:16,  1.65it/s]
 95%|█████████▍| 54607/57600 [9:37:01<30:06,  1.66it/s]
 95%|█████████▍| 54608/57600 [9:37:02<30:20,  1.64it/s]
 95%|█████████▍| 54609/57600 [9:37:02<30:08,  1.65it/s]
 95%|█████████▍| 54610/57600 [9:37:03<30:47,  1.62it/s]
 95%|█████████▍| 54611/57600 [9:37:03<30:10,  1.65it/s]
 95%|█████████▍| 54612/57600 [9:37:04<30:09,  1.65it/s]
 95%|█████████▍| 54613/57600 [9:37:05<30:49,  1.61it/s]
 95%|█████████▍| 54614/57600 [9:37:05<30:23,  1.64it/s]
 95%|█████████▍| 54615/57600 [9:37:06<31:14,  1.59it/s]
 95%|█████████▍| 54616/57600 [9:37:07<30:13,  1.65it/s]
 95%|█████████▍| 54617/57600 [9:37:07<31:12,  1.59it/s]
 95%|█████████▍| 54618/57600 [9:37:08<30:21,  1.64it/s]
 95%|█████████▍| 54619/57600 [9:37:08<30:19,  1.64it/s]
 95%|█████████▍| 54620/57600 [9:37:09<30:15,  1.64it/s]
                                                       
{'loss': 1.1349, 'learning_rate': 1.4672473867595814e-07, 'epoch': 602.87}

 95%|█████████▍| 54620/57600 [9:37:09<30:15,  1.64it/s]
 95%|█████████▍| 54621/57600 [9:37:10<30:05,  1.65it/s]
 95%|█████████▍| 54622/57600 [9:37:10<31:18,  1.59it/s]
 95%|█████████▍| 54623/57600 [9:37:11<31:32,  1.57it/s]
 95%|█████████▍| 54624/57600 [9:37:12<30:57,  1.60it/s]
 95%|█████████▍| 54625/57600 [9:37:12<30:09,  1.64it/s]
 95%|█████████▍| 54626/57600 [9:37:13<29:46,  1.66it/s]
 95%|█████████▍| 54627/57600 [9:37:13<31:05,  1.59it/s]
 95%|█████████▍| 54628/57600 [9:37:14<31:09,  1.59it/s]
 95%|█████████▍| 54629/57600 [9:37:15<29:49,  1.66it/s]
 95%|█████████▍| 54630/57600 [9:37:15<29:08,  1.70it/s]
 95%|█████████▍| 54631/57600 [9:37:16<29:30,  1.68it/s]
 95%|█████████▍| 54632/57600 [9:37:17<31:47,  1.56it/s]
 95%|█████████▍| 54633/57600 [9:37:17<32:17,  1.53it/s]
 95%|█████████▍| 54634/57600 [9:37:18<32:20,  1.53it/s]
 95%|█████████▍| 54635/57600 [9:37:18<31:47,  1.55it/s]
 95%|█████████▍| 54636/57600 [9:37:19<31:41,  1.56it/s]
 95%|█████████▍| 54637/57600 [9:37:20<30:31,  1.62it/s]
 95%|█████████▍| 54638/57600 [9:37:20<29:55,  1.65it/s]
 95%|█████████▍| 54639/57600 [9:37:21<30:19,  1.63it/s]
 95%|█████████▍| 54640/57600 [9:37:21<30:06,  1.64it/s]
                                                       
{'loss': 1.1023, 'learning_rate': 1.4641114982578397e-07, 'epoch': 603.09}

 95%|█████████▍| 54640/57600 [9:37:21<30:06,  1.64it/s]
 95%|█████████▍| 54641/57600 [9:37:22<30:52,  1.60it/s]
 95%|█████████▍| 54642/57600 [9:37:23<30:03,  1.64it/s]
 95%|█████████▍| 54643/57600 [9:37:23<29:17,  1.68it/s]
 95%|█████████▍| 54644/57600 [9:37:24<30:25,  1.62it/s]
 95%|█████████▍| 54645/57600 [9:37:24<29:41,  1.66it/s]
 95%|█████████▍| 54646/57600 [9:37:25<30:22,  1.62it/s]
 95%|█████████▍| 54647/57600 [9:37:26<30:22,  1.62it/s]
 95%|█████████▍| 54648/57600 [9:37:26<30:19,  1.62it/s]
 95%|█████████▍| 54649/57600 [9:37:27<29:26,  1.67it/s]
 95%|█████████▍| 54650/57600 [9:37:28<30:50,  1.59it/s]
 95%|█████████▍| 54651/57600 [9:37:28<30:39,  1.60it/s]
 95%|█████████▍| 54652/57600 [9:37:29<30:59,  1.59it/s]
 95%|█████████▍| 54653/57600 [9:37:30<31:11,  1.57it/s]
 95%|█████████▍| 54654/57600 [9:37:30<30:37,  1.60it/s]
 95%|█████████▍| 54655/57600 [9:37:31<30:16,  1.62it/s]
 95%|█████████▍| 54656/57600 [9:37:31<29:24,  1.67it/s]
 95%|█████████▍| 54657/57600 [9:37:32<29:35,  1.66it/s]
 95%|█████████▍| 54658/57600 [9:37:32<29:06,  1.68it/s]
 95%|█████████▍| 54659/57600 [9:37:33<28:50,  1.70it/s]
 95%|█████████▍| 54660/57600 [9:37:34<29:01,  1.69it/s]
                                                       
{'loss': 1.0891, 'learning_rate': 1.460975609756098e-07, 'epoch': 603.31}

 95%|█████████▍| 54660/57600 [9:37:34<29:01,  1.69it/s]
 95%|█████████▍| 54661/57600 [9:37:34<29:08,  1.68it/s]
 95%|█████████▍| 54662/57600 [9:37:35<29:16,  1.67it/s]
 95%|█████████▍| 54663/57600 [9:37:35<29:45,  1.64it/s]
 95%|█████████▍| 54664/57600 [9:37:36<29:45,  1.64it/s]
 95%|█████████▍| 54665/57600 [9:37:37<30:24,  1.61it/s]
 95%|█████████▍| 54666/57600 [9:37:37<30:26,  1.61it/s]
 95%|█████████▍| 54667/57600 [9:37:38<30:42,  1.59it/s]
 95%|█████████▍| 54668/57600 [9:37:39<30:44,  1.59it/s]
 95%|█████████▍| 54669/57600 [9:37:39<30:36,  1.60it/s]
 95%|█████████▍| 54670/57600 [9:37:40<31:06,  1.57it/s]
 95%|█████████▍| 54671/57600 [9:37:41<31:12,  1.56it/s]
 95%|█████████▍| 54672/57600 [9:37:41<31:06,  1.57it/s]
 95%|█████████▍| 54673/57600 [9:37:42<30:32,  1.60it/s]
 95%|█████████▍| 54674/57600 [9:37:42<29:29,  1.65it/s]
 95%|█████████▍| 54675/57600 [9:37:43<29:52,  1.63it/s]
 95%|█████████▍| 54676/57600 [9:37:44<30:03,  1.62it/s]
 95%|█████████▍| 54677/57600 [9:37:44<31:35,  1.54it/s]
 95%|█████████▍| 54678/57600 [9:37:45<30:54,  1.58it/s]
 95%|█████████▍| 54679/57600 [9:37:46<30:37,  1.59it/s]
 95%|█████████▍| 54680/57600 [9:37:46<29:58,  1.62it/s]
                                                       
{'loss': 1.0676, 'learning_rate': 1.457839721254355e-07, 'epoch': 603.53}

 95%|█████████▍| 54680/57600 [9:37:46<29:58,  1.62it/s]
 95%|█████████▍| 54681/57600 [9:37:47<30:32,  1.59it/s]
 95%|█████████▍| 54682/57600 [9:37:47<30:44,  1.58it/s]
 95%|█████████▍| 54683/57600 [9:37:48<31:16,  1.55it/s]
 95%|█████████▍| 54684/57600 [9:37:49<30:31,  1.59it/s]
 95%|█████████▍| 54685/57600 [9:37:49<30:11,  1.61it/s]
 95%|█████████▍| 54686/57600 [9:37:50<29:03,  1.67it/s]
 95%|█████████▍| 54687/57600 [9:37:50<29:27,  1.65it/s]
 95%|█████████▍| 54688/57600 [9:37:51<29:07,  1.67it/s]
 95%|█████████▍| 54689/57600 [9:37:52<30:30,  1.59it/s]
 95%|█████████▍| 54690/57600 [9:37:52<30:45,  1.58it/s]
 95%|█████████▍| 54691/57600 [9:37:53<30:41,  1.58it/s]
 95%|█████████▍| 54692/57600 [9:37:54<29:25,  1.65it/s]
 95%|█████████▍| 54693/57600 [9:37:54<29:55,  1.62it/s]
 95%|█████████▍| 54694/57600 [9:37:55<29:14,  1.66it/s]
 95%|█████████▍| 54695/57600 [9:37:55<30:00,  1.61it/s]
 95%|█████████▍| 54696/57600 [9:37:56<31:12,  1.55it/s]
 95%|█████████▍| 54697/57600 [9:37:57<30:21,  1.59it/s]
 95%|█████████▍| 54698/57600 [9:37:57<31:32,  1.53it/s]
 95%|█████████▍| 54699/57600 [9:37:58<31:11,  1.55it/s]
 95%|█████████▍| 54700/57600 [9:37:59<31:01,  1.56it/s]
                                                       
{'loss': 1.1309, 'learning_rate': 1.4547038327526133e-07, 'epoch': 603.75}

 95%|█████████▍| 54700/57600 [9:37:59<31:01,  1.56it/s]
 95%|█████████▍| 54701/57600 [9:37:59<31:10,  1.55it/s]
 95%|█████████▍| 54702/57600 [9:38:00<31:48,  1.52it/s]
 95%|█████████▍| 54703/57600 [9:38:01<30:48,  1.57it/s]
 95%|█████████▍| 54704/57600 [9:38:01<30:49,  1.57it/s]
 95%|█████████▍| 54705/57600 [9:38:02<31:04,  1.55it/s]
 95%|█████████▍| 54706/57600 [9:38:03<30:30,  1.58it/s]
 95%|█████████▍| 54707/57600 [9:38:03<29:25,  1.64it/s]
 95%|█████████▍| 54708/57600 [9:38:04<28:49,  1.67it/s]
 95%|█████████▍| 54709/57600 [9:38:04<28:25,  1.69it/s]
 95%|█████████▍| 54710/57600 [9:38:05<28:51,  1.67it/s]
 95%|█████████▍| 54711/57600 [9:38:05<28:59,  1.66it/s]
 95%|█████████▍| 54712/57600 [9:38:06<28:57,  1.66it/s]
 95%|█████████▍| 54713/57600 [9:38:07<29:43,  1.62it/s]
 95%|█████████▍| 54714/57600 [9:38:07<29:52,  1.61it/s]
 95%|█████████▍| 54715/57600 [9:38:08<29:24,  1.64it/s]
 95%|█████████▍| 54716/57600 [9:38:09<28:57,  1.66it/s]
 95%|█████████▍| 54717/57600 [9:38:09<29:12,  1.65it/s]
 95%|█████████▍| 54718/57600 [9:38:10<30:19,  1.58it/s]
 95%|█████████▍| 54719/57600 [9:38:10<29:30,  1.63it/s]
 95%|█████████▌| 54720/57600 [9:38:11<29:11,  1.64it/s]
                                                       
{'loss': 1.1159, 'learning_rate': 1.4515679442508706e-07, 'epoch': 603.97}

 95%|█████████▌| 54720/57600 [9:38:11<29:11,  1.64it/s]
 95%|█████████▌| 54721/57600 [9:38:12<29:36,  1.62it/s]
 95%|█████████▌| 54722/57600 [9:38:12<29:23,  1.63it/s]
 95%|█████████▌| 54723/57600 [9:38:13<30:50,  1.55it/s]
 95%|█████████▌| 54724/57600 [9:38:14<29:56,  1.60it/s]
 95%|█████████▌| 54725/57600 [9:38:14<30:05,  1.59it/s]
 95%|█████████▌| 54726/57600 [9:38:15<29:38,  1.62it/s]
 95%|█████████▌| 54727/57600 [9:38:15<29:19,  1.63it/s]
 95%|█████████▌| 54728/57600 [9:38:16<29:31,  1.62it/s]
 95%|█████████▌| 54729/57600 [9:38:17<29:46,  1.61it/s]
 95%|█████████▌| 54730/57600 [9:38:17<29:43,  1.61it/s]
 95%|█████████▌| 54731/57600 [9:38:18<29:30,  1.62it/s]
 95%|█████████▌| 54732/57600 [9:38:18<29:18,  1.63it/s]
 95%|█████████▌| 54733/57600 [9:38:19<29:14,  1.63it/s]
 95%|█████████▌| 54734/57600 [9:38:20<30:02,  1.59it/s]
 95%|█████████▌| 54735/57600 [9:38:20<30:23,  1.57it/s]
 95%|█████████▌| 54736/57600 [9:38:21<29:26,  1.62it/s]
 95%|█████████▌| 54737/57600 [9:38:22<29:55,  1.59it/s]
 95%|█████████▌| 54738/57600 [9:38:22<30:03,  1.59it/s]
 95%|█████████▌| 54739/57600 [9:38:23<29:18,  1.63it/s]
 95%|█████████▌| 54740/57600 [9:38:23<28:42,  1.66it/s]
                                                       
{'loss': 1.0951, 'learning_rate': 1.448432055749129e-07, 'epoch': 604.19}

 95%|█████████▌| 54740/57600 [9:38:23<28:42,  1.66it/s]
 95%|█████████▌| 54741/57600 [9:38:24<28:06,  1.70it/s]
 95%|█████████▌| 54742/57600 [9:38:25<27:51,  1.71it/s]
 95%|█████████▌| 54743/57600 [9:38:25<27:39,  1.72it/s]
 95%|█████████▌| 54744/57600 [9:38:26<28:12,  1.69it/s]
 95%|█████████▌| 54745/57600 [9:38:26<28:15,  1.68it/s]
 95%|█████████▌| 54746/57600 [9:38:27<28:16,  1.68it/s]
 95%|█████████▌| 54747/57600 [9:38:28<29:07,  1.63it/s]
 95%|█████████▌| 54748/57600 [9:38:28<28:59,  1.64it/s]
 95%|█████████▌| 54749/57600 [9:38:29<29:06,  1.63it/s]
 95%|█████████▌| 54750/57600 [9:38:29<29:21,  1.62it/s]
 95%|█████████▌| 54751/57600 [9:38:30<29:29,  1.61it/s]
 95%|█████████▌| 54752/57600 [9:38:31<29:25,  1.61it/s]
 95%|█████████▌| 54753/57600 [9:38:31<30:15,  1.57it/s]
 95%|█████████▌| 54754/57600 [9:38:32<30:01,  1.58it/s]
 95%|█████████▌| 54755/57600 [9:38:33<30:31,  1.55it/s]
 95%|█████████▌| 54756/57600 [9:38:33<29:27,  1.61it/s]
 95%|█████████▌| 54757/57600 [9:38:34<29:56,  1.58it/s]
 95%|█████████▌| 54758/57600 [9:38:34<29:10,  1.62it/s]
 95%|█████████▌| 54759/57600 [9:38:35<29:40,  1.60it/s]
 95%|█████████▌| 54760/57600 [9:38:36<30:29,  1.55it/s]
                                                       
{'loss': 1.1112, 'learning_rate': 1.4452961672473862e-07, 'epoch': 604.42}

 95%|█████████▌| 54760/57600 [9:38:36<30:29,  1.55it/s]
 95%|█████████▌| 54761/57600 [9:38:36<29:28,  1.61it/s]
 95%|█████████▌| 54762/57600 [9:38:37<29:52,  1.58it/s]
 95%|█████████▌| 54763/57600 [9:38:38<29:25,  1.61it/s]
 95%|█████████▌| 54764/57600 [9:38:38<29:51,  1.58it/s]
 95%|█████████▌| 54765/57600 [9:38:39<29:51,  1.58it/s]
 95%|█████████▌| 54766/57600 [9:38:39<28:50,  1.64it/s]
 95%|█████████▌| 54767/57600 [9:38:40<28:41,  1.65it/s]
 95%|█████████▌| 54768/57600 [9:38:41<29:02,  1.63it/s]
 95%|█████████▌| 54769/57600 [9:38:41<29:30,  1.60it/s]
 95%|█████████▌| 54770/57600 [9:38:42<29:45,  1.58it/s]
 95%|█████████▌| 54771/57600 [9:38:43<30:17,  1.56it/s]
 95%|█████████▌| 54772/57600 [9:38:43<29:49,  1.58it/s]
 95%|█████████▌| 54773/57600 [9:38:44<28:32,  1.65it/s]
 95%|█████████▌| 54774/57600 [9:38:44<28:35,  1.65it/s]
 95%|█████████▌| 54775/57600 [9:38:45<27:54,  1.69it/s]
 95%|█████████▌| 54776/57600 [9:38:46<28:40,  1.64it/s]
 95%|█████████▌| 54777/57600 [9:38:46<28:48,  1.63it/s]
 95%|█████████▌| 54778/57600 [9:38:47<28:06,  1.67it/s]
 95%|█████████▌| 54779/57600 [9:38:48<30:31,  1.54it/s]
 95%|█████████▌| 54780/57600 [9:38:48<29:56,  1.57it/s]
                                                       
{'loss': 1.0841, 'learning_rate': 1.4421602787456445e-07, 'epoch': 604.64}

 95%|█████████▌| 54780/57600 [9:38:48<29:56,  1.57it/s]
 95%|█████████▌| 54781/57600 [9:38:49<31:29,  1.49it/s]
 95%|█████████▌| 54782/57600 [9:38:50<29:54,  1.57it/s]
 95%|█████████▌| 54783/57600 [9:38:50<29:16,  1.60it/s]
 95%|█████████▌| 54784/57600 [9:38:51<29:51,  1.57it/s]
 95%|█████████▌| 54785/57600 [9:38:51<30:46,  1.52it/s]
 95%|█████████▌| 54786/57600 [9:38:52<32:36,  1.44it/s]
 95%|█████████▌| 54787/57600 [9:38:53<32:00,  1.46it/s]
 95%|█████████▌| 54788/57600 [9:38:53<30:10,  1.55it/s]
 95%|█████████▌| 54789/57600 [9:38:54<30:27,  1.54it/s]
 95%|█████████▌| 54790/57600 [9:38:55<30:18,  1.54it/s]
 95%|█████████▌| 54791/57600 [9:38:55<29:42,  1.58it/s]
 95%|█████████▌| 54792/57600 [9:38:56<29:42,  1.58it/s]
 95%|█████████▌| 54793/57600 [9:38:57<28:22,  1.65it/s]
 95%|█████████▌| 54794/57600 [9:38:57<28:37,  1.63it/s]
 95%|█████████▌| 54795/57600 [9:38:58<28:57,  1.61it/s]
 95%|█████████▌| 54796/57600 [9:38:58<28:48,  1.62it/s]
 95%|█████████▌| 54797/57600 [9:38:59<28:03,  1.67it/s]
 95%|█████████▌| 54798/57600 [9:39:00<27:58,  1.67it/s]
 95%|█████████▌| 54799/57600 [9:39:00<28:16,  1.65it/s]
 95%|█████████▌| 54800/57600 [9:39:01<28:57,  1.61it/s]
                                                       
{'loss': 1.0821, 'learning_rate': 1.4390243902439028e-07, 'epoch': 604.86}

 95%|█████████▌| 54800/57600 [9:39:01<28:57,  1.61it/s]
 95%|█████████▌| 54801/57600 [9:39:02<30:07,  1.55it/s]
 95%|█████████▌| 54802/57600 [9:39:02<29:54,  1.56it/s]
 95%|█████████▌| 54803/57600 [9:39:03<29:12,  1.60it/s]
 95%|█████████▌| 54804/57600 [9:39:03<28:44,  1.62it/s]
 95%|█████████▌| 54805/57600 [9:39:04<28:52,  1.61it/s]
 95%|█████████▌| 54806/57600 [9:39:05<28:34,  1.63it/s]
 95%|█████████▌| 54807/57600 [9:39:05<28:10,  1.65it/s]
 95%|█████████▌| 54808/57600 [9:39:06<27:38,  1.68it/s]
 95%|█████████▌| 54809/57600 [9:39:06<28:01,  1.66it/s]
 95%|█████████▌| 54810/57600 [9:39:07<28:26,  1.64it/s]
 95%|█████████▌| 54811/57600 [9:39:08<29:48,  1.56it/s]
 95%|█████████▌| 54812/57600 [9:39:08<29:10,  1.59it/s]
 95%|█████████▌| 54813/57600 [9:39:09<28:23,  1.64it/s]
 95%|█████████▌| 54814/57600 [9:39:10<28:40,  1.62it/s]
 95%|█████████▌| 54815/57600 [9:39:10<29:32,  1.57it/s]
 95%|█████████▌| 54816/57600 [9:39:11<29:37,  1.57it/s]
 95%|█████████▌| 54817/57600 [9:39:12<30:33,  1.52it/s]
 95%|█████████▌| 54818/57600 [9:39:12<29:32,  1.57it/s]
 95%|█████████▌| 54819/57600 [9:39:13<29:19,  1.58it/s]
 95%|█████████▌| 54820/57600 [9:39:13<29:17,  1.58it/s]
                                                       
{'loss': 1.0895, 'learning_rate': 1.43588850174216e-07, 'epoch': 605.08}

 95%|█████████▌| 54820/57600 [9:39:13<29:17,  1.58it/s]
 95%|█████████▌| 54821/57600 [9:39:14<28:26,  1.63it/s]
 95%|█████████▌| 54822/57600 [9:39:15<27:27,  1.69it/s]
 95%|█████████▌| 54823/57600 [9:39:15<28:05,  1.65it/s]
 95%|█████████▌| 54824/57600 [9:39:16<28:10,  1.64it/s]
 95%|█████████▌| 54825/57600 [9:39:16<27:41,  1.67it/s]
 95%|█████████▌| 54826/57600 [9:39:17<27:54,  1.66it/s]
 95%|█████████▌| 54827/57600 [9:39:18<28:13,  1.64it/s]
 95%|█████████▌| 54828/57600 [9:39:18<30:21,  1.52it/s]
 95%|█████████▌| 54829/57600 [9:39:19<29:54,  1.54it/s]
 95%|█████████▌| 54830/57600 [9:39:20<30:05,  1.53it/s]
 95%|█████████▌| 54831/57600 [9:39:20<30:15,  1.53it/s]
 95%|█████████▌| 54832/57600 [9:39:21<29:31,  1.56it/s]
 95%|█████████▌| 54833/57600 [9:39:21<28:43,  1.61it/s]
 95%|█████████▌| 54834/57600 [9:39:22<28:46,  1.60it/s]
 95%|█████████▌| 54835/57600 [9:39:23<28:38,  1.61it/s]
 95%|█████████▌| 54836/57600 [9:39:23<29:05,  1.58it/s]
 95%|█████████▌| 54837/57600 [9:39:24<28:47,  1.60it/s]
 95%|█████████▌| 54838/57600 [9:39:25<27:54,  1.65it/s]
 95%|█████████▌| 54839/57600 [9:39:25<28:18,  1.63it/s]
 95%|█████████▌| 54840/57600 [9:39:26<28:19,  1.62it/s]
                                                       
{'loss': 1.1064, 'learning_rate': 1.4327526132404184e-07, 'epoch': 605.3}

 95%|█████████▌| 54840/57600 [9:39:26<28:19,  1.62it/s]
 95%|█████████▌| 54841/57600 [9:39:26<28:34,  1.61it/s]
 95%|█████████▌| 54842/57600 [9:39:27<28:05,  1.64it/s]
 95%|█████████▌| 54843/57600 [9:39:28<27:31,  1.67it/s]
 95%|█████████▌| 54844/57600 [9:39:28<27:43,  1.66it/s]
 95%|█████████▌| 54845/57600 [9:39:29<29:02,  1.58it/s]
 95%|█████████▌| 54846/57600 [9:39:30<28:27,  1.61it/s]
 95%|█████████▌| 54847/57600 [9:39:30<28:29,  1.61it/s]
 95%|█████████▌| 54848/57600 [9:39:31<27:49,  1.65it/s]
 95%|█████████▌| 54849/57600 [9:39:31<28:18,  1.62it/s]
 95%|█████████▌| 54850/57600 [9:39:32<28:01,  1.64it/s]
 95%|█████████▌| 54851/57600 [9:39:33<28:38,  1.60it/s]
 95%|█████████▌| 54852/57600 [9:39:33<28:21,  1.62it/s]
 95%|█████████▌| 54853/57600 [9:39:34<27:33,  1.66it/s]
 95%|█████████▌| 54854/57600 [9:39:34<27:46,  1.65it/s]
 95%|█████████▌| 54855/57600 [9:39:35<28:12,  1.62it/s]
 95%|█████████▌| 54856/57600 [9:39:36<28:09,  1.62it/s]
 95%|█████████▌| 54857/57600 [9:39:36<27:56,  1.64it/s]
 95%|█████████▌| 54858/57600 [9:39:37<27:59,  1.63it/s]
 95%|█████████▌| 54859/57600 [9:39:38<28:29,  1.60it/s]
 95%|█████████▌| 54860/57600 [9:39:38<29:40,  1.54it/s]
                                                       
{'loss': 1.1224, 'learning_rate': 1.4296167247386756e-07, 'epoch': 605.52}

 95%|█████████▌| 54860/57600 [9:39:38<29:40,  1.54it/s]
 95%|█████████▌| 54861/57600 [9:39:39<28:36,  1.60it/s]
 95%|█████████▌| 54862/57600 [9:39:39<29:29,  1.55it/s]
 95%|█████████▌| 54863/57600 [9:39:40<29:38,  1.54it/s]
 95%|█████████▌| 54864/57600 [9:39:41<29:35,  1.54it/s]
 95%|█████████▌| 54865/57600 [9:39:41<29:15,  1.56it/s]
 95%|█████████▌| 54866/57600 [9:39:42<28:57,  1.57it/s]
 95%|█████████▌| 54867/57600 [9:39:43<30:17,  1.50it/s]
 95%|█████████▌| 54868/57600 [9:39:43<28:59,  1.57it/s]
 95%|█████████▌| 54869/57600 [9:39:44<28:29,  1.60it/s]
 95%|█████████▌| 54870/57600 [9:39:45<28:04,  1.62it/s]
 95%|█████████▌| 54871/57600 [9:39:45<28:07,  1.62it/s]
 95%|█████████▌| 54872/57600 [9:39:46<29:15,  1.55it/s]
 95%|█████████▌| 54873/57600 [9:39:46<29:11,  1.56it/s]
 95%|█████████▌| 54874/57600 [9:39:47<29:34,  1.54it/s]
 95%|█████████▌| 54875/57600 [9:39:48<29:07,  1.56it/s]
 95%|█████████▌| 54876/57600 [9:39:48<27:57,  1.62it/s]
 95%|█████████▌| 54877/57600 [9:39:49<27:44,  1.64it/s]
 95%|█████████▌| 54878/57600 [9:39:50<27:08,  1.67it/s]
 95%|█████████▌| 54879/57600 [9:39:50<27:11,  1.67it/s]
 95%|█████████▌| 54880/57600 [9:39:51<27:23,  1.66it/s]
                                                       
{'loss': 1.0574, 'learning_rate': 1.426480836236934e-07, 'epoch': 605.74}

 95%|█████████▌| 54880/57600 [9:39:51<27:23,  1.66it/s]
 95%|█████████▌| 54881/57600 [9:39:51<27:01,  1.68it/s]
 95%|█████████▌| 54882/57600 [9:39:52<28:00,  1.62it/s]
 95%|█████████▌| 54883/57600 [9:39:53<27:53,  1.62it/s]
 95%|█████████▌| 54884/57600 [9:39:53<28:45,  1.57it/s]
 95%|█████████▌| 54885/57600 [9:39:54<28:33,  1.58it/s]
 95%|█████████▌| 54886/57600 [9:39:54<28:03,  1.61it/s]
 95%|█████████▌| 54887/57600 [9:39:55<28:01,  1.61it/s]
 95%|█████████▌| 54888/57600 [9:39:56<28:00,  1.61it/s]
 95%|█████████▌| 54889/57600 [9:39:56<27:20,  1.65it/s]
 95%|█████████▌| 54890/57600 [9:39:57<28:48,  1.57it/s]
 95%|█████████▌| 54891/57600 [9:39:58<28:05,  1.61it/s]
 95%|█████████▌| 54892/57600 [9:39:58<28:00,  1.61it/s]
 95%|█████████▌| 54893/57600 [9:39:59<28:06,  1.61it/s]
 95%|█████████▌| 54894/57600 [9:39:59<27:57,  1.61it/s]
 95%|█████████▌| 54895/57600 [9:40:00<27:48,  1.62it/s]
 95%|█████████▌| 54896/57600 [9:40:01<27:34,  1.63it/s]
 95%|█████████▌| 54897/57600 [9:40:01<28:21,  1.59it/s]
 95%|█████████▌| 54898/57600 [9:40:02<28:16,  1.59it/s]
 95%|█████████▌| 54899/57600 [9:40:03<28:04,  1.60it/s]
 95%|█████████▌| 54900/57600 [9:40:03<27:55,  1.61it/s]
                                                       
{'loss': 1.117, 'learning_rate': 1.4233449477351912e-07, 'epoch': 605.96}

 95%|█████████▌| 54900/57600 [9:40:03<27:55,  1.61it/s]
 95%|█████████▌| 54901/57600 [9:40:04<28:18,  1.59it/s]
 95%|█████████▌| 54902/57600 [9:40:04<28:16,  1.59it/s]
 95%|█████████▌| 54903/57600 [9:40:05<27:45,  1.62it/s]
 95%|█████████▌| 54904/57600 [9:40:06<29:03,  1.55it/s]
 95%|█████████▌| 54905/57600 [9:40:06<28:15,  1.59it/s]
 95%|█████████▌| 54906/57600 [9:40:07<28:29,  1.58it/s]
 95%|█████████▌| 54907/57600 [9:40:08<28:19,  1.58it/s]
 95%|█████████▌| 54908/57600 [9:40:08<28:54,  1.55it/s]
 95%|█████████▌| 54909/57600 [9:40:09<28:35,  1.57it/s]
 95%|█████████▌| 54910/57600 [9:40:09<27:44,  1.62it/s]
 95%|█████████▌| 54911/57600 [9:40:10<27:32,  1.63it/s]
 95%|█████████▌| 54912/57600 [9:40:11<27:06,  1.65it/s]
 95%|█████████▌| 54913/57600 [9:40:11<27:42,  1.62it/s]
 95%|█████████▌| 54914/57600 [9:40:12<29:03,  1.54it/s]
 95%|█████████▌| 54915/57600 [9:40:13<28:36,  1.56it/s]
 95%|█████████▌| 54916/57600 [9:40:13<28:34,  1.57it/s]
 95%|█████████▌| 54917/57600 [9:40:14<28:32,  1.57it/s]
 95%|█████████▌| 54918/57600 [9:40:15<28:17,  1.58it/s]
 95%|█████████▌| 54919/57600 [9:40:15<28:03,  1.59it/s]
 95%|█████████▌| 54920/57600 [9:40:16<27:52,  1.60it/s]
                                                       
{'loss': 1.1048, 'learning_rate': 1.4202090592334495e-07, 'epoch': 606.18}

 95%|█████████▌| 54920/57600 [9:40:16<27:52,  1.60it/s]
 95%|█████████▌| 54921/57600 [9:40:16<28:38,  1.56it/s]
 95%|█████████▌| 54922/57600 [9:40:17<27:49,  1.60it/s]
 95%|█████████▌| 54923/57600 [9:40:18<27:34,  1.62it/s]
 95%|█████████▌| 54924/57600 [9:40:18<27:57,  1.60it/s]
 95%|█████████▌| 54925/57600 [9:40:19<26:47,  1.66it/s]
 95%|█████████▌| 54926/57600 [9:40:19<26:30,  1.68it/s]
 95%|█████████▌| 54927/57600 [9:40:20<26:42,  1.67it/s]
 95%|█████████▌| 54928/57600 [9:40:21<27:37,  1.61it/s]
 95%|█████████▌| 54929/57600 [9:40:21<27:07,  1.64it/s]
 95%|█████████▌| 54930/57600 [9:40:22<28:17,  1.57it/s]
 95%|█████████▌| 54931/57600 [9:40:23<28:15,  1.57it/s]
 95%|█████████▌| 54932/57600 [9:40:23<28:20,  1.57it/s]
 95%|█████████▌| 54933/57600 [9:40:24<29:04,  1.53it/s]
 95%|█████████▌| 54934/57600 [9:40:25<28:27,  1.56it/s]
 95%|█████████▌| 54935/57600 [9:40:25<28:23,  1.56it/s]
 95%|█████████▌| 54936/57600 [9:40:26<28:44,  1.55it/s]
 95%|█████████▌| 54937/57600 [9:40:26<27:44,  1.60it/s]
 95%|█████████▌| 54938/57600 [9:40:27<27:56,  1.59it/s]
 95%|█████████▌| 54939/57600 [9:40:28<28:08,  1.58it/s]
 95%|█████████▌| 54940/57600 [9:40:28<27:58,  1.58it/s]
                                                       
{'loss': 1.0805, 'learning_rate': 1.4170731707317073e-07, 'epoch': 606.4}

 95%|█████████▌| 54940/57600 [9:40:28<27:58,  1.58it/s]
 95%|█████████▌| 54941/57600 [9:40:29<28:01,  1.58it/s]
 95%|█████████▌| 54942/57600 [9:40:30<28:10,  1.57it/s]
 95%|█████████▌| 54943/57600 [9:40:30<28:26,  1.56it/s]
 95%|█████████▌| 54944/57600 [9:40:31<27:50,  1.59it/s]
 95%|█████████▌| 54945/57600 [9:40:32<27:35,  1.60it/s]
 95%|█████████▌| 54946/57600 [9:40:32<26:51,  1.65it/s]
 95%|█████████▌| 54947/57600 [9:40:33<27:35,  1.60it/s]
 95%|█████████▌| 54948/57600 [9:40:33<27:45,  1.59it/s]
 95%|█████████▌| 54949/57600 [9:40:34<27:24,  1.61it/s]
 95%|█████████▌| 54950/57600 [9:40:35<26:38,  1.66it/s]
 95%|█████████▌| 54951/57600 [9:40:35<27:07,  1.63it/s]
 95%|█████████▌| 54952/57600 [9:40:36<26:59,  1.63it/s]
 95%|█████████▌| 54953/57600 [9:40:36<27:46,  1.59it/s]
 95%|█████████▌| 54954/57600 [9:40:37<28:12,  1.56it/s]
 95%|█████████▌| 54955/57600 [9:40:38<28:03,  1.57it/s]
 95%|█████████▌| 54956/57600 [9:40:38<27:40,  1.59it/s]
 95%|█████████▌| 54957/57600 [9:40:39<27:59,  1.57it/s]
 95%|█████████▌| 54958/57600 [9:40:40<27:44,  1.59it/s]
 95%|█████████▌| 54959/57600 [9:40:40<26:45,  1.65it/s]
 95%|█████████▌| 54960/57600 [9:40:41<26:30,  1.66it/s]
                                                       
{'loss': 1.1119, 'learning_rate': 1.4139372822299648e-07, 'epoch': 606.62}

 95%|█████████▌| 54960/57600 [9:40:41<26:30,  1.66it/s]
 95%|█████████▌| 54961/57600 [9:40:41<25:57,  1.69it/s]
 95%|█████████▌| 54962/57600 [9:40:42<26:26,  1.66it/s]
 95%|█████████▌| 54963/57600 [9:40:43<25:53,  1.70it/s]
 95%|█████████▌| 54964/57600 [9:40:43<25:30,  1.72it/s]
 95%|█████████▌| 54965/57600 [9:40:44<25:56,  1.69it/s]
 95%|█████████▌| 54966/57600 [9:40:44<25:32,  1.72it/s]
 95%|█████████▌| 54967/57600 [9:40:45<25:52,  1.70it/s]
 95%|█████████▌| 54968/57600 [9:40:46<26:55,  1.63it/s]
 95%|█████████▌| 54969/57600 [9:40:46<26:53,  1.63it/s]
 95%|█████████▌| 54970/57600 [9:40:47<26:40,  1.64it/s]
 95%|█████████▌| 54971/57600 [9:40:47<25:52,  1.69it/s]
 95%|█████████▌| 54972/57600 [9:40:48<26:04,  1.68it/s]
 95%|█████████▌| 54973/57600 [9:40:48<25:31,  1.72it/s]
 95%|█████████▌| 54974/57600 [9:40:49<25:38,  1.71it/s]
 95%|█████████▌| 54975/57600 [9:40:50<25:54,  1.69it/s]
 95%|█████████▌| 54976/57600 [9:40:50<25:57,  1.69it/s]
 95%|█████████▌| 54977/57600 [9:40:51<26:52,  1.63it/s]
 95%|█████████▌| 54978/57600 [9:40:51<26:26,  1.65it/s]
 95%|█████████▌| 54979/57600 [9:40:52<26:43,  1.63it/s]
 95%|█████████▌| 54980/57600 [9:40:53<27:08,  1.61it/s]
                                                       
{'loss': 1.1512, 'learning_rate': 1.410801393728223e-07, 'epoch': 606.84}

 95%|█████████▌| 54980/57600 [9:40:53<27:08,  1.61it/s]
 95%|█████████▌| 54981/57600 [9:40:53<26:59,  1.62it/s]
 95%|█████████▌| 54982/57600 [9:40:54<27:50,  1.57it/s]
 95%|█████████▌| 54983/57600 [9:40:55<26:55,  1.62it/s]
 95%|█████████▌| 54984/57600 [9:40:55<26:49,  1.63it/s]
 95%|█████████▌| 54985/57600 [9:40:56<28:47,  1.51it/s]
 95%|█████████▌| 54986/57600 [9:40:57<28:03,  1.55it/s]
 95%|█████████▌| 54987/57600 [9:40:57<28:15,  1.54it/s]
 95%|█████████▌| 54988/57600 [9:40:58<27:32,  1.58it/s]
 95%|█████████▌| 54989/57600 [9:40:59<27:45,  1.57it/s]
 95%|█████████▌| 54990/57600 [9:40:59<26:50,  1.62it/s]
 95%|█████████▌| 54991/57600 [9:41:00<27:15,  1.60it/s]
 95%|█████████▌| 54992/57600 [9:41:00<26:49,  1.62it/s]
 95%|█████████▌| 54993/57600 [9:41:01<26:32,  1.64it/s]
 95%|█████████▌| 54994/57600 [9:41:02<26:52,  1.62it/s]
 95%|█████████▌| 54995/57600 [9:41:02<28:22,  1.53it/s]
 95%|█████████▌| 54996/57600 [9:41:03<28:10,  1.54it/s]
 95%|█████████▌| 54997/57600 [9:41:04<27:50,  1.56it/s]
 95%|█████████▌| 54998/57600 [9:41:04<27:08,  1.60it/s]
 95%|█████████▌| 54999/57600 [9:41:05<26:32,  1.63it/s]
 95%|█████████▌| 55000/57600 [9:41:05<25:35,  1.69it/s]
                                                       
{'loss': 1.0824, 'learning_rate': 1.4076655052264804e-07, 'epoch': 607.06}

 95%|█████████▌| 55000/57600 [9:41:05<25:35,  1.69it/s]
 95%|█████████▌| 55001/57600 [9:41:06<26:33,  1.63it/s]
 95%|█████████▌| 55002/57600 [9:41:06<25:36,  1.69it/s]
 95%|█████████▌| 55003/57600 [9:41:07<26:36,  1.63it/s]
 95%|█████████▌| 55004/57600 [9:41:08<26:10,  1.65it/s]
 95%|█████████▌| 55005/57600 [9:41:08<27:57,  1.55it/s]
 95%|█████████▌| 55006/57600 [9:41:09<28:40,  1.51it/s]
 95%|█████████▌| 55007/57600 [9:41:10<28:53,  1.50it/s]
 96%|█████████▌| 55008/57600 [9:41:10<27:54,  1.55it/s]
 96%|█████████▌| 55009/57600 [9:41:11<26:59,  1.60it/s]
 96%|█████████▌| 55010/57600 [9:41:12<26:29,  1.63it/s]
 96%|█████████▌| 55011/57600 [9:41:12<26:21,  1.64it/s]
 96%|█████████▌| 55012/57600 [9:41:13<26:34,  1.62it/s]
 96%|█████████▌| 55013/57600 [9:41:14<27:31,  1.57it/s]
 96%|█████████▌| 55014/57600 [9:41:14<27:25,  1.57it/s]
 96%|█████████▌| 55015/57600 [9:41:15<27:22,  1.57it/s]
 96%|█████████▌| 55016/57600 [9:41:15<26:20,  1.63it/s]
 96%|█████████▌| 55017/57600 [9:41:16<26:37,  1.62it/s]
 96%|█████████▌| 55018/57600 [9:41:17<27:03,  1.59it/s]
 96%|█████████▌| 55019/57600 [9:41:17<26:56,  1.60it/s]
 96%|█████████▌| 55020/57600 [9:41:18<26:35,  1.62it/s]
                                                       
{'loss': 1.0672, 'learning_rate': 1.4045296167247387e-07, 'epoch': 607.28}

 96%|█████████▌| 55020/57600 [9:41:18<26:35,  1.62it/s]
 96%|█████████▌| 55021/57600 [9:41:18<26:14,  1.64it/s]
 96%|█████████▌| 55022/57600 [9:41:19<26:03,  1.65it/s]
 96%|█████████▌| 55023/57600 [9:41:20<25:26,  1.69it/s]
 96%|█████████▌| 55024/57600 [9:41:20<26:47,  1.60it/s]
 96%|█████████▌| 55025/57600 [9:41:21<26:05,  1.65it/s]
 96%|█████████▌| 55026/57600 [9:41:22<26:55,  1.59it/s]
 96%|█████████▌| 55027/57600 [9:41:22<27:01,  1.59it/s]
 96%|█████████▌| 55028/57600 [9:41:23<26:48,  1.60it/s]
 96%|█████████▌| 55029/57600 [9:41:23<26:10,  1.64it/s]
 96%|█████████▌| 55030/57600 [9:41:24<26:11,  1.64it/s]
 96%|█████████▌| 55031/57600 [9:41:25<25:57,  1.65it/s]
 96%|█████████▌| 55032/57600 [9:41:25<26:20,  1.62it/s]
 96%|█████████▌| 55033/57600 [9:41:26<26:08,  1.64it/s]
 96%|█████████▌| 55034/57600 [9:41:26<26:14,  1.63it/s]
 96%|█████████▌| 55035/57600 [9:41:27<26:45,  1.60it/s]
 96%|█████████▌| 55036/57600 [9:41:28<26:44,  1.60it/s]
 96%|█████████▌| 55037/57600 [9:41:28<26:01,  1.64it/s]
 96%|█████████▌| 55038/57600 [9:41:29<25:53,  1.65it/s]
 96%|█████████▌| 55039/57600 [9:41:30<27:22,  1.56it/s]
 96%|█████████▌| 55040/57600 [9:41:30<27:54,  1.53it/s]
                                                       
{'loss': 1.1384, 'learning_rate': 1.401393728222997e-07, 'epoch': 607.51}

 96%|█████████▌| 55040/57600 [9:41:30<27:54,  1.53it/s]
 96%|█████████▌| 55041/57600 [9:41:31<27:42,  1.54it/s]
 96%|█████████▌| 55042/57600 [9:41:32<26:48,  1.59it/s]
 96%|█████████▌| 55043/57600 [9:41:32<25:58,  1.64it/s]
 96%|█████████▌| 55044/57600 [9:41:33<26:11,  1.63it/s]
 96%|█████████▌| 55045/57600 [9:41:33<25:58,  1.64it/s]
 96%|█████████▌| 55046/57600 [9:41:34<25:55,  1.64it/s]
 96%|█████████▌| 55047/57600 [9:41:35<25:33,  1.67it/s]
 96%|█████████▌| 55048/57600 [9:41:35<26:20,  1.61it/s]
 96%|█████████▌| 55049/57600 [9:41:36<26:29,  1.60it/s]
 96%|█████████▌| 55050/57600 [9:41:36<25:34,  1.66it/s]
 96%|█████████▌| 55051/57600 [9:41:37<25:40,  1.65it/s]
 96%|█████████▌| 55052/57600 [9:41:38<25:42,  1.65it/s]
 96%|█████████▌| 55053/57600 [9:41:38<25:52,  1.64it/s]
 96%|█████████▌| 55054/57600 [9:41:39<25:23,  1.67it/s]
 96%|█████████▌| 55055/57600 [9:41:39<25:59,  1.63it/s]
 96%|█████████▌| 55056/57600 [9:41:40<25:14,  1.68it/s]
 96%|█████████▌| 55057/57600 [9:41:41<25:13,  1.68it/s]
 96%|█████████▌| 55058/57600 [9:41:41<25:24,  1.67it/s]
 96%|█████████▌| 55059/57600 [9:41:42<24:48,  1.71it/s]
 96%|█████████▌| 55060/57600 [9:41:42<25:48,  1.64it/s]
                                                       
{'loss': 1.1327, 'learning_rate': 1.398257839721254e-07, 'epoch': 607.73}

 96%|█████████▌| 55060/57600 [9:41:42<25:48,  1.64it/s]
 96%|█████████▌| 55061/57600 [9:41:43<25:36,  1.65it/s]
 96%|█████████▌| 55062/57600 [9:41:44<25:48,  1.64it/s]
 96%|█████████▌| 55063/57600 [9:41:44<25:43,  1.64it/s]
 96%|█████████▌| 55064/57600 [9:41:45<25:12,  1.68it/s]
 96%|█████████▌| 55065/57600 [9:41:45<26:08,  1.62it/s]
 96%|█████████▌| 55066/57600 [9:41:46<27:01,  1.56it/s]
 96%|█████████▌| 55067/57600 [9:41:47<26:56,  1.57it/s]
 96%|█████████▌| 55068/57600 [9:41:47<27:47,  1.52it/s]
 96%|█████████▌| 55069/57600 [9:41:48<27:32,  1.53it/s]
 96%|█████████▌| 55070/57600 [9:41:49<26:52,  1.57it/s]
 96%|█████████▌| 55071/57600 [9:41:49<26:07,  1.61it/s]
 96%|█████████▌| 55072/57600 [9:41:50<26:12,  1.61it/s]
 96%|█████████▌| 55073/57600 [9:41:51<26:22,  1.60it/s]
 96%|█████████▌| 55074/57600 [9:41:51<26:07,  1.61it/s]
 96%|█████████▌| 55075/57600 [9:41:52<25:50,  1.63it/s]
 96%|█████████▌| 55076/57600 [9:41:52<26:41,  1.58it/s]
 96%|█████████▌| 55077/57600 [9:41:53<25:52,  1.63it/s]
 96%|█████████▌| 55078/57600 [9:41:54<25:06,  1.67it/s]
 96%|█████████▌| 55079/57600 [9:41:54<24:53,  1.69it/s]
 96%|█████████▌| 55080/57600 [9:41:55<25:26,  1.65it/s]
                                                       
{'loss': 1.081, 'learning_rate': 1.3951219512195126e-07, 'epoch': 607.95}

 96%|█████████▌| 55080/57600 [9:41:55<25:26,  1.65it/s]
 96%|█████████▌| 55081/57600 [9:41:55<25:12,  1.67it/s]
 96%|█████████▌| 55082/57600 [9:41:56<25:51,  1.62it/s]
 96%|█████████▌| 55083/57600 [9:41:57<26:01,  1.61it/s]
 96%|█████████▌| 55084/57600 [9:41:57<26:10,  1.60it/s]
 96%|█████████▌| 55085/57600 [9:41:58<27:36,  1.52it/s]
 96%|█████████▌| 55086/57600 [9:41:59<28:13,  1.48it/s]
 96%|█████████▌| 55087/57600 [9:41:59<27:24,  1.53it/s]
 96%|█████████▌| 55088/57600 [9:42:00<27:31,  1.52it/s]
 96%|█████████▌| 55089/57600 [9:42:01<26:13,  1.60it/s]
 96%|█████████▌| 55090/57600 [9:42:01<26:17,  1.59it/s]
 96%|█████████▌| 55091/57600 [9:42:02<25:39,  1.63it/s]
 96%|█████████▌| 55092/57600 [9:42:02<25:12,  1.66it/s]
 96%|█████████▌| 55093/57600 [9:42:03<25:40,  1.63it/s]
 96%|█████████▌| 55094/57600 [9:42:04<25:34,  1.63it/s]
 96%|█████████▌| 55095/57600 [9:42:04<25:28,  1.64it/s]
 96%|█████████▌| 55096/57600 [9:42:05<25:11,  1.66it/s]
 96%|█████████▌| 55097/57600 [9:42:05<24:39,  1.69it/s]
 96%|█████████▌| 55098/57600 [9:42:06<24:41,  1.69it/s]
 96%|█████████▌| 55099/57600 [9:42:07<25:17,  1.65it/s]
 96%|█████████▌| 55100/57600 [9:42:07<25:51,  1.61it/s]
                                                       
{'loss': 1.121, 'learning_rate': 1.3919860627177698e-07, 'epoch': 608.17}

 96%|█████████▌| 55100/57600 [9:42:07<25:51,  1.61it/s]
 96%|█████████▌| 55101/57600 [9:42:08<25:56,  1.61it/s]
 96%|█████████▌| 55102/57600 [9:42:09<26:07,  1.59it/s]
 96%|█████████▌| 55103/57600 [9:42:09<26:42,  1.56it/s]
 96%|█████████▌| 55104/57600 [9:42:10<26:37,  1.56it/s]
 96%|█████████▌| 55105/57600 [9:42:10<25:58,  1.60it/s]
 96%|█████████▌| 55106/57600 [9:42:11<25:37,  1.62it/s]
 96%|█████████▌| 55107/57600 [9:42:12<26:33,  1.56it/s]
 96%|█████████▌| 55108/57600 [9:42:12<26:05,  1.59it/s]
 96%|█████████▌| 55109/57600 [9:42:13<26:54,  1.54it/s]
 96%|█████████▌| 55110/57600 [9:42:14<26:02,  1.59it/s]
 96%|█████████▌| 55111/57600 [9:42:14<26:28,  1.57it/s]
 96%|█████████▌| 55112/57600 [9:42:15<26:34,  1.56it/s]
 96%|█████████▌| 55113/57600 [9:42:16<26:40,  1.55it/s]
 96%|█████████▌| 55114/57600 [9:42:16<26:27,  1.57it/s]
 96%|█████████▌| 55115/57600 [9:42:17<27:04,  1.53it/s]
 96%|█████████▌| 55116/57600 [9:42:18<28:06,  1.47it/s]
 96%|█████████▌| 55117/57600 [9:42:18<27:09,  1.52it/s]
 96%|█████████▌| 55118/57600 [9:42:19<27:08,  1.52it/s]
 96%|█████████▌| 55119/57600 [9:42:19<26:53,  1.54it/s]
 96%|█████████▌| 55120/57600 [9:42:20<26:50,  1.54it/s]
                                                       
{'loss': 1.0568, 'learning_rate': 1.3888501742160279e-07, 'epoch': 608.39}

 96%|█████████▌| 55120/57600 [9:42:20<26:50,  1.54it/s]
 96%|█████████▌| 55121/57600 [9:42:21<27:48,  1.49it/s]
 96%|█████████▌| 55122/57600 [9:42:22<27:44,  1.49it/s]
 96%|█████████▌| 55123/57600 [9:42:22<26:48,  1.54it/s]
 96%|█████████▌| 55124/57600 [9:42:23<25:52,  1.60it/s]
 96%|█████████▌| 55125/57600 [9:42:23<26:42,  1.54it/s]
 96%|█████████▌| 55126/57600 [9:42:24<26:02,  1.58it/s]
 96%|█████████▌| 55127/57600 [9:42:25<26:13,  1.57it/s]
 96%|█████████▌| 55128/57600 [9:42:25<25:50,  1.59it/s]
 96%|█████████▌| 55129/57600 [9:42:26<26:33,  1.55it/s]
 96%|█████████▌| 55130/57600 [9:42:27<26:03,  1.58it/s]
 96%|█████████▌| 55131/57600 [9:42:27<25:39,  1.60it/s]
 96%|█████████▌| 55132/57600 [9:42:28<26:14,  1.57it/s]
 96%|█████████▌| 55133/57600 [9:42:28<25:58,  1.58it/s]
 96%|█████████▌| 55134/57600 [9:42:29<25:20,  1.62it/s]
 96%|█████████▌| 55135/57600 [9:42:30<25:39,  1.60it/s]
 96%|█████████▌| 55136/57600 [9:42:30<25:14,  1.63it/s]
 96%|█████████▌| 55137/57600 [9:42:31<25:20,  1.62it/s]
 96%|█████████▌| 55138/57600 [9:42:32<27:03,  1.52it/s]
 96%|█████████▌| 55139/57600 [9:42:32<26:35,  1.54it/s]
 96%|█████████▌| 55140/57600 [9:42:33<26:16,  1.56it/s]
                                                       
{'loss': 1.1017, 'learning_rate': 1.3857142857142854e-07, 'epoch': 608.61}

 96%|█████████▌| 55140/57600 [9:42:33<26:16,  1.56it/s]
 96%|█████████▌| 55141/57600 [9:42:34<26:45,  1.53it/s]
 96%|█████████▌| 55142/57600 [9:42:34<26:19,  1.56it/s]
 96%|█████████▌| 55143/57600 [9:42:35<26:09,  1.57it/s]
 96%|█████████▌| 55144/57600 [9:42:35<26:28,  1.55it/s]
 96%|█████████▌| 55145/57600 [9:42:36<26:11,  1.56it/s]
 96%|█████████▌| 55146/57600 [9:42:37<26:16,  1.56it/s]
 96%|█████████▌| 55147/57600 [9:42:37<26:15,  1.56it/s]
 96%|█████████▌| 55148/57600 [9:42:38<25:43,  1.59it/s]
 96%|█████████▌| 55149/57600 [9:42:39<25:25,  1.61it/s]
 96%|█████████▌| 55150/57600 [9:42:39<25:33,  1.60it/s]
 96%|█████████▌| 55151/57600 [9:42:40<25:34,  1.60it/s]
 96%|█████████▌| 55152/57600 [9:42:41<25:57,  1.57it/s]
 96%|█████████▌| 55153/57600 [9:42:41<25:56,  1.57it/s]
 96%|█████████▌| 55154/57600 [9:42:42<25:55,  1.57it/s]
 96%|█████████▌| 55155/57600 [9:42:42<26:12,  1.56it/s]
 96%|█████████▌| 55156/57600 [9:42:43<25:17,  1.61it/s]
 96%|█████████▌| 55157/57600 [9:42:44<25:17,  1.61it/s]
 96%|█████████▌| 55158/57600 [9:42:44<25:11,  1.62it/s]
 96%|█████████▌| 55159/57600 [9:42:45<25:20,  1.60it/s]
 96%|█████████▌| 55160/57600 [9:42:46<25:29,  1.60it/s]
                                                       
{'loss': 1.1331, 'learning_rate': 1.3825783972125434e-07, 'epoch': 608.83}

 96%|█████████▌| 55160/57600 [9:42:46<25:29,  1.60it/s]
 96%|█████████▌| 55161/57600 [9:42:46<26:34,  1.53it/s]
 96%|█████████▌| 55162/57600 [9:42:47<26:41,  1.52it/s]
 96%|█████████▌| 55163/57600 [9:42:48<26:57,  1.51it/s]
 96%|█████████▌| 55164/57600 [9:42:48<26:13,  1.55it/s]
 96%|█████████▌| 55165/57600 [9:42:49<25:58,  1.56it/s]
 96%|█████████▌| 55166/57600 [9:42:49<26:25,  1.54it/s]
 96%|█████████▌| 55167/57600 [9:42:50<26:11,  1.55it/s]
 96%|█████████▌| 55168/57600 [9:42:51<25:27,  1.59it/s]
 96%|█████████▌| 55169/57600 [9:42:51<24:38,  1.64it/s]
 96%|█████████▌| 55170/57600 [9:42:52<24:31,  1.65it/s]
 96%|█████████▌| 55171/57600 [9:42:52<24:43,  1.64it/s]
 96%|█████████▌| 55172/57600 [9:42:53<25:26,  1.59it/s]
 96%|█████████▌| 55173/57600 [9:42:54<24:52,  1.63it/s]
 96%|█████████▌| 55174/57600 [9:42:54<25:09,  1.61it/s]
 96%|█████████▌| 55175/57600 [9:42:55<25:06,  1.61it/s]
 96%|█████████▌| 55176/57600 [9:42:56<25:42,  1.57it/s]
 96%|█████████▌| 55177/57600 [9:42:56<26:01,  1.55it/s]
 96%|█████████▌| 55178/57600 [9:42:57<25:21,  1.59it/s]
 96%|█████████▌| 55179/57600 [9:42:57<24:37,  1.64it/s]
 96%|█████████▌| 55180/57600 [9:42:58<24:15,  1.66it/s]
                                                       
{'loss': 1.1321, 'learning_rate': 1.3794425087108017e-07, 'epoch': 609.05}

 96%|█████████▌| 55180/57600 [9:42:58<24:15,  1.66it/s]
 96%|█████████▌| 55181/57600 [9:42:59<25:05,  1.61it/s]
 96%|█████████▌| 55182/57600 [9:42:59<25:34,  1.58it/s]
 96%|█████████▌| 55183/57600 [9:43:00<25:22,  1.59it/s]
 96%|█████████▌| 55184/57600 [9:43:01<25:36,  1.57it/s]
 96%|█████████▌| 55185/57600 [9:43:01<25:05,  1.60it/s]
 96%|█████████▌| 55186/57600 [9:43:02<24:23,  1.65it/s]
 96%|█████████▌| 55187/57600 [9:43:02<24:43,  1.63it/s]
 96%|█████████▌| 55188/57600 [9:43:03<24:58,  1.61it/s]
 96%|█████████▌| 55189/57600 [9:43:04<25:32,  1.57it/s]
 96%|█████████▌| 55190/57600 [9:43:04<25:30,  1.57it/s]
 96%|█████████▌| 55191/57600 [9:43:05<25:24,  1.58it/s]
 96%|█████████▌| 55192/57600 [9:43:06<25:06,  1.60it/s]
 96%|█████████▌| 55193/57600 [9:43:06<25:38,  1.56it/s]
 96%|█████████▌| 55194/57600 [9:43:07<25:03,  1.60it/s]
 96%|█████████▌| 55195/57600 [9:43:08<25:31,  1.57it/s]
 96%|█████████▌| 55196/57600 [9:43:08<26:04,  1.54it/s]
 96%|█████████▌| 55197/57600 [9:43:09<25:40,  1.56it/s]
 96%|█████████▌| 55198/57600 [9:43:10<25:33,  1.57it/s]
 96%|█████████▌| 55199/57600 [9:43:10<24:39,  1.62it/s]
 96%|█████████▌| 55200/57600 [9:43:11<24:58,  1.60it/s]
                                                       
{'loss': 1.1024, 'learning_rate': 1.376306620209059e-07, 'epoch': 609.27}

 96%|█████████▌| 55200/57600 [9:43:11<24:58,  1.60it/s]
 96%|█████████▌| 55201/57600 [9:43:11<24:13,  1.65it/s]
 96%|█████████▌| 55202/57600 [9:43:12<24:54,  1.60it/s]
 96%|█████████▌| 55203/57600 [9:43:13<25:04,  1.59it/s]
 96%|█████████▌| 55204/57600 [9:43:13<25:19,  1.58it/s]
 96%|█████████▌| 55205/57600 [9:43:14<25:00,  1.60it/s]
 96%|█████████▌| 55206/57600 [9:43:14<24:43,  1.61it/s]
 96%|█████████▌| 55207/57600 [9:43:15<25:13,  1.58it/s]
 96%|█████████▌| 55208/57600 [9:43:16<25:29,  1.56it/s]
 96%|█████████▌| 55209/57600 [9:43:16<25:34,  1.56it/s]
 96%|█████████▌| 55210/57600 [9:43:17<24:43,  1.61it/s]
 96%|█████████▌| 55211/57600 [9:43:18<24:24,  1.63it/s]
 96%|█████████▌| 55212/57600 [9:43:18<24:16,  1.64it/s]
 96%|█████████▌| 55213/57600 [9:43:19<24:01,  1.66it/s]
 96%|█████████▌| 55214/57600 [9:43:19<24:22,  1.63it/s]
 96%|█████████▌| 55215/57600 [9:43:20<24:28,  1.62it/s]
 96%|█████████▌| 55216/57600 [9:43:21<24:28,  1.62it/s]
 96%|█████████▌| 55217/57600 [9:43:21<24:05,  1.65it/s]
 96%|█████████▌| 55218/57600 [9:43:22<24:07,  1.65it/s]
 96%|█████████▌| 55219/57600 [9:43:22<24:07,  1.65it/s]
 96%|█████████▌| 55220/57600 [9:43:23<23:40,  1.67it/s]
                                                       
{'loss': 1.0933, 'learning_rate': 1.3731707317073173e-07, 'epoch': 609.49}

 96%|█████████▌| 55220/57600 [9:43:23<23:40,  1.67it/s]
 96%|█████████▌| 55221/57600 [9:43:24<23:39,  1.68it/s]
 96%|█████████▌| 55222/57600 [9:43:24<23:33,  1.68it/s]
 96%|█████████▌| 55223/57600 [9:43:25<23:57,  1.65it/s]
 96%|█████████▌| 55224/57600 [9:43:25<24:04,  1.64it/s]
 96%|█████████▌| 55225/57600 [9:43:26<24:02,  1.65it/s]
 96%|█████████▌| 55226/57600 [9:43:27<23:44,  1.67it/s]
 96%|█████████▌| 55227/57600 [9:43:27<23:53,  1.66it/s]
 96%|█████████▌| 55228/57600 [9:43:28<23:31,  1.68it/s]
 96%|█████████▌| 55229/57600 [9:43:29<24:51,  1.59it/s]
 96%|█████████▌| 55230/57600 [9:43:29<24:08,  1.64it/s]
 96%|█████████▌| 55231/57600 [9:43:30<23:49,  1.66it/s]
 96%|█████████▌| 55232/57600 [9:43:30<24:50,  1.59it/s]
 96%|█████████▌| 55233/57600 [9:43:31<25:47,  1.53it/s]
 96%|█████████▌| 55234/57600 [9:43:32<26:08,  1.51it/s]
 96%|█████████▌| 55235/57600 [9:43:32<26:14,  1.50it/s]
 96%|█████████▌| 55236/57600 [9:43:33<25:50,  1.52it/s]
 96%|█████████▌| 55237/57600 [9:43:34<24:56,  1.58it/s]
 96%|█████████▌| 55238/57600 [9:43:34<23:55,  1.65it/s]
 96%|█████████▌| 55239/57600 [9:43:35<24:19,  1.62it/s]
 96%|█████████▌| 55240/57600 [9:43:35<23:33,  1.67it/s]
                                                       
{'loss': 1.1043, 'learning_rate': 1.3700348432055746e-07, 'epoch': 609.71}

 96%|█████████▌| 55240/57600 [9:43:35<23:33,  1.67it/s]
 96%|█████████▌| 55241/57600 [9:43:36<23:58,  1.64it/s]
 96%|█████████▌| 55242/57600 [9:43:37<23:46,  1.65it/s]
 96%|█████████▌| 55243/57600 [9:43:37<23:47,  1.65it/s]
 96%|█████████▌| 55244/57600 [9:43:38<24:44,  1.59it/s]
 96%|█████████▌| 55245/57600 [9:43:39<24:22,  1.61it/s]
 96%|█████████▌| 55246/57600 [9:43:39<24:37,  1.59it/s]
 96%|█████████▌| 55247/57600 [9:43:40<24:31,  1.60it/s]
 96%|█████████▌| 55248/57600 [9:43:40<24:07,  1.62it/s]
 96%|█████████▌| 55249/57600 [9:43:41<24:05,  1.63it/s]
 96%|█████████▌| 55250/57600 [9:43:42<23:32,  1.66it/s]
 96%|█████████▌| 55251/57600 [9:43:42<23:18,  1.68it/s]
 96%|█████████▌| 55252/57600 [9:43:43<22:55,  1.71it/s]
 96%|█████████▌| 55253/57600 [9:43:43<23:36,  1.66it/s]
 96%|█████████▌| 55254/57600 [9:43:44<23:52,  1.64it/s]
 96%|█████████▌| 55255/57600 [9:43:45<24:34,  1.59it/s]
 96%|█████████▌| 55256/57600 [9:43:45<25:24,  1.54it/s]
 96%|█████████▌| 55257/57600 [9:43:46<25:32,  1.53it/s]
 96%|█████████▌| 55258/57600 [9:43:47<25:07,  1.55it/s]
 96%|█████████▌| 55259/57600 [9:43:47<25:03,  1.56it/s]
 96%|█████████▌| 55260/57600 [9:43:48<24:28,  1.59it/s]
                                                       
{'loss': 1.0982, 'learning_rate': 1.366898954703833e-07, 'epoch': 609.93}

 96%|█████████▌| 55260/57600 [9:43:48<24:28,  1.59it/s]
 96%|█████████▌| 55261/57600 [9:43:48<24:00,  1.62it/s]
 96%|█████████▌| 55262/57600 [9:43:49<24:34,  1.59it/s]
 96%|█████████▌| 55263/57600 [9:43:50<23:58,  1.63it/s]
 96%|█████████▌| 55264/57600 [9:43:50<22:58,  1.69it/s]
 96%|█████████▌| 55265/57600 [9:43:51<23:03,  1.69it/s]
 96%|█████████▌| 55266/57600 [9:43:51<23:11,  1.68it/s]
 96%|█████████▌| 55267/57600 [9:43:52<23:52,  1.63it/s]
 96%|█████████▌| 55268/57600 [9:43:53<24:51,  1.56it/s]
 96%|█████████▌| 55269/57600 [9:43:53<24:23,  1.59it/s]
 96%|█████████▌| 55270/57600 [9:43:54<24:00,  1.62it/s]
 96%|█████████▌| 55271/57600 [9:43:55<23:36,  1.64it/s]
 96%|█████████▌| 55272/57600 [9:43:55<24:41,  1.57it/s]
 96%|█████████▌| 55273/57600 [9:43:56<24:14,  1.60it/s]
 96%|█████████▌| 55274/57600 [9:43:56<23:53,  1.62it/s]
 96%|█████████▌| 55275/57600 [9:43:57<23:40,  1.64it/s]
 96%|█████████▌| 55276/57600 [9:43:58<23:51,  1.62it/s]
 96%|█████████▌| 55277/57600 [9:43:58<23:14,  1.67it/s]
 96%|█████████▌| 55278/57600 [9:43:59<22:50,  1.69it/s]
 96%|█████████▌| 55279/57600 [9:44:00<24:34,  1.57it/s]
 96%|█████████▌| 55280/57600 [9:44:00<24:05,  1.61it/s]
                                                       
{'loss': 1.1275, 'learning_rate': 1.36376306620209e-07, 'epoch': 610.15}

 96%|█████████▌| 55280/57600 [9:44:00<24:05,  1.61it/s]
 96%|█████████▌| 55281/57600 [9:44:01<23:24,  1.65it/s]
 96%|█████████▌| 55282/57600 [9:44:01<23:40,  1.63it/s]
 96%|█████████▌| 55283/57600 [9:44:02<23:37,  1.63it/s]
 96%|█████████▌| 55284/57600 [9:44:03<24:20,  1.59it/s]
 96%|█████████▌| 55285/57600 [9:44:03<24:21,  1.58it/s]
 96%|█████████▌| 55286/57600 [9:44:04<24:23,  1.58it/s]
 96%|█████████▌| 55287/57600 [9:44:04<23:19,  1.65it/s]
 96%|█████████▌| 55288/57600 [9:44:05<23:30,  1.64it/s]
 96%|█████████▌| 55289/57600 [9:44:06<24:11,  1.59it/s]
 96%|█████████▌| 55290/57600 [9:44:06<24:31,  1.57it/s]
 96%|█████████▌| 55291/57600 [9:44:07<24:32,  1.57it/s]
 96%|█████████▌| 55292/57600 [9:44:08<23:48,  1.62it/s]
 96%|█████████▌| 55293/57600 [9:44:08<24:24,  1.58it/s]
 96%|█████████▌| 55294/57600 [9:44:09<23:55,  1.61it/s]
 96%|█████████▌| 55295/57600 [9:44:10<24:20,  1.58it/s]
 96%|█████████▌| 55296/57600 [9:44:10<24:56,  1.54it/s]
 96%|█████████▌| 55297/57600 [9:44:11<23:57,  1.60it/s]
 96%|█████████▌| 55298/57600 [9:44:11<23:04,  1.66it/s]
 96%|█████████▌| 55299/57600 [9:44:12<23:42,  1.62it/s]
 96%|█████████▌| 55300/57600 [9:44:13<23:24,  1.64it/s]
                                                       
{'loss': 1.1074, 'learning_rate': 1.3606271777003484e-07, 'epoch': 610.38}

 96%|█████████▌| 55300/57600 [9:44:13<23:24,  1.64it/s]
 96%|█████████▌| 55301/57600 [9:44:13<22:44,  1.69it/s]
 96%|█████████▌| 55302/57600 [9:44:14<23:08,  1.65it/s]
 96%|█████████▌| 55303/57600 [9:44:14<23:44,  1.61it/s]
 96%|█████████▌| 55304/57600 [9:44:15<23:46,  1.61it/s]
 96%|█████████▌| 55305/57600 [9:44:16<24:53,  1.54it/s]
 96%|█████████▌| 55306/57600 [9:44:16<24:16,  1.58it/s]
 96%|█████████▌| 55307/57600 [9:44:17<25:03,  1.52it/s]
 96%|█████████▌| 55308/57600 [9:44:18<24:49,  1.54it/s]
 96%|█████████▌| 55309/57600 [9:44:18<24:28,  1.56it/s]
 96%|█████████▌| 55310/57600 [9:44:19<24:33,  1.55it/s]
 96%|█████████▌| 55311/57600 [9:44:20<24:20,  1.57it/s]
 96%|█████████▌| 55312/57600 [9:44:20<24:08,  1.58it/s]
 96%|█████████▌| 55313/57600 [9:44:21<23:34,  1.62it/s]
 96%|█████████▌| 55314/57600 [9:44:22<24:43,  1.54it/s]
 96%|█████████▌| 55315/57600 [9:44:22<24:12,  1.57it/s]
 96%|█████████▌| 55316/57600 [9:44:23<23:52,  1.59it/s]
 96%|█████████▌| 55317/57600 [9:44:23<23:19,  1.63it/s]
 96%|█████████▌| 55318/57600 [9:44:24<23:43,  1.60it/s]
 96%|█████████▌| 55319/57600 [9:44:25<23:44,  1.60it/s]
 96%|█████████▌| 55320/57600 [9:44:25<23:12,  1.64it/s]
                                                       
{'loss': 1.0888, 'learning_rate': 1.3574912891986068e-07, 'epoch': 610.6}

 96%|█████████▌| 55320/57600 [9:44:25<23:12,  1.64it/s]
 96%|█████████▌| 55321/57600 [9:44:26<22:54,  1.66it/s]
 96%|█████████▌| 55322/57600 [9:44:26<22:59,  1.65it/s]
 96%|█████████▌| 55323/57600 [9:44:27<23:21,  1.62it/s]
 96%|█████████▌| 55324/57600 [9:44:28<23:03,  1.65it/s]
 96%|█████████▌| 55325/57600 [9:44:28<23:30,  1.61it/s]
 96%|█████████▌| 55326/57600 [9:44:29<23:56,  1.58it/s]
 96%|█████████▌| 55327/57600 [9:44:29<23:19,  1.62it/s]
 96%|█████████▌| 55328/57600 [9:44:30<22:44,  1.67it/s]
 96%|█████████▌| 55329/57600 [9:44:31<21:59,  1.72it/s]
 96%|█████████▌| 55330/57600 [9:44:31<22:29,  1.68it/s]
 96%|█████████▌| 55331/57600 [9:44:32<23:11,  1.63it/s]
 96%|█████████▌| 55332/57600 [9:44:32<23:07,  1.63it/s]
 96%|█████████▌| 55333/57600 [9:44:33<23:14,  1.63it/s]
 96%|█████████▌| 55334/57600 [9:44:34<23:42,  1.59it/s]
 96%|█████████▌| 55335/57600 [9:44:34<24:09,  1.56it/s]
 96%|█████████▌| 55336/57600 [9:44:35<23:34,  1.60it/s]
 96%|█████████▌| 55337/57600 [9:44:36<23:24,  1.61it/s]
 96%|█████████▌| 55338/57600 [9:44:36<23:43,  1.59it/s]
 96%|█████████▌| 55339/57600 [9:44:37<23:16,  1.62it/s]
 96%|█████████▌| 55340/57600 [9:44:38<24:03,  1.57it/s]
                                                       
{'loss': 1.101, 'learning_rate': 1.354355400696864e-07, 'epoch': 610.82}

 96%|█████████▌| 55340/57600 [9:44:38<24:03,  1.57it/s]
 96%|█████████▌| 55341/57600 [9:44:38<23:51,  1.58it/s]
 96%|█████████▌| 55342/57600 [9:44:39<23:59,  1.57it/s]
 96%|█████████▌| 55343/57600 [9:44:39<23:36,  1.59it/s]
 96%|█████████▌| 55344/57600 [9:44:40<23:18,  1.61it/s]
 96%|█████████▌| 55345/57600 [9:44:41<23:55,  1.57it/s]
 96%|█████████▌| 55346/57600 [9:44:41<24:03,  1.56it/s]
 96%|█████████▌| 55347/57600 [9:44:42<23:45,  1.58it/s]
 96%|█████████▌| 55348/57600 [9:44:43<23:19,  1.61it/s]
 96%|█████████▌| 55349/57600 [9:44:43<23:26,  1.60it/s]
 96%|█████████▌| 55350/57600 [9:44:44<23:00,  1.63it/s]
 96%|█████████▌| 55351/57600 [9:44:44<23:16,  1.61it/s]
 96%|█████████▌| 55352/57600 [9:44:45<23:54,  1.57it/s]
 96%|█████████▌| 55353/57600 [9:44:46<24:31,  1.53it/s]
 96%|█████████▌| 55354/57600 [9:44:47<25:02,  1.49it/s]
 96%|█████████▌| 55355/57600 [9:44:47<24:28,  1.53it/s]
 96%|█████████▌| 55356/57600 [9:44:48<23:17,  1.61it/s]
 96%|█████████▌| 55357/57600 [9:44:48<23:44,  1.57it/s]
 96%|█████████▌| 55358/57600 [9:44:49<24:09,  1.55it/s]
 96%|█████████▌| 55359/57600 [9:44:50<23:20,  1.60it/s]
 96%|█████████▌| 55360/57600 [9:44:50<23:02,  1.62it/s]
                                                       
{'loss': 1.1021, 'learning_rate': 1.3512195121951223e-07, 'epoch': 611.04}

 96%|█████████▌| 55360/57600 [9:44:50<23:02,  1.62it/s]
 96%|█████████▌| 55361/57600 [9:44:51<22:59,  1.62it/s]
 96%|█████████▌| 55362/57600 [9:44:51<22:30,  1.66it/s]
 96%|█████████▌| 55363/57600 [9:44:52<22:34,  1.65it/s]
 96%|█████████▌| 55364/57600 [9:44:53<22:30,  1.66it/s]
 96%|█████████▌| 55365/57600 [9:44:53<21:55,  1.70it/s]
 96%|█████████▌| 55366/57600 [9:44:54<22:44,  1.64it/s]
 96%|█████████▌| 55367/57600 [9:44:55<23:56,  1.55it/s]
 96%|█████████▌| 55368/57600 [9:44:55<23:56,  1.55it/s]
 96%|█████████▌| 55369/57600 [9:44:56<24:02,  1.55it/s]
 96%|█████████▌| 55370/57600 [9:44:56<23:26,  1.59it/s]
 96%|█████████▌| 55371/57600 [9:44:57<23:35,  1.57it/s]
 96%|█████████▌| 55372/57600 [9:44:58<23:27,  1.58it/s]
 96%|█████████▌| 55373/57600 [9:44:58<23:15,  1.60it/s]
 96%|█████████▌| 55374/57600 [9:44:59<23:36,  1.57it/s]
 96%|█████████▌| 55375/57600 [9:45:00<24:18,  1.53it/s]
 96%|█████████▌| 55376/57600 [9:45:00<23:42,  1.56it/s]
 96%|█████████▌| 55377/57600 [9:45:01<24:07,  1.54it/s]
 96%|█████████▌| 55378/57600 [9:45:01<23:12,  1.60it/s]
 96%|█████████▌| 55379/57600 [9:45:02<22:56,  1.61it/s]
 96%|█████████▌| 55380/57600 [9:45:03<22:35,  1.64it/s]
                                                       
{'loss': 1.1006, 'learning_rate': 1.3480836236933793e-07, 'epoch': 611.26}

 96%|█████████▌| 55380/57600 [9:45:03<22:35,  1.64it/s]
 96%|█████████▌| 55381/57600 [9:45:03<22:53,  1.62it/s]
 96%|█████████▌| 55382/57600 [9:45:04<22:54,  1.61it/s]
 96%|█████████▌| 55383/57600 [9:45:05<22:45,  1.62it/s]
 96%|█████████▌| 55384/57600 [9:45:05<23:26,  1.58it/s]
 96%|█████████▌| 55385/57600 [9:45:06<24:08,  1.53it/s]
 96%|█████████▌| 55386/57600 [9:45:07<24:03,  1.53it/s]
 96%|█████████▌| 55387/57600 [9:45:07<23:29,  1.57it/s]
 96%|█████████▌| 55388/57600 [9:45:08<23:29,  1.57it/s]
 96%|█████████▌| 55389/57600 [9:45:08<22:54,  1.61it/s]
 96%|█████████▌| 55390/57600 [9:45:09<23:02,  1.60it/s]
 96%|█████████▌| 55391/57600 [9:45:10<22:16,  1.65it/s]
 96%|█████████▌| 55392/57600 [9:45:10<22:16,  1.65it/s]
 96%|█████████▌| 55393/57600 [9:45:11<23:08,  1.59it/s]
 96%|█████████▌| 55394/57600 [9:45:12<23:02,  1.60it/s]
 96%|█████████▌| 55395/57600 [9:45:12<22:19,  1.65it/s]
 96%|█████████▌| 55396/57600 [9:45:13<22:38,  1.62it/s]
 96%|█████████▌| 55397/57600 [9:45:13<22:44,  1.61it/s]
 96%|█████████▌| 55398/57600 [9:45:14<23:12,  1.58it/s]
 96%|█████████▌| 55399/57600 [9:45:15<22:46,  1.61it/s]
 96%|█████████▌| 55400/57600 [9:45:15<22:26,  1.63it/s]
                                                       
{'loss': 1.1054, 'learning_rate': 1.344947735191638e-07, 'epoch': 611.48}

 96%|█████████▌| 55400/57600 [9:45:15<22:26,  1.63it/s]
 96%|█████████▌| 55401/57600 [9:45:16<23:25,  1.56it/s]
 96%|█████████▌| 55402/57600 [9:45:17<23:24,  1.56it/s]
 96%|█████████▌| 55403/57600 [9:45:17<23:37,  1.55it/s]
 96%|█████████▌| 55404/57600 [9:45:18<23:30,  1.56it/s]
 96%|█████████▌| 55405/57600 [9:45:18<23:26,  1.56it/s]
 96%|█████████▌| 55406/57600 [9:45:19<23:43,  1.54it/s]
 96%|█████████▌| 55407/57600 [9:45:20<23:25,  1.56it/s]
 96%|█████████▌| 55408/57600 [9:45:20<24:15,  1.51it/s]
 96%|█████████▌| 55409/57600 [9:45:21<23:43,  1.54it/s]
 96%|█████████▌| 55410/57600 [9:45:22<23:02,  1.58it/s]
 96%|█████████▌| 55411/57600 [9:45:22<23:29,  1.55it/s]
 96%|█████████▌| 55412/57600 [9:45:23<23:19,  1.56it/s]
 96%|█████████▌| 55413/57600 [9:45:24<24:02,  1.52it/s]
 96%|█████████▌| 55414/57600 [9:45:24<22:45,  1.60it/s]
 96%|█████████▌| 55415/57600 [9:45:25<22:10,  1.64it/s]
 96%|█████████▌| 55416/57600 [9:45:25<22:25,  1.62it/s]
 96%|█████████▌| 55417/57600 [9:45:26<22:30,  1.62it/s]
 96%|█████████▌| 55418/57600 [9:45:27<22:19,  1.63it/s]
 96%|█████████▌| 55419/57600 [9:45:27<22:38,  1.61it/s]
 96%|█████████▌| 55420/57600 [9:45:28<22:27,  1.62it/s]
                                                       
{'loss': 1.0861, 'learning_rate': 1.341811846689895e-07, 'epoch': 611.7}

 96%|█████████▌| 55420/57600 [9:45:28<22:27,  1.62it/s]
 96%|█████████▌| 55421/57600 [9:45:29<22:17,  1.63it/s]
 96%|█████████▌| 55422/57600 [9:45:29<22:17,  1.63it/s]
 96%|█████████▌| 55423/57600 [9:45:30<22:39,  1.60it/s]
 96%|█████████▌| 55424/57600 [9:45:30<22:22,  1.62it/s]
 96%|█████████▌| 55425/57600 [9:45:31<21:43,  1.67it/s]
 96%|█████████▌| 55426/57600 [9:45:32<21:30,  1.68it/s]
 96%|█████████▌| 55427/57600 [9:45:32<21:58,  1.65it/s]
 96%|█████████▌| 55428/57600 [9:45:33<21:40,  1.67it/s]
 96%|█████████▌| 55429/57600 [9:45:33<21:36,  1.67it/s]
 96%|█████████▌| 55430/57600 [9:45:34<22:05,  1.64it/s]
 96%|█████████▌| 55431/57600 [9:45:35<22:00,  1.64it/s]
 96%|█████████▌| 55432/57600 [9:45:35<21:49,  1.66it/s]
 96%|█████████▌| 55433/57600 [9:45:36<21:27,  1.68it/s]
 96%|█████████▌| 55434/57600 [9:45:36<22:07,  1.63it/s]
 96%|█████████▌| 55435/57600 [9:45:37<22:35,  1.60it/s]
 96%|█████████▌| 55436/57600 [9:45:38<22:55,  1.57it/s]
 96%|█████████▌| 55437/57600 [9:45:38<22:17,  1.62it/s]
 96%|█████████▌| 55438/57600 [9:45:39<21:56,  1.64it/s]
 96%|█████████▌| 55439/57600 [9:45:39<21:59,  1.64it/s]
 96%|█████████▋| 55440/57600 [9:45:40<22:09,  1.62it/s]
                                                       
{'loss': 1.1017, 'learning_rate': 1.3386759581881532e-07, 'epoch': 611.92}

 96%|█████████▋| 55440/57600 [9:45:40<22:09,  1.62it/s]
 96%|█████████▋| 55441/57600 [9:45:41<21:52,  1.64it/s]
 96%|█████████▋| 55442/57600 [9:45:41<22:25,  1.60it/s]
 96%|█████████▋| 55443/57600 [9:45:42<22:15,  1.61it/s]
 96%|█████████▋| 55444/57600 [9:45:43<22:21,  1.61it/s]
 96%|█████████▋| 55445/57600 [9:45:43<21:58,  1.63it/s]
 96%|█████████▋| 55446/57600 [9:45:44<22:02,  1.63it/s]
 96%|█████████▋| 55447/57600 [9:45:44<21:42,  1.65it/s]
 96%|█████████▋| 55448/57600 [9:45:45<22:29,  1.59it/s]
 96%|█████████▋| 55449/57600 [9:45:46<22:35,  1.59it/s]
 96%|█████████▋| 55450/57600 [9:45:46<22:46,  1.57it/s]
 96%|█████████▋| 55451/57600 [9:45:47<22:03,  1.62it/s]
 96%|█████████▋| 55452/57600 [9:45:48<22:09,  1.62it/s]
 96%|█████████▋| 55453/57600 [9:45:48<21:57,  1.63it/s]
 96%|█████████▋| 55454/57600 [9:45:49<22:23,  1.60it/s]
 96%|█████████▋| 55455/57600 [9:45:50<23:33,  1.52it/s]
 96%|█████████▋| 55456/57600 [9:45:50<23:00,  1.55it/s]
 96%|█████████▋| 55457/57600 [9:45:51<22:32,  1.58it/s]
 96%|█████████▋| 55458/57600 [9:45:51<22:24,  1.59it/s]
 96%|█████████▋| 55459/57600 [9:45:52<22:25,  1.59it/s]
 96%|█████████▋| 55460/57600 [9:45:53<21:50,  1.63it/s]
                                                       
{'loss': 1.1222, 'learning_rate': 1.3355400696864115e-07, 'epoch': 612.14}

 96%|█████████▋| 55460/57600 [9:45:53<21:50,  1.63it/s]
 96%|█████████▋| 55461/57600 [9:45:53<22:02,  1.62it/s]
 96%|█████████▋| 55462/57600 [9:45:54<22:21,  1.59it/s]
 96%|█████████▋| 55463/57600 [9:45:54<21:50,  1.63it/s]
 96%|█████████▋| 55464/57600 [9:45:55<21:52,  1.63it/s]
 96%|█████████▋| 55465/57600 [9:45:56<21:38,  1.64it/s]
 96%|█████████▋| 55466/57600 [9:45:56<21:48,  1.63it/s]
 96%|█████████▋| 55467/57600 [9:45:57<21:43,  1.64it/s]
 96%|█████████▋| 55468/57600 [9:45:57<21:21,  1.66it/s]
 96%|█████████▋| 55469/57600 [9:45:58<21:05,  1.68it/s]
 96%|█████████▋| 55470/57600 [9:45:59<21:22,  1.66it/s]
 96%|█████████▋| 55471/57600 [9:45:59<21:36,  1.64it/s]
 96%|█████████▋| 55472/57600 [9:46:00<21:36,  1.64it/s]
 96%|█████████▋| 55473/57600 [9:46:00<21:05,  1.68it/s]
 96%|█████████▋| 55474/57600 [9:46:01<21:01,  1.69it/s]
 96%|█████████▋| 55475/57600 [9:46:02<21:41,  1.63it/s]
 96%|█████████▋| 55476/57600 [9:46:02<21:37,  1.64it/s]
 96%|█████████▋| 55477/57600 [9:46:03<21:27,  1.65it/s]
 96%|█████████▋| 55478/57600 [9:46:03<21:02,  1.68it/s]
 96%|█████████▋| 55479/57600 [9:46:04<21:27,  1.65it/s]
 96%|█████████▋| 55480/57600 [9:46:05<20:49,  1.70it/s]
                                                       
{'loss': 1.1538, 'learning_rate': 1.3324041811846688e-07, 'epoch': 612.36}

 96%|█████████▋| 55480/57600 [9:46:05<20:49,  1.70it/s]
 96%|█████████▋| 55481/57600 [9:46:05<21:17,  1.66it/s]
 96%|█████████▋| 55482/57600 [9:46:06<20:58,  1.68it/s]
 96%|█████████▋| 55483/57600 [9:46:07<21:31,  1.64it/s]
 96%|█████████▋| 55484/57600 [9:46:07<21:41,  1.63it/s]
 96%|█████████▋| 55485/57600 [9:46:08<21:18,  1.65it/s]
 96%|█████████▋| 55486/57600 [9:46:08<22:37,  1.56it/s]
 96%|█████████▋| 55487/57600 [9:46:09<22:37,  1.56it/s]
 96%|█████████▋| 55488/57600 [9:46:10<22:43,  1.55it/s]
 96%|█████████▋| 55489/57600 [9:46:10<22:07,  1.59it/s]
 96%|█████████▋| 55490/57600 [9:46:11<22:18,  1.58it/s]
 96%|█████████▋| 55491/57600 [9:46:12<21:19,  1.65it/s]
 96%|█████████▋| 55492/57600 [9:46:12<21:08,  1.66it/s]
 96%|█████████▋| 55493/57600 [9:46:13<20:59,  1.67it/s]
 96%|█████████▋| 55494/57600 [9:46:13<21:08,  1.66it/s]
 96%|█████████▋| 55495/57600 [9:46:14<21:37,  1.62it/s]
 96%|█████████▋| 55496/57600 [9:46:15<21:26,  1.64it/s]
 96%|█████████▋| 55497/57600 [9:46:15<21:56,  1.60it/s]
 96%|█████████▋| 55498/57600 [9:46:16<21:41,  1.62it/s]
 96%|█████████▋| 55499/57600 [9:46:16<21:44,  1.61it/s]
 96%|█████████▋| 55500/57600 [9:46:17<21:44,  1.61it/s]
                                                       
{'loss': 1.0675, 'learning_rate': 1.329268292682927e-07, 'epoch': 612.58}

 96%|█████████▋| 55500/57600 [9:46:17<21:44,  1.61it/s]
 96%|█████████▋| 55501/57600 [9:46:18<21:34,  1.62it/s]
 96%|█████████▋| 55502/57600 [9:46:18<21:24,  1.63it/s]
 96%|█████████▋| 55503/57600 [9:46:19<21:08,  1.65it/s]
 96%|█████████▋| 55504/57600 [9:46:19<21:01,  1.66it/s]
 96%|█████████▋| 55505/57600 [9:46:20<20:57,  1.67it/s]
 96%|█████████▋| 55506/57600 [9:46:21<21:25,  1.63it/s]
 96%|█████████▋| 55507/57600 [9:46:21<22:04,  1.58it/s]
 96%|█████████▋| 55508/57600 [9:46:22<21:56,  1.59it/s]
 96%|█████████▋| 55509/57600 [9:46:23<22:56,  1.52it/s]
 96%|█████████▋| 55510/57600 [9:46:23<22:41,  1.54it/s]
 96%|█████████▋| 55511/57600 [9:46:24<22:40,  1.54it/s]
 96%|█████████▋| 55512/57600 [9:46:25<22:19,  1.56it/s]
 96%|█████████▋| 55513/57600 [9:46:25<21:57,  1.58it/s]
 96%|█████████▋| 55514/57600 [9:46:26<22:05,  1.57it/s]
 96%|█████████▋| 55515/57600 [9:46:27<21:49,  1.59it/s]
 96%|█████████▋| 55516/57600 [9:46:27<21:32,  1.61it/s]
 96%|█████████▋| 55517/57600 [9:46:28<21:11,  1.64it/s]
 96%|█████████▋| 55518/57600 [9:46:28<21:01,  1.65it/s]
 96%|█████████▋| 55519/57600 [9:46:29<21:01,  1.65it/s]
 96%|█████████▋| 55520/57600 [9:46:29<20:31,  1.69it/s]
                                                       
{'loss': 1.1322, 'learning_rate': 1.3261324041811843e-07, 'epoch': 612.8}

 96%|█████████▋| 55520/57600 [9:46:29<20:31,  1.69it/s]
 96%|█████████▋| 55521/57600 [9:46:30<20:24,  1.70it/s]
 96%|█████████▋| 55522/57600 [9:46:31<21:06,  1.64it/s]
 96%|█████████▋| 55523/57600 [9:46:31<21:00,  1.65it/s]
 96%|█████████▋| 55524/57600 [9:46:32<21:36,  1.60it/s]
 96%|█████████▋| 55525/57600 [9:46:33<20:53,  1.66it/s]
 96%|█████████▋| 55526/57600 [9:46:33<21:13,  1.63it/s]
 96%|█████████▋| 55527/57600 [9:46:34<20:58,  1.65it/s]
 96%|█████████▋| 55528/57600 [9:46:35<22:44,  1.52it/s]
 96%|█████████▋| 55529/57600 [9:46:35<21:50,  1.58it/s]
 96%|█████████▋| 55530/57600 [9:46:36<21:20,  1.62it/s]
 96%|█████████▋| 55531/57600 [9:46:36<21:05,  1.63it/s]
 96%|█████████▋| 55532/57600 [9:46:37<22:02,  1.56it/s]
 96%|█████████▋| 55533/57600 [9:46:38<22:42,  1.52it/s]
 96%|█████████▋| 55534/57600 [9:46:38<22:10,  1.55it/s]
 96%|█████████▋| 55535/57600 [9:46:39<21:57,  1.57it/s]
 96%|█████████▋| 55536/57600 [9:46:40<22:17,  1.54it/s]
 96%|█████████▋| 55537/57600 [9:46:40<22:26,  1.53it/s]
 96%|█████████▋| 55538/57600 [9:46:41<23:52,  1.44it/s]
 96%|█████████▋| 55539/57600 [9:46:42<22:42,  1.51it/s]
 96%|█████████▋| 55540/57600 [9:46:42<22:20,  1.54it/s]
                                                       
{'loss': 1.0858, 'learning_rate': 1.3229965156794426e-07, 'epoch': 613.02}

 96%|█████████▋| 55540/57600 [9:46:42<22:20,  1.54it/s]
 96%|█████████▋| 55541/57600 [9:46:43<21:48,  1.57it/s]
 96%|█████████▋| 55542/57600 [9:46:43<21:39,  1.58it/s]
 96%|█████████▋| 55543/57600 [9:46:44<21:10,  1.62it/s]
 96%|█████████▋| 55544/57600 [9:46:45<21:45,  1.57it/s]
 96%|█████████▋| 55545/57600 [9:46:45<22:18,  1.54it/s]
 96%|█████████▋| 55546/57600 [9:46:46<21:48,  1.57it/s]
 96%|█████████▋| 55547/57600 [9:46:47<21:26,  1.60it/s]
 96%|█████████▋| 55548/57600 [9:46:47<21:03,  1.62it/s]
 96%|█████████▋| 55549/57600 [9:46:48<21:38,  1.58it/s]
 96%|█████████▋| 55550/57600 [9:46:49<21:20,  1.60it/s]
 96%|█████████▋| 55551/57600 [9:46:49<21:51,  1.56it/s]
 96%|█████████▋| 55552/57600 [9:46:50<21:38,  1.58it/s]
 96%|█████████▋| 55553/57600 [9:46:50<21:10,  1.61it/s]
 96%|█████████▋| 55554/57600 [9:46:51<21:21,  1.60it/s]
 96%|█████████▋| 55555/57600 [9:46:52<21:19,  1.60it/s]
 96%|█████████▋| 55556/57600 [9:46:52<21:43,  1.57it/s]
 96%|█████████▋| 55557/57600 [9:46:53<21:54,  1.55it/s]
 96%|█████████▋| 55558/57600 [9:46:54<21:55,  1.55it/s]
 96%|█████████▋| 55559/57600 [9:46:54<21:55,  1.55it/s]
 96%|█████████▋| 55560/57600 [9:46:55<21:50,  1.56it/s]
                                                       
{'loss': 1.0964, 'learning_rate': 1.3198606271777e-07, 'epoch': 613.25}

 96%|█████████▋| 55560/57600 [9:46:55<21:50,  1.56it/s]
 96%|█████████▋| 55561/57600 [9:46:55<21:20,  1.59it/s]
 96%|█████████▋| 55562/57600 [9:46:56<21:11,  1.60it/s]
 96%|█████████▋| 55563/57600 [9:46:57<21:01,  1.61it/s]
 96%|█████████▋| 55564/57600 [9:46:57<21:03,  1.61it/s]
 96%|█████████▋| 55565/57600 [9:46:58<20:45,  1.63it/s]
 96%|█████████▋| 55566/57600 [9:46:59<20:39,  1.64it/s]
 96%|█████████▋| 55567/57600 [9:46:59<20:50,  1.63it/s]
 96%|█████████▋| 55568/57600 [9:47:00<21:33,  1.57it/s]
 96%|█████████▋| 55569/57600 [9:47:01<21:52,  1.55it/s]
 96%|█████████▋| 55570/57600 [9:47:01<21:17,  1.59it/s]
 96%|█████████▋| 55571/57600 [9:47:02<21:10,  1.60it/s]
 96%|█████████▋| 55572/57600 [9:47:02<20:52,  1.62it/s]
 96%|█████████▋| 55573/57600 [9:47:03<22:00,  1.54it/s]
 96%|█████████▋| 55574/57600 [9:47:04<21:25,  1.58it/s]
 96%|█████████▋| 55575/57600 [9:47:04<21:43,  1.55it/s]
 96%|█████████▋| 55576/57600 [9:47:05<21:04,  1.60it/s]
 96%|█████████▋| 55577/57600 [9:47:05<20:42,  1.63it/s]
 96%|█████████▋| 55578/57600 [9:47:06<20:40,  1.63it/s]
 96%|█████████▋| 55579/57600 [9:47:07<20:39,  1.63it/s]
 96%|█████████▋| 55580/57600 [9:47:07<20:27,  1.65it/s]
                                                       
{'loss': 1.1252, 'learning_rate': 1.3167247386759582e-07, 'epoch': 613.47}

 96%|█████████▋| 55580/57600 [9:47:07<20:27,  1.65it/s]
 96%|█████████▋| 55581/57600 [9:47:08<20:36,  1.63it/s]
 96%|█████████▋| 55582/57600 [9:47:09<20:22,  1.65it/s]
 96%|█████████▋| 55583/57600 [9:47:09<19:58,  1.68it/s]
 96%|█████████▋| 55584/57600 [9:47:10<19:32,  1.72it/s]
 97%|█████████▋| 55585/57600 [9:47:10<19:09,  1.75it/s]
 97%|█████████▋| 55586/57600 [9:47:11<19:47,  1.70it/s]
 97%|█████████▋| 55587/57600 [9:47:11<19:57,  1.68it/s]
 97%|█████████▋| 55588/57600 [9:47:12<20:30,  1.64it/s]
 97%|█████████▋| 55589/57600 [9:47:13<19:54,  1.68it/s]
 97%|█████████▋| 55590/57600 [9:47:13<21:14,  1.58it/s]
 97%|█████████▋| 55591/57600 [9:47:14<20:52,  1.60it/s]
 97%|█████████▋| 55592/57600 [9:47:15<20:28,  1.64it/s]
 97%|█████████▋| 55593/57600 [9:47:15<20:12,  1.65it/s]
 97%|█████████▋| 55594/57600 [9:47:16<20:33,  1.63it/s]
 97%|█████████▋| 55595/57600 [9:47:16<20:22,  1.64it/s]
 97%|█████████▋| 55596/57600 [9:47:17<19:58,  1.67it/s]
 97%|█████████▋| 55597/57600 [9:47:18<20:26,  1.63it/s]
 97%|█████████▋| 55598/57600 [9:47:18<20:15,  1.65it/s]
 97%|█████████▋| 55599/57600 [9:47:19<20:16,  1.64it/s]
 97%|█████████▋| 55600/57600 [9:47:19<20:28,  1.63it/s]
                                                       
{'loss': 1.1413, 'learning_rate': 1.3135888501742163e-07, 'epoch': 613.69}

 97%|█████████▋| 55600/57600 [9:47:19<20:28,  1.63it/s]
 97%|█████████▋| 55601/57600 [9:47:20<20:11,  1.65it/s]
 97%|█████████▋| 55602/57600 [9:47:21<20:04,  1.66it/s]
 97%|█████████▋| 55603/57600 [9:47:21<20:12,  1.65it/s]
 97%|█████████▋| 55604/57600 [9:47:22<20:10,  1.65it/s]
 97%|█████████▋| 55605/57600 [9:47:22<20:24,  1.63it/s]
 97%|█████████▋| 55606/57600 [9:47:23<20:52,  1.59it/s]
 97%|█████████▋| 55607/57600 [9:47:24<20:59,  1.58it/s]
 97%|█████████▋| 55608/57600 [9:47:24<20:52,  1.59it/s]
 97%|█████████▋| 55609/57600 [9:47:25<20:59,  1.58it/s]
 97%|█████████▋| 55610/57600 [9:47:26<20:32,  1.62it/s]
 97%|█████████▋| 55611/57600 [9:47:26<21:54,  1.51it/s]
 97%|█████████▋| 55612/57600 [9:47:27<21:46,  1.52it/s]
 97%|█████████▋| 55613/57600 [9:47:28<21:22,  1.55it/s]
 97%|█████████▋| 55614/57600 [9:47:28<21:45,  1.52it/s]
 97%|█████████▋| 55615/57600 [9:47:29<21:08,  1.56it/s]
 97%|█████████▋| 55616/57600 [9:47:30<21:17,  1.55it/s]
 97%|█████████▋| 55617/57600 [9:47:30<20:58,  1.58it/s]
 97%|█████████▋| 55618/57600 [9:47:31<21:27,  1.54it/s]
 97%|█████████▋| 55619/57600 [9:47:31<20:53,  1.58it/s]
 97%|█████████▋| 55620/57600 [9:47:32<20:24,  1.62it/s]
                                                       
{'loss': 1.0924, 'learning_rate': 1.3104529616724738e-07, 'epoch': 613.91}

 97%|█████████▋| 55620/57600 [9:47:32<20:24,  1.62it/s]
 97%|█████████▋| 55621/57600 [9:47:33<21:01,  1.57it/s]
 97%|█████████▋| 55622/57600 [9:47:33<21:00,  1.57it/s]
 97%|█████████▋| 55623/57600 [9:47:34<21:02,  1.57it/s]
 97%|█████████▋| 55624/57600 [9:47:35<20:53,  1.58it/s]
 97%|█████████▋| 55625/57600 [9:47:35<21:03,  1.56it/s]
 97%|█████████▋| 55626/57600 [9:47:36<21:04,  1.56it/s]
 97%|█████████▋| 55627/57600 [9:47:37<20:51,  1.58it/s]
 97%|█████████▋| 55628/57600 [9:47:37<20:14,  1.62it/s]
 97%|█████████▋| 55629/57600 [9:47:38<21:43,  1.51it/s]
 97%|█████████▋| 55630/57600 [9:47:38<20:55,  1.57it/s]
 97%|█████████▋| 55631/57600 [9:47:39<20:51,  1.57it/s]
 97%|█████████▋| 55632/57600 [9:47:40<20:54,  1.57it/s]
 97%|█████████▋| 55633/57600 [9:47:40<20:24,  1.61it/s]
 97%|█████████▋| 55634/57600 [9:47:41<20:34,  1.59it/s]
 97%|█████████▋| 55635/57600 [9:47:42<20:48,  1.57it/s]
 97%|█████████▋| 55636/57600 [9:47:42<21:28,  1.52it/s]
 97%|█████████▋| 55637/57600 [9:47:43<21:24,  1.53it/s]
 97%|█████████▋| 55638/57600 [9:47:44<20:50,  1.57it/s]
 97%|█████████▋| 55639/57600 [9:47:44<20:59,  1.56it/s]
 97%|█████████▋| 55640/57600 [9:47:45<20:32,  1.59it/s]
                                                       
{'loss': 1.063, 'learning_rate': 1.3073170731707316e-07, 'epoch': 614.13}

 97%|█████████▋| 55640/57600 [9:47:45<20:32,  1.59it/s]
 97%|█████████▋| 55641/57600 [9:47:45<20:28,  1.60it/s]
 97%|█████████▋| 55642/57600 [9:47:46<20:14,  1.61it/s]
 97%|█████████▋| 55643/57600 [9:47:47<20:03,  1.63it/s]
 97%|█████████▋| 55644/57600 [9:47:47<19:51,  1.64it/s]
 97%|█████████▋| 55645/57600 [9:47:48<20:59,  1.55it/s]
 97%|█████████▋| 55646/57600 [9:47:49<20:49,  1.56it/s]
 97%|█████████▋| 55647/57600 [9:47:49<20:47,  1.57it/s]
 97%|█████████▋| 55648/57600 [9:47:50<19:58,  1.63it/s]
 97%|█████████▋| 55649/57600 [9:47:50<20:24,  1.59it/s]
 97%|█████████▋| 55650/57600 [9:47:51<20:05,  1.62it/s]
 97%|█████████▋| 55651/57600 [9:47:52<20:16,  1.60it/s]
 97%|█████████▋| 55652/57600 [9:47:52<20:18,  1.60it/s]
 97%|█████████▋| 55653/57600 [9:47:53<20:44,  1.56it/s]
 97%|█████████▋| 55654/57600 [9:47:54<20:21,  1.59it/s]
 97%|█████████▋| 55655/57600 [9:47:54<20:55,  1.55it/s]
 97%|█████████▋| 55656/57600 [9:47:55<20:47,  1.56it/s]
 97%|█████████▋| 55657/57600 [9:47:56<20:49,  1.56it/s]
 97%|█████████▋| 55658/57600 [9:47:56<20:07,  1.61it/s]
 97%|█████████▋| 55659/57600 [9:47:57<20:21,  1.59it/s]
 97%|█████████▋| 55660/57600 [9:47:57<20:21,  1.59it/s]
                                                       
{'loss': 1.094, 'learning_rate': 1.3041811846689894e-07, 'epoch': 614.35}

 97%|█████████▋| 55660/57600 [9:47:57<20:21,  1.59it/s]
 97%|█████████▋| 55661/57600 [9:47:58<20:28,  1.58it/s]
 97%|█████████▋| 55662/57600 [9:47:59<20:27,  1.58it/s]
 97%|█████████▋| 55663/57600 [9:47:59<20:22,  1.58it/s]
 97%|█████████▋| 55664/57600 [9:48:00<20:02,  1.61it/s]
 97%|█████████▋| 55665/57600 [9:48:00<19:44,  1.63it/s]
 97%|█████████▋| 55666/57600 [9:48:01<19:36,  1.64it/s]
 97%|█████████▋| 55667/57600 [9:48:02<19:57,  1.61it/s]
 97%|█████████▋| 55668/57600 [9:48:02<20:17,  1.59it/s]
 97%|█████████▋| 55669/57600 [9:48:03<19:40,  1.64it/s]
 97%|█████████▋| 55670/57600 [9:48:04<19:33,  1.64it/s]
 97%|█████████▋| 55671/57600 [9:48:04<19:33,  1.64it/s]
 97%|█████████▋| 55672/57600 [9:48:05<19:37,  1.64it/s]
 97%|█████████▋| 55673/57600 [9:48:05<19:34,  1.64it/s]
 97%|█████████▋| 55674/57600 [9:48:06<19:44,  1.63it/s]
 97%|█████████▋| 55675/57600 [9:48:07<20:08,  1.59it/s]
 97%|█████████▋| 55676/57600 [9:48:07<19:32,  1.64it/s]
 97%|█████████▋| 55677/57600 [9:48:08<19:45,  1.62it/s]
 97%|█████████▋| 55678/57600 [9:48:08<19:37,  1.63it/s]
 97%|█████████▋| 55679/57600 [9:48:09<19:46,  1.62it/s]
 97%|█████████▋| 55680/57600 [9:48:10<19:59,  1.60it/s]
                                                       
{'loss': 1.0872, 'learning_rate': 1.3010452961672474e-07, 'epoch': 614.57}

 97%|█████████▋| 55680/57600 [9:48:10<19:59,  1.60it/s]
 97%|█████████▋| 55681/57600 [9:48:10<19:34,  1.63it/s]
 97%|█████████▋| 55682/57600 [9:48:11<19:17,  1.66it/s]
 97%|█████████▋| 55683/57600 [9:48:12<19:16,  1.66it/s]
 97%|█████████▋| 55684/57600 [9:48:12<19:51,  1.61it/s]
 97%|█████████▋| 55685/57600 [9:48:13<19:44,  1.62it/s]
 97%|█████████▋| 55686/57600 [9:48:14<20:42,  1.54it/s]
 97%|█████████▋| 55687/57600 [9:48:14<21:10,  1.51it/s]
 97%|█████████▋| 55688/57600 [9:48:15<20:51,  1.53it/s]
 97%|█████████▋| 55689/57600 [9:48:15<20:22,  1.56it/s]
 97%|█████████▋| 55690/57600 [9:48:16<20:35,  1.55it/s]
 97%|█████████▋| 55691/57600 [9:48:17<20:09,  1.58it/s]
 97%|█████████▋| 55692/57600 [9:48:17<19:34,  1.62it/s]
 97%|█████████▋| 55693/57600 [9:48:18<19:23,  1.64it/s]
 97%|█████████▋| 55694/57600 [9:48:19<19:32,  1.63it/s]
 97%|█████████▋| 55695/57600 [9:48:19<19:56,  1.59it/s]
 97%|█████████▋| 55696/57600 [9:48:20<19:17,  1.64it/s]
 97%|█████████▋| 55697/57600 [9:48:20<18:42,  1.70it/s]
 97%|█████████▋| 55698/57600 [9:48:21<18:45,  1.69it/s]
 97%|█████████▋| 55699/57600 [9:48:22<19:22,  1.64it/s]
 97%|█████████▋| 55700/57600 [9:48:22<19:40,  1.61it/s]
                                                       
{'loss': 1.119, 'learning_rate': 1.2979094076655047e-07, 'epoch': 614.79}

 97%|█████████▋| 55700/57600 [9:48:22<19:40,  1.61it/s]
 97%|█████████▋| 55701/57600 [9:48:23<19:47,  1.60it/s]
 97%|█████████▋| 55702/57600 [9:48:23<19:34,  1.62it/s]
 97%|█████████▋| 55703/57600 [9:48:24<19:53,  1.59it/s]
 97%|█████████▋| 55704/57600 [9:48:25<19:44,  1.60it/s]
 97%|█████████▋| 55705/57600 [9:48:25<19:32,  1.62it/s]
 97%|█████████▋| 55706/57600 [9:48:26<19:39,  1.61it/s]
 97%|█████████▋| 55707/57600 [9:48:27<19:35,  1.61it/s]
 97%|█████████▋| 55708/57600 [9:48:27<19:21,  1.63it/s]
 97%|█████████▋| 55709/57600 [9:48:28<19:10,  1.64it/s]
 97%|█████████▋| 55710/57600 [9:48:28<19:18,  1.63it/s]
 97%|█████████▋| 55711/57600 [9:48:29<19:16,  1.63it/s]
 97%|█████████▋| 55712/57600 [9:48:30<19:45,  1.59it/s]
 97%|█████████▋| 55713/57600 [9:48:30<19:25,  1.62it/s]
 97%|█████████▋| 55714/57600 [9:48:31<19:19,  1.63it/s]
 97%|█████████▋| 55715/57600 [9:48:31<19:13,  1.63it/s]
 97%|█████████▋| 55716/57600 [9:48:32<18:42,  1.68it/s]
 97%|█████████▋| 55717/57600 [9:48:33<19:41,  1.59it/s]
 97%|█████████▋| 55718/57600 [9:48:33<19:42,  1.59it/s]
 97%|█████████▋| 55719/57600 [9:48:34<19:30,  1.61it/s]
 97%|█████████▋| 55720/57600 [9:48:35<19:51,  1.58it/s]
                                                       
{'loss': 1.1066, 'learning_rate': 1.294773519163763e-07, 'epoch': 615.01}

 97%|█████████▋| 55720/57600 [9:48:35<19:51,  1.58it/s]
 97%|█████████▋| 55721/57600 [9:48:35<19:31,  1.60it/s]
 97%|█████████▋| 55722/57600 [9:48:36<20:23,  1.54it/s]
 97%|█████████▋| 55723/57600 [9:48:37<20:44,  1.51it/s]
 97%|█████████▋| 55724/57600 [9:48:37<20:03,  1.56it/s]
 97%|█████████▋| 55725/57600 [9:48:38<20:12,  1.55it/s]
 97%|█████████▋| 55726/57600 [9:48:39<20:30,  1.52it/s]
 97%|█████████▋| 55727/57600 [9:48:39<19:57,  1.56it/s]
 97%|█████████▋| 55728/57600 [9:48:40<19:25,  1.61it/s]
 97%|█████████▋| 55729/57600 [9:48:40<19:41,  1.58it/s]
 97%|█████████▋| 55730/57600 [9:48:41<19:35,  1.59it/s]
 97%|█████████▋| 55731/57600 [9:48:42<19:54,  1.57it/s]
 97%|█████████▋| 55732/57600 [9:48:42<19:20,  1.61it/s]
 97%|█████████▋| 55733/57600 [9:48:43<19:51,  1.57it/s]
 97%|█████████▋| 55734/57600 [9:48:44<19:37,  1.59it/s]
 97%|█████████▋| 55735/57600 [9:48:44<18:54,  1.64it/s]
 97%|█████████▋| 55736/57600 [9:48:45<18:47,  1.65it/s]
 97%|█████████▋| 55737/57600 [9:48:45<18:36,  1.67it/s]
 97%|█████████▋| 55738/57600 [9:48:46<19:08,  1.62it/s]
 97%|█████████▋| 55739/57600 [9:48:47<19:30,  1.59it/s]
 97%|█████████▋| 55740/57600 [9:48:47<19:59,  1.55it/s]
                                                       
{'loss': 1.0862, 'learning_rate': 1.2916376306620213e-07, 'epoch': 615.23}

 97%|█████████▋| 55740/57600 [9:48:47<19:59,  1.55it/s]
 97%|█████████▋| 55741/57600 [9:48:48<19:50,  1.56it/s]
 97%|█████████▋| 55742/57600 [9:48:49<19:37,  1.58it/s]
 97%|█████████▋| 55743/57600 [9:48:49<19:28,  1.59it/s]
 97%|█████████▋| 55744/57600 [9:48:50<19:22,  1.60it/s]
 97%|█████████▋| 55745/57600 [9:48:50<19:50,  1.56it/s]
 97%|█████████▋| 55746/57600 [9:48:51<19:53,  1.55it/s]
 97%|█████████▋| 55747/57600 [9:48:52<19:46,  1.56it/s]
 97%|█████████▋| 55748/57600 [9:48:52<19:59,  1.54it/s]
 97%|█████████▋| 55749/57600 [9:48:53<19:44,  1.56it/s]
 97%|█████████▋| 55750/57600 [9:48:54<19:15,  1.60it/s]
 97%|█████████▋| 55751/57600 [9:48:54<18:50,  1.64it/s]
 97%|█████████▋| 55752/57600 [9:48:55<19:05,  1.61it/s]
 97%|█████████▋| 55753/57600 [9:48:55<19:05,  1.61it/s]
 97%|█████████▋| 55754/57600 [9:48:56<19:44,  1.56it/s]
 97%|█████████▋| 55755/57600 [9:48:57<18:59,  1.62it/s]
 97%|█████████▋| 55756/57600 [9:48:57<18:59,  1.62it/s]
 97%|█████████▋| 55757/57600 [9:48:58<18:46,  1.64it/s]
 97%|█████████▋| 55758/57600 [9:48:59<18:49,  1.63it/s]
 97%|█████████▋| 55759/57600 [9:48:59<18:35,  1.65it/s]
 97%|█████████▋| 55760/57600 [9:49:00<18:34,  1.65it/s]
                                                       
{'loss': 1.1227, 'learning_rate': 1.2885017421602785e-07, 'epoch': 615.45}

 97%|█████████▋| 55760/57600 [9:49:00<18:34,  1.65it/s]
 97%|█████████▋| 55761/57600 [9:49:00<18:40,  1.64it/s]
 97%|█████████▋| 55762/57600 [9:49:01<19:02,  1.61it/s]
 97%|█████████▋| 55763/57600 [9:49:02<18:40,  1.64it/s]
 97%|█████████▋| 55764/57600 [9:49:02<18:23,  1.66it/s]
 97%|█████████▋| 55765/57600 [9:49:03<18:44,  1.63it/s]
 97%|█████████▋| 55766/57600 [9:49:03<18:53,  1.62it/s]
 97%|█████████▋| 55767/57600 [9:49:04<18:31,  1.65it/s]
 97%|█████████▋| 55768/57600 [9:49:05<18:36,  1.64it/s]
 97%|█████████▋| 55769/57600 [9:49:05<19:02,  1.60it/s]
 97%|█████████▋| 55770/57600 [9:49:06<19:14,  1.59it/s]
 97%|█████████▋| 55771/57600 [9:49:07<19:03,  1.60it/s]
 97%|█████████▋| 55772/57600 [9:49:07<18:32,  1.64it/s]
 97%|█████████▋| 55773/57600 [9:49:08<18:09,  1.68it/s]
 97%|█████████▋| 55774/57600 [9:49:08<17:58,  1.69it/s]
 97%|█████████▋| 55775/57600 [9:49:09<18:39,  1.63it/s]
 97%|█████████▋| 55776/57600 [9:49:09<18:31,  1.64it/s]
 97%|█████████▋| 55777/57600 [9:49:10<19:03,  1.59it/s]
 97%|█████████▋| 55778/57600 [9:49:11<18:19,  1.66it/s]
 97%|█████████▋| 55779/57600 [9:49:11<18:19,  1.66it/s]
 97%|█████████▋| 55780/57600 [9:49:12<18:38,  1.63it/s]
                                                       
{'loss': 1.1169, 'learning_rate': 1.2853658536585368e-07, 'epoch': 615.67}

 97%|█████████▋| 55780/57600 [9:49:12<18:38,  1.63it/s]
 97%|█████████▋| 55781/57600 [9:49:13<18:25,  1.65it/s]
 97%|█████████▋| 55782/57600 [9:49:13<18:12,  1.66it/s]
 97%|█████████▋| 55783/57600 [9:49:14<17:56,  1.69it/s]
 97%|█████████▋| 55784/57600 [9:49:14<17:38,  1.72it/s]
 97%|█████████▋| 55785/57600 [9:49:15<18:13,  1.66it/s]
 97%|█████████▋| 55786/57600 [9:49:15<18:00,  1.68it/s]
 97%|█████████▋| 55787/57600 [9:49:16<17:45,  1.70it/s]
 97%|█████████▋| 55788/57600 [9:49:17<17:47,  1.70it/s]
 97%|█████████▋| 55789/57600 [9:49:17<18:30,  1.63it/s]
 97%|█████████▋| 55790/57600 [9:49:18<19:28,  1.55it/s]
 97%|█████████▋| 55791/57600 [9:49:19<19:36,  1.54it/s]
 97%|█████████▋| 55792/57600 [9:49:19<18:50,  1.60it/s]
 97%|█████████▋| 55793/57600 [9:49:20<19:03,  1.58it/s]
 97%|█████████▋| 55794/57600 [9:49:21<18:37,  1.62it/s]
 97%|█████████▋| 55795/57600 [9:49:21<18:20,  1.64it/s]
 97%|█████████▋| 55796/57600 [9:49:22<18:14,  1.65it/s]
 97%|█████████▋| 55797/57600 [9:49:22<18:43,  1.61it/s]
 97%|█████████▋| 55798/57600 [9:49:23<18:27,  1.63it/s]
 97%|█████████▋| 55799/57600 [9:49:24<19:34,  1.53it/s]
 97%|█████████▋| 55800/57600 [9:49:24<19:38,  1.53it/s]
                                                       
{'loss': 1.0992, 'learning_rate': 1.282229965156794e-07, 'epoch': 615.89}

 97%|█████████▋| 55800/57600 [9:49:24<19:38,  1.53it/s]
 97%|█████████▋| 55801/57600 [9:49:25<19:27,  1.54it/s]
 97%|█████████▋| 55802/57600 [9:49:26<18:33,  1.61it/s]
 97%|█████████▋| 55803/57600 [9:49:26<18:21,  1.63it/s]
 97%|█████████▋| 55804/57600 [9:49:27<18:06,  1.65it/s]
 97%|█████████▋| 55805/57600 [9:49:27<18:32,  1.61it/s]
 97%|█████████▋| 55806/57600 [9:49:28<17:52,  1.67it/s]
 97%|█████████▋| 55807/57600 [9:49:29<17:51,  1.67it/s]
 97%|█████████▋| 55808/57600 [9:49:29<18:17,  1.63it/s]
 97%|█████████▋| 55809/57600 [9:49:30<18:23,  1.62it/s]
 97%|█████████▋| 55810/57600 [9:49:31<19:28,  1.53it/s]
 97%|█████████▋| 55811/57600 [9:49:31<19:09,  1.56it/s]
 97%|█████████▋| 55812/57600 [9:49:32<19:06,  1.56it/s]
 97%|█████████▋| 55813/57600 [9:49:32<18:53,  1.58it/s]
 97%|█████████▋| 55814/57600 [9:49:33<18:46,  1.58it/s]
 97%|█████████▋| 55815/57600 [9:49:34<18:33,  1.60it/s]
 97%|█████████▋| 55816/57600 [9:49:34<18:36,  1.60it/s]
 97%|█████████▋| 55817/57600 [9:49:35<18:14,  1.63it/s]
 97%|█████████▋| 55818/57600 [9:49:36<18:37,  1.60it/s]
 97%|█████████▋| 55819/57600 [9:49:36<18:40,  1.59it/s]
 97%|█████████▋| 55820/57600 [9:49:37<18:13,  1.63it/s]
                                                       
{'loss': 1.0949, 'learning_rate': 1.2790940766550524e-07, 'epoch': 616.11}

 97%|█████████▋| 55820/57600 [9:49:37<18:13,  1.63it/s]
 97%|█████████▋| 55821/57600 [9:49:37<18:43,  1.58it/s]
 97%|█████████▋| 55822/57600 [9:49:38<18:16,  1.62it/s]
 97%|█████████▋| 55823/57600 [9:49:39<17:46,  1.67it/s]
 97%|█████████▋| 55824/57600 [9:49:39<18:46,  1.58it/s]
 97%|█████████▋| 55825/57600 [9:49:40<18:25,  1.60it/s]
 97%|█████████▋| 55826/57600 [9:49:40<18:27,  1.60it/s]
 97%|█████████▋| 55827/57600 [9:49:41<18:22,  1.61it/s]
 97%|█████████▋| 55828/57600 [9:49:42<19:01,  1.55it/s]
 97%|█████████▋| 55829/57600 [9:49:42<18:23,  1.61it/s]
 97%|█████████▋| 55830/57600 [9:49:43<17:56,  1.64it/s]
 97%|█████████▋| 55831/57600 [9:49:44<17:59,  1.64it/s]
 97%|█████████▋| 55832/57600 [9:49:44<18:01,  1.63it/s]
 97%|█████████▋| 55833/57600 [9:49:45<18:38,  1.58it/s]
 97%|█████████▋| 55834/57600 [9:49:45<18:34,  1.58it/s]
 97%|█████████▋| 55835/57600 [9:49:46<18:23,  1.60it/s]
 97%|█████████▋| 55836/57600 [9:49:47<18:00,  1.63it/s]
 97%|█████████▋| 55837/57600 [9:49:47<17:23,  1.69it/s]
 97%|█████████▋| 55838/57600 [9:49:48<17:40,  1.66it/s]
 97%|█████████▋| 55839/57600 [9:49:48<17:44,  1.65it/s]
 97%|█████████▋| 55840/57600 [9:49:49<17:47,  1.65it/s]
                                                       
{'loss': 1.1333, 'learning_rate': 1.2759581881533097e-07, 'epoch': 616.34}

 97%|█████████▋| 55840/57600 [9:49:49<17:47,  1.65it/s]
 97%|█████████▋| 55841/57600 [9:49:50<17:26,  1.68it/s]
 97%|█████████▋| 55842/57600 [9:49:50<17:15,  1.70it/s]
 97%|█████████▋| 55843/57600 [9:49:51<17:17,  1.69it/s]
 97%|█████████▋| 55844/57600 [9:49:51<17:05,  1.71it/s]
 97%|█████████▋| 55845/57600 [9:49:52<17:45,  1.65it/s]
 97%|█████████▋| 55846/57600 [9:49:53<18:02,  1.62it/s]
 97%|█████████▋| 55847/57600 [9:49:53<17:59,  1.62it/s]
 97%|█████████▋| 55848/57600 [9:49:54<18:20,  1.59it/s]
 97%|█████████▋| 55849/57600 [9:49:55<17:45,  1.64it/s]
 97%|█████████▋| 55850/57600 [9:49:55<17:45,  1.64it/s]
 97%|█████████▋| 55851/57600 [9:49:56<18:03,  1.61it/s]
 97%|█████████▋| 55852/57600 [9:49:56<18:02,  1.61it/s]
 97%|█████████▋| 55853/57600 [9:49:57<17:55,  1.63it/s]
 97%|█████████▋| 55854/57600 [9:49:58<17:25,  1.67it/s]
 97%|█████████▋| 55855/57600 [9:49:58<17:21,  1.67it/s]
 97%|█████████▋| 55856/57600 [9:49:59<17:56,  1.62it/s]
 97%|█████████▋| 55857/57600 [9:49:59<18:20,  1.58it/s]
 97%|█████████▋| 55858/57600 [9:50:00<18:34,  1.56it/s]
 97%|█████████▋| 55859/57600 [9:50:01<18:05,  1.60it/s]
 97%|█████████▋| 55860/57600 [9:50:01<17:59,  1.61it/s]
                                                       
{'loss': 1.1113, 'learning_rate': 1.2728222996515677e-07, 'epoch': 616.56}

 97%|█████████▋| 55860/57600 [9:50:01<17:59,  1.61it/s]
 97%|█████████▋| 55861/57600 [9:50:02<18:53,  1.53it/s]
 97%|█████████▋| 55862/57600 [9:50:03<18:26,  1.57it/s]
 97%|█████████▋| 55863/57600 [9:50:03<18:14,  1.59it/s]
 97%|█████████▋| 55864/57600 [9:50:04<18:27,  1.57it/s]
 97%|█████████▋| 55865/57600 [9:50:05<19:00,  1.52it/s]
 97%|█████████▋| 55866/57600 [9:50:05<18:12,  1.59it/s]
 97%|█████████▋| 55867/57600 [9:50:06<18:18,  1.58it/s]
 97%|█████████▋| 55868/57600 [9:50:06<18:06,  1.59it/s]
 97%|█████████▋| 55869/57600 [9:50:07<17:36,  1.64it/s]
 97%|█████████▋| 55870/57600 [9:50:08<17:45,  1.62it/s]
 97%|█████████▋| 55871/57600 [9:50:08<17:54,  1.61it/s]
 97%|█████████▋| 55872/57600 [9:50:09<17:41,  1.63it/s]
 97%|█████████▋| 55873/57600 [9:50:10<17:46,  1.62it/s]
 97%|█████████▋| 55874/57600 [9:50:10<18:20,  1.57it/s]
 97%|█████████▋| 55875/57600 [9:50:11<19:21,  1.49it/s]
 97%|█████████▋| 55876/57600 [9:50:12<19:28,  1.48it/s]
 97%|█████████▋| 55877/57600 [9:50:12<18:50,  1.52it/s]
 97%|█████████▋| 55878/57600 [9:50:13<18:16,  1.57it/s]
 97%|█████████▋| 55879/57600 [9:50:13<17:50,  1.61it/s]
 97%|█████████▋| 55880/57600 [9:50:14<17:30,  1.64it/s]
                                                       
{'loss': 1.0913, 'learning_rate': 1.269686411149826e-07, 'epoch': 616.78}

 97%|█████████▋| 55880/57600 [9:50:14<17:30,  1.64it/s]
 97%|█████████▋| 55881/57600 [9:50:15<17:00,  1.68it/s]
 97%|█████████▋| 55882/57600 [9:50:15<17:20,  1.65it/s]
 97%|█████████▋| 55883/57600 [9:50:16<17:46,  1.61it/s]
 97%|█████████▋| 55884/57600 [9:50:16<17:39,  1.62it/s]
 97%|█████████▋| 55885/57600 [9:50:17<17:54,  1.60it/s]
 97%|█████████▋| 55886/57600 [9:50:18<17:33,  1.63it/s]
 97%|█████████▋| 55887/57600 [9:50:18<17:37,  1.62it/s]
 97%|█████████▋| 55888/57600 [9:50:19<17:04,  1.67it/s]
 97%|█████████▋| 55889/57600 [9:50:20<17:47,  1.60it/s]
 97%|█████████▋| 55890/57600 [9:50:20<17:58,  1.59it/s]
 97%|█████████▋| 55891/57600 [9:50:21<18:19,  1.55it/s]
 97%|█████████▋| 55892/57600 [9:50:22<18:52,  1.51it/s]
 97%|█████████▋| 55893/57600 [9:50:22<18:15,  1.56it/s]
 97%|█████████▋| 55894/57600 [9:50:23<17:30,  1.62it/s]
 97%|█████████▋| 55895/57600 [9:50:23<16:59,  1.67it/s]
 97%|█████████▋| 55896/57600 [9:50:24<16:57,  1.67it/s]
 97%|█████████▋| 55897/57600 [9:50:25<17:29,  1.62it/s]
 97%|█████████▋| 55898/57600 [9:50:25<16:52,  1.68it/s]
 97%|█████████▋| 55899/57600 [9:50:26<16:40,  1.70it/s]
 97%|█████████▋| 55900/57600 [9:50:26<16:53,  1.68it/s]
                                                       
{'loss': 1.1172, 'learning_rate': 1.2665505226480833e-07, 'epoch': 617.0}

 97%|█████████▋| 55900/57600 [9:50:26<16:53,  1.68it/s]
 97%|█████████▋| 55901/57600 [9:50:27<17:37,  1.61it/s]
 97%|█████████▋| 55902/57600 [9:50:28<17:22,  1.63it/s]
 97%|█████████▋| 55903/57600 [9:50:28<17:14,  1.64it/s]
 97%|█████████▋| 55904/57600 [9:50:29<17:10,  1.65it/s]
 97%|█████████▋| 55905/57600 [9:50:29<17:11,  1.64it/s]
 97%|█████████▋| 55906/57600 [9:50:30<17:15,  1.64it/s]
 97%|█████████▋| 55907/57600 [9:50:31<17:40,  1.60it/s]
 97%|█████████▋| 55908/57600 [9:50:31<17:54,  1.57it/s]
 97%|█████████▋| 55909/57600 [9:50:32<17:48,  1.58it/s]
 97%|█████████▋| 55910/57600 [9:50:33<17:52,  1.58it/s]
 97%|█████████▋| 55911/57600 [9:50:33<17:26,  1.61it/s]
 97%|█████████▋| 55912/57600 [9:50:34<17:24,  1.62it/s]
 97%|█████████▋| 55913/57600 [9:50:34<17:53,  1.57it/s]
 97%|█████████▋| 55914/57600 [9:50:35<18:20,  1.53it/s]
 97%|█████████▋| 55915/57600 [9:50:36<18:21,  1.53it/s]
 97%|█████████▋| 55916/57600 [9:50:36<18:02,  1.56it/s]
 97%|█████████▋| 55917/57600 [9:50:37<17:28,  1.61it/s]
 97%|█████████▋| 55918/57600 [9:50:38<16:45,  1.67it/s]
 97%|█████████▋| 55919/57600 [9:50:38<16:49,  1.67it/s]
 97%|█████████▋| 55920/57600 [9:50:39<17:03,  1.64it/s]
                                                       
{'loss': 1.1392, 'learning_rate': 1.2634146341463416e-07, 'epoch': 617.22}

 97%|█████████▋| 55920/57600 [9:50:39<17:03,  1.64it/s]
 97%|█████████▋| 55921/57600 [9:50:39<17:10,  1.63it/s]
 97%|█████████▋| 55922/57600 [9:50:40<17:15,  1.62it/s]
 97%|█████████▋| 55923/57600 [9:50:41<17:00,  1.64it/s]
 97%|█████████▋| 55924/57600 [9:50:41<16:55,  1.65it/s]
 97%|█████████▋| 55925/57600 [9:50:42<17:44,  1.57it/s]
 97%|█████████▋| 55926/57600 [9:50:43<17:47,  1.57it/s]
 97%|█████████▋| 55927/57600 [9:50:43<17:38,  1.58it/s]
 97%|█████████▋| 55928/57600 [9:50:44<17:07,  1.63it/s]
 97%|█████████▋| 55929/57600 [9:50:44<16:59,  1.64it/s]
 97%|█████████▋| 55930/57600 [9:50:45<16:41,  1.67it/s]
 97%|█████████▋| 55931/57600 [9:50:46<17:17,  1.61it/s]
 97%|█████████▋| 55932/57600 [9:50:46<17:15,  1.61it/s]
 97%|█████████▋| 55933/57600 [9:50:47<17:18,  1.61it/s]
 97%|█████████▋| 55934/57600 [9:50:47<16:59,  1.63it/s]
 97%|█████████▋| 55935/57600 [9:50:48<16:54,  1.64it/s]
 97%|█████████▋| 55936/57600 [9:50:49<17:11,  1.61it/s]
 97%|█████████▋| 55937/57600 [9:50:49<17:21,  1.60it/s]
 97%|█████████▋| 55938/57600 [9:50:50<17:28,  1.58it/s]
 97%|█████████▋| 55939/57600 [9:50:51<16:58,  1.63it/s]
 97%|█████████▋| 55940/57600 [9:50:51<17:17,  1.60it/s]
                                                       
{'loss': 1.0899, 'learning_rate': 1.2602787456445989e-07, 'epoch': 617.44}

 97%|█████████▋| 55940/57600 [9:50:51<17:17,  1.60it/s]
 97%|█████████▋| 55941/57600 [9:50:52<17:09,  1.61it/s]
 97%|█████████▋| 55942/57600 [9:50:52<16:36,  1.66it/s]
 97%|█████████▋| 55943/57600 [9:50:53<17:09,  1.61it/s]
 97%|█████████▋| 55944/57600 [9:50:54<17:38,  1.56it/s]
 97%|█████████▋| 55945/57600 [9:50:54<17:16,  1.60it/s]
 97%|█████████▋| 55946/57600 [9:50:55<17:33,  1.57it/s]
 97%|█████████▋| 55947/57600 [9:50:56<17:39,  1.56it/s]
 97%|█████████▋| 55948/57600 [9:50:56<17:50,  1.54it/s]
 97%|█████████▋| 55949/57600 [9:50:57<18:18,  1.50it/s]
 97%|█████████▋| 55950/57600 [9:50:58<17:52,  1.54it/s]
 97%|█████████▋| 55951/57600 [9:50:58<17:17,  1.59it/s]
 97%|█████████▋| 55952/57600 [9:50:59<17:30,  1.57it/s]
 97%|█████████▋| 55953/57600 [9:50:59<17:09,  1.60it/s]
 97%|█████████▋| 55954/57600 [9:51:00<16:54,  1.62it/s]
 97%|█████████▋| 55955/57600 [9:51:01<17:03,  1.61it/s]
 97%|█████████▋| 55956/57600 [9:51:01<17:10,  1.59it/s]
 97%|█████████▋| 55957/57600 [9:51:02<16:47,  1.63it/s]
 97%|█████████▋| 55958/57600 [9:51:03<17:03,  1.60it/s]
 97%|█████████▋| 55959/57600 [9:51:03<17:25,  1.57it/s]
 97%|█████████▋| 55960/57600 [9:51:04<17:30,  1.56it/s]
                                                       
{'loss': 1.0693, 'learning_rate': 1.2571428571428572e-07, 'epoch': 617.66}

 97%|█████████▋| 55960/57600 [9:51:04<17:30,  1.56it/s]
 97%|█████████▋| 55961/57600 [9:51:04<17:12,  1.59it/s]
 97%|█████████▋| 55962/57600 [9:51:05<17:20,  1.57it/s]
 97%|█████████▋| 55963/57600 [9:51:06<17:41,  1.54it/s]
 97%|█████████▋| 55964/57600 [9:51:06<17:01,  1.60it/s]
 97%|█████████▋| 55965/57600 [9:51:07<17:02,  1.60it/s]
 97%|█████████▋| 55966/57600 [9:51:08<17:16,  1.58it/s]
 97%|█████████▋| 55967/57600 [9:51:08<16:58,  1.60it/s]
 97%|█████████▋| 55968/57600 [9:51:09<16:37,  1.64it/s]
 97%|█████████▋| 55969/57600 [9:51:09<16:11,  1.68it/s]
 97%|█████████▋| 55970/57600 [9:51:10<17:02,  1.59it/s]
 97%|█████████▋| 55971/57600 [9:51:11<16:34,  1.64it/s]
 97%|█████████▋| 55972/57600 [9:51:11<16:34,  1.64it/s]
 97%|█████████▋| 55973/57600 [9:51:12<17:05,  1.59it/s]
 97%|█████████▋| 55974/57600 [9:51:13<17:16,  1.57it/s]
 97%|█████████▋| 55975/57600 [9:51:13<16:44,  1.62it/s]
 97%|█████████▋| 55976/57600 [9:51:14<17:06,  1.58it/s]
 97%|█████████▋| 55977/57600 [9:51:14<17:06,  1.58it/s]
 97%|█████████▋| 55978/57600 [9:51:15<16:22,  1.65it/s]
 97%|█████████▋| 55979/57600 [9:51:16<16:16,  1.66it/s]
 97%|█████████▋| 55980/57600 [9:51:16<16:35,  1.63it/s]
                                                       
{'loss': 1.0865, 'learning_rate': 1.2540069686411144e-07, 'epoch': 617.88}

 97%|█████████▋| 55980/57600 [9:51:16<16:35,  1.63it/s]
 97%|█████████▋| 55981/57600 [9:51:17<16:58,  1.59it/s]
 97%|█████████▋| 55982/57600 [9:51:17<16:22,  1.65it/s]
 97%|█████████▋| 55983/57600 [9:51:18<15:57,  1.69it/s]
 97%|█████████▋| 55984/57600 [9:51:19<16:00,  1.68it/s]
 97%|█████████▋| 55985/57600 [9:51:19<16:13,  1.66it/s]
 97%|█████████▋| 55986/57600 [9:51:20<15:59,  1.68it/s]
 97%|█████████▋| 55987/57600 [9:51:20<16:09,  1.66it/s]
 97%|█████████▋| 55988/57600 [9:51:21<16:46,  1.60it/s]
 97%|█████████▋| 55989/57600 [9:51:22<17:06,  1.57it/s]
 97%|█████████▋| 55990/57600 [9:51:22<16:46,  1.60it/s]
 97%|█████████▋| 55991/57600 [9:51:23<17:31,  1.53it/s]
 97%|█████████▋| 55992/57600 [9:51:24<17:01,  1.57it/s]
 97%|█████████▋| 55993/57600 [9:51:24<16:27,  1.63it/s]
 97%|█████████▋| 55994/57600 [9:51:25<16:48,  1.59it/s]
 97%|█████████▋| 55995/57600 [9:51:25<16:30,  1.62it/s]
 97%|█████████▋| 55996/57600 [9:51:26<16:58,  1.57it/s]
 97%|█████████▋| 55997/57600 [9:51:27<16:47,  1.59it/s]
 97%|█████████▋| 55998/57600 [9:51:27<16:33,  1.61it/s]
 97%|█████████▋| 55999/57600 [9:51:28<16:44,  1.59it/s]
 97%|█████████▋| 56000/57600 [9:51:29<16:07,  1.65it/s]
                                                       
{'loss': 1.1116, 'learning_rate': 1.2508710801393727e-07, 'epoch': 618.1}

 97%|█████████▋| 56000/57600 [9:51:29<16:07,  1.65it/s]
 97%|█████████▋| 56001/57600 [9:51:29<15:47,  1.69it/s]
 97%|█████████▋| 56002/57600 [9:51:30<15:47,  1.69it/s]
 97%|█████████▋| 56003/57600 [9:51:30<16:09,  1.65it/s]
 97%|█████████▋| 56004/57600 [9:51:31<16:08,  1.65it/s]
 97%|█████████▋| 56005/57600 [9:51:32<16:24,  1.62it/s]
 97%|█████████▋| 56006/57600 [9:51:32<16:17,  1.63it/s]
 97%|█████████▋| 56007/57600 [9:51:33<16:39,  1.59it/s]
 97%|█████████▋| 56008/57600 [9:51:33<16:20,  1.62it/s]
 97%|█████████▋| 56009/57600 [9:51:34<16:09,  1.64it/s]
 97%|█████████▋| 56010/57600 [9:51:35<15:44,  1.68it/s]
 97%|█████████▋| 56011/57600 [9:51:35<16:06,  1.64it/s]
 97%|█████████▋| 56012/57600 [9:51:36<16:10,  1.64it/s]
 97%|█████████▋| 56013/57600 [9:51:36<16:01,  1.65it/s]
 97%|█████████▋| 56014/57600 [9:51:37<15:54,  1.66it/s]
 97%|█████████▋| 56015/57600 [9:51:38<15:45,  1.68it/s]
 97%|█████████▋| 56016/57600 [9:51:38<17:24,  1.52it/s]
 97%|█████████▋| 56017/57600 [9:51:39<17:23,  1.52it/s]
 97%|█████████▋| 56018/57600 [9:51:40<17:10,  1.54it/s]
 97%|█████████▋| 56019/57600 [9:51:40<16:38,  1.58it/s]
 97%|█████████▋| 56020/57600 [9:51:41<16:55,  1.56it/s]
                                                       
{'loss': 1.0897, 'learning_rate': 1.247735191637631e-07, 'epoch': 618.32}

 97%|█████████▋| 56020/57600 [9:51:41<16:55,  1.56it/s]
 97%|█████████▋| 56021/57600 [9:51:42<16:35,  1.59it/s]
 97%|█████████▋| 56022/57600 [9:51:42<16:40,  1.58it/s]
 97%|█████████▋| 56023/57600 [9:51:43<16:15,  1.62it/s]
 97%|█████████▋| 56024/57600 [9:51:43<16:20,  1.61it/s]
 97%|█████████▋| 56025/57600 [9:51:44<15:59,  1.64it/s]
 97%|█████████▋| 56026/57600 [9:51:45<16:03,  1.63it/s]
 97%|█████████▋| 56027/57600 [9:51:45<16:39,  1.57it/s]
 97%|█████████▋| 56028/57600 [9:51:46<16:43,  1.57it/s]
 97%|█████████▋| 56029/57600 [9:51:47<16:22,  1.60it/s]
 97%|█████████▋| 56030/57600 [9:51:47<16:28,  1.59it/s]
 97%|█████████▋| 56031/57600 [9:51:48<16:46,  1.56it/s]
 97%|█████████▋| 56032/57600 [9:51:49<17:12,  1.52it/s]
 97%|█████████▋| 56033/57600 [9:51:49<17:45,  1.47it/s]
 97%|█████████▋| 56034/57600 [9:51:50<17:18,  1.51it/s]
 97%|█████████▋| 56035/57600 [9:51:51<16:47,  1.55it/s]
 97%|█████████▋| 56036/57600 [9:51:51<16:36,  1.57it/s]
 97%|█████████▋| 56037/57600 [9:51:52<16:26,  1.59it/s]
 97%|█████████▋| 56038/57600 [9:51:52<16:19,  1.60it/s]
 97%|█████████▋| 56039/57600 [9:51:53<16:20,  1.59it/s]
 97%|█████████▋| 56040/57600 [9:51:54<16:51,  1.54it/s]
                                                       
{'loss': 1.104, 'learning_rate': 1.2445993031358883e-07, 'epoch': 618.54}

 97%|█████████▋| 56040/57600 [9:51:54<16:51,  1.54it/s]
 97%|█████████▋| 56041/57600 [9:51:54<16:48,  1.55it/s]
 97%|█████████▋| 56042/57600 [9:51:55<17:14,  1.51it/s]
 97%|█████████▋| 56043/57600 [9:51:56<16:53,  1.54it/s]
 97%|█████████▋| 56044/57600 [9:51:56<16:56,  1.53it/s]
 97%|█████████▋| 56045/57600 [9:51:57<16:19,  1.59it/s]
 97%|█████████▋| 56046/57600 [9:51:58<15:56,  1.62it/s]
 97%|█████████▋| 56047/57600 [9:51:58<15:57,  1.62it/s]
 97%|█████████▋| 56048/57600 [9:51:59<16:02,  1.61it/s]
 97%|█████████▋| 56049/57600 [9:51:59<16:04,  1.61it/s]
 97%|█████████▋| 56050/57600 [9:52:00<16:15,  1.59it/s]
 97%|█████████▋| 56051/57600 [9:52:01<15:57,  1.62it/s]
 97%|█████████▋| 56052/57600 [9:52:01<16:00,  1.61it/s]
 97%|█████████▋| 56053/57600 [9:52:02<16:22,  1.57it/s]
 97%|█████████▋| 56054/57600 [9:52:03<16:06,  1.60it/s]
 97%|█████████▋| 56055/57600 [9:52:03<16:34,  1.55it/s]
 97%|█████████▋| 56056/57600 [9:52:04<16:25,  1.57it/s]
 97%|█████████▋| 56057/57600 [9:52:04<16:18,  1.58it/s]
 97%|█████████▋| 56058/57600 [9:52:05<16:13,  1.58it/s]
 97%|█████████▋| 56059/57600 [9:52:06<16:17,  1.58it/s]
 97%|█████████▋| 56060/57600 [9:52:06<16:03,  1.60it/s]
                                                       
{'loss': 1.0987, 'learning_rate': 1.2414634146341466e-07, 'epoch': 618.76}

 97%|█████████▋| 56060/57600 [9:52:06<16:03,  1.60it/s]
 97%|█████████▋| 56061/57600 [9:52:07<16:33,  1.55it/s]
 97%|█████████▋| 56062/57600 [9:52:08<16:12,  1.58it/s]
 97%|█████████▋| 56063/57600 [9:52:08<16:09,  1.59it/s]
 97%|█████████▋| 56064/57600 [9:52:09<16:05,  1.59it/s]
 97%|█████████▋| 56065/57600 [9:52:09<15:41,  1.63it/s]
 97%|█████████▋| 56066/57600 [9:52:10<15:55,  1.60it/s]
 97%|█████████▋| 56067/57600 [9:52:11<16:03,  1.59it/s]
 97%|█████████▋| 56068/57600 [9:52:11<16:06,  1.58it/s]
 97%|█████████▋| 56069/57600 [9:52:12<15:59,  1.59it/s]
 97%|█████████▋| 56070/57600 [9:52:13<16:10,  1.58it/s]
 97%|█████████▋| 56071/57600 [9:52:13<16:22,  1.56it/s]
 97%|█████████▋| 56072/57600 [9:52:14<15:46,  1.61it/s]
 97%|█████████▋| 56073/57600 [9:52:15<15:55,  1.60it/s]
 97%|█████████▋| 56074/57600 [9:52:15<16:22,  1.55it/s]
 97%|█████████▋| 56075/57600 [9:52:16<16:21,  1.55it/s]
 97%|█████████▋| 56076/57600 [9:52:16<16:06,  1.58it/s]
 97%|█████████▋| 56077/57600 [9:52:17<15:42,  1.62it/s]
 97%|█████████▋| 56078/57600 [9:52:18<15:50,  1.60it/s]
 97%|█████████▋| 56079/57600 [9:52:18<15:51,  1.60it/s]
 97%|█████████▋| 56080/57600 [9:52:19<16:00,  1.58it/s]
                                                       
{'loss': 1.094, 'learning_rate': 1.238327526132404e-07, 'epoch': 618.98}

 97%|█████████▋| 56080/57600 [9:52:19<16:00,  1.58it/s]
 97%|█████████▋| 56081/57600 [9:52:20<15:58,  1.58it/s]
 97%|█████████▋| 56082/57600 [9:52:20<16:56,  1.49it/s]
 97%|█████████▋| 56083/57600 [9:52:21<16:36,  1.52it/s]
 97%|█████████▋| 56084/57600 [9:52:22<17:03,  1.48it/s]
 97%|█████████▋| 56085/57600 [9:52:22<16:12,  1.56it/s]
 97%|█████████▋| 56086/57600 [9:52:23<15:54,  1.59it/s]
 97%|█████████▋| 56087/57600 [9:52:23<15:42,  1.60it/s]
 97%|█████████▋| 56088/57600 [9:52:24<15:39,  1.61it/s]
 97%|█████████▋| 56089/57600 [9:52:25<15:18,  1.64it/s]
 97%|█████████▋| 56090/57600 [9:52:25<15:30,  1.62it/s]
 97%|█████████▋| 56091/57600 [9:52:26<15:44,  1.60it/s]
 97%|█████████▋| 56092/57600 [9:52:27<15:49,  1.59it/s]
 97%|█████████▋| 56093/57600 [9:52:27<16:29,  1.52it/s]
 97%|█████████▋| 56094/57600 [9:52:28<16:18,  1.54it/s]
 97%|█████████▋| 56095/57600 [9:52:29<16:01,  1.57it/s]
 97%|█████████▋| 56096/57600 [9:52:29<15:53,  1.58it/s]
 97%|█████████▋| 56097/57600 [9:52:30<16:08,  1.55it/s]
 97%|█████████▋| 56098/57600 [9:52:30<15:56,  1.57it/s]
 97%|█████████▋| 56099/57600 [9:52:31<15:53,  1.57it/s]
 97%|█████████▋| 56100/57600 [9:52:32<16:38,  1.50it/s]
                                                       
{'loss': 1.0933, 'learning_rate': 1.235191637630662e-07, 'epoch': 619.21}

 97%|█████████▋| 56100/57600 [9:52:32<16:38,  1.50it/s]
 97%|█████████▋| 56101/57600 [9:52:32<16:09,  1.55it/s]
 97%|█████████▋| 56102/57600 [9:52:33<16:16,  1.53it/s]
 97%|█████████▋| 56103/57600 [9:52:34<16:04,  1.55it/s]
 97%|█████████▋| 56104/57600 [9:52:34<16:24,  1.52it/s]
 97%|█████████▋| 56105/57600 [9:52:35<16:25,  1.52it/s]
 97%|█████████▋| 56106/57600 [9:52:36<16:39,  1.49it/s]
 97%|█████████▋| 56107/57600 [9:52:36<16:24,  1.52it/s]
 97%|█████████▋| 56108/57600 [9:52:37<16:42,  1.49it/s]
 97%|█████████▋| 56109/57600 [9:52:38<16:18,  1.52it/s]
 97%|█████████▋| 56110/57600 [9:52:38<16:36,  1.50it/s]
 97%|█████████▋| 56111/57600 [9:52:39<15:54,  1.56it/s]
 97%|█████████▋| 56112/57600 [9:52:40<15:43,  1.58it/s]
 97%|█████████▋| 56113/57600 [9:52:40<15:58,  1.55it/s]
 97%|█████████▋| 56114/57600 [9:52:41<15:58,  1.55it/s]
 97%|█████████▋| 56115/57600 [9:52:42<15:39,  1.58it/s]
 97%|█████████▋| 56116/57600 [9:52:42<15:18,  1.62it/s]
 97%|█████████▋| 56117/57600 [9:52:43<15:19,  1.61it/s]
 97%|█████████▋| 56118/57600 [9:52:43<15:10,  1.63it/s]
 97%|█████████▋| 56119/57600 [9:52:44<15:18,  1.61it/s]
 97%|█████████▋| 56120/57600 [9:52:45<15:37,  1.58it/s]
                                                       
{'loss': 1.0618, 'learning_rate': 1.2320557491289202e-07, 'epoch': 619.43}

 97%|█████████▋| 56120/57600 [9:52:45<15:37,  1.58it/s]
 97%|█████████▋| 56121/57600 [9:52:45<14:56,  1.65it/s]
 97%|█████████▋| 56122/57600 [9:52:46<15:04,  1.63it/s]
 97%|█████████▋| 56123/57600 [9:52:46<15:28,  1.59it/s]
 97%|█████████▋| 56124/57600 [9:52:47<15:36,  1.58it/s]
 97%|█████████▋| 56125/57600 [9:52:48<15:31,  1.58it/s]
 97%|█████████▋| 56126/57600 [9:52:48<15:31,  1.58it/s]
 97%|█████████▋| 56127/57600 [9:52:49<15:20,  1.60it/s]
 97%|█████████▋| 56128/57600 [9:52:50<14:58,  1.64it/s]
 97%|█████████▋| 56129/57600 [9:52:50<14:39,  1.67it/s]
 97%|█████████▋| 56130/57600 [9:52:51<14:29,  1.69it/s]
 97%|█████████▋| 56131/57600 [9:52:51<14:50,  1.65it/s]
 97%|█████████▋| 56132/57600 [9:52:52<14:46,  1.66it/s]
 97%|█████████▋| 56133/57600 [9:52:53<14:48,  1.65it/s]
 97%|█████████▋| 56134/57600 [9:52:53<14:59,  1.63it/s]
 97%|█████████▋| 56135/57600 [9:52:54<14:33,  1.68it/s]
 97%|█████████▋| 56136/57600 [9:52:54<14:42,  1.66it/s]
 97%|█████████▋| 56137/57600 [9:52:55<14:33,  1.68it/s]
 97%|█████████▋| 56138/57600 [9:52:56<14:30,  1.68it/s]
 97%|█████████▋| 56139/57600 [9:52:56<14:45,  1.65it/s]
 97%|█████████▋| 56140/57600 [9:52:57<15:08,  1.61it/s]
                                                       
{'loss': 1.1347, 'learning_rate': 1.2289198606271775e-07, 'epoch': 619.65}

 97%|█████████▋| 56140/57600 [9:52:57<15:08,  1.61it/s]
 97%|█████████▋| 56141/57600 [9:52:58<15:38,  1.55it/s]
 97%|█████████▋| 56142/57600 [9:52:58<16:03,  1.51it/s]
 97%|█████████▋| 56143/57600 [9:52:59<15:33,  1.56it/s]
 97%|█████████▋| 56144/57600 [9:52:59<15:20,  1.58it/s]
 97%|█████████▋| 56145/57600 [9:53:00<14:57,  1.62it/s]
 97%|█████████▋| 56146/57600 [9:53:01<14:55,  1.62it/s]
 97%|█████████▋| 56147/57600 [9:53:01<14:52,  1.63it/s]
 97%|█████████▋| 56148/57600 [9:53:02<14:59,  1.61it/s]
 97%|█████████▋| 56149/57600 [9:53:03<15:09,  1.60it/s]
 97%|█████████▋| 56150/57600 [9:53:03<14:49,  1.63it/s]
 97%|█████████▋| 56151/57600 [9:53:04<15:25,  1.57it/s]
 97%|█████████▋| 56152/57600 [9:53:04<14:53,  1.62it/s]
 97%|█████████▋| 56153/57600 [9:53:05<14:38,  1.65it/s]
 97%|█████████▋| 56154/57600 [9:53:06<14:47,  1.63it/s]
 97%|█████████▋| 56155/57600 [9:53:06<14:38,  1.64it/s]
 97%|█████████▋| 56156/57600 [9:53:07<15:20,  1.57it/s]
 97%|█████████▋| 56157/57600 [9:53:07<14:56,  1.61it/s]
 97%|█████████▋| 56158/57600 [9:53:08<14:27,  1.66it/s]
 97%|█████████▋| 56159/57600 [9:53:09<14:20,  1.67it/s]
 98%|█████████▊| 56160/57600 [9:53:09<14:17,  1.68it/s]
                                                       
{'loss': 1.0924, 'learning_rate': 1.2257839721254358e-07, 'epoch': 619.87}

 98%|█████████▊| 56160/57600 [9:53:09<14:17,  1.68it/s]
 98%|█████████▊| 56161/57600 [9:53:10<14:05,  1.70it/s]
 98%|█████████▊| 56162/57600 [9:53:10<14:28,  1.66it/s]
 98%|█████████▊| 56163/57600 [9:53:11<14:11,  1.69it/s]
 98%|█████████▊| 56164/57600 [9:53:12<14:09,  1.69it/s]
 98%|█████████▊| 56165/57600 [9:53:12<14:02,  1.70it/s]
 98%|█████████▊| 56166/57600 [9:53:13<14:02,  1.70it/s]
 98%|█████████▊| 56167/57600 [9:53:13<14:37,  1.63it/s]
 98%|█████████▊| 56168/57600 [9:53:14<14:43,  1.62it/s]
 98%|█████████▊| 56169/57600 [9:53:15<14:59,  1.59it/s]
 98%|█████████▊| 56170/57600 [9:53:15<15:00,  1.59it/s]
 98%|█████████▊| 56171/57600 [9:53:16<15:11,  1.57it/s]
 98%|█████████▊| 56172/57600 [9:53:17<15:01,  1.58it/s]
 98%|█████████▊| 56173/57600 [9:53:17<15:27,  1.54it/s]
 98%|█████████▊| 56174/57600 [9:53:18<15:13,  1.56it/s]
 98%|█████████▊| 56175/57600 [9:53:19<15:16,  1.55it/s]
 98%|█████████▊| 56176/57600 [9:53:19<14:49,  1.60it/s]
 98%|█████████▊| 56177/57600 [9:53:20<15:18,  1.55it/s]
 98%|█████████▊| 56178/57600 [9:53:20<14:43,  1.61it/s]
 98%|█████████▊| 56179/57600 [9:53:21<15:06,  1.57it/s]
 98%|█████████▊| 56180/57600 [9:53:22<14:38,  1.62it/s]
                                                       
{'loss': 1.0804, 'learning_rate': 1.222648083623693e-07, 'epoch': 620.09}

 98%|█████████▊| 56180/57600 [9:53:22<14:38,  1.62it/s]
 98%|█████████▊| 56181/57600 [9:53:22<14:24,  1.64it/s]
 98%|█████████▊| 56182/57600 [9:53:23<14:25,  1.64it/s]
 98%|█████████▊| 56183/57600 [9:53:23<14:29,  1.63it/s]
 98%|█████████▊| 56184/57600 [9:53:24<14:25,  1.64it/s]
 98%|█████████▊| 56185/57600 [9:53:25<14:37,  1.61it/s]
 98%|█████████▊| 56186/57600 [9:53:25<14:55,  1.58it/s]
 98%|█████████▊| 56187/57600 [9:53:26<15:23,  1.53it/s]
 98%|█████████▊| 56188/57600 [9:53:27<15:15,  1.54it/s]
 98%|█████████▊| 56189/57600 [9:53:27<14:55,  1.58it/s]
 98%|█████████▊| 56190/57600 [9:53:28<15:58,  1.47it/s]
 98%|█████████▊| 56191/57600 [9:53:29<16:00,  1.47it/s]
 98%|█████████▊| 56192/57600 [9:53:29<15:30,  1.51it/s]
 98%|█████████▊| 56193/57600 [9:53:30<15:31,  1.51it/s]
 98%|█████████▊| 56194/57600 [9:53:31<15:59,  1.46it/s]
 98%|█████████▊| 56195/57600 [9:53:31<15:56,  1.47it/s]
 98%|█████████▊| 56196/57600 [9:53:32<15:20,  1.52it/s]
 98%|█████████▊| 56197/57600 [9:53:33<14:46,  1.58it/s]
 98%|█████████▊| 56198/57600 [9:53:33<14:57,  1.56it/s]
 98%|█████████▊| 56199/57600 [9:53:34<15:16,  1.53it/s]
 98%|█████████▊| 56200/57600 [9:53:35<15:03,  1.55it/s]
                                                       
{'loss': 1.0635, 'learning_rate': 1.2195121951219514e-07, 'epoch': 620.31}

 98%|█████████▊| 56200/57600 [9:53:35<15:03,  1.55it/s]
 98%|█████████▊| 56201/57600 [9:53:35<14:55,  1.56it/s]
 98%|█████████▊| 56202/57600 [9:53:36<14:48,  1.57it/s]
 98%|█████████▊| 56203/57600 [9:53:36<14:36,  1.59it/s]
 98%|█████████▊| 56204/57600 [9:53:37<14:20,  1.62it/s]
 98%|█████████▊| 56205/57600 [9:53:38<14:14,  1.63it/s]
 98%|█████████▊| 56206/57600 [9:53:38<14:27,  1.61it/s]
 98%|█████████▊| 56207/57600 [9:53:39<14:17,  1.62it/s]
 98%|█████████▊| 56208/57600 [9:53:40<14:23,  1.61it/s]
 98%|█████████▊| 56209/57600 [9:53:40<14:33,  1.59it/s]
 98%|█████████▊| 56210/57600 [9:53:41<14:45,  1.57it/s]
 98%|█████████▊| 56211/57600 [9:53:41<14:34,  1.59it/s]
 98%|█████████▊| 56212/57600 [9:53:42<14:46,  1.57it/s]
 98%|█████████▊| 56213/57600 [9:53:43<14:15,  1.62it/s]
 98%|█████████▊| 56214/57600 [9:53:43<14:18,  1.61it/s]
 98%|█████████▊| 56215/57600 [9:53:44<13:58,  1.65it/s]
 98%|█████████▊| 56216/57600 [9:53:44<13:41,  1.69it/s]
 98%|█████████▊| 56217/57600 [9:53:45<13:46,  1.67it/s]
 98%|█████████▊| 56218/57600 [9:53:46<14:24,  1.60it/s]
 98%|█████████▊| 56219/57600 [9:53:46<14:02,  1.64it/s]
 98%|█████████▊| 56220/57600 [9:53:47<13:53,  1.66it/s]
                                                       
{'loss': 1.1245, 'learning_rate': 1.2163763066202086e-07, 'epoch': 620.53}

 98%|█████████▊| 56220/57600 [9:53:47<13:53,  1.66it/s]
 98%|█████████▊| 56221/57600 [9:53:48<13:57,  1.65it/s]
 98%|█████████▊| 56222/57600 [9:53:48<14:02,  1.64it/s]
 98%|█████████▊| 56223/57600 [9:53:49<14:20,  1.60it/s]
 98%|█████████▊| 56224/57600 [9:53:49<14:13,  1.61it/s]
 98%|█████████▊| 56225/57600 [9:53:50<13:54,  1.65it/s]
 98%|█████████▊| 56226/57600 [9:53:51<13:55,  1.64it/s]
 98%|█████████▊| 56227/57600 [9:53:51<13:43,  1.67it/s]
 98%|█████████▊| 56228/57600 [9:53:52<13:25,  1.70it/s]
 98%|█████████▊| 56229/57600 [9:53:52<13:28,  1.70it/s]
 98%|█████████▊| 56230/57600 [9:53:53<13:39,  1.67it/s]
 98%|█████████▊| 56231/57600 [9:53:54<13:37,  1.67it/s]
 98%|█████████▊| 56232/57600 [9:53:54<13:52,  1.64it/s]
 98%|█████████▊| 56233/57600 [9:53:55<14:01,  1.62it/s]
 98%|█████████▊| 56234/57600 [9:53:55<13:46,  1.65it/s]
 98%|█████████▊| 56235/57600 [9:53:56<13:37,  1.67it/s]
 98%|█████████▊| 56236/57600 [9:53:57<13:33,  1.68it/s]
 98%|█████████▊| 56237/57600 [9:53:57<13:43,  1.66it/s]
 98%|█████████▊| 56238/57600 [9:53:58<14:11,  1.60it/s]
 98%|█████████▊| 56239/57600 [9:53:58<14:09,  1.60it/s]
 98%|█████████▊| 56240/57600 [9:53:59<13:55,  1.63it/s]
                                                       
{'loss': 1.095, 'learning_rate': 1.213240418118467e-07, 'epoch': 620.75}

 98%|█████████▊| 56240/57600 [9:53:59<13:55,  1.63it/s]
 98%|█████████▊| 56241/57600 [9:54:00<13:51,  1.63it/s]
 98%|█████████▊| 56242/57600 [9:54:00<14:08,  1.60it/s]
 98%|█████████▊| 56243/57600 [9:54:01<14:24,  1.57it/s]
 98%|█████████▊| 56244/57600 [9:54:02<14:32,  1.55it/s]
 98%|█████████▊| 56245/57600 [9:54:02<14:17,  1.58it/s]
 98%|█████████▊| 56246/57600 [9:54:03<13:58,  1.61it/s]
 98%|█████████▊| 56247/57600 [9:54:03<13:40,  1.65it/s]
 98%|█████████▊| 56248/57600 [9:54:04<13:38,  1.65it/s]
 98%|█████████▊| 56249/57600 [9:54:05<13:49,  1.63it/s]
 98%|█████████▊| 56250/57600 [9:54:05<13:49,  1.63it/s]
 98%|█████████▊| 56251/57600 [9:54:06<14:00,  1.60it/s]
 98%|█████████▊| 56252/57600 [9:54:07<14:36,  1.54it/s]
 98%|█████████▊| 56253/57600 [9:54:07<14:28,  1.55it/s]
 98%|█████████▊| 56254/57600 [9:54:08<14:38,  1.53it/s]
 98%|█████████▊| 56255/57600 [9:54:09<14:08,  1.58it/s]
 98%|█████████▊| 56256/57600 [9:54:09<13:42,  1.63it/s]
 98%|█████████▊| 56257/57600 [9:54:10<13:32,  1.65it/s]
 98%|█████████▊| 56258/57600 [9:54:10<13:40,  1.63it/s]
 98%|█████████▊| 56259/57600 [9:54:11<13:15,  1.69it/s]
 98%|█████████▊| 56260/57600 [9:54:11<13:07,  1.70it/s]
                                                       
{'loss': 1.1048, 'learning_rate': 1.2101045296167253e-07, 'epoch': 620.97}

 98%|█████████▊| 56260/57600 [9:54:11<13:07,  1.70it/s]
 98%|█████████▊| 56261/57600 [9:54:12<13:47,  1.62it/s]
 98%|█████████▊| 56262/57600 [9:54:13<14:27,  1.54it/s]
 98%|█████████▊| 56263/57600 [9:54:14<14:36,  1.53it/s]
 98%|█████████▊| 56264/57600 [9:54:14<14:17,  1.56it/s]
 98%|█████████▊| 56265/57600 [9:54:15<14:33,  1.53it/s]
 98%|█████████▊| 56266/57600 [9:54:15<14:25,  1.54it/s]
 98%|█████████▊| 56267/57600 [9:54:16<13:48,  1.61it/s]
 98%|█████████▊| 56268/57600 [9:54:17<13:49,  1.61it/s]
 98%|█████████▊| 56269/57600 [9:54:17<13:49,  1.60it/s]
 98%|█████████▊| 56270/57600 [9:54:18<13:35,  1.63it/s]
 98%|█████████▊| 56271/57600 [9:54:19<13:58,  1.58it/s]
 98%|█████████▊| 56272/57600 [9:54:19<14:11,  1.56it/s]
 98%|█████████▊| 56273/57600 [9:54:20<13:38,  1.62it/s]
 98%|█████████▊| 56274/57600 [9:54:20<13:54,  1.59it/s]
 98%|█████████▊| 56275/57600 [9:54:21<14:09,  1.56it/s]
 98%|█████████▊| 56276/57600 [9:54:22<13:43,  1.61it/s]
 98%|█████████▊| 56277/57600 [9:54:22<13:48,  1.60it/s]
 98%|█████████▊| 56278/57600 [9:54:23<14:07,  1.56it/s]
 98%|█████████▊| 56279/57600 [9:54:24<14:11,  1.55it/s]
 98%|█████████▊| 56280/57600 [9:54:24<13:47,  1.60it/s]
                                                       
{'loss': 1.0711, 'learning_rate': 1.2069686411149825e-07, 'epoch': 621.19}

 98%|█████████▊| 56280/57600 [9:54:24<13:47,  1.60it/s]
 98%|█████████▊| 56281/57600 [9:54:25<13:34,  1.62it/s]
 98%|█████████▊| 56282/57600 [9:54:25<13:26,  1.63it/s]
 98%|█████████▊| 56283/57600 [9:54:26<13:20,  1.64it/s]
 98%|█████████▊| 56284/57600 [9:54:27<13:46,  1.59it/s]
 98%|█████████▊| 56285/57600 [9:54:27<13:39,  1.61it/s]
 98%|█████████▊| 56286/57600 [9:54:28<13:34,  1.61it/s]
 98%|█████████▊| 56287/57600 [9:54:28<13:27,  1.63it/s]
 98%|█████████▊| 56288/57600 [9:54:29<14:27,  1.51it/s]
 98%|█████████▊| 56289/57600 [9:54:30<14:14,  1.53it/s]
 98%|█████████▊| 56290/57600 [9:54:31<14:05,  1.55it/s]
 98%|█████████▊| 56291/57600 [9:54:31<14:01,  1.56it/s]
 98%|█████████▊| 56292/57600 [9:54:32<13:44,  1.59it/s]
 98%|█████████▊| 56293/57600 [9:54:32<13:25,  1.62it/s]
 98%|█████████▊| 56294/57600 [9:54:33<13:46,  1.58it/s]
 98%|█████████▊| 56295/57600 [9:54:34<13:58,  1.56it/s]
 98%|█████████▊| 56296/57600 [9:54:34<13:51,  1.57it/s]
 98%|█████████▊| 56297/57600 [9:54:35<13:46,  1.58it/s]
 98%|█████████▊| 56298/57600 [9:54:36<13:51,  1.57it/s]
 98%|█████████▊| 56299/57600 [9:54:36<13:55,  1.56it/s]
 98%|█████████▊| 56300/57600 [9:54:37<13:32,  1.60it/s]
                                                       
{'loss': 1.0852, 'learning_rate': 1.2038327526132406e-07, 'epoch': 621.41}

 98%|█████████▊| 56300/57600 [9:54:37<13:32,  1.60it/s]
 98%|█████████▊| 56301/57600 [9:54:37<13:06,  1.65it/s]
 98%|█████████▊| 56302/57600 [9:54:38<13:01,  1.66it/s]
 98%|█████████▊| 56303/57600 [9:54:39<13:23,  1.61it/s]
 98%|█████████▊| 56304/57600 [9:54:39<13:15,  1.63it/s]
 98%|█████████▊| 56305/57600 [9:54:40<13:17,  1.62it/s]
 98%|█████████▊| 56306/57600 [9:54:40<13:05,  1.65it/s]
 98%|█████████▊| 56307/57600 [9:54:41<13:10,  1.64it/s]
 98%|█████████▊| 56308/57600 [9:54:42<13:09,  1.64it/s]
 98%|█████████▊| 56309/57600 [9:54:42<13:12,  1.63it/s]
 98%|█████████▊| 56310/57600 [9:54:43<13:06,  1.64it/s]
 98%|█████████▊| 56311/57600 [9:54:44<13:56,  1.54it/s]
 98%|█████████▊| 56312/57600 [9:54:44<13:34,  1.58it/s]
 98%|█████████▊| 56313/57600 [9:54:45<13:05,  1.64it/s]
 98%|█████████▊| 56314/57600 [9:54:45<13:19,  1.61it/s]
 98%|█████████▊| 56315/57600 [9:54:46<13:32,  1.58it/s]
 98%|█████████▊| 56316/57600 [9:54:47<13:17,  1.61it/s]
 98%|█████████▊| 56317/57600 [9:54:47<12:55,  1.65it/s]
 98%|█████████▊| 56318/57600 [9:54:48<12:48,  1.67it/s]
 98%|█████████▊| 56319/57600 [9:54:48<13:11,  1.62it/s]
 98%|█████████▊| 56320/57600 [9:54:49<13:34,  1.57it/s]
                                                       
{'loss': 1.1443, 'learning_rate': 1.200696864111498e-07, 'epoch': 621.63}

 98%|█████████▊| 56320/57600 [9:54:49<13:34,  1.57it/s]
 98%|█████████▊| 56321/57600 [9:54:50<13:41,  1.56it/s]
 98%|█████████▊| 56322/57600 [9:54:50<13:12,  1.61it/s]
 98%|█████████▊| 56323/57600 [9:54:51<12:50,  1.66it/s]
 98%|█████████▊| 56324/57600 [9:54:52<12:55,  1.65it/s]
 98%|█████████▊| 56325/57600 [9:54:52<12:59,  1.64it/s]
 98%|█████████▊| 56326/57600 [9:54:53<12:44,  1.67it/s]
 98%|█████████▊| 56327/57600 [9:54:53<13:15,  1.60it/s]
 98%|█████████▊| 56328/57600 [9:54:54<13:19,  1.59it/s]
 98%|█████████▊| 56329/57600 [9:54:55<13:05,  1.62it/s]
 98%|█████████▊| 56330/57600 [9:54:55<12:39,  1.67it/s]
 98%|█████████▊| 56331/57600 [9:54:56<12:22,  1.71it/s]
 98%|█████████▊| 56332/57600 [9:54:56<12:59,  1.63it/s]
 98%|█████████▊| 56333/57600 [9:54:57<12:50,  1.65it/s]
 98%|█████████▊| 56334/57600 [9:54:58<12:26,  1.70it/s]
 98%|█████████▊| 56335/57600 [9:54:58<12:44,  1.66it/s]
 98%|█████████▊| 56336/57600 [9:54:59<12:39,  1.66it/s]
 98%|█████████▊| 56337/57600 [9:54:59<12:57,  1.62it/s]
 98%|█████████▊| 56338/57600 [9:55:00<12:51,  1.64it/s]
 98%|█████████▊| 56339/57600 [9:55:01<12:58,  1.62it/s]
 98%|█████████▊| 56340/57600 [9:55:01<13:01,  1.61it/s]
                                                       
{'loss': 1.098, 'learning_rate': 1.197560975609756e-07, 'epoch': 621.85}

 98%|█████████▊| 56340/57600 [9:55:01<13:01,  1.61it/s]
 98%|█████████▊| 56341/57600 [9:55:02<12:51,  1.63it/s]
 98%|█████████▊| 56342/57600 [9:55:03<13:04,  1.60it/s]
 98%|█████████▊| 56343/57600 [9:55:03<12:44,  1.64it/s]
 98%|█████████▊| 56344/57600 [9:55:04<12:55,  1.62it/s]
 98%|█████████▊| 56345/57600 [9:55:04<12:45,  1.64it/s]
 98%|█████████▊| 56346/57600 [9:55:05<12:43,  1.64it/s]
 98%|█████████▊| 56347/57600 [9:55:06<12:28,  1.67it/s]
 98%|█████████▊| 56348/57600 [9:55:06<12:27,  1.68it/s]
 98%|█████████▊| 56349/57600 [9:55:07<12:27,  1.67it/s]
 98%|█████████▊| 56350/57600 [9:55:07<13:04,  1.59it/s]
 98%|█████████▊| 56351/57600 [9:55:08<12:45,  1.63it/s]
 98%|█████████▊| 56352/57600 [9:55:09<12:34,  1.65it/s]
 98%|█████████▊| 56353/57600 [9:55:09<12:35,  1.65it/s]
 98%|█████████▊| 56354/57600 [9:55:10<13:13,  1.57it/s]
 98%|█████████▊| 56355/57600 [9:55:11<13:02,  1.59it/s]
 98%|█████████▊| 56356/57600 [9:55:11<12:53,  1.61it/s]
 98%|█████████▊| 56357/57600 [9:55:12<12:42,  1.63it/s]
 98%|█████████▊| 56358/57600 [9:55:12<12:43,  1.63it/s]
 98%|█████████▊| 56359/57600 [9:55:13<12:45,  1.62it/s]
 98%|█████████▊| 56360/57600 [9:55:14<12:39,  1.63it/s]
                                                       
{'loss': 1.1561, 'learning_rate': 1.1944250871080134e-07, 'epoch': 622.08}

 98%|█████████▊| 56360/57600 [9:55:14<12:39,  1.63it/s]
 98%|█████████▊| 56361/57600 [9:55:14<12:45,  1.62it/s]
 98%|█████████▊| 56362/57600 [9:55:15<12:59,  1.59it/s]
 98%|█████████▊| 56363/57600 [9:55:15<12:41,  1.63it/s]
 98%|█████████▊| 56364/57600 [9:55:16<12:53,  1.60it/s]
 98%|█████████▊| 56365/57600 [9:55:17<13:00,  1.58it/s]
 98%|█████████▊| 56366/57600 [9:55:17<13:16,  1.55it/s]
 98%|█████████▊| 56367/57600 [9:55:18<12:55,  1.59it/s]
 98%|█████████▊| 56368/57600 [9:55:19<13:13,  1.55it/s]
 98%|█████████▊| 56369/57600 [9:55:19<13:58,  1.47it/s]
 98%|█████████▊| 56370/57600 [9:55:20<13:16,  1.54it/s]
 98%|█████████▊| 56371/57600 [9:55:21<12:45,  1.60it/s]
 98%|█████████▊| 56372/57600 [9:55:21<12:25,  1.65it/s]
 98%|█████████▊| 56373/57600 [9:55:22<12:26,  1.64it/s]
 98%|█████████▊| 56374/57600 [9:55:22<12:27,  1.64it/s]
 98%|█████████▊| 56375/57600 [9:55:23<12:31,  1.63it/s]
 98%|█████████▊| 56376/57600 [9:55:24<12:21,  1.65it/s]
 98%|█████████▊| 56377/57600 [9:55:24<12:31,  1.63it/s]
 98%|█████████▊| 56378/57600 [9:55:25<12:53,  1.58it/s]
 98%|█████████▊| 56379/57600 [9:55:26<12:44,  1.60it/s]
 98%|█████████▊| 56380/57600 [9:55:26<12:40,  1.60it/s]
                                                       
{'loss': 1.0916, 'learning_rate': 1.1912891986062717e-07, 'epoch': 622.3}

 98%|█████████▊| 56380/57600 [9:55:26<12:40,  1.60it/s]
 98%|█████████▊| 56381/57600 [9:55:27<12:41,  1.60it/s]
 98%|█████████▊| 56382/57600 [9:55:27<12:23,  1.64it/s]
 98%|█████████▊| 56383/57600 [9:55:28<12:14,  1.66it/s]
 98%|█████████▊| 56384/57600 [9:55:29<12:22,  1.64it/s]
 98%|█████████▊| 56385/57600 [9:55:29<12:06,  1.67it/s]
 98%|█████████▊| 56386/57600 [9:55:30<12:10,  1.66it/s]
 98%|█████████▊| 56387/57600 [9:55:30<12:31,  1.61it/s]
 98%|█████████▊| 56388/57600 [9:55:31<12:23,  1.63it/s]
 98%|█████████▊| 56389/57600 [9:55:32<12:25,  1.62it/s]
 98%|█████████▊| 56390/57600 [9:55:32<12:31,  1.61it/s]
 98%|█████████▊| 56391/57600 [9:55:33<12:24,  1.62it/s]
 98%|█████████▊| 56392/57600 [9:55:33<12:15,  1.64it/s]
 98%|█████████▊| 56393/57600 [9:55:34<12:05,  1.66it/s]
 98%|█████████▊| 56394/57600 [9:55:35<12:34,  1.60it/s]
 98%|█████████▊| 56395/57600 [9:55:35<12:31,  1.60it/s]
 98%|█████████▊| 56396/57600 [9:55:36<12:34,  1.60it/s]
 98%|█████████▊| 56397/57600 [9:55:37<12:27,  1.61it/s]
 98%|█████████▊| 56398/57600 [9:55:37<12:23,  1.62it/s]
 98%|█████████▊| 56399/57600 [9:55:38<12:33,  1.59it/s]
 98%|█████████▊| 56400/57600 [9:55:39<12:49,  1.56it/s]
                                                       
{'loss': 1.1205, 'learning_rate': 1.18815331010453e-07, 'epoch': 622.52}

 98%|█████████▊| 56400/57600 [9:55:39<12:49,  1.56it/s]
 98%|█████████▊| 56401/57600 [9:55:39<13:03,  1.53it/s]
 98%|█████████▊| 56402/57600 [9:55:40<13:11,  1.51it/s]
 98%|█████████▊| 56403/57600 [9:55:41<13:00,  1.53it/s]
 98%|█████████▊| 56404/57600 [9:55:41<13:04,  1.52it/s]
 98%|█████████▊| 56405/57600 [9:55:42<12:57,  1.54it/s]
 98%|█████████▊| 56406/57600 [9:55:42<12:47,  1.56it/s]
 98%|█████████▊| 56407/57600 [9:55:43<12:19,  1.61it/s]
 98%|█████████▊| 56408/57600 [9:55:44<12:11,  1.63it/s]
 98%|█████████▊| 56409/57600 [9:55:44<12:01,  1.65it/s]
 98%|█████████▊| 56410/57600 [9:55:45<11:50,  1.68it/s]
 98%|█████████▊| 56411/57600 [9:55:45<11:54,  1.66it/s]
 98%|█████████▊| 56412/57600 [9:55:46<12:04,  1.64it/s]
 98%|█████████▊| 56413/57600 [9:55:47<12:27,  1.59it/s]
 98%|█████████▊| 56414/57600 [9:55:47<12:20,  1.60it/s]
 98%|█████████▊| 56415/57600 [9:55:48<12:21,  1.60it/s]
 98%|█████████▊| 56416/57600 [9:55:49<12:25,  1.59it/s]
 98%|█████████▊| 56417/57600 [9:55:49<12:16,  1.61it/s]
 98%|█████████▊| 56418/57600 [9:55:50<12:18,  1.60it/s]
 98%|█████████▊| 56419/57600 [9:55:50<12:35,  1.56it/s]
 98%|█████████▊| 56420/57600 [9:55:51<12:14,  1.61it/s]
                                                       
{'loss': 1.066, 'learning_rate': 1.1850174216027873e-07, 'epoch': 622.74}

 98%|█████████▊| 56420/57600 [9:55:51<12:14,  1.61it/s]
 98%|█████████▊| 56421/57600 [9:55:52<12:10,  1.61it/s]
 98%|█████████▊| 56422/57600 [9:55:52<12:01,  1.63it/s]
 98%|█████████▊| 56423/57600 [9:55:53<12:22,  1.59it/s]
 98%|█████████▊| 56424/57600 [9:55:54<12:24,  1.58it/s]
 98%|█████████▊| 56425/57600 [9:55:54<12:24,  1.58it/s]
 98%|█████████▊| 56426/57600 [9:55:55<11:54,  1.64it/s]
 98%|█████████▊| 56427/57600 [9:55:55<11:42,  1.67it/s]
 98%|█████████▊| 56428/57600 [9:55:56<12:02,  1.62it/s]
 98%|█████████▊| 56429/57600 [9:55:57<12:26,  1.57it/s]
 98%|█████████▊| 56430/57600 [9:55:57<12:11,  1.60it/s]
 98%|█████████▊| 56431/57600 [9:55:58<11:56,  1.63it/s]
 98%|█████████▊| 56432/57600 [9:55:58<11:50,  1.64it/s]
 98%|█████████▊| 56433/57600 [9:55:59<12:29,  1.56it/s]
 98%|█████████▊| 56434/57600 [9:56:00<12:21,  1.57it/s]
 98%|█████████▊| 56435/57600 [9:56:00<12:01,  1.61it/s]
 98%|█████████▊| 56436/57600 [9:56:01<12:00,  1.62it/s]
 98%|█████████▊| 56437/57600 [9:56:02<11:55,  1.63it/s]
 98%|█████████▊| 56438/57600 [9:56:02<11:53,  1.63it/s]
 98%|█████████▊| 56439/57600 [9:56:03<11:42,  1.65it/s]
 98%|█████████▊| 56440/57600 [9:56:03<11:39,  1.66it/s]
                                                       
{'loss': 1.1122, 'learning_rate': 1.1818815331010456e-07, 'epoch': 622.96}

 98%|█████████▊| 56440/57600 [9:56:03<11:39,  1.66it/s]
 98%|█████████▊| 56441/57600 [9:56:04<11:50,  1.63it/s]
 98%|█████████▊| 56442/57600 [9:56:05<11:36,  1.66it/s]
 98%|█████████▊| 56443/57600 [9:56:05<11:14,  1.72it/s]
 98%|█████████▊| 56444/57600 [9:56:06<11:43,  1.64it/s]
 98%|█████████▊| 56445/57600 [9:56:06<11:49,  1.63it/s]
 98%|█████████▊| 56446/57600 [9:56:07<11:48,  1.63it/s]
 98%|█████████▊| 56447/57600 [9:56:08<11:44,  1.64it/s]
 98%|█████████▊| 56448/57600 [9:56:08<11:38,  1.65it/s]
 98%|█████████▊| 56449/57600 [9:56:09<11:29,  1.67it/s]
 98%|█████████▊| 56450/57600 [9:56:09<11:42,  1.64it/s]
 98%|█████████▊| 56451/57600 [9:56:10<11:41,  1.64it/s]
 98%|█████████▊| 56452/57600 [9:56:11<11:41,  1.64it/s]
 98%|█████████▊| 56453/57600 [9:56:11<11:55,  1.60it/s]
 98%|█████████▊| 56454/57600 [9:56:12<12:07,  1.58it/s]
 98%|█████████▊| 56455/57600 [9:56:13<12:03,  1.58it/s]
 98%|█████████▊| 56456/57600 [9:56:13<12:11,  1.56it/s]
 98%|█████████▊| 56457/57600 [9:56:14<11:46,  1.62it/s]
 98%|█████████▊| 56458/57600 [9:56:15<11:48,  1.61it/s]
 98%|█████████▊| 56459/57600 [9:56:15<11:52,  1.60it/s]
 98%|█████████▊| 56460/57600 [9:56:16<11:52,  1.60it/s]
                                                       
{'loss': 1.1093, 'learning_rate': 1.1787456445993028e-07, 'epoch': 623.18}

 98%|█████████▊| 56460/57600 [9:56:16<11:52,  1.60it/s]
 98%|█████████▊| 56461/57600 [9:56:16<11:51,  1.60it/s]
 98%|█████████▊| 56462/57600 [9:56:17<12:04,  1.57it/s]
 98%|█████████▊| 56463/57600 [9:56:18<11:40,  1.62it/s]
 98%|█████████▊| 56464/57600 [9:56:18<11:50,  1.60it/s]
 98%|█████████▊| 56465/57600 [9:56:19<11:28,  1.65it/s]
 98%|█████████▊| 56466/57600 [9:56:19<11:33,  1.64it/s]
 98%|█████████▊| 56467/57600 [9:56:20<11:59,  1.58it/s]
 98%|█████████▊| 56468/57600 [9:56:21<12:01,  1.57it/s]
 98%|█████████▊| 56469/57600 [9:56:21<11:43,  1.61it/s]
 98%|█████████▊| 56470/57600 [9:56:22<12:07,  1.55it/s]
 98%|█████████▊| 56471/57600 [9:56:23<12:12,  1.54it/s]
 98%|█████████▊| 56472/57600 [9:56:23<12:03,  1.56it/s]
 98%|█████████▊| 56473/57600 [9:56:24<12:12,  1.54it/s]
 98%|█████████▊| 56474/57600 [9:56:25<11:48,  1.59it/s]
 98%|█████████▊| 56475/57600 [9:56:25<11:32,  1.63it/s]
 98%|█████████▊| 56476/57600 [9:56:26<11:16,  1.66it/s]
 98%|█████████▊| 56477/57600 [9:56:26<11:39,  1.61it/s]
 98%|█████████▊| 56478/57600 [9:56:27<11:16,  1.66it/s]
 98%|█████████▊| 56479/57600 [9:56:28<11:30,  1.62it/s]
 98%|█████████▊| 56480/57600 [9:56:28<11:53,  1.57it/s]
                                                       
{'loss': 1.082, 'learning_rate': 1.1756097560975611e-07, 'epoch': 623.4}

 98%|█████████▊| 56480/57600 [9:56:28<11:53,  1.57it/s]
 98%|█████████▊| 56481/57600 [9:56:29<11:59,  1.55it/s]
 98%|█████████▊| 56482/57600 [9:56:30<11:40,  1.60it/s]
 98%|█████████▊| 56483/57600 [9:56:30<11:48,  1.58it/s]
 98%|█████████▊| 56484/57600 [9:56:31<11:34,  1.61it/s]
 98%|█████████▊| 56485/57600 [9:56:31<11:54,  1.56it/s]
 98%|█████████▊| 56486/57600 [9:56:32<11:40,  1.59it/s]
 98%|█████████▊| 56487/57600 [9:56:33<11:46,  1.58it/s]
 98%|█████████▊| 56488/57600 [9:56:33<11:24,  1.62it/s]
 98%|█████████▊| 56489/57600 [9:56:34<11:01,  1.68it/s]
 98%|█████████▊| 56490/57600 [9:56:34<10:56,  1.69it/s]
 98%|█████████▊| 56491/57600 [9:56:35<11:12,  1.65it/s]
 98%|█████████▊| 56492/57600 [9:56:36<11:08,  1.66it/s]
 98%|█████████▊| 56493/57600 [9:56:36<11:14,  1.64it/s]
 98%|█████████▊| 56494/57600 [9:56:37<10:59,  1.68it/s]
 98%|█████████▊| 56495/57600 [9:56:37<10:57,  1.68it/s]
 98%|█████████▊| 56496/57600 [9:56:38<11:13,  1.64it/s]
 98%|█████████▊| 56497/57600 [9:56:39<11:34,  1.59it/s]
 98%|█████████▊| 56498/57600 [9:56:39<11:34,  1.59it/s]
 98%|█████████▊| 56499/57600 [9:56:40<11:28,  1.60it/s]
 98%|█████████▊| 56500/57600 [9:56:41<11:03,  1.66it/s]
                                                       
{'loss': 1.1245, 'learning_rate': 1.1724738675958184e-07, 'epoch': 623.62}

 98%|█████████▊| 56500/57600 [9:56:41<11:03,  1.66it/s]
 98%|█████████▊| 56501/57600 [9:56:41<11:10,  1.64it/s]
 98%|█████████▊| 56502/57600 [9:56:42<11:11,  1.64it/s]
 98%|█████████▊| 56503/57600 [9:56:42<11:03,  1.65it/s]
 98%|█████████▊| 56504/57600 [9:56:43<11:09,  1.64it/s]
 98%|█████████▊| 56505/57600 [9:56:44<11:29,  1.59it/s]
 98%|█████████▊| 56506/57600 [9:56:44<11:11,  1.63it/s]
 98%|█████████▊| 56507/57600 [9:56:45<11:38,  1.57it/s]
 98%|█████████▊| 56508/57600 [9:56:46<11:13,  1.62it/s]
 98%|█████████▊| 56509/57600 [9:56:46<11:31,  1.58it/s]
 98%|█████████▊| 56510/57600 [9:56:47<11:29,  1.58it/s]
 98%|█████████▊| 56511/57600 [9:56:47<11:26,  1.59it/s]
 98%|█████████▊| 56512/57600 [9:56:48<11:16,  1.61it/s]
 98%|█████████▊| 56513/57600 [9:56:49<10:50,  1.67it/s]
 98%|█████████▊| 56514/57600 [9:56:49<11:00,  1.65it/s]
 98%|█████████▊| 56515/57600 [9:56:50<11:29,  1.57it/s]
 98%|█████████▊| 56516/57600 [9:56:51<11:37,  1.55it/s]
 98%|█████████▊| 56517/57600 [9:56:51<11:17,  1.60it/s]
 98%|█████████▊| 56518/57600 [9:56:52<10:58,  1.64it/s]
 98%|█████████▊| 56519/57600 [9:56:52<10:58,  1.64it/s]
 98%|█████████▊| 56520/57600 [9:56:53<10:59,  1.64it/s]
                                                       
{'loss': 1.103, 'learning_rate': 1.1693379790940766e-07, 'epoch': 623.84}

 98%|█████████▊| 56520/57600 [9:56:53<10:59,  1.64it/s]
 98%|█████████▊| 56521/57600 [9:56:54<11:43,  1.53it/s]
 98%|█████████▊| 56522/57600 [9:56:54<11:18,  1.59it/s]
 98%|█████████▊| 56523/57600 [9:56:55<11:10,  1.61it/s]
 98%|█████████▊| 56524/57600 [9:56:56<11:34,  1.55it/s]
 98%|█████████▊| 56525/57600 [9:56:56<11:45,  1.52it/s]
 98%|█████████▊| 56526/57600 [9:56:57<11:41,  1.53it/s]
 98%|█████████▊| 56527/57600 [9:56:58<11:19,  1.58it/s]
 98%|█████████▊| 56528/57600 [9:56:58<10:52,  1.64it/s]
 98%|█████████▊| 56529/57600 [9:56:59<10:56,  1.63it/s]
 98%|█████████▊| 56530/57600 [9:56:59<11:08,  1.60it/s]
 98%|█████████▊| 56531/57600 [9:57:00<11:06,  1.60it/s]
 98%|█████████▊| 56532/57600 [9:57:01<10:54,  1.63it/s]
 98%|█████████▊| 56533/57600 [9:57:01<10:57,  1.62it/s]
 98%|█████████▊| 56534/57600 [9:57:02<10:49,  1.64it/s]
 98%|█████████▊| 56535/57600 [9:57:02<11:10,  1.59it/s]
 98%|█████████▊| 56536/57600 [9:57:03<10:51,  1.63it/s]
 98%|█████████▊| 56537/57600 [9:57:04<10:43,  1.65it/s]
 98%|█████████▊| 56538/57600 [9:57:04<11:06,  1.59it/s]
 98%|█████████▊| 56539/57600 [9:57:05<11:18,  1.56it/s]
 98%|█████████▊| 56540/57600 [9:57:06<10:57,  1.61it/s]
                                                       
{'loss': 1.1024, 'learning_rate': 1.1662020905923349e-07, 'epoch': 624.06}

 98%|█████████▊| 56540/57600 [9:57:06<10:57,  1.61it/s]
 98%|█████████▊| 56541/57600 [9:57:06<11:34,  1.52it/s]
 98%|█████████▊| 56542/57600 [9:57:07<11:30,  1.53it/s]
 98%|█████████▊| 56543/57600 [9:57:08<11:13,  1.57it/s]
 98%|█████████▊| 56544/57600 [9:57:08<11:10,  1.57it/s]
 98%|█████████▊| 56545/57600 [9:57:09<10:53,  1.61it/s]
 98%|█████████▊| 56546/57600 [9:57:09<11:01,  1.59it/s]
 98%|█████████▊| 56547/57600 [9:57:10<10:49,  1.62it/s]
 98%|█████████▊| 56548/57600 [9:57:11<10:38,  1.65it/s]
 98%|█████████▊| 56549/57600 [9:57:11<10:44,  1.63it/s]
 98%|█████████▊| 56550/57600 [9:57:12<10:31,  1.66it/s]
 98%|█████████▊| 56551/57600 [9:57:12<10:29,  1.67it/s]
 98%|█████████▊| 56552/57600 [9:57:13<11:01,  1.58it/s]
 98%|█████████▊| 56553/57600 [9:57:14<10:59,  1.59it/s]
 98%|█████████▊| 56554/57600 [9:57:14<11:17,  1.54it/s]
 98%|█████████▊| 56555/57600 [9:57:15<10:52,  1.60it/s]
 98%|█████████▊| 56556/57600 [9:57:16<10:29,  1.66it/s]
 98%|█████████▊| 56557/57600 [9:57:16<10:37,  1.64it/s]
 98%|█████████▊| 56558/57600 [9:57:17<10:51,  1.60it/s]
 98%|█████████▊| 56559/57600 [9:57:17<11:01,  1.57it/s]
 98%|█████████▊| 56560/57600 [9:57:18<10:56,  1.58it/s]
                                                       
{'loss': 1.1122, 'learning_rate': 1.1630662020905921e-07, 'epoch': 624.28}

 98%|█████████▊| 56560/57600 [9:57:18<10:56,  1.58it/s]
 98%|█████████▊| 56561/57600 [9:57:19<10:54,  1.59it/s]
 98%|█████████▊| 56562/57600 [9:57:19<10:57,  1.58it/s]
 98%|█████████▊| 56563/57600 [9:57:20<10:41,  1.62it/s]
 98%|█████████▊| 56564/57600 [9:57:21<11:08,  1.55it/s]
 98%|█████████▊| 56565/57600 [9:57:21<11:28,  1.50it/s]
 98%|█████████▊| 56566/57600 [9:57:22<11:09,  1.54it/s]
 98%|█████████▊| 56567/57600 [9:57:23<11:07,  1.55it/s]
 98%|█████████▊| 56568/57600 [9:57:23<11:11,  1.54it/s]
 98%|█████████▊| 56569/57600 [9:57:24<11:14,  1.53it/s]
 98%|█████████▊| 56570/57600 [9:57:25<10:51,  1.58it/s]
 98%|█████████▊| 56571/57600 [9:57:25<10:57,  1.57it/s]
 98%|█████████▊| 56572/57600 [9:57:26<10:41,  1.60it/s]
 98%|█████████▊| 56573/57600 [9:57:26<10:25,  1.64it/s]
 98%|█████████▊| 56574/57600 [9:57:27<10:13,  1.67it/s]
 98%|█████████▊| 56575/57600 [9:57:28<10:24,  1.64it/s]
 98%|█████████▊| 56576/57600 [9:57:28<10:39,  1.60it/s]
 98%|█████████▊| 56577/57600 [9:57:29<10:18,  1.65it/s]
 98%|█████████▊| 56578/57600 [9:57:29<10:16,  1.66it/s]
 98%|█████████▊| 56579/57600 [9:57:30<10:14,  1.66it/s]
 98%|█████████▊| 56580/57600 [9:57:31<10:31,  1.61it/s]
                                                       
{'loss': 1.0891, 'learning_rate': 1.1599303135888503e-07, 'epoch': 624.5}

 98%|█████████▊| 56580/57600 [9:57:31<10:31,  1.61it/s]
 98%|█████████▊| 56581/57600 [9:57:31<10:42,  1.59it/s]
 98%|█████████▊| 56582/57600 [9:57:32<10:37,  1.60it/s]
 98%|█████████▊| 56583/57600 [9:57:33<10:45,  1.57it/s]
 98%|█████████▊| 56584/57600 [9:57:33<10:42,  1.58it/s]
 98%|█████████▊| 56585/57600 [9:57:34<10:28,  1.62it/s]
 98%|█████████▊| 56586/57600 [9:57:34<10:25,  1.62it/s]
 98%|█████████▊| 56587/57600 [9:57:35<10:31,  1.60it/s]
 98%|█████████▊| 56588/57600 [9:57:36<10:52,  1.55it/s]
 98%|█████████▊| 56589/57600 [9:57:36<10:49,  1.56it/s]
 98%|█████████▊| 56590/57600 [9:57:37<10:49,  1.55it/s]
 98%|█████████▊| 56591/57600 [9:57:38<10:31,  1.60it/s]
 98%|█████████▊| 56592/57600 [9:57:38<10:41,  1.57it/s]
 98%|█████████▊| 56593/57600 [9:57:39<10:34,  1.59it/s]
 98%|█████████▊| 56594/57600 [9:57:39<10:17,  1.63it/s]
 98%|█████████▊| 56595/57600 [9:57:40<10:08,  1.65it/s]
 98%|█████████▊| 56596/57600 [9:57:41<10:38,  1.57it/s]
 98%|█████████▊| 56597/57600 [9:57:41<10:25,  1.60it/s]
 98%|█████████▊| 56598/57600 [9:57:42<10:27,  1.60it/s]
 98%|█████████▊| 56599/57600 [9:57:43<10:15,  1.63it/s]
 98%|█████████▊| 56600/57600 [9:57:43<10:33,  1.58it/s]
                                                       
{'loss': 1.1048, 'learning_rate': 1.1567944250871077e-07, 'epoch': 624.72}

 98%|█████████▊| 56600/57600 [9:57:43<10:33,  1.58it/s]
 98%|█████████▊| 56601/57600 [9:57:44<10:39,  1.56it/s]
 98%|█████████▊| 56602/57600 [9:57:44<10:22,  1.60it/s]
 98%|█████████▊| 56603/57600 [9:57:45<10:10,  1.63it/s]
 98%|█████████▊| 56604/57600 [9:57:46<10:02,  1.65it/s]
 98%|█████████▊| 56605/57600 [9:57:46<10:06,  1.64it/s]
 98%|█████████▊| 56606/57600 [9:57:47<10:01,  1.65it/s]
 98%|█████████▊| 56607/57600 [9:57:47<10:03,  1.64it/s]
 98%|█████████▊| 56608/57600 [9:57:48<10:04,  1.64it/s]
 98%|█████████▊| 56609/57600 [9:57:49<10:01,  1.65it/s]
 98%|█████████▊| 56610/57600 [9:57:49<10:06,  1.63it/s]
 98%|█████████▊| 56611/57600 [9:57:50<10:04,  1.64it/s]
 98%|█████████▊| 56612/57600 [9:57:50<09:59,  1.65it/s]
 98%|█████████▊| 56613/57600 [9:57:51<10:18,  1.60it/s]
 98%|█████████▊| 56614/57600 [9:57:52<10:22,  1.58it/s]
 98%|█████████▊| 56615/57600 [9:57:52<10:10,  1.61it/s]
 98%|█████████▊| 56616/57600 [9:57:53<10:08,  1.62it/s]
 98%|█████████▊| 56617/57600 [9:57:54<10:32,  1.55it/s]
 98%|█████████▊| 56618/57600 [9:57:54<10:29,  1.56it/s]
 98%|█████████▊| 56619/57600 [9:57:55<09:58,  1.64it/s]
 98%|█████████▊| 56620/57600 [9:57:56<10:05,  1.62it/s]
                                                       
{'loss': 1.0908, 'learning_rate': 1.1536585365853659e-07, 'epoch': 624.94}

 98%|█████████▊| 56620/57600 [9:57:56<10:05,  1.62it/s]
 98%|█████████▊| 56621/57600 [9:57:56<09:52,  1.65it/s]
 98%|█████████▊| 56622/57600 [9:57:57<10:00,  1.63it/s]
 98%|█████████▊| 56623/57600 [9:57:57<09:55,  1.64it/s]
 98%|█████████▊| 56624/57600 [9:57:58<09:50,  1.65it/s]
 98%|█████████▊| 56625/57600 [9:57:59<09:46,  1.66it/s]
 98%|█████████▊| 56626/57600 [9:57:59<10:10,  1.60it/s]
 98%|█████████▊| 56627/57600 [9:58:00<10:10,  1.59it/s]
 98%|█████████▊| 56628/57600 [9:58:01<10:22,  1.56it/s]
 98%|█████████▊| 56629/57600 [9:58:01<10:17,  1.57it/s]
 98%|█████████▊| 56630/57600 [9:58:02<10:34,  1.53it/s]
 98%|█████████▊| 56631/57600 [9:58:02<10:20,  1.56it/s]
 98%|█████████▊| 56632/57600 [9:58:03<10:21,  1.56it/s]
 98%|█████████▊| 56633/57600 [9:58:04<10:19,  1.56it/s]
 98%|█████████▊| 56634/57600 [9:58:04<10:13,  1.58it/s]
 98%|█████████▊| 56635/57600 [9:58:05<10:14,  1.57it/s]
 98%|█████████▊| 56636/57600 [9:58:06<10:15,  1.57it/s]
 98%|█████████▊| 56637/57600 [9:58:06<10:12,  1.57it/s]
 98%|█████████▊| 56638/57600 [9:58:07<10:00,  1.60it/s]
 98%|█████████▊| 56639/57600 [9:58:07<09:59,  1.60it/s]
 98%|█████████▊| 56640/57600 [9:58:08<09:48,  1.63it/s]
                                                       
{'loss': 1.0883, 'learning_rate': 1.1505226480836231e-07, 'epoch': 625.17}

 98%|█████████▊| 56640/57600 [9:58:08<09:48,  1.63it/s]
 98%|█████████▊| 56641/57600 [9:58:09<09:54,  1.61it/s]
 98%|█████████▊| 56642/57600 [9:58:09<09:49,  1.63it/s]
 98%|█████████▊| 56643/57600 [9:58:10<09:54,  1.61it/s]
 98%|█████████▊| 56644/57600 [9:58:11<09:39,  1.65it/s]
 98%|█████████▊| 56645/57600 [9:58:11<09:30,  1.67it/s]
 98%|█████████▊| 56646/57600 [9:58:12<10:01,  1.59it/s]
 98%|█████████▊| 56647/57600 [9:58:13<10:23,  1.53it/s]
 98%|█████████▊| 56648/57600 [9:58:13<10:38,  1.49it/s]
 98%|█████████▊| 56649/57600 [9:58:14<10:20,  1.53it/s]
 98%|█████████▊| 56650/57600 [9:58:14<10:20,  1.53it/s]
 98%|█████████▊| 56651/57600 [9:58:15<10:30,  1.51it/s]
 98%|█████████▊| 56652/57600 [9:58:16<10:32,  1.50it/s]
 98%|█████████▊| 56653/57600 [9:58:16<10:14,  1.54it/s]
 98%|█████████▊| 56654/57600 [9:58:17<09:53,  1.59it/s]
 98%|█████████▊| 56655/57600 [9:58:18<09:39,  1.63it/s]
 98%|█████████▊| 56656/57600 [9:58:18<10:05,  1.56it/s]
 98%|█████████▊| 56657/57600 [9:58:19<09:54,  1.59it/s]
 98%|█████████▊| 56658/57600 [9:58:20<09:40,  1.62it/s]
 98%|█████████▊| 56659/57600 [9:58:20<09:43,  1.61it/s]
 98%|█████████▊| 56660/57600 [9:58:21<09:24,  1.67it/s]
                                                       
{'loss': 1.1402, 'learning_rate': 1.1473867595818815e-07, 'epoch': 625.39}

 98%|█████████▊| 56660/57600 [9:58:21<09:24,  1.67it/s]
 98%|█████████▊| 56661/57600 [9:58:21<09:24,  1.66it/s]
 98%|█████████▊| 56662/57600 [9:58:22<09:18,  1.68it/s]
 98%|█████████▊| 56663/57600 [9:58:22<09:24,  1.66it/s]
 98%|█████████▊| 56664/57600 [9:58:23<09:38,  1.62it/s]
 98%|█████████▊| 56665/57600 [9:58:24<10:14,  1.52it/s]
 98%|█████████▊| 56666/57600 [9:58:25<10:06,  1.54it/s]
 98%|█████████▊| 56667/57600 [9:58:25<10:11,  1.53it/s]
 98%|█████████▊| 56668/57600 [9:58:26<10:16,  1.51it/s]
 98%|█████████▊| 56669/57600 [9:58:27<10:16,  1.51it/s]
 98%|█████████▊| 56670/57600 [9:58:27<09:51,  1.57it/s]
 98%|█████████▊| 56671/57600 [9:58:28<09:34,  1.62it/s]
 98%|█████████▊| 56672/57600 [9:58:28<09:32,  1.62it/s]
 98%|█████████▊| 56673/57600 [9:58:29<09:43,  1.59it/s]
 98%|█████████▊| 56674/57600 [9:58:30<09:30,  1.62it/s]
 98%|█████████▊| 56675/57600 [9:58:30<09:40,  1.59it/s]
 98%|█████████▊| 56676/57600 [9:58:31<09:39,  1.60it/s]
 98%|█████████▊| 56677/57600 [9:58:31<09:16,  1.66it/s]
 98%|█████████▊| 56678/57600 [9:58:32<09:23,  1.64it/s]
 98%|█████████▊| 56679/57600 [9:58:33<09:15,  1.66it/s]
 98%|█████████▊| 56680/57600 [9:58:33<09:17,  1.65it/s]
                                                       
{'loss': 1.0784, 'learning_rate': 1.1442508710801398e-07, 'epoch': 625.61}

 98%|█████████▊| 56680/57600 [9:58:33<09:17,  1.65it/s]
 98%|█████████▊| 56681/57600 [9:58:34<09:31,  1.61it/s]
 98%|█████████▊| 56682/57600 [9:58:34<09:26,  1.62it/s]
 98%|█████████▊| 56683/57600 [9:58:35<09:25,  1.62it/s]
 98%|█████████▊| 56684/57600 [9:58:36<09:19,  1.64it/s]
 98%|█████████▊| 56685/57600 [9:58:36<09:20,  1.63it/s]
 98%|█████████▊| 56686/57600 [9:58:37<09:25,  1.62it/s]
 98%|█████████▊| 56687/57600 [9:58:38<09:32,  1.59it/s]
 98%|█████████▊| 56688/57600 [9:58:38<09:23,  1.62it/s]
 98%|█████████▊| 56689/57600 [9:58:39<09:29,  1.60it/s]
 98%|█████████▊| 56690/57600 [9:58:39<09:29,  1.60it/s]
 98%|█████████▊| 56691/57600 [9:58:40<09:13,  1.64it/s]
 98%|█████████▊| 56692/57600 [9:58:41<09:10,  1.65it/s]
 98%|█████████▊| 56693/57600 [9:58:41<09:34,  1.58it/s]
 98%|█████████▊| 56694/57600 [9:58:42<09:31,  1.59it/s]
 98%|█████████▊| 56695/57600 [9:58:43<09:27,  1.59it/s]
 98%|█████████▊| 56696/57600 [9:58:43<09:37,  1.56it/s]
 98%|█████████▊| 56697/57600 [9:58:44<09:24,  1.60it/s]
 98%|█████████▊| 56698/57600 [9:58:44<09:07,  1.65it/s]
 98%|█████████▊| 56699/57600 [9:58:45<08:52,  1.69it/s]
 98%|█████████▊| 56700/57600 [9:58:45<08:42,  1.72it/s]
                                                       
{'loss': 1.1173, 'learning_rate': 1.141114982578397e-07, 'epoch': 625.83}

 98%|█████████▊| 56700/57600 [9:58:45<08:42,  1.72it/s]
 98%|█████████▊| 56701/57600 [9:58:46<09:08,  1.64it/s]
 98%|█████████▊| 56702/57600 [9:58:47<09:07,  1.64it/s]
 98%|█████████▊| 56703/57600 [9:58:47<09:10,  1.63it/s]
 98%|█████████▊| 56704/57600 [9:58:48<09:28,  1.58it/s]
 98%|█████████▊| 56705/57600 [9:58:49<09:09,  1.63it/s]
 98%|█████████▊| 56706/57600 [9:58:49<09:08,  1.63it/s]
 98%|█████████▊| 56707/57600 [9:58:50<09:13,  1.61it/s]
 98%|█████████▊| 56708/57600 [9:58:50<09:10,  1.62it/s]
 98%|█████████▊| 56709/57600 [9:58:51<09:01,  1.64it/s]
 98%|█████████▊| 56710/57600 [9:58:52<08:55,  1.66it/s]
 98%|█████████▊| 56711/57600 [9:58:52<08:51,  1.67it/s]
 98%|█████████▊| 56712/57600 [9:58:53<08:47,  1.68it/s]
 98%|█████████▊| 56713/57600 [9:58:53<08:49,  1.68it/s]
 98%|█████████▊| 56714/57600 [9:58:54<08:54,  1.66it/s]
 98%|█████████▊| 56715/57600 [9:58:55<08:52,  1.66it/s]
 98%|█████████▊| 56716/57600 [9:58:55<09:16,  1.59it/s]
 98%|█████████▊| 56717/57600 [9:58:56<09:36,  1.53it/s]
 98%|█████████▊| 56718/57600 [9:58:57<09:23,  1.57it/s]
 98%|█████████▊| 56719/57600 [9:58:57<09:13,  1.59it/s]
 98%|█████████▊| 56720/57600 [9:58:58<09:25,  1.56it/s]
                                                       
{'loss': 1.106, 'learning_rate': 1.1379790940766552e-07, 'epoch': 626.05}

 98%|█████████▊| 56720/57600 [9:58:58<09:25,  1.56it/s]
 98%|█████████▊| 56721/57600 [9:58:59<09:32,  1.54it/s]
 98%|█████████▊| 56722/57600 [9:58:59<09:02,  1.62it/s]
 98%|█████████▊| 56723/57600 [9:59:00<08:55,  1.64it/s]
 98%|█████████▊| 56724/57600 [9:59:00<09:02,  1.62it/s]
 98%|█████████▊| 56725/57600 [9:59:01<08:56,  1.63it/s]
 98%|█████████▊| 56726/57600 [9:59:02<08:55,  1.63it/s]
 98%|█████████▊| 56727/57600 [9:59:02<08:51,  1.64it/s]
 98%|█████████▊| 56728/57600 [9:59:03<08:57,  1.62it/s]
 98%|█████████▊| 56729/57600 [9:59:03<09:09,  1.59it/s]
 98%|█████████▊| 56730/57600 [9:59:04<09:01,  1.61it/s]
 98%|█████████▊| 56731/57600 [9:59:05<08:57,  1.62it/s]
 98%|█████████▊| 56732/57600 [9:59:05<08:43,  1.66it/s]
 98%|█████████▊| 56733/57600 [9:59:06<08:55,  1.62it/s]
 98%|█████████▊| 56734/57600 [9:59:07<08:49,  1.64it/s]
 98%|█████████▊| 56735/57600 [9:59:07<08:52,  1.62it/s]
 98%|█████████▊| 56736/57600 [9:59:08<08:53,  1.62it/s]
 99%|█████████▊| 56737/57600 [9:59:08<09:03,  1.59it/s]
 99%|█████████▊| 56738/57600 [9:59:09<08:45,  1.64it/s]
 99%|█████████▊| 56739/57600 [9:59:10<08:36,  1.67it/s]
 99%|█████████▊| 56740/57600 [9:59:10<08:49,  1.63it/s]
                                                       
{'loss': 1.1004, 'learning_rate': 1.1348432055749126e-07, 'epoch': 626.27}

 99%|█████████▊| 56740/57600 [9:59:10<08:49,  1.63it/s]
 99%|█████████▊| 56741/57600 [9:59:11<09:13,  1.55it/s]
 99%|█████████▊| 56742/57600 [9:59:12<09:04,  1.57it/s]
 99%|█████████▊| 56743/57600 [9:59:12<09:15,  1.54it/s]
 99%|█████████▊| 56744/57600 [9:59:13<09:11,  1.55it/s]
 99%|█████████▊| 56745/57600 [9:59:13<08:52,  1.61it/s]
 99%|█████████▊| 56746/57600 [9:59:14<08:37,  1.65it/s]
 99%|█████████▊| 56747/57600 [9:59:15<08:58,  1.58it/s]
 99%|█████████▊| 56748/57600 [9:59:15<09:01,  1.57it/s]
 99%|█████████▊| 56749/57600 [9:59:16<08:55,  1.59it/s]
 99%|█████████▊| 56750/57600 [9:59:17<08:51,  1.60it/s]
 99%|█████████▊| 56751/57600 [9:59:17<08:46,  1.61it/s]
 99%|█████████▊| 56752/57600 [9:59:18<08:27,  1.67it/s]
 99%|█████████▊| 56753/57600 [9:59:18<08:24,  1.68it/s]
 99%|█████████▊| 56754/57600 [9:59:19<08:33,  1.65it/s]
 99%|█████████▊| 56755/57600 [9:59:20<08:22,  1.68it/s]
 99%|█████████▊| 56756/57600 [9:59:20<08:21,  1.68it/s]
 99%|█████████▊| 56757/57600 [9:59:21<08:38,  1.63it/s]
 99%|█████████▊| 56758/57600 [9:59:21<08:58,  1.56it/s]
 99%|█████████▊| 56759/57600 [9:59:22<08:45,  1.60it/s]
 99%|█████████▊| 56760/57600 [9:59:23<08:50,  1.58it/s]
                                                       
{'loss': 1.0922, 'learning_rate': 1.1317073170731708e-07, 'epoch': 626.49}

 99%|█████████▊| 56760/57600 [9:59:23<08:50,  1.58it/s]
 99%|█████████▊| 56761/57600 [9:59:23<08:44,  1.60it/s]
 99%|█████████▊| 56762/57600 [9:59:24<08:50,  1.58it/s]
 99%|█████████▊| 56763/57600 [9:59:25<08:49,  1.58it/s]
 99%|█████████▊| 56764/57600 [9:59:25<09:11,  1.52it/s]
 99%|█████████▊| 56765/57600 [9:59:26<08:58,  1.55it/s]
 99%|█████████▊| 56766/57600 [9:59:27<08:56,  1.55it/s]
 99%|█████████▊| 56767/57600 [9:59:27<09:00,  1.54it/s]
 99%|█████████▊| 56768/57600 [9:59:28<09:14,  1.50it/s]
 99%|█████████▊| 56769/57600 [9:59:29<08:57,  1.55it/s]
 99%|█████████▊| 56770/57600 [9:59:29<08:49,  1.57it/s]
 99%|█████████▊| 56771/57600 [9:59:30<08:35,  1.61it/s]
 99%|█████████▊| 56772/57600 [9:59:30<08:44,  1.58it/s]
 99%|█████████▊| 56773/57600 [9:59:31<08:50,  1.56it/s]
 99%|█████████▊| 56774/57600 [9:59:32<09:01,  1.52it/s]
 99%|█████████▊| 56775/57600 [9:59:32<09:02,  1.52it/s]
 99%|█████████▊| 56776/57600 [9:59:33<08:48,  1.56it/s]
 99%|█████████▊| 56777/57600 [9:59:34<08:21,  1.64it/s]
 99%|█████████▊| 56778/57600 [9:59:34<08:21,  1.64it/s]
 99%|█████████▊| 56779/57600 [9:59:35<08:13,  1.66it/s]
 99%|█████████▊| 56780/57600 [9:59:35<08:01,  1.70it/s]
                                                       
{'loss': 1.0832, 'learning_rate': 1.128571428571428e-07, 'epoch': 626.71}

 99%|█████████▊| 56780/57600 [9:59:35<08:01,  1.70it/s]
 99%|█████████▊| 56781/57600 [9:59:36<08:00,  1.71it/s]
 99%|█████████▊| 56782/57600 [9:59:36<08:05,  1.68it/s]
 99%|█████████▊| 56783/57600 [9:59:37<08:07,  1.68it/s]
 99%|█████████▊| 56784/57600 [9:59:38<08:27,  1.61it/s]
 99%|█████████▊| 56785/57600 [9:59:38<08:17,  1.64it/s]
 99%|█████████▊| 56786/57600 [9:59:39<08:25,  1.61it/s]
 99%|█████████▊| 56787/57600 [9:59:40<08:11,  1.65it/s]
 99%|█████████▊| 56788/57600 [9:59:40<08:10,  1.66it/s]
 99%|█████████▊| 56789/57600 [9:59:41<08:05,  1.67it/s]
 99%|█████████▊| 56790/57600 [9:59:41<07:59,  1.69it/s]
 99%|█████████▊| 56791/57600 [9:59:42<08:16,  1.63it/s]
 99%|█████████▊| 56792/57600 [9:59:43<08:16,  1.63it/s]
 99%|█████████▊| 56793/57600 [9:59:43<08:19,  1.61it/s]
 99%|█████████▊| 56794/57600 [9:59:44<08:22,  1.60it/s]
 99%|█████████▊| 56795/57600 [9:59:44<08:15,  1.62it/s]
 99%|█████████▊| 56796/57600 [9:59:45<08:20,  1.61it/s]
 99%|█████████▊| 56797/57600 [9:59:46<08:19,  1.61it/s]
 99%|█████████▊| 56798/57600 [9:59:46<08:35,  1.56it/s]
 99%|█████████▊| 56799/57600 [9:59:47<08:35,  1.55it/s]
 99%|█████████▊| 56800/57600 [9:59:48<08:41,  1.53it/s]
                                                       
{'loss': 1.1321, 'learning_rate': 1.1254355400696863e-07, 'epoch': 626.93}

 99%|█████████▊| 56800/57600 [9:59:48<08:41,  1.53it/s]
 99%|█████████▊| 56801/57600 [9:59:48<08:30,  1.57it/s]
 99%|█████████▊| 56802/57600 [9:59:49<08:21,  1.59it/s]
 99%|█████████▊| 56803/57600 [9:59:50<08:12,  1.62it/s]
 99%|█████████▊| 56804/57600 [9:59:50<08:05,  1.64it/s]
 99%|█████████▊| 56805/57600 [9:59:51<08:11,  1.62it/s]
 99%|█████████▊| 56806/57600 [9:59:51<08:03,  1.64it/s]
 99%|█████████▊| 56807/57600 [9:59:52<08:17,  1.60it/s]
 99%|█████████▊| 56808/57600 [9:59:53<08:12,  1.61it/s]
 99%|█████████▊| 56809/57600 [9:59:53<08:05,  1.63it/s]
 99%|█████████▊| 56810/57600 [9:59:54<08:02,  1.64it/s]
 99%|█████████▊| 56811/57600 [9:59:54<08:09,  1.61it/s]
 99%|█████████▊| 56812/57600 [9:59:55<08:18,  1.58it/s]
 99%|█████████▊| 56813/57600 [9:59:56<08:30,  1.54it/s]
 99%|█████████▊| 56814/57600 [9:59:56<08:13,  1.59it/s]
 99%|█████████▊| 56815/57600 [9:59:57<08:19,  1.57it/s]
 99%|█████████▊| 56816/57600 [9:59:58<08:19,  1.57it/s]
 99%|█████████▊| 56817/57600 [9:59:58<08:31,  1.53it/s]
 99%|█████████▊| 56818/57600 [9:59:59<08:42,  1.50it/s]
 99%|█████████▊| 56819/57600 [10:00:00<08:25,  1.54it/s]
 99%|█████████▊| 56820/57600 [10:00:00<08:21,  1.56it/s]
                                                        
{'loss': 1.1027, 'learning_rate': 1.1222996515679445e-07, 'epoch': 627.15}

 99%|█████████▊| 56820/57600 [10:00:00<08:21,  1.56it/s]
 99%|█████████▊| 56821/57600 [10:00:01<08:13,  1.58it/s]
 99%|█████████▊| 56822/57600 [10:00:02<08:08,  1.59it/s]
 99%|█████████▊| 56823/57600 [10:00:02<08:14,  1.57it/s]
 99%|█████████▊| 56824/57600 [10:00:03<08:11,  1.58it/s]
 99%|█████████▊| 56825/57600 [10:00:03<08:05,  1.59it/s]
 99%|█████████▊| 56826/57600 [10:00:04<08:08,  1.59it/s]
 99%|█████████▊| 56827/57600 [10:00:05<08:19,  1.55it/s]
 99%|█████████▊| 56828/57600 [10:00:05<08:10,  1.57it/s]
 99%|█████████▊| 56829/57600 [10:00:06<08:03,  1.60it/s]
 99%|█████████▊| 56830/57600 [10:00:07<07:52,  1.63it/s]
 99%|█████████▊| 56831/57600 [10:00:07<07:55,  1.62it/s]
 99%|█████████▊| 56832/57600 [10:00:08<07:40,  1.67it/s]
 99%|█████████▊| 56833/57600 [10:00:08<07:47,  1.64it/s]
 99%|█████████▊| 56834/57600 [10:00:09<07:46,  1.64it/s]
 99%|█████████▊| 56835/57600 [10:00:10<07:53,  1.61it/s]
 99%|█████████▊| 56836/57600 [10:00:10<08:09,  1.56it/s]
 99%|█████████▊| 56837/57600 [10:00:11<08:15,  1.54it/s]
 99%|█████████▊| 56838/57600 [10:00:12<07:56,  1.60it/s]
 99%|█████████▊| 56839/57600 [10:00:12<07:46,  1.63it/s]
 99%|█████████▊| 56840/57600 [10:00:13<07:36,  1.66it/s]
                                                        
{'loss': 1.1085, 'learning_rate': 1.1191637630662019e-07, 'epoch': 627.37}

 99%|█████████▊| 56840/57600 [10:00:13<07:36,  1.66it/s]
 99%|█████████▊| 56841/57600 [10:00:13<07:38,  1.66it/s]
 99%|█████████▊| 56842/57600 [10:00:14<07:29,  1.69it/s]
 99%|█████████▊| 56843/57600 [10:00:14<07:25,  1.70it/s]
 99%|█████████▊| 56844/57600 [10:00:15<07:40,  1.64it/s]
 99%|█████████▊| 56845/57600 [10:00:16<08:07,  1.55it/s]
 99%|█████████▊| 56846/57600 [10:00:17<08:02,  1.56it/s]
 99%|█████████▊| 56847/57600 [10:00:17<07:46,  1.61it/s]
 99%|█████████▊| 56848/57600 [10:00:18<08:07,  1.54it/s]
 99%|█████████▊| 56849/57600 [10:00:18<08:08,  1.54it/s]
 99%|█████████▊| 56850/57600 [10:00:19<08:02,  1.55it/s]
 99%|█████████▊| 56851/57600 [10:00:20<08:00,  1.56it/s]
 99%|█████████▊| 56852/57600 [10:00:20<07:58,  1.56it/s]
 99%|█████████▊| 56853/57600 [10:00:21<07:49,  1.59it/s]
 99%|█████████▊| 56854/57600 [10:00:22<07:36,  1.63it/s]
 99%|█████████▊| 56855/57600 [10:00:22<07:31,  1.65it/s]
 99%|█████████▊| 56856/57600 [10:00:23<07:24,  1.67it/s]
 99%|█████████▊| 56857/57600 [10:00:23<07:18,  1.69it/s]
 99%|█████████▊| 56858/57600 [10:00:24<07:40,  1.61it/s]
 99%|█████████▊| 56859/57600 [10:00:25<07:33,  1.64it/s]
 99%|█████████▊| 56860/57600 [10:00:25<07:28,  1.65it/s]
                                                        
{'loss': 1.1344, 'learning_rate': 1.1160278745644601e-07, 'epoch': 627.59}

 99%|█████████▊| 56860/57600 [10:00:25<07:28,  1.65it/s]
 99%|█████████▊| 56861/57600 [10:00:26<07:25,  1.66it/s]
 99%|█████████▊| 56862/57600 [10:00:26<07:25,  1.66it/s]
 99%|█████████▊| 56863/57600 [10:00:27<07:26,  1.65it/s]
 99%|█████████▊| 56864/57600 [10:00:28<07:43,  1.59it/s]
 99%|█████████▊| 56865/57600 [10:00:28<07:33,  1.62it/s]
 99%|█████████▊| 56866/57600 [10:00:29<07:23,  1.66it/s]
 99%|█████████▊| 56867/57600 [10:00:29<07:39,  1.60it/s]
 99%|█████████▊| 56868/57600 [10:00:30<07:24,  1.65it/s]
 99%|█████████▊| 56869/57600 [10:00:31<07:18,  1.67it/s]
 99%|█████████▊| 56870/57600 [10:00:31<07:40,  1.58it/s]
 99%|█████████▊| 56871/57600 [10:00:32<07:32,  1.61it/s]
 99%|█████████▊| 56872/57600 [10:00:32<07:16,  1.67it/s]
 99%|█████████▊| 56873/57600 [10:00:33<07:17,  1.66it/s]
 99%|█████████▊| 56874/57600 [10:00:34<07:21,  1.65it/s]
 99%|█████████▊| 56875/57600 [10:00:34<07:27,  1.62it/s]
 99%|█████████▊| 56876/57600 [10:00:35<07:39,  1.58it/s]
 99%|█████████▊| 56877/57600 [10:00:36<07:36,  1.58it/s]
 99%|█████████▊| 56878/57600 [10:00:36<07:45,  1.55it/s]
 99%|█████████▊| 56879/57600 [10:00:37<07:46,  1.55it/s]
 99%|█████████▉| 56880/57600 [10:00:38<07:44,  1.55it/s]
                                                        
{'loss': 1.1029, 'learning_rate': 1.1128919860627172e-07, 'epoch': 627.81}

 99%|█████████▉| 56880/57600 [10:00:38<07:44,  1.55it/s]
 99%|█████████▉| 56881/57600 [10:00:38<07:25,  1.61it/s]
 99%|█████████▉| 56882/57600 [10:00:39<07:30,  1.59it/s]
 99%|█████████▉| 56883/57600 [10:00:39<07:21,  1.62it/s]
 99%|█████████▉| 56884/57600 [10:00:40<07:39,  1.56it/s]
 99%|█████████▉| 56885/57600 [10:00:41<07:39,  1.56it/s]
 99%|█████████▉| 56886/57600 [10:00:41<07:20,  1.62it/s]
 99%|█████████▉| 56887/57600 [10:00:42<07:22,  1.61it/s]
 99%|█████████▉| 56888/57600 [10:00:43<07:22,  1.61it/s]
 99%|█████████▉| 56889/57600 [10:00:43<07:22,  1.61it/s]
 99%|█████████▉| 56890/57600 [10:00:44<07:16,  1.63it/s]
 99%|█████████▉| 56891/57600 [10:00:44<07:21,  1.61it/s]
 99%|█████████▉| 56892/57600 [10:00:45<07:28,  1.58it/s]
 99%|█████████▉| 56893/57600 [10:00:46<07:28,  1.58it/s]
 99%|█████████▉| 56894/57600 [10:00:46<07:29,  1.57it/s]
 99%|█████████▉| 56895/57600 [10:00:47<07:25,  1.58it/s]
 99%|█████████▉| 56896/57600 [10:00:48<07:19,  1.60it/s]
 99%|█████████▉| 56897/57600 [10:00:48<07:43,  1.52it/s]
 99%|█████████▉| 56898/57600 [10:00:49<07:27,  1.57it/s]
 99%|█████████▉| 56899/57600 [10:00:50<07:30,  1.56it/s]
 99%|█████████▉| 56900/57600 [10:00:50<07:22,  1.58it/s]
                                                        
{'loss': 1.0907, 'learning_rate': 1.1097560975609757e-07, 'epoch': 628.04}

 99%|█████████▉| 56900/57600 [10:00:50<07:22,  1.58it/s]
 99%|█████████▉| 56901/57600 [10:00:51<07:18,  1.59it/s]
 99%|█████████▉| 56902/57600 [10:00:51<07:30,  1.55it/s]
 99%|█████████▉| 56903/57600 [10:00:52<07:13,  1.61it/s]
 99%|█████████▉| 56904/57600 [10:00:53<07:39,  1.52it/s]
 99%|█████████▉| 56905/57600 [10:00:53<07:34,  1.53it/s]
 99%|█████████▉| 56906/57600 [10:00:54<07:18,  1.58it/s]
 99%|█████████▉| 56907/57600 [10:00:55<07:20,  1.57it/s]
 99%|█████████▉| 56908/57600 [10:00:55<07:20,  1.57it/s]
 99%|█████████▉| 56909/57600 [10:00:56<07:10,  1.60it/s]
 99%|█████████▉| 56910/57600 [10:00:57<07:08,  1.61it/s]
 99%|█████████▉| 56911/57600 [10:00:57<07:00,  1.64it/s]
 99%|█████████▉| 56912/57600 [10:00:58<07:08,  1.60it/s]
 99%|█████████▉| 56913/57600 [10:00:58<07:09,  1.60it/s]
 99%|█████████▉| 56914/57600 [10:00:59<07:00,  1.63it/s]
 99%|█████████▉| 56915/57600 [10:01:00<06:59,  1.63it/s]
 99%|█████████▉| 56916/57600 [10:01:00<07:15,  1.57it/s]
 99%|█████████▉| 56917/57600 [10:01:01<07:06,  1.60it/s]
 99%|█████████▉| 56918/57600 [10:01:01<07:07,  1.60it/s]
 99%|█████████▉| 56919/57600 [10:01:02<06:56,  1.63it/s]
 99%|█████████▉| 56920/57600 [10:01:03<06:48,  1.67it/s]
                                                        
{'loss': 1.088, 'learning_rate': 1.1066202090592329e-07, 'epoch': 628.26}

 99%|█████████▉| 56920/57600 [10:01:03<06:48,  1.67it/s]
 99%|█████████▉| 56921/57600 [10:01:03<06:43,  1.68it/s]
 99%|█████████▉| 56922/57600 [10:01:04<06:53,  1.64it/s]
 99%|█████████▉| 56923/57600 [10:01:04<06:46,  1.66it/s]
 99%|█████████▉| 56924/57600 [10:01:05<06:54,  1.63it/s]
 99%|█████████▉| 56925/57600 [10:01:06<06:48,  1.65it/s]
 99%|█████████▉| 56926/57600 [10:01:06<06:53,  1.63it/s]
 99%|█████████▉| 56927/57600 [10:01:07<07:03,  1.59it/s]
 99%|█████████▉| 56928/57600 [10:01:08<07:03,  1.59it/s]
 99%|█████████▉| 56929/57600 [10:01:08<07:11,  1.55it/s]
 99%|█████████▉| 56930/57600 [10:01:09<06:57,  1.60it/s]
 99%|█████████▉| 56931/57600 [10:01:09<06:58,  1.60it/s]
 99%|█████████▉| 56932/57600 [10:01:10<07:02,  1.58it/s]
 99%|█████████▉| 56933/57600 [10:01:11<07:24,  1.50it/s]
 99%|█████████▉| 56934/57600 [10:01:12<07:16,  1.53it/s]
 99%|█████████▉| 56935/57600 [10:01:12<07:16,  1.53it/s]
 99%|█████████▉| 56936/57600 [10:01:13<07:03,  1.57it/s]
 99%|█████████▉| 56937/57600 [10:01:13<07:01,  1.57it/s]
 99%|█████████▉| 56938/57600 [10:01:14<07:09,  1.54it/s]
 99%|█████████▉| 56939/57600 [10:01:15<06:50,  1.61it/s]
 99%|█████████▉| 56940/57600 [10:01:15<06:51,  1.60it/s]
                                                        
{'loss': 1.0601, 'learning_rate': 1.1034843205574912e-07, 'epoch': 628.48}

 99%|█████████▉| 56940/57600 [10:01:15<06:51,  1.60it/s]
 99%|█████████▉| 56941/57600 [10:01:16<06:47,  1.62it/s]
 99%|█████████▉| 56942/57600 [10:01:16<06:35,  1.67it/s]
 99%|█████████▉| 56943/57600 [10:01:17<06:35,  1.66it/s]
 99%|█████████▉| 56944/57600 [10:01:18<06:36,  1.66it/s]
 99%|█████████▉| 56945/57600 [10:01:18<06:24,  1.70it/s]
 99%|█████████▉| 56946/57600 [10:01:19<06:38,  1.64it/s]
 99%|█████████▉| 56947/57600 [10:01:19<06:25,  1.69it/s]
 99%|█████████▉| 56948/57600 [10:01:20<06:35,  1.65it/s]
 99%|█████████▉| 56949/57600 [10:01:21<06:46,  1.60it/s]
 99%|█████████▉| 56950/57600 [10:01:21<06:56,  1.56it/s]
 99%|█████████▉| 56951/57600 [10:01:22<06:49,  1.58it/s]
 99%|█████████▉| 56952/57600 [10:01:23<06:35,  1.64it/s]
 99%|█████████▉| 56953/57600 [10:01:23<06:37,  1.63it/s]
 99%|█████████▉| 56954/57600 [10:01:24<06:29,  1.66it/s]
 99%|█████████▉| 56955/57600 [10:01:24<06:27,  1.67it/s]
 99%|█████████▉| 56956/57600 [10:01:25<06:29,  1.65it/s]
 99%|█████████▉| 56957/57600 [10:01:26<06:35,  1.62it/s]
 99%|█████████▉| 56958/57600 [10:01:26<06:47,  1.58it/s]
 99%|█████████▉| 56959/57600 [10:01:27<06:35,  1.62it/s]
 99%|█████████▉| 56960/57600 [10:01:28<06:39,  1.60it/s]
                                                        
{'loss': 1.1104, 'learning_rate': 1.1003484320557493e-07, 'epoch': 628.7}

 99%|█████████▉| 56960/57600 [10:01:28<06:39,  1.60it/s]
 99%|█████████▉| 56961/57600 [10:01:28<06:39,  1.60it/s]
 99%|█████████▉| 56962/57600 [10:01:29<06:54,  1.54it/s]
 99%|█████████▉| 56963/57600 [10:01:30<06:57,  1.52it/s]
 99%|█████████▉| 56964/57600 [10:01:30<06:54,  1.54it/s]
 99%|█████████▉| 56965/57600 [10:01:31<06:34,  1.61it/s]
 99%|█████████▉| 56966/57600 [10:01:31<06:34,  1.61it/s]
 99%|█████████▉| 56967/57600 [10:01:32<06:26,  1.64it/s]
 99%|█████████▉| 56968/57600 [10:01:33<06:23,  1.65it/s]
 99%|█████████▉| 56969/57600 [10:01:33<06:24,  1.64it/s]
 99%|█████████▉| 56970/57600 [10:01:34<06:29,  1.62it/s]
 99%|█████████▉| 56971/57600 [10:01:34<06:26,  1.63it/s]
 99%|█████████▉| 56972/57600 [10:01:35<06:20,  1.65it/s]
 99%|█████████▉| 56973/57600 [10:01:36<06:24,  1.63it/s]
 99%|█████████▉| 56974/57600 [10:01:36<06:30,  1.60it/s]
 99%|█████████▉| 56975/57600 [10:01:37<06:50,  1.52it/s]
 99%|█████████▉| 56976/57600 [10:01:38<06:38,  1.57it/s]
 99%|█████████▉| 56977/57600 [10:01:38<06:30,  1.60it/s]
 99%|█████████▉| 56978/57600 [10:01:39<06:34,  1.58it/s]
 99%|█████████▉| 56979/57600 [10:01:39<06:34,  1.57it/s]
 99%|█████████▉| 56980/57600 [10:01:40<06:26,  1.60it/s]
                                                        
{'loss': 1.0918, 'learning_rate': 1.0972125435540067e-07, 'epoch': 628.92}

 99%|█████████▉| 56980/57600 [10:01:40<06:26,  1.60it/s]
 99%|█████████▉| 56981/57600 [10:01:41<06:19,  1.63it/s]
 99%|█████████▉| 56982/57600 [10:01:41<06:11,  1.66it/s]
 99%|█████████▉| 56983/57600 [10:01:42<06:09,  1.67it/s]
 99%|█████████▉| 56984/57600 [10:01:42<06:16,  1.64it/s]
 99%|█████████▉| 56985/57600 [10:01:43<06:29,  1.58it/s]
 99%|█████████▉| 56986/57600 [10:01:44<06:36,  1.55it/s]
 99%|█████████▉| 56987/57600 [10:01:44<06:35,  1.55it/s]
 99%|█████████▉| 56988/57600 [10:01:45<06:52,  1.48it/s]
 99%|█████████▉| 56989/57600 [10:01:46<06:46,  1.50it/s]
 99%|█████████▉| 56990/57600 [10:01:46<06:30,  1.56it/s]
 99%|█████████▉| 56991/57600 [10:01:47<06:32,  1.55it/s]
 99%|█████████▉| 56992/57600 [10:01:48<06:23,  1.58it/s]
 99%|█████████▉| 56993/57600 [10:01:48<06:28,  1.56it/s]
 99%|█████████▉| 56994/57600 [10:01:49<06:39,  1.52it/s]
 99%|█████████▉| 56995/57600 [10:01:50<06:32,  1.54it/s]
 99%|█████████▉| 56996/57600 [10:01:50<06:30,  1.55it/s]
 99%|█████████▉| 56997/57600 [10:01:51<06:29,  1.55it/s]
 99%|█████████▉| 56998/57600 [10:01:52<06:17,  1.59it/s]
 99%|█████████▉| 56999/57600 [10:01:52<06:13,  1.61it/s]
 99%|█████████▉| 57000/57600 [10:01:53<06:26,  1.55it/s]
                                                        
{'loss': 1.1119, 'learning_rate': 1.094076655052265e-07, 'epoch': 629.14}

 99%|█████████▉| 57000/57600 [10:01:53<06:26,  1.55it/s]
 99%|█████████▉| 57001/57600 [10:01:54<06:33,  1.52it/s]
 99%|█████████▉| 57002/57600 [10:01:54<06:33,  1.52it/s]
 99%|█████████▉| 57003/57600 [10:01:55<06:21,  1.56it/s]
 99%|█████████▉| 57004/57600 [10:01:55<06:17,  1.58it/s]
 99%|█████████▉| 57005/57600 [10:01:56<06:11,  1.60it/s]
 99%|█████████▉| 57006/57600 [10:01:57<05:59,  1.65it/s]
 99%|█████████▉| 57007/57600 [10:01:57<06:02,  1.64it/s]
 99%|█████████▉| 57008/57600 [10:01:58<05:50,  1.69it/s]
 99%|█████████▉| 57009/57600 [10:01:58<06:01,  1.63it/s]
 99%|█████████▉| 57010/57600 [10:01:59<05:58,  1.65it/s]
 99%|█████████▉| 57011/57600 [10:02:00<05:53,  1.67it/s]
 99%|█████████▉| 57012/57600 [10:02:00<05:51,  1.67it/s]
 99%|█████████▉| 57013/57600 [10:02:01<05:56,  1.65it/s]
 99%|█████████▉| 57014/57600 [10:02:02<06:18,  1.55it/s]
 99%|█████████▉| 57015/57600 [10:02:02<06:12,  1.57it/s]
 99%|█████████▉| 57016/57600 [10:02:03<06:08,  1.59it/s]
 99%|█████████▉| 57017/57600 [10:02:03<06:00,  1.62it/s]
 99%|█████████▉| 57018/57600 [10:02:04<05:53,  1.65it/s]
 99%|█████████▉| 57019/57600 [10:02:05<05:50,  1.66it/s]
 99%|█████████▉| 57020/57600 [10:02:05<05:58,  1.62it/s]
                                                        
{'loss': 1.0701, 'learning_rate': 1.0909407665505222e-07, 'epoch': 629.36}

 99%|█████████▉| 57020/57600 [10:02:05<05:58,  1.62it/s]
 99%|█████████▉| 57021/57600 [10:02:06<06:02,  1.60it/s]
 99%|█████████▉| 57022/57600 [10:02:06<06:00,  1.60it/s]
 99%|█████████▉| 57023/57600 [10:02:07<05:53,  1.63it/s]
 99%|█████████▉| 57024/57600 [10:02:08<05:55,  1.62it/s]
 99%|█████████▉| 57025/57600 [10:02:08<05:56,  1.61it/s]
 99%|█████████▉| 57026/57600 [10:02:09<06:00,  1.59it/s]
 99%|█████████▉| 57027/57600 [10:02:10<05:52,  1.62it/s]
 99%|█████████▉| 57028/57600 [10:02:10<05:55,  1.61it/s]
 99%|█████████▉| 57029/57600 [10:02:11<05:50,  1.63it/s]
 99%|█████████▉| 57030/57600 [10:02:11<05:54,  1.61it/s]
 99%|█████████▉| 57031/57600 [10:02:12<05:49,  1.63it/s]
 99%|█████████▉| 57032/57600 [10:02:13<05:51,  1.62it/s]
 99%|█████████▉| 57033/57600 [10:02:13<05:40,  1.66it/s]
 99%|█████████▉| 57034/57600 [10:02:14<05:58,  1.58it/s]
 99%|█████████▉| 57035/57600 [10:02:15<06:00,  1.57it/s]
 99%|█████████▉| 57036/57600 [10:02:15<05:56,  1.58it/s]
 99%|█████████▉| 57037/57600 [10:02:16<05:51,  1.60it/s]
 99%|█████████▉| 57038/57600 [10:02:16<06:03,  1.54it/s]
 99%|█████████▉| 57039/57600 [10:02:17<05:55,  1.58it/s]
 99%|█████████▉| 57040/57600 [10:02:18<05:57,  1.56it/s]
                                                        
{'loss': 1.0944, 'learning_rate': 1.0878048780487805e-07, 'epoch': 629.58}

 99%|█████████▉| 57040/57600 [10:02:18<05:57,  1.56it/s]
 99%|█████████▉| 57041/57600 [10:02:18<05:59,  1.55it/s]
 99%|█████████▉| 57042/57600 [10:02:19<05:47,  1.61it/s]
 99%|█████████▉| 57043/57600 [10:02:20<05:36,  1.65it/s]
 99%|█████████▉| 57044/57600 [10:02:20<05:37,  1.65it/s]
 99%|█████████▉| 57045/57600 [10:02:21<05:27,  1.70it/s]
 99%|█████████▉| 57046/57600 [10:02:21<05:25,  1.70it/s]
 99%|█████████▉| 57047/57600 [10:02:22<05:28,  1.68it/s]
 99%|█████████▉| 57048/57600 [10:02:23<05:42,  1.61it/s]
 99%|█████████▉| 57049/57600 [10:02:23<05:41,  1.61it/s]
 99%|█████████▉| 57050/57600 [10:02:24<05:49,  1.57it/s]
 99%|█████████▉| 57051/57600 [10:02:25<05:57,  1.54it/s]
 99%|█████████▉| 57052/57600 [10:02:25<05:46,  1.58it/s]
 99%|█████████▉| 57053/57600 [10:02:26<05:42,  1.60it/s]
 99%|█████████▉| 57054/57600 [10:02:26<05:40,  1.60it/s]
 99%|█████████▉| 57055/57600 [10:02:27<05:37,  1.61it/s]
 99%|█████████▉| 57056/57600 [10:02:28<05:38,  1.61it/s]
 99%|█████████▉| 57057/57600 [10:02:28<05:43,  1.58it/s]
 99%|█████████▉| 57058/57600 [10:02:29<05:45,  1.57it/s]
 99%|█████████▉| 57059/57600 [10:02:29<05:38,  1.60it/s]
 99%|█████████▉| 57060/57600 [10:02:30<05:42,  1.58it/s]
                                                        
{'loss': 1.0935, 'learning_rate': 1.0846689895470378e-07, 'epoch': 629.8}

 99%|█████████▉| 57060/57600 [10:02:30<05:42,  1.58it/s]
 99%|█████████▉| 57061/57600 [10:02:31<05:41,  1.58it/s]
 99%|█████████▉| 57062/57600 [10:02:31<05:35,  1.60it/s]
 99%|█████████▉| 57063/57600 [10:02:32<05:42,  1.57it/s]
 99%|█████████▉| 57064/57600 [10:02:33<05:28,  1.63it/s]
 99%|█████████▉| 57065/57600 [10:02:33<05:30,  1.62it/s]
 99%|█████████▉| 57066/57600 [10:02:34<05:30,  1.62it/s]
 99%|█████████▉| 57067/57600 [10:02:34<05:25,  1.64it/s]
 99%|█████████▉| 57068/57600 [10:02:35<05:29,  1.61it/s]
 99%|█████████▉| 57069/57600 [10:02:36<05:20,  1.65it/s]
 99%|█████████▉| 57070/57600 [10:02:36<05:16,  1.67it/s]
 99%|█████████▉| 57071/57600 [10:02:37<05:17,  1.67it/s]
 99%|█████████▉| 57072/57600 [10:02:37<05:08,  1.71it/s]
 99%|█████████▉| 57073/57600 [10:02:38<05:09,  1.70it/s]
 99%|█████████▉| 57074/57600 [10:02:39<05:10,  1.69it/s]
 99%|█████████▉| 57075/57600 [10:02:39<05:16,  1.66it/s]
 99%|█████████▉| 57076/57600 [10:02:40<05:28,  1.59it/s]
 99%|█████████▉| 57077/57600 [10:02:40<05:21,  1.63it/s]
 99%|█████████▉| 57078/57600 [10:02:41<05:25,  1.60it/s]
 99%|█████████▉| 57079/57600 [10:02:42<05:24,  1.61it/s]
 99%|█████████▉| 57080/57600 [10:02:42<05:37,  1.54it/s]
                                                        
{'loss': 1.1178, 'learning_rate': 1.081533101045296e-07, 'epoch': 630.02}

 99%|█████████▉| 57080/57600 [10:02:42<05:37,  1.54it/s]
 99%|█████████▉| 57081/57600 [10:02:43<05:29,  1.58it/s]
 99%|█████████▉| 57082/57600 [10:02:44<05:27,  1.58it/s]
 99%|█████████▉| 57083/57600 [10:02:44<05:18,  1.62it/s]
 99%|█████████▉| 57084/57600 [10:02:45<05:17,  1.63it/s]
 99%|█████████▉| 57085/57600 [10:02:45<05:08,  1.67it/s]
 99%|█████████▉| 57086/57600 [10:02:46<05:14,  1.63it/s]
 99%|█████████▉| 57087/57600 [10:02:47<05:10,  1.65it/s]
 99%|█████████▉| 57088/57600 [10:02:47<05:05,  1.68it/s]
 99%|█████████▉| 57089/57600 [10:02:48<05:16,  1.61it/s]
 99%|█████████▉| 57090/57600 [10:02:48<05:11,  1.64it/s]
 99%|█████████▉| 57091/57600 [10:02:49<05:11,  1.63it/s]
 99%|█████████▉| 57092/57600 [10:02:50<05:10,  1.64it/s]
 99%|█████████▉| 57093/57600 [10:02:50<05:08,  1.64it/s]
 99%|█████████▉| 57094/57600 [10:02:51<05:16,  1.60it/s]
 99%|█████████▉| 57095/57600 [10:02:52<05:11,  1.62it/s]
 99%|█████████▉| 57096/57600 [10:02:52<05:10,  1.62it/s]
 99%|█████████▉| 57097/57600 [10:02:53<05:28,  1.53it/s]
 99%|█████████▉| 57098/57600 [10:02:54<05:35,  1.50it/s]
 99%|█████████▉| 57099/57600 [10:02:54<05:35,  1.50it/s]
 99%|█████████▉| 57100/57600 [10:02:55<05:25,  1.54it/s]
                                                        
{'loss': 1.0934, 'learning_rate': 1.0783972125435543e-07, 'epoch': 630.24}

 99%|█████████▉| 57100/57600 [10:02:55<05:25,  1.54it/s]
 99%|█████████▉| 57101/57600 [10:02:56<05:23,  1.54it/s]
 99%|█████████▉| 57102/57600 [10:02:56<05:37,  1.47it/s]
 99%|█████████▉| 57103/57600 [10:02:57<05:24,  1.53it/s]
 99%|█████████▉| 57104/57600 [10:02:58<05:27,  1.51it/s]
 99%|█████████▉| 57105/57600 [10:02:58<05:26,  1.52it/s]
 99%|█████████▉| 57106/57600 [10:02:59<05:22,  1.53it/s]
 99%|█████████▉| 57107/57600 [10:02:59<05:16,  1.56it/s]
 99%|█████████▉| 57108/57600 [10:03:00<05:02,  1.63it/s]
 99%|█████████▉| 57109/57600 [10:03:01<04:57,  1.65it/s]
 99%|█████████▉| 57110/57600 [10:03:01<04:51,  1.68it/s]
 99%|█████████▉| 57111/57600 [10:03:02<04:59,  1.63it/s]
 99%|█████████▉| 57112/57600 [10:03:02<04:54,  1.66it/s]
 99%|█████████▉| 57113/57600 [10:03:03<04:58,  1.63it/s]
 99%|█████████▉| 57114/57600 [10:03:04<05:05,  1.59it/s]
 99%|█████████▉| 57115/57600 [10:03:04<04:58,  1.62it/s]
 99%|█████████▉| 57116/57600 [10:03:05<05:03,  1.59it/s]
 99%|█████████▉| 57117/57600 [10:03:06<05:18,  1.51it/s]
 99%|█████████▉| 57118/57600 [10:03:06<05:23,  1.49it/s]
 99%|█████████▉| 57119/57600 [10:03:07<05:14,  1.53it/s]
 99%|█████████▉| 57120/57600 [10:03:08<05:19,  1.50it/s]
                                                        
{'loss': 1.057, 'learning_rate': 1.0752613240418116e-07, 'epoch': 630.46}

 99%|█████████▉| 57120/57600 [10:03:08<05:19,  1.50it/s]
 99%|█████████▉| 57121/57600 [10:03:08<05:17,  1.51it/s]
 99%|█████████▉| 57122/57600 [10:03:09<05:18,  1.50it/s]
 99%|█████████▉| 57123/57600 [10:03:10<05:11,  1.53it/s]
 99%|█████████▉| 57124/57600 [10:03:10<05:00,  1.58it/s]
 99%|█████████▉| 57125/57600 [10:03:11<04:50,  1.63it/s]
 99%|█████████▉| 57126/57600 [10:03:11<04:45,  1.66it/s]
 99%|█████████▉| 57127/57600 [10:03:12<04:44,  1.66it/s]
 99%|█████████▉| 57128/57600 [10:03:13<04:48,  1.64it/s]
 99%|█████████▉| 57129/57600 [10:03:13<04:46,  1.64it/s]
 99%|█████████▉| 57130/57600 [10:03:14<04:35,  1.70it/s]
 99%|█████████▉| 57131/57600 [10:03:14<04:35,  1.70it/s]
 99%|█████████▉| 57132/57600 [10:03:15<04:35,  1.70it/s]
 99%|█████████▉| 57133/57600 [10:03:16<04:44,  1.64it/s]
 99%|█████████▉| 57134/57600 [10:03:16<04:43,  1.65it/s]
 99%|█████████▉| 57135/57600 [10:03:17<04:44,  1.64it/s]
 99%|█████████▉| 57136/57600 [10:03:17<04:46,  1.62it/s]
 99%|█████████▉| 57137/57600 [10:03:18<04:48,  1.61it/s]
 99%|█████████▉| 57138/57600 [10:03:19<04:52,  1.58it/s]
 99%|█████████▉| 57139/57600 [10:03:19<04:47,  1.60it/s]
 99%|█████████▉| 57140/57600 [10:03:20<04:42,  1.63it/s]
                                                        
{'loss': 1.1279, 'learning_rate': 1.0721254355400699e-07, 'epoch': 630.68}

 99%|█████████▉| 57140/57600 [10:03:20<04:42,  1.63it/s]
 99%|█████████▉| 57141/57600 [10:03:21<04:37,  1.65it/s]
 99%|█████████▉| 57142/57600 [10:03:21<04:38,  1.64it/s]
 99%|█████████▉| 57143/57600 [10:03:22<04:37,  1.65it/s]
 99%|█████████▉| 57144/57600 [10:03:22<04:39,  1.63it/s]
 99%|█████████▉| 57145/57600 [10:03:23<04:34,  1.66it/s]
 99%|█████████▉| 57146/57600 [10:03:24<04:38,  1.63it/s]
 99%|█████████▉| 57147/57600 [10:03:24<04:41,  1.61it/s]
 99%|█████████▉| 57148/57600 [10:03:25<04:32,  1.66it/s]
 99%|█████████▉| 57149/57600 [10:03:25<04:30,  1.67it/s]
 99%|█████████▉| 57150/57600 [10:03:26<04:41,  1.60it/s]
 99%|█████████▉| 57151/57600 [10:03:27<04:37,  1.62it/s]
 99%|█████████▉| 57152/57600 [10:03:27<04:47,  1.56it/s]
 99%|█████████▉| 57153/57600 [10:03:28<04:43,  1.57it/s]
 99%|█████████▉| 57154/57600 [10:03:29<04:41,  1.58it/s]
 99%|█████████▉| 57155/57600 [10:03:29<04:46,  1.55it/s]
 99%|█████████▉| 57156/57600 [10:03:30<04:37,  1.60it/s]
 99%|█████████▉| 57157/57600 [10:03:31<04:40,  1.58it/s]
 99%|█████████▉| 57158/57600 [10:03:31<04:32,  1.62it/s]
 99%|█████████▉| 57159/57600 [10:03:32<04:31,  1.62it/s]
 99%|█████████▉| 57160/57600 [10:03:32<04:30,  1.63it/s]
                                                        
{'loss': 1.093, 'learning_rate': 1.0689895470383271e-07, 'epoch': 630.91}

 99%|█████████▉| 57160/57600 [10:03:32<04:30,  1.63it/s]
 99%|█████████▉| 57161/57600 [10:03:33<04:34,  1.60it/s]
 99%|█████████▉| 57162/57600 [10:03:34<04:33,  1.60it/s]
 99%|█████████▉| 57163/57600 [10:03:34<04:42,  1.55it/s]
 99%|█████████▉| 57164/57600 [10:03:35<04:40,  1.55it/s]
 99%|█████████▉| 57165/57600 [10:03:36<04:32,  1.59it/s]
 99%|█████████▉| 57166/57600 [10:03:36<04:36,  1.57it/s]
 99%|█████████▉| 57167/57600 [10:03:37<04:40,  1.55it/s]
 99%|█████████▉| 57168/57600 [10:03:37<04:34,  1.57it/s]
 99%|█████████▉| 57169/57600 [10:03:38<04:39,  1.54it/s]
 99%|█████████▉| 57170/57600 [10:03:39<04:36,  1.56it/s]
 99%|█████████▉| 57171/57600 [10:03:39<04:26,  1.61it/s]
 99%|█████████▉| 57172/57600 [10:03:40<04:50,  1.48it/s]
 99%|█████████▉| 57173/57600 [10:03:41<04:44,  1.50it/s]
 99%|█████████▉| 57174/57600 [10:03:41<04:35,  1.55it/s]
 99%|█████████▉| 57175/57600 [10:03:42<04:25,  1.60it/s]
 99%|█████████▉| 57176/57600 [10:03:43<04:24,  1.60it/s]
 99%|█████████▉| 57177/57600 [10:03:43<04:17,  1.65it/s]
 99%|█████████▉| 57178/57600 [10:03:44<04:17,  1.64it/s]
 99%|█████████▉| 57179/57600 [10:03:44<04:19,  1.62it/s]
 99%|█████████▉| 57180/57600 [10:03:45<04:11,  1.67it/s]
                                                        
{'loss': 1.0932, 'learning_rate': 1.0658536585365854e-07, 'epoch': 631.13}

 99%|█████████▉| 57180/57600 [10:03:45<04:11,  1.67it/s]
 99%|█████████▉| 57181/57600 [10:03:46<04:14,  1.64it/s]
 99%|█████████▉| 57182/57600 [10:03:46<04:14,  1.64it/s]
 99%|█████████▉| 57183/57600 [10:03:47<04:21,  1.59it/s]
 99%|█████████▉| 57184/57600 [10:03:47<04:19,  1.61it/s]
 99%|█████████▉| 57185/57600 [10:03:48<04:20,  1.59it/s]
 99%|█████████▉| 57186/57600 [10:03:49<04:29,  1.54it/s]
 99%|█████████▉| 57187/57600 [10:03:49<04:24,  1.56it/s]
 99%|█████████▉| 57188/57600 [10:03:50<04:16,  1.60it/s]
 99%|█████████▉| 57189/57600 [10:03:51<04:18,  1.59it/s]
 99%|█████████▉| 57190/57600 [10:03:51<04:21,  1.57it/s]
 99%|█████████▉| 57191/57600 [10:03:52<04:27,  1.53it/s]
 99%|█████████▉| 57192/57600 [10:03:53<04:26,  1.53it/s]
 99%|█████████▉| 57193/57600 [10:03:53<04:31,  1.50it/s]
 99%|█████████▉| 57194/57600 [10:03:54<04:19,  1.57it/s]
 99%|█████████▉| 57195/57600 [10:03:55<04:14,  1.59it/s]
 99%|█████████▉| 57196/57600 [10:03:55<04:08,  1.63it/s]
 99%|█████████▉| 57197/57600 [10:03:56<04:07,  1.63it/s]
 99%|█████████▉| 57198/57600 [10:03:56<04:06,  1.63it/s]
 99%|█████████▉| 57199/57600 [10:03:57<04:05,  1.64it/s]
 99%|█████████▉| 57200/57600 [10:03:58<04:04,  1.63it/s]
                                                        
{'loss': 1.0942, 'learning_rate': 1.0627177700348436e-07, 'epoch': 631.35}

 99%|█████████▉| 57200/57600 [10:03:58<04:04,  1.63it/s]
 99%|█████████▉| 57201/57600 [10:03:58<04:08,  1.61it/s]
 99%|█████████▉| 57202/57600 [10:03:59<04:13,  1.57it/s]
 99%|█████████▉| 57203/57600 [10:03:59<04:07,  1.61it/s]
 99%|█████████▉| 57204/57600 [10:04:00<04:09,  1.59it/s]
 99%|█████████▉| 57205/57600 [10:04:01<04:04,  1.62it/s]
 99%|█████████▉| 57206/57600 [10:04:01<03:57,  1.66it/s]
 99%|█████████▉| 57207/57600 [10:04:02<03:56,  1.66it/s]
 99%|█████████▉| 57208/57600 [10:04:03<04:03,  1.61it/s]
 99%|█████████▉| 57209/57600 [10:04:03<04:03,  1.60it/s]
 99%|█████████▉| 57210/57600 [10:04:04<04:00,  1.62it/s]
 99%|█████████▉| 57211/57600 [10:04:04<03:54,  1.66it/s]
 99%|█████████▉| 57212/57600 [10:04:05<03:53,  1.66it/s]
 99%|█████████▉| 57213/57600 [10:04:06<03:54,  1.65it/s]
 99%|█████████▉| 57214/57600 [10:04:06<03:54,  1.65it/s]
 99%|█████████▉| 57215/57600 [10:04:07<04:03,  1.58it/s]
 99%|█████████▉| 57216/57600 [10:04:08<04:09,  1.54it/s]
 99%|█████████▉| 57217/57600 [10:04:08<04:09,  1.54it/s]
 99%|█████████▉| 57218/57600 [10:04:09<04:04,  1.56it/s]
 99%|█████████▉| 57219/57600 [10:04:09<03:58,  1.60it/s]
 99%|█████████▉| 57220/57600 [10:04:10<03:58,  1.60it/s]
                                                        
{'loss': 1.0939, 'learning_rate': 1.0595818815331009e-07, 'epoch': 631.57}

 99%|█████████▉| 57220/57600 [10:04:10<03:58,  1.60it/s]
 99%|█████████▉| 57221/57600 [10:04:11<03:52,  1.63it/s]
 99%|█████████▉| 57222/57600 [10:04:11<03:52,  1.62it/s]
 99%|█████████▉| 57223/57600 [10:04:12<03:52,  1.62it/s]
 99%|█████████▉| 57224/57600 [10:04:12<03:50,  1.63it/s]
 99%|█████████▉| 57225/57600 [10:04:13<03:46,  1.65it/s]
 99%|█████████▉| 57226/57600 [10:04:14<03:48,  1.63it/s]
 99%|█████████▉| 57227/57600 [10:04:14<03:45,  1.66it/s]
 99%|█████████▉| 57228/57600 [10:04:15<03:41,  1.68it/s]
 99%|█████████▉| 57229/57600 [10:04:15<03:41,  1.68it/s]
 99%|█████████▉| 57230/57600 [10:04:16<03:39,  1.68it/s]
 99%|█████████▉| 57231/57600 [10:04:17<03:37,  1.70it/s]
 99%|█████████▉| 57232/57600 [10:04:17<03:41,  1.66it/s]
 99%|█████████▉| 57233/57600 [10:04:18<03:41,  1.66it/s]
 99%|█████████▉| 57234/57600 [10:04:19<03:45,  1.62it/s]
 99%|█████████▉| 57235/57600 [10:04:19<03:41,  1.65it/s]
 99%|█████████▉| 57236/57600 [10:04:20<03:46,  1.61it/s]
 99%|█████████▉| 57237/57600 [10:04:20<03:45,  1.61it/s]
 99%|█████████▉| 57238/57600 [10:04:21<03:45,  1.60it/s]
 99%|█████████▉| 57239/57600 [10:04:22<03:41,  1.63it/s]
 99%|█████████▉| 57240/57600 [10:04:22<03:39,  1.64it/s]
                                                        
{'loss': 1.1492, 'learning_rate': 1.0564459930313592e-07, 'epoch': 631.79}

 99%|█████████▉| 57240/57600 [10:04:22<03:39,  1.64it/s]
 99%|█████████▉| 57241/57600 [10:04:23<03:43,  1.61it/s]
 99%|█████████▉| 57242/57600 [10:04:23<03:36,  1.66it/s]
 99%|█████████▉| 57243/57600 [10:04:24<03:34,  1.67it/s]
 99%|█████████▉| 57244/57600 [10:04:25<03:41,  1.61it/s]
 99%|█████████▉| 57245/57600 [10:04:25<03:40,  1.61it/s]
 99%|█████████▉| 57246/57600 [10:04:26<03:44,  1.58it/s]
 99%|█████████▉| 57247/57600 [10:04:27<03:38,  1.62it/s]
 99%|█████████▉| 57248/57600 [10:04:27<03:36,  1.63it/s]
 99%|█████████▉| 57249/57600 [10:04:28<03:43,  1.57it/s]
 99%|█████████▉| 57250/57600 [10:04:28<03:34,  1.63it/s]
 99%|█████████▉| 57251/57600 [10:04:29<03:35,  1.62it/s]
 99%|█████████▉| 57252/57600 [10:04:30<03:37,  1.60it/s]
 99%|█████████▉| 57253/57600 [10:04:30<03:45,  1.54it/s]
 99%|█████████▉| 57254/57600 [10:04:31<03:46,  1.53it/s]
 99%|█████████▉| 57255/57600 [10:04:32<03:40,  1.56it/s]
 99%|█████████▉| 57256/57600 [10:04:32<03:40,  1.56it/s]
 99%|█████████▉| 57257/57600 [10:04:33<03:35,  1.59it/s]
 99%|█████████▉| 57258/57600 [10:04:33<03:31,  1.62it/s]
 99%|█████████▉| 57259/57600 [10:04:34<03:28,  1.64it/s]
 99%|█████████▉| 57260/57600 [10:04:35<03:43,  1.52it/s]
                                                        
{'loss': 1.0726, 'learning_rate': 1.0533101045296164e-07, 'epoch': 632.01}

 99%|█████████▉| 57260/57600 [10:04:35<03:43,  1.52it/s]
 99%|█████████▉| 57261/57600 [10:04:36<03:45,  1.50it/s]
 99%|█████████▉| 57262/57600 [10:04:36<03:40,  1.54it/s]
 99%|█████████▉| 57263/57600 [10:04:37<03:38,  1.54it/s]
 99%|█████████▉| 57264/57600 [10:04:37<03:32,  1.58it/s]
 99%|█████████▉| 57265/57600 [10:04:38<03:32,  1.58it/s]
 99%|█████████▉| 57266/57600 [10:04:39<03:33,  1.57it/s]
 99%|█████████▉| 57267/57600 [10:04:39<03:30,  1.58it/s]
 99%|█████████▉| 57268/57600 [10:04:40<03:27,  1.60it/s]
 99%|█████████▉| 57269/57600 [10:04:41<03:32,  1.56it/s]
 99%|█████████▉| 57270/57600 [10:04:41<03:34,  1.54it/s]
 99%|█████████▉| 57271/57600 [10:04:42<03:33,  1.54it/s]
 99%|█████████▉| 57272/57600 [10:04:43<03:30,  1.55it/s]
 99%|█████████▉| 57273/57600 [10:04:43<03:33,  1.53it/s]
 99%|█████████▉| 57274/57600 [10:04:44<03:31,  1.54it/s]
 99%|█████████▉| 57275/57600 [10:04:44<03:26,  1.57it/s]
 99%|█████████▉| 57276/57600 [10:04:45<03:28,  1.55it/s]
 99%|█████████▉| 57277/57600 [10:04:46<03:38,  1.48it/s]
 99%|█████████▉| 57278/57600 [10:04:47<03:37,  1.48it/s]
 99%|█████████▉| 57279/57600 [10:04:47<03:29,  1.53it/s]
 99%|█████████▉| 57280/57600 [10:04:48<03:28,  1.54it/s]
                                                        
{'loss': 1.0441, 'learning_rate': 1.0501742160278747e-07, 'epoch': 632.23}

 99%|█████████▉| 57280/57600 [10:04:48<03:28,  1.54it/s]
 99%|█████████▉| 57281/57600 [10:04:48<03:24,  1.56it/s]
 99%|█████████▉| 57282/57600 [10:04:49<03:20,  1.59it/s]
 99%|█████████▉| 57283/57600 [10:04:50<03:20,  1.58it/s]
 99%|█████████▉| 57284/57600 [10:04:50<03:19,  1.58it/s]
 99%|█████████▉| 57285/57600 [10:04:51<03:20,  1.57it/s]
 99%|█████████▉| 57286/57600 [10:04:52<03:18,  1.58it/s]
 99%|█████████▉| 57287/57600 [10:04:52<03:12,  1.63it/s]
 99%|█████████▉| 57288/57600 [10:04:53<03:18,  1.57it/s]
 99%|█████████▉| 57289/57600 [10:04:53<03:16,  1.59it/s]
 99%|█████████▉| 57290/57600 [10:04:54<03:15,  1.58it/s]
 99%|█████████▉| 57291/57600 [10:04:55<03:18,  1.56it/s]
 99%|█████████▉| 57292/57600 [10:04:55<03:10,  1.62it/s]
 99%|█████████▉| 57293/57600 [10:04:56<03:09,  1.62it/s]
 99%|█████████▉| 57294/57600 [10:04:57<03:11,  1.60it/s]
 99%|█████████▉| 57295/57600 [10:04:57<03:12,  1.59it/s]
 99%|█████████▉| 57296/57600 [10:04:58<03:12,  1.58it/s]
 99%|█████████▉| 57297/57600 [10:04:58<03:09,  1.60it/s]
 99%|█████████▉| 57298/57600 [10:04:59<03:07,  1.61it/s]
 99%|█████████▉| 57299/57600 [10:05:00<03:02,  1.65it/s]
 99%|█████████▉| 57300/57600 [10:05:00<02:59,  1.68it/s]
                                                        
{'loss': 1.1222, 'learning_rate': 1.047038327526132e-07, 'epoch': 632.45}

 99%|█████████▉| 57300/57600 [10:05:00<02:59,  1.68it/s]
 99%|█████████▉| 57301/57600 [10:05:01<03:05,  1.61it/s]
 99%|█████████▉| 57302/57600 [10:05:01<03:08,  1.58it/s]
 99%|█████████▉| 57303/57600 [10:05:02<03:08,  1.58it/s]
 99%|█████████▉| 57304/57600 [10:05:03<03:11,  1.54it/s]
 99%|█████████▉| 57305/57600 [10:05:03<03:04,  1.60it/s]
 99%|█████████▉| 57306/57600 [10:05:04<02:59,  1.63it/s]
 99%|█████████▉| 57307/57600 [10:05:05<02:56,  1.66it/s]
 99%|█████████▉| 57308/57600 [10:05:05<02:57,  1.64it/s]
 99%|█████████▉| 57309/57600 [10:05:06<03:01,  1.61it/s]
 99%|█████████▉| 57310/57600 [10:05:06<02:57,  1.63it/s]
 99%|█████████▉| 57311/57600 [10:05:07<02:53,  1.66it/s]
100%|█████████▉| 57312/57600 [10:05:08<02:54,  1.65it/s]
100%|█████████▉| 57313/57600 [10:05:08<02:56,  1.62it/s]
100%|█████████▉| 57314/57600 [10:05:09<02:54,  1.64it/s]
100%|█████████▉| 57315/57600 [10:05:09<02:52,  1.65it/s]
100%|█████████▉| 57316/57600 [10:05:10<02:57,  1.60it/s]
100%|█████████▉| 57317/57600 [10:05:11<03:02,  1.55it/s]
100%|█████████▉| 57318/57600 [10:05:11<02:56,  1.60it/s]
100%|█████████▉| 57319/57600 [10:05:12<02:57,  1.59it/s]
100%|█████████▉| 57320/57600 [10:05:13<02:51,  1.63it/s]
                                                        
{'loss': 1.1118, 'learning_rate': 1.0439024390243902e-07, 'epoch': 632.67}

100%|█████████▉| 57320/57600 [10:05:13<02:51,  1.63it/s]
100%|█████████▉| 57321/57600 [10:05:13<02:55,  1.59it/s]
100%|█████████▉| 57322/57600 [10:05:14<02:51,  1.62it/s]
100%|█████████▉| 57323/57600 [10:05:14<02:46,  1.67it/s]
100%|█████████▉| 57324/57600 [10:05:15<02:46,  1.66it/s]
100%|█████████▉| 57325/57600 [10:05:16<02:50,  1.62it/s]
100%|█████████▉| 57326/57600 [10:05:16<02:49,  1.61it/s]
100%|█████████▉| 57327/57600 [10:05:17<02:50,  1.60it/s]
100%|█████████▉| 57328/57600 [10:05:18<02:48,  1.62it/s]
100%|█████████▉| 57329/57600 [10:05:18<02:46,  1.63it/s]
100%|█████████▉| 57330/57600 [10:05:19<02:46,  1.62it/s]
100%|█████████▉| 57331/57600 [10:05:19<02:44,  1.64it/s]
100%|█████████▉| 57332/57600 [10:05:20<02:49,  1.58it/s]
100%|█████████▉| 57333/57600 [10:05:21<02:49,  1.57it/s]
100%|█████████▉| 57334/57600 [10:05:21<02:45,  1.60it/s]
100%|█████████▉| 57335/57600 [10:05:22<02:51,  1.55it/s]
100%|█████████▉| 57336/57600 [10:05:23<02:48,  1.56it/s]
100%|█████████▉| 57337/57600 [10:05:23<02:49,  1.56it/s]
100%|█████████▉| 57338/57600 [10:05:24<02:43,  1.60it/s]
100%|█████████▉| 57339/57600 [10:05:24<02:41,  1.62it/s]
100%|█████████▉| 57340/57600 [10:05:25<02:42,  1.60it/s]
                                                        
{'loss': 1.1005, 'learning_rate': 1.0407665505226485e-07, 'epoch': 632.89}

100%|█████████▉| 57340/57600 [10:05:25<02:42,  1.60it/s]
100%|█████████▉| 57341/57600 [10:05:26<02:43,  1.58it/s]
100%|█████████▉| 57342/57600 [10:05:26<02:40,  1.61it/s]
100%|█████████▉| 57343/57600 [10:05:27<02:37,  1.63it/s]
100%|█████████▉| 57344/57600 [10:05:27<02:31,  1.69it/s]
100%|█████████▉| 57345/57600 [10:05:28<02:32,  1.68it/s]
100%|█████████▉| 57346/57600 [10:05:29<02:36,  1.63it/s]
100%|█████████▉| 57347/57600 [10:05:29<02:31,  1.67it/s]
100%|█████████▉| 57348/57600 [10:05:30<02:36,  1.61it/s]
100%|█████████▉| 57349/57600 [10:05:31<02:38,  1.58it/s]
100%|█████████▉| 57350/57600 [10:05:31<02:45,  1.51it/s]
100%|█████████▉| 57351/57600 [10:05:32<02:51,  1.45it/s]
100%|█████████▉| 57352/57600 [10:05:33<02:50,  1.46it/s]
100%|█████████▉| 57353/57600 [10:05:33<02:46,  1.49it/s]
100%|█████████▉| 57354/57600 [10:05:34<02:43,  1.50it/s]
100%|█████████▉| 57355/57600 [10:05:35<02:37,  1.55it/s]
100%|█████████▉| 57356/57600 [10:05:35<02:36,  1.56it/s]
100%|█████████▉| 57357/57600 [10:05:36<02:34,  1.57it/s]
100%|█████████▉| 57358/57600 [10:05:37<02:33,  1.58it/s]
100%|█████████▉| 57359/57600 [10:05:37<02:36,  1.54it/s]
100%|█████████▉| 57360/57600 [10:05:38<02:32,  1.58it/s]
                                                        
{'loss': 1.0524, 'learning_rate': 1.0376306620209058e-07, 'epoch': 633.11}

100%|█████████▉| 57360/57600 [10:05:38<02:32,  1.58it/s]
100%|█████████▉| 57361/57600 [10:05:38<02:30,  1.58it/s]
100%|█████████▉| 57362/57600 [10:05:39<02:26,  1.63it/s]
100%|█████████▉| 57363/57600 [10:05:40<02:22,  1.66it/s]
100%|█████████▉| 57364/57600 [10:05:40<02:22,  1.65it/s]
100%|█████████▉| 57365/57600 [10:05:41<02:22,  1.65it/s]
100%|█████████▉| 57366/57600 [10:05:41<02:20,  1.66it/s]
100%|█████████▉| 57367/57600 [10:05:42<02:20,  1.66it/s]
100%|█████████▉| 57368/57600 [10:05:43<02:19,  1.67it/s]
100%|█████████▉| 57369/57600 [10:05:43<02:19,  1.65it/s]
100%|█████████▉| 57370/57600 [10:05:44<02:22,  1.62it/s]
100%|█████████▉| 57371/57600 [10:05:45<02:23,  1.59it/s]
100%|█████████▉| 57372/57600 [10:05:45<02:18,  1.65it/s]
100%|█████████▉| 57373/57600 [10:05:46<02:22,  1.59it/s]
100%|█████████▉| 57374/57600 [10:05:46<02:18,  1.63it/s]
100%|█████████▉| 57375/57600 [10:05:47<02:20,  1.61it/s]
100%|█████████▉| 57376/57600 [10:05:48<02:20,  1.59it/s]
100%|█████████▉| 57377/57600 [10:05:48<02:24,  1.55it/s]
100%|█████████▉| 57378/57600 [10:05:49<02:22,  1.55it/s]
100%|█████████▉| 57379/57600 [10:05:50<02:21,  1.56it/s]
100%|█████████▉| 57380/57600 [10:05:50<02:21,  1.55it/s]
                                                        
{'loss': 1.1023, 'learning_rate': 1.0344947735191641e-07, 'epoch': 633.33}

100%|█████████▉| 57380/57600 [10:05:50<02:21,  1.55it/s]
100%|█████████▉| 57381/57600 [10:05:51<02:20,  1.56it/s]
100%|█████████▉| 57382/57600 [10:05:52<02:18,  1.58it/s]
100%|█████████▉| 57383/57600 [10:05:52<02:16,  1.59it/s]
100%|█████████▉| 57384/57600 [10:05:53<02:15,  1.59it/s]
100%|█████████▉| 57385/57600 [10:05:53<02:17,  1.56it/s]
100%|█████████▉| 57386/57600 [10:05:54<02:14,  1.59it/s]
100%|█████████▉| 57387/57600 [10:05:55<02:13,  1.59it/s]
100%|█████████▉| 57388/57600 [10:05:55<02:11,  1.61it/s]
100%|█████████▉| 57389/57600 [10:05:56<02:12,  1.59it/s]
100%|█████████▉| 57390/57600 [10:05:57<02:13,  1.57it/s]
100%|█████████▉| 57391/57600 [10:05:57<02:17,  1.52it/s]
100%|█████████▉| 57392/57600 [10:05:58<02:12,  1.57it/s]
100%|█████████▉| 57393/57600 [10:05:58<02:11,  1.58it/s]
100%|█████████▉| 57394/57600 [10:05:59<02:10,  1.57it/s]
100%|█████████▉| 57395/57600 [10:06:00<02:11,  1.56it/s]
100%|█████████▉| 57396/57600 [10:06:00<02:07,  1.60it/s]
100%|█████████▉| 57397/57600 [10:06:01<02:08,  1.58it/s]
100%|█████████▉| 57398/57600 [10:06:02<02:07,  1.58it/s]
100%|█████████▉| 57399/57600 [10:06:02<02:06,  1.59it/s]
100%|█████████▉| 57400/57600 [10:06:03<02:07,  1.57it/s]
                                                        
{'loss': 1.0984, 'learning_rate': 1.0313588850174213e-07, 'epoch': 633.55}

100%|█████████▉| 57400/57600 [10:06:03<02:07,  1.57it/s]
100%|█████████▉| 57401/57600 [10:06:04<02:06,  1.57it/s]
100%|█████████▉| 57402/57600 [10:06:04<02:03,  1.61it/s]
100%|█████████▉| 57403/57600 [10:06:05<02:02,  1.60it/s]
100%|█████████▉| 57404/57600 [10:06:05<02:03,  1.59it/s]
100%|█████████▉| 57405/57600 [10:06:06<02:01,  1.60it/s]
100%|█████████▉| 57406/57600 [10:06:07<02:05,  1.54it/s]
100%|█████████▉| 57407/57600 [10:06:07<02:03,  1.56it/s]
100%|█████████▉| 57408/57600 [10:06:08<02:00,  1.60it/s]
100%|█████████▉| 57409/57600 [10:06:09<01:58,  1.61it/s]
100%|█████████▉| 57410/57600 [10:06:09<01:55,  1.64it/s]
100%|█████████▉| 57411/57600 [10:06:10<01:56,  1.63it/s]
100%|█████████▉| 57412/57600 [10:06:10<01:52,  1.67it/s]
100%|█████████▉| 57413/57600 [10:06:11<01:52,  1.66it/s]
100%|█████████▉| 57414/57600 [10:06:12<01:51,  1.68it/s]
100%|█████████▉| 57415/57600 [10:06:12<01:53,  1.63it/s]
100%|█████████▉| 57416/57600 [10:06:13<01:58,  1.55it/s]
100%|█████████▉| 57417/57600 [10:06:14<01:57,  1.55it/s]
100%|█████████▉| 57418/57600 [10:06:14<01:53,  1.60it/s]
100%|█████████▉| 57419/57600 [10:06:15<01:50,  1.64it/s]
100%|█████████▉| 57420/57600 [10:06:15<01:48,  1.66it/s]
                                                        
{'loss': 1.1291, 'learning_rate': 1.0282229965156795e-07, 'epoch': 633.77}

100%|█████████▉| 57420/57600 [10:06:15<01:48,  1.66it/s]
100%|█████████▉| 57421/57600 [10:06:16<01:49,  1.64it/s]
100%|█████████▉| 57422/57600 [10:06:17<01:50,  1.60it/s]
100%|█████████▉| 57423/57600 [10:06:17<01:49,  1.62it/s]
100%|█████████▉| 57424/57600 [10:06:18<01:47,  1.64it/s]
100%|█████████▉| 57425/57600 [10:06:18<01:46,  1.64it/s]
100%|█████████▉| 57426/57600 [10:06:19<01:46,  1.64it/s]
100%|█████████▉| 57427/57600 [10:06:20<01:47,  1.61it/s]
100%|█████████▉| 57428/57600 [10:06:20<01:45,  1.63it/s]
100%|█████████▉| 57429/57600 [10:06:21<01:43,  1.66it/s]
100%|█████████▉| 57430/57600 [10:06:21<01:45,  1.62it/s]
100%|█████████▉| 57431/57600 [10:06:22<01:44,  1.62it/s]
100%|█████████▉| 57432/57600 [10:06:23<01:45,  1.59it/s]
100%|█████████▉| 57433/57600 [10:06:23<01:45,  1.58it/s]
100%|█████████▉| 57434/57600 [10:06:24<01:43,  1.60it/s]
100%|█████████▉| 57435/57600 [10:06:25<01:43,  1.59it/s]
100%|█████████▉| 57436/57600 [10:06:25<01:43,  1.59it/s]
100%|█████████▉| 57437/57600 [10:06:26<01:43,  1.58it/s]
100%|█████████▉| 57438/57600 [10:06:27<01:43,  1.56it/s]
100%|█████████▉| 57439/57600 [10:06:27<01:41,  1.58it/s]
100%|█████████▉| 57440/57600 [10:06:28<01:41,  1.58it/s]
                                                        
{'loss': 1.0789, 'learning_rate': 1.0250871080139369e-07, 'epoch': 634.0}

100%|█████████▉| 57440/57600 [10:06:28<01:41,  1.58it/s]
100%|█████████▉| 57441/57600 [10:06:28<01:43,  1.54it/s]
100%|█████████▉| 57442/57600 [10:06:29<01:41,  1.56it/s]
100%|█████████▉| 57443/57600 [10:06:30<01:39,  1.57it/s]
100%|█████████▉| 57444/57600 [10:06:30<01:38,  1.58it/s]
100%|█████████▉| 57445/57600 [10:06:31<01:40,  1.54it/s]
100%|█████████▉| 57446/57600 [10:06:32<01:40,  1.54it/s]
100%|█████████▉| 57447/57600 [10:06:32<01:40,  1.52it/s]
100%|█████████▉| 57448/57600 [10:06:33<01:35,  1.58it/s]
100%|█████████▉| 57449/57600 [10:06:34<01:34,  1.59it/s]
100%|█████████▉| 57450/57600 [10:06:34<01:31,  1.63it/s]
100%|█████████▉| 57451/57600 [10:06:35<01:35,  1.55it/s]
100%|█████████▉| 57452/57600 [10:06:36<01:38,  1.50it/s]
100%|█████████▉| 57453/57600 [10:06:36<01:37,  1.50it/s]
100%|█████████▉| 57454/57600 [10:06:37<01:34,  1.55it/s]
100%|█████████▉| 57455/57600 [10:06:37<01:33,  1.55it/s]
100%|█████████▉| 57456/57600 [10:06:38<01:30,  1.59it/s]
100%|█████████▉| 57457/57600 [10:06:39<01:30,  1.59it/s]
100%|█████████▉| 57458/57600 [10:06:39<01:31,  1.55it/s]
100%|█████████▉| 57459/57600 [10:06:40<01:29,  1.58it/s]
100%|█████████▉| 57460/57600 [10:06:41<01:27,  1.61it/s]
                                                        
{'loss': 1.0854, 'learning_rate': 1.0219512195121951e-07, 'epoch': 634.22}

100%|█████████▉| 57460/57600 [10:06:41<01:27,  1.61it/s]
100%|█████████▉| 57461/57600 [10:06:41<01:25,  1.63it/s]
100%|█████████▉| 57462/57600 [10:06:42<01:23,  1.64it/s]
100%|█████████▉| 57463/57600 [10:06:42<01:24,  1.62it/s]
100%|█████████▉| 57464/57600 [10:06:43<01:23,  1.62it/s]
100%|█████████▉| 57465/57600 [10:06:44<01:22,  1.64it/s]
100%|█████████▉| 57466/57600 [10:06:44<01:22,  1.63it/s]
100%|█████████▉| 57467/57600 [10:06:45<01:22,  1.61it/s]
100%|█████████▉| 57468/57600 [10:06:46<01:22,  1.59it/s]
100%|█████████▉| 57469/57600 [10:06:46<01:21,  1.61it/s]
100%|█████████▉| 57470/57600 [10:06:47<01:21,  1.60it/s]
100%|█████████▉| 57471/57600 [10:06:47<01:20,  1.60it/s]
100%|█████████▉| 57472/57600 [10:06:48<01:19,  1.61it/s]
100%|█████████▉| 57473/57600 [10:06:49<01:19,  1.60it/s]
100%|█████████▉| 57474/57600 [10:06:49<01:18,  1.60it/s]
100%|█████████▉| 57475/57600 [10:06:50<01:18,  1.60it/s]
100%|█████████▉| 57476/57600 [10:06:50<01:17,  1.61it/s]
100%|█████████▉| 57477/57600 [10:06:51<01:17,  1.58it/s]
100%|█████████▉| 57478/57600 [10:06:52<01:16,  1.60it/s]
100%|█████████▉| 57479/57600 [10:06:52<01:14,  1.63it/s]
100%|█████████▉| 57480/57600 [10:06:53<01:14,  1.61it/s]
                                                        
{'loss': 1.059, 'learning_rate': 1.0188153310104534e-07, 'epoch': 634.44}

100%|█████████▉| 57480/57600 [10:06:53<01:14,  1.61it/s]
100%|█████████▉| 57481/57600 [10:06:54<01:12,  1.64it/s]
100%|█████████▉| 57482/57600 [10:06:54<01:13,  1.60it/s]
100%|█████████▉| 57483/57600 [10:06:55<01:12,  1.62it/s]
100%|█████████▉| 57484/57600 [10:06:55<01:11,  1.63it/s]
100%|█████████▉| 57485/57600 [10:06:56<01:11,  1.60it/s]
100%|█████████▉| 57486/57600 [10:06:57<01:10,  1.62it/s]
100%|█████████▉| 57487/57600 [10:06:57<01:08,  1.65it/s]
100%|█████████▉| 57488/57600 [10:06:58<01:07,  1.66it/s]
100%|█████████▉| 57489/57600 [10:06:58<01:08,  1.62it/s]
100%|█████████▉| 57490/57600 [10:06:59<01:08,  1.60it/s]
100%|█████████▉| 57491/57600 [10:07:00<01:06,  1.64it/s]
100%|█████████▉| 57492/57600 [10:07:00<01:06,  1.62it/s]
100%|█████████▉| 57493/57600 [10:07:01<01:05,  1.62it/s]
100%|█████████▉| 57494/57600 [10:07:02<01:05,  1.62it/s]
100%|█████████▉| 57495/57600 [10:07:02<01:06,  1.58it/s]
100%|█████████▉| 57496/57600 [10:07:03<01:06,  1.57it/s]
100%|█████████▉| 57497/57600 [10:07:04<01:05,  1.58it/s]
100%|█████████▉| 57498/57600 [10:07:04<01:04,  1.59it/s]
100%|█████████▉| 57499/57600 [10:07:05<01:03,  1.60it/s]
100%|█████████▉| 57500/57600 [10:07:05<01:03,  1.58it/s]
                                                        
{'loss': 1.116, 'learning_rate': 1.0156794425087106e-07, 'epoch': 634.66}

100%|█████████▉| 57500/57600 [10:07:05<01:03,  1.58it/s]
100%|█████████▉| 57501/57600 [10:07:06<01:01,  1.61it/s]
100%|█████████▉| 57502/57600 [10:07:07<00:59,  1.64it/s]
100%|█████████▉| 57503/57600 [10:07:07<00:59,  1.62it/s]
100%|█████████▉| 57504/57600 [10:07:08<00:58,  1.65it/s]
100%|█████████▉| 57505/57600 [10:07:08<00:56,  1.68it/s]
100%|█████████▉| 57506/57600 [10:07:09<00:58,  1.60it/s]
100%|█████████▉| 57507/57600 [10:07:10<00:57,  1.62it/s]
100%|█████████▉| 57508/57600 [10:07:10<00:57,  1.59it/s]
100%|█████████▉| 57509/57600 [10:07:11<00:57,  1.59it/s]
100%|█████████▉| 57510/57600 [10:07:12<00:56,  1.60it/s]
100%|█████████▉| 57511/57600 [10:07:12<00:55,  1.60it/s]
100%|█████████▉| 57512/57600 [10:07:13<00:54,  1.61it/s]
100%|█████████▉| 57513/57600 [10:07:14<00:57,  1.52it/s]
100%|█████████▉| 57514/57600 [10:07:14<00:56,  1.51it/s]
100%|█████████▉| 57515/57600 [10:07:15<00:54,  1.57it/s]
100%|█████████▉| 57516/57600 [10:07:15<00:51,  1.62it/s]
100%|█████████▉| 57517/57600 [10:07:16<00:50,  1.64it/s]
100%|█████████▉| 57518/57600 [10:07:17<00:51,  1.58it/s]
100%|█████████▉| 57519/57600 [10:07:17<00:52,  1.53it/s]
100%|█████████▉| 57520/57600 [10:07:18<00:52,  1.53it/s]
                                                        
{'loss': 1.0855, 'learning_rate': 1.012543554006969e-07, 'epoch': 634.88}

100%|█████████▉| 57520/57600 [10:07:18<00:52,  1.53it/s]
100%|█████████▉| 57521/57600 [10:07:19<00:50,  1.56it/s]
100%|█████████▉| 57522/57600 [10:07:19<00:50,  1.55it/s]
100%|█████████▉| 57523/57600 [10:07:20<00:48,  1.58it/s]
100%|█████████▉| 57524/57600 [10:07:21<00:48,  1.58it/s]
100%|█████████▉| 57525/57600 [10:07:21<00:46,  1.60it/s]
100%|█████████▉| 57526/57600 [10:07:22<00:46,  1.58it/s]
100%|█████████▉| 57527/57600 [10:07:22<00:45,  1.62it/s]
100%|█████████▉| 57528/57600 [10:07:23<00:45,  1.58it/s]
100%|█████████▉| 57529/57600 [10:07:24<00:44,  1.58it/s]
100%|█████████▉| 57530/57600 [10:07:24<00:44,  1.59it/s]
100%|█████████▉| 57531/57600 [10:07:25<00:43,  1.59it/s]
100%|█████████▉| 57532/57600 [10:07:26<00:44,  1.54it/s]
100%|█████████▉| 57533/57600 [10:07:26<00:42,  1.57it/s]
100%|█████████▉| 57534/57600 [10:07:27<00:41,  1.60it/s]
100%|█████████▉| 57535/57600 [10:07:27<00:40,  1.62it/s]
100%|█████████▉| 57536/57600 [10:07:28<00:40,  1.57it/s]
100%|█████████▉| 57537/57600 [10:07:29<00:39,  1.58it/s]
100%|█████████▉| 57538/57600 [10:07:29<00:39,  1.56it/s]
100%|█████████▉| 57539/57600 [10:07:30<00:37,  1.62it/s]
100%|█████████▉| 57540/57600 [10:07:31<00:36,  1.64it/s]
                                                        
{'loss': 1.1052, 'learning_rate': 1.0094076655052262e-07, 'epoch': 635.1}

100%|█████████▉| 57540/57600 [10:07:31<00:36,  1.64it/s]
100%|█████████▉| 57541/57600 [10:07:31<00:36,  1.62it/s]
100%|█████████▉| 57542/57600 [10:07:32<00:36,  1.61it/s]
100%|█████████▉| 57543/57600 [10:07:32<00:34,  1.63it/s]
100%|█████████▉| 57544/57600 [10:07:33<00:35,  1.57it/s]
100%|█████████▉| 57545/57600 [10:07:34<00:34,  1.59it/s]
100%|█████████▉| 57546/57600 [10:07:34<00:32,  1.64it/s]
100%|█████████▉| 57547/57600 [10:07:35<00:32,  1.64it/s]
100%|█████████▉| 57548/57600 [10:07:35<00:31,  1.63it/s]
100%|█████████▉| 57549/57600 [10:07:36<00:32,  1.57it/s]
100%|█████████▉| 57550/57600 [10:07:37<00:31,  1.59it/s]
100%|█████████▉| 57551/57600 [10:07:37<00:31,  1.57it/s]
100%|█████████▉| 57552/57600 [10:07:38<00:29,  1.64it/s]
100%|█████████▉| 57553/57600 [10:07:39<00:30,  1.55it/s]
100%|█████████▉| 57554/57600 [10:07:39<00:28,  1.59it/s]
100%|█████████▉| 57555/57600 [10:07:40<00:29,  1.55it/s]
100%|█████████▉| 57556/57600 [10:07:41<00:27,  1.58it/s]
100%|█████████▉| 57557/57600 [10:07:41<00:26,  1.60it/s]
100%|█████████▉| 57558/57600 [10:07:42<00:26,  1.59it/s]
100%|█████████▉| 57559/57600 [10:07:43<00:26,  1.55it/s]
100%|█████████▉| 57560/57600 [10:07:43<00:25,  1.55it/s]
                                                        
{'loss': 1.1072, 'learning_rate': 1.0062717770034844e-07, 'epoch': 635.32}

100%|█████████▉| 57560/57600 [10:07:43<00:25,  1.55it/s]
100%|█████████▉| 57561/57600 [10:07:44<00:24,  1.59it/s]
100%|█████████▉| 57562/57600 [10:07:44<00:24,  1.55it/s]
100%|█████████▉| 57563/57600 [10:07:45<00:23,  1.54it/s]
100%|█████████▉| 57564/57600 [10:07:46<00:24,  1.48it/s]
100%|█████████▉| 57565/57600 [10:07:46<00:23,  1.50it/s]
100%|█████████▉| 57566/57600 [10:07:47<00:22,  1.50it/s]
100%|█████████▉| 57567/57600 [10:07:48<00:21,  1.54it/s]
100%|█████████▉| 57568/57600 [10:07:48<00:20,  1.55it/s]
100%|█████████▉| 57569/57600 [10:07:49<00:19,  1.58it/s]
100%|█████████▉| 57570/57600 [10:07:50<00:19,  1.56it/s]
100%|█████████▉| 57571/57600 [10:07:50<00:18,  1.59it/s]
100%|█████████▉| 57572/57600 [10:07:51<00:17,  1.64it/s]
100%|█████████▉| 57573/57600 [10:07:51<00:16,  1.66it/s]
100%|█████████▉| 57574/57600 [10:07:52<00:16,  1.60it/s]
100%|█████████▉| 57575/57600 [10:07:53<00:15,  1.62it/s]
100%|█████████▉| 57576/57600 [10:07:53<00:14,  1.63it/s]
100%|█████████▉| 57577/57600 [10:07:54<00:13,  1.70it/s]
100%|█████████▉| 57578/57600 [10:07:54<00:12,  1.70it/s]
100%|█████████▉| 57579/57600 [10:07:55<00:12,  1.72it/s]
100%|█████████▉| 57580/57600 [10:07:56<00:11,  1.73it/s]
                                                        
{'loss': 1.0774, 'learning_rate': 1.0031358885017416e-07, 'epoch': 635.54}

100%|█████████▉| 57580/57600 [10:07:56<00:11,  1.73it/s]
100%|█████████▉| 57581/57600 [10:07:56<00:11,  1.69it/s]
100%|█████████▉| 57582/57600 [10:07:57<00:11,  1.59it/s]
100%|█████████▉| 57583/57600 [10:07:57<00:10,  1.64it/s]
100%|█████████▉| 57584/57600 [10:07:58<00:09,  1.68it/s]
100%|█████████▉| 57585/57600 [10:07:59<00:09,  1.63it/s]
100%|█████████▉| 57586/57600 [10:07:59<00:08,  1.64it/s]
100%|█████████▉| 57587/57600 [10:08:00<00:08,  1.62it/s]
100%|█████████▉| 57588/57600 [10:08:00<00:07,  1.67it/s]
100%|█████████▉| 57589/57600 [10:08:01<00:06,  1.67it/s]
100%|█████████▉| 57590/57600 [10:08:02<00:06,  1.64it/s]
100%|█████████▉| 57591/57600 [10:08:02<00:05,  1.63it/s]
100%|█████████▉| 57592/57600 [10:08:03<00:04,  1.65it/s]
100%|█████████▉| 57593/57600 [10:08:03<00:04,  1.67it/s]
100%|█████████▉| 57594/57600 [10:08:04<00:03,  1.67it/s]
100%|█████████▉| 57595/57600 [10:08:05<00:02,  1.70it/s]
100%|█████████▉| 57596/57600 [10:08:05<00:02,  1.68it/s]
100%|█████████▉| 57597/57600 [10:08:06<00:01,  1.64it/s]
100%|█████████▉| 57598/57600 [10:08:07<00:01,  1.57it/s]
100%|█████████▉| 57599/57600 [10:08:07<00:00,  1.56it/s]
100%|██████████| 57600/57600 [10:08:08<00:00,  1.59it/s]
                                                        
{'loss': 1.1211, 'learning_rate': 1e-07, 'epoch': 635.76}

100%|██████████| 57600/57600 [10:08:08<00:00,  1.59it/s]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/6 [00:00<?, ?it/s]

 33%|███▎      | 2/6 [00:00<00:00, 11.23it/s]

 67%|██████▋   | 4/6 [00:00<00:00,  7.31it/s]

 83%|████████▎ | 5/6 [00:00<00:00,  4.52it/s]

100%|██████████| 6/6 [00:01<00:00,  3.11it/s]{'score': 50.42307999143571, 'counts': [145, 91, 66, 48], 'totals': [206, 176, 147, 119], 'precisions': [70.3883495145631, 51.70454545454545, 44.89795918367347, 40.33613445378151], 'bp': 0.9951573944744894, 'sys_len': 206, 'ref_len': 207}

                                                        

                                             
{'eval_loss': 1.9816315174102783, 'eval_bleu': 50.4231, 'eval_gen_len': 8.2667, 'eval_runtime': 3.323, 'eval_samples_per_second': 9.028, 'eval_steps_per_second': 1.806, 'epoch': 635.76}

100%|██████████| 57600/57600 [10:08:11<00:00,  1.59it/s]

100%|██████████| 6/6 [00:03<00:00,  3.11it/s]

                                             [WARNING|configuration_utils.py:448] 2024-10-02 17:02:24,528 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
[WARNING|trainer.py:2764] 2024-10-02 17:03:31,472 >> There were missing keys in the checkpoint model loaded: ['model.encoder.embed_tokens.weight', 'model.decoder.embed_tokens.weight', 'lm_head.weight'].

                                                        
{'train_runtime': 36575.1723, 'train_samples_per_second': 39.616, 'train_steps_per_second': 1.575, 'train_loss': 1.2508395995613601, 'epoch': 635.76}

100%|██████████| 57600/57600 [10:09:18<00:00,  1.59it/s]
100%|██████████| 57600/57600 [10:09:18<00:00,  1.58it/s]
[WARNING|configuration_utils.py:448] 2024-10-02 17:04:57,059 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
[WARNING|configuration_utils.py:448] 2024-10-02 17:05:03,905 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}