diff --git "a/run-2024-07-08T23:40:01+00:00.log" "b/run-2024-07-08T23:40:01+00:00.log"
--- "a/run-2024-07-08T23:40:01+00:00.log"
+++ "b/run-2024-07-08T23:40:01+00:00.log"
@@ -4707,4 +4707,1170 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, '
 
 63%|██████▎   | 232300/371472 [7:27:23<11:05:01,  3.49it/s]
 63%|██████▎   | 232301/371472 [7:27:23<10:57:57,  3.53it/s]
 63%|██████▎   | 232302/371472 [7:27:23<10:45:49,  3.59it/s]
 63%|██████▎   | 232303/371472 [7:27:24<10:18:59,  3.75it/s]
 63%|██████▎   | 232304/371472 [7:27:24<10:49:22,  3.57it/s]
 63%|██████▎   | 232305/371472 [7:27:24<11:00:26,  3.51it/s]
 63%|██████▎   | 232306/371472 [7:27:24<10:34:41,  3.65it/s]
 63%|██████▎   | 232307/371472 [7:27:25<11:00:25,  3.51it/s]
 63%|██████▎   | 232308/371472 [7:27:25<10:28:51,  3.69it/s]
 63%|██████▎   | 232309/371472 [7:27:25<10:19:22,  3.74it/s]
 63%|██████▎   | 232310/371472 [7:27:26<10:08:45,  3.81it/s]
 63%|██████▎   | 232311/371472 [7:27:26<10:44:57,  3.60it/s]
 63%|██████▎   | 232312/371472 [7:27:26<10:48:51,  3.57it/s]
 63%|██████▎   | 232313/371472 [7:27:26<10:51:35,  3.56it/s]
 63%|██████▎   | 232314/371472 [7:27:27<11:28:21,  3.37it/s]
 63%|██████▎   | 232315/371472 [7:27:27<11:09:42,  3.46it/s]
 63%|██████▎   | 232316/371472 [7:27:27<11:14:14,  3.44it/s]
 63%|██████▎   | 232317/371472 [7:27:28<14:23:15,  2.69it/s]
 63%|██████▎   | 232318/371472 [7:27:28<13:11:25,  2.93it/s]
 63%|██████▎   | 232319/371472 [7:27:28<12:26:55,  3.10it/s]
 63%|██████▎   | 232320/371472 [7:27:29<12:05:32,  3.20it/s]
                                                            
{'loss': 2.8523, 'learning_rate': 4.3731819259195417e-07, 'epoch': 10.01}
 
 63%|██████▎   | 232320/371472 [7:27:29<12:05:32,  3.20it/s]
 63%|██████▎   | 232321/371472 [7:27:29<11:26:28,  3.38it/s]
 63%|██████▎   | 232322/371472 [7:27:29<11:03:02,  3.50it/s]
 63%|██████▎   | 232323/371472 [7:27:30<11:04:34,  3.49it/s]
 63%|██████▎   | 232324/371472 [7:27:30<10:46:38,  3.59it/s]
 63%|██████▎   | 232325/371472 [7:27:30<11:43:55,  3.29it/s]
 63%|██████▎   | 232326/371472 [7:27:30<11:18:13,  3.42it/s]
 63%|██████▎   | 232327/371472 [7:27:31<11:09:41,  3.46it/s]
 63%|██████▎   | 232328/371472 [7:27:31<11:29:52,  3.36it/s]
 63%|██████▎   | 232329/371472 [7:27:31<11:18:21,  3.42it/s]
 63%|██████▎   | 232330/371472 [7:27:32<11:55:43,  3.24it/s]
 63%|██████▎   | 232331/371472 [7:27:32<11:19:44,  3.41it/s]
 63%|██████▎   | 232332/371472 [7:27:32<11:11:00,  3.46it/s]
 63%|██████▎   | 232333/371472 [7:27:33<11:39:01,  3.32it/s]
 63%|██████▎   | 232334/371472 [7:27:33<11:34:05,  3.34it/s]
 63%|██████▎   | 232335/371472 [7:27:33<11:06:36,  3.48it/s]
 63%|██████▎   | 232336/371472 [7:27:33<11:23:47,  3.39it/s]
 63%|██████▎   | 232337/371472 [7:27:34<11:43:12,  3.30it/s]
 63%|██████▎   | 232338/371472 [7:27:34<11:21:08,  3.40it/s]
 63%|██████▎   | 232339/371472 [7:27:34<11:20:44,  3.41it/s]
 63%|██████▎   | 232340/371472 [7:27:35<11:06:45,  3.48it/s]
                                                            
{'loss': 3.0394, 'learning_rate': 4.3726971061647524e-07, 'epoch': 10.01}
 
 63%|██████▎   | 232340/371472 [7:27:35<11:06:45,  3.48it/s]
 63%|██████▎   | 232341/371472 [7:27:35<11:27:58,  3.37it/s]
 63%|██████▎   | 232342/371472 [7:27:35<10:57:04,  3.53it/s]
 63%|██████▎   | 232343/371472 [7:27:35<10:33:12,  3.66it/s]
 63%|██████▎   | 232344/371472 [7:27:36<11:17:56,  3.42it/s]
 63%|██████▎   | 232345/371472 [7:27:36<10:43:48,  3.60it/s]
 63%|██████▎   | 232346/371472 [7:27:36<11:04:28,  3.49it/s]
 63%|██████▎   | 232347/371472 [7:27:37<10:51:36,  3.56it/s]
 63%|██████▎   | 232348/371472 [7:27:37<10:36:46,  3.64it/s]
 63%|██████▎   | 232349/371472 [7:27:37<10:54:23,  3.54it/s]
 63%|██████▎   | 232350/371472 [7:27:37<10:52:37,  3.55it/s]
 63%|██████▎   | 232351/371472 [7:27:38<10:35:59,  3.65it/s]
 63%|██████▎   | 232352/371472 [7:27:38<10:37:17,  3.64it/s]
 63%|██████▎   | 232353/371472 [7:27:38<10:24:17,  3.71it/s]
 63%|██████▎   | 232354/371472 [7:27:38<10:12:06,  3.79it/s]
 63%|██████▎   | 232355/371472 [7:27:39<10:07:09,  3.82it/s]
 63%|██████▎   | 232356/371472 [7:27:39<10:13:56,  3.78it/s]
 63%|██████▎   | 232357/371472 [7:27:39<11:17:23,  3.42it/s]
 63%|██████▎   | 232358/371472 [7:27:40<10:42:54,  3.61it/s]
 63%|██████▎   | 232359/371472 [7:27:40<10:58:36,  3.52it/s]
 63%|██████▎   | 232360/371472 [7:27:40<10:49:32,  3.57it/s]
                                                            
{'loss': 2.918, 'learning_rate': 4.3722122864099637e-07, 'epoch': 10.01}
-
 63%|██████▎   | 232360/371472 [7:27:40<10:49:32,  3.57it/s]
 63%|██████▎   | 232361/371472 [7:27:40<10:35:19,  3.65it/s]
 63%|██████▎   | 232362/371472 [7:27:41<10:27:35,  3.69it/s]
 63%|██████▎   | 232363/371472 [7:27:41<10:39:50,  3.62it/s]
 63%|██████▎   | 232364/371472 [7:27:41<10:43:17,  3.60it/s]
 63%|██████▎   | 232365/371472 [7:27:41<10:55:36,  3.54it/s]
 63%|██████▎   | 232366/371472 [7:27:42<10:38:38,  3.63it/s]
 63%|██████▎   | 232367/371472 [7:27:42<10:17:06,  3.76it/s]
\ No newline at end of file
+
 63%|██████▎   | 232360/371472 [7:27:40<10:49:32,  3.57it/s]
 63%|██████▎   | 232361/371472 [7:27:40<10:35:19,  3.65it/s]
 63%|██████▎   | 232362/371472 [7:27:41<10:27:35,  3.69it/s]
 63%|██████▎   | 232363/371472 [7:27:41<10:39:50,  3.62it/s]
 63%|██████▎   | 232364/371472 [7:27:41<10:43:17,  3.60it/s]
 63%|██████▎   | 232365/371472 [7:27:41<10:55:36,  3.54it/s]
 63%|██████▎   | 232366/371472 [7:27:42<10:38:38,  3.63it/s]
 63%|██████▎   | 232367/371472 [7:27:42<10:17:06,  3.76it/s]
 63%|██████▎   | 232368/371472 [7:27:42<12:05:19,  3.20it/s]
 63%|██████▎   | 232369/371472 [7:27:43<11:20:42,  3.41it/s]
 63%|██████▎   | 232370/371472 [7:27:43<11:35:05,  3.34it/s]
 63%|██████▎   | 232371/371472 [7:27:43<10:56:17,  3.53it/s]
 63%|██████▎   | 232372/371472 [7:27:44<11:04:19,  3.49it/s]
 63%|██████▎   | 232373/371472 [7:27:44<11:25:43,  3.38it/s]
 63%|██████▎   | 232374/371472 [7:27:44<11:06:41,  3.48it/s]
 63%|██████▎   | 232375/371472 [7:27:44<10:53:37,  3.55it/s]
 63%|██████▎   | 232376/371472 [7:27:45<11:07:18,  3.47it/s]
 63%|██████▎   | 232377/371472 [7:27:45<10:39:27,  3.63it/s]
 63%|██████▎   | 232378/371472 [7:27:45<10:21:18,  3.73it/s]
 63%|██████▎   | 232379/371472 [7:27:45<10:15:53,  3.76it/s]
 63%|██████▎   | 232380/371472 [7:27:46<10:13:48,  3.78it/s]
                                                            
{'loss': 2.8606, 'learning_rate': 4.3717274666551744e-07, 'epoch': 10.01}
+
 63%|██████▎   | 232380/371472 [7:27:46<10:13:48,  3.78it/s]
 63%|██████▎   | 232381/371472 [7:27:46<9:56:46,  3.88it/s] 
 63%|██████▎   | 232382/371472 [7:27:46<10:35:55,  3.65it/s]
 63%|██████▎   | 232383/371472 [7:27:47<10:23:25,  3.72it/s]
 63%|██████▎   | 232384/371472 [7:27:47<11:21:27,  3.40it/s]
 63%|██████▎   | 232385/371472 [7:27:47<11:36:10,  3.33it/s]
 63%|██████▎   | 232386/371472 [7:27:47<11:17:42,  3.42it/s]
 63%|██████▎   | 232387/371472 [7:27:48<10:56:08,  3.53it/s]
 63%|██████▎   | 232388/371472 [7:27:48<12:13:23,  3.16it/s]
 63%|██████▎   | 232389/371472 [7:27:48<11:42:54,  3.30it/s]
 63%|██████▎   | 232390/371472 [7:27:49<10:56:55,  3.53it/s]
 63%|██████▎   | 232391/371472 [7:27:49<10:57:58,  3.52it/s]
 63%|██████▎   | 232392/371472 [7:27:49<11:01:24,  3.50it/s]
 63%|██████▎   | 232393/371472 [7:27:49<10:29:22,  3.68it/s]
 63%|██████▎   | 232394/371472 [7:27:50<11:28:00,  3.37it/s]
 63%|██████▎   | 232395/371472 [7:27:50<11:33:07,  3.34it/s]
 63%|██████▎   | 232396/371472 [7:27:50<11:31:20,  3.35it/s]
 63%|██████▎   | 232397/371472 [7:27:51<11:23:41,  3.39it/s]
 63%|██████▎   | 232398/371472 [7:27:51<11:20:37,  3.41it/s]
 63%|██████▎   | 232399/371472 [7:27:51<11:18:02,  3.42it/s]
 63%|██████▎   | 232400/371472 [7:27:52<11:04:28,  3.49it/s]
                                                            
{'loss': 2.7255, 'learning_rate': 4.371242646900385e-07, 'epoch': 10.01}
+
 63%|██████▎   | 232400/371472 [7:27:52<11:04:28,  3.49it/s]
 63%|██████▎   | 232401/371472 [7:27:52<10:41:07,  3.62it/s]
 63%|██████▎   | 232402/371472 [7:27:52<10:44:06,  3.60it/s]
 63%|██████▎   | 232403/371472 [7:27:52<11:33:42,  3.34it/s]
 63%|██████▎   | 232404/371472 [7:27:53<11:22:14,  3.40it/s]
 63%|██████▎   | 232405/371472 [7:27:53<11:15:29,  3.43it/s]
 63%|██████▎   | 232406/371472 [7:27:53<10:51:22,  3.56it/s]
 63%|██████▎   | 232407/371472 [7:27:53<10:32:09,  3.67it/s]
 63%|██████▎   | 232408/371472 [7:27:54<10:39:20,  3.63it/s]
 63%|██████▎   | 232409/371472 [7:27:54<10:30:43,  3.67it/s]
 63%|██████▎   | 232410/371472 [7:27:54<10:56:49,  3.53it/s]
 63%|██████▎   | 232411/371472 [7:27:55<10:44:37,  3.60it/s]
 63%|██████▎   | 232412/371472 [7:27:55<11:14:31,  3.44it/s]
 63%|██████▎   | 232413/371472 [7:27:55<11:09:33,  3.46it/s]
 63%|██████▎   | 232414/371472 [7:27:55<10:55:45,  3.53it/s]
 63%|██████▎   | 232415/371472 [7:27:56<10:45:30,  3.59it/s]
 63%|██████▎   | 232416/371472 [7:27:56<10:27:05,  3.70it/s]
 63%|██████▎   | 232417/371472 [7:27:56<10:40:46,  3.62it/s]
 63%|██████▎   | 232418/371472 [7:27:57<10:31:25,  3.67it/s]
 63%|██████▎   | 232419/371472 [7:27:57<10:53:53,  3.54it/s]
 63%|██████▎   | 232420/371472 [7:27:57<10:44:37,  3.60it/s]
                                                            
{'loss': 2.9796, 'learning_rate': 4.3707578271455963e-07, 'epoch': 10.01}
+
 63%|██████▎   | 232420/371472 [7:27:57<10:44:37,  3.60it/s]
 63%|██████▎   | 232421/371472 [7:27:57<11:12:09,  3.45it/s]
 63%|██████▎   | 232422/371472 [7:27:58<11:04:25,  3.49it/s]
 63%|██████▎   | 232423/371472 [7:27:58<10:34:39,  3.65it/s]
 63%|██████▎   | 232424/371472 [7:27:58<10:17:18,  3.75it/s]
 63%|██████▎   | 232425/371472 [7:27:59<11:10:15,  3.46it/s]
 63%|██████▎   | 232426/371472 [7:27:59<11:03:27,  3.49it/s]
 63%|██████▎   | 232427/371472 [7:27:59<11:13:36,  3.44it/s]
 63%|██████▎   | 232428/371472 [7:27:59<11:01:53,  3.50it/s]
 63%|██████▎   | 232429/371472 [7:28:00<10:58:26,  3.52it/s]
 63%|██████▎   | 232430/371472 [7:28:00<11:34:53,  3.33it/s]
 63%|██████▎   | 232431/371472 [7:28:00<11:13:01,  3.44it/s]
 63%|██████▎   | 232432/371472 [7:28:01<10:46:38,  3.58it/s]
 63%|██████▎   | 232433/371472 [7:28:01<10:41:05,  3.61it/s]
 63%|██████▎   | 232434/371472 [7:28:01<10:37:45,  3.63it/s]
 63%|██████▎   | 232435/371472 [7:28:01<10:39:43,  3.62it/s]
 63%|██████▎   | 232436/371472 [7:28:02<10:37:52,  3.63it/s]
 63%|██████▎   | 232437/371472 [7:28:02<10:25:29,  3.70it/s]
 63%|██████▎   | 232438/371472 [7:28:02<10:36:33,  3.64it/s]
 63%|██████▎   | 232439/371472 [7:28:02<10:17:18,  3.75it/s]
 63%|██████▎   | 232440/371472 [7:28:03<10:02:50,  3.84it/s]
                                                            
{'loss': 2.8521, 'learning_rate': 4.370273007390807e-07, 'epoch': 10.01}
+
 63%|██████▎   | 232440/371472 [7:28:03<10:02:50,  3.84it/s]
 63%|██████▎   | 232441/371472 [7:28:03<10:55:38,  3.53it/s]
 63%|██████▎   | 232442/371472 [7:28:03<11:10:51,  3.45it/s]
 63%|██████▎   | 232443/371472 [7:28:04<11:43:32,  3.29it/s]
 63%|██████▎   | 232444/371472 [7:28:04<11:33:38,  3.34it/s]
 63%|██████▎   | 232445/371472 [7:28:04<12:10:49,  3.17it/s]
 63%|██████▎   | 232446/371472 [7:28:05<11:31:26,  3.35it/s]
 63%|██████▎   | 232447/371472 [7:28:05<11:16:24,  3.43it/s]
 63%|██████▎   | 232448/371472 [7:28:05<11:08:09,  3.47it/s]
 63%|██████▎   | 232449/371472 [7:28:05<12:04:09,  3.20it/s]
 63%|██████▎   | 232450/371472 [7:28:06<11:35:02,  3.33it/s]
 63%|██████▎   | 232451/371472 [7:28:06<11:24:21,  3.39it/s]
 63%|██████▎   | 232452/371472 [7:28:06<11:00:36,  3.51it/s]
 63%|██████▎   | 232453/371472 [7:28:07<10:56:14,  3.53it/s]
 63%|██████▎   | 232454/371472 [7:28:07<10:46:12,  3.59it/s]
 63%|██████▎   | 232455/371472 [7:28:07<10:29:30,  3.68it/s]
 63%|██████▎   | 232456/371472 [7:28:07<10:35:26,  3.65it/s]
 63%|██████▎   | 232457/371472 [7:28:08<10:51:26,  3.56it/s]
 63%|██████▎   | 232458/371472 [7:28:08<10:41:42,  3.61it/s]
 63%|██████▎   | 232459/371472 [7:28:08<10:37:37,  3.63it/s]
 63%|██████▎   | 232460/371472 [7:28:08<10:26:01,  3.70it/s]
                                                            
{'loss': 2.9039, 'learning_rate': 4.369788187636019e-07, 'epoch': 10.01}
+
 63%|██████▎   | 232460/371472 [7:28:08<10:26:01,  3.70it/s]
 63%|██████▎   | 232461/371472 [7:28:09<11:32:06,  3.35it/s]
 63%|██████▎   | 232462/371472 [7:28:09<11:30:36,  3.35it/s]
 63%|██████▎   | 232463/371472 [7:28:09<11:15:03,  3.43it/s]
 63%|██████▎   | 232464/371472 [7:28:10<10:50:08,  3.56it/s]
 63%|██████▎   | 232465/371472 [7:28:10<10:36:03,  3.64it/s]
 63%|██████▎   | 232466/371472 [7:28:10<11:11:53,  3.45it/s]
 63%|██████▎   | 232467/371472 [7:28:11<10:56:21,  3.53it/s]
 63%|██████▎   | 232468/371472 [7:28:11<11:02:01,  3.50it/s]
 63%|██████▎   | 232469/371472 [7:28:11<11:41:18,  3.30it/s]
 63%|██████▎   | 232470/371472 [7:28:11<11:16:59,  3.42it/s]
 63%|██████▎   | 232471/371472 [7:28:12<10:39:44,  3.62it/s]
 63%|██████▎   | 232472/371472 [7:28:12<11:20:34,  3.40it/s]
 63%|██████▎   | 232473/371472 [7:28:12<11:09:38,  3.46it/s]
 63%|██████▎   | 232474/371472 [7:28:13<11:07:47,  3.47it/s]
 63%|██████▎   | 232475/371472 [7:28:13<11:35:31,  3.33it/s]
 63%|██████▎   | 232476/371472 [7:28:13<11:35:23,  3.33it/s]
 63%|██████▎   | 232477/371472 [7:28:14<11:57:08,  3.23it/s]
 63%|██████▎   | 232478/371472 [7:28:14<11:41:35,  3.30it/s]
 63%|██████▎   | 232479/371472 [7:28:14<11:25:30,  3.38it/s]
 63%|██████▎   | 232480/371472 [7:28:14<11:22:27,  3.39it/s]
                                                            
{'loss': 2.863, 'learning_rate': 4.3693033678812295e-07, 'epoch': 10.01}
+
 63%|██████▎   | 232480/371472 [7:28:14<11:22:27,  3.39it/s]
 63%|██████▎   | 232481/371472 [7:28:15<11:14:21,  3.44it/s]
 63%|██████▎   | 232482/371472 [7:28:15<11:14:56,  3.43it/s]
 63%|██████▎   | 232483/371472 [7:28:15<11:03:39,  3.49it/s]
 63%|██████▎   | 232484/371472 [7:28:16<11:26:39,  3.37it/s]
 63%|██████▎   | 232485/371472 [7:28:16<11:15:54,  3.43it/s]
 63%|██████▎   | 232486/371472 [7:28:16<11:03:30,  3.49it/s]
 63%|██████▎   | 232487/371472 [7:28:16<10:43:15,  3.60it/s]
 63%|██████▎   | 232488/371472 [7:28:17<10:56:46,  3.53it/s]
 63%|██████▎   | 232489/371472 [7:28:17<11:41:19,  3.30it/s]
 63%|██████▎   | 232490/371472 [7:28:17<11:04:46,  3.48it/s]
 63%|██████▎   | 232491/371472 [7:28:18<10:42:39,  3.60it/s]
 63%|██████▎   | 232492/371472 [7:28:18<10:23:28,  3.72it/s]
 63%|██████▎   | 232493/371472 [7:28:18<10:54:30,  3.54it/s]
 63%|██████▎   | 232494/371472 [7:28:18<10:31:18,  3.67it/s]
 63%|██████▎   | 232495/371472 [7:28:19<10:16:08,  3.76it/s]
 63%|██████▎   | 232496/371472 [7:28:19<10:23:54,  3.71it/s]
 63%|██████▎   | 232497/371472 [7:28:19<11:02:14,  3.50it/s]
 63%|██████▎   | 232498/371472 [7:28:19<10:49:06,  3.57it/s]
 63%|██████▎   | 232499/371472 [7:28:20<10:56:55,  3.53it/s]
 63%|██████▎   | 232500/371472 [7:28:20<11:29:07,  3.36it/s]
                                                            
{'loss': 2.8583, 'learning_rate': 4.368818548126441e-07, 'epoch': 10.01}
+
 63%|██████▎   | 232500/371472 [7:28:20<11:29:07,  3.36it/s]
 63%|██████▎   | 232501/371472 [7:28:20<11:27:52,  3.37it/s]
 63%|██████▎   | 232502/371472 [7:28:21<12:04:18,  3.20it/s]
 63%|██████▎   | 232503/371472 [7:28:21<11:46:08,  3.28it/s]
 63%|██████▎   | 232504/371472 [7:28:21<11:44:59,  3.29it/s]
 63%|██████▎   | 232505/371472 [7:28:22<11:41:23,  3.30it/s]
 63%|██████▎   | 232506/371472 [7:28:22<15:26:55,  2.50it/s]
 63%|██████▎   | 232507/371472 [7:28:23<15:14:24,  2.53it/s]
 63%|██████▎   | 232508/371472 [7:28:23<14:04:31,  2.74it/s]
 63%|██████▎   | 232509/371472 [7:28:23<13:24:49,  2.88it/s]
 63%|██████▎   | 232510/371472 [7:28:23<12:28:07,  3.10it/s]
 63%|██████▎   | 232511/371472 [7:28:24<12:11:35,  3.17it/s]
 63%|██████▎   | 232512/371472 [7:28:24<11:28:23,  3.36it/s]
 63%|██████▎   | 232513/371472 [7:28:24<10:57:10,  3.52it/s]
 63%|██████▎   | 232514/371472 [7:28:25<10:45:49,  3.59it/s]
 63%|██████▎   | 232515/371472 [7:28:25<10:27:55,  3.69it/s]
 63%|██████▎   | 232516/371472 [7:28:25<10:09:44,  3.80it/s]
 63%|██████▎   | 232517/371472 [7:28:25<10:26:32,  3.70it/s]
 63%|██████▎   | 232518/371472 [7:28:26<10:37:03,  3.64it/s]
 63%|██████▎   | 232519/371472 [7:28:26<10:33:24,  3.66it/s]
 63%|██████▎   | 232520/371472 [7:28:26<10:40:08,  3.62it/s]
                                                            
{'loss': 2.9127, 'learning_rate': 4.3683337283716515e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232520/371472 [7:28:26<10:40:08,  3.62it/s]
 63%|██████▎   | 232521/371472 [7:28:26<10:42:34,  3.60it/s]
 63%|██████▎   | 232522/371472 [7:28:27<12:06:48,  3.19it/s]
 63%|██████▎   | 232523/371472 [7:28:27<12:31:44,  3.08it/s]
 63%|██████▎   | 232524/371472 [7:28:27<11:50:05,  3.26it/s]
 63%|██████▎   | 232525/371472 [7:28:28<11:52:11,  3.25it/s]
 63%|██████▎   | 232526/371472 [7:28:28<11:15:41,  3.43it/s]
 63%|██████▎   | 232527/371472 [7:28:28<10:46:32,  3.58it/s]
 63%|██████▎   | 232528/371472 [7:28:29<10:54:21,  3.54it/s]
 63%|██████▎   | 232529/371472 [7:28:29<10:52:30,  3.55it/s]
 63%|██████▎   | 232530/371472 [7:28:29<10:48:49,  3.57it/s]
 63%|██████▎   | 232531/371472 [7:28:29<11:09:32,  3.46it/s]
 63%|███��██▎   | 232532/371472 [7:28:30<13:11:54,  2.92it/s]
 63%|██████▎   | 232533/371472 [7:28:30<12:26:54,  3.10it/s]
 63%|██████▎   | 232534/371472 [7:28:30<11:53:21,  3.25it/s]
 63%|██████▎   | 232535/371472 [7:28:31<11:21:09,  3.40it/s]
 63%|██████▎   | 232536/371472 [7:28:31<10:49:56,  3.56it/s]
 63%|██████▎   | 232537/371472 [7:28:31<11:28:37,  3.36it/s]
 63%|██████▎   | 232538/371472 [7:28:32<11:26:49,  3.37it/s]
 63%|██████▎   | 232539/371472 [7:28:32<11:04:01,  3.49it/s]
 63%|██████▎   | 232540/371472 [7:28:32<10:22:46,  3.72it/s]
                                                            
{'loss': 2.9064, 'learning_rate': 4.3678489086168633e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232540/371472 [7:28:32<10:22:46,  3.72it/s]
 63%|██████▎   | 232541/371472 [7:28:32<10:31:56,  3.66it/s]
 63%|██████▎   | 232542/371472 [7:28:33<10:58:42,  3.52it/s]
 63%|██████▎   | 232543/371472 [7:28:33<11:00:28,  3.51it/s]
 63%|██████▎   | 232544/371472 [7:28:33<11:50:25,  3.26it/s]
 63%|██████▎   | 232545/371472 [7:28:34<12:17:36,  3.14it/s]
 63%|██████▎   | 232546/371472 [7:28:34<11:22:59,  3.39it/s]
 63%|██████▎   | 232547/371472 [7:28:34<11:16:40,  3.42it/s]
 63%|██████▎   | 232548/371472 [7:28:34<11:11:10,  3.45it/s]
 63%|██████▎   | 232549/371472 [7:28:35<11:40:21,  3.31it/s]
 63%|██████▎   | 232550/371472 [7:28:35<11:09:13,  3.46it/s]
 63%|██████▎   | 232551/371472 [7:28:35<11:30:56,  3.35it/s]
 63%|██████▎   | 232552/371472 [7:28:36<11:26:31,  3.37it/s]
 63%|██████▎   | 232553/371472 [7:28:36<10:55:33,  3.53it/s]
 63%|██████▎   | 232554/371472 [7:28:36<11:55:58,  3.23it/s]
 63%|██████▎   | 232555/371472 [7:28:37<11:40:17,  3.31it/s]
 63%|██████▎   | 232556/371472 [7:28:37<11:31:40,  3.35it/s]
 63%|██████▎   | 232557/371472 [7:28:37<11:22:38,  3.39it/s]
 63%|██████▎   | 232558/371472 [7:28:37<11:12:40,  3.44it/s]
 63%|██████▎   | 232559/371472 [7:28:38<10:57:18,  3.52it/s]
 63%|██████▎   | 232560/371472 [7:28:38<10:28:37,  3.68it/s]
                                                            
{'loss': 2.943, 'learning_rate': 4.3673640888620735e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232560/371472 [7:28:38<10:28:37,  3.68it/s]
 63%|██████▎   | 232561/371472 [7:28:38<10:41:53,  3.61it/s]
 63%|██████▎   | 232562/371472 [7:28:39<10:51:55,  3.55it/s]
 63%|██████▎   | 232563/371472 [7:28:39<10:34:03,  3.65it/s]
 63%|██████▎   | 232564/371472 [7:28:39<10:40:54,  3.61it/s]
 63%|██████▎   | 232565/371472 [7:28:39<10:57:17,  3.52it/s]
 63%|██████▎   | 232566/371472 [7:28:40<11:10:10,  3.45it/s]
 63%|██████▎   | 232567/371472 [7:28:40<10:49:03,  3.57it/s]
 63%|██████▎   | 232568/371472 [7:28:40<10:46:34,  3.58it/s]
 63%|██████▎   | 232569/371472 [7:28:40<10:27:40,  3.69it/s]
 63%|██████▎   | 232570/371472 [7:28:41<10:55:44,  3.53it/s]
 63%|██████▎   | 232571/371472 [7:28:41<10:35:31,  3.64it/s]
 63%|██████▎   | 232572/371472 [7:28:41<11:00:53,  3.50it/s]
 63%|██████▎   | 232573/371472 [7:28:42<11:26:58,  3.37it/s]
 63%|██████▎   | 232574/371472 [7:28:42<11:18:03,  3.41it/s]
 63%|██████▎   | 232575/371472 [7:28:42<11:27:10,  3.37it/s]
 63%|██████▎   | 232576/371472 [7:28:43<11:34:40,  3.33it/s]
 63%|██████▎   | 232577/371472 [7:28:43<11:54:49,  3.24it/s]
 63%|██████▎   | 232578/371472 [7:28:43<11:33:00,  3.34it/s]
 63%|██████▎   | 232579/371472 [7:28:43<11:07:40,  3.47it/s]
 63%|██████▎   | 232580/371472 [7:28:44<11:18:51,  3.41it/s]
                                                            
{'loss': 2.9952, 'learning_rate': 4.366879269107285e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232580/371472 [7:28:44<11:18:51,  3.41it/s]
 63%|██████▎   | 232581/371472 [7:28:44<11:00:14,  3.51it/s]
 63%|██████▎   | 232582/371472 [7:28:44<10:46:05,  3.58it/s]
 63%|██████▎   | 232583/371472 [7:28:45<10:33:15,  3.66it/s]
 63%|██████▎   | 232584/371472 [7:28:45<10:18:40,  3.74it/s]
 63%|██████▎   | 232585/371472 [7:28:45<11:10:13,  3.45it/s]
 63%|██████▎   | 232586/371472 [7:28:45<10:49:09,  3.57it/s]
 63%|██████▎   | 232587/371472 [7:28:46<10:36:18,  3.64it/s]
 63%|██████▎   | 232588/371472 [7:28:46<10:25:34,  3.70it/s]
 63%|██████▎   | 232589/371472 [7:28:46<10:51:44,  3.55it/s]
 63%|██████▎   | 232590/371472 [7:28:46<10:34:58,  3.65it/s]
 63%|██████▎   | 232591/371472 [7:28:47<10:55:20,  3.53it/s]
 63%|██████▎   | 232592/371472 [7:28:47<10:35:25,  3.64it/s]
 63%|██████▎   | 232593/371472 [7:28:47<10:40:04,  3.62it/s]
 63%|██████▎   | 232594/371472 [7:28:48<10:40:24,  3.61it/s]
 63%|██████▎   | 232595/371472 [7:28:48<10:37:19,  3.63it/s]
 63%|██████▎   | 232596/371472 [7:28:48<11:21:42,  3.40it/s]
 63%|██████▎   | 232597/371472 [7:28:48<11:10:16,  3.45it/s]
 63%|██████▎   | 232598/371472 [7:28:49<11:21:51,  3.39it/s]
 63%|██████▎   | 232599/371472 [7:28:49<11:20:58,  3.40it/s]
 63%|██████▎   | 232600/371472 [7:28:49<10:47:19,  3.58it/s]
                                                            
{'loss': 2.7346, 'learning_rate': 4.3663944493524954e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232600/371472 [7:28:49<10:47:19,  3.58it/s]
 63%|██████▎   | 232601/371472 [7:28:50<10:33:39,  3.65it/s]
 63%|██████▎   | 232602/371472 [7:28:50<10:13:23,  3.77it/s]
 63%|██████▎   | 232603/371472 [7:28:50<10:08:53,  3.80it/s]
 63%|██████▎   | 232604/371472 [7:28:50<10:01:44,  3.85it/s]
 63%|██████▎   | 232605/371472 [7:28:51<9:59:02,  3.86it/s] 
 63%|██████▎   | 232606/371472 [7:28:51<9:45:33,  3.95it/s]
 63%|██████▎   | 232607/371472 [7:28:51<9:45:20,  3.95it/s]
 63%|██████▎   | 232608/371472 [7:28:51<9:37:40,  4.01it/s]
 63%|██████▎   | 232609/371472 [7:28:52<10:10:16,  3.79it/s]
 63%|██████▎   | 232610/371472 [7:28:52<10:12:48,  3.78it/s]
 63%|██████▎   | 232611/371472 [7:28:52<12:11:44,  3.16it/s]
 63%|██████▎   | 232612/371472 [7:28:53<11:34:28,  3.33it/s]
 63%|██████▎   | 232613/371472 [7:28:53<11:22:03,  3.39it/s]
 63%|██████▎   | 232614/371472 [7:28:53<11:45:14,  3.28it/s]
 63%|██████▎   | 232615/371472 [7:28:54<11:43:05,  3.29it/s]
 63%|██████▎   | 232616/371472 [7:28:54<11:27:30,  3.37it/s]
 63%|██████▎   | 232617/371472 [7:28:54<10:52:58,  3.54it/s]
 63%|██████▎   | 232618/371472 [7:28:54<10:17:18,  3.75it/s]
 63%|██████▎   | 232619/371472 [7:28:55<10:26:50,  3.69it/s]
 63%|██████▎   | 232620/371472 [7:28:55<10:26:19,  3.69it/s]
                                                            
{'loss': 2.7908, 'learning_rate': 4.365909629597707e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232620/371472 [7:28:55<10:26:19,  3.69it/s]
 63%|██████▎   | 232621/371472 [7:28:55<10:37:04,  3.63it/s]
 63%|██████▎   | 232622/371472 [7:28:55<10:48:27,  3.57it/s]
 63%|██████▎   | 232623/371472 [7:28:56<10:35:18,  3.64it/s]
 63%|██████▎   | 232624/371472 [7:28:56<10:30:40,  3.67it/s]
 63%|██████▎   | 232625/371472 [7:28:56<10:55:04,  3.53it/s]
 63%|██████▎   | 232626/371472 [7:28:57<10:48:34,  3.57it/s]
 63%|██████▎   | 232627/371472 [7:28:57<11:01:46,  3.50it/s]
 63%|██████▎   | 232628/371472 [7:28:57<10:43:10,  3.60it/s]
 63%|██████▎   | 232629/371472 [7:28:57<10:30:08,  3.67it/s]
 63%|██████▎   | 232630/371472 [7:28:58<10:11:59,  3.78it/s]
 63%|██████▎   | 232631/371472 [7:28:58<10:10:18,  3.79it/s]
 63%|██████▎   | 232632/371472 [7:28:58<10:58:50,  3.51it/s]
 63%|██████▎   | 232633/371472 [7:28:58<10:44:21,  3.59it/s]
 63%|██████▎   | 232634/371472 [7:28:59<10:28:30,  3.68it/s]
 63%|██████▎   | 232635/371472 [7:28:59<10:19:59,  3.73it/s]
 63%|██████▎   | 232636/371472 [7:28:59<10:27:49,  3.69it/s]
 63%|██████▎   | 232637/371472 [7:29:00<10:39:37,  3.62it/s]
 63%|██████▎   | 232638/371472 [7:29:00<10:53:46,  3.54it/s]
 63%|██████▎   | 232639/371472 [7:29:00<10:34:53,  3.64it/s]
 63%|██████▎   | 232640/371472 [7:29:00<10:30:12,  3.67it/s]
                                                            
{'loss': 2.8997, 'learning_rate': 4.365424809842918e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232640/371472 [7:29:00<10:30:12,  3.67it/s]
 63%|██████▎   | 232641/371472 [7:29:01<11:01:56,  3.50it/s]
 63%|██████▎   | 232642/371472 [7:29:01<11:19:01,  3.41it/s]
 63%|██████▎   | 232643/371472 [7:29:01<10:38:40,  3.62it/s]
 63%|██████▎   | 232644/371472 [7:29:02<14:06:03,  2.73it/s]
 63%|██████▎   | 232645/371472 [7:29:02<12:51:25,  3.00it/s]
 63%|██████▎   | 232646/371472 [7:29:02<12:15:51,  3.14it/s]
 63%|██████▎   | 232647/371472 [7:29:03<11:36:14,  3.32it/s]
 63%|██████▎   | 232648/371472 [7:29:03<11:24:09,  3.38it/s]
 63%|██████▎   | 232649/371472 [7:29:03<11:18:58,  3.41it/s]
 63%|██████▎   | 232650/371472 [7:29:03<11:40:05,  3.30it/s]
 63%|██████▎   | 232651/371472 [7:29:04<11:33:56,  3.33it/s]
 63%|██████▎   | 232652/371472 [7:29:04<11:03:29,  3.49it/s]
 63%|██████▎   | 232653/371472 [7:29:04<11:03:48,  3.49it/s]
 63%|██████▎   | 232654/371472 [7:29:05<11:03:13,  3.49it/s]
 63%|██████▎   | 232655/371472 [7:29:05<11:05:52,  3.47it/s]
 63%|██████▎   | 232656/371472 [7:29:05<12:15:52,  3.14it/s]
 63%|██████▎   | 232657/371472 [7:29:06<11:32:00,  3.34it/s]
 63%|██████▎   | 232658/371472 [7:29:06<12:57:32,  2.98it/s]
 63%|██████▎   | 232659/371472 [7:29:06<12:41:35,  3.04it/s]
 63%|██████▎   | 232660/371472 [7:29:07<11:45:51,  3.28it/s]
                                                            
{'loss': 2.8544, 'learning_rate': 4.3649399900881297e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232660/371472 [7:29:07<11:45:51,  3.28it/s]
 63%|██████▎   | 232661/371472 [7:29:07<11:45:48,  3.28it/s]
 63%|██████▎   | 232662/371472 [7:29:07<11:53:35,  3.24it/s]
 63%|██████▎   | 232663/371472 [7:29:07<11:17:11,  3.42it/s]
 63%|██████▎   | 232664/371472 [7:29:08<10:57:48,  3.52it/s]
 63%|██████▎   | 232665/371472 [7:29:08<10:30:49,  3.67it/s]
 63%|██████▎   | 232666/371472 [7:29:08<10:58:49,  3.51it/s]
 63%|██████▎   | 232667/371472 [7:29:08<10:50:32,  3.56it/s]
 63%|██████▎   | 232668/371472 [7:29:09<10:40:10,  3.61it/s]
 63%|██████▎   | 232669/371472 [7:29:09<10:59:03,  3.51it/s]
 63%|██████▎   | 232670/371472 [7:29:09<10:41:13,  3.61it/s]
 63%|██████▎   | 232671/371472 [7:29:10<10:36:59,  3.63it/s]
 63%|██████▎   | 232672/371472 [7:29:10<11:47:21,  3.27it/s]
 63%|██████▎   | 232673/371472 [7:29:10<12:06:15,  3.19it/s]
 63%|██████▎   | 232674/371472 [7:29:11<11:42:57,  3.29it/s]
 63%|██████▎   | 232675/371472 [7:29:11<11:45:05,  3.28it/s]
 63%|██████▎   | 232676/371472 [7:29:11<11:01:37,  3.50it/s]
 63%|██████▎   | 232677/371472 [7:29:11<10:52:00,  3.55it/s]
 63%|██████▎   | 232678/371472 [7:29:12<10:22:45,  3.71it/s]
 63%|██████▎   | 232679/371472 [7:29:12<10:24:49,  3.70it/s]
 63%|██████▎   | 232680/371472 [7:29:12<10:06:28,  3.81it/s]
                                                            
{'loss': 3.0867, 'learning_rate': 4.36445517033334e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232680/371472 [7:29:12<10:06:28,  3.81it/s]
 63%|██████▎   | 232681/371472 [7:29:12<11:00:12,  3.50it/s]
 63%|██████▎   | 232682/371472 [7:29:13<11:08:08,  3.46it/s]
 63%|██████▎   | 232683/371472 [7:29:13<11:35:48,  3.32it/s]
 63%|██████▎   | 232684/371472 [7:29:13<12:10:26,  3.17it/s]
 63%|██████▎   | 232685/371472 [7:29:14<11:29:10,  3.36it/s]
 63%|██████▎   | 232686/371472 [7:29:14<11:07:56,  3.46it/s]
 63%|██████▎   | 232687/371472 [7:29:14<10:49:45,  3.56it/s]
 63%|██████▎   | 232688/371472 [7:29:15<10:50:02,  3.56it/s]
 63%|██████▎   | 232689/371472 [7:29:15<10:35:03,  3.64it/s]
 63%|██████▎   | 232690/371472 [7:29:15<11:01:40,  3.50it/s]
 63%|██████▎   | 232691/371472 [7:29:15<10:37:18,  3.63it/s]
 63%|██████▎   | 232692/371472 [7:29:16<10:34:40,  3.64it/s]
 63%|██████▎   | 232693/371472 [7:29:16<10:25:24,  3.70it/s]
 63%|██████▎   | 232694/371472 [7:29:16<10:36:40,  3.63it/s]
 63%|██████▎   | 232695/371472 [7:29:16<10:42:30,  3.60it/s]
 63%|██████▎   | 232696/371472 [7:29:17<10:53:35,  3.54it/s]
 63%|██████▎   | 232697/371472 [7:29:17<10:53:03,  3.54it/s]
 63%|██████▎   | 232698/371472 [7:29:17<10:56:17,  3.52it/s]
 63%|██████▎   | 232699/371472 [7:29:18<11:57:39,  3.22it/s]
 63%|██████▎   | 232700/371472 [7:29:18<11:24:15,  3.38it/s]
                                                            
{'loss': 2.9509, 'learning_rate': 4.3639703505785516e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232700/371472 [7:29:18<11:24:15,  3.38it/s]
 63%|██████▎   | 232701/371472 [7:29:18<11:30:38,  3.35it/s]
 63%|██████▎   | 232702/371472 [7:29:19<11:28:32,  3.36it/s]
 63%|██████▎   | 232703/371472 [7:29:19<10:59:59,  3.50it/s]
 63%|██████▎   | 232704/371472 [7:29:19<10:44:17,  3.59it/s]
 63%|██████▎   | 232705/371472 [7:29:19<11:00:49,  3.50it/s]
 63%|██████▎   | 232706/371472 [7:29:20<11:11:00,  3.45it/s]
 63%|██████▎   | 232707/371472 [7:29:20<11:24:23,  3.38it/s]
 63%|██████▎   | 232708/371472 [7:29:20<11:02:06,  3.49it/s]
 63%|██████▎   | 232709/371472 [7:29:21<10:45:23,  3.58it/s]
 63%|██████▎   | 232710/371472 [7:29:21<10:23:46,  3.71it/s]
 63%|██████▎   | 232711/371472 [7:29:21<10:48:48,  3.56it/s]
 63%|██████▎   | 232712/371472 [7:29:21<11:09:41,  3.45it/s]
 63%|██████▎   | 232713/371472 [7:29:22<11:35:53,  3.32it/s]
 63%|██████▎   | 232714/371472 [7:29:22<11:03:43,  3.48it/s]
 63%|██████▎   | 232715/371472 [7:29:22<10:52:01,  3.55it/s]
 63%|██████▎   | 232716/371472 [7:29:23<10:48:57,  3.56it/s]
 63%|██████▎   | 232717/371472 [7:29:23<11:00:14,  3.50it/s]
 63%|██████▎   | 232718/371472 [7:29:23<10:44:49,  3.59it/s]
 63%|██████▎   | 232719/371472 [7:29:23<11:03:01,  3.49it/s]
 63%|██████▎   | 232720/371472 [7:29:24<10:28:06,  3.68it/s]
                                                            
{'loss': 2.9711, 'learning_rate': 4.3634855308237624e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232720/371472 [7:29:24<10:28:06,  3.68it/s]
 63%|██████▎   | 232721/371472 [7:29:24<10:55:51,  3.53it/s]
 63%|██████▎   | 232722/371472 [7:29:24<10:37:21,  3.63it/s]
 63%|██████▎   | 232723/371472 [7:29:24<10:52:11,  3.55it/s]
 63%|██████▎   | 232724/371472 [7:29:25<12:13:35,  3.15it/s]
 63%|██████▎   | 232725/371472 [7:29:25<12:57:03,  2.98it/s]
 63%|██████▎   | 232726/371472 [7:29:26<13:31:20,  2.85it/s]
 63%|██████▎   | 232727/371472 [7:29:26<13:20:09,  2.89it/s]
 63%|██████▎   | 232728/371472 [7:29:26<13:20:20,  2.89it/s]
 63%|██████▎   | 232729/371472 [7:29:27<13:03:18,  2.95it/s]
 63%|██████▎   | 232730/371472 [7:29:27<13:38:46,  2.82it/s]
 63%|██████▎   | 232731/371472 [7:29:27<13:08:55,  2.93it/s]
 63%|██████▎   | 232732/371472 [7:29:28<12:25:01,  3.10it/s]
 63%|██████▎   | 232733/371472 [7:29:28<11:51:34,  3.25it/s]
 63%|██████▎   | 232734/371472 [7:29:28<12:47:13,  3.01it/s]
 63%|██████▎   | 232735/371472 [7:29:29<11:58:49,  3.22it/s]
 63%|██████▎   | 232736/371472 [7:29:29<11:41:14,  3.30it/s]
 63%|██████▎   | 232737/371472 [7:29:29<12:35:18,  3.06it/s]
 63%|██████▎   | 232738/371472 [7:29:29<12:00:31,  3.21it/s]
 63%|██████▎   | 232739/371472 [7:29:30<12:08:12,  3.18it/s]
 63%|██████▎   | 232740/371472 [7:29:30<11:36:28,  3.32it/s]
                                                            
{'loss': 2.8312, 'learning_rate': 4.3630007110689736e-07, 'epoch': 10.02}
+
 63%|██████▎   | 232740/371472 [7:29:30<11:36:28,  3.32it/s]
 63%|██████▎   | 232741/371472 [7:29:30<11:02:37,  3.49it/s]
 63%|██████▎   | 232742/371472 [7:29:31<11:45:24,  3.28it/s]
 63%|██████▎   | 232743/371472 [7:29:31<12:58:48,  2.97it/s]
 63%|██████▎   | 232744/371472 [7:29:31<12:26:37,  3.10it/s]
 63%|██████▎   | 232745/371472 [7:29:32<11:25:10,  3.37it/s]
 63%|██████▎   | 232746/371472 [7:29:32<11:15:58,  3.42it/s]
 63%|██████▎   | 232747/371472 [7:29:32<10:40:49,  3.61it/s]
 63%|██████▎   | 232748/371472 [7:29:33<11:42:18,  3.29it/s]
 63%|██████▎   | 232749/371472 [7:29:33<11:59:47,  3.21it/s]
 63%|██████▎   | 232750/371472 [7:29:33<11:20:13,  3.40it/s]
 63%|██████▎   | 232751/371472 [7:29:33<11:05:02,  3.48it/s]
 63%|██████▎   | 232752/371472 [7:29:34<11:22:31,  3.39it/s]
 63%|██████▎   | 232753/371472 [7:29:34<11:00:59,  3.50it/s]
 63%|██████▎   | 232754/371472 [7:29:34<11:30:30,  3.35it/s]
 63%|██████▎   | 232755/371472 [7:29:35<11:31:37,  3.34it/s]
 63%|██████▎   | 232756/371472 [7:29:35<10:56:15,  3.52it/s]
 63%|██████▎   | 232757/371472 [7:29:35<10:36:50,  3.63it/s]
 63%|██████▎   | 232758/371472 [7:29:35<10:16:26,  3.75it/s]
 63%|██████▎   | 232759/371472 [7:29:36<10:24:38,  3.70it/s]
 63%|██████▎   | 232760/371472 [7:29:36<10:46:14,  3.58it/s]
                                                            
{'loss': 2.6038, 'learning_rate': 4.3625158913141843e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232760/371472 [7:29:36<10:46:14,  3.58it/s]
 63%|██████▎   | 232761/371472 [7:29:36<11:25:07,  3.37it/s]
 63%|██████▎   | 232762/371472 [7:29:37<11:04:14,  3.48it/s]
 63%|██████▎   | 232763/371472 [7:29:37<10:44:20,  3.59it/s]
 63%|██████▎   | 232764/371472 [7:29:37<10:59:36,  3.50it/s]
 63%|██████▎   | 232765/371472 [7:29:37<10:39:28,  3.62it/s]
 63%|██████▎   | 232766/371472 [7:29:38<10:25:45,  3.69it/s]
 63%|██████▎   | 232767/371472 [7:29:38<10:27:36,  3.68it/s]
 63%|██████▎   | 232768/371472 [7:29:38<10:11:02,  3.78it/s]
 63%|██████▎   | 232769/371472 [7:29:38<9:58:37,  3.86it/s] 
 63%|██████▎   | 232770/371472 [7:29:39<10:07:42,  3.80it/s]
 63%|██████▎   | 232771/371472 [7:29:39<10:36:35,  3.63it/s]
 63%|██████▎   | 232772/371472 [7:29:39<10:41:33,  3.60it/s]
 63%|██████▎   | 232773/371472 [7:29:39<10:41:09,  3.61it/s]
 63%|██████▎   | 232774/371472 [7:29:40<10:23:27,  3.71it/s]
 63%|██████▎   | 232775/371472 [7:29:40<10:49:10,  3.56it/s]
 63%|██████▎   | 232776/371472 [7:29:40<10:54:28,  3.53it/s]
 63%|██████▎   | 232777/371472 [7:29:41<10:46:52,  3.57it/s]
 63%|██████▎   | 232778/371472 [7:29:41<10:34:50,  3.64it/s]
 63%|██████▎   | 232779/371472 [7:29:41<10:42:14,  3.60it/s]
 63%|██████▎   | 232780/371472 [7:29:41<10:50:02,  3.56it/s]
                                                            
{'loss': 3.0307, 'learning_rate': 4.362031071559396e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232780/371472 [7:29:41<10:50:02,  3.56it/s]
 63%|██████▎   | 232781/371472 [7:29:42<10:45:44,  3.58it/s]
 63%|██████▎   | 232782/371472 [7:29:42<10:33:53,  3.65it/s]
 63%|██████▎   | 232783/371472 [7:29:42<10:19:37,  3.73it/s]
 63%|██████▎   | 232784/371472 [7:29:43<10:49:19,  3.56it/s]
 63%|██████▎   | 232785/371472 [7:29:43<12:06:07,  3.18it/s]
 63%|██████▎   | 232786/371472 [7:29:43<11:42:47,  3.29it/s]
 63%|██████▎   | 232787/371472 [7:29:43<11:19:55,  3.40it/s]
 63%|██████▎   | 232788/371472 [7:29:44<10:44:05,  3.59it/s]
 63%|██████▎   | 232789/371472 [7:29:44<11:05:09,  3.47it/s]
 63%|██████▎   | 232790/371472 [7:29:44<10:45:39,  3.58it/s]
 63%|██████▎   | 232791/371472 [7:29:45<10:56:03,  3.52it/s]
 63%|██████▎   | 232792/371472 [7:29:45<10:58:51,  3.51it/s]
 63%|██████▎   | 232793/371472 [7:29:45<10:38:08,  3.62it/s]
 63%|██████▎   | 232794/371472 [7:29:45<10:33:43,  3.65it/s]
 63%|██████▎   | 232795/371472 [7:29:46<10:17:34,  3.74it/s]
 63%|██████▎   | 232796/371472 [7:29:46<10:38:28,  3.62it/s]
 63%|██████▎   | 232797/371472 [7:29:46<10:54:04,  3.53it/s]
 63%|██████▎   | 232798/371472 [7:29:47<11:08:06,  3.46it/s]
 63%|██████▎   | 232799/371472 [7:29:47<12:03:50,  3.19it/s]
 63%|██████▎   | 232800/371472 [7:29:47<11:44:37,  3.28it/s]
                                                            
{'loss': 2.8837, 'learning_rate': 4.361546251804607e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232800/371472 [7:29:47<11:44:37,  3.28it/s]
 63%|██████▎   | 232801/371472 [7:29:48<11:42:04,  3.29it/s]
 63%|██████▎   | 232802/371472 [7:29:48<11:23:31,  3.38it/s]
 63%|██████▎   | 232803/371472 [7:29:48<11:25:59,  3.37it/s]
 63%|██████▎   | 232804/371472 [7:29:48<11:09:29,  3.45it/s]
 63%|██████▎   | 232805/371472 [7:29:49<11:08:29,  3.46it/s]
 63%|██████▎   | 232806/371472 [7:29:49<10:36:16,  3.63it/s]
 63%|██████▎   | 232807/371472 [7:29:49<11:26:09,  3.37it/s]
 63%|██████▎   | 232808/371472 [7:29:50<11:16:15,  3.42it/s]
 63%|██████▎   | 232809/371472 [7:29:50<10:37:59,  3.62it/s]
 63%|██████▎   | 232810/371472 [7:29:50<11:08:07,  3.46it/s]
 63%|██████▎   | 232811/371472 [7:29:50<10:35:12,  3.64it/s]
 63%|██████▎   | 232812/371472 [7:29:51<11:20:01,  3.40it/s]
 63%|██████▎   | 232813/371472 [7:29:51<11:15:49,  3.42it/s]
 63%|██████▎   | 232814/371472 [7:29:51<10:54:03,  3.53it/s]
 63%|██████▎   | 232815/371472 [7:29:51<10:57:07,  3.52it/s]
 63%|██████▎   | 232816/371472 [7:29:52<10:23:57,  3.70it/s]
 63%|██████▎   | 232817/371472 [7:29:52<10:42:43,  3.60it/s]
 63%|██████▎   | 232818/371472 [7:29:52<10:22:04,  3.71it/s]
 63%|██████▎   | 232819/371472 [7:29:53<10:47:05,  3.57it/s]
 63%|██████▎   | 232820/371472 [7:29:53<11:13:16,  3.43it/s]
                                                            
{'loss': 2.8984, 'learning_rate': 4.361061432049818e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232820/371472 [7:29:53<11:13:16,  3.43it/s]
 63%|██████▎   | 232821/371472 [7:29:53<10:35:33,  3.64it/s]
 63%|██████▎   | 232822/371472 [7:29:53<10:31:12,  3.66it/s]
 63%|██████▎   | 232823/371472 [7:29:54<10:43:47,  3.59it/s]
 63%|██████▎   | 232824/371472 [7:29:54<11:06:22,  3.47it/s]
 63%|██████▎   | 232825/371472 [7:29:54<10:48:03,  3.57it/s]
 63%|██████▎   | 232826/371472 [7:29:55<10:47:13,  3.57it/s]
 63%|██████▎   | 232827/371472 [7:29:55<10:40:10,  3.61it/s]
 63%|██████▎   | 232828/371472 [7:29:55<10:34:43,  3.64it/s]
 63%|██████▎   | 232829/371472 [7:29:55<10:36:02,  3.63it/s]
 63%|██████▎   | 232830/371472 [7:29:56<10:38:19,  3.62it/s]
 63%|██████▎   | 232831/371472 [7:29:56<10:05:38,  3.82it/s]
 63%|██████▎   | 232832/371472 [7:29:56<10:10:25,  3.79it/s]
 63%|██████▎   | 232833/371472 [7:29:56<10:14:50,  3.76it/s]
 63%|██████▎   | 232834/371472 [7:29:57<10:36:59,  3.63it/s]
 63%|██████▎   | 232835/371472 [7:29:57<11:06:50,  3.47it/s]
 63%|██████▎   | 232836/371472 [7:29:57<10:33:42,  3.65it/s]
 63%|██████▎   | 232837/371472 [7:29:58<10:48:40,  3.56it/s]
 63%|██████▎   | 232838/371472 [7:29:58<10:23:54,  3.70it/s]
 63%|██████▎   | 232839/371472 [7:29:58<10:41:30,  3.60it/s]
 63%|██████▎   | 232840/371472 [7:29:58<11:00:14,  3.50it/s]
                                                            
{'loss': 2.8623, 'learning_rate': 4.360576612295029e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232840/371472 [7:29:58<11:00:14,  3.50it/s]
 63%|██████▎   | 232841/371472 [7:29:59<10:29:23,  3.67it/s]
 63%|██████▎   | 232842/371472 [7:29:59<10:59:30,  3.50it/s]
 63%|██████▎   | 232843/371472 [7:29:59<10:32:35,  3.65it/s]
 63%|██████▎   | 232844/371472 [7:29:59<10:33:21,  3.65it/s]
 63%|██████▎   | 232845/371472 [7:30:00<11:33:01,  3.33it/s]
 63%|██████▎   | 232846/371472 [7:30:00<11:22:00,  3.39it/s]
 63%|██████▎   | 232847/371472 [7:30:00<10:47:19,  3.57it/s]
 63%|██████▎   | 232848/371472 [7:30:01<11:07:28,  3.46it/s]
 63%|██████▎   | 232849/371472 [7:30:01<11:02:31,  3.49it/s]
 63%|██████▎   | 232850/371472 [7:30:01<11:06:35,  3.47it/s]
 63%|██████▎   | 232851/371472 [7:30:02<11:18:11,  3.41it/s]
 63%|██████▎   | 232852/371472 [7:30:02<11:14:19,  3.43it/s]
 63%|██████▎   | 232853/371472 [7:30:02<11:03:18,  3.48it/s]
 63%|██████▎   | 232854/371472 [7:30:02<11:29:16,  3.35it/s]
 63%|██████▎   | 232855/371472 [7:30:03<10:49:27,  3.56it/s]
 63%|██████▎   | 232856/371472 [7:30:03<10:53:46,  3.53it/s]
 63%|██████▎   | 232857/371472 [7:30:03<11:57:08,  3.22it/s]
 63%|██████▎   | 232858/371472 [7:30:04<11:17:42,  3.41it/s]
 63%|██████▎   | 232859/371472 [7:30:04<10:34:59,  3.64it/s]
 63%|██████▎   | 232860/371472 [7:30:04<11:20:52,  3.39it/s]
                                                            
{'loss': 2.8977, 'learning_rate': 4.3600917925402405e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232860/371472 [7:30:04<11:20:52,  3.39it/s]
 63%|██████▎   | 232861/371472 [7:30:04<10:55:35,  3.52it/s]
 63%|██████▎   | 232862/371472 [7:30:05<10:55:09,  3.53it/s]
 63%|██████▎   | 232863/371472 [7:30:05<11:19:26,  3.40it/s]
 63%|██████▎   | 232864/371472 [7:30:05<11:07:15,  3.46it/s]
 63%|██████▎   | 232865/371472 [7:30:06<10:38:17,  3.62it/s]
 63%|██████▎   | 232866/371472 [7:30:06<10:56:58,  3.52it/s]
 63%|██████▎   | 232867/371472 [7:30:06<11:52:06,  3.24it/s]
 63%|██████▎   | 232868/371472 [7:30:07<12:01:10,  3.20it/s]
 63%|██████▎   | 232869/371472 [7:30:07<11:53:28,  3.24it/s]
 63%|██████▎   | 232870/371472 [7:30:07<11:21:22,  3.39it/s]
 63%|██████▎   | 232871/371472 [7:30:07<11:04:43,  3.48it/s]
 63%|██████▎   | 232872/371472 [7:30:08<11:03:18,  3.48it/s]
 63%|██████▎   | 232873/371472 [7:30:08<10:25:38,  3.69it/s]
 63%|██████▎   | 232874/371472 [7:30:08<10:19:03,  3.73it/s]
 63%|██████▎   | 232875/371472 [7:30:08<10:07:16,  3.80it/s]
 63%|██████▎   | 232876/371472 [7:30:09<10:18:35,  3.73it/s]
 63%|██████▎   | 232877/371472 [7:30:09<10:17:13,  3.74it/s]
 63%|██████▎   | 232878/371472 [7:30:09<10:00:03,  3.85it/s]
 63%|██████▎   | 232879/371472 [7:30:09<9:56:00,  3.88it/s] 
 63%|██████▎   | 232880/371472 [7:30:10<10:47:38,  3.57it/s]
                                                            
{'loss': 2.8715, 'learning_rate': 4.3596069727854507e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232880/371472 [7:30:10<10:47:38,  3.57it/s]
 63%|██████▎   | 232881/371472 [7:30:10<10:35:00,  3.64it/s]
 63%|██████▎   | 232882/371472 [7:30:10<11:00:45,  3.50it/s]
 63%|██████▎   | 232883/371472 [7:30:11<10:53:53,  3.53it/s]
 63%|██████▎   | 232884/371472 [7:30:11<10:31:46,  3.66it/s]
 63%|██████▎   | 232885/371472 [7:30:11<10:55:52,  3.52it/s]
 63%|██████▎   | 232886/371472 [7:30:11<10:58:28,  3.51it/s]
 63%|██████▎   | 232887/371472 [7:30:12<10:35:13,  3.64it/s]
 63%|██████▎   | 232888/371472 [7:30:12<10:41:21,  3.60it/s]
 63%|██████▎   | 232889/371472 [7:30:12<10:24:29,  3.70it/s]
 63%|██████▎   | 232890/371472 [7:30:13<10:23:28,  3.70it/s]
 63%|██████▎   | 232891/371472 [7:30:13<11:21:08,  3.39it/s]
 63%|██████▎   | 232892/371472 [7:30:13<10:39:53,  3.61it/s]
 63%|██████▎   | 232893/371472 [7:30:13<10:17:11,  3.74it/s]
 63%|██████▎   | 232894/371472 [7:30:14<10:07:29,  3.80it/s]
 63%|██████▎   | 232895/371472 [7:30:14<10:17:47,  3.74it/s]
 63%|██████▎   | 232896/371472 [7:30:14<10:08:17,  3.80it/s]
 63%|██████▎   | 232897/371472 [7:30:14<9:57:56,  3.86it/s] 
 63%|██████▎   | 232898/371472 [7:30:15<10:05:41,  3.81it/s]
 63%|██████▎   | 232899/371472 [7:30:15<10:48:29,  3.56it/s]
 63%|██████▎   | 232900/371472 [7:30:15<10:31:02,  3.66it/s]
                                                            
{'loss': 2.7951, 'learning_rate': 4.3591221530306625e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232900/371472 [7:30:15<10:31:02,  3.66it/s]
 63%|██████▎   | 232901/371472 [7:30:16<11:14:22,  3.42it/s]
 63%|██████▎   | 232902/371472 [7:30:16<11:21:20,  3.39it/s]
 63%|██████▎   | 232903/371472 [7:30:16<10:50:02,  3.55it/s]
 63%|██████▎   | 232904/371472 [7:30:16<10:39:34,  3.61it/s]
 63%|██████▎   | 232905/371472 [7:30:17<10:26:34,  3.69it/s]
 63%|██████▎   | 232906/371472 [7:30:17<10:51:39,  3.54it/s]
 63%|██████▎   | 232907/371472 [7:30:17<10:20:59,  3.72it/s]
 63%|██████▎   | 232908/371472 [7:30:17<10:08:00,  3.80it/s]
 63%|██████▎   | 232909/371472 [7:30:18<9:48:58,  3.92it/s] 
 63%|██████▎   | 232910/371472 [7:30:18<10:25:03,  3.69it/s]
 63%|██████▎   | 232911/371472 [7:30:18<10:30:57,  3.66it/s]
 63%|██████▎   | 232912/371472 [7:30:19<10:07:15,  3.80it/s]
 63%|██████▎   | 232913/371472 [7:30:19<10:28:13,  3.68it/s]
 63%|██████▎   | 232914/371472 [7:30:19<11:05:00,  3.47it/s]
 63%|██████▎   | 232915/371472 [7:30:19<10:56:11,  3.52it/s]
 63%|██████▎   | 232916/371472 [7:30:20<10:45:33,  3.58it/s]
 63%|██████▎   | 232917/371472 [7:30:20<10:37:55,  3.62it/s]
 63%|██████▎   | 232918/371472 [7:30:20<10:15:38,  3.75it/s]
 63%|██████▎   | 232919/371472 [7:30:21<12:02:10,  3.20it/s]
 63%|██████▎   | 232920/371472 [7:30:21<11:43:13,  3.28it/s]
                                                            
{'loss': 2.8826, 'learning_rate': 4.358637333275873e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232920/371472 [7:30:21<11:43:13,  3.28it/s]
 63%|██████▎   | 232921/371472 [7:30:21<11:58:22,  3.21it/s]
 63%|██████▎   | 232922/371472 [7:30:22<11:34:44,  3.32it/s]
 63%|██████▎   | 232923/371472 [7:30:22<11:09:42,  3.45it/s]
 63%|██████▎   | 232924/371472 [7:30:22<10:40:38,  3.60it/s]
 63%|██████▎   | 232925/371472 [7:30:22<10:23:35,  3.70it/s]
 63%|██████▎   | 232926/371472 [7:30:23<11:26:21,  3.36it/s]
 63%|██████▎   | 232927/371472 [7:30:23<10:43:18,  3.59it/s]
 63%|██████▎   | 232928/371472 [7:30:23<10:15:23,  3.75it/s]
 63%|██████▎   | 232929/371472 [7:30:23<10:31:08,  3.66it/s]
 63%|██████▎   | 232930/371472 [7:30:24<10:20:44,  3.72it/s]
 63%|██████▎   | 232931/371472 [7:30:24<11:10:41,  3.44it/s]
 63%|██████▎   | 232932/371472 [7:30:24<12:02:02,  3.20it/s]
 63%|██████▎   | 232933/371472 [7:30:25<11:04:43,  3.47it/s]
 63%|██████▎   | 232934/371472 [7:30:25<10:55:06,  3.52it/s]
 63%|██████▎   | 232935/371472 [7:30:25<10:33:28,  3.64it/s]
 63%|██████▎   | 232936/371472 [7:30:25<10:23:36,  3.70it/s]
 63%|██████▎   | 232937/371472 [7:30:26<10:24:19,  3.70it/s]
 63%|██████▎   | 232938/371472 [7:30:26<10:13:31,  3.76it/s]
 63%|██████▎   | 232939/371472 [7:30:26<10:07:09,  3.80it/s]
 63%|██████▎   | 232940/371472 [7:30:26<10:30:13,  3.66it/s]
                                                            
{'loss': 2.9427, 'learning_rate': 4.3581525135210834e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232940/371472 [7:30:26<10:30:13,  3.66it/s]
 63%|██████▎   | 232941/371472 [7:30:27<10:34:57,  3.64it/s]
 63%|██████▎   | 232942/371472 [7:30:27<10:55:24,  3.52it/s]
 63%|██████▎   | 232943/371472 [7:30:27<10:37:30,  3.62it/s]
 63%|██████▎   | 232944/371472 [7:30:28<11:01:52,  3.49it/s]
 63%|██████▎   | 232945/371472 [7:30:28<10:57:16,  3.51it/s]
 63%|██████▎   | 232946/371472 [7:30:28<10:37:37,  3.62it/s]
 63%|██████▎   | 232947/371472 [7:30:28<10:35:06,  3.64it/s]
 63%|██████▎   | 232948/371472 [7:30:29<10:22:03,  3.71it/s]
 63%|██████▎   | 232949/371472 [7:30:29<10:22:16,  3.71it/s]
 63%|██████▎   | 232950/371472 [7:30:29<10:50:21,  3.55it/s]
 63%|██████▎   | 232951/371472 [7:30:29<10:10:25,  3.78it/s]
 63%|██████▎   | 232952/371472 [7:30:30<10:07:06,  3.80it/s]
 63%|██████▎   | 232953/371472 [7:30:30<10:28:48,  3.67it/s]
 63%|██████▎   | 232954/371472 [7:30:30<10:20:18,  3.72it/s]
 63%|██████▎   | 232955/371472 [7:30:31<10:28:47,  3.67it/s]
 63%|██████▎   | 232956/371472 [7:30:31<10:49:39,  3.55it/s]
 63%|██████▎   | 232957/371472 [7:30:31<10:17:09,  3.74it/s]
 63%|██████▎   | 232958/371472 [7:30:31<10:14:16,  3.76it/s]
 63%|██████▎   | 232959/371472 [7:30:32<10:44:29,  3.58it/s]
 63%|██████▎   | 232960/371472 [7:30:32<11:17:16,  3.41it/s]
                                                            
{'loss': 2.8787, 'learning_rate': 4.357667693766295e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232960/371472 [7:30:32<11:17:16,  3.41it/s]
 63%|██████▎   | 232961/371472 [7:30:32<10:50:09,  3.55it/s]
 63%|██████▎   | 232962/371472 [7:30:33<10:31:50,  3.65it/s]
 63%|██████▎   | 232963/371472 [7:30:33<11:06:37,  3.46it/s]
 63%|██████▎   | 232964/371472 [7:30:33<10:46:13,  3.57it/s]
 63%|██████▎   | 232965/371472 [7:30:33<11:23:41,  3.38it/s]
 63%|██████▎   | 232966/371472 [7:30:34<11:31:39,  3.34it/s]
 63%|██████▎   | 232967/371472 [7:30:34<10:57:14,  3.51it/s]
 63%|██████▎   | 232968/371472 [7:30:34<11:18:03,  3.40it/s]
 63%|██████▎   | 232969/371472 [7:30:35<12:03:08,  3.19it/s]
 63%|██████▎   | 232970/371472 [7:30:35<11:38:41,  3.30it/s]
 63%|██████▎   | 232971/371472 [7:30:35<11:10:19,  3.44it/s]
 63%|██████▎   | 232972/371472 [7:30:36<12:18:17,  3.13it/s]
 63%|██████▎   | 232973/371472 [7:30:36<11:37:55,  3.31it/s]
 63%|██████▎   | 232974/371472 [7:30:36<11:05:26,  3.47it/s]
 63%|██████▎   | 232975/371472 [7:30:37<12:30:55,  3.07it/s]
 63%|██████▎   | 232976/371472 [7:30:37<12:52:44,  2.99it/s]
 63%|██████▎   | 232977/371472 [7:30:37<11:50:55,  3.25it/s]
 63%|██████▎   | 232978/371472 [7:30:37<12:28:37,  3.08it/s]
 63%|██████▎   | 232979/371472 [7:30:38<12:19:32,  3.12it/s]
 63%|██████▎   | 232980/371472 [7:30:38<13:03:56,  2.94it/s]
                                                            
{'loss': 2.7478, 'learning_rate': 4.357182874011506e-07, 'epoch': 10.03}
+
 63%|██████▎   | 232980/371472 [7:30:38<13:03:56,  2.94it/s]
 63%|██████▎   | 232981/371472 [7:30:38<12:07:23,  3.17it/s]
 63%|██████▎   | 232982/371472 [7:30:39<12:05:13,  3.18it/s]
 63%|██████▎   | 232983/371472 [7:30:39<12:23:04,  3.11it/s]
 63%|██████▎   | 232984/371472 [7:30:39<11:41:01,  3.29it/s]
 63%|██████▎   | 232985/371472 [7:30:40<11:11:30,  3.44it/s]
 63%|██████▎   | 232986/371472 [7:30:40<11:09:24,  3.45it/s]
 63%|██████▎   | 232987/371472 [7:30:40<10:50:52,  3.55it/s]
 63%|██████▎   | 232988/371472 [7:30:40<10:13:57,  3.76it/s]
 63%|██████▎   | 232989/371472 [7:30:41<10:33:30,  3.64it/s]
 63%|██████▎   | 232990/371472 [7:30:41<10:52:12,  3.54it/s]
 63%|██████▎   | 232991/371472 [7:30:41<10:57:06,  3.51it/s]
 63%|██████▎   | 232992/371472 [7:30:42<10:32:59,  3.65it/s]
 63%|██████▎   | 232993/371472 [7:30:42<10:35:07,  3.63it/s]
 63%|██████▎   | 232994/371472 [7:30:42<10:10:33,  3.78it/s]
 63%|██████▎   | 232995/371472 [7:30:42<10:04:25,  3.82it/s]
 63%|██████▎   | 232996/371472 [7:30:43<10:29:50,  3.66it/s]
 63%|██████▎   | 232997/371472 [7:30:43<10:14:51,  3.75it/s]
 63%|██████▎   | 232998/371472 [7:30:43<10:15:28,  3.75it/s]
 63%|██████▎   | 232999/371472 [7:30:43<10:19:01,  3.73it/s]
 63%|██████▎   | 233000/371472 [7:30:44<10:02:16,  3.83it/s]
                                                            
{'loss': 3.0213, 'learning_rate': 4.356698054256717e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233000/371472 [7:30:44<10:02:16,  3.83it/s]
 63%|██████▎   | 233001/371472 [7:30:44<10:15:01,  3.75it/s]
 63%|██████▎   | 233002/371472 [7:30:44<10:35:19,  3.63it/s]
 63%|██████▎   | 233003/371472 [7:30:44<10:19:19,  3.73it/s]
 63%|██████▎   | 233004/371472 [7:30:45<10:43:34,  3.59it/s]
 63%|██████▎   | 233005/371472 [7:30:45<11:18:16,  3.40it/s]
 63%|██████▎   | 233006/371472 [7:30:45<11:20:29,  3.39it/s]
 63%|██████▎   | 233007/371472 [7:30:46<11:15:22,  3.42it/s]
 63%|██████▎   | 233008/371472 [7:30:46<11:32:54,  3.33it/s]
 63%|██████▎   | 233009/371472 [7:30:46<10:43:36,  3.59it/s]
 63%|██████▎   | 233010/371472 [7:30:47<10:41:42,  3.60it/s]
 63%|██████▎   | 233011/371472 [7:30:47<11:18:12,  3.40it/s]
 63%|██████▎   | 233012/371472 [7:30:47<11:16:09,  3.41it/s]
 63%|██████▎   | 233013/371472 [7:30:47<10:58:34,  3.50it/s]
 63%|██████▎   | 233014/371472 [7:30:48<10:59:05,  3.50it/s]
 63%|██████▎   | 233015/371472 [7:30:48<10:38:56,  3.61it/s]
 63%|██████▎   | 233016/371472 [7:30:48<10:39:28,  3.61it/s]
 63%|██████▎   | 233017/371472 [7:30:49<10:52:47,  3.53it/s]
 63%|██████▎   | 233018/371472 [7:30:49<10:28:59,  3.67it/s]
 63%|██████▎   | 233019/371472 [7:30:49<10:43:03,  3.59it/s]
 63%|██████▎   | 233020/371472 [7:30:49<10:33:05,  3.64it/s]
                                                            
{'loss': 2.9241, 'learning_rate': 4.3562132345019273e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233020/371472 [7:30:49<10:33:05,  3.64it/s]
 63%|██████▎   | 233021/371472 [7:30:50<10:43:01,  3.59it/s]
 63%|██████▎   | 233022/371472 [7:30:50<10:32:57,  3.65it/s]
 63%|██████▎   | 233023/371472 [7:30:50<10:49:08,  3.55it/s]
 63%|██████▎   | 233024/371472 [7:30:50<10:21:43,  3.71it/s]
 63%|██████▎   | 233025/371472 [7:30:51<11:10:01,  3.44it/s]
 63%|██████▎   | 233026/371472 [7:30:51<10:54:16,  3.53it/s]
 63%|██████▎   | 233027/371472 [7:30:51<10:35:04,  3.63it/s]
 63%|██████▎   | 233028/371472 [7:30:52<10:28:22,  3.67it/s]
 63%|██████▎   | 233029/371472 [7:30:52<10:38:42,  3.61it/s]
 63%|██████▎   | 233030/371472 [7:30:52<10:20:09,  3.72it/s]
 63%|██████▎   | 233031/371472 [7:30:52<10:35:34,  3.63it/s]
 63%|██████▎   | 233032/371472 [7:30:53<11:32:05,  3.33it/s]
 63%|██████▎   | 233033/371472 [7:30:53<11:08:30,  3.45it/s]
 63%|██████▎   | 233034/371472 [7:30:53<10:36:05,  3.63it/s]
 63%|██████▎   | 233035/371472 [7:30:54<10:45:43,  3.57it/s]
 63%|██████▎   | 233036/371472 [7:30:54<10:24:14,  3.70it/s]
 63%|██████▎   | 233037/371472 [7:30:54<10:39:22,  3.61it/s]
 63%|██████▎   | 233038/371472 [7:30:54<10:13:43,  3.76it/s]
 63%|██████▎   | 233039/371472 [7:30:55<10:24:40,  3.69it/s]
 63%|██████▎   | 233040/371472 [7:30:55<10:32:48,  3.65it/s]
                                                            
{'loss': 2.8302, 'learning_rate': 4.3557284147471396e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233040/371472 [7:30:55<10:32:48,  3.65it/s]
 63%|██████▎   | 233041/371472 [7:30:55<10:12:40,  3.77it/s]
 63%|██████▎   | 233042/371472 [7:30:55<9:51:23,  3.90it/s] 
 63%|██████▎   | 233043/371472 [7:30:56<11:25:37,  3.37it/s]
 63%|██████▎   | 233044/371472 [7:30:56<10:41:38,  3.60it/s]
 63%|██████▎   | 233045/371472 [7:30:56<11:00:25,  3.49it/s]
 63%|██████▎   | 233046/371472 [7:30:57<11:00:56,  3.49it/s]
 63%|██████▎   | 233047/371472 [7:30:57<10:52:55,  3.53it/s]
 63%|██████▎   | 233048/371472 [7:30:57<10:43:26,  3.59it/s]
 63%|██████▎   | 233049/371472 [7:30:57<10:52:34,  3.54it/s]
 63%|██████▎   | 233050/371472 [7:30:58<10:57:07,  3.51it/s]
 63%|██████▎   | 233051/371472 [7:30:58<10:52:53,  3.53it/s]
 63%|██████▎   | 233052/371472 [7:30:58<10:40:08,  3.60it/s]
 63%|██████▎   | 233053/371472 [7:30:59<10:49:33,  3.55it/s]
 63%|██████▎   | 233054/371472 [7:30:59<10:42:31,  3.59it/s]
 63%|██████▎   | 233055/371472 [7:30:59<10:44:10,  3.58it/s]
 63%|██████▎   | 233056/371472 [7:30:59<11:25:09,  3.37it/s]
 63%|██████▎   | 233057/371472 [7:31:00<11:47:16,  3.26it/s]
 63%|██████▎   | 233058/371472 [7:31:00<11:34:26,  3.32it/s]
 63%|██████▎   | 233059/371472 [7:31:00<11:39:00,  3.30it/s]
 63%|██████▎   | 233060/371472 [7:31:01<11:12:18,  3.43it/s]
                                                            
{'loss': 2.8723, 'learning_rate': 4.35524359499235e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233060/371472 [7:31:01<11:12:18,  3.43it/s]
 63%|██████▎   | 233061/371472 [7:31:01<11:12:46,  3.43it/s]
 63%|██████▎   | 233062/371472 [7:31:01<10:44:31,  3.58it/s]
 63%|██████▎   | 233063/371472 [7:31:01<10:28:24,  3.67it/s]
 63%|██████▎   | 233064/371472 [7:31:02<10:08:37,  3.79it/s]
 63%|██████▎   | 233065/371472 [7:31:02<10:24:33,  3.69it/s]
 63%|██████▎   | 233066/371472 [7:31:02<10:19:01,  3.73it/s]
 63%|██████▎   | 233067/371472 [7:31:02<10:14:49,  3.75it/s]
 63%|██████▎   | 233068/371472 [7:31:03<10:39:53,  3.60it/s]
 63%|██████▎   | 233069/371472 [7:31:03<10:11:14,  3.77it/s]
 63%|██████▎   | 233070/371472 [7:31:03<10:50:32,  3.55it/s]
 63%|██████▎   | 233071/371472 [7:31:04<11:26:46,  3.36it/s]
 63%|██████▎   | 233072/371472 [7:31:04<10:50:27,  3.55it/s]
 63%|██████▎   | 233073/371472 [7:31:04<10:54:57,  3.52it/s]
 63%|██████▎   | 233074/371472 [7:31:04<10:51:20,  3.54it/s]
 63%|██████▎   | 233075/371472 [7:31:05<10:26:18,  3.68it/s]
 63%|██████▎   | 233076/371472 [7:31:05<10:45:16,  3.57it/s]
 63%|██████▎   | 233077/371472 [7:31:05<10:27:39,  3.67it/s]
 63%|██████▎   | 233078/371472 [7:31:06<10:40:20,  3.60it/s]
 63%|██████▎   | 233079/371472 [7:31:06<10:41:56,  3.59it/s]
 63%|██████▎   | 233080/371472 [7:31:06<10:29:54,  3.66it/s]
                                                            
{'loss': 2.784, 'learning_rate': 4.3547587752375616e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233080/371472 [7:31:06<10:29:54,  3.66it/s]
 63%|██████▎   | 233081/371472 [7:31:06<10:12:49,  3.76it/s]
 63%|██████▎   | 233082/371472 [7:31:07<9:59:41,  3.85it/s] 
 63%|██████▎   | 233083/371472 [7:31:07<10:31:42,  3.65it/s]
 63%|██████▎   | 233084/371472 [7:31:07<10:23:13,  3.70it/s]
 63%|██████▎   | 233085/371472 [7:31:07<10:12:12,  3.77it/s]
 63%|██████▎   | 233086/371472 [7:31:08<9:50:42,  3.90it/s] 
 63%|██████▎   | 233087/371472 [7:31:08<10:02:43,  3.83it/s]
 63%|██████▎   | 233088/371472 [7:31:08<10:12:22,  3.77it/s]
 63%|██████▎   | 233089/371472 [7:31:09<10:39:23,  3.61it/s]
 63%|██████▎   | 233090/371472 [7:31:09<10:19:29,  3.72it/s]
 63%|██████▎   | 233091/371472 [7:31:09<10:00:31,  3.84it/s]
 63%|██████▎   | 233092/371472 [7:31:09<10:33:56,  3.64it/s]
 63%|██████▎   | 233093/371472 [7:31:10<10:04:25,  3.82it/s]
 63%|██████▎   | 233094/371472 [7:31:10<10:18:50,  3.73it/s]
 63%|██████▎   | 233095/371472 [7:31:10<10:38:08,  3.61it/s]
 63%|██████▎   | 233096/371472 [7:31:10<10:27:51,  3.67it/s]
 63%|██████▎   | 233097/371472 [7:31:11<10:33:17,  3.64it/s]
 63%|██████▎   | 233098/371472 [7:31:11<10:22:44,  3.70it/s]
 63%|██████▎   | 233099/371472 [7:31:11<10:15:47,  3.75it/s]
 63%|██████▎   | 233100/371472 [7:31:11<10:33:30,  3.64it/s]
                                                            
{'loss': 2.8636, 'learning_rate': 4.3542739554827723e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233100/371472 [7:31:11<10:33:30,  3.64it/s]
 63%|██████▎   | 233101/371472 [7:31:12<10:11:53,  3.77it/s]
 63%|██████▎   | 233102/371472 [7:31:12<9:55:47,  3.87it/s] 
 63%|██████▎   | 233103/371472 [7:31:12<10:23:55,  3.70it/s]
 63%|██████▎   | 233104/371472 [7:31:13<10:25:23,  3.69it/s]
 63%|██████▎   | 233105/371472 [7:31:13<10:30:30,  3.66it/s]
 63%|██████▎   | 233106/371472 [7:31:13<11:04:24,  3.47it/s]
 63%|██████▎   | 233107/371472 [7:31:13<10:47:40,  3.56it/s]
 63%|██████▎   | 233108/371472 [7:31:14<10:25:15,  3.69it/s]
 63%|██████▎   | 233109/371472 [7:31:14<10:19:28,  3.72it/s]
 63%|██████▎   | 233110/371472 [7:31:14<10:20:40,  3.72it/s]
 63%|██████▎   | 233111/371472 [7:31:14<10:08:46,  3.79it/s]
 63%|██████▎   | 233112/371472 [7:31:15<10:20:23,  3.72it/s]
 63%|██████▎   | 233113/371472 [7:31:15<10:30:28,  3.66it/s]
 63%|██████▎   | 233114/371472 [7:31:15<10:26:38,  3.68it/s]
 63%|██████▎   | 233115/371472 [7:31:16<10:21:30,  3.71it/s]
 63%|██████▎   | 233116/371472 [7:31:16<10:28:10,  3.67it/s]
 63%|██████▎   | 233117/371472 [7:31:16<10:08:27,  3.79it/s]
 63%|██████▎   | 233118/371472 [7:31:16<10:08:31,  3.79it/s]
 63%|██████▎   | 233119/371472 [7:31:17<10:10:54,  3.77it/s]
 63%|██████▎   | 233120/371472 [7:31:17<10:11:18,  3.77it/s]
                                                            
{'loss': 3.0585, 'learning_rate': 4.3537891357279835e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233120/371472 [7:31:17<10:11:18,  3.77it/s]
 63%|██████▎   | 233121/371472 [7:31:17<10:32:00,  3.65it/s]
 63%|██████▎   | 233122/371472 [7:31:17<10:36:06,  3.62it/s]
 63%|██████▎   | 233123/371472 [7:31:18<10:25:04,  3.69it/s]
 63%|██████▎   | 233124/371472 [7:31:18<10:36:19,  3.62it/s]
 63%|██████▎   | 233125/371472 [7:31:18<10:12:47,  3.76it/s]
 63%|██████▎   | 233126/371472 [7:31:18<9:52:28,  3.89it/s] 
 63%|██████▎   | 233127/371472 [7:31:19<10:17:59,  3.73it/s]
 63%|██████▎   | 233128/371472 [7:31:19<9:57:39,  3.86it/s] 
 63%|██████▎   | 233129/371472 [7:31:19<10:18:23,  3.73it/s]
 63%|██████▎   | 233130/371472 [7:31:20<10:14:10,  3.75it/s]
 63%|██████▎   | 233131/371472 [7:31:20<11:45:24,  3.27it/s]
 63%|██████▎   | 233132/371472 [7:31:20<12:46:47,  3.01it/s]
 63%|██████▎   | 233133/371472 [7:31:21<12:03:50,  3.19it/s]
 63%|██████▎   | 233134/371472 [7:31:21<11:31:55,  3.33it/s]
 63%|██████▎   | 233135/371472 [7:31:21<11:46:44,  3.26it/s]
 63%|██████▎   | 233136/371472 [7:31:21<11:16:58,  3.41it/s]
 63%|██████▎   | 233137/371472 [7:31:22<10:59:24,  3.50it/s]
 63%|██████▎   | 233138/371472 [7:31:22<10:39:08,  3.61it/s]
 63%|██████▎   | 233139/371472 [7:31:22<11:23:40,  3.37it/s]
 63%|██████▎   | 233140/371472 [7:31:23<10:54:09,  3.52it/s]
                                                            
{'loss': 2.7695, 'learning_rate': 4.353304315973194e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233140/371472 [7:31:23<10:54:09,  3.52it/s]
 63%|██████▎   | 233141/371472 [7:31:23<11:06:23,  3.46it/s]
 63%|██████▎   | 233142/371472 [7:31:23<10:45:39,  3.57it/s]
 63%|██████▎   | 233143/371472 [7:31:23<10:54:39,  3.52it/s]
 63%|██████▎   | 233144/371472 [7:31:24<11:49:38,  3.25it/s]
 63%|██████▎   | 233145/371472 [7:31:24<11:22:26,  3.38it/s]
 63%|██████▎   | 233146/371472 [7:31:24<11:28:51,  3.35it/s]
 63%|██████▎   | 233147/371472 [7:31:25<10:47:26,  3.56it/s]
 63%|██████▎   | 233148/371472 [7:31:25<11:25:28,  3.36it/s]
 63%|██████▎   | 233149/371472 [7:31:25<11:54:41,  3.23it/s]
 63%|██████▎   | 233150/371472 [7:31:26<11:20:13,  3.39it/s]
 63%|██████▎   | 233151/371472 [7:31:26<11:26:12,  3.36it/s]
 63%|██████▎   | 233152/371472 [7:31:26<11:14:49,  3.42it/s]
 63%|██████▎   | 233153/371472 [7:31:26<11:11:14,  3.43it/s]
 63%|██████▎   | 233154/371472 [7:31:27<10:53:46,  3.53it/s]
 63%|██████▎   | 233155/371472 [7:31:27<10:51:39,  3.54it/s]
 63%|██████▎   | 233156/371472 [7:31:27<10:33:13,  3.64it/s]
 63%|██████▎   | 233157/371472 [7:31:28<10:52:59,  3.53it/s]
 63%|██████▎   | 233158/371472 [7:31:28<10:58:48,  3.50it/s]
 63%|██████▎   | 233159/371472 [7:31:28<10:41:42,  3.59it/s]
 63%|██████▎   | 233160/371472 [7:31:28<10:57:35,  3.51it/s]
                                                            
{'loss': 2.8594, 'learning_rate': 4.352819496218406e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233160/371472 [7:31:28<10:57:35,  3.51it/s]
 63%|██████▎   | 233161/371472 [7:31:29<10:33:13,  3.64it/s]
 63%|██████▎   | 233162/371472 [7:31:29<11:16:58,  3.41it/s]
 63%|██████▎   | 233163/371472 [7:31:29<11:07:07,  3.46it/s]
 63%|██████▎   | 233164/371472 [7:31:30<10:59:45,  3.49it/s]
 63%|██████▎   | 233165/371472 [7:31:30<10:31:39,  3.65it/s]
 63%|██████▎   | 233166/371472 [7:31:30<10:34:55,  3.63it/s]
 63%|██████▎   | 233167/371472 [7:31:30<11:07:25,  3.45it/s]
 63%|██████▎   | 233168/371472 [7:31:31<10:59:54,  3.49it/s]
 63%|██████▎   | 233169/371472 [7:31:31<10:29:41,  3.66it/s]
 63%|██████▎   | 233170/371472 [7:31:31<11:24:49,  3.37it/s]
 63%|██████▎   | 233171/371472 [7:31:32<11:14:22,  3.42it/s]
 63%|██████▎   | 233172/371472 [7:31:32<10:44:08,  3.58it/s]
 63%|██████▎   | 233173/371472 [7:31:32<10:19:28,  3.72it/s]
 63%|██████▎   | 233174/371472 [7:31:32<11:39:18,  3.30it/s]
 63%|██████▎   | 233175/371472 [7:31:33<11:41:51,  3.28it/s]
 63%|██████▎   | 233176/371472 [7:31:33<11:51:42,  3.24it/s]
 63%|██████▎   | 233177/371472 [7:31:33<11:13:13,  3.42it/s]
 63%|██████▎   | 233178/371472 [7:31:34<11:22:45,  3.38it/s]
 63%|██████▎   | 233179/371472 [7:31:34<10:40:10,  3.60it/s]
 63%|██████▎   | 233180/371472 [7:31:34<10:36:35,  3.62it/s]
                                                            
{'loss': 2.8182, 'learning_rate': 4.352334676463617e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233180/371472 [7:31:34<10:36:35,  3.62it/s]
 63%|██████▎   | 233181/371472 [7:31:34<11:01:42,  3.48it/s]
 63%|██████▎   | 233182/371472 [7:31:35<10:49:48,  3.55it/s]
 63%|██████▎   | 233183/371472 [7:31:35<10:16:18,  3.74it/s]
 63%|██████▎   | 233184/371472 [7:31:35<10:03:16,  3.82it/s]
 63%|██████▎   | 233185/371472 [7:31:35<10:30:30,  3.66it/s]
 63%|██████▎   | 233186/371472 [7:31:36<10:08:10,  3.79it/s]
 63%|██████▎   | 233187/371472 [7:31:36<11:07:21,  3.45it/s]
 63%|██████▎   | 233188/371472 [7:31:36<11:27:37,  3.35it/s]
 63%|██████▎   | 233189/371472 [7:31:37<11:03:12,  3.48it/s]
 63%|██��███▎   | 233190/371472 [7:31:37<10:53:25,  3.53it/s]
 63%|██████▎   | 233191/371472 [7:31:37<10:38:21,  3.61it/s]
 63%|██████▎   | 233192/371472 [7:31:37<10:36:28,  3.62it/s]
 63%|██████▎   | 233193/371472 [7:31:38<12:04:47,  3.18it/s]
 63%|██████▎   | 233194/371472 [7:31:38<11:24:29,  3.37it/s]
 63%|██████▎   | 233195/371472 [7:31:38<11:01:13,  3.49it/s]
 63%|██████▎   | 233196/371472 [7:31:39<10:28:30,  3.67it/s]
 63%|██████▎   | 233197/371472 [7:31:39<10:39:53,  3.60it/s]
 63%|██████▎   | 233198/371472 [7:31:39<10:40:28,  3.60it/s]
 63%|██████▎   | 233199/371472 [7:31:39<11:04:36,  3.47it/s]
 63%|██████▎   | 233200/371472 [7:31:40<10:37:48,  3.61it/s]
                                                            
{'loss': 2.8611, 'learning_rate': 4.351849856708828e-07, 'epoch': 10.04}
+
 63%|██████▎   | 233200/371472 [7:31:40<10:37:48,  3.61it/s]
 63%|██████▎   | 233201/371472 [7:31:40<10:41:52,  3.59it/s]
 63%|██████▎   | 233202/371472 [7:31:40<10:37:43,  3.61it/s]
 63%|██████▎   | 233203/371472 [7:31:41<11:24:29,  3.37it/s]
 63%|██████▎   | 233204/371472 [7:31:41<11:06:42,  3.46it/s]
 63%|██████▎   | 233205/371472 [7:31:41<10:51:20,  3.54it/s]
 63%|██████▎   | 233206/371472 [7:31:41<11:21:28,  3.38it/s]
 63%|██████▎   | 233207/371472 [7:31:42<10:58:19,  3.50it/s]
 63%|██████▎   | 233208/371472 [7:31:42<10:46:55,  3.56it/s]
 63%|██████▎   | 233209/371472 [7:31:42<10:20:33,  3.71it/s]
 63%|██████▎   | 233210/371472 [7:31:43<10:30:57,  3.65it/s]
 63%|██████▎   | 233211/371472 [7:31:43<10:52:25,  3.53it/s]
 63%|██████▎   | 233212/371472 [7:31:43<10:50:24,  3.54it/s]
 63%|██████▎   | 233213/371472 [7:31:43<11:13:18,  3.42it/s]
 63%|██████▎   | 233214/371472 [7:31:44<11:02:24,  3.48it/s]
 63%|██████▎   | 233215/371472 [7:31:44<10:41:05,  3.59it/s]
 63%|██████▎   | 233216/371472 [7:31:44<10:32:29,  3.64it/s]
 63%|██████▎   | 233217/371472 [7:31:45<10:32:44,  3.64it/s]
 63%|██████▎   | 233218/371472 [7:31:45<10:26:18,  3.68it/s]
 63%|██████▎   | 233219/371472 [7:31:45<11:08:13,  3.45it/s]
 63%|██████▎   | 233220/371472 [7:31:45<10:41:43,  3.59it/s]
                                                            
{'loss': 2.9178, 'learning_rate': 4.3513650369540387e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233220/371472 [7:31:45<10:41:43,  3.59it/s]
 63%|██████▎   | 233221/371472 [7:31:46<10:25:42,  3.68it/s]
 63%|██████▎   | 233222/371472 [7:31:46<10:19:21,  3.72it/s]
 63%|██████▎   | 233223/371472 [7:31:46<11:03:02,  3.48it/s]
 63%|██████▎   | 233224/371472 [7:31:46<10:28:45,  3.66it/s]
 63%|██████▎   | 233225/371472 [7:31:47<10:11:00,  3.77it/s]
 63%|██████▎   | 233226/371472 [7:31:47<9:52:35,  3.89it/s] 
 63%|██████▎   | 233227/371472 [7:31:47<9:28:05,  4.06it/s]
 63%|██████▎   | 233228/371472 [7:31:47<9:31:39,  4.03it/s]
 63%|██████▎   | 233229/371472 [7:31:48<9:26:28,  4.07it/s]
 63%|██████▎   | 233230/371472 [7:31:48<9:37:07,  3.99it/s]
 63%|██████▎   | 233231/371472 [7:31:48<10:08:50,  3.78it/s]
 63%|██████▎   | 233232/371472 [7:31:48<10:12:01,  3.76it/s]
 63%|██████▎   | 233233/371472 [7:31:49<10:08:18,  3.79it/s]
 63%|██████▎   | 233234/371472 [7:31:49<10:50:00,  3.54it/s]
 63%|██████▎   | 233235/371472 [7:31:49<11:29:55,  3.34it/s]
 63%|██████▎   | 233236/371472 [7:31:50<10:51:36,  3.54it/s]
 63%|██████▎   | 233237/371472 [7:31:50<12:00:27,  3.20it/s]
 63%|██████▎   | 233238/371472 [7:31:50<11:22:57,  3.37it/s]
 63%|██████▎   | 233239/371472 [7:31:51<11:42:39,  3.28it/s]
 63%|██████▎   | 233240/371472 [7:31:51<12:00:33,  3.20it/s]
                                                            
{'loss': 3.0529, 'learning_rate': 4.3508802171992505e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233240/371472 [7:31:51<12:00:33,  3.20it/s]
 63%|██████▎   | 233241/371472 [7:31:51<11:25:45,  3.36it/s]
 63%|██████▎   | 233242/371472 [7:31:51<10:54:51,  3.52it/s]
 63%|██████▎   | 233243/371472 [7:31:52<10:50:15,  3.54it/s]
 63%|██████▎   | 233244/371472 [7:31:52<10:22:37,  3.70it/s]
 63%|██████▎   | 233245/371472 [7:31:52<10:33:07,  3.64it/s]
 63%|██████▎   | 233246/371472 [7:31:53<11:05:12,  3.46it/s]
 63%|██████▎   | 233247/371472 [7:31:53<10:39:15,  3.60it/s]
 63%|██████▎   | 233248/371472 [7:31:53<10:12:39,  3.76it/s]
 63%|██████▎   | 233249/371472 [7:31:53<9:53:21,  3.88it/s] 
 63%|██████▎   | 233250/371472 [7:31:54<10:17:08,  3.73it/s]
 63%|██████▎   | 233251/371472 [7:31:54<10:45:50,  3.57it/s]
 63%|██████▎   | 233252/371472 [7:31:54<10:51:32,  3.54it/s]
 63%|██████▎   | 233253/371472 [7:31:55<10:55:59,  3.51it/s]
 63%|██████▎   | 233254/371472 [7:31:55<11:14:53,  3.41it/s]
 63%|██████▎   | 233255/371472 [7:31:55<10:57:02,  3.51it/s]
 63%|██████▎   | 233256/371472 [7:31:55<10:31:55,  3.65it/s]
 63%|██████▎   | 233257/371472 [7:31:56<10:24:40,  3.69it/s]
 63%|██████▎   | 233258/371472 [7:31:56<10:27:47,  3.67it/s]
 63%|██████▎   | 233259/371472 [7:31:56<10:17:00,  3.73it/s]
 63%|██████▎   | 233260/371472 [7:31:56<10:58:40,  3.50it/s]
                                                            
{'loss': 2.9237, 'learning_rate': 4.3503953974444607e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233260/371472 [7:31:56<10:58:40,  3.50it/s]
 63%|██████▎   | 233261/371472 [7:31:57<10:56:46,  3.51it/s]
 63%|██████▎   | 233262/371472 [7:31:57<11:08:39,  3.44it/s]
 63%|██████▎   | 233263/371472 [7:31:57<10:48:26,  3.55it/s]
 63%|██████▎   | 233264/371472 [7:31:58<10:29:41,  3.66it/s]
 63%|██████▎   | 233265/371472 [7:31:58<10:45:04,  3.57it/s]
 63%|██████▎   | 233266/371472 [7:31:58<10:44:36,  3.57it/s]
 63%|██████▎   | 233267/371472 [7:31:58<10:38:46,  3.61it/s]
 63%|██████▎   | 233268/371472 [7:31:59<10:34:20,  3.63it/s]
 63%|██████▎   | 233269/371472 [7:31:59<10:27:54,  3.67it/s]
 63%|██████▎   | 233270/371472 [7:31:59<11:13:40,  3.42it/s]
 63%|██████▎   | 233271/371472 [7:32:00<10:59:32,  3.49it/s]
 63%|██████▎   | 233272/371472 [7:32:00<11:13:37,  3.42it/s]
 63%|██████▎   | 233273/371472 [7:32:00<12:09:42,  3.16it/s]
 63%|██████▎   | 233274/371472 [7:32:00<11:23:19,  3.37it/s]
 63%|██████▎   | 233275/371472 [7:32:01<10:51:57,  3.53it/s]
 63%|██████▎   | 233276/371472 [7:32:01<10:29:10,  3.66it/s]
 63%|██████▎   | 233277/371472 [7:32:01<10:07:10,  3.79it/s]
 63%|██████▎   | 233278/371472 [7:32:02<10:30:54,  3.65it/s]
 63%|██████▎   | 233279/371472 [7:32:02<10:13:10,  3.76it/s]
 63%|██████▎   | 233280/371472 [7:32:02<9:57:53,  3.85it/s] 
                                                           
{'loss': 2.7762, 'learning_rate': 4.3499105776896724e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233280/371472 [7:32:02<9:57:53,  3.85it/s]
 63%|██████▎   | 233281/371472 [7:32:02<10:44:11,  3.58it/s]
 63%|██████▎   | 233282/371472 [7:32:03<11:13:36,  3.42it/s]
 63%|██████▎   | 233283/371472 [7:32:03<10:59:08,  3.49it/s]
 63%|██████▎   | 233284/371472 [7:32:03<10:33:16,  3.64it/s]
 63%|██████▎   | 233285/371472 [7:32:03<10:52:58,  3.53it/s]
 63%|██████▎   | 233286/371472 [7:32:04<10:57:23,  3.50it/s]
 63%|██████▎   | 233287/371472 [7:32:04<11:04:47,  3.46it/s]
 63%|██████▎   | 233288/371472 [7:32:04<10:42:02,  3.59it/s]
 63%|██████▎   | 233289/371472 [7:32:05<10:52:38,  3.53it/s]
 63%|██████▎   | 233290/371472 [7:32:05<10:24:15,  3.69it/s]
 63%|██████▎   | 233291/371472 [7:32:05<12:54:44,  2.97it/s]
 63%|██████▎   | 233292/371472 [7:32:06<12:09:33,  3.16it/s]
 63%|██████▎   | 233293/371472 [7:32:06<11:42:00,  3.28it/s]
 63%|██████▎   | 233294/371472 [7:32:06<11:24:36,  3.36it/s]
 63%|██████▎   | 233295/371472 [7:32:06<11:13:27,  3.42it/s]
 63%|██████▎   | 233296/371472 [7:32:07<10:53:55,  3.52it/s]
 63%|██████▎   | 233297/371472 [7:32:07<11:07:45,  3.45it/s]
 63%|██████▎   | 233298/371472 [7:32:07<11:31:52,  3.33it/s]
 63%|██████▎   | 233299/371472 [7:32:08<12:37:14,  3.04it/s]
 63%|██████▎   | 233300/371472 [7:32:08<12:22:49,  3.10it/s]
                                                            
{'loss': 2.8364, 'learning_rate': 4.349425757934883e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233300/371472 [7:32:08<12:22:49,  3.10it/s]
 63%|██████▎   | 233301/371472 [7:32:09<13:50:45,  2.77it/s]
 63%|██████▎   | 233302/371472 [7:32:09<12:31:07,  3.07it/s]
 63%|██████▎   | 233303/371472 [7:32:09<11:42:32,  3.28it/s]
 63%|██████▎   | 233304/371472 [7:32:09<11:10:18,  3.44it/s]
 63%|██████▎   | 233305/371472 [7:32:10<10:59:14,  3.49it/s]
 63%|██████▎   | 233306/371472 [7:32:10<11:05:57,  3.46it/s]
 63%|██████▎   | 233307/371472 [7:32:10<10:43:43,  3.58it/s]
 63%|██████▎   | 233308/371472 [7:32:10<10:31:41,  3.65it/s]
 63%|██████▎   | 233309/371472 [7:32:11<10:38:44,  3.61it/s]
 63%|██████▎   | 233310/371472 [7:32:11<10:33:56,  3.63it/s]
 63%|██████▎   | 233311/371472 [7:32:11<10:24:08,  3.69it/s]
 63%|██████▎   | 233312/371472 [7:32:11<10:29:42,  3.66it/s]
 63%|██████▎   | 233313/371472 [7:32:12<10:29:41,  3.66it/s]
 63%|██████▎   | 233314/371472 [7:32:12<10:59:52,  3.49it/s]
 63%|██████▎   | 233315/371472 [7:32:12<10:27:17,  3.67it/s]
 63%|██████▎   | 233316/371472 [7:32:13<10:30:00,  3.65it/s]
 63%|██████▎   | 233317/371472 [7:32:13<10:16:22,  3.74it/s]
 63%|██████▎   | 233318/371472 [7:32:13<10:33:10,  3.64it/s]
 63%|██████▎   | 233319/371472 [7:32:13<10:10:16,  3.77it/s]
 63%|██████▎   | 233320/371472 [7:32:14<12:03:52,  3.18it/s]
                                                            
{'loss': 2.8621, 'learning_rate': 4.3489409381800944e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233320/371472 [7:32:14<12:03:52,  3.18it/s]
 63%|██████▎   | 233321/371472 [7:32:14<11:18:52,  3.39it/s]
 63%|██████▎   | 233322/371472 [7:32:14<11:10:50,  3.43it/s]
 63%|██████▎   | 233323/371472 [7:32:15<10:52:17,  3.53it/s]
 63%|██████▎   | 233324/371472 [7:32:15<10:28:34,  3.66it/s]
 63%|██████▎   | 233325/371472 [7:32:15<10:09:10,  3.78it/s]
 63%|██████▎   | 233326/371472 [7:32:15<10:03:14,  3.82it/s]
 63%|██████▎   | 233327/371472 [7:32:16<10:21:23,  3.71it/s]
 63%|██████▎   | 233328/371472 [7:32:16<10:48:42,  3.55it/s]
 63%|██████▎   | 233329/371472 [7:32:16<10:31:22,  3.65it/s]
 63%|██████▎   | 233330/371472 [7:32:16<10:23:11,  3.69it/s]
 63%|██████▎   | 233331/371472 [7:32:17<10:56:17,  3.51it/s]
 63%|██████▎   | 233332/371472 [7:32:17<10:44:45,  3.57it/s]
 63%|██████▎   | 233333/371472 [7:32:17<11:17:32,  3.40it/s]
 63%|██████▎   | 233334/371472 [7:32:18<11:13:49,  3.42it/s]
 63%|██████▎   | 233335/371472 [7:32:18<10:50:01,  3.54it/s]
 63%|██████▎   | 233336/371472 [7:32:18<10:48:49,  3.55it/s]
 63%|██████▎   | 233337/371472 [7:32:18<10:25:28,  3.68it/s]
 63%|██████▎   | 233338/371472 [7:32:19<10:35:55,  3.62it/s]
 63%|██████▎   | 233339/371472 [7:32:19<10:31:29,  3.65it/s]
 63%|██████▎   | 233340/371472 [7:32:19<10:30:03,  3.65it/s]
                                                            
{'loss': 2.9134, 'learning_rate': 4.348456118425305e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233340/371472 [7:32:19<10:30:03,  3.65it/s]
 63%|██████▎   | 233341/371472 [7:32:20<10:27:21,  3.67it/s]
 63%|██████▎   | 233342/371472 [7:32:20<10:18:16,  3.72it/s]
 63%|██████▎   | 233343/371472 [7:32:20<10:30:43,  3.65it/s]
 63%|██████▎   | 233344/371472 [7:32:20<10:20:03,  3.71it/s]
 63%|██████▎   | 233345/371472 [7:32:21<10:50:06,  3.54it/s]
 63%|██████▎   | 233346/371472 [7:32:21<10:32:33,  3.64it/s]
 63%|██████▎   | 233347/371472 [7:32:21<10:20:18,  3.71it/s]
 63%|██████▎   | 233348/371472 [7:32:21<10:50:12,  3.54it/s]
 63%|██████▎   | 233349/371472 [7:32:22<11:06:46,  3.45it/s]
 63%|██████▎   | 233350/371472 [7:32:22<10:47:22,  3.56it/s]
 63%|██████▎   | 233351/371472 [7:32:22<10:25:39,  3.68it/s]
 63%|██████▎   | 233352/371472 [7:32:23<10:21:40,  3.70it/s]
 63%|██████▎   | 233353/371472 [7:32:23<9:56:06,  3.86it/s] 
 63%|██████▎   | 233354/371472 [7:32:23<9:41:49,  3.96it/s]
 63%|██████▎   | 233355/371472 [7:32:23<9:46:20,  3.93it/s]
 63%|██████▎   | 233356/371472 [7:32:24<9:39:44,  3.97it/s]
 63%|██████▎   | 233357/371472 [7:32:24<9:46:41,  3.92it/s]
 63%|██████▎   | 233358/371472 [7:32:24<10:07:10,  3.79it/s]
 63%|██████▎   | 233359/371472 [7:32:24<9:52:00,  3.89it/s] 
 63%|██████▎   | 233360/371472 [7:32:25<10:00:57,  3.83it/s]
                                                            
{'loss': 3.0314, 'learning_rate': 4.347971298670517e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233360/371472 [7:32:25<10:00:57,  3.83it/s]
 63%|██████▎   | 233361/371472 [7:32:25<9:51:40,  3.89it/s] 
 63%|██████▎   | 233362/371472 [7:32:25<10:22:05,  3.70it/s]
 63%|██████▎   | 233363/371472 [7:32:25<10:14:57,  3.74it/s]
 63%|██████▎   | 233364/371472 [7:32:26<10:19:37,  3.71it/s]
 63%|██████▎   | 233365/371472 [7:32:26<10:40:58,  3.59it/s]
 63%|██████▎   | 233366/371472 [7:32:26<11:17:16,  3.40it/s]
 63%|██████▎   | 233367/371472 [7:32:27<11:13:25,  3.42it/s]
 63%|██████▎   | 233368/371472 [7:32:27<10:48:10,  3.55it/s]
 63%|██████▎   | 233369/371472 [7:32:27<10:27:59,  3.67it/s]
 63%|██████▎   | 233370/371472 [7:32:27<10:30:47,  3.65it/s]
 63%|██████▎   | 233371/371472 [7:32:28<10:53:40,  3.52it/s]
 63%|██████▎   | 233372/371472 [7:32:28<11:04:59,  3.46it/s]
 63%|██████▎   | 233373/371472 [7:32:28<10:37:46,  3.61it/s]
 63%|██████▎   | 233374/371472 [7:32:28<10:22:35,  3.70it/s]
 63%|██████▎   | 233375/371472 [7:32:29<10:08:34,  3.78it/s]
 63%|██████▎   | 233376/371472 [7:32:29<10:20:42,  3.71it/s]
 63%|██████▎   | 233377/371472 [7:32:29<11:41:06,  3.28it/s]
 63%|██████▎   | 233378/371472 [7:32:30<11:18:18,  3.39it/s]
 63%|██████▎   | 233379/371472 [7:32:30<10:50:13,  3.54it/s]
 63%|██████▎   | 233380/371472 [7:32:30<10:17:34,  3.73it/s]
                                                            
{'loss': 2.8845, 'learning_rate': 4.347486478915727e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233380/371472 [7:32:30<10:17:34,  3.73it/s]
 63%|██████▎   | 233381/371472 [7:32:30<10:19:50,  3.71it/s]
 63%|██████▎   | 233382/371472 [7:32:31<10:09:01,  3.78it/s]
 63%|██████▎   | 233383/371472 [7:32:31<10:31:59,  3.64it/s]
 63%|██████▎   | 233384/371472 [7:32:31<10:18:12,  3.72it/s]
 63%|██████▎   | 233385/371472 [7:32:32<10:06:46,  3.79it/s]
 63%|██████▎   | 233386/371472 [7:32:32<9:57:58,  3.85it/s] 
 63%|██████▎   | 233387/371472 [7:32:32<9:40:28,  3.96it/s]
 63%|██████▎   | 233388/371472 [7:32:32<9:48:06,  3.91it/s]
 63%|██████▎   | 233389/371472 [7:32:33<9:56:04,  3.86it/s]
 63%|██████▎   | 233390/371472 [7:32:33<10:05:41,  3.80it/s]
 63%|██████▎   | 233391/371472 [7:32:33<10:08:16,  3.78it/s]
 63%|██████▎   | 233392/371472 [7:32:33<9:46:39,  3.92it/s] 
 63%|██████▎   | 233393/371472 [7:32:34<10:14:56,  3.74it/s]
 63%|██████▎   | 233394/371472 [7:32:34<11:32:05,  3.33it/s]
 63%|██████▎   | 233395/371472 [7:32:34<11:12:48,  3.42it/s]
 63%|██████▎   | 233396/371472 [7:32:35<12:01:04,  3.19it/s]
 63%|██████▎   | 233397/371472 [7:32:35<11:48:57,  3.25it/s]
 63%|██████▎   | 233398/371472 [7:32:35<11:30:05,  3.33it/s]
 63%|██████▎   | 233399/371472 [7:32:35<11:11:20,  3.43it/s]
 63%|██████▎   | 233400/371472 [7:32:36<11:43:43,  3.27it/s]
                                                            
{'loss': 2.7569, 'learning_rate': 4.347001659160939e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233400/371472 [7:32:36<11:43:43,  3.27it/s]
 63%|██████▎   | 233401/371472 [7:32:36<11:27:17,  3.35it/s]
 63%|██████▎   | 233402/371472 [7:32:36<10:52:46,  3.53it/s]
 63%|██████▎   | 233403/371472 [7:32:37<10:48:39,  3.55it/s]
 63%|██████▎   | 233404/371472 [7:32:37<10:58:14,  3.50it/s]
 63%|██████▎   | 233405/371472 [7:32:37<11:26:18,  3.35it/s]
 63%|██████▎   | 233406/371472 [7:32:37<10:59:24,  3.49it/s]
 63%|██████▎   | 233407/371472 [7:32:38<10:19:13,  3.72it/s]
 63%|██████▎   | 233408/371472 [7:32:38<11:19:10,  3.39it/s]
 63%|██████▎   | 233409/371472 [7:32:38<12:08:27,  3.16it/s]
 63%|██████▎   | 233410/371472 [7:32:39<11:34:02,  3.32it/s]
 63%|██████▎   | 233411/371472 [7:32:39<10:54:50,  3.51it/s]
 63%|██████▎   | 233412/371472 [7:32:39<10:41:12,  3.59it/s]
 63%|██████▎   | 233413/371472 [7:32:40<11:21:40,  3.38it/s]
 63%|██████▎   | 233414/371472 [7:32:40<11:56:57,  3.21it/s]
 63%|██████▎   | 233415/371472 [7:32:40<11:26:05,  3.35it/s]
 63%|██████▎   | 233416/371472 [7:32:40<10:49:30,  3.54it/s]
 63%|██████▎   | 233417/371472 [7:32:41<11:17:42,  3.40it/s]
 63%|██████▎   | 233418/371472 [7:32:41<11:24:50,  3.36it/s]
 63%|██████▎   | 233419/371472 [7:32:41<10:46:12,  3.56it/s]
 63%|██████▎   | 233420/371472 [7:32:42<10:25:05,  3.68it/s]
                                                            
{'loss': 2.9819, 'learning_rate': 4.3465168394061496e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233420/371472 [7:32:42<10:25:05,  3.68it/s]
 63%|██████▎   | 233421/371472 [7:32:42<10:12:23,  3.76it/s]
 63%|██████▎   | 233422/371472 [7:32:42<10:03:30,  3.81it/s]
 63%|██████▎   | 233423/371472 [7:32:42<10:06:44,  3.79it/s]
 63%|██████▎   | 233424/371472 [7:32:43<10:25:31,  3.68it/s]
 63%|██████▎   | 233425/371472 [7:32:43<11:05:05,  3.46it/s]
 63%|██████▎   | 233426/371472 [7:32:43<10:42:09,  3.58it/s]
 63%|██████▎   | 233427/371472 [7:32:43<11:08:03,  3.44it/s]
 63%|██████▎   | 233428/371472 [7:32:44<10:37:15,  3.61it/s]
 63%|██████▎   | 233429/371472 [7:32:44<10:39:44,  3.60it/s]
 63%|██████▎   | 233430/371472 [7:32:44<10:19:25,  3.71it/s]
 63%|██████▎   | 233431/371472 [7:32:44<9:54:00,  3.87it/s] 
 63%|██████▎   | 233432/371472 [7:32:45<10:48:06,  3.55it/s]
 63%|██████▎   | 233433/371472 [7:32:45<10:34:57,  3.62it/s]
 63%|██████▎   | 233434/371472 [7:32:45<10:21:29,  3.70it/s]
 63%|██████▎   | 233435/371472 [7:32:46<10:59:26,  3.49it/s]
 63%|██████▎   | 233436/371472 [7:32:46<10:57:27,  3.50it/s]
 63%|██████▎   | 233437/371472 [7:32:46<11:03:25,  3.47it/s]
 63%|██████▎   | 233438/371472 [7:32:47<11:27:15,  3.35it/s]
 63%|██████▎   | 233439/371472 [7:32:47<11:21:26,  3.38it/s]
 63%|██████▎   | 233440/371472 [7:32:47<10:42:53,  3.58it/s]
                                                            
{'loss': 2.8921, 'learning_rate': 4.346032019651361e-07, 'epoch': 10.05}
+
 63%|██████▎   | 233440/371472 [7:32:47<10:42:53,  3.58it/s]
 63%|██████▎   | 233441/371472 [7:32:47<10:46:15,  3.56it/s]
 63%|██████▎   | 233442/371472 [7:32:48<10:51:40,  3.53it/s]
 63%|██████▎   | 233443/371472 [7:32:48<10:41:39,  3.59it/s]
 63%|██████▎   | 233444/371472 [7:32:48<10:43:35,  3.57it/s]
 63%|██████▎   | 233445/371472 [7:32:48<10:30:53,  3.65it/s]
 63%|██████▎   | 233446/371472 [7:32:49<10:21:36,  3.70it/s]
 63%|██████▎   | 233447/371472 [7:32:49<11:37:56,  3.30it/s]
 63%|██████▎   | 233448/371472 [7:32:49<11:17:13,  3.40it/s]
 63%|██████▎   | 233449/371472 [7:32:50<11:05:33,  3.46it/s]
 63%|██████▎   | 233450/371472 [7:32:50<10:48:50,  3.55it/s]
 63%|██████▎   | 233451/371472 [7:32:50<10:35:10,  3.62it/s]
 63%|██████▎   | 233452/371472 [7:32:50<10:33:27,  3.63it/s]
 63%|██████▎   | 233453/371472 [7:32:51<10:49:30,  3.54it/s]
 63%|██████▎   | 233454/371472 [7:32:51<10:36:09,  3.62it/s]
 63%|██████▎   | 233455/371472 [7:32:51<10:17:14,  3.73it/s]
 63%|██████▎   | 233456/371472 [7:32:52<10:35:46,  3.62it/s]
 63%|██████▎   | 233457/371472 [7:32:52<10:40:47,  3.59it/s]
 63%|██████▎   | 233458/371472 [7:32:52<10:25:42,  3.68it/s]
 63%|██████▎   | 233459/371472 [7:32:52<10:55:43,  3.51it/s]
 63%|██████▎   | 233460/371472 [7:32:53<10:42:14,  3.58it/s]
                                                            
{'loss': 2.8411, 'learning_rate': 4.3455471998965715e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233460/371472 [7:32:53<10:42:14,  3.58it/s]
 63%|██████▎   | 233461/371472 [7:32:53<10:44:45,  3.57it/s]
 63%|██████▎   | 233462/371472 [7:32:53<11:11:52,  3.42it/s]
 63%|██████▎   | 233463/371472 [7:32:54<10:57:17,  3.50it/s]
 63%|██████▎   | 233464/371472 [7:32:54<10:43:09,  3.58it/s]
 63%|██████▎   | 233465/371472 [7:32:54<10:23:24,  3.69it/s]
 63%|██████▎   | 233466/371472 [7:32:54<10:15:20,  3.74it/s]
 63%|██████▎   | 233467/371472 [7:32:55<10:32:21,  3.64it/s]
 63%|██████▎   | 233468/371472 [7:32:55<10:15:48,  3.74it/s]
 63%|██████▎   | 233469/371472 [7:32:55<10:50:10,  3.54it/s]
 63%|██████▎   | 233470/371472 [7:32:55<10:44:10,  3.57it/s]
 63%|██████▎   | 233471/371472 [7:32:56<10:34:11,  3.63it/s]
 63%|██████▎   | 233472/371472 [7:32:56<10:27:14,  3.67it/s]
 63%|██████▎   | 233473/371472 [7:32:56<10:04:08,  3.81it/s]
 63%|██████▎   | 233474/371472 [7:32:57<10:07:15,  3.79it/s]
 63%|██████▎   | 233475/371472 [7:32:57<11:13:24,  3.42it/s]
 63%|██████▎   | 233476/371472 [7:32:57<10:53:44,  3.52it/s]
 63%|██████▎   | 233477/371472 [7:32:57<10:28:37,  3.66it/s]
 63%|██████▎   | 233478/371472 [7:32:58<10:18:14,  3.72it/s]
 63%|██████▎   | 233479/371472 [7:32:58<9:58:26,  3.84it/s] 
 63%|██████▎   | 233480/371472 [7:32:58<10:45:54,  3.56it/s]
                                                            
{'loss': 3.0505, 'learning_rate': 4.345062380141782e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233480/371472 [7:32:58<10:45:54,  3.56it/s]
 63%|██████▎   | 233481/371472 [7:32:58<10:25:21,  3.68it/s]
 63%|██████▎   | 233482/371472 [7:32:59<10:15:30,  3.74it/s]
 63%|██████▎   | 233483/371472 [7:32:59<10:42:27,  3.58it/s]
 63%|██████▎   | 233484/371472 [7:32:59<10:24:21,  3.68it/s]
 63%|██████▎   | 233485/371472 [7:33:00<10:09:09,  3.78it/s]
 63%|██████▎   | 233486/371472 [7:33:00<9:58:00,  3.85it/s] 
 63%|██████▎   | 233487/371472 [7:33:00<9:57:31,  3.85it/s]
 63%|██████▎   | 233488/371472 [7:33:00<10:27:34,  3.66it/s]
 63%|██████▎   | 233489/371472 [7:33:01<10:36:35,  3.61it/s]
 63%|██████▎   | 233490/371472 [7:33:01<10:13:31,  3.75it/s]
 63%|██████▎   | 233491/371472 [7:33:01<10:03:50,  3.81it/s]
 63%|██████▎   | 233492/371472 [7:33:01<9:55:47,  3.86it/s] 
 63%|██████▎   | 233493/371472 [7:33:02<10:09:17,  3.77it/s]
 63%|██████▎   | 233494/371472 [7:33:02<10:30:51,  3.65it/s]
 63%|██████▎   | 233495/371472 [7:33:02<10:19:20,  3.71it/s]
 63%|██████▎   | 233496/371472 [7:33:03<10:44:49,  3.57it/s]
 63%|██████▎   | 233497/371472 [7:33:03<11:25:53,  3.35it/s]
 63%|██████▎   | 233498/371472 [7:33:03<10:53:12,  3.52it/s]
 63%|██████▎   | 233499/371472 [7:33:03<11:50:25,  3.24it/s]
 63%|██████▎   | 233500/371472 [7:33:04<11:33:43,  3.31it/s]
                                                            
{'loss': 2.8849, 'learning_rate': 4.344577560386994e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233500/371472 [7:33:04<11:33:43,  3.31it/s]
 63%|██████▎   | 233501/371472 [7:33:04<11:33:03,  3.32it/s]
 63%|██████▎   | 233502/371472 [7:33:04<11:08:36,  3.44it/s]
 63%|██████▎   | 233503/371472 [7:33:05<10:41:39,  3.58it/s]
 63%|██████▎   | 233504/371472 [7:33:05<10:34:34,  3.62it/s]
 63%|██████▎   | 233505/371472 [7:33:05<10:21:22,  3.70it/s]
 63%|██████▎   | 233506/371472 [7:33:05<10:22:41,  3.69it/s]
 63%|██████▎   | 233507/371472 [7:33:06<10:36:19,  3.61it/s]
 63%|██████▎   | 233508/371472 [7:33:06<11:19:05,  3.39it/s]
 63%|██████▎   | 233509/371472 [7:33:06<11:33:40,  3.31it/s]
 63%|██████▎   | 233510/371472 [7:33:07<11:04:14,  3.46it/s]
 63%|██████▎   | 233511/371472 [7:33:07<11:26:29,  3.35it/s]
 63%|██████▎   | 233512/371472 [7:33:07<11:27:17,  3.35it/s]
 63%|██████▎   | 233513/371472 [7:33:08<11:17:44,  3.39it/s]
 63%|██████▎   | 233514/371472 [7:33:08<10:37:01,  3.61it/s]
 63%|██████▎   | 233515/371472 [7:33:08<10:37:52,  3.60it/s]
 63%|██████▎   | 233516/371472 [7:33:08<10:51:06,  3.53it/s]
 63%|██████▎   | 233517/371472 [7:33:09<10:33:56,  3.63it/s]
 63%|██████▎   | 233518/371472 [7:33:09<10:30:16,  3.65it/s]
 63%|██████▎   | 233519/371472 [7:33:09<10:13:56,  3.74it/s]
 63%|██████▎   | 233520/371472 [7:33:09<10:31:19,  3.64it/s]
                                                            
{'loss': 2.8234, 'learning_rate': 4.344092740632204e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233520/371472 [7:33:09<10:31:19,  3.64it/s]
 63%|██████▎   | 233521/371472 [7:33:10<10:25:55,  3.67it/s]
 63%|██████▎   | 233522/371472 [7:33:10<10:51:27,  3.53it/s]
 63%|██████▎   | 233523/371472 [7:33:10<10:53:39,  3.52it/s]
 63%|██████▎   | 233524/371472 [7:33:11<11:08:39,  3.44it/s]
 63%|██████▎   | 233525/371472 [7:33:11<10:52:40,  3.52it/s]
 63%|██████▎   | 233526/371472 [7:33:11<10:52:38,  3.52it/s]
 63%|██████▎   | 233527/371472 [7:33:11<11:26:57,  3.35it/s]
 63%|██████▎   | 233528/371472 [7:33:12<12:31:47,  3.06it/s]
 63%|██████▎   | 233529/371472 [7:33:12<12:33:05,  3.05it/s]
 63%|██████▎   | 233530/371472 [7:33:12<11:38:04,  3.29it/s]
 63%|██████▎   | 233531/371472 [7:33:13<11:48:53,  3.24it/s]
 63%|██████▎   | 233532/371472 [7:33:13<12:13:56,  3.13it/s]
 63%|██████▎   | 233533/371472 [7:33:13<12:16:22,  3.12it/s]
 63%|██████▎   | 233534/371472 [7:33:14<11:36:04,  3.30it/s]
 63%|██████▎   | 233535/371472 [7:33:14<11:07:47,  3.44it/s]
 63%|██████▎   | 233536/371472 [7:33:14<10:37:27,  3.61it/s]
 63%|██████▎   | 233537/371472 [7:33:14<10:26:25,  3.67it/s]
 63%|██████▎   | 233538/371472 [7:33:15<10:15:50,  3.73it/s]
 63%|██████▎   | 233539/371472 [7:33:15<10:14:09,  3.74it/s]
 63%|██████▎   | 233540/371472 [7:33:15<9:55:07,  3.86it/s] 
                                                           
{'loss': 3.0112, 'learning_rate': 4.3436079208774165e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233540/371472 [7:33:15<9:55:07,  3.86it/s]
 63%|██████▎   | 233541/371472 [7:33:15<10:18:56,  3.71it/s]
 63%|██████▎   | 233542/371472 [7:33:16<10:08:53,  3.78it/s]
 63%|██████▎   | 233543/371472 [7:33:16<10:00:38,  3.83it/s]
 63%|██████▎   | 233544/371472 [7:33:16<10:28:02,  3.66it/s]
 63%|██████▎   | 233545/371472 [7:33:17<10:17:22,  3.72it/s]
 63%|██████▎   | 233546/371472 [7:33:17<10:38:22,  3.60it/s]
 63%|██████▎   | 233547/371472 [7:33:17<10:33:36,  3.63it/s]
 63%|██████▎   | 233548/371472 [7:33:17<10:28:51,  3.66it/s]
 63%|████���█▎   | 233549/371472 [7:33:18<11:34:40,  3.31it/s]
 63%|██████▎   | 233550/371472 [7:33:18<10:58:52,  3.49it/s]
 63%|██████▎   | 233551/371472 [7:33:18<11:01:57,  3.47it/s]
 63%|██████▎   | 233552/371472 [7:33:19<10:29:48,  3.65it/s]
 63%|██████▎   | 233553/371472 [7:33:19<10:26:40,  3.67it/s]
 63%|██████▎   | 233554/371472 [7:33:19<11:24:57,  3.36it/s]
 63%|██████▎   | 233555/371472 [7:33:19<11:11:28,  3.42it/s]
 63%|██████▎   | 233556/371472 [7:33:20<10:59:56,  3.48it/s]
 63%|██████▎   | 233557/371472 [7:33:20<10:54:15,  3.51it/s]
 63%|██████▎   | 233558/371472 [7:33:20<10:32:38,  3.63it/s]
 63%|██████▎   | 233559/371472 [7:33:20<10:09:57,  3.77it/s]
 63%|██████▎   | 233560/371472 [7:33:21<9:47:48,  3.91it/s] 
                                                           
{'loss': 3.0086, 'learning_rate': 4.3431231011226267e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233560/371472 [7:33:21<9:47:48,  3.91it/s]
 63%|██████▎   | 233561/371472 [7:33:21<9:49:41,  3.90it/s]
 63%|██████▎   | 233562/371472 [7:33:21<9:59:59,  3.83it/s]
 63%|██████▎   | 233563/371472 [7:33:21<9:45:05,  3.93it/s]
 63%|██████▎   | 233564/371472 [7:33:22<10:24:40,  3.68it/s]
 63%|██████▎   | 233565/371472 [7:33:22<10:15:30,  3.73it/s]
 63%|██████▎   | 233566/371472 [7:33:22<10:24:08,  3.68it/s]
 63%|██████▎   | 233567/371472 [7:33:23<10:39:14,  3.60it/s]
 63%|██████▎   | 233568/371472 [7:33:23<10:25:47,  3.67it/s]
 63%|██████▎   | 233569/371472 [7:33:23<10:22:01,  3.70it/s]
 63%|██████▎   | 233570/371472 [7:33:23<10:23:57,  3.68it/s]
 63%|██████▎   | 233571/371472 [7:33:24<10:35:21,  3.62it/s]
 63%|██████▎   | 233572/371472 [7:33:24<10:33:20,  3.63it/s]
 63%|██████▎   | 233573/371472 [7:33:24<10:39:29,  3.59it/s]
 63%|██████▎   | 233574/371472 [7:33:25<10:43:17,  3.57it/s]
 63%|██████▎   | 233575/371472 [7:33:25<10:46:37,  3.55it/s]
 63%|██████▎   | 233576/371472 [7:33:25<11:20:52,  3.38it/s]
 63%|██████▎   | 233577/371472 [7:33:25<11:25:11,  3.35it/s]
 63%|██████▎   | 233578/371472 [7:33:26<10:50:28,  3.53it/s]
 63%|██████▎   | 233579/371472 [7:33:26<10:18:07,  3.72it/s]
 63%|██████▎   | 233580/371472 [7:33:26<10:56:38,  3.50it/s]
                                                            
{'loss': 2.6346, 'learning_rate': 4.342638281367838e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233580/371472 [7:33:26<10:56:38,  3.50it/s]
 63%|██████▎   | 233581/371472 [7:33:27<10:43:46,  3.57it/s]
 63%|██████▎   | 233582/371472 [7:33:27<10:40:39,  3.59it/s]
 63%|██████▎   | 233583/371472 [7:33:27<10:22:54,  3.69it/s]
 63%|██████▎   | 233584/371472 [7:33:27<10:06:10,  3.79it/s]
 63%|██████▎   | 233585/371472 [7:33:28<10:09:26,  3.77it/s]
 63%|██████▎   | 233586/371472 [7:33:28<10:04:01,  3.80it/s]
 63%|██████▎   | 233587/371472 [7:33:28<11:39:04,  3.29it/s]
 63%|██████▎   | 233588/371472 [7:33:29<11:02:27,  3.47it/s]
 63%|██████▎   | 233589/371472 [7:33:29<10:46:02,  3.56it/s]
 63%|██████▎   | 233590/371472 [7:33:29<10:29:34,  3.65it/s]
 63%|██████▎   | 233591/371472 [7:33:29<10:16:33,  3.73it/s]
 63%|██████▎   | 233592/371472 [7:33:30<9:58:33,  3.84it/s] 
 63%|██████▎   | 233593/371472 [7:33:30<9:54:13,  3.87it/s]
 63%|██████▎   | 233594/371472 [7:33:30<9:38:27,  3.97it/s]
 63%|██████▎   | 233595/371472 [7:33:30<9:53:15,  3.87it/s]
 63%|██████▎   | 233596/371472 [7:33:31<9:55:25,  3.86it/s]
 63%|██████▎   | 233597/371472 [7:33:31<10:09:50,  3.77it/s]
 63%|██████▎   | 233598/371472 [7:33:31<9:55:51,  3.86it/s] 
 63%|██████▎   | 233599/371472 [7:33:31<9:37:35,  3.98it/s]
 63%|██████▎   | 233600/371472 [7:33:32<9:51:12,  3.89it/s]
                                                           
{'loss': 2.9216, 'learning_rate': 4.3421534616130486e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233600/371472 [7:33:32<9:51:12,  3.89it/s]
 63%|██████▎   | 233601/371472 [7:33:32<9:36:51,  3.98it/s]
 63%|██████▎   | 233602/371472 [7:33:32<10:32:59,  3.63it/s]
 63%|██████▎   | 233603/371472 [7:33:32<10:12:07,  3.75it/s]
 63%|██████▎   | 233604/371472 [7:33:33<10:28:48,  3.65it/s]
 63%|██████▎   | 233605/371472 [7:33:33<10:29:53,  3.65it/s]
 63%|██████▎   | 233606/371472 [7:33:33<10:09:56,  3.77it/s]
 63%|██████▎   | 233607/371472 [7:33:33<10:17:35,  3.72it/s]
 63%|██████▎   | 233608/371472 [7:33:34<10:31:42,  3.64it/s]
 63%|██████▎   | 233609/371472 [7:33:34<10:15:17,  3.73it/s]
 63%|██████▎   | 233610/371472 [7:33:34<10:20:22,  3.70it/s]
 63%|██████▎   | 233611/371472 [7:33:35<10:55:18,  3.51it/s]
 63%|██████▎   | 233612/371472 [7:33:35<11:13:06,  3.41it/s]
 63%|██████▎   | 233613/371472 [7:33:35<10:48:49,  3.54it/s]
 63%|██████▎   | 233614/371472 [7:33:35<10:56:12,  3.50it/s]
 63%|██████▎   | 233615/371472 [7:33:36<11:32:08,  3.32it/s]
 63%|██████▎   | 233616/371472 [7:33:36<11:10:54,  3.42it/s]
 63%|██████▎   | 233617/371472 [7:33:36<11:12:37,  3.42it/s]
 63%|██████▎   | 233618/371472 [7:33:37<10:55:07,  3.51it/s]
 63%|██████▎   | 233619/371472 [7:33:37<11:38:11,  3.29it/s]
 63%|██████▎   | 233620/371472 [7:33:37<12:13:00,  3.13it/s]
                                                            
{'loss': 2.86, 'learning_rate': 4.3416686418582604e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233620/371472 [7:33:37<12:13:00,  3.13it/s]
 63%|██████▎   | 233621/371472 [7:33:38<11:26:31,  3.35it/s]
 63%|██████▎   | 233622/371472 [7:33:38<11:19:05,  3.38it/s]
 63%|██████▎   | 233623/371472 [7:33:38<10:54:35,  3.51it/s]
 63%|██████▎   | 233624/371472 [7:33:38<10:48:16,  3.54it/s]
 63%|██████▎   | 233625/371472 [7:33:39<10:27:49,  3.66it/s]
 63%|██████▎   | 233626/371472 [7:33:39<10:41:52,  3.58it/s]
 63%|██████▎   | 233627/371472 [7:33:39<11:25:47,  3.35it/s]
 63%|██████▎   | 233628/371472 [7:33:40<11:56:30,  3.21it/s]
 63%|██████▎   | 233629/371472 [7:33:40<11:19:53,  3.38it/s]
 63%|██████▎   | 233630/371472 [7:33:40<10:49:55,  3.53it/s]
 63%|██████▎   | 233631/371472 [7:33:40<10:41:27,  3.58it/s]
 63%|██████▎   | 233632/371472 [7:33:41<10:33:16,  3.63it/s]
 63%|██████▎   | 233633/371472 [7:33:41<10:37:06,  3.61it/s]
 63%|██████▎   | 233634/371472 [7:33:41<10:33:23,  3.63it/s]
 63%|██████▎   | 233635/371472 [7:33:42<10:36:44,  3.61it/s]
 63%|██████▎   | 233636/371472 [7:33:42<10:33:42,  3.63it/s]
 63%|██████▎   | 233637/371472 [7:33:42<10:16:31,  3.73it/s]
 63%|██████▎   | 233638/371472 [7:33:42<10:16:37,  3.73it/s]
 63%|██████▎   | 233639/371472 [7:33:43<10:26:45,  3.67it/s]
 63%|██████▎   | 233640/371472 [7:33:43<11:12:01,  3.42it/s]
                                                            
{'loss': 2.9154, 'learning_rate': 4.3411838221034706e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233640/371472 [7:33:43<11:12:01,  3.42it/s]
 63%|██████▎   | 233641/371472 [7:33:43<10:41:36,  3.58it/s]
 63%|██████▎   | 233642/371472 [7:33:44<10:59:57,  3.48it/s]
 63%|██████▎   | 233643/371472 [7:33:44<11:02:36,  3.47it/s]
 63%|██████▎   | 233644/371472 [7:33:44<10:40:07,  3.59it/s]
 63%|██████▎   | 233645/371472 [7:33:44<10:39:12,  3.59it/s]
 63%|██████▎   | 233646/371472 [7:33:45<10:23:15,  3.69it/s]
 63%|██████▎   | 233647/371472 [7:33:45<10:12:22,  3.75it/s]
 63%|██████▎   | 233648/371472 [7:33:45<9:55:05,  3.86it/s] 
 63%|██████▎   | 233649/371472 [7:33:45<10:13:18,  3.75it/s]
 63%|██████▎   | 233650/371472 [7:33:46<10:21:00,  3.70it/s]
 63%|██████▎   | 233651/371472 [7:33:46<10:18:50,  3.71it/s]
 63%|██████▎   | 233652/371472 [7:33:46<10:20:48,  3.70it/s]
 63%|██████▎   | 233653/371472 [7:33:47<10:44:50,  3.56it/s]
 63%|██████▎   | 233654/371472 [7:33:47<10:57:58,  3.49it/s]
 63%|██████▎   | 233655/371472 [7:33:47<11:41:09,  3.28it/s]
 63%|██████▎   | 233656/371472 [7:33:47<12:06:30,  3.16it/s]
 63%|██████▎   | 233657/371472 [7:33:48<11:49:58,  3.24it/s]
 63%|██████▎   | 233658/371472 [7:33:48<11:26:37,  3.35it/s]
 63%|██████▎   | 233659/371472 [7:33:48<11:15:44,  3.40it/s]
 63%|██████▎   | 233660/371472 [7:33:49<10:45:45,  3.56it/s]
                                                            
{'loss': 2.7932, 'learning_rate': 4.3406990023486824e-07, 'epoch': 10.06}
+
 63%|██████▎   | 233660/371472 [7:33:49<10:45:45,  3.56it/s]
 63%|██████▎   | 233661/371472 [7:33:49<10:34:19,  3.62it/s]
 63%|██████▎   | 233662/371472 [7:33:49<10:31:24,  3.64it/s]
 63%|██████▎   | 233663/371472 [7:33:49<10:26:49,  3.66it/s]
 63%|██████▎   | 233664/371472 [7:33:50<10:36:13,  3.61it/s]
 63%|██████▎   | 233665/371472 [7:33:50<10:18:54,  3.71it/s]
 63%|██████▎   | 233666/371472 [7:33:50<10:44:57,  3.56it/s]
 63%|██████▎   | 233667/371472 [7:33:51<10:36:04,  3.61it/s]
 63%|██████▎   | 233668/371472 [7:33:51<11:06:23,  3.45it/s]
 63%|██████▎   | 233669/371472 [7:33:51<10:40:39,  3.58it/s]
 63%|██████▎   | 233670/371472 [7:33:51<10:23:19,  3.68it/s]
 63%|██████▎   | 233671/371472 [7:33:52<10:24:27,  3.68it/s]
 63%|██████▎   | 233672/371472 [7:33:52<10:17:23,  3.72it/s]
 63%|██████▎   | 233673/371472 [7:33:52<10:11:39,  3.75it/s]
 63%|██████▎   | 233674/371472 [7:33:52<9:54:45,  3.86it/s] 
 63%|██████▎   | 233675/371472 [7:33:53<9:47:51,  3.91it/s]
 63%|██████▎   | 233676/371472 [7:33:53<10:27:15,  3.66it/s]
 63%|██████▎   | 233677/371472 [7:33:53<10:15:17,  3.73it/s]
 63%|██████▎   | 233678/371472 [7:33:53<10:02:48,  3.81it/s]
 63%|██████▎   | 233679/371472 [7:33:54<9:58:56,  3.83it/s] 
 63%|██████▎   | 233680/371472 [7:33:54<10:04:28,  3.80it/s]
                                                            
{'loss': 3.0443, 'learning_rate': 4.340214182593893e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233680/371472 [7:33:54<10:04:28,  3.80it/s]
 63%|██████▎   | 233681/371472 [7:33:54<10:17:29,  3.72it/s]
 63%|██████▎   | 233682/371472 [7:33:54<9:53:39,  3.87it/s] 
 63%|██████▎   | 233683/371472 [7:33:55<9:53:13,  3.87it/s]
 63%|██████▎   | 233684/371472 [7:33:55<9:46:32,  3.92it/s]
 63%|██████▎   | 233685/371472 [7:33:55<9:59:48,  3.83it/s]
 63%|██████▎   | 233686/371472 [7:33:56<10:13:50,  3.74it/s]
 63%|██████▎   | 233687/371472 [7:33:56<10:08:14,  3.78it/s]
 63%|██████▎   | 233688/371472 [7:33:56<9:55:11,  3.86it/s] 
 63%|██████▎   | 233689/371472 [7:33:56<9:53:32,  3.87it/s]
 63%|██████▎   | 233690/371472 [7:33:57<9:49:06,  3.90it/s]
 63%|██████▎   | 233691/371472 [7:33:57<10:05:07,  3.79it/s]
 63%|██████▎   | 233692/371472 [7:33:57<10:11:44,  3.75it/s]
 63%|██████▎   | 233693/371472 [7:33:57<10:08:55,  3.77it/s]
 63%|██████▎   | 233694/371472 [7:33:58<10:35:12,  3.62it/s]
 63%|██████▎   | 233695/371472 [7:33:58<10:12:47,  3.75it/s]
 63%|██████▎   | 233696/371472 [7:33:58<10:26:22,  3.67it/s]
 63%|██████▎   | 233697/371472 [7:33:58<10:29:45,  3.65it/s]
 63%|██████▎   | 233698/371472 [7:33:59<10:11:40,  3.75it/s]
 63%|██████▎   | 233699/371472 [7:33:59<10:29:01,  3.65it/s]
 63%|██████▎   | 233700/371472 [7:33:59<11:17:07,  3.39it/s]
                                                            
{'loss': 2.7425, 'learning_rate': 4.3397293628391043e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233700/371472 [7:33:59<11:17:07,  3.39it/s]
 63%|██████▎   | 233701/371472 [7:34:00<10:54:22,  3.51it/s]
 63%|██████▎   | 233702/371472 [7:34:00<11:46:48,  3.25it/s]
 63%|██████▎   | 233703/371472 [7:34:00<11:41:30,  3.27it/s]
 63%|██████▎   | 233704/371472 [7:34:01<11:13:53,  3.41it/s]
 63%|██████▎   | 233705/371472 [7:34:01<10:47:25,  3.55it/s]
 63%|██████▎   | 233706/371472 [7:34:01<10:31:07,  3.64it/s]
 63%|██████▎   | 233707/371472 [7:34:01<10:36:42,  3.61it/s]
 63%|██████▎   | 233708/371472 [7:34:02<10:17:49,  3.72it/s]
 63%|██████▎   | 233709/371472 [7:34:02<10:26:00,  3.67it/s]
 63%|██████▎   | 233710/371472 [7:34:02<10:22:13,  3.69it/s]
 63%|██████▎   | 233711/371472 [7:34:02<10:15:09,  3.73it/s]
 63%|██████▎   | 233712/371472 [7:34:03<9:57:59,  3.84it/s] 
 63%|██████▎   | 233713/371472 [7:34:03<10:52:10,  3.52it/s]
 63%|██████▎   | 233714/371472 [7:34:03<10:43:33,  3.57it/s]
 63%|██████▎   | 233715/371472 [7:34:04<12:04:15,  3.17it/s]
 63%|██████▎   | 233716/371472 [7:34:04<12:20:26,  3.10it/s]
 63%|██████▎   | 233717/371472 [7:34:04<11:32:34,  3.32it/s]
 63%|██████▎   | 233718/371472 [7:34:05<10:57:42,  3.49it/s]
 63%|██████▎   | 233719/371472 [7:34:05<10:32:19,  3.63it/s]
 63%|██████▎   | 233720/371472 [7:34:05<10:41:39,  3.58it/s]
                                                            
{'loss': 2.8999, 'learning_rate': 4.339244543084315e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233720/371472 [7:34:05<10:41:39,  3.58it/s]
 63%|██████▎   | 233721/371472 [7:34:05<10:38:44,  3.59it/s]
 63%|██████▎   | 233722/371472 [7:34:06<10:31:04,  3.64it/s]
 63%|██████▎   | 233723/371472 [7:34:06<10:39:50,  3.59it/s]
 63%|██████▎   | 233724/371472 [7:34:06<10:40:05,  3.59it/s]
 63%|██████▎   | 233725/371472 [7:34:06<10:10:35,  3.76it/s]
 63%|██████▎   | 233726/371472 [7:34:07<10:22:55,  3.69it/s]
 63%|██████▎   | 233727/371472 [7:34:07<10:13:31,  3.74it/s]
 63%|██████▎   | 233728/371472 [7:34:07<10:09:51,  3.76it/s]
 63%|██████▎   | 233729/371472 [7:34:07<9:59:53,  3.83it/s] 
 63%|██████▎   | 233730/371472 [7:34:08<10:30:42,  3.64it/s]
 63%|██████▎   | 233731/371472 [7:34:08<10:31:31,  3.64it/s]
 63%|██████▎   | 233732/371472 [7:34:08<10:39:20,  3.59it/s]
 63%|██████▎   | 233733/371472 [7:34:09<10:51:29,  3.52it/s]
 63%|██████▎   | 233734/371472 [7:34:09<10:43:19,  3.57it/s]
 63%|██████▎   | 233735/371472 [7:34:09<10:27:50,  3.66it/s]
 63%|██████▎   | 233736/371472 [7:34:09<10:12:23,  3.75it/s]
 63%|██████▎   | 233737/371472 [7:34:10<10:08:23,  3.77it/s]
 63%|██████▎   | 233738/371472 [7:34:10<10:31:54,  3.63it/s]
 63%|██████▎   | 233739/371472 [7:34:10<10:55:03,  3.50it/s]
 63%|██████▎   | 233740/371472 [7:34:11<10:28:15,  3.65it/s]
                                                            
{'loss': 3.0483, 'learning_rate': 4.338759723329527e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233740/371472 [7:34:11<10:28:15,  3.65it/s]
 63%|██████▎   | 233741/371472 [7:34:11<10:39:02,  3.59it/s]
 63%|██████▎   | 233742/371472 [7:34:11<11:35:49,  3.30it/s]
 63%|██████▎   | 233743/371472 [7:34:11<11:32:03,  3.32it/s]
 63%|██████▎   | 233744/371472 [7:34:12<11:57:02,  3.20it/s]
 63%|██████▎   | 233745/371472 [7:34:12<11:14:38,  3.40it/s]
 63%|██████▎   | 233746/371472 [7:34:12<11:55:26,  3.21it/s]
 63%|██████▎   | 233747/371472 [7:34:13<11:17:01,  3.39it/s]
 63%|██████▎   | 233748/371472 [7:34:13<10:58:27,  3.49it/s]
 63%|██████▎   | 233749/371472 [7:34:13<11:34:18,  3.31it/s]
 63%|██████▎   | 233750/371472 [7:34:14<10:53:47,  3.51it/s]
 63%|██████▎   | 233751/371472 [7:34:14<10:59:32,  3.48it/s]
 63%|██████▎   | 233752/371472 [7:34:14<10:35:54,  3.61it/s]
 63%|██████▎   | 233753/371472 [7:34:14<10:29:25,  3.65it/s]
 63%|██████▎   | 233754/371472 [7:34:15<11:06:46,  3.44it/s]
 63%|██████▎   | 233755/371472 [7:34:15<10:50:20,  3.53it/s]
 63%|██████▎   | 233756/371472 [7:34:15<11:20:37,  3.37it/s]
 63%|██████▎   | 233757/371472 [7:34:16<11:06:40,  3.44it/s]
 63%|██████▎   | 233758/371472 [7:34:16<10:26:13,  3.67it/s]
 63%|██████▎   | 233759/371472 [7:34:16<10:23:40,  3.68it/s]
 63%|██████▎   | 233760/371472 [7:34:16<10:18:18,  3.71it/s]
                                                            
{'loss': 2.829, 'learning_rate': 4.338274903574737e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233760/371472 [7:34:16<10:18:18,  3.71it/s]
 63%|██████▎   | 233761/371472 [7:34:17<10:23:41,  3.68it/s]
 63%|██████▎   | 233762/371472 [7:34:17<10:18:42,  3.71it/s]
 63%|██████▎   | 233763/371472 [7:34:17<10:11:40,  3.75it/s]
 63%|██████▎   | 233764/371472 [7:34:17<9:56:06,  3.85it/s] 
 63%|██████▎   | 233765/371472 [7:34:18<9:57:59,  3.84it/s]
 63%|██████▎   | 233766/371472 [7:34:18<11:10:28,  3.42it/s]
 63%|██████▎   | 233767/371472 [7:34:18<10:34:58,  3.61it/s]
 63%|██████▎   | 233768/371472 [7:34:18<10:23:14,  3.68it/s]
 63%|██████▎   | 233769/371472 [7:34:19<10:36:24,  3.61it/s]
 63%|██████▎   | 233770/371472 [7:34:19<10:11:27,  3.75it/s]
 63%|██████▎   | 233771/371472 [7:34:19<10:07:03,  3.78it/s]
 63%|██████▎   | 233772/371472 [7:34:19<9:46:44,  3.91it/s] 
 63%|██████▎   | 233773/371472 [7:34:20<9:41:34,  3.95it/s]
 63%|██████▎   | 233774/371472 [7:34:20<9:54:22,  3.86it/s]
 63%|██████▎   | 233775/371472 [7:34:20<10:03:24,  3.80it/s]
 63%|██████▎   | 233776/371472 [7:34:21<9:41:52,  3.94it/s] 
 63%|██████▎   | 233777/371472 [7:34:21<10:22:32,  3.69it/s]
 63%|██████▎   | 233778/371472 [7:34:21<10:23:38,  3.68it/s]
 63%|██████▎   | 233779/371472 [7:34:21<10:00:38,  3.82it/s]
 63%|██████▎   | 233780/371472 [7:34:22<9:56:30,  3.85it/s] 
                                                           
{'loss': 2.9305, 'learning_rate': 4.337790083819949e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233780/371472 [7:34:22<9:56:30,  3.85it/s]
 63%|██████▎   | 233781/371472 [7:34:22<10:10:34,  3.76it/s]
 63%|██████▎   | 233782/371472 [7:34:22<10:52:52,  3.52it/s]
 63%|██████▎   | 233783/371472 [7:34:23<11:17:03,  3.39it/s]
 63%|██████▎   | 233784/371472 [7:34:23<10:48:34,  3.54it/s]
 63%|██████▎   | 233785/371472 [7:34:23<10:36:31,  3.61it/s]
 63%|██████▎   | 233786/371472 [7:34:23<10:42:42,  3.57it/s]
 63%|██████▎   | 233787/371472 [7:34:24<10:16:18,  3.72it/s]
 63%|██████▎   | 233788/371472 [7:34:24<10:08:20,  3.77it/s]
 63%|██████▎   | 233789/371472 [7:34:24<10:07:35,  3.78it/s]
 63%|██████▎   | 233790/371472 [7:34:24<10:25:17,  3.67it/s]
 63%|██████▎   | 233791/371472 [7:34:25<10:26:47,  3.66it/s]
 63%|██████▎   | 233792/371472 [7:34:25<11:18:41,  3.38it/s]
 63%|██████▎   | 233793/371472 [7:34:25<11:16:11,  3.39it/s]
 63%|██████▎   | 233794/371472 [7:34:26<10:43:52,  3.56it/s]
 63%|██████▎   | 233795/371472 [7:34:26<10:29:32,  3.64it/s]
 63%|██████▎   | 233796/371472 [7:34:26<10:36:42,  3.60it/s]
 63%|██████▎   | 233797/371472 [7:34:26<10:29:13,  3.65it/s]
 63%|██████▎   | 233798/371472 [7:34:27<10:11:13,  3.75it/s]
 63%|██████▎   | 233799/371472 [7:34:27<10:21:55,  3.69it/s]
 63%|██████▎   | 233800/371472 [7:34:27<11:40:55,  3.27it/s]
                                                            
{'loss': 2.8804, 'learning_rate': 4.3373052640651595e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233800/371472 [7:34:27<11:40:55,  3.27it/s]
 63%|██████▎   | 233801/371472 [7:34:28<11:03:14,  3.46it/s]
 63%|██████▎   | 233802/371472 [7:34:28<11:07:05,  3.44it/s]
 63%|██████▎   | 233803/371472 [7:34:28<11:00:11,  3.48it/s]
 63%|██████▎   | 233804/371472 [7:34:28<11:14:04,  3.40it/s]
 63%|██████▎   | 233805/371472 [7:34:29<12:07:42,  3.15it/s]
 63%|██████▎   | 233806/371472 [7:34:29<11:38:24,  3.29it/s]
 63%|██████▎   | 233807/371472 [7:34:29<11:38:37,  3.28it/s]
 63%|██████▎   | 233808/371472 [7:34:30<11:05:21,  3.45it/s]
 63%|██████▎   | 233809/371472 [7:34:30<10:39:41,  3.59it/s]
 63%|██████▎   | 233810/371472 [7:34:30<10:55:38,  3.50it/s]
 63%|██████▎   | 233811/371472 [7:34:30<10:37:36,  3.60it/s]
 63%|██████▎   | 233812/371472 [7:34:31<10:16:33,  3.72it/s]
 63%|██████▎   | 233813/371472 [7:34:31<10:44:46,  3.56it/s]
 63%|██████▎   | 233814/371472 [7:34:31<10:56:52,  3.49it/s]
 63%|██████▎   | 233815/371472 [7:34:32<10:32:53,  3.63it/s]
 63%|██████▎   | 233816/371472 [7:34:32<10:41:10,  3.58it/s]
 63%|██████▎   | 233817/371472 [7:34:32<10:26:50,  3.66it/s]
 63%|██████▎   | 233818/371472 [7:34:32<11:21:29,  3.37it/s]
 63%|██████▎   | 233819/371472 [7:34:33<10:59:31,  3.48it/s]
 63%|██████▎   | 233820/371472 [7:34:33<10:37:05,  3.60it/s]
                                                            
{'loss': 2.8475, 'learning_rate': 4.3368204443103707e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233820/371472 [7:34:33<10:37:05,  3.60it/s]
 63%|██████▎   | 233821/371472 [7:34:33<10:41:50,  3.57it/s]
 63%|██████▎   | 233822/371472 [7:34:33<10:27:08,  3.66it/s]
 63%|██████▎   | 233823/371472 [7:34:34<10:31:49,  3.63it/s]
 63%|██████▎   | 233824/371472 [7:34:34<10:43:02,  3.57it/s]
 63%|██████▎   | 233825/371472 [7:34:34<10:38:59,  3.59it/s]
 63%|██████▎   | 233826/371472 [7:34:35<10:56:33,  3.49it/s]
 63%|██████▎   | 233827/371472 [7:34:35<11:01:24,  3.47it/s]
 63%|██████▎   | 233828/371472 [7:34:35<11:45:08,  3.25it/s]
 63%|██████▎   | 233829/371472 [7:34:36<11:22:00,  3.36it/s]
 63%|██████▎   | 233830/371472 [7:34:36<10:57:43,  3.49it/s]
 63%|██████▎   | 233831/371472 [7:34:36<11:38:58,  3.28it/s]
 63%|██████▎   | 233832/371472 [7:34:36<11:02:57,  3.46it/s]
 63%|██████▎   | 233833/371472 [7:34:37<11:45:20,  3.25it/s]
 63%|██████▎   | 233834/371472 [7:34:37<11:30:21,  3.32it/s]
 63%|██████▎   | 233835/371472 [7:34:37<10:55:41,  3.50it/s]
 63%|██████▎   | 233836/371472 [7:34:38<11:01:12,  3.47it/s]
 63%|██████▎   | 233837/371472 [7:34:38<10:27:59,  3.65it/s]
 63%|██████▎   | 233838/371472 [7:34:38<11:40:14,  3.28it/s]
 63%|██████▎   | 233839/371472 [7:34:38<10:55:33,  3.50it/s]
 63%|██████▎   | 233840/371472 [7:34:39<10:54:22,  3.51it/s]
                                                            
{'loss': 2.8963, 'learning_rate': 4.3363356245555814e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233840/371472 [7:34:39<10:54:22,  3.51it/s]
 63%|██████▎   | 233841/371472 [7:34:39<10:44:46,  3.56it/s]
 63%|██████▎   | 233842/371472 [7:34:39<10:23:47,  3.68it/s]
 63%|██████▎   | 233843/371472 [7:34:40<10:09:57,  3.76it/s]
 63%|██████▎   | 233844/371472 [7:34:40<9:50:25,  3.88it/s] 
 63%|██████▎   | 233845/371472 [7:34:40<10:35:51,  3.61it/s]
 63%|██████▎   | 233846/371472 [7:34:40<10:55:59,  3.50it/s]
 63%|██████▎   | 233847/371472 [7:34:41<11:13:00,  3.41it/s]
 63%|██████▎   | 233848/371472 [7:34:41<11:05:00,  3.45it/s]
 63%|██████▎   | 233849/371472 [7:34:41<11:09:52,  3.42it/s]
 63%|██████▎   | 233850/371472 [7:34:42<10:31:00,  3.63it/s]
 63%|██████▎   | 233851/371472 [7:34:42<10:31:38,  3.63it/s]
 63%|██████▎   | 233852/371472 [7:34:42<10:20:37,  3.70it/s]
 63%|██████▎   | 233853/371472 [7:34:42<10:39:26,  3.59it/s]
 63%|██████▎   | 233854/371472 [7:34:43<11:11:24,  3.42it/s]
 63%|██████▎   | 233855/371472 [7:34:43<11:29:12,  3.33it/s]
 63%|██████▎   | 233856/371472 [7:34:43<10:54:07,  3.51it/s]
 63%|██████▎   | 233857/371472 [7:34:44<10:53:04,  3.51it/s]
 63%|██████▎   | 233858/371472 [7:34:44<11:43:12,  3.26it/s]
 63%|██████▎   | 233859/371472 [7:34:44<11:29:33,  3.33it/s]
 63%|██████▎   | 233860/371472 [7:34:44<11:08:49,  3.43it/s]
                                                            
{'loss': 2.7511, 'learning_rate': 4.335850804800793e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233860/371472 [7:34:44<11:08:49,  3.43it/s]
 63%|██████▎   | 233861/371472 [7:34:45<10:59:05,  3.48it/s]
 63%|██████▎   | 233862/371472 [7:34:45<11:46:06,  3.25it/s]
 63%|██████▎   | 233863/371472 [7:34:45<11:12:23,  3.41it/s]
 63%|██████▎   | 233864/371472 [7:34:46<10:58:15,  3.48it/s]
 63%|██████▎   | 233865/371472 [7:34:46<11:25:31,  3.35it/s]
 63%|██████▎   | 233866/371472 [7:34:46<11:03:57,  3.45it/s]
 63%|██████▎   | 233867/371472 [7:34:46<10:44:06,  3.56it/s]
 63%|██████▎   | 233868/371472 [7:34:47<11:37:37,  3.29it/s]
 63%|██████▎   | 233869/371472 [7:34:47<11:30:38,  3.32it/s]
 63%|██████▎   | 233870/371472 [7:34:47<11:32:25,  3.31it/s]
 63%|██████▎   | 233871/371472 [7:34:48<11:14:54,  3.40it/s]
 63%|██████▎   | 233872/371472 [7:34:48<11:22:09,  3.36it/s]
 63%|██████▎   | 233873/371472 [7:34:48<11:46:51,  3.24it/s]
 63%|██████▎   | 233874/371472 [7:34:49<11:22:14,  3.36it/s]
 63%|██████▎   | 233875/371472 [7:34:49<11:03:08,  3.46it/s]
 63%|██████▎   | 233876/371472 [7:34:49<10:56:54,  3.49it/s]
 63%|██████▎   | 233877/371472 [7:34:49<10:49:41,  3.53it/s]
 63%|██████▎   | 233878/371472 [7:34:50<10:36:35,  3.60it/s]
 63%|██████▎   | 233879/371472 [7:34:50<10:39:25,  3.59it/s]
 63%|██████▎   | 233880/371472 [7:34:50<11:20:51,  3.37it/s]
                                                            
{'loss': 2.8349, 'learning_rate': 4.335365985046004e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233880/371472 [7:34:50<11:20:51,  3.37it/s]
 63%|██████▎   | 233881/371472 [7:34:51<11:15:07,  3.40it/s]
 63%|██████▎   | 233882/371472 [7:34:51<13:06:14,  2.92it/s]
 63%|██████▎   | 233883/371472 [7:34:51<11:52:47,  3.22it/s]
 63%|██████▎   | 233884/371472 [7:34:52<11:23:56,  3.35it/s]
 63%|██████▎   | 233885/371472 [7:34:52<10:56:34,  3.49it/s]
 63%|██████▎   | 233886/371472 [7:34:52<11:00:45,  3.47it/s]
 63%|██████▎   | 233887/371472 [7:34:52<10:59:31,  3.48it/s]
 63%|██████▎   | 233888/371472 [7:34:53<11:42:21,  3.26it/s]
 63%|██████▎   | 233889/371472 [7:34:53<11:10:15,  3.42it/s]
 63%|██████▎   | 233890/371472 [7:34:53<10:42:13,  3.57it/s]
 63%|██████▎   | 233891/371472 [7:34:54<11:03:30,  3.46it/s]
 63%|██████▎   | 233892/371472 [7:34:54<10:34:01,  3.62it/s]
 63%|██████▎   | 233893/371472 [7:34:54<10:29:59,  3.64it/s]
 63%|██████▎   | 233894/371472 [7:34:54<10:22:06,  3.69it/s]
 63%|██████▎   | 233895/371472 [7:34:55<10:19:47,  3.70it/s]
 63%|██████▎   | 233896/371472 [7:34:55<10:36:47,  3.60it/s]
 63%|██████▎   | 233897/371472 [7:34:55<10:29:47,  3.64it/s]
 63%|██████▎   | 233898/371472 [7:34:55<10:14:03,  3.73it/s]
 63%|██████▎   | 233899/371472 [7:34:56<9:57:55,  3.83it/s] 
 63%|██████▎   | 233900/371472 [7:34:56<9:51:33,  3.88it/s]
                                                           
{'loss': 2.8754, 'learning_rate': 4.334881165291215e-07, 'epoch': 10.07}
+
 63%|██████▎   | 233900/371472 [7:34:56<9:51:33,  3.88it/s]
 63%|██████▎   | 233901/371472 [7:34:56<10:07:44,  3.77it/s]
 63%|██████▎   | 233902/371472 [7:34:57<10:26:07,  3.66it/s]
 63%|██████▎   | 233903/371472 [7:34:57<10:35:03,  3.61it/s]
 63%|██████▎   | 233904/371472 [7:34:57<10:22:14,  3.68it/s]
 63%|██████▎   | 233905/371472 [7:34:57<10:48:13,  3.54it/s]
 63%|██████▎   | 233906/371472 [7:34:58<10:30:18,  3.64it/s]
 63%|██████▎   | 233907/371472 [7:34:58<10:26:48,  3.66it/s]
 63%|██████▎   | 233908/371472 [7:34:58<10:17:13,  3.71it/s]
 63%|██████▎   | 233909/371472 [7:34:58<10:27:58,  3.65it/s]
 63%|██████▎   | 233910/371472 [7:34:59<11:10:16,  3.42it/s]
 63%|██████▎   | 233911/371472 [7:34:59<10:58:15,  3.48it/s]
 63%|██████▎   | 233912/371472 [7:34:59<10:58:10,  3.48it/s]
 63%|██████▎   | 233913/371472 [7:35:00<10:35:02,  3.61it/s]
 63%|██████▎   | 233914/371472 [7:35:00<10:20:04,  3.70it/s]
 63%|██████▎   | 233915/371472 [7:35:00<10:27:43,  3.65it/s]
 63%|██████▎   | 233916/371472 [7:35:00<10:26:47,  3.66it/s]
 63%|██████▎   | 233917/371472 [7:35:01<10:48:29,  3.54it/s]
 63%|██████▎   | 233918/371472 [7:35:01<10:29:19,  3.64it/s]
 63%|██████▎   | 233919/371472 [7:35:01<10:01:04,  3.81it/s]
 63%|██████▎   | 233920/371472 [7:35:01<10:13:48,  3.73it/s]
                                                            
{'loss': 2.9304, 'learning_rate': 4.334396345536426e-07, 'epoch': 10.08}
+
 63%|██████▎   | 233920/371472 [7:35:01<10:13:48,  3.73it/s]
 63%|██████▎   | 233921/371472 [7:35:02<10:43:01,  3.57it/s]
 63%|██████▎   | 233922/371472 [7:35:02<10:27:06,  3.66it/s]
 63%|██████▎   | 233923/371472 [7:35:02<10:29:07,  3.64it/s]
 63%|██████▎   | 233924/371472 [7:35:03<10:37:36,  3.60it/s]
 63%|██████▎   | 233925/371472 [7:35:03<10:26:18,  3.66it/s]
 63%|██████▎   | 233926/371472 [7:35:03<10:25:25,  3.67it/s]
 63%|██████▎   | 233927/371472 [7:35:03<10:22:33,  3.68it/s]
 63%|██████▎   | 233928/371472 [7:35:04<10:29:20,  3.64it/s]
 63%|██████▎   | 233929/371472 [7:35:04<11:16:37,  3.39it/s]
 63%|██████▎   | 233930/371472 [7:35:04<11:09:54,  3.42it/s]
 63%|██████▎   | 233931/371472 [7:35:05<10:49:38,  3.53it/s]
 63%|██████▎   | 233932/371472 [7:35:05<10:27:37,  3.65it/s]
 63%|██████▎   | 233933/371472 [7:35:05<10:20:55,  3.69it/s]
 63%|██████▎   | 233934/371472 [7:35:05<10:33:35,  3.62it/s]
 63%|██████▎   | 233935/371472 [7:35:06<10:32:29,  3.62it/s]
 63%|██████▎   | 233936/371472 [7:35:06<10:43:03,  3.56it/s]
 63%|██████▎   | 233937/371472 [7:35:06<10:29:11,  3.64it/s]
 63%|██████▎   | 233938/371472 [7:35:06<10:15:30,  3.72it/s]
 63%|██████▎   | 233939/371472 [7:35:07<10:22:17,  3.68it/s]
 63%|██████▎   | 233940/371472 [7:35:07<10:43:55,  3.56it/s]
                                                            
{'loss': 2.8387, 'learning_rate': 4.3339115257816377e-07, 'epoch': 10.08}
+
 63%|██████▎   | 233940/371472 [7:35:07<10:43:55,  3.56it/s]
 63%|██████▎   | 233941/371472 [7:35:07<10:48:22,  3.54it/s]
 63%|██████▎   | 233942/371472 [7:35:08<10:42:17,  3.57it/s]
 63%|██████▎   | 233943/371472 [7:35:08<10:31:06,  3.63it/s]
 63%|██████▎   | 233944/371472 [7:35:08<10:40:44,  3.58it/s]
 63%|██████▎   | 233945/371472 [7:35:08<10:21:48,  3.69it/s]
 63%|██████▎   | 233946/371472 [7:35:09<10:37:41,  3.59it/s]
 63%|██████▎   | 233947/371472 [7:35:09<10:28:30,  3.65it/s]
 63%|██████▎   | 233948/371472 [7:35:09<10:18:41,  3.70it/s]
 63%|██████▎   | 233949/371472 [7:35:10<11:14:37,  3.40it/s]
 63%|██████▎   | 233950/371472 [7:35:10<11:48:23,  3.24it/s]
 63%|██████▎   | 233951/371472 [7:35:10<11:31:57,  3.31it/s]
 63%|██████▎   | 233952/371472 [7:35:10<11:19:54,  3.37it/s]
 63%|██████▎   | 233953/371472 [7:35:11<10:50:39,  3.52it/s]
 63%|██████▎   | 233954/371472 [7:35:11<10:35:10,  3.61it/s]
 63%|██████▎   | 233955/371472 [7:35:11<10:44:42,  3.56it/s]
 63%|██████▎   | 233956/371472 [7:35:12<10:33:35,  3.62it/s]
 63%|██████▎   | 233957/371472 [7:35:12<10:36:40,  3.60it/s]
 63%|██████▎   | 233958/371472 [7:35:12<10:43:51,  3.56it/s]
 63%|██████▎   | 233959/371472 [7:35:12<10:34:39,  3.61it/s]
 63%|██████▎   | 233960/371472 [7:35:13<10:16:47,  3.72it/s]
                                                            
{'loss': 2.8098, 'learning_rate': 4.3334267060268484e-07, 'epoch': 10.08}
+
 63%|██████▎   | 233960/371472 [7:35:13<10:16:47,  3.72it/s]
 63%|██████▎   | 233961/371472 [7:35:13<10:33:51,  3.62it/s]
 63%|██████▎   | 233962/371472 [7:35:13<10:16:05,  3.72it/s]
 63%|██████▎   | 233963/371472 [7:35:13<10:24:57,  3.67it/s]
 63%|██████▎   | 233964/371472 [7:35:14<10:31:02,  3.63it/s]
 63%|██████▎   | 233965/371472 [7:35:14<10:24:46,  3.67it/s]
 63%|██████▎   | 233966/371472 [7:35:14<10:38:52,  3.59it/s]
 63%|██████▎   | 233967/371472 [7:35:15<10:28:33,  3.65it/s]
 63%|█████��▎   | 233968/371472 [7:35:15<10:20:37,  3.69it/s]
 63%|██████▎   | 233969/371472 [7:35:15<10:06:26,  3.78it/s]
 63%|██████▎   | 233970/371472 [7:35:15<9:58:55,  3.83it/s] 
 63%|██████▎   | 233971/371472 [7:35:16<10:11:32,  3.75it/s]
 63%|██████▎   | 233972/371472 [7:35:16<10:48:28,  3.53it/s]
 63%|██████▎   | 233973/371472 [7:35:16<10:44:46,  3.55it/s]
 63%|██████▎   | 233974/371472 [7:35:17<10:49:17,  3.53it/s]
 63%|██████▎   | 233975/371472 [7:35:17<10:52:05,  3.51it/s]
 63%|██████▎   | 233976/371472 [7:35:17<11:24:56,  3.35it/s]
 63%|██████▎   | 233977/371472 [7:35:17<10:47:45,  3.54it/s]
 63%|██████▎   | 233978/371472 [7:35:18<10:51:09,  3.52it/s]
 63%|██████▎   | 233979/371472 [7:35:18<10:47:41,  3.54it/s]
 63%|██████▎   | 233980/371472 [7:35:18<10:30:24,  3.64it/s]
                                                            
{'loss': 2.7956, 'learning_rate': 4.3329418862720596e-07, 'epoch': 10.08}
+
 63%|██████▎   | 233980/371472 [7:35:18<10:30:24,  3.64it/s]
 63%|██████▎   | 233981/371472 [7:35:19<10:49:13,  3.53it/s]
 63%|██████▎   | 233982/371472 [7:35:19<11:27:36,  3.33it/s]
 63%|██████▎   | 233983/371472 [7:35:19<10:55:12,  3.50it/s]
 63%|██████▎   | 233984/371472 [7:35:19<11:06:58,  3.44it/s]
 63%|██████▎   | 233985/371472 [7:35:20<10:45:37,  3.55it/s]
 63%|██████▎   | 233986/371472 [7:35:20<10:37:02,  3.60it/s]
 63%|██████▎   | 233987/371472 [7:35:20<10:29:41,  3.64it/s]
 63%|██████▎   | 233988/371472 [7:35:21<11:00:03,  3.47it/s]
 63%|██████▎   | 233989/371472 [7:35:21<10:33:32,  3.62it/s]
 63%|██████▎   | 233990/371472 [7:35:21<10:27:20,  3.65it/s]
 63%|██████▎   | 233991/371472 [7:35:21<10:38:30,  3.59it/s]
 63%|██████▎   | 233992/371472 [7:35:22<10:28:48,  3.64it/s]
 63%|██████▎   | 233993/371472 [7:35:22<10:27:42,  3.65it/s]
 63%|██████▎   | 233994/371472 [7:35:22<10:54:56,  3.50it/s]
 63%|██████▎   | 233995/371472 [7:35:22<11:01:29,  3.46it/s]
 63%|██████▎   | 233996/371472 [7:35:23<10:58:09,  3.48it/s]
 63%|██████▎   | 233997/371472 [7:35:23<11:58:56,  3.19it/s]
 63%|██████▎   | 233998/371472 [7:35:23<11:39:07,  3.28it/s]
 63%|██████▎   | 233999/371472 [7:35:24<10:52:00,  3.51it/s]
 63%|██████▎   | 234000/371472 [7:35:24<10:36:14,  3.60it/s]
                                                            
{'loss': 2.9105, 'learning_rate': 4.3324570665172703e-07, 'epoch': 10.08}
+
 63%|██████▎   | 234000/371472 [7:35:24<10:36:14,  3.60it/s]
 63%|██████▎   | 234001/371472 [7:35:24<10:12:45,  3.74it/s]
 63%|██████▎   | 234002/371472 [7:35:24<10:03:07,  3.80it/s]
 63%|██████▎   | 234003/371472 [7:35:25<10:43:47,  3.56it/s]
 63%|██████▎   | 234004/371472 [7:35:25<10:22:43,  3.68it/s]
 63%|██████▎   | 234005/371472 [7:35:25<10:44:51,  3.55it/s]
 63%|██████▎   | 234006/371472 [7:35:26<10:36:49,  3.60it/s]
 63%|██████▎   | 234007/371472 [7:35:26<11:00:12,  3.47it/s]
 63%|██████▎   | 234008/371472 [7:35:26<12:18:51,  3.10it/s]
 63%|██████▎   | 234009/371472 [7:35:27<11:58:18,  3.19it/s]
 63%|██████▎   | 234010/371472 [7:35:27<12:35:10,  3.03it/s]
 63%|██████▎   | 234011/371472 [7:35:27<12:12:58,  3.13it/s]
 63%|██████▎   | 234012/371472 [7:35:27<11:23:19,  3.35it/s]
 63%|██████▎   | 234013/371472 [7:35:28<10:40:18,  3.58it/s]
 63%|██████▎   | 234014/371472 [7:35:28<10:52:14,  3.51it/s]
 63%|██████▎   | 234015/371472 [7:35:28<10:49:57,  3.52it/s]
 63%|██████▎   | 234016/371472 [7:35:29<10:42:05,  3.57it/s]
 63%|██████▎   | 234017/371472 [7:35:29<11:22:06,  3.36it/s]
 63%|██████▎   | 234018/371472 [7:35:29<11:29:59,  3.32it/s]
 63%|██████▎   | 234019/371472 [7:35:29<11:07:11,  3.43it/s]
 63%|██████▎   | 234020/371472 [7:35:30<11:40:22,  3.27it/s]
                                                            
{'loss': 2.7143, 'learning_rate': 4.3319722467624805e-07, 'epoch': 10.08}
+
 63%|██████▎   | 234020/371472 [7:35:30<11:40:22,  3.27it/s]
 63%|██████▎   | 234021/371472 [7:35:30<11:14:22,  3.40it/s]
 63%|██████▎   | 234022/371472 [7:35:30<11:07:50,  3.43it/s]
 63%|██████▎   | 234023/371472 [7:35:31<10:31:36,  3.63it/s]
 63%|██████▎   | 234024/371472 [7:35:31<10:32:34,  3.62it/s]
 63%|██████▎   | 234025/371472 [7:35:31<10:19:55,  3.70it/s]
 63%|██████▎   | 234026/371472 [7:35:31<10:21:05,  3.69it/s]
 63%|██████▎   | 234027/371472 [7:35:32<10:33:39,  3.62it/s]
 63%|���█████▎   | 234028/371472 [7:35:32<11:09:42,  3.42it/s]
 63%|██████▎   | 234029/371472 [7:35:32<10:46:40,  3.54it/s]
 63%|██████▎   | 234030/371472 [7:35:33<10:41:10,  3.57it/s]
 63%|██████▎   | 234031/371472 [7:35:33<10:23:30,  3.67it/s]
 63%|██████▎   | 234032/371472 [7:35:33<10:16:21,  3.72it/s]
 63%|██████▎   | 234033/371472 [7:35:33<10:26:13,  3.66it/s]
 63%|██████▎   | 234034/371472 [7:35:34<10:13:08,  3.74it/s]
 63%|██████▎   | 234035/371472 [7:35:34<11:01:16,  3.46it/s]
 63%|██████▎   | 234036/371472 [7:35:34<10:39:38,  3.58it/s]
 63%|██████▎   | 234037/371472 [7:35:34<10:29:13,  3.64it/s]
 63%|██████▎   | 234038/371472 [7:35:35<10:38:03,  3.59it/s]
 63%|██████▎   | 234039/371472 [7:35:35<10:36:05,  3.60it/s]
 63%|██████▎   | 234040/371472 [7:35:35<10:13:31,  3.73it/s]
                                                            
{'loss': 2.9883, 'learning_rate': 4.3314874270076923e-07, 'epoch': 10.08}
+
 63%|██████▎   | 234040/371472 [7:35:35<10:13:31,  3.73it/s]
 63%|██████▎   | 234041/371472 [7:35:36<10:14:27,  3.73it/s]
 63%|██████▎   | 234042/371472 [7:35:36<10:01:53,  3.81it/s]
 63%|██████▎   | 234043/371472 [7:35:36<11:04:53,  3.44it/s]
 63%|██████▎   | 234044/371472 [7:35:36<10:50:32,  3.52it/s]
 63%|██████▎   | 234045/371472 [7:35:37<10:36:51,  3.60it/s]
 63%|██████▎   | 234046/371472 [7:35:37<10:53:25,  3.51it/s]
 63%|██████▎   | 234047/371472 [7:35:37<10:28:05,  3.65it/s]
 63%|██████▎   | 234048/371472 [7:35:38<10:41:16,  3.57it/s]
 63%|██████▎   | 234049/371472 [7:35:38<10:31:21,  3.63it/s]
 63%|██████▎   | 234050/371472 [7:35:38<10:16:34,  3.71it/s]
 63%|██████▎   | 234051/371472 [7:35:38<10:42:07,  3.57it/s]
 63%|██████▎   | 234052/371472 [7:35:39<10:29:55,  3.64it/s]
 63%|██████▎   | 234053/371472 [7:35:39<10:11:28,  3.75it/s]
 63%|██████▎   | 234054/371472 [7:35:39<10:09:48,  3.76it/s]
 63%|██████▎   | 234055/371472 [7:35:40<11:20:15,  3.37it/s]
 63%|██████▎   | 234056/371472 [7:35:40<11:16:31,  3.39it/s]
 63%|██████▎   | 234057/371472 [7:35:40<11:03:37,  3.45it/s]
 63%|██████▎   | 234058/371472 [7:35:40<11:28:04,  3.33it/s]
 63%|██████▎   | 234059/371472 [7:35:41<11:03:16,  3.45it/s]
 63%|██████▎   | 234060/371472 [7:35:41<10:41:52,  3.57it/s]
                                                            
{'loss': 2.8373, 'learning_rate': 4.331002607252903e-07, 'epoch': 10.08}
+
 63%|██████▎   | 234060/371472 [7:35:41<10:41:52,  3.57it/s]
 63%|██████▎   | 234061/371472 [7:35:41<11:00:57,  3.46it/s]
 63%|██████▎   | 234062/371472 [7:35:42<12:08:23,  3.14it/s]
 63%|██████▎   | 234063/371472 [7:35:42<11:33:47,  3.30it/s]
 63%|██████▎   | 234064/371472 [7:35:42<12:08:50,  3.14it/s]
 63%|██████▎   | 234065/371472 [7:35:43<12:17:35,  3.10it/s]
 63%|██████▎   | 234066/371472 [7:35:43<11:40:14,  3.27it/s]
 63%|██████▎   | 234067/371472 [7:35:43<11:28:06,  3.33it/s]
 63%|██████▎   | 234068/371472 [7:35:43<11:11:01,  3.41it/s]
 63%|██████▎   | 234069/371472 [7:35:44<11:06:10,  3.44it/s]
 63%|██████▎   | 234070/371472 [7:35:44<11:24:26,  3.35it/s]
 63%|██████▎   | 234071/371472 [7:35:44<10:46:37,  3.54it/s]
 63%|██████▎   | 234072/371472 [7:35:44<10:24:38,  3.67it/s]
 63%|██████▎   | 234073/371472 [7:35:45<10:38:12,  3.59it/s]
 63%|██████▎   | 234074/371472 [7:35:45<10:34:42,  3.61it/s]
 63%|██████▎   | 234075/371472 [7:35:45<10:14:43,  3.73it/s]
 63%|██████▎   | 234076/371472 [7:35:46<10:04:27,  3.79it/s]
 63%|██████▎   | 234077/371472 [7:35:46<11:05:45,  3.44it/s]
 63%|██████▎   | 234078/371472 [7:35:46<10:47:18,  3.54it/s]
 63%|██████▎   | 234079/371472 [7:35:46<10:29:00,  3.64it/s]
 63%|██████▎   | 234080/371472 [7:35:47<10:41:33,  3.57it/s]
                                                            
{'loss': 2.9629, 'learning_rate': 4.330517787498114e-07, 'epoch': 10.08}
+
 63%|██████▎   | 234080/371472 [7:35:47<10:41:33,  3.57it/s]
 63%|██████▎   | 234081/371472 [7:35:47<10:59:40,  3.47it/s]
 63%|██████▎   | 234082/371472 [7:35:47<10:51:14,  3.52it/s]
 63%|██████▎   | 234083/371472 [7:35:48<10:48:28,  3.53it/s]
 63%|██████▎   | 234084/371472 [7:35:48<10:31:24,  3.63it/s]
 63%|██████▎   | 234085/371472 [7:35:48<10:30:36,  3.63it/s]
 63%|██████▎   | 234086/371472 [7:35:48<10:22:27,  3.68it/s]
 63%|██████▎   | 234087/371472 [7:35:49<10:41:47,  3.57it/s]
 63%|██████▎   | 234088/371472 [7:35:49<10:35:42,  3.60it/s]
 63%|██████▎   | 234089/371472 [7:35:49<10:33:12,  3.62it/s]
 63%|██████▎   | 234090/371472 [7:35:49<10:12:20,  3.74it/s]
 63%|██████▎   | 234091/371472 [7:35:50<9:53:36,  3.86it/s] 
 63%|██████▎   | 234092/371472 [7:35:50<9:48:11,  3.89it/s]
 63%|██████▎   | 234093/371472 [7:35:50<9:43:57,  3.92it/s]
 63%|██████▎   | 234094/371472 [7:35:50<9:48:54,  3.89it/s]
 63%|██████▎   | 234095/371472 [7:35:51<10:09:58,  3.75it/s]
 63%|██████▎   | 234096/371472 [7:35:51<10:12:48,  3.74it/s]
 63%|██████▎   | 234097/371472 [7:35:51<10:20:58,  3.69it/s]
 63%|██████▎   | 234098/371472 [7:35:52<11:07:24,  3.43it/s]
 63%|██████▎   | 234099/371472 [7:35:52<10:48:21,  3.53it/s]
 63%|██████▎   | 234100/371472 [7:35:52<10:39:34,  3.58it/s]
                                                            
{'loss': 2.7209, 'learning_rate': 4.330032967743325e-07, 'epoch': 10.08}
+
 63%|██████▎   | 234100/371472 [7:35:52<10:39:34,  3.58it/s]
 63%|██████▎   | 234101/371472 [7:35:53<10:56:21,  3.49it/s]
 63%|██████▎   | 234102/371472 [7:35:53<10:36:23,  3.60it/s]
 63%|██████▎   | 234103/371472 [7:35:53<10:44:02,  3.55it/s]
 63%|██████▎   | 234104/371472 [7:35:53<10:35:09,  3.60it/s]
 63%|██████▎   | 234105/371472 [7:35:54<10:17:22,  3.71it/s]
 63%|██████▎   | 234106/371472 [7:35:54<10:17:20,  3.71it/s]
 63%|██████▎   | 234107/371472 [7:35:54<11:02:32,  3.46it/s]
 63%|██████▎   | 234108/371472 [7:35:54<10:44:02,  3.55it/s]
 63%|██████▎   | 234109/371472 [7:35:55<11:06:09,  3.44it/s]
 63%|██████▎   | 234110/371472 [7:35:55<10:44:07,  3.55it/s]
 63%|██████▎   | 234111/371472 [7:35:55<10:27:52,  3.65it/s]
 63%|██████▎   | 234112/371472 [7:35:56<10:44:31,  3.55it/s]
 63%|██████▎   | 234113/371472 [7:35:56<10:50:57,  3.52it/s]
 63%|██████▎   | 234114/371472 [7:35:56<10:42:53,  3.56it/s]
 63%|██████▎   | 234115/371472 [7:35:56<10:25:57,  3.66it/s]
 63%|██████▎   | 234116/371472 [7:35:57<10:29:00,  3.64it/s]
 63%|██████▎   | 234117/371472 [7:35:57<10:47:49,  3.53it/s]
 63%|██████▎   | 234118/371472 [7:35:57<10:44:24,  3.55it/s]
 63%|██████▎   | 234119/371472 [7:35:58<11:12:09,  3.41it/s]
 63%|██████▎   | 234120/371472 [7:35:58<10:59:14,  3.47it/s]
                                                            
{'loss': 3.0773, 'learning_rate': 4.329548147988537e-07, 'epoch': 10.08}
+
 63%|██████▎   | 234120/371472 [7:35:58<10:59:14,  3.47it/s]
 63%|██████▎   | 234121/371472 [7:35:58<11:57:13,  3.19it/s]
 63%|██████▎   | 234122/371472 [7:35:59<11:48:20,  3.23it/s]
 63%|██████▎   | 234123/371472 [7:35:59<11:40:54,  3.27it/s]
 63%|██████▎   | 234124/371472 [7:35:59<11:38:19,  3.28it/s]
 63%|██████▎   | 234125/371472 [7:35:59<11:25:43,  3.34it/s]
 63%|██████▎   | 234126/371472 [7:36:00<10:54:47,  3.50it/s]
 63%|██████▎   | 234127/371472 [7:36:00<10:38:43,  3.58it/s]
 63%|██████▎   | 234128/371472 [7:36:00<11:01:55,  3.46it/s]
 63%|██████▎   | 234129/371472 [7:36:00<10:39:24,  3.58it/s]
 63%|██████▎   | 234130/371472 [7:36:01<10:38:26,  3.59it/s]
 63%|██████▎   | 234131/371472 [7:36:01<10:28:41,  3.64it/s]
 63%|██████▎   | 234132/371472 [7:36:01<10:10:51,  3.75it/s]
 63%|██████▎   | 234133/371472 [7:36:02<10:05:45,  3.78it/s]
 63%|██████▎   | 234134/371472 [7:36:02<10:22:39,  3.68it/s]
 63%|██████▎   | 234135/371472 [7:36:02<10:04:53,  3.78it/s]
 63%|██████▎   | 234136/371472 [7:36:02<10:48:56,  3.53it/s]
 63%|██████▎   | 234137/371472 [7:36:03<12:00:00,  3.18it/s]
 63%|██████▎   | 234138/371472 [7:36:03<11:51:37,  3.22it/s]
 63%|██████▎   | 234139/371472 [7:36:03<11:22:39,  3.35it/s]
 63%|██████▎   | 234140/371472 [7:36:04<11:05:51,  3.44it/s]
                                                            
{'loss': 2.8062, 'learning_rate': 4.3290633282337475e-07, 'epoch': 10.08}
+
 63%|██████▎   | 234140/371472 [7:36:04<11:05:51,  3.44it/s]
 63%|██████▎   | 234141/371472 [7:36:04<10:39:31,  3.58it/s]
 63%|██████▎   | 234142/371472 [7:36:04<10:21:55,  3.68it/s]
 63%|██████▎   | 234143/371472 [7:36:04<10:09:09,  3.76it/s]
 63%|██████▎   | 234144/371472 [7:36:05<9:57:23,  3.83it/s] 
 63%|██████▎   | 234145/371472 [7:36:05<10:28:38,  3.64it/s]
 63%|██████▎   | 234146/371472 [7:36:05<10:17:43,  3.71it/s]
 63%|██████▎   | 234147/371472 [7:36:05<10:31:39,  3.62it/s]
 63%|██████▎   | 234148/371472 [7:36:06<10:19:41,  3.69it/s]
 63%|██████▎   | 234149/371472 [7:36:06<10:21:47,  3.68it/s]
 63%|██████▎   | 234150/371472 [7:36:06<10:21:18,  3.68it/s]
 63%|██████▎   | 234151/371472 [7:36:07<10:27:15,  3.65it/s]
 63%|██████▎   | 234152/371472 [7:36:07<10:27:21,  3.65it/s]
 63%|██████▎   | 234153/371472 [7:36:07<10:08:41,  3.76it/s]
 63%|██████▎   | 234154/371472 [7:36:07<10:00:09,  3.81it/s]
 63%|██████▎   | 234155/371472 [7:36:08<10:24:13,  3.67it/s]
 63%|██████▎   | 234156/371472 [7:36:08<10:44:22,  3.55it/s]
 63%|██████▎   | 234157/371472 [7:36:08<10:42:53,  3.56it/s]
 63%|██████▎   | 234158/371472 [7:36:09<10:49:33,  3.52it/s]
 63%|██████▎   | 234159/371472 [7:36:09<11:28:00,  3.33it/s]
 63%|██████▎   | 234160/371472 [7:36:09<10:57:35,  3.48it/s]
                                                            
{'loss': 2.9334, 'learning_rate': 4.3285785084789587e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234160/371472 [7:36:09<10:57:35,  3.48it/s]
 63%|██████▎   | 234161/371472 [7:36:09<11:29:53,  3.32it/s]
 63%|██████▎   | 234162/371472 [7:36:10<10:50:42,  3.52it/s]
 63%|██████▎   | 234163/371472 [7:36:10<10:37:42,  3.59it/s]
 63%|██████▎   | 234164/371472 [7:36:10<10:17:36,  3.71it/s]
 63%|██████▎   | 234165/371472 [7:36:11<11:06:16,  3.43it/s]
 63%|██████▎   | 234166/371472 [7:36:11<10:41:41,  3.57it/s]
 63%|██████▎   | 234167/371472 [7:36:11<10:51:11,  3.51it/s]
 63%|██████▎   | 234168/371472 [7:36:11<11:14:28,  3.39it/s]
 63%|██████▎   | 234169/371472 [7:36:12<10:47:48,  3.53it/s]
 63%|██████▎   | 234170/371472 [7:36:12<10:47:17,  3.54it/s]
 63%|██████▎   | 234171/371472 [7:36:12<10:26:19,  3.65it/s]
 63%|██████▎   | 234172/371472 [7:36:12<10:30:32,  3.63it/s]
 63%|██████▎   | 234173/371472 [7:36:13<11:35:33,  3.29it/s]
 63%|██████▎   | 234174/371472 [7:36:13<10:58:49,  3.47it/s]
 63%|██████▎   | 234175/371472 [7:36:13<11:02:53,  3.45it/s]
 63%|██████▎   | 234176/371472 [7:36:14<10:50:41,  3.52it/s]
 63%|██████▎   | 234177/371472 [7:36:14<11:37:39,  3.28it/s]
 63%|██████▎   | 234178/371472 [7:36:14<11:18:27,  3.37it/s]
 63%|██████▎   | 234179/371472 [7:36:15<11:01:49,  3.46it/s]
 63%|██████▎   | 234180/371472 [7:36:15<11:16:14,  3.38it/s]
                                                            
{'loss': 2.7328, 'learning_rate': 4.3280936887241694e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234180/371472 [7:36:15<11:16:14,  3.38it/s]
 63%|██████▎   | 234181/371472 [7:36:15<11:59:53,  3.18it/s]
 63%|██████▎   | 234182/371472 [7:36:16<12:16:21,  3.11it/s]
 63%|██████▎   | 234183/371472 [7:36:16<12:32:32,  3.04it/s]
 63%|██████▎   | 234184/371472 [7:36:16<12:01:46,  3.17it/s]
 63%|██████▎   | 234185/371472 [7:36:17<11:57:59,  3.19it/s]
 63%|██████▎   | 234186/371472 [7:36:17<11:53:00,  3.21it/s]
 63%|██████▎   | 234187/371472 [7:36:17<11:43:38,  3.25it/s]
 63%|██████▎   | 234188/371472 [7:36:17<11:01:04,  3.46it/s]
 63%|██████▎   | 234189/371472 [7:36:18<10:53:06,  3.50it/s]
 63%|██████▎   | 234190/371472 [7:36:18<10:49:42,  3.52it/s]
 63%|██████▎   | 234191/371472 [7:36:18<10:35:37,  3.60it/s]
 63%|██████▎   | 234192/371472 [7:36:18<10:22:49,  3.67it/s]
 63%|██████▎   | 234193/371472 [7:36:19<10:34:44,  3.60it/s]
 63%|██████▎   | 234194/371472 [7:36:19<10:16:25,  3.71it/s]
 63%|██████▎   | 234195/371472 [7:36:19<10:20:38,  3.69it/s]
 63%|██████▎   | 234196/371472 [7:36:20<10:22:52,  3.67it/s]
 63%|██████▎   | 234197/371472 [7:36:20<10:21:57,  3.68it/s]
 63%|██████▎   | 234198/371472 [7:36:20<10:24:27,  3.66it/s]
 63%|██████▎   | 234199/371472 [7:36:20<10:58:39,  3.47it/s]
 63%|██████▎   | 234200/371472 [7:36:21<11:18:54,  3.37it/s]
                                                            
{'loss': 3.0254, 'learning_rate': 4.3276088689693807e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234200/371472 [7:36:21<11:18:54,  3.37it/s]
 63%|██████▎   | 234201/371472 [7:36:21<11:00:56,  3.46it/s]
 63%|██████▎   | 234202/371472 [7:36:21<10:44:57,  3.55it/s]
 63%|██████▎   | 234203/371472 [7:36:22<10:19:29,  3.69it/s]
 63%|██████▎   | 234204/371472 [7:36:22<11:35:15,  3.29it/s]
 63%|██████▎   | 234205/371472 [7:36:22<11:05:19,  3.44it/s]
 63%|██████▎   | 234206/371472 [7:36:22<11:03:52,  3.45it/s]
 63%|██████▎   | 234207/371472 [7:36:23<10:47:15,  3.53it/s]
 63%|██████▎   | 234208/371472 [7:36:23<10:26:04,  3.65it/s]
 63%|██████▎   | 234209/371472 [7:36:23<10:37:54,  3.59it/s]
 63%|██████▎   | 234210/371472 [7:36:24<10:39:29,  3.58it/s]
 63%|██████▎   | 234211/371472 [7:36:24<10:36:51,  3.59it/s]
 63%|██████▎   | 234212/371472 [7:36:24<11:23:56,  3.34it/s]
 63%|██████▎   | 234213/371472 [7:36:24<10:46:48,  3.54it/s]
 63%|██████▎   | 234214/371472 [7:36:25<10:53:20,  3.50it/s]
 63%|██████▎   | 234215/371472 [7:36:25<10:36:26,  3.59it/s]
 63%|██████▎   | 234216/371472 [7:36:25<10:43:40,  3.55it/s]
 63%|██████▎   | 234217/371472 [7:36:26<10:41:36,  3.57it/s]
 63%|██████▎   | 234218/371472 [7:36:26<10:26:07,  3.65it/s]
 63%|██████▎   | 234219/371472 [7:36:26<10:33:01,  3.61it/s]
 63%|██████▎   | 234220/371472 [7:36:26<10:42:57,  3.56it/s]
                                                            
{'loss': 2.8315, 'learning_rate': 4.3271240492145914e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234220/371472 [7:36:26<10:42:57,  3.56it/s]
 63%|██████▎   | 234221/371472 [7:36:27<10:59:20,  3.47it/s]
 63%|██████▎   | 234222/371472 [7:36:27<10:49:38,  3.52it/s]
 63%|██████▎   | 234223/371472 [7:36:27<11:24:50,  3.34it/s]
 63%|██████▎   | 234224/371472 [7:36:28<11:10:09,  3.41it/s]
 63%|██████▎   | 234225/371472 [7:36:28<11:11:41,  3.41it/s]
 63%|██████▎   | 234226/371472 [7:36:28<11:04:34,  3.44it/s]
 63%|██████▎   | 234227/371472 [7:36:28<11:31:49,  3.31it/s]
 63%|██████▎   | 234228/371472 [7:36:29<10:59:11,  3.47it/s]
 63%|██████▎   | 234229/371472 [7:36:29<11:38:50,  3.27it/s]
 63%|██████▎   | 234230/371472 [7:36:29<11:34:30,  3.29it/s]
 63%|██████▎   | 234231/371472 [7:36:30<11:08:14,  3.42it/s]
 63%|██████▎   | 234232/371472 [7:36:30<10:45:26,  3.54it/s]
 63%|██████▎   | 234233/371472 [7:36:30<10:41:01,  3.57it/s]
 63%|██████▎   | 234234/371472 [7:36:30<10:25:06,  3.66it/s]
 63%|██████▎   | 234235/371472 [7:36:31<10:51:32,  3.51it/s]
 63%|██████▎   | 234236/371472 [7:36:31<10:53:49,  3.50it/s]
 63%|██████▎   | 234237/371472 [7:36:31<10:33:22,  3.61it/s]
 63%|██████▎   | 234238/371472 [7:36:32<10:19:19,  3.69it/s]
 63%|██████▎   | 234239/371472 [7:36:32<11:38:06,  3.28it/s]
 63%|██████▎   | 234240/371472 [7:36:32<11:19:33,  3.37it/s]
                                                            
{'loss': 2.8493, 'learning_rate': 4.326639229459803e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234240/371472 [7:36:32<11:19:33,  3.37it/s]
 63%|██████▎   | 234241/371472 [7:36:32<10:59:19,  3.47it/s]
 63%|██████▎   | 234242/371472 [7:36:33<10:33:34,  3.61it/s]
 63%|██████▎   | 234243/371472 [7:36:33<11:19:29,  3.37it/s]
 63%|██████▎   | 234244/371472 [7:36:33<11:20:48,  3.36it/s]
 63%|██████▎   | 234245/371472 [7:36:34<10:51:36,  3.51it/s]
 63%|██████▎   | 234246/371472 [7:36:34<10:42:50,  3.56it/s]
 63%|██████▎   | 234247/371472 [7:36:34<10:12:42,  3.73it/s]
 63%|██████▎   | 234248/371472 [7:36:34<10:39:58,  3.57it/s]
 63%|██████▎   | 234249/371472 [7:36:35<10:12:25,  3.73it/s]
 63%|██████▎   | 234250/371472 [7:36:35<10:35:04,  3.60it/s]
 63%|██████▎   | 234251/371472 [7:36:35<10:15:56,  3.71it/s]
 63%|██████▎   | 234252/371472 [7:36:36<10:54:20,  3.50it/s]
 63%|██████▎   | 234253/371472 [7:36:36<10:56:29,  3.48it/s]
 63%|██████▎   | 234254/371472 [7:36:36<11:02:03,  3.45it/s]
 63%|██████▎   | 234255/371472 [7:36:36<10:56:42,  3.48it/s]
 63%|██████▎   | 234256/371472 [7:36:37<10:54:45,  3.49it/s]
 63%|██████▎   | 234257/371472 [7:36:37<10:50:50,  3.51it/s]
 63%|██████▎   | 234258/371472 [7:36:37<10:33:21,  3.61it/s]
 63%|██████▎   | 234259/371472 [7:36:38<10:34:34,  3.60it/s]
 63%|██████▎   | 234260/371472 [7:36:38<10:34:05,  3.61it/s]
                                                            
{'loss': 2.7214, 'learning_rate': 4.326154409705014e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234260/371472 [7:36:38<10:34:05,  3.61it/s]
 63%|██████▎   | 234261/371472 [7:36:38<10:34:24,  3.60it/s]
 63%|██████▎   | 234262/371472 [7:36:38<10:51:23,  3.51it/s]
 63%|██████▎   | 234263/371472 [7:36:39<12:22:55,  3.08it/s]
 63%|██████▎   | 234264/371472 [7:36:39<11:40:36,  3.26it/s]
 63%|██████▎   | 234265/371472 [7:36:39<11:35:10,  3.29it/s]
 63%|██████▎   | 234266/371472 [7:36:40<11:05:26,  3.44it/s]
 63%|██████▎   | 234267/371472 [7:36:40<10:42:47,  3.56it/s]
 63%|██████▎   | 234268/371472 [7:36:40<10:27:59,  3.64it/s]
 63%|██████▎   | 234269/371472 [7:36:40<10:28:57,  3.64it/s]
 63%|██████▎   | 234270/371472 [7:36:41<10:18:07,  3.70it/s]
 63%|██████▎   | 234271/371472 [7:36:41<10:34:05,  3.61it/s]
 63%|██████▎   | 234272/371472 [7:36:41<12:10:03,  3.13it/s]
 63%|██████▎   | 234273/371472 [7:36:42<11:50:51,  3.22it/s]
 63%|██████▎   | 234274/371472 [7:36:42<11:22:48,  3.35it/s]
 63%|██████▎   | 234275/371472 [7:36:42<11:10:11,  3.41it/s]
 63%|██████▎   | 234276/371472 [7:36:42<10:52:59,  3.50it/s]
 63%|██████▎   | 234277/371472 [7:36:43<11:01:30,  3.46it/s]
 63%|██████▎   | 234278/371472 [7:36:43<10:33:22,  3.61it/s]
 63%|██████▎   | 234279/371472 [7:36:43<10:16:28,  3.71it/s]
 63%|██████▎   | 234280/371472 [7:36:44<10:04:32,  3.78it/s]
                                                            
{'loss': 2.7732, 'learning_rate': 4.325669589950225e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234280/371472 [7:36:44<10:04:32,  3.78it/s]
 63%|██████▎   | 234281/371472 [7:36:44<10:13:48,  3.73it/s]
 63%|██████▎   | 234282/371472 [7:36:44<10:03:19,  3.79it/s]
 63%|██████▎   | 234283/371472 [7:36:44<10:24:57,  3.66it/s]
 63%|██████▎   | 234284/371472 [7:36:45<11:31:23,  3.31it/s]
 63%|██████▎   | 234285/371472 [7:36:45<11:15:27,  3.39it/s]
 63%|██████▎   | 234286/371472 [7:36:45<11:08:39,  3.42it/s]
 63%|██████▎   | 234287/371472 [7:36:46<11:08:18,  3.42it/s]
 63%|██████▎   | 234288/371472 [7:36:46<11:48:15,  3.23it/s]
 63%|██████▎   | 234289/371472 [7:36:46<11:00:22,  3.46it/s]
 63%|██████▎   | 234290/371472 [7:36:47<11:25:11,  3.34it/s]
 63%|██████▎   | 234291/371472 [7:36:47<11:36:00,  3.28it/s]
 63%|██████▎   | 234292/371472 [7:36:47<10:59:39,  3.47it/s]
 63%|██████▎   | 234293/371472 [7:36:47<11:40:45,  3.26it/s]
 63%|██████▎   | 234294/371472 [7:36:48<11:21:14,  3.36it/s]
 63%|██████▎   | 234295/371472 [7:36:48<10:52:42,  3.50it/s]
 63%|██████▎   | 234296/371472 [7:36:48<12:57:33,  2.94it/s]
 63%|██████▎   | 234297/371472 [7:36:49<12:50:42,  2.97it/s]
 63%|██████▎   | 234298/371472 [7:36:49<12:03:45,  3.16it/s]
 63%|██████▎   | 234299/371472 [7:36:49<11:55:56,  3.19it/s]
 63%|██████▎   | 234300/371472 [7:36:50<11:10:21,  3.41it/s]
                                                            
{'loss': 2.7375, 'learning_rate': 4.325184770195436e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234300/371472 [7:36:50<11:10:21,  3.41it/s]
 63%|██████▎   | 234301/371472 [7:36:50<10:45:50,  3.54it/s]
 63%|██████▎   | 234302/371472 [7:36:50<11:22:10,  3.35it/s]
 63%|██████▎   | 234303/371472 [7:36:51<11:49:58,  3.22it/s]
 63%|██████▎   | 234304/371472 [7:36:51<12:08:59,  3.14it/s]
 63%|██████▎   | 234305/371472 [7:36:51<11:46:04,  3.24it/s]
 63%|██████▎   | 234306/371472 [7:36:51<12:06:44,  3.15it/s]
 63%|██████▎   | 234307/371472 [7:36:52<11:29:46,  3.31it/s]
 63%|██████▎   | 234308/371472 [7:36:52<11:20:08,  3.36it/s]
 63%|██████▎   | 234309/371472 [7:36:52<11:14:12,  3.39it/s]
 63%|██████▎   | 234310/371472 [7:36:53<11:02:39,  3.45it/s]
 63%|██████▎   | 234311/371472 [7:36:53<12:05:30,  3.15it/s]
 63%|██████▎   | 234312/371472 [7:36:53<11:28:00,  3.32it/s]
 63%|██████▎   | 234313/371472 [7:36:53<10:44:12,  3.55it/s]
 63%|██████▎   | 234314/371472 [7:36:54<10:37:00,  3.59it/s]
 63%|██████▎   | 234315/371472 [7:36:54<11:24:20,  3.34it/s]
 63%|██████▎   | 234316/371472 [7:36:54<11:33:52,  3.29it/s]
 63%|██████▎   | 234317/371472 [7:36:55<10:57:24,  3.48it/s]
 63%|██████▎   | 234318/371472 [7:36:55<10:51:57,  3.51it/s]
 63%|██████▎   | 234319/371472 [7:36:55<10:28:21,  3.64it/s]
 63%|██████▎   | 234320/371472 [7:36:55<10:30:26,  3.63it/s]
                                                            
{'loss': 2.8935, 'learning_rate': 4.3246999504406476e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234320/371472 [7:36:55<10:30:26,  3.63it/s]
 63%|██████▎   | 234321/371472 [7:36:56<10:40:00,  3.57it/s]
 63%|██████▎   | 234322/371472 [7:36:56<10:24:54,  3.66it/s]
 63%|██████▎   | 234323/371472 [7:36:56<10:29:29,  3.63it/s]
 63%|██████▎   | 234324/371472 [7:36:57<10:42:59,  3.55it/s]
 63%|██████▎   | 234325/371472 [7:36:57<10:41:36,  3.56it/s]
 63%|██████▎   | 234326/371472 [7:36:57<10:28:44,  3.64it/s]
 63%|██���███▎   | 234327/371472 [7:36:57<10:44:08,  3.55it/s]
 63%|██████▎   | 234328/371472 [7:36:58<11:37:54,  3.28it/s]
 63%|██████▎   | 234329/371472 [7:36:58<11:05:12,  3.44it/s]
 63%|██████▎   | 234330/371472 [7:36:58<10:34:09,  3.60it/s]
 63%|██████▎   | 234331/371472 [7:36:59<10:03:36,  3.79it/s]
 63%|██████▎   | 234332/371472 [7:36:59<10:15:05,  3.72it/s]
 63%|██████▎   | 234333/371472 [7:36:59<10:25:52,  3.65it/s]
 63%|██████▎   | 234334/371472 [7:36:59<11:08:03,  3.42it/s]
 63%|██████▎   | 234335/371472 [7:37:00<11:36:37,  3.28it/s]
 63%|██████▎   | 234336/371472 [7:37:00<11:05:37,  3.43it/s]
 63%|██████▎   | 234337/371472 [7:37:00<10:55:13,  3.49it/s]
 63%|██████▎   | 234338/371472 [7:37:01<10:43:22,  3.55it/s]
 63%|██████▎   | 234339/371472 [7:37:01<10:24:06,  3.66it/s]
 63%|██████▎   | 234340/371472 [7:37:01<10:28:37,  3.64it/s]
                                                            
{'loss': 2.8558, 'learning_rate': 4.324215130685858e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234340/371472 [7:37:01<10:28:37,  3.64it/s]
 63%|██████▎   | 234341/371472 [7:37:01<10:37:16,  3.59it/s]
 63%|██████▎   | 234342/371472 [7:37:02<10:32:34,  3.61it/s]
 63%|██████▎   | 234343/371472 [7:37:02<11:06:17,  3.43it/s]
 63%|██████▎   | 234344/371472 [7:37:02<11:25:13,  3.34it/s]
 63%|██████▎   | 234345/371472 [7:37:03<11:02:47,  3.45it/s]
 63%|██████▎   | 234346/371472 [7:37:03<11:27:53,  3.32it/s]
 63%|██████▎   | 234347/371472 [7:37:03<11:02:55,  3.45it/s]
 63%|██████▎   | 234348/371472 [7:37:03<10:38:27,  3.58it/s]
 63%|██████▎   | 234349/371472 [7:37:04<10:13:24,  3.73it/s]
 63%|██████▎   | 234350/371472 [7:37:04<10:12:07,  3.73it/s]
 63%|██████▎   | 234351/371472 [7:37:04<10:05:32,  3.77it/s]
 63%|██████▎   | 234352/371472 [7:37:04<10:02:55,  3.79it/s]
 63%|██████▎   | 234353/371472 [7:37:05<10:11:03,  3.74it/s]
 63%|██████▎   | 234354/371472 [7:37:05<10:35:31,  3.60it/s]
 63%|██████▎   | 234355/371472 [7:37:05<10:15:38,  3.71it/s]
 63%|██████▎   | 234356/371472 [7:37:06<10:20:45,  3.68it/s]
 63%|██████▎   | 234357/371472 [7:37:06<10:57:13,  3.48it/s]
 63%|██████▎   | 234358/371472 [7:37:06<12:23:44,  3.07it/s]
 63%|██████▎   | 234359/371472 [7:37:07<11:52:22,  3.21it/s]
 63%|██████▎   | 234360/371472 [7:37:07<12:19:49,  3.09it/s]
                                                            
{'loss': 2.8363, 'learning_rate': 4.3237303109310696e-07, 'epoch': 10.09}
+
 63%|██████▎   | 234360/371472 [7:37:07<12:19:49,  3.09it/s]
 63%|██████▎   | 234361/371472 [7:37:07<11:40:07,  3.26it/s]
 63%|██████▎   | 234362/371472 [7:37:07<11:20:02,  3.36it/s]
 63%|██████▎   | 234363/371472 [7:37:08<11:03:16,  3.45it/s]
 63%|██████▎   | 234364/371472 [7:37:08<10:32:36,  3.61it/s]
 63%|██████▎   | 234365/371472 [7:37:08<10:47:21,  3.53it/s]
 63%|██████▎   | 234366/371472 [7:37:09<11:06:50,  3.43it/s]
 63%|██████▎   | 234367/371472 [7:37:09<10:38:58,  3.58it/s]
 63%|██████▎   | 234368/371472 [7:37:09<10:16:04,  3.71it/s]
 63%|██████▎   | 234369/371472 [7:37:09<10:35:35,  3.60it/s]
 63%|██████▎   | 234370/371472 [7:37:10<10:27:18,  3.64it/s]
 63%|██████▎   | 234371/371472 [7:37:10<9:57:16,  3.83it/s] 
 63%|██████▎   | 234372/371472 [7:37:10<9:59:48,  3.81it/s]
 63%|██████▎   | 234373/371472 [7:37:10<11:03:00,  3.45it/s]
 63%|██████▎   | 234374/371472 [7:37:11<10:39:44,  3.57it/s]
 63%|██████▎   | 234375/371472 [7:37:11<10:45:51,  3.54it/s]
 63%|██████▎   | 234376/371472 [7:37:11<10:20:39,  3.68it/s]
 63%|██████▎   | 234377/371472 [7:37:12<10:40:26,  3.57it/s]
 63%|██████▎   | 234378/371472 [7:37:12<10:44:24,  3.55it/s]
 63%|██████▎   | 234379/371472 [7:37:12<12:19:10,  3.09it/s]
 63%|██████▎   | 234380/371472 [7:37:13<11:32:38,  3.30it/s]
                                                            
{'loss': 2.9932, 'learning_rate': 4.32324549117628e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234380/371472 [7:37:13<11:32:38,  3.30it/s]
 63%|██████▎   | 234381/371472 [7:37:13<11:23:32,  3.34it/s]
 63%|██████▎   | 234382/371472 [7:37:13<11:12:09,  3.40it/s]
 63%|██████▎   | 234383/371472 [7:37:13<11:03:09,  3.45it/s]
 63%|██████▎   | 234384/371472 [7:37:14<10:32:03,  3.61it/s]
 63%|██████▎   | 234385/371472 [7:37:14<10:16:10,  3.71it/s]
 63%|██████▎   | 234386/371472 [7:37:14<10:06:58,  3.76it/s]
 63%|██████▎   | 234387/371472 [7:37:14<10:00:08,  3.81it/s]
 63%|██████▎   | 234388/371472 [7:37:15<10:07:45,  3.76it/s]
 63%|██████▎   | 234389/371472 [7:37:15<10:29:21,  3.63it/s]
 63%|██████▎   | 234390/371472 [7:37:15<10:32:14,  3.61it/s]
 63%|██████▎   | 234391/371472 [7:37:16<10:32:13,  3.61it/s]
 63%|██████▎   | 234392/371472 [7:37:16<10:15:01,  3.71it/s]
 63%|██████▎   | 234393/371472 [7:37:16<10:54:52,  3.49it/s]
 63%|██████▎   | 234394/371472 [7:37:16<11:11:54,  3.40it/s]
 63%|██████▎   | 234395/371472 [7:37:17<10:57:46,  3.47it/s]
 63%|██████▎   | 234396/371472 [7:37:17<10:44:35,  3.54it/s]
 63%|██████▎   | 234397/371472 [7:37:17<10:46:03,  3.54it/s]
 63%|██████▎   | 234398/371472 [7:37:18<10:50:52,  3.51it/s]
 63%|██████▎   | 234399/371472 [7:37:18<10:26:16,  3.65it/s]
 63%|██████▎   | 234400/371472 [7:37:18<10:43:00,  3.55it/s]
                                                            
{'loss': 2.9108, 'learning_rate': 4.3227606714214915e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234400/371472 [7:37:18<10:43:00,  3.55it/s]
 63%|██████▎   | 234401/371472 [7:37:18<10:54:07,  3.49it/s]
 63%|██████▎   | 234402/371472 [7:37:19<11:11:38,  3.40it/s]
 63%|██████▎   | 234403/371472 [7:37:19<11:24:43,  3.34it/s]
 63%|██████▎   | 234404/371472 [7:37:19<11:04:18,  3.44it/s]
 63%|██████▎   | 234405/371472 [7:37:20<10:35:39,  3.59it/s]
 63%|██████▎   | 234406/371472 [7:37:20<11:19:19,  3.36it/s]
 63%|██████▎   | 234407/371472 [7:37:20<10:59:36,  3.46it/s]
 63%|██████▎   | 234408/371472 [7:37:20<10:44:25,  3.54it/s]
 63%|██████▎   | 234409/371472 [7:37:21<10:23:05,  3.67it/s]
 63%|██████▎   | 234410/371472 [7:37:21<11:32:04,  3.30it/s]
 63%|██████▎   | 234411/371472 [7:37:21<11:31:09,  3.31it/s]
 63%|██████▎   | 234412/371472 [7:37:22<11:01:10,  3.45it/s]
 63%|██████▎   | 234413/371472 [7:37:22<11:33:31,  3.29it/s]
 63%|██████▎   | 234414/371472 [7:37:22<12:06:40,  3.14it/s]
 63%|██████▎   | 234415/371472 [7:37:23<11:58:11,  3.18it/s]
 63%|██████▎   | 234416/371472 [7:37:23<11:27:57,  3.32it/s]
 63%|██████▎   | 234417/371472 [7:37:23<11:12:42,  3.40it/s]
 63%|██████▎   | 234418/371472 [7:37:23<10:52:28,  3.50it/s]
 63%|██████▎   | 234419/371472 [7:37:24<10:42:41,  3.55it/s]
 63%|██████▎   | 234420/371472 [7:37:24<10:32:11,  3.61it/s]
                                                            
{'loss': 2.7449, 'learning_rate': 4.322275851666702e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234420/371472 [7:37:24<10:32:11,  3.61it/s]
 63%|██████▎   | 234421/371472 [7:37:24<10:16:53,  3.70it/s]
 63%|██████▎   | 234422/371472 [7:37:24<10:02:17,  3.79it/s]
 63%|██████▎   | 234423/371472 [7:37:25<9:48:49,  3.88it/s] 
 63%|██████▎   | 234424/371472 [7:37:25<10:14:42,  3.72it/s]
 63%|██████▎   | 234425/371472 [7:37:25<11:54:13,  3.20it/s]
 63%|██████▎   | 234426/371472 [7:37:26<11:03:37,  3.44it/s]
 63%|██████▎   | 234427/371472 [7:37:26<10:58:55,  3.47it/s]
 63%|██████▎   | 234428/371472 [7:37:26<10:56:54,  3.48it/s]
 63%|██████▎   | 234429/371472 [7:37:26<10:40:13,  3.57it/s]
 63%|██████▎   | 234430/371472 [7:37:27<11:25:48,  3.33it/s]
 63%|██████▎   | 234431/371472 [7:37:27<10:47:40,  3.53it/s]
 63%|██████▎   | 234432/371472 [7:37:27<10:46:14,  3.53it/s]
 63%|██████▎   | 234433/371472 [7:37:28<10:43:14,  3.55it/s]
 63%|██████▎   | 234434/371472 [7:37:28<10:29:15,  3.63it/s]
 63%|██████▎   | 234435/371472 [7:37:28<11:23:21,  3.34it/s]
 63%|██████▎   | 234436/371472 [7:37:29<11:15:42,  3.38it/s]
 63%|██████▎   | 234437/371472 [7:37:29<10:53:08,  3.50it/s]
 63%|██████▎   | 234438/371472 [7:37:29<11:01:16,  3.45it/s]
 63%|██████▎   | 234439/371472 [7:37:29<11:06:16,  3.43it/s]
 63%|██████▎   | 234440/371472 [7:37:30<10:45:44,  3.54it/s]
                                                            
{'loss': 2.7835, 'learning_rate': 4.321791031911914e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234440/371472 [7:37:30<10:45:44,  3.54it/s]
 63%|██████▎   | 234441/371472 [7:37:30<11:05:36,  3.43it/s]
 63%|██████▎   | 234442/371472 [7:37:30<11:13:58,  3.39it/s]
 63%|██████▎   | 234443/371472 [7:37:31<11:02:21,  3.45it/s]
 63%|██████▎   | 234444/371472 [7:37:31<10:45:10,  3.54it/s]
 63%|██████▎   | 234445/371472 [7:37:31<10:38:28,  3.58it/s]
 63%|██████▎   | 234446/371472 [7:37:31<11:26:26,  3.33it/s]
 63%|██████▎   | 234447/371472 [7:37:32<11:55:33,  3.19it/s]
 63%|██████▎   | 234448/371472 [7:37:32<11:17:01,  3.37it/s]
 63%|██████▎   | 234449/371472 [7:37:32<11:12:20,  3.40it/s]
 63%|██████▎   | 234450/371472 [7:37:33<11:00:43,  3.46it/s]
 63%|██████▎   | 234451/371472 [7:37:33<11:10:28,  3.41it/s]
 63%|██████▎   | 234452/371472 [7:37:33<10:43:03,  3.55it/s]
 63%|██████▎   | 234453/371472 [7:37:33<10:21:19,  3.68it/s]
 63%|██████▎   | 234454/371472 [7:37:34<10:23:31,  3.66it/s]
 63%|██████▎   | 234455/371472 [7:37:34<10:15:28,  3.71it/s]
 63%|██████▎   | 234456/371472 [7:37:34<13:09:53,  2.89it/s]
 63%|██████▎   | 234457/371472 [7:37:35<12:45:25,  2.98it/s]
 63%|██████▎   | 234458/371472 [7:37:35<12:28:30,  3.05it/s]
 63%|██████▎   | 234459/371472 [7:37:35<11:24:08,  3.34it/s]
 63%|██████▎   | 234460/371472 [7:37:36<11:26:11,  3.33it/s]
                                                            
{'loss': 2.7994, 'learning_rate': 4.321306212157124e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234460/371472 [7:37:36<11:26:11,  3.33it/s]
 63%|██████▎   | 234461/371472 [7:37:36<11:06:04,  3.43it/s]
 63%|██████▎   | 234462/371472 [7:37:36<10:55:00,  3.49it/s]
 63%|██████▎   | 234463/371472 [7:37:36<11:18:10,  3.37it/s]
 63%|██████▎   | 234464/371472 [7:37:37<10:56:08,  3.48it/s]
 63%|██████▎   | 234465/371472 [7:37:37<10:30:03,  3.62it/s]
 63%|██████▎   | 234466/371472 [7:37:37<10:12:25,  3.73it/s]
 63%|██████▎   | 234467/371472 [7:37:38<10:46:16,  3.53it/s]
 63%|██████▎   | 234468/371472 [7:37:38<10:57:25,  3.47it/s]
 63%|██████▎   | 234469/371472 [7:37:38<10:27:01,  3.64it/s]
 63%|██████▎   | 234470/371472 [7:37:38<10:26:53,  3.64it/s]
 63%|██████▎   | 234471/371472 [7:37:39<10:39:40,  3.57it/s]
 63%|██████▎   | 234472/371472 [7:37:39<10:26:02,  3.65it/s]
 63%|██████▎   | 234473/371472 [7:37:39<10:54:24,  3.49it/s]
 63%|██████▎   | 234474/371472 [7:37:40<11:08:09,  3.42it/s]
 63%|██████▎   | 234475/371472 [7:37:40<10:37:11,  3.58it/s]
 63%|██████▎   | 234476/371472 [7:37:40<10:22:06,  3.67it/s]
 63%|██████▎   | 234477/371472 [7:37:40<11:37:23,  3.27it/s]
 63%|██████▎   | 234478/371472 [7:37:41<11:07:27,  3.42it/s]
 63%|██████▎   | 234479/371472 [7:37:41<11:43:02,  3.25it/s]
 63%|██████▎   | 234480/371472 [7:37:41<11:06:50,  3.42it/s]
                                                            
{'loss': 2.8869, 'learning_rate': 4.320821392402336e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234480/371472 [7:37:41<11:06:50,  3.42it/s]
 63%|██████▎   | 234481/371472 [7:37:42<10:58:52,  3.47it/s]
 63%|██████▎   | 234482/371472 [7:37:42<10:51:58,  3.50it/s]
 63%|██████▎   | 234483/371472 [7:37:42<11:24:05,  3.34it/s]
 63%|██████▎   | 234484/371472 [7:37:43<11:51:38,  3.21it/s]
 63%|██████▎   | 234485/371472 [7:37:43<11:27:11,  3.32it/s]
 63%|██████▎   | 234486/371472 [7:37:43<11:00:27,  3.46it/s]
 63%|██████▎   | 234487/371472 [7:37:43<11:27:26,  3.32it/s]
 63%|██████▎   | 234488/371472 [7:37:44<11:57:24,  3.18it/s]
 63%|██████▎   | 234489/371472 [7:37:44<11:52:05,  3.21it/s]
 63%|██████▎   | 234490/371472 [7:37:44<11:35:16,  3.28it/s]
 63%|██████▎   | 234491/371472 [7:37:45<11:20:58,  3.35it/s]
 63%|██████▎   | 234492/371472 [7:37:45<11:36:08,  3.28it/s]
 63%|██████▎   | 234493/371472 [7:37:45<11:53:38,  3.20it/s]
 63%|██████▎   | 234494/371472 [7:37:46<11:27:55,  3.32it/s]
 63%|██████▎   | 234495/371472 [7:37:46<10:59:42,  3.46it/s]
 63%|██████▎   | 234496/371472 [7:37:46<12:04:31,  3.15it/s]
 63%|██████▎   | 234497/371472 [7:37:46<11:47:28,  3.23it/s]
 63%|██████▎   | 234498/371472 [7:37:47<13:11:53,  2.88it/s]
 63%|██████▎   | 234499/371472 [7:37:47<12:39:00,  3.01it/s]
 63%|██████▎   | 234500/371472 [7:37:47<11:51:35,  3.21it/s]
                                                            
{'loss': 2.8864, 'learning_rate': 4.3203365726475467e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234500/371472 [7:37:47<11:51:35,  3.21it/s]
 63%|██████▎   | 234501/371472 [7:37:48<11:15:44,  3.38it/s]
 63%|██████▎   | 234502/371472 [7:37:48<11:01:39,  3.45it/s]
 63%|██████▎   | 234503/371472 [7:37:48<10:35:32,  3.59it/s]
 63%|██████▎   | 234504/371472 [7:37:49<11:23:19,  3.34it/s]
 63%|██████▎   | 234505/371472 [7:37:49<11:18:33,  3.36it/s]
 63%|██████▎   | 234506/371472 [7:37:49<11:08:19,  3.42it/s]
 63%|██████▎   | 234507/371472 [7:37:49<10:52:47,  3.50it/s]
 63%|██████▎   | 234508/371472 [7:37:50<11:05:43,  3.43it/s]
 63%|██████▎   | 234509/371472 [7:37:50<10:50:31,  3.51it/s]
 63%|██████▎   | 234510/371472 [7:37:50<10:29:55,  3.62it/s]
 63%|██████▎   | 234511/371472 [7:37:51<10:31:48,  3.61it/s]
 63%|██████▎   | 234512/371472 [7:37:51<10:53:55,  3.49it/s]
 63%|██████▎   | 234513/371472 [7:37:51<10:45:15,  3.54it/s]
 63%|██████▎   | 234514/371472 [7:37:51<10:44:41,  3.54it/s]
 63%|██████▎   | 234515/371472 [7:37:52<11:03:51,  3.44it/s]
 63%|██████▎   | 234516/371472 [7:37:52<11:05:40,  3.43it/s]
 63%|██████▎   | 234517/371472 [7:37:52<10:52:35,  3.50it/s]
 63%|██████▎   | 234518/371472 [7:37:53<12:04:25,  3.15it/s]
 63%|██████▎   | 234519/371472 [7:37:53<11:42:44,  3.25it/s]
 63%|██████▎   | 234520/371472 [7:37:53<11:16:49,  3.37it/s]
                                                            
{'loss': 3.0242, 'learning_rate': 4.319851752892758e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234520/371472 [7:37:53<11:16:49,  3.37it/s]
 63%|██████▎   | 234521/371472 [7:37:54<10:47:46,  3.52it/s]
 63%|██████▎   | 234522/371472 [7:37:54<10:39:05,  3.57it/s]
 63%|██████▎   | 234523/371472 [7:37:54<10:14:27,  3.71it/s]
 63%|██████▎   | 234524/371472 [7:37:54<10:18:35,  3.69it/s]
 63%|██████▎   | 234525/371472 [7:37:55<10:15:06,  3.71it/s]
 63%|██████▎   | 234526/371472 [7:37:55<10:24:30,  3.65it/s]
 63%|██████▎   | 234527/371472 [7:37:55<10:03:54,  3.78it/s]
 63%|██████▎   | 234528/371472 [7:37:55<10:47:59,  3.52it/s]
 63%|██████▎   | 234529/371472 [7:37:56<10:43:12,  3.55it/s]
 63%|██████▎   | 234530/371472 [7:37:56<12:16:55,  3.10it/s]
 63%|██████▎   | 234531/371472 [7:37:56<12:42:29,  2.99it/s]
 63%|██████▎   | 234532/371472 [7:37:57<12:06:42,  3.14it/s]
 63%|██████▎   | 234533/371472 [7:37:57<11:50:35,  3.21it/s]
 63%|██████▎   | 234534/371472 [7:37:57<11:16:23,  3.37it/s]
 63%|██████▎   | 234535/371472 [7:37:58<10:54:30,  3.49it/s]
 63%|██████▎   | 234536/371472 [7:37:58<11:15:27,  3.38it/s]
 63%|██████▎   | 234537/371472 [7:37:58<10:59:19,  3.46it/s]
 63%|██████▎   | 234538/371472 [7:37:58<10:25:39,  3.65it/s]
 63%|██████▎   | 234539/371472 [7:37:59<10:07:22,  3.76it/s]
 63%|██████▎   | 234540/371472 [7:37:59<10:20:14,  3.68it/s]
                                                            
{'loss': 2.8927, 'learning_rate': 4.3193669331379686e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234540/371472 [7:37:59<10:20:14,  3.68it/s]
 63%|██████▎   | 234541/371472 [7:37:59<10:28:57,  3.63it/s]
 63%|██████▎   | 234542/371472 [7:37:59<10:18:27,  3.69it/s]
 63%|██████▎   | 234543/371472 [7:38:00<11:15:14,  3.38it/s]
 63%|██████▎   | 234544/371472 [7:38:00<10:38:40,  3.57it/s]
 63%|██████▎   | 234545/371472 [7:38:00<11:26:49,  3.32it/s]
 63%|██████▎   | 234546/371472 [7:38:01<10:52:46,  3.50it/s]
 63%|██████▎   | 234547/371472 [7:38:01<10:59:32,  3.46it/s]
 63%|██████▎   | 234548/371472 [7:38:01<10:42:39,  3.55it/s]
 63%|██████▎   | 234549/371472 [7:38:02<11:34:50,  3.28it/s]
 63%|██████▎   | 234550/371472 [7:38:02<11:40:39,  3.26it/s]
 63%|██████▎   | 234551/371472 [7:38:02<11:09:35,  3.41it/s]
 63%|██████▎   | 234552/371472 [7:38:02<11:08:20,  3.41it/s]
 63%|██████▎   | 234553/371472 [7:38:03<12:30:15,  3.04it/s]
 63%|██████▎   | 234554/371472 [7:38:03<11:22:01,  3.35it/s]
 63%|██████▎   | 234555/371472 [7:38:03<10:42:37,  3.55it/s]
 63%|██████▎   | 234556/371472 [7:38:04<10:44:42,  3.54it/s]
 63%|██████▎   | 234557/371472 [7:38:04<11:00:54,  3.45it/s]
 63%|██████▎   | 234558/371472 [7:38:04<10:40:42,  3.56it/s]
 63%|██████▎   | 234559/371472 [7:38:04<10:17:02,  3.70it/s]
 63%|██████▎   | 234560/371472 [7:38:05<10:34:07,  3.60it/s]
                                                            
{'loss': 3.0053, 'learning_rate': 4.3188821133831794e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234560/371472 [7:38:05<10:34:07,  3.60it/s]
 63%|██████▎   | 234561/371472 [7:38:05<10:17:01,  3.70it/s]
 63%|██████▎   | 234562/371472 [7:38:05<10:19:06,  3.69it/s]
 63%|██████▎   | 234563/371472 [7:38:06<10:43:20,  3.55it/s]
 63%|██████▎   | 234564/371472 [7:38:06<10:59:43,  3.46it/s]
 63%|██████▎   | 234565/371472 [7:38:06<11:03:07,  3.44it/s]
 63%|██████▎   | 234566/371472 [7:38:06<10:48:53,  3.52it/s]
 63%|██████▎   | 234567/371472 [7:38:07<10:45:13,  3.54it/s]
 63%|██████▎   | 234568/371472 [7:38:07<11:41:57,  3.25it/s]
 63%|██████▎   | 234569/371472 [7:38:07<11:15:16,  3.38it/s]
 63%|██████▎   | 234570/371472 [7:38:08<10:46:57,  3.53it/s]
 63%|██████▎   | 234571/371472 [7:38:08<10:25:18,  3.65it/s]
 63%|██████▎   | 234572/371472 [7:38:08<10:29:38,  3.62it/s]
 63%|██████▎   | 234573/371472 [7:38:08<10:21:11,  3.67it/s]
 63%|██████▎   | 234574/371472 [7:38:09<10:16:28,  3.70it/s]
 63%|██████▎   | 234575/371472 [7:38:09<10:53:25,  3.49it/s]
 63%|██████▎   | 234576/371472 [7:38:09<10:42:48,  3.55it/s]
 63%|██████▎   | 234577/371472 [7:38:10<11:15:14,  3.38it/s]
 63%|██████▎   | 234578/371472 [7:38:10<10:45:44,  3.53it/s]
 63%|██████▎   | 234579/371472 [7:38:10<10:16:12,  3.70it/s]
 63%|██████▎   | 234580/371472 [7:38:10<10:17:04,  3.70it/s]
                                                            
{'loss': 2.7759, 'learning_rate': 4.318397293628391e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234580/371472 [7:38:10<10:17:04,  3.70it/s]
 63%|██████▎   | 234581/371472 [7:38:11<10:44:13,  3.54it/s]
 63%|██████▎   | 234582/371472 [7:38:11<10:39:20,  3.57it/s]
 63%|██████▎   | 234583/371472 [7:38:11<10:37:41,  3.58it/s]
 63%|██████▎   | 234584/371472 [7:38:11<10:21:02,  3.67it/s]
 63%|██████▎   | 234585/371472 [7:38:12<10:20:47,  3.68it/s]
 63%|██████▎   | 234586/371472 [7:38:12<10:16:28,  3.70it/s]
 63%|██████▎   | 234587/371472 [7:38:12<11:29:09,  3.31it/s]
 63%|██████▎   | 234588/371472 [7:38:13<11:18:16,  3.36it/s]
 63%|██████▎   | 234589/371472 [7:38:13<10:56:47,  3.47it/s]
 63%|██████▎   | 234590/371472 [7:38:13<10:39:05,  3.57it/s]
 63%|██████▎   | 234591/371472 [7:38:13<10:09:54,  3.74it/s]
 63%|██████▎   | 234592/371472 [7:38:14<9:59:16,  3.81it/s] 
 63%|██████▎   | 234593/371472 [7:38:14<10:39:38,  3.57it/s]
 63%|██████▎   | 234594/371472 [7:38:14<10:25:00,  3.65it/s]
 63%|██████▎   | 234595/371472 [7:38:15<11:15:17,  3.38it/s]
 63%|██████▎   | 234596/371472 [7:38:15<10:50:20,  3.51it/s]
 63%|██████▎   | 234597/371472 [7:38:15<10:55:01,  3.48it/s]
 63%|██████▎   | 234598/371472 [7:38:16<11:29:32,  3.31it/s]
 63%|██████▎   | 234599/371472 [7:38:16<12:05:19,  3.15it/s]
 63%|██████▎   | 234600/371472 [7:38:16<11:23:29,  3.34it/s]
                                                            
{'loss': 2.8928, 'learning_rate': 4.3179124738736013e-07, 'epoch': 10.1}
+
 63%|██████▎   | 234600/371472 [7:38:16<11:23:29,  3.34it/s]
 63%|██████▎   | 234601/371472 [7:38:16<11:01:33,  3.45it/s]
 63%|██████▎   | 234602/371472 [7:38:17<11:06:13,  3.42it/s]
 63%|██████▎   | 234603/371472 [7:38:17<10:49:50,  3.51it/s]
 63%|██████▎   | 234604/371472 [7:38:17<10:35:48,  3.59it/s]
 63%|██████▎   | 234605/371472 [7:38:18<10:29:38,  3.62it/s]
 63%|██████▎   | 234606/371472 [7:38:18<10:06:50,  3.76it/s]
 63%|██████▎   | 234607/371472 [7:38:18<10:36:05,  3.59it/s]
 63%|██████▎   | 234608/371472 [7:38:18<10:10:30,  3.74it/s]
 63%|██████▎   | 234609/371472 [7:38:19<10:24:20,  3.65it/s]
 63%|██████▎   | 234610/371472 [7:38:19<10:19:15,  3.68it/s]
 63%|██████▎   | 234611/371472 [7:38:19<10:59:37,  3.46it/s]
 63%|██████▎   | 234612/371472 [7:38:19<10:27:24,  3.64it/s]
 63%|██████▎   | 234613/371472 [7:38:20<10:20:29,  3.68it/s]
 63%|██████▎   | 234614/371472 [7:38:20<10:52:56,  3.49it/s]
 63%|██████▎   | 234615/371472 [7:38:20<10:46:48,  3.53it/s]
 63%|██████▎   | 234616/371472 [7:38:21<10:25:31,  3.65it/s]
 63%|██████▎   | 234617/371472 [7:38:21<10:26:05,  3.64it/s]
 63%|██████▎   | 234618/371472 [7:38:21<10:37:47,  3.58it/s]
 63%|██████▎   | 234619/371472 [7:38:21<10:11:40,  3.73it/s]
 63%|██████▎   | 234620/371472 [7:38:22<10:09:26,  3.74it/s]
                                                            
{'loss': 3.0115, 'learning_rate': 4.317427654118813e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234620/371472 [7:38:22<10:09:26,  3.74it/s]
 63%|██████▎   | 234621/371472 [7:38:22<10:32:35,  3.61it/s]
 63%|██████▎   | 234622/371472 [7:38:22<10:51:23,  3.50it/s]
 63%|██████▎   | 234623/371472 [7:38:22<10:22:39,  3.66it/s]
 63%|██████▎   | 234624/371472 [7:38:23<10:37:29,  3.58it/s]
 63%|██████▎   | 234625/371472 [7:38:23<10:38:08,  3.57it/s]
 63%|██████▎   | 234626/371472 [7:38:23<10:22:17,  3.67it/s]
 63%|██████▎   | 234627/371472 [7:38:24<11:39:55,  3.26it/s]
 63%|██████▎   | 234628/371472 [7:38:24<11:48:37,  3.22it/s]
 63%|██████▎   | 234629/371472 [7:38:24<11:36:55,  3.27it/s]
 63%|██████▎   | 234630/371472 [7:38:25<11:31:13,  3.30it/s]
 63%|██████▎   | 234631/371472 [7:38:25<11:33:42,  3.29it/s]
 63%|██████▎   | 234632/371472 [7:38:25<11:32:37,  3.29it/s]
 63%|██████▎   | 234633/371472 [7:38:25<10:54:50,  3.48it/s]
 63%|██████▎   | 234634/371472 [7:38:26<10:27:09,  3.64it/s]
 63%|██████▎   | 234635/371472 [7:38:26<10:58:44,  3.46it/s]
 63%|██████▎   | 234636/371472 [7:38:26<11:25:58,  3.32it/s]
 63%|██████▎   | 234637/371472 [7:38:27<11:10:42,  3.40it/s]
 63%|██████▎   | 234638/371472 [7:38:27<11:29:23,  3.31it/s]
 63%|██████▎   | 234639/371472 [7:38:27<11:02:51,  3.44it/s]
 63%|██████▎   | 234640/371472 [7:38:27<10:55:31,  3.48it/s]
                                                            
{'loss': 2.843, 'learning_rate': 4.316942834364024e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234640/371472 [7:38:27<10:55:31,  3.48it/s]
 63%|██████▎   | 234641/371472 [7:38:28<10:55:33,  3.48it/s]
 63%|██████▎   | 234642/371472 [7:38:28<11:32:39,  3.29it/s]
 63%|██████▎   | 234643/371472 [7:38:28<11:50:30,  3.21it/s]
 63%|██████▎   | 234644/371472 [7:38:29<11:20:08,  3.35it/s]
 63%|██████▎   | 234645/371472 [7:38:29<11:04:57,  3.43it/s]
 63%|██████▎   | 234646/371472 [7:38:29<10:26:00,  3.64it/s]
 63%|██████▎   | 234647/371472 [7:38:29<10:03:31,  3.78it/s]
 63%|██████▎   | 234648/371472 [7:38:30<10:20:05,  3.68it/s]
 63%|██████▎   | 234649/371472 [7:38:30<10:03:20,  3.78it/s]
 63%|██████▎   | 234650/371472 [7:38:30<9:39:42,  3.93it/s] 
 63%|██████▎   | 234651/371472 [7:38:31<10:37:27,  3.58it/s]
 63%|██████▎   | 234652/371472 [7:38:31<10:58:04,  3.47it/s]
 63%|██████▎   | 234653/371472 [7:38:31<11:02:58,  3.44it/s]
 63%|██████▎   | 234654/371472 [7:38:31<10:53:13,  3.49it/s]
 63%|██████▎   | 234655/371472 [7:38:32<10:29:25,  3.62it/s]
 63%|██████▎   | 234656/371472 [7:38:32<10:44:42,  3.54it/s]
 63%|██████▎   | 234657/371472 [7:38:32<10:39:43,  3.56it/s]
 63%|██████▎   | 234658/371472 [7:38:33<10:14:07,  3.71it/s]
 63%|██████▎   | 234659/371472 [7:38:33<10:05:43,  3.76it/s]
 63%|██████▎   | 234660/371472 [7:38:33<10:02:20,  3.79it/s]
                                                            
{'loss': 2.8304, 'learning_rate': 4.316458014609235e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234660/371472 [7:38:33<10:02:20,  3.79it/s]
 63%|██████▎   | 234661/371472 [7:38:33<10:11:56,  3.73it/s]
 63%|██████▎   | 234662/371472 [7:38:34<10:56:12,  3.47it/s]
 63%|██████▎   | 234663/371472 [7:38:34<11:20:09,  3.35it/s]
 63%|██████▎   | 234664/371472 [7:38:34<10:49:33,  3.51it/s]
 63%|██████▎   | 234665/371472 [7:38:34<10:24:06,  3.65it/s]
 63%|██████▎   | 234666/371472 [7:38:35<10:09:17,  3.74it/s]
 63%|██████▎   | 234667/371472 [7:38:35<10:06:08,  3.76it/s]
 63%|██████▎   | 234668/371472 [7:38:35<9:53:51,  3.84it/s] 
 63%|██████▎   | 234669/371472 [7:38:36<10:00:14,  3.80it/s]
 63%|██████▎   | 234670/371472 [7:38:36<10:04:52,  3.77it/s]
 63%|██████▎   | 234671/371472 [7:38:36<9:48:48,  3.87it/s] 
 63%|██████▎   | 234672/371472 [7:38:36<10:03:16,  3.78it/s]
 63%|██████▎   | 234673/371472 [7:38:37<10:08:32,  3.75it/s]
 63%|██████▎   | 234674/371472 [7:38:37<10:54:03,  3.49it/s]
 63%|██████▎   | 234675/371472 [7:38:37<10:45:17,  3.53it/s]
 63%|██████▎   | 234676/371472 [7:38:37<10:55:45,  3.48it/s]
 63%|██████▎   | 234677/371472 [7:38:38<10:26:38,  3.64it/s]
 63%|██████▎   | 234678/371472 [7:38:38<10:04:51,  3.77it/s]
 63%|██████▎   | 234679/371472 [7:38:38<11:07:03,  3.42it/s]
 63%|██████▎   | 234680/371472 [7:38:39<10:59:40,  3.46it/s]
                                                            
{'loss': 3.1166, 'learning_rate': 4.315973194854446e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234680/371472 [7:38:39<10:59:40,  3.46it/s]
 63%|██████▎   | 234681/371472 [7:38:39<10:47:38,  3.52it/s]
 63%|██████▎   | 234682/371472 [7:38:39<11:24:11,  3.33it/s]
 63%|██████▎   | 234683/371472 [7:38:39<10:56:59,  3.47it/s]
 63%|██████▎   | 234684/371472 [7:38:40<10:48:53,  3.51it/s]
 63%|██████▎   | 234685/371472 [7:38:40<10:31:17,  3.61it/s]
 63%|████���█▎   | 234686/371472 [7:38:40<10:54:32,  3.48it/s]
 63%|██████▎   | 234687/371472 [7:38:41<10:32:14,  3.61it/s]
 63%|██████▎   | 234688/371472 [7:38:41<10:33:47,  3.60it/s]
 63%|██████▎   | 234689/371472 [7:38:41<11:09:58,  3.40it/s]
 63%|██████▎   | 234690/371472 [7:38:41<10:44:06,  3.54it/s]
 63%|██████▎   | 234691/371472 [7:38:42<11:33:00,  3.29it/s]
 63%|██████▎   | 234692/371472 [7:38:42<11:21:45,  3.34it/s]
 63%|██████▎   | 234693/371472 [7:38:42<10:55:03,  3.48it/s]
 63%|██████▎   | 234694/371472 [7:38:43<10:35:18,  3.59it/s]
 63%|██████▎   | 234695/371472 [7:38:43<10:17:37,  3.69it/s]
 63%|██████▎   | 234696/371472 [7:38:43<10:21:09,  3.67it/s]
 63%|██████▎   | 234697/371472 [7:38:43<10:08:54,  3.74it/s]
 63%|██████▎   | 234698/371472 [7:38:44<10:02:05,  3.79it/s]
 63%|██████▎   | 234699/371472 [7:38:44<10:10:26,  3.73it/s]
 63%|██████▎   | 234700/371472 [7:38:44<10:05:57,  3.76it/s]
                                                            
{'loss': 2.8839, 'learning_rate': 4.3154883750996575e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234700/371472 [7:38:44<10:05:57,  3.76it/s]
 63%|██████▎   | 234701/371472 [7:38:44<10:28:58,  3.62it/s]
 63%|██████▎   | 234702/371472 [7:38:45<10:27:41,  3.63it/s]
 63%|██████▎   | 234703/371472 [7:38:45<11:23:58,  3.33it/s]
 63%|██████▎   | 234704/371472 [7:38:45<11:52:52,  3.20it/s]
 63%|██████▎   | 234705/371472 [7:38:46<11:35:07,  3.28it/s]
 63%|██████▎   | 234706/371472 [7:38:46<10:50:34,  3.50it/s]
 63%|██████▎   | 234707/371472 [7:38:46<10:21:34,  3.67it/s]
 63%|██████▎   | 234708/371472 [7:38:47<10:37:50,  3.57it/s]
 63%|██████▎   | 234709/371472 [7:38:47<10:44:44,  3.54it/s]
 63%|██████▎   | 234710/371472 [7:38:47<10:29:44,  3.62it/s]
 63%|██████▎   | 234711/371472 [7:38:47<10:01:33,  3.79it/s]
 63%|██████▎   | 234712/371472 [7:38:48<9:59:58,  3.80it/s] 
 63%|██████▎   | 234713/371472 [7:38:48<9:50:47,  3.86it/s]
 63%|██████▎   | 234714/371472 [7:38:48<9:42:59,  3.91it/s]
 63%|██████▎   | 234715/371472 [7:38:48<9:59:29,  3.80it/s]
 63%|██████▎   | 234716/371472 [7:38:49<9:49:32,  3.87it/s]
 63%|██████▎   | 234717/371472 [7:38:49<9:43:21,  3.91it/s]
 63%|██████▎   | 234718/371472 [7:38:49<9:51:21,  3.85it/s]
 63%|██████▎   | 234719/371472 [7:38:49<9:45:10,  3.89it/s]
 63%|██████▎   | 234720/371472 [7:38:50<10:31:44,  3.61it/s]
                                                            
{'loss': 2.9041, 'learning_rate': 4.3150035553448677e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234720/371472 [7:38:50<10:31:44,  3.61it/s]
 63%|██████▎   | 234721/371472 [7:38:50<10:25:27,  3.64it/s]
 63%|██████▎   | 234722/371472 [7:38:50<10:12:57,  3.72it/s]
 63%|██████▎   | 234723/371472 [7:38:50<10:29:51,  3.62it/s]
 63%|██████▎   | 234724/371472 [7:38:51<11:21:11,  3.35it/s]
 63%|██████▎   | 234725/371472 [7:38:51<10:48:45,  3.51it/s]
 63%|██████▎   | 234726/371472 [7:38:51<10:43:58,  3.54it/s]
 63%|██████▎   | 234727/371472 [7:38:52<10:25:53,  3.64it/s]
 63%|██████▎   | 234728/371472 [7:38:52<10:08:59,  3.74it/s]
 63%|██████▎   | 234729/371472 [7:38:52<10:17:55,  3.69it/s]
 63%|██████▎   | 234730/371472 [7:38:52<10:11:46,  3.73it/s]
 63%|██████▎   | 234731/371472 [7:38:53<10:19:38,  3.68it/s]
 63%|██████▎   | 234732/371472 [7:38:53<10:49:43,  3.51it/s]
 63%|██████▎   | 234733/371472 [7:38:53<10:41:48,  3.55it/s]
 63%|██████▎   | 234734/371472 [7:38:54<11:01:45,  3.44it/s]
 63%|██████▎   | 234735/371472 [7:38:54<11:32:49,  3.29it/s]
 63%|██████▎   | 234736/371472 [7:38:54<11:13:02,  3.39it/s]
 63%|██████▎   | 234737/371472 [7:38:54<10:47:54,  3.52it/s]
 63%|██████▎   | 234738/371472 [7:38:55<10:32:51,  3.60it/s]
 63%|██████▎   | 234739/371472 [7:38:55<10:39:53,  3.56it/s]
 63%|██████▎   | 234740/371472 [7:38:55<10:16:18,  3.70it/s]
                                                            
{'loss': 2.7842, 'learning_rate': 4.3145187355900795e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234740/371472 [7:38:55<10:16:18,  3.70it/s]
 63%|██████▎   | 234741/371472 [7:38:56<9:58:56,  3.80it/s] 
 63%|██████▎   | 234742/371472 [7:38:56<11:45:34,  3.23it/s]
 63%|██████▎   | 234743/371472 [7:38:56<11:00:38,  3.45it/s]
 63%|██████▎   | 234744/371472 [7:38:57<11:42:17,  3.24it/s]
 63%|██████▎   | 234745/371472 [7:38:57<11:56:28,  3.18it/s]
 63%|█���████▎   | 234746/371472 [7:38:57<11:43:16,  3.24it/s]
 63%|██████▎   | 234747/371472 [7:38:57<11:22:05,  3.34it/s]
 63%|██████▎   | 234748/371472 [7:38:58<11:06:09,  3.42it/s]
 63%|██████▎   | 234749/371472 [7:38:58<11:52:42,  3.20it/s]
 63%|██████▎   | 234750/371472 [7:38:58<11:06:35,  3.42it/s]
 63%|██████▎   | 234751/371472 [7:38:59<12:19:55,  3.08it/s]
 63%|██████▎   | 234752/371472 [7:38:59<11:53:18,  3.19it/s]
 63%|██████▎   | 234753/371472 [7:38:59<11:10:06,  3.40it/s]
 63%|██████▎   | 234754/371472 [7:39:00<11:24:02,  3.33it/s]
 63%|██████▎   | 234755/371472 [7:39:00<10:45:44,  3.53it/s]
 63%|██████▎   | 234756/371472 [7:39:00<10:26:21,  3.64it/s]
 63%|██████▎   | 234757/371472 [7:39:00<10:33:06,  3.60it/s]
 63%|██████▎   | 234758/371472 [7:39:01<10:19:48,  3.68it/s]
 63%|██████▎   | 234759/371472 [7:39:01<10:53:01,  3.49it/s]
 63%|██████▎   | 234760/371472 [7:39:01<10:36:31,  3.58it/s]
                                                            
{'loss': 2.9759, 'learning_rate': 4.31403391583529e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234760/371472 [7:39:01<10:36:31,  3.58it/s]
 63%|██████▎   | 234761/371472 [7:39:02<11:02:42,  3.44it/s]
 63%|██████▎   | 234762/371472 [7:39:02<10:46:49,  3.52it/s]
 63%|██████▎   | 234763/371472 [7:39:02<10:50:50,  3.50it/s]
 63%|██████▎   | 234764/371472 [7:39:02<10:27:12,  3.63it/s]
 63%|██████▎   | 234765/371472 [7:39:03<10:28:53,  3.62it/s]
 63%|██████▎   | 234766/371472 [7:39:03<10:05:51,  3.76it/s]
 63%|██████▎   | 234767/371472 [7:39:03<10:24:22,  3.65it/s]
 63%|██████▎   | 234768/371472 [7:39:03<10:49:36,  3.51it/s]
 63%|██████▎   | 234769/371472 [7:39:04<10:45:56,  3.53it/s]
 63%|██████▎   | 234770/371472 [7:39:04<10:31:47,  3.61it/s]
 63%|██████▎   | 234771/371472 [7:39:04<10:29:37,  3.62it/s]
 63%|██████▎   | 234772/371472 [7:39:05<10:48:30,  3.51it/s]
 63%|██████▎   | 234773/371472 [7:39:05<10:31:35,  3.61it/s]
 63%|██████▎   | 234774/371472 [7:39:05<10:44:10,  3.54it/s]
 63%|██████▎   | 234775/371472 [7:39:05<10:21:44,  3.66it/s]
 63%|██████▎   | 234776/371472 [7:39:06<11:07:56,  3.41it/s]
 63%|██████▎   | 234777/371472 [7:39:06<10:46:27,  3.52it/s]
 63%|██████▎   | 234778/371472 [7:39:06<10:36:49,  3.58it/s]
 63%|██████▎   | 234779/371472 [7:39:07<10:52:29,  3.49it/s]
 63%|██████▎   | 234780/371472 [7:39:07<11:06:18,  3.42it/s]
                                                            
{'loss': 2.8695, 'learning_rate': 4.3135490960805015e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234780/371472 [7:39:07<11:06:18,  3.42it/s]
 63%|██████▎   | 234781/371472 [7:39:07<10:51:55,  3.49it/s]
 63%|██████▎   | 234782/371472 [7:39:07<10:51:20,  3.50it/s]
 63%|██████▎   | 234783/371472 [7:39:08<10:58:51,  3.46it/s]
 63%|██████▎   | 234784/371472 [7:39:08<11:10:49,  3.40it/s]
 63%|██████▎   | 234785/371472 [7:39:08<10:58:29,  3.46it/s]
 63%|██████▎   | 234786/371472 [7:39:09<10:42:29,  3.55it/s]
 63%|██████▎   | 234787/371472 [7:39:09<10:18:07,  3.69it/s]
 63%|██████▎   | 234788/371472 [7:39:09<10:28:42,  3.62it/s]
 63%|██████▎   | 234789/371472 [7:39:09<10:15:41,  3.70it/s]
 63%|██████▎   | 234790/371472 [7:39:10<11:59:45,  3.16it/s]
 63%|██████▎   | 234791/371472 [7:39:10<11:22:58,  3.34it/s]
 63%|██████▎   | 234792/371472 [7:39:10<10:51:41,  3.50it/s]
 63%|██████▎   | 234793/371472 [7:39:11<10:46:23,  3.52it/s]
 63%|██████▎   | 234794/371472 [7:39:11<10:53:16,  3.49it/s]
 63%|██████▎   | 234795/371472 [7:39:11<11:59:29,  3.17it/s]
 63%|██████▎   | 234796/371472 [7:39:12<11:29:59,  3.30it/s]
 63%|██████▎   | 234797/371472 [7:39:12<11:24:55,  3.33it/s]
 63%|██████▎   | 234798/371472 [7:39:12<10:46:30,  3.52it/s]
 63%|██████▎   | 234799/371472 [7:39:12<10:30:44,  3.61it/s]
 63%|██████▎   | 234800/371472 [7:39:13<10:09:34,  3.74it/s]
                                                            
{'loss': 2.9111, 'learning_rate': 4.3130642763257116e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234800/371472 [7:39:13<10:09:34,  3.74it/s]
 63%|██████▎   | 234801/371472 [7:39:13<10:14:25,  3.71it/s]
 63%|██████▎   | 234802/371472 [7:39:13<10:07:40,  3.75it/s]
 63%|██████▎   | 234803/371472 [7:39:13<10:45:22,  3.53it/s]
 63%|██████▎   | 234804/371472 [7:39:14<10:30:25,  3.61it/s]
 63%|██████▎   | 234805/371472 [7:39:14<11:01:42,  3.44it/s]
 63%|██████▎   | 234806/371472 [7:39:14<10:44:47,  3.53it/s]
 63%|██████▎   | 234807/371472 [7:39:15<10:38:03,  3.57it/s]
 63%|██████▎   | 234808/371472 [7:39:15<10:41:05,  3.55it/s]
 63%|██████▎   | 234809/371472 [7:39:15<10:51:04,  3.50it/s]
 63%|██████▎   | 234810/371472 [7:39:15<11:31:44,  3.29it/s]
 63%|██████▎   | 234811/371472 [7:39:16<11:31:09,  3.30it/s]
 63%|██████▎   | 234812/371472 [7:39:16<10:55:53,  3.47it/s]
 63%|██████▎   | 234813/371472 [7:39:16<10:40:21,  3.56it/s]
 63%|██████▎   | 234814/371472 [7:39:17<11:02:06,  3.44it/s]
 63%|██████▎   | 234815/371472 [7:39:17<11:24:22,  3.33it/s]
 63%|██████▎   | 234816/371472 [7:39:17<10:49:44,  3.51it/s]
 63%|██████▎   | 234817/371472 [7:39:17<10:57:15,  3.47it/s]
 63%|██████▎   | 234818/371472 [7:39:18<10:43:26,  3.54it/s]
 63%|██████▎   | 234819/371472 [7:39:18<10:48:46,  3.51it/s]
 63%|██████▎   | 234820/371472 [7:39:18<10:18:25,  3.68it/s]
                                                            
{'loss': 2.7276, 'learning_rate': 4.312579456570924e-07, 'epoch': 10.11}
+
 63%|██████▎   | 234820/371472 [7:39:18<10:18:25,  3.68it/s]
 63%|██████▎   | 234821/371472 [7:39:19<10:03:49,  3.77it/s]
 63%|██████▎   | 234822/371472 [7:39:19<9:52:53,  3.84it/s] 
 63%|██████▎   | 234823/371472 [7:39:19<10:14:24,  3.71it/s]
 63%|██████▎   | 234824/371472 [7:39:19<10:38:26,  3.57it/s]
 63%|██████▎   | 234825/371472 [7:39:20<10:36:42,  3.58it/s]
 63%|██████▎   | 234826/371472 [7:39:20<10:40:32,  3.56it/s]
 63%|██████▎   | 234827/371472 [7:39:20<10:43:02,  3.54it/s]
 63%|██████▎   | 234828/371472 [7:39:20<10:39:30,  3.56it/s]
 63%|██████▎   | 234829/371472 [7:39:21<10:58:19,  3.46it/s]
 63%|██████▎   | 234830/371472 [7:39:21<11:10:00,  3.40it/s]
 63%|██████▎   | 234831/371472 [7:39:21<10:41:00,  3.55it/s]
 63%|██████▎   | 234832/371472 [7:39:22<10:22:34,  3.66it/s]
 63%|██████▎   | 234833/371472 [7:39:22<10:15:52,  3.70it/s]
 63%|██████▎   | 234834/371472 [7:39:22<10:59:34,  3.45it/s]
 63%|██████▎   | 234835/371472 [7:39:22<10:31:21,  3.61it/s]
 63%|██████▎   | 234836/371472 [7:39:23<10:09:29,  3.74it/s]
 63%|██████▎   | 234837/371472 [7:39:23<10:49:34,  3.51it/s]
 63%|██████▎   | 234838/371472 [7:39:23<11:26:45,  3.32it/s]
 63%|██████▎   | 234839/371472 [7:39:24<11:36:33,  3.27it/s]
 63%|██████▎   | 234840/371472 [7:39:24<11:11:09,  3.39it/s]
                                                            
{'loss': 3.0737, 'learning_rate': 4.312094636816134e-07, 'epoch': 10.12}
+
 63%|██████▎   | 234840/371472 [7:39:24<11:11:09,  3.39it/s]
 63%|██████▎   | 234841/371472 [7:39:24<11:19:35,  3.35it/s]
 63%|██████▎   | 234842/371472 [7:39:25<12:03:26,  3.15it/s]
 63%|██████▎   | 234843/371472 [7:39:25<11:39:18,  3.26it/s]
 63%|██████▎   | 234844/371472 [7:39:25<13:27:51,  2.82it/s]
 63%|██████▎   | 234845/371472 [7:39:26<12:17:56,  3.09it/s]
 63%|██████▎   | 234846/371472 [7:39:26<11:55:01,  3.18it/s]
 63%|██████▎   | 234847/371472 [7:39:26<11:32:54,  3.29it/s]
 63%|██████▎   | 234848/371472 [7:39:26<11:31:42,  3.29it/s]
 63%|██████▎   | 234849/371472 [7:39:27<11:22:12,  3.34it/s]
 63%|██████▎   | 234850/371472 [7:39:27<11:36:38,  3.27it/s]
 63%|██████▎   | 234851/371472 [7:39:27<11:29:04,  3.30it/s]
 63%|██████▎   | 234852/371472 [7:39:28<11:51:33,  3.20it/s]
 63%|██████▎   | 234853/371472 [7:39:28<12:07:10,  3.13it/s]
 63%|██████▎   | 234854/371472 [7:39:28<11:26:30,  3.32it/s]
 63%|██████▎   | 234855/371472 [7:39:29<11:29:24,  3.30it/s]
 63%|██████▎   | 234856/371472 [7:39:29<11:26:51,  3.31it/s]
 63%|██████▎   | 234857/371472 [7:39:29<10:48:47,  3.51it/s]
 63%|██████▎   | 234858/371472 [7:39:29<10:36:33,  3.58it/s]
 63%|██████▎   | 234859/371472 [7:39:30<11:37:06,  3.27it/s]
 63%|██████▎   | 234860/371472 [7:39:30<11:24:27,  3.33it/s]
                                                            
{'loss': 2.8991, 'learning_rate': 4.311609817061346e-07, 'epoch': 10.12}
+
 63%|██████▎   | 234860/371472 [7:39:30<11:24:27,  3.33it/s]
 63%|██████▎   | 234861/371472 [7:39:30<11:07:59,  3.41it/s]
 63%|██████▎   | 234862/371472 [7:39:31<10:37:02,  3.57it/s]
 63%|██████▎   | 234863/371472 [7:39:31<10:25:43,  3.64it/s]
 63%|██████▎   | 234864/371472 [7:39:31<10:33:30,  3.59it/s]
 63%|██████▎   | 234865/371472 [7:39:31<10:28:20,  3.62it/s]
 63%|██████▎   | 234866/371472 [7:39:32<11:22:33,  3.34it/s]
 63%|██████▎   | 234867/371472 [7:39:32<10:57:22,  3.46it/s]
 63%|██████▎   | 234868/371472 [7:39:32<10:38:59,  3.56it/s]
 63%|██████▎   | 234869/371472 [7:39:33<10:09:30,  3.74it/s]
 63%|██████▎   | 234870/371472 [7:39:33<10:03:03,  3.78it/s]
 63%|██████▎   | 234871/371472 [7:39:33<10:26:53,  3.63it/s]
 63%|██████▎   | 234872/371472 [7:39:33<10:11:53,  3.72it/s]
 63%|██████▎   | 234873/371472 [7:39:34<10:03:11,  3.77it/s]
 63%|██████▎   | 234874/371472 [7:39:34<10:05:51,  3.76it/s]
 63%|██████▎   | 234875/371472 [7:39:34<10:01:51,  3.78it/s]
 63%|██████▎   | 234876/371472 [7:39:34<9:50:29,  3.86it/s] 
 63%|██████▎   | 234877/371472 [7:39:35<9:38:11,  3.94it/s]
 63%|██████▎   | 234878/371472 [7:39:35<9:38:00,  3.94it/s]
 63%|██████▎   | 234879/371472 [7:39:35<10:00:06,  3.79it/s]
 63%|██████▎   | 234880/371472 [7:39:35<9:55:44,  3.82it/s] 
                                                           
{'loss': 2.9442, 'learning_rate': 4.3111249973065566e-07, 'epoch': 10.12}
+
 63%|██████▎   | 234880/371472 [7:39:35<9:55:44,  3.82it/s]
 63%|██████▎   | 234881/371472 [7:39:36<10:24:08,  3.65it/s]
 63%|██████▎   | 234882/371472 [7:39:36<10:25:31,  3.64it/s]
 63%|██████▎   | 234883/371472 [7:39:36<10:33:43,  3.59it/s]
 63%|██████▎   | 234884/371472 [7:39:37<10:27:35,  3.63it/s]
 63%|██████▎   | 234885/371472 [7:39:37<10:33:19,  3.59it/s]
 63%|██████▎   | 234886/371472 [7:39:37<10:20:31,  3.67it/s]
 63%|██████▎   | 234887/371472 [7:39:37<11:04:49,  3.42it/s]
 63%|██████▎   | 234888/371472 [7:39:38<10:37:43,  3.57it/s]
 63%|██████▎   | 234889/371472 [7:39:38<10:24:52,  3.64it/s]
 63%|██████▎   | 234890/371472 [7:39:38<10:54:26,  3.48it/s]
 63%|██████▎   | 234891/371472 [7:39:39<10:33:08,  3.60it/s]
 63%|██████▎   | 234892/371472 [7:39:39<10:45:41,  3.53it/s]
 63%|██████▎   | 234893/371472 [7:39:39<10:25:31,  3.64it/s]
 63%|██████▎   | 234894/371472 [7:39:39<10:38:45,  3.56it/s]
 63%|██████▎   | 234895/371472 [7:39:40<11:26:26,  3.32it/s]
 63%|██████▎   | 234896/371472 [7:39:40<11:12:24,  3.39it/s]
 63%|██████▎   | 234897/371472 [7:39:40<11:01:21,  3.44it/s]
 63%|██████▎   | 234898/371472 [7:39:41<11:57:52,  3.17it/s]
 63%|██████▎   | 234899/371472 [7:39:41<12:07:24,  3.13it/s]
 63%|██████▎   | 234900/371472 [7:39:41<11:40:17,  3.25it/s]
                                                            
{'loss': 2.9239, 'learning_rate': 4.310640177551768e-07, 'epoch': 10.12}
+
 63%|██████▎   | 234900/371472 [7:39:41<11:40:17,  3.25it/s]
 63%|██████▎   | 234901/371472 [7:39:42<11:13:07,  3.38it/s]
 63%|██████▎   | 234902/371472 [7:39:42<12:02:27,  3.15it/s]
 63%|██████▎   | 234903/371472 [7:39:42<11:14:56,  3.37it/s]
 63%|██████▎   | 234904/371472 [7:39:42<10:46:44,  3.52it/s]
 63%|██████▎   | 234905/371472 [7:39:43<10:21:43,  3.66it/s]
 63%|██████▎   | 234906/371472 [7:39:43<10:13:02,  3.71it/s]
 63%|██████▎   | 234907/371472 [7:39:43<10:09:52,  3.73it/s]
 63%|██████▎   | 234908/371472 [7:39:44<10:44:57,  3.53it/s]
 63%|██████▎   | 234909/371472 [7:39:44<10:36:21,  3.58it/s]
 63%|██████▎   | 234910/371472 [7:39:44<10:25:55,  3.64it/s]
 63%|██████▎   | 234911/371472 [7:39:44<10:12:47,  3.71it/s]
 63%|██████▎   | 234912/371472 [7:39:45<11:02:58,  3.43it/s]
 63%|██████▎   | 234913/371472 [7:39:45<10:47:33,  3.51it/s]
 63%|██████▎   | 234914/371472 [7:39:45<10:50:10,  3.50it/s]
 63%|██████▎   | 234915/371472 [7:39:45<10:19:55,  3.67it/s]
 63%|██████▎   | 234916/371472 [7:39:46<10:17:12,  3.69it/s]
 63%|██████▎   | 234917/371472 [7:39:46<10:38:07,  3.57it/s]
 63%|██████▎   | 234918/371472 [7:39:46<11:09:30,  3.40it/s]
 63%|██████▎   | 234919/371472 [7:39:47<11:05:21,  3.42it/s]
 63%|██████▎   | 234920/371472 [7:39:47<11:48:04,  3.21it/s]
                                                            
{'loss': 2.76, 'learning_rate': 4.3101553577969786e-07, 'epoch': 10.12}
+
 63%|██████▎   | 234920/371472 [7:39:47<11:48:04,  3.21it/s]
 63%|██████▎   | 234921/371472 [7:39:47<12:05:24,  3.14it/s]
 63%|██████▎   | 234922/371472 [7:39:48<11:26:33,  3.31it/s]
 63%|██████▎   | 234923/371472 [7:39:48<11:04:32,  3.42it/s]
 63%|██████▎   | 234924/371472 [7:39:48<11:20:26,  3.34it/s]
 63%|██████▎   | 234925/371472 [7:39:48<10:58:40,  3.46it/s]
 63%|██████▎   | 234926/371472 [7:39:49<11:01:19,  3.44it/s]
 63%|██████▎   | 234927/371472 [7:39:49<11:01:41,  3.44it/s]
 63%|██████▎   | 234928/371472 [7:39:49<10:42:57,  3.54it/s]
 63%|██████▎   | 234929/371472 [7:39:50<10:22:52,  3.65it/s]
 63%|██████▎   | 234930/371472 [7:39:50<10:34:52,  3.58it/s]
 63%|██████▎   | 234931/371472 [7:39:50<10:17:39,  3.68it/s]
 63%|██████▎   | 234932/371472 [7:39:50<11:24:45,  3.32it/s]
 63%|██████▎   | 234933/371472 [7:39:51<11:04:15,  3.43it/s]
 63%|██████▎   | 234934/371472 [7:39:51<10:52:07,  3.49it/s]
 63%|██████▎   | 234935/371472 [7:39:51<10:58:21,  3.46it/s]
 63%|██████▎   | 234936/371472 [7:39:52<10:42:19,  3.54it/s]
 63%|██████▎   | 234937/371472 [7:39:52<10:31:29,  3.60it/s]
 63%|██████▎   | 234938/371472 [7:39:52<10:17:32,  3.68it/s]
 63%|██████▎   | 234939/371472 [7:39:52<11:23:08,  3.33it/s]
 63%|██████▎   | 234940/371472 [7:39:53<11:14:49,  3.37it/s]
                                                            
{'loss': 2.7535, 'learning_rate': 4.3096705380421904e-07, 'epoch': 10.12}
+
 63%|██████▎   | 234940/371472 [7:39:53<11:14:49,  3.37it/s]
 63%|██████▎   | 234941/371472 [7:39:53<10:56:39,  3.47it/s]
 63%|██████▎   | 234942/371472 [7:39:53<10:46:17,  3.52it/s]
 63%|██████▎   | 234943/371472 [7:39:54<10:24:33,  3.64it/s]
 63%|██████▎   | 234944/371472 [7:39:54<11:33:43,  3.28it/s]
 63%|██████▎   | 234945/371472 [7:39:54<11:05:18,  3.42it/s]
 63%|██████▎   | 234946/371472 [7:39:54<10:57:47,  3.46it/s]
 63%|██████▎   | 234947/371472 [7:39:55<10:47:44,  3.51it/s]
 63%|██████▎   | 234948/371472 [7:39:55<10:37:34,  3.57it/s]
 63%|██████▎   | 234949/371472 [7:39:55<10:18:53,  3.68it/s]
 63%|██████▎   | 234950/371472 [7:39:56<10:30:18,  3.61it/s]
 63%|██████▎   | 234951/371472 [7:39:56<10:38:40,  3.56it/s]
 63%|██████▎   | 234952/371472 [7:39:56<10:43:34,  3.54it/s]
 63%|██████▎   | 234953/371472 [7:39:56<10:56:57,  3.46it/s]
 63%|██████▎   | 234954/371472 [7:39:57<11:05:17,  3.42it/s]
 63%|██████▎   | 234955/371472 [7:39:57<10:33:49,  3.59it/s]
 63%|██████▎   | 234956/371472 [7:39:57<10:18:51,  3.68it/s]
 63%|██████▎   | 234957/371472 [7:39:57<10:05:26,  3.76it/s]
 63%|██████▎   | 234958/371472 [7:39:58<10:12:48,  3.71it/s]
 63%|██████▎   | 234959/371472 [7:39:58<10:23:17,  3.65it/s]
 63%|██████▎   | 234960/371472 [7:39:58<10:17:45,  3.68it/s]
                                                            
{'loss': 3.058, 'learning_rate': 4.309185718287401e-07, 'epoch': 10.12}
+
 63%|██████▎   | 234960/371472 [7:39:58<10:17:45,  3.68it/s]
 63%|██████▎   | 234961/371472 [7:39:59<10:51:38,  3.49it/s]
 63%|██████▎   | 234962/371472 [7:39:59<10:46:09,  3.52it/s]
 63%|██████▎   | 234963/371472 [7:39:59<11:03:08,  3.43it/s]
 63%|██████▎   | 234964/371472 [7:39:59<10:35:34,  3.58it/s]
 63%|██████▎   | 234965/371472 [7:40:00<10:31:11,  3.60it/s]
 63%|██████▎   | 234966/371472 [7:40:00<10:26:59,  3.63it/s]
 63%|██████▎   | 234967/371472 [7:40:00<10:32:05,  3.60it/s]
 63%|██████▎   | 234968/371472 [7:40:01<10:38:32,  3.56it/s]
 63%|██████▎   | 234969/371472 [7:40:01<10:43:53,  3.53it/s]
 63%|██████▎   | 234970/371472 [7:40:01<10:49:39,  3.50it/s]
 63%|██████▎   | 234971/371472 [7:40:01<10:42:35,  3.54it/s]
 63%|██████▎   | 234972/371472 [7:40:02<10:32:14,  3.60it/s]
 63%|██████▎   | 234973/371472 [7:40:02<10:18:09,  3.68it/s]
 63%|██████▎   | 234974/371472 [7:40:02<10:23:16,  3.65it/s]
 63%|██████▎   | 234975/371472 [7:40:02<10:11:07,  3.72it/s]
 63%|██████▎   | 234976/371472 [7:40:03<11:08:03,  3.41it/s]
 63%|██████▎   | 234977/371472 [7:40:03<11:18:08,  3.35it/s]
 63%|██████▎   | 234978/371472 [7:40:03<10:44:02,  3.53it/s]
 63%|██████▎   | 234979/371472 [7:40:04<10:30:51,  3.61it/s]
 63%|██████▎   | 234980/371472 [7:40:04<10:22:06,  3.66it/s]
                                                            
{'loss': 2.7691, 'learning_rate': 4.3087008985326123e-07, 'epoch': 10.12}
+
 63%|██████▎   | 234980/371472 [7:40:04<10:22:06,  3.66it/s]
 63%|██████▎   | 234981/371472 [7:40:04<10:00:45,  3.79it/s]
 63%|██████▎   | 234982/371472 [7:40:04<10:11:08,  3.72it/s]
 63%|██████▎   | 234983/371472 [7:40:05<10:30:45,  3.61it/s]
 63%|██████▎   | 234984/371472 [7:40:05<10:41:25,  3.55it/s]
 63%|██████▎   | 234985/371472 [7:40:05<10:54:59,  3.47it/s]
 63%|██████▎   | 234986/371472 [7:40:06<10:33:44,  3.59it/s]
 63%|██████▎   | 234987/371472 [7:40:06<10:19:09,  3.67it/s]
 63%|██████▎   | 234988/371472 [7:40:06<10:20:37,  3.67it/s]
 63%|██████▎   | 234989/371472 [7:40:06<10:03:35,  3.77it/s]
 63%|██████▎   | 234990/371472 [7:40:07<9:43:45,  3.90it/s] 
 63%|██████▎   | 234991/371472 [7:40:07<10:24:26,  3.64it/s]
 63%|██████▎   | 234992/371472 [7:40:07<11:28:24,  3.30it/s]
 63%|██████▎   | 234993/371472 [7:40:08<11:07:58,  3.41it/s]
 63%|██████▎   | 234994/371472 [7:40:08<11:05:35,  3.42it/s]
 63%|██████▎   | 234995/371472 [7:40:08<10:59:20,  3.45it/s]
 63%|██████▎   | 234996/371472 [7:40:08<10:58:38,  3.45it/s]
 63%|██████▎   | 234997/371472 [7:40:09<10:50:22,  3.50it/s]
 63%|██████▎   | 234998/371472 [7:40:09<10:34:47,  3.58it/s]
 63%|██████▎   | 234999/371472 [7:40:09<10:19:52,  3.67it/s]
 63%|██████▎   | 235000/371472 [7:40:10<11:05:30,  3.42it/s]
                                                            
{'loss': 3.0156, 'learning_rate': 4.308216078777823e-07, 'epoch': 10.12}
+
 63%|██████▎   | 235000/371472 [7:40:10<11:05:30,  3.42it/s]
 63%|██████▎   | 235001/371472 [7:40:10<10:47:32,  3.51it/s]
 63%|██████▎   | 235002/371472 [7:40:10<10:55:56,  3.47it/s]
 63%|██████▎   | 235003/371472 [7:40:10<10:52:20,  3.49it/s]
 63%|██████▎   | 235004/371472 [7:40:11<10:40:10,  3.55it/s]
 63%|██████▎   | 235005/371472 [7:40:11<10:54:47,  3.47it/s]
 63%|██████▎   | 235006/371472 [7:40:11<10:33:46,  3.59it/s]
 63%|██████▎   | 235007/371472 [7:40:12<10:26:15,  3.63it/s]
 63%|██████▎   | 235008/371472 [7:40:12<10:03:33,  3.77it/s]
 63%|██████▎   | 235009/371472 [7:40:12<10:04:20,  3.76it/s]
 63%|██████▎   | 235010/371472 [7:40:12<9:58:24,  3.80it/s] 
 63%|██████▎   | 235011/371472 [7:40:13<10:22:42,  3.65it/s]
 63%|██████▎   | 235012/371472 [7:40:13<10:13:33,  3.71it/s]
 63%|██████▎   | 235013/371472 [7:40:13<10:24:40,  3.64it/s]
 63%|██████▎   | 235014/371472 [7:40:13<10:44:44,  3.53it/s]
 63%|██████▎   | 235015/371472 [7:40:14<10:41:06,  3.55it/s]
 63%|██████▎   | 235016/371472 [7:40:14<10:21:06,  3.66it/s]
 63%|██████▎   | 235017/371472 [7:40:14<10:04:33,  3.76it/s]
 63%|██████▎   | 235018/371472 [7:40:15<10:28:47,  3.62it/s]
 63%|██████▎   | 235019/371472 [7:40:15<10:50:22,  3.50it/s]
 63%|██████▎   | 235020/371472 [7:40:15<10:52:30,  3.49it/s]
                                                            
{'loss': 2.8453, 'learning_rate': 4.307731259023035e-07, 'epoch': 10.12}
+
 63%|██████▎   | 235020/371472 [7:40:15<10:52:30,  3.49it/s]
 63%|██████▎   | 235021/371472 [7:40:15<10:32:21,  3.60it/s]
 63%|██████▎   | 235022/371472 [7:40:16<11:26:36,  3.31it/s]
 63%|██████▎   | 235023/371472 [7:40:16<11:07:16,  3.41it/s]
 63%|██████▎   | 235024/371472 [7:40:16<10:51:25,  3.49it/s]
 63%|██████▎   | 235025/371472 [7:40:17<10:58:37,  3.45it/s]
 63%|██████▎   | 235026/371472 [7:40:17<10:47:47,  3.51it/s]
 63%|██████▎   | 235027/371472 [7:40:17<11:32:42,  3.28it/s]
 63%|██████▎   | 235028/371472 [7:40:17<11:17:14,  3.36it/s]
 63%|██████▎   | 235029/371472 [7:40:18<10:49:43,  3.50it/s]
 63%|██████▎   | 235030/371472 [7:40:18<10:43:30,  3.53it/s]
 63%|██████▎   | 235031/371472 [7:40:18<10:30:13,  3.61it/s]
 63%|██████▎   | 235032/371472 [7:40:19<10:19:36,  3.67it/s]
 63%|██████▎   | 235033/371472 [7:40:19<10:02:58,  3.77it/s]
 63%|██████▎   | 235034/371472 [7:40:19<10:08:03,  3.74it/s]
 63%|██████▎   | 235035/371472 [7:40:19<9:59:09,  3.80it/s] 
 63%|██████▎   | 235036/371472 [7:40:20<11:36:12,  3.27it/s]
 63%|██████▎   | 235037/371472 [7:40:20<11:30:26,  3.29it/s]
 63%|██████▎   | 235038/371472 [7:40:20<11:35:15,  3.27it/s]
 63%|██████▎   | 235039/371472 [7:40:21<11:30:11,  3.29it/s]
 63%|██████▎   | 235040/371472 [7:40:21<11:29:18,  3.30it/s]
                                                            
{'loss': 2.8668, 'learning_rate': 4.307246439268245e-07, 'epoch': 10.12}
+
 63%|██████▎   | 235040/371472 [7:40:21<11:29:18,  3.30it/s]
 63%|██████▎   | 235041/371472 [7:40:21<11:48:59,  3.21it/s]
 63%|██████▎   | 235042/371472 [7:40:22<11:20:39,  3.34it/s]
 63%|██████▎   | 235043/371472 [7:40:22<10:38:53,  3.56it/s]
 63%|██████▎   | 235044/371472 [7:40:22<10:58:37,  3.45it/s]
 63%|█████���▎   | 235045/371472 [7:40:22<11:33:20,  3.28it/s]
 63%|██████▎   | 235046/371472 [7:40:23<11:11:27,  3.39it/s]
 63%|██████▎   | 235047/371472 [7:40:23<12:16:12,  3.09it/s]
 63%|██████▎   | 235048/371472 [7:40:23<11:16:12,  3.36it/s]
 63%|██████▎   | 235049/371472 [7:40:24<11:05:35,  3.42it/s]
 63%|██████▎   | 235050/371472 [7:40:24<10:58:19,  3.45it/s]
 63%|██████▎   | 235051/371472 [7:40:24<10:43:59,  3.53it/s]
 63%|██████▎   | 235052/371472 [7:40:24<10:43:24,  3.53it/s]
 63%|██████▎   | 235053/371472 [7:40:25<11:39:28,  3.25it/s]
 63%|██████▎   | 235054/371472 [7:40:25<11:01:42,  3.44it/s]
 63%|██████▎   | 235055/371472 [7:40:25<10:48:44,  3.50it/s]
 63%|██████▎   | 235056/371472 [7:40:26<10:45:35,  3.52it/s]
 63%|██████▎   | 235057/371472 [7:40:26<10:51:32,  3.49it/s]
 63%|██████▎   | 235058/371472 [7:40:26<11:33:56,  3.28it/s]
 63%|██████▎   | 235059/371472 [7:40:26<10:57:53,  3.46it/s]
 63%|██████▎   | 235060/371472 [7:40:27<10:29:15,  3.61it/s]
                                                            
{'loss': 2.7903, 'learning_rate': 4.306761619513457e-07, 'epoch': 10.12}
+
 63%|██████▎   | 235060/371472 [7:40:27<10:29:15,  3.61it/s]
 63%|██████▎   | 235061/371472 [7:40:27<10:29:17,  3.61it/s]
 63%|██████▎   | 235062/371472 [7:40:27<10:38:56,  3.56it/s]
 63%|██████▎   | 235063/371472 [7:40:28<10:38:53,  3.56it/s]
 63%|██████▎   | 235064/371472 [7:40:28<10:56:19,  3.46it/s]
 63%|██████▎   | 235065/371472 [7:40:28<10:50:22,  3.50it/s]
 63%|██████▎   | 235066/371472 [7:40:28<10:46:36,  3.52it/s]
 63%|██████▎   | 235067/371472 [7:40:29<10:53:16,  3.48it/s]
 63%|██████▎   | 235068/371472 [7:40:29<11:34:28,  3.27it/s]
 63%|██████▎   | 235069/371472 [7:40:29<10:56:10,  3.46it/s]
 63%|██████▎   | 235070/371472 [7:40:30<11:30:04,  3.29it/s]
 63%|██████▎   | 235071/371472 [7:40:30<11:09:29,  3.40it/s]
 63%|██████▎   | 235072/371472 [7:40:30<10:34:20,  3.58it/s]
 63%|██████▎   | 235073/371472 [7:40:30<10:21:58,  3.65it/s]
 63%|██████▎   | 235074/371472 [7:40:31<10:12:04,  3.71it/s]
 63%|██████▎   | 235075/371472 [7:40:31<9:53:07,  3.83it/s] 
 63%|██████▎   | 235076/371472 [7:40:31<10:01:01,  3.78it/s]
 63%|██████▎   | 235077/371472 [7:40:32<10:09:19,  3.73it/s]
 63%|██████▎   | 235078/371472 [7:40:32<10:09:02,  3.73it/s]
 63%|██████▎   | 235079/371472 [7:40:32<9:58:09,  3.80it/s] 
 63%|██████▎   | 235080/371472 [7:40:32<9:56:44,  3.81it/s]
                                                           
{'loss': 2.9745, 'learning_rate': 4.3062767997586675e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235080/371472 [7:40:32<9:56:44,  3.81it/s]
 63%|██████▎   | 235081/371472 [7:40:33<10:02:46,  3.77it/s]
 63%|██████▎   | 235082/371472 [7:40:33<10:24:45,  3.64it/s]
 63%|██████▎   | 235083/371472 [7:40:33<11:20:28,  3.34it/s]
 63%|██████▎   | 235084/371472 [7:40:34<11:08:29,  3.40it/s]
 63%|██████▎   | 235085/371472 [7:40:34<10:47:38,  3.51it/s]
 63%|██████▎   | 235086/371472 [7:40:34<11:22:22,  3.33it/s]
 63%|██████▎   | 235087/371472 [7:40:34<10:52:13,  3.49it/s]
 63%|██████▎   | 235088/371472 [7:40:35<11:05:13,  3.42it/s]
 63%|██████▎   | 235089/371472 [7:40:35<11:02:49,  3.43it/s]
 63%|██████▎   | 235090/371472 [7:40:35<10:59:31,  3.45it/s]
 63%|██████▎   | 235091/371472 [7:40:35<10:35:12,  3.58it/s]
 63%|██████▎   | 235092/371472 [7:40:36<11:09:23,  3.40it/s]
 63%|██████▎   | 235093/371472 [7:40:36<10:47:01,  3.51it/s]
 63%|██████▎   | 235094/371472 [7:40:36<10:54:28,  3.47it/s]
 63%|██████▎   | 235095/371472 [7:40:37<10:48:32,  3.50it/s]
 63%|██████▎   | 235096/371472 [7:40:37<11:07:21,  3.41it/s]
 63%|██████▎   | 235097/371472 [7:40:37<10:40:10,  3.55it/s]
 63%|██████▎   | 235098/371472 [7:40:38<10:43:43,  3.53it/s]
 63%|██████▎   | 235099/371472 [7:40:38<10:48:24,  3.51it/s]
 63%|██████▎   | 235100/371472 [7:40:38<13:51:09,  2.73it/s]
                                                            
{'loss': 2.8187, 'learning_rate': 4.3057919800038777e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235100/371472 [7:40:38<13:51:09,  2.73it/s]
 63%|██████▎   | 235101/371472 [7:40:39<12:50:57,  2.95it/s]
 63%|██████▎   | 235102/371472 [7:40:39<13:20:43,  2.84it/s]
 63%|██████▎   | 235103/371472 [7:40:39<12:26:53,  3.04it/s]
 63%|██████▎   | 235104/371472 [7:40:40<12:02:33,  3.15it/s]
 63%|█���████▎   | 235105/371472 [7:40:40<11:52:03,  3.19it/s]
 63%|██████▎   | 235106/371472 [7:40:40<11:36:03,  3.27it/s]
 63%|██████▎   | 235107/371472 [7:40:40<11:29:01,  3.30it/s]
 63%|██████▎   | 235108/371472 [7:40:41<11:02:09,  3.43it/s]
 63%|██████▎   | 235109/371472 [7:40:41<11:15:24,  3.36it/s]
 63%|██████▎   | 235110/371472 [7:40:41<11:24:41,  3.32it/s]
 63%|██████▎   | 235111/371472 [7:40:42<10:49:54,  3.50it/s]
 63%|██████▎   | 235112/371472 [7:40:42<10:29:52,  3.61it/s]
 63%|██████▎   | 235113/371472 [7:40:42<10:29:08,  3.61it/s]
 63%|██████▎   | 235114/371472 [7:40:42<10:18:39,  3.67it/s]
 63%|██████▎   | 235115/371472 [7:40:43<10:18:29,  3.67it/s]
 63%|██████▎   | 235116/371472 [7:40:43<10:29:07,  3.61it/s]
 63%|██████▎   | 235117/371472 [7:40:43<10:09:45,  3.73it/s]
 63%|██████▎   | 235118/371472 [7:40:43<10:06:11,  3.75it/s]
 63%|██████▎   | 235119/371472 [7:40:44<9:59:53,  3.79it/s] 
 63%|██████▎   | 235120/371472 [7:40:44<10:22:36,  3.65it/s]
                                                            
{'loss': 3.0, 'learning_rate': 4.3053071602490894e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235120/371472 [7:40:44<10:22:36,  3.65it/s]
 63%|██████▎   | 235121/371472 [7:40:44<10:48:34,  3.50it/s]
 63%|██████▎   | 235122/371472 [7:40:45<11:03:57,  3.42it/s]
 63%|██████▎   | 235123/371472 [7:40:45<10:39:38,  3.55it/s]
 63%|██████▎   | 235124/371472 [7:40:45<10:44:58,  3.52it/s]
 63%|██████▎   | 235125/371472 [7:40:45<10:29:06,  3.61it/s]
 63%|██████▎   | 235126/371472 [7:40:46<10:28:44,  3.61it/s]
 63%|██████▎   | 235127/371472 [7:40:46<10:32:08,  3.59it/s]
 63%|██████▎   | 235128/371472 [7:40:46<11:12:19,  3.38it/s]
 63%|██████▎   | 235129/371472 [7:40:47<11:21:14,  3.34it/s]
 63%|██████▎   | 235130/371472 [7:40:47<12:04:43,  3.14it/s]
 63%|██████▎   | 235131/371472 [7:40:47<11:21:56,  3.33it/s]
 63%|██████▎   | 235132/371472 [7:40:48<11:03:18,  3.43it/s]
 63%|██████▎   | 235133/371472 [7:40:48<10:37:00,  3.57it/s]
 63%|██████▎   | 235134/371472 [7:40:48<10:47:44,  3.51it/s]
 63%|██████▎   | 235135/371472 [7:40:48<10:23:03,  3.65it/s]
 63%|██████▎   | 235136/371472 [7:40:49<11:06:12,  3.41it/s]
 63%|██████▎   | 235137/371472 [7:40:49<10:37:50,  3.56it/s]
 63%|██████▎   | 235138/371472 [7:40:49<10:23:50,  3.64it/s]
 63%|██████▎   | 235139/371472 [7:40:49<10:37:50,  3.56it/s]
 63%|██████▎   | 235140/371472 [7:40:50<10:51:47,  3.49it/s]
                                                            
{'loss': 2.7807, 'learning_rate': 4.3048223404943e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235140/371472 [7:40:50<10:51:47,  3.49it/s]
 63%|██████▎   | 235141/371472 [7:40:50<11:17:02,  3.36it/s]
 63%|██████▎   | 235142/371472 [7:40:50<12:05:26,  3.13it/s]
 63%|██████▎   | 235143/371472 [7:40:51<12:18:10,  3.08it/s]
 63%|██████▎   | 235144/371472 [7:40:51<12:55:08,  2.93it/s]
 63%|██████▎   | 235145/371472 [7:40:51<11:53:39,  3.18it/s]
 63%|██████▎   | 235146/371472 [7:40:52<12:41:23,  2.98it/s]
 63%|██████▎   | 235147/371472 [7:40:52<12:17:05,  3.08it/s]
 63%|██████▎   | 235148/371472 [7:40:52<11:32:53,  3.28it/s]
 63%|██████▎   | 235149/371472 [7:40:53<10:55:39,  3.47it/s]
 63%|██████▎   | 235150/371472 [7:40:53<10:26:23,  3.63it/s]
 63%|██████▎   | 235151/371472 [7:40:53<10:30:37,  3.60it/s]
 63%|██████▎   | 235152/371472 [7:40:53<10:28:34,  3.61it/s]
 63%|██████▎   | 235153/371472 [7:40:54<11:39:44,  3.25it/s]
 63%|██████▎   | 235154/371472 [7:40:54<10:55:41,  3.47it/s]
 63%|██████▎   | 235155/371472 [7:40:54<10:19:56,  3.66it/s]
 63%|██████▎   | 235156/371472 [7:40:55<10:17:19,  3.68it/s]
 63%|██████▎   | 235157/371472 [7:40:55<10:01:06,  3.78it/s]
 63%|██████▎   | 235158/371472 [7:40:55<11:07:59,  3.40it/s]
 63%|██████▎   | 235159/371472 [7:40:55<11:11:57,  3.38it/s]
 63%|██████▎   | 235160/371472 [7:40:56<10:46:14,  3.52it/s]
                                                            
{'loss': 2.8143, 'learning_rate': 4.3043375207395114e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235160/371472 [7:40:56<10:46:14,  3.52it/s]
 63%|██████▎   | 235161/371472 [7:40:56<10:24:38,  3.64it/s]
 63%|██████▎   | 235162/371472 [7:40:56<10:34:37,  3.58it/s]
 63%|██████▎   | 235163/371472 [7:40:57<10:22:26,  3.65it/s]
 63%|██████▎   | 235164/371472 [7:40:57<10:32:39,  3.59it/s]
 63%|██████▎   | 235165/371472 [7:40:57<10:37:53,  3.56it/s]
 63%|██████▎   | 235166/371472 [7:40:57<10:26:37,  3.63it/s]
 63%|██████▎   | 235167/371472 [7:40:58<10:19:05,  3.67it/s]
 63%|██████▎   | 235168/371472 [7:40:58<10:04:26,  3.76it/s]
 63%|██████▎   | 235169/371472 [7:40:58<10:20:58,  3.66it/s]
 63%|██████▎   | 235170/371472 [7:40:58<10:36:20,  3.57it/s]
 63%|██████▎   | 235171/371472 [7:40:59<10:42:43,  3.53it/s]
 63%|██████▎   | 235172/371472 [7:40:59<10:45:19,  3.52it/s]
 63%|██████▎   | 235173/371472 [7:40:59<10:30:57,  3.60it/s]
 63%|██████▎   | 235174/371472 [7:41:00<10:50:11,  3.49it/s]
 63%|██████▎   | 235175/371472 [7:41:00<11:08:57,  3.40it/s]
 63%|██████▎   | 235176/371472 [7:41:00<10:57:43,  3.45it/s]
 63%|██████▎   | 235177/371472 [7:41:00<10:29:24,  3.61it/s]
 63%|██████▎   | 235178/371472 [7:41:01<10:48:59,  3.50it/s]
 63%|██████▎   | 235179/371472 [7:41:01<10:29:06,  3.61it/s]
 63%|██████▎   | 235180/371472 [7:41:01<11:22:49,  3.33it/s]
                                                            
{'loss': 2.9193, 'learning_rate': 4.303852700984722e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235180/371472 [7:41:01<11:22:49,  3.33it/s]
 63%|██████▎   | 235181/371472 [7:41:02<12:05:53,  3.13it/s]
 63%|██████▎   | 235182/371472 [7:41:02<12:10:44,  3.11it/s]
 63%|██████▎   | 235183/371472 [7:41:02<11:20:10,  3.34it/s]
 63%|██████▎   | 235184/371472 [7:41:03<10:41:18,  3.54it/s]
 63%|██████▎   | 235185/371472 [7:41:03<10:28:25,  3.61it/s]
 63%|██████▎   | 235186/371472 [7:41:03<10:16:07,  3.69it/s]
 63%|██████▎   | 235187/371472 [7:41:03<10:06:15,  3.75it/s]
 63%|██████▎   | 235188/371472 [7:41:04<10:05:21,  3.75it/s]
 63%|██████▎   | 235189/371472 [7:41:04<10:03:05,  3.77it/s]
 63%|██████▎   | 235190/371472 [7:41:04<9:49:30,  3.85it/s] 
 63%|██████▎   | 235191/371472 [7:41:04<10:00:06,  3.78it/s]
 63%|██████▎   | 235192/371472 [7:41:05<10:38:12,  3.56it/s]
 63%|██████▎   | 235193/371472 [7:41:05<10:24:43,  3.64it/s]
 63%|██████▎   | 235194/371472 [7:41:05<10:05:35,  3.75it/s]
 63%|██████▎   | 235195/371472 [7:41:06<10:49:27,  3.50it/s]
 63%|██████▎   | 235196/371472 [7:41:06<10:38:09,  3.56it/s]
 63%|██████▎   | 235197/371472 [7:41:06<11:14:23,  3.37it/s]
 63%|██████▎   | 235198/371472 [7:41:06<10:47:03,  3.51it/s]
 63%|██████▎   | 235199/371472 [7:41:07<10:52:33,  3.48it/s]
 63%|██████▎   | 235200/371472 [7:41:07<10:51:15,  3.49it/s]
                                                            
{'loss': 2.9002, 'learning_rate': 4.303367881229934e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235200/371472 [7:41:07<10:51:15,  3.49it/s]
 63%|██████▎   | 235201/371472 [7:41:07<10:17:21,  3.68it/s]
 63%|██████▎   | 235202/371472 [7:41:08<10:12:08,  3.71it/s]
 63%|██████▎   | 235203/371472 [7:41:08<10:34:56,  3.58it/s]
 63%|██████▎   | 235204/371472 [7:41:08<10:58:03,  3.45it/s]
 63%|██████▎   | 235205/371472 [7:41:08<11:10:16,  3.39it/s]
 63%|██████▎   | 235206/371472 [7:41:09<11:02:38,  3.43it/s]
 63%|██████▎   | 235207/371472 [7:41:09<10:34:44,  3.58it/s]
 63%|██████▎   | 235208/371472 [7:41:09<10:14:38,  3.69it/s]
 63%|██████▎   | 235209/371472 [7:41:09<10:14:55,  3.69it/s]
 63%|██████▎   | 235210/371472 [7:41:10<10:10:16,  3.72it/s]
 63%|██████▎   | 235211/371472 [7:41:10<10:38:25,  3.56it/s]
 63%|██████▎   | 235212/371472 [7:41:10<11:19:39,  3.34it/s]
 63%|██████▎   | 235213/371472 [7:41:11<10:49:26,  3.50it/s]
 63%|██████▎   | 235214/371472 [7:41:11<10:41:03,  3.54it/s]
 63%|██████▎   | 235215/371472 [7:41:11<10:31:51,  3.59it/s]
 63%|██████▎   | 235216/371472 [7:41:12<11:24:51,  3.32it/s]
 63%|██████▎   | 235217/371472 [7:41:12<11:06:29,  3.41it/s]
 63%|██████▎   | 235218/371472 [7:41:12<10:43:16,  3.53it/s]
 63%|██████▎   | 235219/371472 [7:41:13<12:45:43,  2.97it/s]
 63%|██████▎   | 235220/371472 [7:41:13<11:55:36,  3.17it/s]
                                                            
{'loss': 2.8388, 'learning_rate': 4.3028830614751446e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235220/371472 [7:41:13<11:55:36,  3.17it/s]
 63%|██████▎   | 235221/371472 [7:41:13<11:27:27,  3.30it/s]
 63%|██████▎   | 235222/371472 [7:41:13<11:37:20,  3.26it/s]
 63%|██████▎   | 235223/371472 [7:41:14<11:09:02,  3.39it/s]
 63%|██████▎   | 235224/371472 [7:41:14<10:48:31,  3.50it/s]
 63%|██████▎   | 235225/371472 [7:41:14<10:28:43,  3.61it/s]
 63%|██████▎   | 235226/371472 [7:41:14<10:46:24,  3.51it/s]
 63%|██████▎   | 235227/371472 [7:41:15<10:53:45,  3.47it/s]
 63%|██████▎   | 235228/371472 [7:41:15<10:39:00,  3.55it/s]
 63%|██████▎   | 235229/371472 [7:41:15<10:57:22,  3.45it/s]
 63%|██████▎   | 235230/371472 [7:41:16<11:15:11,  3.36it/s]
 63%|██████▎   | 235231/371472 [7:41:16<11:02:54,  3.43it/s]
 63%|██████▎   | 235232/371472 [7:41:16<11:29:22,  3.29it/s]
 63%|██████▎   | 235233/371472 [7:41:17<11:32:57,  3.28it/s]
 63%|██████▎   | 235234/371472 [7:41:17<11:44:33,  3.22it/s]
 63%|██████▎   | 235235/371472 [7:41:17<11:30:05,  3.29it/s]
 63%|██████▎   | 235236/371472 [7:41:17<11:03:56,  3.42it/s]
 63%|██████▎   | 235237/371472 [7:41:18<11:00:53,  3.44it/s]
 63%|██████▎   | 235238/371472 [7:41:18<11:10:19,  3.39it/s]
 63%|██████▎   | 235239/371472 [7:41:18<10:46:36,  3.51it/s]
 63%|██████▎   | 235240/371472 [7:41:19<10:13:52,  3.70it/s]
                                                            
{'loss': 2.9643, 'learning_rate': 4.302398241720356e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235240/371472 [7:41:19<10:13:52,  3.70it/s]
 63%|██████▎   | 235241/371472 [7:41:19<10:04:05,  3.76it/s]
 63%|██████▎   | 235242/371472 [7:41:19<9:56:51,  3.80it/s] 
 63%|██████▎   | 235243/371472 [7:41:19<9:58:22,  3.79it/s]
 63%|██████▎   | 235244/371472 [7:41:20<9:44:57,  3.88it/s]
 63%|██████▎   | 235245/371472 [7:41:20<10:09:35,  3.72it/s]
 63%|██████▎   | 235246/371472 [7:41:20<9:57:07,  3.80it/s] 
 63%|██████▎   | 235247/371472 [7:41:20<10:03:57,  3.76it/s]
 63%|██████▎   | 235248/371472 [7:41:21<10:04:39,  3.75it/s]
 63%|██████▎   | 235249/371472 [7:41:21<10:31:22,  3.60it/s]
 63%|██████▎   | 235250/371472 [7:41:21<10:21:23,  3.65it/s]
 63%|██████▎   | 235251/371472 [7:41:22<11:04:57,  3.41it/s]
 63%|██████▎   | 235252/371472 [7:41:22<10:50:27,  3.49it/s]
 63%|██████▎   | 235253/371472 [7:41:22<12:40:48,  2.98it/s]
 63%|██████▎   | 235254/371472 [7:41:23<12:39:25,  2.99it/s]
 63%|██████▎   | 235255/371472 [7:41:23<11:55:34,  3.17it/s]
 63%|██████▎   | 235256/371472 [7:41:23<11:35:48,  3.26it/s]
 63%|██████▎   | 235257/371472 [7:41:23<10:56:27,  3.46it/s]
 63%|██████▎   | 235258/371472 [7:41:24<10:58:21,  3.45it/s]
 63%|██████▎   | 235259/371472 [7:41:24<10:41:24,  3.54it/s]
 63%|██████▎   | 235260/371472 [7:41:24<10:32:06,  3.59it/s]
                                                            
{'loss': 2.844, 'learning_rate': 4.3019134219655666e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235260/371472 [7:41:24<10:32:06,  3.59it/s]
 63%|██████▎   | 235261/371472 [7:41:25<11:09:31,  3.39it/s]
 63%|██████▎   | 235262/371472 [7:41:25<12:22:39,  3.06it/s]
 63%|██████▎   | 235263/371472 [7:41:25<11:32:23,  3.28it/s]
 63%|██████▎   | 235264/371472 [7:41:26<11:06:17,  3.41it/s]
 63%|██████▎   | 235265/371472 [7:41:26<10:48:05,  3.50it/s]
 63%|██████▎   | 235266/371472 [7:41:26<10:26:27,  3.62it/s]
 63%|██████▎   | 235267/371472 [7:41:26<10:11:49,  3.71it/s]
 63%|██████▎   | 235268/371472 [7:41:27<10:23:11,  3.64it/s]
 63%|██████▎   | 235269/371472 [7:41:27<10:29:04,  3.61it/s]
 63%|██████▎   | 235270/371472 [7:41:27<10:20:23,  3.66it/s]
 63%|██████▎   | 235271/371472 [7:41:27<10:28:30,  3.61it/s]
 63%|██████▎   | 235272/371472 [7:41:28<10:59:14,  3.44it/s]
 63%|██████▎   | 235273/371472 [7:41:28<10:50:07,  3.49it/s]
 63%|██████▎   | 235274/371472 [7:41:28<10:32:06,  3.59it/s]
 63%|██████▎   | 235275/371472 [7:41:29<10:53:43,  3.47it/s]
 63%|██████▎   | 235276/371472 [7:41:29<10:57:24,  3.45it/s]
 63%|██████▎   | 235277/371472 [7:41:29<10:43:20,  3.53it/s]
 63%|██████▎   | 235278/371472 [7:41:29<10:27:24,  3.62it/s]
 63%|██████▎   | 235279/371472 [7:41:30<10:56:39,  3.46it/s]
 63%|██████▎   | 235280/371472 [7:41:30<10:54:33,  3.47it/s]
                                                            
{'loss': 2.7598, 'learning_rate': 4.3014286022107783e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235280/371472 [7:41:30<10:54:33,  3.47it/s]
 63%|██████▎   | 235281/371472 [7:41:30<11:30:15,  3.29it/s]
 63%|██████▎   | 235282/371472 [7:41:31<11:25:52,  3.31it/s]
 63%|██████▎   | 235283/371472 [7:41:31<11:20:13,  3.34it/s]
 63%|██████▎   | 235284/371472 [7:41:31<10:52:41,  3.48it/s]
 63%|██████▎   | 235285/371472 [7:41:31<10:52:22,  3.48it/s]
 63%|██████▎   | 235286/371472 [7:41:32<10:50:24,  3.49it/s]
 63%|██████▎   | 235287/371472 [7:41:32<11:04:37,  3.42it/s]
 63%|██████▎   | 235288/371472 [7:41:32<10:36:25,  3.57it/s]
 63%|██████▎   | 235289/371472 [7:41:33<10:37:44,  3.56it/s]
 63%|██████▎   | 235290/371472 [7:41:33<10:21:42,  3.65it/s]
 63%|██████▎   | 235291/371472 [7:41:33<10:14:49,  3.69it/s]
 63%|██████▎   | 235292/371472 [7:41:33<10:06:47,  3.74it/s]
 63%|██████▎   | 235293/371472 [7:41:34<10:02:42,  3.77it/s]
 63%|██████▎   | 235294/371472 [7:41:34<10:38:58,  3.55it/s]
 63%|██████▎   | 235295/371472 [7:41:34<11:40:14,  3.24it/s]
 63%|██████▎   | 235296/371472 [7:41:35<10:59:39,  3.44it/s]
 63%|██████▎   | 235297/371472 [7:41:35<10:39:14,  3.55it/s]
 63%|██████▎   | 235298/371472 [7:41:35<10:34:13,  3.58it/s]
 63%|██████▎   | 235299/371472 [7:41:35<10:30:05,  3.60it/s]
 63%|██████▎   | 235300/371472 [7:41:36<10:23:11,  3.64it/s]
                                                            
{'loss': 2.8586, 'learning_rate': 4.3009437824559885e-07, 'epoch': 10.13}
+
 63%|██████▎   | 235300/371472 [7:41:36<10:23:11,  3.64it/s]
 63%|██████▎   | 235301/371472 [7:41:36<10:13:35,  3.70it/s]
 63%|██████▎   | 235302/371472 [7:41:36<10:03:08,  3.76it/s]
 63%|██████▎   | 235303/371472 [7:41:36<10:10:41,  3.72it/s]
 63%|██████▎   | 235304/371472 [7:41:37<10:28:24,  3.61it/s]
 63%|██████▎   | 235305/371472 [7:41:37<11:19:00,  3.34it/s]
 63%|██████▎   | 235306/371472 [7:41:37<11:21:59,  3.33it/s]
 63%|██████▎   | 235307/371472 [7:41:38<10:51:56,  3.48it/s]
 63%|██████▎   | 235308/371472 [7:41:38<10:34:45,  3.58it/s]
 63%|██████▎   | 235309/371472 [7:41:38<11:13:15,  3.37it/s]
 63%|██████▎   | 235310/371472 [7:41:39<11:45:33,  3.22it/s]
 63%|██████▎   | 235311/371472 [7:41:39<11:42:08,  3.23it/s]
 63%|██████▎   | 235312/371472 [7:41:39<11:14:51,  3.36it/s]
 63%|██████▎   | 235313/371472 [7:41:40<12:15:04,  3.09it/s]
 63%|██████▎   | 235314/371472 [7:41:40<11:55:18,  3.17it/s]
 63%|██████▎   | 235315/371472 [7:41:40<11:23:53,  3.32it/s]
 63%|██████▎   | 235316/371472 [7:41:40<11:04:53,  3.41it/s]
 63%|██████▎   | 235317/371472 [7:41:41<10:32:05,  3.59it/s]
 63%|██████▎   | 235318/371472 [7:41:41<10:12:24,  3.71it/s]
 63%|██████▎   | 235319/371472 [7:41:41<10:19:18,  3.66it/s]
 63%|██████▎   | 235320/371472 [7:41:41<10:22:25,  3.65it/s]
                                                            
{'loss': 2.7754, 'learning_rate': 4.300458962701201e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235320/371472 [7:41:41<10:22:25,  3.65it/s]
 63%|██████▎   | 235321/371472 [7:41:42<11:31:49,  3.28it/s]
 63%|██████▎   | 235322/371472 [7:41:42<10:54:12,  3.47it/s]
 63%|██████▎   | 235323/371472 [7:41:42<10:34:05,  3.58it/s]
 63%|██████▎   | 235324/371472 [7:41:43<10:48:38,  3.50it/s]
 63%|██████▎   | 235325/371472 [7:41:43<10:29:39,  3.60it/s]
 63%|██████▎   | 235326/371472 [7:41:43<10:20:26,  3.66it/s]
 63%|██████▎   | 235327/371472 [7:41:43<10:46:46,  3.51it/s]
 63%|██████▎   | 235328/371472 [7:41:44<10:19:18,  3.66it/s]
 63%|██████▎   | 235329/371472 [7:41:44<10:10:05,  3.72it/s]
 63%|██████▎   | 235330/371472 [7:41:44<10:10:14,  3.72it/s]
 63%|██████▎   | 235331/371472 [7:41:45<10:09:47,  3.72it/s]
 63%|██████▎   | 235332/371472 [7:41:45<10:26:23,  3.62it/s]
 63%|██████▎   | 235333/371472 [7:41:45<10:20:21,  3.66it/s]
 63%|██████▎   | 235334/371472 [7:41:45<10:19:37,  3.66it/s]
 63%|██████▎   | 235335/371472 [7:41:46<10:14:48,  3.69it/s]
 63%|██████▎   | 235336/371472 [7:41:46<10:03:06,  3.76it/s]
 63%|██████▎   | 235337/371472 [7:41:46<10:40:16,  3.54it/s]
 63%|██████▎   | 235338/371472 [7:41:47<10:57:36,  3.45it/s]
 63%|██████▎   | 235339/371472 [7:41:47<11:44:41,  3.22it/s]
 63%|██████▎   | 235340/371472 [7:41:47<10:55:08,  3.46it/s]
                                                            
{'loss': 2.8215, 'learning_rate': 4.299974142946411e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235340/371472 [7:41:47<10:55:08,  3.46it/s]
 63%|██████▎   | 235341/371472 [7:41:47<10:56:18,  3.46it/s]
 63%|██████▎   | 235342/371472 [7:41:48<10:35:44,  3.57it/s]
 63%|██████▎   | 235343/371472 [7:41:48<10:41:39,  3.54it/s]
 63%|██████▎   | 235344/371472 [7:41:48<10:47:30,  3.50it/s]
 63%|██████▎   | 235345/371472 [7:41:49<10:55:40,  3.46it/s]
 63%|██████▎   | 235346/371472 [7:41:49<13:57:37,  2.71it/s]
 63%|██████▎   | 235347/371472 [7:41:49<12:50:08,  2.95it/s]
 63%|██████▎   | 235348/371472 [7:41:50<12:20:19,  3.06it/s]
 63%|██████▎   | 235349/371472 [7:41:50<11:32:01,  3.28it/s]
 63%|██████▎   | 235350/371472 [7:41:50<11:52:45,  3.18it/s]
 63%|██████▎   | 235351/371472 [7:41:51<11:50:05,  3.19it/s]
 63%|██████▎   | 235352/371472 [7:41:51<11:54:46,  3.17it/s]
 63%|██████▎   | 235353/371472 [7:41:51<11:32:45,  3.27it/s]
 63%|██████▎   | 235354/371472 [7:41:51<11:27:16,  3.30it/s]
 63%|██████▎   | 235355/371472 [7:41:52<12:01:26,  3.14it/s]
 63%|██████▎   | 235356/371472 [7:41:52<11:19:47,  3.34it/s]
 63%|██████▎   | 235357/371472 [7:41:52<10:45:23,  3.52it/s]
 63%|██████▎   | 235358/371472 [7:41:53<10:47:32,  3.50it/s]
 63%|██████▎   | 235359/371472 [7:41:53<10:23:42,  3.64it/s]
 63%|██████▎   | 235360/371472 [7:41:53<10:08:57,  3.73it/s]
                                                            
{'loss': 2.8125, 'learning_rate': 4.299489323191622e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235360/371472 [7:41:53<10:08:57,  3.73it/s]
 63%|██████▎   | 235361/371472 [7:41:53<10:30:56,  3.60it/s]
 63%|██████▎   | 235362/371472 [7:41:54<10:28:43,  3.61it/s]
 63%|██████▎   | 235363/371472 [7:41:54<10:35:07,  3.57it/s]
 63%|██████▎   | 235364/371472 [7:41:54<10:41:51,  3.53it/s]
 63%|██████▎   | 235365/371472 [7:41:55<11:05:38,  3.41it/s]
 63%|██████▎   | 235366/371472 [7:41:55<12:02:49,  3.14it/s]
 63%|██████▎   | 235367/371472 [7:41:55<11:45:32,  3.22it/s]
 63%|██████▎   | 235368/371472 [7:41:56<11:11:28,  3.38it/s]
 63%|██████▎   | 235369/371472 [7:41:56<11:08:21,  3.39it/s]
 63%|██████▎   | 235370/371472 [7:41:56<11:09:46,  3.39it/s]
 63%|██████▎   | 235371/371472 [7:41:56<10:53:58,  3.47it/s]
 63%|██████▎   | 235372/371472 [7:41:57<10:45:19,  3.52it/s]
 63%|██████▎   | 235373/371472 [7:41:57<11:15:33,  3.36it/s]
 63%|██████▎   | 235374/371472 [7:41:57<11:54:21,  3.18it/s]
 63%|██████▎   | 235375/371472 [7:41:58<11:37:53,  3.25it/s]
 63%|██████▎   | 235376/371472 [7:41:58<11:32:47,  3.27it/s]
 63%|██████▎   | 235377/371472 [7:41:58<11:20:34,  3.33it/s]
 63%|██████▎   | 235378/371472 [7:41:58<10:58:29,  3.44it/s]
 63%|██████▎   | 235379/371472 [7:41:59<11:48:38,  3.20it/s]
 63%|██████▎   | 235380/371472 [7:41:59<11:25:29,  3.31it/s]
                                                            
{'loss': 2.8452, 'learning_rate': 4.299004503436833e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235380/371472 [7:41:59<11:25:29,  3.31it/s]
 63%|██████▎   | 235381/371472 [7:41:59<11:09:44,  3.39it/s]
 63%|██████▎   | 235382/371472 [7:42:00<10:53:57,  3.47it/s]
 63%|██████▎   | 235383/371472 [7:42:00<10:43:04,  3.53it/s]
 63%|██████▎   | 235384/371472 [7:42:00<11:07:30,  3.40it/s]
 63%|██████▎   | 235385/371472 [7:42:01<11:12:07,  3.37it/s]
 63%|██████▎   | 235386/371472 [7:42:01<10:52:16,  3.48it/s]
 63%|██████▎   | 235387/371472 [7:42:01<10:42:54,  3.53it/s]
 63%|██████▎   | 235388/371472 [7:42:01<11:12:23,  3.37it/s]
 63%|██████▎   | 235389/371472 [7:42:02<11:54:28,  3.17it/s]
 63%|██████▎   | 235390/371472 [7:42:02<11:49:59,  3.19it/s]
 63%|██████▎   | 235391/371472 [7:42:02<11:32:58,  3.27it/s]
 63%|██████▎   | 235392/371472 [7:42:03<11:26:17,  3.30it/s]
 63%|██████▎   | 235393/371472 [7:42:03<10:56:58,  3.45it/s]
 63%|██████▎   | 235394/371472 [7:42:03<10:46:30,  3.51it/s]
 63%|██████▎   | 235395/371472 [7:42:04<10:53:23,  3.47it/s]
 63%|██████▎   | 235396/371472 [7:42:04<10:41:12,  3.54it/s]
 63%|██████▎   | 235397/371472 [7:42:04<10:31:49,  3.59it/s]
 63%|██████▎   | 235398/371472 [7:42:04<10:28:06,  3.61it/s]
 63%|██████▎   | 235399/371472 [7:42:05<11:02:45,  3.42it/s]
 63%|██████▎   | 235400/371472 [7:42:05<11:00:13,  3.44it/s]
                                                            
{'loss': 2.7508, 'learning_rate': 4.298519683682045e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235400/371472 [7:42:05<11:00:13,  3.44it/s]
 63%|██████▎   | 235401/371472 [7:42:05<10:51:21,  3.48it/s]
 63%|██████▎   | 235402/371472 [7:42:05<10:31:14,  3.59it/s]
 63%|██████▎   | 235403/371472 [7:42:06<10:17:57,  3.67it/s]
 63%|█████���▎   | 235404/371472 [7:42:06<10:13:21,  3.70it/s]
 63%|██████▎   | 235405/371472 [7:42:06<10:09:58,  3.72it/s]
 63%|██████▎   | 235406/371472 [7:42:07<9:55:42,  3.81it/s] 
 63%|██████▎   | 235407/371472 [7:42:07<10:17:59,  3.67it/s]
 63%|██████▎   | 235408/371472 [7:42:07<10:16:24,  3.68it/s]
 63%|██████▎   | 235409/371472 [7:42:07<11:17:44,  3.35it/s]
 63%|██████▎   | 235410/371472 [7:42:08<10:52:43,  3.47it/s]
 63%|██████▎   | 235411/371472 [7:42:08<10:40:44,  3.54it/s]
 63%|██████▎   | 235412/371472 [7:42:08<10:36:03,  3.57it/s]
 63%|██████▎   | 235413/371472 [7:42:09<10:28:13,  3.61it/s]
 63%|██████▎   | 235414/371472 [7:42:09<10:11:50,  3.71it/s]
 63%|██████▎   | 235415/371472 [7:42:09<9:58:44,  3.79it/s] 
 63%|██████▎   | 235416/371472 [7:42:09<9:49:27,  3.85it/s]
 63%|██████▎   | 235417/371472 [7:42:10<10:01:27,  3.77it/s]
 63%|██████▎   | 235418/371472 [7:42:10<10:17:30,  3.67it/s]
 63%|██████▎   | 235419/371472 [7:42:10<10:20:00,  3.66it/s]
 63%|██████▎   | 235420/371472 [7:42:10<10:48:00,  3.50it/s]
                                                            
{'loss': 2.8295, 'learning_rate': 4.298034863927255e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235420/371472 [7:42:10<10:48:00,  3.50it/s]
 63%|██████▎   | 235421/371472 [7:42:11<10:41:13,  3.54it/s]
 63%|██████▎   | 235422/371472 [7:42:11<10:46:02,  3.51it/s]
 63%|██████▎   | 235423/371472 [7:42:11<11:04:09,  3.41it/s]
 63%|██████▎   | 235424/371472 [7:42:12<10:46:19,  3.51it/s]
 63%|██████▎   | 235425/371472 [7:42:12<10:25:54,  3.62it/s]
 63%|██████▎   | 235426/371472 [7:42:12<10:12:30,  3.70it/s]
 63%|██████▎   | 235427/371472 [7:42:12<9:59:28,  3.78it/s] 
 63%|██████▎   | 235428/371472 [7:42:13<10:00:17,  3.78it/s]
 63%|██████▎   | 235429/371472 [7:42:13<10:35:59,  3.57it/s]
 63%|██████▎   | 235430/371472 [7:42:13<11:13:40,  3.37it/s]
 63%|██████▎   | 235431/371472 [7:42:14<11:07:55,  3.39it/s]
 63%|██████▎   | 235432/371472 [7:42:14<10:45:21,  3.51it/s]
 63%|██████▎   | 235433/371472 [7:42:14<10:55:55,  3.46it/s]
 63%|██████▎   | 235434/371472 [7:42:14<10:37:47,  3.55it/s]
 63%|██████▎   | 235435/371472 [7:42:15<10:25:46,  3.62it/s]
 63%|██████▎   | 235436/371472 [7:42:15<10:26:50,  3.62it/s]
 63%|██████▎   | 235437/371472 [7:42:15<10:37:48,  3.55it/s]
 63%|██████▎   | 235438/371472 [7:42:15<10:17:45,  3.67it/s]
 63%|██████▎   | 235439/371472 [7:42:16<10:18:12,  3.67it/s]
 63%|██████▎   | 235440/371472 [7:42:16<10:04:58,  3.75it/s]
                                                            
{'loss': 2.8932, 'learning_rate': 4.2975500441724667e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235440/371472 [7:42:16<10:04:58,  3.75it/s]
 63%|██████▎   | 235441/371472 [7:42:16<10:17:26,  3.67it/s]
 63%|██████▎   | 235442/371472 [7:42:17<10:14:43,  3.69it/s]
 63%|██████▎   | 235443/371472 [7:42:17<10:55:21,  3.46it/s]
 63%|██████▎   | 235444/371472 [7:42:17<11:30:33,  3.28it/s]
 63%|██████▎   | 235445/371472 [7:42:17<10:57:38,  3.45it/s]
 63%|██████▎   | 235446/371472 [7:42:18<11:03:06,  3.42it/s]
 63%|██████▎   | 235447/371472 [7:42:18<10:55:45,  3.46it/s]
 63%|██████▎   | 235448/371472 [7:42:18<10:43:17,  3.52it/s]
 63%|██████▎   | 235449/371472 [7:42:19<10:19:47,  3.66it/s]
 63%|██████▎   | 235450/371472 [7:42:19<10:16:29,  3.68it/s]
 63%|██████▎   | 235451/371472 [7:42:19<10:09:12,  3.72it/s]
 63%|██████▎   | 235452/371472 [7:42:19<9:57:40,  3.79it/s] 
 63%|██████▎   | 235453/371472 [7:42:20<9:51:11,  3.83it/s]
 63%|██████▎   | 235454/371472 [7:42:20<9:41:23,  3.90it/s]
 63%|██████▎   | 235455/371472 [7:42:20<9:39:13,  3.91it/s]
 63%|██████▎   | 235456/371472 [7:42:20<9:54:23,  3.81it/s]
 63%|██████▎   | 235457/371472 [7:42:21<10:28:45,  3.61it/s]
 63%|██████▎   | 235458/371472 [7:42:21<10:22:26,  3.64it/s]
 63%|██████▎   | 235459/371472 [7:42:21<10:24:13,  3.63it/s]
 63%|██████▎   | 235460/371472 [7:42:21<10:18:58,  3.66it/s]
                                                            
{'loss': 2.8288, 'learning_rate': 4.2970652244176774e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235460/371472 [7:42:21<10:18:58,  3.66it/s]
 63%|██████▎   | 235461/371472 [7:42:22<11:28:58,  3.29it/s]
 63%|██████▎   | 235462/371472 [7:42:22<10:44:36,  3.52it/s]
 63%|██████▎   | 235463/371472 [7:42:22<10:43:44,  3.52it/s]
 63%|██████▎   | 235464/371472 [7:42:23<10:54:10,  3.47it/s]
 63%|██████▎   | 235465/371472 [7:42:23<10:52:41,  3.47it/s]
 63%|██████▎   | 235466/371472 [7:42:23<11:03:57,  3.41it/s]
 63%|██████▎   | 235467/371472 [7:42:24<11:03:02,  3.42it/s]
 63%|██████▎   | 235468/371472 [7:42:24<10:42:56,  3.53it/s]
 63%|██████▎   | 235469/371472 [7:42:24<10:35:49,  3.56it/s]
 63%|██████▎   | 235470/371472 [7:42:24<10:39:16,  3.55it/s]
 63%|██████▎   | 235471/371472 [7:42:25<10:12:58,  3.70it/s]
 63%|██████▎   | 235472/371472 [7:42:25<10:07:47,  3.73it/s]
 63%|██████▎   | 235473/371472 [7:42:25<11:21:03,  3.33it/s]
 63%|██████▎   | 235474/371472 [7:42:26<11:12:22,  3.37it/s]
 63%|██████▎   | 235475/371472 [7:42:26<10:58:53,  3.44it/s]
 63%|██████▎   | 235476/371472 [7:42:26<10:56:58,  3.45it/s]
 63%|██████▎   | 235477/371472 [7:42:26<11:32:24,  3.27it/s]
 63%|██████▎   | 235478/371472 [7:42:27<12:10:12,  3.10it/s]
 63%|██████▎   | 235479/371472 [7:42:27<12:08:48,  3.11it/s]
 63%|██████▎   | 235480/371472 [7:42:27<11:40:43,  3.23it/s]
                                                            
{'loss': 2.9611, 'learning_rate': 4.2965804046628887e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235480/371472 [7:42:27<11:40:43,  3.23it/s]
 63%|██████▎   | 235481/371472 [7:42:28<11:45:11,  3.21it/s]
 63%|██████▎   | 235482/371472 [7:42:28<11:21:55,  3.32it/s]
 63%|██████▎   | 235483/371472 [7:42:28<11:20:53,  3.33it/s]
 63%|██████▎   | 235484/371472 [7:42:29<10:45:29,  3.51it/s]
 63%|██████▎   | 235485/371472 [7:42:29<10:30:51,  3.59it/s]
 63%|██████▎   | 235486/371472 [7:42:29<10:14:45,  3.69it/s]
 63%|██████▎   | 235487/371472 [7:42:29<10:21:35,  3.65it/s]
 63%|██████▎   | 235488/371472 [7:42:30<9:58:41,  3.79it/s] 
 63%|██████▎   | 235489/371472 [7:42:30<10:15:48,  3.68it/s]
 63%|██████▎   | 235490/371472 [7:42:30<10:46:22,  3.51it/s]
 63%|██████▎   | 235491/371472 [7:42:30<10:32:30,  3.58it/s]
 63%|██████▎   | 235492/371472 [7:42:31<10:36:13,  3.56it/s]
 63%|██████▎   | 235493/371472 [7:42:31<10:29:46,  3.60it/s]
 63%|██████▎   | 235494/371472 [7:42:31<10:20:43,  3.65it/s]
 63%|██████▎   | 235495/371472 [7:42:32<10:16:23,  3.68it/s]
 63%|██████▎   | 235496/371472 [7:42:32<10:37:11,  3.56it/s]
 63%|██████▎   | 235497/371472 [7:42:32<11:48:48,  3.20it/s]
 63%|██████▎   | 235498/371472 [7:42:33<11:02:36,  3.42it/s]
 63%|██████▎   | 235499/371472 [7:42:33<10:45:21,  3.51it/s]
 63%|██████▎   | 235500/371472 [7:42:33<10:12:20,  3.70it/s]
                                                            
{'loss': 2.852, 'learning_rate': 4.2960955849080994e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235500/371472 [7:42:33<10:12:20,  3.70it/s]
 63%|██████▎   | 235501/371472 [7:42:33<10:02:16,  3.76it/s]
 63%|██████▎   | 235502/371472 [7:42:34<10:36:23,  3.56it/s]
 63%|██████▎   | 235503/371472 [7:42:34<10:36:51,  3.56it/s]
 63%|██████▎   | 235504/371472 [7:42:34<10:34:59,  3.57it/s]
 63%|██████▎   | 235505/371472 [7:42:34<10:26:52,  3.61it/s]
 63%|██████▎   | 235506/371472 [7:42:35<10:03:05,  3.76it/s]
 63%|██████▎   | 235507/371472 [7:42:35<10:32:27,  3.58it/s]
 63%|██████▎   | 235508/371472 [7:42:35<11:02:05,  3.42it/s]
 63%|██████▎   | 235509/371472 [7:42:36<11:23:03,  3.32it/s]
 63%|██████▎   | 235510/371472 [7:42:36<10:56:28,  3.45it/s]
 63%|██████▎   | 235511/371472 [7:42:36<11:28:39,  3.29it/s]
 63%|██████▎   | 235512/371472 [7:42:36<11:02:45,  3.42it/s]
 63%|██████▎   | 235513/371472 [7:42:37<10:40:59,  3.54it/s]
 63%|██████▎   | 235514/371472 [7:42:37<10:43:00,  3.52it/s]
 63%|██████▎   | 235515/371472 [7:42:37<10:43:35,  3.52it/s]
 63%|██████▎   | 235516/371472 [7:42:38<10:55:01,  3.46it/s]
 63%|██████▎   | 235517/371472 [7:42:38<10:27:09,  3.61it/s]
 63%|██████▎   | 235518/371472 [7:42:38<11:01:28,  3.43it/s]
 63%|██████▎   | 235519/371472 [7:42:38<10:28:09,  3.61it/s]
 63%|██████▎   | 235520/371472 [7:42:39<10:23:30,  3.63it/s]
                                                            
{'loss': 2.8876, 'learning_rate': 4.295610765153311e-07, 'epoch': 10.14}
+
 63%|██████▎   | 235520/371472 [7:42:39<10:23:30,  3.63it/s]
 63%|██████▎   | 235521/371472 [7:42:39<10:04:49,  3.75it/s]
 63%|██████▎   | 235522/371472 [7:42:39<9:55:28,  3.81it/s] 
 63%|██████▎   | 235523/371472 [7:42:39<9:52:04,  3.83it/s]
 63%|██████▎   | 235524/371472 [7:42:40<10:23:49,  3.63it/s]
 63%|██████▎   | 235525/371472 [7:42:40<10:08:57,  3.72it/s]
 63%|██████▎   | 235526/371472 [7:42:40<9:55:08,  3.81it/s] 
 63%|██████▎   | 235527/371472 [7:42:41<10:00:13,  3.77it/s]
 63%|██████▎   | 235528/371472 [7:42:41<10:42:18,  3.53it/s]
 63%|██████▎   | 235529/371472 [7:42:41<10:24:11,  3.63it/s]
 63%|██████▎   | 235530/371472 [7:42:41<10:08:00,  3.73it/s]
 63%|██████▎   | 235531/371472 [7:42:42<9:52:55,  3.82it/s] 
 63%|██████▎   | 235532/371472 [7:42:42<10:02:07,  3.76it/s]
 63%|██████▎   | 235533/371472 [7:42:42<10:02:23,  3.76it/s]
 63%|██████▎   | 235534/371472 [7:42:42<10:52:00,  3.47it/s]
 63%|██████▎   | 235535/371472 [7:42:43<10:26:20,  3.62it/s]
 63%|██████▎   | 235536/371472 [7:42:43<10:08:25,  3.72it/s]
 63%|██████▎   | 235537/371472 [7:42:43<10:00:58,  3.77it/s]
 63%|██████▎   | 235538/371472 [7:42:43<9:49:56,  3.84it/s] 
 63%|██████▎   | 235539/371472 [7:42:44<9:49:38,  3.84it/s]
 63%|██████▎   | 235540/371472 [7:42:44<9:46:22,  3.86it/s]
                                                           
{'loss': 2.8638, 'learning_rate': 4.2951259453985213e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235540/371472 [7:42:44<9:46:22,  3.86it/s]
 63%|██████▎   | 235541/371472 [7:42:44<10:13:19,  3.69it/s]
 63%|██████▎   | 235542/371472 [7:42:45<10:41:50,  3.53it/s]
 63%|██████▎   | 235543/371472 [7:42:45<10:25:47,  3.62it/s]
 63%|██████▎   | 235544/371472 [7:42:45<10:20:53,  3.65it/s]
 63%|██████▎   | 235545/371472 [7:42:45<10:39:01,  3.55it/s]
 63%|██████▎   | 235546/371472 [7:42:46<10:45:23,  3.51it/s]
 63%|██████▎   | 235547/371472 [7:42:46<10:43:12,  3.52it/s]
 63%|██████▎   | 235548/371472 [7:42:46<11:07:17,  3.39it/s]
 63%|██████▎   | 235549/371472 [7:42:47<11:11:31,  3.37it/s]
 63%|██████▎   | 235550/371472 [7:42:47<11:00:30,  3.43it/s]
 63%|██████▎   | 235551/371472 [7:42:47<10:53:55,  3.46it/s]
 63%|██████▎   | 235552/371472 [7:42:47<10:27:53,  3.61it/s]
 63%|██████▎   | 235553/371472 [7:42:48<10:11:20,  3.71it/s]
 63%|██████▎   | 235554/371472 [7:42:48<10:02:17,  3.76it/s]
 63%|██████▎   | 235555/371472 [7:42:48<10:17:25,  3.67it/s]
 63%|██████▎   | 235556/371472 [7:42:49<11:07:33,  3.39it/s]
 63%|██████▎   | 235557/371472 [7:42:49<11:10:14,  3.38it/s]
 63%|██████▎   | 235558/371472 [7:42:49<11:06:04,  3.40it/s]
 63%|██████▎   | 235559/371472 [7:42:49<10:33:44,  3.57it/s]
 63%|██████▎   | 235560/371472 [7:42:50<10:16:21,  3.68it/s]
                                                            
{'loss': 2.8175, 'learning_rate': 4.294641125643733e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235560/371472 [7:42:50<10:16:21,  3.68it/s]
 63%|██████▎   | 235561/371472 [7:42:50<10:00:52,  3.77it/s]
 63%|██████▎   | 235562/371472 [7:42:50<9:48:47,  3.85it/s] 
 63%|██████▎   | 235563/371472 [7:42:50<9:37:58,  3.92it/s]
 63%|██████▎   | 235564/371472 [7:42:51<9:25:54,  4.00it/s]
 63%|██████▎   | 235565/371472 [7:42:51<9:34:13,  3.94it/s]
 63%|██████▎   | 235566/371472 [7:42:51<9:41:31,  3.90it/s]
 63%|██████▎   | 235567/371472 [7:42:51<10:10:19,  3.71it/s]
 63%|██████▎   | 235568/371472 [7:42:52<10:57:50,  3.44it/s]
 63%|██████▎   | 235569/371472 [7:42:52<11:39:36,  3.24it/s]
 63%|██████▎   | 235570/371472 [7:42:52<11:42:53,  3.22it/s]
 63%|██████▎   | 235571/371472 [7:42:53<11:23:03,  3.32it/s]
 63%|██████▎   | 235572/371472 [7:42:53<10:59:15,  3.44it/s]
 63%|██████▎   | 235573/371472 [7:42:53<10:52:26,  3.47it/s]
 63%|██████▎   | 235574/371472 [7:42:54<10:46:51,  3.50it/s]
 63%|██████▎   | 235575/371472 [7:42:54<10:48:41,  3.49it/s]
 63%|██████▎   | 235576/371472 [7:42:54<10:55:32,  3.46it/s]
 63%|██████▎   | 235577/371472 [7:42:54<10:37:13,  3.55it/s]
 63%|██████▎   | 235578/371472 [7:42:55<10:35:10,  3.57it/s]
 63%|██████▎   | 235579/371472 [7:42:55<11:12:40,  3.37it/s]
 63%|██████▎   | 235580/371472 [7:42:55<10:59:05,  3.44it/s]
                                                            
{'loss': 2.8745, 'learning_rate': 4.294156305888944e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235580/371472 [7:42:55<10:59:05,  3.44it/s]
 63%|██████▎   | 235581/371472 [7:42:56<10:48:59,  3.49it/s]
 63%|██████▎   | 235582/371472 [7:42:56<10:32:07,  3.58it/s]
 63%|██████▎   | 235583/371472 [7:42:56<10:49:13,  3.49it/s]
 63%|██████▎   | 235584/371472 [7:42:56<10:23:06,  3.63it/s]
 63%|██████▎   | 235585/371472 [7:42:57<10:07:39,  3.73it/s]
 63%|██████▎   | 235586/371472 [7:42:57<10:07:09,  3.73it/s]
 63%|██████▎   | 235587/371472 [7:42:57<10:18:33,  3.66it/s]
 63%|██████▎   | 235588/371472 [7:42:58<10:49:35,  3.49it/s]
 63%|██████▎   | 235589/371472 [7:42:58<11:00:39,  3.43it/s]
 63%|██████▎   | 235590/371472 [7:42:58<10:31:18,  3.59it/s]
 63%|██████▎   | 235591/371472 [7:42:58<10:19:26,  3.66it/s]
 63%|██████▎   | 235592/371472 [7:42:59<10:17:08,  3.67it/s]
 63%|██████▎   | 235593/371472 [7:42:59<10:09:28,  3.72it/s]
 63%|██████▎   | 235594/371472 [7:42:59<10:32:06,  3.58it/s]
 63%|██████▎   | 235595/371472 [7:43:00<11:06:30,  3.40it/s]
 63%|██████▎   | 235596/371472 [7:43:00<11:36:26,  3.25it/s]
 63%|██████▎   | 235597/371472 [7:43:00<11:13:04,  3.36it/s]
 63%|██████▎   | 235598/371472 [7:43:00<11:10:26,  3.38it/s]
 63%|██████▎   | 235599/371472 [7:43:01<11:04:50,  3.41it/s]
 63%|██████▎   | 235600/371472 [7:43:01<10:59:54,  3.43it/s]
                                                            
{'loss': 2.8727, 'learning_rate': 4.293671486134155e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235600/371472 [7:43:01<10:59:54,  3.43it/s]
 63%|██████▎   | 235601/371472 [7:43:01<11:09:56,  3.38it/s]
 63%|██████▎   | 235602/371472 [7:43:02<10:56:58,  3.45it/s]
 63%|██████▎   | 235603/371472 [7:43:02<10:29:43,  3.60it/s]
 63%|██████▎   | 235604/371472 [7:43:02<10:34:30,  3.57it/s]
 63%|██████▎   | 235605/371472 [7:43:02<10:48:42,  3.49it/s]
 63%|██████▎   | 235606/371472 [7:43:03<10:18:07,  3.66it/s]
 63%|██████▎   | 235607/371472 [7:43:03<9:53:09,  3.82it/s] 
 63%|██████▎   | 235608/371472 [7:43:03<10:04:52,  3.74it/s]
 63%|██████▎   | 235609/371472 [7:43:03<10:20:15,  3.65it/s]
 63%|██████▎   | 235610/371472 [7:43:04<10:23:03,  3.63it/s]
 63%|██████▎   | 235611/371472 [7:43:04<9:58:55,  3.78it/s] 
 63%|██████▎   | 235612/371472 [7:43:04<10:29:04,  3.60it/s]
 63%|██████▎   | 235613/371472 [7:43:05<9:57:53,  3.79it/s] 
 63%|██████▎   | 235614/371472 [7:43:05<9:42:16,  3.89it/s]
 63%|██████▎   | 235615/371472 [7:43:05<10:34:57,  3.57it/s]
 63%|██████▎   | 235616/371472 [7:43:05<11:11:13,  3.37it/s]
 63%|██████▎   | 235617/371472 [7:43:06<10:55:22,  3.45it/s]
 63%|██████▎   | 235618/371472 [7:43:06<11:19:46,  3.33it/s]
 63%|██████▎   | 235619/371472 [7:43:06<11:38:51,  3.24it/s]
 63%|██████▎   | 235620/371472 [7:43:07<11:22:36,  3.32it/s]
                                                            
{'loss': 2.8814, 'learning_rate': 4.293186666379366e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235620/371472 [7:43:07<11:22:36,  3.32it/s]
 63%|██████▎   | 235621/371472 [7:43:07<12:04:26,  3.13it/s]
 63%|██████▎   | 235622/371472 [7:43:07<11:46:29,  3.20it/s]
 63%|██████▎   | 235623/371472 [7:43:08<10:56:58,  3.45it/s]
 63%|██████▎   | 235624/371472 [7:43:08<11:55:19,  3.17it/s]
 63%|██████▎   | 235625/371472 [7:43:08<11:10:30,  3.38it/s]
 63%|██████▎   | 235626/371472 [7:43:09<11:31:13,  3.28it/s]
 63%|██████▎   | 235627/371472 [7:43:09<11:37:45,  3.24it/s]
 63%|██████▎   | 235628/371472 [7:43:09<11:09:59,  3.38it/s]
 63%|██████▎   | 235629/371472 [7:43:09<10:27:45,  3.61it/s]
 63%|██████▎   | 235630/371472 [7:43:10<10:09:39,  3.71it/s]
 63%|██████▎   | 235631/371472 [7:43:10<10:02:37,  3.76it/s]
 63%|██████▎   | 235632/371472 [7:43:10<10:19:36,  3.65it/s]
 63%|██████▎   | 235633/371472 [7:43:10<10:18:59,  3.66it/s]
 63%|██████▎   | 235634/371472 [7:43:11<10:09:16,  3.72it/s]
 63%|██████▎   | 235635/371472 [7:43:11<10:17:07,  3.67it/s]
 63%|██████▎   | 235636/371472 [7:43:11<10:13:21,  3.69it/s]
 63%|██████▎   | 235637/371472 [7:43:12<10:32:33,  3.58it/s]
 63%|██████▎   | 235638/371472 [7:43:12<11:57:46,  3.15it/s]
 63%|██████▎   | 235639/371472 [7:43:12<11:27:07,  3.29it/s]
 63%|██████▎   | 235640/371472 [7:43:12<11:18:40,  3.34it/s]
                                                            
{'loss': 2.8908, 'learning_rate': 4.2927018466245765e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235640/371472 [7:43:12<11:18:40,  3.34it/s]
 63%|██████▎   | 235641/371472 [7:43:13<10:55:25,  3.45it/s]
 63%|██████▎   | 235642/371472 [7:43:13<10:39:07,  3.54it/s]
 63%|██████▎   | 235643/371472 [7:43:13<10:21:14,  3.64it/s]
 63%|██████▎   | 235644/371472 [7:43:14<10:28:14,  3.60it/s]
 63%|██████▎   | 235645/371472 [7:43:14<10:42:42,  3.52it/s]
 63%|██████▎   | 235646/371472 [7:43:14<10:54:15,  3.46it/s]
 63%|██████▎   | 235647/371472 [7:43:14<10:36:38,  3.56it/s]
 63%|██████▎   | 235648/371472 [7:43:15<10:20:19,  3.65it/s]
 63%|██████▎   | 235649/371472 [7:43:15<10:23:02,  3.63it/s]
 63%|██████▎   | 235650/371472 [7:43:15<10:28:06,  3.60it/s]
 63%|██████▎   | 235651/371472 [7:43:15<10:09:53,  3.71it/s]
 63%|██████▎   | 235652/371472 [7:43:16<10:14:46,  3.68it/s]
 63%|██████▎   | 235653/371472 [7:43:16<9:59:17,  3.78it/s] 
 63%|██████▎   | 235654/371472 [7:43:16<10:19:23,  3.65it/s]
 63%|██████▎   | 235655/371472 [7:43:17<11:05:51,  3.40it/s]
 63%|██████▎   | 235656/371472 [7:43:17<11:01:29,  3.42it/s]
 63%|██████▎   | 235657/371472 [7:43:17<11:45:30,  3.21it/s]
 63%|██████▎   | 235658/371472 [7:43:18<11:16:53,  3.34it/s]
 63%|██████▎   | 235659/371472 [7:43:18<10:56:20,  3.45it/s]
 63%|██████▎   | 235660/371472 [7:43:18<10:49:19,  3.49it/s]
                                                            
{'loss': 2.7536, 'learning_rate': 4.2922170268697883e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235660/371472 [7:43:18<10:49:19,  3.49it/s]
 63%|██████▎   | 235661/371472 [7:43:18<10:43:16,  3.52it/s]
 63%|██████▎   | 235662/371472 [7:43:19<10:45:34,  3.51it/s]
 63%|██████▎   | 235663/371472 [7:43:19<10:21:37,  3.64it/s]
 63%|██████▎   | 235664/371472 [7:43:19<11:10:17,  3.38it/s]
 63%|██████▎   | 235665/371472 [7:43:20<10:45:30,  3.51it/s]
 63%|██████▎   | 235666/371472 [7:43:20<10:33:27,  3.57it/s]
 63%|██████▎   | 235667/371472 [7:43:20<10:09:48,  3.71it/s]
 63%|██████▎   | 235668/371472 [7:43:20<10:21:04,  3.64it/s]
 63%|██████▎   | 235669/371472 [7:43:21<10:09:47,  3.71it/s]
 63%|██████▎   | 235670/371472 [7:43:21<9:57:24,  3.79it/s] 
 63%|██████▎   | 235671/371472 [7:43:21<11:57:36,  3.15it/s]
 63%|██████▎   | 235672/371472 [7:43:22<11:38:12,  3.24it/s]
 63%|██████▎   | 235673/371472 [7:43:22<11:53:04,  3.17it/s]
 63%|██████▎   | 235674/371472 [7:43:22<11:43:09,  3.22it/s]
 63%|██████▎   | 235675/371472 [7:43:22<11:04:55,  3.40it/s]
 63%|██████▎   | 235676/371472 [7:43:23<11:43:45,  3.22it/s]
 63%|██████▎   | 235677/371472 [7:43:23<11:27:21,  3.29it/s]
 63%|██████▎   | 235678/371472 [7:43:23<11:33:24,  3.26it/s]
 63%|██████▎   | 235679/371472 [7:43:24<11:53:53,  3.17it/s]
 63%|██████▎   | 235680/371472 [7:43:24<11:07:04,  3.39it/s]
                                                            
{'loss': 3.0106, 'learning_rate': 4.2917322071149985e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235680/371472 [7:43:24<11:07:04,  3.39it/s]
 63%|██████▎   | 235681/371472 [7:43:24<11:15:28,  3.35it/s]
 63%|██████▎   | 235682/371472 [7:43:25<11:34:42,  3.26it/s]
 63%|██████▎   | 235683/371472 [7:43:25<11:48:00,  3.20it/s]
 63%|██████▎   | 235684/371472 [7:43:25<11:18:59,  3.33it/s]
 63%|██████▎   | 235685/371472 [7:43:25<11:12:34,  3.36it/s]
 63%|██████▎   | 235686/371472 [7:43:26<11:18:09,  3.34it/s]
 63%|██████▎   | 235687/371472 [7:43:26<10:58:55,  3.43it/s]
 63%|██████▎   | 235688/371472 [7:43:26<10:39:42,  3.54it/s]
 63%|██████▎   | 235689/371472 [7:43:27<10:26:35,  3.61it/s]
 63%|██████▎   | 235690/371472 [7:43:27<10:28:03,  3.60it/s]
 63%|██████▎   | 235691/371472 [7:43:27<11:39:31,  3.24it/s]
 63%|██████▎   | 235692/371472 [7:43:28<12:25:33,  3.04it/s]
 63%|██████▎   | 235693/371472 [7:43:28<13:09:40,  2.87it/s]
 63%|██████▎   | 235694/371472 [7:43:28<12:12:24,  3.09it/s]
 63%|██████▎   | 235695/371472 [7:43:29<11:30:02,  3.28it/s]
 63%|██████▎   | 235696/371472 [7:43:29<11:11:47,  3.37it/s]
 63%|██████▎   | 235697/371472 [7:43:29<10:57:05,  3.44it/s]
 63%|██████▎   | 235698/371472 [7:43:29<11:02:11,  3.42it/s]
 63%|██████▎   | 235699/371472 [7:43:30<11:04:52,  3.40it/s]
 63%|██████▎   | 235700/371472 [7:43:30<10:27:14,  3.61it/s]
                                                            
{'loss': 2.8685, 'learning_rate': 4.29124738736021e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235700/371472 [7:43:30<10:27:14,  3.61it/s]
 63%|██████▎   | 235701/371472 [7:43:30<10:12:31,  3.69it/s]
 63%|██████▎   | 235702/371472 [7:43:30<10:15:36,  3.68it/s]
 63%|██████▎   | 235703/371472 [7:43:31<11:28:54,  3.28it/s]
 63%|██████▎   | 235704/371472 [7:43:31<11:02:25,  3.42it/s]
 63%|██████▎   | 235705/371472 [7:43:32<12:00:17,  3.14it/s]
 63%|██████▎   | 235706/371472 [7:43:32<11:38:37,  3.24it/s]
 63%|██████▎   | 235707/371472 [7:43:32<11:19:29,  3.33it/s]
 63%|██████▎   | 235708/371472 [7:43:32<11:02:01,  3.42it/s]
 63%|██████▎   | 235709/371472 [7:43:33<11:12:51,  3.36it/s]
 63%|██████▎   | 235710/371472 [7:43:33<10:41:23,  3.53it/s]
 63%|██████▎   | 235711/371472 [7:43:33<11:31:38,  3.27it/s]
 63%|██████▎   | 235712/371472 [7:43:34<11:29:21,  3.28it/s]
 63%|██████▎   | 235713/371472 [7:43:34<10:46:13,  3.50it/s]
 63%|██████▎   | 235714/371472 [7:43:34<11:02:30,  3.42it/s]
 63%|██████▎   | 235715/371472 [7:43:34<10:56:25,  3.45it/s]
 63%|██████▎   | 235716/371472 [7:43:35<10:44:02,  3.51it/s]
 63%|██████▎   | 235717/371472 [7:43:35<10:26:52,  3.61it/s]
 63%|██████▎   | 235718/371472 [7:43:35<11:03:04,  3.41it/s]
 63%|██████▎   | 235719/371472 [7:43:36<10:55:38,  3.45it/s]
 63%|██████▎   | 235720/371472 [7:43:36<10:29:20,  3.60it/s]
                                                            
{'loss': 2.6483, 'learning_rate': 4.290762567605421e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235720/371472 [7:43:36<10:29:20,  3.60it/s]
 63%|██████▎   | 235721/371472 [7:43:36<10:46:57,  3.50it/s]
 63%|██████▎   | 235722/371472 [7:43:36<10:26:19,  3.61it/s]
 63%|██████▎   | 235723/371472 [7:43:37<10:40:45,  3.53it/s]
 63%|██████▎   | 235724/371472 [7:43:37<10:45:45,  3.50it/s]
 63%|██████▎   | 235725/371472 [7:43:37<11:03:47,  3.41it/s]
 63%|██████▎   | 235726/371472 [7:43:38<11:16:26,  3.34it/s]
 63%|██████▎   | 235727/371472 [7:43:38<10:56:34,  3.45it/s]
 63%|██████▎   | 235728/371472 [7:43:38<11:01:54,  3.42it/s]
 63%|██████▎   | 235729/371472 [7:43:38<10:41:42,  3.53it/s]
 63%|██████▎   | 235730/371472 [7:43:39<10:43:08,  3.52it/s]
 63%|██████▎   | 235731/371472 [7:43:39<10:27:39,  3.60it/s]
 63%|██████▎   | 235732/371472 [7:43:39<10:47:52,  3.49it/s]
 63%|██████▎   | 235733/371472 [7:43:40<10:45:40,  3.50it/s]
 63%|██████▎   | 235734/371472 [7:43:40<10:54:40,  3.46it/s]
 63%|██████▎   | 235735/371472 [7:43:40<10:26:26,  3.61it/s]
 63%|██████▎   | 235736/371472 [7:43:40<10:05:42,  3.73it/s]
 63%|██████▎   | 235737/371472 [7:43:41<10:07:56,  3.72it/s]
 63%|██████▎   | 235738/371472 [7:43:41<10:00:27,  3.77it/s]
 63%|██████▎   | 235739/371472 [7:43:41<10:51:04,  3.47it/s]
 63%|██████▎   | 235740/371472 [7:43:41<10:48:01,  3.49it/s]
                                                            
{'loss': 2.7786, 'learning_rate': 4.2902777478506327e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235740/371472 [7:43:41<10:48:01,  3.49it/s]
 63%|██████▎   | 235741/371472 [7:43:42<11:33:51,  3.26it/s]
 63%|██████▎   | 235742/371472 [7:43:42<11:29:01,  3.28it/s]
 63%|██████▎   | 235743/371472 [7:43:42<11:49:21,  3.19it/s]
 63%|██████▎   | 235744/371472 [7:43:43<11:20:30,  3.32it/s]
 63%|██████▎   | 235745/371472 [7:43:43<11:32:21,  3.27it/s]
 63%|██████▎   | 235746/371472 [7:43:43<10:49:59,  3.48it/s]
 63%|██████▎   | 235747/371472 [7:43:44<10:35:41,  3.56it/s]
 63%|██████▎   | 235748/371472 [7:43:44<10:18:18,  3.66it/s]
 63%|██████▎   | 235749/371472 [7:43:44<10:19:44,  3.65it/s]
 63%|██████▎   | 235750/371472 [7:43:44<10:14:47,  3.68it/s]
 63%|██████▎   | 235751/371472 [7:43:45<10:15:21,  3.68it/s]
 63%|██████▎   | 235752/371472 [7:43:45<10:19:35,  3.65it/s]
 63%|██████▎   | 235753/371472 [7:43:45<10:22:02,  3.64it/s]
 63%|██████▎   | 235754/371472 [7:43:45<10:28:38,  3.60it/s]
 63%|██████▎   | 235755/371472 [7:43:46<10:36:20,  3.55it/s]
 63%|██████▎   | 235756/371472 [7:43:46<11:20:43,  3.32it/s]
 63%|██████▎   | 235757/371472 [7:43:46<11:20:14,  3.33it/s]
 63%|██████▎   | 235758/371472 [7:43:47<11:12:07,  3.37it/s]
 63%|██████▎   | 235759/371472 [7:43:47<10:52:56,  3.46it/s]
 63%|██████▎   | 235760/371472 [7:43:47<10:17:37,  3.66it/s]
                                                            
{'loss': 2.9401, 'learning_rate': 4.289792928095843e-07, 'epoch': 10.15}
+
 63%|██████▎   | 235760/371472 [7:43:47<10:17:37,  3.66it/s]
 63%|██████▎   | 235761/371472 [7:43:47<10:19:46,  3.65it/s]
 63%|██████▎   | 235762/371472 [7:43:48<10:41:16,  3.53it/s]
 63%|██████▎   | 235763/371472 [7:43:48<10:25:58,  3.61it/s]
 63%|██████▎   | 235764/371472 [7:43:48<10:32:12,  3.58it/s]
 63%|██████▎   | 235765/371472 [7:43:49<10:19:58,  3.65it/s]
 63%|██████▎   | 235766/371472 [7:43:49<10:33:02,  3.57it/s]
 63%|██████▎   | 235767/371472 [7:43:49<11:27:19,  3.29it/s]
 63%|██████▎   | 235768/371472 [7:43:50<10:56:17,  3.45it/s]
 63%|██████▎   | 235769/371472 [7:43:50<11:12:00,  3.37it/s]
 63%|██████▎   | 235770/371472 [7:43:50<11:04:15,  3.40it/s]
 63%|██████▎   | 235771/371472 [7:43:50<10:38:26,  3.54it/s]
 63%|██████▎   | 235772/371472 [7:43:51<10:30:21,  3.59it/s]
 63%|██████▎   | 235773/371472 [7:43:51<10:51:32,  3.47it/s]
 63%|██████▎   | 235774/371472 [7:43:51<11:45:55,  3.20it/s]
 63%|██████▎   | 235775/371472 [7:43:52<10:56:27,  3.45it/s]
 63%|██████▎   | 235776/371472 [7:43:52<11:00:42,  3.42it/s]
 63%|██████▎   | 235777/371472 [7:43:52<10:37:49,  3.55it/s]
 63%|██████▎   | 235778/371472 [7:43:52<10:42:03,  3.52it/s]
 63%|██████▎   | 235779/371472 [7:43:53<10:32:48,  3.57it/s]
 63%|██████▎   | 235780/371472 [7:43:53<10:34:42,  3.56it/s]
                                                            
{'loss': 2.9923, 'learning_rate': 4.2893081083410547e-07, 'epoch': 10.16}
+
 63%|██████▎   | 235780/371472 [7:43:53<10:34:42,  3.56it/s]
 63%|██████▎   | 235781/371472 [7:43:53<11:10:51,  3.37it/s]
 63%|██████▎   | 235782/371472 [7:43:54<10:33:53,  3.57it/s]
 63%|██████▎   | 235783/371472 [7:43:54<10:39:18,  3.54it/s]
 63%|██████▎   | 235784/371472 [7:43:54<10:40:19,  3.53it/s]
 63%|██████▎   | 235785/371472 [7:43:54<10:27:21,  3.60it/s]
 63%|██████▎   | 235786/371472 [7:43:55<10:23:42,  3.63it/s]
 63%|██████▎   | 235787/371472 [7:43:55<11:05:36,  3.40it/s]
 63%|██████▎   | 235788/371472 [7:43:55<11:51:50,  3.18it/s]
 63%|██████▎   | 235789/371472 [7:43:56<11:43:14,  3.22it/s]
 63%|██████▎   | 235790/371472 [7:43:56<11:07:11,  3.39it/s]
 63%|██████▎   | 235791/371472 [7:43:56<11:07:00,  3.39it/s]
 63%|██████▎   | 235792/371472 [7:43:57<11:23:17,  3.31it/s]
 63%|██████▎   | 235793/371472 [7:43:57<11:30:35,  3.27it/s]
 63%|██████▎   | 235794/371472 [7:43:57<11:04:43,  3.40it/s]
 63%|██████▎   | 235795/371472 [7:43:57<10:36:36,  3.55it/s]
 63%|██████▎   | 235796/371472 [7:43:58<10:12:20,  3.69it/s]
 63%|██████▎   | 235797/371472 [7:43:58<10:16:30,  3.67it/s]
 63%|██████▎   | 235798/371472 [7:43:58<10:29:34,  3.59it/s]
 63%|██████▎   | 235799/371472 [7:43:58<10:43:27,  3.51it/s]
 63%|██████▎   | 235800/371472 [7:43:59<10:52:30,  3.47it/s]
                                                            
{'loss': 2.8164, 'learning_rate': 4.288823288586265e-07, 'epoch': 10.16}
+
 63%|██████▎   | 235800/371472 [7:43:59<10:52:30,  3.47it/s]
 63%|██████▎   | 235801/371472 [7:43:59<10:30:01,  3.59it/s]
 63%|██████▎   | 235802/371472 [7:43:59<10:12:11,  3.69it/s]
 63%|██████▎   | 235803/371472 [7:44:00<10:17:41,  3.66it/s]
 63%|██████▎   | 235804/371472 [7:44:00<10:45:55,  3.50it/s]
 63%|██████▎   | 235805/371472 [7:44:00<11:48:37,  3.19it/s]
 63%|██████▎   | 235806/371472 [7:44:01<11:37:53,  3.24it/s]
 63%|██████▎   | 235807/371472 [7:44:01<11:38:16,  3.24it/s]
 63%|██████▎   | 235808/371472 [7:44:01<11:03:48,  3.41it/s]
 63%|██████▎   | 235809/371472 [7:44:01<10:54:41,  3.45it/s]
 63%|██████▎   | 235810/371472 [7:44:02<10:37:34,  3.55it/s]
 63%|██████▎   | 235811/371472 [7:44:02<10:35:57,  3.56it/s]
 63%|██████▎   | 235812/371472 [7:44:02<10:46:58,  3.49it/s]
 63%|██████▎   | 235813/371472 [7:44:02<10:32:54,  3.57it/s]
 63%|██████▎   | 235814/371472 [7:44:03<11:13:27,  3.36it/s]
 63%|██████▎   | 235815/371472 [7:44:03<11:46:20,  3.20it/s]
 63%|██████▎   | 235816/371472 [7:44:03<11:14:40,  3.35it/s]
 63%|██████▎   | 235817/371472 [7:44:04<10:35:56,  3.56it/s]
 63%|██████▎   | 235818/371472 [7:44:04<10:45:38,  3.50it/s]
 63%|██████▎   | 235819/371472 [7:44:04<10:40:39,  3.53it/s]
 63%|██████▎   | 235820/371472 [7:44:05<10:22:12,  3.63it/s]
                                                            
{'loss': 2.7779, 'learning_rate': 4.2883384688314766e-07, 'epoch': 10.16}
+
 63%|██████▎   | 235820/371472 [7:44:05<10:22:12,  3.63it/s]
 63%|██████▎   | 235821/371472 [7:44:05<10:17:24,  3.66it/s]
 63%|██████▎   | 235822/371472 [7:44:05<10:14:31,  3.68it/s]
 63%|██████▎   | 235823/371472 [7:44:05<10:08:26,  3.72it/s]
 63%|██████▎   | 235824/371472 [7:44:06<10:03:35,  3.75it/s]
 63%|██████▎   | 235825/371472 [7:44:06<10:47:24,  3.49it/s]
 63%|██████▎   | 235826/371472 [7:44:06<10:21:39,  3.64it/s]
 63%|██████▎   | 235827/371472 [7:44:06<10:13:32,  3.68it/s]
 63%|██████▎   | 235828/371472 [7:44:07<10:17:04,  3.66it/s]
 63%|██████▎   | 235829/371472 [7:44:07<11:06:05,  3.39it/s]
 63%|██████▎   | 235830/371472 [7:44:07<10:41:34,  3.52it/s]
 63%|██████▎   | 235831/371472 [7:44:08<11:28:08,  3.29it/s]
 63%|██████▎   | 235832/371472 [7:44:08<11:42:29,  3.22it/s]
 63%|██████▎   | 235833/371472 [7:44:08<11:33:04,  3.26it/s]
 63%|██████▎   | 235834/371472 [7:44:09<11:16:01,  3.34it/s]
 63%|██████▎   | 235835/371472 [7:44:09<11:15:10,  3.35it/s]
 63%|██████▎   | 235836/371472 [7:44:09<10:50:03,  3.48it/s]
 63%|██████▎   | 235837/371472 [7:44:09<10:52:20,  3.47it/s]
 63%|██████▎   | 235838/371472 [7:44:10<10:58:00,  3.44it/s]
 63%|██████▎   | 235839/371472 [7:44:10<10:41:42,  3.52it/s]
 63%|██████▎   | 235840/371472 [7:44:10<10:26:05,  3.61it/s]
                                                            
{'loss': 2.8662, 'learning_rate': 4.2878536490766874e-07, 'epoch': 10.16}
+
 63%|██████▎   | 235840/371472 [7:44:10<10:26:05,  3.61it/s]
 63%|██████▎   | 235841/371472 [7:44:11<10:34:51,  3.56it/s]
 63%|██████▎   | 235842/371472 [7:44:11<10:33:58,  3.57it/s]
 63%|██████▎   | 235843/371472 [7:44:11<10:30:51,  3.58it/s]
 63%|██████▎   | 235844/371472 [7:44:11<10:51:03,  3.47it/s]
 63%|██████▎   | 235845/371472 [7:44:12<10:44:24,  3.51it/s]
 63%|██████▎   | 235846/371472 [7:44:12<10:31:10,  3.58it/s]
 63%|██████▎   | 235847/371472 [7:44:12<10:28:20,  3.60it/s]
 63%|██████▎   | 235848/371472 [7:44:12<10:23:50,  3.62it/s]
 63%|██████▎   | 235849/371472 [7:44:13<10:16:05,  3.67it/s]
 63%|██████▎   | 235850/371472 [7:44:13<10:06:42,  3.73it/s]
 63%|██████▎   | 235851/371472 [7:44:13<10:03:52,  3.74it/s]
 63%|██████▎   | 235852/371472 [7:44:14<10:21:24,  3.64it/s]
 63%|██████▎   | 235853/371472 [7:44:14<10:19:59,  3.65it/s]
 63%|██████▎   | 235854/371472 [7:44:14<10:34:40,  3.56it/s]
 63%|██████▎   | 235855/371472 [7:44:14<10:22:31,  3.63it/s]
 63%|██████▎   | 235856/371472 [7:44:15<11:24:21,  3.30it/s]
 63%|██████▎   | 235857/371472 [7:44:15<10:56:44,  3.44it/s]
 63%|██████▎   | 235858/371472 [7:44:15<12:07:57,  3.10it/s]
 63%|██████▎   | 235859/371472 [7:44:16<11:47:25,  3.20it/s]
 63%|██████▎   | 235860/371472 [7:44:16<11:28:41,  3.28it/s]
                                                            
{'loss': 2.8219, 'learning_rate': 4.2873688293218986e-07, 'epoch': 10.16}
+
 63%|██████▎   | 235860/371472 [7:44:16<11:28:41,  3.28it/s]
 63%|██████▎   | 235861/371472 [7:44:16<11:05:24,  3.40it/s]
 63%|██████▎   | 235862/371472 [7:44:17<10:36:28,  3.55it/s]
 63%|██████▎   | 235863/371472 [7:44:17<11:36:54,  3.24it/s]
 63%|██████▎   | 235864/371472 [7:44:17<12:20:16,  3.05it/s]
 63%|██████▎   | 235865/371472 [7:44:18<11:41:30,  3.22it/s]
 63%|██████▎   | 235866/371472 [7:44:18<11:27:21,  3.29it/s]
 63%|██████▎   | 235867/371472 [7:44:18<11:05:48,  3.39it/s]
 63%|██████▎   | 235868/371472 [7:44:18<10:52:13,  3.47it/s]
 63%|██████▎   | 235869/371472 [7:44:19<10:26:33,  3.61it/s]
 63%|██████▎   | 235870/371472 [7:44:19<10:23:02,  3.63it/s]
 63%|██████▎   | 235871/371472 [7:44:19<10:45:16,  3.50it/s]
 63%|██████▎   | 235872/371472 [7:44:19<10:44:09,  3.51it/s]
 63%|██████▎   | 235873/371472 [7:44:20<11:36:03,  3.25it/s]
 63%|██████▎   | 235874/371472 [7:44:20<11:26:58,  3.29it/s]
 63%|██████▎   | 235875/371472 [7:44:20<10:49:47,  3.48it/s]
 63%|██████▎   | 235876/371472 [7:44:21<10:38:50,  3.54it/s]
 63%|██████▎   | 235877/371472 [7:44:21<10:17:28,  3.66it/s]
 63%|██████▎   | 235878/371472 [7:44:21<11:11:00,  3.37it/s]
 63%|██████▎   | 235879/371472 [7:44:22<10:52:33,  3.46it/s]
 63%|██████▎   | 235880/371472 [7:44:22<10:52:49,  3.46it/s]
                                                            
{'loss': 2.8571, 'learning_rate': 4.2868840095671093e-07, 'epoch': 10.16}
+
 63%|██████▎   | 235880/371472 [7:44:22<10:52:49,  3.46it/s]
 63%|██████▎   | 235881/371472 [7:44:22<10:49:04,  3.48it/s]
 63%|██████▎   | 235882/371472 [7:44:22<10:29:28,  3.59it/s]
 63%|██████▎   | 235883/371472 [7:44:23<10:20:36,  3.64it/s]
 63%|██████▎   | 235884/371472 [7:44:23<10:03:22,  3.75it/s]
 64%|██████▎   | 235885/371472 [7:44:23<10:18:17,  3.65it/s]
 64%|██████▎   | 235886/371472 [7:44:23<10:05:57,  3.73it/s]
 64%|██████▎   | 235887/371472 [7:44:24<10:19:16,  3.65it/s]
 64%|██████▎   | 235888/371472 [7:44:24<10:10:29,  3.70it/s]
 64%|██████▎   | 235889/371472 [7:44:24<10:57:26,  3.44it/s]
 64%|██████▎   | 235890/371472 [7:44:25<10:28:07,  3.60it/s]
 64%|██████▎   | 235891/371472 [7:44:25<10:17:22,  3.66it/s]
 64%|██████▎   | 235892/371472 [7:44:25<10:14:26,  3.68it/s]
 64%|██████▎   | 235893/371472 [7:44:25<10:04:58,  3.74it/s]
 64%|██████▎   | 235894/371472 [7:44:26<9:46:41,  3.85it/s] 
 64%|██████▎   | 235895/371472 [7:44:26<9:44:24,  3.87it/s]
 64%|██████▎   | 235896/371472 [7:44:26<10:41:51,  3.52it/s]
 64%|██████▎   | 235897/371472 [7:44:26<10:58:55,  3.43it/s]
 64%|██████▎   | 235898/371472 [7:44:27<11:05:29,  3.40it/s]
 64%|██████▎   | 235899/371472 [7:44:27<10:52:04,  3.47it/s]
 64%|██████▎   | 235900/371472 [7:44:27<10:54:12,  3.45it/s]
                                                            
{'loss': 2.8419, 'learning_rate': 4.286399189812321e-07, 'epoch': 10.16}
+
 64%|██████▎   | 235900/371472 [7:44:27<10:54:12,  3.45it/s]
 64%|██████▎   | 235901/371472 [7:44:28<10:51:42,  3.47it/s]
 64%|██████▎   | 235902/371472 [7:44:28<11:18:29,  3.33it/s]
 64%|██████▎   | 235903/371472 [7:44:28<11:19:14,  3.33it/s]
 64%|██████▎   | 235904/371472 [7:44:29<11:43:11,  3.21it/s]
 64%|██████▎   | 235905/371472 [7:44:29<11:04:17,  3.40it/s]
 64%|██████▎   | 235906/371472 [7:44:29<10:47:21,  3.49it/s]
 64%|██████▎   | 235907/371472 [7:44:29<10:31:26,  3.58it/s]
 64%|██████▎   | 235908/371472 [7:44:30<10:41:16,  3.52it/s]
 64%|██████▎   | 235909/371472 [7:44:30<10:28:57,  3.59it/s]
 64%|██████▎   | 235910/371472 [7:44:30<10:00:43,  3.76it/s]
 64%|██████▎   | 235911/371472 [7:44:31<11:14:11,  3.35it/s]
 64%|██████▎   | 235912/371472 [7:44:31<10:51:57,  3.47it/s]
 64%|██████▎   | 235913/371472 [7:44:31<10:18:03,  3.66it/s]
 64%|██████▎   | 235914/371472 [7:44:31<10:14:41,  3.68it/s]
 64%|██████▎   | 235915/371472 [7:44:32<10:16:30,  3.66it/s]
 64%|██████▎   | 235916/371472 [7:44:32<10:35:31,  3.55it/s]
 64%|██████▎   | 235917/371472 [7:44:32<10:21:18,  3.64it/s]
 64%|██████▎   | 235918/371472 [7:44:32<10:36:46,  3.55it/s]
 64%|██████▎   | 235919/371472 [7:44:33<10:22:23,  3.63it/s]
 64%|██████▎   | 235920/371472 [7:44:33<10:52:23,  3.46it/s]
                                                            
{'loss': 2.8924, 'learning_rate': 4.285914370057532e-07, 'epoch': 10.16}
+
 64%|██████▎   | 235920/371472 [7:44:33<10:52:23,  3.46it/s]
 64%|██████▎   | 235921/371472 [7:44:33<10:35:02,  3.56it/s]
 64%|██████▎   | 235922/371472 [7:44:34<10:34:35,  3.56it/s]
 64%|██████▎   | 235923/371472 [7:44:34<10:17:00,  3.66it/s]
 64%|██████▎   | 235924/371472 [7:44:34<10:38:42,  3.54it/s]
 64%|██████▎   | 235925/371472 [7:44:34<10:29:30,  3.59it/s]
 64%|██████▎   | 235926/371472 [7:44:35<9:59:20,  3.77it/s] 
 64%|██████▎   | 235927/371472 [7:44:35<9:53:34,  3.81it/s]
 64%|██████▎   | 235928/371472 [7:44:35<10:00:31,  3.76it/s]
 64%|██████▎   | 235929/371472 [7:44:35<9:53:53,  3.80it/s] 
 64%|██████▎   | 235930/371472 [7:44:36<10:20:51,  3.64it/s]
 64%|██████▎   | 235931/371472 [7:44:36<10:14:45,  3.67it/s]
 64%|██████▎   | 235932/371472 [7:44:36<10:01:27,  3.76it/s]
 64%|██████▎   | 235933/371472 [7:44:37<9:57:13,  3.78it/s] 
 64%|██████▎   | 235934/371472 [7:44:37<10:15:27,  3.67it/s]
 64%|██████▎   | 235935/371472 [7:44:37<9:56:52,  3.78it/s] 
 64%|██████▎   | 235936/371472 [7:44:37<10:14:59,  3.67it/s]
 64%|██████▎   | 235937/371472 [7:44:38<11:04:03,  3.40it/s]
 64%|██████▎   | 235938/371472 [7:44:38<10:47:15,  3.49it/s]
 64%|██████▎   | 235939/371472 [7:44:38<10:39:46,  3.53it/s]
 64%|██████▎   | 235940/371472 [7:44:39<10:50:26,  3.47it/s]
                                                            
{'loss': 2.9723, 'learning_rate': 4.285429550302743e-07, 'epoch': 10.16}
+
 64%|██████▎   | 235940/371472 [7:44:39<10:50:26,  3.47it/s]
 64%|██████▎   | 235941/371472 [7:44:39<10:24:20,  3.62it/s]
 64%|██████▎   | 235942/371472 [7:44:39<10:30:58,  3.58it/s]
 64%|██████▎   | 235943/371472 [7:44:39<10:08:55,  3.71it/s]
 64%|██████▎   | 235944/371472 [7:44:40<10:28:44,  3.59it/s]
 64%|██████▎   | 235945/371472 [7:44:40<10:42:59,  3.51it/s]
 64%|██████▎   | 235946/371472 [7:44:40<10:48:56,  3.48it/s]
 64%|██████▎   | 235947/371472 [7:44:40<10:52:41,  3.46it/s]
 64%|██████▎   | 235948/371472 [7:44:41<11:31:11,  3.27it/s]
 64%|██████▎   | 235949/371472 [7:44:41<11:00:29,  3.42it/s]
 64%|██████▎   | 235950/371472 [7:44:41<10:55:14,  3.45it/s]
 64%|██████▎   | 235951/371472 [7:44:42<11:12:52,  3.36it/s]
 64%|██████▎   | 235952/371472 [7:44:42<11:56:53,  3.15it/s]
 64%|██████▎   | 235953/371472 [7:44:42<12:41:29,  2.97it/s]
 64%|██████▎   | 235954/371472 [7:44:43<11:46:34,  3.20it/s]
 64%|██████▎   | 235955/371472 [7:44:43<10:55:12,  3.45it/s]
 64%|██████▎   | 235956/371472 [7:44:43<10:29:45,  3.59it/s]
 64%|██████▎   | 235957/371472 [7:44:43<10:31:56,  3.57it/s]
 64%|██████▎   | 235958/371472 [7:44:44<10:30:28,  3.58it/s]
 64%|██████▎   | 235959/371472 [7:44:44<10:46:38,  3.49it/s]
 64%|██████▎   | 235960/371472 [7:44:44<10:35:17,  3.56it/s]
                                                            
{'loss': 2.9206, 'learning_rate': 4.284944730547954e-07, 'epoch': 10.16}
+
 64%|██████▎   | 235960/371472 [7:44:44<10:35:17,  3.56it/s]
 64%|██████▎   | 235961/371472 [7:44:45<10:15:13,  3.67it/s]
 64%|██████▎   | 235962/371472 [7:44:45<9:57:26,  3.78it/s] 
 64%|██████▎   | 235963/371472 [7:44:45<9:53:24,  3.81it/s]
 64%|██████▎   | 235964/371472 [7:44:45<10:06:01,  3.73it/s]
 64%|██████▎   | 235965/371472 [7:44:46<10:41:57,  3.52it/s]
 64%|██████▎   | 235966/371472 [7:44:46<10:55:52,  3.44it/s]
 64%|██████▎   | 235967/371472 [7:44:46<10:38:15,  3.54it/s]
 64%|██████▎   | 235968/371472 [7:44:47<10:41:33,  3.52it/s]
 64%|██████▎   | 235969/371472 [7:44:47<11:15:46,  3.34it/s]
 64%|██████▎   | 235970/371472 [7:44:47<11:22:10,  3.31it/s]
 64%|██████▎   | 235971/371472 [7:44:47<10:52:22,  3.46it/s]
 64%|██████▎   | 235972/371472 [7:44:48<10:43:59,  3.51it/s]
 64%|██████▎   | 235973/371472 [7:44:48<10:08:46,  3.71it/s]
 64%|██████▎   | 235974/371472 [7:44:48<10:05:47,  3.73it/s]
 64%|██████▎   | 235975/371472 [7:44:49<10:23:57,  3.62it/s]
 64%|██████▎   | 235976/371472 [7:44:49<10:57:16,  3.44it/s]
 64%|██████▎   | 235977/371472 [7:44:49<10:40:55,  3.52it/s]
 64%|██████▎   | 235978/371472 [7:44:49<11:25:23,  3.29it/s]
 64%|██████▎   | 235979/371472 [7:44:50<10:58:12,  3.43it/s]
 64%|██████▎   | 235980/371472 [7:44:50<11:11:34,  3.36it/s]
                                                            
{'loss': 3.0309, 'learning_rate': 4.284459910793165e-07, 'epoch': 10.16}
+
 64%|██████▎   | 235980/371472 [7:44:50<11:11:34,  3.36it/s]
 64%|██████▎   | 235981/371472 [7:44:50<10:42:32,  3.51it/s]
 64%|██████▎   | 235982/371472 [7:44:51<11:14:16,  3.35it/s]
 64%|██████▎   | 235983/371472 [7:44:51<10:41:54,  3.52it/s]
 64%|██████▎   | 235984/371472 [7:44:51<10:37:16,  3.54it/s]
 64%|██████▎   | 235985/371472 [7:44:51<10:26:34,  3.60it/s]
 64%|██████▎   | 235986/371472 [7:44:52<10:45:09,  3.50it/s]
 64%|██████▎   | 235987/371472 [7:44:52<10:53:37,  3.45it/s]
 64%|██████▎   | 235988/371472 [7:44:52<10:55:24,  3.45it/s]
 64%|██████▎   | 235989/371472 [7:44:53<10:43:02,  3.51it/s]
 64%|██████▎   | 235990/371472 [7:44:53<11:01:31,  3.41it/s]
 64%|██████▎   | 235991/371472 [7:44:53<10:42:29,  3.51it/s]
 64%|██████▎   | 235992/371472 [7:44:53<10:14:16,  3.68it/s]
 64%|██████▎   | 235993/371472 [7:44:54<10:15:49,  3.67it/s]
 64%|██████▎   | 235994/371472 [7:44:54<10:42:45,  3.51it/s]
 64%|██████▎   | 235995/371472 [7:44:54<10:25:13,  3.61it/s]
 64%|██████▎   | 235996/371472 [7:44:55<10:13:37,  3.68it/s]
 64%|██████▎   | 235997/371472 [7:44:55<10:49:47,  3.47it/s]
 64%|██████▎   | 235998/371472 [7:44:55<10:17:52,  3.65it/s]
 64%|██████▎   | 235999/371472 [7:44:55<11:27:42,  3.28it/s]
 64%|██████▎   | 236000/371472 [7:44:56<11:43:47,  3.21it/s]
                                                            
{'loss': 2.8396, 'learning_rate': 4.2839750910383757e-07, 'epoch': 10.16}
+
 64%|██████▎   | 236000/371472 [7:44:56<11:43:47,  3.21it/s]
 64%|██████▎   | 236001/371472 [7:44:56<11:01:23,  3.41it/s]
 64%|██████▎   | 236002/371472 [7:44:56<10:45:32,  3.50it/s]
 64%|██████▎   | 236003/371472 [7:44:57<11:15:51,  3.34it/s]
 64%|██████▎   | 236004/371472 [7:44:57<11:26:46,  3.29it/s]
 64%|██████▎   | 236005/371472 [7:44:57<11:07:25,  3.38it/s]
 64%|██████▎   | 236006/371472 [7:44:57<10:43:50,  3.51it/s]
 64%|██████▎   | 236007/371472 [7:44:58<10:26:15,  3.61it/s]
 64%|██████▎   | 236008/371472 [7:44:58<10:15:59,  3.67it/s]
 64%|██████▎   | 236009/371472 [7:44:58<10:44:26,  3.50it/s]
 64%|██████▎   | 236010/371472 [7:44:59<10:28:47,  3.59it/s]
 64%|██████▎   | 236011/371472 [7:44:59<10:27:57,  3.60it/s]
 64%|██████▎   | 236012/371472 [7:44:59<11:00:40,  3.42it/s]
 64%|██████▎   | 236013/371472 [7:44:59<10:49:51,  3.47it/s]
 64%|██████▎   | 236014/371472 [7:45:00<10:28:18,  3.59it/s]
 64%|██████▎   | 236015/371472 [7:45:00<10:36:33,  3.55it/s]
 64%|██████▎   | 236016/371472 [7:45:00<10:46:42,  3.49it/s]
 64%|██████▎   | 236017/371472 [7:45:01<10:19:25,  3.64it/s]
 64%|██████▎   | 236018/371472 [7:45:01<11:06:32,  3.39it/s]
 64%|██████▎   | 236019/371472 [7:45:01<11:05:34,  3.39it/s]
 64%|██████▎   | 236020/371472 [7:45:01<10:49:04,  3.48it/s]
                                                            
{'loss': 2.7736, 'learning_rate': 4.2834902712835875e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236020/371472 [7:45:01<10:49:04,  3.48it/s]
 64%|██████▎   | 236021/371472 [7:45:02<11:00:58,  3.42it/s]
 64%|██████▎   | 236022/371472 [7:45:02<11:17:48,  3.33it/s]
 64%|██████▎   | 236023/371472 [7:45:02<10:42:33,  3.51it/s]
 64%|██████▎   | 236024/371472 [7:45:03<10:39:11,  3.53it/s]
 64%|██████▎   | 236025/371472 [7:45:03<10:26:42,  3.60it/s]
 64%|██████▎   | 236026/371472 [7:45:03<10:12:23,  3.69it/s]
 64%|██████▎   | 236027/371472 [7:45:03<9:54:07,  3.80it/s] 
 64%|██████▎   | 236028/371472 [7:45:04<10:48:09,  3.48it/s]
 64%|██████▎   | 236029/371472 [7:45:04<10:30:44,  3.58it/s]
 64%|██████▎   | 236030/371472 [7:45:04<10:48:06,  3.48it/s]
 64%|██████▎   | 236031/371472 [7:45:05<10:43:14,  3.51it/s]
 64%|██████▎   | 236032/371472 [7:45:05<10:22:29,  3.63it/s]
 64%|██████▎   | 236033/371472 [7:45:05<10:06:53,  3.72it/s]
 64%|██████▎   | 236034/371472 [7:45:05<9:59:24,  3.77it/s] 
 64%|██████▎   | 236035/371472 [7:45:06<11:06:58,  3.38it/s]
 64%|██████▎   | 236036/371472 [7:45:06<10:53:13,  3.46it/s]
 64%|██████▎   | 236037/371472 [7:45:06<10:29:54,  3.58it/s]
 64%|██████▎   | 236038/371472 [7:45:06<10:14:28,  3.67it/s]
 64%|██████▎   | 236039/371472 [7:45:07<10:09:07,  3.71it/s]
 64%|██████▎   | 236040/371472 [7:45:07<10:00:13,  3.76it/s]
                                                            
{'loss': 2.9078, 'learning_rate': 4.283005451528798e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236040/371472 [7:45:07<10:00:13,  3.76it/s]
 64%|██████▎   | 236041/371472 [7:45:07<10:35:17,  3.55it/s]
 64%|██████▎   | 236042/371472 [7:45:08<11:27:38,  3.28it/s]
 64%|██████▎   | 236043/371472 [7:45:08<11:01:20,  3.41it/s]
 64%|██████▎   | 236044/371472 [7:45:08<11:03:36,  3.40it/s]
 64%|██████▎   | 236045/371472 [7:45:09<11:17:09,  3.33it/s]
 64%|██████▎   | 236046/371472 [7:45:09<11:32:15,  3.26it/s]
 64%|██████▎   | 236047/371472 [7:45:09<11:28:41,  3.28it/s]
 64%|██████▎   | 236048/371472 [7:45:09<11:03:57,  3.40it/s]
 64%|██████▎   | 236049/371472 [7:45:10<10:34:50,  3.56it/s]
 64%|██████▎   | 236050/371472 [7:45:10<11:34:57,  3.25it/s]
 64%|██████▎   | 236051/371472 [7:45:10<11:06:27,  3.39it/s]
 64%|██████▎   | 236052/371472 [7:45:11<10:27:10,  3.60it/s]
 64%|██████▎   | 236053/371472 [7:45:11<10:33:02,  3.57it/s]
 64%|██████▎   | 236054/371472 [7:45:11<10:56:54,  3.44it/s]
 64%|██████▎   | 236055/371472 [7:45:11<11:05:13,  3.39it/s]
 64%|██████▎   | 236056/371472 [7:45:12<10:49:16,  3.48it/s]
 64%|██████▎   | 236057/371472 [7:45:12<10:28:11,  3.59it/s]
 64%|██████▎   | 236058/371472 [7:45:12<10:59:06,  3.42it/s]
 64%|██████▎   | 236059/371472 [7:45:13<10:49:17,  3.48it/s]
 64%|██████▎   | 236060/371472 [7:45:13<11:21:46,  3.31it/s]
                                                            
{'loss': 2.9617, 'learning_rate': 4.2825206317740095e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236060/371472 [7:45:13<11:21:46,  3.31it/s]
 64%|██████▎   | 236061/371472 [7:45:13<11:33:13,  3.26it/s]
 64%|██████▎   | 236062/371472 [7:45:14<11:06:29,  3.39it/s]
 64%|██████▎   | 236063/371472 [7:45:14<10:30:04,  3.58it/s]
 64%|██████▎   | 236064/371472 [7:45:14<10:05:52,  3.72it/s]
 64%|██████▎   | 236065/371472 [7:45:14<10:16:36,  3.66it/s]
 64%|██████▎   | 236066/371472 [7:45:15<10:07:53,  3.71it/s]
 64%|██████▎   | 236067/371472 [7:45:15<10:34:08,  3.56it/s]
 64%|██████▎   | 236068/371472 [7:45:15<10:06:14,  3.72it/s]
 64%|██████▎   | 236069/371472 [7:45:15<10:32:54,  3.57it/s]
 64%|██████▎   | 236070/371472 [7:45:16<11:05:30,  3.39it/s]
 64%|██████▎   | 236071/371472 [7:45:16<10:28:44,  3.59it/s]
 64%|██████▎   | 236072/371472 [7:45:16<10:39:20,  3.53it/s]
 64%|██████▎   | 236073/371472 [7:45:17<10:45:05,  3.50it/s]
 64%|██████▎   | 236074/371472 [7:45:17<11:58:29,  3.14it/s]
 64%|██████▎   | 236075/371472 [7:45:17<11:22:29,  3.31it/s]
 64%|██████▎   | 236076/371472 [7:45:18<11:28:26,  3.28it/s]
 64%|██████▎   | 236077/371472 [7:45:18<11:24:14,  3.30it/s]
 64%|██████▎   | 236078/371472 [7:45:18<10:37:47,  3.54it/s]
 64%|██████▎   | 236079/371472 [7:45:18<10:23:37,  3.62it/s]
 64%|██████▎   | 236080/371472 [7:45:19<10:29:12,  3.59it/s]
                                                            
{'loss': 2.854, 'learning_rate': 4.28203581201922e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236080/371472 [7:45:19<10:29:12,  3.59it/s]
 64%|██████▎   | 236081/371472 [7:45:19<10:12:25,  3.68it/s]
 64%|██████▎   | 236082/371472 [7:45:19<10:14:53,  3.67it/s]
 64%|██████▎   | 236083/371472 [7:45:19<10:23:12,  3.62it/s]
 64%|██████▎   | 236084/371472 [7:45:20<10:39:34,  3.53it/s]
 64%|██████▎   | 236085/371472 [7:45:20<10:23:08,  3.62it/s]
 64%|██████▎   | 236086/371472 [7:45:20<10:23:07,  3.62it/s]
 64%|██████▎   | 236087/371472 [7:45:21<10:13:32,  3.68it/s]
 64%|██████▎   | 236088/371472 [7:45:21<9:59:31,  3.76it/s] 
 64%|██████▎   | 236089/371472 [7:45:21<10:40:25,  3.52it/s]
 64%|██████▎   | 236090/371472 [7:45:21<10:34:12,  3.56it/s]
 64%|██████▎   | 236091/371472 [7:45:22<10:35:50,  3.55it/s]
 64%|██████▎   | 236092/371472 [7:45:22<10:53:05,  3.45it/s]
 64%|██████▎   | 236093/371472 [7:45:22<10:54:19,  3.45it/s]
 64%|██████▎   | 236094/371472 [7:45:23<10:52:49,  3.46it/s]
 64%|██████▎   | 236095/371472 [7:45:23<11:29:06,  3.27it/s]
 64%|██████▎   | 236096/371472 [7:45:23<11:12:34,  3.35it/s]
 64%|██████▎   | 236097/371472 [7:45:23<11:14:36,  3.34it/s]
 64%|██████▎   | 236098/371472 [7:45:24<11:18:49,  3.32it/s]
 64%|██████▎   | 236099/371472 [7:45:24<10:52:32,  3.46it/s]
 64%|██████▎   | 236100/371472 [7:45:24<10:20:44,  3.63it/s]
                                                            
{'loss': 2.9356, 'learning_rate': 4.281550992264432e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236100/371472 [7:45:24<10:20:44,  3.63it/s]
 64%|██████▎   | 236101/371472 [7:45:25<10:09:34,  3.70it/s]
 64%|██████▎   | 236102/371472 [7:45:25<9:53:46,  3.80it/s] 
 64%|██████▎   | 236103/371472 [7:45:25<10:17:22,  3.65it/s]
 64%|██████▎   | 236104/371472 [7:45:25<10:08:00,  3.71it/s]
 64%|██████▎   | 236105/371472 [7:45:26<10:34:28,  3.56it/s]
 64%|██████▎   | 236106/371472 [7:45:26<10:20:26,  3.64it/s]
 64%|██████▎   | 236107/371472 [7:45:26<11:03:48,  3.40it/s]
 64%|██████▎   | 236108/371472 [7:45:27<11:30:18,  3.27it/s]
 64%|██████▎   | 236109/371472 [7:45:27<11:29:51,  3.27it/s]
 64%|██████▎   | 236110/371472 [7:45:27<11:27:47,  3.28it/s]
 64%|██████▎   | 236111/371472 [7:45:27<10:42:14,  3.51it/s]
 64%|██████▎   | 236112/371472 [7:45:28<10:58:56,  3.42it/s]
 64%|██████▎   | 236113/371472 [7:45:28<10:51:20,  3.46it/s]
 64%|██████▎   | 236114/371472 [7:45:28<11:17:36,  3.33it/s]
 64%|██████▎   | 236115/371472 [7:45:29<11:06:07,  3.39it/s]
 64%|██████▎   | 236116/371472 [7:45:29<10:36:04,  3.55it/s]
 64%|██████▎   | 236117/371472 [7:45:29<11:19:11,  3.32it/s]
 64%|██████▎   | 236118/371472 [7:45:30<12:19:24,  3.05it/s]
 64%|██████▎   | 236119/371472 [7:45:30<11:58:02,  3.14it/s]
 64%|██████▎   | 236120/371472 [7:45:30<11:29:51,  3.27it/s]
                                                            
{'loss': 2.7902, 'learning_rate': 4.281066172509642e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236120/371472 [7:45:30<11:29:51,  3.27it/s]
 64%|██████▎   | 236121/371472 [7:45:30<11:26:02,  3.29it/s]
 64%|██████▎   | 236122/371472 [7:45:31<10:58:13,  3.43it/s]
 64%|██████▎   | 236123/371472 [7:45:31<10:34:04,  3.56it/s]
 64%|██████▎   | 236124/371472 [7:45:31<10:41:37,  3.52it/s]
 64%|██████▎   | 236125/371472 [7:45:32<10:28:34,  3.59it/s]
 64%|██████▎   | 236126/371472 [7:45:32<11:25:48,  3.29it/s]
 64%|██████▎   | 236127/371472 [7:45:32<11:16:08,  3.34it/s]
 64%|██████▎   | 236128/371472 [7:45:32<10:47:37,  3.48it/s]
 64%|██████▎   | 236129/371472 [7:45:33<10:33:20,  3.56it/s]
 64%|██████▎   | 236130/371472 [7:45:33<10:51:26,  3.46it/s]
 64%|██████▎   | 236131/371472 [7:45:33<10:26:56,  3.60it/s]
 64%|██████▎   | 236132/371472 [7:45:34<10:08:29,  3.71it/s]
 64%|██████▎   | 236133/371472 [7:45:34<10:20:49,  3.63it/s]
 64%|██████▎   | 236134/371472 [7:45:34<10:09:49,  3.70it/s]
 64%|██████▎   | 236135/371472 [7:45:34<9:56:44,  3.78it/s] 
 64%|██████▎   | 236136/371472 [7:45:35<10:02:59,  3.74it/s]
 64%|██████▎   | 236137/371472 [7:45:35<10:02:10,  3.75it/s]
 64%|██████▎   | 236138/371472 [7:45:35<9:50:51,  3.82it/s] 
 64%|██████▎   | 236139/371472 [7:45:35<9:43:33,  3.87it/s]
 64%|██████▎   | 236140/371472 [7:45:36<9:33:45,  3.93it/s]
                                                           
{'loss': 2.8966, 'learning_rate': 4.280581352754854e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236140/371472 [7:45:36<9:33:45,  3.93it/s]
 64%|██████▎   | 236141/371472 [7:45:36<9:38:43,  3.90it/s]
 64%|██████▎   | 236142/371472 [7:45:36<9:58:02,  3.77it/s]
 64%|██████▎   | 236143/371472 [7:45:36<9:51:35,  3.81it/s]
 64%|██████▎   | 236144/371472 [7:45:37<10:15:58,  3.66it/s]
 64%|██████▎   | 236145/371472 [7:45:37<10:38:42,  3.53it/s]
 64%|██████▎   | 236146/371472 [7:45:37<10:46:30,  3.49it/s]
 64%|██████▎   | 236147/371472 [7:45:38<11:54:04,  3.16it/s]
 64%|██████▎   | 236148/371472 [7:45:38<12:09:01,  3.09it/s]
 64%|██████▎   | 236149/371472 [7:45:38<12:18:25,  3.05it/s]
 64%|██████▎   | 236150/371472 [7:45:39<11:20:16,  3.32it/s]
 64%|██████▎   | 236151/371472 [7:45:39<10:55:50,  3.44it/s]
 64%|██████▎   | 236152/371472 [7:45:39<10:19:09,  3.64it/s]
 64%|██████▎   | 236153/371472 [7:45:39<10:13:12,  3.68it/s]
 64%|██████▎   | 236154/371472 [7:45:40<9:59:38,  3.76it/s] 
 64%|██████▎   | 236155/371472 [7:45:40<10:10:47,  3.69it/s]
 64%|██████▎   | 236156/371472 [7:45:40<10:01:28,  3.75it/s]
 64%|██████▎   | 236157/371472 [7:45:40<9:59:41,  3.76it/s] 
 64%|██████▎   | 236158/371472 [7:45:41<9:51:28,  3.81it/s]
 64%|██████▎   | 236159/371472 [7:45:41<10:07:17,  3.71it/s]
 64%|██████▎   | 236160/371472 [7:45:41<10:04:42,  3.73it/s]
                                                            
{'loss': 2.7286, 'learning_rate': 4.280096533000064e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236160/371472 [7:45:41<10:04:42,  3.73it/s]
 64%|██████▎   | 236161/371472 [7:45:42<11:10:00,  3.37it/s]
 64%|██████▎   | 236162/371472 [7:45:42<10:40:58,  3.52it/s]
 64%|██████▎   | 236163/371472 [7:45:42<10:44:03,  3.50it/s]
 64%|██████▎   | 236164/371472 [7:45:42<10:21:32,  3.63it/s]
 64%|██████▎   | 236165/371472 [7:45:43<10:21:27,  3.63it/s]
 64%|██████▎   | 236166/371472 [7:45:43<11:02:37,  3.40it/s]
 64%|██████▎   | 236167/371472 [7:45:43<10:53:13,  3.45it/s]
 64%|██████▎   | 236168/371472 [7:45:44<10:40:44,  3.52it/s]
 64%|██████▎   | 236169/371472 [7:45:44<10:33:05,  3.56it/s]
 64%|██████▎   | 236170/371472 [7:45:44<10:37:08,  3.54it/s]
 64%|██████▎   | 236171/371472 [7:45:44<10:46:52,  3.49it/s]
 64%|██████▎   | 236172/371472 [7:45:45<10:32:55,  3.56it/s]
 64%|██████▎   | 236173/371472 [7:45:45<10:44:18,  3.50it/s]
 64%|██████▎   | 236174/371472 [7:45:45<10:28:30,  3.59it/s]
 64%|██████▎   | 236175/371472 [7:45:46<10:51:27,  3.46it/s]
 64%|██████▎   | 236176/371472 [7:45:46<11:11:00,  3.36it/s]
 64%|██████▎   | 236177/371472 [7:45:46<11:14:51,  3.34it/s]
 64%|██████▎   | 236178/371472 [7:45:47<11:19:43,  3.32it/s]
 64%|██████▎   | 236179/371472 [7:45:47<11:15:24,  3.34it/s]
 64%|██████▎   | 236180/371472 [7:45:47<11:03:12,  3.40it/s]
                                                            
{'loss': 2.901, 'learning_rate': 4.279611713245275e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236180/371472 [7:45:47<11:03:12,  3.40it/s]
 64%|██████▎   | 236181/371472 [7:45:47<10:39:49,  3.52it/s]
 64%|███��██▎   | 236182/371472 [7:45:48<10:23:58,  3.61it/s]
 64%|██████▎   | 236183/371472 [7:45:48<11:32:40,  3.26it/s]
 64%|██████▎   | 236184/371472 [7:45:48<11:23:08,  3.30it/s]
 64%|██████▎   | 236185/371472 [7:45:49<11:01:12,  3.41it/s]
 64%|██████▎   | 236186/371472 [7:45:49<11:54:59,  3.15it/s]
 64%|██████▎   | 236187/371472 [7:45:49<12:29:05,  3.01it/s]
 64%|██████▎   | 236188/371472 [7:45:50<11:51:00,  3.17it/s]
 64%|██████▎   | 236189/371472 [7:45:50<11:50:52,  3.17it/s]
 64%|██████▎   | 236190/371472 [7:45:50<11:37:32,  3.23it/s]
 64%|██████▎   | 236191/371472 [7:45:50<11:21:09,  3.31it/s]
 64%|██████▎   | 236192/371472 [7:45:51<10:46:29,  3.49it/s]
 64%|██████▎   | 236193/371472 [7:45:51<10:34:08,  3.56it/s]
 64%|██████▎   | 236194/371472 [7:45:51<10:31:26,  3.57it/s]
 64%|██████▎   | 236195/371472 [7:45:52<10:23:44,  3.61it/s]
 64%|██████▎   | 236196/371472 [7:45:52<10:28:20,  3.59it/s]
 64%|██████▎   | 236197/371472 [7:45:52<10:25:16,  3.61it/s]
 64%|██████▎   | 236198/371472 [7:45:52<10:04:16,  3.73it/s]
 64%|██████▎   | 236199/371472 [7:45:53<10:02:03,  3.74it/s]
 64%|██████▎   | 236200/371472 [7:45:53<10:08:34,  3.70it/s]
                                                            
{'loss': 2.7698, 'learning_rate': 4.2791268934904866e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236200/371472 [7:45:53<10:08:34,  3.70it/s]
 64%|██████▎   | 236201/371472 [7:45:53<10:15:52,  3.66it/s]
 64%|██████▎   | 236202/371472 [7:45:53<10:06:41,  3.72it/s]
 64%|██████▎   | 236203/371472 [7:45:54<11:08:06,  3.37it/s]
 64%|██████▎   | 236204/371472 [7:45:54<10:45:20,  3.49it/s]
 64%|██████▎   | 236205/371472 [7:45:54<11:43:23,  3.21it/s]
 64%|██████▎   | 236206/371472 [7:45:55<11:18:32,  3.32it/s]
 64%|██████▎   | 236207/371472 [7:45:55<10:59:40,  3.42it/s]
 64%|██████▎   | 236208/371472 [7:45:55<11:13:19,  3.35it/s]
 64%|██████▎   | 236209/371472 [7:45:56<10:51:24,  3.46it/s]
 64%|██████▎   | 236210/371472 [7:45:56<10:45:26,  3.49it/s]
 64%|██████▎   | 236211/371472 [7:45:56<10:47:55,  3.48it/s]
 64%|██████▎   | 236212/371472 [7:45:56<10:28:10,  3.59it/s]
 64%|██████▎   | 236213/371472 [7:45:57<10:50:58,  3.46it/s]
 64%|██████▎   | 236214/371472 [7:45:57<10:35:44,  3.55it/s]
 64%|██████▎   | 236215/371472 [7:45:57<10:49:04,  3.47it/s]
 64%|██████▎   | 236216/371472 [7:45:58<10:31:59,  3.57it/s]
 64%|██████▎   | 236217/371472 [7:45:58<10:24:23,  3.61it/s]
 64%|██████▎   | 236218/371472 [7:45:58<10:31:33,  3.57it/s]
 64%|██████▎   | 236219/371472 [7:45:58<10:29:58,  3.58it/s]
 64%|██████▎   | 236220/371472 [7:45:59<10:54:04,  3.45it/s]
                                                            
{'loss': 3.0101, 'learning_rate': 4.2786420737356973e-07, 'epoch': 10.17}
+
 64%|██████▎   | 236220/371472 [7:45:59<10:54:04,  3.45it/s]
 64%|██████▎   | 236221/371472 [7:45:59<11:30:03,  3.27it/s]
 64%|██████▎   | 236222/371472 [7:45:59<11:39:28,  3.22it/s]
 64%|██████▎   | 236223/371472 [7:46:00<10:56:22,  3.43it/s]
 64%|██████▎   | 236224/371472 [7:46:00<10:28:46,  3.58it/s]
 64%|██████▎   | 236225/371472 [7:46:00<10:52:21,  3.46it/s]
 64%|██████▎   | 236226/371472 [7:46:00<10:27:28,  3.59it/s]
 64%|██████▎   | 236227/371472 [7:46:01<10:32:17,  3.56it/s]
 64%|██████▎   | 236228/371472 [7:46:01<10:25:12,  3.61it/s]
 64%|██████▎   | 236229/371472 [7:46:01<10:35:42,  3.55it/s]
 64%|██████▎   | 236230/371472 [7:46:02<10:38:52,  3.53it/s]
 64%|██████▎   | 236231/371472 [7:46:02<10:49:26,  3.47it/s]
 64%|██████▎   | 236232/371472 [7:46:02<10:43:19,  3.50it/s]
 64%|██████▎   | 236233/371472 [7:46:02<10:37:35,  3.54it/s]
 64%|██████▎   | 236234/371472 [7:46:03<10:42:36,  3.51it/s]
 64%|██████▎   | 236235/371472 [7:46:03<11:00:03,  3.41it/s]
 64%|██████▎   | 236236/371472 [7:46:03<10:29:38,  3.58it/s]
 64%|██████▎   | 236237/371472 [7:46:04<11:09:47,  3.37it/s]
 64%|██████▎   | 236238/371472 [7:46:04<10:52:44,  3.45it/s]
 64%|██████▎   | 236239/371472 [7:46:04<10:48:04,  3.48it/s]
 64%|██████▎   | 236240/371472 [7:46:04<11:00:56,  3.41it/s]
                                                            
{'loss': 3.046, 'learning_rate': 4.2781572539809085e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236240/371472 [7:46:04<11:00:56,  3.41it/s]
 64%|██████▎   | 236241/371472 [7:46:05<11:15:56,  3.33it/s]
 64%|██████▎   | 236242/371472 [7:46:05<10:31:35,  3.57it/s]
 64%|██████▎   | 236243/371472 [7:46:05<10:26:10,  3.60it/s]
 64%|██████▎   | 236244/371472 [7:46:06<10:46:43,  3.48it/s]
 64%|██████▎   | 236245/371472 [7:46:06<10:55:27,  3.44it/s]
 64%|██████▎   | 236246/371472 [7:46:06<10:34:24,  3.55it/s]
 64%|██████▎   | 236247/371472 [7:46:06<10:24:59,  3.61it/s]
 64%|██████▎   | 236248/371472 [7:46:07<10:48:38,  3.47it/s]
 64%|██████▎   | 236249/371472 [7:46:07<10:16:19,  3.66it/s]
 64%|██████▎   | 236250/371472 [7:46:07<11:11:20,  3.36it/s]
 64%|██████▎   | 236251/371472 [7:46:08<10:53:25,  3.45it/s]
 64%|██████▎   | 236252/371472 [7:46:08<10:52:58,  3.45it/s]
 64%|██████▎   | 236253/371472 [7:46:08<10:28:18,  3.59it/s]
 64%|██████▎   | 236254/371472 [7:46:08<10:29:17,  3.58it/s]
 64%|██████▎   | 236255/371472 [7:46:09<11:19:57,  3.31it/s]
 64%|██████▎   | 236256/371472 [7:46:09<11:20:35,  3.31it/s]
 64%|██████▎   | 236257/371472 [7:46:09<11:30:15,  3.26it/s]
 64%|██████▎   | 236258/371472 [7:46:10<11:29:21,  3.27it/s]
 64%|██████▎   | 236259/371472 [7:46:10<10:58:53,  3.42it/s]
 64%|██████▎   | 236260/371472 [7:46:10<10:30:48,  3.57it/s]
                                                            
{'loss': 3.0687, 'learning_rate': 4.277672434226119e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236260/371472 [7:46:10<10:30:48,  3.57it/s]
 64%|██████▎   | 236261/371472 [7:46:10<10:26:03,  3.60it/s]
 64%|██████▎   | 236262/371472 [7:46:11<10:14:32,  3.67it/s]
 64%|██████▎   | 236263/371472 [7:46:11<10:03:46,  3.73it/s]
 64%|██████▎   | 236264/371472 [7:46:11<10:02:03,  3.74it/s]
 64%|██████▎   | 236265/371472 [7:46:11<9:53:46,  3.80it/s] 
 64%|██████▎   | 236266/371472 [7:46:12<9:56:27,  3.78it/s]
 64%|██████▎   | 236267/371472 [7:46:12<10:02:36,  3.74it/s]
 64%|██████▎   | 236268/371472 [7:46:12<9:48:55,  3.83it/s] 
 64%|██████▎   | 236269/371472 [7:46:13<10:00:30,  3.75it/s]
 64%|██████▎   | 236270/371472 [7:46:13<10:47:44,  3.48it/s]
 64%|██████▎   | 236271/371472 [7:46:13<10:46:05,  3.49it/s]
 64%|██████▎   | 236272/371472 [7:46:13<10:26:34,  3.60it/s]
 64%|██████▎   | 236273/371472 [7:46:14<10:19:30,  3.64it/s]
 64%|██████▎   | 236274/371472 [7:46:14<10:22:25,  3.62it/s]
 64%|██████▎   | 236275/371472 [7:46:14<10:03:31,  3.73it/s]
 64%|██████▎   | 236276/371472 [7:46:15<10:13:34,  3.67it/s]
 64%|██████▎   | 236277/371472 [7:46:15<10:30:55,  3.57it/s]
 64%|██████▎   | 236278/371472 [7:46:15<10:31:14,  3.57it/s]
 64%|██████▎   | 236279/371472 [7:46:15<10:34:05,  3.55it/s]
 64%|██████▎   | 236280/371472 [7:46:16<10:16:58,  3.65it/s]
                                                            
{'loss': 2.9011, 'learning_rate': 4.277187614471331e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236280/371472 [7:46:16<10:16:58,  3.65it/s]
 64%|██████▎   | 236281/371472 [7:46:16<10:49:28,  3.47it/s]
 64%|██████▎   | 236282/371472 [7:46:16<11:52:40,  3.16it/s]
 64%|██████▎   | 236283/371472 [7:46:17<11:21:18,  3.31it/s]
 64%|██████▎   | 236284/371472 [7:46:17<11:12:41,  3.35it/s]
 64%|██████▎   | 236285/371472 [7:46:17<12:42:47,  2.95it/s]
 64%|██████▎   | 236286/371472 [7:46:18<12:03:10,  3.12it/s]
 64%|██████▎   | 236287/371472 [7:46:18<12:03:17,  3.12it/s]
 64%|██████▎   | 236288/371472 [7:46:18<11:55:14,  3.15it/s]
 64%|██████▎   | 236289/371472 [7:46:19<11:46:37,  3.19it/s]
 64%|██████▎   | 236290/371472 [7:46:19<11:17:34,  3.33it/s]
 64%|██████▎   | 236291/371472 [7:46:19<11:09:47,  3.36it/s]
 64%|██████▎   | 236292/371472 [7:46:19<10:56:06,  3.43it/s]
 64%|██████▎   | 236293/371472 [7:46:20<11:02:41,  3.40it/s]
 64%|██████▎   | 236294/371472 [7:46:20<10:48:32,  3.47it/s]
 64%|██████▎   | 236295/371472 [7:46:20<10:42:48,  3.50it/s]
 64%|██████▎   | 236296/371472 [7:46:21<10:59:53,  3.41it/s]
 64%|██████▎   | 236297/371472 [7:46:21<11:05:12,  3.39it/s]
 64%|██████▎   | 236298/371472 [7:46:21<11:30:37,  3.26it/s]
 64%|██████▎   | 236299/371472 [7:46:21<11:31:57,  3.26it/s]
 64%|██████▎   | 236300/371472 [7:46:22<11:07:07,  3.38it/s]
                                                            
{'loss': 2.9096, 'learning_rate': 4.276702794716542e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236300/371472 [7:46:22<11:07:07,  3.38it/s]
 64%|██████▎   | 236301/371472 [7:46:22<11:05:43,  3.38it/s]
 64%|██████▎   | 236302/371472 [7:46:22<11:03:17,  3.40it/s]
 64%|██████▎   | 236303/371472 [7:46:23<11:42:32,  3.21it/s]
 64%|██████▎   | 236304/371472 [7:46:23<11:56:22,  3.14it/s]
 64%|██████▎   | 236305/371472 [7:46:23<11:26:45,  3.28it/s]
 64%|██████▎   | 236306/371472 [7:46:24<10:56:57,  3.43it/s]
 64%|██████▎   | 236307/371472 [7:46:24<11:14:15,  3.34it/s]
 64%|██████▎   | 236308/371472 [7:46:24<12:06:23,  3.10it/s]
 64%|██████▎   | 236309/371472 [7:46:25<11:32:00,  3.26it/s]
 64%|██████▎   | 236310/371472 [7:46:25<11:05:00,  3.39it/s]
 64%|██████▎   | 236311/371472 [7:46:25<12:04:40,  3.11it/s]
 64%|██████▎   | 236312/371472 [7:46:25<11:25:03,  3.29it/s]
 64%|██████▎   | 236313/371472 [7:46:26<11:38:09,  3.23it/s]
 64%|██████▎   | 236314/371472 [7:46:26<11:30:15,  3.26it/s]
 64%|██████▎   | 236315/371472 [7:46:26<11:02:30,  3.40it/s]
 64%|██████▎   | 236316/371472 [7:46:27<10:53:39,  3.45it/s]
 64%|██████▎   | 236317/371472 [7:46:27<10:52:33,  3.45it/s]
 64%|██████▎   | 236318/371472 [7:46:27<10:26:14,  3.60it/s]
 64%|██████▎   | 236319/371472 [7:46:27<10:17:27,  3.65it/s]
 64%|██████▎   | 236320/371472 [7:46:28<10:12:45,  3.68it/s]
                                                            
{'loss': 2.7537, 'learning_rate': 4.276217974961753e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236320/371472 [7:46:28<10:12:45,  3.68it/s]
 64%|██████▎   | 236321/371472 [7:46:28<10:16:48,  3.65it/s]
 64%|██████▎   | 236322/371472 [7:46:28<11:11:00,  3.36it/s]
 64%|██████▎   | 236323/371472 [7:46:29<10:52:56,  3.45it/s]
 64%|██████▎   | 236324/371472 [7:46:29<10:52:47,  3.45it/s]
 64%|██████▎   | 236325/371472 [7:46:29<10:23:05,  3.61it/s]
 64%|██████▎   | 236326/371472 [7:46:29<10:13:56,  3.67it/s]
 64%|██████▎   | 236327/371472 [7:46:30<10:36:58,  3.54it/s]
 64%|██████▎   | 236328/371472 [7:46:30<11:04:35,  3.39it/s]
 64%|██████▎   | 236329/371472 [7:46:30<10:45:17,  3.49it/s]
 64%|██████▎   | 236330/371472 [7:46:31<10:28:19,  3.58it/s]
 64%|██████▎   | 236331/371472 [7:46:31<10:06:19,  3.71it/s]
 64%|██████▎   | 236332/371472 [7:46:31<10:48:38,  3.47it/s]
 64%|██████▎   | 236333/371472 [7:46:31<10:22:31,  3.62it/s]
 64%|██████▎   | 236334/371472 [7:46:32<10:10:57,  3.69it/s]
 64%|██████▎   | 236335/371472 [7:46:32<10:11:51,  3.68it/s]
 64%|██████▎   | 236336/371472 [7:46:32<10:06:22,  3.71it/s]
 64%|██████▎   | 236337/371472 [7:46:32<10:11:42,  3.68it/s]
 64%|██████▎   | 236338/371472 [7:46:33<10:07:01,  3.71it/s]
 64%|██████▎   | 236339/371472 [7:46:33<10:18:36,  3.64it/s]
 64%|██████▎   | 236340/371472 [7:46:33<10:33:14,  3.56it/s]
                                                            
{'loss': 2.9379, 'learning_rate': 4.2757331552069637e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236340/371472 [7:46:33<10:33:14,  3.56it/s]
 64%|██████▎   | 236341/371472 [7:46:34<10:27:34,  3.59it/s]
 64%|██████▎   | 236342/371472 [7:46:34<10:16:30,  3.65it/s]
 64%|██████▎   | 236343/371472 [7:46:34<10:04:55,  3.72it/s]
 64%|██████▎   | 236344/371472 [7:46:34<10:04:27,  3.73it/s]
 64%|██████▎   | 236345/371472 [7:46:35<10:08:45,  3.70it/s]
 64%|██████▎   | 236346/371472 [7:46:35<10:08:06,  3.70it/s]
 64%|██████▎   | 236347/371472 [7:46:35<10:42:47,  3.50it/s]
 64%|██████▎   | 236348/371472 [7:46:36<11:03:14,  3.40it/s]
 64%|██████▎   | 236349/371472 [7:46:36<10:42:02,  3.51it/s]
 64%|██████▎   | 236350/371472 [7:46:36<10:16:01,  3.66it/s]
 64%|██████▎   | 236351/371472 [7:46:36<10:12:20,  3.68it/s]
 64%|██████▎   | 236352/371472 [7:46:37<9:49:25,  3.82it/s] 
 64%|██████▎   | 236353/371472 [7:46:37<10:33:33,  3.55it/s]
 64%|██████▎   | 236354/371472 [7:46:37<10:39:44,  3.52it/s]
 64%|██████▎   | 236355/371472 [7:46:37<10:10:16,  3.69it/s]
 64%|██████▎   | 236356/371472 [7:46:38<10:32:45,  3.56it/s]
 64%|██████▎   | 236357/371472 [7:46:38<11:02:24,  3.40it/s]
 64%|██████▎   | 236358/371472 [7:46:38<11:22:07,  3.30it/s]
 64%|██████▎   | 236359/371472 [7:46:39<11:10:52,  3.36it/s]
 64%|██████▎   | 236360/371472 [7:46:39<11:00:14,  3.41it/s]
                                                            
{'loss': 3.044, 'learning_rate': 4.2752483354521755e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236360/371472 [7:46:39<11:00:14,  3.41it/s]
 64%|██████▎   | 236361/371472 [7:46:39<10:34:44,  3.55it/s]
 64%|██████▎   | 236362/371472 [7:46:39<10:20:28,  3.63it/s]
 64%|██████▎   | 236363/371472 [7:46:40<9:55:52,  3.78it/s] 
 64%|██████▎   | 236364/371472 [7:46:40<10:29:40,  3.58it/s]
 64%|██████▎   | 236365/371472 [7:46:40<10:18:28,  3.64it/s]
 64%|██████▎   | 236366/371472 [7:46:41<10:39:59,  3.52it/s]
 64%|██████▎   | 236367/371472 [7:46:41<10:07:07,  3.71it/s]
 64%|██████▎   | 236368/371472 [7:46:41<11:53:19,  3.16it/s]
 64%|██████▎   | 236369/371472 [7:46:42<11:40:41,  3.21it/s]
 64%|██████▎   | 236370/371472 [7:46:42<11:46:52,  3.19it/s]
 64%|██████▎   | 236371/371472 [7:46:42<11:25:37,  3.28it/s]
 64%|██████▎   | 236372/371472 [7:46:42<12:02:32,  3.12it/s]
 64%|██████▎   | 236373/371472 [7:46:43<11:24:49,  3.29it/s]
 64%|██████▎   | 236374/371472 [7:46:43<10:55:58,  3.43it/s]
 64%|██████▎   | 236375/371472 [7:46:43<10:20:51,  3.63it/s]
 64%|██████▎   | 236376/371472 [7:46:44<10:23:33,  3.61it/s]
 64%|██████▎   | 236377/371472 [7:46:44<11:39:06,  3.22it/s]
 64%|██████▎   | 236378/371472 [7:46:44<10:58:14,  3.42it/s]
 64%|██████▎   | 236379/371472 [7:46:44<10:34:41,  3.55it/s]
 64%|██████▎   | 236380/371472 [7:46:45<10:55:59,  3.43it/s]
                                                            
{'loss': 2.8018, 'learning_rate': 4.2747635156973857e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236380/371472 [7:46:45<10:55:59,  3.43it/s]
 64%|██████▎   | 236381/371472 [7:46:45<10:27:24,  3.59it/s]
 64%|██████▎   | 236382/371472 [7:46:45<11:22:56,  3.30it/s]
 64%|██████▎   | 236383/371472 [7:46:46<10:57:53,  3.42it/s]
 64%|██████▎   | 236384/371472 [7:46:46<11:10:54,  3.36it/s]
 64%|██████▎   | 236385/371472 [7:46:46<11:04:30,  3.39it/s]
 64%|██████▎   | 236386/371472 [7:46:47<10:52:16,  3.45it/s]
 64%|██████▎   | 236387/371472 [7:46:47<10:59:03,  3.42it/s]
 64%|██████▎   | 236388/371472 [7:46:47<11:58:10,  3.13it/s]
 64%|██████▎   | 236389/371472 [7:46:47<11:20:30,  3.31it/s]
 64%|██████▎   | 236390/371472 [7:46:48<10:45:11,  3.49it/s]
 64%|██████▎   | 236391/371472 [7:46:48<10:27:28,  3.59it/s]
 64%|██████▎   | 236392/371472 [7:46:48<10:19:51,  3.63it/s]
 64%|██████▎   | 236393/371472 [7:46:48<10:07:10,  3.71it/s]
 64%|██████▎   | 236394/371472 [7:46:49<10:16:50,  3.65it/s]
 64%|██████▎   | 236395/371472 [7:46:49<11:14:16,  3.34it/s]
 64%|██████▎   | 236396/371472 [7:46:49<11:20:56,  3.31it/s]
 64%|██████▎   | 236397/371472 [7:46:50<10:46:19,  3.48it/s]
 64%|██████▎   | 236398/371472 [7:46:50<10:10:40,  3.69it/s]
 64%|██████▎   | 236399/371472 [7:46:50<10:05:02,  3.72it/s]
 64%|██████▎   | 236400/371472 [7:46:50<10:10:39,  3.69it/s]
                                                            
{'loss': 2.8133, 'learning_rate': 4.2742786959425974e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236400/371472 [7:46:50<10:10:39,  3.69it/s]
 64%|██████▎   | 236401/371472 [7:46:51<10:14:10,  3.67it/s]
 64%|██████▎   | 236402/371472 [7:46:51<10:08:01,  3.70it/s]
 64%|██████▎   | 236403/371472 [7:46:51<10:09:18,  3.69it/s]
 64%|██████▎   | 236404/371472 [7:46:52<10:09:27,  3.69it/s]
 64%|██████▎   | 236405/371472 [7:46:52<9:56:46,  3.77it/s] 
 64%|██████▎   | 236406/371472 [7:46:52<10:06:37,  3.71it/s]
 64%|██████▎   | 236407/371472 [7:46:52<10:45:01,  3.49it/s]
 64%|██████▎   | 236408/371472 [7:46:53<10:35:59,  3.54it/s]
 64%|██████▎   | 236409/371472 [7:46:53<10:50:50,  3.46it/s]
 64%|██████▎   | 236410/371472 [7:46:53<10:20:09,  3.63it/s]
 64%|██████▎   | 236411/371472 [7:46:53<10:13:29,  3.67it/s]
 64%|██████▎   | 236412/371472 [7:46:54<10:14:45,  3.66it/s]
 64%|██████▎   | 236413/371472 [7:46:54<10:13:41,  3.67it/s]
 64%|██████▎   | 236414/371472 [7:46:54<10:10:15,  3.69it/s]
 64%|██████▎   | 236415/371472 [7:46:55<9:59:28,  3.75it/s] 
 64%|██████▎   | 236416/371472 [7:46:55<10:38:52,  3.52it/s]
 64%|██████▎   | 236417/371472 [7:46:55<10:20:35,  3.63it/s]
 64%|██████▎   | 236418/371472 [7:46:55<11:11:27,  3.35it/s]
 64%|██████▎   | 236419/371472 [7:46:56<11:07:01,  3.37it/s]
 64%|██████▎   | 236420/371472 [7:46:56<10:44:41,  3.49it/s]
                                                            
{'loss': 3.0464, 'learning_rate': 4.273793876187808e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236420/371472 [7:46:56<10:44:41,  3.49it/s]
 64%|██████▎   | 236421/371472 [7:46:56<11:24:37,  3.29it/s]
 64%|██████▎   | 236422/371472 [7:46:57<11:32:52,  3.25it/s]
 64%|██████▎   | 236423/371472 [7:46:57<11:31:16,  3.26it/s]
 64%|██████▎   | 236424/371472 [7:46:57<11:20:37,  3.31it/s]
 64%|██████▎   | 236425/371472 [7:46:58<11:06:14,  3.38it/s]
 64%|██████▎   | 236426/371472 [7:46:58<10:39:31,  3.52it/s]
 64%|██████▎   | 236427/371472 [7:46:58<10:47:12,  3.48it/s]
 64%|██████▎   | 236428/371472 [7:46:58<10:22:18,  3.62it/s]
 64%|██████▎   | 236429/371472 [7:46:59<10:11:00,  3.68it/s]
 64%|██████▎   | 236430/371472 [7:46:59<9:48:22,  3.83it/s] 
 64%|██████▎   | 236431/371472 [7:46:59<9:47:09,  3.83it/s]
 64%|██████▎   | 236432/371472 [7:46:59<10:28:28,  3.58it/s]
 64%|██████▎   | 236433/371472 [7:47:00<10:49:28,  3.47it/s]
 64%|██████▎   | 236434/371472 [7:47:00<10:45:17,  3.49it/s]
 64%|██████▎   | 236435/371472 [7:47:00<11:27:32,  3.27it/s]
 64%|██████▎   | 236436/371472 [7:47:01<11:07:44,  3.37it/s]
 64%|██████▎   | 236437/371472 [7:47:01<12:14:30,  3.06it/s]
 64%|██████▎   | 236438/371472 [7:47:01<12:41:44,  2.95it/s]
 64%|██████▎   | 236439/371472 [7:47:02<11:51:47,  3.16it/s]
 64%|██████▎   | 236440/371472 [7:47:02<10:56:22,  3.43it/s]
                                                            
{'loss': 2.9628, 'learning_rate': 4.2733090564330194e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236440/371472 [7:47:02<10:56:22,  3.43it/s]
 64%|██████▎   | 236441/371472 [7:47:02<10:38:16,  3.53it/s]
 64%|██████▎   | 236442/371472 [7:47:02<10:28:31,  3.58it/s]
 64%|██████▎   | 236443/371472 [7:47:03<10:17:58,  3.64it/s]
 64%|██████▎   | 236444/371472 [7:47:03<10:07:03,  3.71it/s]
 64%|██████▎   | 236445/371472 [7:47:03<9:46:03,  3.84it/s] 
 64%|██████▎   | 236446/371472 [7:47:03<9:37:04,  3.90it/s]
 64%|██████▎   | 236447/371472 [7:47:04<10:03:38,  3.73it/s]
 64%|██████▎   | 236448/371472 [7:47:04<9:43:42,  3.86it/s] 
 64%|██████▎   | 236449/371472 [7:47:04<9:47:17,  3.83it/s]
 64%|██████▎   | 236450/371472 [7:47:05<10:22:05,  3.62it/s]
 64%|██████▎   | 236451/371472 [7:47:05<10:36:28,  3.54it/s]
 64%|██████▎   | 236452/371472 [7:47:05<10:40:33,  3.51it/s]
 64%|██████▎   | 236453/371472 [7:47:06<11:15:24,  3.33it/s]
 64%|██████▎   | 236454/371472 [7:47:06<11:29:34,  3.26it/s]
 64%|██████▎   | 236455/371472 [7:47:06<10:57:55,  3.42it/s]
 64%|██████▎   | 236456/371472 [7:47:06<10:30:32,  3.57it/s]
 64%|██████▎   | 236457/371472 [7:47:07<10:42:44,  3.50it/s]
 64%|██████▎   | 236458/371472 [7:47:07<10:37:48,  3.53it/s]
 64%|██████▎   | 236459/371472 [7:47:07<12:06:48,  3.10it/s]
 64%|██████▎   | 236460/371472 [7:47:08<11:28:29,  3.27it/s]
                                                            
{'loss': 2.8244, 'learning_rate': 4.27282423667823e-07, 'epoch': 10.18}
+
 64%|██████▎   | 236460/371472 [7:47:08<11:28:29,  3.27it/s]
 64%|██████▎   | 236461/371472 [7:47:08<11:08:41,  3.37it/s]
 64%|██████▎   | 236462/371472 [7:47:08<10:53:44,  3.44it/s]
 64%|██████▎   | 236463/371472 [7:47:08<10:30:14,  3.57it/s]
 64%|██████▎   | 236464/371472 [7:47:09<11:10:53,  3.35it/s]
 64%|██████▎   | 236465/371472 [7:47:09<11:06:13,  3.38it/s]
 64%|██████▎   | 236466/371472 [7:47:09<11:04:00,  3.39it/s]
 64%|██████▎   | 236467/371472 [7:47:10<10:34:38,  3.55it/s]
 64%|██████▎   | 236468/371472 [7:47:10<11:30:44,  3.26it/s]
 64%|██████▎   | 236469/371472 [7:47:10<10:58:15,  3.42it/s]
 64%|██████▎   | 236470/371472 [7:47:11<10:57:34,  3.42it/s]
 64%|██████▎   | 236471/371472 [7:47:11<10:48:35,  3.47it/s]
 64%|██████▎   | 236472/371472 [7:47:11<10:19:41,  3.63it/s]
 64%|██████▎   | 236473/371472 [7:47:11<9:57:07,  3.77it/s] 
 64%|██████▎   | 236474/371472 [7:47:12<10:51:38,  3.45it/s]
 64%|██████▎   | 236475/371472 [7:47:12<11:37:30,  3.23it/s]
 64%|██████▎   | 236476/371472 [7:47:12<11:12:07,  3.35it/s]
 64%|██████▎   | 236477/371472 [7:47:13<11:03:19,  3.39it/s]
 64%|██████▎   | 236478/371472 [7:47:13<10:58:58,  3.41it/s]
 64%|██████▎   | 236479/371472 [7:47:13<10:49:28,  3.46it/s]
 64%|██████▎   | 236480/371472 [7:47:13<11:19:45,  3.31it/s]
                                                            
{'loss': 2.759, 'learning_rate': 4.272339416923442e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236480/371472 [7:47:13<11:19:45,  3.31it/s]
 64%|██████▎   | 236481/371472 [7:47:14<11:21:52,  3.30it/s]
 64%|██████▎   | 236482/371472 [7:47:14<10:42:56,  3.50it/s]
 64%|██████▎   | 236483/371472 [7:47:14<10:29:25,  3.57it/s]
 64%|██████▎   | 236484/371472 [7:47:15<10:59:08,  3.41it/s]
 64%|██████▎   | 236485/371472 [7:47:15<10:38:30,  3.52it/s]
 64%|██████▎   | 236486/371472 [7:47:15<10:13:48,  3.67it/s]
 64%|██████▎   | 236487/371472 [7:47:15<10:04:32,  3.72it/s]
 64%|██████▎   | 236488/371472 [7:47:16<9:51:44,  3.80it/s] 
 64%|██████▎   | 236489/371472 [7:47:16<10:28:57,  3.58it/s]
 64%|██████▎   | 236490/371472 [7:47:16<10:32:02,  3.56it/s]
 64%|██████▎   | 236491/371472 [7:47:16<10:24:36,  3.60it/s]
 64%|██████▎   | 236492/371472 [7:47:17<10:22:40,  3.61it/s]
 64%|██████▎   | 236493/371472 [7:47:17<10:32:00,  3.56it/s]
 64%|██████▎   | 236494/371472 [7:47:17<10:15:45,  3.65it/s]
 64%|██████▎   | 236495/371472 [7:47:18<11:14:14,  3.34it/s]
 64%|██████▎   | 236496/371472 [7:47:18<11:13:56,  3.34it/s]
 64%|██████▎   | 236497/371472 [7:47:18<10:53:10,  3.44it/s]
 64%|██████▎   | 236498/371472 [7:47:18<10:28:22,  3.58it/s]
 64%|██████▎   | 236499/371472 [7:47:19<10:21:14,  3.62it/s]
 64%|██████▎   | 236500/371472 [7:47:19<10:00:01,  3.75it/s]
                                                            
{'loss': 2.9747, 'learning_rate': 4.271854597168652e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236500/371472 [7:47:19<10:00:01,  3.75it/s]
 64%|██████▎   | 236501/371472 [7:47:19<10:24:31,  3.60it/s]
 64%|██████▎   | 236502/371472 [7:47:20<10:29:26,  3.57it/s]
 64%|██████▎   | 236503/371472 [7:47:20<10:25:38,  3.60it/s]
 64%|██████▎   | 236504/371472 [7:47:20<11:01:22,  3.40it/s]
 64%|██████▎   | 236505/371472 [7:47:20<10:39:33,  3.52it/s]
 64%|██████▎   | 236506/371472 [7:47:21<10:37:31,  3.53it/s]
 64%|██████▎   | 236507/371472 [7:47:21<10:25:55,  3.59it/s]
 64%|██████▎   | 236508/371472 [7:47:21<11:06:49,  3.37it/s]
 64%|██████▎   | 236509/371472 [7:47:22<10:45:27,  3.48it/s]
 64%|██████▎   | 236510/371472 [7:47:22<11:09:00,  3.36it/s]
 64%|██████▎   | 236511/371472 [7:47:22<12:00:04,  3.12it/s]
 64%|██████▎   | 236512/371472 [7:47:23<11:17:21,  3.32it/s]
 64%|██████▎   | 236513/371472 [7:47:23<10:37:10,  3.53it/s]
 64%|██████▎   | 236514/371472 [7:47:23<10:56:07,  3.43it/s]
 64%|██████▎   | 236515/371472 [7:47:23<10:51:55,  3.45it/s]
 64%|██████▎   | 236516/371472 [7:47:24<10:26:41,  3.59it/s]
 64%|██████▎   | 236517/371472 [7:47:24<10:14:56,  3.66it/s]
 64%|██████▎   | 236518/371472 [7:47:24<10:03:52,  3.72it/s]
 64%|██████▎   | 236519/371472 [7:47:24<10:02:48,  3.73it/s]
 64%|██████▎   | 236520/371472 [7:47:25<9:49:33,  3.82it/s] 
                                                           
{'loss': 2.8488, 'learning_rate': 4.271369777413864e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236520/371472 [7:47:25<9:49:33,  3.82it/s]
 64%|██████▎   | 236521/371472 [7:47:25<9:55:54,  3.77it/s]
 64%|██████▎   | 236522/371472 [7:47:25<10:06:51,  3.71it/s]
 64%|██████▎   | 236523/371472 [7:47:26<10:13:04,  3.67it/s]
 64%|██████▎   | 236524/371472 [7:47:26<10:09:54,  3.69it/s]
 64%|██████▎   | 236525/371472 [7:47:26<10:57:12,  3.42it/s]
 64%|██████▎   | 236526/371472 [7:47:26<11:10:30,  3.35it/s]
 64%|██████▎   | 236527/371472 [7:47:27<10:54:30,  3.44it/s]
 64%|██████▎   | 236528/371472 [7:47:27<10:35:46,  3.54it/s]
 64%|██████▎   | 236529/371472 [7:47:27<10:34:16,  3.55it/s]
 64%|██████▎   | 236530/371472 [7:47:27<10:02:05,  3.74it/s]
 64%|██████▎   | 236531/371472 [7:47:28<10:08:52,  3.69it/s]
 64%|██████▎   | 236532/371472 [7:47:28<11:44:18,  3.19it/s]
 64%|██████▎   | 236533/371472 [7:47:28<11:29:24,  3.26it/s]
 64%|██████▎   | 236534/371472 [7:47:29<11:01:20,  3.40it/s]
 64%|██████▎   | 236535/371472 [7:47:29<10:38:14,  3.52it/s]
 64%|██████▎   | 236536/371472 [7:47:29<10:19:11,  3.63it/s]
 64%|██████▎   | 236537/371472 [7:47:30<10:41:45,  3.50it/s]
 64%|██████▎   | 236538/371472 [7:47:30<11:06:42,  3.37it/s]
 64%|██████▎   | 236539/371472 [7:47:30<12:48:33,  2.93it/s]
 64%|██████▎   | 236540/371472 [7:47:31<11:50:00,  3.17it/s]
                                                            
{'loss': 2.8869, 'learning_rate': 4.2708849576590746e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236540/371472 [7:47:31<11:50:00,  3.17it/s]
 64%|███���██▎   | 236541/371472 [7:47:31<11:35:15,  3.23it/s]
 64%|██████▎   | 236542/371472 [7:47:31<11:31:52,  3.25it/s]
 64%|██████▎   | 236543/371472 [7:47:31<11:09:11,  3.36it/s]
 64%|██████▎   | 236544/371472 [7:47:32<10:44:08,  3.49it/s]
 64%|██████▎   | 236545/371472 [7:47:32<10:30:23,  3.57it/s]
 64%|██████▎   | 236546/371472 [7:47:32<10:12:56,  3.67it/s]
 64%|██████▎   | 236547/371472 [7:47:33<10:21:18,  3.62it/s]
 64%|██████▎   | 236548/371472 [7:47:33<10:03:35,  3.73it/s]
 64%|██████▎   | 236549/371472 [7:47:33<10:34:02,  3.55it/s]
 64%|██████▎   | 236550/371472 [7:47:33<11:09:50,  3.36it/s]
 64%|██████▎   | 236551/371472 [7:47:34<11:00:51,  3.40it/s]
 64%|██████▎   | 236552/371472 [7:47:34<10:41:17,  3.51it/s]
 64%|██████▎   | 236553/371472 [7:47:34<10:25:56,  3.59it/s]
 64%|██████▎   | 236554/371472 [7:47:35<10:47:30,  3.47it/s]
 64%|██████▎   | 236555/371472 [7:47:35<10:21:28,  3.62it/s]
 64%|██████▎   | 236556/371472 [7:47:35<10:20:00,  3.63it/s]
 64%|██████▎   | 236557/371472 [7:47:35<9:55:43,  3.77it/s] 
 64%|██████▎   | 236558/371472 [7:47:36<9:55:25,  3.78it/s]
 64%|██████▎   | 236559/371472 [7:47:36<10:03:53,  3.72it/s]
 64%|██████▎   | 236560/371472 [7:47:36<10:16:17,  3.65it/s]
                                                            
{'loss': 2.755, 'learning_rate': 4.270400137904286e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236560/371472 [7:47:36<10:16:17,  3.65it/s]
 64%|██████▎   | 236561/371472 [7:47:36<10:31:25,  3.56it/s]
 64%|██████▎   | 236562/371472 [7:47:37<10:43:56,  3.49it/s]
 64%|██████▎   | 236563/371472 [7:47:37<10:36:13,  3.53it/s]
 64%|██████▎   | 236564/371472 [7:47:37<11:25:42,  3.28it/s]
 64%|██████▎   | 236565/371472 [7:47:38<11:08:34,  3.36it/s]
 64%|██████▎   | 236566/371472 [7:47:38<10:52:21,  3.45it/s]
 64%|██████▎   | 236567/371472 [7:47:38<10:29:22,  3.57it/s]
 64%|██████▎   | 236568/371472 [7:47:38<10:24:34,  3.60it/s]
 64%|██████▎   | 236569/371472 [7:47:39<10:06:29,  3.71it/s]
 64%|██████▎   | 236570/371472 [7:47:39<10:03:38,  3.72it/s]
 64%|██████▎   | 236571/371472 [7:47:39<10:21:24,  3.62it/s]
 64%|██████▎   | 236572/371472 [7:47:40<10:12:13,  3.67it/s]
 64%|██████▎   | 236573/371472 [7:47:40<10:19:48,  3.63it/s]
 64%|██████▎   | 236574/371472 [7:47:40<11:01:00,  3.40it/s]
 64%|██████▎   | 236575/371472 [7:47:40<10:58:22,  3.41it/s]
 64%|██████▎   | 236576/371472 [7:47:41<10:38:47,  3.52it/s]
 64%|██████▎   | 236577/371472 [7:47:41<11:04:58,  3.38it/s]
 64%|██████▎   | 236578/371472 [7:47:41<10:50:54,  3.45it/s]
 64%|██████▎   | 236579/371472 [7:47:42<10:38:54,  3.52it/s]
 64%|██████▎   | 236580/371472 [7:47:42<10:28:41,  3.58it/s]
                                                            
{'loss': 2.6971, 'learning_rate': 4.269915318149496e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236580/371472 [7:47:42<10:28:41,  3.58it/s]
 64%|██████▎   | 236581/371472 [7:47:42<10:29:57,  3.57it/s]
 64%|██████▎   | 236582/371472 [7:47:42<10:33:08,  3.55it/s]
 64%|██████▎   | 236583/371472 [7:47:43<10:49:55,  3.46it/s]
 64%|██████▎   | 236584/371472 [7:47:43<10:55:28,  3.43it/s]
 64%|██████▎   | 236585/371472 [7:47:43<10:30:48,  3.56it/s]
 64%|██████▎   | 236586/371472 [7:47:43<10:14:15,  3.66it/s]
 64%|██████▎   | 236587/371472 [7:47:44<10:09:47,  3.69it/s]
 64%|██████▎   | 236588/371472 [7:47:44<11:10:08,  3.35it/s]
 64%|██████▎   | 236589/371472 [7:47:44<10:44:40,  3.49it/s]
 64%|██████▎   | 236590/371472 [7:47:45<10:44:48,  3.49it/s]
 64%|██████▎   | 236591/371472 [7:47:45<10:49:14,  3.46it/s]
 64%|██████▎   | 236592/371472 [7:47:45<11:02:07,  3.40it/s]
 64%|██████▎   | 236593/371472 [7:47:46<10:30:38,  3.56it/s]
 64%|██████▎   | 236594/371472 [7:47:46<10:27:26,  3.58it/s]
 64%|██████▎   | 236595/371472 [7:47:46<10:21:29,  3.62it/s]
 64%|██████▎   | 236596/371472 [7:47:46<10:38:20,  3.52it/s]
 64%|██████▎   | 236597/371472 [7:47:47<10:20:38,  3.62it/s]
 64%|██████▎   | 236598/371472 [7:47:47<10:22:41,  3.61it/s]
 64%|██████▎   | 236599/371472 [7:47:47<10:16:02,  3.65it/s]
 64%|██████▎   | 236600/371472 [7:47:47<10:15:51,  3.65it/s]
                                                            
{'loss': 3.0584, 'learning_rate': 4.2694304983947083e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236600/371472 [7:47:47<10:15:51,  3.65it/s]
 64%|██████▎   | 236601/371472 [7:47:48<10:10:13,  3.68it/s]
 64%|██████▎   | 236602/371472 [7:47:48<10:12:48,  3.67it/s]
 64%|██████▎   | 236603/371472 [7:47:48<9:59:57,  3.75it/s] 
 64%|██████▎   | 236604/371472 [7:47:49<9:57:46,  3.76it/s]
 64%|██████▎   | 236605/371472 [7:47:49<10:36:18,  3.53it/s]
 64%|██████▎   | 236606/371472 [7:47:49<10:39:21,  3.52it/s]
 64%|██████▎   | 236607/371472 [7:47:49<10:37:48,  3.52it/s]
 64%|██████▎   | 236608/371472 [7:47:50<10:25:03,  3.60it/s]
 64%|██████▎   | 236609/371472 [7:47:50<10:23:51,  3.60it/s]
 64%|██████▎   | 236610/371472 [7:47:50<10:21:34,  3.62it/s]
 64%|██████▎   | 236611/371472 [7:47:50<10:27:10,  3.58it/s]
 64%|██████▎   | 236612/371472 [7:47:51<10:32:45,  3.55it/s]
 64%|██████▎   | 236613/371472 [7:47:51<10:22:50,  3.61it/s]
 64%|██████▎   | 236614/371472 [7:47:51<10:47:10,  3.47it/s]
 64%|██████▎   | 236615/371472 [7:47:52<10:57:16,  3.42it/s]
 64%|██████▎   | 236616/371472 [7:47:52<10:47:54,  3.47it/s]
 64%|██████▎   | 236617/371472 [7:47:52<10:43:57,  3.49it/s]
 64%|██████▎   | 236618/371472 [7:47:53<10:39:58,  3.51it/s]
 64%|██████▎   | 236619/371472 [7:47:53<10:31:56,  3.56it/s]
 64%|██████▎   | 236620/371472 [7:47:53<10:10:24,  3.68it/s]
                                                            
{'loss': 2.9209, 'learning_rate': 4.2689456786399185e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236620/371472 [7:47:53<10:10:24,  3.68it/s]
 64%|██████▎   | 236621/371472 [7:47:53<10:05:35,  3.71it/s]
 64%|██████▎   | 236622/371472 [7:47:54<10:23:24,  3.61it/s]
 64%|██████▎   | 236623/371472 [7:47:54<10:30:08,  3.57it/s]
 64%|██████▎   | 236624/371472 [7:47:54<10:42:54,  3.50it/s]
 64%|██████▎   | 236625/371472 [7:47:54<10:25:17,  3.59it/s]
 64%|██████▎   | 236626/371472 [7:47:55<10:16:36,  3.64it/s]
 64%|██████▎   | 236627/371472 [7:47:55<10:01:22,  3.74it/s]
 64%|██████▎   | 236628/371472 [7:47:55<9:49:54,  3.81it/s] 
 64%|██████▎   | 236629/371472 [7:47:56<10:37:00,  3.53it/s]
 64%|██████▎   | 236630/371472 [7:47:56<10:29:03,  3.57it/s]
 64%|██████▎   | 236631/371472 [7:47:56<10:09:47,  3.69it/s]
 64%|██████▎   | 236632/371472 [7:47:56<10:09:11,  3.69it/s]
 64%|██████▎   | 236633/371472 [7:47:57<10:21:51,  3.61it/s]
 64%|██████▎   | 236634/371472 [7:47:57<10:52:36,  3.44it/s]
 64%|██████▎   | 236635/371472 [7:47:57<10:45:08,  3.48it/s]
 64%|██████▎   | 236636/371472 [7:47:57<10:37:45,  3.52it/s]
 64%|██████▎   | 236637/371472 [7:47:58<10:23:58,  3.60it/s]
 64%|██████▎   | 236638/371472 [7:47:58<10:18:07,  3.64it/s]
 64%|██████▎   | 236639/371472 [7:47:58<11:07:04,  3.37it/s]
 64%|██████▎   | 236640/371472 [7:47:59<10:32:38,  3.55it/s]
                                                            
{'loss': 2.8079, 'learning_rate': 4.26846085888513e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236640/371472 [7:47:59<10:32:38,  3.55it/s]
 64%|██████▎   | 236641/371472 [7:47:59<10:10:44,  3.68it/s]
 64%|██████▎   | 236642/371472 [7:47:59<9:55:41,  3.77it/s] 
 64%|██████▎   | 236643/371472 [7:47:59<10:33:13,  3.55it/s]
 64%|██████▎   | 236644/371472 [7:48:00<10:34:18,  3.54it/s]
 64%|██████▎   | 236645/371472 [7:48:00<11:42:09,  3.20it/s]
 64%|██████▎   | 236646/371472 [7:48:00<11:22:54,  3.29it/s]
 64%|██████▎   | 236647/371472 [7:48:01<11:20:24,  3.30it/s]
 64%|██████▎   | 236648/371472 [7:48:01<10:53:03,  3.44it/s]
 64%|██████▎   | 236649/371472 [7:48:01<10:34:29,  3.54it/s]
 64%|██████▎   | 236650/371472 [7:48:01<10:06:36,  3.70it/s]
 64%|██████▎   | 236651/371472 [7:48:02<10:19:53,  3.62it/s]
 64%|██████▎   | 236652/371472 [7:48:02<10:32:06,  3.55it/s]
 64%|██████▎   | 236653/371472 [7:48:02<10:26:13,  3.59it/s]
 64%|██████▎   | 236654/371472 [7:48:03<10:04:34,  3.72it/s]
 64%|██████▎   | 236655/371472 [7:48:03<9:59:43,  3.75it/s] 
 64%|██████▎   | 236656/371472 [7:48:03<9:38:58,  3.88it/s]
 64%|██████▎   | 236657/371472 [7:48:03<10:25:26,  3.59it/s]
 64%|██████▎   | 236658/371472 [7:48:04<10:19:56,  3.62it/s]
 64%|██████▎   | 236659/371472 [7:48:04<10:28:59,  3.57it/s]
 64%|██████▎   | 236660/371472 [7:48:04<10:04:45,  3.72it/s]
                                                            
{'loss': 2.8885, 'learning_rate': 4.267976039130341e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236660/371472 [7:48:04<10:04:45,  3.72it/s]
 64%|██████▎   | 236661/371472 [7:48:04<10:12:02,  3.67it/s]
 64%|██████▎   | 236662/371472 [7:48:05<10:01:21,  3.74it/s]
 64%|██████▎   | 236663/371472 [7:48:05<11:12:14,  3.34it/s]
 64%|██████▎   | 236664/371472 [7:48:05<10:33:14,  3.55it/s]
 64%|██████▎   | 236665/371472 [7:48:06<10:27:55,  3.58it/s]
 64%|██████▎   | 236666/371472 [7:48:06<10:05:18,  3.71it/s]
 64%|██████▎   | 236667/371472 [7:48:06<9:59:35,  3.75it/s] 
 64%|██████▎   | 236668/371472 [7:48:06<10:09:14,  3.69it/s]
 64%|██████▎   | 236669/371472 [7:48:07<10:31:28,  3.56it/s]
 64%|██████▎   | 236670/371472 [7:48:07<10:30:35,  3.56it/s]
 64%|██████▎   | 236671/371472 [7:48:07<10:36:12,  3.53it/s]
 64%|██████▎   | 236672/371472 [7:48:08<10:17:01,  3.64it/s]
 64%|██████▎   | 236673/371472 [7:48:08<10:04:56,  3.71it/s]
 64%|██████▎   | 236674/371472 [7:48:08<10:55:53,  3.43it/s]
 64%|██████▎   | 236675/371472 [7:48:08<10:44:33,  3.49it/s]
 64%|██████▎   | 236676/371472 [7:48:09<11:01:31,  3.40it/s]
 64%|██████▎   | 236677/371472 [7:48:09<11:20:51,  3.30it/s]
 64%|██████▎   | 236678/371472 [7:48:09<11:04:07,  3.38it/s]
 64%|██████▎   | 236679/371472 [7:48:10<10:34:48,  3.54it/s]
 64%|██████▎   | 236680/371472 [7:48:10<10:19:26,  3.63it/s]
                                                            
{'loss': 2.8441, 'learning_rate': 4.267491219375552e-07, 'epoch': 10.19}
+
 64%|██████▎   | 236680/371472 [7:48:10<10:19:26,  3.63it/s]
 64%|██████▎   | 236681/371472 [7:48:10<10:06:28,  3.70it/s]
 64%|██████▎   | 236682/371472 [7:48:10<9:46:32,  3.83it/s] 
 64%|██████▎   | 236683/371472 [7:48:11<10:34:32,  3.54it/s]
 64%|██████▎   | 236684/371472 [7:48:11<10:12:11,  3.67it/s]
 64%|██████▎   | 236685/371472 [7:48:11<10:19:02,  3.63it/s]
 64%|██████▎   | 236686/371472 [7:48:12<10:47:57,  3.47it/s]
 64%|██████▎   | 236687/371472 [7:48:12<10:14:01,  3.66it/s]
 64%|██████▎   | 236688/371472 [7:48:12<9:48:45,  3.82it/s] 
 64%|██████▎   | 236689/371472 [7:48:12<9:31:53,  3.93it/s]
 64%|██████▎   | 236690/371472 [7:48:13<10:32:24,  3.55it/s]
 64%|██████▎   | 236691/371472 [7:48:13<10:31:55,  3.55it/s]
 64%|██████▎   | 236692/371472 [7:48:13<10:35:07,  3.54it/s]
 64%|██████▎   | 236693/371472 [7:48:13<10:32:21,  3.55it/s]
 64%|██████▎   | 236694/371472 [7:48:14<10:38:10,  3.52it/s]
 64%|██████▎   | 236695/371472 [7:48:14<11:21:48,  3.29it/s]
 64%|██████▎   | 236696/371472 [7:48:14<10:40:53,  3.50it/s]
 64%|██████▎   | 236697/371472 [7:48:15<11:06:04,  3.37it/s]
 64%|██████▎   | 236698/371472 [7:48:15<10:29:01,  3.57it/s]
 64%|██████▎   | 236699/371472 [7:48:15<10:11:06,  3.68it/s]
 64%|██████▎   | 236700/371472 [7:48:15<10:11:01,  3.68it/s]
                                                            
{'loss': 2.8709, 'learning_rate': 4.267006399620763e-07, 'epoch': 10.2}
+
 64%|██████▎   | 236700/371472 [7:48:15<10:11:01,  3.68it/s]
 64%|██████▎   | 236701/371472 [7:48:16<10:20:20,  3.62it/s]
 64%|██████▎   | 236702/371472 [7:48:16<9:56:16,  3.77it/s] 
 64%|██████▎   | 236703/371472 [7:48:16<9:47:03,  3.83it/s]
 64%|██████▎   | 236704/371472 [7:48:16<9:41:58,  3.86it/s]
 64%|██████▎   | 236705/371472 [7:48:17<9:59:42,  3.75it/s]
 64%|██████▎   | 236706/371472 [7:48:17<9:52:05,  3.79it/s]
 64%|██████▎   | 236707/371472 [7:48:17<9:54:57,  3.78it/s]
 64%|██████▎   | 236708/371472 [7:48:17<9:52:06,  3.79it/s]
 64%|██████▎   | 236709/371472 [7:48:18<10:20:24,  3.62it/s]
 64%|██████▎   | 236710/371472 [7:48:18<10:29:47,  3.57it/s]
 64%|██████▎   | 236711/371472 [7:48:18<10:07:50,  3.70it/s]
 64%|██████▎   | 236712/371472 [7:48:19<9:55:15,  3.77it/s] 
 64%|██████▎   | 236713/371472 [7:48:19<9:48:06,  3.82it/s]
 64%|██████▎   | 236714/371472 [7:48:19<9:32:28,  3.92it/s]
 64%|██████▎   | 236715/371472 [7:48:19<9:45:03,  3.84it/s]
 64%|██████▎   | 236716/371472 [7:48:20<10:35:59,  3.53it/s]
 64%|██████▎   | 236717/371472 [7:48:20<10:15:31,  3.65it/s]
 64%|██████▎   | 236718/371472 [7:48:20<10:43:15,  3.49it/s]
 64%|██████▎   | 236719/371472 [7:48:21<10:36:10,  3.53it/s]
 64%|██████▎   | 236720/371472 [7:48:21<10:34:06,  3.54it/s]
                                                            
{'loss': 2.9686, 'learning_rate': 4.2665215798659736e-07, 'epoch': 10.2}
+
 64%|██████▎   | 236720/371472 [7:48:21<10:34:06,  3.54it/s]
 64%|██████▎   | 236721/371472 [7:48:21<12:19:36,  3.04it/s]
 64%|██████▎   | 236722/371472 [7:48:22<11:43:02,  3.19it/s]
 64%|██████▎   | 236723/371472 [7:48:22<11:22:46,  3.29it/s]
 64%|██████▎   | 236724/371472 [7:48:22<11:15:55,  3.32it/s]
 64%|██████▎   | 236725/371472 [7:48:22<11:40:34,  3.21it/s]
 64%|██████▎   | 236726/371472 [7:48:23<10:59:12,  3.41it/s]
 64%|██████▎   | 236727/371472 [7:48:23<10:49:59,  3.46it/s]
 64%|██████▎   | 236728/371472 [7:48:23<10:38:46,  3.52it/s]
 64%|██████▎   | 236729/371472 [7:48:24<10:21:30,  3.61it/s]
 64%|██████▎   | 236730/371472 [7:48:24<10:43:56,  3.49it/s]
 64%|██████▎   | 236731/371472 [7:48:24<10:42:21,  3.50it/s]
 64%|██████▎   | 236732/371472 [7:48:24<10:57:48,  3.41it/s]
 64%|██████▎   | 236733/371472 [7:48:25<11:32:04,  3.24it/s]
 64%|██████▎   | 236734/371472 [7:48:25<11:11:34,  3.34it/s]
 64%|██████▎   | 236735/371472 [7:48:25<11:17:07,  3.32it/s]
 64%|██████▎   | 236736/371472 [7:48:26<10:42:05,  3.50it/s]
 64%|██████▎   | 236737/371472 [7:48:26<10:22:48,  3.61it/s]
 64%|██████▎   | 236738/371472 [7:48:26<10:18:44,  3.63it/s]
 64%|██████▎   | 236739/371472 [7:48:26<10:00:53,  3.74it/s]
 64%|██████▎   | 236740/371472 [7:48:27<11:01:34,  3.39it/s]
                                                            
{'loss': 2.688, 'learning_rate': 4.2660367601111854e-07, 'epoch': 10.2}
+
 64%|██████▎   | 236740/371472 [7:48:27<11:01:34,  3.39it/s]
 64%|██████▎   | 236741/371472 [7:48:27<10:30:14,  3.56it/s]
 64%|██████▎   | 236742/371472 [7:48:27<9:58:02,  3.75it/s] 
 64%|██████▎   | 236743/371472 [7:48:27<10:04:44,  3.71it/s]
 64%|██████▎   | 236744/371472 [7:48:28<10:24:02,  3.60it/s]
 64%|██████▎   | 236745/371472 [7:48:28<10:19:14,  3.63it/s]
 64%|██████▎   | 236746/371472 [7:48:28<10:20:28,  3.62it/s]
 64%|██████▎   | 236747/371472 [7:48:29<10:03:37,  3.72it/s]
 64%|██████▎   | 236748/371472 [7:48:29<10:02:27,  3.73it/s]
 64%|██████▎   | 236749/371472 [7:48:29<9:48:49,  3.81it/s] 
 64%|██████▎   | 236750/371472 [7:48:29<9:52:44,  3.79it/s]
 64%|██████▎   | 236751/371472 [7:48:30<9:49:12,  3.81it/s]
 64%|██████▎   | 236752/371472 [7:48:30<10:46:01,  3.48it/s]
 64%|██████▎   | 236753/371472 [7:48:30<10:28:52,  3.57it/s]
 64%|██████▎   | 236754/371472 [7:48:31<11:16:03,  3.32it/s]
 64%|██████▎   | 236755/371472 [7:48:31<11:29:03,  3.26it/s]
 64%|██████▎   | 236756/371472 [7:48:31<12:08:08,  3.08it/s]
 64%|██████▎   | 236757/371472 [7:48:32<11:18:47,  3.31it/s]
 64%|██████▎   | 236758/371472 [7:48:32<10:45:07,  3.48it/s]
 64%|██████▎   | 236759/371472 [7:48:32<10:15:30,  3.65it/s]
 64%|██████▎   | 236760/371472 [7:48:32<10:56:01,  3.42it/s]
                                                            
{'loss': 2.9012, 'learning_rate': 4.2655519403563956e-07, 'epoch': 10.2}
+
 64%|██████▎   | 236760/371472 [7:48:32<10:56:01,  3.42it/s]
 64%|██████▎   | 236761/371472 [7:48:33<10:43:26,  3.49it/s]
 64%|██████▎   | 236762/371472 [7:48:33<10:27:31,  3.58it/s]
 64%|██████▎   | 236763/371472 [7:48:33<10:53:59,  3.43it/s]
 64%|██████▎   | 236764/371472 [7:48:33<10:51:49,  3.44it/s]
 64%|██████▎   | 236765/371472 [7:48:34<10:24:31,  3.59it/s]
 64%|██████▎   | 236766/371472 [7:48:34<10:19:40,  3.62it/s]
 64%|██████▎   | 236767/371472 [7:48:34<10:17:46,  3.63it/s]
 64%|██████▎   | 236768/371472 [7:48:35<10:44:13,  3.48it/s]
 64%|██████▎   | 236769/371472 [7:48:35<10:16:46,  3.64it/s]
 64%|██████▎   | 236770/371472 [7:48:35<10:02:29,  3.73it/s]
 64%|██████▎   | 236771/371472 [7:48:35<9:57:57,  3.75it/s] 
 64%|██████▎   | 236772/371472 [7:48:36<10:32:44,  3.55it/s]
 64%|██████▎   | 236773/371472 [7:48:36<10:11:20,  3.67it/s]
 64%|██████▎   | 236774/371472 [7:48:36<10:33:38,  3.54it/s]
 64%|██████▎   | 236775/371472 [7:48:36<10:22:54,  3.60it/s]
 64%|██████▎   | 236776/371472 [7:48:37<10:21:44,  3.61it/s]
 64%|██████▎   | 236777/371472 [7:48:37<10:20:03,  3.62it/s]
 64%|██████▎   | 236778/371472 [7:48:37<11:22:59,  3.29it/s]
 64%|██████▎   | 236779/371472 [7:48:38<11:43:25,  3.19it/s]
 64%|██████▎   | 236780/371472 [7:48:38<11:15:45,  3.32it/s]
                                                            
{'loss': 2.936, 'learning_rate': 4.2650671206016074e-07, 'epoch': 10.2}
+
 64%|██████▎   | 236780/371472 [7:48:38<11:15:45,  3.32it/s]
 64%|██████▎   | 236781/371472 [7:48:38<10:42:16,  3.50it/s]
 64%|██████▎   | 236782/371472 [7:48:39<10:17:44,  3.63it/s]
 64%|██████▎   | 236783/371472 [7:48:39<9:59:02,  3.75it/s] 
 64%|██████▎   | 236784/371472 [7:48:39<10:37:11,  3.52it/s]
 64%|██████▎   | 236785/371472 [7:48:39<10:48:54,  3.46it/s]
 64%|██████▎   | 236786/371472 [7:48:40<10:52:27,  3.44it/s]
 64%|██████▎   | 236787/371472 [7:48:40<12:03:13,  3.10it/s]
 64%|██████▎   | 236788/371472 [7:48:40<11:20:01,  3.30it/s]
 64%|██████▎   | 236789/371472 [7:48:41<10:56:06,  3.42it/s]
 64%|██████▎   | 236790/371472 [7:48:41<10:30:47,  3.56it/s]
 64%|██████▎   | 236791/371472 [7:48:41<10:26:07,  3.58it/s]
 64%|██████▎   | 236792/371472 [7:48:41<11:00:38,  3.40it/s]
 64%|██████▎   | 236793/371472 [7:48:42<10:48:59,  3.46it/s]
 64%|██████▎   | 236794/371472 [7:48:42<11:23:35,  3.28it/s]
 64%|██████▎   | 236795/371472 [7:48:42<11:18:49,  3.31it/s]
 64%|██████▎   | 236796/371472 [7:48:43<10:50:42,  3.45it/s]
 64%|██████▎   | 236797/371472 [7:48:43<10:32:47,  3.55it/s]
 64%|██████▎   | 236798/371472 [7:48:43<10:51:50,  3.44it/s]
 64%|██████▎   | 236799/371472 [7:48:44<10:51:11,  3.45it/s]
 64%|██████▎   | 236800/371472 [7:48:44<10:33:10,  3.54it/s]
                                                            
{'loss': 2.8275, 'learning_rate': 4.264582300846818e-07, 'epoch': 10.2}
+
 64%|██████▎   | 236800/371472 [7:48:44<10:33:10,  3.54it/s]
 64%|██████▎   | 236801/371472 [7:48:44<10:22:05,  3.61it/s]
 64%|██████▎   | 236802/371472 [7:48:44<12:16:08,  3.05it/s]
 64%|██████▎   | 236803/371472 [7:48:45<11:24:56,  3.28it/s]
 64%|██████▎   | 236804/371472 [7:48:45<11:01:31,  3.39it/s]
 64%|██████▎   | 236805/371472 [7:48:45<10:31:32,  3.55it/s]
 64%|██████▎   | 236806/371472 [7:48:46<10:42:52,  3.49it/s]
 64%|██████▎   | 236807/371472 [7:48:46<10:22:30,  3.61it/s]
 64%|██████▎   | 236808/371472 [7:48:46<10:20:25,  3.62it/s]
 64%|██████▎   | 236809/371472 [7:48:46<10:40:59,  3.50it/s]
 64%|██████▎   | 236810/371472 [7:48:47<12:13:32,  3.06it/s]
 64%|██████▎   | 236811/371472 [7:48:47<11:53:51,  3.14it/s]
 64%|██████▎   | 236812/371472 [7:48:47<11:05:42,  3.37it/s]
 64%|██████▎   | 236813/371472 [7:48:48<10:45:05,  3.48it/s]
 64%|██████▍   | 236814/371472 [7:48:48<10:14:47,  3.65it/s]
 64%|██████▍   | 236815/371472 [7:48:48<10:14:37,  3.65it/s]
 64%|██████▍   | 236816/371472 [7:48:48<9:48:55,  3.81it/s] 
 64%|██████▍   | 236817/371472 [7:48:49<9:51:56,  3.79it/s]
 64%|██████▍   | 236818/371472 [7:48:49<9:54:01,  3.78it/s]
 64%|██████▍   | 236819/371472 [7:48:49<10:11:49,  3.67it/s]
 64%|██████▍   | 236820/371472 [7:48:50<10:43:12,  3.49it/s]
                                                            
{'loss': 2.8892, 'learning_rate': 4.2640974810920293e-07, 'epoch': 10.2}
+
 64%|██████▍   | 236820/371472 [7:48:50<10:43:12,  3.49it/s]
 64%|██████▍   | 236821/371472 [7:48:50<10:37:40,  3.52it/s]
 64%|██████▍   | 236822/371472 [7:48:50<10:45:40,  3.48it/s]
 64%|██████▍   | 236823/371472 [7:48:50<10:54:31,  3.43it/s]
 64%|██████▍   | 236824/371472 [7:48:51<10:53:18,  3.44it/s]
 64%|██████▍   | 236825/371472 [7:48:51<10:52:16,  3.44it/s]
 64%|██████▍   | 236826/371472 [7:48:51<10:32:03,  3.55it/s]
 64%|██████▍   | 236827/371472 [7:48:52<10:23:05,  3.60it/s]
 64%|██████▍   | 236828/371472 [7:48:52<10:26:40,  3.58it/s]
 64%|██████▍   | 236829/371472 [7:48:52<10:55:00,  3.43it/s]
 64%|██████▍   | 236830/371472 [7:48:52<11:26:58,  3.27it/s]
 64%|██████▍   | 236831/371472 [7:48:53<11:28:14,  3.26it/s]
 64%|██████▍   | 236832/371472 [7:48:53<11:32:33,  3.24it/s]
 64%|██████▍   | 236833/371472 [7:48:53<11:42:00,  3.20it/s]
 64%|██████▍   | 236834/371472 [7:48:54<11:14:35,  3.33it/s]
 64%|██████▍   | 236835/371472 [7:48:54<11:19:10,  3.30it/s]
 64%|██████▍   | 236836/371472 [7:48:54<10:41:13,  3.50it/s]
 64%|██████▍   | 236837/371472 [7:48:54<10:34:07,  3.54it/s]
 64%|██████▍   | 236838/371472 [7:48:55<10:15:59,  3.64it/s]
 64%|██████▍   | 236839/371472 [7:48:55<10:23:36,  3.60it/s]
 64%|██████▍   | 236840/371472 [7:48:55<10:32:03,  3.55it/s]
                                                            
{'loss': 2.9191, 'learning_rate': 4.26361266133724e-07, 'epoch': 10.2}
+
 64%|██████▍   | 236840/371472 [7:48:55<10:32:03,  3.55it/s]
 64%|██████▍   | 236841/371472 [7:48:56<10:48:09,  3.46it/s]
 64%|██████▍   | 236842/371472 [7:48:56<10:31:44,  3.55it/s]
 64%|██████▍   | 236843/371472 [7:48:56<11:03:40,  3.38it/s]
 64%|██████▍   | 236844/371472 [7:48:57<11:07:51,  3.36it/s]
 64%|██████▍   | 236845/371472 [7:48:57<11:04:44,  3.38it/s]
 64%|██████▍   | 236846/371472 [7:48:57<10:38:05,  3.52it/s]
 64%|██████▍   | 236847/371472 [7:48:57<10:28:00,  3.57it/s]
 64%|██████▍   | 236848/371472 [7:48:58<10:33:20,  3.54it/s]
 64%|██████▍   | 236849/371472 [7:48:58<10:21:36,  3.61it/s]
 64%|██████▍   | 236850/371472 [7:48:58<10:23:32,  3.60it/s]
 64%|██████▍   | 236851/371472 [7:48:58<10:24:09,  3.59it/s]
 64%|██████▍   | 236852/371472 [7:48:59<10:42:44,  3.49it/s]
 64%|██████▍   | 236853/371472 [7:48:59<10:49:01,  3.46it/s]
 64%|██████▍   | 236854/371472 [7:48:59<11:12:24,  3.34it/s]
 64%|██████▍   | 236855/371472 [7:49:00<10:37:14,  3.52it/s]
 64%|██████▍   | 236856/371472 [7:49:00<10:36:04,  3.53it/s]
 64%|██████▍   | 236857/371472 [7:49:00<10:57:55,  3.41it/s]
 64%|██████▍   | 236858/371472 [7:49:00<10:40:13,  3.50it/s]
 64%|██████▍   | 236859/371472 [7:49:01<10:18:44,  3.63it/s]
 64%|██████▍   | 236860/371472 [7:49:01<10:45:08,  3.48it/s]
                                                            
{'loss': 2.9947, 'learning_rate': 4.263127841582452e-07, 'epoch': 10.2}
+
 64%|██████▍   | 236860/371472 [7:49:01<10:45:08,  3.48it/s]
 64%|██████▍   | 236861/371472 [7:49:01<10:28:31,  3.57it/s]
 64%|██████▍   | 236862/371472 [7:49:02<10:13:09,  3.66it/s]
 64%|██████▍   | 236863/371472 [7:49:02<10:05:00,  3.71it/s]
 64%|██████▍   | 236864/371472 [7:49:02<10:00:51,  3.73it/s]
 64%|██████▍   | 236865/371472 [7:49:02<10:16:21,  3.64it/s]
 64%|██████▍   | 236866/371472 [7:49:03<10:25:29,  3.59it/s]
 64%|██████▍   | 236867/371472 [7:49:03<10:11:44,  3.67it/s]
 64%|██████▍   | 236868/371472 [7:49:03<10:18:06,  3.63it/s]
 64%|██████▍   | 236869/371472 [7:49:03<10:07:12,  3.69it/s]
 64%|██████▍   | 236870/371472 [7:49:04<10:32:35,  3.55it/s]
 64%|██████▍   | 236871/371472 [7:49:04<12:10:23,  3.07it/s]
 64%|██████▍   | 236872/371472 [7:49:05<11:39:55,  3.21it/s]
 64%|██████▍   | 236873/371472 [7:49:05<11:07:51,  3.36it/s]
 64%|██████▍   | 236874/371472 [7:49:05<11:08:53,  3.35it/s]
 64%|██████▍   | 236875/371472 [7:49:05<10:40:56,  3.50it/s]
 64%|██████▍   | 236876/371472 [7:49:06<10:11:15,  3.67it/s]
 64%|██████▍   | 236877/371472 [7:49:06<10:09:51,  3.68it/s]
 64%|██████▍   | 236878/371472 [7:49:06<11:10:57,  3.34it/s]
 64%|██████▍   | 236879/371472 [7:49:06<10:49:57,  3.45it/s]
 64%|██████▍   | 236880/371472 [7:49:07<11:10:03,  3.35it/s]
                                                            
{'loss': 2.8667, 'learning_rate': 4.262643021827662e-07, 'epoch': 10.2}
+
 64%|██████▍   | 236880/371472 [7:49:07<11:10:03,  3.35it/s]
 64%|██████▍   | 236881/371472 [7:49:07<10:37:26,  3.52it/s]
 64%|██████▍   | 236882/371472 [7:49:07<10:30:14,  3.56it/s]
 64%|██████▍   | 236883/371472 [7:49:08<10:39:00,  3.51it/s]
 64%|██████▍   | 236884/371472 [7:49:08<10:53:24,  3.43it/s]
 64%|██████▍   | 236885/371472 [7:49:08<10:58:38,  3.41it/s]
 64%|██████▍   | 236886/371472 [7:49:08<10:33:24,  3.54it/s]
 64%|██████▍   | 236887/371472 [7:49:09<10:44:09,  3.48it/s]
 64%|██████▍   | 236888/371472 [7:49:09<10:20:00,  3.62it/s]
 64%|██████▍   | 236889/371472 [7:49:09<10:40:37,  3.50it/s]
 64%|██████▍   | 236890/371472 [7:49:10<10:32:59,  3.54it/s]
 64%|██████▍   | 236891/371472 [7:49:10<10:42:38,  3.49it/s]
 64%|██████▍   | 236892/371472 [7:49:10<10:26:24,  3.58it/s]
 64%|██████▍   | 236893/371472 [7:49:10<9:58:31,  3.75it/s] 
 64%|██████▍   | 236894/371472 [7:49:11<9:50:09,  3.80it/s]
 64%|██████▍   | 236895/371472 [7:49:11<10:03:39,  3.72it/s]
 64%|██████▍   | 236896/371472 [7:49:11<10:08:34,  3.69it/s]
 64%|██████▍   | 236897/371472 [7:49:11<10:12:10,  3.66it/s]
 64%|██████▍   | 236898/371472 [7:49:12<9:58:48,  3.75it/s] 
 64%|██████▍   | 236899/371472 [7:49:12<10:15:03,  3.65it/s]
 64%|██████▍   | 236900/371472 [7:49:12<9:56:37,  3.76it/s] 
                                                           
{'loss': 2.8644, 'learning_rate': 4.262158202072874e-07, 'epoch': 10.2}
+
 64%|██████▍   | 236900/371472 [7:49:12<9:56:37,  3.76it/s]
 64%|██████▍   | 236901/371472 [7:49:13<10:15:27,  3.64it/s]
 64%|██████▍   | 236902/371472 [7:49:13<10:25:57,  3.58it/s]
 64%|██████▍   | 236903/371472 [7:49:13<10:05:29,  3.70it/s]
 64%|██████▍   | 236904/371472 [7:49:13<10:47:41,  3.46it/s]
 64%|██████▍   | 236905/371472 [7:49:14<10:30:51,  3.56it/s]
 64%|██████▍   | 236906/371472 [7:49:14<10:40:06,  3.50it/s]
 64%|██████▍   | 236907/371472 [7:49:14<10:39:58,  3.50it/s]
 64%|██████▍   | 236908/371472 [7:49:15<10:43:57,  3.48it/s]
 64%|██████▍   | 236909/371472 [7:49:15<10:31:06,  3.55it/s]
 64%|██████▍   | 236910/371472 [7:49:15<10:16:30,  3.64it/s]
 64%|██████▍   | 236911/371472 [7:49:15<10:23:33,  3.60it/s]
 64%|██████▍   | 236912/371472 [7:49:16<10:41:39,  3.50it/s]
 64%|██████▍   | 236913/371472 [7:49:16<10:27:05,  3.58it/s]
 64%|██████▍   | 236914/371472 [7:49:16<10:42:52,  3.49it/s]
 64%|██████▍   | 236915/371472 [7:49:17<10:56:19,  3.42it/s]
 64%|██████▍   | 236916/371472 [7:49:17<10:31:22,  3.55it/s]
 64%|██████▍   | 236917/371472 [7:49:17<10:03:09,  3.72it/s]
 64%|██████▍   | 236918/371472 [7:49:17<10:07:14,  3.69it/s]
 64%|██████▍   | 236919/371472 [7:49:18<10:17:33,  3.63it/s]
 64%|██████▍   | 236920/371472 [7:49:18<10:21:11,  3.61it/s]
                                                            
{'loss': 2.8327, 'learning_rate': 4.2616733823180845e-07, 'epoch': 10.2}
+
 64%|██████▍   | 236920/371472 [7:49:18<10:21:11,  3.61it/s]
 64%|██████▍   | 236921/371472 [7:49:18<10:19:13,  3.62it/s]
 64%|██████▍   | 236922/371472 [7:49:18<10:15:03,  3.65it/s]
 64%|██████▍   | 236923/371472 [7:49:19<10:22:54,  3.60it/s]
 64%|██████▍   | 236924/371472 [7:49:19<10:08:24,  3.69it/s]
 64%|██████▍   | 236925/371472 [7:49:19<9:52:15,  3.79it/s] 
 64%|██████▍   | 236926/371472 [7:49:20<10:31:01,  3.55it/s]
 64%|██████▍   | 236927/371472 [7:49:20<10:34:55,  3.53it/s]
 64%|██████▍   | 236928/371472 [7:49:20<10:38:52,  3.51it/s]
 64%|██████▍   | 236929/371472 [7:49:20<10:21:15,  3.61it/s]
 64%|██████▍   | 236930/371472 [7:49:21<10:05:01,  3.71it/s]
 64%|██████▍   | 236931/371472 [7:49:21<10:31:20,  3.55it/s]
 64%|██████▍   | 236932/371472 [7:49:21<10:19:47,  3.62it/s]
 64%|██████▍   | 236933/371472 [7:49:22<10:54:45,  3.42it/s]
 64%|██████▍   | 236934/371472 [7:49:22<10:28:26,  3.57it/s]
 64%|██████▍   | 236935/371472 [7:49:22<10:22:14,  3.60it/s]
 64%|██████▍   | 236936/371472 [7:49:22<10:18:39,  3.62it/s]
 64%|██████▍   | 236937/371472 [7:49:23<10:20:50,  3.61it/s]
 64%|██████▍   | 236938/371472 [7:49:23<10:20:00,  3.62it/s]
 64%|██████▍   | 236939/371472 [7:49:23<10:24:19,  3.59it/s]
 64%|██████▍   | 236940/371472 [7:49:23<10:26:51,  3.58it/s]
                                                            
{'loss': 2.8409, 'learning_rate': 4.2611885625632957e-07, 'epoch': 10.21}
+
 64%|██████▍   | 236940/371472 [7:49:23<10:26:51,  3.58it/s]
 64%|██████▍   | 236941/371472 [7:49:24<10:29:53,  3.56it/s]
 64%|██████▍   | 236942/371472 [7:49:24<10:39:22,  3.51it/s]
 64%|██████▍   | 236943/371472 [7:49:24<10:35:32,  3.53it/s]
 64%|██████▍   | 236944/371472 [7:49:25<10:29:48,  3.56it/s]
 64%|██████▍   | 236945/371472 [7:49:25<11:17:05,  3.31it/s]
 64%|██████▍   | 236946/371472 [7:49:25<11:18:00,  3.31it/s]
 64%|██████▍   | 236947/371472 [7:49:26<10:43:45,  3.48it/s]
 64%|██████▍   | 236948/371472 [7:49:26<10:46:02,  3.47it/s]
 64%|██████▍   | 236949/371472 [7:49:26<10:24:12,  3.59it/s]
 64%|██████▍   | 236950/371472 [7:49:26<10:13:25,  3.65it/s]
 64%|██████▍   | 236951/371472 [7:49:27<10:12:26,  3.66it/s]
 64%|██████▍   | 236952/371472 [7:49:27<10:17:21,  3.63it/s]
 64%|██████▍   | 236953/371472 [7:49:27<10:42:58,  3.49it/s]
 64%|██████▍   | 236954/371472 [7:49:27<10:22:49,  3.60it/s]
 64%|██████▍   | 236955/371472 [7:49:28<10:46:26,  3.47it/s]
 64%|██████▍   | 236956/371472 [7:49:28<10:32:21,  3.55it/s]
 64%|██████▍   | 236957/371472 [7:49:28<11:14:30,  3.32it/s]
 64%|██████▍   | 236958/371472 [7:49:29<11:03:22,  3.38it/s]
 64%|██████▍   | 236959/371472 [7:49:29<11:07:10,  3.36it/s]
 64%|██████▍   | 236960/371472 [7:49:29<11:53:05,  3.14it/s]
                                                            
{'loss': 2.8753, 'learning_rate': 4.2607037428085064e-07, 'epoch': 10.21}
+
 64%|██████▍   | 236960/371472 [7:49:29<11:53:05,  3.14it/s]
 64%|██████▍   | 236961/371472 [7:49:30<11:34:32,  3.23it/s]
 64%|██████▍   | 236962/371472 [7:49:30<10:56:00,  3.42it/s]
 64%|██████▍   | 236963/371472 [7:49:30<10:43:38,  3.48it/s]
 64%|██████▍   | 236964/371472 [7:49:30<11:08:05,  3.36it/s]
 64%|██████▍   | 236965/371472 [7:49:31<10:48:45,  3.46it/s]
 64%|██████▍   | 236966/371472 [7:49:31<10:18:37,  3.62it/s]
 64%|██████▍   | 236967/371472 [7:49:31<9:57:25,  3.75it/s] 
 64%|██████▍   | 236968/371472 [7:49:31<9:54:43,  3.77it/s]
 64%|██████▍   | 236969/371472 [7:49:32<9:48:18,  3.81it/s]
 64%|██████▍   | 236970/371472 [7:49:32<9:43:04,  3.84it/s]
 64%|██████▍   | 236971/371472 [7:49:32<10:04:15,  3.71it/s]
 64%|██████▍   | 236972/371472 [7:49:33<9:48:03,  3.81it/s] 
 64%|██████▍   | 236973/371472 [7:49:33<9:46:19,  3.82it/s]
 64%|██████▍   | 236974/371472 [7:49:33<9:44:50,  3.83it/s]
 64%|██████▍   | 236975/371472 [7:49:33<9:52:31,  3.78it/s]
 64%|██████▍   | 236976/371472 [7:49:34<9:55:05,  3.77it/s]
 64%|██████▍   | 236977/371472 [7:49:34<9:58:48,  3.74it/s]
 64%|██████▍   | 236978/371472 [7:49:34<10:10:56,  3.67it/s]
 64%|██████▍   | 236979/371472 [7:49:34<10:24:43,  3.59it/s]
 64%|██████▍   | 236980/371472 [7:49:35<10:29:21,  3.56it/s]
                                                            
{'loss': 2.8131, 'learning_rate': 4.260218923053718e-07, 'epoch': 10.21}
+
 64%|██████▍   | 236980/371472 [7:49:35<10:29:21,  3.56it/s]
 64%|██████▍   | 236981/371472 [7:49:35<10:32:14,  3.55it/s]
 64%|██████▍   | 236982/371472 [7:49:35<10:19:15,  3.62it/s]
 64%|██████▍   | 236983/371472 [7:49:36<10:22:55,  3.60it/s]
 64%|██████▍   | 236984/371472 [7:49:36<10:26:33,  3.58it/s]
 64%|██████▍   | 236985/371472 [7:49:36<11:11:45,  3.34it/s]
 64%|██████▍   | 236986/371472 [7:49:36<10:30:36,  3.55it/s]
 64%|██████▍   | 236987/371472 [7:49:37<10:05:01,  3.70it/s]
 64%|██████▍   | 236988/371472 [7:49:37<10:07:04,  3.69it/s]
 64%|██████▍   | 236989/371472 [7:49:37<11:25:30,  3.27it/s]
 64%|██████▍   | 236990/371472 [7:49:38<10:57:05,  3.41it/s]
 64%|██████▍   | 236991/371472 [7:49:38<10:33:14,  3.54it/s]
 64%|██████▍   | 236992/371472 [7:49:38<10:55:38,  3.42it/s]
 64%|██████▍   | 236993/371472 [7:49:38<10:34:47,  3.53it/s]
 64%|██████▍   | 236994/371472 [7:49:39<10:56:10,  3.42it/s]
 64%|██████▍   | 236995/371472 [7:49:39<10:39:40,  3.50it/s]
 64%|██████▍   | 236996/371472 [7:49:39<10:17:27,  3.63it/s]
 64%|██████▍   | 236997/371472 [7:49:40<10:04:07,  3.71it/s]
 64%|██████▍   | 236998/371472 [7:49:40<10:16:03,  3.64it/s]
 64%|██████▍   | 236999/371472 [7:49:40<10:32:54,  3.54it/s]
 64%|██████▍   | 237000/371472 [7:49:40<10:22:13,  3.60it/s]
                                                            
{'loss': 2.8442, 'learning_rate': 4.259734103298929e-07, 'epoch': 10.21}
+
 64%|██████▍   | 237000/371472 [7:49:40<10:22:13,  3.60it/s]
 64%|██████▍   | 237001/371472 [7:49:41<10:18:17,  3.62it/s]
 64%|██████▍   | 237002/371472 [7:49:41<10:11:17,  3.67it/s]
 64%|██████▍   | 237003/371472 [7:49:41<11:19:58,  3.30it/s]
 64%|██████▍   | 237004/371472 [7:49:42<11:16:05,  3.31it/s]
 64%|██████▍   | 237005/371472 [7:49:42<11:40:15,  3.20it/s]
 64%|██████▍   | 237006/371472 [7:49:42<11:06:16,  3.36it/s]
 64%|██████▍   | 237007/371472 [7:49:42<10:49:26,  3.45it/s]
 64%|██████▍   | 237008/371472 [7:49:43<10:26:14,  3.58it/s]
 64%|██████▍   | 237009/371472 [7:49:43<10:38:06,  3.51it/s]
 64%|██████▍   | 237010/371472 [7:49:43<10:26:59,  3.57it/s]
 64%|██████▍   | 237011/371472 [7:49:44<10:33:20,  3.54it/s]
 64%|██████▍   | 237012/371472 [7:49:44<10:16:02,  3.64it/s]
 64%|██████▍   | 237013/371472 [7:49:44<10:22:08,  3.60it/s]
 64%|██████▍   | 237014/371472 [7:49:44<9:58:27,  3.74it/s] 
 64%|██████▍   | 237015/371472 [7:49:45<9:45:26,  3.83it/s]
 64%|██████▍   | 237016/371472 [7:49:45<10:36:44,  3.52it/s]
 64%|██████▍   | 237017/371472 [7:49:45<10:28:13,  3.57it/s]
 64%|██████▍   | 237018/371472 [7:49:45<10:14:38,  3.65it/s]
 64%|██████▍   | 237019/371472 [7:49:46<10:07:36,  3.69it/s]
 64%|██████▍   | 237020/371472 [7:49:46<10:18:36,  3.62it/s]
                                                            
{'loss': 2.8273, 'learning_rate': 4.25924928354414e-07, 'epoch': 10.21}
+
 64%|██████▍   | 237020/371472 [7:49:46<10:18:36,  3.62it/s]
 64%|██████▍   | 237021/371472 [7:49:46<10:02:19,  3.72it/s]
 64%|██████▍   | 237022/371472 [7:49:47<10:15:09,  3.64it/s]
 64%|██████▍   | 237023/371472 [7:49:47<10:11:17,  3.67it/s]
 64%|██████▍   | 237024/371472 [7:49:47<11:26:43,  3.26it/s]
 64%|██████▍   | 237025/371472 [7:49:47<10:51:29,  3.44it/s]
 64%|██████▍   | 237026/371472 [7:49:48<11:18:53,  3.30it/s]
 64%|██████▍   | 237027/371472 [7:49:48<10:59:23,  3.40it/s]
 64%|██████▍   | 237028/371472 [7:49:48<11:55:30,  3.13it/s]
 64%|██████▍   | 237029/371472 [7:49:49<11:22:23,  3.28it/s]
 64%|██████▍   | 237030/371472 [7:49:49<10:58:23,  3.40it/s]
 64%|██████▍   | 237031/371472 [7:49:49<11:29:46,  3.25it/s]
 64%|██████▍   | 237032/371472 [7:49:50<11:10:49,  3.34it/s]
 64%|██████▍   | 237033/371472 [7:49:50<11:45:17,  3.18it/s]
 64%|██████▍   | 237034/371472 [7:49:50<11:08:15,  3.35it/s]
 64%|██████▍   | 237035/371472 [7:49:50<10:40:53,  3.50it/s]
 64%|██████▍   | 237036/371472 [7:49:51<10:33:07,  3.54it/s]
 64%|██████▍   | 237037/371472 [7:49:51<10:15:09,  3.64it/s]
 64%|██████▍   | 237038/371472 [7:49:51<10:10:01,  3.67it/s]
 64%|██████▍   | 237039/371472 [7:49:52<9:57:18,  3.75it/s] 
 64%|██████▍   | 237040/371472 [7:49:52<9:51:16,  3.79it/s]
                                                           
{'loss': 2.8301, 'learning_rate': 4.258764463789351e-07, 'epoch': 10.21}
+
 64%|██████▍   | 237040/371472 [7:49:52<9:51:16,  3.79it/s]
 64%|██████▍   | 237041/371472 [7:49:52<9:44:38,  3.83it/s]
 64%|██████▍   | 237042/371472 [7:49:52<9:49:58,  3.80it/s]
 64%|██████▍   | 237043/371472 [7:49:53<9:46:09,  3.82it/s]
 64%|██████▍   | 237044/371472 [7:49:53<9:54:15,  3.77it/s]
 64%|██████▍   | 237045/371472 [7:49:53<10:36:47,  3.52it/s]
 64%|██████▍   | 237046/371472 [7:49:53<10:12:20,  3.66it/s]
 64%|██████▍   | 237047/371472 [7:49:54<10:28:30,  3.56it/s]
 64%|██████▍   | 237048/371472 [7:49:54<10:31:21,  3.55it/s]
 64%|██████▍   | 237049/371472 [7:49:54<10:25:30,  3.58it/s]
 64%|██████▍   | 237050/371472 [7:49:55<10:31:01,  3.55it/s]
 64%|██████▍   | 237051/371472 [7:49:55<10:40:47,  3.50it/s]
 64%|██████▍   | 237052/371472 [7:49:55<10:39:59,  3.50it/s]
 64%|██████▍   | 237053/371472 [7:49:55<11:16:48,  3.31it/s]
 64%|██████▍   | 237054/371472 [7:49:56<11:03:08,  3.38it/s]
 64%|██████▍   | 237055/371472 [7:49:56<11:42:30,  3.19it/s]
 64%|██████▍   | 237056/371472 [7:49:56<11:56:10,  3.13it/s]
 64%|██████▍   | 237057/371472 [7:49:57<12:11:17,  3.06it/s]
 64%|██████▍   | 237058/371472 [7:49:57<11:42:18,  3.19it/s]
 64%|██████▍   | 237059/371472 [7:49:57<11:05:06,  3.37it/s]
 64%|██████▍   | 237060/371472 [7:49:58<10:52:27,  3.43it/s]
                                                            
{'loss': 3.0289, 'learning_rate': 4.2582796440345627e-07, 'epoch': 10.21}
+
 64%|██████▍   | 237060/371472 [7:49:58<10:52:27,  3.43it/s]
 64%|██████▍   | 237061/371472 [7:49:58<10:26:08,  3.58it/s]
 64%|██████▍   | 237062/371472 [7:49:58<10:26:32,  3.58it/s]
 64%|██████▍   | 237063/371472 [7:49:58<10:16:26,  3.63it/s]
 64%|██████▍   | 237064/371472 [7:49:59<10:38:54,  3.51it/s]
 64%|██████▍   | 237065/371472 [7:49:59<10:42:22,  3.49it/s]
 64%|██████▍   | 237066/371472 [7:49:59<11:11:25,  3.34it/s]
 64%|██████▍   | 237067/371472 [7:50:00<11:06:42,  3.36it/s]
 64%|██████▍   | 237068/371472 [7:50:00<10:48:24,  3.45it/s]
 64%|██████▍   | 237069/371472 [7:50:00<11:25:52,  3.27it/s]
 64%|██████▍   | 237070/371472 [7:50:01<11:16:34,  3.31it/s]
 64%|██████▍   | 237071/371472 [7:50:01<10:59:20,  3.40it/s]
 64%|██████▍   | 237072/371472 [7:50:01<11:02:45,  3.38it/s]
 64%|██████▍   | 237073/371472 [7:50:01<10:51:21,  3.44it/s]
 64%|██████▍   | 237074/371472 [7:50:02<10:41:47,  3.49it/s]
 64%|██████▍   | 237075/371472 [7:50:02<10:54:13,  3.42it/s]
 64%|██████▍   | 237076/371472 [7:50:02<10:54:46,  3.42it/s]
 64%|██████▍   | 237077/371472 [7:50:03<10:33:45,  3.53it/s]
 64%|██████▍   | 237078/371472 [7:50:03<10:28:33,  3.56it/s]
 64%|██████▍   | 237079/371472 [7:50:03<10:54:14,  3.42it/s]
 64%|██████▍   | 237080/371472 [7:50:03<10:33:36,  3.54it/s]
                                                            
{'loss': 2.8045, 'learning_rate': 4.257794824279773e-07, 'epoch': 10.21}
+
 64%|███��██▍   | 237080/371472 [7:50:03<10:33:36,  3.54it/s]
 64%|██████▍   | 237081/371472 [7:50:04<10:12:32,  3.66it/s]
 64%|██████▍   | 237082/371472 [7:50:04<10:08:31,  3.68it/s]
 64%|██████▍   | 237083/371472 [7:50:04<10:05:31,  3.70it/s]
 64%|██████▍   | 237084/371472 [7:50:04<10:03:00,  3.71it/s]
 64%|██████▍   | 237085/371472 [7:50:05<10:41:27,  3.49it/s]
 64%|██████▍   | 237086/371472 [7:50:05<10:39:53,  3.50it/s]
 64%|██████▍   | 237087/371472 [7:50:05<10:34:41,  3.53it/s]
 64%|██████▍   | 237088/371472 [7:50:06<10:10:31,  3.67it/s]
 64%|██████▍   | 237089/371472 [7:50:06<10:01:47,  3.72it/s]
 64%|██████▍   | 237090/371472 [7:50:06<9:57:07,  3.75it/s] 
 64%|██████▍   | 237091/371472 [7:50:06<10:30:51,  3.55it/s]
 64%|██████▍   | 237092/371472 [7:50:07<11:08:06,  3.35it/s]
 64%|██████▍   | 237093/371472 [7:50:07<10:56:45,  3.41it/s]
 64%|██████▍   | 237094/371472 [7:50:07<10:32:11,  3.54it/s]
 64%|██████▍   | 237095/371472 [7:50:08<10:22:10,  3.60it/s]
 64%|██████▍   | 237096/371472 [7:50:08<10:41:15,  3.49it/s]
 64%|██████▍   | 237097/371472 [7:50:08<10:39:22,  3.50it/s]
 64%|██████▍   | 237098/371472 [7:50:08<10:36:40,  3.52it/s]
 64%|██████▍   | 237099/371472 [7:50:09<10:57:24,  3.41it/s]
 64%|██████▍   | 237100/371472 [7:50:09<10:33:35,  3.53it/s]
                                                            
{'loss': 2.776, 'learning_rate': 4.257310004524985e-07, 'epoch': 10.21}
+
 64%|██████▍   | 237100/371472 [7:50:09<10:33:35,  3.53it/s]
 64%|██████▍   | 237101/371472 [7:50:09<11:20:21,  3.29it/s]
 64%|██████▍   | 237102/371472 [7:50:10<11:15:15,  3.32it/s]
 64%|██████▍   | 237103/371472 [7:50:10<10:54:33,  3.42it/s]
 64%|██████▍   | 237104/371472 [7:50:10<11:29:48,  3.25it/s]
 64%|██████▍   | 237105/371472 [7:50:11<11:09:22,  3.35it/s]
 64%|██████▍   | 237106/371472 [7:50:11<10:56:55,  3.41it/s]
 64%|██████▍   | 237107/371472 [7:50:11<10:51:48,  3.44it/s]
 64%|██████▍   | 237108/371472 [7:50:11<10:57:33,  3.41it/s]
 64%|██████▍   | 237109/371472 [7:50:12<10:55:23,  3.42it/s]
 64%|██████▍   | 237110/371472 [7:50:12<11:04:26,  3.37it/s]
 64%|██████▍   | 237111/371472 [7:50:12<11:06:22,  3.36it/s]
 64%|██████▍   | 237112/371472 [7:50:13<11:04:32,  3.37it/s]
 64%|██████▍   | 237113/371472 [7:50:13<11:00:01,  3.39it/s]
 64%|██████▍   | 237114/371472 [7:50:13<10:43:33,  3.48it/s]
 64%|██████▍   | 237115/371472 [7:50:13<10:50:01,  3.44it/s]
 64%|██████▍   | 237116/371472 [7:50:14<11:05:39,  3.36it/s]
 64%|██████▍   | 237117/371472 [7:50:14<11:22:41,  3.28it/s]
 64%|██████▍   | 237118/371472 [7:50:14<10:47:31,  3.46it/s]
 64%|██████▍   | 237119/371472 [7:50:15<10:27:00,  3.57it/s]
 64%|██████▍   | 237120/371472 [7:50:15<10:39:50,  3.50it/s]
                                                            
{'loss': 2.699, 'learning_rate': 4.2568251847701953e-07, 'epoch': 10.21}
+
 64%|██████▍   | 237120/371472 [7:50:15<10:39:50,  3.50it/s]
 64%|██████▍   | 237121/371472 [7:50:15<10:32:03,  3.54it/s]
 64%|██████▍   | 237122/371472 [7:50:15<10:54:34,  3.42it/s]
 64%|██████▍   | 237123/371472 [7:50:16<10:26:06,  3.58it/s]
 64%|██████▍   | 237124/371472 [7:50:16<10:17:27,  3.63it/s]
 64%|██████▍   | 237125/371472 [7:50:16<10:03:54,  3.71it/s]
 64%|██████▍   | 237126/371472 [7:50:16<9:49:28,  3.80it/s] 
 64%|██████▍   | 237127/371472 [7:50:17<10:05:19,  3.70it/s]
 64%|██████▍   | 237128/371472 [7:50:17<10:41:57,  3.49it/s]
 64%|██████▍   | 237129/371472 [7:50:17<10:25:21,  3.58it/s]
 64%|██████▍   | 237130/371472 [7:50:18<11:15:47,  3.31it/s]
 64%|██████▍   | 237131/371472 [7:50:18<11:53:20,  3.14it/s]
 64%|██████▍   | 237132/371472 [7:50:18<11:52:42,  3.14it/s]
 64%|██████▍   | 237133/371472 [7:50:19<12:05:49,  3.08it/s]
 64%|██████▍   | 237134/371472 [7:50:19<11:17:06,  3.31it/s]
 64%|██████▍   | 237135/371472 [7:50:19<11:43:48,  3.18it/s]
 64%|██████▍   | 237136/371472 [7:50:20<11:09:04,  3.35it/s]
 64%|██████▍   | 237137/371472 [7:50:20<10:51:14,  3.44it/s]
 64%|██████▍   | 237138/371472 [7:50:20<11:14:40,  3.32it/s]
 64%|██████▍   | 237139/371472 [7:50:20<10:38:42,  3.51it/s]
 64%|██████▍   | 237140/371472 [7:50:21<10:17:07,  3.63it/s]
                                                            
{'loss': 2.9159, 'learning_rate': 4.2563403650154066e-07, 'epoch': 10.21}
+
 64%|██████▍   | 237140/371472 [7:50:21<10:17:07,  3.63it/s]
 64%|██████▍   | 237141/371472 [7:50:21<10:08:03,  3.68it/s]
 64%|██████▍   | 237142/371472 [7:50:21<9:58:47,  3.74it/s] 
 64%|██████▍   | 237143/371472 [7:50:21<9:47:19,  3.81it/s]
 64%|██████▍   | 237144/371472 [7:50:22<9:34:28,  3.90it/s]
 64%|██████▍   | 237145/371472 [7:50:22<9:49:11,  3.80it/s]
 64%|██████▍   | 237146/371472 [7:50:22<9:55:17,  3.76it/s]
 64%|██████▍   | 237147/371472 [7:50:23<11:22:48,  3.28it/s]
 64%|██████▍   | 237148/371472 [7:50:23<11:01:35,  3.38it/s]
 64%|██████▍   | 237149/371472 [7:50:23<11:05:34,  3.36it/s]
 64%|██████▍   | 237150/371472 [7:50:23<10:40:18,  3.50it/s]
 64%|██████▍   | 237151/371472 [7:50:24<11:22:20,  3.28it/s]
 64%|██████▍   | 237152/371472 [7:50:24<11:09:48,  3.34it/s]
 64%|██████▍   | 237153/371472 [7:50:24<10:44:55,  3.47it/s]
 64%|██████▍   | 237154/371472 [7:50:25<10:38:12,  3.51it/s]
 64%|██████▍   | 237155/371472 [7:50:25<10:20:21,  3.61it/s]
 64%|██████▍   | 237156/371472 [7:50:25<10:39:38,  3.50it/s]
 64%|██████▍   | 237157/371472 [7:50:26<10:34:43,  3.53it/s]
 64%|██████▍   | 237158/371472 [7:50:26<10:04:33,  3.70it/s]
 64%|██████▍   | 237159/371472 [7:50:26<10:03:21,  3.71it/s]
 64%|██████▍   | 237160/371472 [7:50:26<10:24:07,  3.59it/s]
                                                            
{'loss': 2.8493, 'learning_rate': 4.2558555452606173e-07, 'epoch': 10.21}
+
 64%|██████▍   | 237160/371472 [7:50:26<10:24:07,  3.59it/s]
 64%|██████▍   | 237161/371472 [7:50:27<10:08:18,  3.68it/s]
 64%|██████▍   | 237162/371472 [7:50:27<11:30:35,  3.24it/s]
 64%|██████▍   | 237163/371472 [7:50:27<11:21:26,  3.28it/s]
 64%|██████▍   | 237164/371472 [7:50:28<11:34:57,  3.22it/s]
 64%|██████▍   | 237165/371472 [7:50:28<11:08:32,  3.35it/s]
 64%|██████▍   | 237166/371472 [7:50:28<11:02:27,  3.38it/s]
 64%|██████▍   | 237167/371472 [7:50:29<11:54:07,  3.13it/s]
 64%|██████▍   | 237168/371472 [7:50:29<11:40:20,  3.20it/s]
 64%|██████▍   | 237169/371472 [7:50:29<11:10:46,  3.34it/s]
 64%|██████▍   | 237170/371472 [7:50:29<10:53:53,  3.42it/s]
 64%|██████▍   | 237171/371472 [7:50:30<10:12:39,  3.65it/s]
 64%|██████▍   | 237172/371472 [7:50:30<10:00:48,  3.73it/s]
 64%|██████▍   | 237173/371472 [7:50:30<10:15:07,  3.64it/s]
 64%|██████▍   | 237174/371472 [7:50:30<10:09:15,  3.67it/s]
 64%|██████▍   | 237175/371472 [7:50:31<10:06:20,  3.69it/s]
 64%|██████▍   | 237176/371472 [7:50:31<9:45:25,  3.82it/s] 
 64%|██████▍   | 237177/371472 [7:50:31<9:52:57,  3.77it/s]
 64%|██████▍   | 237178/371472 [7:50:31<10:12:55,  3.65it/s]
 64%|██████▍   | 237179/371472 [7:50:32<11:25:36,  3.26it/s]
 64%|██████▍   | 237180/371472 [7:50:32<10:54:53,  3.42it/s]
                                                            
{'loss': 2.9661, 'learning_rate': 4.255370725505829e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237180/371472 [7:50:32<10:54:53,  3.42it/s]
 64%|██████▍   | 237181/371472 [7:50:32<10:47:24,  3.46it/s]
 64%|██████▍   | 237182/371472 [7:50:33<10:25:10,  3.58it/s]
 64%|██████▍   | 237183/371472 [7:50:33<10:11:30,  3.66it/s]
 64%|██████▍   | 237184/371472 [7:50:33<10:08:49,  3.68it/s]
 64%|██████▍   | 237185/371472 [7:50:33<10:28:12,  3.56it/s]
 64%|██████▍   | 237186/371472 [7:50:34<10:12:03,  3.66it/s]
 64%|██████▍   | 237187/371472 [7:50:34<10:21:04,  3.60it/s]
 64%|██████▍   | 237188/371472 [7:50:34<10:22:03,  3.60it/s]
 64%|██████▍   | 237189/371472 [7:50:35<10:35:40,  3.52it/s]
 64%|██████▍   | 237190/371472 [7:50:35<11:02:16,  3.38it/s]
 64%|██████▍   | 237191/371472 [7:50:35<10:29:48,  3.55it/s]
 64%|██████▍   | 237192/371472 [7:50:35<10:39:41,  3.50it/s]
 64%|██████▍   | 237193/371472 [7:50:36<10:34:53,  3.53it/s]
 64%|██████▍   | 237194/371472 [7:50:36<10:21:47,  3.60it/s]
 64%|██████▍   | 237195/371472 [7:50:36<11:02:26,  3.38it/s]
 64%|██████▍   | 237196/371472 [7:50:37<10:29:49,  3.55it/s]
 64%|██████▍   | 237197/371472 [7:50:37<10:36:45,  3.51it/s]
 64%|██████▍   | 237198/371472 [7:50:37<10:21:58,  3.60it/s]
 64%|██████▍   | 237199/371472 [7:50:37<10:11:59,  3.66it/s]
 64%|██████▍   | 237200/371472 [7:50:38<10:41:45,  3.49it/s]
                                                            
{'loss': 2.7932, 'learning_rate': 4.254885905751039e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237200/371472 [7:50:38<10:41:45,  3.49it/s]
 64%|██████▍   | 237201/371472 [7:50:38<10:30:57,  3.55it/s]
 64%|██████▍   | 237202/371472 [7:50:38<10:31:54,  3.54it/s]
 64%|██████▍   | 237203/371472 [7:50:39<10:10:17,  3.67it/s]
 64%|██████▍   | 237204/371472 [7:50:39<10:17:16,  3.63it/s]
 64%|██████▍   | 237205/371472 [7:50:39<10:35:19,  3.52it/s]
 64%|██████▍   | 237206/371472 [7:50:39<10:22:20,  3.60it/s]
 64%|██████▍   | 237207/371472 [7:50:40<10:13:46,  3.65it/s]
 64%|██████▍   | 237208/371472 [7:50:40<11:09:17,  3.34it/s]
 64%|██████▍   | 237209/371472 [7:50:40<10:55:02,  3.42it/s]
 64%|██████▍   | 237210/371472 [7:50:41<11:48:43,  3.16it/s]
 64%|██████▍   | 237211/371472 [7:50:41<11:05:28,  3.36it/s]
 64%|██████▍   | 237212/371472 [7:50:41<11:08:10,  3.35it/s]
 64%|██████▍   | 237213/371472 [7:50:41<10:49:50,  3.44it/s]
 64%|██████▍   | 237214/371472 [7:50:42<10:24:52,  3.58it/s]
 64%|██████▍   | 237215/371472 [7:50:42<10:29:06,  3.56it/s]
 64%|██████▍   | 237216/371472 [7:50:42<10:39:59,  3.50it/s]
 64%|██████▍   | 237217/371472 [7:50:43<10:47:47,  3.45it/s]
 64%|██████▍   | 237218/371472 [7:50:43<10:38:59,  3.50it/s]
 64%|██████▍   | 237219/371472 [7:50:43<10:16:12,  3.63it/s]
 64%|██████▍   | 237220/371472 [7:50:43<9:55:22,  3.76it/s] 
                                                           
{'loss': 2.9453, 'learning_rate': 4.254401085996251e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237220/371472 [7:50:43<9:55:22,  3.76it/s]
 64%|██████▍   | 237221/371472 [7:50:44<10:42:02,  3.48it/s]
 64%|██████▍   | 237222/371472 [7:50:44<10:23:36,  3.59it/s]
 64%|██████▍   | 237223/371472 [7:50:44<10:05:54,  3.69it/s]
 64%|██████▍   | 237224/371472 [7:50:45<10:10:25,  3.67it/s]
 64%|██████▍   | 237225/371472 [7:50:45<10:16:20,  3.63it/s]
 64%|██████▍   | 237226/371472 [7:50:45<10:41:07,  3.49it/s]
 64%|██████▍   | 237227/371472 [7:50:45<11:00:50,  3.39it/s]
 64%|██████▍   | 237228/371472 [7:50:46<10:46:40,  3.46it/s]
 64%|██████▍   | 237229/371472 [7:50:46<10:23:31,  3.59it/s]
 64%|██████▍   | 237230/371472 [7:50:46<10:06:05,  3.69it/s]
 64%|██████▍   | 237231/371472 [7:50:46<10:15:03,  3.64it/s]
 64%|██████▍   | 237232/371472 [7:50:47<10:16:00,  3.63it/s]
 64%|██████▍   | 237233/371472 [7:50:47<10:20:58,  3.60it/s]
 64%|██████▍   | 237234/371472 [7:50:47<10:33:02,  3.53it/s]
 64%|██████▍   | 237235/371472 [7:50:48<10:49:10,  3.45it/s]
 64%|██████▍   | 237236/371472 [7:50:48<10:24:37,  3.58it/s]
 64%|██████▍   | 237237/371472 [7:50:48<10:35:30,  3.52it/s]
 64%|██████▍   | 237238/371472 [7:50:48<10:36:35,  3.51it/s]
 64%|██████▍   | 237239/371472 [7:50:49<10:52:17,  3.43it/s]
 64%|██████▍   | 237240/371472 [7:50:49<10:55:32,  3.41it/s]
                                                            
{'loss': 2.9602, 'learning_rate': 4.253916266241462e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237240/371472 [7:50:49<10:55:32,  3.41it/s]
 64%|██████▍   | 237241/371472 [7:50:49<10:39:03,  3.50it/s]
 64%|██████▍   | 237242/371472 [7:50:50<11:17:41,  3.30it/s]
 64%|██████▍   | 237243/371472 [7:50:50<11:07:49,  3.35it/s]
 64%|██████▍   | 237244/371472 [7:50:50<10:46:38,  3.46it/s]
 64%|██████▍   | 237245/371472 [7:50:51<10:37:31,  3.51it/s]
 64%|██████▍   | 237246/371472 [7:50:51<10:19:38,  3.61it/s]
 64%|██████▍   | 237247/371472 [7:50:51<10:26:49,  3.57it/s]
 64%|██████▍   | 237248/371472 [7:50:51<10:06:17,  3.69it/s]
 64%|██████▍   | 237249/371472 [7:50:52<10:25:23,  3.58it/s]
 64%|██████▍   | 237250/371472 [7:50:52<10:26:29,  3.57it/s]
 64%|██████▍   | 237251/371472 [7:50:52<10:10:38,  3.66it/s]
 64%|██████▍   | 237252/371472 [7:50:52<9:57:13,  3.75it/s] 
 64%|██████▍   | 237253/371472 [7:50:53<9:50:59,  3.79it/s]
 64%|██████▍   | 237254/371472 [7:50:53<9:33:45,  3.90it/s]
 64%|██████▍   | 237255/371472 [7:50:53<9:40:38,  3.85it/s]
 64%|██████▍   | 237256/371472 [7:50:53<9:56:44,  3.75it/s]
 64%|██████▍   | 237257/371472 [7:50:54<9:58:20,  3.74it/s]
 64%|██████▍   | 237258/371472 [7:50:54<9:50:49,  3.79it/s]
 64%|██████▍   | 237259/371472 [7:50:54<9:59:05,  3.73it/s]
 64%|██████▍   | 237260/371472 [7:50:55<10:39:58,  3.50it/s]
                                                            
{'loss': 2.7128, 'learning_rate': 4.253431446486672e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237260/371472 [7:50:55<10:39:58,  3.50it/s]
 64%|██████▍   | 237261/371472 [7:50:55<10:12:34,  3.65it/s]
 64%|██████▍   | 237262/371472 [7:50:55<10:41:48,  3.49it/s]
 64%|██████▍   | 237263/371472 [7:50:55<10:33:07,  3.53it/s]
 64%|██████▍   | 237264/371472 [7:50:56<11:58:09,  3.11it/s]
 64%|██████▍   | 237265/371472 [7:50:56<11:22:53,  3.28it/s]
 64%|██████▍   | 237266/371472 [7:50:56<11:39:51,  3.20it/s]
 64%|██████▍   | 237267/371472 [7:50:57<12:22:44,  3.01it/s]
 64%|██████▍   | 237268/371472 [7:50:57<11:52:29,  3.14it/s]
 64%|██████▍   | 237269/371472 [7:50:57<11:33:54,  3.22it/s]
 64%|██████▍   | 237270/371472 [7:50:58<10:57:44,  3.40it/s]
 64%|██████▍   | 237271/371472 [7:50:58<11:34:20,  3.22it/s]
 64%|██████▍   | 237272/371472 [7:50:58<11:16:26,  3.31it/s]
 64%|██████▍   | 237273/371472 [7:50:59<10:58:45,  3.40it/s]
 64%|██████▍   | 237274/371472 [7:50:59<11:09:25,  3.34it/s]
 64%|██████▍   | 237275/371472 [7:50:59<11:16:59,  3.30it/s]
 64%|██████▍   | 237276/371472 [7:50:59<11:02:10,  3.38it/s]
 64%|██████▍   | 237277/371472 [7:51:00<10:41:38,  3.49it/s]
 64%|██████▍   | 237278/371472 [7:51:00<10:43:25,  3.48it/s]
 64%|██████▍   | 237279/371472 [7:51:00<10:16:25,  3.63it/s]
 64%|██████▍   | 237280/371472 [7:51:01<10:16:26,  3.63it/s]
                                                            
{'loss': 2.7634, 'learning_rate': 4.2529466267318837e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237280/371472 [7:51:01<10:16:26,  3.63it/s]
 64%|██████▍   | 237281/371472 [7:51:01<10:30:02,  3.55it/s]
 64%|██████▍   | 237282/371472 [7:51:01<10:21:32,  3.60it/s]
 64%|██████▍   | 237283/371472 [7:51:01<10:11:47,  3.66it/s]
 64%|██████▍   | 237284/371472 [7:51:02<10:00:46,  3.72it/s]
 64%|██████▍   | 237285/371472 [7:51:02<10:14:13,  3.64it/s]
 64%|██████▍   | 237286/371472 [7:51:02<9:47:31,  3.81it/s] 
 64%|██████▍   | 237287/371472 [7:51:02<9:46:02,  3.82it/s]
 64%|██████▍   | 237288/371472 [7:51:03<11:07:03,  3.35it/s]
 64%|██████▍   | 237289/371472 [7:51:03<11:21:45,  3.28it/s]
 64%|██████▍   | 237290/371472 [7:51:03<10:52:25,  3.43it/s]
 64%|██████▍   | 237291/371472 [7:51:04<10:48:42,  3.45it/s]
 64%|██████▍   | 237292/371472 [7:51:04<10:53:19,  3.42it/s]
 64%|██████▍   | 237293/371472 [7:51:04<10:55:57,  3.41it/s]
 64%|██████▍   | 237294/371472 [7:51:05<11:23:38,  3.27it/s]
 64%|██████▍   | 237295/371472 [7:51:05<11:31:53,  3.23it/s]
 64%|██████▍   | 237296/371472 [7:51:05<10:54:27,  3.42it/s]
 64%|██████▍   | 237297/371472 [7:51:05<10:59:58,  3.39it/s]
 64%|██████▍   | 237298/371472 [7:51:06<10:48:13,  3.45it/s]
 64%|██████▍   | 237299/371472 [7:51:06<10:29:01,  3.56it/s]
 64%|██████▍   | 237300/371472 [7:51:06<11:09:06,  3.34it/s]
                                                            
{'loss': 2.8303, 'learning_rate': 4.2524618069770944e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237300/371472 [7:51:06<11:09:06,  3.34it/s]
 64%|██████▍   | 237301/371472 [7:51:07<11:28:48,  3.25it/s]
 64%|██████▍   | 237302/371472 [7:51:07<11:23:15,  3.27it/s]
 64%|██████▍   | 237303/371472 [7:51:07<10:50:56,  3.44it/s]
 64%|██████▍   | 237304/371472 [7:51:07<10:30:01,  3.55it/s]
 64%|██████▍   | 237305/371472 [7:51:08<10:59:33,  3.39it/s]
 64%|██████▍   | 237306/371472 [7:51:08<10:35:07,  3.52it/s]
 64%|██████▍   | 237307/371472 [7:51:08<10:08:01,  3.68it/s]
 64%|██████▍   | 237308/371472 [7:51:09<9:52:38,  3.77it/s] 
 64%|██████▍   | 237309/371472 [7:51:09<10:11:24,  3.66it/s]
 64%|██████▍   | 237310/371472 [7:51:09<9:57:57,  3.74it/s] 
 64%|██████▍   | 237311/371472 [7:51:09<10:08:30,  3.67it/s]
 64%|██████▍   | 237312/371472 [7:51:10<9:56:10,  3.75it/s] 
 64%|██████▍   | 237313/371472 [7:51:10<9:55:27,  3.76it/s]
 64%|██████▍   | 237314/371472 [7:51:10<9:42:31,  3.84it/s]
 64%|██████▍   | 237315/371472 [7:51:10<9:41:45,  3.84it/s]
 64%|██████▍   | 237316/371472 [7:51:11<9:32:58,  3.90it/s]
 64%|██████▍   | 237317/371472 [7:51:11<9:31:54,  3.91it/s]
 64%|██████▍   | 237318/371472 [7:51:11<9:49:32,  3.79it/s]
 64%|██████▍   | 237319/371472 [7:51:11<9:36:45,  3.88it/s]
 64%|██████▍   | 237320/371472 [7:51:12<10:28:53,  3.56it/s]
                                                            
{'loss': 2.8821, 'learning_rate': 4.2519769872223057e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237320/371472 [7:51:12<10:28:53,  3.56it/s]
 64%|██████▍   | 237321/371472 [7:51:12<10:18:37,  3.61it/s]
 64%|██████▍   | 237322/371472 [7:51:12<10:13:02,  3.65it/s]
 64%|██████▍   | 237323/371472 [7:51:13<9:55:50,  3.75it/s] 
 64%|██████▍   | 237324/371472 [7:51:13<9:44:25,  3.83it/s]
 64%|██████▍   | 237325/371472 [7:51:13<10:12:12,  3.65it/s]
 64%|██████▍   | 237326/371472 [7:51:13<9:57:57,  3.74it/s] 
 64%|██████▍   | 237327/371472 [7:51:14<10:15:56,  3.63it/s]
 64%|██████▍   | 237328/371472 [7:51:14<10:48:11,  3.45it/s]
 64%|██████▍   | 237329/371472 [7:51:14<10:16:08,  3.63it/s]
 64%|██████▍   | 237330/371472 [7:51:14<9:48:36,  3.80it/s] 
 64%|██████▍   | 237331/371472 [7:51:15<10:28:07,  3.56it/s]
 64%|██████▍   | 237332/371472 [7:51:15<10:58:37,  3.39it/s]
 64%|██████▍   | 237333/371472 [7:51:15<11:08:52,  3.34it/s]
 64%|██████▍   | 237334/371472 [7:51:16<11:07:57,  3.35it/s]
 64%|██████▍   | 237335/371472 [7:51:16<10:26:02,  3.57it/s]
 64%|██████▍   | 237336/371472 [7:51:16<11:04:52,  3.36it/s]
 64%|██████▍   | 237337/371472 [7:51:17<10:49:48,  3.44it/s]
 64%|██████▍   | 237338/371472 [7:51:17<10:52:09,  3.43it/s]
 64%|██████▍   | 237339/371472 [7:51:17<11:31:42,  3.23it/s]
 64%|██████▍   | 237340/371472 [7:51:17<10:51:38,  3.43it/s]
                                                            
{'loss': 2.7955, 'learning_rate': 4.2514921674675164e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237340/371472 [7:51:17<10:51:38,  3.43it/s]
 64%|██████▍   | 237341/371472 [7:51:18<10:33:34,  3.53it/s]
 64%|██████▍   | 237342/371472 [7:51:18<10:30:06,  3.55it/s]
 64%|██████▍   | 237343/371472 [7:51:18<10:49:39,  3.44it/s]
 64%|██████▍   | 237344/371472 [7:51:19<10:32:29,  3.53it/s]
 64%|██████▍   | 237345/371472 [7:51:19<11:03:47,  3.37it/s]
 64%|██████▍   | 237346/371472 [7:51:19<10:24:26,  3.58it/s]
 64%|██████▍   | 237347/371472 [7:51:19<10:09:25,  3.67it/s]
 64%|██████▍   | 237348/371472 [7:51:20<10:28:38,  3.56it/s]
 64%|██████▍   | 237349/371472 [7:51:20<10:13:03,  3.65it/s]
 64%|██████▍   | 237350/371472 [7:51:20<10:14:31,  3.64it/s]
 64%|██████▍   | 237351/371472 [7:51:21<10:01:10,  3.72it/s]
 64%|██████▍   | 237352/371472 [7:51:21<10:11:02,  3.66it/s]
 64%|██████▍   | 237353/371472 [7:51:21<9:48:48,  3.80it/s] 
 64%|██████▍   | 237354/371472 [7:51:21<9:57:29,  3.74it/s]
 64%|██████▍   | 237355/371472 [7:51:22<9:43:50,  3.83it/s]
 64%|██████▍   | 237356/371472 [7:51:22<10:06:04,  3.69it/s]
 64%|██████▍   | 237357/371472 [7:51:22<10:00:16,  3.72it/s]
 64%|██████▍   | 237358/371472 [7:51:22<10:24:24,  3.58it/s]
 64%|██████▍   | 237359/371472 [7:51:23<10:11:24,  3.66it/s]
 64%|██████▍   | 237360/371472 [7:51:23<10:20:08,  3.60it/s]
                                                            
{'loss': 2.6379, 'learning_rate': 4.251007347712728e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237360/371472 [7:51:23<10:20:08,  3.60it/s]
 64%|██████▍   | 237361/371472 [7:51:23<10:29:17,  3.55it/s]
 64%|██████▍   | 237362/371472 [7:51:24<10:10:43,  3.66it/s]
 64%|██████▍   | 237363/371472 [7:51:24<10:10:50,  3.66it/s]
 64%|██████▍   | 237364/371472 [7:51:24<9:59:43,  3.73it/s] 
 64%|██████▍   | 237365/371472 [7:51:24<11:09:35,  3.34it/s]
 64%|██████▍   | 237366/371472 [7:51:25<11:35:02,  3.22it/s]
 64%|██████▍   | 237367/371472 [7:51:25<12:18:36,  3.03it/s]
 64%|██████▍   | 237368/371472 [7:51:25<12:04:11,  3.09it/s]
 64%|██████▍   | 237369/371472 [7:51:26<11:34:03,  3.22it/s]
 64%|██████▍   | 237370/371472 [7:51:26<11:11:03,  3.33it/s]
 64%|██████▍   | 237371/371472 [7:51:26<11:11:19,  3.33it/s]
 64%|██████▍   | 237372/371472 [7:51:27<11:15:04,  3.31it/s]
 64%|██████▍   | 237373/371472 [7:51:27<11:26:11,  3.26it/s]
 64%|██████▍   | 237374/371472 [7:51:27<11:24:33,  3.26it/s]
 64%|██████▍   | 237375/371472 [7:51:28<12:07:08,  3.07it/s]
 64%|██████▍   | 237376/371472 [7:51:28<11:33:34,  3.22it/s]
 64%|██████▍   | 237377/371472 [7:51:28<10:57:53,  3.40it/s]
 64%|██████▍   | 237378/371472 [7:51:28<10:27:46,  3.56it/s]
 64%|██████▍   | 237379/371472 [7:51:29<10:17:18,  3.62it/s]
 64%|██████▍   | 237380/371472 [7:51:29<10:18:00,  3.62it/s]
                                                            
{'loss': 2.9257, 'learning_rate': 4.250522527957939e-07, 'epoch': 10.22}
+
 64%|██████▍   | 237380/371472 [7:51:29<10:18:00,  3.62it/s]
 64%|██████▍   | 237381/371472 [7:51:29<10:09:51,  3.66it/s]
 64%|██████▍   | 237382/371472 [7:51:29<10:29:27,  3.55it/s]
 64%|██████▍   | 237383/371472 [7:51:30<10:24:25,  3.58it/s]
 64%|██████▍   | 237384/371472 [7:51:30<10:07:16,  3.68it/s]
 64%|██████▍   | 237385/371472 [7:51:30<10:40:16,  3.49it/s]
 64%|██████▍   | 237386/371472 [7:51:31<10:37:49,  3.50it/s]
 64%|██████▍   | 237387/371472 [7:51:31<10:21:58,  3.59it/s]
 64%|██████▍   | 237388/371472 [7:51:31<10:38:03,  3.50it/s]
 64%|██████▍   | 237389/371472 [7:51:31<10:13:47,  3.64it/s]
 64%|██████▍   | 237390/371472 [7:51:32<10:46:51,  3.45it/s]
 64%|██████▍   | 237391/371472 [7:51:32<10:44:29,  3.47it/s]
 64%|██████▍   | 237392/371472 [7:51:32<10:20:51,  3.60it/s]
 64%|██████▍   | 237393/371472 [7:51:33<10:26:14,  3.57it/s]
 64%|██████▍   | 237394/371472 [7:51:33<10:16:54,  3.62it/s]
 64%|██████▍   | 237395/371472 [7:51:33<9:54:30,  3.76it/s] 
 64%|██████▍   | 237396/371472 [7:51:33<10:17:23,  3.62it/s]
 64%|██████▍   | 237397/371472 [7:51:34<10:33:45,  3.53it/s]
 64%|██████▍   | 237398/371472 [7:51:34<10:45:31,  3.46it/s]
 64%|██████▍   | 237399/371472 [7:51:34<10:18:13,  3.61it/s]
 64%|██████▍   | 237400/371472 [7:51:35<10:19:11,  3.61it/s]
                                                            
{'loss': 2.925, 'learning_rate': 4.25003770820315e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237400/371472 [7:51:35<10:19:11,  3.61it/s]
 64%|██████▍   | 237401/371472 [7:51:35<10:14:50,  3.63it/s]
 64%|██████▍   | 237402/371472 [7:51:35<10:16:12,  3.63it/s]
 64%|██████▍   | 237403/371472 [7:51:35<10:42:25,  3.48it/s]
 64%|██████▍   | 237404/371472 [7:51:36<10:22:30,  3.59it/s]
 64%|██████▍   | 237405/371472 [7:51:36<10:45:07,  3.46it/s]
 64%|██████▍   | 237406/371472 [7:51:36<10:26:30,  3.57it/s]
 64%|██████▍   | 237407/371472 [7:51:37<11:13:53,  3.32it/s]
 64%|██████▍   | 237408/371472 [7:51:37<11:16:05,  3.30it/s]
 64%|██████▍   | 237409/371472 [7:51:37<10:32:37,  3.53it/s]
 64%|██████▍   | 237410/371472 [7:51:38<14:11:40,  2.62it/s]
 64%|██████▍   | 237411/371472 [7:51:38<13:18:39,  2.80it/s]
 64%|██████▍   | 237412/371472 [7:51:38<13:15:45,  2.81it/s]
 64%|██████▍   | 237413/371472 [7:51:39<12:18:28,  3.03it/s]
 64%|██████▍   | 237414/371472 [7:51:39<11:37:15,  3.20it/s]
 64%|██████▍   | 237415/371472 [7:51:39<11:02:50,  3.37it/s]
 64%|██████▍   | 237416/371472 [7:51:39<10:21:39,  3.59it/s]
 64%|██████▍   | 237417/371472 [7:51:40<10:26:01,  3.57it/s]
 64%|██████▍   | 237418/371472 [7:51:40<10:31:27,  3.54it/s]
 64%|██████▍   | 237419/371472 [7:51:40<10:37:28,  3.50it/s]
 64%|██████▍   | 237420/371472 [7:51:41<10:26:56,  3.56it/s]
                                                            
{'loss': 2.8373, 'learning_rate': 4.249552888448361e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237420/371472 [7:51:41<10:26:56,  3.56it/s]
 64%|██████▍   | 237421/371472 [7:51:41<10:29:11,  3.55it/s]
 64%|██████▍   | 237422/371472 [7:51:41<10:14:18,  3.64it/s]
 64%|██████▍   | 237423/371472 [7:51:42<13:20:11,  2.79it/s]
 64%|██████▍   | 237424/371472 [7:51:42<12:10:25,  3.06it/s]
 64%|██████▍   | 237425/371472 [7:51:42<12:31:45,  2.97it/s]
 64%|██████▍   | 237426/371472 [7:51:43<11:53:04,  3.13it/s]
 64%|██████▍   | 237427/371472 [7:51:43<12:38:34,  2.95it/s]
 64%|██████▍   | 237428/371472 [7:51:43<12:00:22,  3.10it/s]
 64%|██████▍   | 237429/371472 [7:51:43<11:20:09,  3.28it/s]
 64%|██████▍   | 237430/371472 [7:51:44<11:43:52,  3.17it/s]
 64%|██████▍   | 237431/371472 [7:51:44<11:14:52,  3.31it/s]
 64%|██████▍   | 237432/371472 [7:51:44<11:15:38,  3.31it/s]
 64%|██████▍   | 237433/371472 [7:51:45<11:03:24,  3.37it/s]
 64%|██████▍   | 237434/371472 [7:51:45<10:50:40,  3.43it/s]
 64%|██████▍   | 237435/371472 [7:51:45<10:18:46,  3.61it/s]
 64%|██████▍   | 237436/371472 [7:51:45<10:43:38,  3.47it/s]
 64%|██████▍   | 237437/371472 [7:51:46<10:33:34,  3.53it/s]
 64%|██████▍   | 237438/371472 [7:51:46<10:38:04,  3.50it/s]
 64%|██████▍   | 237439/371472 [7:51:46<10:49:54,  3.44it/s]
 64%|██████▍   | 237440/371472 [7:51:47<10:33:13,  3.53it/s]
                                                            
{'loss': 2.7596, 'learning_rate': 4.2490680686935726e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237440/371472 [7:51:47<10:33:13,  3.53it/s]
 64%|██████▍   | 237441/371472 [7:51:47<10:56:38,  3.40it/s]
 64%|██████▍   | 237442/371472 [7:51:47<10:57:44,  3.40it/s]
 64%|██████▍   | 237443/371472 [7:51:48<10:49:11,  3.44it/s]
 64%|██████▍   | 237444/371472 [7:51:48<12:04:14,  3.08it/s]
 64%|██████▍   | 237445/371472 [7:51:48<11:37:18,  3.20it/s]
 64%|██████▍   | 237446/371472 [7:51:48<11:01:28,  3.38it/s]
 64%|██████▍   | 237447/371472 [7:51:49<11:41:05,  3.19it/s]
 64%|██████▍   | 237448/371472 [7:51:49<11:09:52,  3.33it/s]
 64%|██████▍   | 237449/371472 [7:51:49<11:10:43,  3.33it/s]
 64%|██████▍   | 237450/371472 [7:51:50<11:46:18,  3.16it/s]
 64%|██████▍   | 237451/371472 [7:51:50<11:36:20,  3.21it/s]
 64%|██████▍   | 237452/371472 [7:51:50<11:07:39,  3.35it/s]
 64%|██████▍   | 237453/371472 [7:51:51<11:41:47,  3.18it/s]
 64%|██████▍   | 237454/371472 [7:51:51<11:03:29,  3.37it/s]
 64%|██████▍   | 237455/371472 [7:51:51<10:37:23,  3.50it/s]
 64%|██████▍   | 237456/371472 [7:51:51<10:30:09,  3.54it/s]
 64%|██████▍   | 237457/371472 [7:51:52<10:21:08,  3.60it/s]
 64%|██████▍   | 237458/371472 [7:51:52<10:13:12,  3.64it/s]
 64%|██████▍   | 237459/371472 [7:51:52<10:02:56,  3.70it/s]
 64%|██████▍   | 237460/371472 [7:51:52<9:44:37,  3.82it/s] 
                                                           
{'loss': 2.7659, 'learning_rate': 4.248583248938783e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237460/371472 [7:51:52<9:44:37,  3.82it/s]
 64%|██████▍   | 237461/371472 [7:51:53<9:43:29,  3.83it/s]
 64%|██████▍   | 237462/371472 [7:51:53<10:00:25,  3.72it/s]
 64%|██████▍   | 237463/371472 [7:51:53<10:46:57,  3.45it/s]
 64%|██████▍   | 237464/371472 [7:51:54<10:33:35,  3.53it/s]
 64%|██████▍   | 237465/371472 [7:51:54<10:19:26,  3.61it/s]
 64%|██████▍   | 237466/371472 [7:51:54<10:19:24,  3.61it/s]
 64%|██████▍   | 237467/371472 [7:51:54<10:29:17,  3.55it/s]
 64%|██████▍   | 237468/371472 [7:51:55<10:25:47,  3.57it/s]
 64%|██████▍   | 237469/371472 [7:51:55<11:02:46,  3.37it/s]
 64%|██████▍   | 237470/371472 [7:51:55<10:48:39,  3.44it/s]
 64%|██████▍   | 237471/371472 [7:51:56<10:14:31,  3.63it/s]
 64%|██████▍   | 237472/371472 [7:51:56<10:31:14,  3.54it/s]
 64%|██████▍   | 237473/371472 [7:51:56<10:18:32,  3.61it/s]
 64%|██████▍   | 237474/371472 [7:51:56<10:06:17,  3.68it/s]
 64%|██████▍   | 237475/371472 [7:51:57<10:12:00,  3.65it/s]
 64%|██████▍   | 237476/371472 [7:51:57<10:15:12,  3.63it/s]
 64%|██████▍   | 237477/371472 [7:51:57<10:23:59,  3.58it/s]
 64%|██████▍   | 237478/371472 [7:51:58<10:12:50,  3.64it/s]
 64%|██████▍   | 237479/371472 [7:51:58<10:21:37,  3.59it/s]
 64%|██████▍   | 237480/371472 [7:51:58<10:50:30,  3.43it/s]
                                                            
{'loss': 2.8957, 'learning_rate': 4.2480984291839946e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237480/371472 [7:51:58<10:50:30,  3.43it/s]
 64%|██████▍   | 237481/371472 [7:51:58<10:56:38,  3.40it/s]
 64%|██████▍   | 237482/371472 [7:51:59<10:35:27,  3.51it/s]
 64%|██████▍   | 237483/371472 [7:51:59<10:02:44,  3.71it/s]
 64%|██████▍   | 237484/371472 [7:51:59<10:58:48,  3.39it/s]
 64%|██████▍   | 237485/371472 [7:52:00<10:25:47,  3.57it/s]
 64%|██████▍   | 237486/371472 [7:52:00<12:02:13,  3.09it/s]
 64%|██████▍   | 237487/371472 [7:52:00<11:35:11,  3.21it/s]
 64%|██████▍   | 237488/371472 [7:52:01<11:10:44,  3.33it/s]
 64%|██████▍   | 237489/371472 [7:52:01<10:43:18,  3.47it/s]
 64%|██████▍   | 237490/371472 [7:52:01<11:00:34,  3.38it/s]
 64%|██████▍   | 237491/371472 [7:52:01<10:36:21,  3.51it/s]
 64%|██████▍   | 237492/371472 [7:52:02<10:43:46,  3.47it/s]
 64%|██████▍   | 237493/371472 [7:52:02<10:49:19,  3.44it/s]
 64%|██████▍   | 237494/371472 [7:52:02<10:33:03,  3.53it/s]
 64%|██████▍   | 237495/371472 [7:52:03<11:00:38,  3.38it/s]
 64%|██████▍   | 237496/371472 [7:52:03<11:09:30,  3.34it/s]
 64%|██████▍   | 237497/371472 [7:52:03<10:53:49,  3.42it/s]
 64%|██████▍   | 237498/371472 [7:52:03<10:27:41,  3.56it/s]
 64%|██████▍   | 237499/371472 [7:52:04<12:16:44,  3.03it/s]
 64%|██████▍   | 237500/371472 [7:52:04<11:50:06,  3.14it/s]
                                                            
{'loss': 2.7648, 'learning_rate': 4.2476136094292053e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237500/371472 [7:52:04<11:50:06,  3.14it/s]
 64%|██████▍   | 237501/371472 [7:52:04<11:25:02,  3.26it/s]
 64%|██████▍   | 237502/371472 [7:52:05<10:45:53,  3.46it/s]
 64%|██████▍   | 237503/371472 [7:52:05<10:31:32,  3.54it/s]
 64%|██████▍   | 237504/371472 [7:52:05<10:16:53,  3.62it/s]
 64%|██████▍   | 237505/371472 [7:52:05<10:20:08,  3.60it/s]
 64%|██████▍   | 237506/371472 [7:52:06<10:08:56,  3.67it/s]
 64%|██████▍   | 237507/371472 [7:52:06<10:14:17,  3.63it/s]
 64%|██████▍   | 237508/371472 [7:52:06<10:03:07,  3.70it/s]
 64%|██████▍   | 237509/371472 [7:52:07<10:24:44,  3.57it/s]
 64%|██████▍   | 237510/371472 [7:52:07<10:28:23,  3.55it/s]
 64%|██████▍   | 237511/371472 [7:52:07<11:33:20,  3.22it/s]
 64%|██████▍   | 237512/371472 [7:52:07<10:49:54,  3.44it/s]
 64%|██████▍   | 237513/371472 [7:52:08<10:35:30,  3.51it/s]
 64%|██████▍   | 237514/371472 [7:52:08<10:05:09,  3.69it/s]
 64%|██████▍   | 237515/371472 [7:52:08<10:20:46,  3.60it/s]
 64%|██████▍   | 237516/371472 [7:52:09<10:02:54,  3.70it/s]
 64%|██████▍   | 237517/371472 [7:52:09<10:06:47,  3.68it/s]
 64%|██████▍   | 237518/371472 [7:52:09<11:30:07,  3.24it/s]
 64%|██████▍   | 237519/371472 [7:52:09<11:17:11,  3.30it/s]
 64%|██████▍   | 237520/371472 [7:52:10<11:07:44,  3.34it/s]
                                                            
{'loss': 2.7959, 'learning_rate': 4.247128789674417e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237520/371472 [7:52:10<11:07:44,  3.34it/s]
 64%|██████▍   | 237521/371472 [7:52:10<10:34:10,  3.52it/s]
 64%|██████▍   | 237522/371472 [7:52:10<10:35:18,  3.51it/s]
 64%|██████▍   | 237523/371472 [7:52:11<10:41:38,  3.48it/s]
 64%|██████▍   | 237524/371472 [7:52:11<10:55:37,  3.41it/s]
 64%|██████▍   | 237525/371472 [7:52:11<10:24:07,  3.58it/s]
 64%|██████▍   | 237526/371472 [7:52:12<11:35:41,  3.21it/s]
 64%|██████▍   | 237527/371472 [7:52:12<11:21:16,  3.28it/s]
 64%|██████▍   | 237528/371472 [7:52:12<11:24:38,  3.26it/s]
 64%|██████▍   | 237529/371472 [7:52:12<10:48:57,  3.44it/s]
 64%|██████▍   | 237530/371472 [7:52:13<10:38:35,  3.50it/s]
 64%|██████▍   | 237531/371472 [7:52:13<10:17:21,  3.62it/s]
 64%|██████▍   | 237532/371472 [7:52:13<11:03:02,  3.37it/s]
 64%|██████▍   | 237533/371472 [7:52:14<11:51:32,  3.14it/s]
 64%|██████▍   | 237534/371472 [7:52:14<11:08:30,  3.34it/s]
 64%|██████▍   | 237535/371472 [7:52:14<10:58:46,  3.39it/s]
 64%|██████▍   | 237536/371472 [7:52:14<11:05:14,  3.36it/s]
 64%|██████▍   | 237537/371472 [7:52:15<11:04:07,  3.36it/s]
 64%|██████▍   | 237538/371472 [7:52:15<11:26:46,  3.25it/s]
 64%|██████▍   | 237539/371472 [7:52:15<10:51:54,  3.42it/s]
 64%|██████▍   | 237540/371472 [7:52:16<10:47:43,  3.45it/s]
                                                            
{'loss': 2.8134, 'learning_rate': 4.246643969919627e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237540/371472 [7:52:16<10:47:43,  3.45it/s]
 64%|██████▍   | 237541/371472 [7:52:16<11:05:54,  3.35it/s]
 64%|██████▍   | 237542/371472 [7:52:16<10:53:38,  3.41it/s]
 64%|██████▍   | 237543/371472 [7:52:17<10:37:54,  3.50it/s]
 64%|██████▍   | 237544/371472 [7:52:17<11:08:29,  3.34it/s]
 64%|██████▍   | 237545/371472 [7:52:17<10:52:57,  3.42it/s]
 64%|██████▍   | 237546/371472 [7:52:17<10:46:11,  3.45it/s]
 64%|██████▍   | 237547/371472 [7:52:18<10:11:18,  3.65it/s]
 64%|██████▍   | 237548/371472 [7:52:18<10:25:35,  3.57it/s]
 64%|██████▍   | 237549/371472 [7:52:18<10:10:08,  3.66it/s]
 64%|██████▍   | 237550/371472 [7:52:18<9:50:30,  3.78it/s] 
 64%|██████▍   | 237551/371472 [7:52:19<10:00:43,  3.72it/s]
 64%|██████▍   | 237552/371472 [7:52:19<10:33:55,  3.52it/s]
 64%|██████▍   | 237553/371472 [7:52:19<10:26:30,  3.56it/s]
 64%|██████▍   | 237554/371472 [7:52:20<11:45:37,  3.16it/s]
 64%|██████▍   | 237555/371472 [7:52:20<10:56:55,  3.40it/s]
 64%|██████▍   | 237556/371472 [7:52:20<11:09:26,  3.33it/s]
 64%|██████▍   | 237557/371472 [7:52:21<10:53:26,  3.42it/s]
 64%|██████▍   | 237558/371472 [7:52:21<10:10:02,  3.66it/s]
 64%|██████▍   | 237559/371472 [7:52:21<10:08:13,  3.67it/s]
 64%|██████▍   | 237560/371472 [7:52:21<10:17:26,  3.61it/s]
                                                            
{'loss': 2.9787, 'learning_rate': 4.246159150164839e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237560/371472 [7:52:21<10:17:26,  3.61it/s]
 64%|██████▍   | 237561/371472 [7:52:22<10:28:05,  3.55it/s]
 64%|██████▍   | 237562/371472 [7:52:22<10:51:41,  3.42it/s]
 64%|██████▍   | 237563/371472 [7:52:22<11:06:51,  3.35it/s]
 64%|██████▍   | 237564/371472 [7:52:23<11:05:22,  3.35it/s]
 64%|██████▍   | 237565/371472 [7:52:23<10:39:47,  3.49it/s]
 64%|██████▍   | 237566/371472 [7:52:23<10:14:48,  3.63it/s]
 64%|██████▍   | 237567/371472 [7:52:23<10:05:12,  3.69it/s]
 64%|██████▍   | 237568/371472 [7:52:24<10:52:37,  3.42it/s]
 64%|██████▍   | 237569/371472 [7:52:24<10:43:58,  3.47it/s]
 64%|██████▍   | 237570/371472 [7:52:24<10:32:05,  3.53it/s]
 64%|██████▍   | 237571/371472 [7:52:24<10:08:08,  3.67it/s]
 64%|██████▍   | 237572/371472 [7:52:25<10:00:00,  3.72it/s]
 64%|██████▍   | 237573/371472 [7:52:25<9:45:19,  3.81it/s] 
 64%|██████▍   | 237574/371472 [7:52:25<10:22:40,  3.58it/s]
 64%|██████▍   | 237575/371472 [7:52:26<9:59:46,  3.72it/s] 
 64%|██████▍   | 237576/371472 [7:52:26<10:14:44,  3.63it/s]
 64%|██████▍   | 237577/371472 [7:52:26<10:17:17,  3.62it/s]
 64%|██████▍   | 237578/371472 [7:52:26<11:23:13,  3.27it/s]
 64%|██████▍   | 237579/371472 [7:52:27<11:27:26,  3.25it/s]
 64%|██████▍   | 237580/371472 [7:52:27<11:31:52,  3.23it/s]
                                                            
{'loss': 2.7819, 'learning_rate': 4.245674330410049e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237580/371472 [7:52:27<11:31:52,  3.23it/s]
 64%|██████▍   | 237581/371472 [7:52:27<11:23:47,  3.26it/s]
 64%|██████▍   | 237582/371472 [7:52:28<10:39:19,  3.49it/s]
 64%|██████▍   | 237583/371472 [7:52:28<10:40:09,  3.49it/s]
 64%|██████▍   | 237584/371472 [7:52:28<10:09:24,  3.66it/s]
 64%|██████▍   | 237585/371472 [7:52:29<12:22:45,  3.00it/s]
 64%|██████▍   | 237586/371472 [7:52:29<11:36:56,  3.20it/s]
 64%|██████▍   | 237587/371472 [7:52:29<11:09:40,  3.33it/s]
 64%|██████▍   | 237588/371472 [7:52:29<10:57:21,  3.39it/s]
 64%|██████▍   | 237589/371472 [7:52:30<10:29:04,  3.55it/s]
 64%|██████▍   | 237590/371472 [7:52:30<10:20:09,  3.60it/s]
 64%|██████▍   | 237591/371472 [7:52:30<10:51:27,  3.43it/s]
 64%|██████▍   | 237592/371472 [7:52:31<10:38:54,  3.49it/s]
 64%|██████▍   | 237593/371472 [7:52:31<11:13:32,  3.31it/s]
 64%|██████▍   | 237594/371472 [7:52:31<11:01:21,  3.37it/s]
 64%|██████▍   | 237595/371472 [7:52:32<11:23:06,  3.27it/s]
 64%|██████▍   | 237596/371472 [7:52:32<12:40:17,  2.93it/s]
 64%|██████▍   | 237597/371472 [7:52:32<11:56:38,  3.11it/s]
 64%|██████▍   | 237598/371472 [7:52:33<11:41:10,  3.18it/s]
 64%|██████▍   | 237599/371472 [7:52:33<11:46:12,  3.16it/s]
 64%|██████▍   | 237600/371472 [7:52:33<12:07:27,  3.07it/s]
                                                            
{'loss': 2.7122, 'learning_rate': 4.245189510655261e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237600/371472 [7:52:33<12:07:27,  3.07it/s]
 64%|██████▍   | 237601/371472 [7:52:33<11:41:24,  3.18it/s]
 64%|██████▍   | 237602/371472 [7:52:34<11:42:27,  3.18it/s]
 64%|██████▍   | 237603/371472 [7:52:34<11:30:06,  3.23it/s]
 64%|██████▍   | 237604/371472 [7:52:34<12:21:08,  3.01it/s]
 64%|██████▍   | 237605/371472 [7:52:35<12:26:26,  2.99it/s]
 64%|██████▍   | 237606/371472 [7:52:35<11:56:14,  3.12it/s]
 64%|██████▍   | 237607/371472 [7:52:35<11:28:50,  3.24it/s]
 64%|██████▍   | 237608/371472 [7:52:36<10:47:30,  3.45it/s]
 64%|██████▍   | 237609/371472 [7:52:36<10:31:46,  3.53it/s]
 64%|██████▍   | 237610/371472 [7:52:36<10:20:18,  3.60it/s]
 64%|██████▍   | 237611/371472 [7:52:36<10:06:51,  3.68it/s]
 64%|██████▍   | 237612/371472 [7:52:37<10:18:29,  3.61it/s]
 64%|██████▍   | 237613/371472 [7:52:37<10:19:24,  3.60it/s]
 64%|██████▍   | 237614/371472 [7:52:37<10:00:03,  3.72it/s]
 64%|██████▍   | 237615/371472 [7:52:37<9:47:28,  3.80it/s] 
 64%|██████▍   | 237616/371472 [7:52:38<10:13:16,  3.64it/s]
 64%|██████▍   | 237617/371472 [7:52:38<10:08:14,  3.67it/s]
 64%|██████▍   | 237618/371472 [7:52:38<10:11:18,  3.65it/s]
 64%|██████▍   | 237619/371472 [7:52:39<10:40:19,  3.48it/s]
 64%|██████▍   | 237620/371472 [7:52:39<10:21:36,  3.59it/s]
                                                            
{'loss': 2.8805, 'learning_rate': 4.2447046909004717e-07, 'epoch': 10.23}
+
 64%|██████▍   | 237620/371472 [7:52:39<10:21:36,  3.59it/s]
 64%|██████▍   | 237621/371472 [7:52:39<10:20:10,  3.60it/s]
 64%|██████▍   | 237622/371472 [7:52:39<10:15:20,  3.63it/s]
 64%|██████▍   | 237623/371472 [7:52:40<9:56:22,  3.74it/s] 
 64%|██████▍   | 237624/371472 [7:52:40<10:39:29,  3.49it/s]
 64%|██████▍   | 237625/371472 [7:52:40<10:37:43,  3.50it/s]
 64%|██████▍   | 237626/371472 [7:52:41<10:38:30,  3.49it/s]
 64%|██████▍   | 237627/371472 [7:52:41<10:40:22,  3.48it/s]
 64%|██████▍   | 237628/371472 [7:52:41<10:34:31,  3.52it/s]
 64%|██████▍   | 237629/371472 [7:52:41<10:40:28,  3.48it/s]
 64%|██████▍   | 237630/371472 [7:52:42<10:45:06,  3.46it/s]
 64%|██████▍   | 237631/371472 [7:52:42<10:48:57,  3.44it/s]
 64%|██████▍   | 237632/371472 [7:52:42<11:10:06,  3.33it/s]
 64%|██████▍   | 237633/371472 [7:52:43<10:47:55,  3.44it/s]
 64%|██████▍   | 237634/371472 [7:52:43<10:28:59,  3.55it/s]
 64%|██████▍   | 237635/371472 [7:52:43<10:08:49,  3.66it/s]
 64%|██████▍   | 237636/371472 [7:52:43<10:01:11,  3.71it/s]
 64%|██████▍   | 237637/371472 [7:52:44<10:19:36,  3.60it/s]
 64%|██████▍   | 237638/371472 [7:52:44<9:58:34,  3.73it/s] 
 64%|██████▍   | 237639/371472 [7:52:44<10:37:29,  3.50it/s]
 64%|██████▍   | 237640/371472 [7:52:45<10:51:23,  3.42it/s]
                                                            
{'loss': 2.7862, 'learning_rate': 4.244219871145683e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237640/371472 [7:52:45<10:51:23,  3.42it/s]
 64%|██████▍   | 237641/371472 [7:52:45<10:30:22,  3.54it/s]
 64%|██████▍   | 237642/371472 [7:52:45<10:47:10,  3.45it/s]
 64%|██████▍   | 237643/371472 [7:52:45<10:21:49,  3.59it/s]
 64%|██████▍   | 237644/371472 [7:52:46<9:58:10,  3.73it/s] 
 64%|██████▍   | 237645/371472 [7:52:46<9:53:13,  3.76it/s]
 64%|██████▍   | 237646/371472 [7:52:46<10:05:56,  3.68it/s]
 64%|██████▍   | 237647/371472 [7:52:47<10:31:39,  3.53it/s]
 64%|██████▍   | 237648/371472 [7:52:47<10:38:42,  3.49it/s]
 64%|██████▍   | 237649/371472 [7:52:47<10:18:59,  3.60it/s]
 64%|██████▍   | 237650/371472 [7:52:47<10:01:07,  3.71it/s]
 64%|██████▍   | 237651/371472 [7:52:48<11:01:47,  3.37it/s]
 64%|██████▍   | 237652/371472 [7:52:48<10:48:55,  3.44it/s]
 64%|██████▍   | 237653/371472 [7:52:48<10:19:39,  3.60it/s]
 64%|██████▍   | 237654/371472 [7:52:49<10:49:14,  3.44it/s]
 64%|██████▍   | 237655/371472 [7:52:49<10:56:20,  3.40it/s]
 64%|██████▍   | 237656/371472 [7:52:49<10:48:12,  3.44it/s]
 64%|██████▍   | 237657/371472 [7:52:49<10:37:19,  3.50it/s]
 64%|██████▍   | 237658/371472 [7:52:50<10:24:55,  3.57it/s]
 64%|██████▍   | 237659/371472 [7:52:50<10:06:04,  3.68it/s]
 64%|██████▍   | 237660/371472 [7:52:50<10:21:19,  3.59it/s]
                                                            
{'loss': 2.9104, 'learning_rate': 4.2437350513908936e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237660/371472 [7:52:50<10:21:19,  3.59it/s]
 64%|██████▍   | 237661/371472 [7:52:50<10:07:40,  3.67it/s]
 64%|██████▍   | 237662/371472 [7:52:51<10:53:47,  3.41it/s]
 64%|██████▍   | 237663/371472 [7:52:51<10:31:52,  3.53it/s]
 64%|██████▍   | 237664/371472 [7:52:51<10:21:56,  3.59it/s]
 64%|██████▍   | 237665/371472 [7:52:52<11:03:42,  3.36it/s]
 64%|██████▍   | 237666/371472 [7:52:52<11:00:35,  3.38it/s]
 64%|██████▍   | 237667/371472 [7:52:52<10:26:24,  3.56it/s]
 64%|██████▍   | 237668/371472 [7:52:52<10:00:18,  3.71it/s]
 64%|██████▍   | 237669/371472 [7:52:53<10:10:49,  3.65it/s]
 64%|██████▍   | 237670/371472 [7:52:53<10:28:31,  3.55it/s]
 64%|██████▍   | 237671/371472 [7:52:53<10:45:45,  3.45it/s]
 64%|██████▍   | 237672/371472 [7:52:54<11:05:59,  3.35it/s]
 64%|██████▍   | 237673/371472 [7:52:54<12:12:15,  3.05it/s]
 64%|██████▍   | 237674/371472 [7:52:54<11:30:20,  3.23it/s]
 64%|██████▍   | 237675/371472 [7:52:55<10:59:42,  3.38it/s]
 64%|██████▍   | 237676/371472 [7:52:55<11:19:08,  3.28it/s]
 64%|██████▍   | 237677/371472 [7:52:55<11:04:56,  3.35it/s]
 64%|██████▍   | 237678/371472 [7:52:56<11:10:14,  3.33it/s]
 64%|██████▍   | 237679/371472 [7:52:56<10:53:20,  3.41it/s]
 64%|██████▍   | 237680/371472 [7:52:56<10:33:12,  3.52it/s]
                                                            
{'loss': 2.8662, 'learning_rate': 4.2432502316361054e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237680/371472 [7:52:56<10:33:12,  3.52it/s]
 64%|██████▍   | 237681/371472 [7:52:56<10:24:46,  3.57it/s]
 64%|██████▍   | 237682/371472 [7:52:57<10:38:42,  3.49it/s]
 64%|██████▍   | 237683/371472 [7:52:57<10:27:15,  3.55it/s]
 64%|██████▍   | 237684/371472 [7:52:57<10:23:00,  3.58it/s]
 64%|██████▍   | 237685/371472 [7:52:57<10:29:02,  3.54it/s]
 64%|██████▍   | 237686/371472 [7:52:58<10:19:24,  3.60it/s]
 64%|██████▍   | 237687/371472 [7:52:58<10:38:48,  3.49it/s]
 64%|██████▍   | 237688/371472 [7:52:58<10:32:44,  3.52it/s]
 64%|██████▍   | 237689/371472 [7:52:59<10:56:06,  3.40it/s]
 64%|██████▍   | 237690/371472 [7:52:59<10:38:48,  3.49it/s]
 64%|██████▍   | 237691/371472 [7:52:59<10:13:21,  3.64it/s]
 64%|██████▍   | 237692/371472 [7:52:59<10:01:52,  3.70it/s]
 64%|██████▍   | 237693/371472 [7:53:00<9:53:28,  3.76it/s] 
 64%|██████▍   | 237694/371472 [7:53:00<9:55:14,  3.75it/s]
 64%|██████▍   | 237695/371472 [7:53:00<10:05:21,  3.68it/s]
 64%|██████▍   | 237696/371472 [7:53:00<9:58:13,  3.73it/s] 
 64%|██████▍   | 237697/371472 [7:53:01<10:29:15,  3.54it/s]
 64%|██████▍   | 237698/371472 [7:53:01<10:46:16,  3.45it/s]
 64%|██████▍   | 237699/371472 [7:53:01<10:24:33,  3.57it/s]
 64%|██████▍   | 237700/371472 [7:53:02<10:02:12,  3.70it/s]
                                                            
{'loss': 2.8829, 'learning_rate': 4.242765411881316e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237700/371472 [7:53:02<10:02:12,  3.70it/s]
 64%|██████▍   | 237701/371472 [7:53:02<9:49:00,  3.79it/s] 
 64%|██████▍   | 237702/371472 [7:53:02<9:37:30,  3.86it/s]
 64%|██████▍   | 237703/371472 [7:53:02<9:40:42,  3.84it/s]
 64%|██████▍   | 237704/371472 [7:53:03<9:23:59,  3.95it/s]
 64%|██████▍   | 237705/371472 [7:53:03<9:48:40,  3.79it/s]
 64%|██████▍   | 237706/371472 [7:53:03<10:37:46,  3.50it/s]
 64%|██████▍   | 237707/371472 [7:53:03<10:33:12,  3.52it/s]
 64%|██████▍   | 237708/371472 [7:53:04<10:27:17,  3.55it/s]
 64%|██████▍   | 237709/371472 [7:53:04<10:27:24,  3.55it/s]
 64%|██████▍   | 237710/371472 [7:53:04<10:44:44,  3.46it/s]
 64%|██████▍   | 237711/371472 [7:53:05<10:35:28,  3.51it/s]
 64%|██████▍   | 237712/371472 [7:53:05<10:56:45,  3.39it/s]
 64%|██████▍   | 237713/371472 [7:53:05<11:29:46,  3.23it/s]
 64%|██████▍   | 237714/371472 [7:53:06<11:14:38,  3.30it/s]
 64%|██████▍   | 237715/371472 [7:53:06<10:50:32,  3.43it/s]
 64%|██████▍   | 237716/371472 [7:53:06<11:38:38,  3.19it/s]
 64%|██████▍   | 237717/371472 [7:53:06<11:13:31,  3.31it/s]
 64%|██████▍   | 237718/371472 [7:53:07<11:00:01,  3.38it/s]
 64%|██████▍   | 237719/371472 [7:53:07<10:52:59,  3.41it/s]
 64%|██████▍   | 237720/371472 [7:53:07<11:01:57,  3.37it/s]
                                                            
{'loss': 2.8827, 'learning_rate': 4.2422805921265274e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237720/371472 [7:53:07<11:01:57,  3.37it/s]
 64%|██████▍   | 237721/371472 [7:53:08<10:42:31,  3.47it/s]
 64%|██████▍   | 237722/371472 [7:53:08<10:33:55,  3.52it/s]
 64%|██████▍   | 237723/371472 [7:53:08<10:38:30,  3.49it/s]
 64%|██████▍   | 237724/371472 [7:53:09<11:40:56,  3.18it/s]
 64%|██████▍   | 237725/371472 [7:53:09<11:10:14,  3.33it/s]
 64%|██████▍   | 237726/371472 [7:53:09<11:13:46,  3.31it/s]
 64%|██████▍   | 237727/371472 [7:53:09<10:57:51,  3.39it/s]
 64%|██████▍   | 237728/371472 [7:53:10<10:29:40,  3.54it/s]
 64%|██████▍   | 237729/371472 [7:53:10<10:28:40,  3.55it/s]
 64%|██████▍   | 237730/371472 [7:53:10<10:35:03,  3.51it/s]
 64%|██████▍   | 237731/371472 [7:53:11<10:33:58,  3.52it/s]
 64%|██████▍   | 237732/371472 [7:53:11<10:47:51,  3.44it/s]
 64%|██████▍   | 237733/371472 [7:53:11<10:48:44,  3.44it/s]
 64%|██████▍   | 237734/371472 [7:53:11<10:32:27,  3.52it/s]
 64%|██████▍   | 237735/371472 [7:53:12<10:14:17,  3.63it/s]
 64%|██████▍   | 237736/371472 [7:53:12<9:59:10,  3.72it/s] 
 64%|██████▍   | 237737/371472 [7:53:12<9:54:16,  3.75it/s]
 64%|██████▍   | 237738/371472 [7:53:12<9:47:13,  3.80it/s]
 64%|██████▍   | 237739/371472 [7:53:13<9:48:15,  3.79it/s]
 64%|██████▍   | 237740/371472 [7:53:13<10:29:21,  3.54it/s]
                                                            
{'loss': 2.8004, 'learning_rate': 4.241795772371738e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237740/371472 [7:53:13<10:29:21,  3.54it/s]
 64%|██████▍   | 237741/371472 [7:53:13<10:26:12,  3.56it/s]
 64%|██████▍   | 237742/371472 [7:53:14<10:19:41,  3.60it/s]
 64%|██████▍   | 237743/371472 [7:53:14<10:22:40,  3.58it/s]
 64%|██████▍   | 237744/371472 [7:53:14<10:12:53,  3.64it/s]
 64%|██████▍   | 237745/371472 [7:53:14<10:01:28,  3.71it/s]
 64%|██████▍   | 237746/371472 [7:53:15<11:09:20,  3.33it/s]
 64%|██████▍   | 237747/371472 [7:53:15<11:15:29,  3.30it/s]
 64%|██████▍   | 237748/371472 [7:53:15<11:38:37,  3.19it/s]
 64%|██████▍   | 237749/371472 [7:53:16<11:25:50,  3.25it/s]
 64%|██████▍   | 237750/371472 [7:53:16<10:57:14,  3.39it/s]
 64%|██████▍   | 237751/371472 [7:53:16<10:22:51,  3.58it/s]
 64%|██████▍   | 237752/371472 [7:53:17<11:21:00,  3.27it/s]
 64%|██████▍   | 237753/371472 [7:53:17<10:50:35,  3.43it/s]
 64%|██████▍   | 237754/371472 [7:53:17<10:14:03,  3.63it/s]
 64%|██████▍   | 237755/371472 [7:53:17<9:54:20,  3.75it/s] 
 64%|██████▍   | 237756/371472 [7:53:18<9:49:36,  3.78it/s]
 64%|██████▍   | 237757/371472 [7:53:18<9:54:49,  3.75it/s]
 64%|██████▍   | 237758/371472 [7:53:18<10:33:49,  3.52it/s]
 64%|██████▍   | 237759/371472 [7:53:18<11:00:53,  3.37it/s]
 64%|██████▍   | 237760/371472 [7:53:19<11:06:21,  3.34it/s]
                                                            
{'loss': 2.9025, 'learning_rate': 4.2413109526169493e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237760/371472 [7:53:19<11:06:21,  3.34it/s]
 64%|██████▍   | 237761/371472 [7:53:19<10:53:08,  3.41it/s]
 64%|██████▍   | 237762/371472 [7:53:19<10:49:59,  3.43it/s]
 64%|██████▍   | 237763/371472 [7:53:20<10:44:45,  3.46it/s]
 64%|██████▍   | 237764/371472 [7:53:20<10:38:23,  3.49it/s]
 64%|██████▍   | 237765/371472 [7:53:20<10:39:09,  3.49it/s]
 64%|██████▍   | 237766/371472 [7:53:20<10:13:53,  3.63it/s]
 64%|██████▍   | 237767/371472 [7:53:21<10:02:09,  3.70it/s]
 64%|██████▍   | 237768/371472 [7:53:21<10:07:21,  3.67it/s]
 64%|██████▍   | 237769/371472 [7:53:21<10:32:50,  3.52it/s]
 64%|██████▍   | 237770/371472 [7:53:22<10:26:51,  3.55it/s]
 64%|██████▍   | 237771/371472 [7:53:22<10:06:06,  3.68it/s]
 64%|██████▍   | 237772/371472 [7:53:22<10:00:42,  3.71it/s]
 64%|██████▍   | 237773/371472 [7:53:22<10:19:04,  3.60it/s]
 64%|██████▍   | 237774/371472 [7:53:23<10:01:06,  3.71it/s]
 64%|██████▍   | 237775/371472 [7:53:23<10:03:05,  3.69it/s]
 64%|██████▍   | 237776/371472 [7:53:23<11:59:38,  3.10it/s]
 64%|██████▍   | 237777/371472 [7:53:24<11:32:22,  3.22it/s]
 64%|██████▍   | 237778/371472 [7:53:24<11:36:06,  3.20it/s]
 64%|██████▍   | 237779/371472 [7:53:24<11:37:49,  3.19it/s]
 64%|██████▍   | 237780/371472 [7:53:25<11:11:12,  3.32it/s]
                                                            
{'loss': 2.7782, 'learning_rate': 4.24082613286216e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237780/371472 [7:53:25<11:11:12,  3.32it/s]
 64%|██████▍   | 237781/371472 [7:53:25<10:40:50,  3.48it/s]
 64%|██████▍   | 237782/371472 [7:53:25<10:58:41,  3.38it/s]
 64%|██████▍   | 237783/371472 [7:53:25<10:26:28,  3.56it/s]
 64%|██████▍   | 237784/371472 [7:53:26<10:19:39,  3.60it/s]
 64%|██████▍   | 237785/371472 [7:53:26<11:06:18,  3.34it/s]
 64%|██████▍   | 237786/371472 [7:53:26<10:50:39,  3.42it/s]
 64%|██████▍   | 237787/371472 [7:53:27<10:34:32,  3.51it/s]
 64%|██████▍   | 237788/371472 [7:53:27<10:37:26,  3.50it/s]
 64%|██████▍   | 237789/371472 [7:53:27<10:38:08,  3.49it/s]
 64%|██████▍   | 237790/371472 [7:53:27<10:23:02,  3.58it/s]
 64%|██████▍   | 237791/371472 [7:53:28<10:52:41,  3.41it/s]
 64%|██████▍   | 237792/371472 [7:53:28<10:28:32,  3.54it/s]
 64%|██████▍   | 237793/371472 [7:53:28<10:21:39,  3.58it/s]
 64%|██████▍   | 237794/371472 [7:53:29<10:21:42,  3.58it/s]
 64%|██████▍   | 237795/371472 [7:53:29<11:25:05,  3.25it/s]
 64%|██████▍   | 237796/371472 [7:53:29<10:51:11,  3.42it/s]
 64%|██████▍   | 237797/371472 [7:53:29<10:13:20,  3.63it/s]
 64%|██████▍   | 237798/371472 [7:53:30<10:08:05,  3.66it/s]
 64%|██████▍   | 237799/371472 [7:53:30<9:58:23,  3.72it/s] 
 64%|██████▍   | 237800/371472 [7:53:30<10:03:27,  3.69it/s]
                                                            
{'loss': 2.8071, 'learning_rate': 4.240341313107371e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237800/371472 [7:53:30<10:03:27,  3.69it/s]
 64%|██████▍   | 237801/371472 [7:53:31<10:59:28,  3.38it/s]
 64%|██████▍   | 237802/371472 [7:53:31<10:52:10,  3.42it/s]
 64%|██████▍   | 237803/371472 [7:53:31<11:00:18,  3.37it/s]
 64%|██████▍   | 237804/371472 [7:53:31<10:41:48,  3.47it/s]
 64%|██████▍   | 237805/371472 [7:53:32<10:30:28,  3.53it/s]
 64%|██████▍   | 237806/371472 [7:53:32<10:19:00,  3.60it/s]
 64%|██████▍   | 237807/371472 [7:53:32<10:11:02,  3.65it/s]
 64%|██████▍   | 237808/371472 [7:53:32<10:02:37,  3.70it/s]
 64%|██████▍   | 237809/371472 [7:53:33<11:26:49,  3.24it/s]
 64%|██████▍   | 237810/371472 [7:53:33<10:50:56,  3.42it/s]
 64%|██████▍   | 237811/371472 [7:53:33<10:29:56,  3.54it/s]
 64%|██████▍   | 237812/371472 [7:53:34<10:12:06,  3.64it/s]
 64%|██████▍   | 237813/371472 [7:53:34<10:28:34,  3.54it/s]
 64%|██████▍   | 237814/371472 [7:53:34<10:25:55,  3.56it/s]
 64%|██████▍   | 237815/371472 [7:53:34<10:13:32,  3.63it/s]
 64%|██████▍   | 237816/371472 [7:53:35<10:41:59,  3.47it/s]
 64%|██████▍   | 237817/371472 [7:53:35<10:58:09,  3.38it/s]
 64%|██████▍   | 237818/371472 [7:53:35<10:45:24,  3.45it/s]
 64%|██████▍   | 237819/371472 [7:53:36<10:54:42,  3.40it/s]
 64%|██████▍   | 237820/371472 [7:53:36<11:36:49,  3.20it/s]
                                                            
{'loss': 3.0125, 'learning_rate': 4.2398564933525825e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237820/371472 [7:53:36<11:36:49,  3.20it/s]
 64%|██████▍   | 237821/371472 [7:53:36<11:37:42,  3.19it/s]
 64%|██████▍   | 237822/371472 [7:53:37<11:54:44,  3.12it/s]
 64%|██████▍   | 237823/371472 [7:53:37<11:22:57,  3.26it/s]
 64%|██████▍   | 237824/371472 [7:53:37<10:53:47,  3.41it/s]
 64%|██████▍   | 237825/371472 [7:53:38<11:13:57,  3.31it/s]
 64%|██████▍   | 237826/371472 [7:53:38<10:54:24,  3.40it/s]
 64%|██████▍   | 237827/371472 [7:53:38<10:59:11,  3.38it/s]
 64%|██████▍   | 237828/371472 [7:53:38<10:30:32,  3.53it/s]
 64%|██████▍   | 237829/371472 [7:53:39<10:12:19,  3.64it/s]
 64%|██████▍   | 237830/371472 [7:53:39<10:15:25,  3.62it/s]
 64%|██████▍   | 237831/371472 [7:53:39<10:01:02,  3.71it/s]
 64%|██████▍   | 237832/371472 [7:53:39<9:49:38,  3.78it/s] 
 64%|██████▍   | 237833/371472 [7:53:40<9:42:56,  3.82it/s]
 64%|██████▍   | 237834/371472 [7:53:40<9:44:44,  3.81it/s]
 64%|██████▍   | 237835/371472 [7:53:40<10:26:58,  3.55it/s]
 64%|██████▍   | 237836/371472 [7:53:41<11:47:06,  3.15it/s]
 64%|██████▍   | 237837/371472 [7:53:41<11:15:45,  3.30it/s]
 64%|██████▍   | 237838/371472 [7:53:41<11:02:36,  3.36it/s]
 64%|██████▍   | 237839/371472 [7:53:41<10:51:10,  3.42it/s]
 64%|██████▍   | 237840/371472 [7:53:42<11:13:08,  3.31it/s]
                                                            
{'loss': 3.0222, 'learning_rate': 4.2393716735977927e-07, 'epoch': 10.24}
+
 64%|██████▍   | 237840/371472 [7:53:42<11:13:08,  3.31it/s]
 64%|██████▍   | 237841/371472 [7:53:42<11:24:02,  3.26it/s]
 64%|██████▍   | 237842/371472 [7:53:42<11:20:30,  3.27it/s]
 64%|██████▍   | 237843/371472 [7:53:43<11:33:52,  3.21it/s]
 64%|██████▍   | 237844/371472 [7:53:43<12:04:45,  3.07it/s]
 64%|██████▍   | 237845/371472 [7:53:43<11:36:50,  3.20it/s]
 64%|██████▍   | 237846/371472 [7:53:44<10:48:23,  3.43it/s]
 64%|██████▍   | 237847/371472 [7:53:44<11:03:51,  3.35it/s]
 64%|██████▍   | 237848/371472 [7:53:44<10:29:33,  3.54it/s]
 64%|██████▍   | 237849/371472 [7:53:45<11:46:39,  3.15it/s]
 64%|██████▍   | 237850/371472 [7:53:45<11:11:25,  3.32it/s]
 64%|██████▍   | 237851/371472 [7:53:45<11:06:47,  3.34it/s]
 64%|██████▍   | 237852/371472 [7:53:45<10:44:56,  3.45it/s]
 64%|██████▍   | 237853/371472 [7:53:46<10:46:55,  3.44it/s]
 64%|██████▍   | 237854/371472 [7:53:46<10:53:12,  3.41it/s]
 64%|██████▍   | 237855/371472 [7:53:46<10:39:12,  3.48it/s]
 64%|██████▍   | 237856/371472 [7:53:47<10:46:18,  3.45it/s]
 64%|██████▍   | 237857/371472 [7:53:47<10:31:01,  3.53it/s]
 64%|██████▍   | 237858/371472 [7:53:47<10:16:55,  3.61it/s]
 64%|██████▍   | 237859/371472 [7:53:47<11:20:34,  3.27it/s]
 64%|██████▍   | 237860/371472 [7:53:48<11:11:36,  3.32it/s]
                                                            
{'loss': 2.676, 'learning_rate': 4.2388868538430045e-07, 'epoch': 10.25}
+
 64%|██████▍   | 237860/371472 [7:53:48<11:11:36,  3.32it/s]
 64%|██████▍   | 237861/371472 [7:53:48<11:27:00,  3.24it/s]
 64%|██████▍   | 237862/371472 [7:53:48<11:09:56,  3.32it/s]
 64%|██████▍   | 237863/371472 [7:53:49<10:44:32,  3.45it/s]
 64%|██████▍   | 237864/371472 [7:53:49<10:45:08,  3.45it/s]
 64%|██████▍   | 237865/371472 [7:53:49<10:57:18,  3.39it/s]
 64%|██████▍   | 237866/371472 [7:53:50<10:44:59,  3.45it/s]
 64%|██████▍   | 237867/371472 [7:53:50<12:00:19,  3.09it/s]
 64%|██████▍   | 237868/371472 [7:53:50<12:00:43,  3.09it/s]
 64%|██████▍   | 237869/371472 [7:53:51<11:18:25,  3.28it/s]
 64%|██████▍   | 237870/371472 [7:53:51<10:54:02,  3.40it/s]
 64%|██████▍   | 237871/371472 [7:53:51<10:19:26,  3.59it/s]
 64%|██████▍   | 237872/371472 [7:53:51<10:10:43,  3.65it/s]
 64%|██████▍   | 237873/371472 [7:53:52<10:02:50,  3.69it/s]
 64%|██████▍   | 237874/371472 [7:53:52<10:22:27,  3.58it/s]
 64%|██████▍   | 237875/371472 [7:53:52<10:08:53,  3.66it/s]
 64%|██████▍   | 237876/371472 [7:53:52<10:22:46,  3.58it/s]
 64%|██████▍   | 237877/371472 [7:53:53<11:08:48,  3.33it/s]
 64%|██████▍   | 237878/371472 [7:53:53<10:42:43,  3.46it/s]
 64%|██████▍   | 237879/371472 [7:53:53<10:31:34,  3.53it/s]
 64%|██████▍   | 237880/371472 [7:53:54<11:05:41,  3.34it/s]
                                                            
{'loss': 2.9778, 'learning_rate': 4.238402034088215e-07, 'epoch': 10.25}
+
 64%|██████▍   | 237880/371472 [7:53:54<11:05:41,  3.34it/s]
 64%|██████▍   | 237881/371472 [7:53:54<11:39:56,  3.18it/s]
 64%|██████▍   | 237882/371472 [7:53:54<11:18:19,  3.28it/s]
 64%|██████▍   | 237883/371472 [7:53:55<11:00:21,  3.37it/s]
 64%|██████▍   | 237884/371472 [7:53:55<10:37:17,  3.49it/s]
 64%|██████▍   | 237885/371472 [7:53:55<10:10:03,  3.65it/s]
 64%|██████▍   | 237886/371472 [7:53:55<10:09:21,  3.65it/s]
 64%|██████▍   | 237887/371472 [7:53:56<10:38:28,  3.49it/s]
 64%|██████▍   | 237888/371472 [7:53:56<10:11:23,  3.64it/s]
 64%|██████▍   | 237889/371472 [7:53:56<10:24:07,  3.57it/s]
 64%|██████▍   | 237890/371472 [7:53:56<10:55:40,  3.40it/s]
 64%|██████▍   | 237891/371472 [7:53:57<11:18:49,  3.28it/s]
 64%|██████▍   | 237892/371472 [7:53:57<10:36:09,  3.50it/s]
 64%|██████▍   | 237893/371472 [7:53:57<10:26:33,  3.55it/s]
 64%|██████▍   | 237894/371472 [7:53:58<10:35:39,  3.50it/s]
 64%|██████▍   | 237895/371472 [7:53:58<10:24:57,  3.56it/s]
 64%|██████▍   | 237896/371472 [7:53:58<11:10:32,  3.32it/s]
 64%|██████▍   | 237897/371472 [7:53:59<10:45:38,  3.45it/s]
 64%|██████▍   | 237898/371472 [7:53:59<10:22:07,  3.58it/s]
 64%|██████▍   | 237899/371472 [7:53:59<10:24:05,  3.57it/s]
 64%|██████▍   | 237900/371472 [7:53:59<10:21:35,  3.58it/s]
                                                            
{'loss': 2.9969, 'learning_rate': 4.2379172143334265e-07, 'epoch': 10.25}
+
 64%|██████▍   | 237900/371472 [7:53:59<10:21:35,  3.58it/s]
 64%|██████▍   | 237901/371472 [7:54:00<10:55:05,  3.40it/s]
 64%|██████▍   | 237902/371472 [7:54:00<10:13:11,  3.63it/s]
 64%|██████▍   | 237903/371472 [7:54:00<10:40:35,  3.48it/s]
 64%|██████▍   | 237904/371472 [7:54:00<10:24:48,  3.56it/s]
 64%|██████▍   | 237905/371472 [7:54:01<10:39:47,  3.48it/s]
 64%|██████▍   | 237906/371472 [7:54:01<11:26:33,  3.24it/s]
 64%|██████▍   | 237907/371472 [7:54:01<11:12:42,  3.31it/s]
 64%|██████▍   | 237908/371472 [7:54:02<11:34:40,  3.20it/s]
 64%|██████▍   | 237909/371472 [7:54:02<11:14:01,  3.30it/s]
 64%|██████▍   | 237910/371472 [7:54:02<11:07:31,  3.33it/s]
 64%|██████▍   | 237911/371472 [7:54:03<10:59:58,  3.37it/s]
 64%|██████▍   | 237912/371472 [7:54:03<10:25:00,  3.56it/s]
 64%|██████▍   | 237913/371472 [7:54:03<11:03:39,  3.35it/s]
 64%|██████▍   | 237914/371472 [7:54:03<10:57:23,  3.39it/s]
 64%|██████▍   | 237915/371472 [7:54:04<10:36:37,  3.50it/s]
 64%|██████▍   | 237916/371472 [7:54:04<10:14:21,  3.62it/s]
 64%|██████▍   | 237917/371472 [7:54:04<10:22:58,  3.57it/s]
 64%|██████▍   | 237918/371472 [7:54:05<10:13:21,  3.63it/s]
 64%|██████▍   | 237919/371472 [7:54:05<10:49:31,  3.43it/s]
 64%|██████▍   | 237920/371472 [7:54:05<10:35:27,  3.50it/s]
                                                            
{'loss': 2.9052, 'learning_rate': 4.237432394578637e-07, 'epoch': 10.25}
+
 64%|██████▍   | 237920/371472 [7:54:05<10:35:27,  3.50it/s]
 64%|██████▍   | 237921/371472 [7:54:05<10:11:47,  3.64it/s]
 64%|██████▍   | 237922/371472 [7:54:06<10:17:19,  3.61it/s]
 64%|██████▍   | 237923/371472 [7:54:06<10:18:15,  3.60it/s]
 64%|██████▍   | 237924/371472 [7:54:06<10:29:25,  3.54it/s]
 64%|██████▍   | 237925/371472 [7:54:07<10:40:34,  3.47it/s]
 64%|██████▍   | 237926/371472 [7:54:07<10:42:31,  3.46it/s]
 64%|██████▍   | 237927/371472 [7:54:07<10:28:41,  3.54it/s]
 64%|██████▍   | 237928/371472 [7:54:07<11:08:32,  3.33it/s]
 64%|██████▍   | 237929/371472 [7:54:08<11:41:48,  3.17it/s]
 64%|██████▍   | 237930/371472 [7:54:08<11:15:40,  3.29it/s]
 64%|██████▍   | 237931/371472 [7:54:08<11:03:38,  3.35it/s]
 64%|██████▍   | 237932/371472 [7:54:09<10:31:58,  3.52it/s]
 64%|██████▍   | 237933/371472 [7:54:09<10:27:24,  3.55it/s]
 64%|██████▍   | 237934/371472 [7:54:09<10:09:47,  3.65it/s]
 64%|██████▍   | 237935/371472 [7:54:09<10:29:24,  3.54it/s]
 64%|██████▍   | 237936/371472 [7:54:10<10:46:30,  3.44it/s]
 64%|██████▍   | 237937/371472 [7:54:10<10:29:19,  3.54it/s]
 64%|██████▍   | 237938/371472 [7:54:10<10:22:32,  3.58it/s]
 64%|██████▍   | 237939/371472 [7:54:11<10:05:20,  3.68it/s]
 64%|██████▍   | 237940/371472 [7:54:11<10:03:04,  3.69it/s]
                                                            
{'loss': 2.8974, 'learning_rate': 4.2369475748238484e-07, 'epoch': 10.25}
+
 64%|██████▍   | 237940/371472 [7:54:11<10:03:04,  3.69it/s]
 64%|██████▍   | 237941/371472 [7:54:11<9:49:48,  3.77it/s] 
 64%|██████▍   | 237942/371472 [7:54:11<10:58:44,  3.38it/s]
 64%|██████▍   | 237943/371472 [7:54:12<10:35:42,  3.50it/s]
 64%|██████▍   | 237944/371472 [7:54:12<10:08:01,  3.66it/s]
 64%|██████▍   | 237945/371472 [7:54:12<10:42:18,  3.46it/s]
 64%|██████▍   | 237946/371472 [7:54:13<11:46:33,  3.15it/s]
 64%|██████▍   | 237947/371472 [7:54:13<11:46:34,  3.15it/s]
 64%|██████▍   | 237948/371472 [7:54:13<11:10:53,  3.32it/s]
 64%|██████▍   | 237949/371472 [7:54:14<10:37:23,  3.49it/s]
 64%|██████▍   | 237950/371472 [7:54:14<10:23:50,  3.57it/s]
 64%|██████▍   | 237951/371472 [7:54:14<10:25:01,  3.56it/s]
 64%|██████▍   | 237952/371472 [7:54:14<10:34:25,  3.51it/s]
 64%|██████▍   | 237953/371472 [7:54:15<10:35:35,  3.50it/s]
 64%|██████▍   | 237954/371472 [7:54:15<10:25:41,  3.56it/s]
 64%|██████▍   | 237955/371472 [7:54:15<10:37:32,  3.49it/s]
 64%|██████▍   | 237956/371472 [7:54:15<10:37:18,  3.49it/s]
 64%|██████▍   | 237957/371472 [7:54:16<10:23:58,  3.57it/s]
 64%|██████▍   | 237958/371472 [7:54:16<10:37:56,  3.49it/s]
 64%|██████▍   | 237959/371472 [7:54:16<10:21:59,  3.58it/s]
 64%|██████▍   | 237960/371472 [7:54:17<10:33:55,  3.51it/s]
                                                            
{'loss': 2.7644, 'learning_rate': 4.236462755069059e-07, 'epoch': 10.25}
+
 64%|██████▍   | 237960/371472 [7:54:17<10:33:55,  3.51it/s]
 64%|██████▍   | 237961/371472 [7:54:17<11:51:54,  3.13it/s]
 64%|██████▍   | 237962/371472 [7:54:17<11:04:56,  3.35it/s]
 64%|██████▍   | 237963/371472 [7:54:18<10:46:31,  3.44it/s]
 64%|██████▍   | 237964/371472 [7:54:18<10:28:43,  3.54it/s]
 64%|██████▍   | 237965/371472 [7:54:18<10:40:43,  3.47it/s]
 64%|██████▍   | 237966/371472 [7:54:18<10:45:28,  3.45it/s]
 64%|██████▍   | 237967/371472 [7:54:19<10:13:06,  3.63it/s]
 64%|██████▍   | 237968/371472 [7:54:19<10:10:05,  3.65it/s]
 64%|██████▍   | 237969/371472 [7:54:19<9:48:16,  3.78it/s] 
 64%|██████▍   | 237970/371472 [7:54:19<10:23:07,  3.57it/s]
 64%|██████▍   | 237971/371472 [7:54:20<10:53:11,  3.41it/s]
 64%|██████▍   | 237972/371472 [7:54:20<10:59:46,  3.37it/s]
 64%|██████▍   | 237973/371472 [7:54:20<10:38:06,  3.49it/s]
 64%|██████▍   | 237974/371472 [7:54:21<10:46:24,  3.44it/s]
 64%|██████▍   | 237975/371472 [7:54:21<10:36:47,  3.49it/s]
 64%|██████▍   | 237976/371472 [7:54:21<10:37:17,  3.49it/s]
 64%|██████▍   | 237977/371472 [7:54:21<10:23:32,  3.57it/s]
 64%|██████▍   | 237978/371472 [7:54:22<10:08:35,  3.66it/s]
 64%|██████▍   | 237979/371472 [7:54:22<10:00:54,  3.70it/s]
 64%|██████▍   | 237980/371472 [7:54:22<10:03:06,  3.69it/s]
                                                            
{'loss': 3.0208, 'learning_rate': 4.235977935314271e-07, 'epoch': 10.25}
+
 64%|██████▍   | 237980/371472 [7:54:22<10:03:06,  3.69it/s]
 64%|██████▍   | 237981/371472 [7:54:23<10:01:12,  3.70it/s]
 64%|██████▍   | 237982/371472 [7:54:23<10:04:38,  3.68it/s]
 64%|██████▍   | 237983/371472 [7:54:23<9:51:17,  3.76it/s] 
 64%|██████▍   | 237984/371472 [7:54:23<10:37:23,  3.49it/s]
 64%|██████▍   | 237985/371472 [7:54:24<11:01:06,  3.37it/s]
 64%|██████▍   | 237986/371472 [7:54:24<10:46:38,  3.44it/s]
 64%|██████▍   | 237987/371472 [7:54:24<10:15:18,  3.62it/s]
 64%|██████▍   | 237988/371472 [7:54:25<9:58:25,  3.72it/s] 
 64%|██████▍   | 237989/371472 [7:54:25<9:55:42,  3.73it/s]
 64%|██████▍   | 237990/371472 [7:54:25<10:19:01,  3.59it/s]
 64%|██████▍   | 237991/371472 [7:54:25<10:22:25,  3.57it/s]
 64%|██████▍   | 237992/371472 [7:54:26<10:03:05,  3.69it/s]
 64%|██████▍   | 237993/371472 [7:54:26<10:12:05,  3.63it/s]
 64%|██████▍   | 237994/371472 [7:54:26<10:35:52,  3.50it/s]
 64%|██████▍   | 237995/371472 [7:54:27<10:57:25,  3.38it/s]
 64%|██████▍   | 237996/371472 [7:54:27<10:59:45,  3.37it/s]
 64%|██████▍   | 237997/371472 [7:54:27<10:38:45,  3.48it/s]
 64%|██████▍   | 237998/371472 [7:54:27<10:37:54,  3.49it/s]
 64%|██████▍   | 237999/371472 [7:54:28<10:26:36,  3.55it/s]
 64%|██████▍   | 238000/371472 [7:54:28<10:17:51,  3.60it/s]
                                                            
{'loss': 2.7165, 'learning_rate': 4.2354931155594816e-07, 'epoch': 10.25}
+
 64%|██████▍   | 238000/371472 [7:54:28<10:17:51,  3.60it/s]
 64%|██████▍   | 238001/371472 [7:54:28<10:08:36,  3.66it/s]
 64%|██████▍   | 238002/371472 [7:54:28<10:01:04,  3.70it/s]
 64%|██████▍   | 238003/371472 [7:54:29<9:40:15,  3.83it/s] 
 64%|██████▍   | 238004/371472 [7:54:29<9:23:27,  3.95it/s]
 64%|██████▍   | 238005/371472 [7:54:29<9:35:15,  3.87it/s]
 64%|██████▍   | 238006/371472 [7:54:29<9:49:44,  3.77it/s]
 64%|██████▍   | 238007/371472 [7:54:30<10:22:48,  3.57it/s]
 64%|██████▍   | 238008/371472 [7:54:30<10:09:23,  3.65it/s]
 64%|██████▍   | 238009/371472 [7:54:30<9:49:14,  3.77it/s] 
 64%|██████▍   | 238010/371472 [7:54:31<9:48:45,  3.78it/s]
 64%|██████▍   | 238011/371472 [7:54:31<10:00:19,  3.71it/s]
 64%|██████▍   | 238012/371472 [7:54:31<10:47:36,  3.43it/s]
 64%|██████▍   | 238013/371472 [7:54:31<10:46:18,  3.44it/s]
 64%|██████▍   | 238014/371472 [7:54:32<10:23:57,  3.56it/s]
 64%|██████▍   | 238015/371472 [7:54:32<10:20:31,  3.58it/s]
 64%|██████▍   | 238016/371472 [7:54:32<11:01:18,  3.36it/s]
 64%|██████▍   | 238017/371472 [7:54:33<10:42:13,  3.46it/s]
 64%|██████▍   | 238018/371472 [7:54:33<10:20:13,  3.59it/s]
 64%|██████▍   | 238019/371472 [7:54:33<10:13:59,  3.62it/s]
 64%|██████▍   | 238020/371472 [7:54:33<10:24:12,  3.56it/s]
                                                            
{'loss': 2.9093, 'learning_rate': 4.235008295804693e-07, 'epoch': 10.25}
+
 64%|██████▍   | 238020/371472 [7:54:33<10:24:12,  3.56it/s]
 64%|██████▍   | 238021/371472 [7:54:34<10:42:51,  3.46it/s]
 64%|██████▍   | 238022/371472 [7:54:34<10:21:37,  3.58it/s]
 64%|██████▍   | 238023/371472 [7:54:34<10:56:05,  3.39it/s]
 64%|██████▍   | 238024/371472 [7:54:35<10:31:53,  3.52it/s]
 64%|██████▍   | 238025/371472 [7:54:35<10:03:13,  3.69it/s]
 64%|██████▍   | 238026/371472 [7:54:35<10:01:40,  3.70it/s]
 64%|██████▍   | 238027/371472 [7:54:35<10:04:01,  3.68it/s]
 64%|██████▍   | 238028/371472 [7:54:36<9:53:46,  3.75it/s] 
 64%|██████▍   | 238029/371472 [7:54:36<11:33:12,  3.21it/s]
 64%|██████▍   | 238030/371472 [7:54:36<11:09:15,  3.32it/s]
 64%|██████▍   | 238031/371472 [7:54:37<10:56:46,  3.39it/s]
 64%|██████▍   | 238032/371472 [7:54:37<10:50:01,  3.42it/s]
 64%|██████▍   | 238033/371472 [7:54:37<10:38:29,  3.48it/s]
 64%|██████▍   | 238034/371472 [7:54:37<10:35:45,  3.50it/s]
 64%|██████▍   | 238035/371472 [7:54:38<10:34:14,  3.51it/s]
 64%|██████▍   | 238036/371472 [7:54:38<10:21:51,  3.58it/s]
 64%|██████▍   | 238037/371472 [7:54:38<10:02:16,  3.69it/s]
 64%|██████▍   | 238038/371472 [7:54:38<10:01:45,  3.70it/s]
 64%|██████▍   | 238039/371472 [7:54:39<10:07:45,  3.66it/s]
 64%|██████▍   | 238040/371472 [7:54:39<10:12:59,  3.63it/s]
                                                            
{'loss': 2.8954, 'learning_rate': 4.2345234760499036e-07, 'epoch': 10.25}
+
 64%|██████▍   | 238040/371472 [7:54:39<10:12:59,  3.63it/s]
 64%|██████▍   | 238041/371472 [7:54:39<10:20:43,  3.58it/s]
 64%|██████▍   | 238042/371472 [7:54:40<10:19:16,  3.59it/s]
 64%|██████▍   | 238043/371472 [7:54:40<10:10:09,  3.64it/s]
 64%|██████▍   | 238044/371472 [7:54:40<10:02:42,  3.69it/s]
 64%|██████▍   | 238045/371472 [7:54:40<10:07:43,  3.66it/s]
 64%|██████▍   | 238046/371472 [7:54:41<9:52:05,  3.76it/s] 
 64%|██████▍   | 238047/371472 [7:54:41<9:57:28,  3.72it/s]
 64%|██████▍   | 238048/371472 [7:54:41<9:45:37,  3.80it/s]
 64%|██████▍   | 238049/371472 [7:54:42<10:14:34,  3.62it/s]
 64%|██████▍   | 238050/371472 [7:54:42<11:43:39,  3.16it/s]
 64%|██████▍   | 238051/371472 [7:54:42<11:47:53,  3.14it/s]
 64%|██████▍   | 238052/371472 [7:54:43<11:45:36,  3.15it/s]
 64%|██████▍   | 238053/371472 [7:54:43<11:22:06,  3.26it/s]
 64%|██████▍   | 238054/371472 [7:54:43<11:09:17,  3.32it/s]
 64%|██████▍   | 238055/371472 [7:54:43<11:22:47,  3.26it/s]
 64%|██████▍   | 238056/371472 [7:54:44<10:49:17,  3.42it/s]
 64%|██████▍   | 238057/371472 [7:54:44<11:22:58,  3.26it/s]
 64%|██████▍   | 238058/371472 [7:54:44<10:45:33,  3.44it/s]
 64%|██████▍   | 238059/371472 [7:54:45<10:53:06,  3.40it/s]
 64%|██████▍   | 238060/371472 [7:54:45<10:28:05,  3.54it/s]
                                                            
{'loss': 2.8393, 'learning_rate': 4.2340386562951154e-07, 'epoch': 10.25}
+
 64%|██████▍   | 238060/371472 [7:54:45<10:28:05,  3.54it/s]
 64%|██████▍   | 238061/371472 [7:54:45<10:13:16,  3.63it/s]
 64%|██████▍   | 238062/371472 [7:54:45<9:48:48,  3.78it/s] 
 64%|██████▍   | 238063/371472 [7:54:46<10:01:28,  3.70it/s]
 64%|██████▍   | 238064/371472 [7:54:46<11:10:15,  3.32it/s]
 64%|██████▍   | 238065/371472 [7:54:46<11:52:31,  3.12it/s]
 64%|██████▍   | 238066/371472 [7:54:47<11:37:09,  3.19it/s]
 64%|██████▍   | 238067/371472 [7:54:47<11:23:37,  3.25it/s]
 64%|██████▍   | 238068/371472 [7:54:47<10:57:52,  3.38it/s]
 64%|██████▍   | 238069/371472 [7:54:48<11:20:14,  3.27it/s]
 64%|██████▍   | 238070/371472 [7:54:48<11:10:12,  3.32it/s]
 64%|██████▍   | 238071/371472 [7:54:48<11:11:06,  3.31it/s]
 64%|██████▍   | 238072/371472 [7:54:48<11:26:59,  3.24it/s]
 64%|██████▍   | 238073/371472 [7:54:49<11:36:07,  3.19it/s]
 64%|██████▍   | 238074/371472 [7:54:49<11:03:45,  3.35it/s]
 64%|██████▍   | 238075/371472 [7:54:49<10:35:34,  3.50it/s]
 64%|██████▍   | 238076/371472 [7:54:50<10:43:17,  3.46it/s]
 64%|██████▍   | 238077/371472 [7:54:50<10:37:11,  3.49it/s]
 64%|██████▍   | 238078/371472 [7:54:50<10:18:34,  3.59it/s]
 64%|██████▍   | 238079/371472 [7:54:50<10:01:31,  3.70it/s]
 64%|██████▍   | 238080/371472 [7:54:51<10:21:44,  3.58it/s]
                                                            
{'loss': 2.8791, 'learning_rate': 4.233553836540326e-07, 'epoch': 10.25}
+
 64%|██████▍   | 238080/371472 [7:54:51<10:21:44,  3.58it/s]
 64%|██████▍   | 238081/371472 [7:54:51<10:47:32,  3.43it/s]
 64%|██████▍   | 238082/371472 [7:54:51<10:24:03,  3.56it/s]
 64%|██████▍   | 238083/371472 [7:54:52<10:23:59,  3.56it/s]
 64%|██████▍   | 238084/371472 [7:54:52<10:16:17,  3.61it/s]
 64%|██████▍   | 238085/371472 [7:54:52<10:07:29,  3.66it/s]
 64%|██████▍   | 238086/371472 [7:54:52<9:57:13,  3.72it/s] 
 64%|██████▍   | 238087/371472 [7:54:53<10:03:03,  3.69it/s]
 64%|██████▍   | 238088/371472 [7:54:53<10:58:53,  3.37it/s]
 64%|██████▍   | 238089/371472 [7:54:53<10:37:04,  3.49it/s]
 64%|██████▍   | 238090/371472 [7:54:54<10:29:48,  3.53it/s]
 64%|██████▍   | 238091/371472 [7:54:54<10:36:51,  3.49it/s]
 64%|██████▍   | 238092/371472 [7:54:54<10:49:11,  3.42it/s]
 64%|██████▍   | 238093/371472 [7:54:54<10:53:35,  3.40it/s]
 64%|██████▍   | 238094/371472 [7:54:55<11:09:55,  3.32it/s]
 64%|██████▍   | 238095/371472 [7:54:55<10:26:40,  3.55it/s]
 64%|██████▍   | 238096/371472 [7:54:55<10:31:24,  3.52it/s]
 64%|██████▍   | 238097/371472 [7:54:56<10:03:23,  3.68it/s]
 64%|██████▍   | 238098/371472 [7:54:56<9:41:47,  3.82it/s] 
 64%|██████▍   | 238099/371472 [7:54:56<9:40:11,  3.83it/s]
 64%|██████▍   | 238100/371472 [7:54:56<9:55:36,  3.73it/s]
                                                           
{'loss': 3.0217, 'learning_rate': 4.2330690167855373e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238100/371472 [7:54:56<9:55:36,  3.73it/s]
 64%|██████▍   | 238101/371472 [7:54:57<9:52:47,  3.75it/s]
 64%|██████▍   | 238102/371472 [7:54:57<9:54:29,  3.74it/s]
 64%|██████▍   | 238103/371472 [7:54:57<9:46:02,  3.79it/s]
 64%|██████▍   | 238104/371472 [7:54:57<10:00:45,  3.70it/s]
 64%|██████▍   | 238105/371472 [7:54:58<9:54:12,  3.74it/s] 
 64%|██████▍   | 238106/371472 [7:54:58<9:58:04,  3.72it/s]
 64%|██████▍   | 238107/371472 [7:54:58<10:00:56,  3.70it/s]
 64%|██████▍   | 238108/371472 [7:54:58<9:55:58,  3.73it/s] 
 64%|██████▍   | 238109/371472 [7:54:59<10:15:34,  3.61it/s]
 64%|██████▍   | 238110/371472 [7:54:59<10:00:19,  3.70it/s]
 64%|██████▍   | 238111/371472 [7:54:59<10:09:30,  3.65it/s]
 64%|██████▍   | 238112/371472 [7:55:00<9:52:12,  3.75it/s] 
 64%|██████▍   | 238113/371472 [7:55:00<9:30:47,  3.89it/s]
 64%|██████▍   | 238114/371472 [7:55:00<9:56:12,  3.73it/s]
 64%|██████▍   | 238115/371472 [7:55:00<10:07:23,  3.66it/s]
 64%|██████▍   | 238116/371472 [7:55:01<9:55:54,  3.73it/s] 
 64%|██████▍   | 238117/371472 [7:55:01<9:52:06,  3.75it/s]
 64%|██████▍   | 238118/371472 [7:55:01<9:57:08,  3.72it/s]
 64%|██████▍   | 238119/371472 [7:55:01<9:49:59,  3.77it/s]
 64%|██████▍   | 238120/371472 [7:55:02<10:04:36,  3.68it/s]
                                                            
{'loss': 2.7831, 'learning_rate': 4.232584197030748e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238120/371472 [7:55:02<10:04:36,  3.68it/s]
 64%|██████▍   | 238121/371472 [7:55:02<10:07:18,  3.66it/s]
 64%|██████▍   | 238122/371472 [7:55:02<10:11:12,  3.64it/s]
 64%|██████▍   | 238123/371472 [7:55:03<10:04:12,  3.68it/s]
 64%|██████▍   | 238124/371472 [7:55:03<9:56:42,  3.72it/s] 
 64%|██████▍   | 238125/371472 [7:55:03<10:13:31,  3.62it/s]
 64%|██████▍   | 238126/371472 [7:55:03<10:04:32,  3.68it/s]
 64%|██████▍   | 238127/371472 [7:55:04<9:56:00,  3.73it/s] 
 64%|██████▍   | 238128/371472 [7:55:04<10:17:04,  3.60it/s]
 64%|██████▍   | 238129/371472 [7:55:04<10:00:26,  3.70it/s]
 64%|██████▍   | 238130/371472 [7:55:05<11:10:12,  3.32it/s]
 64%|██████▍   | 238131/371472 [7:55:05<10:49:10,  3.42it/s]
 64%|██████▍   | 238132/371472 [7:55:05<10:33:29,  3.51it/s]
 64%|██████▍   | 238133/371472 [7:55:05<10:05:18,  3.67it/s]
 64%|██████▍   | 238134/371472 [7:55:06<10:07:00,  3.66it/s]
 64%|██████▍   | 238135/371472 [7:55:06<9:43:12,  3.81it/s] 
 64%|██████▍   | 238136/371472 [7:55:06<9:26:38,  3.92it/s]
 64%|██████▍   | 238137/371472 [7:55:06<10:07:25,  3.66it/s]
 64%|██████▍   | 238138/371472 [7:55:07<10:33:28,  3.51it/s]
 64%|██████▍   | 238139/371472 [7:55:07<10:18:50,  3.59it/s]
 64%|██████▍   | 238140/371472 [7:55:07<10:09:34,  3.65it/s]
                                                            
{'loss': 2.8808, 'learning_rate': 4.23209937727596e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238140/371472 [7:55:07<10:09:34,  3.65it/s]
 64%|██████▍   | 238141/371472 [7:55:07<10:16:36,  3.60it/s]
 64%|██████▍   | 238142/371472 [7:55:08<11:04:53,  3.34it/s]
 64%|██████▍   | 238143/371472 [7:55:08<11:17:16,  3.28it/s]
 64%|██████▍   | 238144/371472 [7:55:08<11:12:10,  3.31it/s]
 64%|██████▍   | 238145/371472 [7:55:09<10:49:23,  3.42it/s]
 64%|██████▍   | 238146/371472 [7:55:09<10:27:45,  3.54it/s]
 64%|██████▍   | 238147/371472 [7:55:09<10:08:34,  3.65it/s]
 64%|██████▍   | 238148/371472 [7:55:09<9:50:36,  3.76it/s] 
 64%|██████▍   | 238149/371472 [7:55:10<9:56:19,  3.73it/s]
 64%|██████▍   | 238150/371472 [7:55:10<10:05:11,  3.67it/s]
 64%|██████▍   | 238151/371472 [7:55:10<10:46:48,  3.44it/s]
 64%|██████▍   | 238152/371472 [7:55:11<10:42:12,  3.46it/s]
 64%|██████▍   | 238153/371472 [7:55:11<10:28:05,  3.54it/s]
 64%|██████▍   | 238154/371472 [7:55:11<11:06:36,  3.33it/s]
 64%|██████▍   | 238155/371472 [7:55:12<11:19:48,  3.27it/s]
 64%|██████▍   | 238156/371472 [7:55:12<11:10:35,  3.31it/s]
 64%|██████▍   | 238157/371472 [7:55:12<11:24:07,  3.25it/s]
 64%|██████▍   | 238158/371472 [7:55:12<11:01:28,  3.36it/s]
 64%|██████▍   | 238159/371472 [7:55:13<10:45:12,  3.44it/s]
 64%|██████▍   | 238160/371472 [7:55:13<10:24:32,  3.56it/s]
                                                            
{'loss': 2.7111, 'learning_rate': 4.23161455752117e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238160/371472 [7:55:13<10:24:32,  3.56it/s]
 64%|██████▍   | 238161/371472 [7:55:13<11:59:15,  3.09it/s]
 64%|██████▍   | 238162/371472 [7:55:14<11:06:32,  3.33it/s]
 64%|██████▍   | 238163/371472 [7:55:14<10:45:44,  3.44it/s]
 64%|██████▍   | 238164/371472 [7:55:14<10:20:49,  3.58it/s]
 64%|██████▍   | 238165/371472 [7:55:14<10:33:21,  3.51it/s]
 64%|██████▍   | 238166/371472 [7:55:15<10:25:25,  3.55it/s]
 64%|██████▍   | 238167/371472 [7:55:15<10:11:45,  3.63it/s]
 64%|██████▍   | 238168/371472 [7:55:15<9:56:26,  3.72it/s] 
 64%|██████▍   | 238169/371472 [7:55:16<9:49:54,  3.77it/s]
 64%|██████▍   | 238170/371472 [7:55:16<10:15:15,  3.61it/s]
 64%|██████▍   | 238171/371472 [7:55:16<11:02:09,  3.36it/s]
 64%|██████▍   | 238172/371472 [7:55:16<10:55:18,  3.39it/s]
 64%|██████▍   | 238173/371472 [7:55:17<10:44:04,  3.45it/s]
 64%|██████▍   | 238174/371472 [7:55:17<10:33:14,  3.51it/s]
 64%|██████▍   | 238175/371472 [7:55:17<10:30:32,  3.52it/s]
 64%|██████▍   | 238176/371472 [7:55:18<10:07:36,  3.66it/s]
 64%|██████▍   | 238177/371472 [7:55:18<10:03:54,  3.68it/s]
 64%|██████▍   | 238178/371472 [7:55:18<10:10:25,  3.64it/s]
 64%|██████▍   | 238179/371472 [7:55:18<10:01:32,  3.69it/s]
 64%|██████▍   | 238180/371472 [7:55:19<10:13:18,  3.62it/s]
                                                            
{'loss': 2.8857, 'learning_rate': 4.231129737766382e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238180/371472 [7:55:19<10:13:18,  3.62it/s]
 64%|██████▍   | 238181/371472 [7:55:19<10:02:58,  3.68it/s]
 64%|██████▍   | 238182/371472 [7:55:19<9:54:20,  3.74it/s] 
 64%|██████▍   | 238183/371472 [7:55:19<9:54:24,  3.74it/s]
 64%|██████▍   | 238184/371472 [7:55:20<10:15:55,  3.61it/s]
 64%|██████▍   | 238185/371472 [7:55:20<9:58:35,  3.71it/s] 
 64%|██████▍   | 238186/371472 [7:55:20<10:19:18,  3.59it/s]
 64%|██████▍   | 238187/371472 [7:55:21<9:56:32,  3.72it/s] 
 64%|██████▍   | 238188/371472 [7:55:21<10:04:34,  3.67it/s]
 64%|██████▍   | 238189/371472 [7:55:21<10:41:20,  3.46it/s]
 64%|██████▍   | 238190/371472 [7:55:21<10:56:39,  3.38it/s]
 64%|██████▍   | 238191/371472 [7:55:22<10:31:32,  3.52it/s]
 64%|██████▍   | 238192/371472 [7:55:22<11:12:55,  3.30it/s]
 64%|██████▍   | 238193/371472 [7:55:22<10:53:10,  3.40it/s]
 64%|██████▍   | 238194/371472 [7:55:23<10:53:10,  3.40it/s]
 64%|██████▍   | 238195/371472 [7:55:23<10:46:02,  3.44it/s]
 64%|██████▍   | 238196/371472 [7:55:23<11:11:01,  3.31it/s]
 64%|██████▍   | 238197/371472 [7:55:23<10:40:49,  3.47it/s]
 64%|██████▍   | 238198/371472 [7:55:24<10:19:54,  3.58it/s]
 64%|██████▍   | 238199/371472 [7:55:24<10:14:26,  3.61it/s]
 64%|██████▍   | 238200/371472 [7:55:24<10:03:09,  3.68it/s]
                                                            
{'loss': 2.7503, 'learning_rate': 4.2306449180115925e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238200/371472 [7:55:24<10:03:09,  3.68it/s]
 64%|██████▍   | 238201/371472 [7:55:25<10:01:09,  3.69it/s]
 64%|██████▍   | 238202/371472 [7:55:25<10:33:54,  3.50it/s]
 64%|██████▍   | 238203/371472 [7:55:25<10:46:33,  3.44it/s]
 64%|██████▍   | 238204/371472 [7:55:25<10:37:22,  3.48it/s]
 64%|██████▍   | 238205/371472 [7:55:26<10:39:58,  3.47it/s]
 64%|██████▍   | 238206/371472 [7:55:26<10:33:58,  3.50it/s]
 64%|██████▍   | 238207/371472 [7:55:26<10:40:54,  3.47it/s]
 64%|██████▍   | 238208/371472 [7:55:27<10:24:11,  3.56it/s]
 64%|██████▍   | 238209/371472 [7:55:27<10:29:14,  3.53it/s]
 64%|██████▍   | 238210/371472 [7:55:27<10:50:42,  3.41it/s]
 64%|██████▍   | 238211/371472 [7:55:27<10:36:37,  3.49it/s]
 64%|██████▍   | 238212/371472 [7:55:28<10:12:57,  3.62it/s]
 64%|██████▍   | 238213/371472 [7:55:28<9:50:53,  3.76it/s] 
 64%|██████▍   | 238214/371472 [7:55:28<9:43:23,  3.81it/s]
 64%|██████▍   | 238215/371472 [7:55:29<10:06:24,  3.66it/s]
 64%|██████▍   | 238216/371472 [7:55:29<9:52:22,  3.75it/s] 
 64%|██████▍   | 238217/371472 [7:55:29<10:07:06,  3.66it/s]
 64%|██████▍   | 238218/371472 [7:55:29<11:01:37,  3.36it/s]
 64%|██████▍   | 238219/371472 [7:55:30<10:31:33,  3.52it/s]
 64%|██████▍   | 238220/371472 [7:55:30<10:29:24,  3.53it/s]
                                                            
{'loss': 2.7815, 'learning_rate': 4.2301600982568037e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238220/371472 [7:55:30<10:29:24,  3.53it/s]
 64%|██████▍   | 238221/371472 [7:55:30<10:17:52,  3.59it/s]
 64%|██████▍   | 238222/371472 [7:55:30<10:08:40,  3.65it/s]
 64%|██████▍   | 238223/371472 [7:55:31<10:05:13,  3.67it/s]
 64%|██████▍   | 238224/371472 [7:55:31<10:17:53,  3.59it/s]
 64%|██████▍   | 238225/371472 [7:55:31<10:36:34,  3.49it/s]
 64%|██████▍   | 238226/371472 [7:55:32<11:27:21,  3.23it/s]
 64%|██████▍   | 238227/371472 [7:55:32<10:49:51,  3.42it/s]
 64%|██████▍   | 238228/371472 [7:55:32<10:59:47,  3.37it/s]
 64%|██████▍   | 238229/371472 [7:55:33<11:38:31,  3.18it/s]
 64%|██████▍   | 238230/371472 [7:55:33<11:43:19,  3.16it/s]
 64%|██████▍   | 238231/371472 [7:55:33<11:20:54,  3.26it/s]
 64%|██████▍   | 238232/371472 [7:55:33<11:03:46,  3.35it/s]
 64%|██████▍   | 238233/371472 [7:55:34<11:01:42,  3.36it/s]
 64%|██████▍   | 238234/371472 [7:55:34<10:37:22,  3.48it/s]
 64%|██████▍   | 238235/371472 [7:55:34<10:49:52,  3.42it/s]
 64%|██████▍   | 238236/371472 [7:55:35<10:16:58,  3.60it/s]
 64%|██████▍   | 238237/371472 [7:55:35<10:23:22,  3.56it/s]
 64%|██████▍   | 238238/371472 [7:55:35<10:36:01,  3.49it/s]
 64%|██████▍   | 238239/371472 [7:55:36<11:22:37,  3.25it/s]
 64%|██████▍   | 238240/371472 [7:55:36<11:01:16,  3.36it/s]
                                                            
{'loss': 2.7953, 'learning_rate': 4.2296752785020144e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238240/371472 [7:55:36<11:01:16,  3.36it/s]
 64%|██████▍   | 238241/371472 [7:55:36<11:18:42,  3.27it/s]
 64%|██████▍   | 238242/371472 [7:55:36<10:53:39,  3.40it/s]
 64%|██████▍   | 238243/371472 [7:55:37<10:40:04,  3.47it/s]
 64%|██████▍   | 238244/371472 [7:55:37<10:29:26,  3.53it/s]
 64%|██████▍   | 238245/371472 [7:55:37<10:27:00,  3.54it/s]
 64%|██████▍   | 238246/371472 [7:55:38<10:26:04,  3.55it/s]
 64%|██████▍   | 238247/371472 [7:55:38<10:32:27,  3.51it/s]
 64%|██████▍   | 238248/371472 [7:55:38<10:19:59,  3.58it/s]
 64%|██████▍   | 238249/371472 [7:55:38<10:05:17,  3.67it/s]
 64%|██████▍   | 238250/371472 [7:55:39<10:02:55,  3.68it/s]
 64%|██████▍   | 238251/371472 [7:55:39<10:05:44,  3.67it/s]
 64%|██████▍   | 238252/371472 [7:55:39<10:08:19,  3.65it/s]
 64%|██████▍   | 238253/371472 [7:55:39<10:13:15,  3.62it/s]
 64%|██████▍   | 238254/371472 [7:55:40<10:06:25,  3.66it/s]
 64%|██████▍   | 238255/371472 [7:55:40<9:49:51,  3.76it/s] 
 64%|██████▍   | 238256/371472 [7:55:40<10:01:40,  3.69it/s]
 64%|██████▍   | 238257/371472 [7:55:41<10:11:01,  3.63it/s]
 64%|██████▍   | 238258/371472 [7:55:41<9:53:30,  3.74it/s] 
 64%|██████▍   | 238259/371472 [7:55:41<10:21:48,  3.57it/s]
 64%|██████▍   | 238260/371472 [7:55:41<10:17:01,  3.60it/s]
                                                            
{'loss': 2.789, 'learning_rate': 4.229190458747226e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238260/371472 [7:55:41<10:17:01,  3.60it/s]
 64%|██████▍   | 238261/371472 [7:55:42<10:00:48,  3.70it/s]
 64%|██████▍   | 238262/371472 [7:55:42<9:52:50,  3.75it/s] 
 64%|██████▍   | 238263/371472 [7:55:42<9:58:21,  3.71it/s]
 64%|██████▍   | 238264/371472 [7:55:42<9:52:29,  3.75it/s]
 64%|██████▍   | 238265/371472 [7:55:43<10:00:24,  3.70it/s]
 64%|██████▍   | 238266/371472 [7:55:43<10:42:31,  3.46it/s]
 64%|██████▍   | 238267/371472 [7:55:43<11:25:11,  3.24it/s]
 64%|██████▍   | 238268/371472 [7:55:44<11:32:03,  3.21it/s]
 64%|██████▍   | 238269/371472 [7:55:44<11:22:02,  3.25it/s]
 64%|██████▍   | 238270/371472 [7:55:44<10:59:46,  3.36it/s]
 64%|██████▍   | 238271/371472 [7:55:45<11:27:20,  3.23it/s]
 64%|██████▍   | 238272/371472 [7:55:45<10:45:13,  3.44it/s]
 64%|██████▍   | 238273/371472 [7:55:45<10:13:15,  3.62it/s]
 64%|██████▍   | 238274/371472 [7:55:45<10:24:12,  3.56it/s]
 64%|██████▍   | 238275/371472 [7:55:46<10:16:35,  3.60it/s]
 64%|██████▍   | 238276/371472 [7:55:46<10:03:42,  3.68it/s]
 64%|██████▍   | 238277/371472 [7:55:46<9:57:15,  3.72it/s] 
 64%|██████▍   | 238278/371472 [7:55:46<10:30:44,  3.52it/s]
 64%|██████▍   | 238279/371472 [7:55:47<10:21:44,  3.57it/s]
 64%|██████▍   | 238280/371472 [7:55:47<10:42:56,  3.45it/s]
                                                            
{'loss': 2.9304, 'learning_rate': 4.2287056389924364e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238280/371472 [7:55:47<10:42:56,  3.45it/s]
 64%|██████▍   | 238281/371472 [7:55:47<11:08:01,  3.32it/s]
 64%|██████▍   | 238282/371472 [7:55:48<10:42:43,  3.45it/s]
 64%|██████▍   | 238283/371472 [7:55:48<11:17:14,  3.28it/s]
 64%|██████▍   | 238284/371472 [7:55:48<10:56:39,  3.38it/s]
 64%|██████▍   | 238285/371472 [7:55:49<10:58:55,  3.37it/s]
 64%|██████▍   | 238286/371472 [7:55:49<10:33:59,  3.50it/s]
 64%|██████▍   | 238287/371472 [7:55:49<11:08:57,  3.32it/s]
 64%|██████▍   | 238288/371472 [7:55:49<10:33:25,  3.50it/s]
 64%|██████▍   | 238289/371472 [7:55:50<11:25:12,  3.24it/s]
 64%|██████▍   | 238290/371472 [7:55:50<12:15:20,  3.02it/s]
 64%|██████▍   | 238291/371472 [7:55:50<11:34:49,  3.19it/s]
 64%|██████▍   | 238292/371472 [7:55:51<11:04:38,  3.34it/s]
 64%|██████▍   | 238293/371472 [7:55:51<11:24:16,  3.24it/s]
 64%|██████▍   | 238294/371472 [7:55:51<10:58:37,  3.37it/s]
 64%|██████▍   | 238295/371472 [7:55:52<10:35:39,  3.49it/s]
 64%|██████▍   | 238296/371472 [7:55:52<10:28:57,  3.53it/s]
 64%|██████▍   | 238297/371472 [7:55:52<10:16:11,  3.60it/s]
 64%|██████▍   | 238298/371472 [7:55:52<10:09:43,  3.64it/s]
 64%|██████▍   | 238299/371472 [7:55:53<10:24:00,  3.56it/s]
 64%|██████▍   | 238300/371472 [7:55:53<10:13:48,  3.62it/s]
                                                            
{'loss': 2.738, 'learning_rate': 4.228220819237648e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238300/371472 [7:55:53<10:13:48,  3.62it/s]
 64%|██████▍   | 238301/371472 [7:55:53<10:29:43,  3.52it/s]
 64%|██████▍   | 238302/371472 [7:55:54<10:15:49,  3.60it/s]
 64%|██████▍   | 238303/371472 [7:55:54<10:05:46,  3.66it/s]
 64%|██████▍   | 238304/371472 [7:55:54<10:00:32,  3.70it/s]
 64%|██████▍   | 238305/371472 [7:55:54<9:50:49,  3.76it/s] 
 64%|██████▍   | 238306/371472 [7:55:55<9:46:32,  3.78it/s]
 64%|██████▍   | 238307/371472 [7:55:55<9:46:32,  3.78it/s]
 64%|██████▍   | 238308/371472 [7:55:55<9:45:24,  3.79it/s]
 64%|██████▍   | 238309/371472 [7:55:55<9:49:40,  3.76it/s]
 64%|██████▍   | 238310/371472 [7:55:56<10:26:56,  3.54it/s]
 64%|██████▍   | 238311/371472 [7:55:56<10:31:33,  3.51it/s]
 64%|██████▍   | 238312/371472 [7:55:56<10:31:15,  3.52it/s]
 64%|██████▍   | 238313/371472 [7:55:57<10:18:26,  3.59it/s]
 64%|██████▍   | 238314/371472 [7:55:57<10:06:39,  3.66it/s]
 64%|██████▍   | 238315/371472 [7:55:57<10:32:08,  3.51it/s]
 64%|██████▍   | 238316/371472 [7:55:57<10:24:02,  3.56it/s]
 64%|██████▍   | 238317/371472 [7:55:58<10:47:40,  3.43it/s]
 64%|██████▍   | 238318/371472 [7:55:58<10:22:53,  3.56it/s]
 64%|██████▍   | 238319/371472 [7:55:58<10:18:33,  3.59it/s]
 64%|██████▍   | 238320/371472 [7:55:59<11:19:43,  3.26it/s]
                                                            
{'loss': 2.8329, 'learning_rate': 4.227735999482859e-07, 'epoch': 10.26}
+
 64%|██████▍   | 238320/371472 [7:55:59<11:19:43,  3.26it/s]
 64%|██████▍   | 238321/371472 [7:55:59<11:05:06,  3.34it/s]
 64%|██████▍   | 238322/371472 [7:55:59<10:38:53,  3.47it/s]
 64%|██████▍   | 238323/371472 [7:55:59<10:23:56,  3.56it/s]
 64%|██████▍   | 238324/371472 [7:56:00<12:00:43,  3.08it/s]
 64%|██████▍   | 238325/371472 [7:56:00<11:11:47,  3.30it/s]
 64%|██████▍   | 238326/371472 [7:56:00<10:51:24,  3.41it/s]
 64%|██████▍   | 238327/371472 [7:56:01<10:38:31,  3.48it/s]
 64%|██████▍   | 238328/371472 [7:56:01<10:21:28,  3.57it/s]
 64%|██████▍   | 238329/371472 [7:56:01<10:11:05,  3.63it/s]
 64%|██████▍   | 238330/371472 [7:56:01<10:13:42,  3.62it/s]
 64%|██████▍   | 238331/371472 [7:56:02<10:33:50,  3.50it/s]
 64%|██████▍   | 238332/371472 [7:56:02<10:56:31,  3.38it/s]
 64%|██████▍   | 238333/371472 [7:56:02<10:31:32,  3.51it/s]
 64%|██████▍   | 238334/371472 [7:56:03<10:22:22,  3.57it/s]
 64%|██████▍   | 238335/371472 [7:56:03<10:09:04,  3.64it/s]
 64%|██████▍   | 238336/371472 [7:56:03<10:07:15,  3.65it/s]
 64%|██████▍   | 238337/371472 [7:56:03<10:28:53,  3.53it/s]
 64%|██████▍   | 238338/371472 [7:56:04<10:27:32,  3.54it/s]
 64%|██████▍   | 238339/371472 [7:56:04<10:31:17,  3.51it/s]
 64%|██████▍   | 238340/371472 [7:56:04<10:19:16,  3.58it/s]
                                                            
{'loss': 2.9862, 'learning_rate': 4.227251179728069e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238340/371472 [7:56:04<10:19:16,  3.58it/s]
 64%|██████▍   | 238341/371472 [7:56:05<10:11:40,  3.63it/s]
 64%|██████▍   | 238342/371472 [7:56:05<10:38:41,  3.47it/s]
 64%|██████▍   | 238343/371472 [7:56:05<10:38:56,  3.47it/s]
 64%|██████▍   | 238344/371472 [7:56:05<10:21:03,  3.57it/s]
 64%|██████▍   | 238345/371472 [7:56:06<10:43:01,  3.45it/s]
 64%|██████▍   | 238346/371472 [7:56:06<10:42:06,  3.46it/s]
 64%|██████▍   | 238347/371472 [7:56:06<10:36:46,  3.48it/s]
 64%|██████▍   | 238348/371472 [7:56:07<11:08:50,  3.32it/s]
 64%|██████▍   | 238349/371472 [7:56:07<10:54:28,  3.39it/s]
 64%|██████▍   | 238350/371472 [7:56:07<10:29:26,  3.52it/s]
 64%|██████▍   | 238351/371472 [7:56:07<10:28:44,  3.53it/s]
 64%|██████▍   | 238352/371472 [7:56:08<13:11:00,  2.80it/s]
 64%|██████▍   | 238353/371472 [7:56:08<12:20:41,  3.00it/s]
 64%|██████▍   | 238354/371472 [7:56:09<12:47:25,  2.89it/s]
 64%|██████▍   | 238355/371472 [7:56:09<12:17:29,  3.01it/s]
 64%|██████▍   | 238356/371472 [7:56:09<11:44:22,  3.15it/s]
 64%|██████▍   | 238357/371472 [7:56:09<11:18:11,  3.27it/s]
 64%|██████▍   | 238358/371472 [7:56:10<11:02:09,  3.35it/s]
 64%|██████▍   | 238359/371472 [7:56:10<10:22:29,  3.56it/s]
 64%|██████▍   | 238360/371472 [7:56:10<11:04:29,  3.34it/s]
                                                            
{'loss': 2.9572, 'learning_rate': 4.2267663599732803e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238360/371472 [7:56:10<11:04:29,  3.34it/s]
 64%|██████▍   | 238361/371472 [7:56:11<10:46:33,  3.43it/s]
 64%|██████▍   | 238362/371472 [7:56:11<10:26:02,  3.54it/s]
 64%|██████▍   | 238363/371472 [7:56:11<10:01:09,  3.69it/s]
 64%|██████▍   | 238364/371472 [7:56:11<9:44:15,  3.80it/s] 
 64%|██████▍   | 238365/371472 [7:56:12<9:52:50,  3.74it/s]
 64%|██████▍   | 238366/371472 [7:56:12<9:49:21,  3.76it/s]
 64%|██████▍   | 238367/371472 [7:56:12<9:48:54,  3.77it/s]
 64%|██████▍   | 238368/371472 [7:56:12<9:31:33,  3.88it/s]
 64%|██████▍   | 238369/371472 [7:56:13<9:28:25,  3.90it/s]
 64%|██████▍   | 238370/371472 [7:56:13<9:23:18,  3.94it/s]
 64%|██████▍   | 238371/371472 [7:56:13<9:30:11,  3.89it/s]
 64%|██████▍   | 238372/371472 [7:56:13<9:39:49,  3.83it/s]
 64%|██████▍   | 238373/371472 [7:56:14<9:46:33,  3.78it/s]
 64%|██████▍   | 238374/371472 [7:56:14<9:41:01,  3.82it/s]
 64%|██████▍   | 238375/371472 [7:56:14<10:11:48,  3.63it/s]
 64%|██████▍   | 238376/371472 [7:56:15<10:17:13,  3.59it/s]
 64%|██████▍   | 238377/371472 [7:56:15<10:26:08,  3.54it/s]
 64%|██████▍   | 238378/371472 [7:56:15<10:26:55,  3.54it/s]
 64%|██████▍   | 238379/371472 [7:56:15<10:20:12,  3.58it/s]
 64%|██████▍   | 238380/371472 [7:56:16<10:25:07,  3.55it/s]
                                                            
{'loss': 2.8613, 'learning_rate': 4.2262815402184916e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238380/371472 [7:56:16<10:25:07,  3.55it/s]
 64%|██████▍   | 238381/371472 [7:56:16<11:23:21,  3.25it/s]
 64%|██████▍   | 238382/371472 [7:56:16<11:17:28,  3.27it/s]
 64%|██████▍   | 238383/371472 [7:56:17<10:43:47,  3.45it/s]
 64%|██████▍   | 238384/371472 [7:56:17<10:41:04,  3.46it/s]
 64%|██████▍   | 238385/371472 [7:56:17<10:29:34,  3.52it/s]
 64%|██████▍   | 238386/371472 [7:56:17<10:03:53,  3.67it/s]
 64%|██████▍   | 238387/371472 [7:56:18<9:54:24,  3.73it/s] 
 64%|██████▍   | 238388/371472 [7:56:18<9:53:13,  3.74it/s]
 64%|██████▍   | 238389/371472 [7:56:18<10:37:15,  3.48it/s]
 64%|██████▍   | 238390/371472 [7:56:19<10:30:32,  3.52it/s]
 64%|██████▍   | 238391/371472 [7:56:19<11:24:49,  3.24it/s]
 64%|██████▍   | 238392/371472 [7:56:19<11:26:13,  3.23it/s]
 64%|██████▍   | 238393/371472 [7:56:20<11:27:55,  3.22it/s]
 64%|██████▍   | 238394/371472 [7:56:20<11:53:40,  3.11it/s]
 64%|██████▍   | 238395/371472 [7:56:20<11:30:43,  3.21it/s]
 64%|██████▍   | 238396/371472 [7:56:20<11:25:54,  3.23it/s]
 64%|██████▍   | 238397/371472 [7:56:21<11:09:59,  3.31it/s]
 64%|██████▍   | 238398/371472 [7:56:21<11:04:33,  3.34it/s]
 64%|██████▍   | 238399/371472 [7:56:21<10:37:00,  3.48it/s]
 64%|██████▍   | 238400/371472 [7:56:22<11:01:28,  3.35it/s]
                                                            
{'loss': 2.8694, 'learning_rate': 4.225796720463703e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238400/371472 [7:56:22<11:01:28,  3.35it/s]
 64%|██████▍   | 238401/371472 [7:56:22<11:37:24,  3.18it/s]
 64%|██████▍   | 238402/371472 [7:56:22<11:14:34,  3.29it/s]
 64%|██████▍   | 238403/371472 [7:56:23<10:49:22,  3.42it/s]
 64%|██████▍   | 238404/371472 [7:56:23<10:51:04,  3.41it/s]
 64%|██████▍   | 238405/371472 [7:56:23<10:24:04,  3.55it/s]
 64%|██████▍   | 238406/371472 [7:56:23<10:04:59,  3.67it/s]
 64%|██████▍   | 238407/371472 [7:56:24<9:58:19,  3.71it/s] 
 64%|██████▍   | 238408/371472 [7:56:24<10:12:35,  3.62it/s]
 64%|██████▍   | 238409/371472 [7:56:24<10:00:35,  3.69it/s]
 64%|██████▍   | 238410/371472 [7:56:24<9:58:39,  3.70it/s] 
 64%|██████▍   | 238411/371472 [7:56:25<9:59:50,  3.70it/s]
 64%|██████▍   | 238412/371472 [7:56:25<10:03:57,  3.67it/s]
 64%|██████▍   | 238413/371472 [7:56:25<9:45:13,  3.79it/s] 
 64%|██████▍   | 238414/371472 [7:56:26<10:42:30,  3.45it/s]
 64%|██████▍   | 238415/371472 [7:56:26<10:29:47,  3.52it/s]
 64%|██████▍   | 238416/371472 [7:56:26<10:04:58,  3.67it/s]
 64%|██████▍   | 238417/371472 [7:56:26<10:37:32,  3.48it/s]
 64%|██████▍   | 238418/371472 [7:56:27<10:17:03,  3.59it/s]
 64%|██████▍   | 238419/371472 [7:56:27<10:15:54,  3.60it/s]
 64%|██████▍   | 238420/371472 [7:56:27<10:15:59,  3.60it/s]
                                                            
{'loss': 2.9938, 'learning_rate': 4.2253119007089135e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238420/371472 [7:56:27<10:15:59,  3.60it/s]
 64%|██████▍   | 238421/371472 [7:56:27<10:10:12,  3.63it/s]
 64%|██████▍   | 238422/371472 [7:56:28<10:42:39,  3.45it/s]
 64%|██████▍   | 238423/371472 [7:56:28<10:14:01,  3.61it/s]
 64%|██████▍   | 238424/371472 [7:56:28<11:08:13,  3.32it/s]
 64%|██████▍   | 238425/371472 [7:56:29<10:52:20,  3.40it/s]
 64%|██████▍   | 238426/371472 [7:56:29<10:26:03,  3.54it/s]
 64%|██████▍   | 238427/371472 [7:56:29<10:54:01,  3.39it/s]
 64%|██████▍   | 238428/371472 [7:56:30<10:42:46,  3.45it/s]
 64%|██████▍   | 238429/371472 [7:56:30<11:19:19,  3.26it/s]
 64%|██████▍   | 238430/371472 [7:56:30<11:14:54,  3.29it/s]
 64%|██████▍   | 238431/371472 [7:56:30<10:43:08,  3.45it/s]
 64%|██████▍   | 238432/371472 [7:56:31<11:04:26,  3.34it/s]
 64%|██████▍   | 238433/371472 [7:56:31<10:34:51,  3.49it/s]
 64%|██████▍   | 238434/371472 [7:56:31<11:32:31,  3.20it/s]
 64%|██████▍   | 238435/371472 [7:56:32<10:52:33,  3.40it/s]
 64%|██████▍   | 238436/371472 [7:56:32<11:06:41,  3.33it/s]
 64%|██████▍   | 238437/371472 [7:56:32<10:48:53,  3.42it/s]
 64%|██████▍   | 238438/371472 [7:56:32<10:34:34,  3.49it/s]
 64%|██████▍   | 238439/371472 [7:56:33<10:33:44,  3.50it/s]
 64%|██████▍   | 238440/371472 [7:56:33<10:39:51,  3.47it/s]
                                                            
{'loss': 2.886, 'learning_rate': 4.2248270809541253e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238440/371472 [7:56:33<10:39:51,  3.47it/s]
 64%|██████▍   | 238441/371472 [7:56:33<10:21:06,  3.57it/s]
 64%|██████▍   | 238442/371472 [7:56:34<10:12:43,  3.62it/s]
 64%|██████▍   | 238443/371472 [7:56:34<10:11:18,  3.63it/s]
 64%|██████▍   | 238444/371472 [7:56:34<10:34:45,  3.49it/s]
 64%|██████▍   | 238445/371472 [7:56:34<10:31:11,  3.51it/s]
 64%|██████▍   | 238446/371472 [7:56:35<10:36:33,  3.48it/s]
 64%|██████▍   | 238447/371472 [7:56:35<10:24:20,  3.55it/s]
 64%|██████▍   | 238448/371472 [7:56:35<10:51:45,  3.40it/s]
 64%|██████▍   | 238449/371472 [7:56:36<10:44:55,  3.44it/s]
 64%|██████▍   | 238450/371472 [7:56:36<10:13:58,  3.61it/s]
 64%|██████▍   | 238451/371472 [7:56:36<10:14:08,  3.61it/s]
 64%|██████▍   | 238452/371472 [7:56:36<10:01:25,  3.69it/s]
 64%|██████▍   | 238453/371472 [7:56:37<10:39:15,  3.47it/s]
 64%|██████▍   | 238454/371472 [7:56:37<11:28:16,  3.22it/s]
 64%|██████▍   | 238455/371472 [7:56:37<11:33:34,  3.20it/s]
 64%|██████▍   | 238456/371472 [7:56:38<11:31:07,  3.21it/s]
 64%|██████▍   | 238457/371472 [7:56:38<11:23:55,  3.24it/s]
 64%|██████▍   | 238458/371472 [7:56:38<10:40:22,  3.46it/s]
 64%|██████▍   | 238459/371472 [7:56:39<10:14:39,  3.61it/s]
 64%|██████▍   | 238460/371472 [7:56:39<10:29:54,  3.52it/s]
                                                            
{'loss': 2.9385, 'learning_rate': 4.224342261199336e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238460/371472 [7:56:39<10:29:54,  3.52it/s]
 64%|██████▍   | 238461/371472 [7:56:39<10:07:22,  3.65it/s]
 64%|██████▍   | 238462/371472 [7:56:39<10:16:57,  3.59it/s]
 64%|██████▍   | 238463/371472 [7:56:40<10:05:33,  3.66it/s]
 64%|██████▍   | 238464/371472 [7:56:40<10:12:56,  3.62it/s]
 64%|██████▍   | 238465/371472 [7:56:40<10:38:31,  3.47it/s]
 64%|██████▍   | 238466/371472 [7:56:41<10:46:41,  3.43it/s]
 64%|██████▍   | 238467/371472 [7:56:41<10:52:23,  3.40it/s]
 64%|██████▍   | 238468/371472 [7:56:41<11:08:56,  3.31it/s]
 64%|██████▍   | 238469/371472 [7:56:41<11:19:20,  3.26it/s]
 64%|██████▍   | 238470/371472 [7:56:42<11:10:14,  3.31it/s]
 64%|██████▍   | 238471/371472 [7:56:42<10:47:23,  3.42it/s]
 64%|██████▍   | 238472/371472 [7:56:42<10:31:00,  3.51it/s]
 64%|██████▍   | 238473/371472 [7:56:43<10:26:50,  3.54it/s]
 64%|██████▍   | 238474/371472 [7:56:43<10:05:30,  3.66it/s]
 64%|██████▍   | 238475/371472 [7:56:43<10:14:33,  3.61it/s]
 64%|██████▍   | 238476/371472 [7:56:43<10:02:27,  3.68it/s]
 64%|██████▍   | 238477/371472 [7:56:44<10:13:32,  3.61it/s]
 64%|██████▍   | 238478/371472 [7:56:44<10:04:59,  3.66it/s]
 64%|██████▍   | 238479/371472 [7:56:44<10:45:21,  3.43it/s]
 64%|██████▍   | 238480/371472 [7:56:45<10:34:42,  3.49it/s]
                                                            
{'loss': 2.9256, 'learning_rate': 4.223857441444547e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238480/371472 [7:56:45<10:34:42,  3.49it/s]
 64%|██████▍   | 238481/371472 [7:56:45<10:21:20,  3.57it/s]
 64%|██████▍   | 238482/371472 [7:56:45<10:13:40,  3.61it/s]
 64%|██████▍   | 238483/371472 [7:56:45<10:05:00,  3.66it/s]
 64%|██████▍   | 238484/371472 [7:56:46<10:18:30,  3.58it/s]
 64%|██████▍   | 238485/371472 [7:56:46<10:52:10,  3.40it/s]
 64%|██████▍   | 238486/371472 [7:56:46<10:49:52,  3.41it/s]
 64%|██████▍   | 238487/371472 [7:56:47<10:59:33,  3.36it/s]
 64%|██████▍   | 238488/371472 [7:56:47<11:45:11,  3.14it/s]
 64%|██████▍   | 238489/371472 [7:56:47<11:18:36,  3.27it/s]
 64%|██████▍   | 238490/371472 [7:56:47<11:00:42,  3.35it/s]
 64%|██████▍   | 238491/371472 [7:56:48<10:21:11,  3.57it/s]
 64%|██████▍   | 238492/371472 [7:56:48<9:56:32,  3.72it/s] 
 64%|██████▍   | 238493/371472 [7:56:48<9:45:49,  3.78it/s]
 64%|██████▍   | 238494/371472 [7:56:48<10:01:05,  3.69it/s]
 64%|██████▍   | 238495/371472 [7:56:49<10:03:31,  3.67it/s]
 64%|██████▍   | 238496/371472 [7:56:49<10:10:52,  3.63it/s]
 64%|██████▍   | 238497/371472 [7:56:49<9:59:03,  3.70it/s] 
 64%|██████▍   | 238498/371472 [7:56:50<10:40:04,  3.46it/s]
 64%|██████▍   | 238499/371472 [7:56:50<10:43:02,  3.45it/s]
 64%|██████▍   | 238500/371472 [7:56:50<10:23:42,  3.55it/s]
                                                            
{'loss': 2.7134, 'learning_rate': 4.223372621689758e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238500/371472 [7:56:50<10:23:42,  3.55it/s]
 64%|██████▍   | 238501/371472 [7:56:50<10:19:06,  3.58it/s]
 64%|██████▍   | 238502/371472 [7:56:51<10:03:27,  3.67it/s]
 64%|██████▍   | 238503/371472 [7:56:51<9:52:17,  3.74it/s] 
 64%|██████▍   | 238504/371472 [7:56:51<10:02:02,  3.68it/s]
 64%|██████▍   | 238505/371472 [7:56:52<10:02:31,  3.68it/s]
 64%|██████▍   | 238506/371472 [7:56:52<9:50:03,  3.76it/s] 
 64%|██████▍   | 238507/371472 [7:56:52<9:51:52,  3.74it/s]
 64%|██████▍   | 238508/371472 [7:56:52<9:51:42,  3.75it/s]
 64%|██████▍   | 238509/371472 [7:56:53<9:58:18,  3.70it/s]
 64%|██████▍   | 238510/371472 [7:56:53<10:08:07,  3.64it/s]
 64%|██████▍   | 238511/371472 [7:56:53<10:29:19,  3.52it/s]
 64%|██████▍   | 238512/371472 [7:56:53<10:42:16,  3.45it/s]
 64%|██████▍   | 238513/371472 [7:56:54<10:27:13,  3.53it/s]
 64%|██████▍   | 238514/371472 [7:56:54<10:36:55,  3.48it/s]
 64%|██████▍   | 238515/371472 [7:56:54<10:17:04,  3.59it/s]
 64%|██████▍   | 238516/371472 [7:56:55<10:31:26,  3.51it/s]
 64%|██████▍   | 238517/371472 [7:56:55<10:02:45,  3.68it/s]
 64%|██████▍   | 238518/371472 [7:56:55<9:52:53,  3.74it/s] 
 64%|██████▍   | 238519/371472 [7:56:55<9:42:30,  3.80it/s]
 64%|██████▍   | 238520/371472 [7:56:56<10:05:03,  3.66it/s]
                                                            
{'loss': 2.839, 'learning_rate': 4.22288780193497e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238520/371472 [7:56:56<10:05:03,  3.66it/s]
 64%|██████▍   | 238521/371472 [7:56:56<9:50:58,  3.75it/s] 
 64%|██████▍   | 238522/371472 [7:56:56<10:16:42,  3.59it/s]
 64%|██████▍   | 238523/371472 [7:56:56<9:57:36,  3.71it/s] 
 64%|██████▍   | 238524/371472 [7:56:57<10:14:40,  3.60it/s]
 64%|██████▍   | 238525/371472 [7:56:57<10:05:49,  3.66it/s]
 64%|██████▍   | 238526/371472 [7:56:57<10:09:55,  3.63it/s]
 64%|██████▍   | 238527/371472 [7:56:58<10:03:04,  3.67it/s]
 64%|██████▍   | 238528/371472 [7:56:58<9:57:07,  3.71it/s] 
 64%|██████▍   | 238529/371472 [7:56:58<10:22:19,  3.56it/s]
 64%|██████▍   | 238530/371472 [7:56:58<9:50:34,  3.75it/s] 
 64%|██████▍   | 238531/371472 [7:56:59<10:32:59,  3.50it/s]
 64%|██████▍   | 238532/371472 [7:56:59<10:17:07,  3.59it/s]
 64%|██████▍   | 238533/371472 [7:56:59<10:03:22,  3.67it/s]
 64%|██████▍   | 238534/371472 [7:56:59<10:00:07,  3.69it/s]
 64%|██████▍   | 238535/371472 [7:57:00<9:57:39,  3.71it/s] 
 64%|██████▍   | 238536/371472 [7:57:00<9:54:18,  3.73it/s]
 64%|██████▍   | 238537/371472 [7:57:00<9:50:08,  3.75it/s]
 64%|██████▍   | 238538/371472 [7:57:01<10:15:17,  3.60it/s]
 64%|██████▍   | 238539/371472 [7:57:01<10:04:13,  3.67it/s]
 64%|██████▍   | 238540/371472 [7:57:01<10:44:03,  3.44it/s]
                                                            
{'loss': 3.1027, 'learning_rate': 4.22240298218018e-07, 'epoch': 10.27}
+
 64%|██████▍   | 238540/371472 [7:57:01<10:44:03,  3.44it/s]
 64%|██████▍   | 238541/371472 [7:57:01<10:18:04,  3.58it/s]
 64%|██████▍   | 238542/371472 [7:57:02<10:05:08,  3.66it/s]
 64%|██████▍   | 238543/371472 [7:57:02<10:01:51,  3.68it/s]
 64%|██████▍   | 238544/371472 [7:57:02<10:06:23,  3.65it/s]
 64%|██████▍   | 238545/371472 [7:57:03<10:07:02,  3.65it/s]
 64%|██████▍   | 238546/371472 [7:57:03<9:57:56,  3.71it/s] 
 64%|██████▍   | 238547/371472 [7:57:03<9:43:46,  3.79it/s]
 64%|██████▍   | 238548/371472 [7:57:03<9:52:28,  3.74it/s]
 64%|██████▍   | 238549/371472 [7:57:04<9:47:23,  3.77it/s]
 64%|██████▍   | 238550/371472 [7:57:04<9:31:28,  3.88it/s]
 64%|██████▍   | 238551/371472 [7:57:04<9:46:15,  3.78it/s]
 64%|██████▍   | 238552/371472 [7:57:04<9:48:23,  3.77it/s]
 64%|██████▍   | 238553/371472 [7:57:05<10:20:04,  3.57it/s]
 64%|██████▍   | 238554/371472 [7:57:05<10:35:52,  3.48it/s]
 64%|██████▍   | 238555/371472 [7:57:05<10:17:13,  3.59it/s]
 64%|██████▍   | 238556/371472 [7:57:06<10:36:30,  3.48it/s]
 64%|██████▍   | 238557/371472 [7:57:06<10:30:40,  3.51it/s]
 64%|██████▍   | 238558/371472 [7:57:06<11:22:05,  3.25it/s]
 64%|██████▍   | 238559/371472 [7:57:06<10:59:06,  3.36it/s]
 64%|██████▍   | 238560/371472 [7:57:07<10:52:55,  3.39it/s]
                                                            
{'loss': 2.8947, 'learning_rate': 4.2219181624253917e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238560/371472 [7:57:07<10:52:55,  3.39it/s]
 64%|██████▍   | 238561/371472 [7:57:07<10:23:36,  3.55it/s]
 64%|██████▍   | 238562/371472 [7:57:07<10:07:21,  3.65it/s]
 64%|██████▍   | 238563/371472 [7:57:08<10:01:19,  3.68it/s]
 64%|██████▍   | 238564/371472 [7:57:08<9:47:29,  3.77it/s] 
 64%|██████▍   | 238565/371472 [7:57:08<9:54:54,  3.72it/s]
 64%|██████▍   | 238566/371472 [7:57:08<9:45:27,  3.78it/s]
 64%|██████▍   | 238567/371472 [7:57:09<10:39:20,  3.46it/s]
 64%|██████▍   | 238568/371472 [7:57:09<10:45:58,  3.43it/s]
 64%|██████▍   | 238569/371472 [7:57:09<10:35:53,  3.48it/s]
 64%|██████▍   | 238570/371472 [7:57:09<10:26:42,  3.53it/s]
 64%|██████▍   | 238571/371472 [7:57:10<10:38:31,  3.47it/s]
 64%|██████▍   | 238572/371472 [7:57:10<10:22:02,  3.56it/s]
 64%|██████▍   | 238573/371472 [7:57:10<10:15:51,  3.60it/s]
 64%|██████▍   | 238574/371472 [7:57:11<9:56:26,  3.71it/s] 
 64%|██████▍   | 238575/371472 [7:57:11<10:13:37,  3.61it/s]
 64%|██████▍   | 238576/371472 [7:57:11<10:47:10,  3.42it/s]
 64%|██████▍   | 238577/371472 [7:57:11<10:50:36,  3.40it/s]
 64%|██████▍   | 238578/371472 [7:57:12<10:38:22,  3.47it/s]
 64%|██████▍   | 238579/371472 [7:57:12<10:24:15,  3.55it/s]
 64%|██████▍   | 238580/371472 [7:57:12<10:47:21,  3.42it/s]
                                                            
{'loss': 2.9289, 'learning_rate': 4.2214333426706024e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238580/371472 [7:57:12<10:47:21,  3.42it/s]
 64%|██████▍   | 238581/371472 [7:57:13<10:28:26,  3.52it/s]
 64%|██████▍   | 238582/371472 [7:57:13<10:09:31,  3.63it/s]
 64%|██████▍   | 238583/371472 [7:57:13<10:09:01,  3.64it/s]
 64%|██████▍   | 238584/371472 [7:57:13<10:21:27,  3.56it/s]
 64%|██████▍   | 238585/371472 [7:57:14<10:17:09,  3.59it/s]
 64%|██████▍   | 238586/371472 [7:57:14<10:10:57,  3.63it/s]
 64%|██████▍   | 238587/371472 [7:57:14<10:06:09,  3.65it/s]
 64%|██████▍   | 238588/371472 [7:57:15<10:28:38,  3.52it/s]
 64%|██████▍   | 238589/371472 [7:57:15<10:02:39,  3.67it/s]
 64%|██████▍   | 238590/371472 [7:57:15<9:48:56,  3.76it/s] 
 64%|██████▍   | 238591/371472 [7:57:15<10:26:16,  3.54it/s]
 64%|██████▍   | 238592/371472 [7:57:16<10:09:43,  3.63it/s]
 64%|██████▍   | 238593/371472 [7:57:16<10:54:15,  3.38it/s]
 64%|██████▍   | 238594/371472 [7:57:16<11:14:18,  3.28it/s]
 64%|██████▍   | 238595/371472 [7:57:17<11:09:15,  3.31it/s]
 64%|██████▍   | 238596/371472 [7:57:17<10:53:28,  3.39it/s]
 64%|██████▍   | 238597/371472 [7:57:17<10:55:05,  3.38it/s]
 64%|██████▍   | 238598/371472 [7:57:18<11:12:56,  3.29it/s]
 64%|██████▍   | 238599/371472 [7:57:18<11:29:35,  3.21it/s]
 64%|██████▍   | 238600/371472 [7:57:18<11:41:45,  3.16it/s]
                                                            
{'loss': 2.797, 'learning_rate': 4.2209485229158137e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238600/371472 [7:57:18<11:41:45,  3.16it/s]
 64%|██████▍   | 238601/371472 [7:57:18<11:33:14,  3.19it/s]
 64%|██████▍   | 238602/371472 [7:57:19<10:58:37,  3.36it/s]
 64%|██████▍   | 238603/371472 [7:57:19<10:21:41,  3.56it/s]
 64%|██████▍   | 238604/371472 [7:57:19<10:45:02,  3.43it/s]
 64%|██████▍   | 238605/371472 [7:57:20<10:19:55,  3.57it/s]
 64%|██████▍   | 238606/371472 [7:57:20<10:22:33,  3.56it/s]
 64%|██████▍   | 238607/371472 [7:57:20<10:46:12,  3.43it/s]
 64%|██████▍   | 238608/371472 [7:57:20<10:48:20,  3.42it/s]
 64%|██████▍   | 238609/371472 [7:57:21<10:27:22,  3.53it/s]
 64%|██████▍   | 238610/371472 [7:57:21<10:33:17,  3.50it/s]
 64%|██████▍   | 238611/371472 [7:57:21<10:04:40,  3.66it/s]
 64%|██████▍   | 238612/371472 [7:57:22<11:27:54,  3.22it/s]
 64%|██████▍   | 238613/371472 [7:57:22<10:48:16,  3.42it/s]
 64%|██████▍   | 238614/371472 [7:57:22<10:25:41,  3.54it/s]
 64%|██████▍   | 238615/371472 [7:57:22<10:18:50,  3.58it/s]
 64%|██████▍   | 238616/371472 [7:57:23<10:50:27,  3.40it/s]
 64%|██████▍   | 238617/371472 [7:57:23<10:49:08,  3.41it/s]
 64%|██████▍   | 238618/371472 [7:57:23<10:29:47,  3.52it/s]
 64%|██████▍   | 238619/371472 [7:57:24<10:23:51,  3.55it/s]
 64%|██████▍   | 238620/371472 [7:57:24<10:12:51,  3.61it/s]
                                                            
{'loss': 2.6879, 'learning_rate': 4.2204637031610244e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238620/371472 [7:57:24<10:12:51,  3.61it/s]
 64%|██████▍   | 238621/371472 [7:57:24<9:51:56,  3.74it/s] 
 64%|██████▍   | 238622/371472 [7:57:24<10:02:38,  3.67it/s]
 64%|██████▍   | 238623/371472 [7:57:25<10:34:07,  3.49it/s]
 64%|██████▍   | 238624/371472 [7:57:25<10:18:37,  3.58it/s]
 64%|██████▍   | 238625/371472 [7:57:25<10:29:26,  3.52it/s]
 64%|██████▍   | 238626/371472 [7:57:26<11:36:40,  3.18it/s]
 64%|██████▍   | 238627/371472 [7:57:26<11:17:52,  3.27it/s]
 64%|██████▍   | 238628/371472 [7:57:26<11:47:31,  3.13it/s]
 64%|██████▍   | 238629/371472 [7:57:27<11:14:48,  3.28it/s]
 64%|██████▍   | 238630/371472 [7:57:27<11:30:11,  3.21it/s]
 64%|██████▍   | 238631/371472 [7:57:27<11:00:01,  3.35it/s]
 64%|██████▍   | 238632/371472 [7:57:27<10:49:56,  3.41it/s]
 64%|██████▍   | 238633/371472 [7:57:28<10:38:10,  3.47it/s]
 64%|██████▍   | 238634/371472 [7:57:28<10:43:09,  3.44it/s]
 64%|██████▍   | 238635/371472 [7:57:28<11:05:04,  3.33it/s]
 64%|██████▍   | 238636/371472 [7:57:29<10:45:38,  3.43it/s]
 64%|██████▍   | 238637/371472 [7:57:29<10:54:39,  3.38it/s]
 64%|██████▍   | 238638/371472 [7:57:29<11:06:19,  3.32it/s]
 64%|██████▍   | 238639/371472 [7:57:30<11:24:25,  3.23it/s]
 64%|██████▍   | 238640/371472 [7:57:30<10:41:40,  3.45it/s]
                                                            
{'loss': 2.8615, 'learning_rate': 4.219978883406236e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238640/371472 [7:57:30<10:41:40,  3.45it/s]
 64%|██████▍   | 238641/371472 [7:57:30<10:40:59,  3.45it/s]
 64%|██████▍   | 238642/371472 [7:57:30<10:46:36,  3.42it/s]
 64%|██████▍   | 238643/371472 [7:57:31<10:17:14,  3.59it/s]
 64%|██████▍   | 238644/371472 [7:57:31<10:10:24,  3.63it/s]
 64%|██████▍   | 238645/371472 [7:57:31<11:19:17,  3.26it/s]
 64%|██████▍   | 238646/371472 [7:57:32<10:48:21,  3.41it/s]
 64%|██████▍   | 238647/371472 [7:57:32<10:25:47,  3.54it/s]
 64%|██████▍   | 238648/371472 [7:57:32<10:39:31,  3.46it/s]
 64%|██████▍   | 238649/371472 [7:57:32<10:23:20,  3.55it/s]
 64%|██████▍   | 238650/371472 [7:57:33<10:03:45,  3.67it/s]
 64%|██████▍   | 238651/371472 [7:57:33<10:18:54,  3.58it/s]
 64%|██████▍   | 238652/371472 [7:57:33<9:47:30,  3.77it/s] 
 64%|██████▍   | 238653/371472 [7:57:33<9:47:07,  3.77it/s]
 64%|██████▍   | 238654/371472 [7:57:34<10:37:07,  3.47it/s]
 64%|██████▍   | 238655/371472 [7:57:34<10:14:40,  3.60it/s]
 64%|██████▍   | 238656/371472 [7:57:34<10:09:42,  3.63it/s]
 64%|██████▍   | 238657/371472 [7:57:35<9:59:07,  3.69it/s] 
 64%|██████▍   | 238658/371472 [7:57:35<11:07:41,  3.32it/s]
 64%|██████▍   | 238659/371472 [7:57:35<11:22:35,  3.24it/s]
 64%|██████▍   | 238660/371472 [7:57:35<11:08:27,  3.31it/s]
                                                            
{'loss': 2.8147, 'learning_rate': 4.2194940636514463e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238660/371472 [7:57:35<11:08:27,  3.31it/s]
 64%|██████▍   | 238661/371472 [7:57:36<10:44:55,  3.43it/s]
 64%|██████▍   | 238662/371472 [7:57:36<10:40:34,  3.46it/s]
 64%|██████▍   | 238663/371472 [7:57:36<10:38:59,  3.46it/s]
 64%|██████▍   | 238664/371472 [7:57:37<10:28:21,  3.52it/s]
 64%|██████▍   | 238665/371472 [7:57:37<10:35:16,  3.48it/s]
 64%|██████▍   | 238666/371472 [7:57:37<10:14:40,  3.60it/s]
 64%|██████▍   | 238667/371472 [7:57:37<10:44:49,  3.43it/s]
 64%|██████▍   | 238668/371472 [7:57:38<10:36:46,  3.48it/s]
 64%|██████▍   | 238669/371472 [7:57:38<10:21:26,  3.56it/s]
 64%|██████▍   | 238670/371472 [7:57:38<10:16:17,  3.59it/s]
 64%|██████▍   | 238671/371472 [7:57:39<11:29:47,  3.21it/s]
 64%|██████▍   | 238672/371472 [7:57:39<11:03:15,  3.34it/s]
 64%|██████▍   | 238673/371472 [7:57:39<11:08:24,  3.31it/s]
 64%|██████▍   | 238674/371472 [7:57:40<11:10:57,  3.30it/s]
 64%|██████▍   | 238675/371472 [7:57:40<11:10:21,  3.30it/s]
 64%|██████▍   | 238676/371472 [7:57:40<11:54:37,  3.10it/s]
 64%|██████▍   | 238677/371472 [7:57:41<11:42:53,  3.15it/s]
 64%|██████▍   | 238678/371472 [7:57:41<11:41:58,  3.15it/s]
 64%|██████▍   | 238679/371472 [7:57:41<10:55:38,  3.38it/s]
 64%|██████▍   | 238680/371472 [7:57:41<10:54:21,  3.38it/s]
                                                            
{'loss': 2.8483, 'learning_rate': 4.219009243896658e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238680/371472 [7:57:41<10:54:21,  3.38it/s]
 64%|██████▍   | 238681/371472 [7:57:42<11:38:08,  3.17it/s]
 64%|██████▍   | 238682/371472 [7:57:42<12:09:59,  3.03it/s]
 64%|██████▍   | 238683/371472 [7:57:42<12:10:50,  3.03it/s]
 64%|██████▍   | 238684/371472 [7:57:43<11:32:04,  3.20it/s]
 64%|██████▍   | 238685/371472 [7:57:43<11:02:54,  3.34it/s]
 64%|██████▍   | 238686/371472 [7:57:43<10:25:03,  3.54it/s]
 64%|██████▍   | 238687/371472 [7:57:44<10:27:14,  3.53it/s]
 64%|██████▍   | 238688/371472 [7:57:44<10:30:59,  3.51it/s]
 64%|██████▍   | 238689/371472 [7:57:44<10:28:18,  3.52it/s]
 64%|██████▍   | 238690/371472 [7:57:44<10:11:34,  3.62it/s]
 64%|██████▍   | 238691/371472 [7:57:45<10:11:23,  3.62it/s]
 64%|██████▍   | 238692/371472 [7:57:45<10:07:54,  3.64it/s]
 64%|██████▍   | 238693/371472 [7:57:45<10:30:37,  3.51it/s]
 64%|██████▍   | 238694/371472 [7:57:45<10:28:33,  3.52it/s]
 64%|██████▍   | 238695/371472 [7:57:46<11:12:30,  3.29it/s]
 64%|██████▍   | 238696/371472 [7:57:46<10:42:45,  3.44it/s]
 64%|██████▍   | 238697/371472 [7:57:46<10:30:18,  3.51it/s]
 64%|██████▍   | 238698/371472 [7:57:47<11:17:49,  3.26it/s]
 64%|██████▍   | 238699/371472 [7:57:47<11:09:00,  3.31it/s]
 64%|██████▍   | 238700/371472 [7:57:47<10:33:23,  3.49it/s]
                                                            
{'loss': 2.999, 'learning_rate': 4.218524424141869e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238700/371472 [7:57:47<10:33:23,  3.49it/s]
 64%|██████▍   | 238701/371472 [7:57:48<10:12:57,  3.61it/s]
 64%|██████▍   | 238702/371472 [7:57:48<10:14:24,  3.60it/s]
 64%|██████▍   | 238703/371472 [7:57:48<10:22:00,  3.56it/s]
 64%|██████▍   | 238704/371472 [7:57:48<10:20:11,  3.57it/s]
 64%|██████▍   | 238705/371472 [7:57:49<10:19:04,  3.57it/s]
 64%|██████▍   | 238706/371472 [7:57:49<10:27:04,  3.53it/s]
 64%|██████▍   | 238707/371472 [7:57:49<10:31:23,  3.50it/s]
 64%|██████▍   | 238708/371472 [7:57:50<11:21:08,  3.25it/s]
 64%|██████▍   | 238709/371472 [7:57:50<11:21:11,  3.25it/s]
 64%|██████▍   | 238710/371472 [7:57:50<10:59:18,  3.36it/s]
 64%|██████▍   | 238711/371472 [7:57:50<10:53:01,  3.39it/s]
 64%|██████▍   | 238712/371472 [7:57:51<10:42:04,  3.45it/s]
 64%|██████▍   | 238713/371472 [7:57:51<10:21:38,  3.56it/s]
 64%|██████▍   | 238714/371472 [7:57:51<10:40:25,  3.45it/s]
 64%|██████▍   | 238715/371472 [7:57:52<10:58:04,  3.36it/s]
 64%|██████▍   | 238716/371472 [7:57:52<10:46:05,  3.42it/s]
 64%|██████▍   | 238717/371472 [7:57:52<10:40:57,  3.45it/s]
 64%|██████▍   | 238718/371472 [7:57:53<10:57:31,  3.36it/s]
 64%|██████▍   | 238719/371472 [7:57:53<10:33:02,  3.50it/s]
 64%|██████▍   | 238720/371472 [7:57:53<10:44:28,  3.43it/s]
                                                            
{'loss': 2.983, 'learning_rate': 4.21803960438708e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238720/371472 [7:57:53<10:44:28,  3.43it/s]
 64%|██████▍   | 238721/371472 [7:57:53<11:10:23,  3.30it/s]
 64%|██████▍   | 238722/371472 [7:57:54<10:30:00,  3.51it/s]
 64%|██████▍   | 238723/371472 [7:57:54<10:56:38,  3.37it/s]
 64%|██████▍   | 238724/371472 [7:57:54<10:52:27,  3.39it/s]
 64%|██████▍   | 238725/371472 [7:57:55<10:31:34,  3.50it/s]
 64%|██████▍   | 238726/371472 [7:57:55<10:53:12,  3.39it/s]
 64%|██████▍   | 238727/371472 [7:57:55<10:33:27,  3.49it/s]
 64%|██████▍   | 238728/371472 [7:57:55<10:26:35,  3.53it/s]
 64%|██████▍   | 238729/371472 [7:57:56<10:17:34,  3.58it/s]
 64%|██████▍   | 238730/371472 [7:57:56<10:48:03,  3.41it/s]
 64%|██████▍   | 238731/371472 [7:57:56<10:39:38,  3.46it/s]
 64%|██████▍   | 238732/371472 [7:57:57<10:24:58,  3.54it/s]
 64%|██████▍   | 238733/371472 [7:57:57<10:56:47,  3.37it/s]
 64%|██████▍   | 238734/371472 [7:57:57<11:47:26,  3.13it/s]
 64%|██████▍   | 238735/371472 [7:57:58<11:44:19,  3.14it/s]
 64%|██████▍   | 238736/371472 [7:57:58<12:00:51,  3.07it/s]
 64%|██████▍   | 238737/371472 [7:57:58<11:34:40,  3.18it/s]
 64%|██████▍   | 238738/371472 [7:57:58<11:06:39,  3.32it/s]
 64%|██████▍   | 238739/371472 [7:57:59<10:38:35,  3.46it/s]
 64%|██████▍   | 238740/371472 [7:57:59<10:39:15,  3.46it/s]
                                                            
{'loss': 2.9435, 'learning_rate': 4.217554784632291e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238740/371472 [7:57:59<10:39:15,  3.46it/s]
 64%|██████▍   | 238741/371472 [7:57:59<10:29:26,  3.51it/s]
 64%|██████▍   | 238742/371472 [7:58:00<10:17:59,  3.58it/s]
 64%|██████▍   | 238743/371472 [7:58:00<10:32:26,  3.50it/s]
 64%|██████▍   | 238744/371472 [7:58:00<10:28:42,  3.52it/s]
 64%|██████▍   | 238745/371472 [7:58:00<10:51:45,  3.39it/s]
 64%|██████▍   | 238746/371472 [7:58:01<11:12:51,  3.29it/s]
 64%|██████▍   | 238747/371472 [7:58:01<10:51:46,  3.39it/s]
 64%|██████▍   | 238748/371472 [7:58:01<11:07:19,  3.31it/s]
 64%|██████▍   | 238749/371472 [7:58:02<10:55:36,  3.37it/s]
 64%|██████▍   | 238750/371472 [7:58:02<10:55:44,  3.37it/s]
 64%|██████▍   | 238751/371472 [7:58:02<10:26:41,  3.53it/s]
 64%|██████▍   | 238752/371472 [7:58:02<10:45:47,  3.43it/s]
 64%|██████▍   | 238753/371472 [7:58:03<10:25:33,  3.54it/s]
 64%|██████▍   | 238754/371472 [7:58:03<10:17:40,  3.58it/s]
 64%|██████▍   | 238755/371472 [7:58:03<10:58:40,  3.36it/s]
 64%|██████▍   | 238756/371472 [7:58:04<10:50:35,  3.40it/s]
 64%|██████▍   | 238757/371472 [7:58:04<10:52:23,  3.39it/s]
 64%|██████▍   | 238758/371472 [7:58:04<10:58:06,  3.36it/s]
 64%|████��█▍   | 238759/371472 [7:58:05<10:42:54,  3.44it/s]
 64%|██████▍   | 238760/371472 [7:58:05<10:19:50,  3.57it/s]
                                                            
{'loss': 2.9025, 'learning_rate': 4.2170699648775026e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238760/371472 [7:58:05<10:19:50,  3.57it/s]
 64%|██████▍   | 238761/371472 [7:58:05<11:09:46,  3.30it/s]
 64%|██████▍   | 238762/371472 [7:58:05<10:51:26,  3.40it/s]
 64%|██████▍   | 238763/371472 [7:58:06<11:02:02,  3.34it/s]
 64%|██████▍   | 238764/371472 [7:58:06<10:57:19,  3.36it/s]
 64%|██████▍   | 238765/371472 [7:58:06<10:37:06,  3.47it/s]
 64%|██████▍   | 238766/371472 [7:58:07<10:29:31,  3.51it/s]
 64%|██████▍   | 238767/371472 [7:58:07<10:38:52,  3.46it/s]
 64%|██████▍   | 238768/371472 [7:58:07<10:24:12,  3.54it/s]
 64%|██████▍   | 238769/371472 [7:58:07<10:25:27,  3.54it/s]
 64%|██████▍   | 238770/371472 [7:58:08<10:06:06,  3.65it/s]
 64%|██████▍   | 238771/371472 [7:58:08<9:49:06,  3.75it/s] 
 64%|██████▍   | 238772/371472 [7:58:08<10:13:53,  3.60it/s]
 64%|██████▍   | 238773/371472 [7:58:09<10:34:03,  3.49it/s]
 64%|██████▍   | 238774/371472 [7:58:09<10:54:08,  3.38it/s]
 64%|██████▍   | 238775/371472 [7:58:09<10:50:31,  3.40it/s]
 64%|██████▍   | 238776/371472 [7:58:09<11:22:14,  3.24it/s]
 64%|██████▍   | 238777/371472 [7:58:10<10:44:57,  3.43it/s]
 64%|██████▍   | 238778/371472 [7:58:10<10:18:48,  3.57it/s]
 64%|██████▍   | 238779/371472 [7:58:10<10:29:36,  3.51it/s]
 64%|██████▍   | 238780/371472 [7:58:11<10:06:48,  3.64it/s]
                                                            
{'loss': 3.0444, 'learning_rate': 4.2165851451227133e-07, 'epoch': 10.28}
+
 64%|██████▍   | 238780/371472 [7:58:11<10:06:48,  3.64it/s]
 64%|██████▍   | 238781/371472 [7:58:11<9:44:33,  3.78it/s] 
 64%|██████▍   | 238782/371472 [7:58:11<9:40:46,  3.81it/s]
 64%|██████▍   | 238783/371472 [7:58:11<9:27:53,  3.89it/s]
 64%|██████▍   | 238784/371472 [7:58:12<9:31:27,  3.87it/s]
 64%|██████▍   | 238785/371472 [7:58:12<9:35:29,  3.84it/s]
 64%|██████▍   | 238786/371472 [7:58:12<10:06:05,  3.65it/s]
 64%|██████▍   | 238787/371472 [7:58:12<10:11:52,  3.61it/s]
 64%|██████▍   | 238788/371472 [7:58:13<10:10:33,  3.62it/s]
 64%|██████▍   | 238789/371472 [7:58:13<10:39:25,  3.46it/s]
 64%|██████▍   | 238790/371472 [7:58:13<10:41:34,  3.45it/s]
 64%|██████▍   | 238791/371472 [7:58:14<10:06:50,  3.64it/s]
 64%|██████▍   | 238792/371472 [7:58:14<9:58:47,  3.69it/s] 
 64%|██████▍   | 238793/371472 [7:58:14<9:43:59,  3.79it/s]
 64%|██████▍   | 238794/371472 [7:58:14<9:41:50,  3.80it/s]
 64%|██████▍   | 238795/371472 [7:58:15<10:34:09,  3.49it/s]
 64%|██████▍   | 238796/371472 [7:58:15<10:13:48,  3.60it/s]
 64%|██████▍   | 238797/371472 [7:58:15<10:10:07,  3.62it/s]
 64%|██████▍   | 238798/371472 [7:58:15<10:15:09,  3.59it/s]
 64%|██████▍   | 238799/371472 [7:58:16<10:22:59,  3.55it/s]
 64%|██████▍   | 238800/371472 [7:58:16<10:11:11,  3.62it/s]
                                                            
{'loss': 2.7642, 'learning_rate': 4.2161003253679245e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238800/371472 [7:58:16<10:11:11,  3.62it/s]
 64%|██████▍   | 238801/371472 [7:58:16<10:17:56,  3.58it/s]
 64%|██████▍   | 238802/371472 [7:58:17<9:56:15,  3.71it/s] 
 64%|██████▍   | 238803/371472 [7:58:17<10:22:47,  3.55it/s]
 64%|██████▍   | 238804/371472 [7:58:17<10:15:22,  3.59it/s]
 64%|██████▍   | 238805/371472 [7:58:17<10:02:51,  3.67it/s]
 64%|██████▍   | 238806/371472 [7:58:18<10:06:05,  3.65it/s]
 64%|██████▍   | 238807/371472 [7:58:18<10:03:02,  3.67it/s]
 64%|██████▍   | 238808/371472 [7:58:18<10:06:48,  3.64it/s]
 64%|██████▍   | 238809/371472 [7:58:18<10:06:55,  3.64it/s]
 64%|██████▍   | 238810/371472 [7:58:19<10:05:38,  3.65it/s]
 64%|██████▍   | 238811/371472 [7:58:19<10:00:48,  3.68it/s]
 64%|██████▍   | 238812/371472 [7:58:19<9:55:39,  3.71it/s] 
 64%|██████▍   | 238813/371472 [7:58:20<10:07:52,  3.64it/s]
 64%|██████▍   | 238814/371472 [7:58:20<10:27:27,  3.52it/s]
 64%|██████▍   | 238815/371472 [7:58:20<11:01:20,  3.34it/s]
 64%|██████▍   | 238816/371472 [7:58:20<10:47:52,  3.41it/s]
 64%|██████▍   | 238817/371472 [7:58:21<11:06:38,  3.32it/s]
 64%|██████▍   | 238818/371472 [7:58:21<10:42:06,  3.44it/s]
 64%|█���████▍   | 238819/371472 [7:58:21<10:31:58,  3.50it/s]
 64%|██████▍   | 238820/371472 [7:58:22<10:14:12,  3.60it/s]
                                                            
{'loss': 2.7166, 'learning_rate': 4.215615505613135e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238820/371472 [7:58:22<10:14:12,  3.60it/s]
 64%|██████▍   | 238821/371472 [7:58:22<10:04:15,  3.66it/s]
 64%|██████▍   | 238822/371472 [7:58:22<10:04:07,  3.66it/s]
 64%|██████▍   | 238823/371472 [7:58:22<10:52:17,  3.39it/s]
 64%|██████▍   | 238824/371472 [7:58:23<11:02:13,  3.34it/s]
 64%|██████▍   | 238825/371472 [7:58:23<10:56:37,  3.37it/s]
 64%|██████▍   | 238826/371472 [7:58:23<10:56:10,  3.37it/s]
 64%|██████▍   | 238827/371472 [7:58:24<10:51:55,  3.39it/s]
 64%|██████▍   | 238828/371472 [7:58:24<10:20:24,  3.56it/s]
 64%|██████▍   | 238829/371472 [7:58:24<10:43:36,  3.43it/s]
 64%|██████▍   | 238830/371472 [7:58:24<10:21:27,  3.56it/s]
 64%|██████▍   | 238831/371472 [7:58:25<9:55:29,  3.71it/s] 
 64%|██████▍   | 238832/371472 [7:58:25<9:42:00,  3.80it/s]
 64%|██████▍   | 238833/371472 [7:58:25<9:34:01,  3.85it/s]
 64%|██████▍   | 238834/371472 [7:58:26<9:50:27,  3.74it/s]
 64%|██████▍   | 238835/371472 [7:58:26<9:52:35,  3.73it/s]
 64%|██████▍   | 238836/371472 [7:58:26<10:00:45,  3.68it/s]
 64%|██████▍   | 238837/371472 [7:58:26<11:18:19,  3.26it/s]
 64%|██████▍   | 238838/371472 [7:58:27<11:47:45,  3.12it/s]
 64%|██████▍   | 238839/371472 [7:58:27<11:19:18,  3.25it/s]
 64%|██████▍   | 238840/371472 [7:58:27<11:20:03,  3.25it/s]
                                                            
{'loss': 2.7073, 'learning_rate': 4.215130685858347e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238840/371472 [7:58:27<11:20:03,  3.25it/s]
 64%|██████▍   | 238841/371472 [7:58:28<11:00:56,  3.34it/s]
 64%|██████▍   | 238842/371472 [7:58:28<11:18:00,  3.26it/s]
 64%|██████▍   | 238843/371472 [7:58:28<11:11:05,  3.29it/s]
 64%|██████▍   | 238844/371472 [7:58:29<10:47:48,  3.41it/s]
 64%|██████▍   | 238845/371472 [7:58:29<10:23:48,  3.54it/s]
 64%|██████▍   | 238846/371472 [7:58:29<10:15:18,  3.59it/s]
 64%|██████▍   | 238847/371472 [7:58:29<10:19:13,  3.57it/s]
 64%|██████▍   | 238848/371472 [7:58:30<9:51:42,  3.74it/s] 
 64%|██████▍   | 238849/371472 [7:58:30<10:27:06,  3.52it/s]
 64%|██████▍   | 238850/371472 [7:58:30<10:35:15,  3.48it/s]
 64%|██████▍   | 238851/371472 [7:58:31<10:28:58,  3.51it/s]
 64%|██████▍   | 238852/371472 [7:58:31<10:26:21,  3.53it/s]
 64%|██████▍   | 238853/371472 [7:58:31<10:29:42,  3.51it/s]
 64%|██████▍   | 238854/371472 [7:58:31<10:12:36,  3.61it/s]
 64%|██████▍   | 238855/371472 [7:58:32<10:10:01,  3.62it/s]
 64%|██████▍   | 238856/371472 [7:58:32<10:38:38,  3.46it/s]
 64%|██████▍   | 238857/371472 [7:58:32<10:44:20,  3.43it/s]
 64%|██████▍   | 238858/371472 [7:58:33<10:40:05,  3.45it/s]
 64%|██████▍   | 238859/371472 [7:58:33<10:46:45,  3.42it/s]
 64%|██████▍   | 238860/371472 [7:58:33<10:11:34,  3.61it/s]
                                                            
{'loss': 2.8548, 'learning_rate': 4.214645866103557e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238860/371472 [7:58:33<10:11:34,  3.61it/s]
 64%|██████▍   | 238861/371472 [7:58:33<10:10:33,  3.62it/s]
 64%|██████▍   | 238862/371472 [7:58:34<10:14:33,  3.60it/s]
 64%|██████▍   | 238863/371472 [7:58:34<11:08:47,  3.30it/s]
 64%|██████▍   | 238864/371472 [7:58:34<10:42:50,  3.44it/s]
 64%|██████▍   | 238865/371472 [7:58:35<10:46:04,  3.42it/s]
 64%|██████▍   | 238866/371472 [7:58:35<10:48:16,  3.41it/s]
 64%|██████▍   | 238867/371472 [7:58:35<10:36:06,  3.47it/s]
 64%|██████▍   | 238868/371472 [7:58:35<10:57:27,  3.36it/s]
 64%|██████▍   | 238869/371472 [7:58:36<11:40:16,  3.16it/s]
 64%|██████▍   | 238870/371472 [7:58:36<11:43:57,  3.14it/s]
 64%|██████▍   | 238871/371472 [7:58:36<11:22:48,  3.24it/s]
 64%|██████▍   | 238872/371472 [7:58:37<11:13:07,  3.28it/s]
 64%|██████▍   | 238873/371472 [7:58:37<10:46:03,  3.42it/s]
 64%|██████▍   | 238874/371472 [7:58:37<10:37:24,  3.47it/s]
 64%|██████▍   | 238875/371472 [7:58:37<10:15:04,  3.59it/s]
 64%|██████▍   | 238876/371472 [7:58:38<10:32:16,  3.50it/s]
 64%|██████▍   | 238877/371472 [7:58:38<11:14:17,  3.28it/s]
 64%|██████▍   | 238878/371472 [7:58:38<10:59:39,  3.35it/s]
 64%|██████▍   | 238879/371472 [7:58:39<11:22:45,  3.24it/s]
 64%|██████▍   | 238880/371472 [7:58:39<11:31:56,  3.19it/s]
                                                            
{'loss': 2.7809, 'learning_rate': 4.214161046348768e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238880/371472 [7:58:39<11:31:56,  3.19it/s]
 64%|██████▍   | 238881/371472 [7:58:39<11:08:16,  3.31it/s]
 64%|██████▍   | 238882/371472 [7:58:40<11:12:16,  3.29it/s]
 64%|██████▍   | 238883/371472 [7:58:40<10:43:51,  3.43it/s]
 64%|██████▍   | 238884/371472 [7:58:40<10:28:46,  3.51it/s]
 64%|██████▍   | 238885/371472 [7:58:40<10:11:48,  3.61it/s]
 64%|██████▍   | 238886/371472 [7:58:41<10:33:39,  3.49it/s]
 64%|██████▍   | 238887/371472 [7:58:41<10:29:21,  3.51it/s]
 64%|██████▍   | 238888/371472 [7:58:41<10:32:12,  3.50it/s]
 64%|██████▍   | 238889/371472 [7:58:42<10:23:55,  3.54it/s]
 64%|██████▍   | 238890/371472 [7:58:42<10:10:24,  3.62it/s]
 64%|██████▍   | 238891/371472 [7:58:42<10:26:55,  3.52it/s]
 64%|██████▍   | 238892/371472 [7:58:42<10:06:28,  3.64it/s]
 64%|██████▍   | 238893/371472 [7:58:43<9:57:47,  3.70it/s] 
 64%|██████▍   | 238894/371472 [7:58:43<9:52:32,  3.73it/s]
 64%|██████▍   | 238895/371472 [7:58:43<10:13:10,  3.60it/s]
 64%|██████▍   | 238896/371472 [7:58:44<10:42:25,  3.44it/s]
 64%|██████▍   | 238897/371472 [7:58:44<10:16:49,  3.58it/s]
 64%|██████▍   | 238898/371472 [7:58:44<10:35:29,  3.48it/s]
 64%|██████▍   | 238899/371472 [7:58:44<10:27:51,  3.52it/s]
 64%|██████▍   | 238900/371472 [7:58:45<10:29:18,  3.51it/s]
                                                            
{'loss': 2.8546, 'learning_rate': 4.2136762265939797e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238900/371472 [7:58:45<10:29:18,  3.51it/s]
 64%|██████▍   | 238901/371472 [7:58:45<10:42:47,  3.44it/s]
 64%|██████▍   | 238902/371472 [7:58:45<10:21:06,  3.56it/s]
 64%|██████▍   | 238903/371472 [7:58:46<10:18:34,  3.57it/s]
 64%|██████▍   | 238904/371472 [7:58:46<10:00:15,  3.68it/s]
 64%|██████▍   | 238905/371472 [7:58:46<10:01:27,  3.67it/s]
 64%|██████▍   | 238906/371472 [7:58:46<10:00:51,  3.68it/s]
 64%|██████▍   | 238907/371472 [7:58:47<10:42:05,  3.44it/s]
 64%|██████▍   | 238908/371472 [7:58:47<10:29:14,  3.51it/s]
 64%|██████▍   | 238909/371472 [7:58:47<10:23:14,  3.54it/s]
 64%|██████▍   | 238910/371472 [7:58:47<10:17:06,  3.58it/s]
 64%|██████▍   | 238911/371472 [7:58:48<10:21:28,  3.56it/s]
 64%|██████▍   | 238912/371472 [7:58:48<10:14:30,  3.60it/s]
 64%|██████▍   | 238913/371472 [7:58:48<10:03:56,  3.66it/s]
 64%|██████▍   | 238914/371472 [7:58:49<10:25:45,  3.53it/s]
 64%|██████▍   | 238915/371472 [7:58:49<10:02:38,  3.67it/s]
 64%|██████▍   | 238916/371472 [7:58:49<10:21:18,  3.56it/s]
 64%|██████▍   | 238917/371472 [7:58:49<9:55:39,  3.71it/s] 
 64%|██████▍   | 238918/371472 [7:58:50<9:46:47,  3.76it/s]
 64%|██████▍   | 238919/371472 [7:58:50<9:38:42,  3.82it/s]
 64%|██████▍   | 238920/371472 [7:58:50<9:58:24,  3.69it/s]
                                                           
{'loss': 2.9007, 'learning_rate': 4.21319140683919e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238920/371472 [7:58:50<9:58:24,  3.69it/s]
 64%|██████▍   | 238921/371472 [7:58:50<9:43:35,  3.79it/s]
 64%|██████▍   | 238922/371472 [7:58:51<9:38:44,  3.82it/s]
 64%|██████▍   | 238923/371472 [7:58:51<9:58:11,  3.69it/s]
 64%|██████▍   | 238924/371472 [7:58:51<9:46:23,  3.77it/s]
 64%|██████▍   | 238925/371472 [7:58:51<9:37:33,  3.82it/s]
 64%|██████▍   | 238926/371472 [7:58:52<9:38:39,  3.82it/s]
 64%|██████▍   | 238927/371472 [7:58:52<10:39:06,  3.46it/s]
 64%|██████▍   | 238928/371472 [7:58:52<11:21:51,  3.24it/s]
 64%|██████▍   | 238929/371472 [7:58:53<11:10:47,  3.29it/s]
 64%|██████▍   | 238930/371472 [7:58:53<10:42:20,  3.44it/s]
 64%|██████▍   | 238931/371472 [7:58:53<10:56:59,  3.36it/s]
 64%|██████▍   | 238932/371472 [7:58:54<10:39:22,  3.45it/s]
 64%|██████▍   | 238933/371472 [7:58:54<10:26:11,  3.53it/s]
 64%|██████▍   | 238934/371472 [7:58:54<10:19:14,  3.57it/s]
 64%|██████▍   | 238935/371472 [7:58:54<10:03:47,  3.66it/s]
 64%|██████▍   | 238936/371472 [7:58:55<10:05:04,  3.65it/s]
 64%|██████▍   | 238937/371472 [7:58:55<9:49:52,  3.74it/s] 
 64%|██████▍   | 238938/371472 [7:58:55<9:40:28,  3.81it/s]
 64%|██████▍   | 238939/371472 [7:58:55<9:50:49,  3.74it/s]
 64%|██████▍   | 238940/371472 [7:58:56<10:11:40,  3.61it/s]
                                                            
{'loss': 2.8348, 'learning_rate': 4.2127065870844016e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238940/371472 [7:58:56<10:11:40,  3.61it/s]
 64%|██████▍   | 238941/371472 [7:58:56<10:13:47,  3.60it/s]
 64%|██████▍   | 238942/371472 [7:58:56<10:43:06,  3.43it/s]
 64%|██████▍   | 238943/371472 [7:58:57<10:24:49,  3.54it/s]
 64%|██████▍   | 238944/371472 [7:58:57<10:24:59,  3.53it/s]
 64%|██████▍   | 238945/371472 [7:58:57<10:29:42,  3.51it/s]
 64%|██████▍   | 238946/371472 [7:58:58<10:50:34,  3.40it/s]
 64%|██████▍   | 238947/371472 [7:58:58<10:25:43,  3.53it/s]
 64%|██████▍   | 238948/371472 [7:58:58<10:40:39,  3.45it/s]
 64%|██████▍   | 238949/371472 [7:58:58<10:40:39,  3.45it/s]
 64%|██████▍   | 238950/371472 [7:58:59<10:32:31,  3.49it/s]
 64%|██████▍   | 238951/371472 [7:58:59<11:02:02,  3.34it/s]
 64%|██████▍   | 238952/371472 [7:58:59<10:49:52,  3.40it/s]
 64%|██████▍   | 238953/371472 [7:59:00<10:28:08,  3.52it/s]
 64%|██████▍   | 238954/371472 [7:59:00<10:27:38,  3.52it/s]
 64%|██████▍   | 238955/371472 [7:59:00<11:04:27,  3.32it/s]
 64%|██████▍   | 238956/371472 [7:59:00<11:02:46,  3.33it/s]
 64%|██████▍   | 238957/371472 [7:59:01<10:59:27,  3.35it/s]
 64%|██████▍   | 238958/371472 [7:59:01<10:53:59,  3.38it/s]
 64%|██████▍   | 238959/371472 [7:59:01<10:49:44,  3.40it/s]
 64%|██████▍   | 238960/371472 [7:59:02<11:16:37,  3.26it/s]
                                                            
{'loss': 2.7324, 'learning_rate': 4.2122217673296123e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238960/371472 [7:59:02<11:16:37,  3.26it/s]
 64%|██████▍   | 238961/371472 [7:59:02<11:00:31,  3.34it/s]
 64%|██████▍   | 238962/371472 [7:59:02<10:52:45,  3.38it/s]
 64%|██████▍   | 238963/371472 [7:59:02<10:38:13,  3.46it/s]
 64%|██████▍   | 238964/371472 [7:59:03<10:46:12,  3.42it/s]
 64%|██████▍   | 238965/371472 [7:59:03<10:49:51,  3.40it/s]
 64%|██████▍   | 238966/371472 [7:59:03<11:12:23,  3.28it/s]
 64%|██████▍   | 238967/371472 [7:59:04<10:43:56,  3.43it/s]
 64%|██████▍   | 238968/371472 [7:59:04<10:47:46,  3.41it/s]
 64%|██████▍   | 238969/371472 [7:59:04<10:21:23,  3.55it/s]
 64%|██████▍   | 238970/371472 [7:59:04<10:08:28,  3.63it/s]
 64%|██████▍   | 238971/371472 [7:59:05<9:56:19,  3.70it/s] 
 64%|██████▍   | 238972/371472 [7:59:05<9:58:15,  3.69it/s]
 64%|██████▍   | 238973/371472 [7:59:05<10:09:08,  3.63it/s]
 64%|██████▍   | 238974/371472 [7:59:06<10:48:58,  3.40it/s]
 64%|██████▍   | 238975/371472 [7:59:06<10:38:27,  3.46it/s]
 64%|██████▍   | 238976/371472 [7:59:06<11:42:22,  3.14it/s]
 64%|██████▍   | 238977/371472 [7:59:07<11:25:31,  3.22it/s]
 64%|██████▍   | 238978/371472 [7:59:07<11:10:21,  3.29it/s]
 64%|██████▍   | 238979/371472 [7:59:07<11:05:18,  3.32it/s]
 64%|██████▍   | 238980/371472 [7:59:07<11:03:08,  3.33it/s]
                                                            
{'loss': 2.7591, 'learning_rate': 4.2117369475748236e-07, 'epoch': 10.29}
+
 64%|██████▍   | 238980/371472 [7:59:07<11:03:08,  3.33it/s]
 64%|██████▍   | 238981/371472 [7:59:08<11:16:06,  3.27it/s]
 64%|██████▍   | 238982/371472 [7:59:08<10:37:17,  3.46it/s]
 64%|██████▍   | 238983/371472 [7:59:08<10:49:54,  3.40it/s]
 64%|██████▍   | 238984/371472 [7:59:09<10:39:32,  3.45it/s]
 64%|██████▍   | 238985/371472 [7:59:09<10:35:07,  3.48it/s]
 64%|██████▍   | 238986/371472 [7:59:09<10:21:00,  3.56it/s]
 64%|██████▍   | 238987/371472 [7:59:10<11:00:28,  3.34it/s]
 64%|██████▍   | 238988/371472 [7:59:10<10:34:37,  3.48it/s]
 64%|██████▍   | 238989/371472 [7:59:10<10:21:09,  3.55it/s]
 64%|██████▍   | 238990/371472 [7:59:10<10:25:45,  3.53it/s]
 64%|██████▍   | 238991/371472 [7:59:11<10:22:22,  3.55it/s]
 64%|██████▍   | 238992/371472 [7:59:11<11:00:31,  3.34it/s]
 64%|██████▍   | 238993/371472 [7:59:11<10:34:44,  3.48it/s]
 64%|██████▍   | 238994/371472 [7:59:11<10:30:46,  3.50it/s]
 64%|██████▍   | 238995/371472 [7:59:12<10:26:43,  3.52it/s]
 64%|██████▍   | 238996/371472 [7:59:12<10:29:42,  3.51it/s]
 64%|██████▍   | 238997/371472 [7:59:12<10:13:58,  3.60it/s]
 64%|██████▍   | 238998/371472 [7:59:13<10:25:03,  3.53it/s]
 64%|██████▍   | 238999/371472 [7:59:13<10:49:05,  3.40it/s]
 64%|██████▍   | 239000/371472 [7:59:13<10:56:04,  3.37it/s]
                                                            
{'loss': 2.973, 'learning_rate': 4.2112521278200343e-07, 'epoch': 10.29}
+
 64%|██████▍   | 239000/371472 [7:59:13<10:56:04,  3.37it/s]
 64%|██████▍   | 239001/371472 [7:59:14<11:14:23,  3.27it/s]
 64%|██████▍   | 239002/371472 [7:59:14<10:49:20,  3.40it/s]
 64%|██████▍   | 239003/371472 [7:59:14<10:27:13,  3.52it/s]
 64%|██████▍   | 239004/371472 [7:59:14<11:04:34,  3.32it/s]
 64%|██████▍   | 239005/371472 [7:59:15<10:48:07,  3.41it/s]
 64%|██████▍   | 239006/371472 [7:59:15<10:19:41,  3.56it/s]
 64%|██████▍   | 239007/371472 [7:59:15<10:27:47,  3.52it/s]
 64%|██████▍   | 239008/371472 [7:59:16<10:25:23,  3.53it/s]
 64%|██████▍   | 239009/371472 [7:59:16<10:07:16,  3.64it/s]
 64%|██████▍   | 239010/371472 [7:59:16<10:22:09,  3.55it/s]
 64%|██████▍   | 239011/371472 [7:59:16<11:09:34,  3.30it/s]
 64%|██████▍   | 239012/371472 [7:59:17<10:50:38,  3.39it/s]
 64%|██████▍   | 239013/371472 [7:59:17<11:50:20,  3.11it/s]
 64%|██████▍   | 239014/371472 [7:59:17<11:24:56,  3.22it/s]
 64%|██████▍   | 239015/371472 [7:59:18<11:04:31,  3.32it/s]
 64%|██████▍   | 239016/371472 [7:59:18<11:30:22,  3.20it/s]
 64%|██████▍   | 239017/371472 [7:59:18<11:39:12,  3.16it/s]
 64%|██████▍   | 239018/371472 [7:59:19<11:33:52,  3.18it/s]
 64%|██████▍   | 239019/371472 [7:59:19<11:46:02,  3.13it/s]
 64%|██████▍   | 239020/371472 [7:59:19<11:04:56,  3.32it/s]
                                                            
{'loss': 2.8362, 'learning_rate': 4.210767308065246e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239020/371472 [7:59:19<11:04:56,  3.32it/s]
 64%|██████▍   | 239021/371472 [7:59:20<10:53:03,  3.38it/s]
 64%|██████▍   | 239022/371472 [7:59:20<11:16:35,  3.26it/s]
 64%|██████▍   | 239023/371472 [7:59:20<10:37:17,  3.46it/s]
 64%|██████▍   | 239024/371472 [7:59:20<10:32:09,  3.49it/s]
 64%|██████▍   | 239025/371472 [7:59:21<10:39:09,  3.45it/s]
 64%|██████▍   | 239026/371472 [7:59:21<10:33:49,  3.48it/s]
 64%|██████▍   | 239027/371472 [7:59:21<10:22:24,  3.55it/s]
 64%|██████▍   | 239028/371472 [7:59:21<10:08:42,  3.63it/s]
 64%|██████▍   | 239029/371472 [7:59:22<10:05:01,  3.65it/s]
 64%|██████▍   | 239030/371472 [7:59:22<10:32:57,  3.49it/s]
 64%|██████▍   | 239031/371472 [7:59:22<10:52:34,  3.38it/s]
 64%|██████▍   | 239032/371472 [7:59:23<10:56:10,  3.36it/s]
 64%|██████▍   | 239033/371472 [7:59:23<10:35:18,  3.47it/s]
 64%|██████▍   | 239034/371472 [7:59:23<10:37:49,  3.46it/s]
 64%|██████▍   | 239035/371472 [7:59:24<11:03:12,  3.33it/s]
 64%|██████▍   | 239036/371472 [7:59:24<11:01:22,  3.34it/s]
 64%|██████▍   | 239037/371472 [7:59:24<10:38:02,  3.46it/s]
 64%|██████▍   | 239038/371472 [7:59:24<11:12:45,  3.28it/s]
 64%|██████▍   | 239039/371472 [7:59:25<10:42:15,  3.44it/s]
 64%|██████▍   | 239040/371472 [7:59:25<10:51:53,  3.39it/s]
                                                            
{'loss': 2.845, 'learning_rate': 4.2102824883104563e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239040/371472 [7:59:25<10:51:53,  3.39it/s]
 64%|██████▍   | 239041/371472 [7:59:25<11:06:55,  3.31it/s]
 64%|██████▍   | 239042/371472 [7:59:26<11:15:51,  3.27it/s]
 64%|██████▍   | 239043/371472 [7:59:26<11:05:18,  3.32it/s]
 64%|██████▍   | 239044/371472 [7:59:26<10:52:06,  3.38it/s]
 64%|██████▍   | 239045/371472 [7:59:27<10:56:46,  3.36it/s]
 64%|██████▍   | 239046/371472 [7:59:27<10:38:39,  3.46it/s]
 64%|██████▍   | 239047/371472 [7:59:27<11:33:43,  3.18it/s]
 64%|██████▍   | 239048/371472 [7:59:27<10:52:12,  3.38it/s]
 64%|██████▍   | 239049/371472 [7:59:28<10:51:27,  3.39it/s]
 64%|██████▍   | 239050/371472 [7:59:28<10:27:38,  3.52it/s]
 64%|██████▍   | 239051/371472 [7:59:28<10:16:20,  3.58it/s]
 64%|██████▍   | 239052/371472 [7:59:29<9:59:25,  3.68it/s] 
 64%|██████▍   | 239053/371472 [7:59:29<9:44:22,  3.78it/s]
 64%|██████▍   | 239054/371472 [7:59:29<9:53:55,  3.72it/s]
 64%|██████▍   | 239055/371472 [7:59:29<9:55:12,  3.71it/s]
 64%|██████▍   | 239056/371472 [7:59:30<9:47:48,  3.75it/s]
 64%|██████▍   | 239057/371472 [7:59:30<9:35:06,  3.84it/s]
 64%|██████▍   | 239058/371472 [7:59:30<9:31:04,  3.86it/s]
 64%|██████▍   | 239059/371472 [7:59:30<9:27:33,  3.89it/s]
 64%|██████▍   | 239060/371472 [7:59:31<9:41:59,  3.79it/s]
                                                           
{'loss': 2.7932, 'learning_rate': 4.209797668555668e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239060/371472 [7:59:31<9:41:59,  3.79it/s]
 64%|██████▍   | 239061/371472 [7:59:31<9:56:35,  3.70it/s]
 64%|██████▍   | 239062/371472 [7:59:31<9:41:18,  3.80it/s]
 64%|██████▍   | 239063/371472 [7:59:31<9:30:23,  3.87it/s]
 64%|██████▍   | 239064/371472 [7:59:32<9:42:19,  3.79it/s]
 64%|██████▍   | 239065/371472 [7:59:32<9:58:48,  3.69it/s]
 64%|██████▍   | 239066/371472 [7:59:32<9:46:24,  3.76it/s]
 64%|██████▍   | 239067/371472 [7:59:33<10:13:35,  3.60it/s]
 64%|██████▍   | 239068/371472 [7:59:33<10:38:26,  3.46it/s]
 64%|██████▍   | 239069/371472 [7:59:33<10:29:57,  3.50it/s]
 64%|██████▍   | 239070/371472 [7:59:33<10:20:49,  3.55it/s]
 64%|██████▍   | 239071/371472 [7:59:34<10:09:25,  3.62it/s]
 64%|██████▍   | 239072/371472 [7:59:34<10:05:29,  3.64it/s]
 64%|██████▍   | 239073/371472 [7:59:34<10:17:25,  3.57it/s]
 64%|██████▍   | 239074/371472 [7:59:35<10:38:58,  3.45it/s]
 64%|██████▍   | 239075/371472 [7:59:35<10:29:36,  3.50it/s]
 64%|██████▍   | 239076/371472 [7:59:35<10:55:29,  3.37it/s]
 64%|██████▍   | 239077/371472 [7:59:35<10:46:41,  3.41it/s]
 64%|██████▍   | 239078/371472 [7:59:36<10:24:37,  3.53it/s]
 64%|██████▍   | 239079/371472 [7:59:36<10:18:13,  3.57it/s]
 64%|██████▍   | 239080/371472 [7:59:36<10:49:20,  3.40it/s]
                                                            
{'loss': 2.855, 'learning_rate': 4.209312848800879e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239080/371472 [7:59:36<10:49:20,  3.40it/s]
 64%|██████▍   | 239081/371472 [7:59:37<11:11:15,  3.29it/s]
 64%|██████▍   | 239082/371472 [7:59:37<11:04:00,  3.32it/s]
 64%|██████▍   | 239083/371472 [7:59:37<10:30:04,  3.50it/s]
 64%|██████▍   | 239084/371472 [7:59:37<9:56:07,  3.70it/s] 
 64%|██████▍   | 239085/371472 [7:59:38<10:04:00,  3.65it/s]
 64%|██████▍   | 239086/371472 [7:59:38<9:49:56,  3.74it/s] 
 64%|██████▍   | 239087/371472 [7:59:38<10:02:15,  3.66it/s]
 64%|██████▍   | 239088/371472 [7:59:38<10:04:26,  3.65it/s]
 64%|██████▍   | 239089/371472 [7:59:39<9:56:27,  3.70it/s] 
 64%|██████▍   | 239090/371472 [7:59:39<10:19:39,  3.56it/s]
 64%|██████▍   | 239091/371472 [7:59:39<10:12:12,  3.60it/s]
 64%|██████▍   | 239092/371472 [7:59:40<9:46:11,  3.76it/s] 
 64%|██████▍   | 239093/371472 [7:59:40<10:02:05,  3.66it/s]
 64%|██████▍   | 239094/371472 [7:59:40<10:04:56,  3.65it/s]
 64%|██████▍   | 239095/371472 [7:59:40<10:05:14,  3.65it/s]
 64%|██████▍   | 239096/371472 [7:59:41<9:42:08,  3.79it/s] 
 64%|██████▍   | 239097/371472 [7:59:41<10:35:15,  3.47it/s]
 64%|██████▍   | 239098/371472 [7:59:41<10:32:29,  3.49it/s]
 64%|██████▍   | 239099/371472 [7:59:42<10:46:32,  3.41it/s]
 64%|██████▍   | 239100/371472 [7:59:42<10:07:31,  3.63it/s]
                                                            
{'loss': 2.6235, 'learning_rate': 4.20882802904609e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239100/371472 [7:59:42<10:07:31,  3.63it/s]
 64%|██████▍   | 239101/371472 [7:59:42<10:13:40,  3.60it/s]
 64%|██████▍   | 239102/371472 [7:59:42<10:00:51,  3.67it/s]
 64%|██████▍   | 239103/371472 [7:59:43<9:44:17,  3.78it/s] 
 64%|██████▍   | 239104/371472 [7:59:43<9:48:48,  3.75it/s]
 64%|██████▍   | 239105/371472 [7:59:43<11:46:38,  3.12it/s]
 64%|██████▍   | 239106/371472 [7:59:44<11:51:00,  3.10it/s]
 64%|██████▍   | 239107/371472 [7:59:44<11:00:45,  3.34it/s]
 64%|██████▍   | 239108/371472 [7:59:44<10:38:34,  3.45it/s]
 64%|██████▍   | 239109/371472 [7:59:44<10:08:52,  3.62it/s]
 64%|██████▍   | 239110/371472 [7:59:45<9:58:06,  3.69it/s] 
 64%|██████▍   | 239111/371472 [7:59:45<9:37:44,  3.82it/s]
 64%|██████▍   | 239112/371472 [7:59:45<9:36:14,  3.83it/s]
 64%|██████▍   | 239113/371472 [7:59:45<9:53:02,  3.72it/s]
 64%|██████▍   | 239114/371472 [7:59:46<10:06:35,  3.64it/s]
 64%|██████▍   | 239115/371472 [7:59:46<9:52:52,  3.72it/s] 
 64%|██████▍   | 239116/371472 [7:59:46<9:55:40,  3.70it/s]
 64%|██████▍   | 239117/371472 [7:59:47<10:10:43,  3.61it/s]
 64%|██████▍   | 239118/371472 [7:59:47<10:18:38,  3.57it/s]
 64%|██████▍   | 239119/371472 [7:59:47<10:03:18,  3.66it/s]
 64%|██████▍   | 239120/371472 [7:59:47<10:14:51,  3.59it/s]
                                                            
{'loss': 2.8251, 'learning_rate': 4.2083432092913007e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239120/371472 [7:59:47<10:14:51,  3.59it/s]
 64%|██████▍   | 239121/371472 [7:59:48<10:13:14,  3.60it/s]
 64%|██████▍   | 239122/371472 [7:59:48<10:14:04,  3.59it/s]
 64%|██████▍   | 239123/371472 [7:59:48<10:38:54,  3.45it/s]
 64%|██████▍   | 239124/371472 [7:59:48<10:03:50,  3.65it/s]
 64%|██████▍   | 239125/371472 [7:59:49<10:18:21,  3.57it/s]
 64%|██████▍   | 239126/371472 [7:59:49<10:22:23,  3.54it/s]
 64%|██████▍   | 239127/371472 [7:59:49<10:11:23,  3.61it/s]
 64%|██████▍   | 239128/371472 [7:59:50<10:00:06,  3.68it/s]
 64%|██████▍   | 239129/371472 [7:59:50<9:45:16,  3.77it/s] 
 64%|██████▍   | 239130/371472 [7:59:50<10:40:41,  3.44it/s]
 64%|██████▍   | 239131/371472 [7:59:50<10:33:37,  3.48it/s]
 64%|██████▍   | 239132/371472 [7:59:51<10:31:24,  3.49it/s]
 64%|██████▍   | 239133/371472 [7:59:51<10:58:34,  3.35it/s]
 64%|██████▍   | 239134/371472 [7:59:51<10:30:08,  3.50it/s]
 64%|██████▍   | 239135/371472 [7:59:52<10:42:22,  3.43it/s]
 64%|██████▍   | 239136/371472 [7:59:52<10:43:16,  3.43it/s]
 64%|██████▍   | 239137/371472 [7:59:52<10:37:01,  3.46it/s]
 64%|██████▍   | 239138/371472 [7:59:52<10:23:22,  3.54it/s]
 64%|██████▍   | 239139/371472 [7:59:53<10:48:31,  3.40it/s]
 64%|██████▍   | 239140/371472 [7:59:53<11:00:58,  3.34it/s]
                                                            
{'loss': 2.9021, 'learning_rate': 4.2078583895365125e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239140/371472 [7:59:53<11:00:58,  3.34it/s]
 64%|██████▍   | 239141/371472 [7:59:53<10:47:25,  3.41it/s]
 64%|██████▍   | 239142/371472 [7:59:54<10:23:10,  3.54it/s]
 64%|██████▍   | 239143/371472 [7:59:54<10:23:54,  3.53it/s]
 64%|██████▍   | 239144/371472 [7:59:54<10:46:45,  3.41it/s]
 64%|██████▍   | 239145/371472 [7:59:55<10:21:17,  3.55it/s]
 64%|██████▍   | 239146/371472 [7:59:55<10:42:08,  3.43it/s]
 64%|██████▍   | 239147/371472 [7:59:55<10:29:19,  3.50it/s]
 64%|██████▍   | 239148/371472 [7:59:55<10:26:44,  3.52it/s]
 64%|██████▍   | 239149/371472 [7:59:56<10:31:32,  3.49it/s]
 64%|██████▍   | 239150/371472 [7:59:56<10:43:00,  3.43it/s]
 64%|██████▍   | 239151/371472 [7:59:56<11:41:16,  3.14it/s]
 64%|██████▍   | 239152/371472 [7:59:57<10:53:10,  3.38it/s]
 64%|██████▍   | 239153/371472 [7:59:57<10:36:56,  3.46it/s]
 64%|██████▍   | 239154/371472 [7:59:57<10:01:43,  3.66it/s]
 64%|██████▍   | 239155/371472 [7:59:57<10:34:17,  3.48it/s]
 64%|██████▍   | 239156/371472 [7:59:58<10:31:45,  3.49it/s]
 64%|██████▍   | 239157/371472 [7:59:58<10:11:22,  3.61it/s]
 64%|██████▍   | 239158/371472 [7:59:58<9:48:03,  3.75it/s] 
 64%|██████▍   | 239159/371472 [7:59:58<9:36:10,  3.83it/s]
 64%|██████▍   | 239160/371472 [7:59:59<9:24:28,  3.91it/s]
                                                           
{'loss': 2.8316, 'learning_rate': 4.207373569781723e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239160/371472 [7:59:59<9:24:28,  3.91it/s]
 64%|██████▍   | 239161/371472 [7:59:59<9:39:19,  3.81it/s]
 64%|██████▍   | 239162/371472 [7:59:59<10:04:59,  3.64it/s]
 64%|██████▍   | 239163/371472 [8:00:00<9:46:39,  3.76it/s] 
 64%|██████▍   | 239164/371472 [8:00:00<9:42:23,  3.79it/s]
 64%|██████▍   | 239165/371472 [8:00:00<9:31:04,  3.86it/s]
 64%|██████▍   | 239166/371472 [8:00:00<10:50:23,  3.39it/s]
 64%|██████▍   | 239167/371472 [8:00:01<10:31:25,  3.49it/s]
 64%|██████▍   | 239168/371472 [8:00:01<10:28:02,  3.51it/s]
 64%|██████▍   | 239169/371472 [8:00:01<9:59:32,  3.68it/s] 
 64%|██████▍   | 239170/371472 [8:00:01<10:08:25,  3.62it/s]
 64%|██████▍   | 239171/371472 [8:00:02<10:21:11,  3.55it/s]
 64%|██████▍   | 239172/371472 [8:00:02<10:08:44,  3.62it/s]
 64%|██████▍   | 239173/371472 [8:00:02<9:58:23,  3.68it/s] 
 64%|██████▍   | 239174/371472 [8:00:03<10:47:51,  3.40it/s]
 64%|██████▍   | 239175/371472 [8:00:03<10:40:50,  3.44it/s]
 64%|██████▍   | 239176/371472 [8:00:03<11:00:43,  3.34it/s]
 64%|██████▍   | 239177/371472 [8:00:04<10:35:12,  3.47it/s]
 64%|██████▍   | 239178/371472 [8:00:04<10:40:38,  3.44it/s]
 64%|██████▍   | 239179/371472 [8:00:04<10:56:40,  3.36it/s]
 64%|██████▍   | 239180/371472 [8:00:04<10:32:49,  3.48it/s]
                                                            
{'loss': 2.8478, 'learning_rate': 4.2068887500269344e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239180/371472 [8:00:04<10:32:49,  3.48it/s]
 64%|██████▍   | 239181/371472 [8:00:05<10:14:38,  3.59it/s]
 64%|██████▍   | 239182/371472 [8:00:05<9:59:31,  3.68it/s] 
 64%|██████▍   | 239183/371472 [8:00:05<10:08:00,  3.63it/s]
 64%|██████▍   | 239184/371472 [8:00:06<10:47:23,  3.41it/s]
 64%|██████▍   | 239185/371472 [8:00:06<10:25:48,  3.52it/s]
 64%|██████▍   | 239186/371472 [8:00:06<10:53:25,  3.37it/s]
 64%|██████▍   | 239187/371472 [8:00:06<10:36:46,  3.46it/s]
 64%|██████▍   | 239188/371472 [8:00:07<10:21:13,  3.55it/s]
 64%|██████▍   | 239189/371472 [8:00:07<10:30:32,  3.50it/s]
 64%|██████▍   | 239190/371472 [8:00:07<10:31:00,  3.49it/s]
 64%|██████▍   | 239191/371472 [8:00:08<11:05:00,  3.32it/s]
 64%|██████▍   | 239192/371472 [8:00:08<12:02:20,  3.05it/s]
 64%|██████▍   | 239193/371472 [8:00:08<11:21:53,  3.23it/s]
 64%|██████▍   | 239194/371472 [8:00:09<11:37:05,  3.16it/s]
 64%|██████▍   | 239195/371472 [8:00:09<11:13:16,  3.27it/s]
 64%|██████▍   | 239196/371472 [8:00:09<11:26:58,  3.21it/s]
 64%|██████▍   | 239197/371472 [8:00:09<10:56:18,  3.36it/s]
 64%|██████▍   | 239198/371472 [8:00:10<11:04:55,  3.32it/s]
 64%|██████▍   | 239199/371472 [8:00:10<10:25:45,  3.52it/s]
 64%|██████▍   | 239200/371472 [8:00:10<10:07:42,  3.63it/s]
                                                            
{'loss': 2.7871, 'learning_rate': 4.206403930272145e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239200/371472 [8:00:10<10:07:42,  3.63it/s]
 64%|██████▍   | 239201/371472 [8:00:11<10:08:19,  3.62it/s]
 64%|██████▍   | 239202/371472 [8:00:11<10:26:19,  3.52it/s]
 64%|██████▍   | 239203/371472 [8:00:11<10:30:50,  3.49it/s]
 64%|██████▍   | 239204/371472 [8:00:11<10:22:13,  3.54it/s]
 64%|██████▍   | 239205/371472 [8:00:12<9:59:52,  3.67it/s] 
 64%|██████▍   | 239206/371472 [8:00:12<9:52:15,  3.72it/s]
 64%|██████▍   | 239207/371472 [8:00:12<10:11:01,  3.61it/s]
 64%|██████▍   | 239208/371472 [8:00:12<10:23:05,  3.54it/s]
 64%|██████▍   | 239209/371472 [8:00:13<10:07:09,  3.63it/s]
 64%|██████▍   | 239210/371472 [8:00:13<10:02:24,  3.66it/s]
 64%|██████▍   | 239211/371472 [8:00:13<10:21:19,  3.55it/s]
 64%|██████▍   | 239212/371472 [8:00:14<10:35:43,  3.47it/s]
 64%|██████▍   | 239213/371472 [8:00:14<10:48:01,  3.40it/s]
 64%|██████▍   | 239214/371472 [8:00:14<10:42:17,  3.43it/s]
 64%|██████▍   | 239215/371472 [8:00:14<10:38:03,  3.45it/s]
 64%|██████▍   | 239216/371472 [8:00:15<10:36:48,  3.46it/s]
 64%|██████▍   | 239217/371472 [8:00:15<10:33:11,  3.48it/s]
 64%|██████▍   | 239218/371472 [8:00:15<10:15:46,  3.58it/s]
 64%|██████▍   | 239219/371472 [8:00:16<10:14:17,  3.59it/s]
 64%|██████▍   | 239220/371472 [8:00:16<10:05:17,  3.64it/s]
                                                            
{'loss': 2.8483, 'learning_rate': 4.205919110517357e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239220/371472 [8:00:16<10:05:17,  3.64it/s]
 64%|██████▍   | 239221/371472 [8:00:16<10:16:18,  3.58it/s]
 64%|██████▍   | 239222/371472 [8:00:16<10:28:16,  3.51it/s]
 64%|██████▍   | 239223/371472 [8:00:17<10:54:23,  3.37it/s]
 64%|██████▍   | 239224/371472 [8:00:17<10:14:41,  3.59it/s]
 64%|██████▍   | 239225/371472 [8:00:17<10:19:25,  3.56it/s]
 64%|██████▍   | 239226/371472 [8:00:18<10:21:00,  3.55it/s]
 64%|██████▍   | 239227/371472 [8:00:18<10:15:22,  3.58it/s]
 64%|██████▍   | 239228/371472 [8:00:18<10:52:28,  3.38it/s]
 64%|██████▍   | 239229/371472 [8:00:18<10:20:46,  3.55it/s]
 64%|██████▍   | 239230/371472 [8:00:19<10:09:38,  3.62it/s]
 64%|██████▍   | 239231/371472 [8:00:19<10:29:42,  3.50it/s]
 64%|██████▍   | 239232/371472 [8:00:19<10:21:33,  3.55it/s]
 64%|██████▍   | 239233/371472 [8:00:20<10:30:25,  3.50it/s]
 64%|██████▍   | 239234/371472 [8:00:20<10:22:24,  3.54it/s]
 64%|██████▍   | 239235/371472 [8:00:20<10:40:29,  3.44it/s]
 64%|██████▍   | 239236/371472 [8:00:20<10:22:03,  3.54it/s]
 64%|██████▍   | 239237/371472 [8:00:21<10:15:04,  3.58it/s]
 64%|██████▍   | 239238/371472 [8:00:21<10:17:16,  3.57it/s]
 64%|██████▍   | 239239/371472 [8:00:21<9:45:05,  3.77it/s] 
 64%|██████▍   | 239240/371472 [8:00:22<10:45:38,  3.41it/s]
                                                            
{'loss': 2.8935, 'learning_rate': 4.205434290762567e-07, 'epoch': 10.3}
+
 64%|██████▍   | 239240/371472 [8:00:22<10:45:38,  3.41it/s]
 64%|██████▍   | 239241/371472 [8:00:22<11:10:50,  3.29it/s]
 64%|██████▍   | 239242/371472 [8:00:22<10:48:28,  3.40it/s]
 64%|██████▍   | 239243/371472 [8:00:22<10:49:01,  3.40it/s]
 64%|██████▍   | 239244/371472 [8:00:23<10:27:41,  3.51it/s]
 64%|██████▍   | 239245/371472 [8:00:23<10:04:01,  3.65it/s]
 64%|██████▍   | 239246/371472 [8:00:23<10:12:19,  3.60it/s]
 64%|██████▍   | 239247/371472 [8:00:24<10:17:43,  3.57it/s]
 64%|██████▍   | 239248/371472 [8:00:24<9:56:14,  3.70it/s] 
 64%|██████▍   | 239249/371472 [8:00:24<10:46:53,  3.41it/s]
 64%|██████▍   | 239250/371472 [8:00:24<10:11:59,  3.60it/s]
 64%|██████▍   | 239251/371472 [8:00:25<10:13:49,  3.59it/s]
 64%|██████▍   | 239252/371472 [8:00:25<9:54:39,  3.71it/s] 
 64%|██████▍   | 239253/371472 [8:00:25<9:55:03,  3.70it/s]
 64%|██████▍   | 239254/371472 [8:00:25<9:50:42,  3.73it/s]
 64%|██████▍   | 239255/371472 [8:00:26<10:06:57,  3.63it/s]
 64%|██████▍   | 239256/371472 [8:00:26<10:34:03,  3.48it/s]
 64%|██████▍   | 239257/371472 [8:00:26<10:40:51,  3.44it/s]
 64%|██████▍   | 239258/371472 [8:00:27<10:52:53,  3.38it/s]
 64%|██████▍   | 239259/371472 [8:00:27<10:52:49,  3.38it/s]
 64%|██████▍   | 239260/371472 [8:00:27<10:35:08,  3.47it/s]
                                                            
{'loss': 2.7257, 'learning_rate': 4.204949471007779e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239260/371472 [8:00:27<10:35:08,  3.47it/s]
 64%|██████▍   | 239261/371472 [8:00:28<10:27:32,  3.51it/s]
 64%|██████▍   | 239262/371472 [8:00:28<10:38:37,  3.45it/s]
 64%|██████▍   | 239263/371472 [8:00:28<10:10:17,  3.61it/s]
 64%|██████▍   | 239264/371472 [8:00:28<10:18:57,  3.56it/s]
 64%|██████▍   | 239265/371472 [8:00:29<10:23:07,  3.54it/s]
 64%|██████▍   | 239266/371472 [8:00:29<10:05:15,  3.64it/s]
 64%|██████▍   | 239267/371472 [8:00:29<10:36:12,  3.46it/s]
 64%|██████▍   | 239268/371472 [8:00:30<10:58:22,  3.35it/s]
 64%|██████▍   | 239269/371472 [8:00:30<11:01:45,  3.33it/s]
 64%|██████▍   | 239270/371472 [8:00:30<11:15:15,  3.26it/s]
 64%|██████▍   | 239271/371472 [8:00:30<10:58:03,  3.35it/s]
 64%|██████▍   | 239272/371472 [8:00:31<10:42:49,  3.43it/s]
 64%|██████▍   | 239273/371472 [8:00:31<11:16:57,  3.25it/s]
 64%|██████▍   | 239274/371472 [8:00:31<10:52:30,  3.38it/s]
 64%|██████▍   | 239275/371472 [8:00:32<10:46:46,  3.41it/s]
 64%|██████▍   | 239276/371472 [8:00:32<10:34:49,  3.47it/s]
 64%|██████▍   | 239277/371472 [8:00:32<10:18:54,  3.56it/s]
 64%|██████▍   | 239278/371472 [8:00:32<10:24:17,  3.53it/s]
 64%|██████▍   | 239279/371472 [8:00:33<9:54:34,  3.71it/s] 
 64%|██████▍   | 239280/371472 [8:00:33<10:15:14,  3.58it/s]
                                                            
{'loss': 2.8453, 'learning_rate': 4.2044646512529896e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239280/371472 [8:00:33<10:15:14,  3.58it/s]
 64%|██████▍   | 239281/371472 [8:00:33<10:59:46,  3.34it/s]
 64%|██████▍   | 239282/371472 [8:00:34<11:20:57,  3.24it/s]
 64%|██████▍   | 239283/371472 [8:00:34<10:34:28,  3.47it/s]
 64%|██████▍   | 239284/371472 [8:00:34<10:37:45,  3.45it/s]
 64%|██████▍   | 239285/371472 [8:00:34<10:14:36,  3.58it/s]
 64%|██████▍   | 239286/371472 [8:00:35<10:21:16,  3.55it/s]
 64%|██████▍   | 239287/371472 [8:00:35<10:14:39,  3.58it/s]
 64%|██████▍   | 239288/371472 [8:00:35<10:12:53,  3.59it/s]
 64%|██████▍   | 239289/371472 [8:00:36<10:16:32,  3.57it/s]
 64%|██████▍   | 239290/371472 [8:00:36<10:23:27,  3.53it/s]
 64%|██████▍   | 239291/371472 [8:00:36<10:17:22,  3.57it/s]
 64%|██████▍   | 239292/371472 [8:00:36<10:02:12,  3.66it/s]
 64%|██████▍   | 239293/371472 [8:00:37<10:12:08,  3.60it/s]
 64%|██████▍   | 239294/371472 [8:00:37<11:05:50,  3.31it/s]
 64%|██████▍   | 239295/371472 [8:00:37<11:03:44,  3.32it/s]
 64%|██████▍   | 239296/371472 [8:00:38<10:48:34,  3.40it/s]
 64%|██████▍   | 239297/371472 [8:00:38<10:31:37,  3.49it/s]
 64%|██████▍   | 239298/371472 [8:00:38<10:03:38,  3.65it/s]
 64%|██████▍   | 239299/371472 [8:00:38<9:50:20,  3.73it/s] 
 64%|██████▍   | 239300/371472 [8:00:39<10:06:56,  3.63it/s]
                                                            
{'loss': 2.978, 'learning_rate': 4.2039798314982014e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239300/371472 [8:00:39<10:06:56,  3.63it/s]
 64%|██████▍   | 239301/371472 [8:00:39<10:02:36,  3.66it/s]
 64%|██████▍   | 239302/371472 [8:00:39<10:01:15,  3.66it/s]
 64%|██████▍   | 239303/371472 [8:00:40<10:20:44,  3.55it/s]
 64%|██████▍   | 239304/371472 [8:00:40<10:35:25,  3.47it/s]
 64%|██████▍   | 239305/371472 [8:00:40<10:14:09,  3.59it/s]
 64%|██████▍   | 239306/371472 [8:00:40<9:57:28,  3.69it/s] 
 64%|██████▍   | 239307/371472 [8:00:41<10:47:33,  3.40it/s]
 64%|██████▍   | 239308/371472 [8:00:41<10:30:03,  3.50it/s]
 64%|██████▍   | 239309/371472 [8:00:41<10:48:23,  3.40it/s]
 64%|██████▍   | 239310/371472 [8:00:42<10:38:51,  3.45it/s]
 64%|██████▍   | 239311/371472 [8:00:42<10:25:31,  3.52it/s]
 64%|██████▍   | 239312/371472 [8:00:42<10:29:30,  3.50it/s]
 64%|██████▍   | 239313/371472 [8:00:42<10:26:46,  3.51it/s]
 64%|██████▍   | 239314/371472 [8:00:43<10:13:12,  3.59it/s]
 64%|██████▍   | 239315/371472 [8:00:43<10:01:25,  3.66it/s]
 64%|██████▍   | 239316/371472 [8:00:43<10:42:15,  3.43it/s]
 64%|██████▍   | 239317/371472 [8:00:44<11:05:50,  3.31it/s]
 64%|██████▍   | 239318/371472 [8:00:44<10:36:57,  3.46it/s]
 64%|██████▍   | 239319/371472 [8:00:44<11:17:42,  3.25it/s]
 64%|██████▍   | 239320/371472 [8:00:44<10:43:45,  3.42it/s]
                                                            
{'loss': 2.8739, 'learning_rate': 4.2034950117434116e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239320/371472 [8:00:44<10:43:45,  3.42it/s]
 64%|██████▍   | 239321/371472 [8:00:45<10:35:59,  3.46it/s]
 64%|██████▍   | 239322/371472 [8:00:45<10:15:59,  3.58it/s]
 64%|██████▍   | 239323/371472 [8:00:45<10:11:30,  3.60it/s]
 64%|██████▍   | 239324/371472 [8:00:46<10:16:51,  3.57it/s]
 64%|██████▍   | 239325/371472 [8:00:46<9:51:25,  3.72it/s] 
 64%|██████▍   | 239326/371472 [8:00:46<9:53:18,  3.71it/s]
 64%|██████▍   | 239327/371472 [8:00:46<9:54:36,  3.70it/s]
 64%|██████▍   | 239328/371472 [8:00:47<10:11:57,  3.60it/s]
 64%|██████▍   | 239329/371472 [8:00:47<10:09:19,  3.61it/s]
 64%|██████▍   | 239330/371472 [8:00:47<10:01:59,  3.66it/s]
 64%|██████▍   | 239331/371472 [8:00:47<10:44:32,  3.42it/s]
 64%|██████▍   | 239332/371472 [8:00:48<10:50:17,  3.39it/s]
 64%|██████▍   | 239333/371472 [8:00:48<10:11:52,  3.60it/s]
 64%|██████▍   | 239334/371472 [8:00:48<10:09:37,  3.61it/s]
 64%|██████▍   | 239335/371472 [8:00:49<10:07:16,  3.63it/s]
 64%|██████▍   | 239336/371472 [8:00:49<9:46:06,  3.76it/s] 
 64%|██████▍   | 239337/371472 [8:00:49<10:12:43,  3.59it/s]
 64%|██████▍   | 239338/371472 [8:00:49<9:58:01,  3.68it/s] 
 64%|██████▍   | 239339/371472 [8:00:50<9:39:29,  3.80it/s]
 64%|██████▍   | 239340/371472 [8:00:50<9:28:25,  3.87it/s]
                                                           
{'loss': 2.9606, 'learning_rate': 4.2030101919886233e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239340/371472 [8:00:50<9:28:25,  3.87it/s]
 64%|██████▍   | 239341/371472 [8:00:50<9:55:27,  3.70it/s]
 64%|██████▍   | 239342/371472 [8:00:50<10:11:57,  3.60it/s]
 64%|██████▍   | 239343/371472 [8:00:51<10:03:59,  3.65it/s]
 64%|██████▍   | 239344/371472 [8:00:51<9:46:42,  3.75it/s] 
 64%|██████▍   | 239345/371472 [8:00:51<9:43:03,  3.78it/s]
 64%|██████▍   | 239346/371472 [8:00:52<9:49:30,  3.74it/s]
 64%|██████▍   | 239347/371472 [8:00:52<9:28:25,  3.87it/s]
 64%|██████▍   | 239348/371472 [8:00:52<10:24:02,  3.53it/s]
 64%|██████▍   | 239349/371472 [8:00:52<10:11:52,  3.60it/s]
 64%|██████▍   | 239350/371472 [8:00:53<10:47:30,  3.40it/s]
 64%|██████▍   | 239351/371472 [8:00:53<10:24:53,  3.52it/s]
 64%|██████▍   | 239352/371472 [8:00:53<10:34:04,  3.47it/s]
 64%|██████▍   | 239353/371472 [8:00:54<10:28:31,  3.50it/s]
 64%|██████▍   | 239354/371472 [8:00:54<10:26:39,  3.51it/s]
 64%|██████▍   | 239355/371472 [8:00:54<9:57:18,  3.69it/s] 
 64%|██████▍   | 239356/371472 [8:00:54<9:41:04,  3.79it/s]
 64%|██████▍   | 239357/371472 [8:00:55<9:42:36,  3.78it/s]
 64%|██████▍   | 239358/371472 [8:00:55<9:54:19,  3.70it/s]
 64%|██████▍   | 239359/371472 [8:00:55<9:58:05,  3.68it/s]
 64%|██████▍   | 239360/371472 [8:00:55<10:01:28,  3.66it/s]
                                                            
{'loss': 2.8283, 'learning_rate': 4.2025253722338335e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239360/371472 [8:00:55<10:01:28,  3.66it/s]
 64%|██████▍   | 239361/371472 [8:00:56<9:44:55,  3.76it/s] 
 64%|██████▍   | 239362/371472 [8:00:56<10:00:38,  3.67it/s]
 64%|██████▍   | 239363/371472 [8:00:56<10:03:36,  3.65it/s]
 64%|██████▍   | 239364/371472 [8:00:57<11:21:33,  3.23it/s]
 64%|██████▍   | 239365/371472 [8:00:57<11:14:58,  3.26it/s]
 64%|██████▍   | 239366/371472 [8:00:57<10:44:57,  3.41it/s]
 64%|██████▍   | 239367/371472 [8:00:57<10:19:36,  3.55it/s]
 64%|██████▍   | 239368/371472 [8:00:58<10:09:40,  3.61it/s]
 64%|██████▍   | 239369/371472 [8:00:58<11:07:57,  3.30it/s]
 64%|██████▍   | 239370/371472 [8:00:58<10:50:37,  3.38it/s]
 64%|██████▍   | 239371/371472 [8:00:59<10:36:57,  3.46it/s]
 64%|██████▍   | 239372/371472 [8:00:59<10:40:19,  3.44it/s]
 64%|██████▍   | 239373/371472 [8:00:59<10:27:25,  3.51it/s]
 64%|██████▍   | 239374/371472 [8:00:59<10:03:03,  3.65it/s]
 64%|██████▍   | 239375/371472 [8:01:00<10:17:27,  3.57it/s]
 64%|██████▍   | 239376/371472 [8:01:00<9:55:02,  3.70it/s] 
 64%|██████▍   | 239377/371472 [8:01:00<9:43:01,  3.78it/s]
 64%|██████▍   | 239378/371472 [8:01:00<9:49:58,  3.73it/s]
 64%|██████▍   | 239379/371472 [8:01:01<9:36:48,  3.82it/s]
 64%|██████▍   | 239380/371472 [8:01:01<10:00:38,  3.67it/s]
                                                            
{'loss': 2.9331, 'learning_rate': 4.2020405524790453e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239380/371472 [8:01:01<10:00:38,  3.67it/s]
 64%|██████▍   | 239381/371472 [8:01:01<9:57:36,  3.68it/s] 
 64%|██████▍   | 239382/371472 [8:01:02<9:57:44,  3.68it/s]
 64%|██████▍   | 239383/371472 [8:01:02<9:51:34,  3.72it/s]
 64%|██████▍   | 239384/371472 [8:01:02<9:50:31,  3.73it/s]
 64%|██████▍   | 239385/371472 [8:01:02<10:21:04,  3.54it/s]
 64%|██████▍   | 239386/371472 [8:01:03<10:25:50,  3.52it/s]
 64%|██████▍   | 239387/371472 [8:01:03<11:14:07,  3.27it/s]
 64%|██████▍   | 239388/371472 [8:01:03<10:48:17,  3.40it/s]
 64%|██████▍   | 239389/371472 [8:01:04<10:28:26,  3.50it/s]
 64%|██████▍   | 239390/371472 [8:01:04<10:16:19,  3.57it/s]
 64%|██████▍   | 239391/371472 [8:01:04<10:17:31,  3.56it/s]
 64%|██████▍   | 239392/371472 [8:01:04<10:09:20,  3.61it/s]
 64%|██████▍   | 239393/371472 [8:01:05<10:08:54,  3.62it/s]
 64%|██████▍   | 239394/371472 [8:01:05<10:42:53,  3.42it/s]
 64%|██████▍   | 239395/371472 [8:01:05<10:31:17,  3.49it/s]
 64%|██████▍   | 239396/371472 [8:01:06<10:17:38,  3.56it/s]
 64%|██████▍   | 239397/371472 [8:01:06<11:03:21,  3.32it/s]
 64%|██████▍   | 239398/371472 [8:01:06<11:42:48,  3.13it/s]
 64%|██████▍   | 239399/371472 [8:01:07<11:20:56,  3.23it/s]
 64%|██████▍   | 239400/371472 [8:01:07<11:02:08,  3.32it/s]
                                                            
{'loss': 2.8145, 'learning_rate': 4.201555732724256e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239400/371472 [8:01:07<11:02:08,  3.32it/s]
 64%|██████▍   | 239401/371472 [8:01:07<10:38:22,  3.45it/s]
 64%|██████▍   | 239402/371472 [8:01:07<10:43:02,  3.42it/s]
 64%|██████▍   | 239403/371472 [8:01:08<10:22:32,  3.54it/s]
 64%|██████▍   | 239404/371472 [8:01:08<10:06:10,  3.63it/s]
 64%|██████▍   | 239405/371472 [8:01:08<9:49:27,  3.73it/s] 
 64%|██████▍   | 239406/371472 [8:01:09<10:35:27,  3.46it/s]
 64%|██████▍   | 239407/371472 [8:01:09<10:13:55,  3.59it/s]
 64%|██████▍   | 239408/371472 [8:01:09<10:07:24,  3.62it/s]
 64%|██████▍   | 239409/371472 [8:01:09<10:09:11,  3.61it/s]
 64%|██████▍   | 239410/371472 [8:01:10<10:17:14,  3.57it/s]
 64%|██████▍   | 239411/371472 [8:01:10<10:03:31,  3.65it/s]
 64%|██████▍   | 239412/371472 [8:01:10<11:23:53,  3.22it/s]
 64%|██████▍   | 239413/371472 [8:01:11<10:50:01,  3.39it/s]
 64%|██████▍   | 239414/371472 [8:01:11<10:41:15,  3.43it/s]
 64%|██████▍   | 239415/371472 [8:01:11<10:38:28,  3.45it/s]
 64%|██████▍   | 239416/371472 [8:01:11<10:25:54,  3.52it/s]
 64%|██████▍   | 239417/371472 [8:01:12<10:43:40,  3.42it/s]
 64%|██████▍   | 239418/371472 [8:01:12<10:14:45,  3.58it/s]
 64%|██████▍   | 239419/371472 [8:01:12<9:58:38,  3.68it/s] 
 64%|██████▍   | 239420/371472 [8:01:12<9:50:15,  3.73it/s]
                                                           
{'loss': 2.8592, 'learning_rate': 4.2010709129694667e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239420/371472 [8:01:12<9:50:15,  3.73it/s]
 64%|██████▍   | 239421/371472 [8:01:13<9:54:23,  3.70it/s]
 64%|██████▍   | 239422/371472 [8:01:13<10:06:48,  3.63it/s]
 64%|██████▍   | 239423/371472 [8:01:13<10:05:35,  3.63it/s]
 64%|██████▍   | 239424/371472 [8:01:14<10:32:14,  3.48it/s]
 64%|██████▍   | 239425/371472 [8:01:14<10:40:17,  3.44it/s]
 64%|██████▍   | 239426/371472 [8:01:14<11:03:39,  3.32it/s]
 64%|██████▍   | 239427/371472 [8:01:14<10:49:08,  3.39it/s]
 64%|██████▍   | 239428/371472 [8:01:15<10:25:01,  3.52it/s]
 64%|██████▍   | 239429/371472 [8:01:15<10:49:38,  3.39it/s]
 64%|██████▍   | 239430/371472 [8:01:15<10:42:53,  3.42it/s]
 64%|██████▍   | 239431/371472 [8:01:16<10:31:21,  3.49it/s]
 64%|██████▍   | 239432/371472 [8:01:16<10:05:00,  3.64it/s]
 64%|██████▍   | 239433/371472 [8:01:16<10:00:03,  3.67it/s]
 64%|██████▍   | 239434/371472 [8:01:17<11:36:36,  3.16it/s]
 64%|██████▍   | 239435/371472 [8:01:17<11:09:51,  3.29it/s]
 64%|██████▍   | 239436/371472 [8:01:17<10:55:10,  3.36it/s]
 64%|██████▍   | 239437/371472 [8:01:17<10:35:00,  3.47it/s]
 64%|██████▍   | 239438/371472 [8:01:18<11:19:35,  3.24it/s]
 64%|██████▍   | 239439/371472 [8:01:18<10:57:17,  3.35it/s]
 64%|██████▍   | 239440/371472 [8:01:18<11:13:00,  3.27it/s]
                                                            
{'loss': 2.8084, 'learning_rate': 4.200586093214678e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239440/371472 [8:01:18<11:13:00,  3.27it/s]
 64%|██████▍   | 239441/371472 [8:01:19<10:45:11,  3.41it/s]
 64%|██████▍   | 239442/371472 [8:01:19<10:30:40,  3.49it/s]
 64%|██████▍   | 239443/371472 [8:01:19<10:39:21,  3.44it/s]
 64%|██████▍   | 239444/371472 [8:01:19<10:27:15,  3.51it/s]
 64%|██████▍   | 239445/371472 [8:01:20<10:18:27,  3.56it/s]
 64%|██████▍   | 239446/371472 [8:01:20<10:12:51,  3.59it/s]
 64%|██████▍   | 239447/371472 [8:01:20<10:52:14,  3.37it/s]
 64%|██████▍   | 239448/371472 [8:01:21<10:58:11,  3.34it/s]
 64%|██████▍   | 239449/371472 [8:01:21<10:29:53,  3.49it/s]
 64%|██████▍   | 239450/371472 [8:01:21<10:21:20,  3.54it/s]
 64%|██████▍   | 239451/371472 [8:01:21<10:29:27,  3.50it/s]
 64%|██████▍   | 239452/371472 [8:01:22<10:13:43,  3.59it/s]
 64%|██████▍   | 239453/371472 [8:01:22<10:29:35,  3.49it/s]
 64%|██████▍   | 239454/371472 [8:01:22<11:27:34,  3.20it/s]
 64%|██████▍   | 239455/371472 [8:01:23<11:32:14,  3.18it/s]
 64%|██████▍   | 239456/371472 [8:01:23<11:02:56,  3.32it/s]
 64%|██████▍   | 239457/371472 [8:01:23<11:00:51,  3.33it/s]
 64%|██████▍   | 239458/371472 [8:01:24<11:05:33,  3.31it/s]
 64%|██████▍   | 239459/371472 [8:01:24<10:35:01,  3.46it/s]
 64%|██████▍   | 239460/371472 [8:01:24<10:30:35,  3.49it/s]
                                                            
{'loss': 2.7075, 'learning_rate': 4.200101273459889e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239460/371472 [8:01:24<10:30:35,  3.49it/s]
 64%|██████▍   | 239461/371472 [8:01:24<10:33:44,  3.47it/s]
 64%|██████▍   | 239462/371472 [8:01:25<10:40:05,  3.44it/s]
 64%|██████▍   | 239463/371472 [8:01:25<10:23:56,  3.53it/s]
 64%|██████▍   | 239464/371472 [8:01:25<10:46:39,  3.40it/s]
 64%|██████▍   | 239465/371472 [8:01:26<10:29:18,  3.50it/s]
 64%|██████▍   | 239466/371472 [8:01:26<10:48:06,  3.39it/s]
 64%|██████▍   | 239467/371472 [8:01:26<11:29:33,  3.19it/s]
 64%|██████▍   | 239468/371472 [8:01:26<10:48:08,  3.39it/s]
 64%|██████▍   | 239469/371472 [8:01:27<10:39:20,  3.44it/s]
 64%|██████▍   | 239470/371472 [8:01:27<10:22:13,  3.54it/s]
 64%|██████▍   | 239471/371472 [8:01:27<10:03:00,  3.65it/s]
 64%|██████▍   | 239472/371472 [8:01:28<10:23:34,  3.53it/s]
 64%|██████▍   | 239473/371472 [8:01:28<10:25:21,  3.52it/s]
 64%|██████▍   | 239474/371472 [8:01:28<11:00:03,  3.33it/s]
 64%|██████▍   | 239475/371472 [8:01:29<11:11:36,  3.28it/s]
 64%|██████▍   | 239476/371472 [8:01:29<10:42:07,  3.43it/s]
 64%|██████▍   | 239477/371472 [8:01:29<10:33:21,  3.47it/s]
 64%|██████▍   | 239478/371472 [8:01:29<10:16:44,  3.57it/s]
 64%|██████▍   | 239479/371472 [8:01:30<10:29:11,  3.50it/s]
 64%|██████▍   | 239480/371472 [8:01:30<11:06:34,  3.30it/s]
                                                            
{'loss': 2.7826, 'learning_rate': 4.1996164537051005e-07, 'epoch': 10.31}
+
 64%|██████▍   | 239480/371472 [8:01:30<11:06:34,  3.30it/s]
 64%|██████▍   | 239481/371472 [8:01:30<11:13:42,  3.27it/s]
 64%|██████▍   | 239482/371472 [8:01:31<11:36:50,  3.16it/s]
 64%|██████▍   | 239483/371472 [8:01:31<11:22:36,  3.22it/s]
 64%|██████▍   | 239484/371472 [8:01:31<10:54:37,  3.36it/s]
 64%|██████▍   | 239485/371472 [8:01:31<10:47:43,  3.40it/s]
 64%|██████▍   | 239486/371472 [8:01:32<10:43:21,  3.42it/s]
 64%|██████▍   | 239487/371472 [8:01:32<10:29:59,  3.49it/s]
 64%|██████▍   | 239488/371472 [8:01:32<10:43:22,  3.42it/s]
 64%|██████▍   | 239489/371472 [8:01:33<10:38:06,  3.45it/s]
 64%|██████▍   | 239490/371472 [8:01:33<10:24:47,  3.52it/s]
 64%|██████▍   | 239491/371472 [8:01:33<10:21:14,  3.54it/s]
 64%|██████▍   | 239492/371472 [8:01:33<10:19:08,  3.55it/s]
 64%|██████▍   | 239493/371472 [8:01:34<10:05:32,  3.63it/s]
 64%|██████▍   | 239494/371472 [8:01:34<10:03:13,  3.65it/s]
 64%|██████▍   | 239495/371472 [8:01:34<9:53:28,  3.71it/s] 
 64%|██████▍   | 239496/371472 [8:01:35<9:50:39,  3.72it/s]
 64%|██████▍   | 239497/371472 [8:01:35<9:52:23,  3.71it/s]
 64%|██████▍   | 239498/371472 [8:01:35<10:01:26,  3.66it/s]
 64%|██████▍   | 239499/371472 [8:01:35<10:09:30,  3.61it/s]
 64%|██████▍   | 239500/371472 [8:01:36<9:53:41,  3.70it/s] 
                                                           
{'loss': 2.9542, 'learning_rate': 4.1991316339503107e-07, 'epoch': 10.32}
+
 64%|██████▍   | 239500/371472 [8:01:36<9:53:41,  3.70it/s]
 64%|██████▍   | 239501/371472 [8:01:36<9:56:35,  3.69it/s]
 64%|██████▍   | 239502/371472 [8:01:36<9:59:29,  3.67it/s]
 64%|██████▍   | 239503/371472 [8:01:37<10:56:22,  3.35it/s]
 64%|██████▍   | 239504/371472 [8:01:37<10:49:57,  3.38it/s]
 64%|██████▍   | 239505/371472 [8:01:37<10:53:35,  3.37it/s]
 64%|██████▍   | 239506/371472 [8:01:37<10:30:22,  3.49it/s]
 64%|██████▍   | 239507/371472 [8:01:38<10:18:52,  3.55it/s]
 64%|██████▍   | 239508/371472 [8:01:38<10:23:55,  3.53it/s]
 64%|██████▍   | 239509/371472 [8:01:38<10:00:05,  3.67it/s]
 64%|██████▍   | 239510/371472 [8:01:38<10:04:48,  3.64it/s]
 64%|██████▍   | 239511/371472 [8:01:39<9:52:48,  3.71it/s] 
 64%|██████▍   | 239512/371472 [8:01:39<10:07:42,  3.62it/s]
 64%|██████▍   | 239513/371472 [8:01:39<10:12:50,  3.59it/s]
 64%|██████▍   | 239514/371472 [8:01:40<9:42:43,  3.77it/s] 
 64%|██████▍   | 239515/371472 [8:01:40<10:15:53,  3.57it/s]
 64%|██████▍   | 239516/371472 [8:01:40<10:26:01,  3.51it/s]
 64%|██████▍   | 239517/371472 [8:01:40<10:15:48,  3.57it/s]
 64%|██████▍   | 239518/371472 [8:01:41<10:29:44,  3.49it/s]
 64%|██████▍   | 239519/371472 [8:01:41<10:20:50,  3.54it/s]
 64%|██████▍   | 239520/371472 [8:01:41<10:01:56,  3.65it/s]
                                                            
{'loss': 2.7922, 'learning_rate': 4.1986468141955224e-07, 'epoch': 10.32}
+
 64%|██████▍   | 239520/371472 [8:01:41<10:01:56,  3.65it/s]
 64%|██████▍   | 239521/371472 [8:01:41<9:52:02,  3.71it/s] 
 64%|██████▍   | 239522/371472 [8:01:42<9:44:16,  3.76it/s]
 64%|██████▍   | 239523/371472 [8:01:42<9:47:40,  3.74it/s]
 64%|██████▍   | 239524/371472 [8:01:42<9:41:17,  3.78it/s]
 64%|██████▍   | 239525/371472 [8:01:43<9:57:48,  3.68it/s]
 64%|██████▍   | 239526/371472 [8:01:43<10:15:16,  3.57it/s]
 64%|██████▍   | 239527/371472 [8:01:43<9:59:47,  3.67it/s] 
 64%|██████▍   | 239528/371472 [8:01:43<9:44:48,  3.76it/s]
 64%|██████▍   | 239529/371472 [8:01:44<9:37:06,  3.81it/s]
 64%|██████▍   | 239530/371472 [8:01:44<9:40:57,  3.79it/s]
 64%|██████▍   | 239531/371472 [8:01:44<9:26:42,  3.88it/s]
 64%|██████▍   | 239532/371472 [8:01:44<9:48:59,  3.73it/s]
 64%|██████▍   | 239533/371472 [8:01:45<10:08:01,  3.62it/s]
 64%|██████▍   | 239534/371472 [8:01:45<10:16:59,  3.56it/s]
 64%|██████▍   | 239535/371472 [8:01:45<9:59:44,  3.67it/s] 
 64%|██████▍   | 239536/371472 [8:01:46<9:47:01,  3.75it/s]
 64%|██████▍   | 239537/371472 [8:01:46<10:21:30,  3.54it/s]
 64%|██████▍   | 239538/371472 [8:01:46<10:24:13,  3.52it/s]
 64%|██████▍   | 239539/371472 [8:01:46<10:03:19,  3.64it/s]
 64%|██████▍   | 239540/371472 [8:01:47<10:56:07,  3.35it/s]
                                                            
{'loss': 2.9649, 'learning_rate': 4.198161994440733e-07, 'epoch': 10.32}
+
 64%|██████▍   | 239540/371472 [8:01:47<10:56:07,  3.35it/s]
 64%|██████▍   | 239541/371472 [8:01:47<10:25:59,  3.51it/s]
 64%|██████▍   | 239542/371472 [8:01:47<9:55:10,  3.69it/s] 
 64%|██████▍   | 239543/371472 [8:01:48<9:56:51,  3.68it/s]
 64%|██████▍   | 239544/371472 [8:01:48<9:49:35,  3.73it/s]
 64%|██████▍   | 239545/371472 [8:01:48<10:29:45,  3.49it/s]
 64%|██████▍   | 239546/371472 [8:01:48<10:08:04,  3.62it/s]
 64%|██████▍   | 239547/371472 [8:01:49<10:03:16,  3.64it/s]
 64%|██████▍   | 239548/371472 [8:01:49<10:16:11,  3.57it/s]
 64%|██████▍   | 239549/371472 [8:01:49<9:59:18,  3.67it/s] 
 64%|██████▍   | 239550/371472 [8:01:49<9:57:42,  3.68it/s]
 64%|██████▍   | 239551/371472 [8:01:50<9:40:13,  3.79it/s]
 64%|██████▍   | 239552/371472 [8:01:50<9:40:06,  3.79it/s]
 64%|██████▍   | 239553/371472 [8:01:50<9:53:22,  3.71it/s]
 64%|██████▍   | 239554/371472 [8:01:51<10:27:34,  3.50it/s]
 64%|██████▍   | 239555/371472 [8:01:51<10:18:53,  3.55it/s]
 64%|██████▍   | 239556/371472 [8:01:51<10:16:01,  3.57it/s]
 64%|██████▍   | 239557/371472 [8:01:51<9:59:54,  3.66it/s] 
 64%|██████▍   | 239558/371472 [8:01:52<9:42:10,  3.78it/s]
 64%|██████▍   | 239559/371472 [8:01:52<9:55:25,  3.69it/s]
 64%|██████▍   | 239560/371472 [8:01:52<10:01:45,  3.65it/s]
                                                            
{'loss': 2.9466, 'learning_rate': 4.1976771746859444e-07, 'epoch': 10.32}
+
 64%|██████▍   | 239560/371472 [8:01:52<10:01:45,  3.65it/s]
 64%|██████▍   | 239561/371472 [8:01:52<10:12:54,  3.59it/s]
 64%|██████▍   | 239562/371472 [8:01:53<10:18:03,  3.56it/s]
 64%|██████▍   | 239563/371472 [8:01:53<10:04:38,  3.64it/s]
 64%|██████▍   | 239564/371472 [8:01:53<10:16:08,  3.57it/s]
 64%|██████▍   | 239565/371472 [8:01:54<9:38:58,  3.80it/s] 
 64%|██████▍   | 239566/371472 [8:01:54<10:23:08,  3.53it/s]
 64%|██████▍   | 239567/371472 [8:01:54<10:00:15,  3.66it/s]
 64%|██████▍   | 239568/371472 [8:01:54<10:18:42,  3.55it/s]
 64%|██████▍   | 239569/371472 [8:01:55<9:55:22,  3.69it/s] 
 64%|██████▍   | 239570/371472 [8:01:55<10:15:34,  3.57it/s]
 64%|██████▍   | 239571/371472 [8:01:55<11:26:09,  3.20it/s]
 64%|██████▍   | 239572/371472 [8:01:56<11:14:37,  3.26it/s]
 64%|██████▍   | 239573/371472 [8:01:56<11:28:03,  3.19it/s]
 64%|██████▍   | 239574/371472 [8:01:56<10:47:01,  3.40it/s]
 64%|██████▍   | 239575/371472 [8:01:56<10:42:25,  3.42it/s]
 64%|██████▍   | 239576/371472 [8:01:57<10:31:28,  3.48it/s]
 64%|██████▍   | 239577/371472 [8:01:57<10:09:28,  3.61it/s]
 64%|██████▍   | 239578/371472 [8:01:57<9:40:45,  3.79it/s] 
 64%|██████▍   | 239579/371472 [8:01:58<9:55:58,  3.69it/s]
 64%|██████▍   | 239580/371472 [8:01:58<9:54:38,  3.70it/s]
                                                           
{'loss': 2.9064, 'learning_rate': 4.197192354931155e-07, 'epoch': 10.32}
+
 64%|██████▍   | 239580/371472 [8:01:58<9:54:38,  3.70it/s]
 64%|██████▍   | 239581/371472 [8:01:58<10:07:37,  3.62it/s]
 64%|██████▍   | 239582/371472 [8:01:58<10:30:21,  3.49it/s]
 64%|██████▍   | 239583/371472 [8:01:59<10:39:49,  3.44it/s]
 64%|██████▍   | 239584/371472 [8:01:59<10:28:58,  3.49it/s]
 64%|██████▍   | 239585/371472 [8:01:59<11:27:06,  3.20it/s]
 64%|██████▍   | 239586/371472 [8:02:00<10:52:03,  3.37it/s]
 64%|██████▍   | 239587/371472 [8:02:00<10:23:24,  3.53it/s]
 64%|██████▍   | 239588/371472 [8:02:00<10:01:45,  3.65it/s]
 64%|██████▍   | 239589/371472 [8:02:00<9:48:24,  3.74it/s] 
 64%|██████▍   | 239590/371472 [8:02:01<10:38:11,  3.44it/s]
 64%|██████▍   | 239591/371472 [8:02:01<10:17:17,  3.56it/s]
 64%|██████▍   | 239592/371472 [8:02:01<10:22:30,  3.53it/s]
 64%|██████▍   | 239593/371472 [8:02:02<10:42:17,  3.42it/s]
 64%|██████▍   | 239594/371472 [8:02:02<11:37:37,  3.15it/s]
 64%|██████▍   | 239595/371472 [8:02:02<11:00:20,  3.33it/s]
 64%|██████▍   | 239596/371472 [8:02:02<10:34:43,  3.46it/s]
 64%|██████▍   | 239597/371472 [8:02:03<10:20:47,  3.54it/s]
 64%|███���██▍   | 239598/371472 [8:02:03<10:10:37,  3.60it/s]
 64%|██████▍   | 239599/371472 [8:02:03<10:17:15,  3.56it/s]
 65%|██████▍   | 239600/371472 [8:02:04<10:21:12,  3.54it/s]
                                                            
{'loss': 2.856, 'learning_rate': 4.196707535176367e-07, 'epoch': 10.32}
+
 65%|██████▍   | 239600/371472 [8:02:04<10:21:12,  3.54it/s]
 65%|██████▍   | 239601/371472 [8:02:04<10:30:27,  3.49it/s]
 65%|██████▍   | 239602/371472 [8:02:04<10:30:21,  3.49it/s]
 65%|██████▍   | 239603/371472 [8:02:05<11:28:01,  3.19it/s]
 65%|██████▍   | 239604/371472 [8:02:05<11:22:13,  3.22it/s]
 65%|██████▍   | 239605/371472 [8:02:05<10:55:23,  3.35it/s]
 65%|██████▍   | 239606/371472 [8:02:05<10:31:22,  3.48it/s]
 65%|██████▍   | 239607/371472 [8:02:06<10:11:33,  3.59it/s]
 65%|██████▍   | 239608/371472 [8:02:06<9:53:27,  3.70it/s] 
 65%|██████▍   | 239609/371472 [8:02:06<9:52:03,  3.71it/s]
 65%|██████▍   | 239610/371472 [8:02:07<10:36:42,  3.45it/s]
 65%|██████▍   | 239611/371472 [8:02:07<10:37:49,  3.45it/s]
 65%|██████▍   | 239612/371472 [8:02:07<10:47:30,  3.39it/s]
 65%|██████▍   | 239613/371472 [8:02:07<10:24:35,  3.52it/s]
 65%|██████▍   | 239614/371472 [8:02:08<10:54:55,  3.36it/s]
 65%|██████▍   | 239615/371472 [8:02:08<10:25:11,  3.52it/s]
 65%|██████▍   | 239616/371472 [8:02:08<10:24:51,  3.52it/s]
 65%|██████▍   | 239617/371472 [8:02:08<10:14:41,  3.58it/s]
 65%|██████▍   | 239618/371472 [8:02:09<10:08:30,  3.61it/s]
 65%|██████▍   | 239619/371472 [8:02:09<10:07:35,  3.62it/s]
 65%|██████▍   | 239620/371472 [8:02:09<11:02:42,  3.32it/s]
                                                            
{'loss': 2.7955, 'learning_rate': 4.196222715421577e-07, 'epoch': 10.32}
+
 65%|██████▍   | 239620/371472 [8:02:09<11:02:42,  3.32it/s]
 65%|██████▍   | 239621/371472 [8:02:10<10:35:59,  3.46it/s]
 65%|██████▍   | 239622/371472 [8:02:10<10:31:05,  3.48it/s]
 65%|██████▍   | 239623/371472 [8:02:10<10:39:10,  3.44it/s]
 65%|██████▍   | 239624/371472 [8:02:11<10:25:44,  3.51it/s]
 65%|██████▍   | 239625/371472 [8:02:11<11:17:50,  3.24it/s]
 65%|██████▍   | 239626/371472 [8:02:11<11:06:45,  3.30it/s]
 65%|██████▍   | 239627/371472 [8:02:12<12:35:01,  2.91it/s]
 65%|██████▍   | 239628/371472 [8:02:12<12:29:39,  2.93it/s]
 65%|██████▍   | 239629/371472 [8:02:12<11:53:30,  3.08it/s]
 65%|██████▍   | 239630/371472 [8:02:13<11:37:57,  3.15it/s]
 65%|██████▍   | 239631/371472 [8:02:13<11:41:54,  3.13it/s]
 65%|██████▍   | 239632/371472 [8:02:13<11:02:35,  3.32it/s]
 65%|██████▍   | 239633/371472 [8:02:13<10:47:19,  3.39it/s]
 65%|██████▍   | 239634/371472 [8:02:14<10:29:09,  3.49it/s]
 65%|██████▍   | 239635/371472 [8:02:14<10:14:33,  3.58it/s]
 65%|██████▍   | 239636/371472 [8:02:14<10:53:41,  3.36it/s]
 65%|██████▍   | 239637/371472 [8:02:15<10:47:38,  3.39it/s]
 65%|██████▍   | 239638/371472 [8:02:15<11:15:48,  3.25it/s]
 65%|██████▍   | 239639/371472 [8:02:15<10:37:19,  3.45it/s]
 65%|██████▍   | 239640/371472 [8:02:15<10:18:54,  3.55it/s]
                                                            
{'loss': 2.7034, 'learning_rate': 4.195737895666789e-07, 'epoch': 10.32}
+
 65%|██████▍   | 239640/371472 [8:02:15<10:18:54,  3.55it/s]
 65%|██████▍   | 239641/371472 [8:02:16<10:35:51,  3.46it/s]
 65%|██████▍   | 239642/371472 [8:02:16<10:32:22,  3.47it/s]
 65%|██████▍   | 239643/371472 [8:02:16<10:20:12,  3.54it/s]
 65%|██████▍   | 239644/371472 [8:02:17<11:08:28,  3.29it/s]
 65%|██████▍   | 239645/371472 [8:02:17<11:08:57,  3.28it/s]
 65%|██████▍   | 239646/371472 [8:02:17<10:32:45,  3.47it/s]
 65%|██████▍   | 239647/371472 [8:02:17<10:14:13,  3.58it/s]
 65%|██████▍   | 239648/371472 [8:02:18<9:59:49,  3.66it/s] 
 65%|██████▍   | 239649/371472 [8:02:18<10:00:30,  3.66it/s]
 65%|██████▍   | 239650/371472 [8:02:18<10:09:02,  3.61it/s]
 65%|██████▍   | 239651/371472 [8:02:19<9:51:24,  3.71it/s] 
 65%|██████▍   | 239652/371472 [8:02:19<9:58:06,  3.67it/s]
 65%|██████▍   | 239653/371472 [8:02:19<9:54:49,  3.69it/s]
 65%|██████▍   | 239654/371472 [8:02:19<9:42:30,  3.77it/s]
 65%|██████▍   | 239655/371472 [8:02:20<10:08:01,  3.61it/s]
 65%|██████▍   | 239656/371472 [8:02:20<10:04:53,  3.63it/s]
 65%|██████▍   | 239657/371472 [8:02:20<10:04:12,  3.64it/s]
 65%|��█████▍   | 239658/371472 [8:02:20<10:41:24,  3.43it/s]
 65%|██████▍   | 239659/371472 [8:02:21<10:25:59,  3.51it/s]
 65%|██████▍   | 239660/371472 [8:02:21<10:50:17,  3.38it/s]
                                                            
{'loss': 2.8718, 'learning_rate': 4.1952530759119995e-07, 'epoch': 10.32}
+
 65%|██████▍   | 239660/371472 [8:02:21<10:50:17,  3.38it/s]
 65%|██████▍   | 239661/371472 [8:02:21<10:33:44,  3.47it/s]
 65%|██████▍   | 239662/371472 [8:02:22<10:33:30,  3.47it/s]
 65%|██████▍   | 239663/371472 [8:02:22<10:27:44,  3.50it/s]
 65%|██████▍   | 239664/371472 [8:02:22<10:11:13,  3.59it/s]
 65%|██████▍   | 239665/371472 [8:02:22<10:26:47,  3.50it/s]
 65%|██████▍   | 239666/371472 [8:02:23<10:23:18,  3.52it/s]
 65%|██████▍   | 239667/371472 [8:02:23<10:10:49,  3.60it/s]
 65%|██████▍   | 239668/371472 [8:02:23<10:29:22,  3.49it/s]
 65%|██████▍   | 239669/371472 [8:02:24<10:35:57,  3.45it/s]
 65%|██████▍   | 239670/371472 [8:02:24<10:11:23,  3.59it/s]
 65%|██████▍   | 239671/371472 [8:02:24<9:43:02,  3.77it/s] 
 65%|██████▍   | 239672/371472 [8:02:24<11:00:07,  3.33it/s]
 65%|██████▍   | 239673/371472 [8:02:25<10:39:31,  3.43it/s]
 65%|██████▍   | 239674/371472 [8:02:25<10:22:32,  3.53it/s]
 65%|██████▍   | 239675/371472 [8:02:25<10:00:24,  3.66it/s]
 65%|██████▍   | 239676/371472 [8:02:26<9:36:51,  3.81it/s] 
 65%|██████▍   | 239677/371472 [8:02:26<9:32:00,  3.84it/s]
 65%|██████▍   | 239678/371472 [8:02:26<9:47:01,  3.74it/s]
 65%|██████▍   | 239679/371472 [8:02:26<10:06:18,  3.62it/s]
 65%|██████▍   | 239680/371472 [8:02:27<10:02:01,  3.65it/s]
                                                            
{'loss': 2.9219, 'learning_rate': 4.194768256157211e-07, 'epoch': 10.32}
+
 65%|██████▍   | 239680/371472 [8:02:27<10:02:01,  3.65it/s]
 65%|██████▍   | 239681/371472 [8:02:27<10:16:49,  3.56it/s]
 65%|██████▍   | 239682/371472 [8:02:27<10:23:22,  3.52it/s]
 65%|██████▍   | 239683/371472 [8:02:27<9:58:45,  3.67it/s] 
 65%|██████▍   | 239684/371472 [8:02:28<10:28:24,  3.50it/s]
 65%|██████▍   | 239685/371472 [8:02:28<10:31:58,  3.48it/s]
 65%|██████▍   | 239686/371472 [8:02:28<10:25:19,  3.51it/s]
 65%|██████▍   | 239687/371472 [8:02:29<10:19:45,  3.54it/s]
 65%|██████▍   | 239688/371472 [8:02:29<10:05:15,  3.63it/s]
 65%|██████▍   | 239689/371472 [8:02:29<9:59:06,  3.67it/s] 
 65%|██████▍   | 239690/371472 [8:02:29<9:42:34,  3.77it/s]
 65%|██████▍   | 239691/371472 [8:02:30<9:45:07,  3.75it/s]
 65%|██████▍   | 239692/371472 [8:02:30<9:48:02,  3.73it/s]
 65%|██████▍   | 239693/371472 [8:02:30<9:45:33,  3.75it/s]
 65%|██████▍   | 239694/371472 [8:02:30<9:58:01,  3.67it/s]
 65%|██████▍   | 239695/371472 [8:02:31<9:58:53,  3.67it/s]
 65%|██████▍   | 239696/371472 [8:02:31<10:06:53,  3.62it/s]
 65%|██████▍   | 239697/371472 [8:02:31<9:56:30,  3.68it/s] 
 65%|██████▍   | 239698/371472 [8:02:32<9:48:59,  3.73it/s]
 65%|██████▍   | 239699/371472 [8:02:32<10:50:51,  3.37it/s]
 65%|██████▍   | 239700/371472 [8:02:32<10:24:45,  3.52it/s]
                                                            
{'loss': 2.9832, 'learning_rate': 4.1942834364024215e-07, 'epoch': 10.32}
+
 65%|██████▍   | 239700/371472 [8:02:32<10:24:45,  3.52it/s]
 65%|██████▍   | 239701/371472 [8:02:32<10:24:18,  3.52it/s]
 65%|██████▍   | 239702/371472 [8:02:33<10:31:12,  3.48it/s]
 65%|██████▍   | 239703/371472 [8:02:33<11:02:02,  3.32it/s]
 65%|██████▍   | 239704/371472 [8:02:33<11:08:00,  3.29it/s]
 65%|██████▍   | 239705/371472 [8:02:34<11:35:49,  3.16it/s]
 65%|██████▍   | 239706/371472 [8:02:34<11:36:25,  3.15it/s]
 65%|██████▍   | 239707/371472 [8:02:34<11:16:48,  3.24it/s]
 65%|██████▍   | 239708/371472 [8:02:35<11:07:14,  3.29it/s]
 65%|██████▍   | 239709/371472 [8:02:35<10:29:29,  3.49it/s]
 65%|██████▍   | 239710/371472 [8:02:35<10:23:17,  3.52it/s]
 65%|██████▍   | 239711/371472 [8:02:35<10:12:26,  3.59it/s]
 65%|██████▍   | 239712/371472 [8:02:36<10:17:00,  3.56it/s]
 65%|██████▍   | 239713/371472 [8:02:36<10:10:01,  3.60it/s]
 65%|██████▍   | 239714/371472 [8:02:36<10:01:20,  3.65it/s]
 65%|██████▍   | 239715/371472 [8:02:37<10:22:44,  3.53it/s]
 65%|██████▍   | 239716/371472 [8:02:37<11:04:18,  3.31it/s]
 65%|██████▍   | 239717/371472 [8:02:37<11:10:35,  3.27it/s]
 65%|██████▍   | 239718/371472 [8:02:37<10:48:03,  3.39it/s]
 65%|██████▍   | 239719/371472 [8:02:38<10:27:45,  3.50it/s]
 65%|██████▍   | 239720/371472 [8:02:38<10:21:18,  3.53it/s]
                                                            
{'loss': 2.8878, 'learning_rate': 4.193798616647633e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239720/371472 [8:02:38<10:21:18,  3.53it/s]
 65%|██████▍   | 239721/371472 [8:02:38<11:07:19,  3.29it/s]
 65%|██████▍   | 239722/371472 [8:02:39<11:13:31,  3.26it/s]
 65%|██████▍   | 239723/371472 [8:02:39<10:39:52,  3.43it/s]
 65%|██████▍   | 239724/371472 [8:02:39<10:25:26,  3.51it/s]
 65%|██████▍   | 239725/371472 [8:02:40<10:23:46,  3.52it/s]
 65%|██████▍   | 239726/371472 [8:02:40<10:33:30,  3.47it/s]
 65%|██████▍   | 239727/371472 [8:02:40<10:18:22,  3.55it/s]
 65%|██████▍   | 239728/371472 [8:02:40<10:05:44,  3.62it/s]
 65%|██████▍   | 239729/371472 [8:02:41<10:00:19,  3.66it/s]
 65%|██████▍   | 239730/371472 [8:02:41<10:08:26,  3.61it/s]
 65%|██████▍   | 239731/371472 [8:02:41<11:02:27,  3.31it/s]
 65%|██████▍   | 239732/371472 [8:02:41<10:20:34,  3.54it/s]
 65%|██████▍   | 239733/371472 [8:02:42<11:09:29,  3.28it/s]
 65%|██████▍   | 239734/371472 [8:02:42<10:51:50,  3.37it/s]
 65%|██████▍   | 239735/371472 [8:02:42<10:44:59,  3.40it/s]
 65%|██████▍   | 239736/371472 [8:02:43<11:48:59,  3.10it/s]
 65%|██████▍   | 239737/371472 [8:02:43<11:15:56,  3.25it/s]
 65%|██████▍   | 239738/371472 [8:02:43<10:59:29,  3.33it/s]
 65%|██████▍   | 239739/371472 [8:02:44<10:51:41,  3.37it/s]
 65%|██████▍   | 239740/371472 [8:02:44<10:23:29,  3.52it/s]
                                                            
{'loss': 2.9684, 'learning_rate': 4.1933137968928435e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239740/371472 [8:02:44<10:23:29,  3.52it/s]
 65%|██████▍   | 239741/371472 [8:02:44<10:49:14,  3.38it/s]
 65%|██████▍   | 239742/371472 [8:02:45<10:56:15,  3.35it/s]
 65%|██████▍   | 239743/371472 [8:02:45<10:41:24,  3.42it/s]
 65%|██████▍   | 239744/371472 [8:02:45<10:24:28,  3.52it/s]
 65%|██████▍   | 239745/371472 [8:02:45<10:22:28,  3.53it/s]
 65%|██████▍   | 239746/371472 [8:02:46<10:16:09,  3.56it/s]
 65%|██████▍   | 239747/371472 [8:02:46<9:59:21,  3.66it/s] 
 65%|██████▍   | 239748/371472 [8:02:46<10:38:27,  3.44it/s]
 65%|██████▍   | 239749/371472 [8:02:46<10:28:05,  3.50it/s]
 65%|██████▍   | 239750/371472 [8:02:47<10:36:07,  3.45it/s]
 65%|██████▍   | 239751/371472 [8:02:47<10:37:43,  3.44it/s]
 65%|██████▍   | 239752/371472 [8:02:47<10:21:31,  3.53it/s]
 65%|██████▍   | 239753/371472 [8:02:48<10:23:52,  3.52it/s]
 65%|██████▍   | 239754/371472 [8:02:48<10:50:25,  3.38it/s]
 65%|██████▍   | 239755/371472 [8:02:48<10:27:32,  3.50it/s]
 65%|██████▍   | 239756/371472 [8:02:48<10:24:45,  3.51it/s]
 65%|██████▍   | 239757/371472 [8:02:49<10:10:18,  3.60it/s]
 65%|██████▍   | 239758/371472 [8:02:49<10:20:35,  3.54it/s]
 65%|██████▍   | 239759/371472 [8:02:49<11:23:32,  3.21it/s]
 65%|██████▍   | 239760/371472 [8:02:50<10:37:56,  3.44it/s]
                                                            
{'loss': 2.9659, 'learning_rate': 4.192828977138055e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239760/371472 [8:02:50<10:37:56,  3.44it/s]
 65%|██████▍   | 239761/371472 [8:02:50<10:23:42,  3.52it/s]
 65%|██████▍   | 239762/371472 [8:02:50<10:17:58,  3.55it/s]
 65%|██████▍   | 239763/371472 [8:02:51<10:21:00,  3.53it/s]
 65%|██████▍   | 239764/371472 [8:02:51<10:03:23,  3.64it/s]
 65%|██████▍   | 239765/371472 [8:02:51<10:01:59,  3.65it/s]
 65%|██████▍   | 239766/371472 [8:02:51<10:18:08,  3.55it/s]
 65%|██████▍   | 239767/371472 [8:02:52<10:39:47,  3.43it/s]
 65%|██████▍   | 239768/371472 [8:02:52<10:43:37,  3.41it/s]
 65%|██████▍   | 239769/371472 [8:02:52<10:25:33,  3.51it/s]
 65%|██████▍   | 239770/371472 [8:02:52<10:09:13,  3.60it/s]
 65%|██████▍   | 239771/371472 [8:02:53<10:20:55,  3.54it/s]
 65%|██████▍   | 239772/371472 [8:02:53<11:01:14,  3.32it/s]
 65%|██████▍   | 239773/371472 [8:02:53<11:39:15,  3.14it/s]
 65%|██████▍   | 239774/371472 [8:02:54<11:13:27,  3.26it/s]
 65%|██████▍   | 239775/371472 [8:02:54<10:47:15,  3.39it/s]
 65%|██████▍   | 239776/371472 [8:02:54<10:26:30,  3.50it/s]
 65%|██████▍   | 239777/371472 [8:02:55<10:23:21,  3.52it/s]
 65%|██████▍   | 239778/371472 [8:02:55<9:51:56,  3.71it/s] 
 65%|██████▍   | 239779/371472 [8:02:55<10:10:10,  3.60it/s]
 65%|██████▍   | 239780/371472 [8:02:55<11:05:33,  3.30it/s]
                                                            
{'loss': 2.9007, 'learning_rate': 4.192344157383266e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239780/371472 [8:02:55<11:05:33,  3.30it/s]
 65%|██████▍   | 239781/371472 [8:02:56<11:18:22,  3.24it/s]
 65%|██████▍   | 239782/371472 [8:02:56<11:07:33,  3.29it/s]
 65%|██████▍   | 239783/371472 [8:02:56<11:04:42,  3.30it/s]
 65%|██████▍   | 239784/371472 [8:02:57<11:26:54,  3.20it/s]
 65%|██████▍   | 239785/371472 [8:02:57<10:53:00,  3.36it/s]
 65%|██████▍   | 239786/371472 [8:02:57<10:42:34,  3.42it/s]
 65%|██████▍   | 239787/371472 [8:02:58<10:25:54,  3.51it/s]
 65%|██████▍   | 239788/371472 [8:02:58<10:10:46,  3.59it/s]
 65%|██████▍   | 239789/371472 [8:02:58<9:57:44,  3.67it/s] 
 65%|██████▍   | 239790/371472 [8:02:58<10:17:22,  3.55it/s]
 65%|██████▍   | 239791/371472 [8:02:59<10:00:31,  3.65it/s]
 65%|██████▍   | 239792/371472 [8:02:59<10:02:02,  3.65it/s]
 65%|██████▍   | 239793/371472 [8:02:59<10:18:25,  3.55it/s]
 65%|██████▍   | 239794/371472 [8:02:59<10:15:57,  3.56it/s]
 65%|██████▍   | 239795/371472 [8:03:00<10:49:30,  3.38it/s]
 65%|██████▍   | 239796/371472 [8:03:00<10:30:19,  3.48it/s]
 65%|██████▍   | 239797/371472 [8:03:00<10:38:07,  3.44it/s]
 65%|██████▍   | 239798/371472 [8:03:01<10:15:14,  3.57it/s]
 65%|██████▍   | 239799/371472 [8:03:01<9:54:04,  3.69it/s] 
 65%|██████▍   | 239800/371472 [8:03:01<9:57:14,  3.67it/s]
                                                           
{'loss': 2.9019, 'learning_rate': 4.191859337628477e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239800/371472 [8:03:01<9:57:14,  3.67it/s]
 65%|██████▍   | 239801/371472 [8:03:01<10:21:13,  3.53it/s]
 65%|██████▍   | 239802/371472 [8:03:02<10:01:19,  3.65it/s]
 65%|██████▍   | 239803/371472 [8:03:02<11:14:48,  3.25it/s]
 65%|██████▍   | 239804/371472 [8:03:02<10:55:18,  3.35it/s]
 65%|██████▍   | 239805/371472 [8:03:03<10:25:35,  3.51it/s]
 65%|██████▍   | 239806/371472 [8:03:03<10:36:21,  3.45it/s]
 65%|██████▍   | 239807/371472 [8:03:03<10:58:18,  3.33it/s]
 65%|██████▍   | 239808/371472 [8:03:04<10:46:09,  3.40it/s]
 65%|██████▍   | 239809/371472 [8:03:04<10:26:55,  3.50it/s]
 65%|██████▍   | 239810/371472 [8:03:04<10:19:35,  3.54it/s]
 65%|██████▍   | 239811/371472 [8:03:04<10:23:28,  3.52it/s]
 65%|██████▍   | 239812/371472 [8:03:05<10:16:46,  3.56it/s]
 65%|██████▍   | 239813/371472 [8:03:05<10:14:36,  3.57it/s]
 65%|██████▍   | 239814/371472 [8:03:05<10:09:31,  3.60it/s]
 65%|██████▍   | 239815/371472 [8:03:05<10:01:09,  3.65it/s]
 65%|██████▍   | 239816/371472 [8:03:06<9:48:47,  3.73it/s] 
 65%|██████▍   | 239817/371472 [8:03:06<9:54:19,  3.69it/s]
 65%|██████▍   | 239818/371472 [8:03:06<10:14:32,  3.57it/s]
 65%|██████▍   | 239819/371472 [8:03:07<10:32:26,  3.47it/s]
 65%|██████▍   | 239820/371472 [8:03:07<11:13:55,  3.26it/s]
                                                            
{'loss': 2.9702, 'learning_rate': 4.191374517873688e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239820/371472 [8:03:07<11:13:55,  3.26it/s]
 65%|██████▍   | 239821/371472 [8:03:07<10:29:05,  3.49it/s]
 65%|██████▍   | 239822/371472 [8:03:07<10:06:27,  3.62it/s]
 65%|██████▍   | 239823/371472 [8:03:08<9:50:39,  3.71it/s] 
 65%|██████▍   | 239824/371472 [8:03:08<10:04:39,  3.63it/s]
 65%|██████▍   | 239825/371472 [8:03:08<10:04:43,  3.63it/s]
 65%|██████▍   | 239826/371472 [8:03:09<10:19:40,  3.54it/s]
 65%|██████▍   | 239827/371472 [8:03:09<10:27:02,  3.50it/s]
 65%|██████▍   | 239828/371472 [8:03:09<10:33:02,  3.47it/s]
 65%|██████▍   | 239829/371472 [8:03:09<10:14:25,  3.57it/s]
 65%|██████▍   | 239830/371472 [8:03:10<10:10:24,  3.59it/s]
 65%|██████▍   | 239831/371472 [8:03:10<9:55:14,  3.69it/s] 
 65%|██████▍   | 239832/371472 [8:03:10<9:44:53,  3.75it/s]
 65%|██████▍   | 239833/371472 [8:03:10<10:16:25,  3.56it/s]
 65%|██████▍   | 239834/371472 [8:03:11<10:32:41,  3.47it/s]
 65%|██████▍   | 239835/371472 [8:03:11<10:10:40,  3.59it/s]
 65%|██████▍   | 239836/371472 [8:03:11<10:18:09,  3.55it/s]
 65%|██████▍   | 239837/371472 [8:03:12<9:56:51,  3.68it/s] 
 65%|██████▍   | 239838/371472 [8:03:12<10:09:01,  3.60it/s]
 65%|██████▍   | 239839/371472 [8:03:12<10:39:15,  3.43it/s]
 65%|██████▍   | 239840/371472 [8:03:12<10:31:46,  3.47it/s]
                                                            
{'loss': 2.9309, 'learning_rate': 4.1908896981188997e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239840/371472 [8:03:12<10:31:46,  3.47it/s]
 65%|██████▍   | 239841/371472 [8:03:13<10:37:52,  3.44it/s]
 65%|██████▍   | 239842/371472 [8:03:13<10:36:42,  3.45it/s]
 65%|██████▍   | 239843/371472 [8:03:13<10:08:23,  3.61it/s]
 65%|██████▍   | 239844/371472 [8:03:14<9:57:42,  3.67it/s] 
 65%|██████▍   | 239845/371472 [8:03:14<9:36:45,  3.80it/s]
 65%|██████▍   | 239846/371472 [8:03:14<9:40:27,  3.78it/s]
 65%|██████▍   | 239847/371472 [8:03:14<9:47:19,  3.74it/s]
 65%|██████▍   | 239848/371472 [8:03:15<10:01:17,  3.65it/s]
 65%|██████▍   | 239849/371472 [8:03:15<10:36:12,  3.45it/s]
 65%|██████▍   | 239850/371472 [8:03:15<10:32:10,  3.47it/s]
 65%|██████▍   | 239851/371472 [8:03:15<10:02:14,  3.64it/s]
 65%|██████▍   | 239852/371472 [8:03:16<9:49:03,  3.72it/s] 
 65%|██████▍   | 239853/371472 [8:03:16<9:34:02,  3.82it/s]
 65%|██████▍   | 239854/371472 [8:03:16<10:22:06,  3.53it/s]
 65%|██████▍   | 239855/371472 [8:03:17<10:12:11,  3.58it/s]
 65%|██████▍   | 239856/371472 [8:03:17<10:05:06,  3.63it/s]
 65%|██████▍   | 239857/371472 [8:03:17<10:12:52,  3.58it/s]
 65%|██████▍   | 239858/371472 [8:03:18<11:50:34,  3.09it/s]
 65%|██████▍   | 239859/371472 [8:03:18<11:15:32,  3.25it/s]
 65%|██████▍   | 239860/371472 [8:03:18<11:26:24,  3.20it/s]
                                                            
{'loss': 3.0042, 'learning_rate': 4.1904048783641104e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239860/371472 [8:03:18<11:26:24,  3.20it/s]
 65%|██████▍   | 239861/371472 [8:03:18<10:55:44,  3.35it/s]
 65%|██████▍   | 239862/371472 [8:03:19<11:21:38,  3.22it/s]
 65%|██████▍   | 239863/371472 [8:03:19<10:40:14,  3.43it/s]
 65%|██████▍   | 239864/371472 [8:03:19<11:07:01,  3.29it/s]
 65%|██████▍   | 239865/371472 [8:03:20<10:49:34,  3.38it/s]
 65%|██████▍   | 239866/371472 [8:03:20<10:30:00,  3.48it/s]
 65%|██████▍   | 239867/371472 [8:03:20<10:57:41,  3.34it/s]
 65%|██████▍   | 239868/371472 [8:03:20<10:32:35,  3.47it/s]
 65%|██████▍   | 239869/371472 [8:03:21<10:02:48,  3.64it/s]
 65%|██████▍   | 239870/371472 [8:03:21<10:40:48,  3.42it/s]
 65%|██████▍   | 239871/371472 [8:03:21<11:11:47,  3.26it/s]
 65%|██████▍   | 239872/371472 [8:03:22<11:01:16,  3.32it/s]
 65%|██████▍   | 239873/371472 [8:03:22<10:37:35,  3.44it/s]
 65%|██████▍   | 239874/371472 [8:03:22<10:37:16,  3.44it/s]
 65%|██████▍   | 239875/371472 [8:03:23<10:09:42,  3.60it/s]
 65%|██████▍   | 239876/371472 [8:03:23<10:01:02,  3.65it/s]
 65%|██████▍   | 239877/371472 [8:03:23<9:56:36,  3.68it/s] 
 65%|██████▍   | 239878/371472 [8:03:23<10:17:14,  3.55it/s]
 65%|██████▍   | 239879/371472 [8:03:24<10:11:26,  3.59it/s]
 65%|██████▍   | 239880/371472 [8:03:24<10:50:19,  3.37it/s]
                                                            
{'loss': 2.9979, 'learning_rate': 4.1899200586093216e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239880/371472 [8:03:24<10:50:19,  3.37it/s]
 65%|██████▍   | 239881/371472 [8:03:24<10:40:05,  3.43it/s]
 65%|██████▍   | 239882/371472 [8:03:24<10:17:11,  3.55it/s]
 65%|██████▍   | 239883/371472 [8:03:25<10:22:23,  3.52it/s]
 65%|██████▍   | 239884/371472 [8:03:25<10:52:29,  3.36it/s]
 65%|██████▍   | 239885/371472 [8:03:25<10:15:00,  3.57it/s]
 65%|██████▍   | 239886/371472 [8:03:26<10:08:09,  3.61it/s]
 65%|██████▍   | 239887/371472 [8:03:26<11:26:08,  3.20it/s]
 65%|██████▍   | 239888/371472 [8:03:26<11:04:48,  3.30it/s]
 65%|██████▍   | 239889/371472 [8:03:27<12:24:10,  2.95it/s]
 65%|██████▍   | 239890/371472 [8:03:27<11:36:49,  3.15it/s]
 65%|██████▍   | 239891/371472 [8:03:27<10:58:48,  3.33it/s]
 65%|██████▍   | 239892/371472 [8:03:28<10:33:22,  3.46it/s]
 65%|██████▍   | 239893/371472 [8:03:28<10:19:09,  3.54it/s]
 65%|██████▍   | 239894/371472 [8:03:28<10:12:56,  3.58it/s]
 65%|██████▍   | 239895/371472 [8:03:28<10:55:59,  3.34it/s]
 65%|██████▍   | 239896/371472 [8:03:29<10:34:21,  3.46it/s]
 65%|██████▍   | 239897/371472 [8:03:29<11:01:29,  3.32it/s]
 65%|██████▍   | 239898/371472 [8:03:29<11:10:21,  3.27it/s]
 65%|██████▍   | 239899/371472 [8:03:30<11:04:54,  3.30it/s]
 65%|██████▍   | 239900/371472 [8:03:30<10:52:17,  3.36it/s]
                                                            
{'loss': 2.9086, 'learning_rate': 4.1894352388545324e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239900/371472 [8:03:30<10:52:17,  3.36it/s]
 65%|██████▍   | 239901/371472 [8:03:30<11:34:14,  3.16it/s]
 65%|██████▍   | 239902/371472 [8:03:31<11:08:36,  3.28it/s]
 65%|██████▍   | 239903/371472 [8:03:31<11:07:47,  3.28it/s]
 65%|██████▍   | 239904/371472 [8:03:31<11:34:41,  3.16it/s]
 65%|██████▍   | 239905/371472 [8:03:31<11:29:04,  3.18it/s]
 65%|██████▍   | 239906/371472 [8:03:32<12:02:13,  3.04it/s]
 65%|██████▍   | 239907/371472 [8:03:32<11:38:11,  3.14it/s]
 65%|██████▍   | 239908/371472 [8:03:32<11:12:22,  3.26it/s]
 65%|██████▍   | 239909/371472 [8:03:33<10:57:07,  3.34it/s]
 65%|██████▍   | 239910/371472 [8:03:33<10:50:19,  3.37it/s]
 65%|██████▍   | 239911/371472 [8:03:33<10:27:46,  3.49it/s]
 65%|██████▍   | 239912/371472 [8:03:34<10:07:40,  3.61it/s]
 65%|██████▍   | 239913/371472 [8:03:34<10:52:44,  3.36it/s]
 65%|██████▍   | 239914/371472 [8:03:34<10:26:33,  3.50it/s]
 65%|██████▍   | 239915/371472 [8:03:34<10:22:09,  3.52it/s]
 65%|██████▍   | 239916/371472 [8:03:35<10:04:16,  3.63it/s]
 65%|██████▍   | 239917/371472 [8:03:35<9:55:11,  3.68it/s] 
 65%|██████▍   | 239918/371472 [8:03:35<10:17:51,  3.55it/s]
 65%|██████▍   | 239919/371472 [8:03:35<10:04:55,  3.62it/s]
 65%|██████▍   | 239920/371472 [8:03:36<10:08:33,  3.60it/s]
                                                            
{'loss': 2.9217, 'learning_rate': 4.188950419099744e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239920/371472 [8:03:36<10:08:33,  3.60it/s]
 65%|██████▍   | 239921/371472 [8:03:36<10:08:47,  3.60it/s]
 65%|██████▍   | 239922/371472 [8:03:36<10:22:24,  3.52it/s]
 65%|██████▍   | 239923/371472 [8:03:37<10:05:47,  3.62it/s]
 65%|██████▍   | 239924/371472 [8:03:37<10:08:58,  3.60it/s]
 65%|██████▍   | 239925/371472 [8:03:37<11:18:12,  3.23it/s]
 65%|██████▍   | 239926/371472 [8:03:38<11:13:41,  3.25it/s]
 65%|██████▍   | 239927/371472 [8:03:38<11:14:16,  3.25it/s]
 65%|██████▍   | 239928/371472 [8:03:38<10:41:10,  3.42it/s]
 65%|██████▍   | 239929/371472 [8:03:38<11:13:49,  3.25it/s]
 65%|██████▍   | 239930/371472 [8:03:39<10:52:09,  3.36it/s]
 65%|██████▍   | 239931/371472 [8:03:39<10:14:55,  3.57it/s]
 65%|██████▍   | 239932/371472 [8:03:39<10:19:22,  3.54it/s]
 65%|██████▍   | 239933/371472 [8:03:40<10:04:21,  3.63it/s]
 65%|██████▍   | 239934/371472 [8:03:40<10:10:53,  3.59it/s]
 65%|██████▍   | 239935/371472 [8:03:40<10:04:12,  3.63it/s]
 65%|██████▍   | 239936/371472 [8:03:40<9:52:44,  3.70it/s] 
 65%|██████▍   | 239937/371472 [8:03:41<9:39:52,  3.78it/s]
 65%|██████▍   | 239938/371472 [8:03:41<10:16:56,  3.55it/s]
 65%|██████▍   | 239939/371472 [8:03:41<9:54:46,  3.69it/s] 
 65%|██████▍   | 239940/371472 [8:03:41<9:33:47,  3.82it/s]
                                                           
{'loss': 2.9671, 'learning_rate': 4.1884655993449543e-07, 'epoch': 10.33}
+
 65%|██████▍   | 239940/371472 [8:03:41<9:33:47,  3.82it/s]
 65%|██████▍   | 239941/371472 [8:03:42<10:02:16,  3.64it/s]
 65%|██████▍   | 239942/371472 [8:03:42<10:01:50,  3.64it/s]
 65%|██████▍   | 239943/371472 [8:03:42<10:04:10,  3.63it/s]
 65%|██████▍   | 239944/371472 [8:03:43<9:51:05,  3.71it/s] 
 65%|██████▍   | 239945/371472 [8:03:43<9:37:23,  3.80it/s]
 65%|██████▍   | 239946/371472 [8:03:43<10:04:05,  3.63it/s]
 65%|██████▍   | 239947/371472 [8:03:43<10:45:07,  3.40it/s]
 65%|██████▍   | 239948/371472 [8:03:44<10:35:47,  3.45it/s]
 65%|██████▍   | 239949/371472 [8:03:44<10:43:35,  3.41it/s]
 65%|██████▍   | 239950/371472 [8:03:44<10:16:52,  3.55it/s]
 65%|██████▍   | 239951/371472 [8:03:45<10:10:01,  3.59it/s]
 65%|██████▍   | 239952/371472 [8:03:45<9:42:52,  3.76it/s] 
 65%|██████▍   | 239953/371472 [8:03:45<10:08:53,  3.60it/s]
 65%|██████▍   | 239954/371472 [8:03:45<10:11:27,  3.58it/s]
 65%|██████▍   | 239955/371472 [8:03:46<11:14:46,  3.25it/s]
 65%|██████▍   | 239956/371472 [8:03:46<10:43:43,  3.41it/s]
 65%|██████▍   | 239957/371472 [8:03:46<10:18:02,  3.55it/s]
 65%|██████▍   | 239958/371472 [8:03:47<10:38:00,  3.44it/s]
 65%|██████▍   | 239959/371472 [8:03:47<10:49:52,  3.37it/s]
 65%|██████▍   | 239960/371472 [8:03:47<10:21:17,  3.53it/s]
                                                            
{'loss': 2.9144, 'learning_rate': 4.187980779590165e-07, 'epoch': 10.34}
+
 65%|██████▍   | 239960/371472 [8:03:47<10:21:17,  3.53it/s]
 65%|██████▍   | 239961/371472 [8:03:48<11:42:35,  3.12it/s]
 65%|██████▍   | 239962/371472 [8:03:48<11:01:57,  3.31it/s]
 65%|██████▍   | 239963/371472 [8:03:48<11:06:54,  3.29it/s]
 65%|██████▍   | 239964/371472 [8:03:48<10:35:47,  3.45it/s]
 65%|██████▍   | 239965/371472 [8:03:49<10:34:12,  3.46it/s]
 65%|██████▍   | 239966/371472 [8:03:49<11:23:27,  3.21it/s]
 65%|██████▍   | 239967/371472 [8:03:49<11:00:36,  3.32it/s]
 65%|██████▍   | 239968/371472 [8:03:50<10:45:13,  3.40it/s]
 65%|██████▍   | 239969/371472 [8:03:50<10:17:18,  3.55it/s]
 65%|██████▍   | 239970/371472 [8:03:50<9:50:38,  3.71it/s] 
 65%|██████▍   | 239971/371472 [8:03:50<10:06:15,  3.62it/s]
 65%|██████▍   | 239972/371472 [8:03:51<10:09:26,  3.60it/s]
 65%|██████▍   | 239973/371472 [8:03:51<10:13:18,  3.57it/s]
 65%|██████▍   | 239974/371472 [8:03:51<9:48:54,  3.72it/s] 
 65%|██████▍   | 239975/371472 [8:03:51<9:53:18,  3.69it/s]
 65%|██████▍   | 239976/371472 [8:03:52<9:42:31,  3.76it/s]
 65%|██████▍   | 239977/371472 [8:03:52<9:18:28,  3.92it/s]
 65%|██████▍   | 239978/371472 [8:03:52<9:16:36,  3.94it/s]
 65%|██████▍   | 239979/371472 [8:03:52<9:02:37,  4.04it/s]
 65%|██████▍   | 239980/371472 [8:03:53<9:01:23,  4.05it/s]
                                                           
{'loss': 2.6921, 'learning_rate': 4.187495959835377e-07, 'epoch': 10.34}
+
 65%|██████▍   | 239980/371472 [8:03:53<9:01:23,  4.05it/s]
 65%|██████▍   | 239981/371472 [8:03:53<10:04:03,  3.63it/s]
 65%|██████▍   | 239982/371472 [8:03:53<9:51:37,  3.70it/s] 
 65%|██████▍   | 239983/371472 [8:03:53<9:43:54,  3.75it/s]
 65%|██████▍   | 239984/371472 [8:03:54<9:58:21,  3.66it/s]
 65%|██████▍   | 239985/371472 [8:03:54<10:01:04,  3.65it/s]
 65%|██████▍   | 239986/371472 [8:03:54<9:43:16,  3.76it/s] 
 65%|██████▍   | 239987/371472 [8:03:55<9:39:23,  3.78it/s]
 65%|██████▍   | 239988/371472 [8:03:55<9:43:32,  3.76it/s]
 65%|██████▍   | 239989/371472 [8:03:55<9:45:13,  3.74it/s]
 65%|██████▍   | 239990/371472 [8:03:55<9:49:45,  3.72it/s]
 65%|██████▍   | 239991/371472 [8:03:56<9:50:44,  3.71it/s]
 65%|██████▍   | 239992/371472 [8:03:56<9:52:08,  3.70it/s]
 65%|██████▍   | 239993/371472 [8:03:56<10:00:37,  3.65it/s]
 65%|██████▍   | 239994/371472 [8:03:56<10:09:47,  3.59it/s]
 65%|██████▍   | 239995/371472 [8:03:57<10:04:52,  3.62it/s]
 65%|██████▍   | 239996/371472 [8:03:57<10:03:31,  3.63it/s]
 65%|██████▍   | 239997/371472 [8:03:57<9:56:15,  3.67it/s] 
 65%|██████▍   | 239998/371472 [8:03:58<10:44:06,  3.40it/s]
 65%|██████▍   | 239999/371472 [8:03:58<10:34:03,  3.46it/s]
 65%|██████▍   | 240000/371472 [8:03:58<10:32:43,  3.46it/s]
                                                            
{'loss': 2.7335, 'learning_rate': 4.187011140080587e-07, 'epoch': 10.34}
+
 65%|██████▍   | 240000/371472 [8:03:58<10:32:43,  3.46it/s]
 65%|██████▍   | 240001/371472 [8:03:58<10:26:39,  3.50it/s]
 65%|██████▍   | 240002/371472 [8:03:59<10:37:59,  3.43it/s]
 65%|██████▍   | 240003/371472 [8:03:59<10:35:07,  3.45it/s]
 65%|██████▍   | 240004/371472 [8:03:59<10:49:32,  3.37it/s]
 65%|██████▍   | 240005/371472 [8:04:00<11:27:39,  3.19it/s]
 65%|██████▍   | 240006/371472 [8:04:00<11:21:00,  3.22it/s]
 65%|██████▍   | 240007/371472 [8:04:00<10:55:18,  3.34it/s]
 65%|██████▍   | 240008/371472 [8:04:01<10:36:00,  3.44it/s]
 65%|██████▍   | 240009/371472 [8:04:01<10:27:59,  3.49it/s]
 65%|██████▍   | 240010/371472 [8:04:01<10:45:21,  3.40it/s]
 65%|██████▍   | 240011/371472 [8:04:01<10:27:33,  3.49it/s]
 65%|██████▍   | 240012/371472 [8:04:02<11:59:30,  3.05it/s]
 65%|██████▍   | 240013/371472 [8:04:02<11:54:17,  3.07it/s]
 65%|██████▍   | 240014/371472 [8:04:02<11:08:45,  3.28it/s]
 65%|██████▍   | 240015/371472 [8:04:03<10:51:00,  3.37it/s]
 65%|██████▍   | 240016/371472 [8:04:03<10:19:40,  3.54it/s]
 65%|██████▍   | 240017/371472 [8:04:03<10:26:03,  3.50it/s]
 65%|██████▍   | 240018/371472 [8:04:04<10:19:00,  3.54it/s]
 65%|██████▍   | 240019/371472 [8:04:04<10:04:35,  3.62it/s]
 65%|██████▍   | 240020/371472 [8:04:04<9:55:53,  3.68it/s] 
                                                           
{'loss': 2.7453, 'learning_rate': 4.186526320325799e-07, 'epoch': 10.34}
+
 65%|██████▍   | 240020/371472 [8:04:04<9:55:53,  3.68it/s]
 65%|██████▍   | 240021/371472 [8:04:04<10:14:14,  3.57it/s]
 65%|██████▍   | 240022/371472 [8:04:05<10:05:31,  3.62it/s]
 65%|██████▍   | 240023/371472 [8:04:05<10:14:21,  3.57it/s]
 65%|██████▍   | 240024/371472 [8:04:05<9:48:42,  3.72it/s] 
 65%|██████▍   | 240025/371472 [8:04:05<10:07:34,  3.61it/s]
 65%|██████▍   | 240026/371472 [8:04:06<9:53:24,  3.69it/s] 
 65%|██████▍   | 240027/371472 [8:04:06<9:46:33,  3.73it/s]
 65%|██████▍   | 240028/371472 [8:04:06<9:44:40,  3.75it/s]
 65%|██████▍   | 240029/371472 [8:04:06<9:37:45,  3.79it/s]
 65%|██████▍   | 240030/371472 [8:04:07<9:41:30,  3.77it/s]
 65%|██████▍   | 240031/371472 [8:04:07<9:48:21,  3.72it/s]
 65%|██████▍   | 240032/371472 [8:04:07<9:50:24,  3.71it/s]
 65%|██████▍   | 240033/371472 [8:04:08<10:02:40,  3.63it/s]
 65%|██████▍   | 240034/371472 [8:04:08<10:38:43,  3.43it/s]
 65%|██████▍   | 240035/371472 [8:04:08<10:49:16,  3.37it/s]
 65%|██████▍   | 240036/371472 [8:04:08<10:24:43,  3.51it/s]
 65%|██████▍   | 240037/371472 [8:04:09<10:10:28,  3.59it/s]
 65%|██████▍   | 240038/371472 [8:04:09<10:01:30,  3.64it/s]
 65%|██████▍   | 240039/371472 [8:04:09<9:46:50,  3.73it/s] 
 65%|██████▍   | 240040/371472 [8:04:10<9:35:15,  3.81it/s]
                                                           
{'loss': 2.741, 'learning_rate': 4.1860415005710095e-07, 'epoch': 10.34}
+
 65%|██████▍   | 240040/371472 [8:04:10<9:35:15,  3.81it/s]
 65%|██████▍   | 240041/371472 [8:04:10<10:15:50,  3.56it/s]
 65%|██████▍   | 240042/371472 [8:04:10<9:47:08,  3.73it/s] 
 65%|██████▍   | 240043/371472 [8:04:10<9:52:26,  3.70it/s]
 65%|██████▍   | 240044/371472 [8:04:11<9:47:10,  3.73it/s]
 65%|██████▍   | 240045/371472 [8:04:11<9:43:59,  3.75it/s]
 65%|██████▍   | 240046/371472 [8:04:11<9:49:11,  3.72it/s]
 65%|██████▍   | 240047/371472 [8:04:11<9:44:22,  3.75it/s]
 65%|██████▍   | 240048/371472 [8:04:12<9:40:30,  3.77it/s]
 65%|██████▍   | 240049/371472 [8:04:12<9:53:43,  3.69it/s]
 65%|██████▍   | 240050/371472 [8:04:12<9:53:58,  3.69it/s]
 65%|██████▍   | 240051/371472 [8:04:13<9:47:58,  3.73it/s]
 65%|██████▍   | 240052/371472 [8:04:13<9:40:01,  3.78it/s]
 65%|██████▍   | 240053/371472 [8:04:13<9:33:42,  3.82it/s]
 65%|██████▍   | 240054/371472 [8:04:13<9:41:13,  3.77it/s]
 65%|██████▍   | 240055/371472 [8:04:14<9:42:19,  3.76it/s]
 65%|██████▍   | 240056/371472 [8:04:14<9:54:16,  3.69it/s]
 65%|██████▍   | 240057/371472 [8:04:14<9:50:43,  3.71it/s]
 65%|██████▍   | 240058/371472 [8:04:14<9:43:58,  3.75it/s]
 65%|██████▍   | 240059/371472 [8:04:15<10:15:23,  3.56it/s]
 65%|██████▍   | 240060/371472 [8:04:15<10:12:20,  3.58it/s]
                                                            
{'loss': 2.9329, 'learning_rate': 4.1855566808162207e-07, 'epoch': 10.34}
+
 65%|██████▍   | 240060/371472 [8:04:15<10:12:20,  3.58it/s]
 65%|██████▍   | 240061/371472 [8:04:15<10:37:20,  3.44it/s]
 65%|██████▍   | 240062/371472 [8:04:16<10:27:06,  3.49it/s]
 65%|██████▍   | 240063/371472 [8:04:16<10:05:09,  3.62it/s]
 65%|██████▍   | 240064/371472 [8:04:16<10:21:09,  3.53it/s]
 65%|██████▍   | 240065/371472 [8:04:16<10:01:34,  3.64it/s]
 65%|██████▍   | 240066/371472 [8:04:17<10:01:48,  3.64it/s]
 65%|██████▍   | 240067/371472 [8:04:17<9:58:38,  3.66it/s] 
 65%|██████▍   | 240068/371472 [8:04:17<9:57:44,  3.66it/s]
 65%|██████▍   | 240069/371472 [8:04:17<9:34:23,  3.81it/s]
 65%|██████▍   | 240070/371472 [8:04:18<9:48:19,  3.72it/s]
 65%|██████▍   | 240071/371472 [8:04:18<9:42:51,  3.76it/s]
 65%|██████▍   | 240072/371472 [8:04:18<9:54:15,  3.69it/s]
 65%|██████▍   | 240073/371472 [8:04:19<9:49:15,  3.72it/s]
 65%|██████▍   | 240074/371472 [8:04:19<10:20:11,  3.53it/s]
 65%|██████▍   | 240075/371472 [8:04:19<10:26:40,  3.49it/s]
 65%|██████▍   | 240076/371472 [8:04:19<10:20:33,  3.53it/s]
 65%|██████▍   | 240077/371472 [8:04:20<10:17:55,  3.54it/s]
 65%|██████▍   | 240078/371472 [8:04:20<10:01:10,  3.64it/s]
 65%|██████▍   | 240079/371472 [8:04:20<9:59:16,  3.65it/s] 
 65%|██████▍   | 240080/371472 [8:04:20<9:55:33,  3.68it/s]
                                                           
{'loss': 3.0622, 'learning_rate': 4.1850718610614314e-07, 'epoch': 10.34}
+
 65%|██████▍   | 240080/371472 [8:04:20<9:55:33,  3.68it/s]
 65%|██████▍   | 240081/371472 [8:04:21<10:22:29,  3.52it/s]
 65%|██████▍   | 240082/371472 [8:04:21<10:20:13,  3.53it/s]
 65%|██████▍   | 240083/371472 [8:04:21<10:11:55,  3.58it/s]
 65%|██████▍   | 240084/371472 [8:04:22<9:57:40,  3.66it/s] 
 65%|██████▍   | 240085/371472 [8:04:22<9:45:36,  3.74it/s]
 65%|██████▍   | 240086/371472 [8:04:22<9:39:15,  3.78it/s]
 65%|██████▍   | 240087/371472 [8:04:22<10:06:38,  3.61it/s]
 65%|██████▍   | 240088/371472 [8:04:23<11:02:40,  3.30it/s]
 65%|██████▍   | 240089/371472 [8:04:23<10:29:47,  3.48it/s]
 65%|██████▍   | 240090/371472 [8:04:23<10:09:12,  3.59it/s]
 65%|██████▍   | 240091/371472 [8:04:24<10:07:09,  3.61it/s]
 65%|██████▍   | 240092/371472 [8:04:24<10:12:37,  3.57it/s]
 65%|██████▍   | 240093/371472 [8:04:24<10:12:21,  3.58it/s]
 65%|██████▍   | 240094/371472 [8:04:24<10:40:55,  3.42it/s]
 65%|██████▍   | 240095/371472 [8:04:25<10:01:52,  3.64it/s]
 65%|██████▍   | 240096/371472 [8:04:25<10:18:31,  3.54it/s]
 65%|██████▍   | 240097/371472 [8:04:25<10:05:54,  3.61it/s]
 65%|██████▍   | 240098/371472 [8:04:26<10:25:51,  3.50it/s]
 65%|██████▍   | 240099/371472 [8:04:26<10:07:56,  3.60it/s]
 65%|██████▍   | 240100/371472 [8:04:26<10:54:20,  3.35it/s]
                                                            
{'loss': 2.9692, 'learning_rate': 4.184587041306643e-07, 'epoch': 10.34}
+
 65%|██████▍   | 240100/371472 [8:04:26<10:54:20,  3.35it/s]
 65%|██████▍   | 240101/371472 [8:04:26<10:17:05,  3.55it/s]
 65%|██████▍   | 240102/371472 [8:04:27<10:13:36,  3.57it/s]
 65%|██████▍   | 240103/371472 [8:04:27<10:52:23,  3.36it/s]
 65%|██████▍   | 240104/371472 [8:04:27<10:33:46,  3.45it/s]
 65%|██████▍   | 240105/371472 [8:04:28<10:16:08,  3.55it/s]
 65%|██████▍   | 240106/371472 [8:04:28<10:06:58,  3.61it/s]
 65%|██████▍   | 240107/371472 [8:04:28<9:47:10,  3.73it/s] 
 65%|██████▍   | 240108/371472 [8:04:28<10:06:59,  3.61it/s]
 65%|██████▍   | 240109/371472 [8:04:29<9:52:14,  3.70it/s] 
 65%|██████▍   | 240110/371472 [8:04:29<10:04:06,  3.62it/s]
 65%|██████▍   | 240111/371472 [8:04:29<10:08:32,  3.60it/s]
 65%|██████▍   | 240112/371472 [8:04:29<10:17:47,  3.54it/s]
 65%|██████▍   | 240113/371472 [8:04:30<10:51:11,  3.36it/s]
 65%|██████▍   | 240114/371472 [8:04:30<10:32:41,  3.46it/s]
 65%|██████▍   | 240115/371472 [8:04:30<10:14:49,  3.56it/s]
 65%|██████▍   | 240116/371472 [8:04:31<10:44:42,  3.40it/s]
 65%|██████▍   | 240117/371472 [8:04:31<10:20:04,  3.53it/s]
 65%|██████▍   | 240118/371472 [8:04:31<10:15:26,  3.56it/s]
 65%|██████▍   | 240119/371472 [8:04:31<9:58:12,  3.66it/s] 
 65%|██████▍   | 240120/371472 [8:04:32<9:55:27,  3.68it/s]
                                                           
{'loss': 2.8565, 'learning_rate': 4.1841022215518534e-07, 'epoch': 10.34}
+
 65%|██████▍   | 240120/371472 [8:04:32<9:55:27,  3.68it/s]
 65%|██████▍   | 240121/371472 [8:04:32<10:54:23,  3.35it/s]
 65%|██████▍   | 240122/371472 [8:04:32<10:20:45,  3.53it/s]
 65%|██████▍   | 240123/371472 [8:04:33<9:57:17,  3.67it/s] 
 65%|██████▍   | 240124/371472 [8:04:33<9:41:54,  3.76it/s]
 65%|██████▍   | 240125/371472 [8:04:33<9:42:43,  3.76it/s]
 65%|██████▍   | 240126/371472 [8:04:33<9:36:21,  3.80it/s]
 65%|██████▍   | 240127/371472 [8:04:34<10:12:53,  3.57it/s]
 65%|██████▍   | 240128/371472 [8:04:34<10:05:31,  3.62it/s]
 65%|██████▍   | 240129/371472 [8:04:34<9:50:33,  3.71it/s] 
 65%|██████▍   | 240130/371472 [8:04:34<10:03:25,  3.63it/s]
 65%|██████▍   | 240131/371472 [8:04:35<9:52:04,  3.70it/s] 
 65%|██████▍   | 240132/371472 [8:04:35<10:37:33,  3.43it/s]
 65%|██████▍   | 240133/371472 [8:04:35<10:01:23,  3.64it/s]
 65%|██████▍   | 240134/371472 [8:04:36<10:30:05,  3.47it/s]
 65%|██████▍   | 240135/371472 [8:04:36<10:52:43,  3.35it/s]
 65%|██████▍   | 240136/371472 [8:04:36<10:29:57,  3.47it/s]
 65%|██████▍   | 240137/371472 [8:04:36<10:22:57,  3.51it/s]
 65%|██████▍   | 240138/371472 [8:04:37<10:50:08,  3.37it/s]
 65%|██████▍   | 240139/371472 [8:04:37<10:43:10,  3.40it/s]
 65%|██████▍   | 240140/371472 [8:04:37<10:36:40,  3.44it/s]
                                                            
{'loss': 2.9228, 'learning_rate': 4.1836174017970646e-07, 'epoch': 10.34}
+
 65%|██████▍   | 240140/371472 [8:04:37<10:36:40,  3.44it/s]
 65%|██████▍   | 240141/371472 [8:04:38<11:07:02,  3.28it/s]
 65%|██████▍   | 240142/371472 [8:04:38<11:00:13,  3.32it/s]
 65%|██████▍   | 240143/371472 [8:04:38<10:42:54,  3.40it/s]
 65%|██████▍   | 240144/371472 [8:04:39<10:14:19,  3.56it/s]
 65%|██████▍   | 240145/371472 [8:04:39<9:54:25,  3.68it/s] 
 65%|██████▍   | 240146/371472 [8:04:39<9:46:45,  3.73it/s]
 65%|██████▍   | 240147/371472 [8:04:39<10:12:35,  3.57it/s]
 65%|██████▍   | 240148/371472 [8:04:40<10:13:28,  3.57it/s]
 65%|██████▍   | 240149/371472 [8:04:40<10:17:34,  3.54it/s]
 65%|██████▍   | 240150/371472 [8:04:40<10:05:23,  3.62it/s]
 65%|██████▍   | 240151/371472 [8:04:40<10:07:32,  3.60it/s]
 65%|██████▍   | 240152/371472 [8:04:41<10:26:38,  3.49it/s]
 65%|██████▍   | 240153/371472 [8:04:41<10:04:59,  3.62it/s]
 65%|██████▍   | 240154/371472 [8:04:41<10:26:40,  3.49it/s]
 65%|██████▍   | 240155/371472 [8:04:42<10:39:26,  3.42it/s]
 65%|██████▍   | 240156/371472 [8:04:42<10:27:00,  3.49it/s]
 65%|██████▍   | 240157/371472 [8:04:42<9:57:12,  3.66it/s] 
 65%|██████▍   | 240158/371472 [8:04:42<9:34:50,  3.81it/s]
 65%|██████▍   | 240159/371472 [8:04:43<9:36:44,  3.79it/s]
 65%|██████▍   | 240160/371472 [8:04:43<9:23:15,  3.89it/s]
                                                           
{'loss': 2.819, 'learning_rate': 4.183132582042276e-07, 'epoch': 10.34}
+
 65%|██████▍   | 240160/371472 [8:04:43<9:23:15,  3.89it/s]
 65%|██████▍   | 240161/371472 [8:04:43<9:26:04,  3.87it/s]
 65%|██████▍   | 240162/371472 [8:04:43<9:49:13,  3.71it/s]
 65%|██████▍   | 240163/371472 [8:04:44<10:42:18,  3.41it/s]
 65%|██████▍   | 240164/371472 [8:04:44<10:28:30,  3.48it/s]
 65%|██████▍   | 240165/371472 [8:04:44<10:24:31,  3.50it/s]
 65%|██████▍   | 240166/371472 [8:04:45<10:16:05,  3.55it/s]
 65%|██████▍   | 240167/371472 [8:04:45<9:54:01,  3.68it/s] 
 65%|██████▍   | 240168/371472 [8:04:45<9:31:58,  3.83it/s]
 65%|██████▍   | 240169/371472 [8:04:45<10:00:08,  3.65it/s]
 65%|██████▍   | 240170/371472 [8:04:46<10:14:26,  3.56it/s]
 65%|██████▍   | 240171/371472 [8:04:46<10:34:39,  3.45it/s]
 65%|██████▍   | 240172/371472 [8:04:46<10:28:16,  3.48it/s]
 65%|██████▍   | 240173/371472 [8:04:47<10:08:51,  3.59it/s]
 65%|██████▍   | 240174/371472 [8:04:47<10:05:43,  3.61it/s]
 65%|██████▍   | 240175/371472 [8:04:47<10:17:47,  3.54it/s]
 65%|██████▍   | 240176/371472 [8:04:47<10:03:58,  3.62it/s]
 65%|██████▍   | 240177/371472 [8:04:48<10:41:15,  3.41it/s]
 65%|██████▍   | 240178/371472 [8:04:48<10:34:09,  3.45it/s]
 65%|██████▍   | 240179/371472 [8:04:48<10:44:44,  3.39it/s]
 65%|██████▍   | 240180/371472 [8:04:49<10:15:42,  3.55it/s]
                                                            
{'loss': 2.9876, 'learning_rate': 4.182647762287487e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240180/371472 [8:04:49<10:15:42,  3.55it/s]
 65%|██████▍   | 240181/371472 [8:04:49<10:45:06,  3.39it/s]
 65%|██████▍   | 240182/371472 [8:04:49<10:40:47,  3.41it/s]
 65%|██████▍   | 240183/371472 [8:04:50<10:53:59,  3.35it/s]
 65%|██████▍   | 240184/371472 [8:04:50<10:53:02,  3.35it/s]
 65%|██████▍   | 240185/371472 [8:04:50<10:36:43,  3.44it/s]
 65%|██████▍   | 240186/371472 [8:04:50<10:28:14,  3.48it/s]
 65%|██████▍   | 240187/371472 [8:04:51<10:31:18,  3.47it/s]
 65%|██████▍   | 240188/371472 [8:04:51<10:09:28,  3.59it/s]
 65%|██████▍   | 240189/371472 [8:04:51<10:11:24,  3.58it/s]
 65%|██████▍   | 240190/371472 [8:04:52<11:15:42,  3.24it/s]
 65%|██████▍   | 240191/371472 [8:04:52<11:41:07,  3.12it/s]
 65%|██████▍   | 240192/371472 [8:04:52<11:02:46,  3.30it/s]
 65%|██████▍   | 240193/371472 [8:04:52<10:19:57,  3.53it/s]
 65%|██████▍   | 240194/371472 [8:04:53<10:10:41,  3.58it/s]
 65%|██████▍   | 240195/371472 [8:04:53<9:59:43,  3.65it/s] 
 65%|██████▍   | 240196/371472 [8:04:53<10:33:43,  3.45it/s]
 65%|██████▍   | 240197/371472 [8:04:54<10:38:09,  3.43it/s]
 65%|██████▍   | 240198/371472 [8:04:54<10:35:26,  3.44it/s]
 65%|██████▍   | 240199/371472 [8:04:54<11:20:11,  3.22it/s]
 65%|██████▍   | 240200/371472 [8:04:55<11:11:25,  3.26it/s]
                                                            
{'loss': 2.7723, 'learning_rate': 4.182162942532698e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240200/371472 [8:04:55<11:11:25,  3.26it/s]
 65%|██████▍   | 240201/371472 [8:04:55<10:38:45,  3.43it/s]
 65%|██████▍   | 240202/371472 [8:04:55<11:04:10,  3.29it/s]
 65%|██████▍   | 240203/371472 [8:04:55<10:44:21,  3.40it/s]
 65%|██████▍   | 240204/371472 [8:04:56<10:39:58,  3.42it/s]
 65%|██████▍   | 240205/371472 [8:04:56<10:22:24,  3.51it/s]
 65%|██████▍   | 240206/371472 [8:04:56<10:10:55,  3.58it/s]
 65%|██████▍   | 240207/371472 [8:04:56<10:13:32,  3.57it/s]
 65%|██████▍   | 240208/371472 [8:04:57<10:50:49,  3.36it/s]
 65%|██████▍   | 240209/371472 [8:04:57<10:29:11,  3.48it/s]
 65%|██████▍   | 240210/371472 [8:04:57<10:19:11,  3.53it/s]
 65%|██████▍   | 240211/371472 [8:04:58<10:26:17,  3.49it/s]
 65%|██████▍   | 240212/371472 [8:04:58<10:15:53,  3.55it/s]
 65%|██████▍   | 240213/371472 [8:04:58<10:17:30,  3.54it/s]
 65%|██████▍   | 240214/371472 [8:04:58<10:04:25,  3.62it/s]
 65%|██████▍   | 240215/371472 [8:04:59<9:59:11,  3.65it/s] 
 65%|██████▍   | 240216/371472 [8:04:59<10:39:06,  3.42it/s]
 65%|██████▍   | 240217/371472 [8:04:59<10:27:08,  3.49it/s]
 65%|██████▍   | 240218/371472 [8:05:00<10:15:10,  3.56it/s]
 65%|██████▍   | 240219/371472 [8:05:00<9:59:17,  3.65it/s] 
 65%|██████▍   | 240220/371472 [8:05:00<10:16:07,  3.55it/s]
                                                            
{'loss': 2.7839, 'learning_rate': 4.1816781227779096e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240220/371472 [8:05:00<10:16:07,  3.55it/s]
 65%|██████▍   | 240221/371472 [8:05:00<9:45:42,  3.73it/s] 
 65%|██████▍   | 240222/371472 [8:05:01<9:50:21,  3.71it/s]
 65%|██████▍   | 240223/371472 [8:05:01<9:57:08,  3.66it/s]
 65%|██████▍   | 240224/371472 [8:05:01<10:23:04,  3.51it/s]
 65%|██████▍   | 240225/371472 [8:05:02<10:54:54,  3.34it/s]
 65%|██████▍   | 240226/371472 [8:05:02<10:48:39,  3.37it/s]
 65%|██████▍   | 240227/371472 [8:05:03<15:00:38,  2.43it/s]
 65%|██████▍   | 240228/371472 [8:05:03<13:22:57,  2.72it/s]
 65%|██████▍   | 240229/371472 [8:05:03<12:25:22,  2.93it/s]
 65%|██████▍   | 240230/371472 [8:05:03<11:23:31,  3.20it/s]
 65%|██████▍   | 240231/371472 [8:05:04<10:55:09,  3.34it/s]
 65%|██████▍   | 240232/371472 [8:05:04<10:52:06,  3.35it/s]
 65%|██████▍   | 240233/371472 [8:05:04<10:45:41,  3.39it/s]
 65%|██████▍   | 240234/371472 [8:05:05<10:51:12,  3.36it/s]
 65%|██████▍   | 240235/371472 [8:05:05<10:31:38,  3.46it/s]
 65%|██████▍   | 240236/371472 [8:05:05<10:12:31,  3.57it/s]
 65%|██████▍   | 240237/371472 [8:05:05<9:52:30,  3.69it/s] 
 65%|██████▍   | 240238/371472 [8:05:06<9:38:02,  3.78it/s]
 65%|██████▍   | 240239/371472 [8:05:06<9:52:06,  3.69it/s]
 65%|██████▍   | 240240/371472 [8:05:06<9:27:23,  3.85it/s]
                                                           
{'loss': 2.8755, 'learning_rate': 4.1811933030231203e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240240/371472 [8:05:06<9:27:23,  3.85it/s]
 65%|██████▍   | 240241/371472 [8:05:06<9:39:43,  3.77it/s]
 65%|██████▍   | 240242/371472 [8:05:07<9:46:36,  3.73it/s]
 65%|██████▍   | 240243/371472 [8:05:07<10:10:19,  3.58it/s]
 65%|██████▍   | 240244/371472 [8:05:07<10:19:10,  3.53it/s]
 65%|██████▍   | 240245/371472 [8:05:07<10:17:02,  3.54it/s]
 65%|██████▍   | 240246/371472 [8:05:08<9:58:36,  3.65it/s] 
 65%|██████▍   | 240247/371472 [8:05:08<10:18:10,  3.54it/s]
 65%|██████▍   | 240248/371472 [8:05:08<11:05:28,  3.29it/s]
 65%|██████▍   | 240249/371472 [8:05:09<11:26:21,  3.19it/s]
 65%|██████▍   | 240250/371472 [8:05:09<12:03:50,  3.02it/s]
 65%|██████▍   | 240251/371472 [8:05:09<11:58:32,  3.04it/s]
 65%|██████▍   | 240252/371472 [8:05:10<11:11:14,  3.26it/s]
 65%|██████▍   | 240253/371472 [8:05:10<11:24:22,  3.20it/s]
 65%|██████▍   | 240254/371472 [8:05:10<11:15:38,  3.24it/s]
 65%|██████▍   | 240255/371472 [8:05:11<11:04:44,  3.29it/s]
 65%|██████▍   | 240256/371472 [8:05:11<11:01:37,  3.31it/s]
 65%|██████▍   | 240257/371472 [8:05:11<11:01:24,  3.31it/s]
 65%|██████▍   | 240258/371472 [8:05:11<10:42:30,  3.40it/s]
 65%|██████▍   | 240259/371472 [8:05:12<10:35:10,  3.44it/s]
 65%|██████▍   | 240260/371472 [8:05:12<10:28:36,  3.48it/s]
                                                            
{'loss': 2.8823, 'learning_rate': 4.1807084832683316e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240260/371472 [8:05:12<10:28:36,  3.48it/s]
 65%|██████▍   | 240261/371472 [8:05:12<11:10:06,  3.26it/s]
 65%|██████▍   | 240262/371472 [8:05:13<10:54:37,  3.34it/s]
 65%|██████▍   | 240263/371472 [8:05:13<10:40:49,  3.41it/s]
 65%|██████▍   | 240264/371472 [8:05:13<10:23:27,  3.51it/s]
 65%|██████▍   | 240265/371472 [8:05:13<9:58:58,  3.65it/s] 
 65%|██████▍   | 240266/371472 [8:05:14<10:10:03,  3.58it/s]
 65%|██████▍   | 240267/371472 [8:05:14<10:18:26,  3.54it/s]
 65%|██████▍   | 240268/371472 [8:05:14<9:51:51,  3.69it/s] 
 65%|██████▍   | 240269/371472 [8:05:15<10:10:42,  3.58it/s]
 65%|██████▍   | 240270/371472 [8:05:15<9:43:15,  3.75it/s] 
 65%|██████▍   | 240271/371472 [8:05:15<9:24:50,  3.87it/s]
 65%|██████▍   | 240272/371472 [8:05:15<9:47:25,  3.72it/s]
 65%|██████▍   | 240273/371472 [8:05:16<10:07:51,  3.60it/s]
 65%|██████▍   | 240274/371472 [8:05:16<9:49:53,  3.71it/s] 
 65%|██████▍   | 240275/371472 [8:05:16<9:39:41,  3.77it/s]
 65%|██████▍   | 240276/371472 [8:05:16<9:46:50,  3.73it/s]
 65%|██████▍   | 240277/371472 [8:05:17<9:42:01,  3.76it/s]
 65%|██████▍   | 240278/371472 [8:05:17<9:36:53,  3.79it/s]
 65%|██████▍   | 240279/371472 [8:05:17<9:31:11,  3.83it/s]
 65%|██████▍   | 240280/371472 [8:05:17<9:12:14,  3.96it/s]
                                                           
{'loss': 3.0576, 'learning_rate': 4.1802236635135423e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240280/371472 [8:05:17<9:12:14,  3.96it/s]
 65%|██████▍   | 240281/371472 [8:05:18<9:42:16,  3.76it/s]
 65%|██████▍   | 240282/371472 [8:05:18<10:57:17,  3.33it/s]
 65%|██████▍   | 240283/371472 [8:05:18<11:17:06,  3.23it/s]
 65%|██████▍   | 240284/371472 [8:05:19<10:31:16,  3.46it/s]
 65%|██████▍   | 240285/371472 [8:05:19<10:23:27,  3.51it/s]
 65%|██████▍   | 240286/371472 [8:05:19<9:52:13,  3.69it/s] 
 65%|██████▍   | 240287/371472 [8:05:20<10:05:07,  3.61it/s]
 65%|██████▍   | 240288/371472 [8:05:20<10:31:59,  3.46it/s]
 65%|██████▍   | 240289/371472 [8:05:20<10:14:36,  3.56it/s]
 65%|██████▍   | 240290/371472 [8:05:20<10:02:30,  3.63it/s]
 65%|██████▍   | 240291/371472 [8:05:21<10:27:56,  3.48it/s]
 65%|██████▍   | 240292/371472 [8:05:21<11:24:39,  3.19it/s]
 65%|██████▍   | 240293/371472 [8:05:21<11:24:24,  3.19it/s]
 65%|██████▍   | 240294/371472 [8:05:22<11:36:35,  3.14it/s]
 65%|██████▍   | 240295/371472 [8:05:22<11:42:21,  3.11it/s]
 65%|██████▍   | 240296/371472 [8:05:22<10:57:58,  3.32it/s]
 65%|██████▍   | 240297/371472 [8:05:23<10:57:20,  3.33it/s]
 65%|██████▍   | 240298/371472 [8:05:23<10:32:57,  3.45it/s]
 65%|██████▍   | 240299/371472 [8:05:23<10:47:43,  3.38it/s]
 65%|██████▍   | 240300/371472 [8:05:23<10:28:25,  3.48it/s]
                                                            
{'loss': 2.8883, 'learning_rate': 4.179738843758754e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240300/371472 [8:05:23<10:28:25,  3.48it/s]
 65%|██████▍   | 240301/371472 [8:05:24<10:08:07,  3.59it/s]
 65%|██████▍   | 240302/371472 [8:05:24<11:52:26,  3.07it/s]
 65%|██████▍   | 240303/371472 [8:05:24<11:07:59,  3.27it/s]
 65%|██████▍   | 240304/371472 [8:05:25<10:35:34,  3.44it/s]
 65%|██████▍   | 240305/371472 [8:05:25<10:09:20,  3.59it/s]
 65%|██████▍   | 240306/371472 [8:05:25<9:51:12,  3.70it/s] 
 65%|██████▍   | 240307/371472 [8:05:25<10:35:17,  3.44it/s]
 65%|██████▍   | 240308/371472 [8:05:26<10:51:05,  3.36it/s]
 65%|██████▍   | 240309/371472 [8:05:26<10:35:33,  3.44it/s]
 65%|██████▍   | 240310/371472 [8:05:26<10:22:06,  3.51it/s]
 65%|██████▍   | 240311/371472 [8:05:27<9:58:30,  3.65it/s] 
 65%|██████▍   | 240312/371472 [8:05:27<9:55:51,  3.67it/s]
 65%|██████▍   | 240313/371472 [8:05:27<10:16:29,  3.55it/s]
 65%|██████▍   | 240314/371472 [8:05:27<10:23:48,  3.50it/s]
 65%|██████▍   | 240315/371472 [8:05:28<10:06:35,  3.60it/s]
 65%|██████▍   | 240316/371472 [8:05:28<10:07:10,  3.60it/s]
 65%|██████▍   | 240317/371472 [8:05:28<10:01:20,  3.64it/s]
 65%|██████▍   | 240318/371472 [8:05:29<10:15:29,  3.55it/s]
 65%|██████▍   | 240319/371472 [8:05:29<10:06:36,  3.60it/s]
 65%|██████▍   | 240320/371472 [8:05:29<9:48:59,  3.71it/s] 
                                                           
{'loss': 2.744, 'learning_rate': 4.179254024003964e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240320/371472 [8:05:29<9:48:59,  3.71it/s]
 65%|██████▍   | 240321/371472 [8:05:29<9:47:09,  3.72it/s]
 65%|██████▍   | 240322/371472 [8:05:30<10:29:58,  3.47it/s]
 65%|██████▍   | 240323/371472 [8:05:30<10:18:14,  3.54it/s]
 65%|██████▍   | 240324/371472 [8:05:30<10:21:00,  3.52it/s]
 65%|██████▍   | 240325/371472 [8:05:30<9:58:02,  3.65it/s] 
 65%|██████▍   | 240326/371472 [8:05:31<9:45:56,  3.73it/s]
 65%|██████▍   | 240327/371472 [8:05:31<9:52:23,  3.69it/s]
 65%|██████▍   | 240328/371472 [8:05:31<9:28:47,  3.84it/s]
 65%|██████▍   | 240329/371472 [8:05:32<9:49:09,  3.71it/s]
 65%|██████▍   | 240330/371472 [8:05:32<9:59:23,  3.65it/s]
 65%|██████▍   | 240331/371472 [8:05:32<10:01:34,  3.63it/s]
 65%|██████▍   | 240332/371472 [8:05:32<9:48:18,  3.72it/s] 
 65%|██████▍   | 240333/371472 [8:05:33<10:09:17,  3.59it/s]
 65%|██████▍   | 240334/371472 [8:05:33<9:50:44,  3.70it/s] 
 65%|██████▍   | 240335/371472 [8:05:33<9:41:03,  3.76it/s]
 65%|██████▍   | 240336/371472 [8:05:33<10:00:01,  3.64it/s]
 65%|██████▍   | 240337/371472 [8:05:34<9:37:57,  3.78it/s] 
 65%|██████▍   | 240338/371472 [8:05:34<9:26:52,  3.86it/s]
 65%|██████▍   | 240339/371472 [8:05:34<9:18:26,  3.91it/s]
 65%|██████▍   | 240340/371472 [8:05:35<10:30:16,  3.47it/s]
                                                            
{'loss': 2.8487, 'learning_rate': 4.178769204249176e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240340/371472 [8:05:35<10:30:16,  3.47it/s]
 65%|██████▍   | 240341/371472 [8:05:35<10:18:39,  3.53it/s]
 65%|██████▍   | 240342/371472 [8:05:35<10:45:57,  3.38it/s]
 65%|██████▍   | 240343/371472 [8:05:35<10:37:14,  3.43it/s]
 65%|██████▍   | 240344/371472 [8:05:36<10:14:25,  3.56it/s]
 65%|██████▍   | 240345/371472 [8:05:36<9:58:55,  3.65it/s] 
 65%|██████▍   | 240346/371472 [8:05:36<10:03:40,  3.62it/s]
 65%|██████▍   | 240347/371472 [8:05:36<9:40:17,  3.77it/s] 
 65%|██████▍   | 240348/371472 [8:05:37<9:35:01,  3.80it/s]
 65%|██████▍   | 240349/371472 [8:05:37<9:41:23,  3.76it/s]
 65%|██████▍   | 240350/371472 [8:05:37<10:13:08,  3.56it/s]
 65%|██████▍   | 240351/371472 [8:05:38<10:45:52,  3.38it/s]
 65%|██████▍   | 240352/371472 [8:05:38<10:14:14,  3.56it/s]
 65%|██████▍   | 240353/371472 [8:05:38<10:01:45,  3.63it/s]
 65%|██████▍   | 240354/371472 [8:05:39<11:05:22,  3.28it/s]
 65%|██████▍   | 240355/371472 [8:05:39<10:47:58,  3.37it/s]
 65%|██████▍   | 240356/371472 [8:05:39<10:13:28,  3.56it/s]
 65%|██████▍   | 240357/371472 [8:05:39<10:59:06,  3.32it/s]
 65%|██████▍   | 240358/371472 [8:05:40<10:40:40,  3.41it/s]
 65%|██████▍   | 240359/371472 [8:05:40<10:39:16,  3.42it/s]
 65%|██████▍   | 240360/371472 [8:05:40<10:15:33,  3.55it/s]
                                                            
{'loss': 2.9843, 'learning_rate': 4.178284384494387e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240360/371472 [8:05:40<10:15:33,  3.55it/s]
 65%|██████▍   | 240361/371472 [8:05:40<10:12:06,  3.57it/s]
 65%|██████▍   | 240362/371472 [8:05:41<10:07:18,  3.60it/s]
 65%|██████▍   | 240363/371472 [8:05:41<9:59:45,  3.64it/s] 
 65%|██████▍   | 240364/371472 [8:05:41<9:33:27,  3.81it/s]
 65%|██████▍   | 240365/371472 [8:05:41<9:16:20,  3.93it/s]
 65%|██████▍   | 240366/371472 [8:05:42<9:17:57,  3.92it/s]
 65%|██████▍   | 240367/371472 [8:05:42<9:44:57,  3.74it/s]
 65%|██████▍   | 240368/371472 [8:05:42<9:54:34,  3.67it/s]
 65%|██████▍   | 240369/371472 [8:05:43<10:25:14,  3.49it/s]
 65%|██████▍   | 240370/371472 [8:05:43<10:13:18,  3.56it/s]
 65%|██████▍   | 240371/371472 [8:05:43<10:08:02,  3.59it/s]
 65%|██████▍   | 240372/371472 [8:05:43<9:59:33,  3.64it/s] 
 65%|██████▍   | 240373/371472 [8:05:44<9:47:32,  3.72it/s]
 65%|██████▍   | 240374/371472 [8:05:44<9:50:31,  3.70it/s]
 65%|██████▍   | 240375/371472 [8:05:44<9:57:19,  3.66it/s]
 65%|██████▍   | 240376/371472 [8:05:45<10:48:10,  3.37it/s]
 65%|██████▍   | 240377/371472 [8:05:45<10:09:54,  3.58it/s]
 65%|██████▍   | 240378/371472 [8:05:45<10:04:24,  3.61it/s]
 65%|██████▍   | 240379/371472 [8:05:45<10:01:58,  3.63it/s]
 65%|██████▍   | 240380/371472 [8:05:46<9:50:13,  3.70it/s] 
                                                           
{'loss': 2.8375, 'learning_rate': 4.177799564739598e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240380/371472 [8:05:46<9:50:13,  3.70it/s]
 65%|██████▍   | 240381/371472 [8:05:46<9:41:38,  3.76it/s]
 65%|██████▍   | 240382/371472 [8:05:46<11:24:12,  3.19it/s]
 65%|██████▍   | 240383/371472 [8:05:47<10:41:30,  3.41it/s]
 65%|██████▍   | 240384/371472 [8:05:47<11:09:04,  3.27it/s]
 65%|██████▍   | 240385/371472 [8:05:47<10:56:37,  3.33it/s]
 65%|██████▍   | 240386/371472 [8:05:47<10:26:52,  3.49it/s]
 65%|██████▍   | 240387/371472 [8:05:48<10:04:44,  3.61it/s]
 65%|██████▍   | 240388/371472 [8:05:48<9:57:37,  3.66it/s] 
 65%|██████▍   | 240389/371472 [8:05:48<9:57:07,  3.66it/s]
 65%|██████▍   | 240390/371472 [8:05:49<9:57:04,  3.66it/s]
 65%|██████▍   | 240391/371472 [8:05:49<11:03:01,  3.30it/s]
 65%|██████▍   | 240392/371472 [8:05:49<10:53:02,  3.35it/s]
 65%|██████▍   | 240393/371472 [8:05:49<10:16:43,  3.54it/s]
 65%|██████▍   | 240394/371472 [8:05:50<10:06:31,  3.60it/s]
 65%|██████▍   | 240395/371472 [8:05:50<9:53:08,  3.68it/s] 
 65%|██████▍   | 240396/371472 [8:05:50<9:42:36,  3.75it/s]
 65%|██████▍   | 240397/371472 [8:05:50<9:26:53,  3.85it/s]
 65%|██████▍   | 240398/371472 [8:05:51<9:32:27,  3.82it/s]
 65%|██████▍   | 240399/371472 [8:05:51<9:48:50,  3.71it/s]
 65%|██████▍   | 240400/371472 [8:05:51<9:51:15,  3.69it/s]
                                                           
{'loss': 2.9957, 'learning_rate': 4.1773147449848087e-07, 'epoch': 10.35}
+
 65%|██████▍   | 240400/371472 [8:05:51<9:51:15,  3.69it/s]
 65%|██████▍   | 240401/371472 [8:05:52<10:03:47,  3.62it/s]
 65%|██████▍   | 240402/371472 [8:05:52<10:03:51,  3.62it/s]
 65%|██████▍   | 240403/371472 [8:05:52<10:14:11,  3.56it/s]
 65%|██████▍   | 240404/371472 [8:05:52<10:04:24,  3.61it/s]
 65%|██████▍   | 240405/371472 [8:05:53<10:17:47,  3.54it/s]
 65%|██████▍   | 240406/371472 [8:05:53<10:00:06,  3.64it/s]
 65%|██████▍   | 240407/371472 [8:05:53<10:45:32,  3.38it/s]
 65%|██████▍   | 240408/371472 [8:05:54<10:40:07,  3.41it/s]
 65%|██████▍   | 240409/371472 [8:05:54<10:37:21,  3.43it/s]
 65%|██████▍   | 240410/371472 [8:05:54<10:32:08,  3.46it/s]
 65%|██████▍   | 240411/371472 [8:05:55<11:05:35,  3.28it/s]
 65%|██████▍   | 240412/371472 [8:05:55<11:03:04,  3.29it/s]
 65%|██████▍   | 240413/371472 [8:05:55<10:56:03,  3.33it/s]
 65%|██████▍   | 240414/371472 [8:05:55<11:00:01,  3.31it/s]
 65%|██████▍   | 240415/371472 [8:05:56<10:48:48,  3.37it/s]
 65%|██████▍   | 240416/371472 [8:05:56<10:29:21,  3.47it/s]
 65%|██████▍   | 240417/371472 [8:05:56<10:06:18,  3.60it/s]
 65%|██████▍   | 240418/371472 [8:05:56<9:48:12,  3.71it/s] 
 65%|██████▍   | 240419/371472 [8:05:57<10:32:35,  3.45it/s]
 65%|██████▍   | 240420/371472 [8:05:57<10:07:46,  3.59it/s]
                                                            
{'loss': 2.7579, 'learning_rate': 4.1768299252300205e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240420/371472 [8:05:57<10:07:46,  3.59it/s]
 65%|██████▍   | 240421/371472 [8:05:57<10:12:19,  3.57it/s]
 65%|██████▍   | 240422/371472 [8:05:58<10:01:30,  3.63it/s]
 65%|██████▍   | 240423/371472 [8:05:58<9:49:47,  3.70it/s] 
 65%|██████▍   | 240424/371472 [8:05:58<10:10:32,  3.58it/s]
 65%|██████▍   | 240425/371472 [8:05:58<10:12:03,  3.57it/s]
 65%|██████▍   | 240426/371472 [8:05:59<10:06:59,  3.60it/s]
 65%|██████▍   | 240427/371472 [8:05:59<10:17:19,  3.54it/s]
 65%|██████▍   | 240428/371472 [8:05:59<10:24:39,  3.50it/s]
 65%|██████▍   | 240429/371472 [8:06:00<10:16:15,  3.54it/s]
 65%|██████▍   | 240430/371472 [8:06:00<10:22:17,  3.51it/s]
 65%|██████▍   | 240431/371472 [8:06:00<10:19:22,  3.53it/s]
 65%|██████▍   | 240432/371472 [8:06:00<10:37:18,  3.43it/s]
 65%|██████▍   | 240433/371472 [8:06:01<10:26:37,  3.49it/s]
 65%|██████▍   | 240434/371472 [8:06:01<10:13:51,  3.56it/s]
 65%|██████▍   | 240435/371472 [8:06:01<9:59:57,  3.64it/s] 
 65%|██████▍   | 240436/371472 [8:06:02<10:00:09,  3.64it/s]
 65%|██████▍   | 240437/371472 [8:06:02<9:55:40,  3.67it/s] 
 65%|██████▍   | 240438/371472 [8:06:02<11:05:52,  3.28it/s]
 65%|██████▍   | 240439/371472 [8:06:02<10:52:21,  3.35it/s]
 65%|██████▍   | 240440/371472 [8:06:03<11:28:22,  3.17it/s]
                                                            
{'loss': 2.8736, 'learning_rate': 4.1763451054752307e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240440/371472 [8:06:03<11:28:22,  3.17it/s]
 65%|██████▍   | 240441/371472 [8:06:03<11:28:18,  3.17it/s]
 65%|██████▍   | 240442/371472 [8:06:03<11:00:55,  3.30it/s]
 65%|██████▍   | 240443/371472 [8:06:04<10:49:10,  3.36it/s]
 65%|██████▍   | 240444/371472 [8:06:04<10:43:26,  3.39it/s]
 65%|██████▍   | 240445/371472 [8:06:04<10:15:47,  3.55it/s]
 65%|██████▍   | 240446/371472 [8:06:05<10:27:54,  3.48it/s]
 65%|██████▍   | 240447/371472 [8:06:05<10:25:45,  3.49it/s]
 65%|██████▍   | 240448/371472 [8:06:05<10:17:26,  3.54it/s]
 65%|██████▍   | 240449/371472 [8:06:05<10:31:19,  3.46it/s]
 65%|██████▍   | 240450/371472 [8:06:06<10:25:03,  3.49it/s]
 65%|██████▍   | 240451/371472 [8:06:06<10:05:48,  3.60it/s]
 65%|██████▍   | 240452/371472 [8:06:06<10:00:23,  3.64it/s]
 65%|██████▍   | 240453/371472 [8:06:07<10:33:57,  3.44it/s]
 65%|██████▍   | 240454/371472 [8:06:07<10:48:51,  3.37it/s]
 65%|██████▍   | 240455/371472 [8:06:07<10:44:52,  3.39it/s]
 65%|██████▍   | 240456/371472 [8:06:07<10:46:27,  3.38it/s]
 65%|██████▍   | 240457/371472 [8:06:08<11:00:21,  3.31it/s]
 65%|██████▍   | 240458/371472 [8:06:08<11:35:04,  3.14it/s]
 65%|██████▍   | 240459/371472 [8:06:08<10:45:00,  3.39it/s]
 65%|██████▍   | 240460/371472 [8:06:09<10:22:48,  3.51it/s]
                                                            
{'loss': 3.1442, 'learning_rate': 4.1758602857204424e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240460/371472 [8:06:09<10:22:48,  3.51it/s]
 65%|██████▍   | 240461/371472 [8:06:09<10:27:34,  3.48it/s]
 65%|██████▍   | 240462/371472 [8:06:09<9:54:16,  3.67it/s] 
 65%|██████▍   | 240463/371472 [8:06:09<9:52:29,  3.69it/s]
 65%|██████▍   | 240464/371472 [8:06:10<10:17:11,  3.54it/s]
 65%|██████▍   | 240465/371472 [8:06:10<9:58:10,  3.65it/s] 
 65%|██████▍   | 240466/371472 [8:06:10<10:03:05,  3.62it/s]
 65%|██████▍   | 240467/371472 [8:06:11<10:03:48,  3.62it/s]
 65%|██████▍   | 240468/371472 [8:06:11<11:59:02,  3.04it/s]
 65%|██████▍   | 240469/371472 [8:06:11<11:29:30,  3.17it/s]
 65%|██████▍   | 240470/371472 [8:06:12<10:43:14,  3.39it/s]
 65%|██████▍   | 240471/371472 [8:06:12<10:26:49,  3.48it/s]
 65%|██████▍   | 240472/371472 [8:06:12<10:18:31,  3.53it/s]
 65%|██████▍   | 240473/371472 [8:06:12<10:10:21,  3.58it/s]
 65%|██████▍   | 240474/371472 [8:06:13<10:02:28,  3.62it/s]
 65%|██████▍   | 240475/371472 [8:06:13<10:23:25,  3.50it/s]
 65%|██████▍   | 240476/371472 [8:06:13<10:15:57,  3.54it/s]
 65%|██████▍   | 240477/371472 [8:06:13<10:02:45,  3.62it/s]
 65%|██████▍   | 240478/371472 [8:06:14<10:03:27,  3.62it/s]
 65%|██████▍   | 240479/371472 [8:06:14<10:10:50,  3.57it/s]
 65%|██████▍   | 240480/371472 [8:06:14<10:02:11,  3.63it/s]
                                                            
{'loss': 2.9747, 'learning_rate': 4.175375465965653e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240480/371472 [8:06:14<10:02:11,  3.63it/s]
 65%|██████▍   | 240481/371472 [8:06:15<10:05:37,  3.60it/s]
 65%|██████▍   | 240482/371472 [8:06:15<10:10:37,  3.58it/s]
 65%|██████▍   | 240483/371472 [8:06:15<9:58:29,  3.65it/s] 
 65%|██████▍   | 240484/371472 [8:06:15<10:39:24,  3.41it/s]
 65%|██████▍   | 240485/371472 [8:06:16<10:11:50,  3.57it/s]
 65%|██████▍   | 240486/371472 [8:06:16<10:31:58,  3.45it/s]
 65%|██████▍   | 240487/371472 [8:06:16<10:30:52,  3.46it/s]
 65%|██████▍   | 240488/371472 [8:06:17<10:20:08,  3.52it/s]
 65%|██████▍   | 240489/371472 [8:06:17<10:19:13,  3.53it/s]
 65%|██████▍   | 240490/371472 [8:06:17<10:32:11,  3.45it/s]
 65%|██████▍   | 240491/371472 [8:06:17<10:29:54,  3.47it/s]
 65%|██████▍   | 240492/371472 [8:06:18<10:07:52,  3.59it/s]
 65%|██████▍   | 240493/371472 [8:06:18<9:51:18,  3.69it/s] 
 65%|██████▍   | 240494/371472 [8:06:18<9:56:24,  3.66it/s]
 65%|██████▍   | 240495/371472 [8:06:19<10:23:33,  3.50it/s]
 65%|██████▍   | 240496/371472 [8:06:19<10:11:15,  3.57it/s]
 65%|██████▍   | 240497/371472 [8:06:19<9:49:08,  3.71it/s] 
 65%|██████▍   | 240498/371472 [8:06:19<9:42:09,  3.75it/s]
 65%|██████▍   | 240499/371472 [8:06:20<10:17:05,  3.54it/s]
 65%|██████▍   | 240500/371472 [8:06:20<11:00:43,  3.30it/s]
                                                            
{'loss': 2.8587, 'learning_rate': 4.174890646210864e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240500/371472 [8:06:20<11:00:43,  3.30it/s]
 65%|██████▍   | 240501/371472 [8:06:20<10:33:35,  3.45it/s]
 65%|██████▍   | 240502/371472 [8:06:21<10:55:21,  3.33it/s]
 65%|██████▍   | 240503/371472 [8:06:21<10:29:50,  3.47it/s]
 65%|██████▍   | 240504/371472 [8:06:21<9:55:50,  3.66it/s] 
 65%|██████▍   | 240505/371472 [8:06:21<9:50:16,  3.70it/s]
 65%|██████▍   | 240506/371472 [8:06:22<9:42:13,  3.75it/s]
 65%|██████▍   | 240507/371472 [8:06:22<9:39:55,  3.76it/s]
 65%|██████▍   | 240508/371472 [8:06:22<10:56:37,  3.32it/s]
 65%|██████▍   | 240509/371472 [8:06:22<10:22:45,  3.50it/s]
 65%|██████▍   | 240510/371472 [8:06:23<9:55:10,  3.67it/s] 
 65%|██████▍   | 240511/371472 [8:06:23<9:41:30,  3.75it/s]
 65%|██████▍   | 240512/371472 [8:06:23<9:35:26,  3.79it/s]
 65%|██████▍   | 240513/371472 [8:06:23<9:27:46,  3.84it/s]
 65%|██████▍   | 240514/371472 [8:06:24<9:11:30,  3.96it/s]
 65%|██████▍   | 240515/371472 [8:06:24<9:17:51,  3.91it/s]
 65%|██████▍   | 240516/371472 [8:06:24<9:30:07,  3.83it/s]
 65%|██████▍   | 240517/371472 [8:06:25<10:20:28,  3.52it/s]
 65%|██████▍   | 240518/371472 [8:06:25<9:56:43,  3.66it/s] 
 65%|██████▍   | 240519/371472 [8:06:25<10:13:52,  3.56it/s]
 65%|██████▍   | 240520/371472 [8:06:25<10:18:28,  3.53it/s]
                                                            
{'loss': 2.7885, 'learning_rate': 4.174405826456075e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240520/371472 [8:06:25<10:18:28,  3.53it/s]
 65%|██████▍   | 240521/371472 [8:06:26<10:36:27,  3.43it/s]
 65%|██████▍   | 240522/371472 [8:06:26<10:36:54,  3.43it/s]
 65%|██████▍   | 240523/371472 [8:06:26<10:26:26,  3.48it/s]
 65%|██████▍   | 240524/371472 [8:06:27<10:13:55,  3.55it/s]
 65%|██████▍   | 240525/371472 [8:06:27<10:21:41,  3.51it/s]
 65%|██████▍   | 240526/371472 [8:06:27<10:53:46,  3.34it/s]
 65%|██████▍   | 240527/371472 [8:06:27<10:24:35,  3.49it/s]
 65%|██████▍   | 240528/371472 [8:06:28<10:04:56,  3.61it/s]
 65%|██████▍   | 240529/371472 [8:06:28<10:24:38,  3.49it/s]
 65%|██████▍   | 240530/371472 [8:06:28<9:55:29,  3.66it/s] 
 65%|██████▍   | 240531/371472 [8:06:29<9:52:43,  3.68it/s]
 65%|██████▍   | 240532/371472 [8:06:29<9:46:40,  3.72it/s]
 65%|██████▍   | 240533/371472 [8:06:29<10:54:35,  3.33it/s]
 65%|██████▍   | 240534/371472 [8:06:29<10:34:08,  3.44it/s]
 65%|██████▍   | 240535/371472 [8:06:30<10:20:06,  3.52it/s]
 65%|██████▍   | 240536/371472 [8:06:30<10:03:10,  3.62it/s]
 65%|██████▍   | 240537/371472 [8:06:30<9:56:32,  3.66it/s] 
 65%|██████▍   | 240538/371472 [8:06:31<10:52:19,  3.35it/s]
 65%|██████▍   | 240539/371472 [8:06:31<10:20:17,  3.52it/s]
 65%|██████▍   | 240540/371472 [8:06:31<10:11:55,  3.57it/s]
                                                            
{'loss': 2.9606, 'learning_rate': 4.173921006701286e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240540/371472 [8:06:31<10:11:55,  3.57it/s]
 65%|██████▍   | 240541/371472 [8:06:31<10:10:02,  3.58it/s]
 65%|██████▍   | 240542/371472 [8:06:32<9:46:01,  3.72it/s] 
 65%|██████▍   | 240543/371472 [8:06:32<9:51:17,  3.69it/s]
 65%|██████▍   | 240544/371472 [8:06:32<9:51:34,  3.69it/s]
 65%|██████▍   | 240545/371472 [8:06:32<9:55:00,  3.67it/s]
 65%|██████▍   | 240546/371472 [8:06:33<10:03:54,  3.61it/s]
 65%|██████▍   | 240547/371472 [8:06:33<9:49:05,  3.70it/s] 
 65%|██████▍   | 240548/371472 [8:06:33<9:29:50,  3.83it/s]
 65%|██████▍   | 240549/371472 [8:06:34<9:53:16,  3.68it/s]
 65%|██████▍   | 240550/371472 [8:06:34<10:01:14,  3.63it/s]
 65%|██████▍   | 240551/371472 [8:06:34<10:02:53,  3.62it/s]
 65%|██████▍   | 240552/371472 [8:06:34<9:41:03,  3.76it/s] 
 65%|██████▍   | 240553/371472 [8:06:35<10:43:04,  3.39it/s]
 65%|██████▍   | 240554/371472 [8:06:35<10:14:37,  3.55it/s]
 65%|██████▍   | 240555/371472 [8:06:35<12:21:05,  2.94it/s]
 65%|██████▍   | 240556/371472 [8:06:36<11:23:48,  3.19it/s]
 65%|██████▍   | 240557/371472 [8:06:36<10:45:28,  3.38it/s]
 65%|██████▍   | 240558/371472 [8:06:36<11:23:16,  3.19it/s]
 65%|██████▍   | 240559/371472 [8:06:37<10:59:29,  3.31it/s]
 65%|██████▍   | 240560/371472 [8:06:37<11:02:16,  3.29it/s]
                                                            
{'loss': 2.9694, 'learning_rate': 4.1734361869464976e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240560/371472 [8:06:37<11:02:16,  3.29it/s]
 65%|██████▍   | 240561/371472 [8:06:37<10:28:07,  3.47it/s]
 65%|██████▍   | 240562/371472 [8:06:37<9:58:05,  3.65it/s] 
 65%|██████▍   | 240563/371472 [8:06:38<10:07:14,  3.59it/s]
 65%|██████▍   | 240564/371472 [8:06:38<10:17:04,  3.54it/s]
 65%|██████▍   | 240565/371472 [8:06:38<9:43:40,  3.74it/s] 
 65%|██████▍   | 240566/371472 [8:06:39<11:00:26,  3.30it/s]
 65%|██████▍   | 240567/371472 [8:06:39<10:31:18,  3.46it/s]
 65%|██████▍   | 240568/371472 [8:06:39<10:32:35,  3.45it/s]
 65%|██████▍   | 240569/371472 [8:06:39<10:09:36,  3.58it/s]
 65%|██████▍   | 240570/371472 [8:06:40<9:56:20,  3.66it/s] 
 65%|██████▍   | 240571/371472 [8:06:40<9:34:53,  3.79it/s]
 65%|██████▍   | 240572/371472 [8:06:40<9:37:21,  3.78it/s]
 65%|██████▍   | 240573/371472 [8:06:40<9:25:11,  3.86it/s]
 65%|██████▍   | 240574/371472 [8:06:41<9:29:25,  3.83it/s]
 65%|██████▍   | 240575/371472 [8:06:41<9:41:48,  3.75it/s]
 65%|██████▍   | 240576/371472 [8:06:41<10:48:28,  3.36it/s]
 65%|██████▍   | 240577/371472 [8:06:42<10:24:25,  3.49it/s]
 65%|██████▍   | 240578/371472 [8:06:42<10:32:58,  3.45it/s]
 65%|██████▍   | 240579/371472 [8:06:42<10:37:06,  3.42it/s]
 65%|██████▍   | 240580/371472 [8:06:42<10:28:27,  3.47it/s]
                                                            
{'loss': 2.9585, 'learning_rate': 4.172951367191708e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240580/371472 [8:06:42<10:28:27,  3.47it/s]
 65%|██████▍   | 240581/371472 [8:06:43<10:12:51,  3.56it/s]
 65%|██████▍   | 240582/371472 [8:06:43<10:21:20,  3.51it/s]
 65%|██████▍   | 240583/371472 [8:06:43<10:11:43,  3.57it/s]
 65%|██████▍   | 240584/371472 [8:06:44<9:59:14,  3.64it/s] 
 65%|██████▍   | 240585/371472 [8:06:44<10:21:52,  3.51it/s]
 65%|██████▍   | 240586/371472 [8:06:44<10:43:30,  3.39it/s]
 65%|██████▍   | 240587/371472 [8:06:44<10:16:00,  3.54it/s]
 65%|██████▍   | 240588/371472 [8:06:45<10:26:16,  3.48it/s]
 65%|██████▍   | 240589/371472 [8:06:45<10:19:13,  3.52it/s]
 65%|██████▍   | 240590/371472 [8:06:45<10:33:38,  3.44it/s]
 65%|██████▍   | 240591/371472 [8:06:46<10:20:06,  3.52it/s]
 65%|██████▍   | 240592/371472 [8:06:46<10:18:56,  3.52it/s]
 65%|██████▍   | 240593/371472 [8:06:46<10:15:03,  3.55it/s]
 65%|██████▍   | 240594/371472 [8:06:46<10:04:17,  3.61it/s]
 65%|██████▍   | 240595/371472 [8:06:47<9:51:38,  3.69it/s] 
 65%|██████▍   | 240596/371472 [8:06:47<10:13:11,  3.56it/s]
 65%|██████▍   | 240597/371472 [8:06:47<10:28:37,  3.47it/s]
 65%|██████▍   | 240598/371472 [8:06:47<10:09:52,  3.58it/s]
 65%|██████▍   | 240599/371472 [8:06:48<9:52:21,  3.68it/s] 
 65%|██████▍   | 240600/371472 [8:06:48<9:58:14,  3.65it/s]
                                                           
{'loss': 2.7796, 'learning_rate': 4.1724665474369196e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240600/371472 [8:06:48<9:58:14,  3.65it/s]
 65%|██████▍   | 240601/371472 [8:06:48<9:44:20,  3.73it/s]
 65%|██████▍   | 240602/371472 [8:06:49<9:29:01,  3.83it/s]
 65%|██████▍   | 240603/371472 [8:06:49<10:39:48,  3.41it/s]
 65%|██████▍   | 240604/371472 [8:06:49<10:34:28,  3.44it/s]
 65%|██████▍   | 240605/371472 [8:06:49<10:19:30,  3.52it/s]
 65%|██████▍   | 240606/371472 [8:06:50<10:02:20,  3.62it/s]
 65%|██████▍   | 240607/371472 [8:06:50<10:02:37,  3.62it/s]
 65%|██████▍   | 240608/371472 [8:06:50<10:00:23,  3.63it/s]
 65%|██████▍   | 240609/371472 [8:06:51<9:55:32,  3.66it/s] 
 65%|██████▍   | 240610/371472 [8:06:51<10:30:23,  3.46it/s]
 65%|██████▍   | 240611/371472 [8:06:51<10:43:45,  3.39it/s]
 65%|██████▍   | 240612/371472 [8:06:51<10:54:37,  3.33it/s]
 65%|██████▍   | 240613/371472 [8:06:52<10:38:03,  3.42it/s]
 65%|██████▍   | 240614/371472 [8:06:52<10:21:22,  3.51it/s]
 65%|██████▍   | 240615/371472 [8:06:52<10:20:21,  3.52it/s]
 65%|██████▍   | 240616/371472 [8:06:53<10:32:48,  3.45it/s]
 65%|██████▍   | 240617/371472 [8:06:53<10:22:26,  3.50it/s]
 65%|██████▍   | 240618/371472 [8:06:53<11:03:16,  3.29it/s]
 65%|██████▍   | 240619/371472 [8:06:53<10:45:12,  3.38it/s]
 65%|██████▍   | 240620/371472 [8:06:54<10:08:10,  3.59it/s]
                                                            
{'loss': 2.8403, 'learning_rate': 4.1719817276821303e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240620/371472 [8:06:54<10:08:10,  3.59it/s]
 65%|██████▍   | 240621/371472 [8:06:54<9:57:56,  3.65it/s] 
 65%|██████▍   | 240622/371472 [8:06:54<9:52:49,  3.68it/s]
 65%|██████▍   | 240623/371472 [8:06:54<9:29:20,  3.83it/s]
 65%|██████▍   | 240624/371472 [8:06:55<9:32:23,  3.81it/s]
 65%|██████▍   | 240625/371472 [8:06:55<9:27:46,  3.84it/s]
 65%|██████▍   | 240626/371472 [8:06:55<9:40:42,  3.76it/s]
 65%|██████▍   | 240627/371472 [8:06:56<9:27:21,  3.84it/s]
 65%|██████▍   | 240628/371472 [8:06:56<9:29:38,  3.83it/s]
 65%|██████▍   | 240629/371472 [8:06:56<10:13:51,  3.55it/s]
 65%|██████▍   | 240630/371472 [8:06:56<10:32:59,  3.45it/s]
 65%|██████▍   | 240631/371472 [8:06:57<10:21:45,  3.51it/s]
 65%|██████▍   | 240632/371472 [8:06:57<10:23:44,  3.50it/s]
 65%|██████▍   | 240633/371472 [8:06:57<10:13:01,  3.56it/s]
 65%|██████▍   | 240634/371472 [8:06:58<10:20:23,  3.51it/s]
 65%|██████▍   | 240635/371472 [8:06:58<10:20:21,  3.52it/s]
 65%|██████▍   | 240636/371472 [8:06:58<10:11:20,  3.57it/s]
 65%|██████▍   | 240637/371472 [8:06:58<10:43:56,  3.39it/s]
 65%|██████▍   | 240638/371472 [8:06:59<10:12:57,  3.56it/s]
 65%|██████▍   | 240639/371472 [8:06:59<9:56:21,  3.66it/s] 
 65%|██████▍   | 240640/371472 [8:06:59<9:58:52,  3.64it/s]
                                                           
{'loss': 2.9279, 'learning_rate': 4.1714969079273415e-07, 'epoch': 10.36}
+
 65%|██████▍   | 240640/371472 [8:06:59<9:58:52,  3.64it/s]
 65%|██████▍   | 240641/371472 [8:06:59<9:46:30,  3.72it/s]
 65%|██████▍   | 240642/371472 [8:07:00<9:46:48,  3.72it/s]
 65%|██████▍   | 240643/371472 [8:07:00<9:55:27,  3.66it/s]
 65%|██████▍   | 240644/371472 [8:07:00<9:35:42,  3.79it/s]
 65%|██████▍   | 240645/371472 [8:07:01<9:30:17,  3.82it/s]
 65%|██████▍   | 240646/371472 [8:07:01<9:52:23,  3.68it/s]
 65%|██████▍   | 240647/371472 [8:07:01<9:48:27,  3.71it/s]
 65%|██████▍   | 240648/371472 [8:07:01<9:28:37,  3.83it/s]
 65%|██████▍   | 240649/371472 [8:07:02<9:36:55,  3.78it/s]
 65%|██████▍   | 240650/371472 [8:07:02<9:50:21,  3.69it/s]
 65%|██████▍   | 240651/371472 [8:07:02<9:59:11,  3.64it/s]
 65%|██████▍   | 240652/371472 [8:07:02<9:52:24,  3.68it/s]
 65%|██████▍   | 240653/371472 [8:07:03<10:16:11,  3.54it/s]
 65%|██████▍   | 240654/371472 [8:07:03<10:16:13,  3.54it/s]
 65%|██████▍   | 240655/371472 [8:07:03<10:38:21,  3.42it/s]
 65%|██████▍   | 240656/371472 [8:07:04<10:44:53,  3.38it/s]
 65%|██████▍   | 240657/371472 [8:07:04<10:24:32,  3.49it/s]
 65%|██████▍   | 240658/371472 [8:07:04<10:05:38,  3.60it/s]
 65%|██████▍   | 240659/371472 [8:07:04<9:53:51,  3.67it/s] 
 65%|██████▍   | 240660/371472 [8:07:05<9:55:55,  3.66it/s]
                                                           
{'loss': 2.8205, 'learning_rate': 4.171012088172552e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240660/371472 [8:07:05<9:55:55,  3.66it/s]
 65%|██████▍   | 240661/371472 [8:07:05<10:05:44,  3.60it/s]
 65%|██████▍   | 240662/371472 [8:07:05<10:22:00,  3.51it/s]
 65%|██████▍   | 240663/371472 [8:07:06<9:59:41,  3.64it/s] 
 65%|██████▍   | 240664/371472 [8:07:06<9:50:02,  3.69it/s]
 65%|██████▍   | 240665/371472 [8:07:06<9:37:15,  3.78it/s]
 65%|██████▍   | 240666/371472 [8:07:06<9:28:35,  3.83it/s]
 65%|██████▍   | 240667/371472 [8:07:07<9:57:47,  3.65it/s]
 65%|██████▍   | 240668/371472 [8:07:07<10:07:39,  3.59it/s]
 65%|██████▍   | 240669/371472 [8:07:07<10:14:22,  3.55it/s]
 65%|██████▍   | 240670/371472 [8:07:07<9:55:23,  3.66it/s] 
 65%|██████▍   | 240671/371472 [8:07:08<9:42:11,  3.74it/s]
 65%|██████▍   | 240672/371472 [8:07:08<9:55:37,  3.66it/s]
 65%|██████▍   | 240673/371472 [8:07:08<9:55:38,  3.66it/s]
 65%|██████▍   | 240674/371472 [8:07:09<9:43:52,  3.73it/s]
 65%|██████▍   | 240675/371472 [8:07:09<9:48:12,  3.71it/s]
 65%|██████▍   | 240676/371472 [8:07:09<9:59:26,  3.64it/s]
 65%|██████▍   | 240677/371472 [8:07:09<10:35:46,  3.43it/s]
 65%|██████▍   | 240678/371472 [8:07:10<11:24:58,  3.18it/s]
 65%|██████▍   | 240679/371472 [8:07:10<11:01:49,  3.29it/s]
 65%|██████▍   | 240680/371472 [8:07:10<10:40:21,  3.40it/s]
                                                            
{'loss': 3.0433, 'learning_rate': 4.170527268417764e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240680/371472 [8:07:10<10:40:21,  3.40it/s]
 65%|██████▍   | 240681/371472 [8:07:11<10:34:13,  3.44it/s]
 65%|██████▍   | 240682/371472 [8:07:11<10:35:47,  3.43it/s]
 65%|██████▍   | 240683/371472 [8:07:11<10:21:38,  3.51it/s]
 65%|██████▍   | 240684/371472 [8:07:11<10:41:06,  3.40it/s]
 65%|██████▍   | 240685/371472 [8:07:12<10:41:21,  3.40it/s]
 65%|██████▍   | 240686/371472 [8:07:12<11:20:20,  3.20it/s]
 65%|██████▍   | 240687/371472 [8:07:12<10:53:31,  3.34it/s]
 65%|██████▍   | 240688/371472 [8:07:13<10:45:07,  3.38it/s]
 65%|██████▍   | 240689/371472 [8:07:13<10:24:26,  3.49it/s]
 65%|██████▍   | 240690/371472 [8:07:13<10:13:09,  3.55it/s]
 65%|██████▍   | 240691/371472 [8:07:13<9:56:57,  3.65it/s] 
 65%|██████▍   | 240692/371472 [8:07:14<10:12:18,  3.56it/s]
 65%|██████▍   | 240693/371472 [8:07:14<10:23:48,  3.49it/s]
 65%|██████▍   | 240694/371472 [8:07:14<10:44:27,  3.38it/s]
 65%|██████▍   | 240695/371472 [8:07:15<10:44:59,  3.38it/s]
 65%|██████▍   | 240696/371472 [8:07:15<10:43:14,  3.39it/s]
 65%|██████▍   | 240697/371472 [8:07:15<10:40:38,  3.40it/s]
 65%|██████▍   | 240698/371472 [8:07:16<10:06:02,  3.60it/s]
 65%|██████▍   | 240699/371472 [8:07:16<9:57:27,  3.65it/s] 
 65%|██████▍   | 240700/371472 [8:07:16<9:45:51,  3.72it/s]
                                                           
{'loss': 2.785, 'learning_rate': 4.170042448662974e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240700/371472 [8:07:16<9:45:51,  3.72it/s]
 65%|██████▍   | 240701/371472 [8:07:16<9:44:34,  3.73it/s]
 65%|██████▍   | 240702/371472 [8:07:17<9:36:38,  3.78it/s]
 65%|██████▍   | 240703/371472 [8:07:17<10:01:05,  3.63it/s]
 65%|██████▍   | 240704/371472 [8:07:17<11:10:36,  3.25it/s]
 65%|██████▍   | 240705/371472 [8:07:18<10:45:39,  3.38it/s]
 65%|██████▍   | 240706/371472 [8:07:18<11:10:41,  3.25it/s]
 65%|██████▍   | 240707/371472 [8:07:18<12:36:13,  2.88it/s]
 65%|██████▍   | 240708/371472 [8:07:19<12:20:25,  2.94it/s]
 65%|██████▍   | 240709/371472 [8:07:19<12:09:26,  2.99it/s]
 65%|██████▍   | 240710/371472 [8:07:19<11:45:50,  3.09it/s]
 65%|██████▍   | 240711/371472 [8:07:19<10:55:53,  3.32it/s]
 65%|██████▍   | 240712/371472 [8:07:20<10:25:06,  3.49it/s]
 65%|██████▍   | 240713/371472 [8:07:20<10:18:22,  3.52it/s]
 65%|██████▍   | 240714/371472 [8:07:20<9:47:14,  3.71it/s] 
 65%|██████▍   | 240715/371472 [8:07:21<10:06:17,  3.59it/s]
 65%|██████▍   | 240716/371472 [8:07:21<10:29:35,  3.46it/s]
 65%|██████▍   | 240717/371472 [8:07:21<10:34:28,  3.43it/s]
 65%|██████▍   | 240718/371472 [8:07:21<10:38:41,  3.41it/s]
 65%|██████▍   | 240719/371472 [8:07:22<11:22:13,  3.19it/s]
 65%|██████▍   | 240720/371472 [8:07:22<10:56:06,  3.32it/s]
                                                            
{'loss': 2.8016, 'learning_rate': 4.169557628908186e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240720/371472 [8:07:22<10:56:06,  3.32it/s]
 65%|██████▍   | 240721/371472 [8:07:22<11:01:00,  3.30it/s]
 65%|██████▍   | 240722/371472 [8:07:23<10:33:27,  3.44it/s]
 65%|██████▍   | 240723/371472 [8:07:23<10:43:39,  3.39it/s]
 65%|██████▍   | 240724/371472 [8:07:23<10:21:11,  3.51it/s]
 65%|██████▍   | 240725/371472 [8:07:24<10:18:37,  3.52it/s]
 65%|██████▍   | 240726/371472 [8:07:24<10:18:21,  3.52it/s]
 65%|██████▍   | 240727/371472 [8:07:24<10:27:15,  3.47it/s]
 65%|██████▍   | 240728/371472 [8:07:24<10:31:25,  3.45it/s]
 65%|██████▍   | 240729/371472 [8:07:25<10:34:36,  3.43it/s]
 65%|██████▍   | 240730/371472 [8:07:25<10:09:26,  3.58it/s]
 65%|██████▍   | 240731/371472 [8:07:25<10:41:24,  3.40it/s]
 65%|██████▍   | 240732/371472 [8:07:26<10:32:21,  3.45it/s]
 65%|██████▍   | 240733/371472 [8:07:26<10:16:46,  3.53it/s]
 65%|██████▍   | 240734/371472 [8:07:26<10:55:20,  3.32it/s]
 65%|██████▍   | 240735/371472 [8:07:26<10:22:02,  3.50it/s]
 65%|██████▍   | 240736/371472 [8:07:27<10:02:20,  3.62it/s]
 65%|██████▍   | 240737/371472 [8:07:27<10:07:49,  3.58it/s]
 65%|██████▍   | 240738/371472 [8:07:27<9:56:16,  3.65it/s] 
 65%|██████▍   | 240739/371472 [8:07:27<9:44:46,  3.73it/s]
 65%|██████▍   | 240740/371472 [8:07:28<9:56:47,  3.65it/s]
                                                           
{'loss': 2.9566, 'learning_rate': 4.1690728091533967e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240740/371472 [8:07:28<9:56:47,  3.65it/s]
 65%|██████▍   | 240741/371472 [8:07:28<10:20:23,  3.51it/s]
 65%|██████▍   | 240742/371472 [8:07:28<10:15:25,  3.54it/s]
 65%|██████▍   | 240743/371472 [8:07:29<10:55:56,  3.32it/s]
 65%|██████▍   | 240744/371472 [8:07:29<10:24:16,  3.49it/s]
 65%|██████▍   | 240745/371472 [8:07:29<10:10:50,  3.57it/s]
 65%|██████▍   | 240746/371472 [8:07:30<10:32:52,  3.44it/s]
 65%|██████▍   | 240747/371472 [8:07:30<11:13:31,  3.23it/s]
 65%|██████▍   | 240748/371472 [8:07:30<11:28:52,  3.16it/s]
 65%|██████▍   | 240749/371472 [8:07:30<11:02:19,  3.29it/s]
 65%|██████▍   | 240750/371472 [8:07:31<10:42:01,  3.39it/s]
 65%|██████▍   | 240751/371472 [8:07:31<10:23:34,  3.49it/s]
 65%|██████▍   | 240752/371472 [8:07:31<10:09:41,  3.57it/s]
 65%|██████▍   | 240753/371472 [8:07:32<10:35:11,  3.43it/s]
 65%|██████▍   | 240754/371472 [8:07:32<10:08:58,  3.58it/s]
 65%|██████▍   | 240755/371472 [8:07:32<9:49:12,  3.70it/s] 
 65%|██████▍   | 240756/371472 [8:07:32<9:39:54,  3.76it/s]
 65%|██████▍   | 240757/371472 [8:07:33<10:52:36,  3.34it/s]
 65%|██████▍   | 240758/371472 [8:07:33<10:51:42,  3.34it/s]
 65%|██████▍   | 240759/371472 [8:07:33<11:11:10,  3.25it/s]
 65%|██████▍   | 240760/371472 [8:07:34<10:43:29,  3.39it/s]
                                                            
{'loss': 2.6595, 'learning_rate': 4.168587989398608e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240760/371472 [8:07:34<10:43:29,  3.39it/s]
 65%|██████▍   | 240761/371472 [8:07:34<10:55:20,  3.32it/s]
 65%|██████▍   | 240762/371472 [8:07:34<10:35:54,  3.43it/s]
 65%|██████▍   | 240763/371472 [8:07:35<10:54:48,  3.33it/s]
 65%|██████▍   | 240764/371472 [8:07:35<10:45:50,  3.37it/s]
 65%|██████▍   | 240765/371472 [8:07:35<10:32:37,  3.44it/s]
 65%|██████▍   | 240766/371472 [8:07:35<10:41:36,  3.40it/s]
 65%|██████▍   | 240767/371472 [8:07:36<10:53:34,  3.33it/s]
 65%|██████▍   | 240768/371472 [8:07:36<10:18:32,  3.52it/s]
 65%|██████▍   | 240769/371472 [8:07:36<10:13:01,  3.55it/s]
 65%|██████▍   | 240770/371472 [8:07:36<9:58:24,  3.64it/s] 
 65%|██████▍   | 240771/371472 [8:07:37<9:45:38,  3.72it/s]
 65%|██████▍   | 240772/371472 [8:07:37<10:07:44,  3.58it/s]
 65%|██████▍   | 240773/371472 [8:07:37<10:09:50,  3.57it/s]
 65%|██████▍   | 240774/371472 [8:07:38<10:06:36,  3.59it/s]
 65%|██████▍   | 240775/371472 [8:07:38<10:23:18,  3.49it/s]
 65%|██████▍   | 240776/371472 [8:07:38<10:04:55,  3.60it/s]
 65%|██████▍   | 240777/371472 [8:07:38<9:53:03,  3.67it/s] 
 65%|██████▍   | 240778/371472 [8:07:39<10:19:04,  3.52it/s]
 65%|██████▍   | 240779/371472 [8:07:39<10:41:14,  3.40it/s]
 65%|██████▍   | 240780/371472 [8:07:39<10:22:01,  3.50it/s]
                                                            
{'loss': 2.9266, 'learning_rate': 4.1681031696438186e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240780/371472 [8:07:39<10:22:01,  3.50it/s]
 65%|██████▍   | 240781/371472 [8:07:40<10:14:46,  3.54it/s]
 65%|██████▍   | 240782/371472 [8:07:40<10:08:51,  3.58it/s]
 65%|██████▍   | 240783/371472 [8:07:40<10:16:33,  3.53it/s]
 65%|██████▍   | 240784/371472 [8:07:40<10:12:57,  3.55it/s]
 65%|██████▍   | 240785/371472 [8:07:41<9:58:09,  3.64it/s] 
 65%|██████▍   | 240786/371472 [8:07:41<10:01:25,  3.62it/s]
 65%|██████▍   | 240787/371472 [8:07:41<9:49:05,  3.70it/s] 
 65%|██████▍   | 240788/371472 [8:07:41<9:34:49,  3.79it/s]
 65%|██████▍   | 240789/371472 [8:07:42<9:41:23,  3.75it/s]
 65%|██████▍   | 240790/371472 [8:07:42<9:42:22,  3.74it/s]
 65%|██████▍   | 240791/371472 [8:07:42<9:22:39,  3.87it/s]
 65%|██████▍   | 240792/371472 [8:07:43<9:44:52,  3.72it/s]
 65%|██████▍   | 240793/371472 [8:07:43<9:31:07,  3.81it/s]
 65%|██████▍   | 240794/371472 [8:07:43<9:54:06,  3.67it/s]
 65%|██████▍   | 240795/371472 [8:07:43<10:32:25,  3.44it/s]
 65%|██████▍   | 240796/371472 [8:07:44<10:12:43,  3.55it/s]
 65%|██████▍   | 240797/371472 [8:07:44<10:04:02,  3.61it/s]
 65%|██████▍   | 240798/371472 [8:07:44<10:25:22,  3.48it/s]
 65%|██████▍   | 240799/371472 [8:07:45<10:19:29,  3.52it/s]
 65%|██████▍   | 240800/371472 [8:07:45<10:38:36,  3.41it/s]
                                                            
{'loss': 2.9934, 'learning_rate': 4.1676183498890304e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240800/371472 [8:07:45<10:38:36,  3.41it/s]
 65%|██████▍   | 240801/371472 [8:07:45<10:34:04,  3.43it/s]
 65%|██████▍   | 240802/371472 [8:07:45<10:22:06,  3.50it/s]
 65%|██████▍   | 240803/371472 [8:07:46<10:45:59,  3.37it/s]
 65%|██████▍   | 240804/371472 [8:07:46<11:54:32,  3.05it/s]
 65%|██████▍   | 240805/371472 [8:07:46<11:01:28,  3.29it/s]
 65%|██████▍   | 240806/371472 [8:07:47<11:02:48,  3.29it/s]
 65%|██████▍   | 240807/371472 [8:07:47<11:20:26,  3.20it/s]
 65%|██████▍   | 240808/371472 [8:07:47<10:46:16,  3.37it/s]
 65%|██████▍   | 240809/371472 [8:07:48<10:51:53,  3.34it/s]
 65%|██████▍   | 240810/371472 [8:07:48<10:42:13,  3.39it/s]
 65%|██████▍   | 240811/371472 [8:07:48<10:05:44,  3.60it/s]
 65%|██████▍   | 240812/371472 [8:07:48<10:11:07,  3.56it/s]
 65%|██████▍   | 240813/371472 [8:07:49<10:50:50,  3.35it/s]
 65%|██████▍   | 240814/371472 [8:07:49<10:37:20,  3.42it/s]
 65%|██████▍   | 240815/371472 [8:07:49<10:28:24,  3.47it/s]
 65%|██████▍   | 240816/371472 [8:07:50<10:05:12,  3.60it/s]
 65%|██████▍   | 240817/371472 [8:07:50<10:11:09,  3.56it/s]
 65%|██████▍   | 240818/371472 [8:07:50<10:04:24,  3.60it/s]
 65%|██████▍   | 240819/371472 [8:07:50<10:01:18,  3.62it/s]
 65%|██████▍   | 240820/371472 [8:07:51<10:06:18,  3.59it/s]
                                                            
{'loss': 2.8157, 'learning_rate': 4.1671335301342406e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240820/371472 [8:07:51<10:06:18,  3.59it/s]
 65%|██████▍   | 240821/371472 [8:07:51<9:38:20,  3.77it/s] 
 65%|██████▍   | 240822/371472 [8:07:51<9:36:54,  3.77it/s]
 65%|██████▍   | 240823/371472 [8:07:51<9:25:57,  3.85it/s]
 65%|██████▍   | 240824/371472 [8:07:52<9:16:52,  3.91it/s]
 65%|██████▍   | 240825/371472 [8:07:52<9:40:06,  3.75it/s]
 65%|██████▍   | 240826/371472 [8:07:52<9:32:48,  3.80it/s]
 65%|██████▍   | 240827/371472 [8:07:52<9:47:06,  3.71it/s]
 65%|██████▍   | 240828/371472 [8:07:53<9:36:34,  3.78it/s]
 65%|██████▍   | 240829/371472 [8:07:53<9:32:47,  3.80it/s]
 65%|██████▍   | 240830/371472 [8:07:53<9:34:51,  3.79it/s]
 65%|██████▍   | 240831/371472 [8:07:54<9:26:20,  3.84it/s]
 65%|██████▍   | 240832/371472 [8:07:54<9:22:48,  3.87it/s]
 65%|██████▍   | 240833/371472 [8:07:54<9:28:48,  3.83it/s]
 65%|██████▍   | 240834/371472 [8:07:54<9:45:54,  3.72it/s]
 65%|██████▍   | 240835/371472 [8:07:55<10:31:37,  3.45it/s]
 65%|██████▍   | 240836/371472 [8:07:55<10:29:34,  3.46it/s]
 65%|██████▍   | 240837/371472 [8:07:55<10:05:12,  3.60it/s]
 65%|██████▍   | 240838/371472 [8:07:55<9:56:57,  3.65it/s] 
 65%|██████▍   | 240839/371472 [8:07:56<9:59:57,  3.63it/s]
 65%|██████▍   | 240840/371472 [8:07:56<10:42:40,  3.39it/s]
                                                            
{'loss': 2.9155, 'learning_rate': 4.1666487103794524e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240840/371472 [8:07:56<10:42:40,  3.39it/s]
 65%|██████▍   | 240841/371472 [8:07:56<10:24:03,  3.49it/s]
 65%|██████▍   | 240842/371472 [8:07:57<10:00:50,  3.62it/s]
 65%|██████▍   | 240843/371472 [8:07:57<10:37:35,  3.41it/s]
 65%|██████▍   | 240844/371472 [8:07:57<10:25:20,  3.48it/s]
 65%|██████▍   | 240845/371472 [8:07:58<10:19:43,  3.51it/s]
 65%|██████▍   | 240846/371472 [8:07:58<10:31:22,  3.45it/s]
 65%|██████▍   | 240847/371472 [8:07:58<10:15:55,  3.53it/s]
 65%|██████▍   | 240848/371472 [8:07:58<10:08:00,  3.58it/s]
 65%|██████▍   | 240849/371472 [8:07:59<9:59:20,  3.63it/s] 
 65%|██████▍   | 240850/371472 [8:07:59<10:06:41,  3.59it/s]
 65%|██████▍   | 240851/371472 [8:07:59<10:03:10,  3.61it/s]
 65%|██████▍   | 240852/371472 [8:07:59<10:32:26,  3.44it/s]
 65%|██████▍   | 240853/371472 [8:08:00<10:04:07,  3.60it/s]
 65%|██████▍   | 240854/371472 [8:08:00<9:54:02,  3.66it/s] 
 65%|██████▍   | 240855/371472 [8:08:00<9:50:25,  3.69it/s]
 65%|██████▍   | 240856/371472 [8:08:01<9:53:41,  3.67it/s]
 65%|██████▍   | 240857/371472 [8:08:01<10:09:11,  3.57it/s]
 65%|██████▍   | 240858/371472 [8:08:01<10:11:18,  3.56it/s]
 65%|██████▍   | 240859/371472 [8:08:02<12:18:13,  2.95it/s]
 65%|██████▍   | 240860/371472 [8:08:02<12:05:55,  3.00it/s]
                                                            
{'loss': 2.8188, 'learning_rate': 4.166163890624663e-07, 'epoch': 10.37}
+
 65%|██████▍   | 240860/371472 [8:08:02<12:05:55,  3.00it/s]
 65%|██████▍   | 240861/371472 [8:08:02<11:19:55,  3.20it/s]
 65%|██████▍   | 240862/371472 [8:08:02<10:39:31,  3.40it/s]
 65%|██████▍   | 240863/371472 [8:08:03<10:29:42,  3.46it/s]
 65%|██████▍   | 240864/371472 [8:08:03<10:32:08,  3.44it/s]
 65%|██████▍   | 240865/371472 [8:08:03<10:48:39,  3.36it/s]
 65%|██████▍   | 240866/371472 [8:08:04<10:29:14,  3.46it/s]
 65%|██████▍   | 240867/371472 [8:08:04<10:56:12,  3.32it/s]
 65%|██████▍   | 240868/371472 [8:08:04<10:20:31,  3.51it/s]
 65%|██████▍   | 240869/371472 [8:08:04<10:52:03,  3.34it/s]
 65%|██████▍   | 240870/371472 [8:08:05<10:23:59,  3.49it/s]
 65%|██████▍   | 240871/371472 [8:08:05<10:38:04,  3.41it/s]
 65%|██████▍   | 240872/371472 [8:08:05<10:36:33,  3.42it/s]
 65%|██████▍   | 240873/371472 [8:08:06<10:26:33,  3.47it/s]
 65%|██████▍   | 240874/371472 [8:08:06<10:28:48,  3.46it/s]
 65%|██████▍   | 240875/371472 [8:08:06<10:03:48,  3.60it/s]
 65%|██████▍   | 240876/371472 [8:08:06<9:54:24,  3.66it/s] 
 65%|██████▍   | 240877/371472 [8:08:07<10:15:20,  3.54it/s]
 65%|██████▍   | 240878/371472 [8:08:07<9:48:31,  3.70it/s] 
 65%|██████▍   | 240879/371472 [8:08:07<10:02:56,  3.61it/s]
 65%|██████▍   | 240880/371472 [8:08:08<9:57:18,  3.64it/s] 
                                                           
{'loss': 2.9935, 'learning_rate': 4.1656790708698743e-07, 'epoch': 10.38}
+
 65%|██████▍   | 240880/371472 [8:08:08<9:57:18,  3.64it/s]
 65%|██████▍   | 240881/371472 [8:08:08<9:51:25,  3.68it/s]
 65%|██████▍   | 240882/371472 [8:08:08<10:18:04,  3.52it/s]
 65%|██████▍   | 240883/371472 [8:08:08<10:14:52,  3.54it/s]
 65%|██████▍   | 240884/371472 [8:08:09<10:12:48,  3.55it/s]
 65%|██████▍   | 240885/371472 [8:08:09<10:01:24,  3.62it/s]
 65%|██████▍   | 240886/371472 [8:08:09<9:57:55,  3.64it/s] 
 65%|██████▍   | 240887/371472 [8:08:09<10:02:04,  3.61it/s]
 65%|██████▍   | 240888/371472 [8:08:10<9:42:57,  3.73it/s] 
 65%|██████▍   | 240889/371472 [8:08:10<9:43:27,  3.73it/s]
 65%|██████▍   | 240890/371472 [8:08:10<9:55:41,  3.65it/s]
 65%|██████▍   | 240891/371472 [8:08:11<9:53:11,  3.67it/s]
 65%|██████▍   | 240892/371472 [8:08:11<10:12:13,  3.55it/s]
 65%|██████▍   | 240893/371472 [8:08:11<10:18:51,  3.52it/s]
 65%|██████▍   | 240894/371472 [8:08:11<9:58:25,  3.64it/s] 
 65%|██████▍   | 240895/371472 [8:08:12<10:27:10,  3.47it/s]
 65%|██████▍   | 240896/371472 [8:08:12<10:25:35,  3.48it/s]
 65%|██████▍   | 240897/371472 [8:08:12<10:40:33,  3.40it/s]
 65%|██████▍   | 240898/371472 [8:08:13<11:04:52,  3.27it/s]
 65%|██████▍   | 240899/371472 [8:08:13<10:38:20,  3.41it/s]
 65%|██████▍   | 240900/371472 [8:08:13<10:20:12,  3.51it/s]
                                                            
{'loss': 2.9043, 'learning_rate': 4.165194251115085e-07, 'epoch': 10.38}
+
 65%|██████▍   | 240900/371472 [8:08:13<10:20:12,  3.51it/s]
 65%|██████▍   | 240901/371472 [8:08:13<10:15:43,  3.53it/s]
 65%|██████▍   | 240902/371472 [8:08:14<9:48:57,  3.69it/s] 
 65%|██████▍   | 240903/371472 [8:08:14<9:51:00,  3.68it/s]
 65%|██████▍   | 240904/371472 [8:08:14<9:45:05,  3.72it/s]
 65%|██████▍   | 240905/371472 [8:08:15<9:50:49,  3.68it/s]
 65%|██████▍   | 240906/371472 [8:08:15<9:49:07,  3.69it/s]
 65%|██████▍   | 240907/371472 [8:08:15<9:56:34,  3.65it/s]
 65%|██████▍   | 240908/371472 [8:08:15<10:05:38,  3.59it/s]
 65%|██████▍   | 240909/371472 [8:08:16<10:09:22,  3.57it/s]
 65%|██████▍   | 240910/371472 [8:08:16<10:11:22,  3.56it/s]
 65%|██████▍   | 240911/371472 [8:08:16<11:12:46,  3.23it/s]
 65%|██████▍   | 240912/371472 [8:08:17<10:42:43,  3.39it/s]
 65%|██████▍   | 240913/371472 [8:08:17<10:39:42,  3.40it/s]
 65%|██████▍   | 240914/371472 [8:08:17<10:21:14,  3.50it/s]
 65%|██████▍   | 240915/371472 [8:08:17<10:13:14,  3.55it/s]
 65%|██████▍   | 240916/371472 [8:08:18<9:58:12,  3.64it/s] 
 65%|██████▍   | 240917/371472 [8:08:18<9:45:14,  3.72it/s]
 65%|██████▍   | 240918/371472 [8:08:18<10:28:09,  3.46it/s]
 65%|██████▍   | 240919/371472 [8:08:18<10:00:26,  3.62it/s]
 65%|██████▍   | 240920/371472 [8:08:19<9:58:22,  3.64it/s] 
                                                           
{'loss': 2.9468, 'learning_rate': 4.164709431360297e-07, 'epoch': 10.38}
+
 65%|██████▍   | 240920/371472 [8:08:19<9:58:22,  3.64it/s]
 65%|██████▍   | 240921/371472 [8:08:19<10:40:05,  3.40it/s]
 65%|██████▍   | 240922/371472 [8:08:19<10:53:33,  3.33it/s]
 65%|██████▍   | 240923/371472 [8:08:20<10:37:49,  3.41it/s]
 65%|██████▍   | 240924/371472 [8:08:20<10:30:43,  3.45it/s]
 65%|██████▍   | 240925/371472 [8:08:20<10:23:19,  3.49it/s]
 65%|██████▍   | 240926/371472 [8:08:21<10:51:12,  3.34it/s]
 65%|██████▍   | 240927/371472 [8:08:21<10:36:47,  3.42it/s]
 65%|██████▍   | 240928/371472 [8:08:21<10:59:53,  3.30it/s]
 65%|██████▍   | 240929/371472 [8:08:21<10:58:22,  3.30it/s]
 65%|██████▍   | 240930/371472 [8:08:22<10:19:20,  3.51it/s]
 65%|██████▍   | 240931/371472 [8:08:22<10:00:04,  3.63it/s]
 65%|██████▍   | 240932/371472 [8:08:22<10:08:22,  3.58it/s]
 65%|██████▍   | 240933/371472 [8:08:23<10:28:38,  3.46it/s]
 65%|██████▍   | 240934/371472 [8:08:23<10:52:37,  3.33it/s]
 65%|██████▍   | 240935/371472 [8:08:23<10:30:50,  3.45it/s]
 65%|██████▍   | 240936/371472 [8:08:23<10:07:30,  3.58it/s]
 65%|██████▍   | 240937/371472 [8:08:24<10:31:06,  3.45it/s]
 65%|██████▍   | 240938/371472 [8:08:24<10:05:33,  3.59it/s]
 65%|██████▍   | 240939/371472 [8:08:24<10:05:55,  3.59it/s]
 65%|██████▍   | 240940/371472 [8:08:25<10:07:33,  3.58it/s]
                                                            
{'loss': 2.8401, 'learning_rate': 4.1642246116055075e-07, 'epoch': 10.38}
+
 65%|██████▍   | 240940/371472 [8:08:25<10:07:33,  3.58it/s]
 65%|██████▍   | 240941/371472 [8:08:25<10:19:44,  3.51it/s]
 65%|██████▍   | 240942/371472 [8:08:25<10:02:16,  3.61it/s]
 65%|██████▍   | 240943/371472 [8:08:25<10:20:23,  3.51it/s]
 65%|██████▍   | 240944/371472 [8:08:26<12:50:57,  2.82it/s]
 65%|██████▍   | 240945/371472 [8:08:26<12:09:28,  2.98it/s]
 65%|██████▍   | 240946/371472 [8:08:27<11:36:22,  3.12it/s]
 65%|██████▍   | 240947/371472 [8:08:27<11:52:51,  3.05it/s]
 65%|██████▍   | 240948/371472 [8:08:27<11:05:05,  3.27it/s]
 65%|██████▍   | 240949/371472 [8:08:27<10:31:19,  3.45it/s]
 65%|██████▍   | 240950/371472 [8:08:28<10:08:03,  3.58it/s]
 65%|██████▍   | 240951/371472 [8:08:28<10:12:53,  3.55it/s]
 65%|██████▍   | 240952/371472 [8:08:28<9:59:01,  3.63it/s] 
 65%|██████▍   | 240953/371472 [8:08:28<9:48:20,  3.70it/s]
 65%|██████▍   | 240954/371472 [8:08:29<9:24:21,  3.85it/s]
 65%|██████▍   | 240955/371472 [8:08:29<9:18:05,  3.90it/s]
 65%|██████▍   | 240956/371472 [8:08:29<9:16:09,  3.91it/s]
 65%|██████▍   | 240957/371472 [8:08:29<9:54:03,  3.66it/s]
 65%|██████▍   | 240958/371472 [8:08:30<9:34:34,  3.79it/s]
 65%|██████▍   | 240959/371472 [8:08:30<9:33:22,  3.79it/s]
 65%|██████▍   | 240960/371472 [8:08:30<10:40:51,  3.39it/s]
                                                            
{'loss': 2.8695, 'learning_rate': 4.163739791850719e-07, 'epoch': 10.38}
+
 65%|██████▍   | 240960/371472 [8:08:30<10:40:51,  3.39it/s]
 65%|██████▍   | 240961/371472 [8:08:31<10:16:12,  3.53it/s]
 65%|██████▍   | 240962/371472 [8:08:31<9:58:40,  3.63it/s] 
 65%|██████▍   | 240963/371472 [8:08:31<9:44:39,  3.72it/s]
 65%|██████▍   | 240964/371472 [8:08:31<10:29:34,  3.45it/s]
 65%|██████▍   | 240965/371472 [8:08:32<10:08:46,  3.57it/s]
 65%|██████▍   | 240966/371472 [8:08:32<10:01:04,  3.62it/s]
 65%|██████▍   | 240967/371472 [8:08:32<9:41:17,  3.74it/s] 
 65%|██████▍   | 240968/371472 [8:08:32<9:27:32,  3.83it/s]
 65%|██████▍   | 240969/371472 [8:08:33<10:01:04,  3.62it/s]
 65%|██████▍   | 240970/371472 [8:08:33<9:45:13,  3.72it/s] 
 65%|██████▍   | 240971/371472 [8:08:33<9:42:17,  3.74it/s]
 65%|██████▍   | 240972/371472 [8:08:34<9:46:35,  3.71it/s]
 65%|██████▍   | 240973/371472 [8:08:34<9:38:37,  3.76it/s]
 65%|██████▍   | 240974/371472 [8:08:34<9:46:22,  3.71it/s]
 65%|██████▍   | 240975/371472 [8:08:34<9:30:36,  3.81it/s]
 65%|██████▍   | 240976/371472 [8:08:35<9:22:40,  3.87it/s]
 65%|██████▍   | 240977/371472 [8:08:35<9:47:10,  3.70it/s]
 65%|██████▍   | 240978/371472 [8:08:35<9:45:09,  3.72it/s]
 65%|██████▍   | 240979/371472 [8:08:35<9:48:27,  3.70it/s]
 65%|██████▍   | 240980/371472 [8:08:36<9:38:26,  3.76it/s]
                                                           
{'loss': 2.9624, 'learning_rate': 4.1632549720959295e-07, 'epoch': 10.38}
+
 65%|██████▍   | 240980/371472 [8:08:36<9:38:26,  3.76it/s]
 65%|██████▍   | 240981/371472 [8:08:36<10:12:37,  3.55it/s]
 65%|██████▍   | 240982/371472 [8:08:36<10:04:04,  3.60it/s]
 65%|██████▍   | 240983/371472 [8:08:37<10:26:57,  3.47it/s]
 65%|██████▍   | 240984/371472 [8:08:37<10:32:35,  3.44it/s]
 65%|██████▍   | 240985/371472 [8:08:37<10:13:42,  3.54it/s]
 65%|██████▍   | 240986/371472 [8:08:37<9:56:03,  3.65it/s] 
 65%|██████▍   | 240987/371472 [8:08:38<9:50:15,  3.68it/s]
 65%|██████▍   | 240988/371472 [8:08:38<9:57:34,  3.64it/s]
 65%|██████▍   | 240989/371472 [8:08:38<9:47:45,  3.70it/s]
 65%|██████▍   | 240990/371472 [8:08:39<10:01:33,  3.62it/s]
 65%|██████▍   | 240991/371472 [8:08:39<9:57:30,  3.64it/s] 
 65%|██████▍   | 240992/371472 [8:08:39<9:44:41,  3.72it/s]
 65%|██████▍   | 240993/371472 [8:08:39<9:47:20,  3.70it/s]
 65%|██████▍   | 240994/371472 [8:08:40<9:49:24,  3.69it/s]
 65%|██████▍   | 240995/371472 [8:08:40<9:58:06,  3.64it/s]
 65%|██████▍   | 240996/371472 [8:08:40<10:04:21,  3.60it/s]
 65%|██████▍   | 240997/371472 [8:08:40<10:03:20,  3.60it/s]
 65%|██████▍   | 240998/371472 [8:08:41<10:00:15,  3.62it/s]
 65%|██████▍   | 240999/371472 [8:08:41<10:01:41,  3.61it/s]
 65%|██████▍   | 241000/371472 [8:08:41<9:45:29,  3.71it/s] 
                                                           
{'loss': 2.911, 'learning_rate': 4.16277015234114e-07, 'epoch': 10.38}
+
 65%|██████▍   | 241000/371472 [8:08:41<9:45:29,  3.71it/s]
 65%|██████▍   | 241001/371472 [8:08:41<9:39:15,  3.75it/s]
 65%|██████▍   | 241002/371472 [8:08:42<9:34:01,  3.79it/s]
 65%|██████▍   | 241003/371472 [8:08:42<10:43:37,  3.38it/s]
 65%|██████▍   | 241004/371472 [8:08:42<10:29:17,  3.46it/s]
 65%|██████▍   | 241005/371472 [8:08:43<10:08:06,  3.58it/s]
 65%|██████▍   | 241006/371472 [8:08:43<9:50:41,  3.68it/s] 
 65%|██████▍   | 241007/371472 [8:08:43<10:38:44,  3.40it/s]
 65%|██████▍   | 241008/371472 [8:08:44<10:36:07,  3.42it/s]
 65%|██████▍   | 241009/371472 [8:08:44<10:58:27,  3.30it/s]
 65%|██████▍   | 241010/371472 [8:08:44<10:43:35,  3.38it/s]
 65%|██████▍   | 241011/371472 [8:08:45<11:33:19,  3.14it/s]
 65%|██████▍   | 241012/371472 [8:08:45<10:41:53,  3.39it/s]
 65%|██████▍   | 241013/371472 [8:08:45<10:56:28,  3.31it/s]
 65%|██████▍   | 241014/371472 [8:08:45<10:31:47,  3.44it/s]
 65%|██████▍   | 241015/371472 [8:08:46<10:39:34,  3.40it/s]
 65%|██████▍   | 241016/371472 [8:08:46<10:58:34,  3.30it/s]
 65%|██████▍   | 241017/371472 [8:08:46<10:43:12,  3.38it/s]
 65%|██████▍   | 241018/371472 [8:08:47<10:25:50,  3.47it/s]
 65%|██████▍   | 241019/371472 [8:08:47<10:31:52,  3.44it/s]
 65%|██████▍   | 241020/371472 [8:08:47<9:56:30,  3.64it/s] 
                                                           
{'loss': 2.8051, 'learning_rate': 4.1622853325863515e-07, 'epoch': 10.38}
+
 65%|██████▍   | 241020/371472 [8:08:47<9:56:30,  3.64it/s]
 65%|██████▍   | 241021/371472 [8:08:47<9:41:18,  3.74it/s]
 65%|██████▍   | 241022/371472 [8:08:48<9:49:01,  3.69it/s]
 65%|██████▍   | 241023/371472 [8:08:48<9:31:07,  3.81it/s]
 65%|██████▍   | 241024/371472 [8:08:48<9:36:32,  3.77it/s]
 65%|██████▍   | 241025/371472 [8:08:48<10:55:42,  3.32it/s]
 65%|██████▍   | 241026/371472 [8:08:49<10:46:55,  3.36it/s]
 65%|██████▍   | 241027/371472 [8:08:49<10:34:22,  3.43it/s]
 65%|██████▍   | 241028/371472 [8:08:49<10:16:22,  3.53it/s]
 65%|██████▍   | 241029/371472 [8:08:50<10:06:25,  3.58it/s]
 65%|██████▍   | 241030/371472 [8:08:50<10:26:57,  3.47it/s]
 65%|██████▍   | 241031/371472 [8:08:50<10:10:12,  3.56it/s]
 65%|██████▍   | 241032/371472 [8:08:50<10:16:12,  3.53it/s]
 65%|██████▍   | 241033/371472 [8:08:51<10:09:15,  3.57it/s]
 65%|██████▍   | 241034/371472 [8:08:51<9:57:58,  3.64it/s] 
 65%|██████▍   | 241035/371472 [8:08:51<9:40:32,  3.74it/s]
 65%|██████▍   | 241036/371472 [8:08:51<9:34:30,  3.78it/s]
 65%|██████▍   | 241037/371472 [8:08:52<9:35:10,  3.78it/s]
 65%|██████▍   | 241038/371472 [8:08:52<9:49:51,  3.69it/s]
 65%|██████▍   | 241039/371472 [8:08:52<10:03:21,  3.60it/s]
 65%|██████▍   | 241040/371472 [8:08:53<9:52:30,  3.67it/s] 
                                                           
{'loss': 2.8986, 'learning_rate': 4.161800512831562e-07, 'epoch': 10.38}
+
 65%|██████▍   | 241040/371472 [8:08:53<9:52:30,  3.67it/s]
 65%|██████▍   | 241041/371472 [8:08:53<10:23:23,  3.49it/s]
 65%|██████▍   | 241042/371472 [8:08:53<10:04:37,  3.60it/s]
 65%|██████▍   | 241043/371472 [8:08:53<9:50:39,  3.68it/s] 
 65%|██████▍   | 241044/371472 [8:08:54<10:49:56,  3.34it/s]
 65%|██████▍   | 241045/371472 [8:08:54<10:43:41,  3.38it/s]
 65%|██████▍   | 241046/371472 [8:08:54<10:34:06,  3.43it/s]
 65%|██████▍   | 241047/371472 [8:08:55<10:07:04,  3.58it/s]
 65%|██████▍   | 241048/371472 [8:08:55<10:43:35,  3.38it/s]
 65%|██████▍   | 241049/371472 [8:08:55<10:49:36,  3.35it/s]
 65%|██████▍   | 241050/371472 [8:08:56<11:29:31,  3.15it/s]
 65%|██████▍   | 241051/371472 [8:08:56<10:43:15,  3.38it/s]
 65%|██████▍   | 241052/371472 [8:08:56<10:44:17,  3.37it/s]
 65%|██████▍   | 241053/371472 [8:08:56<10:18:49,  3.51it/s]
 65%|██████▍   | 241054/371472 [8:08:57<10:15:22,  3.53it/s]
 65%|██████▍   | 241055/371472 [8:08:57<10:38:22,  3.40it/s]
 65%|██████▍   | 241056/371472 [8:08:57<10:26:48,  3.47it/s]
 65%|██████▍   | 241057/371472 [8:08:58<10:03:39,  3.60it/s]
 65%|██████▍   | 241058/371472 [8:08:58<9:45:31,  3.71it/s] 
 65%|██████▍   | 241059/371472 [8:08:58<9:37:35,  3.76it/s]
 65%|██████▍   | 241060/371472 [8:08:58<9:29:05,  3.82it/s]
                                                           
{'loss': 2.9085, 'learning_rate': 4.161315693076774e-07, 'epoch': 10.38}
+
 65%|██████▍   | 241060/371472 [8:08:58<9:29:05,  3.82it/s]
 65%|██████▍   | 241061/371472 [8:08:59<9:32:47,  3.79it/s]
 65%|██████▍   | 241062/371472 [8:08:59<9:28:58,  3.82it/s]
 65%|██████▍   | 241063/371472 [8:08:59<9:40:59,  3.74it/s]
 65%|██████▍   | 241064/371472 [8:08:59<10:13:13,  3.54it/s]
 65%|██████▍   | 241065/371472 [8:09:00<10:31:09,  3.44it/s]
 65%|██████▍   | 241066/371472 [8:09:00<10:23:51,  3.48it/s]
 65%|██████▍   | 241067/371472 [8:09:00<10:08:18,  3.57it/s]
 65%|██████▍   | 241068/371472 [8:09:01<10:02:22,  3.61it/s]
 65%|██████▍   | 241069/371472 [8:09:01<10:04:26,  3.60it/s]
 65%|██████▍   | 241070/371472 [8:09:01<9:53:47,  3.66it/s] 
 65%|██████▍   | 241071/371472 [8:09:01<9:52:10,  3.67it/s]
 65%|██████▍   | 241072/371472 [8:09:02<10:03:57,  3.60it/s]
 65%|██████▍   | 241073/371472 [8:09:02<10:32:19,  3.44it/s]
 65%|██████▍   | 241074/371472 [8:09:02<10:33:04,  3.43it/s]
 65%|██████▍   | 241075/371472 [8:09:03<10:26:43,  3.47it/s]
 65%|██████▍   | 241076/371472 [8:09:03<10:10:49,  3.56it/s]
 65%|██████▍   | 241077/371472 [8:09:03<10:03:26,  3.60it/s]
 65%|██████▍   | 241078/371472 [8:09:03<10:11:34,  3.55it/s]
 65%|██████▍   | 241079/371472 [8:09:04<10:23:41,  3.48it/s]
 65%|██████▍   | 241080/371472 [8:09:04<10:01:14,  3.61it/s]
                                                            
{'loss': 2.6737, 'learning_rate': 4.160830873321984e-07, 'epoch': 10.38}
+
 65%|██████▍   | 241080/371472 [8:09:04<10:01:14,  3.61it/s]
 65%|██████▍   | 241081/371472 [8:09:04<9:52:44,  3.67it/s] 
 65%|██████▍   | 241082/371472 [8:09:04<10:15:09,  3.53it/s]
 65%|██████▍   | 241083/371472 [8:09:05<10:31:28,  3.44it/s]
 65%|██████▍   | 241084/371472 [8:09:05<10:49:26,  3.35it/s]
 65%|██████▍   | 241085/371472 [8:09:05<10:07:58,  3.57it/s]
 65%|██████▍   | 241086/371472 [8:09:06<9:41:23,  3.74it/s] 
 65%|██████▍   | 241087/371472 [8:09:06<10:12:50,  3.55it/s]
 65%|██████▍   | 241088/371472 [8:09:06<10:01:38,  3.61it/s]
 65%|██████▍   | 241089/371472 [8:09:06<9:50:43,  3.68it/s] 
 65%|██████▍   | 241090/371472 [8:09:07<10:04:04,  3.60it/s]
 65%|██████▍   | 241091/371472 [8:09:07<10:14:31,  3.54it/s]
 65%|██████▍   | 241092/371472 [8:09:07<9:54:38,  3.65it/s] 
 65%|██████▍   | 241093/371472 [8:09:08<10:06:36,  3.58it/s]
 65%|██████▍   | 241094/371472 [8:09:08<10:09:08,  3.57it/s]
 65%|██████▍   | 241095/371472 [8:09:08<10:42:13,  3.38it/s]
 65%|██████▍   | 241096/371472 [8:09:08<10:17:30,  3.52it/s]
 65%|██████▍   | 241097/371472 [8:09:09<10:19:54,  3.51it/s]
 65%|██████▍   | 241098/371472 [8:09:09<9:52:45,  3.67it/s] 
 65%|██████▍   | 241099/371472 [8:09:09<10:16:30,  3.52it/s]
 65%|██████▍   | 241100/371472 [8:09:10<10:23:46,  3.48it/s]
                                                            
{'loss': 2.8121, 'learning_rate': 4.160346053567196e-07, 'epoch': 10.38}
+
 65%|██████▍   | 241100/371472 [8:09:10<10:23:46,  3.48it/s]
 65%|██████▍   | 241101/371472 [8:09:10<10:33:24,  3.43it/s]
 65%|██████▍   | 241102/371472 [8:09:10<10:27:45,  3.46it/s]
 65%|██████▍   | 241103/371472 [8:09:10<10:29:49,  3.45it/s]
 65%|██████▍   | 241104/371472 [8:09:11<10:47:06,  3.36it/s]
 65%|██████▍   | 241105/371472 [8:09:11<11:21:20,  3.19it/s]
 65%|██████▍   | 241106/371472 [8:09:11<11:02:17,  3.28it/s]
 65%|██████▍   | 241107/371472 [8:09:12<10:34:09,  3.43it/s]
 65%|██████▍   | 241108/371472 [8:09:12<10:26:21,  3.47it/s]
 65%|██████▍   | 241109/371472 [8:09:12<10:00:25,  3.62it/s]
 65%|██████▍   | 241110/371472 [8:09:12<10:19:22,  3.51it/s]
 65%|██████▍   | 241111/371472 [8:09:13<10:45:26,  3.37it/s]
 65%|██████▍   | 241112/371472 [8:09:13<11:52:06,  3.05it/s]
 65%|██████▍   | 241113/371472 [8:09:13<11:08:56,  3.25it/s]
 65%|██████▍   | 241114/371472 [8:09:14<10:37:36,  3.41it/s]
 65%|██████▍   | 241115/371472 [8:09:14<10:19:51,  3.51it/s]
 65%|██████▍   | 241116/371472 [8:09:14<10:19:29,  3.51it/s]
 65%|██████▍   | 241117/371472 [8:09:15<10:45:52,  3.36it/s]
 65%|██████▍   | 241118/371472 [8:09:15<10:10:35,  3.56it/s]
 65%|██████▍   | 241119/371472 [8:09:15<10:37:29,  3.41it/s]
 65%|██████▍   | 241120/371472 [8:09:16<10:57:43,  3.30it/s]
                                                            
{'loss': 2.8647, 'learning_rate': 4.1598612338124066e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241120/371472 [8:09:16<10:57:43,  3.30it/s]
 65%|██████▍   | 241121/371472 [8:09:16<10:50:45,  3.34it/s]
 65%|██████▍   | 241122/371472 [8:09:16<10:18:07,  3.51it/s]
 65%|██████▍   | 241123/371472 [8:09:16<10:25:36,  3.47it/s]
 65%|██████▍   | 241124/371472 [8:09:17<10:39:34,  3.40it/s]
 65%|██████▍   | 241125/371472 [8:09:17<10:41:37,  3.39it/s]
 65%|██████▍   | 241126/371472 [8:09:17<10:07:19,  3.58it/s]
 65%|██████▍   | 241127/371472 [8:09:18<10:48:37,  3.35it/s]
 65%|██████▍   | 241128/371472 [8:09:18<10:18:25,  3.51it/s]
 65%|██████▍   | 241129/371472 [8:09:18<10:18:16,  3.51it/s]
 65%|██████▍   | 241130/371472 [8:09:18<10:32:37,  3.43it/s]
 65%|██████▍   | 241131/371472 [8:09:19<10:46:48,  3.36it/s]
 65%|██████▍   | 241132/371472 [8:09:19<10:52:06,  3.33it/s]
 65%|██████▍   | 241133/371472 [8:09:19<10:40:26,  3.39it/s]
 65%|██████▍   | 241134/371472 [8:09:20<10:24:33,  3.48it/s]
 65%|██████▍   | 241135/371472 [8:09:20<10:17:42,  3.52it/s]
 65%|██████▍   | 241136/371472 [8:09:20<10:07:33,  3.58it/s]
 65%|██████▍   | 241137/371472 [8:09:20<9:49:21,  3.69it/s] 
 65%|██████▍   | 241138/371472 [8:09:21<10:12:08,  3.55it/s]
 65%|██████▍   | 241139/371472 [8:09:21<10:41:56,  3.38it/s]
 65%|██████▍   | 241140/371472 [8:09:21<10:43:06,  3.38it/s]
                                                            
{'loss': 2.9447, 'learning_rate': 4.159376414057618e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241140/371472 [8:09:21<10:43:06,  3.38it/s]
 65%|██████▍   | 241141/371472 [8:09:22<10:37:11,  3.41it/s]
 65%|██████▍   | 241142/371472 [8:09:22<10:20:10,  3.50it/s]
 65%|██████▍   | 241143/371472 [8:09:22<11:30:14,  3.15it/s]
 65%|██████▍   | 241144/371472 [8:09:23<11:25:17,  3.17it/s]
 65%|██████▍   | 241145/371472 [8:09:23<11:08:19,  3.25it/s]
 65%|██████▍   | 241146/371472 [8:09:23<10:39:46,  3.40it/s]
 65%|██████▍   | 241147/371472 [8:09:23<10:15:44,  3.53it/s]
 65%|██████▍   | 241148/371472 [8:09:24<10:52:20,  3.33it/s]
 65%|██████▍   | 241149/371472 [8:09:24<10:45:57,  3.36it/s]
 65%|██████▍   | 241150/371472 [8:09:24<10:35:54,  3.42it/s]
 65%|██████▍   | 241151/371472 [8:09:25<10:39:48,  3.39it/s]
 65%|██████▍   | 241152/371472 [8:09:25<10:19:16,  3.51it/s]
 65%|██████▍   | 241153/371472 [8:09:25<10:05:34,  3.59it/s]
 65%|██████▍   | 241154/371472 [8:09:25<10:03:45,  3.60it/s]
 65%|██████▍   | 241155/371472 [8:09:26<9:51:32,  3.67it/s] 
 65%|██████▍   | 241156/371472 [8:09:26<10:23:24,  3.48it/s]
 65%|██████▍   | 241157/371472 [8:09:26<10:21:56,  3.49it/s]
 65%|██████▍   | 241158/371472 [8:09:27<10:33:07,  3.43it/s]
 65%|██████▍   | 241159/371472 [8:09:27<10:55:43,  3.31it/s]
 65%|██████▍   | 241160/371472 [8:09:27<10:16:46,  3.52it/s]
                                                            
{'loss': 2.9149, 'learning_rate': 4.1588915943028286e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241160/371472 [8:09:27<10:16:46,  3.52it/s]
 65%|██████▍   | 241161/371472 [8:09:27<10:20:42,  3.50it/s]
 65%|██████▍   | 241162/371472 [8:09:28<9:54:11,  3.66it/s] 
 65%|██████▍   | 241163/371472 [8:09:28<9:53:30,  3.66it/s]
 65%|██████▍   | 241164/371472 [8:09:28<10:25:16,  3.47it/s]
 65%|██████▍   | 241165/371472 [8:09:29<10:16:45,  3.52it/s]
 65%|██████▍   | 241166/371472 [8:09:29<10:15:12,  3.53it/s]
 65%|██████▍   | 241167/371472 [8:09:29<9:51:37,  3.67it/s] 
 65%|██████▍   | 241168/371472 [8:09:29<9:40:28,  3.74it/s]
 65%|██████▍   | 241169/371472 [8:09:30<9:31:05,  3.80it/s]
 65%|██████▍   | 241170/371472 [8:09:30<10:27:55,  3.46it/s]
 65%|██████▍   | 241171/371472 [8:09:30<10:17:37,  3.52it/s]
 65%|██████▍   | 241172/371472 [8:09:30<10:11:48,  3.55it/s]
 65%|██████▍   | 241173/371472 [8:09:31<10:07:39,  3.57it/s]
 65%|██████▍   | 241174/371472 [8:09:31<10:27:26,  3.46it/s]
 65%|██████▍   | 241175/371472 [8:09:31<10:06:56,  3.58it/s]
 65%|██████▍   | 241176/371472 [8:09:32<9:54:45,  3.65it/s] 
 65%|██████▍   | 241177/371472 [8:09:32<9:38:37,  3.75it/s]
 65%|██████▍   | 241178/371472 [8:09:32<9:44:01,  3.72it/s]
 65%|██████▍   | 241179/371472 [8:09:32<9:49:36,  3.68it/s]
 65%|██████▍   | 241180/371472 [8:09:33<9:30:38,  3.81it/s]
                                                           
{'loss': 2.9659, 'learning_rate': 4.1584067745480404e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241180/371472 [8:09:33<9:30:38,  3.81it/s]
 65%|██████▍   | 241181/371472 [8:09:33<10:13:12,  3.54it/s]
 65%|██████▍   | 241182/371472 [8:09:33<10:36:44,  3.41it/s]
 65%|██████▍   | 241183/371472 [8:09:34<11:05:18,  3.26it/s]
 65%|██████▍   | 241184/371472 [8:09:34<11:12:19,  3.23it/s]
 65%|██████▍   | 241185/371472 [8:09:34<11:14:38,  3.22it/s]
 65%|██████▍   | 241186/371472 [8:09:34<10:41:39,  3.38it/s]
 65%|██████▍   | 241187/371472 [8:09:35<10:32:46,  3.43it/s]
 65%|██████▍   | 241188/371472 [8:09:35<11:00:03,  3.29it/s]
 65%|██████▍   | 241189/371472 [8:09:35<11:09:21,  3.24it/s]
 65%|██████▍   | 241190/371472 [8:09:36<10:26:12,  3.47it/s]
 65%|██████▍   | 241191/371472 [8:09:36<10:36:24,  3.41it/s]
 65%|██████▍   | 241192/371472 [8:09:36<10:30:23,  3.44it/s]
 65%|██████▍   | 241193/371472 [8:09:36<10:16:32,  3.52it/s]
 65%|██████▍   | 241194/371472 [8:09:37<10:48:36,  3.35it/s]
 65%|██████▍   | 241195/371472 [8:09:37<10:18:33,  3.51it/s]
 65%|██████▍   | 241196/371472 [8:09:37<10:45:12,  3.37it/s]
 65%|██████▍   | 241197/371472 [8:09:38<10:23:05,  3.48it/s]
 65%|██████▍   | 241198/371472 [8:09:38<10:24:33,  3.48it/s]
 65%|██████▍   | 241199/371472 [8:09:38<10:26:49,  3.46it/s]
 65%|██████▍   | 241200/371472 [8:09:39<10:07:10,  3.58it/s]
                                                            
{'loss': 2.8037, 'learning_rate': 4.157921954793251e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241200/371472 [8:09:39<10:07:10,  3.58it/s]
 65%|██████▍   | 241201/371472 [8:09:39<10:50:57,  3.34it/s]
 65%|██████▍   | 241202/371472 [8:09:39<10:42:56,  3.38it/s]
 65%|██████▍   | 241203/371472 [8:09:39<10:56:14,  3.31it/s]
 65%|██████▍   | 241204/371472 [8:09:40<10:34:28,  3.42it/s]
 65%|██████▍   | 241205/371472 [8:09:40<10:43:32,  3.37it/s]
 65%|██████▍   | 241206/371472 [8:09:40<10:58:12,  3.30it/s]
 65%|██████▍   | 241207/371472 [8:09:41<10:46:06,  3.36it/s]
 65%|██████▍   | 241208/371472 [8:09:41<10:51:48,  3.33it/s]
 65%|██████▍   | 241209/371472 [8:09:41<11:09:53,  3.24it/s]
 65%|██████▍   | 241210/371472 [8:09:42<10:36:25,  3.41it/s]
 65%|██████▍   | 241211/371472 [8:09:42<10:24:46,  3.47it/s]
 65%|██████▍   | 241212/371472 [8:09:42<10:06:18,  3.58it/s]
 65%|██████▍   | 241213/371472 [8:09:42<10:30:54,  3.44it/s]
 65%|██████▍   | 241214/371472 [8:09:43<10:21:50,  3.49it/s]
 65%|██████▍   | 241215/371472 [8:09:43<10:15:12,  3.53it/s]
 65%|██████▍   | 241216/371472 [8:09:43<10:04:54,  3.59it/s]
 65%|██████▍   | 241217/371472 [8:09:43<10:01:34,  3.61it/s]
 65%|██████▍   | 241218/371472 [8:09:44<11:12:26,  3.23it/s]
 65%|██████▍   | 241219/371472 [8:09:44<10:39:12,  3.40it/s]
 65%|██████▍   | 241220/371472 [8:09:44<10:24:00,  3.48it/s]
                                                            
{'loss': 2.7922, 'learning_rate': 4.1574371350384623e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241220/371472 [8:09:44<10:24:00,  3.48it/s]
 65%|██████▍   | 241221/371472 [8:09:45<10:11:12,  3.55it/s]
 65%|██████▍   | 241222/371472 [8:09:45<10:40:17,  3.39it/s]
 65%|██████▍   | 241223/371472 [8:09:45<10:27:48,  3.46it/s]
 65%|██████▍   | 241224/371472 [8:09:46<10:15:11,  3.53it/s]
 65%|██████▍   | 241225/371472 [8:09:46<10:16:35,  3.52it/s]
 65%|██████▍   | 241226/371472 [8:09:46<10:15:18,  3.53it/s]
 65%|██████▍   | 241227/371472 [8:09:46<10:13:56,  3.54it/s]
 65%|██████▍   | 241228/371472 [8:09:47<10:06:59,  3.58it/s]
 65%|██████▍   | 241229/371472 [8:09:47<11:02:09,  3.28it/s]
 65%|██████▍   | 241230/371472 [8:09:47<10:43:32,  3.37it/s]
 65%|██████▍   | 241231/371472 [8:09:48<10:19:18,  3.51it/s]
 65%|██████▍   | 241232/371472 [8:09:48<10:16:41,  3.52it/s]
 65%|██████▍   | 241233/371472 [8:09:48<9:52:32,  3.66it/s] 
 65%|██████▍   | 241234/371472 [8:09:48<11:09:59,  3.24it/s]
 65%|██████▍   | 241235/371472 [8:09:49<11:36:35,  3.12it/s]
 65%|██████▍   | 241236/371472 [8:09:49<10:51:37,  3.33it/s]
 65%|██████▍   | 241237/371472 [8:09:49<10:23:03,  3.48it/s]
 65%|██████▍   | 241238/371472 [8:09:50<10:18:36,  3.51it/s]
 65%|██████▍   | 241239/371472 [8:09:50<9:55:45,  3.64it/s] 
 65%|██████▍   | 241240/371472 [8:09:50<10:10:02,  3.56it/s]
                                                            
{'loss': 2.7934, 'learning_rate': 4.1569523152836736e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241240/371472 [8:09:50<10:10:02,  3.56it/s]
 65%|██████▍   | 241241/371472 [8:09:50<10:42:36,  3.38it/s]
 65%|██████▍   | 241242/371472 [8:09:51<10:24:36,  3.47it/s]
 65%|██████▍   | 241243/371472 [8:09:51<10:23:11,  3.48it/s]
 65%|██████▍   | 241244/371472 [8:09:51<10:01:50,  3.61it/s]
 65%|██████▍   | 241245/371472 [8:09:52<9:47:38,  3.69it/s] 
 65%|██████▍   | 241246/371472 [8:09:52<9:54:35,  3.65it/s]
 65%|██████▍   | 241247/371472 [8:09:52<9:55:46,  3.64it/s]
 65%|██████▍   | 241248/371472 [8:09:52<10:12:27,  3.54it/s]
 65%|██████▍   | 241249/371472 [8:09:53<9:58:12,  3.63it/s] 
 65%|██████▍   | 241250/371472 [8:09:53<9:55:32,  3.64it/s]
 65%|██████▍   | 241251/371472 [8:09:53<9:49:30,  3.68it/s]
 65%|██████▍   | 241252/371472 [8:09:53<9:52:33,  3.66it/s]
 65%|██████▍   | 241253/371472 [8:09:54<10:19:09,  3.51it/s]
 65%|██████▍   | 241254/371472 [8:09:54<10:33:14,  3.43it/s]
 65%|██████▍   | 241255/371472 [8:09:54<10:18:58,  3.51it/s]
 65%|██████▍   | 241256/371472 [8:09:55<10:23:59,  3.48it/s]
 65%|██████▍   | 241257/371472 [8:09:55<10:16:09,  3.52it/s]
 65%|██████▍   | 241258/371472 [8:09:55<9:56:48,  3.64it/s] 
 65%|██████▍   | 241259/371472 [8:09:55<10:04:26,  3.59it/s]
 65%|██████▍   | 241260/371472 [8:09:56<9:58:25,  3.63it/s] 
                                                           
{'loss': 3.0495, 'learning_rate': 4.156467495528885e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241260/371472 [8:09:56<9:58:25,  3.63it/s]
 65%|██████▍   | 241261/371472 [8:09:56<9:52:31,  3.66it/s]
 65%|██████▍   | 241262/371472 [8:09:56<10:36:06,  3.41it/s]
 65%|██████▍   | 241263/371472 [8:09:57<10:18:28,  3.51it/s]
 65%|██████▍   | 241264/371472 [8:09:57<10:40:54,  3.39it/s]
 65%|██████▍   | 241265/371472 [8:09:57<10:10:41,  3.55it/s]
 65%|██████▍   | 241266/371472 [8:09:57<10:27:48,  3.46it/s]
 65%|██████▍   | 241267/371472 [8:09:58<10:31:20,  3.44it/s]
 65%|██████▍   | 241268/371472 [8:09:58<10:15:26,  3.53it/s]
 65%|██████▍   | 241269/371472 [8:09:58<10:24:26,  3.48it/s]
 65%|██████▍   | 241270/371472 [8:09:59<12:06:46,  2.99it/s]
 65%|██████▍   | 241271/371472 [8:09:59<11:17:58,  3.20it/s]
 65%|██████▍   | 241272/371472 [8:09:59<11:11:54,  3.23it/s]
 65%|██████▍   | 241273/371472 [8:10:00<10:49:45,  3.34it/s]
 65%|██████▍   | 241274/371472 [8:10:00<10:30:29,  3.44it/s]
 65%|██████▍   | 241275/371472 [8:10:00<10:10:57,  3.55it/s]
 65%|██████▍   | 241276/371472 [8:10:00<10:19:20,  3.50it/s]
 65%|██████��   | 241277/371472 [8:10:01<10:26:50,  3.46it/s]
 65%|██████▍   | 241278/371472 [8:10:01<10:38:11,  3.40it/s]
 65%|██████▍   | 241279/371472 [8:10:01<10:12:38,  3.54it/s]
 65%|██████▍   | 241280/371472 [8:10:02<10:13:48,  3.54it/s]
                                                            
{'loss': 2.9014, 'learning_rate': 4.155982675774095e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241280/371472 [8:10:02<10:13:48,  3.54it/s]
 65%|██████▍   | 241281/371472 [8:10:02<10:01:52,  3.61it/s]
 65%|██████▍   | 241282/371472 [8:10:02<10:02:03,  3.60it/s]
 65%|██████▍   | 241283/371472 [8:10:02<10:43:33,  3.37it/s]
 65%|██████▍   | 241284/371472 [8:10:03<10:15:23,  3.53it/s]
 65%|██████▍   | 241285/371472 [8:10:03<10:13:10,  3.54it/s]
 65%|██████▍   | 241286/371472 [8:10:03<10:22:52,  3.48it/s]
 65%|██████▍   | 241287/371472 [8:10:04<10:03:14,  3.60it/s]
 65%|██████▍   | 241288/371472 [8:10:04<9:54:54,  3.65it/s] 
 65%|██████▍   | 241289/371472 [8:10:04<10:06:16,  3.58it/s]
 65%|██████▍   | 241290/371472 [8:10:04<10:07:08,  3.57it/s]
 65%|██████▍   | 241291/371472 [8:10:05<9:52:51,  3.66it/s] 
 65%|██████▍   | 241292/371472 [8:10:05<9:35:35,  3.77it/s]
 65%|██████▍   | 241293/371472 [8:10:05<9:36:05,  3.77it/s]
 65%|██████▍   | 241294/371472 [8:10:05<9:48:21,  3.69it/s]
 65%|██████▍   | 241295/371472 [8:10:06<9:58:21,  3.63it/s]
 65%|██████▍   | 241296/371472 [8:10:06<9:52:43,  3.66it/s]
 65%|██████▍   | 241297/371472 [8:10:06<9:54:55,  3.65it/s]
 65%|██████▍   | 241298/371472 [8:10:07<11:03:39,  3.27it/s]
 65%|██████▍   | 241299/371472 [8:10:07<10:28:14,  3.45it/s]
 65%|██████▍   | 241300/371472 [8:10:07<10:26:34,  3.46it/s]
                                                            
{'loss': 2.8079, 'learning_rate': 4.155497856019307e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241300/371472 [8:10:07<10:26:34,  3.46it/s]
 65%|██████▍   | 241301/371472 [8:10:08<10:38:21,  3.40it/s]
 65%|██████▍   | 241302/371472 [8:10:08<10:30:19,  3.44it/s]
 65%|██████▍   | 241303/371472 [8:10:08<9:57:41,  3.63it/s] 
 65%|██████▍   | 241304/371472 [8:10:08<10:16:26,  3.52it/s]
 65%|██████▍   | 241305/371472 [8:10:09<10:17:14,  3.51it/s]
 65%|██████▍   | 241306/371472 [8:10:09<10:25:00,  3.47it/s]
 65%|██████▍   | 241307/371472 [8:10:09<10:31:09,  3.44it/s]
 65%|██████▍   | 241308/371472 [8:10:10<13:12:30,  2.74it/s]
 65%|██████▍   | 241309/371472 [8:10:10<12:16:49,  2.94it/s]
 65%|██████▍   | 241310/371472 [8:10:10<12:17:03,  2.94it/s]
 65%|██████▍   | 241311/371472 [8:10:11<11:22:45,  3.18it/s]
 65%|██████▍   | 241312/371472 [8:10:11<10:40:20,  3.39it/s]
 65%|██████▍   | 241313/371472 [8:10:11<10:16:04,  3.52it/s]
 65%|██████▍   | 241314/371472 [8:10:11<10:09:37,  3.56it/s]
 65%|██████▍   | 241315/371472 [8:10:12<10:11:46,  3.55it/s]
 65%|██████▍   | 241316/371472 [8:10:12<10:35:16,  3.41it/s]
 65%|██████▍   | 241317/371472 [8:10:12<10:25:58,  3.47it/s]
 65%|██████▍   | 241318/371472 [8:10:13<9:58:25,  3.62it/s] 
 65%|██████▍   | 241319/371472 [8:10:13<9:43:16,  3.72it/s]
 65%|██████▍   | 241320/371472 [8:10:13<9:34:45,  3.77it/s]
                                                           
{'loss': 2.9584, 'learning_rate': 4.1550130362645175e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241320/371472 [8:10:13<9:34:45,  3.77it/s]
 65%|██████▍   | 241321/371472 [8:10:13<9:30:25,  3.80it/s]
 65%|██████▍   | 241322/371472 [8:10:14<10:46:51,  3.35it/s]
 65%|██████▍   | 241323/371472 [8:10:14<10:09:27,  3.56it/s]
 65%|██████▍   | 241324/371472 [8:10:14<9:48:58,  3.68it/s] 
 65%|██████▍   | 241325/371472 [8:10:15<10:11:37,  3.55it/s]
 65%|██████▍   | 241326/371472 [8:10:15<9:57:00,  3.63it/s] 
 65%|██████▍   | 241327/371472 [8:10:15<10:08:02,  3.57it/s]
 65%|██████▍   | 241328/371472 [8:10:15<10:57:06,  3.30it/s]
 65%|██████▍   | 241329/371472 [8:10:16<10:32:43,  3.43it/s]
 65%|██████▍   | 241330/371472 [8:10:16<10:27:10,  3.46it/s]
 65%|██████▍   | 241331/371472 [8:10:16<10:12:42,  3.54it/s]
 65%|██████▍   | 241332/371472 [8:10:17<10:22:56,  3.48it/s]
 65%|██████▍   | 241333/371472 [8:10:17<10:33:15,  3.43it/s]
 65%|██████▍   | 241334/371472 [8:10:17<10:06:03,  3.58it/s]
 65%|██████▍   | 241335/371472 [8:10:17<9:44:45,  3.71it/s] 
 65%|██████▍   | 241336/371472 [8:10:18<9:45:10,  3.71it/s]
 65%|██████▍   | 241337/371472 [8:10:18<9:37:11,  3.76it/s]
 65%|██████▍   | 241338/371472 [8:10:18<10:16:56,  3.52it/s]
 65%|██████▍   | 241339/371472 [8:10:18<9:58:47,  3.62it/s] 
 65%|██████▍   | 241340/371472 [8:10:19<9:37:11,  3.76it/s]
                                                           
{'loss': 2.8479, 'learning_rate': 4.1545282165097287e-07, 'epoch': 10.39}
+
 65%|██████▍   | 241340/371472 [8:10:19<9:37:11,  3.76it/s]
 65%|██████▍   | 241341/371472 [8:10:19<9:28:44,  3.81it/s]
 65%|██████▍   | 241342/371472 [8:10:19<9:17:33,  3.89it/s]
 65%|██████▍   | 241343/371472 [8:10:19<9:25:16,  3.84it/s]
 65%|██████▍   | 241344/371472 [8:10:20<9:36:12,  3.76it/s]
 65%|██████▍   | 241345/371472 [8:10:20<9:22:58,  3.85it/s]
 65%|██████▍   | 241346/371472 [8:10:20<9:15:33,  3.90it/s]
 65%|██████▍   | 241347/371472 [8:10:20<9:25:32,  3.83it/s]
 65%|██████▍   | 241348/371472 [8:10:21<9:42:54,  3.72it/s]
 65%|██████▍   | 241349/371472 [8:10:21<9:32:57,  3.79it/s]
 65%|██████▍   | 241350/371472 [8:10:21<9:46:57,  3.69it/s]
 65%|██████▍   | 241351/371472 [8:10:22<9:57:37,  3.63it/s]
 65%|██████▍   | 241352/371472 [8:10:22<10:04:35,  3.59it/s]
 65%|██████▍   | 241353/371472 [8:10:22<10:40:51,  3.38it/s]
 65%|██████▍   | 241354/371472 [8:10:23<11:30:45,  3.14it/s]
 65%|██████▍   | 241355/371472 [8:10:23<10:43:22,  3.37it/s]
 65%|██████▍   | 241356/371472 [8:10:23<10:27:19,  3.46it/s]
 65%|██████▍   | 241357/371472 [8:10:23<10:47:12,  3.35it/s]
 65%|██████▍   | 241358/371472 [8:10:24<13:00:00,  2.78it/s]
 65%|██████▍   | 241359/371472 [8:10:24<11:53:18,  3.04it/s]
 65%|██████▍   | 241360/371472 [8:10:24<11:08:13,  3.25it/s]
                                                            
{'loss': 3.0081, 'learning_rate': 4.1540433967549394e-07, 'epoch': 10.4}
+
 65%|██████▍   | 241360/371472 [8:10:24<11:08:13,  3.25it/s]
 65%|██████▍   | 241361/371472 [8:10:25<10:44:01,  3.37it/s]
 65%|██████▍   | 241362/371472 [8:10:25<10:20:44,  3.49it/s]
 65%|██████▍   | 241363/371472 [8:10:25<9:51:55,  3.66it/s] 
 65%|██████▍   | 241364/371472 [8:10:26<10:43:03,  3.37it/s]
 65%|██████▍   | 241365/371472 [8:10:26<10:46:36,  3.35it/s]
 65%|██████▍   | 241366/371472 [8:10:26<11:08:05,  3.25it/s]
 65%|██████▍   | 241367/371472 [8:10:26<10:47:32,  3.35it/s]
 65%|██████▍   | 241368/371472 [8:10:27<10:52:28,  3.32it/s]
 65%|██████▍   | 241369/371472 [8:10:27<10:33:03,  3.43it/s]
 65%|██████▍   | 241370/371472 [8:10:27<10:04:26,  3.59it/s]
 65%|██████▍   | 241371/371472 [8:10:28<9:58:18,  3.62it/s] 
 65%|██████▍   | 241372/371472 [8:10:28<10:23:31,  3.48it/s]
 65%|██████▍   | 241373/371472 [8:10:28<10:47:30,  3.35it/s]
 65%|██████▍   | 241374/371472 [8:10:29<10:43:36,  3.37it/s]
 65%|██████▍   | 241375/371472 [8:10:29<10:46:46,  3.35it/s]
 65%|██████▍   | 241376/371472 [8:10:29<10:09:59,  3.55it/s]
 65%|██████▍   | 241377/371472 [8:10:29<10:22:26,  3.48it/s]
 65%|██████▍   | 241378/371472 [8:10:30<10:39:05,  3.39it/s]
 65%|██████▍   | 241379/371472 [8:10:30<10:26:15,  3.46it/s]
 65%|██████▍   | 241380/371472 [8:10:30<10:55:38,  3.31it/s]
                                                            
{'loss': 2.7531, 'learning_rate': 4.153558577000151e-07, 'epoch': 10.4}
+
 65%|██████▍   | 241380/371472 [8:10:30<10:55:38,  3.31it/s]
 65%|██████▍   | 241381/371472 [8:10:31<10:49:05,  3.34it/s]
 65%|██████▍   | 241382/371472 [8:10:31<10:30:43,  3.44it/s]
 65%|██████▍   | 241383/371472 [8:10:31<10:04:22,  3.59it/s]
 65%|██████▍   | 241384/371472 [8:10:31<9:50:15,  3.67it/s] 
 65%|██████▍   | 241385/371472 [8:10:32<10:25:39,  3.47it/s]
 65%|██████▍   | 241386/371472 [8:10:32<9:53:01,  3.66it/s] 
 65%|██████▍   | 241387/371472 [8:10:32<9:53:25,  3.65it/s]
 65%|██████▍   | 241388/371472 [8:10:32<9:56:35,  3.63it/s]
 65%|██████▍   | 241389/371472 [8:10:33<10:28:44,  3.45it/s]
 65%|██████▍   | 241390/371472 [8:10:33<10:15:30,  3.52it/s]
 65%|██████▍   | 241391/371472 [8:10:33<10:17:02,  3.51it/s]
 65%|██████▍   | 241392/371472 [8:10:34<10:12:12,  3.54it/s]
 65%|██████▍   | 241393/371472 [8:10:34<10:48:59,  3.34it/s]
 65%|██████▍   | 241394/371472 [8:10:34<10:42:36,  3.37it/s]
 65%|██████▍   | 241395/371472 [8:10:35<10:22:51,  3.48it/s]
 65%|██████▍   | 241396/371472 [8:10:35<10:27:33,  3.45it/s]
 65%|██████▍   | 241397/371472 [8:10:35<10:18:18,  3.51it/s]
 65%|██████▍   | 241398/371472 [8:10:35<10:42:41,  3.37it/s]
 65%|██████▍   | 241399/371472 [8:10:36<10:35:22,  3.41it/s]
 65%|██████▍   | 241400/371472 [8:10:36<10:15:38,  3.52it/s]
                                                            
{'loss': 2.8114, 'learning_rate': 4.1530737572453614e-07, 'epoch': 10.4}
+
 65%|██████▍   | 241400/371472 [8:10:36<10:15:38,  3.52it/s]
 65%|██████▍   | 241401/371472 [8:10:36<9:51:49,  3.66it/s] 
 65%|██████▍   | 241402/371472 [8:10:37<10:23:16,  3.48it/s]
 65%|██████▍   | 241403/371472 [8:10:37<11:01:56,  3.27it/s]
 65%|██████▍   | 241404/371472 [8:10:37<10:38:30,  3.40it/s]
 65%|██████▍   | 241405/371472 [8:10:37<10:12:09,  3.54it/s]
 65%|██████▍   | 241406/371472 [8:10:38<10:06:54,  3.57it/s]
 65%|██████▍   | 241407/371472 [8:10:38<10:40:26,  3.38it/s]
 65%|██████▍   | 241408/371472 [8:10:38<10:20:13,  3.50it/s]
 65%|██████▍   | 241409/371472 [8:10:39<10:15:49,  3.52it/s]
 65%|██████▍   | 241410/371472 [8:10:39<10:31:04,  3.43it/s]
 65%|██████▍   | 241411/371472 [8:10:39<10:15:27,  3.52it/s]
 65%|██████▍   | 241412/371472 [8:10:39<10:16:23,  3.52it/s]
 65%|██████▍   | 241413/371472 [8:10:40<10:28:54,  3.45it/s]
 65%|██████▍   | 241414/371472 [8:10:40<10:33:24,  3.42it/s]
 65%|██████▍   | 241415/371472 [8:10:40<10:32:37,  3.43it/s]
 65%|██████▍   | 241416/371472 [8:10:41<10:15:25,  3.52it/s]
 65%|██████▍   | 241417/371472 [8:10:41<10:21:34,  3.49it/s]
 65%|██████▍   | 241418/371472 [8:10:41<11:05:09,  3.26it/s]
 65%|██████▍   | 241419/371472 [8:10:41<10:39:16,  3.39it/s]
 65%|██████▍   | 241420/371472 [8:10:42<10:43:09,  3.37it/s]
                                                            
{'loss': 2.9653, 'learning_rate': 4.152588937490573e-07, 'epoch': 10.4}
+
 65%|██████▍   | 241420/371472 [8:10:42<10:43:09,  3.37it/s]
 65%|██████▍   | 241421/371472 [8:10:42<10:45:06,  3.36it/s]
 65%|██████▍   | 241422/371472 [8:10:42<10:36:24,  3.41it/s]
 65%|██████▍   | 241423/371472 [8:10:43<10:17:36,  3.51it/s]
 65%|██████▍   | 241424/371472 [8:10:43<9:59:24,  3.62it/s] 
 65%|██████▍   | 241425/371472 [8:10:43<11:01:09,  3.28it/s]
 65%|██████▍   | 241426/371472 [8:10:44<11:33:50,  3.12it/s]
 65%|██████▍   | 241427/371472 [8:10:44<11:10:55,  3.23it/s]
 65%|██████▍   | 241428/371472 [8:10:44<10:43:52,  3.37it/s]
 65%|██████▍   | 241429/371472 [8:10:44<10:37:45,  3.40it/s]
 65%|██████▍   | 241430/371472 [8:10:45<10:13:36,  3.53it/s]
 65%|██████▍   | 241431/371472 [8:10:45<10:50:31,  3.33it/s]
 65%|██████▍   | 241432/371472 [8:10:45<10:29:32,  3.44it/s]
 65%|██████▍   | 241433/371472 [8:10:46<10:11:39,  3.54it/s]
 65%|██████▍   | 241434/371472 [8:10:46<9:50:20,  3.67it/s] 
 65%|██████▍   | 241435/371472 [8:10:46<9:31:00,  3.80it/s]
 65%|██████▍   | 241436/371472 [8:10:46<9:29:05,  3.81it/s]
 65%|██████▍   | 241437/371472 [8:10:47<10:13:15,  3.53it/s]
 65%|██████▍   | 241438/371472 [8:10:47<10:00:25,  3.61it/s]
 65%|██████▍   | 241439/371472 [8:10:47<9:47:54,  3.69it/s] 
 65%|██████▍   | 241440/371472 [8:10:47<9:29:21,  3.81it/s]
                                                           
{'loss': 2.9949, 'learning_rate': 4.152104117735784e-07, 'epoch': 10.4}
+
 65%|██████▍   | 241440/371472 [8:10:47<9:29:21,  3.81it/s]
 65%|██████▍   | 241441/371472 [8:10:48<9:28:15,  3.81it/s]
 65%|██████▍   | 241442/371472 [8:10:48<9:24:39,  3.84it/s]
 65%|██████▍   | 241443/371472 [8:10:48<9:22:31,  3.85it/s]
 65%|██████▍   | 241444/371472 [8:10:48<9:34:20,  3.77it/s]
 65%|██████▍   | 241445/371472 [8:10:49<9:36:59,  3.76it/s]
 65%|██████▍   | 241446/371472 [8:10:49<9:39:31,  3.74it/s]
 65%|██████▍   | 241447/371472 [8:10:49<9:50:21,  3.67it/s]
 65%|██████▍   | 241448/371472 [8:10:50<9:53:34,  3.65it/s]
 65%|██████▍   | 241449/371472 [8:10:50<10:42:06,  3.37it/s]
 65%|██████▍   | 241450/371472 [8:10:50<10:41:47,  3.38it/s]
 65%|██████▍   | 241451/371472 [8:10:50<10:18:09,  3.51it/s]
 65%|██████▍   | 241452/371472 [8:10:51<9:53:24,  3.65it/s] 
 65%|██████▍   | 241453/371472 [8:10:51<10:08:10,  3.56it/s]
 65%|██████▍   | 241454/371472 [8:10:51<10:13:01,  3.53it/s]
 65%|██████▍   | 241455/371472 [8:10:52<10:04:48,  3.58it/s]
 65%|██████▍   | 241456/371472 [8:10:52<10:07:24,  3.57it/s]
 65%|██████▌   | 241457/371472 [8:10:52<10:13:29,  3.53it/s]
 65%|██████▌   | 241458/371472 [8:10:52<10:10:30,  3.55it/s]
 65%|██████▌   | 241459/371472 [8:10:53<10:02:57,  3.59it/s]
 65%|██████▌   | 241460/371472 [8:10:53<10:06:09,  3.57it/s]
                                                            
{'loss': 2.8473, 'learning_rate': 4.151619297980995e-07, 'epoch': 10.4}
+
 65%|██████▌   | 241460/371472 [8:10:53<10:06:09,  3.57it/s]
 65%|██████▌   | 241461/371472 [8:10:53<9:59:25,  3.61it/s] 
 65%|██████▌   | 241462/371472 [8:10:54<10:04:38,  3.58it/s]
 65%|██████▌   | 241463/371472 [8:10:54<10:16:57,  3.51it/s]
 65%|██████▌   | 241464/371472 [8:10:54<10:06:07,  3.57it/s]
 65%|██████▌   | 241465/371472 [8:10:54<9:50:42,  3.67it/s] 
 65%|██████▌   | 241466/371472 [8:10:55<9:54:41,  3.64it/s]
 65%|██████▌   | 241467/371472 [8:10:55<10:41:44,  3.38it/s]
 65%|██████▌   | 241468/371472 [8:10:55<10:47:49,  3.34it/s]
 65%|██████▌   | 241469/371472 [8:10:56<10:13:13,  3.53it/s]
 65%|██████▌   | 241470/371472 [8:10:56<10:17:51,  3.51it/s]
 65%|██████▌   | 241471/371472 [8:10:56<11:01:23,  3.28it/s]
 65%|██████▌   | 241472/371472 [8:10:56<10:31:13,  3.43it/s]
 65%|██████▌   | 241473/371472 [8:10:57<10:17:04,  3.51it/s]
 65%|██████▌   | 241474/371472 [8:10:57<10:12:13,  3.54it/s]
 65%|██████▌   | 241475/371472 [8:10:57<10:06:27,  3.57it/s]
 65%|██████▌   | 241476/371472 [8:10:58<10:35:34,  3.41it/s]
 65%|██████▌   | 241477/371472 [8:10:58<10:26:31,  3.46it/s]
 65%|██████▌   | 241478/371472 [8:10:58<10:30:29,  3.44it/s]
 65%|██████▌   | 241479/371472 [8:10:58<10:38:25,  3.39it/s]
 65%|██████▌   | 241480/371472 [8:10:59<10:24:07,  3.47it/s]
                                                            
{'loss': 2.8794, 'learning_rate': 4.151134478226206e-07, 'epoch': 10.4}
+
 65%|██████▌   | 241480/371472 [8:10:59<10:24:07,  3.47it/s]
 65%|██████▌   | 241481/371472 [8:10:59<10:15:24,  3.52it/s]
 65%|██████▌   | 241482/371472 [8:10:59<10:22:46,  3.48it/s]
 65%|██████▌   | 241483/371472 [8:11:00<10:42:48,  3.37it/s]
 65%|██████▌   | 241484/371472 [8:11:00<10:26:34,  3.46it/s]
 65%|██████▌   | 241485/371472 [8:11:00<10:02:29,  3.60it/s]
 65%|██████▌   | 241486/371472 [8:11:00<10:01:22,  3.60it/s]
 65%|██████▌   | 241487/371472 [8:11:01<10:42:45,  3.37it/s]
 65%|██████▌   | 241488/371472 [8:11:01<10:08:35,  3.56it/s]
 65%|██████▌   | 241489/371472 [8:11:01<10:09:14,  3.56it/s]
 65%|██████▌   | 241490/371472 [8:11:02<10:01:37,  3.60it/s]
 65%|██████▌   | 241491/371472 [8:11:02<10:00:13,  3.61it/s]
 65%|██████▌   | 241492/371472 [8:11:02<9:45:47,  3.70it/s] 
 65%|██████▌   | 241493/371472 [8:11:02<9:28:44,  3.81it/s]
 65%|██████▌   | 241494/371472 [8:11:03<9:19:35,  3.87it/s]
 65%|██████▌   | 241495/371472 [8:11:03<9:42:13,  3.72it/s]
 65%|██████▌   | 241496/371472 [8:11:03<10:51:57,  3.32it/s]
 65%|██████▌   | 241497/371472 [8:11:04<10:44:41,  3.36it/s]
 65%|██████▌   | 241498/371472 [8:11:04<10:28:46,  3.45it/s]
 65%|██████▌   | 241499/371472 [8:11:04<10:05:27,  3.58it/s]
 65%|██████▌   | 241500/371472 [8:11:04<10:35:39,  3.41it/s]
                                                            
{'loss': 2.798, 'learning_rate': 4.150649658471417e-07, 'epoch': 10.4}
+
 65%|██████▌   | 241500/371472 [8:11:04<10:35:39,  3.41it/s]
 65%|██████▌   | 241501/371472 [8:11:05<10:19:44,  3.50it/s]
 65%|██████▌   | 241502/371472 [8:11:05<10:09:10,  3.56it/s]
 65%|██████▌   | 241503/371472 [8:11:05<9:36:15,  3.76it/s] 
 65%|██████▌   | 241504/371472 [8:11:05<9:35:23,  3.76it/s]
 65%|██████▌   | 241505/371472 [8:11:06<9:46:06,  3.70it/s]
 65%|██████▌   | 241506/371472 [8:11:06<10:17:13,  3.51it/s]
 65%|██████▌   | 241507/371472 [8:11:06<10:20:11,  3.49it/s]
 65%|██████▌   | 241508/371472 [8:11:07<10:09:02,  3.56it/s]
 65%|██████▌   | 241509/371472 [8:11:07<10:11:24,  3.54it/s]
 65%|██████▌   | 241510/371472 [8:11:07<10:07:49,  3.56it/s]
 65%|██████▌   | 241511/371472 [8:11:07<10:44:01,  3.36it/s]
 65%|██████▌   | 241512/371472 [8:11:08<10:39:56,  3.38it/s]
 65%|██████▌   | 241513/371472 [8:11:08<10:38:04,  3.39it/s]
 65%|██████▌   | 241514/371472 [8:11:08<10:08:11,  3.56it/s]
 65%|██████▌   | 241515/371472 [8:11:09<9:52:00,  3.66it/s] 
 65%|██████▌   | 241516/371472 [8:11:09<9:31:18,  3.79it/s]
 65%|██████▌   | 241517/371472 [8:11:09<11:33:28,  3.12it/s]
 65%|██████▌   | 241518/371472 [8:11:10<10:50:14,  3.33it/s]
 65%|██████▌   | 241519/371472 [8:11:10<10:14:03,  3.53it/s]
 65%|██████▌   | 241520/371472 [8:11:10<9:50:09,  3.67it/s] 
                                                           
{'loss': 2.7728, 'learning_rate': 4.150164838716628e-07, 'epoch': 10.4}
+
 65%|██████▌   | 241520/371472 [8:11:10<9:50:09,  3.67it/s]
 65%|██████▌   | 241521/371472 [8:11:10<9:52:17,  3.66it/s]
 65%|██████▌   | 241522/371472 [8:11:11<9:49:13,  3.68it/s]
 65%|██████▌   | 241523/371472 [8:11:11<9:28:31,  3.81it/s]
 65%|██████▌   | 241524/371472 [8:11:11<9:33:51,  3.77it/s]
 65%|██████▌   | 241525/371472 [8:11:11<9:29:20,  3.80it/s]
 65%|██████▌   | 241526/371472 [8:11:12<9:35:32,  3.76it/s]
 65%|██████▌   | 241527/371472 [8:11:12<9:27:59,  3.81it/s]
 65%|██████▌   | 241528/371472 [8:11:12<10:31:15,  3.43it/s]
 65%|██████▌   | 241529/371472 [8:11:13<10:27:06,  3.45it/s]
 65%|██████▌   | 241530/371472 [8:11:13<9:50:55,  3.66it/s] 
 65%|██████▌   | 241531/371472 [8:11:13<9:24:57,  3.83it/s]
 65%|██████▌   | 241532/371472 [8:11:13<9:10:37,  3.93it/s]
 65%|██████▌   | 241533/371472 [8:11:13<9:16:40,  3.89it/s]
 65%|██████▌   | 241534/371472 [8:11:14<10:41:33,  3.38it/s]
 65%|██████▌   | 241535/371472 [8:11:14<10:24:02,  3.47it/s]
 65%|██████▌   | 241536/371472 [8:11:14<10:19:52,  3.49it/s]
 65%|██████▌   | 241537/371472 [8:11:15<10:01:09,  3.60it/s]
 65%|██████▌   | 241538/371472 [8:11:15<10:09:49,  3.55it/s]
 65%|██████▌   | 241539/371472 [8:11:15<10:26:58,  3.45it/s]
 65%|██████▌   | 241540/371472 [8:11:16<10:26:32,  3.46it/s]
                                                            
{'loss': 2.9225, 'learning_rate': 4.1496800189618385e-07, 'epoch': 10.4}
+
 65%|██████▌   | 241540/371472 [8:11:16<10:26:32,  3.46it/s]
 65%|██████▌   | 241541/371472 [8:11:16<10:34:09,  3.41it/s]
 65%|██████▌   | 241542/371472 [8:11:16<10:16:32,  3.51it/s]
 65%|██████▌   | 241543/371472 [8:11:16<9:46:01,  3.70it/s] 
 65%|██████▌   | 241544/371472 [8:11:17<10:32:51,  3.42it/s]
 65%|██████▌   | 241545/371472 [8:11:17<10:02:54,  3.59it/s]
 65%|██████▌   | 241546/371472 [8:11:17<9:42:48,  3.72it/s] 
 65%|██████▌   | 241547/371472 [8:11:17<9:46:36,  3.69it/s]
 65%|██████▌   | 241548/371472 [8:11:18<9:56:01,  3.63it/s]
 65%|██████▌   | 241549/371472 [8:11:18<10:00:38,  3.61it/s]
 65%|██████▌   | 241550/371472 [8:11:18<10:10:09,  3.55it/s]
 65%|██████▌   | 241551/371472 [8:11:19<9:53:29,  3.65it/s] 
 65%|██████▌   | 241552/371472 [8:11:19<10:12:38,  3.53it/s]
 65%|██████▌   | 241553/371472 [8:11:19<10:30:48,  3.43it/s]
 65%|██████▌   | 241554/371472 [8:11:20<10:54:26,  3.31it/s]
 65%|██████▌   | 241555/371472 [8:11:20<10:17:41,  3.51it/s]
 65%|██████▌   | 241556/371472 [8:11:20<10:20:05,  3.49it/s]
 65%|██████▌   | 241557/371472 [8:11:20<10:58:21,  3.29it/s]
 65%|██████▌   | 241558/371472 [8:11:21<10:16:21,  3.51it/s]
 65%|██████▌   | 241559/371472 [8:11:21<9:43:10,  3.71it/s] 
 65%|██████▌   | 241560/371472 [8:11:21<11:15:24,  3.21it/s]
                                                            
{'loss': 2.8209, 'learning_rate': 4.1491951992070503e-07, 'epoch': 10.4}
+
 65%|██████▌   | 241560/371472 [8:11:21<11:15:24,  3.21it/s]
 65%|██████▌   | 241561/371472 [8:11:22<10:37:31,  3.40it/s]
 65%|██████▌   | 241562/371472 [8:11:22<11:07:31,  3.24it/s]
 65%|██████▌   | 241563/371472 [8:11:22<10:18:33,  3.50it/s]
 65%|██████▌   | 241564/371472 [8:11:22<10:52:09,  3.32it/s]
 65%|██████▌   | 241565/371472 [8:11:23<10:49:14,  3.33it/s]
 65%|██████▌   | 241566/371472 [8:11:23<10:22:30,  3.48it/s]
 65%|██████▌   | 241567/371472 [8:11:23<10:15:20,  3.52it/s]
 65%|██████▌   | 241568/371472 [8:11:24<10:21:01,  3.49it/s]
 65%|██████▌   | 241569/371472 [8:11:24<10:02:37,  3.59it/s]
 65%|██████▌   | 241570/371472 [8:11:24<9:29:26,  3.80it/s] 
 65%|██████▌   | 241571/371472 [8:11:24<9:30:46,  3.79it/s]
 65%|██████▌   | 241572/371472 [8:11:25<9:47:36,  3.68it/s]
 65%|██████▌   | 241573/371472 [8:11:25<9:55:42,  3.63it/s]
 65%|██████▌   | 241574/371472 [8:11:25<9:35:17,  3.76it/s]
 65%|██████▌   | 241575/371472 [8:11:25<9:29:43,  3.80it/s]
 65%|██████▌   | 241576/371472 [8:11:26<9:31:27,  3.79it/s]
 65%|██████▌   | 241577/371472 [8:11:26<9:25:48,  3.83it/s]
 65%|██████▌   | 241578/371472 [8:11:26<9:59:17,  3.61it/s]
 65%|██████▌   | 241579/371472 [8:11:27<9:55:10,  3.64it/s]
 65%|██████▌   | 241580/371472 [8:11:27<9:52:20,  3.65it/s]
                                                           
{'loss': 2.8428, 'learning_rate': 4.148710379452261e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241580/371472 [8:11:27<9:52:20,  3.65it/s]
 65%|██████▌   | 241581/371472 [8:11:27<10:03:32,  3.59it/s]
 65%|██████▌   | 241582/371472 [8:11:27<10:12:11,  3.54it/s]
 65%|██████▌   | 241583/371472 [8:11:28<10:12:12,  3.54it/s]
 65%|██████▌   | 241584/371472 [8:11:28<10:40:07,  3.38it/s]
 65%|██████▌   | 241585/371472 [8:11:28<10:52:43,  3.32it/s]
 65%|██████▌   | 241586/371472 [8:11:29<10:32:48,  3.42it/s]
 65%|██████▌   | 241587/371472 [8:11:29<11:01:03,  3.27it/s]
 65%|██████▌   | 241588/371472 [8:11:29<11:17:42,  3.19it/s]
 65%|██████▌   | 241589/371472 [8:11:30<11:00:24,  3.28it/s]
 65%|██████▌   | 241590/371472 [8:11:30<10:31:27,  3.43it/s]
 65%|██████▌   | 241591/371472 [8:11:30<10:32:51,  3.42it/s]
 65%|██████▌   | 241592/371472 [8:11:30<10:02:41,  3.59it/s]
 65%|██████▌   | 241593/371472 [8:11:31<10:22:21,  3.48it/s]
 65%|██████▌   | 241594/371472 [8:11:31<10:22:06,  3.48it/s]
 65%|██████▌   | 241595/371472 [8:11:31<10:15:13,  3.52it/s]
 65%|██████▌   | 241596/371472 [8:11:31<10:03:58,  3.58it/s]
 65%|██████▌   | 241597/371472 [8:11:32<10:01:49,  3.60it/s]
 65%|██████▌   | 241598/371472 [8:11:32<10:04:32,  3.58it/s]
 65%|██████▌   | 241599/371472 [8:11:32<9:56:17,  3.63it/s] 
 65%|██████▌   | 241600/371472 [8:11:33<10:03:47,  3.58it/s]
                                                            
{'loss': 2.8274, 'learning_rate': 4.148225559697472e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241600/371472 [8:11:33<10:03:47,  3.58it/s]
 65%|██████▌   | 241601/371472 [8:11:33<9:55:17,  3.64it/s] 
 65%|██████▌   | 241602/371472 [8:11:33<10:41:53,  3.37it/s]
 65%|██████▌   | 241603/371472 [8:11:33<10:23:12,  3.47it/s]
 65%|██████▌   | 241604/371472 [8:11:34<10:08:13,  3.56it/s]
 65%|██████▌   | 241605/371472 [8:11:34<10:09:53,  3.55it/s]
 65%|██████▌   | 241606/371472 [8:11:34<10:06:36,  3.57it/s]
 65%|██████▌   | 241607/371472 [8:11:35<9:40:09,  3.73it/s] 
 65%|██████▌   | 241608/371472 [8:11:35<10:00:44,  3.60it/s]
 65%|██████▌   | 241609/371472 [8:11:35<9:56:30,  3.63it/s] 
 65%|██████▌   | 241610/371472 [8:11:35<9:49:18,  3.67it/s]
 65%|██████▌   | 241611/371472 [8:11:36<9:35:58,  3.76it/s]
 65%|██████▌   | 241612/371472 [8:11:36<9:37:25,  3.75it/s]
 65%|██████▌   | 241613/371472 [8:11:36<9:14:14,  3.91it/s]
 65%|██████▌   | 241614/371472 [8:11:36<9:54:46,  3.64it/s]
 65%|██████▌   | 241615/371472 [8:11:37<9:59:17,  3.61it/s]
 65%|██████▌   | 241616/371472 [8:11:37<10:09:05,  3.55it/s]
 65%|██████▌   | 241617/371472 [8:11:37<9:52:36,  3.65it/s] 
 65%|██████▌   | 241618/371472 [8:11:38<10:14:44,  3.52it/s]
 65%|██████▌   | 241619/371472 [8:11:38<9:51:35,  3.66it/s] 
 65%|██████▌   | 241620/371472 [8:11:38<9:38:34,  3.74it/s]
                                                           
{'loss': 2.8248, 'learning_rate': 4.147740739942683e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241620/371472 [8:11:38<9:38:34,  3.74it/s]
 65%|██████▌   | 241621/371472 [8:11:38<9:17:36,  3.88it/s]
 65%|██████▌   | 241622/371472 [8:11:39<9:36:49,  3.75it/s]
 65%|██████▌   | 241623/371472 [8:11:39<9:58:00,  3.62it/s]
 65%|██████▌   | 241624/371472 [8:11:39<10:57:16,  3.29it/s]
 65%|██████▌   | 241625/371472 [8:11:39<10:14:52,  3.52it/s]
 65%|██████▌   | 241626/371472 [8:11:40<10:40:08,  3.38it/s]
 65%|██████▌   | 241627/371472 [8:11:40<10:41:13,  3.37it/s]
 65%|██████▌   | 241628/371472 [8:11:40<10:11:49,  3.54it/s]
 65%|██████▌   | 241629/371472 [8:11:41<10:25:47,  3.46it/s]
 65%|██████▌   | 241630/371472 [8:11:41<10:12:42,  3.53it/s]
 65%|██████▌   | 241631/371472 [8:11:41<10:27:14,  3.45it/s]
 65%|██████▌   | 241632/371472 [8:11:41<9:57:46,  3.62it/s] 
 65%|██████▌   | 241633/371472 [8:11:42<9:46:17,  3.69it/s]
 65%|██████▌   | 241634/371472 [8:11:42<9:36:51,  3.75it/s]
 65%|██████▌   | 241635/371472 [8:11:42<9:31:21,  3.79it/s]
 65%|██████▌   | 241636/371472 [8:11:43<9:25:19,  3.83it/s]
 65%|██████▌   | 241637/371472 [8:11:43<9:09:52,  3.94it/s]
 65%|██████▌   | 241638/371472 [8:11:43<9:07:50,  3.95it/s]
 65%|██████▌   | 241639/371472 [8:11:43<10:15:18,  3.52it/s]
 65%|██████▌   | 241640/371472 [8:11:44<10:02:06,  3.59it/s]
                                                            
{'loss': 2.8687, 'learning_rate': 4.1472559201878947e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241640/371472 [8:11:44<10:02:06,  3.59it/s]
 65%|██████▌   | 241641/371472 [8:11:44<10:42:36,  3.37it/s]
 65%|██████▌   | 241642/371472 [8:11:44<10:19:20,  3.49it/s]
 65%|██████▌   | 241643/371472 [8:11:44<10:00:16,  3.60it/s]
 65%|██████▌   | 241644/371472 [8:11:45<10:28:47,  3.44it/s]
 65%|██████▌   | 241645/371472 [8:11:45<10:39:43,  3.38it/s]
 65%|██████▌   | 241646/371472 [8:11:45<10:34:52,  3.41it/s]
 65%|██████▌   | 241647/371472 [8:11:46<10:43:17,  3.36it/s]
 65%|██████▌   | 241648/371472 [8:11:46<10:19:50,  3.49it/s]
 65%|██████▌   | 241649/371472 [8:11:46<10:00:30,  3.60it/s]
 65%|██████▌   | 241650/371472 [8:11:46<9:56:38,  3.63it/s] 
 65%|██████▌   | 241651/371472 [8:11:47<9:56:05,  3.63it/s]
 65%|██████▌   | 241652/371472 [8:11:47<10:03:21,  3.59it/s]
 65%|██████▌   | 241653/371472 [8:11:47<9:43:54,  3.71it/s] 
 65%|██████▌   | 241654/371472 [8:11:48<10:35:21,  3.41it/s]
 65%|██████▌   | 241655/371472 [8:11:48<11:16:20,  3.20it/s]
 65%|██████▌   | 241656/371472 [8:11:48<11:04:56,  3.25it/s]
 65%|██████▌   | 241657/371472 [8:11:49<10:41:03,  3.37it/s]
 65%|██████▌   | 241658/371472 [8:11:49<10:08:38,  3.55it/s]
 65%|██████▌   | 241659/371472 [8:11:49<9:56:48,  3.63it/s] 
 65%|██████▌   | 241660/371472 [8:11:49<10:23:26,  3.47it/s]
                                                            
{'loss': 2.8664, 'learning_rate': 4.146771100433105e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241660/371472 [8:11:49<10:23:26,  3.47it/s]
 65%|██████▌   | 241661/371472 [8:11:50<10:34:30,  3.41it/s]
 65%|██████▌   | 241662/371472 [8:11:50<10:22:34,  3.48it/s]
 65%|██████▌   | 241663/371472 [8:11:50<10:16:50,  3.51it/s]
 65%|██████▌   | 241664/371472 [8:11:51<10:00:56,  3.60it/s]
 65%|██████▌   | 241665/371472 [8:11:51<9:47:28,  3.68it/s] 
 65%|██████▌   | 241666/371472 [8:11:51<9:29:43,  3.80it/s]
 65%|██████▌   | 241667/371472 [8:11:51<9:25:48,  3.82it/s]
 65%|██████▌   | 241668/371472 [8:11:52<9:45:09,  3.70it/s]
 65%|██████▌   | 241669/371472 [8:11:52<9:50:37,  3.66it/s]
 65%|██████▌   | 241670/371472 [8:11:52<9:49:36,  3.67it/s]
 65%|██████▌   | 241671/371472 [8:11:52<9:41:50,  3.72it/s]
 65%|██████▌   | 241672/371472 [8:11:53<10:07:45,  3.56it/s]
 65%|██████▌   | 241673/371472 [8:11:53<11:06:55,  3.24it/s]
 65%|██████▌   | 241674/371472 [8:11:53<10:22:11,  3.48it/s]
 65%|██████▌   | 241675/371472 [8:11:54<12:41:19,  2.84it/s]
 65%|██████▌   | 241676/371472 [8:11:54<11:48:04,  3.06it/s]
 65%|██████▌   | 241677/371472 [8:11:54<11:29:39,  3.14it/s]
 65%|██████▌   | 241678/371472 [8:11:55<10:58:18,  3.29it/s]
 65%|██████▌   | 241679/371472 [8:11:55<10:40:24,  3.38it/s]
 65%|██████▌   | 241680/371472 [8:11:55<10:09:14,  3.55it/s]
                                                            
{'loss': 2.6073, 'learning_rate': 4.1462862806783167e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241680/371472 [8:11:55<10:09:14,  3.55it/s]
 65%|██████▌   | 241681/371472 [8:11:55<9:51:11,  3.66it/s] 
 65%|██████▌   | 241682/371472 [8:11:56<9:54:41,  3.64it/s]
 65%|██████▌   | 241683/371472 [8:11:56<11:10:49,  3.22it/s]
 65%|██████▌   | 241684/371472 [8:11:56<10:34:04,  3.41it/s]
 65%|██████▌   | 241685/371472 [8:11:57<11:49:25,  3.05it/s]
 65%|██████▌   | 241686/371472 [8:11:57<10:57:13,  3.29it/s]
 65%|██████▌   | 241687/371472 [8:11:57<11:11:27,  3.22it/s]
 65%|██████▌   | 241688/371472 [8:11:58<10:27:07,  3.45it/s]
 65%|██████▌   | 241689/371472 [8:11:58<10:29:44,  3.43it/s]
 65%|██████▌   | 241690/371472 [8:11:58<10:05:43,  3.57it/s]
 65%|██████▌   | 241691/371472 [8:11:58<9:42:46,  3.71it/s] 
 65%|██████▌   | 241692/371472 [8:11:59<9:32:45,  3.78it/s]
 65%|██████▌   | 241693/371472 [8:11:59<10:08:18,  3.56it/s]
 65%|██████▌   | 241694/371472 [8:11:59<9:50:41,  3.66it/s] 
 65%|██████▌   | 241695/371472 [8:12:00<10:15:50,  3.51it/s]
 65%|██████▌   | 241696/371472 [8:12:00<10:31:41,  3.42it/s]
 65%|██████▌   | 241697/371472 [8:12:00<10:19:17,  3.49it/s]
 65%|██████▌   | 241698/371472 [8:12:00<10:21:04,  3.48it/s]
 65%|██████▌   | 241699/371472 [8:12:01<11:48:28,  3.05it/s]
 65%|██████▌   | 241700/371472 [8:12:01<11:11:39,  3.22it/s]
                                                            
{'loss': 2.8657, 'learning_rate': 4.1458014609235274e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241700/371472 [8:12:01<11:11:39,  3.22it/s]
 65%|██████▌   | 241701/371472 [8:12:01<10:31:35,  3.42it/s]
 65%|██████▌   | 241702/371472 [8:12:02<10:05:59,  3.57it/s]
 65%|██████▌   | 241703/371472 [8:12:02<10:37:46,  3.39it/s]
 65%|██████▌   | 241704/371472 [8:12:02<10:40:50,  3.37it/s]
 65%|██████▌   | 241705/371472 [8:12:02<10:12:36,  3.53it/s]
 65%|██████▌   | 241706/371472 [8:12:03<10:59:59,  3.28it/s]
 65%|██████▌   | 241707/371472 [8:12:03<10:44:27,  3.36it/s]
 65%|██████▌   | 241708/371472 [8:12:03<10:58:35,  3.28it/s]
 65%|██████▌   | 241709/371472 [8:12:04<10:25:13,  3.46it/s]
 65%|██████▌   | 241710/371472 [8:12:04<10:08:44,  3.55it/s]
 65%|██████▌   | 241711/371472 [8:12:04<10:26:53,  3.45it/s]
 65%|██████▌   | 241712/371472 [8:12:05<10:18:20,  3.50it/s]
 65%|██████▌   | 241713/371472 [8:12:05<10:16:11,  3.51it/s]
 65%|██████▌   | 241714/371472 [8:12:05<10:16:06,  3.51it/s]
 65%|██████▌   | 241715/371472 [8:12:05<10:11:28,  3.54it/s]
 65%|██████▌   | 241716/371472 [8:12:06<9:45:41,  3.69it/s] 
 65%|██████▌   | 241717/371472 [8:12:06<10:01:06,  3.60it/s]
 65%|██████▌   | 241718/371472 [8:12:06<10:06:24,  3.57it/s]
 65%|██████▌   | 241719/371472 [8:12:06<9:51:12,  3.66it/s] 
 65%|██████▌   | 241720/371472 [8:12:07<10:06:52,  3.56it/s]
                                                            
{'loss': 2.9552, 'learning_rate': 4.1453166411687387e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241720/371472 [8:12:07<10:06:52,  3.56it/s]
 65%|██████▌   | 241721/371472 [8:12:07<10:11:20,  3.54it/s]
 65%|██████▌   | 241722/371472 [8:12:07<9:50:07,  3.66it/s] 
 65%|██████▌   | 241723/371472 [8:12:08<10:24:25,  3.46it/s]
 65%|██████▌   | 241724/371472 [8:12:08<9:50:46,  3.66it/s] 
 65%|██████▌   | 241725/371472 [8:12:08<9:41:42,  3.72it/s]
 65%|██████▌   | 241726/371472 [8:12:08<9:30:44,  3.79it/s]
 65%|██████▌   | 241727/371472 [8:12:09<10:25:19,  3.46it/s]
 65%|██████▌   | 241728/371472 [8:12:09<10:03:13,  3.58it/s]
 65%|██████▌   | 241729/371472 [8:12:09<10:09:22,  3.55it/s]
 65%|██████▌   | 241730/371472 [8:12:09<9:44:25,  3.70it/s] 
 65%|██████▌   | 241731/371472 [8:12:10<9:33:17,  3.77it/s]
 65%|██████▌   | 241732/371472 [8:12:10<9:42:18,  3.71it/s]
 65%|██████▌   | 241733/371472 [8:12:10<9:34:26,  3.76it/s]
 65%|██████▌   | 241734/371472 [8:12:11<9:30:01,  3.79it/s]
 65%|██████▌   | 241735/371472 [8:12:11<9:48:58,  3.67it/s]
 65%|██████▌   | 241736/371472 [8:12:11<12:32:12,  2.87it/s]
 65%|██████▌   | 241737/371472 [8:12:12<11:23:06,  3.17it/s]
 65%|██████▌   | 241738/371472 [8:12:12<10:49:40,  3.33it/s]
 65%|██████▌   | 241739/371472 [8:12:12<10:14:40,  3.52it/s]
 65%|██████▌   | 241740/371472 [8:12:12<9:56:47,  3.62it/s] 
                                                           
{'loss': 2.83, 'learning_rate': 4.1448318214139494e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241740/371472 [8:12:12<9:56:47,  3.62it/s]
 65%|██████▌   | 241741/371472 [8:12:13<9:28:23,  3.80it/s]
 65%|██████▌   | 241742/371472 [8:12:13<9:43:04,  3.71it/s]
 65%|██████▌   | 241743/371472 [8:12:13<9:43:49,  3.70it/s]
 65%|██████▌   | 241744/371472 [8:12:13<9:36:02,  3.75it/s]
 65%|██████▌   | 241745/371472 [8:12:14<10:09:16,  3.55it/s]
 65%|██████▌   | 241746/371472 [8:12:14<10:21:18,  3.48it/s]
 65%|██████▌   | 241747/371472 [8:12:14<10:00:01,  3.60it/s]
 65%|██████▌   | 241748/371472 [8:12:15<9:55:13,  3.63it/s] 
 65%|██████▌   | 241749/371472 [8:12:15<9:48:22,  3.67it/s]
 65%|██████▌   | 241750/371472 [8:12:15<10:21:17,  3.48it/s]
 65%|██████▌   | 241751/371472 [8:12:15<10:04:35,  3.58it/s]
 65%|██████▌   | 241752/371472 [8:12:16<10:28:22,  3.44it/s]
 65%|██████▌   | 241753/371472 [8:12:16<10:01:53,  3.59it/s]
 65%|██████▌   | 241754/371472 [8:12:16<9:35:41,  3.76it/s] 
 65%|██████▌   | 241755/371472 [8:12:16<9:45:48,  3.69it/s]
 65%|██████▌   | 241756/371472 [8:12:17<9:55:43,  3.63it/s]
 65%|██████▌   | 241757/371472 [8:12:17<9:50:35,  3.66it/s]
 65%|██████▌   | 241758/371472 [8:12:17<9:55:55,  3.63it/s]
 65%|██████▌   | 241759/371472 [8:12:18<10:25:36,  3.46it/s]
 65%|██████▌   | 241760/371472 [8:12:18<9:51:54,  3.65it/s] 
                                                           
{'loss': 2.9591, 'learning_rate': 4.144347001659161e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241760/371472 [8:12:18<9:51:54,  3.65it/s]
 65%|██████▌   | 241761/371472 [8:12:18<10:11:44,  3.53it/s]
 65%|██████▌   | 241762/371472 [8:12:18<9:56:14,  3.63it/s] 
 65%|██████▌   | 241763/371472 [8:12:19<9:43:51,  3.70it/s]
 65%|██████▌   | 241764/371472 [8:12:19<9:46:06,  3.69it/s]
 65%|██████▌   | 241765/371472 [8:12:19<9:27:39,  3.81it/s]
 65%|██████▌   | 241766/371472 [8:12:19<9:22:17,  3.84it/s]
 65%|██████▌   | 241767/371472 [8:12:20<9:38:26,  3.74it/s]
 65%|██████▌   | 241768/371472 [8:12:20<9:32:04,  3.78it/s]
 65%|██████▌   | 241769/371472 [8:12:20<9:17:18,  3.88it/s]
 65%|██████▌   | 241770/371472 [8:12:21<10:09:59,  3.54it/s]
 65%|██████▌   | 241771/371472 [8:12:21<9:55:39,  3.63it/s] 
 65%|██████▌   | 241772/371472 [8:12:21<9:35:57,  3.75it/s]
 65%|██████▌   | 241773/371472 [8:12:21<9:35:22,  3.76it/s]
 65%|██████▌   | 241774/371472 [8:12:22<9:22:16,  3.84it/s]
 65%|██████▌   | 241775/371472 [8:12:22<9:17:44,  3.88it/s]
 65%|██████▌   | 241776/371472 [8:12:22<9:01:26,  3.99it/s]
 65%|██████▌   | 241777/371472 [8:12:22<9:08:21,  3.94it/s]
 65%|██████▌   | 241778/371472 [8:12:23<9:10:28,  3.93it/s]
 65%|██████▌   | 241779/371472 [8:12:23<9:11:29,  3.92it/s]
 65%|██████▌   | 241780/371472 [8:12:23<9:07:01,  3.95it/s]
                                                           
{'loss': 3.0259, 'learning_rate': 4.1438621819043713e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241780/371472 [8:12:23<9:07:01,  3.95it/s]
 65%|██████▌   | 241781/371472 [8:12:23<10:17:53,  3.50it/s]
 65%|██████▌   | 241782/371472 [8:12:24<9:43:08,  3.71it/s] 
 65%|██████▌   | 241783/371472 [8:12:24<9:28:28,  3.80it/s]
 65%|██████▌   | 241784/371472 [8:12:24<9:16:27,  3.88it/s]
 65%|██████▌   | 241785/371472 [8:12:24<9:21:16,  3.85it/s]
 65%|██████▌   | 241786/371472 [8:12:25<9:16:16,  3.89it/s]
 65%|██████▌   | 241787/371472 [8:12:25<9:35:52,  3.75it/s]
 65%|██████▌   | 241788/371472 [8:12:25<9:28:18,  3.80it/s]
 65%|██████▌   | 241789/371472 [8:12:26<9:27:03,  3.81it/s]
 65%|██████▌   | 241790/371472 [8:12:26<9:21:29,  3.85it/s]
 65%|██████▌   | 241791/371472 [8:12:26<9:10:01,  3.93it/s]
 65%|██████▌   | 241792/371472 [8:12:26<9:43:13,  3.71it/s]
 65%|██████▌   | 241793/371472 [8:12:27<9:37:27,  3.74it/s]
 65%|██████▌   | 241794/371472 [8:12:27<10:32:25,  3.42it/s]
 65%|██████▌   | 241795/371472 [8:12:27<10:20:32,  3.48it/s]
 65%|██████▌   | 241796/371472 [8:12:27<9:48:09,  3.67it/s] 
 65%|██████▌   | 241797/371472 [8:12:28<10:41:03,  3.37it/s]
 65%|██████▌   | 241798/371472 [8:12:28<10:12:52,  3.53it/s]
 65%|██████▌   | 241799/371472 [8:12:28<9:44:33,  3.70it/s] 
 65%|██████▌   | 241800/371472 [8:12:29<9:49:30,  3.67it/s]
                                                           
{'loss': 2.8477, 'learning_rate': 4.143377362149583e-07, 'epoch': 10.41}
+
 65%|██████▌   | 241800/371472 [8:12:29<9:49:30,  3.67it/s]
 65%|██████▌   | 241801/371472 [8:12:29<9:39:50,  3.73it/s]
 65%|██████▌   | 241802/371472 [8:12:29<9:56:30,  3.62it/s]
 65%|██████▌   | 241803/371472 [8:12:29<9:36:55,  3.75it/s]
 65%|██████▌   | 241804/371472 [8:12:30<9:48:18,  3.67it/s]
 65%|██████▌   | 241805/371472 [8:12:30<10:14:51,  3.51it/s]
 65%|██████▌   | 241806/371472 [8:12:30<10:01:02,  3.60it/s]
 65%|██████▌   | 241807/371472 [8:12:31<10:21:45,  3.48it/s]
 65%|██████▌   | 241808/371472 [8:12:31<10:42:46,  3.36it/s]
 65%|██████▌   | 241809/371472 [8:12:31<10:31:40,  3.42it/s]
 65%|██████▌   | 241810/371472 [8:12:31<10:12:30,  3.53it/s]
 65%|██████▌   | 241811/371472 [8:12:32<10:08:19,  3.55it/s]
 65%|██████▌   | 241812/371472 [8:12:32<10:02:46,  3.59it/s]
 65%|██████▌   | 241813/371472 [8:12:32<10:01:53,  3.59it/s]
 65%|██████▌   | 241814/371472 [8:12:32<9:34:30,  3.76it/s] 
 65%|██████▌   | 241815/371472 [8:12:33<9:55:51,  3.63it/s]
 65%|██████▌   | 241816/371472 [8:12:33<9:52:44,  3.65it/s]
 65%|██████▌   | 241817/371472 [8:12:33<9:39:26,  3.73it/s]
 65%|██████▌   | 241818/371472 [8:12:34<9:43:01,  3.71it/s]
 65%|██████▌   | 241819/371472 [8:12:34<9:38:27,  3.74it/s]
 65%|██████▌   | 241820/371472 [8:12:34<9:33:07,  3.77it/s]
                                                           
{'loss': 2.757, 'learning_rate': 4.142892542394794e-07, 'epoch': 10.42}
+
 65%|██████▌   | 241820/371472 [8:12:34<9:33:07,  3.77it/s]
 65%|██████▌   | 241821/371472 [8:12:34<10:54:52,  3.30it/s]
 65%|██████▌   | 241822/371472 [8:12:35<11:29:17,  3.13it/s]
 65%|██████▌   | 241823/371472 [8:12:35<10:55:08,  3.30it/s]
 65%|██████▌   | 241824/371472 [8:12:35<10:19:57,  3.49it/s]
 65%|██████▌   | 241825/371472 [8:12:36<9:44:16,  3.70it/s] 
 65%|██████▌   | 241826/371472 [8:12:36<9:55:03,  3.63it/s]
 65%|██████▌   | 241827/371472 [8:12:36<9:40:18,  3.72it/s]
 65%|██████▌   | 241828/371472 [8:12:36<9:23:39,  3.83it/s]
 65%|██████▌   | 241829/371472 [8:12:37<9:22:30,  3.84it/s]
 65%|██████▌   | 241830/371472 [8:12:37<9:22:59,  3.84it/s]
 65%|██████▌   | 241831/371472 [8:12:37<9:13:43,  3.90it/s]
 65%|██████▌   | 241832/371472 [8:12:37<9:36:03,  3.75it/s]
 65%|██████▌   | 241833/371472 [8:12:38<9:53:31,  3.64it/s]
 65%|██████▌   | 241834/371472 [8:12:38<9:55:03,  3.63it/s]
 65%|██████▌   | 241835/371472 [8:12:38<9:45:57,  3.69it/s]
 65%|██████▌   | 241836/371472 [8:12:39<9:38:59,  3.73it/s]
 65%|██████▌   | 241837/371472 [8:12:39<9:56:44,  3.62it/s]
 65%|██████▌   | 241838/371472 [8:12:39<9:50:15,  3.66it/s]
 65%|██████▌   | 241839/371472 [8:12:39<10:22:56,  3.47it/s]
 65%|██████▌   | 241840/371472 [8:12:40<10:09:17,  3.55it/s]
                                                            
{'loss': 3.0161, 'learning_rate': 4.142407722640005e-07, 'epoch': 10.42}
+
 65%|██████▌   | 241840/371472 [8:12:40<10:09:17,  3.55it/s]
 65%|██████▌   | 241841/371472 [8:12:40<10:50:28,  3.32it/s]
 65%|██████▌   | 241842/371472 [8:12:40<10:28:15,  3.44it/s]
 65%|██████▌   | 241843/371472 [8:12:41<11:21:55,  3.17it/s]
 65%|██████▌   | 241844/371472 [8:12:41<11:11:59,  3.22it/s]
 65%|██████▌   | 241845/371472 [8:12:41<10:41:42,  3.37it/s]
 65%|██████▌   | 241846/371472 [8:12:42<10:46:42,  3.34it/s]
 65%|██████▌   | 241847/371472 [8:12:42<10:44:30,  3.35it/s]
 65%|██████▌   | 241848/371472 [8:12:42<10:12:10,  3.53it/s]
 65%|██████▌   | 241849/371472 [8:12:42<10:06:44,  3.56it/s]
 65%|██████▌   | 241850/371472 [8:12:43<9:50:59,  3.66it/s] 
 65%|██████▌   | 241851/371472 [8:12:43<9:41:42,  3.71it/s]
 65%|██████▌   | 241852/371472 [8:12:43<9:37:55,  3.74it/s]
 65%|██████▌   | 241853/371472 [8:12:43<9:34:50,  3.76it/s]
 65%|██████▌   | 241854/371472 [8:12:44<9:08:52,  3.94it/s]
 65%|██████▌   | 241855/371472 [8:12:44<9:27:08,  3.81it/s]
 65%|██████▌   | 241856/371472 [8:12:44<9:09:53,  3.93it/s]
 65%|██████▌   | 241857/371472 [8:12:44<9:11:43,  3.92it/s]
 65%|██████▌   | 241858/371472 [8:12:45<9:16:39,  3.88it/s]
 65%|██████▌   | 241859/371472 [8:12:45<9:30:53,  3.78it/s]
 65%|██████▌   | 241860/371472 [8:12:45<10:18:15,  3.49it/s]
                                                            
{'loss': 2.9097, 'learning_rate': 4.141922902885216e-07, 'epoch': 10.42}
+
 65%|██████▌   | 241860/371472 [8:12:45<10:18:15,  3.49it/s]
 65%|██████▌   | 241861/371472 [8:12:46<11:41:52,  3.08it/s]
 65%|██████▌   | 241862/371472 [8:12:46<10:50:02,  3.32it/s]
 65%|██████▌   | 241863/371472 [8:12:46<10:12:12,  3.53it/s]
 65%|██████▌   | 241864/371472 [8:12:46<10:27:36,  3.44it/s]
 65%|██████▌   | 241865/371472 [8:12:47<9:57:47,  3.61it/s] 
 65%|██████▌   | 241866/371472 [8:12:47<10:03:12,  3.58it/s]
 65%|██████▌   | 241867/371472 [8:12:47<9:49:17,  3.67it/s] 
 65%|██████▌   | 241868/371472 [8:12:48<10:06:41,  3.56it/s]
 65%|██████▌   | 241869/371472 [8:12:48<10:22:36,  3.47it/s]
 65%|██████▌   | 241870/371472 [8:12:48<10:15:15,  3.51it/s]
 65%|██████▌   | 241871/371472 [8:12:48<9:48:18,  3.67it/s] 
 65%|██████▌   | 241872/371472 [8:12:49<9:30:10,  3.79it/s]
 65%|██████▌   | 241873/371472 [8:12:49<9:20:09,  3.86it/s]
 65%|██████▌   | 241874/371472 [8:12:49<9:42:02,  3.71it/s]
 65%|██████▌   | 241875/371472 [8:12:49<9:23:46,  3.83it/s]
 65%|██████▌   | 241876/371472 [8:12:50<9:44:06,  3.70it/s]
 65%|██████▌   | 241877/371472 [8:12:50<9:35:13,  3.75it/s]
 65%|██████▌   | 241878/371472 [8:12:50<9:23:22,  3.83it/s]
 65%|██████▌   | 241879/371472 [8:12:50<9:20:42,  3.85it/s]
 65%|██████▌   | 241880/371472 [8:12:51<9:17:57,  3.87it/s]
                                                           
{'loss': 2.9386, 'learning_rate': 4.1414380831304275e-07, 'epoch': 10.42}
+
 65%|██████▌   | 241880/371472 [8:12:51<9:17:57,  3.87it/s]
 65%|██████▌   | 241881/371472 [8:12:51<10:02:53,  3.58it/s]
 65%|██████▌   | 241882/371472 [8:12:51<9:37:02,  3.74it/s] 
 65%|██████▌   | 241883/371472 [8:12:52<9:34:36,  3.76it/s]
 65%|██████▌   | 241884/371472 [8:12:52<9:33:11,  3.77it/s]
 65%|██████▌   | 241885/371472 [8:12:52<9:51:50,  3.65it/s]
 65%|██████▌   | 241886/371472 [8:12:52<9:33:39,  3.76it/s]
 65%|██████▌   | 241887/371472 [8:12:53<9:30:08,  3.79it/s]
 65%|██████▌   | 241888/371472 [8:12:53<9:48:39,  3.67it/s]
 65%|██████▌   | 241889/371472 [8:12:53<10:04:16,  3.57it/s]
 65%|██████▌   | 241890/371472 [8:12:53<10:01:41,  3.59it/s]
 65%|██████▌   | 241891/371472 [8:12:54<10:09:22,  3.54it/s]
 65%|██████▌   | 241892/371472 [8:12:54<10:29:08,  3.43it/s]
 65%|██████▌   | 241893/371472 [8:12:54<10:15:57,  3.51it/s]
 65%|██████▌   | 241894/371472 [8:12:55<9:43:52,  3.70it/s] 
 65%|██████▌   | 241895/371472 [8:12:55<9:32:45,  3.77it/s]
 65%|██████▌   | 241896/371472 [8:12:55<9:26:59,  3.81it/s]
 65%|██████▌   | 241897/371472 [8:12:55<9:13:22,  3.90it/s]
 65%|██████▌   | 241898/371472 [8:12:56<9:31:31,  3.78it/s]
 65%|██████▌   | 241899/371472 [8:12:56<10:19:05,  3.49it/s]
 65%|██████▌   | 241900/371472 [8:12:56<10:39:17,  3.38it/s]
                                                            
{'loss': 2.813, 'learning_rate': 4.1409532633756377e-07, 'epoch': 10.42}
+
 65%|██████▌   | 241900/371472 [8:12:56<10:39:17,  3.38it/s]
 65%|██████▌   | 241901/371472 [8:12:57<10:31:28,  3.42it/s]
 65%|██████▌   | 241902/371472 [8:12:57<10:45:36,  3.34it/s]
 65%|██████▌   | 241903/371472 [8:12:57<11:32:56,  3.12it/s]
 65%|██████▌   | 241904/371472 [8:12:58<10:52:02,  3.31it/s]
 65%|██████▌   | 241905/371472 [8:12:58<10:37:59,  3.38it/s]
 65%|██████▌   | 241906/371472 [8:12:58<10:42:34,  3.36it/s]
 65%|██████▌   | 241907/371472 [8:12:58<10:32:28,  3.41it/s]
 65%|██████▌   | 241908/371472 [8:12:59<10:32:27,  3.41it/s]
 65%|██████▌   | 241909/371472 [8:12:59<10:08:35,  3.55it/s]
 65%|██████▌   | 241910/371472 [8:12:59<10:01:48,  3.59it/s]
 65%|██████▌   | 241911/371472 [8:12:59<9:44:54,  3.69it/s] 
 65%|██████▌   | 241912/371472 [8:13:00<9:35:49,  3.75it/s]
 65%|██████▌   | 241913/371472 [8:13:00<10:04:09,  3.57it/s]
 65%|██████▌   | 241914/371472 [8:13:00<10:01:22,  3.59it/s]
 65%|██████▌   | 241915/371472 [8:13:01<9:48:19,  3.67it/s] 
 65%|██████▌   | 241916/371472 [8:13:01<9:47:49,  3.67it/s]
 65%|██████▌   | 241917/371472 [8:13:01<9:37:34,  3.74it/s]
 65%|██████▌   | 241918/371472 [8:13:01<9:40:19,  3.72it/s]
 65%|██████▌   | 241919/371472 [8:13:02<10:07:59,  3.55it/s]
 65%|██████▌   | 241920/371472 [8:13:02<10:09:51,  3.54it/s]
                                                            
{'loss': 2.9615, 'learning_rate': 4.140468443620849e-07, 'epoch': 10.42}
+
 65%|██████▌   | 241920/371472 [8:13:02<10:09:51,  3.54it/s]
 65%|██████▌   | 241921/371472 [8:13:02<9:46:40,  3.68it/s] 
 65%|██████▌   | 241922/371472 [8:13:02<9:23:05,  3.83it/s]
 65%|██████▌   | 241923/371472 [8:13:03<9:22:50,  3.84it/s]
 65%|██████▌   | 241924/371472 [8:13:03<9:32:09,  3.77it/s]
 65%|██████▌   | 241925/371472 [8:13:03<10:02:57,  3.58it/s]
 65%|██████▌   | 241926/371472 [8:13:04<9:59:29,  3.60it/s] 
 65%|██████▌   | 241927/371472 [8:13:04<10:09:47,  3.54it/s]
 65%|██████▌   | 241928/371472 [8:13:04<10:28:24,  3.44it/s]
 65%|██████▌   | 241929/371472 [8:13:04<10:23:30,  3.46it/s]
 65%|██████▌   | 241930/371472 [8:13:05<11:16:54,  3.19it/s]
 65%|██████▌   | 241931/371472 [8:13:05<11:56:42,  3.01it/s]
 65%|██████▌   | 241932/371472 [8:13:05<11:16:31,  3.19it/s]
 65%|██████▌   | 241933/371472 [8:13:06<11:14:16,  3.20it/s]
 65%|██████▌   | 241934/371472 [8:13:06<10:55:09,  3.30it/s]
 65%|██████▌   | 241935/371472 [8:13:06<10:19:48,  3.48it/s]
 65%|██████▌   | 241936/371472 [8:13:07<10:39:47,  3.37it/s]
 65%|██████▌   | 241937/371472 [8:13:07<10:26:07,  3.45it/s]
 65%|██████��   | 241938/371472 [8:13:07<10:12:48,  3.52it/s]
 65%|██████▌   | 241939/371472 [8:13:08<10:57:17,  3.28it/s]
 65%|██████▌   | 241940/371472 [8:13:08<10:22:56,  3.47it/s]
                                                            
{'loss': 2.7823, 'learning_rate': 4.13998362386606e-07, 'epoch': 10.42}
+
 65%|██████▌   | 241940/371472 [8:13:08<10:22:56,  3.47it/s]
 65%|██████▌   | 241941/371472 [8:13:08<9:59:10,  3.60it/s] 
 65%|██████▌   | 241942/371472 [8:13:08<10:19:31,  3.48it/s]
 65%|██████▌   | 241943/371472 [8:13:09<10:30:03,  3.43it/s]
 65%|██████▌   | 241944/371472 [8:13:09<10:31:36,  3.42it/s]
 65%|██████▌   | 241945/371472 [8:13:09<10:15:46,  3.51it/s]
 65%|██████▌   | 241946/371472 [8:13:10<11:44:04,  3.07it/s]
 65%|██████▌   | 241947/371472 [8:13:10<10:54:13,  3.30it/s]
 65%|██████▌   | 241948/371472 [8:13:10<10:28:19,  3.44it/s]
 65%|██████▌   | 241949/371472 [8:13:10<9:53:28,  3.64it/s] 
 65%|██████▌   | 241950/371472 [8:13:11<9:37:21,  3.74it/s]
 65%|██████▌   | 241951/371472 [8:13:11<9:56:20,  3.62it/s]
 65%|██████▌   | 241952/371472 [8:13:11<9:35:06,  3.75it/s]
 65%|██████▌   | 241953/371472 [8:13:11<9:24:17,  3.83it/s]
 65%|██████▌   | 241954/371472 [8:13:12<9:34:39,  3.76it/s]
 65%|██████▌   | 241955/371472 [8:13:12<10:00:34,  3.59it/s]
 65%|██████▌   | 241956/371472 [8:13:12<9:35:01,  3.75it/s] 
 65%|██████▌   | 241957/371472 [8:13:12<9:28:54,  3.79it/s]
 65%|██████▌   | 241958/371472 [8:13:13<9:55:45,  3.62it/s]
 65%|██████▌   | 241959/371472 [8:13:13<9:31:48,  3.77it/s]
 65%|██████▌   | 241960/371472 [8:13:13<9:33:32,  3.76it/s]
                                                           
{'loss': 3.1021, 'learning_rate': 4.1394988041112715e-07, 'epoch': 10.42}
+
 65%|██████▌   | 241960/371472 [8:13:13<9:33:32,  3.76it/s]
 65%|██████▌   | 241961/371472 [8:13:14<9:19:01,  3.86it/s]
 65%|██████▌   | 241962/371472 [8:13:14<9:12:32,  3.91it/s]
 65%|██████▌   | 241963/371472 [8:13:14<9:13:00,  3.90it/s]
 65%|██████▌   | 241964/371472 [8:13:14<10:06:34,  3.56it/s]
 65%|██████▌   | 241965/371472 [8:13:15<9:57:26,  3.61it/s] 
 65%|██████▌   | 241966/371472 [8:13:15<10:08:59,  3.54it/s]
 65%|██████▌   | 241967/371472 [8:13:15<10:01:40,  3.59it/s]
 65%|██████▌   | 241968/371472 [8:13:16<11:33:35,  3.11it/s]
 65%|██████▌   | 241969/371472 [8:13:16<11:16:53,  3.19it/s]
 65%|██████▌   | 241970/371472 [8:13:16<10:33:28,  3.41it/s]
 65%|██████▌   | 241971/371472 [8:13:16<9:54:02,  3.63it/s] 
 65%|██████▌   | 241972/371472 [8:13:17<9:45:03,  3.69it/s]
 65%|██████▌   | 241973/371472 [8:13:17<9:49:21,  3.66it/s]
 65%|██████▌   | 241974/371472 [8:13:17<9:40:06,  3.72it/s]
 65%|██████▌   | 241975/371472 [8:13:17<9:57:10,  3.61it/s]
 65%|██████▌   | 241976/371472 [8:13:18<9:53:23,  3.64it/s]
 65%|██████▌   | 241977/371472 [8:13:18<10:06:23,  3.56it/s]
 65%|██████▌   | 241978/371472 [8:13:18<10:30:14,  3.42it/s]
 65%|██████▌   | 241979/371472 [8:13:19<10:18:02,  3.49it/s]
 65%|██████▌   | 241980/371472 [8:13:19<10:13:37,  3.52it/s]
                                                            
{'loss': 2.7084, 'learning_rate': 4.139013984356482e-07, 'epoch': 10.42}
+
 65%|██████▌   | 241980/371472 [8:13:19<10:13:37,  3.52it/s]
 65%|██████▌   | 241981/371472 [8:13:19<10:11:39,  3.53it/s]
 65%|██████▌   | 241982/371472 [8:13:19<10:11:47,  3.53it/s]
 65%|██████▌   | 241983/371472 [8:13:20<9:42:44,  3.70it/s] 
 65%|██████▌   | 241984/371472 [8:13:20<9:25:36,  3.82it/s]
 65%|██████▌   | 241985/371472 [8:13:20<10:07:07,  3.55it/s]
 65%|██████▌   | 241986/371472 [8:13:21<10:33:31,  3.41it/s]
 65%|██████▌   | 241987/371472 [8:13:21<10:32:12,  3.41it/s]
 65%|██████▌   | 241988/371472 [8:13:21<10:18:21,  3.49it/s]
 65%|██████▌   | 241989/371472 [8:13:21<10:10:50,  3.53it/s]
 65%|██████▌   | 241990/371472 [8:13:22<10:20:26,  3.48it/s]
 65%|██████▌   | 241991/371472 [8:13:22<9:43:42,  3.70it/s] 
 65%|██████▌   | 241992/371472 [8:13:22<10:00:53,  3.59it/s]
 65%|██████▌   | 241993/371472 [8:13:23<9:47:25,  3.67it/s] 
 65%|██████▌   | 241994/371472 [8:13:23<10:32:06,  3.41it/s]
 65%|██████▌   | 241995/371472 [8:13:23<10:43:51,  3.35it/s]
 65%|██████▌   | 241996/371472 [8:13:24<11:17:27,  3.19it/s]
 65%|██████▌   | 241997/371472 [8:13:24<10:46:21,  3.34it/s]
 65%|██████▌   | 241998/371472 [8:13:24<10:26:01,  3.45it/s]
 65%|██████▌   | 241999/371472 [8:13:24<10:04:41,  3.57it/s]
 65%|██████▌   | 242000/371472 [8:13:25<9:37:08,  3.74it/s] 
                                                           
{'loss': 2.8578, 'learning_rate': 4.138529164601694e-07, 'epoch': 10.42}
+
 65%|██████▌   | 242000/371472 [8:13:25<9:37:08,  3.74it/s]
 65%|██████▌   | 242001/371472 [8:13:25<10:03:53,  3.57it/s]
 65%|██████▌   | 242002/371472 [8:13:25<10:02:02,  3.58it/s]
 65%|██████▌   | 242003/371472 [8:13:25<10:23:27,  3.46it/s]
 65%|██████▌   | 242004/371472 [8:13:26<11:17:27,  3.19it/s]
 65%|██████▌   | 242005/371472 [8:13:26<11:21:17,  3.17it/s]
 65%|██████▌   | 242006/371472 [8:13:26<10:45:41,  3.34it/s]
 65%|██████▌   | 242007/371472 [8:13:27<10:19:47,  3.48it/s]
 65%|██████▌   | 242008/371472 [8:13:27<10:46:15,  3.34it/s]
 65%|██████▌   | 242009/371472 [8:13:27<10:26:44,  3.44it/s]
 65%|██████▌   | 242010/371472 [8:13:28<10:18:04,  3.49it/s]
 65%|██████▌   | 242011/371472 [8:13:28<10:01:52,  3.58it/s]
 65%|██████▌   | 242012/371472 [8:13:28<9:53:31,  3.64it/s] 
 65%|██████▌   | 242013/371472 [8:13:28<10:45:45,  3.34it/s]
 65%|██████▌   | 242014/371472 [8:13:29<10:04:39,  3.57it/s]
 65%|██████▌   | 242015/371472 [8:13:29<9:48:46,  3.66it/s] 
 65%|██████▌   | 242016/371472 [8:13:29<10:14:49,  3.51it/s]
 65%|██████▌   | 242017/371472 [8:13:30<10:29:40,  3.43it/s]
 65%|██████▌   | 242018/371472 [8:13:30<10:19:34,  3.48it/s]
 65%|██████▌   | 242019/371472 [8:13:30<10:21:59,  3.47it/s]
 65%|██████▌   | 242020/371472 [8:13:30<9:55:19,  3.62it/s] 
                                                           
{'loss': 2.7607, 'learning_rate': 4.1380443448469047e-07, 'epoch': 10.42}
+
 65%|██████▌   | 242020/371472 [8:13:30<9:55:19,  3.62it/s]
 65%|██████▌   | 242021/371472 [8:13:31<9:23:19,  3.83it/s]
 65%|██████▌   | 242022/371472 [8:13:31<9:15:44,  3.88it/s]
 65%|██████▌   | 242023/371472 [8:13:31<9:46:24,  3.68it/s]
 65%|██████▌   | 242024/371472 [8:13:31<9:33:40,  3.76it/s]
 65%|██████▌   | 242025/371472 [8:13:32<9:21:18,  3.84it/s]
 65%|██████▌   | 242026/371472 [8:13:32<9:15:10,  3.89it/s]
 65%|██████▌   | 242027/371472 [8:13:32<10:13:58,  3.51it/s]
 65%|██████▌   | 242028/371472 [8:13:33<10:15:09,  3.51it/s]
 65%|██████▌   | 242029/371472 [8:13:33<9:53:10,  3.64it/s] 
 65%|██████▌   | 242030/371472 [8:13:33<9:56:50,  3.61it/s]
 65%|██████▌   | 242031/371472 [8:13:33<9:49:06,  3.66it/s]
 65%|██████▌   | 242032/371472 [8:13:34<9:37:54,  3.73it/s]
 65%|██████▌   | 242033/371472 [8:13:34<9:32:16,  3.77it/s]
 65%|██████▌   | 242034/371472 [8:13:34<11:21:16,  3.17it/s]
 65%|██████▌   | 242035/371472 [8:13:35<11:43:01,  3.07it/s]
 65%|██████▌   | 242036/371472 [8:13:35<10:40:08,  3.37it/s]
 65%|██████▌   | 242037/371472 [8:13:35<10:17:35,  3.49it/s]
 65%|██████▌   | 242038/371472 [8:13:35<10:24:00,  3.46it/s]
 65%|██████▌   | 242039/371472 [8:13:36<10:51:46,  3.31it/s]
 65%|██████▌   | 242040/371472 [8:13:36<10:53:50,  3.30it/s]
                                                            
{'loss': 2.9652, 'learning_rate': 4.137559525092116e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242040/371472 [8:13:36<10:53:50,  3.30it/s]
 65%|██████▌   | 242041/371472 [8:13:36<10:39:52,  3.37it/s]
 65%|██████▌   | 242042/371472 [8:13:37<10:00:18,  3.59it/s]
 65%|██████▌   | 242043/371472 [8:13:37<9:56:31,  3.62it/s] 
 65%|██████▌   | 242044/371472 [8:13:37<9:34:27,  3.76it/s]
 65%|██████▌   | 242045/371472 [8:13:37<9:17:18,  3.87it/s]
 65%|██████▌   | 242046/371472 [8:13:38<9:11:38,  3.91it/s]
 65%|██████▌   | 242047/371472 [8:13:38<9:36:09,  3.74it/s]
 65%|██████▌   | 242048/371472 [8:13:38<10:17:11,  3.49it/s]
 65%|██████▌   | 242049/371472 [8:13:39<10:24:01,  3.46it/s]
 65%|██████▌   | 242050/371472 [8:13:39<10:11:37,  3.53it/s]
 65%|██████▌   | 242051/371472 [8:13:39<10:03:13,  3.58it/s]
 65%|██████▌   | 242052/371472 [8:13:39<9:39:34,  3.72it/s] 
 65%|██████▌   | 242053/371472 [8:13:40<9:20:01,  3.85it/s]
 65%|██████▌   | 242054/371472 [8:13:40<9:34:45,  3.75it/s]
 65%|██████▌   | 242055/371472 [8:13:40<9:21:18,  3.84it/s]
 65%|██████▌   | 242056/371472 [8:13:40<9:24:48,  3.82it/s]
 65%|██████▌   | 242057/371472 [8:13:41<9:15:36,  3.88it/s]
 65%|██████▌   | 242058/371472 [8:13:41<9:34:07,  3.76it/s]
 65%|██████▌   | 242059/371472 [8:13:41<9:30:54,  3.78it/s]
 65%|██████▌   | 242060/371472 [8:13:41<9:28:49,  3.79it/s]
                                                           
{'loss': 2.9762, 'learning_rate': 4.1370747053373266e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242060/371472 [8:13:41<9:28:49,  3.79it/s]
 65%|██████▌   | 242061/371472 [8:13:42<9:29:18,  3.79it/s]
 65%|██████▌   | 242062/371472 [8:13:42<9:21:35,  3.84it/s]
 65%|██████▌   | 242063/371472 [8:13:42<9:29:47,  3.79it/s]
 65%|██████▌   | 242064/371472 [8:13:42<9:51:53,  3.64it/s]
 65%|██████▌   | 242065/371472 [8:13:43<9:50:49,  3.65it/s]
 65%|██████▌   | 242066/371472 [8:13:43<9:48:51,  3.66it/s]
 65%|██████▌   | 242067/371472 [8:13:43<9:47:17,  3.67it/s]
 65%|██████▌   | 242068/371472 [8:13:44<9:36:17,  3.74it/s]
 65%|██████▌   | 242069/371472 [8:13:44<9:23:57,  3.82it/s]
 65%|██████▌   | 242070/371472 [8:13:44<9:09:05,  3.93it/s]
 65%|██████▌   | 242071/371472 [8:13:44<9:03:10,  3.97it/s]
 65%|██████▌   | 242072/371472 [8:13:45<9:13:32,  3.90it/s]
 65%|██████▌   | 242073/371472 [8:13:45<10:21:10,  3.47it/s]
 65%|██████▌   | 242074/371472 [8:13:45<10:13:30,  3.52it/s]
 65%|██████▌   | 242075/371472 [8:13:45<10:26:22,  3.44it/s]
 65%|██████▌   | 242076/371472 [8:13:46<10:06:18,  3.56it/s]
 65%|██████▌   | 242077/371472 [8:13:46<9:47:57,  3.67it/s] 
 65%|██████▌   | 242078/371472 [8:13:46<9:53:05,  3.64it/s]
 65%|██████▌   | 242079/371472 [8:13:47<9:48:29,  3.66it/s]
 65%|██████▌   | 242080/371472 [8:13:47<9:50:37,  3.65it/s]
                                                           
{'loss': 2.7743, 'learning_rate': 4.136589885582537e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242080/371472 [8:13:47<9:50:37,  3.65it/s]
 65%|██████▌   | 242081/371472 [8:13:47<9:43:29,  3.70it/s]
 65%|██████▌   | 242082/371472 [8:13:47<9:53:09,  3.64it/s]
 65%|██████▌   | 242083/371472 [8:13:48<9:48:00,  3.67it/s]
 65%|██████▌   | 242084/371472 [8:13:48<9:38:43,  3.73it/s]
 65%|██████▌   | 242085/371472 [8:13:48<9:44:53,  3.69it/s]
 65%|██████▌   | 242086/371472 [8:13:48<9:26:57,  3.80it/s]
 65%|██████▌   | 242087/371472 [8:13:49<9:25:10,  3.82it/s]
 65%|██████▌   | 242088/371472 [8:13:49<9:35:00,  3.75it/s]
 65%|██████▌   | 242089/371472 [8:13:49<9:27:29,  3.80it/s]
 65%|██████▌   | 242090/371472 [8:13:49<9:34:10,  3.76it/s]
 65%|██████▌   | 242091/371472 [8:13:50<9:31:32,  3.77it/s]
 65%|██████▌   | 242092/371472 [8:13:50<9:32:15,  3.77it/s]
 65%|██████▌   | 242093/371472 [8:13:50<9:23:26,  3.83it/s]
 65%|██████▌   | 242094/371472 [8:13:51<9:14:57,  3.89it/s]
 65%|██████▌   | 242095/371472 [8:13:51<9:08:37,  3.93it/s]
 65%|██████▌   | 242096/371472 [8:13:51<9:28:01,  3.80it/s]
 65%|██████▌   | 242097/371472 [8:13:51<9:29:23,  3.79it/s]
 65%|██████▌   | 242098/371472 [8:13:52<9:44:10,  3.69it/s]
 65%|██████▌   | 242099/371472 [8:13:52<9:28:38,  3.79it/s]
 65%|██████▌   | 242100/371472 [8:13:52<9:28:30,  3.79it/s]
                                                           
{'loss': 2.8297, 'learning_rate': 4.1361050658277486e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242100/371472 [8:13:52<9:28:30,  3.79it/s]
 65%|██████▌   | 242101/371472 [8:13:52<9:29:35,  3.79it/s]
 65%|██████▌   | 242102/371472 [8:13:53<10:17:45,  3.49it/s]
 65%|██████▌   | 242103/371472 [8:13:53<9:45:52,  3.68it/s] 
 65%|██████▌   | 242104/371472 [8:13:53<9:27:43,  3.80it/s]
 65%|██████▌   | 242105/371472 [8:13:53<9:14:49,  3.89it/s]
 65%|██████▌   | 242106/371472 [8:13:54<9:29:32,  3.79it/s]
 65%|██████▌   | 242107/371472 [8:13:54<9:15:20,  3.88it/s]
 65%|██████▌   | 242108/371472 [8:13:54<10:02:26,  3.58it/s]
 65%|██████▌   | 242109/371472 [8:13:55<10:03:50,  3.57it/s]
 65%|██████▌   | 242110/371472 [8:13:55<10:16:05,  3.50it/s]
 65%|██████▌   | 242111/371472 [8:13:55<10:21:29,  3.47it/s]
 65%|██████▌   | 242112/371472 [8:13:55<10:03:40,  3.57it/s]
 65%|██████▌   | 242113/371472 [8:13:56<9:41:14,  3.71it/s] 
 65%|██████▌   | 242114/371472 [8:13:56<11:52:06,  3.03it/s]
 65%|██████▌   | 242115/371472 [8:13:56<11:03:29,  3.25it/s]
 65%|██████▌   | 242116/371472 [8:13:57<10:28:12,  3.43it/s]
 65%|██████▌   | 242117/371472 [8:13:57<10:21:07,  3.47it/s]
 65%|██████▌   | 242118/371472 [8:13:57<10:45:59,  3.34it/s]
 65%|██████▌   | 242119/371472 [8:13:58<10:32:03,  3.41it/s]
 65%|██████▌   | 242120/371472 [8:13:58<10:00:57,  3.59it/s]
                                                            
{'loss': 3.0978, 'learning_rate': 4.1356202460729593e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242120/371472 [8:13:58<10:00:57,  3.59it/s]
 65%|██████▌   | 242121/371472 [8:13:58<10:21:01,  3.47it/s]
 65%|██████▌   | 242122/371472 [8:13:58<10:16:02,  3.50it/s]
 65%|██████▌   | 242123/371472 [8:13:59<10:09:49,  3.54it/s]
 65%|██████▌   | 242124/371472 [8:13:59<9:35:30,  3.75it/s] 
 65%|██████▌   | 242125/371472 [8:13:59<9:53:11,  3.63it/s]
 65%|██████▌   | 242126/371472 [8:13:59<10:30:48,  3.42it/s]
 65%|██████▌   | 242127/371472 [8:14:00<9:54:44,  3.62it/s] 
 65%|██████▌   | 242128/371472 [8:14:00<9:50:37,  3.65it/s]
 65%|██████▌   | 242129/371472 [8:14:00<10:52:22,  3.30it/s]
 65%|██████▌   | 242130/371472 [8:14:01<10:12:38,  3.52it/s]
 65%|██████▌   | 242131/371472 [8:14:01<10:56:00,  3.29it/s]
 65%|██████▌   | 242132/371472 [8:14:01<10:54:16,  3.29it/s]
 65%|██████▌   | 242133/371472 [8:14:02<11:30:32,  3.12it/s]
 65%|██████▌   | 242134/371472 [8:14:02<10:53:05,  3.30it/s]
 65%|██████▌   | 242135/371472 [8:14:02<10:21:53,  3.47it/s]
 65%|██████▌   | 242136/371472 [8:14:03<11:55:24,  3.01it/s]
 65%|██████▌   | 242137/371472 [8:14:03<11:06:08,  3.24it/s]
 65%|██████▌   | 242138/371472 [8:14:03<11:05:23,  3.24it/s]
 65%|██████▌   | 242139/371472 [8:14:03<11:01:13,  3.26it/s]
 65%|██████▌   | 242140/371472 [8:14:04<10:31:01,  3.42it/s]
                                                            
{'loss': 2.9973, 'learning_rate': 4.135135426318171e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242140/371472 [8:14:04<10:31:01,  3.42it/s]
 65%|██████▌   | 242141/371472 [8:14:04<10:21:02,  3.47it/s]
 65%|██████▌   | 242142/371472 [8:14:04<9:58:27,  3.60it/s] 
 65%|██████▌   | 242143/371472 [8:14:04<9:33:51,  3.76it/s]
 65%|██████▌   | 242144/371472 [8:14:05<9:39:50,  3.72it/s]
 65%|██████▌   | 242145/371472 [8:14:05<9:34:22,  3.75it/s]
 65%|██████▌   | 242146/371472 [8:14:05<9:32:47,  3.76it/s]
 65%|██████▌   | 242147/371472 [8:14:06<10:09:29,  3.54it/s]
 65%|██████▌   | 242148/371472 [8:14:06<10:26:53,  3.44it/s]
 65%|██████▌   | 242149/371472 [8:14:06<10:04:07,  3.57it/s]
 65%|██████▌   | 242150/371472 [8:14:06<10:12:01,  3.52it/s]
 65%|██████▌   | 242151/371472 [8:14:07<10:38:23,  3.38it/s]
 65%|██████▌   | 242152/371472 [8:14:07<12:26:09,  2.89it/s]
 65%|██████▌   | 242153/371472 [8:14:08<12:18:24,  2.92it/s]
 65%|██████▌   | 242154/371472 [8:14:08<12:08:48,  2.96it/s]
 65%|██████▌   | 242155/371472 [8:14:08<11:53:27,  3.02it/s]
 65%|██████▌   | 242156/371472 [8:14:09<11:28:01,  3.13it/s]
 65%|██████▌   | 242157/371472 [8:14:09<11:06:27,  3.23it/s]
 65%|██████▌   | 242158/371472 [8:14:09<10:56:57,  3.28it/s]
 65%|██████▌   | 242159/371472 [8:14:09<10:13:42,  3.51it/s]
 65%|██████▌   | 242160/371472 [8:14:10<10:19:22,  3.48it/s]
                                                            
{'loss': 2.7198, 'learning_rate': 4.134650606563381e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242160/371472 [8:14:10<10:19:22,  3.48it/s]
 65%|██████▌   | 242161/371472 [8:14:10<9:42:29,  3.70it/s] 
 65%|██████▌   | 242162/371472 [8:14:10<10:01:41,  3.58it/s]
 65%|██████▌   | 242163/371472 [8:14:10<9:51:26,  3.64it/s] 
 65%|██████▌   | 242164/371472 [8:14:11<9:55:46,  3.62it/s]
 65%|██████▌   | 242165/371472 [8:14:11<9:32:26,  3.76it/s]
 65%|██████▌   | 242166/371472 [8:14:11<9:24:20,  3.82it/s]
 65%|██████▌   | 242167/371472 [8:14:11<9:57:45,  3.61it/s]
 65%|██████▌   | 242168/371472 [8:14:12<9:56:32,  3.61it/s]
 65%|██████▌   | 242169/371472 [8:14:12<9:39:45,  3.72it/s]
 65%|██████▌   | 242170/371472 [8:14:12<9:20:03,  3.85it/s]
 65%|██████▌   | 242171/371472 [8:14:13<9:30:52,  3.77it/s]
 65%|██████▌   | 242172/371472 [8:14:13<9:40:01,  3.72it/s]
 65%|██████▌   | 242173/371472 [8:14:13<9:28:31,  3.79it/s]
 65%|██████▌   | 242174/371472 [8:14:13<9:55:11,  3.62it/s]
 65%|██████▌   | 242175/371472 [8:14:14<10:31:35,  3.41it/s]
 65%|██████▌   | 242176/371472 [8:14:14<10:31:49,  3.41it/s]
 65%|██████▌   | 242177/371472 [8:14:14<10:03:22,  3.57it/s]
 65%|██████▌   | 242178/371472 [8:14:15<10:05:22,  3.56it/s]
 65%|██████▌   | 242179/371472 [8:14:15<10:19:18,  3.48it/s]
 65%|██████▌   | 242180/371472 [8:14:15<10:00:55,  3.59it/s]
                                                            
{'loss': 2.8513, 'learning_rate': 4.134165786808593e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242180/371472 [8:14:15<10:00:55,  3.59it/s]
 65%|██████▌   | 242181/371472 [8:14:15<10:11:27,  3.52it/s]
 65%|██████▌   | 242182/371472 [8:14:16<10:07:38,  3.55it/s]
 65%|██████▌   | 242183/371472 [8:14:16<10:05:45,  3.56it/s]
 65%|██████▌   | 242184/371472 [8:14:16<10:16:16,  3.50it/s]
 65%|██████▌   | 242185/371472 [8:14:17<10:26:27,  3.44it/s]
 65%|██████▌   | 242186/371472 [8:14:17<11:17:29,  3.18it/s]
 65%|██████▌   | 242187/371472 [8:14:17<10:41:29,  3.36it/s]
 65%|██████▌   | 242188/371472 [8:14:17<10:47:40,  3.33it/s]
 65%|██████▌   | 242189/371472 [8:14:18<10:18:58,  3.48it/s]
 65%|██████▌   | 242190/371472 [8:14:18<10:43:53,  3.35it/s]
 65%|██████▌   | 242191/371472 [8:14:18<10:51:56,  3.31it/s]
 65%|██████▌   | 242192/371472 [8:14:19<10:41:18,  3.36it/s]
 65%|██████▌   | 242193/371472 [8:14:19<10:13:38,  3.51it/s]
 65%|██████▌   | 242194/371472 [8:14:19<9:56:21,  3.61it/s] 
 65%|██████▌   | 242195/371472 [8:14:20<11:44:35,  3.06it/s]
 65%|██████▌   | 242196/371472 [8:14:20<11:11:59,  3.21it/s]
 65%|██████▌   | 242197/371472 [8:14:20<10:39:11,  3.37it/s]
 65%|██████▌   | 242198/371472 [8:14:20<10:19:59,  3.48it/s]
 65%|██████▌   | 242199/371472 [8:14:21<9:48:16,  3.66it/s] 
 65%|██████▌   | 242200/371472 [8:14:21<9:52:44,  3.63it/s]
                                                           
{'loss': 2.6429, 'learning_rate': 4.133680967053804e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242200/371472 [8:14:21<9:52:44,  3.63it/s]
 65%|██████▌   | 242201/371472 [8:14:21<10:01:56,  3.58it/s]
 65%|██████▌   | 242202/371472 [8:14:21<9:45:23,  3.68it/s] 
 65%|██████▌   | 242203/371472 [8:14:22<9:52:33,  3.64it/s]
 65%|██████▌   | 242204/371472 [8:14:22<9:53:53,  3.63it/s]
 65%|██████▌   | 242205/371472 [8:14:22<9:38:00,  3.73it/s]
 65%|██████▌   | 242206/371472 [8:14:23<9:52:35,  3.64it/s]
 65%|██████▌   | 242207/371472 [8:14:23<10:07:17,  3.55it/s]
 65%|██████▌   | 242208/371472 [8:14:23<10:15:12,  3.50it/s]
 65%|██████▌   | 242209/371472 [8:14:23<10:01:48,  3.58it/s]
 65%|██████▌   | 242210/371472 [8:14:24<9:36:44,  3.74it/s] 
 65%|██████▌   | 242211/371472 [8:14:24<10:04:29,  3.56it/s]
 65%|██████▌   | 242212/371472 [8:14:24<9:32:55,  3.76it/s] 
 65%|██████▌   | 242213/371472 [8:14:24<9:16:23,  3.87it/s]
 65%|██████▌   | 242214/371472 [8:14:25<9:16:05,  3.87it/s]
 65%|██████▌   | 242215/371472 [8:14:25<9:15:28,  3.88it/s]
 65%|██████▌   | 242216/371472 [8:14:25<9:58:55,  3.60it/s]
 65%|██████▌   | 242217/371472 [8:14:26<9:37:32,  3.73it/s]
 65%|██████▌   | 242218/371472 [8:14:26<9:20:34,  3.84it/s]
 65%|██████▌   | 242219/371472 [8:14:26<9:41:32,  3.70it/s]
 65%|██████▌   | 242220/371472 [8:14:26<9:25:54,  3.81it/s]
                                                           
{'loss': 2.9159, 'learning_rate': 4.133196147299015e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242220/371472 [8:14:26<9:25:54,  3.81it/s]
 65%|██████▌   | 242221/371472 [8:14:27<9:21:58,  3.83it/s]
 65%|██████▌   | 242222/371472 [8:14:27<9:41:18,  3.71it/s]
 65%|██████▌   | 242223/371472 [8:14:27<9:29:14,  3.78it/s]
 65%|██████▌   | 242224/371472 [8:14:27<9:19:00,  3.85it/s]
 65%|██████▌   | 242225/371472 [8:14:28<9:30:59,  3.77it/s]
 65%|██████▌   | 242226/371472 [8:14:28<9:10:41,  3.91it/s]
 65%|██████▌   | 242227/371472 [8:14:28<8:59:41,  3.99it/s]
 65%|██████▌   | 242228/371472 [8:14:28<9:34:40,  3.75it/s]
 65%|██████▌   | 242229/371472 [8:14:29<9:56:21,  3.61it/s]
 65%|██████▌   | 242230/371472 [8:14:29<9:57:43,  3.60it/s]
 65%|██████▌   | 242231/371472 [8:14:29<9:38:41,  3.72it/s]
 65%|██████▌   | 242232/371472 [8:14:30<9:20:23,  3.84it/s]
 65%|██████▌   | 242233/371472 [8:14:30<9:10:06,  3.92it/s]
 65%|██████▌   | 242234/371472 [8:14:30<9:10:54,  3.91it/s]
 65%|██████▌   | 242235/371472 [8:14:30<8:54:14,  4.03it/s]
 65%|██████▌   | 242236/371472 [8:14:31<9:24:28,  3.82it/s]
 65%|██████▌   | 242237/371472 [8:14:31<9:12:14,  3.90it/s]
 65%|██████▌   | 242238/371472 [8:14:31<9:15:30,  3.88it/s]
 65%|██████��   | 242239/371472 [8:14:31<9:14:36,  3.88it/s]
 65%|██████▌   | 242240/371472 [8:14:32<9:02:24,  3.97it/s]
                                                           
{'loss': 2.8527, 'learning_rate': 4.1327113275442257e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242240/371472 [8:14:32<9:02:24,  3.97it/s]
 65%|██████▌   | 242241/371472 [8:14:32<8:55:53,  4.02it/s]
 65%|██████▌   | 242242/371472 [8:14:32<9:12:53,  3.90it/s]
 65%|██████▌   | 242243/371472 [8:14:32<9:49:01,  3.66it/s]
 65%|██████▌   | 242244/371472 [8:14:33<10:03:54,  3.57it/s]
 65%|██████▌   | 242245/371472 [8:14:33<9:57:40,  3.60it/s] 
 65%|██████▌   | 242246/371472 [8:14:33<10:10:40,  3.53it/s]
 65%|██████▌   | 242247/371472 [8:14:34<10:33:56,  3.40it/s]
 65%|██████▌   | 242248/371472 [8:14:34<10:11:58,  3.52it/s]
 65%|██████▌   | 242249/371472 [8:14:34<9:48:50,  3.66it/s] 
 65%|██████▌   | 242250/371472 [8:14:34<9:48:31,  3.66it/s]
 65%|██████▌   | 242251/371472 [8:14:35<9:31:25,  3.77it/s]
 65%|██████▌   | 242252/371472 [8:14:35<11:35:49,  3.10it/s]
 65%|██████▌   | 242253/371472 [8:14:35<11:07:15,  3.23it/s]
 65%|██████▌   | 242254/371472 [8:14:36<10:43:44,  3.35it/s]
 65%|██████▌   | 242255/371472 [8:14:36<10:56:00,  3.28it/s]
 65%|██████▌   | 242256/371472 [8:14:36<10:47:43,  3.32it/s]
 65%|██████▌   | 242257/371472 [8:14:36<10:25:30,  3.44it/s]
 65%|██████▌   | 242258/371472 [8:14:37<10:16:24,  3.49it/s]
 65%|██████▌   | 242259/371472 [8:14:37<11:02:05,  3.25it/s]
 65%|██████▌   | 242260/371472 [8:14:37<10:29:51,  3.42it/s]
                                                            
{'loss': 2.8484, 'learning_rate': 4.1322265077894375e-07, 'epoch': 10.43}
+
 65%|██████▌   | 242260/371472 [8:14:37<10:29:51,  3.42it/s]
 65%|██████▌   | 242261/371472 [8:14:38<10:05:24,  3.56it/s]
 65%|██████▌   | 242262/371472 [8:14:38<9:40:34,  3.71it/s] 
 65%|██████▌   | 242263/371472 [8:14:38<9:18:00,  3.86it/s]
 65%|██████▌   | 242264/371472 [8:14:38<9:22:57,  3.83it/s]
 65%|██████▌   | 242265/371472 [8:14:39<9:33:33,  3.75it/s]
 65%|██████▌   | 242266/371472 [8:14:39<10:07:23,  3.55it/s]
 65%|██████▌   | 242267/371472 [8:14:39<10:47:05,  3.33it/s]
 65%|██████▌   | 242268/371472 [8:14:40<10:48:13,  3.32it/s]
 65%|██████▌   | 242269/371472 [8:14:40<10:21:45,  3.46it/s]
 65%|██████▌   | 242270/371472 [8:14:40<9:51:40,  3.64it/s] 
 65%|██████▌   | 242271/371472 [8:14:40<9:38:10,  3.72it/s]
 65%|██████▌   | 242272/371472 [8:14:41<9:23:40,  3.82it/s]
 65%|██████▌   | 242273/371472 [8:14:41<9:12:02,  3.90it/s]
 65%|██████▌   | 242274/371472 [8:14:41<9:18:14,  3.86it/s]
 65%|██████▌   | 242275/371472 [8:14:41<9:01:09,  3.98it/s]
 65%|██████▌   | 242276/371472 [8:14:42<9:18:56,  3.85it/s]
 65%|██████▌   | 242277/371472 [8:14:42<9:48:35,  3.66it/s]
 65%|██████▌   | 242278/371472 [8:14:42<9:34:31,  3.75it/s]
 65%|██████▌   | 242279/371472 [8:14:42<9:38:33,  3.72it/s]
 65%|██████▌   | 242280/371472 [8:14:43<9:24:21,  3.82it/s]
                                                           
{'loss': 2.9427, 'learning_rate': 4.131741688034648e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242280/371472 [8:14:43<9:24:21,  3.82it/s]
 65%|██████▌   | 242281/371472 [8:14:43<9:35:01,  3.74it/s]
 65%|██████▌   | 242282/371472 [8:14:43<11:08:56,  3.22it/s]
 65%|██████▌   | 242283/371472 [8:14:44<11:20:09,  3.17it/s]
 65%|██████▌   | 242284/371472 [8:14:44<10:34:57,  3.39it/s]
 65%|██████▌   | 242285/371472 [8:14:44<10:09:06,  3.53it/s]
 65%|██████▌   | 242286/371472 [8:14:44<10:13:16,  3.51it/s]
 65%|██████▌   | 242287/371472 [8:14:45<9:58:39,  3.60it/s] 
 65%|██████▌   | 242288/371472 [8:14:45<10:36:00,  3.39it/s]
 65%|██████▌   | 242289/371472 [8:14:45<10:18:57,  3.48it/s]
 65%|██████▌   | 242290/371472 [8:14:46<10:04:46,  3.56it/s]
 65%|██████▌   | 242291/371472 [8:14:46<10:02:47,  3.57it/s]
 65%|██████▌   | 242292/371472 [8:14:46<9:47:55,  3.66it/s] 
 65%|██████▌   | 242293/371472 [8:14:46<9:49:21,  3.65it/s]
 65%|██████▌   | 242294/371472 [8:14:47<9:30:10,  3.78it/s]
 65%|██████▌   | 242295/371472 [8:14:47<9:24:21,  3.81it/s]
 65%|██████▌   | 242296/371472 [8:14:47<10:11:18,  3.52it/s]
 65%|██████▌   | 242297/371472 [8:14:48<10:12:31,  3.51it/s]
 65%|██████▌   | 242298/371472 [8:14:48<9:40:22,  3.71it/s] 
 65%|██████▌   | 242299/371472 [8:14:48<9:37:00,  3.73it/s]
 65%|██████▌   | 242300/371472 [8:14:48<9:19:59,  3.84it/s]
                                                           
{'loss': 2.8063, 'learning_rate': 4.1312568682798594e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242300/371472 [8:14:48<9:19:59,  3.84it/s]
 65%|██████▌   | 242301/371472 [8:14:49<9:46:24,  3.67it/s]
 65%|██████▌   | 242302/371472 [8:14:49<9:30:03,  3.78it/s]
 65%|██████▌   | 242303/371472 [8:14:49<10:12:23,  3.52it/s]
 65%|██████▌   | 242304/371472 [8:14:49<9:51:49,  3.64it/s] 
 65%|██████▌   | 242305/371472 [8:14:50<9:40:19,  3.71it/s]
 65%|██████▌   | 242306/371472 [8:14:50<10:20:33,  3.47it/s]
 65%|██████▌   | 242307/371472 [8:14:50<9:56:27,  3.61it/s] 
 65%|██████▌   | 242308/371472 [8:14:51<9:38:39,  3.72it/s]
 65%|██████▌   | 242309/371472 [8:14:51<9:31:06,  3.77it/s]
 65%|██████▌   | 242310/371472 [8:14:51<9:05:24,  3.95it/s]
 65%|██████▌   | 242311/371472 [8:14:51<9:14:44,  3.88it/s]
 65%|██████▌   | 242312/371472 [8:14:52<9:34:12,  3.75it/s]
 65%|██████▌   | 242313/371472 [8:14:52<9:40:11,  3.71it/s]
 65%|██████▌   | 242314/371472 [8:14:52<9:41:21,  3.70it/s]
 65%|██████▌   | 242315/371472 [8:14:52<9:31:34,  3.77it/s]
 65%|██████▌   | 242316/371472 [8:14:53<9:29:52,  3.78it/s]
 65%|██████▌   | 242317/371472 [8:14:53<9:18:20,  3.86it/s]
 65%|██████▌   | 242318/371472 [8:14:53<9:41:28,  3.70it/s]
 65%|██████▌   | 242319/371472 [8:14:53<9:23:42,  3.82it/s]
 65%|██████▌   | 242320/371472 [8:14:54<10:09:56,  3.53it/s]
                                                            
{'loss': 3.0325, 'learning_rate': 4.13077204852507e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242320/371472 [8:14:54<10:09:56,  3.53it/s]
 65%|██████▌   | 242321/371472 [8:14:54<9:58:23,  3.60it/s] 
 65%|██████▌   | 242322/371472 [8:14:54<10:17:00,  3.49it/s]
 65%|██████▌   | 242323/371472 [8:14:55<10:01:36,  3.58it/s]
 65%|██████▌   | 242324/371472 [8:14:55<10:03:34,  3.57it/s]
 65%|██████▌   | 242325/371472 [8:14:55<9:48:06,  3.66it/s] 
 65%|██████▌   | 242326/371472 [8:14:55<9:30:06,  3.78it/s]
 65%|██████▌   | 242327/371472 [8:14:56<9:28:47,  3.78it/s]
 65%|██████▌   | 242328/371472 [8:14:56<9:46:57,  3.67it/s]
 65%|██████▌   | 242329/371472 [8:14:56<9:33:45,  3.75it/s]
 65%|██████▌   | 242330/371472 [8:14:56<9:33:47,  3.75it/s]
 65%|██████▌   | 242331/371472 [8:14:57<9:29:43,  3.78it/s]
 65%|██████▌   | 242332/371472 [8:14:57<9:54:07,  3.62it/s]
 65%|██████▌   | 242333/371472 [8:14:57<11:07:24,  3.22it/s]
 65%|██████▌   | 242334/371472 [8:14:58<10:19:24,  3.47it/s]
 65%|██████▌   | 242335/371472 [8:14:58<9:40:50,  3.71it/s] 
 65%|██████▌   | 242336/371472 [8:14:58<9:50:05,  3.65it/s]
 65%|██████▌   | 242337/371472 [8:14:58<10:07:32,  3.54it/s]
 65%|██████▌   | 242338/371472 [8:14:59<10:48:29,  3.32it/s]
 65%|██████▌   | 242339/371472 [8:14:59<10:11:35,  3.52it/s]
 65%|██████▌   | 242340/371472 [8:14:59<10:12:27,  3.51it/s]
                                                            
{'loss': 2.9978, 'learning_rate': 4.130287228770282e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242340/371472 [8:14:59<10:12:27,  3.51it/s]
 65%|██████▌   | 242341/371472 [8:15:00<9:49:41,  3.65it/s] 
 65%|██████▌   | 242342/371472 [8:15:00<9:29:08,  3.78it/s]
 65%|██████▌   | 242343/371472 [8:15:00<9:23:59,  3.82it/s]
 65%|██████▌   | 242344/371472 [8:15:00<9:40:27,  3.71it/s]
 65%|██████▌   | 242345/371472 [8:15:01<10:20:19,  3.47it/s]
 65%|██████▌   | 242346/371472 [8:15:01<11:01:02,  3.26it/s]
 65%|██████▌   | 242347/371472 [8:15:01<11:27:30,  3.13it/s]
 65%|██████▌   | 242348/371472 [8:15:02<10:49:24,  3.31it/s]
 65%|██████▌   | 242349/371472 [8:15:02<10:47:19,  3.32it/s]
 65%|██████▌   | 242350/371472 [8:15:02<10:26:42,  3.43it/s]
 65%|██████▌   | 242351/371472 [8:15:02<10:09:30,  3.53it/s]
 65%|██████▌   | 242352/371472 [8:15:03<9:49:54,  3.65it/s] 
 65%|██████▌   | 242353/371472 [8:15:03<9:31:48,  3.76it/s]
 65%|██████▌   | 242354/371472 [8:15:03<9:58:10,  3.60it/s]
 65%|██████▌   | 242355/371472 [8:15:04<9:50:43,  3.64it/s]
 65%|██████▌   | 242356/371472 [8:15:04<9:52:22,  3.63it/s]
 65%|██████▌   | 242357/371472 [8:15:04<10:06:56,  3.55it/s]
 65%|██████▌   | 242358/371472 [8:15:04<9:41:47,  3.70it/s] 
 65%|██████▌   | 242359/371472 [8:15:05<10:38:38,  3.37it/s]
 65%|██████▌   | 242360/371472 [8:15:05<10:15:10,  3.50it/s]
                                                            
{'loss': 2.7447, 'learning_rate': 4.129802409015492e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242360/371472 [8:15:05<10:15:10,  3.50it/s]
 65%|██████▌   | 242361/371472 [8:15:05<9:42:04,  3.70it/s] 
 65%|██████▌   | 242362/371472 [8:15:05<9:27:11,  3.79it/s]
 65%|██████▌   | 242363/371472 [8:15:06<9:44:13,  3.68it/s]
 65%|██████▌   | 242364/371472 [8:15:06<9:44:57,  3.68it/s]
 65%|██████▌   | 242365/371472 [8:15:06<9:50:03,  3.65it/s]
 65%|██████▌   | 242366/371472 [8:15:07<10:06:31,  3.55it/s]
 65%|██████▌   | 242367/371472 [8:15:07<9:48:33,  3.66it/s] 
 65%|██████▌   | 242368/371472 [8:15:07<9:34:00,  3.75it/s]
 65%|██████▌   | 242369/371472 [8:15:07<10:27:51,  3.43it/s]
 65%|██████▌   | 242370/371472 [8:15:08<10:54:43,  3.29it/s]
 65%|██████▌   | 242371/371472 [8:15:08<10:18:08,  3.48it/s]
 65%|██████▌   | 242372/371472 [8:15:08<10:12:36,  3.51it/s]
 65%|██████▌   | 242373/371472 [8:15:09<10:12:41,  3.51it/s]
 65%|██████▌   | 242374/371472 [8:15:09<10:17:19,  3.49it/s]
 65%|██████▌   | 242375/371472 [8:15:09<9:52:00,  3.63it/s] 
 65%|██████▌   | 242376/371472 [8:15:09<9:42:32,  3.69it/s]
 65%|██████▌   | 242377/371472 [8:15:10<9:30:12,  3.77it/s]
 65%|██████▌   | 242378/371472 [8:15:10<9:32:25,  3.76it/s]
 65%|██████▌   | 242379/371472 [8:15:10<9:32:10,  3.76it/s]
 65%|██████▌   | 242380/371472 [8:15:11<10:16:50,  3.49it/s]
                                                            
{'loss': 2.8849, 'learning_rate': 4.129317589260704e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242380/371472 [8:15:11<10:16:50,  3.49it/s]
 65%|██████▌   | 242381/371472 [8:15:11<10:24:33,  3.44it/s]
 65%|██████▌   | 242382/371472 [8:15:11<10:40:18,  3.36it/s]
 65%|██████▌   | 242383/371472 [8:15:11<10:34:38,  3.39it/s]
 65%|██████▌   | 242384/371472 [8:15:12<10:29:23,  3.42it/s]
 65%|██████▌   | 242385/371472 [8:15:12<10:15:04,  3.50it/s]
 65%|██████▌   | 242386/371472 [8:15:12<10:26:53,  3.43it/s]
 65%|██████▌   | 242387/371472 [8:15:13<10:39:30,  3.36it/s]
 65%|██████▌   | 242388/371472 [8:15:13<10:21:05,  3.46it/s]
 65%|██████▌   | 242389/371472 [8:15:13<10:24:15,  3.45it/s]
 65%|██████▌   | 242390/371472 [8:15:13<10:21:10,  3.46it/s]
 65%|██████▌   | 242391/371472 [8:15:14<10:04:28,  3.56it/s]
 65%|██████▌   | 242392/371472 [8:15:14<10:03:29,  3.56it/s]
 65%|██████▌   | 242393/371472 [8:15:14<10:00:31,  3.58it/s]
 65%|██████▌   | 242394/371472 [8:15:15<9:41:14,  3.70it/s] 
 65%|██████▌   | 242395/371472 [8:15:15<9:29:27,  3.78it/s]
 65%|██████▌   | 242396/371472 [8:15:15<9:33:02,  3.75it/s]
 65%|██████▌   | 242397/371472 [8:15:15<9:23:50,  3.82it/s]
 65%|██████▌   | 242398/371472 [8:15:16<9:41:05,  3.70it/s]
 65%|██████▌   | 242399/371472 [8:15:16<9:45:43,  3.67it/s]
 65%|██████▌   | 242400/371472 [8:15:16<10:09:41,  3.53it/s]
                                                            
{'loss': 2.8542, 'learning_rate': 4.1288327695059146e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242400/371472 [8:15:16<10:09:41,  3.53it/s]
 65%|██████▌   | 242401/371472 [8:15:16<10:15:07,  3.50it/s]
 65%|██████▌   | 242402/371472 [8:15:17<10:12:38,  3.51it/s]
 65%|██████▌   | 242403/371472 [8:15:17<10:41:01,  3.36it/s]
 65%|██████▌   | 242404/371472 [8:15:17<10:45:19,  3.33it/s]
 65%|██████▌   | 242405/371472 [8:15:18<10:13:16,  3.51it/s]
 65%|██████▌   | 242406/371472 [8:15:18<10:09:18,  3.53it/s]
 65%|██████▌   | 242407/371472 [8:15:18<9:58:06,  3.60it/s] 
 65%|██████▌   | 242408/371472 [8:15:18<9:55:13,  3.61it/s]
 65%|██████▌   | 242409/371472 [8:15:19<9:47:58,  3.66it/s]
 65%|██████▌   | 242410/371472 [8:15:19<10:00:11,  3.58it/s]
 65%|██████▌   | 242411/371472 [8:15:19<10:05:06,  3.55it/s]
 65%|██████▌   | 242412/371472 [8:15:20<9:48:02,  3.66it/s] 
 65%|██████▌   | 242413/371472 [8:15:20<10:00:49,  3.58it/s]
 65%|██████▌   | 242414/371472 [8:15:20<10:07:17,  3.54it/s]
 65%|██████▌   | 242415/371472 [8:15:20<10:36:20,  3.38it/s]
 65%|██████▌   | 242416/371472 [8:15:21<10:43:13,  3.34it/s]
 65%|██████▌   | 242417/371472 [8:15:21<10:10:22,  3.52it/s]
 65%|██████▌   | 242418/371472 [8:15:21<9:59:54,  3.59it/s] 
 65%|██████▌   | 242419/371472 [8:15:22<9:55:28,  3.61it/s]
 65%|██████▌   | 242420/371472 [8:15:22<9:30:51,  3.77it/s]
                                                           
{'loss': 2.7823, 'learning_rate': 4.128347949751126e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242420/371472 [8:15:22<9:30:51,  3.77it/s]
 65%|██████▌   | 242421/371472 [8:15:22<9:25:25,  3.80it/s]
 65%|██████▌   | 242422/371472 [8:15:22<10:15:38,  3.49it/s]
 65%|██████▌   | 242423/371472 [8:15:23<10:13:26,  3.51it/s]
 65%|██████▌   | 242424/371472 [8:15:23<10:03:17,  3.57it/s]
 65%|██████▌   | 242425/371472 [8:15:23<9:49:48,  3.65it/s] 
 65%|██████▌   | 242426/371472 [8:15:23<9:46:45,  3.67it/s]
 65%|██████▌   | 242427/371472 [8:15:24<9:29:59,  3.77it/s]
 65%|██████▌   | 242428/371472 [8:15:24<9:42:29,  3.69it/s]
 65%|██████▌   | 242429/371472 [8:15:24<9:48:32,  3.65it/s]
 65%|██████▌   | 242430/371472 [8:15:25<9:56:50,  3.60it/s]
 65%|██████▌   | 242431/371472 [8:15:25<9:48:55,  3.65it/s]
 65%|██████▌   | 242432/371472 [8:15:25<9:50:54,  3.64it/s]
 65%|██████▌   | 242433/371472 [8:15:25<10:17:20,  3.48it/s]
 65%|██████▌   | 242434/371472 [8:15:26<10:17:27,  3.48it/s]
 65%|██████▌   | 242435/371472 [8:15:26<9:59:43,  3.59it/s] 
 65%|██████▌   | 242436/371472 [8:15:26<10:25:39,  3.44it/s]
 65%|██████▌   | 242437/371472 [8:15:27<10:14:43,  3.50it/s]
 65%|██████▌   | 242438/371472 [8:15:27<10:11:34,  3.52it/s]
 65%|██████▌   | 242439/371472 [8:15:27<10:19:03,  3.47it/s]
 65%|██████▌   | 242440/371472 [8:15:27<10:16:10,  3.49it/s]
                                                            
{'loss': 2.6983, 'learning_rate': 4.1278631299963366e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242440/371472 [8:15:27<10:16:10,  3.49it/s]
 65%|██████▌   | 242441/371472 [8:15:28<9:54:47,  3.62it/s] 
 65%|██████▌   | 242442/371472 [8:15:28<9:36:06,  3.73it/s]
 65%|██████▌   | 242443/371472 [8:15:28<9:39:12,  3.71it/s]
 65%|██████▌   | 242444/371472 [8:15:28<9:53:16,  3.62it/s]
 65%|██████▌   | 242445/371472 [8:15:29<9:39:48,  3.71it/s]
 65%|██████▌   | 242446/371472 [8:15:29<9:28:17,  3.78it/s]
 65%|██████▌   | 242447/371472 [8:15:29<9:58:11,  3.59it/s]
 65%|██████▌   | 242448/371472 [8:15:30<10:26:30,  3.43it/s]
 65%|██████▌   | 242449/371472 [8:15:30<10:16:20,  3.49it/s]
 65%|██████▌   | 242450/371472 [8:15:30<9:48:08,  3.66it/s] 
 65%|██████▌   | 242451/371472 [8:15:30<9:42:15,  3.69it/s]
 65%|██████▌   | 242452/371472 [8:15:31<9:25:20,  3.80it/s]
 65%|██████▌   | 242453/371472 [8:15:31<9:22:25,  3.82it/s]
 65%|██████▌   | 242454/371472 [8:15:31<10:22:58,  3.45it/s]
 65%|██████▌   | 242455/371472 [8:15:32<10:41:53,  3.35it/s]
 65%|██████▌   | 242456/371472 [8:15:32<10:33:12,  3.40it/s]
 65%|██████▌   | 242457/371472 [8:15:32<10:35:04,  3.39it/s]
 65%|██████▌   | 242458/371472 [8:15:32<10:01:52,  3.57it/s]
 65%|██████▌   | 242459/371472 [8:15:33<9:55:45,  3.61it/s] 
 65%|██████▌   | 242460/371472 [8:15:33<10:27:43,  3.43it/s]
                                                            
{'loss': 2.8226, 'learning_rate': 4.1273783102415483e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242460/371472 [8:15:33<10:27:43,  3.43it/s]
 65%|██████▌   | 242461/371472 [8:15:33<10:42:33,  3.35it/s]
 65%|██████▌   | 242462/371472 [8:15:34<10:23:37,  3.45it/s]
 65%|██████▌   | 242463/371472 [8:15:34<10:02:33,  3.57it/s]
 65%|██████▌   | 242464/371472 [8:15:34<10:27:44,  3.43it/s]
 65%|██████▌   | 242465/371472 [8:15:34<9:54:26,  3.62it/s] 
 65%|██████▌   | 242466/371472 [8:15:35<9:44:18,  3.68it/s]
 65%|██████▌   | 242467/371472 [8:15:35<9:46:19,  3.67it/s]
 65%|██████▌   | 242468/371472 [8:15:35<9:42:39,  3.69it/s]
 65%|██████▌   | 242469/371472 [8:15:35<9:35:22,  3.74it/s]
 65%|██████▌   | 242470/371472 [8:15:36<9:56:51,  3.60it/s]
 65%|██████▌   | 242471/371472 [8:15:36<9:40:40,  3.70it/s]
 65%|██████▌   | 242472/371472 [8:15:36<9:22:49,  3.82it/s]
 65%|██████▌   | 242473/371472 [8:15:37<9:12:08,  3.89it/s]
 65%|██████▌   | 242474/371472 [8:15:37<9:18:34,  3.85it/s]
 65%|██████▌   | 242475/371472 [8:15:37<9:07:03,  3.93it/s]
 65%|██████▌   | 242476/371472 [8:15:37<9:00:38,  3.98it/s]
 65%|██████▌   | 242477/371472 [8:15:38<9:36:43,  3.73it/s]
 65%|██████▌   | 242478/371472 [8:15:38<9:36:26,  3.73it/s]
 65%|██████▌   | 242479/371472 [8:15:38<11:19:45,  3.16it/s]
 65%|██████▌   | 242480/371472 [8:15:39<11:17:54,  3.17it/s]
                                                            
{'loss': 2.8756, 'learning_rate': 4.1268934904867585e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242480/371472 [8:15:39<11:17:54,  3.17it/s]
 65%|██████▌   | 242481/371472 [8:15:39<10:54:51,  3.28it/s]
 65%|██████▌   | 242482/371472 [8:15:39<10:42:44,  3.34it/s]
 65%|██████▌   | 242483/371472 [8:15:39<10:45:30,  3.33it/s]
 65%|██████▌   | 242484/371472 [8:15:40<10:17:26,  3.48it/s]
 65%|██████▌   | 242485/371472 [8:15:40<9:43:23,  3.68it/s] 
 65%|██████▌   | 242486/371472 [8:15:40<9:38:21,  3.72it/s]
 65%|██████▌   | 242487/371472 [8:15:40<9:43:53,  3.68it/s]
 65%|██████▌   | 242488/371472 [8:15:41<9:37:00,  3.73it/s]
 65%|██████▌   | 242489/371472 [8:15:41<9:22:40,  3.82it/s]
 65%|██████▌   | 242490/371472 [8:15:41<10:19:04,  3.47it/s]
 65%|██████▌   | 242491/371472 [8:15:42<10:14:42,  3.50it/s]
 65%|██████▌   | 242492/371472 [8:15:42<10:31:26,  3.40it/s]
 65%|██████▌   | 242493/371472 [8:15:42<10:35:26,  3.38it/s]
 65%|██████▌   | 242494/371472 [8:15:43<10:36:41,  3.38it/s]
 65%|██████▌   | 242495/371472 [8:15:43<10:42:00,  3.35it/s]
 65%|██████▌   | 242496/371472 [8:15:43<10:26:28,  3.43it/s]
 65%|██████▌   | 242497/371472 [8:15:43<9:51:42,  3.63it/s] 
 65%|██████▌   | 242498/371472 [8:15:44<9:31:41,  3.76it/s]
 65%|██████▌   | 242499/371472 [8:15:44<9:34:37,  3.74it/s]
 65%|██████▌   | 242500/371472 [8:15:44<9:41:12,  3.70it/s]
                                                           
{'loss': 2.7535, 'learning_rate': 4.1264086707319703e-07, 'epoch': 10.44}
+
 65%|██████▌   | 242500/371472 [8:15:44<9:41:12,  3.70it/s]
 65%|██████▌   | 242501/371472 [8:15:44<9:29:36,  3.77it/s]
 65%|██████▌   | 242502/371472 [8:15:45<9:13:12,  3.89it/s]
 65%|██████▌   | 242503/371472 [8:15:45<9:25:54,  3.80it/s]
 65%|██████▌   | 242504/371472 [8:15:45<9:48:14,  3.65it/s]
 65%|██████▌   | 242505/371472 [8:15:45<9:52:37,  3.63it/s]
 65%|██████▌   | 242506/371472 [8:15:46<9:45:19,  3.67it/s]
 65%|██████▌   | 242507/371472 [8:15:46<10:00:28,  3.58it/s]
 65%|██████▌   | 242508/371472 [8:15:46<9:43:58,  3.68it/s] 
 65%|██████▌   | 242509/371472 [8:15:47<9:48:55,  3.65it/s]
 65%|██████▌   | 242510/371472 [8:15:47<10:02:32,  3.57it/s]
 65%|██████▌   | 242511/371472 [8:15:47<10:03:34,  3.56it/s]
 65%|██████▌   | 242512/371472 [8:15:47<9:59:14,  3.59it/s] 
 65%|██████▌   | 242513/371472 [8:15:48<10:32:08,  3.40it/s]
 65%|██████▌   | 242514/371472 [8:15:48<10:15:44,  3.49it/s]
 65%|██████▌   | 242515/371472 [8:15:48<9:57:39,  3.60it/s] 
 65%|██████▌   | 242516/371472 [8:15:49<9:26:03,  3.80it/s]
 65%|██████▌   | 242517/371472 [8:15:49<9:29:07,  3.78it/s]
 65%|██████▌   | 242518/371472 [8:15:49<9:58:16,  3.59it/s]
 65%|██████▌   | 242519/371472 [8:15:49<9:58:37,  3.59it/s]
 65%|██████▌   | 242520/371472 [8:15:50<10:42:15,  3.35it/s]
                                                            
{'loss': 2.6422, 'learning_rate': 4.125923850977181e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242520/371472 [8:15:50<10:42:15,  3.35it/s]
 65%|██████▌   | 242521/371472 [8:15:50<10:33:26,  3.39it/s]
 65%|██████▌   | 242522/371472 [8:15:50<10:17:18,  3.48it/s]
 65%|██████▌   | 242523/371472 [8:15:51<10:29:55,  3.41it/s]
 65%|██████▌   | 242524/371472 [8:15:51<10:07:45,  3.54it/s]
 65%|██████▌   | 242525/371472 [8:15:51<10:19:27,  3.47it/s]
 65%|██████▌   | 242526/371472 [8:15:51<10:14:53,  3.50it/s]
 65%|██████▌   | 242527/371472 [8:15:52<11:47:34,  3.04it/s]
 65%|██████▌   | 242528/371472 [8:15:52<10:56:37,  3.27it/s]
 65%|██████▌   | 242529/371472 [8:15:52<11:12:33,  3.20it/s]
 65%|██████▌   | 242530/371472 [8:15:53<10:30:30,  3.41it/s]
 65%|██████▌   | 242531/371472 [8:15:53<11:19:30,  3.16it/s]
 65%|██████▌   | 242532/371472 [8:15:53<10:44:09,  3.34it/s]
 65%|██████▌   | 242533/371472 [8:15:54<10:20:41,  3.46it/s]
 65%|██████▌   | 242534/371472 [8:15:54<10:05:14,  3.55it/s]
 65%|██████▌   | 242535/371472 [8:15:54<10:00:35,  3.58it/s]
 65%|██████▌   | 242536/371472 [8:15:54<9:41:04,  3.70it/s] 
 65%|██████▌   | 242537/371472 [8:15:55<9:46:32,  3.66it/s]
 65%|██████▌   | 242538/371472 [8:15:55<9:37:06,  3.72it/s]
 65%|██████▌   | 242539/371472 [8:15:55<9:28:57,  3.78it/s]
 65%|██��███▌   | 242540/371472 [8:15:55<9:49:12,  3.65it/s]
                                                           
{'loss': 2.8537, 'learning_rate': 4.125439031222392e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242540/371472 [8:15:55<9:49:12,  3.65it/s]
 65%|██████▌   | 242541/371472 [8:15:56<10:12:23,  3.51it/s]
 65%|██████▌   | 242542/371472 [8:15:56<10:58:43,  3.26it/s]
 65%|██████▌   | 242543/371472 [8:15:56<10:21:52,  3.46it/s]
 65%|██████▌   | 242544/371472 [8:15:57<10:11:13,  3.52it/s]
 65%|██████▌   | 242545/371472 [8:15:57<10:04:53,  3.55it/s]
 65%|██████▌   | 242546/371472 [8:15:57<9:35:21,  3.73it/s] 
 65%|██████▌   | 242547/371472 [8:15:57<10:13:51,  3.50it/s]
 65%|██████▌   | 242548/371472 [8:15:58<10:52:17,  3.29it/s]
 65%|██████▌   | 242549/371472 [8:15:58<10:14:03,  3.50it/s]
 65%|██████▌   | 242550/371472 [8:15:58<9:50:48,  3.64it/s] 
 65%|██████▌   | 242551/371472 [8:15:59<9:42:42,  3.69it/s]
 65%|██████▌   | 242552/371472 [8:15:59<9:35:33,  3.73it/s]
 65%|██████▌   | 242553/371472 [8:15:59<9:29:13,  3.77it/s]
 65%|██████▌   | 242554/371472 [8:15:59<9:53:22,  3.62it/s]
 65%|██████▌   | 242555/371472 [8:16:00<9:28:39,  3.78it/s]
 65%|██████▌   | 242556/371472 [8:16:00<9:07:16,  3.93it/s]
 65%|██████▌   | 242557/371472 [8:16:00<9:12:07,  3.89it/s]
 65%|██████▌   | 242558/371472 [8:16:00<9:13:32,  3.88it/s]
 65%|██████▌   | 242559/371472 [8:16:01<9:31:45,  3.76it/s]
 65%|██████▌   | 242560/371472 [8:16:01<10:45:56,  3.33it/s]
                                                            
{'loss': 2.8258, 'learning_rate': 4.124954211467603e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242560/371472 [8:16:01<10:45:56,  3.33it/s]
 65%|██████▌   | 242561/371472 [8:16:01<10:28:22,  3.42it/s]
 65%|██████▌   | 242562/371472 [8:16:02<10:33:56,  3.39it/s]
 65%|██████▌   | 242563/371472 [8:16:02<10:03:48,  3.56it/s]
 65%|██████▌   | 242564/371472 [8:16:02<10:29:51,  3.41it/s]
 65%|██████▌   | 242565/371472 [8:16:03<10:30:27,  3.41it/s]
 65%|██████▌   | 242566/371472 [8:16:03<10:17:07,  3.48it/s]
 65%|██████▌   | 242567/371472 [8:16:03<9:54:46,  3.61it/s] 
 65%|██████▌   | 242568/371472 [8:16:03<9:47:27,  3.66it/s]
 65%|██████▌   | 242569/371472 [8:16:04<9:17:27,  3.85it/s]
 65%|██████▌   | 242570/371472 [8:16:04<9:34:15,  3.74it/s]
 65%|██████▌   | 242571/371472 [8:16:04<9:37:13,  3.72it/s]
 65%|██████▌   | 242572/371472 [8:16:04<9:20:28,  3.83it/s]
 65%|██████▌   | 242573/371472 [8:16:05<9:15:24,  3.87it/s]
 65%|██████▌   | 242574/371472 [8:16:05<9:25:32,  3.80it/s]
 65%|██████▌   | 242575/371472 [8:16:05<9:23:46,  3.81it/s]
 65%|██████▌   | 242576/371472 [8:16:05<9:28:13,  3.78it/s]
 65%|██████▌   | 242577/371472 [8:16:06<9:29:30,  3.77it/s]
 65%|██████▌   | 242578/371472 [8:16:06<10:14:58,  3.49it/s]
 65%|██████▌   | 242579/371472 [8:16:06<9:57:02,  3.60it/s] 
 65%|██████▌   | 242580/371472 [8:16:06<9:43:28,  3.68it/s]
                                                           
{'loss': 2.7816, 'learning_rate': 4.124469391712815e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242580/371472 [8:16:06<9:43:28,  3.68it/s]
 65%|██████▌   | 242581/371472 [8:16:07<9:58:34,  3.59it/s]
 65%|██████▌   | 242582/371472 [8:16:07<9:42:02,  3.69it/s]
 65%|██████▌   | 242583/371472 [8:16:07<9:33:45,  3.74it/s]
 65%|██████▌   | 242584/371472 [8:16:08<10:34:43,  3.38it/s]
 65%|██████▌   | 242585/371472 [8:16:08<10:53:14,  3.29it/s]
 65%|██████▌   | 242586/371472 [8:16:08<10:46:47,  3.32it/s]
 65%|██████▌   | 242587/371472 [8:16:09<11:07:03,  3.22it/s]
 65%|██████▌   | 242588/371472 [8:16:09<11:12:51,  3.19it/s]
 65%|██████▌   | 242589/371472 [8:16:09<10:54:42,  3.28it/s]
 65%|██████▌   | 242590/371472 [8:16:09<10:22:03,  3.45it/s]
 65%|██████▌   | 242591/371472 [8:16:10<9:50:13,  3.64it/s] 
 65%|██████▌   | 242592/371472 [8:16:10<9:42:08,  3.69it/s]
 65%|██████▌   | 242593/371472 [8:16:10<10:23:42,  3.44it/s]
 65%|██████▌   | 242594/371472 [8:16:11<9:53:51,  3.62it/s] 
 65%|██████▌   | 242595/371472 [8:16:11<10:20:17,  3.46it/s]
 65%|██████▌   | 242596/371472 [8:16:11<10:01:09,  3.57it/s]
 65%|██████▌   | 242597/371472 [8:16:11<9:56:23,  3.60it/s] 
 65%|██████▌   | 242598/371472 [8:16:12<9:32:31,  3.75it/s]
 65%|██████▌   | 242599/371472 [8:16:12<9:50:41,  3.64it/s]
 65%|██████▌   | 242600/371472 [8:16:12<9:36:41,  3.72it/s]
                                                           
{'loss': 2.7882, 'learning_rate': 4.123984571958025e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242600/371472 [8:16:12<9:36:41,  3.72it/s]
 65%|██████▌   | 242601/371472 [8:16:12<9:47:25,  3.66it/s]
 65%|██████▌   | 242602/371472 [8:16:13<9:35:32,  3.73it/s]
 65%|██████▌   | 242603/371472 [8:16:13<9:10:53,  3.90it/s]
 65%|██████▌   | 242604/371472 [8:16:13<9:22:20,  3.82it/s]
 65%|██████▌   | 242605/371472 [8:16:14<9:41:50,  3.69it/s]
 65%|██████▌   | 242606/371472 [8:16:14<10:34:30,  3.38it/s]
 65%|██████▌   | 242607/371472 [8:16:14<10:02:55,  3.56it/s]
 65%|██████▌   | 242608/371472 [8:16:14<10:12:46,  3.50it/s]
 65%|██████▌   | 242609/371472 [8:16:15<10:00:36,  3.58it/s]
 65%|██████▌   | 242610/371472 [8:16:15<9:46:43,  3.66it/s] 
 65%|██████▌   | 242611/371472 [8:16:15<10:32:03,  3.40it/s]
 65%|██████▌   | 242612/371472 [8:16:16<10:52:24,  3.29it/s]
 65%|██████▌   | 242613/371472 [8:16:16<10:12:37,  3.51it/s]
 65%|██████▌   | 242614/371472 [8:16:16<10:14:29,  3.49it/s]
 65%|██████▌   | 242615/371472 [8:16:16<9:44:41,  3.67it/s] 
 65%|██████▌   | 242616/371472 [8:16:17<9:49:55,  3.64it/s]
 65%|██████▌   | 242617/371472 [8:16:17<9:41:28,  3.69it/s]
 65%|██████▌   | 242618/371472 [8:16:17<9:56:34,  3.60it/s]
 65%|██████▌   | 242619/371472 [8:16:18<10:15:06,  3.49it/s]
 65%|██████▌   | 242620/371472 [8:16:18<10:06:08,  3.54it/s]
                                                            
{'loss': 2.7949, 'learning_rate': 4.1234997522032356e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242620/371472 [8:16:18<10:06:08,  3.54it/s]
 65%|██████▌   | 242621/371472 [8:16:18<10:29:48,  3.41it/s]
 65%|██████▌   | 242622/371472 [8:16:18<10:25:40,  3.43it/s]
 65%|██████▌   | 242623/371472 [8:16:19<10:11:54,  3.51it/s]
 65%|██████▌   | 242624/371472 [8:16:19<10:24:37,  3.44it/s]
 65%|██████▌   | 242625/371472 [8:16:19<10:15:55,  3.49it/s]
 65%|██████▌   | 242626/371472 [8:16:20<9:51:50,  3.63it/s] 
 65%|██████▌   | 242627/371472 [8:16:20<9:48:54,  3.65it/s]
 65%|██████▌   | 242628/371472 [8:16:20<9:41:30,  3.69it/s]
 65%|██████▌   | 242629/371472 [8:16:20<9:35:05,  3.73it/s]
 65%|██████▌   | 242630/371472 [8:16:21<10:50:54,  3.30it/s]
 65%|██████▌   | 242631/371472 [8:16:21<10:28:15,  3.42it/s]
 65%|██████▌   | 242632/371472 [8:16:21<10:51:57,  3.29it/s]
 65%|██████▌   | 242633/371472 [8:16:22<10:33:19,  3.39it/s]
 65%|██████▌   | 242634/371472 [8:16:22<10:19:42,  3.47it/s]
 65%|██████▌   | 242635/371472 [8:16:22<10:16:23,  3.48it/s]
 65%|██████▌   | 242636/371472 [8:16:22<10:21:26,  3.46it/s]
 65%|██████▌   | 242637/371472 [8:16:23<10:45:19,  3.33it/s]
 65%|██████▌   | 242638/371472 [8:16:23<11:12:45,  3.19it/s]
 65%|██████▌   | 242639/371472 [8:16:23<10:55:46,  3.27it/s]
 65%|██████▌   | 242640/371472 [8:16:24<10:27:17,  3.42it/s]
                                                            
{'loss': 2.8093, 'learning_rate': 4.1230149324484474e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242640/371472 [8:16:24<10:27:17,  3.42it/s]
 65%|██████▌   | 242641/371472 [8:16:24<10:11:56,  3.51it/s]
 65%|██████▌   | 242642/371472 [8:16:24<10:36:03,  3.38it/s]
 65%|██████▌   | 242643/371472 [8:16:25<10:23:57,  3.44it/s]
 65%|██████▌   | 242644/371472 [8:16:25<10:10:44,  3.52it/s]
 65%|██████▌   | 242645/371472 [8:16:25<10:03:49,  3.56it/s]
 65%|██████▌   | 242646/371472 [8:16:25<10:03:02,  3.56it/s]
 65%|██████▌   | 242647/371472 [8:16:26<9:51:14,  3.63it/s] 
 65%|██████▌   | 242648/371472 [8:16:26<9:51:59,  3.63it/s]
 65%|██████▌   | 242649/371472 [8:16:26<10:10:50,  3.51it/s]
 65%|██████▌   | 242650/371472 [8:16:26<9:47:47,  3.65it/s] 
 65%|██████▌   | 242651/371472 [8:16:27<10:23:10,  3.45it/s]
 65%|██████▌   | 242652/371472 [8:16:27<10:14:40,  3.49it/s]
 65%|██████▌   | 242653/371472 [8:16:27<10:13:24,  3.50it/s]
 65%|██████▌   | 242654/371472 [8:16:28<10:13:16,  3.50it/s]
 65%|██████▌   | 242655/371472 [8:16:28<10:05:24,  3.55it/s]
 65%|██████▌   | 242656/371472 [8:16:28<9:58:42,  3.59it/s] 
 65%|██████▌   | 242657/371472 [8:16:28<9:50:48,  3.63it/s]
 65%|██████▌   | 242658/371472 [8:16:29<9:29:33,  3.77it/s]
 65%|██████▌   | 242659/371472 [8:16:29<9:46:59,  3.66it/s]
 65%|██████▌   | 242660/371472 [8:16:29<9:39:14,  3.71it/s]
                                                           
{'loss': 2.7618, 'learning_rate': 4.122530112693658e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242660/371472 [8:16:29<9:39:14,  3.71it/s]
 65%|██████▌   | 242661/371472 [8:16:29<9:51:19,  3.63it/s]
 65%|██████▌   | 242662/371472 [8:16:30<9:44:55,  3.67it/s]
 65%|██████▌   | 242663/371472 [8:16:30<9:55:07,  3.61it/s]
 65%|██████▌   | 242664/371472 [8:16:30<9:59:30,  3.58it/s]
 65%|██████▌   | 242665/371472 [8:16:31<9:50:18,  3.64it/s]
 65%|██████▌   | 242666/371472 [8:16:31<9:26:41,  3.79it/s]
 65%|██████▌   | 242667/371472 [8:16:31<9:22:44,  3.81it/s]
 65%|██████▌   | 242668/371472 [8:16:31<9:23:52,  3.81it/s]
 65%|██████▌   | 242669/371472 [8:16:32<9:23:36,  3.81it/s]
 65%|██████▌   | 242670/371472 [8:16:32<9:20:53,  3.83it/s]
 65%|██████▌   | 242671/371472 [8:16:32<9:11:23,  3.89it/s]
 65%|██████▌   | 242672/371472 [8:16:32<9:11:52,  3.89it/s]
 65%|██████▌   | 242673/371472 [8:16:33<9:29:39,  3.77it/s]
 65%|██████▌   | 242674/371472 [8:16:33<9:27:46,  3.78it/s]
 65%|██████▌   | 242675/371472 [8:16:33<9:24:57,  3.80it/s]
 65%|██████▌   | 242676/371472 [8:16:33<9:27:15,  3.78it/s]
 65%|██████▌   | 242677/371472 [8:16:34<10:44:49,  3.33it/s]
 65%|██████▌   | 242678/371472 [8:16:34<10:43:50,  3.33it/s]
 65%|██████▌   | 242679/371472 [8:16:34<10:25:53,  3.43it/s]
 65%|██████▌   | 242680/371472 [8:16:35<10:09:03,  3.52it/s]
                                                            
{'loss': 2.9215, 'learning_rate': 4.1220452929388694e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242680/371472 [8:16:35<10:09:03,  3.52it/s]
 65%|██████▌   | 242681/371472 [8:16:35<10:36:06,  3.37it/s]
 65%|██████▌   | 242682/371472 [8:16:35<10:00:32,  3.57it/s]
 65%|██████▌   | 242683/371472 [8:16:36<9:57:19,  3.59it/s] 
 65%|██████▌   | 242684/371472 [8:16:36<9:58:20,  3.59it/s]
 65%|██████▌   | 242685/371472 [8:16:36<10:42:46,  3.34it/s]
 65%|██████▌   | 242686/371472 [8:16:36<10:24:49,  3.44it/s]
 65%|██████▌   | 242687/371472 [8:16:37<10:32:44,  3.39it/s]
 65%|██████▌   | 242688/371472 [8:16:37<10:13:06,  3.50it/s]
 65%|██████▌   | 242689/371472 [8:16:37<9:46:35,  3.66it/s] 
 65%|██████▌   | 242690/371472 [8:16:37<9:45:50,  3.66it/s]
 65%|██████▌   | 242691/371472 [8:16:38<9:34:02,  3.74it/s]
 65%|██████▌   | 242692/371472 [8:16:38<9:33:51,  3.74it/s]
 65%|██████▌   | 242693/371472 [8:16:38<9:16:27,  3.86it/s]
 65%|██████▌   | 242694/371472 [8:16:39<9:11:04,  3.89it/s]
 65%|██████▌   | 242695/371472 [8:16:39<9:34:20,  3.74it/s]
 65%|██████▌   | 242696/371472 [8:16:39<9:17:43,  3.85it/s]
 65%|██████▌   | 242697/371472 [8:16:39<9:10:50,  3.90it/s]
 65%|██████▌   | 242698/371472 [8:16:40<9:51:54,  3.63it/s]
 65%|██████▌   | 242699/371472 [8:16:40<9:38:36,  3.71it/s]
 65%|██████▌   | 242700/371472 [8:16:40<9:19:47,  3.83it/s]
                                                           
{'loss': 2.778, 'learning_rate': 4.12156047318408e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242700/371472 [8:16:40<9:19:47,  3.83it/s]
 65%|██████▌   | 242701/371472 [8:16:40<9:21:56,  3.82it/s]
 65%|██████▌   | 242702/371472 [8:16:41<9:21:14,  3.82it/s]
 65%|██████▌   | 242703/371472 [8:16:41<9:10:54,  3.90it/s]
 65%|██████▌   | 242704/371472 [8:16:41<9:29:06,  3.77it/s]
 65%|██████▌   | 242705/371472 [8:16:41<9:06:36,  3.93it/s]
 65%|██████▌   | 242706/371472 [8:16:42<9:05:46,  3.93it/s]
 65%|██████▌   | 242707/371472 [8:16:42<9:30:56,  3.76it/s]
 65%|██████▌   | 242708/371472 [8:16:42<9:20:10,  3.83it/s]
 65%|██████▌   | 242709/371472 [8:16:42<9:22:08,  3.82it/s]
 65%|██████▌   | 242710/371472 [8:16:43<9:18:16,  3.84it/s]
 65%|██████▌   | 242711/371472 [8:16:43<9:15:40,  3.86it/s]
 65%|██████▌   | 242712/371472 [8:16:43<10:31:18,  3.40it/s]
 65%|██████▌   | 242713/371472 [8:16:44<10:44:24,  3.33it/s]
 65%|██████▌   | 242714/371472 [8:16:44<10:37:28,  3.37it/s]
 65%|██████▌   | 242715/371472 [8:16:44<10:50:42,  3.30it/s]
 65%|██████▌   | 242716/371472 [8:16:45<10:45:26,  3.32it/s]
 65%|██████▌   | 242717/371472 [8:16:45<10:30:45,  3.40it/s]
 65%|██████▌   | 242718/371472 [8:16:45<10:29:13,  3.41it/s]
 65%|██████▌   | 242719/371472 [8:16:45<10:22:12,  3.45it/s]
 65%|██████▌   | 242720/371472 [8:16:46<10:30:32,  3.40it/s]
                                                            
{'loss': 2.8376, 'learning_rate': 4.121075653429292e-07, 'epoch': 10.45}
+
 65%|██████▌   | 242720/371472 [8:16:46<10:30:32,  3.40it/s]
 65%|██████▌   | 242721/371472 [8:16:46<10:13:15,  3.50it/s]
 65%|██████▌   | 242722/371472 [8:16:46<10:06:58,  3.54it/s]
 65%|██████▌   | 242723/371472 [8:16:47<10:13:49,  3.50it/s]
 65%|██████▌   | 242724/371472 [8:16:47<10:41:15,  3.35it/s]
 65%|██████▌   | 242725/371472 [8:16:47<10:12:46,  3.50it/s]
 65%|██████▌   | 242726/371472 [8:16:47<9:53:59,  3.61it/s] 
 65%|██████▌   | 242727/371472 [8:16:48<9:34:16,  3.74it/s]
 65%|██████▌   | 242728/371472 [8:16:48<9:16:14,  3.86it/s]
 65%|██████▌   | 242729/371472 [8:16:48<9:11:32,  3.89it/s]
 65%|██████▌   | 242730/371472 [8:16:48<10:01:48,  3.57it/s]
 65%|██████▌   | 242731/371472 [8:16:49<9:40:01,  3.70it/s] 
 65%|██████▌   | 242732/371472 [8:16:49<9:35:46,  3.73it/s]
 65%|██████▌   | 242733/371472 [8:16:49<9:18:51,  3.84it/s]
 65%|██████▌   | 242734/371472 [8:16:50<10:51:21,  3.29it/s]
 65%|██████▌   | 242735/371472 [8:16:50<10:25:19,  3.43it/s]
 65%|██████▌   | 242736/371472 [8:16:50<10:35:41,  3.38it/s]
 65%|██████▌   | 242737/371472 [8:16:50<9:53:30,  3.62it/s] 
 65%|██████▌   | 242738/371472 [8:16:51<10:10:14,  3.52it/s]
 65%|██████▌   | 242739/371472 [8:16:51<10:38:07,  3.36it/s]
 65%|██████▌   | 242740/371472 [8:16:51<10:38:32,  3.36it/s]
                                                            
{'loss': 2.9757, 'learning_rate': 4.120590833674502e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242740/371472 [8:16:51<10:38:32,  3.36it/s]
 65%|██████▌   | 242741/371472 [8:16:52<10:28:48,  3.41it/s]
 65%|██████▌   | 242742/371472 [8:16:52<10:13:54,  3.49it/s]
 65%|██████▌   | 242743/371472 [8:16:52<10:19:48,  3.46it/s]
 65%|██████▌   | 242744/371472 [8:16:52<10:10:11,  3.52it/s]
 65%|██████▌   | 242745/371472 [8:16:53<10:15:09,  3.49it/s]
 65%|██████▌   | 242746/371472 [8:16:53<9:59:20,  3.58it/s] 
 65%|██████▌   | 242747/371472 [8:16:53<9:53:49,  3.61it/s]
 65%|██████▌   | 242748/371472 [8:16:54<10:18:27,  3.47it/s]
 65%|██████▌   | 242749/371472 [8:16:54<10:00:45,  3.57it/s]
 65%|██████▌   | 242750/371472 [8:16:54<9:38:31,  3.71it/s] 
 65%|██████▌   | 242751/371472 [8:16:54<10:26:59,  3.42it/s]
 65%|██████▌   | 242752/371472 [8:16:55<10:23:23,  3.44it/s]
 65%|██████▌   | 242753/371472 [8:16:55<10:15:48,  3.48it/s]
 65%|██████▌   | 242754/371472 [8:16:55<10:04:42,  3.55it/s]
 65%|██████▌   | 242755/371472 [8:16:56<9:43:32,  3.68it/s] 
 65%|██████▌   | 242756/371472 [8:16:56<9:42:22,  3.68it/s]
 65%|██████▌   | 242757/371472 [8:16:56<9:34:43,  3.73it/s]
 65%|██████▌   | 242758/371472 [8:16:56<9:39:24,  3.70it/s]
 65%|██████▌   | 242759/371472 [8:16:57<9:34:58,  3.73it/s]
 65%|██████▌   | 242760/371472 [8:16:57<10:07:53,  3.53it/s]
                                                            
{'loss': 2.9655, 'learning_rate': 4.120106013919714e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242760/371472 [8:16:57<10:07:53,  3.53it/s]
 65%|██████▌   | 242761/371472 [8:16:57<9:55:03,  3.60it/s] 
 65%|██████▌   | 242762/371472 [8:16:57<9:28:53,  3.77it/s]
 65%|██████▌   | 242763/371472 [8:16:58<9:35:08,  3.73it/s]
 65%|██████▌   | 242764/371472 [8:16:58<10:00:59,  3.57it/s]
 65%|██████▌   | 242765/371472 [8:16:58<10:15:26,  3.49it/s]
 65%|██████▌   | 242766/371472 [8:16:59<9:51:10,  3.63it/s] 
 65%|██████▌   | 242767/371472 [8:16:59<9:42:17,  3.68it/s]
 65%|██████▌   | 242768/371472 [8:16:59<9:30:27,  3.76it/s]
 65%|██████▌   | 242769/371472 [8:16:59<9:49:45,  3.64it/s]
 65%|██████▌   | 242770/371472 [8:17:00<9:28:47,  3.77it/s]
 65%|██████▌   | 242771/371472 [8:17:00<10:09:18,  3.52it/s]
 65%|██████▌   | 242772/371472 [8:17:00<9:44:38,  3.67it/s] 
 65%|██████▌   | 242773/371472 [8:17:00<9:32:41,  3.75it/s]
 65%|██████▌   | 242774/371472 [8:17:01<9:34:03,  3.74it/s]
 65%|██████▌   | 242775/371472 [8:17:01<9:46:50,  3.66it/s]
 65%|██████▌   | 242776/371472 [8:17:01<9:52:57,  3.62it/s]
 65%|██████▌   | 242777/371472 [8:17:02<9:33:47,  3.74it/s]
 65%|██████▌   | 242778/371472 [8:17:02<9:12:14,  3.88it/s]
 65%|██████▌   | 242779/371472 [8:17:02<9:45:06,  3.67it/s]
 65%|██████▌   | 242780/371472 [8:17:02<10:21:51,  3.45it/s]
                                                            
{'loss': 2.9655, 'learning_rate': 4.1196211941649245e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242780/371472 [8:17:02<10:21:51,  3.45it/s]
 65%|██████▌   | 242781/371472 [8:17:03<9:59:12,  3.58it/s] 
 65%|██████▌   | 242782/371472 [8:17:03<10:05:11,  3.54it/s]
 65%|██████▌   | 242783/371472 [8:17:03<10:34:22,  3.38it/s]
 65%|██████▌   | 242784/371472 [8:17:04<10:11:06,  3.51it/s]
 65%|██████▌   | 242785/371472 [8:17:04<10:07:28,  3.53it/s]
 65%|██████▌   | 242786/371472 [8:17:04<9:41:14,  3.69it/s] 
 65%|██████▌   | 242787/371472 [8:17:04<9:42:51,  3.68it/s]
 65%|██████▌   | 242788/371472 [8:17:05<9:36:43,  3.72it/s]
 65%|██████▌   | 242789/371472 [8:17:05<9:30:59,  3.76it/s]
 65%|██████▌   | 242790/371472 [8:17:05<9:24:46,  3.80it/s]
 65%|██████▌   | 242791/371472 [8:17:05<9:43:40,  3.67it/s]
 65%|██████▌   | 242792/371472 [8:17:06<10:39:04,  3.36it/s]
 65%|██████▌   | 242793/371472 [8:17:06<10:02:37,  3.56it/s]
 65%|██████▌   | 242794/371472 [8:17:06<9:44:20,  3.67it/s] 
 65%|██████▌   | 242795/371472 [8:17:07<9:24:10,  3.80it/s]
 65%|██████▌   | 242796/371472 [8:17:07<9:32:57,  3.74it/s]
 65%|██████▌   | 242797/371472 [8:17:07<9:45:29,  3.66it/s]
 65%|██████▌   | 242798/371472 [8:17:07<9:30:37,  3.76it/s]
 65%|██████▌   | 242799/371472 [8:17:08<9:12:43,  3.88it/s]
 65%|██████▌   | 242800/371472 [8:17:08<9:11:37,  3.89it/s]
                                                           
{'loss': 2.9524, 'learning_rate': 4.119136374410136e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242800/371472 [8:17:08<9:11:37,  3.89it/s]
 65%|██████▌   | 242801/371472 [8:17:08<9:02:44,  3.95it/s]
 65%|██████▌   | 242802/371472 [8:17:08<9:28:22,  3.77it/s]
 65%|██████▌   | 242803/371472 [8:17:09<9:18:03,  3.84it/s]
 65%|██████▌   | 242804/371472 [8:17:09<9:18:59,  3.84it/s]
 65%|██████▌   | 242805/371472 [8:17:09<10:20:38,  3.46it/s]
 65%|██████▌   | 242806/371472 [8:17:10<10:26:50,  3.42it/s]
 65%|██████▌   | 242807/371472 [8:17:10<10:50:22,  3.30it/s]
 65%|██████▌   | 242808/371472 [8:17:10<10:14:41,  3.49it/s]
 65%|██████▌   | 242809/371472 [8:17:10<9:46:28,  3.66it/s] 
 65%|██████▌   | 242810/371472 [8:17:11<9:18:53,  3.84it/s]
 65%|██████▌   | 242811/371472 [8:17:11<9:17:52,  3.84it/s]
 65%|██████▌   | 242812/371472 [8:17:11<9:31:09,  3.75it/s]
 65%|██████▌   | 242813/371472 [8:17:11<9:13:17,  3.88it/s]
 65%|██████▌   | 242814/371472 [8:17:12<8:55:29,  4.00it/s]
 65%|██████▌   | 242815/371472 [8:17:12<8:57:15,  3.99it/s]
 65%|██████▌   | 242816/371472 [8:17:12<10:18:22,  3.47it/s]
 65%|██████▌   | 242817/371472 [8:17:12<10:04:24,  3.55it/s]
 65%|██████▌   | 242818/371472 [8:17:13<10:16:09,  3.48it/s]
 65%|██████▌   | 242819/371472 [8:17:13<9:57:32,  3.59it/s] 
 65%|██████▌   | 242820/371472 [8:17:13<9:32:34,  3.74it/s]
                                                           
{'loss': 2.8481, 'learning_rate': 4.1186515546553465e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242820/371472 [8:17:13<9:32:34,  3.74it/s]
 65%|██████▌   | 242821/371472 [8:17:14<9:52:10,  3.62it/s]
 65%|██████▌   | 242822/371472 [8:17:14<9:45:25,  3.66it/s]
 65%|██████▌   | 242823/371472 [8:17:14<9:50:21,  3.63it/s]
 65%|██████▌   | 242824/371472 [8:17:14<9:34:31,  3.73it/s]
 65%|██████▌   | 242825/371472 [8:17:15<9:41:26,  3.69it/s]
 65%|██████▌   | 242826/371472 [8:17:15<9:49:44,  3.64it/s]
 65%|██████▌   | 242827/371472 [8:17:15<10:21:16,  3.45it/s]
 65%|██████▌   | 242828/371472 [8:17:16<10:12:33,  3.50it/s]
 65%|██████▌   | 242829/371472 [8:17:16<9:51:25,  3.63it/s] 
 65%|██████▌   | 242830/371472 [8:17:16<9:49:24,  3.64it/s]
 65%|██████▌   | 242831/371472 [8:17:16<11:17:54,  3.16it/s]
 65%|██████▌   | 242832/371472 [8:17:17<11:11:33,  3.19it/s]
 65%|██████▌   | 242833/371472 [8:17:17<10:47:18,  3.31it/s]
 65%|██████▌   | 242834/371472 [8:17:17<10:16:19,  3.48it/s]
 65%|██████▌   | 242835/371472 [8:17:18<10:23:22,  3.44it/s]
 65%|██████▌   | 242836/371472 [8:17:18<10:23:23,  3.44it/s]
 65%|██████▌   | 242837/371472 [8:17:18<10:17:50,  3.47it/s]
 65%|██████▌   | 242838/371472 [8:17:18<10:08:57,  3.52it/s]
 65%|██████▌   | 242839/371472 [8:17:19<10:03:00,  3.56it/s]
 65%|██████▌   | 242840/371472 [8:17:19<10:47:55,  3.31it/s]
                                                            
{'loss': 2.6331, 'learning_rate': 4.1181667349005583e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242840/371472 [8:17:19<10:47:55,  3.31it/s]
 65%|██████▌   | 242841/371472 [8:17:19<10:39:37,  3.35it/s]
 65%|██████▌   | 242842/371472 [8:17:20<9:59:34,  3.58it/s] 
 65%|██████▌   | 242843/371472 [8:17:20<10:24:20,  3.43it/s]
 65%|██████▌   | 242844/371472 [8:17:20<10:20:51,  3.45it/s]
 65%|██████▌   | 242845/371472 [8:17:20<10:04:37,  3.55it/s]
 65%|██████▌   | 242846/371472 [8:17:21<10:10:33,  3.51it/s]
 65%|██████▌   | 242847/371472 [8:17:21<10:21:31,  3.45it/s]
 65%|██████▌   | 242848/371472 [8:17:21<10:33:35,  3.38it/s]
 65%|██████▌   | 242849/371472 [8:17:22<10:29:30,  3.41it/s]
 65%|██████▌   | 242850/371472 [8:17:22<10:23:44,  3.44it/s]
 65%|██████▌   | 242851/371472 [8:17:22<10:38:56,  3.36it/s]
 65%|██████▌   | 242852/371472 [8:17:23<10:32:39,  3.39it/s]
 65%|██████▌   | 242853/371472 [8:17:23<10:32:46,  3.39it/s]
 65%|██████▌   | 242854/371472 [8:17:23<10:08:42,  3.52it/s]
 65%|██████▌   | 242855/371472 [8:17:23<10:19:59,  3.46it/s]
 65%|██████▌   | 242856/371472 [8:17:24<10:00:42,  3.57it/s]
 65%|██████▌   | 242857/371472 [8:17:24<11:02:51,  3.23it/s]
 65%|██████▌   | 242858/371472 [8:17:24<11:10:17,  3.20it/s]
 65%|██████▌   | 242859/371472 [8:17:25<10:23:54,  3.44it/s]
 65%|██████▌   | 242860/371472 [8:17:25<10:25:23,  3.43it/s]
                                                            
{'loss': 2.7673, 'learning_rate': 4.1176819151457685e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242860/371472 [8:17:25<10:25:23,  3.43it/s]
 65%|██████▌   | 242861/371472 [8:17:25<10:46:16,  3.32it/s]
 65%|██████▌   | 242862/371472 [8:17:26<10:52:56,  3.28it/s]
 65%|██████▌   | 242863/371472 [8:17:26<11:10:15,  3.20it/s]
 65%|██████▌   | 242864/371472 [8:17:26<10:49:07,  3.30it/s]
 65%|██████▌   | 242865/371472 [8:17:26<11:22:46,  3.14it/s]
 65%|██████▌   | 242866/371472 [8:17:27<10:44:35,  3.33it/s]
 65%|██████▌   | 242867/371472 [8:17:27<10:32:01,  3.39it/s]
 65%|██████▌   | 242868/371472 [8:17:27<10:31:45,  3.39it/s]
 65%|██████▌   | 242869/371472 [8:17:28<10:00:25,  3.57it/s]
 65%|██████▌   | 242870/371472 [8:17:28<9:43:29,  3.67it/s] 
 65%|██████▌   | 242871/371472 [8:17:28<9:27:36,  3.78it/s]
 65%|██████▌   | 242872/371472 [8:17:28<10:23:25,  3.44it/s]
 65%|██████▌   | 242873/371472 [8:17:29<10:00:22,  3.57it/s]
 65%|██████▌   | 242874/371472 [8:17:29<9:40:43,  3.69it/s] 
 65%|██████▌   | 242875/371472 [8:17:29<9:29:46,  3.76it/s]
 65%|██████▌   | 242876/371472 [8:17:30<10:36:43,  3.37it/s]
 65%|██████▌   | 242877/371472 [8:17:30<12:17:44,  2.91it/s]
 65%|██████▌   | 242878/371472 [8:17:30<12:13:48,  2.92it/s]
 65%|██████▌   | 242879/371472 [8:17:31<11:15:19,  3.17it/s]
 65%|██████▌   | 242880/371472 [8:17:31<10:32:56,  3.39it/s]
                                                            
{'loss': 2.8594, 'learning_rate': 4.11719709539098e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242880/371472 [8:17:31<10:32:56,  3.39it/s]
 65%|██████▌   | 242881/371472 [8:17:31<10:07:26,  3.53it/s]
 65%|██████▌   | 242882/371472 [8:17:31<9:56:42,  3.59it/s] 
 65%|██████▌   | 242883/371472 [8:17:32<9:51:38,  3.62it/s]
 65%|██████▌   | 242884/371472 [8:17:32<9:34:07,  3.73it/s]
 65%|██████▌   | 242885/371472 [8:17:32<9:53:43,  3.61it/s]
 65%|██████▌   | 242886/371472 [8:17:32<9:44:47,  3.66it/s]
 65%|██████▌   | 242887/371472 [8:17:33<10:15:33,  3.48it/s]
 65%|██████▌   | 242888/371472 [8:17:33<10:10:39,  3.51it/s]
 65%|██████▌   | 242889/371472 [8:17:33<9:55:29,  3.60it/s] 
 65%|██████▌   | 242890/371472 [8:17:34<10:14:56,  3.48it/s]
 65%|██████▌   | 242891/371472 [8:17:34<10:14:39,  3.49it/s]
 65%|██████▌   | 242892/371472 [8:17:34<10:56:33,  3.26it/s]
 65%|██████▌   | 242893/371472 [8:17:35<11:06:59,  3.21it/s]
 65%|██████▌   | 242894/371472 [8:17:35<11:10:09,  3.20it/s]
 65%|██████▌   | 242895/371472 [8:17:35<11:01:12,  3.24it/s]
 65%|██████▌   | 242896/371472 [8:17:36<11:25:20,  3.13it/s]
 65%|██████▌   | 242897/371472 [8:17:36<11:03:29,  3.23it/s]
 65%|██████▌   | 242898/371472 [8:17:36<10:52:40,  3.28it/s]
 65%|██████▌   | 242899/371472 [8:17:36<10:29:54,  3.40it/s]
 65%|██████▌   | 242900/371472 [8:17:37<10:40:54,  3.34it/s]
                                                            
{'loss': 2.8524, 'learning_rate': 4.116712275636191e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242900/371472 [8:17:37<10:40:54,  3.34it/s]
 65%|██████▌   | 242901/371472 [8:17:37<10:16:00,  3.48it/s]
 65%|██████▌   | 242902/371472 [8:17:37<10:02:39,  3.56it/s]
 65%|██████▌   | 242903/371472 [8:17:37<9:37:43,  3.71it/s] 
 65%|██████▌   | 242904/371472 [8:17:38<9:26:37,  3.78it/s]
 65%|██████▌   | 242905/371472 [8:17:38<9:46:53,  3.65it/s]
 65%|██████▌   | 242906/371472 [8:17:38<9:25:21,  3.79it/s]
 65%|██████▌   | 242907/371472 [8:17:39<9:44:42,  3.66it/s]
 65%|██████▌   | 242908/371472 [8:17:39<10:24:41,  3.43it/s]
 65%|██████▌   | 242909/371472 [8:17:39<9:59:58,  3.57it/s] 
 65%|██████▌   | 242910/371472 [8:17:39<10:19:21,  3.46it/s]
 65%|██████▌   | 242911/371472 [8:17:40<10:07:32,  3.53it/s]
 65%|██████▌   | 242912/371472 [8:17:40<10:37:36,  3.36it/s]
 65%|██████▌   | 242913/371472 [8:17:40<10:31:53,  3.39it/s]
 65%|██████▌   | 242914/371472 [8:17:41<10:10:36,  3.51it/s]
 65%|██████▌   | 242915/371472 [8:17:41<9:43:35,  3.67it/s] 
 65%|██████▌   | 242916/371472 [8:17:41<10:22:01,  3.44it/s]
 65%|██████▌   | 242917/371472 [8:17:41<10:09:32,  3.52it/s]
 65%|██████▌   | 242918/371472 [8:17:42<9:45:11,  3.66it/s] 
 65%|██████▌   | 242919/371472 [8:17:42<9:35:57,  3.72it/s]
 65%|██████▌   | 242920/371472 [8:17:42<9:20:18,  3.82it/s]
                                                           
{'loss': 2.9724, 'learning_rate': 4.116227455881402e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242920/371472 [8:17:42<9:20:18,  3.82it/s]
 65%|██████▌   | 242921/371472 [8:17:43<10:24:08,  3.43it/s]
 65%|██████▌   | 242922/371472 [8:17:43<10:28:38,  3.41it/s]
 65%|██████▌   | 242923/371472 [8:17:43<10:07:25,  3.53it/s]
 65%|██████▌   | 242924/371472 [8:17:43<9:55:33,  3.60it/s] 
 65%|██████▌   | 242925/371472 [8:17:44<9:32:43,  3.74it/s]
 65%|██████▌   | 242926/371472 [8:17:44<9:52:17,  3.62it/s]
 65%|██████▌   | 242927/371472 [8:17:44<9:38:17,  3.70it/s]
 65%|██████▌   | 242928/371472 [8:17:44<9:46:53,  3.65it/s]
 65%|██████▌   | 242929/371472 [8:17:45<9:41:44,  3.68it/s]
 65%|██████▌   | 242930/371472 [8:17:45<9:49:08,  3.64it/s]
 65%|██████▌   | 242931/371472 [8:17:45<9:46:33,  3.65it/s]
 65%|██████▌   | 242932/371472 [8:17:46<9:27:51,  3.77it/s]
 65%|██████▌   | 242933/371472 [8:17:46<9:09:28,  3.90it/s]
 65%|██████▌   | 242934/371472 [8:17:46<9:05:24,  3.93it/s]
 65%|██████▌   | 242935/371472 [8:17:46<9:39:08,  3.70it/s]
 65%|██████▌   | 242936/371472 [8:17:47<9:38:44,  3.70it/s]
 65%|██████▌   | 242937/371472 [8:17:47<9:35:40,  3.72it/s]
 65%|██████▌   | 242938/371472 [8:17:47<9:30:56,  3.75it/s]
 65%|██████▌   | 242939/371472 [8:17:47<9:27:47,  3.77it/s]
 65%|██████▌   | 242940/371472 [8:17:48<9:25:26,  3.79it/s]
                                                           
{'loss': 2.7537, 'learning_rate': 4.115742636126613e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242940/371472 [8:17:48<9:25:26,  3.79it/s]
 65%|██████▌   | 242941/371472 [8:17:48<9:28:00,  3.77it/s]
 65%|██████▌   | 242942/371472 [8:17:48<10:35:01,  3.37it/s]
 65%|██████▌   | 242943/371472 [8:17:49<10:10:22,  3.51it/s]
 65%|██████▌   | 242944/371472 [8:17:49<9:49:35,  3.63it/s] 
 65%|██████▌   | 242945/371472 [8:17:49<9:40:25,  3.69it/s]
 65%|██████▌   | 242946/371472 [8:17:49<9:38:16,  3.70it/s]
 65%|██████▌   | 242947/371472 [8:17:50<9:39:23,  3.70it/s]
 65%|██████▌   | 242948/371472 [8:17:50<10:03:10,  3.55it/s]
 65%|██████▌   | 242949/371472 [8:17:50<10:00:26,  3.57it/s]
 65%|██████▌   | 242950/371472 [8:17:50<10:03:53,  3.55it/s]
 65%|██████▌   | 242951/371472 [8:17:51<9:46:01,  3.66it/s] 
 65%|██████▌   | 242952/371472 [8:17:51<9:43:08,  3.67it/s]
 65%|██████▌   | 242953/371472 [8:17:51<10:17:19,  3.47it/s]
 65%|██████▌   | 242954/371472 [8:17:52<10:25:02,  3.43it/s]
 65%|██████▌   | 242955/371472 [8:17:52<10:35:18,  3.37it/s]
 65%|██████▌   | 242956/371472 [8:17:52<10:20:30,  3.45it/s]
 65%|██████▌   | 242957/371472 [8:17:53<11:39:24,  3.06it/s]
 65%|██████▌   | 242958/371472 [8:17:53<11:59:12,  2.98it/s]
 65%|██████▌   | 242959/371472 [8:17:53<12:14:36,  2.92it/s]
 65%|██████▌   | 242960/371472 [8:17:54<11:00:45,  3.24it/s]
                                                            
{'loss': 2.9491, 'learning_rate': 4.1152578163718247e-07, 'epoch': 10.46}
+
 65%|██████▌   | 242960/371472 [8:17:54<11:00:45,  3.24it/s]
 65%|██████▌   | 242961/371472 [8:17:54<11:11:32,  3.19it/s]
 65%|██████▌   | 242962/371472 [8:17:54<10:44:54,  3.32it/s]
 65%|██████▌   | 242963/371472 [8:17:54<10:17:30,  3.47it/s]
 65%|██████▌   | 242964/371472 [8:17:55<10:40:18,  3.34it/s]
 65%|██████▌   | 242965/371472 [8:17:55<9:55:09,  3.60it/s] 
 65%|██████▌   | 242966/371472 [8:17:55<9:43:07,  3.67it/s]
 65%|██████▌   | 242967/371472 [8:17:56<9:56:34,  3.59it/s]
 65%|██████▌   | 242968/371472 [8:17:56<10:03:05,  3.55it/s]
 65%|██████▌   | 242969/371472 [8:17:56<9:48:29,  3.64it/s] 
 65%|██████▌   | 242970/371472 [8:17:56<9:33:40,  3.73it/s]
 65%|██████▌   | 242971/371472 [8:17:57<9:38:44,  3.70it/s]
 65%|██████▌   | 242972/371472 [8:17:57<9:46:37,  3.65it/s]
 65%|██████▌   | 242973/371472 [8:17:57<9:39:07,  3.70it/s]
 65%|██████▌   | 242974/371472 [8:17:57<10:01:44,  3.56it/s]
 65%|██████▌   | 242975/371472 [8:17:58<10:52:41,  3.28it/s]
 65%|██████▌   | 242976/371472 [8:17:58<10:20:04,  3.45it/s]
 65%|██████▌   | 242977/371472 [8:17:58<11:21:27,  3.14it/s]
 65%|██████▌   | 242978/371472 [8:17:59<10:40:18,  3.34it/s]
 65%|██████▌   | 242979/371472 [8:17:59<10:06:04,  3.53it/s]
 65%|██████▌   | 242980/371472 [8:17:59<10:23:54,  3.43it/s]
                                                            
{'loss': 2.7779, 'learning_rate': 4.1147729966170354e-07, 'epoch': 10.47}
+
 65%|██████▌   | 242980/371472 [8:17:59<10:23:54,  3.43it/s]
 65%|██████▌   | 242981/371472 [8:18:00<10:13:28,  3.49it/s]
 65%|██████▌   | 242982/371472 [8:18:00<9:43:46,  3.67it/s] 
 65%|██████▌   | 242983/371472 [8:18:00<9:41:00,  3.69it/s]
 65%|██████▌   | 242984/371472 [8:18:00<9:31:23,  3.75it/s]
 65%|██████▌   | 242985/371472 [8:18:01<10:04:52,  3.54it/s]
 65%|██████▌   | 242986/371472 [8:18:01<10:06:22,  3.53it/s]
 65%|██████▌   | 242987/371472 [8:18:01<10:01:22,  3.56it/s]
 65%|██████▌   | 242988/371472 [8:18:01<9:49:18,  3.63it/s] 
 65%|██████▌   | 242989/371472 [8:18:02<9:31:24,  3.75it/s]
 65%|██████▌   | 242990/371472 [8:18:02<9:52:44,  3.61it/s]
 65%|██████▌   | 242991/371472 [8:18:02<9:33:08,  3.74it/s]
 65%|██████▌   | 242992/371472 [8:18:02<9:39:12,  3.70it/s]
 65%|██████▌   | 242993/371472 [8:18:03<9:51:47,  3.62it/s]
 65%|██████▌   | 242994/371472 [8:18:03<9:41:57,  3.68it/s]
 65%|██████▌   | 242995/371472 [8:18:03<9:32:47,  3.74it/s]
 65%|██████▌   | 242996/371472 [8:18:04<9:58:54,  3.58it/s]
 65%|██████▌   | 242997/371472 [8:18:04<10:17:00,  3.47it/s]
 65%|██████▌   | 242998/371472 [8:18:04<9:58:54,  3.58it/s] 
 65%|██████▌   | 242999/371472 [8:18:04<9:32:01,  3.74it/s]
 65%|██████▌   | 243000/371472 [8:18:05<10:53:14,  3.28it/s]
                                                            
{'loss': 2.7045, 'learning_rate': 4.1142881768622466e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243000/371472 [8:18:05<10:53:14,  3.28it/s]
 65%|██████▌   | 243001/371472 [8:18:05<11:15:23,  3.17it/s]
 65%|██████▌   | 243002/371472 [8:18:05<10:39:22,  3.35it/s]
 65%|██████▌   | 243003/371472 [8:18:06<10:13:42,  3.49it/s]
 65%|██████▌   | 243004/371472 [8:18:06<10:45:37,  3.32it/s]
 65%|██████▌   | 243005/371472 [8:18:06<10:54:04,  3.27it/s]
 65%|██████▌   | 243006/371472 [8:18:07<10:19:34,  3.46it/s]
 65%|██████▌   | 243007/371472 [8:18:07<10:19:46,  3.45it/s]
 65%|██████▌   | 243008/371472 [8:18:07<10:02:43,  3.55it/s]
 65%|██████▌   | 243009/371472 [8:18:07<9:48:51,  3.64it/s] 
 65%|██████▌   | 243010/371472 [8:18:08<9:26:35,  3.78it/s]
 65%|██████▌   | 243011/371472 [8:18:08<9:09:11,  3.90it/s]
 65%|██████▌   | 243012/371472 [8:18:08<8:59:28,  3.97it/s]
 65%|██████▌   | 243013/371472 [8:18:08<9:51:33,  3.62it/s]
 65%|██████▌   | 243014/371472 [8:18:09<9:38:46,  3.70it/s]
 65%|██████▌   | 243015/371472 [8:18:09<9:35:15,  3.72it/s]
 65%|██████▌   | 243016/371472 [8:18:09<9:26:26,  3.78it/s]
 65%|██████▌   | 243017/371472 [8:18:10<10:02:50,  3.55it/s]
 65%|██████▌   | 243018/371472 [8:18:10<10:02:56,  3.55it/s]
 65%|██████▌   | 243019/371472 [8:18:10<9:32:13,  3.74it/s] 
 65%|██████▌   | 243020/371472 [8:18:10<9:36:32,  3.71it/s]
                                                           
{'loss': 2.8686, 'learning_rate': 4.113803357107458e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243020/371472 [8:18:10<9:36:32,  3.71it/s]
 65%|██████▌   | 243021/371472 [8:18:11<9:15:58,  3.85it/s]
 65%|██████▌   | 243022/371472 [8:18:11<9:19:10,  3.83it/s]
 65%|██████▌   | 243023/371472 [8:18:11<9:12:42,  3.87it/s]
 65%|██████▌   | 243024/371472 [8:18:11<9:28:45,  3.76it/s]
 65%|██████▌   | 243025/371472 [8:18:12<9:29:45,  3.76it/s]
 65%|██████▌   | 243026/371472 [8:18:12<9:14:07,  3.86it/s]
 65%|██████▌   | 243027/371472 [8:18:12<8:56:21,  3.99it/s]
 65%|██████▌   | 243028/371472 [8:18:12<9:08:33,  3.90it/s]
 65%|██████▌   | 243029/371472 [8:18:13<9:04:16,  3.93it/s]
 65%|██████▌   | 243030/371472 [8:18:13<9:00:08,  3.96it/s]
 65%|██████▌   | 243031/371472 [8:18:13<10:44:04,  3.32it/s]
 65%|██████▌   | 243032/371472 [8:18:14<10:13:51,  3.49it/s]
 65%|██████▌   | 243033/371472 [8:18:14<9:56:57,  3.59it/s] 
 65%|██████▌   | 243034/371472 [8:18:14<9:57:41,  3.58it/s]
 65%|██████▌   | 243035/371472 [8:18:14<10:01:20,  3.56it/s]
 65%|██████▌   | 243036/371472 [8:18:15<9:53:12,  3.61it/s] 
 65%|██████▌   | 243037/371472 [8:18:15<10:19:03,  3.46it/s]
 65%|██████▌   | 243038/371472 [8:18:15<10:07:34,  3.52it/s]
 65%|██████▌   | 243039/371472 [8:18:15<10:01:15,  3.56it/s]
 65%|██████▌   | 243040/371472 [8:18:16<10:07:24,  3.52it/s]
                                                            
{'loss': 2.8866, 'learning_rate': 4.113318537352669e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243040/371472 [8:18:16<10:07:24,  3.52it/s]
 65%|██████▌   | 243041/371472 [8:18:16<9:59:55,  3.57it/s] 
 65%|██████▌   | 243042/371472 [8:18:16<9:37:15,  3.71it/s]
 65%|██████▌   | 243043/371472 [8:18:17<10:07:43,  3.52it/s]
 65%|██████▌   | 243044/371472 [8:18:17<9:54:53,  3.60it/s] 
 65%|██████▌   | 243045/371472 [8:18:17<10:06:16,  3.53it/s]
 65%|██████▌   | 243046/371472 [8:18:17<9:54:42,  3.60it/s] 
 65%|██████▌   | 243047/371472 [8:18:18<9:38:27,  3.70it/s]
 65%|██████▌   | 243048/371472 [8:18:18<9:51:46,  3.62it/s]
 65%|██████▌   | 243049/371472 [8:18:18<9:53:14,  3.61it/s]
 65%|██████▌   | 243050/371472 [8:18:19<9:56:23,  3.59it/s]
 65%|██████▌   | 243051/371472 [8:18:19<10:16:07,  3.47it/s]
 65%|██████▌   | 243052/371472 [8:18:19<9:50:02,  3.63it/s] 
 65%|██████▌   | 243053/371472 [8:18:19<9:27:22,  3.77it/s]
 65%|██████▌   | 243054/371472 [8:18:20<9:15:15,  3.85it/s]
 65%|██████▌   | 243055/371472 [8:18:20<9:33:57,  3.73it/s]
 65%|██████▌   | 243056/371472 [8:18:20<9:26:13,  3.78it/s]
 65%|██████▌   | 243057/371472 [8:18:20<9:22:30,  3.80it/s]
 65%|██████▌   | 243058/371472 [8:18:21<9:29:07,  3.76it/s]
 65%|██████▌   | 243059/371472 [8:18:21<9:12:08,  3.88it/s]
 65%|██████▌   | 243060/371472 [8:18:21<9:18:42,  3.83it/s]
                                                           
{'loss': 2.9541, 'learning_rate': 4.1128337175978793e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243060/371472 [8:18:21<9:18:42,  3.83it/s]
 65%|██████▌   | 243061/371472 [8:18:21<9:48:54,  3.63it/s]
 65%|██████▌   | 243062/371472 [8:18:22<10:17:24,  3.47it/s]
 65%|██████▌   | 243063/371472 [8:18:22<10:48:07,  3.30it/s]
 65%|██████▌   | 243064/371472 [8:18:22<10:56:34,  3.26it/s]
 65%|██████▌   | 243065/371472 [8:18:23<11:08:23,  3.20it/s]
 65%|██████▌   | 243066/371472 [8:18:23<10:18:22,  3.46it/s]
 65%|██████▌   | 243067/371472 [8:18:23<9:59:24,  3.57it/s] 
 65%|██████▌   | 243068/371472 [8:18:24<9:34:52,  3.72it/s]
 65%|██████▌   | 243069/371472 [8:18:24<9:30:35,  3.75it/s]
 65%|██████▌   | 243070/371472 [8:18:24<9:18:22,  3.83it/s]
 65%|██████▌   | 243071/371472 [8:18:24<9:45:32,  3.65it/s]
 65%|██████▌   | 243072/371472 [8:18:25<9:23:04,  3.80it/s]
 65%|██████▌   | 243073/371472 [8:18:25<9:34:42,  3.72it/s]
 65%|██████▌   | 243074/371472 [8:18:25<9:29:56,  3.75it/s]
 65%|██████▌   | 243075/371472 [8:18:25<9:42:42,  3.67it/s]
 65%|██████▌   | 243076/371472 [8:18:26<10:05:14,  3.54it/s]
 65%|██████▌   | 243077/371472 [8:18:26<9:26:37,  3.78it/s] 
 65%|██████▌   | 243078/371472 [8:18:26<9:23:30,  3.80it/s]
 65%|██████▌   | 243079/371472 [8:18:26<9:32:56,  3.73it/s]
 65%|██████▌   | 243080/371472 [8:18:27<9:57:13,  3.58it/s]
                                                           
{'loss': 2.8343, 'learning_rate': 4.112348897843091e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243080/371472 [8:18:27<9:57:13,  3.58it/s]
 65%|██████▌   | 243081/371472 [8:18:27<10:27:36,  3.41it/s]
 65%|██████▌   | 243082/371472 [8:18:27<9:56:22,  3.59it/s] 
 65%|██████▌   | 243083/371472 [8:18:28<9:54:55,  3.60it/s]
 65%|██████▌   | 243084/371472 [8:18:28<9:34:51,  3.72it/s]
 65%|██████▌   | 243085/371472 [8:18:28<10:01:33,  3.56it/s]
 65%|██████▌   | 243086/371472 [8:18:28<9:59:00,  3.57it/s] 
 65%|██████▌   | 243087/371472 [8:18:29<9:53:00,  3.61it/s]
 65%|██████▌   | 243088/371472 [8:18:29<9:59:13,  3.57it/s]
 65%|██████▌   | 243089/371472 [8:18:29<10:45:16,  3.32it/s]
 65%|██████▌   | 243090/371472 [8:18:30<10:14:09,  3.48it/s]
 65%|██████▌   | 243091/371472 [8:18:30<10:05:50,  3.53it/s]
 65%|██████▌   | 243092/371472 [8:18:30<10:08:49,  3.51it/s]
 65%|██████▌   | 243093/371472 [8:18:30<9:34:46,  3.72it/s] 
 65%|██████▌   | 243094/371472 [8:18:31<9:36:49,  3.71it/s]
 65%|██████▌   | 243095/371472 [8:18:31<10:09:43,  3.51it/s]
 65%|██████▌   | 243096/371472 [8:18:31<10:16:08,  3.47it/s]
 65%|██████▌   | 243097/371472 [8:18:32<10:01:34,  3.56it/s]
 65%|██████▌   | 243098/371472 [8:18:32<10:25:03,  3.42it/s]
 65%|██████▌   | 243099/371472 [8:18:32<10:02:44,  3.55it/s]
 65%|██████▌   | 243100/371472 [8:18:32<9:45:52,  3.65it/s] 
                                                           
{'loss': 2.6936, 'learning_rate': 4.111864078088302e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243100/371472 [8:18:32<9:45:52,  3.65it/s]
 65%|██████▌   | 243101/371472 [8:18:33<9:28:44,  3.76it/s]
 65%|██████▌   | 243102/371472 [8:18:33<9:23:43,  3.80it/s]
 65%|██████▌   | 243103/371472 [8:18:33<9:46:53,  3.65it/s]
 65%|██████▌   | 243104/371472 [8:18:34<10:09:51,  3.51it/s]
 65%|██████▌   | 243105/371472 [8:18:34<9:51:25,  3.62it/s] 
 65%|██████▌   | 243106/371472 [8:18:34<10:17:38,  3.46it/s]
 65%|██████▌   | 243107/371472 [8:18:34<11:11:49,  3.18it/s]
 65%|██████▌   | 243108/371472 [8:18:35<11:55:19,  2.99it/s]
 65%|██████▌   | 243109/371472 [8:18:35<11:41:31,  3.05it/s]
 65%|██████▌   | 243110/371472 [8:18:35<11:16:36,  3.16it/s]
 65%|██████▌   | 243111/371472 [8:18:36<11:08:58,  3.20it/s]
 65%|██████▌   | 243112/371472 [8:18:36<10:31:23,  3.39it/s]
 65%|██████▌   | 243113/371472 [8:18:36<10:02:55,  3.55it/s]
 65%|██████▌   | 243114/371472 [8:18:36<9:48:34,  3.63it/s] 
 65%|██████▌   | 243115/371472 [8:18:37<10:03:43,  3.54it/s]
 65%|██████▌   | 243116/371472 [8:18:37<9:46:38,  3.65it/s] 
 65%|██████▌   | 243117/371472 [8:18:37<9:31:34,  3.74it/s]
 65%|██████▌   | 243118/371472 [8:18:38<9:37:58,  3.70it/s]
 65%|██████▌   | 243119/371472 [8:18:38<9:45:32,  3.65it/s]
 65%|██████▌   | 243120/371472 [8:18:38<9:36:11,  3.71it/s]
                                                           
{'loss': 2.8204, 'learning_rate': 4.111379258333513e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243120/371472 [8:18:38<9:36:11,  3.71it/s]
 65%|██████▌   | 243121/371472 [8:18:38<9:30:57,  3.75it/s]
 65%|██████▌   | 243122/371472 [8:18:39<9:23:56,  3.79it/s]
 65%|██████▌   | 243123/371472 [8:18:39<10:20:41,  3.45it/s]
 65%|██████▌   | 243124/371472 [8:18:39<9:53:50,  3.60it/s] 
 65%|██████▌   | 243125/371472 [8:18:40<9:56:19,  3.59it/s]
 65%|██████▌   | 243126/371472 [8:18:40<10:23:02,  3.43it/s]
 65%|██████▌   | 243127/371472 [8:18:40<10:14:55,  3.48it/s]
 65%|██████▌   | 243128/371472 [8:18:40<10:09:31,  3.51it/s]
 65%|██████▌   | 243129/371472 [8:18:41<11:02:34,  3.23it/s]
 65%|██████▌   | 243130/371472 [8:18:41<11:23:54,  3.13it/s]
 65%|██████▌   | 243131/371472 [8:18:41<10:55:04,  3.27it/s]
 65%|██████▌   | 243132/371472 [8:18:42<10:23:59,  3.43it/s]
 65%|██████▌   | 243133/371472 [8:18:42<10:11:57,  3.50it/s]
 65%|██████▌   | 243134/371472 [8:18:42<10:31:25,  3.39it/s]
 65%|██████▌   | 243135/371472 [8:18:43<10:28:52,  3.40it/s]
 65%|██████▌   | 243136/371472 [8:18:43<10:34:20,  3.37it/s]
 65%|██████▌   | 243137/371472 [8:18:43<10:50:27,  3.29it/s]
 65%|██████▌   | 243138/371472 [8:18:43<10:43:17,  3.32it/s]
 65%|██████▌   | 243139/371472 [8:18:44<10:23:43,  3.43it/s]
 65%|██████▌   | 243140/371472 [8:18:44<10:02:52,  3.55it/s]
                                                            
{'loss': 2.714, 'learning_rate': 4.110894438578724e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243140/371472 [8:18:44<10:02:52,  3.55it/s]
 65%|██████▌   | 243141/371472 [8:18:44<9:48:18,  3.64it/s] 
 65%|██████▌   | 243142/371472 [8:18:45<10:14:42,  3.48it/s]
 65%|██████▌   | 243143/371472 [8:18:45<10:18:29,  3.46it/s]
 65%|██████▌   | 243144/371472 [8:18:45<10:02:33,  3.55it/s]
 65%|██████▌   | 243145/371472 [8:18:45<9:49:57,  3.63it/s] 
 65%|██████▌   | 243146/371472 [8:18:46<10:12:58,  3.49it/s]
 65%|██████▌   | 243147/371472 [8:18:46<10:49:02,  3.30it/s]
 65%|██████▌   | 243148/371472 [8:18:46<10:29:59,  3.39it/s]
 65%|██████▌   | 243149/371472 [8:18:47<10:08:09,  3.52it/s]
 65%|██████▌   | 243150/371472 [8:18:47<10:37:50,  3.35it/s]
 65%|██████▌   | 243151/371472 [8:18:47<10:28:19,  3.40it/s]
 65%|██████▌   | 243152/371472 [8:18:47<10:48:16,  3.30it/s]
 65%|██████▌   | 243153/371472 [8:18:48<10:34:30,  3.37it/s]
 65%|██████▌   | 243154/371472 [8:18:48<10:07:46,  3.52it/s]
 65%|██████▌   | 243155/371472 [8:18:48<10:11:05,  3.50it/s]
 65%|██████▌   | 243156/371472 [8:18:49<9:59:09,  3.57it/s] 
 65%|██████▌   | 243157/371472 [8:18:49<9:35:44,  3.71it/s]
 65%|██████▌   | 243158/371472 [8:18:49<9:44:35,  3.66it/s]
 65%|██████▌   | 243159/371472 [8:18:49<10:21:58,  3.44it/s]
 65%|██████▌   | 243160/371472 [8:18:50<10:32:07,  3.38it/s]
                                                            
{'loss': 2.8031, 'learning_rate': 4.1104096188239345e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243160/371472 [8:18:50<10:32:07,  3.38it/s]
 65%|██████▌   | 243161/371472 [8:18:50<10:11:34,  3.50it/s]
 65%|██████▌   | 243162/371472 [8:18:50<9:56:21,  3.59it/s] 
 65%|██████▌   | 243163/371472 [8:18:51<9:51:57,  3.61it/s]
 65%|██████▌   | 243164/371472 [8:18:51<9:20:50,  3.81it/s]
 65%|██████▌   | 243165/371472 [8:18:51<9:55:57,  3.59it/s]
 65%|██████▌   | 243166/371472 [8:18:51<10:20:57,  3.44it/s]
 65%|██████▌   | 243167/371472 [8:18:52<10:54:30,  3.27it/s]
 65%|██████▌   | 243168/371472 [8:18:52<10:33:15,  3.38it/s]
 65%|██████▌   | 243169/371472 [8:18:52<10:44:56,  3.32it/s]
 65%|██████▌   | 243170/371472 [8:18:53<10:21:41,  3.44it/s]
 65%|██████▌   | 243171/371472 [8:18:53<10:29:50,  3.40it/s]
 65%|██████▌   | 243172/371472 [8:18:53<10:50:52,  3.29it/s]
 65%|██████▌   | 243173/371472 [8:18:53<10:12:51,  3.49it/s]
 65%|██████▌   | 243174/371472 [8:18:54<10:23:20,  3.43it/s]
 65%|██████▌   | 243175/371472 [8:18:54<10:20:24,  3.45it/s]
 65%|██████▌   | 243176/371472 [8:18:54<9:47:48,  3.64it/s] 
 65%|██████▌   | 243177/371472 [8:18:55<9:53:44,  3.60it/s]
 65%|██████▌   | 243178/371472 [8:18:55<10:02:14,  3.55it/s]
 65%|██████▌   | 243179/371472 [8:18:55<9:53:26,  3.60it/s] 
 65%|██████▌   | 243180/371472 [8:18:55<9:42:39,  3.67it/s]
                                                           
{'loss': 2.8777, 'learning_rate': 4.1099247990691457e-07, 'epoch': 10.47}
+
 65%|██████▌   | 243180/371472 [8:18:55<9:42:39,  3.67it/s]
 65%|██████▌   | 243181/371472 [8:18:56<9:22:01,  3.80it/s]
 65%|██████▌   | 243182/371472 [8:18:56<9:14:28,  3.86it/s]
 65%|██████▌   | 243183/371472 [8:18:56<9:13:25,  3.86it/s]
 65%|██████▌   | 243184/371472 [8:18:56<9:10:05,  3.89it/s]
 65%|██████▌   | 243185/371472 [8:18:57<9:30:11,  3.75it/s]
 65%|██████▌   | 243186/371472 [8:18:57<9:21:53,  3.81it/s]
 65%|██████▌   | 243187/371472 [8:18:57<9:00:14,  3.96it/s]
 65%|██████▌   | 243188/371472 [8:18:57<8:59:11,  3.97it/s]
 65%|██████▌   | 243189/371472 [8:18:58<9:20:54,  3.81it/s]
 65%|██████▌   | 243190/371472 [8:18:58<10:23:09,  3.43it/s]
 65%|██████▌   | 243191/371472 [8:18:58<9:46:33,  3.65it/s] 
 65%|██████▌   | 243192/371472 [8:18:59<9:43:18,  3.67it/s]
 65%|██████▌   | 243193/371472 [8:18:59<9:46:59,  3.64it/s]
 65%|██████▌   | 243194/371472 [8:18:59<10:04:24,  3.54it/s]
 65%|██████▌   | 243195/371472 [8:19:00<10:39:01,  3.35it/s]
 65%|██████▌   | 243196/371472 [8:19:00<9:58:39,  3.57it/s] 
 65%|██████▌   | 243197/371472 [8:19:00<10:06:22,  3.53it/s]
 65%|██████▌   | 243198/371472 [8:19:00<10:05:01,  3.53it/s]
 65%|██████▌   | 243199/371472 [8:19:01<9:44:07,  3.66it/s] 
 65%|██████▌   | 243200/371472 [8:19:01<9:41:44,  3.67it/s]
                                                           
{'loss': 2.8353, 'learning_rate': 4.1094399793143564e-07, 'epoch': 10.48}
+
 65%|██████▌   | 243200/371472 [8:19:01<9:41:44,  3.67it/s]
 65%|██████▌   | 243201/371472 [8:19:01<9:31:50,  3.74it/s]
 65%|██████▌   | 243202/371472 [8:19:01<10:11:39,  3.50it/s]
 65%|██████▌   | 243203/371472 [8:19:02<9:49:05,  3.63it/s] 
 65%|██████▌   | 243204/371472 [8:19:02<9:32:28,  3.73it/s]
 65%|██████▌   | 243205/371472 [8:19:02<9:49:02,  3.63it/s]
 65%|██████▌   | 243206/371472 [8:19:02<9:23:42,  3.79it/s]
 65%|██████▌   | 243207/371472 [8:19:03<9:22:09,  3.80it/s]
 65%|██████▌   | 243208/371472 [8:19:03<9:20:27,  3.81it/s]
 65%|██████▌   | 243209/371472 [8:19:03<9:46:52,  3.64it/s]
 65%|██████▌   | 243210/371472 [8:19:04<9:56:39,  3.58it/s]
 65%|██████▌   | 243211/371472 [8:19:04<9:44:44,  3.66it/s]
 65%|██████▌   | 243212/371472 [8:19:04<9:38:49,  3.69it/s]
 65%|██████▌   | 243213/371472 [8:19:04<9:39:59,  3.69it/s]
 65%|██████▌   | 243214/371472 [8:19:05<9:24:18,  3.79it/s]
 65%|██████▌   | 243215/371472 [8:19:05<9:25:32,  3.78it/s]
 65%|██████▌   | 243216/371472 [8:19:05<9:58:53,  3.57it/s]
 65%|██████▌   | 243217/371472 [8:19:05<9:29:56,  3.75it/s]
 65%|██████▌   | 243218/371472 [8:19:06<9:16:43,  3.84it/s]
 65%|██████▌   | 243219/371472 [8:19:06<9:15:12,  3.85it/s]
 65%|██████▌   | 243220/371472 [8:19:06<10:24:51,  3.42it/s]
                                                            
{'loss': 2.8916, 'learning_rate': 4.108955159559568e-07, 'epoch': 10.48}
+
 65%|██████▌   | 243220/371472 [8:19:06<10:24:51,  3.42it/s]
 65%|██████▌   | 243221/371472 [8:19:07<10:29:35,  3.40it/s]
 65%|██████▌   | 243222/371472 [8:19:07<10:17:38,  3.46it/s]
 65%|██████▌   | 243223/371472 [8:19:07<10:21:27,  3.44it/s]
 65%|██████▌   | 243224/371472 [8:19:07<9:45:40,  3.65it/s] 
 65%|██████▌   | 243225/371472 [8:19:08<9:24:09,  3.79it/s]
 65%|██████▌   | 243226/371472 [8:19:08<9:37:39,  3.70it/s]
 65%|██████▌   | 243227/371472 [8:19:08<9:22:09,  3.80it/s]
 65%|██████▌   | 243228/371472 [8:19:08<9:17:17,  3.84it/s]
 65%|██████▌   | 243229/371472 [8:19:09<9:01:40,  3.95it/s]
 65%|██████▌   | 243230/371472 [8:19:09<9:01:11,  3.95it/s]
 65%|██████▌   | 243231/371472 [8:19:09<9:24:16,  3.79it/s]
 65%|██████▌   | 243232/371472 [8:19:09<9:35:09,  3.72it/s]
 65%|██████▌   | 243233/371472 [8:19:10<10:39:11,  3.34it/s]
 65%|██████▌   | 243234/371472 [8:19:10<10:38:25,  3.35it/s]
 65%|██████▌   | 243235/371472 [8:19:10<10:03:23,  3.54it/s]
 65%|██████▌   | 243236/371472 [8:19:11<9:52:33,  3.61it/s] 
 65%|██████▌   | 243237/371472 [8:19:11<9:57:34,  3.58it/s]
 65%|██████▌   | 243238/371472 [8:19:11<9:44:46,  3.65it/s]
 65%|██████▌   | 243239/371472 [8:19:11<9:42:58,  3.67it/s]
 65%|██████▌   | 243240/371472 [8:19:12<9:40:45,  3.68it/s]
                                                           
{'loss': 2.9302, 'learning_rate': 4.1084703398047784e-07, 'epoch': 10.48}
+
 65%|██████▌   | 243240/371472 [8:19:12<9:40:45,  3.68it/s]
 65%|██████▌   | 243241/371472 [8:19:12<9:55:25,  3.59it/s]
 65%|██████▌   | 243242/371472 [8:19:12<9:30:23,  3.75it/s]
 65%|██████▌   | 243243/371472 [8:19:13<9:48:38,  3.63it/s]
 65%|██████▌   | 243244/371472 [8:19:13<9:18:09,  3.83it/s]
 65%|██████▌   | 243245/371472 [8:19:13<9:49:30,  3.63it/s]
 65%|██████▌   | 243246/371472 [8:19:13<10:13:20,  3.48it/s]
 65%|██████▌   | 243247/371472 [8:19:14<9:55:28,  3.59it/s] 
 65%|██████▌   | 243248/371472 [8:19:14<9:52:25,  3.61it/s]
 65%|██████▌   | 243249/371472 [8:19:14<10:35:56,  3.36it/s]
 65%|██████▌   | 243250/371472 [8:19:15<10:06:17,  3.52it/s]
 65%|██████▌   | 243251/371472 [8:19:15<10:07:23,  3.52it/s]
 65%|██████▌   | 243252/371472 [8:19:15<10:04:26,  3.54it/s]
 65%|██████▌   | 243253/371472 [8:19:15<10:13:23,  3.48it/s]
 65%|██████▌   | 243254/371472 [8:19:16<9:44:13,  3.66it/s] 
 65%|██████▌   | 243255/371472 [8:19:16<9:57:21,  3.58it/s]
 65%|██████▌   | 243256/371472 [8:19:16<9:37:29,  3.70it/s]
 65%|██████▌   | 243257/371472 [8:19:17<9:52:08,  3.61it/s]
 65%|██████▌   | 243258/371472 [8:19:17<11:00:03,  3.24it/s]
 65%|██████▌   | 243259/371472 [8:19:17<10:21:25,  3.44it/s]
 65%|██████▌   | 243260/371472 [8:19:17<10:33:32,  3.37it/s]
                                                            
{'loss': 2.8802, 'learning_rate': 4.10798552004999e-07, 'epoch': 10.48}
+
 65%|██████▌   | 243260/371472 [8:19:17<10:33:32,  3.37it/s]
 65%|██████▌   | 243261/371472 [8:19:18<10:58:22,  3.25it/s]
 65%|██████▌   | 243262/371472 [8:19:18<10:25:33,  3.42it/s]
 65%|██████▌   | 243263/371472 [8:19:18<10:02:56,  3.54it/s]
 65%|██████▌   | 243264/371472 [8:19:19<10:12:01,  3.49it/s]
 65%|██████▌   | 243265/371472 [8:19:19<9:37:50,  3.70it/s] 
 65%|██████▌   | 243266/371472 [8:19:19<10:15:55,  3.47it/s]
 65%|██████▌   | 243267/371472 [8:19:19<9:56:09,  3.58it/s] 
 65%|██████▌   | 243268/371472 [8:19:20<9:35:14,  3.71it/s]
 65%|██████▌   | 243269/371472 [8:19:20<10:29:48,  3.39it/s]
 65%|██████▌   | 243270/371472 [8:19:20<10:02:47,  3.54it/s]
 65%|██████▌   | 243271/371472 [8:19:21<10:12:46,  3.49it/s]
 65%|██████▌   | 243272/371472 [8:19:21<10:14:04,  3.48it/s]
 65%|██████▌   | 243273/371472 [8:19:21<9:42:03,  3.67it/s] 
 65%|██████▌   | 243274/371472 [8:19:21<10:05:58,  3.53it/s]
 65%|██████▌   | 243275/371472 [8:19:22<10:01:18,  3.55it/s]
 65%|██████▌   | 243276/371472 [8:19:22<9:39:08,  3.69it/s] 
 65%|██████▌   | 243277/371472 [8:19:22<9:09:16,  3.89it/s]
 65%|██████▌   | 243278/371472 [8:19:22<8:58:00,  3.97it/s]
 65%|██████▌   | 243279/371472 [8:19:23<9:37:09,  3.70it/s]
 65%|██████▌   | 243280/371472 [8:19:23<9:27:14,  3.77it/s]
                                                           
{'loss': 3.0594, 'learning_rate': 4.107500700295201e-07, 'epoch': 10.48}
+
 65%|██████▌   | 243280/371472 [8:19:23<9:27:14,  3.77it/s]
 65%|██████▌   | 243281/371472 [8:19:23<9:42:50,  3.67it/s]
 65%|██████▌   | 243282/371472 [8:19:24<10:09:37,  3.50it/s]
 65%|██████▌   | 243283/371472 [8:19:24<10:52:38,  3.27it/s]
 65%|██████▌   | 243284/371472 [8:19:24<11:06:46,  3.20it/s]
 65%|██████▌   | 243285/371472 [8:19:25<11:02:31,  3.22it/s]
 65%|██████▌   | 243286/371472 [8:19:25<10:15:30,  3.47it/s]
 65%|██████▌   | 243287/371472 [8:19:25<9:42:30,  3.67it/s] 
 65%|██████▌   | 243288/371472 [8:19:25<10:08:01,  3.51it/s]
 65%|██████▌   | 243289/371472 [8:19:26<10:39:54,  3.34it/s]
 65%|██████▌   | 243290/371472 [8:19:26<10:09:39,  3.50it/s]
 65%|██████▌   | 243291/371472 [8:19:26<10:54:53,  3.26it/s]
 65%|██████▌   | 243292/371472 [8:19:27<10:45:55,  3.31it/s]
 65%|██████▌   | 243293/371472 [8:19:27<10:24:26,  3.42it/s]
 65%|██████▌   | 243294/371472 [8:19:27<10:12:10,  3.49it/s]
 65%|██████▌   | 243295/371472 [8:19:27<9:53:03,  3.60it/s] 
 65%|██████▌   | 243296/371472 [8:19:28<9:33:11,  3.73it/s]
 65%|██████▌   | 243297/371472 [8:19:28<9:18:32,  3.82it/s]
 65%|██████▌   | 243298/371472 [8:19:28<9:19:44,  3.82it/s]
 65%|██████▌   | 243299/371472 [8:19:28<9:24:17,  3.79it/s]
 65%|██████▌   | 243300/371472 [8:19:29<9:30:53,  3.74it/s]
                                                           
{'loss': 2.6782, 'learning_rate': 4.107015880540412e-07, 'epoch': 10.48}
+
 65%|██████▌   | 243300/371472 [8:19:29<9:30:53,  3.74it/s]
 65%|██████▌   | 243301/371472 [8:19:29<9:29:18,  3.75it/s]
 65%|██████▌   | 243302/371472 [8:19:29<9:42:16,  3.67it/s]
 65%|██████▌   | 243303/371472 [8:19:30<9:52:12,  3.61it/s]
 65%|██████▌   | 243304/371472 [8:19:30<10:29:13,  3.39it/s]
 65%|██████▌   | 243305/371472 [8:19:30<10:38:01,  3.35it/s]
 65%|██████▌   | 243306/371472 [8:19:30<10:35:03,  3.36it/s]
 65%|██████▌   | 243307/371472 [8:19:31<10:49:14,  3.29it/s]
 65%|██████▌   | 243308/371472 [8:19:31<10:02:10,  3.55it/s]
 65%|██████▌   | 243309/371472 [8:19:31<9:52:44,  3.60it/s] 
 65%|██████▌   | 243310/371472 [8:19:32<9:42:26,  3.67it/s]
 65%|██████▌   | 243311/371472 [8:19:32<9:19:10,  3.82it/s]
 65%|██████▌   | 243312/371472 [8:19:32<9:48:20,  3.63it/s]
 65%|██████▌   | 243313/371472 [8:19:32<9:25:57,  3.77it/s]
 65%|██████▌   | 243314/371472 [8:19:33<9:23:02,  3.79it/s]
 66%|██████▌   | 243315/371472 [8:19:33<9:18:09,  3.83it/s]
 66%|██████▌   | 243316/371472 [8:19:33<10:02:55,  3.54it/s]
 66%|██████▌   | 243317/371472 [8:19:33<10:08:07,  3.51it/s]
 66%|██████▌   | 243318/371472 [8:19:34<9:51:32,  3.61it/s] 
 66%|██████▌   | 243319/371472 [8:19:34<9:44:23,  3.65it/s]
 66%|██████▌   | 243320/371472 [8:19:34<9:37:40,  3.70it/s]
                                                           
{'loss': 2.9102, 'learning_rate': 4.106531060785623e-07, 'epoch': 10.48}
+
 66%|██████▌   | 243320/371472 [8:19:34<9:37:40,  3.70it/s]
 66%|██████▌   | 243321/371472 [8:19:35<10:01:35,  3.55it/s]
 66%|██████▌   | 243322/371472 [8:19:35<10:29:03,  3.40it/s]
 66%|██████▌   | 243323/371472 [8:19:35<10:30:57,  3.39it/s]
 66%|██████▌   | 243324/371472 [8:19:35<10:02:46,  3.54it/s]
 66%|██████▌   | 243325/371472 [8:19:36<9:37:41,  3.70it/s] 
 66%|██████▌   | 243326/371472 [8:19:36<10:45:29,  3.31it/s]
 66%|██████▌   | 243327/371472 [8:19:36<10:43:49,  3.32it/s]
 66%|██████▌   | 243328/371472 [8:19:37<10:06:25,  3.52it/s]
 66%|██████▌   | 243329/371472 [8:19:37<9:47:20,  3.64it/s] 
 66%|██████▌   | 243330/371472 [8:19:37<9:41:40,  3.67it/s]
 66%|██████▌   | 243331/371472 [8:19:37<9:56:19,  3.58it/s]
 66%|██████▌   | 243332/371472 [8:19:38<9:39:21,  3.69it/s]
 66%|██████▌   | 243333/371472 [8:19:38<9:50:29,  3.62it/s]
 66%|██████▌   | 243334/371472 [8:19:38<10:28:48,  3.40it/s]
 66%|██████▌   | 243335/371472 [8:19:39<10:07:18,  3.52it/s]
 66%|██████▌   | 243336/371472 [8:19:39<11:44:41,  3.03it/s]
 66%|██████▌   | 243337/371472 [8:19:39<11:32:35,  3.08it/s]
 66%|██████▌   | 243338/371472 [8:19:40<11:49:20,  3.01it/s]
 66%|██████▌   | 243339/371472 [8:19:40<10:53:33,  3.27it/s]
 66%|██████▌   | 243340/371472 [8:19:40<10:29:41,  3.39it/s]
                                                            
{'loss': 2.685, 'learning_rate': 4.1060462410308346e-07, 'epoch': 10.48}
+
 66%|██████▌   | 243340/371472 [8:19:40<10:29:41,  3.39it/s]
 66%|██████▌   | 243341/371472 [8:19:40<10:13:20,  3.48it/s]
 66%|██████▌   | 243342/371472 [8:19:41<10:19:13,  3.45it/s]
 66%|██████▌   | 243343/371472 [8:19:41<9:45:13,  3.65it/s] 
 66%|██████▌   | 243344/371472 [8:19:41<9:20:09,  3.81it/s]
 66%|██████▌   | 243345/371472 [8:19:41<9:26:41,  3.77it/s]
 66%|██████▌   | 243346/371472 [8:19:42<9:20:07,  3.81it/s]
 66%|██████▌   | 243347/371472 [8:19:42<10:17:53,  3.46it/s]
 66%|██████▌   | 243348/371472 [8:19:42<10:28:43,  3.40it/s]
 66%|██████▌   | 243349/371472 [8:19:43<10:03:28,  3.54it/s]
 66%|██████▌   | 243350/371472 [8:19:43<10:19:40,  3.45it/s]
 66%|██████▌   | 243351/371472 [8:19:43<10:45:39,  3.31it/s]
 66%|██████▌   | 243352/371472 [8:19:44<10:09:03,  3.51it/s]
 66%|██████▌   | 243353/371472 [8:19:44<10:05:42,  3.53it/s]
 66%|██████▌   | 243354/371472 [8:19:44<9:49:42,  3.62it/s] 
 66%|██████▌   | 243355/371472 [8:19:44<9:50:54,  3.61it/s]
 66%|██████▌   | 243356/371472 [8:19:45<10:01:59,  3.55it/s]
 66%|██████▌   | 243357/371472 [8:19:45<9:38:02,  3.69it/s] 
 66%|██████▌   | 243358/371472 [8:19:45<9:57:50,  3.57it/s]
 66%|██████▌   | 243359/371472 [8:19:45<10:11:22,  3.49it/s]
 66%|██████▌   | 243360/371472 [8:19:46<9:49:21,  3.62it/s] 
                                                           
{'loss': 2.769, 'learning_rate': 4.1055614212760453e-07, 'epoch': 10.48}
+
 66%|██████▌   | 243360/371472 [8:19:46<9:49:21,  3.62it/s]
 66%|██████▌   | 243361/371472 [8:19:46<9:52:08,  3.61it/s]
 66%|██████▌   | 243362/371472 [8:19:46<9:38:33,  3.69it/s]
 66%|██████▌   | 243363/371472 [8:19:46<9:21:51,  3.80it/s]
 66%|██████▌   | 243364/371472 [8:19:47<10:22:06,  3.43it/s]
 66%|██████▌   | 243365/371472 [8:19:47<11:06:38,  3.20it/s]
 66%|██████▌   | 243366/371472 [8:19:47<10:32:38,  3.37it/s]
 66%|██████▌   | 243367/371472 [8:19:48<10:07:15,  3.52it/s]
 66%|██████▌   | 243368/371472 [8:19:48<9:57:11,  3.58it/s] 
 66%|██████▌   | 243369/371472 [8:19:48<9:36:59,  3.70it/s]
 66%|██████▌   | 243370/371472 [8:19:48<9:14:52,  3.85it/s]
 66%|██████▌   | 243371/371472 [8:19:49<9:15:41,  3.84it/s]
 66%|██████▌   | 243372/371472 [8:19:49<10:04:20,  3.53it/s]
 66%|██████▌   | 243373/371472 [8:19:49<9:49:21,  3.62it/s] 
 66%|██████▌   | 243374/371472 [8:19:50<9:51:35,  3.61it/s]
 66%|██████▌   | 243375/371472 [8:19:50<9:41:03,  3.67it/s]
 66%|██████▌   | 243376/371472 [8:19:50<9:32:11,  3.73it/s]
 66%|██████▌   | 243377/371472 [8:19:50<9:18:43,  3.82it/s]
 66%|██████▌   | 243378/371472 [8:19:51<9:16:06,  3.84it/s]
 66%|██████▌   | 243379/371472 [8:19:51<9:42:13,  3.67it/s]
 66%|██████▌   | 243380/371472 [8:19:51<9:52:07,  3.61it/s]
                                                           
{'loss': 3.073, 'learning_rate': 4.1050766015212566e-07, 'epoch': 10.48}
+
 66%|██████▌   | 243380/371472 [8:19:51<9:52:07,  3.61it/s]
 66%|██████▌   | 243381/371472 [8:19:52<9:59:15,  3.56it/s]
 66%|██████▌   | 243382/371472 [8:19:52<10:02:44,  3.54it/s]
 66%|██████▌   | 243383/371472 [8:19:52<9:38:03,  3.69it/s] 
 66%|██████▌   | 243384/371472 [8:19:52<9:46:42,  3.64it/s]
 66%|██████▌   | 243385/371472 [8:19:53<9:16:26,  3.84it/s]
 66%|██████▌   | 243386/371472 [8:19:53<8:54:05,  4.00it/s]
 66%|██████▌   | 243387/371472 [8:19:53<9:01:58,  3.94it/s]
 66%|██████▌   | 243388/371472 [8:19:53<9:13:32,  3.86it/s]
 66%|██████▌   | 243389/371472 [8:19:54<9:30:31,  3.74it/s]
 66%|██████▌   | 243390/371472 [8:19:54<9:20:52,  3.81it/s]
 66%|██████▌   | 243391/371472 [8:19:54<9:27:14,  3.76it/s]
 66%|██████▌   | 243392/371472 [8:19:54<9:42:11,  3.67it/s]
 66%|██████▌   | 243393/371472 [8:19:55<10:03:33,  3.54it/s]
 66%|██████▌   | 243394/371472 [8:19:55<12:07:40,  2.93it/s]
 66%|██████▌   | 243395/371472 [8:19:56<11:57:56,  2.97it/s]
 66%|██████▌   | 243396/371472 [8:19:56<11:04:24,  3.21it/s]
 66%|██████▌   | 243397/371472 [8:19:56<11:08:44,  3.19it/s]
 66%|██████▌   | 243398/371472 [8:19:56<10:49:52,  3.28it/s]
 66%|██████▌   | 243399/371472 [8:19:57<10:39:02,  3.34it/s]
 66%|██████▌   | 243400/371472 [8:19:57<10:36:43,  3.35it/s]
                                                            
{'loss': 3.0161, 'learning_rate': 4.1045917817664673e-07, 'epoch': 10.48}
+
 66%|██████▌   | 243400/371472 [8:19:57<10:36:43,  3.35it/s]
 66%|██████▌   | 243401/371472 [8:19:57<11:15:25,  3.16it/s]
 66%|██████▌   | 243402/371472 [8:19:58<10:39:27,  3.34it/s]
 66%|██████▌   | 243403/371472 [8:19:58<10:10:12,  3.50it/s]
 66%|██████▌   | 243404/371472 [8:19:58<9:58:35,  3.57it/s] 
 66%|██████▌   | 243405/371472 [8:19:58<10:18:16,  3.45it/s]
 66%|██████▌   | 243406/371472 [8:19:59<10:43:22,  3.32it/s]
 66%|██████▌   | 243407/371472 [8:19:59<10:06:41,  3.52it/s]
 66%|██████▌   | 243408/371472 [8:19:59<10:33:23,  3.37it/s]
 66%|██████▌   | 243409/371472 [8:20:00<9:51:09,  3.61it/s] 
 66%|██████▌   | 243410/371472 [8:20:00<9:24:51,  3.78it/s]
 66%|██████▌   | 243411/371472 [8:20:00<10:02:28,  3.54it/s]
 66%|██████▌   | 243412/371472 [8:20:00<10:46:17,  3.30it/s]
 66%|██████▌   | 243413/371472 [8:20:01<10:15:09,  3.47it/s]
 66%|██████▌   | 243414/371472 [8:20:01<9:51:17,  3.61it/s] 
 66%|██████▌   | 243415/371472 [8:20:01<9:41:45,  3.67it/s]
 66%|██████▌   | 243416/371472 [8:20:01<9:31:34,  3.73it/s]
 66%|██████▌   | 243417/371472 [8:20:02<9:18:07,  3.82it/s]
 66%|██████▌   | 243418/371472 [8:20:02<9:42:33,  3.66it/s]
 66%|██████▌   | 243419/371472 [8:20:02<9:50:28,  3.61it/s]
 66%|██████▌   | 243420/371472 [8:20:03<9:33:35,  3.72it/s]
                                                           
{'loss': 2.8726, 'learning_rate': 4.104106962011679e-07, 'epoch': 10.48}
+
 66%|██████▌   | 243420/371472 [8:20:03<9:33:35,  3.72it/s]
 66%|██████▌   | 243421/371472 [8:20:03<9:25:12,  3.78it/s]
 66%|██████▌   | 243422/371472 [8:20:03<9:47:48,  3.63it/s]
 66%|██████▌   | 243423/371472 [8:20:03<9:43:50,  3.66it/s]
 66%|██████▌   | 243424/371472 [8:20:04<9:36:47,  3.70it/s]
 66%|██████▌   | 243425/371472 [8:20:04<9:23:11,  3.79it/s]
 66%|██████▌   | 243426/371472 [8:20:04<9:26:05,  3.77it/s]
 66%|██████▌   | 243427/371472 [8:20:04<9:48:14,  3.63it/s]
 66%|██████▌   | 243428/371472 [8:20:05<9:30:33,  3.74it/s]
 66%|██████▌   | 243429/371472 [8:20:05<9:28:39,  3.75it/s]
 66%|██████▌   | 243430/371472 [8:20:05<9:28:39,  3.75it/s]
 66%|██████▌   | 243431/371472 [8:20:06<9:22:58,  3.79it/s]
 66%|██████▌   | 243432/371472 [8:20:06<9:30:05,  3.74it/s]
 66%|██████▌   | 243433/371472 [8:20:06<9:25:00,  3.78it/s]
 66%|██████▌   | 243434/371472 [8:20:06<9:31:36,  3.73it/s]
 66%|██████▌   | 243435/371472 [8:20:07<9:19:37,  3.81it/s]
 66%|██████▌   | 243436/371472 [8:20:07<9:45:32,  3.64it/s]
 66%|██████▌   | 243437/371472 [8:20:07<9:34:25,  3.71it/s]
 66%|██████▌   | 243438/371472 [8:20:07<9:06:26,  3.91it/s]
 66%|██████▌   | 243439/371472 [8:20:08<9:01:33,  3.94it/s]
 66%|██████▌   | 243440/371472 [8:20:08<9:55:07,  3.59it/s]
                                                           
{'loss': 2.704, 'learning_rate': 4.10362214225689e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243440/371472 [8:20:08<9:55:07,  3.59it/s]
 66%|██████▌   | 243441/371472 [8:20:08<9:46:19,  3.64it/s]
 66%|██████▌   | 243442/371472 [8:20:09<10:02:18,  3.54it/s]
 66%|██████▌   | 243443/371472 [8:20:09<10:00:32,  3.55it/s]
 66%|██████▌   | 243444/371472 [8:20:09<9:59:21,  3.56it/s] 
 66%|██████▌   | 243445/371472 [8:20:09<10:07:07,  3.51it/s]
 66%|██████▌   | 243446/371472 [8:20:10<10:14:36,  3.47it/s]
 66%|██████▌   | 243447/371472 [8:20:10<10:16:20,  3.46it/s]
 66%|██████▌   | 243448/371472 [8:20:10<9:57:20,  3.57it/s] 
 66%|██████▌   | 243449/371472 [8:20:10<9:38:47,  3.69it/s]
 66%|██████▌   | 243450/371472 [8:20:11<10:19:29,  3.44it/s]
 66%|██████▌   | 243451/371472 [8:20:11<10:44:54,  3.31it/s]
 66%|██████▌   | 243452/371472 [8:20:11<10:03:18,  3.54it/s]
 66%|██████▌   | 243453/371472 [8:20:12<10:28:27,  3.40it/s]
 66%|██████▌   | 243454/371472 [8:20:12<10:15:38,  3.47it/s]
 66%|██████▌   | 243455/371472 [8:20:12<9:44:01,  3.65it/s] 
 66%|██████▌   | 243456/371472 [8:20:12<9:34:29,  3.71it/s]
 66%|██████▌   | 243457/371472 [8:20:13<9:41:38,  3.67it/s]
 66%|██████▌   | 243458/371472 [8:20:13<9:53:51,  3.59it/s]
 66%|██████▌   | 243459/371472 [8:20:13<9:23:14,  3.79it/s]
 66%|██████▌   | 243460/371472 [8:20:14<10:12:11,  3.49it/s]
                                                            
{'loss': 2.7353, 'learning_rate': 4.103137322502101e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243460/371472 [8:20:14<10:12:11,  3.49it/s]
 66%|██████▌   | 243461/371472 [8:20:14<9:40:38,  3.67it/s] 
 66%|██████▌   | 243462/371472 [8:20:14<9:50:46,  3.61it/s]
 66%|██████▌   | 243463/371472 [8:20:14<10:08:21,  3.51it/s]
 66%|██████▌   | 243464/371472 [8:20:15<10:07:24,  3.51it/s]
 66%|██████▌   | 243465/371472 [8:20:15<10:01:15,  3.55it/s]
 66%|██████▌   | 243466/371472 [8:20:15<11:28:38,  3.10it/s]
 66%|██████▌   | 243467/371472 [8:20:16<11:12:19,  3.17it/s]
 66%|██████▌   | 243468/371472 [8:20:16<11:37:11,  3.06it/s]
 66%|██████▌   | 243469/371472 [8:20:16<11:41:32,  3.04it/s]
 66%|██████▌   | 243470/371472 [8:20:17<10:56:42,  3.25it/s]
 66%|██████▌   | 243471/371472 [8:20:17<11:28:53,  3.10it/s]
 66%|██████▌   | 243472/371472 [8:20:17<10:44:45,  3.31it/s]
 66%|██████▌   | 243473/371472 [8:20:18<10:46:31,  3.30it/s]
 66%|██████▌   | 243474/371472 [8:20:18<10:47:04,  3.30it/s]
 66%|██████▌   | 243475/371472 [8:20:18<10:01:30,  3.55it/s]
 66%|██████▌   | 243476/371472 [8:20:18<10:21:39,  3.43it/s]
 66%|██████▌   | 243477/371472 [8:20:19<10:30:32,  3.38it/s]
 66%|██████▌   | 243478/371472 [8:20:19<10:01:59,  3.54it/s]
 66%|██████▌   | 243479/371472 [8:20:19<10:43:49,  3.31it/s]
 66%|██████▌   | 243480/371472 [8:20:20<10:42:52,  3.32it/s]
                                                            
{'loss': 2.8407, 'learning_rate': 4.102652502747312e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243480/371472 [8:20:20<10:42:52,  3.32it/s]
 66%|██████▌   | 243481/371472 [8:20:20<10:25:04,  3.41it/s]
 66%|██████▌   | 243482/371472 [8:20:20<10:13:44,  3.48it/s]
 66%|██████▌   | 243483/371472 [8:20:20<10:35:25,  3.36it/s]
 66%|██████▌   | 243484/371472 [8:20:21<10:42:24,  3.32it/s]
 66%|██████▌   | 243485/371472 [8:20:21<10:14:06,  3.47it/s]
 66%|██████▌   | 243486/371472 [8:20:21<9:59:25,  3.56it/s] 
 66%|██████▌   | 243487/371472 [8:20:22<9:57:53,  3.57it/s]
 66%|██████▌   | 243488/371472 [8:20:22<9:46:43,  3.64it/s]
 66%|██████▌   | 243489/371472 [8:20:22<9:43:08,  3.66it/s]
 66%|██████▌   | 243490/371472 [8:20:23<10:54:38,  3.26it/s]
 66%|██████▌   | 243491/371472 [8:20:23<10:20:43,  3.44it/s]
 66%|██████▌   | 243492/371472 [8:20:23<10:34:05,  3.36it/s]
 66%|██████▌   | 243493/371472 [8:20:23<10:27:14,  3.40it/s]
 66%|██████▌   | 243494/371472 [8:20:24<10:01:44,  3.54it/s]
 66%|██████▌   | 243495/371472 [8:20:24<9:53:59,  3.59it/s] 
 66%|██████▌   | 243496/371472 [8:20:24<10:30:12,  3.38it/s]
 66%|██████▌   | 243497/371472 [8:20:25<10:21:45,  3.43it/s]
 66%|██████▌   | 243498/371472 [8:20:25<10:14:19,  3.47it/s]
 66%|██████▌   | 243499/371472 [8:20:25<9:48:18,  3.63it/s] 
 66%|██████▌   | 243500/371472 [8:20:25<9:36:38,  3.70it/s]
                                                           
{'loss': 2.8298, 'learning_rate': 4.102167682992523e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243500/371472 [8:20:25<9:36:38,  3.70it/s]
 66%|██████▌   | 243501/371472 [8:20:26<10:28:32,  3.39it/s]
 66%|██████▌   | 243502/371472 [8:20:26<9:47:02,  3.63it/s] 
 66%|██████▌   | 243503/371472 [8:20:26<10:06:26,  3.52it/s]
 66%|██████▌   | 243504/371472 [8:20:26<9:52:51,  3.60it/s] 
 66%|██████▌   | 243505/371472 [8:20:27<9:46:36,  3.64it/s]
 66%|██████▌   | 243506/371472 [8:20:27<11:18:14,  3.14it/s]
 66%|██████▌   | 243507/371472 [8:20:27<10:53:16,  3.26it/s]
 66%|██████▌   | 243508/371472 [8:20:28<10:22:56,  3.42it/s]
 66%|██████▌   | 243509/371472 [8:20:28<10:06:44,  3.52it/s]
 66%|██████▌   | 243510/371472 [8:20:28<10:34:18,  3.36it/s]
 66%|██████▌   | 243511/371472 [8:20:28<9:55:15,  3.58it/s] 
 66%|██████▌   | 243512/371472 [8:20:29<9:53:24,  3.59it/s]
 66%|██████▌   | 243513/371472 [8:20:29<9:40:36,  3.67it/s]
 66%|██████▌   | 243514/371472 [8:20:29<10:16:12,  3.46it/s]
 66%|██████▌   | 243515/371472 [8:20:30<10:17:44,  3.45it/s]
 66%|██████▌   | 243516/371472 [8:20:30<10:28:31,  3.39it/s]
 66%|██████▌   | 243517/371472 [8:20:30<10:26:02,  3.41it/s]
 66%|██████▌   | 243518/371472 [8:20:31<10:04:38,  3.53it/s]
 66%|██████▌   | 243519/371472 [8:20:31<9:49:10,  3.62it/s] 
 66%|██████▌   | 243520/371472 [8:20:31<9:47:56,  3.63it/s]
                                                           
{'loss': 2.8021, 'learning_rate': 4.1016828632377337e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243520/371472 [8:20:31<9:47:56,  3.63it/s]
 66%|██████▌   | 243521/371472 [8:20:31<9:51:44,  3.60it/s]
 66%|██████▌   | 243522/371472 [8:20:32<10:03:21,  3.53it/s]
 66%|██████▌   | 243523/371472 [8:20:32<11:20:54,  3.13it/s]
 66%|██████▌   | 243524/371472 [8:20:32<10:38:11,  3.34it/s]
 66%|██████▌   | 243525/371472 [8:20:33<10:01:02,  3.55it/s]
 66%|██████▌   | 243526/371472 [8:20:33<9:44:41,  3.65it/s] 
 66%|██████▌   | 243527/371472 [8:20:33<10:28:58,  3.39it/s]
 66%|██████▌   | 243528/371472 [8:20:33<10:05:15,  3.52it/s]
 66%|██████▌   | 243529/371472 [8:20:34<9:47:04,  3.63it/s] 
 66%|██████▌   | 243530/371472 [8:20:34<9:35:09,  3.71it/s]
 66%|██████▌   | 243531/371472 [8:20:34<9:38:28,  3.69it/s]
 66%|██████▌   | 243532/371472 [8:20:34<9:31:10,  3.73it/s]
 66%|██████▌   | 243533/371472 [8:20:35<9:36:52,  3.70it/s]
 66%|██████▌   | 243534/371472 [8:20:35<9:46:37,  3.63it/s]
 66%|██████▌   | 243535/371472 [8:20:35<9:32:51,  3.72it/s]
 66%|██████▌   | 243536/371472 [8:20:36<9:33:42,  3.72it/s]
 66%|██████▌   | 243537/371472 [8:20:36<9:19:41,  3.81it/s]
 66%|██████▌   | 243538/371472 [8:20:36<9:37:36,  3.69it/s]
 66%|██████▌   | 243539/371472 [8:20:36<9:11:52,  3.86it/s]
 66%|██████▌   | 243540/371472 [8:20:37<9:03:49,  3.92it/s]
                                                           
{'loss': 2.8826, 'learning_rate': 4.1011980434829455e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243540/371472 [8:20:37<9:03:49,  3.92it/s]
 66%|██████▌   | 243541/371472 [8:20:37<9:16:53,  3.83it/s]
 66%|██████▌   | 243542/371472 [8:20:37<9:25:58,  3.77it/s]
 66%|██████▌   | 243543/371472 [8:20:37<9:26:53,  3.76it/s]
 66%|██████▌   | 243544/371472 [8:20:38<9:12:48,  3.86it/s]
 66%|██████▌   | 243545/371472 [8:20:38<9:18:10,  3.82it/s]
 66%|██████▌   | 243546/371472 [8:20:38<9:52:30,  3.60it/s]
 66%|██████▌   | 243547/371472 [8:20:38<9:34:57,  3.71it/s]
 66%|██████▌   | 243548/371472 [8:20:39<10:22:19,  3.43it/s]
 66%|██████▌   | 243549/371472 [8:20:39<11:01:49,  3.22it/s]
 66%|██████▌   | 243550/371472 [8:20:39<10:30:24,  3.38it/s]
 66%|██████▌   | 243551/371472 [8:20:40<10:40:25,  3.33it/s]
 66%|██████▌   | 243552/371472 [8:20:40<10:32:42,  3.37it/s]
 66%|██████▌   | 243553/371472 [8:20:40<10:46:34,  3.30it/s]
 66%|██████▌   | 243554/371472 [8:20:41<10:18:18,  3.45it/s]
 66%|██████▌   | 243555/371472 [8:20:41<9:55:49,  3.58it/s] 
 66%|██████▌   | 243556/371472 [8:20:41<10:09:42,  3.50it/s]
 66%|██████▌   | 243557/371472 [8:20:41<10:31:18,  3.38it/s]
 66%|██████▌   | 243558/371472 [8:20:42<10:17:56,  3.45it/s]
 66%|██████▌   | 243559/371472 [8:20:42<9:41:59,  3.66it/s] 
 66%|██████▌   | 243560/371472 [8:20:42<9:24:40,  3.78it/s]
                                                           
{'loss': 2.941, 'learning_rate': 4.1007132237281557e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243560/371472 [8:20:42<9:24:40,  3.78it/s]
 66%|██████▌   | 243561/371472 [8:20:42<9:41:06,  3.67it/s]
 66%|██████▌   | 243562/371472 [8:20:43<9:24:37,  3.78it/s]
 66%|██████▌   | 243563/371472 [8:20:43<9:24:50,  3.77it/s]
 66%|██████▌   | 243564/371472 [8:20:43<9:41:08,  3.67it/s]
 66%|██████▌   | 243565/371472 [8:20:44<10:11:48,  3.48it/s]
 66%|██████▌   | 243566/371472 [8:20:44<9:46:07,  3.64it/s] 
 66%|██████▌   | 243567/371472 [8:20:44<9:58:47,  3.56it/s]
 66%|██████▌   | 243568/371472 [8:20:44<9:40:46,  3.67it/s]
 66%|██████▌   | 243569/371472 [8:20:45<9:20:19,  3.80it/s]
 66%|██████▌   | 243570/371472 [8:20:45<9:28:11,  3.75it/s]
 66%|██████▌   | 243571/371472 [8:20:45<9:42:50,  3.66it/s]
 66%|██████▌   | 243572/371472 [8:20:46<10:05:38,  3.52it/s]
 66%|██████▌   | 243573/371472 [8:20:46<9:45:40,  3.64it/s] 
 66%|██████▌   | 243574/371472 [8:20:46<9:21:15,  3.80it/s]
 66%|██████▌   | 243575/371472 [8:20:46<9:42:14,  3.66it/s]
 66%|██████▌   | 243576/371472 [8:20:47<9:33:00,  3.72it/s]
 66%|██████▌   | 243577/371472 [8:20:47<9:33:10,  3.72it/s]
 66%|██████▌   | 243578/371472 [8:20:47<9:28:19,  3.75it/s]
 66%|██████▌   | 243579/371472 [8:20:47<9:13:08,  3.85it/s]
 66%|██████▌   | 243580/371472 [8:20:48<9:27:45,  3.75it/s]
                                                           
{'loss': 2.6722, 'learning_rate': 4.1002284039733674e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243580/371472 [8:20:48<9:27:45,  3.75it/s]
 66%|██████▌   | 243581/371472 [8:20:48<9:29:44,  3.74it/s]
 66%|██████▌   | 243582/371472 [8:20:48<9:57:20,  3.57it/s]
 66%|██████▌   | 243583/371472 [8:20:48<9:43:45,  3.65it/s]
 66%|██████▌   | 243584/371472 [8:20:49<9:29:54,  3.74it/s]
 66%|██████▌   | 243585/371472 [8:20:49<10:29:35,  3.39it/s]
 66%|██████▌   | 243586/371472 [8:20:49<11:49:35,  3.00it/s]
 66%|██████▌   | 243587/371472 [8:20:50<10:59:59,  3.23it/s]
 66%|██████▌   | 243588/371472 [8:20:50<10:32:30,  3.37it/s]
 66%|██████▌   | 243589/371472 [8:20:50<10:23:37,  3.42it/s]
 66%|██████▌   | 243590/371472 [8:20:51<10:43:20,  3.31it/s]
 66%|██████▌   | 243591/371472 [8:20:51<10:42:29,  3.32it/s]
 66%|██████▌   | 243592/371472 [8:20:51<10:08:06,  3.50it/s]
 66%|██████▌   | 243593/371472 [8:20:51<9:45:11,  3.64it/s] 
 66%|██████▌   | 243594/371472 [8:20:52<9:46:57,  3.63it/s]
 66%|██████▌   | 243595/371472 [8:20:52<9:16:37,  3.83it/s]
 66%|██████▌   | 243596/371472 [8:20:52<9:45:50,  3.64it/s]
 66%|██████▌   | 243597/371472 [8:20:52<9:31:23,  3.73it/s]
 66%|██████▌   | 243598/371472 [8:20:53<9:30:04,  3.74it/s]
 66%|██████▌   | 243599/371472 [8:20:53<9:36:07,  3.70it/s]
 66%|██████▌   | 243600/371472 [8:20:53<9:23:31,  3.78it/s]
                                                           
{'loss': 2.7556, 'learning_rate': 4.099743584218578e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243600/371472 [8:20:53<9:23:31,  3.78it/s]
 66%|██████▌   | 243601/371472 [8:20:54<9:26:37,  3.76it/s]
 66%|██████▌   | 243602/371472 [8:20:54<9:14:01,  3.85it/s]
 66%|██████▌   | 243603/371472 [8:20:54<9:45:11,  3.64it/s]
 66%|██████▌   | 243604/371472 [8:20:54<9:27:50,  3.75it/s]
 66%|██████▌   | 243605/371472 [8:20:55<9:23:31,  3.78it/s]
 66%|██████▌   | 243606/371472 [8:20:55<9:26:01,  3.77it/s]
 66%|██████▌   | 243607/371472 [8:20:55<10:12:19,  3.48it/s]
 66%|██████▌   | 243608/371472 [8:20:55<10:02:29,  3.54it/s]
 66%|██████▌   | 243609/371472 [8:20:56<9:52:43,  3.60it/s] 
 66%|██████▌   | 243610/371472 [8:20:56<9:38:45,  3.68it/s]
 66%|██████▌   | 243611/371472 [8:20:56<9:42:08,  3.66it/s]
 66%|██████▌   | 243612/371472 [8:20:57<9:56:14,  3.57it/s]
 66%|██████▌   | 243613/371472 [8:20:57<10:12:14,  3.48it/s]
 66%|██████▌   | 243614/371472 [8:20:57<9:42:01,  3.66it/s] 
 66%|██████▌   | 243615/371472 [8:20:57<9:13:51,  3.85it/s]
 66%|██████▌   | 243616/371472 [8:20:58<9:46:56,  3.63it/s]
 66%|██████▌   | 243617/371472 [8:20:58<10:23:31,  3.42it/s]
 66%|██████▌   | 243618/371472 [8:20:58<10:09:46,  3.49it/s]
 66%|██████▌   | 243619/371472 [8:20:58<9:42:48,  3.66it/s] 
 66%|██████▌   | 243620/371472 [8:20:59<10:44:32,  3.31it/s]
                                                            
{'loss': 2.7902, 'learning_rate': 4.0992587644637894e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243620/371472 [8:20:59<10:44:32,  3.31it/s]
 66%|██████▌   | 243621/371472 [8:20:59<10:27:19,  3.40it/s]
 66%|██████▌   | 243622/371472 [8:20:59<10:07:44,  3.51it/s]
 66%|██████▌   | 243623/371472 [8:21:00<9:51:19,  3.60it/s] 
 66%|██████▌   | 243624/371472 [8:21:00<9:39:35,  3.68it/s]
 66%|██████▌   | 243625/371472 [8:21:00<9:38:21,  3.68it/s]
 66%|██████▌   | 243626/371472 [8:21:01<10:15:18,  3.46it/s]
 66%|██████▌   | 243627/371472 [8:21:01<10:27:23,  3.40it/s]
 66%|██████▌   | 243628/371472 [8:21:01<9:59:25,  3.55it/s] 
 66%|██████▌   | 243629/371472 [8:21:01<9:35:22,  3.70it/s]
 66%|██████▌   | 243630/371472 [8:21:02<10:01:11,  3.54it/s]
 66%|██████▌   | 243631/371472 [8:21:02<9:55:38,  3.58it/s] 
 66%|██████▌   | 243632/371472 [8:21:02<9:47:03,  3.63it/s]
 66%|██████▌   | 243633/371472 [8:21:03<10:26:43,  3.40it/s]
 66%|██████▌   | 243634/371472 [8:21:03<10:05:06,  3.52it/s]
 66%|██████▌   | 243635/371472 [8:21:03<10:26:31,  3.40it/s]
 66%|██████▌   | 243636/371472 [8:21:03<10:04:04,  3.53it/s]
 66%|██████▌   | 243637/371472 [8:21:04<10:14:39,  3.47it/s]
 66%|██████▌   | 243638/371472 [8:21:04<10:17:21,  3.45it/s]
 66%|██████▌   | 243639/371472 [8:21:04<10:26:44,  3.40it/s]
 66%|██████▌   | 243640/371472 [8:21:05<10:04:21,  3.53it/s]
                                                            
{'loss': 2.8128, 'learning_rate': 4.098773944709e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243640/371472 [8:21:05<10:04:21,  3.53it/s]
 66%|██████▌   | 243641/371472 [8:21:05<9:38:00,  3.69it/s] 
 66%|██████▌   | 243642/371472 [8:21:05<10:56:22,  3.25it/s]
 66%|██████▌   | 243643/371472 [8:21:05<10:29:25,  3.38it/s]
 66%|██████▌   | 243644/371472 [8:21:06<10:48:05,  3.29it/s]
 66%|██████▌   | 243645/371472 [8:21:06<10:49:59,  3.28it/s]
 66%|██████▌   | 243646/371472 [8:21:06<10:44:09,  3.31it/s]
 66%|██████▌   | 243647/371472 [8:21:07<11:37:43,  3.05it/s]
 66%|██████▌   | 243648/371472 [8:21:07<10:58:57,  3.23it/s]
 66%|██████▌   | 243649/371472 [8:21:07<11:22:26,  3.12it/s]
 66%|██████▌   | 243650/371472 [8:21:08<11:00:05,  3.23it/s]
 66%|██████▌   | 243651/371472 [8:21:08<10:22:39,  3.42it/s]
 66%|██████▌   | 243652/371472 [8:21:08<9:55:58,  3.57it/s] 
 66%|██████▌   | 243653/371472 [8:21:09<11:09:07,  3.18it/s]
 66%|██████▌   | 243654/371472 [8:21:09<10:34:06,  3.36it/s]
 66%|██████▌   | 243655/371472 [8:21:09<10:01:41,  3.54it/s]
 66%|██████▌   | 243656/371472 [8:21:09<9:46:10,  3.63it/s] 
 66%|██████▌   | 243657/371472 [8:21:10<10:17:36,  3.45it/s]
 66%|██████▌   | 243658/371472 [8:21:10<9:42:35,  3.66it/s] 
 66%|██████▌   | 243659/371472 [8:21:10<9:35:51,  3.70it/s]
 66%|██████▌   | 243660/371472 [8:21:10<9:54:32,  3.58it/s]
                                                           
{'loss': 2.8449, 'learning_rate': 4.098289124954212e-07, 'epoch': 10.49}
+
 66%|██████▌   | 243660/371472 [8:21:10<9:54:32,  3.58it/s]
 66%|██████▌   | 243661/371472 [8:21:11<10:13:48,  3.47it/s]
 66%|██████▌   | 243662/371472 [8:21:11<9:57:34,  3.56it/s] 
 66%|██████▌   | 243663/371472 [8:21:11<10:24:30,  3.41it/s]
 66%|██████▌   | 243664/371472 [8:21:12<9:52:33,  3.59it/s] 
 66%|██████▌   | 243665/371472 [8:21:12<9:45:27,  3.64it/s]
 66%|██████▌   | 243666/371472 [8:21:12<10:15:32,  3.46it/s]
 66%|██████▌   | 243667/371472 [8:21:12<9:46:55,  3.63it/s] 
 66%|██████▌   | 243668/371472 [8:21:13<9:32:16,  3.72it/s]
 66%|██████▌   | 243669/371472 [8:21:13<9:28:04,  3.75it/s]
 66%|██████▌   | 243670/371472 [8:21:13<11:00:04,  3.23it/s]
 66%|██████▌   | 243671/371472 [8:21:14<10:50:38,  3.27it/s]
 66%|██████▌   | 243672/371472 [8:21:14<10:06:04,  3.51it/s]
 66%|██████▌   | 243673/371472 [8:21:14<10:20:50,  3.43it/s]
 66%|██████▌   | 243674/371472 [8:21:14<10:41:39,  3.32it/s]
 66%|██████▌   | 243675/371472 [8:21:15<10:27:57,  3.39it/s]
 66%|██████▌   | 243676/371472 [8:21:15<10:03:13,  3.53it/s]
 66%|██████▌   | 243677/371472 [8:21:15<9:53:54,  3.59it/s] 
 66%|██████▌   | 243678/371472 [8:21:16<9:34:23,  3.71it/s]
 66%|██████▌   | 243679/371472 [8:21:16<9:21:44,  3.79it/s]
 66%|██████▌   | 243680/371472 [8:21:16<9:12:28,  3.86it/s]
                                                           
{'loss': 2.8533, 'learning_rate': 4.097804305199422e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243680/371472 [8:21:16<9:12:28,  3.86it/s]
 66%|██████▌   | 243681/371472 [8:21:16<9:07:45,  3.89it/s]
 66%|██████▌   | 243682/371472 [8:21:17<9:26:31,  3.76it/s]
 66%|██████▌   | 243683/371472 [8:21:17<9:30:10,  3.74it/s]
 66%|██████▌   | 243684/371472 [8:21:17<9:10:21,  3.87it/s]
 66%|██████▌   | 243685/371472 [8:21:17<9:28:29,  3.75it/s]
 66%|██████▌   | 243686/371472 [8:21:18<9:53:24,  3.59it/s]
 66%|██████▌   | 243687/371472 [8:21:18<9:28:22,  3.75it/s]
 66%|██████▌   | 243688/371472 [8:21:18<9:35:10,  3.70it/s]
 66%|██████▌   | 243689/371472 [8:21:18<10:10:42,  3.49it/s]
 66%|██████▌   | 243690/371472 [8:21:19<9:52:15,  3.60it/s] 
 66%|██████▌   | 243691/371472 [8:21:19<10:12:15,  3.48it/s]
 66%|██████▌   | 243692/371472 [8:21:19<10:29:21,  3.38it/s]
 66%|██████▌   | 243693/371472 [8:21:20<10:10:32,  3.49it/s]
 66%|██████▌   | 243694/371472 [8:21:20<10:41:26,  3.32it/s]
 66%|██████▌   | 243695/371472 [8:21:20<10:07:00,  3.51it/s]
 66%|██████▌   | 243696/371472 [8:21:21<10:10:24,  3.49it/s]
 66%|██████▌   | 243697/371472 [8:21:21<9:36:28,  3.69it/s] 
 66%|██████▌   | 243698/371472 [8:21:21<10:57:59,  3.24it/s]
 66%|██████▌   | 243699/371472 [8:21:22<11:24:22,  3.11it/s]
 66%|██████▌   | 243700/371472 [8:21:22<10:38:40,  3.33it/s]
                                                            
{'loss': 2.7845, 'learning_rate': 4.097319485444633e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243700/371472 [8:21:22<10:38:40,  3.33it/s]
 66%|██████▌   | 243701/371472 [8:21:22<9:55:49,  3.57it/s] 
 66%|██████▌   | 243702/371472 [8:21:22<9:40:49,  3.67it/s]
 66%|██████▌   | 243703/371472 [8:21:22<9:15:01,  3.84it/s]
 66%|██████▌   | 243704/371472 [8:21:23<9:29:49,  3.74it/s]
 66%|██████▌   | 243705/371472 [8:21:23<9:32:29,  3.72it/s]
 66%|██████▌   | 243706/371472 [8:21:23<9:31:52,  3.72it/s]
 66%|██████▌   | 243707/371472 [8:21:24<10:02:00,  3.54it/s]
 66%|██████▌   | 243708/371472 [8:21:24<9:46:04,  3.63it/s] 
 66%|██████▌   | 243709/371472 [8:21:24<9:36:09,  3.70it/s]
 66%|██████▌   | 243710/371472 [8:21:24<9:34:29,  3.71it/s]
 66%|██████▌   | 243711/371472 [8:21:25<9:49:00,  3.62it/s]
 66%|██████▌   | 243712/371472 [8:21:25<9:52:21,  3.59it/s]
 66%|██████▌   | 243713/371472 [8:21:25<9:38:22,  3.68it/s]
 66%|██████▌   | 243714/371472 [8:21:25<9:25:13,  3.77it/s]
 66%|██████▌   | 243715/371472 [8:21:26<10:34:17,  3.36it/s]
 66%|██████▌   | 243716/371472 [8:21:26<10:03:37,  3.53it/s]
 66%|██████▌   | 243717/371472 [8:21:26<10:04:07,  3.52it/s]
 66%|██████▌   | 243718/371472 [8:21:27<9:42:48,  3.65it/s] 
 66%|██████▌   | 243719/371472 [8:21:27<10:50:02,  3.28it/s]
 66%|██████▌   | 243720/371472 [8:21:27<10:28:28,  3.39it/s]
                                                            
{'loss': 2.8275, 'learning_rate': 4.0968346656898446e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243720/371472 [8:21:27<10:28:28,  3.39it/s]
 66%|██████▌   | 243721/371472 [8:21:28<10:05:29,  3.52it/s]
 66%|██████▌   | 243722/371472 [8:21:28<9:40:47,  3.67it/s] 
 66%|██████▌   | 243723/371472 [8:21:28<9:38:43,  3.68it/s]
 66%|██████▌   | 243724/371472 [8:21:28<9:30:59,  3.73it/s]
 66%|██████▌   | 243725/371472 [8:21:29<9:16:28,  3.83it/s]
 66%|██████▌   | 243726/371472 [8:21:29<9:21:48,  3.79it/s]
 66%|██████▌   | 243727/371472 [8:21:29<9:21:56,  3.79it/s]
 66%|██████▌   | 243728/371472 [8:21:29<9:14:51,  3.84it/s]
 66%|██████▌   | 243729/371472 [8:21:30<9:32:04,  3.72it/s]
 66%|██████▌   | 243730/371472 [8:21:30<10:12:22,  3.48it/s]
 66%|██████▌   | 243731/371472 [8:21:30<9:47:46,  3.62it/s] 
 66%|██████▌   | 243732/371472 [8:21:31<10:04:35,  3.52it/s]
 66%|██████▌   | 243733/371472 [8:21:31<10:02:43,  3.53it/s]
 66%|██████▌   | 243734/371472 [8:21:31<10:07:37,  3.50it/s]
 66%|██████▌   | 243735/371472 [8:21:31<11:02:50,  3.21it/s]
 66%|██████▌   | 243736/371472 [8:21:32<10:43:37,  3.31it/s]
 66%|██████▌   | 243737/371472 [8:21:32<10:40:36,  3.32it/s]
 66%|██████▌   | 243738/371472 [8:21:32<10:38:28,  3.33it/s]
 66%|██████▌   | 243739/371472 [8:21:33<10:02:16,  3.53it/s]
 66%|██████▌   | 243740/371472 [8:21:33<9:52:41,  3.59it/s] 
                                                           
{'loss': 2.7654, 'learning_rate': 4.0963498459350553e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243740/371472 [8:21:33<9:52:41,  3.59it/s]
 66%|████���█▌   | 243741/371472 [8:21:33<9:55:51,  3.57it/s]
 66%|██████▌   | 243742/371472 [8:21:33<9:43:17,  3.65it/s]
 66%|██████▌   | 243743/371472 [8:21:34<9:59:11,  3.55it/s]
 66%|██████▌   | 243744/371472 [8:21:34<10:43:17,  3.31it/s]
 66%|██████▌   | 243745/371472 [8:21:34<11:12:40,  3.16it/s]
 66%|██████▌   | 243746/371472 [8:21:35<10:25:26,  3.40it/s]
 66%|██████▌   | 243747/371472 [8:21:35<10:26:52,  3.40it/s]
 66%|██████▌   | 243748/371472 [8:21:35<10:00:43,  3.54it/s]
 66%|██████▌   | 243749/371472 [8:21:35<10:05:03,  3.52it/s]
 66%|██████▌   | 243750/371472 [8:21:36<10:26:03,  3.40it/s]
 66%|██████▌   | 243751/371472 [8:21:36<9:59:52,  3.55it/s] 
 66%|██████▌   | 243752/371472 [8:21:36<9:43:23,  3.65it/s]
 66%|██████▌   | 243753/371472 [8:21:37<10:15:58,  3.46it/s]
 66%|██████▌   | 243754/371472 [8:21:37<10:18:53,  3.44it/s]
 66%|██████▌   | 243755/371472 [8:21:37<9:56:02,  3.57it/s] 
 66%|██████▌   | 243756/371472 [8:21:37<9:46:06,  3.63it/s]
 66%|██████▌   | 243757/371472 [8:21:38<9:34:07,  3.71it/s]
 66%|██████▌   | 243758/371472 [8:21:38<9:37:25,  3.69it/s]
 66%|██████▌   | 243759/371472 [8:21:38<9:23:41,  3.78it/s]
 66%|██████▌   | 243760/371472 [8:21:38<9:14:58,  3.84it/s]
                                                           
{'loss': 2.7517, 'learning_rate': 4.0958650261802665e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243760/371472 [8:21:38<9:14:58,  3.84it/s]
 66%|██████▌   | 243761/371472 [8:21:39<9:11:05,  3.86it/s]
 66%|██████▌   | 243762/371472 [8:21:39<9:49:10,  3.61it/s]
 66%|██████▌   | 243763/371472 [8:21:39<9:35:32,  3.70it/s]
 66%|██████▌   | 243764/371472 [8:21:40<9:49:51,  3.61it/s]
 66%|██████▌   | 243765/371472 [8:21:40<10:01:43,  3.54it/s]
 66%|██████▌   | 243766/371472 [8:21:40<9:48:44,  3.62it/s] 
 66%|██████▌   | 243767/371472 [8:21:40<9:49:36,  3.61it/s]
 66%|██████▌   | 243768/371472 [8:21:41<9:35:09,  3.70it/s]
 66%|██████▌   | 243769/371472 [8:21:41<9:24:33,  3.77it/s]
 66%|██████▌   | 243770/371472 [8:21:41<9:31:24,  3.72it/s]
 66%|██████▌   | 243771/371472 [8:21:42<10:08:42,  3.50it/s]
 66%|██████▌   | 243772/371472 [8:21:42<9:38:20,  3.68it/s] 
 66%|██████▌   | 243773/371472 [8:21:42<9:42:01,  3.66it/s]
 66%|██████▌   | 243774/371472 [8:21:42<9:40:34,  3.67it/s]
 66%|██████▌   | 243775/371472 [8:21:43<9:25:51,  3.76it/s]
 66%|██████▌   | 243776/371472 [8:21:43<10:08:08,  3.50it/s]
 66%|██████▌   | 243777/371472 [8:21:43<9:48:31,  3.62it/s] 
 66%|██████▌   | 243778/371472 [8:21:43<10:04:31,  3.52it/s]
 66%|██████▌   | 243779/371472 [8:21:44<9:48:40,  3.62it/s] 
 66%|██████▌   | 243780/371472 [8:21:44<9:56:08,  3.57it/s]
                                                           
{'loss': 3.142, 'learning_rate': 4.095380206425477e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243780/371472 [8:21:44<9:56:08,  3.57it/s]
 66%|██████▌   | 243781/371472 [8:21:44<9:50:31,  3.60it/s]
 66%|██████▌   | 243782/371472 [8:21:45<10:13:29,  3.47it/s]
 66%|██████▌   | 243783/371472 [8:21:45<10:07:24,  3.50it/s]
 66%|██████▌   | 243784/371472 [8:21:45<10:17:01,  3.45it/s]
 66%|██████▌   | 243785/371472 [8:21:45<9:58:18,  3.56it/s] 
 66%|██████▌   | 243786/371472 [8:21:46<9:52:48,  3.59it/s]
 66%|██████▌   | 243787/371472 [8:21:46<9:39:18,  3.67it/s]
 66%|██████▌   | 243788/371472 [8:21:46<9:20:24,  3.80it/s]
 66%|██████▌   | 243789/371472 [8:21:46<9:10:05,  3.87it/s]
 66%|██████▌   | 243790/371472 [8:21:47<9:08:22,  3.88it/s]
 66%|██████▌   | 243791/371472 [8:21:47<9:13:15,  3.85it/s]
 66%|██████▌   | 243792/371472 [8:21:47<9:45:23,  3.64it/s]
 66%|██████▌   | 243793/371472 [8:21:48<9:58:19,  3.56it/s]
 66%|██████▌   | 243794/371472 [8:21:48<10:05:48,  3.51it/s]
 66%|██████▌   | 243795/371472 [8:21:48<9:44:49,  3.64it/s] 
 66%|██████▌   | 243796/371472 [8:21:48<9:54:03,  3.58it/s]
 66%|██████▌   | 243797/371472 [8:21:49<9:41:28,  3.66it/s]
 66%|██████▌   | 243798/371472 [8:21:49<9:13:55,  3.84it/s]
 66%|██████▌   | 243799/371472 [8:21:49<9:12:49,  3.85it/s]
 66%|██████▌   | 243800/371472 [8:21:49<9:18:20,  3.81it/s]
                                                           
{'loss': 2.8274, 'learning_rate': 4.094895386670689e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243800/371472 [8:21:49<9:18:20,  3.81it/s]
 66%|██████▌   | 243801/371472 [8:21:50<10:04:57,  3.52it/s]
 66%|██████▌   | 243802/371472 [8:21:50<9:29:28,  3.74it/s] 
 66%|██████▌   | 243803/371472 [8:21:50<9:13:53,  3.84it/s]
 66%|██████▌   | 243804/371472 [8:21:50<8:59:10,  3.95it/s]
 66%|██████▌   | 243805/371472 [8:21:51<9:18:36,  3.81it/s]
 66%|██████▌   | 243806/371472 [8:21:51<9:22:22,  3.78it/s]
 66%|██████▌   | 243807/371472 [8:21:51<9:10:26,  3.87it/s]
 66%|██████▌   | 243808/371472 [8:21:52<9:17:20,  3.82it/s]
 66%|██████▌   | 243809/371472 [8:21:52<9:43:45,  3.64it/s]
 66%|██████▌   | 243810/371472 [8:21:52<9:14:51,  3.83it/s]
 66%|██████▌   | 243811/371472 [8:21:52<9:39:42,  3.67it/s]
 66%|██████▌   | 243812/371472 [8:21:53<9:29:36,  3.74it/s]
 66%|██████▌   | 243813/371472 [8:21:53<9:28:41,  3.74it/s]
 66%|██████▌   | 243814/371472 [8:21:53<9:18:02,  3.81it/s]
 66%|██████▌   | 243815/371472 [8:21:53<9:26:18,  3.76it/s]
 66%|██████▌   | 243816/371472 [8:21:54<9:46:36,  3.63it/s]
 66%|██████▌   | 243817/371472 [8:21:54<10:15:08,  3.46it/s]
 66%|██████▌   | 243818/371472 [8:21:54<10:45:31,  3.30it/s]
 66%|██████▌   | 243819/371472 [8:21:55<10:56:25,  3.24it/s]
 66%|██████▌   | 243820/371472 [8:21:55<10:26:16,  3.40it/s]
                                                            
{'loss': 2.918, 'learning_rate': 4.094410566915899e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243820/371472 [8:21:55<10:26:16,  3.40it/s]
 66%|██████▌   | 243821/371472 [8:21:55<9:56:01,  3.57it/s] 
 66%|██████▌   | 243822/371472 [8:21:55<9:36:53,  3.69it/s]
 66%|██████▌   | 243823/371472 [8:21:56<9:34:52,  3.70it/s]
 66%|██████▌   | 243824/371472 [8:21:56<9:15:20,  3.83it/s]
 66%|██████▌   | 243825/371472 [8:21:56<9:20:21,  3.80it/s]
 66%|██████▌   | 243826/371472 [8:21:56<9:15:34,  3.83it/s]
 66%|██████▌   | 243827/371472 [8:21:57<9:37:06,  3.69it/s]
 66%|██████▌   | 243828/371472 [8:21:57<9:23:00,  3.78it/s]
 66%|██████▌   | 243829/371472 [8:21:57<9:15:07,  3.83it/s]
 66%|██████▌   | 243830/371472 [8:21:58<11:07:44,  3.19it/s]
 66%|██████▌   | 243831/371472 [8:21:58<10:36:26,  3.34it/s]
 66%|██████▌   | 243832/371472 [8:21:58<10:10:57,  3.48it/s]
 66%|██████▌   | 243833/371472 [8:21:59<10:09:52,  3.49it/s]
 66%|██████▌   | 243834/371472 [8:21:59<10:19:26,  3.43it/s]
 66%|██████▌   | 243835/371472 [8:21:59<10:18:53,  3.44it/s]
 66%|██████▌   | 243836/371472 [8:21:59<9:57:51,  3.56it/s] 
 66%|██████▌   | 243837/371472 [8:22:00<9:53:23,  3.58it/s]
 66%|██████▌   | 243838/371472 [8:22:00<9:41:43,  3.66it/s]
 66%|██████▌   | 243839/371472 [8:22:00<9:13:57,  3.84it/s]
 66%|██████▌   | 243840/371472 [8:22:00<9:45:28,  3.63it/s]
                                                           
{'loss': 2.8593, 'learning_rate': 4.093925747161111e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243840/371472 [8:22:00<9:45:28,  3.63it/s]
 66%|██████▌   | 243841/371472 [8:22:01<9:59:41,  3.55it/s]
 66%|██████▌   | 243842/371472 [8:22:01<9:50:39,  3.60it/s]
 66%|██████▌   | 243843/371472 [8:22:01<10:04:19,  3.52it/s]
 66%|██████▌   | 243844/371472 [8:22:02<10:16:33,  3.45it/s]
 66%|██████▌   | 243845/371472 [8:22:02<9:58:57,  3.55it/s] 
 66%|██████▌   | 243846/371472 [8:22:02<10:26:05,  3.40it/s]
 66%|██████▌   | 243847/371472 [8:22:02<9:58:19,  3.56it/s] 
 66%|██████▌   | 243848/371472 [8:22:03<9:56:08,  3.57it/s]
 66%|██████▌   | 243849/371472 [8:22:03<10:31:30,  3.37it/s]
 66%|██████▌   | 243850/371472 [8:22:03<10:40:40,  3.32it/s]
 66%|██████▌   | 243851/371472 [8:22:04<10:00:57,  3.54it/s]
 66%|██████▌   | 243852/371472 [8:22:04<10:26:18,  3.40it/s]
 66%|██████▌   | 243853/371472 [8:22:04<10:25:54,  3.40it/s]
 66%|██████▌   | 243854/371472 [8:22:05<10:10:10,  3.49it/s]
 66%|██████▌   | 243855/371472 [8:22:05<9:44:17,  3.64it/s] 
 66%|██████▌   | 243856/371472 [8:22:05<9:22:27,  3.78it/s]
 66%|██████▌   | 243857/371472 [8:22:05<9:29:40,  3.73it/s]
 66%|██████▌   | 243858/371472 [8:22:06<9:20:27,  3.79it/s]
 66%|██████▌   | 243859/371472 [8:22:06<9:19:27,  3.80it/s]
 66%|██████▌   | 243860/371472 [8:22:06<10:02:38,  3.53it/s]
                                                            
{'loss': 2.8557, 'learning_rate': 4.093440927406321e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243860/371472 [8:22:06<10:02:38,  3.53it/s]
 66%|██████▌   | 243861/371472 [8:22:06<10:18:47,  3.44it/s]
 66%|██████▌   | 243862/371472 [8:22:07<10:09:17,  3.49it/s]
 66%|██████▌   | 243863/371472 [8:22:07<10:05:43,  3.51it/s]
 66%|██████▌   | 243864/371472 [8:22:07<10:13:04,  3.47it/s]
 66%|██████▌   | 243865/371472 [8:22:08<10:06:53,  3.50it/s]
 66%|██████▌   | 243866/371472 [8:22:08<10:04:51,  3.52it/s]
 66%|██████▌   | 243867/371472 [8:22:08<10:22:09,  3.42it/s]
 66%|██████▌   | 243868/371472 [8:22:08<10:37:29,  3.34it/s]
 66%|██████▌   | 243869/371472 [8:22:09<10:09:14,  3.49it/s]
 66%|██████▌   | 243870/371472 [8:22:09<9:54:23,  3.58it/s] 
 66%|██████▌   | 243871/371472 [8:22:09<10:09:16,  3.49it/s]
 66%|██████▌   | 243872/371472 [8:22:10<10:03:46,  3.52it/s]
 66%|██████▌   | 243873/371472 [8:22:10<9:29:22,  3.74it/s] 
 66%|██████▌   | 243874/371472 [8:22:10<9:41:02,  3.66it/s]
 66%|██████▌   | 243875/371472 [8:22:10<9:30:25,  3.73it/s]
 66%|██████▌   | 243876/371472 [8:22:11<9:56:07,  3.57it/s]
 66%|██████▌   | 243877/371472 [8:22:11<11:14:54,  3.15it/s]
 66%|██████▌   | 243878/371472 [8:22:11<12:12:54,  2.90it/s]
 66%|██████▌   | 243879/371472 [8:22:12<11:33:38,  3.07it/s]
 66%|██████▌   | 243880/371472 [8:22:12<10:50:42,  3.27it/s]
                                                            
{'loss': 2.8169, 'learning_rate': 4.092956107651533e-07, 'epoch': 10.5}
+
 66%|██████▌   | 243880/371472 [8:22:12<10:50:42,  3.27it/s]
 66%|██████▌   | 243881/371472 [8:22:12<10:19:41,  3.43it/s]
 66%|██████▌   | 243882/371472 [8:22:13<10:27:34,  3.39it/s]
 66%|██████▌   | 243883/371472 [8:22:13<10:52:57,  3.26it/s]
 66%|██████▌   | 243884/371472 [8:22:13<11:46:03,  3.01it/s]
 66%|██████▌   | 243885/371472 [8:22:14<10:45:15,  3.30it/s]
 66%|██████▌   | 243886/371472 [8:22:14<10:47:38,  3.28it/s]
 66%|██████▌   | 243887/371472 [8:22:14<11:11:58,  3.16it/s]
 66%|██████▌   | 243888/371472 [8:22:15<11:17:46,  3.14it/s]
 66%|██████▌   | 243889/371472 [8:22:15<10:52:00,  3.26it/s]
 66%|██████▌   | 243890/371472 [8:22:15<10:31:21,  3.37it/s]
 66%|██████▌   | 243891/371472 [8:22:15<10:07:58,  3.50it/s]
 66%|██████▌   | 243892/371472 [8:22:16<9:56:28,  3.56it/s] 
 66%|██████▌   | 243893/371472 [8:22:16<9:36:05,  3.69it/s]
 66%|██████▌   | 243894/371472 [8:22:16<9:41:15,  3.66it/s]
 66%|██████▌   | 243895/371472 [8:22:16<9:58:05,  3.56it/s]
 66%|██████▌   | 243896/371472 [8:22:17<10:58:18,  3.23it/s]
 66%|██████▌   | 243897/371472 [8:22:17<10:17:00,  3.45it/s]
 66%|██████▌   | 243898/371472 [8:22:17<9:54:37,  3.58it/s] 
 66%|██████▌   | 243899/371472 [8:22:18<10:34:06,  3.35it/s]
 66%|██████▌   | 243900/371472 [8:22:18<10:04:47,  3.52it/s]
                                                            
{'loss': 2.7588, 'learning_rate': 4.0924712878967436e-07, 'epoch': 10.51}
+
 66%|██████▌   | 243900/371472 [8:22:18<10:04:47,  3.52it/s]
 66%|██████▌   | 243901/371472 [8:22:18<9:48:00,  3.62it/s] 
 66%|██████▌   | 243902/371472 [8:22:18<9:18:08,  3.81it/s]
 66%|██████▌   | 243903/371472 [8:22:19<10:13:24,  3.47it/s]
 66%|██████▌   | 243904/371472 [8:22:19<9:41:06,  3.66it/s] 
 66%|██████▌   | 243905/371472 [8:22:19<9:46:49,  3.62it/s]
 66%|██████▌   | 243906/371472 [8:22:19<9:31:18,  3.72it/s]
 66%|██████▌   | 243907/371472 [8:22:20<9:19:56,  3.80it/s]
 66%|██████▌   | 243908/371472 [8:22:20<9:32:30,  3.71it/s]
 66%|██████▌   | 243909/371472 [8:22:20<9:58:46,  3.55it/s]
 66%|██████▌   | 243910/371472 [8:22:21<9:46:22,  3.63it/s]
 66%|██████▌   | 243911/371472 [8:22:21<10:04:59,  3.51it/s]
 66%|██████▌   | 243912/371472 [8:22:21<10:10:08,  3.48it/s]
 66%|██████▌   | 243913/371472 [8:22:21<10:10:29,  3.48it/s]
 66%|██████▌   | 243914/371472 [8:22:22<9:38:47,  3.67it/s] 
 66%|██████▌   | 243915/371472 [8:22:22<9:27:24,  3.75it/s]
 66%|██████▌   | 243916/371472 [8:22:22<9:52:30,  3.59it/s]
 66%|██████▌   | 243917/371472 [8:22:23<9:30:27,  3.73it/s]
 66%|██████▌   | 243918/371472 [8:22:23<9:34:33,  3.70it/s]
 66%|██████▌   | 243919/371472 [8:22:23<9:14:32,  3.83it/s]
 66%|██████▌   | 243920/371472 [8:22:23<9:04:39,  3.90it/s]
                                                           
{'loss': 2.7523, 'learning_rate': 4.0919864681419554e-07, 'epoch': 10.51}
+
 66%|██████▌   | 243920/371472 [8:22:23<9:04:39,  3.90it/s]
 66%|██████▌   | 243921/371472 [8:22:24<9:09:16,  3.87it/s]
 66%|██████▌   | 243922/371472 [8:22:24<9:39:43,  3.67it/s]
 66%|██████▌   | 243923/371472 [8:22:24<9:30:42,  3.72it/s]
 66%|██████▌   | 243924/371472 [8:22:24<9:09:06,  3.87it/s]
 66%|██████▌   | 243925/371472 [8:22:25<9:28:36,  3.74it/s]
 66%|██████▌   | 243926/371472 [8:22:25<10:24:07,  3.41it/s]
 66%|██████▌   | 243927/371472 [8:22:25<10:12:54,  3.47it/s]
 66%|██████▌   | 243928/371472 [8:22:26<9:47:52,  3.62it/s] 
 66%|██████▌   | 243929/371472 [8:22:26<10:16:11,  3.45it/s]
 66%|██████▌   | 243930/371472 [8:22:26<9:57:38,  3.56it/s] 
 66%|██████▌   | 243931/371472 [8:22:26<9:38:55,  3.67it/s]
 66%|██████▌   | 243932/371472 [8:22:27<9:29:48,  3.73it/s]
 66%|██████▌   | 243933/371472 [8:22:27<9:46:18,  3.63it/s]
 66%|██████▌   | 243934/371472 [8:22:27<9:24:22,  3.77it/s]
 66%|██████▌   | 243935/371472 [8:22:27<9:15:33,  3.83it/s]
 66%|██████▌   | 243936/371472 [8:22:28<9:21:49,  3.78it/s]
 66%|██████▌   | 243937/371472 [8:22:28<11:09:50,  3.17it/s]
 66%|██████▌   | 243938/371472 [8:22:28<10:45:29,  3.29it/s]
 66%|██████▌   | 243939/371472 [8:22:29<10:21:36,  3.42it/s]
 66%|██████▌   | 243940/371472 [8:22:29<10:33:11,  3.36it/s]
                                                            
{'loss': 2.9415, 'learning_rate': 4.0915016483871656e-07, 'epoch': 10.51}
+
 66%|██████▌   | 243940/371472 [8:22:29<10:33:11,  3.36it/s]
 66%|██████▌   | 243941/371472 [8:22:29<10:11:27,  3.48it/s]
 66%|██████▌   | 243942/371472 [8:22:30<10:12:03,  3.47it/s]
 66%|██████▌   | 243943/371472 [8:22:30<10:00:43,  3.54it/s]
 66%|██████▌   | 243944/371472 [8:22:30<10:03:38,  3.52it/s]
 66%|██████▌   | 243945/371472 [8:22:30<9:38:05,  3.68it/s] 
 66%|██████▌   | 243946/371472 [8:22:31<10:26:50,  3.39it/s]
 66%|██████▌   | 243947/371472 [8:22:31<10:02:42,  3.53it/s]
 66%|██████▌   | 243948/371472 [8:22:31<9:41:47,  3.65it/s] 
 66%|██████▌   | 243949/371472 [8:22:31<9:30:56,  3.72it/s]
 66%|██████▌   | 243950/371472 [8:22:32<9:04:15,  3.91it/s]
 66%|██████▌   | 243951/371472 [8:22:32<9:08:43,  3.87it/s]
 66%|██████▌   | 243952/371472 [8:22:32<9:15:44,  3.82it/s]
 66%|██████▌   | 243953/371472 [8:22:32<9:38:20,  3.67it/s]
 66%|██████▌   | 243954/371472 [8:22:33<9:27:29,  3.75it/s]
 66%|██████▌   | 243955/371472 [8:22:33<10:09:31,  3.49it/s]
 66%|██████▌   | 243956/371472 [8:22:33<10:24:53,  3.40it/s]
 66%|██████▌   | 243957/371472 [8:22:34<10:17:52,  3.44it/s]
 66%|██████▌   | 243958/371472 [8:22:34<10:08:40,  3.49it/s]
 66%|██████▌   | 243959/371472 [8:22:34<10:00:10,  3.54it/s]
 66%|██████▌   | 243960/371472 [8:22:34<9:32:54,  3.71it/s] 
                                                           
{'loss': 2.8765, 'learning_rate': 4.0910168286323774e-07, 'epoch': 10.51}
+
 66%|██████▌   | 243960/371472 [8:22:34<9:32:54,  3.71it/s]
 66%|██████▌   | 243961/371472 [8:22:35<9:12:01,  3.85it/s]
 66%|██████▌   | 243962/371472 [8:22:35<9:11:44,  3.85it/s]
 66%|██████▌   | 243963/371472 [8:22:35<9:03:40,  3.91it/s]
 66%|██████▌   | 243964/371472 [8:22:35<9:22:09,  3.78it/s]
 66%|██████▌   | 243965/371472 [8:22:36<9:19:03,  3.80it/s]
 66%|██████▌   | 243966/371472 [8:22:36<9:11:31,  3.85it/s]
 66%|██████▌   | 243967/371472 [8:22:36<9:07:56,  3.88it/s]
 66%|██████▌   | 243968/371472 [8:22:37<9:30:35,  3.72it/s]
 66%|██████▌   | 243969/371472 [8:22:37<10:15:24,  3.45it/s]
 66%|██████▌   | 243970/371472 [8:22:37<10:03:50,  3.52it/s]
 66%|██████▌   | 243971/371472 [8:22:37<10:02:53,  3.52it/s]
 66%|██████▌   | 243972/371472 [8:22:38<9:29:24,  3.73it/s] 
 66%|██████▌   | 243973/371472 [8:22:38<9:24:07,  3.77it/s]
 66%|██████▌   | 243974/371472 [8:22:38<9:00:06,  3.93it/s]
 66%|██████▌   | 243975/371472 [8:22:38<9:01:24,  3.92it/s]
 66%|██████▌   | 243976/371472 [8:22:39<9:04:00,  3.91it/s]
 66%|██████▌   | 243977/371472 [8:22:39<8:56:47,  3.96it/s]
 66%|██████▌   | 243978/371472 [8:22:39<8:43:44,  4.06it/s]
 66%|██████▌   | 243979/371472 [8:22:39<8:41:21,  4.08it/s]
 66%|██████▌   | 243980/371472 [8:22:40<9:15:22,  3.83it/s]
                                                           
{'loss': 2.9411, 'learning_rate': 4.090532008877588e-07, 'epoch': 10.51}
+
 66%|██████▌   | 243980/371472 [8:22:40<9:15:22,  3.83it/s]
 66%|██████▌   | 243981/371472 [8:22:40<9:13:48,  3.84it/s]
 66%|██████▌   | 243982/371472 [8:22:40<9:14:14,  3.83it/s]
 66%|██████▌   | 243983/371472 [8:22:40<9:10:32,  3.86it/s]
 66%|██████▌   | 243984/371472 [8:22:41<9:47:03,  3.62it/s]
 66%|██████▌   | 243985/371472 [8:22:41<9:25:37,  3.76it/s]
 66%|██████▌   | 243986/371472 [8:22:41<9:14:54,  3.83it/s]
 66%|██████▌   | 243987/371472 [8:22:42<9:17:39,  3.81it/s]
 66%|██████▌   | 243988/371472 [8:22:42<9:28:15,  3.74it/s]
 66%|██████▌   | 243989/371472 [8:22:42<9:13:13,  3.84it/s]
 66%|██████▌   | 243990/371472 [8:22:42<9:52:01,  3.59it/s]
 66%|██████▌   | 243991/371472 [8:22:43<9:26:17,  3.75it/s]
 66%|██████▌   | 243992/371472 [8:22:43<9:59:08,  3.55it/s]
 66%|██████▌   | 243993/371472 [8:22:43<9:52:25,  3.59it/s]
 66%|██████▌   | 243994/371472 [8:22:43<9:35:30,  3.69it/s]
 66%|██████▌   | 243995/371472 [8:22:44<9:24:53,  3.76it/s]
 66%|██████▌   | 243996/371472 [8:22:44<9:19:24,  3.80it/s]
 66%|██████▌   | 243997/371472 [8:22:44<9:18:24,  3.80it/s]
 66%|██████▌   | 243998/371472 [8:22:44<9:05:05,  3.90it/s]
 66%|██████▌   | 243999/371472 [8:22:45<9:43:30,  3.64it/s]
 66%|██████▌   | 244000/371472 [8:22:45<9:38:34,  3.67it/s]
                                                           
{'loss': 2.9213, 'learning_rate': 4.0900471891227993e-07, 'epoch': 10.51}
+
 66%|██████▌   | 244000/371472 [8:22:45<9:38:34,  3.67it/s]
 66%|██████▌   | 244001/371472 [8:22:45<9:42:48,  3.65it/s]
 66%|██████▌   | 244002/371472 [8:22:46<9:43:52,  3.64it/s]
 66%|██████▌   | 244003/371472 [8:22:46<9:40:16,  3.66it/s]
 66%|██████▌   | 244004/371472 [8:22:46<9:23:59,  3.77it/s]
 66%|██████▌   | 244005/371472 [8:22:46<9:12:21,  3.85it/s]
 66%|██████▌   | 244006/371472 [8:22:47<9:00:54,  3.93it/s]
 66%|██████▌   | 244007/371472 [8:22:47<9:18:42,  3.80it/s]
 66%|██████▌   | 244008/371472 [8:22:47<9:12:44,  3.84it/s]
 66%|██████▌   | 244009/371472 [8:22:47<9:57:50,  3.55it/s]
 66%|██████▌   | 244010/371472 [8:22:48<10:22:50,  3.41it/s]
 66%|██████▌   | 244011/371472 [8:22:48<10:07:32,  3.50it/s]
 66%|██████▌   | 244012/371472 [8:22:48<9:43:55,  3.64it/s] 
 66%|██████▌   | 244013/371472 [8:22:49<9:16:11,  3.82it/s]
 66%|██████▌   | 244014/371472 [8:22:49<10:04:43,  3.51it/s]
 66%|██████▌   | 244015/371472 [8:22:49<9:53:50,  3.58it/s] 
 66%|██████▌   | 244016/371472 [8:22:49<9:40:28,  3.66it/s]
 66%|██████▌   | 244017/371472 [8:22:50<10:01:11,  3.53it/s]
 66%|██████▌   | 244018/371472 [8:22:50<10:12:29,  3.47it/s]
 66%|██████▌   | 244019/371472 [8:22:50<10:07:31,  3.50it/s]
 66%|██████▌   | 244020/371472 [8:22:51<9:53:49,  3.58it/s] 
                                                           
{'loss': 2.8714, 'learning_rate': 4.08956236936801e-07, 'epoch': 10.51}
+
 66%|██████▌   | 244020/371472 [8:22:51<9:53:49,  3.58it/s]
 66%|██████▌   | 244021/371472 [8:22:51<10:01:25,  3.53it/s]
 66%|██████▌   | 244022/371472 [8:22:51<10:09:18,  3.49it/s]
 66%|██████▌   | 244023/371472 [8:22:51<9:54:51,  3.57it/s] 
 66%|██████▌   | 244024/371472 [8:22:52<9:33:05,  3.71it/s]
 66%|██████▌   | 244025/371472 [8:22:52<9:28:38,  3.74it/s]
 66%|██████▌   | 244026/371472 [8:22:52<9:35:47,  3.69it/s]
 66%|██████▌   | 244027/371472 [8:22:53<9:58:17,  3.55it/s]
 66%|██████▌   | 244028/371472 [8:22:53<9:42:14,  3.65it/s]
 66%|██████▌   | 244029/371472 [8:22:53<10:17:47,  3.44it/s]
 66%|██████▌   | 244030/371472 [8:22:53<10:22:55,  3.41it/s]
 66%|██████▌   | 244031/371472 [8:22:54<10:34:33,  3.35it/s]
 66%|██████▌   | 244032/371472 [8:22:54<10:40:03,  3.32it/s]
 66%|██████▌   | 244033/371472 [8:22:54<10:28:56,  3.38it/s]
 66%|██████▌   | 244034/371472 [8:22:55<11:18:12,  3.13it/s]
 66%|██████▌   | 244035/371472 [8:22:55<10:33:22,  3.35it/s]
 66%|██████▌   | 244036/371472 [8:22:55<10:17:37,  3.44it/s]
 66%|██████▌   | 244037/371472 [8:22:56<11:04:02,  3.20it/s]
 66%|██████▌   | 244038/371472 [8:22:56<10:33:12,  3.35it/s]
 66%|██████▌   | 244039/371472 [8:22:56<10:11:04,  3.48it/s]
 66%|██████▌   | 244040/371472 [8:22:56<9:53:54,  3.58it/s] 
                                                           
{'loss': 2.6551, 'learning_rate': 4.089077549613222e-07, 'epoch': 10.51}
+
 66%|██████▌   | 244040/371472 [8:22:56<9:53:54,  3.58it/s]
 66%|██████▌   | 244041/371472 [8:22:57<9:42:02,  3.65it/s]
 66%|██████▌   | 244042/371472 [8:22:57<10:01:20,  3.53it/s]
 66%|██████▌   | 244043/371472 [8:22:57<10:33:21,  3.35it/s]
 66%|██████▌   | 244044/371472 [8:22:58<10:12:12,  3.47it/s]
 66%|██████▌   | 244045/371472 [8:22:58<9:57:38,  3.55it/s] 
 66%|██████▌   | 244046/371472 [8:22:58<9:49:34,  3.60it/s]
 66%|██████▌   | 244047/371472 [8:22:58<9:35:12,  3.69it/s]
 66%|██████▌   | 244048/371472 [8:22:59<9:40:13,  3.66it/s]
 66%|██████▌   | 244049/371472 [8:22:59<9:31:30,  3.72it/s]
 66%|██████▌   | 244050/371472 [8:22:59<9:48:02,  3.61it/s]
 66%|██████▌   | 244051/371472 [8:22:59<9:46:04,  3.62it/s]
 66%|██████▌   | 244052/371472 [8:23:00<9:37:08,  3.68it/s]
 66%|██████▌   | 244053/371472 [8:23:00<9:38:15,  3.67it/s]
 66%|██████▌   | 244054/371472 [8:23:00<9:38:11,  3.67it/s]
 66%|██████▌   | 244055/371472 [8:23:00<9:32:52,  3.71it/s]
 66%|██████▌   | 244056/371472 [8:23:01<9:27:00,  3.75it/s]
 66%|██████▌   | 244057/371472 [8:23:01<9:30:42,  3.72it/s]
 66%|██████▌   | 244058/371472 [8:23:01<9:28:04,  3.74it/s]
 66%|██████▌   | 244059/371472 [8:23:02<9:12:57,  3.84it/s]
 66%|██████▌   | 244060/371472 [8:23:02<10:10:46,  3.48it/s]
                                                            
{'loss': 2.9795, 'learning_rate': 4.0885927298584325e-07, 'epoch': 10.51}
+
 66%|██████▌   | 244060/371472 [8:23:02<10:10:46,  3.48it/s]
 66%|██████▌   | 244061/371472 [8:23:02<11:05:28,  3.19it/s]
 66%|██████▌   | 244062/371472 [8:23:03<10:51:28,  3.26it/s]
 66%|██████▌   | 244063/371472 [8:23:03<10:33:08,  3.35it/s]
 66%|██████▌   | 244064/371472 [8:23:03<10:05:19,  3.51it/s]
 66%|██████▌   | 244065/371472 [8:23:03<9:49:10,  3.60it/s] 
 66%|██████▌   | 244066/371472 [8:23:04<9:31:00,  3.72it/s]
 66%|██████▌   | 244067/371472 [8:23:04<9:38:35,  3.67it/s]
 66%|██████▌   | 244068/371472 [8:23:04<10:53:06,  3.25it/s]
 66%|██████▌   | 244069/371472 [8:23:05<10:37:22,  3.33it/s]
 66%|██████▌   | 244070/371472 [8:23:05<10:41:21,  3.31it/s]
 66%|██████▌   | 244071/371472 [8:23:05<10:04:24,  3.51it/s]
 66%|██████▌   | 244072/371472 [8:23:05<10:08:55,  3.49it/s]
 66%|██████▌   | 244073/371472 [8:23:06<10:01:50,  3.53it/s]
 66%|██████▌   | 244074/371472 [8:23:06<10:06:34,  3.50it/s]
 66%|██████▌   | 244075/371472 [8:23:06<10:13:15,  3.46it/s]
 66%|██████▌   | 244076/371472 [8:23:07<10:30:29,  3.37it/s]
 66%|██████▌   | 244077/371472 [8:23:07<10:16:48,  3.44it/s]
 66%|██████▌   | 244078/371472 [8:23:07<10:57:04,  3.23it/s]
 66%|██████▌   | 244079/371472 [8:23:07<10:55:09,  3.24it/s]
 66%|██████▌   | 244080/371472 [8:23:08<10:28:21,  3.38it/s]
                                                            
{'loss': 2.8696, 'learning_rate': 4.088107910103644e-07, 'epoch': 10.51}
+
 66%|██████▌   | 244080/371472 [8:23:08<10:28:21,  3.38it/s]
 66%|██████▌   | 244081/371472 [8:23:08<10:11:47,  3.47it/s]
 66%|██████▌   | 244082/371472 [8:23:08<10:18:29,  3.43it/s]
 66%|██████▌   | 244083/371472 [8:23:09<9:53:53,  3.57it/s] 
 66%|██████▌   | 244084/371472 [8:23:09<9:51:17,  3.59it/s]
 66%|██████▌   | 244085/371472 [8:23:09<11:05:29,  3.19it/s]
 66%|██████▌   | 244086/371472 [8:23:10<10:24:28,  3.40it/s]
 66%|██████▌   | 244087/371472 [8:23:10<11:14:39,  3.15it/s]
 66%|██████▌   | 244088/371472 [8:23:10<11:12:58,  3.15it/s]
 66%|██████▌   | 244089/371472 [8:23:10<11:07:36,  3.18it/s]
 66%|██████▌   | 244090/371472 [8:23:11<10:34:33,  3.35it/s]
 66%|██████▌   | 244091/371472 [8:23:11<12:29:22,  2.83it/s]
 66%|██████▌   | 244092/371472 [8:23:12<11:36:06,  3.05it/s]
 66%|██████▌   | 244093/371472 [8:23:12<10:52:04,  3.26it/s]
 66%|██████▌   | 244094/371472 [8:23:12<11:31:14,  3.07it/s]
 66%|██████▌   | 244095/371472 [8:23:12<10:40:27,  3.31it/s]
 66%|██████▌   | 244096/371472 [8:23:13<10:04:47,  3.51it/s]
 66%|██████▌   | 244097/371472 [8:23:13<10:11:38,  3.47it/s]
 66%|██████▌   | 244098/371472 [8:23:13<9:58:17,  3.55it/s] 
 66%|██████▌   | 244099/371472 [8:23:14<10:37:13,  3.33it/s]
 66%|██████▌   | 244100/371472 [8:23:14<10:20:17,  3.42it/s]
                                                            
{'loss': 2.7138, 'learning_rate': 4.0876230903488545e-07, 'epoch': 10.51}
+
 66%|██████▌   | 244100/371472 [8:23:14<10:20:17,  3.42it/s]
 66%|██████▌   | 244101/371472 [8:23:14<10:18:41,  3.43it/s]
 66%|██████▌   | 244102/371472 [8:23:14<10:01:22,  3.53it/s]
 66%|██████▌   | 244103/371472 [8:23:15<10:13:00,  3.46it/s]
 66%|██████▌   | 244104/371472 [8:23:15<9:34:21,  3.70it/s] 
 66%|██████▌   | 244105/371472 [8:23:15<11:11:42,  3.16it/s]
 66%|██████▌   | 244106/371472 [8:23:16<10:24:22,  3.40it/s]
 66%|██████▌   | 244107/371472 [8:23:16<11:08:05,  3.18it/s]
 66%|██████▌   | 244108/371472 [8:23:16<11:18:38,  3.13it/s]
 66%|██████▌   | 244109/371472 [8:23:17<10:40:39,  3.31it/s]
 66%|██████▌   | 244110/371472 [8:23:17<10:19:20,  3.43it/s]
 66%|██████▌   | 244111/371472 [8:23:17<10:27:08,  3.38it/s]
 66%|██████▌   | 244112/371472 [8:23:17<10:40:05,  3.32it/s]
 66%|██████▌   | 244113/371472 [8:23:18<10:05:05,  3.51it/s]
 66%|██████▌   | 244114/371472 [8:23:18<10:33:04,  3.35it/s]
 66%|██████▌   | 244115/371472 [8:23:18<10:44:48,  3.29it/s]
 66%|██████▌   | 244116/371472 [8:23:19<10:20:22,  3.42it/s]
 66%|██████▌   | 244117/371472 [8:23:19<10:08:16,  3.49it/s]
 66%|██████▌   | 244118/371472 [8:23:19<9:47:43,  3.61it/s] 
 66%|██████▌   | 244119/371472 [8:23:19<9:59:00,  3.54it/s]
 66%|██████▌   | 244120/371472 [8:23:20<9:59:43,  3.54it/s]
                                                           
{'loss': 2.9857, 'learning_rate': 4.0871382705940663e-07, 'epoch': 10.51}
+
 66%|██████▌   | 244120/371472 [8:23:20<9:59:43,  3.54it/s]
 66%|██████▌   | 244121/371472 [8:23:20<10:19:04,  3.43it/s]
 66%|██████▌   | 244122/371472 [8:23:20<10:03:53,  3.51it/s]
 66%|██████▌   | 244123/371472 [8:23:21<9:46:07,  3.62it/s] 
 66%|██████▌   | 244124/371472 [8:23:21<9:51:18,  3.59it/s]
 66%|██████▌   | 244125/371472 [8:23:21<9:22:20,  3.77it/s]
 66%|██████▌   | 244126/371472 [8:23:21<9:03:20,  3.91it/s]
 66%|██████▌   | 244127/371472 [8:23:22<9:32:55,  3.70it/s]
 66%|██████▌   | 244128/371472 [8:23:22<9:25:07,  3.76it/s]
 66%|██████▌   | 244129/371472 [8:23:22<10:14:00,  3.46it/s]
 66%|██████▌   | 244130/371472 [8:23:22<9:47:39,  3.61it/s] 
 66%|██████▌   | 244131/371472 [8:23:23<9:40:58,  3.65it/s]
 66%|██████▌   | 244132/371472 [8:23:23<10:17:13,  3.44it/s]
 66%|██████▌   | 244133/371472 [8:23:23<9:55:19,  3.56it/s] 
 66%|██████▌   | 244134/371472 [8:23:24<9:33:37,  3.70it/s]
 66%|██████▌   | 244135/371472 [8:23:24<9:39:16,  3.66it/s]
 66%|██████▌   | 244136/371472 [8:23:24<9:35:15,  3.69it/s]
 66%|██████▌   | 244137/371472 [8:23:24<9:20:21,  3.79it/s]
 66%|██████▌   | 244138/371472 [8:23:25<11:02:27,  3.20it/s]
 66%|██████▌   | 244139/371472 [8:23:25<10:22:30,  3.41it/s]
 66%|██████▌   | 244140/371472 [8:23:25<10:09:33,  3.48it/s]
                                                            
{'loss': 2.8253, 'learning_rate': 4.0866534508392765e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244140/371472 [8:23:25<10:09:33,  3.48it/s]
 66%|██████▌   | 244141/371472 [8:23:26<9:57:24,  3.55it/s] 
 66%|██████▌   | 244142/371472 [8:23:26<9:33:42,  3.70it/s]
 66%|██████▌   | 244143/371472 [8:23:26<9:42:11,  3.65it/s]
 66%|██████▌   | 244144/371472 [8:23:26<9:49:13,  3.60it/s]
 66%|██████▌   | 244145/371472 [8:23:27<9:56:08,  3.56it/s]
 66%|██████▌   | 244146/371472 [8:23:27<10:27:20,  3.38it/s]
 66%|██████▌   | 244147/371472 [8:23:27<10:06:34,  3.50it/s]
 66%|██████▌   | 244148/371472 [8:23:28<10:38:33,  3.32it/s]
 66%|██████▌   | 244149/371472 [8:23:28<10:38:16,  3.32it/s]
 66%|██████▌   | 244150/371472 [8:23:28<10:16:42,  3.44it/s]
 66%|██████▌   | 244151/371472 [8:23:28<9:48:28,  3.61it/s] 
 66%|██████▌   | 244152/371472 [8:23:29<10:02:38,  3.52it/s]
 66%|██████▌   | 244153/371472 [8:23:29<9:55:51,  3.56it/s] 
 66%|██████▌   | 244154/371472 [8:23:29<9:59:29,  3.54it/s]
 66%|██████▌   | 244155/371472 [8:23:29<9:54:57,  3.57it/s]
 66%|██████▌   | 244156/371472 [8:23:30<9:33:05,  3.70it/s]
 66%|██████▌   | 244157/371472 [8:23:30<9:28:10,  3.73it/s]
 66%|██████▌   | 244158/371472 [8:23:30<9:36:36,  3.68it/s]
 66%|██████▌   | 244159/371472 [8:23:31<9:28:01,  3.74it/s]
 66%|██████▌   | 244160/371472 [8:23:31<9:10:43,  3.85it/s]
                                                           
{'loss': 2.7987, 'learning_rate': 4.086168631084488e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244160/371472 [8:23:31<9:10:43,  3.85it/s]
 66%|██████▌   | 244161/371472 [8:23:31<9:12:42,  3.84it/s]
 66%|██████▌   | 244162/371472 [8:23:31<9:21:11,  3.78it/s]
 66%|██████▌   | 244163/371472 [8:23:32<9:38:09,  3.67it/s]
 66%|██████▌   | 244164/371472 [8:23:32<9:39:41,  3.66it/s]
 66%|██████▌   | 244165/371472 [8:23:32<9:22:22,  3.77it/s]
 66%|██████▌   | 244166/371472 [8:23:32<9:33:15,  3.70it/s]
 66%|██████▌   | 244167/371472 [8:23:33<9:28:17,  3.73it/s]
 66%|██████▌   | 244168/371472 [8:23:33<9:41:03,  3.65it/s]
 66%|██████▌   | 244169/371472 [8:23:33<10:00:57,  3.53it/s]
 66%|██████▌   | 244170/371472 [8:23:34<9:43:59,  3.63it/s] 
 66%|██████▌   | 244171/371472 [8:23:34<9:31:48,  3.71it/s]
 66%|██████▌   | 244172/371472 [8:23:34<10:09:51,  3.48it/s]
 66%|██████▌   | 244173/371472 [8:23:34<10:42:30,  3.30it/s]
 66%|██████▌   | 244174/371472 [8:23:35<10:08:57,  3.48it/s]
 66%|██████▌   | 244175/371472 [8:23:35<10:15:41,  3.45it/s]
 66%|██████▌   | 244176/371472 [8:23:35<9:52:07,  3.58it/s] 
 66%|██████▌   | 244177/371472 [8:23:35<9:31:20,  3.71it/s]
 66%|██████▌   | 244178/371472 [8:23:36<9:11:31,  3.85it/s]
 66%|██████▌   | 244179/371472 [8:23:36<9:28:08,  3.73it/s]
 66%|██████▌   | 244180/371472 [8:23:36<9:39:33,  3.66it/s]
                                                           
{'loss': 2.6387, 'learning_rate': 4.085683811329699e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244180/371472 [8:23:36<9:39:33,  3.66it/s]
 66%|██████▌   | 244181/371472 [8:23:37<9:24:52,  3.76it/s]
 66%|██████▌   | 244182/371472 [8:23:37<9:54:34,  3.57it/s]
 66%|██████▌   | 244183/371472 [8:23:37<9:48:57,  3.60it/s]
 66%|██████▌   | 244184/371472 [8:23:37<10:23:22,  3.40it/s]
 66%|██████▌   | 244185/371472 [8:23:38<10:08:37,  3.49it/s]
 66%|██████▌   | 244186/371472 [8:23:38<9:56:58,  3.55it/s] 
 66%|██████▌   | 244187/371472 [8:23:38<9:47:59,  3.61it/s]
 66%|██████▌   | 244188/371472 [8:23:39<9:31:04,  3.71it/s]
 66%|██████▌   | 244189/371472 [8:23:39<9:15:20,  3.82it/s]
 66%|██████▌   | 244190/371472 [8:23:39<9:22:02,  3.77it/s]
 66%|██████▌   | 244191/371472 [8:23:39<9:25:56,  3.75it/s]
 66%|██████▌   | 244192/371472 [8:23:40<9:27:06,  3.74it/s]
 66%|██████▌   | 244193/371472 [8:23:40<9:23:28,  3.76it/s]
 66%|██████▌   | 244194/371472 [8:23:40<9:24:41,  3.76it/s]
 66%|██████▌   | 244195/371472 [8:23:40<9:57:30,  3.55it/s]
 66%|██████▌   | 244196/371472 [8:23:41<9:45:24,  3.62it/s]
 66%|██████▌   | 244197/371472 [8:23:41<10:14:31,  3.45it/s]
 66%|██████▌   | 244198/371472 [8:23:41<9:51:24,  3.59it/s] 
 66%|██████▌   | 244199/371472 [8:23:42<10:03:50,  3.51it/s]
 66%|██████▌   | 244200/371472 [8:23:42<9:49:42,  3.60it/s] 
                                                           
{'loss': 2.8444, 'learning_rate': 4.08519899157491e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244200/371472 [8:23:42<9:49:42,  3.60it/s]
 66%|██████▌   | 244201/371472 [8:23:42<9:31:56,  3.71it/s]
 66%|██████▌   | 244202/371472 [8:23:42<9:24:04,  3.76it/s]
 66%|██████▌   | 244203/371472 [8:23:43<9:12:40,  3.84it/s]
 66%|██████▌   | 244204/371472 [8:23:43<9:05:06,  3.89it/s]
 66%|██████▌   | 244205/371472 [8:23:43<9:18:41,  3.80it/s]
 66%|██████▌   | 244206/371472 [8:23:43<9:07:30,  3.87it/s]
 66%|██████▌   | 244207/371472 [8:23:44<9:27:45,  3.74it/s]
 66%|██████▌   | 244208/371472 [8:23:44<9:57:51,  3.55it/s]
 66%|██████▌   | 244209/371472 [8:23:44<9:46:14,  3.62it/s]
 66%|██████▌   | 244210/371472 [8:23:45<10:02:59,  3.52it/s]
 66%|██████▌   | 244211/371472 [8:23:45<9:31:32,  3.71it/s] 
 66%|██████▌   | 244212/371472 [8:23:45<9:19:36,  3.79it/s]
 66%|██████▌   | 244213/371472 [8:23:45<9:29:11,  3.73it/s]
 66%|██████▌   | 244214/371472 [8:23:46<9:22:47,  3.77it/s]
 66%|██████▌   | 244215/371472 [8:23:46<10:04:58,  3.51it/s]
 66%|██████▌   | 244216/371472 [8:23:46<11:11:53,  3.16it/s]
 66%|██████▌   | 244217/371472 [8:23:47<12:08:40,  2.91it/s]
 66%|██████▌   | 244218/371472 [8:23:47<11:16:54,  3.13it/s]
 66%|██████▌   | 244219/371472 [8:23:47<10:50:10,  3.26it/s]
 66%|██████▌   | 244220/371472 [8:23:47<10:03:13,  3.52it/s]
                                                            
{'loss': 2.7983, 'learning_rate': 4.084714171820121e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244220/371472 [8:23:47<10:03:13,  3.52it/s]
 66%|██████▌   | 244221/371472 [8:23:48<10:43:14,  3.30it/s]
 66%|██████▌   | 244222/371472 [8:23:48<10:51:49,  3.25it/s]
 66%|██████▌   | 244223/371472 [8:23:48<10:20:16,  3.42it/s]
 66%|██████▌   | 244224/371472 [8:23:49<9:46:34,  3.62it/s] 
 66%|██████▌   | 244225/371472 [8:23:49<10:03:22,  3.51it/s]
 66%|██████▌   | 244226/371472 [8:23:49<10:17:39,  3.43it/s]
 66%|██████▌   | 244227/371472 [8:23:50<10:58:54,  3.22it/s]
 66%|██████▌   | 244228/371472 [8:23:50<10:26:01,  3.39it/s]
 66%|██████▌   | 244229/371472 [8:23:50<10:12:22,  3.46it/s]
 66%|██████▌   | 244230/371472 [8:23:50<9:41:35,  3.65it/s] 
 66%|██████▌   | 244231/371472 [8:23:51<9:39:12,  3.66it/s]
 66%|██████▌   | 244232/371472 [8:23:51<9:16:32,  3.81it/s]
 66%|██████▌   | 244233/371472 [8:23:51<9:29:35,  3.72it/s]
 66%|██████▌   | 244234/371472 [8:23:52<10:26:31,  3.38it/s]
 66%|██████▌   | 244235/371472 [8:23:52<9:49:20,  3.60it/s] 
 66%|██████▌   | 244236/371472 [8:23:52<9:34:46,  3.69it/s]
 66%|██████▌   | 244237/371472 [8:23:52<9:42:38,  3.64it/s]
 66%|██████▌   | 244238/371472 [8:23:53<10:13:54,  3.45it/s]
 66%|██████▌   | 244239/371472 [8:23:53<9:59:44,  3.54it/s] 
 66%|██████▌   | 244240/371472 [8:23:53<9:44:54,  3.63it/s]
                                                           
{'loss': 2.6933, 'learning_rate': 4.0842293520653316e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244240/371472 [8:23:53<9:44:54,  3.63it/s]
 66%|██████▌   | 244241/371472 [8:23:53<9:42:38,  3.64it/s]
 66%|██████▌   | 244242/371472 [8:23:54<9:20:35,  3.78it/s]
 66%|██████▌   | 244243/371472 [8:23:54<9:13:09,  3.83it/s]
 66%|██████▌   | 244244/371472 [8:23:54<9:05:44,  3.89it/s]
 66%|██████▌   | 244245/371472 [8:23:54<9:14:17,  3.83it/s]
 66%|██████▌   | 244246/371472 [8:23:55<9:39:36,  3.66it/s]
 66%|██████▌   | 244247/371472 [8:23:55<9:21:36,  3.78it/s]
 66%|██████▌   | 244248/371472 [8:23:55<9:39:52,  3.66it/s]
 66%|██████▌   | 244249/371472 [8:23:56<9:52:23,  3.58it/s]
 66%|██████▌   | 244250/371472 [8:23:56<10:04:19,  3.51it/s]
 66%|██████▌   | 244251/371472 [8:23:56<9:54:53,  3.56it/s] 
 66%|██████▌   | 244252/371472 [8:23:56<9:35:56,  3.68it/s]
 66%|██████▌   | 244253/371472 [8:23:57<10:37:49,  3.32it/s]
 66%|██████▌   | 244254/371472 [8:23:57<10:25:44,  3.39it/s]
 66%|██████▌   | 244255/371472 [8:23:57<9:59:44,  3.54it/s] 
 66%|██████▌   | 244256/371472 [8:23:58<9:39:05,  3.66it/s]
 66%|██████▌   | 244257/371472 [8:23:58<9:24:19,  3.76it/s]
 66%|██████▌   | 244258/371472 [8:23:58<9:26:08,  3.75it/s]
 66%|██████▌   | 244259/371472 [8:23:58<9:36:59,  3.67it/s]
 66%|██████▌   | 244260/371472 [8:23:59<10:12:28,  3.46it/s]
                                                            
{'loss': 2.9039, 'learning_rate': 4.083744532310543e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244260/371472 [8:23:59<10:12:28,  3.46it/s]
 66%|██████▌   | 244261/371472 [8:23:59<9:48:57,  3.60it/s] 
 66%|██████▌   | 244262/371472 [8:23:59<10:16:16,  3.44it/s]
 66%|██████▌   | 244263/371472 [8:23:59<9:59:25,  3.54it/s] 
 66%|██████▌   | 244264/371472 [8:24:00<10:18:56,  3.43it/s]
 66%|██████▌   | 244265/371472 [8:24:00<10:53:10,  3.25it/s]
 66%|██████▌   | 244266/371472 [8:24:00<10:25:29,  3.39it/s]
 66%|██████▌   | 244267/371472 [8:24:01<9:50:46,  3.59it/s] 
 66%|██████▌   | 244268/371472 [8:24:01<9:38:15,  3.67it/s]
 66%|██████▌   | 244269/371472 [8:24:01<10:52:56,  3.25it/s]
 66%|██████▌   | 244270/371472 [8:24:02<10:26:50,  3.38it/s]
 66%|██████▌   | 244271/371472 [8:24:02<10:03:29,  3.51it/s]
 66%|██████▌   | 244272/371472 [8:24:02<11:12:34,  3.15it/s]
 66%|██████▌   | 244273/371472 [8:24:03<11:21:06,  3.11it/s]
 66%|██████▌   | 244274/371472 [8:24:03<10:43:13,  3.30it/s]
 66%|██████▌   | 244275/371472 [8:24:03<10:08:32,  3.48it/s]
 66%|██████▌   | 244276/371472 [8:24:03<10:14:43,  3.45it/s]
 66%|██████▌   | 244277/371472 [8:24:04<9:58:30,  3.54it/s] 
 66%|██████▌   | 244278/371472 [8:24:04<10:43:12,  3.30it/s]
 66%|██████▌   | 244279/371472 [8:24:04<10:06:33,  3.49it/s]
 66%|██████▌   | 244280/371472 [8:24:05<10:01:41,  3.52it/s]
                                                            
{'loss': 2.8858, 'learning_rate': 4.083259712555753e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244280/371472 [8:24:05<10:01:41,  3.52it/s]
 66%|██████▌   | 244281/371472 [8:24:05<10:02:05,  3.52it/s]
 66%|██████▌   | 244282/371472 [8:24:05<9:47:49,  3.61it/s] 
 66%|██████▌   | 244283/371472 [8:24:05<9:51:54,  3.58it/s]
 66%|██████▌   | 244284/371472 [8:24:06<9:49:34,  3.60it/s]
 66%|██████▌   | 244285/371472 [8:24:06<10:29:26,  3.37it/s]
 66%|██████▌   | 244286/371472 [8:24:06<10:16:55,  3.44it/s]
 66%|██████▌   | 244287/371472 [8:24:07<10:42:13,  3.30it/s]
 66%|██████▌   | 244288/371472 [8:24:07<10:48:11,  3.27it/s]
 66%|██████▌   | 244289/371472 [8:24:07<10:12:47,  3.46it/s]
 66%|██████▌   | 244290/371472 [8:24:07<10:20:56,  3.41it/s]
 66%|██████▌   | 244291/371472 [8:24:08<11:13:40,  3.15it/s]
 66%|██████▌   | 244292/371472 [8:24:08<10:40:01,  3.31it/s]
 66%|██████▌   | 244293/371472 [8:24:08<10:09:47,  3.48it/s]
 66%|██████▌   | 244294/371472 [8:24:09<10:14:39,  3.45it/s]
 66%|██████▌   | 244295/371472 [8:24:09<9:46:45,  3.61it/s] 
 66%|██████▌   | 244296/371472 [8:24:09<9:40:27,  3.65it/s]
 66%|██████▌   | 244297/371472 [8:24:09<9:21:10,  3.78it/s]
 66%|██████▌   | 244298/371472 [8:24:10<9:22:13,  3.77it/s]
 66%|██████▌   | 244299/371472 [8:24:10<9:14:34,  3.82it/s]
 66%|██████▌   | 244300/371472 [8:24:10<9:42:42,  3.64it/s]
                                                           
{'loss': 2.8241, 'learning_rate': 4.0827748928009653e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244300/371472 [8:24:10<9:42:42,  3.64it/s]
 66%|██████▌   | 244301/371472 [8:24:10<9:57:13,  3.55it/s]
 66%|██████▌   | 244302/371472 [8:24:11<9:35:14,  3.68it/s]
 66%|██████▌   | 244303/371472 [8:24:11<9:49:29,  3.60it/s]
 66%|██████▌   | 244304/371472 [8:24:11<9:58:47,  3.54it/s]
 66%|██████▌   | 244305/371472 [8:24:12<9:51:36,  3.58it/s]
 66%|██████▌   | 244306/371472 [8:24:12<9:39:38,  3.66it/s]
 66%|██████▌   | 244307/371472 [8:24:12<9:20:40,  3.78it/s]
 66%|██████▌   | 244308/371472 [8:24:12<9:26:16,  3.74it/s]
 66%|██████▌   | 244309/371472 [8:24:13<9:22:17,  3.77it/s]
 66%|██████▌   | 244310/371472 [8:24:13<9:07:08,  3.87it/s]
 66%|██████▌   | 244311/371472 [8:24:13<8:59:37,  3.93it/s]
 66%|██████▌   | 244312/371472 [8:24:13<8:57:34,  3.94it/s]
 66%|██████▌   | 244313/371472 [8:24:14<8:59:03,  3.93it/s]
 66%|██████▌   | 244314/371472 [8:24:14<8:59:38,  3.93it/s]
 66%|██████▌   | 244315/371472 [8:24:14<9:11:28,  3.84it/s]
 66%|██████▌   | 244316/371472 [8:24:14<9:21:57,  3.77it/s]
 66%|██████▌   | 244317/371472 [8:24:15<9:38:37,  3.66it/s]
 66%|██████▌   | 244318/371472 [8:24:15<10:12:47,  3.46it/s]
 66%|██████▌   | 244319/371472 [8:24:15<10:13:12,  3.46it/s]
 66%|██████▌   | 244320/371472 [8:24:16<11:03:56,  3.19it/s]
                                                            
{'loss': 2.8422, 'learning_rate': 4.0822900730461755e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244320/371472 [8:24:16<11:03:56,  3.19it/s]
 66%|██████▌   | 244321/371472 [8:24:16<10:45:57,  3.28it/s]
 66%|██████▌   | 244322/371472 [8:24:16<10:39:33,  3.31it/s]
 66%|██████▌   | 244323/371472 [8:24:17<10:07:11,  3.49it/s]
 66%|██████▌   | 244324/371472 [8:24:17<11:05:34,  3.18it/s]
 66%|██████▌   | 244325/371472 [8:24:17<10:41:02,  3.31it/s]
 66%|██████▌   | 244326/371472 [8:24:17<10:27:22,  3.38it/s]
 66%|██████▌   | 244327/371472 [8:24:18<10:14:08,  3.45it/s]
 66%|██████▌   | 244328/371472 [8:24:18<9:51:17,  3.58it/s] 
 66%|██████▌   | 244329/371472 [8:24:18<9:37:43,  3.67it/s]
 66%|██████▌   | 244330/371472 [8:24:19<10:13:54,  3.45it/s]
 66%|██████▌   | 244331/371472 [8:24:19<10:00:19,  3.53it/s]
 66%|██████▌   | 244332/371472 [8:24:19<9:44:14,  3.63it/s] 
 66%|██████▌   | 244333/371472 [8:24:19<9:18:41,  3.79it/s]
 66%|██████▌   | 244334/371472 [8:24:20<9:02:56,  3.90it/s]
 66%|██████▌   | 244335/371472 [8:24:20<8:55:37,  3.96it/s]
 66%|██████▌   | 244336/371472 [8:24:20<8:50:53,  3.99it/s]
 66%|██████▌   | 244337/371472 [8:24:20<9:26:10,  3.74it/s]
 66%|██████▌   | 244338/371472 [8:24:21<10:15:03,  3.45it/s]
 66%|██████▌   | 244339/371472 [8:24:21<9:52:27,  3.58it/s] 
 66%|██████▌   | 244340/371472 [8:24:21<9:58:05,  3.54it/s]
                                                           
{'loss': 2.788, 'learning_rate': 4.0818052532913873e-07, 'epoch': 10.52}
+
 66%|██████▌   | 244340/371472 [8:24:21<9:58:05,  3.54it/s]
 66%|██████▌   | 244341/371472 [8:24:22<9:41:23,  3.64it/s]
 66%|██████▌   | 244342/371472 [8:24:22<9:35:06,  3.68it/s]
 66%|██████▌   | 244343/371472 [8:24:22<9:26:15,  3.74it/s]
 66%|██████▌   | 244344/371472 [8:24:22<9:07:30,  3.87it/s]
 66%|██████▌   | 244345/371472 [8:24:23<9:28:35,  3.73it/s]
 66%|██████▌   | 244346/371472 [8:24:23<9:31:56,  3.70it/s]
 66%|██████▌   | 244347/371472 [8:24:23<9:33:49,  3.69it/s]
 66%|██████▌   | 244348/371472 [8:24:23<10:20:38,  3.41it/s]
 66%|██████▌   | 244349/371472 [8:24:24<10:13:41,  3.45it/s]
 66%|██████▌   | 244350/371472 [8:24:24<9:58:53,  3.54it/s] 
 66%|██████▌   | 244351/371472 [8:24:24<10:19:34,  3.42it/s]
 66%|██████▌   | 244352/371472 [8:24:25<10:26:48,  3.38it/s]
 66%|██████▌   | 244353/371472 [8:24:25<10:13:15,  3.45it/s]
 66%|██████▌   | 244354/371472 [8:24:25<9:41:33,  3.64it/s] 
 66%|██████▌   | 244355/371472 [8:24:26<10:37:37,  3.32it/s]
 66%|██████▌   | 244356/371472 [8:24:26<9:56:32,  3.55it/s] 
 66%|██████▌   | 244357/371472 [8:24:26<10:55:04,  3.23it/s]
 66%|██████▌   | 244358/371472 [8:24:26<10:15:06,  3.44it/s]
 66%|██████▌   | 244359/371472 [8:24:27<10:12:53,  3.46it/s]
 66%|██████▌   | 244360/371472 [8:24:27<10:00:21,  3.53it/s]
                                                            
{'loss': 2.7385, 'learning_rate': 4.081320433536598e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244360/371472 [8:24:27<10:00:21,  3.53it/s]
 66%|██████▌   | 244361/371472 [8:24:27<10:08:43,  3.48it/s]
 66%|██████▌   | 244362/371472 [8:24:27<9:57:32,  3.55it/s] 
 66%|██████▌   | 244363/371472 [8:24:28<9:37:03,  3.67it/s]
 66%|██████▌   | 244364/371472 [8:24:28<9:30:51,  3.71it/s]
 66%|██████▌   | 244365/371472 [8:24:28<9:24:04,  3.76it/s]
 66%|██████▌   | 244366/371472 [8:24:29<9:32:09,  3.70it/s]
 66%|██████▌   | 244367/371472 [8:24:29<9:47:42,  3.60it/s]
 66%|██████▌   | 244368/371472 [8:24:29<10:08:19,  3.48it/s]
 66%|██████▌   | 244369/371472 [8:24:29<9:58:22,  3.54it/s] 
 66%|██████▌   | 244370/371472 [8:24:30<9:49:09,  3.60it/s]
 66%|██████▌   | 244371/371472 [8:24:30<9:29:51,  3.72it/s]
 66%|██████▌   | 244372/371472 [8:24:30<9:35:46,  3.68it/s]
 66%|██████▌   | 244373/371472 [8:24:31<9:53:07,  3.57it/s]
 66%|██████▌   | 244374/371472 [8:24:31<9:17:16,  3.80it/s]
 66%|██████▌   | 244375/371472 [8:24:31<9:12:13,  3.84it/s]
 66%|██████▌   | 244376/371472 [8:24:31<8:59:06,  3.93it/s]
 66%|██████▌   | 244377/371472 [8:24:31<8:49:56,  4.00it/s]
 66%|██████▌   | 244378/371472 [8:24:32<9:23:26,  3.76it/s]
 66%|██████▌   | 244379/371472 [8:24:32<10:20:11,  3.42it/s]
 66%|██████▌   | 244380/371472 [8:24:32<10:12:44,  3.46it/s]
                                                            
{'loss': 2.7961, 'learning_rate': 4.0808356137818093e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244380/371472 [8:24:32<10:12:44,  3.46it/s]
 66%|██████▌   | 244381/371472 [8:24:33<10:17:05,  3.43it/s]
 66%|██████▌   | 244382/371472 [8:24:33<9:45:21,  3.62it/s] 
 66%|██████▌   | 244383/371472 [8:24:33<9:36:55,  3.67it/s]
 66%|██████▌   | 244384/371472 [8:24:33<9:28:56,  3.72it/s]
 66%|██████▌   | 244385/371472 [8:24:34<10:30:24,  3.36it/s]
 66%|██████▌   | 244386/371472 [8:24:34<10:32:03,  3.35it/s]
 66%|██████▌   | 244387/371472 [8:24:34<10:25:19,  3.39it/s]
 66%|██████▌   | 244388/371472 [8:24:35<10:48:37,  3.27it/s]
 66%|██████▌   | 244389/371472 [8:24:35<10:07:48,  3.48it/s]
 66%|██████▌   | 244390/371472 [8:24:35<10:16:22,  3.44it/s]
 66%|██████▌   | 244391/371472 [8:24:36<10:18:07,  3.43it/s]
 66%|██████▌   | 244392/371472 [8:24:36<9:38:07,  3.66it/s] 
 66%|██████▌   | 244393/371472 [8:24:36<9:47:20,  3.61it/s]
 66%|██████▌   | 244394/371472 [8:24:36<9:49:25,  3.59it/s]
 66%|██████▌   | 244395/371472 [8:24:37<9:43:13,  3.63it/s]
 66%|██████▌   | 244396/371472 [8:24:37<10:15:59,  3.44it/s]
 66%|██████▌   | 244397/371472 [8:24:37<9:45:29,  3.62it/s] 
 66%|██████▌   | 244398/371472 [8:24:38<10:06:40,  3.49it/s]
 66%|██████▌   | 244399/371472 [8:24:38<9:42:48,  3.63it/s] 
 66%|██████▌   | 244400/371472 [8:24:38<9:34:01,  3.69it/s]
                                                           
{'loss': 2.8629, 'learning_rate': 4.08035079402702e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244400/371472 [8:24:38<9:34:01,  3.69it/s]
 66%|██████▌   | 244401/371472 [8:24:38<9:13:06,  3.83it/s]
 66%|██████▌   | 244402/371472 [8:24:39<9:07:16,  3.87it/s]
 66%|██████▌   | 244403/371472 [8:24:39<9:44:01,  3.63it/s]
 66%|██████▌   | 244404/371472 [8:24:39<9:51:18,  3.58it/s]
 66%|██████▌   | 244405/371472 [8:24:39<10:14:44,  3.45it/s]
 66%|██████▌   | 244406/371472 [8:24:40<10:20:38,  3.41it/s]
 66%|██████▌   | 244407/371472 [8:24:40<10:42:26,  3.30it/s]
 66%|██████▌   | 244408/371472 [8:24:40<11:12:44,  3.15it/s]
 66%|██████▌   | 244409/371472 [8:24:41<11:03:29,  3.19it/s]
 66%|██████▌   | 244410/371472 [8:24:41<10:39:10,  3.31it/s]
 66%|██████▌   | 244411/371472 [8:24:41<10:27:05,  3.38it/s]
 66%|██████▌   | 244412/371472 [8:24:42<10:21:05,  3.41it/s]
 66%|██████▌   | 244413/371472 [8:24:42<11:25:27,  3.09it/s]
 66%|██████▌   | 244414/371472 [8:24:42<10:56:28,  3.23it/s]
 66%|██████▌   | 244415/371472 [8:24:43<10:33:02,  3.35it/s]
 66%|██████▌   | 244416/371472 [8:24:43<10:09:17,  3.48it/s]
 66%|██████▌   | 244417/371472 [8:24:43<10:07:21,  3.49it/s]
 66%|██████▌   | 244418/371472 [8:24:43<9:28:05,  3.73it/s] 
 66%|██████▌   | 244419/371472 [8:24:44<9:12:03,  3.84it/s]
 66%|██████▌   | 244420/371472 [8:24:44<9:58:03,  3.54it/s]
                                                           
{'loss': 2.6339, 'learning_rate': 4.079865974272232e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244420/371472 [8:24:44<9:58:03,  3.54it/s]
 66%|██████▌   | 244421/371472 [8:24:44<10:06:43,  3.49it/s]
 66%|██████▌   | 244422/371472 [8:24:44<9:53:48,  3.57it/s] 
 66%|██████▌   | 244423/371472 [8:24:45<9:59:48,  3.53it/s]
 66%|██████▌   | 244424/371472 [8:24:45<9:44:51,  3.62it/s]
 66%|██████▌   | 244425/371472 [8:24:45<9:35:06,  3.68it/s]
 66%|██████▌   | 244426/371472 [8:24:45<9:17:46,  3.80it/s]
 66%|██████▌   | 244427/371472 [8:24:46<9:34:26,  3.69it/s]
 66%|██████▌   | 244428/371472 [8:24:46<10:00:06,  3.53it/s]
 66%|██████▌   | 244429/371472 [8:24:46<9:44:54,  3.62it/s] 
 66%|██████▌   | 244430/371472 [8:24:47<9:31:38,  3.70it/s]
 66%|██████▌   | 244431/371472 [8:24:47<9:51:20,  3.58it/s]
 66%|██████▌   | 244432/371472 [8:24:47<10:26:09,  3.38it/s]
 66%|██████▌   | 244433/371472 [8:24:47<9:42:32,  3.63it/s] 
 66%|██████▌   | 244434/371472 [8:24:48<10:03:07,  3.51it/s]
 66%|██████▌   | 244435/371472 [8:24:48<10:07:07,  3.49it/s]
 66%|██████▌   | 244436/371472 [8:24:48<9:55:30,  3.56it/s] 
 66%|██████▌   | 244437/371472 [8:24:49<10:38:54,  3.31it/s]
 66%|██████▌   | 244438/371472 [8:24:49<9:58:28,  3.54it/s] 
 66%|██████▌   | 244439/371472 [8:24:49<10:47:40,  3.27it/s]
 66%|██████▌   | 244440/371472 [8:24:50<10:05:59,  3.49it/s]
                                                            
{'loss': 2.9472, 'learning_rate': 4.0793811545174425e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244440/371472 [8:24:50<10:05:59,  3.49it/s]
 66%|██████▌   | 244441/371472 [8:24:50<9:51:00,  3.58it/s] 
 66%|██████▌   | 244442/371472 [8:24:50<9:45:32,  3.62it/s]
 66%|██████▌   | 244443/371472 [8:24:50<10:01:45,  3.52it/s]
 66%|██████▌   | 244444/371472 [8:24:51<10:02:29,  3.51it/s]
 66%|██████▌   | 244445/371472 [8:24:51<9:37:57,  3.66it/s] 
 66%|██████▌   | 244446/371472 [8:24:51<10:09:25,  3.47it/s]
 66%|██████▌   | 244447/371472 [8:24:51<9:48:35,  3.60it/s] 
 66%|██████▌   | 244448/371472 [8:24:52<9:33:43,  3.69it/s]
 66%|██████▌   | 244449/371472 [8:24:52<9:29:31,  3.72it/s]
 66%|██████▌   | 244450/371472 [8:24:52<9:20:30,  3.78it/s]
 66%|██████▌   | 244451/371472 [8:24:53<9:13:00,  3.83it/s]
 66%|██████▌   | 244452/371472 [8:24:53<9:16:35,  3.80it/s]
 66%|██████▌   | 244453/371472 [8:24:53<9:14:02,  3.82it/s]
 66%|██████▌   | 244454/371472 [8:24:53<9:08:58,  3.86it/s]
 66%|██████▌   | 244455/371472 [8:24:54<9:37:51,  3.66it/s]
 66%|██████▌   | 244456/371472 [8:24:54<10:50:58,  3.25it/s]
 66%|██████▌   | 244457/371472 [8:24:54<10:26:24,  3.38it/s]
 66%|██████▌   | 244458/371472 [8:24:55<10:46:18,  3.28it/s]
 66%|██████▌   | 244459/371472 [8:24:55<10:19:45,  3.42it/s]
 66%|██████▌   | 244460/371472 [8:24:55<11:01:13,  3.20it/s]
                                                            
{'loss': 2.9384, 'learning_rate': 4.0788963347626537e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244460/371472 [8:24:55<11:01:13,  3.20it/s]
 66%|██████▌   | 244461/371472 [8:24:55<10:39:31,  3.31it/s]
 66%|██████▌   | 244462/371472 [8:24:56<10:14:43,  3.44it/s]
 66%|██████▌   | 244463/371472 [8:24:56<10:05:41,  3.49it/s]
 66%|��█████▌   | 244464/371472 [8:24:56<9:47:46,  3.60it/s] 
 66%|██████▌   | 244465/371472 [8:24:57<9:54:55,  3.56it/s]
 66%|██████▌   | 244466/371472 [8:24:57<9:43:49,  3.63it/s]
 66%|██████▌   | 244467/371472 [8:24:57<9:30:53,  3.71it/s]
 66%|██████▌   | 244468/371472 [8:24:57<9:24:55,  3.75it/s]
 66%|██████▌   | 244469/371472 [8:24:58<9:22:37,  3.76it/s]
 66%|██████▌   | 244470/371472 [8:24:58<9:40:22,  3.65it/s]
 66%|██████▌   | 244471/371472 [8:24:58<9:17:04,  3.80it/s]
 66%|██████▌   | 244472/371472 [8:24:58<9:44:27,  3.62it/s]
 66%|██████▌   | 244473/371472 [8:24:59<10:10:08,  3.47it/s]
 66%|██████▌   | 244474/371472 [8:24:59<10:42:35,  3.29it/s]
 66%|██████▌   | 244475/371472 [8:24:59<10:24:48,  3.39it/s]
 66%|██████▌   | 244476/371472 [8:25:00<10:43:49,  3.29it/s]
 66%|██████▌   | 244477/371472 [8:25:00<10:03:16,  3.51it/s]
 66%|██████▌   | 244478/371472 [8:25:00<9:58:40,  3.54it/s] 
 66%|██████▌   | 244479/371472 [8:25:01<10:13:38,  3.45it/s]
 66%|██████▌   | 244480/371472 [8:25:01<10:04:20,  3.50it/s]
                                                            
{'loss': 2.8811, 'learning_rate': 4.0784115150078644e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244480/371472 [8:25:01<10:04:20,  3.50it/s]
 66%|██████▌   | 244481/371472 [8:25:01<9:50:20,  3.59it/s] 
 66%|██████▌   | 244482/371472 [8:25:01<9:39:57,  3.65it/s]
 66%|██████▌   | 244483/371472 [8:25:02<9:49:02,  3.59it/s]
 66%|██████▌   | 244484/371472 [8:25:02<9:42:18,  3.63it/s]
 66%|██████▌   | 244485/371472 [8:25:02<9:35:24,  3.68it/s]
 66%|██████▌   | 244486/371472 [8:25:02<9:23:18,  3.76it/s]
 66%|██████▌   | 244487/371472 [8:25:03<9:41:49,  3.64it/s]
 66%|██████▌   | 244488/371472 [8:25:03<9:32:25,  3.70it/s]
 66%|██████▌   | 244489/371472 [8:25:03<9:18:59,  3.79it/s]
 66%|██████▌   | 244490/371472 [8:25:03<9:36:46,  3.67it/s]
 66%|██████▌   | 244491/371472 [8:25:04<9:25:33,  3.74it/s]
 66%|██████▌   | 244492/371472 [8:25:04<9:29:37,  3.72it/s]
 66%|██████▌   | 244493/371472 [8:25:04<9:26:17,  3.74it/s]
 66%|██████▌   | 244494/371472 [8:25:05<10:40:44,  3.30it/s]
 66%|██████▌   | 244495/371472 [8:25:05<10:24:57,  3.39it/s]
 66%|██████▌   | 244496/371472 [8:25:05<10:08:51,  3.48it/s]
 66%|██████▌   | 244497/371472 [8:25:06<10:06:11,  3.49it/s]
 66%|██████▌   | 244498/371472 [8:25:06<10:07:22,  3.48it/s]
 66%|██████▌   | 244499/371472 [8:25:06<9:54:23,  3.56it/s] 
 66%|██████▌   | 244500/371472 [8:25:06<9:35:51,  3.67it/s]
                                                           
{'loss': 2.9261, 'learning_rate': 4.077926695253076e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244500/371472 [8:25:06<9:35:51,  3.67it/s]
 66%|██████▌   | 244501/371472 [8:25:07<9:26:31,  3.74it/s]
 66%|██████▌   | 244502/371472 [8:25:07<9:28:21,  3.72it/s]
 66%|██████▌   | 244503/371472 [8:25:07<9:49:24,  3.59it/s]
 66%|██████▌   | 244504/371472 [8:25:07<9:41:35,  3.64it/s]
 66%|██████▌   | 244505/371472 [8:25:08<9:42:11,  3.63it/s]
 66%|██████▌   | 244506/371472 [8:25:08<9:23:58,  3.75it/s]
 66%|██████▌   | 244507/371472 [8:25:08<9:25:19,  3.74it/s]
 66%|██████▌   | 244508/371472 [8:25:08<9:17:39,  3.79it/s]
 66%|██████▌   | 244509/371472 [8:25:09<9:10:05,  3.85it/s]
 66%|██████▌   | 244510/371472 [8:25:09<8:56:45,  3.94it/s]
 66%|██████▌   | 244511/371472 [8:25:09<9:34:44,  3.68it/s]
 66%|██████▌   | 244512/371472 [8:25:10<9:24:34,  3.75it/s]
 66%|██████▌   | 244513/371472 [8:25:10<9:05:06,  3.88it/s]
 66%|██████▌   | 244514/371472 [8:25:10<9:07:12,  3.87it/s]
 66%|██████▌   | 244515/371472 [8:25:10<9:29:53,  3.71it/s]
 66%|██████▌   | 244516/371472 [8:25:11<9:57:54,  3.54it/s]
 66%|██████▌   | 244517/371472 [8:25:11<10:08:36,  3.48it/s]
 66%|██████▌   | 244518/371472 [8:25:11<10:15:45,  3.44it/s]
 66%|██████▌   | 244519/371472 [8:25:12<10:33:33,  3.34it/s]
 66%|██████▌   | 244520/371472 [8:25:12<10:43:34,  3.29it/s]
                                                            
{'loss': 2.8287, 'learning_rate': 4.0774418754982864e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244520/371472 [8:25:12<10:43:34,  3.29it/s]
 66%|██████▌   | 244521/371472 [8:25:12<10:11:55,  3.46it/s]
 66%|██████▌   | 244522/371472 [8:25:12<10:29:40,  3.36it/s]
 66%|██████▌   | 244523/371472 [8:25:13<10:01:28,  3.52it/s]
 66%|██████▌   | 244524/371472 [8:25:13<9:48:55,  3.59it/s] 
 66%|██████▌   | 244525/371472 [8:25:13<9:27:23,  3.73it/s]
 66%|██████▌   | 244526/371472 [8:25:14<10:19:53,  3.41it/s]
 66%|██████▌   | 244527/371472 [8:25:14<9:53:47,  3.56it/s] 
 66%|██████▌   | 244528/371472 [8:25:14<10:02:26,  3.51it/s]
 66%|██████▌   | 244529/371472 [8:25:14<9:46:05,  3.61it/s] 
 66%|██████▌   | 244530/371472 [8:25:15<9:39:58,  3.65it/s]
 66%|██████▌   | 244531/371472 [8:25:15<9:46:57,  3.60it/s]
 66%|██████▌   | 244532/371472 [8:25:15<9:32:10,  3.70it/s]
 66%|██████▌   | 244533/371472 [8:25:15<9:44:33,  3.62it/s]
 66%|██████▌   | 244534/371472 [8:25:16<9:24:50,  3.75it/s]
 66%|██████▌   | 244535/371472 [8:25:16<9:10:45,  3.84it/s]
 66%|██████▌   | 244536/371472 [8:25:16<9:26:41,  3.73it/s]
 66%|██████▌   | 244537/371472 [8:25:16<9:07:32,  3.86it/s]
 66%|██████▌   | 244538/371472 [8:25:17<8:58:18,  3.93it/s]
 66%|██████▌   | 244539/371472 [8:25:17<9:03:26,  3.89it/s]
 66%|██████▌   | 244540/371472 [8:25:17<9:05:54,  3.88it/s]
                                                           
{'loss': 2.9956, 'learning_rate': 4.076957055743498e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244540/371472 [8:25:17<9:05:54,  3.88it/s]
 66%|██████▌   | 244541/371472 [8:25:17<9:01:06,  3.91it/s]
 66%|██████▌   | 244542/371472 [8:25:18<9:20:42,  3.77it/s]
 66%|██████▌   | 244543/371472 [8:25:18<9:25:06,  3.74it/s]
 66%|██████▌   | 244544/371472 [8:25:18<9:34:54,  3.68it/s]
 66%|██████▌   | 244545/371472 [8:25:19<9:14:16,  3.82it/s]
 66%|██████▌   | 244546/371472 [8:25:19<9:55:46,  3.55it/s]
 66%|██████▌   | 244547/371472 [8:25:19<10:10:19,  3.47it/s]
 66%|██████▌   | 244548/371472 [8:25:19<9:34:19,  3.68it/s] 
 66%|██████▌   | 244549/371472 [8:25:20<9:19:04,  3.78it/s]
 66%|██████▌   | 244550/371472 [8:25:20<10:08:33,  3.48it/s]
 66%|██████▌   | 244551/371472 [8:25:20<10:12:27,  3.45it/s]
 66%|██████▌   | 244552/371472 [8:25:21<10:08:47,  3.47it/s]
 66%|██████▌   | 244553/371472 [8:25:21<10:35:15,  3.33it/s]
 66%|██████▌   | 244554/371472 [8:25:21<10:10:21,  3.47it/s]
 66%|██████▌   | 244555/371472 [8:25:22<10:45:25,  3.28it/s]
 66%|██████▌   | 244556/371472 [8:25:22<10:19:48,  3.41it/s]
 66%|██████▌   | 244557/371472 [8:25:22<10:05:12,  3.50it/s]
 66%|██████▌   | 244558/371472 [8:25:22<10:08:23,  3.48it/s]
 66%|██████▌   | 244559/371472 [8:25:23<9:46:18,  3.61it/s] 
 66%|██████▌   | 244560/371472 [8:25:23<10:01:25,  3.52it/s]
                                                            
{'loss': 2.8369, 'learning_rate': 4.076472235988709e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244560/371472 [8:25:23<10:01:25,  3.52it/s]
 66%|██████▌   | 244561/371472 [8:25:23<9:29:23,  3.71it/s] 
 66%|██████▌   | 244562/371472 [8:25:23<9:44:55,  3.62it/s]
 66%|██████▌   | 244563/371472 [8:25:24<9:40:22,  3.64it/s]
 66%|██████▌   | 244564/371472 [8:25:24<9:40:00,  3.65it/s]
 66%|██████▌   | 244565/371472 [8:25:24<9:29:56,  3.71it/s]
 66%|██████▌   | 244566/371472 [8:25:24<9:14:16,  3.82it/s]
 66%|██████▌   | 244567/371472 [8:25:25<9:19:13,  3.78it/s]
 66%|██████▌   | 244568/371472 [8:25:25<9:18:39,  3.79it/s]
 66%|██████▌   | 244569/371472 [8:25:25<10:07:58,  3.48it/s]
 66%|██████▌   | 244570/371472 [8:25:26<9:40:13,  3.65it/s] 
 66%|██████▌   | 244571/371472 [8:25:26<9:34:34,  3.68it/s]
 66%|██████▌   | 244572/371472 [8:25:26<9:23:42,  3.75it/s]
 66%|██████▌   | 244573/371472 [8:25:26<9:22:34,  3.76it/s]
 66%|██████▌   | 244574/371472 [8:25:27<9:21:15,  3.77it/s]
 66%|██████▌   | 244575/371472 [8:25:27<9:42:10,  3.63it/s]
 66%|██████▌   | 244576/371472 [8:25:27<9:56:16,  3.55it/s]
 66%|██████▌   | 244577/371472 [8:25:28<10:55:08,  3.23it/s]
 66%|██████▌   | 244578/371472 [8:25:28<11:06:36,  3.17it/s]
 66%|██████▌   | 244579/371472 [8:25:28<10:33:45,  3.34it/s]
 66%|██████▌   | 244580/371472 [8:25:29<11:30:36,  3.06it/s]
                                                            
{'loss': 2.8808, 'learning_rate': 4.07598741623392e-07, 'epoch': 10.53}
+
 66%|██████▌   | 244580/371472 [8:25:29<11:30:36,  3.06it/s]
 66%|██████▌   | 244581/371472 [8:25:29<11:03:41,  3.19it/s]
 66%|██████▌   | 244582/371472 [8:25:29<10:37:25,  3.32it/s]
 66%|██████▌   | 244583/371472 [8:25:29<10:04:18,  3.50it/s]
 66%|██████▌   | 244584/371472 [8:25:30<9:47:23,  3.60it/s] 
 66%|██████▌   | 244585/371472 [8:25:30<10:15:01,  3.44it/s]
 66%|██████▌   | 244586/371472 [8:25:30<9:56:38,  3.54it/s] 
 66%|██████▌   | 244587/371472 [8:25:31<9:56:54,  3.54it/s]
 66%|██████▌   | 244588/371472 [8:25:31<10:10:54,  3.46it/s]
 66%|██████▌   | 244589/371472 [8:25:31<9:56:29,  3.55it/s] 
 66%|██████▌   | 244590/371472 [8:25:31<10:18:51,  3.42it/s]
 66%|██████▌   | 244591/371472 [8:25:32<9:53:54,  3.56it/s] 
 66%|██████▌   | 244592/371472 [8:25:32<10:07:49,  3.48it/s]
 66%|██████▌   | 244593/371472 [8:25:32<9:54:50,  3.55it/s] 
 66%|██████▌   | 244594/371472 [8:25:32<9:30:55,  3.70it/s]
 66%|██████▌   | 244595/371472 [8:25:33<9:28:38,  3.72it/s]
 66%|██████▌   | 244596/371472 [8:25:33<9:31:01,  3.70it/s]
 66%|██████▌   | 244597/371472 [8:25:33<9:26:17,  3.73it/s]
 66%|██████▌   | 244598/371472 [8:25:34<9:43:44,  3.62it/s]
 66%|██████▌   | 244599/371472 [8:25:34<9:41:01,  3.64it/s]
 66%|██████▌   | 244600/371472 [8:25:34<10:27:19,  3.37it/s]
                                                            
{'loss': 2.8509, 'learning_rate': 4.075502596479131e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244600/371472 [8:25:34<10:27:19,  3.37it/s]
 66%|██████▌   | 244601/371472 [8:25:34<10:22:59,  3.39it/s]
 66%|██████▌   | 244602/371472 [8:25:35<9:50:36,  3.58it/s] 
 66%|██████▌   | 244603/371472 [8:25:35<10:01:26,  3.52it/s]
 66%|██████▌   | 244604/371472 [8:25:35<10:01:11,  3.52it/s]
 66%|██████▌   | 244605/371472 [8:25:36<9:38:11,  3.66it/s] 
 66%|██████▌   | 244606/371472 [8:25:36<10:04:51,  3.50it/s]
 66%|██████▌   | 244607/371472 [8:25:36<9:51:44,  3.57it/s] 
 66%|██████▌   | 244608/371472 [8:25:36<9:27:42,  3.72it/s]
 66%|██████▌   | 244609/371472 [8:25:37<9:12:10,  3.83it/s]
 66%|██████▌   | 244610/371472 [8:25:37<9:34:23,  3.68it/s]
 66%|██████▌   | 244611/371472 [8:25:37<9:10:50,  3.84it/s]
 66%|██████▌   | 244612/371472 [8:25:37<8:58:07,  3.93it/s]
 66%|██████▌   | 244613/371472 [8:25:38<8:57:36,  3.93it/s]
 66%|██████▌   | 244614/371472 [8:25:38<9:14:13,  3.81it/s]
 66%|██████▌   | 244615/371472 [8:25:38<9:14:34,  3.81it/s]
 66%|██████▌   | 244616/371472 [8:25:38<9:16:49,  3.80it/s]
 66%|██████▌   | 244617/371472 [8:25:39<9:11:41,  3.83it/s]
 66%|██████▌   | 244618/371472 [8:25:39<9:14:36,  3.81it/s]
 66%|██████▌   | 244619/371472 [8:25:39<9:07:40,  3.86it/s]
 66%|██████▌   | 244620/371472 [8:25:39<9:15:29,  3.81it/s]
                                                           
{'loss': 2.9705, 'learning_rate': 4.0750177767243426e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244620/371472 [8:25:39<9:15:29,  3.81it/s]
 66%|██████▌   | 244621/371472 [8:25:40<10:45:19,  3.28it/s]
 66%|██████▌   | 244622/371472 [8:25:40<10:09:59,  3.47it/s]
 66%|██████▌   | 244623/371472 [8:25:40<9:41:28,  3.64it/s] 
 66%|██████▌   | 244624/371472 [8:25:41<9:56:11,  3.55it/s]
 66%|██████▌   | 244625/371472 [8:25:41<9:40:32,  3.64it/s]
 66%|██████▌   | 244626/371472 [8:25:41<10:15:42,  3.43it/s]
 66%|██████▌   | 244627/371472 [8:25:42<10:51:30,  3.24it/s]
 66%|██████▌   | 244628/371472 [8:25:42<11:10:46,  3.15it/s]
 66%|██████▌   | 244629/371472 [8:25:42<10:40:09,  3.30it/s]
 66%|██████▌   | 244630/371472 [8:25:42<10:04:40,  3.50it/s]
 66%|██████▌   | 244631/371472 [8:25:43<10:14:25,  3.44it/s]
 66%|██████▌   | 244632/371472 [8:25:43<9:54:22,  3.56it/s] 
 66%|██████▌   | 244633/371472 [8:25:43<9:47:34,  3.60it/s]
 66%|██████▌   | 244634/371472 [8:25:44<10:09:50,  3.47it/s]
 66%|██████▌   | 244635/371472 [8:25:44<9:47:10,  3.60it/s] 
 66%|██████▌   | 244636/371472 [8:25:44<10:00:09,  3.52it/s]
 66%|██████▌   | 244637/371472 [8:25:44<9:46:34,  3.60it/s] 
 66%|██████▌   | 244638/371472 [8:25:45<9:26:46,  3.73it/s]
 66%|██████▌   | 244639/371472 [8:25:45<9:19:39,  3.78it/s]
 66%|██████▌   | 244640/371472 [8:25:45<9:33:48,  3.68it/s]
                                                           
{'loss': 2.8371, 'learning_rate': 4.074532956969553e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244640/371472 [8:25:45<9:33:48,  3.68it/s]
 66%|██████▌   | 244641/371472 [8:25:46<10:10:02,  3.47it/s]
 66%|██████▌   | 244642/371472 [8:25:46<9:49:50,  3.58it/s] 
 66%|██████▌   | 244643/371472 [8:25:46<9:28:30,  3.72it/s]
 66%|██████▌   | 244644/371472 [8:25:46<9:22:46,  3.76it/s]
 66%|██████▌   | 244645/371472 [8:25:47<9:13:04,  3.82it/s]
 66%|██████▌   | 244646/371472 [8:25:47<9:15:01,  3.81it/s]
 66%|██████▌   | 244647/371472 [8:25:47<9:19:58,  3.77it/s]
 66%|██████▌   | 244648/371472 [8:25:47<9:32:32,  3.69it/s]
 66%|██████▌   | 244649/371472 [8:25:48<9:46:16,  3.61it/s]
 66%|██████▌   | 244650/371472 [8:25:48<9:59:20,  3.53it/s]
 66%|██████▌   | 244651/371472 [8:25:48<10:35:26,  3.33it/s]
 66%|██████▌   | 244652/371472 [8:25:49<10:48:32,  3.26it/s]
 66%|██████▌   | 244653/371472 [8:25:49<10:09:04,  3.47it/s]
 66%|██████▌   | 244654/371472 [8:25:49<10:02:18,  3.51it/s]
 66%|██████▌   | 244655/371472 [8:25:49<9:36:54,  3.66it/s] 
 66%|██████▌   | 244656/371472 [8:25:50<9:41:05,  3.64it/s]
 66%|██████▌   | 244657/371472 [8:25:50<9:24:05,  3.75it/s]
 66%|██████▌   | 244658/371472 [8:25:50<9:00:06,  3.91it/s]
 66%|██████▌   | 244659/371472 [8:25:50<8:52:34,  3.97it/s]
 66%|██████▌   | 244660/371472 [8:25:51<8:52:04,  3.97it/s]
                                                           
{'loss': 2.8506, 'learning_rate': 4.0740481372147646e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244660/371472 [8:25:51<8:52:04,  3.97it/s]
 66%|██████▌   | 244661/371472 [8:25:51<9:07:23,  3.86it/s]
 66%|██████▌   | 244662/371472 [8:25:51<10:26:06,  3.38it/s]
 66%|██████▌   | 244663/371472 [8:25:52<10:12:09,  3.45it/s]
 66%|██████▌   | 244664/371472 [8:25:52<9:39:31,  3.65it/s] 
 66%|██████▌   | 244665/371472 [8:25:52<9:42:06,  3.63it/s]
 66%|██████▌   | 244666/371472 [8:25:52<9:14:03,  3.81it/s]
 66%|██████▌   | 244667/371472 [8:25:53<9:07:36,  3.86it/s]
 66%|██████▌   | 244668/371472 [8:25:53<9:30:30,  3.70it/s]
 66%|██████▌   | 244669/371472 [8:25:53<9:18:20,  3.79it/s]
 66%|██████▌   | 244670/371472 [8:25:53<9:07:20,  3.86it/s]
 66%|██████▌   | 244671/371472 [8:25:54<9:10:31,  3.84it/s]
 66%|██████▌   | 244672/371472 [8:25:54<8:58:51,  3.92it/s]
 66%|██████▌   | 244673/371472 [8:25:54<9:18:11,  3.79it/s]
 66%|██████▌   | 244674/371472 [8:25:54<9:52:50,  3.56it/s]
 66%|██████▌   | 244675/371472 [8:25:55<10:24:32,  3.38it/s]
 66%|██████▌   | 244676/371472 [8:25:55<9:54:30,  3.55it/s] 
 66%|██████▌   | 244677/371472 [8:25:55<9:40:17,  3.64it/s]
 66%|██████▌   | 244678/371472 [8:25:56<9:24:08,  3.75it/s]
 66%|██████▌   | 244679/371472 [8:25:56<9:12:43,  3.82it/s]
 66%|██████▌   | 244680/371472 [8:25:56<9:51:41,  3.57it/s]
                                                           
{'loss': 2.9529, 'learning_rate': 4.0735633174599753e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244680/371472 [8:25:56<9:51:41,  3.57it/s]
 66%|██████▌   | 244681/371472 [8:25:56<10:02:32,  3.51it/s]
 66%|██████▌   | 244682/371472 [8:25:57<9:55:47,  3.55it/s] 
 66%|██████▌   | 244683/371472 [8:25:57<10:15:10,  3.44it/s]
 66%|██████▌   | 244684/371472 [8:25:57<9:52:04,  3.57it/s] 
 66%|██████▌   | 244685/371472 [8:25:58<9:34:17,  3.68it/s]
 66%|██████▌   | 244686/371472 [8:25:58<9:19:53,  3.77it/s]
 66%|██████▌   | 244687/371472 [8:25:58<9:48:32,  3.59it/s]
 66%|██████▌   | 244688/371472 [8:25:58<9:20:02,  3.77it/s]
 66%|██████▌   | 244689/371472 [8:25:59<9:35:22,  3.67it/s]
 66%|██████▌   | 244690/371472 [8:25:59<10:10:03,  3.46it/s]
 66%|██████▌   | 244691/371472 [8:25:59<9:50:05,  3.58it/s] 
 66%|██████▌   | 244692/371472 [8:25:59<9:39:55,  3.64it/s]
 66%|██████▌   | 244693/371472 [8:26:00<9:32:58,  3.69it/s]
 66%|██████▌   | 244694/371472 [8:26:00<9:40:26,  3.64it/s]
 66%|██████▌   | 244695/371472 [8:26:00<9:27:06,  3.73it/s]
 66%|██████▌   | 244696/371472 [8:26:01<9:12:13,  3.83it/s]
 66%|██████▌   | 244697/371472 [8:26:01<10:04:04,  3.50it/s]
 66%|██████▌   | 244698/371472 [8:26:01<9:48:52,  3.59it/s] 
 66%|██████▌   | 244699/371472 [8:26:01<9:40:29,  3.64it/s]
 66%|██████▌   | 244700/371472 [8:26:02<10:05:43,  3.49it/s]
                                                            
{'loss': 2.9215, 'learning_rate': 4.0730784977051865e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244700/371472 [8:26:02<10:05:43,  3.49it/s]
 66%|██████▌   | 244701/371472 [8:26:02<10:09:34,  3.47it/s]
 66%|██████▌   | 244702/371472 [8:26:02<10:41:08,  3.30it/s]
 66%|██████▌   | 244703/371472 [8:26:03<10:18:39,  3.42it/s]
 66%|██████▌   | 244704/371472 [8:26:03<10:02:31,  3.51it/s]
 66%|█████���▌   | 244705/371472 [8:26:03<9:34:53,  3.68it/s] 
 66%|██████▌   | 244706/371472 [8:26:03<9:12:16,  3.83it/s]
 66%|██████▌   | 244707/371472 [8:26:04<9:05:37,  3.87it/s]
 66%|██████▌   | 244708/371472 [8:26:04<9:05:53,  3.87it/s]
 66%|██████▌   | 244709/371472 [8:26:04<9:18:58,  3.78it/s]
 66%|██████▌   | 244710/371472 [8:26:04<9:39:06,  3.65it/s]
 66%|██████▌   | 244711/371472 [8:26:05<10:34:09,  3.33it/s]
 66%|██████▌   | 244712/371472 [8:26:05<10:30:46,  3.35it/s]
 66%|██████▌   | 244713/371472 [8:26:05<10:08:42,  3.47it/s]
 66%|██████▌   | 244714/371472 [8:26:06<9:52:31,  3.57it/s] 
 66%|██████▌   | 244715/371472 [8:26:06<9:51:45,  3.57it/s]
 66%|██████▌   | 244716/371472 [8:26:06<9:40:20,  3.64it/s]
 66%|██████▌   | 244717/371472 [8:26:06<9:28:42,  3.71it/s]
 66%|██████▌   | 244718/371472 [8:26:07<9:23:43,  3.75it/s]
 66%|██████▌   | 244719/371472 [8:26:07<9:18:55,  3.78it/s]
 66%|██████▌   | 244720/371472 [8:26:07<9:08:06,  3.85it/s]
                                                           
{'loss': 2.8731, 'learning_rate': 4.072593677950397e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244720/371472 [8:26:07<9:08:06,  3.85it/s]
 66%|██████▌   | 244721/371472 [8:26:07<9:06:46,  3.86it/s]
 66%|██████▌   | 244722/371472 [8:26:08<9:34:31,  3.68it/s]
 66%|██████▌   | 244723/371472 [8:26:08<9:46:17,  3.60it/s]
 66%|██████▌   | 244724/371472 [8:26:08<9:19:58,  3.77it/s]
 66%|██████▌   | 244725/371472 [8:26:09<9:23:36,  3.75it/s]
 66%|██████▌   | 244726/371472 [8:26:09<9:35:19,  3.67it/s]
 66%|██████▌   | 244727/371472 [8:26:09<9:48:40,  3.59it/s]
 66%|██████▌   | 244728/371472 [8:26:09<10:37:58,  3.31it/s]
 66%|██████▌   | 244729/371472 [8:26:10<10:16:11,  3.43it/s]
 66%|██████▌   | 244730/371472 [8:26:10<9:51:36,  3.57it/s] 
 66%|██████▌   | 244731/371472 [8:26:10<9:47:24,  3.60it/s]
 66%|██████▌   | 244732/371472 [8:26:11<9:24:51,  3.74it/s]
 66%|██████▌   | 244733/371472 [8:26:11<9:18:09,  3.78it/s]
 66%|██████▌   | 244734/371472 [8:26:11<9:31:10,  3.70it/s]
 66%|██████▌   | 244735/371472 [8:26:11<9:51:38,  3.57it/s]
 66%|██████▌   | 244736/371472 [8:26:12<9:24:58,  3.74it/s]
 66%|██████▌   | 244737/371472 [8:26:12<9:27:15,  3.72it/s]
 66%|██████▌   | 244738/371472 [8:26:12<9:39:31,  3.64it/s]
 66%|██████▌   | 244739/371472 [8:26:12<9:52:54,  3.56it/s]
 66%|██████▌   | 244740/371472 [8:26:13<11:39:57,  3.02it/s]
                                                            
{'loss': 2.7206, 'learning_rate': 4.072108858195609e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244740/371472 [8:26:13<11:39:57,  3.02it/s]
 66%|██████▌   | 244741/371472 [8:26:13<10:37:35,  3.31it/s]
 66%|██████▌   | 244742/371472 [8:26:13<10:19:57,  3.41it/s]
 66%|██████▌   | 244743/371472 [8:26:14<10:10:52,  3.46it/s]
 66%|██████▌   | 244744/371472 [8:26:14<9:46:07,  3.60it/s] 
 66%|██████▌   | 244745/371472 [8:26:14<9:45:17,  3.61it/s]
 66%|██████▌   | 244746/371472 [8:26:15<10:26:00,  3.37it/s]
 66%|██████▌   | 244747/371472 [8:26:15<10:31:42,  3.34it/s]
 66%|██████▌   | 244748/371472 [8:26:15<10:29:40,  3.35it/s]
 66%|██████▌   | 244749/371472 [8:26:15<9:59:45,  3.52it/s] 
 66%|██████▌   | 244750/371472 [8:26:16<11:58:31,  2.94it/s]
 66%|██████▌   | 244751/371472 [8:26:16<11:12:23,  3.14it/s]
 66%|██████▌   | 244752/371472 [8:26:16<10:44:33,  3.28it/s]
 66%|██████▌   | 244753/371472 [8:26:17<10:41:32,  3.29it/s]
 66%|██████▌   | 244754/371472 [8:26:17<10:26:00,  3.37it/s]
 66%|██████▌   | 244755/371472 [8:26:17<10:09:30,  3.46it/s]
 66%|██████▌   | 244756/371472 [8:26:18<10:28:51,  3.36it/s]
 66%|██████▌   | 244757/371472 [8:26:18<10:34:16,  3.33it/s]
 66%|██████▌   | 244758/371472 [8:26:18<9:52:25,  3.56it/s] 
 66%|██████▌   | 244759/371472 [8:26:18<9:28:11,  3.72it/s]
 66%|██████▌   | 244760/371472 [8:26:19<9:20:39,  3.77it/s]
                                                           
{'loss': 2.9216, 'learning_rate': 4.0716240384408197e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244760/371472 [8:26:19<9:20:39,  3.77it/s]
 66%|██████▌   | 244761/371472 [8:26:19<9:12:05,  3.83it/s]
 66%|██████▌   | 244762/371472 [8:26:19<9:31:02,  3.70it/s]
 66%|██████▌   | 244763/371472 [8:26:19<9:26:42,  3.73it/s]
 66%|██████▌   | 244764/371472 [8:26:20<10:15:51,  3.43it/s]
 66%|██████▌   | 244765/371472 [8:26:20<9:46:20,  3.60it/s] 
 66%|██████▌   | 244766/371472 [8:26:20<9:30:38,  3.70it/s]
 66%|██████▌   | 244767/371472 [8:26:21<9:22:22,  3.76it/s]
 66%|██████▌   | 244768/371472 [8:26:21<9:05:54,  3.87it/s]
 66%|██████▌   | 244769/371472 [8:26:21<8:56:14,  3.94it/s]
 66%|██████▌   | 244770/371472 [8:26:21<9:03:25,  3.89it/s]
 66%|██████▌   | 244771/371472 [8:26:22<9:59:52,  3.52it/s]
 66%|██████▌   | 244772/371472 [8:26:22<9:37:37,  3.66it/s]
 66%|██████▌   | 244773/371472 [8:26:22<9:40:55,  3.63it/s]
 66%|██████▌   | 244774/371472 [8:26:22<10:18:14,  3.42it/s]
 66%|██████▌   | 244775/371472 [8:26:23<9:59:18,  3.52it/s] 
 66%|██████▌   | 244776/371472 [8:26:23<9:57:36,  3.53it/s]
 66%|██████▌   | 244777/371472 [8:26:23<9:46:45,  3.60it/s]
 66%|██████▌   | 244778/371472 [8:26:24<9:31:13,  3.70it/s]
 66%|██████▌   | 244779/371472 [8:26:24<9:19:12,  3.78it/s]
 66%|██████▌   | 244780/371472 [8:26:24<9:44:17,  3.61it/s]
                                                           
{'loss': 2.7353, 'learning_rate': 4.07113921868603e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244780/371472 [8:26:24<9:44:17,  3.61it/s]
 66%|██████▌   | 244781/371472 [8:26:24<9:49:11,  3.58it/s]
 66%|██████▌   | 244782/371472 [8:26:25<9:21:03,  3.76it/s]
 66%|██████▌   | 244783/371472 [8:26:25<9:07:09,  3.86it/s]
 66%|██████▌   | 244784/371472 [8:26:25<9:07:35,  3.86it/s]
 66%|██████▌   | 244785/371472 [8:26:25<9:01:48,  3.90it/s]
 66%|██████▌   | 244786/371472 [8:26:26<9:36:27,  3.66it/s]
 66%|██████▌   | 244787/371472 [8:26:26<9:50:23,  3.58it/s]
 66%|██████▌   | 244788/371472 [8:26:26<9:52:47,  3.56it/s]
 66%|██████▌   | 244789/371472 [8:26:27<9:28:42,  3.71it/s]
 66%|██████▌   | 244790/371472 [8:26:27<9:41:21,  3.63it/s]
 66%|██████▌   | 244791/371472 [8:26:27<9:29:22,  3.71it/s]
 66%|██████▌   | 244792/371472 [8:26:27<9:50:11,  3.58it/s]
 66%|██████▌   | 244793/371472 [8:26:28<9:29:17,  3.71it/s]
 66%|██████▌   | 244794/371472 [8:26:28<9:09:23,  3.84it/s]
 66%|██████▌   | 244795/371472 [8:26:28<9:02:17,  3.89it/s]
 66%|██████▌   | 244796/371472 [8:26:28<9:42:42,  3.62it/s]
 66%|██████▌   | 244797/371472 [8:26:29<9:41:16,  3.63it/s]
 66%|██████▌   | 244798/371472 [8:26:29<10:39:47,  3.30it/s]
 66%|██████▌   | 244799/371472 [8:26:29<10:20:31,  3.40it/s]
 66%|██████▌   | 244800/371472 [8:26:30<10:12:31,  3.45it/s]
                                                            
{'loss': 2.7489, 'learning_rate': 4.070654398931242e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244800/371472 [8:26:30<10:12:31,  3.45it/s]
 66%|██████▌   | 244801/371472 [8:26:30<9:44:56,  3.61it/s] 
 66%|██████▌   | 244802/371472 [8:26:30<10:12:51,  3.44it/s]
 66%|██████▌   | 244803/371472 [8:26:30<9:38:42,  3.65it/s] 
 66%|██████▌   | 244804/371472 [8:26:31<9:31:56,  3.69it/s]
 66%|██████▌   | 244805/371472 [8:26:31<10:06:17,  3.48it/s]
 66%|██████▌   | 244806/371472 [8:26:31<9:54:47,  3.55it/s] 
 66%|██████▌   | 244807/371472 [8:26:32<9:49:37,  3.58it/s]
 66%|██████▌   | 244808/371472 [8:26:32<9:39:30,  3.64it/s]
 66%|██████▌   | 244809/371472 [8:26:32<9:24:39,  3.74it/s]
 66%|██████▌   | 244810/371472 [8:26:32<9:13:05,  3.82it/s]
 66%|██████▌   | 244811/371472 [8:26:33<9:12:25,  3.82it/s]
 66%|██████▌   | 244812/371472 [8:26:33<9:18:36,  3.78it/s]
 66%|██████▌   | 244813/371472 [8:26:33<9:25:09,  3.74it/s]
 66%|██████▌   | 244814/371472 [8:26:33<9:34:58,  3.67it/s]
 66%|██████▌   | 244815/371472 [8:26:34<9:27:25,  3.72it/s]
 66%|██████▌   | 244816/371472 [8:26:34<10:11:50,  3.45it/s]
 66%|██████▌   | 244817/371472 [8:26:34<9:50:53,  3.57it/s] 
 66%|██████▌   | 244818/371472 [8:26:35<9:54:41,  3.55it/s]
 66%|██████▌   | 244819/371472 [8:26:35<9:58:32,  3.53it/s]
 66%|██████▌   | 244820/371472 [8:26:35<9:50:25,  3.58it/s]
                                                           
{'loss': 2.867, 'learning_rate': 4.0701695791764524e-07, 'epoch': 10.54}
+
 66%|██████▌   | 244820/371472 [8:26:35<9:50:25,  3.58it/s]
 66%|██████▌   | 244821/371472 [8:26:35<9:56:01,  3.54it/s]
 66%|██████▌   | 244822/371472 [8:26:36<9:48:05,  3.59it/s]
 66%|██████▌   | 244823/371472 [8:26:36<9:42:21,  3.62it/s]
 66%|██████▌   | 244824/371472 [8:26:36<9:28:12,  3.71it/s]
 66%|██████▌   | 244825/371472 [8:26:37<10:01:46,  3.51it/s]
 66%|██████▌   | 244826/371472 [8:26:37<10:09:58,  3.46it/s]
 66%|██████▌   | 244827/371472 [8:26:37<10:21:02,  3.40it/s]
 66%|██████▌   | 244828/371472 [8:26:37<9:50:32,  3.57it/s] 
 66%|██████▌   | 244829/371472 [8:26:38<9:59:02,  3.52it/s]
 66%|██████▌   | 244830/371472 [8:26:38<9:37:19,  3.66it/s]
 66%|██████▌   | 244831/371472 [8:26:38<10:06:36,  3.48it/s]
 66%|██████▌   | 244832/371472 [8:26:39<11:04:34,  3.18it/s]
 66%|██████▌   | 244833/371472 [8:26:39<10:55:15,  3.22it/s]
 66%|██████▌   | 244834/371472 [8:26:39<11:03:51,  3.18it/s]
 66%|██████▌   | 244835/371472 [8:26:39<10:17:00,  3.42it/s]
 66%|██████▌   | 244836/371472 [8:26:40<9:50:21,  3.58it/s] 
 66%|██████▌   | 244837/371472 [8:26:40<9:34:43,  3.67it/s]
 66%|██████▌   | 244838/371472 [8:26:40<10:06:29,  3.48it/s]
 66%|██████▌   | 244839/371472 [8:26:41<10:09:25,  3.46it/s]
 66%|██████▌   | 244840/371472 [8:26:41<9:55:42,  3.54it/s] 
                                                           
{'loss': 2.7139, 'learning_rate': 4.0696847594216637e-07, 'epoch': 10.55}
+
 66%|██████▌   | 244840/371472 [8:26:41<9:55:42,  3.54it/s]
 66%|██████▌   | 244841/371472 [8:26:41<9:52:55,  3.56it/s]
 66%|██████▌   | 244842/371472 [8:26:41<9:31:47,  3.69it/s]
 66%|██████▌   | 244843/371472 [8:26:42<9:29:57,  3.70it/s]
 66%|██████▌   | 244844/371472 [8:26:42<9:38:50,  3.65it/s]
 66%|██████▌   | 244845/371472 [8:26:42<9:34:56,  3.67it/s]
 66%|██████▌   | 244846/371472 [8:26:42<9:13:39,  3.81it/s]
 66%|██████▌   | 244847/371472 [8:26:43<9:29:42,  3.70it/s]
 66%|██████▌   | 244848/371472 [8:26:43<10:00:06,  3.52it/s]
 66%|██████▌   | 244849/371472 [8:26:43<10:08:12,  3.47it/s]
 66%|██████▌   | 244850/371472 [8:26:44<9:52:06,  3.56it/s] 
 66%|██████▌   | 244851/371472 [8:26:44<9:41:23,  3.63it/s]
 66%|██████▌   | 244852/371472 [8:26:44<9:38:44,  3.65it/s]
 66%|██████▌   | 244853/371472 [8:26:44<9:19:01,  3.77it/s]
 66%|██████▌   | 244854/371472 [8:26:45<9:03:10,  3.89it/s]
 66%|██████▌   | 244855/371472 [8:26:45<8:51:39,  3.97it/s]
 66%|██████▌   | 244856/371472 [8:26:45<9:35:22,  3.67it/s]
 66%|██████▌   | 244857/371472 [8:26:45<9:34:23,  3.67it/s]
 66%|██████▌   | 244858/371472 [8:26:46<10:05:32,  3.48it/s]
 66%|██████▌   | 244859/371472 [8:26:46<10:36:35,  3.31it/s]
 66%|██████▌   | 244860/371472 [8:26:46<11:07:13,  3.16it/s]
                                                            
{'loss': 2.821, 'learning_rate': 4.0691999396668744e-07, 'epoch': 10.55}
+
 66%|██████▌   | 244860/371472 [8:26:46<11:07:13,  3.16it/s]
 66%|██████▌   | 244861/371472 [8:26:47<11:27:39,  3.07it/s]
 66%|██████▌   | 244862/371472 [8:26:47<10:44:16,  3.28it/s]
 66%|██████▌   | 244863/371472 [8:26:47<9:58:51,  3.52it/s] 
 66%|██████▌   | 244864/371472 [8:26:48<9:46:12,  3.60it/s]
 66%|██████▌   | 244865/371472 [8:26:48<10:13:49,  3.44it/s]
 66%|██████▌   | 244866/371472 [8:26:48<9:57:55,  3.53it/s] 
 66%|██████▌   | 244867/371472 [8:26:48<9:41:30,  3.63it/s]
 66%|██████▌   | 244868/371472 [8:26:49<9:44:11,  3.61it/s]
 66%|██████▌   | 244869/371472 [8:26:49<9:50:23,  3.57it/s]
 66%|██████▌   | 244870/371472 [8:26:49<9:52:38,  3.56it/s]
 66%|██████▌   | 244871/371472 [8:26:50<9:36:44,  3.66it/s]
 66%|██████▌   | 244872/371472 [8:26:50<9:37:39,  3.65it/s]
 66%|██████▌   | 244873/371472 [8:26:50<9:43:48,  3.61it/s]
 66%|██████▌   | 244874/371472 [8:26:50<9:53:32,  3.55it/s]
 66%|██████▌   | 244875/371472 [8:26:51<10:42:02,  3.29it/s]
 66%|██████▌   | 244876/371472 [8:26:51<10:13:27,  3.44it/s]
 66%|██████▌   | 244877/371472 [8:26:51<10:05:41,  3.48it/s]
 66%|██████▌   | 244878/371472 [8:26:52<10:19:25,  3.41it/s]
 66%|██████▌   | 244879/371472 [8:26:52<9:46:59,  3.59it/s] 
 66%|██████▌   | 244880/371472 [8:26:52<9:54:45,  3.55it/s]
                                                           
{'loss': 2.7853, 'learning_rate': 4.068715119912086e-07, 'epoch': 10.55}
+
 66%|██████▌   | 244880/371472 [8:26:52<9:54:45,  3.55it/s]
 66%|██████▌   | 244881/371472 [8:26:52<9:39:09,  3.64it/s]
 66%|██████▌   | 244882/371472 [8:26:53<9:55:44,  3.54it/s]
 66%|██████▌   | 244883/371472 [8:26:53<9:38:55,  3.64it/s]
 66%|██████▌   | 244884/371472 [8:26:53<9:34:16,  3.67it/s]
 66%|██████▌   | 244885/371472 [8:26:53<9:17:55,  3.78it/s]
 66%|██████▌   | 244886/371472 [8:26:54<9:34:25,  3.67it/s]
 66%|██████▌   | 244887/371472 [8:26:54<9:38:33,  3.65it/s]
 66%|██████▌   | 244888/371472 [8:26:54<9:58:53,  3.52it/s]
 66%|██████▌   | 244889/371472 [8:26:55<10:02:13,  3.50it/s]
 66%|██████▌   | 244890/371472 [8:26:55<9:32:32,  3.68it/s] 
 66%|██████▌   | 244891/371472 [8:26:55<9:46:13,  3.60it/s]
 66%|██████▌   | 244892/371472 [8:26:55<10:00:32,  3.51it/s]
 66%|██████▌   | 244893/371472 [8:26:56<9:59:29,  3.52it/s] 
 66%|██████▌   | 244894/371472 [8:26:56<9:51:44,  3.57it/s]
 66%|██████▌   | 244895/371472 [8:26:56<10:23:49,  3.38it/s]
 66%|██████▌   | 244896/371472 [8:26:57<10:04:03,  3.49it/s]
 66%|██████▌   | 244897/371472 [8:26:57<9:59:18,  3.52it/s] 
 66%|██████▌   | 244898/371472 [8:26:57<9:37:37,  3.65it/s]
 66%|██████▌   | 244899/371472 [8:26:57<9:40:32,  3.63it/s]
 66%|██████▌   | 244900/371472 [8:26:58<9:15:31,  3.80it/s]
                                                           
{'loss': 2.8347, 'learning_rate': 4.0682303001572963e-07, 'epoch': 10.55}
+
 66%|██████▌   | 244900/371472 [8:26:58<9:15:31,  3.80it/s]
 66%|██████▌   | 244901/371472 [8:26:58<9:31:20,  3.69it/s]
 66%|██████▌   | 244902/371472 [8:26:58<9:13:47,  3.81it/s]
 66%|██████▌   | 244903/371472 [8:26:58<9:00:47,  3.90it/s]
 66%|██████▌   | 244904/371472 [8:26:59<9:09:06,  3.84it/s]
 66%|██████▌   | 244905/371472 [8:26:59<8:59:39,  3.91it/s]
 66%|██████▌   | 244906/371472 [8:26:59<8:53:21,  3.96it/s]
 66%|██████▌   | 244907/371472 [8:26:59<9:39:32,  3.64it/s]
 66%|██████▌   | 244908/371472 [8:27:00<10:34:44,  3.32it/s]
 66%|██████▌   | 244909/371472 [8:27:00<10:35:55,  3.32it/s]
 66%|██████▌   | 244910/371472 [8:27:00<10:02:02,  3.50it/s]
 66%|██████▌   | 244911/371472 [8:27:01<10:14:11,  3.43it/s]
 66%|██████▌   | 244912/371472 [8:27:01<9:46:49,  3.59it/s] 
 66%|██████▌   | 244913/371472 [8:27:01<9:46:48,  3.59it/s]
 66%|██████▌   | 244914/371472 [8:27:02<9:54:36,  3.55it/s]
 66%|██████▌   | 244915/371472 [8:27:02<10:25:21,  3.37it/s]
 66%|██████▌   | 244916/371472 [8:27:02<10:52:36,  3.23it/s]
 66%|██████▌   | 244917/371472 [8:27:02<10:33:23,  3.33it/s]
 66%|██████▌   | 244918/371472 [8:27:03<10:45:14,  3.27it/s]
 66%|██████▌   | 244919/371472 [8:27:03<10:12:52,  3.44it/s]
 66%|██████▌   | 244920/371472 [8:27:03<10:15:34,  3.43it/s]
                                                            
{'loss': 2.8383, 'learning_rate': 4.067745480402508e-07, 'epoch': 10.55}
+
 66%|██████▌   | 244920/371472 [8:27:03<10:15:34,  3.43it/s]
 66%|██████▌   | 244921/371472 [8:27:04<9:54:32,  3.55it/s] 
 66%|██████▌   | 244922/371472 [8:27:04<9:36:39,  3.66it/s]
 66%|██████▌   | 244923/371472 [8:27:04<9:39:41,  3.64it/s]
 66%|██████▌   | 244924/371472 [8:27:04<9:30:37,  3.70it/s]
 66%|██████▌   | 244925/371472 [8:27:05<10:06:12,  3.48it/s]
 66%|██████▌   | 244926/371472 [8:27:05<10:22:16,  3.39it/s]
 66%|██████▌   | 244927/371472 [8:27:05<9:45:01,  3.61it/s] 
 66%|██████▌   | 244928/371472 [8:27:05<9:23:33,  3.74it/s]
 66%|██████▌   | 244929/371472 [8:27:06<8:57:11,  3.93it/s]
 66%|██████▌   | 244930/371472 [8:27:06<9:44:13,  3.61it/s]
 66%|██████▌   | 244931/371472 [8:27:06<9:48:04,  3.59it/s]
 66%|██████▌   | 244932/371472 [8:27:07<9:59:51,  3.52it/s]
 66%|██████▌   | 244933/371472 [8:27:07<9:49:24,  3.58it/s]
 66%|██████▌   | 244934/371472 [8:27:07<10:10:30,  3.45it/s]
 66%|██████▌   | 244935/371472 [8:27:07<10:00:12,  3.51it/s]
 66%|██████▌   | 244936/371472 [8:27:08<10:14:34,  3.43it/s]
 66%|██████▌   | 244937/371472 [8:27:08<9:44:12,  3.61it/s] 
 66%|██████▌   | 244938/371472 [8:27:08<9:36:00,  3.66it/s]
 66%|██████▌   | 244939/371472 [8:27:09<9:33:28,  3.68it/s]
 66%|██████▌   | 244940/371472 [8:27:09<9:42:40,  3.62it/s]
                                                           
{'loss': 2.8723, 'learning_rate': 4.067260660647719e-07, 'epoch': 10.55}
+
 66%|██████▌   | 244940/371472 [8:27:09<9:42:40,  3.62it/s]
 66%|██████▌   | 244941/371472 [8:27:09<9:39:02,  3.64it/s]
 66%|██████▌   | 244942/371472 [8:27:09<9:32:20,  3.68it/s]
 66%|██████▌   | 244943/371472 [8:27:10<10:37:14,  3.31it/s]
 66%|██████▌   | 244944/371472 [8:27:10<10:29:42,  3.35it/s]
 66%|██████▌   | 244945/371472 [8:27:10<10:49:35,  3.25it/s]
 66%|██████▌   | 244946/371472 [8:27:11<10:50:29,  3.24it/s]
 66%|██████▌   | 244947/371472 [8:27:11<10:01:57,  3.50it/s]
 66%|██████▌   | 244948/371472 [8:27:11<9:35:19,  3.67it/s] 
 66%|██████▌   | 244949/371472 [8:27:11<10:01:15,  3.51it/s]
 66%|██████▌   | 244950/371472 [8:27:12<9:50:34,  3.57it/s] 
 66%|██████▌   | 244951/371472 [8:27:12<10:04:12,  3.49it/s]
 66%|██████▌   | 244952/371472 [8:27:12<9:47:03,  3.59it/s] 
 66%|██████▌   | 244953/371472 [8:27:13<9:46:23,  3.60it/s]
 66%|██████▌   | 244954/371472 [8:27:13<9:52:27,  3.56it/s]
 66%|██████▌   | 244955/371472 [8:27:13<9:41:28,  3.63it/s]
 66%|██████▌   | 244956/371472 [8:27:13<9:22:59,  3.75it/s]
 66%|██████▌   | 244957/371472 [8:27:14<10:03:33,  3.49it/s]
 66%|██████▌   | 244958/371472 [8:27:14<9:34:38,  3.67it/s] 
 66%|██████▌   | 244959/371472 [8:27:14<9:39:38,  3.64it/s]
 66%|██████▌   | 244960/371472 [8:27:15<9:58:45,  3.52it/s]
                                                           
{'loss': 2.9038, 'learning_rate': 4.06677584089293e-07, 'epoch': 10.55}
+
 66%|██████▌   | 244960/371472 [8:27:15<9:58:45,  3.52it/s]
 66%|██████▌   | 244961/371472 [8:27:15<9:24:53,  3.73it/s]
 66%|██████▌   | 244962/371472 [8:27:15<9:40:46,  3.63it/s]
 66%|██████▌   | 244963/371472 [8:27:15<9:28:55,  3.71it/s]
 66%|██████▌   | 244964/371472 [8:27:16<10:00:09,  3.51it/s]
 66%|██████▌   | 244965/371472 [8:27:16<9:43:01,  3.62it/s] 
 66%|██████▌   | 244966/371472 [8:27:16<9:19:09,  3.77it/s]
 66%|██████▌   | 244967/371472 [8:27:16<9:58:18,  3.52it/s]
 66%|██████▌   | 244968/371472 [8:27:17<9:57:46,  3.53it/s]
 66%|██████▌   | 244969/371472 [8:27:17<10:35:28,  3.32it/s]
 66%|██████▌   | 244970/371472 [8:27:17<10:44:52,  3.27it/s]
 66%|██████▌   | 244971/371472 [8:27:18<10:37:36,  3.31it/s]
 66%|██████▌   | 244972/371472 [8:27:18<10:32:02,  3.34it/s]
 66%|██████▌   | 244973/371472 [8:27:18<10:13:54,  3.43it/s]
 66%|██████▌   | 244974/371472 [8:27:19<9:51:36,  3.56it/s] 
 66%|██████▌   | 244975/371472 [8:27:19<10:01:57,  3.50it/s]
 66%|██████▌   | 244976/371472 [8:27:19<9:47:50,  3.59it/s] 
 66%|██████▌   | 244977/371472 [8:27:19<9:41:43,  3.62it/s]
 66%|██████▌   | 244978/371472 [8:27:20<11:07:51,  3.16it/s]
 66%|██████▌   | 244979/371472 [8:27:20<10:31:22,  3.34it/s]
 66%|██████▌   | 244980/371472 [8:27:20<9:47:00,  3.59it/s] 
                                                           
{'loss': 2.8467, 'learning_rate': 4.066291021138141e-07, 'epoch': 10.55}
+
 66%|██████▌   | 244980/371472 [8:27:20<9:47:00,  3.59it/s]
 66%|██████▌   | 244981/371472 [8:27:21<9:31:50,  3.69it/s]
 66%|██████▌   | 244982/371472 [8:27:21<9:43:53,  3.61it/s]
 66%|██████▌   | 244983/371472 [8:27:21<9:53:54,  3.55it/s]
 66%|██████▌   | 244984/371472 [8:27:21<10:10:50,  3.45it/s]
 66%|██████▌   | 244985/371472 [8:27:22<10:35:37,  3.32it/s]
 66%|██████▌   | 244986/371472 [8:27:22<10:10:08,  3.46it/s]
 66%|██████▌   | 244987/371472 [8:27:22<9:45:07,  3.60it/s] 
 66%|██████▌   | 244988/371472 [8:27:23<9:38:57,  3.64it/s]
 66%|██████▌   | 244989/371472 [8:27:23<9:22:40,  3.75it/s]
 66%|██████▌   | 244990/371472 [8:27:23<9:39:49,  3.64it/s]
 66%|██████▌   | 244991/371472 [8:27:23<9:22:12,  3.75it/s]
 66%|██████▌   | 244992/371472 [8:27:24<8:54:01,  3.95it/s]
 66%|██████▌   | 244993/371472 [8:27:24<9:38:01,  3.65it/s]
 66%|██████▌   | 244994/371472 [8:27:24<10:24:55,  3.37it/s]
 66%|██████▌   | 244995/371472 [8:27:25<10:44:06,  3.27it/s]
 66%|██████▌   | 244996/371472 [8:27:25<10:23:46,  3.38it/s]
 66%|██████▌   | 244997/371472 [8:27:25<9:54:21,  3.55it/s] 
 66%|██████▌   | 244998/371472 [8:27:25<10:20:50,  3.40it/s]
 66%|██████▌   | 244999/371472 [8:27:26<10:00:31,  3.51it/s]
 66%|██████▌   | 245000/371472 [8:27:26<9:40:33,  3.63it/s] 
                                                           
{'loss': 2.7221, 'learning_rate': 4.0658062013833525e-07, 'epoch': 10.55}
+
 66%|██████▌   | 245000/371472 [8:27:26<9:40:33,  3.63it/s]
 66%|██████▌   | 245001/371472 [8:27:26<10:33:16,  3.33it/s]
 66%|██████▌   | 245002/371472 [8:27:27<10:49:47,  3.24it/s]
 66%|██████▌   | 245003/371472 [8:27:27<10:32:49,  3.33it/s]
 66%|██████▌   | 245004/371472 [8:27:27<10:04:44,  3.49it/s]
 66%|██████▌   | 245005/371472 [8:27:27<10:01:08,  3.51it/s]
 66%|██████▌   | 245006/371472 [8:27:28<9:58:29,  3.52it/s] 
 66%|██████▌   | 245007/371472 [8:27:28<9:40:48,  3.63it/s]
 66%|██████▌   | 245008/371472 [8:27:28<9:44:51,  3.60it/s]
 66%|██████▌   | 245009/371472 [8:27:29<10:26:06,  3.37it/s]
 66%|██████▌   | 245010/371472 [8:27:29<10:19:37,  3.40it/s]
 66%|██████▌   | 245011/371472 [8:27:29<10:03:35,  3.49it/s]
 66%|██████▌   | 245012/371472 [8:27:29<10:09:23,  3.46it/s]
 66%|██████▌   | 245013/371472 [8:27:30<9:54:50,  3.54it/s] 
 66%|██████▌   | 245014/371472 [8:27:30<9:49:44,  3.57it/s]
 66%|██████▌   | 245015/371472 [8:27:30<9:50:31,  3.57it/s]
 66%|██████▌   | 245016/371472 [8:27:30<9:34:57,  3.67it/s]
 66%|██████▌   | 245017/371472 [8:27:31<9:39:44,  3.64it/s]
 66%|██████▌   | 245018/371472 [8:27:31<9:37:17,  3.65it/s]
 66%|██████▌   | 245019/371472 [8:27:31<9:36:52,  3.65it/s]
 66%|██████▌   | 245020/371472 [8:27:32<9:15:15,  3.80it/s]
                                                           
{'loss': 2.9386, 'learning_rate': 4.0653213816285627e-07, 'epoch': 10.55}
+
 66%|██████▌   | 245020/371472 [8:27:32<9:15:15,  3.80it/s]
 66%|██████▌   | 245021/371472 [8:27:32<9:09:47,  3.83it/s]
 66%|██████▌   | 245022/371472 [8:27:32<9:12:20,  3.82it/s]
 66%|██████▌   | 245023/371472 [8:27:32<8:59:18,  3.91it/s]
 66%|██████▌   | 245024/371472 [8:27:33<8:58:32,  3.91it/s]
 66%|██████▌   | 245025/371472 [8:27:33<9:24:37,  3.73it/s]
 66%|██████▌   | 245026/371472 [8:27:33<9:09:23,  3.84it/s]
 66%|██████▌   | 245027/371472 [8:27:33<9:12:09,  3.82it/s]
 66%|██████▌   | 245028/371472 [8:27:34<9:51:47,  3.56it/s]
 66%|██████▌   | 245029/371472 [8:27:34<9:39:11,  3.64it/s]
 66%|██████▌   | 245030/371472 [8:27:34<9:41:01,  3.63it/s]
 66%|██████▌   | 245031/371472 [8:27:34<9:35:58,  3.66it/s]
 66%|██████▌   | 245032/371472 [8:27:35<9:14:40,  3.80it/s]
 66%|██████▌   | 245033/371472 [8:27:35<9:26:59,  3.72it/s]
 66%|██████▌   | 245034/371472 [8:27:35<9:07:15,  3.85it/s]
 66%|██████▌   | 245035/371472 [8:27:35<8:56:38,  3.93it/s]
 66%|██████▌   | 245036/371472 [8:27:36<9:12:17,  3.82it/s]
 66%|██████▌   | 245037/371472 [8:27:36<9:52:11,  3.56it/s]
 66%|██████▌   | 245038/371472 [8:27:36<10:42:49,  3.28it/s]
 66%|██████▌   | 245039/371472 [8:27:37<10:05:22,  3.48it/s]
 66%|██████▌   | 245040/371472 [8:27:37<10:25:58,  3.37it/s]
                                                            
{'loss': 2.8489, 'learning_rate': 4.0648365618737745e-07, 'epoch': 10.55}
+
 66%|██████▌   | 245040/371472 [8:27:37<10:25:58,  3.37it/s]
 66%|██████▌   | 245041/371472 [8:27:37<10:12:09,  3.44it/s]
 66%|██████▌   | 245042/371472 [8:27:38<10:08:05,  3.47it/s]
 66%|██████▌   | 245043/371472 [8:27:38<9:58:06,  3.52it/s] 
 66%|██████▌   | 245044/371472 [8:27:38<9:35:20,  3.66it/s]
 66%|██████▌   | 245045/371472 [8:27:38<9:12:35,  3.81it/s]
 66%|██████▌   | 245046/371472 [8:27:39<9:46:11,  3.59it/s]
 66%|██████▌   | 245047/371472 [8:27:39<9:24:47,  3.73it/s]
 66%|██████▌   | 245048/371472 [8:27:39<9:30:15,  3.69it/s]
 66%|██████▌   | 245049/371472 [8:27:39<9:45:29,  3.60it/s]
 66%|██████▌   | 245050/371472 [8:27:40<9:52:23,  3.56it/s]
 66%|██████▌   | 245051/371472 [8:27:40<9:53:31,  3.55it/s]
 66%|██████▌   | 245052/371472 [8:27:40<9:31:39,  3.69it/s]
 66%|██████▌   | 245053/371472 [8:27:41<9:37:08,  3.65it/s]
 66%|██████▌   | 245054/371472 [8:27:41<9:06:54,  3.85it/s]
 66%|██████▌   | 245055/371472 [8:27:41<9:05:13,  3.86it/s]
 66%|██████▌   | 245056/371472 [8:27:41<9:08:00,  3.84it/s]
 66%|██████▌   | 245057/371472 [8:27:42<8:53:42,  3.95it/s]
 66%|██████▌   | 245058/371472 [8:27:42<8:48:41,  3.99it/s]
 66%|██████▌   | 245059/371472 [8:27:42<9:10:30,  3.83it/s]
 66%|██████▌   | 245060/371472 [8:27:42<9:42:41,  3.62it/s]
                                                           
{'loss': 2.9406, 'learning_rate': 4.064351742118985e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245060/371472 [8:27:42<9:42:41,  3.62it/s]
 66%|██████▌   | 245061/371472 [8:27:43<9:33:52,  3.67it/s]
 66%|██████▌   | 245062/371472 [8:27:43<9:49:04,  3.58it/s]
 66%|██████▌   | 245063/371472 [8:27:43<10:50:17,  3.24it/s]
 66%|██████▌   | 245064/371472 [8:27:44<10:31:02,  3.34it/s]
 66%|██████▌   | 245065/371472 [8:27:44<10:16:25,  3.42it/s]
 66%|██████▌   | 245066/371472 [8:27:44<9:53:19,  3.55it/s] 
 66%|██████��   | 245067/371472 [8:27:44<9:24:41,  3.73it/s]
 66%|██████▌   | 245068/371472 [8:27:45<9:40:01,  3.63it/s]
 66%|██████▌   | 245069/371472 [8:27:45<9:39:24,  3.64it/s]
 66%|██████▌   | 245070/371472 [8:27:45<10:12:18,  3.44it/s]
 66%|██████▌   | 245071/371472 [8:27:46<10:32:39,  3.33it/s]
 66%|██████▌   | 245072/371472 [8:27:46<10:05:18,  3.48it/s]
 66%|██████▌   | 245073/371472 [8:27:46<9:51:31,  3.56it/s] 
 66%|██████▌   | 245074/371472 [8:27:46<9:50:52,  3.57it/s]
 66%|██████▌   | 245075/371472 [8:27:47<10:00:56,  3.51it/s]
 66%|██████▌   | 245076/371472 [8:27:47<9:35:49,  3.66it/s] 
 66%|██████▌   | 245077/371472 [8:27:47<9:15:50,  3.79it/s]
 66%|██████▌   | 245078/371472 [8:27:47<9:01:54,  3.89it/s]
 66%|██████▌   | 245079/371472 [8:27:48<9:10:30,  3.83it/s]
 66%|██████▌   | 245080/371472 [8:27:48<9:48:28,  3.58it/s]
                                                           
{'loss': 2.8764, 'learning_rate': 4.0638669223641965e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245080/371472 [8:27:48<9:48:28,  3.58it/s]
 66%|██████▌   | 245081/371472 [8:27:48<10:20:26,  3.40it/s]
 66%|██████▌   | 245082/371472 [8:27:49<9:50:38,  3.57it/s] 
 66%|██████▌   | 245083/371472 [8:27:49<10:14:23,  3.43it/s]
 66%|██████▌   | 245084/371472 [8:27:49<10:05:59,  3.48it/s]
 66%|██████▌   | 245085/371472 [8:27:49<9:41:20,  3.62it/s] 
 66%|██████▌   | 245086/371472 [8:27:50<9:50:37,  3.57it/s]
 66%|██████▌   | 245087/371472 [8:27:50<9:57:36,  3.52it/s]
 66%|██████▌   | 245088/371472 [8:27:50<9:54:56,  3.54it/s]
 66%|██████▌   | 245089/371472 [8:27:51<9:49:27,  3.57it/s]
 66%|██████▌   | 245090/371472 [8:27:51<9:36:23,  3.65it/s]
 66%|██████▌   | 245091/371472 [8:27:51<10:41:08,  3.29it/s]
 66%|██████▌   | 245092/371472 [8:27:52<11:10:43,  3.14it/s]
 66%|██████▌   | 245093/371472 [8:27:52<10:45:11,  3.26it/s]
 66%|██████▌   | 245094/371472 [8:27:52<10:31:09,  3.34it/s]
 66%|██████▌   | 245095/371472 [8:27:52<10:32:00,  3.33it/s]
 66%|██████▌   | 245096/371472 [8:27:53<10:06:00,  3.48it/s]
 66%|██████▌   | 245097/371472 [8:27:53<9:49:02,  3.58it/s] 
 66%|██████▌   | 245098/371472 [8:27:53<9:34:20,  3.67it/s]
 66%|██████▌   | 245099/371472 [8:27:54<10:09:48,  3.45it/s]
 66%|██████▌   | 245100/371472 [8:27:54<10:49:20,  3.24it/s]
                                                            
{'loss': 2.8631, 'learning_rate': 4.063382102609407e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245100/371472 [8:27:54<10:49:20,  3.24it/s]
 66%|██████▌   | 245101/371472 [8:27:54<10:17:07,  3.41it/s]
 66%|██████▌   | 245102/371472 [8:27:54<10:12:50,  3.44it/s]
 66%|██████▌   | 245103/371472 [8:27:55<9:54:09,  3.54it/s] 
 66%|██████▌   | 245104/371472 [8:27:55<9:44:01,  3.61it/s]
 66%|██████▌   | 245105/371472 [8:27:55<9:24:31,  3.73it/s]
 66%|██████▌   | 245106/371472 [8:27:55<9:25:53,  3.72it/s]
 66%|██████▌   | 245107/371472 [8:27:56<9:27:08,  3.71it/s]
 66%|██████▌   | 245108/371472 [8:27:56<9:03:30,  3.87it/s]
 66%|██████▌   | 245109/371472 [8:27:56<9:20:21,  3.76it/s]
 66%|██████▌   | 245110/371472 [8:27:56<9:01:50,  3.89it/s]
 66%|██████▌   | 245111/371472 [8:27:57<9:22:50,  3.74it/s]
 66%|██████▌   | 245112/371472 [8:27:57<8:59:47,  3.90it/s]
 66%|██████▌   | 245113/371472 [8:27:57<8:57:35,  3.92it/s]
 66%|██████▌   | 245114/371472 [8:27:58<8:57:43,  3.92it/s]
 66%|██████▌   | 245115/371472 [8:27:58<8:48:43,  3.98it/s]
 66%|██████▌   | 245116/371472 [8:27:58<9:09:08,  3.83it/s]
 66%|██████▌   | 245117/371472 [8:27:58<10:28:24,  3.35it/s]
 66%|██████▌   | 245118/371472 [8:27:59<10:11:14,  3.45it/s]
 66%|██████▌   | 245119/371472 [8:27:59<9:43:04,  3.61it/s] 
 66%|██████▌   | 245120/371472 [8:27:59<9:29:43,  3.70it/s]
                                                           
{'loss': 2.7572, 'learning_rate': 4.062897282854619e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245120/371472 [8:27:59<9:29:43,  3.70it/s]
 66%|██████▌   | 245121/371472 [8:27:59<9:35:58,  3.66it/s]
 66%|██████▌   | 245122/371472 [8:28:00<10:27:38,  3.36it/s]
 66%|██████▌   | 245123/371472 [8:28:00<9:54:45,  3.54it/s] 
 66%|██████▌   | 245124/371472 [8:28:00<9:54:42,  3.54it/s]
 66%|██████▌   | 245125/371472 [8:28:01<9:52:58,  3.55it/s]
 66%|██████▌   | 245126/371472 [8:28:01<10:11:30,  3.44it/s]
 66%|██████▌   | 245127/371472 [8:28:01<9:40:49,  3.63it/s] 
 66%|██████▌   | 245128/371472 [8:28:01<9:19:08,  3.77it/s]
 66%|██████▌   | 245129/371472 [8:28:02<9:35:25,  3.66it/s]
 66%|██████▌   | 245130/371472 [8:28:02<9:12:30,  3.81it/s]
 66%|██████▌   | 245131/371472 [8:28:02<9:32:11,  3.68it/s]
 66%|██████▌   | 245132/371472 [8:28:03<10:06:55,  3.47it/s]
 66%|██████▌   | 245133/371472 [8:28:03<10:28:38,  3.35it/s]
 66%|██████▌   | 245134/371472 [8:28:03<10:18:57,  3.40it/s]
 66%|██████▌   | 245135/371472 [8:28:03<10:08:35,  3.46it/s]
 66%|██████▌   | 245136/371472 [8:28:04<9:44:47,  3.60it/s] 
 66%|██████▌   | 245137/371472 [8:28:04<9:24:37,  3.73it/s]
 66%|██████▌   | 245138/371472 [8:28:04<9:24:06,  3.73it/s]
 66%|██████▌   | 245139/371472 [8:28:04<9:11:28,  3.82it/s]
 66%|██████▌   | 245140/371472 [8:28:05<9:36:00,  3.66it/s]
                                                           
{'loss': 2.7063, 'learning_rate': 4.0624124630998297e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245140/371472 [8:28:05<9:36:00,  3.66it/s]
 66%|██████▌   | 245141/371472 [8:28:05<9:50:32,  3.57it/s]
 66%|██████▌   | 245142/371472 [8:28:05<9:36:27,  3.65it/s]
 66%|██████▌   | 245143/371472 [8:28:06<9:40:37,  3.63it/s]
 66%|██████▌   | 245144/371472 [8:28:06<9:25:37,  3.72it/s]
 66%|██████▌   | 245145/371472 [8:28:06<9:26:46,  3.71it/s]
 66%|██████▌   | 245146/371472 [8:28:06<9:07:34,  3.84it/s]
 66%|██████▌   | 245147/371472 [8:28:07<9:03:59,  3.87it/s]
 66%|██████▌   | 245148/371472 [8:28:07<9:27:38,  3.71it/s]
 66%|██████▌   | 245149/371472 [8:28:07<10:10:45,  3.45it/s]
 66%|██████▌   | 245150/371472 [8:28:08<9:44:26,  3.60it/s] 
 66%|██████▌   | 245151/371472 [8:28:08<9:58:56,  3.52it/s]
 66%|██████▌   | 245152/371472 [8:28:08<10:19:21,  3.40it/s]
 66%|██████▌   | 245153/371472 [8:28:08<10:23:01,  3.38it/s]
 66%|██████▌   | 245154/371472 [8:28:09<9:58:30,  3.52it/s] 
 66%|██████▌   | 245155/371472 [8:28:09<10:00:19,  3.51it/s]
 66%|██████▌   | 245156/371472 [8:28:09<9:30:42,  3.69it/s] 
 66%|██████▌   | 245157/371472 [8:28:09<9:11:13,  3.82it/s]
 66%|██████▌   | 245158/371472 [8:28:10<9:04:59,  3.86it/s]
 66%|██████▌   | 245159/371472 [8:28:10<9:17:37,  3.78it/s]
 66%|██████▌   | 245160/371472 [8:28:10<9:14:14,  3.80it/s]
                                                           
{'loss': 3.054, 'learning_rate': 4.061927643345041e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245160/371472 [8:28:10<9:14:14,  3.80it/s]
 66%|██████▌   | 245161/371472 [8:28:11<9:21:19,  3.75it/s]
 66%|██████▌   | 245162/371472 [8:28:11<9:40:11,  3.63it/s]
 66%|██████▌   | 245163/371472 [8:28:11<9:39:36,  3.63it/s]
 66%|██████▌   | 245164/371472 [8:28:11<9:46:38,  3.59it/s]
 66%|██████▌   | 245165/371472 [8:28:12<12:46:59,  2.74it/s]
 66%|██████▌   | 245166/371472 [8:28:12<11:40:35,  3.00it/s]
 66%|██████▌   | 245167/371472 [8:28:13<11:27:52,  3.06it/s]
 66%|██████▌   | 245168/371472 [8:28:13<10:51:35,  3.23it/s]
 66%|██████▌   | 245169/371472 [8:28:13<11:03:26,  3.17it/s]
 66%|██████▌   | 245170/371472 [8:28:13<10:54:51,  3.21it/s]
 66%|██████▌   | 245171/371472 [8:28:14<10:16:19,  3.42it/s]
 66%|██████▌   | 245172/371472 [8:28:14<11:09:24,  3.14it/s]
 66%|██████▌   | 245173/371472 [8:28:14<10:23:57,  3.37it/s]
 66%|██████▌   | 245174/371472 [8:28:15<10:49:39,  3.24it/s]
 66%|██████▌   | 245175/371472 [8:28:15<10:15:10,  3.42it/s]
 66%|██████▌   | 245176/371472 [8:28:15<9:35:20,  3.66it/s] 
 66%|██████▌   | 245177/371472 [8:28:15<9:15:27,  3.79it/s]
 66%|██████▌   | 245178/371472 [8:28:16<9:02:33,  3.88it/s]
 66%|██████▌   | 245179/371472 [8:28:16<8:57:43,  3.91it/s]
 66%|██████▌   | 245180/371472 [8:28:16<9:02:53,  3.88it/s]
                                                           
{'loss': 2.8574, 'learning_rate': 4.0614428235902516e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245180/371472 [8:28:16<9:02:53,  3.88it/s]
 66%|██████▌   | 245181/371472 [8:28:16<9:23:32,  3.74it/s]
 66%|██████▌   | 245182/371472 [8:28:17<9:22:53,  3.74it/s]
 66%|██████▌   | 245183/371472 [8:28:17<9:07:26,  3.84it/s]
 66%|██████▌   | 245184/371472 [8:28:17<9:30:49,  3.69it/s]
 66%|██████▌   | 245185/371472 [8:28:17<9:24:28,  3.73it/s]
 66%|██████▌   | 245186/371472 [8:28:18<9:17:26,  3.78it/s]
 66%|██████▌   | 245187/371472 [8:28:18<9:32:53,  3.67it/s]
 66%|██████▌   | 245188/371472 [8:28:18<9:44:54,  3.60it/s]
 66%|██████▌   | 245189/371472 [8:28:19<9:33:45,  3.67it/s]
 66%|██████▌   | 245190/371472 [8:28:19<9:47:48,  3.58it/s]
 66%|██████▌   | 245191/371472 [8:28:19<9:44:07,  3.60it/s]
 66%|██████▌   | 245192/371472 [8:28:19<9:39:54,  3.63it/s]
 66%|██████▌   | 245193/371472 [8:28:20<9:45:31,  3.59it/s]
 66%|██████▌   | 245194/371472 [8:28:20<9:46:03,  3.59it/s]
 66%|██████▌   | 245195/371472 [8:28:20<9:38:26,  3.64it/s]
 66%|██████▌   | 245196/371472 [8:28:21<9:50:17,  3.57it/s]
 66%|██████▌   | 245197/371472 [8:28:21<9:55:42,  3.53it/s]
 66%|██████▌   | 245198/371472 [8:28:21<10:17:26,  3.41it/s]
 66%|██████▌   | 245199/371472 [8:28:21<10:14:48,  3.42it/s]
 66%|██████▌   | 245200/371472 [8:28:22<9:54:19,  3.54it/s] 
                                                           
{'loss': 3.0175, 'learning_rate': 4.0609580038354634e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245200/371472 [8:28:22<9:54:19,  3.54it/s]
 66%|██████▌   | 245201/371472 [8:28:22<9:54:01,  3.54it/s]
 66%|██████▌   | 245202/371472 [8:28:22<9:55:54,  3.53it/s]
 66%|██████▌   | 245203/371472 [8:28:23<9:31:19,  3.68it/s]
 66%|██████▌   | 245204/371472 [8:28:23<9:18:42,  3.77it/s]
 66%|██████▌   | 245205/371472 [8:28:23<9:15:25,  3.79it/s]
 66%|██████▌   | 245206/371472 [8:28:23<9:02:28,  3.88it/s]
 66%|██████▌   | 245207/371472 [8:28:24<9:02:00,  3.88it/s]
 66%|██████▌   | 245208/371472 [8:28:24<9:43:46,  3.60it/s]
 66%|██████▌   | 245209/371472 [8:28:24<9:35:10,  3.66it/s]
 66%|██████▌   | 245210/371472 [8:28:24<9:55:50,  3.53it/s]
 66%|██████▌   | 245211/371472 [8:28:25<10:05:13,  3.48it/s]
 66%|██████▌   | 245212/371472 [8:28:25<9:29:28,  3.70it/s] 
 66%|██████▌   | 245213/371472 [8:28:25<9:13:47,  3.80it/s]
 66%|██████▌   | 245214/371472 [8:28:26<9:55:46,  3.53it/s]
 66%|██████▌   | 245215/371472 [8:28:26<9:59:56,  3.51it/s]
 66%|██████▌   | 245216/371472 [8:28:26<9:37:58,  3.64it/s]
 66%|██████▌   | 245217/371472 [8:28:26<9:32:37,  3.67it/s]
 66%|██████▌   | 245218/371472 [8:28:27<10:38:11,  3.30it/s]
 66%|██████▌   | 245219/371472 [8:28:27<10:01:46,  3.50it/s]
 66%|██████▌   | 245220/371472 [8:28:27<9:50:03,  3.57it/s] 
                                                           
{'loss': 2.7361, 'learning_rate': 4.060473184080674e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245220/371472 [8:28:27<9:50:03,  3.57it/s]
 66%|██████▌   | 245221/371472 [8:28:28<10:41:33,  3.28it/s]
 66%|██████▌   | 245222/371472 [8:28:28<10:05:49,  3.47it/s]
 66%|██████▌   | 245223/371472 [8:28:28<10:15:32,  3.42it/s]
 66%|██████▌   | 245224/371472 [8:28:28<9:53:08,  3.55it/s] 
 66%|██████▌   | 245225/371472 [8:28:29<10:10:46,  3.44it/s]
 66%|██████▌   | 245226/371472 [8:28:29<9:53:41,  3.54it/s] 
 66%|██████▌   | 245227/371472 [8:28:29<10:07:04,  3.47it/s]
 66%|██████▌   | 245228/371472 [8:28:30<9:50:37,  3.56it/s] 
 66%|██████▌   | 245229/371472 [8:28:30<9:33:18,  3.67it/s]
 66%|██████▌   | 245230/371472 [8:28:30<9:44:06,  3.60it/s]
 66%|██████▌   | 245231/371472 [8:28:30<9:41:10,  3.62it/s]
 66%|██████▌   | 245232/371472 [8:28:31<9:28:28,  3.70it/s]
 66%|██████▌   | 245233/371472 [8:28:31<9:27:37,  3.71it/s]
 66%|██████▌   | 245234/371472 [8:28:31<9:32:29,  3.68it/s]
 66%|██████▌   | 245235/371472 [8:28:31<9:48:31,  3.57it/s]
 66%|██████▌   | 245236/371472 [8:28:32<9:35:34,  3.66it/s]
 66%|██████▌   | 245237/371472 [8:28:32<9:35:14,  3.66it/s]
 66%|██████▌   | 245238/371472 [8:28:32<9:33:12,  3.67it/s]
 66%|██████▌   | 245239/371472 [8:28:33<9:30:40,  3.69it/s]
 66%|██████▌   | 245240/371472 [8:28:33<9:21:28,  3.75it/s]
                                                           
{'loss': 2.8103, 'learning_rate': 4.0599883643258854e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245240/371472 [8:28:33<9:21:28,  3.75it/s]
 66%|██████▌   | 245241/371472 [8:28:33<9:08:56,  3.83it/s]
 66%|██████▌   | 245242/371472 [8:28:33<9:46:22,  3.59it/s]
 66%|██████▌   | 245243/371472 [8:28:34<9:24:55,  3.72it/s]
 66%|██████▌   | 245244/371472 [8:28:34<9:21:20,  3.75it/s]
 66%|██████▌   | 245245/371472 [8:28:34<9:28:50,  3.70it/s]
 66%|██████▌   | 245246/371472 [8:28:34<9:28:44,  3.70it/s]
 66%|██████▌   | 245247/371472 [8:28:35<9:16:54,  3.78it/s]
 66%|██████▌   | 245248/371472 [8:28:35<9:34:26,  3.66it/s]
 66%|██████▌   | 245249/371472 [8:28:35<9:25:28,  3.72it/s]
 66%|██████▌   | 245250/371472 [8:28:35<9:10:41,  3.82it/s]
 66%|██████▌   | 245251/371472 [8:28:36<9:29:38,  3.69it/s]
 66%|██████▌   | 245252/371472 [8:28:36<9:17:07,  3.78it/s]
 66%|██████▌   | 245253/371472 [8:28:36<9:40:00,  3.63it/s]
 66%|██████▌   | 245254/371472 [8:28:37<9:53:18,  3.55it/s]
 66%|██████▌   | 245255/371472 [8:28:37<10:02:38,  3.49it/s]
 66%|██████▌   | 245256/371472 [8:28:37<10:14:46,  3.42it/s]
 66%|██████▌   | 245257/371472 [8:28:37<10:30:19,  3.34it/s]
 66%|██████▌   | 245258/371472 [8:28:38<10:51:29,  3.23it/s]
 66%|██████▌   | 245259/371472 [8:28:38<10:23:42,  3.37it/s]
 66%|██████▌   | 245260/371472 [8:28:38<10:00:05,  3.51it/s]
                                                            
{'loss': 3.0218, 'learning_rate': 4.059503544571096e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245260/371472 [8:28:38<10:00:05,  3.51it/s]
 66%|██████▌   | 245261/371472 [8:28:39<9:49:05,  3.57it/s] 
 66%|██████▌   | 245262/371472 [8:28:39<9:34:05,  3.66it/s]
 66%|██████▌   | 245263/371472 [8:28:39<9:28:17,  3.70it/s]
 66%|██████▌   | 245264/371472 [8:28:39<9:36:47,  3.65it/s]
 66%|██████▌   | 245265/371472 [8:28:40<9:17:50,  3.77it/s]
 66%|██████▌   | 245266/371472 [8:28:40<10:00:20,  3.50it/s]
 66%|██████▌   | 245267/371472 [8:28:40<9:45:51,  3.59it/s] 
 66%|██████▌   | 245268/371472 [8:28:41<9:25:09,  3.72it/s]
 66%|██████▌   | 245269/371472 [8:28:41<9:24:35,  3.73it/s]
 66%|██████▌   | 245270/371472 [8:28:41<9:40:57,  3.62it/s]
 66%|██████▌   | 245271/371472 [8:28:41<10:13:06,  3.43it/s]
 66%|██████▌   | 245272/371472 [8:28:42<9:41:45,  3.62it/s] 
 66%|██████▌   | 245273/371472 [8:28:42<10:03:29,  3.49it/s]
 66%|██████▌   | 245274/371472 [8:28:42<9:43:16,  3.61it/s] 
 66%|██████▌   | 245275/371472 [8:28:42<9:35:14,  3.66it/s]
 66%|██████▌   | 245276/371472 [8:28:43<9:11:17,  3.82it/s]
 66%|██████▌   | 245277/371472 [8:28:43<9:26:14,  3.71it/s]
 66%|██████▌   | 245278/371472 [8:28:43<9:13:44,  3.80it/s]
 66%|██████▌   | 245279/371472 [8:28:43<8:56:05,  3.92it/s]
 66%|██████▌   | 245280/371472 [8:28:44<9:07:51,  3.84it/s]
                                                           
{'loss': 2.8368, 'learning_rate': 4.0590187248163073e-07, 'epoch': 10.56}
+
 66%|██████▌   | 245280/371472 [8:28:44<9:07:51,  3.84it/s]
 66%|██████▌   | 245281/371472 [8:28:44<9:12:55,  3.80it/s]
 66%|██████▌   | 245282/371472 [8:28:44<9:14:55,  3.79it/s]
 66%|██████▌   | 245283/371472 [8:28:45<9:12:45,  3.80it/s]
 66%|██████▌   | 245284/371472 [8:28:45<9:57:27,  3.52it/s]
 66%|██████▌   | 245285/371472 [8:28:45<10:14:52,  3.42it/s]
 66%|██████▌   | 245286/371472 [8:28:46<10:26:53,  3.35it/s]
 66%|██████▌   | 245287/371472 [8:28:46<10:41:19,  3.28it/s]
 66%|██████▌   | 245288/371472 [8:28:46<10:02:45,  3.49it/s]
 66%|██████▌   | 245289/371472 [8:28:46<11:25:18,  3.07it/s]
 66%|██████▌   | 245290/371472 [8:28:47<10:46:30,  3.25it/s]
 66%|██████▌   | 245291/371472 [8:28:47<10:20:54,  3.39it/s]
 66%|██████▌   | 245292/371472 [8:28:47<9:40:07,  3.63it/s] 
 66%|██████▌   | 245293/371472 [8:28:48<9:39:18,  3.63it/s]
 66%|██████▌   | 245294/371472 [8:28:48<10:22:03,  3.38it/s]
 66%|██████▌   | 245295/371472 [8:28:48<11:16:19,  3.11it/s]
 66%|██████▌   | 245296/371472 [8:28:49<10:49:04,  3.24it/s]
 66%|██████▌   | 245297/371472 [8:28:49<10:12:46,  3.43it/s]
 66%|██████▌   | 245298/371472 [8:28:49<10:04:40,  3.48it/s]
 66%|██████▌   | 245299/371472 [8:28:49<9:43:09,  3.61it/s] 
 66%|██████▌   | 245300/371472 [8:28:50<9:22:33,  3.74it/s]
                                                           
{'loss': 2.9361, 'learning_rate': 4.058533905061518e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245300/371472 [8:28:50<9:22:33,  3.74it/s]
 66%|██████▌   | 245301/371472 [8:28:50<9:33:52,  3.66it/s]
 66%|██████▌   | 245302/371472 [8:28:50<9:21:59,  3.74it/s]
 66%|██████▌   | 245303/371472 [8:28:50<9:04:25,  3.86it/s]
 66%|██████▌   | 245304/371472 [8:28:51<9:04:06,  3.86it/s]
 66%|██████▌   | 245305/371472 [8:28:51<8:44:38,  4.01it/s]
 66%|██████▌   | 245306/371472 [8:28:51<8:58:52,  3.90it/s]
 66%|██████▌   | 245307/371472 [8:28:51<8:50:57,  3.96it/s]
 66%|██████▌   | 245308/371472 [8:28:52<8:59:15,  3.90it/s]
 66%|██████▌   | 245309/371472 [8:28:52<8:48:14,  3.98it/s]
 66%|██████▌   | 245310/371472 [8:28:52<9:18:11,  3.77it/s]
 66%|██████▌   | 245311/371472 [8:28:52<9:32:57,  3.67it/s]
 66%|██████▌   | 245312/371472 [8:28:53<10:47:46,  3.25it/s]
 66%|██████▌   | 245313/371472 [8:28:53<10:39:36,  3.29it/s]
 66%|██████▌   | 245314/371472 [8:28:53<10:15:47,  3.41it/s]
 66%|██████▌   | 245315/371472 [8:28:54<10:13:21,  3.43it/s]
 66%|██████▌   | 245316/371472 [8:28:54<9:48:47,  3.57it/s] 
 66%|██████▌   | 245317/371472 [8:28:54<9:47:14,  3.58it/s]
 66%|██████▌   | 245318/371472 [8:28:54<9:43:24,  3.60it/s]
 66%|██████▌   | 245319/371472 [8:28:55<9:58:02,  3.52it/s]
 66%|██████▌   | 245320/371472 [8:28:55<9:49:51,  3.56it/s]
                                                           
{'loss': 2.8011, 'learning_rate': 4.058049085306729e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245320/371472 [8:28:55<9:49:51,  3.56it/s]
 66%|██████▌   | 245321/371472 [8:28:55<9:33:20,  3.67it/s]
 66%|██████▌   | 245322/371472 [8:28:56<9:31:10,  3.68it/s]
 66%|██████▌   | 245323/371472 [8:28:56<9:48:17,  3.57it/s]
 66%|██████▌   | 245324/371472 [8:28:56<9:39:11,  3.63it/s]
 66%|██████▌   | 245325/371472 [8:28:56<10:09:19,  3.45it/s]
 66%|██████▌   | 245326/371472 [8:28:57<12:25:53,  2.82it/s]
 66%|██████▌   | 245327/371472 [8:28:57<11:27:25,  3.06it/s]
 66%|██████▌   | 245328/371472 [8:28:57<10:47:26,  3.25it/s]
 66%|██████▌   | 245329/371472 [8:28:58<10:15:01,  3.42it/s]
 66%|██████▌   | 245330/371472 [8:28:58<9:58:35,  3.51it/s] 
 66%|██████▌   | 245331/371472 [8:28:58<9:39:41,  3.63it/s]
 66%|██████▌   | 245332/371472 [8:28:59<9:45:57,  3.59it/s]
 66%|██████▌   | 245333/371472 [8:28:59<9:44:03,  3.60it/s]
 66%|██████▌   | 245334/371472 [8:28:59<9:45:52,  3.59it/s]
 66%|██████▌   | 245335/371472 [8:28:59<9:25:47,  3.72it/s]
 66%|██████▌   | 245336/371472 [8:29:00<9:17:57,  3.77it/s]
 66%|██████▌   | 245337/371472 [8:29:00<9:27:03,  3.71it/s]
 66%|██████▌   | 245338/371472 [8:29:00<9:48:37,  3.57it/s]
 66%|██████▌   | 245339/371472 [8:29:00<9:41:06,  3.62it/s]
 66%|██████▌   | 245340/371472 [8:29:01<9:44:23,  3.60it/s]
                                                           
{'loss': 2.8076, 'learning_rate': 4.05756426555194e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245340/371472 [8:29:01<9:44:23,  3.60it/s]
 66%|██████▌   | 245341/371472 [8:29:01<10:04:20,  3.48it/s]
 66%|██████▌   | 245342/371472 [8:29:01<10:42:56,  3.27it/s]
 66%|██████▌   | 245343/371472 [8:29:02<10:09:43,  3.45it/s]
 66%|██████▌   | 245344/371472 [8:29:02<10:18:35,  3.40it/s]
 66%|██████▌   | 245345/371472 [8:29:02<9:50:30,  3.56it/s] 
 66%|██████▌   | 245346/371472 [8:29:03<10:03:52,  3.48it/s]
 66%|██████▌   | 245347/371472 [8:29:03<9:40:22,  3.62it/s] 
 66%|██████▌   | 245348/371472 [8:29:03<9:25:42,  3.72it/s]
 66%|██████▌   | 245349/371472 [8:29:03<9:43:03,  3.61it/s]
 66%|██████▌   | 245350/371472 [8:29:04<9:48:48,  3.57it/s]
 66%|██████▌   | 245351/371472 [8:29:04<10:59:06,  3.19it/s]
 66%|██████▌   | 245352/371472 [8:29:04<10:34:21,  3.31it/s]
 66%|██████▌   | 245353/371472 [8:29:04<9:49:34,  3.57it/s] 
 66%|██████▌   | 245354/371472 [8:29:05<10:28:26,  3.34it/s]
 66%|██████▌   | 245355/371472 [8:29:05<10:00:59,  3.50it/s]
 66%|██████▌   | 245356/371472 [8:29:05<10:20:42,  3.39it/s]
 66%|██████▌   | 245357/371472 [8:29:06<10:30:36,  3.33it/s]
 66%|██████▌   | 245358/371472 [8:29:06<9:56:59,  3.52it/s] 
 66%|██████▌   | 245359/371472 [8:29:06<10:07:39,  3.46it/s]
 66%|██████▌   | 245360/371472 [8:29:07<10:10:32,  3.44it/s]
                                                            
{'loss': 2.8064, 'learning_rate': 4.0570794457971507e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245360/371472 [8:29:07<10:10:32,  3.44it/s]
 66%|██████▌   | 245361/371472 [8:29:07<11:02:30,  3.17it/s]
 66%|██████▌   | 245362/371472 [8:29:07<11:30:34,  3.04it/s]
 66%|██████▌   | 245363/371472 [8:29:08<10:51:16,  3.23it/s]
 66%|██████▌   | 245364/371472 [8:29:08<10:24:30,  3.37it/s]
 66%|██████▌   | 245365/371472 [8:29:08<9:59:44,  3.50it/s] 
 66%|██████▌   | 245366/371472 [8:29:08<9:45:57,  3.59it/s]
 66%|██████▌   | 245367/371472 [8:29:09<9:32:27,  3.67it/s]
 66%|██████▌   | 245368/371472 [8:29:09<9:22:33,  3.74it/s]
 66%|██████▌   | 245369/371472 [8:29:09<9:16:40,  3.78it/s]
 66%|██████▌   | 245370/371472 [8:29:09<9:32:22,  3.67it/s]
 66%|██████▌   | 245371/371472 [8:29:10<9:45:24,  3.59it/s]
 66%|██████▌   | 245372/371472 [8:29:10<9:20:36,  3.75it/s]
 66%|██████▌   | 245373/371472 [8:29:10<9:23:40,  3.73it/s]
 66%|██████▌   | 245374/371472 [8:29:10<9:19:26,  3.76it/s]
 66%|██████▌   | 245375/371472 [8:29:11<9:14:42,  3.79it/s]
 66%|██████▌   | 245376/371472 [8:29:11<9:13:50,  3.79it/s]
 66%|██████▌   | 245377/371472 [8:29:11<8:54:59,  3.93it/s]
 66%|██████▌   | 245378/371472 [8:29:11<9:03:36,  3.87it/s]
 66%|██████▌   | 245379/371472 [8:29:12<9:09:45,  3.82it/s]
 66%|██████▌   | 245380/371472 [8:29:12<9:46:40,  3.58it/s]
                                                           
{'loss': 2.6836, 'learning_rate': 4.0565946260423625e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245380/371472 [8:29:12<9:46:40,  3.58it/s]
 66%|██████▌   | 245381/371472 [8:29:12<9:45:52,  3.59it/s]
 66%|██████▌   | 245382/371472 [8:29:13<9:47:22,  3.58it/s]
 66%|██████▌   | 245383/371472 [8:29:13<9:45:27,  3.59it/s]
 66%|██████▌   | 245384/371472 [8:29:13<9:39:22,  3.63it/s]
 66%|██████▌   | 245385/371472 [8:29:13<9:30:26,  3.68it/s]
 66%|██████▌   | 245386/371472 [8:29:14<9:18:17,  3.76it/s]
 66%|██████▌   | 245387/371472 [8:29:14<9:08:26,  3.83it/s]
 66%|██████▌   | 245388/371472 [8:29:14<8:57:35,  3.91it/s]
 66%|██████▌   | 245389/371472 [8:29:14<8:55:11,  3.93it/s]
 66%|██████▌   | 245390/371472 [8:29:15<8:59:22,  3.90it/s]
 66%|██████▌   | 245391/371472 [8:29:15<8:54:04,  3.93it/s]
 66%|██████▌   | 245392/371472 [8:29:15<8:43:59,  4.01it/s]
 66%|██████▌   | 245393/371472 [8:29:15<9:13:09,  3.80it/s]
 66%|██████▌   | 245394/371472 [8:29:16<9:23:01,  3.73it/s]
 66%|██████▌   | 245395/371472 [8:29:16<9:00:09,  3.89it/s]
 66%|██████▌   | 245396/371472 [8:29:16<9:25:12,  3.72it/s]
 66%|██████▌   | 245397/371472 [8:29:17<9:14:29,  3.79it/s]
 66%|██████▌   | 245398/371472 [8:29:17<9:23:35,  3.73it/s]
 66%|██████▌   | 245399/371472 [8:29:17<9:09:14,  3.83it/s]
 66%|██████▌   | 245400/371472 [8:29:17<9:05:09,  3.85it/s]
                                                           
{'loss': 2.98, 'learning_rate': 4.0561098062875727e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245400/371472 [8:29:17<9:05:09,  3.85it/s]
 66%|██████▌   | 245401/371472 [8:29:18<9:32:53,  3.67it/s]
 66%|██████▌   | 245402/371472 [8:29:18<10:43:40,  3.26it/s]
 66%|██████▌   | 245403/371472 [8:29:18<10:01:30,  3.49it/s]
 66%|██████▌   | 245404/371472 [8:29:19<9:35:16,  3.65it/s] 
 66%|██████▌   | 245405/371472 [8:29:19<9:20:13,  3.75it/s]
 66%|██████▌   | 245406/371472 [8:29:19<9:30:14,  3.68it/s]
 66%|██████▌   | 245407/371472 [8:29:19<9:51:29,  3.55it/s]
 66%|██████▌   | 245408/371472 [8:29:20<9:41:05,  3.62it/s]
 66%|██████▌   | 245409/371472 [8:29:20<9:32:15,  3.67it/s]
 66%|██████▌   | 245410/371472 [8:29:20<9:16:47,  3.77it/s]
 66%|██████▌   | 245411/371472 [8:29:20<9:56:37,  3.52it/s]
 66%|██████▌   | 245412/371472 [8:29:21<9:47:09,  3.58it/s]
 66%|██████▌   | 245413/371472 [8:29:21<9:18:58,  3.76it/s]
 66%|██████▌   | 245414/371472 [8:29:21<9:20:32,  3.75it/s]
 66%|██████▌   | 245415/371472 [8:29:21<9:30:27,  3.68it/s]
 66%|██████▌   | 245416/371472 [8:29:22<9:12:15,  3.80it/s]
 66%|██████▌   | 245417/371472 [8:29:22<9:32:36,  3.67it/s]
 66%|██████▌   | 245418/371472 [8:29:22<9:23:41,  3.73it/s]
 66%|██████▌   | 245419/371472 [8:29:23<9:22:13,  3.74it/s]
 66%|██████▌   | 245420/371472 [8:29:23<9:21:22,  3.74it/s]
                                                           
{'loss': 2.8401, 'learning_rate': 4.0556249865327844e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245420/371472 [8:29:23<9:21:22,  3.74it/s]
 66%|██████▌   | 245421/371472 [8:29:23<10:01:03,  3.50it/s]
 66%|██████▌   | 245422/371472 [8:29:23<9:51:38,  3.55it/s] 
 66%|██████▌   | 245423/371472 [8:29:24<10:01:58,  3.49it/s]
 66%|██████▌   | 245424/371472 [8:29:24<9:46:02,  3.58it/s] 
 66%|██████▌   | 245425/371472 [8:29:24<9:42:04,  3.61it/s]
 66%|██████▌   | 245426/371472 [8:29:25<9:48:49,  3.57it/s]
 66%|██████▌   | 245427/371472 [8:29:25<9:17:51,  3.77it/s]
 66%|██████▌   | 245428/371472 [8:29:25<10:10:16,  3.44it/s]
 66%|██████▌   | 245429/371472 [8:29:25<10:04:17,  3.48it/s]
 66%|██████▌   | 245430/371472 [8:29:26<10:26:20,  3.35it/s]
 66%|██████▌   | 245431/371472 [8:29:26<10:00:23,  3.50it/s]
 66%|██████▌   | 245432/371472 [8:29:26<9:42:02,  3.61it/s] 
 66%|██████▌   | 245433/371472 [8:29:27<9:31:03,  3.68it/s]
 66%|██████▌   | 245434/371472 [8:29:27<9:45:02,  3.59it/s]
 66%|██████▌   | 245435/371472 [8:29:27<9:33:21,  3.66it/s]
 66%|██████▌   | 245436/371472 [8:29:27<9:15:31,  3.78it/s]
 66%|██████▌   | 245437/371472 [8:29:28<9:14:51,  3.79it/s]
 66%|██████▌   | 245438/371472 [8:29:28<9:17:16,  3.77it/s]
 66%|██████▌   | 245439/371472 [8:29:28<9:23:28,  3.73it/s]
 66%|██████▌   | 245440/371472 [8:29:28<9:57:40,  3.51it/s]
                                                           
{'loss': 2.8088, 'learning_rate': 4.055140166777995e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245440/371472 [8:29:28<9:57:40,  3.51it/s]
 66%|██████▌   | 245441/371472 [8:29:29<11:08:58,  3.14it/s]
 66%|██████▌   | 245442/371472 [8:29:29<12:01:13,  2.91it/s]
 66%|██████▌   | 245443/371472 [8:29:30<11:17:38,  3.10it/s]
 66%|██████▌   | 245444/371472 [8:29:30<11:18:23,  3.10it/s]
 66%|██████▌   | 245445/371472 [8:29:30<10:30:19,  3.33it/s]
 66%|██████▌   | 245446/371472 [8:29:30<10:00:16,  3.50it/s]
 66%|██████▌   | 245447/371472 [8:29:31<10:36:52,  3.30it/s]
 66%|██████▌   | 245448/371472 [8:29:31<10:23:39,  3.37it/s]
 66%|██████▌   | 245449/371472 [8:29:31<9:56:10,  3.52it/s] 
 66%|██████▌   | 245450/371472 [8:29:31<9:36:54,  3.64it/s]
 66%|██████▌   | 245451/371472 [8:29:32<9:54:33,  3.53it/s]
 66%|██████▌   | 245452/371472 [8:29:32<10:13:41,  3.42it/s]
 66%|██████▌   | 245453/371472 [8:29:32<9:52:42,  3.54it/s] 
 66%|██████▌   | 245454/371472 [8:29:33<9:54:15,  3.53it/s]
 66%|██████▌   | 245455/371472 [8:29:33<9:30:18,  3.68it/s]
 66%|██████▌   | 245456/371472 [8:29:33<9:36:25,  3.64it/s]
 66%|██████▌   | 245457/371472 [8:29:33<9:46:28,  3.58it/s]
 66%|██████▌   | 245458/371472 [8:29:34<9:17:38,  3.77it/s]
 66%|██████▌   | 245459/371472 [8:29:34<9:23:46,  3.73it/s]
 66%|██████▌   | 245460/371472 [8:29:34<9:29:37,  3.69it/s]
                                                           
{'loss': 2.9309, 'learning_rate': 4.0546553470232064e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245460/371472 [8:29:34<9:29:37,  3.69it/s]
 66%|██████▌   | 245461/371472 [8:29:34<9:21:32,  3.74it/s]
 66%|██████▌   | 245462/371472 [8:29:35<9:07:41,  3.83it/s]
 66%|██████▌   | 245463/371472 [8:29:35<9:49:41,  3.56it/s]
 66%|██████▌   | 245464/371472 [8:29:35<9:50:07,  3.56it/s]
 66%|██████▌   | 245465/371472 [8:29:36<9:25:04,  3.72it/s]
 66%|██████▌   | 245466/371472 [8:29:36<9:11:13,  3.81it/s]
 66%|██████▌   | 245467/371472 [8:29:36<9:43:06,  3.60it/s]
 66%|██████▌   | 245468/371472 [8:29:36<9:39:43,  3.62it/s]
 66%|██████▌   | 245469/371472 [8:29:37<9:57:12,  3.52it/s]
 66%|██████▌   | 245470/371472 [8:29:37<9:47:04,  3.58it/s]
 66%|██████▌   | 245471/371472 [8:29:37<9:50:25,  3.56it/s]
 66%|██████▌   | 245472/371472 [8:29:38<9:44:19,  3.59it/s]
 66%|██████▌   | 245473/371472 [8:29:38<9:54:54,  3.53it/s]
 66%|██████▌   | 245474/371472 [8:29:38<9:43:04,  3.60it/s]
 66%|██████▌   | 245475/371472 [8:29:38<9:22:53,  3.73it/s]
 66%|██████▌   | 245476/371472 [8:29:39<9:34:43,  3.65it/s]
 66%|██████▌   | 245477/371472 [8:29:39<10:18:52,  3.39it/s]
 66%|██████▌   | 245478/371472 [8:29:39<10:15:00,  3.41it/s]
 66%|██████▌   | 245479/371472 [8:29:40<10:24:33,  3.36it/s]
 66%|██████▌   | 245480/371472 [8:29:40<10:14:17,  3.42it/s]
                                                            
{'loss': 2.8395, 'learning_rate': 4.054170527268417e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245480/371472 [8:29:40<10:14:17,  3.42it/s]
 66%|██████▌   | 245481/371472 [8:29:40<10:31:55,  3.32it/s]
 66%|██████▌   | 245482/371472 [8:29:40<10:46:36,  3.25it/s]
 66%|██████▌   | 245483/371472 [8:29:41<10:28:52,  3.34it/s]
 66%|██████▌   | 245484/371472 [8:29:41<10:16:26,  3.41it/s]
 66%|██████▌   | 245485/371472 [8:29:41<9:47:28,  3.57it/s] 
 66%|██████▌   | 245486/371472 [8:29:42<10:47:06,  3.24it/s]
 66%|██████▌   | 245487/371472 [8:29:42<10:07:22,  3.46it/s]
 66%|██████▌   | 245488/371472 [8:29:42<9:42:39,  3.60it/s] 
 66%|██████▌   | 245489/371472 [8:29:42<9:44:07,  3.59it/s]
 66%|██████▌   | 245490/371472 [8:29:43<9:20:24,  3.75it/s]
 66%|██████▌   | 245491/371472 [8:29:43<8:55:14,  3.92it/s]
 66%|██████▌   | 245492/371472 [8:29:43<8:51:16,  3.95it/s]
 66%|██████▌   | 245493/371472 [8:29:43<8:49:17,  3.97it/s]
 66%|██████▌   | 245494/371472 [8:29:44<9:09:29,  3.82it/s]
 66%|██████▌   | 245495/371472 [8:29:44<9:10:46,  3.81it/s]
 66%|██████▌   | 245496/371472 [8:29:44<9:04:53,  3.85it/s]
 66%|██████▌   | 245497/371472 [8:29:44<9:13:56,  3.79it/s]
 66%|██████▌   | 245498/371472 [8:29:45<9:14:42,  3.78it/s]
 66%|██████▌   | 245499/371472 [8:29:45<10:07:55,  3.45it/s]
 66%|██████▌   | 245500/371472 [8:29:45<9:42:17,  3.61it/s] 
                                                           
{'loss': 3.0989, 'learning_rate': 4.053685707513629e-07, 'epoch': 10.57}
+
 66%|██████▌   | 245500/371472 [8:29:45<9:42:17,  3.61it/s]
 66%|██████▌   | 245501/371472 [8:29:46<9:59:33,  3.50it/s]
 66%|██████▌   | 245502/371472 [8:29:46<10:42:21,  3.27it/s]
 66%|██████▌   | 245503/371472 [8:29:46<10:13:05,  3.42it/s]
 66%|██████▌   | 245504/371472 [8:29:47<10:28:07,  3.34it/s]
 66%|██████▌   | 245505/371472 [8:29:47<10:54:10,  3.21it/s]
 66%|██████▌   | 245506/371472 [8:29:47<10:23:59,  3.36it/s]
 66%|██████▌   | 245507/371472 [8:29:47<10:22:59,  3.37it/s]
 66%|██████▌   | 245508/371472 [8:29:48<9:47:23,  3.57it/s] 
 66%|██████▌   | 245509/371472 [8:29:48<10:06:21,  3.46it/s]
 66%|██████▌   | 245510/371472 [8:29:48<10:26:24,  3.35it/s]
 66%|██████▌   | 245511/371472 [8:29:49<10:31:27,  3.32it/s]
 66%|██████▌   | 245512/371472 [8:29:49<10:12:54,  3.43it/s]
 66%|██████▌   | 245513/371472 [8:29:49<10:10:35,  3.44it/s]
 66%|██████▌   | 245514/371472 [8:29:50<9:57:58,  3.51it/s] 
 66%|██████▌   | 245515/371472 [8:29:50<10:24:28,  3.36it/s]
 66%|██████▌   | 245516/371472 [8:29:50<10:27:04,  3.35it/s]
 66%|██████▌   | 245517/371472 [8:29:51<12:01:32,  2.91it/s]
 66%|██████▌   | 245518/371472 [8:29:51<11:19:56,  3.09it/s]
 66%|██████▌   | 245519/371472 [8:29:51<11:01:01,  3.18it/s]
 66%|██████▌   | 245520/371472 [8:29:51<10:27:24,  3.35it/s]
                                                            
{'loss': 2.8757, 'learning_rate': 4.0532008877588396e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245520/371472 [8:29:51<10:27:24,  3.35it/s]
 66%|██████▌   | 245521/371472 [8:29:52<10:03:52,  3.48it/s]
 66%|██████▌   | 245522/371472 [8:29:52<10:07:31,  3.46it/s]
 66%|██████▌   | 245523/371472 [8:29:52<9:49:52,  3.56it/s] 
 66%|██████▌   | 245524/371472 [8:29:52<9:27:28,  3.70it/s]
 66%|██████▌   | 245525/371472 [8:29:53<9:26:39,  3.70it/s]
 66%|██████▌   | 245526/371472 [8:29:53<9:21:09,  3.74it/s]
 66%|██████▌   | 245527/371472 [8:29:53<9:39:38,  3.62it/s]
 66%|██████▌   | 245528/371472 [8:29:54<9:23:48,  3.72it/s]
 66%|██████▌   | 245529/371472 [8:29:54<9:32:27,  3.67it/s]
 66%|██████▌   | 245530/371472 [8:29:54<9:15:35,  3.78it/s]
 66%|██████▌   | 245531/371472 [8:29:54<10:12:13,  3.43it/s]
 66%|██████▌   | 245532/371472 [8:29:55<10:16:17,  3.41it/s]
 66%|██████▌   | 245533/371472 [8:29:55<9:54:51,  3.53it/s] 
 66%|██████▌   | 245534/371472 [8:29:55<10:26:28,  3.35it/s]
 66%|██████▌   | 245535/371472 [8:29:56<10:04:33,  3.47it/s]
 66%|██████▌   | 245536/371472 [8:29:56<9:46:41,  3.58it/s] 
 66%|██████▌   | 245537/371472 [8:29:56<10:08:00,  3.45it/s]
 66%|██████▌   | 245538/371472 [8:29:56<10:25:00,  3.36it/s]
 66%|██████▌   | 245539/371472 [8:29:57<9:58:25,  3.51it/s] 
 66%|██████▌   | 245540/371472 [8:29:57<9:29:20,  3.69it/s]
                                                           
{'loss': 2.8214, 'learning_rate': 4.052716068004051e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245540/371472 [8:29:57<9:29:20,  3.69it/s]
 66%|██████▌   | 245541/371472 [8:29:57<10:43:28,  3.26it/s]
 66%|██████▌   | 245542/371472 [8:29:58<10:15:18,  3.41it/s]
 66%|██████▌   | 245543/371472 [8:29:58<9:57:06,  3.52it/s] 
 66%|██████▌   | 245544/371472 [8:29:58<9:48:49,  3.56it/s]
 66%|██████▌   | 245545/371472 [8:29:58<10:05:05,  3.47it/s]
 66%|██████▌   | 245546/371472 [8:29:59<9:34:51,  3.65it/s] 
 66%|██████▌   | 245547/371472 [8:29:59<9:36:48,  3.64it/s]
 66%|██████▌   | 245548/371472 [8:29:59<9:40:53,  3.61it/s]
 66%|██████▌   | 245549/371472 [8:30:00<9:16:51,  3.77it/s]
 66%|���█████▌   | 245550/371472 [8:30:00<9:19:38,  3.75it/s]
 66%|██████▌   | 245551/371472 [8:30:00<9:04:33,  3.85it/s]
 66%|██████▌   | 245552/371472 [8:30:00<9:48:04,  3.57it/s]
 66%|██████▌   | 245553/371472 [8:30:01<9:58:57,  3.50it/s]
 66%|██████▌   | 245554/371472 [8:30:01<9:42:43,  3.60it/s]
 66%|██████▌   | 245555/371472 [8:30:01<9:39:15,  3.62it/s]
 66%|██████▌   | 245556/371472 [8:30:01<10:03:06,  3.48it/s]
 66%|██████▌   | 245557/371472 [8:30:02<9:41:49,  3.61it/s] 
 66%|██████▌   | 245558/371472 [8:30:02<9:40:19,  3.62it/s]
 66%|██████▌   | 245559/371472 [8:30:02<9:08:53,  3.82it/s]
 66%|██████▌   | 245560/371472 [8:30:03<9:28:27,  3.69it/s]
                                                           
{'loss': 2.9077, 'learning_rate': 4.0522312482492616e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245560/371472 [8:30:03<9:28:27,  3.69it/s]
 66%|██████▌   | 245561/371472 [8:30:03<9:15:02,  3.78it/s]
 66%|██████▌   | 245562/371472 [8:30:03<9:03:05,  3.86it/s]
 66%|██████▌   | 245563/371472 [8:30:03<9:48:56,  3.56it/s]
 66%|██████▌   | 245564/371472 [8:30:04<10:04:40,  3.47it/s]
 66%|██████▌   | 245565/371472 [8:30:04<10:15:11,  3.41it/s]
 66%|██████▌   | 245566/371472 [8:30:04<9:42:10,  3.60it/s] 
 66%|██████▌   | 245567/371472 [8:30:05<10:34:50,  3.31it/s]
 66%|██████▌   | 245568/371472 [8:30:05<10:20:38,  3.38it/s]
 66%|██████▌   | 245569/371472 [8:30:05<9:59:50,  3.50it/s] 
 66%|██████▌   | 245570/371472 [8:30:05<9:31:24,  3.67it/s]
 66%|██████▌   | 245571/371472 [8:30:06<9:28:24,  3.69it/s]
 66%|██████▌   | 245572/371472 [8:30:06<9:25:35,  3.71it/s]
 66%|██████▌   | 245573/371472 [8:30:06<10:02:58,  3.48it/s]
 66%|██████▌   | 245574/371472 [8:30:07<10:56:43,  3.20it/s]
 66%|██████▌   | 245575/371472 [8:30:07<10:35:35,  3.30it/s]
 66%|██████▌   | 245576/371472 [8:30:07<10:00:33,  3.49it/s]
 66%|██████▌   | 245577/371472 [8:30:07<9:46:54,  3.58it/s] 
 66%|██████▌   | 245578/371472 [8:30:08<9:41:30,  3.61it/s]
 66%|██████▌   | 245579/371472 [8:30:08<9:40:44,  3.61it/s]
 66%|██████▌   | 245580/371472 [8:30:08<9:43:10,  3.60it/s]
                                                           
{'loss': 2.8756, 'learning_rate': 4.0517464284944733e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245580/371472 [8:30:08<9:43:10,  3.60it/s]
 66%|██████▌   | 245581/371472 [8:30:09<10:14:26,  3.41it/s]
 66%|██████▌   | 245582/371472 [8:30:09<9:48:12,  3.57it/s] 
 66%|██████▌   | 245583/371472 [8:30:09<9:36:26,  3.64it/s]
 66%|██████▌   | 245584/371472 [8:30:09<9:19:43,  3.75it/s]
 66%|██████▌   | 245585/371472 [8:30:10<9:37:36,  3.63it/s]
 66%|██████▌   | 245586/371472 [8:30:10<9:30:30,  3.68it/s]
 66%|██████▌   | 245587/371472 [8:30:10<9:38:12,  3.63it/s]
 66%|██████▌   | 245588/371472 [8:30:10<9:36:58,  3.64it/s]
 66%|██████▌   | 245589/371472 [8:30:11<9:11:57,  3.80it/s]
 66%|██████▌   | 245590/371472 [8:30:11<11:27:57,  3.05it/s]
 66%|██████▌   | 245591/371472 [8:30:11<11:08:36,  3.14it/s]
 66%|██████▌   | 245592/371472 [8:30:12<10:33:06,  3.31it/s]
 66%|██████▌   | 245593/371472 [8:30:12<10:43:16,  3.26it/s]
 66%|██████▌   | 245594/371472 [8:30:12<10:07:37,  3.45it/s]
 66%|██████▌   | 245595/371472 [8:30:13<10:00:11,  3.50it/s]
 66%|██████▌   | 245596/371472 [8:30:13<10:05:36,  3.46it/s]
 66%|██████▌   | 245597/371472 [8:30:13<9:57:25,  3.51it/s] 
 66%|██████▌   | 245598/371472 [8:30:13<10:17:58,  3.39it/s]
 66%|██████▌   | 245599/371472 [8:30:14<9:55:15,  3.52it/s] 
 66%|██████▌   | 245600/371472 [8:30:14<9:34:49,  3.65it/s]
                                                           
{'loss': 2.8791, 'learning_rate': 4.0512616087396835e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245600/371472 [8:30:14<9:34:49,  3.65it/s]
 66%|██████▌   | 245601/371472 [8:30:14<9:43:50,  3.59it/s]
 66%|██████▌   | 245602/371472 [8:30:15<9:43:53,  3.59it/s]
 66%|██████▌   | 245603/371472 [8:30:15<9:45:39,  3.58it/s]
 66%|██████▌   | 245604/371472 [8:30:15<9:21:15,  3.74it/s]
 66%|██████▌   | 245605/371472 [8:30:15<9:46:05,  3.58it/s]
 66%|██████▌   | 245606/371472 [8:30:16<10:00:02,  3.50it/s]
 66%|██████▌   | 245607/371472 [8:30:16<9:37:03,  3.64it/s] 
 66%|██████▌   | 245608/371472 [8:30:16<9:28:47,  3.69it/s]
 66%|██████▌   | 245609/371472 [8:30:16<9:10:24,  3.81it/s]
 66%|██████▌   | 245610/371472 [8:30:17<9:06:15,  3.84it/s]
 66%|██████▌   | 245611/371472 [8:30:17<9:29:28,  3.68it/s]
 66%|██████▌   | 245612/371472 [8:30:17<9:31:01,  3.67it/s]
 66%|██████▌   | 245613/371472 [8:30:17<9:34:16,  3.65it/s]
 66%|██████▌   | 245614/371472 [8:30:18<9:28:40,  3.69it/s]
 66%|██████▌   | 245615/371472 [8:30:18<9:37:48,  3.63it/s]
 66%|██████▌   | 245616/371472 [8:30:18<9:33:04,  3.66it/s]
 66%|██████▌   | 245617/371472 [8:30:19<9:07:14,  3.83it/s]
 66%|██████▌   | 245618/371472 [8:30:19<9:01:33,  3.87it/s]
 66%|██████▌   | 245619/371472 [8:30:19<8:47:43,  3.97it/s]
 66%|██████▌   | 245620/371472 [8:30:19<8:47:43,  3.97it/s]
                                                           
{'loss': 3.0601, 'learning_rate': 4.0507767889848953e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245620/371472 [8:30:19<8:47:43,  3.97it/s]
 66%|██████▌   | 245621/371472 [8:30:20<8:46:51,  3.98it/s]
 66%|██████▌   | 245622/371472 [8:30:20<8:52:08,  3.94it/s]
 66%|██████▌   | 245623/371472 [8:30:20<9:16:57,  3.77it/s]
 66%|██████▌   | 245624/371472 [8:30:20<9:03:41,  3.86it/s]
 66%|██████▌   | 245625/371472 [8:30:21<9:41:49,  3.61it/s]
 66%|██████▌   | 245626/371472 [8:30:21<9:57:06,  3.51it/s]
 66%|██████▌   | 245627/371472 [8:30:21<9:34:21,  3.65it/s]
 66%|██████▌   | 245628/371472 [8:30:21<9:23:32,  3.72it/s]
 66%|██████▌   | 245629/371472 [8:30:22<9:10:14,  3.81it/s]
 66%|██████▌   | 245630/371472 [8:30:22<9:19:32,  3.75it/s]
 66%|██████▌   | 245631/371472 [8:30:22<9:03:29,  3.86it/s]
 66%|██████▌   | 245632/371472 [8:30:23<9:47:44,  3.57it/s]
 66%|██████▌   | 245633/371472 [8:30:23<10:18:59,  3.39it/s]
 66%|██████▌   | 245634/371472 [8:30:23<9:54:43,  3.53it/s] 
 66%|██████▌   | 245635/371472 [8:30:23<9:51:33,  3.55it/s]
 66%|██████▌   | 245636/371472 [8:30:24<9:40:47,  3.61it/s]
 66%|██████▌   | 245637/371472 [8:30:24<9:36:50,  3.64it/s]
 66%|██████▌   | 245638/371472 [8:30:24<9:23:02,  3.72it/s]
 66%|██████▌   | 245639/371472 [8:30:24<9:11:01,  3.81it/s]
 66%|██████▌   | 245640/371472 [8:30:25<9:55:38,  3.52it/s]
                                                           
{'loss': 2.8741, 'learning_rate': 4.0502919692301055e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245640/371472 [8:30:25<9:55:38,  3.52it/s]
 66%|██████▌   | 245641/371472 [8:30:25<10:29:49,  3.33it/s]
 66%|██████▌   | 245642/371472 [8:30:25<9:57:34,  3.51it/s] 
 66%|██████▌   | 245643/371472 [8:30:26<10:43:33,  3.26it/s]
 66%|██████▌   | 245644/371472 [8:30:26<11:12:20,  3.12it/s]
 66%|██████▌   | 245645/371472 [8:30:26<11:19:02,  3.09it/s]
 66%|██████▌   | 245646/371472 [8:30:27<11:20:15,  3.08it/s]
 66%|██████▌   | 245647/371472 [8:30:27<11:00:43,  3.17it/s]
 66%|██████▌   | 245648/371472 [8:30:27<10:30:22,  3.33it/s]
 66%|██████▌   | 245649/371472 [8:30:28<9:53:46,  3.53it/s] 
 66%|██████▌   | 245650/371472 [8:30:28<9:29:23,  3.68it/s]
 66%|██████▌   | 245651/371472 [8:30:28<9:23:20,  3.72it/s]
 66%|██████▌   | 245652/371472 [8:30:28<9:42:31,  3.60it/s]
 66%|██████▌   | 245653/371472 [8:30:29<9:28:21,  3.69it/s]
 66%|██████▌   | 245654/371472 [8:30:29<9:18:51,  3.75it/s]
 66%|██████▌   | 245655/371472 [8:30:29<9:15:30,  3.77it/s]
 66%|██████▌   | 245656/371472 [8:30:29<9:49:38,  3.56it/s]
 66%|██████▌   | 245657/371472 [8:30:30<9:44:50,  3.59it/s]
 66%|██████▌   | 245658/371472 [8:30:30<9:44:02,  3.59it/s]
 66%|██████▌   | 245659/371472 [8:30:30<9:26:44,  3.70it/s]
 66%|██████▌   | 245660/371472 [8:30:30<9:06:08,  3.84it/s]
                                                           
{'loss': 2.8701, 'learning_rate': 4.049807149475317e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245660/371472 [8:30:30<9:06:08,  3.84it/s]
 66%|██████▌   | 245661/371472 [8:30:31<9:25:52,  3.71it/s]
 66%|██████▌   | 245662/371472 [8:30:31<9:09:16,  3.82it/s]
 66%|██████▌   | 245663/371472 [8:30:31<9:12:05,  3.80it/s]
 66%|██████▌   | 245664/371472 [8:30:32<9:36:21,  3.64it/s]
 66%|██████▌   | 245665/371472 [8:30:32<9:30:54,  3.67it/s]
 66%|██████▌   | 245666/371472 [8:30:32<9:21:34,  3.73it/s]
 66%|██████▌   | 245667/371472 [8:30:33<11:15:28,  3.10it/s]
 66%|██████▌   | 245668/371472 [8:30:33<11:03:12,  3.16it/s]
 66%|██████▌   | 245669/371472 [8:30:33<10:35:24,  3.30it/s]
 66%|██████▌   | 245670/371472 [8:30:33<11:09:07,  3.13it/s]
 66%|██████▌   | 245671/371472 [8:30:34<11:11:11,  3.12it/s]
 66%|██████▌   | 245672/371472 [8:30:34<10:30:01,  3.33it/s]
 66%|██████▌   | 245673/371472 [8:30:34<10:23:00,  3.37it/s]
 66%|██████▌   | 245674/371472 [8:30:35<10:03:17,  3.48it/s]
 66%|██████▌   | 245675/371472 [8:30:35<9:39:56,  3.62it/s] 
 66%|██████▌   | 245676/371472 [8:30:35<9:17:48,  3.76it/s]
 66%|██████▌   | 245677/371472 [8:30:35<9:12:20,  3.80it/s]
 66%|██████▌   | 245678/371472 [8:30:36<9:37:33,  3.63it/s]
 66%|██████▌   | 245679/371472 [8:30:36<9:59:02,  3.50it/s]
 66%|██████▌   | 245680/371472 [8:30:36<10:26:56,  3.34it/s]
                                                            
{'loss': 2.9446, 'learning_rate': 4.049322329720528e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245680/371472 [8:30:36<10:26:56,  3.34it/s]
 66%|██████▌   | 245681/371472 [8:30:37<10:06:25,  3.46it/s]
 66%|██████▌   | 245682/371472 [8:30:37<9:53:58,  3.53it/s] 
 66%|██████▌   | 245683/371472 [8:30:37<9:51:14,  3.55it/s]
 66%|██████▌   | 245684/371472 [8:30:38<12:24:58,  2.81it/s]
 66%|██████▌   | 245685/371472 [8:30:38<11:16:50,  3.10it/s]
 66%|██████▌   | 245686/371472 [8:30:38<10:24:07,  3.36it/s]
 66%|██████▌   | 245687/371472 [8:30:38<9:50:22,  3.55it/s] 
 66%|██████▌   | 245688/371472 [8:30:39<10:06:59,  3.45it/s]
 66%|██████▌   | 245689/371472 [8:30:39<10:18:16,  3.39it/s]
 66%|██████▌   | 245690/371472 [8:30:39<9:50:41,  3.55it/s] 
 66%|██████▌   | 245691/371472 [8:30:40<9:58:35,  3.50it/s]
 66%|██████▌   | 245692/371472 [8:30:40<9:34:56,  3.65it/s]
 66%|██████▌   | 245693/371472 [8:30:40<9:31:43,  3.67it/s]
 66%|██████▌   | 245694/371472 [8:30:40<11:03:10,  3.16it/s]
 66%|██████▌   | 245695/371472 [8:30:41<10:54:55,  3.20it/s]
 66%|██████▌   | 245696/371472 [8:30:41<10:26:25,  3.35it/s]
 66%|██████▌   | 245697/371472 [8:30:41<10:16:03,  3.40it/s]
 66%|██████▌   | 245698/371472 [8:30:42<9:45:48,  3.58it/s] 
 66%|██████▌   | 245699/371472 [8:30:42<10:03:02,  3.48it/s]
 66%|██████▌   | 245700/371472 [8:30:42<9:39:21,  3.62it/s] 
                                                           
{'loss': 2.7383, 'learning_rate': 4.04883750996574e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245700/371472 [8:30:42<9:39:21,  3.62it/s]
 66%|██████▌   | 245701/371472 [8:30:42<9:32:04,  3.66it/s]
 66%|██████▌   | 245702/371472 [8:30:43<9:26:48,  3.70it/s]
 66%|██████▌   | 245703/371472 [8:30:43<9:12:13,  3.80it/s]
 66%|██████▌   | 245704/371472 [8:30:43<9:36:14,  3.64it/s]
 66%|██████▌   | 245705/371472 [8:30:44<9:43:32,  3.59it/s]
 66%|██████▌   | 245706/371472 [8:30:44<9:38:01,  3.63it/s]
 66%|██████▌   | 245707/371472 [8:30:44<9:21:39,  3.73it/s]
 66%|██████▌   | 245708/371472 [8:30:44<9:21:58,  3.73it/s]
 66%|██████▌   | 245709/371472 [8:30:45<10:10:15,  3.43it/s]
 66%|██████▌   | 245710/371472 [8:30:45<9:39:03,  3.62it/s] 
 66%|██████▌   | 245711/371472 [8:30:45<10:17:24,  3.39it/s]
 66%|██████▌   | 245712/371472 [8:30:46<10:20:02,  3.38it/s]
 66%|██████▌   | 245713/371472 [8:30:46<10:11:00,  3.43it/s]
 66%|██████▌   | 245714/371472 [8:30:46<9:50:21,  3.55it/s] 
 66%|██████▌   | 245715/371472 [8:30:46<9:22:51,  3.72it/s]
 66%|██████▌   | 245716/371472 [8:30:47<9:17:04,  3.76it/s]
 66%|██████▌   | 245717/371472 [8:30:47<9:11:58,  3.80it/s]
 66%|██████▌   | 245718/371472 [8:30:47<9:53:49,  3.53it/s]
 66%|██████▌   | 245719/371472 [8:30:47<9:31:10,  3.67it/s]
 66%|██████▌   | 245720/371472 [8:30:48<9:40:44,  3.61it/s]
                                                           
{'loss': 2.7535, 'learning_rate': 4.04835269021095e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245720/371472 [8:30:48<9:40:44,  3.61it/s]
 66%|██████▌   | 245721/371472 [8:30:48<9:39:13,  3.62it/s]
 66%|██████▌   | 245722/371472 [8:30:48<10:02:58,  3.48it/s]
 66%|██████▌   | 245723/371472 [8:30:49<9:48:05,  3.56it/s] 
 66%|██████▌   | 245724/371472 [8:30:49<9:46:12,  3.58it/s]
 66%|██████▌   | 245725/371472 [8:30:49<10:11:39,  3.43it/s]
 66%|██████▌   | 245726/371472 [8:30:49<10:01:58,  3.48it/s]
 66%|██████▌   | 245727/371472 [8:30:50<9:49:52,  3.55it/s] 
 66%|██████▌   | 245728/371472 [8:30:50<9:54:33,  3.52it/s]
 66%|██████▌   | 245729/371472 [8:30:50<9:29:34,  3.68it/s]
 66%|██████▌   | 245730/371472 [8:30:50<9:28:31,  3.69it/s]
 66%|██████▌   | 245731/371472 [8:30:51<9:17:32,  3.76it/s]
 66%|██████▌   | 245732/371472 [8:30:51<9:31:28,  3.67it/s]
 66%|██████▌   | 245733/371472 [8:30:51<9:22:02,  3.73it/s]
 66%|██████▌   | 245734/371472 [8:30:52<9:39:21,  3.62it/s]
 66%|██████▌   | 245735/371472 [8:30:52<9:37:13,  3.63it/s]
 66%|██████▌   | 245736/371472 [8:30:52<9:33:57,  3.65it/s]
 66%|██████▌   | 245737/371472 [8:30:52<9:48:51,  3.56it/s]
 66%|██████▌   | 245738/371472 [8:30:53<9:27:09,  3.69it/s]
 66%|██████▌   | 245739/371472 [8:30:53<10:18:58,  3.39it/s]
 66%|██████▌   | 245740/371472 [8:30:53<10:02:42,  3.48it/s]
                                                            
{'loss': 2.9015, 'learning_rate': 4.0478678704561617e-07, 'epoch': 10.58}
+
 66%|██████▌   | 245740/371472 [8:30:53<10:02:42,  3.48it/s]
 66%|██████▌   | 245741/371472 [8:30:54<9:27:55,  3.69it/s] 
 66%|██████▌   | 245742/371472 [8:30:54<9:57:35,  3.51it/s]
 66%|██████▌   | 245743/371472 [8:30:54<9:44:27,  3.59it/s]
 66%|██████▌   | 245744/371472 [8:30:54<9:37:18,  3.63it/s]
 66%|██████▌   | 245745/371472 [8:30:55<9:06:42,  3.83it/s]
 66%|██████▌   | 245746/371472 [8:30:55<8:57:06,  3.90it/s]
 66%|██████▌   | 245747/371472 [8:30:55<9:01:15,  3.87it/s]
 66%|██████▌   | 245748/371472 [8:30:55<9:06:12,  3.84it/s]
 66%|██████▌   | 245749/371472 [8:30:56<9:23:25,  3.72it/s]
 66%|██████▌   | 245750/371472 [8:30:56<10:00:01,  3.49it/s]
 66%|██████▌   | 245751/371472 [8:30:56<9:42:03,  3.60it/s] 
 66%|██████▌   | 245752/371472 [8:30:57<9:36:25,  3.64it/s]
 66%|██████▌   | 245753/371472 [8:30:57<9:35:54,  3.64it/s]
 66%|██████▌   | 245754/371472 [8:30:57<9:09:16,  3.81it/s]
 66%|██████▌   | 245755/371472 [8:30:57<9:49:15,  3.56it/s]
 66%|██████▌   | 245756/371472 [8:30:58<11:31:28,  3.03it/s]
 66%|██████▌   | 245757/371472 [8:30:58<10:48:41,  3.23it/s]
 66%|██████▌   | 245758/371472 [8:30:58<10:31:35,  3.32it/s]
 66%|██████▌   | 245759/371472 [8:30:59<10:21:49,  3.37it/s]
 66%|██████▌   | 245760/371472 [8:30:59<10:40:09,  3.27it/s]
                                                            
{'loss': 2.8034, 'learning_rate': 4.0473830507013724e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245760/371472 [8:30:59<10:40:09,  3.27it/s]
 66%|██████▌   | 245761/371472 [8:30:59<10:48:39,  3.23it/s]
 66%|██████▌   | 245762/371472 [8:31:00<11:29:33,  3.04it/s]
 66%|██████▌   | 245763/371472 [8:31:00<10:30:43,  3.32it/s]
 66%|██████▌   | 245764/371472 [8:31:00<11:01:43,  3.17it/s]
 66%|██████▌   | 245765/371472 [8:31:01<11:12:57,  3.11it/s]
 66%|██████▌   | 245766/371472 [8:31:01<11:09:00,  3.13it/s]
 66%|██████▌   | 245767/371472 [8:31:01<10:28:09,  3.34it/s]
 66%|██████▌   | 245768/371472 [8:31:01<10:00:43,  3.49it/s]
 66%|██████▌   | 245769/371472 [8:31:02<9:45:32,  3.58it/s] 
 66%|██████▌   | 245770/371472 [8:31:02<9:23:43,  3.72it/s]
 66%|██████▌   | 245771/371472 [8:31:02<9:11:08,  3.80it/s]
 66%|██████▌   | 245772/371472 [8:31:02<9:17:23,  3.76it/s]
 66%|██████▌   | 245773/371472 [8:31:03<9:47:12,  3.57it/s]
 66%|██████▌   | 245774/371472 [8:31:03<9:40:53,  3.61it/s]
 66%|██████▌   | 245775/371472 [8:31:03<9:38:09,  3.62it/s]
 66%|██████▌   | 245776/371472 [8:31:04<10:16:14,  3.40it/s]
 66%|██████▌   | 245777/371472 [8:31:04<9:47:36,  3.57it/s] 
 66%|██████▌   | 245778/371472 [8:31:04<9:34:53,  3.64it/s]
 66%|██████▌   | 245779/371472 [8:31:04<9:24:38,  3.71it/s]
 66%|██████▌   | 245780/371472 [8:31:05<9:34:23,  3.65it/s]
                                                           
{'loss': 2.779, 'learning_rate': 4.0468982309465837e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245780/371472 [8:31:05<9:34:23,  3.65it/s]
 66%|██████▌   | 245781/371472 [8:31:05<9:36:44,  3.63it/s]
 66%|██████▌   | 245782/371472 [8:31:05<10:13:19,  3.42it/s]
 66%|██████▌   | 245783/371472 [8:31:06<11:00:36,  3.17it/s]
 66%|██████▌   | 245784/371472 [8:31:06<10:30:31,  3.32it/s]
 66%|██████▌   | 245785/371472 [8:31:06<10:51:13,  3.22it/s]
 66%|██████▌   | 245786/371472 [8:31:06<10:12:06,  3.42it/s]
 66%|██████▌   | 245787/371472 [8:31:07<10:17:17,  3.39it/s]
 66%|██████▌   | 245788/371472 [8:31:07<10:22:41,  3.36it/s]
 66%|██████▌   | 245789/371472 [8:31:07<9:43:20,  3.59it/s] 
 66%|██████▌   | 245790/371472 [8:31:08<9:46:11,  3.57it/s]
 66%|██████▌   | 245791/371472 [8:31:08<10:30:28,  3.32it/s]
 66%|██████▌   | 245792/371472 [8:31:08<10:01:18,  3.48it/s]
 66%|██████▌   | 245793/371472 [8:31:08<10:00:39,  3.49it/s]
 66%|██████▌   | 245794/371472 [8:31:09<9:40:48,  3.61it/s] 
 66%|██████▌   | 245795/371472 [8:31:09<10:08:21,  3.44it/s]
 66%|██████▌   | 245796/371472 [8:31:09<10:43:52,  3.25it/s]
 66%|██████▌   | 245797/371472 [8:31:10<10:20:05,  3.38it/s]
 66%|██████▌   | 245798/371472 [8:31:10<10:11:58,  3.42it/s]
 66%|██████▌   | 245799/371472 [8:31:10<9:51:02,  3.54it/s] 
 66%|██████▌   | 245800/371472 [8:31:11<9:53:45,  3.53it/s]
                                                           
{'loss': 2.9091, 'learning_rate': 4.0464134111917944e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245800/371472 [8:31:11<9:53:45,  3.53it/s]
 66%|██████▌   | 245801/371472 [8:31:11<9:32:39,  3.66it/s]
 66%|██████▌   | 245802/371472 [8:31:11<9:19:19,  3.74it/s]
 66%|██████▌   | 245803/371472 [8:31:11<10:32:36,  3.31it/s]
 66%|██████▌   | 245804/371472 [8:31:12<9:56:16,  3.51it/s] 
 66%|██████▌   | 245805/371472 [8:31:12<9:37:15,  3.63it/s]
 66%|██████▌   | 245806/371472 [8:31:12<9:39:27,  3.61it/s]
 66%|██████▌   | 245807/371472 [8:31:12<9:32:25,  3.66it/s]
 66%|██████▌   | 245808/371472 [8:31:13<9:19:51,  3.74it/s]
 66%|██████▌   | 245809/371472 [8:31:13<9:08:05,  3.82it/s]
 66%|██████▌   | 245810/371472 [8:31:13<9:49:17,  3.55it/s]
 66%|██████▌   | 245811/371472 [8:31:14<10:56:55,  3.19it/s]
 66%|██████▌   | 245812/371472 [8:31:14<10:32:10,  3.31it/s]
 66%|██████▌   | 245813/371472 [8:31:14<9:53:21,  3.53it/s] 
 66%|██████▌   | 245814/371472 [8:31:14<9:28:25,  3.68it/s]
 66%|██████▌   | 245815/371472 [8:31:15<9:53:54,  3.53it/s]
 66%|██████▌   | 245816/371472 [8:31:15<9:30:58,  3.67it/s]
 66%|██████▌   | 245817/371472 [8:31:15<9:31:44,  3.66it/s]
 66%|██████▌   | 245818/371472 [8:31:16<9:26:33,  3.70it/s]
 66%|██████▌   | 245819/371472 [8:31:16<9:16:02,  3.77it/s]
 66%|██████▌   | 245820/371472 [8:31:16<9:07:31,  3.82it/s]
                                                           
{'loss': 2.7478, 'learning_rate': 4.045928591437006e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245820/371472 [8:31:16<9:07:31,  3.82it/s]
 66%|██████▌   | 245821/371472 [8:31:16<9:26:16,  3.70it/s]
 66%|██████▌   | 245822/371472 [8:31:17<9:10:11,  3.81it/s]
 66%|██████▌   | 245823/371472 [8:31:17<9:13:41,  3.78it/s]
 66%|██████▌   | 245824/371472 [8:31:17<9:26:22,  3.70it/s]
 66%|██████▌   | 245825/371472 [8:31:17<9:19:21,  3.74it/s]
 66%|██████▌   | 245826/371472 [8:31:18<8:54:42,  3.92it/s]
 66%|██████▌   | 245827/371472 [8:31:18<9:08:12,  3.82it/s]
 66%|██████▌   | 245828/371472 [8:31:18<9:12:24,  3.79it/s]
 66%|██████▌   | 245829/371472 [8:31:18<8:49:22,  3.96it/s]
 66%|██████▌   | 245830/371472 [8:31:19<9:16:33,  3.76it/s]
 66%|██████▌   | 245831/371472 [8:31:19<9:04:28,  3.85it/s]
 66%|██████▌   | 245832/371472 [8:31:19<9:06:16,  3.83it/s]
 66%|██████▌   | 245833/371472 [8:31:19<8:53:26,  3.93it/s]
 66%|██████▌   | 245834/371472 [8:31:20<9:13:17,  3.78it/s]
 66%|██████▌   | 245835/371472 [8:31:20<9:10:54,  3.80it/s]
 66%|██████▌   | 245836/371472 [8:31:20<8:53:01,  3.93it/s]
 66%|██████▌   | 245837/371472 [8:31:21<9:50:16,  3.55it/s]
 66%|██████▌   | 245838/371472 [8:31:21<9:33:09,  3.65it/s]
 66%|██████▌   | 245839/371472 [8:31:21<9:44:59,  3.58it/s]
 66%|██████▌   | 245840/371472 [8:31:21<9:35:44,  3.64it/s]
                                                           
{'loss': 2.7332, 'learning_rate': 4.045443771682217e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245840/371472 [8:31:21<9:35:44,  3.64it/s]
 66%|██████▌   | 245841/371472 [8:31:22<9:19:12,  3.74it/s]
 66%|██████▌   | 245842/371472 [8:31:22<9:37:57,  3.62it/s]
 66%|██████▌   | 245843/371472 [8:31:22<9:23:26,  3.72it/s]
 66%|██████▌   | 245844/371472 [8:31:22<9:05:53,  3.84it/s]
 66%|██████▌   | 245845/371472 [8:31:23<9:16:58,  3.76it/s]
 66%|██████▌   | 245846/371472 [8:31:23<9:39:49,  3.61it/s]
 66%|██████▌   | 245847/371472 [8:31:23<9:34:07,  3.65it/s]
 66%|██████▌   | 245848/371472 [8:31:23<9:15:50,  3.77it/s]
 66%|██████▌   | 245849/371472 [8:31:24<9:39:16,  3.61it/s]
 66%|██████▌   | 245850/371472 [8:31:24<9:16:00,  3.77it/s]
 66%|██████▌   | 245851/371472 [8:31:24<9:45:25,  3.58it/s]
 66%|██████▌   | 245852/371472 [8:31:25<9:18:56,  3.75it/s]
 66%|██████▌   | 245853/371472 [8:31:25<9:30:34,  3.67it/s]
 66%|██████▌   | 245854/371472 [8:31:25<9:34:16,  3.65it/s]
 66%|██████▌   | 245855/371472 [8:31:25<9:57:03,  3.51it/s]
 66%|██████▌   | 245856/371472 [8:31:26<9:41:04,  3.60it/s]
 66%|██████▌   | 245857/371472 [8:31:26<9:26:22,  3.70it/s]
 66%|██████▌   | 245858/371472 [8:31:26<9:47:56,  3.56it/s]
 66%|██████▌   | 245859/371472 [8:31:27<9:41:54,  3.60it/s]
 66%|██████▌   | 245860/371472 [8:31:27<10:34:12,  3.30it/s]
                                                            
{'loss': 2.7768, 'learning_rate': 4.044958951927427e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245860/371472 [8:31:27<10:34:12,  3.30it/s]
 66%|██████▌   | 245861/371472 [8:31:27<10:00:29,  3.49it/s]
 66%|██████▌   | 245862/371472 [8:31:27<10:25:40,  3.35it/s]
 66%|██████▌   | 245863/371472 [8:31:28<9:59:01,  3.49it/s] 
 66%|██████▌   | 245864/371472 [8:31:28<9:28:30,  3.68it/s]
 66%|██████▌   | 245865/371472 [8:31:28<9:37:52,  3.62it/s]
 66%|██████▌   | 245866/371472 [8:31:29<10:01:46,  3.48it/s]
 66%|██████▌   | 245867/371472 [8:31:29<9:52:38,  3.53it/s] 
 66%|██████▌   | 245868/371472 [8:31:29<9:41:35,  3.60it/s]
 66%|██████▌   | 245869/371472 [8:31:29<9:14:09,  3.78it/s]
 66%|██████▌   | 245870/371472 [8:31:30<9:36:13,  3.63it/s]
 66%|██████▌   | 245871/371472 [8:31:30<9:57:53,  3.50it/s]
 66%|██████▌   | 245872/371472 [8:31:30<10:29:06,  3.33it/s]
 66%|██████▌   | 245873/371472 [8:31:31<10:20:02,  3.38it/s]
 66%|██████▌   | 245874/371472 [8:31:31<10:39:59,  3.27it/s]
 66%|██████▌   | 245875/371472 [8:31:31<10:03:36,  3.47it/s]
 66%|██████▌   | 245876/371472 [8:31:31<10:07:49,  3.44it/s]
 66%|██████▌   | 245877/371472 [8:31:32<9:40:56,  3.60it/s] 
 66%|██████▌   | 245878/371472 [8:31:32<9:28:01,  3.69it/s]
 66%|██████▌   | 245879/371472 [8:31:32<9:19:36,  3.74it/s]
 66%|██████▌   | 245880/371472 [8:31:32<9:11:54,  3.79it/s]
                                                           
{'loss': 2.7807, 'learning_rate': 4.044474132172639e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245880/371472 [8:31:32<9:11:54,  3.79it/s]
 66%|██████▌   | 245881/371472 [8:31:33<9:46:13,  3.57it/s]
 66%|██████▌   | 245882/371472 [8:31:33<10:31:57,  3.31it/s]
 66%|██████▌   | 245883/371472 [8:31:33<10:05:13,  3.46it/s]
 66%|██████▌   | 245884/371472 [8:31:34<10:03:46,  3.47it/s]
 66%|██████▌   | 245885/371472 [8:31:34<10:16:15,  3.40it/s]
 66%|██████▌   | 245886/371472 [8:31:34<10:26:36,  3.34it/s]
 66%|██████▌   | 245887/371472 [8:31:35<10:19:35,  3.38it/s]
 66%|██████▌   | 245888/371472 [8:31:35<9:56:53,  3.51it/s] 
 66%|██████▌   | 245889/371472 [8:31:35<9:34:57,  3.64it/s]
 66%|██████▌   | 245890/371472 [8:31:35<10:05:16,  3.46it/s]
 66%|██████▌   | 245891/371472 [8:31:36<9:56:13,  3.51it/s] 
 66%|██████▌   | 245892/371472 [8:31:36<9:42:22,  3.59it/s]
 66%|██████▌   | 245893/371472 [8:31:36<9:33:29,  3.65it/s]
 66%|██████▌   | 245894/371472 [8:31:36<9:22:51,  3.72it/s]
 66%|██████▌   | 245895/371472 [8:31:37<10:10:24,  3.43it/s]
 66%|██████▌   | 245896/371472 [8:31:37<9:36:55,  3.63it/s] 
 66%|██████▌   | 245897/371472 [8:31:37<10:35:08,  3.30it/s]
 66%|██████▌   | 245898/371472 [8:31:38<9:56:01,  3.51it/s] 
 66%|██████▌   | 245899/371472 [8:31:38<9:33:03,  3.65it/s]
 66%|██████▌   | 245900/371472 [8:31:38<9:26:17,  3.70it/s]
                                                           
{'loss': 2.9478, 'learning_rate': 4.0439893124178495e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245900/371472 [8:31:38<9:26:17,  3.70it/s]
 66%|██████▌   | 245901/371472 [8:31:38<9:09:53,  3.81it/s]
 66%|██████▌   | 245902/371472 [8:31:39<9:27:55,  3.69it/s]
 66%|██████▌   | 245903/371472 [8:31:39<9:39:32,  3.61it/s]
 66%|██████▌   | 245904/371472 [8:31:39<10:01:00,  3.48it/s]
 66%|██████▌   | 245905/371472 [8:31:40<10:02:09,  3.48it/s]
 66%|██████▌   | 245906/371472 [8:31:40<10:10:16,  3.43it/s]
 66%|██████▌   | 245907/371472 [8:31:40<10:18:03,  3.39it/s]
 66%|██████▌   | 245908/371472 [8:31:40<9:35:33,  3.64it/s] 
 66%|██████▌   | 245909/371472 [8:31:41<10:13:20,  3.41it/s]
 66%|██████▌   | 245910/371472 [8:31:41<10:11:29,  3.42it/s]
 66%|██████▌   | 245911/371472 [8:31:41<10:09:29,  3.43it/s]
 66%|█��████▌   | 245912/371472 [8:31:42<9:51:00,  3.54it/s] 
 66%|██████▌   | 245913/371472 [8:31:42<10:05:30,  3.46it/s]
 66%|██████▌   | 245914/371472 [8:31:42<9:45:29,  3.57it/s] 
 66%|██████▌   | 245915/371472 [8:31:42<9:19:09,  3.74it/s]
 66%|██████▌   | 245916/371472 [8:31:43<9:16:20,  3.76it/s]
 66%|██████▌   | 245917/371472 [8:31:43<9:11:25,  3.79it/s]
 66%|██████▌   | 245918/371472 [8:31:43<9:39:43,  3.61it/s]
 66%|██████▌   | 245919/371472 [8:31:44<9:32:18,  3.66it/s]
 66%|██████▌   | 245920/371472 [8:31:44<9:11:22,  3.80it/s]
                                                           
{'loss': 2.7797, 'learning_rate': 4.043504492663061e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245920/371472 [8:31:44<9:11:22,  3.80it/s]
 66%|██████▌   | 245921/371472 [8:31:44<9:15:18,  3.77it/s]
 66%|██████▌   | 245922/371472 [8:31:44<9:18:11,  3.75it/s]
 66%|██████▌   | 245923/371472 [8:31:45<9:05:25,  3.84it/s]
 66%|██████▌   | 245924/371472 [8:31:45<9:18:17,  3.75it/s]
 66%|██████▌   | 245925/371472 [8:31:45<9:35:38,  3.64it/s]
 66%|██████▌   | 245926/371472 [8:31:45<10:22:58,  3.36it/s]
 66%|██████▌   | 245927/371472 [8:31:46<10:07:37,  3.44it/s]
 66%|██████▌   | 245928/371472 [8:31:46<9:35:51,  3.63it/s] 
 66%|██████▌   | 245929/371472 [8:31:46<9:27:51,  3.68it/s]
 66%|██████▌   | 245930/371472 [8:31:47<9:51:48,  3.54it/s]
 66%|██████▌   | 245931/371472 [8:31:47<10:21:11,  3.37it/s]
 66%|██████▌   | 245932/371472 [8:31:47<9:55:52,  3.51it/s] 
 66%|██████▌   | 245933/371472 [8:31:47<9:43:09,  3.59it/s]
 66%|██████▌   | 245934/371472 [8:31:48<9:26:37,  3.69it/s]
 66%|██████▌   | 245935/371472 [8:31:48<9:12:08,  3.79it/s]
 66%|██████▌   | 245936/371472 [8:31:48<9:12:15,  3.79it/s]
 66%|██████▌   | 245937/371472 [8:31:48<8:57:35,  3.89it/s]
 66%|██████▌   | 245938/371472 [8:31:49<8:45:31,  3.98it/s]
 66%|██████▌   | 245939/371472 [8:31:49<9:01:06,  3.87it/s]
 66%|██████▌   | 245940/371472 [8:31:49<9:05:00,  3.84it/s]
                                                           
{'loss': 3.016, 'learning_rate': 4.0430196729082715e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245940/371472 [8:31:49<9:05:00,  3.84it/s]
 66%|██████▌   | 245941/371472 [8:31:49<9:14:13,  3.77it/s]
 66%|██████▌   | 245942/371472 [8:31:50<9:24:35,  3.71it/s]
 66%|██████▌   | 245943/371472 [8:31:50<9:16:02,  3.76it/s]
 66%|██████▌   | 245944/371472 [8:31:50<9:15:39,  3.77it/s]
 66%|██████▌   | 245945/371472 [8:31:51<9:10:26,  3.80it/s]
 66%|██████▌   | 245946/371472 [8:31:51<9:06:41,  3.83it/s]
 66%|██████▌   | 245947/371472 [8:31:51<9:39:02,  3.61it/s]
 66%|██████▌   | 245948/371472 [8:31:51<9:22:51,  3.72it/s]
 66%|██████▌   | 245949/371472 [8:31:52<9:20:39,  3.73it/s]
 66%|██████▌   | 245950/371472 [8:31:52<9:22:52,  3.72it/s]
 66%|██████▌   | 245951/371472 [8:31:52<9:22:42,  3.72it/s]
 66%|██████▌   | 245952/371472 [8:31:52<9:39:12,  3.61it/s]
 66%|██████▌   | 245953/371472 [8:31:53<9:31:32,  3.66it/s]
 66%|██████▌   | 245954/371472 [8:31:53<9:35:38,  3.63it/s]
 66%|██████▌   | 245955/371472 [8:31:53<9:51:21,  3.54it/s]
 66%|██████▌   | 245956/371472 [8:31:54<9:51:07,  3.54it/s]
 66%|██████▌   | 245957/371472 [8:31:54<9:23:20,  3.71it/s]
 66%|██████▌   | 245958/371472 [8:31:54<9:21:25,  3.73it/s]
 66%|██████▌   | 245959/371472 [8:31:54<9:17:42,  3.75it/s]
 66%|██████▌   | 245960/371472 [8:31:55<9:58:40,  3.49it/s]
                                                           
{'loss': 2.8166, 'learning_rate': 4.0425348531534833e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245960/371472 [8:31:55<9:58:40,  3.49it/s]
 66%|██████▌   | 245961/371472 [8:31:55<9:30:55,  3.66it/s]
 66%|██████▌   | 245962/371472 [8:31:55<10:31:13,  3.31it/s]
 66%|██████▌   | 245963/371472 [8:31:56<10:06:12,  3.45it/s]
 66%|██████▌   | 245964/371472 [8:31:56<10:28:16,  3.33it/s]
 66%|██████▌   | 245965/371472 [8:31:56<10:18:12,  3.38it/s]
 66%|██████▌   | 245966/371472 [8:31:56<10:43:54,  3.25it/s]
 66%|██████▌   | 245967/371472 [8:31:57<10:43:09,  3.25it/s]
 66%|██████▌   | 245968/371472 [8:31:57<10:30:42,  3.32it/s]
 66%|██████▌   | 245969/371472 [8:31:57<9:58:10,  3.50it/s] 
 66%|██████▌   | 245970/371472 [8:31:58<9:40:13,  3.61it/s]
 66%|██████▌   | 245971/371472 [8:31:58<9:27:41,  3.68it/s]
 66%|██████▌   | 245972/371472 [8:31:58<9:18:50,  3.74it/s]
 66%|██████▌   | 245973/371472 [8:31:58<9:38:29,  3.62it/s]
 66%|██████▌   | 245974/371472 [8:31:59<10:02:35,  3.47it/s]
 66%|██████▌   | 245975/371472 [8:31:59<9:36:02,  3.63it/s] 
 66%|██████▌   | 245976/371472 [8:31:59<9:35:24,  3.63it/s]
 66%|██████▌   | 245977/371472 [8:32:00<9:56:35,  3.51it/s]
 66%|██████▌   | 245978/371472 [8:32:00<9:57:33,  3.50it/s]
 66%|██████▌   | 245979/371472 [8:32:00<9:39:07,  3.61it/s]
 66%|██████▌   | 245980/371472 [8:32:00<10:07:46,  3.44it/s]
                                                            
{'loss': 2.8358, 'learning_rate': 4.0420500333986935e-07, 'epoch': 10.59}
+
 66%|██████▌   | 245980/371472 [8:32:00<10:07:46,  3.44it/s]
 66%|██████▌   | 245981/371472 [8:32:01<9:58:15,  3.50it/s] 
 66%|██████▌   | 245982/371472 [8:32:01<9:32:17,  3.65it/s]
 66%|██████▌   | 245983/371472 [8:32:01<10:05:49,  3.45it/s]
 66%|██████▌   | 245984/371472 [8:32:02<10:34:45,  3.29it/s]
 66%|██████▌   | 245985/371472 [8:32:02<10:37:00,  3.28it/s]
 66%|██████▌   | 245986/371472 [8:32:02<10:53:46,  3.20it/s]
 66%|██████▌   | 245987/371472 [8:32:03<10:43:28,  3.25it/s]
 66%|██████▌   | 245988/371472 [8:32:03<10:26:42,  3.34it/s]
 66%|██████▌   | 245989/371472 [8:32:03<9:55:49,  3.51it/s] 
 66%|██████▌   | 245990/371472 [8:32:03<10:10:43,  3.42it/s]
 66%|██████▌   | 245991/371472 [8:32:04<10:15:07,  3.40it/s]
 66%|██████▌   | 245992/371472 [8:32:04<9:45:48,  3.57it/s] 
 66%|██████▌   | 245993/371472 [8:32:04<9:43:45,  3.58it/s]
 66%|██████▌   | 245994/371472 [8:32:05<10:02:11,  3.47it/s]
 66%|██████▌   | 245995/371472 [8:32:05<9:45:11,  3.57it/s] 
 66%|██████▌   | 245996/371472 [8:32:05<9:37:20,  3.62it/s]
 66%|██████▌   | 245997/371472 [8:32:05<9:24:50,  3.70it/s]
 66%|██████▌   | 245998/371472 [8:32:06<9:31:50,  3.66it/s]
 66%|██████▌   | 245999/371472 [8:32:06<9:29:45,  3.67it/s]
 66%|██████▌   | 246000/371472 [8:32:06<9:45:25,  3.57it/s]
                                                           
{'loss': 2.8103, 'learning_rate': 4.041565213643905e-07, 'epoch': 10.6}
+
 66%|██████▌   | 246000/371472 [8:32:06<9:45:25,  3.57it/s]
 66%|██████▌   | 246001/371472 [8:32:06<9:21:23,  3.73it/s]
 66%|██████▌   | 246002/371472 [8:32:07<10:35:32,  3.29it/s]
 66%|██████▌   | 246003/371472 [8:32:07<10:21:39,  3.36it/s]
 66%|██████▌   | 246004/371472 [8:32:07<9:58:58,  3.49it/s] 
 66%|██████▌   | 246005/371472 [8:32:08<10:50:13,  3.22it/s]
 66%|██████▌   | 246006/371472 [8:32:08<10:40:48,  3.26it/s]
 66%|██████▌   | 246007/371472 [8:32:08<10:33:56,  3.30it/s]
 66%|██████▌   | 246008/371472 [8:32:09<10:55:42,  3.19it/s]
 66%|██████▌   | 246009/371472 [8:32:09<10:36:00,  3.29it/s]
 66%|██████▌   | 246010/371472 [8:32:09<10:04:32,  3.46it/s]
 66%|██████▌   | 246011/371472 [8:32:09<10:39:24,  3.27it/s]
 66%|██████▌   | 246012/371472 [8:32:10<10:31:48,  3.31it/s]
 66%|██████▌   | 246013/371472 [8:32:10<10:01:48,  3.47it/s]
 66%|██████▌   | 246014/371472 [8:32:10<10:32:54,  3.30it/s]
 66%|██████▌   | 246015/371472 [8:32:11<10:30:44,  3.32it/s]
 66%|██████▌   | 246016/371472 [8:32:11<9:59:29,  3.49it/s] 
 66%|██████▌   | 246017/371472 [8:32:11<9:32:03,  3.66it/s]
 66%|██████▌   | 246018/371472 [8:32:11<9:12:47,  3.78it/s]
 66%|██████▌   | 246019/371472 [8:32:12<10:49:56,  3.22it/s]
 66%|██████▌   | 246020/371472 [8:32:12<10:23:12,  3.36it/s]
                                                            
{'loss': 2.815, 'learning_rate': 4.041080393889116e-07, 'epoch': 10.6}
+
 66%|██████▌   | 246020/371472 [8:32:12<10:23:12,  3.36it/s]
 66%|██████▌   | 246021/371472 [8:32:12<9:57:28,  3.50it/s] 
 66%|██████▌   | 246022/371472 [8:32:13<9:40:47,  3.60it/s]
 66%|██████▌   | 246023/371472 [8:32:13<9:42:07,  3.59it/s]
 66%|██████▌   | 246024/371472 [8:32:13<9:48:56,  3.55it/s]
 66%|██████▌   | 246025/371472 [8:32:13<9:46:31,  3.56it/s]
 66%|██████▌   | 246026/371472 [8:32:14<9:46:57,  3.56it/s]
 66%|██████▌   | 246027/371472 [8:32:14<9:56:48,  3.50it/s]
 66%|██████▌   | 246028/371472 [8:32:14<10:13:20,  3.41it/s]
 66%|██████▌   | 246029/371472 [8:32:15<10:12:13,  3.41it/s]
 66%|██████▌   | 246030/371472 [8:32:15<9:59:07,  3.49it/s] 
 66%|██████▌   | 246031/371472 [8:32:15<10:30:51,  3.31it/s]
 66%|██████▌   | 246032/371472 [8:32:16<10:30:20,  3.32it/s]
 66%|██████▌   | 246033/371472 [8:32:16<9:51:55,  3.53it/s] 
 66%|██████▌   | 246034/371472 [8:32:16<9:32:18,  3.65it/s]
 66%|██████▌   | 246035/371472 [8:32:16<9:37:02,  3.62it/s]
 66%|██████▌   | 246036/371472 [8:32:17<9:39:42,  3.61it/s]
 66%|██████▌   | 246037/371472 [8:32:17<9:28:19,  3.68it/s]
 66%|██████▌   | 246038/371472 [8:32:17<10:02:47,  3.47it/s]
 66%|██████▌   | 246039/371472 [8:32:18<10:17:41,  3.38it/s]
 66%|██████▌   | 246040/371472 [8:32:18<10:07:48,  3.44it/s]
                                                            
{'loss': 2.8294, 'learning_rate': 4.040595574134327e-07, 'epoch': 10.6}
+
 66%|██████▌   | 246040/371472 [8:32:18<10:07:48,  3.44it/s]
 66%|██████▌   | 246041/371472 [8:32:18<10:00:13,  3.48it/s]
 66%|██████▌   | 246042/371472 [8:32:18<9:22:34,  3.72it/s] 
 66%|██████▌   | 246043/371472 [8:32:19<9:23:37,  3.71it/s]
 66%|██████▌   | 246044/371472 [8:32:19<9:28:13,  3.68it/s]
 66%|██████▌   | 246045/371472 [8:32:19<9:38:27,  3.61it/s]
 66%|██████▌   | 246046/371472 [8:32:19<9:27:58,  3.68it/s]
 66%|██████▌   | 246047/371472 [8:32:20<9:24:24,  3.70it/s]
 66%|██████▌   | 246048/371472 [8:32:20<10:08:31,  3.44it/s]
 66%|██████▌   | 246049/371472 [8:32:20<10:00:11,  3.48it/s]
 66%|██████▌   | 246050/371472 [8:32:21<9:41:09,  3.60it/s] 
 66%|██████▌   | 246051/371472 [8:32:21<9:48:37,  3.55it/s]
 66%|██████▌   | 246052/371472 [8:32:21<9:33:16,  3.65it/s]
 66%|██████▌   | 246053/371472 [8:32:21<9:25:12,  3.70it/s]
 66%|██████▌   | 246054/371472 [8:32:22<9:02:44,  3.85it/s]
 66%|██████▌   | 246055/371472 [8:32:22<9:09:12,  3.81it/s]
 66%|██████▌   | 246056/371472 [8:32:22<9:21:48,  3.72it/s]
 66%|██████▌   | 246057/371472 [8:32:22<9:11:47,  3.79it/s]
 66%|██████▌   | 246058/371472 [8:32:23<8:57:33,  3.89it/s]
 66%|██████▌   | 246059/371472 [8:32:23<9:24:36,  3.70it/s]
 66%|██████▌   | 246060/371472 [8:32:23<9:17:52,  3.75it/s]
                                                           
{'loss': 2.7577, 'learning_rate': 4.0401107543795374e-07, 'epoch': 10.6}
+
 66%|██████▌   | 246060/371472 [8:32:23<9:17:52,  3.75it/s]
 66%|██████▌   | 246061/371472 [8:32:23<9:17:06,  3.75it/s]
 66%|██████▌   | 246062/371472 [8:32:24<10:01:51,  3.47it/s]
 66%|██████▌   | 246063/371472 [8:32:24<9:43:39,  3.58it/s] 
 66%|██████▌   | 246064/371472 [8:32:24<9:34:53,  3.64it/s]
 66%|██████▌   | 246065/371472 [8:32:25<9:30:22,  3.66it/s]
 66%|██████▌   | 246066/371472 [8:32:25<9:57:21,  3.50it/s]
 66%|██████▌   | 246067/371472 [8:32:25<9:38:40,  3.61it/s]
 66%|██████▌   | 246068/371472 [8:32:25<9:07:31,  3.82it/s]
 66%|██████▌   | 246069/371472 [8:32:26<9:03:40,  3.84it/s]
 66%|██████▌   | 246070/371472 [8:32:26<9:38:09,  3.62it/s]
 66%|██████▌   | 246071/371472 [8:32:26<9:58:58,  3.49it/s]
 66%|██████▌   | 246072/371472 [8:32:27<10:28:38,  3.32it/s]
 66%|██████▌   | 246073/371472 [8:32:27<10:37:10,  3.28it/s]
 66%|██████▌   | 246074/371472 [8:32:27<10:58:18,  3.17it/s]
 66%|██████▌   | 246075/371472 [8:32:27<10:22:21,  3.36it/s]
 66%|██████▌   | 246076/371472 [8:32:28<10:18:22,  3.38it/s]
 66%|██████▌   | 246077/371472 [8:32:28<9:44:55,  3.57it/s] 
 66%|██████▌   | 246078/371472 [8:32:28<9:38:02,  3.62it/s]
 66%|██████▌   | 246079/371472 [8:32:29<9:34:31,  3.64it/s]
 66%|██████▌   | 246080/371472 [8:32:29<9:40:44,  3.60it/s]
                                                           
{'loss': 2.9574, 'learning_rate': 4.0396259346247497e-07, 'epoch': 10.6}
+
 66%|██████▌   | 246080/371472 [8:32:29<9:40:44,  3.60it/s]
 66%|██████▌   | 246081/371472 [8:32:29<9:54:57,  3.51it/s]
 66%|██████▌   | 246082/371472 [8:32:29<9:31:30,  3.66it/s]
 66%|██████▌   | 246083/371472 [8:32:30<9:11:42,  3.79it/s]
 66%|██████▌   | 246084/371472 [8:32:30<9:10:16,  3.80it/s]
 66%|██████▌   | 246085/371472 [8:32:30<9:02:11,  3.85it/s]
 66%|██████▌   | 246086/371472 [8:32:30<9:29:24,  3.67it/s]
 66%|██████▌   | 246087/371472 [8:32:31<9:57:08,  3.50it/s]
 66%|██████▌   | 246088/371472 [8:32:31<9:37:53,  3.62it/s]
 66%|██████▌   | 246089/371472 [8:32:31<10:01:24,  3.47it/s]
 66%|██████▌   | 246090/371472 [8:32:32<9:53:28,  3.52it/s] 
 66%|██████▌   | 246091/371472 [8:32:32<11:01:49,  3.16it/s]
 66%|██████▌   | 246092/371472 [8:32:32<10:07:13,  3.44it/s]
 66%|███���██▌   | 246093/371472 [8:32:33<9:49:28,  3.54it/s] 
 66%|██████▌   | 246094/371472 [8:32:33<9:27:55,  3.68it/s]
 66%|██████▌   | 246095/371472 [8:32:33<9:46:57,  3.56it/s]
 66%|██████▌   | 246096/371472 [8:32:33<10:01:39,  3.47it/s]
 66%|██████▌   | 246097/371472 [8:32:34<10:04:49,  3.45it/s]
 66%|██████▌   | 246098/371472 [8:32:34<9:52:10,  3.53it/s] 
 66%|██████▌   | 246099/371472 [8:32:34<10:05:28,  3.45it/s]
 66%|██████▌   | 246100/371472 [8:32:35<10:01:52,  3.47it/s]
                                                            
{'loss': 2.9365, 'learning_rate': 4.03914111486996e-07, 'epoch': 10.6}
+
 66%|██████▌   | 246100/371472 [8:32:35<10:01:52,  3.47it/s]
 66%|██████▋   | 246101/371472 [8:32:35<9:59:43,  3.48it/s] 
 66%|██████▋   | 246102/371472 [8:32:35<9:30:25,  3.66it/s]
 66%|██████▋   | 246103/371472 [8:32:35<9:37:39,  3.62it/s]
 66%|██████▋   | 246104/371472 [8:32:36<9:57:55,  3.49it/s]
 66%|██████▋   | 246105/371472 [8:32:36<9:46:07,  3.56it/s]
 66%|██████▋   | 246106/371472 [8:32:36<9:55:02,  3.51it/s]
 66%|██████▋   | 246107/371472 [8:32:36<9:39:48,  3.60it/s]
 66%|██████▋   | 246108/371472 [8:32:37<10:18:48,  3.38it/s]
 66%|██████▋   | 246109/371472 [8:32:37<11:02:09,  3.16it/s]
 66%|██████▋   | 246110/371472 [8:32:37<10:41:25,  3.26it/s]
 66%|██████▋   | 246111/371472 [8:32:38<11:27:55,  3.04it/s]
 66%|██████▋   | 246112/371472 [8:32:38<10:54:48,  3.19it/s]
 66%|██████▋   | 246113/371472 [8:32:38<10:17:58,  3.38it/s]
 66%|██████▋   | 246114/371472 [8:32:39<10:30:23,  3.31it/s]
 66%|██████▋   | 246115/371472 [8:32:39<10:06:06,  3.45it/s]
 66%|██████▋   | 246116/371472 [8:32:39<9:46:41,  3.56it/s] 
 66%|██████▋   | 246117/371472 [8:32:40<10:11:13,  3.42it/s]
 66%|██████▋   | 246118/371472 [8:32:40<10:00:20,  3.48it/s]
 66%|██████▋   | 246119/371472 [8:32:40<10:17:56,  3.38it/s]
 66%|██████▋   | 246120/371472 [8:32:40<10:05:46,  3.45it/s]
                                                            
{'loss': 2.6916, 'learning_rate': 4.0386562951151716e-07, 'epoch': 10.6}
+
 66%|██████▋   | 246120/371472 [8:32:40<10:05:46,  3.45it/s]
 66%|██████▋   | 246121/371472 [8:32:41<10:00:45,  3.48it/s]
 66%|██████▋   | 246122/371472 [8:32:41<9:36:54,  3.62it/s] 
 66%|██████▋   | 246123/371472 [8:32:41<9:21:42,  3.72it/s]
 66%|██████▋   | 246124/371472 [8:32:41<9:13:41,  3.77it/s]
 66%|██████▋   | 246125/371472 [8:32:42<9:36:13,  3.63it/s]
 66%|██████▋   | 246126/371472 [8:32:42<9:55:28,  3.51it/s]
 66%|██████▋   | 246127/371472 [8:32:42<9:57:07,  3.50it/s]
 66%|██████▋   | 246128/371472 [8:32:43<9:28:35,  3.67it/s]
 66%|██████▋   | 246129/371472 [8:32:43<9:16:51,  3.75it/s]
 66%|██████▋   | 246130/371472 [8:32:43<9:18:57,  3.74it/s]
 66%|██████▋   | 246131/371472 [8:32:43<9:29:06,  3.67it/s]
 66%|██████▋   | 246132/371472 [8:32:44<9:04:27,  3.84it/s]
 66%|██████▋   | 246133/371472 [8:32:44<9:09:59,  3.80it/s]
 66%|██████▋   | 246134/371472 [8:32:44<8:49:09,  3.95it/s]
 66%|██████▋   | 246135/371472 [8:32:44<8:58:53,  3.88it/s]
 66%|██████▋   | 246136/371472 [8:32:45<8:59:36,  3.87it/s]
 66%|██████▋   | 246137/371472 [8:32:45<9:07:38,  3.81it/s]
 66%|██████▋   | 246138/371472 [8:32:45<9:42:59,  3.58it/s]
 66%|██████▋   | 246139/371472 [8:32:45<9:29:09,  3.67it/s]
 66%|██████▋   | 246140/371472 [8:32:46<9:24:11,  3.70it/s]
                                                           
{'loss': 3.0611, 'learning_rate': 4.0381714753603824e-07, 'epoch': 10.6}
+
 66%|██████▋   | 246140/371472 [8:32:46<9:24:11,  3.70it/s]
 66%|██████▋   | 246141/371472 [8:32:46<9:12:43,  3.78it/s]
 66%|██████▋   | 246142/371472 [8:32:46<9:00:37,  3.86it/s]
 66%|██████▋   | 246143/371472 [8:32:47<9:26:31,  3.69it/s]
 66%|██████▋   | 246144/371472 [8:32:47<9:55:04,  3.51it/s]
 66%|██████▋   | 246145/371472 [8:32:47<9:48:18,  3.55it/s]
 66%|██████▋   | 246146/371472 [8:32:47<10:04:01,  3.46it/s]
 66%|██████▋   | 246147/371472 [8:32:48<10:39:16,  3.27it/s]
 66%|██████▋   | 246148/371472 [8:32:48<10:00:10,  3.48it/s]
 66%|██████▋   | 246149/371472 [8:32:48<9:56:09,  3.50it/s] 
 66%|██████▋   | 246150/371472 [8:32:49<9:44:25,  3.57it/s]
 66%|██████▋   | 246151/371472 [8:32:49<9:35:59,  3.63it/s]
 66%|██████▋   | 246152/371472 [8:32:49<9:37:04,  3.62it/s]
 66%|██████▋   | 246153/371472 [8:32:49<9:28:55,  3.67it/s]
 66%|██████▋   | 246154/371472 [8:32:50<9:12:27,  3.78it/s]
 66%|██████▋   | 246155/371472 [8:32:50<8:57:44,  3.88it/s]
 66%|██████▋   | 246156/371472 [8:32:50<9:45:33,  3.57it/s]
 66%|██████▋   | 246157/371472 [8:32:50<9:38:04,  3.61it/s]
 66%|██████▋   | 246158/371472 [8:32:51<9:39:07,  3.61it/s]
 66%|██████▋   | 246159/371472 [8:32:51<10:15:58,  3.39it/s]
 66%|██████▋   | 246160/371472 [8:32:51<10:21:20,  3.36it/s]
                                                            
{'loss': 2.7856, 'learning_rate': 4.0376866556055936e-07, 'epoch': 10.6}
+
 66%|██████▋   | 246160/371472 [8:32:51<10:21:20,  3.36it/s]
 66%|██████▋   | 246161/371472 [8:32:52<9:57:02,  3.50it/s] 
 66%|██████▋   | 246162/371472 [8:32:52<9:35:34,  3.63it/s]
 66%|██████▋   | 246163/371472 [8:32:52<9:50:31,  3.54it/s]
 66%|██████▋   | 246164/371472 [8:32:52<9:23:10,  3.71it/s]
 66%|██████▋   | 246165/371472 [8:32:53<9:21:35,  3.72it/s]
 66%|██████▋   | 246166/371472 [8:32:53<9:13:26,  3.77it/s]
 66%|██████▋   | 246167/371472 [8:32:53<9:07:33,  3.81it/s]
 66%|██████▋   | 246168/371472 [8:32:54<9:53:19,  3.52it/s]
 66%|██████▋   | 246169/371472 [8:32:54<9:57:24,  3.50it/s]
 66%|██████▋   | 246170/371472 [8:32:54<9:20:34,  3.73it/s]
 66%|██████▋   | 246171/371472 [8:32:54<9:19:02,  3.74it/s]
 66%|██████▋   | 246172/371472 [8:32:55<9:29:48,  3.66it/s]
 66%|██████▋   | 246173/371472 [8:32:55<9:23:32,  3.71it/s]
 66%|██████▋   | 246174/371472 [8:32:55<9:40:29,  3.60it/s]
 66%|██████▋   | 246175/371472 [8:32:55<9:20:34,  3.73it/s]
 66%|██████▋   | 246176/371472 [8:32:56<9:51:31,  3.53it/s]
 66%|██████▋   | 246177/371472 [8:32:56<10:00:42,  3.48it/s]
 66%|██████▋   | 246178/371472 [8:32:56<9:38:26,  3.61it/s] 
 66%|██████▋   | 246179/371472 [8:32:57<9:08:17,  3.81it/s]
 66%|██████▋   | 246180/371472 [8:32:57<9:40:00,  3.60it/s]
                                                           
{'loss': 2.847, 'learning_rate': 4.0372018358508043e-07, 'epoch': 10.6}
+
 66%|██████▋   | 246180/371472 [8:32:57<9:40:00,  3.60it/s]
 66%|██████▋   | 246181/371472 [8:32:57<9:59:54,  3.48it/s]
 66%|██████▋   | 246182/371472 [8:32:57<10:20:52,  3.36it/s]
 66%|██████▋   | 246183/371472 [8:32:58<9:58:14,  3.49it/s] 
 66%|██████▋   | 246184/371472 [8:32:58<9:39:11,  3.61it/s]
 66%|██████▋   | 246185/371472 [8:32:58<9:24:38,  3.70it/s]
 66%|██████▋   | 246186/371472 [8:32:59<9:31:06,  3.66it/s]
 66%|██████▋   | 246187/371472 [8:32:59<9:53:17,  3.52it/s]
 66%|██████▋   | 246188/371472 [8:32:59<9:18:38,  3.74it/s]
 66%|██████▋   | 246189/371472 [8:32:59<9:36:32,  3.62it/s]
 66%|██████▋   | 246190/371472 [8:33:00<9:10:26,  3.79it/s]
 66%|██████▋   | 246191/371472 [8:33:00<9:19:21,  3.73it/s]
 66%|██████▋   | 246192/371472 [8:33:00<10:25:26,  3.34it/s]
 66%|██████▋   | 246193/371472 [8:33:01<10:11:11,  3.42it/s]
 66%|██████▋   | 246194/371472 [8:33:01<10:31:59,  3.30it/s]
 66%|██████▋   | 246195/371472 [8:33:01<9:56:27,  3.50it/s] 
 66%|██████▋   | 246196/371472 [8:33:01<9:43:17,  3.58it/s]
 66%|██████▋   | 246197/371472 [8:33:02<9:45:00,  3.57it/s]
 66%|██████▋   | 246198/371472 [8:33:02<9:36:59,  3.62it/s]
 66%|██████▋   | 246199/371472 [8:33:02<9:24:26,  3.70it/s]
 66%|██████▋   | 246200/371472 [8:33:02<9:09:54,  3.80it/s]
                                                           
{'loss': 2.8786, 'learning_rate': 4.036717016096016e-07, 'epoch': 10.6}
+
 66%|██████▋   | 246200/371472 [8:33:02<9:09:54,  3.80it/s]
 66%|██████▋   | 246201/371472 [8:33:03<9:58:39,  3.49it/s]
 66%|██████▋   | 246202/371472 [8:33:03<9:28:27,  3.67it/s]
 66%|██████▋   | 246203/371472 [8:33:03<9:26:44,  3.68it/s]
 66%|██████▋   | 246204/371472 [8:33:04<9:47:22,  3.55it/s]
 66%|██████▋   | 246205/371472 [8:33:04<9:32:53,  3.64it/s]
 66%|██████▋   | 246206/371472 [8:33:04<9:29:30,  3.67it/s]
 66%|██████▋   | 246207/371472 [8:33:04<9:22:20,  3.71it/s]
 66%|██████▋   | 246208/371472 [8:33:05<10:05:24,  3.45it/s]
 66%|██████▋   | 246209/371472 [8:33:05<10:19:24,  3.37it/s]
 66%|██████▋   | 246210/371472 [8:33:05<9:57:26,  3.49it/s] 
 66%|██████▋   | 246211/371472 [8:33:06<10:04:48,  3.45it/s]
 66%|██████▋   | 246212/371472 [8:33:06<10:37:39,  3.27it/s]
 66%|██████▋   | 246213/371472 [8:33:06<10:13:19,  3.40it/s]
 66%|██████▋   | 246214/371472 [8:33:06<10:01:56,  3.47it/s]
 66%|██████▋   | 246215/371472 [8:33:07<10:01:08,  3.47it/s]
 66%|██████▋   | 246216/371472 [8:33:07<9:32:29,  3.65it/s] 
 66%|██████▋   | 246217/371472 [8:33:07<9:47:19,  3.55it/s]
 66%|██████▋   | 246218/371472 [8:33:08<9:50:23,  3.54it/s]
 66%|██████▋   | 246219/371472 [8:33:08<9:32:47,  3.64it/s]
 66%|██████▋   | 246220/371472 [8:33:08<9:27:21,  3.68it/s]
                                                           
{'loss': 2.811, 'learning_rate': 4.036232196341227e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246220/371472 [8:33:08<9:27:21,  3.68it/s]
 66%|██████▋   | 246221/371472 [8:33:08<10:00:49,  3.47it/s]
 66%|██████▋   | 246222/371472 [8:33:09<9:29:15,  3.67it/s] 
 66%|██████▋   | 246223/371472 [8:33:09<10:05:08,  3.45it/s]
 66%|██████▋   | 246224/371472 [8:33:09<10:23:14,  3.35it/s]
 66%|██████▋   | 246225/371472 [8:33:10<9:51:15,  3.53it/s] 
 66%|██████▋   | 246226/371472 [8:33:10<10:17:19,  3.38it/s]
 66%|██████▋   | 246227/371472 [8:33:10<11:40:00,  2.98it/s]
 66%|██████▋   | 246228/371472 [8:33:11<10:32:57,  3.30it/s]
 66%|██████▋   | 246229/371472 [8:33:11<10:56:11,  3.18it/s]
 66%|██████▋   | 246230/371472 [8:33:11<10:15:17,  3.39it/s]
 66%|██████▋   | 246231/371472 [8:33:11<9:50:56,  3.53it/s] 
 66%|██████▋   | 246232/371472 [8:33:12<9:41:08,  3.59it/s]
 66%|██████▋   | 246233/371472 [8:33:12<9:27:34,  3.68it/s]
 66%|██████▋   | 246234/371472 [8:33:12<9:34:09,  3.64it/s]
 66%|██████▋   | 246235/371472 [8:33:12<9:46:39,  3.56it/s]
 66%|██████▋   | 246236/371472 [8:33:13<9:49:20,  3.54it/s]
 66%|██████▋   | 246237/371472 [8:33:13<9:27:11,  3.68it/s]
 66%|██████▋   | 246238/371472 [8:33:13<9:44:55,  3.57it/s]
 66%|██████▋   | 246239/371472 [8:33:14<9:32:48,  3.64it/s]
 66%|██████▋   | 246240/371472 [8:33:14<9:32:11,  3.65it/s]
                                                           
{'loss': 2.8544, 'learning_rate': 4.035747376586438e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246240/371472 [8:33:14<9:32:11,  3.65it/s]
 66%|██████▋   | 246241/371472 [8:33:14<9:27:28,  3.68it/s]
 66%|██████▋   | 246242/371472 [8:33:14<9:12:54,  3.77it/s]
 66%|██████▋   | 246243/371472 [8:33:15<9:44:06,  3.57it/s]
 66%|██████▋   | 246244/371472 [8:33:15<10:03:09,  3.46it/s]
 66%|██████▋   | 246245/371472 [8:33:15<10:01:16,  3.47it/s]
 66%|██████▋   | 246246/371472 [8:33:15<9:31:59,  3.65it/s] 
 66%|██████▋   | 246247/371472 [8:33:16<10:00:29,  3.48it/s]
 66%|██████▋   | 246248/371472 [8:33:16<9:40:38,  3.59it/s] 
 66%|██████▋   | 246249/371472 [8:33:16<9:26:23,  3.68it/s]
 66%|██████▋   | 246250/371472 [8:33:17<9:30:56,  3.66it/s]
 66%|██████▋   | 246251/371472 [8:33:17<9:18:33,  3.74it/s]
 66%|██████▋   | 246252/371472 [8:33:17<9:15:56,  3.75it/s]
 66%|██████▋   | 246253/371472 [8:33:17<8:53:52,  3.91it/s]
 66%|██████▋   | 246254/371472 [8:33:18<8:50:48,  3.93it/s]
 66%|██████▋   | 246255/371472 [8:33:18<9:34:52,  3.63it/s]
 66%|██████▋   | 246256/371472 [8:33:18<9:36:41,  3.62it/s]
 66%|██████▋   | 246257/371472 [8:33:18<9:41:44,  3.59it/s]
 66%|██████▋   | 246258/371472 [8:33:19<9:39:05,  3.60it/s]
 66%|██████▋   | 246259/371472 [8:33:19<9:29:30,  3.66it/s]
 66%|██████▋   | 246260/371472 [8:33:19<9:40:48,  3.59it/s]
                                                           
{'loss': 3.0073, 'learning_rate': 4.035262556831649e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246260/371472 [8:33:19<9:40:48,  3.59it/s]
 66%|██████▋   | 246261/371472 [8:33:20<9:37:39,  3.61it/s]
 66%|██████▋   | 246262/371472 [8:33:20<9:29:10,  3.67it/s]
 66%|██████▋   | 246263/371472 [8:33:20<9:16:14,  3.75it/s]
 66%|██████▋   | 246264/371472 [8:33:20<9:27:41,  3.68it/s]
 66%|██████▋   | 246265/371472 [8:33:21<10:24:30,  3.34it/s]
 66%|██████▋   | 246266/371472 [8:33:21<10:04:58,  3.45it/s]
 66%|██████▋   | 246267/371472 [8:33:21<10:45:08,  3.23it/s]
 66%|██████▋   | 246268/371472 [8:33:22<11:33:46,  3.01it/s]
 66%|██████▋   | 246269/371472 [8:33:22<10:47:19,  3.22it/s]
 66%|██████▋   | 246270/371472 [8:33:22<10:40:40,  3.26it/s]
 66%|██████▋   | 246271/371472 [8:33:23<10:10:47,  3.42it/s]
 66%|██████▋   | 246272/371472 [8:33:23<9:45:14,  3.57it/s] 
 66%|██████▋   | 246273/371472 [8:33:23<9:30:58,  3.65it/s]
 66%|██████▋   | 246274/371472 [8:33:23<9:10:51,  3.79it/s]
 66%|██████▋   | 246275/371472 [8:33:24<9:01:22,  3.85it/s]
 66%|██████▋   | 246276/371472 [8:33:24<9:30:51,  3.66it/s]
 66%|██████▋   | 246277/371472 [8:33:24<9:13:48,  3.77it/s]
 66%|██████▋   | 246278/371472 [8:33:24<10:18:59,  3.37it/s]
 66%|██████▋   | 246279/371472 [8:33:25<9:50:48,  3.53it/s] 
 66%|██████▋   | 246280/371472 [8:33:25<9:30:43,  3.66it/s]
                                                           
{'loss': 2.874, 'learning_rate': 4.0347777370768605e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246280/371472 [8:33:25<9:30:43,  3.66it/s]
 66%|██████▋   | 246281/371472 [8:33:25<9:28:26,  3.67it/s]
 66%|██████▋   | 246282/371472 [8:33:26<9:24:49,  3.69it/s]
 66%|██████▋   | 246283/371472 [8:33:26<9:08:50,  3.80it/s]
 66%|██████▋   | 246284/371472 [8:33:26<9:03:25,  3.84it/s]
 66%|██████▋   | 246285/371472 [8:33:26<9:02:23,  3.85it/s]
 66%|██████▋   | 246286/371472 [8:33:27<9:24:24,  3.70it/s]
 66%|██████▋   | 246287/371472 [8:33:27<9:30:12,  3.66it/s]
 66%|██████▋   | 246288/371472 [8:33:27<9:37:02,  3.62it/s]
 66%|██████▋   | 246289/371472 [8:33:27<9:21:00,  3.72it/s]
 66%|██████▋   | 246290/371472 [8:33:28<9:38:20,  3.61it/s]
 66%|██████▋   | 246291/371472 [8:33:28<9:12:49,  3.77it/s]
 66%|██████▋   | 246292/371472 [8:33:28<9:14:14,  3.76it/s]
 66%|██████▋   | 246293/371472 [8:33:29<10:08:32,  3.43it/s]
 66%|██████▋   | 246294/371472 [8:33:29<10:11:21,  3.41it/s]
 66%|██████▋   | 246295/371472 [8:33:29<9:38:15,  3.61it/s] 
 66%|██████▋   | 246296/371472 [8:33:29<9:38:17,  3.61it/s]
 66%|██████▋   | 246297/371472 [8:33:30<9:31:11,  3.65it/s]
 66%|██████▋   | 246298/371472 [8:33:30<9:28:34,  3.67it/s]
 66%|██████▋   | 246299/371472 [8:33:30<9:19:19,  3.73it/s]
 66%|██████▋   | 246300/371472 [8:33:30<9:53:24,  3.52it/s]
                                                           
{'loss': 3.0069, 'learning_rate': 4.0342929173220707e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246300/371472 [8:33:30<9:53:24,  3.52it/s]
 66%|██████▋   | 246301/371472 [8:33:31<9:47:00,  3.55it/s]
 66%|██████▋   | 246302/371472 [8:33:31<9:20:48,  3.72it/s]
 66%|██████▋   | 246303/371472 [8:33:31<9:35:15,  3.63it/s]
 66%|██████▋   | 246304/371472 [8:33:32<9:19:18,  3.73it/s]
 66%|██████▋   | 246305/371472 [8:33:32<9:19:03,  3.73it/s]
 66%|██████▋   | 246306/371472 [8:33:32<9:18:49,  3.73it/s]
 66%|██████▋   | 246307/371472 [8:33:33<12:16:39,  2.83it/s]
 66%|██████▋   | 246308/371472 [8:33:33<12:06:19,  2.87it/s]
 66%|██████▋   | 246309/371472 [8:33:33<12:10:47,  2.85it/s]
 66%|██████▋   | 246310/371472 [8:33:34<11:17:21,  3.08it/s]
 66%|██████▋   | 246311/371472 [8:33:34<11:19:00,  3.07it/s]
 66%|██████▋   | 246312/371472 [8:33:34<10:34:53,  3.29it/s]
 66%|██████▋   | 246313/371472 [8:33:34<10:36:29,  3.28it/s]
 66%|██████▋   | 246314/371472 [8:33:35<10:38:46,  3.27it/s]
 66%|██████▋   | 246315/371472 [8:33:35<10:00:38,  3.47it/s]
 66%|██████▋   | 246316/371472 [8:33:35<11:31:34,  3.02it/s]
 66%|██████▋   | 246317/371472 [8:33:36<10:35:53,  3.28it/s]
 66%|██████▋   | 246318/371472 [8:33:36<10:50:09,  3.21it/s]
 66%|██████▋   | 246319/371472 [8:33:36<10:14:39,  3.39it/s]
 66%|██████▋   | 246320/371472 [8:33:37<9:57:36,  3.49it/s] 
                                                           
{'loss': 2.7608, 'learning_rate': 4.0338080975672825e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246320/371472 [8:33:37<9:57:36,  3.49it/s]
 66%|██████▋   | 246321/371472 [8:33:37<10:12:06,  3.41it/s]
 66%|██████▋   | 246322/371472 [8:33:37<11:30:29,  3.02it/s]
 66%|██████▋   | 246323/371472 [8:33:38<11:04:57,  3.14it/s]
 66%|██████▋   | 246324/371472 [8:33:38<10:55:12,  3.18it/s]
 66%|██████▋   | 246325/371472 [8:33:38<10:59:23,  3.16it/s]
 66%|██████▋   | 246326/371472 [8:33:38<10:22:39,  3.35it/s]
 66%|██████▋   | 246327/371472 [8:33:39<9:59:52,  3.48it/s] 
 66%|██████▋   | 246328/371472 [8:33:39<10:35:17,  3.28it/s]
 66%|██████▋   | 246329/371472 [8:33:39<9:55:41,  3.50it/s] 
 66%|██████▋   | 246330/371472 [8:33:40<10:22:26,  3.35it/s]
 66%|██████▋   | 246331/371472 [8:33:40<9:53:24,  3.51it/s] 
 66%|██████▋   | 246332/371472 [8:33:40<9:33:58,  3.63it/s]
 66%|██████▋   | 246333/371472 [8:33:40<9:40:03,  3.60it/s]
 66%|██████▋   | 246334/371472 [8:33:41<9:30:57,  3.65it/s]
 66%|██████▋   | 246335/371472 [8:33:41<10:02:36,  3.46it/s]
 66%|██████▋   | 246336/371472 [8:33:41<9:51:05,  3.53it/s] 
 66%|██████▋   | 246337/371472 [8:33:42<9:58:17,  3.49it/s]
 66%|██████▋   | 246338/371472 [8:33:42<9:56:18,  3.50it/s]
 66%|██████▋   | 246339/371472 [8:33:42<9:39:45,  3.60it/s]
 66%|██████▋   | 246340/371472 [8:33:42<10:26:46,  3.33it/s]
                                                            
{'loss': 2.6251, 'learning_rate': 4.033323277812493e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246340/371472 [8:33:42<10:26:46,  3.33it/s]
 66%|██████▋   | 246341/371472 [8:33:43<9:53:36,  3.51it/s] 
 66%|██████▋   | 246342/371472 [8:33:43<9:44:24,  3.57it/s]
 66%|██████▋   | 246343/371472 [8:33:43<9:20:31,  3.72it/s]
 66%|██████▋   | 246344/371472 [8:33:44<9:30:47,  3.65it/s]
 66%|██████▋   | 246345/371472 [8:33:44<9:17:01,  3.74it/s]
 66%|██████▋   | 246346/371472 [8:33:44<9:00:23,  3.86it/s]
 66%|██████▋   | 246347/371472 [8:33:44<8:51:15,  3.93it/s]
 66%|██████▋   | 246348/371472 [8:33:45<9:37:23,  3.61it/s]
 66%|██████▋   | 246349/371472 [8:33:45<9:09:44,  3.79it/s]
 66%|██████▋   | 246350/371472 [8:33:46<13:45:10,  2.53it/s]
 66%|██████▋   | 246351/371472 [8:33:46<12:30:44,  2.78it/s]
 66%|██████▋   | 246352/371472 [8:33:46<11:14:31,  3.09it/s]
 66%|██████▋   | 246353/371472 [8:33:46<10:43:43,  3.24it/s]
 66%|██████▋   | 246354/371472 [8:33:47<10:26:28,  3.33it/s]
 66%|██████▋   | 246355/371472 [8:33:47<10:14:09,  3.40it/s]
 66%|██████▋   | 246356/371472 [8:33:47<10:09:46,  3.42it/s]
 66%|██████▋   | 246357/371472 [8:33:47<9:32:28,  3.64it/s] 
 66%|██████▋   | 246358/371472 [8:33:48<9:38:25,  3.61it/s]
 66%|██████▋   | 246359/371472 [8:33:48<9:27:53,  3.67it/s]
 66%|██████▋   | 246360/371472 [8:33:48<9:17:39,  3.74it/s]
                                                           
{'loss': 3.0751, 'learning_rate': 4.0328384580577045e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246360/371472 [8:33:48<9:17:39,  3.74it/s]
 66%|██████▋   | 246361/371472 [8:33:48<9:15:11,  3.76it/s]
 66%|██████▋   | 246362/371472 [8:33:49<9:21:45,  3.71it/s]
 66%|██████▋   | 246363/371472 [8:33:49<9:17:40,  3.74it/s]
 66%|██████▋   | 246364/371472 [8:33:49<9:37:09,  3.61it/s]
 66%|██████▋   | 246365/371472 [8:33:50<9:43:35,  3.57it/s]
 66%|██████▋   | 246366/371472 [8:33:50<9:38:16,  3.61it/s]
 66%|██████▋   | 246367/371472 [8:33:50<9:30:50,  3.65it/s]
 66%|██████▋   | 246368/371472 [8:33:50<10:24:46,  3.34it/s]
 66%|██████▋   | 246369/371472 [8:33:51<10:21:21,  3.36it/s]
 66%|██████▋   | 246370/371472 [8:33:51<10:42:44,  3.24it/s]
 66%|██████▋   | 246371/371472 [8:33:51<10:15:13,  3.39it/s]
 66%|██████▋   | 246372/371472 [8:33:52<10:05:43,  3.44it/s]
 66%|██████▋   | 246373/371472 [8:33:52<11:04:12,  3.14it/s]
 66%|██████▋   | 246374/371472 [8:33:52<11:12:44,  3.10it/s]
 66%|██████▋   | 246375/371472 [8:33:53<10:38:00,  3.27it/s]
 66%|██████▋   | 246376/371472 [8:33:53<10:06:06,  3.44it/s]
 66%|██████▋   | 246377/371472 [8:33:53<9:45:16,  3.56it/s] 
 66%|██████▋   | 246378/371472 [8:33:53<9:20:06,  3.72it/s]
 66%|██████▋   | 246379/371472 [8:33:54<9:11:40,  3.78it/s]
 66%|██████▋   | 246380/371472 [8:33:54<9:04:07,  3.83it/s]
                                                           
{'loss': 2.7045, 'learning_rate': 4.032353638302915e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246380/371472 [8:33:54<9:04:07,  3.83it/s]
 66%|██████▋   | 246381/371472 [8:33:54<9:03:39,  3.83it/s]
 66%|██████▋   | 246382/371472 [8:33:54<8:57:52,  3.88it/s]
 66%|██████▋   | 246383/371472 [8:33:55<9:09:10,  3.80it/s]
 66%|██████▋   | 246384/371472 [8:33:55<9:03:53,  3.83it/s]
 66%|██████▋   | 246385/371472 [8:33:55<8:57:38,  3.88it/s]
 66%|██████▋   | 246386/371472 [8:33:56<10:17:52,  3.37it/s]
 66%|██████▋   | 246387/371472 [8:33:56<10:20:35,  3.36it/s]
 66%|██████▋   | 246388/371472 [8:33:56<9:45:15,  3.56it/s] 
 66%|██████▋   | 246389/371472 [8:33:56<9:17:19,  3.74it/s]
 66%|██████▋   | 246390/371472 [8:33:57<9:26:31,  3.68it/s]
 66%|██████▋   | 246391/371472 [8:33:57<9:36:48,  3.61it/s]
 66%|██████▋   | 246392/371472 [8:33:57<9:43:50,  3.57it/s]
 66%|██████▋   | 246393/371472 [8:33:57<9:24:18,  3.69it/s]
 66%|██████▋   | 246394/371472 [8:33:58<9:10:18,  3.79it/s]
 66%|██████▋   | 246395/371472 [8:33:58<9:13:13,  3.77it/s]
 66%|██████▋   | 246396/371472 [8:33:58<9:04:37,  3.83it/s]
 66%|██████▋   | 246397/371472 [8:33:59<9:22:49,  3.70it/s]
 66%|██████▋   | 246398/371472 [8:33:59<9:38:09,  3.61it/s]
 66%|██████▋   | 246399/371472 [8:33:59<9:24:36,  3.69it/s]
 66%|██████▋   | 246400/371472 [8:33:59<9:17:50,  3.74it/s]
                                                           
{'loss': 2.8683, 'learning_rate': 4.031868818548126e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246400/371472 [8:33:59<9:17:50,  3.74it/s]
 66%|██████▋   | 246401/371472 [8:34:00<9:14:13,  3.76it/s]
 66%|██████▋   | 246402/371472 [8:34:00<9:00:08,  3.86it/s]
 66%|██████▋   | 246403/371472 [8:34:00<9:19:09,  3.73it/s]
 66%|██████▋   | 246404/371472 [8:34:00<9:09:42,  3.79it/s]
 66%|██████▋   | 246405/371472 [8:34:01<9:33:15,  3.64it/s]
 66%|██████▋   | 246406/371472 [8:34:01<9:08:08,  3.80it/s]
 66%|██████▋   | 246407/371472 [8:34:01<8:54:07,  3.90it/s]
 66%|██████▋   | 246408/371472 [8:34:01<8:50:53,  3.93it/s]
 66%|██████▋   | 246409/371472 [8:34:02<8:53:37,  3.91it/s]
 66%|██████▋   | 246410/371472 [8:34:02<9:31:49,  3.65it/s]
 66%|██████▋   | 246411/371472 [8:34:02<9:17:22,  3.74it/s]
 66%|██████▋   | 246412/371472 [8:34:02<9:14:11,  3.76it/s]
 66%|██████▋   | 246413/371472 [8:34:03<9:31:05,  3.65it/s]
 66%|██████▋   | 246414/371472 [8:34:03<9:13:10,  3.77it/s]
 66%|██████▋   | 246415/371472 [8:34:03<9:08:13,  3.80it/s]
 66%|██████▋   | 246416/371472 [8:34:04<9:33:23,  3.64it/s]
 66%|██████▋   | 246417/371472 [8:34:04<10:19:49,  3.36it/s]
 66%|██████▋   | 246418/371472 [8:34:04<10:04:55,  3.45it/s]
 66%|██████▋   | 246419/371472 [8:34:05<10:46:36,  3.22it/s]
 66%|██████▋   | 246420/371472 [8:34:05<10:32:11,  3.30it/s]
                                                            
{'loss': 2.8851, 'learning_rate': 4.031383998793337e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246420/371472 [8:34:05<10:32:11,  3.30it/s]
 66%|██████▋   | 246421/371472 [8:34:05<10:06:27,  3.44it/s]
 66%|██████▋   | 246422/371472 [8:34:05<9:57:03,  3.49it/s] 
 66%|██████▋   | 246423/371472 [8:34:06<9:29:00,  3.66it/s]
 66%|██████▋   | 246424/371472 [8:34:06<9:26:53,  3.68it/s]
 66%|██████▋   | 246425/371472 [8:34:06<9:00:59,  3.85it/s]
 66%|██████▋   | 246426/371472 [8:34:06<9:20:32,  3.72it/s]
 66%|██████▋   | 246427/371472 [8:34:07<9:30:07,  3.66it/s]
 66%|██████▋   | 246428/371472 [8:34:07<9:22:58,  3.70it/s]
 66%|██████▋   | 246429/371472 [8:34:07<9:20:17,  3.72it/s]
 66%|██████▋   | 246430/371472 [8:34:08<9:34:44,  3.63it/s]
 66%|██████▋   | 246431/371472 [8:34:08<10:11:16,  3.41it/s]
 66%|██████▋   | 246432/371472 [8:34:08<11:55:41,  2.91it/s]
 66%|██████▋   | 246433/371472 [8:34:09<12:30:03,  2.78it/s]
 66%|██████▋   | 246434/371472 [8:34:09<11:38:48,  2.98it/s]
 66%|██████▋   | 246435/371472 [8:34:09<11:01:47,  3.15it/s]
 66%|██████▋   | 246436/371472 [8:34:10<10:17:46,  3.37it/s]
 66%|██████▋   | 246437/371472 [8:34:10<10:15:20,  3.39it/s]
 66%|██████▋   | 246438/371472 [8:34:10<10:15:09,  3.39it/s]
 66%|██████▋   | 246439/371472 [8:34:10<10:06:31,  3.44it/s]
 66%|██████▋   | 246440/371472 [8:34:11<10:24:19,  3.34it/s]
                                                            
{'loss': 2.7883, 'learning_rate': 4.030899179038548e-07, 'epoch': 10.61}
+
 66%|██████▋   | 246440/371472 [8:34:11<10:24:19,  3.34it/s]
 66%|██████▋   | 246441/371472 [8:34:11<9:51:23,  3.52it/s] 
 66%|██████▋   | 246442/371472 [8:34:11<9:30:49,  3.65it/s]
 66%|██████▋   | 246443/371472 [8:34:11<9:18:02,  3.73it/s]
 66%|██████▋   | 246444/371472 [8:34:12<9:55:33,  3.50it/s]
 66%|██████▋   | 246445/371472 [8:34:12<9:32:16,  3.64it/s]
 66%|██████▋   | 246446/371472 [8:34:12<10:06:19,  3.44it/s]
 66%|██████▋   | 246447/371472 [8:34:13<9:31:06,  3.65it/s] 
 66%|██████▋   | 246448/371472 [8:34:13<9:12:26,  3.77it/s]
 66%|██████▋   | 246449/371472 [8:34:13<8:58:09,  3.87it/s]
 66%|██████▋   | 246450/371472 [8:34:13<8:50:20,  3.93it/s]
 66%|██████▋   | 246451/371472 [8:34:14<9:11:07,  3.78it/s]
 66%|██████▋   | 246452/371472 [8:34:14<9:28:12,  3.67it/s]
 66%|██████▋   | 246453/371472 [8:34:14<9:55:02,  3.50it/s]
 66%|██████▋   | 246454/371472 [8:34:14<9:43:33,  3.57it/s]
 66%|██████▋   | 246455/371472 [8:34:15<10:00:32,  3.47it/s]
 66%|██████▋   | 246456/371472 [8:34:15<9:35:51,  3.62it/s] 
 66%|██████▋   | 246457/371472 [8:34:15<9:20:16,  3.72it/s]
 66%|██████▋   | 246458/371472 [8:34:16<9:15:10,  3.75it/s]
 66%|██████▋   | 246459/371472 [8:34:16<9:48:22,  3.54it/s]
 66%|██████▋   | 246460/371472 [8:34:16<9:59:28,  3.48it/s]
                                                           
{'loss': 2.7739, 'learning_rate': 4.0304143592837596e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246460/371472 [8:34:16<9:59:28,  3.48it/s]
 66%|██████▋   | 246461/371472 [8:34:16<9:35:06,  3.62it/s]
 66%|██████▋   | 246462/371472 [8:34:17<9:33:38,  3.63it/s]
 66%|██████▋   | 246463/371472 [8:34:17<9:16:08,  3.75it/s]
 66%|██████▋   | 246464/371472 [8:34:17<9:18:32,  3.73it/s]
 66%|██████▋   | 246465/371472 [8:34:17<9:07:28,  3.81it/s]
 66%|██████▋   | 246466/371472 [8:34:18<9:44:09,  3.57it/s]
 66%|██████▋   | 246467/371472 [8:34:18<10:17:00,  3.38it/s]
 66%|██████▋   | 246468/371472 [8:34:18<9:44:09,  3.57it/s] 
 66%|██████▋   | 246469/371472 [8:34:19<9:41:08,  3.58it/s]
 66%|██████▋   | 246470/371472 [8:34:19<9:55:51,  3.50it/s]
 66%|██████▋   | 246471/371472 [8:34:19<9:46:39,  3.55it/s]
 66%|██████▋   | 246472/371472 [8:34:20<10:02:14,  3.46it/s]
 66%|██████▋   | 246473/371472 [8:34:20<11:02:59,  3.14it/s]
 66%|██████▋   | 246474/371472 [8:34:20<10:20:50,  3.36it/s]
 66%|██████▋   | 246475/371472 [8:34:20<9:54:17,  3.51it/s] 
 66%|██████▋   | 246476/371472 [8:34:21<9:29:41,  3.66it/s]
 66%|██████▋   | 246477/371472 [8:34:21<9:04:28,  3.83it/s]
 66%|██████▋   | 246478/371472 [8:34:21<9:09:20,  3.79it/s]
 66%|██████▋   | 246479/371472 [8:34:21<9:18:15,  3.73it/s]
 66%|██████▋   | 246480/371472 [8:34:22<9:44:26,  3.56it/s]
                                                           
{'loss': 2.9042, 'learning_rate': 4.0299295395289703e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246480/371472 [8:34:22<9:44:26,  3.56it/s]
 66%|██████▋   | 246481/371472 [8:34:22<9:37:45,  3.61it/s]
 66%|██████▋   | 246482/371472 [8:34:22<9:19:28,  3.72it/s]
 66%|██████▋   | 246483/371472 [8:34:23<10:03:08,  3.45it/s]
 66%|██████▋   | 246484/371472 [8:34:23<9:42:03,  3.58it/s] 
 66%|██████▋   | 246485/371472 [8:34:23<9:49:49,  3.53it/s]
 66%|██████▋   | 246486/371472 [8:34:23<9:21:36,  3.71it/s]
 66%|██████▋   | 246487/371472 [8:34:24<9:12:14,  3.77it/s]
 66%|██████▋   | 246488/371472 [8:34:24<9:47:24,  3.55it/s]
 66%|██████▋   | 246489/371472 [8:34:24<10:12:47,  3.40it/s]
 66%|██████▋   | 246490/371472 [8:34:25<9:30:30,  3.65it/s] 
 66%|██████▋   | 246491/371472 [8:34:25<9:12:35,  3.77it/s]
 66%|██████▋   | 246492/371472 [8:34:25<8:54:22,  3.90it/s]
 66%|██████▋   | 246493/371472 [8:34:25<9:20:59,  3.71it/s]
 66%|██████▋   | 246494/371472 [8:34:26<9:08:03,  3.80it/s]
 66%|██████▋   | 246495/371472 [8:34:26<9:10:51,  3.78it/s]
 66%|██████▋   | 246496/371472 [8:34:26<9:37:06,  3.61it/s]
 66%|██████▋   | 246497/371472 [8:34:26<9:18:56,  3.73it/s]
 66%|██████▋   | 246498/371472 [8:34:27<9:27:42,  3.67it/s]
 66%|██████▋   | 246499/371472 [8:34:27<9:18:10,  3.73it/s]
 66%|██████▋   | 246500/371472 [8:34:27<9:10:20,  3.78it/s]
                                                           
{'loss': 2.8501, 'learning_rate': 4.0294447197741816e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246500/371472 [8:34:27<9:10:20,  3.78it/s]
 66%|██████▋   | 246501/371472 [8:34:27<9:24:56,  3.69it/s]
 66%|██████▋   | 246502/371472 [8:34:28<9:40:03,  3.59it/s]
 66%|██████▋   | 246503/371472 [8:34:28<9:55:20,  3.50it/s]
 66%|██████▋   | 246504/371472 [8:34:28<9:34:47,  3.62it/s]
 66%|██████▋   | 246505/371472 [8:34:29<9:21:30,  3.71it/s]
 66%|██████▋   | 246506/371472 [8:34:29<9:13:50,  3.76it/s]
 66%|██████▋   | 246507/371472 [8:34:29<9:20:11,  3.72it/s]
 66%|██████▋   | 246508/371472 [8:34:29<9:38:30,  3.60it/s]
 66%|██████▋   | 246509/371472 [8:34:30<9:17:23,  3.74it/s]
 66%|██████▋   | 246510/371472 [8:34:30<9:24:46,  3.69it/s]
 66%|██████▋   | 246511/371472 [8:34:30<9:15:54,  3.75it/s]
 66%|██████▋   | 246512/371472 [8:34:30<9:36:07,  3.61it/s]
 66%|██████▋   | 246513/371472 [8:34:31<10:35:11,  3.28it/s]
 66%|██████▋   | 246514/371472 [8:34:31<9:54:43,  3.50it/s] 
 66%|██████▋   | 246515/371472 [8:34:31<9:35:06,  3.62it/s]
 66%|██████▋   | 246516/371472 [8:34:32<9:29:55,  3.65it/s]
 66%|██████▋   | 246517/371472 [8:34:32<9:10:38,  3.78it/s]
 66%|██████▋   | 246518/371472 [8:34:32<9:11:47,  3.77it/s]
 66%|██████▋   | 246519/371472 [8:34:32<9:37:17,  3.61it/s]
 66%|██████▋   | 246520/371472 [8:34:33<9:54:59,  3.50it/s]
                                                           
{'loss': 2.7304, 'learning_rate': 4.0289599000193923e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246520/371472 [8:34:33<9:54:59,  3.50it/s]
 66%|██████▋   | 246521/371472 [8:34:33<9:41:53,  3.58it/s]
 66%|██████▋   | 246522/371472 [8:34:33<9:37:05,  3.61it/s]
 66%|██████▋   | 246523/371472 [8:34:34<9:38:30,  3.60it/s]
 66%|██████▋   | 246524/371472 [8:34:34<9:24:37,  3.69it/s]
 66%|██████▋   | 246525/371472 [8:34:34<9:27:33,  3.67it/s]
 66%|██████▋   | 246526/371472 [8:34:34<10:00:11,  3.47it/s]
 66%|██████▋   | 246527/371472 [8:34:35<9:26:43,  3.67it/s] 
 66%|██████▋   | 246528/371472 [8:34:35<9:04:46,  3.82it/s]
 66%|██████▋   | 246529/371472 [8:34:35<8:57:33,  3.87it/s]
 66%|██████▋   | 246530/371472 [8:34:35<9:17:44,  3.73it/s]
 66%|██████▋   | 246531/371472 [8:34:36<9:03:20,  3.83it/s]
 66%|██████▋   | 246532/371472 [8:34:36<9:06:30,  3.81it/s]
 66%|██████▋   | 246533/371472 [8:34:36<8:57:27,  3.87it/s]
 66%|██████▋   | 246534/371472 [8:34:36<9:17:43,  3.73it/s]
 66%|██████▋   | 246535/371472 [8:34:37<9:15:18,  3.75it/s]
 66%|██████▋   | 246536/371472 [8:34:37<9:30:38,  3.65it/s]
 66%|██████▋   | 246537/371472 [8:34:37<9:43:43,  3.57it/s]
 66%|██████▋   | 246538/371472 [8:34:38<9:28:17,  3.66it/s]
 66%|██████▋   | 246539/371472 [8:34:38<9:11:45,  3.77it/s]
 66%|██████▋   | 246540/371472 [8:34:38<9:39:19,  3.59it/s]
                                                           
{'loss': 3.0191, 'learning_rate': 4.028475080264604e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246540/371472 [8:34:38<9:39:19,  3.59it/s]
 66%|██████▋   | 246541/371472 [8:34:38<10:07:57,  3.42it/s]
 66%|██████▋   | 246542/371472 [8:34:39<10:18:56,  3.36it/s]
 66%|██████▋   | 246543/371472 [8:34:39<10:30:37,  3.30it/s]
 66%|██████▋   | 246544/371472 [8:34:39<9:54:21,  3.50it/s] 
 66%|██████▋   | 246545/371472 [8:34:40<9:41:24,  3.58it/s]
 66%|██████▋   | 246546/371472 [8:34:40<9:54:30,  3.50it/s]
 66%|██████▋   | 246547/371472 [8:34:40<9:54:02,  3.50it/s]
 66%|██████▋   | 246548/371472 [8:34:40<9:53:04,  3.51it/s]
 66%|██████▋   | 246549/371472 [8:34:41<9:36:23,  3.61it/s]
 66%|██████▋   | 246550/371472 [8:34:41<10:10:31,  3.41it/s]
 66%|██████▋   | 246551/371472 [8:34:41<9:51:36,  3.52it/s] 
 66%|██████▋   | 246552/371472 [8:34:42<9:46:05,  3.55it/s]
 66%|██████▋   | 246553/371472 [8:34:42<9:56:02,  3.49it/s]
 66%|██████▋   | 246554/371472 [8:34:42<9:46:33,  3.55it/s]
 66%|██████▋   | 246555/371472 [8:34:42<9:33:54,  3.63it/s]
 66%|██████▋   | 246556/371472 [8:34:43<10:09:15,  3.42it/s]
 66%|██████▋   | 246557/371472 [8:34:43<9:36:21,  3.61it/s] 
 66%|██████▋   | 246558/371472 [8:34:43<9:19:31,  3.72it/s]
 66%|██████▋   | 246559/371472 [8:34:44<10:46:30,  3.22it/s]
 66%|██████▋   | 246560/371472 [8:34:44<10:17:01,  3.37it/s]
                                                            
{'loss': 2.8881, 'learning_rate': 4.027990260509814e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246560/371472 [8:34:44<10:17:01,  3.37it/s]
 66%|██████▋   | 246561/371472 [8:34:44<10:22:53,  3.34it/s]
 66%|██████▋   | 246562/371472 [8:34:44<10:13:00,  3.40it/s]
 66%|██████▋   | 246563/371472 [8:34:45<9:49:46,  3.53it/s] 
 66%|██████▋   | 246564/371472 [8:34:45<9:39:39,  3.59it/s]
 66%|██████▋   | 246565/371472 [8:34:45<9:35:20,  3.62it/s]
 66%|██████▋   | 246566/371472 [8:34:46<9:52:28,  3.51it/s]
 66%|██████▋   | 246567/371472 [8:34:46<10:23:26,  3.34it/s]
 66%|██████▋   | 246568/371472 [8:34:46<10:05:41,  3.44it/s]
 66%|██████▋   | 246569/371472 [8:34:46<10:09:26,  3.42it/s]
 66%|██████▋   | 246570/371472 [8:34:47<10:17:08,  3.37it/s]
 66%|██████▋   | 246571/371472 [8:34:47<9:48:06,  3.54it/s] 
 66%|██████▋   | 246572/371472 [8:34:47<9:15:19,  3.75it/s]
 66%|██████▋   | 246573/371472 [8:34:48<8:51:08,  3.92it/s]
 66%|██████▋   | 246574/371472 [8:34:48<9:13:44,  3.76it/s]
 66%|██████▋   | 246575/371472 [8:34:48<9:13:09,  3.76it/s]
 66%|██████▋   | 246576/371472 [8:34:48<9:30:07,  3.65it/s]
 66%|██████▋   | 246577/371472 [8:34:49<9:10:34,  3.78it/s]
 66%|██████▋   | 246578/371472 [8:34:49<9:00:10,  3.85it/s]
 66%|██████▋   | 246579/371472 [8:34:49<10:17:22,  3.37it/s]
 66%|██████▋   | 246580/371472 [8:34:50<10:19:53,  3.36it/s]
                                                            
{'loss': 2.8836, 'learning_rate': 4.0275054407550266e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246580/371472 [8:34:50<10:19:53,  3.36it/s]
 66%|██████▋   | 246581/371472 [8:34:50<10:42:10,  3.24it/s]
 66%|██████▋   | 246582/371472 [8:34:50<11:06:10,  3.12it/s]
 66%|██████▋   | 246583/371472 [8:34:50<10:18:24,  3.37it/s]
 66%|██████▋   | 246584/371472 [8:34:51<10:13:12,  3.39it/s]
 66%|██████▋   | 246585/371472 [8:34:51<9:59:27,  3.47it/s] 
 66%|██████▋   | 246586/371472 [8:34:51<10:31:52,  3.29it/s]
 66%|██████▋   | 246587/371472 [8:34:52<9:57:37,  3.48it/s] 
 66%|██████▋   | 246588/371472 [8:34:52<9:36:40,  3.61it/s]
 66%|██████▋   | 246589/371472 [8:34:52<10:06:53,  3.43it/s]
 66%|██████▋   | 246590/371472 [8:34:52<10:07:45,  3.42it/s]
 66%|██████▋   | 246591/371472 [8:34:53<11:06:05,  3.12it/s]
 66%|██████▋   | 246592/371472 [8:34:53<11:50:13,  2.93it/s]
 66%|██████▋   | 246593/371472 [8:34:54<11:41:57,  2.96it/s]
 66%|██████▋   | 246594/371472 [8:34:54<11:07:42,  3.12it/s]
 66%|██████▋   | 246595/371472 [8:34:54<11:22:17,  3.05it/s]
 66%|██████▋   | 246596/371472 [8:34:55<11:10:10,  3.11it/s]
 66%|██████▋   | 246597/371472 [8:34:55<10:54:01,  3.18it/s]
 66%|██████▋   | 246598/371472 [8:34:55<10:47:00,  3.22it/s]
 66%|██████▋   | 246599/371472 [8:34:55<10:02:31,  3.45it/s]
 66%|██████▋   | 246600/371472 [8:34:56<10:19:14,  3.36it/s]
                                                            
{'loss': 2.8634, 'learning_rate': 4.027020621000237e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246600/371472 [8:34:56<10:19:14,  3.36it/s]
 66%|██████▋   | 246601/371472 [8:34:56<10:22:43,  3.34it/s]
 66%|██████▋   | 246602/371472 [8:34:56<9:59:34,  3.47it/s] 
 66%|██████▋   | 246603/371472 [8:34:57<9:51:38,  3.52it/s]
 66%|██████▋   | 246604/371472 [8:34:57<10:10:41,  3.41it/s]
 66%|██████▋   | 246605/371472 [8:34:57<10:19:29,  3.36it/s]
 66%|██████▋   | 246606/371472 [8:34:57<9:41:04,  3.58it/s] 
 66%|██████▋   | 246607/371472 [8:34:58<10:24:13,  3.33it/s]
 66%|██████▋   | 246608/371472 [8:34:58<10:08:23,  3.42it/s]
 66%|██████▋   | 246609/371472 [8:34:58<9:48:21,  3.54it/s] 
 66%|██████▋   | 246610/371472 [8:34:59<10:10:45,  3.41it/s]
 66%|██████▋   | 246611/371472 [8:34:59<9:49:21,  3.53it/s] 
 66%|██████▋   | 246612/371472 [8:34:59<9:29:55,  3.65it/s]
 66%|██████▋   | 246613/371472 [8:34:59<9:24:42,  3.69it/s]
 66%|██████▋   | 246614/371472 [8:35:00<9:12:27,  3.77it/s]
 66%|██████▋   | 246615/371472 [8:35:00<9:15:56,  3.74it/s]
 66%|██████▋   | 246616/371472 [8:35:00<9:29:26,  3.65it/s]
 66%|██████▋   | 246617/371472 [8:35:00<9:32:59,  3.63it/s]
 66%|██████▋   | 246618/371472 [8:35:01<9:59:48,  3.47it/s]
 66%|██████▋   | 246619/371472 [8:35:01<9:37:55,  3.60it/s]
 66%|██████▋   | 246620/371472 [8:35:01<9:30:22,  3.65it/s]
                                                           
{'loss': 2.7964, 'learning_rate': 4.026535801245448e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246620/371472 [8:35:01<9:30:22,  3.65it/s]
 66%|██████▋   | 246621/371472 [8:35:02<9:39:47,  3.59it/s]
 66%|██████▋   | 246622/371472 [8:35:02<9:22:22,  3.70it/s]
 66%|██████▋   | 246623/371472 [8:35:02<9:11:15,  3.77it/s]
 66%|██████▋   | 246624/371472 [8:35:02<9:20:55,  3.71it/s]
 66%|██████▋   | 246625/371472 [8:35:03<9:24:14,  3.69it/s]
 66%|██████▋   | 246626/371472 [8:35:03<9:12:04,  3.77it/s]
 66%|██████▋   | 246627/371472 [8:35:03<9:46:29,  3.55it/s]
 66%|██████▋   | 246628/371472 [8:35:04<10:16:08,  3.38it/s]
 66%|██████▋   | 246629/371472 [8:35:04<10:04:21,  3.44it/s]
 66%|██████▋   | 246630/371472 [8:35:04<9:37:36,  3.60it/s] 
 66%|██████▋   | 246631/371472 [8:35:04<9:22:33,  3.70it/s]
 66%|██████▋   | 246632/371472 [8:35:05<10:09:46,  3.41it/s]
 66%|██████▋   | 246633/371472 [8:35:05<10:10:44,  3.41it/s]
 66%|██████▋   | 246634/371472 [8:35:05<9:45:08,  3.56it/s] 
 66%|██████▋   | 246635/371472 [8:35:05<9:35:05,  3.62it/s]
 66%|██████▋   | 246636/371472 [8:35:06<10:24:10,  3.33it/s]
 66%|██████▋   | 246637/371472 [8:35:06<10:07:30,  3.42it/s]
 66%|██████▋   | 246638/371472 [8:35:06<9:26:25,  3.67it/s] 
 66%|██████▋   | 246639/371472 [8:35:07<10:20:26,  3.35it/s]
 66%|██████▋   | 246640/371472 [8:35:07<10:28:33,  3.31it/s]
                                                            
{'loss': 2.9948, 'learning_rate': 4.0260509814906587e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246640/371472 [8:35:07<10:28:33,  3.31it/s]
 66%|██████▋   | 246641/371472 [8:35:07<9:46:46,  3.55it/s] 
 66%|██████▋   | 246642/371472 [8:35:08<9:44:28,  3.56it/s]
 66%|██████▋   | 246643/371472 [8:35:08<9:36:13,  3.61it/s]
 66%|██████▋   | 246644/371472 [8:35:08<9:36:44,  3.61it/s]
 66%|██████▋   | 246645/371472 [8:35:08<9:25:08,  3.68it/s]
 66%|██████▋   | 246646/371472 [8:35:09<9:28:21,  3.66it/s]
 66%|██████▋   | 246647/371472 [8:35:09<9:35:03,  3.62it/s]
 66%|██████▋   | 246648/371472 [8:35:09<9:21:06,  3.71it/s]
 66%|██████▋   | 246649/371472 [8:35:09<9:30:38,  3.65it/s]
 66%|██████▋   | 246650/371472 [8:35:10<9:50:36,  3.52it/s]
 66%|██████▋   | 246651/371472 [8:35:10<9:58:02,  3.48it/s]
 66%|██████▋   | 246652/371472 [8:35:10<10:18:21,  3.36it/s]
 66%|██████▋   | 246653/371472 [8:35:11<10:25:47,  3.32it/s]
 66%|██████▋   | 246654/371472 [8:35:11<10:02:24,  3.45it/s]
 66%|██████▋   | 246655/371472 [8:35:11<9:53:57,  3.50it/s] 
 66%|██████▋   | 246656/371472 [8:35:12<11:34:18,  3.00it/s]
 66%|██████▋   | 246657/371472 [8:35:12<11:01:04,  3.15it/s]
 66%|██████▋   | 246658/371472 [8:35:12<10:19:54,  3.36it/s]
 66%|██████▋   | 246659/371472 [8:35:12<10:40:09,  3.25it/s]
 66%|██████▋   | 246660/371472 [8:35:13<10:10:53,  3.41it/s]
                                                            
{'loss': 2.9357, 'learning_rate': 4.0255661617358705e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246660/371472 [8:35:13<10:10:53,  3.41it/s]
 66%|██████▋   | 246661/371472 [8:35:13<10:22:34,  3.34it/s]
 66%|██████▋   | 246662/371472 [8:35:13<10:09:48,  3.41it/s]
 66%|██████▋   | 246663/371472 [8:35:14<9:45:25,  3.55it/s] 
 66%|██████▋   | 246664/371472 [8:35:14<9:58:35,  3.48it/s]
 66%|██████▋   | 246665/371472 [8:35:14<9:49:46,  3.53it/s]
 66%|██████▋   | 246666/371472 [8:35:14<9:28:09,  3.66it/s]
 66%|██████▋   | 246667/371472 [8:35:15<8:58:31,  3.86it/s]
 66%|██████▋   | 246668/371472 [8:35:15<9:44:17,  3.56it/s]
 66%|██████▋   | 246669/371472 [8:35:15<9:31:23,  3.64it/s]
 66%|██████▋   | 246670/371472 [8:35:16<9:29:33,  3.65it/s]
 66%|██████▋   | 246671/371472 [8:35:16<9:20:38,  3.71it/s]
 66%|██████▋   | 246672/371472 [8:35:16<9:28:01,  3.66it/s]
 66%|██████▋   | 246673/371472 [8:35:16<9:09:52,  3.78it/s]
 66%|██████▋   | 246674/371472 [8:35:17<9:42:37,  3.57it/s]
 66%|██████▋   | 246675/371472 [8:35:17<9:52:08,  3.51it/s]
 66%|██████▋   | 246676/371472 [8:35:17<9:24:47,  3.68it/s]
 66%|██████▋   | 246677/371472 [8:35:17<9:09:47,  3.78it/s]
 66%|██████▋   | 246678/371472 [8:35:18<10:06:28,  3.43it/s]
 66%|██████▋   | 246679/371472 [8:35:18<9:45:48,  3.55it/s] 
 66%|██████▋   | 246680/371472 [8:35:18<9:22:12,  3.70it/s]
                                                           
{'loss': 2.9076, 'learning_rate': 4.0250813419810807e-07, 'epoch': 10.62}
+
 66%|██████▋   | 246680/371472 [8:35:18<9:22:12,  3.70it/s]
 66%|██████▋   | 246681/371472 [8:35:19<9:22:03,  3.70it/s]
 66%|██████▋   | 246682/371472 [8:35:19<9:17:17,  3.73it/s]
 66%|██████▋   | 246683/371472 [8:35:19<9:02:25,  3.83it/s]
 66%|██████▋   | 246684/371472 [8:35:19<9:40:11,  3.58it/s]
 66%|██████▋   | 246685/371472 [8:35:20<10:18:56,  3.36it/s]
 66%|██████▋   | 246686/371472 [8:35:20<10:03:08,  3.45it/s]
 66%|██████▋   | 246687/371472 [8:35:20<11:10:34,  3.10it/s]
 66%|██████▋   | 246688/371472 [8:35:21<10:20:46,  3.35it/s]
 66%|██████▋   | 246689/371472 [8:35:21<9:43:08,  3.57it/s] 
 66%|██████▋   | 246690/371472 [8:35:21<9:31:06,  3.64it/s]
 66%|██████▋   | 246691/371472 [8:35:21<9:12:15,  3.77it/s]
 66%|██████▋   | 246692/371472 [8:35:22<9:22:02,  3.70it/s]
 66%|██████▋   | 246693/371472 [8:35:22<10:02:41,  3.45it/s]
 66%|██████▋   | 246694/371472 [8:35:22<10:11:41,  3.40it/s]
 66%|██████▋   | 246695/371472 [8:35:23<9:34:11,  3.62it/s] 
 66%|██████▋   | 246696/371472 [8:35:23<10:21:58,  3.34it/s]
 66%|██████▋   | 246697/371472 [8:35:23<9:49:12,  3.53it/s] 
 66%|██████▋   | 246698/371472 [8:35:23<9:23:12,  3.69it/s]
 66%|██████▋   | 246699/371472 [8:35:24<9:42:40,  3.57it/s]
 66%|██████▋   | 246700/371472 [8:35:24<9:32:12,  3.63it/s]
                                                           
{'loss': 2.7043, 'learning_rate': 4.0245965222262924e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246700/371472 [8:35:24<9:32:12,  3.63it/s]
 66%|██████▋   | 246701/371472 [8:35:24<9:12:05,  3.77it/s]
 66%|██████▋   | 246702/371472 [8:35:24<9:14:39,  3.75it/s]
 66%|██████▋   | 246703/371472 [8:35:25<9:24:31,  3.68it/s]
 66%|██████▋   | 246704/371472 [8:35:25<9:36:53,  3.60it/s]
 66%|██████▋   | 246705/371472 [8:35:25<9:52:56,  3.51it/s]
 66%|██████▋   | 246706/371472 [8:35:26<10:11:05,  3.40it/s]
 66%|██████▋   | 246707/371472 [8:35:26<9:46:05,  3.55it/s] 
 66%|██████▋   | 246708/371472 [8:35:26<10:10:29,  3.41it/s]
 66%|██████▋   | 246709/371472 [8:35:26<9:58:44,  3.47it/s] 
 66%|██████▋   | 246710/371472 [8:35:27<9:54:47,  3.50it/s]
 66%|██████▋   | 246711/371472 [8:35:27<10:16:12,  3.37it/s]
 66%|██████▋   | 246712/371472 [8:35:27<9:52:04,  3.51it/s] 
 66%|██████▋   | 246713/371472 [8:35:28<9:52:06,  3.51it/s]
 66%|██████▋   | 246714/371472 [8:35:28<9:44:40,  3.56it/s]
 66%|██████▋   | 246715/371472 [8:35:28<9:11:45,  3.77it/s]
 66%|██████▋   | 246716/371472 [8:35:28<8:55:00,  3.89it/s]
 66%|██████▋   | 246717/371472 [8:35:29<9:01:39,  3.84it/s]
 66%|██████▋   | 246718/371472 [8:35:29<9:27:25,  3.66it/s]
 66%|██████▋   | 246719/371472 [8:35:29<9:29:21,  3.65it/s]
 66%|██████▋   | 246720/371472 [8:35:29<9:19:45,  3.71it/s]
                                                           
{'loss': 2.7146, 'learning_rate': 4.024111702471503e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246720/371472 [8:35:29<9:19:45,  3.71it/s]
 66%|██████▋   | 246721/371472 [8:35:30<9:22:38,  3.70it/s]
 66%|██████▋   | 246722/371472 [8:35:30<9:20:57,  3.71it/s]
 66%|██████▋   | 246723/371472 [8:35:30<9:15:55,  3.74it/s]
 66%|██████▋   | 246724/371472 [8:35:31<9:13:24,  3.76it/s]
 66%|██████▋   | 246725/371472 [8:35:31<10:31:21,  3.29it/s]
 66%|██████▋   | 246726/371472 [8:35:31<10:29:56,  3.30it/s]
 66%|██████▋   | 246727/371472 [8:35:31<9:53:47,  3.50it/s] 
 66%|██████▋   | 246728/371472 [8:35:32<9:35:27,  3.61it/s]
 66%|██████▋   | 246729/371472 [8:35:32<9:25:43,  3.68it/s]
 66%|██████▋   | 246730/371472 [8:35:32<9:38:09,  3.60it/s]
 66%|██████▋   | 246731/371472 [8:35:33<9:25:17,  3.68it/s]
 66%|██████▋   | 246732/371472 [8:35:33<10:10:26,  3.41it/s]
 66%|██████▋   | 246733/371472 [8:35:33<10:33:25,  3.28it/s]
 66%|██████▋   | 246734/371472 [8:35:34<10:42:41,  3.23it/s]
 66%|██████▋   | 246735/371472 [8:35:34<10:07:07,  3.42it/s]
 66%|██████▋   | 246736/371472 [8:35:34<9:58:58,  3.47it/s] 
 66%|██████▋   | 246737/371472 [8:35:34<9:56:46,  3.48it/s]
 66%|██████▋   | 246738/371472 [8:35:35<9:59:43,  3.47it/s]
 66%|██████▋   | 246739/371472 [8:35:35<11:13:20,  3.09it/s]
 66%|██████▋   | 246740/371472 [8:35:35<10:13:53,  3.39it/s]
                                                            
{'loss': 2.7766, 'learning_rate': 4.0236268827167144e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246740/371472 [8:35:35<10:13:53,  3.39it/s]
 66%|██████▋   | 246741/371472 [8:35:36<10:58:35,  3.16it/s]
 66%|██████▋   | 246742/371472 [8:35:36<10:53:19,  3.18it/s]
 66%|██████▋   | 246743/371472 [8:35:36<10:25:12,  3.32it/s]
 66%|██████▋   | 246744/371472 [8:35:36<9:58:19,  3.47it/s] 
 66%|██████▋   | 246745/371472 [8:35:37<10:59:36,  3.15it/s]
 66%|██████▋   | 246746/371472 [8:35:37<10:56:44,  3.17it/s]
 66%|██████▋   | 246747/371472 [8:35:37<10:23:23,  3.33it/s]
 66%|██████▋   | 246748/371472 [8:35:38<11:07:17,  3.12it/s]
 66%|██████▋   | 246749/371472 [8:35:38<10:21:16,  3.35it/s]
 66%|██████▋   | 246750/371472 [8:35:38<10:18:41,  3.36it/s]
 66%|██████▋   | 246751/371472 [8:35:39<10:03:13,  3.45it/s]
 66%|██████▋   | 246752/371472 [8:35:39<9:47:53,  3.54it/s] 
 66%|██████▋   | 246753/371472 [8:35:39<10:05:53,  3.43it/s]
 66%|██████▋   | 246754/371472 [8:35:39<10:07:40,  3.42it/s]
 66%|██████▋   | 246755/371472 [8:35:40<10:07:47,  3.42it/s]
 66%|██████▋   | 246756/371472 [8:35:40<11:36:25,  2.98it/s]
 66%|██████▋   | 246757/371472 [8:35:40<10:58:14,  3.16it/s]
 66%|██████▋   | 246758/371472 [8:35:41<10:38:10,  3.26it/s]
 66%|██████▋   | 246759/371472 [8:35:41<9:51:54,  3.51it/s] 
 66%|██████▋   | 246760/371472 [8:35:41<9:38:45,  3.59it/s]
                                                           
{'loss': 2.9135, 'learning_rate': 4.023142062961925e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246760/371472 [8:35:41<9:38:45,  3.59it/s]
 66%|██████▋   | 246761/371472 [8:35:42<10:26:42,  3.32it/s]
 66%|██████▋   | 246762/371472 [8:35:42<9:57:23,  3.48it/s] 
 66%|██████▋   | 246763/371472 [8:35:42<9:39:50,  3.58it/s]
 66%|██████▋   | 246764/371472 [8:35:42<9:41:13,  3.58it/s]
 66%|██████▋   | 246765/371472 [8:35:43<9:24:39,  3.68it/s]
 66%|██████▋   | 246766/371472 [8:35:43<9:12:21,  3.76it/s]
 66%|██████▋   | 246767/371472 [8:35:43<9:21:11,  3.70it/s]
 66%|██████▋   | 246768/371472 [8:35:43<9:26:48,  3.67it/s]
 66%|██████▋   | 246769/371472 [8:35:44<9:15:32,  3.74it/s]
 66%|██████▋   | 246770/371472 [8:35:44<9:02:55,  3.83it/s]
 66%|██████▋   | 246771/371472 [8:35:44<9:07:32,  3.80it/s]
 66%|██████▋   | 246772/371472 [8:35:45<9:23:22,  3.69it/s]
 66%|██████▋   | 246773/371472 [8:35:45<9:17:22,  3.73it/s]
 66%|██████▋   | 246774/371472 [8:35:45<9:09:09,  3.78it/s]
 66%|██████▋   | 246775/371472 [8:35:45<9:17:32,  3.73it/s]
 66%|██████▋   | 246776/371472 [8:35:46<9:01:59,  3.83it/s]
 66%|██████▋   | 246777/371472 [8:35:46<8:53:11,  3.90it/s]
 66%|██████▋   | 246778/371472 [8:35:46<8:39:17,  4.00it/s]
 66%|██████▋   | 246779/371472 [8:35:46<9:54:31,  3.50it/s]
 66%|██████▋   | 246780/371472 [8:35:47<9:45:03,  3.55it/s]
                                                           
{'loss': 2.9584, 'learning_rate': 4.022657243207137e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246780/371472 [8:35:47<9:45:03,  3.55it/s]
 66%|██████▋   | 246781/371472 [8:35:47<9:47:23,  3.54it/s]
 66%|██████▋   | 246782/371472 [8:35:47<9:48:41,  3.53it/s]
 66%|██████▋   | 246783/371472 [8:35:48<9:30:00,  3.65it/s]
 66%|██████▋   | 246784/371472 [8:35:48<9:11:18,  3.77it/s]
 66%|██████▋   | 246785/371472 [8:35:48<8:46:02,  3.95it/s]
 66%|██████▋   | 246786/371472 [8:35:48<8:53:09,  3.90it/s]
 66%|██████▋   | 246787/371472 [8:35:49<8:46:39,  3.95it/s]
 66%|██████▋   | 246788/371472 [8:35:49<8:41:27,  3.99it/s]
 66%|██████▋   | 246789/371472 [8:35:49<9:04:08,  3.82it/s]
 66%|██████▋   | 246790/371472 [8:35:49<8:57:50,  3.86it/s]
 66%|██████▋   | 246791/371472 [8:35:50<8:52:18,  3.90it/s]
 66%|██████▋   | 246792/371472 [8:35:50<8:57:40,  3.86it/s]
 66%|██████▋   | 246793/371472 [8:35:50<9:06:38,  3.80it/s]
 66%|██████▋   | 246794/371472 [8:35:50<9:31:51,  3.63it/s]
 66%|██████▋   | 246795/371472 [8:35:51<9:21:22,  3.70it/s]
 66%|██████▋   | 246796/371472 [8:35:51<9:22:30,  3.69it/s]
 66%|██████▋   | 246797/371472 [8:35:51<10:08:01,  3.42it/s]
 66%|██████▋   | 246798/371472 [8:35:52<9:50:23,  3.52it/s] 
 66%|██████▋   | 246799/371472 [8:35:52<9:38:58,  3.59it/s]
 66%|██████▋   | 246800/371472 [8:35:52<9:58:45,  3.47it/s]
                                                           
{'loss': 2.9363, 'learning_rate': 4.022172423452347e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246800/371472 [8:35:52<9:58:45,  3.47it/s]
 66%|██████▋   | 246801/371472 [8:35:52<9:39:34,  3.59it/s]
 66%|██████▋   | 246802/371472 [8:35:53<9:55:52,  3.49it/s]
 66%|██████▋   | 246803/371472 [8:35:53<9:51:07,  3.51it/s]
 66%|██████▋   | 246804/371472 [8:35:53<10:37:46,  3.26it/s]
 66%|██████▋   | 246805/371472 [8:35:54<10:21:11,  3.34it/s]
 66%|██████▋   | 246806/371472 [8:35:54<11:39:16,  2.97it/s]
 66%|██████▋   | 246807/371472 [8:35:54<10:46:13,  3.22it/s]
 66%|██████▋   | 246808/371472 [8:35:55<10:13:41,  3.39it/s]
 66%|██████▋   | 246809/371472 [8:35:55<10:09:11,  3.41it/s]
 66%|██████▋   | 246810/371472 [8:35:55<10:12:44,  3.39it/s]
 66%|██████▋   | 246811/371472 [8:35:55<10:00:00,  3.46it/s]
 66%|██████▋   | 246812/371472 [8:35:56<9:43:54,  3.56it/s] 
 66%|██████▋   | 246813/371472 [8:35:56<9:52:46,  3.50it/s]
 66%|██████▋   | 246814/371472 [8:35:56<9:31:59,  3.63it/s]
 66%|██████▋   | 246815/371472 [8:35:56<9:13:23,  3.75it/s]
 66%|██████▋   | 246816/371472 [8:35:57<9:58:46,  3.47it/s]
 66%|██████▋   | 246817/371472 [8:35:57<9:45:47,  3.55it/s]
 66%|██████▋   | 246818/371472 [8:35:57<9:19:07,  3.72it/s]
 66%|██████▋   | 246819/371472 [8:35:58<10:03:30,  3.44it/s]
 66%|██████▋   | 246820/371472 [8:35:58<9:26:58,  3.66it/s] 
                                                           
{'loss': 2.7414, 'learning_rate': 4.021687603697559e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246820/371472 [8:35:58<9:26:58,  3.66it/s]
 66%|██████▋   | 246821/371472 [8:35:58<9:22:03,  3.70it/s]
 66%|██████▋   | 246822/371472 [8:35:58<9:22:45,  3.69it/s]
 66%|██████▋   | 246823/371472 [8:35:59<9:40:47,  3.58it/s]
 66%|██████▋   | 246824/371472 [8:35:59<9:29:30,  3.65it/s]
 66%|██████▋   | 246825/371472 [8:35:59<9:21:49,  3.70it/s]
 66%|██████▋   | 246826/371472 [8:35:59<9:17:46,  3.72it/s]
 66%|██████▋   | 246827/371472 [8:36:00<8:57:24,  3.87it/s]
 66%|██████▋   | 246828/371472 [8:36:00<8:50:40,  3.91it/s]
 66%|██████▋   | 246829/371472 [8:36:00<9:15:44,  3.74it/s]
 66%|██████▋   | 246830/371472 [8:36:00<9:04:16,  3.82it/s]
 66%|██████▋   | 246831/371472 [8:36:01<9:11:17,  3.77it/s]
 66%|██████▋   | 246832/371472 [8:36:01<9:42:58,  3.56it/s]
 66%|██████▋   | 246833/371472 [8:36:01<9:41:54,  3.57it/s]
 66%|██████▋   | 246834/371472 [8:36:02<9:33:53,  3.62it/s]
 66%|██████▋   | 246835/371472 [8:36:02<9:30:47,  3.64it/s]
 66%|██████▋   | 246836/371472 [8:36:02<9:50:42,  3.52it/s]
 66%|██████▋   | 246837/371472 [8:36:02<9:36:04,  3.61it/s]
 66%|██████▋   | 246838/371472 [8:36:03<9:31:55,  3.63it/s]
 66%|██████▋   | 246839/371472 [8:36:03<9:29:57,  3.64it/s]
 66%|██████▋   | 246840/371472 [8:36:03<9:20:08,  3.71it/s]
                                                           
{'loss': 2.8153, 'learning_rate': 4.0212027839427696e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246840/371472 [8:36:03<9:20:08,  3.71it/s]
 66%|██████▋   | 246841/371472 [8:36:04<9:40:46,  3.58it/s]
 66%|██████▋   | 246842/371472 [8:36:04<9:45:07,  3.55it/s]
 66%|██████▋   | 246843/371472 [8:36:04<9:19:42,  3.71it/s]
 66%|██████▋   | 246844/371472 [8:36:04<9:25:00,  3.68it/s]
 66%|██████▋   | 246845/371472 [8:36:05<9:26:57,  3.66it/s]
 66%|██████▋   | 246846/371472 [8:36:05<9:52:03,  3.51it/s]
 66%|██████▋   | 246847/371472 [8:36:05<9:43:42,  3.56it/s]
 66%|██████▋   | 246848/371472 [8:36:05<9:30:01,  3.64it/s]
 66%|██████▋   | 246849/371472 [8:36:06<9:47:08,  3.54it/s]
 66%|██████▋   | 246850/371472 [8:36:06<10:15:54,  3.37it/s]
 66%|██████▋   | 246851/371472 [8:36:06<10:00:23,  3.46it/s]
 66%|██████▋   | 246852/371472 [8:36:07<9:44:47,  3.55it/s] 
 66%|██████▋   | 246853/371472 [8:36:07<10:09:14,  3.41it/s]
 66%|██████▋   | 246854/371472 [8:36:07<10:37:42,  3.26it/s]
 66%|██████▋   | 246855/371472 [8:36:08<10:38:40,  3.25it/s]
 66%|██████▋   | 246856/371472 [8:36:08<10:07:29,  3.42it/s]
 66%|██████▋   | 246857/371472 [8:36:08<9:40:28,  3.58it/s] 
 66%|██████▋   | 246858/371472 [8:36:08<9:23:10,  3.69it/s]
 66%|██████▋   | 246859/371472 [8:36:09<9:54:07,  3.50it/s]
 66%|██████▋   | 246860/371472 [8:36:09<9:54:32,  3.49it/s]
                                                           
{'loss': 2.8522, 'learning_rate': 4.020717964187981e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246860/371472 [8:36:09<9:54:32,  3.49it/s]
 66%|██████▋   | 246861/371472 [8:36:09<9:32:39,  3.63it/s]
 66%|██████▋   | 246862/371472 [8:36:10<9:40:17,  3.58it/s]
 66%|██████▋   | 246863/371472 [8:36:10<9:45:28,  3.55it/s]
 66%|██████▋   | 246864/371472 [8:36:10<9:21:35,  3.70it/s]
 66%|██████▋   | 246865/371472 [8:36:10<9:11:11,  3.77it/s]
 66%|██████▋   | 246866/371472 [8:36:11<8:47:36,  3.94it/s]
 66%|██████▋   | 246867/371472 [8:36:11<9:06:03,  3.80it/s]
 66%|██████▋   | 246868/371472 [8:36:11<9:05:57,  3.80it/s]
 66%|██████▋   | 246869/371472 [8:36:11<8:59:06,  3.85it/s]
 66%|██████▋   | 246870/371472 [8:36:12<9:56:32,  3.48it/s]
 66%|██████▋   | 246871/371472 [8:36:12<9:50:53,  3.51it/s]
 66%|██████▋   | 246872/371472 [8:36:12<9:43:36,  3.56it/s]
 66%|██████▋   | 246873/371472 [8:36:13<9:26:22,  3.67it/s]
 66%|██████▋   | 246874/371472 [8:36:13<9:10:06,  3.77it/s]
 66%|██████▋   | 246875/371472 [8:36:13<9:25:09,  3.67it/s]
 66%|██████▋   | 246876/371472 [8:36:13<9:15:00,  3.74it/s]
 66%|██████▋   | 246877/371472 [8:36:14<9:13:43,  3.75it/s]
 66%|██████▋   | 246878/371472 [8:36:14<9:46:47,  3.54it/s]
 66%|██████▋   | 246879/371472 [8:36:14<9:41:51,  3.57it/s]
 66%|██████▋   | 246880/371472 [8:36:14<9:43:36,  3.56it/s]
                                                           
{'loss': 2.8492, 'learning_rate': 4.0202331444331915e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246880/371472 [8:36:14<9:43:36,  3.56it/s]
 66%|██████▋   | 246881/371472 [8:36:15<9:45:49,  3.54it/s]
 66%|██████▋   | 246882/371472 [8:36:15<9:59:48,  3.46it/s]
 66%|██████▋   | 246883/371472 [8:36:15<9:31:08,  3.64it/s]
 66%|██████▋   | 246884/371472 [8:36:16<9:22:39,  3.69it/s]
 66%|██████▋   | 246885/371472 [8:36:16<9:22:14,  3.69it/s]
 66%|██████▋   | 246886/371472 [8:36:16<9:23:15,  3.69it/s]
 66%|██████▋   | 246887/371472 [8:36:16<9:25:46,  3.67it/s]
 66%|██████▋   | 246888/371472 [8:36:17<10:12:37,  3.39it/s]
 66%|██████▋   | 246889/371472 [8:36:17<9:51:43,  3.51it/s] 
 66%|██████▋   | 246890/371472 [8:36:17<10:39:25,  3.25it/s]
 66%|██████▋   | 246891/371472 [8:36:18<10:34:05,  3.27it/s]
 66%|██████▋   | 246892/371472 [8:36:18<9:59:47,  3.46it/s] 
 66%|██████▋   | 246893/371472 [8:36:18<10:39:16,  3.25it/s]
 66%|██████▋   | 246894/371472 [8:36:18<10:11:51,  3.39it/s]
 66%|██████▋   | 246895/371472 [8:36:19<9:53:40,  3.50it/s] 
 66%|██████▋   | 246896/371472 [8:36:19<9:57:46,  3.47it/s]
 66%|██████▋   | 246897/371472 [8:36:19<9:47:15,  3.54it/s]
 66%|██████▋   | 246898/371472 [8:36:20<9:39:29,  3.58it/s]
 66%|██████▋   | 246899/371472 [8:36:20<9:19:01,  3.71it/s]
 66%|██████▋   | 246900/371472 [8:36:20<9:36:37,  3.60it/s]
                                                           
{'loss': 2.8646, 'learning_rate': 4.0197483246784033e-07, 'epoch': 10.63}
+
 66%|██████▋   | 246900/371472 [8:36:20<9:36:37,  3.60it/s]
 66%|██████▋   | 246901/371472 [8:36:20<9:45:32,  3.55it/s]
 66%|██████▋   | 246902/371472 [8:36:21<9:39:50,  3.58it/s]
 66%|██████▋   | 246903/371472 [8:36:21<10:26:52,  3.31it/s]
 66%|██████▋   | 246904/371472 [8:36:21<10:09:40,  3.41it/s]
 66%|██████▋   | 246905/371472 [8:36:22<9:59:09,  3.47it/s] 
 66%|██████▋   | 246906/371472 [8:36:22<9:56:42,  3.48it/s]
 66%|██████▋   | 246907/371472 [8:36:22<10:01:09,  3.45it/s]
 66%|██████▋   | 246908/371472 [8:36:22<10:00:14,  3.46it/s]
 66%|██████▋   | 246909/371472 [8:36:23<9:35:34,  3.61it/s] 
 66%|██████▋   | 246910/371472 [8:36:23<10:02:48,  3.44it/s]
 66%|██████▋   | 246911/371472 [8:36:23<10:14:17,  3.38it/s]
 66%|██████▋   | 246912/371472 [8:36:24<9:53:32,  3.50it/s] 
 66%|██████▋   | 246913/371472 [8:36:24<9:30:23,  3.64it/s]
 66%|██████▋   | 246914/371472 [8:36:24<9:20:59,  3.70it/s]
 66%|██████▋   | 246915/371472 [8:36:24<8:58:41,  3.85it/s]
 66%|██████▋   | 246916/371472 [8:36:25<9:40:20,  3.58it/s]
 66%|██████▋   | 246917/371472 [8:36:25<9:43:38,  3.56it/s]
 66%|██████▋   | 246918/371472 [8:36:25<9:45:17,  3.55it/s]
 66%|██████▋   | 246919/371472 [8:36:26<9:34:05,  3.62it/s]
 66%|██████▋   | 246920/371472 [8:36:26<9:23:34,  3.68it/s]
                                                           
{'loss': 2.8443, 'learning_rate': 4.019263504923614e-07, 'epoch': 10.64}
+
 66%|██████▋   | 246920/371472 [8:36:26<9:23:34,  3.68it/s]
 66%|██████▋   | 246921/371472 [8:36:26<9:01:36,  3.83it/s]
 66%|██████▋   | 246922/371472 [8:36:26<9:18:24,  3.72it/s]
 66%|██████▋   | 246923/371472 [8:36:27<9:17:31,  3.72it/s]
 66%|██████▋   | 246924/371472 [8:36:27<9:36:03,  3.60it/s]
 66%|██████▋   | 246925/371472 [8:36:27<9:31:44,  3.63it/s]
 66%|██████▋   | 246926/371472 [8:36:27<9:33:42,  3.62it/s]
 66%|██████▋   | 246927/371472 [8:36:28<9:26:39,  3.66it/s]
 66%|██████▋   | 246928/371472 [8:36:28<9:14:44,  3.74it/s]
 66%|██████▋   | 246929/371472 [8:36:28<9:41:12,  3.57it/s]
 66%|██████▋   | 246930/371472 [8:36:29<10:37:08,  3.26it/s]
 66%|██████▋   | 246931/371472 [8:36:29<10:20:47,  3.34it/s]
 66%|██████▋   | 246932/371472 [8:36:29<10:08:54,  3.41it/s]
 66%|██████▋   | 246933/371472 [8:36:29<9:48:17,  3.53it/s] 
 66%|██████▋   | 246934/371472 [8:36:30<9:28:40,  3.65it/s]
 66%|██████▋   | 246935/371472 [8:36:30<9:23:37,  3.68it/s]
 66%|██████▋   | 246936/371472 [8:36:30<9:21:56,  3.69it/s]
 66%|██████▋   | 246937/371472 [8:36:31<9:46:45,  3.54it/s]
 66%|██████▋   | 246938/371472 [8:36:31<9:48:25,  3.53it/s]
 66%|██████▋   | 246939/371472 [8:36:31<9:29:54,  3.64it/s]
 66%|██████▋   | 246940/371472 [8:36:31<9:56:20,  3.48it/s]
                                                           
{'loss': 2.934, 'learning_rate': 4.018778685168824e-07, 'epoch': 10.64}
+
 66%|██████▋   | 246940/371472 [8:36:31<9:56:20,  3.48it/s]
 66%|██████▋   | 246941/371472 [8:36:32<11:33:25,  2.99it/s]
 66%|██████▋   | 246942/371472 [8:36:32<10:48:58,  3.20it/s]
 66%|██████▋   | 246943/371472 [8:36:32<10:12:24,  3.39it/s]
 66%|██████▋   | 246944/371472 [8:36:33<10:07:43,  3.42it/s]
 66%|██████▋   | 246945/371472 [8:36:33<9:46:33,  3.54it/s] 
 66%|██████▋   | 246946/371472 [8:36:33<9:47:31,  3.53it/s]
 66%|██████▋   | 246947/371472 [8:36:33<9:46:54,  3.54it/s]
 66%|██████▋   | 246948/371472 [8:36:34<10:03:09,  3.44it/s]
 66%|██████▋   | 246949/371472 [8:36:34<10:13:27,  3.38it/s]
 66%|██████▋   | 246950/371472 [8:36:34<9:40:18,  3.58it/s] 
 66%|██████▋   | 246951/371472 [8:36:35<9:43:28,  3.56it/s]
 66%|██████▋   | 246952/371472 [8:36:35<9:44:25,  3.55it/s]
 66%|██████▋   | 246953/371472 [8:36:35<10:51:45,  3.18it/s]
 66%|██████▋   | 246954/371472 [8:36:36<10:28:05,  3.30it/s]
 66%|██████▋   | 246955/371472 [8:36:36<10:26:21,  3.31it/s]
 66%|██████▋   | 246956/371472 [8:36:36<10:13:53,  3.38it/s]
 66%|██████▋   | 246957/371472 [8:36:36<10:49:36,  3.19it/s]
 66%|██████▋   | 246958/371472 [8:36:37<10:25:26,  3.32it/s]
 66%|██████▋   | 246959/371472 [8:36:37<9:56:22,  3.48it/s] 
 66%|██████▋   | 246960/371472 [8:36:37<9:40:01,  3.58it/s]
                                                           
{'loss': 2.8241, 'learning_rate': 4.018293865414036e-07, 'epoch': 10.64}
+
 66%|██████▋   | 246960/371472 [8:36:37<9:40:01,  3.58it/s]
 66%|██████▋   | 246961/371472 [8:36:38<10:01:32,  3.45it/s]
 66%|██████▋   | 246962/371472 [8:36:38<10:04:01,  3.44it/s]
 66%|██████▋   | 246963/371472 [8:36:38<9:40:49,  3.57it/s] 
 66%|██████▋   | 246964/371472 [8:36:38<9:32:16,  3.63it/s]
 66%|██████▋   | 246965/371472 [8:36:39<12:24:19,  2.79it/s]
 66%|██████▋   | 246966/371472 [8:36:39<11:31:20,  3.00it/s]
 66%|██████▋   | 246967/371472 [8:36:40<11:00:33,  3.14it/s]
 66%|██████▋   | 246968/371472 [8:36:40<10:17:39,  3.36it/s]
 66%|██████▋   | 246969/371472 [8:36:40<10:08:27,  3.41it/s]
 66%|██████▋   | 246970/371472 [8:36:40<9:59:46,  3.46it/s] 
 66%|██████▋   | 246971/371472 [8:36:41<9:53:10,  3.50it/s]
 66%|██████▋   | 246972/371472 [8:36:41<10:00:13,  3.46it/s]
 66%|██████▋   | 246973/371472 [8:36:41<9:56:00,  3.48it/s] 
 66%|██████▋   | 246974/371472 [8:36:41<9:32:47,  3.62it/s]
 66%|██████▋   | 246975/371472 [8:36:42<9:50:04,  3.52it/s]
 66%|██████▋   | 246976/371472 [8:36:42<9:21:48,  3.69it/s]
 66%|██████▋   | 246977/371472 [8:36:42<9:09:06,  3.78it/s]
 66%|██████▋   | 246978/371472 [8:36:43<9:23:01,  3.69it/s]
 66%|██████▋   | 246979/371472 [8:36:43<9:52:01,  3.50it/s]
 66%|██████▋   | 246980/371472 [8:36:43<9:59:12,  3.46it/s]
                                                           
{'loss': 2.8886, 'learning_rate': 4.0178090456592467e-07, 'epoch': 10.64}
+
 66%|██████▋   | 246980/371472 [8:36:43<9:59:12,  3.46it/s]
 66%|██████▋   | 246981/371472 [8:36:43<9:48:55,  3.52it/s]
 66%|██████▋   | 246982/371472 [8:36:44<9:22:52,  3.69it/s]
 66%|██████▋   | 246983/371472 [8:36:44<9:50:54,  3.51it/s]
 66%|██████▋   | 246984/371472 [8:36:44<9:34:05,  3.61it/s]
 66%|██████▋   | 246985/371472 [8:36:44<9:26:28,  3.66it/s]
 66%|██████▋   | 246986/371472 [8:36:45<9:20:49,  3.70it/s]
 66%|██████▋   | 246987/371472 [8:36:45<11:18:01,  3.06it/s]
 66%|██████▋   | 246988/371472 [8:36:45<10:59:57,  3.14it/s]
 66%|██████▋   | 246989/371472 [8:36:46<10:55:38,  3.16it/s]
 66%|██████▋   | 246990/371472 [8:36:46<11:18:11,  3.06it/s]
 66%|██████▋   | 246991/371472 [8:36:46<11:10:40,  3.09it/s]
 66%|██████▋   | 246992/371472 [8:36:47<10:28:22,  3.30it/s]
 66%|██████▋   | 246993/371472 [8:36:47<10:23:16,  3.33it/s]
 66%|██████▋   | 246994/371472 [8:36:47<10:23:19,  3.33it/s]
 66%|██████▋   | 246995/371472 [8:36:48<10:12:47,  3.39it/s]
 66%|██████▋   | 246996/371472 [8:36:48<9:50:34,  3.51it/s] 
 66%|██████▋   | 246997/371472 [8:36:48<10:02:40,  3.44it/s]
 66%|██████▋   | 246998/371472 [8:36:48<9:41:56,  3.56it/s] 
 66%|██████▋   | 246999/371472 [8:36:49<9:24:11,  3.68it/s]
 66%|██████▋   | 247000/371472 [8:36:49<9:08:10,  3.78it/s]
                                                           
{'loss': 2.7455, 'learning_rate': 4.0173242259044584e-07, 'epoch': 10.64}
+
 66%|██████▋   | 247000/371472 [8:36:49<9:08:10,  3.78it/s]
 66%|██████▋   | 247001/371472 [8:36:49<9:30:23,  3.64it/s]
 66%|██████▋   | 247002/371472 [8:36:50<9:50:33,  3.51it/s]
 66%|██████▋   | 247003/371472 [8:36:50<9:52:29,  3.50it/s]
 66%|██████▋   | 247004/371472 [8:36:50<10:12:39,  3.39it/s]
 66%|██████▋   | 247005/371472 [8:36:50<9:47:23,  3.53it/s] 
 66%|██████▋   | 247006/371472 [8:36:51<9:50:59,  3.51it/s]
 66%|██████▋   | 247007/371472 [8:36:51<9:44:32,  3.55it/s]
 66%|██████▋   | 247008/371472 [8:36:51<9:43:18,  3.56it/s]
 66%|██████▋   | 247009/371472 [8:36:51<9:18:00,  3.72it/s]
 66%|██████▋   | 247010/371472 [8:36:52<9:32:55,  3.62it/s]
 66%|██████▋   | 247011/371472 [8:36:52<9:10:41,  3.77it/s]
 66%|██████▋   | 247012/371472 [8:36:52<8:59:59,  3.84it/s]
 66%|██████▋   | 247013/371472 [8:36:53<9:20:02,  3.70it/s]
 66%|██████▋   | 247014/371472 [8:36:53<9:50:20,  3.51it/s]
 66%|██████▋   | 247015/371472 [8:36:53<9:21:43,  3.69it/s]
 66%|██████▋   | 247016/371472 [8:36:53<9:27:27,  3.66it/s]
 66%|██████▋   | 247017/371472 [8:36:54<9:15:54,  3.73it/s]
 66%|██████▋   | 247018/371472 [8:36:54<9:46:17,  3.54it/s]
 66%|██████▋   | 247019/371472 [8:36:54<9:19:37,  3.71it/s]
 66%|██████▋   | 247020/371472 [8:36:54<9:18:32,  3.71it/s]
                                                           
{'loss': 2.9546, 'learning_rate': 4.0168394061496686e-07, 'epoch': 10.64}
+
 66%|██████▋   | 247020/371472 [8:36:54<9:18:32,  3.71it/s]
 66%|██████▋   | 247021/371472 [8:36:55<9:18:46,  3.71it/s]
 66%|██████▋   | 247022/371472 [8:36:55<9:05:22,  3.80it/s]
 66%|██████▋   | 247023/371472 [8:36:55<9:30:00,  3.64it/s]
 66%|██████▋   | 247024/371472 [8:36:56<9:21:06,  3.70it/s]
 66%|██████▋   | 247025/371472 [8:36:56<10:03:32,  3.44it/s]
 66%|██████▋   | 247026/371472 [8:36:56<10:04:01,  3.43it/s]
 66%|██████▋   | 247027/371472 [8:36:56<9:40:41,  3.57it/s] 
 66%|██████▋   | 247028/371472 [8:36:57<9:42:28,  3.56it/s]
 67%|██████▋   | 247029/371472 [8:36:57<9:23:54,  3.68it/s]
 67%|██████▋   | 247030/371472 [8:36:57<9:16:08,  3.73it/s]
 67%|██████▋   | 247031/371472 [8:36:58<9:47:21,  3.53it/s]
 67%|██████▋   | 247032/371472 [8:36:58<9:46:54,  3.53it/s]
 67%|██████▋   | 247033/371472 [8:36:58<9:52:02,  3.50it/s]
 67%|██████▋   | 247034/371472 [8:36:58<9:43:19,  3.56it/s]
 67%|██████▋   | 247035/371472 [8:36:59<9:38:31,  3.58it/s]
 67%|██████▋   | 247036/371472 [8:36:59<9:08:35,  3.78it/s]
 67%|██████▋   | 247037/371472 [8:36:59<9:40:01,  3.58it/s]
 67%|██████▋   | 247038/371472 [8:36:59<9:09:23,  3.77it/s]
 67%|██████▋   | 247039/371472 [8:37:00<9:10:24,  3.77it/s]
 67%|██████▋   | 247040/371472 [8:37:00<8:56:26,  3.87it/s]
                                                           
{'loss': 2.6874, 'learning_rate': 4.0163545863948804e-07, 'epoch': 10.64}
+
 67%|██████▋   | 247040/371472 [8:37:00<8:56:26,  3.87it/s]
 67%|██████▋   | 247041/371472 [8:37:00<8:58:30,  3.85it/s]
 67%|██████▋   | 247042/371472 [8:37:01<9:13:52,  3.74it/s]
 67%|██████▋   | 247043/371472 [8:37:01<9:15:18,  3.73it/s]
 67%|██████▋   | 247044/371472 [8:37:01<9:00:11,  3.84it/s]
 67%|██████▋   | 247045/371472 [8:37:01<8:58:19,  3.85it/s]
 67%|██████▋   | 247046/371472 [8:37:02<9:00:00,  3.84it/s]
 67%|██████▋   | 247047/371472 [8:37:02<8:42:30,  3.97it/s]
 67%|██████▋   | 247048/371472 [8:37:02<8:49:13,  3.92it/s]
 67%|██████▋   | 247049/371472 [8:37:02<8:49:47,  3.91it/s]
 67%|██████▋   | 247050/371472 [8:37:03<9:19:03,  3.71it/s]
 67%|██████▋   | 247051/371472 [8:37:03<9:33:22,  3.62it/s]
 67%|██████▋   | 247052/371472 [8:37:03<9:24:49,  3.67it/s]
 67%|██████▋   | 247053/371472 [8:37:03<9:07:57,  3.78it/s]
 67%|██████▋   | 247054/371472 [8:37:04<8:52:03,  3.90it/s]
 67%|██████▋   | 247055/371472 [8:37:04<8:37:07,  4.01it/s]
 67%|██████▋   | 247056/371472 [8:37:04<8:35:06,  4.03it/s]
 67%|██████▋   | 247057/371472 [8:37:04<8:22:08,  4.13it/s]
 67%|██████▋   | 247058/371472 [8:37:05<8:48:19,  3.92it/s]
 67%|██████▋   | 247059/371472 [8:37:05<9:01:50,  3.83it/s]
 67%|██████▋   | 247060/371472 [8:37:05<9:45:33,  3.54it/s]
                                                           
{'loss': 2.9298, 'learning_rate': 4.0158697666400906e-07, 'epoch': 10.64}
+
 67%|██████▋   | 247060/371472 [8:37:05<9:45:33,  3.54it/s]
 67%|██████▋   | 247061/371472 [8:37:06<9:43:44,  3.55it/s]
 67%|██████▋   | 247062/371472 [8:37:06<9:38:01,  3.59it/s]
 67%|██████▋   | 247063/371472 [8:37:06<9:39:21,  3.58it/s]
 67%|██████▋   | 247064/371472 [8:37:06<9:41:32,  3.57it/s]
 67%|██████▋   | 247065/371472 [8:37:07<9:57:55,  3.47it/s]
 67%|██████▋   | 247066/371472 [8:37:07<9:53:44,  3.49it/s]
 67%|██████▋   | 247067/371472 [8:37:07<9:29:28,  3.64it/s]
 67%|██████▋   | 247068/371472 [8:37:07<9:26:12,  3.66it/s]
 67%|██████▋   | 247069/371472 [8:37:08<9:22:03,  3.69it/s]
 67%|██████▋   | 247070/371472 [8:37:08<9:35:23,  3.60it/s]
 67%|██████▋   | 247071/371472 [8:37:08<9:32:06,  3.62it/s]
 67%|██████▋   | 247072/371472 [8:37:09<9:24:28,  3.67it/s]
 67%|██████▋   | 247073/371472 [8:37:09<9:30:10,  3.64it/s]
 67%|██████▋   | 247074/371472 [8:37:09<9:46:31,  3.53it/s]
 67%|██████▋   | 247075/371472 [8:37:09<10:14:02,  3.38it/s]
 67%|██████▋   | 247076/371472 [8:37:10<9:56:15,  3.48it/s] 
 67%|██████▋   | 247077/371472 [8:37:10<10:35:31,  3.26it/s]
 67%|██████▋   | 247078/371472 [8:37:10<10:13:44,  3.38it/s]
 67%|██████▋   | 247079/371472 [8:37:11<9:57:12,  3.47it/s] 
 67%|██████▋   | 247080/371472 [8:37:11<9:45:14,  3.54it/s]
                                                           
{'loss': 2.8487, 'learning_rate': 4.0153849468853024e-07, 'epoch': 10.64}
+
 67%|██████▋   | 247080/371472 [8:37:11<9:45:14,  3.54it/s]
 67%|██████▋   | 247081/371472 [8:37:11<9:49:39,  3.52it/s]
 67%|██████▋   | 247082/371472 [8:37:12<10:37:00,  3.25it/s]
 67%|██████▋   | 247083/371472 [8:37:12<10:39:01,  3.24it/s]
 67%|██████▋   | 247084/371472 [8:37:12<10:14:49,  3.37it/s]
 67%|██████▋   | 247085/371472 [8:37:12<10:43:04,  3.22it/s]
 67%|██████▋   | 247086/371472 [8:37:13<10:18:46,  3.35it/s]
 67%|██████▋   | 247087/371472 [8:37:13<10:26:56,  3.31it/s]
 67%|██████▋   | 247088/371472 [8:37:13<10:38:58,  3.24it/s]
 67%|██████▋   | 247089/371472 [8:37:14<10:02:51,  3.44it/s]
 67%|██████▋   | 247090/371472 [8:37:14<9:39:37,  3.58it/s] 
 67%|██████▋   | 247091/371472 [8:37:14<9:37:57,  3.59it/s]
 67%|██████▋   | 247092/371472 [8:37:14<9:30:40,  3.63it/s]
 67%|██████▋   | 247093/371472 [8:37:15<9:47:40,  3.53it/s]
 67%|██████▋   | 247094/371472 [8:37:15<9:49:33,  3.52it/s]
 67%|██████▋   | 247095/371472 [8:37:15<9:52:13,  3.50it/s]
 67%|██████▋   | 247096/371472 [8:37:16<11:02:44,  3.13it/s]
 67%|██████▋   | 247097/371472 [8:37:16<10:55:14,  3.16it/s]
 67%|██████▋   | 247098/371472 [8:37:16<11:20:58,  3.04it/s]
 67%|██████▋   | 247099/371472 [8:37:17<10:32:21,  3.28it/s]
 67%|██████▋   | 247100/371472 [8:37:17<10:48:25,  3.20it/s]
                                                            
{'loss': 2.8698, 'learning_rate': 4.014900127130513e-07, 'epoch': 10.64}
+
 67%|██████▋   | 247100/371472 [8:37:17<10:48:25,  3.20it/s]
 67%|██████▋   | 247101/371472 [8:37:17<10:41:20,  3.23it/s]
 67%|██████▋   | 247102/371472 [8:37:18<11:32:43,  2.99it/s]
 67%|██████▋   | 247103/371472 [8:37:18<11:04:41,  3.12it/s]
 67%|██████▋   | 247104/371472 [8:37:18<11:33:27,  2.99it/s]
 67%|██████▋   | 247105/371472 [8:37:19<11:11:43,  3.09it/s]
 67%|██████▋   | 247106/371472 [8:37:19<11:13:49,  3.08it/s]
 67%|██████▋   | 247107/371472 [8:37:19<10:17:48,  3.35it/s]
 67%|██████▋   | 247108/371472 [8:37:19<10:01:43,  3.44it/s]
 67%|██████▋   | 247109/371472 [8:37:20<10:14:14,  3.37it/s]
 67%|██████▋   | 247110/371472 [8:37:20<10:09:16,  3.40it/s]
 67%|██████▋   | 247111/371472 [8:37:20<9:35:01,  3.60it/s] 
 67%|██████▋   | 247112/371472 [8:37:21<10:22:24,  3.33it/s]
 67%|██████▋   | 247113/371472 [8:37:21<11:23:00,  3.03it/s]
 67%|██████▋   | 247114/371472 [8:37:21<10:44:12,  3.22it/s]
 67%|██████▋   | 247115/371472 [8:37:21<9:53:08,  3.49it/s] 
 67%|██████▋   | 247116/371472 [8:37:22<9:26:23,  3.66it/s]
 67%|██████▋   | 247117/371472 [8:37:22<9:13:30,  3.74it/s]
 67%|██████▋   | 247118/371472 [8:37:22<9:13:15,  3.75it/s]
 67%|██████▋   | 247119/371472 [8:37:23<9:32:50,  3.62it/s]
 67%|██████▋   | 247120/371472 [8:37:23<10:13:45,  3.38it/s]
                                                            
{'loss': 2.9566, 'learning_rate': 4.0144153073757243e-07, 'epoch': 10.64}
+
 67%|██████▋   | 247120/371472 [8:37:23<10:13:45,  3.38it/s]
 67%|██████▋   | 247121/371472 [8:37:23<10:44:33,  3.22it/s]
 67%|██████▋   | 247122/371472 [8:37:24<10:31:57,  3.28it/s]
 67%|██████▋   | 247123/371472 [8:37:24<9:51:28,  3.50it/s] 
 67%|██████▋   | 247124/371472 [8:37:24<9:20:11,  3.70it/s]
 67%|██████▋   | 247125/371472 [8:37:24<9:51:52,  3.50it/s]
 67%|██████▋   | 247126/371472 [8:37:25<9:55:30,  3.48it/s]
 67%|██████▋   | 247127/371472 [8:37:25<9:44:16,  3.55it/s]
 67%|██████▋   | 247128/371472 [8:37:25<9:17:49,  3.72it/s]
 67%|██████▋   | 247129/371472 [8:37:25<9:02:54,  3.82it/s]
 67%|██████▋   | 247130/371472 [8:37:26<9:25:21,  3.67it/s]
 67%|██████▋   | 247131/371472 [8:37:26<9:08:07,  3.78it/s]
 67%|██████▋   | 247132/371472 [8:37:26<9:20:12,  3.70it/s]
 67%|██████▋   | 247133/371472 [8:37:26<9:27:33,  3.65it/s]
 67%|██████▋   | 247134/371472 [8:37:27<9:06:32,  3.79it/s]
 67%|██████▋   | 247135/371472 [8:37:27<9:32:49,  3.62it/s]
 67%|██████▋   | 247136/371472 [8:37:27<9:28:16,  3.65it/s]
 67%|██████▋   | 247137/371472 [8:37:28<9:25:24,  3.67it/s]
 67%|██████▋   | 247138/371472 [8:37:28<9:25:03,  3.67it/s]
 67%|██████▋   | 247139/371472 [8:37:28<9:17:44,  3.72it/s]
 67%|██████▋   | 247140/371472 [8:37:28<9:09:08,  3.77it/s]
                                                           
{'loss': 3.0913, 'learning_rate': 4.013930487620935e-07, 'epoch': 10.64}
+
 67%|██████▋   | 247140/371472 [8:37:28<9:09:08,  3.77it/s]
 67%|██████▋   | 247141/371472 [8:37:29<9:16:23,  3.72it/s]
 67%|██████▋   | 247142/371472 [8:37:29<10:15:35,  3.37it/s]
 67%|██████▋   | 247143/371472 [8:37:29<10:03:27,  3.43it/s]
 67%|██████▋   | 247144/371472 [8:37:30<9:52:12,  3.50it/s] 
 67%|██████▋   | 247145/371472 [8:37:30<9:56:02,  3.48it/s]
 67%|██████▋   | 247146/371472 [8:37:30<9:38:51,  3.58it/s]
 67%|██████▋   | 247147/371472 [8:37:30<9:15:53,  3.73it/s]
 67%|██████▋   | 247148/371472 [8:37:31<9:33:22,  3.61it/s]
 67%|██████▋   | 247149/371472 [8:37:31<9:23:17,  3.68it/s]
 67%|██████▋   | 247150/371472 [8:37:31<9:28:09,  3.65it/s]
 67%|██████▋   | 247151/371472 [8:37:31<9:09:28,  3.77it/s]
 67%|██████▋   | 247152/371472 [8:37:32<8:58:41,  3.85it/s]
 67%|██████▋   | 247153/371472 [8:37:32<9:16:42,  3.72it/s]
 67%|██████▋   | 247154/371472 [8:37:32<9:44:56,  3.54it/s]
 67%|██████▋   | 247155/371472 [8:37:33<10:11:22,  3.39it/s]
 67%|██████▋   | 247156/371472 [8:37:33<10:23:45,  3.32it/s]
 67%|██████▋   | 247157/371472 [8:37:33<9:57:20,  3.47it/s] 
 67%|██████▋   | 247158/371472 [8:37:33<9:32:53,  3.62it/s]
 67%|██████▋   | 247159/371472 [8:37:34<9:17:33,  3.72it/s]
 67%|██████▋   | 247160/371472 [8:37:34<9:19:22,  3.70it/s]
                                                           
{'loss': 2.9348, 'learning_rate': 4.013445667866147e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247160/371472 [8:37:34<9:19:22,  3.70it/s]
 67%|██████▋   | 247161/371472 [8:37:34<9:12:43,  3.75it/s]
 67%|██████▋   | 247162/371472 [8:37:34<9:10:05,  3.77it/s]
 67%|██████▋   | 247163/371472 [8:37:35<9:06:57,  3.79it/s]
 67%|██████▋   | 247164/371472 [8:37:35<9:18:46,  3.71it/s]
 67%|██████▋   | 247165/371472 [8:37:35<9:03:53,  3.81it/s]
 67%|██████▋   | 247166/371472 [8:37:36<8:58:35,  3.85it/s]
 67%|██████▋   | 247167/371472 [8:37:36<9:03:56,  3.81it/s]
 67%|██████▋   | 247168/371472 [8:37:36<9:04:50,  3.80it/s]
 67%|██████▋   | 247169/371472 [8:37:36<9:27:05,  3.65it/s]
 67%|██████▋   | 247170/371472 [8:37:37<9:24:56,  3.67it/s]
 67%|██████▋   | 247171/371472 [8:37:37<9:54:30,  3.48it/s]
 67%|██████▋   | 247172/371472 [8:37:37<9:41:23,  3.56it/s]
 67%|██████▋   | 247173/371472 [8:37:37<9:30:38,  3.63it/s]
 67%|██████▋   | 247174/371472 [8:37:38<9:34:06,  3.61it/s]
 67%|██████▋   | 247175/371472 [8:37:38<10:37:05,  3.25it/s]
 67%|██████▋   | 247176/371472 [8:37:38<10:25:08,  3.31it/s]
 67%|██████▋   | 247177/371472 [8:37:39<10:14:45,  3.37it/s]
 67%|██████▋   | 247178/371472 [8:37:39<9:41:59,  3.56it/s] 
 67%|██████▋   | 247179/371472 [8:37:39<11:30:37,  3.00it/s]
 67%|██████▋   | 247180/371472 [8:37:40<10:45:37,  3.21it/s]
                                                            
{'loss': 2.7678, 'learning_rate': 4.0129608481113575e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247180/371472 [8:37:40<10:45:37,  3.21it/s]
 67%|██████▋   | 247181/371472 [8:37:40<10:25:11,  3.31it/s]
 67%|██████▋   | 247182/371472 [8:37:40<10:06:03,  3.42it/s]
 67%|██████▋   | 247183/371472 [8:37:40<9:49:26,  3.51it/s] 
 67%|██████▋   | 247184/371472 [8:37:41<9:29:24,  3.64it/s]
 67%|██████▋   | 247185/371472 [8:37:41<9:22:30,  3.68it/s]
 67%|██████▋   | 247186/371472 [8:37:41<9:31:44,  3.62it/s]
 67%|██████▋   | 247187/371472 [8:37:42<9:25:24,  3.66it/s]
 67%|██████▋   | 247188/371472 [8:37:42<9:28:31,  3.64it/s]
 67%|██████▋   | 247189/371472 [8:37:42<9:33:06,  3.61it/s]
 67%|██████▋   | 247190/371472 [8:37:42<10:02:50,  3.44it/s]
 67%|██████▋   | 247191/371472 [8:37:43<9:33:16,  3.61it/s] 
 67%|██████▋   | 247192/371472 [8:37:43<9:28:00,  3.65it/s]
 67%|██████▋   | 247193/371472 [8:37:43<9:28:12,  3.65it/s]
 67%|██████▋   | 247194/371472 [8:37:44<9:40:07,  3.57it/s]
 67%|██████▋   | 247195/371472 [8:37:44<10:23:22,  3.32it/s]
 67%|██████▋   | 247196/371472 [8:37:44<9:50:04,  3.51it/s] 
 67%|██████▋   | 247197/371472 [8:37:44<9:40:00,  3.57it/s]
 67%|██████▋   | 247198/371472 [8:37:45<9:48:38,  3.52it/s]
 67%|██████▋   | 247199/371472 [8:37:45<9:56:15,  3.47it/s]
 67%|██████▋   | 247200/371472 [8:37:45<9:42:17,  3.56it/s]
                                                           
{'loss': 2.8038, 'learning_rate': 4.012476028356569e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247200/371472 [8:37:45<9:42:17,  3.56it/s]
 67%|██████▋   | 247201/371472 [8:37:46<9:42:50,  3.55it/s]
 67%|██████▋   | 247202/371472 [8:37:46<9:40:54,  3.57it/s]
 67%|██████▋   | 247203/371472 [8:37:46<10:06:30,  3.41it/s]
 67%|██████▋   | 247204/371472 [8:37:46<10:32:57,  3.27it/s]
 67%|██████▋   | 247205/371472 [8:37:47<11:00:45,  3.13it/s]
 67%|██████▋   | 247206/371472 [8:37:47<10:45:15,  3.21it/s]
 67%|██████▋   | 247207/371472 [8:37:47<10:01:12,  3.44it/s]
 67%|██████▋   | 247208/371472 [8:37:48<9:40:36,  3.57it/s] 
 67%|██████▋   | 247209/371472 [8:37:48<9:27:16,  3.65it/s]
 67%|██████▋   | 247210/371472 [8:37:48<9:23:08,  3.68it/s]
 67%|██████▋   | 247211/371472 [8:37:48<9:57:30,  3.47it/s]
 67%|██████▋   | 247212/371472 [8:37:49<9:26:13,  3.66it/s]
 67%|██████▋   | 247213/371472 [8:37:49<9:23:54,  3.67it/s]
 67%|██████▋   | 247214/371472 [8:37:49<9:49:49,  3.51it/s]
 67%|██████▋   | 247215/371472 [8:37:50<9:51:33,  3.50it/s]
 67%|██████▋   | 247216/371472 [8:37:50<9:52:33,  3.49it/s]
 67%|██████▋   | 247217/371472 [8:37:50<10:13:55,  3.37it/s]
 67%|██████▋   | 247218/371472 [8:37:50<9:55:26,  3.48it/s] 
 67%|██████▋   | 247219/371472 [8:37:51<9:40:16,  3.57it/s]
 67%|██████▋   | 247220/371472 [8:37:51<9:41:21,  3.56it/s]
                                                           
{'loss': 2.7365, 'learning_rate': 4.0119912086017795e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247220/371472 [8:37:51<9:41:21,  3.56it/s]
 67%|██████▋   | 247221/371472 [8:37:51<9:36:30,  3.59it/s]
 67%|██████▋   | 247222/371472 [8:37:52<9:24:04,  3.67it/s]
 67%|██████▋   | 247223/371472 [8:37:52<9:46:31,  3.53it/s]
 67%|██████▋   | 247224/371472 [8:37:52<9:30:58,  3.63it/s]
 67%|██████▋   | 247225/371472 [8:37:52<9:10:45,  3.76it/s]
 67%|██████▋   | 247226/371472 [8:37:53<9:09:46,  3.77it/s]
 67%|██████▋   | 247227/371472 [8:37:53<9:37:16,  3.59it/s]
 67%|██████▋   | 247228/371472 [8:37:53<9:41:25,  3.56it/s]
 67%|██████▋   | 247229/371472 [8:37:54<10:28:59,  3.29it/s]
 67%|██████▋   | 247230/371472 [8:37:54<10:13:25,  3.38it/s]
 67%|██████▋   | 247231/371472 [8:37:54<9:51:33,  3.50it/s] 
 67%|██████▋   | 247232/371472 [8:37:54<10:21:01,  3.33it/s]
 67%|██████▋   | 247233/371472 [8:37:55<9:37:24,  3.59it/s] 
 67%|██████▋   | 247234/371472 [8:37:55<9:42:39,  3.55it/s]
 67%|██████▋   | 247235/371472 [8:37:55<9:55:00,  3.48it/s]
 67%|██████▋   | 247236/371472 [8:37:55<9:46:30,  3.53it/s]
 67%|██████▋   | 247237/371472 [8:37:56<9:25:59,  3.66it/s]
 67%|██████▋   | 247238/371472 [8:37:56<10:31:40,  3.28it/s]
 67%|██████▋   | 247239/371472 [8:37:56<10:18:31,  3.35it/s]
 67%|███��██▋   | 247240/371472 [8:37:57<10:10:39,  3.39it/s]
                                                            
{'loss': 2.92, 'learning_rate': 4.0115063888469907e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247240/371472 [8:37:57<10:10:39,  3.39it/s]
 67%|██████▋   | 247241/371472 [8:37:57<10:13:14,  3.38it/s]
 67%|██████▋   | 247242/371472 [8:37:57<10:00:41,  3.45it/s]
 67%|██████▋   | 247243/371472 [8:37:58<9:46:03,  3.53it/s] 
 67%|██████▋   | 247244/371472 [8:37:58<9:49:48,  3.51it/s]
 67%|██████▋   | 247245/371472 [8:37:58<9:44:31,  3.54it/s]
 67%|██████▋   | 247246/371472 [8:37:58<9:35:08,  3.60it/s]
 67%|██████▋   | 247247/371472 [8:37:59<9:04:14,  3.80it/s]
 67%|██████▋   | 247248/371472 [8:37:59<8:55:39,  3.87it/s]
 67%|██████▋   | 247249/371472 [8:37:59<9:03:55,  3.81it/s]
 67%|██████▋   | 247250/371472 [8:37:59<9:10:36,  3.76it/s]
 67%|██████▋   | 247251/371472 [8:38:00<9:14:13,  3.74it/s]
 67%|██████▋   | 247252/371472 [8:38:00<9:53:37,  3.49it/s]
 67%|██████▋   | 247253/371472 [8:38:00<10:11:58,  3.38it/s]
 67%|██████▋   | 247254/371472 [8:38:01<9:51:36,  3.50it/s] 
 67%|██████▋   | 247255/371472 [8:38:01<9:38:46,  3.58it/s]
 67%|██████▋   | 247256/371472 [8:38:01<9:20:55,  3.69it/s]
 67%|██████▋   | 247257/371472 [8:38:01<9:11:06,  3.76it/s]
 67%|██████▋   | 247258/371472 [8:38:02<9:59:28,  3.45it/s]
 67%|██████▋   | 247259/371472 [8:38:02<9:39:28,  3.57it/s]
 67%|██████▋   | 247260/371472 [8:38:02<9:50:13,  3.51it/s]
                                                           
{'loss': 2.8063, 'learning_rate': 4.0110215690922014e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247260/371472 [8:38:02<9:50:13,  3.51it/s]
 67%|██████▋   | 247261/371472 [8:38:03<9:38:15,  3.58it/s]
 67%|██████▋   | 247262/371472 [8:38:03<9:30:59,  3.63it/s]
 67%|██████▋   | 247263/371472 [8:38:03<9:05:44,  3.79it/s]
 67%|██████▋   | 247264/371472 [8:38:03<9:02:48,  3.81it/s]
 67%|██████▋   | 247265/371472 [8:38:04<9:09:54,  3.76it/s]
 67%|██████▋   | 247266/371472 [8:38:04<9:05:25,  3.80it/s]
 67%|██████▋   | 247267/371472 [8:38:04<8:51:11,  3.90it/s]
 67%|██████▋   | 247268/371472 [8:38:04<8:46:44,  3.93it/s]
 67%|██████▋   | 247269/371472 [8:38:05<9:30:52,  3.63it/s]
 67%|██████▋   | 247270/371472 [8:38:05<9:20:55,  3.69it/s]
 67%|██████▋   | 247271/371472 [8:38:05<9:30:14,  3.63it/s]
 67%|██████▋   | 247272/371472 [8:38:05<9:18:56,  3.70it/s]
 67%|██████▋   | 247273/371472 [8:38:06<9:31:51,  3.62it/s]
 67%|██████▋   | 247274/371472 [8:38:06<9:58:42,  3.46it/s]
 67%|██████▋   | 247275/371472 [8:38:06<9:34:43,  3.60it/s]
 67%|██████▋   | 247276/371472 [8:38:07<10:01:34,  3.44it/s]
 67%|██████▋   | 247277/371472 [8:38:07<9:51:08,  3.50it/s] 
 67%|██████▋   | 247278/371472 [8:38:07<9:36:47,  3.59it/s]
 67%|██████▋   | 247279/371472 [8:38:08<10:54:44,  3.16it/s]
 67%|██████▋   | 247280/371472 [8:38:08<10:15:14,  3.36it/s]
                                                            
{'loss': 2.8152, 'learning_rate': 4.010536749337413e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247280/371472 [8:38:08<10:15:14,  3.36it/s]
 67%|██████▋   | 247281/371472 [8:38:08<10:29:19,  3.29it/s]
 67%|██████▋   | 247282/371472 [8:38:08<10:05:11,  3.42it/s]
 67%|██████▋   | 247283/371472 [8:38:09<9:36:16,  3.59it/s] 
 67%|██████▋   | 247284/371472 [8:38:09<9:30:00,  3.63it/s]
 67%|██████▋   | 247285/371472 [8:38:09<9:31:26,  3.62it/s]
 67%|██████▋   | 247286/371472 [8:38:09<9:33:08,  3.61it/s]
 67%|██████▋   | 247287/371472 [8:38:10<9:14:10,  3.73it/s]
 67%|██████▋   | 247288/371472 [8:38:10<8:53:27,  3.88it/s]
 67%|██████▋   | 247289/371472 [8:38:10<9:41:18,  3.56it/s]
 67%|██████▋   | 247290/371472 [8:38:11<9:59:57,  3.45it/s]
 67%|██████▋   | 247291/371472 [8:38:11<10:08:04,  3.40it/s]
 67%|██████▋   | 247292/371472 [8:38:11<9:52:43,  3.49it/s] 
 67%|██████▋   | 247293/371472 [8:38:12<10:39:28,  3.24it/s]
 67%|██████▋   | 247294/371472 [8:38:12<10:13:18,  3.37it/s]
 67%|██████▋   | 247295/371472 [8:38:12<10:14:14,  3.37it/s]
 67%|██████▋   | 247296/371472 [8:38:12<9:37:08,  3.59it/s] 
 67%|██████▋   | 247297/371472 [8:38:13<9:39:41,  3.57it/s]
 67%|██████▋   | 247298/371472 [8:38:13<10:10:13,  3.39it/s]
 67%|██████▋   | 247299/371472 [8:38:13<10:29:13,  3.29it/s]
 67%|██████▋   | 247300/371472 [8:38:14<10:11:09,  3.39it/s]
                                                            
{'loss': 2.8482, 'learning_rate': 4.010051929582624e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247300/371472 [8:38:14<10:11:09,  3.39it/s]
 67%|██████▋   | 247301/371472 [8:38:14<9:43:46,  3.55it/s] 
 67%|██████▋   | 247302/371472 [8:38:14<9:55:55,  3.47it/s]
 67%|██████▋   | 247303/371472 [8:38:14<9:35:23,  3.60it/s]
 67%|██████▋   | 247304/371472 [8:38:15<9:26:26,  3.65it/s]
 67%|██████▋   | 247305/371472 [8:38:15<10:15:46,  3.36it/s]
 67%|██████▋   | 247306/371472 [8:38:15<9:52:29,  3.49it/s] 
 67%|██████▋   | 247307/371472 [8:38:15<9:31:42,  3.62it/s]
 67%|██████▋   | 247308/371472 [8:38:16<9:56:21,  3.47it/s]
 67%|██████▋   | 247309/371472 [8:38:16<9:20:38,  3.69it/s]
 67%|██████▋   | 247310/371472 [8:38:16<9:18:24,  3.71it/s]
 67%|██████▋   | 247311/371472 [8:38:17<9:08:22,  3.77it/s]
 67%|██████▋   | 247312/371472 [8:38:17<9:49:06,  3.51it/s]
 67%|██████▋   | 247313/371472 [8:38:17<9:24:38,  3.66it/s]
 67%|██████▋   | 247314/371472 [8:38:17<9:13:46,  3.74it/s]
 67%|██████▋   | 247315/371472 [8:38:18<9:33:07,  3.61it/s]
 67%|██████▋   | 247316/371472 [8:38:18<9:08:28,  3.77it/s]
 67%|██████▋   | 247317/371472 [8:38:18<9:05:31,  3.79it/s]
 67%|██████▋   | 247318/371472 [8:38:18<9:15:29,  3.72it/s]
 67%|██████▋   | 247319/371472 [8:38:19<9:55:18,  3.48it/s]
 67%|██████▋   | 247320/371472 [8:38:19<9:30:58,  3.62it/s]
                                                           
{'loss': 2.7132, 'learning_rate': 4.009567109827835e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247320/371472 [8:38:19<9:30:58,  3.62it/s]
 67%|██████▋   | 247321/371472 [8:38:19<9:59:46,  3.45it/s]
 67%|██████▋   | 247322/371472 [8:38:20<9:46:12,  3.53it/s]
 67%|██████▋   | 247323/371472 [8:38:20<9:49:46,  3.51it/s]
 67%|██████▋   | 247324/371472 [8:38:20<9:39:55,  3.57it/s]
 67%|██████▋   | 247325/371472 [8:38:20<9:20:34,  3.69it/s]
 67%|██████▋   | 247326/371472 [8:38:21<10:31:27,  3.28it/s]
 67%|██████▋   | 247327/371472 [8:38:21<10:36:49,  3.25it/s]
 67%|██████▋   | 247328/371472 [8:38:21<10:02:13,  3.44it/s]
 67%|██████▋   | 247329/371472 [8:38:22<10:43:35,  3.21it/s]
 67%|██████▋   | 247330/371472 [8:38:22<10:50:14,  3.18it/s]
 67%|██████▋   | 247331/371472 [8:38:22<11:00:41,  3.13it/s]
 67%|██████▋   | 247332/371472 [8:38:23<10:47:12,  3.20it/s]
 67%|██████▋   | 247333/371472 [8:38:23<10:26:48,  3.30it/s]
 67%|██████▋   | 247334/371472 [8:38:23<9:59:38,  3.45it/s] 
 67%|██████▋   | 247335/371472 [8:38:23<9:38:43,  3.58it/s]
 67%|██████▋   | 247336/371472 [8:38:24<9:34:14,  3.60it/s]
 67%|██████▋   | 247337/371472 [8:38:24<9:19:30,  3.70it/s]
 67%|██████▋   | 247338/371472 [8:38:24<9:25:20,  3.66it/s]
 67%|██████▋   | 247339/371472 [8:38:25<10:07:47,  3.40it/s]
 67%|██████▋   | 247340/371472 [8:38:25<9:50:07,  3.51it/s] 
                                                           
{'loss': 2.7281, 'learning_rate': 4.009082290073046e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247340/371472 [8:38:25<9:50:07,  3.51it/s]
 67%|██████▋   | 247341/371472 [8:38:25<10:06:33,  3.41it/s]
 67%|██████▋   | 247342/371472 [8:38:25<9:56:52,  3.47it/s] 
 67%|██████▋   | 247343/371472 [8:38:26<9:46:08,  3.53it/s]
 67%|██████▋   | 247344/371472 [8:38:26<9:34:52,  3.60it/s]
 67%|██████▋   | 247345/371472 [8:38:26<9:28:06,  3.64it/s]
 67%|██████▋   | 247346/371472 [8:38:27<9:26:33,  3.65it/s]
 67%|██████▋   | 247347/371472 [8:38:27<9:38:14,  3.58it/s]
 67%|██████▋   | 247348/371472 [8:38:27<9:30:45,  3.62it/s]
 67%|██████▋   | 247349/371472 [8:38:27<9:18:27,  3.70it/s]
 67%|██████▋   | 247350/371472 [8:38:28<9:17:06,  3.71it/s]
 67%|██████▋   | 247351/371472 [8:38:28<9:18:54,  3.70it/s]
 67%|██████▋   | 247352/371472 [8:38:28<9:05:29,  3.79it/s]
 67%|██████▋   | 247353/371472 [8:38:28<9:26:52,  3.65it/s]
 67%|██████▋   | 247354/371472 [8:38:29<9:11:43,  3.75it/s]
 67%|██████▋   | 247355/371472 [8:38:29<9:02:05,  3.82it/s]
 67%|██████▋   | 247356/371472 [8:38:29<9:13:59,  3.73it/s]
 67%|██████▋   | 247357/371472 [8:38:30<9:14:18,  3.73it/s]
 67%|██████▋   | 247358/371472 [8:38:30<9:30:48,  3.62it/s]
 67%|██████▋   | 247359/371472 [8:38:30<9:10:41,  3.76it/s]
 67%|██████▋   | 247360/371472 [8:38:30<9:17:59,  3.71it/s]
                                                           
{'loss': 3.0214, 'learning_rate': 4.0085974703182577e-07, 'epoch': 10.65}
+
 67%|██████▋   | 247360/371472 [8:38:30<9:17:59,  3.71it/s]
 67%|██████▋   | 247361/371472 [8:38:31<9:20:48,  3.69it/s]
 67%|██████▋   | 247362/371472 [8:38:31<9:42:05,  3.55it/s]
 67%|██████▋   | 247363/371472 [8:38:31<9:21:55,  3.68it/s]
 67%|██████▋   | 247364/371472 [8:38:31<9:43:51,  3.54it/s]
 67%|██████▋   | 247365/371472 [8:38:32<9:38:42,  3.57it/s]
 67%|██████▋   | 247366/371472 [8:38:32<9:16:09,  3.72it/s]
 67%|██████▋   | 247367/371472 [8:38:32<9:29:02,  3.63it/s]
 67%|██████▋   | 247368/371472 [8:38:33<9:28:29,  3.64it/s]
 67%|██████▋   | 247369/371472 [8:38:33<9:19:30,  3.70it/s]
 67%|██████▋   | 247370/371472 [8:38:33<9:05:34,  3.79it/s]
 67%|██████▋   | 247371/371472 [8:38:33<9:33:32,  3.61it/s]
 67%|██████▋   | 247372/371472 [8:38:34<9:49:55,  3.51it/s]
 67%|██████▋   | 247373/371472 [8:38:34<9:45:50,  3.53it/s]
 67%|██████▋   | 247374/371472 [8:38:34<9:41:43,  3.56it/s]
 67%|██████▋   | 247375/371472 [8:38:34<9:18:52,  3.70it/s]
 67%|██████▋   | 247376/371472 [8:38:35<9:12:16,  3.74it/s]
 67%|██████▋   | 247377/371472 [8:38:35<9:08:35,  3.77it/s]
 67%|██████▋   | 247378/371472 [8:38:35<8:57:40,  3.85it/s]
 67%|██████▋   | 247379/371472 [8:38:36<9:29:06,  3.63it/s]
 67%|██████▋   | 247380/371472 [8:38:36<9:29:47,  3.63it/s]
                                                           
{'loss': 2.8932, 'learning_rate': 4.008112650563468e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247380/371472 [8:38:36<9:29:47,  3.63it/s]
 67%|██████▋   | 247381/371472 [8:38:36<9:14:52,  3.73it/s]
 67%|██████▋   | 247382/371472 [8:38:36<9:13:50,  3.73it/s]
 67%|██████▋   | 247383/371472 [8:38:37<9:15:05,  3.73it/s]
 67%|██████▋   | 247384/371472 [8:38:37<9:28:28,  3.64it/s]
 67%|██████▋   | 247385/371472 [8:38:37<9:26:25,  3.65it/s]
 67%|██████▋   | 247386/371472 [8:38:37<10:05:10,  3.42it/s]
 67%|██████▋   | 247387/371472 [8:38:38<10:07:21,  3.41it/s]
 67%|██████▋   | 247388/371472 [8:38:38<10:03:39,  3.43it/s]
 67%|██████▋   | 247389/371472 [8:38:38<9:31:16,  3.62it/s] 
 67%|██████▋   | 247390/371472 [8:38:39<9:43:31,  3.54it/s]
 67%|██████▋   | 247391/371472 [8:38:39<9:20:41,  3.69it/s]
 67%|██████▋   | 247392/371472 [8:38:39<9:15:16,  3.72it/s]
 67%|██████▋   | 247393/371472 [8:38:39<9:13:24,  3.74it/s]
 67%|██████▋   | 247394/371472 [8:38:40<9:44:30,  3.54it/s]
 67%|██████▋   | 247395/371472 [8:38:40<9:22:25,  3.68it/s]
 67%|██████▋   | 247396/371472 [8:38:40<10:01:53,  3.44it/s]
 67%|██████▋   | 247397/371472 [8:38:41<10:22:25,  3.32it/s]
 67%|██████▋   | 247398/371472 [8:38:41<10:13:45,  3.37it/s]
 67%|██████▋   | 247399/371472 [8:38:41<9:44:32,  3.54it/s] 
 67%|██████▋   | 247400/371472 [8:38:42<10:37:58,  3.24it/s]
                                                            
{'loss': 2.8742, 'learning_rate': 4.0076278308086796e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247400/371472 [8:38:42<10:37:58,  3.24it/s]
 67%|██████▋   | 247401/371472 [8:38:42<10:14:04,  3.37it/s]
 67%|██████▋   | 247402/371472 [8:38:42<10:11:43,  3.38it/s]
 67%|██████▋   | 247403/371472 [8:38:42<10:35:48,  3.25it/s]
 67%|██████▋   | 247404/371472 [8:38:43<10:13:32,  3.37it/s]
 67%|██████▋   | 247405/371472 [8:38:43<9:52:06,  3.49it/s] 
 67%|██████▋   | 247406/371472 [8:38:43<10:27:40,  3.29it/s]
 67%|██████▋   | 247407/371472 [8:38:44<10:50:05,  3.18it/s]
 67%|██████▋   | 247408/371472 [8:38:44<9:58:45,  3.45it/s] 
 67%|██████▋   | 247409/371472 [8:38:44<9:29:05,  3.63it/s]
 67%|██████▋   | 247410/371472 [8:38:44<9:42:59,  3.55it/s]
 67%|██████▋   | 247411/371472 [8:38:45<9:50:15,  3.50it/s]
 67%|██████▋   | 247412/371472 [8:38:45<9:29:22,  3.63it/s]
 67%|██████▋   | 247413/371472 [8:38:45<9:09:42,  3.76it/s]
 67%|██████▋   | 247414/371472 [8:38:46<10:03:43,  3.42it/s]
 67%|██████▋   | 247415/371472 [8:38:46<10:39:35,  3.23it/s]
 67%|██████▋   | 247416/371472 [8:38:46<10:15:57,  3.36it/s]
 67%|██████▋   | 247417/371472 [8:38:47<10:38:55,  3.24it/s]
 67%|██████▋   | 247418/371472 [8:38:47<10:14:55,  3.36it/s]
 67%|██████▋   | 247419/371472 [8:38:47<9:39:40,  3.57it/s] 
 67%|██████▋   | 247420/371472 [8:38:47<9:16:44,  3.71it/s]
                                                           
{'loss': 2.9043, 'learning_rate': 4.00714301105389e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247420/371472 [8:38:47<9:16:44,  3.71it/s]
 67%|██████▋   | 247421/371472 [8:38:48<10:20:48,  3.33it/s]
 67%|██████▋   | 247422/371472 [8:38:48<9:41:00,  3.56it/s] 
 67%|██████▋   | 247423/371472 [8:38:48<9:40:11,  3.56it/s]
 67%|██████▋   | 247424/371472 [8:38:48<9:37:02,  3.58it/s]
 67%|██████▋   | 247425/371472 [8:38:49<9:28:05,  3.64it/s]
 67%|██████▋   | 247426/371472 [8:38:49<9:55:51,  3.47it/s]
 67%|██████▋   | 247427/371472 [8:38:49<9:37:01,  3.58it/s]
 67%|██████▋   | 247428/371472 [8:38:50<9:51:11,  3.50it/s]
 67%|██████▋   | 247429/371472 [8:38:50<9:36:30,  3.59it/s]
 67%|██████▋   | 247430/371472 [8:38:50<10:08:01,  3.40it/s]
 67%|██████▋   | 247431/371472 [8:38:50<9:44:09,  3.54it/s] 
 67%|██████▋   | 247432/371472 [8:38:51<10:04:44,  3.42it/s]
 67%|██████▋   | 247433/371472 [8:38:51<10:15:57,  3.36it/s]
 67%|██████▋   | 247434/371472 [8:38:51<11:13:17,  3.07it/s]
 67%|██████▋   | 247435/371472 [8:38:52<10:26:04,  3.30it/s]
 67%|██████▋   | 247436/371472 [8:38:52<10:26:26,  3.30it/s]
 67%|██████▋   | 247437/371472 [8:38:52<10:03:37,  3.42it/s]
 67%|██████▋   | 247438/371472 [8:38:53<11:04:17,  3.11it/s]
 67%|██████▋   | 247439/371472 [8:38:53<11:23:16,  3.03it/s]
 67%|██████▋   | 247440/371472 [8:38:53<10:51:12,  3.17it/s]
                                                            
{'loss': 2.7501, 'learning_rate': 4.0066581912991016e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247440/371472 [8:38:53<10:51:12,  3.17it/s]
 67%|██████▋   | 247441/371472 [8:38:54<10:20:59,  3.33it/s]
 67%|██████▋   | 247442/371472 [8:38:54<9:49:09,  3.51it/s] 
 67%|██████▋   | 247443/371472 [8:38:54<10:55:49,  3.15it/s]
 67%|██████▋   | 247444/371472 [8:38:54<10:34:45,  3.26it/s]
 67%|██████▋   | 247445/371472 [8:38:55<10:05:07,  3.42it/s]
 67%|██████▋   | 247446/371472 [8:38:55<9:52:54,  3.49it/s] 
 67%|██████▋   | 247447/371472 [8:38:55<9:50:46,  3.50it/s]
 67%|██████▋   | 247448/371472 [8:38:56<9:29:12,  3.63it/s]
 67%|██████▋   | 247449/371472 [8:38:56<9:05:11,  3.79it/s]
 67%|██████▋   | 247450/371472 [8:38:56<9:23:24,  3.67it/s]
 67%|██████▋   | 247451/371472 [8:38:56<9:49:05,  3.51it/s]
 67%|██████▋   | 247452/371472 [8:38:57<9:22:48,  3.67it/s]
 67%|██████▋   | 247453/371472 [8:38:57<9:16:01,  3.72it/s]
 67%|██████▋   | 247454/371472 [8:38:57<9:06:16,  3.78it/s]
 67%|██████▋   | 247455/371472 [8:38:57<9:25:31,  3.65it/s]
 67%|██████▋   | 247456/371472 [8:38:58<9:05:58,  3.79it/s]
 67%|██████▋   | 247457/371472 [8:38:58<9:12:31,  3.74it/s]
 67%|██████▋   | 247458/371472 [8:38:58<9:07:23,  3.78it/s]
 67%|██████▋   | 247459/371472 [8:38:58<8:59:29,  3.83it/s]
 67%|██████▋   | 247460/371472 [8:38:59<8:49:55,  3.90it/s]
                                                           
{'loss': 2.9613, 'learning_rate': 4.0061733715443123e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247460/371472 [8:38:59<8:49:55,  3.90it/s]
 67%|██████▋   | 247461/371472 [8:38:59<9:06:32,  3.78it/s]
 67%|██████▋   | 247462/371472 [8:38:59<8:52:12,  3.88it/s]
 67%|██████▋   | 247463/371472 [8:38:59<8:56:29,  3.85it/s]
 67%|██████▋   | 247464/371472 [8:39:00<8:52:02,  3.88it/s]
 67%|██████▋   | 247465/371472 [8:39:00<8:45:45,  3.93it/s]
 67%|██████▋   | 247466/371472 [8:39:00<8:54:27,  3.87it/s]
 67%|██████▋   | 247467/371472 [8:39:01<8:58:45,  3.84it/s]
 67%|██████▋   | 247468/371472 [8:39:01<9:03:15,  3.80it/s]
 67%|██████▋   | 247469/371472 [8:39:01<9:25:41,  3.65it/s]
 67%|██████▋   | 247470/371472 [8:39:01<9:06:23,  3.78it/s]
 67%|██████▋   | 247471/371472 [8:39:02<9:16:35,  3.71it/s]
 67%|██████▋   | 247472/371472 [8:39:02<9:05:01,  3.79it/s]
 67%|██████▋   | 247473/371472 [8:39:02<9:25:03,  3.66it/s]
 67%|██████▋   | 247474/371472 [8:39:02<9:09:17,  3.76it/s]
 67%|██████▋   | 247475/371472 [8:39:03<9:21:56,  3.68it/s]
 67%|██████▋   | 247476/371472 [8:39:03<9:04:11,  3.80it/s]
 67%|██████▋   | 247477/371472 [8:39:03<9:05:53,  3.79it/s]
 67%|██████▋   | 247478/371472 [8:39:03<9:07:32,  3.77it/s]
 67%|██████▋   | 247479/371472 [8:39:04<9:49:43,  3.50it/s]
 67%|██████▋   | 247480/371472 [8:39:04<10:08:50,  3.39it/s]
                                                            
{'loss': 2.7262, 'learning_rate': 4.005688551789523e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247480/371472 [8:39:04<10:08:50,  3.39it/s]
 67%|██████▋   | 247481/371472 [8:39:04<9:37:51,  3.58it/s] 
 67%|██████▋   | 247482/371472 [8:39:05<10:03:45,  3.42it/s]
 67%|██████▋   | 247483/371472 [8:39:05<9:35:00,  3.59it/s] 
 67%|██████▋   | 247484/371472 [8:39:05<9:26:19,  3.65it/s]
 67%|██████▋   | 247485/371472 [8:39:06<9:48:33,  3.51it/s]
 67%|██████▋   | 247486/371472 [8:39:06<10:00:38,  3.44it/s]
 67%|██████▋   | 247487/371472 [8:39:06<10:09:42,  3.39it/s]
 67%|██████▋   | 247488/371472 [8:39:06<10:13:22,  3.37it/s]
 67%|██████▋   | 247489/371472 [8:39:07<10:10:29,  3.38it/s]
 67%|██████▋   | 247490/371472 [8:39:07<9:53:46,  3.48it/s] 
 67%|██████▋   | 247491/371472 [8:39:07<9:53:45,  3.48it/s]
 67%|██████▋   | 247492/371472 [8:39:08<10:17:55,  3.34it/s]
 67%|██████▋   | 247493/371472 [8:39:08<9:54:48,  3.47it/s] 
 67%|██████▋   | 247494/371472 [8:39:08<10:11:54,  3.38it/s]
 67%|██████▋   | 247495/371472 [8:39:08<9:32:51,  3.61it/s] 
 67%|██████▋   | 247496/371472 [8:39:09<9:16:02,  3.72it/s]
 67%|██████▋   | 247497/371472 [8:39:09<9:21:27,  3.68it/s]
 67%|██████▋   | 247498/371472 [8:39:09<9:12:20,  3.74it/s]
 67%|██████▋   | 247499/371472 [8:39:09<8:46:27,  3.92it/s]
 67%|██████▋   | 247500/371472 [8:39:10<9:02:48,  3.81it/s]
                                                           
{'loss': 2.8231, 'learning_rate': 4.005203732034734e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247500/371472 [8:39:10<9:02:48,  3.81it/s]
 67%|██████▋   | 247501/371472 [8:39:10<9:26:17,  3.65it/s]
 67%|██████▋   | 247502/371472 [8:39:10<9:37:23,  3.58it/s]
 67%|██████▋   | 247503/371472 [8:39:11<9:42:01,  3.55it/s]
 67%|██████▋   | 247504/371472 [8:39:11<9:55:20,  3.47it/s]
 67%|██████▋   | 247505/371472 [8:39:11<9:47:39,  3.52it/s]
 67%|██████▋   | 247506/371472 [8:39:11<9:37:28,  3.58it/s]
 67%|██████▋   | 247507/371472 [8:39:12<9:19:43,  3.69it/s]
 67%|██████▋   | 247508/371472 [8:39:12<9:19:35,  3.69it/s]
 67%|██████▋   | 247509/371472 [8:39:12<9:13:56,  3.73it/s]
 67%|██████▋   | 247510/371472 [8:39:12<8:58:18,  3.84it/s]
 67%|██████▋   | 247511/371472 [8:39:13<9:12:23,  3.74it/s]
 67%|██████▋   | 247512/371472 [8:39:13<9:33:51,  3.60it/s]
 67%|██████▋   | 247513/371472 [8:39:13<9:36:52,  3.58it/s]
 67%|██████▋   | 247514/371472 [8:39:14<9:38:56,  3.57it/s]
 67%|██████▋   | 247515/371472 [8:39:14<9:36:32,  3.58it/s]
 67%|██████▋   | 247516/371472 [8:39:14<9:07:52,  3.77it/s]
 67%|██████▋   | 247517/371472 [8:39:14<9:28:09,  3.64it/s]
 67%|██████▋   | 247518/371472 [8:39:15<9:24:38,  3.66it/s]
 67%|██████▋   | 247519/371472 [8:39:15<9:12:59,  3.74it/s]
 67%|██████▋   | 247520/371472 [8:39:15<9:26:47,  3.64it/s]
                                                           
{'loss': 2.881, 'learning_rate': 4.004718912279945e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247520/371472 [8:39:15<9:26:47,  3.64it/s]
 67%|██████▋   | 247521/371472 [8:39:16<9:46:46,  3.52it/s]
 67%|██████▋   | 247522/371472 [8:39:16<9:42:43,  3.55it/s]
 67%|██████▋   | 247523/371472 [8:39:16<9:27:21,  3.64it/s]
 67%|██████▋   | 247524/371472 [8:39:16<10:28:14,  3.29it/s]
 67%|██████▋   | 247525/371472 [8:39:17<10:14:32,  3.36it/s]
 67%|██████▋   | 247526/371472 [8:39:17<10:59:54,  3.13it/s]
 67%|██████▋   | 247527/371472 [8:39:17<10:29:15,  3.28it/s]
 67%|██████▋   | 247528/371472 [8:39:18<10:15:31,  3.36it/s]
 67%|██████▋   | 247529/371472 [8:39:18<10:33:30,  3.26it/s]
 67%|██████▋   | 247530/371472 [8:39:18<10:07:23,  3.40it/s]
 67%|██████▋   | 247531/371472 [8:39:19<10:06:10,  3.41it/s]
 67%|██████▋   | 247532/371472 [8:39:19<9:42:44,  3.54it/s] 
 67%|██████▋   | 247533/371472 [8:39:19<9:30:53,  3.62it/s]
 67%|██████▋   | 247534/371472 [8:39:19<10:03:23,  3.42it/s]
 67%|██████▋   | 247535/371472 [8:39:20<9:56:03,  3.47it/s] 
 67%|██████▋   | 247536/371472 [8:39:20<9:37:43,  3.58it/s]
 67%|██████▋   | 247537/371472 [8:39:20<9:32:12,  3.61it/s]
 67%|██████▋   | 247538/371472 [8:39:21<11:41:04,  2.95it/s]
 67%|██████▋   | 247539/371472 [8:39:21<10:42:14,  3.22it/s]
 67%|██████▋   | 247540/371472 [8:39:21<10:12:45,  3.37it/s]
                                                            
{'loss': 2.8154, 'learning_rate': 4.004234092525157e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247540/371472 [8:39:21<10:12:45,  3.37it/s]
 67%|██████▋   | 247541/371472 [8:39:21<10:00:16,  3.44it/s]
 67%|██████▋   | 247542/371472 [8:39:22<9:43:29,  3.54it/s] 
 67%|██████▋   | 247543/371472 [8:39:22<9:40:46,  3.56it/s]
 67%|██████▋   | 247544/371472 [8:39:22<9:44:29,  3.53it/s]
 67%|██████▋   | 247545/371472 [8:39:23<9:35:45,  3.59it/s]
 67%|██████▋   | 247546/371472 [8:39:23<10:45:14,  3.20it/s]
 67%|██████▋   | 247547/371472 [8:39:23<10:31:55,  3.27it/s]
 67%|██████▋   | 247548/371472 [8:39:23<10:00:54,  3.44it/s]
 67%|██████▋   | 247549/371472 [8:39:24<9:59:21,  3.45it/s] 
 67%|██████▋   | 247550/371472 [8:39:24<9:43:56,  3.54it/s]
 67%|██████▋   | 247551/371472 [8:39:24<10:41:44,  3.22it/s]
 67%|██████▋   | 247552/371472 [8:39:25<11:22:00,  3.03it/s]
 67%|██████▋   | 247553/371472 [8:39:25<10:50:10,  3.18it/s]
 67%|██████▋   | 247554/371472 [8:39:25<10:27:57,  3.29it/s]
 67%|██████▋   | 247555/371472 [8:39:26<10:40:13,  3.23it/s]
 67%|██████▋   | 247556/371472 [8:39:26<10:03:55,  3.42it/s]
 67%|██████▋   | 247557/371472 [8:39:26<9:36:12,  3.58it/s] 
 67%|██████▋   | 247558/371472 [8:39:27<10:12:30,  3.37it/s]
 67%|██████▋   | 247559/371472 [8:39:27<10:22:06,  3.32it/s]
 67%|██████▋   | 247560/371472 [8:39:27<9:45:41,  3.53it/s] 
                                                           
{'loss': 2.8377, 'learning_rate': 4.0037492727703675e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247560/371472 [8:39:27<9:45:41,  3.53it/s]
 67%|██████▋   | 247561/371472 [8:39:27<11:18:29,  3.04it/s]
 67%|██████▋   | 247562/371472 [8:39:28<11:06:39,  3.10it/s]
 67%|██████▋   | 247563/371472 [8:39:28<10:50:22,  3.18it/s]
 67%|██████▋   | 247564/371472 [8:39:28<10:21:55,  3.32it/s]
 67%|██████▋   | 247565/371472 [8:39:29<9:59:50,  3.44it/s] 
 67%|██████▋   | 247566/371472 [8:39:29<9:40:07,  3.56it/s]
 67%|██████▋   | 247567/371472 [8:39:29<9:21:23,  3.68it/s]
 67%|██████▋   | 247568/371472 [8:39:29<9:15:13,  3.72it/s]
 67%|██████▋   | 247569/371472 [8:39:30<9:20:32,  3.68it/s]
 67%|██████▋   | 247570/371472 [8:39:30<9:15:46,  3.72it/s]
 67%|██████▋   | 247571/371472 [8:39:30<9:14:13,  3.73it/s]
 67%|██████▋   | 247572/371472 [8:39:30<9:26:32,  3.64it/s]
 67%|██████▋   | 247573/371472 [8:39:31<9:26:13,  3.65it/s]
 67%|██████▋   | 247574/371472 [8:39:31<9:06:46,  3.78it/s]
 67%|██████▋   | 247575/371472 [8:39:31<9:08:08,  3.77it/s]
 67%|██████▋   | 247576/371472 [8:39:32<9:08:08,  3.77it/s]
 67%|██████▋   | 247577/371472 [8:39:32<8:57:45,  3.84it/s]
 67%|██████▋   | 247578/371472 [8:39:32<9:05:48,  3.78it/s]
 67%|██████▋   | 247579/371472 [8:39:32<9:49:52,  3.50it/s]
 67%|██████▋   | 247580/371472 [8:39:33<9:45:06,  3.53it/s]
                                                           
{'loss': 3.0109, 'learning_rate': 4.0032644530155787e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247580/371472 [8:39:33<9:45:06,  3.53it/s]
 67%|██████▋   | 247581/371472 [8:39:33<9:48:39,  3.51it/s]
 67%|██████▋   | 247582/371472 [8:39:33<9:40:16,  3.56it/s]
 67%|██████▋   | 247583/371472 [8:39:34<9:37:56,  3.57it/s]
 67%|██████▋   | 247584/371472 [8:39:34<11:23:24,  3.02it/s]
 67%|██████▋   | 247585/371472 [8:39:34<10:51:23,  3.17it/s]
 67%|██████▋   | 247586/371472 [8:39:35<10:54:24,  3.16it/s]
 67%|██████▋   | 247587/371472 [8:39:35<10:50:57,  3.17it/s]
 67%|██████▋   | 247588/371472 [8:39:35<10:24:35,  3.31it/s]
 67%|██████▋   | 247589/371472 [8:39:35<10:03:29,  3.42it/s]
 67%|██████▋   | 247590/371472 [8:39:36<10:31:12,  3.27it/s]
 67%|██████▋   | 247591/371472 [8:39:36<10:00:43,  3.44it/s]
 67%|██████▋   | 247592/371472 [8:39:36<10:08:14,  3.39it/s]
 67%|██████▋   | 247593/371472 [8:39:37<9:57:08,  3.46it/s] 
 67%|██████▋   | 247594/371472 [8:39:37<10:00:09,  3.44it/s]
 67%|██████▋   | 247595/371472 [8:39:37<10:48:46,  3.18it/s]
 67%|██████▋   | 247596/371472 [8:39:38<10:30:34,  3.27it/s]
 67%|██████▋   | 247597/371472 [8:39:38<9:45:29,  3.53it/s] 
 67%|██████▋   | 247598/371472 [8:39:38<9:35:00,  3.59it/s]
 67%|██████▋   | 247599/371472 [8:39:38<9:23:00,  3.67it/s]
 67%|██████▋   | 247600/371472 [8:39:39<10:11:49,  3.37it/s]
                                                            
{'loss': 2.8462, 'learning_rate': 4.0027796332607894e-07, 'epoch': 10.66}
+
 67%|██████▋   | 247600/371472 [8:39:39<10:11:49,  3.37it/s]
 67%|██████▋   | 247601/371472 [8:39:39<9:38:38,  3.57it/s] 
 67%|██████▋   | 247602/371472 [8:39:39<9:47:46,  3.51it/s]
 67%|██████▋   | 247603/371472 [8:39:39<9:23:19,  3.66it/s]
 67%|██████▋   | 247604/371472 [8:39:40<9:10:49,  3.75it/s]
 67%|██████▋   | 247605/371472 [8:39:40<9:11:46,  3.74it/s]
 67%|██████▋   | 247606/371472 [8:39:40<9:12:03,  3.74it/s]
 67%|██████▋   | 247607/371472 [8:39:41<10:11:14,  3.38it/s]
 67%|██████▋   | 247608/371472 [8:39:41<10:41:38,  3.22it/s]
 67%|██████▋   | 247609/371472 [8:39:41<10:12:25,  3.37it/s]
 67%|██████▋   | 247610/371472 [8:39:41<10:05:44,  3.41it/s]
 67%|██████▋   | 247611/371472 [8:39:42<10:21:36,  3.32it/s]
 67%|██████▋   | 247612/371472 [8:39:42<9:52:16,  3.49it/s] 
 67%|██████▋   | 247613/371472 [8:39:42<9:28:55,  3.63it/s]
 67%|██████▋   | 247614/371472 [8:39:43<9:15:09,  3.72it/s]
 67%|██████▋   | 247615/371472 [8:39:43<9:09:01,  3.76it/s]
 67%|██████▋   | 247616/371472 [8:39:43<9:08:47,  3.76it/s]
 67%|██████▋   | 247617/371472 [8:39:43<9:14:39,  3.72it/s]
 67%|██████▋   | 247618/371472 [8:39:44<9:43:24,  3.54it/s]
 67%|██████▋   | 247619/371472 [8:39:44<10:06:22,  3.40it/s]
 67%|██████▋   | 247620/371472 [8:39:44<9:41:58,  3.55it/s] 
                                                           
{'loss': 2.9346, 'learning_rate': 4.002294813506001e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247620/371472 [8:39:44<9:41:58,  3.55it/s]
 67%|██████▋   | 247621/371472 [8:39:45<9:51:09,  3.49it/s]
 67%|██████▋   | 247622/371472 [8:39:45<10:01:21,  3.43it/s]
 67%|██████▋   | 247623/371472 [8:39:45<9:47:05,  3.52it/s] 
 67%|██████▋   | 247624/371472 [8:39:45<9:21:21,  3.68it/s]
 67%|██████▋   | 247625/371472 [8:39:46<9:11:12,  3.74it/s]
 67%|██████▋   | 247626/371472 [8:39:46<9:15:51,  3.71it/s]
 67%|██████▋   | 247627/371472 [8:39:46<9:19:19,  3.69it/s]
 67%|██████▋   | 247628/371472 [8:39:46<9:22:48,  3.67it/s]
 67%|██████▋   | 247629/371472 [8:39:47<9:54:47,  3.47it/s]
 67%|██████▋   | 247630/371472 [8:39:47<10:01:44,  3.43it/s]
 67%|██████▋   | 247631/371472 [8:39:47<9:40:54,  3.55it/s] 
 67%|██████▋   | 247632/371472 [8:39:48<9:28:03,  3.63it/s]
 67%|██████▋   | 247633/371472 [8:39:48<10:07:04,  3.40it/s]
 67%|██████▋   | 247634/371472 [8:39:48<9:43:28,  3.54it/s] 
 67%|██████▋   | 247635/371472 [8:39:48<9:11:55,  3.74it/s]
 67%|██████▋   | 247636/371472 [8:39:49<9:08:38,  3.76it/s]
 67%|██████▋   | 247637/371472 [8:39:49<9:28:36,  3.63it/s]
 67%|██████▋   | 247638/371472 [8:39:49<10:06:36,  3.40it/s]
 67%|██████▋   | 247639/371472 [8:39:50<10:06:03,  3.41it/s]
 67%|██████▋   | 247640/371472 [8:39:50<9:41:24,  3.55it/s] 
                                                           
{'loss': 2.8441, 'learning_rate': 4.0018099937512114e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247640/371472 [8:39:50<9:41:24,  3.55it/s]
 67%|██████▋   | 247641/371472 [8:39:50<9:30:53,  3.62it/s]
 67%|██████▋   | 247642/371472 [8:39:50<9:21:39,  3.67it/s]
 67%|██████▋   | 247643/371472 [8:39:51<9:20:51,  3.68it/s]
 67%|██████▋   | 247644/371472 [8:39:51<9:05:15,  3.79it/s]
 67%|██████▋   | 247645/371472 [8:39:51<8:57:42,  3.84it/s]
 67%|██████▋   | 247646/371472 [8:39:51<9:17:38,  3.70it/s]
 67%|██████▋   | 247647/371472 [8:39:52<9:03:30,  3.80it/s]
 67%|██████▋   | 247648/371472 [8:39:52<10:07:13,  3.40it/s]
 67%|██████▋   | 247649/371472 [8:39:52<9:37:25,  3.57it/s] 
 67%|██████▋   | 247650/371472 [8:39:53<9:27:30,  3.64it/s]
 67%|██████▋   | 247651/371472 [8:39:53<10:02:24,  3.43it/s]
 67%|██████▋   | 247652/371472 [8:39:53<9:40:43,  3.55it/s] 
 67%|██████▋   | 247653/371472 [8:39:53<9:44:24,  3.53it/s]
 67%|██████▋   | 247654/371472 [8:39:54<9:36:06,  3.58it/s]
 67%|██████▋   | 247655/371472 [8:39:54<9:21:28,  3.68it/s]
 67%|██████▋   | 247656/371472 [8:39:54<9:10:25,  3.75it/s]
 67%|██████▋   | 247657/371472 [8:39:54<9:11:14,  3.74it/s]
 67%|██████▋   | 247658/371472 [8:39:55<8:50:55,  3.89it/s]
 67%|██████▋   | 247659/371472 [8:39:55<8:41:26,  3.96it/s]
 67%|██████▋   | 247660/371472 [8:39:55<8:45:39,  3.93it/s]
                                                           
{'loss': 3.0761, 'learning_rate': 4.001325173996423e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247660/371472 [8:39:55<8:45:39,  3.93it/s]
 67%|██████▋   | 247661/371472 [8:39:55<8:47:09,  3.91it/s]
 67%|██████▋   | 247662/371472 [8:39:56<9:05:56,  3.78it/s]
 67%|██████▋   | 247663/371472 [8:39:56<9:15:25,  3.72it/s]
 67%|██████▋   | 247664/371472 [8:39:56<9:12:15,  3.74it/s]
 67%|██████▋   | 247665/371472 [8:39:57<9:05:49,  3.78it/s]
 67%|██████▋   | 247666/371472 [8:39:57<9:20:53,  3.68it/s]
 67%|██████▋   | 247667/371472 [8:39:57<9:29:29,  3.62it/s]
 67%|██████▋   | 247668/371472 [8:39:57<9:57:35,  3.45it/s]
 67%|██████▋   | 247669/371472 [8:39:58<9:35:54,  3.58it/s]
 67%|██████▋   | 247670/371472 [8:39:58<9:20:07,  3.68it/s]
 67%|██████▋   | 247671/371472 [8:39:58<9:01:22,  3.81it/s]
 67%|██████▋   | 247672/371472 [8:39:58<8:48:37,  3.90it/s]
 67%|██████▋   | 247673/371472 [8:39:59<9:02:41,  3.80it/s]
 67%|██████▋   | 247674/371472 [8:39:59<9:41:17,  3.55it/s]
 67%|██████▋   | 247675/371472 [8:39:59<9:44:33,  3.53it/s]
 67%|██████▋   | 247676/371472 [8:40:00<9:35:26,  3.59it/s]
 67%|██████▋   | 247677/371472 [8:40:00<10:05:24,  3.41it/s]
 67%|██████▋   | 247678/371472 [8:40:00<10:19:31,  3.33it/s]
 67%|██████▋   | 247679/371472 [8:40:01<9:43:20,  3.54it/s] 
 67%|██████▋   | 247680/371472 [8:40:01<9:18:41,  3.69it/s]
                                                           
{'loss': 2.8316, 'learning_rate': 4.000840354241634e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247680/371472 [8:40:01<9:18:41,  3.69it/s]
 67%|██████▋   | 247681/371472 [8:40:01<8:58:51,  3.83it/s]
 67%|██████▋   | 247682/371472 [8:40:01<8:53:59,  3.86it/s]
 67%|██████▋   | 247683/371472 [8:40:02<9:39:41,  3.56it/s]
 67%|██████▋   | 247684/371472 [8:40:02<9:09:00,  3.76it/s]
 67%|██████▋   | 247685/371472 [8:40:02<9:21:09,  3.68it/s]
 67%|██████▋   | 247686/371472 [8:40:02<9:15:54,  3.71it/s]
 67%|██████▋   | 247687/371472 [8:40:03<9:06:14,  3.78it/s]
 67%|██████▋   | 247688/371472 [8:40:03<9:55:10,  3.47it/s]
 67%|██████▋   | 247689/371472 [8:40:03<9:52:28,  3.48it/s]
 67%|██████▋   | 247690/371472 [8:40:03<9:38:33,  3.57it/s]
 67%|██████▋   | 247691/371472 [8:40:04<9:43:38,  3.53it/s]
 67%|██████▋   | 247692/371472 [8:40:04<9:32:10,  3.61it/s]
 67%|██████▋   | 247693/371472 [8:40:04<9:33:24,  3.60it/s]
 67%|██████▋   | 247694/371472 [8:40:05<9:43:38,  3.53it/s]
 67%|██████▋   | 247695/371472 [8:40:05<9:49:53,  3.50it/s]
 67%|██████▋   | 247696/371472 [8:40:05<9:26:08,  3.64it/s]
 67%|██████▋   | 247697/371472 [8:40:05<9:18:02,  3.70it/s]
 67%|██████▋   | 247698/371472 [8:40:06<9:21:45,  3.67it/s]
 67%|██████▋   | 247699/371472 [8:40:06<9:11:55,  3.74it/s]
 67%|██████▋   | 247700/371472 [8:40:06<9:18:00,  3.70it/s]
                                                           
{'loss': 2.7986, 'learning_rate': 4.000355534486845e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247700/371472 [8:40:06<9:18:00,  3.70it/s]
 67%|██████▋   | 247701/371472 [8:40:06<9:11:02,  3.74it/s]
 67%|██████▋   | 247702/371472 [8:40:07<9:13:34,  3.73it/s]
 67%|██████▋   | 247703/371472 [8:40:07<8:57:24,  3.84it/s]
 67%|██████▋   | 247704/371472 [8:40:07<8:47:30,  3.91it/s]
 67%|██████▋   | 247705/371472 [8:40:08<8:50:32,  3.89it/s]
 67%|██████▋   | 247706/371472 [8:40:08<8:32:31,  4.02it/s]
 67%|██████▋   | 247707/371472 [8:40:08<8:43:04,  3.94it/s]
 67%|██████▋   | 247708/371472 [8:40:08<9:04:44,  3.79it/s]
 67%|██████▋   | 247709/371472 [8:40:09<9:25:21,  3.65it/s]
 67%|██████▋   | 247710/371472 [8:40:09<9:21:04,  3.68it/s]
 67%|██████▋   | 247711/371472 [8:40:09<9:17:38,  3.70it/s]
 67%|██████▋   | 247712/371472 [8:40:09<9:05:57,  3.78it/s]
 67%|██████▋   | 247713/371472 [8:40:10<9:07:06,  3.77it/s]
 67%|██████▋   | 247714/371472 [8:40:10<9:33:38,  3.60it/s]
 67%|██████▋   | 247715/371472 [8:40:10<9:22:16,  3.67it/s]
 67%|██████▋   | 247716/371472 [8:40:10<9:26:26,  3.64it/s]
 67%|██████▋   | 247717/371472 [8:40:11<9:18:23,  3.69it/s]
 67%|██████▋   | 247718/371472 [8:40:11<9:07:08,  3.77it/s]
 67%|██████▋   | 247719/371472 [8:40:11<9:25:45,  3.65it/s]
 67%|██████▋   | 247720/371472 [8:40:12<10:18:07,  3.34it/s]
                                                            
{'loss': 2.7343, 'learning_rate': 3.999870714732056e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247720/371472 [8:40:12<10:18:07,  3.34it/s]
 67%|██████▋   | 247721/371472 [8:40:12<9:55:23,  3.46it/s] 
 67%|██████▋   | 247722/371472 [8:40:12<10:20:36,  3.32it/s]
 67%|██████▋   | 247723/371472 [8:40:13<10:06:30,  3.40it/s]
 67%|██████▋   | 247724/371472 [8:40:13<9:22:24,  3.67it/s] 
 67%|██████▋   | 247725/371472 [8:40:13<9:13:01,  3.73it/s]
 67%|██████▋   | 247726/371472 [8:40:13<8:58:45,  3.83it/s]
 67%|██████▋   | 247727/371472 [8:40:14<9:26:30,  3.64it/s]
 67%|██████▋   | 247728/371472 [8:40:14<10:18:11,  3.34it/s]
 67%|██████▋   | 247729/371472 [8:40:14<9:43:47,  3.53it/s] 
 67%|██████▋   | 247730/371472 [8:40:15<10:52:35,  3.16it/s]
 67%|██████▋   | 247731/371472 [8:40:15<10:19:28,  3.33it/s]
 67%|██████▋   | 247732/371472 [8:40:15<9:44:09,  3.53it/s] 
 67%|██████▋   | 247733/371472 [8:40:15<9:34:44,  3.59it/s]
 67%|██████▋   | 247734/371472 [8:40:16<9:18:54,  3.69it/s]
 67%|██████▋   | 247735/371472 [8:40:16<10:30:04,  3.27it/s]
 67%|██████▋   | 247736/371472 [8:40:16<10:11:45,  3.37it/s]
 67%|██████▋   | 247737/371472 [8:40:17<11:36:19,  2.96it/s]
 67%|██████▋   | 247738/371472 [8:40:17<10:48:39,  3.18it/s]
 67%|██████▋   | 247739/371472 [8:40:17<10:16:33,  3.34it/s]
 67%|██████▋   | 247740/371472 [8:40:18<10:28:08,  3.28it/s]
                                                            
{'loss': 2.683, 'learning_rate': 3.9993858949772676e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247740/371472 [8:40:18<10:28:08,  3.28it/s]
 67%|██████▋   | 247741/371472 [8:40:18<9:46:09,  3.52it/s] 
 67%|██████▋   | 247742/371472 [8:40:18<9:44:50,  3.53it/s]
 67%|██████▋   | 247743/371472 [8:40:18<9:58:06,  3.45it/s]
 67%|██████▋   | 247744/371472 [8:40:19<9:35:31,  3.58it/s]
 67%|██████▋   | 247745/371472 [8:40:19<9:23:46,  3.66it/s]
 67%|██████▋   | 247746/371472 [8:40:19<9:04:07,  3.79it/s]
 67%|██████▋   | 247747/371472 [8:40:19<8:53:54,  3.86it/s]
 67%|██████▋   | 247748/371472 [8:40:20<8:53:56,  3.86it/s]
 67%|██████▋   | 247749/371472 [8:40:20<9:06:20,  3.77it/s]
 67%|██████▋   | 247750/371472 [8:40:20<10:06:11,  3.40it/s]
 67%|██████▋   | 247751/371472 [8:40:21<9:56:51,  3.45it/s] 
 67%|██████▋   | 247752/371472 [8:40:21<9:39:08,  3.56it/s]
 67%|██████▋   | 247753/371472 [8:40:21<9:37:42,  3.57it/s]
 67%|██████▋   | 247754/371472 [8:40:21<10:08:57,  3.39it/s]
 67%|██████▋   | 247755/371472 [8:40:22<9:54:43,  3.47it/s] 
 67%|██████▋   | 247756/371472 [8:40:22<9:32:12,  3.60it/s]
 67%|██████▋   | 247757/371472 [8:40:22<9:21:52,  3.67it/s]
 67%|██████▋   | 247758/371472 [8:40:22<9:05:34,  3.78it/s]
 67%|██████▋   | 247759/371472 [8:40:23<8:47:47,  3.91it/s]
 67%|██████▋   | 247760/371472 [8:40:23<9:01:51,  3.81it/s]
                                                           
{'loss': 3.0695, 'learning_rate': 3.998901075222478e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247760/371472 [8:40:23<9:01:51,  3.81it/s]
 67%|██████▋   | 247761/371472 [8:40:23<9:09:18,  3.75it/s]
 67%|██████▋   | 247762/371472 [8:40:23<8:56:47,  3.84it/s]
 67%|██████▋   | 247763/371472 [8:40:24<8:56:51,  3.84it/s]
 67%|██████▋   | 247764/371472 [8:40:24<9:33:21,  3.60it/s]
 67%|██████▋   | 247765/371472 [8:40:24<9:13:21,  3.73it/s]
 67%|██████▋   | 247766/371472 [8:40:25<9:09:59,  3.75it/s]
 67%|██████▋   | 247767/371472 [8:40:25<9:20:28,  3.68it/s]
 67%|██████▋   | 247768/371472 [8:40:25<9:32:21,  3.60it/s]
 67%|██████▋   | 247769/371472 [8:40:25<10:07:00,  3.40it/s]
 67%|██████▋   | 247770/371472 [8:40:26<10:34:18,  3.25it/s]
 67%|██████▋   | 247771/371472 [8:40:26<10:02:12,  3.42it/s]
 67%|██████▋   | 247772/371472 [8:40:26<9:48:23,  3.50it/s] 
 67%|██████▋   | 247773/371472 [8:40:27<9:23:58,  3.66it/s]
 67%|██████▋   | 247774/371472 [8:40:27<9:25:48,  3.64it/s]
 67%|██████▋   | 247775/371472 [8:40:27<9:03:39,  3.79it/s]
 67%|██████▋   | 247776/371472 [8:40:27<9:27:49,  3.63it/s]
 67%|██████▋   | 247777/371472 [8:40:28<9:35:07,  3.58it/s]
 67%|██████▋   | 247778/371472 [8:40:28<9:41:53,  3.54it/s]
 67%|██████▋   | 247779/371472 [8:40:28<9:19:11,  3.69it/s]
 67%|██████▋   | 247780/371472 [8:40:28<9:27:16,  3.63it/s]
                                                           
{'loss': 2.9061, 'learning_rate': 3.9984162554676896e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247780/371472 [8:40:29<9:27:16,  3.63it/s]
 67%|██████▋   | 247781/371472 [8:40:29<9:48:16,  3.50it/s]
 67%|██████▋   | 247782/371472 [8:40:29<10:46:32,  3.19it/s]
 67%|██████▋   | 247783/371472 [8:40:29<10:11:00,  3.37it/s]
 67%|██████▋   | 247784/371472 [8:40:30<9:47:19,  3.51it/s] 
 67%|██████▋   | 247785/371472 [8:40:30<9:32:03,  3.60it/s]
 67%|██████▋   | 247786/371472 [8:40:30<9:27:22,  3.63it/s]
 67%|██████▋   | 247787/371472 [8:40:31<9:29:39,  3.62it/s]
 67%|██████▋   | 247788/371472 [8:40:31<9:18:08,  3.69it/s]
 67%|██████▋   | 247789/371472 [8:40:31<9:11:19,  3.74it/s]
 67%|██████▋   | 247790/371472 [8:40:31<9:48:34,  3.50it/s]
 67%|██████▋   | 247791/371472 [8:40:32<9:20:47,  3.68it/s]
 67%|██████▋   | 247792/371472 [8:40:32<9:13:20,  3.73it/s]
 67%|██████▋   | 247793/371472 [8:40:32<9:49:21,  3.50it/s]
 67%|██████▋   | 247794/371472 [8:40:33<10:53:28,  3.15it/s]
 67%|██████▋   | 247795/371472 [8:40:33<10:34:36,  3.25it/s]
 67%|██████▋   | 247796/371472 [8:40:33<10:33:43,  3.25it/s]
 67%|██████▋   | 247797/371472 [8:40:34<10:57:03,  3.14it/s]
 67%|██████▋   | 247798/371472 [8:40:34<10:28:51,  3.28it/s]
 67%|██████▋   | 247799/371472 [8:40:34<10:32:57,  3.26it/s]
 67%|██████▋   | 247800/371472 [8:40:34<10:40:37,  3.22it/s]
                                                            
{'loss': 2.7742, 'learning_rate': 3.9979314357129003e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247800/371472 [8:40:34<10:40:37,  3.22it/s]
 67%|██████▋   | 247801/371472 [8:40:35<10:08:08,  3.39it/s]
 67%|██████▋   | 247802/371472 [8:40:35<9:51:13,  3.49it/s] 
 67%|██████▋   | 247803/371472 [8:40:35<9:36:04,  3.58it/s]
 67%|██████▋   | 247804/371472 [8:40:36<9:49:07,  3.50it/s]
 67%|██████▋   | 247805/371472 [8:40:36<10:48:18,  3.18it/s]
 67%|██████▋   | 247806/371472 [8:40:36<10:28:44,  3.28it/s]
 67%|██████▋   | 247807/371472 [8:40:36<9:49:45,  3.49it/s] 
 67%|██████▋   | 247808/371472 [8:40:37<9:50:54,  3.49it/s]
 67%|██████▋   | 247809/371472 [8:40:37<9:39:32,  3.56it/s]
 67%|██████▋   | 247810/371472 [8:40:37<9:50:38,  3.49it/s]
 67%|██████▋   | 247811/371472 [8:40:38<9:48:34,  3.50it/s]
 67%|██████▋   | 247812/371472 [8:40:38<9:28:57,  3.62it/s]
 67%|██████▋   | 247813/371472 [8:40:38<9:11:33,  3.74it/s]
 67%|██████▋   | 247814/371472 [8:40:38<9:06:49,  3.77it/s]
 67%|██████▋   | 247815/371472 [8:40:39<9:32:10,  3.60it/s]
 67%|██████▋   | 247816/371472 [8:40:39<9:09:56,  3.75it/s]
 67%|██████▋   | 247817/371472 [8:40:39<9:05:34,  3.78it/s]
 67%|██████▋   | 247818/371472 [8:40:39<9:08:16,  3.76it/s]
 67%|██████▋   | 247819/371472 [8:40:40<9:02:02,  3.80it/s]
 67%|██████▋   | 247820/371472 [8:40:40<9:30:30,  3.61it/s]
                                                           
{'loss': 2.8589, 'learning_rate': 3.9974466159581115e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247820/371472 [8:40:40<9:30:30,  3.61it/s]
 67%|██████▋   | 247821/371472 [8:40:40<9:32:36,  3.60it/s]
 67%|██████▋   | 247822/371472 [8:40:40<9:06:52,  3.77it/s]
 67%|██████▋   | 247823/371472 [8:40:41<9:31:17,  3.61it/s]
 67%|██████▋   | 247824/371472 [8:40:41<9:44:00,  3.53it/s]
 67%|██████▋   | 247825/371472 [8:40:41<10:13:17,  3.36it/s]
 67%|██████▋   | 247826/371472 [8:40:42<10:33:49,  3.25it/s]
 67%|██████▋   | 247827/371472 [8:40:42<10:22:59,  3.31it/s]
 67%|██████▋   | 247828/371472 [8:40:42<10:28:26,  3.28it/s]
 67%|██████▋   | 247829/371472 [8:40:43<10:16:08,  3.34it/s]
 67%|██████▋   | 247830/371472 [8:40:43<10:00:32,  3.43it/s]
 67%|██████▋   | 247831/371472 [8:40:43<10:34:07,  3.25it/s]
 67%|██████▋   | 247832/371472 [8:40:44<11:14:14,  3.06it/s]
 67%|██████▋   | 247833/371472 [8:40:44<10:33:09,  3.25it/s]
 67%|██████▋   | 247834/371472 [8:40:44<11:11:37,  3.07it/s]
 67%|██████▋   | 247835/371472 [8:40:45<10:30:47,  3.27it/s]
 67%|██████▋   | 247836/371472 [8:40:45<10:23:28,  3.31it/s]
 67%|██████▋   | 247837/371472 [8:40:45<10:02:21,  3.42it/s]
 67%|██████▋   | 247838/371472 [8:40:45<9:53:37,  3.47it/s] 
 67%|██████▋   | 247839/371472 [8:40:46<9:46:12,  3.52it/s]
 67%|██████▋   | 247840/371472 [8:40:46<10:34:19,  3.25it/s]
                                                            
{'loss': 2.8509, 'learning_rate': 3.9969617962033217e-07, 'epoch': 10.67}
+
 67%|██████▋   | 247840/371472 [8:40:46<10:34:19,  3.25it/s]
 67%|���█████▋   | 247841/371472 [8:40:46<10:13:34,  3.36it/s]
 67%|██████▋   | 247842/371472 [8:40:47<11:01:07,  3.12it/s]
 67%|██████▋   | 247843/371472 [8:40:47<10:41:16,  3.21it/s]
 67%|██████▋   | 247844/371472 [8:40:47<10:30:08,  3.27it/s]
 67%|██████▋   | 247845/371472 [8:40:48<11:35:34,  2.96it/s]
 67%|██████▋   | 247846/371472 [8:40:48<10:53:38,  3.15it/s]
 67%|██████▋   | 247847/371472 [8:40:48<10:22:32,  3.31it/s]
 67%|██████▋   | 247848/371472 [8:40:49<11:05:02,  3.10it/s]
 67%|██████▋   | 247849/371472 [8:40:49<10:45:10,  3.19it/s]
 67%|██████▋   | 247850/371472 [8:40:49<11:08:29,  3.08it/s]
 67%|██████▋   | 247851/371472 [8:40:49<10:26:49,  3.29it/s]
 67%|██████▋   | 247852/371472 [8:40:50<9:44:40,  3.52it/s] 
 67%|██████▋   | 247853/371472 [8:40:50<9:19:14,  3.68it/s]
 67%|██████▋   | 247854/371472 [8:40:50<9:12:21,  3.73it/s]
 67%|██████▋   | 247855/371472 [8:40:50<9:27:17,  3.63it/s]
 67%|██████▋   | 247856/371472 [8:40:51<9:30:20,  3.61it/s]
 67%|██████▋   | 247857/371472 [8:40:51<8:59:17,  3.82it/s]
 67%|██████▋   | 247858/371472 [8:40:51<9:03:25,  3.79it/s]
 67%|██████▋   | 247859/371472 [8:40:52<9:45:10,  3.52it/s]
 67%|██████▋   | 247860/371472 [8:40:52<10:30:10,  3.27it/s]
                                                            
{'loss': 3.0373, 'learning_rate': 3.996476976448534e-07, 'epoch': 10.68}
+
 67%|██████▋   | 247860/371472 [8:40:52<10:30:10,  3.27it/s]
 67%|██████▋   | 247861/371472 [8:40:52<10:24:24,  3.30it/s]
 67%|██████▋   | 247862/371472 [8:40:52<9:52:29,  3.48it/s] 
 67%|██████▋   | 247863/371472 [8:40:53<9:47:29,  3.51it/s]
 67%|██████▋   | 247864/371472 [8:40:53<9:21:22,  3.67it/s]
 67%|██████▋   | 247865/371472 [8:40:53<9:13:45,  3.72it/s]
 67%|██████▋   | 247866/371472 [8:40:54<9:01:44,  3.80it/s]
 67%|██████▋   | 247867/371472 [8:40:54<9:00:15,  3.81it/s]
 67%|██████▋   | 247868/371472 [8:40:54<8:49:42,  3.89it/s]
 67%|██████▋   | 247869/371472 [8:40:54<9:09:00,  3.75it/s]
 67%|██████▋   | 247870/371472 [8:40:55<8:59:07,  3.82it/s]
 67%|██████▋   | 247871/371472 [8:40:55<8:46:52,  3.91it/s]
 67%|██████▋   | 247872/371472 [8:40:55<8:52:16,  3.87it/s]
 67%|██████▋   | 247873/371472 [8:40:55<9:12:38,  3.73it/s]
 67%|██████▋   | 247874/371472 [8:40:56<9:03:16,  3.79it/s]
 67%|██████▋   | 247875/371472 [8:40:56<9:19:20,  3.68it/s]
 67%|██████▋   | 247876/371472 [8:40:56<9:58:22,  3.44it/s]
 67%|██████▋   | 247877/371472 [8:40:57<9:57:33,  3.45it/s]
 67%|██████▋   | 247878/371472 [8:40:57<10:12:32,  3.36it/s]
 67%|██████▋   | 247879/371472 [8:40:57<9:48:34,  3.50it/s] 
 67%|██████▋   | 247880/371472 [8:40:57<9:45:33,  3.52it/s]
                                                           
{'loss': 2.8453, 'learning_rate': 3.995992156693744e-07, 'epoch': 10.68}
+
 67%|██████▋   | 247880/371472 [8:40:57<9:45:33,  3.52it/s]
 67%|██████▋   | 247881/371472 [8:40:58<9:38:14,  3.56it/s]
 67%|██████▋   | 247882/371472 [8:40:58<9:26:59,  3.63it/s]
 67%|██████▋   | 247883/371472 [8:40:58<9:51:10,  3.48it/s]
 67%|██████▋   | 247884/371472 [8:40:58<9:34:22,  3.59it/s]
 67%|██████▋   | 247885/371472 [8:40:59<9:33:57,  3.59it/s]
 67%|██████▋   | 247886/371472 [8:40:59<9:37:10,  3.57it/s]
 67%|██████▋   | 247887/371472 [8:40:59<9:42:55,  3.53it/s]
 67%|██████▋   | 247888/371472 [8:41:00<9:24:19,  3.65it/s]
 67%|██████▋   | 247889/371472 [8:41:00<10:35:38,  3.24it/s]
 67%|██████▋   | 247890/371472 [8:41:00<9:55:21,  3.46it/s] 
 67%|██████▋   | 247891/371472 [8:41:00<9:42:51,  3.53it/s]
 67%|██████▋   | 247892/371472 [8:41:01<9:15:37,  3.71it/s]
 67%|██████▋   | 247893/371472 [8:41:01<9:11:30,  3.73it/s]
 67%|██████▋   | 247894/371472 [8:41:01<9:01:05,  3.81it/s]
 67%|██████▋   | 247895/371472 [8:41:02<9:07:10,  3.76it/s]
 67%|██████▋   | 247896/371472 [8:41:02<9:13:11,  3.72it/s]
 67%|██████▋   | 247897/371472 [8:41:02<9:43:52,  3.53it/s]
 67%|██████▋   | 247898/371472 [8:41:02<9:23:01,  3.66it/s]
 67%|██████▋   | 247899/371472 [8:41:03<9:02:36,  3.80it/s]
 67%|██████▋   | 247900/371472 [8:41:03<8:43:14,  3.94it/s]
                                                           
{'loss': 2.9088, 'learning_rate': 3.995507336938956e-07, 'epoch': 10.68}
+
 67%|██████▋   | 247900/371472 [8:41:03<8:43:14,  3.94it/s]
 67%|██████▋   | 247901/371472 [8:41:03<9:03:31,  3.79it/s]
 67%|██████▋   | 247902/371472 [8:41:04<10:33:40,  3.25it/s]
 67%|██████▋   | 247903/371472 [8:41:04<10:18:43,  3.33it/s]
 67%|██████▋   | 247904/371472 [8:41:04<9:36:40,  3.57it/s] 
 67%|██████▋   | 247905/371472 [8:41:04<10:16:40,  3.34it/s]
 67%|██████▋   | 247906/371472 [8:41:05<10:20:07,  3.32it/s]
 67%|██████▋   | 247907/371472 [8:41:05<10:14:25,  3.35it/s]
 67%|██████▋   | 247908/371472 [8:41:05<9:49:53,  3.49it/s] 
 67%|██████▋   | 247909/371472 [8:41:06<9:47:26,  3.51it/s]
 67%|██████▋   | 247910/371472 [8:41:06<9:38:58,  3.56it/s]
 67%|██████▋   | 247911/371472 [8:41:06<9:30:42,  3.61it/s]
 67%|██████▋   | 247912/371472 [8:41:06<9:09:19,  3.75it/s]
 67%|██████▋   | 247913/371472 [8:41:07<8:58:56,  3.82it/s]
 67%|██████▋   | 247914/371472 [8:41:07<9:17:55,  3.69it/s]
 67%|██████▋   | 247915/371472 [8:41:07<9:09:53,  3.74it/s]
 67%|██████▋   | 247916/371472 [8:41:07<9:13:38,  3.72it/s]
 67%|██████▋   | 247917/371472 [8:41:08<9:09:01,  3.75it/s]
 67%|██████▋   | 247918/371472 [8:41:08<10:10:06,  3.38it/s]
 67%|██████▋   | 247919/371472 [8:41:08<9:41:21,  3.54it/s] 
 67%|██████▋   | 247920/371472 [8:41:09<9:42:02,  3.54it/s]
                                                           
{'loss': 2.8075, 'learning_rate': 3.9950225171841667e-07, 'epoch': 10.68}
+
 67%|██████▋   | 247920/371472 [8:41:09<9:42:02,  3.54it/s]
 67%|██████▋   | 247921/371472 [8:41:09<9:16:54,  3.70it/s]
 67%|██████▋   | 247922/371472 [8:41:09<9:18:03,  3.69it/s]
 67%|██████▋   | 247923/371472 [8:41:09<9:11:13,  3.74it/s]
 67%|██████▋   | 247924/371472 [8:41:10<10:12:00,  3.36it/s]
 67%|██████▋   | 247925/371472 [8:41:10<9:48:37,  3.50it/s] 
 67%|██████▋   | 247926/371472 [8:41:10<9:29:16,  3.62it/s]
 67%|██████▋   | 247927/371472 [8:41:11<9:57:22,  3.45it/s]
 67%|██████▋   | 247928/371472 [8:41:11<9:55:21,  3.46it/s]
 67%|██████▋   | 247929/371472 [8:41:11<9:54:00,  3.47it/s]
 67%|██████▋   | 247930/371472 [8:41:11<10:01:19,  3.42it/s]
 67%|██████▋   | 247931/371472 [8:41:12<9:58:11,  3.44it/s] 
 67%|██████▋   | 247932/371472 [8:41:12<10:21:46,  3.31it/s]
 67%|██████▋   | 247933/371472 [8:41:12<9:51:22,  3.48it/s] 
 67%|██████▋   | 247934/371472 [8:41:13<9:33:00,  3.59it/s]
 67%|██████▋   | 247935/371472 [8:41:13<9:12:46,  3.72it/s]
 67%|██████▋   | 247936/371472 [8:41:13<8:58:40,  3.82it/s]
 67%|██████▋   | 247937/371472 [8:41:13<9:01:58,  3.80it/s]
 67%|██████▋   | 247938/371472 [8:41:14<8:53:58,  3.86it/s]
 67%|██████▋   | 247939/371472 [8:41:14<10:01:01,  3.43it/s]
 67%|██████▋   | 247940/371472 [8:41:14<9:59:43,  3.43it/s] 
                                                           
{'loss': 2.7569, 'learning_rate': 3.994537697429378e-07, 'epoch': 10.68}
+
 67%|██████▋   | 247940/371472 [8:41:14<9:59:43,  3.43it/s]
 67%|██████▋   | 247941/371472 [8:41:14<9:41:58,  3.54it/s]
 67%|██████▋   | 247942/371472 [8:41:15<9:44:46,  3.52it/s]
 67%|██████▋   | 247943/371472 [8:41:15<9:11:44,  3.73it/s]
 67%|██████▋   | 247944/371472 [8:41:15<9:27:07,  3.63it/s]
 67%|██████▋   | 247945/371472 [8:41:16<9:39:02,  3.56it/s]
 67%|██████▋   | 247946/371472 [8:41:16<9:36:10,  3.57it/s]
 67%|██████▋   | 247947/371472 [8:41:16<9:40:02,  3.55it/s]
 67%|██████▋   | 247948/371472 [8:41:16<9:22:54,  3.66it/s]
 67%|██████▋   | 247949/371472 [8:41:17<9:06:22,  3.77it/s]
 67%|██████▋   | 247950/371472 [8:41:17<9:16:44,  3.70it/s]
 67%|██████▋   | 247951/371472 [8:41:17<10:12:09,  3.36it/s]
 67%|██████▋   | 247952/371472 [8:41:18<10:21:16,  3.31it/s]
 67%|██████▋   | 247953/371472 [8:41:18<9:52:24,  3.48it/s] 
 67%|██████▋   | 247954/371472 [8:41:18<9:56:58,  3.45it/s]
 67%|██████▋   | 247955/371472 [8:41:18<10:05:06,  3.40it/s]
 67%|██████▋   | 247956/371472 [8:41:19<9:41:04,  3.54it/s] 
 67%|██████▋   | 247957/371472 [8:41:19<9:37:51,  3.56it/s]
 67%|██████▋   | 247958/371472 [8:41:19<9:31:37,  3.60it/s]
 67%|██████▋   | 247959/371472 [8:41:20<9:51:39,  3.48it/s]
 67%|██████▋   | 247960/371472 [8:41:20<9:32:53,  3.59it/s]
                                                           
{'loss': 2.8852, 'learning_rate': 3.9940528776745886e-07, 'epoch': 10.68}
+
 67%|██████▋   | 247960/371472 [8:41:20<9:32:53,  3.59it/s]
 67%|██████▋   | 247961/371472 [8:41:20<9:08:15,  3.75it/s]
 67%|██████▋   | 247962/371472 [8:41:20<8:58:44,  3.82it/s]
 67%|██████▋   | 247963/371472 [8:41:21<8:45:49,  3.91it/s]
 67%|██████▋   | 247964/371472 [8:41:21<9:13:27,  3.72it/s]
 67%|██████▋   | 247965/371472 [8:41:21<9:24:48,  3.64it/s]
 67%|██████▋   | 247966/371472 [8:41:21<9:05:49,  3.77it/s]
 67%|██████▋   | 247967/371472 [8:41:22<8:54:09,  3.85it/s]
 67%|██████▋   | 247968/371472 [8:41:22<9:02:00,  3.80it/s]
 67%|██████▋   | 247969/371472 [8:41:22<8:44:59,  3.92it/s]
 67%|██████▋   | 247970/371472 [8:41:22<8:36:05,  3.99it/s]
 67%|██████▋   | 247971/371472 [8:41:23<8:32:00,  4.02it/s]
 67%|██████▋   | 247972/371472 [8:41:23<8:34:12,  4.00it/s]
 67%|██████▋   | 247973/371472 [8:41:23<8:35:35,  3.99it/s]
 67%|██████▋   | 247974/371472 [8:41:23<8:52:53,  3.86it/s]
 67%|██████▋   | 247975/371472 [8:41:24<8:39:43,  3.96it/s]
 67%|██████▋   | 247976/371472 [8:41:24<8:33:17,  4.01it/s]
 67%|██████▋   | 247977/371472 [8:41:24<8:31:24,  4.02it/s]
 67%|██████▋   | 247978/371472 [8:41:24<8:50:01,  3.88it/s]
 67%|██████▋   | 247979/371472 [8:41:25<9:28:35,  3.62it/s]
 67%|██████▋   | 247980/371472 [8:41:25<10:00:30,  3.43it/s]
                                                            
{'loss': 3.0035, 'learning_rate': 3.9935680579198004e-07, 'epoch': 10.68}
+
 67%|██████▋   | 247980/371472 [8:41:25<10:00:30,  3.43it/s]
 67%|██████▋   | 247981/371472 [8:41:25<9:39:48,  3.55it/s] 
 67%|██████▋   | 247982/371472 [8:41:26<9:55:52,  3.45it/s]
 67%|██████▋   | 247983/371472 [8:41:26<9:57:39,  3.44it/s]
 67%|██████▋   | 247984/371472 [8:41:26<9:40:39,  3.54it/s]
 67%|██████▋   | 247985/371472 [8:41:26<9:13:26,  3.72it/s]
 67%|██████▋   | 247986/371472 [8:41:27<9:21:13,  3.67it/s]
 67%|██████▋   | 247987/371472 [8:41:27<9:08:47,  3.75it/s]
 67%|██████▋   | 247988/371472 [8:41:27<9:11:51,  3.73it/s]
 67%|██████▋   | 247989/371472 [8:41:27<8:58:22,  3.82it/s]
 67%|██████▋   | 247990/371472 [8:41:28<8:55:33,  3.84it/s]
 67%|██████▋   | 247991/371472 [8:41:28<8:56:12,  3.84it/s]
 67%|██████▋   | 247992/371472 [8:41:28<9:15:00,  3.71it/s]
 67%|██████▋   | 247993/371472 [8:41:29<9:14:27,  3.71it/s]
 67%|██████▋   | 247994/371472 [8:41:29<9:09:11,  3.75it/s]
 67%|██████▋   | 247995/371472 [8:41:29<8:54:24,  3.85it/s]
 67%|██████▋   | 247996/371472 [8:41:29<9:22:16,  3.66it/s]
 67%|██████▋   | 247997/371472 [8:41:30<9:03:45,  3.78it/s]
 67%|██████▋   | 247998/371472 [8:41:30<9:37:21,  3.56it/s]
 67%|██████▋   | 247999/371472 [8:41:30<9:56:32,  3.45it/s]
 67%|██████▋   | 248000/371472 [8:41:30<10:01:06,  3.42it/s]
                                                            
{'loss': 3.0173, 'learning_rate': 3.993083238165011e-07, 'epoch': 10.68}
+
 67%|██████▋   | 248000/371472 [8:41:30<10:01:06,  3.42it/s]
 67%|██████▋   | 248001/371472 [8:41:31<9:53:26,  3.47it/s] 
 67%|██████▋   | 248002/371472 [8:41:31<9:59:13,  3.43it/s]
 67%|██████▋   | 248003/371472 [8:41:31<9:37:48,  3.56it/s]
 67%|██████▋   | 248004/371472 [8:41:32<9:27:07,  3.63it/s]
 67%|██████▋   | 248005/371472 [8:41:32<9:18:00,  3.69it/s]
 67%|██████▋   | 248006/371472 [8:41:32<9:33:48,  3.59it/s]
 67%|██████▋   | 248007/371472 [8:41:32<9:30:08,  3.61it/s]
 67%|██████▋   | 248008/371472 [8:41:33<9:27:36,  3.63it/s]
 67%|██████▋   | 248009/371472 [8:41:33<9:53:56,  3.46it/s]
 67%|██████▋   | 248010/371472 [8:41:33<9:55:23,  3.46it/s]
 67%|██████▋   | 248011/371472 [8:41:34<9:43:56,  3.52it/s]
 67%|██████▋   | 248012/371472 [8:41:34<9:43:33,  3.53it/s]
 67%|██████▋   | 248013/371472 [8:41:34<9:50:24,  3.49it/s]
 67%|██████▋   | 248014/371472 [8:41:34<9:39:32,  3.55it/s]
 67%|██████▋   | 248015/371472 [8:41:35<10:27:16,  3.28it/s]
 67%|██████▋   | 248016/371472 [8:41:35<10:53:21,  3.15it/s]
 67%|██████▋   | 248017/371472 [8:41:35<10:48:37,  3.17it/s]
 67%|██████▋   | 248018/371472 [8:41:36<10:09:01,  3.38it/s]
 67%|██████▋   | 248019/371472 [8:41:36<9:59:48,  3.43it/s] 
 67%|██████▋   | 248020/371472 [8:41:36<9:56:19,  3.45it/s]
                                                           
{'loss': 2.9818, 'learning_rate': 3.9925984184102213e-07, 'epoch': 10.68}
+
 67%|██████▋   | 248020/371472 [8:41:36<9:56:19,  3.45it/s]
 67%|██████▋   | 248021/371472 [8:41:37<9:43:45,  3.52it/s]
 67%|██████▋   | 248022/371472 [8:41:37<9:41:43,  3.54it/s]
 67%|██████▋   | 248023/371472 [8:41:37<9:18:56,  3.68it/s]
 67%|██████▋   | 248024/371472 [8:41:37<9:16:48,  3.70it/s]
 67%|██████▋   | 248025/371472 [8:41:38<9:05:33,  3.77it/s]
 67%|██████▋   | 248026/371472 [8:41:38<10:08:02,  3.38it/s]
 67%|██████▋   | 248027/371472 [8:41:38<10:20:15,  3.32it/s]
 67%|██████▋   | 248028/371472 [8:41:39<9:48:36,  3.50it/s] 
 67%|██████▋   | 248029/371472 [8:41:39<9:42:25,  3.53it/s]
 67%|██████▋   | 248030/371472 [8:41:39<9:22:40,  3.66it/s]
 67%|██████▋   | 248031/371472 [8:41:39<9:26:32,  3.63it/s]
 67%|██████▋   | 248032/371472 [8:41:40<9:26:03,  3.63it/s]
 67%|██████▋   | 248033/371472 [8:41:40<9:30:32,  3.61it/s]
 67%|██████▋   | 248034/371472 [8:41:40<9:33:18,  3.59it/s]
 67%|██████▋   | 248035/371472 [8:41:40<9:42:19,  3.53it/s]
 67%|██████▋   | 248036/371472 [8:41:41<9:39:14,  3.55it/s]
 67%|██████▋   | 248037/371472 [8:41:41<9:10:31,  3.74it/s]
 67%|██████▋   | 248038/371472 [8:41:41<8:51:42,  3.87it/s]
 67%|██████▋   | 248039/371472 [8:41:41<9:03:30,  3.79it/s]
 67%|██████▋   | 248040/371472 [8:41:42<9:11:28,  3.73it/s]
                                                           
{'loss': 3.0031, 'learning_rate': 3.992113598655433e-07, 'epoch': 10.68}
+
 67%|██████▋   | 248040/371472 [8:41:42<9:11:28,  3.73it/s]
 67%|██████▋   | 248041/371472 [8:41:42<9:14:48,  3.71it/s]
 67%|██████▋   | 248042/371472 [8:41:42<9:36:34,  3.57it/s]
 67%|██████▋   | 248043/371472 [8:41:43<9:15:56,  3.70it/s]
 67%|██████▋   | 248044/371472 [8:41:43<9:07:31,  3.76it/s]
 67%|██████▋   | 248045/371472 [8:41:43<9:13:32,  3.72it/s]
 67%|██████▋   | 248046/371472 [8:41:43<9:00:28,  3.81it/s]
 67%|██████▋   | 248047/371472 [8:41:44<9:10:00,  3.74it/s]
 67%|██████▋   | 248048/371472 [8:41:44<8:49:47,  3.88it/s]
 67%|██████▋   | 248049/371472 [8:41:44<10:06:11,  3.39it/s]
 67%|██████▋   | 248050/371472 [8:41:44<9:40:28,  3.54it/s] 
 67%|██████▋   | 248051/371472 [8:41:45<9:43:06,  3.53it/s]
 67%|██████▋   | 248052/371472 [8:41:45<9:37:46,  3.56it/s]
 67%|██████▋   | 248053/371472 [8:41:45<10:47:05,  3.18it/s]
 67%|██████▋   | 248054/371472 [8:41:46<9:59:59,  3.43it/s] 
 67%|██████▋   | 248055/371472 [8:41:46<10:01:30,  3.42it/s]
 67%|██████▋   | 248056/371472 [8:41:46<9:38:31,  3.56it/s] 
 67%|██████▋   | 248057/371472 [8:41:47<9:46:03,  3.51it/s]
 67%|██████▋   | 248058/371472 [8:41:47<9:45:27,  3.51it/s]
 67%|██████▋   | 248059/371472 [8:41:47<10:42:44,  3.20it/s]
 67%|██████▋   | 248060/371472 [8:41:47<10:12:45,  3.36it/s]
                                                            
{'loss': 2.9029, 'learning_rate': 3.991628778900644e-07, 'epoch': 10.68}
+
 67%|██████▋   | 248060/371472 [8:41:47<10:12:45,  3.36it/s]
 67%|██████▋   | 248061/371472 [8:41:48<9:58:56,  3.43it/s] 
 67%|██████▋   | 248062/371472 [8:41:48<9:53:34,  3.47it/s]
 67%|██████▋   | 248063/371472 [8:41:48<9:20:19,  3.67it/s]
 67%|██████▋   | 248064/371472 [8:41:49<9:41:16,  3.54it/s]
 67%|██████▋   | 248065/371472 [8:41:49<9:28:05,  3.62it/s]
 67%|██████▋   | 248066/371472 [8:41:49<9:31:21,  3.60it/s]
 67%|██████▋   | 248067/371472 [8:41:49<9:19:07,  3.68it/s]
 67%|██████▋   | 248068/371472 [8:41:50<9:06:59,  3.76it/s]
 67%|██████▋   | 248069/371472 [8:41:50<9:11:07,  3.73it/s]
 67%|██████▋   | 248070/371472 [8:41:50<9:20:23,  3.67it/s]
 67%|██████▋   | 248071/371472 [8:41:50<9:11:48,  3.73it/s]
 67%|██████▋   | 248072/371472 [8:41:51<9:03:50,  3.78it/s]
 67%|██████▋   | 248073/371472 [8:41:51<9:04:22,  3.78it/s]
 67%|██████▋   | 248074/371472 [8:41:51<9:33:59,  3.58it/s]
 67%|██████▋   | 248075/371472 [8:41:52<9:15:15,  3.70it/s]
 67%|██████▋   | 248076/371472 [8:41:52<9:04:39,  3.78it/s]
 67%|██████▋   | 248077/371472 [8:41:52<9:03:48,  3.78it/s]
 67%|██████▋   | 248078/371472 [8:41:52<9:03:53,  3.78it/s]
 67%|██████▋   | 248079/371472 [8:41:53<8:52:17,  3.86it/s]
 67%|██████▋   | 248080/371472 [8:41:53<8:53:36,  3.85it/s]
                                                           
{'loss': 3.0489, 'learning_rate': 3.991143959145855e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248080/371472 [8:41:53<8:53:36,  3.85it/s]
 67%|██████▋   | 248081/371472 [8:41:53<9:37:06,  3.56it/s]
 67%|██████▋   | 248082/371472 [8:41:53<9:32:40,  3.59it/s]
 67%|██████▋   | 248083/371472 [8:41:54<9:54:10,  3.46it/s]
 67%|██████▋   | 248084/371472 [8:41:54<10:02:29,  3.41it/s]
 67%|██████▋   | 248085/371472 [8:41:54<9:38:01,  3.56it/s] 
 67%|██████▋   | 248086/371472 [8:41:55<10:45:13,  3.19it/s]
 67%|██████▋   | 248087/371472 [8:41:55<10:29:55,  3.26it/s]
 67%|██████▋   | 248088/371472 [8:41:55<10:16:28,  3.34it/s]
 67%|██████▋   | 248089/371472 [8:41:56<10:01:41,  3.42it/s]
 67%|██████▋   | 248090/371472 [8:41:56<9:53:25,  3.47it/s] 
 67%|██████▋   | 248091/371472 [8:41:56<9:55:18,  3.45it/s]
 67%|██████▋   | 248092/371472 [8:41:56<9:42:00,  3.53it/s]
 67%|██████▋   | 248093/371472 [8:41:57<9:59:08,  3.43it/s]
 67%|██████▋   | 248094/371472 [8:41:57<9:57:13,  3.44it/s]
 67%|██████▋   | 248095/371472 [8:41:57<9:35:35,  3.57it/s]
 67%|██████▋   | 248096/371472 [8:41:57<9:43:49,  3.52it/s]
 67%|██████▋   | 248097/371472 [8:41:58<9:52:45,  3.47it/s]
 67%|██████▋   | 248098/371472 [8:41:58<9:44:32,  3.52it/s]
 67%|██████▋   | 248099/371472 [8:41:58<9:19:02,  3.68it/s]
 67%|██████▋   | 248100/371472 [8:41:59<8:55:33,  3.84it/s]
                                                           
{'loss': 2.6996, 'learning_rate': 3.990659139391066e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248100/371472 [8:41:59<8:55:33,  3.84it/s]
 67%|██████▋   | 248101/371472 [8:41:59<9:18:25,  3.68it/s]
 67%|██████▋   | 248102/371472 [8:41:59<9:37:54,  3.56it/s]
 67%|██████▋   | 248103/371472 [8:42:00<10:45:49,  3.18it/s]
 67%|██████▋   | 248104/371472 [8:42:00<11:07:58,  3.08it/s]
 67%|██████▋   | 248105/371472 [8:42:00<10:22:02,  3.31it/s]
 67%|██████▋   | 248106/371472 [8:42:00<9:45:26,  3.51it/s] 
 67%|██████▋   | 248107/371472 [8:42:01<9:42:13,  3.53it/s]
 67%|██████▋   | 248108/371472 [8:42:01<9:31:47,  3.60it/s]
 67%|██████▋   | 248109/371472 [8:42:01<10:18:27,  3.32it/s]
 67%|██████▋   | 248110/371472 [8:42:02<10:26:26,  3.28it/s]
 67%|██████▋   | 248111/371472 [8:42:02<9:56:57,  3.44it/s] 
 67%|██████▋   | 248112/371472 [8:42:02<10:07:16,  3.39it/s]
 67%|██████▋   | 248113/371472 [8:42:02<10:08:43,  3.38it/s]
 67%|██████▋   | 248114/371472 [8:42:03<10:01:41,  3.42it/s]
 67%|██████▋   | 248115/371472 [8:42:03<9:47:18,  3.50it/s] 
 67%|██████▋   | 248116/371472 [8:42:03<9:41:24,  3.54it/s]
 67%|██████▋   | 248117/371472 [8:42:04<9:16:26,  3.69it/s]
 67%|██████▋   | 248118/371472 [8:42:04<11:03:55,  3.10it/s]
 67%|██████▋   | 248119/371472 [8:42:04<10:31:24,  3.26it/s]
 67%|██████▋   | 248120/371472 [8:42:04<9:46:17,  3.51it/s] 
                                                           
{'loss': 2.5997, 'learning_rate': 3.9901743196362775e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248120/371472 [8:42:04<9:46:17,  3.51it/s]
 67%|██████▋   | 248121/371472 [8:42:05<9:40:50,  3.54it/s]
 67%|██████▋   | 248122/371472 [8:42:05<9:35:33,  3.57it/s]
 67%|██████▋   | 248123/371472 [8:42:05<9:19:29,  3.67it/s]
 67%|██████▋   | 248124/371472 [8:42:06<9:15:40,  3.70it/s]
 67%|██████▋   | 248125/371472 [8:42:06<9:53:02,  3.47it/s]
 67%|██████▋   | 248126/371472 [8:42:06<9:26:41,  3.63it/s]
 67%|██████▋   | 248127/371472 [8:42:06<9:19:00,  3.68it/s]
 67%|██████▋   | 248128/371472 [8:42:07<9:27:41,  3.62it/s]
 67%|██████▋   | 248129/371472 [8:42:07<10:23:08,  3.30it/s]
 67%|██████▋   | 248130/371472 [8:42:07<10:46:07,  3.18it/s]
 67%|██████▋   | 248131/371472 [8:42:08<10:19:45,  3.32it/s]
 67%|██████▋   | 248132/371472 [8:42:08<9:45:29,  3.51it/s] 
 67%|██████▋   | 248133/371472 [8:42:08<9:35:25,  3.57it/s]
 67%|██████▋   | 248134/371472 [8:42:08<9:35:13,  3.57it/s]
 67%|██████▋   | 248135/371472 [8:42:09<9:59:05,  3.43it/s]
 67%|██████▋   | 248136/371472 [8:42:09<9:59:55,  3.43it/s]
 67%|██████▋   | 248137/371472 [8:42:09<9:59:55,  3.43it/s]
 67%|██████▋   | 248138/371472 [8:42:10<9:57:12,  3.44it/s]
 67%|██████▋   | 248139/371472 [8:42:10<9:39:54,  3.54it/s]
 67%|██████▋   | 248140/371472 [8:42:10<9:44:53,  3.51it/s]
                                                           
{'loss': 2.9318, 'learning_rate': 3.9896894998814877e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248140/371472 [8:42:10<9:44:53,  3.51it/s]
 67%|██████▋   | 248141/371472 [8:42:10<9:37:36,  3.56it/s]
 67%|██████▋   | 248142/371472 [8:42:11<9:25:41,  3.63it/s]
 67%|█████��▋   | 248143/371472 [8:42:11<10:28:59,  3.27it/s]
 67%|██████▋   | 248144/371472 [8:42:11<10:22:34,  3.30it/s]
 67%|██████▋   | 248145/371472 [8:42:12<9:49:40,  3.49it/s] 
 67%|██████▋   | 248146/371472 [8:42:12<9:19:29,  3.67it/s]
 67%|██████▋   | 248147/371472 [8:42:12<9:50:44,  3.48it/s]
 67%|██████▋   | 248148/371472 [8:42:12<9:44:57,  3.51it/s]
 67%|██████▋   | 248149/371472 [8:42:13<9:21:46,  3.66it/s]
 67%|██████▋   | 248150/371472 [8:42:13<9:14:03,  3.71it/s]
 67%|██████▋   | 248151/371472 [8:42:13<9:59:06,  3.43it/s]
 67%|██████▋   | 248152/371472 [8:42:14<9:33:15,  3.59it/s]
 67%|██████▋   | 248153/371472 [8:42:14<9:30:27,  3.60it/s]
 67%|██████▋   | 248154/371472 [8:42:14<9:30:27,  3.60it/s]
 67%|██████▋   | 248155/371472 [8:42:14<9:51:25,  3.48it/s]
 67%|██████▋   | 248156/371472 [8:42:15<9:24:05,  3.64it/s]
 67%|██████▋   | 248157/371472 [8:42:15<9:31:02,  3.60it/s]
 67%|██████▋   | 248158/371472 [8:42:15<9:55:19,  3.45it/s]
 67%|██████▋   | 248159/371472 [8:42:16<9:23:08,  3.65it/s]
 67%|██████▋   | 248160/371472 [8:42:16<9:39:34,  3.55it/s]
                                                           
{'loss': 2.8338, 'learning_rate': 3.9892046801266995e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248160/371472 [8:42:16<9:39:34,  3.55it/s]
 67%|██████▋   | 248161/371472 [8:42:16<10:15:27,  3.34it/s]
 67%|██████▋   | 248162/371472 [8:42:16<9:44:32,  3.52it/s] 
 67%|██████▋   | 248163/371472 [8:42:17<9:38:34,  3.55it/s]
 67%|██████▋   | 248164/371472 [8:42:17<9:06:51,  3.76it/s]
 67%|██████▋   | 248165/371472 [8:42:17<8:48:53,  3.89it/s]
 67%|██████▋   | 248166/371472 [8:42:17<8:57:50,  3.82it/s]
 67%|██████▋   | 248167/371472 [8:42:18<9:51:06,  3.48it/s]
 67%|██████▋   | 248168/371472 [8:42:18<10:02:08,  3.41it/s]
 67%|██████▋   | 248169/371472 [8:42:18<9:40:19,  3.54it/s] 
 67%|██████▋   | 248170/371472 [8:42:19<9:35:06,  3.57it/s]
 67%|██████▋   | 248171/371472 [8:42:19<9:46:25,  3.50it/s]
 67%|██████▋   | 248172/371472 [8:42:19<9:27:41,  3.62it/s]
 67%|██████▋   | 248173/371472 [8:42:19<9:21:54,  3.66it/s]
 67%|██████▋   | 248174/371472 [8:42:20<9:23:36,  3.65it/s]
 67%|██████▋   | 248175/371472 [8:42:20<9:08:45,  3.74it/s]
 67%|██████▋   | 248176/371472 [8:42:20<8:41:51,  3.94it/s]
 67%|██████▋   | 248177/371472 [8:42:20<8:51:37,  3.87it/s]
 67%|██████▋   | 248178/371472 [8:42:21<9:02:06,  3.79it/s]
 67%|██████▋   | 248179/371472 [8:42:21<9:02:09,  3.79it/s]
 67%|██████▋   | 248180/371472 [8:42:21<8:50:06,  3.88it/s]
                                                           
{'loss': 2.8102, 'learning_rate': 3.98871986037191e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248180/371472 [8:42:21<8:50:06,  3.88it/s]
 67%|██████▋   | 248181/371472 [8:42:22<8:57:34,  3.82it/s]
 67%|██████▋   | 248182/371472 [8:42:22<8:59:49,  3.81it/s]
 67%|██████▋   | 248183/371472 [8:42:22<8:41:35,  3.94it/s]
 67%|██████▋   | 248184/371472 [8:42:22<8:46:11,  3.91it/s]
 67%|██████▋   | 248185/371472 [8:42:23<9:54:01,  3.46it/s]
 67%|██████▋   | 248186/371472 [8:42:23<9:24:31,  3.64it/s]
 67%|██████▋   | 248187/371472 [8:42:23<9:48:02,  3.49it/s]
 67%|██████▋   | 248188/371472 [8:42:23<9:38:45,  3.55it/s]
 67%|██████▋   | 248189/371472 [8:42:24<9:31:37,  3.59it/s]
 67%|██████▋   | 248190/371472 [8:42:24<9:09:22,  3.74it/s]
 67%|██████▋   | 248191/371472 [8:42:24<9:43:57,  3.52it/s]
 67%|██████▋   | 248192/371472 [8:42:25<9:16:47,  3.69it/s]
 67%|██████▋   | 248193/371472 [8:42:25<9:20:41,  3.66it/s]
 67%|██████▋   | 248194/371472 [8:42:25<9:28:51,  3.61it/s]
 67%|██████▋   | 248195/371472 [8:42:25<9:08:34,  3.75it/s]
 67%|██████▋   | 248196/371472 [8:42:26<9:32:45,  3.59it/s]
 67%|██████▋   | 248197/371472 [8:42:26<9:23:05,  3.65it/s]
 67%|██████▋   | 248198/371472 [8:42:26<9:27:13,  3.62it/s]
 67%|██████▋   | 248199/371472 [8:42:26<9:27:12,  3.62it/s]
 67%|██████▋   | 248200/371472 [8:42:27<9:07:28,  3.75it/s]
                                                           
{'loss': 2.8166, 'learning_rate': 3.9882350406171215e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248200/371472 [8:42:27<9:07:28,  3.75it/s]
 67%|██████▋   | 248201/371472 [8:42:27<8:59:03,  3.81it/s]
 67%|██████▋   | 248202/371472 [8:42:27<9:32:38,  3.59it/s]
 67%|██████▋   | 248203/371472 [8:42:28<9:22:28,  3.65it/s]
 67%|██████▋   | 248204/371472 [8:42:28<9:11:36,  3.72it/s]
 67%|██████▋   | 248205/371472 [8:42:28<9:05:19,  3.77it/s]
 67%|██████▋   | 248206/371472 [8:42:28<9:04:20,  3.77it/s]
 67%|██████▋   | 248207/371472 [8:42:29<8:41:45,  3.94it/s]
 67%|██████▋   | 248208/371472 [8:42:29<8:43:21,  3.93it/s]
 67%|██████▋   | 248209/371472 [8:42:29<9:25:14,  3.63it/s]
 67%|██████▋   | 248210/371472 [8:42:29<9:43:42,  3.52it/s]
 67%|██████▋   | 248211/371472 [8:42:30<9:23:14,  3.65it/s]
 67%|██████▋   | 248212/371472 [8:42:30<10:27:04,  3.28it/s]
 67%|██████▋   | 248213/371472 [8:42:30<9:54:46,  3.45it/s] 
 67%|██████▋   | 248214/371472 [8:42:31<10:39:04,  3.21it/s]
 67%|██████▋   | 248215/371472 [8:42:31<10:08:15,  3.38it/s]
 67%|██████▋   | 248216/371472 [8:42:31<9:42:56,  3.52it/s] 
 67%|██████▋   | 248217/371472 [8:42:32<9:56:12,  3.45it/s]
 67%|██████▋   | 248218/371472 [8:42:32<9:36:10,  3.57it/s]
 67%|██████▋   | 248219/371472 [8:42:32<9:53:51,  3.46it/s]
 67%|██████▋   | 248220/371472 [8:42:32<9:40:26,  3.54it/s]
                                                           
{'loss': 3.0341, 'learning_rate': 3.987750220862332e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248220/371472 [8:42:32<9:40:26,  3.54it/s]
 67%|██████▋   | 248221/371472 [8:42:33<9:46:53,  3.50it/s]
 67%|██████▋   | 248222/371472 [8:42:33<10:11:20,  3.36it/s]
 67%|██████▋   | 248223/371472 [8:42:33<9:43:28,  3.52it/s] 
 67%|██████▋   | 248224/371472 [8:42:34<10:11:15,  3.36it/s]
 67%|██████▋   | 248225/371472 [8:42:34<10:17:27,  3.33it/s]
 67%|██████▋   | 248226/371472 [8:42:34<10:11:49,  3.36it/s]
 67%|██████▋   | 248227/371472 [8:42:34<9:49:45,  3.48it/s] 
 67%|██████▋   | 248228/371472 [8:42:35<10:32:48,  3.25it/s]
 67%|██████▋   | 248229/371472 [8:42:35<10:07:16,  3.38it/s]
 67%|██████▋   | 248230/371472 [8:42:35<9:52:29,  3.47it/s] 
 67%|██████▋   | 248231/371472 [8:42:36<9:40:46,  3.54it/s]
 67%|██████▋   | 248232/371472 [8:42:36<9:14:42,  3.70it/s]
 67%|██████▋   | 248233/371472 [8:42:36<9:20:36,  3.66it/s]
 67%|██████▋   | 248234/371472 [8:42:36<9:24:22,  3.64it/s]
 67%|██████▋   | 248235/371472 [8:42:37<9:00:27,  3.80it/s]
 67%|██████▋   | 248236/371472 [8:42:37<9:03:09,  3.78it/s]
 67%|██████▋   | 248237/371472 [8:42:37<8:57:43,  3.82it/s]
 67%|██████▋   | 248238/371472 [8:42:37<9:11:54,  3.72it/s]
 67%|██████▋   | 248239/371472 [8:42:38<9:27:26,  3.62it/s]
 67%|██████▋   | 248240/371472 [8:42:38<9:23:53,  3.64it/s]
                                                           
{'loss': 2.9628, 'learning_rate': 3.987265401107544e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248240/371472 [8:42:38<9:23:53,  3.64it/s]
 67%|██████▋   | 248241/371472 [8:42:38<9:27:47,  3.62it/s]
 67%|██████▋   | 248242/371472 [8:42:39<9:47:14,  3.50it/s]
 67%|██████▋   | 248243/371472 [8:42:39<9:40:37,  3.54it/s]
 67%|██████▋   | 248244/371472 [8:42:39<10:14:15,  3.34it/s]
 67%|██████▋   | 248245/371472 [8:42:39<10:04:25,  3.40it/s]
 67%|██████▋   | 248246/371472 [8:42:40<9:43:17,  3.52it/s] 
 67%|██████▋   | 248247/371472 [8:42:40<9:13:01,  3.71it/s]
 67%|██████▋   | 248248/371472 [8:42:40<9:02:42,  3.78it/s]
 67%|██████▋   | 248249/371472 [8:42:40<9:02:12,  3.79it/s]
 67%|██████▋   | 248250/371472 [8:42:41<9:53:39,  3.46it/s]
 67%|██████▋   | 248251/371472 [8:42:41<9:22:30,  3.65it/s]
 67%|██████▋   | 248252/371472 [8:42:41<9:20:17,  3.67it/s]
 67%|██████▋   | 248253/371472 [8:42:42<9:16:07,  3.69it/s]
 67%|██████▋   | 248254/371472 [8:42:42<9:23:15,  3.65it/s]
 67%|██████▋   | 248255/371472 [8:42:42<9:21:15,  3.66it/s]
 67%|██████▋   | 248256/371472 [8:42:42<9:29:29,  3.61it/s]
 67%|██████▋   | 248257/371472 [8:42:43<9:10:03,  3.73it/s]
 67%|██████▋   | 248258/371472 [8:42:43<9:03:50,  3.78it/s]
 67%|██████▋   | 248259/371472 [8:42:43<9:05:50,  3.76it/s]
 67%|██████▋   | 248260/371472 [8:42:43<9:02:43,  3.78it/s]
                                                           
{'loss': 3.0161, 'learning_rate': 3.9867805813527547e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248260/371472 [8:42:43<9:02:43,  3.78it/s]
 67%|██████▋   | 248261/371472 [8:42:44<9:13:32,  3.71it/s]
 67%|██████▋   | 248262/371472 [8:42:44<9:21:36,  3.66it/s]
 67%|██████▋   | 248263/371472 [8:42:44<9:31:24,  3.59it/s]
 67%|██████▋   | 248264/371472 [8:42:45<9:32:40,  3.59it/s]
 67%|██████▋   | 248265/371472 [8:42:45<9:38:51,  3.55it/s]
 67%|██████▋   | 248266/371472 [8:42:45<9:21:03,  3.66it/s]
 67%|██████▋   | 248267/371472 [8:42:45<9:26:42,  3.62it/s]
 67%|██████▋   | 248268/371472 [8:42:46<9:15:34,  3.70it/s]
 67%|██████▋   | 248269/371472 [8:42:46<9:18:25,  3.68it/s]
 67%|██████▋   | 248270/371472 [8:42:46<10:10:29,  3.36it/s]
 67%|██████▋   | 248271/371472 [8:42:47<9:46:20,  3.50it/s] 
 67%|██████▋   | 248272/371472 [8:42:47<9:33:45,  3.58it/s]
 67%|██████▋   | 248273/371472 [8:42:47<9:47:02,  3.50it/s]
 67%|██████▋   | 248274/371472 [8:42:47<10:01:38,  3.41it/s]
 67%|██████▋   | 248275/371472 [8:42:48<9:45:33,  3.51it/s] 
 67%|██████▋   | 248276/371472 [8:42:48<9:19:12,  3.67it/s]
 67%|██████▋   | 248277/371472 [8:42:48<9:22:06,  3.65it/s]
 67%|██████▋   | 248278/371472 [8:42:48<9:05:14,  3.77it/s]
 67%|██████▋   | 248279/371472 [8:42:49<8:50:59,  3.87it/s]
 67%|██████▋   | 248280/371472 [8:42:49<9:06:26,  3.76it/s]
                                                           
{'loss': 2.8523, 'learning_rate': 3.986295761597966e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248280/371472 [8:42:49<9:06:26,  3.76it/s]
 67%|██████▋   | 248281/371472 [8:42:49<9:10:54,  3.73it/s]
 67%|██████▋   | 248282/371472 [8:42:50<9:01:54,  3.79it/s]
 67%|██████▋   | 248283/371472 [8:42:50<9:02:25,  3.79it/s]
 67%|██████▋   | 248284/371472 [8:42:50<8:54:12,  3.84it/s]
 67%|██████▋   | 248285/371472 [8:42:50<9:13:36,  3.71it/s]
 67%|██████▋   | 248286/371472 [8:42:51<8:59:02,  3.81it/s]
 67%|██████▋   | 248287/371472 [8:42:51<8:48:17,  3.89it/s]
 67%|██████▋   | 248288/371472 [8:42:51<8:53:45,  3.85it/s]
 67%|██████▋   | 248289/371472 [8:42:51<8:57:30,  3.82it/s]
 67%|██████▋   | 248290/371472 [8:42:52<8:49:21,  3.88it/s]
 67%|██████▋   | 248291/371472 [8:42:52<8:31:08,  4.02it/s]
 67%|██████▋   | 248292/371472 [8:42:52<8:32:41,  4.00it/s]
 67%|██████▋   | 248293/371472 [8:42:52<8:44:04,  3.92it/s]
 67%|██████▋   | 248294/371472 [8:42:53<9:01:58,  3.79it/s]
 67%|██████▋   | 248295/371472 [8:42:53<9:16:59,  3.69it/s]
 67%|██████▋   | 248296/371472 [8:42:53<9:06:04,  3.76it/s]
 67%|██████▋   | 248297/371472 [8:42:53<8:46:49,  3.90it/s]
 67%|██████▋   | 248298/371472 [8:42:54<9:26:16,  3.63it/s]
 67%|██████▋   | 248299/371472 [8:42:54<9:07:20,  3.75it/s]
 67%|██████▋   | 248300/371472 [8:42:54<9:23:14,  3.64it/s]
                                                           
{'loss': 2.8777, 'learning_rate': 3.9858109418431766e-07, 'epoch': 10.69}
+
 67%|██████▋   | 248300/371472 [8:42:54<9:23:14,  3.64it/s]
 67%|██████▋   | 248301/371472 [8:42:55<9:10:28,  3.73it/s]
 67%|██████▋   | 248302/371472 [8:42:55<9:25:48,  3.63it/s]
 67%|██████▋   | 248303/371472 [8:42:55<9:18:49,  3.67it/s]
 67%|██████▋   | 248304/371472 [8:42:55<9:14:24,  3.70it/s]
 67%|██████▋   | 248305/371472 [8:42:56<9:38:35,  3.55it/s]
 67%|██████▋   | 248306/371472 [8:42:56<9:09:52,  3.73it/s]
 67%|██████▋   | 248307/371472 [8:42:56<9:06:30,  3.76it/s]
 67%|██████▋   | 248308/371472 [8:42:56<9:01:54,  3.79it/s]
 67%|██████▋   | 248309/371472 [8:42:57<9:41:35,  3.53it/s]
 67%|██████▋   | 248310/371472 [8:42:57<10:01:12,  3.41it/s]
 67%|██████▋   | 248311/371472 [8:42:57<10:23:02,  3.29it/s]
 67%|██████▋   | 248312/371472 [8:42:58<9:53:48,  3.46it/s] 
 67%|██████▋   | 248313/371472 [8:42:58<10:03:55,  3.40it/s]
 67%|██████▋   | 248314/371472 [8:42:58<9:57:59,  3.43it/s] 
 67%|██████▋   | 248315/371472 [8:42:58<9:33:36,  3.58it/s]
 67%|██████▋   | 248316/371472 [8:42:59<10:13:56,  3.34it/s]
 67%|██████▋   | 248317/371472 [8:42:59<10:12:29,  3.35it/s]
 67%|██████▋   | 248318/371472 [8:42:59<10:15:43,  3.33it/s]
 67%|██████▋   | 248319/371472 [8:43:00<9:53:00,  3.46it/s] 
 67%|██████▋   | 248320/371472 [8:43:00<10:03:36,  3.40it/s]
                                                            
{'loss': 2.9585, 'learning_rate': 3.9853261220883884e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248320/371472 [8:43:00<10:03:36,  3.40it/s]
 67%|██████▋   | 248321/371472 [8:43:00<10:02:59,  3.40it/s]
 67%|██████▋   | 248322/371472 [8:43:01<9:43:47,  3.52it/s] 
 67%|██████▋   | 248323/371472 [8:43:01<10:06:43,  3.38it/s]
 67%|██████▋   | 248324/371472 [8:43:01<9:39:09,  3.54it/s] 
 67%|██████▋   | 248325/371472 [8:43:01<9:51:39,  3.47it/s]
 67%|██████▋   | 248326/371472 [8:43:02<9:38:35,  3.55it/s]
 67%|██████▋   | 248327/371472 [8:43:02<9:38:17,  3.55it/s]
 67%|██████▋   | 248328/371472 [8:43:02<9:58:50,  3.43it/s]
 67%|██████▋   | 248329/371472 [8:43:03<10:11:00,  3.36it/s]
 67%|██████▋   | 248330/371472 [8:43:03<9:59:14,  3.42it/s] 
 67%|██████▋   | 248331/371472 [8:43:03<9:47:43,  3.49it/s]
 67%|██████▋   | 248332/371472 [8:43:03<9:47:44,  3.49it/s]
 67%|██████▋   | 248333/371472 [8:43:04<9:37:39,  3.55it/s]
 67%|██████▋   | 248334/371472 [8:43:04<9:32:58,  3.58it/s]
 67%|██████▋   | 248335/371472 [8:43:04<9:42:51,  3.52it/s]
 67%|██████▋   | 248336/371472 [8:43:05<9:44:53,  3.51it/s]
 67%|██████▋   | 248337/371472 [8:43:05<9:23:02,  3.64it/s]
 67%|██████▋   | 248338/371472 [8:43:05<9:56:39,  3.44it/s]
 67%|██████▋   | 248339/371472 [8:43:05<10:12:00,  3.35it/s]
 67%|██████▋   | 248340/371472 [8:43:06<10:20:19,  3.31it/s]
                                                            
{'loss': 2.6922, 'learning_rate': 3.9848413023335986e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248340/371472 [8:43:06<10:20:19,  3.31it/s]
 67%|██████▋   | 248341/371472 [8:43:06<10:35:57,  3.23it/s]
 67%|██████▋   | 248342/371472 [8:43:06<10:26:43,  3.27it/s]
 67%|██████▋   | 248343/371472 [8:43:07<10:17:20,  3.32it/s]
 67%|██████▋   | 248344/371472 [8:43:07<10:02:55,  3.40it/s]
 67%|██████▋   | 248345/371472 [8:43:07<10:22:19,  3.30it/s]
 67%|██████▋   | 248346/371472 [8:43:08<9:56:48,  3.44it/s] 
 67%|██████▋   | 248347/371472 [8:43:08<9:33:15,  3.58it/s]
 67%|██████▋   | 248348/371472 [8:43:08<9:28:14,  3.61it/s]
 67%|██████▋   | 248349/371472 [8:43:08<9:24:34,  3.63it/s]
 67%|██████▋   | 248350/371472 [8:43:09<9:20:45,  3.66it/s]
 67%|██████▋   | 248351/371472 [8:43:09<9:11:16,  3.72it/s]
 67%|██████▋   | 248352/371472 [8:43:09<8:48:48,  3.88it/s]
 67%|██████▋   | 248353/371472 [8:43:09<8:33:42,  3.99it/s]
 67%|██████▋   | 248354/371472 [8:43:10<8:53:41,  3.84it/s]
 67%|██████▋   | 248355/371472 [8:43:10<9:27:52,  3.61it/s]
 67%|██████▋   | 248356/371472 [8:43:10<9:25:50,  3.63it/s]
 67%|██████▋   | 248357/371472 [8:43:11<9:44:22,  3.51it/s]
 67%|██████▋   | 248358/371472 [8:43:11<9:19:06,  3.67it/s]
 67%|██████▋   | 248359/371472 [8:43:11<9:11:45,  3.72it/s]
 67%|██████▋   | 248360/371472 [8:43:12<11:29:12,  2.98it/s]
                                                            
{'loss': 2.933, 'learning_rate': 3.984356482578811e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248360/371472 [8:43:12<11:29:12,  2.98it/s]
 67%|██████▋   | 248361/371472 [8:43:12<10:39:30,  3.21it/s]
 67%|██████▋   | 248362/371472 [8:43:12<9:52:20,  3.46it/s] 
 67%|██████▋   | 248363/371472 [8:43:12<9:31:34,  3.59it/s]
 67%|██████▋   | 248364/371472 [8:43:13<9:11:54,  3.72it/s]
 67%|██████▋   | 248365/371472 [8:43:13<9:38:10,  3.55it/s]
 67%|██████▋   | 248366/371472 [8:43:13<9:19:18,  3.67it/s]
 67%|██████▋   | 248367/371472 [8:43:13<9:26:08,  3.62it/s]
 67%|██████▋   | 248368/371472 [8:43:14<9:53:40,  3.46it/s]
 67%|██████▋   | 248369/371472 [8:43:14<9:34:39,  3.57it/s]
 67%|██████▋   | 248370/371472 [8:43:14<10:12:03,  3.35it/s]
 67%|██████▋   | 248371/371472 [8:43:15<10:19:31,  3.31it/s]
 67%|██████▋   | 248372/371472 [8:43:15<9:37:40,  3.55it/s] 
 67%|██████▋   | 248373/371472 [8:43:15<9:37:48,  3.55it/s]
 67%|██████▋   | 248374/371472 [8:43:15<9:21:38,  3.65it/s]
 67%|██████▋   | 248375/371472 [8:43:16<9:15:53,  3.69it/s]
 67%|██████▋   | 248376/371472 [8:43:16<9:43:43,  3.51it/s]
 67%|██████▋   | 248377/371472 [8:43:16<9:41:29,  3.53it/s]
 67%|██████▋   | 248378/371472 [8:43:16<9:17:47,  3.68it/s]
 67%|██████▋   | 248379/371472 [8:43:17<9:06:28,  3.75it/s]
 67%|██████▋   | 248380/371472 [8:43:17<9:18:04,  3.68it/s]
                                                           
{'loss': 2.8785, 'learning_rate': 3.983871662824021e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248380/371472 [8:43:17<9:18:04,  3.68it/s]
 67%|██████▋   | 248381/371472 [8:43:17<8:55:24,  3.83it/s]
 67%|██████▋   | 248382/371472 [8:43:18<8:54:41,  3.84it/s]
 67%|██████▋   | 248383/371472 [8:43:18<9:00:40,  3.79it/s]
 67%|██████▋   | 248384/371472 [8:43:18<8:53:40,  3.84it/s]
 67%|█████��▋   | 248385/371472 [8:43:18<8:48:07,  3.88it/s]
 67%|██████▋   | 248386/371472 [8:43:19<8:49:29,  3.87it/s]
 67%|██████▋   | 248387/371472 [8:43:19<8:51:51,  3.86it/s]
 67%|██████▋   | 248388/371472 [8:43:19<9:31:56,  3.59it/s]
 67%|██████▋   | 248389/371472 [8:43:19<9:22:45,  3.65it/s]
 67%|██████▋   | 248390/371472 [8:43:20<9:50:18,  3.48it/s]
 67%|██████▋   | 248391/371472 [8:43:20<9:36:47,  3.56it/s]
 67%|██████▋   | 248392/371472 [8:43:20<9:43:02,  3.52it/s]
 67%|██████▋   | 248393/371472 [8:43:21<9:25:01,  3.63it/s]
 67%|██████▋   | 248394/371472 [8:43:21<10:30:35,  3.25it/s]
 67%|██████▋   | 248395/371472 [8:43:21<10:33:06,  3.24it/s]
 67%|██████▋   | 248396/371472 [8:43:21<10:20:55,  3.30it/s]
 67%|██████▋   | 248397/371472 [8:43:22<10:18:28,  3.32it/s]
 67%|██████▋   | 248398/371472 [8:43:22<10:02:17,  3.41it/s]
 67%|██████▋   | 248399/371472 [8:43:22<9:45:58,  3.50it/s] 
 67%|██████▋   | 248400/371472 [8:43:23<9:44:39,  3.51it/s]
                                                           
{'loss': 2.8783, 'learning_rate': 3.9833868430692323e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248400/371472 [8:43:23<9:44:39,  3.51it/s]
 67%|██████▋   | 248401/371472 [8:43:23<9:12:38,  3.71it/s]
 67%|██████▋   | 248402/371472 [8:43:23<9:42:02,  3.52it/s]
 67%|██████▋   | 248403/371472 [8:43:23<9:30:17,  3.60it/s]
 67%|██████▋   | 248404/371472 [8:43:24<9:15:38,  3.69it/s]
 67%|██████▋   | 248405/371472 [8:43:24<9:24:01,  3.64it/s]
 67%|██████▋   | 248406/371472 [8:43:24<10:01:11,  3.41it/s]
 67%|██████▋   | 248407/371472 [8:43:25<9:53:48,  3.45it/s] 
 67%|██████▋   | 248408/371472 [8:43:25<9:36:42,  3.56it/s]
 67%|██████▋   | 248409/371472 [8:43:25<9:39:23,  3.54it/s]
 67%|██████▋   | 248410/371472 [8:43:25<9:16:17,  3.69it/s]
 67%|██████▋   | 248411/371472 [8:43:26<8:57:50,  3.81it/s]
 67%|██████▋   | 248412/371472 [8:43:26<9:08:42,  3.74it/s]
 67%|██████▋   | 248413/371472 [8:43:26<9:01:46,  3.79it/s]
 67%|██████▋   | 248414/371472 [8:43:26<9:15:36,  3.69it/s]
 67%|██████▋   | 248415/371472 [8:43:27<9:12:03,  3.72it/s]
 67%|██████▋   | 248416/371472 [8:43:27<9:37:44,  3.55it/s]
 67%|██████▋   | 248417/371472 [8:43:27<9:30:19,  3.60it/s]
 67%|██████▋   | 248418/371472 [8:43:28<9:06:40,  3.75it/s]
 67%|██████▋   | 248419/371472 [8:43:28<9:28:21,  3.61it/s]
 67%|██████▋   | 248420/371472 [8:43:28<9:21:48,  3.65it/s]
                                                           
{'loss': 2.9596, 'learning_rate': 3.982902023314443e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248420/371472 [8:43:28<9:21:48,  3.65it/s]
 67%|██████▋   | 248421/371472 [8:43:28<9:04:37,  3.77it/s]
 67%|██████▋   | 248422/371472 [8:43:29<8:50:30,  3.87it/s]
 67%|██████▋   | 248423/371472 [8:43:29<9:26:01,  3.62it/s]
 67%|██████▋   | 248424/371472 [8:43:29<10:09:39,  3.36it/s]
 67%|██████▋   | 248425/371472 [8:43:30<9:51:18,  3.47it/s] 
 67%|██████▋   | 248426/371472 [8:43:30<9:36:33,  3.56it/s]
 67%|██████▋   | 248427/371472 [8:43:30<9:17:20,  3.68it/s]
 67%|██████▋   | 248428/371472 [8:43:30<9:06:07,  3.76it/s]
 67%|██████▋   | 248429/371472 [8:43:31<8:56:16,  3.82it/s]
 67%|██████▋   | 248430/371472 [8:43:31<9:04:23,  3.77it/s]
 67%|██████▋   | 248431/371472 [8:43:31<9:02:39,  3.78it/s]
 67%|██████▋   | 248432/371472 [8:43:31<8:54:37,  3.84it/s]
 67%|██████▋   | 248433/371472 [8:43:32<8:41:05,  3.94it/s]
 67%|██████▋   | 248434/371472 [8:43:32<9:15:57,  3.69it/s]
 67%|██████▋   | 248435/371472 [8:43:32<9:06:08,  3.75it/s]
 67%|██████▋   | 248436/371472 [8:43:32<9:10:49,  3.72it/s]
 67%|██████▋   | 248437/371472 [8:43:33<9:10:07,  3.73it/s]
 67%|██████▋   | 248438/371472 [8:43:33<9:11:46,  3.72it/s]
 67%|██████▋   | 248439/371472 [8:43:33<9:54:21,  3.45it/s]
 67%|██████▋   | 248440/371472 [8:43:34<9:23:33,  3.64it/s]
                                                           
{'loss': 2.8601, 'learning_rate': 3.982417203559655e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248440/371472 [8:43:34<9:23:33,  3.64it/s]
 67%|██████▋   | 248441/371472 [8:43:34<9:19:30,  3.66it/s]
 67%|██████▋   | 248442/371472 [8:43:34<9:41:13,  3.53it/s]
 67%|██████▋   | 248443/371472 [8:43:35<11:56:40,  2.86it/s]
 67%|██████▋   | 248444/371472 [8:43:35<11:20:32,  3.01it/s]
 67%|██████▋   | 248445/371472 [8:43:35<10:42:34,  3.19it/s]
 67%|██████▋   | 248446/371472 [8:43:35<10:44:53,  3.18it/s]
 67%|██████▋   | 248447/371472 [8:43:36<10:06:57,  3.38it/s]
 67%|██████▋   | 248448/371472 [8:43:36<9:43:01,  3.52it/s] 
 67%|██████▋   | 248449/371472 [8:43:36<9:50:41,  3.47it/s]
 67%|██████▋   | 248450/371472 [8:43:37<9:44:15,  3.51it/s]
 67%|██████▋   | 248451/371472 [8:43:37<9:56:02,  3.44it/s]
 67%|██████▋   | 248452/371472 [8:43:37<10:08:41,  3.37it/s]
 67%|██████▋   | 248453/371472 [8:43:37<9:39:12,  3.54it/s] 
 67%|██████▋   | 248454/371472 [8:43:38<9:19:30,  3.66it/s]
 67%|██████▋   | 248455/371472 [8:43:38<10:32:24,  3.24it/s]
 67%|██████▋   | 248456/371472 [8:43:38<10:45:36,  3.18it/s]
 67%|██████▋   | 248457/371472 [8:43:39<10:21:16,  3.30it/s]
 67%|██████▋   | 248458/371472 [8:43:39<10:08:28,  3.37it/s]
 67%|██████▋   | 248459/371472 [8:43:39<10:17:27,  3.32it/s]
 67%|██████▋   | 248460/371472 [8:43:40<9:59:09,  3.42it/s] 
                                                           
{'loss': 2.7852, 'learning_rate': 3.981932383804865e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248460/371472 [8:43:40<9:59:09,  3.42it/s]
 67%|██████▋   | 248461/371472 [8:43:40<10:26:59,  3.27it/s]
 67%|██████▋   | 248462/371472 [8:43:40<9:52:07,  3.46it/s] 
 67%|██████▋   | 248463/371472 [8:43:40<9:58:05,  3.43it/s]
 67%|██████▋   | 248464/371472 [8:43:41<9:33:29,  3.57it/s]
 67%|██████▋   | 248465/371472 [8:43:41<9:12:54,  3.71it/s]
 67%|██████▋   | 248466/371472 [8:43:41<8:56:22,  3.82it/s]
 67%|██████▋   | 248467/371472 [8:43:41<8:55:23,  3.83it/s]
 67%|██████▋   | 248468/371472 [8:43:42<8:45:25,  3.90it/s]
 67%|██████▋   | 248469/371472 [8:43:42<8:47:28,  3.89it/s]
 67%|██████▋   | 248470/371472 [8:43:42<8:49:42,  3.87it/s]
 67%|██████▋   | 248471/371472 [8:43:42<8:35:50,  3.97it/s]
 67%|██████▋   | 248472/371472 [8:43:43<8:51:51,  3.85it/s]
 67%|██████▋   | 248473/371472 [8:43:43<8:47:10,  3.89it/s]
 67%|██████▋   | 248474/371472 [8:43:43<9:36:46,  3.55it/s]
 67%|██████▋   | 248475/371472 [8:43:44<9:14:18,  3.70it/s]
 67%|██████▋   | 248476/371472 [8:43:44<9:16:40,  3.68it/s]
 67%|██████▋   | 248477/371472 [8:43:44<9:02:25,  3.78it/s]
 67%|██████▋   | 248478/371472 [8:43:44<9:35:10,  3.56it/s]
 67%|██████▋   | 248479/371472 [8:43:45<9:19:39,  3.66it/s]
 67%|██████▋   | 248480/371472 [8:43:45<10:01:05,  3.41it/s]
                                                            
{'loss': 2.8542, 'learning_rate': 3.981447564050077e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248480/371472 [8:43:45<10:01:05,  3.41it/s]
 67%|██████▋   | 248481/371472 [8:43:45<10:11:42,  3.35it/s]
 67%|██████▋   | 248482/371472 [8:43:46<10:13:14,  3.34it/s]
 67%|██████▋   | 248483/371472 [8:43:46<9:32:28,  3.58it/s] 
 67%|██████▋   | 248484/371472 [8:43:46<9:17:39,  3.68it/s]
 67%|██████▋   | 248485/371472 [8:43:46<9:36:35,  3.56it/s]
 67%|██████▋   | 248486/371472 [8:43:47<9:25:11,  3.63it/s]
 67%|██████▋   | 248487/371472 [8:43:47<9:54:13,  3.45it/s]
 67%|██████▋   | 248488/371472 [8:43:47<9:19:05,  3.67it/s]
 67%|██████▋   | 248489/371472 [8:43:47<9:07:45,  3.74it/s]
 67%|██████▋   | 248490/371472 [8:43:48<9:24:16,  3.63it/s]
 67%|██████▋   | 248491/371472 [8:43:48<9:41:17,  3.53it/s]
 67%|██████▋   | 248492/371472 [8:43:48<9:40:52,  3.53it/s]
 67%|██████▋   | 248493/371472 [8:43:49<9:59:30,  3.42it/s]
 67%|██████▋   | 248494/371472 [8:43:49<10:22:54,  3.29it/s]
 67%|██████▋   | 248495/371472 [8:43:49<10:04:41,  3.39it/s]
 67%|██████▋   | 248496/371472 [8:43:49<9:26:14,  3.62it/s] 
 67%|██████▋   | 248497/371472 [8:43:50<10:26:28,  3.27it/s]
 67%|██████▋   | 248498/371472 [8:43:50<11:06:46,  3.07it/s]
 67%|██████▋   | 248499/371472 [8:43:51<10:37:54,  3.21it/s]
 67%|██████▋   | 248500/371472 [8:43:51<9:57:43,  3.43it/s] 
                                                           
{'loss': 2.9365, 'learning_rate': 3.9809627442952875e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248500/371472 [8:43:51<9:57:43,  3.43it/s]
 67%|██████▋   | 248501/371472 [8:43:51<10:12:56,  3.34it/s]
 67%|██████▋   | 248502/371472 [8:43:51<9:57:46,  3.43it/s] 
 67%|██████▋   | 248503/371472 [8:43:52<11:13:23,  3.04it/s]
 67%|██████▋   | 248504/371472 [8:43:52<10:29:30,  3.26it/s]
 67%|██████▋   | 248505/371472 [8:43:52<9:51:11,  3.47it/s] 
 67%|██████▋   | 248506/371472 [8:43:53<9:26:17,  3.62it/s]
 67%|██████▋   | 248507/371472 [8:43:53<9:43:18,  3.51it/s]
 67%|██████▋   | 248508/371472 [8:43:53<9:32:11,  3.58it/s]
 67%|██████▋   | 248509/371472 [8:43:53<10:09:02,  3.36it/s]
 67%|██████▋   | 248510/371472 [8:43:54<9:34:34,  3.57it/s] 
 67%|██████▋   | 248511/371472 [8:43:54<9:13:15,  3.70it/s]
 67%|██████▋   | 248512/371472 [8:43:54<9:18:20,  3.67it/s]
 67%|██████▋   | 248513/371472 [8:43:54<8:51:09,  3.86it/s]
 67%|██████▋   | 248514/371472 [8:43:55<9:04:45,  3.76it/s]
 67%|██████▋   | 248515/371472 [8:43:55<9:57:57,  3.43it/s]
 67%|██████▋   | 248516/371472 [8:43:55<9:52:36,  3.46it/s]
 67%|██████▋   | 248517/371472 [8:43:56<9:54:47,  3.45it/s]
 67%|██████▋   | 248518/371472 [8:43:56<9:55:33,  3.44it/s]
 67%|██████▋   | 248519/371472 [8:43:56<9:34:01,  3.57it/s]
 67%|██████▋   | 248520/371472 [8:43:56<9:15:10,  3.69it/s]
                                                           
{'loss': 2.9045, 'learning_rate': 3.9804779245404987e-07, 'epoch': 10.7}
+
 67%|██████▋   | 248520/371472 [8:43:56<9:15:10,  3.69it/s]
 67%|██████▋   | 248521/371472 [8:43:57<9:11:30,  3.72it/s]
 67%|██████▋   | 248522/371472 [8:43:57<9:53:10,  3.45it/s]
 67%|██████▋   | 248523/371472 [8:43:57<9:45:58,  3.50it/s]
 67%|██████▋   | 248524/371472 [8:43:58<9:57:53,  3.43it/s]
 67%|██████▋   | 248525/371472 [8:43:58<10:07:35,  3.37it/s]
 67%|██████▋   | 248526/371472 [8:43:58<10:58:57,  3.11it/s]
 67%|██████▋   | 248527/371472 [8:43:59<10:23:45,  3.29it/s]
 67%|██████▋   | 248528/371472 [8:43:59<10:54:16,  3.13it/s]
 67%|██████▋   | 248529/371472 [8:43:59<12:10:11,  2.81it/s]
 67%|██████▋   | 248530/371472 [8:44:00<11:26:20,  2.99it/s]
 67%|██████▋   | 248531/371472 [8:44:00<10:41:12,  3.20it/s]
 67%|██████▋   | 248532/371472 [8:44:00<10:06:16,  3.38it/s]
 67%|██████▋   | 248533/371472 [8:44:00<9:49:52,  3.47it/s] 
 67%|██████▋   | 248534/371472 [8:44:01<9:30:58,  3.59it/s]
 67%|██████▋   | 248535/371472 [8:44:01<9:25:28,  3.62it/s]
 67%|██████▋   | 248536/371472 [8:44:01<9:19:20,  3.66it/s]
 67%|██████▋   | 248537/371472 [8:44:01<9:10:12,  3.72it/s]
 67%|██████▋   | 248538/371472 [8:44:02<8:58:11,  3.81it/s]
 67%|██████▋   | 248539/371472 [8:44:02<9:05:22,  3.76it/s]
 67%|██████▋   | 248540/371472 [8:44:02<8:51:27,  3.86it/s]
                                                           
{'loss': 2.9377, 'learning_rate': 3.9799931047857094e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248540/371472 [8:44:02<8:51:27,  3.86it/s]
 67%|██████▋   | 248541/371472 [8:44:02<8:41:16,  3.93it/s]
 67%|██████▋   | 248542/371472 [8:44:03<10:23:25,  3.29it/s]
 67%|██████▋   | 248543/371472 [8:44:03<9:46:01,  3.50it/s] 
 67%|██████▋   | 248544/371472 [8:44:03<9:51:18,  3.46it/s]
 67%|██████▋   | 248545/371472 [8:44:04<9:23:39,  3.63it/s]
 67%|██████▋   | 248546/371472 [8:44:04<9:34:27,  3.57it/s]
 67%|██████▋   | 248547/371472 [8:44:04<9:03:02,  3.77it/s]
 67%|██████▋   | 248548/371472 [8:44:04<9:10:45,  3.72it/s]
 67%|██████▋   | 248549/371472 [8:44:05<9:08:42,  3.73it/s]
 67%|██████▋   | 248550/371472 [8:44:05<8:58:57,  3.80it/s]
 67%|██████▋   | 248551/371472 [8:44:05<8:39:23,  3.94it/s]
 67%|██████▋   | 248552/371472 [8:44:06<8:50:05,  3.86it/s]
 67%|██████▋   | 248553/371472 [8:44:06<9:47:07,  3.49it/s]
 67%|██████▋   | 248554/371472 [8:44:06<9:38:08,  3.54it/s]
 67%|██████▋   | 248555/371472 [8:44:06<9:15:03,  3.69it/s]
 67%|██████▋   | 248556/371472 [8:44:07<8:59:28,  3.80it/s]
 67%|██████▋   | 248557/371472 [8:44:07<9:02:26,  3.78it/s]
 67%|██████▋   | 248558/371472 [8:44:07<8:48:19,  3.88it/s]
 67%|██████▋   | 248559/371472 [8:44:07<9:20:50,  3.65it/s]
 67%|██████▋   | 248560/371472 [8:44:08<9:00:55,  3.79it/s]
                                                           
{'loss': 2.9179, 'learning_rate': 3.97950828503092e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248560/371472 [8:44:08<9:00:55,  3.79it/s]
 67%|██████▋   | 248561/371472 [8:44:08<8:55:09,  3.83it/s]
 67%|██████▋   | 248562/371472 [8:44:08<9:11:09,  3.72it/s]
 67%|██████▋   | 248563/371472 [8:44:09<9:54:47,  3.44it/s]
 67%|██████▋   | 248564/371472 [8:44:09<9:48:58,  3.48it/s]
 67%|██████▋   | 248565/371472 [8:44:09<9:37:35,  3.55it/s]
 67%|██████▋   | 248566/371472 [8:44:09<9:19:43,  3.66it/s]
 67%|██████▋   | 248567/371472 [8:44:10<10:16:41,  3.32it/s]
 67%|██████▋   | 248568/371472 [8:44:10<9:53:09,  3.45it/s] 
 67%|██████▋   | 248569/371472 [8:44:10<9:57:48,  3.43it/s]
 67%|██████▋   | 248570/371472 [8:44:11<10:03:16,  3.40it/s]
 67%|██████▋   | 248571/371472 [8:44:11<9:29:33,  3.60it/s] 
 67%|██████▋   | 248572/371472 [8:44:11<9:29:06,  3.60it/s]
 67%|██████▋   | 248573/371472 [8:44:11<9:20:07,  3.66it/s]
 67%|██████▋   | 248574/371472 [8:44:12<9:35:53,  3.56it/s]
 67%|██████▋   | 248575/371472 [8:44:12<9:20:46,  3.65it/s]
 67%|██████▋   | 248576/371472 [8:44:12<9:14:36,  3.69it/s]
 67%|██████▋   | 248577/371472 [8:44:12<9:03:47,  3.77it/s]
 67%|██████▋   | 248578/371472 [8:44:13<9:05:41,  3.75it/s]
 67%|██████▋   | 248579/371472 [8:44:13<9:05:15,  3.76it/s]
 67%|██████▋   | 248580/371472 [8:44:13<8:58:25,  3.80it/s]
                                                           
{'loss': 2.7555, 'learning_rate': 3.9790234652761314e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248580/371472 [8:44:13<8:58:25,  3.80it/s]
 67%|██████▋   | 248581/371472 [8:44:13<8:40:57,  3.93it/s]
 67%|██████▋   | 248582/371472 [8:44:14<8:59:17,  3.80it/s]
 67%|██████▋   | 248583/371472 [8:44:14<9:11:30,  3.71it/s]
 67%|██████▋   | 248584/371472 [8:44:14<9:10:23,  3.72it/s]
 67%|██████▋   | 248585/371472 [8:44:15<9:55:19,  3.44it/s]
 67%|██████▋   | 248586/371472 [8:44:15<9:57:08,  3.43it/s]
 67%|██████▋   | 248587/371472 [8:44:15<10:00:20,  3.41it/s]
 67%|██████▋   | 248588/371472 [8:44:15<9:25:34,  3.62it/s] 
 67%|██████▋   | 248589/371472 [8:44:16<9:42:11,  3.52it/s]
 67%|██████▋   | 248590/371472 [8:44:16<9:28:59,  3.60it/s]
 67%|██████▋   | 248591/371472 [8:44:16<9:07:18,  3.74it/s]
 67%|██████▋   | 248592/371472 [8:44:17<8:51:06,  3.86it/s]
 67%|██████▋   | 248593/371472 [8:44:17<8:58:08,  3.81it/s]
 67%|██████▋   | 248594/371472 [8:44:17<8:50:13,  3.86it/s]
 67%|██████▋   | 248595/371472 [8:44:17<9:02:26,  3.78it/s]
 67%|██████▋   | 248596/371472 [8:44:18<9:21:09,  3.65it/s]
 67%|██████▋   | 248597/371472 [8:44:18<9:26:28,  3.62it/s]
 67%|██████▋   | 248598/371472 [8:44:18<9:17:30,  3.67it/s]
 67%|██████▋   | 248599/371472 [8:44:18<9:14:41,  3.69it/s]
 67%|██████▋   | 248600/371472 [8:44:19<9:25:16,  3.62it/s]
                                                           
{'loss': 2.8309, 'learning_rate': 3.978538645521342e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248600/371472 [8:44:19<9:25:16,  3.62it/s]
 67%|██████▋   | 248601/371472 [8:44:19<9:13:21,  3.70it/s]
 67%|██████▋   | 248602/371472 [8:44:19<9:53:32,  3.45it/s]
 67%|██████▋   | 248603/371472 [8:44:20<9:48:24,  3.48it/s]
 67%|██████▋   | 248604/371472 [8:44:20<10:09:11,  3.36it/s]
 67%|██████▋   | 248605/371472 [8:44:20<9:35:27,  3.56it/s] 
 67%|██████▋   | 248606/371472 [8:44:20<9:42:03,  3.52it/s]
 67%|██████▋   | 248607/371472 [8:44:21<9:16:43,  3.68it/s]
 67%|██████▋   | 248608/371472 [8:44:21<9:13:12,  3.70it/s]
 67%|██████▋   | 248609/371472 [8:44:21<9:09:58,  3.72it/s]
 67%|██████▋   | 248610/371472 [8:44:21<8:54:16,  3.83it/s]
 67%|██████▋   | 248611/371472 [8:44:22<9:24:23,  3.63it/s]
 67%|██████▋   | 248612/371472 [8:44:22<9:40:53,  3.52it/s]
 67%|██████▋   | 248613/371472 [8:44:22<9:13:01,  3.70it/s]
 67%|██████▋   | 248614/371472 [8:44:23<9:19:49,  3.66it/s]
 67%|██████▋   | 248615/371472 [8:44:23<9:19:50,  3.66it/s]
 67%|██████▋   | 248616/371472 [8:44:23<8:49:29,  3.87it/s]
 67%|██████▋   | 248617/371472 [8:44:23<8:55:24,  3.82it/s]
 67%|██████▋   | 248618/371472 [8:44:24<8:43:37,  3.91it/s]
 67%|██████▋   | 248619/371472 [8:44:24<9:18:22,  3.67it/s]
 67%|██████▋   | 248620/371472 [8:44:24<9:14:45,  3.69it/s]
                                                           
{'loss': 2.7303, 'learning_rate': 3.978053825766554e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248620/371472 [8:44:24<9:14:45,  3.69it/s]
 67%|██████▋   | 248621/371472 [8:44:24<9:21:05,  3.65it/s]
 67%|██████▋   | 248622/371472 [8:44:25<9:30:30,  3.59it/s]
 67%|██████▋   | 248623/371472 [8:44:25<9:26:42,  3.61it/s]
 67%|██████▋   | 248624/371472 [8:44:25<9:20:27,  3.65it/s]
 67%|██████▋   | 248625/371472 [8:44:26<9:05:20,  3.75it/s]
 67%|██████▋   | 248626/371472 [8:44:26<9:28:05,  3.60it/s]
 67%|██████���   | 248627/371472 [8:44:26<10:04:16,  3.39it/s]
 67%|██████▋   | 248628/371472 [8:44:26<9:41:44,  3.52it/s] 
 67%|██████▋   | 248629/371472 [8:44:27<9:30:11,  3.59it/s]
 67%|██████▋   | 248630/371472 [8:44:27<9:19:06,  3.66it/s]
 67%|██████▋   | 248631/371472 [8:44:27<9:10:43,  3.72it/s]
 67%|██████▋   | 248632/371472 [8:44:27<8:53:24,  3.84it/s]
 67%|██████▋   | 248633/371472 [8:44:28<8:49:43,  3.86it/s]
 67%|██████▋   | 248634/371472 [8:44:28<9:12:47,  3.70it/s]
 67%|██████▋   | 248635/371472 [8:44:28<8:57:24,  3.81it/s]
 67%|██████▋   | 248636/371472 [8:44:29<9:05:27,  3.75it/s]
 67%|██████▋   | 248637/371472 [8:44:29<8:58:01,  3.81it/s]
 67%|██████▋   | 248638/371472 [8:44:29<8:42:04,  3.92it/s]
 67%|██████▋   | 248639/371472 [8:44:29<9:14:01,  3.70it/s]
 67%|██████▋   | 248640/371472 [8:44:30<9:23:09,  3.64it/s]
                                                           
{'loss': 2.8866, 'learning_rate': 3.9775690060117646e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248640/371472 [8:44:30<9:23:09,  3.64it/s]
 67%|██████▋   | 248641/371472 [8:44:30<9:12:30,  3.71it/s]
 67%|██████▋   | 248642/371472 [8:44:30<9:31:25,  3.58it/s]
 67%|██████▋   | 248643/371472 [8:44:31<9:55:47,  3.44it/s]
 67%|██████▋   | 248644/371472 [8:44:31<10:43:43,  3.18it/s]
 67%|██████▋   | 248645/371472 [8:44:31<10:41:09,  3.19it/s]
 67%|██████▋   | 248646/371472 [8:44:32<11:17:48,  3.02it/s]
 67%|██████▋   | 248647/371472 [8:44:32<10:49:12,  3.15it/s]
 67%|██████▋   | 248648/371472 [8:44:32<10:04:30,  3.39it/s]
 67%|██████▋   | 248649/371472 [8:44:32<9:42:03,  3.52it/s] 
 67%|██████▋   | 248650/371472 [8:44:33<9:18:31,  3.67it/s]
 67%|██████▋   | 248651/371472 [8:44:33<9:06:39,  3.74it/s]
 67%|██████▋   | 248652/371472 [8:44:33<9:35:58,  3.55it/s]
 67%|██████▋   | 248653/371472 [8:44:33<9:23:05,  3.64it/s]
 67%|██████▋   | 248654/371472 [8:44:34<9:23:22,  3.63it/s]
 67%|██████▋   | 248655/371472 [8:44:34<9:30:47,  3.59it/s]
 67%|██████▋   | 248656/371472 [8:44:34<9:10:45,  3.72it/s]
 67%|██████▋   | 248657/371472 [8:44:35<9:16:59,  3.67it/s]
 67%|██████▋   | 248658/371472 [8:44:35<9:20:06,  3.65it/s]
 67%|██████▋   | 248659/371472 [8:44:35<9:25:43,  3.62it/s]
 67%|██████▋   | 248660/371472 [8:44:35<9:36:27,  3.55it/s]
                                                           
{'loss': 2.9979, 'learning_rate': 3.977084186256976e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248660/371472 [8:44:35<9:36:27,  3.55it/s]
 67%|██████▋   | 248661/371472 [8:44:36<9:57:49,  3.42it/s]
 67%|██████▋   | 248662/371472 [8:44:36<10:16:32,  3.32it/s]
 67%|██████▋   | 248663/371472 [8:44:36<9:55:16,  3.44it/s] 
 67%|██████▋   | 248664/371472 [8:44:37<9:31:26,  3.58it/s]
 67%|██████▋   | 248665/371472 [8:44:37<9:29:52,  3.59it/s]
 67%|██████▋   | 248666/371472 [8:44:37<9:24:31,  3.63it/s]
 67%|██████▋   | 248667/371472 [8:44:37<9:28:00,  3.60it/s]
 67%|██████▋   | 248668/371472 [8:44:38<9:05:07,  3.75it/s]
 67%|██████▋   | 248669/371472 [8:44:38<9:05:35,  3.75it/s]
 67%|██████▋   | 248670/371472 [8:44:38<8:48:02,  3.88it/s]
 67%|██████▋   | 248671/371472 [8:44:38<9:05:53,  3.75it/s]
 67%|██████▋   | 248672/371472 [8:44:39<9:06:09,  3.75it/s]
 67%|██████▋   | 248673/371472 [8:44:39<8:52:51,  3.84it/s]
 67%|██████▋   | 248674/371472 [8:44:39<9:36:48,  3.55it/s]
 67%|██████▋   | 248675/371472 [8:44:39<9:22:31,  3.64it/s]
 67%|██████▋   | 248676/371472 [8:44:40<10:00:23,  3.41it/s]
 67%|██████▋   | 248677/371472 [8:44:40<10:15:54,  3.32it/s]
 67%|██████▋   | 248678/371472 [8:44:40<10:08:09,  3.37it/s]
 67%|██████▋   | 248679/371472 [8:44:41<10:03:47,  3.39it/s]
 67%|██████▋   | 248680/371472 [8:44:41<9:51:41,  3.46it/s] 
                                                           
{'loss': 2.6885, 'learning_rate': 3.9765993665021866e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248680/371472 [8:44:41<9:51:41,  3.46it/s]
 67%|██████▋   | 248681/371472 [8:44:41<9:53:06,  3.45it/s]
 67%|██████▋   | 248682/371472 [8:44:42<9:19:32,  3.66it/s]
 67%|██████▋   | 248683/371472 [8:44:42<8:57:53,  3.80it/s]
 67%|██████▋   | 248684/371472 [8:44:42<8:58:11,  3.80it/s]
 67%|██████▋   | 248685/371472 [8:44:42<9:15:48,  3.68it/s]
 67%|██████▋   | 248686/371472 [8:44:43<10:13:22,  3.34it/s]
 67%|██████▋   | 248687/371472 [8:44:43<9:40:57,  3.52it/s] 
 67%|██████▋   | 248688/371472 [8:44:43<9:53:31,  3.45it/s]
 67%|██████▋   | 248689/371472 [8:44:43<9:37:44,  3.54it/s]
 67%|██████▋   | 248690/371472 [8:44:44<9:21:52,  3.64it/s]
 67%|██████▋   | 248691/371472 [8:44:44<10:11:22,  3.35it/s]
 67%|██████▋   | 248692/371472 [8:44:44<10:04:41,  3.38it/s]
 67%|██████▋   | 248693/371472 [8:44:45<9:53:28,  3.45it/s] 
 67%|██████▋   | 248694/371472 [8:44:45<9:40:09,  3.53it/s]
 67%|██████▋   | 248695/371472 [8:44:45<10:00:15,  3.41it/s]
 67%|██████▋   | 248696/371472 [8:44:46<10:22:07,  3.29it/s]
 67%|██████▋   | 248697/371472 [8:44:46<10:31:59,  3.24it/s]
 67%|██████▋   | 248698/371472 [8:44:46<9:48:10,  3.48it/s] 
 67%|██████▋   | 248699/371472 [8:44:46<9:47:53,  3.48it/s]
 67%|██████▋   | 248700/371472 [8:44:47<9:33:01,  3.57it/s]
                                                           
{'loss': 2.8284, 'learning_rate': 3.9761145467473983e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248700/371472 [8:44:47<9:33:01,  3.57it/s]
 67%|██████▋   | 248701/371472 [8:44:47<9:26:32,  3.61it/s]
 67%|██████▋   | 248702/371472 [8:44:47<9:31:53,  3.58it/s]
 67%|██████▋   | 248703/371472 [8:44:48<9:24:04,  3.63it/s]
 67%|██████▋   | 248704/371472 [8:44:48<9:04:38,  3.76it/s]
 67%|██████▋   | 248705/371472 [8:44:48<9:40:56,  3.52it/s]
 67%|██████▋   | 248706/371472 [8:44:48<9:42:30,  3.51it/s]
 67%|██████▋   | 248707/371472 [8:44:49<9:44:59,  3.50it/s]
 67%|██████▋   | 248708/371472 [8:44:49<10:07:52,  3.37it/s]
 67%|██████▋   | 248709/371472 [8:44:49<9:32:50,  3.57it/s] 
 67%|██████▋   | 248710/371472 [8:44:49<9:24:51,  3.62it/s]
 67%|██████▋   | 248711/371472 [8:44:50<9:06:22,  3.74it/s]
 67%|██████▋   | 248712/371472 [8:44:50<9:17:52,  3.67it/s]
 67%|██████▋   | 248713/371472 [8:44:50<9:23:13,  3.63it/s]
 67%|██████▋   | 248714/371472 [8:44:51<9:26:06,  3.61it/s]
 67%|██████▋   | 248715/371472 [8:44:51<9:07:48,  3.73it/s]
 67%|██████▋   | 248716/371472 [8:44:51<8:53:10,  3.84it/s]
 67%|██████▋   | 248717/371472 [8:44:51<8:47:48,  3.88it/s]
 67%|██████▋   | 248718/371472 [8:44:52<8:51:00,  3.85it/s]
 67%|██████▋   | 248719/371472 [8:44:52<9:11:37,  3.71it/s]
 67%|██████▋   | 248720/371472 [8:44:52<9:01:01,  3.78it/s]
                                                           
{'loss': 2.7435, 'learning_rate': 3.9756297269926085e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248720/371472 [8:44:52<9:01:01,  3.78it/s]
 67%|██████▋   | 248721/371472 [8:44:52<8:59:53,  3.79it/s]
 67%|██████▋   | 248722/371472 [8:44:53<8:56:07,  3.82it/s]
 67%|██████▋   | 248723/371472 [8:44:53<9:46:33,  3.49it/s]
 67%|██████▋   | 248724/371472 [8:44:53<9:43:42,  3.50it/s]
 67%|██████▋   | 248725/371472 [8:44:54<9:23:36,  3.63it/s]
 67%|██████▋   | 248726/371472 [8:44:54<9:11:49,  3.71it/s]
 67%|██████▋   | 248727/371472 [8:44:54<9:01:53,  3.78it/s]
 67%|██████▋   | 248728/371472 [8:44:54<9:54:34,  3.44it/s]
 67%|██████▋   | 248729/371472 [8:44:55<9:28:44,  3.60it/s]
 67%|██████▋   | 248730/371472 [8:44:55<9:24:25,  3.62it/s]
 67%|██████▋   | 248731/371472 [8:44:55<9:18:33,  3.66it/s]
 67%|██████▋   | 248732/371472 [8:44:55<9:04:57,  3.75it/s]
 67%|██████▋   | 248733/371472 [8:44:56<8:44:48,  3.90it/s]
 67%|██████▋   | 248734/371472 [8:44:56<9:22:39,  3.64it/s]
 67%|██████▋   | 248735/371472 [8:44:56<9:47:53,  3.48it/s]
 67%|██████▋   | 248736/371472 [8:44:57<9:31:49,  3.58it/s]
 67%|██████▋   | 248737/371472 [8:44:57<9:32:10,  3.58it/s]
 67%|██████▋   | 248738/371472 [8:44:57<9:30:13,  3.59it/s]
 67%|██████▋   | 248739/371472 [8:44:57<9:09:26,  3.72it/s]
 67%|██████▋   | 248740/371472 [8:44:58<9:22:10,  3.64it/s]
                                                           
{'loss': 2.766, 'learning_rate': 3.9751449072378203e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248740/371472 [8:44:58<9:22:10,  3.64it/s]
 67%|██████▋   | 248741/371472 [8:44:58<9:33:59,  3.56it/s]
 67%|██████▋   | 248742/371472 [8:44:58<9:18:09,  3.66it/s]
 67%|██████▋   | 248743/371472 [8:44:58<9:02:55,  3.77it/s]
 67%|██████▋   | 248744/371472 [8:44:59<8:55:23,  3.82it/s]
 67%|██████▋   | 248745/371472 [8:44:59<8:52:32,  3.84it/s]
 67%|██████▋   | 248746/371472 [8:44:59<9:20:40,  3.65it/s]
 67%|██████▋   | 248747/371472 [8:45:00<10:00:36,  3.41it/s]
 67%|██████��   | 248748/371472 [8:45:00<9:59:33,  3.41it/s] 
 67%|██████▋   | 248749/371472 [8:45:00<9:41:53,  3.52it/s]
 67%|██████▋   | 248750/371472 [8:45:00<9:22:03,  3.64it/s]
 67%|██████▋   | 248751/371472 [8:45:01<9:22:12,  3.64it/s]
 67%|██████▋   | 248752/371472 [8:45:01<10:11:50,  3.34it/s]
 67%|██████▋   | 248753/371472 [8:45:01<10:35:59,  3.22it/s]
 67%|██████▋   | 248754/371472 [8:45:02<10:18:09,  3.31it/s]
 67%|██████▋   | 248755/371472 [8:45:02<9:53:58,  3.44it/s] 
 67%|██████▋   | 248756/371472 [8:45:02<9:51:29,  3.46it/s]
 67%|██████▋   | 248757/371472 [8:45:02<9:26:56,  3.61it/s]
 67%|██████▋   | 248758/371472 [8:45:03<9:14:01,  3.69it/s]
 67%|██████▋   | 248759/371472 [8:45:03<8:59:25,  3.79it/s]
 67%|██████▋   | 248760/371472 [8:45:03<9:07:56,  3.73it/s]
                                                           
{'loss': 2.9922, 'learning_rate': 3.974660087483031e-07, 'epoch': 10.71}
+
 67%|██████▋   | 248760/371472 [8:45:03<9:07:56,  3.73it/s]
 67%|██████▋   | 248761/371472 [8:45:04<9:39:41,  3.53it/s]
 67%|██████▋   | 248762/371472 [8:45:04<9:53:19,  3.45it/s]
 67%|██████▋   | 248763/371472 [8:45:04<9:34:31,  3.56it/s]
 67%|██████▋   | 248764/371472 [8:45:04<9:13:57,  3.69it/s]
 67%|██████▋   | 248765/371472 [8:45:05<9:05:02,  3.75it/s]
 67%|██████▋   | 248766/371472 [8:45:05<9:12:49,  3.70it/s]
 67%|██████▋   | 248767/371472 [8:45:05<8:54:12,  3.83it/s]
 67%|██████▋   | 248768/371472 [8:45:05<8:51:12,  3.85it/s]
 67%|██████▋   | 248769/371472 [8:45:06<9:35:04,  3.56it/s]
 67%|██████▋   | 248770/371472 [8:45:06<9:58:11,  3.42it/s]
 67%|██████▋   | 248771/371472 [8:45:06<9:25:58,  3.61it/s]
 67%|██████▋   | 248772/371472 [8:45:07<9:18:32,  3.66it/s]
 67%|██████▋   | 248773/371472 [8:45:07<9:44:37,  3.50it/s]
 67%|██████▋   | 248774/371472 [8:45:07<9:38:48,  3.53it/s]
 67%|██████▋   | 248775/371472 [8:45:07<9:09:50,  3.72it/s]
 67%|██████▋   | 248776/371472 [8:45:08<10:07:22,  3.37it/s]
 67%|██████▋   | 248777/371472 [8:45:08<9:48:16,  3.48it/s] 
 67%|██████▋   | 248778/371472 [8:45:08<9:25:09,  3.62it/s]
 67%|██████▋   | 248779/371472 [8:45:09<9:17:08,  3.67it/s]
 67%|██████▋   | 248780/371472 [8:45:09<9:01:24,  3.78it/s]
                                                           
{'loss': 2.747, 'learning_rate': 3.974175267728243e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248780/371472 [8:45:09<9:01:24,  3.78it/s]
 67%|██████▋   | 248781/371472 [8:45:09<8:56:55,  3.81it/s]
 67%|██████▋   | 248782/371472 [8:45:09<9:31:56,  3.58it/s]
 67%|██████▋   | 248783/371472 [8:45:10<9:24:01,  3.63it/s]
 67%|██████▋   | 248784/371472 [8:45:10<9:02:50,  3.77it/s]
 67%|██████▋   | 248785/371472 [8:45:10<9:02:43,  3.77it/s]
 67%|██████▋   | 248786/371472 [8:45:10<9:16:06,  3.68it/s]
 67%|██████▋   | 248787/371472 [8:45:11<9:31:09,  3.58it/s]
 67%|██████▋   | 248788/371472 [8:45:11<9:56:28,  3.43it/s]
 67%|██████▋   | 248789/371472 [8:45:11<9:41:01,  3.52it/s]
 67%|██████▋   | 248790/371472 [8:45:12<9:58:02,  3.42it/s]
 67%|██████▋   | 248791/371472 [8:45:12<10:14:33,  3.33it/s]
 67%|██████▋   | 248792/371472 [8:45:12<9:49:39,  3.47it/s] 
 67%|██████▋   | 248793/371472 [8:45:12<9:54:49,  3.44it/s]
 67%|██████▋   | 248794/371472 [8:45:13<10:26:45,  3.26it/s]
 67%|██████▋   | 248795/371472 [8:45:13<10:17:34,  3.31it/s]
 67%|██████▋   | 248796/371472 [8:45:13<9:43:22,  3.50it/s] 
 67%|██████▋   | 248797/371472 [8:45:14<9:12:30,  3.70it/s]
 67%|██████▋   | 248798/371472 [8:45:14<9:12:14,  3.70it/s]
 67%|██████▋   | 248799/371472 [8:45:14<9:40:20,  3.52it/s]
 67%|██████▋   | 248800/371472 [8:45:14<9:30:41,  3.58it/s]
                                                           
{'loss': 2.8719, 'learning_rate': 3.973690447973453e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248800/371472 [8:45:14<9:30:41,  3.58it/s]
 67%|██████▋   | 248801/371472 [8:45:15<9:08:11,  3.73it/s]
 67%|██████▋   | 248802/371472 [8:45:15<9:27:49,  3.60it/s]
 67%|██████▋   | 248803/371472 [8:45:15<10:12:35,  3.34it/s]
 67%|██████▋   | 248804/371472 [8:45:16<9:46:59,  3.48it/s] 
 67%|██████▋   | 248805/371472 [8:45:16<9:30:30,  3.58it/s]
 67%|██████▋   | 248806/371472 [8:45:16<9:20:51,  3.65it/s]
 67%|██████▋   | 248807/371472 [8:45:16<10:03:45,  3.39it/s]
 67%|██████▋   | 248808/371472 [8:45:17<10:24:55,  3.27it/s]
 67%|██████▋   | 248809/371472 [8:45:17<9:55:29,  3.43it/s] 
 67%|██████▋   | 248810/371472 [8:45:17<9:51:49,  3.45it/s]
 67%|██████▋   | 248811/371472 [8:45:18<9:22:46,  3.63it/s]
 67%|██████▋   | 248812/371472 [8:45:18<9:18:15,  3.66it/s]
 67%|██████▋   | 248813/371472 [8:45:18<9:44:59,  3.49it/s]
 67%|██████▋   | 248814/371472 [8:45:18<9:59:01,  3.41it/s]
 67%|██████▋   | 248815/371472 [8:45:19<10:22:22,  3.28it/s]
 67%|██████▋   | 248816/371472 [8:45:19<9:40:12,  3.52it/s] 
 67%|██████▋   | 248817/371472 [8:45:19<10:02:20,  3.39it/s]
 67%|██████▋   | 248818/371472 [8:45:20<9:39:37,  3.53it/s] 
 67%|██████▋   | 248819/371472 [8:45:20<9:13:37,  3.69it/s]
 67%|██████▋   | 248820/371472 [8:45:20<9:42:20,  3.51it/s]
                                                           
{'loss': 2.8216, 'learning_rate': 3.973205628218665e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248820/371472 [8:45:20<9:42:20,  3.51it/s]
 67%|██████▋   | 248821/371472 [8:45:20<9:32:05,  3.57it/s]
 67%|██████▋   | 248822/371472 [8:45:21<9:08:36,  3.73it/s]
 67%|██████▋   | 248823/371472 [8:45:21<8:52:46,  3.84it/s]
 67%|██████▋   | 248824/371472 [8:45:21<10:01:22,  3.40it/s]
 67%|██████▋   | 248825/371472 [8:45:22<10:20:01,  3.30it/s]
 67%|██████▋   | 248826/371472 [8:45:22<9:44:56,  3.49it/s] 
 67%|██████▋   | 248827/371472 [8:45:22<9:38:01,  3.54it/s]
 67%|██████▋   | 248828/371472 [8:45:22<9:19:10,  3.66it/s]
 67%|██████▋   | 248829/371472 [8:45:23<9:05:36,  3.75it/s]
 67%|██████▋   | 248830/371472 [8:45:23<9:06:15,  3.74it/s]
 67%|██████▋   | 248831/371472 [8:45:23<9:34:28,  3.56it/s]
 67%|██████▋   | 248832/371472 [8:45:24<10:05:58,  3.37it/s]
 67%|██████▋   | 248833/371472 [8:45:24<9:25:32,  3.61it/s] 
 67%|██████▋   | 248834/371472 [8:45:24<9:10:12,  3.71it/s]
 67%|██████▋   | 248835/371472 [8:45:24<9:02:20,  3.77it/s]
 67%|██████▋   | 248836/371472 [8:45:25<9:16:43,  3.67it/s]
 67%|██████▋   | 248837/371472 [8:45:25<9:32:12,  3.57it/s]
 67%|██████▋   | 248838/371472 [8:45:25<9:14:52,  3.68it/s]
 67%|██████▋   | 248839/371472 [8:45:25<9:54:05,  3.44it/s]
 67%|██████▋   | 248840/371472 [8:45:26<10:08:28,  3.36it/s]
                                                            
{'loss': 2.8457, 'learning_rate': 3.972720808463875e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248840/371472 [8:45:26<10:08:28,  3.36it/s]
 67%|██████▋   | 248841/371472 [8:45:26<10:54:07,  3.12it/s]
 67%|██████▋   | 248842/371472 [8:45:26<10:33:21,  3.23it/s]
 67%|██████▋   | 248843/371472 [8:45:27<10:04:43,  3.38it/s]
 67%|██████▋   | 248844/371472 [8:45:27<10:04:29,  3.38it/s]
 67%|██████▋   | 248845/371472 [8:45:27<11:58:01,  2.85it/s]
 67%|██████▋   | 248846/371472 [8:45:28<10:52:26,  3.13it/s]
 67%|██████▋   | 248847/371472 [8:45:28<10:09:43,  3.35it/s]
 67%|██████▋   | 248848/371472 [8:45:28<9:52:36,  3.45it/s] 
 67%|██████▋   | 248849/371472 [8:45:29<9:44:26,  3.50it/s]
 67%|██████▋   | 248850/371472 [8:45:29<10:13:49,  3.33it/s]
 67%|██████▋   | 248851/371472 [8:45:29<9:49:37,  3.47it/s] 
 67%|██████▋   | 248852/371472 [8:45:29<9:49:06,  3.47it/s]
 67%|██████▋   | 248853/371472 [8:45:30<9:09:05,  3.72it/s]
 67%|██████▋   | 248854/371472 [8:45:30<9:19:05,  3.66it/s]
 67%|██████▋   | 248855/371472 [8:45:30<9:22:50,  3.63it/s]
 67%|██████▋   | 248856/371472 [8:45:31<9:37:03,  3.54it/s]
 67%|██████▋   | 248857/371472 [8:45:31<9:21:33,  3.64it/s]
 67%|██████▋   | 248858/371472 [8:45:31<9:29:14,  3.59it/s]
 67%|██████▋   | 248859/371472 [8:45:31<9:12:22,  3.70it/s]
 67%|██████▋   | 248860/371472 [8:45:32<9:01:18,  3.78it/s]
                                                           
{'loss': 2.7072, 'learning_rate': 3.9722359887090867e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248860/371472 [8:45:32<9:01:18,  3.78it/s]
 67%|██████▋   | 248861/371472 [8:45:32<8:58:02,  3.80it/s]
 67%|██████▋   | 248862/371472 [8:45:32<9:10:55,  3.71it/s]
 67%|██████▋   | 248863/371472 [8:45:32<9:13:57,  3.69it/s]
 67%|██████▋   | 248864/371472 [8:45:33<10:44:05,  3.17it/s]
 67%|██████▋   | 248865/371472 [8:45:33<10:23:54,  3.28it/s]
 67%|██████▋   | 248866/371472 [8:45:33<10:20:29,  3.29it/s]
 67%|██████▋   | 248867/371472 [8:45:34<9:42:08,  3.51it/s] 
 67%|██████▋   | 248868/371472 [8:45:34<10:09:27,  3.35it/s]
 67%|██��███▋   | 248869/371472 [8:45:34<9:51:51,  3.45it/s] 
 67%|██████▋   | 248870/371472 [8:45:34<9:36:07,  3.55it/s]
 67%|██████▋   | 248871/371472 [8:45:35<9:46:05,  3.49it/s]
 67%|██████▋   | 248872/371472 [8:45:35<9:27:57,  3.60it/s]
 67%|██████▋   | 248873/371472 [8:45:35<9:05:44,  3.74it/s]
 67%|██████▋   | 248874/371472 [8:45:36<9:10:21,  3.71it/s]
 67%|██████▋   | 248875/371472 [8:45:36<9:11:48,  3.70it/s]
 67%|██████▋   | 248876/371472 [8:45:36<9:09:18,  3.72it/s]
 67%|██████▋   | 248877/371472 [8:45:36<9:01:28,  3.77it/s]
 67%|██████▋   | 248878/371472 [8:45:37<9:13:43,  3.69it/s]
 67%|██████▋   | 248879/371472 [8:45:37<9:35:09,  3.55it/s]
 67%|██████▋   | 248880/371472 [8:45:37<9:30:02,  3.58it/s]
                                                           
{'loss': 2.7272, 'learning_rate': 3.9717511689542974e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248880/371472 [8:45:37<9:30:02,  3.58it/s]
 67%|██████▋   | 248881/371472 [8:45:37<9:34:23,  3.56it/s]
 67%|██████▋   | 248882/371472 [8:45:38<9:24:45,  3.62it/s]
 67%|██████▋   | 248883/371472 [8:45:38<9:40:45,  3.52it/s]
 67%|██████▋   | 248884/371472 [8:45:38<9:22:04,  3.63it/s]
 67%|██████▋   | 248885/371472 [8:45:39<9:16:21,  3.67it/s]
 67%|██████▋   | 248886/371472 [8:45:39<9:53:04,  3.44it/s]
 67%|██████▋   | 248887/371472 [8:45:39<9:28:30,  3.59it/s]
 67%|██████▋   | 248888/371472 [8:45:39<9:11:59,  3.70it/s]
 67%|██████▋   | 248889/371472 [8:45:40<9:11:52,  3.70it/s]
 67%|██████▋   | 248890/371472 [8:45:40<9:23:04,  3.63it/s]
 67%|██████▋   | 248891/371472 [8:45:40<9:24:52,  3.62it/s]
 67%|██████▋   | 248892/371472 [8:45:41<9:34:35,  3.56it/s]
 67%|██████▋   | 248893/371472 [8:45:41<10:38:19,  3.20it/s]
 67%|██████▋   | 248894/371472 [8:45:41<10:04:15,  3.38it/s]
 67%|██████▋   | 248895/371472 [8:45:41<9:39:33,  3.52it/s] 
 67%|██████▋   | 248896/371472 [8:45:42<9:37:03,  3.54it/s]
 67%|██████▋   | 248897/371472 [8:45:42<9:19:51,  3.65it/s]
 67%|██████▋   | 248898/371472 [8:45:42<9:59:16,  3.41it/s]
 67%|██████▋   | 248899/371472 [8:45:43<9:56:12,  3.43it/s]
 67%|██████▋   | 248900/371472 [8:45:43<9:42:51,  3.50it/s]
                                                           
{'loss': 2.756, 'learning_rate': 3.9712663491995087e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248900/371472 [8:45:43<9:42:51,  3.50it/s]
 67%|██████▋   | 248901/371472 [8:45:43<9:35:06,  3.55it/s]
 67%|██████▋   | 248902/371472 [8:45:43<9:38:32,  3.53it/s]
 67%|██████▋   | 248903/371472 [8:45:44<9:46:39,  3.48it/s]
 67%|██████▋   | 248904/371472 [8:45:44<10:10:38,  3.35it/s]
 67%|██████▋   | 248905/371472 [8:45:44<9:53:32,  3.44it/s] 
 67%|██████▋   | 248906/371472 [8:45:45<9:50:40,  3.46it/s]
 67%|██████▋   | 248907/371472 [8:45:45<10:37:04,  3.21it/s]
 67%|██████▋   | 248908/371472 [8:45:45<10:10:45,  3.34it/s]
 67%|██████▋   | 248909/371472 [8:45:46<10:00:17,  3.40it/s]
 67%|██████▋   | 248910/371472 [8:45:46<9:42:52,  3.50it/s] 
 67%|██████▋   | 248911/371472 [8:45:46<10:30:27,  3.24it/s]
 67%|██████▋   | 248912/371472 [8:45:46<9:46:31,  3.48it/s] 
 67%|██████▋   | 248913/371472 [8:45:47<10:11:07,  3.34it/s]
 67%|██████▋   | 248914/371472 [8:45:47<9:52:29,  3.45it/s] 
 67%|██████▋   | 248915/371472 [8:45:47<9:43:52,  3.50it/s]
 67%|██████▋   | 248916/371472 [8:45:48<9:36:30,  3.54it/s]
 67%|██████▋   | 248917/371472 [8:45:48<9:16:01,  3.67it/s]
 67%|██████▋   | 248918/371472 [8:45:48<9:05:35,  3.74it/s]
 67%|██████▋   | 248919/371472 [8:45:48<9:09:13,  3.72it/s]
 67%|██████▋   | 248920/371472 [8:45:49<9:21:38,  3.64it/s]
                                                           
{'loss': 2.7385, 'learning_rate': 3.9707815294447194e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248920/371472 [8:45:49<9:21:38,  3.64it/s]
 67%|██████▋   | 248921/371472 [8:45:49<9:12:36,  3.70it/s]
 67%|██████▋   | 248922/371472 [8:45:49<9:26:51,  3.60it/s]
 67%|██████▋   | 248923/371472 [8:45:49<9:39:02,  3.53it/s]
 67%|██████▋   | 248924/371472 [8:45:50<9:20:55,  3.64it/s]
 67%|██████▋   | 248925/371472 [8:45:50<9:35:19,  3.55it/s]
 67%|██████▋   | 248926/371472 [8:45:50<9:14:42,  3.68it/s]
 67%|██████▋   | 248927/371472 [8:45:51<9:09:06,  3.72it/s]
 67%|██████▋   | 248928/371472 [8:45:51<9:28:11,  3.59it/s]
 67%|██████▋   | 248929/371472 [8:45:51<8:57:50,  3.80it/s]
 67%|██████▋   | 248930/371472 [8:45:51<8:57:09,  3.80it/s]
 67%|██████▋   | 248931/371472 [8:45:52<9:08:03,  3.73it/s]
 67%|██████▋   | 248932/371472 [8:45:52<9:13:48,  3.69it/s]
 67%|██████▋   | 248933/371472 [8:45:52<9:24:55,  3.62it/s]
 67%|██████▋   | 248934/371472 [8:45:52<9:05:21,  3.74it/s]
 67%|██████▋   | 248935/371472 [8:45:53<8:59:27,  3.79it/s]
 67%|██████▋   | 248936/371472 [8:45:53<8:54:14,  3.82it/s]
 67%|██████▋   | 248937/371472 [8:45:53<8:41:20,  3.92it/s]
 67%|██████▋   | 248938/371472 [8:45:53<8:34:11,  3.97it/s]
 67%|██████▋   | 248939/371472 [8:45:54<8:29:25,  4.01it/s]
 67%|██████▋   | 248940/371472 [8:45:54<8:33:02,  3.98it/s]
                                                           
{'loss': 2.852, 'learning_rate': 3.970296709689931e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248940/371472 [8:45:54<8:33:02,  3.98it/s]
 67%|██████▋   | 248941/371472 [8:45:54<9:48:14,  3.47it/s]
 67%|██████▋   | 248942/371472 [8:45:55<10:17:09,  3.31it/s]
 67%|██████▋   | 248943/371472 [8:45:55<9:45:05,  3.49it/s] 
 67%|██████▋   | 248944/371472 [8:45:55<9:54:17,  3.44it/s]
 67%|██████▋   | 248945/371472 [8:45:55<9:35:35,  3.55it/s]
 67%|██████▋   | 248946/371472 [8:45:56<10:12:59,  3.33it/s]
 67%|██████▋   | 248947/371472 [8:45:56<9:59:08,  3.41it/s] 
 67%|██████▋   | 248948/371472 [8:45:56<9:44:05,  3.50it/s]
 67%|██████▋   | 248949/371472 [8:45:57<9:48:00,  3.47it/s]
 67%|██████▋   | 248950/371472 [8:45:57<10:02:10,  3.39it/s]
 67%|██████▋   | 248951/371472 [8:45:57<10:06:18,  3.37it/s]
 67%|██████▋   | 248952/371472 [8:45:57<9:52:07,  3.45it/s] 
 67%|██████▋   | 248953/371472 [8:45:58<9:43:43,  3.50it/s]
 67%|██████▋   | 248954/371472 [8:45:58<9:28:27,  3.59it/s]
 67%|██████▋   | 248955/371472 [8:45:58<9:03:17,  3.76it/s]
 67%|██████▋   | 248956/371472 [8:45:59<8:50:31,  3.85it/s]
 67%|██████▋   | 248957/371472 [8:45:59<8:53:09,  3.83it/s]
 67%|██████▋   | 248958/371472 [8:45:59<9:41:04,  3.51it/s]
 67%|██████▋   | 248959/371472 [8:45:59<9:41:48,  3.51it/s]
 67%|██████▋   | 248960/371472 [8:46:00<9:16:30,  3.67it/s]
                                                           
{'loss': 2.7849, 'learning_rate': 3.969811889935142e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248960/371472 [8:46:00<9:16:30,  3.67it/s]
 67%|██████▋   | 248961/371472 [8:46:00<9:19:12,  3.65it/s]
 67%|██████▋   | 248962/371472 [8:46:00<9:26:10,  3.61it/s]
 67%|██████▋   | 248963/371472 [8:46:00<9:04:52,  3.75it/s]
 67%|██████▋   | 248964/371472 [8:46:01<8:56:05,  3.81it/s]
 67%|██████▋   | 248965/371472 [8:46:01<8:54:19,  3.82it/s]
 67%|██████▋   | 248966/371472 [8:46:01<9:00:01,  3.78it/s]
 67%|██████▋   | 248967/371472 [8:46:01<8:47:13,  3.87it/s]
 67%|██████▋   | 248968/371472 [8:46:02<9:10:02,  3.71it/s]
 67%|██████▋   | 248969/371472 [8:46:02<9:37:23,  3.54it/s]
 67%|██████▋   | 248970/371472 [8:46:02<9:38:34,  3.53it/s]
 67%|██████▋   | 248971/371472 [8:46:03<9:27:38,  3.60it/s]
 67%|██████▋   | 248972/371472 [8:46:03<9:43:27,  3.50it/s]
 67%|██████▋   | 248973/371472 [8:46:03<9:24:33,  3.62it/s]
 67%|██████▋   | 248974/371472 [8:46:03<9:30:01,  3.58it/s]
 67%|██████▋   | 248975/371472 [8:46:04<10:00:11,  3.40it/s]
 67%|██████▋   | 248976/371472 [8:46:04<10:08:57,  3.35it/s]
 67%|██████▋   | 248977/371472 [8:46:04<10:43:47,  3.17it/s]
 67%|██████▋   | 248978/371472 [8:46:05<10:12:17,  3.33it/s]
 67%|██████▋   | 248979/371472 [8:46:05<9:50:01,  3.46it/s] 
 67%|██████▋   | 248980/371472 [8:46:05<9:26:17,  3.61it/s]
                                                           
{'loss': 2.7606, 'learning_rate': 3.969327070180353e-07, 'epoch': 10.72}
+
 67%|██████▋   | 248980/371472 [8:46:05<9:26:17,  3.61it/s]
 67%|██████▋   | 248981/371472 [8:46:06<9:21:32,  3.64it/s]
 67%|██████▋   | 248982/371472 [8:46:06<9:47:03,  3.48it/s]
 67%|██████▋   | 248983/371472 [8:46:06<9:31:16,  3.57it/s]
 67%|██████▋   | 248984/371472 [8:46:06<9:38:31,  3.53it/s]
 67%|██████▋   | 248985/371472 [8:46:07<9:19:20,  3.65it/s]
 67%|██████▋   | 248986/371472 [8:46:07<9:28:31,  3.59it/s]
 67%|██████▋   | 248987/371472 [8:46:07<9:20:57,  3.64it/s]
 67%|██████▋   | 248988/371472 [8:46:07<9:15:56,  3.67it/s]
 67%|██████▋   | 248989/371472 [8:46:08<9:37:48,  3.53it/s]
 67%|████���█▋   | 248990/371472 [8:46:08<9:32:19,  3.57it/s]
 67%|██████▋   | 248991/371472 [8:46:08<9:27:45,  3.60it/s]
 67%|██████▋   | 248992/371472 [8:46:09<8:55:42,  3.81it/s]
 67%|██████▋   | 248993/371472 [8:46:09<9:03:10,  3.76it/s]
 67%|██████▋   | 248994/371472 [8:46:09<9:02:23,  3.76it/s]
 67%|██████▋   | 248995/371472 [8:46:09<8:54:29,  3.82it/s]
 67%|██████▋   | 248996/371472 [8:46:10<8:53:33,  3.83it/s]
 67%|██████▋   | 248997/371472 [8:46:10<8:41:40,  3.91it/s]
 67%|██████▋   | 248998/371472 [8:46:10<9:38:29,  3.53it/s]
 67%|██████▋   | 248999/371472 [8:46:10<9:55:27,  3.43it/s]
 67%|██████▋   | 249000/371472 [8:46:11<10:51:51,  3.13it/s]
                                                            
{'loss': 2.762, 'learning_rate': 3.968842250425564e-07, 'epoch': 10.72}
+
 67%|██████▋   | 249000/371472 [8:46:11<10:51:51,  3.13it/s]
 67%|██████▋   | 249001/371472 [8:46:11<10:21:48,  3.28it/s]
 67%|██████▋   | 249002/371472 [8:46:11<10:10:28,  3.34it/s]
 67%|██████▋   | 249003/371472 [8:46:12<10:04:33,  3.38it/s]
 67%|██████▋   | 249004/371472 [8:46:12<9:33:46,  3.56it/s] 
 67%|██████▋   | 249005/371472 [8:46:12<9:09:33,  3.71it/s]
 67%|██████▋   | 249006/371472 [8:46:12<9:07:12,  3.73it/s]
 67%|██████▋   | 249007/371472 [8:46:13<9:17:33,  3.66it/s]
 67%|██████▋   | 249008/371472 [8:46:13<8:51:13,  3.84it/s]
 67%|██████▋   | 249009/371472 [8:46:13<8:52:30,  3.83it/s]
 67%|██████▋   | 249010/371472 [8:46:14<8:45:04,  3.89it/s]
 67%|██████▋   | 249011/371472 [8:46:14<9:11:16,  3.70it/s]
 67%|██████▋   | 249012/371472 [8:46:14<9:39:44,  3.52it/s]
 67%|██████▋   | 249013/371472 [8:46:14<9:39:16,  3.52it/s]
 67%|██████▋   | 249014/371472 [8:46:15<9:42:39,  3.50it/s]
 67%|██████▋   | 249015/371472 [8:46:15<10:06:47,  3.36it/s]
 67%|██████▋   | 249016/371472 [8:46:15<10:15:57,  3.31it/s]
 67%|██████▋   | 249017/371472 [8:46:16<10:01:46,  3.39it/s]
 67%|██████▋   | 249018/371472 [8:46:16<10:18:02,  3.30it/s]
 67%|██████▋   | 249019/371472 [8:46:16<9:39:28,  3.52it/s] 
 67%|██████▋   | 249020/371472 [8:46:16<9:27:56,  3.59it/s]
                                                           
{'loss': 3.0477, 'learning_rate': 3.968357430670775e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249020/371472 [8:46:16<9:27:56,  3.59it/s]
 67%|██████▋   | 249021/371472 [8:46:17<9:12:35,  3.69it/s]
 67%|██████▋   | 249022/371472 [8:46:17<9:34:46,  3.55it/s]
 67%|██████▋   | 249023/371472 [8:46:17<9:21:49,  3.63it/s]
 67%|██████▋   | 249024/371472 [8:46:17<9:03:22,  3.76it/s]
 67%|██████▋   | 249025/371472 [8:46:18<9:21:43,  3.63it/s]
 67%|██████▋   | 249026/371472 [8:46:18<9:19:20,  3.65it/s]
 67%|██████▋   | 249027/371472 [8:46:18<9:08:01,  3.72it/s]
 67%|██████▋   | 249028/371472 [8:46:19<9:11:50,  3.70it/s]
 67%|██████▋   | 249029/371472 [8:46:19<9:18:53,  3.65it/s]
 67%|██████▋   | 249030/371472 [8:46:19<9:35:15,  3.55it/s]
 67%|██████▋   | 249031/371472 [8:46:19<9:28:06,  3.59it/s]
 67%|██████▋   | 249032/371472 [8:46:20<9:16:15,  3.67it/s]
 67%|██████▋   | 249033/371472 [8:46:20<10:13:23,  3.33it/s]
 67%|██████▋   | 249034/371472 [8:46:20<9:44:21,  3.49it/s] 
 67%|██████▋   | 249035/371472 [8:46:21<9:26:33,  3.60it/s]
 67%|██████▋   | 249036/371472 [8:46:21<9:44:59,  3.49it/s]
 67%|██████▋   | 249037/371472 [8:46:21<10:11:11,  3.34it/s]
 67%|██████▋   | 249038/371472 [8:46:21<9:26:08,  3.60it/s] 
 67%|██████▋   | 249039/371472 [8:46:22<9:20:01,  3.64it/s]
 67%|██████▋   | 249040/371472 [8:46:22<9:07:46,  3.73it/s]
                                                           
{'loss': 2.9698, 'learning_rate': 3.967872610915986e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249040/371472 [8:46:22<9:07:46,  3.73it/s]
 67%|██████▋   | 249041/371472 [8:46:22<9:04:17,  3.75it/s]
 67%|██████▋   | 249042/371472 [8:46:23<9:09:00,  3.72it/s]
 67%|██████▋   | 249043/371472 [8:46:23<8:50:24,  3.85it/s]
 67%|██████▋   | 249044/371472 [8:46:23<9:10:22,  3.71it/s]
 67%|██████▋   | 249045/371472 [8:46:23<9:50:17,  3.46it/s]
 67%|██████▋   | 249046/371472 [8:46:24<10:12:06,  3.33it/s]
 67%|██████▋   | 249047/371472 [8:46:24<9:56:33,  3.42it/s] 
 67%|██████▋   | 249048/371472 [8:46:24<9:55:41,  3.43it/s]
 67%|██████▋   | 249049/371472 [8:46:25<9:23:22,  3.62it/s]
 67%|██████▋   | 249050/371472 [8:46:25<9:04:07,  3.75it/s]
 67%|██████▋   | 249051/371472 [8:46:25<9:03:46,  3.75it/s]
 67%|██████▋   | 249052/371472 [8:46:25<9:07:45,  3.72it/s]
 67%|██████▋   | 249053/371472 [8:46:26<8:56:49,  3.80it/s]
 67%|██████▋   | 249054/371472 [8:46:26<10:00:04,  3.40it/s]
 67%|██████▋   | 249055/371472 [8:46:26<9:39:51,  3.52it/s] 
 67%|██████▋   | 249056/371472 [8:46:26<9:42:10,  3.50it/s]
 67%|██████▋   | 249057/371472 [8:46:27<9:35:07,  3.55it/s]
 67%|██████▋   | 249058/371472 [8:46:27<9:07:00,  3.73it/s]
 67%|██████▋   | 249059/371472 [8:46:27<9:11:57,  3.70it/s]
 67%|██████▋   | 249060/371472 [8:46:27<8:57:10,  3.80it/s]
                                                           
{'loss': 2.8541, 'learning_rate': 3.9673877911611976e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249060/371472 [8:46:27<8:57:10,  3.80it/s]
 67%|██████▋   | 249061/371472 [8:46:28<8:44:42,  3.89it/s]
 67%|██████▋   | 249062/371472 [8:46:28<8:53:18,  3.83it/s]
 67%|██████▋   | 249063/371472 [8:46:28<8:33:31,  3.97it/s]
 67%|██████▋   | 249064/371472 [8:46:29<8:48:00,  3.86it/s]
 67%|██████▋   | 249065/371472 [8:46:29<8:53:37,  3.82it/s]
 67%|██████▋   | 249066/371472 [8:46:29<9:10:56,  3.70it/s]
 67%|██████▋   | 249067/371472 [8:46:29<9:26:09,  3.60it/s]
 67%|██████▋   | 249068/371472 [8:46:30<9:17:30,  3.66it/s]
 67%|██████▋   | 249069/371472 [8:46:30<9:16:31,  3.67it/s]
 67%|██████▋   | 249070/371472 [8:46:30<9:20:38,  3.64it/s]
 67%|██████▋   | 249071/371472 [8:46:30<9:22:36,  3.63it/s]
 67%|██████▋   | 249072/371472 [8:46:31<9:18:35,  3.65it/s]
 67%|██████▋   | 249073/371472 [8:46:31<8:56:22,  3.80it/s]
 67%|██████▋   | 249074/371472 [8:46:31<8:47:37,  3.87it/s]
 67%|██████▋   | 249075/371472 [8:46:31<8:38:17,  3.94it/s]
 67%|██████▋   | 249076/371472 [8:46:32<8:56:46,  3.80it/s]
 67%|██████▋   | 249077/371472 [8:46:32<9:52:38,  3.44it/s]
 67%|██████▋   | 249078/371472 [8:46:32<9:32:10,  3.57it/s]
 67%|██████▋   | 249079/371472 [8:46:33<9:41:20,  3.51it/s]
 67%|██████▋   | 249080/371472 [8:46:33<9:50:20,  3.46it/s]
                                                           
{'loss': 2.7647, 'learning_rate': 3.9669029714064083e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249080/371472 [8:46:33<9:50:20,  3.46it/s]
 67%|██████▋   | 249081/371472 [8:46:33<9:45:58,  3.48it/s]
 67%|██████▋   | 249082/371472 [8:46:34<9:45:19,  3.48it/s]
 67%|██████▋   | 249083/371472 [8:46:34<10:22:22,  3.28it/s]
 67%|██████▋   | 249084/371472 [8:46:34<9:59:27,  3.40it/s] 
 67%|██████▋   | 249085/371472 [8:46:34<9:42:08,  3.50it/s]
 67%|██████▋   | 249086/371472 [8:46:35<9:29:55,  3.58it/s]
 67%|██████▋   | 249087/371472 [8:46:35<9:18:48,  3.65it/s]
 67%|██████▋   | 249088/371472 [8:46:35<9:05:58,  3.74it/s]
 67%|██████▋   | 249089/371472 [8:46:36<9:55:29,  3.43it/s]
 67%|██████▋   | 249090/371472 [8:46:36<10:09:01,  3.35it/s]
 67%|██████▋   | 249091/371472 [8:46:36<10:36:00,  3.21it/s]
 67%|██████▋   | 249092/371472 [8:46:36<10:18:46,  3.30it/s]
 67%|██████▋   | 249093/371472 [8:46:37<10:37:04,  3.20it/s]
 67%|██████▋   | 249094/371472 [8:46:37<10:36:45,  3.20it/s]
 67%|██████▋   | 249095/371472 [8:46:37<9:55:31,  3.42it/s] 
 67%|██████▋   | 249096/371472 [8:46:38<9:50:25,  3.45it/s]
 67%|██████▋   | 249097/371472 [8:46:38<9:43:31,  3.50it/s]
 67%|██████▋   | 249098/371472 [8:46:38<9:07:35,  3.72it/s]
 67%|██████▋   | 249099/371472 [8:46:38<9:22:32,  3.63it/s]
 67%|██████▋   | 249100/371472 [8:46:39<8:59:40,  3.78it/s]
                                                           
{'loss': 2.9455, 'learning_rate': 3.9664181516516185e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249100/371472 [8:46:39<8:59:40,  3.78it/s]
 67%|██████▋   | 249101/371472 [8:46:39<9:27:08,  3.60it/s]
 67%|██████▋   | 249102/371472 [8:46:39<9:21:41,  3.63it/s]
 67%|██████▋   | 249103/371472 [8:46:40<9:51:50,  3.45it/s]
 67%|██████▋   | 249104/371472 [8:46:40<9:36:18,  3.54it/s]
 67%|██████▋   | 249105/371472 [8:46:40<9:26:24,  3.60it/s]
 67%|██████▋   | 249106/371472 [8:46:40<9:06:16,  3.73it/s]
 67%|██████▋   | 249107/371472 [8:46:41<9:08:27,  3.72it/s]
 67%|██████▋   | 249108/371472 [8:46:41<9:18:57,  3.65it/s]
 67%|██████▋   | 249109/371472 [8:46:41<9:53:08,  3.44it/s]
 67%|██████▋   | 249110/371472 [8:46:42<10:25:16,  3.26it/s]
 67%|████��█▋   | 249111/371472 [8:46:42<9:40:22,  3.51it/s] 
 67%|██████▋   | 249112/371472 [8:46:42<9:27:32,  3.59it/s]
 67%|██████▋   | 249113/371472 [8:46:42<9:38:26,  3.53it/s]
 67%|██████▋   | 249114/371472 [8:46:43<9:39:03,  3.52it/s]
 67%|██████▋   | 249115/371472 [8:46:43<10:03:10,  3.38it/s]
 67%|██████▋   | 249116/371472 [8:46:43<9:40:15,  3.51it/s] 
 67%|██████▋   | 249117/371472 [8:46:44<9:39:03,  3.52it/s]
 67%|██████▋   | 249118/371472 [8:46:44<9:57:48,  3.41it/s]
 67%|██████▋   | 249119/371472 [8:46:44<9:30:25,  3.57it/s]
 67%|██████▋   | 249120/371472 [8:46:44<9:19:12,  3.65it/s]
                                                           
{'loss': 2.821, 'learning_rate': 3.96593333189683e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249120/371472 [8:46:44<9:19:12,  3.65it/s]
 67%|██████▋   | 249121/371472 [8:46:45<9:12:39,  3.69it/s]
 67%|██████▋   | 249122/371472 [8:46:45<9:45:19,  3.48it/s]
 67%|██████▋   | 249123/371472 [8:46:45<9:25:26,  3.61it/s]
 67%|██████▋   | 249124/371472 [8:46:45<9:37:35,  3.53it/s]
 67%|██████▋   | 249125/371472 [8:46:46<10:48:42,  3.14it/s]
 67%|██████▋   | 249126/371472 [8:46:46<10:45:51,  3.16it/s]
 67%|██████▋   | 249127/371472 [8:46:46<10:20:33,  3.29it/s]
 67%|██████▋   | 249128/371472 [8:46:47<10:26:45,  3.25it/s]
 67%|██████▋   | 249129/371472 [8:46:47<10:09:05,  3.35it/s]
 67%|██████▋   | 249130/371472 [8:46:47<9:30:15,  3.58it/s] 
 67%|██████▋   | 249131/371472 [8:46:48<9:32:04,  3.56it/s]
 67%|██████▋   | 249132/371472 [8:46:48<10:13:38,  3.32it/s]
 67%|██████▋   | 249133/371472 [8:46:48<9:51:37,  3.45it/s] 
 67%|██████▋   | 249134/371472 [8:46:48<9:38:53,  3.52it/s]
 67%|██████▋   | 249135/371472 [8:46:49<9:14:48,  3.68it/s]
 67%|██████▋   | 249136/371472 [8:46:49<8:58:20,  3.79it/s]
 67%|██████▋   | 249137/371472 [8:46:49<9:13:47,  3.68it/s]
 67%|██████▋   | 249138/371472 [8:46:50<9:14:50,  3.67it/s]
 67%|██████▋   | 249139/371472 [8:46:50<9:16:48,  3.66it/s]
 67%|██████▋   | 249140/371472 [8:46:50<9:59:43,  3.40it/s]
                                                           
{'loss': 2.8853, 'learning_rate': 3.965448512142041e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249140/371472 [8:46:50<9:59:43,  3.40it/s]
 67%|██████▋   | 249141/371472 [8:46:50<9:57:47,  3.41it/s]
 67%|██████▋   | 249142/371472 [8:46:51<9:52:14,  3.44it/s]
 67%|██████▋   | 249143/371472 [8:46:51<9:37:40,  3.53it/s]
 67%|██████▋   | 249144/371472 [8:46:51<9:30:58,  3.57it/s]
 67%|██████▋   | 249145/371472 [8:46:52<9:32:33,  3.56it/s]
 67%|██████▋   | 249146/371472 [8:46:52<9:45:07,  3.48it/s]
 67%|██████▋   | 249147/371472 [8:46:52<10:14:38,  3.32it/s]
 67%|██████▋   | 249148/371472 [8:46:52<9:42:42,  3.50it/s] 
 67%|██████▋   | 249149/371472 [8:46:53<9:30:31,  3.57it/s]
 67%|██████▋   | 249150/371472 [8:46:53<9:58:08,  3.41it/s]
 67%|██████▋   | 249151/371472 [8:46:53<9:26:49,  3.60it/s]
 67%|██████▋   | 249152/371472 [8:46:54<9:19:22,  3.64it/s]
 67%|██████▋   | 249153/371472 [8:46:54<9:29:19,  3.58it/s]
 67%|██████▋   | 249154/371472 [8:46:54<9:04:19,  3.75it/s]
 67%|██████▋   | 249155/371472 [8:46:54<9:21:28,  3.63it/s]
 67%|██████▋   | 249156/371472 [8:46:55<9:22:40,  3.62it/s]
 67%|██████▋   | 249157/371472 [8:46:55<11:01:27,  3.08it/s]
 67%|██████▋   | 249158/371472 [8:46:55<10:03:22,  3.38it/s]
 67%|██████▋   | 249159/371472 [8:46:56<9:37:26,  3.53it/s] 
 67%|██████▋   | 249160/371472 [8:46:56<9:38:20,  3.52it/s]
                                                           
{'loss': 2.8274, 'learning_rate': 3.964963692387252e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249160/371472 [8:46:56<9:38:20,  3.52it/s]
 67%|██████▋   | 249161/371472 [8:46:56<9:21:05,  3.63it/s]
 67%|██████▋   | 249162/371472 [8:46:56<9:05:25,  3.74it/s]
 67%|██████▋   | 249163/371472 [8:46:57<8:48:40,  3.86it/s]
 67%|██████▋   | 249164/371472 [8:46:57<8:57:01,  3.80it/s]
 67%|██████▋   | 249165/371472 [8:46:57<8:45:05,  3.88it/s]
 67%|██████▋   | 249166/371472 [8:46:57<8:40:38,  3.92it/s]
 67%|██████▋   | 249167/371472 [8:46:58<8:54:35,  3.81it/s]
 67%|██████▋   | 249168/371472 [8:46:58<8:59:33,  3.78it/s]
 67%|██████▋   | 249169/371472 [8:46:58<8:49:07,  3.85it/s]
 67%|██████▋   | 249170/371472 [8:46:58<8:55:13,  3.81it/s]
 67%|██████▋   | 249171/371472 [8:46:59<8:59:05,  3.78it/s]
 67%|██████▋   | 249172/371472 [8:46:59<9:13:59,  3.68it/s]
 67%|██████▋   | 249173/371472 [8:46:59<9:14:06,  3.68it/s]
 67%|██████▋   | 249174/371472 [8:46:59<9:02:26,  3.76it/s]
 67%|██████▋   | 249175/371472 [8:47:00<9:02:51,  3.75it/s]
 67%|██████▋   | 249176/371472 [8:47:00<9:02:34,  3.76it/s]
 67%|██████▋   | 249177/371472 [8:47:00<9:05:26,  3.74it/s]
 67%|██████▋   | 249178/371472 [8:47:01<10:07:52,  3.35it/s]
 67%|██████▋   | 249179/371472 [8:47:01<10:42:47,  3.17it/s]
 67%|██████▋   | 249180/371472 [8:47:01<10:13:30,  3.32it/s]
                                                            
{'loss': 2.9587, 'learning_rate': 3.964478872632463e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249180/371472 [8:47:01<10:13:30,  3.32it/s]
 67%|██████▋   | 249181/371472 [8:47:02<9:46:57,  3.47it/s] 
 67%|██████▋   | 249182/371472 [8:47:02<9:16:37,  3.66it/s]
 67%|██████▋   | 249183/371472 [8:47:02<9:35:47,  3.54it/s]
 67%|██████▋   | 249184/371472 [8:47:02<9:17:44,  3.65it/s]
 67%|██████▋   | 249185/371472 [8:47:03<9:43:26,  3.49it/s]
 67%|██████▋   | 249186/371472 [8:47:03<9:53:39,  3.43it/s]
 67%|██████▋   | 249187/371472 [8:47:03<9:32:14,  3.56it/s]
 67%|██████▋   | 249188/371472 [8:47:03<9:27:21,  3.59it/s]
 67%|██████▋   | 249189/371472 [8:47:04<10:03:09,  3.38it/s]
 67%|██████▋   | 249190/371472 [8:47:04<9:45:15,  3.48it/s] 
 67%|██████▋   | 249191/371472 [8:47:04<9:34:00,  3.55it/s]
 67%|██████▋   | 249192/371472 [8:47:05<9:01:56,  3.76it/s]
 67%|██████▋   | 249193/371472 [8:47:05<9:10:32,  3.70it/s]
 67%|██████▋   | 249194/371472 [8:47:05<8:45:08,  3.88it/s]
 67%|██████▋   | 249195/371472 [8:47:05<8:56:06,  3.80it/s]
 67%|██████▋   | 249196/371472 [8:47:06<8:50:19,  3.84it/s]
 67%|██████▋   | 249197/371472 [8:47:06<8:43:38,  3.89it/s]
 67%|██████▋   | 249198/371472 [8:47:06<9:43:36,  3.49it/s]
 67%|██████▋   | 249199/371472 [8:47:06<9:06:58,  3.73it/s]
 67%|██████▋   | 249200/371472 [8:47:07<9:42:24,  3.50it/s]
                                                           
{'loss': 3.0002, 'learning_rate': 3.963994052877674e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249200/371472 [8:47:07<9:42:24,  3.50it/s]
 67%|██████▋   | 249201/371472 [8:47:07<10:32:46,  3.22it/s]
 67%|██████▋   | 249202/371472 [8:47:07<9:57:18,  3.41it/s] 
 67%|██████▋   | 249203/371472 [8:47:08<9:29:17,  3.58it/s]
 67%|██████▋   | 249204/371472 [8:47:08<9:07:28,  3.72it/s]
 67%|██████▋   | 249205/371472 [8:47:08<9:29:45,  3.58it/s]
 67%|██████▋   | 249206/371472 [8:47:08<9:10:48,  3.70it/s]
 67%|██████▋   | 249207/371472 [8:47:09<9:19:35,  3.64it/s]
 67%|██████▋   | 249208/371472 [8:47:09<9:38:00,  3.53it/s]
 67%|██████▋   | 249209/371472 [8:47:09<9:58:03,  3.41it/s]
 67%|██████▋   | 249210/371472 [8:47:10<9:59:49,  3.40it/s]
 67%|██████▋   | 249211/371472 [8:47:10<9:41:44,  3.50it/s]
 67%|██████▋   | 249212/371472 [8:47:10<9:41:08,  3.51it/s]
 67%|██████▋   | 249213/371472 [8:47:10<9:13:54,  3.68it/s]
 67%|██████▋   | 249214/371472 [8:47:11<10:01:59,  3.38it/s]
 67%|██████▋   | 249215/371472 [8:47:11<9:54:45,  3.43it/s] 
 67%|██████▋   | 249216/371472 [8:47:11<10:04:42,  3.37it/s]
 67%|██████▋   | 249217/371472 [8:47:12<10:52:23,  3.12it/s]
 67%|██████▋   | 249218/371472 [8:47:12<10:11:44,  3.33it/s]
 67%|██████▋   | 249219/371472 [8:47:12<10:08:56,  3.35it/s]
 67%|██████▋   | 249220/371472 [8:47:13<9:42:47,  3.50it/s] 
                                                           
{'loss': 2.9325, 'learning_rate': 3.963509233122885e-07, 'epoch': 10.73}
+
 67%|██████▋   | 249220/371472 [8:47:13<9:42:47,  3.50it/s]
 67%|██████▋   | 249221/371472 [8:47:13<9:30:54,  3.57it/s]
 67%|██████▋   | 249222/371472 [8:47:13<9:21:24,  3.63it/s]
 67%|██████▋   | 249223/371472 [8:47:13<9:18:12,  3.65it/s]
 67%|██████▋   | 249224/371472 [8:47:14<9:11:38,  3.69it/s]
 67%|██████▋   | 249225/371472 [8:47:14<9:20:47,  3.63it/s]
 67%|██████▋   | 249226/371472 [8:47:14<8:54:32,  3.81it/s]
 67%|██████▋   | 249227/371472 [8:47:14<8:55:00,  3.81it/s]
 67%|██████▋   | 249228/371472 [8:47:15<9:12:07,  3.69it/s]
 67%|██████▋   | 249229/371472 [8:47:15<8:48:29,  3.86it/s]
 67%|██████▋   | 249230/371472 [8:47:15<10:38:37,  3.19it/s]
 67%|██████▋   | 249231/371472 [8:47:16<10:15:17,  3.31it/s]
 67%|████���█▋   | 249232/371472 [8:47:16<9:59:22,  3.40it/s] 
 67%|██████▋   | 249233/371472 [8:47:16<9:20:43,  3.63it/s]
 67%|██████▋   | 249234/371472 [8:47:16<9:38:46,  3.52it/s]
 67%|██████▋   | 249235/371472 [8:47:17<9:21:17,  3.63it/s]
 67%|██████▋   | 249236/371472 [8:47:17<9:50:43,  3.45it/s]
 67%|██████▋   | 249237/371472 [8:47:17<9:58:36,  3.40it/s]
 67%|██████▋   | 249238/371472 [8:47:18<9:41:35,  3.50it/s]
 67%|██████▋   | 249239/371472 [8:47:18<9:18:36,  3.65it/s]
 67%|██████▋   | 249240/371472 [8:47:18<9:43:26,  3.49it/s]
                                                           
{'loss': 2.6846, 'learning_rate': 3.9630244133680966e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249240/371472 [8:47:18<9:43:26,  3.49it/s]
 67%|██████▋   | 249241/371472 [8:47:18<9:47:57,  3.46it/s]
 67%|██████▋   | 249242/371472 [8:47:19<10:18:36,  3.29it/s]
 67%|██████▋   | 249243/371472 [8:47:19<9:44:48,  3.48it/s] 
 67%|██████▋   | 249244/371472 [8:47:19<9:54:16,  3.43it/s]
 67%|██████▋   | 249245/371472 [8:47:20<9:33:15,  3.55it/s]
 67%|██████▋   | 249246/371472 [8:47:20<9:37:23,  3.53it/s]
 67%|██████▋   | 249247/371472 [8:47:20<9:32:46,  3.56it/s]
 67%|██████▋   | 249248/371472 [8:47:20<9:17:14,  3.66it/s]
 67%|██████▋   | 249249/371472 [8:47:21<9:16:04,  3.66it/s]
 67%|██████▋   | 249250/371472 [8:47:21<9:05:55,  3.73it/s]
 67%|██████▋   | 249251/371472 [8:47:21<9:11:28,  3.69it/s]
 67%|██████▋   | 249252/371472 [8:47:21<9:01:25,  3.76it/s]
 67%|██████▋   | 249253/371472 [8:47:22<8:51:37,  3.83it/s]
 67%|██████▋   | 249254/371472 [8:47:22<8:36:05,  3.95it/s]
 67%|██████▋   | 249255/371472 [8:47:22<8:27:28,  4.01it/s]
 67%|██████▋   | 249256/371472 [8:47:23<9:39:53,  3.51it/s]
 67%|██████▋   | 249257/371472 [8:47:23<9:25:00,  3.61it/s]
 67%|██████▋   | 249258/371472 [8:47:23<10:42:12,  3.17it/s]
 67%|██████▋   | 249259/371472 [8:47:24<10:22:05,  3.27it/s]
 67%|██████▋   | 249260/371472 [8:47:24<10:07:38,  3.35it/s]
                                                            
{'loss': 2.9024, 'learning_rate': 3.9625395936133074e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249260/371472 [8:47:24<10:07:38,  3.35it/s]
 67%|██████▋   | 249261/371472 [8:47:24<9:48:29,  3.46it/s] 
 67%|██████▋   | 249262/371472 [8:47:24<9:30:19,  3.57it/s]
 67%|██████▋   | 249263/371472 [8:47:25<9:28:57,  3.58it/s]
 67%|██████▋   | 249264/371472 [8:47:25<9:01:28,  3.76it/s]
 67%|██████▋   | 249265/371472 [8:47:25<9:05:02,  3.74it/s]
 67%|██████▋   | 249266/371472 [8:47:25<8:56:31,  3.80it/s]
 67%|██████▋   | 249267/371472 [8:47:26<8:43:34,  3.89it/s]
 67%|██████▋   | 249268/371472 [8:47:26<8:58:58,  3.78it/s]
 67%|██████▋   | 249269/371472 [8:47:26<8:53:51,  3.82it/s]
 67%|██████▋   | 249270/371472 [8:47:26<9:04:10,  3.74it/s]
 67%|██████▋   | 249271/371472 [8:47:27<9:17:17,  3.65it/s]
 67%|██████▋   | 249272/371472 [8:47:27<9:05:57,  3.73it/s]
 67%|██████▋   | 249273/371472 [8:47:27<9:07:27,  3.72it/s]
 67%|██████▋   | 249274/371472 [8:47:28<9:03:22,  3.75it/s]
 67%|██████▋   | 249275/371472 [8:47:28<9:20:53,  3.63it/s]
 67%|██████▋   | 249276/371472 [8:47:28<9:37:29,  3.53it/s]
 67%|██████▋   | 249277/371472 [8:47:28<9:32:14,  3.56it/s]
 67%|██████▋   | 249278/371472 [8:47:29<9:32:00,  3.56it/s]
 67%|██████▋   | 249279/371472 [8:47:29<9:20:25,  3.63it/s]
 67%|██████▋   | 249280/371472 [8:47:29<9:27:12,  3.59it/s]
                                                           
{'loss': 2.7834, 'learning_rate': 3.9620547738585186e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249280/371472 [8:47:29<9:27:12,  3.59it/s]
 67%|██████▋   | 249281/371472 [8:47:29<9:13:50,  3.68it/s]
 67%|██████▋   | 249282/371472 [8:47:30<9:05:33,  3.73it/s]
 67%|██████▋   | 249283/371472 [8:47:30<8:50:02,  3.84it/s]
 67%|██████▋   | 249284/371472 [8:47:30<8:42:33,  3.90it/s]
 67%|██████▋   | 249285/371472 [8:47:30<8:28:10,  4.01it/s]
 67%|██████▋   | 249286/371472 [8:47:31<8:40:17,  3.91it/s]
 67%|██████▋   | 249287/371472 [8:47:31<8:46:50,  3.87it/s]
 67%|██████▋   | 249288/371472 [8:47:31<9:21:57,  3.62it/s]
 67%|██████▋   | 249289/371472 [8:47:32<9:18:25,  3.65it/s]
 67%|██████▋   | 249290/371472 [8:47:32<10:07:29,  3.35it/s]
 67%|██████▋   | 249291/371472 [8:47:32<9:44:55,  3.48it/s] 
 67%|██████▋   | 249292/371472 [8:47:32<9:30:22,  3.57it/s]
 67%|██████▋   | 249293/371472 [8:47:33<9:14:32,  3.67it/s]
 67%|██████▋   | 249294/371472 [8:47:33<9:20:28,  3.63it/s]
 67%|██████▋   | 249295/371472 [8:47:33<8:58:17,  3.78it/s]
 67%|██████▋   | 249296/371472 [8:47:33<9:02:17,  3.75it/s]
 67%|██████▋   | 249297/371472 [8:47:34<8:54:28,  3.81it/s]
 67%|██████▋   | 249298/371472 [8:47:34<9:11:07,  3.69it/s]
 67%|██████▋   | 249299/371472 [8:47:34<9:17:04,  3.66it/s]
 67%|██████▋   | 249300/371472 [8:47:35<9:00:23,  3.77it/s]
                                                           
{'loss': 2.7053, 'learning_rate': 3.9615699541037293e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249300/371472 [8:47:35<9:00:23,  3.77it/s]
 67%|██████▋   | 249301/371472 [8:47:35<9:54:09,  3.43it/s]
 67%|██████▋   | 249302/371472 [8:47:35<9:29:10,  3.58it/s]
 67%|██████▋   | 249303/371472 [8:47:35<9:44:17,  3.48it/s]
 67%|██████▋   | 249304/371472 [8:47:36<9:32:58,  3.55it/s]
 67%|██████▋   | 249305/371472 [8:47:36<9:20:08,  3.64it/s]
 67%|██████▋   | 249306/371472 [8:47:36<9:47:12,  3.47it/s]
 67%|██████▋   | 249307/371472 [8:47:37<9:50:58,  3.45it/s]
 67%|██████▋   | 249308/371472 [8:47:37<10:08:11,  3.35it/s]
 67%|██████▋   | 249309/371472 [8:47:37<9:36:06,  3.53it/s] 
 67%|██████▋   | 249310/371472 [8:47:37<9:16:19,  3.66it/s]
 67%|██████▋   | 249311/371472 [8:47:38<9:17:21,  3.65it/s]
 67%|██████▋   | 249312/371472 [8:47:38<9:09:45,  3.70it/s]
 67%|██████▋   | 249313/371472 [8:47:38<9:00:47,  3.76it/s]
 67%|██████▋   | 249314/371472 [8:47:38<8:56:26,  3.80it/s]
 67%|██████▋   | 249315/371472 [8:47:39<9:12:58,  3.68it/s]
 67%|██████▋   | 249316/371472 [8:47:39<9:14:39,  3.67it/s]
 67%|██████▋   | 249317/371472 [8:47:39<9:26:31,  3.59it/s]
 67%|██████▋   | 249318/371472 [8:47:40<9:10:01,  3.70it/s]
 67%|██████▋   | 249319/371472 [8:47:40<9:39:06,  3.52it/s]
 67%|██████▋   | 249320/371472 [8:47:40<9:35:02,  3.54it/s]
                                                           
{'loss': 2.739, 'learning_rate': 3.961085134348941e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249320/371472 [8:47:40<9:35:02,  3.54it/s]
 67%|██████▋   | 249321/371472 [8:47:40<9:16:23,  3.66it/s]
 67%|██████▋   | 249322/371472 [8:47:41<9:21:16,  3.63it/s]
 67%|██████▋   | 249323/371472 [8:47:41<9:10:51,  3.70it/s]
 67%|██████▋   | 249324/371472 [8:47:41<9:05:26,  3.73it/s]
 67%|██████▋   | 249325/371472 [8:47:42<9:09:15,  3.71it/s]
 67%|██████▋   | 249326/371472 [8:47:42<9:50:57,  3.44it/s]
 67%|██████▋   | 249327/371472 [8:47:42<9:21:54,  3.62it/s]
 67%|██████▋   | 249328/371472 [8:47:42<9:26:55,  3.59it/s]
 67%|██████▋   | 249329/371472 [8:47:43<9:28:37,  3.58it/s]
 67%|██████▋   | 249330/371472 [8:47:43<9:21:17,  3.63it/s]
 67%|██████▋   | 249331/371472 [8:47:43<9:00:44,  3.76it/s]
 67%|██████▋   | 249332/371472 [8:47:43<9:04:20,  3.74it/s]
 67%|██████▋   | 249333/371472 [8:47:44<9:00:49,  3.76it/s]
 67%|██████▋   | 249334/371472 [8:47:44<8:58:22,  3.78it/s]
 67%|██████▋   | 249335/371472 [8:47:44<8:50:18,  3.84it/s]
 67%|██████▋   | 249336/371472 [8:47:44<8:51:07,  3.83it/s]
 67%|██████▋   | 249337/371472 [8:47:45<8:44:55,  3.88it/s]
 67%|██████▋   | 249338/371472 [8:47:45<8:31:34,  3.98it/s]
 67%|██████▋   | 249339/371472 [8:47:45<9:15:06,  3.67it/s]
 67%|██████▋   | 249340/371472 [8:47:46<10:16:14,  3.30it/s]
                                                            
{'loss': 2.9674, 'learning_rate': 3.960600314594152e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249340/371472 [8:47:46<10:16:14,  3.30it/s]
 67%|██████▋   | 249341/371472 [8:47:46<9:58:27,  3.40it/s] 
 67%|██████▋   | 249342/371472 [8:47:46<9:56:34,  3.41it/s]
 67%|██████▋   | 249343/371472 [8:47:47<10:04:24,  3.37it/s]
 67%|██████▋   | 249344/371472 [8:47:47<10:31:21,  3.22it/s]
 67%|██████▋   | 249345/371472 [8:47:47<10:07:58,  3.35it/s]
 67%|██████▋   | 249346/371472 [8:47:47<9:58:59,  3.40it/s] 
 67%|██████▋   | 249347/371472 [8:47:48<9:28:32,  3.58it/s]
 67%|██████▋   | 249348/371472 [8:47:48<9:20:19,  3.63it/s]
 67%|██████▋   | 249349/371472 [8:47:48<9:07:02,  3.72it/s]
 67%|██████▋   | 249350/371472 [8:47:48<8:48:25,  3.85it/s]
 67%|██████▋   | 249351/371472 [8:47:49<8:50:43,  3.84it/s]
 67%|██████▋   | 249352/371472 [8:47:49<8:39:08,  3.92it/s]
 67%|██████▋   | 249353/371472 [8:47:49<9:03:47,  3.74it/s]
 67%|██████▋   | 249354/371472 [8:47:50<9:11:38,  3.69it/s]
 67%|██████▋   | 249355/371472 [8:47:50<9:14:29,  3.67it/s]
 67%|██████▋   | 249356/371472 [8:47:50<9:16:48,  3.66it/s]
 67%|██████▋   | 249357/371472 [8:47:50<8:55:49,  3.80it/s]
 67%|██████▋   | 249358/371472 [8:47:51<8:54:49,  3.81it/s]
 67%|██████▋   | 249359/371472 [8:47:51<10:21:06,  3.28it/s]
 67%|██████▋   | 249360/371472 [8:47:51<10:10:34,  3.33it/s]
                                                            
{'loss': 2.9267, 'learning_rate': 3.960115494839363e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249360/371472 [8:47:51<10:10:34,  3.33it/s]
 67%|██████▋   | 249361/371472 [8:47:52<9:53:17,  3.43it/s] 
 67%|██████▋   | 249362/371472 [8:47:52<10:01:30,  3.38it/s]
 67%|██████▋   | 249363/371472 [8:47:52<9:35:15,  3.54it/s] 
 67%|██████▋   | 249364/371472 [8:47:52<9:12:12,  3.69it/s]
 67%|██████▋   | 249365/371472 [8:47:53<9:27:39,  3.59it/s]
 67%|██████▋   | 249366/371472 [8:47:53<9:07:20,  3.72it/s]
 67%|██████▋   | 249367/371472 [8:47:53<9:06:13,  3.73it/s]
 67%|██████▋   | 249368/371472 [8:47:53<8:51:51,  3.83it/s]
 67%|██████▋   | 249369/371472 [8:47:54<8:45:38,  3.87it/s]
 67%|██████▋   | 249370/371472 [8:47:54<8:45:42,  3.87it/s]
 67%|██████▋   | 249371/371472 [8:47:54<9:58:22,  3.40it/s]
 67%|██████▋   | 249372/371472 [8:47:55<9:40:37,  3.50it/s]
 67%|██████▋   | 249373/371472 [8:47:55<9:37:44,  3.52it/s]
 67%|██████▋   | 249374/371472 [8:47:55<9:36:49,  3.53it/s]
 67%|██████▋   | 249375/371472 [8:47:55<9:14:10,  3.67it/s]
 67%|██████▋   | 249376/371472 [8:47:56<9:16:26,  3.66it/s]
 67%|██████▋   | 249377/371472 [8:47:56<9:28:37,  3.58it/s]
 67%|██████▋   | 249378/371472 [8:47:56<9:25:54,  3.60it/s]
 67%|██████▋   | 249379/371472 [8:47:56<9:12:29,  3.68it/s]
 67%|██████▋   | 249380/371472 [8:47:57<9:20:46,  3.63it/s]
                                                           
{'loss': 2.8215, 'learning_rate': 3.959630675084574e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249380/371472 [8:47:57<9:20:46,  3.63it/s]
 67%|██████▋   | 249381/371472 [8:47:57<9:33:45,  3.55it/s]
 67%|██████▋   | 249382/371472 [8:47:57<9:45:43,  3.47it/s]
 67%|██████▋   | 249383/371472 [8:47:58<9:18:44,  3.64it/s]
 67%|██████▋   | 249384/371472 [8:47:58<9:20:07,  3.63it/s]
 67%|██████▋   | 249385/371472 [8:47:58<9:04:19,  3.74it/s]
 67%|██████▋   | 249386/371472 [8:47:58<9:13:22,  3.68it/s]
 67%|██████▋   | 249387/371472 [8:47:59<9:10:16,  3.70it/s]
 67%|██████▋   | 249388/371472 [8:47:59<9:41:49,  3.50it/s]
 67%|██████▋   | 249389/371472 [8:47:59<9:26:24,  3.59it/s]
 67%|██████▋   | 249390/371472 [8:47:59<9:10:26,  3.70it/s]
 67%|██████▋   | 249391/371472 [8:48:00<10:01:02,  3.39it/s]
 67%|██████▋   | 249392/371472 [8:48:00<9:52:57,  3.43it/s] 
 67%|██████▋   | 249393/371472 [8:48:00<9:25:46,  3.60it/s]
 67%|██████▋   | 249394/371472 [8:48:01<9:12:57,  3.68it/s]
 67%|██████▋   | 249395/371472 [8:48:01<9:00:53,  3.76it/s]
 67%|██████▋   | 249396/371472 [8:48:01<8:45:58,  3.87it/s]
 67%|██████▋   | 249397/371472 [8:48:01<8:46:09,  3.87it/s]
 67%|██████▋   | 249398/371472 [8:48:02<8:52:36,  3.82it/s]
 67%|██████▋   | 249399/371472 [8:48:02<9:06:39,  3.72it/s]
 67%|██████▋   | 249400/371472 [8:48:02<9:17:03,  3.65it/s]
                                                           
{'loss': 2.9283, 'learning_rate': 3.9591458553297855e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249400/371472 [8:48:02<9:17:03,  3.65it/s]
 67%|██████▋   | 249401/371472 [8:48:02<9:12:43,  3.68it/s]
 67%|██████▋   | 249402/371472 [8:48:03<9:01:11,  3.76it/s]
 67%|██████▋   | 249403/371472 [8:48:03<8:48:22,  3.85it/s]
 67%|██████▋   | 249404/371472 [8:48:03<8:41:53,  3.90it/s]
 67%|██████▋   | 249405/371472 [8:48:03<8:34:21,  3.96it/s]
 67%|██████▋   | 249406/371472 [8:48:04<9:59:34,  3.39it/s]
 67%|██████▋   | 249407/371472 [8:48:04<10:15:01,  3.31it/s]
 67%|██████▋   | 249408/371472 [8:48:04<9:57:17,  3.41it/s] 
 67%|██████▋   | 249409/371472 [8:48:05<9:31:30,  3.56it/s]
 67%|██████▋   | 249410/371472 [8:48:05<9:45:37,  3.47it/s]
 67%|██████▋   | 249411/371472 [8:48:05<9:57:21,  3.41it/s]
 67%|██████▋   | 249412/371472 [8:48:06<9:35:22,  3.54it/s]
 67%|██████▋   | 249413/371472 [8:48:06<9:16:00,  3.66it/s]
 67%|██████▋   | 249414/371472 [8:48:06<9:49:59,  3.45it/s]
 67%|██████▋   | 249415/371472 [8:48:07<10:20:55,  3.28it/s]
 67%|██████▋   | 249416/371472 [8:48:07<10:18:50,  3.29it/s]
 67%|██████▋   | 249417/371472 [8:48:07<9:44:47,  3.48it/s] 
 67%|██████▋   | 249418/371472 [8:48:07<9:51:06,  3.44it/s]
 67%|██████▋   | 249419/371472 [8:48:08<10:07:55,  3.35it/s]
 67%|██████▋   | 249420/371472 [8:48:08<10:00:50,  3.39it/s]
                                                            
{'loss': 2.9136, 'learning_rate': 3.9586610355749957e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249420/371472 [8:48:08<10:00:50,  3.39it/s]
 67%|██████▋   | 249421/371472 [8:48:08<9:32:18,  3.55it/s] 
 67%|██████▋   | 249422/371472 [8:48:08<9:13:15,  3.68it/s]
 67%|██████▋   | 249423/371472 [8:48:09<9:01:29,  3.76it/s]
 67%|██████▋   | 249424/371472 [8:48:09<11:03:22,  3.07it/s]
 67%|██████▋   | 249425/371472 [8:48:09<10:22:29,  3.27it/s]
 67%|██████▋   | 249426/371472 [8:48:10<10:15:13,  3.31it/s]
 67%|██████▋   | 249427/371472 [8:48:10<10:36:51,  3.19it/s]
 67%|██████▋   | 249428/371472 [8:48:10<10:11:50,  3.32it/s]
 67%|██████▋   | 249429/371472 [8:48:11<9:58:20,  3.40it/s] 
 67%|██████▋   | 249430/371472 [8:48:11<9:38:06,  3.52it/s]
 67%|██████▋   | 249431/371472 [8:48:11<9:45:50,  3.47it/s]
 67%|██████▋   | 249432/371472 [8:48:11<9:45:56,  3.47it/s]
 67%|██████▋   | 249433/371472 [8:48:12<9:28:15,  3.58it/s]
 67%|██████▋   | 249434/371472 [8:48:12<9:12:03,  3.68it/s]
 67%|██████▋   | 249435/371472 [8:48:12<9:22:47,  3.61it/s]
 67%|██████▋   | 249436/371472 [8:48:13<9:05:03,  3.73it/s]
 67%|██████▋   | 249437/371472 [8:48:13<8:43:44,  3.88it/s]
 67%|██████▋   | 249438/371472 [8:48:13<9:08:09,  3.71it/s]
 67%|██████▋   | 249439/371472 [8:48:13<8:49:46,  3.84it/s]
 67%|██████▋   | 249440/371472 [8:48:14<10:08:15,  3.34it/s]
                                                            
{'loss': 2.8233, 'learning_rate': 3.9581762158202075e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249440/371472 [8:48:14<10:08:15,  3.34it/s]
 67%|██████▋   | 249441/371472 [8:48:14<9:56:09,  3.41it/s] 
 67%|██████▋   | 249442/371472 [8:48:14<9:32:06,  3.56it/s]
 67%|██████▋   | 249443/371472 [8:48:15<11:45:21,  2.88it/s]
 67%|██████▋   | 249444/371472 [8:48:15<10:55:03,  3.10it/s]
 67%|██████▋   | 249445/371472 [8:48:15<10:22:22,  3.27it/s]
 67%|██████▋   | 249446/371472 [8:48:16<10:28:33,  3.24it/s]
 67%|██████▋   | 249447/371472 [8:48:16<10:01:29,  3.38it/s]
 67%|██████▋   | 249448/371472 [8:48:16<9:28:46,  3.58it/s] 
 67%|██████▋   | 249449/371472 [8:48:16<9:19:45,  3.63it/s]
 67%|██████▋   | 249450/371472 [8:48:17<9:07:16,  3.72it/s]
 67%|██████▋   | 249451/371472 [8:48:17<8:58:43,  3.78it/s]
 67%|██████▋   | 249452/371472 [8:48:17<8:42:36,  3.89it/s]
 67%|██████▋   | 249453/371472 [8:48:17<9:21:25,  3.62it/s]
 67%|██████▋   | 249454/371472 [8:48:18<9:01:19,  3.76it/s]
 67%|██████▋   | 249455/371472 [8:48:18<8:54:39,  3.80it/s]
 67%|██████▋   | 249456/371472 [8:48:18<8:58:27,  3.78it/s]
 67%|██████▋   | 249457/371472 [8:48:18<8:55:19,  3.80it/s]
 67%|██████▋   | 249458/371472 [8:48:19<8:45:57,  3.87it/s]
 67%|██████▋   | 249459/371472 [8:48:19<9:02:54,  3.75it/s]
 67%|██████▋   | 249460/371472 [8:48:19<8:55:03,  3.80it/s]
                                                           
{'loss': 2.9242, 'learning_rate': 3.957691396065418e-07, 'epoch': 10.74}
+
 67%|██████▋   | 249460/371472 [8:48:19<8:55:03,  3.80it/s]
 67%|██████▋   | 249461/371472 [8:48:19<8:43:42,  3.88it/s]
 67%|██████▋   | 249462/371472 [8:48:20<8:37:41,  3.93it/s]
 67%|██████▋   | 249463/371472 [8:48:20<8:38:36,  3.92it/s]
 67%|██████▋   | 249464/371472 [8:48:20<9:15:05,  3.66it/s]
 67%|██████▋   | 249465/371472 [8:48:21<9:36:04,  3.53it/s]
 67%|██████▋   | 249466/371472 [8:48:21<10:05:57,  3.36it/s]
 67%|██████▋   | 249467/371472 [8:48:21<10:10:45,  3.33it/s]
 67%|██████▋   | 249468/371472 [8:48:21<9:49:41,  3.45it/s] 
 67%|██████▋   | 249469/371472 [8:48:22<9:51:56,  3.44it/s]
 67%|██████▋   | 249470/371472 [8:48:22<10:05:13,  3.36it/s]
 67%|██████▋   | 249471/371472 [8:48:22<10:07:24,  3.35it/s]
 67%|██████▋   | 249472/371472 [8:48:23<10:22:10,  3.27it/s]
 67%|██████▋   | 249473/371472 [8:48:23<9:55:29,  3.41it/s] 
 67%|██��███▋   | 249474/371472 [8:48:23<10:52:10,  3.12it/s]
 67%|██████▋   | 249475/371472 [8:48:24<10:26:30,  3.25it/s]
 67%|██████▋   | 249476/371472 [8:48:24<9:53:54,  3.42it/s] 
 67%|██████▋   | 249477/371472 [8:48:24<10:13:32,  3.31it/s]
 67%|██████▋   | 249478/371472 [8:48:24<9:35:36,  3.53it/s] 
 67%|██████▋   | 249479/371472 [8:48:25<9:07:16,  3.72it/s]
 67%|██████▋   | 249480/371472 [8:48:25<9:20:44,  3.63it/s]
                                                           
{'loss': 2.7983, 'learning_rate': 3.9572065763106295e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249480/371472 [8:48:25<9:20:44,  3.63it/s]
 67%|██████▋   | 249481/371472 [8:48:25<9:38:40,  3.51it/s]
 67%|██████▋   | 249482/371472 [8:48:26<9:18:52,  3.64it/s]
 67%|██████▋   | 249483/371472 [8:48:26<9:32:25,  3.55it/s]
 67%|██████▋   | 249484/371472 [8:48:26<9:57:00,  3.41it/s]
 67%|██████▋   | 249485/371472 [8:48:26<9:25:15,  3.60it/s]
 67%|██████▋   | 249486/371472 [8:48:27<9:20:58,  3.62it/s]
 67%|██████▋   | 249487/371472 [8:48:27<9:26:09,  3.59it/s]
 67%|██████▋   | 249488/371472 [8:48:27<9:14:18,  3.67it/s]
 67%|██████▋   | 249489/371472 [8:48:28<9:43:01,  3.49it/s]
 67%|██████▋   | 249490/371472 [8:48:28<9:27:09,  3.58it/s]
 67%|██████▋   | 249491/371472 [8:48:28<9:14:52,  3.66it/s]
 67%|██████▋   | 249492/371472 [8:48:28<9:10:41,  3.69it/s]
 67%|██████▋   | 249493/371472 [8:48:29<9:05:56,  3.72it/s]
 67%|██████▋   | 249494/371472 [8:48:29<9:08:54,  3.70it/s]
 67%|██████▋   | 249495/371472 [8:48:29<9:29:52,  3.57it/s]
 67%|██████▋   | 249496/371472 [8:48:29<9:17:07,  3.65it/s]
 67%|██████▋   | 249497/371472 [8:48:30<8:59:42,  3.77it/s]
 67%|██████▋   | 249498/371472 [8:48:30<9:27:26,  3.58it/s]
 67%|██████▋   | 249499/371472 [8:48:30<9:12:08,  3.68it/s]
 67%|██████▋   | 249500/371472 [8:48:30<8:58:47,  3.77it/s]
                                                           
{'loss': 2.7463, 'learning_rate': 3.95672175655584e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249500/371472 [8:48:30<8:58:47,  3.77it/s]
 67%|██████▋   | 249501/371472 [8:48:31<8:48:36,  3.85it/s]
 67%|██████▋   | 249502/371472 [8:48:31<8:36:27,  3.94it/s]
 67%|██████▋   | 249503/371472 [8:48:31<8:58:43,  3.77it/s]
 67%|██████▋   | 249504/371472 [8:48:32<9:26:36,  3.59it/s]
 67%|██████▋   | 249505/371472 [8:48:32<9:10:26,  3.69it/s]
 67%|██████▋   | 249506/371472 [8:48:32<9:13:32,  3.67it/s]
 67%|██████▋   | 249507/371472 [8:48:32<9:55:07,  3.42it/s]
 67%|██████▋   | 249508/371472 [8:48:33<9:29:36,  3.57it/s]
 67%|██████▋   | 249509/371472 [8:48:33<9:18:05,  3.64it/s]
 67%|██████▋   | 249510/371472 [8:48:33<9:06:24,  3.72it/s]
 67%|██████▋   | 249511/371472 [8:48:34<9:45:46,  3.47it/s]
 67%|██████▋   | 249512/371472 [8:48:34<10:11:33,  3.32it/s]
 67%|██████▋   | 249513/371472 [8:48:34<9:41:28,  3.50it/s] 
 67%|██████▋   | 249514/371472 [8:48:35<11:07:29,  3.05it/s]
 67%|██████▋   | 249515/371472 [8:48:35<10:21:15,  3.27it/s]
 67%|██████▋   | 249516/371472 [8:48:35<10:05:16,  3.36it/s]
 67%|██████▋   | 249517/371472 [8:48:35<10:26:34,  3.24it/s]
 67%|██████▋   | 249518/371472 [8:48:36<10:20:03,  3.28it/s]
 67%|██████▋   | 249519/371472 [8:48:36<9:38:24,  3.51it/s] 
 67%|██████▋   | 249520/371472 [8:48:36<9:14:44,  3.66it/s]
                                                           
{'loss': 2.9453, 'learning_rate': 3.956236936801052e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249520/371472 [8:48:36<9:14:44,  3.66it/s]
 67%|██████▋   | 249521/371472 [8:48:36<9:06:32,  3.72it/s]
 67%|██████▋   | 249522/371472 [8:48:37<9:13:25,  3.67it/s]
 67%|██████▋   | 249523/371472 [8:48:37<8:54:16,  3.80it/s]
 67%|██████▋   | 249524/371472 [8:48:37<10:40:31,  3.17it/s]
 67%|██████▋   | 249525/371472 [8:48:38<10:26:18,  3.25it/s]
 67%|██████▋   | 249526/371472 [8:48:38<10:21:23,  3.27it/s]
 67%|██████▋   | 249527/371472 [8:48:38<10:30:26,  3.22it/s]
 67%|██████▋   | 249528/371472 [8:48:39<9:55:49,  3.41it/s] 
 67%|██████▋   | 249529/371472 [8:48:39<10:16:52,  3.29it/s]
 67%|██████▋   | 249530/371472 [8:48:39<9:39:09,  3.51it/s] 
 67%|██████▋   | 249531/371472 [8:48:39<9:14:55,  3.66it/s]
 67%|██████▋   | 249532/371472 [8:48:40<9:43:06,  3.49it/s]
 67%|██████▋   | 249533/371472 [8:48:40<9:26:58,  3.58it/s]
 67%|██████▋   | 249534/371472 [8:48:40<9:30:21,  3.56it/s]
 67%|██████▋   | 249535/371472 [8:48:41<9:20:21,  3.63it/s]
 67%|██████▋   | 249536/371472 [8:48:41<9:52:44,  3.43it/s]
 67%|██████▋   | 249537/371472 [8:48:41<10:10:29,  3.33it/s]
 67%|██████▋   | 249538/371472 [8:48:41<9:39:14,  3.51it/s] 
 67%|██████▋   | 249539/371472 [8:48:42<9:32:19,  3.55it/s]
 67%|██████▋   | 249540/371472 [8:48:42<9:10:50,  3.69it/s]
                                                           
{'loss': 2.8029, 'learning_rate': 3.955752117046262e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249540/371472 [8:48:42<9:10:50,  3.69it/s]
 67%|██████▋   | 249541/371472 [8:48:42<9:17:18,  3.65it/s]
 67%|██████▋   | 249542/371472 [8:48:43<9:37:59,  3.52it/s]
 67%|██████▋   | 249543/371472 [8:48:43<9:45:02,  3.47it/s]
 67%|██████▋   | 249544/371472 [8:48:43<9:30:28,  3.56it/s]
 67%|██████▋   | 249545/371472 [8:48:43<9:37:22,  3.52it/s]
 67%|██████▋   | 249546/371472 [8:48:44<10:16:29,  3.30it/s]
 67%|██████▋   | 249547/371472 [8:48:44<9:46:41,  3.46it/s] 
 67%|██████▋   | 249548/371472 [8:48:44<9:49:09,  3.45it/s]
 67%|██████▋   | 249549/371472 [8:48:45<10:04:27,  3.36it/s]
 67%|██████▋   | 249550/371472 [8:48:45<10:00:13,  3.39it/s]
 67%|██████▋   | 249551/371472 [8:48:45<9:52:35,  3.43it/s] 
 67%|██████▋   | 249552/371472 [8:48:45<9:34:01,  3.54it/s]
 67%|██████▋   | 249553/371472 [8:48:46<9:32:32,  3.55it/s]
 67%|██████▋   | 249554/371472 [8:48:46<9:12:50,  3.68it/s]
 67%|██████▋   | 249555/371472 [8:48:46<10:05:13,  3.36it/s]
 67%|██████▋   | 249556/371472 [8:48:47<9:49:28,  3.45it/s] 
 67%|██████▋   | 249557/371472 [8:48:47<9:33:26,  3.54it/s]
 67%|██████▋   | 249558/371472 [8:48:47<9:21:58,  3.62it/s]
 67%|██████▋   | 249559/371472 [8:48:47<9:05:10,  3.73it/s]
 67%|██████▋   | 249560/371472 [8:48:48<9:14:14,  3.67it/s]
                                                           
{'loss': 2.7629, 'learning_rate': 3.955267297291474e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249560/371472 [8:48:48<9:14:14,  3.67it/s]
 67%|██████▋   | 249561/371472 [8:48:48<9:08:58,  3.70it/s]
 67%|██████▋   | 249562/371472 [8:48:48<9:36:27,  3.52it/s]
 67%|██████▋   | 249563/371472 [8:48:48<9:27:51,  3.58it/s]
 67%|██████▋   | 249564/371472 [8:48:49<9:12:31,  3.68it/s]
 67%|██████▋   | 249565/371472 [8:48:49<9:20:34,  3.62it/s]
 67%|██████▋   | 249566/371472 [8:48:49<9:34:29,  3.54it/s]
 67%|██████▋   | 249567/371472 [8:48:50<9:03:28,  3.74it/s]
 67%|██████▋   | 249568/371472 [8:48:50<8:59:32,  3.77it/s]
 67%|██████▋   | 249569/371472 [8:48:50<8:47:06,  3.85it/s]
 67%|██████▋   | 249570/371472 [8:48:50<9:07:08,  3.71it/s]
 67%|██████▋   | 249571/371472 [8:48:51<8:45:09,  3.87it/s]
 67%|██████▋   | 249572/371472 [8:48:51<9:15:33,  3.66it/s]
 67%|██████▋   | 249573/371472 [8:48:51<9:18:27,  3.64it/s]
 67%|██████▋   | 249574/371472 [8:48:51<8:56:18,  3.79it/s]
 67%|██████▋   | 249575/371472 [8:48:52<8:50:42,  3.83it/s]
 67%|██████▋   | 249576/371472 [8:48:52<8:47:54,  3.85it/s]
 67%|██████▋   | 249577/371472 [8:48:52<8:44:32,  3.87it/s]
 67%|██████▋   | 249578/371472 [8:48:52<9:00:32,  3.76it/s]
 67%|██████▋   | 249579/371472 [8:48:53<9:51:11,  3.44it/s]
 67%|██████▋   | 249580/371472 [8:48:53<10:03:49,  3.36it/s]
                                                            
{'loss': 2.7932, 'learning_rate': 3.9547824775366846e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249580/371472 [8:48:53<10:03:49,  3.36it/s]
 67%|██████▋   | 249581/371472 [8:48:53<10:04:24,  3.36it/s]
 67%|██████▋   | 249582/371472 [8:48:54<10:12:51,  3.31it/s]
 67%|██████▋   | 249583/371472 [8:48:54<10:13:39,  3.31it/s]
 67%|██████▋   | 249584/371472 [8:48:54<10:15:18,  3.30it/s]
 67%|██████▋   | 249585/371472 [8:48:55<9:55:44,  3.41it/s] 
 67%|██████▋   | 249586/371472 [8:48:55<9:41:00,  3.50it/s]
 67%|██████▋   | 249587/371472 [8:48:55<9:31:30,  3.55it/s]
 67%|██████▋   | 249588/371472 [8:48:55<9:21:03,  3.62it/s]
 67%|██████▋   | 249589/371472 [8:48:56<8:57:35,  3.78it/s]
 67%|██████▋   | 249590/371472 [8:48:56<9:19:17,  3.63it/s]
 67%|██████▋   | 249591/371472 [8:48:56<10:04:16,  3.36it/s]
 67%|██████▋   | 249592/371472 [8:48:57<9:57:12,  3.40it/s] 
 67%|██████▋   | 249593/371472 [8:48:57<9:38:18,  3.51it/s]
 67%|██████▋   | 249594/371472 [8:48:57<9:24:55,  3.60it/s]
 67%|██████▋   | 249595/371472 [8:48:57<9:34:51,  3.53it/s]
 67%|██████▋   | 249596/371472 [8:48:58<9:12:17,  3.68it/s]
 67%|██████▋   | 249597/371472 [8:48:58<9:14:26,  3.66it/s]
 67%|██████▋   | 249598/371472 [8:48:58<9:29:32,  3.57it/s]
 67%|██████▋   | 249599/371472 [8:48:58<9:02:12,  3.75it/s]
 67%|██████▋   | 249600/371472 [8:48:59<8:52:51,  3.81it/s]
                                                           
{'loss': 2.8735, 'learning_rate': 3.954297657781896e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249600/371472 [8:48:59<8:52:51,  3.81it/s]
 67%|██████▋   | 249601/371472 [8:48:59<8:55:52,  3.79it/s]
 67%|██████▋   | 249602/371472 [8:48:59<8:43:38,  3.88it/s]
 67%|██████▋   | 249603/371472 [8:49:00<9:15:29,  3.66it/s]
 67%|██████▋   | 249604/371472 [8:49:00<9:12:03,  3.68it/s]
 67%|██████▋   | 249605/371472 [8:49:00<9:06:44,  3.71it/s]
 67%|██████▋   | 249606/371472 [8:49:00<8:58:56,  3.77it/s]
 67%|██████▋   | 249607/371472 [8:49:01<9:16:24,  3.65it/s]
 67%|██████▋   | 249608/371472 [8:49:01<8:49:36,  3.83it/s]
 67%|██████▋   | 249609/371472 [8:49:01<8:35:19,  3.94it/s]
 67%|██████▋   | 249610/371472 [8:49:01<9:25:05,  3.59it/s]
 67%|██████▋   | 249611/371472 [8:49:02<9:35:46,  3.53it/s]
 67%|██████▋   | 249612/371472 [8:49:02<9:12:47,  3.67it/s]
 67%|██████▋   | 249613/371472 [8:49:02<8:58:30,  3.77it/s]
 67%|██████▋   | 249614/371472 [8:49:03<9:48:55,  3.45it/s]
 67%|██████▋   | 249615/371472 [8:49:03<9:25:35,  3.59it/s]
 67%|██████▋   | 249616/371472 [8:49:03<9:41:12,  3.49it/s]
 67%|██████▋   | 249617/371472 [8:49:03<9:46:04,  3.47it/s]
 67%|██████▋   | 249618/371472 [8:49:04<10:01:26,  3.38it/s]
 67%|██████▋   | 249619/371472 [8:49:04<9:40:49,  3.50it/s] 
 67%|██████▋   | 249620/371472 [8:49:04<9:30:25,  3.56it/s]
                                                           
{'loss': 2.8813, 'learning_rate': 3.953812838027106e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249620/371472 [8:49:04<9:30:25,  3.56it/s]
 67%|██████▋   | 249621/371472 [8:49:05<9:45:09,  3.47it/s]
 67%|██████▋   | 249622/371472 [8:49:05<9:24:09,  3.60it/s]
 67%|██████▋   | 249623/371472 [8:49:05<9:05:42,  3.72it/s]
 67%|██████▋   | 249624/371472 [8:49:05<9:13:13,  3.67it/s]
 67%|██████▋   | 249625/371472 [8:49:06<8:57:07,  3.78it/s]
 67%|██████▋   | 249626/371472 [8:49:06<9:13:46,  3.67it/s]
 67%|██████▋   | 249627/371472 [8:49:06<9:41:48,  3.49it/s]
 67%|██████▋   | 249628/371472 [8:49:06<9:38:50,  3.51it/s]
 67%|██████▋   | 249629/371472 [8:49:07<9:34:53,  3.53it/s]
 67%|██████▋   | 249630/371472 [8:49:07<9:31:09,  3.56it/s]
 67%|██████▋   | 249631/371472 [8:49:07<9:26:09,  3.59it/s]
 67%|██████▋   | 249632/371472 [8:49:08<9:16:06,  3.65it/s]
 67%|██████▋   | 249633/371472 [8:49:08<9:44:08,  3.48it/s]
 67%|██████▋   | 249634/371472 [8:49:08<9:46:49,  3.46it/s]
 67%|██████▋   | 249635/371472 [8:49:08<9:38:36,  3.51it/s]
 67%|██████▋   | 249636/371472 [8:49:09<9:14:20,  3.66it/s]
 67%|██████▋   | 249637/371472 [8:49:09<9:00:34,  3.76it/s]
 67%|██████▋   | 249638/371472 [8:49:09<9:07:13,  3.71it/s]
 67%|██████▋   | 249639/371472 [8:49:10<9:48:13,  3.45it/s]
 67%|██████▋   | 249640/371472 [8:49:10<9:32:27,  3.55it/s]
                                                           
{'loss': 2.9248, 'learning_rate': 3.9533280182723173e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249640/371472 [8:49:10<9:32:27,  3.55it/s]
 67%|██████▋   | 249641/371472 [8:49:10<9:21:04,  3.62it/s]
 67%|██████▋   | 249642/371472 [8:49:10<9:09:36,  3.69it/s]
 67%|██████▋   | 249643/371472 [8:49:11<9:06:49,  3.71it/s]
 67%|██████▋   | 249644/371472 [8:49:11<9:16:51,  3.65it/s]
 67%|██████▋   | 249645/371472 [8:49:11<9:05:55,  3.72it/s]
 67%|██████▋   | 249646/371472 [8:49:11<9:10:46,  3.69it/s]
 67%|██████▋   | 249647/371472 [8:49:12<8:48:15,  3.84it/s]
 67%|██████▋   | 249648/371472 [8:49:12<8:59:54,  3.76it/s]
 67%|██████▋   | 249649/371472 [8:49:12<9:04:45,  3.73it/s]
 67%|██████▋   | 249650/371472 [8:49:13<9:05:11,  3.72it/s]
 67%|██████▋   | 249651/371472 [8:49:13<8:45:03,  3.87it/s]
 67%|██████▋   | 249652/371472 [8:49:13<8:39:04,  3.91it/s]
 67%|██████▋   | 249653/371472 [8:49:13<8:44:19,  3.87it/s]
 67%|██████▋   | 249654/371472 [8:49:14<9:16:43,  3.65it/s]
 67%|██████▋   | 249655/371472 [8:49:14<9:03:24,  3.74it/s]
 67%|██████▋   | 249656/371472 [8:49:14<8:51:23,  3.82it/s]
 67%|██████▋   | 249657/371472 [8:49:14<8:45:16,  3.87it/s]
 67%|██████▋   | 249658/371472 [8:49:15<9:58:56,  3.39it/s]
 67%|██████▋   | 249659/371472 [8:49:15<9:46:28,  3.46it/s]
 67%|██████▋   | 249660/371472 [8:49:15<9:21:42,  3.61it/s]
                                                           
{'loss': 2.7933, 'learning_rate': 3.9528431985175285e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249660/371472 [8:49:15<9:21:42,  3.61it/s]
 67%|██████▋   | 249661/371472 [8:49:15<9:24:51,  3.59it/s]
 67%|██████▋   | 249662/371472 [8:49:16<9:05:30,  3.72it/s]
 67%|██████▋   | 249663/371472 [8:49:16<8:57:07,  3.78it/s]
 67%|██████▋   | 249664/371472 [8:49:16<9:08:37,  3.70it/s]
 67%|██████▋   | 249665/371472 [8:49:17<9:44:20,  3.47it/s]
 67%|██████▋   | 249666/371472 [8:49:17<9:49:27,  3.44it/s]
 67%|██████▋   | 249667/371472 [8:49:17<9:22:53,  3.61it/s]
 67%|██████▋   | 249668/371472 [8:49:17<9:30:09,  3.56it/s]
 67%|██████▋   | 249669/371472 [8:49:18<9:16:25,  3.65it/s]
 67%|██████▋   | 249670/371472 [8:49:18<9:40:49,  3.50it/s]
 67%|██████▋   | 249671/371472 [8:49:18<9:35:33,  3.53it/s]
 67%|██████▋   | 249672/371472 [8:49:19<9:46:21,  3.46it/s]
 67%|██████▋   | 249673/371472 [8:49:19<9:32:06,  3.55it/s]
 67%|██████▋   | 249674/371472 [8:49:19<9:09:41,  3.69it/s]
 67%|██████▋   | 249675/371472 [8:49:19<9:01:29,  3.75it/s]
 67%|██████▋   | 249676/371472 [8:49:20<9:09:46,  3.69it/s]
 67%|██████▋   | 249677/371472 [8:49:20<9:04:30,  3.73it/s]
 67%|██████▋   | 249678/371472 [8:49:20<9:08:05,  3.70it/s]
 67%|██████▋   | 249679/371472 [8:49:20<9:07:53,  3.70it/s]
 67%|██████▋   | 249680/371472 [8:49:21<9:07:04,  3.71it/s]
                                                           
{'loss': 2.9048, 'learning_rate': 3.952358378762739e-07, 'epoch': 10.75}
+
 67%|██████▋   | 249680/371472 [8:49:21<9:07:04,  3.71it/s]
 67%|██████▋   | 249681/371472 [8:49:21<9:08:11,  3.70it/s]
 67%|██████▋   | 249682/371472 [8:49:21<8:57:43,  3.77it/s]
 67%|██████▋   | 249683/371472 [8:49:21<8:42:37,  3.88it/s]
 67%|██████▋   | 249684/371472 [8:49:22<8:57:23,  3.78it/s]
 67%|██████▋   | 249685/371472 [8:49:22<9:23:33,  3.60it/s]
 67%|██████▋   | 249686/371472 [8:49:22<9:37:46,  3.51it/s]
 67%|██████▋   | 249687/371472 [8:49:23<9:36:59,  3.52it/s]
 67%|██████▋   | 249688/371472 [8:49:23<9:03:07,  3.74it/s]
 67%|██████▋   | 249689/371472 [8:49:23<9:08:21,  3.70it/s]
 67%|██████▋   | 249690/371472 [8:49:23<9:03:55,  3.73it/s]
 67%|██████▋   | 249691/371472 [8:49:24<9:05:45,  3.72it/s]
 67%|██████▋   | 249692/371472 [8:49:24<9:11:29,  3.68it/s]
 67%|██████▋   | 249693/371472 [8:49:24<9:09:52,  3.69it/s]
 67%|██████▋   | 249694/371472 [8:49:24<8:57:49,  3.77it/s]
 67%|██████▋   | 249695/371472 [8:49:25<8:58:48,  3.77it/s]
 67%|██████▋   | 249696/371472 [8:49:25<8:59:07,  3.76it/s]
 67%|██████▋   | 249697/371472 [8:49:25<9:03:12,  3.74it/s]
 67%|██████▋   | 249698/371472 [8:49:26<8:49:36,  3.83it/s]
 67%|██████▋   | 249699/371472 [8:49:26<9:07:05,  3.71it/s]
 67%|██████▋   | 249700/371472 [8:49:26<9:06:39,  3.71it/s]
                                                           
{'loss': 3.0998, 'learning_rate': 3.951873559007951e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249700/371472 [8:49:26<9:06:39,  3.71it/s]
 67%|██████▋   | 249701/371472 [8:49:26<9:08:11,  3.70it/s]
 67%|██████▋   | 249702/371472 [8:49:27<8:57:15,  3.78it/s]
 67%|██████▋   | 249703/371472 [8:49:27<9:16:51,  3.64it/s]
 67%|██████▋   | 249704/371472 [8:49:27<9:08:14,  3.70it/s]
 67%|██████▋   | 249705/371472 [8:49:27<9:14:33,  3.66it/s]
 67%|██████▋   | 249706/371472 [8:49:28<8:55:14,  3.79it/s]
 67%|██████▋   | 249707/371472 [8:49:28<9:02:34,  3.74it/s]
 67%|██████▋   | 249708/371472 [8:49:28<8:59:55,  3.76it/s]
 67%|██████▋   | 249709/371472 [8:49:28<8:52:16,  3.81it/s]
 67%|██████▋   | 249710/371472 [8:49:29<8:51:39,  3.82it/s]
 67%|██████▋   | 249711/371472 [8:49:29<8:45:59,  3.86it/s]
 67%|██████▋   | 249712/371472 [8:49:29<8:40:45,  3.90it/s]
 67%|██████▋   | 249713/371472 [8:49:30<8:29:48,  3.98it/s]
 67%|██████▋   | 249714/371472 [8:49:30<8:36:35,  3.93it/s]
 67%|██████▋   | 249715/371472 [8:49:30<8:38:00,  3.92it/s]
 67%|██████▋   | 249716/371472 [8:49:30<8:47:51,  3.84it/s]
 67%|██████▋   | 249717/371472 [8:49:31<9:39:48,  3.50it/s]
 67%|██████▋   | 249718/371472 [8:49:31<9:44:58,  3.47it/s]
 67%|██████▋   | 249719/371472 [8:49:31<9:45:13,  3.47it/s]
 67%|██████▋   | 249720/371472 [8:49:31<9:23:27,  3.60it/s]
                                                           
{'loss': 2.7288, 'learning_rate': 3.951388739253162e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249720/371472 [8:49:31<9:23:27,  3.60it/s]
 67%|██████▋   | 249721/371472 [8:49:32<9:56:30,  3.40it/s]
 67%|██████▋   | 249722/371472 [8:49:32<9:57:41,  3.40it/s]
 67%|██████▋   | 249723/371472 [8:49:32<9:49:08,  3.44it/s]
 67%|██████▋   | 249724/371472 [8:49:33<9:42:04,  3.49it/s]
 67%|██████▋   | 249725/371472 [8:49:33<9:21:37,  3.61it/s]
 67%|██████▋   | 249726/371472 [8:49:33<9:10:48,  3.68it/s]
 67%|██████▋   | 249727/371472 [8:49:33<9:33:17,  3.54it/s]
 67%|██████▋   | 249728/371472 [8:49:34<9:05:17,  3.72it/s]
 67%|██████▋   | 249729/371472 [8:49:34<9:13:25,  3.67it/s]
 67%|██████▋   | 249730/371472 [8:49:34<9:21:09,  3.62it/s]
 67%|██████▋   | 249731/371472 [8:49:35<8:52:25,  3.81it/s]
 67%|██████▋   | 249732/371472 [8:49:35<9:03:09,  3.74it/s]
 67%|██████▋   | 249733/371472 [8:49:35<8:55:05,  3.79it/s]
 67%|██████▋   | 249734/371472 [8:49:35<9:39:09,  3.50it/s]
 67%|██████▋   | 249735/371472 [8:49:36<9:31:43,  3.55it/s]
 67%|██████▋   | 249736/371472 [8:49:36<9:22:41,  3.61it/s]
 67%|██████▋   | 249737/371472 [8:49:36<9:03:17,  3.73it/s]
 67%|██████▋   | 249738/371472 [8:49:36<9:00:27,  3.75it/s]
 67%|██████▋   | 249739/371472 [8:49:37<9:30:42,  3.55it/s]
 67%|██████▋   | 249740/371472 [8:49:37<9:12:54,  3.67it/s]
                                                           
{'loss': 2.8761, 'learning_rate': 3.950903919498373e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249740/371472 [8:49:37<9:12:54,  3.67it/s]
 67%|██████▋   | 249741/371472 [8:49:37<9:29:22,  3.56it/s]
 67%|██████▋   | 249742/371472 [8:49:38<9:31:05,  3.55it/s]
 67%|██████▋   | 249743/371472 [8:49:38<9:12:55,  3.67it/s]
 67%|██████▋   | 249744/371472 [8:49:38<9:31:16,  3.55it/s]
 67%|██████▋   | 249745/371472 [8:49:38<9:22:02,  3.61it/s]
 67%|██████▋   | 249746/371472 [8:49:39<10:53:31,  3.10it/s]
 67%|██████▋   | 249747/371472 [8:49:39<11:05:48,  3.05it/s]
 67%|██████▋   | 249748/371472 [8:49:39<10:29:33,  3.22it/s]
 67%|██████▋   | 249749/371472 [8:49:40<10:13:36,  3.31it/s]
 67%|██████▋   | 249750/371472 [8:49:40<9:43:24,  3.48it/s] 
 67%|██████▋   | 249751/371472 [8:49:40<9:19:56,  3.62it/s]
 67%|██████▋   | 249752/371472 [8:49:40<8:54:03,  3.80it/s]
 67%|██████▋   | 249753/371472 [8:49:41<8:46:30,  3.85it/s]
 67%|██████▋   | 249754/371472 [8:49:41<8:37:12,  3.92it/s]
 67%|██████▋   | 249755/371472 [8:49:41<9:16:08,  3.65it/s]
 67%|██████▋   | 249756/371472 [8:49:42<8:53:51,  3.80it/s]
 67%|██████▋   | 249757/371472 [8:49:42<8:33:56,  3.95it/s]
 67%|██████▋   | 249758/371472 [8:49:42<8:39:19,  3.91it/s]
 67%|██████▋   | 249759/371472 [8:49:42<9:05:23,  3.72it/s]
 67%|██████▋   | 249760/371472 [8:49:43<9:05:53,  3.72it/s]
                                                           
{'loss': 2.8132, 'learning_rate': 3.9504190997435837e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249760/371472 [8:49:43<9:05:53,  3.72it/s]
 67%|██████▋   | 249761/371472 [8:49:43<8:54:39,  3.79it/s]
 67%|██████▋   | 249762/371472 [8:49:43<9:17:18,  3.64it/s]
 67%|██████▋   | 249763/371472 [8:49:43<9:05:36,  3.72it/s]
 67%|██████▋   | 249764/371472 [8:49:44<9:24:41,  3.59it/s]
 67%|██████▋   | 249765/371472 [8:49:44<10:01:07,  3.37it/s]
 67%|██████▋   | 249766/371472 [8:49:44<10:23:01,  3.26it/s]
 67%|██████▋   | 249767/371472 [8:49:45<10:07:05,  3.34it/s]
 67%|██████▋   | 249768/371472 [8:49:45<10:08:44,  3.33it/s]
 67%|██████▋   | 249769/371472 [8:49:45<9:59:49,  3.38it/s] 
 67%|██████▋   | 249770/371472 [8:49:45<9:27:19,  3.58it/s]
 67%|██████▋   | 249771/371472 [8:49:46<9:04:47,  3.72it/s]
 67%|██████▋   | 249772/371472 [8:49:46<9:03:07,  3.73it/s]
 67%|██████▋   | 249773/371472 [8:49:46<9:56:07,  3.40it/s]
 67%|██████▋   | 249774/371472 [8:49:47<9:32:48,  3.54it/s]
 67%|██████▋   | 249775/371472 [8:49:47<9:13:00,  3.67it/s]
 67%|██████▋   | 249776/371472 [8:49:47<9:17:33,  3.64it/s]
 67%|██████▋   | 249777/371472 [8:49:47<8:54:54,  3.79it/s]
 67%|██████▋   | 249778/371472 [8:49:48<9:05:39,  3.72it/s]
 67%|██████▋   | 249779/371472 [8:49:48<9:34:04,  3.53it/s]
 67%|██████▋   | 249780/371472 [8:49:48<9:19:31,  3.62it/s]
                                                           
{'loss': 2.9514, 'learning_rate': 3.9499342799887955e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249780/371472 [8:49:48<9:19:31,  3.62it/s]
 67%|██████▋   | 249781/371472 [8:49:49<9:36:06,  3.52it/s]
 67%|██████▋   | 249782/371472 [8:49:49<9:23:06,  3.60it/s]
 67%|██████▋   | 249783/371472 [8:49:49<9:40:19,  3.49it/s]
 67%|██████▋   | 249784/371472 [8:49:49<9:16:59,  3.64it/s]
 67%|██████▋   | 249785/371472 [8:49:50<9:46:20,  3.46it/s]
 67%|██████▋   | 249786/371472 [8:49:50<10:06:26,  3.34it/s]
 67%|██████▋   | 249787/371472 [8:49:50<9:36:58,  3.51it/s] 
 67%|██████▋   | 249788/371472 [8:49:50<9:24:34,  3.59it/s]
 67%|██████▋   | 249789/371472 [8:49:51<9:41:42,  3.49it/s]
 67%|██████▋   | 249790/371472 [8:49:51<9:36:19,  3.52it/s]
 67%|██████▋   | 249791/371472 [8:49:51<9:28:19,  3.57it/s]
 67%|██████▋   | 249792/371472 [8:49:52<10:13:42,  3.30it/s]
 67%|██████▋   | 249793/371472 [8:49:52<10:01:46,  3.37it/s]
 67%|██████▋   | 249794/371472 [8:49:52<9:44:44,  3.47it/s] 
 67%|██████▋   | 249795/371472 [8:49:53<9:29:48,  3.56it/s]
 67%|██████▋   | 249796/371472 [8:49:53<10:09:42,  3.33it/s]
 67%|██████▋   | 249797/371472 [8:49:53<9:33:52,  3.53it/s] 
 67%|██████▋   | 249798/371472 [8:49:53<9:04:57,  3.72it/s]
 67%|██████▋   | 249799/371472 [8:49:54<8:51:34,  3.81it/s]
 67%|██████▋   | 249800/371472 [8:49:54<8:50:41,  3.82it/s]
                                                           
{'loss': 2.7965, 'learning_rate': 3.9494494602340057e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249800/371472 [8:49:54<8:50:41,  3.82it/s]
 67%|██████▋   | 249801/371472 [8:49:54<9:33:15,  3.54it/s]
 67%|██████▋   | 249802/371472 [8:49:54<9:39:52,  3.50it/s]
 67%|██████▋   | 249803/371472 [8:49:55<9:28:06,  3.57it/s]
 67%|██████▋   | 249804/371472 [8:49:55<9:04:43,  3.72it/s]
 67%|██████▋   | 249805/371472 [8:49:55<9:38:07,  3.51it/s]
 67%|██████▋   | 249806/371472 [8:49:56<9:26:25,  3.58it/s]
 67%|██████▋   | 249807/371472 [8:49:56<9:26:56,  3.58it/s]
 67%|██████▋   | 249808/371472 [8:49:56<9:15:23,  3.65it/s]
 67%|██████▋   | 249809/371472 [8:49:56<9:12:51,  3.67it/s]
 67%|██████▋   | 249810/371472 [8:49:57<9:30:15,  3.56it/s]
 67%|██████▋   | 249811/371472 [8:49:57<9:55:11,  3.41it/s]
 67%|██████▋   | 249812/371472 [8:49:57<9:26:46,  3.58it/s]
 67%|██████▋   | 249813/371472 [8:49:57<9:07:39,  3.70it/s]
 67%|██████▋   | 249814/371472 [8:49:58<9:30:11,  3.56it/s]
 67%|██████▋   | 249815/371472 [8:49:58<9:21:24,  3.61it/s]
 67%|██████▋   | 249816/371472 [8:49:58<9:23:51,  3.60it/s]
 67%|██████▋   | 249817/371472 [8:49:59<9:46:20,  3.46it/s]
 67%|██████▋   | 249818/371472 [8:49:59<9:50:17,  3.43it/s]
 67%|██████▋   | 249819/371472 [8:49:59<10:14:32,  3.30it/s]
 67%|██████▋   | 249820/371472 [8:50:00<9:46:40,  3.46it/s] 
                                                           
{'loss': 2.9526, 'learning_rate': 3.9489646404792174e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249820/371472 [8:50:00<9:46:40,  3.46it/s]
 67%|██████▋   | 249821/371472 [8:50:00<9:30:30,  3.55it/s]
 67%|██████▋   | 249822/371472 [8:50:00<9:06:29,  3.71it/s]
 67%|██████▋   | 249823/371472 [8:50:00<9:37:22,  3.51it/s]
 67%|██████▋   | 249824/371472 [8:50:01<9:26:07,  3.58it/s]
 67%|██████▋   | 249825/371472 [8:50:01<9:22:40,  3.60it/s]
 67%|██████▋   | 249826/371472 [8:50:01<9:42:48,  3.48it/s]
 67%|██████▋   | 249827/371472 [8:50:02<10:04:10,  3.36it/s]
 67%|██████▋   | 249828/371472 [8:50:02<9:41:39,  3.49it/s] 
 67%|██████▋   | 249829/371472 [8:50:02<9:39:54,  3.50it/s]
 67%|██████▋   | 249830/371472 [8:50:02<9:32:02,  3.54it/s]
 67%|██████▋   | 249831/371472 [8:50:03<9:52:58,  3.42it/s]
 67%|██████▋   | 249832/371472 [8:50:03<9:27:44,  3.57it/s]
 67%|██████▋   | 249833/371472 [8:50:03<9:24:04,  3.59it/s]
 67%|██████▋   | 249834/371472 [8:50:03<9:24:04,  3.59it/s]
 67%|██████▋   | 249835/371472 [8:50:04<9:06:26,  3.71it/s]
 67%|██████▋   | 249836/371472 [8:50:04<9:03:09,  3.73it/s]
 67%|██████▋   | 249837/371472 [8:50:04<8:59:02,  3.76it/s]
 67%|██████▋   | 249838/371472 [8:50:05<9:00:30,  3.75it/s]
 67%|██████▋   | 249839/371472 [8:50:05<9:43:41,  3.47it/s]
 67%|██████▋   | 249840/371472 [8:50:05<9:44:10,  3.47it/s]
                                                           
{'loss': 2.7673, 'learning_rate': 3.948479820724428e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249840/371472 [8:50:05<9:44:10,  3.47it/s]
 67%|██████▋   | 249841/371472 [8:50:05<9:43:27,  3.47it/s]
 67%|██████▋   | 249842/371472 [8:50:06<9:47:41,  3.45it/s]
 67%|██████▋   | 249843/371472 [8:50:06<9:45:21,  3.46it/s]
 67%|██████▋   | 249844/371472 [8:50:06<9:57:48,  3.39it/s]
 67%|██████▋   | 249845/371472 [8:50:07<9:54:50,  3.41it/s]
 67%|██████▋   | 249846/371472 [8:50:07<9:52:45,  3.42it/s]
 67%|██████▋   | 249847/371472 [8:50:07<9:28:27,  3.57it/s]
 67%|██████▋   | 249848/371472 [8:50:07<9:39:17,  3.50it/s]
 67%|██████▋   | 249849/371472 [8:50:08<10:01:58,  3.37it/s]
 67%|██████▋   | 249850/371472 [8:50:08<9:46:03,  3.46it/s] 
 67%|██████▋   | 249851/371472 [8:50:08<9:37:04,  3.51it/s]
 67%|██████▋   | 249852/371472 [8:50:09<9:27:09,  3.57it/s]
 67%|██████▋   | 249853/371472 [8:50:09<9:07:23,  3.70it/s]
 67%|██████▋   | 249854/371472 [8:50:09<9:12:11,  3.67it/s]
 67%|██████▋   | 249855/371472 [8:50:09<9:13:01,  3.67it/s]
 67%|██████▋   | 249856/371472 [8:50:10<9:11:13,  3.68it/s]
 67%|██████▋   | 249857/371472 [8:50:10<9:17:20,  3.64it/s]
 67%|██████▋   | 249858/371472 [8:50:10<9:05:23,  3.72it/s]
 67%|██████▋   | 249859/371472 [8:50:10<8:54:11,  3.79it/s]
 67%|██████▋   | 249860/371472 [8:50:11<8:43:55,  3.87it/s]
                                                           
{'loss': 2.8793, 'learning_rate': 3.9479950009696394e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249860/371472 [8:50:11<8:43:55,  3.87it/s]
 67%|██████▋   | 249861/371472 [8:50:11<8:41:54,  3.88it/s]
 67%|██████▋   | 249862/371472 [8:50:11<8:52:14,  3.81it/s]
 67%|██████▋   | 249863/371472 [8:50:11<8:42:48,  3.88it/s]
 67%|██████▋   | 249864/371472 [8:50:12<8:34:59,  3.94it/s]
 67%|██████▋   | 249865/371472 [8:50:12<9:00:15,  3.75it/s]
 67%|██████▋   | 249866/371472 [8:50:12<9:02:39,  3.73it/s]
 67%|██████▋   | 249867/371472 [8:50:13<9:21:20,  3.61it/s]
 67%|██████▋   | 249868/371472 [8:50:13<9:27:42,  3.57it/s]
 67%|██████▋   | 249869/371472 [8:50:13<8:57:54,  3.77it/s]
 67%|██████▋   | 249870/371472 [8:50:13<8:48:56,  3.83it/s]
 67%|██████▋   | 249871/371472 [8:50:14<8:43:01,  3.87it/s]
 67%|██████▋   | 249872/371472 [8:50:14<8:38:09,  3.91it/s]
 67%|██████▋   | 249873/371472 [8:50:14<9:18:31,  3.63it/s]
 67%|██████▋   | 249874/371472 [8:50:15<9:48:52,  3.44it/s]
 67%|██████▋   | 249875/371472 [8:50:15<9:26:29,  3.58it/s]
 67%|██████▋   | 249876/371472 [8:50:15<9:21:08,  3.61it/s]
 67%|██████▋   | 249877/371472 [8:50:15<9:56:58,  3.39it/s]
 67%|██████▋   | 249878/371472 [8:50:16<9:53:09,  3.42it/s]
 67%|██████▋   | 249879/371472 [8:50:16<9:31:27,  3.55it/s]
 67%|██████▋   | 249880/371472 [8:50:16<9:28:04,  3.57it/s]
                                                           
{'loss': 2.8122, 'learning_rate': 3.94751018121485e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249880/371472 [8:50:16<9:28:04,  3.57it/s]
 67%|██████▋   | 249881/371472 [8:50:16<9:23:22,  3.60it/s]
 67%|██████▋   | 249882/371472 [8:50:17<9:05:07,  3.72it/s]
 67%|██████▋   | 249883/371472 [8:50:17<10:21:23,  3.26it/s]
 67%|██████▋   | 249884/371472 [8:50:17<10:03:32,  3.36it/s]
 67%|██████▋   | 249885/371472 [8:50:18<9:43:11,  3.47it/s] 
 67%|██████▋   | 249886/371472 [8:50:18<9:22:51,  3.60it/s]
 67%|██████▋   | 249887/371472 [8:50:18<9:15:50,  3.65it/s]
 67%|██████▋   | 249888/371472 [8:50:18<9:33:47,  3.53it/s]
 67%|██████▋   | 249889/371472 [8:50:19<9:17:49,  3.63it/s]
 67%|██████▋   | 249890/371472 [8:50:19<9:14:07,  3.66it/s]
 67%|██████▋   | 249891/371472 [8:50:19<9:37:16,  3.51it/s]
 67%|██████▋   | 249892/371472 [8:50:20<9:35:26,  3.52it/s]
 67%|██████▋   | 249893/371472 [8:50:20<9:50:44,  3.43it/s]
 67%|██████▋   | 249894/371472 [8:50:20<9:22:28,  3.60it/s]
 67%|██████▋   | 249895/371472 [8:50:20<8:52:35,  3.80it/s]
 67%|██████▋   | 249896/371472 [8:50:21<8:58:45,  3.76it/s]
 67%|██████▋   | 249897/371472 [8:50:21<8:43:15,  3.87it/s]
 67%|██████▋   | 249898/371472 [8:50:21<8:48:50,  3.83it/s]
 67%|██████▋   | 249899/371472 [8:50:21<9:14:59,  3.65it/s]
 67%|██████▋   | 249900/371472 [8:50:22<8:57:29,  3.77it/s]
                                                           
{'loss': 2.752, 'learning_rate': 3.947025361460062e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249900/371472 [8:50:22<8:57:29,  3.77it/s]
 67%|██████▋   | 249901/371472 [8:50:22<8:53:21,  3.80it/s]
 67%|██████▋   | 249902/371472 [8:50:22<9:03:55,  3.73it/s]
 67%|██████▋   | 249903/371472 [8:50:22<8:50:32,  3.82it/s]
 67%|██████▋   | 249904/371472 [8:50:23<9:00:55,  3.75it/s]
 67%|██████▋   | 249905/371472 [8:50:23<9:17:08,  3.64it/s]
 67%|██████▋   | 249906/371472 [8:50:23<9:21:43,  3.61it/s]
 67%|██████▋   | 249907/371472 [8:50:24<9:27:37,  3.57it/s]
 67%|██████▋   | 249908/371472 [8:50:24<9:44:45,  3.46it/s]
 67%|██████▋   | 249909/371472 [8:50:24<9:26:53,  3.57it/s]
 67%|██████▋   | 249910/371472 [8:50:25<10:04:45,  3.35it/s]
 67%|██████▋   | 249911/371472 [8:50:25<9:42:26,  3.48it/s] 
 67%|██████▋   | 249912/371472 [8:50:25<9:50:28,  3.43it/s]
 67%|██████▋   | 249913/371472 [8:50:25<9:33:41,  3.53it/s]
 67%|██████▋   | 249914/371472 [8:50:26<9:16:52,  3.64it/s]
 67%|██████▋   | 249915/371472 [8:50:26<9:10:57,  3.68it/s]
 67%|██████▋   | 249916/371472 [8:50:26<9:17:18,  3.64it/s]
 67%|██████▋   | 249917/371472 [8:50:26<9:03:32,  3.73it/s]
 67%|██████▋   | 249918/371472 [8:50:27<8:56:03,  3.78it/s]
 67%|██████▋   | 249919/371472 [8:50:27<9:52:37,  3.42it/s]
 67%|██████▋   | 249920/371472 [8:50:27<9:43:27,  3.47it/s]
                                                           
{'loss': 2.7637, 'learning_rate': 3.946540541705272e-07, 'epoch': 10.76}
+
 67%|██████▋   | 249920/371472 [8:50:27<9:43:27,  3.47it/s]
 67%|██████▋   | 249921/371472 [8:50:28<11:13:29,  3.01it/s]
 67%|██████▋   | 249922/371472 [8:50:28<10:52:16,  3.11it/s]
 67%|██████▋   | 249923/371472 [8:50:28<10:21:39,  3.26it/s]
 67%|██████▋   | 249924/371472 [8:50:29<9:44:56,  3.46it/s] 
 67%|██████▋   | 249925/371472 [8:50:29<10:05:35,  3.35it/s]
 67%|██████▋   | 249926/371472 [8:50:29<10:03:16,  3.36it/s]
 67%|██████▋   | 249927/371472 [8:50:29<10:00:47,  3.37it/s]
 67%|██████▋   | 249928/371472 [8:50:30<9:24:12,  3.59it/s] 
 67%|██████▋   | 249929/371472 [8:50:30<9:52:48,  3.42it/s]
 67%|██████▋   | 249930/371472 [8:50:30<10:17:23,  3.28it/s]
 67%|██████▋   | 249931/371472 [8:50:31<9:50:07,  3.43it/s] 
 67%|██████▋   | 249932/371472 [8:50:31<9:23:01,  3.60it/s]
 67%|██████▋   | 249933/371472 [8:50:31<9:13:57,  3.66it/s]
 67%|██████▋   | 249934/371472 [8:50:32<10:16:19,  3.29it/s]
 67%|██████▋   | 249935/371472 [8:50:32<9:55:10,  3.40it/s] 
 67%|██████▋   | 249936/371472 [8:50:32<9:24:51,  3.59it/s]
 67%|██████▋   | 249937/371472 [8:50:32<9:05:18,  3.71it/s]
 67%|██████▋   | 249938/371472 [8:50:33<9:59:45,  3.38it/s]
 67%|██████▋   | 249939/371472 [8:50:33<9:24:55,  3.59it/s]
 67%|██████▋   | 249940/371472 [8:50:33<9:03:24,  3.73it/s]
                                                           
{'loss': 2.8339, 'learning_rate': 3.946055721950484e-07, 'epoch': 10.77}
+
 67%|██████▋   | 249940/371472 [8:50:33<9:03:24,  3.73it/s]
 67%|██████▋   | 249941/371472 [8:50:33<8:57:33,  3.77it/s]
 67%|██████▋   | 249942/371472 [8:50:34<8:49:32,  3.82it/s]
 67%|██████▋   | 249943/371472 [8:50:34<8:54:34,  3.79it/s]
 67%|██████▋   | 249944/371472 [8:50:34<8:47:21,  3.84it/s]
 67%|██████▋   | 249945/371472 [8:50:34<8:51:55,  3.81it/s]
 67%|██████▋   | 249946/371472 [8:50:35<8:52:49,  3.80it/s]
 67%|██████▋   | 249947/371472 [8:50:35<8:58:23,  3.76it/s]
 67%|██████▋   | 249948/371472 [8:50:35<9:30:10,  3.55it/s]
 67%|██████▋   | 249949/371472 [8:50:36<9:32:06,  3.54it/s]
 67%|██████▋   | 249950/371472 [8:50:36<9:58:14,  3.39it/s]
 67%|██████▋   | 249951/371472 [8:50:36<10:08:25,  3.33it/s]
 67%|██████▋   | 249952/371472 [8:50:36<9:45:11,  3.46it/s] 
 67%|██████▋   | 249953/371472 [8:50:37<9:46:21,  3.45it/s]
 67%|██████▋   | 249954/371472 [8:50:37<10:14:20,  3.30it/s]
 67%|██████▋   | 249955/371472 [8:50:37<9:50:51,  3.43it/s] 
 67%|██████▋   | 249956/371472 [8:50:38<9:18:00,  3.63it/s]
 67%|██████▋   | 249957/371472 [8:50:38<9:28:57,  3.56it/s]
 67%|██████▋   | 249958/371472 [8:50:38<9:38:24,  3.50it/s]
 67%|██████▋   | 249959/371472 [8:50:38<9:08:51,  3.69it/s]
 67%|██████▋   | 249960/371472 [8:50:39<9:10:26,  3.68it/s]
                                                           
{'loss': 2.724, 'learning_rate': 3.9455709021956946e-07, 'epoch': 10.77}
+
 67%|██████▋   | 249960/371472 [8:50:39<9:10:26,  3.68it/s]
 67%|██████▋   | 249961/371472 [8:50:39<9:00:35,  3.75it/s]
 67%|██████▋   | 249962/371472 [8:50:39<9:04:11,  3.72it/s]
 67%|██████▋   | 249963/371472 [8:50:40<9:31:13,  3.55it/s]
 67%|██████▋   | 249964/371472 [8:50:40<9:09:50,  3.68it/s]
 67%|██████▋   | 249965/371472 [8:50:40<9:35:23,  3.52it/s]
 67%|██████▋   | 249966/371472 [8:50:40<9:10:25,  3.68it/s]
 67%|██████▋   | 249967/371472 [8:50:41<9:27:23,  3.57it/s]
 67%|██████▋   | 249968/371472 [8:50:41<9:50:41,  3.43it/s]
 67%|██████▋   | 249969/371472 [8:50:41<9:59:29,  3.38it/s]
 67%|██████▋   | 249970/371472 [8:50:42<9:36:33,  3.51it/s]
 67%|██████▋   | 249971/371472 [8:50:42<10:07:29,  3.33it/s]
 67%|██████▋   | 249972/371472 [8:50:42<10:03:26,  3.36it/s]
 67%|██████▋   | 249973/371472 [8:50:42<9:40:38,  3.49it/s] 
 67%|██████▋   | 249974/371472 [8:50:43<10:04:14,  3.35it/s]
 67%|██████▋   | 249975/371472 [8:50:43<10:25:23,  3.24it/s]
 67%|██████▋   | 249976/371472 [8:50:43<10:16:28,  3.28it/s]
 67%|██████▋   | 249977/371472 [8:50:44<9:49:20,  3.44it/s] 
 67%|██████▋   | 249978/371472 [8:50:44<9:52:14,  3.42it/s]
 67%|██████▋   | 249979/371472 [8:50:44<9:36:37,  3.51it/s]
 67%|██████▋   | 249980/371472 [8:50:44<9:21:53,  3.60it/s]
                                                           
{'loss': 2.8425, 'learning_rate': 3.945086082440906e-07, 'epoch': 10.77}
+
 67%|██████▋   | 249980/371472 [8:50:44<9:21:53,  3.60it/s]
 67%|██████▋   | 249981/371472 [8:50:45<9:18:20,  3.63it/s]
 67%|██████▋   | 249982/371472 [8:50:45<9:03:56,  3.72it/s]
 67%|██████▋   | 249983/371472 [8:50:45<9:29:30,  3.56it/s]
 67%|██████▋   | 249984/371472 [8:50:46<9:15:05,  3.65it/s]
 67%|██████▋   | 249985/371472 [8:50:46<9:04:39,  3.72it/s]
 67%|██████▋   | 249986/371472 [8:50:46<9:19:15,  3.62it/s]
 67%|██████▋   | 249987/371472 [8:50:46<9:24:15,  3.59it/s]
 67%|██████▋   | 249988/371472 [8:50:47<9:07:12,  3.70it/s]
 67%|██████▋   | 249989/371472 [8:50:47<9:31:33,  3.54it/s]
 67%|██████▋   | 249990/371472 [8:50:47<9:22:30,  3.60it/s]
 67%|██████▋   | 249991/371472 [8:50:47<8:58:16,  3.76it/s]
 67%|██████▋   | 249992/371472 [8:50:48<9:04:29,  3.72it/s]
 67%|██████▋   | 249993/371472 [8:50:48<8:52:31,  3.80it/s]
 67%|██████▋   | 249994/371472 [8:50:48<8:40:38,  3.89it/s]
 67%|██████▋   | 249995/371472 [8:50:48<8:33:58,  3.94it/s]
 67%|██████▋   | 249996/371472 [8:50:49<8:44:05,  3.86it/s]
 67%|██████▋   | 249997/371472 [8:50:49<8:33:41,  3.94it/s]
 67%|██████▋   | 249998/371472 [8:50:49<9:18:51,  3.62it/s]
 67%|██████▋   | 249999/371472 [8:50:50<9:23:53,  3.59it/s]
 67%|██████▋   | 250000/371472 [8:50:50<9:18:45,  3.62it/s]
                                                           
{'loss': 2.7479, 'learning_rate': 3.9446012626861165e-07, 'epoch': 10.77}
+
 67%|██████▋   | 250000/371472 [8:50:50<9:18:45,  3.62it/s]
 67%|██████▋   | 250001/371472 [8:50:50<9:04:56,  3.72it/s]
 67%|██████▋   | 250002/371472 [8:50:50<9:50:23,  3.43it/s]
 67%|██████▋   | 250003/371472 [8:50:51<9:21:17,  3.61it/s]
 67%|██████▋   | 250004/371472 [8:50:51<9:23:57,  3.59it/s]
 67%|██████▋   | 250005/371472 [8:50:51<10:37:41,  3.17it/s]
 67%|██████▋   | 250006/371472 [8:50:52<10:19:32,  3.27it/s]
 67%|██████▋   | 250007/371472 [8:50:52<10:13:36,  3.30it/s]
 67%|██████▋   | 250008/371472 [8:50:52<9:44:40,  3.46it/s] 
 67%|██████▋   | 250009/371472 [8:50:52<9:46:00,  3.45it/s]
 67%|██████▋   | 250010/371472 [8:50:53<9:34:12,  3.53it/s]
 67%|██████▋   | 250011/371472 [8:50:53<9:08:31,  3.69it/s]
 67%|██████▋   | 250012/371472 [8:50:53<9:02:59,  3.73it/s]
 67%|██████▋   | 250013/371472 [8:50:54<8:55:36,  3.78it/s]
 67%|██████▋   | 250014/371472 [8:50:54<9:04:47,  3.72it/s]
 67%|██████▋   | 250015/371472 [8:50:54<8:56:23,  3.77it/s]
 67%|██████▋   | 250016/371472 [8:50:54<9:12:57,  3.66it/s]
 67%|██████▋   | 250017/371472 [8:50:55<9:16:02,  3.64it/s]
 67%|██████▋   | 250018/371472 [8:50:55<9:04:54,  3.71it/s]
 67%|██████▋   | 250019/371472 [8:50:55<9:27:08,  3.57it/s]
 67%|██████▋   | 250020/371472 [8:50:56<10:02:34,  3.36it/s]
                                                            
{'loss': 2.9058, 'learning_rate': 3.9441164429313283e-07, 'epoch': 10.77}
+
 67%|██████▋   | 250020/371472 [8:50:56<10:02:34,  3.36it/s]
 67%|██████▋   | 250021/371472 [8:50:56<9:25:13,  3.58it/s] 
 67%|██████▋   | 250022/371472 [8:50:56<9:13:09,  3.66it/s]
 67%|██████▋   | 250023/371472 [8:50:56<9:00:08,  3.75it/s]
 67%|██████▋   | 250024/371472 [8:50:57<9:29:31,  3.55it/s]
 67%|██████▋   | 250025/371472 [8:50:57<9:30:01,  3.55it/s]
 67%|██████▋   | 250026/371472 [8:50:57<10:41:05,  3.16it/s]
 67%|██████▋   | 250027/371472 [8:50:58<10:03:52,  3.35it/s]
 67%|██████▋   | 250028/371472 [8:50:58<9:28:28,  3.56it/s] 
 67%|██████▋   | 250029/371472 [8:50:58<9:10:13,  3.68it/s]
 67%|██████▋   | 250030/371472 [8:50:58<9:07:47,  3.69it/s]
 67%|██████▋   | 250031/371472 [8:50:59<8:51:52,  3.81it/s]
 67%|██████▋   | 250032/371472 [8:50:59<8:58:35,  3.76it/s]
 67%|██████▋   | 250033/371472 [8:50:59<9:23:56,  3.59it/s]
 67%|██████▋   | 250034/371472 [8:50:59<9:36:56,  3.51it/s]
 67%|██████▋   | 250035/371472 [8:51:00<9:50:33,  3.43it/s]
 67%|██████▋   | 250036/371472 [8:51:00<9:47:52,  3.44it/s]
 67%|██████▋   | 250037/371472 [8:51:00<9:22:12,  3.60it/s]
 67%|██████▋   | 250038/371472 [8:51:01<9:31:11,  3.54it/s]
 67%|██████▋   | 250039/371472 [8:51:01<9:39:37,  3.49it/s]
 67%|██████▋   | 250040/371472 [8:51:01<9:30:40,  3.55it/s]
                                                           
{'loss': 3.0081, 'learning_rate': 3.943631623176539e-07, 'epoch': 10.77}
+
 67%|██████▋   | 250040/371472 [8:51:01<9:30:40,  3.55it/s]
 67%|██████▋   | 250041/371472 [8:51:01<9:12:30,  3.66it/s]
 67%|██████▋   | 250042/371472 [8:51:02<8:55:17,  3.78it/s]
 67%|██████▋   | 250043/371472 [8:51:02<9:28:09,  3.56it/s]
 67%|██████▋   | 250044/371472 [8:51:02<9:39:51,  3.49it/s]
 67%|██████▋   | 250045/371472 [8:51:03<9:51:11,  3.42it/s]
 67%|██████▋   | 250046/371472 [8:51:03<9:33:39,  3.53it/s]
 67%|██████▋   | 250047/371472 [8:51:03<9:19:51,  3.61it/s]
 67%|██████▋   | 250048/371472 [8:51:03<9:37:11,  3.51it/s]
 67%|██████▋   | 250049/371472 [8:51:04<9:19:59,  3.61it/s]
 67%|██████▋   | 250050/371472 [8:51:04<9:32:05,  3.54it/s]
 67%|██████▋   | 250051/371472 [8:51:04<10:13:40,  3.30it/s]
 67%|██████▋   | 250052/371472 [8:51:05<10:03:29,  3.35it/s]
 67%|██████▋   | 250053/371472 [8:51:05<9:35:36,  3.52it/s] 
 67%|██████▋   | 250054/371472 [8:51:05<9:24:29,  3.58it/s]
 67%|██████▋   | 250055/371472 [8:51:05<9:05:01,  3.71it/s]
 67%|██████▋   | 250056/371472 [8:51:06<9:25:47,  3.58it/s]
 67%|██████▋   | 250057/371472 [8:51:06<9:03:19,  3.72it/s]
 67%|██████▋   | 250058/371472 [8:51:06<9:00:03,  3.75it/s]
 67%|██████▋   | 250059/371472 [8:51:06<8:59:45,  3.75it/s]
 67%|██████▋   | 250060/371472 [8:51:07<8:54:06,  3.79it/s]
                                                           
{'loss': 2.7854, 'learning_rate': 3.94314680342175e-07, 'epoch': 10.77}
+
 67%|██████▋   | 250060/371472 [8:51:07<8:54:06,  3.79it/s]
 67%|██████▋   | 250061/371472 [8:51:07<8:45:02,  3.85it/s]
 67%|██████▋   | 250062/371472 [8:51:07<8:40:55,  3.88it/s]
 67%|██████▋   | 250063/371472 [8:51:07<8:44:15,  3.86it/s]
 67%|██████▋   | 250064/371472 [8:51:08<8:28:53,  3.98it/s]
 67%|██████▋   | 250065/371472 [8:51:08<9:07:02,  3.70it/s]
 67%|██████▋   | 250066/371472 [8:51:08<8:59:29,  3.75it/s]
 67%|██████▋   | 250067/371472 [8:51:08<8:57:07,  3.77it/s]
 67%|██████▋   | 250068/371472 [8:51:09<9:15:27,  3.64it/s]
 67%|██████▋   | 250069/371472 [8:51:09<9:02:54,  3.73it/s]
 67%|██████▋   | 250070/371472 [8:51:09<8:47:03,  3.84it/s]
 67%|██████▋   | 250071/371472 [8:51:10<9:15:34,  3.64it/s]
 67%|██████▋   | 250072/371472 [8:51:10<10:27:36,  3.22it/s]
 67%|██████▋   | 250073/371472 [8:51:10<10:13:49,  3.30it/s]
 67%|██████▋   | 250074/371472 [8:51:11<9:51:00,  3.42it/s] 
 67%|██████▋   | 250075/371472 [8:51:11<9:30:24,  3.55it/s]
 67%|██████▋   | 250076/371472 [8:51:11<9:38:53,  3.50it/s]
 67%|██████▋   | 250077/371472 [8:51:11<10:37:35,  3.17it/s]
 67%|██████▋   | 250078/371472 [8:51:12<9:57:03,  3.39it/s] 
 67%|██████▋   | 250079/371472 [8:51:12<10:02:45,  3.36it/s]
 67%|██████▋   | 250080/371472 [8:51:12<9:47:23,  3.44it/s] 
                                                           
{'loss': 2.8686, 'learning_rate': 3.942661983666961e-07, 'epoch': 10.77}
+
 67%|██████▋   | 250080/371472 [8:51:12<9:47:23,  3.44it/s]
 67%|██████▋   | 250081/371472 [8:51:13<10:00:52,  3.37it/s]
 67%|██████▋   | 250082/371472 [8:51:13<10:21:14,  3.26it/s]
 67%|██████▋   | 250083/371472 [8:51:13<9:51:24,  3.42it/s] 
 67%|██████▋   | 250084/371472 [8:51:14<10:02:18,  3.36it/s]
 67%|██████▋   | 250085/371472 [8:51:14<10:08:45,  3.32it/s]
 67%|██████▋   | 250086/371472 [8:51:14<9:49:12,  3.43it/s] 
 67%|██████▋   | 250087/371472 [8:51:14<9:43:01,  3.47it/s]
 67%|██████▋   | 250088/371472 [8:51:15<9:48:00,  3.44it/s]
 67%|██████▋   | 250089/371472 [8:51:15<9:44:02,  3.46it/s]
 67%|██████▋   | 250090/371472 [8:51:15<10:08:46,  3.32it/s]
 67%|██████▋   | 250091/371472 [8:51:16<9:36:33,  3.51it/s] 
 67%|██████▋   | 250092/371472 [8:51:16<9:10:21,  3.68it/s]
 67%|██████▋   | 250093/371472 [8:51:16<9:37:08,  3.51it/s]
 67%|██████▋   | 250094/371472 [8:51:16<9:18:33,  3.62it/s]
 67%|██████▋   | 250095/371472 [8:51:17<9:11:49,  3.67it/s]
 67%|██████▋   | 250096/371472 [8:51:17<9:24:51,  3.58it/s]
 67%|██████▋   | 250097/371472 [8:51:17<9:29:25,  3.55it/s]
 67%|██████▋   | 250098/371472 [8:51:17<9:25:19,  3.58it/s]
 67%|██████▋   | 250099/371472 [8:51:18<9:15:19,  3.64it/s]
 67%|██████▋   | 250100/371472 [8:51:18<8:55:18,  3.78it/s]
                                                           
{'loss': 2.7338, 'learning_rate': 3.9421771639121727e-07, 'epoch': 10.77}
+
 67%|██████▋   | 250100/371472 [8:51:18<8:55:18,  3.78it/s]
 67%|██████▋   | 250101/371472 [8:51:18<8:47:55,  3.83it/s]
 67%|██████▋   | 250102/371472 [8:51:18<8:51:09,  3.81it/s]
 67%|██████▋   | 250103/371472 [8:51:19<8:50:21,  3.81it/s]
 67%|██████▋   | 250104/371472 [8:51:19<8:52:01,  3.80it/s]
 67%|██████▋   | 250105/371472 [8:51:19<9:20:00,  3.61it/s]
 67%|██████▋   | 250106/371472 [8:51:20<10:06:24,  3.34it/s]
 67%|██████▋   | 250107/371472 [8:51:20<9:54:49,  3.40it/s] 
 67%|██████▋   | 250108/371472 [8:51:20<9:42:04,  3.48it/s]
 67%|██████▋   | 250109/371472 [8:51:21<9:57:33,  3.38it/s]
 67%|██████▋   | 250110/371472 [8:51:21<9:25:01,  3.58it/s]
 67%|██████▋   | 250111/371472 [8:51:21<9:51:46,  3.42it/s]
 67%|██████▋   | 250112/371472 [8:51:21<10:47:41,  3.12it/s]
 67%|██████▋   | 250113/371472 [8:51:22<10:18:02,  3.27it/s]
 67%|██████▋   | 250114/371472 [8:51:22<9:55:28,  3.40it/s] 
 67%|██████▋   | 250115/371472 [8:51:22<9:28:53,  3.56it/s]
 67%|██████▋   | 250116/371472 [8:51:23<9:23:52,  3.59it/s]
 67%|██████▋   | 250117/371472 [8:51:23<9:01:53,  3.73it/s]
 67%|██████▋   | 250118/371472 [8:51:23<9:07:58,  3.69it/s]
 67%|██████▋   | 250119/371472 [8:51:23<9:47:21,  3.44it/s]
 67%|██████▋   | 250120/371472 [8:51:24<9:16:02,  3.64it/s]
                                                           
{'loss': 2.754, 'learning_rate': 3.941692344157383e-07, 'epoch': 10.77}
+
 67%|██████▋   | 250120/371472 [8:51:24<9:16:02,  3.64it/s]
 67%|██████▋   | 250121/371472 [8:51:24<9:01:23,  3.74it/s]
 67%|██████▋   | 250122/371472 [8:51:24<8:47:14,  3.84it/s]
 67%|██████▋   | 250123/371472 [8:51:24<8:43:35,  3.86it/s]
 67%|██████▋   | 250124/371472 [8:51:25<8:49:20,  3.82it/s]
 67%|██████▋   | 250125/371472 [8:51:25<9:28:33,  3.56it/s]
 67%|██████▋   | 250126/371472 [8:51:25<9:27:47,  3.56it/s]
 67%|██████▋   | 250127/371472 [8:51:26<9:27:49,  3.56it/s]
 67%|██████▋   | 250128/371472 [8:51:26<9:23:04,  3.59it/s]
 67%|██████▋   | 250129/371472 [8:51:26<9:20:38,  3.61it/s]
 67%|██████▋   | 250130/371472 [8:51:26<9:09:14,  3.68it/s]
 67%|██████▋   | 250131/371472 [8:51:27<9:09:00,  3.68it/s]
 67%|██████▋   | 250132/371472 [8:51:27<9:23:14,  3.59it/s]
 67%|██████▋   | 250133/371472 [8:51:27<9:02:16,  3.73it/s]
 67%|██████▋   | 250134/371472 [8:51:27<9:28:51,  3.56it/s]
 67%|██████▋   | 250135/371472 [8:51:28<9:39:17,  3.49it/s]
 67%|██████▋   | 250136/371472 [8:51:28<9:17:34,  3.63it/s]
 67%|██████▋   | 250137/371472 [8:51:28<8:49:58,  3.82it/s]
 67%|██████▋   | 250138/371472 [8:51:29<9:26:21,  3.57it/s]
 67%|██████▋   | 250139/371472 [8:51:29<9:01:06,  3.74it/s]
 67%|████��█▋   | 250140/371472 [8:51:29<9:08:32,  3.69it/s]
                                                           
{'loss': 2.8295, 'learning_rate': 3.941207524402595e-07, 'epoch': 10.77}
+
 67%|██████▋   | 250140/371472 [8:51:29<9:08:32,  3.69it/s]
 67%|██████▋   | 250141/371472 [8:51:29<9:16:41,  3.63it/s]
 67%|██████▋   | 250142/371472 [8:51:30<9:15:44,  3.64it/s]
 67%|██████▋   | 250143/371472 [8:51:30<9:00:44,  3.74it/s]
 67%|██████▋   | 250144/371472 [8:51:30<8:54:55,  3.78it/s]
 67%|██████▋   | 250145/371472 [8:51:30<9:32:24,  3.53it/s]
 67%|██████▋   | 250146/371472 [8:51:31<9:38:00,  3.50it/s]
 67%|██████▋   | 250147/371472 [8:51:31<9:23:08,  3.59it/s]
 67%|██████▋   | 250148/371472 [8:51:31<9:31:32,  3.54it/s]
 67%|██████▋   | 250149/371472 [8:51:32<9:12:54,  3.66it/s]
 67%|██████▋   | 250150/371472 [8:51:32<9:33:14,  3.53it/s]
 67%|██████▋   | 250151/371472 [8:51:32<9:33:59,  3.52it/s]
 67%|██████▋   | 250152/371472 [8:51:32<9:02:01,  3.73it/s]
 67%|██████▋   | 250153/371472 [8:51:33<8:55:30,  3.78it/s]
 67%|██████▋   | 250154/371472 [8:51:33<8:48:30,  3.83it/s]
 67%|██████▋   | 250155/371472 [8:51:33<8:45:54,  3.84it/s]
 67%|██████▋   | 250156/371472 [8:51:33<8:52:01,  3.80it/s]
 67%|██████▋   | 250157/371472 [8:51:34<9:12:19,  3.66it/s]
 67%|██████▋   | 250158/371472 [8:51:34<9:45:31,  3.45it/s]
 67%|██████▋   | 250159/371472 [8:51:34<9:40:38,  3.48it/s]
 67%|██████▋   | 250160/371472 [8:51:35<9:10:51,  3.67it/s]
                                                           
{'loss': 2.835, 'learning_rate': 3.9407227046478054e-07, 'epoch': 10.77}
+
 67%|██████▋   | 250160/371472 [8:51:35<9:10:51,  3.67it/s]
 67%|██████▋   | 250161/371472 [8:51:35<8:58:50,  3.75it/s]
 67%|██████▋   | 250162/371472 [8:51:35<8:47:43,  3.83it/s]
 67%|██████▋   | 250163/371472 [8:51:35<10:01:04,  3.36it/s]
 67%|██████▋   | 250164/371472 [8:51:36<10:12:46,  3.30it/s]
 67%|██████▋   | 250165/371472 [8:51:36<9:28:57,  3.55it/s] 
 67%|██████▋   | 250166/371472 [8:51:36<9:45:19,  3.45it/s]
 67%|██████▋   | 250167/371472 [8:51:37<9:43:25,  3.47it/s]
 67%|██████▋   | 250168/371472 [8:51:37<9:43:53,  3.46it/s]
 67%|██████▋   | 250169/371472 [8:51:37<9:24:54,  3.58it/s]
 67%|██████▋   | 250170/371472 [8:51:37<9:53:51,  3.40it/s]
 67%|██████▋   | 250171/371472 [8:51:38<9:32:50,  3.53it/s]
 67%|██████▋   | 250172/371472 [8:51:38<10:31:08,  3.20it/s]
 67%|██████▋   | 250173/371472 [8:51:38<10:12:46,  3.30it/s]
 67%|██████▋   | 250174/371472 [8:51:39<9:44:43,  3.46it/s] 
 67%|██████▋   | 250175/371472 [8:51:39<9:27:08,  3.56it/s]
 67%|██████▋   | 250176/371472 [8:51:39<10:32:44,  3.20it/s]
 67%|██████▋   | 250177/371472 [8:51:40<10:31:32,  3.20it/s]
 67%|██████▋   | 250178/371472 [8:51:40<9:54:52,  3.40it/s] 
 67%|██████▋   | 250179/371472 [8:51:40<9:37:51,  3.50it/s]
 67%|██████▋   | 250180/371472 [8:51:40<9:52:50,  3.41it/s]
                                                           
{'loss': 2.6723, 'learning_rate': 3.9402378848930156e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250180/371472 [8:51:40<9:52:50,  3.41it/s]
 67%|██████▋   | 250181/371472 [8:51:41<9:23:53,  3.58it/s]
 67%|██████▋   | 250182/371472 [8:51:41<9:00:35,  3.74it/s]
 67%|██████▋   | 250183/371472 [8:51:41<9:34:51,  3.52it/s]
 67%|██████▋   | 250184/371472 [8:51:42<9:10:23,  3.67it/s]
 67%|██████▋   | 250185/371472 [8:51:42<9:17:22,  3.63it/s]
 67%|██████▋   | 250186/371472 [8:51:42<9:19:27,  3.61it/s]
 67%|██████▋   | 250187/371472 [8:51:42<9:13:13,  3.65it/s]
 67%|██████▋   | 250188/371472 [8:51:43<9:28:06,  3.56it/s]
 67%|██████▋   | 250189/371472 [8:51:43<9:21:51,  3.60it/s]
 67%|██████▋   | 250190/371472 [8:51:43<9:41:43,  3.47it/s]
 67%|██████▋   | 250191/371472 [8:51:43<9:20:57,  3.60it/s]
 67%|██████▋   | 250192/371472 [8:51:44<9:41:54,  3.47it/s]
 67%|██████▋   | 250193/371472 [8:51:44<10:37:07,  3.17it/s]
 67%|██████▋   | 250194/371472 [8:51:44<9:57:52,  3.38it/s] 
 67%|██████▋   | 250195/371472 [8:51:45<10:02:59,  3.35it/s]
 67%|██████▋   | 250196/371472 [8:51:45<9:56:39,  3.39it/s] 
 67%|██████▋   | 250197/371472 [8:51:45<9:40:31,  3.48it/s]
 67%|██████▋   | 250198/371472 [8:51:46<9:36:41,  3.50it/s]
 67%|██████▋   | 250199/371472 [8:51:46<9:43:19,  3.46it/s]
 67%|██████▋   | 250200/371472 [8:51:46<10:04:07,  3.35it/s]
                                                            
{'loss': 2.6764, 'learning_rate': 3.9397530651382274e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250200/371472 [8:51:46<10:04:07,  3.35it/s]
 67%|██████▋   | 250201/371472 [8:51:46<9:47:26,  3.44it/s] 
 67%|██████▋   | 250202/371472 [8:51:47<9:53:25,  3.41it/s]
 67%|██████▋   | 250203/371472 [8:51:47<10:09:36,  3.32it/s]
 67%|██████▋   | 250204/371472 [8:51:47<9:53:20,  3.41it/s] 
 67%|██████▋   | 250205/371472 [8:51:48<9:38:00,  3.50it/s]
 67%|██████▋   | 250206/371472 [8:51:48<9:12:44,  3.66it/s]
 67%|██████▋   | 250207/371472 [8:51:48<9:12:16,  3.66it/s]
 67%|██████▋   | 250208/371472 [8:51:48<9:01:54,  3.73it/s]
 67%|██████▋   | 250209/371472 [8:51:49<9:04:04,  3.71it/s]
 67%|██████▋   | 250210/371472 [8:51:49<9:45:07,  3.45it/s]
 67%|██████▋   | 250211/371472 [8:51:49<10:31:42,  3.20it/s]
 67%|██████▋   | 250212/371472 [8:51:50<10:14:45,  3.29it/s]
 67%|██████▋   | 250213/371472 [8:51:50<11:05:24,  3.04it/s]
 67%|██████▋   | 250214/371472 [8:51:50<10:42:20,  3.15it/s]
 67%|██████▋   | 250215/371472 [8:51:51<9:57:31,  3.38it/s] 
 67%|██████▋   | 250216/371472 [8:51:51<9:21:53,  3.60it/s]
 67%|██████▋   | 250217/371472 [8:51:51<8:56:22,  3.77it/s]
 67%|██████▋   | 250218/371472 [8:51:51<8:59:20,  3.75it/s]
 67%|██████▋   | 250219/371472 [8:51:52<9:33:41,  3.52it/s]
 67%|██████▋   | 250220/371472 [8:51:52<10:19:07,  3.26it/s]
                                                            
{'loss': 2.7453, 'learning_rate': 3.939268245383438e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250220/371472 [8:51:52<10:19:07,  3.26it/s]
 67%|██████▋   | 250221/371472 [8:51:52<9:56:33,  3.39it/s] 
 67%|██████▋   | 250222/371472 [8:51:53<10:06:21,  3.33it/s]
 67%|██████▋   | 250223/371472 [8:51:53<9:28:54,  3.55it/s] 
 67%|██████▋   | 250224/371472 [8:51:53<9:18:42,  3.62it/s]
 67%|██████▋   | 250225/371472 [8:51:53<8:47:02,  3.83it/s]
 67%|██████▋   | 250226/371472 [8:51:54<9:10:17,  3.67it/s]
 67%|██████▋   | 250227/371472 [8:51:54<10:20:02,  3.26it/s]
 67%|██████▋   | 250228/371472 [8:51:54<9:43:40,  3.46it/s] 
 67%|██████▋   | 250229/371472 [8:51:55<9:33:23,  3.52it/s]
 67%|██████▋   | 250230/371472 [8:51:55<9:13:37,  3.65it/s]
 67%|██████▋   | 250231/371472 [8:51:55<9:09:18,  3.68it/s]
 67%|██████▋   | 250232/371472 [8:51:55<10:06:59,  3.33it/s]
 67%|██████▋   | 250233/371472 [8:51:56<9:21:44,  3.60it/s] 
 67%|██████▋   | 250234/371472 [8:51:56<9:06:41,  3.70it/s]
 67%|██████▋   | 250235/371472 [8:51:56<10:26:07,  3.23it/s]
 67%|██████▋   | 250236/371472 [8:51:57<9:54:13,  3.40it/s] 
 67%|██████▋   | 250237/371472 [8:51:57<10:07:52,  3.32it/s]
 67%|██████▋   | 250238/371472 [8:51:57<9:56:57,  3.38it/s] 
 67%|██████▋   | 250239/371472 [8:51:57<9:56:20,  3.39it/s]
 67%|██████▋   | 250240/371472 [8:51:58<9:35:23,  3.51it/s]
                                                           
{'loss': 2.9196, 'learning_rate': 3.9387834256286493e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250240/371472 [8:51:58<9:35:23,  3.51it/s]
 67%|██████▋   | 250241/371472 [8:51:58<9:12:36,  3.66it/s]
 67%|██████▋   | 250242/371472 [8:51:58<9:45:07,  3.45it/s]
 67%|██████▋   | 250243/371472 [8:51:59<9:15:03,  3.64it/s]
 67%|██████▋   | 250244/371472 [8:51:59<8:55:02,  3.78it/s]
 67%|██████▋   | 250245/371472 [8:51:59<8:40:52,  3.88it/s]
 67%|██████▋   | 250246/371472 [8:51:59<9:03:34,  3.72it/s]
 67%|██████▋   | 250247/371472 [8:52:00<9:07:29,  3.69it/s]
 67%|██████▋   | 250248/371472 [8:52:00<10:37:19,  3.17it/s]
 67%|██████▋   | 250249/371472 [8:52:00<10:06:07,  3.33it/s]
 67%|██████▋   | 250250/371472 [8:52:00<9:36:05,  3.51it/s] 
 67%|██████▋   | 250251/371472 [8:52:01<9:57:24,  3.38it/s]
 67%|██████▋   | 250252/371472 [8:52:01<9:55:51,  3.39it/s]
 67%|██████▋   | 250253/371472 [8:52:01<9:39:19,  3.49it/s]
 67%|██████▋   | 250254/371472 [8:52:02<10:04:08,  3.34it/s]
 67%|██████▋   | 250255/371472 [8:52:02<9:44:26,  3.46it/s] 
 67%|██████▋   | 250256/371472 [8:52:02<9:53:00,  3.41it/s]
 67%|██████▋   | 250257/371472 [8:52:03<10:10:17,  3.31it/s]
 67%|██████▋   | 250258/371472 [8:52:03<10:13:19,  3.29it/s]
 67%|██████▋   | 250259/371472 [8:52:03<10:53:05,  3.09it/s]
 67%|██████▋   | 250260/371472 [8:52:04<10:17:50,  3.27it/s]
                                                            
{'loss': 2.8888, 'learning_rate': 3.93829860587386e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250260/371472 [8:52:04<10:17:50,  3.27it/s]
 67%|██████▋   | 250261/371472 [8:52:04<10:21:24,  3.25it/s]
 67%|██████▋   | 250262/371472 [8:52:04<10:01:32,  3.36it/s]
 67%|██████▋   | 250263/371472 [8:52:04<9:56:14,  3.39it/s] 
 67%|██████▋   | 250264/371472 [8:52:05<10:20:06,  3.26it/s]
 67%|██████▋   | 250265/371472 [8:52:05<10:04:02,  3.34it/s]
 67%|██████▋   | 250266/371472 [8:52:05<9:25:49,  3.57it/s] 
 67%|██████▋   | 250267/371472 [8:52:06<9:06:27,  3.70it/s]
 67%|██████▋   | 250268/371472 [8:52:06<9:23:59,  3.58it/s]
 67%|██████▋   | 250269/371472 [8:52:06<9:01:10,  3.73it/s]
 67%|██████▋   | 250270/371472 [8:52:06<9:33:51,  3.52it/s]
 67%|██████▋   | 250271/371472 [8:52:07<9:30:18,  3.54it/s]
 67%|██████▋   | 250272/371472 [8:52:07<10:02:33,  3.35it/s]
 67%|██████▋   | 250273/371472 [8:52:07<9:36:08,  3.51it/s] 
 67%|██████▋   | 250274/371472 [8:52:08<9:25:41,  3.57it/s]
 67%|██████▋   | 250275/371472 [8:52:08<9:11:23,  3.66it/s]
 67%|██████▋   | 250276/371472 [8:52:08<9:28:49,  3.55it/s]
 67%|██████▋   | 250277/371472 [8:52:08<8:56:59,  3.76it/s]
 67%|██████▋   | 250278/371472 [8:52:09<8:57:23,  3.76it/s]
 67%|██████▋   | 250279/371472 [8:52:09<9:11:13,  3.66it/s]
 67%|██████▋   | 250280/371472 [8:52:09<10:11:30,  3.30it/s]
                                                            
{'loss': 2.8977, 'learning_rate': 3.937813786119072e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250280/371472 [8:52:09<10:11:30,  3.30it/s]
 67%|██████▋   | 250281/371472 [8:52:10<10:09:22,  3.31it/s]
 67%|██████▋   | 250282/371472 [8:52:10<10:08:02,  3.32it/s]
 67%|██████▋   | 250283/371472 [8:52:10<9:30:39,  3.54it/s] 
 67%|██████▋   | 250284/371472 [8:52:10<9:52:42,  3.41it/s]
 67%|██████▋   | 250285/371472 [8:52:11<9:27:11,  3.56it/s]
 67%|██████▋   | 250286/371472 [8:52:11<9:41:52,  3.47it/s]
 67%|██████▋   | 250287/371472 [8:52:11<9:20:15,  3.61it/s]
 67%|██████▋   | 250288/371472 [8:52:11<8:56:58,  3.76it/s]
 67%|██████▋   | 250289/371472 [8:52:12<8:41:25,  3.87it/s]
 67%|██████▋   | 250290/371472 [8:52:12<8:23:26,  4.01it/s]
 67%|██████▋   | 250291/371472 [8:52:12<9:11:08,  3.66it/s]
 67%|██████▋   | 250292/371472 [8:52:12<8:58:38,  3.75it/s]
 67%|██████▋   | 250293/371472 [8:52:13<8:37:34,  3.90it/s]
 67%|██████▋   | 250294/371472 [8:52:13<8:28:48,  3.97it/s]
 67%|██████▋   | 250295/371472 [8:52:13<9:04:53,  3.71it/s]
 67%|██████▋   | 250296/371472 [8:52:14<8:48:37,  3.82it/s]
 67%|██████▋   | 250297/371472 [8:52:14<8:44:16,  3.85it/s]
 67%|██████▋   | 250298/371472 [8:52:14<8:50:14,  3.81it/s]
 67%|██████▋   | 250299/371472 [8:52:14<9:02:33,  3.72it/s]
 67%|██████▋   | 250300/371472 [8:52:15<9:26:27,  3.57it/s]
                                                           
{'loss': 2.93, 'learning_rate': 3.937328966364282e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250300/371472 [8:52:15<9:26:27,  3.57it/s]
 67%|██████▋   | 250301/371472 [8:52:15<9:27:49,  3.56it/s]
 67%|██████▋   | 250302/371472 [8:52:15<9:14:31,  3.64it/s]
 67%|██████▋   | 250303/371472 [8:52:15<8:52:23,  3.79it/s]
 67%|██████▋   | 250304/371472 [8:52:16<9:15:26,  3.64it/s]
 67%|██████▋   | 250305/371472 [8:52:16<9:04:28,  3.71it/s]
 67%|██████▋   | 250306/371472 [8:52:16<9:37:09,  3.50it/s]
 67%|██████▋   | 250307/371472 [8:52:17<9:25:50,  3.57it/s]
 67%|██████▋   | 250308/371472 [8:52:17<9:25:16,  3.57it/s]
 67%|██████▋   | 250309/371472 [8:52:17<9:19:43,  3.61it/s]
 67%|██████▋   | 250310/371472 [8:52:17<9:35:52,  3.51it/s]
 67%|██████▋   | 250311/371472 [8:52:18<9:52:43,  3.41it/s]
 67%|██████▋   | 250312/371472 [8:52:18<9:35:47,  3.51it/s]
 67%|██████▋   | 250313/371472 [8:52:18<9:30:48,  3.54it/s]
 67%|██████▋   | 250314/371472 [8:52:19<9:27:03,  3.56it/s]
 67%|██████▋   | 250315/371472 [8:52:19<9:24:15,  3.58it/s]
 67%|██████▋   | 250316/371472 [8:52:19<9:28:03,  3.55it/s]
 67%|██████▋   | 250317/371472 [8:52:19<9:28:50,  3.55it/s]
 67%|██████▋   | 250318/371472 [8:52:20<9:20:28,  3.60it/s]
 67%|██████▋   | 250319/371472 [8:52:20<9:07:44,  3.69it/s]
 67%|██████▋   | 250320/371472 [8:52:20<9:28:05,  3.55it/s]
                                                           
{'loss': 2.8507, 'learning_rate': 3.936844146609494e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250320/371472 [8:52:20<9:28:05,  3.55it/s]
 67%|██████▋   | 250321/371472 [8:52:21<9:55:21,  3.39it/s]
 67%|██████▋   | 250322/371472 [8:52:21<9:49:11,  3.43it/s]
 67%|██████▋   | 250323/371472 [8:52:21<9:40:49,  3.48it/s]
 67%|██████▋   | 250324/371472 [8:52:21<9:44:43,  3.45it/s]
 67%|██████▋   | 250325/371472 [8:52:22<10:30:24,  3.20it/s]
 67%|██████▋   | 250326/371472 [8:52:22<10:06:01,  3.33it/s]
 67%|██████▋   | 250327/371472 [8:52:22<9:44:45,  3.45it/s] 
 67%|██████▋   | 250328/371472 [8:52:23<9:51:23,  3.41it/s]
 67%|██████▋   | 250329/371472 [8:52:23<9:31:04,  3.54it/s]
 67%|██████▋   | 250330/371472 [8:52:23<9:19:14,  3.61it/s]
 67%|██████▋   | 250331/371472 [8:52:23<9:04:27,  3.71it/s]
 67%|██████▋   | 250332/371472 [8:52:24<9:00:22,  3.74it/s]
 67%|██████▋   | 250333/371472 [8:52:24<8:59:54,  3.74it/s]
 67%|██████▋   | 250334/371472 [8:52:24<8:48:20,  3.82it/s]
 67%|██████▋   | 250335/371472 [8:52:24<8:55:11,  3.77it/s]
 67%|██████▋   | 250336/371472 [8:52:25<9:40:49,  3.48it/s]
 67%|██████▋   | 250337/371472 [8:52:25<9:23:09,  3.58it/s]
 67%|██████▋   | 250338/371472 [8:52:25<8:58:38,  3.75it/s]
 67%|██████▋   | 250339/371472 [8:52:26<8:52:50,  3.79it/s]
 67%|██████▋   | 250340/371472 [8:52:26<9:24:11,  3.58it/s]
                                                           
{'loss': 2.8187, 'learning_rate': 3.9363593268547045e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250340/371472 [8:52:26<9:24:11,  3.58it/s]
 67%|██████▋   | 250341/371472 [8:52:26<9:08:11,  3.68it/s]
 67%|██████▋   | 250342/371472 [8:52:26<8:55:26,  3.77it/s]
 67%|██████▋   | 250343/371472 [8:52:27<9:09:51,  3.67it/s]
 67%|██████▋   | 250344/371472 [8:52:27<9:56:14,  3.39it/s]
 67%|██████▋   | 250345/371472 [8:52:27<9:45:43,  3.45it/s]
 67%|██████▋   | 250346/371472 [8:52:28<9:27:33,  3.56it/s]
 67%|██████▋   | 250347/371472 [8:52:28<9:17:02,  3.62it/s]
 67%|██████▋   | 250348/371472 [8:52:28<9:41:18,  3.47it/s]
 67%|██████▋   | 250349/371472 [8:52:28<9:17:37,  3.62it/s]
 67%|██████▋   | 250350/371472 [8:52:29<9:34:03,  3.52it/s]
 67%|██████▋   | 250351/371472 [8:52:29<9:09:01,  3.68it/s]
 67%|██████▋   | 250352/371472 [8:52:29<8:58:58,  3.75it/s]
 67%|██████▋   | 250353/371472 [8:52:29<8:45:03,  3.84it/s]
 67%|██████▋   | 250354/371472 [8:52:30<8:52:15,  3.79it/s]
 67%|██████▋   | 250355/371472 [8:52:30<8:46:40,  3.83it/s]
 67%|██████▋   | 250356/371472 [8:52:30<8:43:59,  3.85it/s]
 67%|██████▋   | 250357/371472 [8:52:30<8:51:26,  3.80it/s]
 67%|██████▋   | 250358/371472 [8:52:31<8:48:30,  3.82it/s]
 67%|██████▋   | 250359/371472 [8:52:31<8:50:52,  3.80it/s]
 67%|██████▋   | 250360/371472 [8:52:31<8:49:13,  3.81it/s]
                                                           
{'loss': 2.8433, 'learning_rate': 3.9358745070999157e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250360/371472 [8:52:31<8:49:13,  3.81it/s]
 67%|██████▋   | 250361/371472 [8:52:32<9:04:17,  3.71it/s]
 67%|██████▋   | 250362/371472 [8:52:32<9:12:23,  3.65it/s]
 67%|██████▋   | 250363/371472 [8:52:32<9:31:20,  3.53it/s]
 67%|██████▋   | 250364/371472 [8:52:32<9:24:26,  3.58it/s]
 67%|██████▋   | 250365/371472 [8:52:33<9:00:18,  3.74it/s]
 67%|██████▋   | 250366/371472 [8:52:33<8:51:29,  3.80it/s]
 67%|██████▋   | 250367/371472 [8:52:33<8:41:04,  3.87it/s]
 67%|██████▋   | 250368/371472 [8:52:34<10:09:59,  3.31it/s]
 67%|██████▋   | 250369/371472 [8:52:34<9:52:20,  3.41it/s] 
 67%|██████▋   | 250370/371472 [8:52:34<9:47:51,  3.43it/s]
 67%|██████▋   | 250371/371472 [8:52:34<9:33:45,  3.52it/s]
 67%|██████▋   | 250372/371472 [8:52:35<9:38:14,  3.49it/s]
 67%|██████▋   | 250373/371472 [8:52:35<9:26:33,  3.56it/s]
 67%|██████▋   | 250374/371472 [8:52:35<9:19:17,  3.61it/s]
 67%|██████▋   | 250375/371472 [8:52:35<9:13:49,  3.64it/s]
 67%|██████▋   | 250376/371472 [8:52:36<10:29:14,  3.21it/s]
 67%|██████▋   | 250377/371472 [8:52:36<10:03:48,  3.34it/s]
 67%|██████▋   | 250378/371472 [8:52:36<10:09:07,  3.31it/s]
 67%|██████▋   | 250379/371472 [8:52:37<9:49:48,  3.42it/s] 
 67%|██████▋   | 250380/371472 [8:52:37<9:26:31,  3.56it/s]
                                                           
{'loss': 2.9556, 'learning_rate': 3.9353896873451264e-07, 'epoch': 10.78}
+
 67%|██████▋   | 250380/371472 [8:52:37<9:26:31,  3.56it/s]
 67%|██████▋   | 250381/371472 [8:52:37<9:18:37,  3.61it/s]
 67%|██████▋   | 250382/371472 [8:52:37<9:17:51,  3.62it/s]
 67%|██████▋   | 250383/371472 [8:52:38<9:32:33,  3.52it/s]
 67%|██████▋   | 250384/371472 [8:52:38<9:14:50,  3.64it/s]
 67%|██████▋   | 250385/371472 [8:52:38<9:10:30,  3.67it/s]
 67%|██████▋   | 250386/371472 [8:52:39<9:18:13,  3.62it/s]
 67%|██████▋   | 250387/371472 [8:52:39<9:03:25,  3.71it/s]
 67%|██████▋   | 250388/371472 [8:52:39<8:50:46,  3.80it/s]
 67%|██████▋   | 250389/371472 [8:52:39<9:23:53,  3.58it/s]
 67%|██████▋   | 250390/371472 [8:52:40<9:36:04,  3.50it/s]
 67%|██████▋   | 250391/371472 [8:52:40<9:12:53,  3.65it/s]
 67%|██████▋   | 250392/371472 [8:52:40<9:57:59,  3.37it/s]
 67%|██████▋   | 250393/371472 [8:52:41<10:17:44,  3.27it/s]
 67%|██████▋   | 250394/371472 [8:52:41<10:04:04,  3.34it/s]
 67%|██████▋   | 250395/371472 [8:52:41<9:50:29,  3.42it/s] 
 67%|██████▋   | 250396/371472 [8:52:41<9:53:54,  3.40it/s]
 67%|██████▋   | 250397/371472 [8:52:42<10:03:49,  3.34it/s]
 67%|██████▋   | 250398/371472 [8:52:42<10:06:29,  3.33it/s]
 67%|██████▋   | 250399/371472 [8:52:42<10:21:08,  3.25it/s]
 67%|██████▋   | 250400/371472 [8:52:43<10:01:49,  3.35it/s]
                                                            
{'loss': 2.7986, 'learning_rate': 3.934904867590338e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250400/371472 [8:52:43<10:01:49,  3.35it/s]
 67%|██████▋   | 250401/371472 [8:52:43<10:19:52,  3.26it/s]
 67%|██████▋   | 250402/371472 [8:52:43<9:46:18,  3.44it/s] 
 67%|██████▋   | 250403/371472 [8:52:44<9:40:38,  3.48it/s]
 67%|██████▋   | 250404/371472 [8:52:44<9:42:34,  3.46it/s]
 67%|██████▋   | 250405/371472 [8:52:44<9:25:43,  3.57it/s]
 67%|██████▋   | 250406/371472 [8:52:44<9:22:32,  3.59it/s]
 67%|██████▋   | 250407/371472 [8:52:45<9:09:29,  3.67it/s]
 67%|██████▋   | 250408/371472 [8:52:45<9:32:31,  3.52it/s]
 67%|██████▋   | 250409/371472 [8:52:45<9:24:58,  3.57it/s]
 67%|██████▋   | 250410/371472 [8:52:46<9:56:06,  3.38it/s]
 67%|██████▋   | 250411/371472 [8:52:46<10:03:03,  3.35it/s]
 67%|██████▋   | 250412/371472 [8:52:46<10:29:07,  3.21it/s]
 67%|██████▋   | 250413/371472 [8:52:46<10:12:08,  3.30it/s]
 67%|██████▋   | 250414/371472 [8:52:47<9:56:23,  3.38it/s] 
 67%|██████▋   | 250415/371472 [8:52:47<10:43:32,  3.14it/s]
 67%|██████▋   | 250416/371472 [8:52:47<10:31:41,  3.19it/s]
 67%|██████▋   | 250417/371472 [8:52:48<9:53:01,  3.40it/s] 
 67%|██████▋   | 250418/371472 [8:52:48<9:49:13,  3.42it/s]
 67%|██████▋   | 250419/371472 [8:52:48<10:01:59,  3.35it/s]
 67%|██████▋   | 250420/371472 [8:52:49<9:43:44,  3.46it/s] 
                                                           
{'loss': 2.7877, 'learning_rate': 3.934420047835549e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250420/371472 [8:52:49<9:43:44,  3.46it/s]
 67%|██████▋   | 250421/371472 [8:52:49<10:25:32,  3.23it/s]
 67%|██████▋   | 250422/371472 [8:52:49<10:20:35,  3.25it/s]
 67%|██████▋   | 250423/371472 [8:52:49<9:44:23,  3.45it/s] 
 67%|██████▋   | 250424/371472 [8:52:50<9:34:07,  3.51it/s]
 67%|██████▋   | 250425/371472 [8:52:50<9:44:51,  3.45it/s]
 67%|██████▋   | 250426/371472 [8:52:50<9:37:18,  3.49it/s]
 67%|██████▋   | 250427/371472 [8:52:51<9:17:03,  3.62it/s]
 67%|██████▋   | 250428/371472 [8:52:51<9:43:54,  3.45it/s]
 67%|██████▋   | 250429/371472 [8:52:51<10:20:06,  3.25it/s]
 67%|██████▋   | 250430/371472 [8:52:52<10:07:34,  3.32it/s]
 67%|██████▋   | 250431/371472 [8:52:52<10:29:33,  3.20it/s]
 67%|██████▋   | 250432/371472 [8:52:52<10:09:51,  3.31it/s]
 67%|██████▋   | 250433/371472 [8:52:52<9:42:36,  3.46it/s] 
 67%|██████▋   | 250434/371472 [8:52:53<9:27:28,  3.55it/s]
 67%|██████▋   | 250435/371472 [8:52:53<9:01:31,  3.73it/s]
 67%|██████▋   | 250436/371472 [8:52:53<8:40:45,  3.87it/s]
 67%|██████▋   | 250437/371472 [8:52:53<9:07:16,  3.69it/s]
 67%|██████▋   | 250438/371472 [8:52:54<8:55:29,  3.77it/s]
 67%|██████▋   | 250439/371472 [8:52:54<8:55:58,  3.76it/s]
 67%|██████▋   | 250440/371472 [8:52:54<9:15:51,  3.63it/s]
                                                           
{'loss': 2.7448, 'learning_rate': 3.93393522808076e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250440/371472 [8:52:54<9:15:51,  3.63it/s]
 67%|██████▋   | 250441/371472 [8:52:55<9:33:34,  3.52it/s]
 67%|██████▋   | 250442/371472 [8:52:55<10:14:19,  3.28it/s]
 67%|██████▋   | 250443/371472 [8:52:55<9:36:19,  3.50it/s] 
 67%|██████▋   | 250444/371472 [8:52:55<9:34:35,  3.51it/s]
 67%|██████▋   | 250445/371472 [8:52:56<9:22:27,  3.59it/s]
 67%|██████▋   | 250446/371472 [8:52:56<10:27:53,  3.21it/s]
 67%|██████▋   | 250447/371472 [8:52:56<9:58:43,  3.37it/s] 
 67%|██████▋   | 250448/371472 [8:52:57<9:32:18,  3.52it/s]
 67%|██████▋   | 250449/371472 [8:52:57<10:38:15,  3.16it/s]
 67%|██████▋   | 250450/371472 [8:52:57<9:54:01,  3.40it/s] 
 67%|██████▋   | 250451/371472 [8:52:58<9:28:46,  3.55it/s]
 67%|██████▋   | 250452/371472 [8:52:58<9:41:47,  3.47it/s]
 67%|██████▋   | 250453/371472 [8:52:58<10:02:14,  3.35it/s]
 67%|██████▋   | 250454/371472 [8:52:58<9:27:06,  3.56it/s] 
 67%|██████▋   | 250455/371472 [8:52:59<9:14:01,  3.64it/s]
 67%|██████▋   | 250456/371472 [8:52:59<9:33:48,  3.51it/s]
 67%|██████▋   | 250457/371472 [8:52:59<9:07:03,  3.69it/s]
 67%|██████▋   | 250458/371472 [8:52:59<9:05:17,  3.70it/s]
 67%|██████▋   | 250459/371472 [8:53:00<8:58:41,  3.74it/s]
 67%|██████▋   | 250460/371472 [8:53:00<9:14:50,  3.63it/s]
                                                           
{'loss': 2.7813, 'learning_rate': 3.933450408325971e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250460/371472 [8:53:00<9:14:50,  3.63it/s]
 67%|██████▋   | 250461/371472 [8:53:00<9:23:04,  3.58it/s]
 67%|██████▋   | 250462/371472 [8:53:01<9:52:04,  3.41it/s]
 67%|██████▋   | 250463/371472 [8:53:01<10:22:01,  3.24it/s]
 67%|██████▋   | 250464/371472 [8:53:01<9:45:31,  3.44it/s] 
 67%|██████▋   | 250465/371472 [8:53:01<9:28:16,  3.55it/s]
 67%|██████▋   | 250466/371472 [8:53:02<9:43:41,  3.46it/s]
 67%|██████▋   | 250467/371472 [8:53:02<9:52:46,  3.40it/s]
 67%|██████▋   | 250468/371472 [8:53:02<9:40:54,  3.47it/s]
 67%|██████▋   | 250469/371472 [8:53:03<9:39:23,  3.48it/s]
 67%|██████▋   | 250470/371472 [8:53:03<9:25:25,  3.57it/s]
 67%|██████▋   | 250471/371472 [8:53:03<9:56:45,  3.38it/s]
 67%|██████▋   | 250472/371472 [8:53:04<9:42:50,  3.46it/s]
 67%|██████▋   | 250473/371472 [8:53:04<9:46:27,  3.44it/s]
 67%|██████▋   | 250474/371472 [8:53:04<10:02:37,  3.35it/s]
 67%|██████▋   | 250475/371472 [8:53:04<9:37:29,  3.49it/s] 
 67%|██████▋   | 250476/371472 [8:53:05<9:08:47,  3.67it/s]
 67%|██████▋   | 250477/371472 [8:53:05<9:38:52,  3.48it/s]
 67%|██████▋   | 250478/371472 [8:53:05<9:50:42,  3.41it/s]
 67%|██████▋   | 250479/371472 [8:53:06<9:34:05,  3.51it/s]
 67%|██████▋   | 250480/371472 [8:53:06<9:19:25,  3.60it/s]
                                                           
{'loss': 2.8129, 'learning_rate': 3.9329655885711827e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250480/371472 [8:53:06<9:19:25,  3.60it/s]
 67%|██████▋   | 250481/371472 [8:53:06<9:24:42,  3.57it/s]
 67%|██████▋   | 250482/371472 [8:53:06<9:17:24,  3.62it/s]
 67%|██████▋   | 250483/371472 [8:53:07<9:23:01,  3.58it/s]
 67%|██████▋   | 250484/371472 [8:53:07<9:45:19,  3.45it/s]
 67%|██████▋   | 250485/371472 [8:53:07<9:31:12,  3.53it/s]
 67%|██████▋   | 250486/371472 [8:53:07<9:12:36,  3.65it/s]
 67%|██████▋   | 250487/371472 [8:53:08<9:13:58,  3.64it/s]
 67%|██████▋   | 250488/371472 [8:53:08<9:10:11,  3.66it/s]
 67%|██████▋   | 250489/371472 [8:53:08<9:18:14,  3.61it/s]
 67%|██████▋   | 250490/371472 [8:53:09<9:06:23,  3.69it/s]
 67%|██████▋   | 250491/371472 [8:53:09<10:27:56,  3.21it/s]
 67%|██████▋   | 250492/371472 [8:53:09<9:57:41,  3.37it/s] 
 67%|██████▋   | 250493/371472 [8:53:09<9:40:43,  3.47it/s]
 67%|██████▋   | 250494/371472 [8:53:10<9:30:35,  3.53it/s]
 67%|██████▋   | 250495/371472 [8:53:10<9:33:16,  3.52it/s]
 67%|██████▋   | 250496/371472 [8:53:10<10:18:19,  3.26it/s]
 67%|██████▋   | 250497/371472 [8:53:11<9:42:57,  3.46it/s] 
 67%|██████▋   | 250498/371472 [8:53:11<9:51:39,  3.41it/s]
 67%|██████▋   | 250499/371472 [8:53:11<9:42:10,  3.46it/s]
 67%|██████▋   | 250500/371472 [8:53:12<10:26:11,  3.22it/s]
                                                            
{'loss': 2.9891, 'learning_rate': 3.932480768816393e-07, 'epoch': 10.79}
+
 67%|��█████▋   | 250500/371472 [8:53:12<10:26:11,  3.22it/s]
 67%|██████▋   | 250501/371472 [8:53:12<10:37:49,  3.16it/s]
 67%|██████▋   | 250502/371472 [8:53:12<10:19:17,  3.26it/s]
 67%|██████▋   | 250503/371472 [8:53:13<10:55:40,  3.07it/s]
 67%|██████▋   | 250504/371472 [8:53:13<10:36:25,  3.17it/s]
 67%|██████▋   | 250505/371472 [8:53:13<10:02:10,  3.35it/s]
 67%|██████▋   | 250506/371472 [8:53:13<9:36:05,  3.50it/s] 
 67%|██████▋   | 250507/371472 [8:53:14<9:49:05,  3.42it/s]
 67%|██████▋   | 250508/371472 [8:53:14<9:19:45,  3.60it/s]
 67%|██████▋   | 250509/371472 [8:53:14<9:22:09,  3.59it/s]
 67%|██████▋   | 250510/371472 [8:53:15<10:12:39,  3.29it/s]
 67%|██████▋   | 250511/371472 [8:53:15<9:53:36,  3.40it/s] 
 67%|██████▋   | 250512/371472 [8:53:15<9:29:57,  3.54it/s]
 67%|██████▋   | 250513/371472 [8:53:15<9:18:27,  3.61it/s]
 67%|██████▋   | 250514/371472 [8:53:16<9:04:15,  3.70it/s]
 67%|██████▋   | 250515/371472 [8:53:16<9:07:15,  3.68it/s]
 67%|██████▋   | 250516/371472 [8:53:16<9:35:08,  3.51it/s]
 67%|██████▋   | 250517/371472 [8:53:17<10:32:26,  3.19it/s]
 67%|██████▋   | 250518/371472 [8:53:17<10:19:36,  3.25it/s]
 67%|██████▋   | 250519/371472 [8:53:17<10:03:58,  3.34it/s]
 67%|██████▋   | 250520/371472 [8:53:17<9:26:29,  3.56it/s] 
                                                           
{'loss': 2.7887, 'learning_rate': 3.9319959490616046e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250520/371472 [8:53:17<9:26:29,  3.56it/s]
 67%|██████▋   | 250521/371472 [8:53:18<9:26:36,  3.56it/s]
 67%|██████▋   | 250522/371472 [8:53:18<9:31:19,  3.53it/s]
 67%|██████▋   | 250523/371472 [8:53:18<9:06:37,  3.69it/s]
 67%|██████▋   | 250524/371472 [8:53:18<9:05:06,  3.70it/s]
 67%|██████▋   | 250525/371472 [8:53:19<9:15:49,  3.63it/s]
 67%|██████▋   | 250526/371472 [8:53:19<9:08:25,  3.68it/s]
 67%|██████▋   | 250527/371472 [8:53:19<9:27:37,  3.55it/s]
 67%|██████▋   | 250528/371472 [8:53:20<9:13:05,  3.64it/s]
 67%|██████▋   | 250529/371472 [8:53:20<9:32:37,  3.52it/s]
 67%|██████▋   | 250530/371472 [8:53:20<9:33:53,  3.51it/s]
 67%|██████▋   | 250531/371472 [8:53:20<9:20:46,  3.59it/s]
 67%|██████▋   | 250532/371472 [8:53:21<9:10:42,  3.66it/s]
 67%|██████▋   | 250533/371472 [8:53:21<9:09:19,  3.67it/s]
 67%|██████▋   | 250534/371472 [8:53:21<9:12:01,  3.65it/s]
 67%|██████▋   | 250535/371472 [8:53:22<9:09:29,  3.67it/s]
 67%|██████▋   | 250536/371472 [8:53:22<9:12:56,  3.65it/s]
 67%|██████▋   | 250537/371472 [8:53:22<9:15:27,  3.63it/s]
 67%|██████▋   | 250538/371472 [8:53:22<9:10:45,  3.66it/s]
 67%|██████▋   | 250539/371472 [8:53:23<8:57:34,  3.75it/s]
 67%|██████▋   | 250540/371472 [8:53:23<9:11:26,  3.65it/s]
                                                           
{'loss': 2.8381, 'learning_rate': 3.9315111293068153e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250540/371472 [8:53:23<9:11:26,  3.65it/s]
 67%|██████▋   | 250541/371472 [8:53:23<9:20:56,  3.59it/s]
 67%|██████▋   | 250542/371472 [8:53:23<9:16:38,  3.62it/s]
 67%|██████▋   | 250543/371472 [8:53:24<9:53:50,  3.39it/s]
 67%|██████▋   | 250544/371472 [8:53:24<9:43:11,  3.46it/s]
 67%|██████▋   | 250545/371472 [8:53:24<9:12:21,  3.65it/s]
 67%|██████▋   | 250546/371472 [8:53:25<8:57:15,  3.75it/s]
 67%|██████▋   | 250547/371472 [8:53:25<9:36:11,  3.50it/s]
 67%|██████▋   | 250548/371472 [8:53:25<9:20:58,  3.59it/s]
 67%|██████▋   | 250549/371472 [8:53:25<8:58:41,  3.74it/s]
 67%|██████▋   | 250550/371472 [8:53:26<9:05:51,  3.69it/s]
 67%|██████▋   | 250551/371472 [8:53:26<9:00:21,  3.73it/s]
 67%|██████▋   | 250552/371472 [8:53:26<9:15:10,  3.63it/s]
 67%|██████▋   | 250553/371472 [8:53:26<8:58:44,  3.74it/s]
 67%|██████▋   | 250554/371472 [8:53:27<9:01:24,  3.72it/s]
 67%|██████▋   | 250555/371472 [8:53:27<8:55:18,  3.76it/s]
 67%|██████▋   | 250556/371472 [8:53:27<9:24:22,  3.57it/s]
 67%|██████▋   | 250557/371472 [8:53:28<9:28:36,  3.54it/s]
 67%|██████▋   | 250558/371472 [8:53:28<9:26:22,  3.56it/s]
 67%|██████▋   | 250559/371472 [8:53:28<9:37:17,  3.49it/s]
 67%|██████▋   | 250560/371472 [8:53:28<9:45:00,  3.44it/s]
                                                           
{'loss': 2.9896, 'learning_rate': 3.931026309552027e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250560/371472 [8:53:28<9:45:00,  3.44it/s]
 67%|██████▋   | 250561/371472 [8:53:29<9:27:20,  3.55it/s]
 67%|██████▋   | 250562/371472 [8:53:29<9:37:56,  3.49it/s]
 67%|██████▋   | 250563/371472 [8:53:29<9:13:02,  3.64it/s]
 67%|██████▋   | 250564/371472 [8:53:30<9:43:33,  3.45it/s]
 67%|██████▋   | 250565/371472 [8:53:30<10:07:42,  3.32it/s]
 67%|██████▋   | 250566/371472 [8:53:30<10:21:27,  3.24it/s]
 67%|██████▋   | 250567/371472 [8:53:31<10:25:13,  3.22it/s]
 67%|██████▋   | 250568/371472 [8:53:31<10:13:12,  3.29it/s]
 67%|██████▋   | 250569/371472 [8:53:31<9:37:30,  3.49it/s] 
 67%|██████▋   | 250570/371472 [8:53:31<9:21:25,  3.59it/s]
 67%|██████▋   | 250571/371472 [8:53:32<8:57:14,  3.75it/s]
 67%|██████▋   | 250572/371472 [8:53:32<9:00:37,  3.73it/s]
 67%|██████▋   | 250573/371472 [8:53:32<9:28:03,  3.55it/s]
 67%|██████▋   | 250574/371472 [8:53:32<9:17:25,  3.61it/s]
 67%|██████▋   | 250575/371472 [8:53:33<10:01:02,  3.35it/s]
 67%|██████▋   | 250576/371472 [8:53:33<9:42:25,  3.46it/s] 
 67%|██████▋   | 250577/371472 [8:53:33<10:43:44,  3.13it/s]
 67%|██████▋   | 250578/371472 [8:53:34<10:18:14,  3.26it/s]
 67%|██████▋   | 250579/371472 [8:53:34<10:44:51,  3.12it/s]
 67%|██████▋   | 250580/371472 [8:53:34<11:00:21,  3.05it/s]
                                                            
{'loss': 2.8467, 'learning_rate': 3.9305414897972373e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250580/371472 [8:53:34<11:00:21,  3.05it/s]
 67%|██████▋   | 250581/371472 [8:53:35<10:22:59,  3.23it/s]
 67%|██████▋   | 250582/371472 [8:53:35<10:04:09,  3.33it/s]
 67%|██████▋   | 250583/371472 [8:53:35<10:06:53,  3.32it/s]
 67%|██████▋   | 250584/371472 [8:53:36<9:36:42,  3.49it/s] 
 67%|██████▋   | 250585/371472 [8:53:36<9:56:20,  3.38it/s]
 67%|██████▋   | 250586/371472 [8:53:36<10:26:29,  3.22it/s]
 67%|██████▋   | 250587/371472 [8:53:36<10:17:23,  3.26it/s]
 67%|██████▋   | 250588/371472 [8:53:37<11:03:20,  3.04it/s]
 67%|██████▋   | 250589/371472 [8:53:37<10:10:48,  3.30it/s]
 67%|██████▋   | 250590/371472 [8:53:37<9:47:09,  3.43it/s] 
 67%|██████▋   | 250591/371472 [8:53:38<9:25:49,  3.56it/s]
 67%|██████▋   | 250592/371472 [8:53:38<9:38:20,  3.48it/s]
 67%|██████▋   | 250593/371472 [8:53:38<9:22:38,  3.58it/s]
 67%|██████▋   | 250594/371472 [8:53:38<9:16:56,  3.62it/s]
 67%|██████▋   | 250595/371472 [8:53:39<11:06:10,  3.02it/s]
 67%|██████▋   | 250596/371472 [8:53:39<10:29:56,  3.20it/s]
 67%|██████▋   | 250597/371472 [8:53:39<10:06:13,  3.32it/s]
 67%|██████▋   | 250598/371472 [8:53:40<9:58:18,  3.37it/s] 
 67%|██████▋   | 250599/371472 [8:53:40<9:32:14,  3.52it/s]
 67%|██████▋   | 250600/371472 [8:53:40<9:23:46,  3.57it/s]
                                                           
{'loss': 2.8864, 'learning_rate': 3.930056670042449e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250600/371472 [8:53:40<9:23:46,  3.57it/s]
 67%|██████▋   | 250601/371472 [8:53:41<9:19:59,  3.60it/s]
 67%|██████▋   | 250602/371472 [8:53:41<9:03:19,  3.71it/s]
 67%|██████▋   | 250603/371472 [8:53:41<9:04:44,  3.70it/s]
 67%|██████▋   | 250604/371472 [8:53:41<9:07:47,  3.68it/s]
 67%|██████▋   | 250605/371472 [8:53:42<8:58:16,  3.74it/s]
 67%|██████▋   | 250606/371472 [8:53:42<9:08:57,  3.67it/s]
 67%|██████▋   | 250607/371472 [8:53:42<9:02:37,  3.71it/s]
 67%|██████▋   | 250608/371472 [8:53:42<9:01:29,  3.72it/s]
 67%|██████▋   | 250609/371472 [8:53:43<8:50:12,  3.80it/s]
 67%|██████▋   | 250610/371472 [8:53:43<8:43:56,  3.84it/s]
 67%|██████▋   | 250611/371472 [8:53:43<9:25:46,  3.56it/s]
 67%|██████▋   | 250612/371472 [8:53:44<9:10:00,  3.66it/s]
 67%|██████▋   | 250613/371472 [8:53:44<9:10:23,  3.66it/s]
 67%|██████▋   | 250614/371472 [8:53:44<9:00:54,  3.72it/s]
 67%|██████▋   | 250615/371472 [8:53:44<8:59:09,  3.74it/s]
 67%|██████▋   | 250616/371472 [8:53:45<8:46:44,  3.82it/s]
 67%|██████▋   | 250617/371472 [8:53:45<8:56:08,  3.76it/s]
 67%|██████▋   | 250618/371472 [8:53:45<9:37:22,  3.49it/s]
 67%|██████▋   | 250619/371472 [8:53:45<9:11:01,  3.66it/s]
 67%|██████▋   | 250620/371472 [8:53:46<8:51:39,  3.79it/s]
                                                           
{'loss': 2.8035, 'learning_rate': 3.929571850287659e-07, 'epoch': 10.79}
+
 67%|██████▋   | 250620/371472 [8:53:46<8:51:39,  3.79it/s]
 67%|██████▋   | 250621/371472 [8:53:46<9:24:30,  3.57it/s]
 67%|██████▋   | 250622/371472 [8:53:46<10:15:03,  3.27it/s]
 67%|██████▋   | 250623/371472 [8:53:47<9:34:55,  3.50it/s] 
 67%|██████▋   | 250624/371472 [8:53:47<10:59:20,  3.05it/s]
 67%|██████▋   | 250625/371472 [8:53:47<10:10:48,  3.30it/s]
 67%|██████▋   | 250626/371472 [8:53:48<9:43:57,  3.45it/s] 
 67%|██████▋   | 250627/371472 [8:53:48<9:50:04,  3.41it/s]
 67%|██████▋   | 250628/371472 [8:53:48<9:36:43,  3.49it/s]
 67%|██████▋   | 250629/371472 [8:53:48<9:15:26,  3.63it/s]
 67%|██████▋   | 250630/371472 [8:53:49<9:21:56,  3.58it/s]
 67%|██████▋   | 250631/371472 [8:53:49<9:33:43,  3.51it/s]
 67%|██████▋   | 250632/371472 [8:53:49<9:05:51,  3.69it/s]
 67%|██████▋   | 250633/371472 [8:53:49<9:12:59,  3.64it/s]
 67%|██████▋   | 250634/371472 [8:53:50<8:58:42,  3.74it/s]
 67%|██████▋   | 250635/371472 [8:53:50<9:03:43,  3.70it/s]
 67%|██████▋   | 250636/371472 [8:53:50<8:44:50,  3.84it/s]
 67%|██████▋   | 250637/371472 [8:53:50<8:58:12,  3.74it/s]
 67%|██████▋   | 250638/371472 [8:53:51<8:35:12,  3.91it/s]
 67%|██████▋   | 250639/371472 [8:53:51<8:57:22,  3.75it/s]
 67%|██████▋   | 250640/371472 [8:53:51<9:13:58,  3.64it/s]
                                                           
{'loss': 2.7519, 'learning_rate': 3.929087030532871e-07, 'epoch': 10.8}
+
 67%|██████▋   | 250640/371472 [8:53:51<9:13:58,  3.64it/s]
 67%|██████▋   | 250641/371472 [8:53:52<9:08:11,  3.67it/s]
 67%|██████▋   | 250642/371472 [8:53:52<8:51:00,  3.79it/s]
 67%|██████▋   | 250643/371472 [8:53:52<8:44:50,  3.84it/s]
 67%|██████▋   | 250644/371472 [8:53:52<8:42:45,  3.85it/s]
 67%|██████▋   | 250645/371472 [8:53:53<8:43:43,  3.85it/s]
 67%|██████▋   | 250646/371472 [8:53:53<8:32:30,  3.93it/s]
 67%|██████▋   | 250647/371472 [8:53:53<9:37:39,  3.49it/s]
 67%|██████▋   | 250648/371472 [8:53:53<9:17:53,  3.61it/s]
 67%|██████▋   | 250649/371472 [8:53:54<9:27:12,  3.55it/s]
 67%|██████▋   | 250650/371472 [8:53:54<9:13:26,  3.64it/s]
 67%|██████▋   | 250651/371472 [8:53:54<9:33:14,  3.51it/s]
 67%|██████▋   | 250652/371472 [8:53:55<9:57:50,  3.37it/s]
 67%|██████▋   | 250653/371472 [8:53:55<9:32:45,  3.52it/s]
 67%|██████▋   | 250654/371472 [8:53:55<9:23:29,  3.57it/s]
 67%|██████▋   | 250655/371472 [8:53:55<8:58:52,  3.74it/s]
 67%|██████▋   | 250656/371472 [8:53:56<9:01:18,  3.72it/s]
 67%|██████▋   | 250657/371472 [8:53:56<8:51:56,  3.79it/s]
 67%|██████▋   | 250658/371472 [8:53:56<9:04:25,  3.70it/s]
 67%|██████▋   | 250659/371472 [8:53:57<9:46:14,  3.43it/s]
 67%|██████▋   | 250660/371472 [8:53:57<9:45:01,  3.44it/s]
                                                           
{'loss': 2.8253, 'learning_rate': 3.928602210778082e-07, 'epoch': 10.8}
+
 67%|██████▋   | 250660/371472 [8:53:57<9:45:01,  3.44it/s]
 67%|██████▋   | 250661/371472 [8:53:57<9:55:12,  3.38it/s]
 67%|██████▋   | 250662/371472 [8:53:57<9:39:43,  3.47it/s]
 67%|██████▋   | 250663/371472 [8:53:58<9:37:31,  3.49it/s]
 67%|██████▋   | 250664/371472 [8:53:58<10:23:44,  3.23it/s]
 67%|██████▋   | 250665/371472 [8:53:58<10:33:22,  3.18it/s]
 67%|██████▋   | 250666/371472 [8:53:59<9:49:47,  3.41it/s] 
 67%|██████▋   | 250667/371472 [8:53:59<9:57:25,  3.37it/s]
 67%|██████▋   | 250668/371472 [8:53:59<9:25:52,  3.56it/s]
 67%|██████▋   | 250669/371472 [8:53:59<9:10:57,  3.65it/s]
 67%|██████▋   | 250670/371472 [8:54:00<9:25:45,  3.56it/s]
 67%|██████▋   | 250671/371472 [8:54:00<9:03:12,  3.71it/s]
 67%|██████▋   | 250672/371472 [8:54:00<9:00:41,  3.72it/s]
 67%|██████▋   | 250673/371472 [8:54:01<9:22:07,  3.58it/s]
 67%|██████▋   | 250674/371472 [8:54:01<9:10:03,  3.66it/s]
 67%|██████▋   | 250675/371472 [8:54:01<9:00:49,  3.72it/s]
 67%|██████▋   | 250676/371472 [8:54:01<10:09:10,  3.30it/s]
 67%|██████▋   | 250677/371472 [8:54:02<10:34:34,  3.17it/s]
 67%|██████▋   | 250678/371472 [8:54:02<10:01:42,  3.35it/s]
 67%|██████▋   | 250679/371472 [8:54:02<9:42:12,  3.46it/s] 
 67%|██████▋   | 250680/371472 [8:54:03<9:26:52,  3.55it/s]
                                                           
{'loss': 2.7492, 'learning_rate': 3.928117391023293e-07, 'epoch': 10.8}
+
 67%|██████▋   | 250680/371472 [8:54:03<9:26:52,  3.55it/s]
 67%|██████▋   | 250681/371472 [8:54:03<9:12:32,  3.64it/s]
 67%|██████▋   | 250682/371472 [8:54:03<9:05:17,  3.69it/s]
 67%|██████▋   | 250683/371472 [8:54:03<8:51:40,  3.79it/s]
 67%|██████▋   | 250684/371472 [8:54:04<9:14:41,  3.63it/s]
 67%|██████▋   | 250685/371472 [8:54:04<9:31:53,  3.52it/s]
 67%|██████▋   | 250686/371472 [8:54:04<9:54:32,  3.39it/s]
 67%|██████▋   | 250687/371472 [8:54:05<9:57:23,  3.37it/s]
 67%|██████▋   | 250688/371472 [8:54:05<9:36:17,  3.49it/s]
 67%|██████▋   | 250689/371472 [8:54:05<9:34:57,  3.50it/s]
 67%|██████▋   | 250690/371472 [8:54:05<9:28:53,  3.54it/s]
 67%|██████▋   | 250691/371472 [8:54:06<9:17:37,  3.61it/s]
 67%|██████▋   | 250692/371472 [8:54:06<9:01:30,  3.72it/s]
 67%|██████▋   | 250693/371472 [8:54:06<8:52:03,  3.78it/s]
 67%|██████▋   | 250694/371472 [8:54:06<8:47:52,  3.81it/s]
 67%|██████▋   | 250695/371472 [8:54:07<9:15:36,  3.62it/s]
 67%|██████▋   | 250696/371472 [8:54:07<9:05:38,  3.69it/s]
 67%|██████▋   | 250697/371472 [8:54:07<9:17:44,  3.61it/s]
 67%|██████▋   | 250698/371472 [8:54:08<9:05:22,  3.69it/s]
 67%|██████▋   | 250699/371472 [8:54:08<9:08:55,  3.67it/s]
 67%|██████▋   | 250700/371472 [8:54:08<9:50:37,  3.41it/s]
                                                           
{'loss': 2.7333, 'learning_rate': 3.9276325712685037e-07, 'epoch': 10.8}
+
 67%|██████▋   | 250700/371472 [8:54:08<9:50:37,  3.41it/s]
 67%|██████▋   | 250701/371472 [8:54:08<9:39:17,  3.47it/s]
 67%|██████▋   | 250702/371472 [8:54:09<9:40:26,  3.47it/s]
 67%|██████▋   | 250703/371472 [8:54:09<9:26:33,  3.55it/s]
 67%|██████▋   | 250704/371472 [8:54:09<9:09:24,  3.66it/s]
 67%|██████▋   | 250705/371472 [8:54:09<8:51:27,  3.79it/s]
 67%|██████▋   | 250706/371472 [8:54:10<8:44:23,  3.84it/s]
 67%|██████▋   | 250707/371472 [8:54:10<8:56:37,  3.75it/s]
 67%|██████▋   | 250708/371472 [8:54:10<8:52:49,  3.78it/s]
 67%|██████▋   | 250709/371472 [8:54:11<8:51:35,  3.79it/s]
 67%|██████▋   | 250710/371472 [8:54:11<9:07:43,  3.67it/s]
 67%|██████▋   | 250711/371472 [8:54:11<9:09:13,  3.66it/s]
 67%|██████▋   | 250712/371472 [8:54:11<9:47:51,  3.42it/s]
 67%|██████▋   | 250713/371472 [8:54:12<9:19:49,  3.60it/s]
 67%|██████▋   | 250714/371472 [8:54:12<9:19:18,  3.60it/s]
 67%|██████▋   | 250715/371472 [8:54:12<9:15:34,  3.62it/s]
 67%|██████▋   | 250716/371472 [8:54:13<11:02:36,  3.04it/s]
 67%|██████▋   | 250717/371472 [8:54:13<10:20:54,  3.24it/s]
 67%|██████▋   | 250718/371472 [8:54:13<9:53:40,  3.39it/s] 
 67%|██████▋   | 250719/371472 [8:54:13<9:14:48,  3.63it/s]
 67%|██████▋   | 250720/371472 [8:54:14<9:02:45,  3.71it/s]
                                                           
{'loss': 2.9225, 'learning_rate': 3.927147751513715e-07, 'epoch': 10.8}
+
 67%|██████▋   | 250720/371472 [8:54:14<9:02:45,  3.71it/s]
 67%|██████▋   | 250721/371472 [8:54:14<9:09:06,  3.67it/s]
 67%|██████▋   | 250722/371472 [8:54:14<8:47:29,  3.82it/s]
 67%|██████▋   | 250723/371472 [8:54:15<9:31:05,  3.52it/s]
 67%|██████▋   | 250724/371472 [8:54:15<9:35:28,  3.50it/s]
 67%|██████▋   | 250725/371472 [8:54:15<9:40:28,  3.47it/s]
 67%|██████▋   | 250726/371472 [8:54:15<9:29:48,  3.53it/s]
 67%|██████▋   | 250727/371472 [8:54:16<9:03:38,  3.70it/s]
 67%|██████▋   | 250728/371472 [8:54:16<9:44:29,  3.44it/s]
 67%|██████▋   | 250729/371472 [8:54:16<9:44:05,  3.45it/s]
 67%|██████▋   | 250730/371472 [8:54:17<9:39:03,  3.48it/s]
 67%|██████▋   | 250731/371472 [8:54:17<9:43:43,  3.45it/s]
 67%|██████▋   | 250732/371472 [8:54:17<9:16:49,  3.61it/s]
 67%|██████▋   | 250733/371472 [8:54:17<9:33:43,  3.51it/s]
 67%|██████▋   | 250734/371472 [8:54:18<9:17:41,  3.61it/s]
 67%|██████▋   | 250735/371472 [8:54:18<9:14:15,  3.63it/s]
 67%|██████▋   | 250736/371472 [8:54:18<8:53:25,  3.77it/s]
 67%|██████▋   | 250737/371472 [8:54:18<8:39:53,  3.87it/s]
 67%|██████▋   | 250738/371472 [8:54:19<9:23:07,  3.57it/s]
 67%|██████▋   | 250739/371472 [8:54:19<9:00:50,  3.72it/s]
 67%|██████▋   | 250740/371472 [8:54:19<9:14:41,  3.63it/s]
                                                           
{'loss': 2.9293, 'learning_rate': 3.926662931758926e-07, 'epoch': 10.8}
+
 67%|██████▋   | 250740/371472 [8:54:19<9:14:41,  3.63it/s]
 67%|██████▋   | 250741/371472 [8:54:20<8:57:51,  3.74it/s]
 67%|████��█▋   | 250742/371472 [8:54:20<8:46:48,  3.82it/s]
 67%|██████▋   | 250743/371472 [8:54:20<8:50:27,  3.79it/s]
 68%|██████▊   | 250744/371472 [8:54:20<8:46:19,  3.82it/s]
 68%|██████▊   | 250745/371472 [8:54:21<8:51:38,  3.78it/s]
 68%|██████▊   | 250746/371472 [8:54:21<9:09:51,  3.66it/s]
 68%|██████▊   | 250747/371472 [8:54:21<9:11:00,  3.65it/s]
 68%|██████▊   | 250748/371472 [8:54:22<10:06:03,  3.32it/s]
 68%|██████▊   | 250749/371472 [8:54:22<9:51:37,  3.40it/s] 
 68%|██████▊   | 250750/371472 [8:54:22<9:44:44,  3.44it/s]
 68%|██████▊   | 250751/371472 [8:54:22<9:52:26,  3.40it/s]
 68%|██████▊   | 250752/371472 [8:54:23<9:59:32,  3.36it/s]
 68%|██████▊   | 250753/371472 [8:54:23<9:43:27,  3.45it/s]
 68%|██████▊   | 250754/371472 [8:54:23<9:26:35,  3.55it/s]
 68%|██████▊   | 250755/371472 [8:54:24<10:24:17,  3.22it/s]
 68%|██████▊   | 250756/371472 [8:54:24<9:55:14,  3.38it/s] 
 68%|██████▊   | 250757/371472 [8:54:24<9:38:01,  3.48it/s]
 68%|██████▊   | 250758/371472 [8:54:24<9:06:32,  3.68it/s]
 68%|██████▊   | 250759/371472 [8:54:25<8:58:23,  3.74it/s]
 68%|██████▊   | 250760/371472 [8:54:25<9:42:38,  3.45it/s]
                                                           
{'loss': 2.9089, 'learning_rate': 3.9261781120041364e-07, 'epoch': 10.8}
+
 68%|██████▊   | 250760/371472 [8:54:25<9:42:38,  3.45it/s]
 68%|██████▊   | 250761/371472 [8:54:25<9:23:11,  3.57it/s]
 68%|██████▊   | 250762/371472 [8:54:25<8:55:11,  3.76it/s]
 68%|██████▊   | 250763/371472 [8:54:26<8:49:48,  3.80it/s]
 68%|██████▊   | 250764/371472 [8:54:26<8:43:08,  3.85it/s]
 68%|██████▊   | 250765/371472 [8:54:26<8:50:20,  3.79it/s]
 68%|██████▊   | 250766/371472 [8:54:26<8:44:08,  3.84it/s]
 68%|██████▊   | 250767/371472 [8:54:27<9:13:27,  3.63it/s]
 68%|██████▊   | 250768/371472 [8:54:27<9:57:44,  3.37it/s]
 68%|██████▊   | 250769/371472 [8:54:27<10:07:25,  3.31it/s]
 68%|██████▊   | 250770/371472 [8:54:28<9:50:13,  3.41it/s] 
 68%|██████▊   | 250771/371472 [8:54:28<9:23:51,  3.57it/s]
 68%|██████▊   | 250772/371472 [8:54:28<9:41:20,  3.46it/s]
 68%|██████▊   | 250773/371472 [8:54:29<9:51:38,  3.40it/s]
 68%|██████▊   | 250774/371472 [8:54:29<9:36:41,  3.49it/s]
 68%|██████▊   | 250775/371472 [8:54:29<9:45:23,  3.44it/s]
 68%|██████▊   | 250776/371472 [8:54:29<9:21:57,  3.58it/s]
 68%|██████▊   | 250777/371472 [8:54:30<9:09:55,  3.66it/s]
 68%|██████▊   | 250778/371472 [8:54:30<8:56:21,  3.75it/s]
 68%|██████▊   | 250779/371472 [8:54:30<8:42:52,  3.85it/s]
 68%|██████▊   | 250780/371472 [8:54:30<8:44:27,  3.84it/s]
                                                           
{'loss': 2.7526, 'learning_rate': 3.925693292249348e-07, 'epoch': 10.8}
+
 68%|██████▊   | 250780/371472 [8:54:30<8:44:27,  3.84it/s]
 68%|██████▊   | 250781/371472 [8:54:31<9:36:51,  3.49it/s]
 68%|██████▊   | 250782/371472 [8:54:31<9:06:18,  3.68it/s]
 68%|██████▊   | 250783/371472 [8:54:31<9:10:33,  3.65it/s]
 68%|██████▊   | 250784/371472 [8:54:32<8:53:49,  3.77it/s]
 68%|██████▊   | 250785/371472 [8:54:32<9:24:54,  3.56it/s]
 68%|██████▊   | 250786/371472 [8:54:32<9:19:02,  3.60it/s]
 68%|██████▊   | 250787/371472 [8:54:32<9:25:10,  3.56it/s]
 68%|██████▊   | 250788/371472 [8:54:33<9:38:20,  3.48it/s]
 68%|██████▊   | 250789/371472 [8:54:33<9:45:30,  3.44it/s]
 68%|██████▊   | 250790/371472 [8:54:33<9:21:07,  3.58it/s]
 68%|██████▊   | 250791/371472 [8:54:34<10:10:37,  3.29it/s]
 68%|██████▊   | 250792/371472 [8:54:34<9:48:16,  3.42it/s] 
 68%|██████▊   | 250793/371472 [8:54:34<9:45:38,  3.43it/s]
 68%|██████▊   | 250794/371472 [8:54:35<10:30:06,  3.19it/s]
 68%|██████▊   | 250795/371472 [8:54:35<9:45:56,  3.43it/s] 
 68%|██████▊   | 250796/371472 [8:54:35<9:55:06,  3.38it/s]
 68%|██████▊   | 250797/371472 [8:54:35<9:51:16,  3.40it/s]
 68%|██████▊   | 250798/371472 [8:54:36<9:48:06,  3.42it/s]
 68%|██████▊   | 250799/371472 [8:54:36<9:24:22,  3.56it/s]
 68%|██████▊   | 250800/371472 [8:54:36<9:04:14,  3.70it/s]
                                                           
{'loss': 2.7974, 'learning_rate': 3.925208472494559e-07, 'epoch': 10.8}
+
 68%|██████▊   | 250800/371472 [8:54:36<9:04:14,  3.70it/s]
 68%|██████▊   | 250801/371472 [8:54:36<9:03:41,  3.70it/s]
 68%|██████▊   | 250802/371472 [8:54:37<9:13:49,  3.63it/s]
 68%|██████▊   | 250803/371472 [8:54:37<9:06:02,  3.68it/s]
 68%|██████▊   | 250804/371472 [8:54:37<9:00:21,  3.72it/s]
 68%|██████▊   | 250805/371472 [8:54:38<8:52:48,  3.77it/s]
 68%|██████▊   | 250806/371472 [8:54:38<8:44:53,  3.83it/s]
 68%|██████▊   | 250807/371472 [8:54:38<8:48:26,  3.81it/s]
 68%|██████▊   | 250808/371472 [8:54:38<9:52:25,  3.39it/s]
 68%|██████▊   | 250809/371472 [8:54:39<9:38:21,  3.48it/s]
 68%|██████▊   | 250810/371472 [8:54:39<9:23:02,  3.57it/s]
 68%|██████▊   | 250811/371472 [8:54:39<9:25:29,  3.56it/s]
 68%|██████▊   | 250812/371472 [8:54:39<9:12:40,  3.64it/s]
 68%|██████▊   | 250813/371472 [8:54:40<9:16:57,  3.61it/s]
 68%|██████▊   | 250814/371472 [8:54:40<9:37:58,  3.48it/s]
 68%|██████▊   | 250815/371472 [8:54:40<9:38:28,  3.48it/s]
 68%|██████▊   | 250816/371472 [8:54:41<9:33:31,  3.51it/s]
 68%|██████▊   | 250817/371472 [8:54:41<9:31:10,  3.52it/s]
 68%|██████▊   | 250818/371472 [8:54:41<9:56:05,  3.37it/s]
 68%|██████▊   | 250819/371472 [8:54:42<10:09:22,  3.30it/s]
 68%|██████▊   | 250820/371472 [8:54:42<10:28:34,  3.20it/s]
                                                            
{'loss': 2.7513, 'learning_rate': 3.92472365273977e-07, 'epoch': 10.8}
+
 68%|██████▊   | 250820/371472 [8:54:42<10:28:34,  3.20it/s]
 68%|██████▊   | 250821/371472 [8:54:42<10:47:27,  3.11it/s]
 68%|██████▊   | 250822/371472 [8:54:43<10:49:03,  3.10it/s]
 68%|██████▊   | 250823/371472 [8:54:43<10:17:00,  3.26it/s]
 68%|██████▊   | 250824/371472 [8:54:43<10:04:48,  3.32it/s]
 68%|██████▊   | 250825/371472 [8:54:43<9:55:32,  3.38it/s] 
 68%|██████▊   | 250826/371472 [8:54:44<9:36:48,  3.49it/s]
 68%|██████▊   | 250827/371472 [8:54:44<9:36:30,  3.49it/s]
 68%|██████▊   | 250828/371472 [8:54:44<9:28:03,  3.54it/s]
 68%|██████▊   | 250829/371472 [8:54:45<11:55:26,  2.81it/s]
 68%|██████▊   | 250830/371472 [8:54:45<10:51:57,  3.08it/s]
 68%|██████▊   | 250831/371472 [8:54:45<10:18:31,  3.25it/s]
 68%|██████▊   | 250832/371472 [8:54:46<9:56:50,  3.37it/s] 
 68%|██████▊   | 250833/371472 [8:54:46<9:32:06,  3.51it/s]
 68%|██████▊   | 250834/371472 [8:54:46<9:27:14,  3.54it/s]
 68%|██████▊   | 250835/371472 [8:54:46<9:40:00,  3.47it/s]
 68%|██████▊   | 250836/371472 [8:54:47<9:23:50,  3.57it/s]
 68%|██████▊   | 250837/371472 [8:54:47<9:34:33,  3.50it/s]
 68%|██████▊   | 250838/371472 [8:54:47<9:37:14,  3.48it/s]
 68%|██████▊   | 250839/371472 [8:54:47<9:16:12,  3.61it/s]
 68%|██████▊   | 250840/371472 [8:54:48<9:01:56,  3.71it/s]
                                                           
{'loss': 2.6834, 'learning_rate': 3.924238832984981e-07, 'epoch': 10.8}
+
 68%|██████▊   | 250840/371472 [8:54:48<9:01:56,  3.71it/s]
 68%|██████▊   | 250841/371472 [8:54:48<9:11:57,  3.64it/s]
 68%|██████▊   | 250842/371472 [8:54:48<9:30:43,  3.52it/s]
 68%|██████▊   | 250843/371472 [8:54:49<9:04:02,  3.70it/s]
 68%|██████▊   | 250844/371472 [8:54:49<9:02:21,  3.71it/s]
 68%|██████▊   | 250845/371472 [8:54:49<9:31:02,  3.52it/s]
 68%|██████▊   | 250846/371472 [8:54:49<10:06:27,  3.32it/s]
 68%|██████▊   | 250847/371472 [8:54:50<9:40:20,  3.46it/s] 
 68%|██████▊   | 250848/371472 [8:54:50<10:09:55,  3.30it/s]
 68%|██████▊   | 250849/371472 [8:54:50<9:43:54,  3.44it/s] 
 68%|██████▊   | 250850/371472 [8:54:51<9:36:03,  3.49it/s]
 68%|██████▊   | 250851/371472 [8:54:51<9:50:19,  3.41it/s]
 68%|██████▊   | 250852/371472 [8:54:51<9:26:11,  3.55it/s]
 68%|██████▊   | 250853/371472 [8:54:51<9:13:06,  3.63it/s]
 68%|██████▊   | 250854/371472 [8:54:52<8:53:03,  3.77it/s]
 68%|██████▊   | 250855/371472 [8:54:52<9:35:30,  3.49it/s]
 68%|██████▊   | 250856/371472 [8:54:52<9:09:18,  3.66it/s]
 68%|██████▊   | 250857/371472 [8:54:53<9:00:20,  3.72it/s]
 68%|██████▊   | 250858/371472 [8:54:53<9:00:43,  3.72it/s]
 68%|██████▊   | 250859/371472 [8:54:53<8:52:09,  3.78it/s]
 68%|██████▊   | 250860/371472 [8:54:53<8:53:49,  3.77it/s]
                                                           
{'loss': 2.837, 'learning_rate': 3.9237540132301926e-07, 'epoch': 10.81}
+
 68%|██████▊   | 250860/371472 [8:54:53<8:53:49,  3.77it/s]
 68%|██████▊   | 250861/371472 [8:54:54<9:47:05,  3.42it/s]
 68%|██████▊   | 250862/371472 [8:54:54<10:29:42,  3.19it/s]
 68%|██████▊   | 250863/371472 [8:54:54<10:14:05,  3.27it/s]
 68%|██████▊   | 250864/371472 [8:54:55<10:18:53,  3.25it/s]
 68%|██████▊   | 250865/371472 [8:54:55<9:49:54,  3.41it/s] 
 68%|██████▊   | 250866/371472 [8:54:55<9:23:37,  3.57it/s]
 68%|██████▊   | 250867/371472 [8:54:55<9:14:53,  3.62it/s]
 68%|██████▊   | 250868/371472 [8:54:56<9:14:05,  3.63it/s]
 68%|██████▊   | 250869/371472 [8:54:56<9:18:16,  3.60it/s]
 68%|██████▊   | 250870/371472 [8:54:56<9:51:14,  3.40it/s]
 68%|██████▊   | 250871/371472 [8:54:57<9:45:19,  3.43it/s]
 68%|██████▊   | 250872/371472 [8:54:57<9:29:28,  3.53it/s]
 68%|██████▊   | 250873/371472 [8:54:57<9:29:54,  3.53it/s]
 68%|██████▊   | 250874/371472 [8:54:57<9:30:36,  3.52it/s]
 68%|██████▊   | 250875/371472 [8:54:58<9:31:12,  3.52it/s]
 68%|██████▊   | 250876/371472 [8:54:58<9:36:25,  3.49it/s]
 68%|██████▊   | 250877/371472 [8:54:58<9:50:15,  3.41it/s]
 68%|██████▊   | 250878/371472 [8:54:59<9:31:46,  3.52it/s]
 68%|██████▊   | 250879/371472 [8:54:59<9:26:19,  3.55it/s]
 68%|██████▊   | 250880/371472 [8:54:59<9:08:46,  3.66it/s]
                                                           
{'loss': 2.8656, 'learning_rate': 3.923269193475403e-07, 'epoch': 10.81}
+
 68%|██████▊   | 250880/371472 [8:54:59<9:08:46,  3.66it/s]
 68%|██████▊   | 250881/371472 [8:54:59<9:15:31,  3.62it/s]
 68%|██████▊   | 250882/371472 [8:55:00<9:40:59,  3.46it/s]
 68%|██████▊   | 250883/371472 [8:55:00<10:34:07,  3.17it/s]
 68%|██████▊   | 250884/371472 [8:55:00<9:57:24,  3.36it/s] 
 68%|██████▊   | 250885/371472 [8:55:01<9:50:24,  3.40it/s]
 68%|██████▊   | 250886/371472 [8:55:01<9:42:28,  3.45it/s]
 68%|██████▊   | 250887/371472 [8:55:01<9:12:49,  3.64it/s]
 68%|██████▊   | 250888/371472 [8:55:01<8:58:16,  3.73it/s]
 68%|██████▊   | 250889/371472 [8:55:02<8:40:13,  3.86it/s]
 68%|██████▊   | 250890/371472 [8:55:02<9:01:36,  3.71it/s]
 68%|██████▊   | 250891/371472 [8:55:02<8:37:55,  3.88it/s]
 68%|██████▊   | 250892/371472 [8:55:02<8:51:41,  3.78it/s]
 68%|██████▊   | 250893/371472 [8:55:03<8:51:00,  3.78it/s]
 68%|██████▊   | 250894/371472 [8:55:03<9:02:28,  3.70it/s]
 68%|██████▊   | 250895/371472 [8:55:03<8:53:31,  3.77it/s]
 68%|██████▊   | 250896/371472 [8:55:04<8:59:32,  3.72it/s]
 68%|██████▊   | 250897/371472 [8:55:04<9:04:18,  3.69it/s]
 68%|██████▊   | 250898/371472 [8:55:04<9:08:44,  3.66it/s]
 68%|██████▊   | 250899/371472 [8:55:04<8:54:00,  3.76it/s]
 68%|██████▊   | 250900/371472 [8:55:05<9:09:18,  3.66it/s]
                                                           
{'loss': 2.8475, 'learning_rate': 3.9227843737206146e-07, 'epoch': 10.81}
+
 68%|██████▊   | 250900/371472 [8:55:05<9:09:18,  3.66it/s]
 68%|██████▊   | 250901/371472 [8:55:05<8:53:28,  3.77it/s]
 68%|██████▊   | 250902/371472 [8:55:05<8:51:53,  3.78it/s]
 68%|██████▊   | 250903/371472 [8:55:05<8:39:16,  3.87it/s]
 68%|██████▊   | 250904/371472 [8:55:06<9:50:36,  3.40it/s]
 68%|██████▊   | 250905/371472 [8:55:06<9:31:08,  3.52it/s]
 68%|██████▊   | 250906/371472 [8:55:06<9:39:50,  3.47it/s]
 68%|██████▊   | 250907/371472 [8:55:07<9:06:32,  3.68it/s]
 68%|██████▊   | 250908/371472 [8:55:07<9:13:07,  3.63it/s]
 68%|██████▊   | 250909/371472 [8:55:07<10:20:05,  3.24it/s]
 68%|██████▊   | 250910/371472 [8:55:07<9:55:18,  3.38it/s] 
 68%|██████▊   | 250911/371472 [8:55:08<9:38:48,  3.47it/s]
 68%|██████▊   | 250912/371472 [8:55:08<10:11:26,  3.29it/s]
 68%|██████▊   | 250913/371472 [8:55:08<11:03:34,  3.03it/s]
 68%|██████▊   | 250914/371472 [8:55:09<10:47:20,  3.10it/s]
 68%|██████▊   | 250915/371472 [8:55:09<10:01:26,  3.34it/s]
 68%|██████▊   | 250916/371472 [8:55:09<9:38:15,  3.47it/s] 
 68%|██████▊   | 250917/371472 [8:55:10<9:42:35,  3.45it/s]
 68%|██████▊   | 250918/371472 [8:55:10<9:17:46,  3.60it/s]
 68%|██████▊   | 250919/371472 [8:55:10<11:30:32,  2.91it/s]
 68%|██████▊   | 250920/371472 [8:55:11<11:26:07,  2.93it/s]
                                                            
{'loss': 2.727, 'learning_rate': 3.9222995539658253e-07, 'epoch': 10.81}
+
 68%|██████▊   | 250920/371472 [8:55:11<11:26:07,  2.93it/s]
 68%|██████▊   | 250921/371472 [8:55:11<10:40:05,  3.14it/s]
 68%|██████▊   | 250922/371472 [8:55:11<10:04:38,  3.32it/s]
 68%|██████▊   | 250923/371472 [8:55:11<9:51:37,  3.40it/s] 
 68%|██████▊   | 250924/371472 [8:55:12<9:52:36,  3.39it/s]
 68%|██████▊   | 250925/371472 [8:55:12<9:37:32,  3.48it/s]
 68%|██████▊   | 250926/371472 [8:55:12<9:40:11,  3.46it/s]
 68%|██████▊   | 250927/371472 [8:55:13<9:26:29,  3.55it/s]
 68%|██████▊   | 250928/371472 [8:55:13<9:06:38,  3.68it/s]
 68%|██████▊   | 250929/371472 [8:55:13<9:56:48,  3.37it/s]
 68%|██████▊   | 250930/371472 [8:55:13<9:53:06,  3.39it/s]
 68%|██████▊   | 250931/371472 [8:55:14<9:48:20,  3.41it/s]
 68%|██████▊   | 250932/371472 [8:55:14<10:17:54,  3.25it/s]
 68%|██████▊   | 250933/371472 [8:55:14<9:44:39,  3.44it/s] 
 68%|██████▊   | 250934/371472 [8:55:15<9:26:00,  3.55it/s]
 68%|██████▊   | 250935/371472 [8:55:15<9:37:49,  3.48it/s]
 68%|██████▊   | 250936/371472 [8:55:15<9:48:41,  3.41it/s]
 68%|██████▊   | 250937/371472 [8:55:16<9:37:17,  3.48it/s]
 68%|██████▊   | 250938/371472 [8:55:16<9:31:40,  3.51it/s]
 68%|██████▊   | 250939/371472 [8:55:16<9:28:59,  3.53it/s]
 68%|██████▊   | 250940/371472 [8:55:16<9:50:17,  3.40it/s]
                                                           
{'loss': 2.8424, 'learning_rate': 3.9218147342110365e-07, 'epoch': 10.81}
+
 68%|██████▊   | 250940/371472 [8:55:16<9:50:17,  3.40it/s]
 68%|██████▊   | 250941/371472 [8:55:17<9:47:28,  3.42it/s]
 68%|██████▊   | 250942/371472 [8:55:17<9:25:09,  3.55it/s]
 68%|██████▊   | 250943/371472 [8:55:17<9:52:32,  3.39it/s]
 68%|██████▊   | 250944/371472 [8:55:18<9:32:19,  3.51it/s]
 68%|██████▊   | 250945/371472 [8:55:18<10:26:39,  3.21it/s]
 68%|██████▊   | 250946/371472 [8:55:18<10:16:50,  3.26it/s]
 68%|██████▊   | 250947/371472 [8:55:19<10:22:03,  3.23it/s]
 68%|██████▊   | 250948/371472 [8:55:19<10:06:16,  3.31it/s]
 68%|██████▊   | 250949/371472 [8:55:19<9:39:03,  3.47it/s] 
 68%|██████▊   | 250950/371472 [8:55:19<9:41:34,  3.45it/s]
 68%|██████▊   | 250951/371472 [8:55:20<9:31:08,  3.52it/s]
 68%|██████▊   | 250952/371472 [8:55:20<9:35:38,  3.49it/s]
 68%|██████▊   | 250953/371472 [8:55:20<9:24:44,  3.56it/s]
 68%|██████▊   | 250954/371472 [8:55:20<9:25:05,  3.55it/s]
 68%|██████▊   | 250955/371472 [8:55:21<9:47:11,  3.42it/s]
 68%|██████▊   | 250956/371472 [8:55:21<9:32:58,  3.51it/s]
 68%|██████▊   | 250957/371472 [8:55:21<9:06:41,  3.67it/s]
 68%|██████▊   | 250958/371472 [8:55:22<8:45:04,  3.83it/s]
 68%|██████▊   | 250959/371472 [8:55:22<8:45:18,  3.82it/s]
 68%|██████▊   | 250960/371472 [8:55:22<8:53:41,  3.76it/s]
                                                           
{'loss': 2.7377, 'learning_rate': 3.921329914456247e-07, 'epoch': 10.81}
+
 68%|██████▊   | 250960/371472 [8:55:22<8:53:41,  3.76it/s]
 68%|██████▊   | 250961/371472 [8:55:22<9:04:29,  3.69it/s]
 68%|██████▊   | 250962/371472 [8:55:23<9:02:56,  3.70it/s]
 68%|██████▊   | 250963/371472 [8:55:23<9:04:33,  3.69it/s]
 68%|██████▊   | 250964/371472 [8:55:23<8:44:06,  3.83it/s]
 68%|██████▊   | 250965/371472 [8:55:23<9:04:31,  3.69it/s]
 68%|██████▊   | 250966/371472 [8:55:24<8:54:14,  3.76it/s]
 68%|██████▊   | 250967/371472 [8:55:24<8:44:05,  3.83it/s]
 68%|██████▊   | 250968/371472 [8:55:24<8:41:39,  3.85it/s]
 68%|██████▊   | 250969/371472 [8:55:24<9:03:47,  3.69it/s]
 68%|██████▊   | 250970/371472 [8:55:25<9:04:20,  3.69it/s]
 68%|██████▊   | 250971/371472 [8:55:25<9:27:53,  3.54it/s]
 68%|██████▊   | 250972/371472 [8:55:25<9:16:42,  3.61it/s]
 68%|██████▊   | 250973/371472 [8:55:26<9:03:23,  3.70it/s]
 68%|██████▊   | 250974/371472 [8:55:26<9:14:15,  3.62it/s]
 68%|██████▊   | 250975/371472 [8:55:26<9:19:17,  3.59it/s]
 68%|██████▊   | 250976/371472 [8:55:26<9:22:15,  3.57it/s]
 68%|██████▊   | 250977/371472 [8:55:27<9:22:00,  3.57it/s]
 68%|██████▊   | 250978/371472 [8:55:27<9:06:30,  3.67it/s]
 68%|██████▊   | 250979/371472 [8:55:27<9:10:22,  3.65it/s]
 68%|██████▊   | 250980/371472 [8:55:28<9:22:39,  3.57it/s]
                                                           
{'loss': 2.983, 'learning_rate': 3.9208450947014585e-07, 'epoch': 10.81}
+
 68%|██████▊   | 250980/371472 [8:55:28<9:22:39,  3.57it/s]
 68%|██████▊   | 250981/371472 [8:55:28<9:00:24,  3.72it/s]
 68%|██████▊   | 250982/371472 [8:55:28<8:36:30,  3.89it/s]
 68%|██████▊   | 250983/371472 [8:55:28<8:35:05,  3.90it/s]
 68%|██████▊   | 250984/371472 [8:55:29<8:39:48,  3.86it/s]
 68%|██████▊   | 250985/371472 [8:55:29<8:36:23,  3.89it/s]
 68%|██████▊   | 250986/371472 [8:55:29<9:01:05,  3.71it/s]
 68%|██████▊   | 250987/371472 [8:55:29<9:39:06,  3.47it/s]
 68%|██████▊   | 250988/371472 [8:55:30<9:23:42,  3.56it/s]
 68%|██████▊   | 250989/371472 [8:55:30<9:26:58,  3.54it/s]
 68%|██████▊   | 250990/371472 [8:55:30<9:54:29,  3.38it/s]
 68%|██████▊   | 250991/371472 [8:55:31<9:21:19,  3.58it/s]
 68%|██████▊   | 250992/371472 [8:55:31<8:59:49,  3.72it/s]
 68%|██████▊   | 250993/371472 [8:55:31<8:44:02,  3.83it/s]
 68%|██████▊   | 250994/371472 [8:55:31<8:43:42,  3.83it/s]
 68%|██████▊   | 250995/371472 [8:55:32<9:35:06,  3.49it/s]
 68%|██████▊   | 250996/371472 [8:55:32<9:04:46,  3.69it/s]
 68%|██████▊   | 250997/371472 [8:55:32<9:19:07,  3.59it/s]
 68%|██████▊   | 250998/371472 [8:55:32<9:21:34,  3.58it/s]
 68%|██████▊   | 250999/371472 [8:55:33<9:07:16,  3.67it/s]
 68%|██████▊   | 251000/371472 [8:55:33<9:24:51,  3.55it/s]
                                                           
{'loss': 2.6517, 'learning_rate': 3.920360274946669e-07, 'epoch': 10.81}
+
 68%|██████▊   | 251000/371472 [8:55:33<9:24:51,  3.55it/s]
 68%|██████▊   | 251001/371472 [8:55:33<9:02:21,  3.70it/s]
 68%|██████▊   | 251002/371472 [8:55:34<9:04:44,  3.69it/s]
 68%|██████▊   | 251003/371472 [8:55:34<9:35:33,  3.49it/s]
 68%|██████▊   | 251004/371472 [8:55:34<9:49:58,  3.40it/s]
 68%|██████▊   | 251005/371472 [8:55:34<9:56:32,  3.37it/s]
 68%|██████▊   | 251006/371472 [8:55:35<9:24:29,  3.56it/s]
 68%|██████▊   | 251007/371472 [8:55:35<8:55:52,  3.75it/s]
 68%|██████▊   | 251008/371472 [8:55:35<8:43:17,  3.84it/s]
 68%|██████▊   | 251009/371472 [8:55:35<8:26:38,  3.96it/s]
 68%|██████▊   | 251010/371472 [8:55:36<8:50:50,  3.78it/s]
 68%|██████▊   | 251011/371472 [8:55:36<8:57:33,  3.73it/s]
 68%|██████▊   | 251012/371472 [8:55:36<9:34:15,  3.50it/s]
 68%|██████▊   | 251013/371472 [8:55:37<9:16:00,  3.61it/s]
 68%|██████▊   | 251014/371472 [8:55:37<9:22:19,  3.57it/s]
 68%|██████▊   | 251015/371472 [8:55:37<10:29:10,  3.19it/s]
 68%|██████▊   | 251016/371472 [8:55:38<10:14:10,  3.27it/s]
 68%|██████▊   | 251017/371472 [8:55:38<10:33:49,  3.17it/s]
 68%|██████▊   | 251018/371472 [8:55:38<9:48:58,  3.41it/s] 
 68%|██████▊   | 251019/371472 [8:55:38<9:14:10,  3.62it/s]
 68%|██████▊   | 251020/371472 [8:55:39<8:58:32,  3.73it/s]
                                                           
{'loss': 2.8317, 'learning_rate': 3.919875455191881e-07, 'epoch': 10.81}
+
 68%|██████▊   | 251020/371472 [8:55:39<8:58:32,  3.73it/s]
 68%|██████▊   | 251021/371472 [8:55:39<9:02:53,  3.70it/s]
 68%|██████▊   | 251022/371472 [8:55:39<9:10:03,  3.65it/s]
 68%|██████▊   | 251023/371472 [8:55:39<8:56:14,  3.74it/s]
 68%|██████▊   | 251024/371472 [8:55:40<9:34:32,  3.49it/s]
 68%|██████▊   | 251025/371472 [8:55:40<9:44:51,  3.43it/s]
 68%|██████▊   | 251026/371472 [8:55:40<10:14:15,  3.27it/s]
 68%|██████▊   | 251027/371472 [8:55:41<10:03:39,  3.33it/s]
 68%|██████▊   | 251028/371472 [8:55:41<9:20:35,  3.58it/s] 
 68%|██████▊   | 251029/371472 [8:55:41<9:37:06,  3.48it/s]
 68%|██████▊   | 251030/371472 [8:55:41<9:25:59,  3.55it/s]
 68%|██████▊   | 251031/371472 [8:55:42<9:16:31,  3.61it/s]
 68%|██████▊   | 251032/371472 [8:55:42<9:16:37,  3.61it/s]
 68%|██████▊   | 251033/371472 [8:55:42<9:19:08,  3.59it/s]
 68%|██████▊   | 251034/371472 [8:55:43<9:06:47,  3.67it/s]
 68%|██████▊   | 251035/371472 [8:55:43<10:09:15,  3.29it/s]
 68%|██████▊   | 251036/371472 [8:55:43<9:53:10,  3.38it/s] 
 68%|██████▊   | 251037/371472 [8:55:43<9:43:58,  3.44it/s]
 68%|██████▊   | 251038/371472 [8:55:44<9:26:10,  3.55it/s]
 68%|██████▊   | 251039/371472 [8:55:44<9:25:27,  3.55it/s]
 68%|██████▊   | 251040/371472 [8:55:44<9:40:34,  3.46it/s]
                                                           
{'loss': 2.7965, 'learning_rate': 3.9193906354370917e-07, 'epoch': 10.81}
+
 68%|██████▊   | 251040/371472 [8:55:44<9:40:34,  3.46it/s]
 68%|██████▊   | 251041/371472 [8:55:45<9:45:37,  3.43it/s]
 68%|██████▊   | 251042/371472 [8:55:45<9:11:15,  3.64it/s]
 68%|██████▊   | 251043/371472 [8:55:45<9:40:42,  3.46it/s]
 68%|██████▊   | 251044/371472 [8:55:46<10:00:56,  3.34it/s]
 68%|██████▊   | 251045/371472 [8:55:46<10:03:28,  3.33it/s]
 68%|██████▊   | 251046/371472 [8:55:46<9:32:47,  3.50it/s] 
 68%|██████▊   | 251047/371472 [8:55:46<9:03:11,  3.70it/s]
 68%|██████▊   | 251048/371472 [8:55:47<9:17:10,  3.60it/s]
 68%|██████▊   | 251049/371472 [8:55:47<9:22:28,  3.57it/s]
 68%|██████▊   | 251050/371472 [8:55:47<9:26:44,  3.54it/s]
 68%|██████▊   | 251051/371472 [8:55:47<9:22:16,  3.57it/s]
 68%|██████▊   | 251052/371472 [8:55:48<9:53:36,  3.38it/s]
 68%|██████▊   | 251053/371472 [8:55:48<10:05:24,  3.32it/s]
 68%|██████▊   | 251054/371472 [8:55:48<9:52:02,  3.39it/s] 
 68%|██████▊   | 251055/371472 [8:55:49<9:33:13,  3.50it/s]
 68%|██████▊   | 251056/371472 [8:55:49<9:12:01,  3.64it/s]
 68%|██████▊   | 251057/371472 [8:55:49<9:17:57,  3.60it/s]
 68%|██████▊   | 251058/371472 [8:55:49<9:25:09,  3.55it/s]
 68%|██████▊   | 251059/371472 [8:55:50<9:50:20,  3.40it/s]
 68%|██████▊   | 251060/371472 [8:55:50<9:38:00,  3.47it/s]
                                                           
{'loss': 2.8637, 'learning_rate': 3.918905815682303e-07, 'epoch': 10.81}
+
 68%|██████▊   | 251060/371472 [8:55:50<9:38:00,  3.47it/s]
 68%|██████▊   | 251061/371472 [8:55:50<9:49:59,  3.40it/s]
 68%|██████▊   | 251062/371472 [8:55:51<9:47:47,  3.41it/s]
 68%|██████▊   | 251063/371472 [8:55:51<10:08:43,  3.30it/s]
 68%|██████▊   | 251064/371472 [8:55:51<9:57:23,  3.36it/s] 
 68%|██████▊   | 251065/371472 [8:55:52<9:29:53,  3.52it/s]
 68%|██████▊   | 251066/371472 [8:55:52<9:12:16,  3.63it/s]
 68%|██████▊   | 251067/371472 [8:55:52<8:55:08,  3.75it/s]
 68%|██████▊   | 251068/371472 [8:55:52<8:57:53,  3.73it/s]
 68%|██████▊   | 251069/371472 [8:55:53<9:03:54,  3.69it/s]
 68%|██████▊   | 251070/371472 [8:55:53<9:10:26,  3.65it/s]
 68%|██████▊   | 251071/371472 [8:55:53<9:12:20,  3.63it/s]
 68%|██████▊   | 251072/371472 [8:55:53<9:13:23,  3.63it/s]
 68%|██████▊   | 251073/371472 [8:55:54<9:01:15,  3.71it/s]
 68%|██████▊   | 251074/371472 [8:55:54<9:47:19,  3.42it/s]
 68%|██████▊   | 251075/371472 [8:55:54<9:28:14,  3.53it/s]
 68%|██████▊   | 251076/371472 [8:55:54<9:00:25,  3.71it/s]
 68%|██████▊   | 251077/371472 [8:55:55<9:37:17,  3.48it/s]
 68%|██████▊   | 251078/371472 [8:55:55<9:21:22,  3.57it/s]
 68%|██████▊   | 251079/371472 [8:55:55<9:00:47,  3.71it/s]
 68%|██████▊   | 251080/371472 [8:55:56<8:51:46,  3.77it/s]
                                                           
{'loss': 2.8462, 'learning_rate': 3.9184209959275136e-07, 'epoch': 10.81}
+
 68%|██████▊   | 251080/371472 [8:55:56<8:51:46,  3.77it/s]
 68%|██████▊   | 251081/371472 [8:55:56<8:51:48,  3.77it/s]
 68%|██████▊   | 251082/371472 [8:55:56<9:03:33,  3.69it/s]
 68%|██████▊   | 251083/371472 [8:55:56<8:44:50,  3.82it/s]
 68%|██████▊   | 251084/371472 [8:55:57<9:04:28,  3.69it/s]
 68%|██████▊   | 251085/371472 [8:55:57<9:30:29,  3.52it/s]
 68%|██████▊   | 251086/371472 [8:55:57<9:18:10,  3.59it/s]
 68%|██████▊   | 251087/371472 [8:55:58<10:16:41,  3.25it/s]
 68%|██████▊   | 251088/371472 [8:55:58<11:03:06,  3.03it/s]
 68%|██████▊   | 251089/371472 [8:55:58<10:04:27,  3.32it/s]
 68%|██████▊   | 251090/371472 [8:55:59<9:47:24,  3.42it/s] 
 68%|██████▊   | 251091/371472 [8:55:59<9:27:41,  3.53it/s]
 68%|██████▊   | 251092/371472 [8:55:59<9:20:50,  3.58it/s]
 68%|██████▊   | 251093/371472 [8:55:59<9:28:40,  3.53it/s]
 68%|██████▊   | 251094/371472 [8:56:00<9:16:43,  3.60it/s]
 68%|██████▊   | 251095/371472 [8:56:00<9:27:22,  3.54it/s]
 68%|██████▊   | 251096/371472 [8:56:00<10:05:40,  3.31it/s]
 68%|██████▊   | 251097/371472 [8:56:01<9:37:38,  3.47it/s] 
 68%|██████▊   | 251098/371472 [8:56:01<11:25:36,  2.93it/s]
 68%|██████▊   | 251099/371472 [8:56:01<10:22:26,  3.22it/s]
 68%|██████▊   | 251100/371472 [8:56:01<9:50:32,  3.40it/s] 
                                                           
{'loss': 2.8885, 'learning_rate': 3.9179361761727254e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251100/371472 [8:56:01<9:50:32,  3.40it/s]
 68%|██████▊   | 251101/371472 [8:56:02<9:43:32,  3.44it/s]
 68%|██████▊   | 251102/371472 [8:56:02<9:45:25,  3.43it/s]
 68%|██████▊   | 251103/371472 [8:56:02<9:39:27,  3.46it/s]
 68%|██████▊   | 251104/371472 [8:56:03<9:49:03,  3.41it/s]
 68%|██████▊   | 251105/371472 [8:56:03<9:29:21,  3.52it/s]
 68%|██████▊   | 251106/371472 [8:56:03<9:00:50,  3.71it/s]
 68%|██████▊   | 251107/371472 [8:56:03<8:41:00,  3.85it/s]
 68%|██████▊   | 251108/371472 [8:56:04<9:18:45,  3.59it/s]
 68%|██████▊   | 251109/371472 [8:56:04<9:08:00,  3.66it/s]
 68%|██████▊   | 251110/371472 [8:56:04<8:51:58,  3.77it/s]
 68%|██████▊   | 251111/371472 [8:56:04<8:41:55,  3.84it/s]
 68%|██████▊   | 251112/371472 [8:56:05<8:38:51,  3.87it/s]
 68%|██████▊   | 251113/371472 [8:56:05<8:45:49,  3.81it/s]
 68%|██████▊   | 251114/371472 [8:56:05<10:43:04,  3.12it/s]
 68%|██████▊   | 251115/371472 [8:56:06<10:06:54,  3.31it/s]
 68%|██████▊   | 251116/371472 [8:56:06<10:09:34,  3.29it/s]
 68%|██████▊   | 251117/371472 [8:56:06<9:33:37,  3.50it/s] 
 68%|██████▊   | 251118/371472 [8:56:07<9:47:00,  3.42it/s]
 68%|██████▊   | 251119/371472 [8:56:07<10:04:26,  3.32it/s]
 68%|██████▊   | 251120/371472 [8:56:07<9:35:04,  3.49it/s] 
                                                           
{'loss': 2.7104, 'learning_rate': 3.917451356417936e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251120/371472 [8:56:07<9:35:04,  3.49it/s]
 68%|██████▊   | 251121/371472 [8:56:07<10:32:01,  3.17it/s]
 68%|██████▊   | 251122/371472 [8:56:08<10:01:22,  3.34it/s]
 68%|██████▊   | 251123/371472 [8:56:08<9:44:01,  3.43it/s] 
 68%|██████▊   | 251124/371472 [8:56:08<9:22:00,  3.57it/s]
 68%|██████▊   | 251125/371472 [8:56:09<9:33:05,  3.50it/s]
 68%|██████▊   | 251126/371472 [8:56:09<9:15:02,  3.61it/s]
 68%|██████▊   | 251127/371472 [8:56:09<9:16:02,  3.61it/s]
 68%|██████▊   | 251128/371472 [8:56:09<8:54:53,  3.75it/s]
 68%|██████▊   | 251129/371472 [8:56:10<8:54:50,  3.75it/s]
 68%|██████▊   | 251130/371472 [8:56:10<9:12:31,  3.63it/s]
 68%|██████▊   | 251131/371472 [8:56:10<8:55:03,  3.75it/s]
 68%|██████▊   | 251132/371472 [8:56:10<9:08:42,  3.66it/s]
 68%|██████▊   | 251133/371472 [8:56:11<8:57:31,  3.73it/s]
 68%|██████▊   | 251134/371472 [8:56:11<8:42:45,  3.84it/s]
 68%|██████▊   | 251135/371472 [8:56:11<8:52:39,  3.77it/s]
 68%|██████▊   | 251136/371472 [8:56:11<8:46:39,  3.81it/s]
 68%|██████▊   | 251137/371472 [8:56:12<8:31:56,  3.92it/s]
 68%|██████▊   | 251138/371472 [8:56:12<8:44:42,  3.82it/s]
 68%|██████▊   | 251139/371472 [8:56:12<8:48:47,  3.79it/s]
 68%|██████▊   | 251140/371472 [8:56:13<9:08:32,  3.66it/s]
                                                           
{'loss': 2.9144, 'learning_rate': 3.9169665366631474e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251140/371472 [8:56:13<9:08:32,  3.66it/s]
 68%|██████▊   | 251141/371472 [8:56:13<9:21:52,  3.57it/s]
 68%|██████▊   | 251142/371472 [8:56:13<9:06:55,  3.67it/s]
 68%|██████▊   | 251143/371472 [8:56:13<9:00:31,  3.71it/s]
 68%|██████▊   | 251144/371472 [8:56:14<9:16:48,  3.60it/s]
 68%|██████▊   | 251145/371472 [8:56:14<9:01:33,  3.70it/s]
 68%|██████▊   | 251146/371472 [8:56:14<8:45:48,  3.81it/s]
 68%|██████▊   | 251147/371472 [8:56:14<8:54:42,  3.75it/s]
 68%|██████▊   | 251148/371472 [8:56:15<10:45:45,  3.11it/s]
 68%|██████▊   | 251149/371472 [8:56:15<10:06:13,  3.31it/s]
 68%|██████▊   | 251150/371472 [8:56:15<9:59:53,  3.34it/s] 
 68%|██████▊   | 251151/371472 [8:56:16<9:42:16,  3.44it/s]
 68%|██████▊   | 251152/371472 [8:56:16<9:20:07,  3.58it/s]
 68%|██████▊   | 251153/371472 [8:56:16<9:03:30,  3.69it/s]
 68%|██████▊   | 251154/371472 [8:56:16<8:42:25,  3.84it/s]
 68%|██████▊   | 251155/371472 [8:56:17<8:53:02,  3.76it/s]
 68%|██████▊   | 251156/371472 [8:56:17<8:56:08,  3.74it/s]
 68%|██████▊   | 251157/371472 [8:56:17<9:19:55,  3.58it/s]
 68%|██████▊   | 251158/371472 [8:56:18<9:35:34,  3.48it/s]
 68%|██████▊   | 251159/371472 [8:56:18<9:12:11,  3.63it/s]
 68%|██████▊   | 251160/371472 [8:56:18<9:49:14,  3.40it/s]
                                                           
{'loss': 2.9292, 'learning_rate': 3.916481716908358e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251160/371472 [8:56:18<9:49:14,  3.40it/s]
 68%|██████▊   | 251161/371472 [8:56:19<10:08:03,  3.30it/s]
 68%|██████▊   | 251162/371472 [8:56:19<9:44:55,  3.43it/s] 
 68%|██████▊   | 251163/371472 [8:56:19<9:58:32,  3.35it/s]
 68%|██████▊   | 251164/371472 [8:56:19<9:43:45,  3.43it/s]
 68%|██████▊   | 251165/371472 [8:56:20<9:47:39,  3.41it/s]
 68%|██████▊   | 251166/371472 [8:56:20<10:02:41,  3.33it/s]
 68%|██████▊   | 251167/371472 [8:56:20<10:02:13,  3.33it/s]
 68%|██████▊   | 251168/371472 [8:56:21<9:17:32,  3.60it/s] 
 68%|██████▊   | 251169/371472 [8:56:21<10:10:47,  3.28it/s]
 68%|██████▊   | 251170/371472 [8:56:21<10:23:38,  3.22it/s]
 68%|██████▊   | 251171/371472 [8:56:22<10:04:03,  3.32it/s]
 68%|██████▊   | 251172/371472 [8:56:22<11:06:05,  3.01it/s]
 68%|██████▊   | 251173/371472 [8:56:22<10:55:43,  3.06it/s]
 68%|██████▊   | 251174/371472 [8:56:23<10:29:03,  3.19it/s]
 68%|██████▊   | 251175/371472 [8:56:23<9:47:26,  3.41it/s] 
 68%|██████▊   | 251176/371472 [8:56:23<9:29:49,  3.52it/s]
 68%|██████▊   | 251177/371472 [8:56:23<9:56:35,  3.36it/s]
 68%|██████▊   | 251178/371472 [8:56:24<9:43:37,  3.44it/s]
 68%|██████▊   | 251179/371472 [8:56:24<9:22:14,  3.57it/s]
 68%|██████▊   | 251180/371472 [8:56:24<9:03:41,  3.69it/s]
                                                           
{'loss': 2.7636, 'learning_rate': 3.91599689715357e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251180/371472 [8:56:24<9:03:41,  3.69it/s]
 68%|██████▊   | 251181/371472 [8:56:24<9:10:27,  3.64it/s]
 68%|██████▊   | 251182/371472 [8:56:25<8:51:16,  3.77it/s]
 68%|██████▊   | 251183/371472 [8:56:25<8:45:48,  3.81it/s]
 68%|██████▊   | 251184/371472 [8:56:25<8:37:26,  3.87it/s]
 68%|██████▊   | 251185/371472 [8:56:25<9:20:41,  3.58it/s]
 68%|██████▊   | 251186/371472 [8:56:26<9:35:06,  3.49it/s]
 68%|██████▊   | 251187/371472 [8:56:26<9:09:23,  3.65it/s]
 68%|██████▊   | 251188/371472 [8:56:26<8:55:58,  3.74it/s]
 68%|██████▊   | 251189/371472 [8:56:27<8:56:35,  3.74it/s]
 68%|██████▊   | 251190/371472 [8:56:27<9:06:57,  3.67it/s]
 68%|██████▊   | 251191/371472 [8:56:27<9:22:19,  3.56it/s]
 68%|██████▊   | 251192/371472 [8:56:27<9:11:38,  3.63it/s]
 68%|██████▊   | 251193/371472 [8:56:28<9:06:36,  3.67it/s]
 68%|██████▊   | 251194/371472 [8:56:28<9:17:53,  3.59it/s]
 68%|██████▊   | 251195/371472 [8:56:28<9:10:38,  3.64it/s]
 68%|██████▊   | 251196/371472 [8:56:29<9:18:38,  3.59it/s]
 68%|██████▊   | 251197/371472 [8:56:29<9:09:40,  3.65it/s]
 68%|██████▊   | 251198/371472 [8:56:29<9:01:34,  3.70it/s]
 68%|██████▊   | 251199/371472 [8:56:29<9:15:03,  3.61it/s]
 68%|██████▊   | 251200/371472 [8:56:30<9:23:46,  3.56it/s]
                                                           
{'loss': 2.9416, 'learning_rate': 3.91551207739878e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251200/371472 [8:56:30<9:23:46,  3.56it/s]
 68%|██████▊   | 251201/371472 [8:56:30<9:17:11,  3.60it/s]
 68%|██████▊   | 251202/371472 [8:56:30<9:27:26,  3.53it/s]
 68%|██████▊   | 251203/371472 [8:56:30<9:16:27,  3.60it/s]
 68%|██████▊   | 251204/371472 [8:56:31<9:39:05,  3.46it/s]
 68%|██████▊   | 251205/371472 [8:56:31<9:25:03,  3.55it/s]
 68%|██████▊   | 251206/371472 [8:56:31<9:14:03,  3.62it/s]
 68%|██████▊   | 251207/371472 [8:56:32<9:02:03,  3.70it/s]
 68%|██████▊   | 251208/371472 [8:56:32<8:58:50,  3.72it/s]
 68%|██████▊   | 251209/371472 [8:56:32<8:59:11,  3.72it/s]
 68%|██████▊   | 251210/371472 [8:56:32<9:04:22,  3.68it/s]
 68%|██████▊   | 251211/371472 [8:56:33<9:18:08,  3.59it/s]
 68%|██████▊   | 251212/371472 [8:56:33<9:02:01,  3.70it/s]
 68%|██████▊   | 251213/371472 [8:56:33<8:49:06,  3.79it/s]
 68%|██████▊   | 251214/371472 [8:56:33<8:46:34,  3.81it/s]
 68%|██████▊   | 251215/371472 [8:56:34<8:59:50,  3.71it/s]
 68%|██████▊   | 251216/371472 [8:56:34<9:19:47,  3.58it/s]
 68%|██████▊   | 251217/371472 [8:56:34<9:21:20,  3.57it/s]
 68%|██████▊   | 251218/371472 [8:56:35<9:13:26,  3.62it/s]
 68%|██████▊   | 251219/371472 [8:56:35<9:41:54,  3.44it/s]
 68%|██████▊   | 251220/371472 [8:56:35<11:02:22,  3.03it/s]
                                                            
{'loss': 2.8762, 'learning_rate': 3.915027257643992e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251220/371472 [8:56:35<11:02:22,  3.03it/s]
 68%|██████▊   | 251221/371472 [8:56:36<10:33:27,  3.16it/s]
 68%|██████▊   | 251222/371472 [8:56:36<9:52:05,  3.38it/s] 
 68%|██████▊   | 251223/371472 [8:56:36<10:03:29,  3.32it/s]
 68%|██████▊   | 251224/371472 [8:56:36<10:05:10,  3.31it/s]
 68%|██████▊   | 251225/371472 [8:56:37<9:39:00,  3.46it/s] 
 68%|██████▊   | 251226/371472 [8:56:37<9:19:49,  3.58it/s]
 68%|██████▊   | 251227/371472 [8:56:37<9:30:41,  3.51it/s]
 68%|██████▊   | 251228/371472 [8:56:38<9:34:12,  3.49it/s]
 68%|██████▊   | 251229/371472 [8:56:38<9:08:11,  3.66it/s]
 68%|██████▊   | 251230/371472 [8:56:38<9:25:24,  3.54it/s]
 68%|██████▊   | 251231/371472 [8:56:38<9:09:53,  3.64it/s]
 68%|██████▊   | 251232/371472 [8:56:39<8:41:38,  3.84it/s]
 68%|██████▊   | 251233/371472 [8:56:39<8:53:34,  3.76it/s]
 68%|██████▊   | 251234/371472 [8:56:39<9:00:38,  3.71it/s]
 68%|██████▊   | 251235/371472 [8:56:40<11:05:22,  3.01it/s]
 68%|██████▊   | 251236/371472 [8:56:40<10:40:39,  3.13it/s]
 68%|██████▊   | 251237/371472 [8:56:40<9:53:34,  3.38it/s] 
 68%|██████▊   | 251238/371472 [8:56:40<9:22:45,  3.56it/s]
 68%|██████▊   | 251239/371472 [8:56:41<9:41:28,  3.45it/s]
 68%|██████▊   | 251240/371472 [8:56:41<9:53:10,  3.38it/s]
                                                           
{'loss': 2.8578, 'learning_rate': 3.9145424378892025e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251240/371472 [8:56:41<9:53:10,  3.38it/s]
 68%|██████▊   | 251241/371472 [8:56:41<9:20:29,  3.58it/s]
 68%|██████▊   | 251242/371472 [8:56:42<9:19:16,  3.58it/s]
 68%|██████▊   | 251243/371472 [8:56:42<9:07:10,  3.66it/s]
 68%|██████▊   | 251244/371472 [8:56:42<8:50:16,  3.78it/s]
 68%|██████▊   | 251245/371472 [8:56:42<8:36:29,  3.88it/s]
 68%|██████▊   | 251246/371472 [8:56:43<9:10:29,  3.64it/s]
 68%|██████▊   | 251247/371472 [8:56:43<9:08:14,  3.65it/s]
 68%|██████▊   | 251248/371472 [8:56:43<9:48:11,  3.41it/s]
 68%|██████▊   | 251249/371472 [8:56:43<9:37:04,  3.47it/s]
 68%|██████▊   | 251250/371472 [8:56:44<9:40:52,  3.45it/s]
 68%|██████▊   | 251251/371472 [8:56:44<9:18:54,  3.58it/s]
 68%|██████▊   | 251252/371472 [8:56:44<9:35:43,  3.48it/s]
 68%|██████▊   | 251253/371472 [8:56:45<10:02:24,  3.33it/s]
 68%|██████▊   | 251254/371472 [8:56:45<9:32:01,  3.50it/s] 
 68%|██████▊   | 251255/371472 [8:56:45<9:14:28,  3.61it/s]
 68%|██████▊   | 251256/371472 [8:56:45<9:27:06,  3.53it/s]
 68%|██████▊   | 251257/371472 [8:56:46<9:10:59,  3.64it/s]
 68%|██████▊   | 251258/371472 [8:56:46<9:32:50,  3.50it/s]
 68%|██████▊   | 251259/371472 [8:56:46<9:34:55,  3.48it/s]
 68%|██████▊   | 251260/371472 [8:56:47<10:08:12,  3.29it/s]
                                                            
{'loss': 2.9038, 'learning_rate': 3.9140576181344127e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251260/371472 [8:56:47<10:08:12,  3.29it/s]
 68%|██████▊   | 251261/371472 [8:56:47<10:01:06,  3.33it/s]
 68%|██████▊   | 251262/371472 [8:56:47<10:38:39,  3.14it/s]
 68%|██████▊   | 251263/371472 [8:56:48<10:17:58,  3.24it/s]
 68%|██████▊   | 251264/371472 [8:56:48<9:56:30,  3.36it/s] 
 68%|██████▊   | 251265/371472 [8:56:48<9:23:09,  3.56it/s]
 68%|██████▊   | 251266/371472 [8:56:48<9:33:07,  3.50it/s]
 68%|██████▊   | 251267/371472 [8:56:49<9:12:34,  3.63it/s]
 68%|██████▊   | 251268/371472 [8:56:49<9:10:15,  3.64it/s]
 68%|██████▊   | 251269/371472 [8:56:49<9:17:45,  3.59it/s]
 68%|██████▊   | 251270/371472 [8:56:49<8:58:22,  3.72it/s]
 68%|██████▊   | 251271/371472 [8:56:50<9:00:35,  3.71it/s]
 68%|██████▊   | 251272/371472 [8:56:50<9:07:36,  3.66it/s]
 68%|██████▊   | 251273/371472 [8:56:50<9:16:46,  3.60it/s]
 68%|██████▊   | 251274/371472 [8:56:51<9:29:08,  3.52it/s]
 68%|██████▊   | 251275/371472 [8:56:51<9:11:26,  3.63it/s]
 68%|██████▊   | 251276/371472 [8:56:51<9:22:20,  3.56it/s]
 68%|██████▊   | 251277/371472 [8:56:51<9:09:27,  3.65it/s]
 68%|██████▊   | 251278/371472 [8:56:52<9:01:49,  3.70it/s]
 68%|██████▊   | 251279/371472 [8:56:52<8:51:53,  3.77it/s]
 68%|██████▊   | 251280/371472 [8:56:52<9:12:25,  3.63it/s]
                                                           
{'loss': 2.8882, 'learning_rate': 3.9135727983796245e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251280/371472 [8:56:52<9:12:25,  3.63it/s]
 68%|██████▊   | 251281/371472 [8:56:52<8:56:36,  3.73it/s]
 68%|██████▊   | 251282/371472 [8:56:53<8:55:58,  3.74it/s]
 68%|██████▊   | 251283/371472 [8:56:53<8:56:07,  3.74it/s]
 68%|██████▊   | 251284/371472 [8:56:53<8:51:24,  3.77it/s]
 68%|██████▊   | 251285/371472 [8:56:54<9:05:25,  3.67it/s]
 68%|██████▊   | 251286/371472 [8:56:54<9:16:13,  3.60it/s]
 68%|██████▊   | 251287/371472 [8:56:54<9:15:29,  3.61it/s]
 68%|██████▊   | 251288/371472 [8:56:54<9:05:29,  3.67it/s]
 68%|██████▊   | 251289/371472 [8:56:55<9:25:17,  3.54it/s]
 68%|██████▊   | 251290/371472 [8:56:55<9:46:46,  3.41it/s]
 68%|██████▊   | 251291/371472 [8:56:55<9:22:01,  3.56it/s]
 68%|██████▊   | 251292/371472 [8:56:56<9:49:58,  3.40it/s]
 68%|██████▊   | 251293/371472 [8:56:56<9:35:08,  3.48it/s]
 68%|██████▊   | 251294/371472 [8:56:56<9:27:15,  3.53it/s]
 68%|██████▊   | 251295/371472 [8:56:56<9:17:03,  3.60it/s]
 68%|██████▊   | 251296/371472 [8:56:57<9:18:46,  3.58it/s]
 68%|██████▊   | 251297/371472 [8:56:57<9:27:33,  3.53it/s]
 68%|██████▊   | 251298/371472 [8:56:57<9:16:16,  3.60it/s]
 68%|██████▊   | 251299/371472 [8:56:58<9:07:50,  3.66it/s]
 68%|██████▊   | 251300/371472 [8:56:58<9:04:20,  3.68it/s]
                                                           
{'loss': 2.8898, 'learning_rate': 3.913087978624835e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251300/371472 [8:56:58<9:04:20,  3.68it/s]
 68%|██████▊   | 251301/371472 [8:56:58<9:37:29,  3.47it/s]
 68%|██████▊   | 251302/371472 [8:56:58<9:13:33,  3.62it/s]
 68%|██████▊   | 251303/371472 [8:56:59<9:07:51,  3.66it/s]
 68%|██████▊   | 251304/371472 [8:56:59<9:00:49,  3.70it/s]
 68%|██████▊   | 251305/371472 [8:56:59<8:39:34,  3.85it/s]
 68%|██████▊   | 251306/371472 [8:56:59<9:01:00,  3.70it/s]
 68%|██████▊   | 251307/371472 [8:57:00<8:59:06,  3.71it/s]
 68%|██████▊   | 251308/371472 [8:57:00<9:34:08,  3.49it/s]
 68%|██████▊   | 251309/371472 [8:57:00<9:17:35,  3.59it/s]
 68%|██████▊   | 251310/371472 [8:57:01<9:18:54,  3.58it/s]
 68%|██████▊   | 251311/371472 [8:57:01<9:04:21,  3.68it/s]
 68%|██████▊   | 251312/371472 [8:57:01<9:01:45,  3.70it/s]
 68%|██████▊   | 251313/371472 [8:57:01<8:59:18,  3.71it/s]
 68%|██████▊   | 251314/371472 [8:57:02<9:23:11,  3.56it/s]
 68%|██████▊   | 251315/371472 [8:57:02<9:17:21,  3.59it/s]
 68%|██████▊   | 251316/371472 [8:57:02<10:38:14,  3.14it/s]
 68%|██████▊   | 251317/371472 [8:57:03<10:06:24,  3.30it/s]
 68%|██████▊   | 251318/371472 [8:57:03<10:57:40,  3.04it/s]
 68%|██████▊   | 251319/371472 [8:57:03<10:25:07,  3.20it/s]
 68%|██████▊   | 251320/371472 [8:57:04<9:49:40,  3.40it/s] 
                                                           
{'loss': 2.8746, 'learning_rate': 3.9126031588700465e-07, 'epoch': 10.82}
+
 68%|██████▊   | 251320/371472 [8:57:04<9:49:40,  3.40it/s]
 68%|██████▊   | 251321/371472 [8:57:04<10:04:00,  3.32it/s]
 68%|██████▊   | 251322/371472 [8:57:04<9:38:45,  3.46it/s] 
 68%|██████▊   | 251323/371472 [8:57:04<9:26:14,  3.54it/s]
 68%|██████▊   | 251324/371472 [8:57:05<9:30:46,  3.51it/s]
 68%|██████▊   | 251325/371472 [8:57:05<8:59:00,  3.72it/s]
 68%|██████▊   | 251326/371472 [8:57:05<8:54:49,  3.74it/s]
 68%|██████▊   | 251327/371472 [8:57:06<10:09:34,  3.28it/s]
 68%|██████▊   | 251328/371472 [8:57:06<9:43:30,  3.43it/s] 
 68%|██████▊   | 251329/371472 [8:57:06<9:19:19,  3.58it/s]
 68%|██████▊   | 251330/371472 [8:57:06<8:52:54,  3.76it/s]
 68%|██████▊   | 251331/371472 [8:57:07<8:55:41,  3.74it/s]
 68%|██████▊   | 251332/371472 [8:57:07<9:44:01,  3.43it/s]
 68%|██████▊   | 251333/371472 [8:57:07<9:46:43,  3.41it/s]
 68%|██████▊   | 251334/371472 [8:57:07<9:18:18,  3.59it/s]
 68%|██████▊   | 251335/371472 [8:57:08<9:05:55,  3.67it/s]
 68%|██████▊   | 251336/371472 [8:57:08<8:56:14,  3.73it/s]
 68%|██████▊   | 251337/371472 [8:57:08<8:44:58,  3.81it/s]
 68%|██████▊   | 251338/371472 [8:57:09<10:12:21,  3.27it/s]
 68%|██████▊   | 251339/371472 [8:57:09<10:14:46,  3.26it/s]
 68%|██████▊   | 251340/371472 [8:57:09<9:52:37,  3.38it/s] 
                                                           
{'loss': 2.9246, 'learning_rate': 3.912118339115257e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251340/371472 [8:57:09<9:52:37,  3.38it/s]
 68%|██████▊   | 251341/371472 [8:57:09<9:31:47,  3.50it/s]
 68%|██████▊   | 251342/371472 [8:57:10<9:50:26,  3.39it/s]
 68%|██████▊   | 251343/371472 [8:57:10<9:34:10,  3.49it/s]
 68%|██████▊   | 251344/371472 [8:57:10<9:34:43,  3.48it/s]
 68%|██████▊   | 251345/371472 [8:57:11<10:10:12,  3.28it/s]
 68%|██████▊   | 251346/371472 [8:57:11<9:45:41,  3.42it/s] 
 68%|██████▊   | 251347/371472 [8:57:11<10:21:27,  3.22it/s]
 68%|██████▊   | 251348/371472 [8:57:12<9:47:39,  3.41it/s] 
 68%|██████▊   | 251349/371472 [8:57:12<9:17:44,  3.59it/s]
 68%|██████▊   | 251350/371472 [8:57:12<9:09:42,  3.64it/s]
 68%|██████▊   | 251351/371472 [8:57:12<9:25:12,  3.54it/s]
 68%|██████▊   | 251352/371472 [8:57:13<9:52:32,  3.38it/s]
 68%|██████▊   | 251353/371472 [8:57:13<9:52:45,  3.38it/s]
 68%|██████▊   | 251354/371472 [8:57:13<10:14:35,  3.26it/s]
 68%|██████▊   | 251355/371472 [8:57:14<9:34:32,  3.48it/s] 
 68%|██████▊   | 251356/371472 [8:57:14<9:41:48,  3.44it/s]
 68%|██████▊   | 251357/371472 [8:57:14<9:36:08,  3.47it/s]
 68%|██████▊   | 251358/371472 [8:57:14<9:58:21,  3.35it/s]
 68%|██████▊   | 251359/371472 [8:57:15<9:26:36,  3.53it/s]
 68%|██████▊   | 251360/371472 [8:57:15<9:04:02,  3.68it/s]
                                                           
{'loss': 2.8203, 'learning_rate': 3.911633519360469e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251360/371472 [8:57:15<9:04:02,  3.68it/s]
 68%|██████▊   | 251361/371472 [8:57:15<9:22:06,  3.56it/s]
 68%|██████▊   | 251362/371472 [8:57:16<9:26:55,  3.53it/s]
 68%|██████▊   | 251363/371472 [8:57:16<10:01:43,  3.33it/s]
 68%|██████▊   | 251364/371472 [8:57:16<9:36:49,  3.47it/s] 
 68%|██████▊   | 251365/371472 [8:57:16<9:35:43,  3.48it/s]
 68%|██████▊   | 251366/371472 [8:57:17<9:34:44,  3.48it/s]
 68%|██████▊   | 251367/371472 [8:57:17<9:44:57,  3.42it/s]
 68%|██████▊   | 251368/371472 [8:57:17<9:22:06,  3.56it/s]
 68%|██████▊   | 251369/371472 [8:57:18<9:03:26,  3.68it/s]
 68%|██████▊   | 251370/371472 [8:57:18<9:11:45,  3.63it/s]
 68%|██████▊   | 251371/371472 [8:57:18<9:31:58,  3.50it/s]
 68%|██████▊   | 251372/371472 [8:57:18<9:36:57,  3.47it/s]
 68%|██████▊   | 251373/371472 [8:57:19<9:18:23,  3.58it/s]
 68%|██████▊   | 251374/371472 [8:57:19<9:08:38,  3.65it/s]
 68%|██████▊   | 251375/371472 [8:57:19<8:50:57,  3.77it/s]
 68%|██████▊   | 251376/371472 [8:57:19<8:37:40,  3.87it/s]
 68%|██████▊   | 251377/371472 [8:57:20<8:45:48,  3.81it/s]
 68%|██████▊   | 251378/371472 [8:57:20<8:39:00,  3.86it/s]
 68%|██████▊   | 251379/371472 [8:57:20<8:48:53,  3.78it/s]
 68%|██████▊   | 251380/371472 [8:57:20<8:49:49,  3.78it/s]
                                                           
{'loss': 2.7926, 'learning_rate': 3.911148699605679e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251380/371472 [8:57:20<8:49:49,  3.78it/s]
 68%|██████▊   | 251381/371472 [8:57:21<8:41:38,  3.84it/s]
 68%|██████▊   | 251382/371472 [8:57:21<8:37:20,  3.87it/s]
 68%|██████▊   | 251383/371472 [8:57:21<9:06:04,  3.67it/s]
 68%|██████▊   | 251384/371472 [8:57:22<8:44:32,  3.82it/s]
 68%|██████▊   | 251385/371472 [8:57:22<8:50:37,  3.77it/s]
 68%|██████▊   | 251386/371472 [8:57:22<8:56:37,  3.73it/s]
 68%|██████▊   | 251387/371472 [8:57:22<9:25:16,  3.54it/s]
 68%|██████▊   | 251388/371472 [8:57:23<9:39:46,  3.45it/s]
 68%|██████▊   | 251389/371472 [8:57:23<9:19:28,  3.58it/s]
 68%|██████▊   | 251390/371472 [8:57:23<9:28:21,  3.52it/s]
 68%|██████▊   | 251391/371472 [8:57:24<10:15:27,  3.25it/s]
 68%|██████▊   | 251392/371472 [8:57:24<10:29:47,  3.18it/s]
 68%|██████▊   | 251393/371472 [8:57:24<10:16:25,  3.25it/s]
 68%|██████▊   | 251394/371472 [8:57:25<10:23:15,  3.21it/s]
 68%|██████▊   | 251395/371472 [8:57:25<9:39:15,  3.45it/s] 
 68%|██████▊   | 251396/371472 [8:57:25<9:59:34,  3.34it/s]
 68%|██████▊   | 251397/371472 [8:57:25<9:50:45,  3.39it/s]
 68%|██████▊   | 251398/371472 [8:57:26<9:49:27,  3.40it/s]
 68%|██████▊   | 251399/371472 [8:57:26<9:42:05,  3.44it/s]
 68%|██████▊   | 251400/371472 [8:57:26<10:10:46,  3.28it/s]
                                                            
{'loss': 2.6715, 'learning_rate': 3.9106638798508904e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251400/371472 [8:57:26<10:10:46,  3.28it/s]
 68%|██████▊   | 251401/371472 [8:57:27<9:42:21,  3.44it/s] 
 68%|██████▊   | 251402/371472 [8:57:27<9:16:50,  3.59it/s]
 68%|██████▊   | 251403/371472 [8:57:27<9:44:26,  3.42it/s]
 68%|██████▊   | 251404/371472 [8:57:27<9:45:10,  3.42it/s]
 68%|██████▊   | 251405/371472 [8:57:28<9:20:29,  3.57it/s]
 68%|██████▊   | 251406/371472 [8:57:28<9:12:37,  3.62it/s]
 68%|██████▊   | 251407/371472 [8:57:28<9:31:17,  3.50it/s]
 68%|██████▊   | 251408/371472 [8:57:29<9:36:00,  3.47it/s]
 68%|██████▊   | 251409/371472 [8:57:29<9:15:57,  3.60it/s]
 68%|██████▊   | 251410/371472 [8:57:29<9:25:28,  3.54it/s]
 68%|██████▊   | 251411/371472 [8:57:29<10:08:07,  3.29it/s]
 68%|██████▊   | 251412/371472 [8:57:30<10:16:40,  3.24it/s]
 68%|██████▊   | 251413/371472 [8:57:30<10:03:55,  3.31it/s]
 68%|██████▊   | 251414/371472 [8:57:30<9:45:01,  3.42it/s] 
 68%|██████▊   | 251415/371472 [8:57:31<9:39:25,  3.45it/s]
 68%|██████▊   | 251416/371472 [8:57:31<9:50:07,  3.39it/s]
 68%|██████▊   | 251417/371472 [8:57:31<9:24:43,  3.54it/s]
 68%|██████▊   | 251418/371472 [8:57:32<9:53:55,  3.37it/s]
 68%|██████▊   | 251419/371472 [8:57:32<9:38:36,  3.46it/s]
 68%|██████▊   | 251420/371472 [8:57:32<9:44:21,  3.42it/s]
                                                           
{'loss': 2.8358, 'learning_rate': 3.9101790600961016e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251420/371472 [8:57:32<9:44:21,  3.42it/s]
 68%|██████▊   | 251421/371472 [8:57:32<9:16:41,  3.59it/s]
 68%|██████▊   | 251422/371472 [8:57:33<9:02:59,  3.68it/s]
 68%|██████▊   | 251423/371472 [8:57:33<9:57:32,  3.35it/s]
 68%|██████▊   | 251424/371472 [8:57:33<10:13:22,  3.26it/s]
 68%|██████▊   | 251425/371472 [8:57:34<9:56:09,  3.36it/s] 
 68%|██████▊   | 251426/371472 [8:57:34<9:33:29,  3.49it/s]
 68%|██████▊   | 251427/371472 [8:57:34<9:09:18,  3.64it/s]
 68%|██████▊   | 251428/371472 [8:57:34<9:31:31,  3.50it/s]
 68%|██████▊   | 251429/371472 [8:57:35<9:41:37,  3.44it/s]
 68%|██████▊   | 251430/371472 [8:57:35<9:05:10,  3.67it/s]
 68%|██████▊   | 251431/371472 [8:57:35<9:01:22,  3.70it/s]
 68%|██████▊   | 251432/371472 [8:57:35<8:48:38,  3.78it/s]
 68%|██████▊   | 251433/371472 [8:57:36<8:47:55,  3.79it/s]
 68%|██████▊   | 251434/371472 [8:57:36<8:52:21,  3.76it/s]
 68%|██████▊   | 251435/371472 [8:57:36<8:54:09,  3.75it/s]
 68%|██████▊   | 251436/371472 [8:57:37<9:17:25,  3.59it/s]
 68%|██████▊   | 251437/371472 [8:57:37<9:17:03,  3.59it/s]
 68%|██████▊   | 251438/371472 [8:57:37<9:06:53,  3.66it/s]
 68%|██████▊   | 251439/371472 [8:57:37<9:02:42,  3.69it/s]
 68%|██████▊   | 251440/371472 [8:57:38<8:47:21,  3.79it/s]
                                                           
{'loss': 2.7255, 'learning_rate': 3.909694240341313e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251440/371472 [8:57:38<8:47:21,  3.79it/s]
 68%|██████▊   | 251441/371472 [8:57:38<8:39:25,  3.85it/s]
 68%|██████▊   | 251442/371472 [8:57:38<9:10:24,  3.63it/s]
 68%|██████▊   | 251443/371472 [8:57:38<9:00:01,  3.70it/s]
 68%|██████▊   | 251444/371472 [8:57:39<8:46:56,  3.80it/s]
 68%|██████▊   | 251445/371472 [8:57:39<8:40:23,  3.84it/s]
 68%|██████▊   | 251446/371472 [8:57:39<9:22:59,  3.55it/s]
 68%|██████▊   | 251447/371472 [8:57:40<9:29:23,  3.51it/s]
 68%|██████▊   | 251448/371472 [8:57:40<9:12:16,  3.62it/s]
 68%|██████▊   | 251449/371472 [8:57:40<8:54:01,  3.75it/s]
 68%|██████▊   | 251450/371472 [8:57:40<9:17:55,  3.59it/s]
 68%|██████▊   | 251451/371472 [8:57:41<8:51:03,  3.77it/s]
 68%|██████▊   | 251452/371472 [8:57:41<8:47:56,  3.79it/s]
 68%|██████▊   | 251453/371472 [8:57:41<8:34:50,  3.89it/s]
 68%|██████▊   | 251454/371472 [8:57:41<8:26:44,  3.95it/s]
 68%|██████▊   | 251455/371472 [8:57:42<8:55:42,  3.73it/s]
 68%|██████▊   | 251456/371472 [8:57:42<9:41:54,  3.44it/s]
 68%|██████▊   | 251457/371472 [8:57:42<9:43:09,  3.43it/s]
 68%|██████▊   | 251458/371472 [8:57:43<9:52:04,  3.38it/s]
 68%|██████▊   | 251459/371472 [8:57:43<9:44:29,  3.42it/s]
 68%|██████▊   | 251460/371472 [8:57:43<10:06:01,  3.30it/s]
                                                            
{'loss': 2.8978, 'learning_rate': 3.9092094205865236e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251460/371472 [8:57:43<10:06:01,  3.30it/s]
 68%|██████▊   | 251461/371472 [8:57:44<10:27:55,  3.19it/s]
 68%|██████▊   | 251462/371472 [8:57:44<9:35:54,  3.47it/s] 
 68%|██████▊   | 251463/371472 [8:57:44<9:10:41,  3.63it/s]
 68%|██████▊   | 251464/371472 [8:57:44<9:16:27,  3.59it/s]
 68%|██████▊   | 251465/371472 [8:57:45<8:59:49,  3.71it/s]
 68%|██████▊   | 251466/371472 [8:57:45<9:17:45,  3.59it/s]
 68%|██████▊   | 251467/371472 [8:57:45<9:12:38,  3.62it/s]
 68%|██████▊   | 251468/371472 [8:57:45<9:04:22,  3.67it/s]
 68%|██████▊   | 251469/371472 [8:57:46<8:53:40,  3.75it/s]
 68%|██████▊   | 251470/371472 [8:57:46<8:45:48,  3.80it/s]
 68%|██████▊   | 251471/371472 [8:57:46<9:17:35,  3.59it/s]
 68%|██████▊   | 251472/371472 [8:57:46<9:11:03,  3.63it/s]
 68%|██████▊   | 251473/371472 [8:57:47<9:03:44,  3.68it/s]
 68%|██████▊   | 251474/371472 [8:57:47<9:30:51,  3.50it/s]
 68%|██████▊   | 251475/371472 [8:57:47<9:10:38,  3.63it/s]
 68%|██████▊   | 251476/371472 [8:57:48<8:52:17,  3.76it/s]
 68%|██████▊   | 251477/371472 [8:57:48<8:36:57,  3.87it/s]
 68%|██████▊   | 251478/371472 [8:57:48<8:32:19,  3.90it/s]
 68%|██████▊   | 251479/371472 [8:57:48<8:45:57,  3.80it/s]
 68%|██████▊   | 251480/371472 [8:57:49<9:32:50,  3.49it/s]
                                                           
{'loss': 2.8346, 'learning_rate': 3.9087246008317354e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251480/371472 [8:57:49<9:32:50,  3.49it/s]
 68%|██████▊   | 251481/371472 [8:57:49<10:18:29,  3.23it/s]
 68%|██████▊   | 251482/371472 [8:57:49<10:22:38,  3.21it/s]
 68%|██████▊   | 251483/371472 [8:57:50<12:10:36,  2.74it/s]
 68%|██████▊   | 251484/371472 [8:57:50<11:45:35,  2.83it/s]
 68%|██████▊   | 251485/371472 [8:57:50<11:15:37,  2.96it/s]
 68%|██████▊   | 251486/371472 [8:57:51<11:03:08,  3.02it/s]
 68%|██████▊   | 251487/371472 [8:57:51<10:44:44,  3.10it/s]
 68%|██████▊   | 251488/371472 [8:57:51<9:58:55,  3.34it/s] 
 68%|██████▊   | 251489/371472 [8:57:52<9:31:30,  3.50it/s]
 68%|██████▊   | 251490/371472 [8:57:52<9:21:19,  3.56it/s]
 68%|██████▊   | 251491/371472 [8:57:52<9:19:07,  3.58it/s]
 68%|██████▊   | 251492/371472 [8:57:52<9:08:28,  3.65it/s]
 68%|██████▊   | 251493/371472 [8:57:53<9:15:17,  3.60it/s]
 68%|██████▊   | 251494/371472 [8:57:53<8:58:02,  3.72it/s]
 68%|██████▊   | 251495/371472 [8:57:53<8:45:55,  3.80it/s]
 68%|██████▊   | 251496/371472 [8:57:53<8:54:04,  3.74it/s]
 68%|██████▊   | 251497/371472 [8:57:54<9:03:38,  3.68it/s]
 68%|██████▊   | 251498/371472 [8:57:54<9:02:54,  3.68it/s]
 68%|██████▊   | 251499/371472 [8:57:54<9:21:11,  3.56it/s]
 68%|██████▊   | 251500/371472 [8:57:55<9:19:55,  3.57it/s]
                                                           
{'loss': 2.6441, 'learning_rate': 3.908239781076946e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251500/371472 [8:57:55<9:19:55,  3.57it/s]
 68%|██████▊   | 251501/371472 [8:57:55<10:12:33,  3.26it/s]
 68%|██████▊   | 251502/371472 [8:57:55<9:36:44,  3.47it/s] 
 68%|██████▊   | 251503/371472 [8:57:55<9:31:30,  3.50it/s]
 68%|██████▊   | 251504/371472 [8:57:56<9:06:18,  3.66it/s]
 68%|██████▊   | 251505/371472 [8:57:56<9:17:15,  3.59it/s]
 68%|██████▊   | 251506/371472 [8:57:56<9:44:38,  3.42it/s]
 68%|██████▊   | 251507/371472 [8:57:57<9:35:53,  3.47it/s]
 68%|██████▊   | 251508/371472 [8:57:57<9:55:04,  3.36it/s]
 68%|██████▊   | 251509/371472 [8:57:57<10:37:03,  3.14it/s]
 68%|██████▊   | 251510/371472 [8:57:58<10:22:59,  3.21it/s]
 68%|██████▊   | 251511/371472 [8:57:58<10:11:37,  3.27it/s]
 68%|██████▊   | 251512/371472 [8:57:58<9:44:27,  3.42it/s] 
 68%|██████▊   | 251513/371472 [8:57:58<9:23:07,  3.55it/s]
 68%|██████▊   | 251514/371472 [8:57:59<9:24:45,  3.54it/s]
 68%|██████▊   | 251515/371472 [8:57:59<9:25:56,  3.53it/s]
 68%|██████▊   | 251516/371472 [8:57:59<9:27:31,  3.52it/s]
 68%|██████▊   | 251517/371472 [8:57:59<9:09:12,  3.64it/s]
 68%|██████▊   | 251518/371472 [8:58:00<8:48:31,  3.78it/s]
 68%|██████▊   | 251519/371472 [8:58:00<8:35:33,  3.88it/s]
 68%|██████▊   | 251520/371472 [8:58:00<8:21:50,  3.98it/s]
                                                           
{'loss': 3.0129, 'learning_rate': 3.9077549613221573e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251520/371472 [8:58:00<8:21:50,  3.98it/s]
 68%|██████▊   | 251521/371472 [8:58:00<8:29:06,  3.93it/s]
 68%|██████▊   | 251522/371472 [8:58:01<8:23:51,  3.97it/s]
 68%|██████▊   | 251523/371472 [8:58:01<8:25:43,  3.95it/s]
 68%|██████▊   | 251524/371472 [8:58:01<8:29:43,  3.92it/s]
 68%|██████▊   | 251525/371472 [8:58:02<8:48:34,  3.78it/s]
 68%|██████▊   | 251526/371472 [8:58:02<9:00:53,  3.70it/s]
 68%|██████▊   | 251527/371472 [8:58:02<9:10:47,  3.63it/s]
 68%|██████▊   | 251528/371472 [8:58:02<9:36:05,  3.47it/s]
 68%|██████▊   | 251529/371472 [8:58:03<13:43:59,  2.43it/s]
 68%|██████▊   | 251530/371472 [8:58:03<12:07:12,  2.75it/s]
 68%|██████▊   | 251531/371472 [8:58:04<12:21:24,  2.70it/s]
 68%|██████▊   | 251532/371472 [8:58:04<11:30:26,  2.90it/s]
 68%|██████▊   | 251533/371472 [8:58:04<10:30:08,  3.17it/s]
 68%|██████▊   | 251534/371472 [8:58:05<9:47:37,  3.40it/s] 
 68%|██████▊   | 251535/371472 [8:58:05<9:27:13,  3.52it/s]
 68%|██████▊   | 251536/371472 [8:58:05<9:24:22,  3.54it/s]
 68%|██████▊   | 251537/371472 [8:58:05<9:10:44,  3.63it/s]
 68%|██████▊   | 251538/371472 [8:58:06<9:08:17,  3.65it/s]
 68%|██████▊   | 251539/371472 [8:58:06<9:56:32,  3.35it/s]
 68%|██████▊   | 251540/371472 [8:58:06<9:39:41,  3.45it/s]
                                                           
{'loss': 2.8213, 'learning_rate': 3.907270141567368e-07, 'epoch': 10.83}
+
 68%|██████▊   | 251540/371472 [8:58:06<9:39:41,  3.45it/s]
 68%|██████▊   | 251541/371472 [8:58:06<9:31:15,  3.50it/s]
 68%|██████▊   | 251542/371472 [8:58:07<9:45:14,  3.42it/s]
 68%|██████▊   | 251543/371472 [8:58:07<9:27:55,  3.52it/s]
 68%|██████▊   | 251544/371472 [8:58:07<9:36:50,  3.47it/s]
 68%|██████▊   | 251545/371472 [8:58:08<9:15:30,  3.60it/s]
 68%|██████▊   | 251546/371472 [8:58:08<9:33:14,  3.49it/s]
 68%|██████▊   | 251547/371472 [8:58:08<10:05:44,  3.30it/s]
 68%|██████▊   | 251548/371472 [8:58:09<9:40:05,  3.45it/s] 
 68%|██████▊   | 251549/371472 [8:58:09<9:35:07,  3.48it/s]
 68%|██████▊   | 251550/371472 [8:58:09<9:51:42,  3.38it/s]
 68%|██████▊   | 251551/371472 [8:58:09<9:39:55,  3.45it/s]
 68%|██████▊   | 251552/371472 [8:58:10<9:32:10,  3.49it/s]
 68%|██████▊   | 251553/371472 [8:58:10<9:17:15,  3.59it/s]
 68%|██████▊   | 251554/371472 [8:58:10<8:58:47,  3.71it/s]
 68%|██████▊   | 251555/371472 [8:58:10<8:48:13,  3.78it/s]
 68%|██████▊   | 251556/371472 [8:58:11<9:05:21,  3.66it/s]
 68%|██████▊   | 251557/371472 [8:58:11<9:05:27,  3.66it/s]
 68%|██████▊   | 251558/371472 [8:58:11<8:54:27,  3.74it/s]
 68%|██████▊   | 251559/371472 [8:58:12<8:59:30,  3.70it/s]
 68%|██████▊   | 251560/371472 [8:58:12<8:58:35,  3.71it/s]
                                                           
{'loss': 3.0219, 'learning_rate': 3.90678532181258e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251560/371472 [8:58:12<8:58:35,  3.71it/s]
 68%|██████▊   | 251561/371472 [8:58:12<9:33:55,  3.48it/s]
 68%|██████▊   | 251562/371472 [8:58:12<9:23:30,  3.55it/s]
 68%|██████▊   | 251563/371472 [8:58:13<9:16:08,  3.59it/s]
 68%|██████▊   | 251564/371472 [8:58:13<9:18:21,  3.58it/s]
 68%|██████▊   | 251565/371472 [8:58:13<9:14:46,  3.60it/s]
 68%|██████▊   | 251566/371472 [8:58:13<9:11:34,  3.62it/s]
 68%|██████▊   | 251567/371472 [8:58:14<9:04:33,  3.67it/s]
 68%|██████▊   | 251568/371472 [8:58:14<8:51:31,  3.76it/s]
 68%|██████▊   | 251569/371472 [8:58:14<8:44:34,  3.81it/s]
 68%|██████▊   | 251570/371472 [8:58:15<8:36:31,  3.87it/s]
 68%|██████▊   | 251571/371472 [8:58:15<8:46:46,  3.79it/s]
 68%|██████▊   | 251572/371472 [8:58:15<8:50:18,  3.77it/s]
 68%|██████▊   | 251573/371472 [8:58:15<8:58:05,  3.71it/s]
 68%|██████▊   | 251574/371472 [8:58:16<9:02:36,  3.68it/s]
 68%|██████▊   | 251575/371472 [8:58:16<9:28:51,  3.51it/s]
 68%|██████▊   | 251576/371472 [8:58:16<9:12:44,  3.62it/s]
 68%|██████▊   | 251577/371472 [8:58:16<9:06:47,  3.65it/s]
 68%|██████▊   | 251578/371472 [8:58:17<8:58:38,  3.71it/s]
 68%|██████▊   | 251579/371472 [8:58:17<8:59:15,  3.71it/s]
 68%|██████▊   | 251580/371472 [8:58:17<9:15:26,  3.60it/s]
                                                           
{'loss': 2.7446, 'learning_rate': 3.90630050205779e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251580/371472 [8:58:17<9:15:26,  3.60it/s]
 68%|██████▊   | 251581/371472 [8:58:18<9:14:47,  3.60it/s]
 68%|██████▊   | 251582/371472 [8:58:18<9:10:06,  3.63it/s]
 68%|██████▊   | 251583/371472 [8:58:18<9:31:46,  3.49it/s]
 68%|██████▊   | 251584/371472 [8:58:18<9:37:40,  3.46it/s]
 68%|██████▊   | 251585/371472 [8:58:19<10:32:48,  3.16it/s]
 68%|██████▊   | 251586/371472 [8:58:19<9:56:41,  3.35it/s] 
 68%|██████▊   | 251587/371472 [8:58:19<10:10:32,  3.27it/s]
 68%|██████▊   | 251588/371472 [8:58:20<10:42:19,  3.11it/s]
 68%|██████▊   | 251589/371472 [8:58:20<10:13:28,  3.26it/s]
 68%|██████▊   | 251590/371472 [8:58:20<9:51:11,  3.38it/s] 
 68%|██████▊   | 251591/371472 [8:58:21<9:34:49,  3.48it/s]
 68%|██████▊   | 251592/371472 [8:58:21<9:27:04,  3.52it/s]
 68%|██████▊   | 251593/371472 [8:58:21<9:26:52,  3.52it/s]
 68%|██████▊   | 251594/371472 [8:58:21<9:20:28,  3.56it/s]
 68%|██████▊   | 251595/371472 [8:58:22<9:22:02,  3.55it/s]
 68%|██████▊   | 251596/371472 [8:58:22<9:23:53,  3.54it/s]
 68%|██████▊   | 251597/371472 [8:58:22<9:46:44,  3.41it/s]
 68%|██████▊   | 251598/371472 [8:58:23<9:27:35,  3.52it/s]
 68%|██████▊   | 251599/371472 [8:58:23<9:16:10,  3.59it/s]
 68%|██████▊   | 251600/371472 [8:58:23<9:19:44,  3.57it/s]
                                                           
{'loss': 2.8841, 'learning_rate': 3.905815682303002e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251600/371472 [8:58:23<9:19:44,  3.57it/s]
 68%|██████▊   | 251601/371472 [8:58:23<9:03:00,  3.68it/s]
 68%|██████▊   | 251602/371472 [8:58:24<9:15:00,  3.60it/s]
 68%|██████▊   | 251603/371472 [8:58:24<9:00:30,  3.70it/s]
 68%|██████▊   | 251604/371472 [8:58:24<9:38:56,  3.45it/s]
 68%|██████▊   | 251605/371472 [8:58:24<9:19:35,  3.57it/s]
 68%|██████▊   | 251606/371472 [8:58:25<9:15:49,  3.59it/s]
 68%|██████▊   | 251607/371472 [8:58:25<9:27:08,  3.52it/s]
 68%|██████▊   | 251608/371472 [8:58:25<8:59:42,  3.70it/s]
 68%|██████▊   | 251609/371472 [8:58:26<8:41:53,  3.83it/s]
 68%|██████▊   | 251610/371472 [8:58:26<8:58:48,  3.71it/s]
 68%|██████▊   | 251611/371472 [8:58:26<8:55:32,  3.73it/s]
 68%|██████▊   | 251612/371472 [8:58:26<9:11:34,  3.62it/s]
 68%|██████▊   | 251613/371472 [8:58:27<10:11:17,  3.27it/s]
 68%|██████▊   | 251614/371472 [8:58:27<9:30:08,  3.50it/s] 
 68%|██████▊   | 251615/371472 [8:58:27<9:27:27,  3.52it/s]
 68%|██████▊   | 251616/371472 [8:58:28<9:27:11,  3.52it/s]
 68%|██████▊   | 251617/371472 [8:58:28<9:04:22,  3.67it/s]
 68%|██████▊   | 251618/371472 [8:58:28<9:13:31,  3.61it/s]
 68%|██████▊   | 251619/371472 [8:58:28<9:16:50,  3.59it/s]
 68%|██████▊   | 251620/371472 [8:58:29<9:31:55,  3.49it/s]
                                                           
{'loss': 2.8729, 'learning_rate': 3.9053308625482125e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251620/371472 [8:58:29<9:31:55,  3.49it/s]
 68%|██████▊   | 251621/371472 [8:58:29<9:00:30,  3.70it/s]
 68%|██████▊   | 251622/371472 [8:58:29<9:43:26,  3.42it/s]
 68%|██████▊   | 251623/371472 [8:58:30<9:22:16,  3.55it/s]
 68%|██████▊   | 251624/371472 [8:58:30<8:59:33,  3.70it/s]
 68%|██████▊   | 251625/371472 [8:58:30<9:16:09,  3.59it/s]
 68%|██████▊   | 251626/371472 [8:58:30<9:03:46,  3.67it/s]
 68%|██████▊   | 251627/371472 [8:58:31<8:53:22,  3.74it/s]
 68%|██████▊   | 251628/371472 [8:58:31<8:41:01,  3.83it/s]
 68%|██████▊   | 251629/371472 [8:58:31<8:46:14,  3.80it/s]
 68%|██████▊   | 251630/371472 [8:58:31<8:24:09,  3.96it/s]
 68%|██████▊   | 251631/371472 [8:58:32<8:36:53,  3.86it/s]
 68%|██████▊   | 251632/371472 [8:58:32<8:49:16,  3.77it/s]
 68%|██████▊   | 251633/371472 [8:58:32<9:10:22,  3.63it/s]
 68%|██████▊   | 251634/371472 [8:58:32<9:13:31,  3.61it/s]
 68%|██████▊   | 251635/371472 [8:58:33<9:11:42,  3.62it/s]
 68%|██████▊   | 251636/371472 [8:58:33<9:00:23,  3.70it/s]
 68%|██████▊   | 251637/371472 [8:58:33<8:48:26,  3.78it/s]
 68%|██████▊   | 251638/371472 [8:58:34<9:17:16,  3.58it/s]
 68%|██████▊   | 251639/371472 [8:58:34<9:05:09,  3.66it/s]
 68%|██████▊   | 251640/371472 [8:58:34<8:56:53,  3.72it/s]
                                                           
{'loss': 2.7769, 'learning_rate': 3.9048460427934237e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251640/371472 [8:58:34<8:56:53,  3.72it/s]
 68%|██████▊   | 251641/371472 [8:58:34<9:23:32,  3.54it/s]
 68%|██████▊   | 251642/371472 [8:58:35<9:12:24,  3.62it/s]
 68%|██████▊   | 251643/371472 [8:58:35<9:04:37,  3.67it/s]
 68%|██████▊   | 251644/371472 [8:58:35<9:34:05,  3.48it/s]
 68%|██████▊   | 251645/371472 [8:58:36<9:59:15,  3.33it/s]
 68%|██████▊   | 251646/371472 [8:58:36<9:41:53,  3.43it/s]
 68%|██████▊   | 251647/371472 [8:58:36<9:16:30,  3.59it/s]
 68%|██████▊   | 251648/371472 [8:58:36<9:00:22,  3.70it/s]
 68%|██████▊   | 251649/371472 [8:58:37<9:00:22,  3.70it/s]
 68%|█████���▊   | 251650/371472 [8:58:37<9:09:13,  3.64it/s]
 68%|██████▊   | 251651/371472 [8:58:37<8:56:37,  3.72it/s]
 68%|██████▊   | 251652/371472 [8:58:37<8:56:58,  3.72it/s]
 68%|██████▊   | 251653/371472 [8:58:38<9:12:26,  3.61it/s]
 68%|██████▊   | 251654/371472 [8:58:38<9:06:46,  3.65it/s]
 68%|██████▊   | 251655/371472 [8:58:38<9:14:00,  3.60it/s]
 68%|██████▊   | 251656/371472 [8:58:38<8:55:08,  3.73it/s]
 68%|██████▊   | 251657/371472 [8:58:39<9:28:01,  3.52it/s]
 68%|██████▊   | 251658/371472 [8:58:39<9:16:06,  3.59it/s]
 68%|██████▊   | 251659/371472 [8:58:39<9:31:15,  3.50it/s]
 68%|██████▊   | 251660/371472 [8:58:40<9:09:43,  3.63it/s]
                                                           
{'loss': 2.9334, 'learning_rate': 3.9043612230386344e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251660/371472 [8:58:40<9:09:43,  3.63it/s]
 68%|██████▊   | 251661/371472 [8:58:40<8:55:22,  3.73it/s]
 68%|██████▊   | 251662/371472 [8:58:40<9:19:35,  3.57it/s]
 68%|██████▊   | 251663/371472 [8:58:40<9:02:42,  3.68it/s]
 68%|██████▊   | 251664/371472 [8:58:41<8:44:23,  3.81it/s]
 68%|██████▊   | 251665/371472 [8:58:41<8:39:14,  3.85it/s]
 68%|██████▊   | 251666/371472 [8:58:41<8:47:19,  3.79it/s]
 68%|██████▊   | 251667/371472 [8:58:41<8:49:59,  3.77it/s]
 68%|██████▊   | 251668/371472 [8:58:42<8:48:30,  3.78it/s]
 68%|██████▊   | 251669/371472 [8:58:42<9:03:33,  3.67it/s]
 68%|██████▊   | 251670/371472 [8:58:42<9:08:37,  3.64it/s]
 68%|██████▊   | 251671/371472 [8:58:43<8:45:27,  3.80it/s]
 68%|██████▊   | 251672/371472 [8:58:43<9:35:54,  3.47it/s]
 68%|██████▊   | 251673/371472 [8:58:43<9:25:55,  3.53it/s]
 68%|██████▊   | 251674/371472 [8:58:43<9:09:14,  3.64it/s]
 68%|██████▊   | 251675/371472 [8:58:44<9:00:07,  3.70it/s]
 68%|██████▊   | 251676/371472 [8:58:44<10:02:32,  3.31it/s]
 68%|██████▊   | 251677/371472 [8:58:44<9:47:14,  3.40it/s] 
 68%|██████▊   | 251678/371472 [8:58:45<9:54:05,  3.36it/s]
 68%|██████▊   | 251679/371472 [8:58:45<9:55:39,  3.35it/s]
 68%|██████▊   | 251680/371472 [8:58:45<9:22:03,  3.55it/s]
                                                           
{'loss': 2.9346, 'learning_rate': 3.903876403283846e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251680/371472 [8:58:45<9:22:03,  3.55it/s]
 68%|██████▊   | 251681/371472 [8:58:45<9:16:35,  3.59it/s]
 68%|██████▊   | 251682/371472 [8:58:46<9:13:08,  3.61it/s]
 68%|██████▊   | 251683/371472 [8:58:46<9:42:38,  3.43it/s]
 68%|██████▊   | 251684/371472 [8:58:46<9:36:29,  3.46it/s]
 68%|██████▊   | 251685/371472 [8:58:47<9:22:24,  3.55it/s]
 68%|██████▊   | 251686/371472 [8:58:47<9:27:34,  3.52it/s]
 68%|██████▊   | 251687/371472 [8:58:47<9:31:43,  3.49it/s]
 68%|██████▊   | 251688/371472 [8:58:47<9:25:27,  3.53it/s]
 68%|██████▊   | 251689/371472 [8:58:48<9:03:51,  3.67it/s]
 68%|██████▊   | 251690/371472 [8:58:48<9:35:20,  3.47it/s]
 68%|██████▊   | 251691/371472 [8:58:48<9:12:12,  3.62it/s]
 68%|██████▊   | 251692/371472 [8:58:49<9:18:13,  3.58it/s]
 68%|██████▊   | 251693/371472 [8:58:49<9:23:36,  3.54it/s]
 68%|██████▊   | 251694/371472 [8:58:49<9:21:27,  3.56it/s]
 68%|██████▊   | 251695/371472 [8:58:49<9:14:02,  3.60it/s]
 68%|██████▊   | 251696/371472 [8:58:50<8:54:12,  3.74it/s]
 68%|██████▊   | 251697/371472 [8:58:50<8:48:00,  3.78it/s]
 68%|██████▊   | 251698/371472 [8:58:50<9:39:10,  3.45it/s]
 68%|██████▊   | 251699/371472 [8:58:51<9:40:35,  3.44it/s]
 68%|██████▊   | 251700/371472 [8:58:51<9:22:49,  3.55it/s]
                                                           
{'loss': 2.9054, 'learning_rate': 3.9033915835290564e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251700/371472 [8:58:51<9:22:49,  3.55it/s]
 68%|██████▊   | 251701/371472 [8:58:51<9:04:42,  3.66it/s]
 68%|██████▊   | 251702/371472 [8:58:51<8:54:48,  3.73it/s]
 68%|██████▊   | 251703/371472 [8:58:52<9:13:37,  3.61it/s]
 68%|██████▊   | 251704/371472 [8:58:52<9:31:36,  3.49it/s]
 68%|██████▊   | 251705/371472 [8:58:52<9:32:51,  3.48it/s]
 68%|██████▊   | 251706/371472 [8:58:53<10:36:00,  3.14it/s]
 68%|██████▊   | 251707/371472 [8:58:53<10:07:12,  3.29it/s]
 68%|██████▊   | 251708/371472 [8:58:53<10:52:29,  3.06it/s]
 68%|██████▊   | 251709/371472 [8:58:54<10:15:13,  3.24it/s]
 68%|██████▊   | 251710/371472 [8:58:54<10:27:21,  3.18it/s]
 68%|██████▊   | 251711/371472 [8:58:54<9:53:10,  3.37it/s] 
 68%|██████▊   | 251712/371472 [8:58:54<9:21:09,  3.56it/s]
 68%|██████▊   | 251713/371472 [8:58:55<9:09:55,  3.63it/s]
 68%|██████▊   | 251714/371472 [8:58:55<9:06:16,  3.65it/s]
 68%|██████▊   | 251715/371472 [8:58:55<9:09:20,  3.63it/s]
 68%|██████▊   | 251716/371472 [8:58:55<8:58:40,  3.71it/s]
 68%|██████▊   | 251717/371472 [8:58:56<8:47:21,  3.78it/s]
 68%|██████▊   | 251718/371472 [8:58:56<8:40:34,  3.83it/s]
 68%|██████▊   | 251719/371472 [8:58:56<8:52:56,  3.75it/s]
 68%|██████▊   | 251720/371472 [8:58:56<9:01:55,  3.68it/s]
                                                           
{'loss': 2.8851, 'learning_rate': 3.902906763774268e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251720/371472 [8:58:56<9:01:55,  3.68it/s]
 68%|██████▊   | 251721/371472 [8:58:57<9:00:35,  3.69it/s]
 68%|██████▊   | 251722/371472 [8:58:57<8:41:58,  3.82it/s]
 68%|██████▊   | 251723/371472 [8:58:57<8:23:22,  3.96it/s]
 68%|██████▊   | 251724/371472 [8:58:57<8:33:32,  3.89it/s]
 68%|██████▊   | 251725/371472 [8:58:58<8:35:00,  3.88it/s]
 68%|██████▊   | 251726/371472 [8:58:58<8:56:38,  3.72it/s]
 68%|██████▊   | 251727/371472 [8:58:58<9:24:46,  3.53it/s]
 68%|██████▊   | 251728/371472 [8:58:59<9:47:16,  3.40it/s]
 68%|██████▊   | 251729/371472 [8:58:59<9:25:56,  3.53it/s]
 68%|██████▊   | 251730/371472 [8:58:59<9:07:54,  3.64it/s]
 68%|██████▊   | 251731/371472 [8:58:59<8:47:44,  3.78it/s]
 68%|██████▊   | 251732/371472 [8:59:00<9:06:14,  3.65it/s]
 68%|██████▊   | 251733/371472 [8:59:00<8:59:00,  3.70it/s]
 68%|██████▊   | 251734/371472 [8:59:00<9:02:18,  3.68it/s]
 68%|██████▊   | 251735/371472 [8:59:01<8:47:14,  3.79it/s]
 68%|██████▊   | 251736/371472 [8:59:01<8:45:38,  3.80it/s]
 68%|██████▊   | 251737/371472 [8:59:01<9:04:00,  3.67it/s]
 68%|██████▊   | 251738/371472 [8:59:01<10:10:38,  3.27it/s]
 68%|██████▊   | 251739/371472 [8:59:02<9:46:31,  3.40it/s] 
 68%|██████▊   | 251740/371472 [8:59:02<9:49:11,  3.39it/s]
                                                           
{'loss': 2.9972, 'learning_rate': 3.902421944019479e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251740/371472 [8:59:02<9:49:11,  3.39it/s]
 68%|██████▊   | 251741/371472 [8:59:02<9:20:25,  3.56it/s]
 68%|██████▊   | 251742/371472 [8:59:03<9:08:36,  3.64it/s]
 68%|██████▊   | 251743/371472 [8:59:03<9:07:44,  3.64it/s]
 68%|██████▊   | 251744/371472 [8:59:03<9:32:19,  3.49it/s]
 68%|██████▊   | 251745/371472 [8:59:03<9:59:57,  3.33it/s]
 68%|██████▊   | 251746/371472 [8:59:04<9:58:52,  3.33it/s]
 68%|██████▊   | 251747/371472 [8:59:04<9:38:15,  3.45it/s]
 68%|██████▊   | 251748/371472 [8:59:04<9:28:32,  3.51it/s]
 68%|██████▊   | 251749/371472 [8:59:05<9:16:01,  3.59it/s]
 68%|██████▊   | 251750/371472 [8:59:05<9:28:05,  3.51it/s]
 68%|██████▊   | 251751/371472 [8:59:05<9:26:33,  3.52it/s]
 68%|██████▊   | 251752/371472 [8:59:05<9:28:52,  3.51it/s]
 68%|██████▊   | 251753/371472 [8:59:06<9:40:54,  3.43it/s]
 68%|██████▊   | 251754/371472 [8:59:06<9:13:24,  3.61it/s]
 68%|██████▊   | 251755/371472 [8:59:06<9:17:51,  3.58it/s]
 68%|██████▊   | 251756/371472 [8:59:07<9:00:20,  3.69it/s]
 68%|██████▊   | 251757/371472 [8:59:07<9:34:25,  3.47it/s]
 68%|██████▊   | 251758/371472 [8:59:07<9:01:17,  3.69it/s]
 68%|██████▊   | 251759/371472 [8:59:07<9:04:45,  3.66it/s]
 68%|██████▊   | 251760/371472 [8:59:08<9:00:34,  3.69it/s]
                                                           
{'loss': 2.9633, 'learning_rate': 3.90193712426469e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251760/371472 [8:59:08<9:00:34,  3.69it/s]
 68%|██████▊   | 251761/371472 [8:59:08<9:20:23,  3.56it/s]
 68%|██████▊   | 251762/371472 [8:59:08<9:31:48,  3.49it/s]
 68%|██████▊   | 251763/371472 [8:59:08<9:00:46,  3.69it/s]
 68%|██████▊   | 251764/371472 [8:59:09<9:00:51,  3.69it/s]
 68%|██████▊   | 251765/371472 [8:59:09<8:55:58,  3.72it/s]
 68%|██████▊   | 251766/371472 [8:59:09<8:51:00,  3.76it/s]
 68%|██████▊   | 251767/371472 [8:59:10<9:09:59,  3.63it/s]
 68%|██████▊   | 251768/371472 [8:59:10<8:57:02,  3.71it/s]
 68%|██████▊   | 251769/371472 [8:59:10<9:43:11,  3.42it/s]
 68%|██████▊   | 251770/371472 [8:59:10<9:42:45,  3.42it/s]
 68%|██████▊   | 251771/371472 [8:59:11<9:14:23,  3.60it/s]
 68%|██████▊   | 251772/371472 [8:59:11<9:14:52,  3.60it/s]
 68%|██████▊   | 251773/371472 [8:59:11<9:56:07,  3.35it/s]
 68%|██████▊   | 251774/371472 [8:59:12<9:35:50,  3.46it/s]
 68%|██████▊   | 251775/371472 [8:59:12<9:27:20,  3.52it/s]
 68%|██████▊   | 251776/371472 [8:59:12<9:13:07,  3.61it/s]
 68%|██████▊   | 251777/371472 [8:59:12<9:06:30,  3.65it/s]
 68%|██████▊   | 251778/371472 [8:59:13<9:24:30,  3.53it/s]
 68%|██████▊   | 251779/371472 [8:59:13<9:25:57,  3.52it/s]
 68%|██████▊   | 251780/371472 [8:59:13<9:03:39,  3.67it/s]
                                                           
{'loss': 2.8134, 'learning_rate': 3.901452304509901e-07, 'epoch': 10.84}
+
 68%|██████▊   | 251780/371472 [8:59:13<9:03:39,  3.67it/s]
 68%|██████▊   | 251781/371472 [8:59:13<9:08:36,  3.64it/s]
 68%|██████▊   | 251782/371472 [8:59:14<9:08:09,  3.64it/s]
 68%|██████▊   | 251783/371472 [8:59:14<10:08:21,  3.28it/s]
 68%|██████▊   | 251784/371472 [8:59:14<9:55:18,  3.35it/s] 
 68%|██████▊   | 251785/371472 [8:59:15<9:22:34,  3.55it/s]
 68%|██████▊   | 251786/371472 [8:59:15<9:45:53,  3.40it/s]
 68%|██████▊   | 251787/371472 [8:59:15<10:05:14,  3.30it/s]
 68%|██████▊   | 251788/371472 [8:59:16<9:38:49,  3.45it/s] 
 68%|██████▊   | 251789/371472 [8:59:16<9:59:20,  3.33it/s]
 68%|██████▊   | 251790/371472 [8:59:16<10:04:49,  3.30it/s]
 68%|██████▊   | 251791/371472 [8:59:16<9:41:37,  3.43it/s] 
 68%|██████▊   | 251792/371472 [8:59:17<9:23:55,  3.54it/s]
 68%|██████▊   | 251793/371472 [8:59:17<8:58:01,  3.71it/s]
 68%|██████▊   | 251794/371472 [8:59:17<8:53:24,  3.74it/s]
 68%|██████▊   | 251795/371472 [8:59:18<8:59:33,  3.70it/s]
 68%|██████▊   | 251796/371472 [8:59:18<9:16:40,  3.58it/s]
 68%|██████▊   | 251797/371472 [8:59:18<9:19:08,  3.57it/s]
 68%|██████▊   | 251798/371472 [8:59:18<9:09:24,  3.63it/s]
 68%|██████▊   | 251799/371472 [8:59:19<9:24:43,  3.53it/s]
 68%|██████▊   | 251800/371472 [8:59:19<9:01:15,  3.68it/s]
                                                           
{'loss': 2.8373, 'learning_rate': 3.9009674847551116e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251800/371472 [8:59:19<9:01:15,  3.68it/s]
 68%|██████▊   | 251801/371472 [8:59:19<9:17:06,  3.58it/s]
 68%|██████▊   | 251802/371472 [8:59:19<8:58:29,  3.70it/s]
 68%|██████▊   | 251803/371472 [8:59:20<8:46:39,  3.79it/s]
 68%|██████▊   | 251804/371472 [8:59:20<8:44:00,  3.81it/s]
 68%|██████▊   | 251805/371472 [8:59:20<9:08:25,  3.64it/s]
 68%|██████▊   | 251806/371472 [8:59:21<8:52:33,  3.75it/s]
 68%|██████▊   | 251807/371472 [8:59:21<8:51:20,  3.75it/s]
 68%|██████▊   | 251808/371472 [8:59:21<9:55:58,  3.35it/s]
 68%|██████▊   | 251809/371472 [8:59:21<9:27:10,  3.52it/s]
 68%|██████▊   | 251810/371472 [8:59:22<9:10:03,  3.63it/s]
 68%|██████▊   | 251811/371472 [8:59:22<8:53:59,  3.73it/s]
 68%|██████▊   | 251812/371472 [8:59:22<8:43:51,  3.81it/s]
 68%|██████▊   | 251813/371472 [8:59:22<8:46:04,  3.79it/s]
 68%|██████▊   | 251814/371472 [8:59:23<8:54:15,  3.73it/s]
 68%|██████▊   | 251815/371472 [8:59:23<8:29:18,  3.92it/s]
 68%|██████▊   | 251816/371472 [8:59:23<8:45:08,  3.80it/s]
 68%|██████▊   | 251817/371472 [8:59:23<8:29:46,  3.91it/s]
 68%|██████▊   | 251818/371472 [8:59:24<8:47:19,  3.78it/s]
 68%|██████▊   | 251819/371472 [8:59:24<9:53:18,  3.36it/s]
 68%|██████▊   | 251820/371472 [8:59:24<9:53:13,  3.36it/s]
                                                           
{'loss': 3.1026, 'learning_rate': 3.9004826650003233e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251820/371472 [8:59:24<9:53:13,  3.36it/s]
 68%|██████▊   | 251821/371472 [8:59:25<10:17:34,  3.23it/s]
 68%|██████▊   | 251822/371472 [8:59:25<10:10:18,  3.27it/s]
 68%|██████▊   | 251823/371472 [8:59:25<9:40:27,  3.44it/s] 
 68%|██████▊   | 251824/371472 [8:59:26<10:43:23,  3.10it/s]
 68%|██████▊   | 251825/371472 [8:59:26<10:20:20,  3.21it/s]
 68%|██████▊   | 251826/371472 [8:59:26<10:20:51,  3.21it/s]
 68%|██████▊   | 251827/371472 [8:59:27<9:55:34,  3.35it/s] 
 68%|██████▊   | 251828/371472 [8:59:27<9:29:22,  3.50it/s]
 68%|██████▊   | 251829/371472 [8:59:27<9:16:58,  3.58it/s]
 68%|██████▊   | 251830/371472 [8:59:27<9:33:39,  3.48it/s]
 68%|██████▊   | 251831/371472 [8:59:28<9:46:10,  3.40it/s]
 68%|���█████▊   | 251832/371472 [8:59:28<9:19:45,  3.56it/s]
 68%|██████▊   | 251833/371472 [8:59:28<9:13:03,  3.61it/s]
 68%|██████▊   | 251834/371472 [8:59:28<9:01:02,  3.69it/s]
 68%|██████▊   | 251835/371472 [8:59:29<8:47:32,  3.78it/s]
 68%|██████▊   | 251836/371472 [8:59:29<9:00:39,  3.69it/s]
 68%|██████▊   | 251837/371472 [8:59:29<8:33:00,  3.89it/s]
 68%|██████▊   | 251838/371472 [8:59:30<9:31:55,  3.49it/s]
 68%|██████▊   | 251839/371472 [8:59:30<9:06:01,  3.65it/s]
 68%|██████▊   | 251840/371472 [8:59:30<8:54:48,  3.73it/s]
                                                           
{'loss': 2.8209, 'learning_rate': 3.8999978452455335e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251840/371472 [8:59:30<8:54:48,  3.73it/s]
 68%|██████▊   | 251841/371472 [8:59:30<9:26:03,  3.52it/s]
 68%|██████▊   | 251842/371472 [8:59:31<9:09:25,  3.63it/s]
 68%|██████▊   | 251843/371472 [8:59:31<9:26:30,  3.52it/s]
 68%|██████▊   | 251844/371472 [8:59:31<9:03:55,  3.67it/s]
 68%|██████▊   | 251845/371472 [8:59:31<8:44:05,  3.80it/s]
 68%|██████▊   | 251846/371472 [8:59:32<8:53:15,  3.74it/s]
 68%|██████▊   | 251847/371472 [8:59:32<8:54:04,  3.73it/s]
 68%|██████▊   | 251848/371472 [8:59:32<8:57:26,  3.71it/s]
 68%|██████▊   | 251849/371472 [8:59:33<9:05:16,  3.66it/s]
 68%|██████▊   | 251850/371472 [8:59:33<9:02:17,  3.68it/s]
 68%|██████▊   | 251851/371472 [8:59:33<8:48:39,  3.77it/s]
 68%|██████▊   | 251852/371472 [8:59:33<8:49:28,  3.77it/s]
 68%|██████▊   | 251853/371472 [8:59:34<9:19:33,  3.56it/s]
 68%|██████▊   | 251854/371472 [8:59:34<9:35:27,  3.46it/s]
 68%|██████▊   | 251855/371472 [8:59:34<9:24:48,  3.53it/s]
 68%|██████▊   | 251856/371472 [8:59:35<9:37:23,  3.45it/s]
 68%|██████▊   | 251857/371472 [8:59:35<9:15:45,  3.59it/s]
 68%|██████▊   | 251858/371472 [8:59:35<9:15:32,  3.59it/s]
 68%|██████▊   | 251859/371472 [8:59:35<9:19:54,  3.56it/s]
 68%|██████▊   | 251860/371472 [8:59:36<8:58:07,  3.70it/s]
                                                           
{'loss': 2.837, 'learning_rate': 3.8995130254907453e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251860/371472 [8:59:36<8:58:07,  3.70it/s]
 68%|██████▊   | 251861/371472 [8:59:36<8:54:58,  3.73it/s]
 68%|██████▊   | 251862/371472 [8:59:36<8:59:54,  3.69it/s]
 68%|██████▊   | 251863/371472 [8:59:36<8:45:52,  3.79it/s]
 68%|██████▊   | 251864/371472 [8:59:37<8:48:13,  3.77it/s]
 68%|██████▊   | 251865/371472 [8:59:37<8:48:08,  3.77it/s]
 68%|██████▊   | 251866/371472 [8:59:37<9:07:58,  3.64it/s]
 68%|██████▊   | 251867/371472 [8:59:38<10:04:04,  3.30it/s]
 68%|██████▊   | 251868/371472 [8:59:38<9:37:08,  3.45it/s] 
 68%|██████▊   | 251869/371472 [8:59:38<9:13:45,  3.60it/s]
 68%|██████▊   | 251870/371472 [8:59:38<9:10:01,  3.62it/s]
 68%|██████▊   | 251871/371472 [8:59:39<9:13:11,  3.60it/s]
 68%|██████▊   | 251872/371472 [8:59:39<9:12:26,  3.61it/s]
 68%|██████▊   | 251873/371472 [8:59:39<9:21:42,  3.55it/s]
 68%|██████▊   | 251874/371472 [8:59:39<9:01:12,  3.68it/s]
 68%|██████▊   | 251875/371472 [8:59:40<9:07:00,  3.64it/s]
 68%|██████▊   | 251876/371472 [8:59:40<9:13:47,  3.60it/s]
 68%|██████▊   | 251877/371472 [8:59:40<9:20:20,  3.56it/s]
 68%|██████▊   | 251878/371472 [8:59:41<8:54:47,  3.73it/s]
 68%|██████▊   | 251879/371472 [8:59:41<9:04:58,  3.66it/s]
 68%|██████▊   | 251880/371472 [8:59:41<9:21:05,  3.55it/s]
                                                           
{'loss': 2.7915, 'learning_rate': 3.899028205735956e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251880/371472 [8:59:41<9:21:05,  3.55it/s]
 68%|██████▊   | 251881/371472 [8:59:41<9:08:35,  3.63it/s]
 68%|██████▊   | 251882/371472 [8:59:42<8:54:28,  3.73it/s]
 68%|██████▊   | 251883/371472 [8:59:42<8:51:57,  3.75it/s]
 68%|██████▊   | 251884/371472 [8:59:42<9:56:16,  3.34it/s]
 68%|██████▊   | 251885/371472 [8:59:43<9:47:15,  3.39it/s]
 68%|██████▊   | 251886/371472 [8:59:43<9:54:31,  3.35it/s]
 68%|██████▊   | 251887/371472 [8:59:43<9:38:34,  3.44it/s]
 68%|██████▊   | 251888/371472 [8:59:43<9:56:48,  3.34it/s]
 68%|██████▊   | 251889/371472 [8:59:44<9:46:22,  3.40it/s]
 68%|██████▊   | 251890/371472 [8:59:44<10:02:53,  3.31it/s]
 68%|██████▊   | 251891/371472 [8:59:44<9:53:19,  3.36it/s] 
 68%|██████▊   | 251892/371472 [8:59:45<9:22:48,  3.54it/s]
 68%|██████▊   | 251893/371472 [8:59:45<9:11:22,  3.61it/s]
 68%|██████▊   | 251894/371472 [8:59:45<9:31:50,  3.49it/s]
 68%|██████▊   | 251895/371472 [8:59:45<9:28:46,  3.50it/s]
 68%|██████▊   | 251896/371472 [8:59:46<9:19:29,  3.56it/s]
 68%|██████▊   | 251897/371472 [8:59:46<8:58:27,  3.70it/s]
 68%|██████▊   | 251898/371472 [8:59:46<9:31:16,  3.49it/s]
 68%|██████▊   | 251899/371472 [8:59:47<9:18:27,  3.57it/s]
 68%|██████▊   | 251900/371472 [8:59:47<13:06:50,  2.53it/s]
                                                            
{'loss': 2.8663, 'learning_rate': 3.898543385981167e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251900/371472 [8:59:47<13:06:50,  2.53it/s]
 68%|██████▊   | 251901/371472 [8:59:47<11:42:41,  2.84it/s]
 68%|██████▊   | 251902/371472 [8:59:48<11:09:48,  2.98it/s]
 68%|██████▊   | 251903/371472 [8:59:48<11:02:35,  3.01it/s]
 68%|██████▊   | 251904/371472 [8:59:48<10:29:49,  3.16it/s]
 68%|██████▊   | 251905/371472 [8:59:49<10:39:40,  3.12it/s]
 68%|██████▊   | 251906/371472 [8:59:49<10:09:46,  3.27it/s]
 68%|██████▊   | 251907/371472 [8:59:49<9:53:35,  3.36it/s] 
 68%|██████▊   | 251908/371472 [8:59:50<9:23:38,  3.54it/s]
 68%|██████▊   | 251909/371472 [8:59:50<9:01:13,  3.68it/s]
 68%|██████▊   | 251910/371472 [8:59:50<10:06:38,  3.28it/s]
 68%|██████▊   | 251911/371472 [8:59:50<9:53:11,  3.36it/s] 
 68%|██████▊   | 251912/371472 [8:59:51<9:57:59,  3.33it/s]
 68%|██████▊   | 251913/371472 [8:59:51<9:45:34,  3.40it/s]
 68%|██████▊   | 251914/371472 [8:59:51<9:38:29,  3.44it/s]
 68%|██████▊   | 251915/371472 [8:59:52<9:40:45,  3.43it/s]
 68%|██████▊   | 251916/371472 [8:59:52<9:11:43,  3.61it/s]
 68%|██████▊   | 251917/371472 [8:59:52<9:00:18,  3.69it/s]
 68%|██████▊   | 251918/371472 [8:59:52<8:43:26,  3.81it/s]
 68%|██████▊   | 251919/371472 [8:59:53<8:44:23,  3.80it/s]
 68%|██████▊   | 251920/371472 [8:59:53<8:33:00,  3.88it/s]
                                                           
{'loss': 2.8782, 'learning_rate': 3.898058566226378e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251920/371472 [8:59:53<8:33:00,  3.88it/s]
 68%|██████▊   | 251921/371472 [8:59:53<8:34:08,  3.88it/s]
 68%|██████▊   | 251922/371472 [8:59:53<9:13:04,  3.60it/s]
 68%|██████▊   | 251923/371472 [8:59:54<9:09:31,  3.63it/s]
 68%|██████▊   | 251924/371472 [8:59:54<9:00:14,  3.69it/s]
 68%|██████▊   | 251925/371472 [8:59:54<8:56:03,  3.72it/s]
 68%|██████▊   | 251926/371472 [8:59:54<8:45:32,  3.79it/s]
 68%|██████▊   | 251927/371472 [8:59:55<8:50:56,  3.75it/s]
 68%|██████▊   | 251928/371472 [8:59:55<9:05:32,  3.65it/s]
 68%|██████▊   | 251929/371472 [8:59:55<8:59:47,  3.69it/s]
 68%|██████▊   | 251930/371472 [8:59:56<8:53:30,  3.73it/s]
 68%|██████▊   | 251931/371472 [8:59:56<9:06:27,  3.65it/s]
 68%|██████▊   | 251932/371472 [8:59:56<9:07:06,  3.64it/s]
 68%|██████▊   | 251933/371472 [8:59:56<8:51:31,  3.75it/s]
 68%|██████▊   | 251934/371472 [8:59:57<9:05:45,  3.65it/s]
 68%|██████▊   | 251935/371472 [8:59:57<9:02:50,  3.67it/s]
 68%|██████▊   | 251936/371472 [8:59:57<9:25:45,  3.52it/s]
 68%|██████▊   | 251937/371472 [8:59:57<8:59:47,  3.69it/s]
 68%|██████▊   | 251938/371472 [8:59:58<9:39:07,  3.44it/s]
 68%|██████▊   | 251939/371472 [8:59:58<10:35:38,  3.13it/s]
 68%|██████▊   | 251940/371472 [8:59:58<9:51:33,  3.37it/s] 
                                                           
{'loss': 2.8738, 'learning_rate': 3.89757374647159e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251940/371472 [8:59:58<9:51:33,  3.37it/s]
 68%|██████▊   | 251941/371472 [8:59:59<9:30:13,  3.49it/s]
 68%|██████▊   | 251942/371472 [8:59:59<8:55:00,  3.72it/s]
 68%|██████▊   | 251943/371472 [8:59:59<8:46:36,  3.78it/s]
 68%|██████▊   | 251944/371472 [9:00:00<9:54:34,  3.35it/s]
 68%|██████▊   | 251945/371472 [9:00:00<9:39:57,  3.43it/s]
 68%|██████▊   | 251946/371472 [9:00:00<9:41:25,  3.43it/s]
 68%|██████▊   | 251947/371472 [9:00:00<9:42:30,  3.42it/s]
 68%|██████▊   | 251948/371472 [9:00:01<9:33:48,  3.47it/s]
 68%|██████▊   | 251949/371472 [9:00:01<9:17:01,  3.58it/s]
 68%|██████▊   | 251950/371472 [9:00:01<9:11:37,  3.61it/s]
 68%|██████▊   | 251951/371472 [9:00:02<9:13:13,  3.60it/s]
 68%|██████▊   | 251952/371472 [9:00:02<8:58:18,  3.70it/s]
 68%|██████▊   | 251953/371472 [9:00:02<8:49:31,  3.76it/s]
 68%|██████▊   | 251954/371472 [9:00:02<9:43:58,  3.41it/s]
 68%|██████▊   | 251955/371472 [9:00:03<9:49:35,  3.38it/s]
 68%|██████▊   | 251956/371472 [9:00:03<9:27:26,  3.51it/s]
 68%|██████▊   | 251957/371472 [9:00:03<10:28:44,  3.17it/s]
 68%|██████▊   | 251958/371472 [9:00:04<9:56:54,  3.34it/s] 
 68%|██████▊   | 251959/371472 [9:00:04<9:35:48,  3.46it/s]
 68%|██████▊   | 251960/371472 [9:00:04<9:52:01,  3.36it/s]
                                                           
{'loss': 2.7913, 'learning_rate': 3.8970889267168e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251960/371472 [9:00:04<9:52:01,  3.36it/s]
 68%|██████▊   | 251961/371472 [9:00:04<9:33:50,  3.47it/s]
 68%|██████▊   | 251962/371472 [9:00:05<9:41:26,  3.43it/s]
 68%|██████▊   | 251963/371472 [9:00:05<9:27:17,  3.51it/s]
 68%|██████▊   | 251964/371472 [9:00:05<9:39:31,  3.44it/s]
 68%|██████▊   | 251965/371472 [9:00:06<9:10:12,  3.62it/s]
 68%|██████▊   | 251966/371472 [9:00:06<9:56:05,  3.34it/s]
 68%|██████▊   | 251967/371472 [9:00:06<9:29:32,  3.50it/s]
 68%|██████▊   | 251968/371472 [9:00:06<9:10:13,  3.62it/s]
 68%|██████▊   | 251969/371472 [9:00:07<9:10:13,  3.62it/s]
 68%|██████▊   | 251970/371472 [9:00:07<9:13:25,  3.60it/s]
 68%|██████▊   | 251971/371472 [9:00:07<8:59:14,  3.69it/s]
 68%|██████▊   | 251972/371472 [9:00:07<8:46:11,  3.79it/s]
 68%|██████▊   | 251973/371472 [9:00:08<9:33:22,  3.47it/s]
 68%|██████▊   | 251974/371472 [9:00:08<9:27:31,  3.51it/s]
 68%|██████▊   | 251975/371472 [9:00:08<9:13:37,  3.60it/s]
 68%|██████▊   | 251976/371472 [9:00:09<9:25:50,  3.52it/s]
 68%|██████▊   | 251977/371472 [9:00:09<10:00:05,  3.32it/s]
 68%|██████▊   | 251978/371472 [9:00:09<10:08:06,  3.27it/s]
 68%|██████▊   | 251979/371472 [9:00:10<10:09:09,  3.27it/s]
 68%|██████▊   | 251980/371472 [9:00:10<9:46:30,  3.40it/s] 
                                                           
{'loss': 3.0585, 'learning_rate': 3.8966041069620117e-07, 'epoch': 10.85}
+
 68%|██████▊   | 251980/371472 [9:00:10<9:46:30,  3.40it/s]
 68%|██████▊   | 251981/371472 [9:00:10<9:25:53,  3.52it/s]
 68%|██████▊   | 251982/371472 [9:00:10<9:13:06,  3.60it/s]
 68%|██████▊   | 251983/371472 [9:00:11<9:25:30,  3.52it/s]
 68%|██████▊   | 251984/371472 [9:00:11<9:17:44,  3.57it/s]
 68%|██████▊   | 251985/371472 [9:00:11<9:06:22,  3.64it/s]
 68%|██████▊   | 251986/371472 [9:00:12<8:57:23,  3.71it/s]
 68%|██████▊   | 251987/371472 [9:00:12<8:52:48,  3.74it/s]
 68%|██████▊   | 251988/371472 [9:00:12<8:37:14,  3.85it/s]
 68%|██████▊   | 251989/371472 [9:00:12<8:47:44,  3.77it/s]
 68%|██████▊   | 251990/371472 [9:00:13<8:44:34,  3.80it/s]
 68%|██████▊   | 251991/371472 [9:00:13<8:33:11,  3.88it/s]
 68%|██████▊   | 251992/371472 [9:00:13<8:26:12,  3.93it/s]
 68%|██████▊   | 251993/371472 [9:00:13<8:15:23,  4.02it/s]
 68%|██████▊   | 251994/371472 [9:00:14<8:11:02,  4.06it/s]
 68%|██████▊   | 251995/371472 [9:00:14<8:16:17,  4.01it/s]
 68%|██████▊   | 251996/371472 [9:00:14<8:21:27,  3.97it/s]
 68%|██████▊   | 251997/371472 [9:00:14<8:27:44,  3.92it/s]
 68%|██████▊   | 251998/371472 [9:00:15<8:40:32,  3.83it/s]
 68%|██████▊   | 251999/371472 [9:00:15<8:40:03,  3.83it/s]
 68%|██████▊   | 252000/371472 [9:00:15<8:52:12,  3.74it/s]
                                                           
{'loss': 2.813, 'learning_rate': 3.8961192872072224e-07, 'epoch': 10.85}
+
 68%|██████▊   | 252000/371472 [9:00:15<8:52:12,  3.74it/s]
 68%|██████▊   | 252001/371472 [9:00:15<8:53:17,  3.73it/s]
 68%|██████▊   | 252002/371472 [9:00:16<8:54:19,  3.73it/s]
 68%|██████▊   | 252003/371472 [9:00:16<8:52:15,  3.74it/s]
 68%|██████▊   | 252004/371472 [9:00:16<8:48:32,  3.77it/s]
 68%|██████▊   | 252005/371472 [9:00:16<8:55:02,  3.72it/s]
 68%|██████▊   | 252006/371472 [9:00:17<9:04:25,  3.66it/s]
 68%|██████▊   | 252007/371472 [9:00:17<9:15:32,  3.58it/s]
 68%|██████▊   | 252008/371472 [9:00:17<9:20:26,  3.55it/s]
 68%|██████▊   | 252009/371472 [9:00:18<9:20:24,  3.55it/s]
 68%|██████▊   | 252010/371472 [9:00:18<9:19:54,  3.56it/s]
 68%|██████▊   | 252011/371472 [9:00:18<10:45:20,  3.09it/s]
 68%|██████▊   | 252012/371472 [9:00:19<10:41:27,  3.10it/s]
 68%|██████▊   | 252013/371472 [9:00:19<10:18:50,  3.22it/s]
 68%|██████▊   | 252014/371472 [9:00:19<9:38:02,  3.44it/s] 
 68%|██████▊   | 252015/371472 [9:00:19<9:30:36,  3.49it/s]
 68%|██████▊   | 252016/371472 [9:00:20<9:07:39,  3.64it/s]
 68%|██████▊   | 252017/371472 [9:00:20<10:22:58,  3.20it/s]
 68%|██████▊   | 252018/371472 [9:00:20<10:08:05,  3.27it/s]
 68%|██████▊   | 252019/371472 [9:00:21<9:34:33,  3.47it/s] 
 68%|██████▊   | 252020/371472 [9:00:21<9:53:25,  3.35it/s]
                                                           
{'loss': 2.8263, 'learning_rate': 3.8956344674524337e-07, 'epoch': 10.85}
+
 68%|██████▊   | 252020/371472 [9:00:21<9:53:25,  3.35it/s]
 68%|██████▊   | 252021/371472 [9:00:21<10:12:27,  3.25it/s]
 68%|██████▊   | 252022/371472 [9:00:22<9:36:24,  3.45it/s] 
 68%|██████▊   | 252023/371472 [9:00:22<9:07:39,  3.64it/s]
 68%|██████▊   | 252024/371472 [9:00:22<8:51:42,  3.74it/s]
 68%|██████▊   | 252025/371472 [9:00:22<8:33:34,  3.88it/s]
 68%|██████▊   | 252026/371472 [9:00:22<8:34:56,  3.87it/s]
 68%|██████▊   | 252027/371472 [9:00:23<8:14:06,  4.03it/s]
 68%|██████▊   | 252028/371472 [9:00:23<8:10:59,  4.05it/s]
 68%|██████▊   | 252029/371472 [9:00:23<8:25:44,  3.94it/s]
 68%|██████▊   | 252030/371472 [9:00:24<8:32:42,  3.88it/s]
 68%|██████▊   | 252031/371472 [9:00:24<8:37:33,  3.85it/s]
 68%|██████▊   | 252032/371472 [9:00:24<8:54:18,  3.73it/s]
 68%|██████▊   | 252033/371472 [9:00:24<9:12:02,  3.61it/s]
 68%|██████▊   | 252034/371472 [9:00:25<9:01:10,  3.68it/s]
 68%|██████▊   | 252035/371472 [9:00:25<9:14:47,  3.59it/s]
 68%|██████▊   | 252036/371472 [9:00:25<8:50:38,  3.75it/s]
 68%|██████▊   | 252037/371472 [9:00:25<9:04:44,  3.65it/s]
 68%|██████▊   | 252038/371472 [9:00:26<8:45:48,  3.79it/s]
 68%|██████▊   | 252039/371472 [9:00:26<9:09:55,  3.62it/s]
 68%|██████▊   | 252040/371472 [9:00:26<9:15:03,  3.59it/s]
                                                           
{'loss': 2.9531, 'learning_rate': 3.8951496476976444e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252040/371472 [9:00:26<9:15:03,  3.59it/s]
 68%|██████▊   | 252041/371472 [9:00:27<9:14:36,  3.59it/s]
 68%|██████▊   | 252042/371472 [9:00:27<9:28:41,  3.50it/s]
 68%|██████▊   | 252043/371472 [9:00:27<9:42:34,  3.42it/s]
 68%|██████▊   | 252044/371472 [9:00:27<9:22:54,  3.54it/s]
 68%|██████▊   | 252045/371472 [9:00:28<9:16:06,  3.58it/s]
 68%|██████▊   | 252046/371472 [9:00:28<9:05:57,  3.65it/s]
 68%|██████▊   | 252047/371472 [9:00:28<9:15:22,  3.58it/s]
 68%|██████▊   | 252048/371472 [9:00:29<9:19:25,  3.56it/s]
 68%|██████▊   | 252049/371472 [9:00:29<9:39:12,  3.44it/s]
 68%|██████▊   | 252050/371472 [9:00:29<9:52:14,  3.36it/s]
 68%|██████▊   | 252051/371472 [9:00:29<10:08:25,  3.27it/s]
 68%|██████▊   | 252052/371472 [9:00:30<10:13:09,  3.25it/s]
 68%|██████▊   | 252053/371472 [9:00:30<10:15:58,  3.23it/s]
 68%|██████▊   | 252054/371472 [9:00:30<9:53:15,  3.35it/s] 
 68%|██████▊   | 252055/371472 [9:00:31<9:30:21,  3.49it/s]
 68%|██████▊   | 252056/371472 [9:00:31<9:25:27,  3.52it/s]
 68%|██████▊   | 252057/371472 [9:00:31<9:35:38,  3.46it/s]
 68%|██████▊   | 252058/371472 [9:00:32<9:42:48,  3.41it/s]
 68%|██████▊   | 252059/371472 [9:00:32<9:30:23,  3.49it/s]
 68%|██████▊   | 252060/371472 [9:00:32<9:10:53,  3.61it/s]
                                                           
{'loss': 2.8026, 'learning_rate': 3.894664827942856e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252060/371472 [9:00:32<9:10:53,  3.61it/s]
 68%|██████▊   | 252061/371472 [9:00:32<9:26:40,  3.51it/s]
 68%|██████▊   | 252062/371472 [9:00:33<9:31:46,  3.48it/s]
 68%|██████▊   | 252063/371472 [9:00:33<9:05:38,  3.65it/s]
 68%|██████▊   | 252064/371472 [9:00:33<8:57:15,  3.70it/s]
 68%|██████▊   | 252065/371472 [9:00:33<9:08:12,  3.63it/s]
 68%|██████▊   | 252066/371472 [9:00:34<9:01:57,  3.67it/s]
 68%|██████▊   | 252067/371472 [9:00:34<8:58:06,  3.70it/s]
 68%|██████▊   | 252068/371472 [9:00:34<8:57:08,  3.70it/s]
 68%|██████▊   | 252069/371472 [9:00:35<9:35:46,  3.46it/s]
 68%|██████▊   | 252070/371472 [9:00:35<9:32:14,  3.48it/s]
 68%|██████▊   | 252071/371472 [9:00:35<9:46:16,  3.39it/s]
 68%|██████▊   | 252072/371472 [9:00:35<9:32:42,  3.47it/s]
 68%|██████▊   | 252073/371472 [9:00:36<9:20:57,  3.55it/s]
 68%|██████▊   | 252074/371472 [9:00:36<9:06:12,  3.64it/s]
 68%|██████▊   | 252075/371472 [9:00:36<8:51:08,  3.75it/s]
 68%|██████▊   | 252076/371472 [9:00:37<9:47:27,  3.39it/s]
 68%|██████▊   | 252077/371472 [9:00:37<9:38:18,  3.44it/s]
 68%|██████▊   | 252078/371472 [9:00:37<9:59:20,  3.32it/s]
 68%|██████▊   | 252079/371472 [9:00:37<9:36:36,  3.45it/s]
 68%|██████▊   | 252080/371472 [9:00:38<9:46:40,  3.39it/s]
                                                           
{'loss': 2.8609, 'learning_rate': 3.8941800081880663e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252080/371472 [9:00:38<9:46:40,  3.39it/s]
 68%|██████▊   | 252081/371472 [9:00:38<9:34:17,  3.46it/s]
 68%|██████▊   | 252082/371472 [9:00:38<9:03:05,  3.66it/s]
 68%|██████▊   | 252083/371472 [9:00:38<8:43:14,  3.80it/s]
 68%|██████▊   | 252084/371472 [9:00:39<10:07:14,  3.28it/s]
 68%|██████▊   | 252085/371472 [9:00:39<10:21:42,  3.20it/s]
 68%|██████▊   | 252086/371472 [9:00:40<11:02:16,  3.00it/s]
 68%|██████▊   | 252087/371472 [9:00:40<10:32:21,  3.15it/s]
 68%|██████▊   | 252088/371472 [9:00:40<10:21:18,  3.20it/s]
 68%|██████▊   | 252089/371472 [9:00:40<9:47:58,  3.38it/s] 
 68%|██████▊   | 252090/371472 [9:00:41<10:09:32,  3.26it/s]
 68%|██████▊   | 252091/371472 [9:00:41<9:53:21,  3.35it/s] 
 68%|██████▊   | 252092/371472 [9:00:41<9:37:14,  3.45it/s]
 68%|██████▊   | 252093/371472 [9:00:42<9:09:31,  3.62it/s]
 68%|██████▊   | 252094/371472 [9:00:42<9:30:46,  3.49it/s]
 68%|██████▊   | 252095/371472 [9:00:42<9:24:13,  3.53it/s]
 68%|██████▊   | 252096/371472 [9:00:42<9:06:07,  3.64it/s]
 68%|██████▊   | 252097/371472 [9:00:43<9:02:29,  3.67it/s]
 68%|██████▊   | 252098/371472 [9:00:43<9:05:15,  3.65it/s]
 68%|██████▊   | 252099/371472 [9:00:43<9:31:41,  3.48it/s]
 68%|██████▊   | 252100/371472 [9:00:44<9:32:01,  3.48it/s]
                                                           
{'loss': 2.8749, 'learning_rate': 3.893695188433278e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252100/371472 [9:00:44<9:32:01,  3.48it/s]
 68%|██████▊   | 252101/371472 [9:00:44<9:13:18,  3.60it/s]
 68%|██████▊   | 252102/371472 [9:00:44<8:58:54,  3.69it/s]
 68%|██████▊   | 252103/371472 [9:00:44<8:52:58,  3.73it/s]
 68%|██████▊   | 252104/371472 [9:00:45<8:59:00,  3.69it/s]
 68%|██████▊   | 252105/371472 [9:00:45<8:32:52,  3.88it/s]
 68%|██████▊   | 252106/371472 [9:00:45<8:48:24,  3.76it/s]
 68%|██████▊   | 252107/371472 [9:00:45<8:40:14,  3.82it/s]
 68%|██████▊   | 252108/371472 [9:00:46<8:29:18,  3.91it/s]
 68%|██████▊   | 252109/371472 [9:00:46<8:40:19,  3.82it/s]
 68%|██████▊   | 252110/371472 [9:00:46<8:38:38,  3.84it/s]
 68%|██████▊   | 252111/371472 [9:00:47<9:33:15,  3.47it/s]
 68%|██████▊   | 252112/371472 [9:00:47<9:28:56,  3.50it/s]
 68%|██████▊   | 252113/371472 [9:00:47<9:33:26,  3.47it/s]
 68%|██████▊   | 252114/371472 [9:00:47<9:34:55,  3.46it/s]
 68%|██████▊   | 252115/371472 [9:00:48<9:35:44,  3.46it/s]
 68%|██████▊   | 252116/371472 [9:00:48<9:33:52,  3.47it/s]
 68%|██████▊   | 252117/371472 [9:00:48<10:20:36,  3.21it/s]
 68%|██████▊   | 252118/371472 [9:00:49<10:04:05,  3.29it/s]
 68%|██████▊   | 252119/371472 [9:00:49<9:40:39,  3.43it/s] 
 68%|██████▊   | 252120/371472 [9:00:49<9:14:13,  3.59it/s]
                                                           
{'loss': 2.8547, 'learning_rate': 3.893210368678489e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252120/371472 [9:00:49<9:14:13,  3.59it/s]
 68%|██████▊   | 252121/371472 [9:00:49<9:23:30,  3.53it/s]
 68%|██████▊   | 252122/371472 [9:00:50<9:06:06,  3.64it/s]
 68%|██████▊   | 252123/371472 [9:00:50<8:59:52,  3.68it/s]
 68%|██████▊   | 252124/371472 [9:00:50<8:47:06,  3.77it/s]
 68%|██████▊   | 252125/371472 [9:00:50<8:37:16,  3.85it/s]
 68%|██████▊   | 252126/371472 [9:00:51<9:14:53,  3.58it/s]
 68%|██████▊   | 252127/371472 [9:00:51<9:18:45,  3.56it/s]
 68%|██████▊   | 252128/371472 [9:00:51<8:57:44,  3.70it/s]
 68%|██████▊   | 252129/371472 [9:00:52<9:02:29,  3.67it/s]
 68%|██████▊   | 252130/371472 [9:00:52<8:49:35,  3.76it/s]
 68%|██████▊   | 252131/371472 [9:00:52<8:55:46,  3.71it/s]
 68%|██████▊   | 252132/371472 [9:00:52<8:55:43,  3.71it/s]
 68%|██████▊   | 252133/371472 [9:00:53<9:30:42,  3.49it/s]
 68%|██████▊   | 252134/371472 [9:00:53<9:09:24,  3.62it/s]
 68%|██████▊   | 252135/371472 [9:00:53<9:40:36,  3.43it/s]
 68%|██████▊   | 252136/371472 [9:00:54<9:45:04,  3.40it/s]
 68%|██████▊   | 252137/371472 [9:00:54<9:25:51,  3.51it/s]
 68%|██████▊   | 252138/371472 [9:00:54<9:20:48,  3.55it/s]
 68%|██████▊   | 252139/371472 [9:00:54<9:46:01,  3.39it/s]
 68%|██████▊   | 252140/371472 [9:00:55<9:43:48,  3.41it/s]
                                                           
{'loss': 2.6931, 'learning_rate': 3.8927255489237e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252140/371472 [9:00:55<9:43:48,  3.41it/s]
 68%|██████▊   | 252141/371472 [9:00:55<9:29:31,  3.49it/s]
 68%|██████▊   | 252142/371472 [9:00:55<9:33:01,  3.47it/s]
 68%|██████▊   | 252143/371472 [9:00:56<9:37:04,  3.45it/s]
 68%|██████▊   | 252144/371472 [9:00:56<10:04:36,  3.29it/s]
 68%|██████▊   | 252145/371472 [9:00:56<9:35:21,  3.46it/s] 
 68%|██████▊   | 252146/371472 [9:00:56<9:18:24,  3.56it/s]
 68%|██████▊   | 252147/371472 [9:00:57<8:54:35,  3.72it/s]
 68%|██████▊   | 252148/371472 [9:00:57<8:58:55,  3.69it/s]
 68%|██████▊   | 252149/371472 [9:00:57<8:56:54,  3.70it/s]
 68%|██████▊   | 252150/371472 [9:00:57<9:01:52,  3.67it/s]
 68%|██████▊   | 252151/371472 [9:00:58<9:00:52,  3.68it/s]
 68%|██████▊   | 252152/371472 [9:00:58<9:39:50,  3.43it/s]
 68%|██████▊   | 252153/371472 [9:00:58<10:09:19,  3.26it/s]
 68%|██████▊   | 252154/371472 [9:00:59<9:57:15,  3.33it/s] 
 68%|██████▊   | 252155/371472 [9:00:59<10:27:27,  3.17it/s]
 68%|██████▊   | 252156/371472 [9:00:59<10:15:01,  3.23it/s]
 68%|██████▊   | 252157/371472 [9:01:00<10:05:26,  3.28it/s]
 68%|██████▊   | 252158/371472 [9:01:00<9:39:25,  3.43it/s] 
 68%|██████▊   | 252159/371472 [9:01:00<9:36:49,  3.45it/s]
 68%|██████▊   | 252160/371472 [9:01:01<9:41:14,  3.42it/s]
                                                           
{'loss': 2.9677, 'learning_rate': 3.892240729168911e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252160/371472 [9:01:01<9:41:14,  3.42it/s]
 68%|██████▊   | 252161/371472 [9:01:01<9:08:15,  3.63it/s]
 68%|██████▊   | 252162/371472 [9:01:01<9:51:47,  3.36it/s]
 68%|██████▊   | 252163/371472 [9:01:01<9:41:49,  3.42it/s]
 68%|██████▊   | 252164/371472 [9:01:02<9:47:33,  3.38it/s]
 68%|██████▊   | 252165/371472 [9:01:02<9:26:53,  3.51it/s]
 68%|██████▊   | 252166/371472 [9:01:02<9:27:35,  3.50it/s]
 68%|██████▊   | 252167/371472 [9:01:02<9:25:56,  3.51it/s]
 68%|██████▊   | 252168/371472 [9:01:03<9:18:55,  3.56it/s]
 68%|██████▊   | 252169/371472 [9:01:03<9:14:02,  3.59it/s]
 68%|██████▊   | 252170/371472 [9:01:03<9:06:55,  3.64it/s]
 68%|██████▊   | 252171/371472 [9:01:04<9:10:41,  3.61it/s]
 68%|██████▊   | 252172/371472 [9:01:04<8:47:36,  3.77it/s]
 68%|██████▊   | 252173/371472 [9:01:04<9:27:42,  3.50it/s]
 68%|██████▊   | 252174/371472 [9:01:04<9:05:46,  3.64it/s]
 68%|██████▊   | 252175/371472 [9:01:05<9:03:46,  3.66it/s]
 68%|██████▊   | 252176/371472 [9:01:05<8:40:46,  3.82it/s]
 68%|██████▊   | 252177/371472 [9:01:05<9:19:48,  3.55it/s]
 68%|██████▊   | 252178/371472 [9:01:06<9:34:02,  3.46it/s]
 68%|██████▊   | 252179/371472 [9:01:06<9:42:09,  3.42it/s]
 68%|██████▊   | 252180/371472 [9:01:06<9:08:19,  3.63it/s]
                                                           
{'loss': 2.8588, 'learning_rate': 3.8917559094141226e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252180/371472 [9:01:06<9:08:19,  3.63it/s]
 68%|██████▊   | 252181/371472 [9:01:06<9:06:41,  3.64it/s]
 68%|██████▊   | 252182/371472 [9:01:07<9:48:57,  3.38it/s]
 68%|██████▊   | 252183/371472 [9:01:07<10:10:36,  3.26it/s]
 68%|██████▊   | 252184/371472 [9:01:07<9:49:59,  3.37it/s] 
 68%|██████▊   | 252185/371472 [9:01:08<9:26:20,  3.51it/s]
 68%|██████▊   | 252186/371472 [9:01:08<8:58:28,  3.69it/s]
 68%|██████▊   | 252187/371472 [9:01:08<9:50:18,  3.37it/s]
 68%|██████▊   | 252188/371472 [9:01:08<9:27:45,  3.50it/s]
 68%|██████▊   | 252189/371472 [9:01:09<9:27:45,  3.50it/s]
 68%|██████▊   | 252190/371472 [9:01:09<9:19:41,  3.55it/s]
 68%|██████▊   | 252191/371472 [9:01:09<9:25:04,  3.52it/s]
 68%|██████▊   | 252192/371472 [9:01:10<9:23:30,  3.53it/s]
 68%|██████▊   | 252193/371472 [9:01:10<9:10:41,  3.61it/s]
 68%|██████▊   | 252194/371472 [9:01:10<9:32:28,  3.47it/s]
 68%|██████▊   | 252195/371472 [9:01:10<9:56:50,  3.33it/s]
 68%|██████▊   | 252196/371472 [9:01:11<9:29:58,  3.49it/s]
 68%|██████▊   | 252197/371472 [9:01:11<9:08:37,  3.62it/s]
 68%|██████▊   | 252198/371472 [9:01:11<9:14:40,  3.58it/s]
 68%|██████▊   | 252199/371472 [9:01:12<9:24:46,  3.52it/s]
 68%|██████▊   | 252200/371472 [9:01:12<9:19:09,  3.56it/s]
                                                           
{'loss': 2.6202, 'learning_rate': 3.8912710896593333e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252200/371472 [9:01:12<9:19:09,  3.56it/s]
 68%|██████▊   | 252201/371472 [9:01:12<9:25:28,  3.52it/s]
 68%|██████▊   | 252202/371472 [9:01:12<9:14:46,  3.58it/s]
 68%|██████▊   | 252203/371472 [9:01:13<9:21:09,  3.54it/s]
 68%|██████▊   | 252204/371472 [9:01:13<9:03:59,  3.65it/s]
 68%|██████▊   | 252205/371472 [9:01:13<9:17:12,  3.57it/s]
 68%|██████▊   | 252206/371472 [9:01:14<9:16:56,  3.57it/s]
 68%|██████▊   | 252207/371472 [9:01:14<9:09:57,  3.61it/s]
 68%|██████▊   | 252208/371472 [9:01:14<9:05:26,  3.64it/s]
 68%|██████▊   | 252209/371472 [9:01:14<9:00:18,  3.68it/s]
 68%|██████▊   | 252210/371472 [9:01:15<8:36:17,  3.85it/s]
 68%|██████▊   | 252211/371472 [9:01:15<8:43:22,  3.80it/s]
 68%|██████▊   | 252212/371472 [9:01:15<9:04:49,  3.65it/s]
 68%|██████▊   | 252213/371472 [9:01:15<9:57:17,  3.33it/s]
 68%|██████▊   | 252214/371472 [9:01:16<9:26:14,  3.51it/s]
 68%|██████▊   | 252215/371472 [9:01:16<9:29:44,  3.49it/s]
 68%|██████▊   | 252216/371472 [9:01:16<9:16:30,  3.57it/s]
 68%|██████▊   | 252217/371472 [9:01:17<8:55:15,  3.71it/s]
 68%|██████▊   | 252218/371472 [9:01:17<9:24:31,  3.52it/s]
 68%|██████▊   | 252219/371472 [9:01:17<9:06:40,  3.64it/s]
 68%|██████▊   | 252220/371472 [9:01:17<9:08:18,  3.62it/s]
                                                           
{'loss': 2.7904, 'learning_rate': 3.8907862699045445e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252220/371472 [9:01:17<9:08:18,  3.62it/s]
 68%|██████▊   | 252221/371472 [9:01:18<9:11:27,  3.60it/s]
 68%|██████▊   | 252222/371472 [9:01:18<9:02:07,  3.67it/s]
 68%|██████▊   | 252223/371472 [9:01:18<9:02:25,  3.66it/s]
 68%|██████▊   | 252224/371472 [9:01:18<9:08:57,  3.62it/s]
 68%|██████▊   | 252225/371472 [9:01:19<8:49:32,  3.75it/s]
 68%|██████▊   | 252226/371472 [9:01:19<9:10:32,  3.61it/s]
 68%|██████▊   | 252227/371472 [9:01:19<9:02:33,  3.66it/s]
 68%|██████▊   | 252228/371472 [9:01:20<9:17:34,  3.56it/s]
 68%|██████▊   | 252229/371472 [9:01:20<9:12:21,  3.60it/s]
 68%|██████▊   | 252230/371472 [9:01:20<9:48:01,  3.38it/s]
 68%|██████▊   | 252231/371472 [9:01:20<9:36:59,  3.44it/s]
 68%|██████▊   | 252232/371472 [9:01:21<9:27:44,  3.50it/s]
 68%|██████▊   | 252233/371472 [9:01:21<9:03:10,  3.66it/s]
 68%|██████▊   | 252234/371472 [9:01:21<9:38:35,  3.43it/s]
 68%|██████▊   | 252235/371472 [9:01:22<9:15:55,  3.57it/s]
 68%|██████▊   | 252236/371472 [9:01:22<9:07:25,  3.63it/s]
 68%|██████▊   | 252237/371472 [9:01:22<8:41:20,  3.81it/s]
 68%|██████▊   | 252238/371472 [9:01:22<8:28:10,  3.91it/s]
 68%|██████▊   | 252239/371472 [9:01:23<8:32:42,  3.88it/s]
 68%|██████▊   | 252240/371472 [9:01:23<8:30:23,  3.89it/s]
                                                           
{'loss': 2.8254, 'learning_rate': 3.890301450149755e-07, 'epoch': 10.86}
+
 68%|██████▊   | 252240/371472 [9:01:23<8:30:23,  3.89it/s]
 68%|██████▊   | 252241/371472 [9:01:23<8:25:11,  3.93it/s]
 68%|██████▊   | 252242/371472 [9:01:23<8:10:08,  4.05it/s]
 68%|██████▊   | 252243/371472 [9:01:24<8:06:44,  4.08it/s]
 68%|██████▊   | 252244/371472 [9:01:24<8:12:37,  4.03it/s]
 68%|██████▊   | 252245/371472 [9:01:24<10:34:44,  3.13it/s]
 68%|██████▊   | 252246/371472 [9:01:25<10:07:57,  3.27it/s]
 68%|██████▊   | 252247/371472 [9:01:25<9:44:54,  3.40it/s] 
 68%|██████▊   | 252248/371472 [9:01:25<9:07:17,  3.63it/s]
 68%|██████▊   | 252249/371472 [9:01:25<8:50:49,  3.74it/s]
 68%|██████▊   | 252250/371472 [9:01:26<8:44:42,  3.79it/s]
 68%|██████▊   | 252251/371472 [9:01:26<9:28:26,  3.50it/s]
 68%|██████▊   | 252252/371472 [9:01:26<9:29:17,  3.49it/s]
 68%|██████▊   | 252253/371472 [9:01:26<9:45:20,  3.39it/s]
 68%|██████▊   | 252254/371472 [9:01:27<9:57:19,  3.33it/s]
 68%|██████▊   | 252255/371472 [9:01:27<9:43:11,  3.41it/s]
 68%|██████▊   | 252256/371472 [9:01:27<9:12:09,  3.60it/s]
 68%|██████▊   | 252257/371472 [9:01:28<9:39:31,  3.43it/s]
 68%|██████▊   | 252258/371472 [9:01:28<9:09:49,  3.61it/s]
 68%|██████▊   | 252259/371472 [9:01:28<10:11:49,  3.25it/s]
 68%|██████▊   | 252260/371472 [9:01:29<9:25:04,  3.52it/s] 
                                                           
{'loss': 2.7863, 'learning_rate': 3.889816630394967e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252260/371472 [9:01:29<9:25:04,  3.52it/s]
 68%|██████▊   | 252261/371472 [9:01:29<9:37:27,  3.44it/s]
 68%|██████▊   | 252262/371472 [9:01:29<9:27:32,  3.50it/s]
 68%|██████▊   | 252263/371472 [9:01:29<9:18:59,  3.55it/s]
 68%|██████▊   | 252264/371472 [9:01:30<9:17:44,  3.56it/s]
 68%|██████▊   | 252265/371472 [9:01:30<9:02:17,  3.66it/s]
 68%|██████▊   | 252266/371472 [9:01:30<8:58:45,  3.69it/s]
 68%|██████▊   | 252267/371472 [9:01:30<9:04:25,  3.65it/s]
 68%|██████▊   | 252268/371472 [9:01:31<8:57:05,  3.70it/s]
 68%|██████▊   | 252269/371472 [9:01:31<9:39:32,  3.43it/s]
 68%|██████▊   | 252270/371472 [9:01:31<9:34:57,  3.46it/s]
 68%|██████▊   | 252271/371472 [9:01:32<10:01:33,  3.30it/s]
 68%|██████▊   | 252272/371472 [9:01:32<9:25:49,  3.51it/s] 
 68%|██████▊   | 252273/371472 [9:01:32<10:09:15,  3.26it/s]
 68%|██████▊   | 252274/371472 [9:01:33<9:42:42,  3.41it/s] 
 68%|██████▊   | 252275/371472 [9:01:33<9:17:51,  3.56it/s]
 68%|██████▊   | 252276/371472 [9:01:33<9:14:42,  3.58it/s]
 68%|██████▊   | 252277/371472 [9:01:33<9:09:08,  3.62it/s]
 68%|██████▊   | 252278/371472 [9:01:34<8:58:38,  3.69it/s]
 68%|██████▊   | 252279/371472 [9:01:34<8:54:52,  3.71it/s]
 68%|██████▊   | 252280/371472 [9:01:34<8:47:50,  3.76it/s]
                                                           
{'loss': 2.8245, 'learning_rate': 3.889331810640177e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252280/371472 [9:01:34<8:47:50,  3.76it/s]
 68%|██████▊   | 252281/371472 [9:01:34<8:41:38,  3.81it/s]
 68%|██████▊   | 252282/371472 [9:01:35<9:14:37,  3.58it/s]
 68%|██████▊   | 252283/371472 [9:01:35<9:02:40,  3.66it/s]
 68%|██████▊   | 252284/371472 [9:01:35<8:44:31,  3.79it/s]
 68%|██████▊   | 252285/371472 [9:01:35<8:50:47,  3.74it/s]
 68%|██████▊   | 252286/371472 [9:01:36<10:00:12,  3.31it/s]
 68%|██████▊   | 252287/371472 [9:01:36<9:53:39,  3.35it/s] 
 68%|██████▊   | 252288/371472 [9:01:36<9:52:21,  3.35it/s]
 68%|██████▊   | 252289/371472 [9:01:37<9:38:10,  3.44it/s]
 68%|██████▊   | 252290/371472 [9:01:37<9:10:58,  3.61it/s]
 68%|██████▊   | 252291/371472 [9:01:37<9:18:51,  3.55it/s]
 68%|██████▊   | 252292/371472 [9:01:38<9:32:59,  3.47it/s]
 68%|██████▊   | 252293/371472 [9:01:38<9:39:33,  3.43it/s]
 68%|██████▊   | 252294/371472 [9:01:38<9:20:17,  3.55it/s]
 68%|██████▊   | 252295/371472 [9:01:38<9:11:24,  3.60it/s]
 68%|██████▊   | 252296/371472 [9:01:39<9:21:06,  3.54it/s]
 68%|██████▊   | 252297/371472 [9:01:39<8:59:15,  3.68it/s]
 68%|██████▊   | 252298/371472 [9:01:39<9:05:46,  3.64it/s]
 68%|██████▊   | 252299/371472 [9:01:39<8:37:45,  3.84it/s]
 68%|██████▊   | 252300/371472 [9:01:40<8:26:17,  3.92it/s]
                                                           
{'loss': 2.7688, 'learning_rate': 3.888846990885389e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252300/371472 [9:01:40<8:26:17,  3.92it/s]
 68%|██████▊   | 252301/371472 [9:01:40<8:39:50,  3.82it/s]
 68%|██████▊   | 252302/371472 [9:01:40<8:46:59,  3.77it/s]
 68%|██████▊   | 252303/371472 [9:01:40<8:59:43,  3.68it/s]
 68%|██████▊   | 252304/371472 [9:01:41<8:46:23,  3.77it/s]
 68%|██████▊   | 252305/371472 [9:01:41<9:13:08,  3.59it/s]
 68%|██████▊   | 252306/371472 [9:01:41<9:51:17,  3.36it/s]
 68%|██████▊   | 252307/371472 [9:01:42<9:21:27,  3.54it/s]
 68%|██████▊   | 252308/371472 [9:01:42<10:48:55,  3.06it/s]
 68%|██████▊   | 252309/371472 [9:01:42<10:12:49,  3.24it/s]
 68%|██████▊   | 252310/371472 [9:01:43<9:59:01,  3.32it/s] 
 68%|██████▊   | 252311/371472 [9:01:43<9:41:18,  3.42it/s]
 68%|██████▊   | 252312/371472 [9:01:43<9:28:38,  3.49it/s]
 68%|██████▊   | 252313/371472 [9:01:43<9:25:41,  3.51it/s]
 68%|██████▊   | 252314/371472 [9:01:44<9:23:40,  3.52it/s]
 68%|██████▊   | 252315/371472 [9:01:44<9:21:14,  3.54it/s]
 68%|██████▊   | 252316/371472 [9:01:44<9:16:38,  3.57it/s]
 68%|██████▊   | 252317/371472 [9:01:45<9:02:24,  3.66it/s]
 68%|██████▊   | 252318/371472 [9:01:45<8:42:49,  3.80it/s]
 68%|██████▊   | 252319/371472 [9:01:45<9:07:40,  3.63it/s]
 68%|██████▊   | 252320/371472 [9:01:45<9:25:33,  3.51it/s]
                                                           
{'loss': 2.7685, 'learning_rate': 3.8883621711305997e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252320/371472 [9:01:45<9:25:33,  3.51it/s]
 68%|██████▊   | 252321/371472 [9:01:46<9:19:13,  3.55it/s]
 68%|██████▊   | 252322/371472 [9:01:46<9:19:02,  3.55it/s]
 68%|██████▊   | 252323/371472 [9:01:46<9:12:54,  3.59it/s]
 68%|██████▊   | 252324/371472 [9:01:46<8:49:41,  3.75it/s]
 68%|██████▊   | 252325/371472 [9:01:47<8:39:17,  3.82it/s]
 68%|██████▊   | 252326/371472 [9:01:47<8:48:14,  3.76it/s]
 68%|██████▊   | 252327/371472 [9:01:47<9:00:50,  3.67it/s]
 68%|██████▊   | 252328/371472 [9:01:48<9:02:40,  3.66it/s]
 68%|██████▊   | 252329/371472 [9:01:48<8:51:14,  3.74it/s]
 68%|██████▊   | 252330/371472 [9:01:48<8:44:55,  3.78it/s]
 68%|██████▊   | 252331/371472 [9:01:48<8:59:42,  3.68it/s]
 68%|██████▊   | 252332/371472 [9:01:49<8:34:54,  3.86it/s]
 68%|██████▊   | 252333/371472 [9:01:49<9:13:14,  3.59it/s]
 68%|██████▊   | 252334/371472 [9:01:49<9:43:40,  3.40it/s]
 68%|██████▊   | 252335/371472 [9:01:50<9:35:52,  3.45it/s]
 68%|██████▊   | 252336/371472 [9:01:50<9:25:59,  3.51it/s]
 68%|██████▊   | 252337/371472 [9:01:50<9:30:19,  3.48it/s]
 68%|██████▊   | 252338/371472 [9:01:50<9:21:02,  3.54it/s]
 68%|██████▊   | 252339/371472 [9:01:51<9:00:31,  3.67it/s]
 68%|██████▊   | 252340/371472 [9:01:51<9:06:42,  3.63it/s]
                                                           
{'loss': 2.8424, 'learning_rate': 3.88787735137581e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252340/371472 [9:01:51<9:06:42,  3.63it/s]
 68%|██████▊   | 252341/371472 [9:01:51<9:04:46,  3.64it/s]
 68%|██████▊   | 252342/371472 [9:01:51<8:51:54,  3.73it/s]
 68%|██████▊   | 252343/371472 [9:01:52<8:42:56,  3.80it/s]
 68%|██████▊   | 252344/371472 [9:01:52<8:27:30,  3.91it/s]
 68%|██████▊   | 252345/371472 [9:01:52<8:45:23,  3.78it/s]
 68%|██████▊   | 252346/371472 [9:01:52<8:27:19,  3.91it/s]
 68%|██████▊   | 252347/371472 [9:01:53<8:24:00,  3.94it/s]
 68%|██████▊   | 252348/371472 [9:01:53<8:29:31,  3.90it/s]
 68%|██████▊   | 252349/371472 [9:01:53<8:21:02,  3.96it/s]
 68%|██████▊   | 252350/371472 [9:01:53<8:40:12,  3.82it/s]
 68%|██████▊   | 252351/371472 [9:01:54<9:10:39,  3.61it/s]
 68%|██████▊   | 252352/371472 [9:01:54<9:14:07,  3.58it/s]
 68%|██████▊   | 252353/371472 [9:01:54<9:08:08,  3.62it/s]
 68%|██████▊   | 252354/371472 [9:01:55<9:08:38,  3.62it/s]
 68%|██████▊   | 252355/371472 [9:01:55<8:49:49,  3.75it/s]
 68%|██████▊   | 252356/371472 [9:01:55<8:55:23,  3.71it/s]
 68%|██████▊   | 252357/371472 [9:01:55<8:43:50,  3.79it/s]
 68%|██████▊   | 252358/371472 [9:01:56<8:40:48,  3.81it/s]
 68%|██████▊   | 252359/371472 [9:01:56<8:29:44,  3.89it/s]
 68%|██████▊   | 252360/371472 [9:01:56<8:33:06,  3.87it/s]
                                                           
{'loss': 2.823, 'learning_rate': 3.8873925316210216e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252360/371472 [9:01:56<8:33:06,  3.87it/s]
 68%|██████▊   | 252361/371472 [9:01:56<8:38:28,  3.83it/s]
 68%|██████▊   | 252362/371472 [9:01:57<8:35:19,  3.85it/s]
 68%|██████▊   | 252363/371472 [9:01:57<8:52:14,  3.73it/s]
 68%|██████▊   | 252364/371472 [9:01:57<8:55:38,  3.71it/s]
 68%|██████▊   | 252365/371472 [9:01:58<13:36:45,  2.43it/s]
 68%|██████▊   | 252366/371472 [9:01:58<12:46:49,  2.59it/s]
 68%|██████▊   | 252367/371472 [9:01:59<11:36:35,  2.85it/s]
 68%|██████▊   | 252368/371472 [9:01:59<10:45:08,  3.08it/s]
 68%|██████▊   | 252369/371472 [9:01:59<10:15:14,  3.23it/s]
 68%|██████▊   | 252370/371472 [9:01:59<9:44:55,  3.39it/s] 
 68%|██████▊   | 252371/371472 [9:02:00<9:27:56,  3.50it/s]
 68%|██████▊   | 252372/371472 [9:02:00<9:16:53,  3.56it/s]
 68%|██████▊   | 252373/371472 [9:02:00<9:26:31,  3.50it/s]
 68%|██████▊   | 252374/371472 [9:02:00<9:14:35,  3.58it/s]
 68%|██████▊   | 252375/371472 [9:02:01<9:22:18,  3.53it/s]
 68%|██████▊   | 252376/371472 [9:02:01<9:39:11,  3.43it/s]
 68%|██████▊   | 252377/371472 [9:02:01<10:26:06,  3.17it/s]
 68%|██████▊   | 252378/371472 [9:02:02<10:11:12,  3.25it/s]
 68%|██████▊   | 252379/371472 [9:02:02<9:41:42,  3.41it/s] 
 68%|██████▊   | 252380/371472 [9:02:02<9:31:17,  3.47it/s]
                                                           
{'loss': 2.7799, 'learning_rate': 3.8869077118662323e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252380/371472 [9:02:02<9:31:17,  3.47it/s]
 68%|██████▊   | 252381/371472 [9:02:03<10:08:31,  3.26it/s]
 68%|██████▊   | 252382/371472 [9:02:03<10:15:54,  3.22it/s]
 68%|██████▊   | 252383/371472 [9:02:03<9:48:08,  3.37it/s] 
 68%|██████▊   | 252384/371472 [9:02:03<9:30:38,  3.48it/s]
 68%|██████▊   | 252385/371472 [9:02:04<9:39:59,  3.42it/s]
 68%|██████▊   | 252386/371472 [9:02:04<9:35:36,  3.45it/s]
 68%|██████▊   | 252387/371472 [9:02:04<9:29:20,  3.49it/s]
 68%|██████▊   | 252388/371472 [9:02:05<9:21:16,  3.54it/s]
 68%|██████▊   | 252389/371472 [9:02:05<9:27:26,  3.50it/s]
 68%|██████▊   | 252390/371472 [9:02:05<9:38:08,  3.43it/s]
 68%|██████▊   | 252391/371472 [9:02:05<9:31:33,  3.47it/s]
 68%|██████▊   | 252392/371472 [9:02:06<9:18:39,  3.55it/s]
 68%|██████▊   | 252393/371472 [9:02:06<8:58:48,  3.68it/s]
 68%|██████▊   | 252394/371472 [9:02:06<9:09:39,  3.61it/s]
 68%|██████▊   | 252395/371472 [9:02:07<9:40:26,  3.42it/s]
 68%|██████▊   | 252396/371472 [9:02:07<9:48:09,  3.37it/s]
 68%|██████▊   | 252397/371472 [9:02:07<9:38:35,  3.43it/s]
 68%|██████▊   | 252398/371472 [9:02:07<9:14:17,  3.58it/s]
 68%|██████▊   | 252399/371472 [9:02:08<9:43:17,  3.40it/s]
 68%|██████▊   | 252400/371472 [9:02:08<9:13:36,  3.58it/s]
                                                           
{'loss': 2.8706, 'learning_rate': 3.8864228921114436e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252400/371472 [9:02:08<9:13:36,  3.58it/s]
 68%|██████▊   | 252401/371472 [9:02:08<9:35:38,  3.45it/s]
 68%|██████▊   | 252402/371472 [9:02:09<9:06:56,  3.63it/s]
 68%|██████▊   | 252403/371472 [9:02:09<9:21:53,  3.53it/s]
 68%|██████▊   | 252404/371472 [9:02:09<8:58:32,  3.68it/s]
 68%|██████▊   | 252405/371472 [9:02:09<9:03:40,  3.65it/s]
 68%|██████▊   | 252406/371472 [9:02:10<9:07:11,  3.63it/s]
 68%|██████▊   | 252407/371472 [9:02:10<8:51:06,  3.74it/s]
 68%|██████▊   | 252408/371472 [9:02:10<9:08:04,  3.62it/s]
 68%|██████▊   | 252409/371472 [9:02:11<9:22:07,  3.53it/s]
 68%|██████▊   | 252410/371472 [9:02:11<9:36:55,  3.44it/s]
 68%|██████▊   | 252411/371472 [9:02:11<10:06:10,  3.27it/s]
 68%|██████▊   | 252412/371472 [9:02:11<9:41:07,  3.41it/s] 
 68%|██████▊   | 252413/371472 [9:02:12<9:24:39,  3.51it/s]
 68%|██████▊   | 252414/371472 [9:02:12<9:09:14,  3.61it/s]
 68%|██████▊   | 252415/371472 [9:02:12<9:09:20,  3.61it/s]
 68%|██████▊   | 252416/371472 [9:02:13<9:18:15,  3.55it/s]
 68%|██████▊   | 252417/371472 [9:02:13<8:51:08,  3.74it/s]
 68%|██████▊   | 252418/371472 [9:02:13<8:45:22,  3.78it/s]
 68%|██████▊   | 252419/371472 [9:02:13<8:39:20,  3.82it/s]
 68%|██████▊   | 252420/371472 [9:02:13<8:21:05,  3.96it/s]
                                                           
{'loss': 2.7512, 'learning_rate': 3.8859380723566543e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252420/371472 [9:02:14<8:21:05,  3.96it/s]
 68%|██████▊   | 252421/371472 [9:02:14<8:16:47,  3.99it/s]
 68%|██████▊   | 252422/371472 [9:02:14<9:28:09,  3.49it/s]
 68%|██████▊   | 252423/371472 [9:02:14<9:18:17,  3.55it/s]
 68%|██████▊   | 252424/371472 [9:02:15<9:12:45,  3.59it/s]
 68%|██████▊   | 252425/371472 [9:02:15<8:49:26,  3.75it/s]
 68%|██████▊   | 252426/371472 [9:02:15<8:54:01,  3.72it/s]
 68%|██████▊   | 252427/371472 [9:02:15<8:47:16,  3.76it/s]
 68%|██████▊   | 252428/371472 [9:02:16<9:01:42,  3.66it/s]
 68%|██████▊   | 252429/371472 [9:02:16<9:55:18,  3.33it/s]
 68%|██████▊   | 252430/371472 [9:02:16<9:28:10,  3.49it/s]
 68%|██████▊   | 252431/371472 [9:02:17<10:40:56,  3.10it/s]
 68%|██████▊   | 252432/371472 [9:02:17<11:07:07,  2.97it/s]
 68%|██████▊   | 252433/371472 [9:02:17<11:10:35,  2.96it/s]
 68%|██████▊   | 252434/371472 [9:02:18<10:37:00,  3.11it/s]
 68%|██████▊   | 252435/371472 [9:02:18<10:07:54,  3.26it/s]
 68%|██████▊   | 252436/371472 [9:02:18<9:44:03,  3.40it/s] 
 68%|██████▊   | 252437/371472 [9:02:19<9:13:49,  3.58it/s]
 68%|██████▊   | 252438/371472 [9:02:19<9:13:02,  3.59it/s]
 68%|██████▊   | 252439/371472 [9:02:19<9:08:33,  3.62it/s]
 68%|██████▊   | 252440/371472 [9:02:19<8:54:22,  3.71it/s]
                                                           
{'loss': 2.6946, 'learning_rate': 3.885453252601866e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252440/371472 [9:02:19<8:54:22,  3.71it/s]
 68%|██████▊   | 252441/371472 [9:02:20<8:56:13,  3.70it/s]
 68%|██████▊   | 252442/371472 [9:02:20<8:53:59,  3.72it/s]
 68%|██████▊   | 252443/371472 [9:02:20<8:48:45,  3.75it/s]
 68%|██████▊   | 252444/371472 [9:02:20<9:12:06,  3.59it/s]
 68%|██████▊   | 252445/371472 [9:02:21<9:04:05,  3.65it/s]
 68%|██████▊   | 252446/371472 [9:02:21<9:01:34,  3.66it/s]
 68%|██████▊   | 252447/371472 [9:02:21<8:50:31,  3.74it/s]
 68%|██████▊   | 252448/371472 [9:02:21<8:59:00,  3.68it/s]
 68%|██████▊   | 252449/371472 [9:02:22<8:47:24,  3.76it/s]
 68%|██████▊   | 252450/371472 [9:02:22<8:31:05,  3.88it/s]
 68%|██████▊   | 252451/371472 [9:02:22<9:18:55,  3.55it/s]
 68%|██████▊   | 252452/371472 [9:02:23<8:48:09,  3.76it/s]
 68%|██████▊   | 252453/371472 [9:02:23<8:48:38,  3.75it/s]
 68%|██████▊   | 252454/371472 [9:02:23<8:50:30,  3.74it/s]
 68%|██████▊   | 252455/371472 [9:02:23<8:43:35,  3.79it/s]
 68%|██████▊   | 252456/371472 [9:02:24<9:04:11,  3.65it/s]
 68%|██████▊   | 252457/371472 [9:02:24<8:56:39,  3.70it/s]
 68%|██████▊   | 252458/371472 [9:02:24<9:06:26,  3.63it/s]
 68%|██████▊   | 252459/371472 [9:02:24<8:52:35,  3.72it/s]
 68%|██████▊   | 252460/371472 [9:02:25<9:20:49,  3.54it/s]
                                                           
{'loss': 2.7631, 'learning_rate': 3.884968432847077e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252460/371472 [9:02:25<9:20:49,  3.54it/s]
 68%|██████▊   | 252461/371472 [9:02:25<8:59:22,  3.68it/s]
 68%|██████▊   | 252462/371472 [9:02:25<8:59:33,  3.68it/s]
 68%|██████▊   | 252463/371472 [9:02:26<9:00:07,  3.67it/s]
 68%|██████▊   | 252464/371472 [9:02:26<9:06:33,  3.63it/s]
 68%|██████▊   | 252465/371472 [9:02:26<8:43:20,  3.79it/s]
 68%|██████▊   | 252466/371472 [9:02:26<8:27:11,  3.91it/s]
 68%|██████▊   | 252467/371472 [9:02:27<8:23:11,  3.94it/s]
 68%|██████▊   | 252468/371472 [9:02:27<8:33:41,  3.86it/s]
 68%|██████▊   | 252469/371472 [9:02:27<8:30:14,  3.89it/s]
 68%|██████▊   | 252470/371472 [9:02:27<8:37:50,  3.83it/s]
 68%|██████▊   | 252471/371472 [9:02:28<8:40:39,  3.81it/s]
 68%|██████▊   | 252472/371472 [9:02:28<8:51:15,  3.73it/s]
 68%|██████▊   | 252473/371472 [9:02:28<9:18:57,  3.55it/s]
 68%|██████▊   | 252474/371472 [9:02:28<9:13:10,  3.59it/s]
 68%|██████▊   | 252475/371472 [9:02:29<8:47:59,  3.76it/s]
 68%|██████▊   | 252476/371472 [9:02:29<8:27:49,  3.91it/s]
 68%|██████▊   | 252477/371472 [9:02:29<8:38:00,  3.83it/s]
 68%|██████▊   | 252478/371472 [9:02:30<8:47:34,  3.76it/s]
 68%|██████▊   | 252479/371472 [9:02:30<8:52:58,  3.72it/s]
 68%|██████▊   | 252480/371472 [9:02:30<9:13:40,  3.58it/s]
                                                           
{'loss': 2.7395, 'learning_rate': 3.884483613092288e-07, 'epoch': 10.87}
+
 68%|██████▊   | 252480/371472 [9:02:30<9:13:40,  3.58it/s]
 68%|██████▊   | 252481/371472 [9:02:30<9:21:24,  3.53it/s]
 68%|██████▊   | 252482/371472 [9:02:31<9:07:20,  3.62it/s]
 68%|██████▊   | 252483/371472 [9:02:31<8:49:01,  3.75it/s]
 68%|██████▊   | 252484/371472 [9:02:31<8:32:08,  3.87it/s]
 68%|██████▊   | 252485/371472 [9:02:31<8:55:59,  3.70it/s]
 68%|██████▊   | 252486/371472 [9:02:32<8:41:14,  3.80it/s]
 68%|██████▊   | 252487/371472 [9:02:32<8:31:38,  3.88it/s]
 68%|██████▊   | 252488/371472 [9:02:32<8:48:34,  3.75it/s]
 68%|██████▊   | 252489/371472 [9:02:32<8:50:11,  3.74it/s]
 68%|██████▊   | 252490/371472 [9:02:33<9:05:14,  3.64it/s]
 68%|██████▊   | 252491/371472 [9:02:33<8:58:25,  3.68it/s]
 68%|██████▊   | 252492/371472 [9:02:33<9:15:01,  3.57it/s]
 68%|██████▊   | 252493/371472 [9:02:34<9:12:14,  3.59it/s]
 68%|██████▊   | 252494/371472 [9:02:34<8:56:12,  3.70it/s]
 68%|██████▊   | 252495/371472 [9:02:34<9:11:49,  3.59it/s]
 68%|██████▊   | 252496/371472 [9:02:34<8:53:01,  3.72it/s]
 68%|██████▊   | 252497/371472 [9:02:35<9:27:07,  3.50it/s]
 68%|██████▊   | 252498/371472 [9:02:35<9:14:48,  3.57it/s]
 68%|██████▊   | 252499/371472 [9:02:35<9:15:02,  3.57it/s]
 68%|██████▊   | 252500/371472 [9:02:36<9:11:29,  3.60it/s]
                                                           
{'loss': 2.9258, 'learning_rate': 3.8839987933374993e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252500/371472 [9:02:36<9:11:29,  3.60it/s]
 68%|██████▊   | 252501/371472 [9:02:36<9:08:45,  3.61it/s]
 68%|██████▊   | 252502/371472 [9:02:36<9:18:43,  3.55it/s]
 68%|██████▊   | 252503/371472 [9:02:36<9:37:28,  3.43it/s]
 68%|██████▊   | 252504/371472 [9:02:37<9:14:21,  3.58it/s]
 68%|██████▊   | 252505/371472 [9:02:37<9:14:35,  3.58it/s]
 68%|██████▊   | 252506/371472 [9:02:37<8:59:16,  3.68it/s]
 68%|██████▊   | 252507/371472 [9:02:37<8:52:33,  3.72it/s]
 68%|██████▊   | 252508/371472 [9:02:38<8:57:24,  3.69it/s]
 68%|██████▊   | 252509/371472 [9:02:38<8:48:12,  3.75it/s]
 68%|██████▊   | 252510/371472 [9:02:38<8:57:17,  3.69it/s]
 68%|██████▊   | 252511/371472 [9:02:39<9:04:11,  3.64it/s]
 68%|██████▊   | 252512/371472 [9:02:39<9:05:26,  3.64it/s]
 68%|██████▊   | 252513/371472 [9:02:39<8:48:42,  3.75it/s]
 68%|██████▊   | 252514/371472 [9:02:39<8:40:40,  3.81it/s]
 68%|██████▊   | 252515/371472 [9:02:40<8:35:36,  3.85it/s]
 68%|██████▊   | 252516/371472 [9:02:40<9:20:53,  3.53it/s]
 68%|██████▊   | 252517/371472 [9:02:40<9:00:00,  3.67it/s]
 68%|██████▊   | 252518/371472 [9:02:40<8:41:49,  3.80it/s]
 68%|██████▊   | 252519/371472 [9:02:41<8:45:06,  3.78it/s]
 68%|██████▊   | 252520/371472 [9:02:41<8:35:03,  3.85it/s]
                                                           
{'loss': 3.0228, 'learning_rate': 3.8835139735827105e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252520/371472 [9:02:41<8:35:03,  3.85it/s]
 68%|██████▊   | 252521/371472 [9:02:41<8:20:25,  3.96it/s]
 68%|██████▊   | 252522/371472 [9:02:41<8:26:22,  3.92it/s]
 68%|██████▊   | 252523/371472 [9:02:42<8:49:31,  3.74it/s]
 68%|██████▊   | 252524/371472 [9:02:42<9:02:09,  3.66it/s]
 68%|██████▊   | 252525/371472 [9:02:42<9:17:32,  3.56it/s]
 68%|██████▊   | 252526/371472 [9:02:43<9:29:02,  3.48it/s]
 68%|██████▊   | 252527/371472 [9:02:43<9:38:02,  3.43it/s]
 68%|██████▊   | 252528/371472 [9:02:43<9:27:21,  3.49it/s]
 68%|██████▊   | 252529/371472 [9:02:43<9:16:23,  3.56it/s]
 68%|██████▊   | 252530/371472 [9:02:44<8:50:09,  3.74it/s]
 68%|██████▊   | 252531/371472 [9:02:44<8:49:47,  3.74it/s]
 68%|██████▊   | 252532/371472 [9:02:44<8:50:29,  3.74it/s]
 68%|██████▊   | 252533/371472 [9:02:44<8:40:17,  3.81it/s]
 68%|██████▊   | 252534/371472 [9:02:45<8:55:06,  3.70it/s]
 68%|██████▊   | 252535/371472 [9:02:45<8:41:37,  3.80it/s]
 68%|██████▊   | 252536/371472 [9:02:45<8:47:22,  3.76it/s]
 68%|██████▊   | 252537/371472 [9:02:46<8:41:12,  3.80it/s]
 68%|██████▊   | 252538/371472 [9:02:46<8:43:47,  3.78it/s]
 68%|██████▊   | 252539/371472 [9:02:46<8:46:12,  3.77it/s]
 68%|██████▊   | 252540/371472 [9:02:46<8:47:22,  3.76it/s]
                                                           
{'loss': 2.8839, 'learning_rate': 3.8830291538279207e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252540/371472 [9:02:46<8:47:22,  3.76it/s]
 68%|██████▊   | 252541/371472 [9:02:47<10:15:55,  3.22it/s]
 68%|██████▊   | 252542/371472 [9:02:47<9:52:19,  3.35it/s] 
 68%|██████▊   | 252543/371472 [9:02:47<9:33:17,  3.46it/s]
 68%|██████▊   | 252544/371472 [9:02:48<9:11:47,  3.59it/s]
 68%|██████▊   | 252545/371472 [9:02:48<9:18:06,  3.55it/s]
 68%|██████▊   | 252546/371472 [9:02:48<9:41:08,  3.41it/s]
 68%|██████▊   | 252547/371472 [9:02:48<9:06:57,  3.62it/s]
 68%|██████▊   | 252548/371472 [9:02:49<8:49:38,  3.74it/s]
 68%|██████▊   | 252549/371472 [9:02:49<8:39:20,  3.82it/s]
 68%|██████▊   | 252550/371472 [9:02:49<8:31:39,  3.87it/s]
 68%|██████▊   | 252551/371472 [9:02:49<8:45:50,  3.77it/s]
 68%|██████▊   | 252552/371472 [9:02:50<9:06:47,  3.62it/s]
 68%|██████▊   | 252553/371472 [9:02:50<9:08:53,  3.61it/s]
 68%|██████▊   | 252554/371472 [9:02:50<10:04:01,  3.28it/s]
 68%|██████▊   | 252555/371472 [9:02:51<9:56:10,  3.32it/s] 
 68%|██████▊   | 252556/371472 [9:02:51<9:26:05,  3.50it/s]
 68%|██████▊   | 252557/371472 [9:02:51<9:23:15,  3.52it/s]
 68%|██████▊   | 252558/371472 [9:02:52<9:35:26,  3.44it/s]
 68%|████��█▊   | 252559/371472 [9:02:52<11:07:33,  2.97it/s]
 68%|██████▊   | 252560/371472 [9:02:52<10:38:46,  3.10it/s]
                                                            
{'loss': 3.0869, 'learning_rate': 3.8825443340731325e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252560/371472 [9:02:52<10:38:46,  3.10it/s]
 68%|██████▊   | 252561/371472 [9:02:53<10:11:14,  3.24it/s]
 68%|██████▊   | 252562/371472 [9:02:53<10:00:40,  3.30it/s]
 68%|██████▊   | 252563/371472 [9:02:53<9:41:36,  3.41it/s] 
 68%|██████▊   | 252564/371472 [9:02:53<9:15:34,  3.57it/s]
 68%|██████▊   | 252565/371472 [9:02:54<8:58:01,  3.68it/s]
 68%|██████▊   | 252566/371472 [9:02:54<9:38:34,  3.43it/s]
 68%|██████▊   | 252567/371472 [9:02:54<9:19:08,  3.54it/s]
 68%|██████▊   | 252568/371472 [9:02:54<9:41:38,  3.41it/s]
 68%|██████▊   | 252569/371472 [9:02:55<9:35:42,  3.44it/s]
 68%|██████▊   | 252570/371472 [9:02:55<9:10:41,  3.60it/s]
 68%|██████▊   | 252571/371472 [9:02:55<9:39:38,  3.42it/s]
 68%|██████▊   | 252572/371472 [9:02:56<9:33:19,  3.46it/s]
 68%|██████▊   | 252573/371472 [9:02:56<9:10:29,  3.60it/s]
 68%|██████▊   | 252574/371472 [9:02:56<8:51:25,  3.73it/s]
 68%|██████▊   | 252575/371472 [9:02:56<8:44:38,  3.78it/s]
 68%|██████▊   | 252576/371472 [9:02:57<8:43:57,  3.78it/s]
 68%|██████▊   | 252577/371472 [9:02:57<9:29:09,  3.48it/s]
 68%|██████▊   | 252578/371472 [9:02:57<9:07:00,  3.62it/s]
 68%|██████▊   | 252579/371472 [9:02:57<8:54:53,  3.70it/s]
 68%|██████▊   | 252580/371472 [9:02:58<10:28:06,  3.15it/s]
                                                            
{'loss': 2.6797, 'learning_rate': 3.882059514318343e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252580/371472 [9:02:58<10:28:06,  3.15it/s]
 68%|██████▊   | 252581/371472 [9:02:58<10:06:40,  3.27it/s]
 68%|██████▊   | 252582/371472 [9:02:58<9:29:55,  3.48it/s] 
 68%|██████▊   | 252583/371472 [9:02:59<9:21:18,  3.53it/s]
 68%|██████▊   | 252584/371472 [9:02:59<8:54:24,  3.71it/s]
 68%|██████▊   | 252585/371472 [9:02:59<8:53:23,  3.71it/s]
 68%|██████▊   | 252586/371472 [9:02:59<8:47:41,  3.75it/s]
 68%|██████▊   | 252587/371472 [9:03:00<8:54:04,  3.71it/s]
 68%|██████▊   | 252588/371472 [9:03:00<9:20:10,  3.54it/s]
 68%|██████▊   | 252589/371472 [9:03:00<9:11:27,  3.59it/s]
 68%|██████▊   | 252590/371472 [9:03:01<9:09:33,  3.61it/s]
 68%|██████▊   | 252591/371472 [9:03:01<8:52:37,  3.72it/s]
 68%|██████▊   | 252592/371472 [9:03:01<8:51:53,  3.73it/s]
 68%|██████▊   | 252593/371472 [9:03:01<8:54:24,  3.71it/s]
 68%|██████▊   | 252594/371472 [9:03:02<8:55:12,  3.70it/s]
 68%|██████▊   | 252595/371472 [9:03:02<9:18:31,  3.55it/s]
 68%|██████▊   | 252596/371472 [9:03:02<9:28:52,  3.48it/s]
 68%|██████▊   | 252597/371472 [9:03:03<9:23:14,  3.52it/s]
 68%|██████▊   | 252598/371472 [9:03:03<9:22:34,  3.52it/s]
 68%|██████▊   | 252599/371472 [9:03:03<9:00:57,  3.66it/s]
 68%|██████▊   | 252600/371472 [9:03:03<8:47:21,  3.76it/s]
                                                           
{'loss': 2.7581, 'learning_rate': 3.8815746945635544e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252600/371472 [9:03:03<8:47:21,  3.76it/s]
 68%|██████▊   | 252601/371472 [9:03:04<8:48:38,  3.75it/s]
 68%|██████▊   | 252602/371472 [9:03:04<8:48:36,  3.75it/s]
 68%|██████▊   | 252603/371472 [9:03:04<8:59:24,  3.67it/s]
 68%|██████▊   | 252604/371472 [9:03:04<8:47:27,  3.76it/s]
 68%|██████▊   | 252605/371472 [9:03:05<8:37:13,  3.83it/s]
 68%|██████▊   | 252606/371472 [9:03:05<9:01:34,  3.66it/s]
 68%|██████▊   | 252607/371472 [9:03:05<9:03:41,  3.64it/s]
 68%|██████▊   | 252608/371472 [9:03:06<9:06:32,  3.62it/s]
 68%|██████▊   | 252609/371472 [9:03:06<9:03:06,  3.65it/s]
 68%|██████▊   | 252610/371472 [9:03:06<9:29:47,  3.48it/s]
 68%|██████▊   | 252611/371472 [9:03:06<9:02:02,  3.65it/s]
 68%|██████▊   | 252612/371472 [9:03:07<9:08:32,  3.61it/s]
 68%|██████▊   | 252613/371472 [9:03:07<9:03:25,  3.65it/s]
 68%|██████▊   | 252614/371472 [9:03:07<8:50:28,  3.73it/s]
 68%|██████▊   | 252615/371472 [9:03:07<8:44:40,  3.78it/s]
 68%|██████▊   | 252616/371472 [9:03:08<8:40:19,  3.81it/s]
 68%|██████▊   | 252617/371472 [9:03:08<9:27:36,  3.49it/s]
 68%|██████▊   | 252618/371472 [9:03:08<9:25:19,  3.50it/s]
 68%|██████▊   | 252619/371472 [9:03:09<9:05:51,  3.63it/s]
 68%|██████▊   | 252620/371472 [9:03:09<9:03:54,  3.64it/s]
                                                           
{'loss': 2.7613, 'learning_rate': 3.881089874808765e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252620/371472 [9:03:09<9:03:54,  3.64it/s]
 68%|██████▊   | 252621/371472 [9:03:09<8:55:26,  3.70it/s]
 68%|██████▊   | 252622/371472 [9:03:09<8:36:23,  3.84it/s]
 68%|██████▊   | 252623/371472 [9:03:10<8:43:48,  3.78it/s]
 68%|██████▊   | 252624/371472 [9:03:10<8:59:14,  3.67it/s]
 68%|██████▊   | 252625/371472 [9:03:10<8:49:23,  3.74it/s]
 68%|██████▊   | 252626/371472 [9:03:10<9:12:20,  3.59it/s]
 68%|██████▊   | 252627/371472 [9:03:11<9:05:01,  3.63it/s]
 68%|██████▊   | 252628/371472 [9:03:11<9:22:01,  3.52it/s]
 68%|██████▊   | 252629/371472 [9:03:11<8:51:57,  3.72it/s]
 68%|██████▊   | 252630/371472 [9:03:12<9:02:06,  3.65it/s]
 68%|██████▊   | 252631/371472 [9:03:12<9:08:32,  3.61it/s]
 68%|██████▊   | 252632/371472 [9:03:12<9:27:09,  3.49it/s]
 68%|██████▊   | 252633/371472 [9:03:12<9:44:35,  3.39it/s]
 68%|██████▊   | 252634/371472 [9:03:13<9:30:57,  3.47it/s]
 68%|██████▊   | 252635/371472 [9:03:13<9:30:23,  3.47it/s]
 68%|██████▊   | 252636/371472 [9:03:13<8:55:00,  3.70it/s]
 68%|██████▊   | 252637/371472 [9:03:13<8:46:51,  3.76it/s]
 68%|██████▊   | 252638/371472 [9:03:14<9:24:15,  3.51it/s]
 68%|██████▊   | 252639/371472 [9:03:14<8:59:52,  3.67it/s]
 68%|██████▊   | 252640/371472 [9:03:14<8:50:24,  3.73it/s]
                                                           
{'loss': 2.8487, 'learning_rate': 3.880605055053977e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252640/371472 [9:03:14<8:50:24,  3.73it/s]
 68%|██████▊   | 252641/371472 [9:03:15<9:01:44,  3.66it/s]
 68%|██████▊   | 252642/371472 [9:03:15<8:58:55,  3.67it/s]
 68%|██████▊   | 252643/371472 [9:03:15<9:11:54,  3.59it/s]
 68%|██████▊   | 252644/371472 [9:03:15<8:57:15,  3.69it/s]
 68%|██████▊   | 252645/371472 [9:03:16<9:23:24,  3.52it/s]
 68%|██████▊   | 252646/371472 [9:03:16<9:05:15,  3.63it/s]
 68%|██████▊   | 252647/371472 [9:03:16<9:19:27,  3.54it/s]
 68%|██████▊   | 252648/371472 [9:03:17<10:10:32,  3.24it/s]
 68%|██████▊   | 252649/371472 [9:03:17<9:51:03,  3.35it/s] 
 68%|██████▊   | 252650/371472 [9:03:17<9:36:33,  3.43it/s]
 68%|██████▊   | 252651/371472 [9:03:17<9:18:00,  3.55it/s]
 68%|██████▊   | 252652/371472 [9:03:18<8:59:09,  3.67it/s]
 68%|██████▊   | 252653/371472 [9:03:18<8:39:31,  3.81it/s]
 68%|██████▊   | 252654/371472 [9:03:18<8:43:32,  3.78it/s]
 68%|██████▊   | 252655/371472 [9:03:19<9:11:17,  3.59it/s]
 68%|██████▊   | 252656/371472 [9:03:19<8:51:38,  3.72it/s]
 68%|██████▊   | 252657/371472 [9:03:19<8:41:14,  3.80it/s]
 68%|██████▊   | 252658/371472 [9:03:19<8:52:53,  3.72it/s]
 68%|██████▊   | 252659/371472 [9:03:20<8:47:20,  3.76it/s]
 68%|██████▊   | 252660/371472 [9:03:20<8:53:42,  3.71it/s]
                                                           
{'loss': 2.8303, 'learning_rate': 3.880120235299187e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252660/371472 [9:03:20<8:53:42,  3.71it/s]
 68%|██████▊   | 252661/371472 [9:03:20<8:57:25,  3.68it/s]
 68%|██████▊   | 252662/371472 [9:03:20<8:50:33,  3.73it/s]
 68%|██████▊   | 252663/371472 [9:03:21<8:33:05,  3.86it/s]
 68%|██████▊   | 252664/371472 [9:03:21<9:16:56,  3.56it/s]
 68%|██████▊   | 252665/371472 [9:03:21<9:03:53,  3.64it/s]
 68%|██████▊   | 252666/371472 [9:03:21<8:53:50,  3.71it/s]
 68%|██████▊   | 252667/371472 [9:03:22<8:43:19,  3.78it/s]
 68%|██████▊   | 252668/371472 [9:03:22<8:32:35,  3.86it/s]
 68%|██████▊   | 252669/371472 [9:03:22<8:47:12,  3.76it/s]
 68%|██████▊   | 252670/371472 [9:03:23<9:10:50,  3.59it/s]
 68%|██████▊   | 252671/371472 [9:03:23<8:59:42,  3.67it/s]
 68%|██████▊   | 252672/371472 [9:03:23<8:48:47,  3.74it/s]
 68%|██████▊   | 252673/371472 [9:03:23<8:27:20,  3.90it/s]
 68%|██████▊   | 252674/371472 [9:03:24<8:49:44,  3.74it/s]
 68%|██████▊   | 252675/371472 [9:03:24<8:41:02,  3.80it/s]
 68%|██████▊   | 252676/371472 [9:03:24<9:06:19,  3.62it/s]
 68%|██████▊   | 252677/371472 [9:03:24<8:37:30,  3.83it/s]
 68%|██████▊   | 252678/371472 [9:03:25<8:36:06,  3.84it/s]
 68%|██████▊   | 252679/371472 [9:03:25<8:36:34,  3.83it/s]
 68%|██████▊   | 252680/371472 [9:03:25<9:03:23,  3.64it/s]
                                                           
{'loss': 2.8159, 'learning_rate': 3.879635415544399e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252680/371472 [9:03:25<9:03:23,  3.64it/s]
 68%|██████▊   | 252681/371472 [9:03:25<8:51:06,  3.73it/s]
 68%|██████▊   | 252682/371472 [9:03:26<8:41:45,  3.79it/s]
 68%|██████▊   | 252683/371472 [9:03:26<9:16:34,  3.56it/s]
 68%|██████▊   | 252684/371472 [9:03:26<9:08:44,  3.61it/s]
 68%|██████▊   | 252685/371472 [9:03:27<8:51:28,  3.73it/s]
 68%|██████▊   | 252686/371472 [9:03:27<9:03:41,  3.64it/s]
 68%|██████▊   | 252687/371472 [9:03:27<9:14:47,  3.57it/s]
 68%|██████▊   | 252688/371472 [9:03:27<9:16:25,  3.56it/s]
 68%|██████▊   | 252689/371472 [9:03:28<8:57:42,  3.68it/s]
 68%|██████▊   | 252690/371472 [9:03:28<8:48:37,  3.74it/s]
 68%|██████▊   | 252691/371472 [9:03:28<8:46:33,  3.76it/s]
 68%|██████▊   | 252692/371472 [9:03:28<8:37:20,  3.83it/s]
 68%|██████▊   | 252693/371472 [9:03:29<9:24:09,  3.51it/s]
 68%|██████▊   | 252694/371472 [9:03:29<9:46:34,  3.37it/s]
 68%|██████▊   | 252695/371472 [9:03:29<9:26:11,  3.50it/s]
 68%|██████▊   | 252696/371472 [9:03:30<9:40:25,  3.41it/s]
 68%|██████▊   | 252697/371472 [9:03:30<9:11:30,  3.59it/s]
 68%|██████▊   | 252698/371472 [9:03:30<9:16:23,  3.56it/s]
 68%|██████▊   | 252699/371472 [9:03:31<9:26:06,  3.50it/s]
 68%|██████▊   | 252700/371472 [9:03:31<9:30:31,  3.47it/s]
                                                           
{'loss': 2.9024, 'learning_rate': 3.8791505957896096e-07, 'epoch': 10.88}
+
 68%|██████▊   | 252700/371472 [9:03:31<9:30:31,  3.47it/s]
 68%|██████▊   | 252701/371472 [9:03:31<9:25:14,  3.50it/s]
 68%|██████▊   | 252702/371472 [9:03:31<9:29:13,  3.48it/s]
 68%|██████▊   | 252703/371472 [9:03:32<9:33:55,  3.45it/s]
 68%|██████▊   | 252704/371472 [9:03:32<9:20:05,  3.53it/s]
 68%|██████▊   | 252705/371472 [9:03:32<9:31:15,  3.47it/s]
 68%|██████▊   | 252706/371472 [9:03:32<9:03:14,  3.64it/s]
 68%|██████▊   | 252707/371472 [9:03:33<8:44:46,  3.77it/s]
 68%|██████▊   | 252708/371472 [9:03:33<8:36:34,  3.83it/s]
 68%|██████▊   | 252709/371472 [9:03:33<8:49:51,  3.74it/s]
 68%|██████▊   | 252710/371472 [9:03:34<8:45:20,  3.77it/s]
 68%|██████▊   | 252711/371472 [9:03:34<9:08:13,  3.61it/s]
 68%|██████▊   | 252712/371472 [9:03:34<10:11:22,  3.24it/s]
 68%|██████▊   | 252713/371472 [9:03:34<9:37:23,  3.43it/s] 
 68%|██████▊   | 252714/371472 [9:03:35<9:46:38,  3.37it/s]
 68%|██████▊   | 252715/371472 [9:03:35<9:17:02,  3.55it/s]
 68%|██████▊   | 252716/371472 [9:03:35<9:14:15,  3.57it/s]
 68%|██████▊   | 252717/371472 [9:03:36<8:50:50,  3.73it/s]
 68%|██████▊   | 252718/371472 [9:03:36<9:21:14,  3.53it/s]
 68%|██████▊   | 252719/371472 [9:03:36<10:06:37,  3.26it/s]
 68%|██████▊   | 252720/371472 [9:03:37<10:10:44,  3.24it/s]
                                                            
{'loss': 2.7674, 'learning_rate': 3.878665776034821e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252720/371472 [9:03:37<10:10:44,  3.24it/s]
 68%|██████▊   | 252721/371472 [9:03:37<10:04:09,  3.28it/s]
 68%|██████▊   | 252722/371472 [9:03:37<9:45:14,  3.38it/s] 
 68%|██████▊   | 252723/371472 [9:03:37<9:56:46,  3.32it/s]
 68%|██████▊   | 252724/371472 [9:03:38<9:58:56,  3.30it/s]
 68%|██████▊   | 252725/371472 [9:03:38<9:31:50,  3.46it/s]
 68%|██████▊   | 252726/371472 [9:03:38<9:44:49,  3.38it/s]
 68%|██████▊   | 252727/371472 [9:03:39<10:04:26,  3.27it/s]
 68%|██████▊   | 252728/371472 [9:03:39<9:45:25,  3.38it/s] 
 68%|██████▊   | 252729/371472 [9:03:39<9:28:38,  3.48it/s]
 68%|██████▊   | 252730/371472 [9:03:39<9:15:06,  3.57it/s]
 68%|██████▊   | 252731/371472 [9:03:40<8:47:33,  3.75it/s]
 68%|██████▊   | 252732/371472 [9:03:40<8:43:12,  3.78it/s]
 68%|██████▊   | 252733/371472 [9:03:40<9:25:07,  3.50it/s]
 68%|██████▊   | 252734/371472 [9:03:40<9:02:33,  3.65it/s]
 68%|██████▊   | 252735/371472 [9:03:41<8:42:19,  3.79it/s]
 68%|██████▊   | 252736/371472 [9:03:41<8:31:23,  3.87it/s]
 68%|██████▊   | 252737/371472 [9:03:41<8:34:28,  3.85it/s]
 68%|██████▊   | 252738/371472 [9:03:42<9:13:47,  3.57it/s]
 68%|██████▊   | 252739/371472 [9:03:42<8:50:08,  3.73it/s]
 68%|██████▊   | 252740/371472 [9:03:42<8:42:09,  3.79it/s]
                                                           
{'loss': 3.0725, 'learning_rate': 3.8781809562800316e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252740/371472 [9:03:42<8:42:09,  3.79it/s]
 68%|██████▊   | 252741/371472 [9:03:42<8:31:48,  3.87it/s]
 68%|██████▊   | 252742/371472 [9:03:43<8:25:18,  3.92it/s]
 68%|██████▊   | 252743/371472 [9:03:43<8:49:03,  3.74it/s]
 68%|██████▊   | 252744/371472 [9:03:43<9:01:45,  3.65it/s]
 68%|██████▊   | 252745/371472 [9:03:43<8:39:52,  3.81it/s]
 68%|██████▊   | 252746/371472 [9:03:44<8:45:50,  3.76it/s]
 68%|██████▊   | 252747/371472 [9:03:44<9:44:44,  3.38it/s]
 68%|██████▊   | 252748/371472 [9:03:44<9:20:29,  3.53it/s]
 68%|██████▊   | 252749/371472 [9:03:45<10:05:33,  3.27it/s]
 68%|██████▊   | 252750/371472 [9:03:45<9:53:52,  3.33it/s] 
 68%|██████▊   | 252751/371472 [9:03:45<9:49:06,  3.36it/s]
 68%|██████▊   | 252752/371472 [9:03:46<9:56:31,  3.32it/s]
 68%|██████▊   | 252753/371472 [9:03:46<9:47:02,  3.37it/s]
 68%|██████▊   | 252754/371472 [9:03:46<9:21:39,  3.52it/s]
 68%|██████▊   | 252755/371472 [9:03:46<9:16:00,  3.56it/s]
 68%|██████▊   | 252756/371472 [9:03:47<9:44:56,  3.38it/s]
 68%|██████▊   | 252757/371472 [9:03:47<9:17:45,  3.55it/s]
 68%|██████▊   | 252758/371472 [9:03:47<8:48:15,  3.75it/s]
 68%|██████▊   | 252759/371472 [9:03:47<9:22:27,  3.52it/s]
 68%|██████▊   | 252760/371472 [9:03:48<9:01:06,  3.66it/s]
                                                           
{'loss': 2.8202, 'learning_rate': 3.877696136525243e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252760/371472 [9:03:48<9:01:06,  3.66it/s]
 68%|██████▊   | 252761/371472 [9:03:48<9:05:44,  3.63it/s]
 68%|██████▊   | 252762/371472 [9:03:48<9:40:42,  3.41it/s]
 68%|██████▊   | 252763/371472 [9:03:49<9:30:36,  3.47it/s]
 68%|██████▊   | 252764/371472 [9:03:49<9:22:10,  3.52it/s]
 68%|██████▊   | 252765/371472 [9:03:49<9:00:48,  3.66it/s]
 68%|██████▊   | 252766/371472 [9:03:49<9:04:13,  3.64it/s]
 68%|██████▊   | 252767/371472 [9:03:50<9:34:45,  3.44it/s]
 68%|██████▊   | 252768/371472 [9:03:50<9:08:55,  3.60it/s]
 68%|██████▊   | 252769/371472 [9:03:50<8:55:19,  3.70it/s]
 68%|██████▊   | 252770/371472 [9:03:51<9:11:40,  3.59it/s]
 68%|██████▊   | 252771/371472 [9:03:51<9:22:10,  3.52it/s]
 68%|██████▊   | 252772/371472 [9:03:51<9:45:32,  3.38it/s]
 68%|██████▊   | 252773/371472 [9:03:51<9:59:20,  3.30it/s]
 68%|██████▊   | 252774/371472 [9:03:52<10:17:44,  3.20it/s]
 68%|██████▊   | 252775/371472 [9:03:52<10:29:22,  3.14it/s]
 68%|██████▊   | 252776/371472 [9:03:53<10:50:42,  3.04it/s]
 68%|██████▊   | 252777/371472 [9:03:53<10:44:01,  3.07it/s]
 68%|██████▊   | 252778/371472 [9:03:53<10:02:53,  3.28it/s]
 68%|██████▊   | 252779/371472 [9:03:53<9:31:08,  3.46it/s] 
 68%|██████▊   | 252780/371472 [9:03:54<9:25:26,  3.50it/s]
                                                           
{'loss': 2.9157, 'learning_rate': 3.8772113167704535e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252780/371472 [9:03:54<9:25:26,  3.50it/s]
 68%|██████▊   | 252781/371472 [9:03:54<8:55:13,  3.70it/s]
 68%|██████▊   | 252782/371472 [9:03:54<9:51:08,  3.35it/s]
 68%|██████▊   | 252783/371472 [9:03:54<9:34:53,  3.44it/s]
 68%|██████▊   | 252784/371472 [9:03:55<9:27:23,  3.49it/s]
 68%|██████▊   | 252785/371472 [9:03:55<8:58:19,  3.67it/s]
 68%|██████▊   | 252786/371472 [9:03:55<9:00:00,  3.66it/s]
 68%|██████▊   | 252787/371472 [9:03:56<8:49:12,  3.74it/s]
 68%|██████▊   | 252788/371472 [9:03:56<8:51:25,  3.72it/s]
 68%|██████▊   | 252789/371472 [9:03:56<9:03:59,  3.64it/s]
 68%|██████▊   | 252790/371472 [9:03:56<9:10:51,  3.59it/s]
 68%|██████▊   | 252791/371472 [9:03:57<8:49:11,  3.74it/s]
 68%|██████▊   | 252792/371472 [9:03:57<9:13:06,  3.58it/s]
 68%|██████▊   | 252793/371472 [9:03:57<9:45:40,  3.38it/s]
 68%|██████▊   | 252794/371472 [9:03:58<9:28:28,  3.48it/s]
 68%|██████▊   | 252795/371472 [9:03:58<9:42:25,  3.40it/s]
 68%|██████▊   | 252796/371472 [9:03:58<9:11:42,  3.59it/s]
 68%|██████▊   | 252797/371472 [9:03:58<9:37:28,  3.43it/s]
 68%|██████▊   | 252798/371472 [9:03:59<9:16:28,  3.55it/s]
 68%|██████▊   | 252799/371472 [9:03:59<9:00:53,  3.66it/s]
 68%|██████▊   | 252800/371472 [9:03:59<8:56:00,  3.69it/s]
                                                           
{'loss': 2.7437, 'learning_rate': 3.8767264970156653e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252800/371472 [9:03:59<8:56:00,  3.69it/s]
 68%|██████▊   | 252801/371472 [9:03:59<9:00:52,  3.66it/s]
 68%|██████▊   | 252802/371472 [9:04:00<8:40:23,  3.80it/s]
 68%|██████▊   | 252803/371472 [9:04:00<9:51:22,  3.34it/s]
 68%|██████▊   | 252804/371472 [9:04:00<9:27:33,  3.48it/s]
 68%|██████▊   | 252805/371472 [9:04:01<9:23:19,  3.51it/s]
 68%|██████▊   | 252806/371472 [9:04:01<8:55:07,  3.70it/s]
 68%|██████▊   | 252807/371472 [9:04:01<9:03:15,  3.64it/s]
 68%|██████▊   | 252808/371472 [9:04:01<8:59:57,  3.66it/s]
 68%|██████▊   | 252809/371472 [9:04:02<8:55:13,  3.70it/s]
 68%|██████▊   | 252810/371472 [9:04:02<8:47:47,  3.75it/s]
 68%|██████▊   | 252811/371472 [9:04:02<9:41:26,  3.40it/s]
 68%|██████▊   | 252812/371472 [9:04:03<9:20:01,  3.53it/s]
 68%|██████▊   | 252813/371472 [9:04:03<9:10:26,  3.59it/s]
 68%|██████▊   | 252814/371472 [9:04:03<8:48:49,  3.74it/s]
 68%|██████▊   | 252815/371472 [9:04:03<8:48:10,  3.74it/s]
 68%|██████▊   | 252816/371472 [9:04:04<8:48:01,  3.75it/s]
 68%|██████▊   | 252817/371472 [9:04:04<8:36:19,  3.83it/s]
 68%|██████▊   | 252818/371472 [9:04:04<9:30:19,  3.47it/s]
 68%|██████▊   | 252819/371472 [9:04:04<9:07:58,  3.61it/s]
 68%|██████▊   | 252820/371472 [9:04:05<9:04:06,  3.63it/s]
                                                           
{'loss': 2.9591, 'learning_rate': 3.876241677260876e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252820/371472 [9:04:05<9:04:06,  3.63it/s]
 68%|██████▊   | 252821/371472 [9:04:05<9:18:14,  3.54it/s]
 68%|██████▊   | 252822/371472 [9:04:05<9:08:11,  3.61it/s]
 68%|██████▊   | 252823/371472 [9:04:06<9:09:18,  3.60it/s]
 68%|██████▊   | 252824/371472 [9:04:06<8:49:14,  3.74it/s]
 68%|██████▊   | 252825/371472 [9:04:06<9:30:51,  3.46it/s]
 68%|██████▊   | 252826/371472 [9:04:06<9:15:24,  3.56it/s]
 68%|██████▊   | 252827/371472 [9:04:07<8:58:15,  3.67it/s]
 68%|██████▊   | 252828/371472 [9:04:07<9:08:28,  3.61it/s]
 68%|██████▊   | 252829/371472 [9:04:07<8:56:42,  3.68it/s]
 68%|██████▊   | 252830/371472 [9:04:07<8:46:51,  3.75it/s]
 68%|██████▊   | 252831/371472 [9:04:08<8:21:18,  3.94it/s]
 68%|██████▊   | 252832/371472 [9:04:08<8:52:27,  3.71it/s]
 68%|██████▊   | 252833/371472 [9:04:08<9:03:56,  3.64it/s]
 68%|██████▊   | 252834/371472 [9:04:09<8:54:59,  3.70it/s]
 68%|██████▊   | 252835/371472 [9:04:09<9:16:45,  3.55it/s]
 68%|██████▊   | 252836/371472 [9:04:09<9:09:39,  3.60it/s]
 68%|██████▊   | 252837/371472 [9:04:09<9:07:44,  3.61it/s]
 68%|██████▊   | 252838/371472 [9:04:10<8:56:59,  3.68it/s]
 68%|██████▊   | 252839/371472 [9:04:10<9:09:21,  3.60it/s]
 68%|██████▊   | 252840/371472 [9:04:10<10:07:12,  3.26it/s]
                                                            
{'loss': 2.7014, 'learning_rate': 3.875756857506087e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252840/371472 [9:04:10<10:07:12,  3.26it/s]
 68%|██████▊   | 252841/371472 [9:04:11<9:41:43,  3.40it/s] 
 68%|██████▊   | 252842/371472 [9:04:11<9:14:31,  3.57it/s]
 68%|██████▊   | 252843/371472 [9:04:11<8:56:11,  3.69it/s]
 68%|██████▊   | 252844/371472 [9:04:11<10:21:25,  3.18it/s]
 68%|██████▊   | 252845/371472 [9:04:12<10:09:45,  3.24it/s]
 68%|██████▊   | 252846/371472 [9:04:12<9:48:35,  3.36it/s] 
 68%|██████▊   | 252847/371472 [9:04:12<10:15:57,  3.21it/s]
 68%|██████▊   | 252848/371472 [9:04:13<10:15:33,  3.21it/s]
 68%|██████▊   | 252849/371472 [9:04:13<10:43:20,  3.07it/s]
 68%|██████▊   | 252850/371472 [9:04:13<10:30:14,  3.14it/s]
 68%|██████▊   | 252851/371472 [9:04:14<10:09:01,  3.25it/s]
 68%|██████▊   | 252852/371472 [9:04:14<9:45:00,  3.38it/s] 
 68%|██████▊   | 252853/371472 [9:04:14<9:23:39,  3.51it/s]
 68%|██████▊   | 252854/371472 [9:04:14<9:07:50,  3.61it/s]
 68%|██████▊   | 252855/371472 [9:04:15<8:51:32,  3.72it/s]
 68%|██████▊   | 252856/371472 [9:04:15<8:45:35,  3.76it/s]
 68%|██████▊   | 252857/371472 [9:04:15<9:25:01,  3.50it/s]
 68%|██████▊   | 252858/371472 [9:04:16<10:06:17,  3.26it/s]
 68%|██████▊   | 252859/371472 [9:04:16<10:14:04,  3.22it/s]
 68%|██████▊   | 252860/371472 [9:04:16<9:40:57,  3.40it/s] 
                                                           
{'loss': 2.7922, 'learning_rate': 3.875272037751298e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252860/371472 [9:04:16<9:40:57,  3.40it/s]
 68%|██████▊   | 252861/371472 [9:04:16<9:19:44,  3.53it/s]
 68%|██████▊   | 252862/371472 [9:04:17<9:01:43,  3.65it/s]
 68%|██████▊   | 252863/371472 [9:04:17<10:41:33,  3.08it/s]
 68%|██████▊   | 252864/371472 [9:04:17<10:11:11,  3.23it/s]
 68%|██████▊   | 252865/371472 [9:04:18<10:31:43,  3.13it/s]
 68%|██████▊   | 252866/371472 [9:04:18<10:30:32,  3.14it/s]
 68%|██████▊   | 252867/371472 [9:04:18<9:57:30,  3.31it/s] 
 68%|██████▊   | 252868/371472 [9:04:19<9:38:50,  3.41it/s]
 68%|██████▊   | 252869/371472 [9:04:19<9:19:47,  3.53it/s]
 68%|██████▊   | 252870/371472 [9:04:19<8:50:45,  3.72it/s]
 68%|██████▊   | 252871/371472 [9:04:19<8:36:33,  3.83it/s]
 68%|██████▊   | 252872/371472 [9:04:20<8:32:24,  3.86it/s]
 68%|██████▊   | 252873/371472 [9:04:20<8:22:41,  3.93it/s]
 68%|██████▊   | 252874/371472 [9:04:20<8:52:22,  3.71it/s]
 68%|██████▊   | 252875/371472 [9:04:20<8:53:58,  3.70it/s]
 68%|██████▊   | 252876/371472 [9:04:21<8:44:14,  3.77it/s]
 68%|██████▊   | 252877/371472 [9:04:21<8:41:29,  3.79it/s]
 68%|██████▊   | 252878/371472 [9:04:21<8:30:40,  3.87it/s]
 68%|██████▊   | 252879/371472 [9:04:21<8:33:15,  3.85it/s]
 68%|██████▊   | 252880/371472 [9:04:22<8:39:29,  3.80it/s]
                                                           
{'loss': 2.9765, 'learning_rate': 3.8747872179965087e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252880/371472 [9:04:22<8:39:29,  3.80it/s]
 68%|██████▊   | 252881/371472 [9:04:22<8:55:52,  3.69it/s]
 68%|██████▊   | 252882/371472 [9:04:22<8:59:09,  3.67it/s]
 68%|██████▊   | 252883/371472 [9:04:23<9:09:51,  3.59it/s]
 68%|██████▊   | 252884/371472 [9:04:23<9:03:22,  3.64it/s]
 68%|██████▊   | 252885/371472 [9:04:23<9:08:23,  3.60it/s]
 68%|██████▊   | 252886/371472 [9:04:23<9:03:55,  3.63it/s]
 68%|██████▊   | 252887/371472 [9:04:24<9:08:26,  3.60it/s]
 68%|██████▊   | 252888/371472 [9:04:24<8:53:47,  3.70it/s]
 68%|██████▊   | 252889/371472 [9:04:24<8:40:23,  3.80it/s]
 68%|██████▊   | 252890/371472 [9:04:24<8:26:04,  3.91it/s]
 68%|██████▊   | 252891/371472 [9:04:25<9:20:37,  3.53it/s]
 68%|██████▊   | 252892/371472 [9:04:25<9:54:49,  3.32it/s]
 68%|██████▊   | 252893/371472 [9:04:25<10:32:41,  3.12it/s]
 68%|██████▊   | 252894/371472 [9:04:26<10:16:34,  3.21it/s]
 68%|██████▊   | 252895/371472 [9:04:26<9:52:21,  3.34it/s] 
 68%|██████▊   | 252896/371472 [9:04:26<9:16:18,  3.55it/s]
 68%|██████▊   | 252897/371472 [9:04:27<9:45:05,  3.38it/s]
 68%|██████▊   | 252898/371472 [9:04:27<9:32:20,  3.45it/s]
 68%|██████▊   | 252899/371472 [9:04:27<9:56:35,  3.31it/s]
 68%|██████▊   | 252900/371472 [9:04:27<9:29:10,  3.47it/s]
                                                           
{'loss': 2.7002, 'learning_rate': 3.8743023982417205e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252900/371472 [9:04:27<9:29:10,  3.47it/s]
 68%|██████▊   | 252901/371472 [9:04:28<9:45:29,  3.38it/s]
 68%|██████▊   | 252902/371472 [9:04:28<9:15:52,  3.56it/s]
 68%|██████▊   | 252903/371472 [9:04:28<9:17:19,  3.55it/s]
 68%|██████▊   | 252904/371472 [9:04:29<9:03:23,  3.64it/s]
 68%|██████▊   | 252905/371472 [9:04:29<9:01:10,  3.65it/s]
 68%|██████▊   | 252906/371472 [9:04:29<9:50:26,  3.35it/s]
 68%|██████▊   | 252907/371472 [9:04:30<10:03:37,  3.27it/s]
 68%|██████▊   | 252908/371472 [9:04:30<10:08:44,  3.25it/s]
 68%|██████▊   | 252909/371472 [9:04:30<10:59:18,  3.00it/s]
 68%|██████▊   | 252910/371472 [9:04:31<10:18:34,  3.19it/s]
 68%|██████▊   | 252911/371472 [9:04:31<9:53:37,  3.33it/s] 
 68%|██████▊   | 252912/371472 [9:04:31<9:25:52,  3.49it/s]
 68%|██████▊   | 252913/371472 [9:04:31<9:27:39,  3.48it/s]
 68%|██████▊   | 252914/371472 [9:04:32<9:17:10,  3.55it/s]
 68%|██████▊   | 252915/371472 [9:04:32<9:02:15,  3.64it/s]
 68%|██████▊   | 252916/371472 [9:04:32<8:50:55,  3.72it/s]
 68%|██████▊   | 252917/371472 [9:04:32<8:45:29,  3.76it/s]
 68%|██████▊   | 252918/371472 [9:04:33<8:45:03,  3.76it/s]
 68%|██████▊   | 252919/371472 [9:04:33<9:05:14,  3.62it/s]
 68%|██████▊   | 252920/371472 [9:04:33<8:58:50,  3.67it/s]
                                                           
{'loss': 2.8686, 'learning_rate': 3.8738175784869307e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252920/371472 [9:04:33<8:58:50,  3.67it/s]
 68%|██████▊   | 252921/371472 [9:04:33<8:57:31,  3.68it/s]
 68%|██████▊   | 252922/371472 [9:04:34<9:01:01,  3.65it/s]
 68%|██████▊   | 252923/371472 [9:04:34<8:50:48,  3.72it/s]
 68%|██████▊   | 252924/371472 [9:04:34<9:06:39,  3.61it/s]
 68%|██████▊   | 252925/371472 [9:04:35<8:53:16,  3.71it/s]
 68%|██████▊   | 252926/371472 [9:04:35<8:44:29,  3.77it/s]
 68%|██████▊   | 252927/371472 [9:04:35<8:40:26,  3.80it/s]
 68%|██████▊   | 252928/371472 [9:04:35<8:56:43,  3.68it/s]
 68%|██████▊   | 252929/371472 [9:04:36<9:05:43,  3.62it/s]
 68%|██████▊   | 252930/371472 [9:04:36<9:33:10,  3.45it/s]
 68%|██████▊   | 252931/371472 [9:04:36<9:09:42,  3.59it/s]
 68%|██████▊   | 252932/371472 [9:04:36<8:52:04,  3.71it/s]
 68%|██████▊   | 252933/371472 [9:04:37<8:39:12,  3.81it/s]
 68%|██████▊   | 252934/371472 [9:04:37<8:23:22,  3.92it/s]
 68%|██████▊   | 252935/371472 [9:04:37<8:39:20,  3.80it/s]
 68%|██████▊   | 252936/371472 [9:04:37<8:33:19,  3.85it/s]
 68%|██████▊   | 252937/371472 [9:04:38<8:17:27,  3.97it/s]
 68%|██████▊   | 252938/371472 [9:04:38<8:26:48,  3.90it/s]
 68%|██████▊   | 252939/371472 [9:04:38<8:48:07,  3.74it/s]
 68%|██████▊   | 252940/371472 [9:04:39<8:35:32,  3.83it/s]
                                                           
{'loss': 2.6365, 'learning_rate': 3.8733327587321424e-07, 'epoch': 10.89}
+
 68%|██████▊   | 252940/371472 [9:04:39<8:35:32,  3.83it/s]
 68%|██████▊   | 252941/371472 [9:04:39<9:01:09,  3.65it/s]
 68%|██████▊   | 252942/371472 [9:04:39<9:14:05,  3.57it/s]
 68%|██████▊   | 252943/371472 [9:04:39<8:43:00,  3.78it/s]
 68%|██████▊   | 252944/371472 [9:04:40<9:19:54,  3.53it/s]
 68%|██████▊   | 252945/371472 [9:04:40<9:34:54,  3.44it/s]
 68%|██████▊   | 252946/371472 [9:04:40<9:20:58,  3.52it/s]
 68%|██████▊   | 252947/371472 [9:04:41<9:03:43,  3.63it/s]
 68%|██████▊   | 252948/371472 [9:04:41<9:19:45,  3.53it/s]
 68%|██████▊   | 252949/371472 [9:04:41<9:55:35,  3.32it/s]
 68%|██████▊   | 252950/371472 [9:04:41<9:27:25,  3.48it/s]
 68%|██████▊   | 252951/371472 [9:04:42<10:00:12,  3.29it/s]
 68%|██████▊   | 252952/371472 [9:04:42<9:36:53,  3.42it/s] 
 68%|██████▊   | 252953/371472 [9:04:42<9:14:30,  3.56it/s]
 68%|██████▊   | 252954/371472 [9:04:43<9:06:27,  3.61it/s]
 68%|██████▊   | 252955/371472 [9:04:43<8:55:37,  3.69it/s]
 68%|██████▊   | 252956/371472 [9:04:43<9:01:09,  3.65it/s]
 68%|██████▊   | 252957/371472 [9:04:43<9:09:15,  3.60it/s]
 68%|██████▊   | 252958/371472 [9:04:44<9:27:34,  3.48it/s]
 68%|██████▊   | 252959/371472 [9:04:44<9:27:55,  3.48it/s]
 68%|██████▊   | 252960/371472 [9:04:44<9:28:16,  3.48it/s]
                                                           
{'loss': 2.8512, 'learning_rate': 3.872847938977353e-07, 'epoch': 10.9}
+
 68%|██████▊   | 252960/371472 [9:04:44<9:28:16,  3.48it/s]
 68%|██████▊   | 252961/371472 [9:04:45<9:31:29,  3.46it/s]
 68%|██████▊   | 252962/371472 [9:04:45<8:54:54,  3.69it/s]
 68%|██████▊   | 252963/371472 [9:04:45<8:59:44,  3.66it/s]
 68%|██████▊   | 252964/371472 [9:04:45<9:00:04,  3.66it/s]
 68%|██████▊   | 252965/371472 [9:04:46<8:34:11,  3.84it/s]
 68%|██████▊   | 252966/371472 [9:04:46<8:48:05,  3.74it/s]
 68%|██████▊   | 252967/371472 [9:04:46<9:52:50,  3.33it/s]
 68%|██████▊   | 252968/371472 [9:04:46<9:21:19,  3.52it/s]
 68%|██████▊   | 252969/371472 [9:04:47<9:06:47,  3.61it/s]
 68%|██████▊   | 252970/371472 [9:04:47<8:49:00,  3.73it/s]
 68%|██████▊   | 252971/371472 [9:04:47<8:44:09,  3.77it/s]
 68%|██████▊   | 252972/371472 [9:04:48<8:54:02,  3.70it/s]
 68%|██████▊   | 252973/371472 [9:04:48<8:36:48,  3.82it/s]
 68%|██████▊   | 252974/371472 [9:04:48<8:39:32,  3.80it/s]
 68%|██████▊   | 252975/371472 [9:04:48<8:34:05,  3.84it/s]
 68%|██████▊   | 252976/371472 [9:04:49<8:28:43,  3.88it/s]
 68%|██████▊   | 252977/371472 [9:04:49<9:25:20,  3.49it/s]
 68%|██████▊   | 252978/371472 [9:04:49<9:01:00,  3.65it/s]
 68%|██████▊   | 252979/371472 [9:04:50<10:47:27,  3.05it/s]
 68%|██████▊   | 252980/371472 [9:04:50<10:28:42,  3.14it/s]
                                                            
{'loss': 2.8822, 'learning_rate': 3.8723631192225644e-07, 'epoch': 10.9}
+
 68%|██████▊   | 252980/371472 [9:04:50<10:28:42,  3.14it/s]
 68%|██████▊   | 252981/371472 [9:04:50<10:07:53,  3.25it/s]
 68%|██████▊   | 252982/371472 [9:04:50<9:30:21,  3.46it/s] 
 68%|██████▊   | 252983/371472 [9:04:51<9:19:27,  3.53it/s]
 68%|██████▊   | 252984/371472 [9:04:51<8:57:28,  3.67it/s]
 68%|██████▊   | 252985/371472 [9:04:51<8:47:58,  3.74it/s]
 68%|██████▊   | 252986/371472 [9:04:51<8:40:38,  3.79it/s]
 68%|██████▊   | 252987/371472 [9:04:52<8:38:37,  3.81it/s]
 68%|██████▊   | 252988/371472 [9:04:52<8:32:22,  3.85it/s]
 68%|██████▊   | 252989/371472 [9:04:52<9:02:57,  3.64it/s]
 68%|██████▊   | 252990/371472 [9:04:53<9:21:08,  3.52it/s]
 68%|██████▊   | 252991/371472 [9:04:53<9:12:29,  3.57it/s]
 68%|██████▊   | 252992/371472 [9:04:53<8:57:18,  3.68it/s]
 68%|██████▊   | 252993/371472 [9:04:53<8:57:43,  3.67it/s]
 68%|██████▊   | 252994/371472 [9:04:54<9:07:43,  3.61it/s]
 68%|██████▊   | 252995/371472 [9:04:54<9:02:36,  3.64it/s]
 68%|██████▊   | 252996/371472 [9:04:54<8:55:09,  3.69it/s]
 68%|██████▊   | 252997/371472 [9:04:54<8:45:45,  3.76it/s]
 68%|██████▊   | 252998/371472 [9:04:55<8:48:00,  3.74it/s]
 68%|██████▊   | 252999/371472 [9:04:55<8:38:44,  3.81it/s]
 68%|██████▊   | 253000/371472 [9:04:55<8:26:35,  3.90it/s]
                                                           
{'loss': 2.8732, 'learning_rate': 3.871878299467775e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253000/371472 [9:04:55<8:26:35,  3.90it/s]
 68%|██████▊   | 253001/371472 [9:04:55<8:24:03,  3.92it/s]
 68%|██████▊   | 253002/371472 [9:04:56<9:00:18,  3.65it/s]
 68%|██████▊   | 253003/371472 [9:04:56<9:11:15,  3.58it/s]
 68%|██████▊   | 253004/371472 [9:04:56<9:30:05,  3.46it/s]
 68%|██████▊   | 253005/371472 [9:04:57<9:05:38,  3.62it/s]
 68%|██████▊   | 253006/371472 [9:04:57<9:00:49,  3.65it/s]
 68%|██████▊   | 253007/371472 [9:04:57<8:53:03,  3.70it/s]
 68%|██████▊   | 253008/371472 [9:04:57<8:45:26,  3.76it/s]
 68%|██████▊   | 253009/371472 [9:04:58<8:38:34,  3.81it/s]
 68%|██████▊   | 253010/371472 [9:04:58<8:46:51,  3.75it/s]
 68%|██████▊   | 253011/371472 [9:04:58<8:59:55,  3.66it/s]
 68%|██████▊   | 253012/371472 [9:04:59<9:14:11,  3.56it/s]
 68%|██████▊   | 253013/371472 [9:04:59<8:53:20,  3.70it/s]
 68%|██████▊   | 253014/371472 [9:04:59<9:00:18,  3.65it/s]
 68%|██████▊   | 253015/371472 [9:04:59<9:11:18,  3.58it/s]
 68%|██████▊   | 253016/371472 [9:05:00<8:47:27,  3.74it/s]
 68%|██████▊   | 253017/371472 [9:05:00<8:39:37,  3.80it/s]
 68%|██████▊   | 253018/371472 [9:05:00<8:33:31,  3.84it/s]
 68%|██████▊   | 253019/371472 [9:05:00<8:52:16,  3.71it/s]
 68%|██████▊   | 253020/371472 [9:05:01<8:54:52,  3.69it/s]
                                                           
{'loss': 2.8302, 'learning_rate': 3.871393479712987e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253020/371472 [9:05:01<8:54:52,  3.69it/s]
 68%|██████▊   | 253021/371472 [9:05:01<9:05:43,  3.62it/s]
 68%|██████▊   | 253022/371472 [9:05:01<8:57:21,  3.67it/s]
 68%|██████▊   | 253023/371472 [9:05:02<9:30:42,  3.46it/s]
 68%|██████▊   | 253024/371472 [9:05:02<9:35:27,  3.43it/s]
 68%|██████▊   | 253025/371472 [9:05:02<9:38:02,  3.42it/s]
 68%|██████▊   | 253026/371472 [9:05:02<9:25:42,  3.49it/s]
 68%|██████▊   | 253027/371472 [9:05:03<9:33:21,  3.44it/s]
 68%|██████▊   | 253028/371472 [9:05:03<9:51:48,  3.34it/s]
 68%|██████▊   | 253029/371472 [9:05:03<9:25:47,  3.49it/s]
 68%|██████▊   | 253030/371472 [9:05:04<9:14:49,  3.56it/s]
 68%|██████▊   | 253031/371472 [9:05:04<9:04:59,  3.62it/s]
 68%|██████▊   | 253032/371472 [9:05:04<9:00:14,  3.65it/s]
 68%|██████▊   | 253033/371472 [9:05:04<8:53:15,  3.70it/s]
 68%|██████▊   | 253034/371472 [9:05:05<8:55:39,  3.69it/s]
 68%|██████▊   | 253035/371472 [9:05:05<8:37:15,  3.82it/s]
 68%|██████▊   | 253036/371472 [9:05:05<8:58:33,  3.67it/s]
 68%|██████▊   | 253037/371472 [9:05:05<8:49:38,  3.73it/s]
 68%|██████▊   | 253038/371472 [9:05:06<9:28:16,  3.47it/s]
 68%|██████▊   | 253039/371472 [9:05:06<9:01:04,  3.65it/s]
 68%|██████▊   | 253040/371472 [9:05:06<9:38:01,  3.41it/s]
                                                           
{'loss': 2.7081, 'learning_rate': 3.870908659958197e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253040/371472 [9:05:06<9:38:01,  3.41it/s]
 68%|██████▊   | 253041/371472 [9:05:07<9:28:58,  3.47it/s]
 68%|██████▊   | 253042/371472 [9:05:07<9:27:26,  3.48it/s]
 68%|██████▊   | 253043/371472 [9:05:07<9:10:47,  3.58it/s]
 68%|██████▊   | 253044/371472 [9:05:07<9:28:48,  3.47it/s]
 68%|██████▊   | 253045/371472 [9:05:08<9:11:48,  3.58it/s]
 68%|██████▊   | 253046/371472 [9:05:08<9:14:53,  3.56it/s]
 68%|██████▊   | 253047/371472 [9:05:08<9:45:35,  3.37it/s]
 68%|██████▊   | 253048/371472 [9:05:09<9:41:26,  3.39it/s]
 68%|██████▊   | 253049/371472 [9:05:09<9:14:43,  3.56it/s]
 68%|██████▊   | 253050/371472 [9:05:09<9:11:54,  3.58it/s]
 68%|██████▊   | 253051/371472 [9:05:09<8:53:27,  3.70it/s]
 68%|██████▊   | 253052/371472 [9:05:10<8:41:45,  3.78it/s]
 68%|██████▊   | 253053/371472 [9:05:10<8:58:35,  3.66it/s]
 68%|██████▊   | 253054/371472 [9:05:10<9:44:39,  3.38it/s]
 68%|██████▊   | 253055/371472 [9:05:11<9:14:40,  3.56it/s]
 68%|██████▊   | 253056/371472 [9:05:11<9:06:59,  3.61it/s]
 68%|██████▊   | 253057/371472 [9:05:11<9:18:08,  3.54it/s]
 68%|██████▊   | 253058/371472 [9:05:11<9:17:36,  3.54it/s]
 68%|██████▊   | 253059/371472 [9:05:12<9:05:22,  3.62it/s]
 68%|██████▊   | 253060/371472 [9:05:12<8:51:00,  3.72it/s]
                                                           
{'loss': 2.7551, 'learning_rate': 3.870423840203409e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253060/371472 [9:05:12<8:51:00,  3.72it/s]
 68%|██████▊   | 253061/371472 [9:05:12<8:56:36,  3.68it/s]
 68%|██████▊   | 253062/371472 [9:05:12<8:52:53,  3.70it/s]
 68%|██████▊   | 253063/371472 [9:05:13<9:03:14,  3.63it/s]
 68%|██████▊   | 253064/371472 [9:05:13<8:59:28,  3.66it/s]
 68%|██████▊   | 253065/371472 [9:05:13<8:43:32,  3.77it/s]
 68%|██████▊   | 253066/371472 [9:05:14<9:06:29,  3.61it/s]
 68%|██████▊   | 253067/371472 [9:05:14<10:16:27,  3.20it/s]
 68%|██████▊   | 253068/371472 [9:05:14<10:09:18,  3.24it/s]
 68%|██████▊   | 253069/371472 [9:05:14<9:44:18,  3.38it/s] 
 68%|██████▊   | 253070/371472 [9:05:15<9:28:18,  3.47it/s]
 68%|██████▊   | 253071/371472 [9:05:15<9:14:44,  3.56it/s]
 68%|██████▊   | 253072/371472 [9:05:15<9:11:01,  3.58it/s]
 68%|██████▊   | 253073/371472 [9:05:16<9:53:46,  3.32it/s]
 68%|██████▊   | 253074/371472 [9:05:16<9:33:41,  3.44it/s]
 68%|██████▊   | 253075/371472 [9:05:16<9:27:20,  3.48it/s]
 68%|██████▊   | 253076/371472 [9:05:16<9:16:40,  3.54it/s]
 68%|██████▊   | 253077/371472 [9:05:17<9:51:29,  3.34it/s]
 68%|██████▊   | 253078/371472 [9:05:17<9:46:48,  3.36it/s]
 68%|██████▊   | 253079/371472 [9:05:17<9:22:08,  3.51it/s]
 68%|██████▊   | 253080/371472 [9:05:18<9:09:21,  3.59it/s]
                                                           
{'loss': 2.7322, 'learning_rate': 3.8699390204486195e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253080/371472 [9:05:18<9:09:21,  3.59it/s]
 68%|██████▊   | 253081/371472 [9:05:18<9:01:23,  3.64it/s]
 68%|██████▊   | 253082/371472 [9:05:18<8:59:18,  3.66it/s]
 68%|██████▊   | 253083/371472 [9:05:18<8:48:54,  3.73it/s]
 68%|██████▊   | 253084/371472 [9:05:19<8:50:26,  3.72it/s]
 68%|██████▊   | 253085/371472 [9:05:19<8:57:53,  3.67it/s]
 68%|██████▊   | 253086/371472 [9:05:19<9:34:10,  3.44it/s]
 68%|██████▊   | 253087/371472 [9:05:20<9:24:36,  3.49it/s]
 68%|██████▊   | 253088/371472 [9:05:20<9:04:01,  3.63it/s]
 68%|██████▊   | 253089/371472 [9:05:20<9:04:23,  3.62it/s]
 68%|██████▊   | 253090/371472 [9:05:20<8:38:37,  3.80it/s]
 68%|██████▊   | 253091/371472 [9:05:21<9:16:42,  3.54it/s]
 68%|██████▊   | 253092/371472 [9:05:21<9:43:57,  3.38it/s]
 68%|██████▊   | 253093/371472 [9:05:21<9:19:40,  3.53it/s]
 68%|██████▊   | 253094/371472 [9:05:22<9:21:57,  3.51it/s]
 68%|██████▊   | 253095/371472 [9:05:22<10:11:22,  3.23it/s]
 68%|██████▊   | 253096/371472 [9:05:22<10:08:07,  3.24it/s]
 68%|██████▊   | 253097/371472 [9:05:23<10:01:16,  3.28it/s]
 68%|██████▊   | 253098/371472 [9:05:23<9:21:53,  3.51it/s] 
 68%|██████▊   | 253099/371472 [9:05:23<9:26:06,  3.49it/s]
 68%|██████▊   | 253100/371472 [9:05:23<9:12:31,  3.57it/s]
                                                           
{'loss': 2.8544, 'learning_rate': 3.869454200693831e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253100/371472 [9:05:23<9:12:31,  3.57it/s]
 68%|██████▊   | 253101/371472 [9:05:24<9:16:34,  3.54it/s]
 68%|██████▊   | 253102/371472 [9:05:24<9:15:53,  3.55it/s]
 68%|██████▊   | 253103/371472 [9:05:24<8:50:04,  3.72it/s]
 68%|██████▊   | 253104/371472 [9:05:24<8:55:57,  3.68it/s]
 68%|██████▊   | 253105/371472 [9:05:25<8:55:02,  3.69it/s]
 68%|██████▊   | 253106/371472 [9:05:25<8:47:40,  3.74it/s]
 68%|██████▊   | 253107/371472 [9:05:25<8:37:14,  3.81it/s]
 68%|██████▊   | 253108/371472 [9:05:25<8:53:26,  3.70it/s]
 68%|██████▊   | 253109/371472 [9:05:26<8:54:44,  3.69it/s]
 68%|██████▊   | 253110/371472 [9:05:26<8:42:24,  3.78it/s]
 68%|██████▊   | 253111/371472 [9:05:26<8:54:27,  3.69it/s]
 68%|██████▊   | 253112/371472 [9:05:27<9:05:21,  3.62it/s]
 68%|██████▊   | 253113/371472 [9:05:27<9:10:52,  3.58it/s]
 68%|██████▊   | 253114/371472 [9:05:27<8:46:30,  3.75it/s]
 68%|██████▊   | 253115/371472 [9:05:27<9:00:15,  3.65it/s]
 68%|██████▊   | 253116/371472 [9:05:28<8:59:58,  3.65it/s]
 68%|██████▊   | 253117/371472 [9:05:28<8:54:40,  3.69it/s]
 68%|██████▊   | 253118/371472 [9:05:28<9:00:57,  3.65it/s]
 68%|██████▊   | 253119/371472 [9:05:28<8:56:29,  3.68it/s]
 68%|██████▊   | 253120/371472 [9:05:29<9:00:45,  3.65it/s]
                                                           
{'loss': 2.7952, 'learning_rate': 3.8689693809390415e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253120/371472 [9:05:29<9:00:45,  3.65it/s]
 68%|██████▊   | 253121/371472 [9:05:29<9:02:04,  3.64it/s]
 68%|██████▊   | 253122/371472 [9:05:29<8:49:54,  3.72it/s]
 68%|██████▊   | 253123/371472 [9:05:30<8:41:01,  3.79it/s]
 68%|██████▊   | 253124/371472 [9:05:30<9:19:30,  3.53it/s]
 68%|██████▊   | 253125/371472 [9:05:30<9:10:17,  3.58it/s]
 68%|██████▊   | 253126/371472 [9:05:30<8:46:53,  3.74it/s]
 68%|██████▊   | 253127/371472 [9:05:31<9:17:39,  3.54it/s]
 68%|██████▊   | 253128/371472 [9:05:31<10:00:45,  3.28it/s]
 68%|██████▊   | 253129/371472 [9:05:31<9:50:46,  3.34it/s] 
 68%|██████▊   | 253130/371472 [9:05:32<9:23:37,  3.50it/s]
 68%|██████▊   | 253131/371472 [9:05:32<9:17:32,  3.54it/s]
 68%|██████▊   | 253132/371472 [9:05:32<9:06:25,  3.61it/s]
 68%|██████▊   | 253133/371472 [9:05:32<8:47:18,  3.74it/s]
 68%|██████▊   | 253134/371472 [9:05:33<8:52:48,  3.70it/s]
 68%|██████▊   | 253135/371472 [9:05:33<9:40:16,  3.40it/s]
 68%|██████▊   | 253136/371472 [9:05:33<9:21:15,  3.51it/s]
 68%|██████▊   | 253137/371472 [9:05:33<8:54:52,  3.69it/s]
 68%|██████▊   | 253138/371472 [9:05:34<8:58:22,  3.66it/s]
 68%|██████▊   | 253139/371472 [9:05:34<9:42:24,  3.39it/s]
 68%|██████▊   | 253140/371472 [9:05:34<9:17:44,  3.54it/s]
                                                           
{'loss': 2.6736, 'learning_rate': 3.8684845611842533e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253140/371472 [9:05:34<9:17:44,  3.54it/s]
 68%|██████▊   | 253141/371472 [9:05:35<8:48:57,  3.73it/s]
 68%|██████▊   | 253142/371472 [9:05:35<8:41:08,  3.78it/s]
 68%|██████▊   | 253143/371472 [9:05:35<8:34:21,  3.83it/s]
 68%|██████▊   | 253144/371472 [9:05:35<8:49:15,  3.73it/s]
 68%|██████▊   | 253145/371472 [9:05:36<8:34:25,  3.83it/s]
 68%|██████▊   | 253146/371472 [9:05:36<8:31:26,  3.86it/s]
 68%|██████▊   | 253147/371472 [9:05:36<8:41:35,  3.78it/s]
 68%|██████▊   | 253148/371472 [9:05:36<8:56:13,  3.68it/s]
 68%|██████▊   | 253149/371472 [9:05:37<8:46:20,  3.75it/s]
 68%|██████▊   | 253150/371472 [9:05:37<8:34:11,  3.84it/s]
 68%|██████▊   | 253151/371472 [9:05:37<9:13:37,  3.56it/s]
 68%|██████▊   | 253152/371472 [9:05:38<9:33:18,  3.44it/s]
 68%|██████▊   | 253153/371472 [9:05:38<9:03:42,  3.63it/s]
 68%|██████▊   | 253154/371472 [9:05:38<9:08:48,  3.59it/s]
 68%|██████▊   | 253155/371472 [9:05:38<8:50:05,  3.72it/s]
 68%|██████▊   | 253156/371472 [9:05:39<9:09:16,  3.59it/s]
 68%|██████▊   | 253157/371472 [9:05:39<8:48:25,  3.73it/s]
 68%|██████▊   | 253158/371472 [9:05:39<9:28:52,  3.47it/s]
 68%|██████▊   | 253159/371472 [9:05:40<9:38:48,  3.41it/s]
 68%|██████▊   | 253160/371472 [9:05:40<9:06:35,  3.61it/s]
                                                           
{'loss': 2.8139, 'learning_rate': 3.8679997414294635e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253160/371472 [9:05:40<9:06:35,  3.61it/s]
 68%|██████▊   | 253161/371472 [9:05:40<8:55:02,  3.69it/s]
 68%|██████▊   | 253162/371472 [9:05:40<9:41:44,  3.39it/s]
 68%|██████▊   | 253163/371472 [9:05:41<9:48:33,  3.35it/s]
 68%|██████▊   | 253164/371472 [9:05:41<9:18:28,  3.53it/s]
 68%|██████▊   | 253165/371472 [9:05:41<9:02:18,  3.64it/s]
 68%|██████▊   | 253166/371472 [9:05:41<8:42:33,  3.77it/s]
 68%|██████▊   | 253167/371472 [9:05:42<8:26:10,  3.90it/s]
 68%|██████▊   | 253168/371472 [9:05:42<8:19:24,  3.95it/s]
 68%|██████▊   | 253169/371472 [9:05:42<8:48:06,  3.73it/s]
 68%|██████▊   | 253170/371472 [9:05:43<8:49:30,  3.72it/s]
 68%|██████▊   | 253171/371472 [9:05:43<9:06:42,  3.61it/s]
 68%|██████▊   | 253172/371472 [9:05:43<8:44:32,  3.76it/s]
 68%|██████▊   | 253173/371472 [9:05:43<8:58:26,  3.66it/s]
 68%|██████▊   | 253174/371472 [9:05:44<9:23:50,  3.50it/s]
 68%|██████▊   | 253175/371472 [9:05:44<9:10:07,  3.58it/s]
 68%|██████▊   | 253176/371472 [9:05:44<9:10:49,  3.58it/s]
 68%|██████▊   | 253177/371472 [9:05:44<9:03:13,  3.63it/s]
 68%|██████▊   | 253178/371472 [9:05:45<10:11:51,  3.22it/s]
 68%|██████▊   | 253179/371472 [9:05:45<10:16:16,  3.20it/s]
 68%|██████▊   | 253180/371472 [9:05:45<9:46:51,  3.36it/s] 
                                                           
{'loss': 2.9112, 'learning_rate': 3.8675149216746747e-07, 'epoch': 10.9}
+
 68%|██████▊   | 253180/371472 [9:05:45<9:46:51,  3.36it/s]
 68%|██████▊   | 253181/371472 [9:05:46<9:18:30,  3.53it/s]
 68%|██████▊   | 253182/371472 [9:05:46<9:41:32,  3.39it/s]
 68%|██████▊   | 253183/371472 [9:05:46<9:27:22,  3.47it/s]
 68%|██████▊   | 253184/371472 [9:05:47<9:29:40,  3.46it/s]
 68%|██████▊   | 253185/371472 [9:05:47<9:16:34,  3.54it/s]
 68%|██████▊   | 253186/371472 [9:05:47<9:01:01,  3.64it/s]
 68%|██████▊   | 253187/371472 [9:05:47<9:47:21,  3.36it/s]
 68%|██████▊   | 253188/371472 [9:05:48<9:39:06,  3.40it/s]
 68%|██████▊   | 253189/371472 [9:05:48<9:31:38,  3.45it/s]
 68%|██████▊   | 253190/371472 [9:05:48<9:42:23,  3.38it/s]
 68%|██████▊   | 253191/371472 [9:05:49<9:20:13,  3.52it/s]
 68%|██████▊   | 253192/371472 [9:05:49<9:02:45,  3.63it/s]
 68%|██████▊   | 253193/371472 [9:05:49<8:37:13,  3.81it/s]
 68%|██████▊   | 253194/371472 [9:05:49<9:02:01,  3.64it/s]
 68%|██████▊   | 253195/371472 [9:05:50<8:50:24,  3.72it/s]
 68%|██████▊   | 253196/371472 [9:05:50<9:16:59,  3.54it/s]
 68%|██████▊   | 253197/371472 [9:05:50<9:16:19,  3.54it/s]
 68%|██████▊   | 253198/371472 [9:05:50<9:14:50,  3.55it/s]
 68%|██████▊   | 253199/371472 [9:05:51<9:11:00,  3.58it/s]
 68%|██████▊   | 253200/371472 [9:05:51<8:55:14,  3.68it/s]
                                                           
{'loss': 2.8758, 'learning_rate': 3.867030101919886e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253200/371472 [9:05:51<8:55:14,  3.68it/s]
 68%|██████▊   | 253201/371472 [9:05:51<8:43:49,  3.76it/s]
 68%|██████▊   | 253202/371472 [9:05:52<8:44:36,  3.76it/s]
 68%|██████▊   | 253203/371472 [9:05:52<8:32:52,  3.84it/s]
 68%|██████▊   | 253204/371472 [9:05:52<8:22:30,  3.92it/s]
 68%|██████▊   | 253205/371472 [9:05:52<8:24:16,  3.91it/s]
 68%|██████▊   | 253206/371472 [9:05:53<8:27:43,  3.88it/s]
 68%|██████▊   | 253207/371472 [9:05:53<8:50:18,  3.72it/s]
 68%|██████▊   | 253208/371472 [9:05:53<8:43:20,  3.77it/s]
 68%|██████▊   | 253209/371472 [9:05:53<8:55:16,  3.68it/s]
 68%|██████▊   | 253210/371472 [9:05:54<8:41:50,  3.78it/s]
 68%|██████▊   | 253211/371472 [9:05:54<8:45:44,  3.75it/s]
 68%|██████▊   | 253212/371472 [9:05:54<8:54:32,  3.69it/s]
 68%|██████▊   | 253213/371472 [9:05:54<8:52:31,  3.70it/s]
 68%|██████▊   | 253214/371472 [9:05:55<9:10:42,  3.58it/s]
 68%|██████▊   | 253215/371472 [9:05:55<9:01:46,  3.64it/s]
 68%|██████▊   | 253216/371472 [9:05:55<8:47:30,  3.74it/s]
 68%|██████▊   | 253217/371472 [9:05:56<8:43:46,  3.76it/s]
 68%|██████▊   | 253218/371472 [9:05:56<8:36:53,  3.81it/s]
 68%|██████▊   | 253219/371472 [9:05:56<9:09:15,  3.59it/s]
 68%|██████▊   | 253220/371472 [9:05:56<8:56:52,  3.67it/s]
                                                           
{'loss': 2.7202, 'learning_rate': 3.866545282165097e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253220/371472 [9:05:56<8:56:52,  3.67it/s]
 68%|██████▊   | 253221/371472 [9:05:57<10:23:56,  3.16it/s]
 68%|██████▊   | 253222/371472 [9:05:57<9:40:09,  3.40it/s] 
 68%|█��████▊   | 253223/371472 [9:05:57<9:24:36,  3.49it/s]
 68%|██████▊   | 253224/371472 [9:05:58<8:53:34,  3.69it/s]
 68%|██████▊   | 253225/371472 [9:05:58<9:03:51,  3.62it/s]
 68%|██████▊   | 253226/371472 [9:05:58<9:08:40,  3.59it/s]
 68%|██████▊   | 253227/371472 [9:05:58<9:13:14,  3.56it/s]
 68%|██████▊   | 253228/371472 [9:05:59<9:03:32,  3.63it/s]
 68%|██████▊   | 253229/371472 [9:05:59<8:37:27,  3.81it/s]
 68%|██████▊   | 253230/371472 [9:05:59<8:52:37,  3.70it/s]
 68%|██████▊   | 253231/371472 [9:05:59<8:39:14,  3.80it/s]
 68%|██████▊   | 253232/371472 [9:06:00<8:47:19,  3.74it/s]
 68%|██████▊   | 253233/371472 [9:06:00<9:47:03,  3.36it/s]
 68%|██████▊   | 253234/371472 [9:06:00<9:35:21,  3.43it/s]
 68%|██████▊   | 253235/371472 [9:06:01<9:02:42,  3.63it/s]
 68%|██████▊   | 253236/371472 [9:06:01<8:42:30,  3.77it/s]
 68%|██████▊   | 253237/371472 [9:06:01<8:27:07,  3.89it/s]
 68%|██████▊   | 253238/371472 [9:06:01<8:20:28,  3.94it/s]
 68%|██████▊   | 253239/371472 [9:06:02<8:30:59,  3.86it/s]
 68%|██████▊   | 253240/371472 [9:06:02<8:22:15,  3.92it/s]
                                                           
{'loss': 2.8961, 'learning_rate': 3.866060462410308e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253240/371472 [9:06:02<8:22:15,  3.92it/s]
 68%|██████▊   | 253241/371472 [9:06:02<8:17:31,  3.96it/s]
 68%|██████▊   | 253242/371472 [9:06:02<8:10:21,  4.02it/s]
 68%|██████▊   | 253243/371472 [9:06:03<8:22:10,  3.92it/s]
 68%|██████▊   | 253244/371472 [9:06:03<8:12:36,  4.00it/s]
 68%|██████▊   | 253245/371472 [9:06:03<8:26:12,  3.89it/s]
 68%|██████▊   | 253246/371472 [9:06:03<8:38:09,  3.80it/s]
 68%|██████▊   | 253247/371472 [9:06:04<8:36:36,  3.81it/s]
 68%|██████▊   | 253248/371472 [9:06:04<8:33:03,  3.84it/s]
 68%|██████▊   | 253249/371472 [9:06:04<8:27:49,  3.88it/s]
 68%|██████▊   | 253250/371472 [9:06:04<9:23:42,  3.50it/s]
 68%|██████▊   | 253251/371472 [9:06:05<8:50:18,  3.72it/s]
 68%|██████▊   | 253252/371472 [9:06:05<8:42:56,  3.77it/s]
 68%|██████▊   | 253253/371472 [9:06:05<9:13:46,  3.56it/s]
 68%|██████▊   | 253254/371472 [9:06:06<9:01:29,  3.64it/s]
 68%|██████▊   | 253255/371472 [9:06:06<9:18:19,  3.53it/s]
 68%|██████▊   | 253256/371472 [9:06:06<9:24:08,  3.49it/s]
 68%|██████▊   | 253257/371472 [9:06:06<9:32:18,  3.44it/s]
 68%|██████▊   | 253258/371472 [9:06:07<9:23:50,  3.49it/s]
 68%|██████▊   | 253259/371472 [9:06:07<8:56:25,  3.67it/s]
 68%|██████▊   | 253260/371472 [9:06:07<9:00:22,  3.65it/s]
                                                           
{'loss': 2.9228, 'learning_rate': 3.8655756426555197e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253260/371472 [9:06:07<9:00:22,  3.65it/s]
 68%|██████▊   | 253261/371472 [9:06:07<8:45:44,  3.75it/s]
 68%|██████▊   | 253262/371472 [9:06:08<9:11:11,  3.57it/s]
 68%|██████▊   | 253263/371472 [9:06:08<9:38:20,  3.41it/s]
 68%|██████▊   | 253264/371472 [9:06:08<9:34:23,  3.43it/s]
 68%|██████▊   | 253265/371472 [9:06:09<9:15:31,  3.55it/s]
 68%|██████▊   | 253266/371472 [9:06:09<9:13:00,  3.56it/s]
 68%|██████▊   | 253267/371472 [9:06:09<8:54:51,  3.68it/s]
 68%|██████▊   | 253268/371472 [9:06:09<8:44:51,  3.75it/s]
 68%|██████▊   | 253269/371472 [9:06:10<9:54:05,  3.32it/s]
 68%|██████▊   | 253270/371472 [9:06:10<9:25:41,  3.48it/s]
 68%|██████▊   | 253271/371472 [9:06:10<9:22:34,  3.50it/s]
 68%|██████▊   | 253272/371472 [9:06:11<9:25:10,  3.49it/s]
 68%|██████▊   | 253273/371472 [9:06:11<9:05:09,  3.61it/s]
 68%|██████▊   | 253274/371472 [9:06:11<8:44:25,  3.76it/s]
 68%|██████▊   | 253275/371472 [9:06:11<8:49:28,  3.72it/s]
 68%|██████▊   | 253276/371472 [9:06:12<8:40:44,  3.78it/s]
 68%|██████▊   | 253277/371472 [9:06:12<8:43:24,  3.76it/s]
 68%|██████▊   | 253278/371472 [9:06:12<8:32:38,  3.84it/s]
 68%|██████▊   | 253279/371472 [9:06:13<9:40:04,  3.40it/s]
 68%|██████▊   | 253280/371472 [9:06:13<9:18:07,  3.53it/s]
                                                           
{'loss': 2.7281, 'learning_rate': 3.8650908229007304e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253280/371472 [9:06:13<9:18:07,  3.53it/s]
 68%|██████▊   | 253281/371472 [9:06:13<9:17:02,  3.54it/s]
 68%|██████▊   | 253282/371472 [9:06:13<9:20:15,  3.52it/s]
 68%|██████▊   | 253283/371472 [9:06:14<9:08:17,  3.59it/s]
 68%|██████▊   | 253284/371472 [9:06:14<9:00:51,  3.64it/s]
 68%|██████▊   | 253285/371472 [9:06:14<9:15:06,  3.55it/s]
 68%|██████▊   | 253286/371472 [9:06:15<9:07:15,  3.60it/s]
 68%|██████▊   | 253287/371472 [9:06:15<9:01:28,  3.64it/s]
 68%|██████▊   | 253288/371472 [9:06:15<9:07:08,  3.60it/s]
 68%|██████▊   | 253289/371472 [9:06:15<9:56:10,  3.30it/s]
 68%|██████▊   | 253290/371472 [9:06:16<9:46:46,  3.36it/s]
 68%|██████▊   | 253291/371472 [9:06:16<9:19:15,  3.52it/s]
 68%|██████▊   | 253292/371472 [9:06:16<9:08:45,  3.59it/s]
 68%|██████▊   | 253293/371472 [9:06:16<9:02:01,  3.63it/s]
 68%|██████▊   | 253294/371472 [9:06:17<8:53:00,  3.70it/s]
 68%|██████▊   | 253295/371472 [9:06:17<9:24:44,  3.49it/s]
 68%|██████▊   | 253296/371472 [9:06:17<9:18:55,  3.52it/s]
 68%|██████▊   | 253297/371472 [9:06:18<9:02:55,  3.63it/s]
 68%|██████▊   | 253298/371472 [9:06:18<9:21:11,  3.51it/s]
 68%|██████▊   | 253299/371472 [9:06:18<9:19:42,  3.52it/s]
 68%|██████▊   | 253300/371472 [9:06:18<9:02:47,  3.63it/s]
                                                           
{'loss': 2.8065, 'learning_rate': 3.8646060031459416e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253300/371472 [9:06:18<9:02:47,  3.63it/s]
 68%|██████▊   | 253301/371472 [9:06:19<8:55:48,  3.68it/s]
 68%|██████▊   | 253302/371472 [9:06:19<8:46:04,  3.74it/s]
 68%|██████▊   | 253303/371472 [9:06:19<8:37:42,  3.80it/s]
 68%|██████▊   | 253304/371472 [9:06:19<8:31:21,  3.85it/s]
 68%|██████▊   | 253305/371472 [9:06:20<8:28:38,  3.87it/s]
 68%|██████▊   | 253306/371472 [9:06:20<8:59:54,  3.65it/s]
 68%|██████▊   | 253307/371472 [9:06:20<8:39:58,  3.79it/s]
 68%|██████▊   | 253308/371472 [9:06:21<8:23:14,  3.91it/s]
 68%|██████▊   | 253309/371472 [9:06:21<8:40:42,  3.78it/s]
 68%|██████▊   | 253310/371472 [9:06:21<8:36:29,  3.81it/s]
 68%|██████▊   | 253311/371472 [9:06:21<9:03:17,  3.62it/s]
 68%|██████▊   | 253312/371472 [9:06:22<8:38:10,  3.80it/s]
 68%|██████▊   | 253313/371472 [9:06:22<8:32:32,  3.84it/s]
 68%|██████▊   | 253314/371472 [9:06:22<8:55:46,  3.68it/s]
 68%|██████▊   | 253315/371472 [9:06:22<9:00:38,  3.64it/s]
 68%|██████▊   | 253316/371472 [9:06:23<8:53:59,  3.69it/s]
 68%|██████▊   | 253317/371472 [9:06:23<8:58:47,  3.65it/s]
 68%|██████▊   | 253318/371472 [9:06:23<9:11:41,  3.57it/s]
 68%|██████▊   | 253319/371472 [9:06:24<9:17:18,  3.53it/s]
 68%|██████▊   | 253320/371472 [9:06:24<9:10:13,  3.58it/s]
                                                           
{'loss': 2.7927, 'learning_rate': 3.8641211833911524e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253320/371472 [9:06:24<9:10:13,  3.58it/s]
 68%|██████▊   | 253321/371472 [9:06:24<9:06:14,  3.60it/s]
 68%|██████▊   | 253322/371472 [9:06:24<9:32:02,  3.44it/s]
 68%|██████▊   | 253323/371472 [9:06:25<9:11:50,  3.57it/s]
 68%|██████▊   | 253324/371472 [9:06:25<9:57:43,  3.29it/s]
 68%|██████▊   | 253325/371472 [9:06:25<9:55:32,  3.31it/s]
 68%|██████▊   | 253326/371472 [9:06:26<9:40:20,  3.39it/s]
 68%|██████▊   | 253327/371472 [9:06:26<9:51:15,  3.33it/s]
 68%|██████▊   | 253328/371472 [9:06:26<9:37:05,  3.41it/s]
 68%|██████▊   | 253329/371472 [9:06:26<9:01:03,  3.64it/s]
 68%|██████▊   | 253330/371472 [9:06:27<8:54:39,  3.68it/s]
 68%|██████▊   | 253331/371472 [9:06:27<9:15:49,  3.54it/s]
 68%|██████▊   | 253332/371472 [9:06:27<9:15:12,  3.55it/s]
 68%|██████▊   | 253333/371472 [9:06:28<8:51:33,  3.70it/s]
 68%|██████▊   | 253334/371472 [9:06:28<8:49:29,  3.72it/s]
 68%|██████▊   | 253335/371472 [9:06:28<9:03:54,  3.62it/s]
 68%|██████▊   | 253336/371472 [9:06:28<9:01:33,  3.64it/s]
 68%|██████▊   | 253337/371472 [9:06:29<8:47:36,  3.73it/s]
 68%|██████▊   | 253338/371472 [9:06:29<8:40:26,  3.78it/s]
 68%|██████▊   | 253339/371472 [9:06:29<9:09:41,  3.58it/s]
 68%|██████▊   | 253340/371472 [9:06:29<9:03:31,  3.62it/s]
                                                           
{'loss': 2.8555, 'learning_rate': 3.863636363636364e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253340/371472 [9:06:29<9:03:31,  3.62it/s]
 68%|██████▊   | 253341/371472 [9:06:30<9:09:20,  3.58it/s]
 68%|██████▊   | 253342/371472 [9:06:30<8:47:20,  3.73it/s]
 68%|██████▊   | 253343/371472 [9:06:30<8:49:23,  3.72it/s]
 68%|██████▊   | 253344/371472 [9:06:31<8:51:08,  3.71it/s]
 68%|██████▊   | 253345/371472 [9:06:31<8:49:23,  3.72it/s]
 68%|██████▊   | 253346/371472 [9:06:31<8:34:46,  3.82it/s]
 68%|██████▊   | 253347/371472 [9:06:31<8:34:20,  3.83it/s]
 68%|██████▊   | 253348/371472 [9:06:32<8:25:32,  3.89it/s]
 68%|██████▊   | 253349/371472 [9:06:32<8:34:12,  3.83it/s]
 68%|██████▊   | 253350/371472 [9:06:32<8:16:22,  3.97it/s]
 68%|██████▊   | 253351/371472 [9:06:32<8:21:44,  3.92it/s]
 68%|██████▊   | 253352/371472 [9:06:33<8:21:17,  3.93it/s]
 68%|██████▊   | 253353/371472 [9:06:33<8:38:59,  3.79it/s]
 68%|██████▊   | 253354/371472 [9:06:33<8:49:27,  3.72it/s]
 68%|██████▊   | 253355/371472 [9:06:33<8:36:00,  3.82it/s]
 68%|██████▊   | 253356/371472 [9:06:34<9:08:15,  3.59it/s]
 68%|██████▊   | 253357/371472 [9:06:34<9:31:59,  3.44it/s]
 68%|██████▊   | 253358/371472 [9:06:34<9:55:22,  3.31it/s]
 68%|██████▊   | 253359/371472 [9:06:35<10:05:08,  3.25it/s]
 68%|██████▊   | 253360/371472 [9:06:35<9:17:31,  3.53it/s] 
                                                           
{'loss': 2.8318, 'learning_rate': 3.8631515438815743e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253360/371472 [9:06:35<9:17:31,  3.53it/s]
 68%|██████▊   | 253361/371472 [9:06:35<9:02:26,  3.63it/s]
 68%|██████▊   | 253362/371472 [9:06:35<9:15:49,  3.54it/s]
 68%|██████▊   | 253363/371472 [9:06:36<8:47:28,  3.73it/s]
 68%|██████▊   | 253364/371472 [9:06:36<8:39:29,  3.79it/s]
 68%|██████▊   | 253365/371472 [9:06:36<8:35:39,  3.82it/s]
 68%|██████▊   | 253366/371472 [9:06:36<9:04:19,  3.62it/s]
 68%|██████▊   | 253367/371472 [9:06:37<8:47:52,  3.73it/s]
 68%|██████▊   | 253368/371472 [9:06:37<8:25:06,  3.90it/s]
 68%|██████▊   | 253369/371472 [9:06:37<8:49:34,  3.72it/s]
 68%|██████▊   | 253370/371472 [9:06:38<8:46:59,  3.74it/s]
 68%|██████▊   | 253371/371472 [9:06:38<9:22:56,  3.50it/s]
 68%|██████▊   | 253372/371472 [9:06:38<9:44:00,  3.37it/s]
 68%|██████▊   | 253373/371472 [9:06:38<9:11:53,  3.57it/s]
 68%|██████▊   | 253374/371472 [9:06:39<8:47:00,  3.73it/s]
 68%|██████▊   | 253375/371472 [9:06:39<9:21:02,  3.51it/s]
 68%|██████▊   | 253376/371472 [9:06:39<9:08:36,  3.59it/s]
 68%|██████▊   | 253377/371472 [9:06:40<9:36:57,  3.41it/s]
 68%|██████▊   | 253378/371472 [9:06:40<9:34:37,  3.43it/s]
 68%|██████▊   | 253379/371472 [9:06:40<9:15:40,  3.54it/s]
 68%|██████▊   | 253380/371472 [9:06:40<8:51:01,  3.71it/s]
                                                           
{'loss': 2.9747, 'learning_rate': 3.862666724126786e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253380/371472 [9:06:40<8:51:01,  3.71it/s]
 68%|██████▊   | 253381/371472 [9:06:41<8:37:52,  3.80it/s]
 68%|██████▊   | 253382/371472 [9:06:41<9:15:56,  3.54it/s]
 68%|██████▊   | 253383/371472 [9:06:41<9:08:29,  3.59it/s]
 68%|██████▊   | 253384/371472 [9:06:42<9:23:39,  3.49it/s]
 68%|██████▊   | 253385/371472 [9:06:42<9:14:05,  3.55it/s]
 68%|██████▊   | 253386/371472 [9:06:42<8:47:38,  3.73it/s]
 68%|██████▊   | 253387/371472 [9:06:42<8:26:43,  3.88it/s]
 68%|██████▊   | 253388/371472 [9:06:43<8:21:33,  3.92it/s]
 68%|██████▊   | 253389/371472 [9:06:43<8:28:39,  3.87it/s]
 68%|██████▊   | 253390/371472 [9:06:43<8:26:50,  3.88it/s]
 68%|██████▊   | 253391/371472 [9:06:43<8:23:51,  3.91it/s]
 68%|██████▊   | 253392/371472 [9:06:44<8:18:05,  3.95it/s]
 68%|██████▊   | 253393/371472 [9:06:44<8:38:17,  3.80it/s]
 68%|██████▊   | 253394/371472 [9:06:44<8:50:20,  3.71it/s]
 68%|██████▊   | 253395/371472 [9:06:44<8:46:03,  3.74it/s]
 68%|██████▊   | 253396/371472 [9:06:45<8:33:11,  3.83it/s]
 68%|██████▊   | 253397/371472 [9:06:45<8:51:15,  3.70it/s]
 68%|██████▊   | 253398/371472 [9:06:45<8:33:06,  3.84it/s]
 68%|██████▊   | 253399/371472 [9:06:45<8:38:47,  3.79it/s]
 68%|██████▊   | 253400/371472 [9:06:46<9:15:00,  3.55it/s]
                                                           
{'loss': 2.8773, 'learning_rate': 3.862181904371997e-07, 'epoch': 10.91}
+
 68%|██████▊   | 253400/371472 [9:06:46<9:15:00,  3.55it/s]
 68%|██████▊   | 253401/371472 [9:06:46<8:59:24,  3.65it/s]
 68%|██████▊   | 253402/371472 [9:06:46<9:01:47,  3.63it/s]
 68%|██████▊   | 253403/371472 [9:06:47<9:06:25,  3.60it/s]
 68%|██████▊   | 253404/371472 [9:06:47<9:19:14,  3.52it/s]
 68%|██████▊   | 253405/371472 [9:06:47<10:47:09,  3.04it/s]
 68%|██████▊   | 253406/371472 [9:06:48<10:06:27,  3.24it/s]
 68%|██████▊   | 253407/371472 [9:06:48<9:29:33,  3.45it/s] 
 68%|██████▊   | 253408/371472 [9:06:48<9:13:00,  3.56it/s]
 68%|██████▊   | 253409/371472 [9:06:48<8:45:25,  3.75it/s]
 68%|██████▊   | 253410/371472 [9:06:49<8:58:06,  3.66it/s]
 68%|██████▊   | 253411/371472 [9:06:49<9:49:38,  3.34it/s]
 68%|██████▊   | 253412/371472 [9:06:49<9:26:16,  3.47it/s]
 68%|██████▊   | 253413/371472 [9:06:49<9:07:07,  3.60it/s]
 68%|██████▊   | 253414/371472 [9:06:50<8:51:36,  3.70it/s]
 68%|██████▊   | 253415/371472 [9:06:50<8:42:56,  3.76it/s]
 68%|██████▊   | 253416/371472 [9:06:50<8:26:40,  3.88it/s]
 68%|██████▊   | 253417/371472 [9:06:50<8:45:03,  3.75it/s]
 68%|██████▊   | 253418/371472 [9:06:51<8:38:31,  3.79it/s]
 68%|██████▊   | 253419/371472 [9:06:51<8:39:17,  3.79it/s]
 68%|██████▊   | 253420/371472 [9:06:51<8:47:43,  3.73it/s]
                                                           
{'loss': 2.8811, 'learning_rate': 3.861697084617207e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253420/371472 [9:06:51<8:47:43,  3.73it/s]
 68%|██████▊   | 253421/371472 [9:06:52<9:01:18,  3.63it/s]
 68%|██████▊   | 253422/371472 [9:06:52<9:09:36,  3.58it/s]
 68%|██████▊   | 253423/371472 [9:06:52<8:59:13,  3.65it/s]
 68%|██████▊   | 253424/371472 [9:06:52<9:04:29,  3.61it/s]
 68%|██████▊   | 253425/371472 [9:06:53<9:07:45,  3.59it/s]
 68%|██████▊   | 253426/371472 [9:06:53<8:50:19,  3.71it/s]
 68%|██████▊   | 253427/371472 [9:06:53<8:59:40,  3.65it/s]
 68%|██████▊   | 253428/371472 [9:06:53<8:45:19,  3.75it/s]
 68%|██████▊   | 253429/371472 [9:06:54<8:53:11,  3.69it/s]
 68%|██████▊   | 253430/371472 [9:06:54<9:14:13,  3.55it/s]
 68%|██████▊   | 253431/371472 [9:06:54<8:46:11,  3.74it/s]
 68%|██████▊   | 253432/371472 [9:06:55<9:08:41,  3.59it/s]
 68%|██████▊   | 253433/371472 [9:06:55<8:43:29,  3.76it/s]
 68%|██████▊   | 253434/371472 [9:06:55<8:38:18,  3.80it/s]
 68%|██████▊   | 253435/371472 [9:06:55<8:30:16,  3.86it/s]
 68%|██████▊   | 253436/371472 [9:06:56<8:31:04,  3.85it/s]
 68%|██████▊   | 253437/371472 [9:06:56<8:27:01,  3.88it/s]
 68%|██████▊   | 253438/371472 [9:06:56<8:43:11,  3.76it/s]
 68%|██████▊   | 253439/371472 [9:06:56<9:32:38,  3.44it/s]
 68%|██████▊   | 253440/371472 [9:06:57<9:46:45,  3.35it/s]
                                                           
{'loss': 2.932, 'learning_rate': 3.861212264862419e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253440/371472 [9:06:57<9:46:45,  3.35it/s]
 68%|██████▊   | 253441/371472 [9:06:57<9:14:28,  3.55it/s]
 68%|██████▊   | 253442/371472 [9:06:57<8:55:17,  3.67it/s]
 68%|██████▊   | 253443/371472 [9:06:58<8:42:07,  3.77it/s]
 68%|██████▊   | 253444/371472 [9:06:58<8:34:49,  3.82it/s]
 68%|██████▊   | 253445/371472 [9:06:58<8:15:27,  3.97it/s]
 68%|██████▊   | 253446/371472 [9:06:58<8:28:44,  3.87it/s]
 68%|██████▊   | 253447/371472 [9:06:59<8:38:41,  3.79it/s]
 68%|██████▊   | 253448/371472 [9:06:59<8:23:26,  3.91it/s]
 68%|██████▊   | 253449/371472 [9:06:59<8:38:37,  3.79it/s]
 68%|██████▊   | 253450/371472 [9:06:59<8:23:51,  3.90it/s]
 68%|██████▊   | 253451/371472 [9:07:00<8:50:58,  3.70it/s]
 68%|██████▊   | 253452/371472 [9:07:00<8:50:33,  3.71it/s]
 68%|██████▊   | 253453/371472 [9:07:00<9:02:39,  3.62it/s]
 68%|██████▊   | 253454/371472 [9:07:00<8:45:18,  3.74it/s]
 68%|██████▊   | 253455/371472 [9:07:01<8:30:38,  3.85it/s]
 68%|██████▊   | 253456/371472 [9:07:01<8:28:15,  3.87it/s]
 68%|██████▊   | 253457/371472 [9:07:01<8:36:12,  3.81it/s]
 68%|██████▊   | 253458/371472 [9:07:02<8:45:32,  3.74it/s]
 68%|██████▊   | 253459/371472 [9:07:02<8:44:59,  3.75it/s]
 68%|██████▊   | 253460/371472 [9:07:02<8:56:38,  3.67it/s]
                                                           
{'loss': 3.0393, 'learning_rate': 3.8607274451076295e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253460/371472 [9:07:02<8:56:38,  3.67it/s]
 68%|██████▊   | 253461/371472 [9:07:02<8:40:43,  3.78it/s]
 68%|██████▊   | 253462/371472 [9:07:03<8:19:23,  3.94it/s]
 68%|██████▊   | 253463/371472 [9:07:03<8:22:55,  3.91it/s]
 68%|██████▊   | 253464/371472 [9:07:03<8:46:09,  3.74it/s]
 68%|██████▊   | 253465/371472 [9:07:03<8:43:24,  3.76it/s]
 68%|██████▊   | 253466/371472 [9:07:04<8:34:44,  3.82it/s]
 68%|██████▊   | 253467/371472 [9:07:04<8:17:19,  3.95it/s]
 68%|██████▊   | 253468/371472 [9:07:04<8:33:50,  3.83it/s]
 68%|██████▊   | 253469/371472 [9:07:04<8:30:25,  3.85it/s]
 68%|██████▊   | 253470/371472 [9:07:05<8:35:16,  3.82it/s]
 68%|██████▊   | 253471/371472 [9:07:05<8:35:24,  3.82it/s]
 68%|██████▊   | 253472/371472 [9:07:05<8:52:06,  3.70it/s]
 68%|██████▊   | 253473/371472 [9:07:05<9:00:28,  3.64it/s]
 68%|██████▊   | 253474/371472 [9:07:06<8:47:01,  3.73it/s]
 68%|██████▊   | 253475/371472 [9:07:06<9:05:11,  3.61it/s]
 68%|██████▊   | 253476/371472 [9:07:06<10:03:39,  3.26it/s]
 68%|██████▊   | 253477/371472 [9:07:07<9:46:44,  3.35it/s] 
 68%|██████▊   | 253478/371472 [9:07:07<9:47:58,  3.34it/s]
 68%|██████▊   | 253479/371472 [9:07:07<9:28:29,  3.46it/s]
 68%|██████▊   | 253480/371472 [9:07:08<9:30:52,  3.44it/s]
                                                           
{'loss': 3.0404, 'learning_rate': 3.8602426253528407e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253480/371472 [9:07:08<9:30:52,  3.44it/s]
 68%|██████▊   | 253481/371472 [9:07:08<9:27:37,  3.46it/s]
 68%|██████▊   | 253482/371472 [9:07:08<9:26:57,  3.47it/s]
 68%|██████▊   | 253483/371472 [9:07:08<9:23:50,  3.49it/s]
 68%|██████▊   | 253484/371472 [9:07:09<8:53:35,  3.69it/s]
 68%|██████▊   | 253485/371472 [9:07:09<9:19:19,  3.52it/s]
 68%|██████▊   | 253486/371472 [9:07:09<9:27:17,  3.47it/s]
 68%|██████▊   | 253487/371472 [9:07:10<9:15:11,  3.54it/s]
 68%|██████▊   | 253488/371472 [9:07:10<9:32:41,  3.43it/s]
 68%|██████▊   | 253489/371472 [9:07:10<10:07:42,  3.24it/s]
 68%|██████▊   | 253490/371472 [9:07:10<9:34:00,  3.43it/s] 
 68%|██████▊   | 253491/371472 [9:07:11<9:08:54,  3.58it/s]
 68%|██████▊   | 253492/371472 [9:07:11<8:41:23,  3.77it/s]
 68%|██████▊   | 253493/371472 [9:07:11<9:09:27,  3.58it/s]
 68%|██████▊   | 253494/371472 [9:07:11<9:05:03,  3.61it/s]
 68%|██████▊   | 253495/371472 [9:07:12<8:43:13,  3.76it/s]
 68%|██████▊   | 253496/371472 [9:07:12<9:48:44,  3.34it/s]
 68%|██████▊   | 253497/371472 [9:07:12<10:08:58,  3.23it/s]
 68%|██████▊   | 253498/371472 [9:07:13<9:39:50,  3.39it/s] 
 68%|██████▊   | 253499/371472 [9:07:13<9:21:44,  3.50it/s]
 68%|██████▊   | 253500/371472 [9:07:13<9:04:23,  3.61it/s]
                                                           
{'loss': 2.894, 'learning_rate': 3.8597578055980514e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253500/371472 [9:07:13<9:04:23,  3.61it/s]
 68%|██████▊   | 253501/371472 [9:07:13<8:58:04,  3.65it/s]
 68%|██████▊   | 253502/371472 [9:07:14<10:25:49,  3.14it/s]
 68%|██████▊   | 253503/371472 [9:07:14<9:45:42,  3.36it/s] 
 68%|██████▊   | 253504/371472 [9:07:14<9:50:59,  3.33it/s]
 68%|██████▊   | 253505/371472 [9:07:15<9:04:58,  3.61it/s]
 68%|██████▊   | 253506/371472 [9:07:15<8:54:21,  3.68it/s]
 68%|██████▊   | 253507/371472 [9:07:15<8:46:50,  3.73it/s]
 68%|██████▊   | 253508/371472 [9:07:15<8:54:33,  3.68it/s]
 68%|██████▊   | 253509/371472 [9:07:16<8:51:27,  3.70it/s]
 68%|██████▊   | 253510/371472 [9:07:16<8:47:36,  3.73it/s]
 68%|██████▊   | 253511/371472 [9:07:16<8:54:49,  3.68it/s]
 68%|██████▊   | 253512/371472 [9:07:17<8:59:42,  3.64it/s]
 68%|██████▊   | 253513/371472 [9:07:17<8:48:24,  3.72it/s]
 68%|██████▊   | 253514/371472 [9:07:17<9:10:20,  3.57it/s]
 68%|██████▊   | 253515/371472 [9:07:17<9:13:15,  3.55it/s]
 68%|██████▊   | 253516/371472 [9:07:18<9:23:06,  3.49it/s]
 68%|██████▊   | 253517/371472 [9:07:18<9:03:06,  3.62it/s]
 68%|██████▊   | 253518/371472 [9:07:18<9:51:06,  3.33it/s]
 68%|██████▊   | 253519/371472 [9:07:19<10:23:14,  3.15it/s]
 68%|██████▊   | 253520/371472 [9:07:19<10:30:07,  3.12it/s]
                                                            
{'loss': 2.9075, 'learning_rate': 3.859272985843263e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253520/371472 [9:07:19<10:30:07,  3.12it/s]
 68%|██████▊   | 253521/371472 [9:07:19<10:19:47,  3.17it/s]
 68%|██████▊   | 253522/371472 [9:07:20<9:51:58,  3.32it/s] 
 68%|██████▊   | 253523/371472 [9:07:20<9:23:28,  3.49it/s]
 68%|██████▊   | 253524/371472 [9:07:20<9:09:56,  3.57it/s]
 68%|██████▊   | 253525/371472 [9:07:20<9:07:24,  3.59it/s]
 68%|██████▊   | 253526/371472 [9:07:21<8:37:57,  3.80it/s]
 68%|██████▊   | 253527/371472 [9:07:21<10:01:06,  3.27it/s]
 68%|██████▊   | 253528/371472 [9:07:21<10:03:46,  3.26it/s]
 68%|██████▊   | 253529/371472 [9:07:22<9:56:31,  3.30it/s] 
 68%|██████▊   | 253530/371472 [9:07:22<9:52:30,  3.32it/s]
 68%|██████▊   | 253531/371472 [9:07:22<9:22:17,  3.50it/s]
 68%|██████▊   | 253532/371472 [9:07:22<9:09:33,  3.58it/s]
 68%|██████▊   | 253533/371472 [9:07:23<9:00:41,  3.64it/s]
 68%|██████▊   | 253534/371472 [9:07:23<9:08:58,  3.58it/s]
 68%|██████▊   | 253535/371472 [9:07:23<9:01:47,  3.63it/s]
 68%|██████▊   | 253536/371472 [9:07:24<8:50:54,  3.70it/s]
 68%|██████▊   | 253537/371472 [9:07:24<9:12:28,  3.56it/s]
 68%|██████▊   | 253538/371472 [9:07:24<10:27:38,  3.13it/s]
 68%|██████▊   | 253539/371472 [9:07:25<10:10:10,  3.22it/s]
 68%|██████▊   | 253540/371472 [9:07:25<9:44:25,  3.36it/s] 
                                                           
{'loss': 2.8533, 'learning_rate': 3.858788166088474e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253540/371472 [9:07:25<9:44:25,  3.36it/s]
 68%|██████▊   | 253541/371472 [9:07:25<9:30:07,  3.45it/s]
 68%|██████▊   | 253542/371472 [9:07:25<8:59:40,  3.64it/s]
 68%|██████▊   | 253543/371472 [9:07:26<8:34:15,  3.82it/s]
 68%|██████▊   | 253544/371472 [9:07:26<8:30:48,  3.85it/s]
 68%|██████▊   | 253545/371472 [9:07:26<9:21:46,  3.50it/s]
 68%|██████▊   | 253546/371472 [9:07:26<9:02:34,  3.62it/s]
 68%|██████▊   | 253547/371472 [9:07:27<8:36:22,  3.81it/s]
 68%|██████▊   | 253548/371472 [9:07:27<9:17:13,  3.53it/s]
 68%|██████▊   | 253549/371472 [9:07:27<8:54:53,  3.67it/s]
 68%|██████▊   | 253550/371472 [9:07:27<8:37:44,  3.80it/s]
 68%|██████▊   | 253551/371472 [9:07:28<8:17:31,  3.95it/s]
 68%|██████▊   | 253552/371472 [9:07:28<8:10:47,  4.00it/s]
 68%|██████▊   | 253553/371472 [9:07:28<8:11:50,  4.00it/s]
 68%|██████▊   | 253554/371472 [9:07:28<8:18:38,  3.94it/s]
 68%|██████▊   | 253555/371472 [9:07:29<8:56:08,  3.67it/s]
 68%|██████▊   | 253556/371472 [9:07:29<9:17:57,  3.52it/s]
 68%|██████▊   | 253557/371472 [9:07:29<9:01:54,  3.63it/s]
 68%|██████▊   | 253558/371472 [9:07:30<9:03:19,  3.62it/s]
 68%|██████▊   | 253559/371472 [9:07:30<8:50:58,  3.70it/s]
 68%|██████▊   | 253560/371472 [9:07:30<9:13:02,  3.55it/s]
                                                           
{'loss': 2.9995, 'learning_rate': 3.858303346333685e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253560/371472 [9:07:30<9:13:02,  3.55it/s]
 68%|██████▊   | 253561/371472 [9:07:30<9:11:04,  3.57it/s]
 68%|██████▊   | 253562/371472 [9:07:31<9:05:53,  3.60it/s]
 68%|██████▊   | 253563/371472 [9:07:31<9:14:12,  3.55it/s]
 68%|██████▊   | 253564/371472 [9:07:31<9:13:19,  3.55it/s]
 68%|██████▊   | 253565/371472 [9:07:32<9:08:27,  3.58it/s]
 68%|██████▊   | 253566/371472 [9:07:32<9:04:36,  3.61it/s]
 68%|██████▊   | 253567/371472 [9:07:32<9:06:39,  3.59it/s]
 68%|██████▊   | 253568/371472 [9:07:32<8:58:48,  3.65it/s]
 68%|██████▊   | 253569/371472 [9:07:33<8:54:30,  3.68it/s]
 68%|██████▊   | 253570/371472 [9:07:33<8:53:52,  3.68it/s]
 68%|██████▊   | 253571/371472 [9:07:33<9:17:06,  3.53it/s]
 68%|██████▊   | 253572/371472 [9:07:33<9:13:37,  3.55it/s]
 68%|██████▊   | 253573/371472 [9:07:34<9:17:05,  3.53it/s]
 68%|██████▊   | 253574/371472 [9:07:34<9:26:32,  3.47it/s]
 68%|██████▊   | 253575/371472 [9:07:34<9:16:00,  3.53it/s]
 68%|██████▊   | 253576/371472 [9:07:35<9:17:54,  3.52it/s]
 68%|██████▊   | 253577/371472 [9:07:35<9:41:39,  3.38it/s]
 68%|██████▊   | 253578/371472 [9:07:35<9:31:32,  3.44it/s]
 68%|██████▊   | 253579/371472 [9:07:36<9:30:31,  3.44it/s]
 68%|██████▊   | 253580/371472 [9:07:36<9:24:23,  3.48it/s]
                                                           
{'loss': 2.7764, 'learning_rate': 3.857818526578896e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253580/371472 [9:07:36<9:24:23,  3.48it/s]
 68%|██████▊   | 253581/371472 [9:07:36<9:16:50,  3.53it/s]
 68%|██████▊   | 253582/371472 [9:07:36<9:03:47,  3.61it/s]
 68%|██████▊   | 253583/371472 [9:07:37<9:27:01,  3.47it/s]
 68%|██████▊   | 253584/371472 [9:07:37<9:35:12,  3.42it/s]
 68%|██████▊   | 253585/371472 [9:07:37<9:18:14,  3.52it/s]
 68%|██████▊   | 253586/371472 [9:07:37<9:08:15,  3.58it/s]
 68%|██████▊   | 253587/371472 [9:07:38<9:44:27,  3.36it/s]
 68%|██████▊   | 253588/371472 [9:07:38<9:03:56,  3.61it/s]
 68%|██████▊   | 253589/371472 [9:07:38<8:35:09,  3.81it/s]
 68%|██████▊   | 253590/371472 [9:07:39<8:51:20,  3.70it/s]
 68%|██████▊   | 253591/371472 [9:07:39<8:48:10,  3.72it/s]
 68%|██████▊   | 253592/371472 [9:07:39<8:51:50,  3.69it/s]
 68%|██████▊   | 253593/371472 [9:07:39<9:45:44,  3.35it/s]
 68%|██████▊   | 253594/371472 [9:07:40<10:08:01,  3.23it/s]
 68%|██████▊   | 253595/371472 [9:07:40<9:28:22,  3.46it/s] 
 68%|██████▊   | 253596/371472 [9:07:40<9:29:09,  3.45it/s]
 68%|██████▊   | 253597/371472 [9:07:41<9:14:11,  3.54it/s]
 68%|██████▊   | 253598/371472 [9:07:41<8:44:22,  3.75it/s]
 68%|██████▊   | 253599/371472 [9:07:41<8:28:45,  3.86it/s]
 68%|██████▊   | 253600/371472 [9:07:41<8:42:42,  3.76it/s]
                                                           
{'loss': 2.8862, 'learning_rate': 3.8573337068241077e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253600/371472 [9:07:41<8:42:42,  3.76it/s]
 68%|██████▊   | 253601/371472 [9:07:42<8:35:38,  3.81it/s]
 68%|██████▊   | 253602/371472 [9:07:42<8:44:03,  3.75it/s]
 68%|██████▊   | 253603/371472 [9:07:42<9:13:22,  3.55it/s]
 68%|██████▊   | 253604/371472 [9:07:42<8:58:16,  3.65it/s]
 68%|██████▊   | 253605/371472 [9:07:43<9:18:03,  3.52it/s]
 68%|██████▊   | 253606/371472 [9:07:43<9:25:38,  3.47it/s]
 68%|██████▊   | 253607/371472 [9:07:43<9:37:16,  3.40it/s]
 68%|██████▊   | 253608/371472 [9:07:44<9:28:32,  3.46it/s]
 68%|██████▊   | 253609/371472 [9:07:44<9:21:24,  3.50it/s]
 68%|██████▊   | 253610/371472 [9:07:44<9:34:23,  3.42it/s]
 68%|██████▊   | 253611/371472 [9:07:45<9:45:33,  3.35it/s]
 68%|██████▊   | 253612/371472 [9:07:45<9:23:59,  3.48it/s]
 68%|██████▊   | 253613/371472 [9:07:45<9:21:57,  3.50it/s]
 68%|██████▊   | 253614/371472 [9:07:45<9:22:34,  3.49it/s]
 68%|██████▊   | 253615/371472 [9:07:46<10:53:45,  3.00it/s]
 68%|██████▊   | 253616/371472 [9:07:46<10:43:31,  3.05it/s]
 68%|██████▊   | 253617/371472 [9:07:46<10:39:32,  3.07it/s]
 68%|██████▊   | 253618/371472 [9:07:47<10:10:57,  3.22it/s]
 68%|██████▊   | 253619/371472 [9:07:47<10:06:28,  3.24it/s]
 68%|██████▊   | 253620/371472 [9:07:47<9:36:17,  3.41it/s] 
                                                           
{'loss': 2.6222, 'learning_rate': 3.856848887069318e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253620/371472 [9:07:47<9:36:17,  3.41it/s]
 68%|██████▊   | 253621/371472 [9:07:48<9:27:15,  3.46it/s]
 68%|██████▊   | 253622/371472 [9:07:48<8:53:29,  3.68it/s]
 68%|██████▊   | 253623/371472 [9:07:48<8:57:40,  3.65it/s]
 68%|██████▊   | 253624/371472 [9:07:48<8:42:49,  3.76it/s]
 68%|██████▊   | 253625/371472 [9:07:49<9:36:15,  3.41it/s]
 68%|██████▊   | 253626/371472 [9:07:49<9:12:11,  3.56it/s]
 68%|██████▊   | 253627/371472 [9:07:49<8:54:05,  3.68it/s]
 68%|██████▊   | 253628/371472 [9:07:49<8:49:31,  3.71it/s]
 68%|██████▊   | 253629/371472 [9:07:50<9:57:08,  3.29it/s]
 68%|██████▊   | 253630/371472 [9:07:50<10:06:28,  3.24it/s]
 68%|██████▊   | 253631/371472 [9:07:50<9:45:51,  3.35it/s] 
 68%|██████▊   | 253632/371472 [9:07:51<10:21:18,  3.16it/s]
 68%|██████▊   | 253633/371472 [9:07:51<10:24:14,  3.15it/s]
 68%|██████▊   | 253634/371472 [9:07:51<10:33:21,  3.10it/s]
 68%|██████▊   | 253635/371472 [9:07:52<10:39:26,  3.07it/s]
 68%|██████▊   | 253636/371472 [9:07:52<10:56:54,  2.99it/s]
 68%|██████▊   | 253637/371472 [9:07:52<10:20:20,  3.17it/s]
 68%|██████▊   | 253638/371472 [9:07:53<10:24:24,  3.15it/s]
 68%|██████▊   | 253639/371472 [9:07:53<10:03:13,  3.26it/s]
 68%|██████▊   | 253640/371472 [9:07:53<9:31:08,  3.44it/s] 
                                                           
{'loss': 2.9034, 'learning_rate': 3.8563640673145296e-07, 'epoch': 10.92}
+
 68%|██████▊   | 253640/371472 [9:07:53<9:31:08,  3.44it/s]
 68%|██████▊   | 253641/371472 [9:07:54<10:11:21,  3.21it/s]
 68%|██████▊   | 253642/371472 [9:07:54<9:51:20,  3.32it/s] 
 68%|██████▊   | 253643/371472 [9:07:54<9:42:40,  3.37it/s]
 68%|██████▊   | 253644/371472 [9:07:54<9:17:28,  3.52it/s]
 68%|██████▊   | 253645/371472 [9:07:55<9:13:56,  3.55it/s]
 68%|██████▊   | 253646/371472 [9:07:55<9:12:41,  3.55it/s]
 68%|██████▊   | 253647/371472 [9:07:55<8:43:15,  3.75it/s]
 68%|██████▊   | 253648/371472 [9:07:56<8:59:41,  3.64it/s]
 68%|██████▊   | 253649/371472 [9:07:56<8:58:06,  3.65it/s]
 68%|██████▊   | 253650/371472 [9:07:56<8:44:53,  3.74it/s]
 68%|██████▊   | 253651/371472 [9:07:56<9:02:25,  3.62it/s]
 68%|██████▊   | 253652/371472 [9:07:57<9:13:52,  3.55it/s]
 68%|██████▊   | 253653/371472 [9:07:57<9:02:14,  3.62it/s]
 68%|██████▊   | 253654/371472 [9:07:57<9:23:42,  3.48it/s]
 68%|██████▊   | 253655/371472 [9:07:58<9:25:38,  3.47it/s]
 68%|██████▊   | 253656/371472 [9:07:58<8:55:55,  3.66it/s]
 68%|██████▊   | 253657/371472 [9:07:58<8:48:00,  3.72it/s]
 68%|██████▊   | 253658/371472 [9:07:58<8:45:42,  3.74it/s]
 68%|██████▊   | 253659/371472 [9:07:59<8:51:03,  3.70it/s]
 68%|██████▊   | 253660/371472 [9:07:59<8:56:23,  3.66it/s]
                                                           
{'loss': 2.9543, 'learning_rate': 3.8558792475597403e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253660/371472 [9:07:59<8:56:23,  3.66it/s]
 68%|██████▊   | 253661/371472 [9:07:59<9:09:57,  3.57it/s]
 68%|██████▊   | 253662/371472 [9:07:59<8:52:16,  3.69it/s]
 68%|██████▊   | 253663/371472 [9:08:00<9:06:31,  3.59it/s]
 68%|██████▊   | 253664/371472 [9:08:00<9:07:14,  3.59it/s]
 68%|██████▊   | 253665/371472 [9:08:00<8:47:40,  3.72it/s]
 68%|██████▊   | 253666/371472 [9:08:01<9:14:14,  3.54it/s]
 68%|██████▊   | 253667/371472 [9:08:01<9:43:13,  3.37it/s]
 68%|██████▊   | 253668/371472 [9:08:01<9:35:27,  3.41it/s]
 68%|██████▊   | 253669/371472 [9:08:01<9:57:05,  3.29it/s]
 68%|██████▊   | 253670/371472 [9:08:02<9:22:08,  3.49it/s]
 68%|██████▊   | 253671/371472 [9:08:02<9:15:11,  3.54it/s]
 68%|██████▊   | 253672/371472 [9:08:02<8:56:29,  3.66it/s]
 68%|██████▊   | 253673/371472 [9:08:02<8:56:20,  3.66it/s]
 68%|██████▊   | 253674/371472 [9:08:03<9:06:40,  3.59it/s]
 68%|██████▊   | 253675/371472 [9:08:03<8:53:01,  3.68it/s]
 68%|██████▊   | 253676/371472 [9:08:03<8:48:01,  3.72it/s]
 68%|██████▊   | 253677/371472 [9:08:04<8:59:39,  3.64it/s]
 68%|██████▊   | 253678/371472 [9:08:04<10:03:40,  3.25it/s]
 68%|██████▊   | 253679/371472 [9:08:04<9:28:07,  3.46it/s] 
 68%|██████▊   | 253680/371472 [9:08:05<11:12:26,  2.92it/s]
                                                            
{'loss': 2.6245, 'learning_rate': 3.8553944278049516e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253680/371472 [9:08:05<11:12:26,  2.92it/s]
 68%|██████▊   | 253681/371472 [9:08:05<10:22:05,  3.16it/s]
 68%|██████▊   | 253682/371472 [9:08:05<10:30:55,  3.11it/s]
 68%|██████▊   | 253683/371472 [9:08:06<9:48:26,  3.34it/s] 
 68%|██████▊   | 253684/371472 [9:08:06<9:49:51,  3.33it/s]
 68%|██████▊   | 253685/371472 [9:08:06<9:19:42,  3.51it/s]
 68%|██████▊   | 253686/371472 [9:08:06<9:23:33,  3.48it/s]
 68%|██████▊   | 253687/371472 [9:08:07<8:57:09,  3.65it/s]
 68%|██████▊   | 253688/371472 [9:08:07<8:55:27,  3.67it/s]
 68%|██████▊   | 253689/371472 [9:08:07<9:25:22,  3.47it/s]
 68%|██████▊   | 253690/371472 [9:08:07<9:01:51,  3.62it/s]
 68%|██████▊   | 253691/371472 [9:08:08<9:13:48,  3.54it/s]
 68%|██████▊   | 253692/371472 [9:08:08<8:50:22,  3.70it/s]
 68%|██████▊   | 253693/371472 [9:08:08<9:06:42,  3.59it/s]
 68%|██████▊   | 253694/371472 [9:08:09<9:31:16,  3.44it/s]
 68%|██████▊   | 253695/371472 [9:08:09<9:38:21,  3.39it/s]
 68%|██████▊   | 253696/371472 [9:08:09<9:08:05,  3.58it/s]
 68%|██████▊   | 253697/371472 [9:08:09<9:11:24,  3.56it/s]
 68%|██████▊   | 253698/371472 [9:08:10<9:58:18,  3.28it/s]
 68%|██████▊   | 253699/371472 [9:08:10<9:46:05,  3.35it/s]
 68%|██████▊   | 253700/371472 [9:08:10<9:35:09,  3.41it/s]
                                                           
{'loss': 2.9382, 'learning_rate': 3.8549096080501623e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253700/371472 [9:08:10<9:35:09,  3.41it/s]
 68%|██████▊   | 253701/371472 [9:08:11<9:27:08,  3.46it/s]
 68%|██████▊   | 253702/371472 [9:08:11<9:55:30,  3.30it/s]
 68%|██████▊   | 253703/371472 [9:08:11<9:48:41,  3.33it/s]
 68%|██████▊   | 253704/371472 [9:08:12<9:20:31,  3.50it/s]
 68%|██████▊   | 253705/371472 [9:08:12<10:19:07,  3.17it/s]
 68%|██████▊   | 253706/371472 [9:08:12<9:43:30,  3.36it/s] 
 68%|██████▊   | 253707/371472 [9:08:12<9:40:27,  3.38it/s]
 68%|██████▊   | 253708/371472 [9:08:13<9:34:09,  3.42it/s]
 68%|██████▊   | 253709/371472 [9:08:13<9:06:30,  3.59it/s]
 68%|██████▊   | 253710/371472 [9:08:13<9:05:57,  3.59it/s]
 68%|██████▊   | 253711/371472 [9:08:14<8:39:35,  3.78it/s]
 68%|██████▊   | 253712/371472 [9:08:14<8:28:41,  3.86it/s]
 68%|██████▊   | 253713/371472 [9:08:14<8:50:54,  3.70it/s]
 68%|██████▊   | 253714/371472 [9:08:14<8:59:12,  3.64it/s]
 68%|██████▊   | 253715/371472 [9:08:15<8:42:44,  3.75it/s]
 68%|██████▊   | 253716/371472 [9:08:15<8:32:39,  3.83it/s]
 68%|██████▊   | 253717/371472 [9:08:15<8:36:23,  3.80it/s]
 68%|██████▊   | 253718/371472 [9:08:15<8:44:33,  3.74it/s]
 68%|██████▊   | 253719/371472 [9:08:16<9:00:43,  3.63it/s]
 68%|██████▊   | 253720/371472 [9:08:16<8:43:44,  3.75it/s]
                                                           
{'loss': 2.8172, 'learning_rate': 3.854424788295374e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253720/371472 [9:08:16<8:43:44,  3.75it/s]
 68%|██████▊   | 253721/371472 [9:08:16<8:45:04,  3.74it/s]
 68%|██████▊   | 253722/371472 [9:08:16<8:54:41,  3.67it/s]
 68%|██████▊   | 253723/371472 [9:08:17<8:34:33,  3.81it/s]
 68%|██████▊   | 253724/371472 [9:08:17<8:30:51,  3.84it/s]
 68%|██████▊   | 253725/371472 [9:08:17<8:39:29,  3.78it/s]
 68%|██████▊   | 253726/371472 [9:08:18<9:36:16,  3.41it/s]
 68%|██████▊   | 253727/371472 [9:08:18<10:13:41,  3.20it/s]
 68%|██████▊   | 253728/371472 [9:08:18<9:35:47,  3.41it/s] 
 68%|██████▊   | 253729/371472 [9:08:18<9:17:14,  3.52it/s]
 68%|██████▊   | 253730/371472 [9:08:19<9:04:40,  3.60it/s]
 68%|██████▊   | 253731/371472 [9:08:19<8:49:02,  3.71it/s]
 68%|██████▊   | 253732/371472 [9:08:19<8:50:17,  3.70it/s]
 68%|██████▊   | 253733/371472 [9:08:20<8:40:39,  3.77it/s]
 68%|██████▊   | 253734/371472 [9:08:20<8:45:47,  3.73it/s]
 68%|██████▊   | 253735/371472 [9:08:20<8:43:28,  3.75it/s]
 68%|██████▊   | 253736/371472 [9:08:20<9:04:50,  3.60it/s]
 68%|██████▊   | 253737/371472 [9:08:21<8:55:44,  3.66it/s]
 68%|██████▊   | 253738/371472 [9:08:21<9:01:05,  3.63it/s]
 68%|██████▊   | 253739/371472 [9:08:21<8:59:37,  3.64it/s]
 68%|██████▊   | 253740/371472 [9:08:21<9:09:07,  3.57it/s]
                                                           
{'loss': 2.8541, 'learning_rate': 3.853939968540584e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253740/371472 [9:08:21<9:09:07,  3.57it/s]
 68%|██████▊   | 253741/371472 [9:08:22<9:32:29,  3.43it/s]
 68%|██████▊   | 253742/371472 [9:08:22<8:54:48,  3.67it/s]
 68%|██████▊   | 253743/371472 [9:08:22<9:02:59,  3.61it/s]
 68%|██████▊   | 253744/371472 [9:08:23<9:27:02,  3.46it/s]
 68%|██████▊   | 253745/371472 [9:08:23<9:19:12,  3.51it/s]
 68%|██████▊   | 253746/371472 [9:08:23<9:13:06,  3.55it/s]
 68%|██████▊   | 253747/371472 [9:08:23<8:54:52,  3.67it/s]
 68%|██████▊   | 253748/371472 [9:08:24<8:45:22,  3.73it/s]
 68%|██████▊   | 253749/371472 [9:08:24<8:59:04,  3.64it/s]
 68%|██████▊   | 253750/371472 [9:08:24<8:53:02,  3.68it/s]
 68%|██████▊   | 253751/371472 [9:08:25<8:58:48,  3.64it/s]
 68%|██████▊   | 253752/371472 [9:08:25<8:50:07,  3.70it/s]
 68%|██████▊   | 253753/371472 [9:08:25<8:48:05,  3.72it/s]
 68%|██████▊   | 253754/371472 [9:08:25<9:01:04,  3.63it/s]
 68%|██████▊   | 253755/371472 [9:08:26<8:57:05,  3.65it/s]
 68%|██████▊   | 253756/371472 [9:08:26<10:05:44,  3.24it/s]
 68%|██████▊   | 253757/371472 [9:08:26<9:52:19,  3.31it/s] 
 68%|██████▊   | 253758/371472 [9:08:27<9:27:30,  3.46it/s]
 68%|██████▊   | 253759/371472 [9:08:27<9:25:45,  3.47it/s]
 68%|██████▊   | 253760/371472 [9:08:27<9:00:33,  3.63it/s]
                                                           
{'loss': 2.831, 'learning_rate': 3.853455148785796e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253760/371472 [9:08:27<9:00:33,  3.63it/s]
 68%|██████▊   | 253761/371472 [9:08:27<9:03:15,  3.61it/s]
 68%|██████▊   | 253762/371472 [9:08:28<9:19:54,  3.50it/s]
 68%|██████▊   | 253763/371472 [9:08:28<9:30:19,  3.44it/s]
 68%|██████▊   | 253764/371472 [9:08:28<9:11:21,  3.56it/s]
 68%|██████▊   | 253765/371472 [9:08:28<8:49:35,  3.70it/s]
 68%|██████▊   | 253766/371472 [9:08:29<8:57:27,  3.65it/s]
 68%|██████▊   | 253767/371472 [9:08:29<9:00:30,  3.63it/s]
 68%|██████▊   | 253768/371472 [9:08:29<9:18:26,  3.51it/s]
 68%|██████▊   | 253769/371472 [9:08:30<9:20:16,  3.50it/s]
 68%|██████▊   | 253770/371472 [9:08:30<10:05:24,  3.24it/s]
 68%|██████▊   | 253771/371472 [9:08:30<9:23:39,  3.48it/s] 
 68%|██████▊   | 253772/371472 [9:08:30<9:14:40,  3.54it/s]
 68%|██████▊   | 253773/371472 [9:08:31<9:01:37,  3.62it/s]
 68%|██████▊   | 253774/371472 [9:08:31<9:20:16,  3.50it/s]
 68%|██████▊   | 253775/371472 [9:08:31<9:53:12,  3.31it/s]
 68%|██████▊   | 253776/371472 [9:08:32<9:58:13,  3.28it/s]
 68%|██████▊   | 253777/371472 [9:08:32<9:14:59,  3.53it/s]
 68%|██████▊   | 253778/371472 [9:08:32<10:00:52,  3.26it/s]
 68%|██████▊   | 253779/371472 [9:08:33<9:53:28,  3.31it/s] 
 68%|██████▊   | 253780/371472 [9:08:33<9:35:08,  3.41it/s]
                                                           
{'loss': 2.8265, 'learning_rate': 3.852970329031007e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253780/371472 [9:08:33<9:35:08,  3.41it/s]
 68%|██████▊   | 253781/371472 [9:08:33<9:22:34,  3.49it/s]
 68%|██████▊   | 253782/371472 [9:08:33<9:00:40,  3.63it/s]
 68%|██████▊   | 253783/371472 [9:08:34<8:55:08,  3.67it/s]
 68%|██████▊   | 253784/371472 [9:08:34<9:02:25,  3.62it/s]
 68%|██████▊   | 253785/371472 [9:08:34<8:48:07,  3.71it/s]
 68%|██████▊   | 253786/371472 [9:08:34<8:43:27,  3.75it/s]
 68%|██████▊   | 253787/371472 [9:08:35<9:22:10,  3.49it/s]
 68%|██████▊   | 253788/371472 [9:08:35<9:09:11,  3.57it/s]
 68%|██████▊   | 253789/371472 [9:08:35<8:47:50,  3.72it/s]
 68%|██████▊   | 253790/371472 [9:08:36<8:26:42,  3.87it/s]
 68%|██████▊   | 253791/371472 [9:08:36<8:37:47,  3.79it/s]
 68%|██████▊   | 253792/371472 [9:08:36<8:24:19,  3.89it/s]
 68%|██████▊   | 253793/371472 [9:08:36<9:08:25,  3.58it/s]
 68%|██████▊   | 253794/371472 [9:08:37<9:12:54,  3.55it/s]
 68%|██████▊   | 253795/371472 [9:08:37<9:34:37,  3.41it/s]
 68%|██████▊   | 253796/371472 [9:08:37<9:23:49,  3.48it/s]
 68%|██████▊   | 253797/371472 [9:08:37<9:02:05,  3.62it/s]
 68%|██████▊   | 253798/371472 [9:08:38<8:57:32,  3.65it/s]
 68%|██████▊   | 253799/371472 [9:08:38<8:45:55,  3.73it/s]
 68%|██████▊   | 253800/371472 [9:08:38<9:10:00,  3.57it/s]
                                                           
{'loss': 2.6632, 'learning_rate': 3.852485509276218e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253800/371472 [9:08:38<9:10:00,  3.57it/s]
 68%|██████▊   | 253801/371472 [9:08:39<9:10:36,  3.56it/s]
 68%|██████▊   | 253802/371472 [9:08:39<8:52:06,  3.69it/s]
 68%|██████▊   | 253803/371472 [9:08:39<8:37:53,  3.79it/s]
 68%|██████▊   | 253804/371472 [9:08:39<8:44:38,  3.74it/s]
 68%|██████▊   | 253805/371472 [9:08:40<8:32:51,  3.82it/s]
 68%|██████▊   | 253806/371472 [9:08:40<8:30:31,  3.84it/s]
 68%|██████▊   | 253807/371472 [9:08:40<8:37:24,  3.79it/s]
 68%|██████▊   | 253808/371472 [9:08:40<8:38:57,  3.78it/s]
 68%|██████▊   | 253809/371472 [9:08:41<9:11:38,  3.55it/s]
 68%|██████▊   | 253810/371472 [9:08:41<9:34:37,  3.41it/s]
 68%|██████▊   | 253811/371472 [9:08:41<9:11:28,  3.56it/s]
 68%|██████▊   | 253812/371472 [9:08:42<9:06:28,  3.59it/s]
 68%|██████▊   | 253813/371472 [9:08:42<8:56:09,  3.66it/s]
 68%|██████▊   | 253814/371472 [9:08:42<9:06:31,  3.59it/s]
 68%|██████▊   | 253815/371472 [9:08:42<9:07:35,  3.58it/s]
 68%|██████▊   | 253816/371472 [9:08:43<9:03:45,  3.61it/s]
 68%|██████▊   | 253817/371472 [9:08:43<8:47:17,  3.72it/s]
 68%|██████▊   | 253818/371472 [9:08:43<9:29:48,  3.44it/s]
 68%|██████▊   | 253819/371472 [9:08:44<9:11:42,  3.55it/s]
 68%|██████▊   | 253820/371472 [9:08:44<9:07:34,  3.58it/s]
                                                           
{'loss': 2.8523, 'learning_rate': 3.8520006895214287e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253820/371472 [9:08:44<9:07:34,  3.58it/s]
 68%|██████▊   | 253821/371472 [9:08:44<8:57:50,  3.65it/s]
 68%|██████▊   | 253822/371472 [9:08:44<8:57:58,  3.64it/s]
 68%|██████▊   | 253823/371472 [9:08:45<8:49:22,  3.70it/s]
 68%|██████▊   | 253824/371472 [9:08:45<8:44:26,  3.74it/s]
 68%|██████▊   | 253825/371472 [9:08:45<9:04:39,  3.60it/s]
 68%|██████▊   | 253826/371472 [9:08:45<8:55:24,  3.66it/s]
 68%|██████▊   | 253827/371472 [9:08:46<9:05:47,  3.59it/s]
 68%|██████▊   | 253828/371472 [9:08:46<9:07:29,  3.58it/s]
 68%|█████���▊   | 253829/371472 [9:08:46<9:06:49,  3.59it/s]
 68%|██████▊   | 253830/371472 [9:08:47<8:59:17,  3.64it/s]
 68%|██████▊   | 253831/371472 [9:08:47<8:57:02,  3.65it/s]
 68%|██████▊   | 253832/371472 [9:08:47<8:39:53,  3.77it/s]
 68%|██████▊   | 253833/371472 [9:08:47<8:38:48,  3.78it/s]
 68%|██████▊   | 253834/371472 [9:08:48<9:22:53,  3.48it/s]
 68%|██████▊   | 253835/371472 [9:08:48<9:12:07,  3.55it/s]
 68%|██████▊   | 253836/371472 [9:08:48<9:21:17,  3.49it/s]
 68%|██████▊   | 253837/371472 [9:08:48<8:59:21,  3.64it/s]
 68%|██████▊   | 253838/371472 [9:08:49<9:48:36,  3.33it/s]
 68%|██████▊   | 253839/371472 [9:08:49<9:17:50,  3.51it/s]
 68%|██████▊   | 253840/371472 [9:08:49<9:00:22,  3.63it/s]
                                                           
{'loss': 2.7753, 'learning_rate': 3.8515158697666405e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253840/371472 [9:08:49<9:00:22,  3.63it/s]
 68%|██████▊   | 253841/371472 [9:08:50<8:45:17,  3.73it/s]
 68%|██████▊   | 253842/371472 [9:08:50<8:50:56,  3.69it/s]
 68%|██████▊   | 253843/371472 [9:08:50<8:38:50,  3.78it/s]
 68%|██████▊   | 253844/371472 [9:08:50<8:59:14,  3.64it/s]
 68%|██████▊   | 253845/371472 [9:08:51<8:45:12,  3.73it/s]
 68%|██████▊   | 253846/371472 [9:08:51<8:47:29,  3.72it/s]
 68%|██████▊   | 253847/371472 [9:08:51<9:15:15,  3.53it/s]
 68%|██████▊   | 253848/371472 [9:08:52<8:55:34,  3.66it/s]
 68%|██████▊   | 253849/371472 [9:08:52<8:55:33,  3.66it/s]
 68%|██████▊   | 253850/371472 [9:08:52<8:55:50,  3.66it/s]
 68%|██████▊   | 253851/371472 [9:08:52<9:00:32,  3.63it/s]
 68%|██████▊   | 253852/371472 [9:08:53<8:47:10,  3.72it/s]
 68%|██████▊   | 253853/371472 [9:08:53<8:40:53,  3.76it/s]
 68%|██████▊   | 253854/371472 [9:08:53<8:45:45,  3.73it/s]
 68%|██████▊   | 253855/371472 [9:08:53<8:42:41,  3.75it/s]
 68%|██████▊   | 253856/371472 [9:08:54<8:46:03,  3.73it/s]
 68%|██████▊   | 253857/371472 [9:08:54<8:22:54,  3.90it/s]
 68%|██████▊   | 253858/371472 [9:08:54<9:17:57,  3.51it/s]
 68%|██████▊   | 253859/371472 [9:08:55<10:05:54,  3.24it/s]
 68%|██████▊   | 253860/371472 [9:08:55<9:35:35,  3.41it/s] 
                                                           
{'loss': 3.0294, 'learning_rate': 3.8510310500118507e-07, 'epoch': 10.93}
+
 68%|██████▊   | 253860/371472 [9:08:55<9:35:35,  3.41it/s]
 68%|██████▊   | 253861/371472 [9:08:55<9:00:12,  3.63it/s]
 68%|██████▊   | 253862/371472 [9:08:55<9:04:34,  3.60it/s]
 68%|██████▊   | 253863/371472 [9:08:56<8:43:02,  3.75it/s]
 68%|██████▊   | 253864/371472 [9:08:56<9:37:57,  3.39it/s]
 68%|██████▊   | 253865/371472 [9:08:56<9:10:18,  3.56it/s]
 68%|██████▊   | 253866/371472 [9:08:57<9:50:10,  3.32it/s]
 68%|██████▊   | 253867/371472 [9:08:57<9:59:53,  3.27it/s]
 68%|██████▊   | 253868/371472 [9:08:57<10:22:14,  3.15it/s]
 68%|██████▊   | 253869/371472 [9:08:58<10:10:36,  3.21it/s]
 68%|██████▊   | 253870/371472 [9:08:58<9:52:08,  3.31it/s] 
 68%|██████▊   | 253871/371472 [9:08:58<9:53:56,  3.30it/s]
 68%|██████▊   | 253872/371472 [9:08:58<9:43:47,  3.36it/s]
 68%|██████▊   | 253873/371472 [9:08:59<9:03:56,  3.60it/s]
 68%|██████▊   | 253874/371472 [9:08:59<9:30:40,  3.43it/s]
 68%|██████▊   | 253875/371472 [9:08:59<9:35:12,  3.41it/s]
 68%|██████▊   | 253876/371472 [9:09:00<9:40:18,  3.38it/s]
 68%|██████▊   | 253877/371472 [9:09:00<9:56:04,  3.29it/s]
 68%|██████▊   | 253878/371472 [9:09:00<9:33:21,  3.42it/s]
 68%|██████▊   | 253879/371472 [9:09:00<9:18:16,  3.51it/s]
 68%|██████▊   | 253880/371472 [9:09:01<9:40:14,  3.38it/s]
                                                           
{'loss': 2.889, 'learning_rate': 3.8505462302570624e-07, 'epoch': 10.94}
+
 68%|██████▊   | 253880/371472 [9:09:01<9:40:14,  3.38it/s]
 68%|██████▊   | 253881/371472 [9:09:01<9:39:55,  3.38it/s]
 68%|██████▊   | 253882/371472 [9:09:01<9:09:06,  3.57it/s]
 68%|██████▊   | 253883/371472 [9:09:02<8:51:01,  3.69it/s]
 68%|██████▊   | 253884/371472 [9:09:02<8:39:57,  3.77it/s]
 68%|██████▊   | 253885/371472 [9:09:02<8:48:08,  3.71it/s]
 68%|██████▊   | 253886/371472 [9:09:02<8:39:40,  3.77it/s]
 68%|██████▊   | 253887/371472 [9:09:03<9:06:28,  3.59it/s]
 68%|██████▊   | 253888/371472 [9:09:03<8:43:39,  3.74it/s]
 68%|██████▊   | 253889/371472 [9:09:03<8:38:30,  3.78it/s]
 68%|██████▊   | 253890/371472 [9:09:03<8:50:03,  3.70it/s]
 68%|██████▊   | 253891/371472 [9:09:04<8:31:52,  3.83it/s]
 68%|██████▊   | 253892/371472 [9:09:04<8:47:29,  3.72it/s]
 68%|██████▊   | 253893/371472 [9:09:04<9:07:44,  3.58it/s]
 68%|██████▊   | 253894/371472 [9:09:05<9:33:54,  3.41it/s]
 68%|██████▊   | 253895/371472 [9:09:05<9:43:02,  3.36it/s]
 68%|██████▊   | 253896/371472 [9:09:05<9:14:38,  3.53it/s]
 68%|██████▊   | 253897/371472 [9:09:05<8:57:07,  3.65it/s]
 68%|██████▊   | 253898/371472 [9:09:06<9:04:19,  3.60it/s]
 68%|██████▊   | 253899/371472 [9:09:06<8:45:49,  3.73it/s]
 68%|██████▊   | 253900/371472 [9:09:06<9:04:02,  3.60it/s]
                                                           
{'loss': 2.8061, 'learning_rate': 3.850061410502273e-07, 'epoch': 10.94}
+
 68%|██████▊   | 253900/371472 [9:09:06<9:04:02,  3.60it/s]
 68%|██████▊   | 253901/371472 [9:09:07<9:40:01,  3.38it/s]
 68%|██████▊   | 253902/371472 [9:09:07<9:30:42,  3.43it/s]
 68%|██████▊   | 253903/371472 [9:09:07<9:14:42,  3.53it/s]
 68%|██████▊   | 253904/371472 [9:09:07<9:34:42,  3.41it/s]
 68%|██████▊   | 253905/371472 [9:09:08<9:13:18,  3.54it/s]
 68%|██████▊   | 253906/371472 [9:09:08<9:02:04,  3.61it/s]
 68%|██████▊   | 253907/371472 [9:09:08<9:29:25,  3.44it/s]
 68%|██████▊   | 253908/371472 [9:09:09<9:03:45,  3.60it/s]
 68%|██████▊   | 253909/371472 [9:09:09<9:07:55,  3.58it/s]
 68%|██████▊   | 253910/371472 [9:09:09<9:16:22,  3.52it/s]
 68%|██████▊   | 253911/371472 [9:09:09<9:14:35,  3.53it/s]
 68%|██████▊   | 253912/371472 [9:09:10<9:12:21,  3.55it/s]
 68%|██████▊   | 253913/371472 [9:09:10<9:45:55,  3.34it/s]
 68%|██████▊   | 253914/371472 [9:09:10<9:27:02,  3.46it/s]
 68%|██████▊   | 253915/371472 [9:09:11<9:21:19,  3.49it/s]
 68%|██████▊   | 253916/371472 [9:09:11<9:18:39,  3.51it/s]
 68%|██████▊   | 253917/371472 [9:09:11<9:10:08,  3.56it/s]
 68%|██████▊   | 253918/371472 [9:09:11<8:57:15,  3.65it/s]
 68%|██████▊   | 253919/371472 [9:09:12<9:03:47,  3.60it/s]
 68%|██████▊   | 253920/371472 [9:09:12<8:43:48,  3.74it/s]
                                                           
{'loss': 2.9312, 'learning_rate': 3.8495765907474844e-07, 'epoch': 10.94}
+
 68%|██████▊   | 253920/371472 [9:09:12<8:43:48,  3.74it/s]
 68%|██████▊   | 253921/371472 [9:09:12<8:37:33,  3.79it/s]
 68%|██████▊   | 253922/371472 [9:09:12<8:54:53,  3.66it/s]
 68%|██████▊   | 253923/371472 [9:09:13<9:46:49,  3.34it/s]
 68%|██████▊   | 253924/371472 [9:09:13<9:18:18,  3.51it/s]
 68%|██████▊   | 253925/371472 [9:09:13<8:51:44,  3.68it/s]
 68%|██████▊   | 253926/371472 [9:09:14<9:20:11,  3.50it/s]
 68%|██████▊   | 253927/371472 [9:09:14<9:03:48,  3.60it/s]
 68%|██████▊   | 253928/371472 [9:09:14<8:54:34,  3.66it/s]
 68%|██████▊   | 253929/371472 [9:09:14<8:37:14,  3.79it/s]
 68%|██████▊   | 253930/371472 [9:09:15<8:28:25,  3.85it/s]
 68%|██████▊   | 253931/371472 [9:09:15<8:35:25,  3.80it/s]
 68%|██████▊   | 253932/371472 [9:09:15<8:26:12,  3.87it/s]
 68%|██████▊   | 253933/371472 [9:09:15<8:18:48,  3.93it/s]
 68%|██████▊   | 253934/371472 [9:09:16<8:58:43,  3.64it/s]
 68%|██████▊   | 253935/371472 [9:09:16<9:12:46,  3.54it/s]
 68%|██████▊   | 253936/371472 [9:09:16<8:53:46,  3.67it/s]
 68%|██████▊   | 253937/371472 [9:09:17<8:50:50,  3.69it/s]
 68%|██████▊   | 253938/371472 [9:09:17<8:39:47,  3.77it/s]
 68%|██████▊   | 253939/371472 [9:09:17<8:26:10,  3.87it/s]
 68%|██████▊   | 253940/371472 [9:09:17<8:44:12,  3.74it/s]
                                                           
{'loss': 2.914, 'learning_rate': 3.849091770992695e-07, 'epoch': 10.94}
+
 68%|██████▊   | 253940/371472 [9:09:17<8:44:12,  3.74it/s]
 68%|██████▊   | 253941/371472 [9:09:18<8:55:22,  3.66it/s]
 68%|██████▊   | 253942/371472 [9:09:18<8:49:35,  3.70it/s]
 68%|██████▊   | 253943/371472 [9:09:18<9:21:47,  3.49it/s]
 68%|██████▊   | 253944/371472 [9:09:18<9:42:23,  3.36it/s]
 68%|██████▊   | 253945/371472 [9:09:19<9:24:19,  3.47it/s]
 68%|██████▊   | 253946/371472 [9:09:19<9:00:33,  3.62it/s]
 68%|██████▊   | 253947/371472 [9:09:19<9:17:48,  3.51it/s]
 68%|██████▊   | 253948/371472 [9:09:20<9:04:03,  3.60it/s]
 68%|██████▊   | 253949/371472 [9:09:20<9:19:35,  3.50it/s]
 68%|██████▊   | 253950/371472 [9:09:20<9:22:46,  3.48it/s]
 68%|██████▊   | 253951/371472 [9:09:20<9:12:20,  3.55it/s]
 68%|██████▊   | 253952/371472 [9:09:21<9:31:36,  3.43it/s]
 68%|██████▊   | 253953/371472 [9:09:21<9:00:19,  3.62it/s]
 68%|██████▊   | 253954/371472 [9:09:21<9:07:12,  3.58it/s]
 68%|██████▊   | 253955/371472 [9:09:22<8:49:03,  3.70it/s]
 68%|██████▊   | 253956/371472 [9:09:22<8:34:42,  3.81it/s]
 68%|██████▊   | 253957/371472 [9:09:22<8:18:46,  3.93it/s]
 68%|██████▊   | 253958/371472 [9:09:22<8:34:30,  3.81it/s]
 68%|██████▊   | 253959/371472 [9:09:23<9:46:57,  3.34it/s]
 68%|██████▊   | 253960/371472 [9:09:23<10:05:32,  3.23it/s]
                                                            
{'loss': 2.8144, 'learning_rate': 3.848606951237906e-07, 'epoch': 10.94}
+
 68%|██████▊   | 253960/371472 [9:09:23<10:05:32,  3.23it/s]
 68%|██████▊   | 253961/371472 [9:09:23<9:52:06,  3.31it/s] 
 68%|██████▊   | 253962/371472 [9:09:24<10:04:22,  3.24it/s]
 68%|██████▊   | 253963/371472 [9:09:24<9:49:09,  3.32it/s] 
 68%|██████▊   | 253964/371472 [9:09:24<9:47:27,  3.33it/s]
 68%|██████▊   | 253965/371472 [9:09:24<9:41:18,  3.37it/s]
 68%|██████▊   | 253966/371472 [9:09:25<9:22:09,  3.48it/s]
 68%|██████▊   | 253967/371472 [9:09:25<9:49:07,  3.32it/s]
 68%|██████▊   | 253968/371472 [9:09:25<9:34:32,  3.41it/s]
 68%|██████▊   | 253969/371472 [9:09:26<9:13:08,  3.54it/s]
 68%|██████▊   | 253970/371472 [9:09:26<9:03:43,  3.60it/s]
 68%|██████▊   | 253971/371472 [9:09:26<8:48:36,  3.70it/s]
 68%|██████▊   | 253972/371472 [9:09:26<9:24:55,  3.47it/s]
 68%|██████▊   | 253973/371472 [9:09:27<8:53:03,  3.67it/s]
 68%|██████▊   | 253974/371472 [9:09:27<9:14:44,  3.53it/s]
 68%|██████▊   | 253975/371472 [9:09:27<8:55:50,  3.65it/s]
 68%|██████▊   | 253976/371472 [9:09:27<8:29:30,  3.84it/s]
 68%|██████▊   | 253977/371472 [9:09:28<8:56:52,  3.65it/s]
 68%|██████▊   | 253978/371472 [9:09:28<8:32:01,  3.82it/s]
 68%|██████▊   | 253979/371472 [9:09:28<8:46:45,  3.72it/s]
 68%|██████▊   | 253980/371472 [9:09:29<8:41:18,  3.76it/s]
                                                           
{'loss': 2.6128, 'learning_rate': 3.8481221314831176e-07, 'epoch': 10.94}
+
 68%|██████▊   | 253980/371472 [9:09:29<8:41:18,  3.76it/s]
 68%|██████▊   | 253981/371472 [9:09:29<8:40:12,  3.76it/s]
 68%|██████▊   | 253982/371472 [9:09:29<8:42:51,  3.75it/s]
 68%|██████▊   | 253983/371472 [9:09:29<8:23:36,  3.89it/s]
 68%|██████▊   | 253984/371472 [9:09:30<8:22:27,  3.90it/s]
 68%|██████▊   | 253985/371472 [9:09:30<8:30:24,  3.84it/s]
 68%|██████▊   | 253986/371472 [9:09:30<8:19:51,  3.92it/s]
 68%|██████▊   | 253987/371472 [9:09:30<8:39:12,  3.77it/s]
 68%|██████▊   | 253988/371472 [9:09:31<8:35:50,  3.80it/s]
 68%|██████▊   | 253989/371472 [9:09:31<9:46:55,  3.34it/s]
 68%|██████▊   | 253990/371472 [9:09:31<9:41:39,  3.37it/s]
 68%|██████▊   | 253991/371472 [9:09:32<9:25:47,  3.46it/s]
 68%|██████▊   | 253992/371472 [9:09:32<9:49:37,  3.32it/s]
 68%|██████▊   | 253993/371472 [9:09:32<9:43:21,  3.36it/s]
 68%|██████▊   | 253994/371472 [9:09:33<9:40:52,  3.37it/s]
 68%|██████▊   | 253995/371472 [9:09:33<9:34:39,  3.41it/s]
 68%|██████▊   | 253996/371472 [9:09:33<10:01:41,  3.25it/s]
 68%|██████▊   | 253997/371472 [9:09:33<10:12:04,  3.20it/s]
 68%|██████▊   | 253998/371472 [9:09:34<10:42:16,  3.05it/s]
 68%|██████▊   | 253999/371472 [9:09:34<9:50:48,  3.31it/s] 
 68%|██████▊   | 254000/371472 [9:09:34<9:23:51,  3.47it/s]
                                                           
{'loss': 2.6676, 'learning_rate': 3.847637311728328e-07, 'epoch': 10.94}
+
 68%|██████▊   | 254000/371472 [9:09:34<9:23:51,  3.47it/s]
 68%|██████▊   | 254001/371472 [9:09:35<9:02:41,  3.61it/s]
 68%|██████▊   | 254002/371472 [9:09:35<8:40:31,  3.76it/s]
 68%|██████▊   | 254003/371472 [9:09:35<9:00:09,  3.62it/s]
 68%|██████▊   | 254004/371472 [9:09:35<8:53:02,  3.67it/s]
 68%|██████▊   | 254005/371472 [9:09:36<9:03:56,  3.60it/s]
 68%|██████▊   | 254006/371472 [9:09:36<8:59:05,  3.63it/s]
 68%|██████▊   | 254007/371472 [9:09:36<8:30:59,  3.83it/s]
 68%|██████▊   | 254008/371472 [9:09:36<8:31:12,  3.83it/s]
 68%|██████▊   | 254009/371472 [9:09:37<8:21:30,  3.90it/s]
 68%|██████▊   | 254010/371472 [9:09:37<8:55:09,  3.66it/s]
 68%|██████▊   | 254011/371472 [9:09:37<9:00:52,  3.62it/s]
 68%|██████▊   | 254012/371472 [9:09:38<9:24:24,  3.47it/s]
 68%|██████▊   | 254013/371472 [9:09:38<9:14:37,  3.53it/s]
 68%|██████▊   | 254014/371472 [9:09:38<9:40:50,  3.37it/s]
 68%|██████▊   | 254015/371472 [9:09:39<9:48:59,  3.32it/s]
 68%|██████▊   | 254016/371472 [9:09:39<9:46:11,  3.34it/s]
 68%|██████▊   | 254017/371472 [9:09:39<9:40:47,  3.37it/s]
 68%|██████▊   | 254018/371472 [9:09:39<9:49:42,  3.32it/s]
 68%|██████▊   | 254019/371472 [9:09:40<9:26:55,  3.45it/s]
 68%|██████▊   | 254020/371472 [9:09:40<8:59:44,  3.63it/s]
                                                           
{'loss': 3.024, 'learning_rate': 3.8471524919735396e-07, 'epoch': 10.94}
+
 68%|██████▊   | 254020/371472 [9:09:40<8:59:44,  3.63it/s]
 68%|██████▊   | 254021/371472 [9:09:40<9:08:02,  3.57it/s]
 68%|██████▊   | 254022/371472 [9:09:40<9:08:45,  3.57it/s]
 68%|██████▊   | 254023/371472 [9:09:41<8:55:30,  3.66it/s]
 68%|██████▊   | 254024/371472 [9:09:41<9:39:18,  3.38it/s]
 68%|██████▊   | 254025/371472 [9:09:41<9:24:04,  3.47it/s]
 68%|██████▊   | 254026/371472 [9:09:42<9:16:46,  3.52it/s]
 68%|██████▊   | 254027/371472 [9:09:42<9:21:49,  3.48it/s]
 68%|██████▊   | 254028/371472 [9:09:42<9:14:20,  3.53it/s]
 68%|██████▊   | 254029/371472 [9:09:42<9:07:27,  3.58it/s]
 68%|██████▊   | 254030/371472 [9:09:43<8:49:24,  3.70it/s]
 68%|██████▊   | 254031/371472 [9:09:43<8:46:19,  3.72it/s]
 68%|██████▊   | 254032/371472 [9:09:43<8:22:49,  3.89it/s]
 68%|██████▊   | 254033/371472 [9:09:43<8:28:55,  3.85it/s]
 68%|██████▊   | 254034/371472 [9:09:44<8:41:11,  3.76it/s]
 68%|██████▊   | 254035/371472 [9:09:44<8:43:22,  3.74it/s]
 68%|██████▊   | 254036/371472 [9:09:44<8:41:44,  3.75it/s]
 68%|██████▊   | 254037/371472 [9:09:45<9:05:40,  3.59it/s]
 68%|██████▊   | 254038/371472 [9:09:45<8:55:31,  3.65it/s]
 68%|██████▊   | 254039/371472 [9:09:45<8:39:33,  3.77it/s]
 68%|██████▊   | 254040/371472 [9:09:45<8:37:11,  3.78it/s]
                                                           
{'loss': 2.8975, 'learning_rate': 3.8466676722187503e-07, 'epoch': 10.94}
+
 68%|██████▊   | 254040/371472 [9:09:45<8:37:11,  3.78it/s]
 68%|██████▊   | 254041/371472 [9:09:46<8:31:00,  3.83it/s]
 68%|██████▊   | 254042/371472 [9:09:46<8:34:00,  3.81it/s]
 68%|██████▊   | 254043/371472 [9:09:46<8:27:49,  3.85it/s]
 68%|██████▊   | 254044/371472 [9:09:46<8:34:48,  3.80it/s]
 68%|██████▊   | 254045/371472 [9:09:47<8:48:23,  3.70it/s]
 68%|██████▊   | 254046/371472 [9:09:47<8:49:28,  3.70it/s]
 68%|██████▊   | 254047/371472 [9:09:47<8:50:36,  3.69it/s]
 68%|██████▊   | 254048/371472 [9:09:47<8:38:45,  3.77it/s]
 68%|██████▊   | 254049/371472 [9:09:48<8:46:40,  3.72it/s]
 68%|██████▊   | 254050/371472 [9:09:48<8:53:43,  3.67it/s]
 68%|██████▊   | 254051/371472 [9:09:48<9:31:59,  3.42it/s]
 68%|██████▊   | 254052/371472 [9:09:49<9:28:04,  3.44it/s]
 68%|██████▊   | 254053/371472 [9:09:49<9:51:49,  3.31it/s]
 68%|██████▊   | 254054/371472 [9:09:49<9:22:37,  3.48it/s]
 68%|██████▊   | 254055/371472 [9:09:50<9:29:13,  3.44it/s]
 68%|██████▊   | 254056/371472 [9:09:50<9:08:44,  3.57it/s]
 68%|██████▊   | 254057/371472 [9:09:50<9:20:01,  3.49it/s]
 68%|██████▊   | 254058/371472 [9:09:50<9:33:41,  3.41it/s]
 68%|██████▊   | 254059/371472 [9:09:51<9:44:09,  3.35it/s]
 68%|██████▊   | 254060/371472 [9:09:51<9:27:23,  3.45it/s]
                                                           
{'loss': 2.9072, 'learning_rate': 3.8461828524639615e-07, 'epoch': 10.94}
+
 68%|██████▊   | 254060/371472 [9:09:51<9:27:23,  3.45it/s]
 68%|██████▊   | 254061/371472 [9:09:51<9:17:18,  3.51it/s]
 68%|██████▊   | 254062/371472 [9:09:52<9:19:21,  3.50it/s]
 68%|██████▊   | 254063/371472 [9:09:52<9:03:39,  3.60it/s]
 68%|██████▊   | 254064/371472 [9:09:52<9:02:23,  3.61it/s]
 68%|██████▊   | 254065/371472 [9:09:52<9:06:24,  3.58it/s]
 68%|██████▊   | 254066/371472 [9:09:53<9:06:09,  3.58it/s]
 68%|██████▊   | 254067/371472 [9:09:53<9:01:31,  3.61it/s]
 68%|██████▊   | 254068/371472 [9:09:53<9:09:37,  3.56it/s]
 68%|██████▊   | 254069/371472 [9:09:54<9:08:32,  3.57it/s]
 68%|██████▊   | 254070/371472 [9:09:54<9:02:47,  3.60it/s]
 68%|██████▊   | 254071/371472 [9:09:54<8:52:53,  3.67it/s]
 68%|██████▊   | 254072/371472 [9:09:54<8:54:07,  3.66it/s]
 68%|██████▊   | 254073/371472 [9:09:55<8:49:44,  3.69it/s]
 68%|██████▊   | 254074/371472 [9:09:55<8:58:30,  3.63it/s]
 68%|██████▊   | 254075/371472 [9:09:55<8:33:54,  3.81it/s]
 68%|██████▊   | 254076/371472 [9:09:55<8:37:36,  3.78it/s]
 68%|██████▊   | 254077/371472 [9:09:56<9:15:24,  3.52it/s]
 68%|██████▊   | 254078/371472 [9:09:56<9:17:16,  3.51it/s]
 68%|██████▊   | 254079/371472 [9:09:56<10:04:14,  3.24it/s]
 68%|██████▊   | 254080/371472 [9:09:57<10:37:19,  3.07it/s]
                                                            
{'loss': 2.9482, 'learning_rate': 3.845698032709172e-07, 'epoch': 10.94}
+
 68%|██████▊   | 254080/371472 [9:09:57<10:37:19,  3.07it/s]
 68%|██████▊   | 254081/371472 [9:09:57<9:55:57,  3.28it/s] 
 68%|██████▊   | 254082/371472 [9:09:57<9:26:13,  3.46it/s]
 68%|██████▊   | 254083/371472 [9:09:58<9:36:54,  3.39it/s]
 68%|██████▊   | 254084/371472 [9:09:58<9:56:44,  3.28it/s]
 68%|██████▊   | 254085/371472 [9:09:58<9:34:00,  3.41it/s]
 68%|██████▊   | 254086/371472 [9:09:58<9:25:32,  3.46it/s]
 68%|██████▊   | 254087/371472 [9:09:59<9:17:22,  3.51it/s]
 68%|██████▊   | 254088/371472 [9:09:59<9:17:52,  3.51it/s]
 68%|██████▊   | 254089/371472 [9:09:59<9:04:13,  3.59it/s]
 68%|██████▊   | 254090/371472 [9:09:59<8:53:26,  3.67it/s]
 68%|██████▊   | 254091/371472 [9:10:00<8:33:19,  3.81it/s]
 68%|██████▊   | 254092/371472 [9:10:00<8:33:38,  3.81it/s]
 68%|██████▊   | 254093/371472 [9:10:00<8:31:33,  3.82it/s]
 68%|██████▊   | 254094/371472 [9:10:01<8:29:56,  3.84it/s]
 68%|██████▊   | 254095/371472 [9:10:01<8:28:06,  3.85it/s]
 68%|██████▊   | 254096/371472 [9:10:01<8:22:32,  3.89it/s]
 68%|██████▊   | 254097/371472 [9:10:01<8:21:52,  3.90it/s]
 68%|██████▊   | 254098/371472 [9:10:02<8:12:03,  3.98it/s]
 68%|██████▊   | 254099/371472 [9:10:02<8:20:24,  3.91it/s]
 68%|██████▊   | 254100/371472 [9:10:02<8:15:28,  3.95it/s]
                                                           
{'loss': 2.8628, 'learning_rate': 3.845213212954384e-07, 'epoch': 10.94}
+
 68%|██████▊   | 254100/371472 [9:10:02<8:15:28,  3.95it/s]
 68%|██████▊   | 254101/371472 [9:10:02<8:17:46,  3.93it/s]
 68%|██████▊   | 254102/371472 [9:10:03<8:13:23,  3.96it/s]
 68%|██████▊   | 254103/371472 [9:10:03<8:15:47,  3.95it/s]
 68%|██████▊   | 254104/371472 [9:10:03<8:12:19,  3.97it/s]
 68%|██████▊   | 254105/371472 [9:10:03<8:22:38,  3.89it/s]
 68%|██████▊   | 254106/371472 [9:10:04<8:55:44,  3.65it/s]
 68%|██████▊   | 254107/371472 [9:10:04<8:45:20,  3.72it/s]
 68%|██████▊   | 254108/371472 [9:10:04<8:47:05,  3.71it/s]
 68%|██████▊   | 254109/371472 [9:10:04<8:30:08,  3.83it/s]
 68%|██████▊   | 254110/371472 [9:10:05<8:15:32,  3.95it/s]
 68%|██████▊   | 254111/371472 [9:10:05<9:51:58,  3.30it/s]
 68%|██████▊   | 254112/371472 [9:10:05<9:42:16,  3.36it/s]
 68%|██████▊   | 254113/371472 [9:10:06<9:45:25,  3.34it/s]
 68%|██████▊   | 254114/371472 [9:10:06<9:09:42,  3.56it/s]
 68%|██████▊   | 254115/371472 [9:10:06<9:25:20,  3.46it/s]
 68%|██████▊   | 254116/371472 [9:10:06<9:10:48,  3.55it/s]
 68%|██████▊   | 254117/371472 [9:10:07<10:01:01,  3.25it/s]
 68%|██████▊   | 254118/371472 [9:10:07<9:46:44,  3.33it/s] 
 68%|██████▊   | 254119/371472 [9:10:07<9:25:49,  3.46it/s]
 68%|██████▊   | 254120/371472 [9:10:08<9:07:58,  3.57it/s]
                                                           
{'loss': 3.0014, 'learning_rate': 3.844728393199594e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254120/371472 [9:10:08<9:07:58,  3.57it/s]
 68%|██████▊   | 254121/371472 [9:10:08<9:09:11,  3.56it/s]
 68%|██████▊   | 254122/371472 [9:10:08<8:57:14,  3.64it/s]
 68%|██████▊   | 254123/371472 [9:10:09<9:45:07,  3.34it/s]
 68%|██████▊   | 254124/371472 [9:10:09<9:19:30,  3.50it/s]
 68%|██████▊   | 254125/371472 [9:10:09<9:24:45,  3.46it/s]
 68%|██████▊   | 254126/371472 [9:10:09<9:00:07,  3.62it/s]
 68%|██████▊   | 254127/371472 [9:10:10<8:56:14,  3.65it/s]
 68%|██████▊   | 254128/371472 [9:10:10<8:31:04,  3.83it/s]
 68%|██████▊   | 254129/371472 [9:10:10<9:14:11,  3.53it/s]
 68%|██████▊   | 254130/371472 [9:10:10<8:56:05,  3.65it/s]
 68%|██████▊   | 254131/371472 [9:10:11<9:07:51,  3.57it/s]
 68%|██████▊   | 254132/371472 [9:10:11<8:54:23,  3.66it/s]
 68%|██████▊   | 254133/371472 [9:10:11<9:29:16,  3.44it/s]
 68%|██████▊   | 254134/371472 [9:10:12<9:05:51,  3.58it/s]
 68%|██████▊   | 254135/371472 [9:10:12<9:23:44,  3.47it/s]
 68%|██████▊   | 254136/371472 [9:10:12<9:20:01,  3.49it/s]
 68%|██████▊   | 254137/371472 [9:10:12<8:54:39,  3.66it/s]
 68%|██████▊   | 254138/371472 [9:10:13<8:52:25,  3.67it/s]
 68%|██████▊   | 254139/371472 [9:10:13<8:41:28,  3.75it/s]
 68%|██████▊   | 254140/371472 [9:10:13<9:03:11,  3.60it/s]
                                                           
{'loss': 2.85, 'learning_rate': 3.844243573444806e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254140/371472 [9:10:13<9:03:11,  3.60it/s]
 68%|██████▊   | 254141/371472 [9:10:13<8:43:45,  3.73it/s]
 68%|██████▊   | 254142/371472 [9:10:14<8:37:36,  3.78it/s]
 68%|██████▊   | 254143/371472 [9:10:14<8:40:45,  3.76it/s]
 68%|██████▊   | 254144/371472 [9:10:14<9:14:53,  3.52it/s]
 68%|██████▊   | 254145/371472 [9:10:15<9:11:40,  3.54it/s]
 68%|██████▊   | 254146/371472 [9:10:15<9:21:27,  3.48it/s]
 68%|██████▊   | 254147/371472 [9:10:15<9:05:08,  3.59it/s]
 68%|██████▊   | 254148/371472 [9:10:15<8:53:29,  3.67it/s]
 68%|██████▊   | 254149/371472 [9:10:16<9:32:14,  3.42it/s]
 68%|██████▊   | 254150/371472 [9:10:16<9:20:45,  3.49it/s]
 68%|██████▊   | 254151/371472 [9:10:16<9:25:05,  3.46it/s]
 68%|██████▊   | 254152/371472 [9:10:17<10:09:21,  3.21it/s]
 68%|██████▊   | 254153/371472 [9:10:17<9:45:56,  3.34it/s] 
 68%|██████▊   | 254154/371472 [9:10:17<9:23:30,  3.47it/s]
 68%|██████▊   | 254155/371472 [9:10:18<10:31:34,  3.10it/s]
 68%|██████▊   | 254156/371472 [9:10:18<10:20:40,  3.15it/s]
 68%|██████▊   | 254157/371472 [9:10:18<10:06:06,  3.23it/s]
 68%|██████▊   | 254158/371472 [9:10:19<10:09:24,  3.21it/s]
 68%|██████▊   | 254159/371472 [9:10:19<9:47:57,  3.33it/s] 
 68%|██████▊   | 254160/371472 [9:10:19<9:15:57,  3.52it/s]
                                                           
{'loss': 2.7256, 'learning_rate': 3.8437587536900167e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254160/371472 [9:10:19<9:15:57,  3.52it/s]
 68%|██████▊   | 254161/371472 [9:10:19<9:34:39,  3.40it/s]
 68%|██████▊   | 254162/371472 [9:10:20<9:13:35,  3.53it/s]
 68%|██████▊   | 254163/371472 [9:10:20<8:59:28,  3.62it/s]
 68%|██████▊   | 254164/371472 [9:10:20<8:40:41,  3.75it/s]
 68%|██████▊   | 254165/371472 [9:10:20<8:25:18,  3.87it/s]
 68%|██████▊   | 254166/371472 [9:10:21<8:32:34,  3.81it/s]
 68%|██████▊   | 254167/371472 [9:10:21<8:32:25,  3.82it/s]
 68%|██████▊   | 254168/371472 [9:10:21<8:30:35,  3.83it/s]
 68%|██████▊   | 254169/371472 [9:10:21<8:24:43,  3.87it/s]
 68%|██████▊   | 254170/371472 [9:10:22<8:19:10,  3.92it/s]
 68%|██████▊   | 254171/371472 [9:10:22<8:37:17,  3.78it/s]
 68%|██████▊   | 254172/371472 [9:10:22<8:38:42,  3.77it/s]
 68%|██████▊   | 254173/371472 [9:10:22<8:21:58,  3.89it/s]
 68%|██████▊   | 254174/371472 [9:10:23<8:29:08,  3.84it/s]
 68%|██████▊   | 254175/371472 [9:10:23<8:25:35,  3.87it/s]
 68%|██████▊   | 254176/371472 [9:10:23<8:36:49,  3.78it/s]
 68%|██████▊   | 254177/371472 [9:10:24<9:12:12,  3.54it/s]
 68%|██████▊   | 254178/371472 [9:10:24<8:59:07,  3.63it/s]
 68%|██████▊   | 254179/371472 [9:10:24<9:07:39,  3.57it/s]
 68%|██████▊   | 254180/371472 [9:10:24<9:02:48,  3.60it/s]
                                                           
{'loss': 2.9503, 'learning_rate': 3.843273933935228e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254180/371472 [9:10:24<9:02:48,  3.60it/s]
 68%|██████▊   | 254181/371472 [9:10:25<10:38:58,  3.06it/s]
 68%|██████▊   | 254182/371472 [9:10:25<9:59:33,  3.26it/s] 
 68%|██████▊   | 254183/371472 [9:10:25<9:52:55,  3.30it/s]
 68%|██████▊   | 254184/371472 [9:10:26<10:31:10,  3.10it/s]
 68%|██████▊   | 254185/371472 [9:10:26<10:01:06,  3.25it/s]
 68%|██████▊   | 254186/371472 [9:10:26<9:34:03,  3.41it/s] 
 68%|██████▊   | 254187/371472 [9:10:27<9:01:30,  3.61it/s]
 68%|██████▊   | 254188/371472 [9:10:27<9:49:33,  3.32it/s]
 68%|██████▊   | 254189/371472 [9:10:27<9:39:36,  3.37it/s]
 68%|██████▊   | 254190/371472 [9:10:27<9:35:06,  3.40it/s]
 68%|██████▊   | 254191/371472 [9:10:28<9:50:11,  3.31it/s]
 68%|██████▊   | 254192/371472 [9:10:28<9:24:13,  3.46it/s]
 68%|██████▊   | 254193/371472 [9:10:28<9:27:01,  3.45it/s]
 68%|██████▊   | 254194/371472 [9:10:29<9:23:22,  3.47it/s]
 68%|██████▊   | 254195/371472 [9:10:29<9:21:22,  3.48it/s]
 68%|██████▊   | 254196/371472 [9:10:29<9:08:00,  3.57it/s]
 68%|██████▊   | 254197/371472 [9:10:29<8:40:38,  3.75it/s]
 68%|██████▊   | 254198/371472 [9:10:30<8:25:18,  3.87it/s]
 68%|██████▊   | 254199/371472 [9:10:30<8:46:54,  3.71it/s]
 68%|██████▊   | 254200/371472 [9:10:30<8:46:54,  3.71it/s]
                                                           
{'loss': 2.8861, 'learning_rate': 3.8427891141804386e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254200/371472 [9:10:30<8:46:54,  3.71it/s]
 68%|██████▊   | 254201/371472 [9:10:31<9:15:58,  3.52it/s]
 68%|██████▊   | 254202/371472 [9:10:31<8:54:38,  3.66it/s]
 68%|██████▊   | 254203/371472 [9:10:31<8:56:38,  3.64it/s]
 68%|██████▊   | 254204/371472 [9:10:31<8:55:34,  3.65it/s]
 68%|██████▊   | 254205/371472 [9:10:32<8:43:32,  3.73it/s]
 68%|██████▊   | 254206/371472 [9:10:32<8:35:45,  3.79it/s]
 68%|██████▊   | 254207/371472 [9:10:32<8:43:01,  3.74it/s]
 68%|██████▊   | 254208/371472 [9:10:32<9:00:55,  3.61it/s]
 68%|██████▊   | 254209/371472 [9:10:33<8:58:06,  3.63it/s]
 68%|██████▊   | 254210/371472 [9:10:33<9:50:21,  3.31it/s]
 68%|██████▊   | 254211/371472 [9:10:33<9:15:31,  3.52it/s]
 68%|██████▊   | 254212/371472 [9:10:34<9:23:25,  3.47it/s]
 68%|██████▊   | 254213/371472 [9:10:34<9:24:28,  3.46it/s]
 68%|██████▊   | 254214/371472 [9:10:34<9:00:58,  3.61it/s]
 68%|██████▊   | 254215/371472 [9:10:34<9:49:35,  3.31it/s]
 68%|██████▊   | 254216/371472 [9:10:35<9:31:18,  3.42it/s]
 68%|██████▊   | 254217/371472 [9:10:35<9:31:53,  3.42it/s]
 68%|██████▊   | 254218/371472 [9:10:35<9:17:23,  3.51it/s]
 68%|██████▊   | 254219/371472 [9:10:36<11:09:46,  2.92it/s]
 68%|██████▊   | 254220/371472 [9:10:36<10:05:58,  3.22it/s]
                                                            
{'loss': 2.8803, 'learning_rate': 3.8423042944256504e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254220/371472 [9:10:36<10:05:58,  3.22it/s]
 68%|██████▊   | 254221/371472 [9:10:36<9:34:55,  3.40it/s] 
 68%|██████▊   | 254222/371472 [9:10:37<9:45:33,  3.34it/s]
 68%|██████▊   | 254223/371472 [9:10:37<9:42:05,  3.36it/s]
 68%|██████▊   | 254224/371472 [9:10:37<9:17:26,  3.51it/s]
 68%|██████▊   | 254225/371472 [9:10:37<8:57:02,  3.64it/s]
 68%|██████▊   | 254226/371472 [9:10:38<9:15:35,  3.52it/s]
 68%|██████▊   | 254227/371472 [9:10:38<8:50:21,  3.68it/s]
 68%|██████▊   | 254228/371472 [9:10:38<8:54:15,  3.66it/s]
 68%|██████▊   | 254229/371472 [9:10:38<8:34:21,  3.80it/s]
 68%|██████▊   | 254230/371472 [9:10:39<8:22:43,  3.89it/s]
 68%|██████▊   | 254231/371472 [9:10:39<8:31:13,  3.82it/s]
 68%|██████▊   | 254232/371472 [9:10:39<8:48:50,  3.69it/s]
 68%|██████▊   | 254233/371472 [9:10:40<10:27:45,  3.11it/s]
 68%|██████▊   | 254234/371472 [9:10:40<9:45:31,  3.34it/s] 
 68%|██████▊   | 254235/371472 [9:10:40<9:21:43,  3.48it/s]
 68%|██████▊   | 254236/371472 [9:10:40<8:53:52,  3.66it/s]
 68%|██████▊   | 254237/371472 [9:10:41<9:51:05,  3.31it/s]
 68%|██████▊   | 254238/371472 [9:10:41<10:19:17,  3.16it/s]
 68%|██████▊   | 254239/371472 [9:10:41<9:49:00,  3.32it/s] 
 68%|██████▊   | 254240/371472 [9:10:42<9:58:25,  3.26it/s]
                                                           
{'loss': 2.8295, 'learning_rate': 3.841819474670861e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254240/371472 [9:10:42<9:58:25,  3.26it/s]
 68%|██████▊   | 254241/371472 [9:10:42<9:40:08,  3.37it/s]
 68%|██████▊   | 254242/371472 [9:10:42<9:32:19,  3.41it/s]
 68%|██████▊   | 254243/371472 [9:10:43<8:59:38,  3.62it/s]
 68%|██████▊   | 254244/371472 [9:10:43<8:40:15,  3.76it/s]
 68%|██████▊   | 254245/371472 [9:10:43<8:33:35,  3.80it/s]
 68%|██████▊   | 254246/371472 [9:10:43<8:42:13,  3.74it/s]
 68%|██████▊   | 254247/371472 [9:10:44<9:12:25,  3.54it/s]
 68%|██████▊   | 254248/371472 [9:10:44<8:59:07,  3.62it/s]
 68%|██████▊   | 254249/371472 [9:10:44<9:12:51,  3.53it/s]
 68%|██████▊   | 254250/371472 [9:10:44<9:11:21,  3.54it/s]
 68%|██████▊   | 254251/371472 [9:10:45<8:45:17,  3.72it/s]
 68%|██████▊   | 254252/371472 [9:10:45<8:59:37,  3.62it/s]
 68%|██████▊   | 254253/371472 [9:10:45<9:39:59,  3.37it/s]
 68%|██████▊   | 254254/371472 [9:10:46<9:37:07,  3.39it/s]
 68%|██████▊   | 254255/371472 [9:10:46<9:05:06,  3.58it/s]
 68%|██████▊   | 254256/371472 [9:10:46<8:48:25,  3.70it/s]
 68%|██████▊   | 254257/371472 [9:10:46<9:04:48,  3.59it/s]
 68%|██████▊   | 254258/371472 [9:10:47<10:04:10,  3.23it/s]
 68%|██████▊   | 254259/371472 [9:10:47<9:34:24,  3.40it/s] 
 68%|██████▊   | 254260/371472 [9:10:47<8:59:14,  3.62it/s]
                                                           
{'loss': 3.0234, 'learning_rate': 3.8413346549160724e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254260/371472 [9:10:47<8:59:14,  3.62it/s]
 68%|██████▊   | 254261/371472 [9:10:48<9:15:58,  3.51it/s]
 68%|██████▊   | 254262/371472 [9:10:48<8:56:35,  3.64it/s]
 68%|██████▊   | 254263/371472 [9:10:48<8:44:51,  3.72it/s]
 68%|██████▊   | 254264/371472 [9:10:48<9:03:16,  3.60it/s]
 68%|██████▊   | 254265/371472 [9:10:49<8:59:55,  3.62it/s]
 68%|██████▊   | 254266/371472 [9:10:49<8:47:24,  3.70it/s]
 68%|██████▊   | 254267/371472 [9:10:49<9:12:59,  3.53it/s]
 68%|██████▊   | 254268/371472 [9:10:50<8:57:10,  3.64it/s]
 68%|██████▊   | 254269/371472 [9:10:50<8:47:29,  3.70it/s]
 68%|██████▊   | 254270/371472 [9:10:50<8:33:36,  3.80it/s]
 68%|██████▊   | 254271/371472 [9:10:50<8:29:14,  3.84it/s]
 68%|██████▊   | 254272/371472 [9:10:51<8:21:44,  3.89it/s]
 68%|██████▊   | 254273/371472 [9:10:51<8:29:37,  3.83it/s]
 68%|██████▊   | 254274/371472 [9:10:51<8:23:00,  3.88it/s]
 68%|██████▊   | 254275/371472 [9:10:51<8:27:25,  3.85it/s]
 68%|██████▊   | 254276/371472 [9:10:52<8:35:16,  3.79it/s]
 68%|██████▊   | 254277/371472 [9:10:52<8:32:06,  3.81it/s]
 68%|██████▊   | 254278/371472 [9:10:52<8:56:45,  3.64it/s]
 68%|██████▊   | 254279/371472 [9:10:52<8:51:07,  3.68it/s]
 68%|██████▊   | 254280/371472 [9:10:53<8:51:06,  3.68it/s]
                                                           
{'loss': 2.8308, 'learning_rate': 3.8408498351612836e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254280/371472 [9:10:53<8:51:06,  3.68it/s]
 68%|██████▊   | 254281/371472 [9:10:53<8:38:29,  3.77it/s]
 68%|██████▊   | 254282/371472 [9:10:53<9:22:05,  3.47it/s]
 68%|██████▊   | 254283/371472 [9:10:54<9:54:10,  3.29it/s]
 68%|██████▊   | 254284/371472 [9:10:54<9:24:42,  3.46it/s]
 68%|██████▊   | 254285/371472 [9:10:54<8:50:18,  3.68it/s]
 68%|██████▊   | 254286/371472 [9:10:54<9:17:05,  3.51it/s]
 68%|██████▊   | 254287/371472 [9:10:55<8:51:33,  3.67it/s]
 68%|██████▊   | 254288/371472 [9:10:55<8:32:34,  3.81it/s]
 68%|██████▊   | 254289/371472 [9:10:55<9:28:30,  3.44it/s]
 68%|██████▊   | 254290/371472 [9:10:56<9:27:57,  3.44it/s]
 68%|██████▊   | 254291/371472 [9:10:56<9:30:14,  3.42it/s]
 68%|██████▊   | 254292/371472 [9:10:56<9:12:05,  3.54it/s]
 68%|██████▊   | 254293/371472 [9:10:56<8:50:51,  3.68it/s]
 68%|██████▊   | 254294/371472 [9:10:57<8:43:56,  3.73it/s]
 68%|██████▊   | 254295/371472 [9:10:57<8:56:55,  3.64it/s]
 68%|██████▊   | 254296/371472 [9:10:57<9:02:14,  3.60it/s]
 68%|██████▊   | 254297/371472 [9:10:57<8:47:14,  3.70it/s]
 68%|██████▊   | 254298/371472 [9:10:58<8:52:54,  3.66it/s]
 68%|██████▊   | 254299/371472 [9:10:58<9:04:32,  3.59it/s]
 68%|██████▊   | 254300/371472 [9:10:58<8:52:40,  3.67it/s]
                                                           
{'loss': 2.7905, 'learning_rate': 3.840365015406495e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254300/371472 [9:10:58<8:52:40,  3.67it/s]
 68%|██████▊   | 254301/371472 [9:10:59<9:00:51,  3.61it/s]
 68%|██████▊   | 254302/371472 [9:10:59<8:46:58,  3.71it/s]
 68%|██████▊   | 254303/371472 [9:10:59<9:38:41,  3.37it/s]
 68%|██████▊   | 254304/371472 [9:10:59<9:52:25,  3.30it/s]
 68%|██████▊   | 254305/371472 [9:11:00<9:49:27,  3.31it/s]
 68%|██████▊   | 254306/371472 [9:11:00<9:22:28,  3.47it/s]
 68%|██████▊   | 254307/371472 [9:11:00<9:01:32,  3.61it/s]
 68%|██████▊   | 254308/371472 [9:11:01<9:30:28,  3.42it/s]
 68%|██████▊   | 254309/371472 [9:11:01<9:28:26,  3.44it/s]
 68%|██████▊   | 254310/371472 [9:11:01<8:58:57,  3.62it/s]
 68%|██████▊   | 254311/371472 [9:11:01<8:45:53,  3.71it/s]
 68%|██████▊   | 254312/371472 [9:11:02<8:44:07,  3.73it/s]
 68%|██████▊   | 254313/371472 [9:11:02<8:47:41,  3.70it/s]
 68%|█████��▊   | 254314/371472 [9:11:02<8:55:42,  3.64it/s]
 68%|██████▊   | 254315/371472 [9:11:03<9:12:49,  3.53it/s]
 68%|██████▊   | 254316/371472 [9:11:03<9:12:04,  3.54it/s]
 68%|██████▊   | 254317/371472 [9:11:03<9:02:56,  3.60it/s]
 68%|██████▊   | 254318/371472 [9:11:03<8:39:54,  3.76it/s]
 68%|██████▊   | 254319/371472 [9:11:04<8:22:32,  3.89it/s]
 68%|██████▊   | 254320/371472 [9:11:04<8:15:40,  3.94it/s]
                                                           
{'loss': 2.808, 'learning_rate': 3.839880195651705e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254320/371472 [9:11:04<8:15:40,  3.94it/s]
 68%|██████▊   | 254321/371472 [9:11:04<8:37:33,  3.77it/s]
 68%|██████▊   | 254322/371472 [9:11:04<8:34:39,  3.79it/s]
 68%|██████▊   | 254323/371472 [9:11:05<8:40:49,  3.75it/s]
 68%|██████▊   | 254324/371472 [9:11:05<8:38:24,  3.77it/s]
 68%|██████▊   | 254325/371472 [9:11:05<8:52:21,  3.67it/s]
 68%|██████▊   | 254326/371472 [9:11:05<9:03:49,  3.59it/s]
 68%|██████▊   | 254327/371472 [9:11:06<9:12:39,  3.53it/s]
 68%|██████▊   | 254328/371472 [9:11:06<11:12:44,  2.90it/s]
 68%|██████▊   | 254329/371472 [9:11:07<11:11:40,  2.91it/s]
 68%|██████▊   | 254330/371472 [9:11:07<10:38:58,  3.06it/s]
 68%|██████▊   | 254331/371472 [9:11:07<10:01:18,  3.25it/s]
 68%|██████▊   | 254332/371472 [9:11:07<9:37:35,  3.38it/s] 
 68%|██████▊   | 254333/371472 [9:11:08<9:18:34,  3.50it/s]
 68%|██████▊   | 254334/371472 [9:11:08<9:00:23,  3.61it/s]
 68%|██████▊   | 254335/371472 [9:11:08<8:51:31,  3.67it/s]
 68%|██████▊   | 254336/371472 [9:11:08<9:06:30,  3.57it/s]
 68%|██████▊   | 254337/371472 [9:11:09<9:05:40,  3.58it/s]
 68%|██████▊   | 254338/371472 [9:11:09<9:03:48,  3.59it/s]
 68%|██████▊   | 254339/371472 [9:11:09<8:41:05,  3.75it/s]
 68%|██████▊   | 254340/371472 [9:11:10<9:02:21,  3.60it/s]
                                                           
{'loss': 2.8106, 'learning_rate': 3.839395375896917e-07, 'epoch': 10.95}
+
 68%|██████▊   | 254340/371472 [9:11:10<9:02:21,  3.60it/s]
 68%|██████▊   | 254341/371472 [9:11:10<8:43:16,  3.73it/s]
 68%|██████▊   | 254342/371472 [9:11:10<8:32:19,  3.81it/s]
 68%|██████▊   | 254343/371472 [9:11:10<8:34:23,  3.80it/s]
 68%|██████▊   | 254344/371472 [9:11:11<8:48:14,  3.70it/s]
 68%|██████▊   | 254345/371472 [9:11:11<8:30:31,  3.82it/s]
 68%|██████▊   | 254346/371472 [9:11:11<9:24:59,  3.46it/s]
 68%|██████▊   | 254347/371472 [9:11:12<9:26:03,  3.45it/s]
 68%|██████▊   | 254348/371472 [9:11:12<8:49:15,  3.69it/s]
 68%|██████▊   | 254349/371472 [9:11:12<8:44:15,  3.72it/s]
 68%|██████▊   | 254350/371472 [9:11:12<8:58:14,  3.63it/s]
 68%|██████▊   | 254351/371472 [9:11:13<8:32:14,  3.81it/s]
 68%|██████▊   | 254352/371472 [9:11:13<8:51:48,  3.67it/s]
 68%|██████▊   | 254353/371472 [9:11:13<8:39:27,  3.76it/s]
 68%|██████▊   | 254354/371472 [9:11:13<9:07:36,  3.56it/s]
 68%|██████▊   | 254355/371472 [9:11:14<8:55:16,  3.65it/s]
 68%|██████▊   | 254356/371472 [9:11:14<8:36:40,  3.78it/s]
 68%|██████▊   | 254357/371472 [9:11:14<8:40:23,  3.75it/s]
 68%|██████▊   | 254358/371472 [9:11:14<8:45:33,  3.71it/s]
 68%|██████▊   | 254359/371472 [9:11:15<9:07:31,  3.56it/s]
 68%|██████▊   | 254360/371472 [9:11:15<10:00:49,  3.25it/s]
                                                            
{'loss': 2.814, 'learning_rate': 3.8389105561421275e-07, 'epoch': 10.96}
+
 68%|██████▊   | 254360/371472 [9:11:15<10:00:49,  3.25it/s]
 68%|██████▊   | 254361/371472 [9:11:15<9:28:48,  3.43it/s] 
 68%|██████▊   | 254362/371472 [9:11:16<9:26:18,  3.45it/s]
 68%|██████▊   | 254363/371472 [9:11:16<10:03:04,  3.24it/s]
 68%|██████▊   | 254364/371472 [9:11:16<10:00:34,  3.25it/s]
 68%|██████▊   | 254365/371472 [9:11:17<9:50:58,  3.30it/s] 
 68%|██████▊   | 254366/371472 [9:11:17<9:27:03,  3.44it/s]
 68%|██████▊   | 254367/371472 [9:11:17<9:11:53,  3.54it/s]
 68%|██████▊   | 254368/371472 [9:11:17<9:16:26,  3.51it/s]
 68%|██████▊   | 254369/371472 [9:11:18<9:21:24,  3.48it/s]
 68%|██████▊   | 254370/371472 [9:11:18<9:58:19,  3.26it/s]
 68%|██████▊   | 254371/371472 [9:11:18<10:25:02,  3.12it/s]
 68%|██████▊   | 254372/371472 [9:11:19<10:04:14,  3.23it/s]
 68%|██████▊   | 254373/371472 [9:11:19<9:17:48,  3.50it/s] 
 68%|██████▊   | 254374/371472 [9:11:19<10:06:18,  3.22it/s]
 68%|██████▊   | 254375/371472 [9:11:20<10:47:04,  3.02it/s]
 68%|██████▊   | 254376/371472 [9:11:20<9:50:05,  3.31it/s] 
 68%|██████▊   | 254377/371472 [9:11:20<9:49:56,  3.31it/s]
 68%|██████▊   | 254378/371472 [9:11:20<9:28:49,  3.43it/s]
 68%|██████▊   | 254379/371472 [9:11:21<9:18:27,  3.49it/s]
 68%|██████▊   | 254380/371472 [9:11:21<9:14:41,  3.52it/s]
                                                           
{'loss': 2.8547, 'learning_rate': 3.838425736387339e-07, 'epoch': 10.96}
+
 68%|██████▊   | 254380/371472 [9:11:21<9:14:41,  3.52it/s]
 68%|██████▊   | 254381/371472 [9:11:21<9:21:45,  3.47it/s]
 68%|██████▊   | 254382/371472 [9:11:22<9:49:25,  3.31it/s]
 68%|██████▊   | 254383/371472 [9:11:22<9:17:17,  3.50it/s]
 68%|██████▊   | 254384/371472 [9:11:22<9:07:31,  3.56it/s]
 68%|██████▊   | 254385/371472 [9:11:22<9:04:16,  3.59it/s]
 68%|██████▊   | 254386/371472 [9:11:23<9:07:22,  3.57it/s]
 68%|██████▊   | 254387/371472 [9:11:23<9:13:24,  3.53it/s]
 68%|██████▊   | 254388/371472 [9:11:23<9:17:38,  3.50it/s]
 68%|██████▊   | 254389/371472 [9:11:24<8:47:37,  3.70it/s]
 68%|██████▊   | 254390/371472 [9:11:24<9:54:31,  3.28it/s]
 68%|██████▊   | 254391/371472 [9:11:24<9:23:44,  3.46it/s]
 68%|██████▊   | 254392/371472 [9:11:24<9:11:09,  3.54it/s]
 68%|██████▊   | 254393/371472 [9:11:25<9:08:29,  3.56it/s]
 68%|██████▊   | 254394/371472 [9:11:25<8:46:27,  3.71it/s]
 68%|██████▊   | 254395/371472 [9:11:25<8:35:03,  3.79it/s]
 68%|██████▊   | 254396/371472 [9:11:26<8:44:09,  3.72it/s]
 68%|██████▊   | 254397/371472 [9:11:26<8:31:33,  3.81it/s]
 68%|██████▊   | 254398/371472 [9:11:26<8:42:43,  3.73it/s]
 68%|██████▊   | 254399/371472 [9:11:26<8:41:05,  3.74it/s]
 68%|██████▊   | 254400/371472 [9:11:27<8:57:56,  3.63it/s]
                                                           
{'loss': 2.7772, 'learning_rate': 3.8379409166325495e-07, 'epoch': 10.96}
+
 68%|██████▊   | 254400/371472 [9:11:27<8:57:56,  3.63it/s]
 68%|██████▊   | 254401/371472 [9:11:27<9:10:52,  3.54it/s]
 68%|██████▊   | 254402/371472 [9:11:27<8:44:15,  3.72it/s]
 68%|██████▊   | 254403/371472 [9:11:27<8:41:04,  3.74it/s]
 68%|██████▊   | 254404/371472 [9:11:28<8:25:09,  3.86it/s]
 68%|██████▊   | 254405/371472 [9:11:28<8:13:03,  3.96it/s]
 68%|██████▊   | 254406/371472 [9:11:28<8:23:29,  3.88it/s]
 68%|██████▊   | 254407/371472 [9:11:28<8:32:40,  3.81it/s]
 68%|██████▊   | 254408/371472 [9:11:29<8:15:54,  3.93it/s]
 68%|██████▊   | 254409/371472 [9:11:29<8:28:13,  3.84it/s]
 68%|██████▊   | 254410/371472 [9:11:29<8:27:20,  3.85it/s]
 68%|██████▊   | 254411/371472 [9:11:29<8:18:39,  3.91it/s]
 68%|██████▊   | 254412/371472 [9:11:30<8:14:53,  3.94it/s]
 68%|██████▊   | 254413/371472 [9:11:30<8:33:57,  3.80it/s]
 68%|██████▊   | 254414/371472 [9:11:30<8:52:56,  3.66it/s]
 68%|██████▊   | 254415/371472 [9:11:31<8:33:10,  3.80it/s]
 68%|██████▊   | 254416/371472 [9:11:31<8:52:07,  3.67it/s]
 68%|██████▊   | 254417/371472 [9:11:31<8:49:28,  3.68it/s]
 68%|██████▊   | 254418/371472 [9:11:31<8:21:48,  3.89it/s]
 68%|██████▊   | 254419/371472 [9:11:32<8:24:20,  3.87it/s]
 68%|██████▊   | 254420/371472 [9:11:32<8:40:01,  3.75it/s]
                                                           
{'loss': 2.8506, 'learning_rate': 3.8374560968777613e-07, 'epoch': 10.96}
+
 68%|██████▊   | 254420/371472 [9:11:32<8:40:01,  3.75it/s]
 68%|██████▊   | 254421/371472 [9:11:32<8:50:49,  3.68it/s]
 68%|██████▊   | 254422/371472 [9:11:32<8:40:19,  3.75it/s]
 68%|██████▊   | 254423/371472 [9:11:33<8:43:50,  3.72it/s]
 68%|██████▊   | 254424/371472 [9:11:33<8:21:48,  3.89it/s]
 68%|██████▊   | 254425/371472 [9:11:33<8:22:23,  3.88it/s]
 68%|██████▊   | 254426/371472 [9:11:33<8:26:32,  3.85it/s]
 68%|██████▊   | 254427/371472 [9:11:34<8:14:25,  3.95it/s]
 68%|██████▊   | 254428/371472 [9:11:34<8:14:32,  3.94it/s]
 68%|██████▊   | 254429/371472 [9:11:34<9:02:15,  3.60it/s]
 68%|██████▊   | 254430/371472 [9:11:34<8:42:24,  3.73it/s]
 68%|██████▊   | 254431/371472 [9:11:35<8:34:48,  3.79it/s]
 68%|██████▊   | 254432/371472 [9:11:35<9:24:50,  3.45it/s]
 68%|██████▊   | 254433/371472 [9:11:35<9:37:18,  3.38it/s]
 68%|██████▊   | 254434/371472 [9:11:36<9:36:42,  3.38it/s]
 68%|██████▊   | 254435/371472 [9:11:36<9:08:18,  3.56it/s]
 68%|██████▊   | 254436/371472 [9:11:36<9:07:19,  3.56it/s]
 68%|██████▊   | 254437/371472 [9:11:37<9:16:05,  3.51it/s]
 68%|██████▊   | 254438/371472 [9:11:37<9:33:38,  3.40it/s]
 68%|██████▊   | 254439/371472 [9:11:37<9:13:06,  3.53it/s]
 68%|██████▊   | 254440/371472 [9:11:37<9:29:08,  3.43it/s]
                                                           
{'loss': 2.8753, 'learning_rate': 3.8369712771229715e-07, 'epoch': 10.96}
+
 68%|██████▊   | 254440/371472 [9:11:37<9:29:08,  3.43it/s]
 68%|██████▊   | 254441/371472 [9:11:38<9:07:53,  3.56it/s]
 68%|██████▊   | 254442/371472 [9:11:38<9:07:29,  3.56it/s]
 68%|██████▊   | 254443/371472 [9:11:38<8:49:05,  3.69it/s]
 68%|██████▊   | 254444/371472 [9:11:38<8:38:00,  3.77it/s]
 68%|██████▊   | 254445/371472 [9:11:39<9:03:02,  3.59it/s]
 68%|██████▊   | 254446/371472 [9:11:39<9:21:26,  3.47it/s]
 68%|██████▊   | 254447/371472 [9:11:39<9:13:27,  3.52it/s]
 68%|██████▊   | 254448/371472 [9:11:40<8:41:46,  3.74it/s]
 68%|██████▊   | 254449/371472 [9:11:40<8:59:03,  3.62it/s]
 68%|██████▊   | 254450/371472 [9:11:40<8:42:45,  3.73it/s]
 68%|██████▊   | 254451/371472 [9:11:40<8:22:21,  3.88it/s]
 68%|██████▊   | 254452/371472 [9:11:41<8:07:54,  4.00it/s]
 68%|██████▊   | 254453/371472 [9:11:41<8:12:58,  3.96it/s]
 68%|██████▊   | 254454/371472 [9:11:41<8:06:58,  4.00it/s]
 68%|██████▊   | 254455/371472 [9:11:41<8:30:30,  3.82it/s]
 68%|██████▊   | 254456/371472 [9:11:42<8:51:59,  3.67it/s]
 68%|██████▊   | 254457/371472 [9:11:42<8:34:35,  3.79it/s]
 68%|██████▊   | 254458/371472 [9:11:42<8:32:02,  3.81it/s]
 69%|██████▊   | 254459/371472 [9:11:42<8:41:35,  3.74it/s]
 69%|██████▊   | 254460/371472 [9:11:43<9:31:56,  3.41it/s]
                                                           
{'loss': 2.8417, 'learning_rate': 3.836486457368183e-07, 'epoch': 10.96}
+
 69%|██████▊   | 254460/371472 [9:11:43<9:31:56,  3.41it/s]
 69%|██████▊   | 254461/371472 [9:11:43<9:06:13,  3.57it/s]
 69%|██████▊   | 254462/371472 [9:11:43<9:09:32,  3.55it/s]
 69%|██████▊   | 254463/371472 [9:11:44<8:54:20,  3.65it/s]
 69%|██████▊   | 254464/371472 [9:11:44<8:51:20,  3.67it/s]
 69%|██████▊   | 254465/371472 [9:11:44<8:44:21,  3.72it/s]
 69%|██████▊   | 254466/371472 [9:11:44<8:51:24,  3.67it/s]
 69%|██████▊   | 254467/371472 [9:11:45<8:43:11,  3.73it/s]
 69%|██████▊   | 254468/371472 [9:11:45<8:56:36,  3.63it/s]
 69%|██████▊   | 254469/371472 [9:11:45<8:52:28,  3.66it/s]
 69%|██████▊   | 254470/371472 [9:11:45<8:48:24,  3.69it/s]
 69%|██████▊   | 254471/371472 [9:11:46<8:48:53,  3.69it/s]
 69%|██████▊   | 254472/371472 [9:11:46<9:07:27,  3.56it/s]
 69%|██████▊   | 254473/371472 [9:11:46<9:10:00,  3.55it/s]
 69%|██████▊   | 254474/371472 [9:11:47<8:55:05,  3.64it/s]
 69%|██████▊   | 254475/371472 [9:11:47<8:44:46,  3.72it/s]
 69%|██████▊   | 254476/371472 [9:11:47<8:21:56,  3.88it/s]
 69%|██████▊   | 254477/371472 [9:11:47<8:22:18,  3.88it/s]
 69%|██████▊   | 254478/371472 [9:11:48<9:16:01,  3.51it/s]
 69%|██████▊   | 254479/371472 [9:11:48<9:03:17,  3.59it/s]
 69%|██████▊   | 254480/371472 [9:11:48<8:49:24,  3.68it/s]
                                                           
{'loss': 2.9394, 'learning_rate': 3.836001637613394e-07, 'epoch': 10.96}
+
 69%|██████▊   | 254480/371472 [9:11:48<8:49:24,  3.68it/s]
 69%|██████▊   | 254481/371472 [9:11:49<9:20:20,  3.48it/s]
 69%|██████▊   | 254482/371472 [9:11:49<9:17:12,  3.50it/s]
 69%|██████▊   | 254483/371472 [9:11:49<8:55:35,  3.64it/s]
 69%|██████▊   | 254484/371472 [9:11:49<8:37:10,  3.77it/s]
 69%|██████▊   | 254485/371472 [9:11:50<8:26:35,  3.85it/s]
 69%|██████▊   | 254486/371472 [9:11:50<8:58:44,  3.62it/s]
 69%|██████▊   | 254487/371472 [9:11:50<8:37:29,  3.77it/s]
 69%|██████▊   | 254488/371472 [9:11:50<8:21:26,  3.89it/s]
 69%|██████▊   | 254489/371472 [9:11:51<8:45:55,  3.71it/s]
 69%|██████▊   | 254490/371472 [9:11:51<8:53:45,  3.65it/s]
 69%|██████▊   | 254491/371472 [9:11:51<8:45:57,  3.71it/s]
 69%|██████▊   | 254492/371472 [9:11:51<8:37:13,  3.77it/s]
 69%|██████▊   | 254493/371472 [9:11:52<8:55:04,  3.64it/s]
 69%|██████▊   | 254494/371472 [9:11:52<9:44:43,  3.33it/s]
 69%|██████▊   | 254495/371472 [9:11:52<9:31:17,  3.41it/s]
 69%|██��███▊   | 254496/371472 [9:11:53<9:11:17,  3.54it/s]
 69%|██████▊   | 254497/371472 [9:11:53<9:05:03,  3.58it/s]
 69%|██████▊   | 254498/371472 [9:11:53<9:31:56,  3.41it/s]
 69%|██████▊   | 254499/371472 [9:11:54<9:24:30,  3.45it/s]
 69%|██████▊   | 254500/371472 [9:11:54<8:52:58,  3.66it/s]
                                                           
{'loss': 2.945, 'learning_rate': 3.835516817858604e-07, 'epoch': 10.96}
+
 69%|██████▊   | 254500/371472 [9:11:54<8:52:58,  3.66it/s]
 69%|██████▊   | 254501/371472 [9:11:54<8:46:49,  3.70it/s]
 69%|██████▊   | 254502/371472 [9:11:54<8:54:00,  3.65it/s]
 69%|██████▊   | 254503/371472 [9:11:55<9:08:15,  3.56it/s]
 69%|██████▊   | 254504/371472 [9:11:55<8:46:25,  3.70it/s]
 69%|██████▊   | 254505/371472 [9:11:55<8:34:12,  3.79it/s]
 69%|██████▊   | 254506/371472 [9:11:55<8:55:42,  3.64it/s]
 69%|██████▊   | 254507/371472 [9:11:56<9:03:26,  3.59it/s]
 69%|██████▊   | 254508/371472 [9:11:56<10:17:51,  3.16it/s]
 69%|██████▊   | 254509/371472 [9:11:56<10:46:39,  3.01it/s]
 69%|██████▊   | 254510/371472 [9:11:57<10:19:21,  3.15it/s]
 69%|██████▊   | 254511/371472 [9:11:57<10:09:38,  3.20it/s]
 69%|██████▊   | 254512/371472 [9:11:57<9:39:11,  3.37it/s] 
 69%|██████▊   | 254513/371472 [9:11:58<9:59:48,  3.25it/s]
 69%|██████▊   | 254514/371472 [9:11:58<9:31:03,  3.41it/s]
 69%|██████▊   | 254515/371472 [9:11:58<9:14:34,  3.51it/s]
 69%|██████▊   | 254516/371472 [9:11:58<9:12:15,  3.53it/s]
 69%|██████▊   | 254517/371472 [9:11:59<9:00:28,  3.61it/s]
 69%|██████▊   | 254518/371472 [9:11:59<9:11:59,  3.53it/s]
 69%|██████▊   | 254519/371472 [9:11:59<9:00:02,  3.61it/s]
 69%|██████▊   | 254520/371472 [9:11:59<8:43:38,  3.72it/s]
                                                           
{'loss': 2.7508, 'learning_rate': 3.835031998103816e-07, 'epoch': 10.96}
+
 69%|██████▊   | 254520/371472 [9:11:59<8:43:38,  3.72it/s]
 69%|██████▊   | 254521/371472 [9:12:00<8:37:09,  3.77it/s]
 69%|██████▊   | 254522/371472 [9:12:00<8:50:22,  3.68it/s]
 69%|██████▊   | 254523/371472 [9:12:00<8:35:07,  3.78it/s]
 69%|██████▊   | 254524/371472 [9:12:01<8:33:23,  3.80it/s]
 69%|██████▊   | 254525/371472 [9:12:01<9:04:35,  3.58it/s]
 69%|██████▊   | 254526/371472 [9:12:01<8:54:25,  3.65it/s]
 69%|██████▊   | 254527/371472 [9:12:01<8:42:30,  3.73it/s]
 69%|██████▊   | 254528/371472 [9:12:02<8:39:38,  3.75it/s]
 69%|██████▊   | 254529/371472 [9:12:02<8:32:36,  3.80it/s]
 69%|██████▊   | 254530/371472 [9:12:02<8:20:54,  3.89it/s]
 69%|██████▊   | 254531/371472 [9:12:02<8:37:54,  3.76it/s]
 69%|██████▊   | 254532/371472 [9:12:03<8:41:32,  3.74it/s]
 69%|██████▊   | 254533/371472 [9:12:03<8:36:16,  3.78it/s]
 69%|██████▊   | 254534/371472 [9:12:03<8:25:02,  3.86it/s]
 69%|██████▊   | 254535/371472 [9:12:03<8:13:48,  3.95it/s]
 69%|██████▊   | 254536/371472 [9:12:04<8:33:24,  3.80it/s]
 69%|██████▊   | 254537/371472 [9:12:04<8:29:29,  3.83it/s]
 69%|██████▊   | 254538/371472 [9:12:04<8:24:02,  3.87it/s]
 69%|██████▊   | 254539/371472 [9:12:05<8:28:21,  3.83it/s]
 69%|██████▊   | 254540/371472 [9:12:05<8:28:03,  3.84it/s]
                                                           
{'loss': 2.9123, 'learning_rate': 3.8345471783490266e-07, 'epoch': 10.96}
+
 69%|██████▊   | 254540/371472 [9:12:05<8:28:03,  3.84it/s]
 69%|██████▊   | 254541/371472 [9:12:05<8:10:34,  3.97it/s]
 69%|██████▊   | 254542/371472 [9:12:05<8:16:52,  3.92it/s]
 69%|██████▊   | 254543/371472 [9:12:06<8:37:40,  3.76it/s]
 69%|██████▊   | 254544/371472 [9:12:06<9:15:06,  3.51it/s]
 69%|██████▊   | 254545/371472 [9:12:06<9:05:36,  3.57it/s]
 69%|██████▊   | 254546/371472 [9:12:06<8:47:20,  3.70it/s]
 69%|██████▊   | 254547/371472 [9:12:07<8:36:21,  3.77it/s]
 69%|██████▊   | 254548/371472 [9:12:07<8:30:53,  3.81it/s]
 69%|██████▊   | 254549/371472 [9:12:07<8:21:13,  3.89it/s]
 69%|██████▊   | 254550/371472 [9:12:07<8:20:01,  3.90it/s]
 69%|██████▊   | 254551/371472 [9:12:08<8:24:18,  3.86it/s]
 69%|██████▊   | 254552/371472 [9:12:08<8:24:46,  3.86it/s]
 69%|██████▊   | 254553/371472 [9:12:08<9:16:28,  3.50it/s]
 69%|██████▊   | 254554/371472 [9:12:09<9:15:42,  3.51it/s]
 69%|██████▊   | 254555/371472 [9:12:09<9:06:56,  3.56it/s]
 69%|██████▊   | 254556/371472 [9:12:09<8:49:45,  3.68it/s]
 69%|██████▊   | 254557/371472 [9:12:09<8:40:41,  3.74it/s]
 69%|██████▊   | 254558/371472 [9:12:10<8:58:58,  3.62it/s]
 69%|██████▊   | 254559/371472 [9:12:10<8:44:20,  3.72it/s]
 69%|██████▊   | 254560/371472 [9:12:10<8:47:50,  3.69it/s]
                                                           
{'loss': 2.8882, 'learning_rate': 3.834062358594238e-07, 'epoch': 10.96}
+
 69%|██████▊   | 254560/371472 [9:12:10<8:47:50,  3.69it/s]
 69%|██████▊   | 254561/371472 [9:12:10<8:31:35,  3.81it/s]
 69%|██████▊   | 254562/371472 [9:12:11<8:45:58,  3.70it/s]
 69%|██████▊   | 254563/371472 [9:12:11<9:48:29,  3.31it/s]
 69%|██████▊   | 254564/371472 [9:12:11<10:03:42,  3.23it/s]
 69%|██████▊   | 254565/371472 [9:12:12<9:42:30,  3.34it/s] 
 69%|██████▊   | 254566/371472 [9:12:12<9:25:37,  3.44it/s]
 69%|██████▊   | 254567/371472 [9:12:12<8:56:26,  3.63it/s]
 69%|██████▊   | 254568/371472 [9:12:12<8:49:40,  3.68it/s]
 69%|██████▊   | 254569/371472 [9:12:13<8:33:41,  3.79it/s]
 69%|██████▊   | 254570/371472 [9:12:13<9:10:58,  3.54it/s]
 69%|██████▊   | 254571/371472 [9:12:13<9:29:57,  3.42it/s]
 69%|██████▊   | 254572/371472 [9:12:14<9:08:39,  3.55it/s]
 69%|██████▊   | 254573/371472 [9:12:14<9:19:32,  3.48it/s]
 69%|██████▊   | 254574/371472 [9:12:14<9:18:24,  3.49it/s]
 69%|██████▊   | 254575/371472 [9:12:15<9:51:02,  3.30it/s]
 69%|██████▊   | 254576/371472 [9:12:15<9:26:03,  3.44it/s]
 69%|██████▊   | 254577/371472 [9:12:15<8:54:49,  3.64it/s]
 69%|██████▊   | 254578/371472 [9:12:15<8:50:05,  3.68it/s]
 69%|██████▊   | 254579/371472 [9:12:16<8:40:18,  3.74it/s]
 69%|██████▊   | 254580/371472 [9:12:16<8:29:49,  3.82it/s]
                                                           
{'loss': 2.8665, 'learning_rate': 3.8335775388394486e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254580/371472 [9:12:16<8:29:49,  3.82it/s]
 69%|██████▊   | 254581/371472 [9:12:16<8:29:14,  3.83it/s]
 69%|██████▊   | 254582/371472 [9:12:16<8:24:29,  3.86it/s]
 69%|██████▊   | 254583/371472 [9:12:17<8:45:25,  3.71it/s]
 69%|██████▊   | 254584/371472 [9:12:17<10:34:08,  3.07it/s]
 69%|██████▊   | 254585/371472 [9:12:17<9:51:27,  3.29it/s] 
 69%|██████▊   | 254586/371472 [9:12:18<9:32:20,  3.40it/s]
 69%|██████▊   | 254587/371472 [9:12:18<9:28:55,  3.42it/s]
 69%|██████▊   | 254588/371472 [9:12:18<9:08:34,  3.55it/s]
 69%|██████▊   | 254589/371472 [9:12:18<9:04:28,  3.58it/s]
 69%|██████▊   | 254590/371472 [9:12:19<9:01:49,  3.60it/s]
 69%|██████▊   | 254591/371472 [9:12:19<8:38:50,  3.75it/s]
 69%|██████▊   | 254592/371472 [9:12:19<9:10:48,  3.54it/s]
 69%|██████▊   | 254593/371472 [9:12:20<9:18:28,  3.49it/s]
 69%|██████▊   | 254594/371472 [9:12:20<8:47:42,  3.69it/s]
 69%|██████▊   | 254595/371472 [9:12:20<8:34:31,  3.79it/s]
 69%|██████▊   | 254596/371472 [9:12:20<8:38:24,  3.76it/s]
 69%|██████▊   | 254597/371472 [9:12:21<9:00:13,  3.61it/s]
 69%|██████▊   | 254598/371472 [9:12:21<8:45:32,  3.71it/s]
 69%|██████▊   | 254599/371472 [9:12:21<8:45:39,  3.71it/s]
 69%|██████▊   | 254600/371472 [9:12:21<9:07:28,  3.56it/s]
                                                           
{'loss': 2.8234, 'learning_rate': 3.8330927190846604e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254600/371472 [9:12:21<9:07:28,  3.56it/s]
 69%|██████▊   | 254601/371472 [9:12:22<8:45:04,  3.71it/s]
 69%|██████▊   | 254602/371472 [9:12:22<8:42:32,  3.73it/s]
 69%|██████▊   | 254603/371472 [9:12:22<8:37:34,  3.76it/s]
 69%|██████▊   | 254604/371472 [9:12:22<8:27:55,  3.83it/s]
 69%|██████▊   | 254605/371472 [9:12:23<8:26:31,  3.85it/s]
 69%|██████▊   | 254606/371472 [9:12:23<8:50:25,  3.67it/s]
 69%|██████▊   | 254607/371472 [9:12:23<8:31:31,  3.81it/s]
 69%|██████▊   | 254608/371472 [9:12:24<8:41:03,  3.74it/s]
 69%|██████▊   | 254609/371472 [9:12:24<8:30:18,  3.82it/s]
 69%|██████▊   | 254610/371472 [9:12:24<8:26:27,  3.85it/s]
 69%|██████▊   | 254611/371472 [9:12:24<8:09:42,  3.98it/s]
 69%|██████▊   | 254612/371472 [9:12:25<8:32:42,  3.80it/s]
 69%|██████▊   | 254613/371472 [9:12:25<8:41:39,  3.73it/s]
 69%|██████▊   | 254614/371472 [9:12:25<8:57:33,  3.62it/s]
 69%|██████▊   | 254615/371472 [9:12:25<8:39:14,  3.75it/s]
 69%|██████▊   | 254616/371472 [9:12:26<9:00:47,  3.60it/s]
 69%|██████▊   | 254617/371472 [9:12:26<9:06:53,  3.56it/s]
 69%|██████▊   | 254618/371472 [9:12:26<8:48:59,  3.68it/s]
 69%|██████▊   | 254619/371472 [9:12:26<8:26:16,  3.85it/s]
 69%|██████▊   | 254620/371472 [9:12:27<8:32:07,  3.80it/s]
                                                           
{'loss': 3.0836, 'learning_rate': 3.832607899329871e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254620/371472 [9:12:27<8:32:07,  3.80it/s]
 69%|██████▊   | 254621/371472 [9:12:27<8:20:21,  3.89it/s]
 69%|██████▊   | 254622/371472 [9:12:27<8:33:37,  3.79it/s]
 69%|██████▊   | 254623/371472 [9:12:28<9:47:23,  3.32it/s]
 69%|██████▊   | 254624/371472 [9:12:28<9:04:32,  3.58it/s]
 69%|██████▊   | 254625/371472 [9:12:28<9:06:06,  3.57it/s]
 69%|██████▊   | 254626/371472 [9:12:28<8:55:17,  3.64it/s]
 69%|██████▊   | 254627/371472 [9:12:29<8:40:34,  3.74it/s]
 69%|██████▊   | 254628/371472 [9:12:29<8:49:43,  3.68it/s]
 69%|██████▊   | 254629/371472 [9:12:29<8:47:11,  3.69it/s]
 69%|██████▊   | 254630/371472 [9:12:29<8:41:31,  3.73it/s]
 69%|██████▊   | 254631/371472 [9:12:30<8:32:23,  3.80it/s]
 69%|██████▊   | 254632/371472 [9:12:30<9:04:20,  3.58it/s]
 69%|██████▊   | 254633/371472 [9:12:30<9:01:59,  3.59it/s]
 69%|██████▊   | 254634/371472 [9:12:31<9:22:45,  3.46it/s]
 69%|██████▊   | 254635/371472 [9:12:31<9:24:03,  3.45it/s]
 69%|██████▊   | 254636/371472 [9:12:31<9:25:38,  3.44it/s]
 69%|██████▊   | 254637/371472 [9:12:31<9:15:57,  3.50it/s]
 69%|██████▊   | 254638/371472 [9:12:32<9:18:55,  3.48it/s]
 69%|██████▊   | 254639/371472 [9:12:32<8:45:10,  3.71it/s]
 69%|██████▊   | 254640/371472 [9:12:32<8:23:19,  3.87it/s]
                                                           
{'loss': 2.7296, 'learning_rate': 3.8321230795750823e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254640/371472 [9:12:32<8:23:19,  3.87it/s]
 69%|██████▊   | 254641/371472 [9:12:32<8:20:10,  3.89it/s]
 69%|██████▊   | 254642/371472 [9:12:33<8:18:41,  3.90it/s]
 69%|██████▊   | 254643/371472 [9:12:33<8:33:28,  3.79it/s]
 69%|██████▊   | 254644/371472 [9:12:33<8:49:50,  3.67it/s]
 69%|██████▊   | 254645/371472 [9:12:34<9:11:58,  3.53it/s]
 69%|██████▊   | 254646/371472 [9:12:34<9:11:37,  3.53it/s]
 69%|██████▊   | 254647/371472 [9:12:34<9:25:32,  3.44it/s]
 69%|██████▊   | 254648/371472 [9:12:34<9:21:35,  3.47it/s]
 69%|██████▊   | 254649/371472 [9:12:35<9:37:16,  3.37it/s]
 69%|██████▊   | 254650/371472 [9:12:35<9:31:19,  3.41it/s]
 69%|██████▊   | 254651/371472 [9:12:35<9:13:58,  3.51it/s]
 69%|██████▊   | 254652/371472 [9:12:36<8:56:36,  3.63it/s]
 69%|██████▊   | 254653/371472 [9:12:36<9:19:18,  3.48it/s]
 69%|██████▊   | 254654/371472 [9:12:36<9:02:54,  3.59it/s]
 69%|██████▊   | 254655/371472 [9:12:36<8:38:10,  3.76it/s]
 69%|██████▊   | 254656/371472 [9:12:37<8:36:08,  3.77it/s]
 69%|██████▊   | 254657/371472 [9:12:37<8:21:53,  3.88it/s]
 69%|██████▊   | 254658/371472 [9:12:37<8:32:00,  3.80it/s]
 69%|██████▊   | 254659/371472 [9:12:37<9:00:16,  3.60it/s]
 69%|██████▊   | 254660/371472 [9:12:38<8:54:09,  3.64it/s]
                                                           
{'loss': 2.8029, 'learning_rate': 3.831638259820293e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254660/371472 [9:12:38<8:54:09,  3.64it/s]
 69%|██████▊   | 254661/371472 [9:12:38<9:00:43,  3.60it/s]
 69%|██████▊   | 254662/371472 [9:12:38<9:54:01,  3.28it/s]
 69%|██████▊   | 254663/371472 [9:12:39<9:25:24,  3.44it/s]
 69%|██████▊   | 254664/371472 [9:12:39<9:03:53,  3.58it/s]
 69%|██████▊   | 254665/371472 [9:12:39<9:19:56,  3.48it/s]
 69%|██████▊   | 254666/371472 [9:12:40<9:06:48,  3.56it/s]
 69%|██████▊   | 254667/371472 [9:12:40<8:47:53,  3.69it/s]
 69%|██████▊   | 254668/371472 [9:12:40<8:43:27,  3.72it/s]
 69%|██████▊   | 254669/371472 [9:12:40<8:37:22,  3.76it/s]
 69%|██████▊   | 254670/371472 [9:12:41<8:37:31,  3.76it/s]
 69%|██████▊   | 254671/371472 [9:12:41<8:39:00,  3.75it/s]
 69%|██████▊   | 254672/371472 [9:12:41<8:35:40,  3.77it/s]
 69%|██████▊   | 254673/371472 [9:12:41<9:15:48,  3.50it/s]
 69%|██████▊   | 254674/371472 [9:12:42<9:18:30,  3.49it/s]
 69%|██████▊   | 254675/371472 [9:12:42<9:24:00,  3.45it/s]
 69%|██████▊   | 254676/371472 [9:12:42<8:59:53,  3.61it/s]
 69%|██████▊   | 254677/371472 [9:12:42<8:48:22,  3.68it/s]
 69%|██���███▊   | 254678/371472 [9:12:43<8:47:52,  3.69it/s]
 69%|██████▊   | 254679/371472 [9:12:43<8:27:55,  3.83it/s]
 69%|██████▊   | 254680/371472 [9:12:43<8:41:41,  3.73it/s]
                                                           
{'loss': 2.9259, 'learning_rate': 3.831153440065505e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254680/371472 [9:12:43<8:41:41,  3.73it/s]
 69%|██████▊   | 254681/371472 [9:12:44<8:31:28,  3.81it/s]
 69%|██████▊   | 254682/371472 [9:12:44<9:05:56,  3.57it/s]
 69%|██████▊   | 254683/371472 [9:12:44<8:36:36,  3.77it/s]
 69%|██████▊   | 254684/371472 [9:12:44<8:24:48,  3.86it/s]
 69%|██████▊   | 254685/371472 [9:12:45<8:38:52,  3.75it/s]
 69%|██████▊   | 254686/371472 [9:12:45<9:08:00,  3.55it/s]
 69%|██████▊   | 254687/371472 [9:12:45<9:53:00,  3.28it/s]
 69%|██████▊   | 254688/371472 [9:12:46<9:18:20,  3.49it/s]
 69%|██████▊   | 254689/371472 [9:12:46<10:00:27,  3.24it/s]
 69%|██████▊   | 254690/371472 [9:12:46<9:23:07,  3.46it/s] 
 69%|██████▊   | 254691/371472 [9:12:46<8:55:27,  3.63it/s]
 69%|██████▊   | 254692/371472 [9:12:47<9:06:44,  3.56it/s]
 69%|██████▊   | 254693/371472 [9:12:47<9:23:31,  3.45it/s]
 69%|██████▊   | 254694/371472 [9:12:47<8:46:59,  3.69it/s]
 69%|██████▊   | 254695/371472 [9:12:48<9:01:42,  3.59it/s]
 69%|██████▊   | 254696/371472 [9:12:48<9:58:19,  3.25it/s]
 69%|██████▊   | 254697/371472 [9:12:48<10:15:50,  3.16it/s]
 69%|██████▊   | 254698/371472 [9:12:49<10:33:51,  3.07it/s]
 69%|██████▊   | 254699/371472 [9:12:49<10:09:56,  3.19it/s]
 69%|██████▊   | 254700/371472 [9:12:49<10:12:59,  3.17it/s]
                                                            
{'loss': 2.8765, 'learning_rate': 3.830668620310715e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254700/371472 [9:12:49<10:12:59,  3.17it/s]
 69%|██████▊   | 254701/371472 [9:12:49<9:46:38,  3.32it/s] 
 69%|██████▊   | 254702/371472 [9:12:50<9:10:47,  3.53it/s]
 69%|██████▊   | 254703/371472 [9:12:50<9:25:56,  3.44it/s]
 69%|██████▊   | 254704/371472 [9:12:50<9:42:11,  3.34it/s]
 69%|██████▊   | 254705/371472 [9:12:51<9:41:07,  3.35it/s]
 69%|██████▊   | 254706/371472 [9:12:51<9:36:08,  3.38it/s]
 69%|██████▊   | 254707/371472 [9:12:51<9:50:41,  3.29it/s]
 69%|██████▊   | 254708/371472 [9:12:51<9:32:18,  3.40it/s]
 69%|██████▊   | 254709/371472 [9:12:52<9:22:10,  3.46it/s]
 69%|██████▊   | 254710/371472 [9:12:52<9:27:07,  3.43it/s]
 69%|██████▊   | 254711/371472 [9:12:52<9:01:16,  3.60it/s]
 69%|██████▊   | 254712/371472 [9:12:53<8:43:13,  3.72it/s]
 69%|██████▊   | 254713/371472 [9:12:53<9:28:09,  3.43it/s]
 69%|██████▊   | 254714/371472 [9:12:53<9:03:31,  3.58it/s]
 69%|██████▊   | 254715/371472 [9:12:53<9:19:34,  3.48it/s]
 69%|██████▊   | 254716/371472 [9:12:54<9:15:08,  3.51it/s]
 69%|██████▊   | 254717/371472 [9:12:54<9:22:59,  3.46it/s]
 69%|██████▊   | 254718/371472 [9:12:54<9:53:00,  3.28it/s]
 69%|██████▊   | 254719/371472 [9:12:55<9:24:07,  3.45it/s]
 69%|██████▊   | 254720/371472 [9:12:55<9:35:42,  3.38it/s]
                                                           
{'loss': 2.6791, 'learning_rate': 3.830183800555927e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254720/371472 [9:12:55<9:35:42,  3.38it/s]
 69%|██████▊   | 254721/371472 [9:12:55<9:12:00,  3.53it/s]
 69%|██████▊   | 254722/371472 [9:12:55<9:08:54,  3.54it/s]
 69%|██████▊   | 254723/371472 [9:12:56<8:56:30,  3.63it/s]
 69%|██████▊   | 254724/371472 [9:12:56<8:47:03,  3.69it/s]
 69%|██████▊   | 254725/371472 [9:12:56<9:06:50,  3.56it/s]
 69%|██████▊   | 254726/371472 [9:12:57<8:48:02,  3.68it/s]
 69%|██████▊   | 254727/371472 [9:12:57<8:35:24,  3.78it/s]
 69%|██████▊   | 254728/371472 [9:12:57<8:59:26,  3.61it/s]
 69%|██████▊   | 254729/371472 [9:12:57<9:08:59,  3.54it/s]
 69%|██████▊   | 254730/371472 [9:12:58<9:13:36,  3.51it/s]
 69%|██████▊   | 254731/371472 [9:12:58<8:54:46,  3.64it/s]
 69%|██████▊   | 254732/371472 [9:12:58<9:21:12,  3.47it/s]
 69%|██████▊   | 254733/371472 [9:12:59<9:33:09,  3.39it/s]
 69%|██████▊   | 254734/371472 [9:12:59<9:20:31,  3.47it/s]
 69%|██████▊   | 254735/371472 [9:12:59<9:16:24,  3.50it/s]
 69%|██████▊   | 254736/371472 [9:12:59<9:28:29,  3.42it/s]
 69%|██████▊   | 254737/371472 [9:13:00<9:51:08,  3.29it/s]
 69%|██████▊   | 254738/371472 [9:13:00<9:16:57,  3.49it/s]
 69%|██████▊   | 254739/371472 [9:13:00<9:10:36,  3.53it/s]
 69%|██████▊   | 254740/371472 [9:13:01<9:07:46,  3.55it/s]
                                                           
{'loss': 2.8286, 'learning_rate': 3.8296989808011375e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254740/371472 [9:13:01<9:07:46,  3.55it/s]
 69%|██████▊   | 254741/371472 [9:13:01<8:56:24,  3.63it/s]
 69%|██████▊   | 254742/371472 [9:13:01<9:15:34,  3.50it/s]
 69%|██████▊   | 254743/371472 [9:13:01<9:01:21,  3.59it/s]
 69%|██████▊   | 254744/371472 [9:13:02<8:42:22,  3.72it/s]
 69%|██████▊   | 254745/371472 [9:13:02<8:34:59,  3.78it/s]
 69%|██████▊   | 254746/371472 [9:13:02<8:24:42,  3.85it/s]
 69%|██████▊   | 254747/371472 [9:13:02<8:46:21,  3.70it/s]
 69%|██████▊   | 254748/371472 [9:13:03<8:35:58,  3.77it/s]
 69%|██████▊   | 254749/371472 [9:13:03<8:48:33,  3.68it/s]
 69%|██████▊   | 254750/371472 [9:13:03<8:35:16,  3.78it/s]
 69%|██████▊   | 254751/371472 [9:13:03<8:35:19,  3.78it/s]
 69%|██████▊   | 254752/371472 [9:13:04<8:26:30,  3.84it/s]
 69%|██████▊   | 254753/371472 [9:13:04<8:22:33,  3.87it/s]
 69%|██████▊   | 254754/371472 [9:13:04<8:25:21,  3.85it/s]
 69%|██████▊   | 254755/371472 [9:13:05<8:50:33,  3.67it/s]
 69%|██████▊   | 254756/371472 [9:13:05<8:39:06,  3.75it/s]
 69%|██████▊   | 254757/371472 [9:13:05<8:20:59,  3.88it/s]
 69%|██████▊   | 254758/371472 [9:13:05<8:48:42,  3.68it/s]
 69%|██████▊   | 254759/371472 [9:13:06<9:11:34,  3.53it/s]
 69%|██████▊   | 254760/371472 [9:13:06<9:00:27,  3.60it/s]
                                                           
{'loss': 3.0006, 'learning_rate': 3.8292141610463487e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254760/371472 [9:13:06<9:00:27,  3.60it/s]
 69%|██████▊   | 254761/371472 [9:13:06<8:54:59,  3.64it/s]
 69%|██████▊   | 254762/371472 [9:13:06<9:05:17,  3.57it/s]
 69%|██████▊   | 254763/371472 [9:13:07<8:49:34,  3.67it/s]
 69%|██████▊   | 254764/371472 [9:13:07<8:49:09,  3.68it/s]
 69%|██████▊   | 254765/371472 [9:13:07<9:02:49,  3.58it/s]
 69%|██████▊   | 254766/371472 [9:13:08<8:46:32,  3.69it/s]
 69%|██████▊   | 254767/371472 [9:13:08<8:50:09,  3.67it/s]
 69%|██████▊   | 254768/371472 [9:13:08<8:50:43,  3.66it/s]
 69%|██████▊   | 254769/371472 [9:13:08<8:46:14,  3.70it/s]
 69%|██████▊   | 254770/371472 [9:13:09<9:27:09,  3.43it/s]
 69%|██████▊   | 254771/371472 [9:13:09<9:27:30,  3.43it/s]
 69%|██████▊   | 254772/371472 [9:13:09<9:00:44,  3.60it/s]
 69%|██████▊   | 254773/371472 [9:13:10<8:51:27,  3.66it/s]
 69%|██████▊   | 254774/371472 [9:13:10<8:57:34,  3.62it/s]
 69%|██████▊   | 254775/371472 [9:13:10<8:49:44,  3.67it/s]
 69%|██████▊   | 254776/371472 [9:13:10<8:45:02,  3.70it/s]
 69%|██████▊   | 254777/371472 [9:13:11<8:31:31,  3.80it/s]
 69%|██████▊   | 254778/371472 [9:13:11<8:26:49,  3.84it/s]
 69%|██████▊   | 254779/371472 [9:13:11<8:18:36,  3.90it/s]
 69%|██████▊   | 254780/371472 [9:13:11<8:19:31,  3.89it/s]
                                                           
{'loss': 2.8118, 'learning_rate': 3.8287293412915594e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254780/371472 [9:13:11<8:19:31,  3.89it/s]
 69%|██████▊   | 254781/371472 [9:13:12<8:11:12,  3.96it/s]
 69%|██████▊   | 254782/371472 [9:13:12<8:17:31,  3.91it/s]
 69%|██████▊   | 254783/371472 [9:13:12<8:18:22,  3.90it/s]
 69%|██████▊   | 254784/371472 [9:13:12<8:30:17,  3.81it/s]
 69%|██████▊   | 254785/371472 [9:13:13<8:47:55,  3.68it/s]
 69%|██████▊   | 254786/371472 [9:13:13<8:38:21,  3.75it/s]
 69%|██████▊   | 254787/371472 [9:13:13<8:36:58,  3.76it/s]
 69%|██████▊   | 254788/371472 [9:13:13<8:33:38,  3.79it/s]
 69%|██████▊   | 254789/371472 [9:13:14<8:42:51,  3.72it/s]
 69%|██████▊   | 254790/371472 [9:13:14<8:40:00,  3.74it/s]
 69%|██████▊   | 254791/371472 [9:13:14<8:38:10,  3.75it/s]
 69%|██████▊   | 254792/371472 [9:13:15<9:04:57,  3.57it/s]
 69%|██████▊   | 254793/371472 [9:13:15<9:24:49,  3.44it/s]
 69%|██████▊   | 254794/371472 [9:13:15<9:03:20,  3.58it/s]
 69%|██████▊   | 254795/371472 [9:13:15<9:14:40,  3.51it/s]
 69%|██████▊   | 254796/371472 [9:13:16<9:00:56,  3.59it/s]
 69%|██████▊   | 254797/371472 [9:13:16<8:42:04,  3.72it/s]
 69%|██████▊   | 254798/371472 [9:13:16<8:32:01,  3.80it/s]
 69%|██████▊   | 254799/371472 [9:13:16<8:48:40,  3.68it/s]
 69%|██████▊   | 254800/371472 [9:13:17<8:47:21,  3.69it/s]
                                                           
{'loss': 2.7945, 'learning_rate': 3.828244521536771e-07, 'epoch': 10.97}
+
 69%|██████▊   | 254800/371472 [9:13:17<8:47:21,  3.69it/s]
 69%|██████▊   | 254801/371472 [9:13:17<8:54:20,  3.64it/s]
 69%|██████▊   | 254802/371472 [9:13:17<9:20:03,  3.47it/s]
 69%|██████▊   | 254803/371472 [9:13:18<9:19:08,  3.48it/s]
 69%|██████▊   | 254804/371472 [9:13:18<9:29:52,  3.41it/s]
 69%|██████▊   | 254805/371472 [9:13:18<9:56:34,  3.26it/s]
 69%|██████▊   | 254806/371472 [9:13:19<9:36:38,  3.37it/s]
 69%|██████▊   | 254807/371472 [9:13:19<9:27:57,  3.42it/s]
 69%|██████▊   | 254808/371472 [9:13:19<9:07:21,  3.55it/s]
 69%|██████▊   | 254809/371472 [9:13:19<8:55:23,  3.63it/s]
 69%|██████▊   | 254810/371472 [9:13:20<8:45:43,  3.70it/s]
 69%|██████▊   | 254811/371472 [9:13:20<8:38:01,  3.75it/s]
 69%|██████▊   | 254812/371472 [9:13:20<8:33:37,  3.79it/s]
 69%|██████▊   | 254813/371472 [9:13:20<8:31:17,  3.80it/s]
 69%|██████▊   | 254814/371472 [9:13:21<8:17:44,  3.91it/s]
 69%|██████▊   | 254815/371472 [9:13:21<8:50:25,  3.67it/s]
 69%|██████▊   | 254816/371472 [9:13:21<8:28:14,  3.83it/s]
 69%|██████▊   | 254817/371472 [9:13:21<8:52:30,  3.65it/s]
 69%|██████▊   | 254818/371472 [9:13:22<9:00:54,  3.59it/s]
 69%|██████▊   | 254819/371472 [9:13:22<9:34:51,  3.38it/s]
 69%|██████▊   | 254820/371472 [9:13:22<9:37:02,  3.37it/s]
                                                           
{'loss': 2.7572, 'learning_rate': 3.8277597017819814e-07, 'epoch': 10.98}
+
 69%|██████▊   | 254820/371472 [9:13:22<9:37:02,  3.37it/s]
 69%|██████▊   | 254821/371472 [9:13:23<9:02:48,  3.58it/s]
 69%|██████▊   | 254822/371472 [9:13:23<8:39:13,  3.74it/s]
 69%|██████▊   | 254823/371472 [9:13:23<8:40:02,  3.74it/s]
 69%|██████▊   | 254824/371472 [9:13:23<8:39:09,  3.74it/s]
 69%|██████▊   | 254825/371472 [9:13:24<9:35:37,  3.38it/s]
 69%|██████▊   | 254826/371472 [9:13:24<9:42:58,  3.33it/s]
 69%|██████▊   | 254827/371472 [9:13:24<9:25:19,  3.44it/s]
 69%|██████▊   | 254828/371472 [9:13:25<9:04:40,  3.57it/s]
 69%|██████▊   | 254829/371472 [9:13:25<9:09:47,  3.54it/s]
 69%|██████▊   | 254830/371472 [9:13:25<8:59:35,  3.60it/s]
 69%|██████▊   | 254831/371472 [9:13:25<8:48:06,  3.68it/s]
 69%|██████▊   | 254832/371472 [9:13:26<8:51:29,  3.66it/s]
 69%|██████▊   | 254833/371472 [9:13:26<9:11:41,  3.52it/s]
 69%|██████▊   | 254834/371472 [9:13:26<8:59:46,  3.60it/s]
 69%|██████▊   | 254835/371472 [9:13:27<9:02:46,  3.58it/s]
 69%|██████▊   | 254836/371472 [9:13:27<9:07:21,  3.55it/s]
 69%|██████▊   | 254837/371472 [9:13:27<9:06:37,  3.56it/s]
 69%|██████▊   | 254838/371472 [9:13:27<9:28:47,  3.42it/s]
 69%|██████▊   | 254839/371472 [9:13:28<9:43:36,  3.33it/s]
 69%|██████▊   | 254840/371472 [9:13:28<9:43:14,  3.33it/s]
                                                           
{'loss': 2.7257, 'learning_rate': 3.827274882027193e-07, 'epoch': 10.98}
+
 69%|██████▊   | 254840/371472 [9:13:28<9:43:14,  3.33it/s]
 69%|██████▊   | 254841/371472 [9:13:28<9:17:45,  3.49it/s]
 69%|██████▊   | 254842/371472 [9:13:29<9:17:28,  3.49it/s]
 69%|██████▊   | 254843/371472 [9:13:29<9:09:50,  3.54it/s]
 69%|██████▊   | 254844/371472 [9:13:29<9:32:16,  3.40it/s]
 69%|██████▊   | 254845/371472 [9:13:30<9:38:45,  3.36it/s]
 69%|██████▊   | 254846/371472 [9:13:30<10:06:53,  3.20it/s]
 69%|██████▊   | 254847/371472 [9:13:30<10:14:37,  3.16it/s]
 69%|██████▊   | 254848/371472 [9:13:30<9:35:39,  3.38it/s] 
 69%|██████▊   | 254849/371472 [9:13:31<9:05:26,  3.56it/s]
 69%|██████▊   | 254850/371472 [9:13:31<9:02:50,  3.58it/s]
 69%|██████▊   | 254851/371472 [9:13:31<8:51:20,  3.66it/s]
 69%|██████▊   | 254852/371472 [9:13:31<8:39:32,  3.74it/s]
 69%|██████▊   | 254853/371472 [9:13:32<9:23:05,  3.45it/s]
 69%|██████▊   | 254854/371472 [9:13:32<8:54:46,  3.63it/s]
 69%|██████▊   | 254855/371472 [9:13:32<9:05:04,  3.57it/s]
 69%|██████▊   | 254856/371472 [9:13:33<8:41:33,  3.73it/s]
 69%|██████▊   | 254857/371472 [9:13:33<9:03:53,  3.57it/s]
 69%|██████▊   | 254858/371472 [9:13:33<9:01:09,  3.59it/s]
 69%|██████▊   | 254859/371472 [9:13:33<9:12:04,  3.52it/s]
 69%|��█████▊   | 254860/371472 [9:13:34<8:57:17,  3.62it/s]
                                                           
{'loss': 2.8034, 'learning_rate': 3.826790062272404e-07, 'epoch': 10.98}
+
 69%|██████▊   | 254860/371472 [9:13:34<8:57:17,  3.62it/s]
 69%|██████▊   | 254861/371472 [9:13:34<9:13:48,  3.51it/s]
 69%|██████▊   | 254862/371472 [9:13:34<8:56:11,  3.62it/s]
 69%|██████▊   | 254863/371472 [9:13:35<8:37:46,  3.75it/s]
 69%|██████▊   | 254864/371472 [9:13:35<8:57:10,  3.62it/s]
 69%|██████▊   | 254865/371472 [9:13:35<9:13:47,  3.51it/s]
 69%|██████▊   | 254866/371472 [9:13:35<8:47:02,  3.69it/s]
 69%|██████▊   | 254867/371472 [9:13:36<8:22:25,  3.87it/s]
 69%|██████▊   | 254868/371472 [9:13:36<8:43:42,  3.71it/s]
 69%|██████▊   | 254869/371472 [9:13:36<9:05:11,  3.56it/s]
 69%|██████▊   | 254870/371472 [9:13:36<8:46:22,  3.69it/s]
 69%|██████▊   | 254871/371472 [9:13:37<8:51:48,  3.65it/s]
 69%|██████▊   | 254872/371472 [9:13:37<10:02:42,  3.22it/s]
 69%|██████▊   | 254873/371472 [9:13:37<10:04:49,  3.21it/s]
 69%|██████▊   | 254874/371472 [9:13:38<10:12:38,  3.17it/s]
 69%|██████▊   | 254875/371472 [9:13:38<9:32:54,  3.39it/s] 
 69%|██████▊   | 254876/371472 [9:13:38<9:26:53,  3.43it/s]
 69%|██████▊   | 254877/371472 [9:13:39<9:55:24,  3.26it/s]
 69%|██████▊   | 254878/371472 [9:13:39<9:30:28,  3.41it/s]
 69%|██████▊   | 254879/371472 [9:13:39<9:30:28,  3.41it/s]
 69%|██████▊   | 254880/371472 [9:13:39<9:05:04,  3.56it/s]
                                                           
{'loss': 2.7029, 'learning_rate': 3.826305242517615e-07, 'epoch': 10.98}
+
 69%|██████▊   | 254880/371472 [9:13:39<9:05:04,  3.56it/s]
 69%|██████▊   | 254881/371472 [9:13:40<10:12:38,  3.17it/s]
 69%|██████▊   | 254882/371472 [9:13:40<9:40:16,  3.35it/s] 
 69%|██████▊   | 254883/371472 [9:13:40<9:01:04,  3.59it/s]
 69%|██████▊   | 254884/371472 [9:13:41<8:39:13,  3.74it/s]
 69%|██████▊   | 254885/371472 [9:13:41<8:27:36,  3.83it/s]
 69%|██████▊   | 254886/371472 [9:13:41<8:52:14,  3.65it/s]
 69%|██████▊   | 254887/371472 [9:13:41<8:39:47,  3.74it/s]
 69%|██████▊   | 254888/371472 [9:13:42<8:44:58,  3.70it/s]
 69%|██████▊   | 254889/371472 [9:13:42<8:55:04,  3.63it/s]
 69%|██████▊   | 254890/371472 [9:13:42<9:05:28,  3.56it/s]
 69%|██████▊   | 254891/371472 [9:13:42<8:47:13,  3.69it/s]
 69%|██████▊   | 254892/371472 [9:13:43<9:23:34,  3.45it/s]
 69%|██████▊   | 254893/371472 [9:13:43<8:57:37,  3.61it/s]
 69%|██████▊   | 254894/371472 [9:13:43<8:42:19,  3.72it/s]
 69%|██████▊   | 254895/371472 [9:13:44<8:31:59,  3.79it/s]
 69%|██████▊   | 254896/371472 [9:13:44<8:56:34,  3.62it/s]
 69%|██████▊   | 254897/371472 [9:13:44<8:46:24,  3.69it/s]
 69%|██████▊   | 254898/371472 [9:13:44<8:54:16,  3.64it/s]
 69%|██████▊   | 254899/371472 [9:13:45<8:58:58,  3.60it/s]
 69%|██████▊   | 254900/371472 [9:13:45<9:05:23,  3.56it/s]
                                                           
{'loss': 2.8751, 'learning_rate': 3.825820422762826e-07, 'epoch': 10.98}
+
 69%|██████▊   | 254900/371472 [9:13:45<9:05:23,  3.56it/s]
 69%|██████▊   | 254901/371472 [9:13:45<8:42:29,  3.72it/s]
 69%|██████▊   | 254902/371472 [9:13:46<8:49:19,  3.67it/s]
 69%|██████▊   | 254903/371472 [9:13:46<8:33:41,  3.78it/s]
 69%|██████▊   | 254904/371472 [9:13:46<8:35:46,  3.77it/s]
 69%|██████▊   | 254905/371472 [9:13:46<8:51:08,  3.66it/s]
 69%|██████▊   | 254906/371472 [9:13:47<9:04:32,  3.57it/s]
 69%|██████▊   | 254907/371472 [9:13:47<9:21:27,  3.46it/s]
 69%|██████▊   | 254908/371472 [9:13:47<9:09:06,  3.54it/s]
 69%|██████▊   | 254909/371472 [9:13:47<8:43:00,  3.71it/s]
 69%|██████▊   | 254910/371472 [9:13:48<8:51:27,  3.66it/s]
 69%|██████▊   | 254911/371472 [9:13:48<8:28:52,  3.82it/s]
 69%|██████▊   | 254912/371472 [9:13:48<8:22:53,  3.86it/s]
 69%|██████▊   | 254913/371472 [9:13:49<11:53:22,  2.72it/s]
 69%|██████▊   | 254914/371472 [9:13:49<10:45:34,  3.01it/s]
 69%|██████▊   | 254915/371472 [9:13:49<9:59:29,  3.24it/s] 
 69%|██████▊   | 254916/371472 [9:13:50<9:28:22,  3.42it/s]
 69%|██████▊   | 254917/371472 [9:13:50<9:08:02,  3.54it/s]
 69%|██████▊   | 254918/371472 [9:13:50<8:42:08,  3.72it/s]
 69%|██████▊   | 254919/371472 [9:13:50<8:32:50,  3.79it/s]
 69%|██████▊   | 254920/371472 [9:13:51<9:33:21,  3.39it/s]
                                                           
{'loss': 2.7634, 'learning_rate': 3.8253356030080376e-07, 'epoch': 10.98}
+
 69%|██████▊   | 254920/371472 [9:13:51<9:33:21,  3.39it/s]
 69%|██████▊   | 254921/371472 [9:13:51<9:33:28,  3.39it/s]
 69%|██████▊   | 254922/371472 [9:13:51<9:22:36,  3.45it/s]
 69%|██████▊   | 254923/371472 [9:13:52<9:16:40,  3.49it/s]
 69%|██████▊   | 254924/371472 [9:13:52<9:10:34,  3.53it/s]
 69%|██████▊   | 254925/371472 [9:13:52<8:55:21,  3.63it/s]
 69%|██████▊   | 254926/371472 [9:13:52<8:58:21,  3.61it/s]
 69%|██████▊   | 254927/371472 [9:13:53<8:55:26,  3.63it/s]
 69%|██████▊   | 254928/371472 [9:13:53<8:54:03,  3.64it/s]
 69%|██████▊   | 254929/371472 [9:13:53<8:36:35,  3.76it/s]
 69%|██████▊   | 254930/371472 [9:13:53<8:26:14,  3.84it/s]
 69%|██████▊   | 254931/371472 [9:13:54<9:29:34,  3.41it/s]
 69%|██████▊   | 254932/371472 [9:13:54<9:16:18,  3.49it/s]
 69%|██████▊   | 254933/371472 [9:13:54<8:53:55,  3.64it/s]
 69%|██████▊   | 254934/371472 [9:13:55<9:06:11,  3.56it/s]
 69%|██████▊   | 254935/371472 [9:13:55<9:20:30,  3.47it/s]
 69%|██████▊   | 254936/371472 [9:13:55<8:56:09,  3.62it/s]
 69%|██████▊   | 254937/371472 [9:13:55<9:22:31,  3.45it/s]
 69%|██████▊   | 254938/371472 [9:13:56<9:38:49,  3.36it/s]
 69%|██████▊   | 254939/371472 [9:13:56<9:08:34,  3.54it/s]
 69%|██████▊   | 254940/371472 [9:13:56<8:52:59,  3.64it/s]
                                                           
{'loss': 2.8483, 'learning_rate': 3.824850783253248e-07, 'epoch': 10.98}
+
 69%|██████▊   | 254940/371472 [9:13:56<8:52:59,  3.64it/s]
 69%|██████▊   | 254941/371472 [9:13:57<8:57:48,  3.61it/s]
 69%|██████▊   | 254942/371472 [9:13:57<8:50:33,  3.66it/s]
 69%|██████▊   | 254943/371472 [9:13:57<10:36:13,  3.05it/s]
 69%|██████▊   | 254944/371472 [9:13:58<9:50:35,  3.29it/s] 
 69%|██████▊   | 254945/371472 [9:13:58<9:15:26,  3.50it/s]
 69%|██████▊   | 254946/371472 [9:13:58<8:54:14,  3.64it/s]
 69%|██████▊   | 254947/371472 [9:13:58<8:41:15,  3.73it/s]
 69%|██████▊   | 254948/371472 [9:13:59<8:50:15,  3.66it/s]
 69%|██████▊   | 254949/371472 [9:13:59<8:58:58,  3.60it/s]
 69%|██████▊   | 254950/371472 [9:13:59<8:42:48,  3.71it/s]
 69%|██████▊   | 254951/371472 [9:13:59<8:34:30,  3.77it/s]
 69%|██████▊   | 254952/371472 [9:14:00<8:46:18,  3.69it/s]
 69%|██████▊   | 254953/371472 [9:14:00<8:44:55,  3.70it/s]
 69%|██████▊   | 254954/371472 [9:14:00<8:57:01,  3.62it/s]
 69%|██████▊   | 254955/371472 [9:14:00<9:08:09,  3.54it/s]
 69%|██████▊   | 254956/371472 [9:14:01<9:07:23,  3.55it/s]
 69%|██████▊   | 254957/371472 [9:14:01<9:01:50,  3.58it/s]
 69%|██████▊   | 254958/371472 [9:14:01<9:01:51,  3.58it/s]
 69%|██████▊   | 254959/371472 [9:14:02<9:01:32,  3.59it/s]
 69%|██████▊   | 254960/371472 [9:14:02<8:57:34,  3.61it/s]
                                                           
{'loss': 3.0447, 'learning_rate': 3.824365963498459e-07, 'epoch': 10.98}
+
 69%|██████▊   | 254960/371472 [9:14:02<8:57:34,  3.61it/s]
 69%|██████▊   | 254961/371472 [9:14:02<9:01:43,  3.58it/s]
 69%|██████▊   | 254962/371472 [9:14:02<9:34:42,  3.38it/s]
 69%|██████▊   | 254963/371472 [9:14:03<9:30:05,  3.41it/s]
 69%|██████▊   | 254964/371472 [9:14:03<9:02:24,  3.58it/s]
 69%|██████▊   | 254965/371472 [9:14:03<8:51:45,  3.65it/s]
 69%|██████▊   | 254966/371472 [9:14:04<8:46:37,  3.69it/s]
 69%|██████▊   | 254967/371472 [9:14:04<9:02:05,  3.58it/s]
 69%|██████▊   | 254968/371472 [9:14:04<9:03:30,  3.57it/s]
 69%|██████▊   | 254969/371472 [9:14:04<8:50:05,  3.66it/s]
 69%|██████▊   | 254970/371472 [9:14:05<9:04:33,  3.57it/s]
 69%|██████▊   | 254971/371472 [9:14:05<9:02:10,  3.58it/s]
 69%|██████▊   | 254972/371472 [9:14:05<8:50:35,  3.66it/s]
 69%|██████▊   | 254973/371472 [9:14:06<9:22:17,  3.45it/s]
 69%|██████▊   | 254974/371472 [9:14:06<9:09:05,  3.54it/s]
 69%|██████▊   | 254975/371472 [9:14:06<8:50:43,  3.66it/s]
 69%|██████▊   | 254976/371472 [9:14:06<8:55:35,  3.63it/s]
 69%|██████▊   | 254977/371472 [9:14:07<9:08:11,  3.54it/s]
 69%|██████▊   | 254978/371472 [9:14:07<9:16:51,  3.49it/s]
 69%|██████▊   | 254979/371472 [9:14:07<9:51:50,  3.28it/s]
 69%|██████▊   | 254980/371472 [9:14:08<9:24:19,  3.44it/s]
                                                           
{'loss': 2.7779, 'learning_rate': 3.8238811437436703e-07, 'epoch': 10.98}
+
 69%|██████▊   | 254980/371472 [9:14:08<9:24:19,  3.44it/s]
 69%|██████▊   | 254981/371472 [9:14:08<9:20:53,  3.46it/s]
 69%|██████▊   | 254982/371472 [9:14:08<8:56:13,  3.62it/s]
 69%|██████▊   | 254983/371472 [9:14:08<8:44:09,  3.70it/s]
 69%|██████▊   | 254984/371472 [9:14:09<8:41:53,  3.72it/s]
 69%|██████▊   | 254985/371472 [9:14:09<8:36:58,  3.76it/s]
 69%|██████▊   | 254986/371472 [9:14:09<8:38:03,  3.75it/s]
 69%|██████▊   | 254987/371472 [9:14:09<8:45:35,  3.69it/s]
 69%|██████▊   | 254988/371472 [9:14:10<8:52:43,  3.64it/s]
 69%|██████▊   | 254989/371472 [9:14:10<8:56:25,  3.62it/s]
 69%|██████▊   | 254990/371472 [9:14:10<9:15:28,  3.50it/s]
 69%|██████▊   | 254991/371472 [9:14:11<9:16:00,  3.49it/s]
 69%|██████▊   | 254992/371472 [9:14:11<9:13:24,  3.51it/s]
 69%|██████▊   | 254993/371472 [9:14:11<9:18:31,  3.48it/s]
 69%|██████▊   | 254994/371472 [9:14:11<8:48:52,  3.67it/s]
 69%|██████▊   | 254995/371472 [9:14:12<9:55:24,  3.26it/s]
 69%|██████▊   | 254996/371472 [9:14:12<9:18:46,  3.47it/s]
 69%|██████▊   | 254997/371472 [9:14:12<9:26:03,  3.43it/s]
 69%|██████▊   | 254998/371472 [9:14:13<9:12:30,  3.51it/s]
 69%|██████▊   | 254999/371472 [9:14:13<9:26:57,  3.42it/s]
 69%|██████▊   | 255000/371472 [9:14:13<9:10:03,  3.53it/s]
                                                           
{'loss': 2.8687, 'learning_rate': 3.8233963239888815e-07, 'epoch': 10.98}
+
 69%|██████▊   | 255000/371472 [9:14:13<9:10:03,  3.53it/s]
 69%|██████▊   | 255001/371472 [9:14:13<8:48:04,  3.68it/s]
 69%|██████▊   | 255002/371472 [9:14:14<9:07:35,  3.54it/s]
 69%|██████▊   | 255003/371472 [9:14:14<8:40:35,  3.73it/s]
 69%|██████▊   | 255004/371472 [9:14:14<9:13:05,  3.51it/s]
 69%|██████▊   | 255005/371472 [9:14:15<9:25:26,  3.43it/s]
 69%|██████▊   | 255006/371472 [9:14:15<9:18:16,  3.48it/s]
 69%|██████▊   | 255007/371472 [9:14:15<8:56:35,  3.62it/s]
 69%|██████▊   | 255008/371472 [9:14:15<9:00:12,  3.59it/s]
 69%|██████▊   | 255009/371472 [9:14:16<9:01:51,  3.58it/s]
 69%|██████▊   | 255010/371472 [9:14:16<8:58:46,  3.60it/s]
 69%|██████▊   | 255011/371472 [9:14:16<8:44:43,  3.70it/s]
 69%|██████▊   | 255012/371472 [9:14:16<8:48:06,  3.68it/s]
 69%|██████▊   | 255013/371472 [9:14:17<8:37:17,  3.75it/s]
 69%|██████▊   | 255014/371472 [9:14:17<8:46:13,  3.69it/s]
 69%|██████▊   | 255015/371472 [9:14:17<9:05:40,  3.56it/s]
 69%|██████▊   | 255016/371472 [9:14:18<9:01:07,  3.59it/s]
 69%|██████▊   | 255017/371472 [9:14:18<8:43:35,  3.71it/s]
 69%|██████▊   | 255018/371472 [9:14:18<8:42:39,  3.71it/s]
 69%|██████▊   | 255019/371472 [9:14:18<9:05:45,  3.56it/s]
 69%|██████▊   | 255020/371472 [9:14:19<8:43:34,  3.71it/s]
                                                           
{'loss': 2.9266, 'learning_rate': 3.822911504234092e-07, 'epoch': 10.98}
+
 69%|██████▊   | 255020/371472 [9:14:19<8:43:34,  3.71it/s]
 69%|██████▊   | 255021/371472 [9:14:19<8:42:05,  3.72it/s]
 69%|██████▊   | 255022/371472 [9:14:19<8:56:50,  3.62it/s]
 69%|██████▊   | 255023/371472 [9:14:20<9:42:52,  3.33it/s]
 69%|██████▊   | 255024/371472 [9:14:20<9:26:42,  3.42it/s]
 69%|██████▊   | 255025/371472 [9:14:20<9:56:05,  3.26it/s]
 69%|██████▊   | 255026/371472 [9:14:20<9:35:05,  3.37it/s]
 69%|██████▊   | 255027/371472 [9:14:21<9:27:46,  3.42it/s]
 69%|██████▊   | 255028/371472 [9:14:21<9:44:29,  3.32it/s]
 69%|██████▊   | 255029/371472 [9:14:21<9:29:51,  3.41it/s]
 69%|██████▊   | 255030/371472 [9:14:22<9:10:24,  3.53it/s]
 69%|██████▊   | 255031/371472 [9:14:22<9:30:35,  3.40it/s]
 69%|██████▊   | 255032/371472 [9:14:22<9:06:53,  3.55it/s]
 69%|██████▊   | 255033/371472 [9:14:22<9:13:48,  3.50it/s]
 69%|██████▊   | 255034/371472 [9:14:23<9:05:41,  3.56it/s]
 69%|██████▊   | 255035/371472 [9:14:23<8:51:17,  3.65it/s]
 69%|██████▊   | 255036/371472 [9:14:23<8:46:40,  3.68it/s]
 69%|██████▊   | 255037/371472 [9:14:23<8:31:49,  3.79it/s]
 69%|██████▊   | 255038/371472 [9:14:24<8:55:09,  3.63it/s]
 69%|██████▊   | 255039/371472 [9:14:24<8:53:13,  3.64it/s]
 69%|██████▊   | 255040/371472 [9:14:24<9:00:07,  3.59it/s]
                                                           
{'loss': 2.7911, 'learning_rate': 3.822426684479303e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255040/371472 [9:14:24<9:00:07,  3.59it/s]
 69%|██████▊   | 255041/371472 [9:14:25<9:30:31,  3.40it/s]
 69%|██████▊   | 255042/371472 [9:14:25<9:20:08,  3.46it/s]
 69%|██████▊   | 255043/371472 [9:14:25<8:58:50,  3.60it/s]
 69%|██████▊   | 255044/371472 [9:14:25<8:39:42,  3.73it/s]
 69%|██████▊   | 255045/371472 [9:14:26<8:22:07,  3.86it/s]
 69%|██████▊   | 255046/371472 [9:14:26<8:21:19,  3.87it/s]
 69%|██████▊   | 255047/371472 [9:14:26<8:57:31,  3.61it/s]
 69%|██████▊   | 255048/371472 [9:14:27<9:23:01,  3.45it/s]
 69%|██████▊   | 255049/371472 [9:14:27<9:00:26,  3.59it/s]
 69%|██████▊   | 255050/371472 [9:14:27<8:57:14,  3.61it/s]
 69%|██████▊   | 255051/371472 [9:14:27<9:02:54,  3.57it/s]
 69%|██████▊   | 255052/371472 [9:14:28<9:07:29,  3.54it/s]
 69%|██████▊   | 255053/371472 [9:14:28<8:58:27,  3.60it/s]
 69%|██████▊   | 255054/371472 [9:14:28<8:54:40,  3.63it/s]
 69%|██████▊   | 255055/371472 [9:14:29<8:59:24,  3.60it/s]
 69%|██████▊   | 255056/371472 [9:14:29<9:46:52,  3.31it/s]
 69%|██████▊   | 255057/371472 [9:14:29<9:16:18,  3.49it/s]
 69%|██████▊   | 255058/371472 [9:14:29<8:48:43,  3.67it/s]
 69%|██████▊   | 255059/371472 [9:14:30<9:06:56,  3.55it/s]
 69%|██████▊   | 255060/371472 [9:14:30<8:42:48,  3.71it/s]
                                                           
{'loss': 2.9215, 'learning_rate': 3.821941864724515e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255060/371472 [9:14:30<8:42:48,  3.71it/s]
 69%|██████▊   | 255061/371472 [9:14:30<8:55:32,  3.62it/s]
 69%|██████▊   | 255062/371472 [9:14:30<8:53:16,  3.64it/s]
 69%|██████▊   | 255063/371472 [9:14:31<9:04:48,  3.56it/s]
 69%|██████▊   | 255064/371472 [9:14:31<8:59:28,  3.60it/s]
 69%|██████▊   | 255065/371472 [9:14:31<8:47:47,  3.68it/s]
 69%|██████▊   | 255066/371472 [9:14:32<9:45:12,  3.32it/s]
 69%|██████▊   | 255067/371472 [9:14:32<9:27:49,  3.42it/s]
 69%|██████▊   | 255068/371472 [9:14:32<9:51:40,  3.28it/s]
 69%|██████▊   | 255069/371472 [9:14:33<9:35:23,  3.37it/s]
 69%|██████▊   | 255070/371472 [9:14:33<11:05:31,  2.92it/s]
 69%|██████▊   | 255071/371472 [9:14:33<10:12:19,  3.17it/s]
 69%|██████▊   | 255072/371472 [9:14:34<9:51:31,  3.28it/s] 
 69%|██████▊   | 255073/371472 [9:14:34<9:33:49,  3.38it/s]
 69%|██████▊   | 255074/371472 [9:14:34<9:10:26,  3.52it/s]
 69%|██████▊   | 255075/371472 [9:14:34<8:52:38,  3.64it/s]
 69%|██████▊   | 255076/371472 [9:14:35<8:42:25,  3.71it/s]
 69%|██████▊   | 255077/371472 [9:14:35<8:40:43,  3.73it/s]
 69%|██████▊   | 255078/371472 [9:14:35<8:39:59,  3.73it/s]
 69%|██████▊   | 255079/371472 [9:14:35<8:18:45,  3.89it/s]
 69%|██████▊   | 255080/371472 [9:14:36<8:16:24,  3.91it/s]
                                                           
{'loss': 2.8432, 'learning_rate': 3.821457044969725e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255080/371472 [9:14:36<8:16:24,  3.91it/s]
 69%|██████▊   | 255081/371472 [9:14:36<8:45:20,  3.69it/s]
 69%|██████▊   | 255082/371472 [9:14:36<8:30:57,  3.80it/s]
 69%|██████▊   | 255083/371472 [9:14:36<8:48:23,  3.67it/s]
 69%|██████▊   | 255084/371472 [9:14:37<8:35:16,  3.76it/s]
 69%|██████▊   | 255085/371472 [9:14:37<8:36:49,  3.75it/s]
 69%|██████▊   | 255086/371472 [9:14:37<8:51:21,  3.65it/s]
 69%|██████▊   | 255087/371472 [9:14:37<8:36:19,  3.76it/s]
 69%|██████▊   | 255088/371472 [9:14:38<8:55:18,  3.62it/s]
 69%|██████▊   | 255089/371472 [9:14:38<8:49:55,  3.66it/s]
 69%|██████▊   | 255090/371472 [9:14:38<8:34:12,  3.77it/s]
 69%|██████▊   | 255091/371472 [9:14:39<8:42:36,  3.71it/s]
 69%|██████▊   | 255092/371472 [9:14:39<8:27:01,  3.83it/s]
 69%|██████▊   | 255093/371472 [9:14:39<8:22:13,  3.86it/s]
 69%|██████▊   | 255094/371472 [9:14:39<8:25:41,  3.84it/s]
 69%|██████▊   | 255095/371472 [9:14:40<8:41:51,  3.72it/s]
 69%|██████▊   | 255096/371472 [9:14:40<8:46:31,  3.68it/s]
 69%|██████▊   | 255097/371472 [9:14:40<8:39:33,  3.73it/s]
 69%|██████▊   | 255098/371472 [9:14:40<9:09:57,  3.53it/s]
 69%|██████▊   | 255099/371472 [9:14:41<8:47:36,  3.68it/s]
 69%|██████▊   | 255100/371472 [9:14:41<9:46:10,  3.31it/s]
                                                           
{'loss': 2.7459, 'learning_rate': 3.8209722252149367e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255100/371472 [9:14:41<9:46:10,  3.31it/s]
 69%|██████▊   | 255101/371472 [9:14:41<10:26:38,  3.10it/s]
 69%|██████▊   | 255102/371472 [9:14:42<9:49:01,  3.29it/s] 
 69%|██████▊   | 255103/371472 [9:14:42<9:16:25,  3.49it/s]
 69%|██████▊   | 255104/371472 [9:14:42<9:00:34,  3.59it/s]
 69%|██████▊   | 255105/371472 [9:14:43<8:55:15,  3.62it/s]
 69%|██████▊   | 255106/371472 [9:14:43<8:40:11,  3.73it/s]
 69%|██████▊   | 255107/371472 [9:14:43<8:24:16,  3.85it/s]
 69%|██████▊   | 255108/371472 [9:14:43<8:26:49,  3.83it/s]
 69%|██████▊   | 255109/371472 [9:14:44<8:23:05,  3.85it/s]
 69%|██████▊   | 255110/371472 [9:14:44<8:27:11,  3.82it/s]
 69%|██████▊   | 255111/371472 [9:14:44<9:03:36,  3.57it/s]
 69%|██████▊   | 255112/371472 [9:14:44<8:54:32,  3.63it/s]
 69%|██████▊   | 255113/371472 [9:14:45<8:28:44,  3.81it/s]
 69%|██████▊   | 255114/371472 [9:14:45<8:43:55,  3.70it/s]
 69%|██████▊   | 255115/371472 [9:14:45<9:21:25,  3.45it/s]
 69%|██████▊   | 255116/371472 [9:14:46<9:09:00,  3.53it/s]
 69%|██████▊   | 255117/371472 [9:14:46<9:02:59,  3.57it/s]
 69%|██████▊   | 255118/371472 [9:14:46<8:51:38,  3.65it/s]
 69%|██████▊   | 255119/371472 [9:14:46<8:33:12,  3.78it/s]
 69%|██████▊   | 255120/371472 [9:14:47<9:08:37,  3.53it/s]
                                                           
{'loss': 2.8036, 'learning_rate': 3.820487405460147e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255120/371472 [9:14:47<9:08:37,  3.53it/s]
 69%|██████▊   | 255121/371472 [9:14:47<10:04:03,  3.21it/s]
 69%|██████▊   | 255122/371472 [9:14:47<9:47:28,  3.30it/s] 
 69%|██████▊   | 255123/371472 [9:14:48<9:51:03,  3.28it/s]
 69%|██████▊   | 255124/371472 [9:14:48<9:21:36,  3.45it/s]
 69%|██████▊   | 255125/371472 [9:14:48<9:07:38,  3.54it/s]
 69%|██████▊   | 255126/371472 [9:14:49<10:52:17,  2.97it/s]
 69%|██████▊   | 255127/371472 [9:14:49<9:58:28,  3.24it/s] 
 69%|██████▊   | 255128/371472 [9:14:49<9:16:29,  3.48it/s]
 69%|██████▊   | 255129/371472 [9:14:49<9:03:28,  3.57it/s]
 69%|██████▊   | 255130/371472 [9:14:50<8:55:06,  3.62it/s]
 69%|██████▊   | 255131/371472 [9:14:50<9:22:24,  3.45it/s]
 69%|██████▊   | 255132/371472 [9:14:50<9:43:55,  3.32it/s]
 69%|██████▊   | 255133/371472 [9:14:50<9:23:48,  3.44it/s]
 69%|██████▊   | 255134/371472 [9:14:51<9:11:16,  3.52it/s]
 69%|██████▊   | 255135/371472 [9:14:51<8:59:22,  3.59it/s]
 69%|██████▊   | 255136/371472 [9:14:51<9:06:48,  3.55it/s]
 69%|██████▊   | 255137/371472 [9:14:52<9:39:24,  3.35it/s]
 69%|██████▊   | 255138/371472 [9:14:52<9:03:40,  3.57it/s]
 69%|██████▊   | 255139/371472 [9:14:52<8:53:17,  3.64it/s]
 69%|██████▊   | 255140/371472 [9:14:52<8:29:09,  3.81it/s]
                                                           
{'loss': 2.9141, 'learning_rate': 3.8200025857053587e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255140/371472 [9:14:52<8:29:09,  3.81it/s]
 69%|██████▊   | 255141/371472 [9:14:53<9:06:03,  3.55it/s]
 69%|██████▊   | 255142/371472 [9:14:53<8:47:28,  3.68it/s]
 69%|██████▊   | 255143/371472 [9:14:53<9:01:09,  3.58it/s]
 69%|██████▊   | 255144/371472 [9:14:54<8:52:48,  3.64it/s]
 69%|██████▊   | 255145/371472 [9:14:54<9:26:58,  3.42it/s]
 69%|██████▊   | 255146/371472 [9:14:54<9:11:05,  3.52it/s]
 69%|██████▊   | 255147/371472 [9:14:54<9:06:14,  3.55it/s]
 69%|██████▊   | 255148/371472 [9:14:55<9:03:28,  3.57it/s]
 69%|██████▊   | 255149/371472 [9:14:55<8:39:37,  3.73it/s]
 69%|██████▊   | 255150/371472 [9:14:55<9:05:43,  3.55it/s]
 69%|██████▊   | 255151/371472 [9:14:56<9:21:57,  3.45it/s]
 69%|██████▊   | 255152/371472 [9:14:56<9:22:10,  3.45it/s]
 69%|██████▊   | 255153/371472 [9:14:56<8:57:02,  3.61it/s]
 69%|██████▊   | 255154/371472 [9:14:56<9:04:22,  3.56it/s]
 69%|██████▊   | 255155/371472 [9:14:57<8:47:50,  3.67it/s]
 69%|██████▊   | 255156/371472 [9:14:57<9:37:21,  3.36it/s]
 69%|██████▊   | 255157/371472 [9:14:57<9:19:23,  3.47it/s]
 69%|██████▊   | 255158/371472 [9:14:57<8:53:04,  3.64it/s]
 69%|██████▊   | 255159/371472 [9:14:58<9:03:35,  3.57it/s]
 69%|██████▊   | 255160/371472 [9:14:58<8:48:36,  3.67it/s]
                                                           
{'loss': 2.656, 'learning_rate': 3.8195177659505694e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255160/371472 [9:14:58<8:48:36,  3.67it/s]
 69%|██████▊   | 255161/371472 [9:14:58<8:30:43,  3.80it/s]
 69%|██████▊   | 255162/371472 [9:14:59<8:31:11,  3.79it/s]
 69%|██████▊   | 255163/371472 [9:14:59<8:19:03,  3.88it/s]
 69%|██████▊   | 255164/371472 [9:14:59<8:29:42,  3.80it/s]
 69%|██████▊   | 255165/371472 [9:14:59<8:33:19,  3.78it/s]
 69%|██████▊   | 255166/371472 [9:15:00<8:56:19,  3.61it/s]
 69%|██████▊   | 255167/371472 [9:15:00<8:37:05,  3.75it/s]
 69%|██████▊   | 255168/371472 [9:15:00<8:47:36,  3.67it/s]
 69%|██████▊   | 255169/371472 [9:15:00<8:44:51,  3.69it/s]
 69%|██████▊   | 255170/371472 [9:15:01<8:43:43,  3.70it/s]
 69%|██████▊   | 255171/371472 [9:15:01<8:42:31,  3.71it/s]
 69%|██████▊   | 255172/371472 [9:15:01<8:46:03,  3.68it/s]
 69%|██████▊   | 255173/371472 [9:15:02<9:00:41,  3.58it/s]
 69%|██████▊   | 255174/371472 [9:15:02<8:58:16,  3.60it/s]
 69%|██████▊   | 255175/371472 [9:15:02<8:43:12,  3.70it/s]
 69%|██████▊   | 255176/371472 [9:15:02<8:31:46,  3.79it/s]
 69%|██████▊   | 255177/371472 [9:15:03<8:26:48,  3.82it/s]
 69%|██████▊   | 255178/371472 [9:15:03<8:38:54,  3.74it/s]
 69%|██████▊   | 255179/371472 [9:15:03<8:33:53,  3.77it/s]
 69%|██████▊   | 255180/371472 [9:15:03<8:44:50,  3.69it/s]
                                                           
{'loss': 2.8081, 'learning_rate': 3.819032946195781e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255180/371472 [9:15:03<8:44:50,  3.69it/s]
 69%|██████▊   | 255181/371472 [9:15:04<8:40:10,  3.73it/s]
 69%|██████▊   | 255182/371472 [9:15:04<9:25:11,  3.43it/s]
 69%|██████▊   | 255183/371472 [9:15:04<9:22:38,  3.44it/s]
 69%|██████▊   | 255184/371472 [9:15:05<9:10:40,  3.52it/s]
 69%|██████▊   | 255185/371472 [9:15:05<8:55:15,  3.62it/s]
 69%|██████▊   | 255186/371472 [9:15:05<9:02:12,  3.57it/s]
 69%|██████▊   | 255187/371472 [9:15:05<8:49:17,  3.66it/s]
 69%|██████▊   | 255188/371472 [9:15:06<8:41:13,  3.72it/s]
 69%|██████▊   | 255189/371472 [9:15:06<8:47:25,  3.67it/s]
 69%|██████▊   | 255190/371472 [9:15:06<8:29:38,  3.80it/s]
 69%|██████▊   | 255191/371472 [9:15:06<8:22:20,  3.86it/s]
 69%|██████▊   | 255192/371472 [9:15:07<9:18:07,  3.47it/s]
 69%|██████▊   | 255193/371472 [9:15:07<8:55:47,  3.62it/s]
 69%|██████▊   | 255194/371472 [9:15:07<8:51:48,  3.64it/s]
 69%|██████▊   | 255195/371472 [9:15:08<8:49:22,  3.66it/s]
 69%|██████▊   | 255196/371472 [9:15:08<8:40:53,  3.72it/s]
 69%|██████▊   | 255197/371472 [9:15:08<8:27:03,  3.82it/s]
 69%|██████▊   | 255198/371472 [9:15:08<8:48:07,  3.67it/s]
 69%|██████▊   | 255199/371472 [9:15:09<9:40:40,  3.34it/s]
 69%|██████▊   | 255200/371472 [9:15:09<9:16:06,  3.48it/s]
                                                           
{'loss': 3.065, 'learning_rate': 3.8185481264409913e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255200/371472 [9:15:09<9:16:06,  3.48it/s]
 69%|██████▊   | 255201/371472 [9:15:09<9:05:43,  3.55it/s]
 69%|██████▊   | 255202/371472 [9:15:10<9:19:32,  3.46it/s]
 69%|██████▊   | 255203/371472 [9:15:10<8:54:44,  3.62it/s]
 69%|██████▊   | 255204/371472 [9:15:10<8:45:29,  3.69it/s]
 69%|██████▊   | 255205/371472 [9:15:10<8:33:32,  3.77it/s]
 69%|██████▊   | 255206/371472 [9:15:11<8:57:02,  3.61it/s]
 69%|██████▊   | 255207/371472 [9:15:11<8:44:34,  3.69it/s]
 69%|██████▊   | 255208/371472 [9:15:11<8:38:17,  3.74it/s]
 69%|██████▊   | 255209/371472 [9:15:11<8:37:28,  3.74it/s]
 69%|██████▊   | 255210/371472 [9:15:12<8:51:47,  3.64it/s]
 69%|██████▊   | 255211/371472 [9:15:12<8:54:53,  3.62it/s]
 69%|██████▊   | 255212/371472 [9:15:12<8:59:56,  3.59it/s]
 69%|██████▊   | 255213/371472 [9:15:13<9:16:29,  3.48it/s]
 69%|██████▊   | 255214/371472 [9:15:13<9:06:28,  3.55it/s]
 69%|██████▊   | 255215/371472 [9:15:13<8:56:15,  3.61it/s]
 69%|██████▊   | 255216/371472 [9:15:13<9:05:20,  3.55it/s]
 69%|██████▊   | 255217/371472 [9:15:14<9:18:08,  3.47it/s]
 69%|██████▊   | 255218/371472 [9:15:14<8:56:32,  3.61it/s]
 69%|██████▊   | 255219/371472 [9:15:14<8:34:18,  3.77it/s]
 69%|██████▊   | 255220/371472 [9:15:14<8:21:45,  3.86it/s]
                                                           
{'loss': 2.8738, 'learning_rate': 3.818063306686203e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255220/371472 [9:15:14<8:21:45,  3.86it/s]
 69%|██████▊   | 255221/371472 [9:15:15<8:39:09,  3.73it/s]
 69%|██████▊   | 255222/371472 [9:15:15<8:50:25,  3.65it/s]
 69%|██████▊   | 255223/371472 [9:15:15<8:27:59,  3.81it/s]
 69%|██████▊   | 255224/371472 [9:15:15<8:17:48,  3.89it/s]
 69%|██████▊   | 255225/371472 [9:15:16<8:31:04,  3.79it/s]
 69%|██████▊   | 255226/371472 [9:15:16<8:26:28,  3.83it/s]
 69%|██████▊   | 255227/371472 [9:15:16<8:37:04,  3.75it/s]
 69%|██████▊   | 255228/371472 [9:15:17<8:39:33,  3.73it/s]
 69%|██████▊   | 255229/371472 [9:15:17<8:51:40,  3.64it/s]
 69%|██████▊   | 255230/371472 [9:15:17<8:45:48,  3.68it/s]
 69%|██████▊   | 255231/371472 [9:15:17<8:45:25,  3.69it/s]
 69%|██████▊   | 255232/371472 [9:15:18<8:36:11,  3.75it/s]
 69%|██████▊   | 255233/371472 [9:15:18<8:34:22,  3.77it/s]
 69%|██████▊   | 255234/371472 [9:15:18<8:29:19,  3.80it/s]
 69%|██████▊   | 255235/371472 [9:15:18<8:54:01,  3.63it/s]
 69%|██████▊   | 255236/371472 [9:15:19<9:04:54,  3.56it/s]
 69%|██████▊   | 255237/371472 [9:15:19<8:49:35,  3.66it/s]
 69%|██████▊   | 255238/371472 [9:15:19<9:08:18,  3.53it/s]
 69%|██████▊   | 255239/371472 [9:15:20<9:10:05,  3.52it/s]
 69%|██████▊   | 255240/371472 [9:15:20<8:55:52,  3.62it/s]
                                                           
{'loss': 2.7932, 'learning_rate': 3.817578486931414e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255240/371472 [9:15:20<8:55:52,  3.62it/s]
 69%|██████▊   | 255241/371472 [9:15:20<8:47:20,  3.67it/s]
 69%|██████▊   | 255242/371472 [9:15:20<8:42:48,  3.71it/s]
 69%|██████▊   | 255243/371472 [9:15:21<9:17:31,  3.47it/s]
 69%|██████▊   | 255244/371472 [9:15:21<9:13:04,  3.50it/s]
 69%|██████▊   | 255245/371472 [9:15:21<9:04:05,  3.56it/s]
 69%|██████▊   | 255246/371472 [9:15:22<8:47:14,  3.67it/s]
 69%|██████▊   | 255247/371472 [9:15:22<8:39:22,  3.73it/s]
 69%|██████▊   | 255248/371472 [9:15:22<8:23:03,  3.85it/s]
 69%|██████▊   | 255249/371472 [9:15:22<8:40:00,  3.73it/s]
 69%|██████▊   | 255250/371472 [9:15:23<9:16:48,  3.48it/s]
 69%|██████▊   | 255251/371472 [9:15:23<9:35:16,  3.37it/s]
 69%|██████▊   | 255252/371472 [9:15:23<9:04:33,  3.56it/s]
 69%|██████▊   | 255253/371472 [9:15:23<8:59:43,  3.59it/s]
 69%|██████▊   | 255254/371472 [9:15:24<8:37:59,  3.74it/s]
 69%|██████▊   | 255255/371472 [9:15:24<8:44:01,  3.70it/s]
 69%|██████▊   | 255256/371472 [9:15:24<9:02:48,  3.57it/s]
 69%|██████▊   | 255257/371472 [9:15:25<8:45:09,  3.69it/s]
 69%|██████▊   | 255258/371472 [9:15:25<9:30:09,  3.40it/s]
 69%|██████▊   | 255259/371472 [9:15:25<8:50:13,  3.65it/s]
 69%|██████▊   | 255260/371472 [9:15:25<8:51:59,  3.64it/s]
                                                           
{'loss': 2.8375, 'learning_rate': 3.817093667176625e-07, 'epoch': 10.99}
+
 69%|██████▊   | 255260/371472 [9:15:25<8:51:59,  3.64it/s]
 69%|██████▊   | 255261/371472 [9:15:26<8:54:39,  3.62it/s]
 69%|██████▊   | 255262/371472 [9:15:26<8:49:23,  3.66it/s]
 69%|██████▊   | 255263/371472 [9:15:26<9:01:41,  3.58it/s]
 69%|██████▊   | 255264/371472 [9:15:27<9:16:10,  3.48it/s]
 69%|██████▊   | 255265/371472 [9:15:27<9:32:37,  3.38it/s]
 69%|██████▊   | 255266/371472 [9:15:27<8:58:28,  3.60it/s]
 69%|██████▊   | 255267/371472 [9:15:27<8:48:01,  3.67it/s]
 69%|██████▊   | 255268/371472 [9:15:28<8:38:28,  3.74it/s]
 69%|██████▊   | 255269/371472 [9:15:28<8:49:53,  3.65it/s]
 69%|██████▊   | 255270/371472 [9:15:28<9:33:17,  3.38it/s]
 69%|██████▊   | 255271/371472 [9:15:29<9:37:48,  3.35it/s]
 69%|██████▊   | 255272/371472 [9:15:29<9:16:08,  3.48it/s]
 69%|██████▊   | 255273/371472 [9:15:29<9:57:24,  3.24it/s]
 69%|██████▊   | 255274/371472 [9:15:30<10:20:21,  3.12it/s]
 69%|██████▊   | 255275/371472 [9:15:30<9:30:56,  3.39it/s] 
 69%|██████▊   | 255276/371472 [9:15:30<8:57:54,  3.60it/s]
 69%|██████▊   | 255277/371472 [9:15:30<8:30:16,  3.80it/s]
 69%|██████▊   | 255278/371472 [9:15:31<9:03:09,  3.57it/s]
 69%|██████▊   | 255279/371472 [9:15:31<9:36:16,  3.36it/s]
 69%|██████▊   | 255280/371472 [9:15:31<9:12:32,  3.50it/s]
                                                           
{'loss': 2.837, 'learning_rate': 3.816608847421836e-07, 'epoch': 11.0}
+
 69%|██████▊   | 255280/371472 [9:15:31<9:12:32,  3.50it/s]
 69%|██████▊   | 255281/371472 [9:15:31<8:55:23,  3.62it/s]
 69%|██████▊   | 255282/371472 [9:15:32<8:57:01,  3.61it/s]
 69%|██████▊   | 255283/371472 [9:15:32<8:48:49,  3.66it/s]
 69%|██████▊   | 255284/371472 [9:15:32<9:18:02,  3.47it/s]
 69%|██████▊   | 255285/371472 [9:15:33<9:03:48,  3.56it/s]
 69%|██████▊   | 255286/371472 [9:15:33<9:40:02,  3.34it/s]
 69%|██████▊   | 255287/371472 [9:15:33<10:24:16,  3.10it/s]
 69%|██████▊   | 255288/371472 [9:15:34<10:34:29,  3.05it/s]
 69%|██████▊   | 255289/371472 [9:15:34<10:18:21,  3.13it/s]
 69%|██████▊   | 255290/371472 [9:15:34<9:39:56,  3.34it/s] 
 69%|██████▊   | 255291/371472 [9:15:34<9:27:25,  3.41it/s]
 69%|██████▊   | 255292/371472 [9:15:35<9:39:40,  3.34it/s]
 69%|██████▊   | 255293/371472 [9:15:35<9:57:15,  3.24it/s]
 69%|██████▊   | 255294/371472 [9:15:35<9:51:08,  3.28it/s]
 69%|██████▊   | 255295/371472 [9:15:36<9:37:25,  3.35it/s]
 69%|██████▊   | 255296/371472 [9:15:36<9:34:55,  3.37it/s]
 69%|██████▊   | 255297/371472 [9:15:36<9:56:51,  3.24it/s]
 69%|██████▊   | 255298/371472 [9:15:37<9:45:37,  3.31it/s]
 69%|██████▊   | 255299/371472 [9:15:37<9:33:12,  3.38it/s]
 69%|██████▊   | 255300/371472 [9:15:37<9:13:52,  3.50it/s]
                                                           
{'loss': 2.9323, 'learning_rate': 3.8161240276670475e-07, 'epoch': 11.0}
+
 69%|██████▊   | 255300/371472 [9:15:37<9:13:52,  3.50it/s]
 69%|██████▊   | 255301/371472 [9:15:37<9:15:40,  3.48it/s]
 69%|██████▊   | 255302/371472 [9:15:38<9:18:50,  3.46it/s]
 69%|██████▊   | 255303/371472 [9:15:38<9:21:32,  3.45it/s]
 69%|██████▊   | 255304/371472 [9:15:38<8:54:34,  3.62it/s]
 69%|██████▊   | 255305/371472 [9:15:38<8:32:46,  3.78it/s]
 69%|██████▊   | 255306/371472 [9:15:39<8:26:11,  3.82it/s]
 69%|██████▊   | 255307/371472 [9:15:39<8:32:10,  3.78it/s]
 69%|██████▊   | 255308/371472 [9:15:39<8:50:49,  3.65it/s]
 69%|██████▊   | 255309/371472 [9:15:40<9:25:50,  3.42it/s]
 69%|██████▊   | 255310/371472 [9:15:40<9:03:30,  3.56it/s]
 69%|██████▊   | 255311/371472 [9:15:40<8:40:43,  3.72it/s]
 69%|██████▊   | 255312/371472 [9:15:40<8:39:43,  3.73it/s]
 69%|██████▊   | 255313/371472 [9:15:41<8:43:03,  3.70it/s]
 69%|██████▊   | 255314/371472 [9:15:41<9:14:09,  3.49it/s]
 69%|██████▊   | 255315/371472 [9:15:41<9:20:34,  3.45it/s]
 69%|██████▊   | 255316/371472 [9:15:42<9:04:46,  3.55it/s]
 69%|██████▊   | 255317/371472 [9:15:42<9:06:28,  3.54it/s]
 69%|██████▊   | 255318/371472 [9:15:42<9:03:18,  3.56it/s]
 69%|██████▊   | 255319/371472 [9:15:42<9:13:24,  3.50it/s]
 69%|██████▊   | 255320/371472 [9:15:43<9:02:48,  3.57it/s]
                                                           
{'loss': 2.9747, 'learning_rate': 3.815639207912258e-07, 'epoch': 11.0}
+
 69%|██████▊   | 255320/371472 [9:15:43<9:02:48,  3.57it/s]
 69%|██████▊   | 255321/371472 [9:15:43<8:54:31,  3.62it/s]
 69%|██████▊   | 255322/371472 [9:15:43<9:12:08,  3.51it/s]
 69%|██████▊   | 255323/371472 [9:15:44<9:50:23,  3.28it/s]
 69%|██████▊   | 255324/371472 [9:15:44<9:50:28,  3.28it/s]
 69%|██████▊   | 255325/371472 [9:15:44<9:42:50,  3.32it/s]
 69%|██████▊   | 255326/371472 [9:15:44<9:47:53,  3.29it/s]
 69%|██████▊   | 255327/371472 [9:15:45<9:16:15,  3.48it/s]
 69%|██████▊   | 255328/371472 [9:15:45<9:07:59,  3.53it/s]
 69%|██████▊   | 255329/371472 [9:15:45<9:18:08,  3.47it/s]
 69%|██████▊   | 255330/371472 [9:15:46<9:07:49,  3.53it/s]
 69%|██████▊   | 255331/371472 [9:15:46<8:50:27,  3.65it/s]
 69%|██████▊   | 255332/371472 [9:15:46<8:59:19,  3.59it/s]
 69%|██████▊   | 255333/371472 [9:15:46<8:50:03,  3.65it/s]
 69%|██████▊   | 255334/371472 [9:15:47<8:45:10,  3.69it/s]
 69%|██████▊   | 255335/371472 [9:15:47<9:00:38,  3.58it/s]
 69%|██████▊   | 255336/371472 [9:15:47<9:09:25,  3.52it/s]
 69%|██████▊   | 255337/371472 [9:15:48<9:14:10,  3.49it/s]
 69%|██████▊   | 255338/371472 [9:15:48<9:01:17,  3.58it/s]
 69%|██████▊   | 255339/371472 [9:15:48<8:49:08,  3.66it/s]
 69%|██████▊   | 255340/371472 [9:15:48<8:30:35,  3.79it/s]
                                                           
{'loss': 2.8868, 'learning_rate': 3.8151543881574695e-07, 'epoch': 11.0}
+
 69%|██████▊   | 255340/371472 [9:15:48<8:30:35,  3.79it/s]
 69%|██████▊   | 255341/371472 [9:15:49<8:52:56,  3.63it/s]
 69%|██████▊   | 255342/371472 [9:15:49<8:43:59,  3.69it/s]
 69%|██████▊   | 255343/371472 [9:15:49<8:57:41,  3.60it/s]
 69%|██████▊   | 255344/371472 [9:15:49<8:45:08,  3.69it/s]
 69%|██████▊   | 255345/371472 [9:15:50<8:54:15,  3.62it/s]
 69%|██████▊   | 255346/371472 [9:15:50<8:54:48,  3.62it/s]
 69%|██████▊   | 255347/371472 [9:15:50<8:35:51,  3.75it/s]
 69%|██████▊   | 255348/371472 [9:15:51<9:37:05,  3.35it/s]
 69%|██████▊   | 255349/371472 [9:15:51<9:38:54,  3.34it/s]
 69%|██████▊   | 255350/371472 [9:15:51<9:13:05,  3.50it/s]
 69%|██████▊   | 255351/371472 [9:15:51<8:51:23,  3.64it/s]
 69%|██████▊   | 255352/371472 [9:15:52<8:53:33,  3.63it/s]
 69%|██████▊   | 255353/371472 [9:15:52<9:34:43,  3.37it/s]
 69%|██████▊   | 255354/371472 [9:15:52<9:35:48,  3.36it/s]
 69%|██████▊   | 255355/371472 [9:15:53<9:21:57,  3.44it/s]
 69%|██████▊   | 255356/371472 [9:15:53<8:53:47,  3.63it/s]
 69%|██████▊   | 255357/371472 [9:15:53<8:59:04,  3.59it/s]
 69%|██████▊   | 255358/371472 [9:15:53<8:46:19,  3.68it/s]
 69%|██████▊   | 255359/371472 [9:15:54<8:32:56,  3.77it/s]
 69%|██████▊   | 255360/371472 [9:15:54<8:24:49,  3.83it/s]
                                                           
{'loss': 2.851, 'learning_rate': 3.81466956840268e-07, 'epoch': 11.0}
+
 69%|██████▊   | 255360/371472 [9:15:54<8:24:49,  3.83it/s]
 69%|██████▊   | 255361/371472 [9:15:54<8:16:21,  3.90it/s]
 69%|██████▊   | 255362/371472 [9:15:54<8:02:06,  4.01it/s]
 69%|██████▊   | 255363/371472 [9:15:55<8:16:02,  3.90it/s]
 69%|██████▊   | 255364/371472 [9:15:55<8:43:15,  3.70it/s]
 69%|██████▊   | 255365/371472 [9:15:55<9:05:04,  3.55it/s]
 69%|██████▊   | 255366/371472 [9:15:55<8:39:38,  3.72it/s]
 69%|██████▊   | 255367/371472 [9:15:56<8:49:31,  3.65it/s]
 69%|██████▊   | 255368/371472 [9:15:56<8:44:47,  3.69it/s]
 69%|██████▊   | 255369/371472 [9:15:56<8:45:22,  3.68it/s]
 69%|██████▊   | 255370/371472 [9:15:57<9:45:15,  3.31it/s]
 69%|██████▊   | 255371/371472 [9:15:57<9:29:51,  3.40it/s]
 69%|██████▊   | 255372/371472 [9:15:57<9:24:08,  3.43it/s]
 69%|██████▊   | 255373/371472 [9:15:57<9:08:06,  3.53it/s]
 69%|██████▊   | 255374/371472 [9:15:58<9:06:08,  3.54it/s]
 69%|██████▊   | 255375/371472 [9:15:58<9:02:31,  3.57it/s]
 69%|██████▊   | 255376/371472 [9:15:58<8:45:56,  3.68it/s]
 69%|██████▊   | 255377/371472 [9:15:59<9:21:28,  3.45it/s]
 69%|██████▊   | 255378/371472 [9:15:59<8:55:33,  3.61it/s]
 69%|██████▊   | 255379/371472 [9:15:59<8:55:05,  3.62it/s]
 69%|██████▊   | 255380/371472 [9:15:59<8:43:29,  3.70it/s]
                                                           
{'loss': 2.7944, 'learning_rate': 3.814184748647892e-07, 'epoch': 11.0}
+
 69%|██████▊   | 255380/371472 [9:15:59<8:43:29,  3.70it/s]
 69%|██████▊   | 255381/371472 [9:16:00<8:34:27,  3.76it/s]
 69%|██████▊   | 255382/371472 [9:16:00<8:49:30,  3.65it/s]
 69%|██████▊   | 255383/371472 [9:16:00<8:48:46,  3.66it/s]
 69%|██████▊   | 255384/371472 [9:16:00<8:47:56,  3.66it/s]
 69%|██████▊   | 255385/371472 [9:16:01<8:53:14,  3.63it/s]
 69%|██████▊   | 255386/371472 [9:16:01<8:49:56,  3.65it/s]
 69%|██████▉   | 255387/371472 [9:16:01<9:33:31,  3.37it/s]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}
+/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
+  self.pid = os.fork()
+
 69%|██████▉   | 255388/371472 [9:16:24<227:20:36,  7.05s/it]
 69%|██████▉   | 255389/371472 [9:16:25<161:58:44,  5.02s/it]
 69%|██████▉   | 255390/371472 [9:16:25<115:54:12,  3.59s/it]
 69%|██████▉   | 255391/371472 [9:16:25<83:33:59,  2.59s/it] 
 69%|██████▉   | 255392/371472 [9:16:25<61:02:04,  1.89s/it]
 69%|██████▉   | 255393/371472 [9:16:26<45:59:15,  1.43s/it]
 69%|██████▉   | 255394/371472 [9:16:26<35:01:23,  1.09s/it]
 69%|██████▉   | 255395/371472 [9:16:26<28:23:12,  1.14it/s]
 69%|██████▉   | 255396/371472 [9:16:27<22:32:02,  1.43it/s]
 69%|██████▉   | 255397/371472 [9:16:27<19:48:08,  1.63it/s]
 69%|██████▉   | 255398/371472 [9:16:27<16:44:05,  1.93it/s]
 69%|██████▉   | 255399/371472 [9:16:28<14:05:03,  2.29it/s]
 69%|██████▉   | 255400/371472 [9:16:28<12:45:40,  2.53it/s]
                                                            
{'loss': 2.8535, 'learning_rate': 3.813699928893102e-07, 'epoch': 11.0}
+
 69%|██████▉   | 255400/371472 [9:16:28<12:45:40,  2.53it/s]
 69%|██████▉   | 255401/371472 [9:16:28<12:30:05,  2.58it/s]
 69%|██████▉   | 255402/371472 [9:16:28<11:14:42,  2.87it/s]
 69%|██████▉   | 255403/371472 [9:16:29<10:34:17,  3.05it/s]
 69%|██████▉   | 255404/371472 [9:16:29<9:59:56,  3.22it/s] 
 69%|██████▉   | 255405/371472 [9:16:29<9:35:32,  3.36it/s]
 69%|██████▉   | 255406/371472 [9:16:30<9:21:10,  3.45it/s]
 69%|██████▉   | 255407/371472 [9:16:30<9:27:02,  3.41it/s]
 69%|██████▉   | 255408/371472 [9:16:30<9:09:41,  3.52it/s]
 69%|██████▉   | 255409/371472 [9:16:30<9:33:37,  3.37it/s]
 69%|██████▉   | 255410/371472 [9:16:31<9:54:30,  3.25it/s]
 69%|██████▉   | 255411/371472 [9:16:31<9:28:24,  3.40it/s]
 69%|██████▉   | 255412/371472 [9:16:31<9:13:34,  3.49it/s]
 69%|██████▉   | 255413/371472 [9:16:32<9:06:09,  3.54it/s]
 69%|██████▉   | 255414/371472 [9:16:32<8:49:10,  3.66it/s]
 69%|██████▉   | 255415/371472 [9:16:32<8:32:51,  3.77it/s]
 69%|██████▉   | 255416/371472 [9:16:32<8:45:32,  3.68it/s]
 69%|██████▉   | 255417/371472 [9:16:33<8:51:01,  3.64it/s]
 69%|██████▉   | 255418/371472 [9:16:33<9:14:14,  3.49it/s]
 69%|██████▉   | 255419/371472 [9:16:33<9:22:07,  3.44it/s]
 69%|██████▉   | 255420/371472 [9:16:34<9:13:37,  3.49it/s]
                                                           
{'loss': 2.7894, 'learning_rate': 3.813215109138314e-07, 'epoch': 11.0}
+
 69%|██████▉   | 255420/371472 [9:16:34<9:13:37,  3.49it/s]
 69%|██████▉   | 255421/371472 [9:16:34<9:02:36,  3.56it/s]
 69%|██████▉   | 255422/371472 [9:16:34<9:19:27,  3.46it/s]
 69%|██████▉   | 255423/371472 [9:16:34<8:46:47,  3.67it/s]
 69%|██████▉   | 255424/371472 [9:16:35<8:43:21,  3.70it/s]
 69%|██████▉   | 255425/371472 [9:16:35<8:35:55,  3.75it/s]
 69%|██████▉   | 255426/371472 [9:16:35<8:57:57,  3.60it/s]
 69%|██████▉   | 255427/371472 [9:16:35<8:51:06,  3.64it/s]
 69%|██████▉   | 255428/371472 [9:16:36<8:42:54,  3.70it/s]
 69%|██████▉   | 255429/371472 [9:16:36<9:14:14,  3.49it/s]
 69%|██████▉   | 255430/371472 [9:16:36<8:52:27,  3.63it/s]
 69%|██████▉   | 255431/371472 [9:16:37<8:57:31,  3.60it/s]
 69%|██████▉   | 255432/371472 [9:16:37<9:46:43,  3.30it/s]
 69%|██████▉   | 255433/371472 [9:16:37<9:41:16,  3.33it/s]
 69%|██████▉   | 255434/371472 [9:16:37<9:24:16,  3.43it/s]
 69%|██████▉   | 255435/371472 [9:16:38<10:20:25,  3.12it/s]
 69%|██████▉   | 255436/371472 [9:16:38<9:39:32,  3.34it/s] 
 69%|██████▉   | 255437/371472 [9:16:38<9:19:47,  3.45it/s]
 69%|██████▉   | 255438/371472 [9:16:39<9:49:58,  3.28it/s]
 69%|██████▉   | 255439/371472 [9:16:39<9:12:03,  3.50it/s]
 69%|██████▉   | 255440/371472 [9:16:39<9:16:15,  3.48it/s]
                                                           
{'loss': 2.7491, 'learning_rate': 3.8127302893835247e-07, 'epoch': 11.0}
+
 69%|██████▉   | 255440/371472 [9:16:39<9:16:15,  3.48it/s]
 69%|██████▉   | 255441/371472 [9:16:40<9:01:34,  3.57it/s]
 69%|██████▉   | 255442/371472 [9:16:40<8:53:51,  3.62it/s]
 69%|██████▉   | 255443/371472 [9:16:40<9:13:51,  3.49it/s]
 69%|██████▉   | 255444/371472 [9:16:40<9:14:13,  3.49it/s]
 69%|██████▉   | 255445/371472 [9:16:41<9:16:40,  3.47it/s]
 69%|██████▉   | 255446/371472 [9:16:41<9:18:24,  3.46it/s]
 69%|██████▉   | 255447/371472 [9:16:41<9:43:24,  3.31it/s]
 69%|██████▉   | 255448/371472 [9:16:42<10:06:25,  3.19it/s]
 69%|██████▉   | 255449/371472 [9:16:42<9:51:15,  3.27it/s] 
 69%|██████▉   | 255450/371472 [9:16:42<9:45:50,  3.30it/s]
 69%|██████▉   | 255451/371472 [9:16:43<9:46:30,  3.30it/s]
 69%|██████▉   | 255452/371472 [9:16:43<9:44:38,  3.31it/s]
 69%|██████▉   | 255453/371472 [9:16:43<9:26:51,  3.41it/s]
 69%|██████▉   | 255454/371472 [9:16:43<9:19:19,  3.46it/s]
 69%|██████▉   | 255455/371472 [9:16:44<9:00:09,  3.58it/s]
 69%|██████▉   | 255456/371472 [9:16:44<8:49:54,  3.65it/s]
 69%|██████▉   | 255457/371472 [9:16:44<8:33:58,  3.76it/s]
 69%|██████▉   | 255458/371472 [9:16:44<8:29:31,  3.79it/s]
 69%|██████▉   | 255459/371472 [9:16:45<9:01:40,  3.57it/s]
 69%|██████▉   | 255460/371472 [9:16:45<8:52:13,  3.63it/s]
                                                           
{'loss': 2.7817, 'learning_rate': 3.812245469628736e-07, 'epoch': 11.0}
+
 69%|██████▉   | 255460/371472 [9:16:45<8:52:13,  3.63it/s]
 69%|██████▉   | 255461/371472 [9:16:45<8:49:33,  3.65it/s]
 69%|██████▉   | 255462/371472 [9:16:46<8:38:50,  3.73it/s]
 69%|██████▉   | 255463/371472 [9:16:46<8:56:25,  3.60it/s]
 69%|██████▉   | 255464/371472 [9:16:46<8:52:32,  3.63it/s]
 69%|██████▉   | 255465/371472 [9:16:46<9:05:26,  3.54it/s]
 69%|██████▉   | 255466/371472 [9:16:47<8:40:25,  3.72it/s]
 69%|██████▉   | 255467/371472 [9:16:47<8:32:14,  3.77it/s]
 69%|██████▉   | 255468/371472 [9:16:47<8:56:14,  3.61it/s]
 69%|██████▉   | 255469/371472 [9:16:48<9:47:16,  3.29it/s]
 69%|██████▉   | 255470/371472 [9:16:48<9:25:36,  3.42it/s]
 69%|██████▉   | 255471/371472 [9:16:48<9:02:53,  3.56it/s]
 69%|██████▉   | 255472/371472 [9:16:48<8:58:56,  3.59it/s]
 69%|██████▉   | 255473/371472 [9:16:49<9:54:38,  3.25it/s]
 69%|██████▉   | 255474/371472 [9:16:49<10:12:38,  3.16it/s]
 69%|██████▉   | 255475/371472 [9:16:49<10:15:11,  3.14it/s]
 69%|██████▉   | 255476/371472 [9:16:50<10:23:01,  3.10it/s]
 69%|██████▉   | 255477/371472 [9:16:50<9:53:33,  3.26it/s] 
 69%|██████▉   | 255478/371472 [9:16:50<11:19:55,  2.84it/s]
 69%|██████▉   | 255479/371472 [9:16:51<11:07:47,  2.89it/s]
 69%|██████▉   | 255480/371472 [9:16:51<11:20:17,  2.84it/s]
                                                            
{'loss': 2.6906, 'learning_rate': 3.8117606498739466e-07, 'epoch': 11.0}
+
 69%|██████▉   | 255480/371472 [9:16:51<11:20:17,  2.84it/s]
 69%|██████▉   | 255481/371472 [9:16:51<10:51:21,  2.97it/s]
 69%|██████▉   | 255482/371472 [9:16:52<10:48:01,  2.98it/s]
 69%|██████▉   | 255483/371472 [9:16:52<10:05:06,  3.19it/s]
 69%|██████▉   | 255484/371472 [9:16:52<9:42:52,  3.32it/s] 
 69%|██████▉   | 255485/371472 [9:16:53<9:17:00,  3.47it/s]
 69%|██████▉   | 255486/371472 [9:16:53<9:23:26,  3.43it/s]
 69%|██████▉   | 255487/371472 [9:16:53<9:41:35,  3.32it/s]
 69%|██████▉   | 255488/371472 [9:16:54<10:11:36,  3.16it/s]
 69%|██████▉   | 255489/371472 [9:16:54<10:17:37,  3.13it/s]
 69%|██████▉   | 255490/371472 [9:16:54<10:32:43,  3.06it/s]
 69%|██████▉   | 255491/371472 [9:16:54<10:05:36,  3.19it/s]
 69%|██████▉   | 255492/371472 [9:16:55<11:26:53,  2.81it/s]
 69%|██████▉   | 255493/371472 [9:16:55<11:32:32,  2.79it/s]
 69%|██████▉   | 255494/371472 [9:16:56<10:44:41,  3.00it/s]
 69%|██████▉   | 255495/371472 [9:16:56<10:41:54,  3.01it/s]
 69%|██████▉   | 255496/371472 [9:16:56<10:22:01,  3.11it/s]
 69%|██████▉   | 255497/371472 [9:16:56<9:55:37,  3.25it/s] 
 69%|██████▉   | 255498/371472 [9:16:57<10:14:31,  3.15it/s]
 69%|██████▉   | 255499/371472 [9:16:57<10:09:54,  3.17it/s]
 69%|██████▉   | 255500/371472 [9:16:57<10:13:47,  3.15it/s]
                                                            
{'loss': 2.8882, 'learning_rate': 3.8112758301191584e-07, 'epoch': 11.0}
+
 69%|██████▉   | 255500/371472 [9:16:57<10:13:47,  3.15it/s]
 69%|██████▉   | 255501/371472 [9:16:58<10:19:52,  3.12it/s]
 69%|██████▉   | 255502/371472 [9:16:58<9:58:24,  3.23it/s] 
 69%|██████▉   | 255503/371472 [9:16:58<9:47:34,  3.29it/s]
 69%|██████▉   | 255504/371472 [9:16:59<10:02:05,  3.21it/s]
 69%|██████▉   | 255505/371472 [9:16:59<10:09:08,  3.17it/s]
 69%|██████▉   | 255506/371472 [9:16:59<9:47:32,  3.29it/s] 
 69%|██████▉   | 255507/371472 [9:17:00<9:28:12,  3.40it/s]
 69%|██████▉   | 255508/371472 [9:17:00<9:19:17,  3.46it/s]
 69%|██████▉   | 255509/371472 [9:17:00<9:14:54,  3.48it/s]
 69%|██████▉   | 255510/371472 [9:17:00<9:05:55,  3.54it/s]
 69%|██████▉   | 255511/371472 [9:17:01<8:51:57,  3.63it/s]
 69%|██████▉   | 255512/371472 [9:17:01<8:41:47,  3.70it/s]
 69%|██████▉   | 255513/371472 [9:17:01<9:15:05,  3.48it/s]
 69%|██████▉   | 255514/371472 [9:17:02<9:02:17,  3.56it/s]
 69%|██████▉   | 255515/371472 [9:17:02<8:49:07,  3.65it/s]
 69%|██████▉   | 255516/371472 [9:17:02<8:52:21,  3.63it/s]
 69%|██████▉   | 255517/371472 [9:17:02<9:05:04,  3.55it/s]
 69%|██████▉   | 255518/371472 [9:17:03<8:42:41,  3.70it/s]
 69%|██████▉   | 255519/371472 [9:17:03<8:34:02,  3.76it/s]
 69%|██████▉   | 255520/371472 [9:17:03<9:41:37,  3.32it/s]
                                                           
{'loss': 2.6933, 'learning_rate': 3.8107910103643686e-07, 'epoch': 11.01}
+
 69%|██████▉   | 255520/371472 [9:17:03<9:41:37,  3.32it/s]
 69%|██████▉   | 255521/371472 [9:17:03<9:21:02,  3.44it/s]
 69%|██████▉   | 255522/371472 [9:17:04<9:03:44,  3.55it/s]
 69%|██████▉   | 255523/371472 [9:17:04<8:48:44,  3.65it/s]
 69%|██████▉   | 255524/371472 [9:17:04<8:56:03,  3.60it/s]
 69%|██████▉   | 255525/371472 [9:17:05<8:51:56,  3.63it/s]
 69%|██████▉   | 255526/371472 [9:17:05<8:59:32,  3.58it/s]
 69%|██████▉   | 255527/371472 [9:17:05<8:50:13,  3.64it/s]
 69%|██████▉   | 255528/371472 [9:17:05<8:48:52,  3.65it/s]
 69%|██████▉   | 255529/371472 [9:17:06<9:11:33,  3.50it/s]
 69%|██████▉   | 255530/371472 [9:17:06<9:17:56,  3.46it/s]
 69%|██████▉   | 255531/371472 [9:17:06<9:23:08,  3.43it/s]
 69%|██████▉   | 255532/371472 [9:17:07<9:11:09,  3.51it/s]
 69%|██████▉   | 255533/371472 [9:17:07<9:40:57,  3.33it/s]
 69%|██████▉   | 255534/371472 [9:17:07<10:09:07,  3.17it/s]
 69%|██████▉   | 255535/371472 [9:17:08<10:20:53,  3.11it/s]
 69%|██████▉   | 255536/371472 [9:17:08<9:51:19,  3.27it/s] 
 69%|██████▉   | 255537/371472 [9:17:08<9:28:55,  3.40it/s]
 69%|██████▉   | 255538/371472 [9:17:08<9:35:18,  3.36it/s]
 69%|██████▉   | 255539/371472 [9:17:09<9:15:02,  3.48it/s]
 69%|██████▉   | 255540/371472 [9:17:09<8:55:16,  3.61it/s]
                                                           
{'loss': 2.6741, 'learning_rate': 3.8103061906095804e-07, 'epoch': 11.01}
+
 69%|██████▉   | 255540/371472 [9:17:09<8:55:16,  3.61it/s]
 69%|██████▉   | 255541/371472 [9:17:09<9:08:23,  3.52it/s]
 69%|██████▉   | 255542/371472 [9:17:10<9:01:10,  3.57it/s]
 69%|██████▉   | 255543/371472 [9:17:10<9:16:00,  3.48it/s]
 69%|██████▉   | 255544/371472 [9:17:10<9:01:37,  3.57it/s]
 69%|██████▉   | 255545/371472 [9:17:10<9:17:25,  3.47it/s]
 69%|██████▉   | 255546/371472 [9:17:11<9:29:54,  3.39it/s]
 69%|██████▉   | 255547/371472 [9:17:11<9:25:08,  3.42it/s]
 69%|██████▉   | 255548/371472 [9:17:11<9:50:54,  3.27it/s]
 69%|██████▉   | 255549/371472 [9:17:12<10:03:58,  3.20it/s]
 69%|██████▉   | 255550/371472 [9:17:12<9:22:15,  3.44it/s] 
 69%|██████▉   | 255551/371472 [9:17:12<9:52:07,  3.26it/s]
 69%|██████▉   | 255552/371472 [9:17:13<9:52:56,  3.26it/s]
 69%|██████▉   | 255553/371472 [9:17:13<9:25:38,  3.42it/s]
 69%|██████▉   | 255554/371472 [9:17:13<9:03:29,  3.55it/s]
 69%|██████▉   | 255555/371472 [9:17:13<8:41:51,  3.70it/s]
 69%|██████▉   | 255556/371472 [9:17:14<8:37:31,  3.73it/s]
 69%|██████▉   | 255557/371472 [9:17:14<8:28:52,  3.80it/s]
 69%|██████▉   | 255558/371472 [9:17:14<8:46:31,  3.67it/s]
 69%|██████▉   | 255559/371472 [9:17:14<8:47:30,  3.66it/s]
 69%|██████▉   | 255560/371472 [9:17:15<9:00:27,  3.57it/s]
                                                           
{'loss': 2.7526, 'learning_rate': 3.809821370854791e-07, 'epoch': 11.01}
+
 69%|██████▉   | 255560/371472 [9:17:15<9:00:27,  3.57it/s]
 69%|██████▉   | 255561/371472 [9:17:15<8:58:27,  3.59it/s]
 69%|██████▉   | 255562/371472 [9:17:15<9:14:24,  3.48it/s]
 69%|██████▉   | 255563/371472 [9:17:16<10:18:34,  3.12it/s]
 69%|██████▉   | 255564/371472 [9:17:16<9:54:19,  3.25it/s] 
 69%|██████▉   | 255565/371472 [9:17:16<9:37:02,  3.35it/s]
 69%|██████▉   | 255566/371472 [9:17:17<9:28:03,  3.40it/s]
 69%|██████▉   | 255567/371472 [9:17:17<9:01:33,  3.57it/s]
 69%|██████▉   | 255568/371472 [9:17:17<8:53:15,  3.62it/s]
 69%|██████▉   | 255569/371472 [9:17:17<8:37:52,  3.73it/s]
 69%|██████▉   | 255570/371472 [9:17:18<8:49:28,  3.65it/s]
 69%|██████▉   | 255571/371472 [9:17:18<8:45:33,  3.68it/s]
 69%|██████▉   | 255572/371472 [9:17:18<8:56:25,  3.60it/s]
 69%|██████▉   | 255573/371472 [9:17:18<9:35:42,  3.36it/s]
 69%|██████▉   | 255574/371472 [9:17:19<9:20:13,  3.45it/s]
 69%|██████▉   | 255575/371472 [9:17:19<9:13:26,  3.49it/s]
 69%|██████▉   | 255576/371472 [9:17:19<9:02:58,  3.56it/s]
 69%|██████▉   | 255577/371472 [9:17:20<8:57:28,  3.59it/s]
 69%|██████▉   | 255578/371472 [9:17:20<9:32:49,  3.37it/s]
 69%|██████▉   | 255579/371472 [9:17:20<9:14:25,  3.48it/s]
 69%|██████▉   | 255580/371472 [9:17:20<9:32:09,  3.38it/s]
                                                           
{'loss': 2.8929, 'learning_rate': 3.809336551100001e-07, 'epoch': 11.01}
+
 69%|██████▉   | 255580/371472 [9:17:20<9:32:09,  3.38it/s]
 69%|██████▉   | 255581/371472 [9:17:21<9:39:11,  3.33it/s]
 69%|██████▉   | 255582/371472 [9:17:21<9:53:11,  3.26it/s]
 69%|██████▉   | 255583/371472 [9:17:21<9:26:46,  3.41it/s]
 69%|██████▉   | 255584/371472 [9:17:22<9:19:36,  3.45it/s]
 69%|██████▉   | 255585/371472 [9:17:22<9:14:10,  3.49it/s]
 69%|██████▉   | 255586/371472 [9:17:22<8:51:24,  3.63it/s]
 69%|██████▉   | 255587/371472 [9:17:22<8:43:02,  3.69it/s]
 69%|██████▉   | 255588/371472 [9:17:23<8:38:06,  3.73it/s]
 69%|██████▉   | 255589/371472 [9:17:23<8:30:42,  3.78it/s]
 69%|██████▉   | 255590/371472 [9:17:23<8:24:28,  3.83it/s]
 69%|██████▉   | 255591/371472 [9:17:24<8:53:24,  3.62it/s]
 69%|██████▉   | 255592/371472 [9:17:24<8:53:37,  3.62it/s]
 69%|██████▉   | 255593/371472 [9:17:24<8:55:53,  3.60it/s]
 69%|██████▉   | 255594/371472 [9:17:24<8:57:52,  3.59it/s]
 69%|██████▉   | 255595/371472 [9:17:25<8:58:49,  3.58it/s]
 69%|██████▉   | 255596/371472 [9:17:25<8:56:01,  3.60it/s]
 69%|██████▉   | 255597/371472 [9:17:25<9:06:46,  3.53it/s]
 69%|██████▉   | 255598/371472 [9:17:26<9:16:26,  3.47it/s]
 69%|██████▉   | 255599/371472 [9:17:26<9:21:32,  3.44it/s]
 69%|██████▉   | 255600/371472 [9:17:26<9:45:36,  3.30it/s]
                                                           
{'loss': 2.852, 'learning_rate': 3.808851731345213e-07, 'epoch': 11.01}
+
 69%|██████▉   | 255600/371472 [9:17:26<9:45:36,  3.30it/s]
 69%|██████▉   | 255601/371472 [9:17:26<9:48:58,  3.28it/s]
 69%|██████▉   | 255602/371472 [9:17:27<10:53:54,  2.95it/s]
 69%|██████▉   | 255603/371472 [9:17:27<9:57:01,  3.23it/s] 
 69%|██████▉   | 255604/371472 [9:17:27<9:18:17,  3.46it/s]
 69%|██████▉   | 255605/371472 [9:17:28<9:14:59,  3.48it/s]
 69%|██████▉   | 255606/371472 [9:17:28<9:21:00,  3.44it/s]
 69%|██████▉   | 255607/371472 [9:17:28<8:58:07,  3.59it/s]
 69%|██████▉   | 255608/371472 [9:17:28<8:45:38,  3.67it/s]
 69%|██████▉   | 255609/371472 [9:17:29<8:58:50,  3.58it/s]
 69%|██████▉   | 255610/371472 [9:17:29<8:57:09,  3.59it/s]
 69%|██████▉   | 255611/371472 [9:17:29<8:47:30,  3.66it/s]
 69%|██████▉   | 255612/371472 [9:17:30<9:06:26,  3.53it/s]
\ No newline at end of file