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]