diff --git "a/run-2024-07-15T17:00:53+00:00.log" "b/run-2024-07-15T17:00:53+00:00.log"
--- "a/run-2024-07-15T17:00:53+00:00.log"
+++ "b/run-2024-07-15T17:00:53+00:00.log"
@@ -3538,4 +3538,1170 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, '
 
 56%|█████▋    | 209000/371472 [5:54:43<14:02:30,  3.21it/s]
 56%|█████▋    | 209001/371472 [5:54:44<14:31:06,  3.11it/s]
 56%|█████▋    | 209002/371472 [5:54:44<15:13:00,  2.97it/s]
 56%|█████▋    | 209003/371472 [5:54:44<14:32:47,  3.10it/s]
 56%|█████▋    | 209004/371472 [5:54:45<14:07:07,  3.20it/s]
 56%|█████▋    | 209005/371472 [5:54:45<14:01:32,  3.22it/s]
 56%|█████▋    | 209006/371472 [5:54:45<13:51:03,  3.26it/s]
 56%|█████▋    | 209007/371472 [5:54:45<13:38:58,  3.31it/s]
 56%|█████▋    | 209008/371472 [5:54:46<13:37:13,  3.31it/s]
 56%|█████▋    | 209009/371472 [5:54:46<13:17:41,  3.39it/s]
 56%|█████▋    | 209010/371472 [5:54:46<13:15:18,  3.40it/s]
 56%|█████▋    | 209011/371472 [5:54:47<13:12:58,  3.41it/s]
 56%|█████▋    | 209012/371472 [5:54:47<13:51:48,  3.26it/s]
 56%|█████▋    | 209013/371472 [5:54:47<14:21:47,  3.14it/s]
 56%|█████▋    | 209014/371472 [5:54:48<14:55:14,  3.02it/s]
 56%|█████▋    | 209015/371472 [5:54:48<14:58:22,  3.01it/s]
 56%|█████▋    | 209016/371472 [5:54:48<15:31:17,  2.91it/s]
 56%|█████▋    | 209017/371472 [5:54:49<14:59:14,  3.01it/s]
 56%|█████▋    | 209018/371472 [5:54:49<14:02:46,  3.21it/s]
 56%|█████▋    | 209019/371472 [5:54:49<13:38:54,  3.31it/s]
 56%|█████▋    | 209020/371472 [5:54:50<13:34:22,  3.32it/s]
                                                            
{'loss': 2.8549, 'learning_rate': 4.937996940248659e-07, 'epoch': 9.0}
 
 56%|█████▋    | 209020/371472 [5:54:50<13:34:22,  3.32it/s]
 56%|█████▋    | 209021/371472 [5:54:50<14:20:10,  3.15it/s]
 56%|█████▋    | 209022/371472 [5:54:50<14:12:01,  3.18it/s]
 56%|█████▋    | 209023/371472 [5:54:50<13:40:43,  3.30it/s]
 56%|█████▋    | 209024/371472 [5:54:51<13:28:58,  3.35it/s]
 56%|█████▋    | 209025/371472 [5:54:51<13:17:49,  3.39it/s]
 56%|█████▋    | 209026/371472 [5:54:51<13:29:48,  3.34it/s]
 56%|█████▋    | 209027/371472 [5:54:52<14:29:44,  3.11it/s]
 56%|█████▋    | 209028/371472 [5:54:52<14:12:35,  3.18it/s]
 56%|█████▋    | 209029/371472 [5:54:52<13:34:20,  3.32it/s]
 56%|█████▋    | 209030/371472 [5:54:53<13:48:03,  3.27it/s]
 56%|█████▋    | 209031/371472 [5:54:53<13:37:02,  3.31it/s]
 56%|█████▋    | 209032/371472 [5:54:53<13:52:18,  3.25it/s]
 56%|█████▋    | 209033/371472 [5:54:54<14:08:58,  3.19it/s]
 56%|█████▋    | 209034/371472 [5:54:54<14:11:24,  3.18it/s]
 56%|█████▋    | 209035/371472 [5:54:54<14:17:04,  3.16it/s]
 56%|█████▋    | 209036/371472 [5:54:55<15:05:00,  2.99it/s]
 56%|█████▋    | 209037/371472 [5:54:55<15:05:16,  2.99it/s]
 56%|█████▋    | 209038/371472 [5:54:55<15:39:14,  2.88it/s]
 56%|█████▋    | 209039/371472 [5:54:56<14:56:46,  3.02it/s]
 56%|█████▋    | 209040/371472 [5:54:56<14:41:00,  3.07it/s]
                                                            
{'loss': 2.8284, 'learning_rate': 4.93751212049387e-07, 'epoch': 9.0}
 
 56%|█████▋    | 209040/371472 [5:54:56<14:41:00,  3.07it/s]
 56%|█████▋    | 209041/371472 [5:54:56<14:40:30,  3.07it/s]
 56%|█████▋    | 209042/371472 [5:54:57<14:45:19,  3.06it/s]
 56%|█████▋    | 209043/371472 [5:54:57<14:35:33,  3.09it/s]
 56%|█████▋    | 209044/371472 [5:54:57<14:12:26,  3.18it/s]
 56%|█████▋    | 209045/371472 [5:54:58<15:13:08,  2.96it/s]
 56%|█████▋    | 209046/371472 [5:54:58<15:04:54,  2.99it/s]
 56%|█████▋    | 209047/371472 [5:54:58<14:30:27,  3.11it/s]
 56%|█████▋    | 209048/371472 [5:54:59<14:44:58,  3.06it/s]
 56%|█████▋    | 209049/371472 [5:54:59<14:18:44,  3.15it/s]
 56%|█████▋    | 209050/371472 [5:54:59<15:39:41,  2.88it/s]
 56%|█████▋    | 209051/371472 [5:55:00<15:06:20,  2.99it/s]
 56%|█████▋    | 209052/371472 [5:55:00<14:38:30,  3.08it/s]
 56%|█████▋    | 209053/371472 [5:55:00<14:48:35,  3.05it/s]
 56%|█████▋    | 209054/371472 [5:55:01<14:48:28,  3.05it/s]
 56%|█████▋    | 209055/371472 [5:55:01<14:22:14,  3.14it/s]
 56%|█████▋    | 209056/371472 [5:55:01<14:44:26,  3.06it/s]
 56%|█████▋    | 209057/371472 [5:55:02<15:57:05,  2.83it/s]
 56%|█████▋    | 209058/371472 [5:55:02<14:50:37,  3.04it/s]
 56%|█████▋    | 209059/371472 [5:55:02<14:12:37,  3.17it/s]
 56%|█████▋    | 209060/371472 [5:55:02<13:56:00,  3.24it/s]
                                                            
{'loss': 2.7087, 'learning_rate': 4.937027300739081e-07, 'epoch': 9.0}
-
 56%|██���██▋    | 209060/371472 [5:55:02<13:56:00,  3.24it/s]
 56%|█████▋    | 209061/371472 [5:55:03<13:31:03,  3.34it/s]
 56%|█████▋    | 209062/371472 [5:55:03<13:34:26,  3.32it/s]
 56%|█████▋    | 209063/371472 [5:55:03<13:37:26,  3.31it/s]
 56%|█████▋    | 209064/371472 [5:55:04<13:34:36,  3.32it/s]
 56%|█████▋    | 209065/371472 [5:55:04<13:14:35,  3.41it/s]
 56%|█████▋    | 209066/371472 [5:55:04<14:05:59,  3.20it/s]
 56%|█████▋    | 209067/371472 [5:55:05<14:29:41,  3.11it/s]
 56%|█████▋    | 209068/371472 [5:55:05<14:11:41,  3.18it/s]
 56%|█████▋    | 209069/371472 [5:55:05<14:24:04,  3.13it/s]
 56%|█████▋    | 209070/371472 [5:55:06<14:18:14,  3.15it/s]
 56%|█████▋    | 209071/371472 [5:55:06<13:56:54,  3.23it/s]
 56%|█████▋    | 209072/371472 [5:55:06<14:01:07,  3.22it/s]
 56%|█████▋    | 209073/371472 [5:55:06<13:58:48,  3.23it/s]
\ No newline at end of file
+
 56%|█████▋    | 209060/371472 [5:55:02<13:56:00,  3.24it/s]
 56%|█████▋    | 209061/371472 [5:55:03<13:31:03,  3.34it/s]
 56%|█████▋    | 209062/371472 [5:55:03<13:34:26,  3.32it/s]
 56%|█████▋    | 209063/371472 [5:55:03<13:37:26,  3.31it/s]
 56%|█████▋    | 209064/371472 [5:55:04<13:34:36,  3.32it/s]
 56%|█████▋    | 209065/371472 [5:55:04<13:14:35,  3.41it/s]
 56%|█████▋    | 209066/371472 [5:55:04<14:05:59,  3.20it/s]
 56%|█████▋    | 209067/371472 [5:55:05<14:29:41,  3.11it/s]
 56%|█████▋    | 209068/371472 [5:55:05<14:11:41,  3.18it/s]
 56%|█████▋    | 209069/371472 [5:55:05<14:24:04,  3.13it/s]
 56%|█████▋    | 209070/371472 [5:55:06<14:18:14,  3.15it/s]
 56%|█████▋    | 209071/371472 [5:55:06<13:56:54,  3.23it/s]
 56%|█████▋    | 209072/371472 [5:55:06<14:01:07,  3.22it/s]
 56%|█████▋    | 209073/371472 [5:55:06<13:58:48,  3.23it/s]
 56%|█████▋    | 209074/371472 [5:55:07<17:10:17,  2.63it/s]
 56%|█████▋    | 209075/371472 [5:55:07<15:55:38,  2.83it/s]
 56%|█████▋    | 209076/371472 [5:55:08<15:06:05,  2.99it/s]
 56%|█████▋    | 209077/371472 [5:55:08<14:30:19,  3.11it/s]
 56%|█████▋    | 209078/371472 [5:55:08<14:27:55,  3.12it/s]
 56%|█████▋    | 209079/371472 [5:55:08<13:47:27,  3.27it/s]
 56%|█████▋    | 209080/371472 [5:55:09<13:11:59,  3.42it/s]
                                                            
{'loss': 2.8894, 'learning_rate': 4.936542480984291e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209080/371472 [5:55:09<13:11:59,  3.42it/s]
 56%|█████▋    | 209081/371472 [5:55:09<13:10:49,  3.42it/s]
 56%|█████▋    | 209082/371472 [5:55:09<13:04:36,  3.45it/s]
 56%|█████▋    | 209083/371472 [5:55:10<13:11:30,  3.42it/s]
 56%|█████▋    | 209084/371472 [5:55:10<14:27:06,  3.12it/s]
 56%|█████▋    | 209085/371472 [5:55:10<14:10:07,  3.18it/s]
 56%|█████▋    | 209086/371472 [5:55:11<13:43:07,  3.29it/s]
 56%|█████▋    | 209087/371472 [5:55:11<14:00:42,  3.22it/s]
 56%|█████▋    | 209088/371472 [5:55:11<14:48:26,  3.05it/s]
 56%|█████▋    | 209089/371472 [5:55:12<14:49:13,  3.04it/s]
 56%|█████▋    | 209090/371472 [5:55:12<15:11:04,  2.97it/s]
 56%|█████▋    | 209091/371472 [5:55:12<15:28:16,  2.92it/s]
 56%|█████▋    | 209092/371472 [5:55:13<15:05:57,  2.99it/s]
 56%|█████▋    | 209093/371472 [5:55:13<14:28:58,  3.11it/s]
 56%|█████▋    | 209094/371472 [5:55:13<14:04:08,  3.21it/s]
 56%|█████▋    | 209095/371472 [5:55:13<13:58:48,  3.23it/s]
 56%|█████▋    | 209096/371472 [5:55:14<14:12:30,  3.17it/s]
 56%|█████▋    | 209097/371472 [5:55:14<14:02:10,  3.21it/s]
 56%|█████▋    | 209098/371472 [5:55:14<14:57:00,  3.02it/s]
 56%|█████▋    | 209099/371472 [5:55:15<14:46:19,  3.05it/s]
 56%|█████▋    | 209100/371472 [5:55:15<14:15:54,  3.16it/s]
                                                            
{'loss': 2.697, 'learning_rate': 4.936057661229503e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209100/371472 [5:55:15<14:15:54,  3.16it/s]
 56%|█████▋    | 209101/371472 [5:55:15<14:12:00,  3.18it/s]
 56%|█████▋    | 209102/371472 [5:55:16<13:36:17,  3.32it/s]
 56%|█████▋    | 209103/371472 [5:55:16<13:40:53,  3.30it/s]
 56%|█████▋    | 209104/371472 [5:55:16<13:31:52,  3.33it/s]
 56%|█████▋    | 209105/371472 [5:55:17<13:09:51,  3.43it/s]
 56%|█████▋    | 209106/371472 [5:55:17<13:44:02,  3.28it/s]
 56%|█████▋    | 209107/371472 [5:55:17<13:49:49,  3.26it/s]
 56%|█████▋    | 209108/371472 [5:55:18<14:01:27,  3.22it/s]
 56%|█████▋    | 209109/371472 [5:55:18<14:45:06,  3.06it/s]
 56%|███���█▋    | 209110/371472 [5:55:18<14:21:05,  3.14it/s]
 56%|█████▋    | 209111/371472 [5:55:18<13:48:19,  3.27it/s]
 56%|█████▋    | 209112/371472 [5:55:19<14:00:18,  3.22it/s]
 56%|█████▋    | 209113/371472 [5:55:19<14:11:48,  3.18it/s]
 56%|█████▋    | 209114/371472 [5:55:19<13:45:10,  3.28it/s]
 56%|█████▋    | 209115/371472 [5:55:20<13:20:52,  3.38it/s]
 56%|█████▋    | 209116/371472 [5:55:20<13:21:49,  3.37it/s]
 56%|█████▋    | 209117/371472 [5:55:20<13:15:50,  3.40it/s]
 56%|█████▋    | 209118/371472 [5:55:21<13:05:56,  3.44it/s]
 56%|█████▋    | 209119/371472 [5:55:21<13:10:12,  3.42it/s]
 56%|█████▋    | 209120/371472 [5:55:21<13:55:53,  3.24it/s]
                                                            
{'loss': 2.7267, 'learning_rate': 4.935572841474714e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209120/371472 [5:55:21<13:55:53,  3.24it/s]
 56%|█████▋    | 209121/371472 [5:55:21<13:29:11,  3.34it/s]
 56%|█████▋    | 209122/371472 [5:55:22<13:37:41,  3.31it/s]
 56%|█████▋    | 209123/371472 [5:55:22<13:43:34,  3.29it/s]
 56%|█████▋    | 209124/371472 [5:55:22<13:19:36,  3.38it/s]
 56%|█████▋    | 209125/371472 [5:55:23<13:27:12,  3.35it/s]
 56%|█████▋    | 209126/371472 [5:55:23<13:21:05,  3.38it/s]
 56%|█████▋    | 209127/371472 [5:55:23<14:19:01,  3.15it/s]
 56%|█████▋    | 209128/371472 [5:55:24<14:09:08,  3.19it/s]
 56%|█████▋    | 209129/371472 [5:55:24<13:52:50,  3.25it/s]
 56%|█████▋    | 209130/371472 [5:55:24<13:45:57,  3.28it/s]
 56%|█████▋    | 209131/371472 [5:55:24<13:40:59,  3.30it/s]
 56%|█████▋    | 209132/371472 [5:55:25<13:20:09,  3.38it/s]
 56%|█████▋    | 209133/371472 [5:55:25<13:54:29,  3.24it/s]
 56%|█████▋    | 209134/371472 [5:55:25<13:47:45,  3.27it/s]
 56%|█████▋    | 209135/371472 [5:55:26<14:12:45,  3.17it/s]
 56%|█████▋    | 209136/371472 [5:55:26<14:24:28,  3.13it/s]
 56%|█████▋    | 209137/371472 [5:55:26<13:54:52,  3.24it/s]
 56%|█████▋    | 209138/371472 [5:55:27<13:25:04,  3.36it/s]
 56%|█████▋    | 209139/371472 [5:55:27<14:03:12,  3.21it/s]
 56%|█████▋    | 209140/371472 [5:55:27<13:59:52,  3.22it/s]
                                                            
{'loss': 2.8956, 'learning_rate': 4.935088021719926e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209140/371472 [5:55:27<13:59:52,  3.22it/s]
 56%|█████▋    | 209141/371472 [5:55:28<14:17:08,  3.16it/s]
 56%|█████▋    | 209142/371472 [5:55:28<13:53:49,  3.24it/s]
 56%|█████▋    | 209143/371472 [5:55:28<14:34:25,  3.09it/s]
 56%|█████▋    | 209144/371472 [5:55:29<14:37:06,  3.08it/s]
 56%|█████▋    | 209145/371472 [5:55:29<14:05:12,  3.20it/s]
 56%|█████▋    | 209146/371472 [5:55:29<14:18:57,  3.15it/s]
 56%|█████▋    | 209147/371472 [5:55:30<14:34:58,  3.09it/s]
 56%|█████▋    | 209148/371472 [5:55:30<14:31:35,  3.10it/s]
 56%|█████▋    | 209149/371472 [5:55:30<14:26:22,  3.12it/s]
 56%|█████▋    | 209150/371472 [5:55:30<14:14:41,  3.17it/s]
 56%|█████▋    | 209151/371472 [5:55:31<13:31:27,  3.33it/s]
 56%|█████▋    | 209152/371472 [5:55:31<14:02:26,  3.21it/s]
 56%|█████▋    | 209153/371472 [5:55:31<13:58:32,  3.23it/s]
 56%|█████▋    | 209154/371472 [5:55:32<13:58:05,  3.23it/s]
 56%|█████▋    | 209155/371472 [5:55:32<14:15:39,  3.16it/s]
 56%|█████▋    | 209156/371472 [5:55:32<13:57:28,  3.23it/s]
 56%|█████▋    | 209157/371472 [5:55:33<14:22:00,  3.14it/s]
 56%|█████▋    | 209158/371472 [5:55:33<14:44:25,  3.06it/s]
 56%|█████▋    | 209159/371472 [5:55:33<14:20:57,  3.14it/s]
 56%|█████▋    | 209160/371472 [5:55:34<14:28:24,  3.12it/s]
                                                            
{'loss': 2.866, 'learning_rate': 4.934603201965136e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209160/371472 [5:55:34<14:28:24,  3.12it/s]
 56%|█████▋    | 209161/371472 [5:55:34<14:02:34,  3.21it/s]
 56%|█████▋    | 209162/371472 [5:55:34<14:59:22,  3.01it/s]
 56%|█████▋    | 209163/371472 [5:55:35<14:38:30,  3.08it/s]
 56%|█████▋    | 209164/371472 [5:55:35<14:45:30,  3.05it/s]
 56%|█████▋    | 209165/371472 [5:55:35<15:16:47,  2.95it/s]
 56%|█████▋    | 209166/371472 [5:55:36<15:27:39,  2.92it/s]
 56%|█████▋    | 209167/371472 [5:55:36<14:29:32,  3.11it/s]
 56%|█████▋    | 209168/371472 [5:55:36<14:55:56,  3.02it/s]
 56%|█████▋    | 209169/371472 [5:55:37<14:52:42,  3.03it/s]
 56%|█████▋    | 209170/371472 [5:55:37<15:08:48,  2.98it/s]
 56%|█████▋    | 209171/371472 [5:55:37<15:23:12,  2.93it/s]
 56%|█████▋    | 209172/371472 [5:55:38<16:18:42,  2.76it/s]
 56%|█████▋    | 209173/371472 [5:55:38<15:41:04,  2.87it/s]
 56%|█████▋    | 209174/371472 [5:55:38<15:37:48,  2.88it/s]
 56%|█████▋    | 209175/371472 [5:55:39<16:37:57,  2.71it/s]
 56%|█████▋    | 209176/371472 [5:55:39<16:45:29,  2.69it/s]
 56%|█████▋    | 209177/371472 [5:55:40<16:11:19,  2.78it/s]
 56%|█████▋    | 209178/371472 [5:55:40<16:35:15,  2.72it/s]
 56%|█████▋    | 209179/371472 [5:55:40<16:01:00,  2.81it/s]
 56%|█████▋    | 209180/371472 [5:55:41<16:12:08,  2.78it/s]
                                                            
{'loss': 2.8339, 'learning_rate': 4.934118382210347e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209180/371472 [5:55:41<16:12:08,  2.78it/s]
 56%|█████▋    | 209181/371472 [5:55:41<16:00:33,  2.82it/s]
 56%|█████▋    | 209182/371472 [5:55:41<16:03:07,  2.81it/s]
 56%|█████▋    | 209183/371472 [5:55:42<15:33:13,  2.90it/s]
 56%|█████▋    | 209184/371472 [5:55:42<15:29:23,  2.91it/s]
 56%|█████▋    | 209185/371472 [5:55:42<14:54:20,  3.02it/s]
 56%|█████▋    | 209186/371472 [5:55:43<14:56:39,  3.02it/s]
 56%|█████▋    | 209187/371472 [5:55:43<15:36:49,  2.89it/s]
 56%|█████▋    | 209188/371472 [5:55:43<15:33:48,  2.90it/s]
 56%|█████▋    | 209189/371472 [5:55:44<16:19:59,  2.76it/s]
 56%|█████▋    | 209190/371472 [5:55:44<17:17:59,  2.61it/s]
 56%|█████▋    | 209191/371472 [5:55:45<17:54:41,  2.52it/s]
 56%|█████▋    | 209192/371472 [5:55:45<17:10:17,  2.63it/s]
 56%|█████▋    | 209193/371472 [5:55:45<16:17:36,  2.77it/s]
 56%|█████▋    | 209194/371472 [5:55:46<15:12:22,  2.96it/s]
 56%|█████▋    | 209195/371472 [5:55:46<14:49:45,  3.04it/s]
 56%|█████▋    | 209196/371472 [5:55:46<14:25:15,  3.13it/s]
 56%|█████▋    | 209197/371472 [5:55:46<14:35:44,  3.09it/s]
 56%|█████▋    | 209198/371472 [5:55:47<14:29:18,  3.11it/s]
 56%|█████▋    | 209199/371472 [5:55:47<15:07:22,  2.98it/s]
 56%|█████▋    | 209200/371472 [5:55:48<15:39:05,  2.88it/s]
                                                            
{'loss': 2.6688, 'learning_rate': 4.933633562455558e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209200/371472 [5:55:48<15:39:05,  2.88it/s]
 56%|█████▋    | 209201/371472 [5:55:48<15:20:16,  2.94it/s]
 56%|█████▋    | 209202/371472 [5:55:48<15:30:35,  2.91it/s]
 56%|█████▋    | 209203/371472 [5:55:49<15:08:05,  2.98it/s]
 56%|█████▋    | 209204/371472 [5:55:49<15:17:47,  2.95it/s]
 56%|█████▋    | 209205/371472 [5:55:49<14:58:32,  3.01it/s]
 56%|█████▋    | 209206/371472 [5:55:49<14:40:00,  3.07it/s]
 56%|█████▋    | 209207/371472 [5:55:50<14:39:48,  3.07it/s]
 56%|█████▋    | 209208/371472 [5:55:50<14:40:24,  3.07it/s]
 56%|█████▋    | 209209/371472 [5:55:50<14:28:19,  3.11it/s]
 56%|█████▋    | 209210/371472 [5:55:51<14:49:38,  3.04it/s]
 56%|█████▋    | 209211/371472 [5:55:51<14:42:57,  3.06it/s]
 56%|█████▋    | 209212/371472 [5:55:51<14:19:30,  3.15it/s]
 56%|█████▋    | 209213/371472 [5:55:52<14:02:44,  3.21it/s]
 56%|█████▋    | 209214/371472 [5:55:52<14:56:47,  3.02it/s]
 56%|█████▋    | 209215/371472 [5:55:52<14:27:17,  3.12it/s]
 56%|█████▋    | 209216/371472 [5:55:53<15:09:17,  2.97it/s]
 56%|█████▋    | 209217/371472 [5:55:53<15:02:47,  3.00it/s]
 56%|█████▋    | 209218/371472 [5:55:53<14:59:30,  3.01it/s]
 56%|█████▋    | 209219/371472 [5:55:54<15:37:29,  2.88it/s]
 56%|█████▋    | 209220/371472 [5:55:54<16:04:38,  2.80it/s]
                                                            
{'loss': 2.8458, 'learning_rate': 4.933148742700768e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209220/371472 [5:55:54<16:04:38,  2.80it/s]
 56%|█████▋    | 209221/371472 [5:55:55<15:35:17,  2.89it/s]
 56%|█████▋    | 209222/371472 [5:55:55<15:03:06,  2.99it/s]
 56%|█████▋    | 209223/371472 [5:55:55<14:07:07,  3.19it/s]
 56%|█████▋    | 209224/371472 [5:55:55<13:42:49,  3.29it/s]
 56%|█████▋    | 209225/371472 [5:55:56<13:42:09,  3.29it/s]
 56%|█████▋    | 209226/371472 [5:55:56<13:12:31,  3.41it/s]
 56%|█████▋    | 209227/371472 [5:55:56<13:51:40,  3.25it/s]
 56%|█████▋    | 209228/371472 [5:55:57<13:26:15,  3.35it/s]
 56%|█████▋    | 209229/371472 [5:55:57<13:22:49,  3.37it/s]
 56%|█████▋    | 209230/371472 [5:55:57<13:15:53,  3.40it/s]
 56%|█████▋    | 209231/371472 [5:55:57<14:08:40,  3.19it/s]
 56%|█████▋    | 209232/371472 [5:55:58<14:39:36,  3.07it/s]
 56%|█████▋    | 209233/371472 [5:55:58<14:36:54,  3.08it/s]
 56%|█████▋    | 209234/371472 [5:55:59<14:56:40,  3.02it/s]
 56%|█████▋    | 209235/371472 [5:55:59<14:26:57,  3.12it/s]
 56%|█████▋    | 209236/371472 [5:55:59<14:20:00,  3.14it/s]
 56%|█████▋    | 209237/371472 [5:55:59<13:44:05,  3.28it/s]
 56%|█████▋    | 209238/371472 [5:56:00<13:31:06,  3.33it/s]
 56%|█████▋    | 209239/371472 [5:56:00<13:47:03,  3.27it/s]
 56%|█████▋    | 209240/371472 [5:56:00<14:13:34,  3.17it/s]
                                                            
{'loss': 2.7636, 'learning_rate': 4.93266392294598e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209240/371472 [5:56:00<14:13:34,  3.17it/s]
 56%|█████▋    | 209241/371472 [5:56:01<13:58:09,  3.23it/s]
 56%|█████▋    | 209242/371472 [5:56:01<13:45:45,  3.27it/s]
 56%|█████▋    | 209243/371472 [5:56:01<13:36:18,  3.31it/s]
 56%|█████▋    | 209244/371472 [5:56:02<14:18:22,  3.15it/s]
 56%|█████▋    | 209245/371472 [5:56:02<14:00:09,  3.22it/s]
 56%|█████▋    | 209246/371472 [5:56:02<13:52:04,  3.25it/s]
 56%|█████▋    | 209247/371472 [5:56:03<14:11:37,  3.17it/s]
 56%|█████▋    | 209248/371472 [5:56:03<14:33:37,  3.09it/s]
 56%|█████▋    | 209249/371472 [5:56:03<13:57:08,  3.23it/s]
 56%|█████▋    | 209250/371472 [5:56:03<13:30:58,  3.33it/s]
 56%|█████▋    | 209251/371472 [5:56:04<13:30:43,  3.33it/s]
 56%|█████▋    | 209252/371472 [5:56:04<13:23:25,  3.37it/s]
 56%|█████▋    | 209253/371472 [5:56:04<13:36:07,  3.31it/s]
 56%|█████▋    | 209254/371472 [5:56:05<13:56:46,  3.23it/s]
 56%|█████▋    | 209255/371472 [5:56:05<14:28:22,  3.11it/s]
 56%|█████▋    | 209256/371472 [5:56:05<14:40:02,  3.07it/s]
 56%|█████▋    | 209257/371472 [5:56:06<14:37:04,  3.08it/s]
 56%|█████▋    | 209258/371472 [5:56:06<14:29:45,  3.11it/s]
 56%|█████▋    | 209259/371472 [5:56:06<14:01:12,  3.21it/s]
 56%|█████▋    | 209260/371472 [5:56:07<14:15:59,  3.16it/s]
                                                            
{'loss': 2.7693, 'learning_rate': 4.932179103191191e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209260/371472 [5:56:07<14:15:59,  3.16it/s]
 56%|█████▋    | 209261/371472 [5:56:07<14:10:20,  3.18it/s]
 56%|█████▋    | 209262/371472 [5:56:07<13:57:07,  3.23it/s]
 56%|█████▋    | 209263/371472 [5:56:08<14:43:03,  3.06it/s]
 56%|█████▋    | 209264/371472 [5:56:08<15:07:05,  2.98it/s]
 56%|█████▋    | 209265/371472 [5:56:08<15:29:40,  2.91it/s]
 56%|█████▋    | 209266/371472 [5:56:09<15:01:28,  3.00it/s]
 56%|█████▋    | 209267/371472 [5:56:09<14:55:01,  3.02it/s]
 56%|█████▋    | 209268/371472 [5:56:09<16:19:02,  2.76it/s]
 56%|█████▋    | 209269/371472 [5:56:10<16:19:58,  2.76it/s]
 56%|█████▋    | 209270/371472 [5:56:10<15:37:44,  2.88it/s]
 56%|█████▋    | 209271/371472 [5:56:10<15:30:15,  2.91it/s]
 56%|█████▋    | 209272/371472 [5:56:11<15:00:26,  3.00it/s]
 56%|█████▋    | 209273/371472 [5:56:11<14:31:37,  3.10it/s]
 56%|█████▋    | 209274/371472 [5:56:11<14:10:20,  3.18it/s]
 56%|█████▋    | 209275/371472 [5:56:12<13:20:04,  3.38it/s]
 56%|█████▋    | 209276/371472 [5:56:12<13:08:33,  3.43it/s]
 56%|█████▋    | 209277/371472 [5:56:12<13:07:54,  3.43it/s]
 56%|█████▋    | 209278/371472 [5:56:12<13:23:33,  3.36it/s]
 56%|█████▋    | 209279/371472 [5:56:13<13:48:23,  3.26it/s]
 56%|█████▋    | 209280/371472 [5:56:13<13:27:26,  3.35it/s]
                                                            
{'loss': 2.8906, 'learning_rate': 4.931694283436403e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209280/371472 [5:56:13<13:27:26,  3.35it/s]
 56%|█████▋    | 209281/371472 [5:56:13<13:53:08,  3.24it/s]
 56%|█████▋    | 209282/371472 [5:56:14<15:26:30,  2.92it/s]
 56%|█████▋    | 209283/371472 [5:56:14<15:21:59,  2.93it/s]
 56%|█████▋    | 209284/371472 [5:56:14<15:37:25,  2.88it/s]
 56%|█████▋    | 209285/371472 [5:56:15<16:08:24,  2.79it/s]
 56%|█████▋    | 209286/371472 [5:56:15<16:04:48,  2.80it/s]
 56%|█████▋    | 209287/371472 [5:56:16<15:58:12,  2.82it/s]
 56%|█████▋    | 209288/371472 [5:56:16<15:38:19,  2.88it/s]
 56%|█████▋    | 209289/371472 [5:56:16<14:48:51,  3.04it/s]
 56%|█████▋    | 209290/371472 [5:56:16<14:37:37,  3.08it/s]
 56%|█████▋    | 209291/371472 [5:56:17<14:26:26,  3.12it/s]
 56%|█████▋    | 209292/371472 [5:56:17<14:18:36,  3.15it/s]
 56%|█████▋    | 209293/371472 [5:56:17<14:27:32,  3.12it/s]
 56%|█████▋    | 209294/371472 [5:56:18<14:03:33,  3.20it/s]
 56%|█████▋    | 209295/371472 [5:56:18<13:34:45,  3.32it/s]
 56%|█████▋    | 209296/371472 [5:56:18<13:19:54,  3.38it/s]
 56%|█████▋    | 209297/371472 [5:56:19<14:26:25,  3.12it/s]
 56%|█████▋    | 209298/371472 [5:56:19<14:36:56,  3.08it/s]
 56%|█████▋    | 209299/371472 [5:56:19<14:58:16,  3.01it/s]
 56%|█████▋    | 209300/371472 [5:56:20<15:29:52,  2.91it/s]
                                                            
{'loss': 2.83, 'learning_rate': 4.931209463681613e-07, 'epoch': 9.01}
+
 56%|█████▋    | 209300/371472 [5:56:20<15:29:52,  2.91it/s]
 56%|█████▋    | 209301/371472 [5:56:20<14:56:49,  3.01it/s]
 56%|█████▋    | 209302/371472 [5:56:20<16:41:49,  2.70it/s]
 56%|█████▋    | 209303/371472 [5:56:21<16:08:31,  2.79it/s]
 56%|█████▋    | 209304/371472 [5:56:21<15:51:32,  2.84it/s]
 56%|█████▋    | 209305/371472 [5:56:21<15:18:06,  2.94it/s]
 56%|█████▋    | 209306/371472 [5:56:22<14:56:15,  3.02it/s]
 56%|█████▋    | 209307/371472 [5:56:22<14:56:23,  3.02it/s]
 56%|█████▋    | 209308/371472 [5:56:22<14:32:45,  3.10it/s]
 56%|█████▋    | 209309/371472 [5:56:23<14:03:04,  3.21it/s]
 56%|█████▋    | 209310/371472 [5:56:23<13:57:48,  3.23it/s]
 56%|█████▋    | 209311/371472 [5:56:23<14:45:25,  3.05it/s]
 56%|█████▋    | 209312/371472 [5:56:24<15:37:09,  2.88it/s]
 56%|█████▋    | 209313/371472 [5:56:24<16:44:20,  2.69it/s]
 56%|█████▋    | 209314/371472 [5:56:24<15:39:25,  2.88it/s]
 56%|█████▋    | 209315/371472 [5:56:25<14:40:43,  3.07it/s]
 56%|█████▋    | 209316/371472 [5:56:25<14:45:06,  3.05it/s]
 56%|█████▋    | 209317/371472 [5:56:25<14:01:32,  3.21it/s]
 56%|█████▋    | 209318/371472 [5:56:26<14:14:45,  3.16it/s]
 56%|█████▋    | 209319/371472 [5:56:26<13:46:25,  3.27it/s]
 56%|█████▋    | 209320/371472 [5:56:26<13:35:09,  3.32it/s]
                                                            
{'loss': 2.8182, 'learning_rate': 4.930724643926824e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209320/371472 [5:56:26<13:35:09,  3.32it/s]
 56%|█████▋    | 209321/371472 [5:56:27<13:35:08,  3.32it/s]
 56%|█████▋    | 209322/371472 [5:56:27<13:41:46,  3.29it/s]
 56%|█████▋    | 209323/371472 [5:56:27<13:39:28,  3.30it/s]
 56%|█████▋    | 209324/371472 [5:56:27<13:48:39,  3.26it/s]
 56%|█████▋    | 209325/371472 [5:56:28<13:46:34,  3.27it/s]
 56%|█████▋    | 209326/371472 [5:56:28<13:38:29,  3.30it/s]
 56%|█████▋    | 209327/371472 [5:56:28<13:25:02,  3.36it/s]
 56%|█████▋    | 209328/371472 [5:56:29<14:07:05,  3.19it/s]
 56%|█████▋    | 209329/371472 [5:56:29<14:20:28,  3.14it/s]
 56%|█████▋    | 209330/371472 [5:56:29<14:44:51,  3.05it/s]
 56%|█████▋    | 209331/371472 [5:56:30<14:17:15,  3.15it/s]
 56%|█████▋    | 209332/371472 [5:56:30<14:02:03,  3.21it/s]
 56%|█████▋    | 209333/371472 [5:56:30<14:52:14,  3.03it/s]
 56%|█████▋    | 209334/371472 [5:56:31<14:15:37,  3.16it/s]
 56%|█████▋    | 209335/371472 [5:56:31<13:48:24,  3.26it/s]
 56%|█████▋    | 209336/371472 [5:56:31<14:00:21,  3.22it/s]
 56%|█████▋    | 209337/371472 [5:56:32<13:38:12,  3.30it/s]
 56%|█████▋    | 209338/371472 [5:56:32<13:49:42,  3.26it/s]
 56%|█████▋    | 209339/371472 [5:56:32<13:56:49,  3.23it/s]
 56%|█████▋    | 209340/371472 [5:56:32<13:41:26,  3.29it/s]
                                                            
{'loss': 2.9462, 'learning_rate': 4.930239824172035e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209340/371472 [5:56:32<13:41:26,  3.29it/s]
 56%|█████▋    | 209341/371472 [5:56:33<13:13:13,  3.41it/s]
 56%|█████▋    | 209342/371472 [5:56:33<12:51:08,  3.50it/s]
 56%|█████▋    | 209343/371472 [5:56:33<13:50:06,  3.26it/s]
 56%|█████▋    | 209344/371472 [5:56:34<13:51:28,  3.25it/s]
 56%|█████▋    | 209345/371472 [5:56:34<13:45:50,  3.27it/s]
 56%|█████▋    | 209346/371472 [5:56:34<15:20:05,  2.94it/s]
 56%|█████▋    | 209347/371472 [5:56:35<15:32:11,  2.90it/s]
 56%|█████▋    | 209348/371472 [5:56:35<15:19:41,  2.94it/s]
 56%|█████▋    | 209349/371472 [5:56:35<14:35:03,  3.09it/s]
 56%|█████▋    | 209350/371472 [5:56:36<14:15:55,  3.16it/s]
 56%|█████▋    | 209351/371472 [5:56:36<14:20:41,  3.14it/s]
 56%|█████▋    | 209352/371472 [5:56:36<14:14:36,  3.16it/s]
 56%|█████▋    | 209353/371472 [5:56:37<13:38:25,  3.30it/s]
 56%|█████▋    | 209354/371472 [5:56:37<13:42:15,  3.29it/s]
 56%|█████▋    | 209355/371472 [5:56:37<13:27:06,  3.35it/s]
 56%|█████▋    | 209356/371472 [5:56:37<13:30:17,  3.33it/s]
 56%|█████▋    | 209357/371472 [5:56:38<14:00:14,  3.22it/s]
 56%|█████▋    | 209358/371472 [5:56:38<13:47:19,  3.27it/s]
 56%|█████▋    | 209359/371472 [5:56:38<13:32:14,  3.33it/s]
 56%|█████▋    | 209360/371472 [5:56:39<14:02:17,  3.21it/s]
                                                            
{'loss': 2.6256, 'learning_rate': 4.929755004417247e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209360/371472 [5:56:39<14:02:17,  3.21it/s]
 56%|█████▋    | 209361/371472 [5:56:39<13:45:15,  3.27it/s]
 56%|█████▋    | 209362/371472 [5:56:39<13:37:36,  3.30it/s]
 56%|█████▋    | 209363/371472 [5:56:40<13:31:43,  3.33it/s]
 56%|█████▋    | 209364/371472 [5:56:40<13:32:37,  3.32it/s]
 56%|█████▋    | 209365/371472 [5:56:40<13:11:36,  3.41it/s]
 56%|█████▋    | 209366/371472 [5:56:40<12:52:09,  3.50it/s]
 56%|█████▋    | 209367/371472 [5:56:41<12:45:18,  3.53it/s]
 56%|█████▋    | 209368/371472 [5:56:41<12:43:16,  3.54it/s]
 56%|█████▋    | 209369/371472 [5:56:41<12:41:07,  3.55it/s]
 56%|█████▋    | 209370/371472 [5:56:42<13:14:54,  3.40it/s]
 56%|█████▋    | 209371/371472 [5:56:42<14:07:14,  3.19it/s]
 56%|█████▋    | 209372/371472 [5:56:42<13:51:17,  3.25it/s]
 56%|█████▋    | 209373/371472 [5:56:43<13:26:28,  3.35it/s]
 56%|█████▋    | 209374/371472 [5:56:43<13:54:02,  3.24it/s]
 56%|█████▋    | 209375/371472 [5:56:43<13:45:14,  3.27it/s]
 56%|█████▋    | 209376/371472 [5:56:43<13:34:20,  3.32it/s]
 56%|█████▋    | 209377/371472 [5:56:44<13:32:42,  3.32it/s]
 56%|█████▋    | 209378/371472 [5:56:44<13:28:51,  3.34it/s]
 56%|█████▋    | 209379/371472 [5:56:44<14:10:58,  3.17it/s]
 56%|█████▋    | 209380/371472 [5:56:45<14:16:59,  3.15it/s]
                                                            
{'loss': 2.813, 'learning_rate': 4.929270184662457e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209380/371472 [5:56:45<14:16:59,  3.15it/s]
 56%|█████▋    | 209381/371472 [5:56:45<13:47:20,  3.27it/s]
 56%|█████▋    | 209382/371472 [5:56:45<13:40:08,  3.29it/s]
 56%|█████▋    | 209383/371472 [5:56:46<13:23:29,  3.36it/s]
 56%|█████▋    | 209384/371472 [5:56:46<13:58:34,  3.22it/s]
 56%|█████▋    | 209385/371472 [5:56:46<14:28:34,  3.11it/s]
 56%|█████▋    | 209386/371472 [5:56:47<14:26:49,  3.12it/s]
 56%|█████▋    | 209387/371472 [5:56:47<13:54:09,  3.24it/s]
 56%|█████▋    | 209388/371472 [5:56:47<13:52:21,  3.25it/s]
 56%|█████▋    | 209389/371472 [5:56:48<14:41:34,  3.06it/s]
 56%|█████▋    | 209390/371472 [5:56:48<14:16:18,  3.15it/s]
 56%|█████▋    | 209391/371472 [5:56:48<14:04:49,  3.20it/s]
 56%|█████▋    | 209392/371472 [5:56:48<14:01:08,  3.21it/s]
 56%|█████▋    | 209393/371472 [5:56:49<13:54:19,  3.24it/s]
 56%|█████▋    | 209394/371472 [5:56:49<13:52:13,  3.25it/s]
 56%|█████▋    | 209395/371472 [5:56:49<14:49:45,  3.04it/s]
 56%|█████▋    | 209396/371472 [5:56:50<14:13:19,  3.17it/s]
 56%|█████▋    | 209397/371472 [5:56:50<13:51:04,  3.25it/s]
 56%|█████▋    | 209398/371472 [5:56:50<13:41:17,  3.29it/s]
 56%|█████▋    | 209399/371472 [5:56:51<13:18:04,  3.38it/s]
 56%|█████▋    | 209400/371472 [5:56:51<13:00:47,  3.46it/s]
                                                            
{'loss': 2.6426, 'learning_rate': 4.928785364907669e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209400/371472 [5:56:51<13:00:47,  3.46it/s]
 56%|█████▋    | 209401/371472 [5:56:51<13:53:46,  3.24it/s]
 56%|█████▋    | 209402/371472 [5:56:51<13:23:54,  3.36it/s]
 56%|█████▋    | 209403/371472 [5:56:52<13:43:36,  3.28it/s]
 56%|█████▋    | 209404/371472 [5:56:52<13:15:11,  3.40it/s]
 56%|█████▋    | 209405/371472 [5:56:52<14:04:40,  3.20it/s]
 56%|█████▋    | 209406/371472 [5:56:53<13:48:36,  3.26it/s]
 56%|█████▋    | 209407/371472 [5:56:53<13:33:14,  3.32it/s]
 56%|█████▋    | 209408/371472 [5:56:53<13:21:18,  3.37it/s]
 56%|█████▋    | 209409/371472 [5:56:54<13:21:19,  3.37it/s]
 56%|█████▋    | 209410/371472 [5:56:54<13:16:14,  3.39it/s]
 56%|█████▋    | 209411/371472 [5:56:54<14:01:27,  3.21it/s]
 56%|█████▋    | 209412/371472 [5:56:55<14:38:04,  3.08it/s]
 56%|█████▋    | 209413/371472 [5:56:55<14:19:53,  3.14it/s]
 56%|█████▋    | 209414/371472 [5:56:55<14:11:15,  3.17it/s]
 56%|█████▋    | 209415/371472 [5:56:55<14:03:29,  3.20it/s]
 56%|█████▋    | 209416/371472 [5:56:56<13:41:00,  3.29it/s]
 56%|█████▋    | 209417/371472 [5:56:56<13:52:54,  3.24it/s]
 56%|███��█▋    | 209418/371472 [5:56:56<13:53:04,  3.24it/s]
 56%|█████▋    | 209419/371472 [5:56:57<13:25:28,  3.35it/s]
 56%|█████▋    | 209420/371472 [5:56:57<13:09:28,  3.42it/s]
                                                            
{'loss': 2.6395, 'learning_rate': 4.92830054515288e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209420/371472 [5:56:57<13:09:28,  3.42it/s]
 56%|█████▋    | 209421/371472 [5:56:57<13:00:41,  3.46it/s]
 56%|█████▋    | 209422/371472 [5:56:58<13:02:56,  3.45it/s]
 56%|█████▋    | 209423/371472 [5:56:58<12:54:35,  3.49it/s]
 56%|█████▋    | 209424/371472 [5:56:58<13:38:22,  3.30it/s]
 56%|█████▋    | 209425/371472 [5:56:58<13:42:29,  3.28it/s]
 56%|█████▋    | 209426/371472 [5:56:59<14:57:02,  3.01it/s]
 56%|█████▋    | 209427/371472 [5:56:59<15:10:24,  2.97it/s]
 56%|█████▋    | 209428/371472 [5:57:00<14:36:04,  3.08it/s]
 56%|█████▋    | 209429/371472 [5:57:00<13:46:56,  3.27it/s]
 56%|█████▋    | 209430/371472 [5:57:00<13:53:45,  3.24it/s]
 56%|█████▋    | 209431/371472 [5:57:00<13:42:37,  3.28it/s]
 56%|█████▋    | 209432/371472 [5:57:01<13:19:57,  3.38it/s]
 56%|█████▋    | 209433/371472 [5:57:01<13:05:06,  3.44it/s]
 56%|█████▋    | 209434/371472 [5:57:01<13:22:17,  3.37it/s]
 56%|█████▋    | 209435/371472 [5:57:02<13:41:22,  3.29it/s]
 56%|█████▋    | 209436/371472 [5:57:02<14:19:35,  3.14it/s]
 56%|█████▋    | 209437/371472 [5:57:02<13:55:30,  3.23it/s]
 56%|█████▋    | 209438/371472 [5:57:02<13:29:39,  3.34it/s]
 56%|█████▋    | 209439/371472 [5:57:03<13:47:04,  3.27it/s]
 56%|█████▋    | 209440/371472 [5:57:03<13:36:47,  3.31it/s]
                                                            
{'loss': 2.8371, 'learning_rate': 4.92781572539809e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209440/371472 [5:57:03<13:36:47,  3.31it/s]
 56%|█████▋    | 209441/371472 [5:57:03<14:00:23,  3.21it/s]
 56%|█████▋    | 209442/371472 [5:57:04<13:40:17,  3.29it/s]
 56%|█████▋    | 209443/371472 [5:57:04<13:59:06,  3.22it/s]
 56%|█████▋    | 209444/371472 [5:57:04<13:57:03,  3.23it/s]
 56%|█████▋    | 209445/371472 [5:57:05<13:21:53,  3.37it/s]
 56%|█████▋    | 209446/371472 [5:57:05<13:15:27,  3.39it/s]
 56%|█████▋    | 209447/371472 [5:57:05<13:11:16,  3.41it/s]
 56%|█████▋    | 209448/371472 [5:57:06<13:21:47,  3.37it/s]
 56%|█████▋    | 209449/371472 [5:57:06<13:21:49,  3.37it/s]
 56%|█████▋    | 209450/371472 [5:57:06<13:14:11,  3.40it/s]
 56%|█████▋    | 209451/371472 [5:57:06<13:18:59,  3.38it/s]
 56%|█████▋    | 209452/371472 [5:57:07<14:06:52,  3.19it/s]
 56%|█████▋    | 209453/371472 [5:57:07<13:27:16,  3.34it/s]
 56%|█████▋    | 209454/371472 [5:57:07<13:50:52,  3.25it/s]
 56%|█████▋    | 209455/371472 [5:57:08<13:59:29,  3.22it/s]
 56%|█████▋    | 209456/371472 [5:57:08<13:48:33,  3.26it/s]
 56%|█████▋    | 209457/371472 [5:57:08<13:22:17,  3.37it/s]
 56%|█████▋    | 209458/371472 [5:57:08<12:59:08,  3.47it/s]
 56%|█████▋    | 209459/371472 [5:57:09<13:48:06,  3.26it/s]
 56%|█████▋    | 209460/371472 [5:57:09<13:27:53,  3.34it/s]
                                                            
{'loss': 2.7289, 'learning_rate': 4.927330905643301e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209460/371472 [5:57:09<13:27:53,  3.34it/s]
 56%|█████▋    | 209461/371472 [5:57:09<14:11:38,  3.17it/s]
 56%|█████▋    | 209462/371472 [5:57:10<13:41:09,  3.29it/s]
 56%|█████▋    | 209463/371472 [5:57:10<13:14:56,  3.40it/s]
 56%|█████▋    | 209464/371472 [5:57:10<14:10:11,  3.18it/s]
 56%|█████▋    | 209465/371472 [5:57:11<13:41:26,  3.29it/s]
 56%|█████▋    | 209466/371472 [5:57:11<13:54:27,  3.24it/s]
 56%|█████▋    | 209467/371472 [5:57:11<13:54:55,  3.23it/s]
 56%|█████▋    | 209468/371472 [5:57:12<13:22:58,  3.36it/s]
 56%|█████▋    | 209469/371472 [5:57:12<13:02:28,  3.45it/s]
 56%|█████▋    | 209470/371472 [5:57:12<12:58:53,  3.47it/s]
 56%|█████▋    | 209471/371472 [5:57:12<13:06:29,  3.43it/s]
 56%|█████▋    | 209472/371472 [5:57:13<13:37:59,  3.30it/s]
 56%|█████▋    | 209473/371472 [5:57:13<13:27:39,  3.34it/s]
 56%|█████▋    | 209474/371472 [5:57:13<13:27:03,  3.35it/s]
 56%|█████▋    | 209475/371472 [5:57:14<13:07:51,  3.43it/s]
 56%|█████▋    | 209476/371472 [5:57:14<13:24:17,  3.36it/s]
 56%|█████▋    | 209477/371472 [5:57:14<13:26:51,  3.35it/s]
 56%|█████▋    | 209478/371472 [5:57:15<14:27:45,  3.11it/s]
 56%|█████▋    | 209479/371472 [5:57:15<15:07:11,  2.98it/s]
 56%|█████▋    | 209480/371472 [5:57:15<14:21:41,  3.13it/s]
                                                            
{'loss': 2.6307, 'learning_rate': 4.926846085888513e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209480/371472 [5:57:15<14:21:41,  3.13it/s]
 56%|█████▋    | 209481/371472 [5:57:16<13:54:10,  3.24it/s]
 56%|█████▋    | 209482/371472 [5:57:16<14:07:56,  3.18it/s]
 56%|█████▋    | 209483/371472 [5:57:16<13:52:43,  3.24it/s]
 56%|█████▋    | 209484/371472 [5:57:16<13:14:57,  3.40it/s]
 56%|█████▋    | 209485/371472 [5:57:17<13:34:23,  3.32it/s]
 56%|█████▋    | 209486/371472 [5:57:17<13:40:26,  3.29it/s]
 56%|█████▋    | 209487/371472 [5:57:17<13:29:42,  3.33it/s]
 56%|█████▋    | 209488/371472 [5:57:18<14:18:07,  3.15it/s]
 56%|█████▋    | 209489/371472 [5:57:18<14:03:31,  3.20it/s]
 56%|█████▋    | 209490/371472 [5:57:18<14:19:33,  3.14it/s]
 56%|█████▋    | 209491/371472 [5:57:19<14:04:33,  3.20it/s]
 56%|█████▋    | 209492/371472 [5:57:19<13:36:56,  3.30it/s]
 56%|█████▋    | 209493/371472 [5:57:19<14:29:03,  3.11it/s]
 56%|█████▋    | 209494/371472 [5:57:20<15:29:13,  2.91it/s]
 56%|█████▋    | 209495/371472 [5:57:20<15:11:45,  2.96it/s]
 56%|█████▋    | 209496/371472 [5:57:20<14:28:47,  3.11it/s]
 56%|█████▋    | 209497/371472 [5:57:21<14:00:20,  3.21it/s]
 56%|█████▋    | 209498/371472 [5:57:21<13:45:43,  3.27it/s]
 56%|█████▋    | 209499/371472 [5:57:21<13:30:21,  3.33it/s]
 56%|█████▋    | 209500/371472 [5:57:21<14:09:51,  3.18it/s]
                                                            
{'loss': 2.7825, 'learning_rate': 4.926361266133724e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209500/371472 [5:57:22<14:09:51,  3.18it/s]
 56%|█████▋    | 209501/371472 [5:57:22<14:25:11,  3.12it/s]
 56%|█████▋    | 209502/371472 [5:57:22<14:01:15,  3.21it/s]
 56%|█████▋    | 209503/371472 [5:57:22<13:49:07,  3.26it/s]
 56%|█████▋    | 209504/371472 [5:57:23<13:33:08,  3.32it/s]
 56%|█████▋    | 209505/371472 [5:57:23<13:23:21,  3.36it/s]
 56%|█████▋    | 209506/371472 [5:57:23<13:07:42,  3.43it/s]
 56%|█████▋    | 209507/371472 [5:57:24<12:56:58,  3.47it/s]
 56%|█████▋    | 209508/371472 [5:57:24<15:03:55,  2.99it/s]
 56%|█████▋    | 209509/371472 [5:57:24<14:33:30,  3.09it/s]
 56%|█████▋    | 209510/371472 [5:57:25<14:15:56,  3.15it/s]
 56%|█████▋    | 209511/371472 [5:57:25<13:59:20,  3.22it/s]
 56%|█████▋    | 209512/371472 [5:57:25<13:18:47,  3.38it/s]
 56%|█████▋    | 209513/371472 [5:57:25<13:46:28,  3.27it/s]
 56%|█████▋    | 209514/371472 [5:57:26<13:17:33,  3.38it/s]
 56%|█████▋    | 209515/371472 [5:57:26<13:15:41,  3.39it/s]
 56%|█████▋    | 209516/371472 [5:57:26<12:56:09,  3.48it/s]
 56%|█████▋    | 209517/371472 [5:57:27<12:50:00,  3.51it/s]
 56%|█████▋    | 209518/371472 [5:57:27<13:15:13,  3.39it/s]
 56%|█████▋    | 209519/371472 [5:57:27<13:37:26,  3.30it/s]
 56%|█████▋    | 209520/371472 [5:57:28<13:41:02,  3.29it/s]
                                                            
{'loss': 2.8287, 'learning_rate': 4.925876446378935e-07, 'epoch': 9.02}
+
 56%|█████▋    | 209520/371472 [5:57:28<13:41:02,  3.29it/s]
 56%|█████▋    | 209521/371472 [5:57:28<13:40:58,  3.29it/s]
 56%|█████▋    | 209522/371472 [5:57:28<13:07:19,  3.43it/s]
 56%|█████▋    | 209523/371472 [5:57:28<13:03:25,  3.45it/s]
 56%|█████▋    | 209524/371472 [5:57:29<12:39:59,  3.55it/s]
 56%|█████▋    | 209525/371472 [5:57:29<12:59:00,  3.46it/s]
 56%|█████▋    | 209526/371472 [5:57:29<13:07:36,  3.43it/s]
 56%|█████▋    | 209527/371472 [5:57:30<13:05:36,  3.44it/s]
 56%|█████▋    | 209528/371472 [5:57:30<13:24:42,  3.35it/s]
 56%|█████▋    | 209529/371472 [5:57:30<13:51:19,  3.25it/s]
 56%|█████▋    | 209530/371472 [5:57:31<13:46:36,  3.27it/s]
 56%|█████▋    | 209531/371472 [5:57:31<14:19:00,  3.14it/s]
 56%|█████▋    | 209532/371472 [5:57:31<13:43:56,  3.28it/s]
 56%|█████▋    | 209533/371472 [5:57:31<14:18:39,  3.14it/s]
 56%|█████▋    | 209534/371472 [5:57:32<14:34:15,  3.09it/s]
 56%|█████▋    | 209535/371472 [5:57:32<13:42:59,  3.28it/s]
 56%|█████▋    | 209536/371472 [5:57:32<13:45:39,  3.27it/s]
 56%|█████▋    | 209537/371472 [5:57:33<13:40:06,  3.29it/s]
 56%|█████▋    | 209538/371472 [5:57:33<13:29:33,  3.33it/s]
 56%|█████▋    | 209539/371472 [5:57:33<13:59:10,  3.22it/s]
 56%|█████▋    | 209540/371472 [5:57:34<13:40:04,  3.29it/s]
                                                            
{'loss': 2.7915, 'learning_rate': 4.925391626624146e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209540/371472 [5:57:34<13:40:04,  3.29it/s]
 56%|█████▋    | 209541/371472 [5:57:34<13:39:53,  3.29it/s]
 56%|█████▋    | 209542/371472 [5:57:34<13:38:31,  3.30it/s]
 56%|█████▋    | 209543/371472 [5:57:34<13:13:47,  3.40it/s]
 56%|█████▋    | 209544/371472 [5:57:35<13:10:16,  3.42it/s]
 56%|█████▋    | 209545/371472 [5:57:35<13:29:19,  3.33it/s]
 56%|█████▋    | 209546/371472 [5:57:35<13:24:02,  3.36it/s]
 56%|█████▋    | 209547/371472 [5:57:36<13:49:51,  3.25it/s]
 56%|█████▋    | 209548/371472 [5:57:36<14:33:01,  3.09it/s]
 56%|█████▋    | 209549/371472 [5:57:36<14:00:01,  3.21it/s]
 56%|█████▋    | 209550/371472 [5:57:37<13:37:16,  3.30it/s]
 56%|█████▋    | 209551/371472 [5:57:37<13:42:58,  3.28it/s]
 56%|█████▋    | 209552/371472 [5:57:37<13:41:28,  3.29it/s]
 56%|█████▋    | 209553/371472 [5:57:38<13:52:39,  3.24it/s]
 56%|█████▋    | 209554/371472 [5:57:38<13:32:09,  3.32it/s]
 56%|█████▋    | 209555/371472 [5:57:38<13:23:28,  3.36it/s]
 56%|█████▋    | 209556/371472 [5:57:38<13:10:27,  3.41it/s]
 56%|█████▋    | 209557/371472 [5:57:39<13:25:57,  3.35it/s]
 56%|█████▋    | 209558/371472 [5:57:39<14:05:07,  3.19it/s]
 56%|█████▋    | 209559/371472 [5:57:39<13:51:04,  3.25it/s]
 56%|█████▋    | 209560/371472 [5:57:40<13:51:50,  3.24it/s]
                                                            
{'loss': 2.7484, 'learning_rate': 4.924906806869357e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209560/371472 [5:57:40<13:51:50,  3.24it/s]
 56%|█████▋    | 209561/371472 [5:57:40<13:52:37,  3.24it/s]
 56%|█████▋    | 209562/371472 [5:57:40<13:57:15,  3.22it/s]
 56%|█████▋    | 209563/371472 [5:57:41<13:41:38,  3.28it/s]
 56%|█████▋    | 209564/371472 [5:57:41<13:31:37,  3.32it/s]
 56%|█████▋    | 209565/371472 [5:57:41<13:23:06,  3.36it/s]
 56%|█████▋    | 209566/371472 [5:57:42<14:02:51,  3.20it/s]
 56%|█████▋    | 209567/371472 [5:57:42<13:32:43,  3.32it/s]
 56%|█████▋    | 209568/371472 [5:57:42<13:48:34,  3.26it/s]
 56%|█████▋    | 209569/371472 [5:57:42<13:24:32,  3.35it/s]
 56%|█████▋    | 209570/371472 [5:57:43<13:17:24,  3.38it/s]
 56%|█████▋    | 209571/371472 [5:57:43<13:28:28,  3.34it/s]
 56%|█████▋    | 209572/371472 [5:57:43<13:23:41,  3.36it/s]
 56%|█████▋    | 209573/371472 [5:57:44<13:42:50,  3.28it/s]
 56%|█████▋    | 209574/371472 [5:57:44<13:45:34,  3.27it/s]
 56%|█████▋    | 209575/371472 [5:57:44<13:17:55,  3.38it/s]
 56%|█████▋    | 209576/371472 [5:57:45<13:36:30,  3.30it/s]
 56%|█████▋    | 209577/371472 [5:57:45<14:10:55,  3.17it/s]
 56%|█████▋    | 209578/371472 [5:57:45<13:46:47,  3.26it/s]
 56%|█████▋    | 209579/371472 [5:57:45<13:28:48,  3.34it/s]
 56%|█████▋    | 209580/371472 [5:57:46<13:24:08,  3.36it/s]
                                                            
{'loss': 2.7852, 'learning_rate': 4.924421987114568e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209580/371472 [5:57:46<13:24:08,  3.36it/s]
 56%|█████▋    | 209581/371472 [5:57:46<13:11:32,  3.41it/s]
 56%|█████▋    | 209582/371472 [5:57:46<13:04:49,  3.44it/s]
 56%|█████▋    | 209583/371472 [5:57:47<12:56:18,  3.48it/s]
 56%|█████▋    | 209584/371472 [5:57:47<12:48:17,  3.51it/s]
 56%|█████▋    | 209585/371472 [5:57:47<13:20:53,  3.37it/s]
 56%|█████▋    | 209586/371472 [5:57:47<13:09:40,  3.42it/s]
 56%|█████▋    | 209587/371472 [5:57:48<13:00:07,  3.46it/s]
 56%|█████▋    | 209588/371472 [5:57:48<13:02:14,  3.45it/s]
 56%|█████▋    | 209589/371472 [5:57:48<13:03:42,  3.44it/s]
 56%|█████▋    | 209590/371472 [5:57:49<13:18:41,  3.38it/s]
 56%|█████▋    | 209591/371472 [5:57:49<14:26:21,  3.11it/s]
 56%|█████▋    | 209592/371472 [5:57:49<14:31:51,  3.09it/s]
 56%|█████▋    | 209593/371472 [5:57:50<14:05:36,  3.19it/s]
 56%|█████▋    | 209594/371472 [5:57:50<13:52:12,  3.24it/s]
 56%|█████▋    | 209595/371472 [5:57:50<13:27:00,  3.34it/s]
 56%|█████▋    | 209596/371472 [5:57:50<13:22:32,  3.36it/s]
 56%|█████▋    | 209597/371472 [5:57:51<13:31:42,  3.32it/s]
 56%|█████▋    | 209598/371472 [5:57:51<13:28:14,  3.34it/s]
 56%|█████▋    | 209599/371472 [5:57:51<13:19:17,  3.38it/s]
 56%|█████▋    | 209600/371472 [5:57:52<13:43:17,  3.28it/s]
                                                            
{'loss': 2.7298, 'learning_rate': 4.923937167359779e-07, 'epoch': 9.03}
+
 56%|██���██▋    | 209600/371472 [5:57:52<13:43:17,  3.28it/s]
 56%|█████▋    | 209601/371472 [5:57:52<13:39:28,  3.29it/s]
 56%|█████▋    | 209602/371472 [5:57:52<13:17:51,  3.38it/s]
 56%|█████▋    | 209603/371472 [5:57:53<15:51:45,  2.83it/s]
 56%|█████▋    | 209604/371472 [5:57:53<14:51:45,  3.03it/s]
 56%|█████▋    | 209605/371472 [5:57:53<14:00:34,  3.21it/s]
 56%|█████▋    | 209606/371472 [5:57:54<13:37:12,  3.30it/s]
 56%|█████▋    | 209607/371472 [5:57:54<13:16:53,  3.39it/s]
 56%|█████▋    | 209608/371472 [5:57:54<13:19:51,  3.37it/s]
 56%|█████▋    | 209609/371472 [5:57:54<13:24:23,  3.35it/s]
 56%|█████▋    | 209610/371472 [5:57:55<13:49:26,  3.25it/s]
 56%|█████▋    | 209611/371472 [5:57:55<13:49:06,  3.25it/s]
 56%|█████▋    | 209612/371472 [5:57:55<13:19:00,  3.38it/s]
 56%|█████▋    | 209613/371472 [5:57:56<13:05:35,  3.43it/s]
 56%|█████▋    | 209614/371472 [5:57:56<13:56:49,  3.22it/s]
 56%|█████▋    | 209615/371472 [5:57:56<13:45:31,  3.27it/s]
 56%|█████▋    | 209616/371472 [5:57:57<13:39:37,  3.29it/s]
 56%|█████▋    | 209617/371472 [5:57:57<13:36:49,  3.30it/s]
 56%|█████▋    | 209618/371472 [5:57:57<13:17:09,  3.38it/s]
 56%|█████▋    | 209619/371472 [5:57:58<13:39:31,  3.29it/s]
 56%|█████▋    | 209620/371472 [5:57:58<13:34:13,  3.31it/s]
                                                            
{'loss': 2.9529, 'learning_rate': 4.92345234760499e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209620/371472 [5:57:58<13:34:13,  3.31it/s]
 56%|█████▋    | 209621/371472 [5:57:58<14:35:31,  3.08it/s]
 56%|█████▋    | 209622/371472 [5:57:58<14:00:44,  3.21it/s]
 56%|█████▋    | 209623/371472 [5:57:59<13:31:17,  3.32it/s]
 56%|█████▋    | 209624/371472 [5:57:59<14:26:32,  3.11it/s]
 56%|█████▋    | 209625/371472 [5:57:59<13:42:09,  3.28it/s]
 56%|█████▋    | 209626/371472 [5:58:00<13:14:40,  3.39it/s]
 56%|█████▋    | 209627/371472 [5:58:00<13:08:15,  3.42it/s]
 56%|█████▋    | 209628/371472 [5:58:00<13:29:04,  3.33it/s]
 56%|█████▋    | 209629/371472 [5:58:01<13:35:29,  3.31it/s]
 56%|█████▋    | 209630/371472 [5:58:01<13:44:03,  3.27it/s]
 56%|█████▋    | 209631/371472 [5:58:01<13:45:30,  3.27it/s]
 56%|█████▋    | 209632/371472 [5:58:01<13:27:18,  3.34it/s]
 56%|█████▋    | 209633/371472 [5:58:02<13:50:15,  3.25it/s]
 56%|█████▋    | 209634/371472 [5:58:02<15:20:59,  2.93it/s]
 56%|█████▋    | 209635/371472 [5:58:03<14:40:41,  3.06it/s]
 56%|█████▋    | 209636/371472 [5:58:03<14:10:39,  3.17it/s]
 56%|█████▋    | 209637/371472 [5:58:03<14:18:58,  3.14it/s]
 56%|█████▋    | 209638/371472 [5:58:03<14:43:36,  3.05it/s]
 56%|█████▋    | 209639/371472 [5:58:04<14:41:26,  3.06it/s]
 56%|█████▋    | 209640/371472 [5:58:04<14:04:06,  3.20it/s]
                                                            
{'loss': 2.7925, 'learning_rate': 4.922967527850202e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209640/371472 [5:58:04<14:04:06,  3.20it/s]
 56%|█████▋    | 209641/371472 [5:58:04<13:36:27,  3.30it/s]
 56%|█████▋    | 209642/371472 [5:58:05<13:15:19,  3.39it/s]
 56%|█████▋    | 209643/371472 [5:58:05<12:59:31,  3.46it/s]
 56%|█████▋    | 209644/371472 [5:58:05<12:53:08,  3.49it/s]
 56%|█████▋    | 209645/371472 [5:58:06<13:54:06,  3.23it/s]
 56%|█████▋    | 209646/371472 [5:58:06<13:47:54,  3.26it/s]
 56%|█████▋    | 209647/371472 [5:58:06<13:41:23,  3.28it/s]
 56%|█████▋    | 209648/371472 [5:58:06<13:28:45,  3.33it/s]
 56%|█████▋    | 209649/371472 [5:58:07<13:10:43,  3.41it/s]
 56%|█████▋    | 209650/371472 [5:58:07<13:46:38,  3.26it/s]
 56%|█████▋    | 209651/371472 [5:58:07<13:35:34,  3.31it/s]
 56%|█████▋    | 209652/371472 [5:58:08<13:47:50,  3.26it/s]
 56%|█████▋    | 209653/371472 [5:58:08<13:55:37,  3.23it/s]
 56%|█████▋    | 209654/371472 [5:58:08<13:33:59,  3.31it/s]
 56%|█████▋    | 209655/371472 [5:58:09<13:22:18,  3.36it/s]
 56%|█████▋    | 209656/371472 [5:58:09<13:04:37,  3.44it/s]
 56%|█████▋    | 209657/371472 [5:58:09<13:47:07,  3.26it/s]
 56%|█████▋    | 209658/371472 [5:58:10<14:29:19,  3.10it/s]
 56%|█████▋    | 209659/371472 [5:58:10<14:19:46,  3.14it/s]
 56%|█████▋    | 209660/371472 [5:58:10<13:57:35,  3.22it/s]
                                                            
{'loss': 2.8614, 'learning_rate': 4.922482708095413e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209660/371472 [5:58:10<13:57:35,  3.22it/s]
 56%|█████▋    | 209661/371472 [5:58:10<13:42:28,  3.28it/s]
 56%|█████▋    | 209662/371472 [5:58:11<13:51:33,  3.24it/s]
 56%|█████▋    | 209663/371472 [5:58:11<14:32:37,  3.09it/s]
 56%|█████▋    | 209664/371472 [5:58:11<14:12:39,  3.16it/s]
 56%|█████▋    | 209665/371472 [5:58:12<14:46:06,  3.04it/s]
 56%|█████▋    | 209666/371472 [5:58:12<14:13:50,  3.16it/s]
 56%|█████▋    | 209667/371472 [5:58:12<13:55:02,  3.23it/s]
 56%|█████▋    | 209668/371472 [5:58:13<14:27:17,  3.11it/s]
 56%|█████▋    | 209669/371472 [5:58:13<14:07:51,  3.18it/s]
 56%|█████▋    | 209670/371472 [5:58:13<13:42:40,  3.28it/s]
 56%|█████▋    | 209671/371472 [5:58:14<13:24:06,  3.35it/s]
 56%|█████▋    | 209672/371472 [5:58:14<13:07:42,  3.42it/s]
 56%|█████▋    | 209673/371472 [5:58:14<12:51:01,  3.50it/s]
 56%|█████▋    | 209674/371472 [5:58:14<13:00:10,  3.46it/s]
 56%|█████▋    | 209675/371472 [5:58:15<12:46:23,  3.52it/s]
 56%|█████▋    | 209676/371472 [5:58:15<12:42:36,  3.54it/s]
 56%|█████▋    | 209677/371472 [5:58:15<13:30:25,  3.33it/s]
 56%|█████▋    | 209678/371472 [5:58:16<13:22:08,  3.36it/s]
 56%|█████▋    | 209679/371472 [5:58:16<13:27:01,  3.34it/s]
 56%|█████▋    | 209680/371472 [5:58:16<13:11:55,  3.41it/s]
                                                            
{'loss': 2.8169, 'learning_rate': 4.921997888340623e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209680/371472 [5:58:16<13:11:55,  3.41it/s]
 56%|█████▋    | 209681/371472 [5:58:16<13:12:26,  3.40it/s]
 56%|█████▋    | 209682/371472 [5:58:17<14:17:04,  3.15it/s]
 56%|█████▋    | 209683/371472 [5:58:17<13:53:51,  3.23it/s]
 56%|█████▋    | 209684/371472 [5:58:17<13:43:35,  3.27it/s]
 56%|█████▋    | 209685/371472 [5:58:18<13:20:08,  3.37it/s]
 56%|█████▋    | 209686/371472 [5:58:18<13:17:06,  3.38it/s]
 56%|█████▋    | 209687/371472 [5:58:18<13:12:31,  3.40it/s]
 56%|█████▋    | 209688/371472 [5:58:19<13:11:59,  3.40it/s]
 56%|█████▋    | 209689/371472 [5:58:19<13:38:57,  3.29it/s]
 56%|█████▋    | 209690/371472 [5:58:19<13:11:00,  3.41it/s]
 56%|█████▋    | 209691/371472 [5:58:19<13:25:36,  3.35it/s]
 56%|█████▋    | 209692/371472 [5:58:20<13:07:20,  3.42it/s]
 56%|█████▋    | 209693/371472 [5:58:20<13:03:42,  3.44it/s]
 56%|█████▋    | 209694/371472 [5:58:20<13:04:36,  3.44it/s]
 56%|█████▋    | 209695/371472 [5:58:21<13:53:49,  3.23it/s]
 56%|█████▋    | 209696/371472 [5:58:21<13:43:05,  3.28it/s]
 56%|█████▋    | 209697/371472 [5:58:21<13:33:19,  3.32it/s]
 56%|█████▋    | 209698/371472 [5:58:22<13:55:33,  3.23it/s]
 56%|█████▋    | 209699/371472 [5:58:22<13:24:23,  3.35it/s]
 56%|█████▋    | 209700/371472 [5:58:22<12:48:35,  3.51it/s]
                                                            
{'loss': 2.7182, 'learning_rate': 4.921513068585834e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209700/371472 [5:58:22<12:48:35,  3.51it/s]
 56%|█████▋    | 209701/371472 [5:58:22<13:13:14,  3.40it/s]
 56%|█████▋    | 209702/371472 [5:58:23<13:58:44,  3.21it/s]
 56%|█████▋    | 209703/371472 [5:58:23<14:15:31,  3.15it/s]
 56%|█████▋    | 209704/371472 [5:58:23<14:39:53,  3.06it/s]
 56%|█████▋    | 209705/371472 [5:58:24<15:07:14,  2.97it/s]
 56%|█████▋    | 209706/371472 [5:58:24<14:31:31,  3.09it/s]
 56%|█████▋    | 209707/371472 [5:58:24<14:37:40,  3.07it/s]
 56%|█████▋    | 209708/371472 [5:58:25<14:35:16,  3.08it/s]
 56%|█████▋    | 209709/371472 [5:58:25<14:15:32,  3.15it/s]
 56%|█████▋    | 209710/371472 [5:58:25<13:49:47,  3.25it/s]
 56%|█████▋    | 209711/371472 [5:58:26<13:47:22,  3.26it/s]
 56%|█████▋    | 209712/371472 [5:58:26<13:32:10,  3.32it/s]
 56%|█████▋    | 209713/371472 [5:58:26<13:14:04,  3.40it/s]
 56%|█████▋    | 209714/371472 [5:58:27<13:16:45,  3.38it/s]
 56%|█████▋    | 209715/371472 [5:58:27<13:04:01,  3.44it/s]
 56%|█████▋    | 209716/371472 [5:58:27<12:56:41,  3.47it/s]
 56%|█████▋    | 209717/371472 [5:58:27<12:50:23,  3.50it/s]
 56%|█████▋    | 209718/371472 [5:58:28<12:43:21,  3.53it/s]
 56%|█████▋    | 209719/371472 [5:58:28<13:23:27,  3.36it/s]
 56%|█████▋    | 209720/371472 [5:58:28<13:22:55,  3.36it/s]
                                                            
{'loss': 2.765, 'learning_rate': 4.921028248831046e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209720/371472 [5:58:28<13:22:55,  3.36it/s]
 56%|█████▋    | 209721/371472 [5:58:29<13:09:54,  3.41it/s]
 56%|█████▋    | 209722/371472 [5:58:29<13:04:56,  3.43it/s]
 56%|█████▋    | 209723/371472 [5:58:29<13:02:02,  3.45it/s]
 56%|█████▋    | 209724/371472 [5:58:29<12:57:24,  3.47it/s]
 56%|█████▋    | 209725/371472 [5:58:30<13:52:32,  3.24it/s]
 56%|█████▋    | 209726/371472 [5:58:30<13:21:45,  3.36it/s]
 56%|█████▋    | 209727/371472 [5:58:30<13:07:59,  3.42it/s]
 56%|█████▋    | 209728/371472 [5:58:31<13:15:05,  3.39it/s]
 56%|█████▋    | 209729/371472 [5:58:31<13:30:19,  3.33it/s]
 56%|█████▋    | 209730/371472 [5:58:31<13:05:59,  3.43it/s]
 56%|█████▋    | 209731/371472 [5:58:31<12:48:45,  3.51it/s]
 56%|█████▋    | 209732/371472 [5:58:32<12:43:05,  3.53it/s]
 56%|█████▋    | 209733/371472 [5:58:32<15:25:05,  2.91it/s]
 56%|█████▋    | 209734/371472 [5:58:33<15:49:44,  2.84it/s]
 56%|█████▋    | 209735/371472 [5:58:33<15:09:30,  2.96it/s]
 56%|█████▋    | 209736/371472 [5:58:33<14:32:06,  3.09it/s]
 56%|█████▋    | 209737/371472 [5:58:34<14:31:10,  3.09it/s]
 56%|█████▋    | 209738/371472 [5:58:34<14:51:17,  3.02it/s]
 56%|█████▋    | 209739/371472 [5:58:34<14:42:47,  3.05it/s]
 56%|█████▋    | 209740/371472 [5:58:35<14:17:52,  3.14it/s]
                                                            
{'loss': 2.728, 'learning_rate': 4.920543429076257e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209740/371472 [5:58:35<14:17:52,  3.14it/s]
 56%|█████▋    | 209741/371472 [5:58:35<13:49:56,  3.25it/s]
 56%|█████▋    | 209742/371472 [5:58:35<13:49:02,  3.25it/s]
 56%|█████▋    | 209743/371472 [5:58:35<13:33:28,  3.31it/s]
 56%|█████▋    | 209744/371472 [5:58:36<13:57:21,  3.22it/s]
 56%|█████▋    | 209745/371472 [5:58:36<13:40:52,  3.28it/s]
 56%|█████▋    | 209746/371472 [5:58:36<13:29:27,  3.33it/s]
 56%|█████▋    | 209747/371472 [5:58:37<13:46:21,  3.26it/s]
 56%|█████▋    | 209748/371472 [5:58:37<13:51:32,  3.24it/s]
 56%|█████▋    | 209749/371472 [5:58:37<13:13:41,  3.40it/s]
 56%|█████▋    | 209750/371472 [5:58:38<13:37:07,  3.30it/s]
 56%|█████▋    | 209751/371472 [5:58:38<13:14:57,  3.39it/s]
 56%|█████▋    | 209752/371472 [5:58:38<12:53:08,  3.49it/s]
 56%|█████▋    | 209753/371472 [5:58:38<13:19:26,  3.37it/s]
 56%|█████▋    | 209754/371472 [5:58:39<13:11:11,  3.41it/s]
 56%|█████▋    | 209755/371472 [5:58:39<14:36:18,  3.08it/s]
 56%|█████▋    | 209756/371472 [5:58:39<13:55:25,  3.23it/s]
 56%|█████▋    | 209757/371472 [5:58:40<14:25:53,  3.11it/s]
 56%|█████▋    | 209758/371472 [5:58:40<14:29:03,  3.10it/s]
 56%|█████▋    | 209759/371472 [5:58:40<13:44:41,  3.27it/s]
 56%|█████▋    | 209760/371472 [5:58:41<13:37:07,  3.30it/s]
                                                            
{'loss': 2.677, 'learning_rate': 4.920058609321467e-07, 'epoch': 9.03}
+
 56%|█████▋    | 209760/371472 [5:58:41<13:37:07,  3.30it/s]
 56%|█████▋    | 209761/371472 [5:58:41<13:39:43,  3.29it/s]
 56%|█████▋    | 209762/371472 [5:58:41<13:33:31,  3.31it/s]
 56%|█████▋    | 209763/371472 [5:58:42<14:22:14,  3.13it/s]
 56%|█████▋    | 209764/371472 [5:58:42<14:06:43,  3.18it/s]
 56%|█████▋    | 209765/371472 [5:58:42<14:45:41,  3.04it/s]
 56%|█████▋    | 209766/371472 [5:58:43<15:24:21,  2.92it/s]
 56%|█████▋    | 209767/371472 [5:58:43<14:41:43,  3.06it/s]
 56%|█████▋    | 209768/371472 [5:58:43<14:48:47,  3.03it/s]
 56%|█████▋    | 209769/371472 [5:58:44<14:17:28,  3.14it/s]
 56%|█████▋    | 209770/371472 [5:58:44<14:09:09,  3.17it/s]
 56%|█████▋    | 209771/371472 [5:58:44<13:48:58,  3.25it/s]
 56%|█████▋    | 209772/371472 [5:58:44<14:03:25,  3.20it/s]
 56%|█████▋    | 209773/371472 [5:58:45<13:58:46,  3.21it/s]
 56%|█████▋    | 209774/371472 [5:58:45<13:41:14,  3.28it/s]
 56%|█████▋    | 209775/371472 [5:58:45<14:09:22,  3.17it/s]
 56%|█████▋    | 209776/371472 [5:58:46<13:51:31,  3.24it/s]
 56%|█████▋    | 209777/371472 [5:58:46<13:44:25,  3.27it/s]
 56%|█████▋    | 209778/371472 [5:58:46<13:49:20,  3.25it/s]
 56%|█████▋    | 209779/371472 [5:58:47<13:42:26,  3.28it/s]
 56%|█████▋    | 209780/371472 [5:58:47<13:11:13,  3.41it/s]
                                                            
{'loss': 2.6246, 'learning_rate': 4.919573789566679e-07, 'epoch': 9.04}
+
 56%|█████▋    | 209780/371472 [5:58:47<13:11:13,  3.41it/s]
 56%|█████▋    | 209781/371472 [5:58:47<13:13:07,  3.40it/s]
 56%|█████▋    | 209782/371472 [5:58:47<13:08:34,  3.42it/s]
 56%|█████▋    | 209783/371472 [5:58:48<13:46:53,  3.26it/s]
 56%|█████▋    | 209784/371472 [5:58:48<13:30:05,  3.33it/s]
 56%|█████▋    | 209785/371472 [5:58:48<13:58:41,  3.21it/s]
 56%|█████▋    | 209786/371472 [5:58:49<15:30:08,  2.90it/s]
 56%|█████▋    | 209787/371472 [5:58:49<16:01:50,  2.80it/s]
 56%|█████▋    | 209788/371472 [5:58:49<14:59:48,  2.99it/s]
 56%|█████▋    | 209789/371472 [5:58:50<14:14:12,  3.15it/s]
 56%|█████▋    | 209790/371472 [5:58:50<14:40:29,  3.06it/s]
 56%|█████▋    | 209791/371472 [5:58:50<14:08:21,  3.18it/s]
 56%|█████▋    | 209792/371472 [5:58:51<13:34:02,  3.31it/s]
 56%|█████▋    | 209793/371472 [5:58:51<14:08:16,  3.18it/s]
 56%|█████▋    | 209794/371472 [5:58:51<13:56:27,  3.22it/s]
 56%|█████▋    | 209795/371472 [5:58:52<14:08:09,  3.18it/s]
 56%|█████▋    | 209796/371472 [5:58:52<13:50:23,  3.24it/s]
 56%|█████▋    | 209797/371472 [5:58:52<13:33:42,  3.31it/s]
 56%|█████▋    | 209798/371472 [5:58:52<13:22:43,  3.36it/s]
 56%|█████▋    | 209799/371472 [5:58:53<13:09:09,  3.41it/s]
 56%|█████▋    | 209800/371472 [5:58:53<12:51:08,  3.49it/s]
                                                            
{'loss': 2.7099, 'learning_rate': 4.91908896981189e-07, 'epoch': 9.04}
+
 56%|█████▋    | 209800/371472 [5:58:53<12:51:08,  3.49it/s]
 56%|█████▋    | 209801/371472 [5:58:53<12:47:20,  3.51it/s]
 56%|█████▋    | 209802/371472 [5:58:54<13:33:35,  3.31it/s]
 56%|█████▋    | 209803/371472 [5:58:54<13:16:30,  3.38it/s]
 56%|█████▋    | 209804/371472 [5:58:54<13:24:24,  3.35it/s]
 56%|█████▋    | 209805/371472 [5:58:55<13:11:09,  3.41it/s]
 56%|█████▋    | 209806/371472 [5:58:55<13:25:31,  3.34it/s]
 56%|█████▋    | 209807/371472 [5:58:55<13:13:56,  3.39it/s]
 56%|█████▋    | 209808/371472 [5:58:55<12:44:02,  3.53it/s]
 56%|█████▋    | 209809/371472 [5:58:56<12:47:21,  3.51it/s]
 56%|█████▋    | 209810/371472 [5:58:56<13:02:37,  3.44it/s]
 56%|█████▋    | 209811/371472 [5:58:56<13:28:56,  3.33it/s]
 56%|█████▋    | 209812/371472 [5:58:57<13:00:05,  3.45it/s]
 56%|█████▋    | 209813/371472 [5:58:57<13:00:36,  3.45it/s]
 56%|█████▋    | 209814/371472 [5:58:57<12:48:49,  3.50it/s]
 56%|█████▋    | 209815/371472 [5:58:57<13:45:30,  3.26it/s]
 56%|█████▋    | 209816/371472 [5:58:58<13:38:34,  3.29it/s]
 56%|█████▋    | 209817/371472 [5:58:58<13:14:00,  3.39it/s]
 56%|█████▋    | 209818/371472 [5:58:58<13:05:48,  3.43it/s]
 56%|█████▋    | 209819/371472 [5:58:59<13:27:29,  3.34it/s]
 56%|█████▋    | 209820/371472 [5:58:59<13:18:34,  3.37it/s]
                                                            
{'loss': 2.7465, 'learning_rate': 4.9186041500571e-07, 'epoch': 9.04}
+
 56%|█████▋    | 209820/371472 [5:58:59<13:18:34,  3.37it/s]
 56%|█████▋    | 209821/371472 [5:58:59<13:04:14,  3.44it/s]
 56%|█████▋    | 209822/371472 [5:59:00<13:23:56,  3.35it/s]
 56%|█████▋    | 209823/371472 [5:59:00<12:55:30,  3.47it/s]
 56%|█████▋    | 209824/371472 [5:59:00<13:21:04,  3.36it/s]
 56%|█████▋    | 209825/371472 [5:59:00<12:59:36,  3.46it/s]
 56%|█████▋    | 209826/371472 [5:59:01<13:00:54,  3.45it/s]
 56%|█████▋    | 209827/371472 [5:59:01<12:40:03,  3.54it/s]
 56%|█████▋    | 209828/371472 [5:59:01<12:56:20,  3.47it/s]
 56%|█████▋    | 209829/371472 [5:59:02<12:42:50,  3.53it/s]
 56%|█████▋    | 209830/371472 [5:59:02<13:00:42,  3.45it/s]
 56%|█████▋    | 209831/371472 [5:59:02<13:03:25,  3.44it/s]
 56%|█████▋    | 209832/371472 [5:59:02<12:39:51,  3.55it/s]
 56%|█████▋    | 209833/371472 [5:59:03<13:49:28,  3.25it/s]
 56%|█████▋    | 209834/371472 [5:59:03<13:42:33,  3.28it/s]
 56%|█████▋    | 209835/371472 [5:59:03<13:44:30,  3.27it/s]
 56%|█████▋    | 209836/371472 [5:59:04<13:50:01,  3.25it/s]
 56%|█████▋    | 209837/371472 [5:59:04<13:49:35,  3.25it/s]
 56%|█████▋    | 209838/371472 [5:59:04<13:49:25,  3.25it/s]
 56%|█████▋    | 209839/371472 [5:59:05<13:59:25,  3.21it/s]
 56%|█████▋    | 209840/371472 [5:59:05<13:55:03,  3.23it/s]
                                                            
{'loss': 2.8671, 'learning_rate': 4.918119330302311e-07, 'epoch': 9.04}
+
 56%|█████▋    | 209840/371472 [5:59:05<13:55:03,  3.23it/s]
 56%|█████▋    | 209841/371472 [5:59:05<13:53:16,  3.23it/s]
 56%|█████▋    | 209842/371472 [5:59:06<13:39:55,  3.29it/s]
 56%|█████▋    | 209843/371472 [5:59:06<13:19:45,  3.37it/s]
 56%|█████▋    | 209844/371472 [5:59:06<13:15:59,  3.38it/s]
 56%|█████▋    | 209845/371472 [5:59:06<13:01:52,  3.45it/s]
 56%|█████▋    | 209846/371472 [5:59:07<13:33:55,  3.31it/s]
 56%|█████▋    | 209847/371472 [5:59:07<13:45:06,  3.26it/s]
 56%|█████▋    | 209848/371472 [5:59:07<13:44:02,  3.27it/s]
 56%|█████▋    | 209849/371472 [5:59:08<13:48:36,  3.25it/s]
 56%|█████▋    | 209850/371472 [5:59:08<13:20:26,  3.37it/s]
 56%|█████▋    | 209851/371472 [5:59:08<13:18:28,  3.37it/s]
 56%|█████▋    | 209852/371472 [5:59:09<13:50:45,  3.24it/s]
 56%|█████▋    | 209853/371472 [5:59:09<13:55:36,  3.22it/s]
 56%|█████▋    | 209854/371472 [5:59:09<14:00:54,  3.20it/s]
 56%|█████▋    | 209855/371472 [5:59:09<13:40:51,  3.28it/s]
 56%|█████▋    | 209856/371472 [5:59:10<13:29:48,  3.33it/s]
 56%|█████▋    | 209857/371472 [5:59:10<13:24:05,  3.35it/s]
 56%|█████▋    | 209858/371472 [5:59:10<12:55:41,  3.47it/s]
 56%|█████▋    | 209859/371472 [5:59:11<12:53:37,  3.48it/s]
 56%|█████▋    | 209860/371472 [5:59:11<13:07:40,  3.42it/s]
                                                            
{'loss': 2.7427, 'learning_rate': 4.917634510547523e-07, 'epoch': 9.04}
+
 56%|█████▋    | 209860/371472 [5:59:11<13:07:40,  3.42it/s]
 56%|█████▋    | 209861/371472 [5:59:11<13:14:47,  3.39it/s]
 56%|█████▋    | 209862/371472 [5:59:11<13:07:13,  3.42it/s]
 56%|█████▋    | 209863/371472 [5:59:12<13:13:32,  3.39it/s]
 56%|█████▋    | 209864/371472 [5:59:12<13:01:23,  3.45it/s]
 56%|█████▋    | 209865/371472 [5:59:12<12:57:29,  3.46it/s]
 56%|█████▋    | 209866/371472 [5:59:13<13:16:42,  3.38it/s]
 56%|█████▋    | 209867/371472 [5:59:13<13:06:50,  3.42it/s]
 56%|█████▋    | 209868/371472 [5:59:13<13:04:42,  3.43it/s]
 56%|█████▋    | 209869/371472 [5:59:14<14:14:46,  3.15it/s]
 56%|█████▋    | 209870/371472 [5:59:14<14:06:03,  3.18it/s]
 56%|█████▋    | 209871/371472 [5:59:14<14:59:33,  2.99it/s]
 56%|█████▋    | 209872/371472 [5:59:15<14:49:24,  3.03it/s]
 56%|█████▋    | 209873/371472 [5:59:15<14:24:57,  3.11it/s]
 56%|█████▋    | 209874/371472 [5:59:15<13:44:54,  3.26it/s]
 56%|█████▋    | 209875/371472 [5:59:15<13:26:44,  3.34it/s]
 56%|█████▋    | 209876/371472 [5:59:16<13:34:20,  3.31it/s]
 56%|█████▋    | 209877/371472 [5:59:16<13:11:14,  3.40it/s]
 56%|█████▋    | 209878/371472 [5:59:16<13:10:16,  3.41it/s]
 56%|█████▋    | 209879/371472 [5:59:17<12:59:10,  3.46it/s]
 56%|█████▋    | 209880/371472 [5:59:17<12:54:24,  3.48it/s]
                                                            
{'loss': 2.8203, 'learning_rate': 4.917149690792734e-07, 'epoch': 9.04}
+
 56%|█████▋    | 209880/371472 [5:59:17<12:54:24,  3.48it/s]
 56%|█████▋    | 209881/371472 [5:59:17<12:48:28,  3.50it/s]
 57%|█████▋    | 209882/371472 [5:59:17<12:54:48,  3.48it/s]
 57%|█████▋    | 209883/371472 [5:59:18<13:36:09,  3.30it/s]
 57%|█████▋    | 209884/371472 [5:59:18<13:26:47,  3.34it/s]
 57%|█████▋    | 209885/371472 [5:59:18<13:08:01,  3.42it/s]
 57%|█████▋    | 209886/371472 [5:59:19<13:05:09,  3.43it/s]
 57%|█████▋    | 209887/371472 [5:59:19<13:45:25,  3.26it/s]
 57%|█████▋    | 209888/371472 [5:59:19<13:49:23,  3.25it/s]
 57%|█████▋    | 209889/371472 [5:59:20<13:45:15,  3.26it/s]
 57%|█████▋    | 209890/371472 [5:59:20<13:56:56,  3.22it/s]
 57%|█████▋    | 209891/371472 [5:59:20<13:28:06,  3.33it/s]
 57%|█████▋    | 209892/371472 [5:59:21<13:47:42,  3.25it/s]
 57%|█████▋    | 209893/371472 [5:59:21<13:14:04,  3.39it/s]
 57%|█████▋    | 209894/371472 [5:59:21<13:08:55,  3.41it/s]
 57%|█████▋    | 209895/371472 [5:59:21<13:22:18,  3.36it/s]
 57%|█████▋    | 209896/371472 [5:59:22<13:07:35,  3.42it/s]
 57%|█████▋    | 209897/371472 [5:59:22<13:21:39,  3.36it/s]
 57%|█████▋    | 209898/371472 [5:59:22<13:18:43,  3.37it/s]
 57%|█████▋    | 209899/371472 [5:59:23<12:58:01,  3.46it/s]
 57%|█████▋    | 209900/371472 [5:59:23<13:30:20,  3.32it/s]
                                                            
{'loss': 2.7269, 'learning_rate': 4.916664871037945e-07, 'epoch': 9.04}
+
 57%|█████▋    | 209900/371472 [5:59:23<13:30:20,  3.32it/s]
 57%|█████▋    | 209901/371472 [5:59:23<13:59:07,  3.21it/s]
 57%|█████▋    | 209902/371472 [5:59:24<13:39:01,  3.29it/s]
 57%|█████▋    | 209903/371472 [5:59:24<13:22:58,  3.35it/s]
 57%|█████▋    | 209904/371472 [5:59:24<13:19:59,  3.37it/s]
 57%|█████▋    | 209905/371472 [5:59:24<13:49:43,  3.25it/s]
 57%|█████▋    | 209906/371472 [5:59:25<13:43:10,  3.27it/s]
 57%|█████▋    | 209907/371472 [5:59:25<13:52:18,  3.24it/s]
 57%|███���█▋    | 209908/371472 [5:59:25<13:40:49,  3.28it/s]
 57%|█████▋    | 209909/371472 [5:59:26<13:24:23,  3.35it/s]
 57%|█████▋    | 209910/371472 [5:59:26<13:43:10,  3.27it/s]
 57%|█████▋    | 209911/371472 [5:59:26<13:45:13,  3.26it/s]
 57%|█████▋    | 209912/371472 [5:59:27<13:32:55,  3.31it/s]
 57%|█████▋    | 209913/371472 [5:59:27<13:42:49,  3.27it/s]
 57%|█████▋    | 209914/371472 [5:59:27<13:20:43,  3.36it/s]
 57%|█████▋    | 209915/371472 [5:59:27<13:31:04,  3.32it/s]
 57%|█████▋    | 209916/371472 [5:59:28<13:16:18,  3.38it/s]
 57%|█████▋    | 209917/371472 [5:59:28<13:01:30,  3.45it/s]
 57%|█████▋    | 209918/371472 [5:59:28<12:56:55,  3.47it/s]
 57%|█████▋    | 209919/371472 [5:59:29<12:45:00,  3.52it/s]
 57%|█████▋    | 209920/371472 [5:59:29<12:55:21,  3.47it/s]
                                                            
{'loss': 2.9496, 'learning_rate': 4.916180051283156e-07, 'epoch': 9.04}
+
 57%|█████▋    | 209920/371472 [5:59:29<12:55:21,  3.47it/s]
 57%|█████▋    | 209921/371472 [5:59:29<12:59:52,  3.45it/s]
 57%|█████▋    | 209922/371472 [5:59:30<13:55:49,  3.22it/s]
 57%|█████▋    | 209923/371472 [5:59:30<13:29:34,  3.33it/s]
 57%|█████▋    | 209924/371472 [5:59:30<13:11:48,  3.40it/s]
 57%|█████▋    | 209925/371472 [5:59:30<12:46:21,  3.51it/s]
 57%|█████▋    | 209926/371472 [5:59:31<13:18:03,  3.37it/s]
 57%|█████▋    | 209927/371472 [5:59:31<13:13:19,  3.39it/s]
 57%|█████▋    | 209928/371472 [5:59:31<12:59:58,  3.45it/s]
 57%|█████▋    | 209929/371472 [5:59:32<13:00:02,  3.45it/s]
 57%|█████▋    | 209930/371472 [5:59:32<13:00:42,  3.45it/s]
 57%|█████▋    | 209931/371472 [5:59:32<13:09:25,  3.41it/s]
 57%|█████▋    | 209932/371472 [5:59:32<12:55:10,  3.47it/s]
 57%|█████▋    | 209933/371472 [5:59:33<12:36:59,  3.56it/s]
 57%|█████▋    | 209934/371472 [5:59:33<12:59:33,  3.45it/s]
 57%|█████▋    | 209935/371472 [5:59:33<13:28:48,  3.33it/s]
 57%|█████▋    | 209936/371472 [5:59:34<13:30:21,  3.32it/s]
 57%|█████▋    | 209937/371472 [5:59:34<13:41:07,  3.28it/s]
 57%|█████▋    | 209938/371472 [5:59:34<13:22:27,  3.35it/s]
 57%|█████▋    | 209939/371472 [5:59:34<12:59:51,  3.45it/s]
 57%|█████▋    | 209940/371472 [5:59:35<13:37:34,  3.29it/s]
                                                            
{'loss': 2.7703, 'learning_rate': 4.915695231528367e-07, 'epoch': 9.04}
+
 57%|█████▋    | 209940/371472 [5:59:35<13:37:34,  3.29it/s]
 57%|█████▋    | 209941/371472 [5:59:35<13:37:52,  3.29it/s]
 57%|█████▋    | 209942/371472 [5:59:35<13:48:19,  3.25it/s]
 57%|█████▋    | 209943/371472 [5:59:36<13:25:04,  3.34it/s]
 57%|█████▋    | 209944/371472 [5:59:36<13:24:43,  3.35it/s]
 57%|█████▋    | 209945/371472 [5:59:36<13:27:14,  3.33it/s]
 57%|█████▋    | 209946/371472 [5:59:37<13:54:38,  3.23it/s]
 57%|█████▋    | 209947/371472 [5:59:37<13:45:20,  3.26it/s]
 57%|█████▋    | 209948/371472 [5:59:37<14:39:41,  3.06it/s]
 57%|█████▋    | 209949/371472 [5:59:38<15:01:12,  2.99it/s]
 57%|█████▋    | 209950/371472 [5:59:38<14:20:45,  3.13it/s]
 57%|█████▋    | 209951/371472 [5:59:38<14:02:56,  3.19it/s]
 57%|█████▋    | 209952/371472 [5:59:39<13:46:04,  3.26it/s]
 57%|█████▋    | 209953/371472 [5:59:39<13:17:47,  3.37it/s]
 57%|█████▋    | 209954/371472 [5:59:39<13:07:12,  3.42it/s]
 57%|█████▋    | 209955/371472 [5:59:39<13:06:34,  3.42it/s]
 57%|█████▋    | 209956/371472 [5:59:40<12:57:19,  3.46it/s]
 57%|█████▋    | 209957/371472 [5:59:40<13:02:17,  3.44it/s]
 57%|█████▋    | 209958/371472 [5:59:40<13:08:50,  3.41it/s]
 57%|█████▋    | 209959/371472 [5:59:41<13:04:26,  3.43it/s]
 57%|█████▋    | 209960/371472 [5:59:41<13:25:42,  3.34it/s]
                                                            
{'loss': 2.7397, 'learning_rate': 4.915210411773578e-07, 'epoch': 9.04}
+
 57%|█████▋    | 209960/371472 [5:59:41<13:25:42,  3.34it/s]
 57%|█████▋    | 209961/371472 [5:59:41<13:52:45,  3.23it/s]
 57%|█████▋    | 209962/371472 [5:59:41<13:37:18,  3.29it/s]
 57%|█████▋    | 209963/371472 [5:59:42<13:36:02,  3.30it/s]
 57%|█████▋    | 209964/371472 [5:59:42<13:17:32,  3.38it/s]
 57%|█████▋    | 209965/371472 [5:59:42<13:02:08,  3.44it/s]
 57%|█████▋    | 209966/371472 [5:59:43<13:05:42,  3.43it/s]
 57%|█████▋    | 209967/371472 [5:59:43<12:55:26,  3.47it/s]
 57%|█████▋    | 209968/371472 [5:59:43<12:42:35,  3.53it/s]
 57%|█████▋    | 209969/371472 [5:59:44<13:14:32,  3.39it/s]
 57%|█████▋    | 209970/371472 [5:59:44<13:12:21,  3.40it/s]
 57%|█████▋    | 209971/371472 [5:59:44<13:09:09,  3.41it/s]
 57%|█████▋    | 209972/371472 [5:59:44<13:02:06,  3.44it/s]
 57%|█████▋    | 209973/371472 [5:59:45<13:00:30,  3.45it/s]
 57%|█████▋    | 209974/371472 [5:59:45<13:09:03,  3.41it/s]
 57%|█████▋    | 209975/371472 [5:59:45<12:55:34,  3.47it/s]
 57%|█████▋    | 209976/371472 [5:59:46<12:38:38,  3.55it/s]
 57%|█████▋    | 209977/371472 [5:59:46<13:01:53,  3.44it/s]
 57%|█████▋    | 209978/371472 [5:59:46<13:05:04,  3.43it/s]
 57%|█████▋    | 209979/371472 [5:59:46<12:54:35,  3.47it/s]
 57%|█████▋    | 209980/371472 [5:59:47<14:02:40,  3.19it/s]
                                                            
{'loss': 2.7152, 'learning_rate': 4.914725592018789e-07, 'epoch': 9.04}
+
 57%|█████▋    | 209980/371472 [5:59:47<14:02:40,  3.19it/s]
 57%|█████▋    | 209981/371472 [5:59:47<14:18:53,  3.13it/s]
 57%|█████▋    | 209982/371472 [5:59:47<14:15:24,  3.15it/s]
 57%|█████▋    | 209983/371472 [5:59:48<13:41:11,  3.28it/s]
 57%|█████▋    | 209984/371472 [5:59:48<13:24:37,  3.34it/s]
 57%|█████▋    | 209985/371472 [5:59:48<13:13:47,  3.39it/s]
 57%|█████▋    | 209986/371472 [5:59:49<12:58:41,  3.46it/s]
 57%|█████▋    | 209987/371472 [5:59:49<12:57:31,  3.46it/s]
 57%|█████▋    | 209988/371472 [5:59:49<12:58:58,  3.46it/s]
 57%|█████▋    | 209989/371472 [5:59:49<13:04:34,  3.43it/s]
 57%|█████▋    | 209990/371472 [5:59:50<12:59:26,  3.45it/s]
 57%|█████▋    | 209991/371472 [5:59:50<12:53:54,  3.48it/s]
 57%|█████▋    | 209992/371472 [5:59:50<12:50:38,  3.49it/s]
 57%|█████▋    | 209993/371472 [5:59:51<12:59:11,  3.45it/s]
 57%|█████▋    | 209994/371472 [5:59:51<13:56:33,  3.22it/s]
 57%|█████▋    | 209995/371472 [5:59:51<13:42:29,  3.27it/s]
 57%|█████▋    | 209996/371472 [5:59:52<14:39:41,  3.06it/s]
 57%|█████▋    | 209997/371472 [5:59:52<14:41:33,  3.05it/s]
 57%|█████▋    | 209998/371472 [5:59:52<14:11:22,  3.16it/s]
 57%|█████▋    | 209999/371472 [5:59:53<14:39:54,  3.06it/s]
 57%|█████▋    | 210000/371472 [5:59:53<13:48:21,  3.25it/s]
                                                            
{'loss': 2.6606, 'learning_rate': 4.914240772264e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210000/371472 [5:59:53<13:48:21,  3.25it/s]
 57%|█████▋    | 210001/371472 [5:59:53<13:30:06,  3.32it/s]
 57%|█████▋    | 210002/371472 [5:59:53<13:49:17,  3.25it/s]
 57%|█████▋    | 210003/371472 [5:59:54<13:28:56,  3.33it/s]
 57%|█████▋    | 210004/371472 [5:59:54<13:27:41,  3.33it/s]
 57%|█████▋    | 210005/371472 [5:59:54<13:40:49,  3.28it/s]
 57%|█████▋    | 210006/371472 [5:59:55<13:24:37,  3.34it/s]
 57%|█████▋    | 210007/371472 [5:59:55<13:36:20,  3.30it/s]
 57%|█████▋    | 210008/371472 [5:59:55<13:24:46,  3.34it/s]
 57%|█████▋    | 210009/371472 [5:59:56<14:33:13,  3.08it/s]
 57%|█████▋    | 210010/371472 [5:59:56<14:18:11,  3.14it/s]
 57%|█████▋    | 210011/371472 [5:59:56<13:54:16,  3.23it/s]
 57%|█████▋    | 210012/371472 [5:59:56<13:39:44,  3.28it/s]
 57%|█████▋    | 210013/371472 [5:59:57<13:22:40,  3.35it/s]
 57%|█████▋    | 210014/371472 [5:59:57<13:42:06,  3.27it/s]
 57%|█████▋    | 210015/371472 [5:59:57<14:06:46,  3.18it/s]
 57%|█████▋    | 210016/371472 [5:59:58<14:02:45,  3.19it/s]
 57%|█████▋    | 210017/371472 [5:59:58<14:26:24,  3.11it/s]
 57%|█████▋    | 210018/371472 [5:59:58<14:42:14,  3.05it/s]
 57%|█████▋    | 210019/371472 [5:59:59<14:06:05,  3.18it/s]
 57%|█████▋    | 210020/371472 [5:59:59<14:13:00,  3.15it/s]
                                                            
{'loss': 2.8625, 'learning_rate': 4.913755952509212e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210020/371472 [5:59:59<14:13:00,  3.15it/s]
 57%|█████▋    | 210021/371472 [5:59:59<14:10:40,  3.16it/s]
 57%|█████▋    | 210022/371472 [6:00:00<14:30:49,  3.09it/s]
 57%|█████▋    | 210023/371472 [6:00:00<13:55:51,  3.22it/s]
 57%|█████▋    | 210024/371472 [6:00:00<13:27:27,  3.33it/s]
 57%|█████▋    | 210025/371472 [6:00:01<13:21:56,  3.36it/s]
 57%|█████▋    | 210026/371472 [6:00:01<13:46:29,  3.26it/s]
 57%|█████▋    | 210027/371472 [6:00:01<13:38:18,  3.29it/s]
 57%|█████▋    | 210028/371472 [6:00:01<13:22:37,  3.35it/s]
 57%|█████▋    | 210029/371472 [6:00:02<13:11:49,  3.40it/s]
 57%|█████▋    | 210030/371472 [6:00:02<13:10:19,  3.40it/s]
 57%|█████▋    | 210031/371472 [6:00:02<12:45:34,  3.51it/s]
 57%|█████▋    | 210032/371472 [6:00:03<12:44:17,  3.52it/s]
 57%|█████▋    | 210033/371472 [6:00:03<12:45:43,  3.51it/s]
 57%|█████▋    | 210034/371472 [6:00:03<13:10:41,  3.40it/s]
 57%|█████▋    | 210035/371472 [6:00:03<13:14:08,  3.39it/s]
 57%|█████▋    | 210036/371472 [6:00:04<13:07:06,  3.42it/s]
 57%|█████▋    | 210037/371472 [6:00:04<13:05:39,  3.42it/s]
 57%|█████▋    | 210038/371472 [6:00:04<12:53:40,  3.48it/s]
 57%|█████▋    | 210039/371472 [6:00:05<13:18:31,  3.37it/s]
 57%|█████▋    | 210040/371472 [6:00:05<13:23:57,  3.35it/s]
                                                            
{'loss': 2.909, 'learning_rate': 4.913271132754423e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210040/371472 [6:00:05<13:23:57,  3.35it/s]
 57%|█████▋    | 210041/371472 [6:00:05<13:18:12,  3.37it/s]
 57%|█████▋    | 210042/371472 [6:00:06<13:25:31,  3.34it/s]
 57%|█████▋    | 210043/371472 [6:00:06<13:28:23,  3.33it/s]
 57%|█████▋    | 210044/371472 [6:00:06<13:28:53,  3.33it/s]
 57%|█████▋    | 210045/371472 [6:00:06<13:19:18,  3.37it/s]
 57%|█████▋    | 210046/371472 [6:00:07<15:23:31,  2.91it/s]
 57%|█████▋    | 210047/371472 [6:00:07<14:38:41,  3.06it/s]
 57%|█████▋    | 210048/371472 [6:00:08<14:47:34,  3.03it/s]
 57%|█████▋    | 210049/371472 [6:00:08<14:41:27,  3.05it/s]
 57%|█████▋    | 210050/371472 [6:00:08<14:28:07,  3.10it/s]
 57%|█████▋    | 210051/371472 [6:00:08<14:16:51,  3.14it/s]
 57%|█████▋    | 210052/371472 [6:00:09<14:03:58,  3.19it/s]
 57%|█████▋    | 210053/371472 [6:00:09<14:19:54,  3.13it/s]
 57%|█████▋    | 210054/371472 [6:00:09<13:49:05,  3.24it/s]
 57%|█████▋    | 210055/371472 [6:00:10<14:25:31,  3.11it/s]
 57%|█████▋    | 210056/371472 [6:00:10<13:57:10,  3.21it/s]
 57%|█████▋    | 210057/371472 [6:00:10<14:10:02,  3.16it/s]
 57%|█████▋    | 210058/371472 [6:00:11<13:54:41,  3.22it/s]
 57%|█████▋    | 210059/371472 [6:00:11<13:44:50,  3.26it/s]
 57%|█████▋    | 210060/371472 [6:00:11<13:57:33,  3.21it/s]
                                                            
{'loss': 2.7786, 'learning_rate': 4.912786312999633e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210060/371472 [6:00:11<13:57:33,  3.21it/s]
 57%|█████▋    | 210061/371472 [6:00:12<14:22:10,  3.12it/s]
 57%|█████▋    | 210062/371472 [6:00:12<14:09:20,  3.17it/s]
 57%|█████▋    | 210063/371472 [6:00:12<13:49:53,  3.24it/s]
 57%|█████▋    | 210064/371472 [6:00:13<15:17:11,  2.93it/s]
 57%|█████▋    | 210065/371472 [6:00:13<14:18:35,  3.13it/s]
 57%|█████▋    | 210066/371472 [6:00:13<13:33:02,  3.31it/s]
 57%|█████▋    | 210067/371472 [6:00:13<13:53:44,  3.23it/s]
 57%|█████▋    | 210068/371472 [6:00:14<13:38:32,  3.29it/s]
 57%|█████▋    | 210069/371472 [6:00:14<13:27:10,  3.33it/s]
 57%|█████▋    | 210070/371472 [6:00:14<13:46:13,  3.26it/s]
 57%|█████▋    | 210071/371472 [6:00:15<13:20:19,  3.36it/s]
 57%|█████▋    | 210072/371472 [6:00:15<13:16:30,  3.38it/s]
 57%|█████▋    | 210073/371472 [6:00:15<13:09:49,  3.41it/s]
 57%|█████▋    | 210074/371472 [6:00:16<13:13:36,  3.39it/s]
 57%|█████▋    | 210075/371472 [6:00:16<13:11:36,  3.40it/s]
 57%|█████▋    | 210076/371472 [6:00:16<13:33:51,  3.31it/s]
 57%|█████▋    | 210077/371472 [6:00:16<13:13:47,  3.39it/s]
 57%|█████▋    | 210078/371472 [6:00:17<14:36:53,  3.07it/s]
 57%|█████▋    | 210079/371472 [6:00:17<14:13:35,  3.15it/s]
 57%|█████▋    | 210080/371472 [6:00:17<13:54:50,  3.22it/s]
                                                            
{'loss': 2.829, 'learning_rate': 4.912301493244844e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210080/371472 [6:00:17<13:54:50,  3.22it/s]
 57%|█████▋    | 210081/371472 [6:00:18<13:21:11,  3.36it/s]
 57%|█████▋    | 210082/371472 [6:00:18<13:05:36,  3.42it/s]
 57%|█████▋    | 210083/371472 [6:00:18<13:17:46,  3.37it/s]
 57%|█████▋    | 210084/371472 [6:00:19<13:18:08,  3.37it/s]
 57%|█████▋    | 210085/371472 [6:00:19<13:16:55,  3.38it/s]
 57%|█████▋    | 210086/371472 [6:00:19<13:21:34,  3.36it/s]
 57%|█████▋    | 210087/371472 [6:00:19<13:18:18,  3.37it/s]
 57%|█████▋    | 210088/371472 [6:00:20<13:10:11,  3.40it/s]
 57%|█████▋    | 210089/371472 [6:00:20<13:04:56,  3.43it/s]
 57%|█████▋    | 210090/371472 [6:00:20<12:57:45,  3.46it/s]
 57%|█████▋    | 210091/371472 [6:00:21<12:54:06,  3.47it/s]
 57%|█████▋    | 210092/371472 [6:00:21<13:20:53,  3.36it/s]
 57%|█████▋    | 210093/371472 [6:00:21<14:12:58,  3.15it/s]
 57%|█████▋    | 210094/371472 [6:00:22<13:47:09,  3.25it/s]
 57%|█████▋    | 210095/371472 [6:00:22<13:25:34,  3.34it/s]
 57%|█████▋    | 210096/371472 [6:00:22<13:17:35,  3.37it/s]
 57%|█████▋    | 210097/371472 [6:00:22<13:13:47,  3.39it/s]
 57%|█████▋    | 210098/371472 [6:00:23<13:29:32,  3.32it/s]
 57%|█████▋    | 210099/371472 [6:00:23<13:27:19,  3.33it/s]
 57%|█████▋    | 210100/371472 [6:00:23<14:44:22,  3.04it/s]
                                                            
{'loss': 2.8775, 'learning_rate': 4.911816673490056e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210100/371472 [6:00:23<14:44:22,  3.04it/s]
 57%|█████▋    | 210101/371472 [6:00:24<14:33:09,  3.08it/s]
 57%|█████▋    | 210102/371472 [6:00:24<14:07:52,  3.17it/s]
 57%|█████▋    | 210103/371472 [6:00:24<13:38:49,  3.28it/s]
 57%|█████▋    | 210104/371472 [6:00:25<13:31:02,  3.32it/s]
 57%|█████▋    | 210105/371472 [6:00:25<13:33:00,  3.31it/s]
 57%|█████▋    | 210106/371472 [6:00:25<13:21:13,  3.36it/s]
 57%|█████▋    | 210107/371472 [6:00:26<13:48:38,  3.25it/s]
 57%|█████▋    | 210108/371472 [6:00:26<13:39:33,  3.28it/s]
 57%|█████▋    | 210109/371472 [6:00:26<14:49:59,  3.02it/s]
 57%|█████▋    | 210110/371472 [6:00:27<14:25:43,  3.11it/s]
 57%|█████▋    | 210111/371472 [6:00:27<13:57:27,  3.21it/s]
 57%|█████▋    | 210112/371472 [6:00:27<13:31:59,  3.31it/s]
 57%|█████▋    | 210113/371472 [6:00:27<13:39:01,  3.28it/s]
 57%|█████▋    | 210114/371472 [6:00:28<14:04:45,  3.18it/s]
 57%|█████▋    | 210115/371472 [6:00:28<13:26:09,  3.34it/s]
 57%|█████▋    | 210116/371472 [6:00:28<13:15:43,  3.38it/s]
 57%|█████▋    | 210117/371472 [6:00:29<13:00:57,  3.44it/s]
 57%|█████▋    | 210118/371472 [6:00:29<13:15:27,  3.38it/s]
 57%|█████▋    | 210119/371472 [6:00:29<14:33:46,  3.08it/s]
 57%|█████▋    | 210120/371472 [6:00:30<14:02:00,  3.19it/s]
                                                            
{'loss': 2.664, 'learning_rate': 4.911331853735266e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210120/371472 [6:00:30<14:02:00,  3.19it/s]
 57%|█████▋    | 210121/371472 [6:00:30<14:30:09,  3.09it/s]
 57%|█████▋    | 210122/371472 [6:00:30<14:02:24,  3.19it/s]
 57%|█████▋    | 210123/371472 [6:00:30<13:33:28,  3.31it/s]
 57%|█████▋    | 210124/371472 [6:00:31<13:20:53,  3.36it/s]
 57%|█████▋    | 210125/371472 [6:00:31<13:41:23,  3.27it/s]
 57%|█████▋    | 210126/371472 [6:00:31<13:28:32,  3.33it/s]
 57%|█████▋    | 210127/371472 [6:00:32<14:09:18,  3.17it/s]
 57%|█████▋    | 210128/371472 [6:00:32<14:47:54,  3.03it/s]
 57%|█████▋    | 210129/371472 [6:00:32<14:08:34,  3.17it/s]
 57%|█████▋    | 210130/371472 [6:00:33<13:41:57,  3.27it/s]
 57%|█████▋    | 210131/371472 [6:00:33<13:23:18,  3.35it/s]
 57%|█████▋    | 210132/371472 [6:00:33<13:21:40,  3.35it/s]
 57%|█████▋    | 210133/371472 [6:00:34<13:16:40,  3.38it/s]
 57%|█████▋    | 210134/371472 [6:00:34<13:02:51,  3.43it/s]
 57%|█████▋    | 210135/371472 [6:00:34<13:06:42,  3.42it/s]
 57%|█████▋    | 210136/371472 [6:00:34<13:17:34,  3.37it/s]
 57%|█████▋    | 210137/371472 [6:00:35<13:14:34,  3.38it/s]
 57%|█████▋    | 210138/371472 [6:00:35<13:01:44,  3.44it/s]
 57%|█████▋    | 210139/371472 [6:00:35<13:05:14,  3.42it/s]
 57%|█████▋    | 210140/371472 [6:00:36<13:08:44,  3.41it/s]
                                                            
{'loss': 2.7338, 'learning_rate': 4.910847033980478e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210140/371472 [6:00:36<13:08:44,  3.41it/s]
 57%|█████▋    | 210141/371472 [6:00:36<13:24:42,  3.34it/s]
 57%|█████▋    | 210142/371472 [6:00:36<13:04:40,  3.43it/s]
 57%|█████▋    | 210143/371472 [6:00:36<12:58:57,  3.45it/s]
 57%|█████▋    | 210144/371472 [6:00:37<12:48:18,  3.50it/s]
 57%|█████▋    | 210145/371472 [6:00:37<12:54:11,  3.47it/s]
 57%|█████▋    | 210146/371472 [6:00:37<13:21:21,  3.36it/s]
 57%|█████▋    | 210147/371472 [6:00:38<13:56:38,  3.21it/s]
 57%|█████▋    | 210148/371472 [6:00:38<13:36:14,  3.29it/s]
 57%|█████▋    | 210149/371472 [6:00:38<13:45:57,  3.26it/s]
 57%|█████▋    | 210150/371472 [6:00:39<13:37:28,  3.29it/s]
 57%|█████▋    | 210151/371472 [6:00:39<13:14:58,  3.38it/s]
 57%|█████▋    | 210152/371472 [6:00:39<13:17:57,  3.37it/s]
 57%|█████▋    | 210153/371472 [6:00:39<13:36:59,  3.29it/s]
 57%|█████▋    | 210154/371472 [6:00:40<13:54:16,  3.22it/s]
 57%|█████▋    | 210155/371472 [6:00:40<13:36:50,  3.29it/s]
 57%|█████▋    | 210156/371472 [6:00:40<14:24:00,  3.11it/s]
 57%|█████▋    | 210157/371472 [6:00:41<13:40:47,  3.28it/s]
 57%|█████▋    | 210158/371472 [6:00:41<14:02:40,  3.19it/s]
 57%|█████▋    | 210159/371472 [6:00:41<13:28:10,  3.33it/s]
 57%|█████▋    | 210160/371472 [6:00:42<13:24:57,  3.34it/s]
                                                            
{'loss': 2.6413, 'learning_rate': 4.910362214225689e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210160/371472 [6:00:42<13:24:57,  3.34it/s]
 57%|█████▋    | 210161/371472 [6:00:42<13:06:09,  3.42it/s]
 57%|█████▋    | 210162/371472 [6:00:42<12:55:25,  3.47it/s]
 57%|█████▋    | 210163/371472 [6:00:43<13:30:21,  3.32it/s]
 57%|█████▋    | 210164/371472 [6:00:43<13:11:35,  3.40it/s]
 57%|█████▋    | 210165/371472 [6:00:43<14:09:15,  3.17it/s]
 57%|█████▋    | 210166/371472 [6:00:43<14:19:39,  3.13it/s]
 57%|█████▋    | 210167/371472 [6:00:44<14:09:47,  3.16it/s]
 57%|█████▋    | 210168/371472 [6:00:44<13:27:52,  3.33it/s]
 57%|█████▋    | 210169/371472 [6:00:44<13:01:15,  3.44it/s]
 57%|█████▋    | 210170/371472 [6:00:45<13:03:41,  3.43it/s]
 57%|█████▋    | 210171/371472 [6:00:45<13:13:49,  3.39it/s]
 57%|█████▋    | 210172/371472 [6:00:45<13:01:27,  3.44it/s]
 57%|█████▋    | 210173/371472 [6:00:45<13:04:48,  3.43it/s]
 57%|█████▋    | 210174/371472 [6:00:46<12:49:37,  3.49it/s]
 57%|█████▋    | 210175/371472 [6:00:46<13:03:34,  3.43it/s]
 57%|█████▋    | 210176/371472 [6:00:46<13:11:18,  3.40it/s]
 57%|█████▋    | 210177/371472 [6:00:47<13:25:40,  3.34it/s]
 57%|█████▋    | 210178/371472 [6:00:47<13:18:39,  3.37it/s]
 57%|█████▋    | 210179/371472 [6:00:47<13:14:23,  3.38it/s]
 57%|█████▋    | 210180/371472 [6:00:48<13:35:24,  3.30it/s]
                                                            
{'loss': 2.7625, 'learning_rate': 4.9098773944709e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210180/371472 [6:00:48<13:35:24,  3.30it/s]
 57%|█████▋    | 210181/371472 [6:00:48<13:18:13,  3.37it/s]
 57%|█████▋    | 210182/371472 [6:00:48<13:10:22,  3.40it/s]
 57%|█████▋    | 210183/371472 [6:00:49<14:25:18,  3.11it/s]
 57%|█████▋    | 210184/371472 [6:00:49<13:47:00,  3.25it/s]
 57%|█████▋    | 210185/371472 [6:00:49<13:49:03,  3.24it/s]
 57%|█████▋    | 210186/371472 [6:00:49<13:23:04,  3.35it/s]
 57%|█████▋    | 210187/371472 [6:00:50<13:16:29,  3.37it/s]
 57%|█████▋    | 210188/371472 [6:00:50<14:10:36,  3.16it/s]
 57%|█████▋    | 210189/371472 [6:00:50<14:10:37,  3.16it/s]
 57%|█████▋    | 210190/371472 [6:00:51<14:09:46,  3.16it/s]
 57%|█████▋    | 210191/371472 [6:00:51<14:45:09,  3.04it/s]
 57%|█████▋    | 210192/371472 [6:00:51<14:18:35,  3.13it/s]
 57%|█████▋    | 210193/371472 [6:00:52<14:33:34,  3.08it/s]
 57%|█████▋    | 210194/371472 [6:00:52<14:21:10,  3.12it/s]
 57%|█████▋    | 210195/371472 [6:00:52<14:37:24,  3.06it/s]
 57%|█████▋    | 210196/371472 [6:00:53<15:01:58,  2.98it/s]
 57%|█████▋    | 210197/371472 [6:00:53<14:10:32,  3.16it/s]
 57%|█████▋    | 210198/371472 [6:00:53<13:49:32,  3.24it/s]
 57%|█████▋    | 210199/371472 [6:00:54<13:31:04,  3.31it/s]
 57%|█████▋    | 210200/371472 [6:00:54<13:29:43,  3.32it/s]
                                                            
{'loss': 2.7116, 'learning_rate': 4.90939257471611e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210200/371472 [6:00:54<13:29:43,  3.32it/s]
 57%|█████▋    | 210201/371472 [6:00:54<13:46:18,  3.25it/s]
 57%|█████▋    | 210202/371472 [6:00:54<13:53:18,  3.23it/s]
 57%|█████▋    | 210203/371472 [6:00:55<13:28:39,  3.32it/s]
 57%|█████▋    | 210204/371472 [6:00:55<13:20:04,  3.36it/s]
 57%|█████▋    | 210205/371472 [6:00:55<13:40:58,  3.27it/s]
 57%|█████▋    | 210206/371472 [6:00:56<13:56:00,  3.22it/s]
 57%|█████▋    | 210207/371472 [6:00:56<13:27:48,  3.33it/s]
 57%|█████▋    | 210208/371472 [6:00:56<13:15:39,  3.38it/s]
 57%|█████▋    | 210209/371472 [6:00:57<13:01:14,  3.44it/s]
 57%|█████▋    | 210210/371472 [6:00:57<13:22:43,  3.35it/s]
 57%|█████▋    | 210211/371472 [6:00:57<13:34:58,  3.30it/s]
 57%|█████▋    | 210212/371472 [6:00:58<14:12:36,  3.15it/s]
 57%|█████▋    | 210213/371472 [6:00:58<13:46:48,  3.25it/s]
 57%|█████▋    | 210214/371472 [6:00:58<13:26:48,  3.33it/s]
 57%|█████▋    | 210215/371472 [6:00:58<12:58:16,  3.45it/s]
 57%|█████▋    | 210216/371472 [6:00:59<13:04:30,  3.43it/s]
 57%|█████▋    | 210217/371472 [6:00:59<13:15:29,  3.38it/s]
 57%|█████▋    | 210218/371472 [6:00:59<13:45:21,  3.26it/s]
 57%|█████▋    | 210219/371472 [6:01:00<13:30:08,  3.32it/s]
 57%|█████▋    | 210220/371472 [6:01:00<13:59:10,  3.20it/s]
                                                            
{'loss': 2.7952, 'learning_rate': 4.908907754961322e-07, 'epoch': 9.05}
+
 57%|█████▋    | 210220/371472 [6:01:00<13:59:10,  3.20it/s]
 57%|█████▋    | 210221/371472 [6:01:00<14:35:08,  3.07it/s]
 57%|█████▋    | 210222/371472 [6:01:01<13:57:54,  3.21it/s]
 57%|█████▋    | 210223/371472 [6:01:01<14:27:51,  3.10it/s]
 57%|█████▋    | 210224/371472 [6:01:01<13:57:00,  3.21it/s]
 57%|█████▋    | 210225/371472 [6:01:01<13:58:05,  3.21it/s]
 57%|█████▋    | 210226/371472 [6:01:02<14:15:30,  3.14it/s]
 57%|█████▋    | 210227/371472 [6:01:02<14:02:13,  3.19it/s]
 57%|█████▋    | 210228/371472 [6:01:02<13:53:14,  3.23it/s]
 57%|█████▋    | 210229/371472 [6:01:03<13:22:52,  3.35it/s]
 57%|█████▋    | 210230/371472 [6:01:03<13:21:55,  3.35it/s]
 57%|█████▋    | 210231/371472 [6:01:03<13:04:50,  3.42it/s]
 57%|█████▋    | 210232/371472 [6:01:04<12:59:33,  3.45it/s]
 57%|█████▋    | 210233/371472 [6:01:04<13:21:39,  3.35it/s]
 57%|█████▋    | 210234/371472 [6:01:04<13:56:30,  3.21it/s]
 57%|█████▋    | 210235/371472 [6:01:05<14:13:13,  3.15it/s]
 57%|█████▋    | 210236/371472 [6:01:05<13:31:05,  3.31it/s]
 57%|█████▋    | 210237/371472 [6:01:05<14:27:35,  3.10it/s]
 57%|█████▋    | 210238/371472 [6:01:06<14:58:34,  2.99it/s]
 57%|█████▋    | 210239/371472 [6:01:06<14:30:57,  3.09it/s]
 57%|█████▋    | 210240/371472 [6:01:06<13:51:47,  3.23it/s]
                                                            
{'loss': 2.7026, 'learning_rate': 4.908422935206533e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210240/371472 [6:01:06<13:51:47,  3.23it/s]
 57%|█████▋    | 210241/371472 [6:01:06<13:52:28,  3.23it/s]
 57%|█████▋    | 210242/371472 [6:01:07<13:34:52,  3.30it/s]
 57%|█████▋    | 210243/371472 [6:01:07<13:26:45,  3.33it/s]
 57%|█████▋    | 210244/371472 [6:01:07<13:44:11,  3.26it/s]
 57%|█████▋    | 210245/371472 [6:01:08<13:29:50,  3.32it/s]
 57%|█████▋    | 210246/371472 [6:01:08<14:00:12,  3.20it/s]
 57%|█████▋    | 210247/371472 [6:01:08<13:47:17,  3.25it/s]
 57%|█████▋    | 210248/371472 [6:01:09<14:35:42,  3.07it/s]
 57%|█████▋    | 210249/371472 [6:01:09<14:23:54,  3.11it/s]
 57%|█████▋    | 210250/371472 [6:01:09<15:01:10,  2.98it/s]
 57%|█████▋    | 210251/371472 [6:01:10<14:26:17,  3.10it/s]
 57%|█████▋    | 210252/371472 [6:01:10<13:54:22,  3.22it/s]
 57%|█████▋    | 210253/371472 [6:01:10<13:39:36,  3.28it/s]
 57%|█████▋    | 210254/371472 [6:01:11<14:39:03,  3.06it/s]
 57%|█████▋    | 210255/371472 [6:01:11<14:33:42,  3.08it/s]
 57%|█████▋    | 210256/371472 [6:01:11<14:07:51,  3.17it/s]
 57%|█████▋    | 210257/371472 [6:01:11<13:48:59,  3.24it/s]
 57%|█████▋    | 210258/371472 [6:01:12<13:35:20,  3.30it/s]
 57%|█████▋    | 210259/371472 [6:01:12<13:14:28,  3.38it/s]
 57%|█████▋    | 210260/371472 [6:01:12<13:25:59,  3.33it/s]
                                                            
{'loss': 2.7441, 'learning_rate': 4.907938115451745e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210260/371472 [6:01:12<13:25:59,  3.33it/s]
 57%|█████▋    | 210261/371472 [6:01:13<13:38:17,  3.28it/s]
 57%|█████▋    | 210262/371472 [6:01:13<13:22:30,  3.35it/s]
 57%|█████▋    | 210263/371472 [6:01:13<13:27:02,  3.33it/s]
 57%|█████▋    | 210264/371472 [6:01:14<13:21:09,  3.35it/s]
 57%|█████▋    | 210265/371472 [6:01:14<13:06:43,  3.42it/s]
 57%|█████▋    | 210266/371472 [6:01:14<13:08:25,  3.41it/s]
 57%|█████▋    | 210267/371472 [6:01:14<14:16:34,  3.14it/s]
 57%|█████▋    | 210268/371472 [6:01:15<13:59:17,  3.20it/s]
 57%|█████▋    | 210269/371472 [6:01:15<13:50:55,  3.23it/s]
 57%|█████▋    | 210270/371472 [6:01:15<13:42:38,  3.27it/s]
 57%|█████▋    | 210271/371472 [6:01:16<13:35:51,  3.29it/s]
 57%|█████▋    | 210272/371472 [6:01:16<13:52:03,  3.23it/s]
 57%|█████▋    | 210273/371472 [6:01:16<14:20:09,  3.12it/s]
 57%|█████▋    | 210274/371472 [6:01:17<14:20:07,  3.12it/s]
 57%|█████▋    | 210275/371472 [6:01:17<13:56:24,  3.21it/s]
 57%|█████▋    | 210276/371472 [6:01:17<13:38:01,  3.28it/s]
 57%|█████▋    | 210277/371472 [6:01:18<14:01:40,  3.19it/s]
 57%|█████▋    | 210278/371472 [6:01:18<13:32:24,  3.31it/s]
 57%|█████▋    | 210279/371472 [6:01:18<14:42:41,  3.04it/s]
 57%|█████▋    | 210280/371472 [6:01:19<14:08:10,  3.17it/s]
                                                            
{'loss': 2.8, 'learning_rate': 4.907453295696955e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210280/371472 [6:01:19<14:08:10,  3.17it/s]
 57%|█████▋    | 210281/371472 [6:01:19<13:48:55,  3.24it/s]
 57%|█████▋    | 210282/371472 [6:01:19<13:32:57,  3.30it/s]
 57%|█████▋    | 210283/371472 [6:01:19<13:44:05,  3.26it/s]
 57%|█████▋    | 210284/371472 [6:01:20<13:36:49,  3.29it/s]
 57%|█████▋    | 210285/371472 [6:01:20<13:39:23,  3.28it/s]
 57%|█████▋    | 210286/371472 [6:01:20<13:56:23,  3.21it/s]
 57%|█████▋    | 210287/371472 [6:01:21<13:20:01,  3.36it/s]
 57%|█████▋    | 210288/371472 [6:01:21<13:01:45,  3.44it/s]
 57%|█████▋    | 210289/371472 [6:01:21<12:44:41,  3.51it/s]
 57%|█████▋    | 210290/371472 [6:01:22<13:21:04,  3.35it/s]
 57%|█████▋    | 210291/371472 [6:01:22<13:53:10,  3.22it/s]
 57%|█████▋    | 210292/371472 [6:01:22<13:21:48,  3.35it/s]
 57%|█████▋    | 210293/371472 [6:01:22<13:13:08,  3.39it/s]
 57%|█████▋    | 210294/371472 [6:01:23<13:38:21,  3.28it/s]
 57%|█████▋    | 210295/371472 [6:01:23<13:23:37,  3.34it/s]
 57%|█████▋    | 210296/371472 [6:01:23<13:23:28,  3.34it/s]
 57%|█████▋    | 210297/371472 [6:01:24<13:57:52,  3.21it/s]
 57%|█████▋    | 210298/371472 [6:01:24<13:31:29,  3.31it/s]
 57%|█████▋    | 210299/371472 [6:01:24<13:31:13,  3.31it/s]
 57%|█████▋    | 210300/371472 [6:01:25<14:28:27,  3.09it/s]
                                                            
{'loss': 2.6163, 'learning_rate': 4.906968475942166e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210300/371472 [6:01:25<14:28:27,  3.09it/s]
 57%|█████▋    | 210301/371472 [6:01:25<14:26:02,  3.10it/s]
 57%|█████▋    | 210302/371472 [6:01:25<14:10:12,  3.16it/s]
 57%|█████▋    | 210303/371472 [6:01:26<14:47:00,  3.03it/s]
 57%|█████▋    | 210304/371472 [6:01:26<13:53:27,  3.22it/s]
 57%|█████▋    | 210305/371472 [6:01:26<13:30:44,  3.31it/s]
 57%|█████▋    | 210306/371472 [6:01:26<13:20:19,  3.36it/s]
 57%|█████▋    | 210307/371472 [6:01:27<13:29:50,  3.32it/s]
 57%|█████▋    | 210308/371472 [6:01:27<13:37:02,  3.29it/s]
 57%|█████▋    | 210309/371472 [6:01:27<13:34:11,  3.30it/s]
 57%|█████▋    | 210310/371472 [6:01:28<13:35:12,  3.29it/s]
 57%|█████▋    | 210311/371472 [6:01:28<13:20:27,  3.36it/s]
 57%|█████▋    | 210312/371472 [6:01:28<13:29:44,  3.32it/s]
 57%|█████▋    | 210313/371472 [6:01:29<13:48:17,  3.24it/s]
 57%|█████▋    | 210314/371472 [6:01:29<13:49:35,  3.24it/s]
 57%|█████▋    | 210315/371472 [6:01:29<14:02:57,  3.19it/s]
 57%|█████▋    | 210316/371472 [6:01:30<14:51:18,  3.01it/s]
 57%|█████▋    | 210317/371472 [6:01:30<14:30:34,  3.09it/s]
 57%|█████▋    | 210318/371472 [6:01:30<14:01:14,  3.19it/s]
 57%|█████▋    | 210319/371472 [6:01:31<14:24:01,  3.11it/s]
 57%|█████▋    | 210320/371472 [6:01:31<14:33:38,  3.07it/s]
                                                            
{'loss': 2.8324, 'learning_rate': 4.906483656187377e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210320/371472 [6:01:31<14:33:38,  3.07it/s]
 57%|█████▋    | 210321/371472 [6:01:31<13:50:54,  3.23it/s]
 57%|█████▋    | 210322/371472 [6:01:31<13:28:14,  3.32it/s]
 57%|█████▋    | 210323/371472 [6:01:32<13:08:34,  3.41it/s]
 57%|█████▋    | 210324/371472 [6:01:32<12:48:01,  3.50it/s]
 57%|█████▋    | 210325/371472 [6:01:32<12:53:23,  3.47it/s]
 57%|█████▋    | 210326/371472 [6:01:33<13:55:57,  3.21it/s]
 57%|█████▋    | 210327/371472 [6:01:33<13:31:27,  3.31it/s]
 57%|█████▋    | 210328/371472 [6:01:33<13:10:06,  3.40it/s]
 57%|█████▋    | 210329/371472 [6:01:33<12:51:13,  3.48it/s]
 57%|█████▋    | 210330/371472 [6:01:34<12:47:32,  3.50it/s]
 57%|█████▋    | 210331/371472 [6:01:34<12:49:01,  3.49it/s]
 57%|█████▋    | 210332/371472 [6:01:34<12:36:02,  3.55it/s]
 57%|█████▋    | 210333/371472 [6:01:35<12:29:42,  3.58it/s]
 57%|█████▋    | 210334/371472 [6:01:35<12:17:11,  3.64it/s]
 57%|█████▋    | 210335/371472 [6:01:35<12:14:48,  3.65it/s]
 57%|█████▋    | 210336/371472 [6:01:35<12:55:01,  3.47it/s]
 57%|█████▋    | 210337/371472 [6:01:36<12:42:38,  3.52it/s]
 57%|█████▋    | 210338/371472 [6:01:36<12:54:24,  3.47it/s]
 57%|█████▋    | 210339/371472 [6:01:36<12:43:13,  3.52it/s]
 57%|█████▋    | 210340/371472 [6:01:37<12:39:06,  3.54it/s]
                                                            
{'loss': 2.8528, 'learning_rate': 4.905998836432587e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210340/371472 [6:01:37<12:39:06,  3.54it/s]
 57%|█████▋    | 210341/371472 [6:01:37<12:59:15,  3.45it/s]
 57%|█████▋    | 210342/371472 [6:01:37<13:08:51,  3.40it/s]
 57%|█████▋    | 210343/371472 [6:01:38<14:39:10,  3.05it/s]
 57%|█████▋    | 210344/371472 [6:01:38<14:08:03,  3.17it/s]
 57%|█████▋    | 210345/371472 [6:01:38<13:48:31,  3.24it/s]
 57%|█████▋    | 210346/371472 [6:01:38<13:33:09,  3.30it/s]
 57%|█████▋    | 210347/371472 [6:01:39<13:25:25,  3.33it/s]
 57%|█████▋    | 210348/371472 [6:01:39<13:48:32,  3.24it/s]
 57%|█████▋    | 210349/371472 [6:01:39<14:07:59,  3.17it/s]
 57%|█████▋    | 210350/371472 [6:01:40<13:35:09,  3.29it/s]
 57%|█████▋    | 210351/371472 [6:01:40<13:15:09,  3.38it/s]
 57%|█████▋    | 210352/371472 [6:01:40<13:20:06,  3.36it/s]
 57%|█████▋    | 210353/371472 [6:01:41<13:13:56,  3.38it/s]
 57%|█████▋    | 210354/371472 [6:01:41<13:05:51,  3.42it/s]
 57%|█████▋    | 210355/371472 [6:01:41<12:45:59,  3.51it/s]
 57%|█████▋    | 210356/371472 [6:01:41<13:21:37,  3.35it/s]
 57%|█████▋    | 210357/371472 [6:01:42<13:25:57,  3.33it/s]
 57%|█████▋    | 210358/371472 [6:01:42<13:55:00,  3.22it/s]
 57%|█████▋    | 210359/371472 [6:01:42<14:32:51,  3.08it/s]
 57%|█████▋    | 210360/371472 [6:01:43<14:07:06,  3.17it/s]
                                                            
{'loss': 2.7707, 'learning_rate': 4.905514016677799e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210360/371472 [6:01:43<14:07:06,  3.17it/s]
 57%|█████▋    | 210361/371472 [6:01:43<13:56:37,  3.21it/s]
 57%|█████▋    | 210362/371472 [6:01:43<13:57:02,  3.21it/s]
 57%|█████▋    | 210363/371472 [6:01:44<13:37:42,  3.28it/s]
 57%|█████▋    | 210364/371472 [6:01:44<13:11:33,  3.39it/s]
 57%|█████▋    | 210365/371472 [6:01:44<13:03:08,  3.43it/s]
 57%|█████▋    | 210366/371472 [6:01:44<12:56:02,  3.46it/s]
 57%|█████▋    | 210367/371472 [6:01:45<12:52:26,  3.48it/s]
 57%|█████▋    | 210368/371472 [6:01:45<13:00:41,  3.44it/s]
 57%|█████▋    | 210369/371472 [6:01:45<13:27:17,  3.33it/s]
 57%|█████▋    | 210370/371472 [6:01:46<13:02:25,  3.43it/s]
 57%|█████▋    | 210371/371472 [6:01:46<13:01:25,  3.44it/s]
 57%|█████▋    | 210372/371472 [6:01:46<13:03:07,  3.43it/s]
 57%|█████▋    | 210373/371472 [6:01:46<12:52:27,  3.48it/s]
 57%|█████▋    | 210374/371472 [6:01:47<13:03:33,  3.43it/s]
 57%|█████▋    | 210375/371472 [6:01:47<12:56:19,  3.46it/s]
 57%|█████▋    | 210376/371472 [6:01:47<13:01:45,  3.43it/s]
 57%|█████▋    | 210377/371472 [6:01:48<14:15:28,  3.14it/s]
 57%|█████▋    | 210378/371472 [6:01:48<13:53:30,  3.22it/s]
 57%|█████▋    | 210379/371472 [6:01:48<13:59:10,  3.20it/s]
 57%|█████▋    | 210380/371472 [6:01:49<13:46:50,  3.25it/s]
                                                            
{'loss': 2.7224, 'learning_rate': 4.90502919692301e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210380/371472 [6:01:49<13:46:50,  3.25it/s]
 57%|█████▋    | 210381/371472 [6:01:49<13:25:02,  3.34it/s]
 57%|█████▋    | 210382/371472 [6:01:49<13:03:08,  3.43it/s]
 57%|█████▋    | 210383/371472 [6:01:50<13:08:46,  3.40it/s]
 57%|█████▋    | 210384/371472 [6:01:50<13:01:38,  3.43it/s]
 57%|█████▋    | 210385/371472 [6:01:50<12:49:13,  3.49it/s]
 57%|█████▋    | 210386/371472 [6:01:50<13:08:20,  3.41it/s]
 57%|█████▋    | 210387/371472 [6:01:51<13:21:26,  3.35it/s]
 57%|█████▋    | 210388/371472 [6:01:51<13:13:26,  3.38it/s]
 57%|█████▋    | 210389/371472 [6:01:51<13:16:43,  3.37it/s]
 57%|█████▋    | 210390/371472 [6:01:52<12:54:02,  3.47it/s]
 57%|█████▋    | 210391/371472 [6:01:52<12:47:05,  3.50it/s]
 57%|█████▋    | 210392/371472 [6:01:52<12:53:03,  3.47it/s]
 57%|█████▋    | 210393/371472 [6:01:52<12:50:32,  3.48it/s]
 57%|█████▋    | 210394/371472 [6:01:53<13:14:33,  3.38it/s]
 57%|█████▋    | 210395/371472 [6:01:53<13:04:01,  3.42it/s]
 57%|█████▋    | 210396/371472 [6:01:53<13:09:46,  3.40it/s]
 57%|█████▋    | 210397/371472 [6:01:54<13:02:24,  3.43it/s]
 57%|█████▋    | 210398/371472 [6:01:54<13:31:37,  3.31it/s]
 57%|█████▋    | 210399/371472 [6:01:54<13:28:13,  3.32it/s]
 57%|█████▋    | 210400/371472 [6:01:55<13:38:13,  3.28it/s]
                                                            
{'loss': 2.8389, 'learning_rate': 4.904544377168222e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210400/371472 [6:01:55<13:38:13,  3.28it/s]
 57%|█████▋    | 210401/371472 [6:01:55<13:42:45,  3.26it/s]
 57%|█████▋    | 210402/371472 [6:01:55<13:28:12,  3.32it/s]
 57%|█████▋    | 210403/371472 [6:01:55<13:45:59,  3.25it/s]
 57%|█████▋    | 210404/371472 [6:01:56<13:37:41,  3.28it/s]
 57%|█████▋    | 210405/371472 [6:01:56<14:51:07,  3.01it/s]
 57%|█████▋    | 210406/371472 [6:01:56<14:52:32,  3.01it/s]
 57%|█████▋    | 210407/371472 [6:01:57<14:06:10,  3.17it/s]
 57%|█████▋    | 210408/371472 [6:01:57<13:33:26,  3.30it/s]
 57%|█████▋    | 210409/371472 [6:01:57<13:11:34,  3.39it/s]
 57%|█████▋    | 210410/371472 [6:01:58<13:09:30,  3.40it/s]
 57%|█████▋    | 210411/371472 [6:01:58<13:16:53,  3.37it/s]
 57%|█████▋    | 210412/371472 [6:01:58<13:14:00,  3.38it/s]
 57%|█████▋    | 210413/371472 [6:01:58<13:05:06,  3.42it/s]
 57%|█████▋    | 210414/371472 [6:01:59<13:18:15,  3.36it/s]
 57%|█████▋    | 210415/371472 [6:01:59<12:46:34,  3.50it/s]
 57%|█████▋    | 210416/371472 [6:01:59<12:43:38,  3.52it/s]
 57%|█████▋    | 210417/371472 [6:02:00<13:10:35,  3.40it/s]
 57%|█████▋    | 210418/371472 [6:02:00<13:35:19,  3.29it/s]
 57%|█████▋    | 210419/371472 [6:02:00<13:34:50,  3.29it/s]
 57%|█████▋    | 210420/371472 [6:02:01<13:59:54,  3.20it/s]
                                                            
{'loss': 2.7061, 'learning_rate': 4.904059557413432e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210420/371472 [6:02:01<13:59:54,  3.20it/s]
 57%|█████▋    | 210421/371472 [6:02:01<14:32:06,  3.08it/s]
 57%|█████▋    | 210422/371472 [6:02:01<13:49:41,  3.24it/s]
 57%|█████▋    | 210423/371472 [6:02:02<13:49:09,  3.24it/s]
 57%|█████▋    | 210424/371472 [6:02:02<13:23:55,  3.34it/s]
 57%|█████▋    | 210425/371472 [6:02:02<13:07:58,  3.41it/s]
 57%|█████▋    | 210426/371472 [6:02:02<12:53:52,  3.47it/s]
 57%|█████▋    | 210427/371472 [6:02:03<13:34:00,  3.30it/s]
 57%|█████▋    | 210428/371472 [6:02:03<14:01:47,  3.19it/s]
 57%|█████▋    | 210429/371472 [6:02:03<13:34:14,  3.30it/s]
 57%|█████▋    | 210430/371472 [6:02:04<13:23:21,  3.34it/s]
 57%|█████▋    | 210431/371472 [6:02:04<13:10:25,  3.40it/s]
 57%|█████▋    | 210432/371472 [6:02:04<13:40:03,  3.27it/s]
 57%|█████▋    | 210433/371472 [6:02:05<14:01:33,  3.19it/s]
 57%|█████▋    | 210434/371472 [6:02:05<13:12:12,  3.39it/s]
 57%|█████▋    | 210435/371472 [6:02:05<13:23:08,  3.34it/s]
 57%|█████▋    | 210436/371472 [6:02:05<13:08:24,  3.40it/s]
 57%|█████▋    | 210437/371472 [6:02:06<13:00:34,  3.44it/s]
 57%|█████▋    | 210438/371472 [6:02:06<13:12:59,  3.38it/s]
 57%|█████▋    | 210439/371472 [6:02:06<13:01:18,  3.44it/s]
 57%|█████▋    | 210440/371472 [6:02:07<12:49:18,  3.49it/s]
                                                            
{'loss': 2.7977, 'learning_rate': 4.903574737658643e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210440/371472 [6:02:07<12:49:18,  3.49it/s]
 57%|█████▋    | 210441/371472 [6:02:07<12:36:06,  3.55it/s]
 57%|█████▋    | 210442/371472 [6:02:07<12:40:13,  3.53it/s]
 57%|█████▋    | 210443/371472 [6:02:07<12:51:12,  3.48it/s]
 57%|█████▋    | 210444/371472 [6:02:08<12:57:02,  3.45it/s]
 57%|█████▋    | 210445/371472 [6:02:08<13:14:45,  3.38it/s]
 57%|█████▋    | 210446/371472 [6:02:08<14:32:26,  3.08it/s]
 57%|█████▋    | 210447/371472 [6:02:09<14:02:07,  3.19it/s]
 57%|█████▋    | 210448/371472 [6:02:09<13:57:13,  3.21it/s]
 57%|█████▋    | 210449/371472 [6:02:09<13:29:46,  3.31it/s]
 57%|█████▋    | 210450/371472 [6:02:10<13:15:55,  3.37it/s]
 57%|█████▋    | 210451/371472 [6:02:10<13:14:02,  3.38it/s]
 57%|█████▋    | 210452/371472 [6:02:10<13:27:47,  3.32it/s]
 57%|█████▋    | 210453/371472 [6:02:10<13:02:38,  3.43it/s]
 57%|█████▋    | 210454/371472 [6:02:11<13:15:36,  3.37it/s]
 57%|█████▋    | 210455/371472 [6:02:11<13:12:41,  3.39it/s]
 57%|█████▋    | 210456/371472 [6:02:11<13:12:05,  3.39it/s]
 57%|█████▋    | 210457/371472 [6:02:12<13:45:04,  3.25it/s]
 57%|█████▋    | 210458/371472 [6:02:12<13:35:15,  3.29it/s]
 57%|█████▋    | 210459/371472 [6:02:12<13:41:51,  3.27it/s]
 57%|█████▋    | 210460/371472 [6:02:13<13:39:39,  3.27it/s]
                                                            
{'loss': 2.992, 'learning_rate': 4.903089917903854e-07, 'epoch': 9.06}
+
 57%|█████▋    | 210460/371472 [6:02:13<13:39:39,  3.27it/s]
 57%|█████▋    | 210461/371472 [6:02:13<13:52:51,  3.22it/s]
 57%|█████▋    | 210462/371472 [6:02:13<13:38:11,  3.28it/s]
 57%|█████▋    | 210463/371472 [6:02:14<14:31:10,  3.08it/s]
 57%|█████▋    | 210464/371472 [6:02:14<14:17:17,  3.13it/s]
 57%|█████▋    | 210465/371472 [6:02:14<13:59:07,  3.20it/s]
 57%|█████▋    | 210466/371472 [6:02:14<13:28:49,  3.32it/s]
 57%|█████▋    | 210467/371472 [6:02:15<13:36:13,  3.29it/s]
 57%|█████▋    | 210468/371472 [6:02:15<13:27:45,  3.32it/s]
 57%|█████▋    | 210469/371472 [6:02:15<13:23:51,  3.34it/s]
 57%|█████▋    | 210470/371472 [6:02:16<13:23:03,  3.34it/s]
 57%|█████▋    | 210471/371472 [6:02:16<13:19:29,  3.36it/s]
 57%|█████▋    | 210472/371472 [6:02:16<13:41:21,  3.27it/s]
 57%|█████▋    | 210473/371472 [6:02:17<13:17:29,  3.36it/s]
 57%|█████▋    | 210474/371472 [6:02:17<13:16:05,  3.37it/s]
 57%|█████▋    | 210475/371472 [6:02:17<12:52:23,  3.47it/s]
 57%|█████▋    | 210476/371472 [6:02:17<14:02:40,  3.18it/s]
 57%|█████▋    | 210477/371472 [6:02:18<13:39:51,  3.27it/s]
 57%|█████▋    | 210478/371472 [6:02:18<13:37:36,  3.28it/s]
 57%|█████▋    | 210479/371472 [6:02:18<13:11:45,  3.39it/s]
 57%|█████▋    | 210480/371472 [6:02:19<13:29:12,  3.32it/s]
                                                            
{'loss': 3.0235, 'learning_rate': 4.902605098149066e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210480/371472 [6:02:19<13:29:12,  3.32it/s]
 57%|█████▋    | 210481/371472 [6:02:19<13:13:29,  3.38it/s]
 57%|█████▋    | 210482/371472 [6:02:19<12:55:57,  3.46it/s]
 57%|█████▋    | 210483/371472 [6:02:19<12:48:41,  3.49it/s]
 57%|█████▋    | 210484/371472 [6:02:20<13:15:57,  3.37it/s]
 57%|█████▋    | 210485/371472 [6:02:20<13:34:31,  3.29it/s]
 57%|█████▋    | 210486/371472 [6:02:20<13:28:56,  3.32it/s]
 57%|█████▋    | 210487/371472 [6:02:21<14:11:48,  3.15it/s]
 57%|█████▋    | 210488/371472 [6:02:21<14:05:57,  3.17it/s]
 57%|█████▋    | 210489/371472 [6:02:21<13:55:23,  3.21it/s]
 57%|█████▋    | 210490/371472 [6:02:22<13:26:32,  3.33it/s]
 57%|█████▋    | 210491/371472 [6:02:22<13:16:12,  3.37it/s]
 57%|█████▋    | 210492/371472 [6:02:22<13:29:26,  3.31it/s]
 57%|█████▋    | 210493/371472 [6:02:23<13:39:30,  3.27it/s]
 57%|█████▋    | 210494/371472 [6:02:23<13:41:12,  3.27it/s]
 57%|█████▋    | 210495/371472 [6:02:23<13:37:30,  3.28it/s]
 57%|█████▋    | 210496/371472 [6:02:23<13:19:26,  3.36it/s]
 57%|█████▋    | 210497/371472 [6:02:24<14:35:17,  3.07it/s]
 57%|█████▋    | 210498/371472 [6:02:24<13:51:21,  3.23it/s]
 57%|█████▋    | 210499/371472 [6:02:24<13:41:37,  3.27it/s]
 57%|█████▋    | 210500/371472 [6:02:25<13:59:33,  3.20it/s]
                                                            
{'loss': 3.007, 'learning_rate': 4.902120278394276e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210500/371472 [6:02:25<13:59:33,  3.20it/s]
 57%|█████▋    | 210501/371472 [6:02:25<13:39:18,  3.27it/s]
 57%|█████▋    | 210502/371472 [6:02:25<13:20:51,  3.35it/s]
 57%|█████▋    | 210503/371472 [6:02:26<13:19:01,  3.36it/s]
 57%|█████▋    | 210504/371472 [6:02:26<13:17:53,  3.36it/s]
 57%|█████▋    | 210505/371472 [6:02:26<13:01:14,  3.43it/s]
 57%|█████▋    | 210506/371472 [6:02:26<12:56:22,  3.46it/s]
 57%|█████▋    | 210507/371472 [6:02:27<13:07:43,  3.41it/s]
 57%|█████▋    | 210508/371472 [6:02:27<13:13:22,  3.38it/s]
 57%|█████▋    | 210509/371472 [6:02:27<13:56:29,  3.21it/s]
 57%|█████▋    | 210510/371472 [6:02:28<14:17:26,  3.13it/s]
 57%|█████▋    | 210511/371472 [6:02:28<13:53:35,  3.22it/s]
 57%|█████▋    | 210512/371472 [6:02:28<13:41:34,  3.27it/s]
 57%|█████▋    | 210513/371472 [6:02:29<15:20:48,  2.91it/s]
 57%|█████▋    | 210514/371472 [6:02:29<14:46:02,  3.03it/s]
 57%|█████▋    | 210515/371472 [6:02:29<15:26:00,  2.90it/s]
 57%|█████▋    | 210516/371472 [6:02:30<15:37:51,  2.86it/s]
 57%|█████▋    | 210517/371472 [6:02:30<14:49:16,  3.02it/s]
 57%|█████▋    | 210518/371472 [6:02:30<14:59:22,  2.98it/s]
 57%|█████▋    | 210519/371472 [6:02:31<14:44:18,  3.03it/s]
 57%|█████▋    | 210520/371472 [6:02:31<14:32:47,  3.07it/s]
                                                            
{'loss': 2.8629, 'learning_rate': 4.901635458639488e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210520/371472 [6:02:31<14:32:47,  3.07it/s]
 57%|█████▋    | 210521/371472 [6:02:31<14:14:36,  3.14it/s]
 57%|█████▋    | 210522/371472 [6:02:32<13:42:58,  3.26it/s]
 57%|█████▋    | 210523/371472 [6:02:32<14:38:19,  3.05it/s]
 57%|█████▋    | 210524/371472 [6:02:32<14:02:39,  3.18it/s]
 57%|█████▋    | 210525/371472 [6:02:33<13:53:49,  3.22it/s]
 57%|█████▋    | 210526/371472 [6:02:33<14:00:47,  3.19it/s]
 57%|█████▋    | 210527/371472 [6:02:33<13:20:33,  3.35it/s]
 57%|█████▋    | 210528/371472 [6:02:33<12:52:56,  3.47it/s]
 57%|█████▋    | 210529/371472 [6:02:34<12:53:22,  3.47it/s]
 57%|█████▋    | 210530/371472 [6:02:34<12:53:29,  3.47it/s]
 57%|█████▋    | 210531/371472 [6:02:34<13:26:40,  3.33it/s]
 57%|█████▋    | 210532/371472 [6:02:35<13:12:55,  3.38it/s]
 57%|█████▋    | 210533/371472 [6:02:35<13:09:18,  3.40it/s]
 57%|█████▋    | 210534/371472 [6:02:35<13:13:29,  3.38it/s]
 57%|█████▋    | 210535/371472 [6:02:36<13:30:35,  3.31it/s]
 57%|█████▋    | 210536/371472 [6:02:36<13:14:43,  3.38it/s]
 57%|█████▋    | 210537/371472 [6:02:36<13:35:06,  3.29it/s]
 57%|█████▋    | 210538/371472 [6:02:37<13:51:29,  3.23it/s]
 57%|█████▋    | 210539/371472 [6:02:37<13:56:33,  3.21it/s]
 57%|█████▋    | 210540/371472 [6:02:37<13:27:39,  3.32it/s]
                                                            
{'loss': 2.8134, 'learning_rate': 4.901150638884699e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210540/371472 [6:02:37<13:27:39,  3.32it/s]
 57%|█████▋    | 210541/371472 [6:02:37<13:52:22,  3.22it/s]
 57%|█████▋    | 210542/371472 [6:02:38<13:50:06,  3.23it/s]
 57%|█████▋    | 210543/371472 [6:02:38<13:40:03,  3.27it/s]
 57%|█████▋    | 210544/371472 [6:02:38<13:25:35,  3.33it/s]
 57%|█████▋    | 210545/371472 [6:02:39<13:47:25,  3.24it/s]
 57%|█████▋    | 210546/371472 [6:02:39<13:45:39,  3.25it/s]
 57%|█████▋    | 210547/371472 [6:02:39<13:48:08,  3.24it/s]
 57%|█████▋    | 210548/371472 [6:02:40<13:43:56,  3.26it/s]
 57%|█████▋    | 210549/371472 [6:02:40<13:26:34,  3.33it/s]
 57%|█████▋    | 210550/371472 [6:02:40<14:46:28,  3.03it/s]
 57%|█████▋    | 210551/371472 [6:02:41<14:22:30,  3.11it/s]
 57%|█████▋    | 210552/371472 [6:02:41<14:11:44,  3.15it/s]
 57%|█████▋    | 210553/371472 [6:02:41<14:07:48,  3.16it/s]
 57%|█████▋    | 210554/371472 [6:02:42<14:37:04,  3.06it/s]
 57%|█████▋    | 210555/371472 [6:02:42<14:31:26,  3.08it/s]
 57%|█████▋    | 210556/371472 [6:02:42<15:20:44,  2.91it/s]
 57%|█████▋    | 210557/371472 [6:02:43<14:47:15,  3.02it/s]
 57%|█████▋    | 210558/371472 [6:02:43<13:53:13,  3.22it/s]
 57%|█████▋    | 210559/371472 [6:02:43<13:48:32,  3.24it/s]
 57%|█████▋    | 210560/371472 [6:02:43<13:33:20,  3.30it/s]
                                                            
{'loss': 2.7196, 'learning_rate': 4.90066581912991e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210560/371472 [6:02:43<13:33:20,  3.30it/s]
 57%|█████▋    | 210561/371472 [6:02:44<13:16:58,  3.37it/s]
 57%|█████▋    | 210562/371472 [6:02:44<12:52:18,  3.47it/s]
 57%|█████▋    | 210563/371472 [6:02:44<13:06:57,  3.41it/s]
 57%|█████▋    | 210564/371472 [6:02:45<13:34:26,  3.29it/s]
 57%|█████▋    | 210565/371472 [6:02:45<13:23:35,  3.34it/s]
 57%|█████▋    | 210566/371472 [6:02:45<13:08:29,  3.40it/s]
 57%|█████▋    | 210567/371472 [6:02:45<13:02:02,  3.43it/s]
 57%|█████▋    | 210568/371472 [6:02:46<13:01:59,  3.43it/s]
 57%|█████▋    | 210569/371472 [6:02:46<12:52:36,  3.47it/s]
 57%|█████▋    | 210570/371472 [6:02:46<13:13:43,  3.38it/s]
 57%|█████▋    | 210571/371472 [6:02:47<13:26:58,  3.32it/s]
 57%|█████▋    | 210572/371472 [6:02:47<13:26:05,  3.33it/s]
 57%|█████▋    | 210573/371472 [6:02:47<13:18:30,  3.36it/s]
 57%|█████▋    | 210574/371472 [6:02:48<13:43:54,  3.25it/s]
 57%|█████▋    | 210575/371472 [6:02:48<13:36:47,  3.28it/s]
 57%|█████▋    | 210576/371472 [6:02:48<13:30:33,  3.31it/s]
 57%|█████▋    | 210577/371472 [6:02:49<14:24:06,  3.10it/s]
 57%|█████▋    | 210578/371472 [6:02:49<14:04:24,  3.18it/s]
 57%|█████▋    | 210579/371472 [6:02:49<13:44:21,  3.25it/s]
 57%|█████▋    | 210580/371472 [6:02:49<13:33:57,  3.29it/s]
                                                            
{'loss': 2.7868, 'learning_rate': 4.90018099937512e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210580/371472 [6:02:49<13:33:57,  3.29it/s]
 57%|█████▋    | 210581/371472 [6:02:50<13:15:23,  3.37it/s]
 57%|█████▋    | 210582/371472 [6:02:50<12:49:37,  3.48it/s]
 57%|█████▋    | 210583/371472 [6:02:50<14:25:09,  3.10it/s]
 57%|█████▋    | 210584/371472 [6:02:51<13:50:25,  3.23it/s]
 57%|█████▋    | 210585/371472 [6:02:51<13:28:53,  3.31it/s]
 57%|█████▋    | 210586/371472 [6:02:51<13:08:05,  3.40it/s]
 57%|█████▋    | 210587/371472 [6:02:52<13:34:20,  3.29it/s]
 57%|█████▋    | 210588/371472 [6:02:52<13:21:14,  3.35it/s]
 57%|█████▋    | 210589/371472 [6:02:52<14:31:06,  3.08it/s]
 57%|█████▋    | 210590/371472 [6:02:53<14:20:48,  3.11it/s]
 57%|█████▋    | 210591/371472 [6:02:53<13:53:01,  3.22it/s]
 57%|█████▋    | 210592/371472 [6:02:53<14:09:43,  3.16it/s]
 57%|█████▋    | 210593/371472 [6:02:53<13:35:17,  3.29it/s]
 57%|█████▋    | 210594/371472 [6:02:54<13:52:12,  3.22it/s]
 57%|█████▋    | 210595/371472 [6:02:54<13:42:05,  3.26it/s]
 57%|█████▋    | 210596/371472 [6:02:54<13:23:41,  3.34it/s]
 57%|█████▋    | 210597/371472 [6:02:55<12:58:38,  3.44it/s]
 57%|█████▋    | 210598/371472 [6:02:55<12:51:03,  3.48it/s]
 57%|█████▋    | 210599/371472 [6:02:55<13:06:09,  3.41it/s]
 57%|█████▋    | 210600/371472 [6:02:55<12:57:20,  3.45it/s]
                                                            
{'loss': 2.8761, 'learning_rate': 4.899696179620332e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210600/371472 [6:02:55<12:57:20,  3.45it/s]
 57%|█████▋    | 210601/371472 [6:02:56<13:02:13,  3.43it/s]
 57%|█████▋    | 210602/371472 [6:02:56<13:06:09,  3.41it/s]
 57%|█████▋    | 210603/371472 [6:02:56<13:18:42,  3.36it/s]
 57%|█████▋    | 210604/371472 [6:02:57<13:55:14,  3.21it/s]
 57%|█████▋    | 210605/371472 [6:02:57<14:01:25,  3.19it/s]
 57%|█████▋    | 210606/371472 [6:02:57<13:45:56,  3.25it/s]
 57%|█████▋    | 210607/371472 [6:02:58<14:10:23,  3.15it/s]
 57%|█████▋    | 210608/371472 [6:02:58<13:59:31,  3.19it/s]
 57%|█████▋    | 210609/371472 [6:02:58<13:32:18,  3.30it/s]
 57%|█████▋    | 210610/371472 [6:02:59<13:33:24,  3.30it/s]
 57%|█████▋    | 210611/371472 [6:02:59<13:29:01,  3.31it/s]
 57%|█████▋    | 210612/371472 [6:02:59<13:04:23,  3.42it/s]
 57%|█████▋    | 210613/371472 [6:02:59<13:07:08,  3.41it/s]
 57%|█████▋    | 210614/371472 [6:03:00<12:57:03,  3.45it/s]
 57%|█████▋    | 210615/371472 [6:03:00<12:40:45,  3.52it/s]
 57%|█████▋    | 210616/371472 [6:03:00<12:41:22,  3.52it/s]
 57%|█████▋    | 210617/371472 [6:03:01<12:48:23,  3.49it/s]
 57%|█████▋    | 210618/371472 [6:03:01<13:31:40,  3.30it/s]
 57%|█████▋    | 210619/371472 [6:03:01<13:54:42,  3.21it/s]
 57%|█████▋    | 210620/371472 [6:03:01<13:34:16,  3.29it/s]
                                                            
{'loss': 2.74, 'learning_rate': 4.899211359865543e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210620/371472 [6:03:01<13:34:16,  3.29it/s]
 57%|█████▋    | 210621/371472 [6:03:02<13:30:18,  3.31it/s]
 57%|█████▋    | 210622/371472 [6:03:02<15:12:50,  2.94it/s]
 57%|█████▋    | 210623/371472 [6:03:03<14:39:23,  3.05it/s]
 57%|█████▋    | 210624/371472 [6:03:03<15:31:34,  2.88it/s]
 57%|█████▋    | 210625/371472 [6:03:03<15:04:01,  2.97it/s]
 57%|█████▋    | 210626/371472 [6:03:04<14:33:19,  3.07it/s]
 57%|█████▋    | 210627/371472 [6:03:04<13:57:19,  3.20it/s]
 57%|█████▋    | 210628/371472 [6:03:04<13:35:46,  3.29it/s]
 57%|█████▋    | 210629/371472 [6:03:04<13:38:23,  3.28it/s]
 57%|█████▋    | 210630/371472 [6:03:05<13:32:22,  3.30it/s]
 57%|█████▋    | 210631/371472 [6:03:05<13:32:25,  3.30it/s]
 57%|█████▋    | 210632/371472 [6:03:05<13:01:50,  3.43it/s]
 57%|█████▋    | 210633/371472 [6:03:06<12:51:14,  3.48it/s]
 57%|█████▋    | 210634/371472 [6:03:06<12:59:49,  3.44it/s]
 57%|█████▋    | 210635/371472 [6:03:06<13:07:19,  3.40it/s]
 57%|█████▋    | 210636/371472 [6:03:06<13:00:06,  3.44it/s]
 57%|█████▋    | 210637/371472 [6:03:07<12:42:06,  3.52it/s]
 57%|█████▋    | 210638/371472 [6:03:07<12:37:02,  3.54it/s]
 57%|█████▋    | 210639/371472 [6:03:07<13:44:51,  3.25it/s]
 57%|█████▋    | 210640/371472 [6:03:08<13:57:31,  3.20it/s]
                                                            
{'loss': 2.7413, 'learning_rate': 4.898726540110755e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210640/371472 [6:03:08<13:57:31,  3.20it/s]
 57%|█████▋    | 210641/371472 [6:03:08<13:35:51,  3.29it/s]
 57%|█████▋    | 210642/371472 [6:03:08<13:26:44,  3.32it/s]
 57%|█████▋    | 210643/371472 [6:03:09<13:37:47,  3.28it/s]
 57%|█████▋    | 210644/371472 [6:03:09<13:31:11,  3.30it/s]
 57%|█████▋    | 210645/371472 [6:03:09<13:09:41,  3.39it/s]
 57%|█████▋    | 210646/371472 [6:03:09<13:14:06,  3.38it/s]
 57%|█████▋    | 210647/371472 [6:03:10<13:35:17,  3.29it/s]
 57%|█████▋    | 210648/371472 [6:03:10<13:30:47,  3.31it/s]
 57%|█████▋    | 210649/371472 [6:03:10<13:07:16,  3.40it/s]
 57%|█████▋    | 210650/371472 [6:03:11<13:04:43,  3.42it/s]
 57%|█████▋    | 210651/371472 [6:03:11<13:12:02,  3.38it/s]
 57%|█████▋    | 210652/371472 [6:03:11<12:52:03,  3.47it/s]
 57%|█████▋    | 210653/371472 [6:03:11<13:05:31,  3.41it/s]
 57%|█████▋    | 210654/371472 [6:03:12<12:56:38,  3.45it/s]
 57%|█████▋    | 210655/371472 [6:03:12<13:39:26,  3.27it/s]
 57%|█████▋    | 210656/371472 [6:03:12<13:33:18,  3.30it/s]
 57%|█████▋    | 210657/371472 [6:03:13<13:27:26,  3.32it/s]
 57%|█████▋    | 210658/371472 [6:03:13<13:07:25,  3.40it/s]
 57%|█████▋    | 210659/371472 [6:03:13<12:54:31,  3.46it/s]
 57%|█████▋    | 210660/371472 [6:03:14<13:13:07,  3.38it/s]
                                                            
{'loss': 2.8491, 'learning_rate': 4.898241720355965e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210660/371472 [6:03:14<13:13:07,  3.38it/s]
 57%|█████▋    | 210661/371472 [6:03:14<13:06:37,  3.41it/s]
 57%|█████▋    | 210662/371472 [6:03:14<13:06:57,  3.41it/s]
 57%|█████▋    | 210663/371472 [6:03:14<12:54:04,  3.46it/s]
 57%|█████▋    | 210664/371472 [6:03:15<13:17:36,  3.36it/s]
 57%|█████▋    | 210665/371472 [6:03:15<12:55:30,  3.46it/s]
 57%|█████▋    | 210666/371472 [6:03:15<12:48:27,  3.49it/s]
 57%|█████▋    | 210667/371472 [6:03:16<12:46:47,  3.50it/s]
 57%|█████▋    | 210668/371472 [6:03:16<12:49:00,  3.49it/s]
 57%|█████▋    | 210669/371472 [6:03:16<12:50:33,  3.48it/s]
 57%|█████▋    | 210670/371472 [6:03:16<12:53:41,  3.46it/s]
 57%|█████▋    | 210671/371472 [6:03:17<13:03:02,  3.42it/s]
 57%|█████▋    | 210672/371472 [6:03:17<13:32:59,  3.30it/s]
 57%|█████▋    | 210673/371472 [6:03:17<13:24:44,  3.33it/s]
 57%|█████▋    | 210674/371472 [6:03:18<13:29:03,  3.31it/s]
 57%|█████▋    | 210675/371472 [6:03:18<13:13:27,  3.38it/s]
 57%|█████▋    | 210676/371472 [6:03:18<13:01:32,  3.43it/s]
 57%|█████▋    | 210677/371472 [6:03:19<13:21:04,  3.35it/s]
 57%|█████▋    | 210678/371472 [6:03:19<13:43:49,  3.25it/s]
 57%|█████▋    | 210679/371472 [6:03:19<13:19:17,  3.35it/s]
 57%|█████▋    | 210680/371472 [6:03:20<14:11:24,  3.15it/s]
                                                            
{'loss': 2.8067, 'learning_rate': 4.897756900601176e-07, 'epoch': 9.07}
+
 57%|█████▋    | 210680/371472 [6:03:20<14:11:24,  3.15it/s]
 57%|█████▋    | 210681/371472 [6:03:20<13:57:07,  3.20it/s]
 57%|█████▋    | 210682/371472 [6:03:20<13:37:02,  3.28it/s]
 57%|█████▋    | 210683/371472 [6:03:20<13:36:44,  3.28it/s]
 57%|█████▋    | 210684/371472 [6:03:21<13:27:34,  3.32it/s]
 57%|█████▋    | 210685/371472 [6:03:21<12:54:07,  3.46it/s]
 57%|█████▋    | 210686/371472 [6:03:21<13:12:47,  3.38it/s]
 57%|█████▋    | 210687/371472 [6:03:22<13:08:20,  3.40it/s]
 57%|█████▋    | 210688/371472 [6:03:22<13:30:34,  3.31it/s]
 57%|█████▋    | 210689/371472 [6:03:22<13:11:14,  3.39it/s]
 57%|█████▋    | 210690/371472 [6:03:22<12:56:01,  3.45it/s]
 57%|█████▋    | 210691/371472 [6:03:23<12:54:37,  3.46it/s]
 57%|█████▋    | 210692/371472 [6:03:23<12:51:08,  3.47it/s]
 57%|█████▋    | 210693/371472 [6:03:23<12:48:01,  3.49it/s]
 57%|█████▋    | 210694/371472 [6:03:24<13:00:32,  3.43it/s]
 57%|█████▋    | 210695/371472 [6:03:24<12:59:30,  3.44it/s]
 57%|█████▋    | 210696/371472 [6:03:24<12:48:12,  3.49it/s]
 57%|█████▋    | 210697/371472 [6:03:24<12:48:20,  3.49it/s]
 57%|█████▋    | 210698/371472 [6:03:25<12:42:45,  3.51it/s]
 57%|█████▋    | 210699/371472 [6:03:25<12:48:35,  3.49it/s]
 57%|█████▋    | 210700/371472 [6:03:25<12:37:56,  3.54it/s]
                                                            
{'loss': 2.9919, 'learning_rate': 4.897272080846387e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210700/371472 [6:03:25<12:37:56,  3.54it/s]
 57%|█████▋    | 210701/371472 [6:03:26<12:47:59,  3.49it/s]
 57%|█████▋    | 210702/371472 [6:03:26<13:32:57,  3.30it/s]
 57%|█████▋    | 210703/371472 [6:03:26<13:16:17,  3.36it/s]
 57%|█████▋    | 210704/371472 [6:03:27<13:00:25,  3.43it/s]
 57%|█████▋    | 210705/371472 [6:03:27<13:09:16,  3.39it/s]
 57%|█████▋    | 210706/371472 [6:03:27<12:53:49,  3.46it/s]
 57%|█████▋    | 210707/371472 [6:03:27<13:16:46,  3.36it/s]
 57%|█████▋    | 210708/371472 [6:03:28<14:03:29,  3.18it/s]
 57%|█████▋    | 210709/371472 [6:03:28<14:47:03,  3.02it/s]
 57%|█████▋    | 210710/371472 [6:03:28<14:13:19,  3.14it/s]
 57%|█████▋    | 210711/371472 [6:03:29<13:41:12,  3.26it/s]
 57%|█████▋    | 210712/371472 [6:03:29<14:01:51,  3.18it/s]
 57%|█████▋    | 210713/371472 [6:03:29<15:17:40,  2.92it/s]
 57%|█████▋    | 210714/371472 [6:03:30<14:50:27,  3.01it/s]
 57%|█████▋    | 210715/371472 [6:03:30<14:26:32,  3.09it/s]
 57%|█████▋    | 210716/371472 [6:03:30<14:05:43,  3.17it/s]
 57%|█████▋    | 210717/371472 [6:03:31<15:11:46,  2.94it/s]
 57%|█████▋    | 210718/371472 [6:03:31<14:45:58,  3.02it/s]
 57%|█████▋    | 210719/371472 [6:03:31<14:36:02,  3.06it/s]
 57%|█████▋    | 210720/371472 [6:03:32<14:31:20,  3.07it/s]
                                                            
{'loss': 2.7304, 'learning_rate': 4.8967872610916e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210720/371472 [6:03:32<14:31:20,  3.07it/s]
 57%|█████▋    | 210721/371472 [6:03:32<14:30:06,  3.08it/s]
 57%|█████▋    | 210722/371472 [6:03:32<13:45:14,  3.25it/s]
 57%|█████▋    | 210723/371472 [6:03:33<14:39:00,  3.05it/s]
 57%|█████▋    | 210724/371472 [6:03:33<14:10:45,  3.15it/s]
 57%|█████▋    | 210725/371472 [6:03:33<17:05:35,  2.61it/s]
 57%|█████▋    | 210726/371472 [6:03:34<17:47:47,  2.51it/s]
 57%|█████▋    | 210727/371472 [6:03:34<17:08:06,  2.61it/s]
 57%|█████▋    | 210728/371472 [6:03:35<16:31:06,  2.70it/s]
 57%|█████▋    | 210729/371472 [6:03:35<18:17:49,  2.44it/s]
 57%|█████▋    | 210730/371472 [6:03:35<17:13:56,  2.59it/s]
 57%|█████▋    | 210731/371472 [6:03:36<15:59:14,  2.79it/s]
 57%|█████▋    | 210732/371472 [6:03:36<15:19:44,  2.91it/s]
 57%|█████▋    | 210733/371472 [6:03:36<14:18:45,  3.12it/s]
 57%|█████▋    | 210734/371472 [6:03:37<13:42:28,  3.26it/s]
 57%|█████▋    | 210735/371472 [6:03:37<13:09:52,  3.39it/s]
 57%|█████▋    | 210736/371472 [6:03:37<12:54:56,  3.46it/s]
 57%|█████▋    | 210737/371472 [6:03:37<13:31:17,  3.30it/s]
 57%|█████▋    | 210738/371472 [6:03:38<13:07:02,  3.40it/s]
 57%|█████▋    | 210739/371472 [6:03:38<12:56:54,  3.45it/s]
 57%|█████▋    | 210740/371472 [6:03:38<13:00:25,  3.43it/s]
                                                            
{'loss': 2.8144, 'learning_rate': 4.896302441336809e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210740/371472 [6:03:38<13:00:25,  3.43it/s]
 57%|█████▋    | 210741/371472 [6:03:39<13:31:05,  3.30it/s]
 57%|█████▋    | 210742/371472 [6:03:39<13:14:22,  3.37it/s]
 57%|█████▋    | 210743/371472 [6:03:39<13:00:46,  3.43it/s]
 57%|█████▋    | 210744/371472 [6:03:40<13:22:12,  3.34it/s]
 57%|█████▋    | 210745/371472 [6:03:40<13:07:14,  3.40it/s]
 57%|█████▋    | 210746/371472 [6:03:40<13:25:43,  3.32it/s]
 57%|█████▋    | 210747/371472 [6:03:40<13:30:06,  3.31it/s]
 57%|█████▋    | 210748/371472 [6:03:41<13:07:46,  3.40it/s]
 57%|█████▋    | 210749/371472 [6:03:41<13:03:48,  3.42it/s]
 57%|█████▋    | 210750/371472 [6:03:41<13:10:48,  3.39it/s]
 57%|█████▋    | 210751/371472 [6:03:42<13:32:40,  3.30it/s]
 57%|█████▋    | 210752/371472 [6:03:42<13:25:23,  3.33it/s]
 57%|█████▋    | 210753/371472 [6:03:42<13:11:03,  3.39it/s]
 57%|█████▋    | 210754/371472 [6:03:42<12:41:00,  3.52it/s]
 57%|█████▋    | 210755/371472 [6:03:43<12:57:17,  3.45it/s]
 57%|█████▋    | 210756/371472 [6:03:43<13:02:01,  3.43it/s]
 57%|█████▋    | 210757/371472 [6:03:43<12:57:38,  3.44it/s]
 57%|█████▋    | 210758/371472 [6:03:44<12:52:46,  3.47it/s]
 57%|█████▋    | 210759/371472 [6:03:44<13:04:27,  3.41it/s]
 57%|█████▋    | 210760/371472 [6:03:44<12:51:55,  3.47it/s]
                                                            
{'loss': 2.6616, 'learning_rate': 4.895817621582021e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210760/371472 [6:03:44<12:51:55,  3.47it/s]
 57%|█████▋    | 210761/371472 [6:03:45<13:16:45,  3.36it/s]
 57%|█████▋    | 210762/371472 [6:03:45<12:46:23,  3.49it/s]
 57%|█████▋    | 210763/371472 [6:03:45<12:49:20,  3.48it/s]
 57%|█████▋    | 210764/371472 [6:03:45<12:37:42,  3.53it/s]
 57%|█████▋    | 210765/371472 [6:03:46<12:58:36,  3.44it/s]
 57%|█████▋    | 210766/371472 [6:03:46<12:53:39,  3.46it/s]
 57%|█████▋    | 210767/371472 [6:03:46<12:32:12,  3.56it/s]
 57%|█████▋    | 210768/371472 [6:03:46<12:30:31,  3.57it/s]
 57%|█████▋    | 210769/371472 [6:03:47<12:31:48,  3.56it/s]
 57%|█████▋    | 210770/371472 [6:03:47<13:14:16,  3.37it/s]
 57%|█████▋    | 210771/371472 [6:03:47<13:43:49,  3.25it/s]
 57%|█████▋    | 210772/371472 [6:03:48<13:38:25,  3.27it/s]
 57%|█████▋    | 210773/371472 [6:03:48<13:47:13,  3.24it/s]
 57%|█████▋    | 210774/371472 [6:03:48<13:22:56,  3.34it/s]
 57%|█████▋    | 210775/371472 [6:03:49<13:15:21,  3.37it/s]
 57%|█████▋    | 210776/371472 [6:03:49<14:02:35,  3.18it/s]
 57%|█████▋    | 210777/371472 [6:03:49<13:50:29,  3.22it/s]
 57%|█████▋    | 210778/371472 [6:03:50<13:21:23,  3.34it/s]
 57%|█████▋    | 210779/371472 [6:03:50<13:02:45,  3.42it/s]
 57%|█████▋    | 210780/371472 [6:03:50<14:09:42,  3.15it/s]
                                                            
{'loss': 2.7471, 'learning_rate': 4.895332801827232e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210780/371472 [6:03:50<14:09:42,  3.15it/s]
 57%|█████▋    | 210781/371472 [6:03:51<14:04:54,  3.17it/s]
 57%|█████▋    | 210782/371472 [6:03:51<14:20:40,  3.11it/s]
 57%|█████▋    | 210783/371472 [6:03:51<13:47:43,  3.24it/s]
 57%|█████▋    | 210784/371472 [6:03:51<13:14:47,  3.37it/s]
 57%|█████▋    | 210785/371472 [6:03:52<12:49:52,  3.48it/s]
 57%|█████▋    | 210786/371472 [6:03:52<12:40:05,  3.52it/s]
 57%|█████▋    | 210787/371472 [6:03:52<12:49:41,  3.48it/s]
 57%|█████▋    | 210788/371472 [6:03:53<12:48:25,  3.49it/s]
 57%|█████▋    | 210789/371472 [6:03:53<12:22:53,  3.60it/s]
 57%|█████▋    | 210790/371472 [6:03:53<12:22:46,  3.61it/s]
 57%|█████▋    | 210791/371472 [6:03:53<13:31:14,  3.30it/s]
 57%|█████▋    | 210792/371472 [6:03:54<14:47:54,  3.02it/s]
 57%|█████▋    | 210793/371472 [6:03:54<14:06:21,  3.16it/s]
 57%|█████▋    | 210794/371472 [6:03:54<14:49:36,  3.01it/s]
 57%|█████▋    | 210795/371472 [6:03:55<14:09:19,  3.15it/s]
 57%|█████▋    | 210796/371472 [6:03:55<14:02:28,  3.18it/s]
 57%|█████▋    | 210797/371472 [6:03:55<14:10:02,  3.15it/s]
 57%|█████▋    | 210798/371472 [6:03:56<13:50:32,  3.22it/s]
 57%|█████▋    | 210799/371472 [6:03:56<14:18:51,  3.12it/s]
 57%|█████▋    | 210800/371472 [6:03:56<13:40:25,  3.26it/s]
                                                            
{'loss': 2.6589, 'learning_rate': 4.894847982072442e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210800/371472 [6:03:56<13:40:25,  3.26it/s]
 57%|█████▋    | 210801/371472 [6:03:57<13:50:07,  3.23it/s]
 57%|█████▋    | 210802/371472 [6:03:57<14:26:32,  3.09it/s]
 57%|█████▋    | 210803/371472 [6:03:57<14:10:24,  3.15it/s]
 57%|█████▋    | 210804/371472 [6:03:58<13:50:11,  3.23it/s]
 57%|█████▋    | 210805/371472 [6:03:58<13:28:00,  3.31it/s]
 57%|█████▋    | 210806/371472 [6:03:58<13:22:01,  3.34it/s]
 57%|█████▋    | 210807/371472 [6:03:58<13:24:00,  3.33it/s]
 57%|█████▋    | 210808/371472 [6:03:59<14:46:11,  3.02it/s]
 57%|█████▋    | 210809/371472 [6:03:59<14:20:03,  3.11it/s]
 57%|█████▋    | 210810/371472 [6:03:59<14:00:28,  3.19it/s]
 57%|█████▋    | 210811/371472 [6:04:00<13:38:19,  3.27it/s]
 57%|█████▋    | 210812/371472 [6:04:00<14:00:15,  3.19it/s]
 57%|█████▋    | 210813/371472 [6:04:00<13:53:30,  3.21it/s]
 57%|█████▋    | 210814/371472 [6:04:01<14:42:03,  3.04it/s]
 57%|█████▋    | 210815/371472 [6:04:01<13:52:23,  3.22it/s]
 57%|█████▋    | 210816/371472 [6:04:01<13:43:47,  3.25it/s]
 57%|█████▋    | 210817/371472 [6:04:02<13:29:24,  3.31it/s]
 57%|█████▋    | 210818/371472 [6:04:02<13:42:15,  3.26it/s]
 57%|█████▋    | 210819/371472 [6:04:02<13:28:53,  3.31it/s]
 57%|█████▋    | 210820/371472 [6:04:02<13:06:26,  3.40it/s]
                                                            
{'loss': 2.7406, 'learning_rate': 4.894363162317653e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210820/371472 [6:04:02<13:06:26,  3.40it/s]
 57%|█████▋    | 210821/371472 [6:04:03<13:26:57,  3.32it/s]
 57%|█████▋    | 210822/371472 [6:04:03<13:46:40,  3.24it/s]
 57%|█████▋    | 210823/371472 [6:04:03<13:26:30,  3.32it/s]
 57%|█████▋    | 210824/371472 [6:04:04<13:22:37,  3.34it/s]
 57%|█████▋    | 210825/371472 [6:04:04<13:11:46,  3.38it/s]
 57%|█████▋    | 210826/371472 [6:04:04<13:09:14,  3.39it/s]
 57%|█████▋    | 210827/371472 [6:04:05<13:29:23,  3.31it/s]
 57%|█████▋    | 210828/371472 [6:04:05<13:14:05,  3.37it/s]
 57%|█████▋    | 210829/371472 [6:04:05<13:13:22,  3.37it/s]
 57%|█████▋    | 210830/371472 [6:04:05<13:12:34,  3.38it/s]
 57%|█████▋    | 210831/371472 [6:04:06<13:24:00,  3.33it/s]
 57%|█████▋    | 210832/371472 [6:04:06<13:56:52,  3.20it/s]
 57%|█████▋    | 210833/371472 [6:04:06<13:16:19,  3.36it/s]
 57%|█████▋    | 210834/371472 [6:04:07<15:09:15,  2.94it/s]
 57%|█████▋    | 210835/371472 [6:04:07<14:23:27,  3.10it/s]
 57%|█████▋    | 210836/371472 [6:04:07<13:57:03,  3.20it/s]
 57%|█████▋    | 210837/371472 [6:04:08<13:37:14,  3.28it/s]
 57%|█████▋    | 210838/371472 [6:04:08<13:16:01,  3.36it/s]
 57%|█████▋    | 210839/371472 [6:04:08<12:59:20,  3.44it/s]
 57%|█████▋    | 210840/371472 [6:04:09<12:55:39,  3.45it/s]
                                                            
{'loss': 2.7401, 'learning_rate': 4.893878342562864e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210840/371472 [6:04:09<12:55:39,  3.45it/s]
 57%|█████▋    | 210841/371472 [6:04:09<12:47:10,  3.49it/s]
 57%|█████▋    | 210842/371472 [6:04:09<12:31:08,  3.56it/s]
 57%|█████▋    | 210843/371472 [6:04:09<12:51:29,  3.47it/s]
 57%|█████▋    | 210844/371472 [6:04:10<13:06:56,  3.40it/s]
 57%|█████▋    | 210845/371472 [6:04:10<12:56:48,  3.45it/s]
 57%|█████▋    | 210846/371472 [6:04:10<12:47:49,  3.49it/s]
 57%|█████▋    | 210847/371472 [6:04:11<13:22:21,  3.34it/s]
 57%|█████▋    | 210848/371472 [6:04:11<13:28:22,  3.31it/s]
 57%|█████▋    | 210849/371472 [6:04:11<13:25:10,  3.32it/s]
 57%|█████▋    | 210850/371472 [6:04:11<13:09:43,  3.39it/s]
 57%|█████▋    | 210851/371472 [6:04:12<12:55:45,  3.45it/s]
 57%|█████▋    | 210852/371472 [6:04:12<12:53:52,  3.46it/s]
 57%|█████▋    | 210853/371472 [6:04:12<13:38:35,  3.27it/s]
 57%|█████▋    | 210854/371472 [6:04:13<13:44:26,  3.25it/s]
 57%|█████▋    | 210855/371472 [6:04:13<13:04:44,  3.41it/s]
 57%|█████▋    | 210856/371472 [6:04:13<13:02:37,  3.42it/s]
 57%|█████▋    | 210857/371472 [6:04:14<13:16:33,  3.36it/s]
 57%|█████▋    | 210858/371472 [6:04:14<13:34:21,  3.29it/s]
 57%|█████▋    | 210859/371472 [6:04:14<13:41:08,  3.26it/s]
 57%|█████▋    | 210860/371472 [6:04:15<14:29:09,  3.08it/s]
                                                            
{'loss': 2.7378, 'learning_rate': 4.893393522808076e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210860/371472 [6:04:15<14:29:09,  3.08it/s]
 57%|█████▋    | 210861/371472 [6:04:15<14:16:02,  3.13it/s]
 57%|█████▋    | 210862/371472 [6:04:15<13:58:58,  3.19it/s]
 57%|█████▋    | 210863/371472 [6:04:15<13:32:51,  3.29it/s]
 57%|█████▋    | 210864/371472 [6:04:16<13:30:16,  3.30it/s]
 57%|█████▋    | 210865/371472 [6:04:16<13:18:22,  3.35it/s]
 57%|█████▋    | 210866/371472 [6:04:16<13:19:51,  3.35it/s]
 57%|█████▋    | 210867/371472 [6:04:17<13:01:39,  3.42it/s]
 57%|█████▋    | 210868/371472 [6:04:17<13:14:04,  3.37it/s]
 57%|█████▋    | 210869/371472 [6:04:17<13:33:52,  3.29it/s]
 57%|█████▋    | 210870/371472 [6:04:18<13:47:00,  3.24it/s]
 57%|█████▋    | 210871/371472 [6:04:18<13:16:47,  3.36it/s]
 57%|█████▋    | 210872/371472 [6:04:18<13:16:04,  3.36it/s]
 57%|█████▋    | 210873/371472 [6:04:18<13:03:30,  3.42it/s]
 57%|█████▋    | 210874/371472 [6:04:19<12:59:21,  3.43it/s]
 57%|█████▋    | 210875/371472 [6:04:19<12:37:54,  3.53it/s]
 57%|█████▋    | 210876/371472 [6:04:19<12:30:57,  3.56it/s]
 57%|█████▋    | 210877/371472 [6:04:19<12:23:58,  3.60it/s]
 57%|█████▋    | 210878/371472 [6:04:20<12:23:27,  3.60it/s]
 57%|█████▋    | 210879/371472 [6:04:20<12:31:33,  3.56it/s]
 57%|█████▋    | 210880/371472 [6:04:20<12:37:35,  3.53it/s]
                                                            
{'loss': 2.8288, 'learning_rate': 4.892908703053286e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210880/371472 [6:04:20<12:37:35,  3.53it/s]
 57%|█████▋    | 210881/371472 [6:04:21<13:29:25,  3.31it/s]
 57%|█████▋    | 210882/371472 [6:04:21<13:08:14,  3.40it/s]
 57%|█████▋    | 210883/371472 [6:04:21<12:53:38,  3.46it/s]
 57%|█████▋    | 210884/371472 [6:04:22<12:59:52,  3.43it/s]
 57%|█████▋    | 210885/371472 [6:04:22<13:31:47,  3.30it/s]
 57%|█████▋    | 210886/371472 [6:04:22<13:13:45,  3.37it/s]
 57%|█████▋    | 210887/371472 [6:04:22<13:05:13,  3.41it/s]
 57%|█████▋    | 210888/371472 [6:04:23<12:52:22,  3.47it/s]
 57%|█████▋    | 210889/371472 [6:04:23<13:42:28,  3.25it/s]
 57%|█████▋    | 210890/371472 [6:04:23<13:33:33,  3.29it/s]
 57%|█████▋    | 210891/371472 [6:04:24<13:58:47,  3.19it/s]
 57%|█████▋    | 210892/371472 [6:04:24<13:54:25,  3.21it/s]
 57%|█████▋    | 210893/371472 [6:04:24<13:50:57,  3.22it/s]
 57%|█████▋    | 210894/371472 [6:04:25<14:16:13,  3.13it/s]
 57%|█████▋    | 210895/371472 [6:04:25<13:47:28,  3.23it/s]
 57%|█████▋    | 210896/371472 [6:04:25<13:37:09,  3.28it/s]
 57%|█████▋    | 210897/371472 [6:04:26<13:28:26,  3.31it/s]
 57%|█████▋    | 210898/371472 [6:04:26<13:15:27,  3.36it/s]
 57%|█████▋    | 210899/371472 [6:04:26<13:18:31,  3.35it/s]
 57%|█████▋    | 210900/371472 [6:04:26<13:48:15,  3.23it/s]
                                                            
{'loss': 2.682, 'learning_rate': 4.892423883298498e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210900/371472 [6:04:26<13:48:15,  3.23it/s]
 57%|█████▋    | 210901/371472 [6:04:27<13:36:29,  3.28it/s]
 57%|█████▋    | 210902/371472 [6:04:27<13:22:50,  3.33it/s]
 57%|█████▋    | 210903/371472 [6:04:27<13:26:48,  3.32it/s]
 57%|█████▋    | 210904/371472 [6:04:28<14:13:01,  3.14it/s]
 57%|█████▋    | 210905/371472 [6:04:28<13:53:21,  3.21it/s]
 57%|█████▋    | 210906/371472 [6:04:28<13:18:21,  3.35it/s]
 57%|█████▋    | 210907/371472 [6:04:29<13:07:06,  3.40it/s]
 57%|█████▋    | 210908/371472 [6:04:29<13:01:05,  3.43it/s]
 57%|█████▋    | 210909/371472 [6:04:29<14:03:57,  3.17it/s]
 57%|█████▋    | 210910/371472 [6:04:30<14:28:47,  3.08it/s]
 57%|█████▋    | 210911/371472 [6:04:30<14:57:31,  2.98it/s]
 57%|█████▋    | 210912/371472 [6:04:30<14:27:06,  3.09it/s]
 57%|█████▋    | 210913/371472 [6:04:31<14:13:56,  3.13it/s]
 57%|█████▋    | 210914/371472 [6:04:31<13:46:25,  3.24it/s]
 57%|█████▋    | 210915/371472 [6:04:31<13:59:31,  3.19it/s]
 57%|█████▋    | 210916/371472 [6:04:31<13:57:34,  3.19it/s]
 57%|█████▋    | 210917/371472 [6:04:32<13:40:31,  3.26it/s]
 57%|█████▋    | 210918/371472 [6:04:32<13:34:08,  3.29it/s]
 57%|█████▋    | 210919/371472 [6:04:32<13:22:22,  3.33it/s]
 57%|█████▋    | 210920/371472 [6:04:33<13:19:11,  3.35it/s]
                                                            
{'loss': 2.8812, 'learning_rate': 4.891939063543709e-07, 'epoch': 9.08}
+
 57%|█████▋    | 210920/371472 [6:04:33<13:19:11,  3.35it/s]
 57%|█████▋    | 210921/371472 [6:04:33<13:12:48,  3.38it/s]
 57%|█████▋    | 210922/371472 [6:04:33<13:35:17,  3.28it/s]
 57%|█████▋    | 210923/371472 [6:04:33<13:09:37,  3.39it/s]
 57%|█████▋    | 210924/371472 [6:04:34<13:04:48,  3.41it/s]
 57%|█████▋    | 210925/371472 [6:04:34<13:33:31,  3.29it/s]
 57%|█████▋    | 210926/371472 [6:04:34<13:51:30,  3.22it/s]
 57%|█████▋    | 210927/371472 [6:04:35<13:41:56,  3.26it/s]
 57%|█████▋    | 210928/371472 [6:04:35<13:13:12,  3.37it/s]
 57%|█████▋    | 210929/371472 [6:04:35<13:18:51,  3.35it/s]
 57%|█████▋    | 210930/371472 [6:04:36<13:07:00,  3.40it/s]
 57%|█████▋    | 210931/371472 [6:04:36<13:37:32,  3.27it/s]
 57%|█████▋    | 210932/371472 [6:04:36<13:58:48,  3.19it/s]
 57%|█████▋    | 210933/371472 [6:04:37<14:36:33,  3.05it/s]
 57%|█████▋    | 210934/371472 [6:04:37<15:28:34,  2.88it/s]
 57%|█████▋    | 210935/371472 [6:04:37<16:02:07,  2.78it/s]
 57%|█████▋    | 210936/371472 [6:04:38<15:27:34,  2.88it/s]
 57%|█████▋    | 210937/371472 [6:04:38<14:44:55,  3.02it/s]
 57%|█████▋    | 210938/371472 [6:04:38<14:11:55,  3.14it/s]
 57%|█████▋    | 210939/371472 [6:04:39<15:16:16,  2.92it/s]
 57%|█████▋    | 210940/371472 [6:04:39<14:31:46,  3.07it/s]
                                                            
{'loss': 2.7509, 'learning_rate': 4.89145424378892e-07, 'epoch': 9.09}
+
 57%|█████▋    | 210940/371472 [6:04:39<14:31:46,  3.07it/s]
 57%|█████▋    | 210941/371472 [6:04:39<15:16:24,  2.92it/s]
 57%|█████▋    | 210942/371472 [6:04:40<14:51:38,  3.00it/s]
 57%|█████▋    | 210943/371472 [6:04:40<14:04:29,  3.17it/s]
 57%|█████▋    | 210944/371472 [6:04:40<14:00:21,  3.18it/s]
 57%|█████▋    | 210945/371472 [6:04:41<13:55:11,  3.20it/s]
 57%|█████▋    | 210946/371472 [6:04:41<14:00:28,  3.18it/s]
 57%|█████▋    | 210947/371472 [6:04:41<13:28:57,  3.31it/s]
 57%|█████▋    | 210948/371472 [6:04:41<13:12:49,  3.37it/s]
 57%|█████▋    | 210949/371472 [6:04:42<13:12:46,  3.37it/s]
 57%|█████▋    | 210950/371472 [6:04:42<13:22:30,  3.33it/s]
 57%|█████▋    | 210951/371472 [6:04:42<13:19:15,  3.35it/s]
 57%|█████▋    | 210952/371472 [6:04:43<13:15:03,  3.36it/s]
 57%|█████▋    | 210953/371472 [6:04:43<13:48:21,  3.23it/s]
 57%|█████▋    | 210954/371472 [6:04:43<15:27:15,  2.89it/s]
 57%|█████▋    | 210955/371472 [6:04:44<14:41:02,  3.04it/s]
 57%|█████▋    | 210956/371472 [6:04:44<14:15:50,  3.13it/s]
 57%|█████▋    | 210957/371472 [6:04:44<13:49:12,  3.23it/s]
 57%|█████▋    | 210958/371472 [6:04:45<14:02:43,  3.17it/s]
 57%|█████▋    | 210959/371472 [6:04:45<13:46:58,  3.23it/s]
 57%|█████▋    | 210960/371472 [6:04:45<13:35:29,  3.28it/s]
                                                            
{'loss': 2.6837, 'learning_rate': 4.89096942403413e-07, 'epoch': 9.09}
+
 57%|█████▋    | 210960/371472 [6:04:45<13:35:29,  3.28it/s]
 57%|█████▋    | 210961/371472 [6:04:46<14:07:35,  3.16it/s]
 57%|█████▋    | 210962/371472 [6:04:46<14:07:03,  3.16it/s]
 57%|█████▋    | 210963/371472 [6:04:46<14:12:21,  3.14it/s]
 57%|█████▋    | 210964/371472 [6:04:46<14:02:24,  3.18it/s]
 57%|█████▋    | 210965/371472 [6:04:47<13:57:04,  3.20it/s]
 57%|█████▋    | 210966/371472 [6:04:47<13:44:56,  3.24it/s]
 57%|█████▋    | 210967/371472 [6:04:47<13:42:16,  3.25it/s]
 57%|█████▋    | 210968/371472 [6:04:48<14:10:46,  3.14it/s]
 57%|█████▋    | 210969/371472 [6:04:48<13:58:47,  3.19it/s]
 57%|█████▋    | 210970/371472 [6:04:48<13:25:06,  3.32it/s]
 57%|█████▋    | 210971/371472 [6:04:49<13:16:28,  3.36it/s]
 57%|█████▋    | 210972/371472 [6:04:49<12:57:59,  3.44it/s]
 57%|█████▋    | 210973/371472 [6:04:49<13:16:23,  3.36it/s]
 57%|█████▋    | 210974/371472 [6:04:49<13:07:03,  3.40it/s]
 57%|█████▋    | 210975/371472 [6:04:50<12:52:52,  3.46it/s]
 57%|█████▋    | 210976/371472 [6:04:50<12:51:28,  3.47it/s]
 57%|█████▋    | 210977/371472 [6:04:50<12:42:56,  3.51it/s]
 57%|█████▋    | 210978/371472 [6:04:51<12:44:08,  3.50it/s]
 57%|█████▋    | 210979/371472 [6:04:51<12:55:07,  3.45it/s]
 57%|█████▋    | 210980/371472 [6:04:51<12:49:41,  3.48it/s]
                                                            
{'loss': 2.7617, 'learning_rate': 4.890484604279343e-07, 'epoch': 9.09}
+
 57%|█████▋    | 210980/371472 [6:04:51<12:49:41,  3.48it/s]
 57%|█████▋    | 210981/371472 [6:04:51<12:48:37,  3.48it/s]
 57%|█████▋    | 210982/371472 [6:04:52<13:06:36,  3.40it/s]
 57%|█████▋    | 210983/371472 [6:04:52<13:09:33,  3.39it/s]
 57%|█████▋    | 210984/371472 [6:04:52<13:39:54,  3.26it/s]
 57%|█████▋    | 210985/371472 [6:04:53<13:13:10,  3.37it/s]
 57%|█████▋    | 210986/371472 [6:04:53<12:56:20,  3.45it/s]
 57%|█████▋    | 210987/371472 [6:04:53<12:50:28,  3.47it/s]
 57%|█████▋    | 210988/371472 [6:04:54<12:41:41,  3.51it/s]
 57%|█████▋    | 210989/371472 [6:04:54<12:38:47,  3.53it/s]
 57%|█████▋    | 210990/371472 [6:04:54<12:39:40,  3.52it/s]
 57%|█████▋    | 210991/371472 [6:04:54<12:28:13,  3.57it/s]
 57%|█████▋    | 210992/371472 [6:04:55<12:50:59,  3.47it/s]
 57%|█████▋    | 210993/371472 [6:04:55<12:54:30,  3.45it/s]
 57%|█████▋    | 210994/371472 [6:04:55<12:59:05,  3.43it/s]
 57%|█████▋    | 210995/371472 [6:04:56<13:12:52,  3.37it/s]
 57%|█████▋    | 210996/371472 [6:04:56<13:59:32,  3.19it/s]
 57%|█████▋    | 210997/371472 [6:04:56<13:45:27,  3.24it/s]
 57%|█████▋    | 210998/371472 [6:04:57<13:31:10,  3.30it/s]
 57%|█████▋    | 210999/371472 [6:04:57<13:40:52,  3.26it/s]
 57%|█████▋    | 211000/371472 [6:04:57<13:53:12,  3.21it/s]
                                                            
{'loss': 2.7113, 'learning_rate': 4.889999784524553e-07, 'epoch': 9.09}
+
 57%|█████▋    | 211000/371472 [6:04:57<13:53:12,  3.21it/s]
 57%|█████▋    | 211001/371472 [6:04:57<13:41:14,  3.26it/s]
 57%|█████▋    | 211002/371472 [6:04:58<13:42:31,  3.25it/s]
 57%|█████▋    | 211003/371472 [6:04:58<14:45:45,  3.02it/s]
 57%|█████▋    | 211004/371472 [6:04:58<14:19:20,  3.11it/s]
 57%|█████▋    | 211005/371472 [6:04:59<14:26:38,  3.09it/s]
 57%|█████▋    | 211006/371472 [6:04:59<13:52:34,  3.21it/s]
 57%|█████▋    | 211007/371472 [6:04:59<13:47:34,  3.23it/s]
 57%|█████▋    | 211008/371472 [6:05:00<13:36:38,  3.27it/s]
 57%|█████▋    | 211009/371472 [6:05:00<13:31:48,  3.29it/s]
 57%|█████▋    | 211010/371472 [6:05:00<13:25:57,  3.32it/s]
 57%|█████▋    | 211011/371472 [6:05:01<14:10:09,  3.15it/s]
 57%|█████▋    | 211012/371472 [6:05:01<13:59:41,  3.18it/s]
 57%|█████▋    | 211013/371472 [6:05:01<13:46:25,  3.24it/s]
 57%|█████���    | 211014/371472 [6:05:01<13:20:07,  3.34it/s]
 57%|█████▋    | 211015/371472 [6:05:02<13:01:55,  3.42it/s]
 57%|█████▋    | 211016/371472 [6:05:02<12:48:02,  3.48it/s]
 57%|█████▋    | 211017/371472 [6:05:02<13:06:01,  3.40it/s]
 57%|█████▋    | 211018/371472 [6:05:03<12:52:40,  3.46it/s]
 57%|█████▋    | 211019/371472 [6:05:03<12:37:44,  3.53it/s]
 57%|█████▋    | 211020/371472 [6:05:03<12:59:14,  3.43it/s]
                                                            
{'loss': 2.8437, 'learning_rate': 4.889514964769764e-07, 'epoch': 9.09}
+
 57%|█████▋    | 211020/371472 [6:05:03<12:59:14,  3.43it/s]
 57%|█████▋    | 211021/371472 [6:05:04<13:14:53,  3.36it/s]
 57%|█████▋    | 211022/371472 [6:05:04<13:32:25,  3.29it/s]
 57%|█████▋    | 211023/371472 [6:05:04<14:07:31,  3.16it/s]
 57%|█████▋    | 211024/371472 [6:05:04<13:50:31,  3.22it/s]
 57%|█████▋    | 211025/371472 [6:05:05<13:51:43,  3.22it/s]
 57%|█████▋    | 211026/371472 [6:05:05<13:33:43,  3.29it/s]
 57%|█████▋    | 211027/371472 [6:05:05<13:11:50,  3.38it/s]
 57%|█████▋    | 211028/371472 [6:05:06<13:21:52,  3.33it/s]
 57%|█████▋    | 211029/371472 [6:05:06<13:14:39,  3.36it/s]
 57%|█████▋    | 211030/371472 [6:05:06<13:07:24,  3.40it/s]
 57%|█████▋    | 211031/371472 [6:05:07<12:40:48,  3.51it/s]
 57%|█████▋    | 211032/371472 [6:05:07<13:33:20,  3.29it/s]
 57%|█████▋    | 211033/371472 [6:05:07<13:26:57,  3.31it/s]
 57%|█████▋    | 211034/371472 [6:05:07<13:41:43,  3.25it/s]
 57%|█████▋    | 211035/371472 [6:05:08<13:28:48,  3.31it/s]
 57%|█████▋    | 211036/371472 [6:05:08<13:26:27,  3.32it/s]
 57%|█████▋    | 211037/371472 [6:05:08<13:27:36,  3.31it/s]
 57%|█████▋    | 211038/371472 [6:05:09<13:56:11,  3.20it/s]
 57%|█████▋    | 211039/371472 [6:05:09<13:42:28,  3.25it/s]
 57%|█████▋    | 211040/371472 [6:05:09<13:37:55,  3.27it/s]
                                                            
{'loss': 2.7288, 'learning_rate': 4.889030145014975e-07, 'epoch': 9.09}
+
 57%|█████▋    | 211040/371472 [6:05:09<13:37:55,  3.27it/s]
 57%|█████▋    | 211041/371472 [6:05:10<13:14:11,  3.37it/s]
 57%|█████▋    | 211042/371472 [6:05:10<12:52:04,  3.46it/s]
 57%|█████▋    | 211043/371472 [6:05:10<12:31:56,  3.56it/s]
 57%|█████▋    | 211044/371472 [6:05:10<12:49:23,  3.48it/s]
 57%|█████▋    | 211045/371472 [6:05:11<12:41:10,  3.51it/s]
 57%|█████▋    | 211046/371472 [6:05:11<12:26:44,  3.58it/s]
 57%|█████▋    | 211047/371472 [6:05:11<12:20:32,  3.61it/s]
 57%|█████▋    | 211048/371472 [6:05:12<12:33:08,  3.55it/s]
 57%|█████▋    | 211049/371472 [6:05:12<12:43:22,  3.50it/s]
 57%|█████▋    | 211050/371472 [6:05:12<13:24:28,  3.32it/s]
 57%|█████▋    | 211051/371472 [6:05:12<13:02:10,  3.42it/s]
 57%|█████▋    | 211052/371472 [6:05:13<13:01:04,  3.42it/s]
 57%|█████▋    | 211053/371472 [6:05:13<12:57:49,  3.44it/s]
 57%|█████▋    | 211054/371472 [6:05:13<12:54:16,  3.45it/s]
 57%|█████▋    | 211055/371472 [6:05:14<12:53:39,  3.46it/s]
 57%|█████▋    | 211056/371472 [6:05:14<12:49:04,  3.48it/s]
 57%|█████▋    | 211057/371472 [6:05:14<13:34:24,  3.28it/s]
 57%|█████▋    | 211058/371472 [6:05:14<13:13:28,  3.37it/s]
 57%|█████▋    | 211059/371472 [6:05:15<13:17:32,  3.35it/s]
 57%|█████▋    | 211060/371472 [6:05:15<13:04:19,  3.41it/s]
                                                            
{'loss': 2.9409, 'learning_rate': 4.888545325260186e-07, 'epoch': 9.09}
+
 57%|█████▋    | 211060/371472 [6:05:15<13:04:19,  3.41it/s]
 57%|█████▋    | 211061/371472 [6:05:15<13:30:54,  3.30it/s]
 57%|█████▋    | 211062/371472 [6:05:16<13:22:26,  3.33it/s]
 57%|█████▋    | 211063/371472 [6:05:16<14:08:53,  3.15it/s]
 57%|█████▋    | 211064/371472 [6:05:16<13:29:18,  3.30it/s]
 57%|█████▋    | 211065/371472 [6:05:17<13:38:56,  3.26it/s]
 57%|█████▋    | 211066/371472 [6:05:17<13:16:16,  3.36it/s]
 57%|█████▋    | 211067/371472 [6:05:17<13:11:50,  3.38it/s]
 57%|█████▋    | 211068/371472 [6:05:18<13:26:55,  3.31it/s]
 57%|█████▋    | 211069/371472 [6:05:18<13:39:41,  3.26it/s]
 57%|█████▋    | 211070/371472 [6:05:18<13:13:37,  3.37it/s]
 57%|█████▋    | 211071/371472 [6:05:18<13:05:24,  3.40it/s]
 57%|█████▋    | 211072/371472 [6:05:19<12:55:08,  3.45it/s]
 57%|█████▋    | 211073/371472 [6:05:19<12:49:44,  3.47it/s]
 57%|█████▋    | 211074/371472 [6:05:19<13:46:20,  3.24it/s]
 57%|█████▋    | 211075/371472 [6:05:20<13:27:49,  3.31it/s]
 57%|█████▋    | 211076/371472 [6:05:20<13:27:14,  3.31it/s]
 57%|█████▋    | 211077/371472 [6:05:20<13:04:18,  3.41it/s]
 57%|█████▋    | 211078/371472 [6:05:21<13:32:54,  3.29it/s]
 57%|█████▋    | 211079/371472 [6:05:21<13:47:34,  3.23it/s]
 57%|█████▋    | 211080/371472 [6:05:21<13:45:09,  3.24it/s]
                                                            
{'loss': 2.7346, 'learning_rate': 4.888060505505397e-07, 'epoch': 9.09}
+
 57%|█████▋    | 211080/371472 [6:05:21<13:45:09,  3.24it/s]
 57%|█████▋    | 211081/371472 [6:05:21<13:28:43,  3.31it/s]
 57%|█████▋    | 211082/371472 [6:05:22<13:05:46,  3.40it/s]
 57%|█████▋    | 211083/371472 [6:05:22<12:51:55,  3.46it/s]
 57%|█████▋    | 211084/371472 [6:05:22<12:57:52,  3.44it/s]
 57%|█████▋    | 211085/371472 [6:05:23<12:37:10,  3.53it/s]
 57%|█████▋    | 211086/371472 [6:05:23<13:00:08,  3.43it/s]
 57%|█████▋    | 211087/371472 [6:05:23<12:35:49,  3.54it/s]
 57%|█████▋    | 211088/371472 [6:05:23<12:40:05,  3.52it/s]
 57%|█████▋    | 211089/371472 [6:05:24<12:50:48,  3.47it/s]
 57%|█████▋    | 211090/371472 [6:05:24<12:33:47,  3.55it/s]
 57%|█████▋    | 211091/371472 [6:05:24<12:33:04,  3.55it/s]
 57%|█████▋    | 211092/371472 [6:05:25<12:45:39,  3.49it/s]
 57%|█████▋    | 211093/371472 [6:05:25<12:33:33,  3.55it/s]
 57%|█████▋    | 211094/371472 [6:05:25<12:35:40,  3.54it/s]
 57%|█████▋    | 211095/371472 [6:05:25<12:40:55,  3.51it/s]
 57%|█████▋    | 211096/371472 [6:05:26<12:31:30,  3.56it/s]
 57%|█████▋    | 211097/371472 [6:05:26<12:44:27,  3.50it/s]
 57%|█████▋    | 211098/371472 [6:05:26<12:46:22,  3.49it/s]
 57%|█████▋    | 211099/371472 [6:05:27<12:44:32,  3.50it/s]
 57%|█████▋    | 211100/371472 [6:05:27<12:45:34,  3.49it/s]
                                                            
{'loss': 2.7377, 'learning_rate': 4.88757568575061e-07, 'epoch': 9.09}
+
 57%|█████▋    | 211100/371472 [6:05:27<12:45:34,  3.49it/s]
 57%|█████▋    | 211101/371472 [6:05:27<12:41:25,  3.51it/s]
 57%|█████▋    | 211102/371472 [6:05:27<12:53:17,  3.46it/s]
 57%|█████▋    | 211103/371472 [6:05:28<13:04:56,  3.41it/s]
 57%|█████▋    | 211104/371472 [6:05:28<13:42:42,  3.25it/s]
 57%|█████▋    | 211105/371472 [6:05:28<13:15:59,  3.36it/s]
 57%|█████▋    | 211106/371472 [6:05:29<14:14:01,  3.13it/s]
 57%|█████▋    | 211107/371472 [6:05:29<14:21:02,  3.10it/s]
 57%|█████▋    | 211108/371472 [6:05:29<14:06:02,  3.16it/s]
 57%|█████▋    | 211109/371472 [6:05:30<14:17:15,  3.12it/s]
 57%|█████▋    | 211110/371472 [6:05:30<13:58:06,  3.19it/s]
 57%|█████▋    | 211111/371472 [6:05:30<13:54:23,  3.20it/s]
 57%|█████▋    | 211112/371472 [6:05:31<13:54:16,  3.20it/s]
 57%|█████▋    | 211113/371472 [6:05:31<13:45:02,  3.24it/s]
 57%|█████▋    | 211114/371472 [6:05:31<13:41:41,  3.25it/s]
 57%|█████▋    | 211115/371472 [6:05:31<13:12:52,  3.37it/s]
 57%|█████▋    | 211116/371472 [6:05:32<13:40:11,  3.26it/s]
 57%|█████▋    | 211117/371472 [6:05:32<13:12:30,  3.37it/s]
 57%|█████▋    | 211118/371472 [6:05:32<13:13:50,  3.37it/s]
 57%|█████▋    | 211119/371472 [6:05:33<13:13:50,  3.37it/s]
 57%|█████▋    | 211120/371472 [6:05:33<13:48:56,  3.22it/s]
                                                            
{'loss': 2.8065, 'learning_rate': 4.887090865995819e-07, 'epoch': 9.09}
+
 57%|█████▋    | 211120/371472 [6:05:33<13:48:56,  3.22it/s]
 57%|█████▋    | 211121/371472 [6:05:33<13:44:20,  3.24it/s]
 57%|█████▋    | 211122/371472 [6:05:34<13:36:41,  3.27it/s]
 57%|█████▋    | 211123/371472 [6:05:34<13:33:29,  3.29it/s]
 57%|█████▋    | 211124/371472 [6:05:34<13:17:15,  3.35it/s]
 57%|█████▋    | 211125/371472 [6:05:34<13:00:51,  3.42it/s]
 57%|█████▋    | 211126/371472 [6:05:35<12:34:45,  3.54it/s]
 57%|█████▋    | 211127/371472 [6:05:35<12:41:47,  3.51it/s]
 57%|█████▋    | 211128/371472 [6:05:35<13:00:01,  3.43it/s]
 57%|█████▋    | 211129/371472 [6:05:36<13:52:11,  3.21it/s]
 57%|█████▋    | 211130/371472 [6:05:36<13:25:52,  3.32it/s]
 57%|█████▋    | 211131/371472 [6:05:36<14:12:20,  3.14it/s]
 57%|█████▋    | 211132/371472 [6:05:37<14:24:30,  3.09it/s]
 57%|█████▋    | 211133/371472 [6:05:37<14:08:02,  3.15it/s]
 57%|█████▋    | 211134/371472 [6:05:37<13:44:12,  3.24it/s]
 57%|█████▋    | 211135/371472 [6:05:38<14:01:56,  3.17it/s]
 57%|█████▋    | 211136/371472 [6:05:38<14:02:29,  3.17it/s]
 57%|█████▋    | 211137/371472 [6:05:38<13:45:54,  3.24it/s]
 57%|█████▋    | 211138/371472 [6:05:38<13:27:42,  3.31it/s]
 57%|█████▋    | 211139/371472 [6:05:39<13:24:40,  3.32it/s]
 57%|█████▋    | 211140/371472 [6:05:39<13:15:59,  3.36it/s]
                                                            
{'loss': 2.7825, 'learning_rate': 4.886606046241031e-07, 'epoch': 9.09}
+
 57%|█████▋    | 211140/371472 [6:05:39<13:15:59,  3.36it/s]
 57%|█████▋    | 211141/371472 [6:05:39<13:22:41,  3.33it/s]
 57%|█████▋    | 211142/371472 [6:05:40<14:08:44,  3.15it/s]
 57%|█████▋    | 211143/371472 [6:05:40<13:55:43,  3.20it/s]
 57%|█████▋    | 211144/371472 [6:05:40<13:31:47,  3.29it/s]
 57%|█████▋    | 211145/371472 [6:05:41<12:52:49,  3.46it/s]
 57%|█████▋    | 211146/371472 [6:05:41<13:19:26,  3.34it/s]
 57%|█████▋    | 211147/371472 [6:05:41<13:30:44,  3.30it/s]
 57%|█████▋    | 211148/371472 [6:05:41<13:28:11,  3.31it/s]
 57%|█████▋    | 211149/371472 [6:05:42<13:21:08,  3.34it/s]
 57%|█████▋    | 211150/371472 [6:05:42<13:19:02,  3.34it/s]
 57%|█████▋    | 211151/371472 [6:05:42<13:30:18,  3.30it/s]
 57%|█████▋    | 211152/371472 [6:05:43<13:34:03,  3.28it/s]
 57%|█████▋    | 211153/371472 [6:05:43<13:14:10,  3.36it/s]
 57%|█████▋    | 211154/371472 [6:05:43<13:02:40,  3.41it/s]
 57%|█████▋    | 211155/371472 [6:05:44<12:44:44,  3.49it/s]
 57%|█████▋    | 211156/371472 [6:05:44<12:36:03,  3.53it/s]
 57%|█████▋    | 211157/371472 [6:05:44<12:34:07,  3.54it/s]
 57%|█████▋    | 211158/371472 [6:05:44<12:46:39,  3.49it/s]
 57%|█████▋    | 211159/371472 [6:05:45<12:41:10,  3.51it/s]
 57%|█████▋    | 211160/371472 [6:05:45<13:30:47,  3.30it/s]
                                                            
{'loss': 2.9028, 'learning_rate': 4.886121226486242e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211160/371472 [6:05:45<13:30:47,  3.30it/s]
 57%|█████▋    | 211161/371472 [6:05:45<13:17:06,  3.35it/s]
 57%|█████▋    | 211162/371472 [6:05:46<12:48:42,  3.48it/s]
 57%|█████▋    | 211163/371472 [6:05:46<12:46:55,  3.48it/s]
 57%|█████▋    | 211164/371472 [6:05:46<12:51:54,  3.46it/s]
 57%|█████▋    | 211165/371472 [6:05:46<13:17:10,  3.35it/s]
 57%|█████▋    | 211166/371472 [6:05:47<13:03:01,  3.41it/s]
 57%|█████▋    | 211167/371472 [6:05:47<12:54:16,  3.45it/s]
 57%|█████▋    | 211168/371472 [6:05:47<12:47:32,  3.48it/s]
 57%|█████▋    | 211169/371472 [6:05:48<14:43:55,  3.02it/s]
 57%|█████▋    | 211170/371472 [6:05:48<14:26:50,  3.08it/s]
 57%|█████▋    | 211171/371472 [6:05:48<14:11:03,  3.14it/s]
 57%|█████▋    | 211172/371472 [6:05:49<14:01:06,  3.18it/s]
 57%|█████▋    | 211173/371472 [6:05:49<13:50:23,  3.22it/s]
 57%|█████▋    | 211174/371472 [6:05:49<13:35:58,  3.27it/s]
 57%|█████▋    | 211175/371472 [6:05:50<13:28:06,  3.31it/s]
 57%|█████▋    | 211176/371472 [6:05:50<14:27:52,  3.08it/s]
 57%|█████▋    | 211177/371472 [6:05:50<14:24:36,  3.09it/s]
 57%|█████▋    | 211178/371472 [6:05:51<13:49:12,  3.22it/s]
 57%|█████▋    | 211179/371472 [6:05:51<13:24:06,  3.32it/s]
 57%|█████▋    | 211180/371472 [6:05:51<12:56:23,  3.44it/s]
                                                            
{'loss': 2.9024, 'learning_rate': 4.885636406731452e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211180/371472 [6:05:51<12:56:23,  3.44it/s]
 57%|█████▋    | 211181/371472 [6:05:51<13:21:14,  3.33it/s]
 57%|█████▋    | 211182/371472 [6:05:52<14:05:54,  3.16it/s]
 57%|█████▋    | 211183/371472 [6:05:52<13:28:23,  3.30it/s]
 57%|█████▋    | 211184/371472 [6:05:52<13:08:51,  3.39it/s]
 57%|█████▋    | 211185/371472 [6:05:53<12:56:38,  3.44it/s]
 57%|█████▋    | 211186/371472 [6:05:53<12:55:01,  3.45it/s]
 57%|█████▋    | 211187/371472 [6:05:53<12:57:55,  3.43it/s]
 57%|█████▋    | 211188/371472 [6:05:54<13:56:42,  3.19it/s]
 57%|█████▋    | 211189/371472 [6:05:54<13:58:13,  3.19it/s]
 57%|█████▋    | 211190/371472 [6:05:54<13:42:52,  3.25it/s]
 57%|█████▋    | 211191/371472 [6:05:54<13:30:49,  3.29it/s]
 57%|█████▋    | 211192/371472 [6:05:55<13:24:27,  3.32it/s]
 57%|█████▋    | 211193/371472 [6:05:55<13:11:24,  3.38it/s]
 57%|█████▋    | 211194/371472 [6:05:55<12:51:58,  3.46it/s]
 57%|█████▋    | 211195/371472 [6:05:56<12:49:17,  3.47it/s]
 57%|█████▋    | 211196/371472 [6:05:56<13:16:06,  3.36it/s]
 57%|█████▋    | 211197/371472 [6:05:56<14:48:32,  3.01it/s]
 57%|█████▋    | 211198/371472 [6:05:57<15:21:01,  2.90it/s]
 57%|��████▋    | 211199/371472 [6:05:57<14:45:11,  3.02it/s]
 57%|█████▋    | 211200/371472 [6:05:57<14:09:03,  3.15it/s]
                                                            
{'loss': 2.7885, 'learning_rate': 4.885151586976663e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211200/371472 [6:05:57<14:09:03,  3.15it/s]
 57%|█████▋    | 211201/371472 [6:05:58<13:57:25,  3.19it/s]
 57%|█████▋    | 211202/371472 [6:05:58<13:36:41,  3.27it/s]
 57%|█████▋    | 211203/371472 [6:05:58<13:13:00,  3.37it/s]
 57%|█████▋    | 211204/371472 [6:05:58<13:29:08,  3.30it/s]
 57%|█████▋    | 211205/371472 [6:05:59<13:37:46,  3.27it/s]
 57%|█████▋    | 211206/371472 [6:05:59<13:11:13,  3.38it/s]
 57%|█████▋    | 211207/371472 [6:05:59<13:56:39,  3.19it/s]
 57%|█████▋    | 211208/371472 [6:06:00<13:25:51,  3.31it/s]
 57%|█████▋    | 211209/371472 [6:06:00<13:18:55,  3.34it/s]
 57%|█████▋    | 211210/371472 [6:06:00<12:54:28,  3.45it/s]
 57%|█████▋    | 211211/371472 [6:06:00<12:37:25,  3.53it/s]
 57%|█████▋    | 211212/371472 [6:06:01<12:38:16,  3.52it/s]
 57%|█████▋    | 211213/371472 [6:06:01<13:44:45,  3.24it/s]
 57%|█████▋    | 211214/371472 [6:06:02<14:27:02,  3.08it/s]
 57%|█████▋    | 211215/371472 [6:06:02<13:58:33,  3.19it/s]
 57%|█████▋    | 211216/371472 [6:06:02<13:33:44,  3.28it/s]
 57%|█████▋    | 211217/371472 [6:06:02<13:14:52,  3.36it/s]
 57%|█████▋    | 211218/371472 [6:06:03<13:11:25,  3.37it/s]
 57%|█████▋    | 211219/371472 [6:06:03<13:18:39,  3.34it/s]
 57%|█████▋    | 211220/371472 [6:06:03<13:14:12,  3.36it/s]
                                                            
{'loss': 2.8232, 'learning_rate': 4.884666767221876e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211220/371472 [6:06:03<13:14:12,  3.36it/s]
 57%|█████▋    | 211221/371472 [6:06:04<13:03:53,  3.41it/s]
 57%|█████▋    | 211222/371472 [6:06:04<12:58:34,  3.43it/s]
 57%|█████▋    | 211223/371472 [6:06:04<13:50:44,  3.21it/s]
 57%|█████▋    | 211224/371472 [6:06:04<13:30:02,  3.30it/s]
 57%|█████▋    | 211225/371472 [6:06:05<13:12:47,  3.37it/s]
 57%|█████▋    | 211226/371472 [6:06:05<14:28:12,  3.08it/s]
 57%|█████▋    | 211227/371472 [6:06:05<14:16:56,  3.12it/s]
 57%|█████▋    | 211228/371472 [6:06:06<14:10:18,  3.14it/s]
 57%|█████▋    | 211229/371472 [6:06:06<14:41:16,  3.03it/s]
 57%|█████▋    | 211230/371472 [6:06:06<13:59:41,  3.18it/s]
 57%|█████▋    | 211231/371472 [6:06:07<13:37:47,  3.27it/s]
 57%|█████▋    | 211232/371472 [6:06:07<14:10:07,  3.14it/s]
 57%|█████▋    | 211233/371472 [6:06:07<14:12:38,  3.13it/s]
 57%|█████▋    | 211234/371472 [6:06:08<15:37:51,  2.85it/s]
 57%|█████▋    | 211235/371472 [6:06:08<15:08:19,  2.94it/s]
 57%|█████▋    | 211236/371472 [6:06:08<14:38:45,  3.04it/s]
 57%|█████▋    | 211237/371472 [6:06:09<14:06:24,  3.16it/s]
 57%|█████▋    | 211238/371472 [6:06:09<13:42:19,  3.25it/s]
 57%|█████▋    | 211239/371472 [6:06:09<13:38:06,  3.26it/s]
 57%|█████▋    | 211240/371472 [6:06:10<13:08:02,  3.39it/s]
                                                            
{'loss': 2.8803, 'learning_rate': 4.884181947467086e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211240/371472 [6:06:10<13:08:02,  3.39it/s]
 57%|█████▋    | 211241/371472 [6:06:10<12:59:29,  3.43it/s]
 57%|█████▋    | 211242/371472 [6:06:10<13:35:53,  3.27it/s]
 57%|█████▋    | 211243/371472 [6:06:10<13:50:58,  3.21it/s]
 57%|█████▋    | 211244/371472 [6:06:11<13:56:07,  3.19it/s]
 57%|█████▋    | 211245/371472 [6:06:11<14:01:25,  3.17it/s]
 57%|█████▋    | 211246/371472 [6:06:11<13:55:51,  3.19it/s]
 57%|█████▋    | 211247/371472 [6:06:12<14:03:59,  3.16it/s]
 57%|█████▋    | 211248/371472 [6:06:12<13:43:45,  3.24it/s]
 57%|█████▋    | 211249/371472 [6:06:12<13:11:46,  3.37it/s]
 57%|█████▋    | 211250/371472 [6:06:13<13:19:56,  3.34it/s]
 57%|█████▋    | 211251/371472 [6:06:13<13:16:53,  3.35it/s]
 57%|█████▋    | 211252/371472 [6:06:13<13:10:23,  3.38it/s]
 57%|█████▋    | 211253/371472 [6:06:14<13:50:49,  3.21it/s]
 57%|█████▋    | 211254/371472 [6:06:14<13:21:24,  3.33it/s]
 57%|█████▋    | 211255/371472 [6:06:14<13:24:02,  3.32it/s]
 57%|█████▋    | 211256/371472 [6:06:14<13:39:47,  3.26it/s]
 57%|█████▋    | 211257/371472 [6:06:15<13:13:28,  3.37it/s]
 57%|█████▋    | 211258/371472 [6:06:15<13:31:15,  3.29it/s]
 57%|█████▋    | 211259/371472 [6:06:15<13:07:17,  3.39it/s]
 57%|█████▋    | 211260/371472 [6:06:16<14:04:45,  3.16it/s]
                                                            
{'loss': 2.75, 'learning_rate': 4.883697127712297e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211260/371472 [6:06:16<14:04:45,  3.16it/s]
 57%|█████▋    | 211261/371472 [6:06:16<13:53:04,  3.21it/s]
 57%|█████▋    | 211262/371472 [6:06:16<13:22:34,  3.33it/s]
 57%|█████▋    | 211263/371472 [6:06:17<13:21:48,  3.33it/s]
 57%|█████▋    | 211264/371472 [6:06:17<13:01:37,  3.42it/s]
 57%|█████▋    | 211265/371472 [6:06:17<12:43:06,  3.50it/s]
 57%|█████▋    | 211266/371472 [6:06:17<12:55:13,  3.44it/s]
 57%|█████▋    | 211267/371472 [6:06:18<12:55:12,  3.44it/s]
 57%|█████▋    | 211268/371472 [6:06:18<13:07:30,  3.39it/s]
 57%|█████▋    | 211269/371472 [6:06:18<13:42:45,  3.25it/s]
 57%|█████▋    | 211270/371472 [6:06:19<13:21:51,  3.33it/s]
 57%|█████▋    | 211271/371472 [6:06:19<14:02:08,  3.17it/s]
 57%|█████▋    | 211272/371472 [6:06:19<13:55:49,  3.19it/s]
 57%|█████▋    | 211273/371472 [6:06:20<14:05:03,  3.16it/s]
 57%|█████▋    | 211274/371472 [6:06:20<13:29:09,  3.30it/s]
 57%|█████▋    | 211275/371472 [6:06:20<13:36:30,  3.27it/s]
 57%|█████▋    | 211276/371472 [6:06:21<14:04:22,  3.16it/s]
 57%|█████▋    | 211277/371472 [6:06:21<13:47:39,  3.23it/s]
 57%|█████▋    | 211278/371472 [6:06:21<13:33:07,  3.28it/s]
 57%|█████▋    | 211279/371472 [6:06:21<13:34:20,  3.28it/s]
 57%|█████▋    | 211280/371472 [6:06:22<13:10:48,  3.38it/s]
                                                            
{'loss': 2.6685, 'learning_rate': 4.883212307957508e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211280/371472 [6:06:22<13:10:48,  3.38it/s]
 57%|█████▋    | 211281/371472 [6:06:22<13:38:47,  3.26it/s]
 57%|█████▋    | 211282/371472 [6:06:22<13:48:41,  3.22it/s]
 57%|█████▋    | 211283/371472 [6:06:23<13:27:17,  3.31it/s]
 57%|█████▋    | 211284/371472 [6:06:23<13:19:57,  3.34it/s]
 57%|█████▋    | 211285/371472 [6:06:23<13:39:21,  3.26it/s]
 57%|█████▋    | 211286/371472 [6:06:24<13:10:57,  3.38it/s]
 57%|█████▋    | 211287/371472 [6:06:24<13:09:02,  3.38it/s]
 57%|█████▋    | 211288/371472 [6:06:24<13:05:52,  3.40it/s]
 57%|█████▋    | 211289/371472 [6:06:24<12:55:57,  3.44it/s]
 57%|█████▋    | 211290/371472 [6:06:25<12:48:30,  3.47it/s]
 57%|█████▋    | 211291/371472 [6:06:25<12:51:31,  3.46it/s]
 57%|█████▋    | 211292/371472 [6:06:25<12:49:20,  3.47it/s]
 57%|█████▋    | 211293/371472 [6:06:26<12:46:30,  3.48it/s]
 57%|█████▋    | 211294/371472 [6:06:26<13:29:51,  3.30it/s]
 57%|█████▋    | 211295/371472 [6:06:26<13:52:52,  3.21it/s]
 57%|█████▋    | 211296/371472 [6:06:27<13:41:30,  3.25it/s]
 57%|█████▋    | 211297/371472 [6:06:27<13:27:00,  3.31it/s]
 57%|█████▋    | 211298/371472 [6:06:27<13:10:35,  3.38it/s]
 57%|█████▋    | 211299/371472 [6:06:27<13:11:00,  3.37it/s]
 57%|█████▋    | 211300/371472 [6:06:28<13:20:39,  3.33it/s]
                                                            
{'loss': 2.7195, 'learning_rate': 4.882727488202719e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211300/371472 [6:06:28<13:20:39,  3.33it/s]
 57%|█████▋    | 211301/371472 [6:06:28<13:15:38,  3.36it/s]
 57%|█████▋    | 211302/371472 [6:06:28<13:20:10,  3.34it/s]
 57%|█████▋    | 211303/371472 [6:06:29<13:11:43,  3.37it/s]
 57%|█████▋    | 211304/371472 [6:06:29<13:09:43,  3.38it/s]
 57%|█████▋    | 211305/371472 [6:06:29<13:04:53,  3.40it/s]
 57%|█████▋    | 211306/371472 [6:06:30<14:40:22,  3.03it/s]
 57%|█████▋    | 211307/371472 [6:06:30<14:13:03,  3.13it/s]
 57%|█████▋    | 211308/371472 [6:06:30<14:31:12,  3.06it/s]
 57%|█████▋    | 211309/371472 [6:06:30<13:38:13,  3.26it/s]
 57%|█████▋    | 211310/371472 [6:06:31<13:01:47,  3.41it/s]
 57%|█████▋    | 211311/371472 [6:06:31<13:15:50,  3.35it/s]
 57%|█████▋    | 211312/371472 [6:06:31<13:22:34,  3.33it/s]
 57%|█████▋    | 211313/371472 [6:06:32<13:01:48,  3.41it/s]
 57%|█████▋    | 211314/371472 [6:06:32<13:36:44,  3.27it/s]
 57%|█████▋    | 211315/371472 [6:06:32<13:37:00,  3.27it/s]
 57%|█████▋    | 211316/371472 [6:06:33<13:05:54,  3.40it/s]
 57%|█████▋    | 211317/371472 [6:06:33<12:53:05,  3.45it/s]
 57%|█████▋    | 211318/371472 [6:06:33<13:07:22,  3.39it/s]
 57%|█████▋    | 211319/371472 [6:06:33<12:58:38,  3.43it/s]
 57%|█████▋    | 211320/371472 [6:06:34<13:13:54,  3.36it/s]
                                                            
{'loss': 2.6886, 'learning_rate': 4.882242668447929e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211320/371472 [6:06:34<13:13:54,  3.36it/s]
 57%|█████▋    | 211321/371472 [6:06:34<13:34:54,  3.28it/s]
 57%|█████▋    | 211322/371472 [6:06:34<14:12:03,  3.13it/s]
 57%|█████▋    | 211323/371472 [6:06:35<14:21:35,  3.10it/s]
 57%|█████▋    | 211324/371472 [6:06:35<14:00:40,  3.18it/s]
 57%|█████▋    | 211325/371472 [6:06:35<13:39:37,  3.26it/s]
 57%|█████▋    | 211326/371472 [6:06:36<13:35:48,  3.27it/s]
 57%|█████▋    | 211327/371472 [6:06:36<13:35:14,  3.27it/s]
 57%|█████▋    | 211328/371472 [6:06:36<13:27:39,  3.30it/s]
 57%|█████▋    | 211329/371472 [6:06:36<13:04:30,  3.40it/s]
 57%|█████▋    | 211330/371472 [6:06:37<13:02:28,  3.41it/s]
 57%|█████▋    | 211331/371472 [6:06:37<13:07:41,  3.39it/s]
 57%|█████▋    | 211332/371472 [6:06:37<12:58:09,  3.43it/s]
 57%|█████▋    | 211333/371472 [6:06:38<13:14:09,  3.36it/s]
 57%|█████▋    | 211334/371472 [6:06:38<13:11:46,  3.37it/s]
 57%|█████▋    | 211335/371472 [6:06:38<13:20:08,  3.34it/s]
 57%|█████▋    | 211336/371472 [6:06:39<13:20:31,  3.33it/s]
 57%|█████▋    | 211337/371472 [6:06:39<13:16:39,  3.35it/s]
 57%|█████▋    | 211338/371472 [6:06:39<13:19:19,  3.34it/s]
 57%|█████▋    | 211339/371472 [6:06:39<12:52:30,  3.45it/s]
 57%|█████▋    | 211340/371472 [6:06:40<13:55:00,  3.20it/s]
                                                            
{'loss': 2.6708, 'learning_rate': 4.881757848693142e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211340/371472 [6:06:40<13:55:00,  3.20it/s]
 57%|█████▋    | 211341/371472 [6:06:40<13:50:29,  3.21it/s]
 57%|█████▋    | 211342/371472 [6:06:40<14:14:50,  3.12it/s]
 57%|█████▋    | 211343/371472 [6:06:41<13:38:12,  3.26it/s]
 57%|█████▋    | 211344/371472 [6:06:41<13:53:34,  3.20it/s]
 57%|█████▋    | 211345/371472 [6:06:41<13:26:24,  3.31it/s]
 57%|█████▋    | 211346/371472 [6:06:42<12:57:42,  3.43it/s]
 57%|█████▋    | 211347/371472 [6:06:42<13:41:00,  3.25it/s]
 57%|█████▋    | 211348/371472 [6:06:42<13:45:46,  3.23it/s]
 57%|█████▋    | 211349/371472 [6:06:43<14:44:40,  3.02it/s]
 57%|█████▋    | 211350/371472 [6:06:43<14:17:42,  3.11it/s]
 57%|█████▋    | 211351/371472 [6:06:43<14:04:30,  3.16it/s]
 57%|█████▋    | 211352/371472 [6:06:44<14:10:36,  3.14it/s]
 57%|█████▋    | 211353/371472 [6:06:44<14:03:15,  3.16it/s]
 57%|█████▋    | 211354/371472 [6:06:44<13:33:39,  3.28it/s]
 57%|█████▋    | 211355/371472 [6:06:44<13:24:09,  3.32it/s]
 57%|█████▋    | 211356/371472 [6:06:45<13:02:15,  3.41it/s]
 57%|█████▋    | 211357/371472 [6:06:45<12:58:03,  3.43it/s]
 57%|█████▋    | 211358/371472 [6:06:45<12:37:54,  3.52it/s]
 57%|█████▋    | 211359/371472 [6:06:46<12:42:14,  3.50it/s]
 57%|█████▋    | 211360/371472 [6:06:46<12:58:57,  3.43it/s]
                                                            
{'loss': 2.77, 'learning_rate': 4.881273028938353e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211360/371472 [6:06:46<12:58:57,  3.43it/s]
 57%|█████▋    | 211361/371472 [6:06:46<12:51:57,  3.46it/s]
 57%|█████▋    | 211362/371472 [6:06:46<13:42:30,  3.24it/s]
 57%|█████▋    | 211363/371472 [6:06:47<13:47:03,  3.23it/s]
 57%|█████▋    | 211364/371472 [6:06:47<13:30:51,  3.29it/s]
 57%|█████▋    | 211365/371472 [6:06:47<13:30:14,  3.29it/s]
 57%|█████▋    | 211366/371472 [6:06:48<13:10:40,  3.37it/s]
 57%|█████▋    | 211367/371472 [6:06:48<12:56:20,  3.44it/s]
 57%|█████▋    | 211368/371472 [6:06:48<12:48:25,  3.47it/s]
 57%|█████▋    | 211369/371472 [6:06:49<12:59:14,  3.42it/s]
 57%|█████▋    | 211370/371472 [6:06:49<12:59:27,  3.42it/s]
 57%|█████▋    | 211371/371472 [6:06:49<12:47:55,  3.47it/s]
 57%|█████▋    | 211372/371472 [6:06:49<13:02:39,  3.41it/s]
 57%|█████▋    | 211373/371472 [6:06:50<13:20:34,  3.33it/s]
 57%|█████▋    | 211374/371472 [6:06:50<13:28:21,  3.30it/s]
 57%|█████▋    | 211375/371472 [6:06:50<13:34:06,  3.28it/s]
 57%|█████▋    | 211376/371472 [6:06:51<13:20:18,  3.33it/s]
 57%|█████▋    | 211377/371472 [6:06:51<13:43:26,  3.24it/s]
 57%|█████▋    | 211378/371472 [6:06:51<14:40:49,  3.03it/s]
 57%|█████▋    | 211379/371472 [6:06:52<14:25:33,  3.08it/s]
 57%|█████▋    | 211380/371472 [6:06:52<14:17:59,  3.11it/s]
                                                            
{'loss': 2.8255, 'learning_rate': 4.880788209183563e-07, 'epoch': 9.1}
+
 57%|█████▋    | 211380/371472 [6:06:52<14:17:59,  3.11it/s]
 57%|███���█▋    | 211381/371472 [6:06:52<13:56:04,  3.19it/s]
 57%|█████▋    | 211382/371472 [6:06:53<13:39:47,  3.25it/s]
 57%|█████▋    | 211383/371472 [6:06:53<13:52:04,  3.21it/s]
 57%|█████▋    | 211384/371472 [6:06:53<13:33:48,  3.28it/s]
 57%|█████▋    | 211385/371472 [6:06:54<14:11:37,  3.13it/s]
 57%|█████▋    | 211386/371472 [6:06:54<13:54:43,  3.20it/s]
 57%|█████▋    | 211387/371472 [6:06:54<14:17:06,  3.11it/s]
 57%|█████▋    | 211388/371472 [6:06:54<13:55:39,  3.19it/s]
 57%|█████▋    | 211389/371472 [6:06:55<13:42:33,  3.24it/s]
 57%|█████▋    | 211390/371472 [6:06:55<13:58:45,  3.18it/s]
 57%|█████▋    | 211391/371472 [6:06:55<13:43:57,  3.24it/s]
 57%|█████▋    | 211392/371472 [6:06:56<13:43:53,  3.24it/s]
 57%|█████▋    | 211393/371472 [6:06:56<13:22:04,  3.33it/s]
 57%|█████▋    | 211394/371472 [6:06:56<12:56:52,  3.43it/s]
 57%|█████▋    | 211395/371472 [6:06:57<12:59:24,  3.42it/s]
 57%|█████▋    | 211396/371472 [6:06:57<13:47:47,  3.22it/s]
 57%|█████▋    | 211397/371472 [6:06:57<13:57:53,  3.18it/s]
 57%|█████▋    | 211398/371472 [6:06:58<14:22:43,  3.09it/s]
 57%|█████▋    | 211399/371472 [6:06:58<15:00:26,  2.96it/s]
 57%|█████▋    | 211400/371472 [6:06:58<13:53:32,  3.20it/s]
                                                            
{'loss': 2.88, 'learning_rate': 4.880303389428774e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211400/371472 [6:06:58<13:53:32,  3.20it/s]
 57%|█████▋    | 211401/371472 [6:06:58<13:44:40,  3.24it/s]
 57%|█████▋    | 211402/371472 [6:06:59<13:26:01,  3.31it/s]
 57%|█████▋    | 211403/371472 [6:06:59<13:14:50,  3.36it/s]
 57%|█████▋    | 211404/371472 [6:06:59<12:58:24,  3.43it/s]
 57%|█████▋    | 211405/371472 [6:07:00<13:38:37,  3.26it/s]
 57%|█████▋    | 211406/371472 [6:07:00<13:16:48,  3.35it/s]
 57%|█████▋    | 211407/371472 [6:07:00<13:06:59,  3.39it/s]
 57%|█████▋    | 211408/371472 [6:07:01<13:37:42,  3.26it/s]
 57%|█████▋    | 211409/371472 [6:07:01<13:37:57,  3.26it/s]
 57%|█████▋    | 211410/371472 [6:07:01<13:22:52,  3.32it/s]
 57%|█████▋    | 211411/371472 [6:07:01<13:12:10,  3.37it/s]
 57%|█████▋    | 211412/371472 [6:07:02<13:16:04,  3.35it/s]
 57%|█████▋    | 211413/371472 [6:07:02<13:14:07,  3.36it/s]
 57%|█████▋    | 211414/371472 [6:07:02<12:53:28,  3.45it/s]
 57%|█████▋    | 211415/371472 [6:07:03<13:11:29,  3.37it/s]
 57%|█████▋    | 211416/371472 [6:07:03<12:40:21,  3.51it/s]
 57%|█████▋    | 211417/371472 [6:07:03<12:38:36,  3.52it/s]
 57%|█████▋    | 211418/371472 [6:07:04<13:16:28,  3.35it/s]
 57%|█████▋    | 211419/371472 [6:07:04<13:23:18,  3.32it/s]
 57%|█████▋    | 211420/371472 [6:07:04<13:15:04,  3.36it/s]
                                                            
{'loss': 2.8699, 'learning_rate': 4.879818569673985e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211420/371472 [6:07:04<13:15:04,  3.36it/s]
 57%|█████▋    | 211421/371472 [6:07:04<13:22:09,  3.33it/s]
 57%|█████▋    | 211422/371472 [6:07:05<13:00:51,  3.42it/s]
 57%|█████▋    | 211423/371472 [6:07:05<12:44:09,  3.49it/s]
 57%|█████▋    | 211424/371472 [6:07:05<12:32:13,  3.55it/s]
 57%|█████▋    | 211425/371472 [6:07:06<12:41:38,  3.50it/s]
 57%|█████▋    | 211426/371472 [6:07:06<12:53:47,  3.45it/s]
 57%|█████▋    | 211427/371472 [6:07:06<12:56:54,  3.43it/s]
 57%|█████▋    | 211428/371472 [6:07:06<12:58:45,  3.43it/s]
 57%|█████▋    | 211429/371472 [6:07:07<13:47:10,  3.22it/s]
 57%|█████▋    | 211430/371472 [6:07:07<13:51:39,  3.21it/s]
 57%|█████▋    | 211431/371472 [6:07:07<13:40:37,  3.25it/s]
 57%|█████▋    | 211432/371472 [6:07:08<13:47:54,  3.22it/s]
 57%|█████▋    | 211433/371472 [6:07:08<13:20:13,  3.33it/s]
 57%|█████▋    | 211434/371472 [6:07:08<13:01:48,  3.41it/s]
 57%|█████▋    | 211435/371472 [6:07:09<12:47:30,  3.48it/s]
 57%|█████▋    | 211436/371472 [6:07:09<12:43:53,  3.49it/s]
 57%|█████▋    | 211437/371472 [6:07:09<12:56:25,  3.44it/s]
 57%|█████▋    | 211438/371472 [6:07:09<12:51:05,  3.46it/s]
 57%|█████▋    | 211439/371472 [6:07:10<12:52:53,  3.45it/s]
 57%|█████▋    | 211440/371472 [6:07:10<12:40:20,  3.51it/s]
                                                            
{'loss': 2.8845, 'learning_rate': 4.879333749919196e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211440/371472 [6:07:10<12:40:20,  3.51it/s]
 57%|█████▋    | 211441/371472 [6:07:10<13:03:10,  3.41it/s]
 57%|█████▋    | 211442/371472 [6:07:11<12:59:17,  3.42it/s]
 57%|█████▋    | 211443/371472 [6:07:11<12:37:59,  3.52it/s]
 57%|█████▋    | 211444/371472 [6:07:11<12:47:26,  3.48it/s]
 57%|█████▋    | 211445/371472 [6:07:11<12:31:12,  3.55it/s]
 57%|█████▋    | 211446/371472 [6:07:12<14:54:00,  2.98it/s]
 57%|█████▋    | 211447/371472 [6:07:12<14:09:24,  3.14it/s]
 57%|█████▋    | 211448/371472 [6:07:12<14:05:29,  3.15it/s]
 57%|█████▋    | 211449/371472 [6:07:13<14:18:18,  3.11it/s]
 57%|█████▋    | 211450/371472 [6:07:13<14:56:39,  2.97it/s]
 57%|█████▋    | 211451/371472 [6:07:13<14:10:28,  3.14it/s]
 57%|█████▋    | 211452/371472 [6:07:14<14:29:08,  3.07it/s]
 57%|█████▋    | 211453/371472 [6:07:14<14:31:10,  3.06it/s]
 57%|█████▋    | 211454/371472 [6:07:14<15:14:10,  2.92it/s]
 57%|█████▋    | 211455/371472 [6:07:15<14:50:31,  2.99it/s]
 57%|█████▋    | 211456/371472 [6:07:15<14:01:43,  3.17it/s]
 57%|█████▋    | 211457/371472 [6:07:15<14:25:27,  3.08it/s]
 57%|█████▋    | 211458/371472 [6:07:16<14:02:42,  3.16it/s]
 57%|█████▋    | 211459/371472 [6:07:16<13:41:23,  3.25it/s]
 57%|█████▋    | 211460/371472 [6:07:16<13:24:07,  3.32it/s]
                                                            
{'loss': 2.6452, 'learning_rate': 4.878848930164407e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211460/371472 [6:07:16<13:24:07,  3.32it/s]
 57%|█████▋    | 211461/371472 [6:07:17<13:02:48,  3.41it/s]
 57%|█████▋    | 211462/371472 [6:07:17<13:45:34,  3.23it/s]
 57%|█████▋    | 211463/371472 [6:07:17<13:47:55,  3.22it/s]
 57%|█████▋    | 211464/371472 [6:07:18<14:26:15,  3.08it/s]
 57%|█████▋    | 211465/371472 [6:07:18<13:57:07,  3.19it/s]
 57%|█████▋    | 211466/371472 [6:07:18<13:32:33,  3.28it/s]
 57%|█████▋    | 211467/371472 [6:07:18<13:12:48,  3.36it/s]
 57%|█████▋    | 211468/371472 [6:07:19<13:00:10,  3.42it/s]
 57%|█████▋    | 211469/371472 [6:07:19<13:06:17,  3.39it/s]
 57%|█████▋    | 211470/371472 [6:07:19<13:07:47,  3.38it/s]
 57%|█████▋    | 211471/371472 [6:07:20<13:21:00,  3.33it/s]
 57%|█████▋    | 211472/371472 [6:07:20<13:23:01,  3.32it/s]
 57%|█████▋    | 211473/371472 [6:07:20<12:51:44,  3.46it/s]
 57%|█████▋    | 211474/371472 [6:07:20<12:49:54,  3.46it/s]
 57%|█████▋    | 211475/371472 [6:07:21<13:45:46,  3.23it/s]
 57%|█████▋    | 211476/371472 [6:07:21<13:12:44,  3.36it/s]
 57%|█████▋    | 211477/371472 [6:07:21<13:06:50,  3.39it/s]
 57%|█████▋    | 211478/371472 [6:07:22<13:46:57,  3.22it/s]
 57%|█████▋    | 211479/371472 [6:07:22<13:10:59,  3.37it/s]
 57%|█████▋    | 211480/371472 [6:07:22<13:16:05,  3.35it/s]
                                                            
{'loss': 2.7368, 'learning_rate': 4.878364110409619e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211480/371472 [6:07:22<13:16:05,  3.35it/s]
 57%|█████▋    | 211481/371472 [6:07:23<13:24:13,  3.32it/s]
 57%|█████▋    | 211482/371472 [6:07:23<13:33:42,  3.28it/s]
 57%|█████▋    | 211483/371472 [6:07:23<14:06:03,  3.15it/s]
 57%|█████▋    | 211484/371472 [6:07:24<14:01:52,  3.17it/s]
 57%|█████▋    | 211485/371472 [6:07:24<13:28:26,  3.30it/s]
 57%|█████▋    | 211486/371472 [6:07:24<13:45:00,  3.23it/s]
 57%|█████▋    | 211487/371472 [6:07:24<13:23:40,  3.32it/s]
 57%|█████▋    | 211488/371472 [6:07:25<13:24:44,  3.31it/s]
 57%|█████▋    | 211489/371472 [6:07:25<13:00:00,  3.42it/s]
 57%|█████▋    | 211490/371472 [6:07:25<14:13:09,  3.13it/s]
 57%|█████▋    | 211491/371472 [6:07:26<13:57:24,  3.18it/s]
 57%|█████▋    | 211492/371472 [6:07:26<13:59:38,  3.18it/s]
 57%|█████▋    | 211493/371472 [6:07:26<13:57:08,  3.19it/s]
 57%|█████▋    | 211494/371472 [6:07:27<13:31:49,  3.28it/s]
 57%|█████▋    | 211495/371472 [6:07:27<13:08:14,  3.38it/s]
 57%|█████▋    | 211496/371472 [6:07:27<13:04:43,  3.40it/s]
 57%|█████▋    | 211497/371472 [6:07:28<13:31:58,  3.28it/s]
 57%|█████▋    | 211498/371472 [6:07:28<13:51:02,  3.21it/s]
 57%|█████▋    | 211499/371472 [6:07:28<13:45:27,  3.23it/s]
 57%|█████▋    | 211500/371472 [6:07:28<13:27:46,  3.30it/s]
                                                            
{'loss': 2.6705, 'learning_rate': 4.877879290654829e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211500/371472 [6:07:28<13:27:46,  3.30it/s]
 57%|█████▋    | 211501/371472 [6:07:29<13:28:57,  3.30it/s]
 57%|█████▋    | 211502/371472 [6:07:29<13:16:14,  3.35it/s]
 57%|█████▋    | 211503/371472 [6:07:29<13:13:00,  3.36it/s]
 57%|█████▋    | 211504/371472 [6:07:30<13:58:58,  3.18it/s]
 57%|█████▋    | 211505/371472 [6:07:30<14:02:40,  3.16it/s]
 57%|█████▋    | 211506/371472 [6:07:30<13:40:53,  3.25it/s]
 57%|█████▋    | 211507/371472 [6:07:31<13:37:09,  3.26it/s]
 57%|█████▋    | 211508/371472 [6:07:31<13:15:39,  3.35it/s]
 57%|█████▋    | 211509/371472 [6:07:31<13:13:56,  3.36it/s]
 57%|█████▋    | 211510/371472 [6:07:31<13:36:56,  3.26it/s]
 57%|█████▋    | 211511/371472 [6:07:32<13:51:36,  3.21it/s]
 57%|█████▋    | 211512/371472 [6:07:32<13:35:47,  3.27it/s]
 57%|█████▋    | 211513/371472 [6:07:32<13:41:10,  3.25it/s]
 57%|█████▋    | 211514/371472 [6:07:33<13:35:19,  3.27it/s]
 57%|█████▋    | 211515/371472 [6:07:33<13:20:56,  3.33it/s]
 57%|█████▋    | 211516/371472 [6:07:33<13:30:09,  3.29it/s]
 57%|█████▋    | 211517/371472 [6:07:34<13:12:37,  3.36it/s]
 57%|█████▋    | 211518/371472 [6:07:34<14:01:00,  3.17it/s]
 57%|█████▋    | 211519/371472 [6:07:34<13:38:45,  3.26it/s]
 57%|█████▋    | 211520/371472 [6:07:35<13:25:27,  3.31it/s]
                                                            
{'loss': 2.9266, 'learning_rate': 4.877394470900041e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211520/371472 [6:07:35<13:25:27,  3.31it/s]
 57%|█████▋    | 211521/371472 [6:07:35<13:09:05,  3.38it/s]
 57%|█████▋    | 211522/371472 [6:07:35<13:22:16,  3.32it/s]
 57%|█████▋    | 211523/371472 [6:07:35<13:18:05,  3.34it/s]
 57%|█████▋    | 211524/371472 [6:07:36<13:07:30,  3.39it/s]
 57%|█████▋    | 211525/371472 [6:07:36<12:58:04,  3.43it/s]
 57%|█████▋    | 211526/371472 [6:07:36<12:57:39,  3.43it/s]
 57%|█████▋    | 211527/371472 [6:07:37<13:19:29,  3.33it/s]
 57%|█████▋    | 211528/371472 [6:07:37<13:09:36,  3.38it/s]
 57%|█████▋    | 211529/371472 [6:07:37<14:32:23,  3.06it/s]
 57%|█████▋    | 211530/371472 [6:07:38<14:30:30,  3.06it/s]
 57%|█████▋    | 211531/371472 [6:07:38<14:21:29,  3.09it/s]
 57%|█████▋    | 211532/371472 [6:07:38<13:50:58,  3.21it/s]
 57%|█████▋    | 211533/371472 [6:07:39<13:31:16,  3.29it/s]
 57%|█████▋    | 211534/371472 [6:07:39<13:34:34,  3.27it/s]
 57%|█████▋    | 211535/371472 [6:07:39<13:20:09,  3.33it/s]
 57%|█████▋    | 211536/371472 [6:07:39<13:27:32,  3.30it/s]
 57%|█████▋    | 211537/371472 [6:07:40<13:15:40,  3.35it/s]
 57%|█████▋    | 211538/371472 [6:07:40<12:58:25,  3.42it/s]
 57%|█████▋    | 211539/371472 [6:07:40<12:55:44,  3.44it/s]
 57%|█████▋    | 211540/371472 [6:07:41<13:24:31,  3.31it/s]
                                                            
{'loss': 2.7933, 'learning_rate': 4.876909651145252e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211540/371472 [6:07:41<13:24:31,  3.31it/s]
 57%|█████▋    | 211541/371472 [6:07:41<13:02:05,  3.41it/s]
 57%|█████▋    | 211542/371472 [6:07:41<13:11:57,  3.37it/s]
 57%|█████▋    | 211543/371472 [6:07:41<13:11:38,  3.37it/s]
 57%|█████▋    | 211544/371472 [6:07:42<13:04:20,  3.40it/s]
 57%|█████▋    | 211545/371472 [6:07:42<12:44:05,  3.49it/s]
 57%|█████▋    | 211546/371472 [6:07:42<13:03:45,  3.40it/s]
 57%|█████▋    | 211547/371472 [6:07:43<13:24:52,  3.31it/s]
 57%|█████▋    | 211548/371472 [6:07:43<13:17:40,  3.34it/s]
 57%|█████▋    | 211549/371472 [6:07:43<14:09:46,  3.14it/s]
 57%|█████▋    | 211550/371472 [6:07:44<13:28:48,  3.30it/s]
 57%|█████▋    | 211551/371472 [6:07:44<13:55:09,  3.19it/s]
 57%|█████▋    | 211552/371472 [6:07:44<14:57:02,  2.97it/s]
 57%|█████▋    | 211553/371472 [6:07:45<14:19:42,  3.10it/s]
 57%|█████▋    | 211554/371472 [6:07:45<13:57:14,  3.18it/s]
 57%|█████▋    | 211555/371472 [6:07:45<14:08:25,  3.14it/s]
 57%|█████▋    | 211556/371472 [6:07:46<13:44:56,  3.23it/s]
 57%|█████▋    | 211557/371472 [6:07:46<14:11:11,  3.13it/s]
 57%|█████▋    | 211558/371472 [6:07:46<14:03:43,  3.16it/s]
 57%|█████▋    | 211559/371472 [6:07:46<13:56:33,  3.19it/s]
 57%|█████▋    | 211560/371472 [6:07:47<14:06:08,  3.15it/s]
                                                            
{'loss': 2.8466, 'learning_rate': 4.876424831390462e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211560/371472 [6:07:47<14:06:08,  3.15it/s]
 57%|█████▋    | 211561/371472 [6:07:47<13:40:07,  3.25it/s]
 57%|█████▋    | 211562/371472 [6:07:47<13:28:24,  3.30it/s]
 57%|█████▋    | 211563/371472 [6:07:48<13:44:20,  3.23it/s]
 57%|█████▋    | 211564/371472 [6:07:48<14:22:06,  3.09it/s]
 57%|█████▋    | 211565/371472 [6:07:48<14:20:47,  3.10it/s]
 57%|█████▋    | 211566/371472 [6:07:49<14:39:40,  3.03it/s]
 57%|█████▋    | 211567/371472 [6:07:49<14:21:48,  3.09it/s]
 57%|█████▋    | 211568/371472 [6:07:49<13:53:44,  3.20it/s]
 57%|█████▋    | 211569/371472 [6:07:50<13:33:38,  3.28it/s]
 57%|█████▋    | 211570/371472 [6:07:50<13:05:42,  3.39it/s]
 57%|█████▋    | 211571/371472 [6:07:50<13:01:43,  3.41it/s]
 57%|█████▋    | 211572/371472 [6:07:50<12:54:36,  3.44it/s]
 57%|█████▋    | 211573/371472 [6:07:51<13:08:43,  3.38it/s]
 57%|█████▋    | 211574/371472 [6:07:51<12:46:58,  3.47it/s]
 57%|█████▋    | 211575/371472 [6:07:51<12:52:05,  3.45it/s]
 57%|█████▋    | 211576/371472 [6:07:52<13:22:22,  3.32it/s]
 57%|█████▋    | 211577/371472 [6:07:52<13:09:15,  3.38it/s]
 57%|█████▋    | 211578/371472 [6:07:52<13:14:08,  3.36it/s]
 57%|█████▋    | 211579/371472 [6:07:53<13:17:02,  3.34it/s]
 57%|█████▋    | 211580/371472 [6:07:53<13:37:53,  3.26it/s]
                                                            
{'loss': 2.6953, 'learning_rate': 4.875940011635673e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211580/371472 [6:07:53<13:37:53,  3.26it/s]
 57%|█████▋    | 211581/371472 [6:07:53<13:22:48,  3.32it/s]
 57%|█████▋    | 211582/371472 [6:07:53<13:30:57,  3.29it/s]
 57%|█████▋    | 211583/371472 [6:07:54<13:04:24,  3.40it/s]
 57%|█████▋    | 211584/371472 [6:07:54<12:57:38,  3.43it/s]
 57%|█████▋    | 211585/371472 [6:07:54<13:00:10,  3.42it/s]
 57%|█████▋    | 211586/371472 [6:07:55<12:46:37,  3.48it/s]
 57%|█████▋    | 211587/371472 [6:07:55<12:46:23,  3.48it/s]
 57%|█████▋    | 211588/371472 [6:07:55<12:44:58,  3.48it/s]
 57%|█████▋    | 211589/371472 [6:07:56<14:04:57,  3.15it/s]
 57%|█████▋    | 211590/371472 [6:07:56<14:07:16,  3.15it/s]
 57%|█████▋    | 211591/371472 [6:07:56<14:01:52,  3.17it/s]
 57%|█████▋    | 211592/371472 [6:07:56<13:33:41,  3.27it/s]
 57%|█████▋    | 211593/371472 [6:07:57<15:13:39,  2.92it/s]
 57%|█████▋    | 211594/371472 [6:07:57<14:39:17,  3.03it/s]
 57%|█████▋    | 211595/371472 [6:07:58<14:45:18,  3.01it/s]
 57%|█████▋    | 211596/371472 [6:07:58<15:44:02,  2.82it/s]
 57%|█████▋    | 211597/371472 [6:07:58<15:27:22,  2.87it/s]
 57%|█████▋    | 211598/371472 [6:07:59<15:07:12,  2.94it/s]
 57%|█████▋    | 211599/371472 [6:07:59<14:52:37,  2.99it/s]
 57%|█████▋    | 211600/371472 [6:07:59<14:28:28,  3.07it/s]
                                                            
{'loss': 2.7673, 'learning_rate': 4.875455191880886e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211600/371472 [6:07:59<14:28:28,  3.07it/s]
 57%|█████▋    | 211601/371472 [6:08:00<14:31:06,  3.06it/s]
 57%|█████▋    | 211602/371472 [6:08:00<14:34:24,  3.05it/s]
 57%|█████▋    | 211603/371472 [6:08:00<14:57:46,  2.97it/s]
 57%|█████▋    | 211604/371472 [6:08:01<14:21:59,  3.09it/s]
 57%|█████▋    | 211605/371472 [6:08:01<14:17:05,  3.11it/s]
 57%|█████▋    | 211606/371472 [6:08:01<14:02:21,  3.16it/s]
 57%|█████▋    | 211607/371472 [6:08:01<13:57:27,  3.18it/s]
 57%|█████▋    | 211608/371472 [6:08:02<13:36:38,  3.26it/s]
 57%|█████▋    | 211609/371472 [6:08:02<13:35:51,  3.27it/s]
 57%|█████▋    | 211610/371472 [6:08:02<13:41:10,  3.24it/s]
 57%|█████▋    | 211611/371472 [6:08:03<13:38:38,  3.25it/s]
 57%|█████▋    | 211612/371472 [6:08:03<13:24:58,  3.31it/s]
 57%|█████▋    | 211613/371472 [6:08:04<16:56:05,  2.62it/s]
 57%|█████▋    | 211614/371472 [6:08:04<15:58:39,  2.78it/s]
 57%|█████▋    | 211615/371472 [6:08:04<15:07:49,  2.93it/s]
 57%|█████▋    | 211616/371472 [6:08:04<15:10:04,  2.93it/s]
 57%|█████▋    | 211617/371472 [6:08:05<14:27:19,  3.07it/s]
 57%|█████▋    | 211618/371472 [6:08:05<14:01:18,  3.17it/s]
 57%|█████▋    | 211619/371472 [6:08:05<14:43:14,  3.02it/s]
 57%|█████▋    | 211620/371472 [6:08:06<14:05:03,  3.15it/s]
                                                            
{'loss': 2.7531, 'learning_rate': 4.874970372126097e-07, 'epoch': 9.11}
+
 57%|█████▋    | 211620/371472 [6:08:06<14:05:03,  3.15it/s]
 57%|█████▋    | 211621/371472 [6:08:06<13:51:29,  3.20it/s]
 57%|█████▋    | 211622/371472 [6:08:06<13:59:04,  3.18it/s]
 57%|█████▋    | 211623/371472 [6:08:07<13:40:29,  3.25it/s]
 57%|█████▋    | 211624/371472 [6:08:07<13:23:12,  3.32it/s]
 57%|█████▋    | 211625/371472 [6:08:07<13:49:15,  3.21it/s]
 57%|█████▋    | 211626/371472 [6:08:08<14:36:18,  3.04it/s]
 57%|█████▋    | 211627/371472 [6:08:08<14:04:51,  3.15it/s]
 57%|█████▋    | 211628/371472 [6:08:08<13:54:35,  3.19it/s]
 57%|█████▋    | 211629/371472 [6:08:09<13:28:25,  3.30it/s]
 57%|█████▋    | 211630/371472 [6:08:09<13:15:40,  3.35it/s]
 57%|█████▋    | 211631/371472 [6:08:09<13:17:14,  3.34it/s]
 57%|█████▋    | 211632/371472 [6:08:09<12:58:04,  3.42it/s]
 57%|█████▋    | 211633/371472 [6:08:10<13:09:38,  3.37it/s]
 57%|█████▋    | 211634/371472 [6:08:10<12:48:24,  3.47it/s]
 57%|█████▋    | 211635/371472 [6:08:10<13:01:56,  3.41it/s]
 57%|█████▋    | 211636/371472 [6:08:11<13:27:46,  3.30it/s]
 57%|█████▋    | 211637/371472 [6:08:11<13:21:40,  3.32it/s]
 57%|█████▋    | 211638/371472 [6:08:11<13:33:02,  3.28it/s]
 57%|█████▋    | 211639/371472 [6:08:11<13:37:20,  3.26it/s]
 57%|█████▋    | 211640/371472 [6:08:12<13:50:21,  3.21it/s]
                                                            
{'loss': 2.7172, 'learning_rate': 4.874485552371307e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211640/371472 [6:08:12<13:50:21,  3.21it/s]
 57%|█████▋    | 211641/371472 [6:08:12<14:34:50,  3.04it/s]
 57%|█████▋    | 211642/371472 [6:08:12<13:58:45,  3.18it/s]
 57%|█████▋    | 211643/371472 [6:08:13<13:41:08,  3.24it/s]
 57%|█████▋    | 211644/371472 [6:08:13<13:20:25,  3.33it/s]
 57%|█████▋    | 211645/371472 [6:08:13<13:21:19,  3.32it/s]
 57%|█████▋    | 211646/371472 [6:08:14<13:26:28,  3.30it/s]
 57%|█████▋    | 211647/371472 [6:08:14<13:22:15,  3.32it/s]
 57%|█████▋    | 211648/371472 [6:08:14<13:06:41,  3.39it/s]
 57%|█████▋    | 211649/371472 [6:08:15<13:13:41,  3.36it/s]
 57%|█████▋    | 211650/371472 [6:08:15<13:43:39,  3.23it/s]
 57%|█████▋    | 211651/371472 [6:08:15<13:15:31,  3.35it/s]
 57%|█████▋    | 211652/371472 [6:08:15<13:43:51,  3.23it/s]
 57%|█████▋    | 211653/371472 [6:08:16<14:19:24,  3.10it/s]
 57%|█████▋    | 211654/371472 [6:08:16<14:23:21,  3.09it/s]
 57%|█████▋    | 211655/371472 [6:08:16<14:09:39,  3.13it/s]
 57%|█████▋    | 211656/371472 [6:08:17<14:34:09,  3.05it/s]
 57%|█████▋    | 211657/371472 [6:08:17<14:08:47,  3.14it/s]
 57%|█████▋    | 211658/371472 [6:08:17<14:06:14,  3.15it/s]
 57%|█████▋    | 211659/371472 [6:08:18<14:07:21,  3.14it/s]
 57%|█████▋    | 211660/371472 [6:08:18<13:35:44,  3.27it/s]
                                                            
{'loss': 2.9402, 'learning_rate': 4.874000732616518e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211660/371472 [6:08:18<13:35:44,  3.27it/s]
 57%|█████▋    | 211661/371472 [6:08:18<13:33:03,  3.28it/s]
 57%|█████▋    | 211662/371472 [6:08:19<13:35:57,  3.26it/s]
 57%|█████▋    | 211663/371472 [6:08:19<13:17:14,  3.34it/s]
 57%|█████▋    | 211664/371472 [6:08:19<13:14:30,  3.35it/s]
 57%|█████▋    | 211665/371472 [6:08:19<12:51:30,  3.45it/s]
 57%|█████▋    | 211666/371472 [6:08:20<12:35:16,  3.53it/s]
 57%|█████▋    | 211667/371472 [6:08:20<12:52:34,  3.45it/s]
 57%|█████▋    | 211668/371472 [6:08:20<12:50:41,  3.46it/s]
 57%|█████▋    | 211669/371472 [6:08:21<13:15:16,  3.35it/s]
 57%|█████▋    | 211670/371472 [6:08:21<13:09:42,  3.37it/s]
 57%|█████▋    | 211671/371472 [6:08:21<13:06:13,  3.39it/s]
 57%|█████▋    | 211672/371472 [6:08:22<12:57:42,  3.42it/s]
 57%|█████▋    | 211673/371472 [6:08:22<12:59:47,  3.42it/s]
 57%|█████▋    | 211674/371472 [6:08:22<13:00:40,  3.41it/s]
 57%|█████▋    | 211675/371472 [6:08:22<13:23:35,  3.31it/s]
 57%|█████▋    | 211676/371472 [6:08:23<13:15:15,  3.35it/s]
 57%|█████▋    | 211677/371472 [6:08:23<13:03:22,  3.40it/s]
 57%|█████▋    | 211678/371472 [6:08:23<13:07:18,  3.38it/s]
 57%|█████▋    | 211679/371472 [6:08:24<13:20:43,  3.33it/s]
 57%|█████▋    | 211680/371472 [6:08:24<12:54:19,  3.44it/s]
                                                            
{'loss': 2.8385, 'learning_rate': 4.873515912861729e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211680/371472 [6:08:24<12:54:19,  3.44it/s]
 57%|█████▋    | 211681/371472 [6:08:24<14:28:33,  3.07it/s]
 57%|█████▋    | 211682/371472 [6:08:25<14:08:19,  3.14it/s]
 57%|█████▋    | 211683/371472 [6:08:25<13:39:11,  3.25it/s]
 57%|█████▋    | 211684/371472 [6:08:25<13:49:37,  3.21it/s]
 57%|█████▋    | 211685/371472 [6:08:26<13:46:50,  3.22it/s]
 57%|█████▋    | 211686/371472 [6:08:26<13:25:45,  3.31it/s]
 57%|█████▋    | 211687/371472 [6:08:26<13:12:43,  3.36it/s]
 57%|█████▋    | 211688/371472 [6:08:26<12:56:01,  3.43it/s]
 57%|██��██▋    | 211689/371472 [6:08:27<12:57:02,  3.43it/s]
 57%|█████▋    | 211690/371472 [6:08:27<12:59:37,  3.42it/s]
 57%|█████▋    | 211691/371472 [6:08:27<13:43:09,  3.24it/s]
 57%|█████▋    | 211692/371472 [6:08:28<13:40:52,  3.24it/s]
 57%|█████▋    | 211693/371472 [6:08:28<13:44:50,  3.23it/s]
 57%|█████▋    | 211694/371472 [6:08:28<14:33:45,  3.05it/s]
 57%|█████▋    | 211695/371472 [6:08:29<14:07:46,  3.14it/s]
 57%|█████▋    | 211696/371472 [6:08:29<13:43:15,  3.23it/s]
 57%|█████▋    | 211697/371472 [6:08:29<13:23:47,  3.31it/s]
 57%|█████▋    | 211698/371472 [6:08:29<13:38:15,  3.25it/s]
 57%|█████▋    | 211699/371472 [6:08:30<13:20:25,  3.33it/s]
 57%|█████▋    | 211700/371472 [6:08:30<13:03:23,  3.40it/s]
                                                            
{'loss': 2.6852, 'learning_rate': 4.873031093106939e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211700/371472 [6:08:30<13:03:23,  3.40it/s]
 57%|█████▋    | 211701/371472 [6:08:30<13:15:17,  3.35it/s]
 57%|█████▋    | 211702/371472 [6:08:31<12:58:56,  3.42it/s]
 57%|█████▋    | 211703/371472 [6:08:31<13:14:38,  3.35it/s]
 57%|█████▋    | 211704/371472 [6:08:31<13:17:00,  3.34it/s]
 57%|█████▋    | 211705/371472 [6:08:32<14:09:00,  3.14it/s]
 57%|█████▋    | 211706/371472 [6:08:32<13:30:15,  3.29it/s]
 57%|█████▋    | 211707/371472 [6:08:32<13:36:11,  3.26it/s]
 57%|█████▋    | 211708/371472 [6:08:32<13:15:06,  3.35it/s]
 57%|█████▋    | 211709/371472 [6:08:33<13:04:24,  3.39it/s]
 57%|█████▋    | 211710/371472 [6:08:33<13:04:25,  3.39it/s]
 57%|█████▋    | 211711/371472 [6:08:33<13:18:26,  3.33it/s]
 57%|█████▋    | 211712/371472 [6:08:34<13:06:21,  3.39it/s]
 57%|█████▋    | 211713/371472 [6:08:34<13:25:04,  3.31it/s]
 57%|█████▋    | 211714/371472 [6:08:34<13:18:13,  3.34it/s]
 57%|█████▋    | 211715/371472 [6:08:35<13:14:40,  3.35it/s]
 57%|█████▋    | 211716/371472 [6:08:35<13:27:29,  3.30it/s]
 57%|█████▋    | 211717/371472 [6:08:36<19:07:52,  2.32it/s]
 57%|█████▋    | 211718/371472 [6:08:36<17:08:39,  2.59it/s]
 57%|█████▋    | 211719/371472 [6:08:36<16:04:19,  2.76it/s]
 57%|█████▋    | 211720/371472 [6:08:36<14:58:09,  2.96it/s]
                                                            
{'loss': 2.8735, 'learning_rate': 4.872546273352152e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211720/371472 [6:08:36<14:58:09,  2.96it/s]
 57%|█████▋    | 211721/371472 [6:08:37<14:25:50,  3.08it/s]
 57%|█████▋    | 211722/371472 [6:08:37<13:58:33,  3.18it/s]
 57%|█████▋    | 211723/371472 [6:08:37<13:47:57,  3.22it/s]
 57%|█████▋    | 211724/371472 [6:08:38<14:18:43,  3.10it/s]
 57%|█████▋    | 211725/371472 [6:08:38<14:04:54,  3.15it/s]
 57%|█████▋    | 211726/371472 [6:08:38<13:31:31,  3.28it/s]
 57%|█████▋    | 211727/371472 [6:08:39<13:15:27,  3.35it/s]
 57%|█████▋    | 211728/371472 [6:08:39<13:04:07,  3.40it/s]
 57%|█████▋    | 211729/371472 [6:08:39<12:54:14,  3.44it/s]
 57%|█████▋    | 211730/371472 [6:08:39<12:51:21,  3.45it/s]
 57%|█████▋    | 211731/371472 [6:08:40<13:07:41,  3.38it/s]
 57%|█████▋    | 211732/371472 [6:08:40<13:58:10,  3.18it/s]
 57%|█████▋    | 211733/371472 [6:08:40<13:34:48,  3.27it/s]
 57%|█████▋    | 211734/371472 [6:08:41<13:35:39,  3.26it/s]
 57%|█████▋    | 211735/371472 [6:08:41<14:05:14,  3.15it/s]
 57%|█████▋    | 211736/371472 [6:08:41<13:43:28,  3.23it/s]
 57%|█████▋    | 211737/371472 [6:08:42<13:41:20,  3.24it/s]
 57%|█████▋    | 211738/371472 [6:08:42<13:37:15,  3.26it/s]
 57%|█████▋    | 211739/371472 [6:08:42<13:20:19,  3.33it/s]
 57%|█████▋    | 211740/371472 [6:08:43<13:10:55,  3.37it/s]
                                                            
{'loss': 2.7933, 'learning_rate': 4.872061453597363e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211740/371472 [6:08:43<13:10:55,  3.37it/s]
 57%|█████▋    | 211741/371472 [6:08:43<14:12:21,  3.12it/s]
 57%|█████▋    | 211742/371472 [6:08:43<14:10:47,  3.13it/s]
 57%|█████▋    | 211743/371472 [6:08:44<14:13:52,  3.12it/s]
 57%|█████▋    | 211744/371472 [6:08:44<13:54:31,  3.19it/s]
 57%|█████▋    | 211745/371472 [6:08:44<13:46:13,  3.22it/s]
 57%|█████▋    | 211746/371472 [6:08:44<13:37:33,  3.26it/s]
 57%|█████▋    | 211747/371472 [6:08:45<13:04:48,  3.39it/s]
 57%|█████▋    | 211748/371472 [6:08:45<13:03:55,  3.40it/s]
 57%|█████▋    | 211749/371472 [6:08:45<13:00:49,  3.41it/s]
 57%|█████▋    | 211750/371472 [6:08:46<13:01:08,  3.41it/s]
 57%|█████▋    | 211751/371472 [6:08:46<13:45:48,  3.22it/s]
 57%|█████▋    | 211752/371472 [6:08:46<13:50:46,  3.20it/s]
 57%|█████▋    | 211753/371472 [6:08:47<14:14:57,  3.11it/s]
 57%|█████▋    | 211754/371472 [6:08:47<13:50:56,  3.20it/s]
 57%|█████▋    | 211755/371472 [6:08:47<13:59:46,  3.17it/s]
 57%|█████▋    | 211756/371472 [6:08:48<14:55:18,  2.97it/s]
 57%|█████▋    | 211757/371472 [6:08:48<14:36:47,  3.04it/s]
 57%|█████▋    | 211758/371472 [6:08:48<14:24:18,  3.08it/s]
 57%|█████▋    | 211759/371472 [6:08:49<14:10:38,  3.13it/s]
 57%|█████▋    | 211760/371472 [6:08:49<14:12:55,  3.12it/s]
                                                            
{'loss': 2.9273, 'learning_rate': 4.871576633842574e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211760/371472 [6:08:49<14:12:55,  3.12it/s]
 57%|█████▋    | 211761/371472 [6:08:49<13:51:57,  3.20it/s]
 57%|█████▋    | 211762/371472 [6:08:49<13:44:02,  3.23it/s]
 57%|█████▋    | 211763/371472 [6:08:50<13:38:13,  3.25it/s]
 57%|█████▋    | 211764/371472 [6:08:50<13:06:40,  3.38it/s]
 57%|█████▋    | 211765/371472 [6:08:50<13:05:45,  3.39it/s]
 57%|█████▋    | 211766/371472 [6:08:51<12:46:23,  3.47it/s]
 57%|█████▋    | 211767/371472 [6:08:51<13:00:40,  3.41it/s]
 57%|█████▋    | 211768/371472 [6:08:51<13:00:48,  3.41it/s]
 57%|█████▋    | 211769/371472 [6:08:51<12:48:16,  3.46it/s]
 57%|█████▋    | 211770/371472 [6:08:52<12:51:04,  3.45it/s]
 57%|█████▋    | 211771/371472 [6:08:52<12:59:14,  3.42it/s]
 57%|█████▋    | 211772/371472 [6:08:52<13:11:08,  3.36it/s]
 57%|█████▋    | 211773/371472 [6:08:53<13:15:39,  3.35it/s]
 57%|█████▋    | 211774/371472 [6:08:53<13:14:14,  3.35it/s]
 57%|█████▋    | 211775/371472 [6:08:53<13:22:49,  3.32it/s]
 57%|█████▋    | 211776/371472 [6:08:54<13:33:27,  3.27it/s]
 57%|█████▋    | 211777/371472 [6:08:54<13:32:35,  3.28it/s]
 57%|█████▋    | 211778/371472 [6:08:54<13:37:36,  3.26it/s]
 57%|█████▋    | 211779/371472 [6:08:54<13:13:48,  3.35it/s]
 57%|█████▋    | 211780/371472 [6:08:55<13:35:04,  3.27it/s]
                                                            
{'loss': 2.7936, 'learning_rate': 4.871091814087784e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211780/371472 [6:08:55<13:35:04,  3.27it/s]
 57%|█████▋    | 211781/371472 [6:08:55<13:20:42,  3.32it/s]
 57%|█████▋    | 211782/371472 [6:08:55<13:34:01,  3.27it/s]
 57%|█████▋    | 211783/371472 [6:08:56<13:27:35,  3.30it/s]
 57%|█████▋    | 211784/371472 [6:08:56<13:44:32,  3.23it/s]
 57%|█████▋    | 211785/371472 [6:08:56<13:30:44,  3.28it/s]
 57%|█████▋    | 211786/371472 [6:08:57<13:21:05,  3.32it/s]
 57%|█████▋    | 211787/371472 [6:08:57<13:07:09,  3.38it/s]
 57%|█████▋    | 211788/371472 [6:08:57<13:12:22,  3.36it/s]
 57%|█████▋    | 211789/371472 [6:08:58<13:31:19,  3.28it/s]
 57%|█████▋    | 211790/371472 [6:08:58<15:28:30,  2.87it/s]
 57%|█████▋    | 211791/371472 [6:08:58<15:50:38,  2.80it/s]
 57%|█████▋    | 211792/371472 [6:08:59<14:56:18,  2.97it/s]
 57%|█████▋    | 211793/371472 [6:08:59<14:27:28,  3.07it/s]
 57%|█████▋    | 211794/371472 [6:08:59<14:31:40,  3.05it/s]
 57%|█████▋    | 211795/371472 [6:09:00<13:51:40,  3.20it/s]
 57%|█████▋    | 211796/371472 [6:09:00<13:54:04,  3.19it/s]
 57%|█████▋    | 211797/371472 [6:09:00<13:40:49,  3.24it/s]
 57%|█████▋    | 211798/371472 [6:09:00<14:12:00,  3.12it/s]
 57%|█████▋    | 211799/371472 [6:09:01<14:26:16,  3.07it/s]
 57%|█████▋    | 211800/371472 [6:09:01<14:38:43,  3.03it/s]
                                                            
{'loss': 2.6287, 'learning_rate': 4.870606994332996e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211800/371472 [6:09:01<14:38:43,  3.03it/s]
 57%|█████▋    | 211801/371472 [6:09:02<15:29:52,  2.86it/s]
 57%|█████▋    | 211802/371472 [6:09:02<14:44:24,  3.01it/s]
 57%|█████▋    | 211803/371472 [6:09:02<14:24:21,  3.08it/s]
 57%|█████▋    | 211804/371472 [6:09:02<13:49:47,  3.21it/s]
 57%|█████▋    | 211805/371472 [6:09:03<13:26:15,  3.30it/s]
 57%|█████▋    | 211806/371472 [6:09:03<13:05:20,  3.39it/s]
 57%|█████▋    | 211807/371472 [6:09:03<12:55:07,  3.43it/s]
 57%|█████▋    | 211808/371472 [6:09:04<12:41:55,  3.49it/s]
 57%|█████▋    | 211809/371472 [6:09:04<12:33:02,  3.53it/s]
 57%|█████▋    | 211810/371472 [6:09:04<12:48:56,  3.46it/s]
 57%|█████▋    | 211811/371472 [6:09:04<12:38:23,  3.51it/s]
 57%|█████▋    | 211812/371472 [6:09:05<12:58:09,  3.42it/s]
 57%|█████▋    | 211813/371472 [6:09:05<13:11:22,  3.36it/s]
 57%|█████▋    | 211814/371472 [6:09:05<13:16:24,  3.34it/s]
 57%|█████▋    | 211815/371472 [6:09:06<13:21:45,  3.32it/s]
 57%|█████▋    | 211816/371472 [6:09:06<13:21:11,  3.32it/s]
 57%|█████▋    | 211817/371472 [6:09:06<13:09:29,  3.37it/s]
 57%|█████▋    | 211818/371472 [6:09:07<13:08:45,  3.37it/s]
 57%|█████▋    | 211819/371472 [6:09:07<13:35:42,  3.26it/s]
 57%|█████▋    | 211820/371472 [6:09:07<13:32:16,  3.28it/s]
                                                            
{'loss': 2.8238, 'learning_rate': 4.870122174578206e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211820/371472 [6:09:07<13:32:16,  3.28it/s]
 57%|█████▋    | 211821/371472 [6:09:07<13:51:54,  3.20it/s]
 57%|█████▋    | 211822/371472 [6:09:08<13:42:35,  3.23it/s]
 57%|█████▋    | 211823/371472 [6:09:08<14:22:51,  3.08it/s]
 57%|█████▋    | 211824/371472 [6:09:08<14:04:08,  3.15it/s]
 57%|█████▋    | 211825/371472 [6:09:09<13:44:19,  3.23it/s]
 57%|█████▋    | 211826/371472 [6:09:09<13:21:53,  3.32it/s]
 57%|█████▋    | 211827/371472 [6:09:09<13:20:16,  3.32it/s]
 57%|█████▋    | 211828/371472 [6:09:10<13:17:25,  3.34it/s]
 57%|█████▋    | 211829/371472 [6:09:10<13:47:17,  3.22it/s]
 57%|█████▋    | 211830/371472 [6:09:10<13:30:03,  3.28it/s]
 57%|█████▋    | 211831/371472 [6:09:11<13:05:29,  3.39it/s]
 57%|█████▋    | 211832/371472 [6:09:11<13:03:38,  3.40it/s]
 57%|█████▋    | 211833/371472 [6:09:11<12:58:15,  3.42it/s]
 57%|█████▋    | 211834/371472 [6:09:11<12:49:37,  3.46it/s]
 57%|█████▋    | 211835/371472 [6:09:12<15:04:50,  2.94it/s]
 57%|█████▋    | 211836/371472 [6:09:12<15:09:29,  2.93it/s]
 57%|█████▋    | 211837/371472 [6:09:12<14:42:25,  3.02it/s]
 57%|█████▋    | 211838/371472 [6:09:13<14:08:45,  3.13it/s]
 57%|█████▋    | 211839/371472 [6:09:13<13:55:23,  3.18it/s]
 57%|█████▋    | 211840/371472 [6:09:13<13:25:48,  3.30it/s]
                                                            
{'loss': 2.7757, 'learning_rate': 4.869637354823419e-07, 'epoch': 9.12}
+
 57%|█████▋    | 211840/371472 [6:09:13<13:25:48,  3.30it/s]
 57%|█████▋    | 211841/371472 [6:09:14<13:16:12,  3.34it/s]
 57%|█████▋    | 211842/371472 [6:09:14<13:18:06,  3.33it/s]
 57%|█████▋    | 211843/371472 [6:09:14<14:11:40,  3.12it/s]
 57%|█████▋    | 211844/371472 [6:09:15<13:46:54,  3.22it/s]
 57%|█████▋    | 211845/371472 [6:09:15<13:24:08,  3.31it/s]
 57%|█████▋    | 211846/371472 [6:09:15<13:06:18,  3.38it/s]
 57%|█████▋    | 211847/371472 [6:09:15<12:53:37,  3.44it/s]
 57%|█████▋    | 211848/371472 [6:09:16<12:48:32,  3.46it/s]
 57%|█████▋    | 211849/371472 [6:09:16<12:40:22,  3.50it/s]
 57%|█████▋    | 211850/371472 [6:09:16<13:10:10,  3.37it/s]
 57%|█████▋    | 211851/371472 [6:09:17<13:24:14,  3.31it/s]
 57%|█████▋    | 211852/371472 [6:09:17<13:29:13,  3.29it/s]
 57%|█████▋    | 211853/371472 [6:09:17<13:35:42,  3.26it/s]
 57%|█████▋    | 211854/371472 [6:09:18<13:45:32,  3.22it/s]
 57%|█████▋    | 211855/371472 [6:09:18<13:35:04,  3.26it/s]
 57%|█████▋    | 211856/371472 [6:09:18<13:56:10,  3.18it/s]
 57%|█████▋    | 211857/371472 [6:09:19<13:46:07,  3.22it/s]
 57%|█████▋    | 211858/371472 [6:09:19<13:59:34,  3.17it/s]
 57%|█████▋    | 211859/371472 [6:09:19<14:43:49,  3.01it/s]
 57%|█████▋    | 211860/371472 [6:09:20<16:31:19,  2.68it/s]
                                                            
{'loss': 2.7307, 'learning_rate': 4.869152535068629e-07, 'epoch': 9.13}
+
 57%|█████▋    | 211860/371472 [6:09:20<16:31:19,  2.68it/s]
 57%|█████▋    | 211861/371472 [6:09:20<15:29:53,  2.86it/s]
 57%|█████▋    | 211862/371472 [6:09:20<14:59:56,  2.96it/s]
 57%|█████▋    | 211863/371472 [6:09:21<14:13:45,  3.12it/s]
 57%|█████▋    | 211864/371472 [6:09:21<13:49:10,  3.21it/s]
 57%|█████▋    | 211865/371472 [6:09:21<13:28:10,  3.29it/s]
 57%|█████▋    | 211866/371472 [6:09:21<12:57:08,  3.42it/s]
 57%|█████▋    | 211867/371472 [6:09:22<13:06:35,  3.38it/s]
 57%|█████▋    | 211868/371472 [6:09:22<12:58:52,  3.42it/s]
 57%|█████▋    | 211869/371472 [6:09:22<12:45:14,  3.48it/s]
 57%|█████▋    | 211870/371472 [6:09:23<12:38:14,  3.51it/s]
 57%|█████▋    | 211871/371472 [6:09:23<12:32:12,  3.54it/s]
 57%|█████▋    | 211872/371472 [6:09:23<12:37:11,  3.51it/s]
 57%|█████▋    | 211873/371472 [6:09:23<13:11:29,  3.36it/s]
 57%|█████▋    | 211874/371472 [6:09:24<13:16:50,  3.34it/s]
 57%|█████▋    | 211875/371472 [6:09:24<13:09:36,  3.37it/s]
 57%|█████▋    | 211876/371472 [6:09:24<13:08:29,  3.37it/s]
 57%|█████▋    | 211877/371472 [6:09:25<12:54:08,  3.44it/s]
 57%|█████▋    | 211878/371472 [6:09:25<13:12:38,  3.36it/s]
 57%|█████▋    | 211879/371472 [6:09:25<12:58:48,  3.42it/s]
 57%|█████▋    | 211880/371472 [6:09:26<12:45:02,  3.48it/s]
                                                            
{'loss': 2.7887, 'learning_rate': 4.86866771531384e-07, 'epoch': 9.13}
+
 57%|█████▋    | 211880/371472 [6:09:26<12:45:02,  3.48it/s]
 57%|█████▋    | 211881/371472 [6:09:26<13:17:55,  3.33it/s]
 57%|█████▋    | 211882/371472 [6:09:26<13:35:48,  3.26it/s]
 57%|█████▋    | 211883/371472 [6:09:26<12:59:02,  3.41it/s]
 57%|█████▋    | 211884/371472 [6:09:27<13:27:44,  3.29it/s]
 57%|█████▋    | 211885/371472 [6:09:27<13:12:04,  3.36it/s]
 57%|█████▋    | 211886/371472 [6:09:27<13:00:47,  3.41it/s]
 57%|█████▋    | 211887/371472 [6:09:28<13:20:32,  3.32it/s]
 57%|█████▋    | 211888/371472 [6:09:28<13:05:23,  3.39it/s]
 57%|█████▋    | 211889/371472 [6:09:28<13:30:18,  3.28it/s]
 57%|█████▋    | 211890/371472 [6:09:29<13:25:55,  3.30it/s]
 57%|█████▋    | 211891/371472 [6:09:29<13:20:27,  3.32it/s]
 57%|█████▋    | 211892/371472 [6:09:29<13:03:56,  3.39it/s]
 57%|█████▋    | 211893/371472 [6:09:29<13:45:39,  3.22it/s]
 57%|█████▋    | 211894/371472 [6:09:30<13:31:22,  3.28it/s]
 57%|█████▋    | 211895/371472 [6:09:30<13:48:18,  3.21it/s]
 57%|█████▋    | 211896/371472 [6:09:30<13:23:55,  3.31it/s]
 57%|█████▋    | 211897/371472 [6:09:31<13:07:42,  3.38it/s]
 57%|█████▋    | 211898/371472 [6:09:31<12:50:57,  3.45it/s]
 57%|█████▋    | 211899/371472 [6:09:31<15:07:26,  2.93it/s]
 57%|█████▋    | 211900/371472 [6:09:32<14:15:17,  3.11it/s]
                                                            
{'loss': 2.8678, 'learning_rate': 4.868182895559051e-07, 'epoch': 9.13}
+
 57%|█████▋    | 211900/371472 [6:09:32<14:15:17,  3.11it/s]
 57%|█████▋    | 211901/371472 [6:09:32<14:01:17,  3.16it/s]
 57%|█████▋    | 211902/371472 [6:09:32<15:30:24,  2.86it/s]
 57%|█████▋    | 211903/371472 [6:09:33<14:41:11,  3.02it/s]
 57%|█████▋    | 211904/371472 [6:09:33<14:00:43,  3.16it/s]
 57%|█████▋    | 211905/371472 [6:09:33<13:33:11,  3.27it/s]
 57%|█████▋    | 211906/371472 [6:09:34<13:27:20,  3.29it/s]
 57%|█████▋    | 211907/371472 [6:09:34<14:31:03,  3.05it/s]
 57%|█████▋    | 211908/371472 [6:09:34<14:20:06,  3.09it/s]
 57%|█████▋    | 211909/371472 [6:09:35<13:55:46,  3.18it/s]
 57%|█████▋    | 211910/371472 [6:09:35<15:09:53,  2.92it/s]
 57%|█████▋    | 211911/371472 [6:09:35<14:29:47,  3.06it/s]
 57%|█████▋    | 211912/371472 [6:09:36<14:00:12,  3.17it/s]
 57%|█████▋    | 211913/371472 [6:09:36<15:29:33,  2.86it/s]
 57%|█████▋    | 211914/371472 [6:09:36<15:23:20,  2.88it/s]
 57%|█████▋    | 211915/371472 [6:09:37<14:45:51,  3.00it/s]
 57%|█████▋    | 211916/371472 [6:09:37<14:05:24,  3.15it/s]
 57%|█████▋    | 211917/371472 [6:09:37<15:00:03,  2.95it/s]
 57%|█████▋    | 211918/371472 [6:09:38<14:34:57,  3.04it/s]
 57%|█████▋    | 211919/371472 [6:09:38<13:54:54,  3.19it/s]
 57%|█████▋    | 211920/371472 [6:09:38<13:48:36,  3.21it/s]
                                                            
{'loss': 2.7273, 'learning_rate': 4.867698075804261e-07, 'epoch': 9.13}
+
 57%|█████▋    | 211920/371472 [6:09:38<13:48:36,  3.21it/s]
 57%|█████▋    | 211921/371472 [6:09:38<13:49:46,  3.20it/s]
 57%|█████▋    | 211922/371472 [6:09:39<13:16:51,  3.34it/s]
 57%|█████▋    | 211923/371472 [6:09:39<13:03:01,  3.40it/s]
 57%|█████▋    | 211924/371472 [6:09:39<13:05:38,  3.38it/s]
 57%|█████▋    | 211925/371472 [6:09:40<12:41:39,  3.49it/s]
 57%|█████▋    | 211926/371472 [6:09:40<12:38:40,  3.50it/s]
 57%|█████▋    | 211927/371472 [6:09:40<12:31:21,  3.54it/s]
 57%|█████▋    | 211928/371472 [6:09:40<12:55:56,  3.43it/s]
 57%|█████▋    | 211929/371472 [6:09:41<12:56:04,  3.43it/s]
 57%|█████▋    | 211930/371472 [6:09:41<12:58:48,  3.41it/s]
 57%|█████▋    | 211931/371472 [6:09:41<13:06:04,  3.38it/s]
 57%|█████▋    | 211932/371472 [6:09:42<12:56:58,  3.42it/s]
 57%|█████▋    | 211933/371472 [6:09:42<12:55:17,  3.43it/s]
 57%|█████▋    | 211934/371472 [6:09:42<12:59:41,  3.41it/s]
 57%|█████▋    | 211935/371472 [6:09:42<12:56:22,  3.42it/s]
 57%|█████▋    | 211936/371472 [6:09:43<12:50:26,  3.45it/s]
 57%|█████▋    | 211937/371472 [6:09:43<13:11:53,  3.36it/s]
 57%|█████▋    | 211938/371472 [6:09:44<15:34:33,  2.85it/s]
 57%|█████▋    | 211939/371472 [6:09:44<14:55:35,  2.97it/s]
 57%|█████▋    | 211940/371472 [6:09:44<14:10:37,  3.13it/s]
                                                            
{'loss': 2.7432, 'learning_rate': 4.867213256049472e-07, 'epoch': 9.13}
+
 57%|█████▋    | 211940/371472 [6:09:44<14:10:37,  3.13it/s]
 57%|█████▋    | 211941/371472 [6:09:44<13:37:04,  3.25it/s]
 57%|█████▋    | 211942/371472 [6:09:45<14:23:33,  3.08it/s]
 57%|█████▋    | 211943/371472 [6:09:45<14:06:04,  3.14it/s]
 57%|█████▋    | 211944/371472 [6:09:45<13:25:57,  3.30it/s]
 57%|█████▋    | 211945/371472 [6:09:46<13:10:59,  3.36it/s]
 57%|█████▋    | 211946/371472 [6:09:46<13:08:17,  3.37it/s]
 57%|█████▋    | 211947/371472 [6:09:46<13:05:09,  3.39it/s]
 57%|█████▋    | 211948/371472 [6:09:47<13:00:01,  3.41it/s]
 57%|█████▋    | 211949/371472 [6:09:47<13:16:30,  3.34it/s]
 57%|█████▋    | 211950/371472 [6:09:47<13:20:56,  3.32it/s]
 57%|█████▋    | 211951/371472 [6:09:47<13:36:46,  3.26it/s]
 57%|█████▋    | 211952/371472 [6:09:48<13:06:48,  3.38it/s]
 57%|█████▋    | 211953/371472 [6:09:48<12:55:15,  3.43it/s]
 57%|█████▋    | 211954/371472 [6:09:48<13:19:13,  3.33it/s]
 57%|█████▋    | 211955/371472 [6:09:49<13:24:24,  3.31it/s]
 57%|█████▋    | 211956/371472 [6:09:49<13:40:12,  3.24it/s]
 57%|█████▋    | 211957/371472 [6:09:49<14:17:35,  3.10it/s]
 57%|█████▋    | 211958/371472 [6:09:50<13:58:03,  3.17it/s]
 57%|█████▋    | 211959/371472 [6:09:50<14:08:40,  3.13it/s]
 57%|█████▋    | 211960/371472 [6:09:50<14:37:03,  3.03it/s]
                                                            
{'loss': 2.8012, 'learning_rate': 4.866728436294683e-07, 'epoch': 9.13}
+
 57%|█████▋    | 211960/371472 [6:09:50<14:37:03,  3.03it/s]
 57%|█████▋    | 211961/371472 [6:09:51<14:29:32,  3.06it/s]
 57%|█████▋    | 211962/371472 [6:09:51<15:12:49,  2.91it/s]
 57%|█████▋    | 211963/371472 [6:09:51<14:56:09,  2.97it/s]
 57%|█████▋    | 211964/371472 [6:09:52<13:58:22,  3.17it/s]
 57%|█████▋    | 211965/371472 [6:09:52<13:26:16,  3.30it/s]
 57%|█████▋    | 211966/371472 [6:09:52<13:24:12,  3.31it/s]
 57%|█████▋    | 211967/371472 [6:09:53<13:49:26,  3.21it/s]
 57%|█████▋    | 211968/371472 [6:09:53<13:33:47,  3.27it/s]
 57%|█████▋    | 211969/371472 [6:09:53<13:16:02,  3.34it/s]
 57%|█████▋    | 211970/371472 [6:09:53<13:05:22,  3.38it/s]
 57%|█████▋    | 211971/371472 [6:09:54<13:28:22,  3.29it/s]
 57%|█████▋    | 211972/371472 [6:09:54<13:00:59,  3.40it/s]
 57%|█████▋    | 211973/371472 [6:09:54<13:38:01,  3.25it/s]
 57%|█████▋    | 211974/371472 [6:09:55<13:05:13,  3.39it/s]
 57%|█████▋    | 211975/371472 [6:09:55<12:46:42,  3.47it/s]
 57%|█████▋    | 211976/371472 [6:09:55<12:53:10,  3.44it/s]
 57%|█████▋    | 211977/371472 [6:09:55<12:54:39,  3.43it/s]
 57%|█████▋    | 211978/371472 [6:09:56<13:28:05,  3.29it/s]
 57%|█████▋    | 211979/371472 [6:09:56<13:32:39,  3.27it/s]
 57%|█████▋    | 211980/371472 [6:09:56<13:24:07,  3.31it/s]
                                                            
{'loss': 2.9162, 'learning_rate': 4.866243616539896e-07, 'epoch': 9.13}
+
 57%|█████▋    | 211980/371472 [6:09:56<13:24:07,  3.31it/s]
 57%|█████▋    | 211981/371472 [6:09:57<13:39:42,  3.24it/s]
 57%|█████▋    | 211982/371472 [6:09:57<13:17:19,  3.33it/s]
 57%|█████▋    | 211983/371472 [6:09:57<13:06:56,  3.38it/s]
 57%|█████▋    | 211984/371472 [6:09:58<13:28:31,  3.29it/s]
 57%|█████▋    | 211985/371472 [6:09:58<13:16:37,  3.34it/s]
 57%|█████▋    | 211986/371472 [6:09:58<12:52:55,  3.44it/s]
 57%|█████▋    | 211987/371472 [6:09:58<12:40:04,  3.50it/s]
 57%|█████▋    | 211988/371472 [6:09:59<12:49:36,  3.45it/s]
 57%|█████▋    | 211989/371472 [6:09:59<12:36:07,  3.52it/s]
 57%|█████▋    | 211990/371472 [6:09:59<12:32:19,  3.53it/s]
 57%|█████▋    | 211991/371472 [6:10:00<12:25:06,  3.57it/s]
 57%|█████▋    | 211992/371472 [6:10:00<12:22:42,  3.58it/s]
 57%|█████▋    | 211993/371472 [6:10:00<12:29:04,  3.55it/s]
 57%|█████▋    | 211994/371472 [6:10:00<12:34:17,  3.52it/s]
 57%|█████▋    | 211995/371472 [6:10:01<13:05:33,  3.38it/s]
 57%|█████▋    | 211996/371472 [6:10:01<12:50:32,  3.45it/s]
 57%|█��███▋    | 211997/371472 [6:10:01<12:59:47,  3.41it/s]
 57%|█████▋    | 211998/371472 [6:10:02<12:48:17,  3.46it/s]
 57%|█████▋    | 211999/371472 [6:10:02<13:38:02,  3.25it/s]
 57%|█████▋    | 212000/371472 [6:10:02<13:28:24,  3.29it/s]
                                                            
{'loss': 2.98, 'learning_rate': 4.865758796785106e-07, 'epoch': 9.13}
+
 57%|█████▋    | 212000/371472 [6:10:02<13:28:24,  3.29it/s]
 57%|█████▋    | 212001/371472 [6:10:03<13:31:10,  3.28it/s]
 57%|█████▋    | 212002/371472 [6:10:03<12:58:12,  3.42it/s]
 57%|█████▋    | 212003/371472 [6:10:03<13:35:58,  3.26it/s]
 57%|█████▋    | 212004/371472 [6:10:03<13:17:46,  3.33it/s]
 57%|█████▋    | 212005/371472 [6:10:04<13:02:22,  3.40it/s]
 57%|█████▋    | 212006/371472 [6:10:04<12:51:45,  3.44it/s]
 57%|█████▋    | 212007/371472 [6:10:04<12:53:10,  3.44it/s]
 57%|█████▋    | 212008/371472 [6:10:05<12:55:51,  3.43it/s]
 57%|█████▋    | 212009/371472 [6:10:05<13:08:14,  3.37it/s]
 57%|█████▋    | 212010/371472 [6:10:05<13:18:35,  3.33it/s]
 57%|█████▋    | 212011/371472 [6:10:05<13:04:46,  3.39it/s]
 57%|█████▋    | 212012/371472 [6:10:06<13:56:08,  3.18it/s]
 57%|█████▋    | 212013/371472 [6:10:06<13:43:31,  3.23it/s]
 57%|█████▋    | 212014/371472 [6:10:06<14:22:33,  3.08it/s]
 57%|█████▋    | 212015/371472 [6:10:07<15:40:26,  2.83it/s]
 57%|█████▋    | 212016/371472 [6:10:07<15:21:14,  2.88it/s]
 57%|█████▋    | 212017/371472 [6:10:08<14:40:31,  3.02it/s]
 57%|█████▋    | 212018/371472 [6:10:08<13:49:02,  3.21it/s]
 57%|█████▋    | 212019/371472 [6:10:08<13:15:14,  3.34it/s]
 57%|█████▋    | 212020/371472 [6:10:08<13:38:30,  3.25it/s]
                                                            
{'loss': 2.7121, 'learning_rate': 4.865273977030317e-07, 'epoch': 9.13}
+
 57%|█████▋    | 212020/371472 [6:10:08<13:38:30,  3.25it/s]
 57%|█████▋    | 212021/371472 [6:10:09<18:34:35,  2.38it/s]
 57%|█████▋    | 212022/371472 [6:10:09<17:04:13,  2.59it/s]
 57%|█████▋    | 212023/371472 [6:10:10<16:23:29,  2.70it/s]
 57%|█████▋    | 212024/371472 [6:10:10<15:05:51,  2.93it/s]
 57%|█████▋    | 212025/371472 [6:10:10<14:40:22,  3.02it/s]
 57%|█████▋    | 212026/371472 [6:10:11<14:03:23,  3.15it/s]
 57%|█████▋    | 212027/371472 [6:10:11<14:12:38,  3.12it/s]
 57%|█████▋    | 212028/371472 [6:10:11<14:57:59,  2.96it/s]
 57%|█████▋    | 212029/371472 [6:10:12<14:46:15,  3.00it/s]
 57%|█████▋    | 212030/371472 [6:10:12<14:35:02,  3.04it/s]
 57%|█████▋    | 212031/371472 [6:10:12<14:09:44,  3.13it/s]
 57%|█████▋    | 212032/371472 [6:10:13<14:30:23,  3.05it/s]
 57%|█████▋    | 212033/371472 [6:10:13<14:13:54,  3.11it/s]
 57%|█████▋    | 212034/371472 [6:10:13<14:03:14,  3.15it/s]
 57%|█████▋    | 212035/371472 [6:10:13<13:39:09,  3.24it/s]
 57%|█████▋    | 212036/371472 [6:10:14<13:33:17,  3.27it/s]
 57%|█████▋    | 212037/371472 [6:10:14<13:50:30,  3.20it/s]
 57%|█████▋    | 212038/371472 [6:10:14<14:03:47,  3.15it/s]
 57%|█████▋    | 212039/371472 [6:10:15<13:35:56,  3.26it/s]
 57%|█████▋    | 212040/371472 [6:10:15<13:43:42,  3.23it/s]
                                                            
{'loss': 2.8153, 'learning_rate': 4.864789157275528e-07, 'epoch': 9.13}
+
 57%|█████▋    | 212040/371472 [6:10:15<13:43:42,  3.23it/s]
 57%|█████▋    | 212041/371472 [6:10:15<13:51:58,  3.19it/s]
 57%|█████▋    | 212042/371472 [6:10:16<14:08:03,  3.13it/s]
 57%|█████▋    | 212043/371472 [6:10:16<13:54:03,  3.19it/s]
 57%|█████▋    | 212044/371472 [6:10:16<13:34:19,  3.26it/s]
 57%|█████▋    | 212045/371472 [6:10:17<13:31:39,  3.27it/s]
 57%|█████▋    | 212046/371472 [6:10:17<13:30:25,  3.28it/s]
 57%|█████▋    | 212047/371472 [6:10:17<13:37:20,  3.25it/s]
 57%|█████▋    | 212048/371472 [6:10:18<14:30:01,  3.05it/s]
 57%|█████▋    | 212049/371472 [6:10:18<14:14:46,  3.11it/s]
 57%|█████▋    | 212050/371472 [6:10:18<13:57:19,  3.17it/s]
 57%|█████▋    | 212051/371472 [6:10:18<13:48:57,  3.21it/s]
 57%|█████▋    | 212052/371472 [6:10:19<13:14:14,  3.35it/s]
 57%|█████▋    | 212053/371472 [6:10:19<13:27:08,  3.29it/s]
 57%|█████▋    | 212054/371472 [6:10:19<13:32:05,  3.27it/s]
 57%|█████▋    | 212055/371472 [6:10:20<13:12:45,  3.35it/s]
 57%|█████▋    | 212056/371472 [6:10:20<12:57:43,  3.42it/s]
 57%|█████▋    | 212057/371472 [6:10:20<12:47:41,  3.46it/s]
 57%|█████▋    | 212058/371472 [6:10:21<12:54:11,  3.43it/s]
 57%|█████▋    | 212059/371472 [6:10:21<12:47:21,  3.46it/s]
 57%|█████▋    | 212060/371472 [6:10:21<13:17:31,  3.33it/s]
                                                            
{'loss': 2.7326, 'learning_rate': 4.86430433752074e-07, 'epoch': 9.13}
+
 57%|█████▋    | 212060/371472 [6:10:21<13:17:31,  3.33it/s]
 57%|█████▋    | 212061/371472 [6:10:21<13:27:08,  3.29it/s]
 57%|█████▋    | 212062/371472 [6:10:22<13:30:22,  3.28it/s]
 57%|█████▋    | 212063/371472 [6:10:22<13:11:14,  3.36it/s]
 57%|█████▋    | 212064/371472 [6:10:22<12:59:29,  3.41it/s]
 57%|█████▋    | 212065/371472 [6:10:23<13:04:09,  3.39it/s]
 57%|█████▋    | 212066/371472 [6:10:23<13:04:13,  3.39it/s]
 57%|█████▋    | 212067/371472 [6:10:23<13:18:22,  3.33it/s]
 57%|█████▋    | 212068/371472 [6:10:24<13:22:12,  3.31it/s]
 57%|█████▋    | 212069/371472 [6:10:24<13:34:57,  3.26it/s]
 57%|█████▋    | 212070/371472 [6:10:24<13:57:31,  3.17it/s]
 57%|█████▋    | 212071/371472 [6:10:24<13:37:17,  3.25it/s]
 57%|█████▋    | 212072/371472 [6:10:25<13:20:49,  3.32it/s]
 57%|█████▋    | 212073/371472 [6:10:25<13:05:48,  3.38it/s]
 57%|█████▋    | 212074/371472 [6:10:25<13:05:18,  3.38it/s]
 57%|█████▋    | 212075/371472 [6:10:26<12:51:12,  3.44it/s]
 57%|█████▋    | 212076/371472 [6:10:26<13:21:53,  3.31it/s]
 57%|█████▋    | 212077/371472 [6:10:26<13:17:01,  3.33it/s]
 57%|█████▋    | 212078/371472 [6:10:27<13:12:45,  3.35it/s]
 57%|█████▋    | 212079/371472 [6:10:27<12:52:34,  3.44it/s]
 57%|█████▋    | 212080/371472 [6:10:27<12:42:27,  3.48it/s]
                                                            
{'loss': 2.8942, 'learning_rate': 4.863819517765949e-07, 'epoch': 9.13}
+
 57%|█████▋    | 212080/371472 [6:10:27<12:42:27,  3.48it/s]
 57%|█████▋    | 212081/371472 [6:10:27<13:11:36,  3.36it/s]
 57%|█████▋    | 212082/371472 [6:10:28<13:11:52,  3.35it/s]
 57%|█████▋    | 212083/371472 [6:10:28<13:07:30,  3.37it/s]
 57%|█████▋    | 212084/371472 [6:10:28<12:44:22,  3.48it/s]
 57%|█████▋    | 212085/371472 [6:10:29<12:29:31,  3.54it/s]
 57%|█████▋    | 212086/371472 [6:10:29<13:27:10,  3.29it/s]
 57%|█████▋    | 212087/371472 [6:10:29<15:45:19,  2.81it/s]
 57%|█████▋    | 212088/371472 [6:10:30<14:43:11,  3.01it/s]
 57%|█████▋    | 212089/371472 [6:10:30<14:36:30,  3.03it/s]
 57%|█████▋    | 212090/371472 [6:10:30<13:49:21,  3.20it/s]
 57%|█████▋    | 212091/371472 [6:10:31<13:35:59,  3.26it/s]
 57%|█████▋    | 212092/371472 [6:10:31<13:36:20,  3.25it/s]
 57%|█████▋    | 212093/371472 [6:10:31<13:26:08,  3.30it/s]
 57%|█████▋    | 212094/371472 [6:10:31<13:18:47,  3.33it/s]
 57%|█████▋    | 212095/371472 [6:10:32<13:14:10,  3.34it/s]
 57%|█████▋    | 212096/371472 [6:10:32<13:02:35,  3.39it/s]
 57%|█████▋    | 212097/371472 [6:10:32<13:04:34,  3.39it/s]
 57%|█████▋    | 212098/371472 [6:10:33<12:46:23,  3.47it/s]
 57%|█████▋    | 212099/371472 [6:10:33<13:03:48,  3.39it/s]
 57%|█████▋    | 212100/371472 [6:10:33<12:55:51,  3.42it/s]
                                                            
{'loss': 2.8813, 'learning_rate': 4.863334698011162e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212100/371472 [6:10:33<12:55:51,  3.42it/s]
 57%|█████▋    | 212101/371472 [6:10:33<13:11:14,  3.36it/s]
 57%|█████▋    | 212102/371472 [6:10:34<13:19:54,  3.32it/s]
 57%|█████▋    | 212103/371472 [6:10:34<13:12:29,  3.35it/s]
 57%|█████▋    | 212104/371472 [6:10:34<12:58:33,  3.41it/s]
 57%|█████▋    | 212105/371472 [6:10:35<13:01:27,  3.40it/s]
 57%|█████▋    | 212106/371472 [6:10:35<13:07:21,  3.37it/s]
 57%|█████▋    | 212107/371472 [6:10:35<12:41:51,  3.49it/s]
 57%|█████▋    | 212108/371472 [6:10:35<12:25:05,  3.56it/s]
 57%|█████▋    | 212109/371472 [6:10:36<12:09:18,  3.64it/s]
 57%|█████▋    | 212110/371472 [6:10:36<12:32:01,  3.53it/s]
 57%|█████▋    | 212111/371472 [6:10:36<12:53:28,  3.43it/s]
 57%|█████▋    | 212112/371472 [6:10:37<12:39:49,  3.50it/s]
 57%|█████▋    | 212113/371472 [6:10:37<12:46:33,  3.46it/s]
 57%|█████▋    | 212114/371472 [6:10:37<13:03:49,  3.39it/s]
 57%|█████▋    | 212115/371472 [6:10:38<13:18:06,  3.33it/s]
 57%|█████▋    | 212116/371472 [6:10:38<13:06:16,  3.38it/s]
 57%|█████▋    | 212117/371472 [6:10:38<12:57:47,  3.41it/s]
 57%|█████▋    | 212118/371472 [6:10:38<12:44:20,  3.47it/s]
 57%|█████▋    | 212119/371472 [6:10:39<12:32:07,  3.53it/s]
 57%|█████▋    | 212120/371472 [6:10:39<12:58:23,  3.41it/s]
                                                            
{'loss': 2.7346, 'learning_rate': 4.862849878256373e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212120/371472 [6:10:39<12:58:23,  3.41it/s]
 57%|█████▋    | 212121/371472 [6:10:39<13:08:23,  3.37it/s]
 57%|█████▋    | 212122/371472 [6:10:40<13:50:36,  3.20it/s]
 57%|█████▋    | 212123/371472 [6:10:40<13:38:17,  3.25it/s]
 57%|█████▋    | 212124/371472 [6:10:40<13:40:10,  3.24it/s]
 57%|█████▋    | 212125/371472 [6:10:41<13:11:11,  3.36it/s]
 57%|█████▋    | 212126/371472 [6:10:41<13:05:28,  3.38it/s]
 57%|█████▋    | 212127/371472 [6:10:41<12:50:04,  3.45it/s]
 57%|█████▋    | 212128/371472 [6:10:41<14:11:34,  3.12it/s]
 57%|█████▋    | 212129/371472 [6:10:42<13:42:32,  3.23it/s]
 57%|█████▋    | 212130/371472 [6:10:42<13:23:58,  3.30it/s]
 57%|█████▋    | 212131/371472 [6:10:42<13:19:53,  3.32it/s]
 57%|█████▋    | 212132/371472 [6:10:43<13:01:49,  3.40it/s]
 57%|█████▋    | 212133/371472 [6:10:43<12:41:53,  3.49it/s]
 57%|█████▋    | 212134/371472 [6:10:43<12:44:37,  3.47it/s]
 57%|█████▋    | 212135/371472 [6:10:43<12:49:52,  3.45it/s]
 57%|█████▋    | 212136/371472 [6:10:44<12:45:37,  3.47it/s]
 57%|█████▋    | 212137/371472 [6:10:44<13:36:31,  3.25it/s]
 57%|█████▋    | 212138/371472 [6:10:44<13:13:30,  3.35it/s]
 57%|█████▋    | 212139/371472 [6:10:45<14:00:53,  3.16it/s]
 57%|█████▋    | 212140/371472 [6:10:45<13:45:56,  3.22it/s]
                                                            
{'loss': 2.8459, 'learning_rate': 4.862365058501584e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212140/371472 [6:10:45<13:45:56,  3.22it/s]
 57%|█████▋    | 212141/371472 [6:10:45<14:02:42,  3.15it/s]
 57%|█████▋    | 212142/371472 [6:10:46<13:19:51,  3.32it/s]
 57%|█████▋    | 212143/371472 [6:10:46<13:34:24,  3.26it/s]
 57%|█████▋    | 212144/371472 [6:10:46<14:02:17,  3.15it/s]
 57%|█████▋    | 212145/371472 [6:10:47<13:51:00,  3.20it/s]
 57%|█████▋    | 212146/371472 [6:10:47<13:32:44,  3.27it/s]
 57%|█████▋    | 212147/371472 [6:10:47<13:21:51,  3.31it/s]
 57%|█████▋    | 212148/371472 [6:10:48<13:44:39,  3.22it/s]
 57%|█████▋    | 212149/371472 [6:10:48<14:05:51,  3.14it/s]
 57%|█████▋    | 212150/371472 [6:10:48<13:37:00,  3.25it/s]
 57%|█████▋    | 212151/371472 [6:10:48<13:43:42,  3.22it/s]
 57%|█████▋    | 212152/371472 [6:10:49<13:30:04,  3.28it/s]
 57%|█████▋    | 212153/371472 [6:10:49<13:23:39,  3.30it/s]
 57%|█████▋    | 212154/371472 [6:10:49<13:40:55,  3.23it/s]
 57%|█████▋    | 212155/371472 [6:10:50<13:29:09,  3.28it/s]
 57%|█████▋    | 212156/371472 [6:10:50<13:12:39,  3.35it/s]
 57%|█████▋    | 212157/371472 [6:10:50<13:13:15,  3.35it/s]
 57%|█████▋    | 212158/371472 [6:10:51<12:44:24,  3.47it/s]
 57%|█████▋    | 212159/371472 [6:10:51<12:40:18,  3.49it/s]
 57%|█████▋    | 212160/371472 [6:10:51<12:59:34,  3.41it/s]
                                                            
{'loss': 2.808, 'learning_rate': 4.861880238746794e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212160/371472 [6:10:51<12:59:34,  3.41it/s]
 57%|█████▋    | 212161/371472 [6:10:51<12:58:30,  3.41it/s]
 57%|█████▋    | 212162/371472 [6:10:52<12:57:49,  3.41it/s]
 57%|█████▋    | 212163/371472 [6:10:52<12:51:25,  3.44it/s]
 57%|█████▋    | 212164/371472 [6:10:52<12:58:34,  3.41it/s]
 57%|█████▋    | 212165/371472 [6:10:53<13:26:17,  3.29it/s]
 57%|█████▋    | 212166/371472 [6:10:53<13:24:40,  3.30it/s]
 57%|█████▋    | 212167/371472 [6:10:53<13:45:29,  3.22it/s]
 57%|█████▋    | 212168/371472 [6:10:54<13:38:06,  3.25it/s]
 57%|█████▋    | 212169/371472 [6:10:54<13:30:49,  3.27it/s]
 57%|█████▋    | 212170/371472 [6:10:54<13:01:53,  3.40it/s]
 57%|█████▋    | 212171/371472 [6:10:54<12:59:36,  3.41it/s]
 57%|█████▋    | 212172/371472 [6:10:55<13:25:58,  3.29it/s]
 57%|█████▋    | 212173/371472 [6:10:55<12:56:15,  3.42it/s]
 57%|█████▋    | 212174/371472 [6:10:55<12:44:26,  3.47it/s]
 57%|█████▋    | 212175/371472 [6:10:56<12:47:35,  3.46it/s]
 57%|█████▋    | 212176/371472 [6:10:56<12:45:18,  3.47it/s]
 57%|█████▋    | 212177/371472 [6:10:56<13:31:10,  3.27it/s]
 57%|█████▋    | 212178/371472 [6:10:57<14:40:01,  3.02it/s]
 57%|█████▋    | 212179/371472 [6:10:57<14:34:23,  3.04it/s]
 57%|█████▋    | 212180/371472 [6:10:57<14:18:17,  3.09it/s]
                                                            
{'loss': 2.7127, 'learning_rate': 4.861395418992006e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212180/371472 [6:10:57<14:18:17,  3.09it/s]
 57%|█████▋    | 212181/371472 [6:10:58<14:05:34,  3.14it/s]
 57%|█████▋    | 212182/371472 [6:10:58<13:29:39,  3.28it/s]
 57%|█████▋    | 212183/371472 [6:10:58<13:26:32,  3.29it/s]
 57%|█████▋    | 212184/371472 [6:10:58<13:24:20,  3.30it/s]
 57%|█████▋    | 212185/371472 [6:10:59<13:13:14,  3.35it/s]
 57%|█████▋    | 212186/371472 [6:10:59<13:06:27,  3.38it/s]
 57%|█████▋    | 212187/371472 [6:10:59<13:16:00,  3.34it/s]
 57%|█████▋    | 212188/371472 [6:11:00<13:09:43,  3.36it/s]
 57%|█████▋    | 212189/371472 [6:11:00<13:23:03,  3.31it/s]
 57%|█████▋    | 212190/371472 [6:11:00<13:27:58,  3.29it/s]
 57%|█████▋    | 212191/371472 [6:11:01<13:20:35,  3.32it/s]
 57%|█████▋    | 212192/371472 [6:11:01<13:55:09,  3.18it/s]
 57%|█████▋    | 212193/371472 [6:11:01<14:32:24,  3.04it/s]
 57%|█████▋    | 212194/371472 [6:11:02<14:01:36,  3.15it/s]
 57%|█████▋    | 212195/371472 [6:11:02<13:19:35,  3.32it/s]
 57%|█████▋    | 212196/371472 [6:11:02<13:28:25,  3.28it/s]
 57%|█████▋    | 212197/371472 [6:11:02<13:31:43,  3.27it/s]
 57%|█████▋    | 212198/371472 [6:11:03<13:29:26,  3.28it/s]
 57%|█████▋    | 212199/371472 [6:11:03<13:09:21,  3.36it/s]
 57%|█████▋    | 212200/371472 [6:11:03<13:12:05,  3.35it/s]
                                                            
{'loss': 2.8106, 'learning_rate': 4.860910599237216e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212200/371472 [6:11:03<13:12:05,  3.35it/s]
 57%|█████▋    | 212201/371472 [6:11:04<13:06:41,  3.37it/s]
 57%|█████▋    | 212202/371472 [6:11:04<12:49:21,  3.45it/s]
 57%|█████▋    | 212203/371472 [6:11:04<12:38:47,  3.50it/s]
 57%|█████▋    | 212204/371472 [6:11:04<12:29:20,  3.54it/s]
 57%|█████▋    | 212205/371472 [6:11:05<12:29:44,  3.54it/s]
 57%|█████▋    | 212206/371472 [6:11:05<12:24:21,  3.57it/s]
 57%|█████▋    | 212207/371472 [6:11:05<13:07:55,  3.37it/s]
 57%|█████▋    | 212208/371472 [6:11:06<13:24:22,  3.30it/s]
 57%|█████▋    | 212209/371472 [6:11:06<13:05:14,  3.38it/s]
 57%|█████▋    | 212210/371472 [6:11:06<12:53:21,  3.43it/s]
 57%|█████▋    | 212211/371472 [6:11:06<12:50:21,  3.45it/s]
 57%|█████▋    | 212212/371472 [6:11:07<13:11:40,  3.35it/s]
 57%|█████▋    | 212213/371472 [6:11:07<13:17:40,  3.33it/s]
 57%|█████▋    | 212214/371472 [6:11:07<12:54:21,  3.43it/s]
 57%|█████▋    | 212215/371472 [6:11:08<14:24:23,  3.07it/s]
 57%|█████▋    | 212216/371472 [6:11:08<13:56:34,  3.17it/s]
 57%|█████▋    | 212217/371472 [6:11:08<13:22:40,  3.31it/s]
 57%|█████▋    | 212218/371472 [6:11:09<13:11:33,  3.35it/s]
 57%|█████▋    | 212219/371472 [6:11:09<13:02:42,  3.39it/s]
 57%|█████▋    | 212220/371472 [6:11:09<13:06:48,  3.37it/s]
                                                            
{'loss': 2.9485, 'learning_rate': 4.860425779482429e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212220/371472 [6:11:09<13:06:48,  3.37it/s]
 57%|█████▋    | 212221/371472 [6:11:09<13:13:49,  3.34it/s]
 57%|█████▋    | 212222/371472 [6:11:10<14:27:42,  3.06it/s]
 57%|█████▋    | 212223/371472 [6:11:10<13:42:26,  3.23it/s]
 57%|█████▋    | 212224/371472 [6:11:10<13:42:27,  3.23it/s]
 57%|█████▋    | 212225/371472 [6:11:11<13:39:15,  3.24it/s]
 57%|█████▋    | 212226/371472 [6:11:11<14:19:51,  3.09it/s]
 57%|█████▋    | 212227/371472 [6:11:11<13:44:18,  3.22it/s]
 57%|█████▋    | 212228/371472 [6:11:12<13:04:59,  3.38it/s]
 57%|█████▋    | 212229/371472 [6:11:12<12:55:37,  3.42it/s]
 57%|█████▋    | 212230/371472 [6:11:12<13:17:59,  3.33it/s]
 57%|█████▋    | 212231/371472 [6:11:13<14:00:45,  3.16it/s]
 57%|█████▋    | 212232/371472 [6:11:13<14:01:59,  3.15it/s]
 57%|█████▋    | 212233/371472 [6:11:13<13:30:36,  3.27it/s]
 57%|█████▋    | 212234/371472 [6:11:14<13:22:07,  3.31it/s]
 57%|█████▋    | 212235/371472 [6:11:14<13:15:44,  3.34it/s]
 57%|█████▋    | 212236/371472 [6:11:14<12:58:16,  3.41it/s]
 57%|█████▋    | 212237/371472 [6:11:14<12:54:03,  3.43it/s]
 57%|█████▋    | 212238/371472 [6:11:15<13:03:52,  3.39it/s]
 57%|█████▋    | 212239/371472 [6:11:15<14:03:31,  3.15it/s]
 57%|█████▋    | 212240/371472 [6:11:15<15:05:47,  2.93it/s]
                                                            
{'loss': 2.7833, 'learning_rate': 4.859940959727639e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212240/371472 [6:11:15<15:05:47,  2.93it/s]
 57%|█████▋    | 212241/371472 [6:11:16<14:33:37,  3.04it/s]
 57%|█████▋    | 212242/371472 [6:11:16<14:53:46,  2.97it/s]
 57%|█████▋    | 212243/371472 [6:11:16<14:19:59,  3.09it/s]
 57%|█████▋    | 212244/371472 [6:11:17<14:18:33,  3.09it/s]
 57%|█████▋    | 212245/371472 [6:11:17<14:19:10,  3.09it/s]
 57%|█████▋    | 212246/371472 [6:11:17<13:51:30,  3.19it/s]
 57%|█████▋    | 212247/371472 [6:11:18<13:59:57,  3.16it/s]
 57%|█████▋    | 212248/371472 [6:11:18<13:36:58,  3.25it/s]
 57%|█████▋    | 212249/371472 [6:11:19<18:17:58,  2.42it/s]
 57%|█████▋    | 212250/371472 [6:11:19<17:03:37,  2.59it/s]
 57%|█████▋    | 212251/371472 [6:11:19<15:47:06,  2.80it/s]
 57%|█████▋    | 212252/371472 [6:11:20<15:35:47,  2.84it/s]
 57%|█████▋    | 212253/371472 [6:11:20<15:17:58,  2.89it/s]
 57%|█████▋    | 212254/371472 [6:11:20<14:45:56,  3.00it/s]
 57%|█████▋    | 212255/371472 [6:11:21<15:04:01,  2.94it/s]
 57%|█████▋    | 212256/371472 [6:11:21<14:29:30,  3.05it/s]
 57%|█████▋    | 212257/371472 [6:11:21<15:47:15,  2.80it/s]
 57%|█████▋    | 212258/371472 [6:11:22<15:50:08,  2.79it/s]
 57%|█████▋    | 212259/371472 [6:11:22<15:36:09,  2.83it/s]
 57%|█████▋    | 212260/371472 [6:11:22<14:32:40,  3.04it/s]
                                                            
{'loss': 2.7181, 'learning_rate': 4.85945613997285e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212260/371472 [6:11:22<14:32:40,  3.04it/s]
 57%|█████▋    | 212261/371472 [6:11:23<13:59:43,  3.16it/s]
 57%|█████▋    | 212262/371472 [6:11:23<13:34:27,  3.26it/s]
 57%|█████▋    | 212263/371472 [6:11:23<13:53:33,  3.18it/s]
 57%|█████▋    | 212264/371472 [6:11:23<13:27:04,  3.29it/s]
 57%|█████▋    | 212265/371472 [6:11:24<13:29:24,  3.28it/s]
 57%|█████▋    | 212266/371472 [6:11:24<14:27:40,  3.06it/s]
 57%|█████▋    | 212267/371472 [6:11:24<15:01:10,  2.94it/s]
 57%|█████▋    | 212268/371472 [6:11:25<15:20:03,  2.88it/s]
 57%|█████▋    | 212269/371472 [6:11:25<15:06:52,  2.93it/s]
 57%|█████▋    | 212270/371472 [6:11:25<14:34:35,  3.03it/s]
 57%|█████▋    | 212271/371472 [6:11:26<13:53:08,  3.18it/s]
 57%|█████▋    | 212272/371472 [6:11:26<13:35:56,  3.25it/s]
 57%|█████▋    | 212273/371472 [6:11:26<13:19:46,  3.32it/s]
 57%|█████▋    | 212274/371472 [6:11:27<13:23:56,  3.30it/s]
 57%|█████▋    | 212275/371472 [6:11:27<13:21:30,  3.31it/s]
 57%|█████▋    | 212276/371472 [6:11:27<12:53:40,  3.43it/s]
 57%|█████▋    | 212277/371472 [6:11:28<13:09:27,  3.36it/s]
 57%|█████▋    | 212278/371472 [6:11:28<12:57:43,  3.41it/s]
 57%|█████▋    | 212279/371472 [6:11:28<12:42:51,  3.48it/s]
 57%|█████▋    | 212280/371472 [6:11:28<12:31:58,  3.53it/s]
                                                            
{'loss': 2.8519, 'learning_rate': 4.858971320218061e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212280/371472 [6:11:28<12:31:58,  3.53it/s]
 57%|█████▋    | 212281/371472 [6:11:29<12:26:00,  3.56it/s]
 57%|█████▋    | 212282/371472 [6:11:29<12:38:51,  3.50it/s]
 57%|█████▋    | 212283/371472 [6:11:29<12:37:44,  3.50it/s]
 57%|█████▋    | 212284/371472 [6:11:30<12:43:20,  3.48it/s]
 57%|█████▋    | 212285/371472 [6:11:30<12:42:59,  3.48it/s]
 57%|█████▋    | 212286/371472 [6:11:30<13:06:14,  3.37it/s]
 57%|█████▋    | 212287/371472 [6:11:30<13:16:34,  3.33it/s]
 57%|█████▋    | 212288/371472 [6:11:31<13:28:10,  3.28it/s]
 57%|█████▋    | 212289/371472 [6:11:31<13:09:02,  3.36it/s]
 57%|█████▋    | 212290/371472 [6:11:31<13:11:42,  3.35it/s]
 57%|█████▋    | 212291/371472 [6:11:32<13:12:45,  3.35it/s]
 57%|█████▋    | 212292/371472 [6:11:32<13:34:45,  3.26it/s]
 57%|█████▋    | 212293/371472 [6:11:32<13:38:24,  3.24it/s]
 57%|█████▋    | 212294/371472 [6:11:33<13:38:24,  3.24it/s]
 57%|█████▋    | 212295/371472 [6:11:33<13:24:53,  3.30it/s]
 57%|█████▋    | 212296/371472 [6:11:33<13:25:18,  3.29it/s]
 57%|█████▋    | 212297/371472 [6:11:33<13:06:36,  3.37it/s]
 57%|█████▋    | 212298/371472 [6:11:34<13:15:25,  3.34it/s]
 57%|█████▋    | 212299/371472 [6:11:34<13:06:33,  3.37it/s]
 57%|█████▋    | 212300/371472 [6:11:34<13:05:11,  3.38it/s]
                                                            
{'loss': 2.7646, 'learning_rate': 4.858486500463272e-07, 'epoch': 9.14}
+
 57%|█████▋    | 212300/371472 [6:11:34<13:05:11,  3.38it/s]
 57%|█████▋    | 212301/371472 [6:11:35<13:00:32,  3.40it/s]
 57%|█████��    | 212302/371472 [6:11:35<13:00:39,  3.40it/s]
 57%|█████▋    | 212303/371472 [6:11:35<13:22:19,  3.31it/s]
 57%|█████▋    | 212304/371472 [6:11:36<13:11:55,  3.35it/s]
 57%|█████▋    | 212305/371472 [6:11:36<13:05:49,  3.38it/s]
 57%|█████▋    | 212306/371472 [6:11:36<13:57:04,  3.17it/s]
 57%|█████▋    | 212307/371472 [6:11:36<13:27:19,  3.29it/s]
 57%|█████▋    | 212308/371472 [6:11:37<14:02:55,  3.15it/s]
 57%|█████▋    | 212309/371472 [6:11:37<13:33:52,  3.26it/s]
 57%|█████▋    | 212310/371472 [6:11:37<13:40:08,  3.23it/s]
 57%|█████▋    | 212311/371472 [6:11:38<13:17:21,  3.33it/s]
 57%|█████▋    | 212312/371472 [6:11:38<13:32:27,  3.26it/s]
 57%|█████▋    | 212313/371472 [6:11:38<14:03:08,  3.15it/s]
 57%|█████▋    | 212314/371472 [6:11:39<13:44:24,  3.22it/s]
 57%|█████▋    | 212315/371472 [6:11:39<13:29:11,  3.28it/s]
 57%|█████▋    | 212316/371472 [6:11:39<13:23:27,  3.30it/s]
 57%|█████▋    | 212317/371472 [6:11:40<14:04:55,  3.14it/s]
 57%|█████▋    | 212318/371472 [6:11:40<14:14:02,  3.11it/s]
 57%|█████▋    | 212319/371472 [6:11:40<13:47:35,  3.21it/s]
 57%|█████▋    | 212320/371472 [6:11:40<13:22:10,  3.31it/s]
                                                            
{'loss': 2.6661, 'learning_rate': 4.858001680708482e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212320/371472 [6:11:40<13:22:10,  3.31it/s]
 57%|█████▋    | 212321/371472 [6:11:41<13:24:32,  3.30it/s]
 57%|█████▋    | 212322/371472 [6:11:41<13:05:20,  3.38it/s]
 57%|█████▋    | 212323/371472 [6:11:41<13:08:13,  3.37it/s]
 57%|█████▋    | 212324/371472 [6:11:42<13:03:46,  3.38it/s]
 57%|█████▋    | 212325/371472 [6:11:42<12:53:41,  3.43it/s]
 57%|█████▋    | 212326/371472 [6:11:42<12:59:55,  3.40it/s]
 57%|█████▋    | 212327/371472 [6:11:43<13:05:41,  3.38it/s]
 57%|█████▋    | 212328/371472 [6:11:43<13:05:38,  3.38it/s]
 57%|█████▋    | 212329/371472 [6:11:43<13:29:54,  3.27it/s]
 57%|█████▋    | 212330/371472 [6:11:44<14:38:13,  3.02it/s]
 57%|█████▋    | 212331/371472 [6:11:44<14:28:25,  3.05it/s]
 57%|█████▋    | 212332/371472 [6:11:44<13:49:59,  3.20it/s]
 57%|█████▋    | 212333/371472 [6:11:44<13:44:29,  3.22it/s]
 57%|█████▋    | 212334/371472 [6:11:45<13:16:10,  3.33it/s]
 57%|█████▋    | 212335/371472 [6:11:45<13:48:54,  3.20it/s]
 57%|█████▋    | 212336/371472 [6:11:45<13:36:08,  3.25it/s]
 57%|█████▋    | 212337/371472 [6:11:46<13:34:48,  3.26it/s]
 57%|█████▋    | 212338/371472 [6:11:46<13:17:36,  3.33it/s]
 57%|█████▋    | 212339/371472 [6:11:46<13:30:43,  3.27it/s]
 57%|█████▋    | 212340/371472 [6:11:47<13:32:01,  3.27it/s]
                                                            
{'loss': 2.8405, 'learning_rate': 4.857516860953695e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212340/371472 [6:11:47<13:32:01,  3.27it/s]
 57%|█████▋    | 212341/371472 [6:11:47<13:16:36,  3.33it/s]
 57%|█████▋    | 212342/371472 [6:11:47<14:17:48,  3.09it/s]
 57%|█████▋    | 212343/371472 [6:11:48<14:01:51,  3.15it/s]
 57%|█████▋    | 212344/371472 [6:11:48<13:41:52,  3.23it/s]
 57%|█████▋    | 212345/371472 [6:11:48<13:28:43,  3.28it/s]
 57%|█████▋    | 212346/371472 [6:11:48<13:03:40,  3.38it/s]
 57%|█████▋    | 212347/371472 [6:11:49<13:06:25,  3.37it/s]
 57%|█████▋    | 212348/371472 [6:11:49<13:07:13,  3.37it/s]
 57%|█████▋    | 212349/371472 [6:11:49<13:13:17,  3.34it/s]
 57%|█████▋    | 212350/371472 [6:11:50<13:15:53,  3.33it/s]
 57%|█████▋    | 212351/371472 [6:11:50<12:49:28,  3.45it/s]
 57%|█████▋    | 212352/371472 [6:11:50<12:51:45,  3.44it/s]
 57%|█████▋    | 212353/371472 [6:11:50<12:53:03,  3.43it/s]
 57%|█████▋    | 212354/371472 [6:11:51<12:55:59,  3.42it/s]
 57%|█████▋    | 212355/371472 [6:11:51<12:52:41,  3.43it/s]
 57%|█████▋    | 212356/371472 [6:11:51<13:42:30,  3.22it/s]
 57%|█████▋    | 212357/371472 [6:11:52<13:45:27,  3.21it/s]
 57%|█████▋    | 212358/371472 [6:11:52<13:41:25,  3.23it/s]
 57%|█████▋    | 212359/371472 [6:11:52<13:30:54,  3.27it/s]
 57%|█████▋    | 212360/371472 [6:11:53<13:50:20,  3.19it/s]
                                                            
{'loss': 2.7817, 'learning_rate': 4.857032041198906e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212360/371472 [6:11:53<13:50:20,  3.19it/s]
 57%|█████▋    | 212361/371472 [6:11:53<13:39:06,  3.24it/s]
 57%|█████▋    | 212362/371472 [6:11:53<13:54:32,  3.18it/s]
 57%|█████▋    | 212363/371472 [6:11:54<13:25:51,  3.29it/s]
 57%|█████▋    | 212364/371472 [6:11:54<13:23:11,  3.30it/s]
 57%|█████▋    | 212365/371472 [6:11:54<13:16:24,  3.33it/s]
 57%|█████▋    | 212366/371472 [6:11:54<12:55:13,  3.42it/s]
 57%|█████▋    | 212367/371472 [6:11:55<12:40:30,  3.49it/s]
 57%|█████▋    | 212368/371472 [6:11:55<13:04:10,  3.38it/s]
 57%|█████▋    | 212369/371472 [6:11:55<13:37:54,  3.24it/s]
 57%|█████▋    | 212370/371472 [6:11:56<13:29:39,  3.28it/s]
 57%|█████▋    | 212371/371472 [6:11:56<13:27:54,  3.28it/s]
 57%|█████▋    | 212372/371472 [6:11:56<13:24:44,  3.30it/s]
 57%|█████▋    | 212373/371472 [6:11:57<13:05:49,  3.37it/s]
 57%|█████▋    | 212374/371472 [6:11:57<13:06:03,  3.37it/s]
 57%|█████▋    | 212375/371472 [6:11:57<13:12:05,  3.35it/s]
 57%|█████▋    | 212376/371472 [6:11:57<13:11:35,  3.35it/s]
 57%|█████▋    | 212377/371472 [6:11:58<12:53:42,  3.43it/s]
 57%|█████▋    | 212378/371472 [6:11:58<13:16:44,  3.33it/s]
 57%|█████▋    | 212379/371472 [6:11:58<13:00:19,  3.40it/s]
 57%|█████▋    | 212380/371472 [6:11:59<12:58:25,  3.41it/s]
                                                            
{'loss': 2.7087, 'learning_rate': 4.856547221444116e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212380/371472 [6:11:59<12:58:25,  3.41it/s]
 57%|█████▋    | 212381/371472 [6:11:59<13:19:24,  3.32it/s]
 57%|█████▋    | 212382/371472 [6:11:59<13:16:39,  3.33it/s]
 57%|█████▋    | 212383/371472 [6:11:59<12:50:04,  3.44it/s]
 57%|█████▋    | 212384/371472 [6:12:00<13:01:59,  3.39it/s]
 57%|█████▋    | 212385/371472 [6:12:00<13:23:21,  3.30it/s]
 57%|█████▋    | 212386/371472 [6:12:00<13:07:04,  3.37it/s]
 57%|█████▋    | 212387/371472 [6:12:01<12:55:21,  3.42it/s]
 57%|█████▋    | 212388/371472 [6:12:01<13:03:14,  3.39it/s]
 57%|█████▋    | 212389/371472 [6:12:01<13:02:04,  3.39it/s]
 57%|█████▋    | 212390/371472 [6:12:02<12:45:37,  3.46it/s]
 57%|█████▋    | 212391/371472 [6:12:02<13:02:18,  3.39it/s]
 57%|█████▋    | 212392/371472 [6:12:02<12:56:20,  3.42it/s]
 57%|█████▋    | 212393/371472 [6:12:02<12:48:52,  3.45it/s]
 57%|█████▋    | 212394/371472 [6:12:03<13:16:47,  3.33it/s]
 57%|█████▋    | 212395/371472 [6:12:03<13:38:52,  3.24it/s]
 57%|█████▋    | 212396/371472 [6:12:03<13:46:35,  3.21it/s]
 57%|█████▋    | 212397/371472 [6:12:04<13:27:53,  3.28it/s]
 57%|█████▋    | 212398/371472 [6:12:04<13:24:42,  3.29it/s]
 57%|█████▋    | 212399/371472 [6:12:04<13:35:34,  3.25it/s]
 57%|█████▋    | 212400/371472 [6:12:05<13:34:30,  3.25it/s]
                                                            
{'loss': 2.7313, 'learning_rate': 4.856062401689327e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212400/371472 [6:12:05<13:34:30,  3.25it/s]
 57%|█████▋    | 212401/371472 [6:12:05<13:38:44,  3.24it/s]
 57%|█████▋    | 212402/371472 [6:12:05<13:14:32,  3.34it/s]
 57%|█████▋    | 212403/371472 [6:12:06<13:29:48,  3.27it/s]
 57%|█████▋    | 212404/371472 [6:12:06<13:19:58,  3.31it/s]
 57%|█████▋    | 212405/371472 [6:12:06<12:53:41,  3.43it/s]
 57%|█████▋    | 212406/371472 [6:12:06<12:43:35,  3.47it/s]
 57%|█████▋    | 212407/371472 [6:12:07<13:07:11,  3.37it/s]
 57%|█████▋    | 212408/371472 [6:12:07<12:55:06,  3.42it/s]
 57%|█████▋    | 212409/371472 [6:12:07<13:08:18,  3.36it/s]
 57%|█████▋    | 212410/371472 [6:12:08<13:32:31,  3.26it/s]
 57%|█████▋    | 212411/371472 [6:12:08<13:04:21,  3.38it/s]
 57%|█████▋    | 212412/371472 [6:12:08<13:46:57,  3.21it/s]
 57%|█████▋    | 212413/371472 [6:12:09<13:29:27,  3.28it/s]
 57%|█████▋    | 212414/371472 [6:12:09<13:30:22,  3.27it/s]
 57%|█████▋    | 212415/371472 [6:12:09<13:11:26,  3.35it/s]
 57%|█████▋    | 212416/371472 [6:12:09<13:04:47,  3.38it/s]
 57%|█████▋    | 212417/371472 [6:12:10<12:45:57,  3.46it/s]
 57%|█████▋    | 212418/371472 [6:12:10<13:05:36,  3.37it/s]
 57%|█████▋    | 212419/371472 [6:12:10<14:05:46,  3.13it/s]
 57%|█████▋    | 212420/371472 [6:12:11<13:39:26,  3.23it/s]
                                                            
{'loss': 2.7778, 'learning_rate': 4.855577581934539e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212420/371472 [6:12:11<13:39:26,  3.23it/s]
 57%|█████▋    | 212421/371472 [6:12:11<13:34:04,  3.26it/s]
 57%|█████▋    | 212422/371472 [6:12:11<13:36:33,  3.25it/s]
 57%|█████▋    | 212423/371472 [6:12:12<13:35:40,  3.25it/s]
 57%|█████▋    | 212424/371472 [6:12:12<13:49:33,  3.20it/s]
 57%|█████▋    | 212425/371472 [6:12:12<13:39:35,  3.23it/s]
 57%|█████▋    | 212426/371472 [6:12:12<13:21:36,  3.31it/s]
 57%|█████▋    | 212427/371472 [6:12:13<13:18:02,  3.32it/s]
 57%|█████▋    | 212428/371472 [6:12:13<13:15:48,  3.33it/s]
 57%|█████▋    | 212429/371472 [6:12:13<13:01:49,  3.39it/s]
 57%|█████▋    | 212430/371472 [6:12:14<13:03:34,  3.38it/s]
 57%|█████▋    | 212431/371472 [6:12:14<13:01:18,  3.39it/s]
 57%|█████▋    | 212432/371472 [6:12:14<12:41:21,  3.48it/s]
 57%|█████▋    | 212433/371472 [6:12:15<13:09:28,  3.36it/s]
 57%|█████▋    | 212434/371472 [6:12:15<13:02:33,  3.39it/s]
 57%|█████▋    | 212435/371472 [6:12:15<13:11:49,  3.35it/s]
 57%|█████▋    | 212436/371472 [6:12:15<13:05:52,  3.37it/s]
 57%|█████▋    | 212437/371472 [6:12:16<13:11:35,  3.35it/s]
 57%|█████▋    | 212438/371472 [6:12:16<13:25:26,  3.29it/s]
 57%|█████▋    | 212439/371472 [6:12:16<13:18:29,  3.32it/s]
 57%|█████▋    | 212440/371472 [6:12:17<13:14:48,  3.33it/s]
                                                            
{'loss': 2.686, 'learning_rate': 4.85509276217975e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212440/371472 [6:12:17<13:14:48,  3.33it/s]
 57%|█████▋    | 212441/371472 [6:12:17<13:25:13,  3.29it/s]
 57%|█████▋    | 212442/371472 [6:12:17<13:28:36,  3.28it/s]
 57%|█████▋    | 212443/371472 [6:12:18<13:39:39,  3.23it/s]
 57%|█████▋    | 212444/371472 [6:12:18<13:28:32,  3.28it/s]
 57%|█████▋    | 212445/371472 [6:12:18<13:45:52,  3.21it/s]
 57%|█████▋    | 212446/371472 [6:12:18<13:29:14,  3.28it/s]
 57%|█████▋    | 212447/371472 [6:12:19<13:11:53,  3.35it/s]
 57%|█████▋    | 212448/371472 [6:12:19<13:47:55,  3.20it/s]
 57%|█████▋    | 212449/371472 [6:12:19<13:34:25,  3.25it/s]
 57%|█████▋    | 212450/371472 [6:12:20<13:32:10,  3.26it/s]
 57%|█████▋    | 212451/371472 [6:12:20<13:18:10,  3.32it/s]
 57%|█████▋    | 212452/371472 [6:12:20<13:30:43,  3.27it/s]
 57%|█████▋    | 212453/371472 [6:12:21<13:42:46,  3.22it/s]
 57%|█████▋    | 212454/371472 [6:12:21<13:22:44,  3.30it/s]
 57%|█████▋    | 212455/371472 [6:12:21<14:21:09,  3.08it/s]
 57%|█████▋    | 212456/371472 [6:12:22<13:33:16,  3.26it/s]
 57%|█████▋    | 212457/371472 [6:12:22<13:20:44,  3.31it/s]
 57%|█████▋    | 212458/371472 [6:12:22<13:15:56,  3.33it/s]
 57%|█████▋    | 212459/371472 [6:12:22<13:45:44,  3.21it/s]
 57%|█████▋    | 212460/371472 [6:12:23<14:11:31,  3.11it/s]
                                                            
{'loss': 2.7028, 'learning_rate': 4.854607942424959e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212460/371472 [6:12:23<14:11:31,  3.11it/s]
 57%|█████▋    | 212461/371472 [6:12:23<13:49:48,  3.19it/s]
 57%|█████▋    | 212462/371472 [6:12:23<13:58:39,  3.16it/s]
 57%|█████▋    | 212463/371472 [6:12:24<13:29:16,  3.27it/s]
 57%|█████▋    | 212464/371472 [6:12:24<13:34:06,  3.26it/s]
 57%|█████▋    | 212465/371472 [6:12:24<13:24:39,  3.29it/s]
 57%|█████▋    | 212466/371472 [6:12:25<13:27:26,  3.28it/s]
 57%|█████▋    | 212467/371472 [6:12:25<13:03:20,  3.38it/s]
 57%|█████▋    | 212468/371472 [6:12:25<12:51:19,  3.44it/s]
 57%|█████▋    | 212469/371472 [6:12:25<12:45:59,  3.46it/s]
 57%|█████▋    | 212470/371472 [6:12:26<13:13:28,  3.34it/s]
 57%|█████▋    | 212471/371472 [6:12:26<13:10:48,  3.35it/s]
 57%|█████▋    | 212472/371472 [6:12:26<13:30:09,  3.27it/s]
 57%|█████▋    | 212473/371472 [6:12:27<14:44:00,  3.00it/s]
 57%|█████▋    | 212474/371472 [6:12:27<14:59:49,  2.94it/s]
 57%|█████▋    | 212475/371472 [6:12:28<15:11:22,  2.91it/s]
 57%|█████▋    | 212476/371472 [6:12:28<14:55:04,  2.96it/s]
 57%|█████▋    | 212477/371472 [6:12:28<15:13:08,  2.90it/s]
 57%|█████▋    | 212478/371472 [6:12:29<14:24:35,  3.06it/s]
 57%|█████▋    | 212479/371472 [6:12:29<13:37:20,  3.24it/s]
 57%|█████▋    | 212480/371472 [6:12:29<13:28:03,  3.28it/s]
                                                            
{'loss': 2.838, 'learning_rate': 4.854123122670172e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212480/371472 [6:12:29<13:28:03,  3.28it/s]
 57%|█████▋    | 212481/371472 [6:12:29<13:28:35,  3.28it/s]
 57%|█████▋    | 212482/371472 [6:12:30<13:32:12,  3.26it/s]
 57%|█████▋    | 212483/371472 [6:12:30<13:38:32,  3.24it/s]
 57%|█████▋    | 212484/371472 [6:12:30<13:35:42,  3.25it/s]
 57%|█████▋    | 212485/371472 [6:12:31<13:52:26,  3.18it/s]
 57%|█████▋    | 212486/371472 [6:12:31<14:12:16,  3.11it/s]
 57%|█████▋    | 212487/371472 [6:12:31<14:09:08,  3.12it/s]
 57%|█████▋    | 212488/371472 [6:12:32<13:58:11,  3.16it/s]
 57%|█████▋    | 212489/371472 [6:12:32<14:05:16,  3.13it/s]
 57%|█████▋    | 212490/371472 [6:12:32<14:00:07,  3.15it/s]
 57%|█████▋    | 212491/371472 [6:12:33<13:49:13,  3.20it/s]
 57%|█████▋    | 212492/371472 [6:12:33<13:48:23,  3.20it/s]
 57%|█████▋    | 212493/371472 [6:12:33<13:29:11,  3.27it/s]
 57%|█████▋    | 212494/371472 [6:12:33<13:41:26,  3.23it/s]
 57%|█████▋    | 212495/371472 [6:12:34<14:25:03,  3.06it/s]
 57%|█████▋    | 212496/371472 [6:12:34<14:30:46,  3.04it/s]
 57%|█████▋    | 212497/371472 [6:12:34<14:20:54,  3.08it/s]
 57%|█████▋    | 212498/371472 [6:12:35<14:24:59,  3.06it/s]
 57%|█████▋    | 212499/371472 [6:12:35<13:51:24,  3.19it/s]
 57%|█████▋    | 212500/371472 [6:12:35<13:37:20,  3.24it/s]
                                                            
{'loss': 2.7864, 'learning_rate': 4.853638302915383e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212500/371472 [6:12:35<13:37:20,  3.24it/s]
 57%|█████▋    | 212501/371472 [6:12:36<13:52:10,  3.18it/s]
 57%|█████▋    | 212502/371472 [6:12:36<13:24:55,  3.29it/s]
 57%|█████▋    | 212503/371472 [6:12:36<13:16:08,  3.33it/s]
 57%|█████▋    | 212504/371472 [6:12:37<14:45:22,  2.99it/s]
 57%|█████▋    | 212505/371472 [6:12:37<14:04:02,  3.14it/s]
 57%|█████▋    | 212506/371472 [6:12:37<13:53:17,  3.18it/s]
 57%|█████▋    | 212507/371472 [6:12:38<13:47:27,  3.20it/s]
 57%|█████▋    | 212508/371472 [6:12:38<13:17:47,  3.32it/s]
 57%|█████▋    | 212509/371472 [6:12:38<13:11:31,  3.35it/s]
 57%|█████▋    | 212510/371472 [6:12:38<13:07:47,  3.36it/s]
 57%|█████▋    | 212511/371472 [6:12:39<12:59:58,  3.40it/s]
 57%|█████▋    | 212512/371472 [6:12:39<13:05:21,  3.37it/s]
 57%|█████▋    | 212513/371472 [6:12:39<13:14:45,  3.33it/s]
 57%|█████▋    | 212514/371472 [6:12:40<12:54:14,  3.42it/s]
 57%|█████▋    | 212515/371472 [6:12:40<12:59:03,  3.40it/s]
 57%|█████▋    | 212516/371472 [6:12:40<13:08:23,  3.36it/s]
 57%|█████▋    | 212517/371472 [6:12:41<13:13:38,  3.34it/s]
 57%|█████▋    | 212518/371472 [6:12:41<13:15:25,  3.33it/s]
 57%|█████▋    | 212519/371472 [6:12:41<13:44:27,  3.21it/s]
 57%|█████▋    | 212520/371472 [6:12:42<14:02:06,  3.15it/s]
                                                            
{'loss': 2.7843, 'learning_rate': 4.853153483160594e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212520/371472 [6:12:42<14:02:06,  3.15it/s]
 57%|█████▋    | 212521/371472 [6:12:42<15:00:02,  2.94it/s]
 57%|█████▋    | 212522/371472 [6:12:42<15:11:03,  2.91it/s]
 57%|█████▋    | 212523/371472 [6:12:43<14:14:35,  3.10it/s]
 57%|█████▋    | 212524/371472 [6:12:43<13:46:40,  3.20it/s]
 57%|█████▋    | 212525/371472 [6:12:43<13:23:48,  3.30it/s]
 57%|█████▋    | 212526/371472 [6:12:43<13:20:05,  3.31it/s]
 57%|█████▋    | 212527/371472 [6:12:44<12:54:20,  3.42it/s]
 57%|█████▋    | 212528/371472 [6:12:44<12:52:30,  3.43it/s]
 57%|█████▋    | 212529/371472 [6:12:44<12:45:53,  3.46it/s]
 57%|█████▋    | 212530/371472 [6:12:45<12:38:24,  3.49it/s]
 57%|█████▋    | 212531/371472 [6:12:45<12:53:39,  3.42it/s]
 57%|█████▋    | 212532/371472 [6:12:45<14:05:33,  3.13it/s]
 57%|█████▋    | 212533/371472 [6:12:45<13:43:20,  3.22it/s]
 57%|█████▋    | 212534/371472 [6:12:46<13:43:57,  3.21it/s]
 57%|█████▋    | 212535/371472 [6:12:46<14:00:44,  3.15it/s]
 57%|█████▋    | 212536/371472 [6:12:46<14:00:10,  3.15it/s]
 57%|█████▋    | 212537/371472 [6:12:47<13:53:57,  3.18it/s]
 57%|█████▋    | 212538/371472 [6:12:47<13:30:11,  3.27it/s]
 57%|█████▋    | 212539/371472 [6:12:47<13:58:36,  3.16it/s]
 57%|█████▋    | 212540/371472 [6:12:48<13:39:24,  3.23it/s]
                                                            
{'loss': 2.8295, 'learning_rate': 4.852668663405804e-07, 'epoch': 9.15}
+
 57%|█████▋    | 212540/371472 [6:12:48<13:39:24,  3.23it/s]
 57%|█████▋    | 212541/371472 [6:12:48<14:04:37,  3.14it/s]
 57%|█████▋    | 212542/371472 [6:12:48<14:05:46,  3.13it/s]
 57%|█████▋    | 212543/371472 [6:12:49<13:36:31,  3.24it/s]
 57%|█████▋    | 212544/371472 [6:12:49<13:19:21,  3.31it/s]
 57%|█████▋    | 212545/371472 [6:12:49<13:24:56,  3.29it/s]
 57%|█████▋    | 212546/371472 [6:12:50<13:18:28,  3.32it/s]
 57%|█████▋    | 212547/371472 [6:12:50<13:05:58,  3.37it/s]
 57%|█████▋    | 212548/371472 [6:12:50<12:52:34,  3.43it/s]
 57%|█████▋    | 212549/371472 [6:12:50<12:45:13,  3.46it/s]
 57%|█████▋    | 212550/371472 [6:12:51<12:51:40,  3.43it/s]
 57%|█████▋    | 212551/371472 [6:12:51<12:58:49,  3.40it/s]
 57%|█████▋    | 212552/371472 [6:12:51<13:12:33,  3.34it/s]
 57%|█████▋    | 212553/371472 [6:12:52<13:12:59,  3.34it/s]
 57%|█████▋    | 212554/371472 [6:12:52<13:25:16,  3.29it/s]
 57%|█████▋    | 212555/371472 [6:12:52<13:45:54,  3.21it/s]
 57%|█████▋    | 212556/371472 [6:12:53<14:51:24,  2.97it/s]
 57%|█████▋    | 212557/371472 [6:12:53<14:12:26,  3.11it/s]
 57%|█████▋    | 212558/371472 [6:12:53<13:42:24,  3.22it/s]
 57%|█████▋    | 212559/371472 [6:12:54<13:51:24,  3.19it/s]
 57%|█████▋    | 212560/371472 [6:12:54<13:36:51,  3.24it/s]
                                                            
{'loss': 2.6963, 'learning_rate': 4.852183843651016e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212560/371472 [6:12:54<13:36:51,  3.24it/s]
 57%|█████▋    | 212561/371472 [6:12:54<13:30:27,  3.27it/s]
 57%|█████▋    | 212562/371472 [6:12:54<13:47:41,  3.20it/s]
 57%|█████▋    | 212563/371472 [6:12:55<13:26:22,  3.28it/s]
 57%|█████▋    | 212564/371472 [6:12:55<13:18:09,  3.32it/s]
 57%|█████▋    | 212565/371472 [6:12:55<13:16:24,  3.33it/s]
 57%|█████▋    | 212566/371472 [6:12:56<12:58:04,  3.40it/s]
 57%|█████▋    | 212567/371472 [6:12:56<13:04:49,  3.37it/s]
 57%|█████▋    | 212568/371472 [6:12:56<12:55:41,  3.41it/s]
 57%|█████▋    | 212569/371472 [6:12:57<13:44:46,  3.21it/s]
 57%|█████▋    | 212570/371472 [6:12:57<14:24:19,  3.06it/s]
 57%|█████▋    | 212571/371472 [6:12:57<13:48:56,  3.19it/s]
 57%|█████▋    | 212572/371472 [6:12:57<13:48:36,  3.20it/s]
 57%|█████▋    | 212573/371472 [6:12:58<13:41:37,  3.22it/s]
 57%|█████▋    | 212574/371472 [6:12:58<13:45:17,  3.21it/s]
 57%|█████▋    | 212575/371472 [6:12:58<14:52:02,  2.97it/s]
 57%|█████▋    | 212576/371472 [6:12:59<15:21:56,  2.87it/s]
 57%|█████▋    | 212577/371472 [6:12:59<14:35:37,  3.02it/s]
 57%|█████▋    | 212578/371472 [6:13:00<15:12:12,  2.90it/s]
 57%|█████▋    | 212579/371472 [6:13:00<14:31:10,  3.04it/s]
 57%|█████▋    | 212580/371472 [6:13:00<14:14:51,  3.10it/s]
                                                            
{'loss': 2.8218, 'learning_rate': 4.851699023896226e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212580/371472 [6:13:00<14:14:51,  3.10it/s]
 57%|█████▋    | 212581/371472 [6:13:00<13:46:18,  3.20it/s]
 57%|█████▋    | 212582/371472 [6:13:01<14:50:21,  2.97it/s]
 57%|█████▋    | 212583/371472 [6:13:01<14:11:14,  3.11it/s]
 57%|█████▋    | 212584/371472 [6:13:01<14:33:26,  3.03it/s]
 57%|█████▋    | 212585/371472 [6:13:02<14:07:27,  3.12it/s]
 57%|█████▋    | 212586/371472 [6:13:02<13:31:56,  3.26it/s]
 57%|█████▋    | 212587/371472 [6:13:02<13:11:00,  3.35it/s]
 57%|█████▋    | 212588/371472 [6:13:03<13:08:39,  3.36it/s]
 57%|█████▋    | 212589/371472 [6:13:03<13:36:13,  3.24it/s]
 57%|█████▋    | 212590/371472 [6:13:03<13:35:45,  3.25it/s]
 57%|█████▋    | 212591/371472 [6:13:04<13:59:36,  3.15it/s]
 57%|█████▋    | 212592/371472 [6:13:04<13:27:36,  3.28it/s]
 57%|█████▋    | 212593/371472 [6:13:04<13:13:44,  3.34it/s]
 57%|█████▋    | 212594/371472 [6:13:04<13:09:36,  3.35it/s]
 57%|█████▋    | 212595/371472 [6:13:05<13:01:18,  3.39it/s]
 57%|█████▋    | 212596/371472 [6:13:05<13:29:34,  3.27it/s]
 57%|█████▋    | 212597/371472 [6:13:05<13:23:29,  3.30it/s]
 57%|█████▋    | 212598/371472 [6:13:06<13:06:50,  3.37it/s]
 57%|█████▋    | 212599/371472 [6:13:06<12:57:19,  3.41it/s]
 57%|█████▋    | 212600/371472 [6:13:06<13:43:08,  3.22it/s]
                                                            
{'loss': 2.8548, 'learning_rate': 4.851214204141439e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212600/371472 [6:13:06<13:43:08,  3.22it/s]
 57%|█████▋    | 212601/371472 [6:13:07<13:25:52,  3.29it/s]
 57%|█████▋    | 212602/371472 [6:13:07<13:01:17,  3.39it/s]
 57%|█████▋    | 212603/371472 [6:13:07<12:56:49,  3.41it/s]
 57%|█████▋    | 212604/371472 [6:13:07<13:01:47,  3.39it/s]
 57%|█████▋    | 212605/371472 [6:13:08<13:08:35,  3.36it/s]
 57%|█████▋    | 212606/371472 [6:13:08<12:56:48,  3.41it/s]
 57%|█████▋    | 212607/371472 [6:13:08<13:09:25,  3.35it/s]
 57%|█████▋    | 212608/371472 [6:13:09<13:03:04,  3.38it/s]
 57%|█████▋    | 212609/371472 [6:13:09<12:54:18,  3.42it/s]
 57%|█████���    | 212610/371472 [6:13:09<12:56:07,  3.41it/s]
 57%|█████▋    | 212611/371472 [6:13:09<12:37:22,  3.50it/s]
 57%|█████▋    | 212612/371472 [6:13:10<12:35:39,  3.50it/s]
 57%|█████▋    | 212613/371472 [6:13:10<12:32:23,  3.52it/s]
 57%|█████▋    | 212614/371472 [6:13:10<13:01:05,  3.39it/s]
 57%|█████▋    | 212615/371472 [6:13:11<13:07:22,  3.36it/s]
 57%|█████▋    | 212616/371472 [6:13:11<12:57:40,  3.40it/s]
 57%|█████▋    | 212617/371472 [6:13:11<12:38:52,  3.49it/s]
 57%|█████▋    | 212618/371472 [6:13:11<12:28:19,  3.54it/s]
 57%|█████▋    | 212619/371472 [6:13:12<12:37:05,  3.50it/s]
 57%|█████▋    | 212620/371472 [6:13:12<12:37:25,  3.50it/s]
                                                            
{'loss': 3.0033, 'learning_rate': 4.850729384386649e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212620/371472 [6:13:12<12:37:25,  3.50it/s]
 57%|█████▋    | 212621/371472 [6:13:12<12:40:48,  3.48it/s]
 57%|█████▋    | 212622/371472 [6:13:13<12:46:00,  3.46it/s]
 57%|█████▋    | 212623/371472 [6:13:13<13:04:02,  3.38it/s]
 57%|█████▋    | 212624/371472 [6:13:13<13:19:07,  3.31it/s]
 57%|█████▋    | 212625/371472 [6:13:14<13:01:19,  3.39it/s]
 57%|█████▋    | 212626/371472 [6:13:14<13:10:10,  3.35it/s]
 57%|█████▋    | 212627/371472 [6:13:14<12:51:45,  3.43it/s]
 57%|█████▋    | 212628/371472 [6:13:15<14:22:42,  3.07it/s]
 57%|█████▋    | 212629/371472 [6:13:15<13:43:19,  3.22it/s]
 57%|█████▋    | 212630/371472 [6:13:15<13:31:36,  3.26it/s]
 57%|█████▋    | 212631/371472 [6:13:15<13:30:33,  3.27it/s]
 57%|█████▋    | 212632/371472 [6:13:16<13:52:08,  3.18it/s]
 57%|█████▋    | 212633/371472 [6:13:16<13:30:56,  3.26it/s]
 57%|█████▋    | 212634/371472 [6:13:16<13:44:28,  3.21it/s]
 57%|█████▋    | 212635/371472 [6:13:17<13:30:47,  3.27it/s]
 57%|█████▋    | 212636/371472 [6:13:17<13:11:13,  3.35it/s]
 57%|█████▋    | 212637/371472 [6:13:17<13:57:52,  3.16it/s]
 57%|█████▋    | 212638/371472 [6:13:18<14:24:04,  3.06it/s]
 57%|█████▋    | 212639/371472 [6:13:18<14:04:10,  3.14it/s]
 57%|█████▋    | 212640/371472 [6:13:18<13:53:24,  3.18it/s]
                                                            
{'loss': 2.7761, 'learning_rate': 4.85024456463186e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212640/371472 [6:13:18<13:53:24,  3.18it/s]
 57%|█████▋    | 212641/371472 [6:13:19<13:27:04,  3.28it/s]
 57%|█████▋    | 212642/371472 [6:13:19<14:29:20,  3.05it/s]
 57%|█████▋    | 212643/371472 [6:13:19<13:53:18,  3.18it/s]
 57%|█████▋    | 212644/371472 [6:13:19<13:37:02,  3.24it/s]
 57%|█████▋    | 212645/371472 [6:13:20<13:52:47,  3.18it/s]
 57%|█████▋    | 212646/371472 [6:13:20<13:27:03,  3.28it/s]
 57%|█████▋    | 212647/371472 [6:13:20<13:59:49,  3.15it/s]
 57%|█████▋    | 212648/371472 [6:13:21<13:20:26,  3.31it/s]
 57%|█████▋    | 212649/371472 [6:13:21<14:05:38,  3.13it/s]
 57%|█████▋    | 212650/371472 [6:13:21<13:41:20,  3.22it/s]
 57%|█████▋    | 212651/371472 [6:13:22<13:22:42,  3.30it/s]
 57%|█████▋    | 212652/371472 [6:13:22<13:19:55,  3.31it/s]
 57%|█████▋    | 212653/371472 [6:13:22<13:02:59,  3.38it/s]
 57%|█████▋    | 212654/371472 [6:13:23<13:02:17,  3.38it/s]
 57%|█████▋    | 212655/371472 [6:13:23<12:50:20,  3.44it/s]
 57%|█████▋    | 212656/371472 [6:13:23<12:39:22,  3.49it/s]
 57%|█████▋    | 212657/371472 [6:13:23<12:33:36,  3.51it/s]
 57%|█████▋    | 212658/371472 [6:13:24<12:31:41,  3.52it/s]
 57%|█████▋    | 212659/371472 [6:13:24<13:18:09,  3.32it/s]
 57%|█████▋    | 212660/371472 [6:13:24<13:02:45,  3.38it/s]
                                                            
{'loss': 2.7804, 'learning_rate': 4.849759744877071e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212660/371472 [6:13:24<13:02:45,  3.38it/s]
 57%|█████▋    | 212661/371472 [6:13:25<13:49:41,  3.19it/s]
 57%|█████▋    | 212662/371472 [6:13:25<13:40:43,  3.23it/s]
 57%|█████▋    | 212663/371472 [6:13:25<13:32:26,  3.26it/s]
 57%|█████▋    | 212664/371472 [6:13:26<13:21:21,  3.30it/s]
 57%|█████▋    | 212665/371472 [6:13:26<13:07:29,  3.36it/s]
 57%|█████▋    | 212666/371472 [6:13:26<13:35:53,  3.24it/s]
 57%|█████▋    | 212667/371472 [6:13:26<13:29:06,  3.27it/s]
 57%|█████▋    | 212668/371472 [6:13:27<13:40:46,  3.22it/s]
 57%|█████▋    | 212669/371472 [6:13:27<13:34:11,  3.25it/s]
 57%|█████▋    | 212670/371472 [6:13:27<13:41:31,  3.22it/s]
 57%|█████▋    | 212671/371472 [6:13:28<13:32:27,  3.26it/s]
 57%|█████▋    | 212672/371472 [6:13:28<13:16:49,  3.32it/s]
 57%|█████▋    | 212673/371472 [6:13:28<13:12:15,  3.34it/s]
 57%|█████▋    | 212674/371472 [6:13:29<13:04:13,  3.37it/s]
 57%|█████▋    | 212675/371472 [6:13:29<12:46:38,  3.45it/s]
 57%|█████▋    | 212676/371472 [6:13:29<12:54:06,  3.42it/s]
 57%|█████▋    | 212677/371472 [6:13:29<13:11:51,  3.34it/s]
 57%|█████▋    | 212678/371472 [6:13:30<13:48:18,  3.20it/s]
 57%|█████▋    | 212679/371472 [6:13:30<14:06:59,  3.12it/s]
 57%|█████▋    | 212680/371472 [6:13:30<13:40:12,  3.23it/s]
                                                            
{'loss': 2.7053, 'learning_rate': 4.849274925122282e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212680/371472 [6:13:30<13:40:12,  3.23it/s]
 57%|█████▋    | 212681/371472 [6:13:31<14:00:49,  3.15it/s]
 57%|█████▋    | 212682/371472 [6:13:31<13:56:46,  3.16it/s]
 57%|█████▋    | 212683/371472 [6:13:31<13:42:27,  3.22it/s]
 57%|█████▋    | 212684/371472 [6:13:32<13:31:20,  3.26it/s]
 57%|█████▋    | 212685/371472 [6:13:32<13:24:00,  3.29it/s]
 57%|█████▋    | 212686/371472 [6:13:32<13:27:46,  3.28it/s]
 57%|█████▋    | 212687/371472 [6:13:33<13:55:08,  3.17it/s]
 57%|█████▋    | 212688/371472 [6:13:33<13:27:40,  3.28it/s]
 57%|█████▋    | 212689/371472 [6:13:33<13:38:14,  3.23it/s]
 57%|█████▋    | 212690/371472 [6:13:34<14:04:25,  3.13it/s]
 57%|█████▋    | 212691/371472 [6:13:34<15:31:22,  2.84it/s]
 57%|█████▋    | 212692/371472 [6:13:34<14:27:51,  3.05it/s]
 57%|█████▋    | 212693/371472 [6:13:35<14:14:41,  3.10it/s]
 57%|█████▋    | 212694/371472 [6:13:35<14:58:24,  2.95it/s]
 57%|█████▋    | 212695/371472 [6:13:35<14:33:33,  3.03it/s]
 57%|█████▋    | 212696/371472 [6:13:36<14:16:11,  3.09it/s]
 57%|█████▋    | 212697/371472 [6:13:36<13:56:11,  3.16it/s]
 57%|█████▋    | 212698/371472 [6:13:36<14:21:55,  3.07it/s]
 57%|█████▋    | 212699/371472 [6:13:36<13:39:32,  3.23it/s]
 57%|█████▋    | 212700/371472 [6:13:37<13:52:15,  3.18it/s]
                                                            
{'loss': 2.7786, 'learning_rate': 4.848790105367493e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212700/371472 [6:13:37<13:52:15,  3.18it/s]
 57%|█████▋    | 212701/371472 [6:13:37<14:33:13,  3.03it/s]
 57%|█████▋    | 212702/371472 [6:13:37<14:37:12,  3.02it/s]
 57%|█████▋    | 212703/371472 [6:13:38<13:53:31,  3.17it/s]
 57%|█████▋    | 212704/371472 [6:13:38<13:26:38,  3.28it/s]
 57%|█████▋    | 212705/371472 [6:13:38<13:22:44,  3.30it/s]
 57%|█████▋    | 212706/371472 [6:13:39<13:02:36,  3.38it/s]
 57%|█████▋    | 212707/371472 [6:13:39<12:52:08,  3.43it/s]
 57%|█████▋    | 212708/371472 [6:13:39<13:43:19,  3.21it/s]
 57%|█████▋    | 212709/371472 [6:13:40<13:15:40,  3.33it/s]
 57%|█████▋    | 212710/371472 [6:13:40<13:22:08,  3.30it/s]
 57%|█████▋    | 212711/371472 [6:13:40<12:58:54,  3.40it/s]
 57%|█████▋    | 212712/371472 [6:13:40<12:57:09,  3.40it/s]
 57%|█████▋    | 212713/371472 [6:13:41<13:20:25,  3.31it/s]
 57%|█████▋    | 212714/371472 [6:13:41<13:09:34,  3.35it/s]
 57%|█████▋    | 212715/371472 [6:13:41<12:52:15,  3.43it/s]
 57%|█████▋    | 212716/371472 [6:13:42<13:33:16,  3.25it/s]
 57%|█████▋    | 212717/371472 [6:13:42<14:04:43,  3.13it/s]
 57%|█████▋    | 212718/371472 [6:13:42<13:43:34,  3.21it/s]
 57%|█████▋    | 212719/371472 [6:13:43<13:20:15,  3.31it/s]
 57%|█████▋    | 212720/371472 [6:13:43<12:50:22,  3.43it/s]
                                                            
{'loss': 2.8218, 'learning_rate': 4.848305285612705e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212720/371472 [6:13:43<12:50:22,  3.43it/s]
 57%|█████▋    | 212721/371472 [6:13:43<12:41:42,  3.47it/s]
 57%|█████▋    | 212722/371472 [6:13:43<12:36:10,  3.50it/s]
 57%|█████▋    | 212723/371472 [6:13:44<13:24:40,  3.29it/s]
 57%|█████▋    | 212724/371472 [6:13:44<13:25:31,  3.28it/s]
 57%|█████▋    | 212725/371472 [6:13:44<13:49:43,  3.19it/s]
 57%|█████▋    | 212726/371472 [6:13:45<13:24:57,  3.29it/s]
 57%|█████▋    | 212727/371472 [6:13:45<13:18:47,  3.31it/s]
 57%|█████▋    | 212728/371472 [6:13:45<12:59:48,  3.39it/s]
 57%|█████▋    | 212729/371472 [6:13:46<12:45:58,  3.45it/s]
 57%|█████▋    | 212730/371472 [6:13:46<12:53:06,  3.42it/s]
 57%|█████▋    | 212731/371472 [6:13:46<12:48:26,  3.44it/s]
 57%|█████▋    | 212732/371472 [6:13:46<12:55:08,  3.41it/s]
 57%|█████▋    | 212733/371472 [6:13:47<12:56:09,  3.41it/s]
 57%|█████▋    | 212734/371472 [6:13:47<12:50:14,  3.43it/s]
 57%|█████▋    | 212735/371472 [6:13:47<13:22:05,  3.30it/s]
 57%|█████▋    | 212736/371472 [6:13:48<13:51:47,  3.18it/s]
 57%|█████▋    | 212737/371472 [6:13:48<13:23:00,  3.29it/s]
 57%|█████▋    | 212738/371472 [6:13:48<12:59:12,  3.40it/s]
 57%|█████▋    | 212739/371472 [6:13:48<12:47:21,  3.45it/s]
 57%|█████▋    | 212740/371472 [6:13:49<13:08:09,  3.36it/s]
                                                            
{'loss': 2.7728, 'learning_rate': 4.847820465857916e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212740/371472 [6:13:49<13:08:09,  3.36it/s]
 57%|█████▋    | 212741/371472 [6:13:49<13:10:57,  3.34it/s]
 57%|█████▋    | 212742/371472 [6:13:49<12:53:52,  3.42it/s]
 57%|█████▋    | 212743/371472 [6:13:50<13:34:24,  3.25it/s]
 57%|█████▋    | 212744/371472 [6:13:50<13:01:24,  3.39it/s]
 57%|█████▋    | 212745/371472 [6:13:50<13:02:52,  3.38it/s]
 57%|█████▋    | 212746/371472 [6:13:51<12:49:53,  3.44it/s]
 57%|█████▋    | 212747/371472 [6:13:51<12:49:51,  3.44it/s]
 57%|█████▋    | 212748/371472 [6:13:51<13:01:37,  3.38it/s]
 57%|█████▋    | 212749/371472 [6:13:51<12:45:12,  3.46it/s]
 57%|█████▋    | 212750/371472 [6:13:52<12:34:50,  3.50it/s]
 57%|█████▋    | 212751/371472 [6:13:52<12:36:19,  3.50it/s]
 57%|█████▋    | 212752/371472 [6:13:52<12:27:21,  3.54it/s]
 57%|█████▋    | 212753/371472 [6:13:53<13:26:13,  3.28it/s]
 57%|█████▋    | 212754/371472 [6:13:53<13:09:35,  3.35it/s]
 57%|█████▋    | 212755/371472 [6:13:53<13:27:14,  3.28it/s]
 57%|█████▋    | 212756/371472 [6:13:54<13:11:57,  3.34it/s]
 57%|█████▋    | 212757/371472 [6:13:54<12:53:23,  3.42it/s]
 57%|█████▋    | 212758/371472 [6:13:54<12:45:06,  3.46it/s]
 57%|█████▋    | 212759/371472 [6:13:54<13:32:46,  3.25it/s]
 57%|█████▋    | 212760/371472 [6:13:55<13:11:01,  3.34it/s]
                                                            
{'loss': 2.8223, 'learning_rate': 4.847335646103126e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212760/371472 [6:13:55<13:11:01,  3.34it/s]
 57%|█████▋    | 212761/371472 [6:13:55<13:36:02,  3.24it/s]
 57%|█████▋    | 212762/371472 [6:13:55<13:38:02,  3.23it/s]
 57%|█████▋    | 212763/371472 [6:13:56<14:08:24,  3.12it/s]
 57%|█████▋    | 212764/371472 [6:13:56<13:26:39,  3.28it/s]
 57%|█████▋    | 212765/371472 [6:13:56<13:12:46,  3.34it/s]
 57%|█████▋    | 212766/371472 [6:13:57<13:04:53,  3.37it/s]
 57%|█████▋    | 212767/371472 [6:13:57<13:12:53,  3.34it/s]
 57%|█████▋    | 212768/371472 [6:13:57<13:03:22,  3.38it/s]
 57%|█████▋    | 212769/371472 [6:13:57<12:52:14,  3.43it/s]
 57%|█████▋    | 212770/371472 [6:13:58<13:15:54,  3.32it/s]
 57%|█████▋    | 212771/371472 [6:13:58<13:16:00,  3.32it/s]
 57%|█████▋    | 212772/371472 [6:13:58<13:16:38,  3.32it/s]
 57%|█████▋    | 212773/371472 [6:13:59<13:17:11,  3.32it/s]
 57%|█████▋    | 212774/371472 [6:13:59<13:17:42,  3.32it/s]
 57%|█████▋    | 212775/371472 [6:13:59<13:20:26,  3.30it/s]
 57%|█████▋    | 212776/371472 [6:14:00<13:15:31,  3.32it/s]
 57%|█████▋    | 212777/371472 [6:14:00<12:59:14,  3.39it/s]
 57%|█████▋    | 212778/371472 [6:14:00<13:06:57,  3.36it/s]
 57%|█████▋    | 212779/371472 [6:14:00<13:05:41,  3.37it/s]
 57%|█████▋    | 212780/371472 [6:14:01<12:56:24,  3.41it/s]
                                                            
{'loss': 2.9852, 'learning_rate': 4.846850826348337e-07, 'epoch': 9.16}
+
 57%|█████▋    | 212780/371472 [6:14:01<12:56:24,  3.41it/s]
 57%|█████▋    | 212781/371472 [6:14:01<13:27:07,  3.28it/s]
 57%|█████▋    | 212782/371472 [6:14:01<13:48:24,  3.19it/s]
 57%|█████▋    | 212783/371472 [6:14:02<13:19:02,  3.31it/s]
 57%|█████▋    | 212784/371472 [6:14:02<14:00:02,  3.15it/s]
 57%|█████▋    | 212785/371472 [6:14:02<14:17:41,  3.08it/s]
 57%|█████▋    | 212786/371472 [6:14:03<13:59:31,  3.15it/s]
 57%|█████▋    | 212787/371472 [6:14:03<13:54:58,  3.17it/s]
 57%|█████▋    | 212788/371472 [6:14:03<15:19:40,  2.88it/s]
 57%|█████▋    | 212789/371472 [6:14:04<15:17:08,  2.88it/s]
 57%|█████▋    | 212790/371472 [6:14:04<14:30:41,  3.04it/s]
 57%|█████▋    | 212791/371472 [6:14:04<13:50:29,  3.18it/s]
 57%|█████▋    | 212792/371472 [6:14:05<13:32:25,  3.26it/s]
 57%|█████▋    | 212793/371472 [6:14:05<13:21:34,  3.30it/s]
 57%|█████▋    | 212794/371472 [6:14:05<14:20:04,  3.07it/s]
 57%|█████▋    | 212795/371472 [6:14:06<14:23:30,  3.06it/s]
 57%|█████▋    | 212796/371472 [6:14:06<13:32:40,  3.25it/s]
 57%|█████▋    | 212797/371472 [6:14:06<13:44:05,  3.21it/s]
 57%|█████▋    | 212798/371472 [6:14:06<13:40:01,  3.23it/s]
 57%|█████▋    | 212799/371472 [6:14:07<14:02:33,  3.14it/s]
 57%|█████▋    | 212800/371472 [6:14:07<13:54:51,  3.17it/s]
                                                            
{'loss': 2.7812, 'learning_rate': 4.846366006593549e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212800/371472 [6:14:07<13:54:51,  3.17it/s]
 57%|█████▋    | 212801/371472 [6:14:07<13:57:42,  3.16it/s]
 57%|█████▋    | 212802/371472 [6:14:08<13:36:57,  3.24it/s]
 57%|█████▋    | 212803/371472 [6:14:08<13:05:13,  3.37it/s]
 57%|█████▋    | 212804/371472 [6:14:08<13:38:23,  3.23it/s]
 57%|█████▋    | 212805/371472 [6:14:09<13:50:03,  3.19it/s]
 57%|█████▋    | 212806/371472 [6:14:09<14:05:44,  3.13it/s]
 57%|█████▋    | 212807/371472 [6:14:09<14:04:04,  3.13it/s]
 57%|█████▋    | 212808/371472 [6:14:10<14:15:07,  3.09it/s]
 57%|█████▋    | 212809/371472 [6:14:10<13:32:19,  3.26it/s]
 57%|█████▋    | 212810/371472 [6:14:10<13:26:42,  3.28it/s]
 57%|█████▋    | 212811/371472 [6:14:11<13:43:04,  3.21it/s]
 57%|█████▋    | 212812/371472 [6:14:11<14:23:36,  3.06it/s]
 57%|█████▋    | 212813/371472 [6:14:11<13:55:55,  3.16it/s]
 57%|█████▋    | 212814/371472 [6:14:12<13:46:07,  3.20it/s]
 57%|█████▋    | 212815/371472 [6:14:12<13:05:36,  3.37it/s]
 57%|█████▋    | 212816/371472 [6:14:12<12:55:19,  3.41it/s]
 57%|█████▋    | 212817/371472 [6:14:12<13:17:20,  3.32it/s]
 57%|█████▋    | 212818/371472 [6:14:13<13:07:46,  3.36it/s]
 57%|█████▋    | 212819/371472 [6:14:13<15:16:32,  2.88it/s]
 57%|█████▋    | 212820/371472 [6:14:13<14:54:38,  2.96it/s]
                                                            
{'loss': 2.7516, 'learning_rate': 4.84588118683876e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212820/371472 [6:14:13<14:54:38,  2.96it/s]
 57%|█████▋    | 212821/371472 [6:14:14<14:03:29,  3.13it/s]
 57%|█████▋    | 212822/371472 [6:14:14<13:35:12,  3.24it/s]
 57%|█████▋    | 212823/371472 [6:14:14<13:22:57,  3.29it/s]
 57%|█████▋    | 212824/371472 [6:14:15<13:19:38,  3.31it/s]
 57%|█████▋    | 212825/371472 [6:14:15<13:07:50,  3.36it/s]
 57%|█████▋    | 212826/371472 [6:14:15<13:43:31,  3.21it/s]
 57%|█████▋    | 212827/371472 [6:14:16<13:19:37,  3.31it/s]
 57%|█████▋    | 212828/371472 [6:14:16<13:02:09,  3.38it/s]
 57%|█████▋    | 212829/371472 [6:14:16<13:05:15,  3.37it/s]
 57%|█████▋    | 212830/371472 [6:14:16<12:45:40,  3.45it/s]
 57%|█████▋    | 212831/371472 [6:14:17<12:49:38,  3.44it/s]
 57%|█████▋    | 212832/371472 [6:14:17<13:18:24,  3.31it/s]
 57%|█████▋    | 212833/371472 [6:14:17<13:16:10,  3.32it/s]
 57%|█████▋    | 212834/371472 [6:14:18<13:42:52,  3.21it/s]
 57%|█████▋    | 212835/371472 [6:14:18<13:28:46,  3.27it/s]
 57%|█████▋    | 212836/371472 [6:14:18<13:03:46,  3.37it/s]
 57%|█████▋    | 212837/371472 [6:14:18<13:04:57,  3.37it/s]
 57%|█████▋    | 212838/371472 [6:14:19<12:50:55,  3.43it/s]
 57%|█████▋    | 212839/371472 [6:14:19<13:46:49,  3.20it/s]
 57%|█████▋    | 212840/371472 [6:14:19<14:01:59,  3.14it/s]
                                                            
{'loss': 2.7151, 'learning_rate': 4.845396367083971e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212840/371472 [6:14:19<14:01:59,  3.14it/s]
 57%|█████▋    | 212841/371472 [6:14:20<13:45:57,  3.20it/s]
 57%|█████▋    | 212842/371472 [6:14:20<13:38:48,  3.23it/s]
 57%|█████▋    | 212843/371472 [6:14:20<13:18:29,  3.31it/s]
 57%|█████▋    | 212844/371472 [6:14:21<13:01:43,  3.38it/s]
 57%|█████▋    | 212845/371472 [6:14:21<12:52:56,  3.42it/s]
 57%|█████▋    | 212846/371472 [6:14:21<12:46:56,  3.45it/s]
 57%|█████▋    | 212847/371472 [6:14:21<12:57:58,  3.40it/s]
 57%|█████▋    | 212848/371472 [6:14:22<15:18:48,  2.88it/s]
 57%|█████▋    | 212849/371472 [6:14:22<14:28:43,  3.04it/s]
 57%|█████▋    | 212850/371472 [6:14:23<14:04:42,  3.13it/s]
 57%|█████▋    | 212851/371472 [6:14:23<13:46:59,  3.20it/s]
 57%|█████▋    | 212852/371472 [6:14:23<13:39:22,  3.23it/s]
 57%|█████▋    | 212853/371472 [6:14:23<13:52:11,  3.18it/s]
 57%|█████▋    | 212854/371472 [6:14:24<13:25:10,  3.28it/s]
 57%|█████▋    | 212855/371472 [6:14:24<13:11:00,  3.34it/s]
 57%|█████▋    | 212856/371472 [6:14:24<13:23:13,  3.29it/s]
 57%|█████▋    | 212857/371472 [6:14:25<16:14:53,  2.71it/s]
 57%|█████▋    | 212858/371472 [6:14:25<15:16:11,  2.89it/s]
 57%|█████▋    | 212859/371472 [6:14:25<14:28:37,  3.04it/s]
 57%|█████▋    | 212860/371472 [6:14:26<14:07:14,  3.12it/s]
                                                            
{'loss': 2.8112, 'learning_rate': 4.844911547329182e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212860/371472 [6:14:26<14:07:14,  3.12it/s]
 57%|█████▋    | 212861/371472 [6:14:26<13:44:38,  3.21it/s]
 57%|█████▋    | 212862/371472 [6:14:26<13:05:46,  3.36it/s]
 57%|█████▋    | 212863/371472 [6:14:27<12:55:18,  3.41it/s]
 57%|█████▋    | 212864/371472 [6:14:27<12:46:30,  3.45it/s]
 57%|█████▋    | 212865/371472 [6:14:27<13:28:10,  3.27it/s]
 57%|█████▋    | 212866/371472 [6:14:28<13:38:23,  3.23it/s]
 57%|█████▋    | 212867/371472 [6:14:28<13:27:44,  3.27it/s]
 57%|█████▋    | 212868/371472 [6:14:28<13:26:59,  3.28it/s]
 57%|█████▋    | 212869/371472 [6:14:28<13:13:20,  3.33it/s]
 57%|█████▋    | 212870/371472 [6:14:29<13:04:44,  3.37it/s]
 57%|█████▋    | 212871/371472 [6:14:29<13:26:23,  3.28it/s]
 57%|█████▋    | 212872/371472 [6:14:29<13:27:45,  3.27it/s]
 57%|█████▋    | 212873/371472 [6:14:30<13:19:23,  3.31it/s]
 57%|█████▋    | 212874/371472 [6:14:30<13:17:00,  3.32it/s]
 57%|█████▋    | 212875/371472 [6:14:30<13:12:49,  3.33it/s]
 57%|█████▋    | 212876/371472 [6:14:31<13:32:59,  3.25it/s]
 57%|█████▋    | 212877/371472 [6:14:31<13:29:07,  3.27it/s]
 57%|█████▋    | 212878/371472 [6:14:31<13:20:09,  3.30it/s]
 57%|█████▋    | 212879/371472 [6:14:31<13:24:14,  3.29it/s]
 57%|█████▋    | 212880/371472 [6:14:32<13:14:11,  3.33it/s]
                                                            
{'loss': 2.6776, 'learning_rate': 4.844426727574393e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212880/371472 [6:14:32<13:14:11,  3.33it/s]
 57%|█████▋    | 212881/371472 [6:14:32<14:37:45,  3.01it/s]
 57%|█████▋    | 212882/371472 [6:14:33<14:40:05,  3.00it/s]
 57%|█████▋    | 212883/371472 [6:14:33<14:24:05,  3.06it/s]
 57%|█████▋    | 212884/371472 [6:14:33<14:25:03,  3.06it/s]
 57%|█████▋    | 212885/371472 [6:14:33<13:59:51,  3.15it/s]
 57%|█████▋    | 212886/371472 [6:14:34<13:29:35,  3.26it/s]
 57%|█████▋    | 212887/371472 [6:14:34<13:13:00,  3.33it/s]
 57%|█████▋    | 212888/371472 [6:14:34<13:13:06,  3.33it/s]
 57%|█████▋    | 212889/371472 [6:14:35<12:51:11,  3.43it/s]
 57%|█████▋    | 212890/371472 [6:14:35<12:40:31,  3.48it/s]
 57%|█████▋    | 212891/371472 [6:14:35<12:46:16,  3.45it/s]
 57%|█████▋    | 212892/371472 [6:14:35<12:50:01,  3.43it/s]
 57%|█████▋    | 212893/371472 [6:14:36<13:35:22,  3.24it/s]
 57%|█████▋    | 212894/371472 [6:14:36<13:21:35,  3.30it/s]
 57%|█████▋    | 212895/371472 [6:14:36<13:08:37,  3.35it/s]
 57%|█████▋    | 212896/371472 [6:14:37<13:02:39,  3.38it/s]
 57%|█████▋    | 212897/371472 [6:14:37<13:11:06,  3.34it/s]
 57%|█████▋    | 212898/371472 [6:14:37<13:27:38,  3.27it/s]
 57%|█████▋    | 212899/371472 [6:14:38<13:38:50,  3.23it/s]
 57%|█████▋    | 212900/371472 [6:14:38<13:08:25,  3.35it/s]
                                                            
{'loss': 2.9367, 'learning_rate': 4.843941907819603e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212900/371472 [6:14:38<13:08:25,  3.35it/s]
 57%|█████▋    | 212901/371472 [6:14:38<13:08:47,  3.35it/s]
 57%|█████▋    | 212902/371472 [6:14:38<12:43:20,  3.46it/s]
 57%|█████▋    | 212903/371472 [6:14:39<12:31:58,  3.51it/s]
 57%|█████▋    | 212904/371472 [6:14:39<12:41:45,  3.47it/s]
 57%|█████▋    | 212905/371472 [6:14:39<12:42:57,  3.46it/s]
 57%|█████▋    | 212906/371472 [6:14:40<13:01:12,  3.38it/s]
 57%|█████▋    | 212907/371472 [6:14:40<13:18:46,  3.31it/s]
 57%|█████▋    | 212908/371472 [6:14:40<13:08:44,  3.35it/s]
 57%|█████▋    | 212909/371472 [6:14:41<12:59:37,  3.39it/s]
 57%|█████▋    | 212910/371472 [6:14:41<13:06:59,  3.36it/s]
 57%|█████▋    | 212911/371472 [6:14:41<13:05:39,  3.36it/s]
 57%|█████▋    | 212912/371472 [6:14:41<13:44:38,  3.20it/s]
 57%|█████▋    | 212913/371472 [6:14:42<13:30:44,  3.26it/s]
 57%|█████▋    | 212914/371472 [6:14:42<13:12:11,  3.34it/s]
 57%|█████▋    | 212915/371472 [6:14:42<13:08:13,  3.35it/s]
 57%|█████▋    | 212916/371472 [6:14:43<12:57:51,  3.40it/s]
 57%|█████▋    | 212917/371472 [6:14:43<13:00:32,  3.39it/s]
 57%|████��▋    | 212918/371472 [6:14:43<12:57:03,  3.40it/s]
 57%|█████▋    | 212919/371472 [6:14:44<13:01:28,  3.38it/s]
 57%|█████▋    | 212920/371472 [6:14:44<12:50:27,  3.43it/s]
                                                            
{'loss': 2.6525, 'learning_rate': 4.843457088064815e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212920/371472 [6:14:44<12:50:27,  3.43it/s]
 57%|█████▋    | 212921/371472 [6:14:44<13:12:37,  3.33it/s]
 57%|█████▋    | 212922/371472 [6:14:44<13:16:54,  3.32it/s]
 57%|█████▋    | 212923/371472 [6:14:45<13:21:33,  3.30it/s]
 57%|█████▋    | 212924/371472 [6:14:45<13:20:45,  3.30it/s]
 57%|█████▋    | 212925/371472 [6:14:45<13:25:21,  3.28it/s]
 57%|█████▋    | 212926/371472 [6:14:46<13:11:33,  3.34it/s]
 57%|█████▋    | 212927/371472 [6:14:46<13:04:43,  3.37it/s]
 57%|█████▋    | 212928/371472 [6:14:46<13:16:05,  3.32it/s]
 57%|█████▋    | 212929/371472 [6:14:47<13:01:36,  3.38it/s]
 57%|█████▋    | 212930/371472 [6:14:47<13:03:39,  3.37it/s]
 57%|█████▋    | 212931/371472 [6:14:47<13:09:28,  3.35it/s]
 57%|█████▋    | 212932/371472 [6:14:47<13:28:05,  3.27it/s]
 57%|█████▋    | 212933/371472 [6:14:48<13:25:37,  3.28it/s]
 57%|█████▋    | 212934/371472 [6:14:48<13:45:39,  3.20it/s]
 57%|█████▋    | 212935/371472 [6:14:48<14:10:36,  3.11it/s]
 57%|█████▋    | 212936/371472 [6:14:49<13:49:26,  3.19it/s]
 57%|█████▋    | 212937/371472 [6:14:49<14:25:19,  3.05it/s]
 57%|█████▋    | 212938/371472 [6:14:49<13:57:21,  3.16it/s]
 57%|█████▋    | 212939/371472 [6:14:50<14:25:56,  3.05it/s]
 57%|█████▋    | 212940/371472 [6:14:50<14:10:42,  3.11it/s]
                                                            
{'loss': 2.731, 'learning_rate': 4.842972268310026e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212940/371472 [6:14:50<14:10:42,  3.11it/s]
 57%|█████▋    | 212941/371472 [6:14:50<13:54:51,  3.16it/s]
 57%|█████▋    | 212942/371472 [6:14:51<13:33:45,  3.25it/s]
 57%|█████▋    | 212943/371472 [6:14:51<13:12:52,  3.33it/s]
 57%|█████▋    | 212944/371472 [6:14:51<13:09:39,  3.35it/s]
 57%|█████▋    | 212945/371472 [6:14:51<12:48:25,  3.44it/s]
 57%|█████▋    | 212946/371472 [6:14:52<14:20:27,  3.07it/s]
 57%|█████▋    | 212947/371472 [6:14:52<14:09:55,  3.11it/s]
 57%|█████▋    | 212948/371472 [6:14:52<13:50:37,  3.18it/s]
 57%|█████▋    | 212949/371472 [6:14:53<13:28:10,  3.27it/s]
 57%|█████▋    | 212950/371472 [6:14:53<13:06:49,  3.36it/s]
 57%|█████▋    | 212951/371472 [6:14:53<12:47:52,  3.44it/s]
 57%|█████▋    | 212952/371472 [6:14:54<12:51:17,  3.43it/s]
 57%|█████▋    | 212953/371472 [6:14:54<12:40:24,  3.47it/s]
 57%|█████▋    | 212954/371472 [6:14:54<12:35:00,  3.50it/s]
 57%|█████▋    | 212955/371472 [6:14:54<12:36:51,  3.49it/s]
 57%|█████▋    | 212956/371472 [6:14:55<14:13:56,  3.09it/s]
 57%|█████▋    | 212957/371472 [6:14:55<14:19:11,  3.07it/s]
 57%|█████▋    | 212958/371472 [6:14:55<13:41:37,  3.22it/s]
 57%|█████▋    | 212959/371472 [6:14:56<13:12:39,  3.33it/s]
 57%|█████▋    | 212960/371472 [6:14:56<13:44:52,  3.20it/s]
                                                            
{'loss': 2.7802, 'learning_rate': 4.842487448555238e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212960/371472 [6:14:56<13:44:52,  3.20it/s]
 57%|█████▋    | 212961/371472 [6:14:56<13:24:08,  3.29it/s]
 57%|█████▋    | 212962/371472 [6:14:57<13:29:48,  3.26it/s]
 57%|█████▋    | 212963/371472 [6:14:57<13:10:51,  3.34it/s]
 57%|█████▋    | 212964/371472 [6:14:57<12:47:54,  3.44it/s]
 57%|█████▋    | 212965/371472 [6:14:58<13:15:41,  3.32it/s]
 57%|█████▋    | 212966/371472 [6:14:58<14:22:39,  3.06it/s]
 57%|█████▋    | 212967/371472 [6:14:58<13:46:56,  3.19it/s]
 57%|█████▋    | 212968/371472 [6:14:59<13:17:36,  3.31it/s]
 57%|█████▋    | 212969/371472 [6:14:59<13:10:41,  3.34it/s]
 57%|█████▋    | 212970/371472 [6:14:59<13:02:55,  3.37it/s]
 57%|█████▋    | 212971/371472 [6:14:59<12:40:53,  3.47it/s]
 57%|█████▋    | 212972/371472 [6:15:00<12:44:34,  3.46it/s]
 57%|█████▋    | 212973/371472 [6:15:00<12:59:46,  3.39it/s]
 57%|█████▋    | 212974/371472 [6:15:00<13:02:02,  3.38it/s]
 57%|█████▋    | 212975/371472 [6:15:01<13:50:31,  3.18it/s]
 57%|█████▋    | 212976/371472 [6:15:01<13:16:26,  3.32it/s]
 57%|█████▋    | 212977/371472 [6:15:01<14:04:14,  3.13it/s]
 57%|█████▋    | 212978/371472 [6:15:02<13:44:05,  3.21it/s]
 57%|█████▋    | 212979/371472 [6:15:02<13:29:20,  3.26it/s]
 57%|█████▋    | 212980/371472 [6:15:02<13:47:56,  3.19it/s]
                                                            
{'loss': 2.763, 'learning_rate': 4.842002628800448e-07, 'epoch': 9.17}
+
 57%|█████▋    | 212980/371472 [6:15:02<13:47:56,  3.19it/s]
 57%|█████▋    | 212981/371472 [6:15:02<13:47:33,  3.19it/s]
 57%|█████▋    | 212982/371472 [6:15:03<14:00:11,  3.14it/s]
 57%|█████▋    | 212983/371472 [6:15:03<13:59:17,  3.15it/s]
 57%|█████▋    | 212984/371472 [6:15:03<14:12:52,  3.10it/s]
 57%|█████▋    | 212985/371472 [6:15:04<13:54:25,  3.17it/s]
 57%|█████▋    | 212986/371472 [6:15:04<14:07:23,  3.12it/s]
 57%|█████▋    | 212987/371472 [6:15:04<13:40:54,  3.22it/s]
 57%|█████▋    | 212988/371472 [6:15:05<13:17:13,  3.31it/s]
 57%|█████▋    | 212989/371472 [6:15:05<13:15:58,  3.32it/s]
 57%|█████▋    | 212990/371472 [6:15:05<13:31:14,  3.26it/s]
 57%|█████▋    | 212991/371472 [6:15:06<13:57:41,  3.15it/s]
 57%|█████▋    | 212992/371472 [6:15:06<13:57:11,  3.15it/s]
 57%|█████▋    | 212993/371472 [6:15:06<14:07:54,  3.12it/s]
 57%|█████▋    | 212994/371472 [6:15:07<13:43:31,  3.21it/s]
 57%|█████▋    | 212995/371472 [6:15:07<13:31:19,  3.26it/s]
 57%|█████▋    | 212996/371472 [6:15:07<13:06:35,  3.36it/s]
 57%|█████▋    | 212997/371472 [6:15:07<12:51:54,  3.42it/s]
 57%|█████▋    | 212998/371472 [6:15:08<13:51:34,  3.18it/s]
 57%|█████▋    | 212999/371472 [6:15:08<13:29:52,  3.26it/s]
 57%|█████▋    | 213000/371472 [6:15:08<12:55:22,  3.41it/s]
                                                            
{'loss': 2.652, 'learning_rate': 4.841517809045659e-07, 'epoch': 9.17}
+
 57%|█████▋    | 213000/371472 [6:15:08<12:55:22,  3.41it/s]
 57%|█████▋    | 213001/371472 [6:15:09<12:46:03,  3.45it/s]
 57%|█████▋    | 213002/371472 [6:15:09<12:45:48,  3.45it/s]
 57%|█████▋    | 213003/371472 [6:15:09<12:38:33,  3.48it/s]
 57%|█████▋    | 213004/371472 [6:15:09<12:41:33,  3.47it/s]
 57%|█████▋    | 213005/371472 [6:15:10<13:06:16,  3.36it/s]
 57%|█████▋    | 213006/371472 [6:15:10<12:45:54,  3.45it/s]
 57%|█████▋    | 213007/371472 [6:15:10<12:34:12,  3.50it/s]
 57%|█████▋    | 213008/371472 [6:15:11<12:40:52,  3.47it/s]
 57%|█████▋    | 213009/371472 [6:15:11<12:32:33,  3.51it/s]
 57%|█████▋    | 213010/371472 [6:15:11<12:22:36,  3.56it/s]
 57%|█████▋    | 213011/371472 [6:15:12<15:20:49,  2.87it/s]
 57%|█████▋    | 213012/371472 [6:15:12<14:17:35,  3.08it/s]
 57%|█████▋    | 213013/371472 [6:15:12<13:36:25,  3.23it/s]
 57%|█████▋    | 213014/371472 [6:15:13<14:23:47,  3.06it/s]
 57%|█████▋    | 213015/371472 [6:15:13<13:50:27,  3.18it/s]
 57%|█████▋    | 213016/371472 [6:15:13<13:20:10,  3.30it/s]
 57%|█████▋    | 213017/371472 [6:15:13<13:07:37,  3.35it/s]
 57%|█████▋    | 213018/371472 [6:15:14<13:09:00,  3.35it/s]
 57%|█████▋    | 213019/371472 [6:15:14<13:17:56,  3.31it/s]
 57%|█████▋    | 213020/371472 [6:15:14<13:01:16,  3.38it/s]
                                                            
{'loss': 2.8239, 'learning_rate': 4.84103298929087e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213020/371472 [6:15:14<13:01:16,  3.38it/s]
 57%|█████▋    | 213021/371472 [6:15:15<13:09:28,  3.35it/s]
 57%|█████▋    | 213022/371472 [6:15:15<13:11:42,  3.34it/s]
 57%|█████▋    | 213023/371472 [6:15:15<12:51:12,  3.42it/s]
 57%|█████▋    | 213024/371472 [6:15:16<13:49:39,  3.18it/s]
 57%|█████▋    | 213025/371472 [6:15:16<13:20:45,  3.30it/s]
 57%|█████▋    | 213026/371472 [6:15:16<13:49:43,  3.18it/s]
 57%|█████▋    | 213027/371472 [6:15:17<13:47:48,  3.19it/s]
 57%|█████▋    | 213028/371472 [6:15:17<14:08:00,  3.11it/s]
 57%|█████▋    | 213029/371472 [6:15:17<13:49:29,  3.18it/s]
 57%|█████▋    | 213030/371472 [6:15:17<14:14:07,  3.09it/s]
 57%|█████▋    | 213031/371472 [6:15:18<14:39:02,  3.00it/s]
 57%|█████▋    | 213032/371472 [6:15:18<13:47:54,  3.19it/s]
 57%|█████▋    | 213033/371472 [6:15:18<13:43:23,  3.21it/s]
 57%|█████▋    | 213034/371472 [6:15:19<13:50:23,  3.18it/s]
 57%|█████▋    | 213035/371472 [6:15:19<13:42:43,  3.21it/s]
 57%|█████▋    | 213036/371472 [6:15:19<13:11:06,  3.34it/s]
 57%|█████▋    | 213037/371472 [6:15:20<13:56:43,  3.16it/s]
 57%|█████▋    | 213038/371472 [6:15:20<13:42:41,  3.21it/s]
 57%|█████▋    | 213039/371472 [6:15:20<13:19:16,  3.30it/s]
 57%|█████▋    | 213040/371472 [6:15:21<13:20:54,  3.30it/s]
                                                            
{'loss': 2.8207, 'learning_rate': 4.840548169536081e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213040/371472 [6:15:21<13:20:54,  3.30it/s]
 57%|█████▋    | 213041/371472 [6:15:21<13:23:52,  3.28it/s]
 57%|█████▋    | 213042/371472 [6:15:21<13:15:09,  3.32it/s]
 57%|█████▋    | 213043/371472 [6:15:21<13:03:35,  3.37it/s]
 57%|█████▋    | 213044/371472 [6:15:22<12:44:28,  3.45it/s]
 57%|█████▋    | 213045/371472 [6:15:22<12:42:57,  3.46it/s]
 57%|█████▋    | 213046/371472 [6:15:22<12:46:50,  3.44it/s]
 57%|█████▋    | 213047/371472 [6:15:23<13:05:52,  3.36it/s]
 57%|█████▋    | 213048/371472 [6:15:23<12:42:09,  3.46it/s]
 57%|█████▋    | 213049/371472 [6:15:23<12:52:28,  3.42it/s]
 57%|█████▋    | 213050/371472 [6:15:24<13:22:59,  3.29it/s]
 57%|█████▋    | 213051/371472 [6:15:24<12:56:43,  3.40it/s]
 57%|█████▋    | 213052/371472 [6:15:24<13:05:21,  3.36it/s]
 57%|█████▋    | 213053/371472 [6:15:24<13:10:19,  3.34it/s]
 57%|█████▋    | 213054/371472 [6:15:25<13:14:52,  3.32it/s]
 57%|█████▋    | 213055/371472 [6:15:25<13:09:18,  3.35it/s]
 57%|█████▋    | 213056/371472 [6:15:25<13:19:20,  3.30it/s]
 57%|█████▋    | 213057/371472 [6:15:26<13:08:46,  3.35it/s]
 57%|█████▋    | 213058/371472 [6:15:26<13:20:23,  3.30it/s]
 57%|█████▋    | 213059/371472 [6:15:26<13:23:57,  3.28it/s]
 57%|█████▋    | 213060/371472 [6:15:27<13:42:29,  3.21it/s]
                                                            
{'loss': 2.7807, 'learning_rate': 4.840063349781292e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213060/371472 [6:15:27<13:42:29,  3.21it/s]
 57%|█████▋    | 213061/371472 [6:15:27<14:09:06,  3.11it/s]
 57%|█████▋    | 213062/371472 [6:15:27<14:57:49,  2.94it/s]
 57%|█████▋    | 213063/371472 [6:15:28<14:22:16,  3.06it/s]
 57%|█████▋    | 213064/371472 [6:15:28<14:00:36,  3.14it/s]
 57%|█████▋    | 213065/371472 [6:15:28<14:07:16,  3.12it/s]
 57%|█████▋    | 213066/371472 [6:15:28<13:31:39,  3.25it/s]
 57%|█████▋    | 213067/371472 [6:15:29<13:26:00,  3.28it/s]
 57%|█████▋    | 213068/371472 [6:15:29<13:21:14,  3.29it/s]
 57%|█████▋    | 213069/371472 [6:15:29<12:55:38,  3.40it/s]
 57%|█████▋    | 213070/371472 [6:15:30<12:42:20,  3.46it/s]
 57%|█████▋    | 213071/371472 [6:15:30<12:58:15,  3.39it/s]
 57%|█████▋    | 213072/371472 [6:15:30<12:52:12,  3.42it/s]
 57%|█████▋    | 213073/371472 [6:15:31<13:58:34,  3.15it/s]
 57%|█████▋    | 213074/371472 [6:15:31<13:18:54,  3.30it/s]
 57%|█████▋    | 213075/371472 [6:15:31<13:08:25,  3.35it/s]
 57%|█████▋    | 213076/371472 [6:15:31<13:37:20,  3.23it/s]
 57%|█████▋    | 213077/371472 [6:15:32<13:16:19,  3.32it/s]
 57%|█████▋    | 213078/371472 [6:15:32<13:00:22,  3.38it/s]
 57%|█████▋    | 213079/371472 [6:15:32<13:06:24,  3.36it/s]
 57%|█████▋    | 213080/371472 [6:15:33<15:04:54,  2.92it/s]
                                                            
{'loss': 2.8629, 'learning_rate': 4.839578530026503e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213080/371472 [6:15:33<15:04:54,  2.92it/s]
 57%|█████▋    | 213081/371472 [6:15:33<14:36:52,  3.01it/s]
 57%|█████▋    | 213082/371472 [6:15:33<14:00:39,  3.14it/s]
 57%|█████▋    | 213083/371472 [6:15:34<13:12:08,  3.33it/s]
 57%|█████▋    | 213084/371472 [6:15:34<13:35:37,  3.24it/s]
 57%|█████▋    | 213085/371472 [6:15:34<13:20:19,  3.30it/s]
 57%|█████▋    | 213086/371472 [6:15:35<13:19:33,  3.30it/s]
 57%|█████▋    | 213087/371472 [6:15:35<13:47:53,  3.19it/s]
 57%|█████▋    | 213088/371472 [6:15:35<14:08:27,  3.11it/s]
 57%|█████▋    | 213089/371472 [6:15:36<13:46:01,  3.20it/s]
 57%|█████▋    | 213090/371472 [6:15:36<14:09:57,  3.11it/s]
 57%|█████▋    | 213091/371472 [6:15:36<13:34:31,  3.24it/s]
 57%|█████▋    | 213092/371472 [6:15:36<13:11:07,  3.34it/s]
 57%|█████▋    | 213093/371472 [6:15:37<13:01:04,  3.38it/s]
 57%|█████▋    | 213094/371472 [6:15:37<12:37:47,  3.48it/s]
 57%|█████▋    | 213095/371472 [6:15:37<13:11:03,  3.34it/s]
 57%|█████▋    | 213096/371472 [6:15:38<13:35:36,  3.24it/s]
 57%|█████▋    | 213097/371472 [6:15:38<13:22:33,  3.29it/s]
 57%|█████▋    | 213098/371472 [6:15:38<13:41:30,  3.21it/s]
 57%|█████▋    | 213099/371472 [6:15:39<13:30:50,  3.26it/s]
 57%|█████▋    | 213100/371472 [6:15:39<13:03:22,  3.37it/s]
                                                            
{'loss': 2.7593, 'learning_rate': 4.839093710271715e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213100/371472 [6:15:39<13:03:22,  3.37it/s]
 57%|█████▋    | 213101/371472 [6:15:39<13:03:27,  3.37it/s]
 57%|█████▋    | 213102/371472 [6:15:40<14:16:51,  3.08it/s]
 57%|█████▋    | 213103/371472 [6:15:40<13:37:52,  3.23it/s]
 57%|█████▋    | 213104/371472 [6:15:40<13:41:07,  3.21it/s]
 57%|█████▋    | 213105/371472 [6:15:40<13:28:55,  3.26it/s]
 57%|█████▋    | 213106/371472 [6:15:41<13:24:25,  3.28it/s]
 57%|█████▋    | 213107/371472 [6:15:41<13:31:23,  3.25it/s]
 57%|█████▋    | 213108/371472 [6:15:41<13:21:01,  3.30it/s]
 57%|█████▋    | 213109/371472 [6:15:42<13:05:45,  3.36it/s]
 57%|█████▋    | 213110/371472 [6:15:42<12:55:27,  3.40it/s]
 57%|█████▋    | 213111/371472 [6:15:42<12:58:47,  3.39it/s]
 57%|█████▋    | 213112/371472 [6:15:42<12:33:40,  3.50it/s]
 57%|█████▋    | 213113/371472 [6:15:43<12:54:24,  3.41it/s]
 57%|█████▋    | 213114/371472 [6:15:43<13:08:47,  3.35it/s]
 57%|█████▋    | 213115/371472 [6:15:43<13:54:10,  3.16it/s]
 57%|█████▋    | 213116/371472 [6:15:44<13:44:57,  3.20it/s]
 57%|█████▋    | 213117/371472 [6:15:44<13:37:16,  3.23it/s]
 57%|█████▋    | 213118/371472 [6:15:44<13:03:52,  3.37it/s]
 57%|█████▋    | 213119/371472 [6:15:45<12:46:59,  3.44it/s]
 57%|█████▋    | 213120/371472 [6:15:45<12:34:52,  3.50it/s]
                                                            
{'loss': 3.0015, 'learning_rate': 4.838608890516926e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213120/371472 [6:15:45<12:34:52,  3.50it/s]
 57%|█████▋    | 213121/371472 [6:15:45<12:51:51,  3.42it/s]
 57%|█████▋    | 213122/371472 [6:15:45<13:13:35,  3.33it/s]
 57%|█████▋    | 213123/371472 [6:15:46<13:12:16,  3.33it/s]
 57%|█████▋    | 213124/371472 [6:15:46<13:09:37,  3.34it/s]
 57%|█████▋    | 213125/371472 [6:15:46<13:15:47,  3.32it/s]
 57%|█████▋    | 213126/371472 [6:15:47<13:13:23,  3.33it/s]
 57%|█████▋    | 213127/371472 [6:15:47<12:43:19,  3.46it/s]
 57%|█████▋    | 213128/371472 [6:15:47<12:53:38,  3.41it/s]
 57%|█████▋    | 213129/371472 [6:15:48<13:00:17,  3.38it/s]
 57%|█████▋    | 213130/371472 [6:15:48<12:46:38,  3.44it/s]
 57%|█████▋    | 213131/371472 [6:15:48<12:47:28,  3.44it/s]
 57%|█████▋    | 213132/371472 [6:15:48<12:50:25,  3.43it/s]
 57%|█████▋    | 213133/371472 [6:15:49<12:51:56,  3.42it/s]
 57%|█████▋    | 213134/371472 [6:15:49<12:45:17,  3.45it/s]
 57%|█████▋    | 213135/371472 [6:15:49<12:50:32,  3.42it/s]
 57%|█████▋    | 213136/371472 [6:15:50<12:57:48,  3.39it/s]
 57%|█████▋    | 213137/371472 [6:15:50<13:20:22,  3.30it/s]
 57%|█████▋    | 213138/371472 [6:15:50<13:28:11,  3.27it/s]
 57%|█████▋    | 213139/371472 [6:15:51<13:39:53,  3.22it/s]
 57%|█████▋    | 213140/371472 [6:15:51<13:21:26,  3.29it/s]
                                                            
{'loss': 2.839, 'learning_rate': 4.838124070762136e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213140/371472 [6:15:51<13:21:26,  3.29it/s]
 57%|█████▋    | 213141/371472 [6:15:51<13:05:59,  3.36it/s]
 57%|█████▋    | 213142/371472 [6:15:51<13:04:52,  3.36it/s]
 57%|█████▋    | 213143/371472 [6:15:52<13:28:39,  3.26it/s]
 57%|█████▋    | 213144/371472 [6:15:52<13:39:23,  3.22it/s]
 57%|█████▋    | 213145/371472 [6:15:52<13:32:01,  3.25it/s]
 57%|█████▋    | 213146/371472 [6:15:53<13:27:48,  3.27it/s]
 57%|█████▋    | 213147/371472 [6:15:53<13:05:40,  3.36it/s]
 57%|█████▋    | 213148/371472 [6:15:53<13:18:41,  3.30it/s]
 57%|█████▋    | 213149/371472 [6:15:54<13:14:41,  3.32it/s]
 57%|█████▋    | 213150/371472 [6:15:54<13:47:02,  3.19it/s]
 57%|█████▋    | 213151/371472 [6:15:54<13:46:32,  3.19it/s]
 57%|█████▋    | 213152/371472 [6:15:55<13:24:37,  3.28it/s]
 57%|█████▋    | 213153/371472 [6:15:55<13:22:52,  3.29it/s]
 57%|█████▋    | 213154/371472 [6:15:55<13:37:26,  3.23it/s]
 57%|█████▋    | 213155/371472 [6:15:55<13:52:45,  3.17it/s]
 57%|█████▋    | 213156/371472 [6:15:56<13:23:04,  3.29it/s]
 57%|█████▋    | 213157/371472 [6:15:56<13:04:42,  3.36it/s]
 57%|█████▋    | 213158/371472 [6:15:56<13:20:48,  3.29it/s]
 57%|█████▋    | 213159/371472 [6:15:57<13:42:15,  3.21it/s]
 57%|█████▋    | 213160/371472 [6:15:57<14:14:48,  3.09it/s]
                                                            
{'loss': 2.7609, 'learning_rate': 4.837639251007347e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213160/371472 [6:15:57<14:14:48,  3.09it/s]
 57%|█████▋    | 213161/371472 [6:15:57<14:11:21,  3.10it/s]
 57%|█████▋    | 213162/371472 [6:15:58<13:59:46,  3.14it/s]
 57%|█████▋    | 213163/371472 [6:15:58<13:19:29,  3.30it/s]
 57%|█████▋    | 213164/371472 [6:15:58<13:18:56,  3.30it/s]
 57%|█████▋    | 213165/371472 [6:15:59<14:02:01,  3.13it/s]
 57%|█████▋    | 213166/371472 [6:15:59<13:28:19,  3.26it/s]
 57%|█████▋    | 213167/371472 [6:15:59<13:09:30,  3.34it/s]
 57%|█████▋    | 213168/371472 [6:15:59<12:48:08,  3.43it/s]
 57%|█████▋    | 213169/371472 [6:16:00<13:23:29,  3.28it/s]
 57%|█████▋    | 213170/371472 [6:16:00<12:59:40,  3.38it/s]
 57%|█████▋    | 213171/371472 [6:16:00<12:50:21,  3.42it/s]
 57%|█████▋    | 213172/371472 [6:16:01<13:31:15,  3.25it/s]
 57%|█████▋    | 213173/371472 [6:16:01<13:24:39,  3.28it/s]
 57%|█████▋    | 213174/371472 [6:16:01<13:22:25,  3.29it/s]
 57%|█████▋    | 213175/371472 [6:16:02<13:27:07,  3.27it/s]
 57%|█████▋    | 213176/371472 [6:16:02<13:21:52,  3.29it/s]
 57%|█████▋    | 213177/371472 [6:16:02<13:49:07,  3.18it/s]
 57%|█████▋    | 213178/371472 [6:16:03<13:50:09,  3.18it/s]
 57%|█████▋    | 213179/371472 [6:16:03<13:47:02,  3.19it/s]
 57%|█████▋    | 213180/371472 [6:16:03<13:46:32,  3.19it/s]
                                                            
{'loss': 2.7606, 'learning_rate': 4.837154431252559e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213180/371472 [6:16:03<13:46:32,  3.19it/s]
 57%|█████▋    | 213181/371472 [6:16:03<13:29:28,  3.26it/s]
 57%|█████▋    | 213182/371472 [6:16:04<13:31:54,  3.25it/s]
 57%|█████▋    | 213183/371472 [6:16:04<13:51:32,  3.17it/s]
 57%|█████▋    | 213184/371472 [6:16:04<13:39:39,  3.22it/s]
 57%|█████▋    | 213185/371472 [6:16:05<13:22:03,  3.29it/s]
 57%|█████▋    | 213186/371472 [6:16:05<13:24:04,  3.28it/s]
 57%|█████▋    | 213187/371472 [6:16:05<12:59:29,  3.38it/s]
 57%|█████▋    | 213188/371472 [6:16:06<13:06:15,  3.36it/s]
 57%|█████▋    | 213189/371472 [6:16:06<13:23:38,  3.28it/s]
 57%|█████▋    | 213190/371472 [6:16:06<13:19:46,  3.30it/s]
 57%|█████▋    | 213191/371472 [6:16:06<13:12:11,  3.33it/s]
 57%|█████▋    | 213192/371472 [6:16:07<13:53:59,  3.16it/s]
 57%|█████▋    | 213193/371472 [6:16:07<14:26:40,  3.04it/s]
 57%|█████▋    | 213194/371472 [6:16:08<14:28:55,  3.04it/s]
 57%|█████▋    | 213195/371472 [6:16:08<13:53:15,  3.17it/s]
 57%|█████▋    | 213196/371472 [6:16:08<13:32:00,  3.25it/s]
 57%|█████▋    | 213197/371472 [6:16:08<13:10:03,  3.34it/s]
 57%|█████▋    | 213198/371472 [6:16:09<13:30:28,  3.25it/s]
 57%|█████▋    | 213199/371472 [6:16:09<14:22:21,  3.06it/s]
 57%|█████▋    | 213200/371472 [6:16:09<13:45:46,  3.19it/s]
                                                            
{'loss': 2.8152, 'learning_rate': 4.83666961149777e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213200/371472 [6:16:09<13:45:46,  3.19it/s]
 57%|█████▋    | 213201/371472 [6:16:10<13:09:54,  3.34it/s]
 57%|█████▋    | 213202/371472 [6:16:10<13:09:04,  3.34it/s]
 57%|█████▋    | 213203/371472 [6:16:10<13:53:17,  3.17it/s]
 57%|█████▋    | 213204/371472 [6:16:11<13:22:34,  3.29it/s]
 57%|█████▋    | 213205/371472 [6:16:11<14:24:40,  3.05it/s]
 57%|█████▋    | 213206/371472 [6:16:11<13:51:25,  3.17it/s]
 57%|█████▋    | 213207/371472 [6:16:12<13:50:19,  3.18it/s]
 57%|█████▋    | 213208/371472 [6:16:12<13:42:41,  3.21it/s]
 57%|█████▋    | 213209/371472 [6:16:12<14:13:51,  3.09it/s]
 57%|█████▋    | 213210/371472 [6:16:12<13:47:44,  3.19it/s]
 57%|█████▋    | 213211/371472 [6:16:13<13:32:43,  3.25it/s]
 57%|█████▋    | 213212/371472 [6:16:13<13:19:38,  3.30it/s]
 57%|█████▋    | 213213/371472 [6:16:13<13:18:23,  3.30it/s]
 57%|█████▋    | 213214/371472 [6:16:14<13:11:30,  3.33it/s]
 57%|█████▋    | 213215/371472 [6:16:14<14:46:11,  2.98it/s]
 57%|█████▋    | 213216/371472 [6:16:14<14:24:07,  3.05it/s]
 57%|█████▋    | 213217/371472 [6:16:15<14:32:19,  3.02it/s]
 57%|█████▋    | 213218/371472 [6:16:15<13:59:57,  3.14it/s]
 57%|█████▋    | 213219/371472 [6:16:15<13:46:05,  3.19it/s]
 57%|█████▋    | 213220/371472 [6:16:16<13:33:10,  3.24it/s]
                                                            
{'loss': 2.8119, 'learning_rate': 4.836184791742981e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213220/371472 [6:16:16<13:33:10,  3.24it/s]
 57%|█████▋    | 213221/371472 [6:16:16<13:16:12,  3.31it/s]
 57%|█████▋    | 213222/371472 [6:16:16<13:20:33,  3.29it/s]
 57%|█████▋    | 213223/371472 [6:16:16<13:17:41,  3.31it/s]
 57%|█████▋    | 213224/371472 [6:16:17<13:18:06,  3.30it/s]
 57%|█████▋    | 213225/371472 [6:16:17<14:00:34,  3.14it/s]
 57%|█████▋    | 213226/371472 [6:16:17<13:42:01,  3.21it/s]
 57%|█████▋    | 213227/371472 [6:16:18<14:10:36,  3.10it/s]
 57%|█████▋    | 213228/371472 [6:16:18<13:55:58,  3.15it/s]
 57%|█████▋    | 213229/371472 [6:16:18<13:43:34,  3.20it/s]
 57%|█████▋    | 213230/371472 [6:16:19<14:02:16,  3.13it/s]
 57%|█████▋    | 213231/371472 [6:16:19<13:31:10,  3.25it/s]
 57%|█████▋    | 213232/371472 [6:16:19<13:14:18,  3.32it/s]
 57%|█████▋    | 213233/371472 [6:16:20<13:50:11,  3.18it/s]
 57%|█████▋    | 213234/371472 [6:16:20<13:31:35,  3.25it/s]
 57%|█████▋    | 213235/371472 [6:16:20<13:36:59,  3.23it/s]
 57%|█████▋    | 213236/371472 [6:16:21<13:18:32,  3.30it/s]
 57%|█████▋    | 213237/371472 [6:16:21<13:46:43,  3.19it/s]
 57%|█████▋    | 213238/371472 [6:16:21<13:17:46,  3.31it/s]
 57%|█████▋    | 213239/371472 [6:16:21<13:09:43,  3.34it/s]
 57%|█████▋    | 213240/371472 [6:16:22<12:53:20,  3.41it/s]
                                                            
{'loss': 2.7964, 'learning_rate': 4.835699971988192e-07, 'epoch': 9.18}
+
 57%|█████▋    | 213240/371472 [6:16:22<12:53:20,  3.41it/s]
 57%|█████▋    | 213241/371472 [6:16:22<12:56:04,  3.40it/s]
 57%|█████▋    | 213242/371472 [6:16:22<13:32:53,  3.24it/s]
 57%|█████▋    | 213243/371472 [6:16:23<13:15:15,  3.32it/s]
 57%|█████▋    | 213244/371472 [6:16:23<13:07:14,  3.35it/s]
 57%|█████▋    | 213245/371472 [6:16:23<13:02:24,  3.37it/s]
 57%|█████▋    | 213246/371472 [6:16:24<12:55:30,  3.40it/s]
 57%|█████▋    | 213247/371472 [6:16:24<12:37:50,  3.48it/s]
 57%|█████▋    | 213248/371472 [6:16:24<12:45:31,  3.44it/s]
 57%|█████▋    | 213249/371472 [6:16:24<12:42:42,  3.46it/s]
 57%|█████▋    | 213250/371472 [6:16:25<12:39:46,  3.47it/s]
 57%|█████▋    | 213251/371472 [6:16:25<12:47:02,  3.44it/s]
 57%|█████▋    | 213252/371472 [6:16:25<12:36:50,  3.48it/s]
 57%|█████▋    | 213253/371472 [6:16:26<14:02:17,  3.13it/s]
 57%|█████▋    | 213254/371472 [6:16:26<13:29:04,  3.26it/s]
 57%|█████▋    | 213255/371472 [6:16:26<13:35:09,  3.23it/s]
 57%|█████▋    | 213256/371472 [6:16:27<13:16:46,  3.31it/s]
 57%|█████▋    | 213257/371472 [6:16:27<13:54:34,  3.16it/s]
 57%|█████▋    | 213258/371472 [6:16:27<13:31:00,  3.25it/s]
 57%|█████▋    | 213259/371472 [6:16:27<13:58:25,  3.15it/s]
 57%|█████▋    | 213260/371472 [6:16:28<14:26:07,  3.04it/s]
                                                            
{'loss': 2.6985, 'learning_rate': 4.835215152233403e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213260/371472 [6:16:28<14:26:07,  3.04it/s]
 57%|█████▋    | 213261/371472 [6:16:28<14:24:15,  3.05it/s]
 57%|█████▋    | 213262/371472 [6:16:28<13:43:58,  3.20it/s]
 57%|█████▋    | 213263/371472 [6:16:29<13:15:44,  3.31it/s]
 57%|█████▋    | 213264/371472 [6:16:29<13:29:51,  3.26it/s]
 57%|█████▋    | 213265/371472 [6:16:29<13:09:50,  3.34it/s]
 57%|█████▋    | 213266/371472 [6:16:30<12:56:00,  3.40it/s]
 57%|█████▋    | 213267/371472 [6:16:30<13:15:55,  3.31it/s]
 57%|█████▋    | 213268/371472 [6:16:30<13:29:43,  3.26it/s]
 57%|█████▋    | 213269/371472 [6:16:31<13:14:36,  3.32it/s]
 57%|█████▋    | 213270/371472 [6:16:31<13:35:52,  3.23it/s]
 57%|█████▋    | 213271/371472 [6:16:31<13:24:39,  3.28it/s]
 57%|█████▋    | 213272/371472 [6:16:31<13:10:26,  3.34it/s]
 57%|█████▋    | 213273/371472 [6:16:32<13:29:41,  3.26it/s]
 57%|█████▋    | 213274/371472 [6:16:32<13:21:07,  3.29it/s]
 57%|█████▋    | 213275/371472 [6:16:32<13:43:50,  3.20it/s]
 57%|█████▋    | 213276/371472 [6:16:33<13:29:32,  3.26it/s]
 57%|█████▋    | 213277/371472 [6:16:33<13:14:58,  3.32it/s]
 57%|█████▋    | 213278/371472 [6:16:33<13:17:04,  3.31it/s]
 57%|█████▋    | 213279/371472 [6:16:34<13:15:36,  3.31it/s]
 57%|█████▋    | 213280/371472 [6:16:34<13:17:17,  3.31it/s]
                                                            
{'loss': 2.7612, 'learning_rate': 4.834730332478613e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213280/371472 [6:16:34<13:17:17,  3.31it/s]
 57%|█████▋    | 213281/371472 [6:16:34<13:43:25,  3.20it/s]
 57%|█████▋    | 213282/371472 [6:16:34<13:06:37,  3.35it/s]
 57%|█████▋    | 213283/371472 [6:16:35<13:37:27,  3.23it/s]
 57%|█████▋    | 213284/371472 [6:16:35<13:06:51,  3.35it/s]
 57%|█████▋    | 213285/371472 [6:16:35<12:58:54,  3.38it/s]
 57%|█████▋    | 213286/371472 [6:16:36<12:49:43,  3.43it/s]
 57%|█████▋    | 213287/371472 [6:16:36<12:50:14,  3.42it/s]
 57%|█████▋    | 213288/371472 [6:16:36<13:24:02,  3.28it/s]
 57%|█████▋    | 213289/371472 [6:16:37<13:28:19,  3.26it/s]
 57%|█████▋    | 213290/371472 [6:16:37<13:07:35,  3.35it/s]
 57%|█████▋    | 213291/371472 [6:16:37<13:26:49,  3.27it/s]
 57%|█████▋    | 213292/371472 [6:16:38<14:21:17,  3.06it/s]
 57%|█████▋    | 213293/371472 [6:16:38<13:53:07,  3.16it/s]
 57%|█████▋    | 213294/371472 [6:16:38<14:25:48,  3.04it/s]
 57%|█████▋    | 213295/371472 [6:16:39<14:16:55,  3.08it/s]
 57%|█████▋    | 213296/371472 [6:16:39<13:47:05,  3.19it/s]
 57%|█████▋    | 213297/371472 [6:16:39<13:28:09,  3.26it/s]
 57%|█████▋    | 213298/371472 [6:16:39<13:11:40,  3.33it/s]
 57%|█████▋    | 213299/371472 [6:16:40<14:30:29,  3.03it/s]
 57%|█████▋    | 213300/371472 [6:16:40<13:53:22,  3.16it/s]
                                                            
{'loss': 2.9069, 'learning_rate': 4.834245512723825e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213300/371472 [6:16:40<13:53:22,  3.16it/s]
 57%|█████▋    | 213301/371472 [6:16:40<13:42:00,  3.21it/s]
 57%|█████▋    | 213302/371472 [6:16:41<13:09:46,  3.34it/s]
 57%|█████▋    | 213303/371472 [6:16:41<13:05:02,  3.36it/s]
 57%|█████▋    | 213304/371472 [6:16:41<13:17:23,  3.31it/s]
 57%|█████▋    | 213305/371472 [6:16:42<13:09:48,  3.34it/s]
 57%|█████▋    | 213306/371472 [6:16:42<13:05:33,  3.36it/s]
 57%|█████▋    | 213307/371472 [6:16:42<13:00:08,  3.38it/s]
 57%|█████▋    | 213308/371472 [6:16:42<12:47:42,  3.43it/s]
 57%|█████▋    | 213309/371472 [6:16:43<12:47:39,  3.43it/s]
 57%|█████▋    | 213310/371472 [6:16:43<12:45:43,  3.44it/s]
 57%|█████▋    | 213311/371472 [6:16:43<12:28:56,  3.52it/s]
 57%|█████▋    | 213312/371472 [6:16:44<12:41:12,  3.46it/s]
 57%|█████▋    | 213313/371472 [6:16:44<12:43:01,  3.45it/s]
 57%|█████▋    | 213314/371472 [6:16:44<12:47:44,  3.43it/s]
 57%|█████▋    | 213315/371472 [6:16:44<12:55:48,  3.40it/s]
 57%|█████▋    | 213316/371472 [6:16:45<12:44:43,  3.45it/s]
 57%|█████▋    | 213317/371472 [6:16:45<13:11:27,  3.33it/s]
 57%|█████▋    | 213318/371472 [6:16:45<13:11:50,  3.33it/s]
 57%|█████▋    | 213319/371472 [6:16:46<12:54:01,  3.41it/s]
 57%|█████▋    | 213320/371472 [6:16:46<12:43:10,  3.45it/s]
                                                            
{'loss': 2.9639, 'learning_rate': 4.833760692969036e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213320/371472 [6:16:46<12:43:10,  3.45it/s]
 57%|█████▋    | 213321/371472 [6:16:46<13:53:33,  3.16it/s]
 57%|█████▋    | 213322/371472 [6:16:47<13:27:04,  3.27it/s]
 57%|█████▋    | 213323/371472 [6:16:47<13:41:52,  3.21it/s]
 57%|█████▋    | 213324/371472 [6:16:47<13:11:39,  3.33it/s]
 57%|█████▋    | 213325/371472 [6:16:47<13:05:33,  3.36it/s]
 57%|█████▋    | 213326/371472 [6:16:48<13:37:01,  3.23it/s]
 57%|█████▋    | 213327/371472 [6:16:48<13:14:56,  3.32it/s]
 57%|█████▋    | 213328/371472 [6:16:48<12:53:29,  3.41it/s]
 57%|█████▋    | 213329/371472 [6:16:49<12:59:55,  3.38it/s]
 57%|█████▋    | 213330/371472 [6:16:49<13:18:42,  3.30it/s]
 57%|█████▋    | 213331/371472 [6:16:49<13:11:10,  3.33it/s]
 57%|█████▋    | 213332/371472 [6:16:50<12:49:27,  3.43it/s]
 57%|█████▋    | 213333/371472 [6:16:50<13:06:54,  3.35it/s]
 57%|█████▋    | 213334/371472 [6:16:50<13:03:29,  3.36it/s]
 57%|█████▋    | 213335/371472 [6:16:50<12:58:13,  3.39it/s]
 57%|█████▋    | 213336/371472 [6:16:51<12:58:41,  3.38it/s]
 57%|█████▋    | 213337/371472 [6:16:51<13:03:19,  3.36it/s]
 57%|█████▋    | 213338/371472 [6:16:51<13:10:51,  3.33it/s]
 57%|█████▋    | 213339/371472 [6:16:52<13:28:46,  3.26it/s]
 57%|█████▋    | 213340/371472 [6:16:52<13:21:42,  3.29it/s]
                                                            
{'loss': 2.6816, 'learning_rate': 4.833275873214248e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213340/371472 [6:16:52<13:21:42,  3.29it/s]
 57%|█████▋    | 213341/371472 [6:16:52<13:04:08,  3.36it/s]
 57%|█████▋    | 213342/371472 [6:16:53<13:12:47,  3.32it/s]
 57%|█████▋    | 213343/371472 [6:16:53<12:47:58,  3.43it/s]
 57%|█████▋    | 213344/371472 [6:16:53<13:22:04,  3.29it/s]
 57%|█████▋    | 213345/371472 [6:16:53<13:11:15,  3.33it/s]
 57%|█████▋    | 213346/371472 [6:16:54<13:17:44,  3.30it/s]
 57%|█████▋    | 213347/371472 [6:16:54<13:01:45,  3.37it/s]
 57%|█████▋    | 213348/371472 [6:16:54<13:04:40,  3.36it/s]
 57%|█████▋    | 213349/371472 [6:16:55<13:01:32,  3.37it/s]
 57%|█████▋    | 213350/371472 [6:16:55<12:53:04,  3.41it/s]
 57%|█████▋    | 213351/371472 [6:16:55<12:54:50,  3.40it/s]
 57%|█████▋    | 213352/371472 [6:16:56<12:41:31,  3.46it/s]
 57%|█████▋    | 213353/371472 [6:16:56<13:01:59,  3.37it/s]
 57%|█████▋    | 213354/371472 [6:16:56<12:57:08,  3.39it/s]
 57%|█████▋    | 213355/371472 [6:16:56<12:44:52,  3.45it/s]
 57%|█████▋    | 213356/371472 [6:16:57<13:13:41,  3.32it/s]
 57%|█████▋    | 213357/371472 [6:16:57<12:59:39,  3.38it/s]
 57%|█████▋    | 213358/371472 [6:16:57<12:58:43,  3.38it/s]
 57%|█████▋    | 213359/371472 [6:16:58<13:38:35,  3.22it/s]
 57%|█████▋    | 213360/371472 [6:16:58<13:19:06,  3.30it/s]
                                                            
{'loss': 2.9023, 'learning_rate': 4.832791053459458e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213360/371472 [6:16:58<13:19:06,  3.30it/s]
 57%|█████▋    | 213361/371472 [6:16:58<13:02:57,  3.37it/s]
 57%|█████▋    | 213362/371472 [6:16:59<12:55:19,  3.40it/s]
 57%|█████▋    | 213363/371472 [6:16:59<12:37:44,  3.48it/s]
 57%|█████▋    | 213364/371472 [6:16:59<12:43:22,  3.45it/s]
 57%|█████▋    | 213365/371472 [6:16:59<12:57:19,  3.39it/s]
 57%|█████▋    | 213366/371472 [6:17:00<12:38:44,  3.47it/s]
 57%|█████▋    | 213367/371472 [6:17:00<12:48:37,  3.43it/s]
 57%|█████▋    | 213368/371472 [6:17:00<12:55:54,  3.40it/s]
 57%|█████▋    | 213369/371472 [6:17:01<13:01:54,  3.37it/s]
 57%|█████▋    | 213370/371472 [6:17:01<12:57:24,  3.39it/s]
 57%|█████▋    | 213371/371472 [6:17:01<12:50:05,  3.42it/s]
 57%|█████▋    | 213372/371472 [6:17:01<12:37:28,  3.48it/s]
 57%|█████▋    | 213373/371472 [6:17:02<12:22:33,  3.55it/s]
 57%|█████▋    | 213374/371472 [6:17:02<12:44:23,  3.45it/s]
 57%|█████▋    | 213375/371472 [6:17:02<12:26:59,  3.53it/s]
 57%|█████▋    | 213376/371472 [6:17:03<13:26:06,  3.27it/s]
 57%|█████▋    | 213377/371472 [6:17:03<13:17:37,  3.30it/s]
 57%|█████▋    | 213378/371472 [6:17:03<13:38:14,  3.22it/s]
 57%|█████▋    | 213379/371472 [6:17:04<13:22:45,  3.28it/s]
 57%|█████▋    | 213380/371472 [6:17:04<13:15:35,  3.31it/s]
                                                            
{'loss': 2.8334, 'learning_rate': 4.832306233704669e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213380/371472 [6:17:04<13:15:35,  3.31it/s]
 57%|█████▋    | 213381/371472 [6:17:04<14:10:36,  3.10it/s]
 57%|█████▋    | 213382/371472 [6:17:05<15:08:29,  2.90it/s]
 57%|█████▋    | 213383/371472 [6:17:05<14:13:24,  3.09it/s]
 57%|█████▋    | 213384/371472 [6:17:05<13:58:31,  3.14it/s]
 57%|█████▋    | 213385/371472 [6:17:05<13:44:29,  3.20it/s]
 57%|█████▋    | 213386/371472 [6:17:06<13:14:35,  3.32it/s]
 57%|█████▋    | 213387/371472 [6:17:06<13:49:14,  3.18it/s]
 57%|█████▋    | 213388/371472 [6:17:06<13:13:49,  3.32it/s]
 57%|█████▋    | 213389/371472 [6:17:07<13:08:55,  3.34it/s]
 57%|█████▋    | 213390/371472 [6:17:07<12:54:22,  3.40it/s]
 57%|█████▋    | 213391/371472 [6:17:07<13:22:14,  3.28it/s]
 57%|█████▋    | 213392/371472 [6:17:08<13:26:22,  3.27it/s]
 57%|█████▋    | 213393/371472 [6:17:08<13:09:46,  3.34it/s]
 57%|█████▋    | 213394/371472 [6:17:08<13:09:01,  3.34it/s]
 57%|█████▋    | 213395/371472 [6:17:08<13:10:31,  3.33it/s]
 57%|█████▋    | 213396/371472 [6:17:09<12:47:57,  3.43it/s]
 57%|█████▋    | 213397/371472 [6:17:09<13:14:35,  3.32it/s]
 57%|█████▋    | 213398/371472 [6:17:09<13:07:31,  3.35it/s]
 57%|█████▋    | 213399/371472 [6:17:10<12:54:37,  3.40it/s]
 57%|█████▋    | 213400/371472 [6:17:10<13:40:31,  3.21it/s]
                                                            
{'loss': 2.7348, 'learning_rate': 4.83182141394988e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213400/371472 [6:17:10<13:40:31,  3.21it/s]
 57%|█████▋    | 213401/371472 [6:17:10<13:23:40,  3.28it/s]
 57%|█████▋    | 213402/371472 [6:17:11<13:03:13,  3.36it/s]
 57%|█████▋    | 213403/371472 [6:17:11<12:53:15,  3.41it/s]
 57%|█████▋    | 213404/371472 [6:17:11<13:22:37,  3.28it/s]
 57%|█████▋    | 213405/371472 [6:17:11<13:06:45,  3.35it/s]
 57%|█████▋    | 213406/371472 [6:17:12<13:45:38,  3.19it/s]
 57%|█████▋    | 213407/371472 [6:17:12<13:32:00,  3.24it/s]
 57%|███��█▋    | 213408/371472 [6:17:12<13:18:23,  3.30it/s]
 57%|█████▋    | 213409/371472 [6:17:13<14:13:53,  3.09it/s]
 57%|█████▋    | 213410/371472 [6:17:13<13:40:43,  3.21it/s]
 57%|█████▋    | 213411/371472 [6:17:13<13:20:32,  3.29it/s]
 57%|█████▋    | 213412/371472 [6:17:14<13:30:21,  3.25it/s]
 57%|█████▋    | 213413/371472 [6:17:14<13:43:45,  3.20it/s]
 57%|█████▋    | 213414/371472 [6:17:14<13:28:26,  3.26it/s]
 57%|█████▋    | 213415/371472 [6:17:15<13:11:53,  3.33it/s]
 57%|█████▋    | 213416/371472 [6:17:15<14:54:58,  2.94it/s]
 57%|█████▋    | 213417/371472 [6:17:15<14:16:14,  3.08it/s]
 57%|█████▋    | 213418/371472 [6:17:16<13:49:54,  3.17it/s]
 57%|█████▋    | 213419/371472 [6:17:16<13:58:35,  3.14it/s]
 57%|█████▋    | 213420/371472 [6:17:16<13:32:51,  3.24it/s]
                                                            
{'loss': 2.8176, 'learning_rate': 4.831336594195092e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213420/371472 [6:17:16<13:32:51,  3.24it/s]
 57%|█████▋    | 213421/371472 [6:17:16<13:10:12,  3.33it/s]
 57%|█████▋    | 213422/371472 [6:17:17<12:51:45,  3.41it/s]
 57%|█████▋    | 213423/371472 [6:17:17<13:05:43,  3.35it/s]
 57%|█████▋    | 213424/371472 [6:17:17<13:08:31,  3.34it/s]
 57%|█████▋    | 213425/371472 [6:17:18<13:12:07,  3.33it/s]
 57%|█████▋    | 213426/371472 [6:17:18<13:08:31,  3.34it/s]
 57%|█████▋    | 213427/371472 [6:17:18<13:20:56,  3.29it/s]
 57%|█████▋    | 213428/371472 [6:17:19<13:22:24,  3.28it/s]
 57%|█████▋    | 213429/371472 [6:17:19<14:01:46,  3.13it/s]
 57%|█████▋    | 213430/371472 [6:17:19<13:36:28,  3.23it/s]
 57%|█████▋    | 213431/371472 [6:17:20<13:53:01,  3.16it/s]
 57%|█████▋    | 213432/371472 [6:17:20<13:48:47,  3.18it/s]
 57%|█████▋    | 213433/371472 [6:17:20<14:26:35,  3.04it/s]
 57%|█████▋    | 213434/371472 [6:17:21<13:54:03,  3.16it/s]
 57%|█████▋    | 213435/371472 [6:17:21<13:30:58,  3.25it/s]
 57%|█████▋    | 213436/371472 [6:17:21<13:09:45,  3.34it/s]
 57%|█████▋    | 213437/371472 [6:17:21<13:42:35,  3.20it/s]
 57%|█████▋    | 213438/371472 [6:17:22<13:43:37,  3.20it/s]
 57%|█████▋    | 213439/371472 [6:17:22<13:27:10,  3.26it/s]
 57%|█████▋    | 213440/371472 [6:17:22<13:16:39,  3.31it/s]
                                                            
{'loss': 2.7926, 'learning_rate': 4.830851774440302e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213440/371472 [6:17:22<13:16:39,  3.31it/s]
 57%|█████▋    | 213441/371472 [6:17:23<13:00:58,  3.37it/s]
 57%|█████▋    | 213442/371472 [6:17:23<13:08:31,  3.34it/s]
 57%|█████▋    | 213443/371472 [6:17:23<13:23:07,  3.28it/s]
 57%|█████▋    | 213444/371472 [6:17:24<13:10:15,  3.33it/s]
 57%|█████▋    | 213445/371472 [6:17:24<13:52:33,  3.16it/s]
 57%|█████▋    | 213446/371472 [6:17:24<13:22:51,  3.28it/s]
 57%|█████▋    | 213447/371472 [6:17:24<13:11:08,  3.33it/s]
 57%|█████▋    | 213448/371472 [6:17:25<13:25:17,  3.27it/s]
 57%|█████▋    | 213449/371472 [6:17:25<13:19:07,  3.30it/s]
 57%|█████▋    | 213450/371472 [6:17:25<13:04:38,  3.36it/s]
 57%|█████▋    | 213451/371472 [6:17:26<13:07:52,  3.34it/s]
 57%|█████▋    | 213452/371472 [6:17:26<13:05:22,  3.35it/s]
 57%|█████▋    | 213453/371472 [6:17:26<14:16:06,  3.08it/s]
 57%|█████▋    | 213454/371472 [6:17:27<13:36:30,  3.23it/s]
 57%|█████▋    | 213455/371472 [6:17:27<13:21:52,  3.28it/s]
 57%|█████▋    | 213456/371472 [6:17:27<14:20:12,  3.06it/s]
 57%|█████▋    | 213457/371472 [6:17:28<14:11:21,  3.09it/s]
 57%|█████▋    | 213458/371472 [6:17:28<13:45:43,  3.19it/s]
 57%|█████▋    | 213459/371472 [6:17:28<13:24:59,  3.27it/s]
 57%|█████▋    | 213460/371472 [6:17:28<13:11:22,  3.33it/s]
                                                            
{'loss': 2.7795, 'learning_rate': 4.830366954685514e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213460/371472 [6:17:28<13:11:22,  3.33it/s]
 57%|█████▋    | 213461/371472 [6:17:29<13:06:23,  3.35it/s]
 57%|█████▋    | 213462/371472 [6:17:29<13:19:17,  3.29it/s]
 57%|█████▋    | 213463/371472 [6:17:29<13:38:36,  3.22it/s]
 57%|█████▋    | 213464/371472 [6:17:30<13:26:57,  3.26it/s]
 57%|█████▋    | 213465/371472 [6:17:30<14:06:36,  3.11it/s]
 57%|█████▋    | 213466/371472 [6:17:30<13:54:46,  3.15it/s]
 57%|█████▋    | 213467/371472 [6:17:31<14:03:17,  3.12it/s]
 57%|█████▋    | 213468/371472 [6:17:31<13:36:36,  3.22it/s]
 57%|█████▋    | 213469/371472 [6:17:31<13:14:45,  3.31it/s]
 57%|█████▋    | 213470/371472 [6:17:32<13:33:18,  3.24it/s]
 57%|█████▋    | 213471/371472 [6:17:32<15:07:19,  2.90it/s]
 57%|█████▋    | 213472/371472 [6:17:32<14:27:58,  3.03it/s]
 57%|█████▋    | 213473/371472 [6:17:33<14:09:26,  3.10it/s]
 57%|█████▋    | 213474/371472 [6:17:33<13:25:48,  3.27it/s]
 57%|█████▋    | 213475/371472 [6:17:33<13:14:13,  3.32it/s]
 57%|█████▋    | 213476/371472 [6:17:33<13:03:38,  3.36it/s]
 57%|█████▋    | 213477/371472 [6:17:34<12:44:56,  3.44it/s]
 57%|█████▋    | 213478/371472 [6:17:34<13:31:49,  3.24it/s]
 57%|█████▋    | 213479/371472 [6:17:34<13:14:00,  3.32it/s]
 57%|█████▋    | 213480/371472 [6:17:35<13:11:05,  3.33it/s]
                                                            
{'loss': 2.9301, 'learning_rate': 4.829882134930725e-07, 'epoch': 9.19}
+
 57%|█████▋    | 213480/371472 [6:17:35<13:11:05,  3.33it/s]
 57%|█████▋    | 213481/371472 [6:17:35<13:09:52,  3.33it/s]
 57%|█████▋    | 213482/371472 [6:17:35<13:30:15,  3.25it/s]
 57%|█████▋    | 213483/371472 [6:17:36<14:01:37,  3.13it/s]
 57%|█████▋    | 213484/371472 [6:17:36<13:59:48,  3.14it/s]
 57%|█████▋    | 213485/371472 [6:17:36<13:50:58,  3.17it/s]
 57%|█████▋    | 213486/371472 [6:17:37<14:27:40,  3.03it/s]
 57%|█████▋    | 213487/371472 [6:17:37<14:00:13,  3.13it/s]
 57%|█████▋    | 213488/371472 [6:17:37<13:58:53,  3.14it/s]
 57%|█████▋    | 213489/371472 [6:17:38<13:45:10,  3.19it/s]
 57%|█████▋    | 213490/371472 [6:17:38<13:38:38,  3.22it/s]
 57%|█████▋    | 213491/371472 [6:17:38<14:13:14,  3.09it/s]
 57%|█████▋    | 213492/371472 [6:17:38<13:36:27,  3.22it/s]
 57%|█████▋    | 213493/371472 [6:17:39<15:13:41,  2.88it/s]
 57%|█████▋    | 213494/371472 [6:17:39<14:24:30,  3.05it/s]
 57%|█████▋    | 213495/371472 [6:17:39<14:12:30,  3.09it/s]
 57%|█████▋    | 213496/371472 [6:17:40<13:30:29,  3.25it/s]
 57%|█████▋    | 213497/371472 [6:17:40<13:45:46,  3.19it/s]
 57%|█████▋    | 213498/371472 [6:17:40<14:26:05,  3.04it/s]
 57%|█████▋    | 213499/371472 [6:17:41<14:02:01,  3.13it/s]
 57%|█████▋    | 213500/371472 [6:17:41<14:40:10,  2.99it/s]
                                                            
{'loss': 2.742, 'learning_rate': 4.829397315175936e-07, 'epoch': 9.2}
+
 57%|█████▋    | 213500/371472 [6:17:41<14:40:10,  2.99it/s]
 57%|█████▋    | 213501/371472 [6:17:41<14:45:49,  2.97it/s]
 57%|█████▋    | 213502/371472 [6:17:42<14:19:29,  3.06it/s]
 57%|█████▋    | 213503/371472 [6:17:42<14:08:14,  3.10it/s]
 57%|█████▋    | 213504/371472 [6:17:42<13:31:51,  3.24it/s]
 57%|█████▋    | 213505/371472 [6:17:43<14:48:28,  2.96it/s]
 57%|█████▋    | 213506/371472 [6:17:43<14:14:53,  3.08it/s]
 57%|█████▋    | 213507/371472 [6:17:43<14:35:07,  3.01it/s]
 57%|█████▋    | 213508/371472 [6:17:44<13:54:58,  3.15it/s]
 57%|█████▋    | 213509/371472 [6:17:44<13:52:47,  3.16it/s]
 57%|█████▋    | 213510/371472 [6:17:44<13:36:46,  3.22it/s]
 57%|█████▋    | 213511/371472 [6:17:45<13:33:41,  3.24it/s]
 57%|█████▋    | 213512/371472 [6:17:45<13:15:50,  3.31it/s]
 57%|█████▋    | 213513/371472 [6:17:45<14:02:34,  3.12it/s]
 57%|█████▋    | 213514/371472 [6:17:46<13:33:19,  3.24it/s]
 57%|█████▋    | 213515/371472 [6:17:46<13:15:48,  3.31it/s]
 57%|█████▋    | 213516/371472 [6:17:46<13:09:23,  3.33it/s]
 57%|█████▋    | 213517/371472 [6:17:46<12:59:43,  3.38it/s]
 57%|█████▋    | 213518/371472 [6:17:47<13:16:48,  3.30it/s]
 57%|█████▋    | 213519/371472 [6:17:47<13:06:24,  3.35it/s]
 57%|█████▋    | 213520/371472 [6:17:47<13:07:09,  3.34it/s]
                                                            
{'loss': 2.8339, 'learning_rate': 4.828912495421146e-07, 'epoch': 9.2}
+
 57%|█████▋    | 213520/371472 [6:17:47<13:07:09,  3.34it/s]
 57%|█████▋    | 213521/371472 [6:17:48<13:20:52,  3.29it/s]
 57%|█████▋    | 213522/371472 [6:17:48<14:19:17,  3.06it/s]
 57%|█████▋    | 213523/371472 [6:17:48<13:53:52,  3.16it/s]
 57%|█████▋    | 213524/371472 [6:17:49<13:33:45,  3.23it/s]
 57%|█████▋    | 213525/371472 [6:17:49<13:23:58,  3.27it/s]
 57%|█████▋    | 213526/371472 [6:17:49<13:29:51,  3.25it/s]
 57%|█████▋    | 213527/371472 [6:17:50<13:35:36,  3.23it/s]
 57%|█████▋    | 213528/371472 [6:17:50<13:20:18,  3.29it/s]
 57%|█████▋    | 213529/371472 [6:17:50<13:38:40,  3.22it/s]
 57%|█████▋    | 213530/371472 [6:17:50<13:29:36,  3.25it/s]
 57%|█████▋    | 213531/371472 [6:17:51<13:07:58,  3.34it/s]
 57%|█████▋    | 213532/371472 [6:17:51<13:56:58,  3.15it/s]
 57%|█████▋    | 213533/371472 [6:17:51<14:18:12,  3.07it/s]
 57%|█████▋    | 213534/371472 [6:17:52<13:31:39,  3.24it/s]
 57%|█████▋    | 213535/371472 [6:17:52<13:08:00,  3.34it/s]
 57%|█████▋    | 213536/371472 [6:17:52<13:46:30,  3.18it/s]
 57%|█████▋    | 213537/371472 [6:17:53<13:27:29,  3.26it/s]
 57%|█████▋    | 213538/371472 [6:17:53<13:28:52,  3.25it/s]
 57%|█████▋    | 213539/371472 [6:17:53<13:15:21,  3.31it/s]
 57%|█████▋    | 213540/371472 [6:17:54<13:14:00,  3.32it/s]
                                                            
{'loss': 2.756, 'learning_rate': 4.828427675666357e-07, 'epoch': 9.2}
+
 57%|█████▋    | 213540/371472 [6:17:54<13:14:00,  3.32it/s]
 57%|█████▋    | 213541/371472 [6:17:54<13:00:32,  3.37it/s]
 57%|█████▋    | 213542/371472 [6:17:54<13:48:44,  3.18it/s]
 57%|█████▋    | 213543/371472 [6:17:54<13:41:33,  3.20it/s]
 57%|█████▋    | 213544/371472 [6:17:55<13:44:13,  3.19it/s]
 57%|█████▋    | 213545/371472 [6:17:55<13:19:16,  3.29it/s]
 57%|█████▋    | 213546/371472 [6:17:55<14:20:36,  3.06it/s]
 57%|█████▋    | 213547/371472 [6:17:56<13:32:01,  3.24it/s]
 57%|█████▋    | 213548/371472 [6:17:56<14:17:42,  3.07it/s]
 57%|█████▋    | 213549/371472 [6:17:56<15:01:17,  2.92it/s]
 57%|█████▋    | 213550/371472 [6:17:57<14:27:30,  3.03it/s]
 57%|█████▋    | 213551/371472 [6:17:57<13:40:58,  3.21it/s]
 57%|█████▋    | 213552/371472 [6:17:57<13:27:31,  3.26it/s]
 57%|█████▋    | 213553/371472 [6:17:58<13:34:01,  3.23it/s]
 57%|█████▋    | 213554/371472 [6:17:58<13:08:49,  3.34it/s]
 57%|█████▋    | 213555/371472 [6:17:58<13:02:46,  3.36it/s]
 57%|█████▋    | 213556/371472 [6:17:58<12:37:51,  3.47it/s]
 57%|█████▋    | 213557/371472 [6:17:59<12:30:20,  3.51it/s]
 57%|█████▋    | 213558/371472 [6:17:59<12:35:16,  3.48it/s]
 57%|█████▋    | 213559/371472 [6:17:59<12:46:53,  3.43it/s]
 57%|█████▋    | 213560/371472 [6:18:00<12:16:49,  3.57it/s]
                                                            
{'loss': 2.6859, 'learning_rate': 4.827942855911569e-07, 'epoch': 9.2}
+
 57%|█████▋    | 213560/371472 [6:18:00<12:16:49,  3.57it/s]
 57%|█████▋    | 213561/371472 [6:18:00<12:27:08,  3.52it/s]
 57%|█████▋    | 213562/371472 [6:18:00<12:34:26,  3.49it/s]
 57%|█████▋    | 213563/371472 [6:18:00<12:38:54,  3.47it/s]
 57%|█████▋    | 213564/371472 [6:18:01<12:43:23,  3.45it/s]
 57%|█████▋    | 213565/371472 [6:18:01<12:27:44,  3.52it/s]
 57%|█████▋    | 213566/371472 [6:18:01<13:21:06,  3.29it/s]
 57%|█████▋    | 213567/371472 [6:18:02<14:04:38,  3.12it/s]
 57%|█████▋    | 213568/371472 [6:18:02<13:20:51,  3.29it/s]
 57%|█████▋    | 213569/371472 [6:18:02<14:04:01,  3.12it/s]
 57%|█████▋    | 213570/371472 [6:18:03<13:33:35,  3.23it/s]
 57%|█████▋    | 213571/371472 [6:18:03<13:24:15,  3.27it/s]
 57%|█████▋    | 213572/371472 [6:18:03<13:48:41,  3.18it/s]
 57%|█████▋    | 213573/371472 [6:18:04<13:37:49,  3.22it/s]
 57%|█████▋    | 213574/371472 [6:18:04<13:32:29,  3.24it/s]
 57%|█████▋    | 213575/371472 [6:18:04<13:56:20,  3.15it/s]
 57%|█████▋    | 213576/371472 [6:18:05<14:36:58,  3.00it/s]
 57%|█████▋    | 213577/371472 [6:18:05<13:54:43,  3.15it/s]
 57%|█████▋    | 213578/371472 [6:18:05<13:44:00,  3.19it/s]
 57%|█████▋    | 213579/371472 [6:18:05<13:48:08,  3.18it/s]
 57%|█████▋    | 213580/371472 [6:18:06<13:32:21,  3.24it/s]
                                                            
{'loss': 2.6961, 'learning_rate': 4.827458036156779e-07, 'epoch': 9.2}
+
 57%|█████▋    | 213580/371472 [6:18:06<13:32:21,  3.24it/s]
 57%|█████▋    | 213581/371472 [6:18:06<13:24:54,  3.27it/s]
 57%|█████▋    | 213582/371472 [6:18:06<13:34:01,  3.23it/s]
 57%|█████▋    | 213583/371472 [6:18:07<14:15:52,  3.07it/s]
 57%|█████▋    | 213584/371472 [6:18:07<13:47:09,  3.18it/s]
 57%|█████▋    | 213585/371472 [6:18:07<13:40:38,  3.21it/s]
 57%|█████▋    | 213586/371472 [6:18:08<13:34:45,  3.23it/s]
 57%|█████▋    | 213587/371472 [6:18:08<13:38:15,  3.22it/s]
 57%|█████▋    | 213588/371472 [6:18:08<14:13:49,  3.08it/s]
 57%|█████▋    | 213589/371472 [6:18:09<13:55:33,  3.15it/s]
 57%|█████▋    | 213590/371472 [6:18:09<13:55:21,  3.15it/s]
 57%|█████▋    | 213591/371472 [6:18:09<13:53:33,  3.16it/s]
 57%|█████▋    | 213592/371472 [6:18:10<14:27:13,  3.03it/s]
 57%|���████▋    | 213593/371472 [6:18:10<14:12:56,  3.08it/s]
 57%|█████▋    | 213594/371472 [6:18:10<13:59:21,  3.13it/s]
 57%|█████▋    | 213595/371472 [6:18:11<13:48:02,  3.18it/s]
 57%|█████▋    | 213596/371472 [6:18:11<13:37:37,  3.22it/s]
 58%|█████▊    | 213597/371472 [6:18:11<13:33:51,  3.23it/s]
 58%|█████▊    | 213598/371472 [6:18:11<13:56:30,  3.15it/s]
 58%|█████▊    | 213599/371472 [6:18:12<14:53:10,  2.95it/s]
 58%|█████▊    | 213600/371472 [6:18:12<15:25:22,  2.84it/s]
                                                            
{'loss': 2.655, 'learning_rate': 4.826973216401991e-07, 'epoch': 9.2}
+
 58%|█████▊    | 213600/371472 [6:18:12<15:25:22,  2.84it/s]
 58%|█████▊    | 213601/371472 [6:18:13<15:26:32,  2.84it/s]
 58%|█████▊    | 213602/371472 [6:18:13<14:29:42,  3.03it/s]
 58%|█████▊    | 213603/371472 [6:18:13<14:05:06,  3.11it/s]
 58%|█████▊    | 213604/371472 [6:18:13<13:36:29,  3.22it/s]
 58%|█████▊    | 213605/371472 [6:18:14<13:19:04,  3.29it/s]
 58%|█████▊    | 213606/371472 [6:18:14<13:20:52,  3.29it/s]
 58%|█████▊    | 213607/371472 [6:18:14<12:52:45,  3.40it/s]
 58%|█████▊    | 213608/371472 [6:18:15<12:56:18,  3.39it/s]
 58%|█████▊    | 213609/371472 [6:18:15<12:50:34,  3.41it/s]
 58%|█████▊    | 213610/371472 [6:18:15<13:03:31,  3.36it/s]
 58%|█████▊    | 213611/371472 [6:18:16<13:35:07,  3.23it/s]
 58%|█████▊    | 213612/371472 [6:18:16<13:25:20,  3.27it/s]
 58%|█████▊    | 213613/371472 [6:18:16<13:15:50,  3.31it/s]
 58%|█████▊    | 213614/371472 [6:18:16<13:00:14,  3.37it/s]
 58%|█████▊    | 213615/371472 [6:18:17<13:05:35,  3.35it/s]
 58%|█████▊    | 213616/371472 [6:18:17<13:06:50,  3.34it/s]
 58%|█████▊    | 213617/371472 [6:18:17<12:58:28,  3.38it/s]
 58%|█████▊    | 213618/371472 [6:18:18<12:51:15,  3.41it/s]
 58%|█████▊    | 213619/371472 [6:18:18<13:09:30,  3.33it/s]
 58%|█████▊    | 213620/371472 [6:18:18<13:12:48,  3.32it/s]
                                                            
{'loss': 2.773, 'learning_rate': 4.826488396647202e-07, 'epoch': 9.2}
+
 58%|█████▊    | 213620/371472 [6:18:18<13:12:48,  3.32it/s]
 58%|█████▊    | 213621/371472 [6:18:19<13:21:05,  3.28it/s]
 58%|█████▊    | 213622/371472 [6:18:19<13:04:01,  3.36it/s]
 58%|█████▊    | 213623/371472 [6:18:19<13:01:06,  3.37it/s]
 58%|█████▊    | 213624/371472 [6:18:19<12:59:16,  3.38it/s]
 58%|█████▊    | 213625/371472 [6:18:20<13:12:37,  3.32it/s]
 58%|█████▊    | 213626/371472 [6:18:20<13:44:06,  3.19it/s]
 58%|█████▊    | 213627/371472 [6:18:20<13:32:50,  3.24it/s]
 58%|█████▊    | 213628/371472 [6:18:21<13:03:10,  3.36it/s]
 58%|█████▊    | 213629/371472 [6:18:21<12:50:11,  3.42it/s]
 58%|█████▊    | 213630/371472 [6:18:21<12:40:49,  3.46it/s]
 58%|█████▊    | 213631/371472 [6:18:21<12:27:35,  3.52it/s]
 58%|█████▊    | 213632/371472 [6:18:22<12:47:42,  3.43it/s]
 58%|█████▊    | 213633/371472 [6:18:22<12:55:23,  3.39it/s]
 58%|█████▊    | 213634/371472 [6:18:22<13:20:37,  3.29it/s]
 58%|█████▊    | 213635/371472 [6:18:23<13:22:52,  3.28it/s]
 58%|█████▊    | 213636/371472 [6:18:23<13:04:39,  3.35it/s]
 58%|█████▊    | 213637/371472 [6:18:23<12:59:20,  3.38it/s]
 58%|█████▊    | 213638/371472 [6:18:24<13:57:12,  3.14it/s]
 58%|█████▊    | 213639/371472 [6:18:24<13:37:50,  3.22it/s]
 58%|█████▊    | 213640/371472 [6:18:24<13:34:28,  3.23it/s]
                                                            
{'loss': 2.7564, 'learning_rate': 4.826003576892413e-07, 'epoch': 9.2}
+
 58%|█████▊    | 213640/371472 [6:18:24<13:34:28,  3.23it/s]
 58%|█████▊    | 213641/371472 [6:18:25<13:16:44,  3.30it/s]
 58%|█████▊    | 213642/371472 [6:18:25<13:32:05,  3.24it/s]
 58%|█████▊    | 213643/371472 [6:18:25<13:10:03,  3.33it/s]
 58%|█████▊    | 213644/371472 [6:18:26<13:52:50,  3.16it/s]
 58%|█████▊    | 213645/371472 [6:18:26<13:13:09,  3.32it/s]
 58%|█████▊    | 213646/371472 [6:18:26<13:24:53,  3.27it/s]
 58%|█████▊    | 213647/371472 [6:18:26<13:12:50,  3.32it/s]
 58%|█████▊    | 213648/371472 [6:18:27<12:53:12,  3.40it/s]
 58%|█████▊    | 213649/371472 [6:18:27<13:08:47,  3.33it/s]
 58%|█████▊    | 213650/371472 [6:18:27<12:59:44,  3.37it/s]
 58%|█████▊    | 213651/371472 [6:18:28<13:38:27,  3.21it/s]
 58%|█████▊    | 213652/371472 [6:18:28<13:17:47,  3.30it/s]
 58%|█████▊    | 213653/371472 [6:18:28<14:06:26,  3.11it/s]
 58%|█████▊    | 213654/371472 [6:18:29<14:10:07,  3.09it/s]
 58%|█████▊    | 213655/371472 [6:18:29<13:38:22,  3.21it/s]
 58%|█████▊    | 213656/371472 [6:18:29<13:09:46,  3.33it/s]
 58%|█████▊    | 213657/371472 [6:18:30<14:18:03,  3.07it/s]
 58%|█████▊    | 213658/371472 [6:18:30<13:48:34,  3.17it/s]
 58%|█████▊    | 213659/371472 [6:18:30<14:09:33,  3.10it/s]
 58%|█████▊    | 213660/371472 [6:18:30<13:36:58,  3.22it/s]
                                                            
{'loss': 2.7459, 'learning_rate': 4.825518757137623e-07, 'epoch': 9.2}
+
 58%|█████▊    | 213660/371472 [6:18:30<13:36:58,  3.22it/s]
 58%|█████▊    | 213661/371472 [6:18:31<14:08:59,  3.10it/s]
 58%|█████▊    | 213662/371472 [6:18:31<13:37:10,  3.22it/s]
 58%|█████▊    | 213663/371472 [6:18:31<13:28:41,  3.25it/s]
 58%|█████▊    | 213664/371472 [6:18:32<13:15:56,  3.30it/s]
 58%|█████▊    | 213665/371472 [6:18:32<13:39:48,  3.21it/s]
 58%|█████▊    | 213666/371472 [6:18:32<13:21:26,  3.28it/s]
 58%|█████▊    | 213667/371472 [6:18:33<13:15:34,  3.31it/s]
 58%|█████▊    | 213668/371472 [6:18:33<13:17:38,  3.30it/s]
 58%|█████▊    | 213669/371472 [6:18:33<12:54:08,  3.40it/s]
 58%|█████▊    | 213670/371472 [6:18:33<13:07:12,  3.34it/s]
 58%|█████▊    | 213671/371472 [6:18:34<13:25:17,  3.27it/s]
 58%|█████▊    | 213672/371472 [6:18:34<13:23:34,  3.27it/s]
 58%|█████▊    | 213673/371472 [6:18:34<13:18:58,  3.29it/s]
 58%|█████▊    | 213674/371472 [6:18:35<13:09:42,  3.33it/s]
 58%|█████▊    | 213675/371472 [6:18:35<14:00:45,  3.13it/s]
 58%|█████▊    | 213676/371472 [6:18:35<13:36:44,  3.22it/s]
 58%|█████▊    | 213677/371472 [6:18:36<13:49:10,  3.17it/s]
 58%|█████▊    | 213678/371472 [6:18:36<13:29:36,  3.25it/s]
 58%|█████▊    | 213679/371472 [6:18:36<13:30:08,  3.25it/s]
 58%|█████▊    | 213680/371472 [6:18:37<13:10:52,  3.33it/s]
                                                            
{'loss': 2.6344, 'learning_rate': 4.825033937382835e-07, 'epoch': 9.2}
+
 58%|█████▊    | 213680/371472 [6:18:37<13:10:52,  3.33it/s]
 58%|█████▊    | 213681/371472 [6:18:37<13:35:50,  3.22it/s]
 58%|█████▊    | 213682/371472 [6:18:37<13:14:36,  3.31it/s]
 58%|█████▊    | 213683/371472 [6:18:38<14:04:58,  3.11it/s]
 58%|█████▊    | 213684/371472 [6:18:38<14:23:54,  3.04it/s]
 58%|█████▊    | 213685/371472 [6:18:38<13:39:39,  3.21it/s]
 58%|█████▊    | 213686/371472 [6:18:38<13:34:41,  3.23it/s]
 58%|█████▊    | 213687/371472 [6:18:39<14:04:45,  3.11it/s]
 58%|█████▊    | 213688/371472 [6:18:39<13:45:17,  3.19it/s]
 58%|█████▊    | 213689/371472 [6:18:39<13:27:25,  3.26it/s]
 58%|█████▊    | 213690/371472 [6:18:40<13:20:55,  3.28it/s]
 58%|█████▊    | 213691/371472 [6:18:40<13:40:29,  3.21it/s]
 58%|█████▊    | 213692/371472 [6:18:40<13:06:47,  3.34it/s]
 58%|█████▊    | 213693/371472 [6:18:41<13:48:46,  3.17it/s]
 58%|█████▊    | 213694/371472 [6:18:41<13:19:18,  3.29it/s]
 58%|█████▊    | 213695/371472 [6:18:41<13:28:22,  3.25it/s]
 58%|█████▊    | 213696/371472 [6:18:42<13:07:51,  3.34it/s]
 58%|█████▊    | 213697/371472 [6:18:42<13:08:15,  3.34it/s]
 58%|█████▊    | 213698/371472 [6:18:42<13:19:31,  3.29it/s]
 58%|█████▊    | 213699/371472 [6:18:42<13:15:18,  3.31it/s]
 58%|█████▊    | 213700/371472 [6:18:43<13:16:30,  3.30it/s]
                                                            
{'loss': 2.7902, 'learning_rate': 4.824549117628046e-07, 'epoch': 9.2}
+
 58%|█████▊    | 213700/371472 [6:18:43<13:16:30,  3.30it/s]
 58%|█████▊    | 213701/371472 [6:18:43<13:32:24,  3.24it/s]
 58%|█████▊    | 213702/371472 [6:18:43<13:39:59,  3.21it/s]
 58%|█████▊    | 213703/371472 [6:18:44<13:36:39,  3.22it/s]
 58%|█████▊    | 213704/371472 [6:18:44<13:07:02,  3.34it/s]
 58%|█████▊    | 213705/371472 [6:18:44<13:24:23,  3.27it/s]
 58%|█████▊    | 213706/371472 [6:18:45<13:17:31,  3.30it/s]
 58%|█████▊    | 213707/371472 [6:18:45<13:20:16,  3.29it/s]
 58%|█████▊    | 213708/371472 [6:18:45<13:06:47,  3.34it/s]
 58%|█████▊    | 213709/371472 [6:18:45<12:46:45,  3.43it/s]
 58%|█████▊    | 213710/371472 [6:18:46<12:40:59,  3.46it/s]
 58%|█████▊    | 213711/371472 [6:18:46<13:00:38,  3.37it/s]
 58%|█████▊    | 213712/371472 [6:18:46<12:48:06,  3.42it/s]
 58%|█████▊    | 213713/371472 [6:18:47<12:36:49,  3.47it/s]
 58%|█████▊    | 213714/371472 [6:18:47<12:41:53,  3.45it/s]
 58%|█████▊    | 213715/371472 [6:18:47<12:46:01,  3.43it/s]
 58%|█████▊    | 213716/371472 [6:18:48<13:12:37,  3.32it/s]
 58%|█████▊    | 213717/371472 [6:18:48<13:27:16,  3.26it/s]
 58%|█████▊    | 213718/371472 [6:18:48<13:11:07,  3.32it/s]
 58%|█████▊    | 213719/371472 [6:18:48<12:47:17,  3.43it/s]
 58%|█████▊    | 213720/371472 [6:18:49<13:18:59,  3.29it/s]
                                                            
{'loss': 2.8005, 'learning_rate': 4.824064297873258e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213720/371472 [6:18:49<13:18:59,  3.29it/s]
 58%|█████▊    | 213721/371472 [6:18:49<13:12:48,  3.32it/s]
 58%|█████▊    | 213722/371472 [6:18:49<13:01:01,  3.37it/s]
 58%|█████▊    | 213723/371472 [6:18:50<13:10:42,  3.33it/s]
 58%|█████▊    | 213724/371472 [6:18:50<14:00:04,  3.13it/s]
 58%|█████▊    | 213725/371472 [6:18:50<13:33:09,  3.23it/s]
 58%|█████▊    | 213726/371472 [6:18:51<13:29:26,  3.25it/s]
 58%|█████▊    | 213727/371472 [6:18:51<13:07:22,  3.34it/s]
 58%|█████▊    | 213728/371472 [6:18:51<13:16:30,  3.30it/s]
 58%|█████▊    | 213729/371472 [6:18:51<12:58:53,  3.38it/s]
 58%|█████▊    | 213730/371472 [6:18:52<13:13:32,  3.31it/s]
 58%|█████▊    | 213731/371472 [6:18:52<12:40:03,  3.46it/s]
 58%|█████▊    | 213732/371472 [6:18:52<12:19:28,  3.56it/s]
 58%|█████▊    | 213733/371472 [6:18:53<12:20:36,  3.55it/s]
 58%|█████▊    | 213734/371472 [6:18:53<13:21:55,  3.28it/s]
 58%|█████▊    | 213735/371472 [6:18:53<13:04:13,  3.35it/s]
 58%|█████▊    | 213736/371472 [6:18:54<12:58:15,  3.38it/s]
 58%|█████▊    | 213737/371472 [6:18:54<13:07:23,  3.34it/s]
 58%|█████▊    | 213738/371472 [6:18:54<15:10:18,  2.89it/s]
 58%|█████▊    | 213739/371472 [6:18:55<14:27:45,  3.03it/s]
 58%|█████▊    | 213740/371472 [6:18:55<14:59:52,  2.92it/s]
                                                            
{'loss': 2.7273, 'learning_rate': 4.823579478118468e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213740/371472 [6:18:55<14:59:52,  2.92it/s]
 58%|█████▊    | 213741/371472 [6:18:55<14:59:48,  2.92it/s]
 58%|█████▊    | 213742/371472 [6:18:56<14:22:36,  3.05it/s]
 58%|█████▊    | 213743/371472 [6:18:56<14:42:12,  2.98it/s]
 58%|█████▊    | 213744/371472 [6:18:56<14:10:09,  3.09it/s]
 58%|█████▊    | 213745/371472 [6:18:57<13:37:29,  3.22it/s]
 58%|█████▊    | 213746/371472 [6:18:57<13:21:33,  3.28it/s]
 58%|█████▊    | 213747/371472 [6:18:57<13:33:34,  3.23it/s]
 58%|█████▊    | 213748/371472 [6:18:57<13:09:38,  3.33it/s]
 58%|█████▊    | 213749/371472 [6:18:58<12:56:31,  3.39it/s]
 58%|█████▊    | 213750/371472 [6:18:58<12:39:18,  3.46it/s]
 58%|█████▊    | 213751/371472 [6:18:58<12:41:05,  3.45it/s]
 58%|█████▊    | 213752/371472 [6:18:59<13:59:05,  3.13it/s]
 58%|█████▊    | 213753/371472 [6:18:59<13:53:39,  3.15it/s]
 58%|█████▊    | 213754/371472 [6:18:59<13:30:55,  3.24it/s]
 58%|█████▊    | 213755/371472 [6:19:00<13:23:11,  3.27it/s]
 58%|█████▊    | 213756/371472 [6:19:00<13:03:59,  3.35it/s]
 58%|█████▊    | 213757/371472 [6:19:00<13:00:13,  3.37it/s]
 58%|█████▊    | 213758/371472 [6:19:00<12:50:21,  3.41it/s]
 58%|█████▊    | 213759/371472 [6:19:01<13:03:17,  3.36it/s]
 58%|█████▊    | 213760/371472 [6:19:01<12:36:34,  3.47it/s]
                                                            
{'loss': 2.9303, 'learning_rate': 4.823094658363679e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213760/371472 [6:19:01<12:36:34,  3.47it/s]
 58%|█████▊    | 213761/371472 [6:19:01<12:38:48,  3.46it/s]
 58%|█████▊    | 213762/371472 [6:19:02<12:39:30,  3.46it/s]
 58%|█████▊    | 213763/371472 [6:19:02<13:51:05,  3.16it/s]
 58%|█████▊    | 213764/371472 [6:19:02<13:46:22,  3.18it/s]
 58%|█████▊    | 213765/371472 [6:19:03<13:52:23,  3.16it/s]
 58%|█████▊    | 213766/371472 [6:19:03<13:24:45,  3.27it/s]
 58%|█████▊    | 213767/371472 [6:19:03<13:00:30,  3.37it/s]
 58%|█████▊    | 213768/371472 [6:19:03<13:18:33,  3.29it/s]
 58%|█████▊    | 213769/371472 [6:19:04<13:14:23,  3.31it/s]
 58%|█████▊    | 213770/371472 [6:19:04<13:18:01,  3.29it/s]
 58%|█████▊    | 213771/371472 [6:19:04<13:01:50,  3.36it/s]
 58%|█████▊    | 213772/371472 [6:19:05<12:57:52,  3.38it/s]
 58%|█████▊    | 213773/371472 [6:19:05<12:59:18,  3.37it/s]
 58%|█████▊    | 213774/371472 [6:19:05<13:34:04,  3.23it/s]
 58%|█████▊    | 213775/371472 [6:19:06<13:27:53,  3.25it/s]
 58%|█████▊    | 213776/371472 [6:19:06<13:18:26,  3.29it/s]
 58%|█████▊    | 213777/371472 [6:19:06<13:03:47,  3.35it/s]
 58%|█████▊    | 213778/371472 [6:19:06<12:58:53,  3.37it/s]
 58%|█████▊    | 213779/371472 [6:19:07<12:42:16,  3.45it/s]
 58%|█████▊    | 213780/371472 [6:19:07<12:45:47,  3.43it/s]
                                                            
{'loss': 2.7787, 'learning_rate': 4.82260983860889e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213780/371472 [6:19:07<12:45:47,  3.43it/s]
 58%|█████▊    | 213781/371472 [6:19:07<12:44:34,  3.44it/s]
 58%|█████▊    | 213782/371472 [6:19:08<13:05:28,  3.35it/s]
 58%|█████▊    | 213783/371472 [6:19:08<12:49:38,  3.41it/s]
 58%|█████▊    | 213784/371472 [6:19:08<13:09:04,  3.33it/s]
 58%|█████▊    | 213785/371472 [6:19:09<13:55:28,  3.15it/s]
 58%|█████▊    | 213786/371472 [6:19:09<13:31:37,  3.24it/s]
 58%|█████▊    | 213787/371472 [6:19:09<13:19:03,  3.29it/s]
 58%|█████▊    | 213788/371472 [6:19:09<13:08:12,  3.33it/s]
 58%|█████▊    | 213789/371472 [6:19:10<12:54:20,  3.39it/s]
 58%|█████▊    | 213790/371472 [6:19:10<12:51:21,  3.41it/s]
 58%|█████▊    | 213791/371472 [6:19:10<12:56:53,  3.38it/s]
 58%|█████▊    | 213792/371472 [6:19:11<12:41:13,  3.45it/s]
 58%|█████▊    | 213793/371472 [6:19:11<13:32:38,  3.23it/s]
 58%|█████▊    | 213794/371472 [6:19:11<13:42:31,  3.20it/s]
 58%|█████▊    | 213795/371472 [6:19:12<13:21:50,  3.28it/s]
 58%|█████▊    | 213796/371472 [6:19:12<13:14:23,  3.31it/s]
 58%|█████▊    | 213797/371472 [6:19:12<13:07:39,  3.34it/s]
 58%|█████▊    | 213798/371472 [6:19:12<13:28:46,  3.25it/s]
 58%|█████▊    | 213799/371472 [6:19:13<13:57:18,  3.14it/s]
 58%|█████▊    | 213800/371472 [6:19:13<13:46:22,  3.18it/s]
                                                            
{'loss': 2.7766, 'learning_rate': 4.822125018854102e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213800/371472 [6:19:13<13:46:22,  3.18it/s]
 58%|█████▊    | 213801/371472 [6:19:13<13:30:01,  3.24it/s]
 58%|█████▊    | 213802/371472 [6:19:14<13:21:37,  3.28it/s]
 58%|█████▊    | 213803/371472 [6:19:14<13:32:57,  3.23it/s]
 58%|█████▊    | 213804/371472 [6:19:14<14:54:47,  2.94it/s]
 58%|█████▊    | 213805/371472 [6:19:15<15:10:17,  2.89it/s]
 58%|█████▊    | 213806/371472 [6:19:15<15:36:52,  2.80it/s]
 58%|█████▊    | 213807/371472 [6:19:16<16:04:58,  2.72it/s]
 58%|█████▊    | 213808/371472 [6:19:16<15:12:47,  2.88it/s]
 58%|█████▊    | 213809/371472 [6:19:16<14:24:51,  3.04it/s]
 58%|█████▊    | 213810/371472 [6:19:16<13:52:07,  3.16it/s]
 58%|█████▊    | 213811/371472 [6:19:17<13:21:59,  3.28it/s]
 58%|█████▊    | 213812/371472 [6:19:17<13:01:16,  3.36it/s]
 58%|█████▊    | 213813/371472 [6:19:17<13:02:34,  3.36it/s]
 58%|█████▊    | 213814/371472 [6:19:18<14:00:02,  3.13it/s]
 58%|█████▊    | 213815/371472 [6:19:18<13:28:42,  3.25it/s]
 58%|█████▊    | 213816/371472 [6:19:18<13:43:06,  3.19it/s]
 58%|█████▊    | 213817/371472 [6:19:19<13:24:01,  3.27it/s]
 58%|█████▊    | 213818/371472 [6:19:19<12:52:37,  3.40it/s]
 58%|█████▊    | 213819/371472 [6:19:19<12:45:08,  3.43it/s]
 58%|█████▊    | 213820/371472 [6:19:19<12:58:51,  3.37it/s]
                                                            
{'loss': 2.6748, 'learning_rate': 4.821640199099312e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213820/371472 [6:19:19<12:58:51,  3.37it/s]
 58%|█████▊    | 213821/371472 [6:19:20<13:08:52,  3.33it/s]
 58%|█████▊    | 213822/371472 [6:19:20<12:52:10,  3.40it/s]
 58%|█████▊    | 213823/371472 [6:19:20<12:48:47,  3.42it/s]
 58%|█████▊    | 213824/371472 [6:19:21<13:03:38,  3.35it/s]
 58%|█████▊    | 213825/371472 [6:19:21<13:43:18,  3.19it/s]
 58%|█████▊    | 213826/371472 [6:19:21<13:27:18,  3.25it/s]
 58%|█████▊    | 213827/371472 [6:19:22<13:05:01,  3.35it/s]
 58%|█████▊    | 213828/371472 [6:19:22<12:39:42,  3.46it/s]
 58%|█████▊    | 213829/371472 [6:19:22<13:20:05,  3.28it/s]
 58%|█████▊    | 213830/371472 [6:19:22<13:24:59,  3.26it/s]
 58%|█████▊    | 213831/371472 [6:19:23<13:55:12,  3.15it/s]
 58%|█████▊    | 213832/371472 [6:19:23<14:35:44,  3.00it/s]
 58%|█████▊    | 213833/371472 [6:19:24<14:45:16,  2.97it/s]
 58%|█████▊    | 213834/371472 [6:19:24<13:57:51,  3.14it/s]
 58%|█████▊    | 213835/371472 [6:19:24<13:26:12,  3.26it/s]
 58%|█████▊    | 213836/371472 [6:19:24<14:28:32,  3.02it/s]
 58%|█████▊    | 213837/371472 [6:19:25<14:41:03,  2.98it/s]
 58%|█████▊    | 213838/371472 [6:19:25<14:00:44,  3.12it/s]
 58%|█████▊    | 213839/371472 [6:19:25<13:35:50,  3.22it/s]
 58%|█████▊    | 213840/371472 [6:19:26<13:10:57,  3.32it/s]
                                                            
{'loss': 2.7941, 'learning_rate': 4.821155379344524e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213840/371472 [6:19:26<13:10:57,  3.32it/s]
 58%|█████▊    | 213841/371472 [6:19:26<13:03:32,  3.35it/s]
 58%|█████▊    | 213842/371472 [6:19:26<13:00:41,  3.37it/s]
 58%|█████▊    | 213843/371472 [6:19:27<14:37:25,  2.99it/s]
 58%|█████▊    | 213844/371472 [6:19:27<13:46:53,  3.18it/s]
 58%|█████▊    | 213845/371472 [6:19:27<13:31:27,  3.24it/s]
 58%|█████▊    | 213846/371472 [6:19:28<13:12:37,  3.31it/s]
 58%|█████▊    | 213847/371472 [6:19:28<12:55:04,  3.39it/s]
 58%|█████▊    | 213848/371472 [6:19:28<12:38:59,  3.46it/s]
 58%|█████▊    | 213849/371472 [6:19:28<13:02:48,  3.36it/s]
 58%|█████▊    | 213850/371472 [6:19:29<14:22:03,  3.05it/s]
 58%|█████▊    | 213851/371472 [6:19:29<13:34:18,  3.23it/s]
 58%|█████▊    | 213852/371472 [6:19:29<13:27:54,  3.25it/s]
 58%|█████▊    | 213853/371472 [6:19:30<13:21:50,  3.28it/s]
 58%|█████▊    | 213854/371472 [6:19:30<13:06:25,  3.34it/s]
 58%|█████▊    | 213855/371472 [6:19:30<12:50:05,  3.41it/s]
 58%|█████▊    | 213856/371472 [6:19:30<12:43:35,  3.44it/s]
 58%|█████▊    | 213857/371472 [6:19:31<12:37:47,  3.47it/s]
 58%|█████▊    | 213858/371472 [6:19:31<12:50:00,  3.41it/s]
 58%|█████▊    | 213859/371472 [6:19:31<12:49:59,  3.41it/s]
 58%|█████▊    | 213860/371472 [6:19:32<12:50:43,  3.41it/s]
                                                            
{'loss': 2.7436, 'learning_rate': 4.820670559589735e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213860/371472 [6:19:32<12:50:43,  3.41it/s]
 58%|█████▊    | 213861/371472 [6:19:32<12:36:42,  3.47it/s]
 58%|█████▊    | 213862/371472 [6:19:32<12:41:01,  3.45it/s]
 58%|█████▊    | 213863/371472 [6:19:33<12:24:56,  3.53it/s]
 58%|█████▊    | 213864/371472 [6:19:33<12:53:34,  3.40it/s]
 58%|█████▊    | 213865/371472 [6:19:33<12:49:24,  3.41it/s]
 58%|█████▊    | 213866/371472 [6:19:33<12:35:44,  3.48it/s]
 58%|█████▊    | 213867/371472 [6:19:34<13:07:21,  3.34it/s]
 58%|█████▊    | 213868/371472 [6:19:34<12:59:50,  3.37it/s]
 58%|█████▊    | 213869/371472 [6:19:34<12:55:33,  3.39it/s]
 58%|█████▊    | 213870/371472 [6:19:35<13:42:49,  3.19it/s]
 58%|█████▊    | 213871/371472 [6:19:35<13:14:42,  3.31it/s]
 58%|█████▊    | 213872/371472 [6:19:35<12:59:35,  3.37it/s]
 58%|█████▊    | 213873/371472 [6:19:36<12:50:39,  3.41it/s]
 58%|█████▊    | 213874/371472 [6:19:36<12:35:27,  3.48it/s]
 58%|█████▊    | 213875/371472 [6:19:36<12:49:20,  3.41it/s]
 58%|█████▊    | 213876/371472 [6:19:36<12:57:08,  3.38it/s]
 58%|█████▊    | 213877/371472 [6:19:37<12:33:52,  3.48it/s]
 58%|█████▊    | 213878/371472 [6:19:37<12:12:47,  3.58it/s]
 58%|█████▊    | 213879/371472 [6:19:37<12:09:57,  3.60it/s]
 58%|█████▊    | 213880/371472 [6:19:38<12:44:58,  3.43it/s]
                                                            
{'loss': 2.8231, 'learning_rate': 4.820185739834945e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213880/371472 [6:19:38<12:44:58,  3.43it/s]
 58%|█████▊    | 213881/371472 [6:19:38<12:54:06,  3.39it/s]
 58%|█████▊    | 213882/371472 [6:19:38<14:33:37,  3.01it/s]
 58%|█████▊    | 213883/371472 [6:19:39<13:46:44,  3.18it/s]
 58%|█████▊    | 213884/371472 [6:19:39<13:46:14,  3.18it/s]
 58%|█████▊    | 213885/371472 [6:19:39<13:25:32,  3.26it/s]
 58%|█████▊    | 213886/371472 [6:19:39<13:59:12,  3.13it/s]
 58%|█████▊    | 213887/371472 [6:19:40<13:39:09,  3.21it/s]
 58%|█████▊    | 213888/371472 [6:19:40<13:24:46,  3.26it/s]
 58%|█████▊    | 213889/371472 [6:19:40<13:11:06,  3.32it/s]
 58%|█████▊    | 213890/371472 [6:19:41<13:09:05,  3.33it/s]
 58%|█████▊    | 213891/371472 [6:19:41<12:49:45,  3.41it/s]
 58%|█████▊    | 213892/371472 [6:19:41<12:40:32,  3.45it/s]
 58%|█████▊    | 213893/371472 [6:19:42<13:24:08,  3.27it/s]
 58%|█████▊    | 213894/371472 [6:19:42<13:43:02,  3.19it/s]
 58%|█████▊    | 213895/371472 [6:19:42<13:17:58,  3.29it/s]
 58%|█████▊    | 213896/371472 [6:19:42<13:27:50,  3.25it/s]
 58%|█████▊    | 213897/371472 [6:19:43<12:48:23,  3.42it/s]
 58%|█████▊    | 213898/371472 [6:19:43<12:39:06,  3.46it/s]
 58%|█████▊    | 213899/371472 [6:19:43<12:39:30,  3.46it/s]
 58%|█████▊    | 213900/371472 [6:19:44<12:27:59,  3.51it/s]
                                                            
{'loss': 2.9088, 'learning_rate': 4.819700920080156e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213900/371472 [6:19:44<12:27:59,  3.51it/s]
 58%|█████▊    | 213901/371472 [6:19:44<12:36:56,  3.47it/s]
 58%|█████▊    | 213902/371472 [6:19:44<12:35:18,  3.48it/s]
 58%|█████▊    | 213903/371472 [6:19:44<13:09:45,  3.33it/s]
 58%|█████▊    | 213904/371472 [6:19:45<12:50:17,  3.41it/s]
 58%|█████▊    | 213905/371472 [6:19:45<13:02:21,  3.36it/s]
 58%|█████▊    | 213906/371472 [6:19:45<13:37:18,  3.21it/s]
 58%|█████▊    | 213907/371472 [6:19:46<13:52:34,  3.15it/s]
 58%|█████▊    | 213908/371472 [6:19:46<13:38:03,  3.21it/s]
 58%|█████▊    | 213909/371472 [6:19:46<13:29:54,  3.24it/s]
 58%|█████▊    | 213910/371472 [6:19:47<14:07:02,  3.10it/s]
 58%|█████▊    | 213911/371472 [6:19:47<13:42:42,  3.19it/s]
 58%|█████▊    | 213912/371472 [6:19:47<13:31:35,  3.24it/s]
 58%|█████▊    | 213913/371472 [6:19:48<13:45:16,  3.18it/s]
 58%|█████▊    | 213914/371472 [6:19:48<13:53:17,  3.15it/s]
 58%|█████▊    | 213915/371472 [6:19:48<13:50:56,  3.16it/s]
 58%|█████▊    | 213916/371472 [6:19:49<14:05:32,  3.11it/s]
 58%|█████▊    | 213917/371472 [6:19:49<14:18:54,  3.06it/s]
 58%|█████▊    | 213918/371472 [6:19:49<14:38:13,  2.99it/s]
 58%|█████▊    | 213919/371472 [6:19:50<14:02:32,  3.12it/s]
 58%|█████▊    | 213920/371472 [6:19:50<13:45:24,  3.18it/s]
                                                            
{'loss': 2.7446, 'learning_rate': 4.819216100325368e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213920/371472 [6:19:50<13:45:24,  3.18it/s]
 58%|█████▊    | 213921/371472 [6:19:50<13:03:18,  3.35it/s]
 58%|█████▊    | 213922/371472 [6:19:50<12:48:47,  3.42it/s]
 58%|█████▊    | 213923/371472 [6:19:51<12:54:00,  3.39it/s]
 58%|█████▊    | 213924/371472 [6:19:51<12:46:59,  3.42it/s]
 58%|█████▊    | 213925/371472 [6:19:51<12:49:14,  3.41it/s]
 58%|█████▊    | 213926/371472 [6:19:52<13:29:41,  3.24it/s]
 58%|█████▊    | 213927/371472 [6:19:52<13:19:23,  3.28it/s]
 58%|█████▊    | 213928/371472 [6:19:52<13:06:40,  3.34it/s]
 58%|█████▊    | 213929/371472 [6:19:53<13:04:14,  3.35it/s]
 58%|█████▊    | 213930/371472 [6:19:53<12:53:38,  3.39it/s]
 58%|█████▊    | 213931/371472 [6:19:53<12:44:39,  3.43it/s]
 58%|█████▊    | 213932/371472 [6:19:53<12:51:23,  3.40it/s]
 58%|█████▊    | 213933/371472 [6:19:54<13:20:04,  3.28it/s]
 58%|█████▊    | 213934/371472 [6:19:54<13:07:36,  3.33it/s]
 58%|█████▊    | 213935/371472 [6:19:54<13:08:16,  3.33it/s]
 58%|█████▊    | 213936/371472 [6:19:55<12:55:12,  3.39it/s]
 58%|█████▊    | 213937/371472 [6:19:55<12:53:29,  3.39it/s]
 58%|█████▊    | 213938/371472 [6:19:55<13:07:49,  3.33it/s]
 58%|█████▊    | 213939/371472 [6:19:55<12:59:37,  3.37it/s]
 58%|█████▊    | 213940/371472 [6:19:56<13:08:27,  3.33it/s]
                                                            
{'loss': 2.7752, 'learning_rate': 4.818731280570579e-07, 'epoch': 9.21}
+
 58%|█████▊    | 213940/371472 [6:19:56<13:08:27,  3.33it/s]
 58%|█████▊    | 213941/371472 [6:19:56<13:45:46,  3.18it/s]
 58%|█████▊    | 213942/371472 [6:19:56<14:00:27,  3.12it/s]
 58%|█████▊    | 213943/371472 [6:19:57<13:41:31,  3.20it/s]
 58%|█████▊    | 213944/371472 [6:19:57<13:12:58,  3.31it/s]
 58%|█████▊    | 213945/371472 [6:19:57<13:05:41,  3.34it/s]
 58%|█████▊    | 213946/371472 [6:19:58<13:05:34,  3.34it/s]
 58%|█████▊    | 213947/371472 [6:19:58<13:10:41,  3.32it/s]
 58%|█████▊    | 213948/371472 [6:19:58<12:59:42,  3.37it/s]
 58%|█████▊    | 213949/371472 [6:19:59<12:58:55,  3.37it/s]
 58%|█████▊    | 213950/371472 [6:19:59<13:05:51,  3.34it/s]
 58%|█████▊    | 213951/371472 [6:19:59<12:44:31,  3.43it/s]
 58%|█████▊    | 213952/371472 [6:19:59<12:59:46,  3.37it/s]
 58%|█████▊    | 213953/371472 [6:20:00<12:37:04,  3.47it/s]
 58%|█████▊    | 213954/371472 [6:20:00<12:41:24,  3.45it/s]
 58%|█████▊    | 213955/371472 [6:20:00<13:01:28,  3.36it/s]
 58%|█████▊    | 213956/371472 [6:20:01<13:03:09,  3.35it/s]
 58%|█████▊    | 213957/371472 [6:20:01<12:50:35,  3.41it/s]
 58%|█████▊    | 213958/371472 [6:20:01<12:42:46,  3.44it/s]
 58%|█████▊    | 213959/371472 [6:20:02<14:02:27,  3.12it/s]
 58%|█████▊    | 213960/371472 [6:20:02<13:39:20,  3.20it/s]
                                                            
{'loss': 2.7244, 'learning_rate': 4.81824646081579e-07, 'epoch': 9.22}
+
 58%|█████▊    | 213960/371472 [6:20:02<13:39:20,  3.20it/s]
 58%|█████▊    | 213961/371472 [6:20:02<13:23:53,  3.27it/s]
 58%|█████▊    | 213962/371472 [6:20:02<13:15:43,  3.30it/s]
 58%|█████▊    | 213963/371472 [6:20:03<13:08:29,  3.33it/s]
 58%|█████▊    | 213964/371472 [6:20:03<13:20:47,  3.28it/s]
 58%|█████▊    | 213965/371472 [6:20:03<13:13:34,  3.31it/s]
 58%|█████▊    | 213966/371472 [6:20:04<13:09:39,  3.32it/s]
 58%|█████▊    | 213967/371472 [6:20:04<13:46:12,  3.18it/s]
 58%|█████▊    | 213968/371472 [6:20:04<13:43:13,  3.19it/s]
 58%|█████▊    | 213969/371472 [6:20:05<13:32:31,  3.23it/s]
 58%|█████▊    | 213970/371472 [6:20:05<13:12:59,  3.31it/s]
 58%|█████▊    | 213971/371472 [6:20:05<13:08:40,  3.33it/s]
 58%|█████▊    | 213972/371472 [6:20:05<13:01:47,  3.36it/s]
 58%|█████▊    | 213973/371472 [6:20:06<13:19:05,  3.28it/s]
 58%|█████▊    | 213974/371472 [6:20:06<12:52:06,  3.40it/s]
 58%|█████▊    | 213975/371472 [6:20:06<12:45:42,  3.43it/s]
 58%|█████▊    | 213976/371472 [6:20:07<12:34:57,  3.48it/s]
 58%|█████▊    | 213977/371472 [6:20:07<12:36:29,  3.47it/s]
 58%|█████▊    | 213978/371472 [6:20:07<12:41:35,  3.45it/s]
 58%|█████▊    | 213979/371472 [6:20:08<13:18:17,  3.29it/s]
 58%|█████▊    | 213980/371472 [6:20:08<13:04:59,  3.34it/s]
                                                            
{'loss': 2.7014, 'learning_rate': 4.817761641061001e-07, 'epoch': 9.22}
+
 58%|█████▊    | 213980/371472 [6:20:08<13:04:59,  3.34it/s]
 58%|█████▊    | 213981/371472 [6:20:08<12:59:11,  3.37it/s]
 58%|█████▊    | 213982/371472 [6:20:08<13:38:24,  3.21it/s]
 58%|█████▊    | 213983/371472 [6:20:09<13:27:56,  3.25it/s]
 58%|█████▊    | 213984/371472 [6:20:09<13:14:12,  3.30it/s]
 58%|█████▊    | 213985/371472 [6:20:09<13:02:46,  3.35it/s]
 58%|█████▊    | 213986/371472 [6:20:10<12:36:38,  3.47it/s]
 58%|█████▊    | 213987/371472 [6:20:10<12:36:17,  3.47it/s]
 58%|█████▊    | 213988/371472 [6:20:10<12:58:35,  3.37it/s]
 58%|█████▊    | 213989/371472 [6:20:11<13:03:54,  3.35it/s]
 58%|█████▊    | 213990/371472 [6:20:11<13:00:06,  3.36it/s]
 58%|█████▊    | 213991/371472 [6:20:11<13:00:46,  3.36it/s]
 58%|█████▊    | 213992/371472 [6:20:11<13:00:09,  3.36it/s]
 58%|█████▊    | 213993/371472 [6:20:12<12:53:46,  3.39it/s]
 58%|█████▊    | 213994/371472 [6:20:12<12:49:10,  3.41it/s]
 58%|█████▊    | 213995/371472 [6:20:12<13:08:29,  3.33it/s]
 58%|█████▊    | 213996/371472 [6:20:13<13:55:15,  3.14it/s]
 58%|█████▊    | 213997/371472 [6:20:13<13:42:47,  3.19it/s]
 58%|█████▊    | 213998/371472 [6:20:13<13:36:25,  3.21it/s]
 58%|█████▊    | 213999/371472 [6:20:14<13:11:22,  3.32it/s]
 58%|█████▊    | 214000/371472 [6:20:14<13:16:56,  3.29it/s]
                                                            
{'loss': 2.809, 'learning_rate': 4.817276821306212e-07, 'epoch': 9.22}
+
 58%|█████▊    | 214000/371472 [6:20:14<13:16:56,  3.29it/s]
 58%|█████▊    | 214001/371472 [6:20:14<14:05:39,  3.10it/s]
 58%|█████▊    | 214002/371472 [6:20:15<14:05:52,  3.10it/s]
 58%|█████▊    | 214003/371472 [6:20:15<13:58:17,  3.13it/s]
 58%|█████▊    | 214004/371472 [6:20:15<14:07:35,  3.10it/s]
 58%|█████▊    | 214005/371472 [6:20:15<13:43:18,  3.19it/s]
 58%|█████▊    | 214006/371472 [6:20:16<13:32:51,  3.23it/s]
 58%|█████▊    | 214007/371472 [6:20:16<13:44:01,  3.18it/s]
 58%|█████▊    | 214008/371472 [6:20:16<13:24:44,  3.26it/s]
 58%|█████▊    | 214009/371472 [6:20:17<12:55:34,  3.38it/s]
 58%|█████▊    | 214010/371472 [6:20:17<12:56:11,  3.38it/s]
 58%|█████▊    | 214011/371472 [6:20:17<13:18:20,  3.29it/s]
 58%|█████▊    | 214012/371472 [6:20:18<13:50:23,  3.16it/s]
 58%|█████▊    | 214013/371472 [6:20:18<14:34:52,  3.00it/s]
 58%|█████▊    | 214014/371472 [6:20:18<13:52:02,  3.15it/s]
 58%|█████▊    | 214015/371472 [6:20:19<13:10:04,  3.32it/s]
 58%|█████▊    | 214016/371472 [6:20:19<12:39:33,  3.45it/s]
 58%|█████▊    | 214017/371472 [6:20:19<12:29:51,  3.50it/s]
 58%|█████▊    | 214018/371472 [6:20:19<12:22:28,  3.53it/s]
 58%|█████▊    | 214019/371472 [6:20:20<13:05:42,  3.34it/s]
 58%|█████▊    | 214020/371472 [6:20:20<13:31:47,  3.23it/s]
                                                            
{'loss': 2.8281, 'learning_rate': 4.816792001551423e-07, 'epoch': 9.22}
+
 58%|█████▊    | 214020/371472 [6:20:20<13:31:47,  3.23it/s]
 58%|█████▊    | 214021/371472 [6:20:20<13:20:31,  3.28it/s]
 58%|█████▊    | 214022/371472 [6:20:21<13:19:37,  3.28it/s]
 58%|█████▊    | 214023/371472 [6:20:21<13:27:11,  3.25it/s]
 58%|█████▊    | 214024/371472 [6:20:21<13:46:51,  3.17it/s]
 58%|█████▊    | 214025/371472 [6:20:22<13:44:41,  3.18it/s]
 58%|█████▊    | 214026/371472 [6:20:22<13:27:54,  3.25it/s]
 58%|█████▊    | 214027/371472 [6:20:22<13:19:44,  3.28it/s]
 58%|█████▊    | 214028/371472 [6:20:22<13:24:37,  3.26it/s]
 58%|█████▊    | 214029/371472 [6:20:23<13:11:29,  3.32it/s]
 58%|█████▊    | 214030/371472 [6:20:23<13:12:21,  3.31it/s]
 58%|█████▊    | 214031/371472 [6:20:23<12:48:09,  3.42it/s]
 58%|█████▊    | 214032/371472 [6:20:24<12:39:43,  3.45it/s]
 58%|█████▊    | 214033/371472 [6:20:24<13:35:42,  3.22it/s]
 58%|█████▊    | 214034/371472 [6:20:24<13:31:29,  3.23it/s]
 58%|█████▊    | 214035/371472 [6:20:25<13:39:24,  3.20it/s]
 58%|█████▊    | 214036/371472 [6:20:25<14:03:04,  3.11it/s]
 58%|█████▊    | 214037/371472 [6:20:25<14:26:39,  3.03it/s]
 58%|█████▊    | 214038/371472 [6:20:26<14:10:48,  3.08it/s]
 58%|█████▊    | 214039/371472 [6:20:26<13:49:39,  3.16it/s]
 58%|█████▊    | 214040/371472 [6:20:26<13:41:52,  3.19it/s]
                                                            
{'loss': 2.7548, 'learning_rate': 4.816307181796634e-07, 'epoch': 9.22}
+
 58%|█████▊    | 214040/371472 [6:20:26<13:41:52,  3.19it/s]
 58%|█████▊    | 214041/371472 [6:20:27<13:25:13,  3.26it/s]
 58%|█████▊    | 214042/371472 [6:20:27<13:20:25,  3.28it/s]
 58%|█████▊    | 214043/371472 [6:20:27<12:50:03,  3.41it/s]
 58%|█████▊    | 214044/371472 [6:20:27<13:14:50,  3.30it/s]
 58%|█████▊    | 214045/371472 [6:20:28<13:22:34,  3.27it/s]
 58%|█████▊    | 214046/371472 [6:20:28<13:16:21,  3.29it/s]
 58%|█████▊    | 214047/371472 [6:20:28<13:11:44,  3.31it/s]
 58%|█████▊    | 214048/371472 [6:20:29<13:38:18,  3.21it/s]
 58%|█████▊    | 214049/371472 [6:20:29<13:24:57,  3.26it/s]
 58%|█████▊    | 214050/371472 [6:20:29<12:58:56,  3.37it/s]
 58%|█████▊    | 214051/371472 [6:20:30<13:26:01,  3.26it/s]
 58%|█████▊    | 214052/371472 [6:20:30<13:58:27,  3.13it/s]
 58%|█████▊    | 214053/371472 [6:20:30<13:35:39,  3.22it/s]
 58%|█████▊    | 214054/371472 [6:20:30<13:22:34,  3.27it/s]
 58%|█████▊    | 214055/371472 [6:20:31<13:37:25,  3.21it/s]
 58%|█████▊    | 214056/371472 [6:20:31<13:48:38,  3.17it/s]
 58%|█████▊    | 214057/371472 [6:20:31<13:53:39,  3.15it/s]
 58%|█████▊    | 214058/371472 [6:20:32<13:37:42,  3.21it/s]
 58%|█████▊    | 214059/371472 [6:20:32<14:28:15,  3.02it/s]
 58%|█████▊    | 214060/371472 [6:20:32<14:00:11,  3.12it/s]
                                                            
{'loss': 2.8694, 'learning_rate': 4.815822362041845e-07, 'epoch': 9.22}
+
 58%|█████▊    | 214060/371472 [6:20:32<14:00:11,  3.12it/s]
 58%|█████▊    | 214061/371472 [6:20:33<14:01:36,  3.12it/s]
 58%|█████▊    | 214062/371472 [6:20:33<14:25:46,  3.03it/s]
 58%|█████▊    | 214063/371472 [6:20:33<14:50:37,  2.95it/s]
 58%|█████▊    | 214064/371472 [6:20:34<14:26:32,  3.03it/s]
 58%|█████▊    | 214065/371472 [6:20:34<13:49:03,  3.16it/s]
 58%|█████▊    | 214066/371472 [6:20:34<13:26:37,  3.25it/s]
 58%|█████▊    | 214067/371472 [6:20:35<13:32:00,  3.23it/s]
 58%|█████▊    | 214068/371472 [6:20:35<13:03:52,  3.35it/s]
 58%|█████▊    | 214069/371472 [6:20:35<13:34:16,  3.22it/s]
 58%|█████▊    | 214070/371472 [6:20:36<13:06:23,  3.34it/s]
 58%|█████▊    | 214071/371472 [6:20:36<12:55:57,  3.38it/s]
 58%|█████▊    | 214072/371472 [6:20:36<12:56:17,  3.38it/s]
 58%|█████▊    | 214073/371472 [6:20:36<13:39:12,  3.20it/s]
 58%|█████▊    | 214074/371472 [6:20:37<15:00:42,  2.91it/s]
 58%|█████▊    | 214075/371472 [6:20:37<14:32:37,  3.01it/s]
 58%|█████▊    | 214076/371472 [6:20:38<14:23:02,  3.04it/s]
 58%|█████▊    | 214077/371472 [6:20:38<14:00:33,  3.12it/s]
 58%|█████▊    | 214078/371472 [6:20:38<13:50:45,  3.16it/s]
 58%|█████▊    | 214079/371472 [6:20:38<13:30:11,  3.24it/s]
 58%|█████▊    | 214080/371472 [6:20:39<13:31:22,  3.23it/s]
                                                            
{'loss': 2.6885, 'learning_rate': 4.815337542287056e-07, 'epoch': 9.22}
+
 58%|█████▊    | 214080/371472 [6:20:39<13:31:22,  3.23it/s]
 58%|█████▊    | 214081/371472 [6:20:39<13:30:26,  3.24it/s]
 58%|█████▊    | 214082/371472 [6:20:39<13:27:52,  3.25it/s]
 58%|��████▊    | 214083/371472 [6:20:40<13:19:26,  3.28it/s]
 58%|█████▊    | 214084/371472 [6:20:40<13:31:47,  3.23it/s]
 58%|█████▊    | 214085/371472 [6:20:40<13:18:39,  3.28it/s]
 58%|█████▊    | 214086/371472 [6:20:41<13:19:22,  3.28it/s]
 58%|█████▊    | 214087/371472 [6:20:41<13:31:28,  3.23it/s]
 58%|█████▊    | 214088/371472 [6:20:41<13:48:34,  3.17it/s]
 58%|█████▊    | 214089/371472 [6:20:42<13:28:38,  3.24it/s]
 58%|█████▊    | 214090/371472 [6:20:42<13:04:34,  3.34it/s]
 58%|█████▊    | 214091/371472 [6:20:42<13:27:11,  3.25it/s]
 58%|█████▊    | 214092/371472 [6:20:42<13:17:21,  3.29it/s]
 58%|█████▊    | 214093/371472 [6:20:43<14:15:49,  3.06it/s]
 58%|█████▊    | 214094/371472 [6:20:43<13:55:06,  3.14it/s]
 58%|█████▊    | 214095/371472 [6:20:43<13:38:22,  3.21it/s]
 58%|█████▊    | 214096/371472 [6:20:44<13:02:37,  3.35it/s]
 58%|█████▊    | 214097/371472 [6:20:44<12:58:34,  3.37it/s]
 58%|█████▊    | 214098/371472 [6:20:44<12:52:11,  3.40it/s]
 58%|█████▊    | 214099/371472 [6:20:45<13:05:13,  3.34it/s]
 58%|█████▊    | 214100/371472 [6:20:45<12:40:22,  3.45it/s]
                                                            
{'loss': 2.7604, 'learning_rate': 4.814852722532268e-07, 'epoch': 9.22}
+
 58%|█████▊    | 214100/371472 [6:20:45<12:40:22,  3.45it/s]
 58%|█████▊    | 214101/371472 [6:20:45<12:40:05,  3.45it/s]
 58%|█████▊    | 214102/371472 [6:20:45<12:37:22,  3.46it/s]
 58%|█████▊    | 214103/371472 [6:20:46<12:43:07,  3.44it/s]
 58%|█████▊    | 214104/371472 [6:20:46<12:48:37,  3.41it/s]
 58%|█████▊    | 214105/371472 [6:20:46<12:44:34,  3.43it/s]
 58%|█████▊    | 214106/371472 [6:20:47<13:15:09,  3.30it/s]
 58%|█████▊    | 214107/371472 [6:20:47<15:29:56,  2.82it/s]
 58%|█████▊    | 214108/371472 [6:20:47<14:49:38,  2.95it/s]
 58%|█████▊    | 214109/371472 [6:20:48<14:21:54,  3.04it/s]
 58%|█████▊    | 214110/371472 [6:20:48<14:52:53,  2.94it/s]
 58%|█████▊    | 214111/371472 [6:20:48<14:56:05,  2.93it/s]
 58%|█████▊    | 214112/371472 [6:20:49<14:12:40,  3.08it/s]
 58%|█████▊    | 214113/371472 [6:20:49<14:19:12,  3.05it/s]
 58%|█████▊    | 214114/371472 [6:20:49<14:02:28,  3.11it/s]
 58%|█████▊    | 214115/371472 [6:20:50<13:34:53,  3.22it/s]
 58%|█████▊    | 214116/371472 [6:20:50<13:29:42,  3.24it/s]
 58%|█████▊    | 214117/371472 [6:20:50<13:05:01,  3.34it/s]
 58%|█████▊    | 214118/371472 [6:20:51<13:22:00,  3.27it/s]
 58%|█████▊    | 214119/371472 [6:20:51<14:04:08,  3.11it/s]
 58%|█████▊    | 214120/371472 [6:20:51<13:21:38,  3.27it/s]
                                                            
{'loss': 2.7137, 'learning_rate': 4.814367902777478e-07, 'epoch': 9.22}
+
 58%|█████▊    | 214120/371472 [6:20:51<13:21:38,  3.27it/s]
 58%|█████▊    | 214121/371472 [6:20:51<12:59:15,  3.37it/s]
 58%|█████▊    | 214122/371472 [6:20:52<14:21:15,  3.04it/s]
 58%|█████▊    | 214123/371472 [6:20:52<14:59:19,  2.92it/s]
 58%|█████▊    | 214124/371472 [6:20:52<14:28:55,  3.02it/s]
 58%|█████▊    | 214125/371472 [6:20:53<13:51:01,  3.16it/s]
 58%|█████▊    | 214126/371472 [6:20:53<13:19:39,  3.28it/s]
 58%|█████▊    | 214127/371472 [6:20:53<13:21:14,  3.27it/s]
 58%|█████▊    | 214128/371472 [6:20:54<13:10:23,  3.32it/s]
 58%|█████▊    | 214129/371472 [6:20:54<13:10:57,  3.32it/s]
 58%|█████▊    | 214130/371472 [6:20:54<13:29:15,  3.24it/s]
 58%|█████▊    | 214131/371472 [6:20:55<13:11:32,  3.31it/s]
 58%|█████▊    | 214132/371472 [6:20:55<13:25:41,  3.25it/s]
 58%|█████▊    | 214133/371472 [6:20:55<13:09:03,  3.32it/s]
 58%|█████▊    | 214134/371472 [6:20:55<13:32:34,  3.23it/s]
 58%|█████▊    | 214135/371472 [6:20:56<13:42:35,  3.19it/s]
 58%|█████▊    | 214136/371472 [6:20:56<13:41:02,  3.19it/s]
 58%|█████▊    | 214137/371472 [6:20:56<13:46:59,  3.17it/s]
 58%|█████▊    | 214138/371472 [6:20:57<13:35:48,  3.21it/s]
 58%|█████▊    | 214139/371472 [6:20:57<13:34:38,  3.22it/s]
 58%|█████▊    | 214140/371472 [6:20:57<13:51:57,  3.15it/s]
                                                            
{'loss': 2.7509, 'learning_rate': 4.813883083022689e-07, 'epoch': 9.22}
+
 58%|█████▊    | 214140/371472 [6:20:57<13:51:57,  3.15it/s]
 58%|█████▊    | 214141/371472 [6:20:58<13:18:29,  3.28it/s]
 58%|█████▊    | 214142/371472 [6:20:58<12:57:22,  3.37it/s]
 58%|█████▊    | 214143/371472 [6:20:58<12:38:13,  3.46it/s]
 58%|█████▊    | 214144/371472 [6:20:58<12:21:19,  3.54it/s]
 58%|█████▊    | 214145/371472 [6:20:59<12:36:09,  3.47it/s]
 58%|█████▊    | 214146/371472 [6:20:59<12:31:09,  3.49it/s]
 58%|█████▊    | 214147/371472 [6:20:59<12:20:48,  3.54it/s]
 58%|█████▊    | 214148/371472 [6:21:00<13:17:41,  3.29it/s]
 58%|█████▊    | 214149/371472 [6:21:00<12:58:13,  3.37it/s]
 58%|█████▊    | 214150/371472 [6:21:00<13:22:26,  3.27it/s]
 58%|█████▊    | 214151/371472 [6:21:01<14:38:53,  2.98it/s]
 58%|█████▊    | 214152/371472 [6:21:01<14:10:06,  3.08it/s]
 58%|█████▊    | 214153/371472 [6:21:01<13:47:46,  3.17it/s]
 58%|█████▊    | 214154/371472 [6:21:02<13:26:33,  3.25it/s]
 58%|█████▊    | 214155/371472 [6:21:02<13:16:43,  3.29it/s]
 58%|█████▊    | 214156/371472 [6:21:02<13:02:08,  3.35it/s]
 58%|█████▊    | 214157/371472 [6:21:02<12:58:36,  3.37it/s]
 58%|█████▊    | 214158/371472 [6:21:03<13:29:21,  3.24it/s]
 58%|█████▊    | 214159/371472 [6:21:03<13:11:30,  3.31it/s]
 58%|█████▊    | 214160/371472 [6:21:03<12:54:53,  3.38it/s]
                                                            
{'loss': 2.834, 'learning_rate': 4.8133982632679e-07, 'epoch': 9.22}
+
 58%|█████▊    | 214160/371472 [6:21:03<12:54:53,  3.38it/s]
 58%|█████▊    | 214161/371472 [6:21:04<12:58:10,  3.37it/s]
 58%|█████▊    | 214162/371472 [6:21:04<13:09:10,  3.32it/s]
 58%|█████▊    | 214163/371472 [6:21:04<13:57:32,  3.13it/s]
 58%|█████▊    | 214164/371472 [6:21:05<14:33:54,  3.00it/s]
 58%|█████▊    | 214165/371472 [6:21:05<13:54:44,  3.14it/s]
 58%|█████▊    | 214166/371472 [6:21:05<13:39:32,  3.20it/s]
 58%|█████▊    | 214167/371472 [6:21:06<13:17:34,  3.29it/s]
 58%|█████▊    | 214168/371472 [6:21:06<13:15:54,  3.29it/s]
 58%|█████▊    | 214169/371472 [6:21:06<12:54:30,  3.38it/s]
 58%|█████▊    | 214170/371472 [6:21:06<13:18:06,  3.28it/s]
 58%|█████▊    | 214171/371472 [6:21:07<13:22:18,  3.27it/s]
 58%|█████▊    | 214172/371472 [6:21:07<13:05:45,  3.34it/s]
 58%|█████▊    | 214173/371472 [6:21:07<13:05:43,  3.34it/s]
 58%|█████▊    | 214174/371472 [6:21:08<12:47:00,  3.42it/s]
 58%|█████▊    | 214175/371472 [6:21:08<12:39:39,  3.45it/s]
 58%|█████▊    | 214176/371472 [6:21:08<12:47:13,  3.42it/s]
 58%|█████▊    | 214177/371472 [6:21:09<13:15:40,  3.29it/s]
 58%|█████▊    | 214178/371472 [6:21:09<13:27:48,  3.25it/s]
 58%|█████▊    | 214179/371472 [6:21:09<13:21:53,  3.27it/s]
 58%|█████▊    | 214180/371472 [6:21:09<13:20:47,  3.27it/s]
                                                            
{'loss': 2.6781, 'learning_rate': 4.812913443513111e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214180/371472 [6:21:09<13:20:47,  3.27it/s]
 58%|█████▊    | 214181/371472 [6:21:10<12:59:21,  3.36it/s]
 58%|█████▊    | 214182/371472 [6:21:10<13:31:21,  3.23it/s]
 58%|█████▊    | 214183/371472 [6:21:10<14:36:54,  2.99it/s]
 58%|█████▊    | 214184/371472 [6:21:11<14:08:30,  3.09it/s]
 58%|█████▊    | 214185/371472 [6:21:11<14:29:06,  3.02it/s]
 58%|█████▊    | 214186/371472 [6:21:11<13:54:10,  3.14it/s]
 58%|█████▊    | 214187/371472 [6:21:12<13:37:02,  3.21it/s]
 58%|█████▊    | 214188/371472 [6:21:12<13:49:33,  3.16it/s]
 58%|█████▊    | 214189/371472 [6:21:12<14:02:25,  3.11it/s]
 58%|█████▊    | 214190/371472 [6:21:13<14:22:51,  3.04it/s]
 58%|█████▊    | 214191/371472 [6:21:13<13:53:26,  3.15it/s]
 58%|█████▊    | 214192/371472 [6:21:13<13:57:33,  3.13it/s]
 58%|█████▊    | 214193/371472 [6:21:14<14:35:08,  3.00it/s]
 58%|█████▊    | 214194/371472 [6:21:14<14:14:40,  3.07it/s]
 58%|█████▊    | 214195/371472 [6:21:14<13:31:56,  3.23it/s]
 58%|█████▊    | 214196/371472 [6:21:15<14:16:09,  3.06it/s]
 58%|█████▊    | 214197/371472 [6:21:15<13:45:42,  3.17it/s]
 58%|█████▊    | 214198/371472 [6:21:15<15:04:19,  2.90it/s]
 58%|█████▊    | 214199/371472 [6:21:16<15:15:04,  2.86it/s]
 58%|█████▊    | 214200/371472 [6:21:16<14:20:22,  3.05it/s]
                                                            
{'loss': 2.6976, 'learning_rate': 4.812428623758322e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214200/371472 [6:21:16<14:20:22,  3.05it/s]
 58%|█████▊    | 214201/371472 [6:21:16<13:40:43,  3.19it/s]
 58%|█████▊    | 214202/371472 [6:21:17<14:00:10,  3.12it/s]
 58%|█████▊    | 214203/371472 [6:21:17<13:35:04,  3.22it/s]
 58%|█████▊    | 214204/371472 [6:21:17<13:39:35,  3.20it/s]
 58%|█████▊    | 214205/371472 [6:21:18<14:06:54,  3.09it/s]
 58%|█████▊    | 214206/371472 [6:21:18<13:43:51,  3.18it/s]
 58%|█████▊    | 214207/371472 [6:21:18<13:31:15,  3.23it/s]
 58%|█████▊    | 214208/371472 [6:21:18<13:26:25,  3.25it/s]
 58%|█████▊    | 214209/371472 [6:21:19<13:10:46,  3.31it/s]
 58%|█████▊    | 214210/371472 [6:21:19<13:01:27,  3.35it/s]
 58%|█████▊    | 214211/371472 [6:21:19<13:20:33,  3.27it/s]
 58%|█████▊    | 214212/371472 [6:21:20<13:25:01,  3.26it/s]
 58%|█████▊    | 214213/371472 [6:21:20<13:46:20,  3.17it/s]
 58%|█████▊    | 214214/371472 [6:21:20<13:32:42,  3.22it/s]
 58%|█████▊    | 214215/371472 [6:21:21<13:43:13,  3.18it/s]
 58%|█████▊    | 214216/371472 [6:21:21<13:19:30,  3.28it/s]
 58%|█████▊    | 214217/371472 [6:21:21<12:56:04,  3.38it/s]
 58%|█████▊    | 214218/371472 [6:21:21<12:48:59,  3.41it/s]
 58%|█████▊    | 214219/371472 [6:21:22<13:18:01,  3.28it/s]
 58%|█████▊    | 214220/371472 [6:21:22<12:48:35,  3.41it/s]
                                                            
{'loss': 2.6986, 'learning_rate': 4.811943804003534e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214220/371472 [6:21:22<12:48:35,  3.41it/s]
 58%|█████▊    | 214221/371472 [6:21:22<13:33:41,  3.22it/s]
 58%|█████▊    | 214222/371472 [6:21:23<13:21:44,  3.27it/s]
 58%|█████▊    | 214223/371472 [6:21:23<12:56:52,  3.37it/s]
 58%|█████▊    | 214224/371472 [6:21:23<12:39:44,  3.45it/s]
 58%|█████▊    | 214225/371472 [6:21:24<12:39:01,  3.45it/s]
 58%|█████▊    | 214226/371472 [6:21:24<12:50:14,  3.40it/s]
 58%|█████▊    | 214227/371472 [6:21:24<12:51:34,  3.40it/s]
 58%|█████▊    | 214228/371472 [6:21:24<12:29:34,  3.50it/s]
 58%|█████▊    | 214229/371472 [6:21:25<12:31:47,  3.49it/s]
 58%|█████▊    | 214230/371472 [6:21:25<12:32:06,  3.48it/s]
 58%|█████▊    | 214231/371472 [6:21:25<12:40:51,  3.44it/s]
 58%|█████▊    | 214232/371472 [6:21:26<13:21:49,  3.27it/s]
 58%|█████▊    | 214233/371472 [6:21:26<13:33:20,  3.22it/s]
 58%|█████▊    | 214234/371472 [6:21:26<14:04:58,  3.10it/s]
 58%|█████▊    | 214235/371472 [6:21:27<13:43:40,  3.18it/s]
 58%|█████▊    | 214236/371472 [6:21:27<13:14:44,  3.30it/s]
 58%|█████▊    | 214237/371472 [6:21:27<13:53:14,  3.15it/s]
 58%|█████▊    | 214238/371472 [6:21:28<13:29:26,  3.24it/s]
 58%|█████▊    | 214239/371472 [6:21:28<13:05:47,  3.33it/s]
 58%|█████▊    | 214240/371472 [6:21:28<13:41:41,  3.19it/s]
                                                            
{'loss': 2.8735, 'learning_rate': 4.811458984248745e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214240/371472 [6:21:28<13:41:41,  3.19it/s]
 58%|█████▊    | 214241/371472 [6:21:28<14:01:35,  3.11it/s]
 58%|█████▊    | 214242/371472 [6:21:29<13:47:23,  3.17it/s]
 58%|█████▊    | 214243/371472 [6:21:29<13:27:33,  3.24it/s]
 58%|█████▊    | 214244/371472 [6:21:29<13:12:28,  3.31it/s]
 58%|█████▊    | 214245/371472 [6:21:30<13:27:13,  3.25it/s]
 58%|█████▊    | 214246/371472 [6:21:30<13:29:37,  3.24it/s]
 58%|█████▊    | 214247/371472 [6:21:30<14:21:30,  3.04it/s]
 58%|█████▊    | 214248/371472 [6:21:31<13:47:25,  3.17it/s]
 58%|█████▊    | 214249/371472 [6:21:31<13:26:38,  3.25it/s]
 58%|█████▊    | 214250/371472 [6:21:31<13:53:46,  3.14it/s]
 58%|█████▊    | 214251/371472 [6:21:32<13:38:52,  3.20it/s]
 58%|█████▊    | 214252/371472 [6:21:32<14:13:34,  3.07it/s]
 58%|█████▊    | 214253/371472 [6:21:32<13:58:30,  3.12it/s]
 58%|█████▊    | 214254/371472 [6:21:33<13:30:53,  3.23it/s]
 58%|█████▊    | 214255/371472 [6:21:33<13:29:47,  3.24it/s]
 58%|█████▊    | 214256/371472 [6:21:33<13:27:50,  3.24it/s]
 58%|█████▊    | 214257/371472 [6:21:33<12:58:39,  3.37it/s]
 58%|█████▊    | 214258/371472 [6:21:34<12:42:14,  3.44it/s]
 58%|█████▊    | 214259/371472 [6:21:34<12:38:07,  3.46it/s]
 58%|█████▊    | 214260/371472 [6:21:34<12:34:32,  3.47it/s]
                                                            
{'loss': 2.8408, 'learning_rate': 4.810974164493955e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214260/371472 [6:21:34<12:34:32,  3.47it/s]
 58%|█████▊    | 214261/371472 [6:21:35<13:02:34,  3.35it/s]
 58%|█████▊    | 214262/371472 [6:21:35<13:08:18,  3.32it/s]
 58%|█████▊    | 214263/371472 [6:21:35<13:19:43,  3.28it/s]
 58%|█████▊    | 214264/371472 [6:21:36<13:25:34,  3.25it/s]
 58%|█████▊    | 214265/371472 [6:21:36<13:10:18,  3.32it/s]
 58%|█████▊    | 214266/371472 [6:21:36<12:42:03,  3.44it/s]
 58%|█████▊    | 214267/371472 [6:21:36<12:39:08,  3.45it/s]
 58%|█████▊    | 214268/371472 [6:21:37<12:28:01,  3.50it/s]
 58%|█████▊    | 214269/371472 [6:21:37<13:10:47,  3.31it/s]
 58%|█████▊    | 214270/371472 [6:21:37<13:13:49,  3.30it/s]
 58%|█████▊    | 214271/371472 [6:21:38<13:21:08,  3.27it/s]
 58%|█████▊    | 214272/371472 [6:21:38<13:11:44,  3.31it/s]
 58%|█████▊    | 214273/371472 [6:21:38<13:06:37,  3.33it/s]
 58%|█████▊    | 214274/371472 [6:21:38<12:54:17,  3.38it/s]
 58%|█████▊    | 214275/371472 [6:21:39<12:53:07,  3.39it/s]
 58%|█████▊    | 214276/371472 [6:21:39<12:50:15,  3.40it/s]
 58%|█████▊    | 214277/371472 [6:21:39<12:36:57,  3.46it/s]
 58%|█████▊    | 214278/371472 [6:21:40<12:53:59,  3.38it/s]
 58%|█████▊    | 214279/371472 [6:21:40<12:39:39,  3.45it/s]
 58%|█████▊    | 214280/371472 [6:21:40<12:28:36,  3.50it/s]
                                                            
{'loss': 2.8558, 'learning_rate': 4.810489344739166e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214280/371472 [6:21:40<12:28:36,  3.50it/s]
 58%|█████▊    | 214281/371472 [6:21:40<12:15:07,  3.56it/s]
 58%|█████▊    | 214282/371472 [6:21:41<12:16:29,  3.56it/s]
 58%|█████▊    | 214283/371472 [6:21:41<13:15:18,  3.29it/s]
 58%|█████▊    | 214284/371472 [6:21:41<13:06:00,  3.33it/s]
 58%|█████▊    | 214285/371472 [6:21:42<12:36:38,  3.46it/s]
 58%|█████▊    | 214286/371472 [6:21:42<13:17:46,  3.28it/s]
 58%|█████▊    | 214287/371472 [6:21:42<13:02:03,  3.35it/s]
 58%|█████▊    | 214288/371472 [6:21:43<12:54:44,  3.38it/s]
 58%|█████▊    | 214289/371472 [6:21:43<13:05:14,  3.34it/s]
 58%|█████▊    | 214290/371472 [6:21:43<13:40:19,  3.19it/s]
 58%|█████▊    | 214291/371472 [6:21:44<13:17:36,  3.28it/s]
 58%|█████▊    | 214292/371472 [6:21:44<12:56:00,  3.38it/s]
 58%|█████▊    | 214293/371472 [6:21:44<12:46:17,  3.42it/s]
 58%|█████▊    | 214294/371472 [6:21:44<13:07:50,  3.33it/s]
 58%|█████▊    | 214295/371472 [6:21:45<13:01:14,  3.35it/s]
 58%|█████▊    | 214296/371472 [6:21:45<12:58:29,  3.36it/s]
 58%|█████▊    | 214297/371472 [6:21:45<13:42:28,  3.19it/s]
 58%|█████▊    | 214298/371472 [6:21:46<13:25:35,  3.25it/s]
 58%|█████▊    | 214299/371472 [6:21:46<13:48:23,  3.16it/s]
 58%|█████▊    | 214300/371472 [6:21:46<13:54:13,  3.14it/s]
                                                            
{'loss': 2.8054, 'learning_rate': 4.810004524984378e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214300/371472 [6:21:46<13:54:13,  3.14it/s]
 58%|█████▊    | 214301/371472 [6:21:47<13:27:23,  3.24it/s]
 58%|█████▊    | 214302/371472 [6:21:47<13:08:27,  3.32it/s]
 58%|█████▊    | 214303/371472 [6:21:47<13:34:19,  3.22it/s]
 58%|█████▊    | 214304/371472 [6:21:48<13:35:14,  3.21it/s]
 58%|█████▊    | 214305/371472 [6:21:48<13:36:51,  3.21it/s]
 58%|█████▊    | 214306/371472 [6:21:48<14:25:16,  3.03it/s]
 58%|█████▊    | 214307/371472 [6:21:48<13:43:48,  3.18it/s]
 58%|█████▊    | 214308/371472 [6:21:49<13:09:52,  3.32it/s]
 58%|█████▊    | 214309/371472 [6:21:49<13:27:05,  3.25it/s]
 58%|█████▊    | 214310/371472 [6:21:49<12:58:23,  3.37it/s]
 58%|█████▊    | 214311/371472 [6:21:50<13:03:02,  3.35it/s]
 58%|█████▊    | 214312/371472 [6:21:50<12:41:06,  3.44it/s]
 58%|█████▊    | 214313/371472 [6:21:50<12:22:08,  3.53it/s]
 58%|█████▊    | 214314/371472 [6:21:50<12:32:39,  3.48it/s]
 58%|█████▊    | 214315/371472 [6:21:51<12:26:56,  3.51it/s]
 58%|█████▊    | 214316/371472 [6:21:51<12:59:30,  3.36it/s]
 58%|█████▊    | 214317/371472 [6:21:51<13:12:48,  3.30it/s]
 58%|█████▊    | 214318/371472 [6:21:52<13:23:04,  3.26it/s]
 58%|█████▊    | 214319/371472 [6:21:52<12:50:02,  3.40it/s]
 58%|█████▊    | 214320/371472 [6:21:52<12:51:32,  3.39it/s]
                                                            
{'loss': 2.9913, 'learning_rate': 4.809519705229589e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214320/371472 [6:21:52<12:51:32,  3.39it/s]
 58%|█████▊    | 214321/371472 [6:21:53<12:41:03,  3.44it/s]
 58%|█████▊    | 214322/371472 [6:21:53<12:40:55,  3.44it/s]
 58%|█████▊    | 214323/371472 [6:21:53<12:38:48,  3.45it/s]
 58%|█████▊    | 214324/371472 [6:21:53<12:41:42,  3.44it/s]
 58%|█████▊    | 214325/371472 [6:21:54<12:46:17,  3.42it/s]
 58%|█████▊    | 214326/371472 [6:21:54<13:08:07,  3.32it/s]
 58%|█████▊    | 214327/371472 [6:21:54<12:40:13,  3.45it/s]
 58%|█████▊    | 214328/371472 [6:21:55<12:46:31,  3.42it/s]
 58%|█████▊    | 214329/371472 [6:21:55<13:06:29,  3.33it/s]
 58%|█████▊    | 214330/371472 [6:21:55<12:46:07,  3.42it/s]
 58%|█████▊    | 214331/371472 [6:21:56<12:56:54,  3.37it/s]
 58%|█████▊    | 214332/371472 [6:21:56<12:46:55,  3.41it/s]
 58%|█████▊    | 214333/371472 [6:21:56<12:24:06,  3.52it/s]
 58%|█████▊    | 214334/371472 [6:21:56<12:28:55,  3.50it/s]
 58%|█████▊    | 214335/371472 [6:21:57<12:21:20,  3.53it/s]
 58%|█████▊    | 214336/371472 [6:21:57<12:23:36,  3.52it/s]
 58%|█████▊    | 214337/371472 [6:21:57<12:22:26,  3.53it/s]
 58%|█████▊    | 214338/371472 [6:21:58<12:48:19,  3.41it/s]
 58%|█████▊    | 214339/371472 [6:21:58<12:43:14,  3.43it/s]
 58%|█████▊    | 214340/371472 [6:21:58<12:35:27,  3.47it/s]
                                                            
{'loss': 2.6871, 'learning_rate': 4.8090348854748e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214340/371472 [6:21:58<12:35:27,  3.47it/s]
 58%|█████▊    | 214341/371472 [6:21:58<12:36:32,  3.46it/s]
 58%|█████▊    | 214342/371472 [6:21:59<12:29:24,  3.49it/s]
 58%|█████▊    | 214343/371472 [6:21:59<12:14:42,  3.56it/s]
 58%|█████▊    | 214344/371472 [6:21:59<12:11:55,  3.58it/s]
 58%|█████▊    | 214345/371472 [6:21:59<12:00:54,  3.63it/s]
 58%|█████▊    | 214346/371472 [6:22:00<12:19:58,  3.54it/s]
 58%|█████▊    | 214347/371472 [6:22:00<12:30:05,  3.49it/s]
 58%|█████▊    | 214348/371472 [6:22:00<12:39:31,  3.45it/s]
 58%|█████▊    | 214349/371472 [6:22:01<12:54:06,  3.38it/s]
 58%|█████▊    | 214350/371472 [6:22:01<13:16:25,  3.29it/s]
 58%|█████▊    | 214351/371472 [6:22:01<13:31:02,  3.23it/s]
 58%|█████▊    | 214352/371472 [6:22:02<13:10:30,  3.31it/s]
 58%|█████▊    | 214353/371472 [6:22:02<13:31:52,  3.23it/s]
 58%|█████▊    | 214354/371472 [6:22:02<13:28:38,  3.24it/s]
 58%|█████▊    | 214355/371472 [6:22:03<13:07:15,  3.33it/s]
 58%|█████▊    | 214356/371472 [6:22:03<12:48:52,  3.41it/s]
 58%|█████▊    | 214357/371472 [6:22:03<12:49:53,  3.40it/s]
 58%|█████▊    | 214358/371472 [6:22:03<12:52:06,  3.39it/s]
 58%|█████▊    | 214359/371472 [6:22:04<13:49:19,  3.16it/s]
 58%|█████▊    | 214360/371472 [6:22:04<13:52:16,  3.15it/s]
                                                            
{'loss': 2.8645, 'learning_rate': 4.808550065720011e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214360/371472 [6:22:04<13:52:16,  3.15it/s]
 58%|█████▊    | 214361/371472 [6:22:04<13:59:25,  3.12it/s]
 58%|█████▊    | 214362/371472 [6:22:05<14:29:01,  3.01it/s]
 58%|█████▊    | 214363/371472 [6:22:05<15:05:28,  2.89it/s]
 58%|█████▊    | 214364/371472 [6:22:05<14:33:05,  3.00it/s]
 58%|█████▊    | 214365/371472 [6:22:06<13:53:46,  3.14it/s]
 58%|█████▊    | 214366/371472 [6:22:06<13:33:16,  3.22it/s]
 58%|█████▊    | 214367/371472 [6:22:06<13:14:57,  3.29it/s]
 58%|█████▊    | 214368/371472 [6:22:07<13:07:40,  3.32it/s]
 58%|█████▊    | 214369/371472 [6:22:07<13:39:33,  3.19it/s]
 58%|█████▊    | 214370/371472 [6:22:07<13:17:11,  3.28it/s]
 58%|█████▊    | 214371/371472 [6:22:08<13:09:51,  3.31it/s]
 58%|█████▊    | 214372/371472 [6:22:08<12:59:41,  3.36it/s]
 58%|█████▊    | 214373/371472 [6:22:08<13:01:06,  3.35it/s]
 58%|█████▊    | 214374/371472 [6:22:08<12:51:42,  3.39it/s]
 58%|█████▊    | 214375/371472 [6:22:09<13:31:27,  3.23it/s]
 58%|█████▊    | 214376/371472 [6:22:09<14:05:54,  3.10it/s]
 58%|█████▊    | 214377/371472 [6:22:09<13:45:14,  3.17it/s]
 58%|█████▊    | 214378/371472 [6:22:10<13:31:36,  3.23it/s]
 58%|█████▊    | 214379/371472 [6:22:10<15:51:39,  2.75it/s]
 58%|█████▊    | 214380/371472 [6:22:10<14:57:47,  2.92it/s]
                                                            
{'loss': 2.9013, 'learning_rate': 4.808065245965222e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214380/371472 [6:22:10<14:57:47,  2.92it/s]
 58%|█████▊    | 214381/371472 [6:22:11<14:22:37,  3.04it/s]
 58%|█████▊    | 214382/371472 [6:22:11<13:38:57,  3.20it/s]
 58%|█████▊    | 214383/371472 [6:22:11<13:06:54,  3.33it/s]
 58%|█████▊    | 214384/371472 [6:22:12<13:39:16,  3.20it/s]
 58%|█████▊    | 214385/371472 [6:22:12<13:16:51,  3.29it/s]
 58%|█████▊    | 214386/371472 [6:22:12<13:20:36,  3.27it/s]
 58%|█████▊    | 214387/371472 [6:22:13<13:30:06,  3.23it/s]
 58%|█████▊    | 214388/371472 [6:22:13<13:08:05,  3.32it/s]
 58%|█████▊    | 214389/371472 [6:22:13<12:59:43,  3.36it/s]
 58%|█████▊    | 214390/371472 [6:22:13<13:07:48,  3.32it/s]
 58%|█████▊    | 214391/371472 [6:22:14<12:51:30,  3.39it/s]
 58%|█████▊    | 214392/371472 [6:22:14<12:41:12,  3.44it/s]
 58%|█████▊    | 214393/371472 [6:22:14<12:41:14,  3.44it/s]
 58%|█████▊    | 214394/371472 [6:22:15<12:13:36,  3.57it/s]
 58%|█████▊    | 214395/371472 [6:22:15<12:15:44,  3.56it/s]
 58%|█████▊    | 214396/371472 [6:22:15<12:06:26,  3.60it/s]
 58%|█████▊    | 214397/371472 [6:22:15<12:45:18,  3.42it/s]
 58%|█████▊    | 214398/371472 [6:22:16<12:41:28,  3.44it/s]
 58%|█████▊    | 214399/371472 [6:22:16<13:17:56,  3.28it/s]
 58%|█████▊    | 214400/371472 [6:22:16<13:15:50,  3.29it/s]
                                                            
{'loss': 2.7107, 'learning_rate': 4.807580426210432e-07, 'epoch': 9.23}
+
 58%|█████▊    | 214400/371472 [6:22:16<13:15:50,  3.29it/s]
 58%|█████▊    | 214401/371472 [6:22:17<13:24:28,  3.25it/s]
 58%|█████▊    | 214402/371472 [6:22:17<13:21:04,  3.27it/s]
 58%|█████▊    | 214403/371472 [6:22:17<13:44:36,  3.17it/s]
 58%|█████▊    | 214404/371472 [6:22:18<13:44:45,  3.17it/s]
 58%|█████▊    | 214405/371472 [6:22:18<13:32:32,  3.22it/s]
 58%|█████▊    | 214406/371472 [6:22:18<13:28:46,  3.24it/s]
 58%|█████▊    | 214407/371472 [6:22:19<13:10:16,  3.31it/s]
 58%|█████▊    | 214408/371472 [6:22:19<12:51:02,  3.40it/s]
 58%|█████▊    | 214409/371472 [6:22:19<14:14:42,  3.06it/s]
 58%|█████▊    | 214410/371472 [6:22:19<13:38:32,  3.20it/s]
 58%|█████▊    | 214411/371472 [6:22:20<12:57:55,  3.36it/s]
 58%|█████▊    | 214412/371472 [6:22:20<12:39:02,  3.45it/s]
 58%|█████▊    | 214413/371472 [6:22:20<12:48:16,  3.41it/s]
 58%|█████▊    | 214414/371472 [6:22:21<12:39:52,  3.44it/s]
 58%|█████▊    | 214415/371472 [6:22:21<12:30:53,  3.49it/s]
 58%|█████▊    | 214416/371472 [6:22:21<12:29:14,  3.49it/s]
 58%|█████▊    | 214417/371472 [6:22:21<12:56:19,  3.37it/s]
 58%|█████▊    | 214418/371472 [6:22:22<14:23:13,  3.03it/s]
 58%|█████▊    | 214419/371472 [6:22:22<14:11:59,  3.07it/s]
 58%|█████▊    | 214420/371472 [6:22:23<14:36:17,  2.99it/s]
                                                            
{'loss': 2.8391, 'learning_rate': 4.807095606455644e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214420/371472 [6:22:23<14:36:17,  2.99it/s]
 58%|█████▊    | 214421/371472 [6:22:23<14:15:48,  3.06it/s]
 58%|█████▊    | 214422/371472 [6:22:23<14:00:37,  3.11it/s]
 58%|█████▊    | 214423/371472 [6:22:23<14:00:27,  3.11it/s]
 58%|█████▊    | 214424/371472 [6:22:24<13:23:30,  3.26it/s]
 58%|█████▊    | 214425/371472 [6:22:24<13:01:27,  3.35it/s]
 58%|█████▊    | 214426/371472 [6:22:24<12:49:25,  3.40it/s]
 58%|█████▊    | 214427/371472 [6:22:25<12:17:20,  3.55it/s]
 58%|█████▊    | 214428/371472 [6:22:25<12:12:51,  3.57it/s]
 58%|█████▊    | 214429/371472 [6:22:25<13:21:49,  3.26it/s]
 58%|█████▊    | 214430/371472 [6:22:26<13:06:34,  3.33it/s]
 58%|█████▊    | 214431/371472 [6:22:26<12:54:00,  3.38it/s]
 58%|█████▊    | 214432/371472 [6:22:26<12:41:19,  3.44it/s]
 58%|█████▊    | 214433/371472 [6:22:26<12:40:33,  3.44it/s]
 58%|█████▊    | 214434/371472 [6:22:27<12:40:45,  3.44it/s]
 58%|█████▊    | 214435/371472 [6:22:27<12:43:17,  3.43it/s]
 58%|█████▊    | 214436/371472 [6:22:27<12:54:04,  3.38it/s]
 58%|█████▊    | 214437/371472 [6:22:28<13:06:38,  3.33it/s]
 58%|█████▊    | 214438/371472 [6:22:28<12:50:13,  3.40it/s]
 58%|█████▊    | 214439/371472 [6:22:28<12:25:47,  3.51it/s]
 58%|█████▊    | 214440/371472 [6:22:28<12:25:36,  3.51it/s]
                                                            
{'loss': 2.865, 'learning_rate': 4.806610786700855e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214440/371472 [6:22:28<12:25:36,  3.51it/s]
 58%|█████▊    | 214441/371472 [6:22:29<12:57:39,  3.37it/s]
 58%|█████▊    | 214442/371472 [6:22:29<12:45:57,  3.42it/s]
 58%|█████▊    | 214443/371472 [6:22:29<12:54:28,  3.38it/s]
 58%|█████▊    | 214444/371472 [6:22:30<12:55:51,  3.37it/s]
 58%|█████▊    | 214445/371472 [6:22:30<12:39:17,  3.45it/s]
 58%|█████▊    | 214446/371472 [6:22:30<12:30:15,  3.49it/s]
 58%|█████▊    | 214447/371472 [6:22:30<12:26:38,  3.51it/s]
 58%|█████▊    | 214448/371472 [6:22:31<12:21:50,  3.53it/s]
 58%|█████▊    | 214449/371472 [6:22:31<12:10:26,  3.58it/s]
 58%|█████▊    | 214450/371472 [6:22:31<13:10:19,  3.31it/s]
 58%|█████▊    | 214451/371472 [6:22:32<12:58:37,  3.36it/s]
 58%|█████▊    | 214452/371472 [6:22:32<12:44:34,  3.42it/s]
 58%|█████▊    | 214453/371472 [6:22:32<12:39:25,  3.45it/s]
 58%|█████▊    | 214454/371472 [6:22:32<12:41:37,  3.44it/s]
 58%|█████▊    | 214455/371472 [6:22:33<12:21:14,  3.53it/s]
 58%|█████▊    | 214456/371472 [6:22:33<12:27:08,  3.50it/s]
 58%|█████▊    | 214457/371472 [6:22:33<12:09:54,  3.59it/s]
 58%|█████▊    | 214458/371472 [6:22:34<12:18:20,  3.54it/s]
 58%|█████▊    | 214459/371472 [6:22:34<12:34:43,  3.47it/s]
 58%|█████▊    | 214460/371472 [6:22:34<12:30:22,  3.49it/s]
                                                            
{'loss': 2.8037, 'learning_rate': 4.806125966946067e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214460/371472 [6:22:34<12:30:22,  3.49it/s]
 58%|█████▊    | 214461/371472 [6:22:34<12:23:41,  3.52it/s]
 58%|█████▊    | 214462/371472 [6:22:35<12:17:48,  3.55it/s]
 58%|█████▊    | 214463/371472 [6:22:35<11:55:38,  3.66it/s]
 58%|█████▊    | 214464/371472 [6:22:35<11:52:19,  3.67it/s]
 58%|█████▊    | 214465/371472 [6:22:36<13:28:52,  3.24it/s]
 58%|█████▊    | 214466/371472 [6:22:36<13:12:24,  3.30it/s]
 58%|█████▊    | 214467/371472 [6:22:36<13:02:54,  3.34it/s]
 58%|█████▊    | 214468/371472 [6:22:37<12:55:24,  3.37it/s]
 58%|█████▊    | 214469/371472 [6:22:37<12:35:17,  3.46it/s]
 58%|█████▊    | 214470/371472 [6:22:37<12:30:41,  3.49it/s]
 58%|█████▊    | 214471/371472 [6:22:37<13:16:29,  3.29it/s]
 58%|█████▊    | 214472/371472 [6:22:38<13:07:13,  3.32it/s]
 58%|█████▊    | 214473/371472 [6:22:38<14:03:36,  3.10it/s]
 58%|█████▊    | 214474/371472 [6:22:38<14:02:43,  3.10it/s]
 58%|█████▊    | 214475/371472 [6:22:39<13:24:42,  3.25it/s]
 58%|█████▊    | 214476/371472 [6:22:39<13:08:40,  3.32it/s]
 58%|█████▊    | 214477/371472 [6:22:39<12:54:35,  3.38it/s]
 58%|█████▊    | 214478/371472 [6:22:40<12:51:11,  3.39it/s]
 58%|█████▊    | 214479/371472 [6:22:40<12:39:44,  3.44it/s]
 58%|█████▊    | 214480/371472 [6:22:40<12:38:08,  3.45it/s]
                                                            
{'loss': 2.8826, 'learning_rate': 4.805641147191277e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214480/371472 [6:22:40<12:38:08,  3.45it/s]
 58%|█████▊    | 214481/371472 [6:22:40<12:39:42,  3.44it/s]
 58%|█████▊    | 214482/371472 [6:22:41<12:50:09,  3.40it/s]
 58%|█████▊    | 214483/371472 [6:22:41<13:07:26,  3.32it/s]
 58%|█████▊    | 214484/371472 [6:22:41<12:59:32,  3.36it/s]
 58%|█████▊    | 214485/371472 [6:22:42<13:08:37,  3.32it/s]
 58%|█████▊    | 214486/371472 [6:22:42<12:48:56,  3.40it/s]
 58%|█████▊    | 214487/371472 [6:22:42<12:54:48,  3.38it/s]
 58%|█████▊    | 214488/371472 [6:22:42<12:39:42,  3.44it/s]
 58%|█████▊    | 214489/371472 [6:22:43<13:30:30,  3.23it/s]
 58%|█████▊    | 214490/371472 [6:22:43<13:18:39,  3.28it/s]
 58%|█████▊    | 214491/371472 [6:22:43<13:10:23,  3.31it/s]
 58%|█████▊    | 214492/371472 [6:22:44<13:02:11,  3.34it/s]
 58%|█████▊    | 214493/371472 [6:22:44<13:02:46,  3.34it/s]
 58%|█████▊    | 214494/371472 [6:22:44<12:45:24,  3.42it/s]
 58%|█████▊    | 214495/371472 [6:22:45<12:31:43,  3.48it/s]
 58%|█████▊    | 214496/371472 [6:22:45<12:31:36,  3.48it/s]
 58%|█████▊    | 214497/371472 [6:22:45<13:03:10,  3.34it/s]
 58%|█████▊    | 214498/371472 [6:22:45<12:52:34,  3.39it/s]
 58%|█████▊    | 214499/371472 [6:22:46<13:15:47,  3.29it/s]
 58%|█████▊    | 214500/371472 [6:22:46<14:12:15,  3.07it/s]
                                                            
{'loss': 2.8241, 'learning_rate': 4.805156327436488e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214500/371472 [6:22:46<14:12:15,  3.07it/s]
 58%|█████▊    | 214501/371472 [6:22:46<13:49:24,  3.15it/s]
 58%|█████▊    | 214502/371472 [6:22:47<14:06:41,  3.09it/s]
 58%|█████▊    | 214503/371472 [6:22:47<15:10:10,  2.87it/s]
 58%|█████▊    | 214504/371472 [6:22:48<14:53:07,  2.93it/s]
 58%|█████▊    | 214505/371472 [6:22:48<14:47:04,  2.95it/s]
 58%|█████▊    | 214506/371472 [6:22:48<14:04:50,  3.10it/s]
 58%|█████▊    | 214507/371472 [6:22:48<13:32:00,  3.22it/s]
 58%|█████▊    | 214508/371472 [6:22:49<13:05:45,  3.33it/s]
 58%|█████▊    | 214509/371472 [6:22:49<13:01:53,  3.35it/s]
 58%|█████▊    | 214510/371472 [6:22:49<13:09:07,  3.32it/s]
 58%|█████▊    | 214511/371472 [6:22:50<12:57:28,  3.36it/s]
 58%|█████▊    | 214512/371472 [6:22:50<12:52:37,  3.39it/s]
 58%|█████▊    | 214513/371472 [6:22:50<12:49:39,  3.40it/s]
 58%|█████��    | 214514/371472 [6:22:50<12:57:59,  3.36it/s]
 58%|█████▊    | 214515/371472 [6:22:51<13:18:37,  3.28it/s]
 58%|█████▊    | 214516/371472 [6:22:51<12:58:26,  3.36it/s]
 58%|█████▊    | 214517/371472 [6:22:51<12:44:33,  3.42it/s]
 58%|█████▊    | 214518/371472 [6:22:52<12:36:15,  3.46it/s]
 58%|█████▊    | 214519/371472 [6:22:52<12:37:35,  3.45it/s]
 58%|█████▊    | 214520/371472 [6:22:52<13:24:32,  3.25it/s]
                                                            
{'loss': 2.7252, 'learning_rate': 4.804671507681699e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214520/371472 [6:22:52<13:24:32,  3.25it/s]
 58%|█████▊    | 214521/371472 [6:22:53<13:52:51,  3.14it/s]
 58%|█████▊    | 214522/371472 [6:22:53<13:36:09,  3.21it/s]
 58%|█████▊    | 214523/371472 [6:22:53<13:31:43,  3.22it/s]
 58%|█████▊    | 214524/371472 [6:22:54<13:05:04,  3.33it/s]
 58%|█████▊    | 214525/371472 [6:22:54<13:27:21,  3.24it/s]
 58%|█████▊    | 214526/371472 [6:22:54<13:36:44,  3.20it/s]
 58%|█████▊    | 214527/371472 [6:22:54<13:43:48,  3.18it/s]
 58%|█████▊    | 214528/371472 [6:22:55<14:08:21,  3.08it/s]
 58%|█████▊    | 214529/371472 [6:22:55<14:18:04,  3.05it/s]
 58%|█████▊    | 214530/371472 [6:22:55<14:01:29,  3.11it/s]
 58%|█████▊    | 214531/371472 [6:22:56<14:11:38,  3.07it/s]
 58%|█████▊    | 214532/371472 [6:22:56<13:37:20,  3.20it/s]
 58%|█████▊    | 214533/371472 [6:22:56<13:57:31,  3.12it/s]
 58%|█████▊    | 214534/371472 [6:22:57<13:24:36,  3.25it/s]
 58%|█████▊    | 214535/371472 [6:22:57<13:51:46,  3.14it/s]
 58%|█████▊    | 214536/371472 [6:22:57<14:13:01,  3.07it/s]
 58%|█████▊    | 214537/371472 [6:22:58<13:42:10,  3.18it/s]
 58%|█████▊    | 214538/371472 [6:22:58<13:30:15,  3.23it/s]
 58%|█████▊    | 214539/371472 [6:22:58<13:08:49,  3.32it/s]
 58%|█████▊    | 214540/371472 [6:22:59<13:47:57,  3.16it/s]
                                                            
{'loss': 2.5828, 'learning_rate': 4.804186687926912e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214540/371472 [6:22:59<13:47:57,  3.16it/s]
 58%|█████▊    | 214541/371472 [6:22:59<13:04:01,  3.34it/s]
 58%|█████▊    | 214542/371472 [6:22:59<13:13:09,  3.30it/s]
 58%|█████▊    | 214543/371472 [6:23:00<13:29:04,  3.23it/s]
 58%|█████▊    | 214544/371472 [6:23:00<13:10:12,  3.31it/s]
 58%|█████▊    | 214545/371472 [6:23:00<13:43:39,  3.18it/s]
 58%|█████▊    | 214546/371472 [6:23:00<13:29:35,  3.23it/s]
 58%|█████▊    | 214547/371472 [6:23:01<14:24:36,  3.02it/s]
 58%|█████▊    | 214548/371472 [6:23:01<13:37:25,  3.20it/s]
 58%|█████▊    | 214549/371472 [6:23:01<13:19:57,  3.27it/s]
 58%|█████▊    | 214550/371472 [6:23:02<13:09:07,  3.31it/s]
 58%|█████▊    | 214551/371472 [6:23:02<13:41:42,  3.18it/s]
 58%|█████▊    | 214552/371472 [6:23:02<13:39:28,  3.19it/s]
 58%|█████▊    | 214553/371472 [6:23:03<13:21:30,  3.26it/s]
 58%|█████▊    | 214554/371472 [6:23:03<13:27:43,  3.24it/s]
 58%|█████▊    | 214555/371472 [6:23:03<12:51:26,  3.39it/s]
 58%|█████▊    | 214556/371472 [6:23:04<13:00:29,  3.35it/s]
 58%|█████▊    | 214557/371472 [6:23:04<13:16:36,  3.28it/s]
 58%|█████▊    | 214558/371472 [6:23:04<14:04:20,  3.10it/s]
 58%|█████▊    | 214559/371472 [6:23:05<14:17:49,  3.05it/s]
 58%|█████▊    | 214560/371472 [6:23:05<13:46:50,  3.16it/s]
                                                            
{'loss': 2.7707, 'learning_rate': 4.803701868172121e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214560/371472 [6:23:05<13:46:50,  3.16it/s]
 58%|█████▊    | 214561/371472 [6:23:05<13:32:57,  3.22it/s]
 58%|█████▊    | 214562/371472 [6:23:05<13:03:31,  3.34it/s]
 58%|█████▊    | 214563/371472 [6:23:06<13:09:16,  3.31it/s]
 58%|█████▊    | 214564/371472 [6:23:06<13:21:35,  3.26it/s]
 58%|█████▊    | 214565/371472 [6:23:06<13:18:00,  3.28it/s]
 58%|█████▊    | 214566/371472 [6:23:07<12:59:39,  3.35it/s]
 58%|█████▊    | 214567/371472 [6:23:07<12:36:04,  3.46it/s]
 58%|█████▊    | 214568/371472 [6:23:07<12:36:49,  3.46it/s]
 58%|█████▊    | 214569/371472 [6:23:08<13:31:32,  3.22it/s]
 58%|█████▊    | 214570/371472 [6:23:08<13:22:52,  3.26it/s]
 58%|█████▊    | 214571/371472 [6:23:08<13:03:02,  3.34it/s]
 58%|█████▊    | 214572/371472 [6:23:08<12:54:26,  3.38it/s]
 58%|█████▊    | 214573/371472 [6:23:09<13:26:46,  3.24it/s]
 58%|█████▊    | 214574/371472 [6:23:09<13:00:09,  3.35it/s]
 58%|█████▊    | 214575/371472 [6:23:09<13:34:14,  3.21it/s]
 58%|█████▊    | 214576/371472 [6:23:10<13:06:54,  3.32it/s]
 58%|█████▊    | 214577/371472 [6:23:10<12:50:18,  3.39it/s]
 58%|█████▊    | 214578/371472 [6:23:10<13:16:42,  3.28it/s]
 58%|█████▊    | 214579/371472 [6:23:11<14:00:43,  3.11it/s]
 58%|█████▊    | 214580/371472 [6:23:11<13:31:37,  3.22it/s]
                                                            
{'loss': 2.7082, 'learning_rate': 4.803217048417333e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214580/371472 [6:23:11<13:31:37,  3.22it/s]
 58%|█████▊    | 214581/371472 [6:23:11<13:13:16,  3.30it/s]
 58%|█████▊    | 214582/371472 [6:23:11<12:58:28,  3.36it/s]
 58%|█████▊    | 214583/371472 [6:23:12<12:53:16,  3.38it/s]
 58%|█████▊    | 214584/371472 [6:23:12<12:36:38,  3.46it/s]
 58%|█████▊    | 214585/371472 [6:23:12<12:44:19,  3.42it/s]
 58%|█████▊    | 214586/371472 [6:23:13<12:52:48,  3.38it/s]
 58%|█████▊    | 214587/371472 [6:23:13<13:01:41,  3.34it/s]
 58%|█████▊    | 214588/371472 [6:23:13<13:15:18,  3.29it/s]
 58%|█████▊    | 214589/371472 [6:23:14<12:55:20,  3.37it/s]
 58%|█████▊    | 214590/371472 [6:23:14<12:54:44,  3.37it/s]
 58%|█████▊    | 214591/371472 [6:23:14<12:40:00,  3.44it/s]
 58%|█████▊    | 214592/371472 [6:23:14<12:18:07,  3.54it/s]
 58%|█████▊    | 214593/371472 [6:23:15<12:16:53,  3.55it/s]
 58%|█████▊    | 214594/371472 [6:23:15<12:53:54,  3.38it/s]
 58%|█████▊    | 214595/371472 [6:23:15<12:49:41,  3.40it/s]
 58%|█████▊    | 214596/371472 [6:23:16<13:27:41,  3.24it/s]
 58%|█████▊    | 214597/371472 [6:23:16<12:50:34,  3.39it/s]
 58%|█████▊    | 214598/371472 [6:23:16<12:44:39,  3.42it/s]
 58%|█████▊    | 214599/371472 [6:23:17<13:38:51,  3.19it/s]
 58%|█████▊    | 214600/371472 [6:23:17<13:20:00,  3.27it/s]
                                                            
{'loss': 2.9447, 'learning_rate': 4.802732228662544e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214600/371472 [6:23:17<13:20:00,  3.27it/s]
 58%|█████▊    | 214601/371472 [6:23:17<14:10:23,  3.07it/s]
 58%|█████▊    | 214602/371472 [6:23:17<13:42:43,  3.18it/s]
 58%|█████▊    | 214603/371472 [6:23:18<14:06:50,  3.09it/s]
 58%|█████▊    | 214604/371472 [6:23:18<13:38:33,  3.19it/s]
 58%|█████▊    | 214605/371472 [6:23:18<13:09:31,  3.31it/s]
 58%|█████▊    | 214606/371472 [6:23:19<12:55:49,  3.37it/s]
 58%|█████▊    | 214607/371472 [6:23:19<12:42:10,  3.43it/s]
 58%|█████▊    | 214608/371472 [6:23:19<12:27:31,  3.50it/s]
 58%|█████▊    | 214609/371472 [6:23:19<12:20:26,  3.53it/s]
 58%|█████▊    | 214610/371472 [6:23:20<12:11:00,  3.58it/s]
 58%|█████▊    | 214611/371472 [6:23:20<12:58:22,  3.36it/s]
 58%|█████▊    | 214612/371472 [6:23:20<12:45:20,  3.42it/s]
 58%|█████▊    | 214613/371472 [6:23:21<13:40:28,  3.19it/s]
 58%|█████▊    | 214614/371472 [6:23:21<13:22:18,  3.26it/s]
 58%|█████▊    | 214615/371472 [6:23:21<12:42:17,  3.43it/s]
 58%|█████▊    | 214616/371472 [6:23:22<12:29:28,  3.49it/s]
 58%|█████▊    | 214617/371472 [6:23:22<12:34:48,  3.46it/s]
 58%|█████▊    | 214618/371472 [6:23:22<12:21:46,  3.52it/s]
 58%|█████▊    | 214619/371472 [6:23:22<12:41:14,  3.43it/s]
 58%|█████▊    | 214620/371472 [6:23:23<12:45:52,  3.41it/s]
                                                            
{'loss': 2.8645, 'learning_rate': 4.802247408907755e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214620/371472 [6:23:23<12:45:52,  3.41it/s]
 58%|█████▊    | 214621/371472 [6:23:23<12:37:24,  3.45it/s]
 58%|█████▊    | 214622/371472 [6:23:23<12:38:03,  3.45it/s]
 58%|█████▊    | 214623/371472 [6:23:24<12:16:05,  3.55it/s]
 58%|█████▊    | 214624/371472 [6:23:24<11:55:08,  3.66it/s]
 58%|█████▊    | 214625/371472 [6:23:24<12:41:22,  3.43it/s]
 58%|█████▊    | 214626/371472 [6:23:24<12:44:46,  3.42it/s]
 58%|█████▊    | 214627/371472 [6:23:25<12:49:03,  3.40it/s]
 58%|█████▊    | 214628/371472 [6:23:25<13:24:30,  3.25it/s]
 58%|█████▊    | 214629/371472 [6:23:25<13:18:13,  3.27it/s]
 58%|█████▊    | 214630/371472 [6:23:26<13:18:09,  3.28it/s]
 58%|█████▊    | 214631/371472 [6:23:26<13:03:00,  3.34it/s]
 58%|█████▊    | 214632/371472 [6:23:26<13:33:58,  3.21it/s]
 58%|█████▊    | 214633/371472 [6:23:27<13:19:47,  3.27it/s]
 58%|█████▊    | 214634/371472 [6:23:27<12:55:08,  3.37it/s]
 58%|█████▊    | 214635/371472 [6:23:27<13:05:17,  3.33it/s]
 58%|█████▊    | 214636/371472 [6:23:28<13:43:03,  3.18it/s]
 58%|█████▊    | 214637/371472 [6:23:28<13:19:32,  3.27it/s]
 58%|█████▊    | 214638/371472 [6:23:28<13:22:13,  3.26it/s]
 58%|█████▊    | 214639/371472 [6:23:28<12:49:03,  3.40it/s]
 58%|█████▊    | 214640/371472 [6:23:29<12:47:42,  3.40it/s]
                                                            
{'loss': 2.7345, 'learning_rate': 4.801762589152965e-07, 'epoch': 9.24}
+
 58%|█████▊    | 214640/371472 [6:23:29<12:47:42,  3.40it/s]
 58%|█████▊    | 214641/371472 [6:23:29<12:32:03,  3.48it/s]
 58%|█████▊    | 214642/371472 [6:23:29<12:14:36,  3.56it/s]
 58%|█████▊    | 214643/371472 [6:23:29<11:58:13,  3.64it/s]
 58%|█████▊    | 214644/371472 [6:23:30<11:49:59,  3.68it/s]
 58%|█████▊    | 214645/371472 [6:23:30<12:56:45,  3.36it/s]
 58%|█████▊    | 214646/371472 [6:23:30<12:53:16,  3.38it/s]
 58%|█████▊    | 214647/371472 [6:23:31<12:45:54,  3.41it/s]
 58%|█████▊    | 214648/371472 [6:23:31<12:30:43,  3.48it/s]
 58%|█████▊    | 214649/371472 [6:23:31<12:30:01,  3.48it/s]
 58%|█████▊    | 214650/371472 [6:23:32<12:31:01,  3.48it/s]
 58%|█████▊    | 214651/371472 [6:23:32<12:21:32,  3.52it/s]
 58%|█████▊    | 214652/371472 [6:23:32<12:06:26,  3.60it/s]
 58%|█████▊    | 214653/371472 [6:23:32<12:18:11,  3.54it/s]
 58%|█████▊    | 214654/371472 [6:23:33<12:36:10,  3.46it/s]
 58%|█████▊    | 214655/371472 [6:23:33<12:28:05,  3.49it/s]
 58%|█████▊    | 214656/371472 [6:23:33<15:40:55,  2.78it/s]
 58%|█████▊    | 214657/371472 [6:23:34<15:34:49,  2.80it/s]
 58%|█████▊    | 214658/371472 [6:23:34<14:40:53,  2.97it/s]
 58%|█████▊    | 214659/371472 [6:23:34<13:39:06,  3.19it/s]
 58%|█████▊    | 214660/371472 [6:23:35<13:15:28,  3.29it/s]
                                                            
{'loss': 2.9838, 'learning_rate': 4.801277769398176e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214660/371472 [6:23:35<13:15:28,  3.29it/s]
 58%|█████▊    | 214661/371472 [6:23:35<13:25:40,  3.24it/s]
 58%|█████▊    | 214662/371472 [6:23:35<14:15:54,  3.05it/s]
 58%|█████▊    | 214663/371472 [6:23:36<13:30:24,  3.22it/s]
 58%|█████▊    | 214664/371472 [6:23:36<12:51:27,  3.39it/s]
 58%|█████▊    | 214665/371472 [6:23:36<12:45:04,  3.42it/s]
 58%|█████▊    | 214666/371472 [6:23:36<12:54:42,  3.37it/s]
 58%|█████▊    | 214667/371472 [6:23:37<12:32:45,  3.47it/s]
 58%|█████▊    | 214668/371472 [6:23:37<12:38:41,  3.44it/s]
 58%|█████▊    | 214669/371472 [6:23:37<13:35:15,  3.21it/s]
 58%|█████▊    | 214670/371472 [6:23:38<13:18:13,  3.27it/s]
 58%|█████▊    | 214671/371472 [6:23:38<12:41:51,  3.43it/s]
 58%|█████▊    | 214672/371472 [6:23:38<13:09:14,  3.31it/s]
 58%|█████▊    | 214673/371472 [6:23:39<12:47:16,  3.41it/s]
 58%|█████▊    | 214674/371472 [6:23:39<12:38:46,  3.44it/s]
 58%|█████▊    | 214675/371472 [6:23:39<13:22:50,  3.26it/s]
 58%|█████▊    | 214676/371472 [6:23:39<12:55:34,  3.37it/s]
 58%|█████▊    | 214677/371472 [6:23:40<13:14:10,  3.29it/s]
 58%|█████▊    | 214678/371472 [6:23:40<12:46:41,  3.41it/s]
 58%|█████▊    | 214679/371472 [6:23:40<13:18:32,  3.27it/s]
 58%|█████▊    | 214680/371472 [6:23:41<12:54:49,  3.37it/s]
                                                            
{'loss': 2.7544, 'learning_rate': 4.800792949643388e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214680/371472 [6:23:41<12:54:49,  3.37it/s]
 58%|█████▊    | 214681/371472 [6:23:41<13:11:28,  3.30it/s]
 58%|█████▊    | 214682/371472 [6:23:41<13:59:38,  3.11it/s]
 58%|█████▊    | 214683/371472 [6:23:42<13:47:20,  3.16it/s]
 58%|█████▊    | 214684/371472 [6:23:42<13:28:22,  3.23it/s]
 58%|█████▊    | 214685/371472 [6:23:42<13:04:07,  3.33it/s]
 58%|█████▊    | 214686/371472 [6:23:42<12:38:22,  3.45it/s]
 58%|█████▊    | 214687/371472 [6:23:43<12:16:17,  3.55it/s]
 58%|█████▊    | 214688/371472 [6:23:43<12:16:15,  3.55it/s]
 58%|█████▊    | 214689/371472 [6:23:43<12:05:49,  3.60it/s]
 58%|█████▊    | 214690/371472 [6:23:44<12:28:41,  3.49it/s]
 58%|█████▊    | 214691/371472 [6:23:44<12:38:27,  3.45it/s]
 58%|█████▊    | 214692/371472 [6:23:44<12:31:13,  3.48it/s]
 58%|█████▊    | 214693/371472 [6:23:45<13:30:18,  3.22it/s]
 58%|█████▊    | 214694/371472 [6:23:45<13:40:22,  3.19it/s]
 58%|█████▊    | 214695/371472 [6:23:45<13:26:34,  3.24it/s]
 58%|█████▊    | 214696/371472 [6:23:45<13:03:31,  3.33it/s]
 58%|█████▊    | 214697/371472 [6:23:46<12:59:16,  3.35it/s]
 58%|█████▊    | 214698/371472 [6:23:46<12:51:38,  3.39it/s]
 58%|█████▊    | 214699/371472 [6:23:46<13:27:47,  3.23it/s]
 58%|█████▊    | 214700/371472 [6:23:47<13:23:26,  3.25it/s]
                                                            
{'loss': 2.6974, 'learning_rate': 4.800308129888599e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214700/371472 [6:23:47<13:23:26,  3.25it/s]
 58%|█████▊    | 214701/371472 [6:23:47<13:36:54,  3.20it/s]
 58%|█████▊    | 214702/371472 [6:23:47<13:02:14,  3.34it/s]
 58%|█████▊    | 214703/371472 [6:23:48<13:25:01,  3.25it/s]
 58%|█████▊    | 214704/371472 [6:23:48<13:06:32,  3.32it/s]
 58%|█████▊    | 214705/371472 [6:23:48<12:40:39,  3.43it/s]
 58%|█████▊    | 214706/371472 [6:23:48<12:25:52,  3.50it/s]
 58%|█████▊    | 214707/371472 [6:23:49<12:47:12,  3.41it/s]
 58%|█████▊    | 214708/371472 [6:23:49<13:02:54,  3.34it/s]
 58%|█████▊    | 214709/371472 [6:23:49<12:31:51,  3.48it/s]
 58%|█████▊    | 214710/371472 [6:23:50<13:19:54,  3.27it/s]
 58%|█████▊    | 214711/371472 [6:23:50<12:42:02,  3.43it/s]
 58%|█████▊    | 214712/371472 [6:23:50<12:44:16,  3.42it/s]
 58%|█████▊    | 214713/371472 [6:23:51<12:48:48,  3.40it/s]
 58%|█████▊    | 214714/371472 [6:23:51<13:36:15,  3.20it/s]
 58%|█████▊    | 214715/371472 [6:23:51<15:01:40,  2.90it/s]
 58%|█████▊    | 214716/371472 [6:23:52<14:33:50,  2.99it/s]
 58%|█████▊    | 214717/371472 [6:23:52<13:58:35,  3.12it/s]
 58%|█████▊    | 214718/371472 [6:23:52<13:16:15,  3.28it/s]
 58%|█████▊    | 214719/371472 [6:23:52<13:00:47,  3.35it/s]
 58%|█████▊    | 214720/371472 [6:23:53<12:56:57,  3.36it/s]
                                                            
{'loss': 2.7511, 'learning_rate': 4.79982331013381e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214720/371472 [6:23:53<12:56:57,  3.36it/s]
 58%|█████▊    | 214721/371472 [6:23:53<12:49:25,  3.40it/s]
 58%|█████▊    | 214722/371472 [6:23:53<12:32:50,  3.47it/s]
 58%|█████▊    | 214723/371472 [6:23:54<12:23:11,  3.52it/s]
 58%|█████▊    | 214724/371472 [6:23:54<12:07:54,  3.59it/s]
 58%|█████▊    | 214725/371472 [6:23:54<12:09:58,  3.58it/s]
 58%|█████▊    | 214726/371472 [6:23:54<12:15:36,  3.55it/s]
 58%|█████▊    | 214727/371472 [6:23:55<12:48:13,  3.40it/s]
 58%|█████▊    | 214728/371472 [6:23:55<12:34:35,  3.46it/s]
 58%|█████▊    | 214729/371472 [6:23:55<13:10:09,  3.31it/s]
 58%|█████▊    | 214730/371472 [6:23:56<13:29:22,  3.23it/s]
 58%|█████▊    | 214731/371472 [6:23:56<12:57:04,  3.36it/s]
 58%|█████▊    | 214732/371472 [6:23:56<13:34:02,  3.21it/s]
 58%|█████▊    | 214733/371472 [6:23:57<13:37:07,  3.20it/s]
 58%|█████▊    | 214734/371472 [6:23:57<13:11:05,  3.30it/s]
 58%|█████▊    | 214735/371472 [6:23:57<12:44:41,  3.42it/s]
 58%|█████▊    | 214736/371472 [6:23:57<13:32:14,  3.22it/s]
 58%|█████▊    | 214737/371472 [6:23:58<12:58:42,  3.35it/s]
 58%|█████▊    | 214738/371472 [6:23:58<13:07:44,  3.32it/s]
 58%|█████▊    | 214739/371472 [6:23:58<13:14:18,  3.29it/s]
 58%|█████▊    | 214740/371472 [6:23:59<12:56:12,  3.37it/s]
                                                            
{'loss': 2.8622, 'learning_rate': 4.799338490379021e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214740/371472 [6:23:59<12:56:12,  3.37it/s]
 58%|█████▊    | 214741/371472 [6:23:59<13:00:57,  3.34it/s]
 58%|█████▊    | 214742/371472 [6:23:59<12:44:14,  3.42it/s]
 58%|█████▊    | 214743/371472 [6:24:00<12:36:25,  3.45it/s]
 58%|█████▊    | 214744/371472 [6:24:00<12:35:14,  3.46it/s]
 58%|█████▊    | 214745/371472 [6:24:00<12:23:52,  3.51it/s]
 58%|█████▊    | 214746/371472 [6:24:00<12:34:41,  3.46it/s]
 58%|█████▊    | 214747/371472 [6:24:01<12:44:53,  3.42it/s]
 58%|█████▊    | 214748/371472 [6:24:01<12:20:09,  3.53it/s]
 58%|█████▊    | 214749/371472 [6:24:01<11:58:49,  3.63it/s]
 58%|█████▊    | 214750/371472 [6:24:02<13:20:24,  3.26it/s]
 58%|█████▊    | 214751/371472 [6:24:02<14:11:10,  3.07it/s]
 58%|█████▊    | 214752/371472 [6:24:02<14:49:24,  2.94it/s]
 58%|█████▊    | 214753/371472 [6:24:03<14:06:44,  3.08it/s]
 58%|█████▊    | 214754/371472 [6:24:03<13:26:18,  3.24it/s]
 58%|█████▊    | 214755/371472 [6:24:03<13:15:14,  3.28it/s]
 58%|█████▊    | 214756/371472 [6:24:03<12:53:58,  3.37it/s]
 58%|█████▊    | 214757/371472 [6:24:04<13:03:05,  3.34it/s]
 58%|█████▊    | 214758/371472 [6:24:04<13:53:29,  3.13it/s]
 58%|█████▊    | 214759/371472 [6:24:04<13:35:02,  3.20it/s]
 58%|█████▊    | 214760/371472 [6:24:05<14:24:10,  3.02it/s]
                                                            
{'loss': 2.8547, 'learning_rate': 4.798853670624232e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214760/371472 [6:24:05<14:24:10,  3.02it/s]
 58%|█████▊    | 214761/371472 [6:24:05<14:02:34,  3.10it/s]
 58%|█████▊    | 214762/371472 [6:24:05<13:59:37,  3.11it/s]
 58%|█████▊    | 214763/371472 [6:24:06<14:01:04,  3.11it/s]
 58%|█████▊    | 214764/371472 [6:24:06<14:19:53,  3.04it/s]
 58%|█████▊    | 214765/371472 [6:24:06<13:46:22,  3.16it/s]
 58%|█████▊    | 214766/371472 [6:24:07<13:20:57,  3.26it/s]
 58%|█████▊    | 214767/371472 [6:24:07<13:00:16,  3.35it/s]
 58%|█████▊    | 214768/371472 [6:24:07<13:23:38,  3.25it/s]
 58%|█████▊    | 214769/371472 [6:24:08<13:29:54,  3.22it/s]
 58%|█████▊    | 214770/371472 [6:24:08<13:19:00,  3.27it/s]
 58%|█████▊    | 214771/371472 [6:24:08<14:03:25,  3.10it/s]
 58%|█████▊    | 214772/371472 [6:24:09<15:27:51,  2.81it/s]
 58%|█████▊    | 214773/371472 [6:24:09<14:22:50,  3.03it/s]
 58%|█████▊    | 214774/371472 [6:24:09<14:25:28,  3.02it/s]
 58%|█████▊    | 214775/371472 [6:24:10<13:55:49,  3.12it/s]
 58%|█████▊    | 214776/371472 [6:24:10<13:54:34,  3.13it/s]
 58%|█████▊    | 214777/371472 [6:24:10<13:17:56,  3.27it/s]
 58%|█████▊    | 214778/371472 [6:24:10<13:12:38,  3.29it/s]
 58%|█████▊    | 214779/371472 [6:24:11<13:02:31,  3.34it/s]
 58%|█████▊    | 214780/371472 [6:24:11<12:56:22,  3.36it/s]
                                                            
{'loss': 2.8388, 'learning_rate': 4.798368850869442e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214780/371472 [6:24:11<12:56:22,  3.36it/s]
 58%|█████▊    | 214781/371472 [6:24:11<13:13:28,  3.29it/s]
 58%|█████▊    | 214782/371472 [6:24:12<12:51:51,  3.38it/s]
 58%|█████▊    | 214783/371472 [6:24:12<12:52:08,  3.38it/s]
 58%|█████▊    | 214784/371472 [6:24:12<13:00:10,  3.35it/s]
 58%|█████▊    | 214785/371472 [6:24:13<12:36:30,  3.45it/s]
 58%|█████▊    | 214786/371472 [6:24:13<12:37:34,  3.45it/s]
 58%|█████▊    | 214787/371472 [6:24:13<12:22:04,  3.52it/s]
 58%|█████▊    | 214788/371472 [6:24:13<12:48:41,  3.40it/s]
 58%|█████▊    | 214789/371472 [6:24:14<12:35:32,  3.46it/s]
 58%|█████▊    | 214790/371472 [6:24:14<12:25:57,  3.50it/s]
 58%|█████▊    | 214791/371472 [6:24:14<12:24:27,  3.51it/s]
 58%|█████▊    | 214792/371472 [6:24:15<12:29:21,  3.48it/s]
 58%|█████▊    | 214793/371472 [6:24:15<12:35:36,  3.46it/s]
 58%|█████▊    | 214794/371472 [6:24:15<12:27:39,  3.49it/s]
 58%|█████▊    | 214795/371472 [6:24:15<12:23:28,  3.51it/s]
 58%|█████▊    | 214796/371472 [6:24:16<12:22:34,  3.52it/s]
 58%|█████▊    | 214797/371472 [6:24:16<12:32:02,  3.47it/s]
 58%|█████▊    | 214798/371472 [6:24:16<12:40:42,  3.43it/s]
 58%|█████▊    | 214799/371472 [6:24:17<12:46:46,  3.41it/s]
 58%|█████▊    | 214800/371472 [6:24:17<14:14:28,  3.06it/s]
                                                            
{'loss': 2.7055, 'learning_rate': 4.797884031114654e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214800/371472 [6:24:17<14:14:28,  3.06it/s]
 58%|█████▊    | 214801/371472 [6:24:17<13:52:21,  3.14it/s]
 58%|█████▊    | 214802/371472 [6:24:18<13:46:25,  3.16it/s]
 58%|█████▊    | 214803/371472 [6:24:18<13:24:29,  3.25it/s]
 58%|█████▊    | 214804/371472 [6:24:18<14:15:16,  3.05it/s]
 58%|█████▊    | 214805/371472 [6:24:19<13:51:32,  3.14it/s]
 58%|█████▊    | 214806/371472 [6:24:19<13:19:37,  3.27it/s]
 58%|█████▊    | 214807/371472 [6:24:19<13:22:03,  3.26it/s]
 58%|█████▊    | 214808/371472 [6:24:19<13:52:01,  3.14it/s]
 58%|█████▊    | 214809/371472 [6:24:20<14:01:20,  3.10it/s]
 58%|█████▊    | 214810/371472 [6:24:20<13:25:01,  3.24it/s]
 58%|█████▊    | 214811/371472 [6:24:20<13:22:35,  3.25it/s]
 58%|█████▊    | 214812/371472 [6:24:21<13:25:33,  3.24it/s]
 58%|█████▊    | 214813/371472 [6:24:21<13:05:17,  3.32it/s]
 58%|█████▊    | 214814/371472 [6:24:21<12:34:28,  3.46it/s]
 58%|█████▊    | 214815/371472 [6:24:22<12:39:46,  3.44it/s]
 58%|█████▊    | 214816/371472 [6:24:22<12:42:59,  3.42it/s]
 58%|█████▊    | 214817/371472 [6:24:22<12:41:48,  3.43it/s]
 58%|█████▊    | 214818/371472 [6:24:22<12:33:51,  3.46it/s]
 58%|█████▊    | 214819/371472 [6:24:23<12:44:26,  3.42it/s]
 58%|█████▊    | 214820/371472 [6:24:23<12:20:47,  3.52it/s]
                                                            
{'loss': 2.8674, 'learning_rate': 4.797399211359865e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214820/371472 [6:24:23<12:20:47,  3.52it/s]
 58%|█████▊    | 214821/371472 [6:24:23<12:18:57,  3.53it/s]
 58%|█████▊    | 214822/371472 [6:24:24<12:20:29,  3.53it/s]
 58%|█████▊    | 214823/371472 [6:24:24<13:09:07,  3.31it/s]
 58%|█████▊    | 214824/371472 [6:24:24<12:48:38,  3.40it/s]
 58%|█████▊    | 214825/371472 [6:24:24<12:19:43,  3.53it/s]
 58%|█████▊    | 214826/371472 [6:24:25<12:36:48,  3.45it/s]
 58%|█████▊    | 214827/371472 [6:24:25<12:13:33,  3.56it/s]
 58%|█████▊    | 214828/371472 [6:24:25<12:16:38,  3.54it/s]
 58%|█████▊    | 214829/371472 [6:24:26<13:21:54,  3.26it/s]
 58%|█████▊    | 214830/371472 [6:24:26<13:07:36,  3.31it/s]
 58%|█████▊    | 214831/371472 [6:24:26<12:53:30,  3.38it/s]
 58%|█████▊    | 214832/371472 [6:24:26<12:43:44,  3.42it/s]
 58%|█████▊    | 214833/371472 [6:24:27<12:37:14,  3.45it/s]
 58%|█████▊    | 214834/371472 [6:24:27<12:43:42,  3.42it/s]
 58%|█████▊    | 214835/371472 [6:24:27<12:42:10,  3.43it/s]
 58%|█████▊    | 214836/371472 [6:24:28<13:07:52,  3.31it/s]
 58%|█████▊    | 214837/371472 [6:24:28<13:35:02,  3.20it/s]
 58%|█████▊    | 214838/371472 [6:24:28<13:37:31,  3.19it/s]
 58%|█████▊    | 214839/371472 [6:24:29<13:11:28,  3.30it/s]
 58%|█████▊    | 214840/371472 [6:24:29<13:20:24,  3.26it/s]
                                                            
{'loss': 2.7443, 'learning_rate': 4.796914391605077e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214840/371472 [6:24:29<13:20:24,  3.26it/s]
 58%|█████▊    | 214841/371472 [6:24:29<13:12:36,  3.29it/s]
 58%|█████▊    | 214842/371472 [6:24:30<14:12:04,  3.06it/s]
 58%|█████▊    | 214843/371472 [6:24:30<13:34:53,  3.20it/s]
 58%|█████▊    | 214844/371472 [6:24:30<13:02:33,  3.34it/s]
 58%|█████▊    | 214845/371472 [6:24:30<12:42:37,  3.42it/s]
 58%|█████▊    | 214846/371472 [6:24:31<12:32:58,  3.47it/s]
 58%|█████▊    | 214847/371472 [6:24:31<12:34:58,  3.46it/s]
 58%|█████▊    | 214848/371472 [6:24:31<14:59:09,  2.90it/s]
 58%|█████▊    | 214849/371472 [6:24:32<13:58:40,  3.11it/s]
 58%|█████▊    | 214850/371472 [6:24:32<13:39:46,  3.18it/s]
 58%|█████▊    | 214851/371472 [6:24:32<13:12:39,  3.29it/s]
 58%|█████▊    | 214852/371472 [6:24:33<13:04:42,  3.33it/s]
 58%|█████▊    | 214853/371472 [6:24:33<12:47:35,  3.40it/s]
 58%|█████▊    | 214854/371472 [6:24:33<13:30:49,  3.22it/s]
 58%|█████▊    | 214855/371472 [6:24:34<13:46:19,  3.16it/s]
 58%|█████▊    | 214856/371472 [6:24:34<13:43:51,  3.17it/s]
 58%|█████▊    | 214857/371472 [6:24:34<13:43:11,  3.17it/s]
 58%|█████▊    | 214858/371472 [6:24:34<13:03:46,  3.33it/s]
 58%|█████▊    | 214859/371472 [6:24:35<13:12:34,  3.29it/s]
 58%|█████▊    | 214860/371472 [6:24:35<12:46:01,  3.41it/s]
                                                            
{'loss': 2.7057, 'learning_rate': 4.796429571850287e-07, 'epoch': 9.25}
+
 58%|█████▊    | 214860/371472 [6:24:35<12:46:01,  3.41it/s]
 58%|█████▊    | 214861/371472 [6:24:35<12:50:58,  3.39it/s]
 58%|█████▊    | 214862/371472 [6:24:36<14:08:02,  3.08it/s]
 58%|█████▊    | 214863/371472 [6:24:36<13:26:50,  3.23it/s]
 58%|█████▊    | 214864/371472 [6:24:36<13:24:32,  3.24it/s]
 58%|█████▊    | 214865/371472 [6:24:37<13:16:17,  3.28it/s]
 58%|█████▊    | 214866/371472 [6:24:37<13:29:51,  3.22it/s]
 58%|█████▊    | 214867/371472 [6:24:37<13:25:07,  3.24it/s]
 58%|█████▊    | 214868/371472 [6:24:38<13:27:41,  3.23it/s]
 58%|█████▊    | 214869/371472 [6:24:38<13:18:22,  3.27it/s]
 58%|█████▊    | 214870/371472 [6:24:38<12:49:44,  3.39it/s]
 58%|█████▊    | 214871/371472 [6:24:38<13:06:01,  3.32it/s]
 58%|█████▊    | 214872/371472 [6:24:39<13:11:30,  3.30it/s]
 58%|█████▊    | 214873/371472 [6:24:39<13:10:48,  3.30it/s]
 58%|█████▊    | 214874/371472 [6:24:39<12:45:18,  3.41it/s]
 58%|█████▊    | 214875/371472 [6:24:40<12:37:13,  3.45it/s]
 58%|█████▊    | 214876/371472 [6:24:40<12:32:31,  3.47it/s]
 58%|█████▊    | 214877/371472 [6:24:40<12:16:47,  3.54it/s]
 58%|█████▊    | 214878/371472 [6:24:40<12:22:32,  3.51it/s]
 58%|█████▊    | 214879/371472 [6:24:41<13:00:38,  3.34it/s]
 58%|█████▊    | 214880/371472 [6:24:41<12:39:10,  3.44it/s]
                                                            
{'loss': 2.8693, 'learning_rate': 4.795944752095498e-07, 'epoch': 9.26}
+
 58%|█████▊    | 214880/371472 [6:24:41<12:39:10,  3.44it/s]
 58%|█████▊    | 214881/371472 [6:24:41<12:15:46,  3.55it/s]
 58%|█████▊    | 214882/371472 [6:24:42<13:07:52,  3.31it/s]
 58%|█████▊    | 214883/371472 [6:24:42<12:53:09,  3.38it/s]
 58%|█████▊    | 214884/371472 [6:24:42<13:09:15,  3.31it/s]
 58%|█████▊    | 214885/371472 [6:24:43<12:51:09,  3.38it/s]
 58%|█████▊    | 214886/371472 [6:24:43<16:13:05,  2.68it/s]
 58%|█████▊    | 214887/371472 [6:24:43<14:48:14,  2.94it/s]
 58%|█████▊    | 214888/371472 [6:24:44<14:16:13,  3.05it/s]
 58%|█████▊    | 214889/371472 [6:24:44<13:49:30,  3.15it/s]
 58%|█████▊    | 214890/371472 [6:24:44<13:15:56,  3.28it/s]
 58%|█████▊    | 214891/371472 [6:24:45<13:08:08,  3.31it/s]
 58%|█████▊    | 214892/371472 [6:24:45<12:53:27,  3.37it/s]
 58%|█████▊    | 214893/371472 [6:24:45<13:17:38,  3.27it/s]
 58%|█████▊    | 214894/371472 [6:24:45<13:02:39,  3.33it/s]
 58%|█████▊    | 214895/371472 [6:24:46<13:20:12,  3.26it/s]
 58%|█████▊    | 214896/371472 [6:24:46<12:52:09,  3.38it/s]
 58%|█████▊    | 214897/371472 [6:24:46<13:23:24,  3.25it/s]
 58%|█████▊    | 214898/371472 [6:24:47<12:54:53,  3.37it/s]
 58%|█████▊    | 214899/371472 [6:24:47<12:30:16,  3.48it/s]
 58%|█████▊    | 214900/371472 [6:24:47<12:47:15,  3.40it/s]
                                                            
{'loss': 2.9006, 'learning_rate': 4.795459932340709e-07, 'epoch': 9.26}
+
 58%|█████▊    | 214900/371472 [6:24:47<12:47:15,  3.40it/s]
 58%|█████▊    | 214901/371472 [6:24:47<13:01:53,  3.34it/s]
 58%|█████▊    | 214902/371472 [6:24:48<13:09:09,  3.31it/s]
 58%|█████▊    | 214903/371472 [6:24:48<13:36:21,  3.20it/s]
 58%|█████▊    | 214904/371472 [6:24:48<13:00:18,  3.34it/s]
 58%|█████▊    | 214905/371472 [6:24:49<12:56:28,  3.36it/s]
 58%|█████▊    | 214906/371472 [6:24:49<12:39:58,  3.43it/s]
 58%|█████▊    | 214907/371472 [6:24:49<12:39:23,  3.44it/s]
 58%|█████▊    | 214908/371472 [6:24:50<12:19:36,  3.53it/s]
 58%|█████▊    | 214909/371472 [6:24:50<12:27:55,  3.49it/s]
 58%|█████▊    | 214910/371472 [6:24:50<13:06:53,  3.32it/s]
 58%|█████▊    | 214911/371472 [6:24:50<12:56:47,  3.36it/s]
 58%|█████▊    | 214912/371472 [6:24:51<13:03:47,  3.33it/s]
 58%|█████▊    | 214913/371472 [6:24:51<13:11:02,  3.30it/s]
 58%|█████▊    | 214914/371472 [6:24:51<13:16:10,  3.28it/s]
 58%|█████▊    | 214915/371472 [6:24:52<13:01:51,  3.34it/s]
 58%|█████▊    | 214916/371472 [6:24:52<12:52:08,  3.38it/s]
 58%|█████▊    | 214917/371472 [6:24:52<13:21:19,  3.26it/s]
 58%|█████▊    | 214918/371472 [6:24:53<12:48:54,  3.39it/s]
 58%|█████▊    | 214919/371472 [6:24:53<12:48:07,  3.40it/s]
 58%|█████▊    | 214920/371472 [6:24:53<12:34:49,  3.46it/s]
                                                            
{'loss': 2.7086, 'learning_rate': 4.794975112585922e-07, 'epoch': 9.26}
+
 58%|█████▊    | 214920/371472 [6:24:53<12:34:49,  3.46it/s]
 58%|█████▊    | 214921/371472 [6:24:53<12:49:28,  3.39it/s]
 58%|█████▊    | 214922/371472 [6:24:54<12:46:13,  3.41it/s]
 58%|█████▊    | 214923/371472 [6:24:54<12:56:15,  3.36it/s]
 58%|█████▊    | 214924/371472 [6:24:54<13:06:32,  3.32it/s]
 58%|█████▊    | 214925/371472 [6:24:55<12:50:25,  3.39it/s]
 58%|█████▊    | 214926/371472 [6:24:55<12:50:54,  3.38it/s]
 58%|█████▊    | 214927/371472 [6:24:55<12:38:02,  3.44it/s]
 58%|█████▊    | 214928/371472 [6:24:55<12:28:04,  3.49it/s]
 58%|█████▊    | 214929/371472 [6:24:56<12:52:17,  3.38it/s]
 58%|█████▊    | 214930/371472 [6:24:56<12:20:00,  3.53it/s]
 58%|█████▊    | 214931/371472 [6:24:56<12:10:18,  3.57it/s]
 58%|█████▊    | 214932/371472 [6:24:57<12:11:09,  3.57it/s]
 58%|█████▊    | 214933/371472 [6:24:57<12:08:37,  3.58it/s]
 58%|█████▊    | 214934/371472 [6:24:57<11:53:32,  3.66it/s]
 58%|█████▊    | 214935/371472 [6:24:57<12:09:33,  3.58it/s]
 58%|█████▊    | 214936/371472 [6:24:58<12:51:05,  3.38it/s]
 58%|█████▊    | 214937/371472 [6:24:58<12:53:11,  3.37it/s]
 58%|█████▊    | 214938/371472 [6:24:58<12:40:52,  3.43it/s]
 58%|█████▊    | 214939/371472 [6:24:59<12:37:10,  3.45it/s]
 58%|█████▊    | 214940/371472 [6:24:59<12:49:32,  3.39it/s]
                                                            
{'loss': 3.0234, 'learning_rate': 4.794490292831131e-07, 'epoch': 9.26}
+
 58%|█████▊    | 214940/371472 [6:24:59<12:49:32,  3.39it/s]
 58%|█████▊    | 214941/371472 [6:24:59<13:39:23,  3.18it/s]
 58%|█████▊    | 214942/371472 [6:25:00<13:11:45,  3.30it/s]
 58%|█████▊    | 214943/371472 [6:25:00<13:05:51,  3.32it/s]
 58%|█████▊    | 214944/371472 [6:25:00<12:52:29,  3.38it/s]
 58%|█████▊    | 214945/371472 [6:25:00<12:41:49,  3.42it/s]
 58%|█████▊    | 214946/371472 [6:25:01<12:35:13,  3.45it/s]
 58%|█████▊    | 214947/371472 [6:25:01<12:19:50,  3.53it/s]
 58%|█████▊    | 214948/371472 [6:25:01<13:10:35,  3.30it/s]
 58%|█████▊    | 214949/371472 [6:25:02<13:25:54,  3.24it/s]
 58%|█████▊    | 214950/371472 [6:25:02<12:58:18,  3.35it/s]
 58%|█████▊    | 214951/371472 [6:25:02<12:52:04,  3.38it/s]
 58%|█████▊    | 214952/371472 [6:25:03<12:47:31,  3.40it/s]
 58%|█████▊    | 214953/371472 [6:25:03<12:39:07,  3.44it/s]
 58%|█████▊    | 214954/371472 [6:25:03<13:28:19,  3.23it/s]
 58%|█████▊    | 214955/371472 [6:25:03<13:06:21,  3.32it/s]
 58%|█████▊    | 214956/371472 [6:25:04<12:52:00,  3.38it/s]
 58%|█████▊    | 214957/371472 [6:25:04<12:57:45,  3.35it/s]
 58%|█████▊    | 214958/371472 [6:25:04<12:52:19,  3.38it/s]
 58%|█████▊    | 214959/371472 [6:25:05<13:51:18,  3.14it/s]
 58%|█████▊    | 214960/371472 [6:25:05<13:12:06,  3.29it/s]
                                                            
{'loss': 2.8577, 'learning_rate': 4.794005473076343e-07, 'epoch': 9.26}
+
 58%|█████▊    | 214960/371472 [6:25:05<13:12:06,  3.29it/s]
 58%|█████▊    | 214961/371472 [6:25:05<13:43:53,  3.17it/s]
 58%|█████▊    | 214962/371472 [6:25:06<13:16:36,  3.27it/s]
 58%|█████▊    | 214963/371472 [6:25:06<12:59:59,  3.34it/s]
 58%|█████▊    | 214964/371472 [6:25:06<12:31:48,  3.47it/s]
 58%|█████▊    | 214965/371472 [6:25:06<13:03:45,  3.33it/s]
 58%|█████▊    | 214966/371472 [6:25:07<13:01:08,  3.34it/s]
 58%|█████▊    | 214967/371472 [6:25:07<12:40:41,  3.43it/s]
 58%|█████▊    | 214968/371472 [6:25:07<13:10:52,  3.30it/s]
 58%|█████▊    | 214969/371472 [6:25:08<14:13:55,  3.05it/s]
 58%|█████▊    | 214970/371472 [6:25:08<13:54:05,  3.13it/s]
 58%|█████▊    | 214971/371472 [6:25:08<13:48:18,  3.15it/s]
 58%|█████▊    | 214972/371472 [6:25:09<13:20:55,  3.26it/s]
 58%|█████▊    | 214973/371472 [6:25:09<13:30:46,  3.22it/s]
 58%|█████▊    | 214974/371472 [6:25:09<13:06:09,  3.32it/s]
 58%|█████▊    | 214975/371472 [6:25:10<13:02:01,  3.34it/s]
 58%|█████▊    | 214976/371472 [6:25:10<12:49:37,  3.39it/s]
 58%|█████▊    | 214977/371472 [6:25:10<12:32:22,  3.47it/s]
 58%|█████▊    | 214978/371472 [6:25:10<12:30:30,  3.48it/s]
 58%|█████▊    | 214979/371472 [6:25:11<12:42:50,  3.42it/s]
 58%|█████▊    | 214980/371472 [6:25:11<12:58:52,  3.35it/s]
                                                            
{'loss': 2.689, 'learning_rate': 4.793520653321554e-07, 'epoch': 9.26}
+
 58%|█████▊    | 214980/371472 [6:25:11<12:58:52,  3.35it/s]
 58%|█████▊    | 214981/371472 [6:25:11<13:46:29,  3.16it/s]
 58%|█████▊    | 214982/371472 [6:25:12<13:40:43,  3.18it/s]
 58%|█████▊    | 214983/371472 [6:25:12<13:15:06,  3.28it/s]
 58%|█████▊    | 214984/371472 [6:25:12<12:52:42,  3.38it/s]
 58%|█████▊    | 214985/371472 [6:25:13<12:55:06,  3.36it/s]
 58%|█████▊    | 214986/371472 [6:25:13<12:30:13,  3.48it/s]
 58%|█████▊    | 214987/371472 [6:25:13<12:37:02,  3.45it/s]
 58%|█████▊    | 214988/371472 [6:25:13<12:12:28,  3.56it/s]
 58%|█████▊    | 214989/371472 [6:25:14<12:40:49,  3.43it/s]
 58%|█████▊    | 214990/371472 [6:25:14<13:17:25,  3.27it/s]
 58%|█████▊    | 214991/371472 [6:25:14<13:20:04,  3.26it/s]
 58%|█████▊    | 214992/371472 [6:25:15<12:55:36,  3.36it/s]
 58%|█████▊    | 214993/371472 [6:25:15<12:54:15,  3.37it/s]
 58%|█████▊    | 214994/371472 [6:25:15<12:34:49,  3.46it/s]
 58%|█████▊    | 214995/371472 [6:25:15<12:33:57,  3.46it/s]
 58%|█████▊    | 214996/371472 [6:25:16<12:31:58,  3.47it/s]
 58%|█████▊    | 214997/371472 [6:25:16<12:32:31,  3.47it/s]
 58%|█████▊    | 214998/371472 [6:25:16<12:47:24,  3.40it/s]
 58%|█████▊    | 214999/371472 [6:25:17<13:14:24,  3.28it/s]
 58%|█████▊    | 215000/371472 [6:25:17<14:03:14,  3.09it/s]
                                                            
{'loss': 2.8257, 'learning_rate': 4.793035833566765e-07, 'epoch': 9.26}
+
 58%|█████▊    | 215000/371472 [6:25:17<14:03:14,  3.09it/s]
 58%|█████▊    | 215001/371472 [6:25:17<13:45:50,  3.16it/s]
 58%|█████▊    | 215002/371472 [6:25:18<13:47:13,  3.15it/s]
 58%|█████▊    | 215003/371472 [6:25:18<13:14:07,  3.28it/s]
 58%|█████▊    | 215004/371472 [6:25:18<12:53:48,  3.37it/s]
 58%|█████▊    | 215005/371472 [6:25:18<12:50:55,  3.38it/s]
 58%|█████▊    | 215006/371472 [6:25:19<12:50:31,  3.38it/s]
 58%|█████▊    | 215007/371472 [6:25:19<12:56:19,  3.36it/s]
 58%|█████▊    | 215008/371472 [6:25:19<12:43:35,  3.42it/s]
 58%|█████▊    | 215009/371472 [6:25:20<13:24:07,  3.24it/s]
 58%|█████▊    | 215010/371472 [6:25:20<13:20:49,  3.26it/s]
 58%|█████▊    | 215011/371472 [6:25:20<12:51:07,  3.38it/s]
 58%|█████▊    | 215012/371472 [6:25:21<13:18:32,  3.27it/s]
 58%|█████▊    | 215013/371472 [6:25:21<14:00:48,  3.10it/s]
 58%|█████▊    | 215014/371472 [6:25:21<13:30:46,  3.22it/s]
 58%|█████▊    | 215015/371472 [6:25:22<13:59:24,  3.11it/s]
 58%|█████▊    | 215016/371472 [6:25:22<13:06:14,  3.32it/s]
 58%|█████▊    | 215017/371472 [6:25:22<13:05:58,  3.32it/s]
 58%|█████▊    | 215018/371472 [6:25:22<13:37:14,  3.19it/s]
 58%|█████▊    | 215019/371472 [6:25:23<13:43:10,  3.17it/s]
 58%|█████▊    | 215020/371472 [6:25:23<13:08:02,  3.31it/s]
                                                            
{'loss': 2.8232, 'learning_rate': 4.792551013811975e-07, 'epoch': 9.26}
+
 58%|█████▊    | 215020/371472 [6:25:23<13:08:02,  3.31it/s]
 58%|█████▊    | 215021/371472 [6:25:23<12:42:21,  3.42it/s]
 58%|█████▊    | 215022/371472 [6:25:24<12:31:23,  3.47it/s]
 58%|█████▊    | 215023/371472 [6:25:24<12:15:39,  3.54it/s]
 58%|█████▊    | 215024/371472 [6:25:24<12:33:58,  3.46it/s]
 58%|█████▊    | 215025/371472 [6:25:24<12:23:57,  3.50it/s]
 58%|█████▊    | 215026/371472 [6:25:25<12:08:33,  3.58it/s]
 58%|█████▊    | 215027/371472 [6:25:25<11:59:26,  3.62it/s]
 58%|█████▊    | 215028/371472 [6:25:25<13:05:33,  3.32it/s]
 58%|█████▊    | 215029/371472 [6:25:26<12:49:16,  3.39it/s]
 58%|█████▊    | 215030/371472 [6:25:26<12:25:10,  3.50it/s]
 58%|█████▊    | 215031/371472 [6:25:26<12:56:51,  3.36it/s]
 58%|█████▊    | 215032/371472 [6:25:27<12:52:53,  3.37it/s]
 58%|█████▊    | 215033/371472 [6:25:27<12:42:43,  3.42it/s]
 58%|█████▊    | 215034/371472 [6:25:27<12:49:18,  3.39it/s]
 58%|█████▊    | 215035/371472 [6:25:27<13:04:09,  3.32it/s]
 58%|█████▊    | 215036/371472 [6:25:28<13:23:40,  3.24it/s]
 58%|█████▊    | 215037/371472 [6:25:28<13:01:05,  3.34it/s]
 58%|█████▊    | 215038/371472 [6:25:28<12:31:04,  3.47it/s]
 58%|█████▊    | 215039/371472 [6:25:29<12:11:16,  3.57it/s]
 58%|█████▊    | 215040/371472 [6:25:29<12:07:40,  3.58it/s]
                                                            
{'loss': 2.8038, 'learning_rate': 4.792066194057188e-07, 'epoch': 9.26}
+
 58%|█████▊    | 215040/371472 [6:25:29<12:07:40,  3.58it/s]
 58%|█████▊    | 215041/371472 [6:25:29<12:12:06,  3.56it/s]
 58%|█████▊    | 215042/371472 [6:25:29<12:12:40,  3.56it/s]
 58%|█████▊    | 215043/371472 [6:25:30<12:05:42,  3.59it/s]
 58%|█████▊    | 215044/371472 [6:25:30<12:26:21,  3.49it/s]
 58%|█████▊    | 215045/371472 [6:25:30<12:25:16,  3.50it/s]
 58%|█████▊    | 215046/371472 [6:25:31<12:29:43,  3.48it/s]
 58%|█████▊    | 215047/371472 [6:25:31<12:22:18,  3.51it/s]
 58%|█████▊    | 215048/371472 [6:25:31<13:32:07,  3.21it/s]
 58%|█████▊    | 215049/371472 [6:25:32<13:52:36,  3.13it/s]
 58%|█████▊    | 215050/371472 [6:25:32<13:38:12,  3.19it/s]
 58%|█████▊    | 215051/371472 [6:25:32<13:22:53,  3.25it/s]
 58%|█████▊    | 215052/371472 [6:25:32<13:26:26,  3.23it/s]
 58%|█████▊    | 215053/371472 [6:25:33<13:38:36,  3.18it/s]
 58%|█████▊    | 215054/371472 [6:25:33<13:12:14,  3.29it/s]
 58%|█████▊    | 215055/371472 [6:25:33<12:47:54,  3.39it/s]
 58%|█████▊    | 215056/371472 [6:25:34<12:43:08,  3.42it/s]
 58%|█████▊    | 215057/371472 [6:25:34<12:27:41,  3.49it/s]
 58%|█████▊    | 215058/371472 [6:25:34<12:18:27,  3.53it/s]
 58%|█████▊    | 215059/371472 [6:25:34<12:03:45,  3.60it/s]
 58%|█████▊    | 215060/371472 [6:25:35<11:54:57,  3.65it/s]
                                                            
{'loss': 2.8183, 'learning_rate': 4.791581374302398e-07, 'epoch': 9.26}
+
 58%|█████▊    | 215060/371472 [6:25:35<11:54:57,  3.65it/s]
 58%|█████▊    | 215061/371472 [6:25:35<12:12:17,  3.56it/s]
 58%|█████▊    | 215062/371472 [6:25:35<12:20:20,  3.52it/s]
 58%|█████▊    | 215063/371472 [6:25:36<12:22:31,  3.51it/s]
 58%|█████▊    | 215064/371472 [6:25:36<12:52:50,  3.37it/s]
 58%|█████▊    | 215065/371472 [6:25:36<12:28:16,  3.48it/s]
 58%|█████▊    | 215066/371472 [6:25:36<12:13:30,  3.55it/s]
 58%|█████▊    | 215067/371472 [6:25:37<12:35:56,  3.45it/s]
 58%|█████▊    | 215068/371472 [6:25:37<12:43:21,  3.41it/s]
 58%|█████▊    | 215069/371472 [6:25:37<13:20:32,  3.26it/s]
 58%|█████▊    | 215070/371472 [6:25:38<13:28:46,  3.22it/s]
 58%|█████▊    | 215071/371472 [6:25:38<13:46:11,  3.16it/s]
 58%|█████▊    | 215072/371472 [6:25:38<13:38:53,  3.18it/s]
 58%|█████▊    | 215073/371472 [6:25:39<13:40:11,  3.18it/s]
 58%|█████▊    | 215074/371472 [6:25:39<13:06:27,  3.31it/s]
 58%|█████▊    | 215075/371472 [6:25:39<13:12:31,  3.29it/s]
 58%|█████▊    | 215076/371472 [6:25:40<13:07:51,  3.31it/s]
 58%|█████▊    | 215077/371472 [6:25:40<12:44:35,  3.41it/s]
 58%|█████▊    | 215078/371472 [6:25:40<12:24:01,  3.50it/s]
 58%|█████▊    | 215079/371472 [6:25:40<12:14:30,  3.55it/s]
 58%|█████▊    | 215080/371472 [6:25:41<12:24:22,  3.50it/s]
                                                            
{'loss': 2.7844, 'learning_rate': 4.79109655454761e-07, 'epoch': 9.26}
+
 58%|█████▊    | 215080/371472 [6:25:41<12:24:22,  3.50it/s]
 58%|█████▊    | 215081/371472 [6:25:41<12:27:20,  3.49it/s]
 58%|█████▊    | 215082/371472 [6:25:41<13:43:01,  3.17it/s]
 58%|█████▊    | 215083/371472 [6:25:42<12:59:44,  3.34it/s]
 58%|█████▊    | 215084/371472 [6:25:42<12:39:15,  3.43it/s]
 58%|█████▊    | 215085/371472 [6:25:42<13:56:07,  3.12it/s]
 58%|█████▊    | 215086/371472 [6:25:43<13:34:17,  3.20it/s]
 58%|█████▊    | 215087/371472 [6:25:43<13:48:26,  3.15it/s]
 58%|█████▊    | 215088/371472 [6:25:43<13:43:05,  3.17it/s]
 58%|█████▊    | 215089/371472 [6:25:43<13:37:30,  3.19it/s]
 58%|█████▊    | 215090/371472 [6:25:44<13:07:27,  3.31it/s]
 58%|█████▊    | 215091/371472 [6:25:44<12:52:21,  3.37it/s]
 58%|█████▊    | 215092/371472 [6:25:44<12:30:51,  3.47it/s]
 58%|█████▊    | 215093/371472 [6:25:45<13:01:41,  3.33it/s]
 58%|█████▊    | 215094/371472 [6:25:45<12:41:57,  3.42it/s]
 58%|█████▊    | 215095/371472 [6:25:45<12:23:54,  3.50it/s]
 58%|█████▊    | 215096/371472 [6:25:45<12:38:44,  3.43it/s]
 58%|█████▊    | 215097/371472 [6:25:46<12:59:25,  3.34it/s]
 58%|█████▊    | 215098/371472 [6:25:46<12:40:46,  3.43it/s]
 58%|█████▊    | 215099/371472 [6:25:46<12:59:07,  3.35it/s]
 58%|█████▊    | 215100/371472 [6:25:47<12:47:26,  3.40it/s]
                                                            
{'loss': 2.8101, 'learning_rate': 4.79061173479282e-07, 'epoch': 9.26}
+
 58%|█████▊    | 215100/371472 [6:25:47<12:47:26,  3.40it/s]
 58%|█████▊    | 215101/371472 [6:25:47<12:26:43,  3.49it/s]
 58%|█████▊    | 215102/371472 [6:25:47<12:20:40,  3.52it/s]
 58%|█████▊    | 215103/371472 [6:25:48<12:30:34,  3.47it/s]
 58%|█████▊    | 215104/371472 [6:25:48<12:30:01,  3.47it/s]
 58%|█████▊    | 215105/371472 [6:25:48<12:51:06,  3.38it/s]
 58%|█████▊    | 215106/371472 [6:25:48<13:21:28,  3.25it/s]
 58%|█████▊    | 215107/371472 [6:25:49<13:14:44,  3.28it/s]
 58%|█████▊    | 215108/371472 [6:25:49<12:53:26,  3.37it/s]
 58%|█████▊    | 215109/371472 [6:25:49<13:42:54,  3.17it/s]
 58%|█████▊    | 215110/371472 [6:25:50<12:57:54,  3.35it/s]
 58%|█████▊    | 215111/371472 [6:25:50<12:21:41,  3.51it/s]
 58%|█████▊    | 215112/371472 [6:25:50<12:20:01,  3.52it/s]
 58%|█████▊    | 215113/371472 [6:25:51<12:50:20,  3.38it/s]
 58%|█████▊    | 215114/371472 [6:25:51<12:42:48,  3.42it/s]
 58%|█████▊    | 215115/371472 [6:25:51<12:28:19,  3.48it/s]
 58%|█████▊    | 215116/371472 [6:25:51<12:06:27,  3.59it/s]
 58%|█████▊    | 215117/371472 [6:25:52<11:49:15,  3.67it/s]
 58%|█████▊    | 215118/371472 [6:25:52<11:43:14,  3.71it/s]
 58%|█████▊    | 215119/371472 [6:25:52<11:46:35,  3.69it/s]
 58%|█████▊    | 215120/371472 [6:25:52<12:05:31,  3.59it/s]
                                                            
{'loss': 2.9274, 'learning_rate': 4.790126915038031e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215120/371472 [6:25:52<12:05:31,  3.59it/s]
 58%|█████▊    | 215121/371472 [6:25:53<12:41:15,  3.42it/s]
 58%|█████▊    | 215122/371472 [6:25:53<12:33:31,  3.46it/s]
 58%|█████▊    | 215123/371472 [6:25:53<12:43:53,  3.41it/s]
 58%|█████▊    | 215124/371472 [6:25:54<12:45:49,  3.40it/s]
 58%|█████▊    | 215125/371472 [6:25:54<13:18:28,  3.26it/s]
 58%|█████▊    | 215126/371472 [6:25:54<12:39:25,  3.43it/s]
 58%|█████▊    | 215127/371472 [6:25:54<12:21:12,  3.52it/s]
 58%|█████▊    | 215128/371472 [6:25:55<12:36:00,  3.45it/s]
 58%|█████▊    | 215129/371472 [6:25:55<12:39:18,  3.43it/s]
 58%|█████▊    | 215130/371472 [6:25:55<12:17:22,  3.53it/s]
 58%|█████▊    | 215131/371472 [6:25:56<12:15:15,  3.54it/s]
 58%|█████▊    | 215132/371472 [6:25:56<11:52:54,  3.65it/s]
 58%|█████▊    | 215133/371472 [6:25:56<11:58:59,  3.62it/s]
 58%|█████▊    | 215134/371472 [6:25:56<11:43:52,  3.70it/s]
 58%|█████▊    | 215135/371472 [6:25:57<11:58:48,  3.62it/s]
 58%|█████▊    | 215136/371472 [6:25:57<12:03:16,  3.60it/s]
 58%|█████▊    | 215137/371472 [6:25:57<13:03:32,  3.33it/s]
 58%|█████▊    | 215138/371472 [6:25:58<13:23:01,  3.24it/s]
 58%|█████▊    | 215139/371472 [6:25:58<14:50:01,  2.93it/s]
 58%|█████▊    | 215140/371472 [6:25:58<14:12:32,  3.06it/s]
                                                            
{'loss': 2.7084, 'learning_rate': 4.789642095283242e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215140/371472 [6:25:58<14:12:32,  3.06it/s]
 58%|█████▊    | 215141/371472 [6:25:59<13:28:37,  3.22it/s]
 58%|█████▊    | 215142/371472 [6:25:59<13:15:12,  3.28it/s]
 58%|█████▊    | 215143/371472 [6:25:59<13:42:01,  3.17it/s]
 58%|█████▊    | 215144/371472 [6:26:00<13:13:05,  3.29it/s]
 58%|█████▊    | 215145/371472 [6:26:00<13:06:44,  3.31it/s]
 58%|█████▊    | 215146/371472 [6:26:00<12:36:35,  3.44it/s]
 58%|█████▊    | 215147/371472 [6:26:00<12:40:02,  3.43it/s]
 58%|█████▊    | 215148/371472 [6:26:01<12:18:56,  3.53it/s]
 58%|█████▊    | 215149/371472 [6:26:01<12:11:33,  3.56it/s]
 58%|█████▊    | 215150/371472 [6:26:01<12:53:39,  3.37it/s]
 58%|█████▊    | 215151/371472 [6:26:02<13:46:29,  3.15it/s]
 58%|█████▊    | 215152/371472 [6:26:02<14:13:25,  3.05it/s]
 58%|█████▊    | 215153/371472 [6:26:02<14:44:10,  2.95it/s]
 58%|█████▊    | 215154/371472 [6:26:03<15:27:59,  2.81it/s]
 58%|█████▊    | 215155/371472 [6:26:03<14:29:41,  3.00it/s]
 58%|█████▊    | 215156/371472 [6:26:03<13:45:59,  3.15it/s]
 58%|█████▊    | 215157/371472 [6:26:04<13:31:59,  3.21it/s]
 58%|█████▊    | 215158/371472 [6:26:04<13:24:21,  3.24it/s]
 58%|█████▊    | 215159/371472 [6:26:04<13:47:33,  3.15it/s]
 58%|█████▊    | 215160/371472 [6:26:05<13:21:55,  3.25it/s]
                                                            
{'loss': 2.8471, 'learning_rate': 4.789157275528452e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215160/371472 [6:26:05<13:21:55,  3.25it/s]
 58%|█████▊    | 215161/371472 [6:26:05<13:53:10,  3.13it/s]
 58%|█████▊    | 215162/371472 [6:26:05<14:03:26,  3.09it/s]
 58%|█████▊    | 215163/371472 [6:26:05<13:14:17,  3.28it/s]
 58%|█████▊    | 215164/371472 [6:26:06<12:45:19,  3.40it/s]
 58%|█████▊    | 215165/371472 [6:26:06<14:08:59,  3.07it/s]
 58%|█████▊    | 215166/371472 [6:26:06<13:39:09,  3.18it/s]
 58%|█████▊    | 215167/371472 [6:26:07<12:58:27,  3.35it/s]
 58%|█████▊    | 215168/371472 [6:26:07<13:12:15,  3.29it/s]
 58%|█████▊    | 215169/371472 [6:26:07<12:45:24,  3.40it/s]
 58%|█████▊    | 215170/371472 [6:26:08<12:56:35,  3.35it/s]
 58%|█████▊    | 215171/371472 [6:26:08<12:38:24,  3.43it/s]
 58%|█████▊    | 215172/371472 [6:26:08<12:26:07,  3.49it/s]
 58%|█████▊    | 215173/371472 [6:26:08<13:02:55,  3.33it/s]
 58%|█████▊    | 215174/371472 [6:26:09<12:42:25,  3.42it/s]
 58%|█████▊    | 215175/371472 [6:26:09<12:16:16,  3.54it/s]
 58%|█████▊    | 215176/371472 [6:26:09<12:17:38,  3.53it/s]
 58%|█████▊    | 215177/371472 [6:26:10<11:59:15,  3.62it/s]
 58%|█████▊    | 215178/371472 [6:26:10<12:05:27,  3.59it/s]
 58%|█████▊    | 215179/371472 [6:26:10<13:00:40,  3.34it/s]
 58%|█████▊    | 215180/371472 [6:26:10<12:46:47,  3.40it/s]
                                                            
{'loss': 2.6728, 'learning_rate': 4.788672455773665e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215180/371472 [6:26:10<12:46:47,  3.40it/s]
 58%|█████▊    | 215181/371472 [6:26:11<12:59:08,  3.34it/s]
 58%|█████▊    | 215182/371472 [6:26:11<12:40:26,  3.43it/s]
 58%|█████▊    | 215183/371472 [6:26:11<12:41:22,  3.42it/s]
 58%|█████▊    | 215184/371472 [6:26:12<12:20:33,  3.52it/s]
 58%|█████▊    | 215185/371472 [6:26:12<12:36:37,  3.44it/s]
 58%|█████▊    | 215186/371472 [6:26:12<12:24:36,  3.50it/s]
 58%|█████▊    | 215187/371472 [6:26:12<12:28:02,  3.48it/s]
 58%|█████▊    | 215188/371472 [6:26:13<12:16:34,  3.54it/s]
 58%|█████▊    | 215189/371472 [6:26:13<11:55:39,  3.64it/s]
 58%|█████▊    | 215190/371472 [6:26:13<12:03:55,  3.60it/s]
 58%|█████▊    | 215191/371472 [6:26:14<12:15:09,  3.54it/s]
 58%|█████▊    | 215192/371472 [6:26:14<13:15:02,  3.28it/s]
 58%|█████▊    | 215193/371472 [6:26:14<13:04:11,  3.32it/s]
 58%|█████▊    | 215194/371472 [6:26:15<13:09:24,  3.30it/s]
 58%|█████▊    | 215195/371472 [6:26:15<13:03:42,  3.32it/s]
 58%|█████▊    | 215196/371472 [6:26:15<13:07:36,  3.31it/s]
 58%|█████▊    | 215197/371472 [6:26:15<12:55:33,  3.36it/s]
 58%|█████▊    | 215198/371472 [6:26:16<12:39:15,  3.43it/s]
 58%|█████▊    | 215199/371472 [6:26:16<12:32:31,  3.46it/s]
 58%|█████▊    | 215200/371472 [6:26:16<12:27:29,  3.48it/s]
                                                            
{'loss': 2.8401, 'learning_rate': 4.788187636018875e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215200/371472 [6:26:16<12:27:29,  3.48it/s]
 58%|█████▊    | 215201/371472 [6:26:17<12:57:28,  3.35it/s]
 58%|█████▊    | 215202/371472 [6:26:17<12:39:25,  3.43it/s]
 58%|█████▊    | 215203/371472 [6:26:17<12:26:20,  3.49it/s]
 58%|█████▊    | 215204/371472 [6:26:17<12:11:15,  3.56it/s]
 58%|█████▊    | 215205/371472 [6:26:18<11:56:28,  3.64it/s]
 58%|█████▊    | 215206/371472 [6:26:18<12:10:25,  3.57it/s]
 58%|█████▊    | 215207/371472 [6:26:18<12:36:54,  3.44it/s]
 58%|█████▊    | 215208/371472 [6:26:19<12:22:51,  3.51it/s]
 58%|█████▊    | 215209/371472 [6:26:19<11:59:14,  3.62it/s]
 58%|█████▊    | 215210/371472 [6:26:19<11:32:08,  3.76it/s]
 58%|█████▊    | 215211/371472 [6:26:19<12:11:16,  3.56it/s]
 58%|█████▊    | 215212/371472 [6:26:20<11:50:32,  3.67it/s]
 58%|█████▊    | 215213/371472 [6:26:20<13:20:34,  3.25it/s]
 58%|█████▊    | 215214/371472 [6:26:20<13:11:00,  3.29it/s]
 58%|█████▊    | 215215/371472 [6:26:21<12:41:35,  3.42it/s]
 58%|█████▊    | 215216/371472 [6:26:21<12:32:01,  3.46it/s]
 58%|█████▊    | 215217/371472 [6:26:21<12:13:11,  3.55it/s]
 58%|█████▊    | 215218/371472 [6:26:21<12:05:04,  3.59it/s]
 58%|█████▊    | 215219/371472 [6:26:22<12:00:27,  3.61it/s]
 58%|█████▊    | 215220/371472 [6:26:22<12:28:36,  3.48it/s]
                                                            
{'loss': 2.8208, 'learning_rate': 4.787702816264087e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215220/371472 [6:26:22<12:28:36,  3.48it/s]
 58%|█████▊    | 215221/371472 [6:26:22<12:19:43,  3.52it/s]
 58%|█████▊    | 215222/371472 [6:26:23<12:31:23,  3.47it/s]
 58%|█████▊    | 215223/371472 [6:26:23<12:49:06,  3.39it/s]
 58%|█████▊    | 215224/371472 [6:26:23<12:31:16,  3.47it/s]
 58%|█████▊    | 215225/371472 [6:26:23<12:29:30,  3.47it/s]
 58%|█████▊    | 215226/371472 [6:26:24<13:12:29,  3.29it/s]
 58%|█████▊    | 215227/371472 [6:26:24<12:48:20,  3.39it/s]
 58%|█████▊    | 215228/371472 [6:26:24<13:12:54,  3.28it/s]
 58%|█████▊    | 215229/371472 [6:26:25<12:40:34,  3.42it/s]
 58%|█████▊    | 215230/371472 [6:26:25<12:14:36,  3.54it/s]
 58%|█████▊    | 215231/371472 [6:26:25<12:31:02,  3.47it/s]
 58%|█████▊    | 215232/371472 [6:26:25<12:24:27,  3.50it/s]
 58%|█████▊    | 215233/371472 [6:26:26<12:18:58,  3.52it/s]
 58%|█████▊    | 215234/371472 [6:26:26<13:28:02,  3.22it/s]
 58%|█████▊    | 215235/371472 [6:26:26<13:11:30,  3.29it/s]
 58%|█████▊    | 215236/371472 [6:26:27<13:11:31,  3.29it/s]
 58%|█████▊    | 215237/371472 [6:26:27<13:07:01,  3.31it/s]
 58%|█████▊    | 215238/371472 [6:26:27<13:49:46,  3.14it/s]
 58%|█████▊    | 215239/371472 [6:26:28<13:32:03,  3.21it/s]
 58%|█████▊    | 215240/371472 [6:26:28<13:17:06,  3.27it/s]
                                                            
{'loss': 2.608, 'learning_rate': 4.787217996509297e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215240/371472 [6:26:28<13:17:06,  3.27it/s]
 58%|█████▊    | 215241/371472 [6:26:28<13:16:12,  3.27it/s]
 58%|█████▊    | 215242/371472 [6:26:29<12:36:19,  3.44it/s]
 58%|█████▊    | 215243/371472 [6:26:29<12:52:41,  3.37it/s]
 58%|█████▊    | 215244/371472 [6:26:29<13:21:52,  3.25it/s]
 58%|█████▊    | 215245/371472 [6:26:30<14:08:27,  3.07it/s]
 58%|█████▊    | 215246/371472 [6:26:30<13:14:45,  3.28it/s]
 58%|█████▊    | 215247/371472 [6:26:30<12:55:54,  3.36it/s]
 58%|█████▊    | 215248/371472 [6:26:30<12:35:57,  3.44it/s]
 58%|█████▊    | 215249/371472 [6:26:31<12:36:59,  3.44it/s]
 58%|█████▊    | 215250/371472 [6:26:31<12:18:08,  3.53it/s]
 58%|█████▊    | 215251/371472 [6:26:31<12:04:34,  3.59it/s]
 58%|█████▊    | 215252/371472 [6:26:31<12:10:52,  3.56it/s]
 58%|█████▊    | 215253/371472 [6:26:32<12:08:34,  3.57it/s]
 58%|█████▊    | 215254/371472 [6:26:32<11:59:19,  3.62it/s]
 58%|█████▊    | 215255/371472 [6:26:32<12:07:41,  3.58it/s]
 58%|█████▊    | 215256/371472 [6:26:33<12:31:38,  3.46it/s]
 58%|█████▊    | 215257/371472 [6:26:33<12:46:34,  3.40it/s]
 58%|█████▊    | 215258/371472 [6:26:33<13:02:16,  3.33it/s]
 58%|█████▊    | 215259/371472 [6:26:34<12:46:10,  3.40it/s]
 58%|█████▊    | 215260/371472 [6:26:34<12:58:51,  3.34it/s]
                                                            
{'loss': 2.8091, 'learning_rate': 4.786733176754508e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215260/371472 [6:26:34<12:58:51,  3.34it/s]
 58%|█████▊    | 215261/371472 [6:26:34<12:54:16,  3.36it/s]
 58%|█████▊    | 215262/371472 [6:26:34<13:01:29,  3.33it/s]
 58%|█████▊    | 215263/371472 [6:26:35<13:34:37,  3.20it/s]
 58%|█████▊    | 215264/371472 [6:26:35<13:00:11,  3.34it/s]
 58%|█████▊    | 215265/371472 [6:26:35<12:51:27,  3.37it/s]
 58%|█████▊    | 215266/371472 [6:26:36<12:31:34,  3.46it/s]
 58%|█████▊    | 215267/371472 [6:26:36<12:31:08,  3.47it/s]
 58%|█████▊    | 215268/371472 [6:26:36<12:49:57,  3.38it/s]
 58%|█████▊    | 215269/371472 [6:26:36<12:31:36,  3.46it/s]
 58%|█████▊    | 215270/371472 [6:26:37<12:54:57,  3.36it/s]
 58%|█████▊    | 215271/371472 [6:26:37<13:43:15,  3.16it/s]
 58%|█████▊    | 215272/371472 [6:26:37<13:25:56,  3.23it/s]
 58%|█████▊    | 215273/371472 [6:26:38<13:47:46,  3.14it/s]
 58%|█████▊    | 215274/371472 [6:26:38<13:42:20,  3.17it/s]
 58%|█████▊    | 215275/371472 [6:26:38<14:00:10,  3.10it/s]
 58%|█████▊    | 215276/371472 [6:26:39<13:18:35,  3.26it/s]
 58%|█████▊    | 215277/371472 [6:26:39<12:56:17,  3.35it/s]
 58%|█████▊    | 215278/371472 [6:26:39<12:56:59,  3.35it/s]
 58%|█████▊    | 215279/371472 [6:26:40<13:05:06,  3.32it/s]
 58%|█████▊    | 215280/371472 [6:26:40<13:30:35,  3.21it/s]
                                                            
{'loss': 2.9819, 'learning_rate': 4.786248356999719e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215280/371472 [6:26:40<13:30:35,  3.21it/s]
 58%|█████▊    | 215281/371472 [6:26:40<12:54:35,  3.36it/s]
 58%|█████▊    | 215282/371472 [6:26:40<12:53:33,  3.37it/s]
 58%|█████▊    | 215283/371472 [6:26:41<12:41:21,  3.42it/s]
 58%|█████▊    | 215284/371472 [6:26:41<12:11:00,  3.56it/s]
 58%|█████▊    | 215285/371472 [6:26:41<12:13:10,  3.55it/s]
 58%|█████▊    | 215286/371472 [6:26:42<11:56:26,  3.63it/s]
 58%|█████▊    | 215287/371472 [6:26:42<12:01:55,  3.61it/s]
 58%|█████▊    | 215288/371472 [6:26:42<12:39:59,  3.43it/s]
 58%|█████▊    | 215289/371472 [6:26:42<12:30:05,  3.47it/s]
 58%|█████▊    | 215290/371472 [6:26:43<12:46:29,  3.40it/s]
 58%|█████▊    | 215291/371472 [6:26:43<12:50:19,  3.38it/s]
 58%|█████▊    | 215292/371472 [6:26:43<12:27:13,  3.48it/s]
 58%|█████▊    | 215293/371472 [6:26:44<12:42:19,  3.41it/s]
 58%|█████▊    | 215294/371472 [6:26:44<12:34:49,  3.45it/s]
 58%|█████▊    | 215295/371472 [6:26:44<12:23:12,  3.50it/s]
 58%|█████▊    | 215296/371472 [6:26:44<12:27:40,  3.48it/s]
 58%|█████▊    | 215297/371472 [6:26:45<13:39:11,  3.18it/s]
 58%|█████▊    | 215298/371472 [6:26:45<13:37:30,  3.18it/s]
 58%|█████▊    | 215299/371472 [6:26:45<13:20:35,  3.25it/s]
 58%|█████▊    | 215300/371472 [6:26:46<12:56:27,  3.35it/s]
                                                            
{'loss': 2.8235, 'learning_rate': 4.785763537244932e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215300/371472 [6:26:46<12:56:27,  3.35it/s]
 58%|█████▊    | 215301/371472 [6:26:46<12:54:18,  3.36it/s]
 58%|█████▊    | 215302/371472 [6:26:46<12:49:49,  3.38it/s]
 58%|█████▊    | 215303/371472 [6:26:47<12:47:26,  3.39it/s]
 58%|█████▊    | 215304/371472 [6:26:47<13:00:27,  3.33it/s]
 58%|█████▊    | 215305/371472 [6:26:47<12:52:34,  3.37it/s]
 58%|█████▊    | 215306/371472 [6:26:48<12:54:48,  3.36it/s]
 58%|█████▊    | 215307/371472 [6:26:48<12:32:13,  3.46it/s]
 58%|█████▊    | 215308/371472 [6:26:48<13:11:25,  3.29it/s]
 58%|█████▊    | 215309/371472 [6:26:48<12:43:51,  3.41it/s]
 58%|█████▊    | 215310/371472 [6:26:49<12:25:57,  3.49it/s]
 58%|█████▊    | 215311/371472 [6:26:49<12:09:05,  3.57it/s]
 58%|██��██▊    | 215312/371472 [6:26:49<12:05:49,  3.59it/s]
 58%|█████▊    | 215313/371472 [6:26:49<12:04:21,  3.59it/s]
 58%|█████▊    | 215314/371472 [6:26:50<12:12:44,  3.55it/s]
 58%|█████▊    | 215315/371472 [6:26:50<11:49:17,  3.67it/s]
 58%|█████▊    | 215316/371472 [6:26:50<12:38:19,  3.43it/s]
 58%|█████▊    | 215317/371472 [6:26:51<12:30:00,  3.47it/s]
 58%|█████▊    | 215318/371472 [6:26:51<12:32:57,  3.46it/s]
 58%|█████▊    | 215319/371472 [6:26:51<12:31:26,  3.46it/s]
 58%|█████▊    | 215320/371472 [6:26:51<12:12:12,  3.55it/s]
                                                            
{'loss': 2.8206, 'learning_rate': 4.785278717490141e-07, 'epoch': 9.27}
+
 58%|█████▊    | 215320/371472 [6:26:51<12:12:12,  3.55it/s]
 58%|█████▊    | 215321/371472 [6:26:52<12:01:20,  3.61it/s]
 58%|█████▊    | 215322/371472 [6:26:52<11:58:03,  3.62it/s]
 58%|█████▊    | 215323/371472 [6:26:52<11:50:49,  3.66it/s]
 58%|█████▊    | 215324/371472 [6:26:53<12:14:02,  3.55it/s]
 58%|█████▊    | 215325/371472 [6:26:53<12:30:14,  3.47it/s]
 58%|█████▊    | 215326/371472 [6:26:53<12:23:28,  3.50it/s]
 58%|█████▊    | 215327/371472 [6:26:53<12:07:16,  3.58it/s]
 58%|█████▊    | 215328/371472 [6:26:54<11:56:13,  3.63it/s]
 58%|█████▊    | 215329/371472 [6:26:54<13:28:57,  3.22it/s]
 58%|█████▊    | 215330/371472 [6:26:54<12:56:18,  3.35it/s]
 58%|█████▊    | 215331/371472 [6:26:55<12:55:08,  3.36it/s]
 58%|█████▊    | 215332/371472 [6:26:55<12:42:09,  3.41it/s]
 58%|█████▊    | 215333/371472 [6:26:55<12:25:06,  3.49it/s]
 58%|█████▊    | 215334/371472 [6:26:55<12:19:25,  3.52it/s]
 58%|█████▊    | 215335/371472 [6:26:56<12:21:12,  3.51it/s]
 58%|█████▊    | 215336/371472 [6:26:56<13:06:13,  3.31it/s]
 58%|█████▊    | 215337/371472 [6:26:56<13:07:16,  3.31it/s]
 58%|█████▊    | 215338/371472 [6:26:57<12:54:37,  3.36it/s]
 58%|█████▊    | 215339/371472 [6:26:57<12:50:51,  3.38it/s]
 58%|█████▊    | 215340/371472 [6:26:57<12:48:45,  3.38it/s]
                                                            
{'loss': 2.8924, 'learning_rate': 4.784793897735353e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215340/371472 [6:26:57<12:48:45,  3.38it/s]
 58%|█████▊    | 215341/371472 [6:26:58<13:34:51,  3.19it/s]
 58%|█████▊    | 215342/371472 [6:26:58<13:49:10,  3.14it/s]
 58%|█████▊    | 215343/371472 [6:26:58<13:22:36,  3.24it/s]
 58%|█████▊    | 215344/371472 [6:26:59<12:56:40,  3.35it/s]
 58%|█████▊    | 215345/371472 [6:26:59<13:01:54,  3.33it/s]
 58%|█████▊    | 215346/371472 [6:26:59<12:57:51,  3.35it/s]
 58%|█████▊    | 215347/371472 [6:26:59<12:27:31,  3.48it/s]
 58%|█████▊    | 215348/371472 [6:27:00<13:19:50,  3.25it/s]
 58%|█████▊    | 215349/371472 [6:27:00<13:12:35,  3.28it/s]
 58%|█████▊    | 215350/371472 [6:27:00<12:53:24,  3.36it/s]
 58%|█████▊    | 215351/371472 [6:27:01<13:26:02,  3.23it/s]
 58%|█████▊    | 215352/371472 [6:27:01<12:56:28,  3.35it/s]
 58%|█████▊    | 215353/371472 [6:27:01<12:39:41,  3.43it/s]
 58%|█████▊    | 215354/371472 [6:27:02<12:33:17,  3.45it/s]
 58%|█████▊    | 215355/371472 [6:27:02<12:22:30,  3.50it/s]
 58%|█████▊    | 215356/371472 [6:27:02<12:38:52,  3.43it/s]
 58%|█████▊    | 215357/371472 [6:27:02<12:32:51,  3.46it/s]
 58%|█████▊    | 215358/371472 [6:27:03<12:29:06,  3.47it/s]
 58%|█████▊    | 215359/371472 [6:27:03<12:14:22,  3.54it/s]
 58%|█████▊    | 215360/371472 [6:27:03<12:10:40,  3.56it/s]
                                                            
{'loss': 2.6921, 'learning_rate': 4.784309077980564e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215360/371472 [6:27:03<12:10:40,  3.56it/s]
 58%|█████▊    | 215361/371472 [6:27:03<11:54:02,  3.64it/s]
 58%|█████▊    | 215362/371472 [6:27:04<11:47:57,  3.68it/s]
 58%|█████▊    | 215363/371472 [6:27:04<12:09:24,  3.57it/s]
 58%|█████▊    | 215364/371472 [6:27:04<12:19:49,  3.52it/s]
 58%|█████▊    | 215365/371472 [6:27:05<12:44:02,  3.41it/s]
 58%|█████▊    | 215366/371472 [6:27:05<12:52:41,  3.37it/s]
 58%|█████▊    | 215367/371472 [6:27:05<12:44:36,  3.40it/s]
 58%|█████▊    | 215368/371472 [6:27:06<14:01:52,  3.09it/s]
 58%|█████▊    | 215369/371472 [6:27:06<13:34:50,  3.19it/s]
 58%|█████▊    | 215370/371472 [6:27:06<13:17:48,  3.26it/s]
 58%|█████▊    | 215371/371472 [6:27:07<13:13:07,  3.28it/s]
 58%|█████▊    | 215372/371472 [6:27:07<13:03:57,  3.32it/s]
 58%|█████▊    | 215373/371472 [6:27:07<13:31:04,  3.21it/s]
 58%|█████▊    | 215374/371472 [6:27:07<13:51:50,  3.13it/s]
 58%|█████▊    | 215375/371472 [6:27:08<13:18:48,  3.26it/s]
 58%|█████▊    | 215376/371472 [6:27:08<12:43:54,  3.41it/s]
 58%|█████▊    | 215377/371472 [6:27:08<12:25:24,  3.49it/s]
 58%|█████▊    | 215378/371472 [6:27:09<12:56:30,  3.35it/s]
 58%|█████▊    | 215379/371472 [6:27:09<12:51:00,  3.37it/s]
 58%|█████▊    | 215380/371472 [6:27:09<13:13:17,  3.28it/s]
                                                            
{'loss': 2.7133, 'learning_rate': 4.783824258225774e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215380/371472 [6:27:09<13:13:17,  3.28it/s]
 58%|█████▊    | 215381/371472 [6:27:10<13:30:12,  3.21it/s]
 58%|█████▊    | 215382/371472 [6:27:10<13:07:11,  3.30it/s]
 58%|█████▊    | 215383/371472 [6:27:10<12:47:03,  3.39it/s]
 58%|█████▊    | 215384/371472 [6:27:10<12:55:05,  3.36it/s]
 58%|█████▊    | 215385/371472 [6:27:11<12:33:53,  3.45it/s]
 58%|█████▊    | 215386/371472 [6:27:11<13:05:19,  3.31it/s]
 58%|█████▊    | 215387/371472 [6:27:11<13:45:46,  3.15it/s]
 58%|█████▊    | 215388/371472 [6:27:12<15:11:46,  2.85it/s]
 58%|█████▊    | 215389/371472 [6:27:12<14:08:14,  3.07it/s]
 58%|█████▊    | 215390/371472 [6:27:12<13:38:34,  3.18it/s]
 58%|█████▊    | 215391/371472 [6:27:13<13:17:54,  3.26it/s]
 58%|█████▊    | 215392/371472 [6:27:13<13:23:31,  3.24it/s]
 58%|█████▊    | 215393/371472 [6:27:13<12:52:39,  3.37it/s]
 58%|█████▊    | 215394/371472 [6:27:14<12:59:53,  3.34it/s]
 58%|█████▊    | 215395/371472 [6:27:14<12:42:44,  3.41it/s]
 58%|█████▊    | 215396/371472 [6:27:14<12:39:47,  3.42it/s]
 58%|█████▊    | 215397/371472 [6:27:14<12:28:21,  3.48it/s]
 58%|█████▊    | 215398/371472 [6:27:15<12:19:28,  3.52it/s]
 58%|█████▊    | 215399/371472 [6:27:15<12:23:09,  3.50it/s]
 58%|█████▊    | 215400/371472 [6:27:15<12:55:48,  3.35it/s]
                                                            
{'loss': 2.6839, 'learning_rate': 4.783339438470985e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215400/371472 [6:27:15<12:55:48,  3.35it/s]
 58%|█████▊    | 215401/371472 [6:27:16<13:00:14,  3.33it/s]
 58%|█████▊    | 215402/371472 [6:27:16<12:43:40,  3.41it/s]
 58%|█████▊    | 215403/371472 [6:27:16<12:29:46,  3.47it/s]
 58%|█████▊    | 215404/371472 [6:27:16<12:29:00,  3.47it/s]
 58%|█████▊    | 215405/371472 [6:27:17<12:39:37,  3.42it/s]
 58%|█████▊    | 215406/371472 [6:27:17<13:23:58,  3.24it/s]
 58%|█████▊    | 215407/371472 [6:27:17<13:03:01,  3.32it/s]
 58%|█████▊    | 215408/371472 [6:27:18<14:01:28,  3.09it/s]
 58%|█████▊    | 215409/371472 [6:27:18<14:16:02,  3.04it/s]
 58%|█████▊    | 215410/371472 [6:27:18<13:59:29,  3.10it/s]
 58%|█████▊    | 215411/371472 [6:27:19<13:44:36,  3.15it/s]
 58%|█████▊    | 215412/371472 [6:27:19<13:23:26,  3.24it/s]
 58%|█████▊    | 215413/371472 [6:27:19<13:07:05,  3.30it/s]
 58%|█████▊    | 215414/371472 [6:27:20<13:19:41,  3.25it/s]
 58%|█████▊    | 215415/371472 [6:27:20<12:58:56,  3.34it/s]
 58%|█████▊    | 215416/371472 [6:27:20<12:59:34,  3.34it/s]
 58%|█████▊    | 215417/371472 [6:27:20<13:21:53,  3.24it/s]
 58%|█████▊    | 215418/371472 [6:27:21<13:24:29,  3.23it/s]
 58%|█████▊    | 215419/371472 [6:27:21<13:33:01,  3.20it/s]
 58%|█████▊    | 215420/371472 [6:27:21<13:18:30,  3.26it/s]
                                                            
{'loss': 2.7344, 'learning_rate': 4.782854618716198e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215420/371472 [6:27:21<13:18:30,  3.26it/s]
 58%|█████▊    | 215421/371472 [6:27:22<13:38:33,  3.18it/s]
 58%|█████▊    | 215422/371472 [6:27:22<14:02:40,  3.09it/s]
 58%|█████▊    | 215423/371472 [6:27:22<14:14:36,  3.04it/s]
 58%|█████▊    | 215424/371472 [6:27:23<13:32:36,  3.20it/s]
 58%|█████▊    | 215425/371472 [6:27:23<13:12:16,  3.28it/s]
 58%|█████▊    | 215426/371472 [6:27:23<14:26:03,  3.00it/s]
 58%|█████▊    | 215427/371472 [6:27:24<13:57:40,  3.10it/s]
 58%|█████▊    | 215428/371472 [6:27:24<13:17:18,  3.26it/s]
 58%|█████▊    | 215429/371472 [6:27:24<13:03:06,  3.32it/s]
 58%|█████▊    | 215430/371472 [6:27:25<12:52:02,  3.37it/s]
 58%|█████▊    | 215431/371472 [6:27:25<12:43:35,  3.41it/s]
 58%|█████▊    | 215432/371472 [6:27:25<12:39:33,  3.42it/s]
 58%|█████▊    | 215433/371472 [6:27:25<12:25:26,  3.49it/s]
 58%|█████▊    | 215434/371472 [6:27:26<13:17:43,  3.26it/s]
 58%|█████▊    | 215435/371472 [6:27:26<13:04:21,  3.32it/s]
 58%|█████▊    | 215436/371472 [6:27:26<12:49:35,  3.38it/s]
 58%|█████▊    | 215437/371472 [6:27:27<12:48:47,  3.38it/s]
 58%|█████▊    | 215438/371472 [6:27:27<12:39:56,  3.42it/s]
 58%|█████▊    | 215439/371472 [6:27:27<12:26:45,  3.48it/s]
 58%|█████▊    | 215440/371472 [6:27:27<12:27:39,  3.48it/s]
                                                            
{'loss': 2.7001, 'learning_rate': 4.782369798961408e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215440/371472 [6:27:27<12:27:39,  3.48it/s]
 58%|█████▊    | 215441/371472 [6:27:28<12:16:04,  3.53it/s]
 58%|█████▊    | 215442/371472 [6:27:28<12:15:02,  3.54it/s]
 58%|█████▊    | 215443/371472 [6:27:28<12:17:21,  3.53it/s]
 58%|█████▊    | 215444/371472 [6:27:29<12:09:41,  3.56it/s]
 58%|█████▊    | 215445/371472 [6:27:29<12:20:33,  3.51it/s]
 58%|█████▊    | 215446/371472 [6:27:29<12:13:30,  3.55it/s]
 58%|█████▊    | 215447/371472 [6:27:29<12:07:23,  3.58it/s]
 58%|█████▊    | 215448/371472 [6:27:30<12:15:39,  3.53it/s]
 58%|█████▊    | 215449/371472 [6:27:30<12:40:06,  3.42it/s]
 58%|█████▊    | 215450/371472 [6:27:30<13:03:49,  3.32it/s]
 58%|█████▊    | 215451/371472 [6:27:31<12:35:34,  3.44it/s]
 58%|█████▊    | 215452/371472 [6:27:31<12:28:01,  3.48it/s]
 58%|█████▊    | 215453/371472 [6:27:31<12:12:58,  3.55it/s]
 58%|█████▊    | 215454/371472 [6:27:31<12:16:00,  3.53it/s]
 58%|█████▊    | 215455/371472 [6:27:32<12:06:46,  3.58it/s]
 58%|█████▊    | 215456/371472 [6:27:32<12:20:04,  3.51it/s]
 58%|█████▊    | 215457/371472 [6:27:32<12:30:10,  3.47it/s]
 58%|█████▊    | 215458/371472 [6:27:33<12:15:18,  3.54it/s]
 58%|█████▊    | 215459/371472 [6:27:33<12:00:25,  3.61it/s]
 58%|█████▊    | 215460/371472 [6:27:33<11:53:55,  3.64it/s]
                                                            
{'loss': 2.7773, 'learning_rate': 4.781884979206619e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215460/371472 [6:27:33<11:53:55,  3.64it/s]
 58%|█████▊    | 215461/371472 [6:27:33<12:08:03,  3.57it/s]
 58%|█████▊    | 215462/371472 [6:27:34<12:13:02,  3.55it/s]
 58%|█████▊    | 215463/371472 [6:27:34<12:14:27,  3.54it/s]
 58%|█████▊    | 215464/371472 [6:27:34<12:29:54,  3.47it/s]
 58%|█████▊    | 215465/371472 [6:27:35<13:24:37,  3.23it/s]
 58%|█████▊    | 215466/371472 [6:27:35<13:08:31,  3.30it/s]
 58%|█████▊    | 215467/371472 [6:27:35<13:04:51,  3.31it/s]
 58%|█████▊    | 215468/371472 [6:27:36<14:31:15,  2.98it/s]
 58%|█████▊    | 215469/371472 [6:27:36<14:02:25,  3.09it/s]
 58%|█████▊    | 215470/371472 [6:27:36<13:16:47,  3.26it/s]
 58%|█████▊    | 215471/371472 [6:27:37<14:10:37,  3.06it/s]
 58%|█████▊    | 215472/371472 [6:27:37<13:51:37,  3.13it/s]
 58%|█████▊    | 215473/371472 [6:27:37<13:28:54,  3.21it/s]
 58%|█████▊    | 215474/371472 [6:27:38<13:48:41,  3.14it/s]
 58%|█████▊    | 215475/371472 [6:27:38<13:18:22,  3.26it/s]
 58%|█████▊    | 215476/371472 [6:27:38<13:06:07,  3.31it/s]
 58%|█████▊    | 215477/371472 [6:27:38<13:11:05,  3.29it/s]
 58%|█████▊    | 215478/371472 [6:27:39<12:54:00,  3.36it/s]
 58%|█████▊    | 215479/371472 [6:27:39<12:48:46,  3.38it/s]
 58%|█████▊    | 215480/371472 [6:27:39<12:40:28,  3.42it/s]
                                                            
{'loss': 2.8666, 'learning_rate': 4.78140015945183e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215480/371472 [6:27:39<12:40:28,  3.42it/s]
 58%|█████▊    | 215481/371472 [6:27:40<12:52:05,  3.37it/s]
 58%|█████▊    | 215482/371472 [6:27:40<12:52:27,  3.37it/s]
 58%|█████▊    | 215483/371472 [6:27:40<12:47:40,  3.39it/s]
 58%|█████▊    | 215484/371472 [6:27:40<12:53:23,  3.36it/s]
 58%|█████▊    | 215485/371472 [6:27:41<13:16:36,  3.26it/s]
 58%|█████▊    | 215486/371472 [6:27:41<12:56:13,  3.35it/s]
 58%|█████▊    | 215487/371472 [6:27:41<12:23:06,  3.50it/s]
 58%|█████▊    | 215488/371472 [6:27:42<12:22:05,  3.50it/s]
 58%|█████▊    | 215489/371472 [6:27:42<12:07:44,  3.57it/s]
 58%|█████▊    | 215490/371472 [6:27:42<12:10:57,  3.56it/s]
 58%|█████▊    | 215491/371472 [6:27:42<11:48:16,  3.67it/s]
 58%|█████▊    | 215492/371472 [6:27:43<11:35:37,  3.74it/s]
 58%|█████▊    | 215493/371472 [6:27:43<11:58:02,  3.62it/s]
 58%|█████▊    | 215494/371472 [6:27:43<12:19:40,  3.51it/s]
 58%|█████▊    | 215495/371472 [6:27:44<12:30:31,  3.46it/s]
 58%|█████▊    | 215496/371472 [6:27:44<12:49:10,  3.38it/s]
 58%|█████▊    | 215497/371472 [6:27:44<13:03:23,  3.32it/s]
 58%|█████▊    | 215498/371472 [6:27:44<12:38:01,  3.43it/s]
 58%|█████▊    | 215499/371472 [6:27:45<12:18:40,  3.52it/s]
 58%|█████▊    | 215500/371472 [6:27:45<12:22:41,  3.50it/s]
                                                            
{'loss': 2.7814, 'learning_rate': 4.780915339697041e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215500/371472 [6:27:45<12:22:41,  3.50it/s]
 58%|█████▊    | 215501/371472 [6:27:45<12:58:14,  3.34it/s]
 58%|█████▊    | 215502/371472 [6:27:46<12:43:55,  3.40it/s]
 58%|█████▊    | 215503/371472 [6:27:46<12:50:28,  3.37it/s]
 58%|█████▊    | 215504/371472 [6:27:46<12:40:28,  3.42it/s]
 58%|█████▊    | 215505/371472 [6:27:47<13:53:33,  3.12it/s]
 58%|█████▊    | 215506/371472 [6:27:47<13:22:45,  3.24it/s]
 58%|█████▊    | 215507/371472 [6:27:47<13:05:32,  3.31it/s]
 58%|█████▊    | 215508/371472 [6:27:47<13:18:29,  3.26it/s]
 58%|█████▊    | 215509/371472 [6:27:48<14:28:38,  2.99it/s]
 58%|█████▊    | 215510/371472 [6:27:48<13:31:32,  3.20it/s]
 58%|█████▊    | 215511/371472 [6:27:48<13:26:34,  3.22it/s]
 58%|█████▊    | 215512/371472 [6:27:49<12:48:50,  3.38it/s]
 58%|█████▊    | 215513/371472 [6:27:49<12:52:46,  3.36it/s]
 58%|█████▊    | 215514/371472 [6:27:49<13:00:02,  3.33it/s]
 58%|█████▊    | 215515/371472 [6:27:50<13:08:07,  3.30it/s]
 58%|█████▊    | 215516/371472 [6:27:50<13:20:35,  3.25it/s]
 58%|█████▊    | 215517/371472 [6:27:50<13:12:39,  3.28it/s]
 58%|█████▊    | 215518/371472 [6:27:51<13:40:46,  3.17it/s]
 58%|█████▊    | 215519/371472 [6:27:51<13:22:19,  3.24it/s]
 58%|█████▊    | 215520/371472 [6:27:51<13:30:45,  3.21it/s]
                                                            
{'loss': 2.6307, 'learning_rate': 4.780430519942252e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215520/371472 [6:27:51<13:30:45,  3.21it/s]
 58%|█████▊    | 215521/371472 [6:27:51<12:50:01,  3.38it/s]
 58%|█████▊    | 215522/371472 [6:27:52<12:27:00,  3.48it/s]
 58%|█████▊    | 215523/371472 [6:27:52<12:03:51,  3.59it/s]
 58%|█████▊    | 215524/371472 [6:27:52<12:22:35,  3.50it/s]
 58%|█████▊    | 215525/371472 [6:27:53<12:13:57,  3.54it/s]
 58%|█████▊    | 215526/371472 [6:27:53<11:51:01,  3.66it/s]
 58%|█████▊    | 215527/371472 [6:27:53<12:54:27,  3.36it/s]
 58%|█████▊    | 215528/371472 [6:27:53<12:44:38,  3.40it/s]
 58%|█████▊    | 215529/371472 [6:27:54<13:24:38,  3.23it/s]
 58%|█████▊    | 215530/371472 [6:27:54<13:29:53,  3.21it/s]
 58%|█████▊    | 215531/371472 [6:27:54<13:12:12,  3.28it/s]
 58%|█████▊    | 215532/371472 [6:27:55<13:06:42,  3.30it/s]
 58%|█████▊    | 215533/371472 [6:27:55<13:14:32,  3.27it/s]
 58%|█████▊    | 215534/371472 [6:27:55<13:15:40,  3.27it/s]
 58%|█████▊    | 215535/371472 [6:27:56<12:54:52,  3.35it/s]
 58%|█████▊    | 215536/371472 [6:27:56<12:28:45,  3.47it/s]
 58%|█████▊    | 215537/371472 [6:27:56<12:15:33,  3.53it/s]
 58%|█████▊    | 215538/371472 [6:27:56<12:06:50,  3.58it/s]
 58%|█████▊    | 215539/371472 [6:27:57<13:14:08,  3.27it/s]
 58%|█████▊    | 215540/371472 [6:27:57<13:13:48,  3.27it/s]
                                                            
{'loss': 2.8385, 'learning_rate': 4.779945700187464e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215540/371472 [6:27:57<13:13:48,  3.27it/s]
 58%|█████▊    | 215541/371472 [6:27:57<12:58:30,  3.34it/s]
 58%|█████▊    | 215542/371472 [6:27:58<12:54:16,  3.36it/s]
 58%|█████▊    | 215543/371472 [6:27:58<12:28:50,  3.47it/s]
 58%|█████▊    | 215544/371472 [6:27:58<12:40:27,  3.42it/s]
 58%|█████▊    | 215545/371472 [6:27:58<12:22:30,  3.50it/s]
 58%|█████▊    | 215546/371472 [6:27:59<12:25:25,  3.49it/s]
 58%|█████▊    | 215547/371472 [6:27:59<12:15:42,  3.53it/s]
 58%|█████▊    | 215548/371472 [6:27:59<12:05:39,  3.58it/s]
 58%|█████▊    | 215549/371472 [6:28:00<12:11:09,  3.55it/s]
 58%|█████▊    | 215550/371472 [6:28:00<13:05:48,  3.31it/s]
 58%|█████▊    | 215551/371472 [6:28:00<12:49:40,  3.38it/s]
 58%|█████▊    | 215552/371472 [6:28:00<12:25:21,  3.49it/s]
 58%|█████▊    | 215553/371472 [6:28:01<12:23:14,  3.50it/s]
 58%|█████▊    | 215554/371472 [6:28:01<12:29:09,  3.47it/s]
 58%|█████▊    | 215555/371472 [6:28:01<12:25:08,  3.49it/s]
 58%|█████▊    | 215556/371472 [6:28:02<12:19:04,  3.52it/s]
 58%|█████▊    | 215557/371472 [6:28:02<12:02:17,  3.60it/s]
 58%|█████▊    | 215558/371472 [6:28:02<12:06:16,  3.58it/s]
 58%|█████▊    | 215559/371472 [6:28:02<12:05:59,  3.58it/s]
 58%|█████▊    | 215560/371472 [6:28:03<12:04:30,  3.59it/s]
                                                            
{'loss': 2.9439, 'learning_rate': 4.779460880432675e-07, 'epoch': 9.28}
+
 58%|█████▊    | 215560/371472 [6:28:03<12:04:30,  3.59it/s]
 58%|█████▊    | 215561/371472 [6:28:03<11:56:24,  3.63it/s]
 58%|█████▊    | 215562/371472 [6:28:03<12:11:58,  3.55it/s]
 58%|█████▊    | 215563/371472 [6:28:04<12:28:47,  3.47it/s]
 58%|█████▊    | 215564/371472 [6:28:04<13:02:39,  3.32it/s]
 58%|█████▊    | 215565/371472 [6:28:04<12:40:04,  3.42it/s]
 58%|█████▊    | 215566/371472 [6:28:04<12:32:11,  3.45it/s]
 58%|█████▊    | 215567/371472 [6:28:05<12:32:15,  3.45it/s]
 58%|█████▊    | 215568/371472 [6:28:05<12:22:00,  3.50it/s]
 58%|█████▊    | 215569/371472 [6:28:05<12:20:22,  3.51it/s]
 58%|█████▊    | 215570/371472 [6:28:06<12:13:40,  3.54it/s]
 58%|█████▊    | 215571/371472 [6:28:06<11:58:07,  3.62it/s]
 58%|█████▊    | 215572/371472 [6:28:06<12:05:51,  3.58it/s]
 58%|█████▊    | 215573/371472 [6:28:06<12:36:01,  3.44it/s]
 58%|█████▊    | 215574/371472 [6:28:07<13:10:15,  3.29it/s]
 58%|█████▊    | 215575/371472 [6:28:07<13:30:58,  3.20it/s]
 58%|█████▊    | 215576/371472 [6:28:07<13:33:19,  3.19it/s]
 58%|█████▊    | 215577/371472 [6:28:08<13:39:24,  3.17it/s]
 58%|█████▊    | 215578/371472 [6:28:08<12:58:51,  3.34it/s]
 58%|█████▊    | 215579/371472 [6:28:08<13:09:49,  3.29it/s]
 58%|█████▊    | 215580/371472 [6:28:09<12:51:15,  3.37it/s]
                                                            
{'loss': 2.8195, 'learning_rate': 4.778976060677886e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215580/371472 [6:28:09<12:51:15,  3.37it/s]
 58%|█████▊    | 215581/371472 [6:28:09<12:46:49,  3.39it/s]
 58%|█████▊    | 215582/371472 [6:28:09<12:38:17,  3.43it/s]
 58%|█████▊    | 215583/371472 [6:28:10<12:29:51,  3.46it/s]
 58%|█████▊    | 215584/371472 [6:28:10<12:29:27,  3.47it/s]
 58%|█████▊    | 215585/371472 [6:28:10<12:26:18,  3.48it/s]
 58%|█████▊    | 215586/371472 [6:28:10<12:21:10,  3.51it/s]
 58%|█████▊    | 215587/371472 [6:28:11<12:03:33,  3.59it/s]
 58%|█████▊    | 215588/371472 [6:28:11<12:15:29,  3.53it/s]
 58%|█████▊    | 215589/371472 [6:28:11<12:31:35,  3.46it/s]
 58%|█████▊    | 215590/371472 [6:28:11<12:13:38,  3.54it/s]
 58%|█████▊    | 215591/371472 [6:28:12<12:28:12,  3.47it/s]
 58%|█████▊    | 215592/371472 [6:28:12<12:12:05,  3.55it/s]
 58%|█████▊    | 215593/371472 [6:28:12<12:29:11,  3.47it/s]
 58%|█████▊    | 215594/371472 [6:28:13<12:21:41,  3.50it/s]
 58%|█████▊    | 215595/371472 [6:28:13<12:14:18,  3.54it/s]
 58%|█████▊    | 215596/371472 [6:28:13<12:58:20,  3.34it/s]
 58%|█████▊    | 215597/371472 [6:28:14<12:32:26,  3.45it/s]
 58%|█████▊    | 215598/371472 [6:28:14<13:20:35,  3.24it/s]
 58%|█████▊    | 215599/371472 [6:28:14<13:05:25,  3.31it/s]
 58%|█████▊    | 215600/371472 [6:28:14<12:39:00,  3.42it/s]
                                                            
{'loss': 2.8578, 'learning_rate': 4.778491240923097e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215600/371472 [6:28:14<12:39:00,  3.42it/s]
 58%|█████▊    | 215601/371472 [6:28:15<13:22:52,  3.24it/s]
 58%|█████▊    | 215602/371472 [6:28:15<13:10:09,  3.29it/s]
 58%|█████▊    | 215603/371472 [6:28:15<12:51:57,  3.37it/s]
 58%|█████▊    | 215604/371472 [6:28:16<12:52:27,  3.36it/s]
 58%|█████▊    | 215605/371472 [6:28:16<12:34:05,  3.44it/s]
 58%|█████▊    | 215606/371472 [6:28:16<12:26:59,  3.48it/s]
 58%|█████▊    | 215607/371472 [6:28:16<12:10:32,  3.56it/s]
 58%|█████▊    | 215608/371472 [6:28:17<11:56:06,  3.63it/s]
 58%|█████▊    | 215609/371472 [6:28:17<12:02:00,  3.60it/s]
 58%|█████▊    | 215610/371472 [6:28:17<12:16:57,  3.52it/s]
 58%|█████▊    | 215611/371472 [6:28:18<12:59:05,  3.33it/s]
 58%|█████▊    | 215612/371472 [6:28:18<12:49:55,  3.37it/s]
 58%|█████▊    | 215613/371472 [6:28:18<13:03:02,  3.32it/s]
 58%|█████▊    | 215614/371472 [6:28:19<13:05:32,  3.31it/s]
 58%|█████▊    | 215615/371472 [6:28:19<12:44:06,  3.40it/s]
 58%|█████▊    | 215616/371472 [6:28:19<12:30:41,  3.46it/s]
 58%|█████▊    | 215617/371472 [6:28:19<12:20:38,  3.51it/s]
 58%|█████▊    | 215618/371472 [6:28:20<15:00:51,  2.88it/s]
 58%|█████▊    | 215619/371472 [6:28:20<14:26:59,  3.00it/s]
 58%|█��███▊    | 215620/371472 [6:28:20<14:04:58,  3.07it/s]
                                                            
{'loss': 2.8657, 'learning_rate': 4.778006421168308e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215620/371472 [6:28:20<14:04:58,  3.07it/s]
 58%|█████▊    | 215621/371472 [6:28:21<13:26:00,  3.22it/s]
 58%|█████▊    | 215622/371472 [6:28:21<13:23:32,  3.23it/s]
 58%|█████▊    | 215623/371472 [6:28:21<13:22:42,  3.24it/s]
 58%|█████▊    | 215624/371472 [6:28:22<12:48:20,  3.38it/s]
 58%|█████▊    | 215625/371472 [6:28:22<12:33:39,  3.45it/s]
 58%|█████▊    | 215626/371472 [6:28:22<12:21:43,  3.50it/s]
 58%|█████▊    | 215627/371472 [6:28:22<12:11:29,  3.55it/s]
 58%|█████▊    | 215628/371472 [6:28:23<12:00:06,  3.61it/s]
 58%|█████▊    | 215629/371472 [6:28:23<12:07:48,  3.57it/s]
 58%|█████▊    | 215630/371472 [6:28:23<11:51:47,  3.65it/s]
 58%|█████▊    | 215631/371472 [6:28:24<11:52:54,  3.64it/s]
 58%|█████▊    | 215632/371472 [6:28:24<11:41:13,  3.70it/s]
 58%|█████▊    | 215633/371472 [6:28:24<11:46:24,  3.68it/s]
 58%|█████▊    | 215634/371472 [6:28:24<12:26:55,  3.48it/s]
 58%|█████▊    | 215635/371472 [6:28:25<12:14:12,  3.54it/s]
 58%|█████▊    | 215636/371472 [6:28:25<12:14:12,  3.54it/s]
 58%|█████▊    | 215637/371472 [6:28:25<12:00:36,  3.60it/s]
 58%|█████▊    | 215638/371472 [6:28:26<12:49:58,  3.37it/s]
 58%|█████▊    | 215639/371472 [6:28:26<13:03:48,  3.31it/s]
 58%|█████▊    | 215640/371472 [6:28:26<13:18:10,  3.25it/s]
                                                            
{'loss': 2.8134, 'learning_rate': 4.777521601413518e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215640/371472 [6:28:26<13:18:10,  3.25it/s]
 58%|█████▊    | 215641/371472 [6:28:26<13:01:42,  3.32it/s]
 58%|█████▊    | 215642/371472 [6:28:27<12:34:34,  3.44it/s]
 58%|█████▊    | 215643/371472 [6:28:27<12:35:59,  3.44it/s]
 58%|█████▊    | 215644/371472 [6:28:27<13:26:26,  3.22it/s]
 58%|█████▊    | 215645/371472 [6:28:28<13:34:08,  3.19it/s]
 58%|█████▊    | 215646/371472 [6:28:28<14:03:29,  3.08it/s]
 58%|█████▊    | 215647/371472 [6:28:28<13:57:08,  3.10it/s]
 58%|█████▊    | 215648/371472 [6:28:29<15:01:03,  2.88it/s]
 58%|█████▊    | 215649/371472 [6:28:29<13:59:50,  3.09it/s]
 58%|█████▊    | 215650/371472 [6:28:29<13:15:56,  3.26it/s]
 58%|█████▊    | 215651/371472 [6:28:30<13:06:57,  3.30it/s]
 58%|█████▊    | 215652/371472 [6:28:30<13:30:28,  3.20it/s]
 58%|█████▊    | 215653/371472 [6:28:30<15:19:00,  2.83it/s]
 58%|█████▊    | 215654/371472 [6:28:31<14:18:29,  3.03it/s]
 58%|█████▊    | 215655/371472 [6:28:31<13:34:14,  3.19it/s]
 58%|█████▊    | 215656/371472 [6:28:31<13:29:13,  3.21it/s]
 58%|█████▊    | 215657/371472 [6:28:32<13:15:49,  3.26it/s]
 58%|█████▊    | 215658/371472 [6:28:32<12:53:16,  3.36it/s]
 58%|█████▊    | 215659/371472 [6:28:32<13:26:26,  3.22it/s]
 58%|█████▊    | 215660/371472 [6:28:32<12:55:52,  3.35it/s]
                                                            
{'loss': 2.8343, 'learning_rate': 4.777036781658731e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215660/371472 [6:28:32<12:55:52,  3.35it/s]
 58%|█████▊    | 215661/371472 [6:28:33<13:14:11,  3.27it/s]
 58%|█████▊    | 215662/371472 [6:28:33<13:20:01,  3.25it/s]
 58%|█████▊    | 215663/371472 [6:28:33<13:21:03,  3.24it/s]
 58%|█████▊    | 215664/371472 [6:28:34<13:12:46,  3.28it/s]
 58%|█████▊    | 215665/371472 [6:28:34<12:59:05,  3.33it/s]
 58%|█████▊    | 215666/371472 [6:28:34<12:34:43,  3.44it/s]
 58%|█████▊    | 215667/371472 [6:28:35<12:27:18,  3.47it/s]
 58%|█████▊    | 215668/371472 [6:28:35<12:28:34,  3.47it/s]
 58%|█████▊    | 215669/371472 [6:28:35<12:18:59,  3.51it/s]
 58%|█████▊    | 215670/371472 [6:28:35<12:17:25,  3.52it/s]
 58%|█████▊    | 215671/371472 [6:28:36<13:18:38,  3.25it/s]
 58%|█████▊    | 215672/371472 [6:28:36<13:05:13,  3.31it/s]
 58%|█████▊    | 215673/371472 [6:28:36<12:46:30,  3.39it/s]
 58%|█████▊    | 215674/371472 [6:28:37<13:15:18,  3.26it/s]
 58%|█████▊    | 215675/371472 [6:28:37<13:29:50,  3.21it/s]
 58%|█████▊    | 215676/371472 [6:28:37<13:26:38,  3.22it/s]
 58%|█████▊    | 215677/371472 [6:28:38<13:54:07,  3.11it/s]
 58%|█████▊    | 215678/371472 [6:28:38<13:47:57,  3.14it/s]
 58%|█████▊    | 215679/371472 [6:28:38<14:01:21,  3.09it/s]
 58%|█████▊    | 215680/371472 [6:28:39<13:41:01,  3.16it/s]
                                                            
{'loss': 2.656, 'learning_rate': 4.776551961903942e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215680/371472 [6:28:39<13:41:01,  3.16it/s]
 58%|█████▊    | 215681/371472 [6:28:39<13:37:51,  3.17it/s]
 58%|█████▊    | 215682/371472 [6:28:39<13:53:24,  3.12it/s]
 58%|█████▊    | 215683/371472 [6:28:40<14:41:02,  2.95it/s]
 58%|█████▊    | 215684/371472 [6:28:40<14:20:56,  3.02it/s]
 58%|█████▊    | 215685/371472 [6:28:40<14:04:05,  3.08it/s]
 58%|█████▊    | 215686/371472 [6:28:41<13:35:59,  3.18it/s]
 58%|█████▊    | 215687/371472 [6:28:41<13:27:48,  3.21it/s]
 58%|█████▊    | 215688/371472 [6:28:41<13:24:11,  3.23it/s]
 58%|█████▊    | 215689/371472 [6:28:41<12:56:20,  3.34it/s]
 58%|█████▊    | 215690/371472 [6:28:42<13:12:06,  3.28it/s]
 58%|█████▊    | 215691/371472 [6:28:42<13:00:19,  3.33it/s]
 58%|█████▊    | 215692/371472 [6:28:42<12:55:55,  3.35it/s]
 58%|█████▊    | 215693/371472 [6:28:43<12:54:44,  3.35it/s]
 58%|█████▊    | 215694/371472 [6:28:43<12:35:46,  3.44it/s]
 58%|█████▊    | 215695/371472 [6:28:43<13:56:56,  3.10it/s]
 58%|█████▊    | 215696/371472 [6:28:44<14:11:23,  3.05it/s]
 58%|█████▊    | 215697/371472 [6:28:44<13:28:16,  3.21it/s]
 58%|█████▊    | 215698/371472 [6:28:44<13:28:00,  3.21it/s]
 58%|█████▊    | 215699/371472 [6:28:44<13:07:08,  3.30it/s]
 58%|█████▊    | 215700/371472 [6:28:45<12:52:21,  3.36it/s]
                                                            
{'loss': 2.6626, 'learning_rate': 4.776067142149151e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215700/371472 [6:28:45<12:52:21,  3.36it/s]
 58%|█████▊    | 215701/371472 [6:28:45<12:43:52,  3.40it/s]
 58%|█████▊    | 215702/371472 [6:28:45<13:07:35,  3.30it/s]
 58%|█████▊    | 215703/371472 [6:28:46<13:03:02,  3.32it/s]
 58%|█████▊    | 215704/371472 [6:28:46<12:45:25,  3.39it/s]
 58%|█████▊    | 215705/371472 [6:28:46<14:17:08,  3.03it/s]
 58%|█████▊    | 215706/371472 [6:28:47<13:36:50,  3.18it/s]
 58%|█████▊    | 215707/371472 [6:28:47<13:02:10,  3.32it/s]
 58%|█████▊    | 215708/371472 [6:28:47<15:06:50,  2.86it/s]
 58%|█████▊    | 215709/371472 [6:28:48<14:25:32,  3.00it/s]
 58%|█████▊    | 215710/371472 [6:28:48<14:13:57,  3.04it/s]
 58%|█████▊    | 215711/371472 [6:28:48<14:03:04,  3.08it/s]
 58%|█████▊    | 215712/371472 [6:28:49<13:15:08,  3.26it/s]
 58%|█████▊    | 215713/371472 [6:28:49<13:15:28,  3.26it/s]
 58%|█████▊    | 215714/371472 [6:28:49<12:50:49,  3.37it/s]
 58%|█████▊    | 215715/371472 [6:28:49<12:29:47,  3.46it/s]
 58%|█████▊    | 215716/371472 [6:28:50<12:22:48,  3.49it/s]
 58%|█████▊    | 215717/371472 [6:28:50<12:46:06,  3.39it/s]
 58%|█████▊    | 215718/371472 [6:28:50<13:30:47,  3.20it/s]
 58%|█████▊    | 215719/371472 [6:28:51<13:42:59,  3.15it/s]
 58%|█████▊    | 215720/371472 [6:28:51<14:07:40,  3.06it/s]
                                                            
{'loss': 2.8446, 'learning_rate': 4.775582322394363e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215720/371472 [6:28:51<14:07:40,  3.06it/s]
 58%|█████▊    | 215721/371472 [6:28:51<15:02:32,  2.88it/s]
 58%|█████▊    | 215722/371472 [6:28:52<14:23:42,  3.01it/s]
 58%|█████▊    | 215723/371472 [6:28:52<13:44:34,  3.15it/s]
 58%|█████▊    | 215724/371472 [6:28:52<13:45:08,  3.15it/s]
 58%|█████▊    | 215725/371472 [6:28:53<13:23:11,  3.23it/s]
 58%|█████▊    | 215726/371472 [6:28:53<13:34:08,  3.19it/s]
 58%|█████▊    | 215727/371472 [6:28:53<13:07:45,  3.30it/s]
 58%|█████▊    | 215728/371472 [6:28:53<12:39:23,  3.42it/s]
 58%|█████▊    | 215729/371472 [6:28:54<12:54:23,  3.35it/s]
 58%|█████▊    | 215730/371472 [6:28:54<13:19:45,  3.25it/s]
 58%|█████▊    | 215731/371472 [6:28:54<12:58:22,  3.33it/s]
 58%|█████▊    | 215732/371472 [6:28:55<12:28:14,  3.47it/s]
 58%|█████▊    | 215733/371472 [6:28:55<12:29:58,  3.46it/s]
 58%|█████▊    | 215734/371472 [6:28:55<12:41:46,  3.41it/s]
 58%|█████▊    | 215735/371472 [6:28:56<13:02:10,  3.32it/s]
 58%|█████▊    | 215736/371472 [6:28:56<13:31:12,  3.20it/s]
 58%|█████▊    | 215737/371472 [6:28:56<13:16:16,  3.26it/s]
 58%|█████▊    | 215738/371472 [6:28:57<13:04:45,  3.31it/s]
 58%|█████▊    | 215739/371472 [6:28:57<12:38:03,  3.42it/s]
 58%|█████▊    | 215740/371472 [6:28:57<12:45:31,  3.39it/s]
                                                            
{'loss': 2.7615, 'learning_rate': 4.775097502639574e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215740/371472 [6:28:57<12:45:31,  3.39it/s]
 58%|█████▊    | 215741/371472 [6:28:57<12:41:18,  3.41it/s]
 58%|█████▊    | 215742/371472 [6:28:58<12:30:39,  3.46it/s]
 58%|█████▊    | 215743/371472 [6:28:58<12:56:32,  3.34it/s]
 58%|█████▊    | 215744/371472 [6:28:58<12:23:15,  3.49it/s]
 58%|█████▊    | 215745/371472 [6:28:59<12:45:07,  3.39it/s]
 58%|█████▊    | 215746/371472 [6:28:59<12:40:20,  3.41it/s]
 58%|█████▊    | 215747/371472 [6:28:59<12:20:59,  3.50it/s]
 58%|█████▊    | 215748/371472 [6:28:59<12:17:38,  3.52it/s]
 58%|█████▊    | 215749/371472 [6:29:00<12:54:56,  3.35it/s]
 58%|█████▊    | 215750/371472 [6:29:00<13:07:15,  3.30it/s]
 58%|█████▊    | 215751/371472 [6:29:00<12:37:35,  3.43it/s]
 58%|█████▊    | 215752/371472 [6:29:01<12:25:11,  3.48it/s]
 58%|█████▊    | 215753/371472 [6:29:01<12:11:30,  3.55it/s]
 58%|█████▊    | 215754/371472 [6:29:01<12:34:11,  3.44it/s]
 58%|█████▊    | 215755/371472 [6:29:02<13:17:14,  3.26it/s]
 58%|█████▊    | 215756/371472 [6:29:02<13:25:12,  3.22it/s]
 58%|█████▊    | 215757/371472 [6:29:02<12:58:24,  3.33it/s]
 58%|█████▊    | 215758/371472 [6:29:02<12:30:59,  3.46it/s]
 58%|█████▊    | 215759/371472 [6:29:03<12:25:40,  3.48it/s]
 58%|█████▊    | 215760/371472 [6:29:03<12:18:04,  3.52it/s]
                                                            
{'loss': 2.8748, 'learning_rate': 4.774612682884784e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215760/371472 [6:29:03<12:18:04,  3.52it/s]
 58%|█████▊    | 215761/371472 [6:29:03<12:55:10,  3.35it/s]
 58%|█████▊    | 215762/371472 [6:29:04<12:39:01,  3.42it/s]
 58%|█████▊    | 215763/371472 [6:29:04<12:24:01,  3.49it/s]
 58%|█████▊    | 215764/371472 [6:29:04<12:13:46,  3.54it/s]
 58%|█████▊    | 215765/371472 [6:29:04<11:50:08,  3.65it/s]
 58%|█████▊    | 215766/371472 [6:29:05<11:49:55,  3.66it/s]
 58%|█████▊    | 215767/371472 [6:29:05<12:44:18,  3.40it/s]
 58%|█████▊    | 215768/371472 [6:29:05<12:27:52,  3.47it/s]
 58%|█████▊    | 215769/371472 [6:29:06<13:00:16,  3.33it/s]
 58%|█████▊    | 215770/371472 [6:29:06<12:23:54,  3.49it/s]
 58%|█████▊    | 215771/371472 [6:29:06<12:23:31,  3.49it/s]
 58%|█████▊    | 215772/371472 [6:29:06<12:08:00,  3.56it/s]
 58%|█████▊    | 215773/371472 [6:29:07<14:09:07,  3.06it/s]
 58%|█████▊    | 215774/371472 [6:29:07<13:39:10,  3.17it/s]
 58%|█████▊    | 215775/371472 [6:29:08<15:13:58,  2.84it/s]
 58%|█████▊    | 215776/371472 [6:29:08<14:31:12,  2.98it/s]
 58%|█████▊    | 215777/371472 [6:29:08<14:42:21,  2.94it/s]
 58%|█████▊    | 215778/371472 [6:29:08<13:46:00,  3.14it/s]
 58%|█████▊    | 215779/371472 [6:29:09<13:26:00,  3.22it/s]
 58%|█████▊    | 215780/371472 [6:29:09<13:18:20,  3.25it/s]
                                                            
{'loss': 2.9536, 'learning_rate': 4.774127863129995e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215780/371472 [6:29:09<13:18:20,  3.25it/s]
 58%|█████▊    | 215781/371472 [6:29:09<13:42:40,  3.15it/s]
 58%|█████▊    | 215782/371472 [6:29:10<13:33:27,  3.19it/s]
 58%|█████▊    | 215783/371472 [6:29:10<14:09:12,  3.06it/s]
 58%|█████▊    | 215784/371472 [6:29:10<13:41:38,  3.16it/s]
 58%|█████▊    | 215785/371472 [6:29:11<13:14:15,  3.27it/s]
 58%|█████▊    | 215786/371472 [6:29:11<13:40:35,  3.16it/s]
 58%|█████▊    | 215787/371472 [6:29:11<13:57:03,  3.10it/s]
 58%|█████▊    | 215788/371472 [6:29:12<13:00:23,  3.32it/s]
 58%|█████▊    | 215789/371472 [6:29:12<12:59:42,  3.33it/s]
 58%|█████▊    | 215790/371472 [6:29:12<12:49:45,  3.37it/s]
 58%|█████▊    | 215791/371472 [6:29:12<12:47:33,  3.38it/s]
 58%|█████▊    | 215792/371472 [6:29:13<13:40:11,  3.16it/s]
 58%|█████▊    | 215793/371472 [6:29:13<15:11:26,  2.85it/s]
 58%|█████▊    | 215794/371472 [6:29:13<14:21:00,  3.01it/s]
 58%|█████▊    | 215795/371472 [6:29:14<13:53:08,  3.11it/s]
 58%|█████▊    | 215796/371472 [6:29:14<13:16:24,  3.26it/s]
 58%|█████▊    | 215797/371472 [6:29:14<12:44:38,  3.39it/s]
 58%|█████▊    | 215798/371472 [6:29:15<12:25:06,  3.48it/s]
 58%|█████▊    | 215799/371472 [6:29:15<12:15:12,  3.53it/s]
 58%|█████▊    | 215800/371472 [6:29:15<12:29:12,  3.46it/s]
                                                            
{'loss': 2.6563, 'learning_rate': 4.773643043375208e-07, 'epoch': 9.29}
+
 58%|█████▊    | 215800/371472 [6:29:15<12:29:12,  3.46it/s]
 58%|█████▊    | 215801/371472 [6:29:15<12:17:09,  3.52it/s]
 58%|█████▊    | 215802/371472 [6:29:16<12:09:34,  3.56it/s]
 58%|█████▊    | 215803/371472 [6:29:16<12:43:29,  3.40it/s]
 58%|█████▊    | 215804/371472 [6:29:16<12:52:45,  3.36it/s]
 58%|█████▊    | 215805/371472 [6:29:17<13:02:25,  3.32it/s]
 58%|█████▊    | 215806/371472 [6:29:17<12:21:39,  3.50it/s]
 58%|█████▊    | 215807/371472 [6:29:17<12:29:32,  3.46it/s]
 58%|█████▊    | 215808/371472 [6:29:18<12:59:13,  3.33it/s]
 58%|█████▊    | 215809/371472 [6:29:18<13:13:02,  3.27it/s]
 58%|█████▊    | 215810/371472 [6:29:18<12:53:11,  3.36it/s]
 58%|█████▊    | 215811/371472 [6:29:18<12:51:33,  3.36it/s]
 58%|█████▊    | 215812/371472 [6:29:19<12:59:15,  3.33it/s]
 58%|█████▊    | 215813/371472 [6:29:19<12:46:11,  3.39it/s]
 58%|█████▊    | 215814/371472 [6:29:19<13:16:08,  3.26it/s]
 58%|█████▊    | 215815/371472 [6:29:20<12:49:59,  3.37it/s]
 58%|█████▊    | 215816/371472 [6:29:20<12:44:53,  3.39it/s]
 58%|█████▊    | 215817/371472 [6:29:20<12:33:44,  3.44it/s]
 58%|█████▊    | 215818/371472 [6:29:20<12:12:42,  3.54it/s]
 58%|█████▊    | 215819/371472 [6:29:21<12:00:56,  3.60it/s]
 58%|█████▊    | 215820/371472 [6:29:21<11:45:20,  3.68it/s]
                                                            
{'loss': 2.7203, 'learning_rate': 4.773158223620418e-07, 'epoch': 9.3}
+
 58%|█████▊    | 215820/371472 [6:29:21<11:45:20,  3.68it/s]
 58%|█████▊    | 215821/371472 [6:29:21<11:44:41,  3.68it/s]
 58%|█████▊    | 215822/371472 [6:29:22<11:48:16,  3.66it/s]
 58%|█████▊    | 215823/371472 [6:29:22<12:20:13,  3.50it/s]
 58%|█████▊    | 215824/371472 [6:29:22<12:28:37,  3.47it/s]
 58%|█████▊    | 215825/371472 [6:29:23<13:25:30,  3.22it/s]
 58%|█████▊    | 215826/371472 [6:29:23<13:12:39,  3.27it/s]
 58%|█████▊    | 215827/371472 [6:29:23<13:24:17,  3.23it/s]
 58%|█████▊    | 215828/371472 [6:29:23<13:02:45,  3.31it/s]
 58%|█████▊    | 215829/371472 [6:29:24<14:01:54,  3.08it/s]
 58%|█████▊    | 215830/371472 [6:29:24<14:00:36,  3.09it/s]
 58%|█████▊    | 215831/371472 [6:29:24<13:28:30,  3.21it/s]
 58%|█████▊    | 215832/371472 [6:29:25<12:50:47,  3.37it/s]
 58%|█████▊    | 215833/371472 [6:29:25<13:09:11,  3.29it/s]
 58%|█████▊    | 215834/371472 [6:29:25<12:59:57,  3.33it/s]
 58%|█████▊    | 215835/371472 [6:29:26<12:44:45,  3.39it/s]
 58%|█████▊    | 215836/371472 [6:29:26<12:48:10,  3.38it/s]
 58%|█████▊    | 215837/371472 [6:29:26<12:51:20,  3.36it/s]
 58%|█████▊    | 215838/371472 [6:29:26<12:51:19,  3.36it/s]
 58%|█████▊    | 215839/371472 [6:29:27<14:02:24,  3.08it/s]
 58%|█████▊    | 215840/371472 [6:29:27<13:35:35,  3.18it/s]
                                                            
{'loss': 2.7041, 'learning_rate': 4.772673403865629e-07, 'epoch': 9.3}
+
 58%|█████▊    | 215840/371472 [6:29:27<13:35:35,  3.18it/s]
 58%|█████▊    | 215841/371472 [6:29:27<13:25:26,  3.22it/s]
 58%|█████▊    | 215842/371472 [6:29:28<13:08:12,  3.29it/s]
 58%|█████▊    | 215843/371472 [6:29:28<13:37:04,  3.17it/s]
 58%|█████▊    | 215844/371472 [6:29:28<13:06:28,  3.30it/s]
 58%|█████▊    | 215845/371472 [6:29:29<13:48:55,  3.13it/s]
 58%|█████▊    | 215846/371472 [6:29:29<13:59:09,  3.09it/s]
 58%|█████▊    | 215847/371472 [6:29:29<14:14:23,  3.04it/s]
 58%|█████▊    | 215848/371472 [6:29:30<13:38:31,  3.17it/s]
 58%|█████▊    | 215849/371472 [6:29:30<13:51:36,  3.12it/s]
 58%|█████▊    | 215850/371472 [6:29:30<13:31:53,  3.19it/s]
 58%|█████▊    | 215851/371472 [6:29:31<13:07:36,  3.29it/s]
 58%|█████▊    | 215852/371472 [6:29:31<12:58:54,  3.33it/s]
 58%|█████▊    | 215853/371472 [6:29:31<12:27:12,  3.47it/s]
 58%|█████▊    | 215854/371472 [6:29:31<13:03:46,  3.31it/s]
 58%|█████▊    | 215855/371472 [6:29:32<12:57:58,  3.33it/s]
 58%|█████▊    | 215856/371472 [6:29:32<12:36:23,  3.43it/s]
 58%|█████▊    | 215857/371472 [6:29:32<12:05:23,  3.58it/s]
 58%|█████▊    | 215858/371472 [6:29:33<14:09:46,  3.05it/s]
 58%|█████▊    | 215859/371472 [6:29:33<13:35:57,  3.18it/s]
 58%|█████▊    | 215860/371472 [6:29:33<13:00:53,  3.32it/s]
                                                            
{'loss': 2.6837, 'learning_rate': 4.77218858411084e-07, 'epoch': 9.3}
+
 58%|█████▊    | 215860/371472 [6:29:33<13:00:53,  3.32it/s]
 58%|█████▊    | 215861/371472 [6:29:34<13:41:25,  3.16it/s]
 58%|█████▊    | 215862/371472 [6:29:34<13:02:16,  3.32it/s]
 58%|█████▊    | 215863/371472 [6:29:34<12:45:18,  3.39it/s]
 58%|█████▊    | 215864/371472 [6:29:35<13:54:33,  3.11it/s]
 58%|█████▊    | 215865/371472 [6:29:35<13:24:39,  3.22it/s]
 58%|█████▊    | 215866/371472 [6:29:35<12:55:01,  3.35it/s]
 58%|█████▊    | 215867/371472 [6:29:35<12:38:29,  3.42it/s]
 58%|█████▊    | 215868/371472 [6:29:36<12:15:31,  3.53it/s]
 58%|█████▊    | 215869/371472 [6:29:36<12:15:49,  3.52it/s]
 58%|█████▊    | 215870/371472 [6:29:36<15:20:24,  2.82it/s]
 58%|█████▊    | 215871/371472 [6:29:37<14:03:32,  3.07it/s]
 58%|█████▊    | 215872/371472 [6:29:37<14:03:58,  3.07it/s]
 58%|█████▊    | 215873/371472 [6:29:37<13:42:05,  3.15it/s]
 58%|█████▊    | 215874/371472 [6:29:38<13:30:13,  3.20it/s]
 58%|█████▊    | 215875/371472 [6:29:38<13:10:22,  3.28it/s]
 58%|█████▊    | 215876/371472 [6:29:38<12:45:24,  3.39it/s]
 58%|█████▊    | 215877/371472 [6:29:38<12:38:48,  3.42it/s]
 58%|█████▊    | 215878/371472 [6:29:39<12:05:50,  3.57it/s]
 58%|█████▊    | 215879/371472 [6:29:39<12:12:37,  3.54it/s]
 58%|█████▊    | 215880/371472 [6:29:39<12:06:36,  3.57it/s]
                                                            
{'loss': 2.9107, 'learning_rate': 4.771703764356051e-07, 'epoch': 9.3}
+
 58%|█████▊    | 215880/371472 [6:29:39<12:06:36,  3.57it/s]
 58%|█████▊    | 215881/371472 [6:29:40<12:35:39,  3.43it/s]
 58%|█████▊    | 215882/371472 [6:29:40<13:11:56,  3.27it/s]
 58%|█████▊    | 215883/371472 [6:29:40<12:42:51,  3.40it/s]
 58%|█████▊    | 215884/371472 [6:29:40<12:35:38,  3.43it/s]
 58%|█████▊    | 215885/371472 [6:29:41<13:42:02,  3.15it/s]
 58%|█████▊    | 215886/371472 [6:29:41<13:27:46,  3.21it/s]
 58%|█████▊    | 215887/371472 [6:29:41<12:58:17,  3.33it/s]
 58%|█████▊    | 215888/371472 [6:29:42<12:37:08,  3.42it/s]
 58%|█████▊    | 215889/371472 [6:29:42<12:09:00,  3.56it/s]
 58%|█████▊    | 215890/371472 [6:29:42<12:37:53,  3.42it/s]
 58%|█████▊    | 215891/371472 [6:29:43<12:33:48,  3.44it/s]
 58%|█████▊    | 215892/371472 [6:29:43<12:40:08,  3.41it/s]
 58%|█████▊    | 215893/371472 [6:29:43<12:31:33,  3.45it/s]
 58%|█████▊    | 215894/371472 [6:29:43<12:31:58,  3.45it/s]
 58%|█████▊    | 215895/371472 [6:29:44<13:15:17,  3.26it/s]
 58%|█████▊    | 215896/371472 [6:29:44<12:52:28,  3.36it/s]
 58%|█████▊    | 215897/371472 [6:29:44<12:46:50,  3.38it/s]
 58%|█████▊    | 215898/371472 [6:29:45<13:02:56,  3.31it/s]
 58%|█████▊    | 215899/371472 [6:29:45<12:57:08,  3.34it/s]
 58%|█████▊    | 215900/371472 [6:29:45<13:01:10,  3.32it/s]
                                                            
{'loss': 2.6808, 'learning_rate': 4.771218944601262e-07, 'epoch': 9.3}
+
 58%|█████▊    | 215900/371472 [6:29:45<13:01:10,  3.32it/s]
 58%|█████▊    | 215901/371472 [6:29:46<12:45:06,  3.39it/s]
 58%|█████▊    | 215902/371472 [6:29:46<12:30:58,  3.45it/s]
 58%|█████▊    | 215903/371472 [6:29:46<12:57:11,  3.34it/s]
 58%|█████▊    | 215904/371472 [6:29:46<13:14:43,  3.26it/s]
 58%|█████▊    | 215905/371472 [6:29:47<12:36:22,  3.43it/s]
 58%|█████▊    | 215906/371472 [6:29:47<12:33:36,  3.44it/s]
 58%|█████▊    | 215907/371472 [6:29:47<12:32:03,  3.45it/s]
 58%|█████▊    | 215908/371472 [6:29:48<12:26:27,  3.47it/s]
 58%|█████▊    | 215909/371472 [6:29:48<12:35:34,  3.43it/s]
 58%|█████▊    | 215910/371472 [6:29:48<12:55:11,  3.34it/s]
 58%|█████▊    | 215911/371472 [6:29:49<12:47:33,  3.38it/s]
 58%|█████▊    | 215912/371472 [6:29:49<12:53:24,  3.35it/s]
 58%|█████▊    | 215913/371472 [6:29:49<12:38:30,  3.42it/s]
 58%|█████▊    | 215914/371472 [6:29:49<13:01:00,  3.32it/s]
 58%|█████▊    | 215915/371472 [6:29:50<13:13:28,  3.27it/s]
 58%|█████▊    | 215916/371472 [6:29:50<13:51:39,  3.12it/s]
 58%|█████▊    | 215917/371472 [6:29:50<13:08:12,  3.29it/s]
 58%|█████▊    | 215918/371472 [6:29:51<13:27:45,  3.21it/s]
 58%|█████▊    | 215919/371472 [6:29:51<13:10:19,  3.28it/s]
 58%|█████▊    | 215920/371472 [6:29:51<13:00:30,  3.32it/s]
                                                            
{'loss': 2.7624, 'learning_rate': 4.770734124846474e-07, 'epoch': 9.3}
+
 58%|█████▊    | 215920/371472 [6:29:51<13:00:30,  3.32it/s]
 58%|█████▊    | 215921/371472 [6:29:52<12:40:31,  3.41it/s]
 58%|█████▊    | 215922/371472 [6:29:52<12:16:30,  3.52it/s]
 58%|█████▊    | 215923/371472 [6:29:52<12:17:05,  3.52it/s]
 58%|█████▊    | 215924/371472 [6:29:52<12:31:44,  3.45it/s]
 58%|█████▊    | 215925/371472 [6:29:53<12:17:41,  3.51it/s]
 58%|█████▊    | 215926/371472 [6:29:53<12:14:35,  3.53it/s]
 58%|█████▊    | 215927/371472 [6:29:53<12:41:45,  3.40it/s]
 58%|█████▊    | 215928/371472 [6:29:54<12:58:09,  3.33it/s]
 58%|█████▊    | 215929/371472 [6:29:54<12:32:13,  3.45it/s]
 58%|█████▊    | 215930/371472 [6:29:54<12:23:45,  3.49it/s]
 58%|█████▊    | 215931/371472 [6:29:54<12:47:53,  3.38it/s]
 58%|█████▊    | 215932/371472 [6:29:55<13:18:27,  3.25it/s]
 58%|█████▊    | 215933/371472 [6:29:55<12:54:21,  3.35it/s]
 58%|█████▊    | 215934/371472 [6:29:55<12:40:35,  3.41it/s]
 58%|█████▊    | 215935/371472 [6:29:56<12:49:27,  3.37it/s]
 58%|█████▊    | 215936/371472 [6:29:56<13:07:19,  3.29it/s]
 58%|█████▊    | 215937/371472 [6:29:56<12:51:37,  3.36it/s]
 58%|█████▊    | 215938/371472 [6:29:57<13:39:18,  3.16it/s]
 58%|█████▊    | 215939/371472 [6:29:57<13:18:05,  3.25it/s]
 58%|█████▊    | 215940/371472 [6:29:57<12:55:49,  3.34it/s]
                                                            
{'loss': 2.7494, 'learning_rate': 4.770249305091685e-07, 'epoch': 9.3}
+
 58%|█████▊    | 215940/371472 [6:29:57<12:55:49,  3.34it/s]
 58%|█████▊    | 215941/371472 [6:29:57<12:45:32,  3.39it/s]
 58%|█████▊    | 215942/371472 [6:29:58<12:28:30,  3.46it/s]
 58%|█████▊    | 215943/371472 [6:29:58<12:35:38,  3.43it/s]
 58%|█████▊    | 215944/371472 [6:29:58<12:20:58,  3.50it/s]
 58%|█████▊    | 215945/371472 [6:29:59<12:04:35,  3.58it/s]
 58%|█████▊    | 215946/371472 [6:29:59<12:33:47,  3.44it/s]
 58%|█████▊    | 215947/371472 [6:29:59<13:08:10,  3.29it/s]
 58%|█████▊    | 215948/371472 [6:30:00<13:23:12,  3.23it/s]
 58%|█████▊    | 215949/371472 [6:30:00<12:51:03,  3.36it/s]
 58%|█████▊    | 215950/371472 [6:30:00<12:43:07,  3.40it/s]
 58%|█████▊    | 215951/371472 [6:30:00<12:28:09,  3.46it/s]
 58%|█████▊    | 215952/371472 [6:30:01<12:11:14,  3.54it/s]
 58%|█████▊    | 215953/371472 [6:30:01<13:04:25,  3.30it/s]
 58%|█████▊    | 215954/371472 [6:30:01<13:00:00,  3.32it/s]
 58%|█████▊    | 215955/371472 [6:30:02<12:48:32,  3.37it/s]
 58%|█████▊    | 215956/371472 [6:30:02<12:50:36,  3.36it/s]
 58%|█████▊    | 215957/371472 [6:30:02<12:41:20,  3.40it/s]
 58%|█████▊    | 215958/371472 [6:30:02<12:20:09,  3.50it/s]
 58%|█████▊    | 215959/371472 [6:30:03<12:35:11,  3.43it/s]
 58%|█████▊    | 215960/371472 [6:30:03<12:27:28,  3.47it/s]
                                                            
{'loss': 2.7703, 'learning_rate': 4.769764485336896e-07, 'epoch': 9.3}
+
 58%|█████▊    | 215960/371472 [6:30:03<12:27:28,  3.47it/s]
 58%|█████▊    | 215961/371472 [6:30:03<12:17:18,  3.52it/s]
 58%|█████▊    | 215962/371472 [6:30:04<12:16:00,  3.52it/s]
 58%|█████▊    | 215963/371472 [6:30:04<12:28:57,  3.46it/s]
 58%|█████▊    | 215964/371472 [6:30:04<12:03:08,  3.58it/s]
 58%|█████▊    | 215965/371472 [6:30:04<11:51:31,  3.64it/s]
 58%|█████▊    | 215966/371472 [6:30:05<12:08:55,  3.56it/s]
 58%|█████▊    | 215967/371472 [6:30:05<12:33:03,  3.44it/s]
 58%|█████▊    | 215968/371472 [6:30:05<12:21:56,  3.49it/s]
 58%|█████▊    | 215969/371472 [6:30:06<12:12:30,  3.54it/s]
 58%|█████▊    | 215970/371472 [6:30:06<12:05:38,  3.57it/s]
 58%|█████▊    | 215971/371472 [6:30:06<12:17:10,  3.52it/s]
 58%|█████▊    | 215972/371472 [6:30:06<12:06:22,  3.57it/s]
 58%|█████▊    | 215973/371472 [6:30:07<12:00:18,  3.60it/s]
 58%|█████▊    | 215974/371472 [6:30:07<12:13:40,  3.53it/s]
 58%|█████▊    | 215975/371472 [6:30:07<12:13:23,  3.53it/s]
 58%|█████▊    | 215976/371472 [6:30:08<12:45:37,  3.38it/s]
 58%|█████▊    | 215977/371472 [6:30:08<12:39:06,  3.41it/s]
 58%|█████▊    | 215978/371472 [6:30:08<12:29:49,  3.46it/s]
 58%|█████▊    | 215979/371472 [6:30:08<12:27:02,  3.47it/s]
 58%|█████▊    | 215980/371472 [6:30:09<12:30:31,  3.45it/s]
                                                            
{'loss': 2.8778, 'learning_rate': 4.769279665582107e-07, 'epoch': 9.3}
+
 58%|█████▊    | 215980/371472 [6:30:09<12:30:31,  3.45it/s]
 58%|█████▊    | 215981/371472 [6:30:09<12:33:38,  3.44it/s]
 58%|█████▊    | 215982/371472 [6:30:09<12:37:44,  3.42it/s]
 58%|█████▊    | 215983/371472 [6:30:10<14:00:42,  3.08it/s]
 58%|█████▊    | 215984/371472 [6:30:10<13:14:13,  3.26it/s]
 58%|█████▊    | 215985/371472 [6:30:10<13:06:51,  3.29it/s]
 58%|█████▊    | 215986/371472 [6:30:11<12:32:03,  3.45it/s]
 58%|█████▊    | 215987/371472 [6:30:11<12:20:24,  3.50it/s]
 58%|█████▊    | 215988/371472 [6:30:11<12:03:37,  3.58it/s]
 58%|█████▊    | 215989/371472 [6:30:11<12:11:35,  3.54it/s]
 58%|█████▊    | 215990/371472 [6:30:12<11:54:48,  3.63it/s]
 58%|█████▊    | 215991/371472 [6:30:12<12:26:10,  3.47it/s]
 58%|█████▊    | 215992/371472 [6:30:12<12:22:35,  3.49it/s]
 58%|█████▊    | 215993/371472 [6:30:12<12:04:49,  3.58it/s]
 58%|█████▊    | 215994/371472 [6:30:13<11:33:51,  3.73it/s]
 58%|█████▊    | 215995/371472 [6:30:13<11:42:15,  3.69it/s]
 58%|█████▊    | 215996/371472 [6:30:13<11:44:47,  3.68it/s]
 58%|█████▊    | 215997/371472 [6:30:14<11:55:45,  3.62it/s]
 58%|█████▊    | 215998/371472 [6:30:14<11:46:14,  3.67it/s]
 58%|█████▊    | 215999/371472 [6:30:14<11:41:33,  3.69it/s]
 58%|█████▊    | 216000/371472 [6:30:14<12:11:08,  3.54it/s]
                                                            
{'loss': 2.7031, 'learning_rate': 4.768794845827318e-07, 'epoch': 9.3}
+
 58%|█████▊    | 216000/371472 [6:30:14<12:11:08,  3.54it/s]
 58%|█████▊    | 216001/371472 [6:30:15<13:02:28,  3.31it/s]
 58%|█████▊    | 216002/371472 [6:30:15<12:49:35,  3.37it/s]
 58%|█████▊    | 216003/371472 [6:30:15<12:53:01,  3.35it/s]
 58%|█████▊    | 216004/371472 [6:30:16<12:36:33,  3.42it/s]
 58%|█████▊    | 216005/371472 [6:30:16<12:31:12,  3.45it/s]
 58%|█████▊    | 216006/371472 [6:30:16<12:24:49,  3.48it/s]
 58%|█████▊    | 216007/371472 [6:30:16<12:39:12,  3.41it/s]
 58%|█████▊    | 216008/371472 [6:30:17<12:51:58,  3.36it/s]
 58%|█████▊    | 216009/371472 [6:30:17<13:48:43,  3.13it/s]
 58%|█████▊    | 216010/371472 [6:30:18<14:32:01,  2.97it/s]
 58%|█████▊    | 216011/371472 [6:30:18<14:26:31,  2.99it/s]
 58%|█████▊    | 216012/371472 [6:30:18<13:28:23,  3.21it/s]
 58%|█████▊    | 216013/371472 [6:30:18<13:23:32,  3.22it/s]
 58%|█████▊    | 216014/371472 [6:30:19<13:43:12,  3.15it/s]
 58%|█████▊    | 216015/371472 [6:30:19<13:43:29,  3.15it/s]
 58%|█████▊    | 216016/371472 [6:30:19<13:23:24,  3.22it/s]
 58%|█████▊    | 216017/371472 [6:30:20<13:27:12,  3.21it/s]
 58%|█████▊    | 216018/371472 [6:30:20<13:19:49,  3.24it/s]
 58%|█████▊    | 216019/371472 [6:30:20<13:12:32,  3.27it/s]
 58%|█████▊    | 216020/371472 [6:30:21<13:14:33,  3.26it/s]
                                                            
{'loss': 2.6789, 'learning_rate': 4.7683100260725285e-07, 'epoch': 9.3}
+
 58%|█████▊    | 216020/371472 [6:30:21<13:14:33,  3.26it/s]
 58%|█████▊    | 216021/371472 [6:30:21<12:46:19,  3.38it/s]
 58%|█████▊    | 216022/371472 [6:30:21<12:50:44,  3.36it/s]
 58%|█████▊    | 216023/371472 [6:30:21<12:27:35,  3.47it/s]
 58%|█████▊    | 216024/371472 [6:30:22<12:40:29,  3.41it/s]
 58%|█████▊    | 216025/371472 [6:30:22<12:25:28,  3.48it/s]
 58%|█████▊    | 216026/371472 [6:30:22<12:23:26,  3.48it/s]
 58%|█████▊    | 216027/371472 [6:30:23<13:21:35,  3.23it/s]
 58%|█████▊    | 216028/371472 [6:30:23<13:05:51,  3.30it/s]
 58%|█████▊    | 216029/371472 [6:30:23<13:03:09,  3.31it/s]
 58%|█████▊    | 216030/371472 [6:30:24<13:23:35,  3.22it/s]
 58%|█████▊    | 216031/371472 [6:30:24<15:17:46,  2.82it/s]
 58%|█████▊    | 216032/371472 [6:30:24<14:37:08,  2.95it/s]
 58%|█████▊    | 216033/371472 [6:30:25<13:39:52,  3.16it/s]
 58%|█████▊    | 216034/371472 [6:30:25<13:28:03,  3.21it/s]
 58%|█████▊    | 216035/371472 [6:30:25<12:55:24,  3.34it/s]
 58%|█████▊    | 216036/371472 [6:30:25<12:51:29,  3.36it/s]
 58%|█████▊    | 216037/371472 [6:30:26<13:08:34,  3.29it/s]
 58%|█████▊    | 216038/371472 [6:30:26<12:57:03,  3.33it/s]
 58%|█████▊    | 216039/371472 [6:30:26<13:08:21,  3.29it/s]
 58%|█████▊    | 216040/371472 [6:30:27<12:45:42,  3.38it/s]
                                                            
{'loss': 2.6724, 'learning_rate': 4.76782520631774e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216040/371472 [6:30:27<12:45:42,  3.38it/s]
 58%|█████▊    | 216041/371472 [6:30:27<13:38:41,  3.16it/s]
 58%|█████▊    | 216042/371472 [6:30:27<14:13:55,  3.03it/s]
 58%|█████▊    | 216043/371472 [6:30:28<13:38:24,  3.17it/s]
 58%|█████▊    | 216044/371472 [6:30:28<13:36:09,  3.17it/s]
 58%|█████▊    | 216045/371472 [6:30:28<13:10:05,  3.28it/s]
 58%|█████▊    | 216046/371472 [6:30:29<12:58:10,  3.33it/s]
 58%|█████▊    | 216047/371472 [6:30:29<12:40:34,  3.41it/s]
 58%|█████▊    | 216048/371472 [6:30:29<12:40:41,  3.41it/s]
 58%|█████▊    | 216049/371472 [6:30:29<13:26:54,  3.21it/s]
 58%|█████▊    | 216050/371472 [6:30:30<13:11:56,  3.27it/s]
 58%|█████▊    | 216051/371472 [6:30:30<12:48:47,  3.37it/s]
 58%|█████▊    | 216052/371472 [6:30:30<12:52:28,  3.35it/s]
 58%|█████▊    | 216053/371472 [6:30:31<14:55:24,  2.89it/s]
 58%|█████▊    | 216054/371472 [6:30:31<13:48:23,  3.13it/s]
 58%|█████▊    | 216055/371472 [6:30:31<13:11:50,  3.27it/s]
 58%|█████▊    | 216056/371472 [6:30:32<12:50:24,  3.36it/s]
 58%|█████▊    | 216057/371472 [6:30:32<12:27:30,  3.47it/s]
 58%|█████▊    | 216058/371472 [6:30:32<12:23:08,  3.49it/s]
 58%|█████▊    | 216059/371472 [6:30:32<12:25:23,  3.47it/s]
 58%|█████▊    | 216060/371472 [6:30:33<12:34:42,  3.43it/s]
                                                            
{'loss': 2.9111, 'learning_rate': 4.767340386562951e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216060/371472 [6:30:33<12:34:42,  3.43it/s]
 58%|█████▊    | 216061/371472 [6:30:33<12:32:08,  3.44it/s]
 58%|█████▊    | 216062/371472 [6:30:33<12:19:42,  3.50it/s]
 58%|█████▊    | 216063/371472 [6:30:34<12:32:19,  3.44it/s]
 58%|█████▊    | 216064/371472 [6:30:34<12:26:11,  3.47it/s]
 58%|█████▊    | 216065/371472 [6:30:34<12:21:55,  3.49it/s]
 58%|█████▊    | 216066/371472 [6:30:34<12:20:58,  3.50it/s]
 58%|█████▊    | 216067/371472 [6:30:35<12:13:29,  3.53it/s]
 58%|█████▊    | 216068/371472 [6:30:35<12:42:01,  3.40it/s]
 58%|█████▊    | 216069/371472 [6:30:35<12:34:31,  3.43it/s]
 58%|█████▊    | 216070/371472 [6:30:36<12:36:31,  3.42it/s]
 58%|█████▊    | 216071/371472 [6:30:36<12:35:58,  3.43it/s]
 58%|█████▊    | 216072/371472 [6:30:36<12:21:29,  3.49it/s]
 58%|█████▊    | 216073/371472 [6:30:36<12:15:43,  3.52it/s]
 58%|█████▊    | 216074/371472 [6:30:37<12:29:39,  3.45it/s]
 58%|█████▊    | 216075/371472 [6:30:37<12:43:20,  3.39it/s]
 58%|█████▊    | 216076/371472 [6:30:37<12:43:40,  3.39it/s]
 58%|█████▊    | 216077/371472 [6:30:38<12:30:15,  3.45it/s]
 58%|█████▊    | 216078/371472 [6:30:38<12:24:39,  3.48it/s]
 58%|█████▊    | 216079/371472 [6:30:38<14:04:03,  3.07it/s]
 58%|█████▊    | 216080/371472 [6:30:39<13:27:26,  3.21it/s]
                                                            
{'loss': 2.8785, 'learning_rate': 4.766855566808162e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216080/371472 [6:30:39<13:27:26,  3.21it/s]
 58%|█████▊    | 216081/371472 [6:30:39<13:01:14,  3.32it/s]
 58%|█████▊    | 216082/371472 [6:30:39<13:26:39,  3.21it/s]
 58%|█████▊    | 216083/371472 [6:30:40<13:15:41,  3.25it/s]
 58%|█████▊    | 216084/371472 [6:30:40<12:48:39,  3.37it/s]
 58%|█████▊    | 216085/371472 [6:30:40<13:00:43,  3.32it/s]
 58%|█████▊    | 216086/371472 [6:30:41<13:58:02,  3.09it/s]
 58%|█████▊    | 216087/371472 [6:30:41<13:30:30,  3.20it/s]
 58%|█████▊    | 216088/371472 [6:30:41<13:10:46,  3.27it/s]
 58%|█████▊    | 216089/371472 [6:30:41<12:45:08,  3.38it/s]
 58%|█████▊    | 216090/371472 [6:30:42<12:36:44,  3.42it/s]
 58%|█████▊    | 216091/371472 [6:30:42<12:25:36,  3.47it/s]
 58%|█████▊    | 216092/371472 [6:30:42<12:29:08,  3.46it/s]
 58%|█████▊    | 216093/371472 [6:30:43<12:53:27,  3.35it/s]
 58%|█████▊    | 216094/371472 [6:30:43<12:42:58,  3.39it/s]
 58%|█████▊    | 216095/371472 [6:30:43<12:56:17,  3.34it/s]
 58%|█████▊    | 216096/371472 [6:30:43<13:06:12,  3.29it/s]
 58%|█████▊    | 216097/371472 [6:30:44<13:56:19,  3.10it/s]
 58%|█████▊    | 216098/371472 [6:30:44<13:23:19,  3.22it/s]
 58%|█████▊    | 216099/371472 [6:30:44<13:43:01,  3.15it/s]
 58%|█████▊    | 216100/371472 [6:30:45<13:37:17,  3.17it/s]
                                                            
{'loss': 2.6516, 'learning_rate': 4.766370747053373e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216100/371472 [6:30:45<13:37:17,  3.17it/s]
 58%|█████▊    | 216101/371472 [6:30:45<14:12:48,  3.04it/s]
 58%|█████▊    | 216102/371472 [6:30:45<13:45:16,  3.14it/s]
 58%|█████▊    | 216103/371472 [6:30:46<13:30:18,  3.20it/s]
 58%|█████▊    | 216104/371472 [6:30:46<13:35:39,  3.17it/s]
 58%|█████▊    | 216105/371472 [6:30:46<13:35:21,  3.18it/s]
 58%|█████▊    | 216106/371472 [6:30:47<13:01:09,  3.31it/s]
 58%|█████▊    | 216107/371472 [6:30:47<12:39:22,  3.41it/s]
 58%|█████▊    | 216108/371472 [6:30:47<13:39:34,  3.16it/s]
 58%|█████▊    | 216109/371472 [6:30:48<13:11:45,  3.27it/s]
 58%|██��██▊    | 216110/371472 [6:30:48<12:49:36,  3.36it/s]
 58%|█████▊    | 216111/371472 [6:30:48<12:49:22,  3.37it/s]
 58%|█████▊    | 216112/371472 [6:30:48<12:56:12,  3.34it/s]
 58%|█████▊    | 216113/371472 [6:30:49<12:56:54,  3.33it/s]
 58%|█████▊    | 216114/371472 [6:30:49<13:05:51,  3.29it/s]
 58%|█████▊    | 216115/371472 [6:30:49<12:53:00,  3.35it/s]
 58%|█████▊    | 216116/371472 [6:30:50<12:23:46,  3.48it/s]
 58%|█████▊    | 216117/371472 [6:30:50<12:18:26,  3.51it/s]
 58%|█████▊    | 216118/371472 [6:30:50<12:32:44,  3.44it/s]
 58%|█████▊    | 216119/371472 [6:30:50<12:27:36,  3.46it/s]
 58%|█████▊    | 216120/371472 [6:30:51<12:29:32,  3.45it/s]
                                                            
{'loss': 2.7743, 'learning_rate': 4.7658859272985847e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216120/371472 [6:30:51<12:29:32,  3.45it/s]
 58%|█████▊    | 216121/371472 [6:30:51<12:09:02,  3.55it/s]
 58%|█████▊    | 216122/371472 [6:30:51<12:03:50,  3.58it/s]
 58%|█████▊    | 216123/371472 [6:30:52<11:57:52,  3.61it/s]
 58%|█████▊    | 216124/371472 [6:30:52<12:04:34,  3.57it/s]
 58%|█████▊    | 216125/371472 [6:30:52<12:03:42,  3.58it/s]
 58%|█████▊    | 216126/371472 [6:30:52<11:54:14,  3.62it/s]
 58%|█████▊    | 216127/371472 [6:30:53<11:53:50,  3.63it/s]
 58%|█████▊    | 216128/371472 [6:30:53<12:03:16,  3.58it/s]
 58%|█████▊    | 216129/371472 [6:30:53<11:54:31,  3.62it/s]
 58%|█████▊    | 216130/371472 [6:30:53<11:46:50,  3.66it/s]
 58%|█████▊    | 216131/371472 [6:30:54<11:50:51,  3.64it/s]
 58%|█████▊    | 216132/371472 [6:30:54<11:50:20,  3.64it/s]
 58%|█████▊    | 216133/371472 [6:30:54<12:45:55,  3.38it/s]
 58%|█████▊    | 216134/371472 [6:30:55<12:54:43,  3.34it/s]
 58%|█████▊    | 216135/371472 [6:30:55<13:34:05,  3.18it/s]
 58%|█████▊    | 216136/371472 [6:30:55<13:13:10,  3.26it/s]
 58%|█████▊    | 216137/371472 [6:30:56<13:21:03,  3.23it/s]
 58%|█████▊    | 216138/371472 [6:30:56<12:49:47,  3.36it/s]
 58%|█████▊    | 216139/371472 [6:30:56<12:43:24,  3.39it/s]
 58%|█████▊    | 216140/371472 [6:30:56<12:30:39,  3.45it/s]
                                                            
{'loss': 2.7974, 'learning_rate': 4.765401107543795e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216140/371472 [6:30:56<12:30:39,  3.45it/s]
 58%|█████▊    | 216141/371472 [6:30:57<12:14:05,  3.53it/s]
 58%|█████▊    | 216142/371472 [6:30:57<12:31:30,  3.44it/s]
 58%|█████▊    | 216143/371472 [6:30:57<13:08:52,  3.28it/s]
 58%|█████▊    | 216144/371472 [6:30:58<12:49:47,  3.36it/s]
 58%|█████▊    | 216145/371472 [6:30:58<13:06:00,  3.29it/s]
 58%|█████▊    | 216146/371472 [6:30:58<13:31:38,  3.19it/s]
 58%|█████▊    | 216147/371472 [6:30:59<12:55:09,  3.34it/s]
 58%|█████▊    | 216148/371472 [6:30:59<13:28:55,  3.20it/s]
 58%|█████▊    | 216149/371472 [6:30:59<13:19:47,  3.24it/s]
 58%|█████▊    | 216150/371472 [6:31:00<13:05:28,  3.30it/s]
 58%|█████▊    | 216151/371472 [6:31:00<13:18:46,  3.24it/s]
 58%|█████▊    | 216152/371472 [6:31:00<13:04:55,  3.30it/s]
 58%|█████▊    | 216153/371472 [6:31:00<14:03:50,  3.07it/s]
 58%|█████▊    | 216154/371472 [6:31:01<13:30:06,  3.20it/s]
 58%|█████▊    | 216155/371472 [6:31:01<13:16:10,  3.25it/s]
 58%|█████▊    | 216156/371472 [6:31:01<13:08:39,  3.28it/s]
 58%|█████▊    | 216157/371472 [6:31:02<13:16:39,  3.25it/s]
 58%|█████▊    | 216158/371472 [6:31:02<13:07:18,  3.29it/s]
 58%|█████▊    | 216159/371472 [6:31:02<12:48:56,  3.37it/s]
 58%|█████▊    | 216160/371472 [6:31:03<12:15:12,  3.52it/s]
                                                            
{'loss': 2.8888, 'learning_rate': 4.7649162877890066e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216160/371472 [6:31:03<12:15:12,  3.52it/s]
 58%|█████▊    | 216161/371472 [6:31:03<12:46:39,  3.38it/s]
 58%|█████▊    | 216162/371472 [6:31:03<12:49:44,  3.36it/s]
 58%|█████▊    | 216163/371472 [6:31:03<13:28:30,  3.20it/s]
 58%|█████▊    | 216164/371472 [6:31:04<13:07:44,  3.29it/s]
 58%|█████▊    | 216165/371472 [6:31:04<12:45:25,  3.38it/s]
 58%|█████▊    | 216166/371472 [6:31:04<12:50:25,  3.36it/s]
 58%|█████▊    | 216167/371472 [6:31:05<12:40:44,  3.40it/s]
 58%|█████▊    | 216168/371472 [6:31:05<12:37:17,  3.42it/s]
 58%|█████▊    | 216169/371472 [6:31:05<13:07:17,  3.29it/s]
 58%|█████▊    | 216170/371472 [6:31:06<12:42:56,  3.39it/s]
 58%|█████▊    | 216171/371472 [6:31:06<12:36:52,  3.42it/s]
 58%|█████▊    | 216172/371472 [6:31:06<13:13:12,  3.26it/s]
 58%|█████▊    | 216173/371472 [6:31:06<13:07:54,  3.29it/s]
 58%|█████▊    | 216174/371472 [6:31:07<12:48:41,  3.37it/s]
 58%|█████▊    | 216175/371472 [6:31:07<13:10:33,  3.27it/s]
 58%|█████▊    | 216176/371472 [6:31:07<13:02:30,  3.31it/s]
 58%|█████▊    | 216177/371472 [6:31:08<12:55:19,  3.34it/s]
 58%|█████▊    | 216178/371472 [6:31:08<12:34:58,  3.43it/s]
 58%|█████▊    | 216179/371472 [6:31:08<12:26:45,  3.47it/s]
 58%|█████▊    | 216180/371472 [6:31:08<12:24:56,  3.47it/s]
                                                            
{'loss': 2.6167, 'learning_rate': 4.7644314680342174e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216180/371472 [6:31:08<12:24:56,  3.47it/s]
 58%|█████▊    | 216181/371472 [6:31:09<12:27:20,  3.46it/s]
 58%|█████▊    | 216182/371472 [6:31:09<12:12:45,  3.53it/s]
 58%|█████▊    | 216183/371472 [6:31:09<12:10:11,  3.54it/s]
 58%|█████▊    | 216184/371472 [6:31:10<13:09:45,  3.28it/s]
 58%|█████▊    | 216185/371472 [6:31:10<13:07:10,  3.29it/s]
 58%|█████▊    | 216186/371472 [6:31:10<13:21:10,  3.23it/s]
 58%|█████▊    | 216187/371472 [6:31:11<13:13:09,  3.26it/s]
 58%|█████▊    | 216188/371472 [6:31:11<13:04:03,  3.30it/s]
 58%|█████▊    | 216189/371472 [6:31:11<12:47:40,  3.37it/s]
 58%|█████▊    | 216190/371472 [6:31:11<12:44:31,  3.39it/s]
 58%|█████▊    | 216191/371472 [6:31:12<12:47:21,  3.37it/s]
 58%|█████▊    | 216192/371472 [6:31:12<12:41:31,  3.40it/s]
 58%|█████▊    | 216193/371472 [6:31:12<13:02:47,  3.31it/s]
 58%|█████▊    | 216194/371472 [6:31:13<13:12:05,  3.27it/s]
 58%|█████▊    | 216195/371472 [6:31:13<12:35:34,  3.43it/s]
 58%|█████▊    | 216196/371472 [6:31:13<12:32:55,  3.44it/s]
 58%|█████▊    | 216197/371472 [6:31:14<13:14:06,  3.26it/s]
 58%|█████▊    | 216198/371472 [6:31:14<12:57:43,  3.33it/s]
 58%|█████▊    | 216199/371472 [6:31:14<12:27:28,  3.46it/s]
 58%|█████▊    | 216200/371472 [6:31:14<12:43:37,  3.39it/s]
                                                            
{'loss': 2.66, 'learning_rate': 4.7639466482794286e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216200/371472 [6:31:14<12:43:37,  3.39it/s]
 58%|█████▊    | 216201/371472 [6:31:15<12:43:38,  3.39it/s]
 58%|█████▊    | 216202/371472 [6:31:15<12:54:32,  3.34it/s]
 58%|█████▊    | 216203/371472 [6:31:15<12:43:12,  3.39it/s]
 58%|█████▊    | 216204/371472 [6:31:16<12:55:32,  3.34it/s]
 58%|█████▊    | 216205/371472 [6:31:16<12:59:31,  3.32it/s]
 58%|█████▊    | 216206/371472 [6:31:16<12:46:07,  3.38it/s]
 58%|█████▊    | 216207/371472 [6:31:17<13:00:50,  3.31it/s]
 58%|█████▊    | 216208/371472 [6:31:17<12:43:10,  3.39it/s]
 58%|█████▊    | 216209/371472 [6:31:17<12:31:06,  3.45it/s]
 58%|█████▊    | 216210/371472 [6:31:17<12:19:41,  3.50it/s]
 58%|█████▊    | 216211/371472 [6:31:18<12:24:47,  3.47it/s]
 58%|█████▊    | 216212/371472 [6:31:18<12:23:22,  3.48it/s]
 58%|█████▊    | 216213/371472 [6:31:18<12:09:27,  3.55it/s]
 58%|█████▊    | 216214/371472 [6:31:19<12:32:14,  3.44it/s]
 58%|█████▊    | 216215/371472 [6:31:19<13:45:01,  3.14it/s]
 58%|█████▊    | 216216/371472 [6:31:19<13:11:45,  3.27it/s]
 58%|█████▊    | 216217/371472 [6:31:19<12:48:36,  3.37it/s]
 58%|█████▊    | 216218/371472 [6:31:20<12:29:33,  3.45it/s]
 58%|█████▊    | 216219/371472 [6:31:20<12:45:21,  3.38it/s]
 58%|█████▊    | 216220/371472 [6:31:20<13:16:05,  3.25it/s]
                                                            
{'loss': 2.807, 'learning_rate': 4.7634618285246393e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216220/371472 [6:31:20<13:16:05,  3.25it/s]
 58%|█████▊    | 216221/371472 [6:31:21<12:49:03,  3.36it/s]
 58%|█████▊    | 216222/371472 [6:31:21<12:31:38,  3.44it/s]
 58%|█████▊    | 216223/371472 [6:31:21<12:26:16,  3.47it/s]
 58%|█████▊    | 216224/371472 [6:31:22<12:09:40,  3.55it/s]
 58%|█████▊    | 216225/371472 [6:31:22<12:05:17,  3.57it/s]
 58%|█████▊    | 216226/371472 [6:31:22<12:44:27,  3.38it/s]
 58%|█████▊    | 216227/371472 [6:31:22<12:32:54,  3.44it/s]
 58%|█████▊    | 216228/371472 [6:31:23<12:21:07,  3.49it/s]
 58%|█████▊    | 216229/371472 [6:31:23<12:54:29,  3.34it/s]
 58%|█████▊    | 216230/371472 [6:31:23<12:45:59,  3.38it/s]
 58%|█████▊    | 216231/371472 [6:31:24<13:51:54,  3.11it/s]
 58%|█████▊    | 216232/371472 [6:31:24<13:12:34,  3.26it/s]
 58%|█████▊    | 216233/371472 [6:31:24<13:09:25,  3.28it/s]
 58%|█████▊    | 216234/371472 [6:31:25<13:57:01,  3.09it/s]
 58%|█████▊    | 216235/371472 [6:31:25<13:33:33,  3.18it/s]
 58%|█████▊    | 216236/371472 [6:31:25<13:56:41,  3.09it/s]
 58%|█████▊    | 216237/371472 [6:31:26<13:30:34,  3.19it/s]
 58%|█████▊    | 216238/371472 [6:31:26<12:55:59,  3.33it/s]
 58%|█████▊    | 216239/371472 [6:31:26<13:00:26,  3.32it/s]
 58%|█████▊    | 216240/371472 [6:31:26<13:14:09,  3.26it/s]
                                                            
{'loss': 2.6777, 'learning_rate': 4.76297700876985e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216240/371472 [6:31:26<13:14:09,  3.26it/s]
 58%|█████▊    | 216241/371472 [6:31:27<13:36:24,  3.17it/s]
 58%|█████▊    | 216242/371472 [6:31:27<13:19:52,  3.23it/s]
 58%|█████▊    | 216243/371472 [6:31:27<13:45:08,  3.14it/s]
 58%|█████▊    | 216244/371472 [6:31:28<13:18:06,  3.24it/s]
 58%|█████▊    | 216245/371472 [6:31:28<14:36:47,  2.95it/s]
 58%|█████▊    | 216246/371472 [6:31:28<13:53:09,  3.11it/s]
 58%|█████▊    | 216247/371472 [6:31:29<13:44:33,  3.14it/s]
 58%|█████▊    | 216248/371472 [6:31:29<13:14:27,  3.26it/s]
 58%|█████▊    | 216249/371472 [6:31:29<13:11:15,  3.27it/s]
 58%|█████▊    | 216250/371472 [6:31:30<13:34:32,  3.18it/s]
 58%|█████▊    | 216251/371472 [6:31:30<13:14:52,  3.25it/s]
 58%|█████▊    | 216252/371472 [6:31:30<13:06:34,  3.29it/s]
 58%|█████▊    | 216253/371472 [6:31:30<13:06:23,  3.29it/s]
 58%|█████▊    | 216254/371472 [6:31:31<12:58:49,  3.32it/s]
 58%|█████▊    | 216255/371472 [6:31:31<12:55:51,  3.33it/s]
 58%|█████▊    | 216256/371472 [6:31:31<12:38:01,  3.41it/s]
 58%|█████▊    | 216257/371472 [6:31:32<12:24:01,  3.48it/s]
 58%|█████▊    | 216258/371472 [6:31:32<12:17:00,  3.51it/s]
 58%|█████▊    | 216259/371472 [6:31:32<12:03:57,  3.57it/s]
 58%|█████▊    | 216260/371472 [6:31:32<12:02:03,  3.58it/s]
                                                            
{'loss': 2.7346, 'learning_rate': 4.762492189015062e-07, 'epoch': 9.31}
+
 58%|█████▊    | 216260/371472 [6:31:32<12:02:03,  3.58it/s]
 58%|█████▊    | 216261/371472 [6:31:33<11:54:12,  3.62it/s]
 58%|█████▊    | 216262/371472 [6:31:33<12:42:50,  3.39it/s]
 58%|█████▊    | 216263/371472 [6:31:33<12:45:22,  3.38it/s]
 58%|█████▊    | 216264/371472 [6:31:34<12:39:46,  3.40it/s]
 58%|█████▊    | 216265/371472 [6:31:34<12:17:47,  3.51it/s]
 58%|█████▊    | 216266/371472 [6:31:34<12:21:11,  3.49it/s]
 58%|█████▊    | 216267/371472 [6:31:35<12:30:01,  3.45it/s]
 58%|█████▊    | 216268/371472 [6:31:35<12:23:20,  3.48it/s]
 58%|█████▊    | 216269/371472 [6:31:35<11:56:03,  3.61it/s]
 58%|█████▊    | 216270/371472 [6:31:35<11:54:57,  3.62it/s]
 58%|█████▊    | 216271/371472 [6:31:36<12:37:36,  3.41it/s]
 58%|█████▊    | 216272/371472 [6:31:36<12:32:40,  3.44it/s]
 58%|█████▊    | 216273/371472 [6:31:36<13:06:10,  3.29it/s]
 58%|█████▊    | 216274/371472 [6:31:37<12:50:42,  3.36it/s]
 58%|█████▊    | 216275/371472 [6:31:37<12:26:53,  3.46it/s]
 58%|█████▊    | 216276/371472 [6:31:37<12:45:40,  3.38it/s]
 58%|█████▊    | 216277/371472 [6:31:37<13:09:24,  3.28it/s]
 58%|█████▊    | 216278/371472 [6:31:38<12:50:37,  3.36it/s]
 58%|█████▊    | 216279/371472 [6:31:38<12:59:18,  3.32it/s]
 58%|█████▊    | 216280/371472 [6:31:38<12:48:16,  3.37it/s]
                                                            
{'loss': 2.7119, 'learning_rate': 4.762007369260272e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216280/371472 [6:31:38<12:48:16,  3.37it/s]
 58%|█████▊    | 216281/371472 [6:31:39<12:58:54,  3.32it/s]
 58%|█████▊    | 216282/371472 [6:31:39<12:46:12,  3.38it/s]
 58%|█████▊    | 216283/371472 [6:31:39<12:32:37,  3.44it/s]
 58%|█████▊    | 216284/371472 [6:31:39<12:27:02,  3.46it/s]
 58%|█████▊    | 216285/371472 [6:31:40<12:07:29,  3.56it/s]
 58%|█████▊    | 216286/371472 [6:31:40<12:05:38,  3.56it/s]
 58%|█████▊    | 216287/371472 [6:31:40<11:49:27,  3.65it/s]
 58%|█████▊    | 216288/371472 [6:31:41<11:47:41,  3.65it/s]
 58%|█████▊    | 216289/371472 [6:31:41<11:49:31,  3.65it/s]
 58%|█████▊    | 216290/371472 [6:31:41<11:49:38,  3.64it/s]
 58%|█████▊    | 216291/371472 [6:31:41<11:54:23,  3.62it/s]
 58%|█████▊    | 216292/371472 [6:31:42<11:48:56,  3.65it/s]
 58%|█████▊    | 216293/371472 [6:31:42<12:31:04,  3.44it/s]
 58%|█████▊    | 216294/371472 [6:31:42<12:38:17,  3.41it/s]
 58%|█████▊    | 216295/371472 [6:31:43<13:38:52,  3.16it/s]
 58%|█████▊    | 216296/371472 [6:31:43<13:06:27,  3.29it/s]
 58%|█████▊    | 216297/371472 [6:31:43<12:30:52,  3.44it/s]
 58%|█████▊    | 216298/371472 [6:31:43<12:14:21,  3.52it/s]
 58%|█████▊    | 216299/371472 [6:31:44<12:18:22,  3.50it/s]
 58%|█████▊    | 216300/371472 [6:31:44<12:37:34,  3.41it/s]
                                                            
{'loss': 2.6735, 'learning_rate': 4.761522549505484e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216300/371472 [6:31:44<12:37:34,  3.41it/s]
 58%|█████▊    | 216301/371472 [6:31:44<12:18:44,  3.50it/s]
 58%|█████▊    | 216302/371472 [6:31:45<12:16:07,  3.51it/s]
 58%|█████▊    | 216303/371472 [6:31:45<12:15:40,  3.52it/s]
 58%|█████▊    | 216304/371472 [6:31:45<12:06:27,  3.56it/s]
 58%|█████▊    | 216305/371472 [6:31:45<12:12:59,  3.53it/s]
 58%|█████▊    | 216306/371472 [6:31:46<12:30:40,  3.45it/s]
 58%|█████▊    | 216307/371472 [6:31:46<12:47:53,  3.37it/s]
 58%|█████▊    | 216308/371472 [6:31:46<12:32:31,  3.44it/s]
 58%|█████▊    | 216309/371472 [6:31:47<12:52:53,  3.35it/s]
 58%|█████▊    | 216310/371472 [6:31:47<12:44:45,  3.38it/s]
 58%|█████▊    | 216311/371472 [6:31:47<12:35:13,  3.42it/s]
 58%|█████▊    | 216312/371472 [6:31:48<12:31:25,  3.44it/s]
 58%|█████▊    | 216313/371472 [6:31:48<12:26:31,  3.46it/s]
 58%|█████▊    | 216314/371472 [6:31:48<12:17:03,  3.51it/s]
 58%|█████▊    | 216315/371472 [6:31:48<12:21:53,  3.49it/s]
 58%|█████▊    | 216316/371472 [6:31:49<12:09:47,  3.54it/s]
 58%|█████▊    | 216317/371472 [6:31:49<12:12:40,  3.53it/s]
 58%|█████▊    | 216318/371472 [6:31:49<12:01:58,  3.58it/s]
 58%|█████▊    | 216319/371472 [6:31:49<11:58:17,  3.60it/s]
 58%|█████▊    | 216320/371472 [6:31:50<12:00:03,  3.59it/s]
                                                            
{'loss': 2.9062, 'learning_rate': 4.7610377297506945e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216320/371472 [6:31:50<12:00:03,  3.59it/s]
 58%|█████▊    | 216321/371472 [6:31:50<12:09:05,  3.55it/s]
 58%|█████▊    | 216322/371472 [6:31:50<12:31:16,  3.44it/s]
 58%|█████▊    | 216323/371472 [6:31:51<12:39:46,  3.40it/s]
 58%|█████▊    | 216324/371472 [6:31:51<13:29:34,  3.19it/s]
 58%|█████▊    | 216325/371472 [6:31:51<13:04:09,  3.30it/s]
 58%|█████▊    | 216326/371472 [6:31:52<13:37:50,  3.16it/s]
 58%|█████▊    | 216327/371472 [6:31:52<13:19:53,  3.23it/s]
 58%|█████▊    | 216328/371472 [6:31:52<13:00:20,  3.31it/s]
 58%|█████▊    | 216329/371472 [6:31:53<12:33:57,  3.43it/s]
 58%|█████▊    | 216330/371472 [6:31:53<12:29:27,  3.45it/s]
 58%|█████▊    | 216331/371472 [6:31:53<12:05:20,  3.56it/s]
 58%|█████▊    | 216332/371472 [6:31:53<12:04:51,  3.57it/s]
 58%|█████▊    | 216333/371472 [6:31:54<11:38:55,  3.70it/s]
 58%|█████▊    | 216334/371472 [6:31:54<11:34:15,  3.72it/s]
 58%|█████▊    | 216335/371472 [6:31:54<11:31:51,  3.74it/s]
 58%|█████▊    | 216336/371472 [6:31:54<11:51:40,  3.63it/s]
 58%|█████▊    | 216337/371472 [6:31:55<12:06:18,  3.56it/s]
 58%|█████▊    | 216338/371472 [6:31:55<12:08:17,  3.55it/s]
 58%|█████▊    | 216339/371472 [6:31:55<12:07:06,  3.56it/s]
 58%|█████▊    | 216340/371472 [6:31:56<12:05:27,  3.56it/s]
                                                            
{'loss': 2.7525, 'learning_rate': 4.7605529099959057e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216340/371472 [6:31:56<12:05:27,  3.56it/s]
 58%|█████▊    | 216341/371472 [6:31:56<12:26:43,  3.46it/s]
 58%|█████▊    | 216342/371472 [6:31:56<13:19:05,  3.24it/s]
 58%|█████▊    | 216343/371472 [6:31:57<13:47:34,  3.12it/s]
 58%|█████▊    | 216344/371472 [6:31:57<13:23:42,  3.22it/s]
 58%|█████▊    | 216345/371472 [6:31:57<13:02:11,  3.31it/s]
 58%|█████▊    | 216346/371472 [6:31:57<13:03:09,  3.30it/s]
 58%|█████▊    | 216347/371472 [6:31:58<13:03:19,  3.30it/s]
 58%|█████▊    | 216348/371472 [6:31:58<13:40:25,  3.15it/s]
 58%|█████▊    | 216349/371472 [6:31:58<14:20:42,  3.00it/s]
 58%|█████▊    | 216350/371472 [6:31:59<13:03:30,  3.30it/s]
 58%|█████▊    | 216351/371472 [6:31:59<12:39:41,  3.40it/s]
 58%|█████▊    | 216352/371472 [6:31:59<12:21:17,  3.49it/s]
 58%|█████▊    | 216353/371472 [6:32:00<12:27:47,  3.46it/s]
 58%|█████▊    | 216354/371472 [6:32:00<13:07:24,  3.28it/s]
 58%|█████▊    | 216355/371472 [6:32:00<12:45:04,  3.38it/s]
 58%|█████▊    | 216356/371472 [6:32:00<12:31:55,  3.44it/s]
 58%|█████▊    | 216357/371472 [6:32:01<12:25:14,  3.47it/s]
 58%|█████▊    | 216358/371472 [6:32:01<12:35:33,  3.42it/s]
 58%|█████▊    | 216359/371472 [6:32:01<11:59:31,  3.59it/s]
 58%|█████▊    | 216360/371472 [6:32:02<12:10:07,  3.54it/s]
                                                            
{'loss': 2.6748, 'learning_rate': 4.7600680902411164e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216360/371472 [6:32:02<12:10:07,  3.54it/s]
 58%|█████▊    | 216361/371472 [6:32:02<11:59:44,  3.59it/s]
 58%|█████▊    | 216362/371472 [6:32:02<11:47:47,  3.65it/s]
 58%|█████▊    | 216363/371472 [6:32:02<11:55:12,  3.61it/s]
 58%|█████▊    | 216364/371472 [6:32:03<12:36:07,  3.42it/s]
 58%|█████▊    | 216365/371472 [6:32:03<13:21:10,  3.23it/s]
 58%|█████▊    | 216366/371472 [6:32:03<13:05:40,  3.29it/s]
 58%|█████▊    | 216367/371472 [6:32:04<12:43:53,  3.38it/s]
 58%|█████▊    | 216368/371472 [6:32:04<12:23:47,  3.48it/s]
 58%|█████▊    | 216369/371472 [6:32:04<12:48:45,  3.36it/s]
 58%|█████▊    | 216370/371472 [6:32:04<12:23:07,  3.48it/s]
 58%|█████▊    | 216371/371472 [6:32:05<12:23:50,  3.48it/s]
 58%|█████▊    | 216372/371472 [6:32:05<12:06:06,  3.56it/s]
 58%|█████▊    | 216373/371472 [6:32:05<12:22:29,  3.48it/s]
 58%|█████▊    | 216374/371472 [6:32:06<12:17:59,  3.50it/s]
 58%|█████▊    | 216375/371472 [6:32:06<12:48:05,  3.37it/s]
 58%|█████▊    | 216376/371472 [6:32:06<12:38:47,  3.41it/s]
 58%|█████▊    | 216377/371472 [6:32:06<12:29:17,  3.45it/s]
 58%|█████▊    | 216378/371472 [6:32:07<12:25:34,  3.47it/s]
 58%|█████▊    | 216379/371472 [6:32:07<12:24:48,  3.47it/s]
 58%|█████▊    | 216380/371472 [6:32:07<12:20:00,  3.49it/s]
                                                            
{'loss': 2.6888, 'learning_rate': 4.759583270486328e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216380/371472 [6:32:07<12:20:00,  3.49it/s]
 58%|█████▊    | 216381/371472 [6:32:08<13:01:01,  3.31it/s]
 58%|█████▊    | 216382/371472 [6:32:08<12:50:17,  3.36it/s]
 58%|█████▊    | 216383/371472 [6:32:08<12:40:27,  3.40it/s]
 58%|█████▊    | 216384/371472 [6:32:09<13:18:00,  3.24it/s]
 58%|█████▊    | 216385/371472 [6:32:09<13:15:53,  3.25it/s]
 58%|█████▊    | 216386/371472 [6:32:09<13:22:49,  3.22it/s]
 58%|█████▊    | 216387/371472 [6:32:10<13:07:34,  3.28it/s]
 58%|█████▊    | 216388/371472 [6:32:10<12:54:27,  3.34it/s]
 58%|█████▊    | 216389/371472 [6:32:10<13:13:42,  3.26it/s]
 58%|█████▊    | 216390/371472 [6:32:10<13:13:35,  3.26it/s]
 58%|█████▊    | 216391/371472 [6:32:11<12:55:00,  3.34it/s]
 58%|█████▊    | 216392/371472 [6:32:11<12:29:33,  3.45it/s]
 58%|█████▊    | 216393/371472 [6:32:11<12:11:12,  3.53it/s]
 58%|█████▊    | 216394/371472 [6:32:12<12:06:57,  3.56it/s]
 58%|█████▊    | 216395/371472 [6:32:12<12:00:58,  3.58it/s]
 58%|█████▊    | 216396/371472 [6:32:12<11:55:42,  3.61it/s]
 58%|█████▊    | 216397/371472 [6:32:12<12:16:45,  3.51it/s]
 58%|█████▊    | 216398/371472 [6:32:13<12:13:49,  3.52it/s]
 58%|█████▊    | 216399/371472 [6:32:13<12:33:22,  3.43it/s]
 58%|█████▊    | 216400/371472 [6:32:13<12:48:50,  3.36it/s]
                                                            
{'loss': 2.7734, 'learning_rate': 4.7590984507315384e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216400/371472 [6:32:13<12:48:50,  3.36it/s]
 58%|█████▊    | 216401/371472 [6:32:14<12:18:43,  3.50it/s]
 58%|█████▊    | 216402/371472 [6:32:14<12:32:10,  3.44it/s]
 58%|█████▊    | 216403/371472 [6:32:14<12:12:57,  3.53it/s]
 58%|█████▊    | 216404/371472 [6:32:14<11:51:23,  3.63it/s]
 58%|█████▊    | 216405/371472 [6:32:15<12:14:45,  3.52it/s]
 58%|█████▊    | 216406/371472 [6:32:15<12:14:36,  3.52it/s]
 58%|█████▊    | 216407/371472 [6:32:15<11:53:49,  3.62it/s]
 58%|█████▊    | 216408/371472 [6:32:15<11:45:11,  3.66it/s]
 58%|█████▊    | 216409/371472 [6:32:16<11:54:08,  3.62it/s]
 58%|█████▊    | 216410/371472 [6:32:16<12:01:51,  3.58it/s]
 58%|█████▊    | 216411/371472 [6:32:16<12:39:03,  3.40it/s]
 58%|█████▊    | 216412/371472 [6:32:17<12:22:53,  3.48it/s]
 58%|█████▊    | 216413/371472 [6:32:17<12:50:38,  3.35it/s]
 58%|█████▊    | 216414/371472 [6:32:17<12:51:53,  3.35it/s]
 58%|█████▊    | 216415/371472 [6:32:18<13:08:24,  3.28it/s]
 58%|█████▊    | 216416/371472 [6:32:18<14:01:13,  3.07it/s]
 58%|█████▊    | 216417/371472 [6:32:18<13:33:16,  3.18it/s]
 58%|█████▊    | 216418/371472 [6:32:19<12:54:51,  3.34it/s]
 58%|█████▊    | 216419/371472 [6:32:19<12:52:00,  3.35it/s]
 58%|█████▊    | 216420/371472 [6:32:19<12:56:43,  3.33it/s]
                                                            
{'loss': 2.9006, 'learning_rate': 4.75861363097675e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216420/371472 [6:32:19<12:56:43,  3.33it/s]
 58%|█████▊    | 216421/371472 [6:32:19<12:44:52,  3.38it/s]
 58%|█████▊    | 216422/371472 [6:32:20<12:14:44,  3.52it/s]
 58%|█████▊    | 216423/371472 [6:32:20<11:44:53,  3.67it/s]
 58%|█████▊    | 216424/371472 [6:32:20<12:01:46,  3.58it/s]
 58%|█████▊    | 216425/371472 [6:32:20<11:53:48,  3.62it/s]
 58%|█████▊    | 216426/371472 [6:32:21<13:18:08,  3.24it/s]
 58%|█████▊    | 216427/371472 [6:32:21<12:52:40,  3.34it/s]
 58%|█████▊    | 216428/371472 [6:32:21<12:36:24,  3.42it/s]
 58%|█████▊    | 216429/371472 [6:32:22<12:10:54,  3.54it/s]
 58%|█████▊    | 216430/371472 [6:32:22<12:58:05,  3.32it/s]
 58%|█████▊    | 216431/371472 [6:32:22<12:23:27,  3.48it/s]
 58%|█████▊    | 216432/371472 [6:32:23<12:18:05,  3.50it/s]
 58%|█████▊    | 216433/371472 [6:32:23<12:12:36,  3.53it/s]
 58%|█████▊    | 216434/371472 [6:32:23<12:20:46,  3.49it/s]
 58%|█████▊    | 216435/371472 [6:32:23<12:21:14,  3.49it/s]
 58%|█████▊    | 216436/371472 [6:32:24<12:14:24,  3.52it/s]
 58%|█████▊    | 216437/371472 [6:32:24<12:26:01,  3.46it/s]
 58%|█████▊    | 216438/371472 [6:32:24<13:37:21,  3.16it/s]
 58%|█████▊    | 216439/371472 [6:32:25<13:02:50,  3.30it/s]
 58%|█████▊    | 216440/371472 [6:32:25<12:54:11,  3.34it/s]
                                                            
{'loss': 2.7669, 'learning_rate': 4.758128811221961e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216440/371472 [6:32:25<12:54:11,  3.34it/s]
 58%|█████▊    | 216441/371472 [6:32:25<12:27:08,  3.46it/s]
 58%|█████▊    | 216442/371472 [6:32:25<12:10:13,  3.54it/s]
 58%|█████▊    | 216443/371472 [6:32:26<12:44:39,  3.38it/s]
 58%|█████▊    | 216444/371472 [6:32:26<12:51:24,  3.35it/s]
 58%|█████▊    | 216445/371472 [6:32:26<12:51:48,  3.35it/s]
 58%|█████▊    | 216446/371472 [6:32:27<12:58:39,  3.32it/s]
 58%|█████▊    | 216447/371472 [6:32:27<12:42:35,  3.39it/s]
 58%|█████▊    | 216448/371472 [6:32:27<12:35:05,  3.42it/s]
 58%|█████▊    | 216449/371472 [6:32:28<12:21:06,  3.49it/s]
 58%|█████▊    | 216450/371472 [6:32:28<13:03:08,  3.30it/s]
 58%|█████▊    | 216451/371472 [6:32:28<13:06:33,  3.28it/s]
 58%|█████▊    | 216452/371472 [6:32:28<12:36:39,  3.41it/s]
 58%|█████▊    | 216453/371472 [6:32:29<12:43:57,  3.38it/s]
 58%|█████▊    | 216454/371472 [6:32:29<12:06:56,  3.55it/s]
 58%|█████▊    | 216455/371472 [6:32:29<11:58:20,  3.60it/s]
 58%|█████▊    | 216456/371472 [6:32:30<12:20:09,  3.49it/s]
 58%|█████▊    | 216457/371472 [6:32:30<12:01:48,  3.58it/s]
 58%|█████▊    | 216458/371472 [6:32:30<12:12:44,  3.53it/s]
 58%|█████▊    | 216459/371472 [6:32:30<12:27:45,  3.46it/s]
 58%|█████▊    | 216460/371472 [6:32:31<12:19:09,  3.50it/s]
                                                            
{'loss': 2.8867, 'learning_rate': 4.757643991467172e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216460/371472 [6:32:31<12:19:09,  3.50it/s]
 58%|█████▊    | 216461/371472 [6:32:31<11:59:16,  3.59it/s]
 58%|█████▊    | 216462/371472 [6:32:31<11:49:43,  3.64it/s]
 58%|█████▊    | 216463/371472 [6:32:32<12:16:29,  3.51it/s]
 58%|█████▊    | 216464/371472 [6:32:32<12:03:36,  3.57it/s]
 58%|█████▊    | 216465/371472 [6:32:32<11:43:06,  3.67it/s]
 58%|█████▊    | 216466/371472 [6:32:32<13:19:53,  3.23it/s]
 58%|█████▊    | 216467/371472 [6:32:33<13:47:40,  3.12it/s]
 58%|█████▊    | 216468/371472 [6:32:33<13:34:55,  3.17it/s]
 58%|█████▊    | 216469/371472 [6:32:33<13:03:32,  3.30it/s]
 58%|█████▊    | 216470/371472 [6:32:34<12:31:52,  3.44it/s]
 58%|█████▊    | 216471/371472 [6:32:34<12:04:31,  3.57it/s]
 58%|█████▊    | 216472/371472 [6:32:34<12:51:49,  3.35it/s]
 58%|█████▊    | 216473/371472 [6:32:35<12:33:55,  3.43it/s]
 58%|█████▊    | 216474/371472 [6:32:35<12:13:16,  3.52it/s]
 58%|█████▊    | 216475/371472 [6:32:35<12:07:36,  3.55it/s]
 58%|█████▊    | 216476/371472 [6:32:35<12:08:16,  3.55it/s]
 58%|█████▊    | 216477/371472 [6:32:36<12:24:14,  3.47it/s]
 58%|█████▊    | 216478/371472 [6:32:36<12:33:30,  3.43it/s]
 58%|█████▊    | 216479/371472 [6:32:36<12:28:22,  3.45it/s]
 58%|█████▊    | 216480/371472 [6:32:37<12:18:18,  3.50it/s]
                                                            
{'loss': 2.7095, 'learning_rate': 4.757159171712383e-07, 'epoch': 9.32}
+
 58%|█████▊    | 216480/371472 [6:32:37<12:18:18,  3.50it/s]
 58%|█████▊    | 216481/371472 [6:32:37<12:18:16,  3.50it/s]
 58%|█████▊    | 216482/371472 [6:32:37<11:57:04,  3.60it/s]
 58%|█████▊    | 216483/371472 [6:32:37<12:30:42,  3.44it/s]
 58%|█████▊    | 216484/371472 [6:32:38<12:50:20,  3.35it/s]
 58%|█████▊    | 216485/371472 [6:32:38<12:27:55,  3.45it/s]
 58%|█████▊    | 216486/371472 [6:32:38<12:39:40,  3.40it/s]
 58%|█████▊    | 216487/371472 [6:32:39<12:30:29,  3.44it/s]
 58%|█████▊    | 216488/371472 [6:32:39<12:11:49,  3.53it/s]
 58%|█████▊    | 216489/371472 [6:32:39<12:06:47,  3.55it/s]
 58%|█████▊    | 216490/371472 [6:32:39<11:52:08,  3.63it/s]
 58%|█████▊    | 216491/371472 [6:32:40<11:55:53,  3.61it/s]
 58%|█████▊    | 216492/371472 [6:32:40<11:42:41,  3.68it/s]
 58%|█████▊    | 216493/371472 [6:32:40<11:42:42,  3.68it/s]
 58%|█████▊    | 216494/371472 [6:32:40<11:41:20,  3.68it/s]
 58%|█████▊    | 216495/371472 [6:32:41<11:56:56,  3.60it/s]
 58%|█████▊    | 216496/371472 [6:32:41<12:16:57,  3.50it/s]
 58%|█████▊    | 216497/371472 [6:32:41<13:23:59,  3.21it/s]
 58%|█████▊    | 216498/371472 [6:32:42<13:22:07,  3.22it/s]
 58%|█████▊    | 216499/371472 [6:32:42<12:52:36,  3.34it/s]
 58%|█████▊    | 216500/371472 [6:32:42<12:40:55,  3.39it/s]
                                                            
{'loss': 2.7579, 'learning_rate': 4.7566743519575946e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216500/371472 [6:32:42<12:40:55,  3.39it/s]
 58%|█████▊    | 216501/371472 [6:32:43<12:43:49,  3.38it/s]
 58%|█████▊    | 216502/371472 [6:32:43<12:38:50,  3.40it/s]
 58%|█████▊    | 216503/371472 [6:32:43<12:24:53,  3.47it/s]
 58%|█████▊    | 216504/371472 [6:32:43<12:32:59,  3.43it/s]
 58%|█████▊    | 216505/371472 [6:32:44<12:24:22,  3.47it/s]
 58%|█████▊    | 216506/371472 [6:32:44<12:30:09,  3.44it/s]
 58%|█████▊    | 216507/371472 [6:32:44<12:13:52,  3.52it/s]
 58%|█████▊    | 216508/371472 [6:32:45<12:04:23,  3.57it/s]
 58%|█████▊    | 216509/371472 [6:32:45<12:00:00,  3.59it/s]
 58%|█████▊    | 216510/371472 [6:32:45<12:05:50,  3.56it/s]
 58%|█████▊    | 216511/371472 [6:32:45<12:40:58,  3.39it/s]
 58%|█████▊    | 216512/371472 [6:32:46<12:07:09,  3.55it/s]
 58%|█████▊    | 216513/371472 [6:32:46<13:02:02,  3.30it/s]
 58%|█████▊    | 216514/371472 [6:32:46<12:47:23,  3.37it/s]
 58%|█████▊    | 216515/371472 [6:32:47<13:51:31,  3.11it/s]
 58%|█████▊    | 216516/371472 [6:32:47<13:37:56,  3.16it/s]
 58%|█████▊    | 216517/371472 [6:32:47<13:28:26,  3.19it/s]
 58%|█████▊    | 216518/371472 [6:32:48<13:47:31,  3.12it/s]
 58%|█████▊    | 216519/371472 [6:32:48<13:04:58,  3.29it/s]
 58%|█████▊    | 216520/371472 [6:32:48<13:57:44,  3.08it/s]
                                                            
{'loss': 2.9818, 'learning_rate': 4.756189532202805e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216520/371472 [6:32:48<13:57:44,  3.08it/s]
 58%|█████▊    | 216521/371472 [6:32:49<13:49:06,  3.11it/s]
 58%|█████▊    | 216522/371472 [6:32:49<13:48:49,  3.12it/s]
 58%|█████▊    | 216523/371472 [6:32:49<13:24:49,  3.21it/s]
 58%|█████▊    | 216524/371472 [6:32:50<13:39:03,  3.15it/s]
 58%|█████▊    | 216525/371472 [6:32:50<13:17:21,  3.24it/s]
 58%|█████▊    | 216526/371472 [6:32:50<13:10:25,  3.27it/s]
 58%|█████▊    | 216527/371472 [6:32:50<13:08:49,  3.27it/s]
 58%|█████▊    | 216528/371472 [6:32:51<12:45:08,  3.38it/s]
 58%|█████▊    | 216529/371472 [6:32:51<12:55:49,  3.33it/s]
 58%|█████▊    | 216530/371472 [6:32:51<14:05:49,  3.05it/s]
 58%|█████▊    | 216531/371472 [6:32:52<13:57:20,  3.08it/s]
 58%|█████▊    | 216532/371472 [6:32:52<13:00:18,  3.31it/s]
 58%|█████▊    | 216533/371472 [6:32:52<12:47:53,  3.36it/s]
 58%|█████▊    | 216534/371472 [6:32:53<12:48:05,  3.36it/s]
 58%|█████▊    | 216535/371472 [6:32:53<13:04:56,  3.29it/s]
 58%|█████▊    | 216536/371472 [6:32:53<12:41:17,  3.39it/s]
 58%|█████▊    | 216537/371472 [6:32:53<12:23:52,  3.47it/s]
 58%|█████▊    | 216538/371472 [6:32:54<12:19:23,  3.49it/s]
 58%|█████▊    | 216539/371472 [6:32:54<12:15:30,  3.51it/s]
 58%|█████▊    | 216540/371472 [6:32:54<12:20:47,  3.49it/s]
                                                            
{'loss': 2.6963, 'learning_rate': 4.7557047124480166e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216540/371472 [6:32:54<12:20:47,  3.49it/s]
 58%|█████▊    | 216541/371472 [6:32:55<12:39:56,  3.40it/s]
 58%|█████▊    | 216542/371472 [6:32:55<12:22:03,  3.48it/s]
 58%|█████▊    | 216543/371472 [6:32:55<12:16:51,  3.50it/s]
 58%|█████▊    | 216544/371472 [6:32:55<11:50:25,  3.63it/s]
 58%|█████▊    | 216545/371472 [6:32:56<11:36:48,  3.71it/s]
 58%|█████▊    | 216546/371472 [6:32:56<12:14:01,  3.52it/s]
 58%|█████▊    | 216547/371472 [6:32:56<11:53:28,  3.62it/s]
 58%|█████▊    | 216548/371472 [6:32:57<12:33:39,  3.43it/s]
 58%|█████▊    | 216549/371472 [6:32:57<12:58:32,  3.32it/s]
 58%|█████▊    | 216550/371472 [6:32:57<12:48:36,  3.36it/s]
 58%|█████▊    | 216551/371472 [6:32:57<12:46:17,  3.37it/s]
 58%|█████▊    | 216552/371472 [6:32:58<13:32:54,  3.18it/s]
 58%|█████▊    | 216553/371472 [6:32:58<12:51:19,  3.35it/s]
 58%|█████▊    | 216554/371472 [6:32:58<12:34:19,  3.42it/s]
 58%|█████▊    | 216555/371472 [6:32:59<12:21:57,  3.48it/s]
 58%|█████▊    | 216556/371472 [6:32:59<12:12:52,  3.52it/s]
 58%|█████▊    | 216557/371472 [6:32:59<12:52:51,  3.34it/s]
 58%|█████▊    | 216558/371472 [6:33:00<12:39:41,  3.40it/s]
 58%|█████▊    | 216559/371472 [6:33:00<12:22:34,  3.48it/s]
 58%|█████▊    | 216560/371472 [6:33:00<12:05:52,  3.56it/s]
                                                            
{'loss': 2.8073, 'learning_rate': 4.7552198926932273e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216560/371472 [6:33:00<12:05:52,  3.56it/s]
 58%|█████▊    | 216561/371472 [6:33:00<11:47:15,  3.65it/s]
 58%|█████▊    | 216562/371472 [6:33:01<12:20:32,  3.49it/s]
 58%|█████▊    | 216563/371472 [6:33:01<11:53:55,  3.62it/s]
 58%|█████▊    | 216564/371472 [6:33:01<12:00:53,  3.58it/s]
 58%|█████▊    | 216565/371472 [6:33:02<12:39:51,  3.40it/s]
 58%|█████▊    | 216566/371472 [6:33:02<13:23:38,  3.21it/s]
 58%|█████▊    | 216567/371472 [6:33:02<12:48:52,  3.36it/s]
 58%|█████▊    | 216568/371472 [6:33:02<12:45:31,  3.37it/s]
 58%|█████▊    | 216569/371472 [6:33:03<12:51:14,  3.35it/s]
 58%|█████▊    | 216570/371472 [6:33:03<13:48:56,  3.11it/s]
 58%|█████▊    | 216571/371472 [6:33:03<13:10:35,  3.27it/s]
 58%|█████▊    | 216572/371472 [6:33:04<12:27:13,  3.46it/s]
 58%|█████▊    | 216573/371472 [6:33:04<13:07:54,  3.28it/s]
 58%|█████▊    | 216574/371472 [6:33:04<12:29:32,  3.44it/s]
 58%|█████▊    | 216575/371472 [6:33:04<12:12:19,  3.53it/s]
 58%|█████▊    | 216576/371472 [6:33:05<11:51:11,  3.63it/s]
 58%|█████▊    | 216577/371472 [6:33:05<11:54:57,  3.61it/s]
 58%|█████▊    | 216578/371472 [6:33:05<12:26:49,  3.46it/s]
 58%|█████▊    | 216579/371472 [6:33:06<12:29:48,  3.44it/s]
 58%|█████▊    | 216580/371472 [6:33:06<12:20:27,  3.49it/s]
                                                            
{'loss': 2.7222, 'learning_rate': 4.7547350729384385e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216580/371472 [6:33:06<12:20:27,  3.49it/s]
 58%|█████▊    | 216581/371472 [6:33:06<13:03:28,  3.29it/s]
 58%|█████▊    | 216582/371472 [6:33:07<13:13:28,  3.25it/s]
 58%|█████▊    | 216583/371472 [6:33:07<12:37:21,  3.41it/s]
 58%|█████▊    | 216584/371472 [6:33:07<12:57:35,  3.32it/s]
 58%|█████▊    | 216585/371472 [6:33:08<13:41:05,  3.14it/s]
 58%|█████▊    | 216586/371472 [6:33:08<12:54:30,  3.33it/s]
 58%|█████▊    | 216587/371472 [6:33:08<12:44:35,  3.38it/s]
 58%|█████▊    | 216588/371472 [6:33:08<13:04:23,  3.29it/s]
 58%|█████▊    | 216589/371472 [6:33:09<13:19:18,  3.23it/s]
 58%|█████▊    | 216590/371472 [6:33:09<13:11:12,  3.26it/s]
 58%|█████▊    | 216591/371472 [6:33:09<12:36:53,  3.41it/s]
 58%|█████▊    | 216592/371472 [6:33:10<12:12:06,  3.53it/s]
 58%|█████▊    | 216593/371472 [6:33:10<11:48:38,  3.64it/s]
 58%|█████▊    | 216594/371472 [6:33:10<12:04:36,  3.56it/s]
 58%|█████▊    | 216595/371472 [6:33:10<13:43:59,  3.13it/s]
 58%|█████▊    | 216596/371472 [6:33:11<13:30:17,  3.19it/s]
 58%|█████▊    | 216597/371472 [6:33:11<13:17:25,  3.24it/s]
 58%|█████▊    | 216598/371472 [6:33:11<12:50:49,  3.35it/s]
 58%|█████▊    | 216599/371472 [6:33:12<12:32:57,  3.43it/s]
 58%|█████▊    | 216600/371472 [6:33:12<12:15:19,  3.51it/s]
                                                            
{'loss': 2.7137, 'learning_rate': 4.754250253183649e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216600/371472 [6:33:12<12:15:19,  3.51it/s]
 58%|█████▊    | 216601/371472 [6:33:12<11:50:53,  3.63it/s]
 58%|█████▊    | 216602/371472 [6:33:13<12:48:42,  3.36it/s]
 58%|█████▊    | 216603/371472 [6:33:13<12:48:45,  3.36it/s]
 58%|█████▊    | 216604/371472 [6:33:13<12:50:39,  3.35it/s]
 58%|█████▊    | 216605/371472 [6:33:13<12:29:43,  3.44it/s]
 58%|█████▊    | 216606/371472 [6:33:14<12:20:58,  3.48it/s]
 58%|█████▊    | 216607/371472 [6:33:14<12:18:21,  3.50it/s]
 58%|█████▊    | 216608/371472 [6:33:14<12:33:55,  3.42it/s]
 58%|█████▊    | 216609/371472 [6:33:15<13:12:54,  3.26it/s]
 58%|█████▊    | 216610/371472 [6:33:15<13:00:40,  3.31it/s]
 58%|█████▊    | 216611/371472 [6:33:15<12:27:53,  3.45it/s]
 58%|█████▊    | 216612/371472 [6:33:15<12:03:33,  3.57it/s]
 58%|█████▊    | 216613/371472 [6:33:16<12:19:37,  3.49it/s]
 58%|█████▊    | 216614/371472 [6:33:16<12:13:20,  3.52it/s]
 58%|█████▊    | 216615/371472 [6:33:16<12:01:36,  3.58it/s]
 58%|█████▊    | 216616/371472 [6:33:17<12:20:05,  3.49it/s]
 58%|█████▊    | 216617/371472 [6:33:17<12:12:12,  3.52it/s]
 58%|█████▊    | 216618/371472 [6:33:17<12:01:17,  3.58it/s]
 58%|█████▊    | 216619/371472 [6:33:17<13:14:52,  3.25it/s]
 58%|█████▊    | 216620/371472 [6:33:18<13:22:11,  3.22it/s]
                                                            
{'loss': 2.8584, 'learning_rate': 4.753765433428861e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216620/371472 [6:33:18<13:22:11,  3.22it/s]
 58%|█████▊    | 216621/371472 [6:33:18<12:54:55,  3.33it/s]
 58%|█████▊    | 216622/371472 [6:33:18<12:34:53,  3.42it/s]
 58%|█████▊    | 216623/371472 [6:33:19<12:10:07,  3.53it/s]
 58%|█████▊    | 216624/371472 [6:33:19<12:32:16,  3.43it/s]
 58%|█████▊    | 216625/371472 [6:33:19<12:09:35,  3.54it/s]
 58%|█████▊    | 216626/371472 [6:33:19<12:07:32,  3.55it/s]
 58%|█████▊    | 216627/371472 [6:33:20<13:35:21,  3.17it/s]
 58%|█████▊    | 216628/371472 [6:33:20<13:24:44,  3.21it/s]
 58%|█████▊    | 216629/371472 [6:33:20<13:18:49,  3.23it/s]
 58%|█████▊    | 216630/371472 [6:33:21<13:31:58,  3.18it/s]
 58%|█████▊    | 216631/371472 [6:33:21<12:57:49,  3.32it/s]
 58%|█████▊    | 216632/371472 [6:33:21<12:51:46,  3.34it/s]
 58%|█████▊    | 216633/371472 [6:33:22<13:35:12,  3.17it/s]
 58%|█████▊    | 216634/371472 [6:33:22<12:52:44,  3.34it/s]
 58%|█████▊    | 216635/371472 [6:33:22<12:33:31,  3.42it/s]
 58%|█████▊    | 216636/371472 [6:33:23<12:33:17,  3.43it/s]
 58%|█████▊    | 216637/371472 [6:33:23<12:32:55,  3.43it/s]
 58%|█████▊    | 216638/371472 [6:33:23<13:15:02,  3.25it/s]
 58%|█████▊    | 216639/371472 [6:33:23<13:12:29,  3.26it/s]
 58%|█████▊    | 216640/371472 [6:33:24<12:37:42,  3.41it/s]
                                                            
{'loss': 2.927, 'learning_rate': 4.753280613674072e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216640/371472 [6:33:24<12:37:42,  3.41it/s]
 58%|█████▊    | 216641/371472 [6:33:24<12:10:48,  3.53it/s]
 58%|█████▊    | 216642/371472 [6:33:24<11:55:31,  3.61it/s]
 58%|█████▊    | 216643/371472 [6:33:25<11:53:54,  3.61it/s]
 58%|█████▊    | 216644/371472 [6:33:25<13:01:21,  3.30it/s]
 58%|█████▊    | 216645/371472 [6:33:25<13:23:32,  3.21it/s]
 58%|█████▊    | 216646/371472 [6:33:26<14:14:12,  3.02it/s]
 58%|█████▊    | 216647/371472 [6:33:26<13:21:51,  3.22it/s]
 58%|█████▊    | 216648/371472 [6:33:26<13:53:15,  3.10it/s]
 58%|█████▊    | 216649/371472 [6:33:26<13:15:42,  3.24it/s]
 58%|█████▊    | 216650/371472 [6:33:27<12:37:04,  3.41it/s]
 58%|█████▊    | 216651/371472 [6:33:27<12:45:51,  3.37it/s]
 58%|█████▊    | 216652/371472 [6:33:27<12:34:27,  3.42it/s]
 58%|█████▊    | 216653/371472 [6:33:28<13:00:27,  3.31it/s]
 58%|█████▊    | 216654/371472 [6:33:28<12:29:39,  3.44it/s]
 58%|█████▊    | 216655/371472 [6:33:28<12:20:38,  3.48it/s]
 58%|█████▊    | 216656/371472 [6:33:28<12:17:05,  3.50it/s]
 58%|█████▊    | 216657/371472 [6:33:29<12:13:20,  3.52it/s]
 58%|█████▊    | 216658/371472 [6:33:29<13:01:28,  3.30it/s]
 58%|█████▊    | 216659/371472 [6:33:29<12:57:22,  3.32it/s]
 58%|█████▊    | 216660/371472 [6:33:30<12:21:13,  3.48it/s]
                                                            
{'loss': 2.6638, 'learning_rate': 4.752795793919283e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216660/371472 [6:33:30<12:21:13,  3.48it/s]
 58%|█████▊    | 216661/371472 [6:33:30<12:28:30,  3.45it/s]
 58%|█████▊    | 216662/371472 [6:33:30<12:12:24,  3.52it/s]
 58%|█████▊    | 216663/371472 [6:33:31<12:31:05,  3.44it/s]
 58%|█████▊    | 216664/371472 [6:33:31<12:12:38,  3.52it/s]
 58%|█████▊    | 216665/371472 [6:33:31<11:55:59,  3.60it/s]
 58%|█████▊    | 216666/371472 [6:33:31<12:12:03,  3.52it/s]
 58%|█████▊    | 216667/371472 [6:33:32<11:47:54,  3.64it/s]
 58%|█████▊    | 216668/371472 [6:33:32<11:49:36,  3.64it/s]
 58%|█████▊    | 216669/371472 [6:33:32<12:06:52,  3.55it/s]
 58%|█████▊    | 216670/371472 [6:33:32<12:04:11,  3.56it/s]
 58%|█████▊    | 216671/371472 [6:33:33<12:05:16,  3.56it/s]
 58%|█████▊    | 216672/371472 [6:33:33<12:17:33,  3.50it/s]
 58%|█████▊    | 216673/371472 [6:33:33<11:59:58,  3.58it/s]
 58%|█████▊    | 216674/371472 [6:33:34<12:02:39,  3.57it/s]
 58%|█████▊    | 216675/371472 [6:33:34<11:56:05,  3.60it/s]
 58%|█████▊    | 216676/371472 [6:33:34<11:43:22,  3.67it/s]
 58%|█████▊    | 216677/371472 [6:33:34<11:49:01,  3.64it/s]
 58%|█████▊    | 216678/371472 [6:33:35<12:01:01,  3.58it/s]
 58%|█████▊    | 216679/371472 [6:33:35<11:58:36,  3.59it/s]
 58%|█████▊    | 216680/371472 [6:33:35<12:15:06,  3.51it/s]
                                                            
{'loss': 2.8273, 'learning_rate': 4.7523109741644937e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216680/371472 [6:33:35<12:15:06,  3.51it/s]
 58%|█████▊    | 216681/371472 [6:33:36<12:06:45,  3.55it/s]
 58%|█████▊    | 216682/371472 [6:33:36<11:52:59,  3.62it/s]
 58%|█████▊    | 216683/371472 [6:33:36<11:41:40,  3.68it/s]
 58%|█████▊    | 216684/371472 [6:33:36<12:23:38,  3.47it/s]
 58%|█████▊    | 216685/371472 [6:33:37<12:24:10,  3.47it/s]
 58%|█████▊    | 216686/371472 [6:33:37<12:33:53,  3.42it/s]
 58%|█████▊    | 216687/371472 [6:33:37<12:27:13,  3.45it/s]
 58%|█████▊    | 216688/371472 [6:33:38<12:40:58,  3.39it/s]
 58%|█████▊    | 216689/371472 [6:33:38<13:04:25,  3.29it/s]
 58%|█████▊    | 216690/371472 [6:33:38<13:27:28,  3.19it/s]
 58%|█████▊    | 216691/371472 [6:33:39<14:02:49,  3.06it/s]
 58%|█████▊    | 216692/371472 [6:33:39<13:20:15,  3.22it/s]
 58%|█████▊    | 216693/371472 [6:33:39<12:56:00,  3.32it/s]
 58%|█████▊    | 216694/371472 [6:33:39<12:45:19,  3.37it/s]
 58%|█████▊    | 216695/371472 [6:33:40<12:35:56,  3.41it/s]
 58%|█████▊    | 216696/371472 [6:33:40<12:25:07,  3.46it/s]
 58%|█████▊    | 216697/371472 [6:33:40<12:38:25,  3.40it/s]
 58%|█████▊    | 216698/371472 [6:33:41<11:57:58,  3.59it/s]
 58%|█████▊    | 216699/371472 [6:33:41<12:24:34,  3.46it/s]
 58%|█████▊    | 216700/371472 [6:33:41<12:34:49,  3.42it/s]
                                                            
{'loss': 2.8107, 'learning_rate': 4.7518261544097055e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216700/371472 [6:33:41<12:34:49,  3.42it/s]
 58%|█████▊    | 216701/371472 [6:33:41<12:03:00,  3.57it/s]
 58%|█████▊    | 216702/371472 [6:33:42<11:40:13,  3.68it/s]
 58%|█████▊    | 216703/371472 [6:33:42<11:50:44,  3.63it/s]
 58%|█████▊    | 216704/371472 [6:33:42<11:48:15,  3.64it/s]
 58%|█████▊    | 216705/371472 [6:33:42<11:34:05,  3.72it/s]
 58%|█████▊    | 216706/371472 [6:33:43<11:31:43,  3.73it/s]
 58%|█████▊    | 216707/371472 [6:33:43<12:18:49,  3.49it/s]
 58%|█████▊    | 216708/371472 [6:33:43<11:57:55,  3.59it/s]
 58%|█████▊    | 216709/371472 [6:33:44<12:32:41,  3.43it/s]
 58%|█████▊    | 216710/371472 [6:33:44<12:25:42,  3.46it/s]
 58%|█████▊    | 216711/371472 [6:33:44<12:16:12,  3.50it/s]
 58%|█████▊    | 216712/371472 [6:33:45<12:23:30,  3.47it/s]
 58%|█████▊    | 216713/371472 [6:33:45<13:38:25,  3.15it/s]
 58%|█████▊    | 216714/371472 [6:33:45<13:21:36,  3.22it/s]
 58%|█████▊    | 216715/371472 [6:33:45<12:52:56,  3.34it/s]
 58%|█████▊    | 216716/371472 [6:33:46<12:19:29,  3.49it/s]
 58%|█████▊    | 216717/371472 [6:33:46<12:25:44,  3.46it/s]
 58%|█████▊    | 216718/371472 [6:33:46<12:14:06,  3.51it/s]
 58%|█████▊    | 216719/371472 [6:33:47<12:38:28,  3.40it/s]
 58%|█████▊    | 216720/371472 [6:33:47<12:33:04,  3.42it/s]
                                                            
{'loss': 2.7368, 'learning_rate': 4.7513413346549157e-07, 'epoch': 9.33}
+
 58%|█████▊    | 216720/371472 [6:33:47<12:33:04,  3.42it/s]
 58%|█████▊    | 216721/371472 [6:33:47<12:21:12,  3.48it/s]
 58%|█████▊    | 216722/371472 [6:33:47<12:11:04,  3.53it/s]
 58%|���████▊    | 216723/371472 [6:33:48<12:05:35,  3.55it/s]
 58%|█████▊    | 216724/371472 [6:33:48<12:01:42,  3.57it/s]
 58%|█████▊    | 216725/371472 [6:33:48<12:14:20,  3.51it/s]
 58%|█████▊    | 216726/371472 [6:33:49<12:07:32,  3.54it/s]
 58%|█████▊    | 216727/371472 [6:33:49<12:08:15,  3.54it/s]
 58%|█████▊    | 216728/371472 [6:33:49<12:15:10,  3.51it/s]
 58%|█████▊    | 216729/371472 [6:33:49<12:11:03,  3.53it/s]
 58%|█████▊    | 216730/371472 [6:33:50<12:11:04,  3.53it/s]
 58%|█████▊    | 216731/371472 [6:33:50<12:17:27,  3.50it/s]
 58%|█████▊    | 216732/371472 [6:33:50<12:16:15,  3.50it/s]
 58%|█████▊    | 216733/371472 [6:33:51<12:06:40,  3.55it/s]
 58%|█████▊    | 216734/371472 [6:33:51<11:57:09,  3.60it/s]
 58%|█████▊    | 216735/371472 [6:33:51<12:32:50,  3.43it/s]
 58%|█████▊    | 216736/371472 [6:33:51<13:04:44,  3.29it/s]
 58%|█████▊    | 216737/371472 [6:33:52<12:42:41,  3.38it/s]
 58%|█████▊    | 216738/371472 [6:33:52<12:26:13,  3.46it/s]
 58%|█████▊    | 216739/371472 [6:33:52<12:17:00,  3.50it/s]
 58%|█████▊    | 216740/371472 [6:33:53<12:23:21,  3.47it/s]
                                                            
{'loss': 2.8687, 'learning_rate': 4.7508565149001274e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216740/371472 [6:33:53<12:23:21,  3.47it/s]
 58%|█████▊    | 216741/371472 [6:33:53<12:32:21,  3.43it/s]
 58%|█████▊    | 216742/371472 [6:33:53<12:55:35,  3.33it/s]
 58%|█████▊    | 216743/371472 [6:33:54<12:55:51,  3.32it/s]
 58%|█████▊    | 216744/371472 [6:33:54<12:42:27,  3.38it/s]
 58%|█████▊    | 216745/371472 [6:33:54<12:55:17,  3.33it/s]
 58%|█████▊    | 216746/371472 [6:33:54<12:55:24,  3.33it/s]
 58%|█████▊    | 216747/371472 [6:33:55<13:08:53,  3.27it/s]
 58%|█████▊    | 216748/371472 [6:33:55<12:47:34,  3.36it/s]
 58%|█████▊    | 216749/371472 [6:33:55<13:11:51,  3.26it/s]
 58%|█████▊    | 216750/371472 [6:33:56<12:38:44,  3.40it/s]
 58%|█████▊    | 216751/371472 [6:33:56<13:10:33,  3.26it/s]
 58%|█████▊    | 216752/371472 [6:33:56<12:36:58,  3.41it/s]
 58%|█████▊    | 216753/371472 [6:33:56<12:29:00,  3.44it/s]
 58%|█████▊    | 216754/371472 [6:33:57<13:02:41,  3.29it/s]
 58%|█████▊    | 216755/371472 [6:33:57<12:48:01,  3.36it/s]
 58%|█████▊    | 216756/371472 [6:33:57<12:41:53,  3.38it/s]
 58%|█████▊    | 216757/371472 [6:33:58<14:53:52,  2.88it/s]
 58%|█████▊    | 216758/371472 [6:33:58<14:54:35,  2.88it/s]
 58%|█████▊    | 216759/371472 [6:33:58<13:54:16,  3.09it/s]
 58%|█████▊    | 216760/371472 [6:33:59<13:18:23,  3.23it/s]
                                                            
{'loss': 2.8141, 'learning_rate': 4.750371695145338e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216760/371472 [6:33:59<13:18:23,  3.23it/s]
 58%|█████▊    | 216761/371472 [6:33:59<14:26:30,  2.98it/s]
 58%|█████▊    | 216762/371472 [6:33:59<14:12:30,  3.02it/s]
 58%|█████▊    | 216763/371472 [6:34:00<17:31:34,  2.45it/s]
 58%|█████▊    | 216764/371472 [6:34:00<15:59:40,  2.69it/s]
 58%|█████▊    | 216765/371472 [6:34:01<15:01:11,  2.86it/s]
 58%|█████▊    | 216766/371472 [6:34:01<13:56:25,  3.08it/s]
 58%|█████▊    | 216767/371472 [6:34:01<13:45:47,  3.12it/s]
 58%|█████▊    | 216768/371472 [6:34:02<13:59:49,  3.07it/s]
 58%|█████▊    | 216769/371472 [6:34:02<13:27:16,  3.19it/s]
 58%|█████▊    | 216770/371472 [6:34:02<13:00:33,  3.30it/s]
 58%|█████▊    | 216771/371472 [6:34:02<13:22:14,  3.21it/s]
 58%|█████▊    | 216772/371472 [6:34:03<13:04:28,  3.29it/s]
 58%|█████▊    | 216773/371472 [6:34:03<12:44:46,  3.37it/s]
 58%|█████▊    | 216774/371472 [6:34:03<12:29:11,  3.44it/s]
 58%|█████▊    | 216775/371472 [6:34:04<12:03:10,  3.57it/s]
 58%|█████▊    | 216776/371472 [6:34:04<12:51:44,  3.34it/s]
 58%|█████▊    | 216777/371472 [6:34:04<12:35:25,  3.41it/s]
 58%|█████▊    | 216778/371472 [6:34:04<12:54:45,  3.33it/s]
 58%|█████▊    | 216779/371472 [6:34:05<13:28:38,  3.19it/s]
 58%|█████▊    | 216780/371472 [6:34:05<13:22:07,  3.21it/s]
                                                            
{'loss': 2.7724, 'learning_rate': 4.7498868753905483e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216780/371472 [6:34:05<13:22:07,  3.21it/s]
 58%|█████▊    | 216781/371472 [6:34:05<13:05:59,  3.28it/s]
 58%|█████▊    | 216782/371472 [6:34:06<13:35:43,  3.16it/s]
 58%|█████▊    | 216783/371472 [6:34:06<13:53:04,  3.09it/s]
 58%|█████▊    | 216784/371472 [6:34:06<13:19:32,  3.22it/s]
 58%|█████▊    | 216785/371472 [6:34:07<13:11:59,  3.26it/s]
 58%|█████▊    | 216786/371472 [6:34:07<12:43:43,  3.38it/s]
 58%|█████▊    | 216787/371472 [6:34:07<13:03:42,  3.29it/s]
 58%|█████▊    | 216788/371472 [6:34:08<13:16:16,  3.24it/s]
 58%|█████▊    | 216789/371472 [6:34:08<12:41:54,  3.38it/s]
 58%|█████▊    | 216790/371472 [6:34:08<12:43:22,  3.38it/s]
 58%|█████▊    | 216791/371472 [6:34:08<12:26:55,  3.45it/s]
 58%|█████▊    | 216792/371472 [6:34:09<13:28:18,  3.19it/s]
 58%|█████▊    | 216793/371472 [6:34:09<13:17:56,  3.23it/s]
 58%|█████▊    | 216794/371472 [6:34:09<13:53:15,  3.09it/s]
 58%|█████▊    | 216795/371472 [6:34:10<13:13:54,  3.25it/s]
 58%|█████▊    | 216796/371472 [6:34:10<13:01:46,  3.30it/s]
 58%|█████▊    | 216797/371472 [6:34:10<12:40:35,  3.39it/s]
 58%|█████▊    | 216798/371472 [6:34:11<12:18:48,  3.49it/s]
 58%|█████▊    | 216799/371472 [6:34:11<12:20:46,  3.48it/s]
 58%|█████▊    | 216800/371472 [6:34:11<12:18:13,  3.49it/s]
                                                            
{'loss': 2.6339, 'learning_rate': 4.74940205563576e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216800/371472 [6:34:11<12:18:13,  3.49it/s]
 58%|█████▊    | 216801/371472 [6:34:11<12:46:35,  3.36it/s]
 58%|█████▊    | 216802/371472 [6:34:12<12:45:36,  3.37it/s]
 58%|█████▊    | 216803/371472 [6:34:12<12:08:35,  3.54it/s]
 58%|█████▊    | 216804/371472 [6:34:12<13:09:19,  3.27it/s]
 58%|█████▊    | 216805/371472 [6:34:13<12:51:23,  3.34it/s]
 58%|█████▊    | 216806/371472 [6:34:13<13:16:33,  3.24it/s]
 58%|█████▊    | 216807/371472 [6:34:13<13:36:02,  3.16it/s]
 58%|█████▊    | 216808/371472 [6:34:14<12:59:32,  3.31it/s]
 58%|█████▊    | 216809/371472 [6:34:14<12:33:48,  3.42it/s]
 58%|█████▊    | 216810/371472 [6:34:14<12:41:04,  3.39it/s]
 58%|█████▊    | 216811/371472 [6:34:14<12:38:17,  3.40it/s]
 58%|█████▊    | 216812/371472 [6:34:15<12:49:43,  3.35it/s]
 58%|█████▊    | 216813/371472 [6:34:15<12:46:10,  3.36it/s]
 58%|█████▊    | 216814/371472 [6:34:15<12:22:28,  3.47it/s]
 58%|█████▊    | 216815/371472 [6:34:16<13:22:55,  3.21it/s]
 58%|█████▊    | 216816/371472 [6:34:16<13:25:26,  3.20it/s]
 58%|█████▊    | 216817/371472 [6:34:16<13:00:56,  3.30it/s]
 58%|█████▊    | 216818/371472 [6:34:17<13:11:12,  3.26it/s]
 58%|█████▊    | 216819/371472 [6:34:17<12:52:45,  3.34it/s]
 58%|█████▊    | 216820/371472 [6:34:17<12:28:59,  3.44it/s]
                                                            
{'loss': 2.7346, 'learning_rate': 4.748917235880971e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216820/371472 [6:34:17<12:28:59,  3.44it/s]
 58%|█████▊    | 216821/371472 [6:34:17<12:28:08,  3.45it/s]
 58%|█████▊    | 216822/371472 [6:34:18<12:16:43,  3.50it/s]
 58%|█████▊    | 216823/371472 [6:34:18<12:09:22,  3.53it/s]
 58%|█████▊    | 216824/371472 [6:34:18<12:33:02,  3.42it/s]
 58%|█████▊    | 216825/371472 [6:34:19<12:00:13,  3.58it/s]
 58%|█████▊    | 216826/371472 [6:34:19<11:44:49,  3.66it/s]
 58%|█████▊    | 216827/371472 [6:34:19<11:50:49,  3.63it/s]
 58%|█████▊    | 216828/371472 [6:34:19<12:16:16,  3.50it/s]
 58%|█████▊    | 216829/371472 [6:34:20<12:39:39,  3.39it/s]
 58%|█████▊    | 216830/371472 [6:34:20<12:28:19,  3.44it/s]
 58%|█████▊    | 216831/371472 [6:34:20<12:38:20,  3.40it/s]
 58%|█████▊    | 216832/371472 [6:34:21<12:20:03,  3.48it/s]
 58%|█████▊    | 216833/371472 [6:34:21<13:10:12,  3.26it/s]
 58%|█████▊    | 216834/371472 [6:34:21<12:35:48,  3.41it/s]
 58%|█████▊    | 216835/371472 [6:34:21<12:37:15,  3.40it/s]
 58%|█████▊    | 216836/371472 [6:34:22<12:29:06,  3.44it/s]
 58%|█████▊    | 216837/371472 [6:34:22<12:47:10,  3.36it/s]
 58%|█████▊    | 216838/371472 [6:34:22<12:51:03,  3.34it/s]
 58%|█████▊    | 216839/371472 [6:34:23<12:49:36,  3.35it/s]
 58%|█████▊    | 216840/371472 [6:34:23<13:04:06,  3.29it/s]
                                                            
{'loss': 2.7309, 'learning_rate': 4.748432416126182e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216840/371472 [6:34:23<13:04:06,  3.29it/s]
 58%|█████▊    | 216841/371472 [6:34:23<13:10:07,  3.26it/s]
 58%|█████▊    | 216842/371472 [6:34:24<12:56:37,  3.32it/s]
 58%|█████▊    | 216843/371472 [6:34:24<13:04:12,  3.29it/s]
 58%|█████▊    | 216844/371472 [6:34:24<13:01:00,  3.30it/s]
 58%|█████▊    | 216845/371472 [6:34:25<13:19:41,  3.22it/s]
 58%|████���▊    | 216846/371472 [6:34:25<12:46:42,  3.36it/s]
 58%|█████▊    | 216847/371472 [6:34:25<13:25:40,  3.20it/s]
 58%|█████▊    | 216848/371472 [6:34:25<13:05:05,  3.28it/s]
 58%|█████▊    | 216849/371472 [6:34:26<12:54:49,  3.33it/s]
 58%|█████▊    | 216850/371472 [6:34:26<12:52:38,  3.34it/s]
 58%|█████▊    | 216851/371472 [6:34:26<12:48:05,  3.36it/s]
 58%|█████▊    | 216852/371472 [6:34:27<12:43:54,  3.37it/s]
 58%|█████▊    | 216853/371472 [6:34:27<12:28:47,  3.44it/s]
 58%|█████▊    | 216854/371472 [6:34:27<12:27:52,  3.45it/s]
 58%|█████▊    | 216855/371472 [6:34:27<12:32:56,  3.42it/s]
 58%|█████▊    | 216856/371472 [6:34:28<12:33:13,  3.42it/s]
 58%|█████▊    | 216857/371472 [6:34:28<12:36:36,  3.41it/s]
 58%|█████▊    | 216858/371472 [6:34:28<12:26:15,  3.45it/s]
 58%|█████▊    | 216859/371472 [6:34:29<12:07:28,  3.54it/s]
 58%|█████▊    | 216860/371472 [6:34:29<12:10:10,  3.53it/s]
                                                            
{'loss': 2.8673, 'learning_rate': 4.747947596371393e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216860/371472 [6:34:29<12:10:10,  3.53it/s]
 58%|█████▊    | 216861/371472 [6:34:29<12:11:40,  3.52it/s]
 58%|█████▊    | 216862/371472 [6:34:30<13:09:27,  3.26it/s]
 58%|█████▊    | 216863/371472 [6:34:30<13:41:55,  3.14it/s]
 58%|█████▊    | 216864/371472 [6:34:30<13:10:18,  3.26it/s]
 58%|█████▊    | 216865/371472 [6:34:30<12:52:43,  3.33it/s]
 58%|█████▊    | 216866/371472 [6:34:31<12:36:47,  3.40it/s]
 58%|█████▊    | 216867/371472 [6:34:31<12:26:04,  3.45it/s]
 58%|█████▊    | 216868/371472 [6:34:31<12:58:02,  3.31it/s]
 58%|█████▊    | 216869/371472 [6:34:32<12:36:59,  3.40it/s]
 58%|█████▊    | 216870/371472 [6:34:32<13:10:45,  3.26it/s]
 58%|█████▊    | 216871/371472 [6:34:32<13:25:12,  3.20it/s]
 58%|█████▊    | 216872/371472 [6:34:33<12:53:05,  3.33it/s]
 58%|█████▊    | 216873/371472 [6:34:33<12:47:14,  3.36it/s]
 58%|█████▊    | 216874/371472 [6:34:33<12:45:31,  3.37it/s]
 58%|█████▊    | 216875/371472 [6:34:34<13:34:24,  3.16it/s]
 58%|█████▊    | 216876/371472 [6:34:34<13:17:09,  3.23it/s]
 58%|█████▊    | 216877/371472 [6:34:34<13:09:17,  3.26it/s]
 58%|█████▊    | 216878/371472 [6:34:34<12:59:04,  3.31it/s]
 58%|█████▊    | 216879/371472 [6:34:35<12:50:02,  3.35it/s]
 58%|█████▊    | 216880/371472 [6:34:35<12:22:24,  3.47it/s]
                                                            
{'loss': 2.6364, 'learning_rate': 4.7474627766166046e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216880/371472 [6:34:35<12:22:24,  3.47it/s]
 58%|█████▊    | 216881/371472 [6:34:35<12:14:06,  3.51it/s]
 58%|█████▊    | 216882/371472 [6:34:36<12:01:30,  3.57it/s]
 58%|█████▊    | 216883/371472 [6:34:36<13:25:00,  3.20it/s]
 58%|█████▊    | 216884/371472 [6:34:36<13:14:36,  3.24it/s]
 58%|█████▊    | 216885/371472 [6:34:36<12:36:27,  3.41it/s]
 58%|█████▊    | 216886/371472 [6:34:37<12:30:33,  3.43it/s]
 58%|█████▊    | 216887/371472 [6:34:37<12:09:25,  3.53it/s]
 58%|█████▊    | 216888/371472 [6:34:37<12:32:16,  3.42it/s]
 58%|█████▊    | 216889/371472 [6:34:38<12:50:12,  3.35it/s]
 58%|█████▊    | 216890/371472 [6:34:38<12:20:39,  3.48it/s]
 58%|█████▊    | 216891/371472 [6:34:38<11:51:41,  3.62it/s]
 58%|█████▊    | 216892/371472 [6:34:38<11:38:23,  3.69it/s]
 58%|█████▊    | 216893/371472 [6:34:39<12:39:51,  3.39it/s]
 58%|█████▊    | 216894/371472 [6:34:39<12:30:18,  3.43it/s]
 58%|█████▊    | 216895/371472 [6:34:39<12:10:34,  3.53it/s]
 58%|█████▊    | 216896/371472 [6:34:40<12:47:54,  3.35it/s]
 58%|█████▊    | 216897/371472 [6:34:40<12:24:29,  3.46it/s]
 58%|█████▊    | 216898/371472 [6:34:40<13:00:06,  3.30it/s]
 58%|█████▊    | 216899/371472 [6:34:41<13:04:27,  3.28it/s]
 58%|█████▊    | 216900/371472 [6:34:41<12:30:41,  3.43it/s]
                                                            
{'loss': 2.8734, 'learning_rate': 4.7469779568618153e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216900/371472 [6:34:41<12:30:41,  3.43it/s]
 58%|█████▊    | 216901/371472 [6:34:41<12:35:29,  3.41it/s]
 58%|█████▊    | 216902/371472 [6:34:41<12:24:35,  3.46it/s]
 58%|█████▊    | 216903/371472 [6:34:42<13:01:04,  3.30it/s]
 58%|█████▊    | 216904/371472 [6:34:42<12:28:09,  3.44it/s]
 58%|█████▊    | 216905/371472 [6:34:42<12:12:11,  3.52it/s]
 58%|█████▊    | 216906/371472 [6:34:43<12:06:42,  3.54it/s]
 58%|█████▊    | 216907/371472 [6:34:43<12:57:49,  3.31it/s]
 58%|█████▊    | 216908/371472 [6:34:43<13:03:50,  3.29it/s]
 58%|█████▊    | 216909/371472 [6:34:43<12:43:27,  3.37it/s]
 58%|█████▊    | 216910/371472 [6:34:44<12:26:59,  3.45it/s]
 58%|█████▊    | 216911/371472 [6:34:44<12:27:22,  3.45it/s]
 58%|█████▊    | 216912/371472 [6:34:44<12:12:29,  3.52it/s]
 58%|█████▊    | 216913/371472 [6:34:45<13:28:43,  3.19it/s]
 58%|█████▊    | 216914/371472 [6:34:45<13:08:13,  3.27it/s]
 58%|█████▊    | 216915/371472 [6:34:45<13:29:07,  3.18it/s]
 58%|█████▊    | 216916/371472 [6:34:46<13:21:37,  3.21it/s]
 58%|█████▊    | 216917/371472 [6:34:46<13:17:40,  3.23it/s]
 58%|█████▊    | 216918/371472 [6:34:46<13:00:01,  3.30it/s]
 58%|█████▊    | 216919/371472 [6:34:47<14:03:13,  3.05it/s]
 58%|█████▊    | 216920/371472 [6:34:47<14:16:31,  3.01it/s]
                                                            
{'loss': 2.6972, 'learning_rate': 4.7464931371070265e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216920/371472 [6:34:47<14:16:31,  3.01it/s]
 58%|█████▊    | 216921/371472 [6:34:47<13:36:19,  3.16it/s]
 58%|█████▊    | 216922/371472 [6:34:48<13:33:58,  3.16it/s]
 58%|█████▊    | 216923/371472 [6:34:48<13:37:49,  3.15it/s]
 58%|█████▊    | 216924/371472 [6:34:48<13:14:48,  3.24it/s]
 58%|█████▊    | 216925/371472 [6:34:48<12:53:22,  3.33it/s]
 58%|█████▊    | 216926/371472 [6:34:49<13:18:02,  3.23it/s]
 58%|█████▊    | 216927/371472 [6:34:49<13:10:03,  3.26it/s]
 58%|█████▊    | 216928/371472 [6:34:49<13:46:26,  3.12it/s]
 58%|█████▊    | 216929/371472 [6:34:50<13:14:36,  3.24it/s]
 58%|█████▊    | 216930/371472 [6:34:50<13:10:21,  3.26it/s]
 58%|█████▊    | 216931/371472 [6:34:50<13:03:26,  3.29it/s]
 58%|█████▊    | 216932/371472 [6:34:51<12:44:41,  3.37it/s]
 58%|█████▊    | 216933/371472 [6:34:51<12:27:00,  3.45it/s]
 58%|█████▊    | 216934/371472 [6:34:51<12:15:27,  3.50it/s]
 58%|█████▊    | 216935/371472 [6:34:51<12:29:52,  3.43it/s]
 58%|█████▊    | 216936/371472 [6:34:52<12:14:10,  3.51it/s]
 58%|█████▊    | 216937/371472 [6:34:52<12:10:40,  3.52it/s]
 58%|█████▊    | 216938/371472 [6:34:52<12:18:35,  3.49it/s]
 58%|█████▊    | 216939/371472 [6:34:53<12:43:25,  3.37it/s]
 58%|█████▊    | 216940/371472 [6:34:53<12:48:02,  3.35it/s]
                                                            
{'loss': 2.8335, 'learning_rate': 4.746008317352238e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216940/371472 [6:34:53<12:48:02,  3.35it/s]
 58%|█████▊    | 216941/371472 [6:34:53<12:54:46,  3.32it/s]
 58%|█████▊    | 216942/371472 [6:34:54<13:15:28,  3.24it/s]
 58%|█████▊    | 216943/371472 [6:34:54<13:41:33,  3.13it/s]
 58%|█████▊    | 216944/371472 [6:34:54<13:32:46,  3.17it/s]
 58%|█████▊    | 216945/371472 [6:34:54<13:16:59,  3.23it/s]
 58%|█████▊    | 216946/371472 [6:34:55<13:17:26,  3.23it/s]
 58%|█████▊    | 216947/371472 [6:34:55<13:04:34,  3.28it/s]
 58%|█████▊    | 216948/371472 [6:34:55<12:26:31,  3.45it/s]
 58%|█████▊    | 216949/371472 [6:34:56<12:41:30,  3.38it/s]
 58%|█████▊    | 216950/371472 [6:34:56<12:35:30,  3.41it/s]
 58%|█████▊    | 216951/371472 [6:34:56<12:17:40,  3.49it/s]
 58%|█████▊    | 216952/371472 [6:34:56<12:24:44,  3.46it/s]
 58%|█████▊    | 216953/371472 [6:34:57<12:33:15,  3.42it/s]
 58%|█████▊    | 216954/371472 [6:34:57<12:30:50,  3.43it/s]
 58%|█████▊    | 216955/371472 [6:34:57<12:19:42,  3.48it/s]
 58%|█████▊    | 216956/371472 [6:34:58<12:42:56,  3.38it/s]
 58%|█████▊    | 216957/371472 [6:34:58<12:25:01,  3.46it/s]
 58%|█████▊    | 216958/371472 [6:34:58<12:37:46,  3.40it/s]
 58%|█████▊    | 216959/371472 [6:34:59<12:52:28,  3.33it/s]
 58%|█████▊    | 216960/371472 [6:34:59<12:52:20,  3.33it/s]
                                                            
{'loss': 2.702, 'learning_rate': 4.745523497597449e-07, 'epoch': 9.34}
+
 58%|█████▊    | 216960/371472 [6:34:59<12:52:20,  3.33it/s]
 58%|█████▊    | 216961/371472 [6:34:59<12:46:49,  3.36it/s]
 58%|█████▊    | 216962/371472 [6:34:59<12:31:38,  3.43it/s]
 58%|█████▊    | 216963/371472 [6:35:00<13:15:00,  3.24it/s]
 58%|█████▊    | 216964/371472 [6:35:00<13:15:48,  3.24it/s]
 58%|█████▊    | 216965/371472 [6:35:00<12:49:23,  3.35it/s]
 58%|█████▊    | 216966/371472 [6:35:01<12:30:21,  3.43it/s]
 58%|█████▊    | 216967/371472 [6:35:01<12:08:56,  3.53it/s]
 58%|█████▊    | 216968/371472 [6:35:01<12:09:14,  3.53it/s]
 58%|█████▊    | 216969/371472 [6:35:01<12:00:30,  3.57it/s]
 58%|█████▊    | 216970/371472 [6:35:02<11:59:00,  3.58it/s]
 58%|█████▊    | 216971/371472 [6:35:02<12:15:45,  3.50it/s]
 58%|█████▊    | 216972/371472 [6:35:02<12:30:04,  3.43it/s]
 58%|█████▊    | 216973/371472 [6:35:03<12:35:01,  3.41it/s]
 58%|█████▊    | 216974/371472 [6:35:03<12:19:24,  3.48it/s]
 58%|█████▊    | 216975/371472 [6:35:03<12:30:47,  3.43it/s]
 58%|█████▊    | 216976/371472 [6:35:03<12:12:19,  3.52it/s]
 58%|█████▊    | 216977/371472 [6:35:04<12:19:26,  3.48it/s]
 58%|█████▊    | 216978/371472 [6:35:04<12:09:16,  3.53it/s]
 58%|█████▊    | 216979/371472 [6:35:04<11:56:24,  3.59it/s]
 58%|█████▊    | 216980/371472 [6:35:05<12:31:57,  3.42it/s]
                                                            
{'loss': 2.9223, 'learning_rate': 4.745038677842659e-07, 'epoch': 9.35}
+
 58%|█████▊    | 216980/371472 [6:35:05<12:31:57,  3.42it/s]
 58%|█████▊    | 216981/371472 [6:35:05<12:25:31,  3.45it/s]
 58%|█████▊    | 216982/371472 [6:35:05<12:12:10,  3.52it/s]
 58%|█████▊    | 216983/371472 [6:35:06<13:14:35,  3.24it/s]
 58%|█████▊    | 216984/371472 [6:35:06<13:17:48,  3.23it/s]
 58%|█████▊    | 216985/371472 [6:35:06<12:40:34,  3.39it/s]
 58%|█████▊    | 216986/371472 [6:35:06<13:21:07,  3.21it/s]
 58%|█████▊    | 216987/371472 [6:35:07<12:50:11,  3.34it/s]
 58%|█████▊    | 216988/371472 [6:35:07<12:42:07,  3.38it/s]
 58%|█████▊    | 216989/371472 [6:35:07<12:17:39,  3.49it/s]
 58%|█████▊    | 216990/371472 [6:35:08<12:53:24,  3.33it/s]
 58%|█████▊    | 216991/371472 [6:35:08<12:39:29,  3.39it/s]
 58%|█████▊    | 216992/371472 [6:35:08<13:02:25,  3.29it/s]
 58%|█████▊    | 216993/371472 [6:35:09<12:59:35,  3.30it/s]
 58%|█████▊    | 216994/371472 [6:35:09<12:49:15,  3.35it/s]
 58%|█████▊    | 216995/371472 [6:35:09<12:29:27,  3.44it/s]
 58%|█████▊    | 216996/371472 [6:35:09<12:17:20,  3.49it/s]
 58%|█████▊    | 216997/371472 [6:35:10<12:46:46,  3.36it/s]
 58%|█████▊    | 216998/371472 [6:35:10<13:12:57,  3.25it/s]
 58%|█████▊    | 216999/371472 [6:35:10<12:36:06,  3.41it/s]
 58%|█████▊    | 217000/371472 [6:35:11<12:16:14,  3.50it/s]
                                                            
{'loss': 2.8573, 'learning_rate': 4.744553858087871e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217000/371472 [6:35:11<12:16:14,  3.50it/s]
 58%|█████▊    | 217001/371472 [6:35:11<12:00:54,  3.57it/s]
 58%|█████▊    | 217002/371472 [6:35:11<11:40:19,  3.68it/s]
 58%|█████▊    | 217003/371472 [6:35:11<11:21:34,  3.78it/s]
 58%|█████▊    | 217004/371472 [6:35:12<11:41:38,  3.67it/s]
 58%|█████▊    | 217005/371472 [6:35:12<12:20:05,  3.48it/s]
 58%|█████▊    | 217006/371472 [6:35:12<12:18:38,  3.49it/s]
 58%|█████▊    | 217007/371472 [6:35:13<13:07:37,  3.27it/s]
 58%|█████▊    | 217008/371472 [6:35:13<13:07:12,  3.27it/s]
 58%|█████▊    | 217009/371472 [6:35:13<13:24:52,  3.20it/s]
 58%|█████▊    | 217010/371472 [6:35:13<12:51:39,  3.34it/s]
 58%|█████▊    | 217011/371472 [6:35:14<12:19:41,  3.48it/s]
 58%|█████▊    | 217012/371472 [6:35:14<12:17:52,  3.49it/s]
 58%|█████▊    | 217013/371472 [6:35:14<12:31:12,  3.43it/s]
 58%|█████▊    | 217014/371472 [6:35:15<12:21:28,  3.47it/s]
 58%|█████▊    | 217015/371472 [6:35:15<12:23:02,  3.46it/s]
 58%|█████▊    | 217016/371472 [6:35:15<16:17:37,  2.63it/s]
 58%|█████▊    | 217017/371472 [6:35:16<15:44:45,  2.72it/s]
 58%|█████▊    | 217018/371472 [6:35:16<15:47:02,  2.72it/s]
 58%|█████▊    | 217019/371472 [6:35:17<15:32:43,  2.76it/s]
 58%|█████▊    | 217020/371472 [6:35:17<15:04:02,  2.85it/s]
                                                            
{'loss': 2.8069, 'learning_rate': 4.7440690383330817e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217020/371472 [6:35:17<15:04:02,  2.85it/s]
 58%|█████▊    | 217021/371472 [6:35:17<14:08:59,  3.03it/s]
 58%|█████▊    | 217022/371472 [6:35:17<13:45:21,  3.12it/s]
 58%|█████▊    | 217023/371472 [6:35:18<13:18:45,  3.22it/s]
 58%|█████▊    | 217024/371472 [6:35:18<12:53:05,  3.33it/s]
 58%|█████▊    | 217025/371472 [6:35:18<12:48:12,  3.35it/s]
 58%|█████▊    | 217026/371472 [6:35:19<13:31:16,  3.17it/s]
 58%|█████▊    | 217027/371472 [6:35:19<12:58:21,  3.31it/s]
 58%|█████▊    | 217028/371472 [6:35:19<13:03:04,  3.29it/s]
 58%|█████▊    | 217029/371472 [6:35:20<12:44:05,  3.37it/s]
 58%|█████▊    | 217030/371472 [6:35:20<13:07:38,  3.27it/s]
 58%|█████▊    | 217031/371472 [6:35:20<14:26:43,  2.97it/s]
 58%|█████▊    | 217032/371472 [6:35:21<13:47:28,  3.11it/s]
 58%|█████▊    | 217033/371472 [6:35:21<13:02:40,  3.29it/s]
 58%|█████▊    | 217034/371472 [6:35:21<12:46:18,  3.36it/s]
 58%|█████▊    | 217035/371472 [6:35:21<12:25:52,  3.45it/s]
 58%|█████▊    | 217036/371472 [6:35:22<12:09:09,  3.53it/s]
 58%|█████▊    | 217037/371472 [6:35:22<12:03:43,  3.56it/s]
 58%|█████▊    | 217038/371472 [6:35:22<12:29:07,  3.44it/s]
 58%|█████▊    | 217039/371472 [6:35:22<12:20:39,  3.48it/s]
 58%|█████▊    | 217040/371472 [6:35:23<12:18:11,  3.49it/s]
                                                            
{'loss': 2.7429, 'learning_rate': 4.743584218578293e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217040/371472 [6:35:23<12:18:11,  3.49it/s]
 58%|█████▊    | 217041/371472 [6:35:23<12:02:36,  3.56it/s]
 58%|█████▊    | 217042/371472 [6:35:23<12:09:33,  3.53it/s]
 58%|█████▊    | 217043/371472 [6:35:24<11:47:37,  3.64it/s]
 58%|█████▊    | 217044/371472 [6:35:24<11:56:14,  3.59it/s]
 58%|█████▊    | 217045/371472 [6:35:24<12:00:48,  3.57it/s]
 58%|█████▊    | 217046/371472 [6:35:24<11:51:48,  3.62it/s]
 58%|█████▊    | 217047/371472 [6:35:25<12:05:43,  3.55it/s]
 58%|█████▊    | 217048/371472 [6:35:25<12:22:24,  3.47it/s]
 58%|█████▊    | 217049/371472 [6:35:25<12:23:19,  3.46it/s]
 58%|█████▊    | 217050/371472 [6:35:26<12:34:31,  3.41it/s]
 58%|█████▊    | 217051/371472 [6:35:26<12:31:31,  3.42it/s]
 58%|█████▊    | 217052/371472 [6:35:26<12:26:42,  3.45it/s]
 58%|█████▊    | 217053/371472 [6:35:26<12:28:17,  3.44it/s]
 58%|█████▊    | 217054/371472 [6:35:27<12:23:21,  3.46it/s]
 58%|█████▊    | 217055/371472 [6:35:27<12:23:37,  3.46it/s]
 58%|█████▊    | 217056/371472 [6:35:27<12:22:23,  3.47it/s]
 58%|█████▊    | 217057/371472 [6:35:28<12:20:41,  3.47it/s]
 58%|█████▊    | 217058/371472 [6:35:28<12:19:06,  3.48it/s]
 58%|█████▊    | 217059/371472 [6:35:28<12:28:30,  3.44it/s]
 58%|█████▊    | 217060/371472 [6:35:29<12:31:00,  3.43it/s]
                                                            
{'loss': 2.7815, 'learning_rate': 4.7430993988235036e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217060/371472 [6:35:29<12:31:00,  3.43it/s]
 58%|█████▊    | 217061/371472 [6:35:29<13:58:47,  3.07it/s]
 58%|█████▊    | 217062/371472 [6:35:29<13:55:57,  3.08it/s]
 58%|█████▊    | 217063/371472 [6:35:30<13:16:14,  3.23it/s]
 58%|█████▊    | 217064/371472 [6:35:30<14:01:34,  3.06it/s]
 58%|█████▊    | 217065/371472 [6:35:30<13:36:52,  3.15it/s]
 58%|█████▊    | 217066/371472 [6:35:30<13:05:33,  3.28it/s]
 58%|█████▊    | 217067/371472 [6:35:31<12:51:56,  3.33it/s]
 58%|█████▊    | 217068/371472 [6:35:31<12:47:26,  3.35it/s]
 58%|█████▊    | 217069/371472 [6:35:31<12:33:16,  3.42it/s]
 58%|█████▊    | 217070/371472 [6:35:32<12:43:14,  3.37it/s]
 58%|█████▊    | 217071/371472 [6:35:32<12:29:55,  3.43it/s]
 58%|█████▊    | 217072/371472 [6:35:32<12:21:12,  3.47it/s]
 58%|█████▊    | 217073/371472 [6:35:32<12:08:47,  3.53it/s]
 58%|█████▊    | 217074/371472 [6:35:33<12:59:34,  3.30it/s]
 58%|█████▊    | 217075/371472 [6:35:33<12:37:11,  3.40it/s]
 58%|█████▊    | 217076/371472 [6:35:33<13:02:58,  3.29it/s]
 58%|█████▊    | 217077/371472 [6:35:34<13:37:16,  3.15it/s]
 58%|█████▊    | 217078/371472 [6:35:34<13:18:50,  3.22it/s]
 58%|█████▊    | 217079/371472 [6:35:34<13:06:52,  3.27it/s]
 58%|█████▊    | 217080/371472 [6:35:35<12:56:15,  3.31it/s]
                                                            
{'loss': 2.6812, 'learning_rate': 4.7426145790687154e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217080/371472 [6:35:35<12:56:15,  3.31it/s]
 58%|█████▊    | 217081/371472 [6:35:35<13:22:27,  3.21it/s]
 58%|█████▊    | 217082/371472 [6:35:35<14:08:21,  3.03it/s]
 58%|█████▊    | 217083/371472 [6:35:36<13:31:34,  3.17it/s]
 58%|█████▊    | 217084/371472 [6:35:36<12:58:31,  3.31it/s]
 58%|█████▊    | 217085/371472 [6:35:36<12:51:23,  3.34it/s]
 58%|█████▊    | 217086/371472 [6:35:36<12:34:36,  3.41it/s]
 58%|█████▊    | 217087/371472 [6:35:37<12:12:03,  3.51it/s]
 58%|█████▊    | 217088/371472 [6:35:37<12:07:35,  3.54it/s]
 58%|█████▊    | 217089/371472 [6:35:37<13:25:16,  3.20it/s]
 58%|█████▊    | 217090/371472 [6:35:38<12:46:04,  3.36it/s]
 58%|█████▊    | 217091/371472 [6:35:38<12:26:52,  3.45it/s]
 58%|█████▊    | 217092/371472 [6:35:38<13:08:27,  3.26it/s]
 58%|█████▊    | 217093/371472 [6:35:39<12:45:59,  3.36it/s]
 58%|█████▊    | 217094/371472 [6:35:39<12:30:22,  3.43it/s]
 58%|█████▊    | 217095/371472 [6:35:39<12:45:11,  3.36it/s]
 58%|█████▊    | 217096/371472 [6:35:39<12:36:51,  3.40it/s]
 58%|█████▊    | 217097/371472 [6:35:40<12:25:19,  3.45it/s]
 58%|█████▊    | 217098/371472 [6:35:40<13:07:40,  3.27it/s]
 58%|█████▊    | 217099/371472 [6:35:40<13:13:33,  3.24it/s]
 58%|█████▊    | 217100/371472 [6:35:41<13:03:47,  3.28it/s]
                                                            
{'loss': 2.6339, 'learning_rate': 4.7421297593139256e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217100/371472 [6:35:41<13:03:47,  3.28it/s]
 58%|█████▊    | 217101/371472 [6:35:41<12:48:14,  3.35it/s]
 58%|█████▊    | 217102/371472 [6:35:41<14:09:26,  3.03it/s]
 58%|█████▊    | 217103/371472 [6:35:42<13:40:59,  3.13it/s]
 58%|█████▊    | 217104/371472 [6:35:42<13:03:39,  3.28it/s]
 58%|█████▊    | 217105/371472 [6:35:42<12:26:35,  3.45it/s]
 58%|█████▊    | 217106/371472 [6:35:42<12:51:08,  3.34it/s]
 58%|█████▊    | 217107/371472 [6:35:43<12:47:15,  3.35it/s]
 58%|█████▊    | 217108/371472 [6:35:43<12:29:35,  3.43it/s]
 58%|█████▊    | 217109/371472 [6:35:43<12:56:47,  3.31it/s]
 58%|█████▊    | 217110/371472 [6:35:44<12:38:24,  3.39it/s]
 58%|█████▊    | 217111/371472 [6:35:44<13:21:32,  3.21it/s]
 58%|█████▊    | 217112/371472 [6:35:44<13:21:18,  3.21it/s]
 58%|█████▊    | 217113/371472 [6:35:45<13:09:36,  3.26it/s]
 58%|█████▊    | 217114/371472 [6:35:45<12:58:00,  3.31it/s]
 58%|█████▊    | 217115/371472 [6:35:45<12:44:43,  3.36it/s]
 58%|█████▊    | 217116/371472 [6:35:46<12:45:56,  3.36it/s]
 58%|█████▊    | 217117/371472 [6:35:46<12:50:55,  3.34it/s]
 58%|█████▊    | 217118/371472 [6:35:46<12:33:02,  3.42it/s]
 58%|█████▊    | 217119/371472 [6:35:46<11:59:43,  3.57it/s]
 58%|█████▊    | 217120/371472 [6:35:47<11:38:25,  3.68it/s]
                                                            
{'loss': 2.7107, 'learning_rate': 4.7416449395591374e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217120/371472 [6:35:47<11:38:25,  3.68it/s]
 58%|█████▊    | 217121/371472 [6:35:47<11:35:09,  3.70it/s]
 58%|█████▊    | 217122/371472 [6:35:47<11:53:56,  3.60it/s]
 58%|█████▊    | 217123/371472 [6:35:47<12:07:12,  3.54it/s]
 58%|█████▊    | 217124/371472 [6:35:48<12:00:20,  3.57it/s]
 58%|█████▊    | 217125/371472 [6:35:48<12:17:04,  3.49it/s]
 58%|█████▊    | 217126/371472 [6:35:48<12:10:05,  3.52it/s]
 58%|█████▊    | 217127/371472 [6:35:49<12:26:29,  3.45it/s]
 58%|█████▊    | 217128/371472 [6:35:49<11:54:48,  3.60it/s]
 58%|█████▊    | 217129/371472 [6:35:49<12:15:02,  3.50it/s]
 58%|█████▊    | 217130/371472 [6:35:49<12:22:26,  3.46it/s]
 58%|█████▊    | 217131/371472 [6:35:50<12:03:16,  3.56it/s]
 58%|█████▊    | 217132/371472 [6:35:50<12:40:32,  3.38it/s]
 58%|█████▊    | 217133/371472 [6:35:50<12:06:59,  3.54it/s]
 58%|█████▊    | 217134/371472 [6:35:51<12:22:23,  3.46it/s]
 58%|█████▊    | 217135/371472 [6:35:51<12:27:04,  3.44it/s]
 58%|█████▊    | 217136/371472 [6:35:51<12:25:29,  3.45it/s]
 58%|█████▊    | 217137/371472 [6:35:51<12:00:33,  3.57it/s]
 58%|█████▊    | 217138/371472 [6:35:52<11:57:00,  3.59it/s]
 58%|█████▊    | 217139/371472 [6:35:52<12:13:20,  3.51it/s]
 58%|█████▊    | 217140/371472 [6:35:52<12:24:21,  3.46it/s]
                                                            
{'loss': 2.7021, 'learning_rate': 4.741160119804348e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217140/371472 [6:35:52<12:24:21,  3.46it/s]
 58%|█████▊    | 217141/371472 [6:35:53<12:45:01,  3.36it/s]
 58%|█████▊    | 217142/371472 [6:35:53<12:24:29,  3.45it/s]
 58%|█████▊    | 217143/371472 [6:35:53<12:39:16,  3.39it/s]
 58%|█████▊    | 217144/371472 [6:35:53<12:06:43,  3.54it/s]
 58%|█████▊    | 217145/371472 [6:35:54<12:14:39,  3.50it/s]
 58%|█████▊    | 217146/371472 [6:35:54<11:58:18,  3.58it/s]
 58%|█████▊    | 217147/371472 [6:35:54<12:10:40,  3.52it/s]
 58%|█████▊    | 217148/371472 [6:35:55<11:58:18,  3.58it/s]
 58%|█████▊    | 217149/371472 [6:35:55<11:55:10,  3.60it/s]
 58%|█████▊    | 217150/371472 [6:35:55<12:35:08,  3.41it/s]
 58%|█████▊    | 217151/371472 [6:35:55<12:28:11,  3.44it/s]
 58%|█████▊    | 217152/371472 [6:35:56<12:07:44,  3.53it/s]
 58%|█████▊    | 217153/371472 [6:35:56<11:56:34,  3.59it/s]
 58%|��████▊    | 217154/371472 [6:35:56<11:44:51,  3.65it/s]
 58%|█████▊    | 217155/371472 [6:35:57<12:43:38,  3.37it/s]
 58%|█████▊    | 217156/371472 [6:35:57<12:51:29,  3.33it/s]
 58%|█████▊    | 217157/371472 [6:35:57<12:42:07,  3.37it/s]
 58%|█████▊    | 217158/371472 [6:35:58<13:28:13,  3.18it/s]
 58%|█████▊    | 217159/371472 [6:35:58<13:25:32,  3.19it/s]
 58%|█████▊    | 217160/371472 [6:35:58<12:39:59,  3.38it/s]
                                                            
{'loss': 2.8311, 'learning_rate': 4.7406753000495593e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217160/371472 [6:35:58<12:39:59,  3.38it/s]
 58%|█████▊    | 217161/371472 [6:35:58<13:13:39,  3.24it/s]
 58%|█████▊    | 217162/371472 [6:35:59<12:40:54,  3.38it/s]
 58%|█████▊    | 217163/371472 [6:35:59<12:23:50,  3.46it/s]
 58%|█████▊    | 217164/371472 [6:35:59<12:20:35,  3.47it/s]
 58%|█████▊    | 217165/371472 [6:36:00<12:08:48,  3.53it/s]
 58%|█████▊    | 217166/371472 [6:36:00<12:40:17,  3.38it/s]
 58%|█████▊    | 217167/371472 [6:36:00<12:53:43,  3.32it/s]
 58%|█████▊    | 217168/371472 [6:36:01<12:55:24,  3.32it/s]
 58%|█████▊    | 217169/371472 [6:36:01<12:36:30,  3.40it/s]
 58%|█████▊    | 217170/371472 [6:36:01<12:14:14,  3.50it/s]
 58%|█████▊    | 217171/371472 [6:36:01<12:03:50,  3.55it/s]
 58%|█████▊    | 217172/371472 [6:36:02<12:14:04,  3.50it/s]
 58%|█████▊    | 217173/371472 [6:36:02<12:39:28,  3.39it/s]
 58%|█████▊    | 217174/371472 [6:36:02<12:57:04,  3.31it/s]
 58%|█████▊    | 217175/371472 [6:36:03<13:26:03,  3.19it/s]
 58%|█████▊    | 217176/371472 [6:36:03<13:11:45,  3.25it/s]
 58%|█████▊    | 217177/371472 [6:36:03<13:08:36,  3.26it/s]
 58%|█████▊    | 217178/371472 [6:36:04<14:04:41,  3.04it/s]
 58%|█████▊    | 217179/371472 [6:36:04<13:18:25,  3.22it/s]
 58%|█████▊    | 217180/371472 [6:36:04<13:20:48,  3.21it/s]
                                                            
{'loss': 2.6569, 'learning_rate': 4.74019048029477e-07, 'epoch': 9.35}
+
 58%|█████▊    | 217180/371472 [6:36:04<13:20:48,  3.21it/s]
 58%|█████▊    | 217181/371472 [6:36:04<13:11:55,  3.25it/s]
 58%|█████▊    | 217182/371472 [6:36:05<13:03:33,  3.28it/s]
 58%|█████▊    | 217183/371472 [6:36:05<12:38:38,  3.39it/s]
 58%|█████▊    | 217184/371472 [6:36:05<14:01:54,  3.05it/s]
 58%|█████▊    | 217185/371472 [6:36:06<13:15:21,  3.23it/s]
 58%|█████▊    | 217186/371472 [6:36:06<13:04:32,  3.28it/s]
 58%|█████▊    | 217187/371472 [6:36:06<13:08:31,  3.26it/s]
 58%|█████▊    | 217188/371472 [6:36:07<13:28:31,  3.18it/s]
 58%|█████▊    | 217189/371472 [6:36:07<13:06:26,  3.27it/s]
 58%|█████▊    | 217190/371472 [6:36:07<12:59:52,  3.30it/s]
 58%|█████▊    | 217191/371472 [6:36:08<13:15:13,  3.23it/s]
 58%|█████▊    | 217192/371472 [6:36:08<13:34:45,  3.16it/s]
 58%|█████▊    | 217193/371472 [6:36:08<12:57:01,  3.31it/s]
 58%|█████▊    | 217194/371472 [6:36:08<12:49:06,  3.34it/s]
 58%|█████▊    | 217195/371472 [6:36:09<12:45:54,  3.36it/s]
 58%|█████▊    | 217196/371472 [6:36:09<13:11:59,  3.25it/s]
 58%|█████▊    | 217197/371472 [6:36:09<12:45:00,  3.36it/s]
 58%|█████▊    | 217198/371472 [6:36:10<12:38:46,  3.39it/s]
 58%|█████▊    | 217199/371472 [6:36:10<12:23:33,  3.46it/s]
 58%|█████▊    | 217200/371472 [6:36:10<12:15:31,  3.50it/s]
                                                            
{'loss': 2.7586, 'learning_rate': 4.739705660539982e-07, 'epoch': 9.36}
+
 58%|█████▊    | 217200/371472 [6:36:10<12:15:31,  3.50it/s]
 58%|█████▊    | 217201/371472 [6:36:11<12:49:07,  3.34it/s]
 58%|█████▊    | 217202/371472 [6:36:11<12:23:09,  3.46it/s]
 58%|█████▊    | 217203/371472 [6:36:11<12:16:17,  3.49it/s]
 58%|█████▊    | 217204/371472 [6:36:11<13:02:19,  3.29it/s]
 58%|█████▊    | 217205/371472 [6:36:12<12:51:24,  3.33it/s]
 58%|█████▊    | 217206/371472 [6:36:12<12:50:09,  3.34it/s]
 58%|█████▊    | 217207/371472 [6:36:12<12:22:09,  3.46it/s]
 58%|█████▊    | 217208/371472 [6:36:13<11:56:56,  3.59it/s]
 58%|█████▊    | 217209/371472 [6:36:13<12:16:28,  3.49it/s]
 58%|█████▊    | 217210/371472 [6:36:13<12:09:28,  3.52it/s]
 58%|█████▊    | 217211/371472 [6:36:13<12:37:04,  3.40it/s]
 58%|█████▊    | 217212/371472 [6:36:14<12:41:27,  3.38it/s]
 58%|█████▊    | 217213/371472 [6:36:14<12:30:34,  3.43it/s]
 58%|█████▊    | 217214/371472 [6:36:14<12:23:42,  3.46it/s]
 58%|█████▊    | 217215/371472 [6:36:15<12:26:03,  3.45it/s]
 58%|█████▊    | 217216/371472 [6:36:15<12:07:06,  3.54it/s]
 58%|█████▊    | 217217/371472 [6:36:15<12:18:27,  3.48it/s]
 58%|█████▊    | 217218/371472 [6:36:15<12:37:50,  3.39it/s]
 58%|█████▊    | 217219/371472 [6:36:16<12:21:39,  3.47it/s]
 58%|█████▊    | 217220/371472 [6:36:16<12:13:42,  3.50it/s]
                                                            
{'loss': 2.8908, 'learning_rate': 4.739220840785192e-07, 'epoch': 9.36}
+
 58%|█████▊    | 217220/371472 [6:36:16<12:13:42,  3.50it/s]
 58%|█████▊    | 217221/371472 [6:36:16<12:01:31,  3.56it/s]
 58%|█████▊    | 217222/371472 [6:36:17<11:55:26,  3.59it/s]
 58%|█████▊    | 217223/371472 [6:36:17<11:50:44,  3.62it/s]
 58%|█████▊    | 217224/371472 [6:36:17<11:53:02,  3.61it/s]
 58%|█████▊    | 217225/371472 [6:36:17<11:58:58,  3.58it/s]
 58%|█████▊    | 217226/371472 [6:36:18<12:07:47,  3.53it/s]
 58%|█████▊    | 217227/371472 [6:36:18<12:09:04,  3.53it/s]
 58%|█████▊    | 217228/371472 [6:36:18<12:01:07,  3.56it/s]
 58%|█████▊    | 217229/371472 [6:36:19<12:24:24,  3.45it/s]
 58%|█████▊    | 217230/371472 [6:36:19<12:30:09,  3.43it/s]
 58%|█████▊    | 217231/371472 [6:36:19<11:58:22,  3.58it/s]
 58%|█████▊    | 217232/371472 [6:36:19<12:21:29,  3.47it/s]
 58%|█████▊    | 217233/371472 [6:36:20<12:49:47,  3.34it/s]
 58%|█████▊    | 217234/371472 [6:36:20<12:58:34,  3.30it/s]
 58%|█████▊    | 217235/371472 [6:36:20<12:36:57,  3.40it/s]
 58%|█████▊    | 217236/371472 [6:36:21<12:34:21,  3.41it/s]
 58%|█████▊    | 217237/371472 [6:36:21<13:05:52,  3.27it/s]
 58%|█████▊    | 217238/371472 [6:36:21<12:34:20,  3.41it/s]
 58%|█████▊    | 217239/371472 [6:36:22<13:20:06,  3.21it/s]
 58%|█████▊    | 217240/371472 [6:36:22<13:06:01,  3.27it/s]
                                                            
{'loss': 2.7593, 'learning_rate': 4.738736021030404e-07, 'epoch': 9.36}
+
 58%|█████▊    | 217240/371472 [6:36:22<13:06:01,  3.27it/s]
 58%|█████▊    | 217241/371472 [6:36:22<12:31:54,  3.42it/s]
 58%|█████▊    | 217242/371472 [6:36:22<12:17:40,  3.48it/s]
 58%|█████▊    | 217243/371472 [6:36:23<12:34:45,  3.41it/s]
 58%|█████▊    | 217244/371472 [6:36:23<12:22:53,  3.46it/s]
 58%|█████▊    | 217245/371472 [6:36:23<12:04:20,  3.55it/s]
 58%|█████▊    | 217246/371472 [6:36:24<13:11:17,  3.25it/s]
 58%|█████▊    | 217247/371472 [6:36:24<13:54:31,  3.08it/s]
 58%|█████▊    | 217248/371472 [6:36:24<13:43:51,  3.12it/s]
 58%|█████▊    | 217249/371472 [6:36:25<13:18:00,  3.22it/s]
 58%|█████▊    | 217250/371472 [6:36:25<12:54:04,  3.32it/s]
 58%|█████▊    | 217251/371472 [6:36:25<13:34:51,  3.15it/s]
 58%|█████▊    | 217252/371472 [6:36:25<13:03:34,  3.28it/s]
 58%|█████▊    | 217253/371472 [6:36:26<12:59:37,  3.30it/s]
 58%|█████▊    | 217254/371472 [6:36:26<12:49:04,  3.34it/s]
 58%|█████▊    | 217255/371472 [6:36:26<12:57:20,  3.31it/s]
 58%|█████▊    | 217256/371472 [6:36:27<13:10:57,  3.25it/s]
 58%|█████▊    | 217257/371472 [6:36:27<13:21:59,  3.20it/s]
 58%|█████▊    | 217258/371472 [6:36:27<13:53:00,  3.09it/s]
 58%|█████▊    | 217259/371472 [6:36:28<14:05:39,  3.04it/s]
 58%|█████▊    | 217260/371472 [6:36:28<14:04:44,  3.04it/s]
                                                            
{'loss': 2.7375, 'learning_rate': 4.7382512012756145e-07, 'epoch': 9.36}
+
 58%|█████▊    | 217260/371472 [6:36:28<14:04:44,  3.04it/s]
 58%|█████▊    | 217261/371472 [6:36:28<13:42:44,  3.12it/s]
 58%|█████▊    | 217262/371472 [6:36:29<13:08:33,  3.26it/s]
 58%|█████▊    | 217263/371472 [6:36:29<12:58:53,  3.30it/s]
 58%|█████▊    | 217264/371472 [6:36:29<13:40:16,  3.13it/s]
 58%|█████▊    | 217265/371472 [6:36:30<13:17:17,  3.22it/s]
 58%|█████▊    | 217266/371472 [6:36:30<13:08:36,  3.26it/s]
 58%|█████▊    | 217267/371472 [6:36:30<12:48:55,  3.34it/s]
 58%|█████▊    | 217268/371472 [6:36:30<12:32:08,  3.42it/s]
 58%|█████▊    | 217269/371472 [6:36:31<12:10:05,  3.52it/s]
 58%|█████▊    | 217270/371472 [6:36:31<12:56:26,  3.31it/s]
 58%|█████▊    | 217271/371472 [6:36:31<13:00:15,  3.29it/s]
 58%|█████▊    | 217272/371472 [6:36:32<12:37:43,  3.39it/s]
 58%|█████▊    | 217273/371472 [6:36:32<12:43:36,  3.37it/s]
 58%|█████▊    | 217274/371472 [6:36:32<12:21:38,  3.47it/s]
 58%|█████▊    | 217275/371472 [6:36:32<12:24:28,  3.45it/s]
 58%|█████▊    | 217276/371472 [6:36:33<12:21:07,  3.47it/s]
 58%|████��▊    | 217277/371472 [6:36:33<12:27:59,  3.44it/s]
 58%|█████▊    | 217278/371472 [6:36:33<12:39:09,  3.39it/s]
 58%|█████▊    | 217279/371472 [6:36:34<12:18:06,  3.48it/s]
 58%|█████▊    | 217280/371472 [6:36:34<12:21:25,  3.47it/s]
                                                            
{'loss': 2.891, 'learning_rate': 4.737766381520826e-07, 'epoch': 9.36}
+
 58%|█████▊    | 217280/371472 [6:36:34<12:21:25,  3.47it/s]
 58%|█████▊    | 217281/371472 [6:36:34<12:28:07,  3.44it/s]
 58%|█████▊    | 217282/371472 [6:36:35<13:37:48,  3.14it/s]
 58%|█████▊    | 217283/371472 [6:36:35<13:55:06,  3.08it/s]
 58%|█████▊    | 217284/371472 [6:36:35<13:27:34,  3.18it/s]
 58%|█████▊    | 217285/371472 [6:36:35<12:58:16,  3.30it/s]
 58%|█████▊    | 217286/371472 [6:36:36<12:51:33,  3.33it/s]
 58%|█████▊    | 217287/371472 [6:36:36<13:00:28,  3.29it/s]
 58%|█████▊    | 217288/371472 [6:36:36<12:41:19,  3.38it/s]
 58%|█████▊    | 217289/371472 [6:36:37<12:29:38,  3.43it/s]
 58%|█████▊    | 217290/371472 [6:36:37<12:24:28,  3.45it/s]
 58%|█████▊    | 217291/371472 [6:36:37<12:41:56,  3.37it/s]
 58%|█████▊    | 217292/371472 [6:36:38<13:28:31,  3.18it/s]
 58%|█████▊    | 217293/371472 [6:36:38<12:55:08,  3.32it/s]
 58%|█████▊    | 217294/371472 [6:36:38<12:36:20,  3.40it/s]
 58%|█████▊    | 217295/371472 [6:36:38<12:13:27,  3.50it/s]
 58%|█████▊    | 217296/371472 [6:36:39<12:36:32,  3.40it/s]
 58%|█████▊    | 217297/371472 [6:36:39<12:08:10,  3.53it/s]
 58%|█████▊    | 217298/371472 [6:36:39<12:34:03,  3.41it/s]
 58%|█████▊    | 217299/371472 [6:36:40<12:18:08,  3.48it/s]
 58%|█████▊    | 217300/371472 [6:36:40<12:09:37,  3.52it/s]
                                                            
{'loss': 2.7291, 'learning_rate': 4.7372815617660365e-07, 'epoch': 9.36}
+
 58%|█████▊    | 217300/371472 [6:36:40<12:09:37,  3.52it/s]
 58%|█████▊    | 217301/371472 [6:36:40<11:54:46,  3.59it/s]
 58%|█████▊    | 217302/371472 [6:36:40<12:06:07,  3.54it/s]
 58%|█████▊    | 217303/371472 [6:36:41<12:30:31,  3.42it/s]
 58%|█████▊    | 217304/371472 [6:36:41<12:40:19,  3.38it/s]
 58%|█████▊    | 217305/371472 [6:36:41<12:05:27,  3.54it/s]
 58%|█████▊    | 217306/371472 [6:36:42<11:59:17,  3.57it/s]
 58%|█████▊    | 217307/371472 [6:36:42<12:39:10,  3.38it/s]
 58%|█████▊    | 217308/371472 [6:36:42<12:11:25,  3.51it/s]
 58%|█████▊    | 217309/371472 [6:36:42<11:56:14,  3.59it/s]
 58%|█████▊    | 217310/371472 [6:36:43<12:09:09,  3.52it/s]
 58%|█████▊    | 217311/371472 [6:36:43<12:12:01,  3.51it/s]
 59%|█████▊    | 217312/371472 [6:36:43<12:18:34,  3.48it/s]
 59%|█████▊    | 217313/371472 [6:36:44<13:01:17,  3.29it/s]
 59%|█████▊    | 217314/371472 [6:36:44<13:07:08,  3.26it/s]
 59%|█████▊    | 217315/371472 [6:36:44<13:04:27,  3.28it/s]
 59%|█████▊    | 217316/371472 [6:36:44<12:22:20,  3.46it/s]
 59%|█████▊    | 217317/371472 [6:36:45<12:51:20,  3.33it/s]
 59%|█████▊    | 217318/371472 [6:36:45<12:32:48,  3.41it/s]
 59%|█████▊    | 217319/371472 [6:36:45<13:43:44,  3.12it/s]
 59%|█████▊    | 217320/371472 [6:36:46<13:00:42,  3.29it/s]
                                                            
{'loss': 2.7541, 'learning_rate': 4.736796742011247e-07, 'epoch': 9.36}
+
 59%|█████▊    | 217320/371472 [6:36:46<13:00:42,  3.29it/s]
 59%|█████▊    | 217321/371472 [6:36:46<13:35:25,  3.15it/s]
 59%|█████▊    | 217322/371472 [6:36:46<13:11:27,  3.25it/s]
 59%|█████▊    | 217323/371472 [6:36:47<12:39:49,  3.38it/s]
 59%|█████▊    | 217324/371472 [6:36:47<12:39:56,  3.38it/s]
 59%|█████▊    | 217325/371472 [6:36:47<12:31:05,  3.42it/s]
 59%|█████▊    | 217326/371472 [6:36:48<13:00:22,  3.29it/s]
 59%|█████▊    | 217327/371472 [6:36:48<13:42:06,  3.13it/s]
 59%|█████▊    | 217328/371472 [6:36:48<12:57:41,  3.30it/s]
 59%|█████▊    | 217329/371472 [6:36:49<13:34:47,  3.15it/s]
 59%|█████▊    | 217330/371472 [6:36:49<13:07:47,  3.26it/s]
 59%|█████▊    | 217331/371472 [6:36:49<13:02:16,  3.28it/s]
 59%|█████▊    | 217332/371472 [6:36:49<12:52:01,  3.33it/s]
 59%|█████▊    | 217333/371472 [6:36:50<12:28:56,  3.43it/s]
 59%|█████▊    | 217334/371472 [6:36:50<12:15:21,  3.49it/s]
 59%|█████▊    | 217335/371472 [6:36:50<12:05:29,  3.54it/s]
 59%|█████▊    | 217336/371472 [6:36:51<12:31:53,  3.42it/s]
 59%|█████▊    | 217337/371472 [6:36:51<12:30:11,  3.42it/s]
 59%|█████▊    | 217338/371472 [6:36:51<12:33:06,  3.41it/s]
 59%|█████▊    | 217339/371472 [6:36:51<12:13:05,  3.50it/s]
 59%|█████▊    | 217340/371472 [6:36:52<12:21:36,  3.46it/s]
                                                            
{'loss': 2.7715, 'learning_rate': 4.736311922256459e-07, 'epoch': 9.36}
+
 59%|█████▊    | 217340/371472 [6:36:52<12:21:36,  3.46it/s]
 59%|█████▊    | 217341/371472 [6:36:52<12:40:25,  3.38it/s]
 59%|█████▊    | 217342/371472 [6:36:52<12:58:47,  3.30it/s]
 59%|█████▊    | 217343/371472 [6:36:53<12:41:47,  3.37it/s]
 59%|█████▊    | 217344/371472 [6:36:53<12:24:08,  3.45it/s]
 59%|█████▊    | 217345/371472 [6:36:53<12:30:05,  3.42it/s]
 59%|█████▊    | 217346/371472 [6:36:54<13:09:20,  3.25it/s]
 59%|█████▊    | 217347/371472 [6:36:54<13:37:37,  3.14it/s]
 59%|█████▊    | 217348/371472 [6:36:54<13:03:37,  3.28it/s]
 59%|█████▊    | 217349/371472 [6:36:54<12:47:04,  3.35it/s]
 59%|█████▊    | 217350/371472 [6:36:55<12:35:54,  3.40it/s]
 59%|█████▊    | 217351/371472 [6:36:55<12:24:28,  3.45it/s]
 59%|█████▊    | 217352/371472 [6:36:55<12:30:23,  3.42it/s]
 59%|█████▊    | 217353/371472 [6:36:56<12:30:27,  3.42it/s]
 59%|█████▊    | 217354/371472 [6:36:56<12:46:23,  3.35it/s]
 59%|█████▊    | 217355/371472 [6:36:56<12:26:29,  3.44it/s]
 59%|█████▊    | 217356/371472 [6:36:56<12:33:10,  3.41it/s]
 59%|█████▊    | 217357/371472 [6:36:57<12:17:38,  3.48it/s]
 59%|█████▊    | 217358/371472 [6:36:57<12:18:25,  3.48it/s]
 59%|█████▊    | 217359/371472 [6:36:57<12:09:58,  3.52it/s]
 59%|█████▊    | 217360/371472 [6:36:58<12:07:44,  3.53it/s]
                                                            
{'loss': 2.8804, 'learning_rate': 4.7358271025016697e-07, 'epoch': 9.36}
+
 59%|█████▊    | 217360/371472 [6:36:58<12:07:44,  3.53it/s]
 59%|█████▊    | 217361/371472 [6:36:58<12:07:59,  3.53it/s]
 59%|█████▊    | 217362/371472 [6:36:58<12:23:10,  3.46it/s]
 59%|█████▊    | 217363/371472 [6:36:58<12:47:15,  3.35it/s]
 59%|█████▊    | 217364/371472 [6:36:59<13:18:48,  3.22it/s]
 59%|█████▊    | 217365/371472 [6:36:59<13:17:24,  3.22it/s]
 59%|█████▊    | 217366/371472 [6:36:59<12:59:35,  3.29it/s]
 59%|█████▊    | 217367/371472 [6:37:00<13:35:30,  3.15it/s]
 59%|█████▊    | 217368/371472 [6:37:00<13:18:21,  3.22it/s]
 59%|█████▊    | 217369/371472 [6:37:00<12:52:35,  3.32it/s]
 59%|█████▊    | 217370/371472 [6:37:01<12:56:05,  3.31it/s]
 59%|█████▊    | 217371/371472 [6:37:01<14:48:30,  2.89it/s]
 59%|█████▊    | 217372/371472 [6:37:01<13:49:08,  3.10it/s]
 59%|█████▊    | 217373/371472 [6:37:02<13:15:00,  3.23it/s]
 59%|█████▊    | 217374/371472 [6:37:02<13:41:18,  3.13it/s]
 59%|█████▊    | 217375/371472 [6:37:02<13:16:54,  3.22it/s]
 59%|█████▊    | 217376/371472 [6:37:03<13:32:31,  3.16it/s]
 59%|█████▊    | 217377/371472 [6:37:03<14:26:34,  2.96it/s]
 59%|█████▊    | 217378/371472 [6:37:03<15:23:13,  2.78it/s]
 59%|█████▊    | 217379/371472 [6:37:04<14:19:44,  2.99it/s]
 59%|█████▊    | 217380/371472 [6:37:04<14:14:40,  3.00it/s]
                                                            
{'loss': 2.6993, 'learning_rate': 4.735342282746881e-07, 'epoch': 9.36}
+
 59%|█████▊    | 217380/371472 [6:37:04<14:14:40,  3.00it/s]
 59%|█████▊    | 217381/371472 [6:37:04<13:13:49,  3.24it/s]
 59%|█████▊    | 217382/371472 [6:37:05<12:31:24,  3.42it/s]
 59%|█████▊    | 217383/371472 [6:37:05<12:47:15,  3.35it/s]
 59%|█████▊    | 217384/371472 [6:37:05<12:39:56,  3.38it/s]
 59%|█████▊    | 217385/371472 [6:37:05<12:32:22,  3.41it/s]
 59%|█████▊    | 217386/371472 [6:37:06<13:41:47,  3.13it/s]
 59%|█████▊    | 217387/371472 [6:37:06<13:02:19,  3.28it/s]
 59%|█████▊    | 217388/371472 [6:37:06<13:02:25,  3.28it/s]
 59%|█████▊    | 217389/371472 [6:37:07<13:22:39,  3.20it/s]
 59%|█████▊    | 217390/371472 [6:37:07<13:09:35,  3.25it/s]
 59%|█████▊    | 217391/371472 [6:37:07<12:51:14,  3.33it/s]
 59%|█████▊    | 217392/371472 [6:37:08<13:16:23,  3.22it/s]
 59%|█████▊    | 217393/371472 [6:37:08<12:54:07,  3.32it/s]
 59%|█████▊    | 217394/371472 [6:37:08<12:41:44,  3.37it/s]
 59%|█████▊    | 217395/371472 [6:37:08<12:26:04,  3.44it/s]
 59%|█████▊    | 217396/371472 [6:37:09<12:26:29,  3.44it/s]
 59%|█████▊    | 217397/371472 [6:37:09<12:21:27,  3.46it/s]
 59%|█████▊    | 217398/371472 [6:37:09<12:50:42,  3.33it/s]
 59%|█████▊    | 217399/371472 [6:37:10<12:43:39,  3.36it/s]
 59%|█████▊    | 217400/371472 [6:37:10<12:43:43,  3.36it/s]
                                                            
{'loss': 2.702, 'learning_rate': 4.7348574629920916e-07, 'epoch': 9.36}
+
 59%|█████▊    | 217400/371472 [6:37:10<12:43:43,  3.36it/s]
 59%|█████▊    | 217401/371472 [6:37:10<12:35:03,  3.40it/s]
 59%|█████▊    | 217402/371472 [6:37:11<12:35:05,  3.40it/s]
 59%|█████▊    | 217403/371472 [6:37:11<13:13:19,  3.24it/s]
 59%|█████▊    | 217404/371472 [6:37:11<13:28:39,  3.18it/s]
 59%|█████▊    | 217405/371472 [6:37:11<12:44:21,  3.36it/s]
 59%|█████▊    | 217406/371472 [6:37:12<12:18:48,  3.48it/s]
 59%|█████▊    | 217407/371472 [6:37:12<12:18:00,  3.48it/s]
 59%|█████▊    | 217408/371472 [6:37:12<12:19:08,  3.47it/s]
 59%|█████▊    | 217409/371472 [6:37:13<12:30:53,  3.42it/s]
 59%|█████▊    | 217410/371472 [6:37:13<12:37:21,  3.39it/s]
 59%|█████▊    | 217411/371472 [6:37:13<12:22:38,  3.46it/s]
 59%|█████▊    | 217412/371472 [6:37:13<12:34:13,  3.40it/s]
 59%|█████▊    | 217413/371472 [6:37:14<12:29:58,  3.42it/s]
 59%|█████▊    | 217414/371472 [6:37:14<12:30:41,  3.42it/s]
 59%|█████▊    | 217415/371472 [6:37:14<13:40:08,  3.13it/s]
 59%|█████▊    | 217416/371472 [6:37:15<13:25:00,  3.19it/s]
 59%|█████▊    | 217417/371472 [6:37:15<13:04:40,  3.27it/s]
 59%|█████▊    | 217418/371472 [6:37:15<13:37:16,  3.14it/s]
 59%|█████▊    | 217419/371472 [6:37:16<12:55:29,  3.31it/s]
 59%|█████▊    | 217420/371472 [6:37:16<13:08:11,  3.26it/s]
                                                            
{'loss': 2.5604, 'learning_rate': 4.734372643237303e-07, 'epoch': 9.36}
+
 59%|█████▊    | 217420/371472 [6:37:16<13:08:11,  3.26it/s]
 59%|█████▊    | 217421/371472 [6:37:16<12:37:19,  3.39it/s]
 59%|█████▊    | 217422/371472 [6:37:17<12:34:02,  3.40it/s]
 59%|█████▊    | 217423/371472 [6:37:17<13:19:31,  3.21it/s]
 59%|█████▊    | 217424/371472 [6:37:17<13:03:51,  3.28it/s]
 59%|█████▊    | 217425/371472 [6:37:17<13:01:48,  3.28it/s]
 59%|█████▊    | 217426/371472 [6:37:18<12:55:33,  3.31it/s]
 59%|█████▊    | 217427/371472 [6:37:18<12:53:55,  3.32it/s]
 59%|█████▊    | 217428/371472 [6:37:18<12:43:08,  3.36it/s]
 59%|█████▊    | 217429/371472 [6:37:19<12:45:11,  3.36it/s]
 59%|█████▊    | 217430/371472 [6:37:19<12:47:10,  3.35it/s]
 59%|█████▊    | 217431/371472 [6:37:19<12:30:23,  3.42it/s]
 59%|█████▊    | 217432/371472 [6:37:20<12:28:06,  3.43it/s]
 59%|█████▊    | 217433/371472 [6:37:20<12:33:35,  3.41it/s]
 59%|█████▊    | 217434/371472 [6:37:20<12:48:05,  3.34it/s]
 59%|█████▊    | 217435/371472 [6:37:20<12:33:07,  3.41it/s]
 59%|█████▊    | 217436/371472 [6:37:21<12:03:46,  3.55it/s]
 59%|█████▊    | 217437/371472 [6:37:21<12:07:36,  3.53it/s]
 59%|█████▊    | 217438/371472 [6:37:21<12:43:52,  3.36it/s]
 59%|█████▊    | 217439/371472 [6:37:22<12:26:23,  3.44it/s]
 59%|█████▊    | 217440/371472 [6:37:22<12:31:01,  3.42it/s]
                                                            
{'loss': 2.7732, 'learning_rate': 4.7338878234825136e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217440/371472 [6:37:22<12:31:01,  3.42it/s]
 59%|█████▊    | 217441/371472 [6:37:22<13:05:45,  3.27it/s]
 59%|█████▊    | 217442/371472 [6:37:22<12:38:07,  3.39it/s]
 59%|█████▊    | 217443/371472 [6:37:23<12:47:48,  3.34it/s]
 59%|█████▊    | 217444/371472 [6:37:23<12:21:41,  3.46it/s]
 59%|█████▊    | 217445/371472 [6:37:23<12:44:14,  3.36it/s]
 59%|█████▊    | 217446/371472 [6:37:24<12:25:54,  3.44it/s]
 59%|█████▊    | 217447/371472 [6:37:24<12:22:25,  3.46it/s]
 59%|█████▊    | 217448/371472 [6:37:24<12:04:03,  3.55it/s]
 59%|█████▊    | 217449/371472 [6:37:24<12:18:53,  3.47it/s]
 59%|█████▊    | 217450/371472 [6:37:25<12:32:11,  3.41it/s]
 59%|█████▊    | 217451/371472 [6:37:25<13:15:36,  3.23it/s]
 59%|█████▊    | 217452/371472 [6:37:25<13:16:08,  3.22it/s]
 59%|█████▊    | 217453/371472 [6:37:26<13:11:14,  3.24it/s]
 59%|█████▊    | 217454/371472 [6:37:26<13:05:17,  3.27it/s]
 59%|█████▊    | 217455/371472 [6:37:26<13:40:17,  3.13it/s]
 59%|█████▊    | 217456/371472 [6:37:27<13:10:41,  3.25it/s]
 59%|█████▊    | 217457/371472 [6:37:27<12:55:40,  3.31it/s]
 59%|█████▊    | 217458/371472 [6:37:27<12:56:02,  3.31it/s]
 59%|█████▊    | 217459/371472 [6:37:28<13:14:05,  3.23it/s]
 59%|█████▊    | 217460/371472 [6:37:28<12:46:51,  3.35it/s]
                                                            
{'loss': 2.7692, 'learning_rate': 4.7334030037277253e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217460/371472 [6:37:28<12:46:51,  3.35it/s]
 59%|█████▊    | 217461/371472 [6:37:28<12:36:52,  3.39it/s]
 59%|█████▊    | 217462/371472 [6:37:28<12:20:06,  3.47it/s]
 59%|█████▊    | 217463/371472 [6:37:29<12:19:05,  3.47it/s]
 59%|█████▊    | 217464/371472 [6:37:29<12:44:51,  3.36it/s]
 59%|█████▊    | 217465/371472 [6:37:29<12:39:12,  3.38it/s]
 59%|█████▊    | 217466/371472 [6:37:30<12:22:54,  3.46it/s]
 59%|█████▊    | 217467/371472 [6:37:30<12:04:00,  3.55it/s]
 59%|█████▊    | 217468/371472 [6:37:30<12:24:49,  3.45it/s]
 59%|█████▊    | 217469/371472 [6:37:30<12:48:33,  3.34it/s]
 59%|█████▊    | 217470/371472 [6:37:31<12:52:48,  3.32it/s]
 59%|█████▊    | 217471/371472 [6:37:31<12:43:34,  3.36it/s]
 59%|█████▊    | 217472/371472 [6:37:31<12:21:42,  3.46it/s]
 59%|█████▊    | 217473/371472 [6:37:32<12:35:21,  3.40it/s]
 59%|█████▊    | 217474/371472 [6:37:32<12:44:12,  3.36it/s]
 59%|█████▊    | 217475/371472 [6:37:32<12:27:08,  3.44it/s]
 59%|█████▊    | 217476/371472 [6:37:33<12:51:52,  3.33it/s]
 59%|█████▊    | 217477/371472 [6:37:33<13:09:58,  3.25it/s]
 59%|█████▊    | 217478/371472 [6:37:33<13:14:38,  3.23it/s]
 59%|█████▊    | 217479/371472 [6:37:34<13:12:37,  3.24it/s]
 59%|█████▊    | 217480/371472 [6:37:34<13:35:06,  3.15it/s]
                                                            
{'loss': 2.7861, 'learning_rate': 4.7329181839729355e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217480/371472 [6:37:34<13:35:06,  3.15it/s]
 59%|█████▊    | 217481/371472 [6:37:34<13:04:01,  3.27it/s]
 59%|█████▊    | 217482/371472 [6:37:34<13:17:31,  3.22it/s]
 59%|█████▊    | 217483/371472 [6:37:35<13:19:34,  3.21it/s]
 59%|█████▊    | 217484/371472 [6:37:35<13:12:56,  3.24it/s]
 59%|█████▊    | 217485/371472 [6:37:35<14:11:11,  3.02it/s]
 59%|█████▊    | 217486/371472 [6:37:36<13:24:42,  3.19it/s]
 59%|█████▊    | 217487/371472 [6:37:36<13:50:20,  3.09it/s]
 59%|█████▊    | 217488/371472 [6:37:36<13:18:04,  3.22it/s]
 59%|█████▊    | 217489/371472 [6:37:37<12:37:21,  3.39it/s]
 59%|█████▊    | 217490/371472 [6:37:37<12:11:05,  3.51it/s]
 59%|█████▊    | 217491/371472 [6:37:37<12:27:12,  3.43it/s]
 59%|█████▊    | 217492/371472 [6:37:37<12:35:46,  3.40it/s]
 59%|█████▊    | 217493/371472 [6:37:38<12:32:26,  3.41it/s]
 59%|█████▊    | 217494/371472 [6:37:38<12:06:24,  3.53it/s]
 59%|█████▊    | 217495/371472 [6:37:38<11:51:54,  3.60it/s]
 59%|█████▊    | 217496/371472 [6:37:39<11:52:18,  3.60it/s]
 59%|█████▊    | 217497/371472 [6:37:39<11:53:48,  3.60it/s]
 59%|█████▊    | 217498/371472 [6:37:39<12:26:41,  3.44it/s]
 59%|█████▊    | 217499/371472 [6:37:39<12:12:08,  3.51it/s]
 59%|█████▊    | 217500/371472 [6:37:40<12:05:56,  3.53it/s]
                                                            
{'loss': 2.7939, 'learning_rate': 4.7324333642181473e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217500/371472 [6:37:40<12:05:56,  3.53it/s]
 59%|█████▊    | 217501/371472 [6:37:40<12:03:01,  3.55it/s]
 59%|█████▊    | 217502/371472 [6:37:40<12:32:01,  3.41it/s]
 59%|█████▊    | 217503/371472 [6:37:41<12:31:42,  3.41it/s]
 59%|█████▊    | 217504/371472 [6:37:41<12:33:20,  3.41it/s]
 59%|█████▊    | 217505/371472 [6:37:41<12:50:00,  3.33it/s]
 59%|█████▊    | 217506/371472 [6:37:41<12:27:55,  3.43it/s]
 59%|█████▊    | 217507/371472 [6:37:42<13:14:48,  3.23it/s]
 59%|█████▊    | 217508/371472 [6:37:42<12:55:13,  3.31it/s]
 59%|█████▊    | 217509/371472 [6:37:42<12:34:12,  3.40it/s]
 59%|█████▊    | 217510/371472 [6:37:43<12:14:23,  3.49it/s]
 59%|█████▊    | 217511/371472 [6:37:43<11:54:31,  3.59it/s]
 59%|█████▊    | 217512/371472 [6:37:43<11:53:08,  3.60it/s]
 59%|█████▊    | 217513/371472 [6:37:44<12:20:01,  3.47it/s]
 59%|█████▊    | 217514/371472 [6:37:44<14:03:05,  3.04it/s]
 59%|█████▊    | 217515/371472 [6:37:44<13:48:48,  3.10it/s]
 59%|█████▊    | 217516/371472 [6:37:45<13:40:08,  3.13it/s]
 59%|█████▊    | 217517/371472 [6:37:45<13:18:49,  3.21it/s]
 59%|█████▊    | 217518/371472 [6:37:45<13:16:48,  3.22it/s]
 59%|█████▊    | 217519/371472 [6:37:45<12:45:49,  3.35it/s]
 59%|█████▊    | 217520/371472 [6:37:46<12:30:16,  3.42it/s]
                                                            
{'loss': 2.8307, 'learning_rate': 4.731948544463358e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217520/371472 [6:37:46<12:30:16,  3.42it/s]
 59%|█████▊    | 217521/371472 [6:37:46<12:19:02,  3.47it/s]
 59%|█████▊    | 217522/371472 [6:37:46<12:20:24,  3.47it/s]
 59%|█████▊    | 217523/371472 [6:37:47<12:09:40,  3.52it/s]
 59%|█████▊    | 217524/371472 [6:37:47<11:57:45,  3.57it/s]
 59%|█████▊    | 217525/371472 [6:37:47<12:00:45,  3.56it/s]
 59%|█████▊    | 217526/371472 [6:37:48<14:24:26,  2.97it/s]
 59%|█████▊    | 217527/371472 [6:37:48<13:59:19,  3.06it/s]
 59%|█████▊    | 217528/371472 [6:37:48<13:47:05,  3.10it/s]
 59%|█████▊    | 217529/371472 [6:37:48<13:08:19,  3.25it/s]
 59%|█████▊    | 217530/371472 [6:37:49<12:52:20,  3.32it/s]
 59%|█████▊    | 217531/371472 [6:37:49<12:35:28,  3.40it/s]
 59%|█████▊    | 217532/371472 [6:37:49<12:31:56,  3.41it/s]
 59%|█████▊    | 217533/371472 [6:37:50<12:21:23,  3.46it/s]
 59%|█████▊    | 217534/371472 [6:37:50<12:32:28,  3.41it/s]
 59%|█████▊    | 217535/371472 [6:37:50<12:31:22,  3.41it/s]
 59%|█████▊    | 217536/371472 [6:37:50<12:22:51,  3.45it/s]
 59%|█████▊    | 217537/371472 [6:37:51<12:32:07,  3.41it/s]
 59%|█████▊    | 217538/371472 [6:37:51<12:37:12,  3.39it/s]
 59%|█████▊    | 217539/371472 [6:37:51<12:25:27,  3.44it/s]
 59%|█████▊    | 217540/371472 [6:37:52<12:56:31,  3.30it/s]
                                                            
{'loss': 2.8812, 'learning_rate': 4.7314637247085693e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217540/371472 [6:37:52<12:56:31,  3.30it/s]
 59%|█████▊    | 217541/371472 [6:37:52<13:15:55,  3.22it/s]
 59%|█████▊    | 217542/371472 [6:37:52<13:05:25,  3.27it/s]
 59%|█████▊    | 217543/371472 [6:37:53<12:38:30,  3.38it/s]
 59%|█████▊    | 217544/371472 [6:37:53<12:25:54,  3.44it/s]
 59%|█████▊    | 217545/371472 [6:37:53<12:03:26,  3.55it/s]
 59%|█████▊    | 217546/371472 [6:37:53<11:48:17,  3.62it/s]
 59%|█████▊    | 217547/371472 [6:37:54<11:44:42,  3.64it/s]
 59%|█████▊    | 217548/371472 [6:37:54<12:05:17,  3.54it/s]
 59%|█████▊    | 217549/371472 [6:37:54<12:08:20,  3.52it/s]
 59%|█████▊    | 217550/371472 [6:37:55<12:36:12,  3.39it/s]
 59%|█████▊    | 217551/371472 [6:37:55<12:27:02,  3.43it/s]
 59%|█████▊    | 217552/371472 [6:37:55<13:19:53,  3.21it/s]
 59%|█████▊    | 217553/371472 [6:37:55<12:52:59,  3.32it/s]
 59%|█████▊    | 217554/371472 [6:37:56<12:24:56,  3.44it/s]
 59%|█████▊    | 217555/371472 [6:37:56<12:02:42,  3.55it/s]
 59%|█████▊    | 217556/371472 [6:37:56<12:01:54,  3.55it/s]
 59%|█████▊    | 217557/371472 [6:37:57<12:00:23,  3.56it/s]
 59%|█████▊    | 217558/371472 [6:37:57<11:56:28,  3.58it/s]
 59%|█████▊    | 217559/371472 [6:37:57<12:09:49,  3.51it/s]
 59%|█████▊    | 217560/371472 [6:37:57<12:31:11,  3.41it/s]
                                                            
{'loss': 2.7517, 'learning_rate': 4.73097890495378e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217560/371472 [6:37:57<12:31:11,  3.41it/s]
 59%|█████▊    | 217561/371472 [6:37:58<12:05:33,  3.54it/s]
 59%|█████▊    | 217562/371472 [6:37:58<12:40:36,  3.37it/s]
 59%|█████▊    | 217563/371472 [6:37:58<13:36:00,  3.14it/s]
 59%|█████▊    | 217564/371472 [6:37:59<12:57:31,  3.30it/s]
 59%|█████▊    | 217565/371472 [6:37:59<12:37:56,  3.38it/s]
 59%|█████▊    | 217566/371472 [6:37:59<12:30:45,  3.42it/s]
 59%|█████▊    | 217567/371472 [6:38:00<12:30:48,  3.42it/s]
 59%|█████▊    | 217568/371472 [6:38:00<12:35:06,  3.40it/s]
 59%|█████▊    | 217569/371472 [6:38:00<12:26:56,  3.43it/s]
 59%|█████▊    | 217570/371472 [6:38:00<12:22:02,  3.46it/s]
 59%|█████▊    | 217571/371472 [6:38:01<12:36:45,  3.39it/s]
 59%|█████▊    | 217572/371472 [6:38:01<12:26:51,  3.43it/s]
 59%|█████▊    | 217573/371472 [6:38:01<12:14:20,  3.49it/s]
 59%|█████▊    | 217574/371472 [6:38:02<12:22:19,  3.46it/s]
 59%|█████▊    | 217575/371472 [6:38:02<12:52:58,  3.32it/s]
 59%|█████▊    | 217576/371472 [6:38:02<12:36:38,  3.39it/s]
 59%|█████▊    | 217577/371472 [6:38:02<12:43:03,  3.36it/s]
 59%|█████▊    | 217578/371472 [6:38:03<13:17:45,  3.22it/s]
 59%|█████▊    | 217579/371472 [6:38:03<13:02:12,  3.28it/s]
 59%|█████▊    | 217580/371472 [6:38:03<12:42:31,  3.36it/s]
                                                            
{'loss': 2.7045, 'learning_rate': 4.730494085198992e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217580/371472 [6:38:03<12:42:31,  3.36it/s]
 59%|█████▊    | 217581/371472 [6:38:04<12:23:16,  3.45it/s]
 59%|█████���    | 217582/371472 [6:38:04<13:00:50,  3.28it/s]
 59%|█████▊    | 217583/371472 [6:38:04<13:10:03,  3.25it/s]
 59%|█████▊    | 217584/371472 [6:38:05<12:36:06,  3.39it/s]
 59%|█████▊    | 217585/371472 [6:38:05<13:32:48,  3.16it/s]
 59%|█████▊    | 217586/371472 [6:38:05<13:43:38,  3.11it/s]
 59%|█████▊    | 217587/371472 [6:38:06<13:09:07,  3.25it/s]
 59%|█████▊    | 217588/371472 [6:38:06<12:53:46,  3.31it/s]
 59%|█████▊    | 217589/371472 [6:38:06<13:05:50,  3.26it/s]
 59%|█████▊    | 217590/371472 [6:38:06<12:51:05,  3.33it/s]
 59%|█████▊    | 217591/371472 [6:38:07<12:49:45,  3.33it/s]
 59%|█████▊    | 217592/371472 [6:38:07<13:06:33,  3.26it/s]
 59%|█████▊    | 217593/371472 [6:38:07<12:52:22,  3.32it/s]
 59%|█████▊    | 217594/371472 [6:38:08<12:46:24,  3.35it/s]
 59%|█████▊    | 217595/371472 [6:38:08<12:46:33,  3.35it/s]
 59%|█████▊    | 217596/371472 [6:38:08<13:09:13,  3.25it/s]
 59%|█████▊    | 217597/371472 [6:38:09<13:00:02,  3.29it/s]
 59%|█████▊    | 217598/371472 [6:38:09<12:59:52,  3.29it/s]
 59%|█████▊    | 217599/371472 [6:38:09<14:38:50,  2.92it/s]
 59%|█████▊    | 217600/371472 [6:38:10<13:40:24,  3.13it/s]
                                                            
{'loss': 2.8497, 'learning_rate': 4.730009265444202e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217600/371472 [6:38:10<13:40:24,  3.13it/s]
 59%|█████▊    | 217601/371472 [6:38:10<13:36:29,  3.14it/s]
 59%|█████▊    | 217602/371472 [6:38:10<13:05:35,  3.26it/s]
 59%|█████▊    | 217603/371472 [6:38:11<13:33:04,  3.15it/s]
 59%|█████▊    | 217604/371472 [6:38:11<13:48:46,  3.09it/s]
 59%|█████▊    | 217605/371472 [6:38:11<13:55:05,  3.07it/s]
 59%|█████▊    | 217606/371472 [6:38:11<13:30:57,  3.16it/s]
 59%|█████▊    | 217607/371472 [6:38:12<13:01:00,  3.28it/s]
 59%|█████▊    | 217608/371472 [6:38:12<13:04:34,  3.27it/s]
 59%|█████▊    | 217609/371472 [6:38:12<12:51:56,  3.32it/s]
 59%|█████▊    | 217610/371472 [6:38:13<12:19:52,  3.47it/s]
 59%|█████▊    | 217611/371472 [6:38:13<12:14:44,  3.49it/s]
 59%|█████▊    | 217612/371472 [6:38:13<12:22:28,  3.45it/s]
 59%|█████▊    | 217613/371472 [6:38:13<12:07:39,  3.52it/s]
 59%|█████▊    | 217614/371472 [6:38:14<12:22:43,  3.45it/s]
 59%|█████▊    | 217615/371472 [6:38:14<12:56:59,  3.30it/s]
 59%|█████▊    | 217616/371472 [6:38:14<13:33:50,  3.15it/s]
 59%|█████▊    | 217617/371472 [6:38:15<14:30:15,  2.95it/s]
 59%|█████▊    | 217618/371472 [6:38:15<13:49:52,  3.09it/s]
 59%|█████▊    | 217619/371472 [6:38:15<13:35:57,  3.14it/s]
 59%|█████▊    | 217620/371472 [6:38:16<12:58:21,  3.29it/s]
                                                            
{'loss': 2.7783, 'learning_rate': 4.729524445689413e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217620/371472 [6:38:16<12:58:21,  3.29it/s]
 59%|█████▊    | 217621/371472 [6:38:16<12:35:13,  3.40it/s]
 59%|█████▊    | 217622/371472 [6:38:16<12:16:23,  3.48it/s]
 59%|█████▊    | 217623/371472 [6:38:17<11:58:55,  3.57it/s]
 59%|█████▊    | 217624/371472 [6:38:17<11:45:57,  3.63it/s]
 59%|█████▊    | 217625/371472 [6:38:17<11:54:51,  3.59it/s]
 59%|█████▊    | 217626/371472 [6:38:17<12:04:27,  3.54it/s]
 59%|█████▊    | 217627/371472 [6:38:18<12:09:43,  3.51it/s]
 59%|█████▊    | 217628/371472 [6:38:18<12:11:14,  3.51it/s]
 59%|█████▊    | 217629/371472 [6:38:18<12:09:34,  3.51it/s]
 59%|█████▊    | 217630/371472 [6:38:18<11:59:34,  3.56it/s]
 59%|█████▊    | 217631/371472 [6:38:19<12:08:55,  3.52it/s]
 59%|█████▊    | 217632/371472 [6:38:19<12:13:17,  3.50it/s]
 59%|█████▊    | 217633/371472 [6:38:19<13:28:32,  3.17it/s]
 59%|█████▊    | 217634/371472 [6:38:20<13:29:35,  3.17it/s]
 59%|█████▊    | 217635/371472 [6:38:20<13:00:40,  3.28it/s]
 59%|█████▊    | 217636/371472 [6:38:20<12:38:19,  3.38it/s]
 59%|█████▊    | 217637/371472 [6:38:21<12:31:17,  3.41it/s]
 59%|█████▊    | 217638/371472 [6:38:21<12:16:49,  3.48it/s]
 59%|█████▊    | 217639/371472 [6:38:21<12:47:20,  3.34it/s]
 59%|█████▊    | 217640/371472 [6:38:21<12:23:53,  3.45it/s]
                                                            
{'loss': 2.7794, 'learning_rate': 4.7290396259346244e-07, 'epoch': 9.37}
+
 59%|█████▊    | 217640/371472 [6:38:21<12:23:53,  3.45it/s]
 59%|█████▊    | 217641/371472 [6:38:22<11:57:40,  3.57it/s]
 59%|█████▊    | 217642/371472 [6:38:22<11:54:15,  3.59it/s]
 59%|█████▊    | 217643/371472 [6:38:22<12:02:36,  3.55it/s]
 59%|█████▊    | 217644/371472 [6:38:23<11:50:00,  3.61it/s]
 59%|█████▊    | 217645/371472 [6:38:23<11:38:07,  3.67it/s]
 59%|█████▊    | 217646/371472 [6:38:23<11:56:56,  3.58it/s]
 59%|█████▊    | 217647/371472 [6:38:23<12:37:18,  3.39it/s]
 59%|█████▊    | 217648/371472 [6:38:24<13:07:28,  3.26it/s]
 59%|█████▊    | 217649/371472 [6:38:24<13:11:36,  3.24it/s]
 59%|█████▊    | 217650/371472 [6:38:24<13:00:02,  3.29it/s]
 59%|█████▊    | 217651/371472 [6:38:25<12:59:41,  3.29it/s]
 59%|█████▊    | 217652/371472 [6:38:25<12:33:36,  3.40it/s]
 59%|█████▊    | 217653/371472 [6:38:25<12:26:50,  3.43it/s]
 59%|█████▊    | 217654/371472 [6:38:26<12:14:48,  3.49it/s]
 59%|█████▊    | 217655/371472 [6:38:26<12:09:16,  3.52it/s]
 59%|█████▊    | 217656/371472 [6:38:26<12:28:09,  3.43it/s]
 59%|█████▊    | 217657/371472 [6:38:26<12:26:11,  3.44it/s]
 59%|█████▊    | 217658/371472 [6:38:27<12:45:27,  3.35it/s]
 59%|█████▊    | 217659/371472 [6:38:27<12:17:45,  3.47it/s]
 59%|█████▊    | 217660/371472 [6:38:27<12:23:33,  3.45it/s]
                                                            
{'loss': 2.9148, 'learning_rate': 4.7285548061798357e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217660/371472 [6:38:27<12:23:33,  3.45it/s]
 59%|█████▊    | 217661/371472 [6:38:28<12:34:10,  3.40it/s]
 59%|█████▊    | 217662/371472 [6:38:28<12:27:40,  3.43it/s]
 59%|█████▊    | 217663/371472 [6:38:28<12:23:42,  3.45it/s]
 59%|█████▊    | 217664/371472 [6:38:28<12:06:47,  3.53it/s]
 59%|█████▊    | 217665/371472 [6:38:29<12:53:14,  3.32it/s]
 59%|█████▊    | 217666/371472 [6:38:29<13:24:55,  3.18it/s]
 59%|█████▊    | 217667/371472 [6:38:30<15:19:17,  2.79it/s]
 59%|█████▊    | 217668/371472 [6:38:30<14:43:02,  2.90it/s]
 59%|█████▊    | 217669/371472 [6:38:30<13:49:30,  3.09it/s]
 59%|█████▊    | 217670/371472 [6:38:30<13:33:11,  3.15it/s]
 59%|█████▊    | 217671/371472 [6:38:31<13:32:42,  3.15it/s]
 59%|█████▊    | 217672/371472 [6:38:31<13:06:40,  3.26it/s]
 59%|█████▊    | 217673/371472 [6:38:31<13:21:21,  3.20it/s]
 59%|█████▊    | 217674/371472 [6:38:32<12:43:08,  3.36it/s]
 59%|█████▊    | 217675/371472 [6:38:32<12:13:09,  3.50it/s]
 59%|█████▊    | 217676/371472 [6:38:32<12:15:49,  3.48it/s]
 59%|█████▊    | 217677/371472 [6:38:32<12:08:18,  3.52it/s]
 59%|█████▊    | 217678/371472 [6:38:33<12:20:51,  3.46it/s]
 59%|█████▊    | 217679/371472 [6:38:33<12:16:43,  3.48it/s]
 59%|█████▊    | 217680/371472 [6:38:33<12:50:32,  3.33it/s]
                                                            
{'loss': 2.7302, 'learning_rate': 4.7280699864250464e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217680/371472 [6:38:33<12:50:32,  3.33it/s]
 59%|█████▊    | 217681/371472 [6:38:34<12:58:26,  3.29it/s]
 59%|█████▊    | 217682/371472 [6:38:34<12:37:12,  3.39it/s]
 59%|█████▊    | 217683/371472 [6:38:34<12:15:08,  3.49it/s]
 59%|█████▊    | 217684/371472 [6:38:35<12:27:25,  3.43it/s]
 59%|█████▊    | 217685/371472 [6:38:35<12:58:09,  3.29it/s]
 59%|█████▊    | 217686/371472 [6:38:35<13:05:10,  3.26it/s]
 59%|█████▊    | 217687/371472 [6:38:35<12:27:00,  3.43it/s]
 59%|█████▊    | 217688/371472 [6:38:36<12:10:06,  3.51it/s]
 59%|█████▊    | 217689/371472 [6:38:36<12:12:22,  3.50it/s]
 59%|█████▊    | 217690/371472 [6:38:36<11:55:33,  3.58it/s]
 59%|█████▊    | 217691/371472 [6:38:37<12:07:29,  3.52it/s]
 59%|█████▊    | 217692/371472 [6:38:37<12:05:09,  3.53it/s]
 59%|█████▊    | 217693/371472 [6:38:37<12:17:52,  3.47it/s]
 59%|█████▊    | 217694/371472 [6:38:37<12:34:28,  3.40it/s]
 59%|█████▊    | 217695/371472 [6:38:38<12:16:11,  3.48it/s]
 59%|█████▊    | 217696/371472 [6:38:38<12:08:20,  3.52it/s]
 59%|█████▊    | 217697/371472 [6:38:38<12:10:07,  3.51it/s]
 59%|█████▊    | 217698/371472 [6:38:39<12:09:35,  3.51it/s]
 59%|█████▊    | 217699/371472 [6:38:39<12:54:09,  3.31it/s]
 59%|█████▊    | 217700/371472 [6:38:39<12:37:48,  3.38it/s]
                                                            
{'loss': 2.8039, 'learning_rate': 4.727585166670258e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217700/371472 [6:38:39<12:37:48,  3.38it/s]
 59%|█████▊    | 217701/371472 [6:38:40<12:56:55,  3.30it/s]
 59%|█████▊    | 217702/371472 [6:38:40<13:09:34,  3.25it/s]
 59%|█████▊    | 217703/371472 [6:38:40<13:14:09,  3.23it/s]
 59%|█████▊    | 217704/371472 [6:38:41<13:49:49,  3.09it/s]
 59%|█████▊    | 217705/371472 [6:38:41<13:22:52,  3.19it/s]
 59%|█████▊    | 217706/371472 [6:38:41<13:08:36,  3.25it/s]
 59%|█████▊    | 217707/371472 [6:38:41<12:59:29,  3.29it/s]
 59%|█████▊    | 217708/371472 [6:38:42<12:17:57,  3.47it/s]
 59%|█████▊    | 217709/371472 [6:38:42<12:27:50,  3.43it/s]
 59%|█████▊    | 217710/371472 [6:38:42<12:22:57,  3.45it/s]
 59%|█████▊    | 217711/371472 [6:38:43<13:04:00,  3.27it/s]
 59%|█████▊    | 217712/371472 [6:38:43<12:47:32,  3.34it/s]
 59%|█████▊    | 217713/371472 [6:38:43<12:32:48,  3.40it/s]
 59%|█████▊    | 217714/371472 [6:38:43<12:47:07,  3.34it/s]
 59%|█████▊    | 217715/371472 [6:38:44<13:50:27,  3.09it/s]
 59%|█████▊    | 217716/371472 [6:38:44<14:04:46,  3.03it/s]
 59%|█████▊    | 217717/371472 [6:38:45<14:02:23,  3.04it/s]
 59%|█████▊    | 217718/371472 [6:38:45<13:32:28,  3.15it/s]
 59%|█████▊    | 217719/371472 [6:38:45<13:05:34,  3.26it/s]
 59%|█████▊    | 217720/371472 [6:38:45<13:05:52,  3.26it/s]
                                                            
{'loss': 2.6189, 'learning_rate': 4.727100346915469e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217720/371472 [6:38:45<13:05:52,  3.26it/s]
 59%|█████▊    | 217721/371472 [6:38:46<13:02:44,  3.27it/s]
 59%|█████▊    | 217722/371472 [6:38:46<12:23:44,  3.45it/s]
 59%|█████▊    | 217723/371472 [6:38:46<13:10:37,  3.24it/s]
 59%|█████▊    | 217724/371472 [6:38:47<13:18:07,  3.21it/s]
 59%|█████▊    | 217725/371472 [6:38:47<13:17:47,  3.21it/s]
 59%|█████▊    | 217726/371472 [6:38:47<13:21:39,  3.20it/s]
 59%|█████▊    | 217727/371472 [6:38:48<13:14:54,  3.22it/s]
 59%|█████▊    | 217728/371472 [6:38:48<13:15:27,  3.22it/s]
 59%|█████▊    | 217729/371472 [6:38:48<12:55:00,  3.31it/s]
 59%|█████▊    | 217730/371472 [6:38:48<12:25:09,  3.44it/s]
 59%|█████▊    | 217731/371472 [6:38:49<12:20:48,  3.46it/s]
 59%|█████▊    | 217732/371472 [6:38:49<12:09:36,  3.51it/s]
 59%|█████▊    | 217733/371472 [6:38:49<13:02:07,  3.28it/s]
 59%|█████▊    | 217734/371472 [6:38:50<12:38:15,  3.38it/s]
 59%|█████▊    | 217735/371472 [6:38:50<12:19:44,  3.46it/s]
 59%|█████▊    | 217736/371472 [6:38:50<12:05:43,  3.53it/s]
 59%|█████▊    | 217737/371472 [6:38:50<12:02:01,  3.55it/s]
 59%|█████▊    | 217738/371472 [6:38:51<11:36:03,  3.68it/s]
 59%|█████▊    | 217739/371472 [6:38:51<11:32:39,  3.70it/s]
 59%|█████▊    | 217740/371472 [6:38:51<11:36:39,  3.68it/s]
                                                            
{'loss': 2.7212, 'learning_rate': 4.72661552716068e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217740/371472 [6:38:51<11:36:39,  3.68it/s]
 59%|█████▊    | 217741/371472 [6:38:52<12:18:33,  3.47it/s]
 59%|█████▊    | 217742/371472 [6:38:52<12:07:21,  3.52it/s]
 59%|█████▊    | 217743/371472 [6:38:52<12:07:40,  3.52it/s]
 59%|█████▊    | 217744/371472 [6:38:52<11:57:49,  3.57it/s]
 59%|█████▊    | 217745/371472 [6:38:53<11:54:34,  3.59it/s]
 59%|█████▊    | 217746/371472 [6:38:53<11:50:07,  3.61it/s]
 59%|█████▊    | 217747/371472 [6:38:53<11:41:43,  3.65it/s]
 59%|█████▊    | 217748/371472 [6:38:53<11:42:02,  3.65it/s]
 59%|█████▊    | 217749/371472 [6:38:54<11:36:32,  3.68it/s]
 59%|█████▊    | 217750/371472 [6:38:54<11:56:00,  3.58it/s]
 59%|█████▊    | 217751/371472 [6:38:54<12:15:34,  3.48it/s]
 59%|█████▊    | 217752/371472 [6:38:55<12:38:04,  3.38it/s]
 59%|█████▊    | 217753/371472 [6:38:55<12:36:14,  3.39it/s]
 59%|█████▊    | 217754/371472 [6:38:55<13:42:38,  3.11it/s]
 59%|█████▊    | 217755/371472 [6:38:56<13:45:49,  3.10it/s]
 59%|█████▊    | 217756/371472 [6:38:56<13:02:35,  3.27it/s]
 59%|█████▊    | 217757/371472 [6:38:56<13:10:56,  3.24it/s]
 59%|█████▊    | 217758/371472 [6:38:56<12:49:01,  3.33it/s]
 59%|█████▊    | 217759/371472 [6:38:57<12:57:12,  3.30it/s]
 59%|█████▊    | 217760/371472 [6:38:57<12:25:37,  3.44it/s]
                                                            
{'loss': 2.7878, 'learning_rate': 4.726130707405891e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217760/371472 [6:38:57<12:25:37,  3.44it/s]
 59%|█████▊    | 217761/371472 [6:38:57<12:15:10,  3.48it/s]
 59%|█████▊    | 217762/371472 [6:38:58<12:09:49,  3.51it/s]
 59%|█████▊    | 217763/371472 [6:38:58<11:55:29,  3.58it/s]
 59%|█████▊    | 217764/371472 [6:38:58<12:22:21,  3.45it/s]
 59%|█████▊    | 217765/371472 [6:38:58<12:06:22,  3.53it/s]
 59%|█████▊    | 217766/371472 [6:38:59<13:19:26,  3.20it/s]
 59%|█████▊    | 217767/371472 [6:38:59<13:09:02,  3.25it/s]
 59%|█████▊    | 217768/371472 [6:38:59<12:42:19,  3.36it/s]
 59%|█████▊    | 217769/371472 [6:39:00<12:20:05,  3.46it/s]
 59%|█████▊    | 217770/371472 [6:39:00<12:13:04,  3.49it/s]
 59%|█████▊    | 217771/371472 [6:39:00<12:10:30,  3.51it/s]
 59%|█████▊    | 217772/371472 [6:39:01<12:05:40,  3.53it/s]
 59%|█████▊    | 217773/371472 [6:39:01<11:51:24,  3.60it/s]
 59%|█████▊    | 217774/371472 [6:39:01<11:56:49,  3.57it/s]
 59%|█████▊    | 217775/371472 [6:39:01<11:49:16,  3.61it/s]
 59%|█████▊    | 217776/371472 [6:39:02<11:48:18,  3.62it/s]
 59%|█████▊    | 217777/371472 [6:39:02<12:01:52,  3.55it/s]
 59%|█████▊    | 217778/371472 [6:39:02<12:00:15,  3.56it/s]
 59%|█████▊    | 217779/371472 [6:39:03<13:28:44,  3.17it/s]
 59%|█████▊    | 217780/371472 [6:39:03<13:52:20,  3.08it/s]
                                                            
{'loss': 2.6635, 'learning_rate': 4.7256458876511026e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217780/371472 [6:39:03<13:52:20,  3.08it/s]
 59%|█████▊    | 217781/371472 [6:39:03<13:14:12,  3.23it/s]
 59%|█████▊    | 217782/371472 [6:39:03<12:47:35,  3.34it/s]
 59%|█████▊    | 217783/371472 [6:39:04<12:50:24,  3.32it/s]
 59%|█████▊    | 217784/371472 [6:39:04<13:02:31,  3.27it/s]
 59%|█████▊    | 217785/371472 [6:39:04<13:39:24,  3.13it/s]
 59%|█████▊    | 217786/371472 [6:39:05<13:26:43,  3.18it/s]
 59%|█████▊    | 217787/371472 [6:39:05<12:52:43,  3.31it/s]
 59%|█████▊    | 217788/371472 [6:39:05<12:16:30,  3.48it/s]
 59%|█████▊    | 217789/371472 [6:39:06<11:53:19,  3.59it/s]
 59%|█████▊    | 217790/371472 [6:39:06<11:56:46,  3.57it/s]
 59%|█████▊    | 217791/371472 [6:39:06<11:59:48,  3.56it/s]
 59%|█████▊    | 217792/371472 [6:39:06<11:57:33,  3.57it/s]
 59%|█████▊    | 217793/371472 [6:39:07<11:36:29,  3.68it/s]
 59%|█████▊    | 217794/371472 [6:39:07<11:24:09,  3.74it/s]
 59%|█████▊    | 217795/371472 [6:39:07<11:29:56,  3.71it/s]
 59%|█████▊    | 217796/371472 [6:39:07<11:56:09,  3.58it/s]
 59%|█████▊    | 217797/371472 [6:39:08<11:58:50,  3.56it/s]
 59%|█████▊    | 217798/371472 [6:39:08<11:54:22,  3.59it/s]
 59%|█████▊    | 217799/371472 [6:39:08<12:18:41,  3.47it/s]
 59%|█████▊    | 217800/371472 [6:39:09<12:07:14,  3.52it/s]
                                                            
{'loss': 2.8616, 'learning_rate': 4.725161067896313e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217800/371472 [6:39:09<12:07:14,  3.52it/s]
 59%|█████▊    | 217801/371472 [6:39:09<11:46:49,  3.62it/s]
 59%|█████▊    | 217802/371472 [6:39:09<11:47:39,  3.62it/s]
 59%|█████▊    | 217803/371472 [6:39:09<11:43:23,  3.64it/s]
 59%|█████▊    | 217804/371472 [6:39:10<11:51:14,  3.60it/s]
 59%|█████▊    | 217805/371472 [6:39:10<12:09:52,  3.51it/s]
 59%|█████▊    | 217806/371472 [6:39:10<11:54:21,  3.59it/s]
 59%|█████▊    | 217807/371472 [6:39:11<11:54:46,  3.58it/s]
 59%|█████▊    | 217808/371472 [6:39:11<12:20:01,  3.46it/s]
 59%|█████▊    | 217809/371472 [6:39:11<12:38:40,  3.38it/s]
 59%|█████▊    | 217810/371472 [6:39:11<12:19:25,  3.46it/s]
 59%|█████▊    | 217811/371472 [6:39:12<13:06:13,  3.26it/s]
 59%|█████▊    | 217812/371472 [6:39:12<12:36:59,  3.38it/s]
 59%|█████▊    | 217813/371472 [6:39:12<13:07:34,  3.25it/s]
 59%|█████▊    | 217814/371472 [6:39:13<13:51:53,  3.08it/s]
 59%|█████▊    | 217815/371472 [6:39:13<13:30:48,  3.16it/s]
 59%|█████▊    | 217816/371472 [6:39:13<12:50:34,  3.32it/s]
 59%|█████▊    | 217817/371472 [6:39:14<12:20:53,  3.46it/s]
 59%|█████▊    | 217818/371472 [6:39:14<13:05:30,  3.26it/s]
 59%|█████▊    | 217819/371472 [6:39:14<12:42:00,  3.36it/s]
 59%|█████▊    | 217820/371472 [6:39:15<12:52:39,  3.31it/s]
                                                            
{'loss': 2.7216, 'learning_rate': 4.7246762481415246e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217820/371472 [6:39:15<12:52:39,  3.31it/s]
 59%|█████▊    | 217821/371472 [6:39:15<12:27:15,  3.43it/s]
 59%|█████▊    | 217822/371472 [6:39:15<12:10:45,  3.50it/s]
 59%|█████▊    | 217823/371472 [6:39:15<12:32:16,  3.40it/s]
 59%|█████▊    | 217824/371472 [6:39:16<12:13:32,  3.49it/s]
 59%|█████▊    | 217825/371472 [6:39:16<12:01:39,  3.55it/s]
 59%|█████▊    | 217826/371472 [6:39:16<11:47:16,  3.62it/s]
 59%|█████▊    | 217827/371472 [6:39:16<11:53:14,  3.59it/s]
 59%|█████▊    | 217828/371472 [6:39:17<11:50:52,  3.60it/s]
 59%|█████▊    | 217829/371472 [6:39:17<13:08:23,  3.25it/s]
 59%|█████▊    | 217830/371472 [6:39:17<13:07:02,  3.25it/s]
 59%|█████▊    | 217831/371472 [6:39:18<13:10:06,  3.24it/s]
 59%|█████▊    | 217832/371472 [6:39:18<12:48:43,  3.33it/s]
 59%|█████▊    | 217833/371472 [6:39:18<12:41:15,  3.36it/s]
 59%|█████▊    | 217834/371472 [6:39:19<13:02:15,  3.27it/s]
 59%|█████▊    | 217835/371472 [6:39:19<12:38:06,  3.38it/s]
 59%|█████▊    | 217836/371472 [6:39:19<12:58:40,  3.29it/s]
 59%|█████▊    | 217837/371472 [6:39:20<12:26:34,  3.43it/s]
 59%|█████▊    | 217838/371472 [6:39:20<12:15:39,  3.48it/s]
 59%|█████▊    | 217839/371472 [6:39:20<12:06:11,  3.53it/s]
 59%|█████▊    | 217840/371472 [6:39:20<12:34:02,  3.40it/s]
                                                            
{'loss': 2.8782, 'learning_rate': 4.7241914283867353e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217840/371472 [6:39:20<12:34:02,  3.40it/s]
 59%|█████▊    | 217841/371472 [6:39:21<13:06:12,  3.26it/s]
 59%|█████▊    | 217842/371472 [6:39:21<12:21:47,  3.45it/s]
 59%|█████▊    | 217843/371472 [6:39:21<12:35:17,  3.39it/s]
 59%|█████▊    | 217844/371472 [6:39:22<12:11:38,  3.50it/s]
 59%|█████▊    | 217845/371472 [6:39:22<12:23:41,  3.44it/s]
 59%|█████▊    | 217846/371472 [6:39:22<12:17:32,  3.47it/s]
 59%|█████▊    | 217847/371472 [6:39:22<12:43:53,  3.35it/s]
 59%|█████▊    | 217848/371472 [6:39:23<12:49:02,  3.33it/s]
 59%|█████▊    | 217849/371472 [6:39:23<12:34:09,  3.40it/s]
 59%|█████▊    | 217850/371472 [6:39:23<13:10:36,  3.24it/s]
 59%|█████▊    | 217851/371472 [6:39:24<12:47:33,  3.34it/s]
 59%|█████▊    | 217852/371472 [6:39:24<13:36:53,  3.13it/s]
 59%|█████▊    | 217853/371472 [6:39:24<13:19:25,  3.20it/s]
 59%|█████▊    | 217854/371472 [6:39:25<13:11:47,  3.23it/s]
 59%|█████▊    | 217855/371472 [6:39:25<13:02:15,  3.27it/s]
 59%|█████▊    | 217856/371472 [6:39:25<13:52:51,  3.07it/s]
 59%|█████▊    | 217857/371472 [6:39:26<13:03:25,  3.27it/s]
 59%|█████▊    | 217858/371472 [6:39:26<12:19:58,  3.46it/s]
 59%|█████▊    | 217859/371472 [6:39:26<12:15:54,  3.48it/s]
 59%|█████▊    | 217860/371472 [6:39:26<12:46:10,  3.34it/s]
                                                            
{'loss': 2.7975, 'learning_rate': 4.7237066086319455e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217860/371472 [6:39:26<12:46:10,  3.34it/s]
 59%|█████▊    | 217861/371472 [6:39:27<12:32:40,  3.40it/s]
 59%|█████▊    | 217862/371472 [6:39:27<12:35:53,  3.39it/s]
 59%|█████▊    | 217863/371472 [6:39:27<12:19:45,  3.46it/s]
 59%|█████▊    | 217864/371472 [6:39:28<12:25:22,  3.43it/s]
 59%|█████▊    | 217865/371472 [6:39:28<12:31:12,  3.41it/s]
 59%|█████▊    | 217866/371472 [6:39:28<12:24:06,  3.44it/s]
 59%|█████▊    | 217867/371472 [6:39:28<12:24:55,  3.44it/s]
 59%|█████▊    | 217868/371472 [6:39:29<12:11:57,  3.50it/s]
 59%|█████▊    | 217869/371472 [6:39:29<11:43:29,  3.64it/s]
 59%|█████▊    | 217870/371472 [6:39:29<11:40:12,  3.66it/s]
 59%|█████▊    | 217871/371472 [6:39:29<11:47:27,  3.62it/s]
 59%|█████▊    | 217872/371472 [6:39:30<12:00:55,  3.55it/s]
 59%|█████▊    | 217873/371472 [6:39:30<12:00:06,  3.56it/s]
 59%|█████▊    | 217874/371472 [6:39:30<12:10:08,  3.51it/s]
 59%|█████▊    | 217875/371472 [6:39:31<12:52:45,  3.31it/s]
 59%|█████▊    | 217876/371472 [6:39:31<12:47:35,  3.34it/s]
 59%|█████▊    | 217877/371472 [6:39:31<12:49:20,  3.33it/s]
 59%|█████▊    | 217878/371472 [6:39:32<12:33:30,  3.40it/s]
 59%|█████▊    | 217879/371472 [6:39:32<12:22:32,  3.45it/s]
 59%|█████▊    | 217880/371472 [6:39:32<12:03:58,  3.54it/s]
                                                            
{'loss': 2.8146, 'learning_rate': 4.723221788877157e-07, 'epoch': 9.38}
+
 59%|█████▊    | 217880/371472 [6:39:32<12:03:58,  3.54it/s]
 59%|█████▊    | 217881/371472 [6:39:32<11:44:11,  3.64it/s]
 59%|█████▊    | 217882/371472 [6:39:33<11:34:39,  3.69it/s]
 59%|█████▊    | 217883/371472 [6:39:33<11:40:18,  3.66it/s]
 59%|█████▊    | 217884/371472 [6:39:33<11:34:54,  3.68it/s]
 59%|█████▊    | 217885/371472 [6:39:34<13:04:04,  3.26it/s]
 59%|█████▊    | 217886/371472 [6:39:34<13:40:56,  3.12it/s]
 59%|█████▊    | 217887/371472 [6:39:34<13:11:33,  3.23it/s]
 59%|█████▊    | 217888/371472 [6:39:34<12:27:59,  3.42it/s]
 59%|█████▊    | 217889/371472 [6:39:35<12:23:16,  3.44it/s]
 59%|█████▊    | 217890/371472 [6:39:35<12:48:38,  3.33it/s]
 59%|█████▊    | 217891/371472 [6:39:35<13:22:12,  3.19it/s]
 59%|█████▊    | 217892/371472 [6:39:36<13:52:36,  3.07it/s]
 59%|█████▊    | 217893/371472 [6:39:36<14:09:22,  3.01it/s]
 59%|█████▊    | 217894/371472 [6:39:36<13:45:52,  3.10it/s]
 59%|█████▊    | 217895/371472 [6:39:37<13:24:15,  3.18it/s]
 59%|█████▊    | 217896/371472 [6:39:37<12:58:51,  3.29it/s]
 59%|█████▊    | 217897/371472 [6:39:37<13:11:18,  3.23it/s]
 59%|█████▊    | 217898/371472 [6:39:38<13:03:05,  3.27it/s]
 59%|█████▊    | 217899/371472 [6:39:38<12:43:12,  3.35it/s]
 59%|█████▊    | 217900/371472 [6:39:38<12:52:10,  3.31it/s]
                                                            
{'loss': 2.6604, 'learning_rate': 4.722736969122368e-07, 'epoch': 9.39}
+
 59%|█████▊    | 217900/371472 [6:39:38<12:52:10,  3.31it/s]
 59%|█████▊    | 217901/371472 [6:39:39<12:49:06,  3.33it/s]
 59%|█████▊    | 217902/371472 [6:39:39<12:57:12,  3.29it/s]
 59%|█████▊    | 217903/371472 [6:39:39<12:12:20,  3.49it/s]
 59%|█████▊    | 217904/371472 [6:39:39<12:39:28,  3.37it/s]
 59%|█████▊    | 217905/371472 [6:39:40<13:00:55,  3.28it/s]
 59%|█████▊    | 217906/371472 [6:39:40<12:42:27,  3.36it/s]
 59%|█████▊    | 217907/371472 [6:39:40<12:48:09,  3.33it/s]
 59%|█████▊    | 217908/371472 [6:39:41<13:25:49,  3.18it/s]
 59%|█████▊    | 217909/371472 [6:39:41<13:06:39,  3.25it/s]
 59%|█████▊    | 217910/371472 [6:39:41<12:51:13,  3.32it/s]
 59%|█████▊    | 217911/371472 [6:39:42<12:53:54,  3.31it/s]
 59%|█████▊    | 217912/371472 [6:39:42<12:32:31,  3.40it/s]
 59%|█████▊    | 217913/371472 [6:39:42<12:14:59,  3.48it/s]
 59%|█████▊    | 217914/371472 [6:39:42<12:30:44,  3.41it/s]
 59%|█████▊    | 217915/371472 [6:39:43<11:59:20,  3.56it/s]
 59%|█████▊    | 217916/371472 [6:39:43<11:45:57,  3.63it/s]
 59%|█████▊    | 217917/371472 [6:39:43<12:13:24,  3.49it/s]
 59%|█████▊    | 217918/371472 [6:39:43<12:12:46,  3.49it/s]
 59%|█████▊    | 217919/371472 [6:39:44<12:47:26,  3.33it/s]
 59%|█████▊    | 217920/371472 [6:39:44<13:00:07,  3.28it/s]
                                                            
{'loss': 2.7254, 'learning_rate': 4.722252149367579e-07, 'epoch': 9.39}
+
 59%|█████▊    | 217920/371472 [6:39:44<13:00:07,  3.28it/s]
 59%|█████▊    | 217921/371472 [6:39:44<12:51:26,  3.32it/s]
 59%|█████▊    | 217922/371472 [6:39:45<12:43:57,  3.35it/s]
 59%|█████▊    | 217923/371472 [6:39:45<12:25:45,  3.43it/s]
 59%|█████▊    | 217924/371472 [6:39:45<12:30:59,  3.41it/s]
 59%|█████▊    | 217925/371472 [6:39:46<12:27:05,  3.43it/s]
 59%|█████▊    | 217926/371472 [6:39:46<12:31:25,  3.41it/s]
 59%|█████▊    | 217927/371472 [6:39:46<13:04:53,  3.26it/s]
 59%|█████▊    | 217928/371472 [6:39:47<12:45:27,  3.34it/s]
 59%|█████▊    | 217929/371472 [6:39:47<12:16:46,  3.47it/s]
 59%|█████▊    | 217930/371472 [6:39:47<12:56:58,  3.29it/s]
 59%|█████▊    | 217931/371472 [6:39:47<13:10:52,  3.24it/s]
 59%|█████▊    | 217932/371472 [6:39:48<13:06:43,  3.25it/s]
 59%|█████▊    | 217933/371472 [6:39:48<12:53:31,  3.31it/s]
 59%|█████▊    | 217934/371472 [6:39:48<12:40:14,  3.37it/s]
 59%|█████▊    | 217935/371472 [6:39:49<12:31:05,  3.41it/s]
 59%|█████▊    | 217936/371472 [6:39:49<12:15:40,  3.48it/s]
 59%|█████▊    | 217937/371472 [6:39:49<12:18:35,  3.46it/s]
 59%|█████▊    | 217938/371472 [6:39:49<12:23:04,  3.44it/s]
 59%|█████▊    | 217939/371472 [6:39:50<12:00:55,  3.55it/s]
 59%|█████▊    | 217940/371472 [6:39:50<11:56:17,  3.57it/s]
                                                            
{'loss': 2.858, 'learning_rate': 4.72176732961279e-07, 'epoch': 9.39}
+
 59%|█████▊    | 217940/371472 [6:39:50<11:56:17,  3.57it/s]
 59%|█████▊    | 217941/371472 [6:39:50<12:07:39,  3.52it/s]
 59%|█████▊    | 217942/371472 [6:39:51<11:56:06,  3.57it/s]
 59%|█████▊    | 217943/371472 [6:39:51<12:48:27,  3.33it/s]
 59%|█████▊    | 217944/371472 [6:39:51<12:44:00,  3.35it/s]
 59%|█████▊    | 217945/371472 [6:39:51<12:27:00,  3.43it/s]
 59%|█████▊    | 217946/371472 [6:39:52<12:25:31,  3.43it/s]
 59%|█████▊    | 217947/371472 [6:39:52<12:57:49,  3.29it/s]
 59%|█████▊    | 217948/371472 [6:39:52<12:46:18,  3.34it/s]
 59%|█████▊    | 217949/371472 [6:39:53<12:51:02,  3.32it/s]
 59%|█████▊    | 217950/371472 [6:39:53<12:59:58,  3.28it/s]
 59%|█████▊    | 217951/371472 [6:39:53<12:23:26,  3.44it/s]
 59%|█████▊    | 217952/371472 [6:39:54<13:08:26,  3.25it/s]
 59%|█████▊    | 217953/371472 [6:39:54<13:01:05,  3.28it/s]
 59%|█████▊    | 217954/371472 [6:39:54<13:16:26,  3.21it/s]
 59%|█████▊    | 217955/371472 [6:39:55<12:40:09,  3.37it/s]
 59%|█████▊    | 217956/371472 [6:39:55<12:15:06,  3.48it/s]
 59%|█████▊    | 217957/371472 [6:39:55<12:28:51,  3.42it/s]
 59%|█████▊    | 217958/371472 [6:39:55<12:40:08,  3.37it/s]
 59%|█████▊    | 217959/371472 [6:39:56<12:56:28,  3.30it/s]
 59%|█████▊    | 217960/371472 [6:39:56<12:34:01,  3.39it/s]
                                                            
{'loss': 2.6999, 'learning_rate': 4.7212825098580017e-07, 'epoch': 9.39}
+
 59%|█████▊    | 217960/371472 [6:39:56<12:34:01,  3.39it/s]
 59%|█████▊    | 217961/371472 [6:39:56<12:34:55,  3.39it/s]
 59%|█████▊    | 217962/371472 [6:39:57<12:21:58,  3.45it/s]
 59%|█████▊    | 217963/371472 [6:39:57<13:38:03,  3.13it/s]
 59%|█████▊    | 217964/371472 [6:39:57<13:37:20,  3.13it/s]
 59%|█████▊    | 217965/371472 [6:39:58<13:49:43,  3.08it/s]
 59%|█████▊    | 217966/371472 [6:39:58<13:00:10,  3.28it/s]
 59%|█████▊    | 217967/371472 [6:39:58<12:52:25,  3.31it/s]
 59%|█████▊    | 217968/371472 [6:39:58<12:41:26,  3.36it/s]
 59%|█████▊    | 217969/371472 [6:39:59<12:17:27,  3.47it/s]
 59%|█████▊    | 217970/371472 [6:39:59<12:43:44,  3.35it/s]
 59%|█████▊    | 217971/371472 [6:39:59<12:27:22,  3.42it/s]
 59%|█████▊    | 217972/371472 [6:40:00<12:02:05,  3.54it/s]
 59%|█████▊    | 217973/371472 [6:40:00<11:44:41,  3.63it/s]
 59%|█████▊    | 217974/371472 [6:40:00<11:32:48,  3.69it/s]
 59%|█████▊    | 217975/371472 [6:40:00<11:40:20,  3.65it/s]
 59%|█████▊    | 217976/371472 [6:40:01<11:26:50,  3.72it/s]
 59%|█████▊    | 217977/371472 [6:40:01<11:40:24,  3.65it/s]
 59%|█████▊    | 217978/371472 [6:40:01<11:45:40,  3.63it/s]
 59%|█████▊    | 217979/371472 [6:40:01<11:48:59,  3.61it/s]
 59%|█████▊    | 217980/371472 [6:40:02<11:27:35,  3.72it/s]
                                                            
{'loss': 2.778, 'learning_rate': 4.7207976901032124e-07, 'epoch': 9.39}
+
 59%|█████▊    | 217980/371472 [6:40:02<11:27:35,  3.72it/s]
 59%|█████▊    | 217981/371472 [6:40:02<11:45:55,  3.62it/s]
 59%|█████▊    | 217982/371472 [6:40:02<11:51:52,  3.59it/s]
 59%|█████▊    | 217983/371472 [6:40:03<12:41:12,  3.36it/s]
 59%|█████▊    | 217984/371472 [6:40:03<12:19:41,  3.46it/s]
 59%|█████▊    | 217985/371472 [6:40:03<12:00:49,  3.55it/s]
 59%|█████▊    | 217986/371472 [6:40:03<11:51:15,  3.60it/s]
 59%|█████▊    | 217987/371472 [6:40:04<11:40:34,  3.65it/s]
 59%|█████▊    | 217988/371472 [6:40:04<11:38:29,  3.66it/s]
 59%|█████▊    | 217989/371472 [6:40:04<11:23:55,  3.74it/s]
 59%|█████▊    | 217990/371472 [6:40:04<11:32:08,  3.70it/s]
 59%|█████▊    | 217991/371472 [6:40:05<12:33:35,  3.39it/s]
 59%|█████▊    | 217992/371472 [6:40:05<13:07:38,  3.25it/s]
 59%|█████▊    | 217993/371472 [6:40:05<12:47:21,  3.33it/s]
 59%|█████▊    | 217994/371472 [6:40:06<12:12:07,  3.49it/s]
 59%|█████▊    | 217995/371472 [6:40:06<12:04:04,  3.53it/s]
 59%|█████▊    | 217996/371472 [6:40:06<12:41:57,  3.36it/s]
 59%|█████▊    | 217997/371472 [6:40:07<12:45:51,  3.34it/s]
 59%|█████▊    | 217998/371472 [6:40:07<12:49:56,  3.32it/s]
 59%|█████▊    | 217999/371472 [6:40:07<12:43:54,  3.35it/s]
 59%|█████▊    | 218000/371472 [6:40:08<12:53:46,  3.31it/s]
                                                            
{'loss': 2.7209, 'learning_rate': 4.7203128703484236e-07, 'epoch': 9.39}
+
 59%|█████▊    | 218000/371472 [6:40:08<12:53:46,  3.31it/s]
 59%|█████▊    | 218001/371472 [6:40:08<16:06:16,  2.65it/s]
 59%|█████▊    | 218002/371472 [6:40:08<14:58:17,  2.85it/s]
 59%|█████▊    | 218003/371472 [6:40:09<14:13:42,  3.00it/s]
 59%|█████▊    | 218004/371472 [6:40:09<13:21:22,  3.19it/s]
 59%|█████▊    | 218005/371472 [6:40:09<12:39:44,  3.37it/s]
 59%|█████▊    | 218006/371472 [6:40:09<12:34:27,  3.39it/s]
 59%|█████▊    | 218007/371472 [6:40:10<12:15:47,  3.48it/s]
 59%|█████▊    | 218008/371472 [6:40:10<12:02:30,  3.54it/s]
 59%|█████▊    | 218009/371472 [6:40:10<12:35:31,  3.39it/s]
 59%|█████▊    | 218010/371472 [6:40:11<12:12:19,  3.49it/s]
 59%|█████▊    | 218011/371472 [6:40:11<12:12:51,  3.49it/s]
 59%|█████▊    | 218012/371472 [6:40:11<12:36:20,  3.38it/s]
 59%|█████▊    | 218013/371472 [6:40:12<12:30:24,  3.41it/s]
 59%|█████▊    | 218014/371472 [6:40:12<12:57:19,  3.29it/s]
 59%|█████▊    | 218015/371472 [6:40:12<12:25:03,  3.43it/s]
 59%|█████▊    | 218016/371472 [6:40:12<12:07:21,  3.52it/s]
 59%|█████▊    | 218017/371472 [6:40:13<12:45:05,  3.34it/s]
 59%|█████▊    | 218018/371472 [6:40:13<12:34:12,  3.39it/s]
 59%|█████▊    | 218019/371472 [6:40:13<12:07:39,  3.51it/s]
 59%|█████▊    | 218020/371472 [6:40:14<11:55:13,  3.58it/s]
                                                            
{'loss': 2.7458, 'learning_rate': 4.7198280505936344e-07, 'epoch': 9.39}
+
 59%|█████▊    | 218020/371472 [6:40:14<11:55:13,  3.58it/s]
 59%|█████▊    | 218021/371472 [6:40:14<12:05:10,  3.53it/s]
 59%|█████▊    | 218022/371472 [6:40:14<11:47:18,  3.62it/s]
 59%|█████▊    | 218023/371472 [6:40:14<11:29:12,  3.71it/s]
 59%|█████▊    | 218024/371472 [6:40:15<11:49:26,  3.60it/s]
 59%|█████▊    | 218025/371472 [6:40:15<11:40:58,  3.65it/s]
 59%|█████▊    | 218026/371472 [6:40:15<11:33:42,  3.69it/s]
 59%|█████▊    | 218027/371472 [6:40:15<11:46:55,  3.62it/s]
 59%|█████▊    | 218028/371472 [6:40:16<11:43:30,  3.64it/s]
 59%|█████▊    | 218029/371472 [6:40:16<11:52:38,  3.59it/s]
 59%|█████▊    | 218030/371472 [6:40:16<11:59:39,  3.55it/s]
 59%|█████▊    | 218031/371472 [6:40:17<12:02:57,  3.54it/s]
 59%|█████▊    | 218032/371472 [6:40:17<12:06:14,  3.52it/s]
 59%|█████▊    | 218033/371472 [6:40:17<11:59:55,  3.55it/s]
 59%|█████▊    | 218034/371472 [6:40:17<12:38:56,  3.37it/s]
 59%|█████▊    | 218035/371472 [6:40:18<12:27:25,  3.42it/s]
 59%|█████▊    | 218036/371472 [6:40:18<12:33:16,  3.39it/s]
 59%|█████▊    | 218037/371472 [6:40:18<12:36:45,  3.38it/s]
 59%|█████▊    | 218038/371472 [6:40:19<12:28:59,  3.41it/s]
 59%|█████▊    | 218039/371472 [6:40:19<12:38:27,  3.37it/s]
 59%|█████▊    | 218040/371472 [6:40:19<12:21:48,  3.45it/s]
                                                            
{'loss': 2.749, 'learning_rate': 4.719343230838846e-07, 'epoch': 9.39}
+
 59%|█████▊    | 218040/371472 [6:40:19<12:21:48,  3.45it/s]
 59%|█████▊    | 218041/371472 [6:40:20<12:15:49,  3.48it/s]
 59%|█████▊    | 218042/371472 [6:40:20<12:22:24,  3.44it/s]
 59%|█████▊    | 218043/371472 [6:40:20<12:05:57,  3.52it/s]
 59%|█████▊    | 218044/371472 [6:40:20<13:03:10,  3.27it/s]
 59%|█████▊    | 218045/371472 [6:40:21<12:43:16,  3.35it/s]
 59%|█████▊    | 218046/371472 [6:40:21<12:31:53,  3.40it/s]
 59%|█████▊    | 218047/371472 [6:40:21<12:33:01,  3.40it/s]
 59%|█████▊    | 218048/371472 [6:40:22<12:07:55,  3.51it/s]
 59%|█████▊    | 218049/371472 [6:40:22<11:52:01,  3.59it/s]
 59%|█████▊    | 218050/371472 [6:40:22<13:05:24,  3.26it/s]
 59%|█████▊    | 218051/371472 [6:40:22<12:37:59,  3.37it/s]
 59%|█████▊    | 218052/371472 [6:40:23<12:42:46,  3.35it/s]
 59%|█████▊    | 218053/371472 [6:40:23<12:19:26,  3.46it/s]
 59%|█████▊    | 218054/371472 [6:40:23<13:10:17,  3.24it/s]
 59%|█████▊    | 218055/371472 [6:40:24<13:57:21,  3.05it/s]
 59%|█████▊    | 218056/371472 [6:40:24<13:18:20,  3.20it/s]
 59%|█████▊    | 218057/371472 [6:40:24<14:16:24,  2.99it/s]
 59%|█████▊    | 218058/371472 [6:40:25<13:45:35,  3.10it/s]
 59%|█████▊    | 218059/371472 [6:40:25<13:06:58,  3.25it/s]
 59%|█████▊    | 218060/371472 [6:40:25<12:40:05,  3.36it/s]
                                                            
{'loss': 2.7289, 'learning_rate': 4.7188584110840563e-07, 'epoch': 9.39}
+
 59%|█████▊    | 218060/371472 [6:40:25<12:40:05,  3.36it/s]
 59%|█████▊    | 218061/371472 [6:40:26<13:21:27,  3.19it/s]
 59%|█████▊    | 218062/371472 [6:40:26<13:16:34,  3.21it/s]
 59%|█████▊    | 218063/371472 [6:40:26<12:55:16,  3.30it/s]
 59%|█████▊    | 218064/371472 [6:40:26<12:45:59,  3.34it/s]
 59%|█████▊    | 218065/371472 [6:40:27<12:43:33,  3.35it/s]
 59%|█████▊    | 218066/371472 [6:40:27<12:30:52,  3.41it/s]
 59%|█████▊    | 218067/371472 [6:40:27<13:53:35,  3.07it/s]
 59%|█████▊    | 218068/371472 [6:40:28<13:12:05,  3.23it/s]
 59%|█████▊    | 218069/371472 [6:40:28<12:41:33,  3.36it/s]
 59%|█████▊    | 218070/371472 [6:40:28<12:44:36,  3.34it/s]
 59%|█████▊    | 218071/371472 [6:40:29<12:05:14,  3.53it/s]
 59%|█████▊    | 218072/371472 [6:40:29<12:52:51,  3.31it/s]
 59%|█████▊    | 218073/371472 [6:40:29<12:25:38,  3.43it/s]
 59%|█████▊    | 218074/371472 [6:40:29<12:09:59,  3.50it/s]
 59%|█████▊    | 218075/371472 [6:40:30<12:11:34,  3.49it/s]
 59%|█████▊    | 218076/371472 [6:40:30<12:29:20,  3.41it/s]
 59%|█████▊    | 218077/371472 [6:40:30<12:14:41,  3.48it/s]
 59%|█████▊    | 218078/371472 [6:40:31<12:59:58,  3.28it/s]
 59%|█████▊    | 218079/371472 [6:40:31<13:02:04,  3.27it/s]
 59%|█████▊    | 218080/371472 [6:40:31<12:38:13,  3.37it/s]
                                                            
{'loss': 2.732, 'learning_rate': 4.718373591329268e-07, 'epoch': 9.39}
+
 59%|█████▊    | 218080/371472 [6:40:31<12:38:13,  3.37it/s]
 59%|█████▊    | 218081/371472 [6:40:32<12:26:24,  3.43it/s]
 59%|█████▊    | 218082/371472 [6:40:32<11:49:25,  3.60it/s]
 59%|█████▊    | 218083/371472 [6:40:32<12:01:55,  3.54it/s]
 59%|█████▊    | 218084/371472 [6:40:32<11:48:01,  3.61it/s]
 59%|█████▊    | 218085/371472 [6:40:33<12:17:28,  3.47it/s]
 59%|█████▊    | 218086/371472 [6:40:33<11:44:02,  3.63it/s]
 59%|█████▊    | 218087/371472 [6:40:33<12:03:49,  3.53it/s]
 59%|█████▊    | 218088/371472 [6:40:33<11:58:31,  3.56it/s]
 59%|█████▊    | 218089/371472 [6:40:34<12:54:22,  3.30it/s]
 59%|█████▊    | 218090/371472 [6:40:34<12:31:50,  3.40it/s]
 59%|█████▊    | 218091/371472 [6:40:34<13:23:57,  3.18it/s]
 59%|█████▊    | 218092/371472 [6:40:35<13:30:13,  3.16it/s]
 59%|█████▊    | 218093/371472 [6:40:35<12:47:06,  3.33it/s]
 59%|█████▊    | 218094/371472 [6:40:35<12:26:42,  3.42it/s]
 59%|█████▊    | 218095/371472 [6:40:36<12:33:38,  3.39it/s]
 59%|█████▊    | 218096/371472 [6:40:36<13:17:21,  3.21it/s]
 59%|█████▊    | 218097/371472 [6:40:36<13:16:06,  3.21it/s]
 59%|█████▊    | 218098/371472 [6:40:37<12:48:46,  3.33it/s]
 59%|█████▊    | 218099/371472 [6:40:37<13:04:51,  3.26it/s]
 59%|█████▊    | 218100/371472 [6:40:37<12:40:39,  3.36it/s]
                                                            
{'loss': 2.7003, 'learning_rate': 4.717888771574479e-07, 'epoch': 9.39}
+
 59%|█████▊    | 218100/371472 [6:40:37<12:40:39,  3.36it/s]
 59%|█████▊    | 218101/371472 [6:40:37<12:53:47,  3.30it/s]
 59%|█████▊    | 218102/371472 [6:40:38<13:26:23,  3.17it/s]
 59%|█████▊    | 218103/371472 [6:40:38<13:31:09,  3.15it/s]
 59%|█████▊    | 218104/371472 [6:40:38<13:05:08,  3.26it/s]
 59%|█████▊    | 218105/371472 [6:40:39<12:56:44,  3.29it/s]
 59%|█████▊    | 218106/371472 [6:40:39<12:43:30,  3.35it/s]
 59%|█████▊    | 218107/371472 [6:40:39<12:34:32,  3.39it/s]
 59%|█████▊    | 218108/371472 [6:40:40<12:29:20,  3.41it/s]
 59%|█████▊    | 218109/371472 [6:40:40<13:23:20,  3.18it/s]
 59%|█████▊    | 218110/371472 [6:40:40<13:11:33,  3.23it/s]
 59%|█████▊    | 218111/371472 [6:40:40<12:31:06,  3.40it/s]
 59%|█████▊    | 218112/371472 [6:40:41<12:09:36,  3.50it/s]
 59%|█████▊    | 218113/371472 [6:40:41<12:07:59,  3.51it/s]
 59%|█████▊    | 218114/371472 [6:40:41<12:54:50,  3.30it/s]
 59%|█████▊    | 218115/371472 [6:40:42<12:57:10,  3.29it/s]
 59%|█████▊    | 218116/371472 [6:40:42<12:55:46,  3.29it/s]
 59%|█████▊    | 218117/371472 [6:40:42<12:51:10,  3.31it/s]
 59%|█████▊    | 218118/371472 [6:40:43<12:45:50,  3.34it/s]
 59%|█████▊    | 218119/371472 [6:40:43<12:34:50,  3.39it/s]
 59%|█████▊    | 218120/371472 [6:40:43<12:09:57,  3.50it/s]
                                                            
{'loss': 2.7173, 'learning_rate': 4.71740395181969e-07, 'epoch': 9.39}
+
 59%|█████▊    | 218120/371472 [6:40:43<12:09:57,  3.50it/s]
 59%|█████▊    | 218121/371472 [6:40:43<13:07:50,  3.24it/s]
 59%|█████▊    | 218122/371472 [6:40:44<12:57:30,  3.29it/s]
 59%|█████▊    | 218123/371472 [6:40:44<12:36:33,  3.38it/s]
 59%|█████▊    | 218124/371472 [6:40:44<12:19:59,  3.45it/s]
 59%|█████▊    | 218125/371472 [6:40:45<12:00:13,  3.55it/s]
 59%|█████▊    | 218126/371472 [6:40:45<11:47:25,  3.61it/s]
 59%|█████▊    | 218127/371472 [6:40:45<11:31:05,  3.70it/s]
 59%|█████▊    | 218128/371472 [6:40:45<11:26:56,  3.72it/s]
 59%|█████▊    | 218129/371472 [6:40:46<11:29:16,  3.71it/s]
 59%|█████▊    | 218130/371472 [6:40:46<14:00:02,  3.04it/s]
 59%|█████▊    | 218131/371472 [6:40:46<13:00:42,  3.27it/s]
 59%|█████▊    | 218132/371472 [6:40:47<13:36:29,  3.13it/s]
 59%|█████▊    | 218133/371472 [6:40:47<13:46:28,  3.09it/s]
 59%|█████▊    | 218134/371472 [6:40:47<13:15:39,  3.21it/s]
 59%|█████▊    | 218135/371472 [6:40:48<13:04:13,  3.26it/s]
 59%|█████▊    | 218136/371472 [6:40:48<13:53:18,  3.07it/s]
 59%|█████▊    | 218137/371472 [6:40:48<13:32:29,  3.15it/s]
 59%|█████▊    | 218138/371472 [6:40:49<13:01:51,  3.27it/s]
 59%|█████▊    | 218139/371472 [6:40:49<13:55:03,  3.06it/s]
 59%|█████▊    | 218140/371472 [6:40:49<14:22:51,  2.96it/s]
                                                            
{'loss': 2.7349, 'learning_rate': 4.716919132064901e-07, 'epoch': 9.4}
+
 59%|█████▊    | 218140/371472 [6:40:49<14:22:51,  2.96it/s]
 59%|█████▊    | 218141/371472 [6:40:50<14:21:10,  2.97it/s]
 59%|█████▊    | 218142/371472 [6:40:50<14:14:11,  2.99it/s]
 59%|█████▊    | 218143/371472 [6:40:50<13:33:06,  3.14it/s]
 59%|█████▊    | 218144/371472 [6:40:51<13:25:52,  3.17it/s]
 59%|█████▊    | 218145/371472 [6:40:51<12:54:03,  3.30it/s]
 59%|█████▊    | 218146/371472 [6:40:51<12:34:31,  3.39it/s]
 59%|█████▊    | 218147/371472 [6:40:51<12:20:16,  3.45it/s]
 59%|█████▊    | 218148/371472 [6:40:52<11:59:16,  3.55it/s]
 59%|█████▊    | 218149/371472 [6:40:52<11:44:16,  3.63it/s]
 59%|█████▊    | 218150/371472 [6:40:52<12:04:32,  3.53it/s]
 59%|█████▊    | 218151/371472 [6:40:53<11:51:39,  3.59it/s]
 59%|█████▊    | 218152/371472 [6:40:53<11:40:37,  3.65it/s]
 59%|█████▊    | 218153/371472 [6:40:53<11:33:20,  3.69it/s]
 59%|█████▊    | 218154/371472 [6:40:53<13:03:20,  3.26it/s]
 59%|█████▊    | 218155/371472 [6:40:54<12:57:12,  3.29it/s]
 59%|█████▊    | 218156/371472 [6:40:54<12:35:42,  3.38it/s]
 59%|█████▊    | 218157/371472 [6:40:54<12:19:17,  3.46it/s]
 59%|█████▊    | 218158/371472 [6:40:55<12:50:14,  3.32it/s]
 59%|█████▊    | 218159/371472 [6:40:55<12:54:34,  3.30it/s]
 59%|█████▊    | 218160/371472 [6:40:55<13:25:18,  3.17it/s]
                                                            
{'loss': 2.7273, 'learning_rate': 4.7164343123101125e-07, 'epoch': 9.4}
+
 59%|█████▊    | 218160/371472 [6:40:55<13:25:18,  3.17it/s]
 59%|█████▊    | 218161/371472 [6:40:56<13:33:50,  3.14it/s]
 59%|█████▊    | 218162/371472 [6:40:56<13:43:04,  3.10it/s]
 59%|█████▊    | 218163/371472 [6:40:56<13:27:36,  3.16it/s]
 59%|█████▊    | 218164/371472 [6:40:57<13:43:14,  3.10it/s]
 59%|█████▊    | 218165/371472 [6:40:57<14:00:32,  3.04it/s]
 59%|█████▊    | 218166/371472 [6:40:57<14:32:25,  2.93it/s]
 59%|█████▊    | 218167/371472 [6:40:58<14:15:03,  2.99it/s]
 59%|█████▊    | 218168/371472 [6:40:58<14:40:28,  2.90it/s]
 59%|█████▊    | 218169/371472 [6:40:58<13:51:25,  3.07it/s]
 59%|█████▊    | 218170/371472 [6:40:59<14:44:06,  2.89it/s]
 59%|█████▊    | 218171/371472 [6:40:59<13:46:06,  3.09it/s]
 59%|█████▊    | 218172/371472 [6:40:59<13:17:14,  3.20it/s]
 59%|█████▊    | 218173/371472 [6:40:59<13:20:43,  3.19it/s]
 59%|█████▊    | 218174/371472 [6:41:00<12:52:47,  3.31it/s]
 59%|█████▊    | 218175/371472 [6:41:00<12:17:56,  3.46it/s]
 59%|█████▊    | 218176/371472 [6:41:00<12:23:01,  3.44it/s]
 59%|█████▊    | 218177/371472 [6:41:01<12:12:00,  3.49it/s]
 59%|█████▊    | 218178/371472 [6:41:01<12:12:06,  3.49it/s]
 59%|█████▊    | 218179/371472 [6:41:01<12:16:00,  3.47it/s]
 59%|█████▊    | 218180/371472 [6:41:01<12:35:01,  3.38it/s]
                                                            
{'loss': 2.8421, 'learning_rate': 4.7159494925553227e-07, 'epoch': 9.4}
+
 59%|█████▊    | 218180/371472 [6:41:01<12:35:01,  3.38it/s]
 59%|█████▊    | 218181/371472 [6:41:02<12:50:36,  3.32it/s]
 59%|█████▊    | 218182/371472 [6:41:02<12:40:27,  3.36it/s]
 59%|█████▊    | 218183/371472 [6:41:02<12:17:23,  3.46it/s]
 59%|█████▊    | 218184/371472 [6:41:03<12:35:16,  3.38it/s]
 59%|█████▊    | 218185/371472 [6:41:03<13:58:55,  3.05it/s]
 59%|█████▊    | 218186/371472 [6:41:03<13:15:28,  3.21it/s]
 59%|█████▊    | 218187/371472 [6:41:04<13:01:25,  3.27it/s]
 59%|█████▊    | 218188/371472 [6:41:04<13:57:58,  3.05it/s]
 59%|█████▊    | 218189/371472 [6:41:04<13:11:32,  3.23it/s]
 59%|█████▊    | 218190/371472 [6:41:05<12:39:01,  3.37it/s]
 59%|█████▊    | 218191/371472 [6:41:05<12:40:52,  3.36it/s]
 59%|█████▊    | 218192/371472 [6:41:05<12:32:54,  3.39it/s]
 59%|█████▊    | 218193/371472 [6:41:05<12:35:43,  3.38it/s]
 59%|█████▊    | 218194/371472 [6:41:06<12:11:40,  3.49it/s]
 59%|█████▊    | 218195/371472 [6:41:06<12:11:34,  3.49it/s]
 59%|█████▊    | 218196/371472 [6:41:06<12:22:23,  3.44it/s]
 59%|█████▊    | 218197/371472 [6:41:07<12:02:30,  3.54it/s]
 59%|█���███▊    | 218198/371472 [6:41:07<12:11:08,  3.49it/s]
 59%|█████▊    | 218199/371472 [6:41:07<13:26:29,  3.17it/s]
 59%|█████▊    | 218200/371472 [6:41:08<12:58:23,  3.28it/s]
                                                            
{'loss': 2.7992, 'learning_rate': 4.7154646728005345e-07, 'epoch': 9.4}
+
 59%|█████▊    | 218200/371472 [6:41:08<12:58:23,  3.28it/s]
 59%|█████▊    | 218201/371472 [6:41:08<12:52:14,  3.31it/s]
 59%|█████▊    | 218202/371472 [6:41:08<12:28:05,  3.41it/s]
 59%|█████▊    | 218203/371472 [6:41:08<12:05:15,  3.52it/s]
 59%|█████▊    | 218204/371472 [6:41:09<11:51:40,  3.59it/s]
 59%|█████▊    | 218205/371472 [6:41:09<11:40:42,  3.65it/s]
 59%|█████▊    | 218206/371472 [6:41:09<11:51:51,  3.59it/s]
 59%|█████▊    | 218207/371472 [6:41:09<11:54:30,  3.58it/s]
 59%|█████▊    | 218208/371472 [6:41:10<11:57:16,  3.56it/s]
 59%|█████▊    | 218209/371472 [6:41:10<12:17:49,  3.46it/s]
 59%|█████▊    | 218210/371472 [6:41:10<12:29:21,  3.41it/s]
 59%|█████▊    | 218211/371472 [6:41:11<12:32:58,  3.39it/s]
 59%|█████▊    | 218212/371472 [6:41:11<12:06:55,  3.51it/s]
 59%|█████▊    | 218213/371472 [6:41:11<12:17:46,  3.46it/s]
 59%|█████▊    | 218214/371472 [6:41:11<11:59:34,  3.55it/s]
 59%|█████▊    | 218215/371472 [6:41:12<12:29:10,  3.41it/s]
 59%|█████▊    | 218216/371472 [6:41:12<12:40:49,  3.36it/s]
 59%|█████▊    | 218217/371472 [6:41:12<12:25:44,  3.43it/s]
 59%|█████▊    | 218218/371472 [6:41:13<12:18:51,  3.46it/s]
 59%|█████▊    | 218219/371472 [6:41:13<12:10:14,  3.50it/s]
 59%|█████▊    | 218220/371472 [6:41:13<12:17:01,  3.47it/s]
                                                            
{'loss': 2.7876, 'learning_rate': 4.714979853045745e-07, 'epoch': 9.4}
+
 59%|█████▊    | 218220/371472 [6:41:13<12:17:01,  3.47it/s]
 59%|█████▊    | 218221/371472 [6:41:14<12:22:22,  3.44it/s]
 59%|█████▊    | 218222/371472 [6:41:14<12:07:26,  3.51it/s]
 59%|█████▊    | 218223/371472 [6:41:14<12:13:34,  3.48it/s]
 59%|█████▊    | 218224/371472 [6:41:14<13:38:03,  3.12it/s]
 59%|█████▊    | 218225/371472 [6:41:15<13:18:58,  3.20it/s]
 59%|█████▊    | 218226/371472 [6:41:15<13:01:04,  3.27it/s]
 59%|█████▊    | 218227/371472 [6:41:15<12:23:56,  3.43it/s]
 59%|█████▊    | 218228/371472 [6:41:16<12:45:45,  3.34it/s]
 59%|█████▊    | 218229/371472 [6:41:16<12:19:33,  3.45it/s]
 59%|█████▊    | 218230/371472 [6:41:16<12:28:29,  3.41it/s]
 59%|█████▊    | 218231/371472 [6:41:17<12:21:49,  3.44it/s]
 59%|█████▊    | 218232/371472 [6:41:17<12:22:37,  3.44it/s]
 59%|█████▊    | 218233/371472 [6:41:17<11:58:04,  3.56it/s]
 59%|█████▊    | 218234/371472 [6:41:17<12:09:41,  3.50it/s]
 59%|█████▊    | 218235/371472 [6:41:18<12:49:42,  3.32it/s]
 59%|█████▊    | 218236/371472 [6:41:18<13:10:23,  3.23it/s]
 59%|█████▊    | 218237/371472 [6:41:18<12:57:10,  3.29it/s]
 59%|█████▊    | 218238/371472 [6:41:19<12:30:15,  3.40it/s]
 59%|█████▊    | 218239/371472 [6:41:19<12:14:44,  3.48it/s]
 59%|█████▉    | 218240/371472 [6:41:19<11:58:18,  3.56it/s]
                                                            
{'loss': 2.8685, 'learning_rate': 4.7144950332909565e-07, 'epoch': 9.4}
+
 59%|█████▉    | 218240/371472 [6:41:19<11:58:18,  3.56it/s]
 59%|█████▉    | 218241/371472 [6:41:19<11:47:00,  3.61it/s]
 59%|█████▉    | 218242/371472 [6:41:20<12:06:37,  3.51it/s]
 59%|█████▉    | 218243/371472 [6:41:20<13:02:10,  3.27it/s]
 59%|█████▉    | 218244/371472 [6:41:20<12:41:04,  3.36it/s]
 59%|█████▉    | 218245/371472 [6:41:21<12:20:19,  3.45it/s]
 59%|█████▉    | 218246/371472 [6:41:21<12:05:58,  3.52it/s]
 59%|█████▉    | 218247/371472 [6:41:21<13:23:57,  3.18it/s]
 59%|█████▉    | 218248/371472 [6:41:22<13:01:31,  3.27it/s]
 59%|█████▉    | 218249/371472 [6:41:22<13:19:18,  3.19it/s]
 59%|█████▉    | 218250/371472 [6:41:22<12:51:57,  3.31it/s]
 59%|█████▉    | 218251/371472 [6:41:22<12:41:04,  3.36it/s]
 59%|█████▉    | 218252/371472 [6:41:23<12:24:50,  3.43it/s]
 59%|█████▉    | 218253/371472 [6:41:23<11:51:45,  3.59it/s]
 59%|█████▉    | 218254/371472 [6:41:23<13:13:34,  3.22it/s]
 59%|█████▉    | 218255/371472 [6:41:24<12:49:19,  3.32it/s]
 59%|█████▉    | 218256/371472 [6:41:24<12:40:27,  3.36it/s]
 59%|█████▉    | 218257/371472 [6:41:24<12:11:28,  3.49it/s]
 59%|█████▉    | 218258/371472 [6:41:24<12:02:25,  3.53it/s]
 59%|█████▉    | 218259/371472 [6:41:25<12:40:13,  3.36it/s]
 59%|█████▉    | 218260/371472 [6:41:25<12:16:44,  3.47it/s]
                                                            
{'loss': 2.8043, 'learning_rate': 4.714010213536167e-07, 'epoch': 9.4}
+
 59%|█████▉    | 218260/371472 [6:41:25<12:16:44,  3.47it/s]
 59%|█████▉    | 218261/371472 [6:41:25<12:00:08,  3.55it/s]
 59%|█████▉    | 218262/371472 [6:41:26<12:25:40,  3.42it/s]
 59%|█████▉    | 218263/371472 [6:41:26<12:14:45,  3.48it/s]
 59%|█████▉    | 218264/371472 [6:41:26<12:01:49,  3.54it/s]
 59%|█████▉    | 218265/371472 [6:41:26<11:55:42,  3.57it/s]
 59%|█████▉    | 218266/371472 [6:41:27<11:52:00,  3.59it/s]
 59%|█████▉    | 218267/371472 [6:41:27<11:52:45,  3.58it/s]
 59%|█████▉    | 218268/371472 [6:41:27<12:20:22,  3.45it/s]
 59%|█████▉    | 218269/371472 [6:41:28<12:18:25,  3.46it/s]
 59%|█████▉    | 218270/371472 [6:41:28<12:17:00,  3.46it/s]
 59%|█████▉    | 218271/371472 [6:41:28<12:05:34,  3.52it/s]
 59%|█████▉    | 218272/371472 [6:41:29<12:50:57,  3.31it/s]
 59%|█████▉    | 218273/371472 [6:41:29<14:31:05,  2.93it/s]
 59%|█████▉    | 218274/371472 [6:41:29<13:44:47,  3.10it/s]
 59%|█████▉    | 218275/371472 [6:41:30<13:11:13,  3.23it/s]
 59%|█████▉    | 218276/371472 [6:41:30<13:05:49,  3.25it/s]
 59%|█████▉    | 218277/371472 [6:41:30<12:55:38,  3.29it/s]
 59%|█████▉    | 218278/371472 [6:41:30<12:56:59,  3.29it/s]
 59%|█████▉    | 218279/371472 [6:41:31<12:53:45,  3.30it/s]
 59%|█████▉    | 218280/371472 [6:41:31<14:01:05,  3.04it/s]
                                                            
{'loss': 2.7657, 'learning_rate': 4.713525393781379e-07, 'epoch': 9.4}
+
 59%|█████▉    | 218280/371472 [6:41:31<14:01:05,  3.04it/s]
 59%|█████▉    | 218281/371472 [6:41:31<13:45:25,  3.09it/s]
 59%|█████▉    | 218282/371472 [6:41:32<13:28:23,  3.16it/s]
 59%|█████▉    | 218283/371472 [6:41:32<12:48:10,  3.32it/s]
 59%|█████▉    | 218284/371472 [6:41:32<12:32:03,  3.39it/s]
 59%|█████▉    | 218285/371472 [6:41:33<12:18:37,  3.46it/s]
 59%|█████▉    | 218286/371472 [6:41:33<13:09:41,  3.23it/s]
 59%|█████▉    | 218287/371472 [6:41:33<13:29:55,  3.15it/s]
 59%|█████▉    | 218288/371472 [6:41:34<13:31:24,  3.15it/s]
 59%|█████▉    | 218289/371472 [6:41:34<13:07:19,  3.24it/s]
 59%|█████▉    | 218290/371472 [6:41:34<12:59:03,  3.28it/s]
 59%|█████▉    | 218291/371472 [6:41:34<13:15:55,  3.21it/s]
 59%|█████▉    | 218292/371472 [6:41:35<13:15:33,  3.21it/s]
 59%|█████▉    | 218293/371472 [6:41:35<12:33:06,  3.39it/s]
 59%|█████▉    | 218294/371472 [6:41:35<12:17:34,  3.46it/s]
 59%|█████▉    | 218295/371472 [6:41:36<13:17:23,  3.20it/s]
 59%|█████▉    | 218296/371472 [6:41:36<13:16:12,  3.21it/s]
 59%|█████▉    | 218297/371472 [6:41:36<12:44:33,  3.34it/s]
 59%|█████▉    | 218298/371472 [6:41:37<13:34:04,  3.14it/s]
 59%|█████▉    | 218299/371472 [6:41:37<13:13:04,  3.22it/s]
 59%|█████▉    | 218300/371472 [6:41:37<12:51:51,  3.31it/s]
                                                            
{'loss': 2.7798, 'learning_rate': 4.713040574026589e-07, 'epoch': 9.4}
+
 59%|█████▉    | 218300/371472 [6:41:37<12:51:51,  3.31it/s]
 59%|█████▉    | 218301/371472 [6:41:37<12:58:16,  3.28it/s]
 59%|█████▉    | 218302/371472 [6:41:38<12:56:07,  3.29it/s]
 59%|█████▉    | 218303/371472 [6:41:38<12:35:55,  3.38it/s]
 59%|█████▉    | 218304/371472 [6:41:38<12:39:08,  3.36it/s]
 59%|█████▉    | 218305/371472 [6:41:39<12:27:49,  3.41it/s]
 59%|█████▉    | 218306/371472 [6:41:39<12:28:56,  3.41it/s]
 59%|█████▉    | 218307/371472 [6:41:39<13:46:37,  3.09it/s]
 59%|█████▉    | 218308/371472 [6:41:40<13:09:49,  3.23it/s]
 59%|█████▉    | 218309/371472 [6:41:40<12:36:33,  3.37it/s]
 59%|█████▉    | 218310/371472 [6:41:40<12:18:50,  3.45it/s]
 59%|█████▉    | 218311/371472 [6:41:40<12:05:05,  3.52it/s]
 59%|█████▉    | 218312/371472 [6:41:41<12:27:18,  3.42it/s]
 59%|█████▉    | 218313/371472 [6:41:41<12:25:00,  3.43it/s]
 59%|█████▉    | 218314/371472 [6:41:41<12:35:27,  3.38it/s]
 59%|█████▉    | 218315/371472 [6:41:42<12:30:34,  3.40it/s]
 59%|█████▉    | 218316/371472 [6:41:42<12:26:04,  3.42it/s]
 59%|█████▉    | 218317/371472 [6:41:42<12:37:50,  3.37it/s]
 59%|█████▉    | 218318/371472 [6:41:43<12:29:37,  3.41it/s]
 59%|█████▉    | 218319/371472 [6:41:43<12:26:22,  3.42it/s]
 59%|█████▉    | 218320/371472 [6:41:43<13:03:25,  3.26it/s]
                                                            
{'loss': 2.7966, 'learning_rate': 4.712555754271801e-07, 'epoch': 9.4}
+
 59%|█████▉    | 218320/371472 [6:41:43<13:03:25,  3.26it/s]
 59%|█████▉    | 218321/371472 [6:41:43<12:44:13,  3.34it/s]
 59%|█████▉    | 218322/371472 [6:41:44<12:43:44,  3.34it/s]
 59%|█████▉    | 218323/371472 [6:41:44<13:20:04,  3.19it/s]
 59%|█████▉    | 218324/371472 [6:41:44<12:58:20,  3.28it/s]
 59%|█████▉    | 218325/371472 [6:41:45<13:04:39,  3.25it/s]
 59%|█████▉    | 218326/371472 [6:41:45<14:08:23,  3.01it/s]
 59%|█████▉    | 218327/371472 [6:41:45<13:37:54,  3.12it/s]
 59%|█████▉    | 218328/371472 [6:41:46<13:01:36,  3.27it/s]
 59%|█████▉    | 218329/371472 [6:41:46<13:07:29,  3.24it/s]
 59%|█████▉    | 218330/371472 [6:41:46<12:55:32,  3.29it/s]
 59%|█████▉    | 218331/371472 [6:41:47<12:40:26,  3.36it/s]
 59%|█████▉    | 218332/371472 [6:41:47<12:51:30,  3.31it/s]
 59%|█████▉    | 218333/371472 [6:41:47<12:46:04,  3.33it/s]
 59%|█████▉    | 218334/371472 [6:41:47<12:43:24,  3.34it/s]
 59%|█████▉    | 218335/371472 [6:41:48<13:05:19,  3.25it/s]
 59%|█████▉    | 218336/371472 [6:41:48<13:18:20,  3.20it/s]
 59%|█████▉    | 218337/371472 [6:41:48<13:15:06,  3.21it/s]
 59%|█████▉    | 218338/371472 [6:41:49<13:06:42,  3.24it/s]
 59%|█████▉    | 218339/371472 [6:41:49<13:14:33,  3.21it/s]
 59%|█████▉    | 218340/371472 [6:41:49<12:48:24,  3.32it/s]
                                                            
{'loss': 2.6801, 'learning_rate': 4.7120709345170116e-07, 'epoch': 9.4}
+
 59%|█████▉    | 218340/371472 [6:41:49<12:48:24,  3.32it/s]
 59%|█████▉    | 218341/371472 [6:41:50<12:37:39,  3.37it/s]
 59%|█████▉    | 218342/371472 [6:41:50<13:02:45,  3.26it/s]
 59%|█████▉    | 218343/371472 [6:41:50<12:43:29,  3.34it/s]
 59%|█████▉    | 218344/371472 [6:41:50<12:27:47,  3.41it/s]
 59%|█████▉    | 218345/371472 [6:41:51<12:15:46,  3.47it/s]
 59%|█████▉    | 218346/371472 [6:41:51<12:20:46,  3.45it/s]
 59%|█████▉    | 218347/371472 [6:41:51<12:39:26,  3.36it/s]
 59%|█████▉    | 218348/371472 [6:41:52<12:34:13,  3.38it/s]
 59%|█████▉    | 218349/371472 [6:41:52<12:28:32,  3.41it/s]
 59%|█████▉    | 218350/371472 [6:41:52<12:35:09,  3.38it/s]
 59%|█████▉    | 218351/371472 [6:41:53<12:27:09,  3.42it/s]
 59%|█████▉    | 218352/371472 [6:41:53<12:18:57,  3.45it/s]
 59%|█████▉    | 218353/371472 [6:41:53<12:59:58,  3.27it/s]
 59%|█████▉    | 218354/371472 [6:41:53<12:56:30,  3.29it/s]
 59%|█████▉    | 218355/371472 [6:41:54<12:45:34,  3.33it/s]
 59%|█████▉    | 218356/371472 [6:41:54<12:49:04,  3.32it/s]
 59%|█████▉    | 218357/371472 [6:41:54<12:47:45,  3.32it/s]
 59%|█████▉    | 218358/371472 [6:41:55<12:23:31,  3.43it/s]
 59%|█████▉    | 218359/371472 [6:41:55<12:16:49,  3.46it/s]
 59%|█████▉    | 218360/371472 [6:41:55<12:10:35,  3.49it/s]
                                                            
{'loss': 2.8211, 'learning_rate': 4.711586114762223e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218360/371472 [6:41:55<12:10:35,  3.49it/s]
 59%|█████▉    | 218361/371472 [6:41:55<12:19:32,  3.45it/s]
 59%|█████▉    | 218362/371472 [6:41:56<12:00:11,  3.54it/s]
 59%|█████▉    | 218363/371472 [6:41:56<12:16:32,  3.46it/s]
 59%|█████▉    | 218364/371472 [6:41:56<12:34:43,  3.38it/s]
 59%|█████▉    | 218365/371472 [6:41:57<12:22:40,  3.44it/s]
 59%|█████▉    | 218366/371472 [6:41:57<12:11:23,  3.49it/s]
 59%|█████▉    | 218367/371472 [6:41:57<13:38:58,  3.12it/s]
 59%|█████▉    | 218368/371472 [6:41:58<14:45:14,  2.88it/s]
 59%|█████▉    | 218369/371472 [6:41:58<14:38:10,  2.91it/s]
 59%|█████▉    | 218370/371472 [6:41:58<13:41:30,  3.11it/s]
 59%|█████▉    | 218371/371472 [6:41:59<13:12:10,  3.22it/s]
 59%|█████▉    | 218372/371472 [6:41:59<13:14:20,  3.21it/s]
 59%|█████▉    | 218373/371472 [6:41:59<12:49:25,  3.32it/s]
 59%|█████▉    | 218374/371472 [6:41:59<12:17:12,  3.46it/s]
 59%|█████▉    | 218375/371472 [6:42:00<12:01:37,  3.54it/s]
 59%|█████▉    | 218376/371472 [6:42:00<13:16:00,  3.21it/s]
 59%|█████▉    | 218377/371472 [6:42:00<12:42:35,  3.35it/s]
 59%|█████▉    | 218378/371472 [6:42:01<12:30:14,  3.40it/s]
 59%|█████▉    | 218379/371472 [6:42:01<12:32:48,  3.39it/s]
 59%|█████▉    | 218380/371472 [6:42:01<12:28:02,  3.41it/s]
                                                            
{'loss': 2.8401, 'learning_rate': 4.7111012950074336e-07, 'epoch': 9.41}
+
 59%|��████▉    | 218380/371472 [6:42:01<12:28:02,  3.41it/s]
 59%|█████▉    | 218381/371472 [6:42:02<12:24:06,  3.43it/s]
 59%|█████▉    | 218382/371472 [6:42:02<12:18:45,  3.45it/s]
 59%|█████▉    | 218383/371472 [6:42:02<12:13:47,  3.48it/s]
 59%|█████▉    | 218384/371472 [6:42:02<11:59:02,  3.55it/s]
 59%|█████▉    | 218385/371472 [6:42:03<11:56:24,  3.56it/s]
 59%|█████▉    | 218386/371472 [6:42:03<12:22:21,  3.44it/s]
 59%|█████▉    | 218387/371472 [6:42:03<12:11:32,  3.49it/s]
 59%|█████▉    | 218388/371472 [6:42:04<12:16:16,  3.47it/s]
 59%|█████▉    | 218389/371472 [6:42:04<12:16:23,  3.46it/s]
 59%|█████▉    | 218390/371472 [6:42:04<12:42:25,  3.35it/s]
 59%|█████▉    | 218391/371472 [6:42:04<13:27:58,  3.16it/s]
 59%|█████▉    | 218392/371472 [6:42:05<13:00:57,  3.27it/s]
 59%|█████▉    | 218393/371472 [6:42:05<12:46:30,  3.33it/s]
 59%|█████▉    | 218394/371472 [6:42:05<12:41:17,  3.35it/s]
 59%|█████▉    | 218395/371472 [6:42:06<13:09:32,  3.23it/s]
 59%|█████▉    | 218396/371472 [6:42:06<12:37:41,  3.37it/s]
 59%|█████▉    | 218397/371472 [6:42:06<12:31:43,  3.39it/s]
 59%|█████▉    | 218398/371472 [6:42:07<12:18:29,  3.45it/s]
 59%|█████▉    | 218399/371472 [6:42:07<12:19:44,  3.45it/s]
 59%|█████▉    | 218400/371472 [6:42:07<12:19:05,  3.45it/s]
                                                            
{'loss': 2.7618, 'learning_rate': 4.7106164752526443e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218400/371472 [6:42:07<12:19:05,  3.45it/s]
 59%|█████▉    | 218401/371472 [6:42:07<12:47:20,  3.32it/s]
 59%|█████▉    | 218402/371472 [6:42:08<12:37:10,  3.37it/s]
 59%|█████▉    | 218403/371472 [6:42:08<12:36:25,  3.37it/s]
 59%|█████▉    | 218404/371472 [6:42:08<12:09:12,  3.50it/s]
 59%|█████▉    | 218405/371472 [6:42:09<12:41:35,  3.35it/s]
 59%|█████▉    | 218406/371472 [6:42:09<13:28:47,  3.15it/s]
 59%|█████▉    | 218407/371472 [6:42:09<13:02:17,  3.26it/s]
 59%|█████▉    | 218408/371472 [6:42:10<12:36:47,  3.37it/s]
 59%|█████▉    | 218409/371472 [6:42:10<12:15:32,  3.47it/s]
 59%|█████▉    | 218410/371472 [6:42:10<12:04:54,  3.52it/s]
 59%|█████▉    | 218411/371472 [6:42:10<12:04:58,  3.52it/s]
 59%|█████▉    | 218412/371472 [6:42:11<12:20:15,  3.45it/s]
 59%|█████▉    | 218413/371472 [6:42:11<12:12:12,  3.48it/s]
 59%|█████▉    | 218414/371472 [6:42:11<12:02:27,  3.53it/s]
 59%|█████▉    | 218415/371472 [6:42:12<12:16:35,  3.46it/s]
 59%|█████▉    | 218416/371472 [6:42:12<12:11:24,  3.49it/s]
 59%|█████▉    | 218417/371472 [6:42:12<12:09:48,  3.50it/s]
 59%|█████▉    | 218418/371472 [6:42:12<12:46:36,  3.33it/s]
 59%|█████▉    | 218419/371472 [6:42:13<13:14:09,  3.21it/s]
 59%|█████▉    | 218420/371472 [6:42:13<12:55:10,  3.29it/s]
                                                            
{'loss': 2.7974, 'learning_rate': 4.710131655497856e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218420/371472 [6:42:13<12:55:10,  3.29it/s]
 59%|█████▉    | 218421/371472 [6:42:13<13:08:54,  3.23it/s]
 59%|█████▉    | 218422/371472 [6:42:14<12:34:59,  3.38it/s]
 59%|█████▉    | 218423/371472 [6:42:14<12:24:34,  3.43it/s]
 59%|█████▉    | 218424/371472 [6:42:14<12:45:20,  3.33it/s]
 59%|█████▉    | 218425/371472 [6:42:15<12:59:39,  3.27it/s]
 59%|█████▉    | 218426/371472 [6:42:15<12:53:10,  3.30it/s]
 59%|█████▉    | 218427/371472 [6:42:15<13:12:25,  3.22it/s]
 59%|█████▉    | 218428/371472 [6:42:15<12:33:10,  3.39it/s]
 59%|█████▉    | 218429/371472 [6:42:16<12:38:40,  3.36it/s]
 59%|█████▉    | 218430/371472 [6:42:16<12:25:19,  3.42it/s]
 59%|█████▉    | 218431/371472 [6:42:16<12:21:05,  3.44it/s]
 59%|█████▉    | 218432/371472 [6:42:17<12:21:56,  3.44it/s]
 59%|█████▉    | 218433/371472 [6:42:17<11:56:53,  3.56it/s]
 59%|█████▉    | 218434/371472 [6:42:17<12:35:18,  3.38it/s]
 59%|█████▉    | 218435/371472 [6:42:18<13:02:02,  3.26it/s]
 59%|█████▉    | 218436/371472 [6:42:18<13:01:57,  3.26it/s]
 59%|█████▉    | 218437/371472 [6:42:18<13:13:01,  3.22it/s]
 59%|█████▉    | 218438/371472 [6:42:19<14:10:30,  3.00it/s]
 59%|█████▉    | 218439/371472 [6:42:19<13:36:27,  3.12it/s]
 59%|█████▉    | 218440/371472 [6:42:19<13:18:26,  3.19it/s]
                                                            
{'loss': 2.6125, 'learning_rate': 4.709646835743066e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218440/371472 [6:42:19<13:18:26,  3.19it/s]
 59%|█████▉    | 218441/371472 [6:42:19<12:56:20,  3.29it/s]
 59%|█████▉    | 218442/371472 [6:42:20<13:18:29,  3.19it/s]
 59%|█████▉    | 218443/371472 [6:42:20<12:52:28,  3.30it/s]
 59%|█████▉    | 218444/371472 [6:42:20<12:33:17,  3.39it/s]
 59%|█████▉    | 218445/371472 [6:42:21<12:23:42,  3.43it/s]
 59%|█████▉    | 218446/371472 [6:42:21<12:18:32,  3.45it/s]
 59%|█████▉    | 218447/371472 [6:42:21<12:27:17,  3.41it/s]
 59%|█████▉    | 218448/371472 [6:42:21<13:08:43,  3.23it/s]
 59%|█████▉    | 218449/371472 [6:42:22<12:54:25,  3.29it/s]
 59%|█████▉    | 218450/371472 [6:42:22<12:32:06,  3.39it/s]
 59%|█████▉    | 218451/371472 [6:42:22<12:26:24,  3.42it/s]
 59%|█████▉    | 218452/371472 [6:42:23<12:47:37,  3.32it/s]
 59%|█████▉    | 218453/371472 [6:42:23<12:44:05,  3.34it/s]
 59%|█████▉    | 218454/371472 [6:42:23<12:22:37,  3.43it/s]
 59%|█████▉    | 218455/371472 [6:42:24<12:06:43,  3.51it/s]
 59%|█████▉    | 218456/371472 [6:42:24<14:08:12,  3.01it/s]
 59%|█████▉    | 218457/371472 [6:42:24<13:38:09,  3.12it/s]
 59%|█████▉    | 218458/371472 [6:42:25<14:06:09,  3.01it/s]
 59%|█████▉    | 218459/371472 [6:42:25<13:42:10,  3.10it/s]
 59%|█████▉    | 218460/371472 [6:42:25<13:32:46,  3.14it/s]
                                                            
{'loss': 2.8947, 'learning_rate': 4.709162015988278e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218460/371472 [6:42:25<13:32:46,  3.14it/s]
 59%|█████▉    | 218461/371472 [6:42:26<13:14:58,  3.21it/s]
 59%|█████▉    | 218462/371472 [6:42:26<12:38:23,  3.36it/s]
 59%|█████▉    | 218463/371472 [6:42:26<12:20:31,  3.44it/s]
 59%|█████▉    | 218464/371472 [6:42:26<12:05:21,  3.52it/s]
 59%|█████▉    | 218465/371472 [6:42:27<11:51:51,  3.58it/s]
 59%|█████▉    | 218466/371472 [6:42:27<12:38:07,  3.36it/s]
 59%|█████▉    | 218467/371472 [6:42:27<12:29:23,  3.40it/s]
 59%|█████▉    | 218468/371472 [6:42:28<12:32:12,  3.39it/s]
 59%|█████▉    | 218469/371472 [6:42:28<12:34:47,  3.38it/s]
 59%|█████▉    | 218470/371472 [6:42:28<12:27:11,  3.41it/s]
 59%|█████▉    | 218471/371472 [6:42:28<12:10:12,  3.49it/s]
 59%|█████▉    | 218472/371472 [6:42:29<12:39:52,  3.36it/s]
 59%|█████▉    | 218473/371472 [6:42:29<12:37:32,  3.37it/s]
 59%|█████▉    | 218474/371472 [6:42:29<12:58:47,  3.27it/s]
 59%|█████▉    | 218475/371472 [6:42:30<12:48:01,  3.32it/s]
 59%|█████▉    | 218476/371472 [6:42:30<12:38:53,  3.36it/s]
 59%|█████▉    | 218477/371472 [6:42:30<12:32:32,  3.39it/s]
 59%|█████▉    | 218478/371472 [6:42:30<12:20:09,  3.45it/s]
 59%|█████▉    | 218479/371472 [6:42:31<12:27:02,  3.41it/s]
 59%|█████▉    | 218480/371472 [6:42:31<13:11:12,  3.22it/s]
                                                            
{'loss': 2.765, 'learning_rate': 4.708677196233489e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218480/371472 [6:42:31<13:11:12,  3.22it/s]
 59%|█████▉    | 218481/371472 [6:42:31<12:49:37,  3.31it/s]
 59%|█████▉    | 218482/371472 [6:42:32<12:22:34,  3.43it/s]
 59%|█████▉    | 218483/371472 [6:42:32<12:32:10,  3.39it/s]
 59%|█████▉    | 218484/371472 [6:42:32<12:34:44,  3.38it/s]
 59%|█████▉    | 218485/371472 [6:42:33<12:43:03,  3.34it/s]
 59%|█████▉    | 218486/371472 [6:42:33<12:28:24,  3.41it/s]
 59%|█████▉    | 218487/371472 [6:42:33<12:18:45,  3.45it/s]
 59%|█████▉    | 218488/371472 [6:42:33<12:51:50,  3.30it/s]
 59%|█████▉    | 218489/371472 [6:42:34<12:47:59,  3.32it/s]
 59%|█████▉    | 218490/371472 [6:42:34<12:21:02,  3.44it/s]
 59%|█████▉    | 218491/371472 [6:42:34<12:16:40,  3.46it/s]
 59%|█████▉    | 218492/371472 [6:42:35<12:14:15,  3.47it/s]
 59%|█████▉    | 218493/371472 [6:42:35<12:18:49,  3.45it/s]
 59%|█████▉    | 218494/371472 [6:42:35<12:06:16,  3.51it/s]
 59%|█████▉    | 218495/371472 [6:42:35<12:05:11,  3.52it/s]
 59%|█████▉    | 218496/371472 [6:42:36<11:47:25,  3.60it/s]
 59%|█████▉    | 218497/371472 [6:42:36<11:36:02,  3.66it/s]
 59%|█████▉    | 218498/371472 [6:42:36<11:51:22,  3.58it/s]
 59%|█████▉    | 218499/371472 [6:42:37<12:13:35,  3.48it/s]
 59%|█████▉    | 218500/371472 [6:42:37<12:02:17,  3.53it/s]
                                                            
{'loss': 2.9609, 'learning_rate': 4.7081923764787e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218500/371472 [6:42:37<12:02:17,  3.53it/s]
 59%|█████▉    | 218501/371472 [6:42:37<12:21:38,  3.44it/s]
 59%|█████▉    | 218502/371472 [6:42:37<12:49:07,  3.31it/s]
 59%|█████��    | 218503/371472 [6:42:38<12:40:31,  3.35it/s]
 59%|█████▉    | 218504/371472 [6:42:38<12:30:38,  3.40it/s]
 59%|█████▉    | 218505/371472 [6:42:38<12:18:42,  3.45it/s]
 59%|█████▉    | 218506/371472 [6:42:39<12:13:13,  3.48it/s]
 59%|█████▉    | 218507/371472 [6:42:39<12:00:29,  3.54it/s]
 59%|█████▉    | 218508/371472 [6:42:39<12:29:09,  3.40it/s]
 59%|█████▉    | 218509/371472 [6:42:39<12:22:39,  3.43it/s]
 59%|█████▉    | 218510/371472 [6:42:40<12:39:18,  3.36it/s]
 59%|█████▉    | 218511/371472 [6:42:40<12:18:34,  3.45it/s]
 59%|█████▉    | 218512/371472 [6:42:40<12:17:46,  3.46it/s]
 59%|█████▉    | 218513/371472 [6:42:41<11:45:17,  3.61it/s]
 59%|█████▉    | 218514/371472 [6:42:41<12:38:15,  3.36it/s]
 59%|█████▉    | 218515/371472 [6:42:41<12:34:15,  3.38it/s]
 59%|█████▉    | 218516/371472 [6:42:42<12:21:45,  3.44it/s]
 59%|█████▉    | 218517/371472 [6:42:42<12:29:46,  3.40it/s]
 59%|█████▉    | 218518/371472 [6:42:42<12:41:52,  3.35it/s]
 59%|█████▉    | 218519/371472 [6:42:42<12:32:46,  3.39it/s]
 59%|█████▉    | 218520/371472 [6:42:43<13:07:16,  3.24it/s]
                                                            
{'loss': 2.7321, 'learning_rate': 4.7077075567239107e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218520/371472 [6:42:43<13:07:16,  3.24it/s]
 59%|█████▉    | 218521/371472 [6:42:43<13:45:21,  3.09it/s]
 59%|█████▉    | 218522/371472 [6:42:43<13:17:31,  3.20it/s]
 59%|█████▉    | 218523/371472 [6:42:44<13:22:15,  3.18it/s]
 59%|█████▉    | 218524/371472 [6:42:44<13:06:10,  3.24it/s]
 59%|█████▉    | 218525/371472 [6:42:44<13:24:01,  3.17it/s]
 59%|█████▉    | 218526/371472 [6:42:45<13:41:29,  3.10it/s]
 59%|█████▉    | 218527/371472 [6:42:45<13:07:09,  3.24it/s]
 59%|█████▉    | 218528/371472 [6:42:45<12:52:36,  3.30it/s]
 59%|█████▉    | 218529/371472 [6:42:46<13:02:40,  3.26it/s]
 59%|█████▉    | 218530/371472 [6:42:46<12:55:57,  3.28it/s]
 59%|█████▉    | 218531/371472 [6:42:46<13:17:08,  3.20it/s]
 59%|█████▉    | 218532/371472 [6:42:47<13:46:09,  3.09it/s]
 59%|█████▉    | 218533/371472 [6:42:47<14:10:11,  3.00it/s]
 59%|█████▉    | 218534/371472 [6:42:47<13:57:16,  3.04it/s]
 59%|█████▉    | 218535/371472 [6:42:48<13:44:11,  3.09it/s]
 59%|█████▉    | 218536/371472 [6:42:48<13:14:00,  3.21it/s]
 59%|█████▉    | 218537/371472 [6:42:48<13:37:25,  3.12it/s]
 59%|█████▉    | 218538/371472 [6:42:48<13:24:05,  3.17it/s]
 59%|█████▉    | 218539/371472 [6:42:49<13:13:54,  3.21it/s]
 59%|█████▉    | 218540/371472 [6:42:49<13:29:19,  3.15it/s]
                                                            
{'loss': 2.9344, 'learning_rate': 4.7072227369691225e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218540/371472 [6:42:49<13:29:19,  3.15it/s]
 59%|█████▉    | 218541/371472 [6:42:49<12:49:25,  3.31it/s]
 59%|█████▉    | 218542/371472 [6:42:50<13:15:59,  3.20it/s]
 59%|█████▉    | 218543/371472 [6:42:50<12:50:42,  3.31it/s]
 59%|█████▉    | 218544/371472 [6:42:50<12:30:09,  3.40it/s]
 59%|█████▉    | 218545/371472 [6:42:51<12:10:56,  3.49it/s]
 59%|█████▉    | 218546/371472 [6:42:51<11:49:48,  3.59it/s]
 59%|█████▉    | 218547/371472 [6:42:51<11:57:04,  3.55it/s]
 59%|█████▉    | 218548/371472 [6:42:51<11:47:01,  3.60it/s]
 59%|█████▉    | 218549/371472 [6:42:52<12:01:14,  3.53it/s]
 59%|█████▉    | 218550/371472 [6:42:52<12:04:05,  3.52it/s]
 59%|█████▉    | 218551/371472 [6:42:52<12:36:34,  3.37it/s]
 59%|█████▉    | 218552/371472 [6:42:53<12:30:56,  3.39it/s]
 59%|█████▉    | 218553/371472 [6:42:53<12:23:15,  3.43it/s]
 59%|█████▉    | 218554/371472 [6:42:53<12:36:15,  3.37it/s]
 59%|█████▉    | 218555/371472 [6:42:53<12:43:23,  3.34it/s]
 59%|█████▉    | 218556/371472 [6:42:54<12:33:04,  3.38it/s]
 59%|█████▉    | 218557/371472 [6:42:54<12:31:41,  3.39it/s]
 59%|█████▉    | 218558/371472 [6:42:54<12:26:52,  3.41it/s]
 59%|█████▉    | 218559/371472 [6:42:55<12:30:17,  3.40it/s]
 59%|█████▉    | 218560/371472 [6:42:55<12:38:03,  3.36it/s]
                                                            
{'loss': 2.8201, 'learning_rate': 4.7067379172143327e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218560/371472 [6:42:55<12:38:03,  3.36it/s]
 59%|█████▉    | 218561/371472 [6:42:55<13:13:16,  3.21it/s]
 59%|█████▉    | 218562/371472 [6:42:56<13:23:07,  3.17it/s]
 59%|█████▉    | 218563/371472 [6:42:56<13:09:24,  3.23it/s]
 59%|█████▉    | 218564/371472 [6:42:56<12:57:44,  3.28it/s]
 59%|█████▉    | 218565/371472 [6:42:56<12:51:25,  3.30it/s]
 59%|█████▉    | 218566/371472 [6:42:57<12:26:42,  3.41it/s]
 59%|█████▉    | 218567/371472 [6:42:57<12:48:49,  3.31it/s]
 59%|█████▉    | 218568/371472 [6:42:57<12:58:55,  3.27it/s]
 59%|█████▉    | 218569/371472 [6:42:58<13:03:42,  3.25it/s]
 59%|█████▉    | 218570/371472 [6:42:58<12:56:40,  3.28it/s]
 59%|█████▉    | 218571/371472 [6:42:58<12:59:09,  3.27it/s]
 59%|█████▉    | 218572/371472 [6:42:59<12:51:16,  3.30it/s]
 59%|█████▉    | 218573/371472 [6:42:59<12:45:22,  3.33it/s]
 59%|█████▉    | 218574/371472 [6:42:59<12:51:13,  3.30it/s]
 59%|█████▉    | 218575/371472 [6:42:59<12:36:50,  3.37it/s]
 59%|█████▉    | 218576/371472 [6:43:00<12:46:55,  3.32it/s]
 59%|█████▉    | 218577/371472 [6:43:00<13:48:09,  3.08it/s]
 59%|█████▉    | 218578/371472 [6:43:00<13:39:26,  3.11it/s]
 59%|█████▉    | 218579/371472 [6:43:01<13:14:03,  3.21it/s]
 59%|█████▉    | 218580/371472 [6:43:01<13:14:14,  3.21it/s]
                                                            
{'loss': 2.7655, 'learning_rate': 4.7062530974595444e-07, 'epoch': 9.41}
+
 59%|█████▉    | 218580/371472 [6:43:01<13:14:14,  3.21it/s]
 59%|█████▉    | 218581/371472 [6:43:01<12:58:58,  3.27it/s]
 59%|█████▉    | 218582/371472 [6:43:02<13:40:52,  3.10it/s]
 59%|█████▉    | 218583/371472 [6:43:02<13:16:47,  3.20it/s]
 59%|█████▉    | 218584/371472 [6:43:02<12:56:53,  3.28it/s]
 59%|█████▉    | 218585/371472 [6:43:03<13:09:15,  3.23it/s]
 59%|█████▉    | 218586/371472 [6:43:03<12:39:09,  3.36it/s]
 59%|█████▉    | 218587/371472 [6:43:03<12:32:38,  3.39it/s]
 59%|█████▉    | 218588/371472 [6:43:03<12:24:52,  3.42it/s]
 59%|█████▉    | 218589/371472 [6:43:04<12:04:43,  3.52it/s]
 59%|█████▉    | 218590/371472 [6:43:04<12:20:19,  3.44it/s]
 59%|█████▉    | 218591/371472 [6:43:04<12:22:15,  3.43it/s]
 59%|█████▉    | 218592/371472 [6:43:05<12:19:29,  3.45it/s]
 59%|█████▉    | 218593/371472 [6:43:05<12:16:50,  3.46it/s]
 59%|█████▉    | 218594/371472 [6:43:05<12:30:54,  3.39it/s]
 59%|█████▉    | 218595/371472 [6:43:06<12:43:59,  3.34it/s]
 59%|█████▉    | 218596/371472 [6:43:06<13:16:19,  3.20it/s]
 59%|█████▉    | 218597/371472 [6:43:06<13:06:56,  3.24it/s]
 59%|█████▉    | 218598/371472 [6:43:07<13:24:32,  3.17it/s]
 59%|█████▉    | 218599/371472 [6:43:07<13:00:08,  3.27it/s]
 59%|█████▉    | 218600/371472 [6:43:07<13:57:11,  3.04it/s]
                                                            
{'loss': 2.8186, 'learning_rate': 4.705768277704755e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218600/371472 [6:43:07<13:57:11,  3.04it/s]
 59%|█████▉    | 218601/371472 [6:43:07<13:55:44,  3.05it/s]
 59%|█████▉    | 218602/371472 [6:43:08<13:33:14,  3.13it/s]
 59%|█████▉    | 218603/371472 [6:43:08<13:30:09,  3.14it/s]
 59%|█████▉    | 218604/371472 [6:43:08<13:09:22,  3.23it/s]
 59%|█████▉    | 218605/371472 [6:43:09<12:56:04,  3.28it/s]
 59%|█████▉    | 218606/371472 [6:43:09<12:53:40,  3.29it/s]
 59%|█████▉    | 218607/371472 [6:43:09<13:49:48,  3.07it/s]
 59%|█████▉    | 218608/371472 [6:43:10<14:06:50,  3.01it/s]
 59%|█████▉    | 218609/371472 [6:43:10<14:38:58,  2.90it/s]
 59%|█████▉    | 218610/371472 [6:43:10<13:44:15,  3.09it/s]
 59%|█████▉    | 218611/371472 [6:43:11<13:12:10,  3.22it/s]
 59%|█████▉    | 218612/371472 [6:43:11<13:04:43,  3.25it/s]
 59%|█████▉    | 218613/371472 [6:43:11<13:21:37,  3.18it/s]
 59%|█████▉    | 218614/371472 [6:43:12<13:50:17,  3.07it/s]
 59%|█████▉    | 218615/371472 [6:43:12<13:35:40,  3.12it/s]
 59%|█████▉    | 218616/371472 [6:43:12<12:49:06,  3.31it/s]
 59%|█████▉    | 218617/371472 [6:43:12<12:39:46,  3.35it/s]
 59%|█████▉    | 218618/371472 [6:43:13<12:18:32,  3.45it/s]
 59%|█████▉    | 218619/371472 [6:43:13<12:34:47,  3.38it/s]
 59%|█████▉    | 218620/371472 [6:43:13<12:48:29,  3.31it/s]
                                                            
{'loss': 2.6848, 'learning_rate': 4.7052834579499664e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218620/371472 [6:43:13<12:48:29,  3.31it/s]
 59%|█████▉    | 218621/371472 [6:43:14<12:22:41,  3.43it/s]
 59%|█████▉    | 218622/371472 [6:43:14<12:12:15,  3.48it/s]
 59%|█████▉    | 218623/371472 [6:43:14<12:10:22,  3.49it/s]
 59%|█████▉    | 218624/371472 [6:43:14<12:04:15,  3.52it/s]
 59%|█████▉    | 218625/371472 [6:43:15<12:23:51,  3.42it/s]
 59%|█████▉    | 218626/371472 [6:43:15<12:48:48,  3.31it/s]
 59%|█████▉    | 218627/371472 [6:43:15<12:59:25,  3.27it/s]
 59%|█████▉    | 218628/371472 [6:43:16<12:44:28,  3.33it/s]
 59%|█████▉    | 218629/371472 [6:43:16<13:01:30,  3.26it/s]
 59%|█████▉    | 218630/371472 [6:43:16<12:30:13,  3.40it/s]
 59%|█████▉    | 218631/371472 [6:43:17<12:19:35,  3.44it/s]
 59%|█████▉    | 218632/371472 [6:43:17<12:23:45,  3.42it/s]
 59%|█████▉    | 218633/371472 [6:43:17<12:32:26,  3.39it/s]
 59%|█████▉    | 218634/371472 [6:43:18<13:22:38,  3.17it/s]
 59%|█████▉    | 218635/371472 [6:43:18<12:48:18,  3.32it/s]
 59%|█████▉    | 218636/371472 [6:43:18<13:34:18,  3.13it/s]
 59%|█████▉    | 218637/371472 [6:43:18<12:50:19,  3.31it/s]
 59%|█████▉    | 218638/371472 [6:43:19<13:25:45,  3.16it/s]
 59%|█████▉    | 218639/371472 [6:43:19<12:41:57,  3.34it/s]
 59%|█████▉    | 218640/371472 [6:43:19<12:07:30,  3.50it/s]
                                                            
{'loss': 2.8518, 'learning_rate': 4.704798638195177e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218640/371472 [6:43:19<12:07:30,  3.50it/s]
 59%|█████▉    | 218641/371472 [6:43:20<12:38:51,  3.36it/s]
 59%|█████▉    | 218642/371472 [6:43:20<12:31:18,  3.39it/s]
 59%|█████▉    | 218643/371472 [6:43:20<12:13:50,  3.47it/s]
 59%|█████▉    | 218644/371472 [6:43:20<12:16:33,  3.46it/s]
 59%|█████▉    | 218645/371472 [6:43:21<14:10:02,  3.00it/s]
 59%|█████▉    | 218646/371472 [6:43:21<13:24:31,  3.17it/s]
 59%|█████▉    | 218647/371472 [6:43:21<12:38:42,  3.36it/s]
 59%|█████▉    | 218648/371472 [6:43:22<12:36:11,  3.37it/s]
 59%|█████▉    | 218649/371472 [6:43:22<12:33:06,  3.38it/s]
 59%|█████▉    | 218650/371472 [6:43:22<12:21:11,  3.44it/s]
 59%|█████▉    | 218651/371472 [6:43:23<12:21:31,  3.43it/s]
 59%|█████▉    | 218652/371472 [6:43:23<12:08:30,  3.50it/s]
 59%|█████▉    | 218653/371472 [6:43:23<12:00:09,  3.54it/s]
 59%|█████▉    | 218654/371472 [6:43:23<11:51:19,  3.58it/s]
 59%|█████▉    | 218655/371472 [6:43:24<12:03:44,  3.52it/s]
 59%|█████▉    | 218656/371472 [6:43:24<12:59:42,  3.27it/s]
 59%|█████▉    | 218657/371472 [6:43:24<12:29:41,  3.40it/s]
 59%|█████▉    | 218658/371472 [6:43:25<12:06:52,  3.50it/s]
 59%|█████▉    | 218659/371472 [6:43:25<11:59:13,  3.54it/s]
 59%|█████▉    | 218660/371472 [6:43:25<12:01:40,  3.53it/s]
                                                            
{'loss': 2.8492, 'learning_rate': 4.704313818440389e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218660/371472 [6:43:25<12:01:40,  3.53it/s]
 59%|█████▉    | 218661/371472 [6:43:25<12:00:12,  3.54it/s]
 59%|█████▉    | 218662/371472 [6:43:26<11:52:18,  3.58it/s]
 59%|█████▉    | 218663/371472 [6:43:26<11:40:07,  3.64it/s]
 59%|█████▉    | 218664/371472 [6:43:26<11:31:56,  3.68it/s]
 59%|█████▉    | 218665/371472 [6:43:27<11:43:34,  3.62it/s]
 59%|█████▉    | 218666/371472 [6:43:27<11:48:17,  3.60it/s]
 59%|█████▉    | 218667/371472 [6:43:27<12:09:55,  3.49it/s]
 59%|█████▉    | 218668/371472 [6:43:27<12:19:15,  3.44it/s]
 59%|█████▉    | 218669/371472 [6:43:28<12:33:59,  3.38it/s]
 59%|█████▉    | 218670/371472 [6:43:28<12:24:16,  3.42it/s]
 59%|█████▉    | 218671/371472 [6:43:28<12:32:27,  3.38it/s]
 59%|█████▉    | 218672/371472 [6:43:29<12:24:46,  3.42it/s]
 59%|█████▉    | 218673/371472 [6:43:29<12:18:59,  3.45it/s]
 59%|█████▉    | 218674/371472 [6:43:29<12:11:58,  3.48it/s]
 59%|█████▉    | 218675/371472 [6:43:29<12:11:06,  3.48it/s]
 59%|█████▉    | 218676/371472 [6:43:30<12:21:40,  3.43it/s]
 59%|█████▉    | 218677/371472 [6:43:30<12:32:35,  3.38it/s]
 59%|█████▉    | 218678/371472 [6:43:30<12:33:33,  3.38it/s]
 59%|█████▉    | 218679/371472 [6:43:31<12:53:43,  3.29it/s]
 59%|█████▉    | 218680/371472 [6:43:31<12:58:15,  3.27it/s]
                                                            
{'loss': 2.8951, 'learning_rate': 4.7038289986855996e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218680/371472 [6:43:31<12:58:15,  3.27it/s]
 59%|█████▉    | 218681/371472 [6:43:31<13:35:24,  3.12it/s]
 59%|█████▉    | 218682/371472 [6:43:32<12:52:28,  3.30it/s]
 59%|█████▉    | 218683/371472 [6:43:32<12:58:24,  3.27it/s]
 59%|█████▉    | 218684/371472 [6:43:32<12:52:37,  3.30it/s]
 59%|█████▉    | 218685/371472 [6:43:32<12:18:02,  3.45it/s]
 59%|█████▉    | 218686/371472 [6:43:33<12:04:50,  3.51it/s]
 59%|█████▉    | 218687/371472 [6:43:33<11:58:57,  3.54it/s]
 59%|█████▉    | 218688/371472 [6:43:33<12:26:14,  3.41it/s]
 59%|█████▉    | 218689/371472 [6:43:34<13:28:33,  3.15it/s]
 59%|█████▉    | 218690/371472 [6:43:34<13:54:42,  3.05it/s]
 59%|█████▉    | 218691/371472 [6:43:34<13:21:29,  3.18it/s]
 59%|█████▉    | 218692/371472 [6:43:35<12:34:44,  3.37it/s]
 59%|█████▉    | 218693/371472 [6:43:35<12:36:35,  3.37it/s]
 59%|█████▉    | 218694/371472 [6:43:35<12:45:18,  3.33it/s]
 59%|█████▉    | 218695/371472 [6:43:36<12:39:35,  3.35it/s]
 59%|█████▉    | 218696/371472 [6:43:36<12:19:56,  3.44it/s]
 59%|█████▉    | 218697/371472 [6:43:36<12:22:25,  3.43it/s]
 59%|█████▉    | 218698/371472 [6:43:36<12:26:07,  3.41it/s]
 59%|█████▉    | 218699/371472 [6:43:37<12:28:55,  3.40it/s]
 59%|█████▉    | 218700/371472 [6:43:37<12:26:07,  3.41it/s]
                                                            
{'loss': 2.6785, 'learning_rate': 4.703344178930811e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218700/371472 [6:43:37<12:26:07,  3.41it/s]
 59%|█████▉    | 218701/371472 [6:43:37<12:46:39,  3.32it/s]
 59%|█████▉    | 218702/371472 [6:43:38<12:51:16,  3.30it/s]
 59%|█████▉    | 218703/371472 [6:43:38<14:40:47,  2.89it/s]
 59%|█████▉    | 218704/371472 [6:43:38<14:10:35,  2.99it/s]
 59%|█████▉    | 218705/371472 [6:43:39<13:53:42,  3.05it/s]
 59%|█████▉    | 218706/371472 [6:43:39<13:43:18,  3.09it/s]
 59%|█████▉    | 218707/371472 [6:43:39<13:33:27,  3.13it/s]
 59%|█████▉    | 218708/371472 [6:43:40<13:48:29,  3.07it/s]
 59%|█████▉    | 218709/371472 [6:43:40<13:42:24,  3.10it/s]
 59%|█████▉    | 218710/371472 [6:43:40<13:33:35,  3.13it/s]
 59%|█████▉    | 218711/371472 [6:43:41<13:00:04,  3.26it/s]
 59%|█████▉    | 218712/371472 [6:43:41<12:50:24,  3.30it/s]
 59%|█████▉    | 218713/371472 [6:43:41<12:48:24,  3.31it/s]
 59%|█████▉    | 218714/371472 [6:43:41<12:49:10,  3.31it/s]
 59%|█████▉    | 218715/371472 [6:43:42<13:17:43,  3.19it/s]
 59%|█████▉    | 218716/371472 [6:43:42<12:55:57,  3.28it/s]
 59%|█████▉    | 218717/371472 [6:43:42<13:14:21,  3.21it/s]
 59%|█████▉    | 218718/371472 [6:43:43<12:58:38,  3.27it/s]
 59%|█████▉    | 218719/371472 [6:43:43<13:01:33,  3.26it/s]
 59%|█████▉    | 218720/371472 [6:43:43<13:19:06,  3.19it/s]
                                                            
{'loss': 2.7418, 'learning_rate': 4.702859359176022e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218720/371472 [6:43:43<13:19:06,  3.19it/s]
 59%|█████▉    | 218721/371472 [6:43:44<13:25:51,  3.16it/s]
 59%|█████▉    | 218722/371472 [6:43:44<13:27:29,  3.15it/s]
 59%|█████▉    | 218723/371472 [6:43:44<12:49:19,  3.31it/s]
 59%|█████▉    | 218724/371472 [6:43:45<13:03:20,  3.25it/s]
 59%|█████▉    | 218725/371472 [6:43:45<12:48:09,  3.31it/s]
 59%|█████▉    | 218726/371472 [6:43:45<12:39:28,  3.35it/s]
 59%|█████▉    | 218727/371472 [6:43:45<12:39:40,  3.35it/s]
 59%|█████▉    | 218728/371472 [6:43:46<12:37:33,  3.36it/s]
 59%|█████▉    | 218729/371472 [6:43:46<12:34:31,  3.37it/s]
 59%|█████▉    | 218730/371472 [6:43:46<13:01:20,  3.26it/s]
 59%|█████▉    | 218731/371472 [6:43:47<13:16:14,  3.20it/s]
 59%|█████▉    | 218732/371472 [6:43:47<13:10:56,  3.22it/s]
 59%|█████▉    | 218733/371472 [6:43:47<12:59:23,  3.27it/s]
 59%|█████▉    | 218734/371472 [6:43:48<13:13:14,  3.21it/s]
 59%|█████▉    | 218735/371472 [6:43:48<13:03:33,  3.25it/s]
 59%|█████▉    | 218736/371472 [6:43:48<12:54:23,  3.29it/s]
 59%|█████▉    | 218737/371472 [6:43:49<13:02:31,  3.25it/s]
 59%|█████▉    | 218738/371472 [6:43:49<13:21:09,  3.18it/s]
 59%|█████▉    | 218739/371472 [6:43:49<12:50:54,  3.30it/s]
 59%|█████▉    | 218740/371472 [6:43:49<12:41:47,  3.34it/s]
                                                            
{'loss': 2.7158, 'learning_rate': 4.7023745394212333e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218740/371472 [6:43:49<12:41:47,  3.34it/s]
 59%|█████▉    | 218741/371472 [6:43:50<13:13:35,  3.21it/s]
 59%|█████▉    | 218742/371472 [6:43:50<13:14:34,  3.20it/s]
 59%|█████▉    | 218743/371472 [6:43:50<12:57:27,  3.27it/s]
 59%|█████▉    | 218744/371472 [6:43:51<12:57:48,  3.27it/s]
 59%|█████▉    | 218745/371472 [6:43:51<13:24:45,  3.16it/s]
 59%|█████▉    | 218746/371472 [6:43:51<13:17:34,  3.19it/s]
 59%|█████▉    | 218747/371472 [6:43:52<13:07:34,  3.23it/s]
 59%|█████▉    | 218748/371472 [6:43:52<13:14:50,  3.20it/s]
 59%|█████▉    | 218749/371472 [6:43:52<13:02:43,  3.25it/s]
 59%|█████▉    | 218750/371472 [6:43:53<12:50:36,  3.30it/s]
 59%|█████▉    | 218751/371472 [6:43:53<12:41:03,  3.34it/s]
 59%|█████▉    | 218752/371472 [6:43:53<12:16:22,  3.46it/s]
 59%|█████▉    | 218753/371472 [6:43:53<12:00:50,  3.53it/s]
 59%|█████▉    | 218754/371472 [6:43:54<11:58:20,  3.54it/s]
 59%|█████▉    | 218755/371472 [6:43:54<11:49:06,  3.59it/s]
 59%|█████▉    | 218756/371472 [6:43:54<12:04:39,  3.51it/s]
 59%|█████▉    | 218757/371472 [6:43:54<12:11:42,  3.48it/s]
 59%|█████▉    | 218758/371472 [6:43:55<12:09:19,  3.49it/s]
 59%|█████▉    | 218759/371472 [6:43:55<11:49:23,  3.59it/s]
 59%|█████▉    | 218760/371472 [6:43:55<12:03:09,  3.52it/s]
                                                            
{'loss': 2.7968, 'learning_rate': 4.7018897196664435e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218760/371472 [6:43:55<12:03:09,  3.52it/s]
 59%|█████▉    | 218761/371472 [6:43:56<12:03:45,  3.52it/s]
 59%|█████▉    | 218762/371472 [6:43:56<12:27:23,  3.41it/s]
 59%|█████▉    | 218763/371472 [6:43:56<12:29:43,  3.39it/s]
 59%|█████▉    | 218764/371472 [6:43:57<13:21:06,  3.18it/s]
 59%|█████▉    | 218765/371472 [6:43:57<13:17:19,  3.19it/s]
 59%|█████▉    | 218766/371472 [6:43:57<12:58:20,  3.27it/s]
 59%|█████▉    | 218767/371472 [6:43:57<12:47:23,  3.32it/s]
 59%|█████▉    | 218768/371472 [6:43:58<12:51:12,  3.30it/s]
 59%|█████▉    | 218769/371472 [6:43:58<12:31:08,  3.39it/s]
 59%|█████▉    | 218770/371472 [6:43:58<12:31:41,  3.39it/s]
 59%|█████▉    | 218771/371472 [6:43:59<12:15:52,  3.46it/s]
 59%|█████▉    | 218772/371472 [6:43:59<12:53:35,  3.29it/s]
 59%|█████▉    | 218773/371472 [6:43:59<13:18:58,  3.19it/s]
 59%|█████▉    | 218774/371472 [6:44:00<12:41:40,  3.34it/s]
 59%|█████▉    | 218775/371472 [6:44:00<12:49:57,  3.31it/s]
 59%|█████▉    | 218776/371472 [6:44:00<12:45:58,  3.32it/s]
 59%|█████▉    | 218777/371472 [6:44:00<12:36:51,  3.36it/s]
 59%|█████▉    | 218778/371472 [6:44:01<12:14:54,  3.46it/s]
 59%|█████▉    | 218779/371472 [6:44:01<13:32:39,  3.13it/s]
 59%|█████▉    | 218780/371472 [6:44:01<13:05:54,  3.24it/s]
                                                            
{'loss': 2.7231, 'learning_rate': 4.7014048999116553e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218780/371472 [6:44:01<13:05:54,  3.24it/s]
 59%|█████▉    | 218781/371472 [6:44:02<13:31:44,  3.14it/s]
 59%|█████▉    | 218782/371472 [6:44:02<13:42:08,  3.10it/s]
 59%|█████▉    | 218783/371472 [6:44:02<13:34:49,  3.12it/s]
 59%|█████▉    | 218784/371472 [6:44:03<13:12:19,  3.21it/s]
 59%|█████▉    | 218785/371472 [6:44:03<13:30:22,  3.14it/s]
 59%|█████▉    | 218786/371472 [6:44:03<14:25:46,  2.94it/s]
 59%|█████▉    | 218787/371472 [6:44:04<14:07:40,  3.00it/s]
 59%|█████▉    | 218788/371472 [6:44:04<14:28:37,  2.93it/s]
 59%|█████▉    | 218789/371472 [6:44:04<14:14:53,  2.98it/s]
 59%|█████▉    | 218790/371472 [6:44:05<13:44:37,  3.09it/s]
 59%|█████▉    | 218791/371472 [6:44:05<13:35:11,  3.12it/s]
 59%|█████▉    | 218792/371472 [6:44:05<13:37:03,  3.11it/s]
 59%|█████▉    | 218793/371472 [6:44:06<13:22:01,  3.17it/s]
 59%|█████▉    | 218794/371472 [6:44:06<13:13:18,  3.21it/s]
 59%|█████▉    | 218795/371472 [6:44:06<13:17:06,  3.19it/s]
 59%|█████▉    | 218796/371472 [6:44:07<13:19:30,  3.18it/s]
 59%|█████▉    | 218797/371472 [6:44:07<13:19:49,  3.18it/s]
 59%|█████▉    | 218798/371472 [6:44:07<13:10:51,  3.22it/s]
 59%|█████▉    | 218799/371472 [6:44:08<13:24:04,  3.16it/s]
 59%|█████▉    | 218800/371472 [6:44:08<13:12:07,  3.21it/s]
                                                            
{'loss': 2.6582, 'learning_rate': 4.700920080156866e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218800/371472 [6:44:08<13:12:07,  3.21it/s]
 59%|█████▉    | 218801/371472 [6:44:08<13:02:23,  3.25it/s]
 59%|█████▉    | 218802/371472 [6:44:08<12:38:38,  3.35it/s]
 59%|█████▉    | 218803/371472 [6:44:09<12:29:56,  3.39it/s]
 59%|█████▉    | 218804/371472 [6:44:09<12:28:24,  3.40it/s]
 59%|█████▉    | 218805/371472 [6:44:09<12:25:16,  3.41it/s]
 59%|█████▉    | 218806/371472 [6:44:10<12:16:54,  3.45it/s]
 59%|█████▉    | 218807/371472 [6:44:10<12:11:51,  3.48it/s]
 59%|█████▉    | 218808/371472 [6:44:10<12:09:58,  3.49it/s]
 59%|█████▉    | 218809/371472 [6:44:10<11:57:55,  3.54it/s]
 59%|█████▉    | 218810/371472 [6:44:11<12:08:58,  3.49it/s]
 59%|█���███▉    | 218811/371472 [6:44:11<12:30:42,  3.39it/s]
 59%|█████▉    | 218812/371472 [6:44:11<12:32:12,  3.38it/s]
 59%|█████▉    | 218813/371472 [6:44:12<12:15:27,  3.46it/s]
 59%|█████▉    | 218814/371472 [6:44:12<12:25:09,  3.41it/s]
 59%|█████▉    | 218815/371472 [6:44:12<11:58:23,  3.54it/s]
 59%|█████▉    | 218816/371472 [6:44:12<11:53:36,  3.57it/s]
 59%|█████▉    | 218817/371472 [6:44:13<12:20:31,  3.44it/s]
 59%|█████▉    | 218818/371472 [6:44:13<12:44:50,  3.33it/s]
 59%|█████▉    | 218819/371472 [6:44:13<13:09:53,  3.22it/s]
 59%|█████▉    | 218820/371472 [6:44:14<14:54:24,  2.84it/s]
                                                            
{'loss': 2.9426, 'learning_rate': 4.700435260402077e-07, 'epoch': 9.42}
+
 59%|█████▉    | 218820/371472 [6:44:14<14:54:24,  2.84it/s]
 59%|█████▉    | 218821/371472 [6:44:14<13:58:28,  3.03it/s]
 59%|█████▉    | 218822/371472 [6:44:14<13:25:17,  3.16it/s]
 59%|█████▉    | 218823/371472 [6:44:15<12:55:44,  3.28it/s]
 59%|█████▉    | 218824/371472 [6:44:15<12:48:53,  3.31it/s]
 59%|█████▉    | 218825/371472 [6:44:15<13:39:01,  3.11it/s]
 59%|█████▉    | 218826/371472 [6:44:16<13:10:55,  3.22it/s]
 59%|█████▉    | 218827/371472 [6:44:16<12:40:41,  3.34it/s]
 59%|█████▉    | 218828/371472 [6:44:16<13:34:40,  3.12it/s]
 59%|█████▉    | 218829/371472 [6:44:17<12:53:13,  3.29it/s]
 59%|█████▉    | 218830/371472 [6:44:17<12:39:16,  3.35it/s]
 59%|█████▉    | 218831/371472 [6:44:17<12:16:31,  3.45it/s]
 59%|█████▉    | 218832/371472 [6:44:17<12:26:56,  3.41it/s]
 59%|█████▉    | 218833/371472 [6:44:18<12:41:08,  3.34it/s]
 59%|█████▉    | 218834/371472 [6:44:18<12:51:56,  3.30it/s]
 59%|█████▉    | 218835/371472 [6:44:18<12:32:37,  3.38it/s]
 59%|█████▉    | 218836/371472 [6:44:19<12:48:27,  3.31it/s]
 59%|█████▉    | 218837/371472 [6:44:19<12:31:03,  3.39it/s]
 59%|█████▉    | 218838/371472 [6:44:19<12:30:53,  3.39it/s]
 59%|█████▉    | 218839/371472 [6:44:20<13:12:46,  3.21it/s]
 59%|█████▉    | 218840/371472 [6:44:20<13:00:08,  3.26it/s]
                                                            
{'loss': 2.7211, 'learning_rate': 4.699950440647288e-07, 'epoch': 9.43}
+
 59%|█████▉    | 218840/371472 [6:44:20<13:00:08,  3.26it/s]
 59%|█████▉    | 218841/371472 [6:44:20<12:26:38,  3.41it/s]
 59%|█████▉    | 218842/371472 [6:44:20<12:19:36,  3.44it/s]
 59%|█████▉    | 218843/371472 [6:44:21<11:59:49,  3.53it/s]
 59%|█████▉    | 218844/371472 [6:44:21<12:16:41,  3.45it/s]
 59%|█████▉    | 218845/371472 [6:44:21<12:16:36,  3.45it/s]
 59%|█████▉    | 218846/371472 [6:44:22<12:33:05,  3.38it/s]
 59%|█████▉    | 218847/371472 [6:44:22<12:19:59,  3.44it/s]
 59%|█████▉    | 218848/371472 [6:44:22<11:57:21,  3.55it/s]
 59%|█████▉    | 218849/371472 [6:44:22<12:11:16,  3.48it/s]
 59%|█████▉    | 218850/371472 [6:44:23<12:26:22,  3.41it/s]
 59%|█████▉    | 218851/371472 [6:44:23<12:11:13,  3.48it/s]
 59%|█████▉    | 218852/371472 [6:44:23<13:18:40,  3.18it/s]
 59%|█████▉    | 218853/371472 [6:44:24<12:45:32,  3.32it/s]
 59%|█████▉    | 218854/371472 [6:44:24<12:36:10,  3.36it/s]
 59%|█████▉    | 218855/371472 [6:44:24<12:47:55,  3.31it/s]
 59%|█████▉    | 218856/371472 [6:44:25<12:57:42,  3.27it/s]
 59%|█████▉    | 218857/371472 [6:44:25<12:36:57,  3.36it/s]
 59%|█████▉    | 218858/371472 [6:44:25<12:29:27,  3.39it/s]
 59%|█████▉    | 218859/371472 [6:44:25<12:39:36,  3.35it/s]
 59%|█████▉    | 218860/371472 [6:44:26<12:31:58,  3.38it/s]
                                                            
{'loss': 2.6901, 'learning_rate': 4.6994656208925e-07, 'epoch': 9.43}
+
 59%|█████▉    | 218860/371472 [6:44:26<12:31:58,  3.38it/s]
 59%|█████▉    | 218861/371472 [6:44:26<15:03:16,  2.82it/s]
 59%|█████▉    | 218862/371472 [6:44:26<14:00:17,  3.03it/s]
 59%|█████▉    | 218863/371472 [6:44:27<13:20:17,  3.18it/s]
 59%|█████▉    | 218864/371472 [6:44:27<13:20:46,  3.18it/s]
 59%|█████▉    | 218865/371472 [6:44:27<12:53:55,  3.29it/s]
 59%|█████▉    | 218866/371472 [6:44:28<13:02:20,  3.25it/s]
 59%|█████▉    | 218867/371472 [6:44:28<12:55:41,  3.28it/s]
 59%|█████▉    | 218868/371472 [6:44:28<12:52:20,  3.29it/s]
 59%|█████▉    | 218869/371472 [6:44:29<12:20:11,  3.44it/s]
 59%|█████▉    | 218870/371472 [6:44:29<12:11:16,  3.48it/s]
 59%|█████▉    | 218871/371472 [6:44:29<12:44:40,  3.33it/s]
 59%|█████▉    | 218872/371472 [6:44:29<12:26:37,  3.41it/s]
 59%|█████▉    | 218873/371472 [6:44:30<12:46:24,  3.32it/s]
 59%|█████▉    | 218874/371472 [6:44:30<12:32:36,  3.38it/s]
 59%|█████▉    | 218875/371472 [6:44:30<12:36:17,  3.36it/s]
 59%|█████▉    | 218876/371472 [6:44:31<12:24:58,  3.41it/s]
 59%|█████▉    | 218877/371472 [6:44:31<12:13:28,  3.47it/s]
 59%|█████▉    | 218878/371472 [6:44:31<12:00:03,  3.53it/s]
 59%|█████▉    | 218879/371472 [6:44:31<11:51:13,  3.58it/s]
 59%|█████▉    | 218880/371472 [6:44:32<11:42:25,  3.62it/s]
                                                            
{'loss': 2.6718, 'learning_rate': 4.69898080113771e-07, 'epoch': 9.43}
+
 59%|█████▉    | 218880/371472 [6:44:32<11:42:25,  3.62it/s]
 59%|█████▉    | 218881/371472 [6:44:32<11:40:22,  3.63it/s]
 59%|█████▉    | 218882/371472 [6:44:32<11:40:51,  3.63it/s]
 59%|█████▉    | 218883/371472 [6:44:32<11:40:07,  3.63it/s]
 59%|█████▉    | 218884/371472 [6:44:33<11:54:29,  3.56it/s]
 59%|█████▉    | 218885/371472 [6:44:33<12:14:31,  3.46it/s]
 59%|█████▉    | 218886/371472 [6:44:33<12:00:12,  3.53it/s]
 59%|█████▉    | 218887/371472 [6:44:34<11:44:46,  3.61it/s]
 59%|█████▉    | 218888/371472 [6:44:34<11:47:12,  3.60it/s]
 59%|█████▉    | 218889/371472 [6:44:34<12:20:33,  3.43it/s]
 59%|█████▉    | 218890/371472 [6:44:35<12:28:02,  3.40it/s]
 59%|█████▉    | 218891/371472 [6:44:35<12:14:30,  3.46it/s]
 59%|█████▉    | 218892/371472 [6:44:35<12:41:44,  3.34it/s]
 59%|█████▉    | 218893/371472 [6:44:35<12:59:18,  3.26it/s]
 59%|█████▉    | 218894/371472 [6:44:36<13:27:04,  3.15it/s]
 59%|█████▉    | 218895/371472 [6:44:36<13:10:20,  3.22it/s]
 59%|█████▉    | 218896/371472 [6:44:36<13:09:44,  3.22it/s]
 59%|█████▉    | 218897/371472 [6:44:37<13:16:48,  3.19it/s]
 59%|█████▉    | 218898/371472 [6:44:37<12:44:51,  3.32it/s]
 59%|█████▉    | 218899/371472 [6:44:37<12:43:17,  3.33it/s]
 59%|█████▉    | 218900/371472 [6:44:38<13:09:57,  3.22it/s]
                                                            
{'loss': 2.7882, 'learning_rate': 4.6984959813829217e-07, 'epoch': 9.43}
+
 59%|█████▉    | 218900/371472 [6:44:38<13:09:57,  3.22it/s]
 59%|█████▉    | 218901/371472 [6:44:38<12:48:27,  3.31it/s]
 59%|█████▉    | 218902/371472 [6:44:38<12:39:10,  3.35it/s]
 59%|█████▉    | 218903/371472 [6:44:38<12:26:22,  3.41it/s]
 59%|█████▉    | 218904/371472 [6:44:39<13:04:49,  3.24it/s]
 59%|█████▉    | 218905/371472 [6:44:39<12:48:50,  3.31it/s]
 59%|█████▉    | 218906/371472 [6:44:39<13:14:24,  3.20it/s]
 59%|█████▉    | 218907/371472 [6:44:40<14:05:12,  3.01it/s]
 59%|█████▉    | 218908/371472 [6:44:40<14:08:07,  3.00it/s]
 59%|█████▉    | 218909/371472 [6:44:40<13:29:20,  3.14it/s]
 59%|█████▉    | 218910/371472 [6:44:41<13:29:58,  3.14it/s]
 59%|█████▉    | 218911/371472 [6:44:41<13:13:56,  3.20it/s]
 59%|█████▉    | 218912/371472 [6:44:41<12:49:10,  3.31it/s]
 59%|█████▉    | 218913/371472 [6:44:42<12:42:44,  3.33it/s]
 59%|█████▉    | 218914/371472 [6:44:42<12:36:06,  3.36it/s]
 59%|█████▉    | 218915/371472 [6:44:42<12:20:47,  3.43it/s]
 59%|█████▉    | 218916/371472 [6:44:43<12:48:43,  3.31it/s]
 59%|█████▉    | 218917/371472 [6:44:43<12:30:28,  3.39it/s]
 59%|█████▉    | 218918/371472 [6:44:43<12:40:24,  3.34it/s]
 59%|█████▉    | 218919/371472 [6:44:43<12:36:27,  3.36it/s]
 59%|█████▉    | 218920/371472 [6:44:44<12:44:05,  3.33it/s]
                                                            
{'loss': 2.8221, 'learning_rate': 4.6980111616281324e-07, 'epoch': 9.43}
+
 59%|█████▉    | 218920/371472 [6:44:44<12:44:05,  3.33it/s]
 59%|█████▉    | 218921/371472 [6:44:44<12:40:18,  3.34it/s]
 59%|█████▉    | 218922/371472 [6:44:44<12:30:16,  3.39it/s]
 59%|█████▉    | 218923/371472 [6:44:45<12:45:42,  3.32it/s]
 59%|█████▉    | 218924/371472 [6:44:45<12:47:47,  3.31it/s]
 59%|█████▉    | 218925/371472 [6:44:45<13:05:42,  3.24it/s]
 59%|█████▉    | 218926/371472 [6:44:46<13:24:08,  3.16it/s]
 59%|█████▉    | 218927/371472 [6:44:46<13:03:03,  3.25it/s]
 59%|█████▉    | 218928/371472 [6:44:46<12:49:16,  3.30it/s]
 59%|█████▉    | 218929/371472 [6:44:46<13:00:05,  3.26it/s]
 59%|█████▉    | 218930/371472 [6:44:47<12:48:59,  3.31it/s]
 59%|█████▉    | 218931/371472 [6:44:47<12:47:13,  3.31it/s]
 59%|█████▉    | 218932/371472 [6:44:47<12:44:24,  3.33it/s]
 59%|█████▉    | 218933/371472 [6:44:48<13:04:13,  3.24it/s]
 59%|█████▉    | 218934/371472 [6:44:48<12:42:33,  3.33it/s]
 59%|█████▉    | 218935/371472 [6:44:48<12:24:09,  3.42it/s]
 59%|█████▉    | 218936/371472 [6:44:49<12:10:27,  3.48it/s]
 59%|█████▉    | 218937/371472 [6:44:49<12:19:14,  3.44it/s]
 59%|█████▉    | 218938/371472 [6:44:49<12:09:34,  3.48it/s]
 59%|█████▉    | 218939/371472 [6:44:49<12:33:20,  3.37it/s]
 59%|█████▉    | 218940/371472 [6:44:50<13:34:24,  3.12it/s]
                                                            
{'loss': 2.8577, 'learning_rate': 4.6975263418733426e-07, 'epoch': 9.43}
+
 59%|█████▉    | 218940/371472 [6:44:50<13:34:24,  3.12it/s]
 59%|█████▉    | 218941/371472 [6:44:50<13:40:11,  3.10it/s]
 59%|█████▉    | 218942/371472 [6:44:50<13:15:57,  3.19it/s]
 59%|█████▉    | 218943/371472 [6:44:51<12:50:31,  3.30it/s]
 59%|█████▉    | 218944/371472 [6:44:51<12:44:20,  3.33it/s]
 59%|█████▉    | 218945/371472 [6:44:51<12:37:37,  3.36it/s]
 59%|█████▉    | 218946/371472 [6:44:52<12:34:01,  3.37it/s]
 59%|█████▉    | 218947/371472 [6:44:52<13:00:12,  3.26it/s]
 59%|█████▉    | 218948/371472 [6:44:52<12:37:26,  3.36it/s]
 59%|█████▉    | 218949/371472 [6:44:53<13:12:40,  3.21it/s]
 59%|█████▉    | 218950/371472 [6:44:53<13:29:36,  3.14it/s]
 59%|█████▉    | 218951/371472 [6:44:53<13:13:28,  3.20it/s]
 59%|█████▉    | 218952/371472 [6:44:54<14:05:45,  3.01it/s]
 59%|█████▉    | 218953/371472 [6:44:54<13:36:33,  3.11it/s]
 59%|█████▉    | 218954/371472 [6:44:54<13:13:45,  3.20it/s]
 59%|█████▉    | 218955/371472 [6:44:54<12:44:00,  3.33it/s]
 59%|█████▉    | 218956/371472 [6:44:55<12:39:24,  3.35it/s]
 59%|█████▉    | 218957/371472 [6:44:55<12:19:41,  3.44it/s]
 59%|█████▉    | 218958/371472 [6:44:55<12:14:19,  3.46it/s]
 59%|█████▉    | 218959/371472 [6:44:56<12:13:49,  3.46it/s]
 59%|█████▉    | 218960/371472 [6:44:56<12:16:37,  3.45it/s]
                                                            
{'loss': 2.8326, 'learning_rate': 4.6970415221185544e-07, 'epoch': 9.43}
+
 59%|█████▉    | 218960/371472 [6:44:56<12:16:37,  3.45it/s]
 59%|█████▉    | 218961/371472 [6:44:56<12:27:03,  3.40it/s]
 59%|█████▉    | 218962/371472 [6:44:56<12:49:06,  3.30it/s]
 59%|█████▉    | 218963/371472 [6:44:57<12:21:15,  3.43it/s]
 59%|█████▉    | 218964/371472 [6:44:57<12:22:58,  3.42it/s]
 59%|█████▉    | 218965/371472 [6:44:57<12:36:34,  3.36it/s]
 59%|█████▉    | 218966/371472 [6:44:58<12:43:14,  3.33it/s]
 59%|█████▉    | 218967/371472 [6:44:58<12:48:09,  3.31it/s]
 59%|█████▉    | 218968/371472 [6:44:58<12:29:05,  3.39it/s]
 59%|█████▉    | 218969/371472 [6:44:59<12:53:15,  3.29it/s]
 59%|█████▉    | 218970/371472 [6:44:59<12:53:20,  3.29it/s]
 59%|█████▉    | 218971/371472 [6:44:59<13:19:27,  3.18it/s]
 59%|█████▉    | 218972/371472 [6:44:59<12:58:22,  3.27it/s]
 59%|█████▉    | 218973/371472 [6:45:00<12:44:25,  3.32it/s]
 59%|█████▉    | 218974/371472 [6:45:00<12:31:30,  3.38it/s]
 59%|█████▉    | 218975/371472 [6:45:00<12:29:03,  3.39it/s]
 59%|█████▉    | 218976/371472 [6:45:01<12:32:05,  3.38it/s]
 59%|█████▉    | 218977/371472 [6:45:01<12:19:42,  3.44it/s]
 59%|█████▉    | 218978/371472 [6:45:01<12:07:07,  3.50it/s]
 59%|█████▉    | 218979/371472 [6:45:02<12:36:30,  3.36it/s]
 59%|█████▉    | 218980/371472 [6:45:02<12:45:03,  3.32it/s]
                                                            
{'loss': 2.7996, 'learning_rate': 4.696556702363765e-07, 'epoch': 9.43}
+
 59%|█████▉    | 218980/371472 [6:45:02<12:45:03,  3.32it/s]
 59%|█████▉    | 218981/371472 [6:45:02<12:22:17,  3.42it/s]
 59%|█████▉    | 218982/371472 [6:45:02<13:07:38,  3.23it/s]
 59%|█████▉    | 218983/371472 [6:45:03<12:46:53,  3.31it/s]
 59%|█████▉    | 218984/371472 [6:45:03<12:36:19,  3.36it/s]
 59%|█████▉    | 218985/371472 [6:45:03<12:46:54,  3.31it/s]
 59%|█████▉    | 218986/371472 [6:45:04<12:57:44,  3.27it/s]
 59%|█████▉    | 218987/371472 [6:45:04<12:48:22,  3.31it/s]
 59%|█████▉    | 218988/371472 [6:45:04<12:40:14,  3.34it/s]
 59%|█████▉    | 218989/371472 [6:45:05<12:29:58,  3.39it/s]
 59%|█████▉    | 218990/371472 [6:45:05<13:44:38,  3.08it/s]
 59%|█████▉    | 218991/371472 [6:45:05<13:31:16,  3.13it/s]
 59%|█████▉    | 218992/371472 [6:45:05<13:02:21,  3.25it/s]
 59%|█████▉    | 218993/371472 [6:45:06<12:42:40,  3.33it/s]
 59%|█████▉    | 218994/371472 [6:45:06<12:23:22,  3.42it/s]
 59%|█████▉    | 218995/371472 [6:45:06<12:22:42,  3.42it/s]
 59%|█████▉    | 218996/371472 [6:45:07<12:39:45,  3.34it/s]
 59%|█████▉    | 218997/371472 [6:45:07<12:14:52,  3.46it/s]
 59%|█████▉    | 218998/371472 [6:45:07<13:03:21,  3.24it/s]
 59%|█████▉    | 218999/371472 [6:45:08<14:30:28,  2.92it/s]
 59%|█████▉    | 219000/371472 [6:45:08<13:41:40,  3.09it/s]
                                                            
{'loss': 2.8635, 'learning_rate': 4.6960718826089763e-07, 'epoch': 9.43}
+
 59%|█████▉    | 219000/371472 [6:45:08<13:41:40,  3.09it/s]
 59%|█████▉    | 219001/371472 [6:45:08<13:25:58,  3.15it/s]
 59%|█████▉    | 219002/371472 [6:45:09<13:09:29,  3.22it/s]
 59%|█████▉    | 219003/371472 [6:45:09<12:55:23,  3.28it/s]
 59%|█████▉    | 219004/371472 [6:45:09<12:23:26,  3.42it/s]
 59%|█████▉    | 219005/371472 [6:45:09<12:11:40,  3.47it/s]
 59%|█████▉    | 219006/371472 [6:45:10<12:18:45,  3.44it/s]
 59%|█████▉    | 219007/371472 [6:45:10<12:16:01,  3.45it/s]
 59%|█████▉    | 219008/371472 [6:45:10<12:02:11,  3.52it/s]
 59%|█████▉    | 219009/371472 [6:45:11<12:01:44,  3.52it/s]
 59%|█████▉    | 219010/371472 [6:45:11<13:07:49,  3.23it/s]
 59%|█████▉    | 219011/371472 [6:45:11<12:53:46,  3.28it/s]
 59%|█████▉    | 219012/371472 [6:45:11<12:19:21,  3.44it/s]
 59%|█████▉    | 219013/371472 [6:45:12<12:14:08,  3.46it/s]
 59%|█████▉    | 219014/371472 [6:45:12<12:15:47,  3.45it/s]
 59%|█████▉    | 219015/371472 [6:45:12<12:08:24,  3.49it/s]
 59%|█████▉    | 219016/371472 [6:45:13<12:08:29,  3.49it/s]
 59%|█████▉    | 219017/371472 [6:45:13<12:29:55,  3.39it/s]
 59%|█████▉    | 219018/371472 [6:45:13<12:17:28,  3.45it/s]
 59%|█████▉    | 219019/371472 [6:45:13<12:03:09,  3.51it/s]
 59%|█████▉    | 219020/371472 [6:45:14<12:06:53,  3.50it/s]
                                                            
{'loss': 2.7414, 'learning_rate': 4.695587062854187e-07, 'epoch': 9.43}
+
 59%|█████▉    | 219020/371472 [6:45:14<12:06:53,  3.50it/s]
 59%|█████▉    | 219021/371472 [6:45:14<12:47:43,  3.31it/s]
 59%|█████▉    | 219022/371472 [6:45:14<13:08:16,  3.22it/s]
 59%|█████▉    | 219023/371472 [6:45:15<12:51:30,  3.29it/s]
 59%|█████▉    | 219024/371472 [6:45:15<12:53:54,  3.28it/s]
 59%|█████▉    | 219025/371472 [6:45:15<13:29:10,  3.14it/s]
 59%|█████▉    | 219026/371472 [6:45:16<12:57:33,  3.27it/s]
 59%|█████▉    | 219027/371472 [6:45:16<12:43:25,  3.33it/s]
 59%|█████▉    | 219028/371472 [6:45:16<13:14:57,  3.20it/s]
 59%|█████▉    | 219029/371472 [6:45:17<12:46:36,  3.31it/s]
 59%|█████▉    | 219030/371472 [6:45:17<12:40:44,  3.34it/s]
 59%|█████▉    | 219031/371472 [6:45:17<12:48:10,  3.31it/s]
 59%|█████▉    | 219032/371472 [6:45:17<12:52:48,  3.29it/s]
 59%|█████▉    | 219033/371472 [6:45:18<13:03:20,  3.24it/s]
 59%|█████▉    | 219034/371472 [6:45:18<12:37:58,  3.35it/s]
 59%|█████▉    | 219035/371472 [6:45:18<12:45:54,  3.32it/s]
 59%|█████▉    | 219036/371472 [6:45:19<12:37:24,  3.35it/s]
 59%|█████▉    | 219037/371472 [6:45:19<12:44:20,  3.32it/s]
 59%|█████▉    | 219038/371472 [6:45:19<12:35:59,  3.36it/s]
 59%|█████▉    | 219039/371472 [6:45:20<12:30:09,  3.39it/s]
 59%|█████▉    | 219040/371472 [6:45:20<12:48:53,  3.30it/s]
                                                            
{'loss': 2.6799, 'learning_rate': 4.695102243099399e-07, 'epoch': 9.43}
+
 59%|█████▉    | 219040/371472 [6:45:20<12:48:53,  3.30it/s]
 59%|█████▉    | 219041/371472 [6:45:20<13:15:25,  3.19it/s]
 59%|█████▉    | 219042/371472 [6:45:21<13:22:12,  3.17it/s]
 59%|█████▉    | 219043/371472 [6:45:21<14:10:21,  2.99it/s]
 59%|█████▉    | 219044/371472 [6:45:21<13:39:26,  3.10it/s]
 59%|█████▉    | 219045/371472 [6:45:21<13:06:51,  3.23it/s]
 59%|█████▉    | 219046/371472 [6:45:22<13:45:33,  3.08it/s]
 59%|█████▉    | 219047/371472 [6:45:22<13:13:18,  3.20it/s]
 59%|█████▉    | 219048/371472 [6:45:22<12:39:36,  3.34it/s]
 59%|█████▉    | 219049/371472 [6:45:23<12:23:22,  3.42it/s]
 59%|█████▉    | 219050/371472 [6:45:23<12:25:41,  3.41it/s]
 59%|█████▉    | 219051/371472 [6:45:23<12:12:58,  3.47it/s]
 59%|█████▉    | 219052/371472 [6:45:24<12:05:41,  3.50it/s]
 59%|█████▉    | 219053/371472 [6:45:24<12:19:48,  3.43it/s]
 59%|█████▉    | 219054/371472 [6:45:24<12:11:39,  3.47it/s]
 59%|█████▉    | 219055/371472 [6:45:24<12:46:16,  3.32it/s]
 59%|█████▉    | 219056/371472 [6:45:25<12:33:45,  3.37it/s]
 59%|█████▉    | 219057/371472 [6:45:25<13:00:22,  3.26it/s]
 59%|█████▉    | 219058/371472 [6:45:25<12:30:19,  3.39it/s]
 59%|█████▉    | 219059/371472 [6:45:26<12:22:41,  3.42it/s]
 59%|█████▉    | 219060/371472 [6:45:26<12:44:42,  3.32it/s]
                                                            
{'loss': 2.7515, 'learning_rate': 4.6946174233446095e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219060/371472 [6:45:26<12:44:42,  3.32it/s]
 59%|█████▉    | 219061/371472 [6:45:26<12:39:17,  3.35it/s]
 59%|█████▉    | 219062/371472 [6:45:27<13:05:01,  3.24it/s]
 59%|█████▉    | 219063/371472 [6:45:27<12:44:01,  3.32it/s]
 59%|█████▉    | 219064/371472 [6:45:27<12:30:36,  3.38it/s]
 59%|█████▉    | 219065/371472 [6:45:27<12:17:28,  3.44it/s]
 59%|█████▉    | 219066/371472 [6:45:28<12:44:09,  3.32it/s]
 59%|█████▉    | 219067/371472 [6:45:28<12:30:13,  3.39it/s]
 59%|█████▉    | 219068/371472 [6:45:28<12:13:51,  3.46it/s]
 59%|█████▉    | 219069/371472 [6:45:29<12:25:04,  3.41it/s]
 59%|█████▉    | 219070/371472 [6:45:29<12:38:29,  3.35it/s]
 59%|█████▉    | 219071/371472 [6:45:29<12:21:43,  3.42it/s]
 59%|█████▉    | 219072/371472 [6:45:29<12:13:36,  3.46it/s]
 59%|█████▉    | 219073/371472 [6:45:30<11:58:28,  3.54it/s]
 59%|█████▉    | 219074/371472 [6:45:30<11:53:13,  3.56it/s]
 59%|█████▉    | 219075/371472 [6:45:30<11:57:08,  3.54it/s]
 59%|█████▉    | 219076/371472 [6:45:31<11:54:20,  3.56it/s]
 59%|█████▉    | 219077/371472 [6:45:31<11:46:43,  3.59it/s]
 59%|█████▉    | 219078/371472 [6:45:31<12:01:48,  3.52it/s]
 59%|█████▉    | 219079/371472 [6:45:31<12:13:38,  3.46it/s]
 59%|█████▉    | 219080/371472 [6:45:32<12:10:16,  3.48it/s]
                                                            
{'loss': 2.869, 'learning_rate': 4.694132603589821e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219080/371472 [6:45:32<12:10:16,  3.48it/s]
 59%|█████▉    | 219081/371472 [6:45:32<13:34:26,  3.12it/s]
 59%|█████▉    | 219082/371472 [6:45:32<13:43:48,  3.08it/s]
 59%|█████▉    | 219083/371472 [6:45:33<13:08:48,  3.22it/s]
 59%|█████▉    | 219084/371472 [6:45:33<13:32:33,  3.13it/s]
 59%|█████▉    | 219085/371472 [6:45:33<14:21:26,  2.95it/s]
 59%|█████▉    | 219086/371472 [6:45:34<13:54:01,  3.05it/s]
 59%|█████▉    | 219087/371472 [6:45:34<13:16:25,  3.19it/s]
 59%|█████▉    | 219088/371472 [6:45:34<14:03:24,  3.01it/s]
 59%|█████▉    | 219089/371472 [6:45:35<13:26:05,  3.15it/s]
 59%|█████▉    | 219090/371472 [6:45:35<13:48:58,  3.06it/s]
 59%|█████▉    | 219091/371472 [6:45:35<13:14:30,  3.20it/s]
 59%|█████▉    | 219092/371472 [6:45:36<12:47:34,  3.31it/s]
 59%|█████▉    | 219093/371472 [6:45:36<13:03:08,  3.24it/s]
 59%|█████▉    | 219094/371472 [6:45:36<13:26:52,  3.15it/s]
 59%|█████▉    | 219095/371472 [6:45:37<13:43:15,  3.08it/s]
 59%|█████▉    | 219096/371472 [6:45:37<13:07:10,  3.23it/s]
 59%|█████▉    | 219097/371472 [6:45:37<14:03:16,  3.01it/s]
 59%|█████▉    | 219098/371472 [6:45:38<13:45:20,  3.08it/s]
 59%|█████▉    | 219099/371472 [6:45:38<13:16:24,  3.19it/s]
 59%|█████▉    | 219100/371472 [6:45:38<12:49:56,  3.30it/s]
                                                            
{'loss': 2.6511, 'learning_rate': 4.6936477838350315e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219100/371472 [6:45:38<12:49:56,  3.30it/s]
 59%|█████▉    | 219101/371472 [6:45:38<12:37:07,  3.35it/s]
 59%|█████▉    | 219102/371472 [6:45:39<12:42:09,  3.33it/s]
 59%|█████▉    | 219103/371472 [6:45:39<12:45:47,  3.32it/s]
 59%|█████▉    | 219104/371472 [6:45:39<12:53:27,  3.28it/s]
 59%|█████▉    | 219105/371472 [6:45:40<12:56:16,  3.27it/s]
 59%|█████▉    | 219106/371472 [6:45:40<12:39:56,  3.34it/s]
 59%|█████▉    | 219107/371472 [6:45:40<12:42:17,  3.33it/s]
 59%|█████▉    | 219108/371472 [6:45:41<12:22:49,  3.42it/s]
 59%|█████▉    | 219109/371472 [6:45:41<12:20:23,  3.43it/s]
 59%|█████▉    | 219110/371472 [6:45:41<12:01:18,  3.52it/s]
 59%|█████▉    | 219111/371472 [6:45:41<11:49:50,  3.58it/s]
 59%|█████▉    | 219112/371472 [6:45:42<12:25:53,  3.40it/s]
 59%|█████▉    | 219113/371472 [6:45:42<12:22:54,  3.42it/s]
 59%|█████▉    | 219114/371472 [6:45:42<12:26:07,  3.40it/s]
 59%|█████▉    | 219115/371472 [6:45:43<12:43:48,  3.32it/s]
 59%|█████▉    | 219116/371472 [6:45:43<12:16:19,  3.45it/s]
 59%|█████▉    | 219117/371472 [6:45:43<12:33:36,  3.37it/s]
 59%|█████▉    | 219118/371472 [6:45:43<12:29:02,  3.39it/s]
 59%|█████▉    | 219119/371472 [6:45:44<13:16:14,  3.19it/s]
 59%|█████▉    | 219120/371472 [6:45:44<12:41:53,  3.33it/s]
                                                            
{'loss': 2.8963, 'learning_rate': 4.6931629640802433e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219120/371472 [6:45:44<12:41:53,  3.33it/s]
 59%|█████▉    | 219121/371472 [6:45:44<12:11:36,  3.47it/s]
 59%|█████▉    | 219122/371472 [6:45:45<11:57:24,  3.54it/s]
 59%|█████▉    | 219123/371472 [6:45:45<12:18:40,  3.44it/s]
 59%|█████▉    | 219124/371472 [6:45:45<12:15:50,  3.45it/s]
 59%|█████▉    | 219125/371472 [6:45:46<14:07:25,  3.00it/s]
 59%|█████▉    | 219126/371472 [6:45:46<13:29:19,  3.14it/s]
 59%|█████▉    | 219127/371472 [6:45:46<13:38:38,  3.10it/s]
 59%|█████▉    | 219128/371472 [6:45:47<14:01:16,  3.02it/s]
 59%|█████▉    | 219129/371472 [6:45:47<14:24:20,  2.94it/s]
 59%|█████▉    | 219130/371472 [6:45:47<13:46:18,  3.07it/s]
 59%|█████▉    | 219131/371472 [6:45:48<13:31:48,  3.13it/s]
 59%|█████▉    | 219132/371472 [6:45:48<12:49:23,  3.30it/s]
 59%|█████▉    | 219133/371472 [6:45:48<12:48:19,  3.30it/s]
 59%|█████▉    | 219134/371472 [6:45:48<12:24:04,  3.41it/s]
 59%|█████▉    | 219135/371472 [6:45:49<11:45:45,  3.60it/s]
 59%|█████▉    | 219136/371472 [6:45:49<11:49:12,  3.58it/s]
 59%|█████▉    | 219137/371472 [6:45:49<11:49:50,  3.58it/s]
 59%|█████▉    | 219138/371472 [6:45:49<11:42:40,  3.61it/s]
 59%|█████▉    | 219139/371472 [6:45:50<11:40:18,  3.63it/s]
 59%|█████▉    | 219140/371472 [6:45:50<11:46:27,  3.59it/s]
                                                            
{'loss': 2.5918, 'learning_rate': 4.692678144325454e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219140/371472 [6:45:50<11:46:27,  3.59it/s]
 59%|█████▉    | 219141/371472 [6:45:50<11:33:33,  3.66it/s]
 59%|█████▉    | 219142/371472 [6:45:51<11:44:52,  3.60it/s]
 59%|█████▉    | 219143/371472 [6:45:51<12:01:56,  3.52it/s]
 59%|█████▉    | 219144/371472 [6:45:51<12:40:35,  3.34it/s]
 59%|█████▉    | 219145/371472 [6:45:52<12:54:44,  3.28it/s]
 59%|█████▉    | 219146/371472 [6:45:52<13:07:57,  3.22it/s]
 59%|█████▉    | 219147/371472 [6:45:52<13:02:03,  3.25it/s]
 59%|█████▉    | 219148/371472 [6:45:52<12:53:41,  3.28it/s]
 59%|█████▉    | 219149/371472 [6:45:53<12:54:40,  3.28it/s]
 59%|█████▉    | 219150/371472 [6:45:53<12:28:42,  3.39it/s]
 59%|█████▉    | 219151/371472 [6:45:53<13:00:39,  3.25it/s]
 59%|█████▉    | 219152/371472 [6:45:54<12:36:42,  3.35it/s]
 59%|█████▉    | 219153/371472 [6:45:54<12:24:30,  3.41it/s]
 59%|█████▉    | 219154/371472 [6:45:54<12:10:48,  3.47it/s]
 59%|█████▉    | 219155/371472 [6:45:55<12:25:52,  3.40it/s]
 59%|█████▉    | 219156/371472 [6:45:55<12:27:20,  3.40it/s]
 59%|█████▉    | 219157/371472 [6:45:55<12:13:57,  3.46it/s]
 59%|█████▉    | 219158/371472 [6:45:55<12:10:57,  3.47it/s]
 59%|█████▉    | 219159/371472 [6:45:56<12:08:33,  3.48it/s]
 59%|█████▉    | 219160/371472 [6:45:56<11:54:10,  3.55it/s]
                                                            
{'loss': 2.6708, 'learning_rate': 4.692193324570665e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219160/371472 [6:45:56<11:54:10,  3.55it/s]
 59%|█████▉    | 219161/371472 [6:45:56<12:16:28,  3.45it/s]
 59%|█████▉    | 219162/371472 [6:45:57<12:24:30,  3.41it/s]
 59%|█████▉    | 219163/371472 [6:45:57<12:11:55,  3.47it/s]
 59%|█████▉    | 219164/371472 [6:45:57<15:32:46,  2.72it/s]
 59%|█████▉    | 219165/371472 [6:45:58<14:38:47,  2.89it/s]
 59%|█████▉    | 219166/371472 [6:45:58<13:42:26,  3.09it/s]
 59%|█████▉    | 219167/371472 [6:45:58<13:48:40,  3.06it/s]
 59%|█████▉    | 219168/371472 [6:45:59<13:10:40,  3.21it/s]
 59%|█████▉    | 219169/371472 [6:45:59<13:33:00,  3.12it/s]
 59%|█████▉    | 219170/371472 [6:45:59<12:50:57,  3.29it/s]
 59%|█████▉    | 219171/371472 [6:45:59<12:42:23,  3.33it/s]
 59%|█████▉    | 219172/371472 [6:46:00<12:18:48,  3.44it/s]
 59%|█████▉    | 219173/371472 [6:46:00<12:21:14,  3.42it/s]
 59%|█████▉    | 219174/371472 [6:46:00<12:34:37,  3.36it/s]
 59%|█████▉    | 219175/371472 [6:46:01<12:04:07,  3.51it/s]
 59%|█████▉    | 219176/371472 [6:46:01<12:09:48,  3.48it/s]
 59%|█████▉    | 219177/371472 [6:46:01<12:00:06,  3.52it/s]
 59%|█████▉    | 219178/371472 [6:46:01<12:17:12,  3.44it/s]
 59%|█████▉    | 219179/371472 [6:46:02<12:08:43,  3.48it/s]
 59%|█████▉    | 219180/371472 [6:46:02<14:37:55,  2.89it/s]
                                                            
{'loss': 3.0272, 'learning_rate': 4.691708504815876e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219180/371472 [6:46:02<14:37:55,  2.89it/s]
 59%|█████▉    | 219181/371472 [6:46:02<13:57:32,  3.03it/s]
 59%|█████▉    | 219182/371472 [6:46:03<14:14:03,  2.97it/s]
 59%|█████▉    | 219183/371472 [6:46:03<13:35:27,  3.11it/s]
 59%|█████▉    | 219184/371472 [6:46:03<12:58:42,  3.26it/s]
 59%|█████▉    | 219185/371472 [6:46:04<12:40:24,  3.34it/s]
 59%|█████▉    | 219186/371472 [6:46:04<12:54:50,  3.28it/s]
 59%|█████▉    | 219187/371472 [6:46:04<12:49:02,  3.30it/s]
 59%|█████▉    | 219188/371472 [6:46:05<12:41:02,  3.34it/s]
 59%|█████▉    | 219189/371472 [6:46:05<14:35:00,  2.90it/s]
 59%|█████▉    | 219190/371472 [6:46:05<14:17:35,  2.96it/s]
 59%|█████▉    | 219191/371472 [6:46:06<13:33:21,  3.12it/s]
 59%|█████▉    | 219192/371472 [6:46:06<12:57:56,  3.26it/s]
 59%|█████▉    | 219193/371472 [6:46:06<12:49:59,  3.30it/s]
 59%|█████▉    | 219194/371472 [6:46:07<13:05:06,  3.23it/s]
 59%|█████▉    | 219195/371472 [6:46:07<12:36:07,  3.36it/s]
 59%|█████▉    | 219196/371472 [6:46:07<12:24:37,  3.41it/s]
 59%|█████▉    | 219197/371472 [6:46:07<12:32:18,  3.37it/s]
 59%|█████▉    | 219198/371472 [6:46:08<12:33:14,  3.37it/s]
 59%|█████▉    | 219199/371472 [6:46:08<12:18:30,  3.44it/s]
 59%|█████▉    | 219200/371472 [6:46:08<12:13:18,  3.46it/s]
                                                            
{'loss': 2.6152, 'learning_rate': 4.691223685061087e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219200/371472 [6:46:08<12:13:18,  3.46it/s]
 59%|█████▉    | 219201/371472 [6:46:09<12:06:38,  3.49it/s]
 59%|█████▉    | 219202/371472 [6:46:09<12:04:48,  3.50it/s]
 59%|█████▉    | 219203/371472 [6:46:09<12:16:31,  3.45it/s]
 59%|█████▉    | 219204/371472 [6:46:09<12:05:08,  3.50it/s]
 59%|█████▉    | 219205/371472 [6:46:10<12:21:11,  3.42it/s]
 59%|█████▉    | 219206/371472 [6:46:10<12:47:20,  3.31it/s]
 59%|█████▉    | 219207/371472 [6:46:10<12:56:40,  3.27it/s]
 59%|█████▉    | 219208/371472 [6:46:11<12:59:30,  3.26it/s]
 59%|█████▉    | 219209/371472 [6:46:11<13:01:50,  3.25it/s]
 59%|█████▉    | 219210/371472 [6:46:11<12:32:41,  3.37it/s]
 59%|█████▉    | 219211/371472 [6:46:12<12:42:31,  3.33it/s]
 59%|█████▉    | 219212/371472 [6:46:12<12:45:19,  3.32it/s]
 59%|█████▉    | 219213/371472 [6:46:12<12:39:18,  3.34it/s]
 59%|█████▉    | 219214/371472 [6:46:12<12:22:31,  3.42it/s]
 59%|█████▉    | 219215/371472 [6:46:13<12:16:25,  3.45it/s]
 59%|█████▉    | 219216/371472 [6:46:13<12:33:56,  3.37it/s]
 59%|█████▉    | 219217/371472 [6:46:13<13:00:58,  3.25it/s]
 59%|█████▉    | 219218/371472 [6:46:14<13:16:46,  3.18it/s]
 59%|█████▉    | 219219/371472 [6:46:14<13:09:34,  3.21it/s]
 59%|█████▉    | 219220/371472 [6:46:14<12:49:21,  3.30it/s]
                                                            
{'loss': 2.7087, 'learning_rate': 4.690738865306298e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219220/371472 [6:46:14<12:49:21,  3.30it/s]
 59%|█████▉    | 219221/371472 [6:46:15<12:40:29,  3.34it/s]
 59%|█████▉    | 219222/371472 [6:46:15<12:55:27,  3.27it/s]
 59%|█████▉    | 219223/371472 [6:46:15<12:56:59,  3.27it/s]
 59%|█████▉    | 219224/371472 [6:46:15<12:58:24,  3.26it/s]
 59%|█████▉    | 219225/371472 [6:46:16<13:23:11,  3.16it/s]
 59%|█████▉    | 219226/371472 [6:46:16<13:40:01,  3.09it/s]
 59%|█████▉    | 219227/371472 [6:46:17<13:52:20,  3.05it/s]
 59%|█████▉    | 219228/371472 [6:46:17<13:17:25,  3.18it/s]
 59%|█████▉    | 219229/371472 [6:46:17<12:53:02,  3.28it/s]
 59%|█████▉    | 219230/371472 [6:46:17<12:42:00,  3.33it/s]
 59%|█████▉    | 219231/371472 [6:46:18<12:40:28,  3.34it/s]
 59%|█████▉    | 219232/371472 [6:46:18<12:54:42,  3.28it/s]
 59%|█████▉    | 219233/371472 [6:46:18<12:53:06,  3.28it/s]
 59%|█████▉    | 219234/371472 [6:46:19<13:00:41,  3.25it/s]
 59%|█████▉    | 219235/371472 [6:46:19<13:04:12,  3.24it/s]
 59%|█████▉    | 219236/371472 [6:46:19<13:21:44,  3.16it/s]
 59%|█████▉    | 219237/371472 [6:46:20<12:46:45,  3.31it/s]
 59%|█████▉    | 219238/371472 [6:46:20<12:29:23,  3.39it/s]
 59%|█████▉    | 219239/371472 [6:46:20<12:29:01,  3.39it/s]
 59%|█████▉    | 219240/371472 [6:46:20<12:32:42,  3.37it/s]
                                                            
{'loss': 2.7778, 'learning_rate': 4.6902540455515097e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219240/371472 [6:46:20<12:32:42,  3.37it/s]
 59%|█████▉    | 219241/371472 [6:46:21<12:26:47,  3.40it/s]
 59%|█████▉    | 219242/371472 [6:46:21<12:11:31,  3.47it/s]
 59%|█████▉    | 219243/371472 [6:46:21<12:11:27,  3.47it/s]
 59%|█████▉    | 219244/371472 [6:46:22<12:24:41,  3.41it/s]
 59%|█████▉    | 219245/371472 [6:46:22<13:38:43,  3.10it/s]
 59%|█████▉    | 219246/371472 [6:46:22<13:11:39,  3.20it/s]
 59%|█████▉    | 219247/371472 [6:46:22<12:38:48,  3.34it/s]
 59%|█████▉    | 219248/371472 [6:46:23<13:15:03,  3.19it/s]
 59%|█████▉    | 219249/371472 [6:46:23<14:03:22,  3.01it/s]
 59%|█████▉    | 219250/371472 [6:46:24<14:23:37,  2.94it/s]
 59%|█████▉    | 219251/371472 [6:46:24<15:08:18,  2.79it/s]
 59%|█████▉    | 219252/371472 [6:46:24<14:55:20,  2.83it/s]
 59%|█████▉    | 219253/371472 [6:46:25<14:08:06,  2.99it/s]
 59%|█████▉    | 219254/371472 [6:46:25<13:36:44,  3.11it/s]
 59%|█████▉    | 219255/371472 [6:46:25<13:05:52,  3.23it/s]
 59%|█████▉    | 219256/371472 [6:46:25<12:59:15,  3.26it/s]
 59%|█████▉    | 219257/371472 [6:46:26<12:54:20,  3.28it/s]
 59%|█████▉    | 219258/371472 [6:46:26<12:56:36,  3.27it/s]
 59%|█████▉    | 219259/371472 [6:46:26<12:44:27,  3.32it/s]
 59%|█████▉    | 219260/371472 [6:46:27<12:25:14,  3.40it/s]
                                                            
{'loss': 2.7955, 'learning_rate': 4.68976922579672e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219260/371472 [6:46:27<12:25:14,  3.40it/s]
 59%|█████▉    | 219261/371472 [6:46:27<12:23:59,  3.41it/s]
 59%|█████▉    | 219262/371472 [6:46:27<11:59:46,  3.52it/s]
 59%|█████▉    | 219263/371472 [6:46:28<12:13:27,  3.46it/s]
 59%|█████▉    | 219264/371472 [6:46:28<12:05:44,  3.50it/s]
 59%|█████▉    | 219265/371472 [6:46:28<12:30:43,  3.38it/s]
 59%|█████▉    | 219266/371472 [6:46:28<12:43:21,  3.32it/s]
 59%|█████▉    | 219267/371472 [6:46:29<12:17:58,  3.44it/s]
 59%|█████▉    | 219268/371472 [6:46:29<12:07:24,  3.49it/s]
 59%|█████▉    | 219269/371472 [6:46:29<12:01:34,  3.52it/s]
 59%|█████▉    | 219270/371472 [6:46:30<12:22:05,  3.42it/s]
 59%|█████▉    | 219271/371472 [6:46:30<12:22:31,  3.42it/s]
 59%|█████▉    | 219272/371472 [6:46:30<12:07:55,  3.48it/s]
 59%|█████▉    | 219273/371472 [6:46:30<11:54:24,  3.55it/s]
 59%|█████▉    | 219274/371472 [6:46:31<11:53:21,  3.56it/s]
 59%|█████▉    | 219275/371472 [6:46:31<12:06:22,  3.49it/s]
 59%|█████▉    | 219276/371472 [6:46:31<12:34:29,  3.36it/s]
 59%|█████▉    | 219277/371472 [6:46:32<12:43:52,  3.32it/s]
 59%|█████▉    | 219278/371472 [6:46:32<12:56:01,  3.27it/s]
 59%|█████▉    | 219279/371472 [6:46:32<12:21:13,  3.42it/s]
 59%|█████▉    | 219280/371472 [6:46:32<12:13:54,  3.46it/s]
                                                            
{'loss': 2.7842, 'learning_rate': 4.6892844060419316e-07, 'epoch': 9.44}
+
 59%|█████▉    | 219280/371472 [6:46:32<12:13:54,  3.46it/s]
 59%|█████▉    | 219281/371472 [6:46:33<11:55:11,  3.55it/s]
 59%|█████▉    | 219282/371472 [6:46:33<12:14:43,  3.45it/s]
 59%|█████▉    | 219283/371472 [6:46:33<12:07:41,  3.49it/s]
 59%|█████▉    | 219284/371472 [6:46:34<12:06:49,  3.49it/s]
 59%|█████▉    | 219285/371472 [6:46:34<11:49:06,  3.58it/s]
 59%|█████▉    | 219286/371472 [6:46:34<11:51:58,  3.56it/s]
 59%|█████▉    | 219287/371472 [6:46:34<12:10:28,  3.47it/s]
 59%|█████▉    | 219288/371472 [6:46:35<12:07:36,  3.49it/s]
 59%|█████▉    | 219289/371472 [6:46:35<11:50:45,  3.57it/s]
 59%|█████▉    | 219290/371472 [6:46:35<12:25:11,  3.40it/s]
 59%|█████▉    | 219291/371472 [6:46:36<12:15:43,  3.45it/s]
 59%|█████▉    | 219292/371472 [6:46:36<11:53:13,  3.56it/s]
 59%|█████▉    | 219293/371472 [6:46:36<12:37:33,  3.35it/s]
 59%|█████▉    | 219294/371472 [6:46:37<14:09:40,  2.99it/s]
 59%|█████▉    | 219295/371472 [6:46:37<14:01:12,  3.02it/s]
 59%|█████▉    | 219296/371472 [6:46:37<13:12:24,  3.20it/s]
 59%|█████▉    | 219297/371472 [6:46:38<13:01:13,  3.25it/s]
 59%|█████▉    | 219298/371472 [6:46:38<12:39:41,  3.34it/s]
 59%|█████▉    | 219299/371472 [6:46:38<12:18:26,  3.43it/s]
 59%|█████▉    | 219300/371472 [6:46:38<12:04:35,  3.50it/s]
                                                            
{'loss': 2.6905, 'learning_rate': 4.6887995862871424e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219300/371472 [6:46:38<12:04:35,  3.50it/s]
 59%|█████▉    | 219301/371472 [6:46:39<12:30:44,  3.38it/s]
 59%|█████▉    | 219302/371472 [6:46:39<12:19:19,  3.43it/s]
 59%|█████▉    | 219303/371472 [6:46:39<13:23:56,  3.15it/s]
 59%|█████▉    | 219304/371472 [6:46:40<12:56:49,  3.26it/s]
 59%|█████▉    | 219305/371472 [6:46:40<12:45:41,  3.31it/s]
 59%|█████▉    | 219306/371472 [6:46:40<13:18:01,  3.18it/s]
 59%|█████▉    | 219307/371472 [6:46:41<13:02:49,  3.24it/s]
 59%|█████▉    | 219308/371472 [6:46:41<12:57:50,  3.26it/s]
 59%|█████▉    | 219309/371472 [6:46:41<12:50:26,  3.29it/s]
 59%|█████▉    | 219310/371472 [6:46:41<12:51:58,  3.29it/s]
 59%|█████▉    | 219311/371472 [6:46:42<12:42:28,  3.33it/s]
 59%|█████▉    | 219312/371472 [6:46:42<12:59:29,  3.25it/s]
 59%|█████▉    | 219313/371472 [6:46:42<12:42:44,  3.32it/s]
 59%|█████▉    | 219314/371472 [6:46:43<12:18:31,  3.43it/s]
 59%|█████▉    | 219315/371472 [6:46:43<12:09:57,  3.47it/s]
 59%|█████▉    | 219316/371472 [6:46:43<12:12:17,  3.46it/s]
 59%|█████▉    | 219317/371472 [6:46:44<12:41:20,  3.33it/s]
 59%|█████▉    | 219318/371472 [6:46:44<12:36:35,  3.35it/s]
 59%|█████▉    | 219319/371472 [6:46:44<12:34:21,  3.36it/s]
 59%|█████▉    | 219320/371472 [6:46:44<12:46:59,  3.31it/s]
                                                            
{'loss': 2.6503, 'learning_rate': 4.6883147665323536e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219320/371472 [6:46:44<12:46:59,  3.31it/s]
 59%|█████▉    | 219321/371472 [6:46:45<12:39:12,  3.34it/s]
 59%|█████▉    | 219322/371472 [6:46:45<14:19:57,  2.95it/s]
 59%|█████▉    | 219323/371472 [6:46:45<13:28:23,  3.14it/s]
 59%|█████▉    | 219324/371472 [6:46:46<12:55:27,  3.27it/s]
 59%|█████▉    | 219325/371472 [6:46:46<13:04:04,  3.23it/s]
 59%|█████▉    | 219326/371472 [6:46:46<13:48:19,  3.06it/s]
 59%|█████▉    | 219327/371472 [6:46:47<13:11:36,  3.20it/s]
 59%|█████▉    | 219328/371472 [6:46:47<13:37:30,  3.10it/s]
 59%|█████▉    | 219329/371472 [6:46:47<13:44:27,  3.08it/s]
 59%|█████▉    | 219330/371472 [6:46:48<13:25:36,  3.15it/s]
 59%|█████▉    | 219331/371472 [6:46:48<13:00:53,  3.25it/s]
 59%|█████▉    | 219332/371472 [6:46:48<12:35:37,  3.36it/s]
 59%|█████▉    | 219333/371472 [6:46:48<12:20:04,  3.43it/s]
 59%|█████▉    | 219334/371472 [6:46:49<12:09:20,  3.48it/s]
 59%|█████▉    | 219335/371472 [6:46:49<11:57:41,  3.53it/s]
 59%|█████▉    | 219336/371472 [6:46:49<11:59:12,  3.53it/s]
 59%|█████▉    | 219337/371472 [6:46:50<13:05:55,  3.23it/s]
 59%|█████▉    | 219338/371472 [6:46:50<12:35:10,  3.36it/s]
 59%|█████▉    | 219339/371472 [6:46:50<12:24:38,  3.41it/s]
 59%|█████▉    | 219340/371472 [6:46:51<12:22:03,  3.42it/s]
                                                            
{'loss': 2.709, 'learning_rate': 4.6878299467775643e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219340/371472 [6:46:51<12:22:03,  3.42it/s]
 59%|█████▉    | 219341/371472 [6:46:51<12:13:39,  3.46it/s]
 59%|█████▉    | 219342/371472 [6:46:51<12:10:12,  3.47it/s]
 59%|█████▉    | 219343/371472 [6:46:51<12:32:50,  3.37it/s]
 59%|█████▉    | 219344/371472 [6:46:52<13:12:25,  3.20it/s]
 59%|█████▉    | 219345/371472 [6:46:52<12:34:15,  3.36it/s]
 59%|█████▉    | 219346/371472 [6:46:52<12:24:02,  3.41it/s]
 59%|█████▉    | 219347/371472 [6:46:53<13:30:02,  3.13it/s]
 59%|█████▉    | 219348/371472 [6:46:53<13:34:30,  3.11it/s]
 59%|█████▉    | 219349/371472 [6:46:53<13:16:37,  3.18it/s]
 59%|█████▉    | 219350/371472 [6:46:54<12:44:32,  3.32it/s]
 59%|█████▉    | 219351/371472 [6:46:54<12:23:42,  3.41it/s]
 59%|█████▉    | 219352/371472 [6:46:54<12:03:19,  3.51it/s]
 59%|█████▉    | 219353/371472 [6:46:54<12:40:28,  3.33it/s]
 59%|█████▉    | 219354/371472 [6:46:55<12:51:40,  3.29it/s]
 59%|█████▉    | 219355/371472 [6:46:55<12:41:02,  3.33it/s]
 59%|█████▉    | 219356/371472 [6:46:55<12:30:42,  3.38it/s]
 59%|█████▉    | 219357/371472 [6:46:56<12:47:47,  3.30it/s]
 59%|█████▉    | 219358/371472 [6:46:56<12:23:07,  3.41it/s]
 59%|█████▉    | 219359/371472 [6:46:56<12:20:52,  3.42it/s]
 59%|█████▉    | 219360/371472 [6:46:57<12:59:00,  3.25it/s]
                                                            
{'loss': 2.742, 'learning_rate': 4.687345127022776e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219360/371472 [6:46:57<12:59:00,  3.25it/s]
 59%|█████▉    | 219361/371472 [6:46:57<13:57:40,  3.03it/s]
 59%|█████▉    | 219362/371472 [6:46:57<13:02:14,  3.24it/s]
 59%|█████▉    | 219363/371472 [6:46:57<12:43:59,  3.32it/s]
 59%|█████▉    | 219364/371472 [6:46:58<12:21:37,  3.42it/s]
 59%|█████▉    | 219365/371472 [6:46:58<12:25:34,  3.40it/s]
 59%|█████▉    | 219366/371472 [6:46:58<13:25:26,  3.15it/s]
 59%|█████▉    | 219367/371472 [6:46:59<13:05:39,  3.23it/s]
 59%|█████▉    | 219368/371472 [6:46:59<12:54:10,  3.27it/s]
 59%|█████▉    | 219369/371472 [6:46:59<12:32:10,  3.37it/s]
 59%|█████▉    | 219370/371472 [6:47:00<12:15:18,  3.45it/s]
 59%|█████▉    | 219371/371472 [6:47:00<12:07:10,  3.49it/s]
 59%|█████▉    | 219372/371472 [6:47:00<12:27:51,  3.39it/s]
 59%|█████▉    | 219373/371472 [6:47:00<12:33:29,  3.36it/s]
 59%|█████▉    | 219374/371472 [6:47:01<12:39:21,  3.34it/s]
 59%|█████▉    | 219375/371472 [6:47:01<12:22:33,  3.41it/s]
 59%|█████▉    | 219376/371472 [6:47:01<12:23:51,  3.41it/s]
 59%|█████▉    | 219377/371472 [6:47:02<12:16:34,  3.44it/s]
 59%|█████▉    | 219378/371472 [6:47:02<12:31:44,  3.37it/s]
 59%|█████▉    | 219379/371472 [6:47:02<12:37:26,  3.35it/s]
 59%|█████▉    | 219380/371472 [6:47:03<13:02:16,  3.24it/s]
                                                            
{'loss': 2.6826, 'learning_rate': 4.6868603072679863e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219380/371472 [6:47:03<13:02:16,  3.24it/s]
 59%|█████▉    | 219381/371472 [6:47:03<13:27:28,  3.14it/s]
 59%|█████▉    | 219382/371472 [6:47:03<12:48:26,  3.30it/s]
 59%|█████▉    | 219383/371472 [6:47:03<12:43:35,  3.32it/s]
 59%|█████▉    | 219384/371472 [6:47:04<12:25:55,  3.40it/s]
 59%|█████▉    | 219385/371472 [6:47:04<12:11:43,  3.46it/s]
 59%|█████▉    | 219386/371472 [6:47:04<13:37:40,  3.10it/s]
 59%|█████▉    | 219387/371472 [6:47:05<13:04:38,  3.23it/s]
 59%|█████▉    | 219388/371472 [6:47:05<13:08:30,  3.21it/s]
 59%|█████▉    | 219389/371472 [6:47:05<12:45:22,  3.31it/s]
 59%|█████▉    | 219390/371472 [6:47:06<12:15:48,  3.44it/s]
 59%|█████▉    | 219391/371472 [6:47:06<12:01:40,  3.51it/s]
 59%|█████▉    | 219392/371472 [6:47:06<12:52:17,  3.28it/s]
 59%|█████▉    | 219393/371472 [6:47:06<12:40:42,  3.33it/s]
 59%|█████▉    | 219394/371472 [6:47:07<12:12:27,  3.46it/s]
 59%|█████▉    | 219395/371472 [6:47:07<11:59:20,  3.52it/s]
 59%|█████▉    | 219396/371472 [6:47:07<11:54:43,  3.55it/s]
 59%|█████▉    | 219397/371472 [6:47:08<12:53:22,  3.28it/s]
 59%|█████▉    | 219398/371472 [6:47:08<12:45:17,  3.31it/s]
 59%|█████▉    | 219399/371472 [6:47:08<12:57:38,  3.26it/s]
 59%|█████▉    | 219400/371472 [6:47:09<12:37:40,  3.35it/s]
                                                            
{'loss': 2.7637, 'learning_rate': 4.6863754875131975e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219400/371472 [6:47:09<12:37:40,  3.35it/s]
 59%|█████▉    | 219401/371472 [6:47:09<12:31:29,  3.37it/s]
 59%|█████▉    | 219402/371472 [6:47:09<12:09:48,  3.47it/s]
 59%|█████▉    | 219403/371472 [6:47:09<12:22:15,  3.41it/s]
 59%|█████▉    | 219404/371472 [6:47:10<12:16:00,  3.44it/s]
 59%|█████▉    | 219405/371472 [6:47:10<12:01:38,  3.51it/s]
 59%|█████▉    | 219406/371472 [6:47:10<11:49:52,  3.57it/s]
 59%|█████▉    | 219407/371472 [6:47:11<12:26:32,  3.39it/s]
 59%|█████▉    | 219408/371472 [6:47:11<12:09:23,  3.47it/s]
 59%|█████▉    | 219409/371472 [6:47:11<11:39:14,  3.62it/s]
 59%|█████▉    | 219410/371472 [6:47:11<11:38:06,  3.63it/s]
 59%|█████▉    | 219411/371472 [6:47:12<12:14:30,  3.45it/s]
 59%|█████▉    | 219412/371472 [6:47:12<12:03:27,  3.50it/s]
 59%|█████▉    | 219413/371472 [6:47:12<12:04:02,  3.50it/s]
 59%|█████▉    | 219414/371472 [6:47:13<12:02:57,  3.51it/s]
 59%|█████▉    | 219415/371472 [6:47:13<12:11:07,  3.47it/s]
 59%|█████▉    | 219416/371472 [6:47:13<11:54:39,  3.55it/s]
 59%|█████▉    | 219417/371472 [6:47:13<11:49:23,  3.57it/s]
 59%|█████▉    | 219418/371472 [6:47:14<11:42:08,  3.61it/s]
 59%|█████▉    | 219419/371472 [6:47:14<11:43:47,  3.60it/s]
 59%|█████▉    | 219420/371472 [6:47:14<12:09:35,  3.47it/s]
                                                            
{'loss': 2.7583, 'learning_rate': 4.685890667758409e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219420/371472 [6:47:14<12:09:35,  3.47it/s]
 59%|█████▉    | 219421/371472 [6:47:15<12:25:07,  3.40it/s]
 59%|█████▉    | 219422/371472 [6:47:15<12:10:59,  3.47it/s]
 59%|█████▉    | 219423/371472 [6:47:15<12:11:58,  3.46it/s]
 59%|█████▉    | 219424/371472 [6:47:15<11:54:43,  3.55it/s]
 59%|█████▉    | 219425/371472 [6:47:16<11:59:15,  3.52it/s]
 59%|█████▉    | 219426/371472 [6:47:16<11:38:56,  3.63it/s]
 59%|█████▉    | 219427/371472 [6:47:16<11:41:02,  3.61it/s]
 59%|█████▉    | 219428/371472 [6:47:16<11:30:49,  3.67it/s]
 59%|█████▉    | 219429/371472 [6:47:17<11:38:51,  3.63it/s]
 59%|█████▉    | 219430/371472 [6:47:17<11:53:53,  3.55it/s]
 59%|█████▉    | 219431/371472 [6:47:17<11:57:42,  3.53it/s]
 59%|█████▉    | 219432/371472 [6:47:18<12:10:40,  3.47it/s]
 59%|█████▉    | 219433/371472 [6:47:18<12:03:02,  3.50it/s]
 59%|█████▉    | 219434/371472 [6:47:18<11:52:03,  3.56it/s]
 59%|█████▉    | 219435/371472 [6:47:18<12:10:16,  3.47it/s]
 59%|█████▉    | 219436/371472 [6:47:19<11:52:23,  3.56it/s]
 59%|█████▉    | 219437/371472 [6:47:19<11:37:55,  3.63it/s]
 59%|█████▉    | 219438/371472 [6:47:19<11:40:46,  3.62it/s]
 59%|█████▉    | 219439/371472 [6:47:20<12:15:56,  3.44it/s]
 59%|█████▉    | 219440/371472 [6:47:20<11:57:30,  3.53it/s]
                                                            
{'loss': 2.6713, 'learning_rate': 4.68540584800362e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219440/371472 [6:47:20<11:57:30,  3.53it/s]
 59%|█████▉    | 219441/371472 [6:47:20<12:22:53,  3.41it/s]
 59%|█████▉    | 219442/371472 [6:47:20<12:15:06,  3.45it/s]
 59%|█████▉    | 219443/371472 [6:47:21<12:02:00,  3.51it/s]
 59%|█████▉    | 219444/371472 [6:47:21<12:08:55,  3.48it/s]
 59%|█████▉    | 219445/371472 [6:47:21<12:40:02,  3.33it/s]
 59%|█████▉    | 219446/371472 [6:47:22<12:32:14,  3.37it/s]
 59%|█████▉    | 219447/371472 [6:47:22<12:00:57,  3.51it/s]
 59%|█████▉    | 219448/371472 [6:47:22<12:14:47,  3.45it/s]
 59%|█████▉    | 219449/371472 [6:47:22<11:59:11,  3.52it/s]
 59%|█████▉    | 219450/371472 [6:47:23<12:18:19,  3.43it/s]
 59%|█████▉    | 219451/371472 [6:47:23<12:13:49,  3.45it/s]
 59%|█████▉    | 219452/371472 [6:47:23<12:05:17,  3.49it/s]
 59%|█████▉    | 219453/371472 [6:47:24<11:42:58,  3.60it/s]
 59%|█████▉    | 219454/371472 [6:47:24<12:40:12,  3.33it/s]
 59%|█████▉    | 219455/371472 [6:47:24<13:46:16,  3.07it/s]
 59%|█████▉    | 219456/371472 [6:47:25<13:18:14,  3.17it/s]
 59%|█████▉    | 219457/371472 [6:47:25<12:51:02,  3.29it/s]
 59%|█████▉    | 219458/371472 [6:47:25<12:26:28,  3.39it/s]
 59%|█████▉    | 219459/371472 [6:47:25<12:05:33,  3.49it/s]
 59%|█████▉    | 219460/371472 [6:47:26<12:26:06,  3.40it/s]
                                                            
{'loss': 2.8431, 'learning_rate': 4.6849210282488307e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219460/371472 [6:47:26<12:26:06,  3.40it/s]
 59%|█████▉    | 219461/371472 [6:47:26<12:21:09,  3.42it/s]
 59%|█████▉    | 219462/371472 [6:47:26<12:40:06,  3.33it/s]
 59%|█████▉    | 219463/371472 [6:47:27<13:16:11,  3.18it/s]
 59%|█████▉    | 219464/371472 [6:47:27<12:56:18,  3.26it/s]
 59%|█████▉    | 219465/371472 [6:47:27<12:46:12,  3.31it/s]
 59%|█████▉    | 219466/371472 [6:47:28<12:50:43,  3.29it/s]
 59%|█████▉    | 219467/371472 [6:47:28<13:03:33,  3.23it/s]
 59%|█████▉    | 219468/371472 [6:47:28<12:48:06,  3.30it/s]
 59%|█████▉    | 219469/371472 [6:47:29<12:44:52,  3.31it/s]
 59%|█████▉    | 219470/371472 [6:47:29<13:10:42,  3.20it/s]
 59%|█████▉    | 219471/371472 [6:47:29<12:58:56,  3.25it/s]
 59%|█████▉    | 219472/371472 [6:47:29<12:44:43,  3.31it/s]
 59%|█████▉    | 219473/371472 [6:47:30<12:30:11,  3.38it/s]
 59%|█████▉    | 219474/371472 [6:47:30<12:46:44,  3.30it/s]
 59%|█████▉    | 219475/371472 [6:47:30<12:38:53,  3.34it/s]
 59%|█████▉    | 219476/371472 [6:47:31<12:00:02,  3.52it/s]
 59%|█████▉    | 219477/371472 [6:47:31<12:28:12,  3.39it/s]
 59%|█████▉    | 219478/371472 [6:47:31<12:28:36,  3.38it/s]
 59%|█████▉    | 219479/371472 [6:47:31<12:07:32,  3.48it/s]
 59%|█████▉    | 219480/371472 [6:47:32<12:38:14,  3.34it/s]
                                                            
{'loss': 2.7665, 'learning_rate': 4.6844362084940414e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219480/371472 [6:47:32<12:38:14,  3.34it/s]
 59%|█████▉    | 219481/371472 [6:47:32<12:37:46,  3.34it/s]
 59%|█████▉    | 219482/371472 [6:47:32<12:29:08,  3.38it/s]
 59%|█████▉    | 219483/371472 [6:47:33<12:46:53,  3.30it/s]
 59%|█████▉    | 219484/371472 [6:47:33<12:10:37,  3.47it/s]
 59%|█████▉    | 219485/371472 [6:47:33<11:49:53,  3.57it/s]
 59%|█████▉    | 219486/371472 [6:47:34<12:47:12,  3.30it/s]
 59%|█████▉    | 219487/371472 [6:47:34<13:37:08,  3.10it/s]
 59%|█████▉    | 219488/371472 [6:47:34<13:49:35,  3.05it/s]
 59%|█████▉    | 219489/371472 [6:47:35<13:13:05,  3.19it/s]
 59%|█████▉    | 219490/371472 [6:47:35<14:16:37,  2.96it/s]
 59%|█████▉    | 219491/371472 [6:47:35<13:12:18,  3.20it/s]
 59%|█████▉    | 219492/371472 [6:47:36<13:04:50,  3.23it/s]
 59%|█████▉    | 219493/371472 [6:47:36<12:49:40,  3.29it/s]
 59%|█████▉    | 219494/371472 [6:47:36<13:00:48,  3.24it/s]
 59%|█████▉    | 219495/371472 [6:47:36<12:28:56,  3.38it/s]
 59%|█████▉    | 219496/371472 [6:47:37<12:14:14,  3.45it/s]
 59%|█████▉    | 219497/371472 [6:47:37<12:27:50,  3.39it/s]
 59%|█████▉    | 219498/371472 [6:47:37<12:49:35,  3.29it/s]
 59%|█████▉    | 219499/371472 [6:47:38<12:42:47,  3.32it/s]
 59%|█████▉    | 219500/371472 [6:47:38<12:42:36,  3.32it/s]
                                                            
{'loss': 2.7237, 'learning_rate': 4.683951388739253e-07, 'epoch': 9.45}
+
 59%|█████▉    | 219500/371472 [6:47:38<12:42:36,  3.32it/s]
 59%|█████▉    | 219501/371472 [6:47:38<13:11:47,  3.20it/s]
 59%|█████▉    | 219502/371472 [6:47:39<12:43:13,  3.32it/s]
 59%|█████▉    | 219503/371472 [6:47:39<12:14:11,  3.45it/s]
 59%|█████▉    | 219504/371472 [6:47:39<12:13:03,  3.46it/s]
 59%|█████▉    | 219505/371472 [6:47:39<12:04:27,  3.50it/s]
 59%|█████▉    | 219506/371472 [6:47:40<12:01:26,  3.51it/s]
 59%|█████▉    | 219507/371472 [6:47:40<12:04:13,  3.50it/s]
 59%|█████▉    | 219508/371472 [6:47:40<12:07:51,  3.48it/s]
 59%|█████▉    | 219509/371472 [6:47:41<13:25:13,  3.15it/s]
 59%|█████▉    | 219510/371472 [6:47:41<12:59:14,  3.25it/s]
 59%|█████▉    | 219511/371472 [6:47:41<12:33:50,  3.36it/s]
 59%|█████▉    | 219512/371472 [6:47:41<12:23:42,  3.41it/s]
 59%|█████▉    | 219513/371472 [6:47:42<12:12:40,  3.46it/s]
 59%|█████▉    | 219514/371472 [6:47:42<12:14:13,  3.45it/s]
 59%|█████▉    | 219515/371472 [6:47:42<12:33:09,  3.36it/s]
 59%|█████▉    | 219516/371472 [6:47:43<12:13:21,  3.45it/s]
 59%|█████▉    | 219517/371472 [6:47:43<12:05:29,  3.49it/s]
 59%|█████▉    | 219518/371472 [6:47:43<12:38:30,  3.34it/s]
 59%|█████▉    | 219519/371472 [6:47:43<12:12:48,  3.46it/s]
 59%|█████▉    | 219520/371472 [6:47:44<12:20:25,  3.42it/s]
                                                            
{'loss': 2.739, 'learning_rate': 4.6834665689844634e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219520/371472 [6:47:44<12:20:25,  3.42it/s]
 59%|█████▉    | 219521/371472 [6:47:44<12:57:13,  3.26it/s]
 59%|█████▉    | 219522/371472 [6:47:44<14:02:54,  3.00it/s]
 59%|█████▉    | 219523/371472 [6:47:45<14:54:57,  2.83it/s]
 59%|█████▉    | 219524/371472 [6:47:45<13:49:42,  3.05it/s]
 59%|█████▉    | 219525/371472 [6:47:45<13:05:44,  3.22it/s]
 59%|█████▉    | 219526/371472 [6:47:46<12:29:33,  3.38it/s]
 59%|█████▉    | 219527/371472 [6:47:46<12:22:09,  3.41it/s]
 59%|█████▉    | 219528/371472 [6:47:46<12:26:54,  3.39it/s]
 59%|█████▉    | 219529/371472 [6:47:47<12:10:59,  3.46it/s]
 59%|█████▉    | 219530/371472 [6:47:47<12:31:10,  3.37it/s]
 59%|█████▉    | 219531/371472 [6:47:47<12:04:22,  3.50it/s]
 59%|█████▉    | 219532/371472 [6:47:47<12:10:50,  3.46it/s]
 59%|█████▉    | 219533/371472 [6:47:48<12:42:55,  3.32it/s]
 59%|█████▉    | 219534/371472 [6:47:48<12:50:42,  3.29it/s]
 59%|█████▉    | 219535/371472 [6:47:48<12:28:34,  3.38it/s]
 59%|█████▉    | 219536/371472 [6:47:49<12:06:55,  3.48it/s]
 59%|█████▉    | 219537/371472 [6:47:49<12:03:36,  3.50it/s]
 59%|█████▉    | 219538/371472 [6:47:49<11:58:39,  3.52it/s]
 59%|█████▉    | 219539/371472 [6:47:49<12:04:30,  3.50it/s]
 59%|█████▉    | 219540/371472 [6:47:50<11:50:25,  3.56it/s]
                                                            
{'loss': 2.7976, 'learning_rate': 4.682981749229675e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219540/371472 [6:47:50<11:50:25,  3.56it/s]
 59%|█████▉    | 219541/371472 [6:47:50<11:54:26,  3.54it/s]
 59%|█████▉    | 219542/371472 [6:47:50<12:03:30,  3.50it/s]
 59%|█████▉    | 219543/371472 [6:47:51<11:58:56,  3.52it/s]
 59%|█████▉    | 219544/371472 [6:47:51<11:55:40,  3.54it/s]
 59%|█████▉    | 219545/371472 [6:47:51<12:05:25,  3.49it/s]
 59%|█████▉    | 219546/371472 [6:47:51<12:39:13,  3.34it/s]
 59%|███��█▉    | 219547/371472 [6:47:52<12:15:19,  3.44it/s]
 59%|█████▉    | 219548/371472 [6:47:52<12:12:36,  3.46it/s]
 59%|█████▉    | 219549/371472 [6:47:52<12:38:04,  3.34it/s]
 59%|█████▉    | 219550/371472 [6:47:53<13:03:10,  3.23it/s]
 59%|█████▉    | 219551/371472 [6:47:53<12:49:14,  3.29it/s]
 59%|█████▉    | 219552/371472 [6:47:53<12:34:28,  3.36it/s]
 59%|█████▉    | 219553/371472 [6:47:54<12:18:50,  3.43it/s]
 59%|█████▉    | 219554/371472 [6:47:54<12:11:00,  3.46it/s]
 59%|█████▉    | 219555/371472 [6:47:54<12:02:38,  3.50it/s]
 59%|█████▉    | 219556/371472 [6:47:54<11:47:54,  3.58it/s]
 59%|█████▉    | 219557/371472 [6:47:55<11:58:47,  3.52it/s]
 59%|█████▉    | 219558/371472 [6:47:55<11:38:10,  3.63it/s]
 59%|█████▉    | 219559/371472 [6:47:55<11:41:47,  3.61it/s]
 59%|█████▉    | 219560/371472 [6:47:55<11:45:28,  3.59it/s]
                                                            
{'loss': 2.8751, 'learning_rate': 4.6824969294748854e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219560/371472 [6:47:55<11:45:28,  3.59it/s]
 59%|█████▉    | 219561/371472 [6:47:56<11:48:07,  3.58it/s]
 59%|█████▉    | 219562/371472 [6:47:56<11:31:43,  3.66it/s]
 59%|█████▉    | 219563/371472 [6:47:56<11:23:41,  3.70it/s]
 59%|█████▉    | 219564/371472 [6:47:57<11:44:43,  3.59it/s]
 59%|█████▉    | 219565/371472 [6:47:57<11:42:40,  3.60it/s]
 59%|█████▉    | 219566/371472 [6:47:57<12:10:55,  3.46it/s]
 59%|█████▉    | 219567/371472 [6:47:58<13:45:29,  3.07it/s]
 59%|█████▉    | 219568/371472 [6:47:58<13:35:43,  3.10it/s]
 59%|█████▉    | 219569/371472 [6:47:58<13:20:20,  3.16it/s]
 59%|█████▉    | 219570/371472 [6:47:59<12:56:52,  3.26it/s]
 59%|█████▉    | 219571/371472 [6:47:59<12:35:14,  3.35it/s]
 59%|█████▉    | 219572/371472 [6:47:59<14:33:46,  2.90it/s]
 59%|█████▉    | 219573/371472 [6:48:00<13:48:42,  3.05it/s]
 59%|█████▉    | 219574/371472 [6:48:00<13:16:02,  3.18it/s]
 59%|█████▉    | 219575/371472 [6:48:00<12:57:46,  3.25it/s]
 59%|█████▉    | 219576/371472 [6:48:00<12:24:11,  3.40it/s]
 59%|█████▉    | 219577/371472 [6:48:01<12:48:25,  3.29it/s]
 59%|█████▉    | 219578/371472 [6:48:01<13:10:40,  3.20it/s]
 59%|█████▉    | 219579/371472 [6:48:01<12:47:54,  3.30it/s]
 59%|█████▉    | 219580/371472 [6:48:02<12:30:09,  3.37it/s]
                                                            
{'loss': 2.8261, 'learning_rate': 4.682012109720097e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219580/371472 [6:48:02<12:30:09,  3.37it/s]
 59%|█████▉    | 219581/371472 [6:48:02<12:35:08,  3.35it/s]
 59%|█████▉    | 219582/371472 [6:48:02<12:22:40,  3.41it/s]
 59%|█████▉    | 219583/371472 [6:48:02<12:10:28,  3.47it/s]
 59%|█████▉    | 219584/371472 [6:48:03<12:51:45,  3.28it/s]
 59%|█████▉    | 219585/371472 [6:48:03<12:47:29,  3.30it/s]
 59%|█████▉    | 219586/371472 [6:48:03<12:15:58,  3.44it/s]
 59%|█████▉    | 219587/371472 [6:48:04<11:40:49,  3.61it/s]
 59%|█████▉    | 219588/371472 [6:48:04<12:41:59,  3.32it/s]
 59%|█████▉    | 219589/371472 [6:48:04<13:45:43,  3.07it/s]
 59%|█████▉    | 219590/371472 [6:48:05<13:01:02,  3.24it/s]
 59%|█████▉    | 219591/371472 [6:48:05<14:13:18,  2.97it/s]
 59%|█████▉    | 219592/371472 [6:48:05<13:41:21,  3.08it/s]
 59%|█████▉    | 219593/371472 [6:48:06<12:53:12,  3.27it/s]
 59%|█████▉    | 219594/371472 [6:48:06<13:48:37,  3.05it/s]
 59%|█████▉    | 219595/371472 [6:48:06<13:00:30,  3.24it/s]
 59%|█████▉    | 219596/371472 [6:48:06<12:43:23,  3.32it/s]
 59%|█████▉    | 219597/371472 [6:48:07<12:30:31,  3.37it/s]
 59%|█████▉    | 219598/371472 [6:48:07<12:19:58,  3.42it/s]
 59%|█████▉    | 219599/371472 [6:48:07<12:08:53,  3.47it/s]
 59%|█████▉    | 219600/371472 [6:48:08<13:11:44,  3.20it/s]
                                                            
{'loss': 2.682, 'learning_rate': 4.681527289965308e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219600/371472 [6:48:08<13:11:44,  3.20it/s]
 59%|█████▉    | 219601/371472 [6:48:08<12:42:30,  3.32it/s]
 59%|█████▉    | 219602/371472 [6:48:08<12:13:45,  3.45it/s]
 59%|█████▉    | 219603/371472 [6:48:09<11:58:48,  3.52it/s]
 59%|█████▉    | 219604/371472 [6:48:09<11:43:16,  3.60it/s]
 59%|█████▉    | 219605/371472 [6:48:09<11:34:32,  3.64it/s]
 59%|█████▉    | 219606/371472 [6:48:09<12:14:06,  3.45it/s]
 59%|█████▉    | 219607/371472 [6:48:10<12:07:37,  3.48it/s]
 59%|█████▉    | 219608/371472 [6:48:10<12:00:32,  3.51it/s]
 59%|█████▉    | 219609/371472 [6:48:10<12:15:12,  3.44it/s]
 59%|█████▉    | 219610/371472 [6:48:11<12:17:49,  3.43it/s]
 59%|█████▉    | 219611/371472 [6:48:11<12:14:20,  3.45it/s]
 59%|█████▉    | 219612/371472 [6:48:11<12:18:25,  3.43it/s]
 59%|█████▉    | 219613/371472 [6:48:11<12:03:14,  3.50it/s]
 59%|█████▉    | 219614/371472 [6:48:12<11:53:26,  3.55it/s]
 59%|█████▉    | 219615/371472 [6:48:12<11:50:21,  3.56it/s]
 59%|█████▉    | 219616/371472 [6:48:12<12:01:43,  3.51it/s]
 59%|█████▉    | 219617/371472 [6:48:13<12:06:49,  3.48it/s]
 59%|█████▉    | 219618/371472 [6:48:13<12:02:24,  3.50it/s]
 59%|█████▉    | 219619/371472 [6:48:13<12:07:51,  3.48it/s]
 59%|█████▉    | 219620/371472 [6:48:13<11:49:13,  3.57it/s]
                                                            
{'loss': 2.8218, 'learning_rate': 4.6810424702105196e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219620/371472 [6:48:13<11:49:13,  3.57it/s]
 59%|█████▉    | 219621/371472 [6:48:14<11:30:45,  3.66it/s]
 59%|█████▉    | 219622/371472 [6:48:14<11:46:50,  3.58it/s]
 59%|█████▉    | 219623/371472 [6:48:14<12:15:48,  3.44it/s]
 59%|█████▉    | 219624/371472 [6:48:15<12:28:36,  3.38it/s]
 59%|█████▉    | 219625/371472 [6:48:15<12:33:36,  3.36it/s]
 59%|█████▉    | 219626/371472 [6:48:15<12:18:41,  3.43it/s]
 59%|█████▉    | 219627/371472 [6:48:15<11:54:48,  3.54it/s]
 59%|█████▉    | 219628/371472 [6:48:16<11:57:59,  3.52it/s]
 59%|█████▉    | 219629/371472 [6:48:16<11:52:26,  3.55it/s]
 59%|█████▉    | 219630/371472 [6:48:16<12:04:05,  3.49it/s]
 59%|█████▉    | 219631/371472 [6:48:17<11:53:29,  3.55it/s]
 59%|█████▉    | 219632/371472 [6:48:17<11:41:29,  3.61it/s]
 59%|█████▉    | 219633/371472 [6:48:17<11:51:06,  3.56it/s]
 59%|█████▉    | 219634/371472 [6:48:17<12:06:50,  3.48it/s]
 59%|█████▉    | 219635/371472 [6:48:18<12:16:14,  3.44it/s]
 59%|█████▉    | 219636/371472 [6:48:18<12:08:01,  3.48it/s]
 59%|█████▉    | 219637/371472 [6:48:18<12:29:56,  3.37it/s]
 59%|█████▉    | 219638/371472 [6:48:19<12:04:25,  3.49it/s]
 59%|█████▉    | 219639/371472 [6:48:19<11:47:32,  3.58it/s]
 59%|█████▉    | 219640/371472 [6:48:19<11:56:31,  3.53it/s]
                                                            
{'loss': 2.807, 'learning_rate': 4.68055765045573e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219640/371472 [6:48:19<11:56:31,  3.53it/s]
 59%|█████▉    | 219641/371472 [6:48:19<11:43:21,  3.60it/s]
 59%|█████▉    | 219642/371472 [6:48:20<11:31:25,  3.66it/s]
 59%|█████▉    | 219643/371472 [6:48:20<11:44:37,  3.59it/s]
 59%|█████▉    | 219644/371472 [6:48:20<11:46:40,  3.58it/s]
 59%|█████▉    | 219645/371472 [6:48:20<12:13:58,  3.45it/s]
 59%|█████▉    | 219646/371472 [6:48:21<11:48:06,  3.57it/s]
 59%|█████▉    | 219647/371472 [6:48:21<11:44:15,  3.59it/s]
 59%|█████▉    | 219648/371472 [6:48:21<11:46:11,  3.58it/s]
 59%|█████▉    | 219649/371472 [6:48:22<12:00:53,  3.51it/s]
 59%|█████▉    | 219650/371472 [6:48:22<11:45:34,  3.59it/s]
 59%|█████▉    | 219651/371472 [6:48:22<11:48:31,  3.57it/s]
 59%|█████▉    | 219652/371472 [6:48:22<12:28:50,  3.38it/s]
 59%|█████▉    | 219653/371472 [6:48:23<12:00:06,  3.51it/s]
 59%|█████▉    | 219654/371472 [6:48:23<11:35:51,  3.64it/s]
 59%|█████▉    | 219655/371472 [6:48:23<11:27:27,  3.68it/s]
 59%|█████▉    | 219656/371472 [6:48:24<11:14:43,  3.75it/s]
 59%|█████▉    | 219657/371472 [6:48:24<11:12:11,  3.76it/s]
 59%|█████▉    | 219658/371472 [6:48:24<11:32:18,  3.65it/s]
 59%|█████▉    | 219659/371472 [6:48:24<11:55:40,  3.54it/s]
 59%|█████▉    | 219660/371472 [6:48:25<11:45:51,  3.58it/s]
                                                            
{'loss': 2.7572, 'learning_rate': 4.6800728307009416e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219660/371472 [6:48:25<11:45:51,  3.58it/s]
 59%|█████▉    | 219661/371472 [6:48:25<11:48:33,  3.57it/s]
 59%|█████▉    | 219662/371472 [6:48:25<12:09:28,  3.47it/s]
 59%|█████▉    | 219663/371472 [6:48:26<12:15:37,  3.44it/s]
 59%|█████▉    | 219664/371472 [6:48:26<12:12:11,  3.46it/s]
 59%|█████▉    | 219665/371472 [6:48:26<12:22:41,  3.41it/s]
 59%|█████▉    | 219666/371472 [6:48:26<12:02:19,  3.50it/s]
 59%|█████▉    | 219667/371472 [6:48:27<11:51:36,  3.56it/s]
 59%|█████▉    | 219668/371472 [6:48:27<11:51:55,  3.55it/s]
 59%|█████▉    | 219669/371472 [6:48:27<11:45:03,  3.59it/s]
 59%|█████▉    | 219670/371472 [6:48:28<12:02:52,  3.50it/s]
 59%|█████▉    | 219671/371472 [6:48:28<12:12:36,  3.45it/s]
 59%|█████▉    | 219672/371472 [6:48:28<12:13:04,  3.45it/s]
 59%|█████▉    | 219673/371472 [6:48:28<12:25:36,  3.39it/s]
 59%|█████▉    | 219674/371472 [6:48:29<12:55:12,  3.26it/s]
 59%|█████▉    | 219675/371472 [6:48:29<13:13:52,  3.19it/s]
 59%|█████▉    | 219676/371472 [6:48:29<13:01:21,  3.24it/s]
 59%|█████▉    | 219677/371472 [6:48:30<13:08:41,  3.21it/s]
 59%|█████▉    | 219678/371472 [6:48:30<13:52:15,  3.04it/s]
 59%|█████▉    | 219679/371472 [6:48:30<13:24:46,  3.14it/s]
 59%|█████▉    | 219680/371472 [6:48:31<12:45:10,  3.31it/s]
                                                            
{'loss': 2.8307, 'learning_rate': 4.6795880109461523e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219680/371472 [6:48:31<12:45:10,  3.31it/s]
 59%|█████▉    | 219681/371472 [6:48:31<12:25:56,  3.39it/s]
 59%|█████▉    | 219682/371472 [6:48:31<12:31:12,  3.37it/s]
 59%|█████▉    | 219683/371472 [6:48:31<12:24:40,  3.40it/s]
 59%|█████▉    | 219684/371472 [6:48:32<12:24:17,  3.40it/s]
 59%|█████▉    | 219685/371472 [6:48:32<11:59:38,  3.52it/s]
 59%|█████▉    | 219686/371472 [6:48:32<12:48:32,  3.29it/s]
 59%|█████▉    | 219687/371472 [6:48:33<12:39:00,  3.33it/s]
 59%|█████▉    | 219688/371472 [6:48:33<12:25:15,  3.39it/s]
 59%|█████▉    | 219689/371472 [6:48:33<12:00:34,  3.51it/s]
 59%|█████▉    | 219690/371472 [6:48:33<11:50:25,  3.56it/s]
 59%|█████▉    | 219691/371472 [6:48:34<11:39:55,  3.61it/s]
 59%|█████▉    | 219692/371472 [6:48:34<11:47:08,  3.58it/s]
 59%|█████▉    | 219693/371472 [6:48:34<11:51:08,  3.56it/s]
 59%|█████▉    | 219694/371472 [6:48:35<11:53:00,  3.55it/s]
 59%|█████▉    | 219695/371472 [6:48:35<12:00:01,  3.51it/s]
 59%|█████▉    | 219696/371472 [6:48:35<12:06:30,  3.48it/s]
 59%|█████▉    | 219697/371472 [6:48:35<12:07:18,  3.48it/s]
 59%|█████▉    | 219698/371472 [6:48:36<12:14:10,  3.45it/s]
 59%|█████▉    | 219699/371472 [6:48:36<12:04:00,  3.49it/s]
 59%|█████▉    | 219700/371472 [6:48:36<12:31:45,  3.36it/s]
                                                            
{'loss': 2.6896, 'learning_rate': 4.6791031911913635e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219700/371472 [6:48:36<12:31:45,  3.36it/s]
 59%|█████▉    | 219701/371472 [6:48:37<13:20:08,  3.16it/s]
 59%|█████▉    | 219702/371472 [6:48:37<12:57:10,  3.25it/s]
 59%|█████▉    | 219703/371472 [6:48:37<13:19:41,  3.16it/s]
 59%|█████▉    | 219704/371472 [6:48:38<13:35:06,  3.10it/s]
 59%|█████▉    | 219705/371472 [6:48:38<13:33:06,  3.11it/s]
 59%|█████▉    | 219706/371472 [6:48:38<13:09:21,  3.20it/s]
 59%|█████▉    | 219707/371472 [6:48:39<12:35:18,  3.35it/s]
 59%|█████▉    | 219708/371472 [6:48:39<12:30:16,  3.37it/s]
 59%|█████▉    | 219709/371472 [6:48:39<12:09:46,  3.47it/s]
 59%|█████▉    | 219710/371472 [6:48:39<11:46:48,  3.58it/s]
 59%|█████▉    | 219711/371472 [6:48:40<12:15:45,  3.44it/s]
 59%|█████▉    | 219712/371472 [6:48:40<12:17:07,  3.43it/s]
 59%|█████▉    | 219713/371472 [6:48:40<12:10:12,  3.46it/s]
 59%|█████▉    | 219714/371472 [6:48:41<12:27:21,  3.38it/s]
 59%|█████▉    | 219715/371472 [6:48:41<12:00:03,  3.51it/s]
 59%|█████▉    | 219716/371472 [6:48:41<11:37:28,  3.63it/s]
 59%|█████▉    | 219717/371472 [6:48:41<11:30:58,  3.66it/s]
 59%|█████▉    | 219718/371472 [6:48:42<11:32:33,  3.65it/s]
 59%|█████▉    | 219719/371472 [6:48:42<11:25:33,  3.69it/s]
 59%|█████▉    | 219720/371472 [6:48:42<11:57:37,  3.52it/s]
                                                            
{'loss': 2.8259, 'learning_rate': 4.678618371436574e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219720/371472 [6:48:42<11:57:37,  3.52it/s]
 59%|█████▉    | 219721/371472 [6:48:43<12:06:50,  3.48it/s]
 59%|█████▉    | 219722/371472 [6:48:43<16:12:23,  2.60it/s]
 59%|█████▉    | 219723/371472 [6:48:43<15:13:09,  2.77it/s]
 59%|█████▉    | 219724/371472 [6:48:44<14:22:33,  2.93it/s]
 59%|█████▉    | 219725/371472 [6:48:44<13:42:24,  3.08it/s]
 59%|█████▉    | 219726/371472 [6:48:44<13:07:40,  3.21it/s]
 59%|█████▉    | 219727/371472 [6:48:45<12:53:58,  3.27it/s]
 59%|█████▉    | 219728/371472 [6:48:45<12:57:05,  3.25it/s]
 59%|█████▉    | 219729/371472 [6:48:45<12:35:54,  3.35it/s]
 59%|█████▉    | 219730/371472 [6:48:45<12:35:37,  3.35it/s]
 59%|█████▉    | 219731/371472 [6:48:46<12:22:10,  3.41it/s]
 59%|█████▉    | 219732/371472 [6:48:46<12:16:23,  3.43it/s]
 59%|█████▉    | 219733/371472 [6:48:46<12:31:56,  3.36it/s]
 59%|█████▉    | 219734/371472 [6:48:47<13:29:27,  3.12it/s]
 59%|█████▉    | 219735/371472 [6:48:47<13:32:56,  3.11it/s]
 59%|█████▉    | 219736/371472 [6:48:47<13:11:52,  3.19it/s]
 59%|█████▉    | 219737/371472 [6:48:48<12:47:39,  3.29it/s]
 59%|█████▉    | 219738/371472 [6:48:48<12:43:46,  3.31it/s]
 59%|█████▉    | 219739/371472 [6:48:48<12:37:56,  3.34it/s]
 59%|█████▉    | 219740/371472 [6:48:49<12:26:25,  3.39it/s]
                                                            
{'loss': 2.8468, 'learning_rate': 4.678133551681786e-07, 'epoch': 9.46}
+
 59%|█████▉    | 219740/371472 [6:48:49<12:26:25,  3.39it/s]
 59%|█████▉    | 219741/371472 [6:48:49<12:16:11,  3.44it/s]
 59%|█████▉    | 219742/371472 [6:48:49<13:08:33,  3.21it/s]
 59%|█████▉    | 219743/371472 [6:48:49<12:42:24,  3.32it/s]
 59%|█████▉    | 219744/371472 [6:48:50<12:25:19,  3.39it/s]
 59%|█████▉    | 219745/371472 [6:48:50<12:40:00,  3.33it/s]
 59%|█████▉    | 219746/371472 [6:48:50<12:29:38,  3.37it/s]
 59%|█████▉    | 219747/371472 [6:48:51<12:09:36,  3.47it/s]
 59%|█████▉    | 219748/371472 [6:48:51<12:22:43,  3.40it/s]
 59%|█████▉    | 219749/371472 [6:48:51<13:43:38,  3.07it/s]
 59%|█████▉    | 219750/371472 [6:48:52<12:47:47,  3.29it/s]
 59%|█████▉    | 219751/371472 [6:48:52<13:02:30,  3.23it/s]
 59%|█████▉    | 219752/371472 [6:48:52<12:30:01,  3.37it/s]
 59%|█████▉    | 219753/371472 [6:48:52<12:22:28,  3.41it/s]
 59%|█████▉    | 219754/371472 [6:48:53<13:08:03,  3.21it/s]
 59%|█████▉    | 219755/371472 [6:48:53<13:07:39,  3.21it/s]
 59%|█████▉    | 219756/371472 [6:48:54<14:24:34,  2.92it/s]
 59%|█████▉    | 219757/371472 [6:48:54<13:35:41,  3.10it/s]
 59%|█████▉    | 219758/371472 [6:48:54<13:55:57,  3.02it/s]
 59%|█████▉    | 219759/371472 [6:48:54<13:41:05,  3.08it/s]
 59%|█████▉    | 219760/371472 [6:48:55<13:13:05,  3.19it/s]
                                                            
{'loss': 2.8159, 'learning_rate': 4.677648731926997e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219760/371472 [6:48:55<13:13:05,  3.19it/s]
 59%|█████▉    | 219761/371472 [6:48:55<13:08:20,  3.21it/s]
 59%|█████▉    | 219762/371472 [6:48:55<13:34:17,  3.11it/s]
 59%|█████▉    | 219763/371472 [6:48:56<12:44:04,  3.31it/s]
 59%|█████▉    | 219764/371472 [6:48:56<13:31:26,  3.12it/s]
 59%|█████▉    | 219765/371472 [6:48:56<13:08:00,  3.21it/s]
 59%|█████▉    | 219766/371472 [6:48:57<12:42:49,  3.31it/s]
 59%|█████▉    | 219767/371472 [6:48:57<12:13:27,  3.45it/s]
 59%|█████▉    | 219768/371472 [6:48:57<11:58:06,  3.52it/s]
 59%|█████▉    | 219769/371472 [6:48:57<12:04:54,  3.49it/s]
 59%|█████▉    | 219770/371472 [6:48:58<11:56:05,  3.53it/s]
 59%|█████▉    | 219771/371472 [6:48:58<11:36:37,  3.63it/s]
 59%|█████▉    | 219772/371472 [6:48:58<11:38:11,  3.62it/s]
 59%|█████▉    | 219773/371472 [6:48:58<11:39:19,  3.62it/s]
 59%|█████▉    | 219774/371472 [6:48:59<11:44:55,  3.59it/s]
 59%|█████▉    | 219775/371472 [6:48:59<12:05:32,  3.48it/s]
 59%|█████▉    | 219776/371472 [6:48:59<13:05:43,  3.22it/s]
 59%|█████▉    | 219777/371472 [6:49:00<12:58:17,  3.25it/s]
 59%|█████▉    | 219778/371472 [6:49:00<12:55:28,  3.26it/s]
 59%|█████▉    | 219779/371472 [6:49:00<12:48:14,  3.29it/s]
 59%|█████▉    | 219780/371472 [6:49:01<12:20:26,  3.41it/s]
                                                            
{'loss': 2.6888, 'learning_rate': 4.677163912172208e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219780/371472 [6:49:01<12:20:26,  3.41it/s]
 59%|█████▉    | 219781/371472 [6:49:01<12:12:24,  3.45it/s]
 59%|█████▉    | 219782/371472 [6:49:01<12:45:11,  3.30it/s]
 59%|█████▉    | 219783/371472 [6:49:02<12:35:54,  3.34it/s]
 59%|█████▉    | 219784/371472 [6:49:02<13:23:37,  3.15it/s]
 59%|█████▉    | 219785/371472 [6:49:02<12:57:13,  3.25it/s]
 59%|█████▉    | 219786/371472 [6:49:02<12:32:05,  3.36it/s]
 59%|█████▉    | 219787/371472 [6:49:03<12:17:28,  3.43it/s]
 59%|█████▉    | 219788/371472 [6:49:03<12:08:34,  3.47it/s]
 59%|█████▉    | 219789/371472 [6:49:03<11:58:58,  3.52it/s]
 59%|█████▉    | 219790/371472 [6:49:04<12:13:11,  3.45it/s]
 59%|█████▉    | 219791/371472 [6:49:04<11:54:41,  3.54it/s]
 59%|█████▉    | 219792/371472 [6:49:04<12:08:06,  3.47it/s]
 59%|█████▉    | 219793/371472 [6:49:04<12:01:23,  3.50it/s]
 59%|█████▉    | 219794/371472 [6:49:05<11:52:48,  3.55it/s]
 59%|█████▉    | 219795/371472 [6:49:05<12:05:35,  3.48it/s]
 59%|█████▉    | 219796/371472 [6:49:05<12:36:52,  3.34it/s]
 59%|█████▉    | 219797/371472 [6:49:06<13:02:31,  3.23it/s]
 59%|█████▉    | 219798/371472 [6:49:06<12:32:49,  3.36it/s]
 59%|█████▉    | 219799/371472 [6:49:06<12:26:09,  3.39it/s]
 59%|█████▉    | 219800/371472 [6:49:06<12:09:09,  3.47it/s]
                                                            
{'loss': 2.9189, 'learning_rate': 4.6766790924174187e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219800/371472 [6:49:06<12:09:09,  3.47it/s]
 59%|█████▉    | 219801/371472 [6:49:07<12:11:02,  3.46it/s]
 59%|█████▉    | 219802/371472 [6:49:07<12:02:45,  3.50it/s]
 59%|█████▉    | 219803/371472 [6:49:07<12:41:07,  3.32it/s]
 59%|█████▉    | 219804/371472 [6:49:08<12:29:35,  3.37it/s]
 59%|█████▉    | 219805/371472 [6:49:08<12:35:17,  3.35it/s]
 59%|█████▉    | 219806/371472 [6:49:08<12:40:49,  3.32it/s]
 59%|█████▉    | 219807/371472 [6:49:09<12:22:13,  3.41it/s]
 59%|█████▉    | 219808/371472 [6:49:09<12:11:59,  3.45it/s]
 59%|█████▉    | 219809/371472 [6:49:09<12:26:30,  3.39it/s]
 59%|█████▉    | 219810/371472 [6:49:09<12:10:26,  3.46it/s]
 59%|█████▉    | 219811/371472 [6:49:10<11:54:15,  3.54it/s]
 59%|█████▉    | 219812/371472 [6:49:10<11:57:48,  3.52it/s]
 59%|█████▉    | 219813/371472 [6:49:10<11:59:43,  3.51it/s]
 59%|█████▉    | 219814/371472 [6:49:11<12:11:52,  3.45it/s]
 59%|█████▉    | 219815/371472 [6:49:11<12:48:01,  3.29it/s]
 59%|█████▉    | 219816/371472 [6:49:11<12:47:45,  3.29it/s]
 59%|█████▉    | 219817/371472 [6:49:12<12:44:19,  3.31it/s]
 59%|█████▉    | 219818/371472 [6:49:12<12:41:59,  3.32it/s]
 59%|█████▉    | 219819/371472 [6:49:12<12:08:41,  3.47it/s]
 59%|█████▉    | 219820/371472 [6:49:12<12:09:00,  3.47it/s]
                                                            
{'loss': 2.618, 'learning_rate': 4.6761942726626305e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219820/371472 [6:49:12<12:09:00,  3.47it/s]
 59%|█████▉    | 219821/371472 [6:49:13<13:03:05,  3.23it/s]
 59%|█████▉    | 219822/371472 [6:49:13<12:49:52,  3.28it/s]
 59%|█████▉    | 219823/371472 [6:49:13<12:40:02,  3.33it/s]
 59%|█████▉    | 219824/371472 [6:49:14<12:42:20,  3.32it/s]
 59%|█████▉    | 219825/371472 [6:49:14<12:23:45,  3.40it/s]
 59%|█████▉    | 219826/371472 [6:49:14<13:27:43,  3.13it/s]
 59%|█████▉    | 219827/371472 [6:49:15<12:48:45,  3.29it/s]
 59%|█████▉    | 219828/371472 [6:49:15<12:21:01,  3.41it/s]
 59%|█████▉    | 219829/371472 [6:49:15<12:52:55,  3.27it/s]
 59%|█████▉    | 219830/371472 [6:49:15<12:30:14,  3.37it/s]
 59%|█████▉    | 219831/371472 [6:49:16<12:32:02,  3.36it/s]
 59%|█████▉    | 219832/371472 [6:49:16<12:17:46,  3.43it/s]
 59%|█████▉    | 219833/371472 [6:49:16<12:42:26,  3.31it/s]
 59%|█████▉    | 219834/371472 [6:49:17<12:24:41,  3.39it/s]
 59%|█████▉    | 219835/371472 [6:49:17<14:53:26,  2.83it/s]
 59%|█████▉    | 219836/371472 [6:49:17<14:15:38,  2.95it/s]
 59%|█████▉    | 219837/371472 [6:49:18<13:28:55,  3.12it/s]
 59%|█████▉    | 219838/371472 [6:49:18<12:57:57,  3.25it/s]
 59%|█████▉    | 219839/371472 [6:49:18<12:29:45,  3.37it/s]
 59%|█████▉    | 219840/371472 [6:49:18<12:01:09,  3.50it/s]
                                                            
{'loss': 2.9062, 'learning_rate': 4.6757094529078407e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219840/371472 [6:49:18<12:01:09,  3.50it/s]
 59%|█████▉    | 219841/371472 [6:49:19<12:04:16,  3.49it/s]
 59%|█████▉    | 219842/371472 [6:49:19<12:38:27,  3.33it/s]
 59%|█████▉    | 219843/371472 [6:49:19<12:35:36,  3.34it/s]
 59%|█████▉    | 219844/371472 [6:49:20<13:17:34,  3.17it/s]
 59%|█████▉    | 219845/371472 [6:49:20<14:20:11,  2.94it/s]
 59%|█████▉    | 219846/371472 [6:49:20<14:12:51,  2.96it/s]
 59%|█████▉    | 219847/371472 [6:49:21<13:36:50,  3.09it/s]
 59%|█████▉    | 219848/371472 [6:49:21<13:21:06,  3.15it/s]
 59%|█████▉    | 219849/371472 [6:49:21<12:37:15,  3.34it/s]
 59%|█████▉    | 219850/371472 [6:49:22<12:12:56,  3.45it/s]
 59%|█████▉    | 219851/371472 [6:49:22<12:04:47,  3.49it/s]
 59%|█████▉    | 219852/371472 [6:49:22<12:24:31,  3.39it/s]
 59%|█████▉    | 219853/371472 [6:49:22<12:18:46,  3.42it/s]
 59%|█████▉    | 219854/371472 [6:49:23<12:48:38,  3.29it/s]
 59%|█████▉    | 219855/371472 [6:49:23<12:28:21,  3.38it/s]
 59%|█████▉    | 219856/371472 [6:49:23<12:19:42,  3.42it/s]
 59%|█████▉    | 219857/371472 [6:49:24<12:45:25,  3.30it/s]
 59%|█████▉    | 219858/371472 [6:49:24<12:49:35,  3.28it/s]
 59%|█████▉    | 219859/371472 [6:49:24<12:51:28,  3.28it/s]
 59%|█████▉    | 219860/371472 [6:49:25<14:08:50,  2.98it/s]
                                                            
{'loss': 2.8533, 'learning_rate': 4.6752246331530524e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219860/371472 [6:49:25<14:08:50,  2.98it/s]
 59%|█████▉    | 219861/371472 [6:49:25<14:25:55,  2.92it/s]
 59%|█████▉    | 219862/371472 [6:49:25<13:45:00,  3.06it/s]
 59%|█████▉    | 219863/371472 [6:49:26<13:44:41,  3.06it/s]
 59%|█████▉    | 219864/371472 [6:49:26<14:06:12,  2.99it/s]
 59%|█████▉    | 219865/371472 [6:49:26<13:11:28,  3.19it/s]
 59%|█████▉    | 219866/371472 [6:49:27<12:32:33,  3.36it/s]
 59%|█████▉    | 219867/371472 [6:49:27<12:23:52,  3.40it/s]
 59%|█████▉    | 219868/371472 [6:49:27<12:30:20,  3.37it/s]
 59%|█████▉    | 219869/371472 [6:49:28<13:28:04,  3.13it/s]
 59%|█████▉    | 219870/371472 [6:49:28<12:54:12,  3.26it/s]
 59%|█████▉    | 219871/371472 [6:49:28<12:41:37,  3.32it/s]
 59%|█████▉    | 219872/371472 [6:49:28<13:25:42,  3.14it/s]
 59%|█████▉    | 219873/371472 [6:49:29<13:22:28,  3.15it/s]
 59%|█████▉    | 219874/371472 [6:49:29<12:49:15,  3.28it/s]
 59%|█████▉    | 219875/371472 [6:49:29<12:48:48,  3.29it/s]
 59%|█████▉    | 219876/371472 [6:49:30<12:20:16,  3.41it/s]
 59%|█████▉    | 219877/371472 [6:49:30<12:06:15,  3.48it/s]
 59%|█████▉    | 219878/371472 [6:49:30<12:30:00,  3.37it/s]
 59%|█████▉    | 219879/371472 [6:49:30<12:16:41,  3.43it/s]
 59%|█████▉    | 219880/371472 [6:49:31<12:13:33,  3.44it/s]
                                                            
{'loss': 2.7796, 'learning_rate': 4.674739813398263e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219880/371472 [6:49:31<12:13:33,  3.44it/s]
 59%|█████▉    | 219881/371472 [6:49:31<12:06:52,  3.48it/s]
 59%|█████▉    | 219882/371472 [6:49:31<13:38:03,  3.09it/s]
 59%|█████▉    | 219883/371472 [6:49:32<13:06:32,  3.21it/s]
 59%|█████▉    | 219884/371472 [6:49:32<12:46:09,  3.30it/s]
 59%|█████▉    | 219885/371472 [6:49:32<12:33:32,  3.35it/s]
 59%|█████▉    | 219886/371472 [6:49:33<12:29:49,  3.37it/s]
 59%|█████▉    | 219887/371472 [6:49:33<12:58:04,  3.25it/s]
 59%|█████▉    | 219888/371472 [6:49:33<13:02:33,  3.23it/s]
 59%|█████▉    | 219889/371472 [6:49:34<13:08:22,  3.20it/s]
 59%|█████▉    | 219890/371472 [6:49:34<12:42:31,  3.31it/s]
 59%|█████▉    | 219891/371472 [6:49:34<12:40:39,  3.32it/s]
 59%|█████▉    | 219892/371472 [6:49:35<13:25:31,  3.14it/s]
 59%|█████▉    | 219893/371472 [6:49:35<14:54:36,  2.82it/s]
 59%|█████▉    | 219894/371472 [6:49:35<13:41:26,  3.08it/s]
 59%|█████▉    | 219895/371472 [6:49:35<12:58:36,  3.24it/s]
 59%|█████▉    | 219896/371472 [6:49:36<12:54:01,  3.26it/s]
 59%|█████▉    | 219897/371472 [6:49:36<12:50:15,  3.28it/s]
 59%|█████▉    | 219898/371472 [6:49:37<15:23:55,  2.73it/s]
 59%|█████▉    | 219899/371472 [6:49:37<14:35:26,  2.89it/s]
 59%|█████▉    | 219900/371472 [6:49:37<15:01:59,  2.80it/s]
                                                            
{'loss': 2.5566, 'learning_rate': 4.6742549936434744e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219900/371472 [6:49:37<15:01:59,  2.80it/s]
 59%|█████▉    | 219901/371472 [6:49:38<14:25:30,  2.92it/s]
 59%|█████▉    | 219902/371472 [6:49:38<13:25:02,  3.14it/s]
 59%|█████▉    | 219903/371472 [6:49:38<14:18:17,  2.94it/s]
 59%|█████▉    | 219904/371472 [6:49:39<13:29:12,  3.12it/s]
 59%|█████▉    | 219905/371472 [6:49:39<12:50:54,  3.28it/s]
 59%|█████▉    | 219906/371472 [6:49:39<12:34:51,  3.35it/s]
 59%|█████▉    | 219907/371472 [6:49:39<12:37:44,  3.33it/s]
 59%|█████▉    | 219908/371472 [6:49:40<12:45:13,  3.30it/s]
 59%|█████▉    | 219909/371472 [6:49:40<12:08:35,  3.47it/s]
 59%|█████▉    | 219910/371472 [6:49:40<12:22:44,  3.40it/s]
 59%|█████▉    | 219911/371472 [6:49:41<12:12:22,  3.45it/s]
 59%|█████▉    | 219912/371472 [6:49:41<11:53:04,  3.54it/s]
 59%|█████▉    | 219913/371472 [6:49:41<12:00:28,  3.51it/s]
 59%|█████▉    | 219914/371472 [6:49:41<12:09:10,  3.46it/s]
 59%|█████▉    | 219915/371472 [6:49:42<11:50:54,  3.55it/s]
 59%|█████▉    | 219916/371472 [6:49:42<11:55:35,  3.53it/s]
 59%|█████▉    | 219917/371472 [6:49:42<12:20:11,  3.41it/s]
 59%|█████▉    | 219918/371472 [6:49:42<11:52:32,  3.54it/s]
 59%|█████▉    | 219919/371472 [6:49:43<11:55:20,  3.53it/s]
 59%|█████▉    | 219920/371472 [6:49:43<12:36:38,  3.34it/s]
                                                            
{'loss': 2.6976, 'learning_rate': 4.673770173888685e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219920/371472 [6:49:43<12:36:38,  3.34it/s]
 59%|█████▉    | 219921/371472 [6:49:43<12:20:08,  3.41it/s]
 59%|█████▉    | 219922/371472 [6:49:44<12:04:18,  3.49it/s]
 59%|█████▉    | 219923/371472 [6:49:44<11:57:35,  3.52it/s]
 59%|█████▉    | 219924/371472 [6:49:44<11:47:15,  3.57it/s]
 59%|█████▉    | 219925/371472 [6:49:45<12:01:08,  3.50it/s]
 59%|█████▉    | 219926/371472 [6:49:45<12:51:10,  3.28it/s]
 59%|█████▉    | 219927/371472 [6:49:45<13:24:24,  3.14it/s]
 59%|█████▉    | 219928/371472 [6:49:45<12:59:42,  3.24it/s]
 59%|█████▉    | 219929/371472 [6:49:46<12:55:20,  3.26it/s]
 59%|█████▉    | 219930/371472 [6:49:46<12:43:12,  3.31it/s]
 59%|█████▉    | 219931/371472 [6:49:46<12:40:52,  3.32it/s]
 59%|█████▉    | 219932/371472 [6:49:47<12:02:18,  3.50it/s]
 59%|█████▉    | 219933/371472 [6:49:47<12:15:39,  3.43it/s]
 59%|█████▉    | 219934/371472 [6:49:47<12:30:20,  3.37it/s]
 59%|█████▉    | 219935/371472 [6:49:48<12:44:50,  3.30it/s]
 59%|█████▉    | 219936/371472 [6:49:48<12:19:10,  3.42it/s]
 59%|█████▉    | 219937/371472 [6:49:48<11:56:24,  3.53it/s]
 59%|█████▉    | 219938/371472 [6:49:48<12:54:04,  3.26it/s]
 59%|█████▉    | 219939/371472 [6:49:49<13:10:48,  3.19it/s]
 59%|█████▉    | 219940/371472 [6:49:49<12:47:32,  3.29it/s]
                                                            
{'loss': 2.6365, 'learning_rate': 4.673285354133897e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219940/371472 [6:49:49<12:47:32,  3.29it/s]
 59%|█████▉    | 219941/371472 [6:49:49<12:32:29,  3.36it/s]
 59%|█████▉    | 219942/371472 [6:49:50<12:19:32,  3.41it/s]
 59%|█████▉    | 219943/371472 [6:49:50<12:47:02,  3.29it/s]
 59%|█████▉    | 219944/371472 [6:49:50<12:39:17,  3.33it/s]
 59%|█████▉    | 219945/371472 [6:49:51<12:56:25,  3.25it/s]
 59%|█████▉    | 219946/371472 [6:49:51<12:22:24,  3.40it/s]
 59%|█████▉    | 219947/371472 [6:49:51<13:00:52,  3.23it/s]
 59%|█████▉    | 219948/371472 [6:49:52<13:07:46,  3.21it/s]
 59%|█████▉    | 219949/371472 [6:49:52<12:45:18,  3.30it/s]
 59%|█████▉    | 219950/371472 [6:49:52<13:09:11,  3.20it/s]
 59%|█████▉    | 219951/371472 [6:49:52<12:38:18,  3.33it/s]
 59%|█████▉    | 219952/371472 [6:49:53<12:26:49,  3.38it/s]
 59%|█████▉    | 219953/371472 [6:49:53<12:33:44,  3.35it/s]
 59%|█████▉    | 219954/371472 [6:49:53<13:01:22,  3.23it/s]
 59%|█████▉    | 219955/371472 [6:49:54<12:45:00,  3.30it/s]
 59%|█████▉    | 219956/371472 [6:49:54<12:22:56,  3.40it/s]
 59%|█████▉    | 219957/371472 [6:49:54<12:22:47,  3.40it/s]
 59%|█████▉    | 219958/371472 [6:49:54<12:16:22,  3.43it/s]
 59%|█████▉    | 219959/371472 [6:49:55<12:23:41,  3.40it/s]
 59%|█████▉    | 219960/371472 [6:49:55<12:04:20,  3.49it/s]
                                                            
{'loss': 2.7811, 'learning_rate': 4.672800534379107e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219960/371472 [6:49:55<12:04:20,  3.49it/s]
 59%|█████▉    | 219961/371472 [6:49:55<12:45:02,  3.30it/s]
 59%|█████▉    | 219962/371472 [6:49:56<12:35:55,  3.34it/s]
 59%|█████▉    | 219963/371472 [6:49:56<12:36:39,  3.34it/s]
 59%|█████▉    | 219964/371472 [6:49:56<13:16:48,  3.17it/s]
 59%|█████▉    | 219965/371472 [6:49:57<12:47:15,  3.29it/s]
 59%|█████▉    | 219966/371472 [6:49:57<12:46:13,  3.30it/s]
 59%|█████▉    | 219967/371472 [6:49:57<12:31:51,  3.36it/s]
 59%|█████▉    | 219968/371472 [6:49:57<12:24:24,  3.39it/s]
 59%|█████▉    | 219969/371472 [6:49:58<12:06:40,  3.47it/s]
 59%|█████▉    | 219970/371472 [6:49:58<12:01:51,  3.50it/s]
 59%|█████▉    | 219971/371472 [6:49:58<11:59:43,  3.51it/s]
 59%|█████▉    | 219972/371472 [6:49:59<12:01:29,  3.50it/s]
 59%|█████▉    | 219973/371472 [6:49:59<11:52:33,  3.54it/s]
 59%|█████▉    | 219974/371472 [6:49:59<11:42:14,  3.60it/s]
 59%|█████▉    | 219975/371472 [6:49:59<11:43:55,  3.59it/s]
 59%|█████▉    | 219976/371472 [6:50:00<12:05:08,  3.48it/s]
 59%|█████▉    | 219977/371472 [6:50:00<12:12:47,  3.45it/s]
 59%|████��▉    | 219978/371472 [6:50:00<11:53:07,  3.54it/s]
 59%|█████▉    | 219979/371472 [6:50:01<12:01:57,  3.50it/s]
 59%|█████▉    | 219980/371472 [6:50:01<12:22:30,  3.40it/s]
                                                            
{'loss': 2.712, 'learning_rate': 4.672315714624319e-07, 'epoch': 9.47}
+
 59%|█████▉    | 219980/371472 [6:50:01<12:22:30,  3.40it/s]
 59%|█████▉    | 219981/371472 [6:50:01<12:08:19,  3.47it/s]
 59%|█████▉    | 219982/371472 [6:50:01<11:58:29,  3.51it/s]
 59%|█████▉    | 219983/371472 [6:50:02<12:02:35,  3.49it/s]
 59%|█████▉    | 219984/371472 [6:50:02<12:32:01,  3.36it/s]
 59%|█████▉    | 219985/371472 [6:50:02<12:41:08,  3.32it/s]
 59%|█████▉    | 219986/371472 [6:50:03<12:26:23,  3.38it/s]
 59%|█████▉    | 219987/371472 [6:50:03<12:32:24,  3.36it/s]
 59%|█████▉    | 219988/371472 [6:50:03<12:15:41,  3.43it/s]
 59%|█████▉    | 219989/371472 [6:50:04<12:04:42,  3.48it/s]
 59%|█████▉    | 219990/371472 [6:50:04<11:30:58,  3.65it/s]
 59%|█████▉    | 219991/371472 [6:50:04<11:33:40,  3.64it/s]
 59%|█████▉    | 219992/371472 [6:50:04<11:41:46,  3.60it/s]
 59%|█████▉    | 219993/371472 [6:50:05<11:54:02,  3.54it/s]
 59%|█████▉    | 219994/371472 [6:50:05<11:48:12,  3.56it/s]
 59%|█████▉    | 219995/371472 [6:50:05<12:12:25,  3.45it/s]
 59%|█████▉    | 219996/371472 [6:50:05<12:06:42,  3.47it/s]
 59%|█████▉    | 219997/371472 [6:50:06<12:38:50,  3.33it/s]
 59%|█████▉    | 219998/371472 [6:50:06<12:51:32,  3.27it/s]
 59%|█████▉    | 219999/371472 [6:50:06<13:07:10,  3.21it/s]
 59%|█████▉    | 220000/371472 [6:50:07<12:29:57,  3.37it/s]
                                                            
{'loss': 2.8672, 'learning_rate': 4.6718308948695296e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220000/371472 [6:50:07<12:29:57,  3.37it/s]
 59%|█████▉    | 220001/371472 [6:50:07<12:45:01,  3.30it/s]
 59%|█████▉    | 220002/371472 [6:50:07<12:30:02,  3.37it/s]
 59%|█████▉    | 220003/371472 [6:50:08<12:37:08,  3.33it/s]
 59%|█████▉    | 220004/371472 [6:50:08<12:48:04,  3.29it/s]
 59%|█████▉    | 220005/371472 [6:50:08<12:25:09,  3.39it/s]
 59%|█████▉    | 220006/371472 [6:50:08<12:14:47,  3.44it/s]
 59%|█████▉    | 220007/371472 [6:50:09<13:21:54,  3.15it/s]
 59%|█████▉    | 220008/371472 [6:50:09<13:20:37,  3.15it/s]
 59%|█████▉    | 220009/371472 [6:50:10<13:29:04,  3.12it/s]
 59%|█████▉    | 220010/371472 [6:50:10<13:21:08,  3.15it/s]
 59%|█████▉    | 220011/371472 [6:50:10<13:11:32,  3.19it/s]
 59%|█████▉    | 220012/371472 [6:50:10<13:31:59,  3.11it/s]
 59%|█████▉    | 220013/371472 [6:50:11<13:10:30,  3.19it/s]
 59%|█████▉    | 220014/371472 [6:50:11<12:27:18,  3.38it/s]
 59%|█████▉    | 220015/371472 [6:50:11<12:49:07,  3.28it/s]
 59%|█████▉    | 220016/371472 [6:50:12<12:37:03,  3.33it/s]
 59%|█████▉    | 220017/371472 [6:50:12<12:32:52,  3.35it/s]
 59%|█████▉    | 220018/371472 [6:50:12<12:38:26,  3.33it/s]
 59%|█████▉    | 220019/371472 [6:50:12<12:01:22,  3.50it/s]
 59%|█████▉    | 220020/371472 [6:50:13<11:55:20,  3.53it/s]
                                                            
{'loss': 2.7057, 'learning_rate': 4.67134607511474e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220020/371472 [6:50:13<11:55:20,  3.53it/s]
 59%|█████▉    | 220021/371472 [6:50:13<11:58:55,  3.51it/s]
 59%|█████▉    | 220022/371472 [6:50:13<11:57:16,  3.52it/s]
 59%|█████▉    | 220023/371472 [6:50:14<12:10:35,  3.45it/s]
 59%|█████▉    | 220024/371472 [6:50:14<14:09:39,  2.97it/s]
 59%|█████▉    | 220025/371472 [6:50:14<13:20:47,  3.15it/s]
 59%|█████▉    | 220026/371472 [6:50:15<12:51:08,  3.27it/s]
 59%|█████▉    | 220027/371472 [6:50:15<14:14:08,  2.96it/s]
 59%|█████▉    | 220028/371472 [6:50:15<14:08:47,  2.97it/s]
 59%|█████▉    | 220029/371472 [6:50:16<13:32:53,  3.11it/s]
 59%|█████▉    | 220030/371472 [6:50:16<13:25:32,  3.13it/s]
 59%|█████▉    | 220031/371472 [6:50:16<12:47:40,  3.29it/s]
 59%|█████▉    | 220032/371472 [6:50:17<13:27:06,  3.13it/s]
 59%|█████▉    | 220033/371472 [6:50:17<12:52:01,  3.27it/s]
 59%|█████▉    | 220034/371472 [6:50:17<12:34:03,  3.35it/s]
 59%|█████▉    | 220035/371472 [6:50:17<12:13:10,  3.44it/s]
 59%|█████▉    | 220036/371472 [6:50:18<12:59:25,  3.24it/s]
 59%|█████▉    | 220037/371472 [6:50:18<12:57:58,  3.24it/s]
 59%|█████▉    | 220038/371472 [6:50:18<12:59:32,  3.24it/s]
 59%|█████▉    | 220039/371472 [6:50:19<12:39:58,  3.32it/s]
 59%|█████▉    | 220040/371472 [6:50:19<12:27:23,  3.38it/s]
                                                            
{'loss': 2.6057, 'learning_rate': 4.6708612553599515e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220040/371472 [6:50:19<12:27:23,  3.38it/s]
 59%|█████▉    | 220041/371472 [6:50:19<12:17:21,  3.42it/s]
 59%|█████▉    | 220042/371472 [6:50:20<12:11:15,  3.45it/s]
 59%|█████▉    | 220043/371472 [6:50:20<12:04:54,  3.48it/s]
 59%|█████▉    | 220044/371472 [6:50:20<12:40:51,  3.32it/s]
 59%|█████▉    | 220045/371472 [6:50:20<12:20:16,  3.41it/s]
 59%|█████▉    | 220046/371472 [6:50:21<12:07:18,  3.47it/s]
 59%|█████▉    | 220047/371472 [6:50:21<12:15:54,  3.43it/s]
 59%|█████▉    | 220048/371472 [6:50:21<12:11:09,  3.45it/s]
 59%|█████▉    | 220049/371472 [6:50:22<13:34:09,  3.10it/s]
 59%|█████▉    | 220050/371472 [6:50:22<13:02:27,  3.23it/s]
 59%|█████▉    | 220051/371472 [6:50:22<13:02:22,  3.23it/s]
 59%|█████▉    | 220052/371472 [6:50:23<13:01:58,  3.23it/s]
 59%|█████▉    | 220053/371472 [6:50:23<13:07:09,  3.21it/s]
 59%|█████▉    | 220054/371472 [6:50:23<12:28:43,  3.37it/s]
 59%|█████▉    | 220055/371472 [6:50:23<12:48:36,  3.28it/s]
 59%|█████▉    | 220056/371472 [6:50:24<13:54:12,  3.03it/s]
 59%|█████▉    | 220057/371472 [6:50:24<13:28:18,  3.12it/s]
 59%|█████▉    | 220058/371472 [6:50:24<12:42:32,  3.31it/s]
 59%|█████▉    | 220059/371472 [6:50:25<12:43:21,  3.31it/s]
 59%|█████▉    | 220060/371472 [6:50:25<12:31:33,  3.36it/s]
                                                            
{'loss': 2.7621, 'learning_rate': 4.670376435605162e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220060/371472 [6:50:25<12:31:33,  3.36it/s]
 59%|█████▉    | 220061/371472 [6:50:25<12:24:49,  3.39it/s]
 59%|█████▉    | 220062/371472 [6:50:26<12:06:47,  3.47it/s]
 59%|█████▉    | 220063/371472 [6:50:26<12:10:04,  3.46it/s]
 59%|█████▉    | 220064/371472 [6:50:26<12:24:27,  3.39it/s]
 59%|█████▉    | 220065/371472 [6:50:26<12:11:26,  3.45it/s]
 59%|█████▉    | 220066/371472 [6:50:27<11:57:20,  3.52it/s]
 59%|█████▉    | 220067/371472 [6:50:27<12:01:14,  3.50it/s]
 59%|█████▉    | 220068/371472 [6:50:27<12:23:30,  3.39it/s]
 59%|█████▉    | 220069/371472 [6:50:28<13:02:24,  3.23it/s]
 59%|█████▉    | 220070/371472 [6:50:28<13:13:05,  3.18it/s]
 59%|█████▉    | 220071/371472 [6:50:28<13:04:01,  3.22it/s]
 59%|█████▉    | 220072/371472 [6:50:29<13:01:10,  3.23it/s]
 59%|█████▉    | 220073/371472 [6:50:29<12:44:27,  3.30it/s]
 59%|█████▉    | 220074/371472 [6:50:29<13:02:44,  3.22it/s]
 59%|█████▉    | 220075/371472 [6:50:30<13:13:23,  3.18it/s]
 59%|█████▉    | 220076/371472 [6:50:30<12:40:05,  3.32it/s]
 59%|█████▉    | 220077/371472 [6:50:30<12:17:54,  3.42it/s]
 59%|█████▉    | 220078/371472 [6:50:30<12:59:32,  3.24it/s]
 59%|█████▉    | 220079/371472 [6:50:31<13:02:26,  3.22it/s]
 59%|█████▉    | 220080/371472 [6:50:31<13:25:05,  3.13it/s]
                                                            
{'loss': 2.812, 'learning_rate': 4.6698916158503735e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220080/371472 [6:50:31<13:25:05,  3.13it/s]
 59%|█████▉    | 220081/371472 [6:50:31<13:04:57,  3.21it/s]
 59%|█████▉    | 220082/371472 [6:50:32<12:55:50,  3.25it/s]
 59%|█████▉    | 220083/371472 [6:50:32<12:55:26,  3.25it/s]
 59%|█████▉    | 220084/371472 [6:50:32<12:50:09,  3.28it/s]
 59%|█████▉    | 220085/371472 [6:50:33<12:42:04,  3.31it/s]
 59%|█████▉    | 220086/371472 [6:50:33<12:44:51,  3.30it/s]
 59%|█████▉    | 220087/371472 [6:50:33<12:47:45,  3.29it/s]
 59%|█████▉    | 220088/371472 [6:50:34<13:17:24,  3.16it/s]
 59%|█████▉    | 220089/371472 [6:50:34<13:28:21,  3.12it/s]
 59%|█████▉    | 220090/371472 [6:50:34<13:21:14,  3.15it/s]
 59%|█████▉    | 220091/371472 [6:50:34<13:01:30,  3.23it/s]
 59%|█████▉    | 220092/371472 [6:50:35<12:52:01,  3.27it/s]
 59%|█████▉    | 220093/371472 [6:50:35<12:31:39,  3.36it/s]
 59%|█████▉    | 220094/371472 [6:50:35<12:08:12,  3.46it/s]
 59%|█████▉    | 220095/371472 [6:50:36<12:14:42,  3.43it/s]
 59%|█████▉    | 220096/371472 [6:50:36<12:29:21,  3.37it/s]
 59%|█████▉    | 220097/371472 [6:50:36<13:05:50,  3.21it/s]
 59%|█████▉    | 220098/371472 [6:50:37<13:18:52,  3.16it/s]
 59%|█████▉    | 220099/371472 [6:50:37<13:19:01,  3.16it/s]
 59%|█████▉    | 220100/371472 [6:50:37<13:13:38,  3.18it/s]
                                                            
{'loss': 2.6328, 'learning_rate': 4.669406796095584e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220100/371472 [6:50:37<13:13:38,  3.18it/s]
 59%|█████▉    | 220101/371472 [6:50:38<13:12:45,  3.18it/s]
 59%|█████▉    | 220102/371472 [6:50:38<13:51:15,  3.03it/s]
 59%|█████▉    | 220103/371472 [6:50:38<13:20:22,  3.15it/s]
 59%|█████▉    | 220104/371472 [6:50:38<12:46:11,  3.29it/s]
 59%|█████▉    | 220105/371472 [6:50:39<12:11:42,  3.45it/s]
 59%|█████▉    | 220106/371472 [6:50:39<12:12:27,  3.44it/s]
 59%|█████▉    | 220107/371472 [6:50:39<11:43:56,  3.58it/s]
 59%|█████▉    | 220108/371472 [6:50:40<11:36:48,  3.62it/s]
 59%|█████▉    | 220109/371472 [6:50:40<11:46:26,  3.57it/s]
 59%|█████▉    | 220110/371472 [6:50:40<11:32:55,  3.64it/s]
 59%|█████▉    | 220111/371472 [6:50:40<11:31:30,  3.65it/s]
 59%|█████▉    | 220112/371472 [6:50:41<11:12:06,  3.75it/s]
 59%|█████▉    | 220113/371472 [6:50:41<11:34:24,  3.63it/s]
 59%|█████▉    | 220114/371472 [6:50:41<11:14:49,  3.74it/s]
 59%|█████▉    | 220115/371472 [6:50:41<11:34:39,  3.63it/s]
 59%|█████▉    | 220116/371472 [6:50:42<11:36:33,  3.62it/s]
 59%|█████▉    | 220117/371472 [6:50:42<11:46:45,  3.57it/s]
 59%|█████▉    | 220118/371472 [6:50:42<11:44:45,  3.58it/s]
 59%|█████▉    | 220119/371472 [6:50:43<12:05:25,  3.48it/s]
 59%|█████▉    | 220120/371472 [6:50:43<12:15:56,  3.43it/s]
                                                            
{'loss': 2.8228, 'learning_rate': 4.668921976340796e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220120/371472 [6:50:43<12:15:56,  3.43it/s]
 59%|█████▉    | 220121/371472 [6:50:43<12:14:50,  3.43it/s]
 59%|█████▉    | 220122/371472 [6:50:43<12:06:37,  3.47it/s]
 59%|█████▉    | 220123/371472 [6:50:44<12:04:54,  3.48it/s]
 59%|█████▉    | 220124/371472 [6:50:44<12:59:56,  3.23it/s]
 59%|█████▉    | 220125/371472 [6:50:44<12:42:09,  3.31it/s]
 59%|█████▉    | 220126/371472 [6:50:45<12:18:59,  3.41it/s]
 59%|█████▉    | 220127/371472 [6:50:45<12:04:26,  3.48it/s]
 59%|█████▉    | 220128/371472 [6:50:45<11:50:36,  3.55it/s]
 59%|█████▉    | 220129/371472 [6:50:46<12:06:49,  3.47it/s]
 59%|█████▉    | 220130/371472 [6:50:46<11:58:27,  3.51it/s]
 59%|█████▉    | 220131/371472 [6:50:46<13:01:51,  3.23it/s]
 59%|█████▉    | 220132/371472 [6:50:46<12:38:18,  3.33it/s]
 59%|█████▉    | 220133/371472 [6:50:47<13:26:00,  3.13it/s]
 59%|█████▉    | 220134/371472 [6:50:47<12:58:35,  3.24it/s]
 59%|█████▉    | 220135/371472 [6:50:47<13:00:49,  3.23it/s]
 59%|█████▉    | 220136/371472 [6:50:48<12:42:54,  3.31it/s]
 59%|█████▉    | 220137/371472 [6:50:48<12:12:58,  3.44it/s]
 59%|█████▉    | 220138/371472 [6:50:48<12:16:42,  3.42it/s]
 59%|█████▉    | 220139/371472 [6:50:49<12:32:30,  3.35it/s]
 59%|█████▉    | 220140/371472 [6:50:49<12:25:25,  3.38it/s]
                                                            
{'loss': 2.7412, 'learning_rate': 4.6684371565860067e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220140/371472 [6:50:49<12:25:25,  3.38it/s]
 59%|█████▉    | 220141/371472 [6:50:49<12:09:21,  3.46it/s]
 59%|█████▉    | 220142/371472 [6:50:49<12:06:55,  3.47it/s]
 59%|█████▉    | 220143/371472 [6:50:50<12:16:18,  3.43it/s]
 59%|█████▉    | 220144/371472 [6:50:50<13:20:29,  3.15it/s]
 59%|█████▉    | 220145/371472 [6:50:50<12:50:31,  3.27it/s]
 59%|█████▉    | 220146/371472 [6:50:51<12:27:55,  3.37it/s]
 59%|█████▉    | 220147/371472 [6:50:51<13:00:09,  3.23it/s]
 59%|█████▉    | 220148/371472 [6:50:51<12:28:40,  3.37it/s]
 59%|█████▉    | 220149/371472 [6:50:52<12:13:49,  3.44it/s]
 59%|█████▉    | 220150/371472 [6:50:52<12:17:51,  3.42it/s]
 59%|█████▉    | 220151/371472 [6:50:52<12:30:43,  3.36it/s]
 59%|█████▉    | 220152/371472 [6:50:52<12:27:11,  3.38it/s]
 59%|█████▉    | 220153/371472 [6:50:53<12:37:18,  3.33it/s]
 59%|█████▉    | 220154/371472 [6:50:53<12:46:36,  3.29it/s]
 59%|█████▉    | 220155/371472 [6:50:53<12:52:13,  3.27it/s]
 59%|█████▉    | 220156/371472 [6:50:54<13:28:21,  3.12it/s]
 59%|█████▉    | 220157/371472 [6:50:54<12:40:26,  3.32it/s]
 59%|█████▉    | 220158/371472 [6:50:54<12:27:18,  3.37it/s]
 59%|█████▉    | 220159/371472 [6:50:55<12:19:27,  3.41it/s]
 59%|█████▉    | 220160/371472 [6:50:55<12:15:13,  3.43it/s]
                                                            
{'loss': 2.8407, 'learning_rate': 4.667952336831218e-07, 'epoch': 9.48}
+
 59%|██���██▉    | 220160/371472 [6:50:55<12:15:13,  3.43it/s]
 59%|█████▉    | 220161/371472 [6:50:55<12:14:42,  3.43it/s]
 59%|█████▉    | 220162/371472 [6:50:55<12:08:36,  3.46it/s]
 59%|█████▉    | 220163/371472 [6:50:56<11:45:23,  3.58it/s]
 59%|█████▉    | 220164/371472 [6:50:56<11:24:47,  3.68it/s]
 59%|█████▉    | 220165/371472 [6:50:56<11:36:25,  3.62it/s]
 59%|█████▉    | 220166/371472 [6:50:56<11:47:05,  3.57it/s]
 59%|█████▉    | 220167/371472 [6:50:57<11:42:05,  3.59it/s]
 59%|█████▉    | 220168/371472 [6:50:57<11:34:01,  3.63it/s]
 59%|█████▉    | 220169/371472 [6:50:57<11:44:16,  3.58it/s]
 59%|█████▉    | 220170/371472 [6:50:58<12:20:34,  3.41it/s]
 59%|█████▉    | 220171/371472 [6:50:58<12:19:00,  3.41it/s]
 59%|█████▉    | 220172/371472 [6:50:58<12:11:22,  3.45it/s]
 59%|█████▉    | 220173/371472 [6:50:59<12:05:36,  3.48it/s]
 59%|█████▉    | 220174/371472 [6:50:59<12:09:20,  3.46it/s]
 59%|█████▉    | 220175/371472 [6:50:59<11:55:55,  3.52it/s]
 59%|█████▉    | 220176/371472 [6:50:59<12:17:37,  3.42it/s]
 59%|█████▉    | 220177/371472 [6:51:00<12:18:42,  3.41it/s]
 59%|█████▉    | 220178/371472 [6:51:00<11:55:56,  3.52it/s]
 59%|█████▉    | 220179/371472 [6:51:00<11:55:41,  3.52it/s]
 59%|█████▉    | 220180/371472 [6:51:01<12:23:40,  3.39it/s]
                                                            
{'loss': 2.8508, 'learning_rate': 4.6674675170764286e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220180/371472 [6:51:01<12:23:40,  3.39it/s]
 59%|█████▉    | 220181/371472 [6:51:01<12:36:50,  3.33it/s]
 59%|█████▉    | 220182/371472 [6:51:01<12:27:00,  3.38it/s]
 59%|█████▉    | 220183/371472 [6:51:01<12:33:01,  3.35it/s]
 59%|█████▉    | 220184/371472 [6:51:02<12:33:54,  3.34it/s]
 59%|█████▉    | 220185/371472 [6:51:02<12:13:14,  3.44it/s]
 59%|█████▉    | 220186/371472 [6:51:02<12:23:33,  3.39it/s]
 59%|█████▉    | 220187/371472 [6:51:03<12:10:14,  3.45it/s]
 59%|█████▉    | 220188/371472 [6:51:03<12:23:24,  3.39it/s]
 59%|█████▉    | 220189/371472 [6:51:03<12:32:19,  3.35it/s]
 59%|█████▉    | 220190/371472 [6:51:04<13:04:28,  3.21it/s]
 59%|█████▉    | 220191/371472 [6:51:04<13:04:13,  3.22it/s]
 59%|█████▉    | 220192/371472 [6:51:04<12:51:59,  3.27it/s]
 59%|█████▉    | 220193/371472 [6:51:04<12:52:45,  3.26it/s]
 59%|█████▉    | 220194/371472 [6:51:05<13:31:38,  3.11it/s]
 59%|█████▉    | 220195/371472 [6:51:05<14:01:04,  3.00it/s]
 59%|█████▉    | 220196/371472 [6:51:05<13:13:38,  3.18it/s]
 59%|█████▉    | 220197/371472 [6:51:06<12:51:45,  3.27it/s]
 59%|█████▉    | 220198/371472 [6:51:06<13:15:53,  3.17it/s]
 59%|█████▉    | 220199/371472 [6:51:06<12:43:47,  3.30it/s]
 59%|█████▉    | 220200/371472 [6:51:07<12:53:04,  3.26it/s]
                                                            
{'loss': 2.8285, 'learning_rate': 4.6669826973216404e-07, 'epoch': 9.48}
+
 59%|█████▉    | 220200/371472 [6:51:07<12:53:04,  3.26it/s]
 59%|█████▉    | 220201/371472 [6:51:07<13:56:57,  3.01it/s]
 59%|█████▉    | 220202/371472 [6:51:07<14:00:07,  3.00it/s]
 59%|█████▉    | 220203/371472 [6:51:08<13:17:26,  3.16it/s]
 59%|█████▉    | 220204/371472 [6:51:08<13:09:23,  3.19it/s]
 59%|█████▉    | 220205/371472 [6:51:08<12:43:43,  3.30it/s]
 59%|█████▉    | 220206/371472 [6:51:09<12:30:32,  3.36it/s]
 59%|█████▉    | 220207/371472 [6:51:09<12:30:26,  3.36it/s]
 59%|█████▉    | 220208/371472 [6:51:09<12:26:45,  3.38it/s]
 59%|█████▉    | 220209/371472 [6:51:09<13:01:45,  3.22it/s]
 59%|█████▉    | 220210/371472 [6:51:10<13:04:51,  3.21it/s]
 59%|█████▉    | 220211/371472 [6:51:10<12:44:59,  3.30it/s]
 59%|█████▉    | 220212/371472 [6:51:10<12:25:16,  3.38it/s]
 59%|█████▉    | 220213/371472 [6:51:11<12:00:31,  3.50it/s]
 59%|█████▉    | 220214/371472 [6:51:11<11:45:58,  3.57it/s]
 59%|█████▉    | 220215/371472 [6:51:11<11:56:12,  3.52it/s]
 59%|█████▉    | 220216/371472 [6:51:11<11:43:12,  3.58it/s]
 59%|█████▉    | 220217/371472 [6:51:12<11:38:19,  3.61it/s]
 59%|█████▉    | 220218/371472 [6:51:12<12:29:21,  3.36it/s]
 59%|█████▉    | 220219/371472 [6:51:12<12:32:40,  3.35it/s]
 59%|█████▉    | 220220/371472 [6:51:13<12:57:44,  3.24it/s]
                                                            
{'loss': 2.7229, 'learning_rate': 4.6664978775668506e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220220/371472 [6:51:13<12:57:44,  3.24it/s]
 59%|█████▉    | 220221/371472 [6:51:13<13:30:49,  3.11it/s]
 59%|█████▉    | 220222/371472 [6:51:13<13:19:29,  3.15it/s]
 59%|█████▉    | 220223/371472 [6:51:14<13:21:28,  3.15it/s]
 59%|█████▉    | 220224/371472 [6:51:14<13:41:08,  3.07it/s]
 59%|█████▉    | 220225/371472 [6:51:14<13:08:56,  3.20it/s]
 59%|█████▉    | 220226/371472 [6:51:15<12:53:41,  3.26it/s]
 59%|█████▉    | 220227/371472 [6:51:15<12:30:18,  3.36it/s]
 59%|█████▉    | 220228/371472 [6:51:15<12:30:24,  3.36it/s]
 59%|█████▉    | 220229/371472 [6:51:15<12:23:38,  3.39it/s]
 59%|█████▉    | 220230/371472 [6:51:16<12:12:13,  3.44it/s]
 59%|█████▉    | 220231/371472 [6:51:16<12:08:42,  3.46it/s]
 59%|█████▉    | 220232/371472 [6:51:16<12:35:01,  3.34it/s]
 59%|█████▉    | 220233/371472 [6:51:17<12:25:26,  3.38it/s]
 59%|█████▉    | 220234/371472 [6:51:17<12:10:06,  3.45it/s]
 59%|█████▉    | 220235/371472 [6:51:17<12:30:00,  3.36it/s]
 59%|█████▉    | 220236/371472 [6:51:18<12:27:37,  3.37it/s]
 59%|█████▉    | 220237/371472 [6:51:18<12:16:40,  3.42it/s]
 59%|█████▉    | 220238/371472 [6:51:18<12:17:20,  3.42it/s]
 59%|█████▉    | 220239/371472 [6:51:18<11:57:16,  3.51it/s]
 59%|█████▉    | 220240/371472 [6:51:19<11:53:45,  3.53it/s]
                                                            
{'loss': 2.773, 'learning_rate': 4.6660130578120624e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220240/371472 [6:51:19<11:53:45,  3.53it/s]
 59%|█████▉    | 220241/371472 [6:51:19<14:38:12,  2.87it/s]
 59%|█████▉    | 220242/371472 [6:51:20<15:17:19,  2.75it/s]
 59%|█████▉    | 220243/371472 [6:51:20<14:26:48,  2.91it/s]
 59%|█████▉    | 220244/371472 [6:51:20<13:49:45,  3.04it/s]
 59%|█████▉    | 220245/371472 [6:51:20<14:00:31,  3.00it/s]
 59%|█████▉    | 220246/371472 [6:51:21<13:20:30,  3.15it/s]
 59%|█████▉    | 220247/371472 [6:51:21<13:14:17,  3.17it/s]
 59%|█████▉    | 220248/371472 [6:51:21<13:23:56,  3.14it/s]
 59%|█████▉    | 220249/371472 [6:51:22<13:05:04,  3.21it/s]
 59%|█████▉    | 220250/371472 [6:51:22<12:46:39,  3.29it/s]
 59%|█████▉    | 220251/371472 [6:51:22<13:00:52,  3.23it/s]
 59%|█████▉    | 220252/371472 [6:51:23<12:39:22,  3.32it/s]
 59%|█████▉    | 220253/371472 [6:51:23<12:30:30,  3.36it/s]
 59%|█████▉    | 220254/371472 [6:51:23<12:35:52,  3.33it/s]
 59%|█████▉    | 220255/371472 [6:51:23<12:17:28,  3.42it/s]
 59%|█████▉    | 220256/371472 [6:51:24<12:18:31,  3.41it/s]
 59%|█████▉    | 220257/371472 [6:51:24<12:07:52,  3.46it/s]
 59%|█████▉    | 220258/371472 [6:51:24<11:40:42,  3.60it/s]
 59%|█████▉    | 220259/371472 [6:51:25<11:43:19,  3.58it/s]
 59%|█████▉    | 220260/371472 [6:51:25<12:05:44,  3.47it/s]
                                                            
{'loss': 2.7426, 'learning_rate': 4.665528238057273e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220260/371472 [6:51:25<12:05:44,  3.47it/s]
 59%|█████▉    | 220261/371472 [6:51:25<13:13:42,  3.18it/s]
 59%|█████▉    | 220262/371472 [6:51:26<13:00:22,  3.23it/s]
 59%|█████▉    | 220263/371472 [6:51:26<13:20:42,  3.15it/s]
 59%|█████▉    | 220264/371472 [6:51:26<12:54:12,  3.26it/s]
 59%|█████▉    | 220265/371472 [6:51:26<13:03:54,  3.21it/s]
 59%|█████▉    | 220266/371472 [6:51:27<12:58:10,  3.24it/s]
 59%|█████▉    | 220267/371472 [6:51:27<12:31:35,  3.35it/s]
 59%|█████▉    | 220268/371472 [6:51:27<12:42:28,  3.31it/s]
 59%|█████▉    | 220269/371472 [6:51:28<12:41:29,  3.31it/s]
 59%|█████▉    | 220270/371472 [6:51:28<12:34:23,  3.34it/s]
 59%|█████▉    | 220271/371472 [6:51:28<12:26:44,  3.37it/s]
 59%|█████▉    | 220272/371472 [6:51:29<12:18:29,  3.41it/s]
 59%|█████▉    | 220273/371472 [6:51:29<12:26:19,  3.38it/s]
 59%|█████▉    | 220274/371472 [6:51:29<12:44:23,  3.30it/s]
 59%|█████▉    | 220275/371472 [6:51:29<12:27:42,  3.37it/s]
 59%|█████▉    | 220276/371472 [6:51:30<12:16:16,  3.42it/s]
 59%|█████▉    | 220277/371472 [6:51:30<12:12:04,  3.44it/s]
 59%|█████▉    | 220278/371472 [6:51:30<13:05:35,  3.21it/s]
 59%|█████▉    | 220279/371472 [6:51:31<12:44:00,  3.30it/s]
 59%|█████▉    | 220280/371472 [6:51:31<12:16:53,  3.42it/s]
                                                            
{'loss': 2.8881, 'learning_rate': 4.6650434183024843e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220280/371472 [6:51:31<12:16:53,  3.42it/s]
 59%|█████▉    | 220281/371472 [6:51:31<11:51:03,  3.54it/s]
 59%|█████▉    | 220282/371472 [6:51:32<12:40:08,  3.31it/s]
 59%|█████���    | 220283/371472 [6:51:32<13:14:28,  3.17it/s]
 59%|█████▉    | 220284/371472 [6:51:32<12:43:29,  3.30it/s]
 59%|█████▉    | 220285/371472 [6:51:32<13:02:19,  3.22it/s]
 59%|█████▉    | 220286/371472 [6:51:33<13:44:37,  3.06it/s]
 59%|█████▉    | 220287/371472 [6:51:33<13:02:09,  3.22it/s]
 59%|█████▉    | 220288/371472 [6:51:34<14:36:39,  2.87it/s]
 59%|█████▉    | 220289/371472 [6:51:34<14:19:49,  2.93it/s]
 59%|█████▉    | 220290/371472 [6:51:34<13:21:15,  3.14it/s]
 59%|█████▉    | 220291/371472 [6:51:34<13:13:43,  3.17it/s]
 59%|█████▉    | 220292/371472 [6:51:35<13:09:33,  3.19it/s]
 59%|█████▉    | 220293/371472 [6:51:35<12:43:59,  3.30it/s]
 59%|█████▉    | 220294/371472 [6:51:35<12:33:43,  3.34it/s]
 59%|█████▉    | 220295/371472 [6:51:36<12:40:13,  3.31it/s]
 59%|█████▉    | 220296/371472 [6:51:36<13:16:12,  3.16it/s]
 59%|█████▉    | 220297/371472 [6:51:36<12:53:14,  3.26it/s]
 59%|█████▉    | 220298/371472 [6:51:37<12:45:13,  3.29it/s]
 59%|█████▉    | 220299/371472 [6:51:37<12:32:21,  3.35it/s]
 59%|█████▉    | 220300/371472 [6:51:37<12:13:38,  3.43it/s]
                                                            
{'loss': 2.6345, 'learning_rate': 4.664558598547695e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220300/371472 [6:51:37<12:13:38,  3.43it/s]
 59%|█████▉    | 220301/371472 [6:51:37<12:17:10,  3.42it/s]
 59%|█████▉    | 220302/371472 [6:51:38<11:53:37,  3.53it/s]
 59%|█████▉    | 220303/371472 [6:51:38<14:54:57,  2.82it/s]
 59%|█████▉    | 220304/371472 [6:51:38<13:54:52,  3.02it/s]
 59%|█████▉    | 220305/371472 [6:51:39<13:26:47,  3.12it/s]
 59%|█████▉    | 220306/371472 [6:51:39<12:56:30,  3.24it/s]
 59%|█████▉    | 220307/371472 [6:51:39<12:48:01,  3.28it/s]
 59%|█████▉    | 220308/371472 [6:51:40<12:32:37,  3.35it/s]
 59%|█████▉    | 220309/371472 [6:51:40<12:16:11,  3.42it/s]
 59%|█████▉    | 220310/371472 [6:51:40<12:01:07,  3.49it/s]
 59%|█████▉    | 220311/371472 [6:51:41<12:46:32,  3.29it/s]
 59%|█████▉    | 220312/371472 [6:51:41<13:01:28,  3.22it/s]
 59%|█████▉    | 220313/371472 [6:51:41<13:22:40,  3.14it/s]
 59%|█████▉    | 220314/371472 [6:51:41<12:46:27,  3.29it/s]
 59%|█████▉    | 220315/371472 [6:51:42<12:38:08,  3.32it/s]
 59%|█████▉    | 220316/371472 [6:51:42<12:07:59,  3.46it/s]
 59%|█████▉    | 220317/371472 [6:51:42<12:00:26,  3.50it/s]
 59%|█████▉    | 220318/371472 [6:51:43<11:42:06,  3.59it/s]
 59%|█████▉    | 220319/371472 [6:51:43<12:07:17,  3.46it/s]
 59%|█████▉    | 220320/371472 [6:51:43<12:00:27,  3.50it/s]
                                                            
{'loss': 2.7257, 'learning_rate': 4.664073778792907e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220320/371472 [6:51:43<12:00:27,  3.50it/s]
 59%|█████▉    | 220321/371472 [6:51:43<11:55:47,  3.52it/s]
 59%|█████▉    | 220322/371472 [6:51:44<12:35:45,  3.33it/s]
 59%|█████▉    | 220323/371472 [6:51:44<12:21:22,  3.40it/s]
 59%|█████▉    | 220324/371472 [6:51:44<12:15:30,  3.43it/s]
 59%|█████▉    | 220325/371472 [6:51:45<12:14:49,  3.43it/s]
 59%|█████▉    | 220326/371472 [6:51:45<11:53:54,  3.53it/s]
 59%|█████▉    | 220327/371472 [6:51:45<11:42:35,  3.59it/s]
 59%|█████▉    | 220328/371472 [6:51:45<11:53:17,  3.53it/s]
 59%|█████▉    | 220329/371472 [6:51:46<12:11:34,  3.44it/s]
 59%|█████▉    | 220330/371472 [6:51:46<11:55:38,  3.52it/s]
 59%|█████▉    | 220331/371472 [6:51:46<13:12:24,  3.18it/s]
 59%|█████▉    | 220332/371472 [6:51:47<12:25:54,  3.38it/s]
 59%|█████▉    | 220333/371472 [6:51:47<12:28:39,  3.36it/s]
 59%|█████▉    | 220334/371472 [6:51:47<12:00:56,  3.49it/s]
 59%|█████▉    | 220335/371472 [6:51:48<12:00:56,  3.49it/s]
 59%|█████▉    | 220336/371472 [6:51:48<11:48:44,  3.55it/s]
 59%|█████▉    | 220337/371472 [6:51:48<11:57:45,  3.51it/s]
 59%|█████▉    | 220338/371472 [6:51:48<11:48:26,  3.56it/s]
 59%|█████▉    | 220339/371472 [6:51:49<11:49:38,  3.55it/s]
 59%|█████▉    | 220340/371472 [6:51:49<11:44:43,  3.57it/s]
                                                            
{'loss': 2.8465, 'learning_rate': 4.663588959038117e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220340/371472 [6:51:49<11:44:43,  3.57it/s]
 59%|█████▉    | 220341/371472 [6:51:49<12:00:13,  3.50it/s]
 59%|█████▉    | 220342/371472 [6:51:49<11:58:12,  3.51it/s]
 59%|█████▉    | 220343/371472 [6:51:50<12:12:58,  3.44it/s]
 59%|█████▉    | 220344/371472 [6:51:50<12:09:08,  3.45it/s]
 59%|█████▉    | 220345/371472 [6:51:50<11:59:18,  3.50it/s]
 59%|█████▉    | 220346/371472 [6:51:51<12:08:42,  3.46it/s]
 59%|█████▉    | 220347/371472 [6:51:51<12:02:30,  3.49it/s]
 59%|█████▉    | 220348/371472 [6:51:51<11:40:16,  3.60it/s]
 59%|█████▉    | 220349/371472 [6:51:51<11:42:55,  3.58it/s]
 59%|█████▉    | 220350/371472 [6:51:52<12:10:31,  3.45it/s]
 59%|█████▉    | 220351/371472 [6:51:52<11:58:52,  3.50it/s]
 59%|█████▉    | 220352/371472 [6:51:52<11:52:29,  3.53it/s]
 59%|█████▉    | 220353/371472 [6:51:53<11:45:05,  3.57it/s]
 59%|█████▉    | 220354/371472 [6:51:53<12:06:20,  3.47it/s]
 59%|█████▉    | 220355/371472 [6:51:53<13:01:02,  3.22it/s]
 59%|█████▉    | 220356/371472 [6:51:54<13:01:46,  3.22it/s]
 59%|█████▉    | 220357/371472 [6:51:54<12:47:48,  3.28it/s]
 59%|█████▉    | 220358/371472 [6:51:54<12:11:02,  3.45it/s]
 59%|█████▉    | 220359/371472 [6:51:54<12:03:12,  3.48it/s]
 59%|█████▉    | 220360/371472 [6:51:55<12:04:37,  3.48it/s]
                                                            
{'loss': 2.9037, 'learning_rate': 4.663104139283329e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220360/371472 [6:51:55<12:04:37,  3.48it/s]
 59%|█████▉    | 220361/371472 [6:51:55<12:07:07,  3.46it/s]
 59%|█████▉    | 220362/371472 [6:51:55<12:12:21,  3.44it/s]
 59%|█████▉    | 220363/371472 [6:51:56<12:24:23,  3.38it/s]
 59%|█████▉    | 220364/371472 [6:51:56<12:09:32,  3.45it/s]
 59%|█████▉    | 220365/371472 [6:51:56<11:58:28,  3.51it/s]
 59%|█████▉    | 220366/371472 [6:51:56<11:57:35,  3.51it/s]
 59%|█████▉    | 220367/371472 [6:51:57<12:24:23,  3.38it/s]
 59%|█████▉    | 220368/371472 [6:51:57<12:35:14,  3.33it/s]
 59%|█████▉    | 220369/371472 [6:51:57<12:33:19,  3.34it/s]
 59%|█████▉    | 220370/371472 [6:51:58<12:31:29,  3.35it/s]
 59%|█████▉    | 220371/371472 [6:51:58<12:33:12,  3.34it/s]
 59%|█████▉    | 220372/371472 [6:51:58<13:08:11,  3.20it/s]
 59%|█████▉    | 220373/371472 [6:51:59<12:48:50,  3.28it/s]
 59%|█████▉    | 220374/371472 [6:51:59<12:25:58,  3.38it/s]
 59%|█████▉    | 220375/371472 [6:51:59<11:59:17,  3.50it/s]
 59%|█████▉    | 220376/371472 [6:51:59<12:12:07,  3.44it/s]
 59%|█████▉    | 220377/371472 [6:52:00<12:05:18,  3.47it/s]
 59%|█████▉    | 220378/371472 [6:52:00<12:07:07,  3.46it/s]
 59%|█████▉    | 220379/371472 [6:52:00<11:54:19,  3.53it/s]
 59%|█████▉    | 220380/371472 [6:52:01<11:40:17,  3.60it/s]
                                                            
{'loss': 2.7852, 'learning_rate': 4.6626193195285395e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220380/371472 [6:52:01<11:40:17,  3.60it/s]
 59%|█████▉    | 220381/371472 [6:52:01<11:46:42,  3.56it/s]
 59%|█████▉    | 220382/371472 [6:52:01<11:52:33,  3.53it/s]
 59%|█████▉    | 220383/371472 [6:52:01<11:54:59,  3.52it/s]
 59%|█████▉    | 220384/371472 [6:52:02<12:13:07,  3.43it/s]
 59%|█████▉    | 220385/371472 [6:52:02<12:38:45,  3.32it/s]
 59%|█████▉    | 220386/371472 [6:52:02<12:45:37,  3.29it/s]
 59%|█████▉    | 220387/371472 [6:52:03<12:56:11,  3.24it/s]
 59%|█████▉    | 220388/371472 [6:52:03<12:37:25,  3.32it/s]
 59%|█████▉    | 220389/371472 [6:52:03<12:51:35,  3.26it/s]
 59%|█████▉    | 220390/371472 [6:52:04<12:31:01,  3.35it/s]
 59%|█████▉    | 220391/371472 [6:52:04<12:16:04,  3.42it/s]
 59%|█████▉    | 220392/371472 [6:52:04<12:14:50,  3.43it/s]
 59%|█████▉    | 220393/371472 [6:52:04<12:12:21,  3.44it/s]
 59%|█████▉    | 220394/371472 [6:52:05<12:40:02,  3.31it/s]
 59%|█████▉    | 220395/371472 [6:52:05<12:29:02,  3.36it/s]
 59%|█████▉    | 220396/371472 [6:52:05<12:27:20,  3.37it/s]
 59%|█████▉    | 220397/371472 [6:52:06<12:25:20,  3.38it/s]
 59%|█████▉    | 220398/371472 [6:52:06<12:15:20,  3.42it/s]
 59%|█████▉    | 220399/371472 [6:52:06<13:02:51,  3.22it/s]
 59%|█████▉    | 220400/371472 [6:52:07<12:48:06,  3.28it/s]
                                                            
{'loss': 2.7868, 'learning_rate': 4.6621344997737507e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220400/371472 [6:52:07<12:48:06,  3.28it/s]
 59%|█████▉    | 220401/371472 [6:52:07<12:35:01,  3.33it/s]
 59%|█████▉    | 220402/371472 [6:52:07<12:36:03,  3.33it/s]
 59%|█████▉    | 220403/371472 [6:52:07<12:56:47,  3.24it/s]
 59%|█████▉    | 220404/371472 [6:52:08<13:05:20,  3.21it/s]
 59%|█████▉    | 220405/371472 [6:52:08<13:06:09,  3.20it/s]
 59%|█████▉    | 220406/371472 [6:52:08<12:59:11,  3.23it/s]
 59%|█████▉    | 220407/371472 [6:52:09<13:08:36,  3.19it/s]
 59%|█████▉    | 220408/371472 [6:52:09<12:48:49,  3.27it/s]
 59%|█████▉    | 220409/371472 [6:52:09<12:26:27,  3.37it/s]
 59%|█████▉    | 220410/371472 [6:52:10<12:27:52,  3.37it/s]
 59%|█████▉    | 220411/371472 [6:52:10<12:05:11,  3.47it/s]
 59%|█████▉    | 220412/371472 [6:52:10<11:58:41,  3.50it/s]
 59%|█████▉    | 220413/371472 [6:52:10<12:19:10,  3.41it/s]
 59%|█████▉    | 220414/371472 [6:52:11<13:00:51,  3.22it/s]
 59%|█████▉    | 220415/371472 [6:52:11<14:15:20,  2.94it/s]
 59%|█████▉    | 220416/371472 [6:52:11<13:15:03,  3.17it/s]
 59%|█████▉    | 220417/371472 [6:52:12<12:46:32,  3.28it/s]
 59%|█████▉    | 220418/371472 [6:52:12<12:34:36,  3.34it/s]
 59%|█████▉    | 220419/371472 [6:52:12<12:14:33,  3.43it/s]
 59%|█████▉    | 220420/371472 [6:52:13<12:33:53,  3.34it/s]
                                                            
{'loss': 2.692, 'learning_rate': 4.6616496800189614e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220420/371472 [6:52:13<12:33:53,  3.34it/s]
 59%|█████▉    | 220421/371472 [6:52:13<12:26:35,  3.37it/s]
 59%|█████▉    | 220422/371472 [6:52:13<12:05:02,  3.47it/s]
 59%|█████▉    | 220423/371472 [6:52:13<12:12:30,  3.44it/s]
 59%|█████▉    | 220424/371472 [6:52:14<12:35:44,  3.33it/s]
 59%|█████▉    | 220425/371472 [6:52:14<12:12:02,  3.44it/s]
 59%|█████▉    | 220426/371472 [6:52:14<12:11:34,  3.44it/s]
 59%|█████▉    | 220427/371472 [6:52:15<12:03:21,  3.48it/s]
 59%|█████▉    | 220428/371472 [6:52:15<11:45:15,  3.57it/s]
 59%|█████▉    | 220429/371472 [6:52:15<12:14:15,  3.43it/s]
 59%|█████▉    | 220430/371472 [6:52:16<12:07:57,  3.46it/s]
 59%|█████▉    | 220431/371472 [6:52:16<11:58:40,  3.50it/s]
 59%|█████▉    | 220432/371472 [6:52:16<11:55:19,  3.52it/s]
 59%|█████▉    | 220433/371472 [6:52:16<11:50:23,  3.54it/s]
 59%|█████▉    | 220434/371472 [6:52:17<11:54:57,  3.52it/s]
 59%|█████▉    | 220435/371472 [6:52:17<11:55:14,  3.52it/s]
 59%|█████▉    | 220436/371472 [6:52:17<12:45:46,  3.29it/s]
 59%|█████▉    | 220437/371472 [6:52:18<12:59:12,  3.23it/s]
 59%|█████▉    | 220438/371472 [6:52:18<12:34:27,  3.34it/s]
 59%|█████▉    | 220439/371472 [6:52:18<12:13:29,  3.43it/s]
 59%|█████▉    | 220440/371472 [6:52:18<13:10:59,  3.18it/s]
                                                            
{'loss': 2.6847, 'learning_rate': 4.661164860264173e-07, 'epoch': 9.49}
+
 59%|█████▉    | 220440/371472 [6:52:19<13:10:59,  3.18it/s]
 59%|█████▉    | 220441/371472 [6:52:19<12:44:00,  3.29it/s]
 59%|█████▉    | 220442/371472 [6:52:19<12:19:19,  3.40it/s]
 59%|█████▉    | 220443/371472 [6:52:19<12:08:36,  3.45it/s]
 59%|█████▉    | 220444/371472 [6:52:20<12:08:02,  3.46it/s]
 59%|█████▉    | 220445/371472 [6:52:20<11:53:48,  3.53it/s]
 59%|█████▉    | 220446/371472 [6:52:20<12:09:47,  3.45it/s]
 59%|█████▉    | 220447/371472 [6:52:20<11:51:39,  3.54it/s]
 59%|█████▉    | 220448/371472 [6:52:21<12:13:04,  3.43it/s]
 59%|█████▉    | 220449/371472 [6:52:21<12:12:49,  3.43it/s]
 59%|█████▉    | 220450/371472 [6:52:21<12:10:25,  3.45it/s]
 59%|█████▉    | 220451/371472 [6:52:22<13:09:18,  3.19it/s]
 59%|█████▉    | 220452/371472 [6:52:22<12:30:51,  3.35it/s]
 59%|█████▉    | 220453/371472 [6:52:22<12:19:02,  3.41it/s]
 59%|█████▉    | 220454/371472 [6:52:23<12:32:44,  3.34it/s]
 59%|█████▉    | 220455/371472 [6:52:23<12:29:37,  3.36it/s]
 59%|█████▉    | 220456/371472 [6:52:23<13:28:47,  3.11it/s]
 59%|█████▉    | 220457/371472 [6:52:24<13:07:00,  3.20it/s]
 59%|█████▉    | 220458/371472 [6:52:24<12:39:23,  3.31it/s]
 59%|█████▉    | 220459/371472 [6:52:24<12:18:12,  3.41it/s]
 59%|█████▉    | 220460/371472 [6:52:24<12:18:14,  3.41it/s]
                                                            
{'loss': 2.562, 'learning_rate': 4.660680040509384e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220460/371472 [6:52:24<12:18:14,  3.41it/s]
 59%|█████▉    | 220461/371472 [6:52:25<12:30:24,  3.35it/s]
 59%|█████▉    | 220462/371472 [6:52:25<12:36:49,  3.33it/s]
 59%|█████▉    | 220463/371472 [6:52:25<12:26:23,  3.37it/s]
 59%|█████▉    | 220464/371472 [6:52:26<12:12:49,  3.43it/s]
 59%|█████▉    | 220465/371472 [6:52:26<12:01:55,  3.49it/s]
 59%|█████▉    | 220466/371472 [6:52:26<12:32:47,  3.34it/s]
 59%|█████▉    | 220467/371472 [6:52:26<12:29:44,  3.36it/s]
 59%|█████▉    | 220468/371472 [6:52:27<12:52:06,  3.26it/s]
 59%|█████▉    | 220469/371472 [6:52:27<12:40:12,  3.31it/s]
 59%|█████▉    | 220470/371472 [6:52:27<12:43:42,  3.30it/s]
 59%|█████▉    | 220471/371472 [6:52:28<12:28:22,  3.36it/s]
 59%|█████▉    | 220472/371472 [6:52:28<12:11:24,  3.44it/s]
 59%|█████▉    | 220473/371472 [6:52:28<12:08:03,  3.46it/s]
 59%|█████▉    | 220474/371472 [6:52:29<12:41:48,  3.30it/s]
 59%|█████▉    | 220475/371472 [6:52:29<12:22:49,  3.39it/s]
 59%|█████▉    | 220476/371472 [6:52:29<12:01:23,  3.49it/s]
 59%|█████▉    | 220477/371472 [6:52:29<12:31:52,  3.35it/s]
 59%|█████▉    | 220478/371472 [6:52:30<12:11:43,  3.44it/s]
 59%|█████▉    | 220479/371472 [6:52:30<11:46:48,  3.56it/s]
 59%|█████▉    | 220480/371472 [6:52:30<12:25:16,  3.38it/s]
                                                            
{'loss': 2.7846, 'learning_rate': 4.660195220754595e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220480/371472 [6:52:30<12:25:16,  3.38it/s]
 59%|█████▉    | 220481/371472 [6:52:31<13:00:12,  3.23it/s]
 59%|█████▉    | 220482/371472 [6:52:31<12:31:43,  3.35it/s]
 59%|█████▉    | 220483/371472 [6:52:31<12:24:39,  3.38it/s]
 59%|█████▉    | 220484/371472 [6:52:32<12:39:13,  3.31it/s]
 59%|█████▉    | 220485/371472 [6:52:32<12:24:25,  3.38it/s]
 59%|█████▉    | 220486/371472 [6:52:32<12:08:02,  3.46it/s]
 59%|█████▉    | 220487/371472 [6:52:32<12:19:56,  3.40it/s]
 59%|█████▉    | 220488/371472 [6:52:33<12:18:39,  3.41it/s]
 59%|█████▉    | 220489/371472 [6:52:33<12:15:13,  3.42it/s]
 59%|█████▉    | 220490/371472 [6:52:33<11:58:28,  3.50it/s]
 59%|█████▉    | 220491/371472 [6:52:34<11:55:54,  3.51it/s]
 59%|█████▉    | 220492/371472 [6:52:34<12:16:09,  3.42it/s]
 59%|█████▉    | 220493/371472 [6:52:34<11:52:19,  3.53it/s]
 59%|█████▉    | 220494/371472 [6:52:34<12:47:38,  3.28it/s]
 59%|█████▉    | 220495/371472 [6:52:35<12:27:36,  3.37it/s]
 59%|█████▉    | 220496/371472 [6:52:35<12:21:09,  3.40it/s]
 59%|█████▉    | 220497/371472 [6:52:35<11:52:33,  3.53it/s]
 59%|█████▉    | 220498/371472 [6:52:36<11:52:06,  3.53it/s]
 59%|█████▉    | 220499/371472 [6:52:36<13:26:11,  3.12it/s]
 59%|█████▉    | 220500/371472 [6:52:36<12:59:09,  3.23it/s]
                                                            
{'loss': 2.7741, 'learning_rate': 4.6597104009998064e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220500/371472 [6:52:36<12:59:09,  3.23it/s]
 59%|█████▉    | 220501/371472 [6:52:37<12:40:56,  3.31it/s]
 59%|█████▉    | 220502/371472 [6:52:37<12:44:37,  3.29it/s]
 59%|█████▉    | 220503/371472 [6:52:37<12:37:19,  3.32it/s]
 59%|█████▉    | 220504/371472 [6:52:37<13:01:28,  3.22it/s]
 59%|█████▉    | 220505/371472 [6:52:38<12:31:22,  3.35it/s]
 59%|█████▉    | 220506/371472 [6:52:38<12:29:01,  3.36it/s]
 59%|█████▉    | 220507/371472 [6:52:38<12:41:14,  3.31it/s]
 59%|█████▉    | 220508/371472 [6:52:39<13:54:43,  3.01it/s]
 59%|█████▉    | 220509/371472 [6:52:39<13:35:20,  3.09it/s]
 59%|█████▉    | 220510/371472 [6:52:39<12:51:41,  3.26it/s]
 59%|█████▉    | 220511/371472 [6:52:40<14:31:34,  2.89it/s]
 59%|█████▉    | 220512/371472 [6:52:40<14:41:35,  2.85it/s]
 59%|█████▉    | 220513/371472 [6:52:40<13:42:52,  3.06it/s]
 59%|█████▉    | 220514/371472 [6:52:41<13:32:09,  3.10it/s]
 59%|█████▉    | 220515/371472 [6:52:41<12:54:45,  3.25it/s]
 59%|█████▉    | 220516/371472 [6:52:41<12:27:03,  3.37it/s]
 59%|█████▉    | 220517/371472 [6:52:42<12:24:03,  3.38it/s]
 59%|█████▉    | 220518/371472 [6:52:42<12:59:59,  3.23it/s]
 59%|█████▉    | 220519/371472 [6:52:42<13:10:56,  3.18it/s]
 59%|█████▉    | 220520/371472 [6:52:42<12:44:23,  3.29it/s]
                                                            
{'loss': 2.89, 'learning_rate': 4.6592255812450177e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220520/371472 [6:52:42<12:44:23,  3.29it/s]
 59%|█████▉    | 220521/371472 [6:52:43<12:37:03,  3.32it/s]
 59%|█████▉    | 220522/371472 [6:52:43<12:29:02,  3.36it/s]
 59%|█████▉    | 220523/371472 [6:52:43<12:22:19,  3.39it/s]
 59%|█████▉    | 220524/371472 [6:52:44<12:59:31,  3.23it/s]
 59%|█████▉    | 220525/371472 [6:52:44<13:02:09,  3.22it/s]
 59%|█████▉    | 220526/371472 [6:52:44<13:10:36,  3.18it/s]
 59%|█████▉    | 220527/371472 [6:52:45<12:44:26,  3.29it/s]
 59%|█████▉    | 220528/371472 [6:52:45<12:50:04,  3.27it/s]
 59%|█████▉    | 220529/371472 [6:52:45<13:15:39,  3.16it/s]
 59%|█████▉    | 220530/371472 [6:52:46<12:59:20,  3.23it/s]
 59%|█████▉    | 220531/371472 [6:52:46<13:04:32,  3.21it/s]
 59%|█████▉    | 220532/371472 [6:52:46<13:12:27,  3.17it/s]
 59%|█████▉    | 220533/371472 [6:52:46<12:42:41,  3.30it/s]
 59%|█████▉    | 220534/371472 [6:52:47<12:22:12,  3.39it/s]
 59%|█████▉    | 220535/371472 [6:52:47<12:07:23,  3.46it/s]
 59%|█████▉    | 220536/371472 [6:52:47<12:09:10,  3.45it/s]
 59%|█████▉    | 220537/371472 [6:52:48<12:28:11,  3.36it/s]
 59%|█████▉    | 220538/371472 [6:52:48<12:02:36,  3.48it/s]
 59%|█████▉    | 220539/371472 [6:52:48<11:50:48,  3.54it/s]
 59%|█████▉    | 220540/371472 [6:52:48<12:07:46,  3.46it/s]
                                                            
{'loss': 2.686, 'learning_rate': 4.658740761490228e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220540/371472 [6:52:48<12:07:46,  3.46it/s]
 59%|█████▉    | 220541/371472 [6:52:49<12:26:25,  3.37it/s]
 59%|█████▉    | 220542/371472 [6:52:49<12:13:30,  3.43it/s]
 59%|█████▉    | 220543/371472 [6:52:49<12:25:06,  3.38it/s]
 59%|█████▉    | 220544/371472 [6:52:50<12:53:48,  3.25it/s]
 59%|█████▉    | 220545/371472 [6:52:50<12:32:45,  3.34it/s]
 59%|█████▉    | 220546/371472 [6:52:50<12:42:21,  3.30it/s]
 59%|█████▉    | 220547/371472 [6:52:51<12:33:39,  3.34it/s]
 59%|█████▉    | 220548/371472 [6:52:51<12:18:03,  3.41it/s]
 59%|█████▉    | 220549/371472 [6:52:51<12:52:54,  3.25it/s]
 59%|█████▉    | 220550/371472 [6:52:52<12:49:02,  3.27it/s]
 59%|█████▉    | 220551/371472 [6:52:52<12:18:23,  3.41it/s]
 59%|█████▉    | 220552/371472 [6:52:52<12:13:10,  3.43it/s]
 59%|█████▉    | 220553/371472 [6:52:52<12:00:17,  3.49it/s]
 59%|█████▉    | 220554/371472 [6:52:53<11:48:59,  3.55it/s]
 59%|█████▉    | 220555/371472 [6:52:53<12:02:24,  3.48it/s]
 59%|█████▉    | 220556/371472 [6:52:53<11:57:10,  3.51it/s]
 59%|█████▉    | 220557/371472 [6:52:53<11:55:59,  3.51it/s]
 59%|█████▉    | 220558/371472 [6:52:54<12:17:46,  3.41it/s]
 59%|█████▉    | 220559/371472 [6:52:54<12:49:42,  3.27it/s]
 59%|█████▉    | 220560/371472 [6:52:54<13:39:40,  3.07it/s]
                                                            
{'loss': 2.7728, 'learning_rate': 4.6582559417354386e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220560/371472 [6:52:54<13:39:40,  3.07it/s]
 59%|█████▉    | 220561/371472 [6:52:55<13:40:08,  3.07it/s]
 59%|█████▉    | 220562/371472 [6:52:55<14:47:46,  2.83it/s]
 59%|█████▉    | 220563/371472 [6:52:56<14:46:55,  2.84it/s]
 59%|█████▉    | 220564/371472 [6:52:56<14:16:43,  2.94it/s]
 59%|█████▉    | 220565/371472 [6:52:56<14:15:11,  2.94it/s]
 59%|█████▉    | 220566/371472 [6:52:57<13:42:17,  3.06it/s]
 59%|█████▉    | 220567/371472 [6:52:57<12:56:45,  3.24it/s]
 59%|█████▉    | 220568/371472 [6:52:57<12:43:25,  3.29it/s]
 59%|█████▉    | 220569/371472 [6:52:57<12:46:05,  3.28it/s]
 59%|█████▉    | 220570/371472 [6:52:58<14:47:38,  2.83it/s]
 59%|█████▉    | 220571/371472 [6:52:58<14:14:10,  2.94it/s]
 59%|█████▉    | 220572/371472 [6:52:58<13:17:48,  3.15it/s]
 59%|█████▉    | 220573/371472 [6:52:59<13:50:41,  3.03it/s]
 59%|█████▉    | 220574/371472 [6:52:59<14:04:25,  2.98it/s]
 59%|█████▉    | 220575/371472 [6:52:59<14:03:51,  2.98it/s]
 59%|█████▉    | 220576/371472 [6:53:00<13:15:09,  3.16it/s]
 59%|█████▉    | 220577/371472 [6:53:00<12:54:44,  3.25it/s]
 59%|█████▉    | 220578/371472 [6:53:00<12:54:07,  3.25it/s]
 59%|█████▉    | 220579/371472 [6:53:01<12:53:09,  3.25it/s]
 59%|█████▉    | 220580/371472 [6:53:01<12:58:11,  3.23it/s]
                                                            
{'loss': 2.7762, 'learning_rate': 4.6577711219806503e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220580/371472 [6:53:01<12:58:11,  3.23it/s]
 59%|█████▉    | 220581/371472 [6:53:01<12:35:07,  3.33it/s]
 59%|█████▉    | 220582/371472 [6:53:02<12:05:41,  3.47it/s]
 59%|█████▉    | 220583/371472 [6:53:02<11:54:11,  3.52it/s]
 59%|█████▉    | 220584/371472 [6:53:02<12:06:53,  3.46it/s]
 59%|█████▉    | 220585/371472 [6:53:02<12:11:52,  3.44it/s]
 59%|█████▉    | 220586/371472 [6:53:03<12:09:36,  3.45it/s]
 59%|█████▉    | 220587/371472 [6:53:03<12:00:14,  3.49it/s]
 59%|█████▉    | 220588/371472 [6:53:03<11:45:43,  3.56it/s]
 59%|█████▉    | 220589/371472 [6:53:04<12:08:57,  3.45it/s]
 59%|█████▉    | 220590/371472 [6:53:04<12:01:25,  3.49it/s]
 59%|█████��    | 220591/371472 [6:53:04<11:43:26,  3.57it/s]
 59%|█████▉    | 220592/371472 [6:53:04<11:56:00,  3.51it/s]
 59%|█████▉    | 220593/371472 [6:53:05<11:44:43,  3.57it/s]
 59%|█████▉    | 220594/371472 [6:53:05<11:48:43,  3.55it/s]
 59%|█████▉    | 220595/371472 [6:53:05<12:02:45,  3.48it/s]
 59%|█████▉    | 220596/371472 [6:53:05<11:48:20,  3.55it/s]
 59%|█████▉    | 220597/371472 [6:53:06<12:34:49,  3.33it/s]
 59%|█████▉    | 220598/371472 [6:53:06<12:21:00,  3.39it/s]
 59%|█████▉    | 220599/371472 [6:53:06<12:19:44,  3.40it/s]
 59%|█████▉    | 220600/371472 [6:53:07<12:34:06,  3.33it/s]
                                                            
{'loss': 2.7031, 'learning_rate': 4.6572863022258605e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220600/371472 [6:53:07<12:34:06,  3.33it/s]
 59%|█████▉    | 220601/371472 [6:53:07<13:22:36,  3.13it/s]
 59%|█████▉    | 220602/371472 [6:53:07<13:37:02,  3.08it/s]
 59%|█████▉    | 220603/371472 [6:53:08<13:39:27,  3.07it/s]
 59%|█████▉    | 220604/371472 [6:53:08<12:50:30,  3.26it/s]
 59%|█████▉    | 220605/371472 [6:53:08<12:29:05,  3.36it/s]
 59%|█████▉    | 220606/371472 [6:53:09<12:15:16,  3.42it/s]
 59%|█████▉    | 220607/371472 [6:53:09<11:55:39,  3.51it/s]
 59%|█████▉    | 220608/371472 [6:53:09<12:05:37,  3.47it/s]
 59%|█████▉    | 220609/371472 [6:53:09<11:46:22,  3.56it/s]
 59%|█████▉    | 220610/371472 [6:53:10<12:06:34,  3.46it/s]
 59%|█████▉    | 220611/371472 [6:53:10<12:47:00,  3.28it/s]
 59%|█████▉    | 220612/371472 [6:53:10<13:06:27,  3.20it/s]
 59%|█████▉    | 220613/371472 [6:53:11<13:42:55,  3.06it/s]
 59%|█████▉    | 220614/371472 [6:53:11<14:27:31,  2.90it/s]
 59%|█████▉    | 220615/371472 [6:53:11<13:37:01,  3.08it/s]
 59%|█████▉    | 220616/371472 [6:53:12<12:59:51,  3.22it/s]
 59%|█████▉    | 220617/371472 [6:53:12<12:31:46,  3.34it/s]
 59%|█████▉    | 220618/371472 [6:53:12<12:27:44,  3.36it/s]
 59%|█████▉    | 220619/371472 [6:53:13<12:58:23,  3.23it/s]
 59%|█████▉    | 220620/371472 [6:53:13<12:42:34,  3.30it/s]
                                                            
{'loss': 2.867, 'learning_rate': 4.6568014824710723e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220620/371472 [6:53:13<12:42:34,  3.30it/s]
 59%|█████▉    | 220621/371472 [6:53:13<13:00:25,  3.22it/s]
 59%|█████▉    | 220622/371472 [6:53:14<13:27:15,  3.11it/s]
 59%|█████▉    | 220623/371472 [6:53:14<13:53:21,  3.02it/s]
 59%|█████▉    | 220624/371472 [6:53:14<13:28:54,  3.11it/s]
 59%|█████▉    | 220625/371472 [6:53:14<12:52:41,  3.25it/s]
 59%|█████▉    | 220626/371472 [6:53:15<13:38:48,  3.07it/s]
 59%|█████▉    | 220627/371472 [6:53:15<12:45:00,  3.29it/s]
 59%|█████▉    | 220628/371472 [6:53:15<12:48:15,  3.27it/s]
 59%|█████▉    | 220629/371472 [6:53:16<12:44:56,  3.29it/s]
 59%|█████▉    | 220630/371472 [6:53:16<12:15:14,  3.42it/s]
 59%|█████▉    | 220631/371472 [6:53:16<12:02:05,  3.48it/s]
 59%|█████▉    | 220632/371472 [6:53:17<12:25:45,  3.37it/s]
 59%|█████▉    | 220633/371472 [6:53:17<12:54:37,  3.25it/s]
 59%|█████▉    | 220634/371472 [6:53:17<13:09:50,  3.18it/s]
 59%|█████▉    | 220635/371472 [6:53:18<12:46:40,  3.28it/s]
 59%|█████▉    | 220636/371472 [6:53:18<12:28:20,  3.36it/s]
 59%|█████▉    | 220637/371472 [6:53:18<12:09:36,  3.45it/s]
 59%|█████▉    | 220638/371472 [6:53:18<12:11:45,  3.44it/s]
 59%|█████▉    | 220639/371472 [6:53:19<12:05:44,  3.46it/s]
 59%|█████▉    | 220640/371472 [6:53:19<12:13:05,  3.43it/s]
                                                            
{'loss': 2.7529, 'learning_rate': 4.656316662716283e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220640/371472 [6:53:19<12:13:05,  3.43it/s]
 59%|█████▉    | 220641/371472 [6:53:19<12:18:39,  3.40it/s]
 59%|█████▉    | 220642/371472 [6:53:20<12:03:07,  3.48it/s]
 59%|█████▉    | 220643/371472 [6:53:20<11:57:47,  3.50it/s]
 59%|█████▉    | 220644/371472 [6:53:20<13:16:00,  3.16it/s]
 59%|█████▉    | 220645/371472 [6:53:20<12:47:08,  3.28it/s]
 59%|█████▉    | 220646/371472 [6:53:21<12:48:06,  3.27it/s]
 59%|█████▉    | 220647/371472 [6:53:21<12:22:42,  3.38it/s]
 59%|█████▉    | 220648/371472 [6:53:21<12:45:20,  3.28it/s]
 59%|█████▉    | 220649/371472 [6:53:22<12:26:31,  3.37it/s]
 59%|█████▉    | 220650/371472 [6:53:22<12:10:10,  3.44it/s]
 59%|█████▉    | 220651/371472 [6:53:22<12:12:17,  3.43it/s]
 59%|█████▉    | 220652/371472 [6:53:22<12:01:17,  3.48it/s]
 59%|█████▉    | 220653/371472 [6:53:23<11:59:31,  3.49it/s]
 59%|█████▉    | 220654/371472 [6:53:23<11:55:39,  3.51it/s]
 59%|█████▉    | 220655/371472 [6:53:23<12:38:27,  3.31it/s]
 59%|█████▉    | 220656/371472 [6:53:24<12:11:01,  3.44it/s]
 59%|█████▉    | 220657/371472 [6:53:24<11:57:30,  3.50it/s]
 59%|█████▉    | 220658/371472 [6:53:24<12:17:51,  3.41it/s]
 59%|█████▉    | 220659/371472 [6:53:25<12:52:35,  3.25it/s]
 59%|█████▉    | 220660/371472 [6:53:25<12:32:48,  3.34it/s]
                                                            
{'loss': 2.7569, 'learning_rate': 4.655831842961494e-07, 'epoch': 9.5}
+
 59%|█████▉    | 220660/371472 [6:53:25<12:32:48,  3.34it/s]
 59%|█████▉    | 220661/371472 [6:53:25<13:28:14,  3.11it/s]
 59%|█████▉    | 220662/371472 [6:53:26<12:50:22,  3.26it/s]
 59%|█████▉    | 220663/371472 [6:53:26<12:34:08,  3.33it/s]
 59%|█████▉    | 220664/371472 [6:53:26<13:18:50,  3.15it/s]
 59%|█████▉    | 220665/371472 [6:53:26<13:18:06,  3.15it/s]
 59%|█████▉    | 220666/371472 [6:53:27<12:50:19,  3.26it/s]
 59%|█████▉    | 220667/371472 [6:53:27<12:25:37,  3.37it/s]
 59%|█████▉    | 220668/371472 [6:53:27<12:29:18,  3.35it/s]
 59%|█████▉    | 220669/371472 [6:53:28<12:48:55,  3.27it/s]
 59%|█████▉    | 220670/371472 [6:53:28<12:37:57,  3.32it/s]
 59%|█████▉    | 220671/371472 [6:53:28<12:20:27,  3.39it/s]
 59%|█████▉    | 220672/371472 [6:53:29<12:10:54,  3.44it/s]
 59%|█████▉    | 220673/371472 [6:53:29<12:41:23,  3.30it/s]
 59%|█████▉    | 220674/371472 [6:53:29<12:20:25,  3.39it/s]
 59%|█████▉    | 220675/371472 [6:53:29<12:07:55,  3.45it/s]
 59%|█████▉    | 220676/371472 [6:53:30<12:02:03,  3.48it/s]
 59%|█████▉    | 220677/371472 [6:53:30<11:33:05,  3.63it/s]
 59%|█████▉    | 220678/371472 [6:53:30<11:24:21,  3.67it/s]
 59%|█████▉    | 220679/371472 [6:53:30<11:18:51,  3.70it/s]
 59%|█████▉    | 220680/371472 [6:53:31<11:38:22,  3.60it/s]
                                                            
{'loss': 2.7325, 'learning_rate': 4.655347023206705e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220680/371472 [6:53:31<11:38:22,  3.60it/s]
 59%|█████▉    | 220681/371472 [6:53:31<11:56:42,  3.51it/s]
 59%|█████▉    | 220682/371472 [6:53:31<12:04:31,  3.47it/s]
 59%|█████▉    | 220683/371472 [6:53:32<11:48:19,  3.55it/s]
 59%|█████▉    | 220684/371472 [6:53:32<11:36:58,  3.61it/s]
 59%|█████▉    | 220685/371472 [6:53:32<11:29:06,  3.65it/s]
 59%|█████▉    | 220686/371472 [6:53:32<11:24:07,  3.67it/s]
 59%|█████▉    | 220687/371472 [6:53:33<11:45:19,  3.56it/s]
 59%|█████▉    | 220688/371472 [6:53:33<11:42:20,  3.58it/s]
 59%|█████▉    | 220689/371472 [6:53:33<11:38:11,  3.60it/s]
 59%|█████▉    | 220690/371472 [6:53:34<11:55:39,  3.51it/s]
 59%|█████▉    | 220691/371472 [6:53:34<11:41:03,  3.58it/s]
 59%|█████▉    | 220692/371472 [6:53:34<11:48:16,  3.55it/s]
 59%|█████▉    | 220693/371472 [6:53:34<12:02:13,  3.48it/s]
 59%|█████▉    | 220694/371472 [6:53:35<11:44:11,  3.57it/s]
 59%|█████▉    | 220695/371472 [6:53:35<11:33:39,  3.62it/s]
 59%|█████▉    | 220696/371472 [6:53:35<11:59:16,  3.49it/s]
 59%|█████▉    | 220697/371472 [6:53:36<11:51:42,  3.53it/s]
 59%|█████▉    | 220698/371472 [6:53:36<12:00:18,  3.49it/s]
 59%|█████▉    | 220699/371472 [6:53:36<11:38:50,  3.60it/s]
 59%|█████▉    | 220700/371472 [6:53:36<11:52:02,  3.53it/s]
                                                            
{'loss': 2.7647, 'learning_rate': 4.654862203451917e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220700/371472 [6:53:36<11:52:02,  3.53it/s]
 59%|█████▉    | 220701/371472 [6:53:37<12:16:21,  3.41it/s]
 59%|█████▉    | 220702/371472 [6:53:37<12:09:15,  3.45it/s]
 59%|█████▉    | 220703/371472 [6:53:37<12:16:50,  3.41it/s]
 59%|█████▉    | 220704/371472 [6:53:38<12:06:14,  3.46it/s]
 59%|█████▉    | 220705/371472 [6:53:38<11:51:40,  3.53it/s]
 59%|█████▉    | 220706/371472 [6:53:38<12:33:17,  3.34it/s]
 59%|█████▉    | 220707/371472 [6:53:38<12:18:52,  3.40it/s]
 59%|█████▉    | 220708/371472 [6:53:39<12:07:31,  3.45it/s]
 59%|█████▉    | 220709/371472 [6:53:39<12:06:05,  3.46it/s]
 59%|█████▉    | 220710/371472 [6:53:39<12:00:32,  3.49it/s]
 59%|█████▉    | 220711/371472 [6:53:40<11:59:02,  3.49it/s]
 59%|█████▉    | 220712/371472 [6:53:40<12:04:24,  3.47it/s]
 59%|█████▉    | 220713/371472 [6:53:40<11:55:34,  3.51it/s]
 59%|█████▉    | 220714/371472 [6:53:40<11:44:34,  3.57it/s]
 59%|█████▉    | 220715/371472 [6:53:41<12:00:34,  3.49it/s]
 59%|█████▉    | 220716/371472 [6:53:41<12:01:48,  3.48it/s]
 59%|█████▉    | 220717/371472 [6:53:41<11:57:18,  3.50it/s]
 59%|█████▉    | 220718/371472 [6:53:42<12:18:27,  3.40it/s]
 59%|█████▉    | 220719/371472 [6:53:42<13:20:55,  3.14it/s]
 59%|█████▉    | 220720/371472 [6:53:42<14:07:54,  2.96it/s]
                                                            
{'loss': 2.8313, 'learning_rate': 4.654377383697127e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220720/371472 [6:53:42<14:07:54,  2.96it/s]
 59%|█████▉    | 220721/371472 [6:53:43<13:29:54,  3.10it/s]
 59%|█████▉    | 220722/371472 [6:53:43<13:47:24,  3.04it/s]
 59%|█████▉    | 220723/371472 [6:53:43<13:37:50,  3.07it/s]
 59%|█████▉    | 220724/371472 [6:53:44<13:38:24,  3.07it/s]
 59%|█████▉    | 220725/371472 [6:53:44<12:57:12,  3.23it/s]
 59%|█████▉    | 220726/371472 [6:53:44<12:36:21,  3.32it/s]
 59%|█████▉    | 220727/371472 [6:53:44<12:24:42,  3.37it/s]
 59%|█████▉    | 220728/371472 [6:53:45<12:51:11,  3.26it/s]
 59%|█████▉    | 220729/371472 [6:53:45<13:10:07,  3.18it/s]
 59%|█████▉    | 220730/371472 [6:53:45<13:23:32,  3.13it/s]
 59%|█████▉    | 220731/371472 [6:53:46<14:45:26,  2.84it/s]
 59%|█████▉    | 220732/371472 [6:53:46<14:13:31,  2.94it/s]
 59%|█████▉    | 220733/371472 [6:53:47<13:36:08,  3.08it/s]
 59%|█████▉    | 220734/371472 [6:53:47<12:46:18,  3.28it/s]
 59%|█████▉    | 220735/371472 [6:53:47<12:54:42,  3.24it/s]
 59%|█████▉    | 220736/371472 [6:53:47<12:27:26,  3.36it/s]
 59%|█████▉    | 220737/371472 [6:53:48<12:27:04,  3.36it/s]
 59%|█████▉    | 220738/371472 [6:53:48<12:09:45,  3.44it/s]
 59%|█████▉    | 220739/371472 [6:53:48<11:45:09,  3.56it/s]
 59%|█████▉    | 220740/371472 [6:53:48<11:45:44,  3.56it/s]
                                                            
{'loss': 2.6693, 'learning_rate': 4.6538925639423387e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220740/371472 [6:53:48<11:45:44,  3.56it/s]
 59%|█████▉    | 220741/371472 [6:53:49<11:37:12,  3.60it/s]
 59%|█████▉    | 220742/371472 [6:53:49<12:00:19,  3.49it/s]
 59%|█████▉    | 220743/371472 [6:53:49<11:43:47,  3.57it/s]
 59%|█████▉    | 220744/371472 [6:53:50<11:51:11,  3.53it/s]
 59%|█████▉    | 220745/371472 [6:53:50<11:39:12,  3.59it/s]
 59%|█████▉    | 220746/371472 [6:53:50<11:26:51,  3.66it/s]
 59%|█████▉    | 220747/371472 [6:53:51<12:56:24,  3.24it/s]
 59%|█████▉    | 220748/371472 [6:53:51<12:31:30,  3.34it/s]
 59%|█████▉    | 220749/371472 [6:53:51<12:07:03,  3.46it/s]
 59%|█████▉    | 220750/371472 [6:53:51<11:59:09,  3.49it/s]
 59%|█████▉    | 220751/371472 [6:53:52<11:47:08,  3.55it/s]
 59%|█████▉    | 220752/371472 [6:53:52<11:31:19,  3.63it/s]
 59%|█████▉    | 220753/371472 [6:53:52<11:39:29,  3.59it/s]
 59%|█████▉    | 220754/371472 [6:53:52<11:43:44,  3.57it/s]
 59%|█████▉    | 220755/371472 [6:53:53<11:36:07,  3.61it/s]
 59%|█████▉    | 220756/371472 [6:53:53<11:41:20,  3.58it/s]
 59%|█████▉    | 220757/371472 [6:53:53<11:44:34,  3.57it/s]
 59%|█████▉    | 220758/371472 [6:53:54<11:29:15,  3.64it/s]
 59%|█████▉    | 220759/371472 [6:53:54<11:58:40,  3.50it/s]
 59%|█████▉    | 220760/371472 [6:53:54<12:41:39,  3.30it/s]
                                                            
{'loss': 2.7826, 'learning_rate': 4.6534077441875494e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220760/371472 [6:53:54<12:41:39,  3.30it/s]
 59%|█████▉    | 220761/371472 [6:53:54<12:27:27,  3.36it/s]
 59%|█████▉    | 220762/371472 [6:53:55<12:51:07,  3.26it/s]
 59%|█████▉    | 220763/371472 [6:53:55<12:35:55,  3.32it/s]
 59%|█████▉    | 220764/371472 [6:53:55<12:26:41,  3.36it/s]
 59%|█████▉    | 220765/371472 [6:53:56<12:18:38,  3.40it/s]
 59%|█████▉    | 220766/371472 [6:53:56<12:05:30,  3.46it/s]
 59%|█████▉    | 220767/371472 [6:53:56<11:59:29,  3.49it/s]
 59%|█████▉    | 220768/371472 [6:53:56<11:42:59,  3.57it/s]
 59%|█████▉    | 220769/371472 [6:53:57<11:37:32,  3.60it/s]
 59%|█████▉    | 220770/371472 [6:53:57<12:51:35,  3.26it/s]
 59%|█████▉    | 220771/371472 [6:53:57<12:22:54,  3.38it/s]
 59%|█████▉    | 220772/371472 [6:53:58<12:25:28,  3.37it/s]
 59%|█████▉    | 220773/371472 [6:53:58<12:22:21,  3.38it/s]
 59%|█████▉    | 220774/371472 [6:53:58<12:00:45,  3.48it/s]
 59%|█████▉    | 220775/371472 [6:53:59<12:02:09,  3.48it/s]
 59%|���████▉    | 220776/371472 [6:53:59<11:43:23,  3.57it/s]
 59%|█████▉    | 220777/371472 [6:53:59<11:19:01,  3.70it/s]
 59%|█████▉    | 220778/371472 [6:53:59<11:05:08,  3.78it/s]
 59%|█████▉    | 220779/371472 [6:54:00<11:19:49,  3.69it/s]
 59%|█████▉    | 220780/371472 [6:54:00<11:58:41,  3.49it/s]
                                                            
{'loss': 2.8352, 'learning_rate': 4.6529229244327607e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220780/371472 [6:54:00<11:58:41,  3.49it/s]
 59%|█████▉    | 220781/371472 [6:54:00<11:55:06,  3.51it/s]
 59%|█████▉    | 220782/371472 [6:54:01<12:07:00,  3.45it/s]
 59%|█████▉    | 220783/371472 [6:54:01<12:09:12,  3.44it/s]
 59%|█████▉    | 220784/371472 [6:54:01<12:40:28,  3.30it/s]
 59%|█████▉    | 220785/371472 [6:54:01<12:51:08,  3.26it/s]
 59%|█████▉    | 220786/371472 [6:54:02<12:38:47,  3.31it/s]
 59%|█████▉    | 220787/371472 [6:54:02<13:44:25,  3.05it/s]
 59%|█████▉    | 220788/371472 [6:54:02<13:10:52,  3.18it/s]
 59%|█████▉    | 220789/371472 [6:54:03<12:28:28,  3.36it/s]
 59%|█████▉    | 220790/371472 [6:54:03<12:00:26,  3.49it/s]
 59%|█████▉    | 220791/371472 [6:54:03<12:07:47,  3.45it/s]
 59%|█████▉    | 220792/371472 [6:54:04<12:19:08,  3.40it/s]
 59%|█████▉    | 220793/371472 [6:54:04<12:26:59,  3.36it/s]
 59%|█████▉    | 220794/371472 [6:54:04<12:30:19,  3.35it/s]
 59%|█████▉    | 220795/371472 [6:54:04<12:28:30,  3.36it/s]
 59%|█████▉    | 220796/371472 [6:54:05<12:15:27,  3.41it/s]
 59%|█████▉    | 220797/371472 [6:54:05<12:47:08,  3.27it/s]
 59%|█████▉    | 220798/371472 [6:54:05<12:18:30,  3.40it/s]
 59%|█████▉    | 220799/371472 [6:54:06<11:58:49,  3.49it/s]
 59%|█████▉    | 220800/371472 [6:54:06<11:57:15,  3.50it/s]
                                                            
{'loss': 2.8352, 'learning_rate': 4.6524381046779714e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220800/371472 [6:54:06<11:57:15,  3.50it/s]
 59%|█████▉    | 220801/371472 [6:54:06<12:28:53,  3.35it/s]
 59%|█████▉    | 220802/371472 [6:54:06<12:11:27,  3.43it/s]
 59%|█████▉    | 220803/371472 [6:54:07<12:00:09,  3.49it/s]
 59%|█████▉    | 220804/371472 [6:54:07<12:54:45,  3.24it/s]
 59%|█████▉    | 220805/371472 [6:54:07<12:35:49,  3.32it/s]
 59%|█████▉    | 220806/371472 [6:54:08<12:11:48,  3.43it/s]
 59%|█████▉    | 220807/371472 [6:54:08<11:54:23,  3.52it/s]
 59%|█████▉    | 220808/371472 [6:54:08<12:53:15,  3.25it/s]
 59%|█████▉    | 220809/371472 [6:54:09<12:46:06,  3.28it/s]
 59%|█████▉    | 220810/371472 [6:54:09<12:08:13,  3.45it/s]
 59%|█████▉    | 220811/371472 [6:54:09<12:12:36,  3.43it/s]
 59%|█████▉    | 220812/371472 [6:54:09<11:48:49,  3.54it/s]
 59%|█████▉    | 220813/371472 [6:54:10<11:37:53,  3.60it/s]
 59%|█████▉    | 220814/371472 [6:54:10<11:37:41,  3.60it/s]
 59%|█████▉    | 220815/371472 [6:54:10<11:41:10,  3.58it/s]
 59%|█████▉    | 220816/371472 [6:54:11<11:41:12,  3.58it/s]
 59%|█████▉    | 220817/371472 [6:54:11<11:30:39,  3.64it/s]
 59%|█████▉    | 220818/371472 [6:54:11<11:13:00,  3.73it/s]
 59%|█████▉    | 220819/371472 [6:54:11<11:10:05,  3.75it/s]
 59%|█████▉    | 220820/371472 [6:54:12<11:23:40,  3.67it/s]
                                                            
{'loss': 2.7102, 'learning_rate': 4.651953284923183e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220820/371472 [6:54:12<11:23:40,  3.67it/s]
 59%|█████▉    | 220821/371472 [6:54:12<11:51:16,  3.53it/s]
 59%|█████▉    | 220822/371472 [6:54:12<11:51:32,  3.53it/s]
 59%|█████▉    | 220823/371472 [6:54:12<11:52:11,  3.53it/s]
 59%|█████▉    | 220824/371472 [6:54:13<12:01:49,  3.48it/s]
 59%|█████▉    | 220825/371472 [6:54:13<12:02:29,  3.48it/s]
 59%|█████▉    | 220826/371472 [6:54:13<11:39:56,  3.59it/s]
 59%|█████▉    | 220827/371472 [6:54:14<11:39:44,  3.59it/s]
 59%|█████▉    | 220828/371472 [6:54:14<13:06:50,  3.19it/s]
 59%|█████▉    | 220829/371472 [6:54:14<12:45:39,  3.28it/s]
 59%|█████▉    | 220830/371472 [6:54:15<12:34:53,  3.33it/s]
 59%|█████▉    | 220831/371472 [6:54:15<12:48:06,  3.27it/s]
 59%|█████▉    | 220832/371472 [6:54:15<12:27:38,  3.36it/s]
 59%|█████▉    | 220833/371472 [6:54:15<12:06:01,  3.46it/s]
 59%|█████▉    | 220834/371472 [6:54:16<11:58:34,  3.49it/s]
 59%|█████▉    | 220835/371472 [6:54:16<12:32:58,  3.33it/s]
 59%|█████▉    | 220836/371472 [6:54:16<12:03:28,  3.47it/s]
 59%|█████▉    | 220837/371472 [6:54:17<12:58:39,  3.22it/s]
 59%|█████▉    | 220838/371472 [6:54:17<12:29:19,  3.35it/s]
 59%|█████▉    | 220839/371472 [6:54:17<12:26:34,  3.36it/s]
 59%|█████▉    | 220840/371472 [6:54:18<12:39:30,  3.31it/s]
                                                            
{'loss': 2.6711, 'learning_rate': 4.651468465168394e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220840/371472 [6:54:18<12:39:30,  3.31it/s]
 59%|█████▉    | 220841/371472 [6:54:18<12:23:47,  3.38it/s]
 59%|█████▉    | 220842/371472 [6:54:18<12:05:53,  3.46it/s]
 59%|█████▉    | 220843/371472 [6:54:18<12:05:22,  3.46it/s]
 59%|█████▉    | 220844/371472 [6:54:19<12:49:31,  3.26it/s]
 59%|█████▉    | 220845/371472 [6:54:19<12:50:14,  3.26it/s]
 59%|█████▉    | 220846/371472 [6:54:19<12:52:05,  3.25it/s]
 59%|█████▉    | 220847/371472 [6:54:20<12:26:47,  3.36it/s]
 59%|█████▉    | 220848/371472 [6:54:20<12:34:54,  3.33it/s]
 59%|█████▉    | 220849/371472 [6:54:20<12:15:32,  3.41it/s]
 59%|█████▉    | 220850/371472 [6:54:20<11:59:18,  3.49it/s]
 59%|█████▉    | 220851/371472 [6:54:21<12:28:36,  3.35it/s]
 59%|█████▉    | 220852/371472 [6:54:21<12:09:16,  3.44it/s]
 59%|█████▉    | 220853/371472 [6:54:21<12:04:32,  3.46it/s]
 59%|█████▉    | 220854/371472 [6:54:22<11:54:03,  3.52it/s]
 59%|█████▉    | 220855/371472 [6:54:22<11:59:03,  3.49it/s]
 59%|█████▉    | 220856/371472 [6:54:22<11:59:41,  3.49it/s]
 59%|█████▉    | 220857/371472 [6:54:22<11:32:27,  3.63it/s]
 59%|█████▉    | 220858/371472 [6:54:23<11:47:05,  3.55it/s]
 59%|█████▉    | 220859/371472 [6:54:23<11:26:40,  3.66it/s]
 59%|█████▉    | 220860/371472 [6:54:23<11:37:40,  3.60it/s]
                                                            
{'loss': 2.7535, 'learning_rate': 4.650983645413605e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220860/371472 [6:54:23<11:37:40,  3.60it/s]
 59%|█████▉    | 220861/371472 [6:54:24<11:42:04,  3.58it/s]
 59%|█████▉    | 220862/371472 [6:54:24<11:25:18,  3.66it/s]
 59%|█████▉    | 220863/371472 [6:54:24<11:54:54,  3.51it/s]
 59%|█████▉    | 220864/371472 [6:54:24<11:50:29,  3.53it/s]
 59%|█████▉    | 220865/371472 [6:54:25<11:44:18,  3.56it/s]
 59%|█████▉    | 220866/371472 [6:54:25<12:17:04,  3.41it/s]
 59%|█████▉    | 220867/371472 [6:54:25<12:29:37,  3.35it/s]
 59%|█████▉    | 220868/371472 [6:54:26<12:10:39,  3.44it/s]
 59%|█████▉    | 220869/371472 [6:54:26<11:56:55,  3.50it/s]
 59%|█████▉    | 220870/371472 [6:54:26<11:44:36,  3.56it/s]
 59%|█████▉    | 220871/371472 [6:54:26<12:29:51,  3.35it/s]
 59%|█████▉    | 220872/371472 [6:54:27<12:56:40,  3.23it/s]
 59%|█████▉    | 220873/371472 [6:54:27<12:13:42,  3.42it/s]
 59%|█████▉    | 220874/371472 [6:54:27<12:02:52,  3.47it/s]
 59%|█████▉    | 220875/371472 [6:54:28<11:55:39,  3.51it/s]
 59%|█████▉    | 220876/371472 [6:54:28<12:11:29,  3.43it/s]
 59%|█████▉    | 220877/371472 [6:54:28<13:16:21,  3.15it/s]
 59%|█████▉    | 220878/371472 [6:54:29<12:54:21,  3.24it/s]
 59%|█████▉    | 220879/371472 [6:54:29<12:24:31,  3.37it/s]
 59%|█████▉    | 220880/371472 [6:54:29<11:55:26,  3.51it/s]
                                                            
{'loss': 2.801, 'learning_rate': 4.650498825658816e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220880/371472 [6:54:29<11:55:26,  3.51it/s]
 59%|█████▉    | 220881/371472 [6:54:29<12:02:30,  3.47it/s]
 59%|█████▉    | 220882/371472 [6:54:30<11:51:31,  3.53it/s]
 59%|█████▉    | 220883/371472 [6:54:30<11:38:33,  3.59it/s]
 59%|█████▉    | 220884/371472 [6:54:30<11:26:43,  3.65it/s]
 59%|█████▉    | 220885/371472 [6:54:31<11:51:45,  3.53it/s]
 59%|█████▉    | 220886/371472 [6:54:31<11:53:10,  3.52it/s]
 59%|█████▉    | 220887/371472 [6:54:31<12:05:11,  3.46it/s]
 59%|█████▉    | 220888/371472 [6:54:31<12:26:44,  3.36it/s]
 59%|█████▉    | 220889/371472 [6:54:32<12:15:42,  3.41it/s]
 59%|█████▉    | 220890/371472 [6:54:32<12:31:58,  3.34it/s]
 59%|█████▉    | 220891/371472 [6:54:32<12:27:04,  3.36it/s]
 59%|█████▉    | 220892/371472 [6:54:33<12:02:59,  3.47it/s]
 59%|█████▉    | 220893/371472 [6:54:33<11:50:07,  3.53it/s]
 59%|█████▉    | 220894/371472 [6:54:33<12:06:57,  3.45it/s]
 59%|█████▉    | 220895/371472 [6:54:33<12:03:12,  3.47it/s]
 59%|█████▉    | 220896/371472 [6:54:34<12:41:22,  3.30it/s]
 59%|█████▉    | 220897/371472 [6:54:34<13:09:11,  3.18it/s]
 59%|█████▉    | 220898/371472 [6:54:34<12:34:04,  3.33it/s]
 59%|████���▉    | 220899/371472 [6:54:35<12:03:09,  3.47it/s]
 59%|█████▉    | 220900/371472 [6:54:35<11:58:46,  3.49it/s]
                                                            
{'loss': 2.7716, 'learning_rate': 4.6500140059040276e-07, 'epoch': 9.51}
+
 59%|█████▉    | 220900/371472 [6:54:35<11:58:46,  3.49it/s]
 59%|█████▉    | 220901/371472 [6:54:35<11:58:09,  3.49it/s]
 59%|█████▉    | 220902/371472 [6:54:35<11:26:29,  3.66it/s]
 59%|█████▉    | 220903/371472 [6:54:36<11:22:10,  3.68it/s]
 59%|█████▉    | 220904/371472 [6:54:36<11:46:19,  3.55it/s]
 59%|█████▉    | 220905/371472 [6:54:36<11:29:42,  3.64it/s]
 59%|█████▉    | 220906/371472 [6:54:37<12:44:47,  3.28it/s]
 59%|█████▉    | 220907/371472 [6:54:37<12:58:29,  3.22it/s]
 59%|█████▉    | 220908/371472 [6:54:37<12:33:21,  3.33it/s]
 59%|█████▉    | 220909/371472 [6:54:38<12:13:28,  3.42it/s]
 59%|█████▉    | 220910/371472 [6:54:38<12:04:35,  3.46it/s]
 59%|█████▉    | 220911/371472 [6:54:38<11:51:17,  3.53it/s]
 59%|█████▉    | 220912/371472 [6:54:38<12:18:09,  3.40it/s]
 59%|█████▉    | 220913/371472 [6:54:39<13:08:29,  3.18it/s]
 59%|█████▉    | 220914/371472 [6:54:39<13:30:38,  3.10it/s]
 59%|█████▉    | 220915/371472 [6:54:39<12:59:28,  3.22it/s]
 59%|█████▉    | 220916/371472 [6:54:40<12:20:36,  3.39it/s]
 59%|█████▉    | 220917/371472 [6:54:40<12:18:59,  3.40it/s]
 59%|█████▉    | 220918/371472 [6:54:40<14:55:57,  2.80it/s]
 59%|█████▉    | 220919/371472 [6:54:41<14:02:31,  2.98it/s]
 59%|█████▉    | 220920/371472 [6:54:41<13:50:50,  3.02it/s]
                                                            
{'loss': 2.719, 'learning_rate': 4.6495291861492383e-07, 'epoch': 9.52}
+
 59%|█████▉    | 220920/371472 [6:54:41<13:50:50,  3.02it/s]
 59%|█████▉    | 220921/371472 [6:54:41<13:07:10,  3.19it/s]
 59%|█████▉    | 220922/371472 [6:54:42<12:43:39,  3.29it/s]
 59%|█████▉    | 220923/371472 [6:54:42<12:31:28,  3.34it/s]
 59%|█████▉    | 220924/371472 [6:54:42<12:18:43,  3.40it/s]
 59%|█████▉    | 220925/371472 [6:54:42<12:03:09,  3.47it/s]
 59%|█████▉    | 220926/371472 [6:54:43<11:48:52,  3.54it/s]
 59%|█████▉    | 220927/371472 [6:54:43<12:02:16,  3.47it/s]
 59%|█████▉    | 220928/371472 [6:54:43<11:40:00,  3.58it/s]
 59%|█████▉    | 220929/371472 [6:54:44<11:35:06,  3.61it/s]
 59%|█████▉    | 220930/371472 [6:54:44<12:09:14,  3.44it/s]
 59%|█████▉    | 220931/371472 [6:54:44<13:09:12,  3.18it/s]
 59%|█████▉    | 220932/371472 [6:54:45<12:28:07,  3.35it/s]
 59%|█████▉    | 220933/371472 [6:54:45<12:14:23,  3.42it/s]
 59%|█████▉    | 220934/371472 [6:54:45<12:18:58,  3.40it/s]
 59%|█████▉    | 220935/371472 [6:54:45<12:02:00,  3.47it/s]
 59%|█████▉    | 220936/371472 [6:54:46<12:09:26,  3.44it/s]
 59%|█████▉    | 220937/371472 [6:54:46<12:05:08,  3.46it/s]
 59%|█████▉    | 220938/371472 [6:54:46<11:46:59,  3.55it/s]
 59%|█████▉    | 220939/371472 [6:54:46<11:34:58,  3.61it/s]
 59%|█████▉    | 220940/371472 [6:54:47<11:31:52,  3.63it/s]
                                                            
{'loss': 2.7264, 'learning_rate': 4.6490443663944496e-07, 'epoch': 9.52}
+
 59%|█████▉    | 220940/371472 [6:54:47<11:31:52,  3.63it/s]
 59%|█████▉    | 220941/371472 [6:54:47<11:33:09,  3.62it/s]
 59%|█████▉    | 220942/371472 [6:54:47<11:36:03,  3.60it/s]
 59%|█████▉    | 220943/371472 [6:54:48<12:15:48,  3.41it/s]
 59%|█████▉    | 220944/371472 [6:54:48<11:44:10,  3.56it/s]
 59%|█████▉    | 220945/371472 [6:54:48<11:36:39,  3.60it/s]
 59%|█████▉    | 220946/371472 [6:54:48<11:35:15,  3.61it/s]
 59%|█████▉    | 220947/371472 [6:54:49<12:15:47,  3.41it/s]
 59%|█████▉    | 220948/371472 [6:54:49<12:32:44,  3.33it/s]
 59%|█████▉    | 220949/371472 [6:54:49<12:08:16,  3.44it/s]
 59%|█████▉    | 220950/371472 [6:54:50<12:15:54,  3.41it/s]
 59%|█████▉    | 220951/371472 [6:54:50<12:08:58,  3.44it/s]
 59%|█████▉    | 220952/371472 [6:54:50<12:06:21,  3.45it/s]
 59%|█████▉    | 220953/371472 [6:54:51<11:56:56,  3.50it/s]
 59%|█████▉    | 220954/371472 [6:54:51<11:35:55,  3.60it/s]
 59%|█████▉    | 220955/371472 [6:54:51<13:07:51,  3.18it/s]
 59%|█████▉    | 220956/371472 [6:54:51<12:51:25,  3.25it/s]
 59%|█████▉    | 220957/371472 [6:54:52<12:38:45,  3.31it/s]
 59%|█████▉    | 220958/371472 [6:54:52<14:20:41,  2.91it/s]
 59%|█████▉    | 220959/371472 [6:54:52<13:59:16,  2.99it/s]
 59%|█████▉    | 220960/371472 [6:54:53<13:15:22,  3.15it/s]
                                                            
{'loss': 2.8272, 'learning_rate': 4.6485595466396603e-07, 'epoch': 9.52}
+
 59%|█████▉    | 220960/371472 [6:54:53<13:15:22,  3.15it/s]
 59%|█████▉    | 220961/371472 [6:54:53<13:06:56,  3.19it/s]
 59%|█████▉    | 220962/371472 [6:54:53<12:42:56,  3.29it/s]
 59%|█████▉    | 220963/371472 [6:54:54<12:27:14,  3.36it/s]
 59%|█████▉    | 220964/371472 [6:54:54<12:54:26,  3.24it/s]
 59%|█████▉    | 220965/371472 [6:54:54<12:28:21,  3.35it/s]
 59%|█████▉    | 220966/371472 [6:54:55<12:42:49,  3.29it/s]
 59%|█████▉    | 220967/371472 [6:54:55<12:38:35,  3.31it/s]
 59%|█████▉    | 220968/371472 [6:54:55<12:36:07,  3.32it/s]
 59%|█████▉    | 220969/371472 [6:54:55<12:44:13,  3.28it/s]
 59%|█████▉    | 220970/371472 [6:54:56<13:04:58,  3.20it/s]
 59%|█████▉    | 220971/371472 [6:54:56<15:07:33,  2.76it/s]
 59%|█████▉    | 220972/371472 [6:54:57<14:22:49,  2.91it/s]
 59%|█████▉    | 220973/371472 [6:54:57<13:15:37,  3.15it/s]
 59%|█████▉    | 220974/371472 [6:54:57<12:45:36,  3.28it/s]
 59%|█████▉    | 220975/371472 [6:54:57<12:20:22,  3.39it/s]
 59%|█████▉    | 220976/371472 [6:54:58<12:18:29,  3.40it/s]
 59%|█████▉    | 220977/371472 [6:54:58<12:07:31,  3.45it/s]
 59%|█████▉    | 220978/371472 [6:54:58<12:37:57,  3.31it/s]
 59%|█████▉    | 220979/371472 [6:54:59<12:14:39,  3.41it/s]
 59%|█████▉    | 220980/371472 [6:54:59<12:02:59,  3.47it/s]
                                                            
{'loss': 2.7964, 'learning_rate': 4.6480747268848715e-07, 'epoch': 9.52}
+
 59%|█████▉    | 220980/371472 [6:54:59<12:02:59,  3.47it/s]
 59%|█████▉    | 220981/371472 [6:54:59<12:02:56,  3.47it/s]
 59%|█████▉    | 220982/371472 [6:54:59<11:25:12,  3.66it/s]
 59%|█████▉    | 220983/371472 [6:55:00<11:06:31,  3.76it/s]
 59%|█████▉    | 220984/371472 [6:55:00<12:13:18,  3.42it/s]
 59%|█████▉    | 220985/371472 [6:55:00<11:49:23,  3.54it/s]
 59%|█████▉    | 220986/371472 [6:55:00<11:35:09,  3.61it/s]
 59%|█████▉    | 220987/371472 [6:55:01<11:38:03,  3.59it/s]
 59%|█████▉    | 220988/371472 [6:55:01<11:49:30,  3.53it/s]
 59%|█████▉    | 220989/371472 [6:55:01<12:43:50,  3.28it/s]
 59%|█████▉    | 220990/371472 [6:55:02<12:42:54,  3.29it/s]
 59%|█████▉    | 220991/371472 [6:55:02<11:59:14,  3.49it/s]
 59%|█████▉    | 220992/371472 [6:55:02<12:05:51,  3.46it/s]
 59%|█████▉    | 220993/371472 [6:55:03<11:48:02,  3.54it/s]
 59%|█████▉    | 220994/371472 [6:55:03<11:49:54,  3.53it/s]
 59%|█████▉    | 220995/371472 [6:55:03<11:41:00,  3.58it/s]
 59%|█████▉    | 220996/371472 [6:55:03<11:40:15,  3.58it/s]
 59%|█████▉    | 220997/371472 [6:55:04<12:30:41,  3.34it/s]
 59%|█████▉    | 220998/371472 [6:55:04<11:56:53,  3.50it/s]
 59%|█████▉    | 220999/371472 [6:55:04<11:35:24,  3.61it/s]
 59%|█████▉    | 221000/371472 [6:55:05<11:29:15,  3.64it/s]
                                                            
{'loss': 2.8806, 'learning_rate': 4.647589907130082e-07, 'epoch': 9.52}
+
 59%|█████▉    | 221000/371472 [6:55:05<11:29:15,  3.64it/s]
 59%|█████▉    | 221001/371472 [6:55:05<11:37:32,  3.60it/s]
 59%|█████▉    | 221002/371472 [6:55:05<11:46:56,  3.55it/s]
 59%|█████▉    | 221003/371472 [6:55:05<11:39:51,  3.58it/s]
 59%|█████▉    | 221004/371472 [6:55:06<11:45:59,  3.55it/s]
 59%|█████▉    | 221005/371472 [6:55:06<12:03:03,  3.47it/s]
 59%|█████▉    | 221006/371472 [6:55:06<11:56:46,  3.50it/s]
 59%|█████▉    | 221007/371472 [6:55:07<12:03:46,  3.46it/s]
 59%|█████▉    | 221008/371472 [6:55:07<11:54:54,  3.51it/s]
 59%|█████▉    | 221009/371472 [6:55:07<11:50:12,  3.53it/s]
 59%|█████▉    | 221010/371472 [6:55:07<11:34:06,  3.61it/s]
 59%|█████▉    | 221011/371472 [6:55:08<11:49:50,  3.53it/s]
 59%|█████▉    | 221012/371472 [6:55:08<11:46:15,  3.55it/s]
 59%|█████▉    | 221013/371472 [6:55:08<11:38:12,  3.59it/s]
 59%|█████▉    | 221014/371472 [6:55:08<11:29:08,  3.64it/s]
 59%|█████▉    | 221015/371472 [6:55:09<11:34:06,  3.61it/s]
 59%|█████▉    | 221016/371472 [6:55:09<11:26:41,  3.65it/s]
 59%|█████▉    | 221017/371472 [6:55:09<11:30:08,  3.63it/s]
 59%|█████▉    | 221018/371472 [6:55:10<11:18:35,  3.70it/s]
 59%|█████▉    | 221019/371472 [6:55:10<11:20:02,  3.69it/s]
 59%|█████▉    | 221020/371472 [6:55:10<11:26:46,  3.65it/s]
                                                            
{'loss': 2.5979, 'learning_rate': 4.647105087375294e-07, 'epoch': 9.52}
+
 59%|█████▉    | 221020/371472 [6:55:10<11:26:46,  3.65it/s]
 59%|█████▉    | 221021/371472 [6:55:10<11:52:13,  3.52it/s]
 59%|█████▉    | 221022/371472 [6:55:11<12:04:06,  3.46it/s]
 59%|█████▉    | 221023/371472 [6:55:11<11:57:35,  3.49it/s]
 59%|█████▉    | 221024/371472 [6:55:11<11:59:45,  3.48it/s]
 59%|█████▉    | 221025/371472 [6:55:12<12:09:23,  3.44it/s]
 60%|█████▉    | 221026/371472 [6:55:12<14:53:37,  2.81it/s]
 60%|█████▉    | 221027/371472 [6:55:12<13:38:39,  3.06it/s]
 60%|█████▉    | 221028/371472 [6:55:13<13:04:39,  3.20it/s]
 60%|█████▉    | 221029/371472 [6:55:13<12:25:32,  3.36it/s]
 60%|█████▉    | 221030/371472 [6:55:13<12:35:08,  3.32it/s]
 60%|█████▉    | 221031/371472 [6:55:13<12:13:18,  3.42it/s]
 60%|█████▉    | 221032/371472 [6:55:14<12:14:01,  3.42it/s]
 60%|█████▉    | 221033/371472 [6:55:14<11:57:27,  3.49it/s]
 60%|█████▉    | 221034/371472 [6:55:14<12:10:51,  3.43it/s]
 60%|█████▉    | 221035/371472 [6:55:15<12:58:51,  3.22it/s]
 60%|█████▉    | 221036/371472 [6:55:15<12:41:12,  3.29it/s]
 60%|█████▉    | 221037/371472 [6:55:15<13:00:31,  3.21it/s]
 60%|█████▉    | 221038/371472 [6:55:16<13:04:05,  3.20it/s]
 60%|█████▉    | 221039/371472 [6:55:16<14:53:24,  2.81it/s]
 60%|█████▉    | 221040/371472 [6:55:16<14:08:48,  2.95it/s]
                                                            
{'loss': 2.7241, 'learning_rate': 4.646620267620504e-07, 'epoch': 9.52}
+
 60%|█████▉    | 221040/371472 [6:55:16<14:08:48,  2.95it/s]
 60%|█████▉    | 221041/371472 [6:55:17<13:25:00,  3.11it/s]
 60%|█████▉    | 221042/371472 [6:55:17<13:03:59,  3.20it/s]
 60%|█████▉    | 221043/371472 [6:55:17<13:22:20,  3.12it/s]
 60%|█████▉    | 221044/371472 [6:55:18<13:05:41,  3.19it/s]
 60%|█████▉    | 221045/371472 [6:55:18<13:46:49,  3.03it/s]
 60%|█████▉    | 221046/371472 [6:55:18<13:38:02,  3.06it/s]
 60%|█████▉    | 221047/371472 [6:55:19<14:04:39,  2.97it/s]
 60%|█████▉    | 221048/371472 [6:55:19<13:12:23,  3.16it/s]
 60%|█████▉    | 221049/371472 [6:55:19<12:39:36,  3.30it/s]
 60%|█████▉    | 221050/371472 [6:55:19<12:07:27,  3.45it/s]
 60%|█████▉    | 221051/371472 [6:55:20<12:07:42,  3.45it/s]
 60%|█████▉    | 221052/371472 [6:55:20<12:14:23,  3.41it/s]
 60%|█████▉    | 221053/371472 [6:55:20<12:06:52,  3.45it/s]
 60%|█████▉    | 221054/371472 [6:55:21<11:52:00,  3.52it/s]
 60%|█████▉    | 221055/371472 [6:55:21<11:57:03,  3.50it/s]
 60%|█████▉    | 221056/371472 [6:55:21<11:47:19,  3.54it/s]
 60%|█████▉    | 221057/371472 [6:55:21<11:43:36,  3.56it/s]
 60%|█████▉    | 221058/371472 [6:55:22<12:06:01,  3.45it/s]
 60%|█████▉    | 221059/371472 [6:55:22<12:10:16,  3.43it/s]
 60%|█████▉    | 221060/371472 [6:55:22<12:10:42,  3.43it/s]
                                                            
{'loss': 2.9737, 'learning_rate': 4.646135447865716e-07, 'epoch': 9.52}
+
 60%|█████▉    | 221060/371472 [6:55:22<12:10:42,  3.43it/s]
 60%|█████▉    | 221061/371472 [6:55:23<12:45:33,  3.27it/s]
 60%|█████▉    | 221062/371472 [6:55:23<12:23:40,  3.37it/s]
 60%|█████▉    | 221063/371472 [6:55:23<12:12:40,  3.42it/s]
 60%|█████▉    | 221064/371472 [6:55:23<11:58:35,  3.49it/s]
 60%|█████▉    | 221065/371472 [6:55:24<13:46:07,  3.03it/s]
 60%|█████▉    | 221066/371472 [6:55:24<12:59:49,  3.21it/s]
 60%|█████▉    | 221067/371472 [6:55:25<14:20:17,  2.91it/s]
 60%|█████▉    | 221068/371472 [6:55:25<14:03:15,  2.97it/s]
 60%|█████▉    | 221069/371472 [6:55:25<13:30:33,  3.09it/s]
 60%|█████▉    | 221070/371472 [6:55:25<12:39:34,  3.30it/s]
 60%|█████▉    | 221071/371472 [6:55:26<12:13:57,  3.42it/s]
 60%|█████▉    | 221072/371472 [6:55:26<12:28:31,  3.35it/s]
 60%|█████▉    | 221073/371472 [6:55:26<12:48:00,  3.26it/s]
 60%|█████▉    | 221074/371472 [6:55:27<12:35:51,  3.32it/s]
 60%|█████▉    | 221075/371472 [6:55:27<12:16:22,  3.40it/s]
 60%|█████▉    | 221076/371472 [6:55:27<12:21:07,  3.38it/s]
 60%|█████▉    | 221077/371472 [6:55:28<12:38:14,  3.31it/s]
 60%|█████▉    | 221078/371472 [6:55:28<12:15:47,  3.41it/s]
 60%|█████▉    | 221079/371472 [6:55:28<12:11:33,  3.43it/s]
 60%|█████▉    | 221080/371472 [6:55:28<12:38:49,  3.30it/s]
                                                            
{'loss': 2.662, 'learning_rate': 4.6456506281109267e-07, 'epoch': 9.52}
+
 60%|█████▉    | 221080/371472 [6:55:28<12:38:49,  3.30it/s]
 60%|█████▉    | 221081/371472 [6:55:29<12:16:01,  3.41it/s]
 60%|█████▉    | 221082/371472 [6:55:29<12:51:27,  3.25it/s]
 60%|█████▉    | 221083/371472 [6:55:29<12:15:12,  3.41it/s]
 60%|█████▉    | 221084/371472 [6:55:30<12:05:25,  3.46it/s]
 60%|█████▉    | 221085/371472 [6:55:30<12:17:49,  3.40it/s]
 60%|█████▉    | 221086/371472 [6:55:30<12:53:54,  3.24it/s]
 60%|█████▉    | 221087/371472 [6:55:31<12:38:15,  3.31it/s]
 60%|█████▉    | 221088/371472 [6:55:31<13:19:46,  3.13it/s]
 60%|█████▉    | 221089/371472 [6:55:31<12:40:29,  3.30it/s]
 60%|█████▉    | 221090/371472 [6:55:31<12:03:35,  3.46it/s]
 60%|█████▉    | 221091/371472 [6:55:32<12:08:10,  3.44it/s]
 60%|█████▉    | 221092/371472 [6:55:32<12:07:15,  3.45it/s]
 60%|█████▉    | 221093/371472 [6:55:32<12:13:18,  3.42it/s]
 60%|█████▉    | 221094/371472 [6:55:33<12:08:00,  3.44it/s]
 60%|█████▉    | 221095/371472 [6:55:33<12:04:20,  3.46it/s]
 60%|█████▉    | 221096/371472 [6:55:33<12:46:32,  3.27it/s]
 60%|█████▉    | 221097/371472 [6:55:34<13:46:21,  3.03it/s]
 60%|█████▉    | 221098/371472 [6:55:34<12:50:47,  3.25it/s]
 60%|█████▉    | 221099/371472 [6:55:34<13:07:03,  3.18it/s]
 60%|█████▉    | 221100/371472 [6:55:35<13:59:29,  2.99it/s]
                                                            
{'loss': 2.662, 'learning_rate': 4.6451658083561374e-07, 'epoch': 9.52}
+
 60%|█████▉    | 221100/371472 [6:55:35<13:59:29,  2.99it/s]
 60%|█████▉    | 221101/371472 [6:55:35<13:21:53,  3.13it/s]
 60%|█████▉    | 221102/371472 [6:55:35<13:01:56,  3.21it/s]
 60%|█████▉    | 221103/371472 [6:55:35<12:20:37,  3.38it/s]
 60%|█████▉    | 221104/371472 [6:55:36<15:01:14,  2.78it/s]
 60%|█████▉    | 221105/371472 [6:55:36<13:50:47,  3.02it/s]
 60%|█████▉    | 221106/371472 [6:55:37<13:53:40,  3.01it/s]
 60%|█████▉    | 221107/371472 [6:55:37<13:29:04,  3.10it/s]
 60%|█████▉    | 221108/371472 [6:55:37<12:41:53,  3.29it/s]
 60%|█████▉    | 221109/371472 [6:55:37<12:18:17,  3.39it/s]
 60%|█████▉    | 221110/371472 [6:55:38<12:15:53,  3.41it/s]
 60%|█████▉    | 221111/371472 [6:55:38<11:47:25,  3.54it/s]
 60%|█████▉    | 221112/371472 [6:55:38<11:41:59,  3.57it/s]
 60%|█████▉    | 221113/371472 [6:55:38<11:32:23,  3.62it/s]
 60%|█████▉    | 221114/371472 [6:55:39<11:50:13,  3.53it/s]
 60%|█████▉    | 221115/371472 [6:55:39<11:31:33,  3.62it/s]
 60%|█████▉    | 221116/371472 [6:55:39<11:35:35,  3.60it/s]
 60%|█████▉    | 221117/371472 [6:55:40<11:20:08,  3.68it/s]
 60%|█████▉    | 221118/371472 [6:55:40<12:19:05,  3.39it/s]
 60%|█████▉    | 221119/371472 [6:55:40<12:08:40,  3.44it/s]
 60%|█████▉    | 221120/371472 [6:55:40<12:05:01,  3.46it/s]
                                                            
{'loss': 2.8679, 'learning_rate': 4.6446809886013486e-07, 'epoch': 9.52}
+
 60%|█████▉    | 221120/371472 [6:55:40<12:05:01,  3.46it/s]
 60%|█████▉    | 221121/371472 [6:55:41<11:43:34,  3.56it/s]
 60%|█████▉    | 221122/371472 [6:55:41<11:39:49,  3.58it/s]
 60%|█████▉    | 221123/371472 [6:55:41<11:37:31,  3.59it/s]
 60%|█████▉    | 221124/371472 [6:55:42<11:18:52,  3.69it/s]
 60%|█████▉    | 221125/371472 [6:55:42<11:27:53,  3.64it/s]
 60%|█████▉    | 221126/371472 [6:55:42<11:17:31,  3.70it/s]
 60%|█████▉    | 221127/371472 [6:55:42<11:15:50,  3.71it/s]
 60%|█████▉    | 221128/371472 [6:55:43<11:02:05,  3.78it/s]
 60%|█████▉    | 221129/371472 [6:55:43<11:32:25,  3.62it/s]
 60%|█████▉    | 221130/371472 [6:55:43<12:27:15,  3.35it/s]
 60%|█████▉    | 221131/371472 [6:55:44<12:21:24,  3.38it/s]
 60%|█████▉    | 221132/371472 [6:55:44<12:09:02,  3.44it/s]
 60%|█████▉    | 221133/371472 [6:55:44<12:10:21,  3.43it/s]
 60%|█████▉    | 221134/371472 [6:55:44<11:50:18,  3.53it/s]
 60%|█████▉    | 221135/371472 [6:55:45<11:30:18,  3.63it/s]
 60%|█████▉    | 221136/371472 [6:55:45<11:30:39,  3.63it/s]
 60%|█████▉    | 221137/371472 [6:55:45<11:16:15,  3.71it/s]
 60%|█████▉    | 221138/371472 [6:55:45<11:27:08,  3.65it/s]
 60%|█████▉    | 221139/371472 [6:55:46<11:16:17,  3.70it/s]
 60%|█████▉    | 221140/371472 [6:55:46<11:16:58,  3.70it/s]
                                                            
{'loss': 2.7523, 'learning_rate': 4.6441961688465594e-07, 'epoch': 9.52}
+
 60%|█████▉    | 221140/371472 [6:55:46<11:16:58,  3.70it/s]
 60%|█████▉    | 221141/371472 [6:55:46<12:18:24,  3.39it/s]
 60%|█████▉    | 221142/371472 [6:55:47<12:10:02,  3.43it/s]
 60%|█████▉    | 221143/371472 [6:55:47<12:21:53,  3.38it/s]
 60%|█████▉    | 221144/371472 [6:55:47<13:49:26,  3.02it/s]
 60%|█████▉    | 221145/371472 [6:55:48<13:37:23,  3.07it/s]
 60%|█████▉    | 221146/371472 [6:55:48<13:12:12,  3.16it/s]
 60%|█████▉    | 221147/371472 [6:55:48<15:04:44,  2.77it/s]
 60%|█████▉    | 221148/371472 [6:55:49<13:58:16,  2.99it/s]
 60%|█████▉    | 221149/371472 [6:55:49<13:19:59,  3.13it/s]
 60%|█████▉    | 221150/371472 [6:55:49<12:31:02,  3.34it/s]
 60%|█████▉    | 221151/371472 [6:55:49<12:23:40,  3.37it/s]
 60%|█████▉    | 221152/371472 [6:55:50<12:08:31,  3.44it/s]
 60%|█████▉    | 221153/371472 [6:55:50<11:43:35,  3.56it/s]
 60%|█████▉    | 221154/371472 [6:55:50<11:37:42,  3.59it/s]
 60%|█████▉    | 221155/371472 [6:55:51<11:43:30,  3.56it/s]
 60%|█████▉    | 221156/371472 [6:55:51<11:45:56,  3.55it/s]
 60%|█████▉    | 221157/371472 [6:55:51<11:52:35,  3.52it/s]
 60%|█████▉    | 221158/371472 [6:55:51<11:41:35,  3.57it/s]
 60%|█████▉    | 221159/371472 [6:55:52<11:51:30,  3.52it/s]
 60%|█████▉    | 221160/371472 [6:55:52<11:32:29,  3.62it/s]
                                                            
{'loss': 2.6111, 'learning_rate': 4.6437113490917706e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221160/371472 [6:55:52<11:32:29,  3.62it/s]
 60%|█████▉    | 221161/371472 [6:55:52<11:35:13,  3.60it/s]
 60%|█████▉    | 221162/371472 [6:55:53<11:47:23,  3.54it/s]
 60%|█████▉    | 221163/371472 [6:55:53<11:28:10,  3.64it/s]
 60%|█████▉    | 221164/371472 [6:55:53<11:17:30,  3.70it/s]
 60%|█████▉    | 221165/371472 [6:55:53<11:22:26,  3.67it/s]
 60%|█████▉    | 221166/371472 [6:55:54<11:06:57,  3.76it/s]
 60%|█████▉    | 221167/371472 [6:55:54<11:23:00,  3.67it/s]
 60%|█████▉    | 221168/371472 [6:55:54<11:07:17,  3.75it/s]
 60%|█████▉    | 221169/371472 [6:55:54<10:59:43,  3.80it/s]
 60%|█████▉    | 221170/371472 [6:55:55<11:29:02,  3.64it/s]
 60%|█████▉    | 221171/371472 [6:55:55<12:36:12,  3.31it/s]
 60%|█████▉    | 221172/371472 [6:55:55<12:04:43,  3.46it/s]
 60%|█████▉    | 221173/371472 [6:55:56<13:34:25,  3.08it/s]
 60%|█████▉    | 221174/371472 [6:55:56<12:50:02,  3.25it/s]
 60%|█████▉    | 221175/371472 [6:55:56<12:38:49,  3.30it/s]
 60%|█████▉    | 221176/371472 [6:55:57<12:14:08,  3.41it/s]
 60%|█████▉    | 221177/371472 [6:55:57<11:54:07,  3.51it/s]
 60%|█████▉    | 221178/371472 [6:55:57<11:43:21,  3.56it/s]
 60%|█████▉    | 221179/371472 [6:55:57<11:41:24,  3.57it/s]
 60%|█████▉    | 221180/371472 [6:55:58<11:40:21,  3.58it/s]
                                                            
{'loss': 2.6969, 'learning_rate': 4.6432265293369813e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221180/371472 [6:55:58<11:40:21,  3.58it/s]
 60%|█████▉    | 221181/371472 [6:55:58<11:55:58,  3.50it/s]
 60%|█████▉    | 221182/371472 [6:55:58<12:03:55,  3.46it/s]
 60%|█████▉    | 221183/371472 [6:55:59<12:05:45,  3.45it/s]
 60%|█████▉    | 221184/371472 [6:55:59<12:38:28,  3.30it/s]
 60%|█████▉    | 221185/371472 [6:55:59<12:20:17,  3.38it/s]
 60%|█████▉    | 221186/371472 [6:55:59<12:01:42,  3.47it/s]
 60%|█████▉    | 221187/371472 [6:56:00<11:53:00,  3.51it/s]
 60%|█████▉    | 221188/371472 [6:56:00<11:32:59,  3.61it/s]
 60%|█████▉    | 221189/371472 [6:56:00<11:42:45,  3.56it/s]
 60%|█████▉    | 221190/371472 [6:56:01<12:01:29,  3.47it/s]
 60%|█████▉    | 221191/371472 [6:56:01<11:56:27,  3.50it/s]
 60%|█████▉    | 221192/371472 [6:56:01<12:59:41,  3.21it/s]
 60%|█████▉    | 221193/371472 [6:56:01<12:23:30,  3.37it/s]
 60%|█████▉    | 221194/371472 [6:56:02<12:09:55,  3.43it/s]
 60%|█████▉    | 221195/371472 [6:56:02<11:59:54,  3.48it/s]
 60%|█████▉    | 221196/371472 [6:56:02<11:50:31,  3.53it/s]
 60%|█████▉    | 221197/371472 [6:56:03<11:46:33,  3.54it/s]
 60%|█████▉    | 221198/371472 [6:56:03<12:17:31,  3.40it/s]
 60%|█████▉    | 221199/371472 [6:56:03<12:23:51,  3.37it/s]
 60%|█████▉    | 221200/371472 [6:56:03<11:58:53,  3.48it/s]
                                                            
{'loss': 2.9035, 'learning_rate': 4.642741709582193e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221200/371472 [6:56:03<11:58:53,  3.48it/s]
 60%|█████▉    | 221201/371472 [6:56:04<13:24:28,  3.11it/s]
 60%|█████▉    | 221202/371472 [6:56:04<12:36:29,  3.31it/s]
 60%|█████▉    | 221203/371472 [6:56:04<12:50:27,  3.25it/s]
 60%|█████▉    | 221204/371472 [6:56:05<12:38:15,  3.30it/s]
 60%|█████▉    | 221205/371472 [6:56:05<12:02:48,  3.46it/s]
 60%|█████▉    | 221206/371472 [6:56:05<12:11:09,  3.43it/s]
 60%|█████▉    | 221207/371472 [6:56:06<11:56:53,  3.49it/s]
 60%|█████▉    | 221208/371472 [6:56:06<11:30:58,  3.62it/s]
 60%|█████▉    | 221209/371472 [6:56:06<11:52:35,  3.51it/s]
 60%|█████▉    | 221210/371472 [6:56:06<11:34:19,  3.61it/s]
 60%|█████▉    | 221211/371472 [6:56:07<11:36:40,  3.59it/s]
 60%|█████▉    | 221212/371472 [6:56:07<11:27:20,  3.64it/s]
 60%|█████▉    | 221213/371472 [6:56:07<11:46:39,  3.54it/s]
 60%|█████▉    | 221214/371472 [6:56:08<12:04:46,  3.46it/s]
 60%|█████▉    | 221215/371472 [6:56:08<12:23:06,  3.37it/s]
 60%|█████▉    | 221216/371472 [6:56:08<12:26:37,  3.35it/s]
 60%|█████▉    | 221217/371472 [6:56:08<12:05:50,  3.45it/s]
 60%|█████▉    | 221218/371472 [6:56:09<11:38:31,  3.59it/s]
 60%|█████▉    | 221219/371472 [6:56:09<11:08:20,  3.75it/s]
 60%|█████▉    | 221220/371472 [6:56:09<11:26:21,  3.65it/s]
                                                            
{'loss': 2.6181, 'learning_rate': 4.642256889827404e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221220/371472 [6:56:09<11:26:21,  3.65it/s]
 60%|█████▉    | 221221/371472 [6:56:09<11:40:20,  3.58it/s]
 60%|█████▉    | 221222/371472 [6:56:10<11:29:52,  3.63it/s]
 60%|█████▉    | 221223/371472 [6:56:10<11:30:12,  3.63it/s]
 60%|█████▉    | 221224/371472 [6:56:10<11:37:09,  3.59it/s]
 60%|█████▉    | 221225/371472 [6:56:11<11:37:15,  3.59it/s]
 60%|█████▉    | 221226/371472 [6:56:11<12:11:45,  3.42it/s]
 60%|█████▉    | 221227/371472 [6:56:11<12:20:52,  3.38it/s]
 60%|█████▉    | 221228/371472 [6:56:11<12:00:30,  3.48it/s]
 60%|█████▉    | 221229/371472 [6:56:12<12:12:39,  3.42it/s]
 60%|█████▉    | 221230/371472 [6:56:12<12:01:11,  3.47it/s]
 60%|█████▉    | 221231/371472 [6:56:12<11:44:58,  3.55it/s]
 60%|█████▉    | 221232/371472 [6:56:13<11:50:47,  3.52it/s]
 60%|█████▉    | 221233/371472 [6:56:13<11:52:59,  3.51it/s]
 60%|█████▉    | 221234/371472 [6:56:13<12:22:15,  3.37it/s]
 60%|█████▉    | 221235/371472 [6:56:14<11:58:23,  3.49it/s]
 60%|█████▉    | 221236/371472 [6:56:14<12:17:39,  3.39it/s]
 60%|█████▉    | 221237/371472 [6:56:14<11:55:26,  3.50it/s]
 60%|█████▉    | 221238/371472 [6:56:14<11:46:08,  3.55it/s]
 60%|█████▉    | 221239/371472 [6:56:15<11:34:47,  3.60it/s]
 60%|█████▉    | 221240/371472 [6:56:15<11:35:43,  3.60it/s]
                                                            
{'loss': 2.6503, 'learning_rate': 4.641772070072615e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221240/371472 [6:56:15<11:35:43,  3.60it/s]
 60%|█████▉    | 221241/371472 [6:56:15<11:36:20,  3.60it/s]
 60%|█████▉    | 221242/371472 [6:56:15<11:36:48,  3.59it/s]
 60%|█████▉    | 221243/371472 [6:56:16<11:36:21,  3.60it/s]
 60%|█████▉    | 221244/371472 [6:56:16<11:46:59,  3.54it/s]
 60%|█████▉    | 221245/371472 [6:56:16<12:08:26,  3.44it/s]
 60%|█████▉    | 221246/371472 [6:56:17<11:51:51,  3.52it/s]
 60%|█████▉    | 221247/371472 [6:56:17<11:35:57,  3.60it/s]
 60%|█████▉    | 221248/371472 [6:56:17<11:33:56,  3.61it/s]
 60%|█████▉    | 221249/371472 [6:56:17<12:13:52,  3.41it/s]
 60%|█████▉    | 221250/371472 [6:56:18<12:15:20,  3.40it/s]
 60%|█████▉    | 221251/371472 [6:56:18<12:25:36,  3.36it/s]
 60%|█████▉    | 221252/371472 [6:56:18<12:23:45,  3.37it/s]
 60%|█████▉    | 221253/371472 [6:56:19<12:08:16,  3.44it/s]
 60%|█████▉    | 221254/371472 [6:56:19<12:14:00,  3.41it/s]
 60%|█████▉    | 221255/371472 [6:56:19<12:03:44,  3.46it/s]
 60%|█████▉    | 221256/371472 [6:56:20<12:17:24,  3.40it/s]
 60%|█████▉    | 221257/371472 [6:56:20<11:56:38,  3.49it/s]
 60%|█████▉    | 221258/371472 [6:56:20<11:40:00,  3.58it/s]
 60%|█████▉    | 221259/371472 [6:56:20<11:46:51,  3.54it/s]
 60%|█████▉    | 221260/371472 [6:56:21<11:53:48,  3.51it/s]
                                                            
{'loss': 2.698, 'learning_rate': 4.641287250317826e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221260/371472 [6:56:21<11:53:48,  3.51it/s]
 60%|█████▉    | 221261/371472 [6:56:21<11:57:59,  3.49it/s]
 60%|█████▉    | 221262/371472 [6:56:21<11:30:27,  3.63it/s]
 60%|█████▉    | 221263/371472 [6:56:21<11:32:40,  3.61it/s]
 60%|█████▉    | 221264/371472 [6:56:22<11:21:42,  3.67it/s]
 60%|█████▉    | 221265/371472 [6:56:22<11:15:18,  3.71it/s]
 60%|█████▉    | 221266/371472 [6:56:22<12:16:56,  3.40it/s]
 60%|█████▉    | 221267/371472 [6:56:23<13:54:07,  3.00it/s]
 60%|█████▉    | 221268/371472 [6:56:23<13:22:11,  3.12it/s]
 60%|█████▉    | 221269/371472 [6:56:23<13:20:25,  3.13it/s]
 60%|█████▉    | 221270/371472 [6:56:24<14:27:37,  2.89it/s]
 60%|█████▉    | 221271/371472 [6:56:24<13:32:16,  3.08it/s]
 60%|█████▉    | 221272/371472 [6:56:24<12:57:18,  3.22it/s]
 60%|█████▉    | 221273/371472 [6:56:25<12:50:08,  3.25it/s]
 60%|█████▉    | 221274/371472 [6:56:25<12:30:38,  3.33it/s]
 60%|█████▉    | 221275/371472 [6:56:25<12:30:44,  3.33it/s]
 60%|█████▉    | 221276/371472 [6:56:26<12:44:21,  3.27it/s]
 60%|█████▉    | 221277/371472 [6:56:26<12:18:22,  3.39it/s]
 60%|█████▉    | 221278/371472 [6:56:26<12:07:46,  3.44it/s]
 60%|█████▉    | 221279/371472 [6:56:26<11:48:21,  3.53it/s]
 60%|█████▉    | 221280/371472 [6:56:27<11:45:34,  3.55it/s]
                                                            
{'loss': 2.8984, 'learning_rate': 4.6408024305630375e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221280/371472 [6:56:27<11:45:34,  3.55it/s]
 60%|█████▉    | 221281/371472 [6:56:27<11:40:08,  3.58it/s]
 60%|█████▉    | 221282/371472 [6:56:27<11:31:50,  3.62it/s]
 60%|█████▉    | 221283/371472 [6:56:28<12:08:05,  3.44it/s]
 60%|█████▉    | 221284/371472 [6:56:28<12:00:39,  3.47it/s]
 60%|█████▉    | 221285/371472 [6:56:28<11:56:21,  3.49it/s]
 60%|█████▉    | 221286/371472 [6:56:28<12:07:30,  3.44it/s]
 60%|█████▉    | 221287/371472 [6:56:29<12:07:56,  3.44it/s]
 60%|█████▉    | 221288/371472 [6:56:29<12:04:04,  3.46it/s]
 60%|█████▉    | 221289/371472 [6:56:29<11:53:11,  3.51it/s]
 60%|█████▉    | 221290/371472 [6:56:30<11:53:34,  3.51it/s]
 60%|█████▉    | 221291/371472 [6:56:30<12:00:56,  3.47it/s]
 60%|█████▉    | 221292/371472 [6:56:30<11:48:53,  3.53it/s]
 60%|█████▉    | 221293/371472 [6:56:30<11:34:51,  3.60it/s]
 60%|█████▉    | 221294/371472 [6:56:31<11:25:43,  3.65it/s]
 60%|█████▉    | 221295/371472 [6:56:31<11:29:05,  3.63it/s]
 60%|█████▉    | 221296/371472 [6:56:31<12:17:54,  3.39it/s]
 60%|█████▉    | 221297/371472 [6:56:32<12:05:09,  3.45it/s]
 60%|█████▉    | 221298/371472 [6:56:32<12:03:53,  3.46it/s]
 60%|█████▉    | 221299/371472 [6:56:32<11:59:35,  3.48it/s]
 60%|█████▉    | 221300/371472 [6:56:32<12:03:47,  3.46it/s]
                                                            
{'loss': 2.8184, 'learning_rate': 4.6403176108082477e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221300/371472 [6:56:32<12:03:47,  3.46it/s]
 60%|█████▉    | 221301/371472 [6:56:33<12:03:37,  3.46it/s]
 60%|█████▉    | 221302/371472 [6:56:33<11:40:38,  3.57it/s]
 60%|█████▉    | 221303/371472 [6:56:33<11:55:55,  3.50it/s]
 60%|█████▉    | 221304/371472 [6:56:33<11:34:26,  3.60it/s]
 60%|█████▉    | 221305/371472 [6:56:34<11:44:39,  3.55it/s]
 60%|█████▉    | 221306/371472 [6:56:34<11:35:03,  3.60it/s]
 60%|█████▉    | 221307/371472 [6:56:34<11:51:32,  3.52it/s]
 60%|█████▉    | 221308/371472 [6:56:35<11:44:40,  3.55it/s]
 60%|█████▉    | 221309/371472 [6:56:35<12:40:34,  3.29it/s]
 60%|█████▉    | 221310/371472 [6:56:35<12:22:29,  3.37it/s]
 60%|█████▉    | 221311/371472 [6:56:36<12:24:17,  3.36it/s]
 60%|█████▉    | 221312/371472 [6:56:36<13:30:46,  3.09it/s]
 60%|█████▉    | 221313/371472 [6:56:36<13:08:42,  3.17it/s]
 60%|█████▉    | 221314/371472 [6:56:37<12:49:20,  3.25it/s]
 60%|█████▉    | 221315/371472 [6:56:37<12:05:30,  3.45it/s]
 60%|█████▉    | 221316/371472 [6:56:37<12:16:18,  3.40it/s]
 60%|█████▉    | 221317/371472 [6:56:37<12:58:29,  3.21it/s]
 60%|█████▉    | 221318/371472 [6:56:38<12:48:11,  3.26it/s]
 60%|█████▉    | 221319/371472 [6:56:38<12:25:53,  3.36it/s]
 60%|█████▉    | 221320/371472 [6:56:38<12:49:09,  3.25it/s]
                                                            
{'loss': 2.7037, 'learning_rate': 4.6398327910534595e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221320/371472 [6:56:38<12:49:09,  3.25it/s]
 60%|█████▉    | 221321/371472 [6:56:39<12:35:12,  3.31it/s]
 60%|█████▉    | 221322/371472 [6:56:39<12:09:04,  3.43it/s]
 60%|█████▉    | 221323/371472 [6:56:39<12:11:28,  3.42it/s]
 60%|█████▉    | 221324/371472 [6:56:40<12:56:33,  3.22it/s]
 60%|█████▉    | 221325/371472 [6:56:40<12:45:09,  3.27it/s]
 60%|█████▉    | 221326/371472 [6:56:40<12:16:43,  3.40it/s]
 60%|█████▉    | 221327/371472 [6:56:40<12:02:00,  3.47it/s]
 60%|█████▉    | 221328/371472 [6:56:41<11:49:39,  3.53it/s]
 60%|█████▉    | 221329/371472 [6:56:41<11:47:44,  3.54it/s]
 60%|█████▉    | 221330/371472 [6:56:41<11:42:35,  3.56it/s]
 60%|█████▉    | 221331/371472 [6:56:41<11:49:25,  3.53it/s]
 60%|█████▉    | 221332/371472 [6:56:42<11:27:30,  3.64it/s]
 60%|█████▉    | 221333/371472 [6:56:42<11:19:21,  3.68it/s]
 60%|█████▉    | 221334/371472 [6:56:42<11:37:45,  3.59it/s]
 60%|█████▉    | 221335/371472 [6:56:43<11:32:08,  3.62it/s]
 60%|█████▉    | 221336/371472 [6:56:43<11:45:01,  3.55it/s]
 60%|█████▉    | 221337/371472 [6:56:43<12:33:17,  3.32it/s]
 60%|█████▉    | 221338/371472 [6:56:43<11:51:49,  3.52it/s]
 60%|█████▉    | 221339/371472 [6:56:44<11:54:38,  3.50it/s]
 60%|█████▉    | 221340/371472 [6:56:44<12:30:33,  3.33it/s]
                                                            
{'loss': 2.7479, 'learning_rate': 4.6393479712986697e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221340/371472 [6:56:44<12:30:33,  3.33it/s]
 60%|█████▉    | 221341/371472 [6:56:44<12:18:29,  3.39it/s]
 60%|█████▉    | 221342/371472 [6:56:45<12:21:57,  3.37it/s]
 60%|█████▉    | 221343/371472 [6:56:45<12:01:37,  3.47it/s]
 60%|█████▉    | 221344/371472 [6:56:45<12:01:55,  3.47it/s]
 60%|█████▉    | 221345/371472 [6:56:46<12:08:24,  3.44it/s]
 60%|█████▉    | 221346/371472 [6:56:46<11:51:48,  3.52it/s]
 60%|█████▉    | 221347/371472 [6:56:46<12:01:17,  3.47it/s]
 60%|█████▉    | 221348/371472 [6:56:46<12:04:18,  3.45it/s]
 60%|█████▉    | 221349/371472 [6:56:47<12:03:22,  3.46it/s]
 60%|█████▉    | 221350/371472 [6:56:47<12:04:44,  3.45it/s]
 60%|█████▉    | 221351/371472 [6:56:47<12:07:20,  3.44it/s]
 60%|█████▉    | 221352/371472 [6:56:48<12:16:33,  3.40it/s]
 60%|█████▉    | 221353/371472 [6:56:48<11:53:52,  3.50it/s]
 60%|█████▉    | 221354/371472 [6:56:48<11:49:51,  3.52it/s]
 60%|█████▉    | 221355/371472 [6:56:48<12:16:18,  3.40it/s]
 60%|█████▉    | 221356/371472 [6:56:49<11:57:24,  3.49it/s]
 60%|█████▉    | 221357/371472 [6:56:49<12:20:20,  3.38it/s]
 60%|█████▉    | 221358/371472 [6:56:49<12:29:47,  3.34it/s]
 60%|█████▉    | 221359/371472 [6:56:50<11:59:21,  3.48it/s]
 60%|█████▉    | 221360/371472 [6:56:50<11:44:16,  3.55it/s]
                                                            
{'loss': 2.6851, 'learning_rate': 4.6388631515438815e-07, 'epoch': 9.53}
+
 60%|█████▉    | 221360/371472 [6:56:50<11:44:16,  3.55it/s]
 60%|█████▉    | 221361/371472 [6:56:50<11:55:56,  3.49it/s]
 60%|█████▉    | 221362/371472 [6:56:50<11:46:42,  3.54it/s]
 60%|█████▉    | 221363/371472 [6:56:51<11:41:40,  3.57it/s]
 60%|█████▉    | 221364/371472 [6:56:51<11:56:15,  3.49it/s]
 60%|█████▉    | 221365/371472 [6:56:51<11:56:54,  3.49it/s]
 60%|█████▉    | 221366/371472 [6:56:52<11:54:28,  3.50it/s]
 60%|█████▉    | 221367/371472 [6:56:52<12:05:10,  3.45it/s]
 60%|█████▉    | 221368/371472 [6:56:52<12:18:22,  3.39it/s]
 60%|█████▉    | 221369/371472 [6:56:52<12:01:13,  3.47it/s]
 60%|█████▉    | 221370/371472 [6:56:53<12:26:48,  3.35it/s]
 60%|█████▉    | 221371/371472 [6:56:53<12:10:32,  3.42it/s]
 60%|█████▉    | 221372/371472 [6:56:53<12:17:50,  3.39it/s]
 60%|█████▉    | 221373/371472 [6:56:54<12:01:48,  3.47it/s]
 60%|█████▉    | 221374/371472 [6:56:54<11:49:26,  3.53it/s]
 60%|█████▉    | 221375/371472 [6:56:54<11:49:25,  3.53it/s]
 60%|█████▉    | 221376/371472 [6:56:54<11:50:11,  3.52it/s]
 60%|█████▉    | 221377/371472 [6:56:55<12:06:12,  3.44it/s]
 60%|█████▉    | 221378/371472 [6:56:55<11:45:49,  3.54it/s]
 60%|█████▉    | 221379/371472 [6:56:55<11:53:18,  3.51it/s]
 60%|█████▉    | 221380/371472 [6:56:56<12:47:03,  3.26it/s]
                                                            
{'loss': 2.9043, 'learning_rate': 4.638378331789092e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221380/371472 [6:56:56<12:47:03,  3.26it/s]
 60%|█████▉    | 221381/371472 [6:56:56<12:22:22,  3.37it/s]
 60%|█████▉    | 221382/371472 [6:56:56<12:11:10,  3.42it/s]
 60%|█████▉    | 221383/371472 [6:56:56<11:45:39,  3.54it/s]
 60%|█████▉    | 221384/371472 [6:56:57<11:52:08,  3.51it/s]
 60%|█████▉    | 221385/371472 [6:56:57<11:45:21,  3.55it/s]
 60%|█████▉    | 221386/371472 [6:56:57<12:03:40,  3.46it/s]
 60%|█████▉    | 221387/371472 [6:56:58<12:15:50,  3.40it/s]
 60%|█████▉    | 221388/371472 [6:56:58<12:41:52,  3.28it/s]
 60%|█████▉    | 221389/371472 [6:56:58<12:42:11,  3.28it/s]
 60%|█████▉    | 221390/371472 [6:56:59<12:12:57,  3.41it/s]
 60%|█████▉    | 221391/371472 [6:56:59<12:32:34,  3.32it/s]
 60%|█████▉    | 221392/371472 [6:56:59<12:29:52,  3.34it/s]
 60%|█████▉    | 221393/371472 [6:56:59<12:11:23,  3.42it/s]
 60%|█████▉    | 221394/371472 [6:57:00<12:50:04,  3.25it/s]
 60%|█████▉    | 221395/371472 [6:57:00<12:49:19,  3.25it/s]
 60%|█████▉    | 221396/371472 [6:57:00<12:43:01,  3.28it/s]
 60%|█████▉    | 221397/371472 [6:57:01<12:21:06,  3.38it/s]
 60%|█████▉    | 221398/371472 [6:57:01<12:02:08,  3.46it/s]
 60%|█████▉    | 221399/371472 [6:57:01<11:38:51,  3.58it/s]
 60%|█████▉    | 221400/371472 [6:57:01<11:18:46,  3.68it/s]
                                                            
{'loss': 2.7045, 'learning_rate': 4.637893512034304e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221400/371472 [6:57:01<11:18:46,  3.68it/s]
 60%|█████▉    | 221401/371472 [6:57:02<11:27:22,  3.64it/s]
 60%|█████▉    | 221402/371472 [6:57:02<11:20:04,  3.68it/s]
 60%|█████▉    | 221403/371472 [6:57:02<13:20:39,  3.12it/s]
 60%|█████▉    | 221404/371472 [6:57:03<12:57:07,  3.22it/s]
 60%|█████▉    | 221405/371472 [6:57:03<13:19:05,  3.13it/s]
 60%|█████▉    | 221406/371472 [6:57:03<12:34:52,  3.31it/s]
 60%|█████▉    | 221407/371472 [6:57:04<12:21:25,  3.37it/s]
 60%|█████▉    | 221408/371472 [6:57:04<11:57:36,  3.49it/s]
 60%|█████▉    | 221409/371472 [6:57:04<11:49:47,  3.52it/s]
 60%|█████▉    | 221410/371472 [6:57:04<11:38:17,  3.58it/s]
 60%|█████▉    | 221411/371472 [6:57:05<11:43:33,  3.55it/s]
 60%|█████▉    | 221412/371472 [6:57:05<11:30:47,  3.62it/s]
 60%|█████▉    | 221413/371472 [6:57:05<11:58:14,  3.48it/s]
 60%|█████▉    | 221414/371472 [6:57:06<12:41:47,  3.28it/s]
 60%|█████▉    | 221415/371472 [6:57:06<12:35:20,  3.31it/s]
 60%|█████▉    | 221416/371472 [6:57:06<12:04:02,  3.45it/s]
 60%|█████▉    | 221417/371472 [6:57:06<11:45:45,  3.54it/s]
 60%|█████▉    | 221418/371472 [6:57:07<11:45:46,  3.54it/s]
 60%|█████▉    | 221419/371472 [6:57:07<11:39:32,  3.58it/s]
 60%|█████▉    | 221420/371472 [6:57:07<13:37:54,  3.06it/s]
                                                            
{'loss': 2.7692, 'learning_rate': 4.637408692279514e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221420/371472 [6:57:07<13:37:54,  3.06it/s]
 60%|█████▉    | 221421/371472 [6:57:08<13:09:08,  3.17it/s]
 60%|█████▉    | 221422/371472 [6:57:08<13:33:17,  3.07it/s]
 60%|█████▉    | 221423/371472 [6:57:08<12:59:49,  3.21it/s]
 60%|█████▉    | 221424/371472 [6:57:09<12:34:00,  3.32it/s]
 60%|█████▉    | 221425/371472 [6:57:09<12:56:22,  3.22it/s]
 60%|█████▉    | 221426/371472 [6:57:09<12:32:01,  3.33it/s]
 60%|█████▉    | 221427/371472 [6:57:10<13:10:01,  3.17it/s]
 60%|█████▉    | 221428/371472 [6:57:10<13:46:01,  3.03it/s]
 60%|█████▉    | 221429/371472 [6:57:10<13:01:12,  3.20it/s]
 60%|█████▉    | 221430/371472 [6:57:10<12:33:42,  3.32it/s]
 60%|█████▉    | 221431/371472 [6:57:11<12:21:29,  3.37it/s]
 60%|█████▉    | 221432/371472 [6:57:11<12:03:48,  3.45it/s]
 60%|█████▉    | 221433/371472 [6:57:11<12:04:44,  3.45it/s]
 60%|█████▉    | 221434/371472 [6:57:12<12:09:15,  3.43it/s]
 60%|█████▉    | 221435/371472 [6:57:12<12:30:47,  3.33it/s]
 60%|█████▉    | 221436/371472 [6:57:12<12:00:27,  3.47it/s]
 60%|█████▉    | 221437/371472 [6:57:13<11:56:10,  3.49it/s]
 60%|█████▉    | 221438/371472 [6:57:13<11:54:00,  3.50it/s]
 60%|█████▉    | 221439/371472 [6:57:13<12:08:52,  3.43it/s]
 60%|█████▉    | 221440/371472 [6:57:13<12:14:03,  3.41it/s]
                                                            
{'loss': 2.6278, 'learning_rate': 4.636923872524726e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221440/371472 [6:57:13<12:14:03,  3.41it/s]
 60%|█████▉    | 221441/371472 [6:57:14<12:16:41,  3.39it/s]
 60%|█████▉    | 221442/371472 [6:57:14<12:02:52,  3.46it/s]
 60%|█████▉    | 221443/371472 [6:57:14<11:50:17,  3.52it/s]
 60%|█████▉    | 221444/371472 [6:57:15<12:22:13,  3.37it/s]
 60%|█████▉    | 221445/371472 [6:57:15<13:22:04,  3.12it/s]
 60%|█████▉    | 221446/371472 [6:57:15<13:01:05,  3.20it/s]
 60%|█████▉    | 221447/371472 [6:57:16<12:56:47,  3.22it/s]
 60%|█████▉    | 221448/371472 [6:57:16<12:33:14,  3.32it/s]
 60%|█████▉    | 221449/371472 [6:57:16<12:28:13,  3.34it/s]
 60%|█████▉    | 221450/371472 [6:57:16<12:11:21,  3.42it/s]
 60%|█████▉    | 221451/371472 [6:57:17<12:02:45,  3.46it/s]
 60%|█████▉    | 221452/371472 [6:57:17<11:45:00,  3.55it/s]
 60%|█████▉    | 221453/371472 [6:57:17<12:18:01,  3.39it/s]
 60%|█████▉    | 221454/371472 [6:57:18<12:40:07,  3.29it/s]
 60%|█████▉    | 221455/371472 [6:57:18<12:13:43,  3.41it/s]
 60%|█████▉    | 221456/371472 [6:57:18<12:01:11,  3.47it/s]
 60%|█████▉    | 221457/371472 [6:57:18<11:59:31,  3.47it/s]
 60%|█████▉    | 221458/371472 [6:57:19<12:02:05,  3.46it/s]
 60%|█████▉    | 221459/371472 [6:57:19<11:57:47,  3.48it/s]
 60%|█████▉    | 221460/371472 [6:57:19<12:06:05,  3.44it/s]
                                                            
{'loss': 2.8553, 'learning_rate': 4.6364390527699366e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221460/371472 [6:57:19<12:06:05,  3.44it/s]
 60%|█████▉    | 221461/371472 [6:57:20<11:46:13,  3.54it/s]
 60%|█████▉    | 221462/371472 [6:57:20<12:17:59,  3.39it/s]
 60%|█████▉    | 221463/371472 [6:57:20<13:01:42,  3.20it/s]
 60%|█████▉    | 221464/371472 [6:57:21<13:44:50,  3.03it/s]
 60%|█████▉    | 221465/371472 [6:57:21<12:59:12,  3.21it/s]
 60%|█████▉    | 221466/371472 [6:57:21<12:34:03,  3.32it/s]
 60%|█████▉    | 221467/371472 [6:57:21<12:02:05,  3.46it/s]
 60%|█████▉    | 221468/371472 [6:57:22<11:56:57,  3.49it/s]
 60%|█████▉    | 221469/371472 [6:57:22<11:49:04,  3.53it/s]
 60%|█████▉    | 221470/371472 [6:57:22<13:03:22,  3.19it/s]
 60%|█████▉    | 221471/371472 [6:57:23<12:42:00,  3.28it/s]
 60%|█████▉    | 221472/371472 [6:57:23<12:26:40,  3.35it/s]
 60%|█████▉    | 221473/371472 [6:57:23<12:15:19,  3.40it/s]
 60%|█████▉    | 221474/371472 [6:57:23<11:52:29,  3.51it/s]
 60%|█████▉    | 221475/371472 [6:57:24<12:01:01,  3.47it/s]
 60%|█████▉    | 221476/371472 [6:57:24<12:13:04,  3.41it/s]
 60%|█████▉    | 221477/371472 [6:57:24<12:08:49,  3.43it/s]
 60%|█████▉    | 221478/371472 [6:57:25<12:16:30,  3.39it/s]
 60%|█████▉    | 221479/371472 [6:57:25<12:04:20,  3.45it/s]
 60%|█████▉    | 221480/371472 [6:57:25<12:48:19,  3.25it/s]
                                                            
{'loss': 2.7888, 'learning_rate': 4.635954233015148e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221480/371472 [6:57:25<12:48:19,  3.25it/s]
 60%|█████▉    | 221481/371472 [6:57:26<12:40:30,  3.29it/s]
 60%|█████▉    | 221482/371472 [6:57:26<12:30:58,  3.33it/s]
 60%|█████▉    | 221483/371472 [6:57:26<12:19:22,  3.38it/s]
 60%|█████▉    | 221484/371472 [6:57:26<12:14:11,  3.40it/s]
 60%|█████▉    | 221485/371472 [6:57:27<12:28:48,  3.34it/s]
 60%|█████▉    | 221486/371472 [6:57:27<12:07:10,  3.44it/s]
 60%|█████▉    | 221487/371472 [6:57:27<12:29:17,  3.34it/s]
 60%|█████▉    | 221488/371472 [6:57:28<12:37:29,  3.30it/s]
 60%|█████▉    | 221489/371472 [6:57:28<12:32:20,  3.32it/s]
 60%|█████▉    | 221490/371472 [6:57:28<12:09:12,  3.43it/s]
 60%|█████▉    | 221491/371472 [6:57:29<12:26:09,  3.35it/s]
 60%|█████▉    | 221492/371472 [6:57:29<13:09:05,  3.17it/s]
 60%|█████▉    | 221493/371472 [6:57:29<12:52:12,  3.24it/s]
 60%|█████▉    | 221494/371472 [6:57:29<12:35:55,  3.31it/s]
 60%|█████▉    | 221495/371472 [6:57:30<12:02:44,  3.46it/s]
 60%|█████▉    | 221496/371472 [6:57:30<11:39:06,  3.58it/s]
 60%|█████▉    | 221497/371472 [6:57:30<11:23:06,  3.66it/s]
 60%|█████▉    | 221498/371472 [6:57:31<11:17:04,  3.69it/s]
 60%|█████▉    | 221499/371472 [6:57:31<11:23:26,  3.66it/s]
 60%|█████▉    | 221500/371472 [6:57:31<11:27:39,  3.63it/s]
                                                            
{'loss': 2.6852, 'learning_rate': 4.6354694132603586e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221500/371472 [6:57:31<11:27:39,  3.63it/s]
 60%|█████▉    | 221501/371472 [6:57:31<11:32:34,  3.61it/s]
 60%|█████▉    | 221502/371472 [6:57:32<11:56:51,  3.49it/s]
 60%|█████▉    | 221503/371472 [6:57:32<11:49:05,  3.52it/s]
 60%|█████▉    | 221504/371472 [6:57:32<11:45:36,  3.54it/s]
 60%|█████▉    | 221505/371472 [6:57:33<12:09:39,  3.43it/s]
 60%|█████▉    | 221506/371472 [6:57:33<12:01:11,  3.47it/s]
 60%|█████▉    | 221507/371472 [6:57:33<11:53:04,  3.51it/s]
 60%|█████▉    | 221508/371472 [6:57:33<11:28:14,  3.63it/s]
 60%|█████▉    | 221509/371472 [6:57:34<11:48:00,  3.53it/s]
 60%|█████▉    | 221510/371472 [6:57:34<12:15:39,  3.40it/s]
 60%|█████▉    | 221511/371472 [6:57:34<12:31:19,  3.33it/s]
 60%|��████▉    | 221512/371472 [6:57:35<12:25:14,  3.35it/s]
 60%|█████▉    | 221513/371472 [6:57:35<12:19:10,  3.38it/s]
 60%|█████▉    | 221514/371472 [6:57:35<12:26:27,  3.35it/s]
 60%|█████▉    | 221515/371472 [6:57:35<12:39:49,  3.29it/s]
 60%|█████▉    | 221516/371472 [6:57:36<13:39:38,  3.05it/s]
 60%|█████▉    | 221517/371472 [6:57:36<13:27:47,  3.09it/s]
 60%|█████▉    | 221518/371472 [6:57:37<13:20:41,  3.12it/s]
 60%|█████▉    | 221519/371472 [6:57:37<12:57:09,  3.22it/s]
 60%|█████▉    | 221520/371472 [6:57:37<12:32:33,  3.32it/s]
                                                            
{'loss': 2.6897, 'learning_rate': 4.6349845935055704e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221520/371472 [6:57:37<12:32:33,  3.32it/s]
 60%|█████▉    | 221521/371472 [6:57:37<12:55:38,  3.22it/s]
 60%|█████▉    | 221522/371472 [6:57:38<12:24:11,  3.36it/s]
 60%|█████▉    | 221523/371472 [6:57:38<12:27:50,  3.34it/s]
 60%|█████▉    | 221524/371472 [6:57:38<12:56:57,  3.22it/s]
 60%|█████▉    | 221525/371472 [6:57:39<12:53:56,  3.23it/s]
 60%|█████▉    | 221526/371472 [6:57:39<12:55:48,  3.22it/s]
 60%|█████▉    | 221527/371472 [6:57:39<12:46:46,  3.26it/s]
 60%|█████▉    | 221528/371472 [6:57:40<13:44:36,  3.03it/s]
 60%|█████▉    | 221529/371472 [6:57:40<13:48:51,  3.02it/s]
 60%|█████▉    | 221530/371472 [6:57:40<13:10:16,  3.16it/s]
 60%|█████▉    | 221531/371472 [6:57:41<13:05:06,  3.18it/s]
 60%|█████▉    | 221532/371472 [6:57:41<12:57:18,  3.21it/s]
 60%|█████▉    | 221533/371472 [6:57:41<12:24:08,  3.36it/s]
 60%|█████▉    | 221534/371472 [6:57:41<13:11:29,  3.16it/s]
 60%|█████▉    | 221535/371472 [6:57:42<13:26:04,  3.10it/s]
 60%|█████▉    | 221536/371472 [6:57:42<12:48:43,  3.25it/s]
 60%|█████▉    | 221537/371472 [6:57:42<12:29:51,  3.33it/s]
 60%|█████▉    | 221538/371472 [6:57:43<12:25:11,  3.35it/s]
 60%|█████▉    | 221539/371472 [6:57:43<13:54:25,  2.99it/s]
 60%|█████▉    | 221540/371472 [6:57:43<13:15:13,  3.14it/s]
                                                            
{'loss': 2.5976, 'learning_rate': 4.634499773750781e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221540/371472 [6:57:43<13:15:13,  3.14it/s]
 60%|█████▉    | 221541/371472 [6:57:44<12:39:53,  3.29it/s]
 60%|█████▉    | 221542/371472 [6:57:44<12:21:41,  3.37it/s]
 60%|█████▉    | 221543/371472 [6:57:44<12:10:17,  3.42it/s]
 60%|█████▉    | 221544/371472 [6:57:44<11:52:43,  3.51it/s]
 60%|█████▉    | 221545/371472 [6:57:45<12:09:43,  3.42it/s]
 60%|█████▉    | 221546/371472 [6:57:45<12:15:31,  3.40it/s]
 60%|█████▉    | 221547/371472 [6:57:45<12:35:41,  3.31it/s]
 60%|█████▉    | 221548/371472 [6:57:46<12:24:57,  3.35it/s]
 60%|█████▉    | 221549/371472 [6:57:46<12:24:15,  3.36it/s]
 60%|█████▉    | 221550/371472 [6:57:46<12:03:19,  3.45it/s]
 60%|█████▉    | 221551/371472 [6:57:47<12:07:10,  3.44it/s]
 60%|█████▉    | 221552/371472 [6:57:47<12:04:13,  3.45it/s]
 60%|█████▉    | 221553/371472 [6:57:47<11:46:43,  3.54it/s]
 60%|█████▉    | 221554/371472 [6:57:47<12:08:10,  3.43it/s]
 60%|█████▉    | 221555/371472 [6:57:48<12:45:45,  3.26it/s]
 60%|█████▉    | 221556/371472 [6:57:48<12:45:04,  3.27it/s]
 60%|█████▉    | 221557/371472 [6:57:49<14:44:38,  2.82it/s]
 60%|█████▉    | 221558/371472 [6:57:49<13:48:08,  3.02it/s]
 60%|█████▉    | 221559/371472 [6:57:49<13:16:52,  3.14it/s]
 60%|█████▉    | 221560/371472 [6:57:49<12:47:05,  3.26it/s]
                                                            
{'loss': 2.9348, 'learning_rate': 4.6340149539959923e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221560/371472 [6:57:49<12:47:05,  3.26it/s]
 60%|█████▉    | 221561/371472 [6:57:50<13:24:47,  3.10it/s]
 60%|█████▉    | 221562/371472 [6:57:50<12:55:47,  3.22it/s]
 60%|█████▉    | 221563/371472 [6:57:50<13:34:57,  3.07it/s]
 60%|█████▉    | 221564/371472 [6:57:51<14:36:43,  2.85it/s]
 60%|█████▉    | 221565/371472 [6:57:51<13:37:33,  3.06it/s]
 60%|█████▉    | 221566/371472 [6:57:51<13:29:07,  3.09it/s]
 60%|█████▉    | 221567/371472 [6:57:52<13:09:29,  3.16it/s]
 60%|█████▉    | 221568/371472 [6:57:52<12:48:19,  3.25it/s]
 60%|█████▉    | 221569/371472 [6:57:52<12:43:31,  3.27it/s]
 60%|█████▉    | 221570/371472 [6:57:53<12:14:14,  3.40it/s]
 60%|█████▉    | 221571/371472 [6:57:53<12:03:27,  3.45it/s]
 60%|█████▉    | 221572/371472 [6:57:53<12:55:43,  3.22it/s]
 60%|█████▉    | 221573/371472 [6:57:53<13:20:09,  3.12it/s]
 60%|█████▉    | 221574/371472 [6:57:54<12:59:06,  3.21it/s]
 60%|█████▉    | 221575/371472 [6:57:54<12:42:01,  3.28it/s]
 60%|█████▉    | 221576/371472 [6:57:54<12:23:03,  3.36it/s]
 60%|█████▉    | 221577/371472 [6:57:55<12:22:48,  3.36it/s]
 60%|█████▉    | 221578/371472 [6:57:55<12:40:08,  3.29it/s]
 60%|█████▉    | 221579/371472 [6:57:55<12:28:44,  3.34it/s]
 60%|█████▉    | 221580/371472 [6:57:56<12:29:04,  3.34it/s]
                                                            
{'loss': 2.7513, 'learning_rate': 4.633530134241203e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221580/371472 [6:57:56<12:29:04,  3.34it/s]
 60%|█████▉    | 221581/371472 [6:57:56<12:47:38,  3.25it/s]
 60%|█████▉    | 221582/371472 [6:57:56<13:25:17,  3.10it/s]
 60%|█████▉    | 221583/371472 [6:57:57<13:41:42,  3.04it/s]
 60%|█████▉    | 221584/371472 [6:57:57<13:18:37,  3.13it/s]
 60%|█████▉    | 221585/371472 [6:57:57<13:53:21,  3.00it/s]
 60%|█████▉    | 221586/371472 [6:57:58<13:34:31,  3.07it/s]
 60%|█████▉    | 221587/371472 [6:57:58<13:15:52,  3.14it/s]
 60%|█████▉    | 221588/371472 [6:57:58<14:17:56,  2.91it/s]
 60%|█████▉    | 221589/371472 [6:57:59<13:31:36,  3.08it/s]
 60%|█████▉    | 221590/371472 [6:57:59<14:21:28,  2.90it/s]
 60%|█████▉    | 221591/371472 [6:57:59<14:43:24,  2.83it/s]
 60%|█████▉    | 221592/371472 [6:58:00<13:34:02,  3.07it/s]
 60%|█████▉    | 221593/371472 [6:58:00<13:22:38,  3.11it/s]
 60%|█████▉    | 221594/371472 [6:58:00<12:58:36,  3.21it/s]
 60%|█████▉    | 221595/371472 [6:58:00<12:36:18,  3.30it/s]
 60%|█████▉    | 221596/371472 [6:58:01<12:25:34,  3.35it/s]
 60%|█████▉    | 221597/371472 [6:58:01<12:50:18,  3.24it/s]
 60%|█████▉    | 221598/371472 [6:58:01<12:27:55,  3.34it/s]
 60%|█████▉    | 221599/371472 [6:58:02<12:11:32,  3.41it/s]
 60%|█████▉    | 221600/371472 [6:58:02<12:01:42,  3.46it/s]
                                                            
{'loss': 2.7227, 'learning_rate': 4.633045314486415e-07, 'epoch': 9.54}
+
 60%|█████▉    | 221600/371472 [6:58:02<12:01:42,  3.46it/s]
 60%|█████▉    | 221601/371472 [6:58:02<11:52:43,  3.50it/s]
 60%|█████▉    | 221602/371472 [6:58:02<11:51:05,  3.51it/s]
 60%|█████▉    | 221603/371472 [6:58:03<12:06:56,  3.44it/s]
 60%|█████▉    | 221604/371472 [6:58:03<12:14:36,  3.40it/s]
 60%|█████▉    | 221605/371472 [6:58:03<11:57:48,  3.48it/s]
 60%|█████▉    | 221606/371472 [6:58:04<12:01:49,  3.46it/s]
 60%|█████▉    | 221607/371472 [6:58:04<11:57:55,  3.48it/s]
 60%|█████▉    | 221608/371472 [6:58:04<11:45:11,  3.54it/s]
 60%|█████▉    | 221609/371472 [6:58:04<11:50:16,  3.52it/s]
 60%|█████▉    | 221610/371472 [6:58:05<12:22:25,  3.36it/s]
 60%|█████▉    | 221611/371472 [6:58:05<12:06:39,  3.44it/s]
 60%|█████▉    | 221612/371472 [6:58:05<12:15:42,  3.39it/s]
 60%|█████▉    | 221613/371472 [6:58:06<12:10:31,  3.42it/s]
 60%|█████▉    | 221614/371472 [6:58:06<12:31:25,  3.32it/s]
 60%|█████▉    | 221615/371472 [6:58:06<12:05:24,  3.44it/s]
 60%|█████▉    | 221616/371472 [6:58:07<12:32:46,  3.32it/s]
 60%|█████▉    | 221617/371472 [6:58:07<12:03:36,  3.45it/s]
 60%|█████▉    | 221618/371472 [6:58:07<12:15:42,  3.39it/s]
 60%|█████▉    | 221619/371472 [6:58:07<12:20:10,  3.37it/s]
 60%|█████▉    | 221620/371472 [6:58:08<12:14:04,  3.40it/s]
                                                            
{'loss': 2.81, 'learning_rate': 4.632560494731625e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221620/371472 [6:58:08<12:14:04,  3.40it/s]
 60%|█████▉    | 221621/371472 [6:58:08<11:54:37,  3.49it/s]
 60%|█████▉    | 221622/371472 [6:58:08<12:32:34,  3.32it/s]
 60%|█████▉    | 221623/371472 [6:58:09<12:09:13,  3.42it/s]
 60%|█████▉    | 221624/371472 [6:58:09<12:31:45,  3.32it/s]
 60%|█████▉    | 221625/371472 [6:58:09<12:16:06,  3.39it/s]
 60%|█████▉    | 221626/371472 [6:58:09<11:55:37,  3.49it/s]
 60%|█████▉    | 221627/371472 [6:58:10<11:51:51,  3.51it/s]
 60%|█████▉    | 221628/371472 [6:58:10<11:52:29,  3.51it/s]
 60%|█████▉    | 221629/371472 [6:58:10<11:34:48,  3.59it/s]
 60%|█████▉    | 221630/371472 [6:58:11<11:30:44,  3.62it/s]
 60%|█████▉    | 221631/371472 [6:58:11<11:10:06,  3.73it/s]
 60%|█████▉    | 221632/371472 [6:58:11<11:14:59,  3.70it/s]
 60%|█████▉    | 221633/371472 [6:58:11<11:21:47,  3.66it/s]
 60%|█████▉    | 221634/371472 [6:58:12<11:37:39,  3.58it/s]
 60%|█████▉    | 221635/371472 [6:58:12<12:13:01,  3.41it/s]
 60%|█████▉    | 221636/371472 [6:58:12<12:01:34,  3.46it/s]
 60%|█████▉    | 221637/371472 [6:58:13<12:00:05,  3.47it/s]
 60%|█████▉    | 221638/371472 [6:58:13<11:36:45,  3.58it/s]
 60%|█████▉    | 221639/371472 [6:58:13<11:34:37,  3.60it/s]
 60%|█████▉    | 221640/371472 [6:58:13<11:35:15,  3.59it/s]
                                                            
{'loss': 2.8312, 'learning_rate': 4.6320756749768357e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221640/371472 [6:58:13<11:35:15,  3.59it/s]
 60%|█████▉    | 221641/371472 [6:58:14<11:34:44,  3.59it/s]
 60%|█████▉    | 221642/371472 [6:58:14<12:05:17,  3.44it/s]
 60%|█████▉    | 221643/371472 [6:58:14<11:58:31,  3.48it/s]
 60%|█████▉    | 221644/371472 [6:58:15<11:52:55,  3.50it/s]
 60%|█████▉    | 221645/371472 [6:58:15<11:53:30,  3.50it/s]
 60%|█████▉    | 221646/371472 [6:58:15<12:03:34,  3.45it/s]
 60%|█████▉    | 221647/371472 [6:58:15<12:08:58,  3.43it/s]
 60%|█████▉    | 221648/371472 [6:58:16<11:57:10,  3.48it/s]
 60%|█████▉    | 221649/371472 [6:58:16<12:00:47,  3.46it/s]
 60%|█████▉    | 221650/371472 [6:58:16<11:48:29,  3.52it/s]
 60%|█████▉    | 221651/371472 [6:58:17<12:06:30,  3.44it/s]
 60%|█████▉    | 221652/371472 [6:58:17<12:06:26,  3.44it/s]
 60%|█████▉    | 221653/371472 [6:58:17<13:25:27,  3.10it/s]
 60%|█████▉    | 221654/371472 [6:58:18<13:40:01,  3.04it/s]
 60%|█████▉    | 221655/371472 [6:58:18<13:02:22,  3.19it/s]
 60%|█████▉    | 221656/371472 [6:58:18<12:39:34,  3.29it/s]
 60%|█████▉    | 221657/371472 [6:58:18<12:12:04,  3.41it/s]
 60%|█████▉    | 221658/371472 [6:58:19<12:25:33,  3.35it/s]
 60%|█████▉    | 221659/371472 [6:58:19<11:55:30,  3.49it/s]
 60%|█████▉    | 221660/371472 [6:58:19<11:43:27,  3.55it/s]
                                                            
{'loss': 2.9392, 'learning_rate': 4.6315908552220475e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221660/371472 [6:58:19<11:43:27,  3.55it/s]
 60%|█████▉    | 221661/371472 [6:58:20<12:12:21,  3.41it/s]
 60%|█████▉    | 221662/371472 [6:58:20<11:56:33,  3.48it/s]
 60%|█████▉    | 221663/371472 [6:58:20<12:02:34,  3.46it/s]
 60%|█████▉    | 221664/371472 [6:58:20<12:29:45,  3.33it/s]
 60%|█████▉    | 221665/371472 [6:58:21<12:10:01,  3.42it/s]
 60%|█████▉    | 221666/371472 [6:58:21<12:34:08,  3.31it/s]
 60%|█████▉    | 221667/371472 [6:58:21<12:15:29,  3.39it/s]
 60%|█████▉    | 221668/371472 [6:58:22<12:25:26,  3.35it/s]
 60%|█████▉    | 221669/371472 [6:58:22<12:09:34,  3.42it/s]
 60%|█████▉    | 221670/371472 [6:58:22<12:04:12,  3.45it/s]
 60%|█████▉    | 221671/371472 [6:58:23<12:04:30,  3.45it/s]
 60%|█████▉    | 221672/371472 [6:58:23<12:37:24,  3.30it/s]
 60%|█████▉    | 221673/371472 [6:58:23<13:17:23,  3.13it/s]
 60%|█████▉    | 221674/371472 [6:58:24<13:57:44,  2.98it/s]
 60%|█████▉    | 221675/371472 [6:58:24<13:29:18,  3.08it/s]
 60%|█████▉    | 221676/371472 [6:58:24<13:14:54,  3.14it/s]
 60%|█████▉    | 221677/371472 [6:58:24<12:41:31,  3.28it/s]
 60%|█████▉    | 221678/371472 [6:58:25<12:35:36,  3.30it/s]
 60%|█████▉    | 221679/371472 [6:58:25<12:27:25,  3.34it/s]
 60%|█████▉    | 221680/371472 [6:58:25<12:09:53,  3.42it/s]
                                                            
{'loss': 2.868, 'learning_rate': 4.6311060354672577e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221680/371472 [6:58:25<12:09:53,  3.42it/s]
 60%|█████▉    | 221681/371472 [6:58:26<12:19:00,  3.38it/s]
 60%|█████▉    | 221682/371472 [6:58:26<12:11:28,  3.41it/s]
 60%|█████▉    | 221683/371472 [6:58:26<12:54:19,  3.22it/s]
 60%|█████▉    | 221684/371472 [6:58:27<13:41:01,  3.04it/s]
 60%|█████▉    | 221685/371472 [6:58:27<12:59:58,  3.20it/s]
 60%|█████▉    | 221686/371472 [6:58:27<12:40:05,  3.28it/s]
 60%|█████▉    | 221687/371472 [6:58:28<12:37:01,  3.30it/s]
 60%|█████▉    | 221688/371472 [6:58:28<14:02:19,  2.96it/s]
 60%|█████▉    | 221689/371472 [6:58:28<13:20:20,  3.12it/s]
 60%|█████▉    | 221690/371472 [6:58:29<12:59:54,  3.20it/s]
 60%|█████▉    | 221691/371472 [6:58:29<12:39:15,  3.29it/s]
 60%|█████▉    | 221692/371472 [6:58:29<12:38:55,  3.29it/s]
 60%|█████▉    | 221693/371472 [6:58:29<12:16:58,  3.39it/s]
 60%|█████▉    | 221694/371472 [6:58:30<12:05:09,  3.44it/s]
 60%|█████▉    | 221695/371472 [6:58:30<11:37:31,  3.58it/s]
 60%|█████▉    | 221696/371472 [6:58:30<11:55:52,  3.49it/s]
 60%|█████▉    | 221697/371472 [6:58:30<11:43:16,  3.55it/s]
 60%|█████▉    | 221698/371472 [6:58:31<11:40:09,  3.57it/s]
 60%|█████▉    | 221699/371472 [6:58:31<11:52:52,  3.50it/s]
 60%|█████▉    | 221700/371472 [6:58:31<12:34:22,  3.31it/s]
                                                            
{'loss': 2.7795, 'learning_rate': 4.6306212157124694e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221700/371472 [6:58:31<12:34:22,  3.31it/s]
 60%|█████▉    | 221701/371472 [6:58:32<12:39:59,  3.28it/s]
 60%|█████▉    | 221702/371472 [6:58:32<12:42:53,  3.27it/s]
 60%|█████▉    | 221703/371472 [6:58:32<12:16:44,  3.39it/s]
 60%|█████▉    | 221704/371472 [6:58:33<12:31:52,  3.32it/s]
 60%|█████▉    | 221705/371472 [6:58:33<12:54:32,  3.22it/s]
 60%|█████▉    | 221706/371472 [6:58:33<12:18:09,  3.38it/s]
 60%|█████▉    | 221707/371472 [6:58:33<12:05:02,  3.44it/s]
 60%|█████▉    | 221708/371472 [6:58:34<11:52:25,  3.50it/s]
 60%|█████▉    | 221709/371472 [6:58:34<12:22:00,  3.36it/s]
 60%|█████▉    | 221710/371472 [6:58:34<12:15:38,  3.39it/s]
 60%|█████▉    | 221711/371472 [6:58:35<12:14:24,  3.40it/s]
 60%|█████▉    | 221712/371472 [6:58:35<12:03:00,  3.45it/s]
 60%|█████▉    | 221713/371472 [6:58:35<12:02:07,  3.46it/s]
 60%|█████▉    | 221714/371472 [6:58:36<13:24:17,  3.10it/s]
 60%|█████▉    | 221715/371472 [6:58:36<12:57:27,  3.21it/s]
 60%|█████▉    | 221716/371472 [6:58:36<12:41:55,  3.28it/s]
 60%|█████▉    | 221717/371472 [6:58:37<12:47:34,  3.25it/s]
 60%|█████▉    | 221718/371472 [6:58:37<12:34:32,  3.31it/s]
 60%|█████▉    | 221719/371472 [6:58:37<12:34:59,  3.31it/s]
 60%|█████▉    | 221720/371472 [6:58:37<13:07:51,  3.17it/s]
                                                            
{'loss': 2.7455, 'learning_rate': 4.63013639595768e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221720/371472 [6:58:37<13:07:51,  3.17it/s]
 60%|█████▉    | 221721/371472 [6:58:38<12:46:46,  3.26it/s]
 60%|█████▉    | 221722/371472 [6:58:38<13:06:18,  3.17it/s]
 60%|█████▉    | 221723/371472 [6:58:38<12:48:36,  3.25it/s]
 60%|█████▉    | 221724/371472 [6:58:39<12:52:29,  3.23it/s]
 60%|█████▉    | 221725/371472 [6:58:39<12:27:33,  3.34it/s]
 60%|█████▉    | 221726/371472 [6:58:39<12:05:25,  3.44it/s]
 60%|█████▉    | 221727/371472 [6:58:40<12:08:17,  3.43it/s]
 60%|█████▉    | 221728/371472 [6:58:40<11:56:39,  3.48it/s]
 60%|█████▉    | 221729/371472 [6:58:40<11:46:59,  3.53it/s]
 60%|█████▉    | 221730/371472 [6:58:40<12:23:38,  3.36it/s]
 60%|█████▉    | 221731/371472 [6:58:41<12:23:30,  3.36it/s]
 60%|█████▉    | 221732/371472 [6:58:41<12:25:22,  3.35it/s]
 60%|█████▉    | 221733/371472 [6:58:41<12:05:12,  3.44it/s]
 60%|█████▉    | 221734/371472 [6:58:42<11:57:53,  3.48it/s]
 60%|█████▉    | 221735/371472 [6:58:42<13:00:23,  3.20it/s]
 60%|█████▉    | 221736/371472 [6:58:42<13:12:13,  3.15it/s]
 60%|█████▉    | 221737/371472 [6:58:43<12:32:38,  3.32it/s]
 60%|█████▉    | 221738/371472 [6:58:43<12:06:48,  3.43it/s]
 60%|█████▉    | 221739/371472 [6:58:43<12:01:15,  3.46it/s]
 60%|█████▉    | 221740/371472 [6:58:43<12:25:17,  3.35it/s]
                                                            
{'loss': 2.6211, 'learning_rate': 4.6296515762028914e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221740/371472 [6:58:43<12:25:17,  3.35it/s]
 60%|█████▉    | 221741/371472 [6:58:44<12:15:46,  3.39it/s]
 60%|█████▉    | 221742/371472 [6:58:44<12:14:41,  3.40it/s]
 60%|█████▉    | 221743/371472 [6:58:44<12:11:14,  3.41it/s]
 60%|█████▉    | 221744/371472 [6:58:45<12:16:46,  3.39it/s]
 60%|█████▉    | 221745/371472 [6:58:45<12:08:54,  3.42it/s]
 60%|█████▉    | 221746/371472 [6:58:45<12:25:29,  3.35it/s]
 60%|█████▉    | 221747/371472 [6:58:45<12:05:38,  3.44it/s]
 60%|█████▉    | 221748/371472 [6:58:46<11:45:12,  3.54it/s]
 60%|█████▉    | 221749/371472 [6:58:46<11:48:43,  3.52it/s]
 60%|█████▉    | 221750/371472 [6:58:46<11:40:30,  3.56it/s]
 60%|█████▉    | 221751/371472 [6:58:47<11:34:55,  3.59it/s]
 60%|█████▉    | 221752/371472 [6:58:47<11:45:31,  3.54it/s]
 60%|█████▉    | 221753/371472 [6:58:47<13:11:18,  3.15it/s]
 60%|█████▉    | 221754/371472 [6:58:48<14:25:17,  2.88it/s]
 60%|█████▉    | 221755/371472 [6:58:48<13:53:01,  3.00it/s]
 60%|█████▉    | 221756/371472 [6:58:48<13:06:51,  3.17it/s]
 60%|█████▉    | 221757/371472 [6:58:48<12:55:07,  3.22it/s]
 60%|█████▉    | 221758/371472 [6:58:49<12:37:06,  3.30it/s]
 60%|█████▉    | 221759/371472 [6:58:49<12:16:52,  3.39it/s]
 60%|█████▉    | 221760/371472 [6:58:49<12:06:14,  3.44it/s]
                                                            
{'loss': 2.6358, 'learning_rate': 4.6291667564481016e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221760/371472 [6:58:49<12:06:14,  3.44it/s]
 60%|█████▉    | 221761/371472 [6:58:50<12:28:14,  3.33it/s]
 60%|█████▉    | 221762/371472 [6:58:50<12:19:20,  3.37it/s]
 60%|█████▉    | 221763/371472 [6:58:50<12:16:31,  3.39it/s]
 60%|█████▉    | 221764/371472 [6:58:51<12:37:30,  3.29it/s]
 60%|█████▉    | 221765/371472 [6:58:51<12:32:50,  3.31it/s]
 60%|█████▉    | 221766/371472 [6:58:51<13:07:27,  3.17it/s]
 60%|█████▉    | 221767/371472 [6:58:51<12:44:00,  3.27it/s]
 60%|█████▉    | 221768/371472 [6:58:52<12:19:37,  3.37it/s]
 60%|█████▉    | 221769/371472 [6:58:52<12:24:20,  3.35it/s]
 60%|█████▉    | 221770/371472 [6:58:52<12:14:52,  3.40it/s]
 60%|█████▉    | 221771/371472 [6:58:53<12:20:31,  3.37it/s]
 60%|█████▉    | 221772/371472 [6:58:53<12:36:28,  3.30it/s]
 60%|█████▉    | 221773/371472 [6:58:53<12:11:24,  3.41it/s]
 60%|█████▉    | 221774/371472 [6:58:54<12:48:18,  3.25it/s]
 60%|█████▉    | 221775/371472 [6:58:54<12:47:09,  3.25it/s]
 60%|█████▉    | 221776/371472 [6:58:54<13:08:05,  3.17it/s]
 60%|█████▉    | 221777/371472 [6:58:55<13:08:10,  3.17it/s]
 60%|█████▉    | 221778/371472 [6:58:55<13:08:01,  3.17it/s]
 60%|█████▉    | 221779/371472 [6:58:55<13:01:09,  3.19it/s]
 60%|█████▉    | 221780/371472 [6:58:55<12:31:26,  3.32it/s]
                                                            
{'loss': 2.6719, 'learning_rate': 4.628681936693314e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221780/371472 [6:58:55<12:31:26,  3.32it/s]
 60%|█████▉    | 221781/371472 [6:58:56<13:01:15,  3.19it/s]
 60%|█████▉    | 221782/371472 [6:58:56<12:46:09,  3.26it/s]
 60%|█████▉    | 221783/371472 [6:58:56<12:40:58,  3.28it/s]
 60%|█████▉    | 221784/371472 [6:58:57<12:36:28,  3.30it/s]
 60%|█████▉    | 221785/371472 [6:58:57<12:20:59,  3.37it/s]
 60%|█████▉    | 221786/371472 [6:58:57<12:02:35,  3.45it/s]
 60%|█████▉    | 221787/371472 [6:58:58<12:16:43,  3.39it/s]
 60%|█████▉    | 221788/371472 [6:58:58<12:12:24,  3.41it/s]
 60%|█████▉    | 221789/371472 [6:58:58<12:20:42,  3.37it/s]
 60%|█████▉    | 221790/371472 [6:58:58<12:32:01,  3.32it/s]
 60%|█████▉    | 221791/371472 [6:58:59<12:25:36,  3.35it/s]
 60%|█████▉    | 221792/371472 [6:58:59<12:19:23,  3.37it/s]
 60%|█████▉    | 221793/371472 [6:58:59<12:02:12,  3.45it/s]
 60%|█████▉    | 221794/371472 [6:59:00<11:39:49,  3.56it/s]
 60%|█████▉    | 221795/371472 [6:59:00<11:36:34,  3.58it/s]
 60%|█████▉    | 221796/371472 [6:59:00<12:22:24,  3.36it/s]
 60%|█████▉    | 221797/371472 [6:59:00<12:15:53,  3.39it/s]
 60%|█████▉    | 221798/371472 [6:59:01<12:33:17,  3.31it/s]
 60%|█████▉    | 221799/371472 [6:59:01<12:26:24,  3.34it/s]
 60%|█████▉    | 221800/371472 [6:59:01<12:29:28,  3.33it/s]
                                                            
{'loss': 2.6254, 'learning_rate': 4.628197116938524e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221800/371472 [6:59:01<12:29:28,  3.33it/s]
 60%|█████▉    | 221801/371472 [6:59:02<13:22:12,  3.11it/s]
 60%|█████▉    | 221802/371472 [6:59:02<13:12:34,  3.15it/s]
 60%|█████▉    | 221803/371472 [6:59:02<12:47:32,  3.25it/s]
 60%|█████▉    | 221804/371472 [6:59:03<12:36:15,  3.30it/s]
 60%|█████▉    | 221805/371472 [6:59:03<12:28:15,  3.33it/s]
 60%|█████▉    | 221806/371472 [6:59:03<12:06:47,  3.43it/s]
 60%|█████▉    | 221807/371472 [6:59:04<12:55:05,  3.22it/s]
 60%|█████▉    | 221808/371472 [6:59:04<12:24:34,  3.35it/s]
 60%|█████▉    | 221809/371472 [6:59:04<12:23:35,  3.35it/s]
 60%|█████▉    | 221810/371472 [6:59:04<12:11:28,  3.41it/s]
 60%|█████▉    | 221811/371472 [6:59:05<11:56:06,  3.48it/s]
 60%|█████▉    | 221812/371472 [6:59:05<12:15:31,  3.39it/s]
 60%|█████▉    | 221813/371472 [6:59:05<12:32:12,  3.32it/s]
 60%|█████▉    | 221814/371472 [6:59:06<12:36:39,  3.30it/s]
 60%|█████▉    | 221815/371472 [6:59:06<12:59:45,  3.20it/s]
 60%|█████▉    | 221816/371472 [6:59:07<16:34:29,  2.51it/s]
 60%|█████▉    | 221817/371472 [6:59:07<15:25:01,  2.70it/s]
 60%|█████▉    | 221818/371472 [6:59:07<14:25:15,  2.88it/s]
 60%|█████▉    | 221819/371472 [6:59:07<14:03:51,  2.96it/s]
 60%|█████▉    | 221820/371472 [6:59:08<13:20:14,  3.12it/s]
                                                            
{'loss': 2.7804, 'learning_rate': 4.627712297183736e-07, 'epoch': 9.55}
+
 60%|█████▉    | 221820/371472 [6:59:08<13:20:14,  3.12it/s]
 60%|█████▉    | 221821/371472 [6:59:08<13:50:27,  3.00it/s]
 60%|█████▉    | 221822/371472 [6:59:08<12:59:33,  3.20it/s]
 60%|█████▉    | 221823/371472 [6:59:09<12:47:16,  3.25it/s]
 60%|█████▉    | 221824/371472 [6:59:09<12:36:34,  3.30it/s]
 60%|█████▉    | 221825/371472 [6:59:09<12:52:02,  3.23it/s]
 60%|█████▉    | 221826/371472 [6:59:10<12:32:41,  3.31it/s]
 60%|█████▉    | 221827/371472 [6:59:10<13:05:19,  3.18it/s]
 60%|█████▉    | 221828/371472 [6:59:10<12:48:25,  3.25it/s]
 60%|█████▉    | 221829/371472 [6:59:11<13:02:04,  3.19it/s]
 60%|█████▉    | 221830/371472 [6:59:11<13:38:14,  3.05it/s]
 60%|█████▉    | 221831/371472 [6:59:11<12:47:08,  3.25it/s]
 60%|█████▉    | 221832/371472 [6:59:11<12:30:49,  3.32it/s]
 60%|█████▉    | 221833/371472 [6:59:12<12:47:01,  3.25it/s]
 60%|█████▉    | 221834/371472 [6:59:12<14:08:42,  2.94it/s]
 60%|█████▉    | 221835/371472 [6:59:12<13:48:50,  3.01it/s]
 60%|█████▉    | 221836/371472 [6:59:13<13:13:20,  3.14it/s]
 60%|█████▉    | 221837/371472 [6:59:13<12:44:05,  3.26it/s]
 60%|█████▉    | 221838/371472 [6:59:13<12:42:31,  3.27it/s]
 60%|█████▉    | 221839/371472 [6:59:14<12:45:19,  3.26it/s]
 60%|█████▉    | 221840/371472 [6:59:14<12:42:15,  3.27it/s]
                                                            
{'loss': 2.6968, 'learning_rate': 4.6272274774289466e-07, 'epoch': 9.56}
+
 60%|█████▉    | 221840/371472 [6:59:14<12:42:15,  3.27it/s]
 60%|█████▉    | 221841/371472 [6:59:14<12:36:19,  3.30it/s]
 60%|█████▉    | 221842/371472 [6:59:15<12:28:31,  3.33it/s]
 60%|█████▉    | 221843/371472 [6:59:15<12:30:32,  3.32it/s]
 60%|█████▉    | 221844/371472 [6:59:15<12:32:44,  3.31it/s]
 60%|█████▉    | 221845/371472 [6:59:15<12:33:18,  3.31it/s]
 60%|█████▉    | 221846/371472 [6:59:16<12:37:29,  3.29it/s]
 60%|█████▉    | 221847/371472 [6:59:16<12:25:16,  3.35it/s]
 60%|█████▉    | 221848/371472 [6:59:16<12:17:40,  3.38it/s]
 60%|█████▉    | 221849/371472 [6:59:17<12:20:39,  3.37it/s]
 60%|█████▉    | 221850/371472 [6:59:17<12:14:24,  3.40it/s]
 60%|█████▉    | 221851/371472 [6:59:17<12:07:53,  3.43it/s]
 60%|█████▉    | 221852/371472 [6:59:18<12:17:54,  3.38it/s]
 60%|█████▉    | 221853/371472 [6:59:18<12:07:37,  3.43it/s]
 60%|█████▉    | 221854/371472 [6:59:18<12:03:37,  3.45it/s]
 60%|█████▉    | 221855/371472 [6:59:18<12:59:31,  3.20it/s]
 60%|█████▉    | 221856/371472 [6:59:19<12:26:24,  3.34it/s]
 60%|█████▉    | 221857/371472 [6:59:19<12:48:59,  3.24it/s]
 60%|█████▉    | 221858/371472 [6:59:19<12:39:50,  3.28it/s]
 60%|█████▉    | 221859/371472 [6:59:20<12:18:59,  3.37it/s]
 60%|█████▉    | 221860/371472 [6:59:20<12:34:46,  3.30it/s]
                                                            
{'loss': 2.7047, 'learning_rate': 4.626742657674158e-07, 'epoch': 9.56}
+
 60%|█████▉    | 221860/371472 [6:59:20<12:34:46,  3.30it/s]
 60%|█████▉    | 221861/371472 [6:59:20<12:43:50,  3.26it/s]
 60%|█████▉    | 221862/371472 [6:59:21<12:44:52,  3.26it/s]
 60%|█████▉    | 221863/371472 [6:59:21<12:24:19,  3.35it/s]
 60%|█████▉    | 221864/371472 [6:59:21<12:14:20,  3.40it/s]
 60%|█████▉    | 221865/371472 [6:59:21<12:22:14,  3.36it/s]
 60%|█████▉    | 221866/371472 [6:59:22<12:13:41,  3.40it/s]
 60%|█████▉    | 221867/371472 [6:59:22<12:52:52,  3.23it/s]
 60%|█████▉    | 221868/371472 [6:59:22<12:49:29,  3.24it/s]
 60%|█████▉    | 221869/371472 [6:59:23<12:21:28,  3.36it/s]
 60%|█████▉    | 221870/371472 [6:59:23<12:53:54,  3.22it/s]
 60%|█████▉    | 221871/371472 [6:59:23<12:26:27,  3.34it/s]
 60%|█████▉    | 221872/371472 [6:59:24<12:55:19,  3.22it/s]
 60%|█████▉    | 221873/371472 [6:59:24<12:23:07,  3.36it/s]
 60%|█████▉    | 221874/371472 [6:59:24<12:45:51,  3.26it/s]
 60%|█████▉    | 221875/371472 [6:59:24<12:05:18,  3.44it/s]
 60%|█████▉    | 221876/371472 [6:59:25<12:13:15,  3.40it/s]
 60%|█████▉    | 221877/371472 [6:59:25<12:03:03,  3.45it/s]
 60%|█████▉    | 221878/371472 [6:59:25<12:25:07,  3.35it/s]
 60%|█████▉    | 221879/371472 [6:59:26<12:14:15,  3.40it/s]
 60%|█████▉    | 221880/371472 [6:59:26<12:48:34,  3.24it/s]
                                                            
{'loss': 2.8242, 'learning_rate': 4.6262578379193685e-07, 'epoch': 9.56}
+
 60%|█████▉    | 221880/371472 [6:59:26<12:48:34,  3.24it/s]
 60%|█████▉    | 221881/371472 [6:59:26<12:46:44,  3.25it/s]
 60%|█████▉    | 221882/371472 [6:59:27<12:23:29,  3.35it/s]
 60%|█████▉    | 221883/371472 [6:59:27<12:05:38,  3.44it/s]
 60%|█████▉    | 221884/371472 [6:59:27<12:14:31,  3.39it/s]
 60%|█████▉    | 221885/371472 [6:59:27<12:09:46,  3.42it/s]
 60%|█████▉    | 221886/371472 [6:59:28<11:51:45,  3.50it/s]
 60%|█████▉    | 221887/371472 [6:59:28<11:59:12,  3.47it/s]
 60%|█████▉    | 221888/371472 [6:59:28<11:58:17,  3.47it/s]
 60%|█████▉    | 221889/371472 [6:59:29<12:14:20,  3.39it/s]
 60%|█████▉    | 221890/371472 [6:59:29<12:47:48,  3.25it/s]
 60%|█████▉    | 221891/371472 [6:59:29<12:43:02,  3.27it/s]
 60%|█████▉    | 221892/371472 [6:59:30<12:28:03,  3.33it/s]
 60%|█████▉    | 221893/371472 [6:59:30<12:22:06,  3.36it/s]
 60%|█████▉    | 221894/371472 [6:59:30<12:40:01,  3.28it/s]
 60%|█████▉    | 221895/371472 [6:59:30<12:43:58,  3.26it/s]
 60%|█████▉    | 221896/371472 [6:59:31<13:07:16,  3.17it/s]
 60%|█████▉    | 221897/371472 [6:59:31<12:54:51,  3.22it/s]
 60%|█████▉    | 221898/371472 [6:59:31<13:00:05,  3.20it/s]
 60%|█████▉    | 221899/371472 [6:59:32<12:40:07,  3.28it/s]
 60%|█████▉    | 221900/371472 [6:59:32<12:25:43,  3.34it/s]
                                                            
{'loss': 2.7317, 'learning_rate': 4.6257730181645803e-07, 'epoch': 9.56}
+
 60%|█████▉    | 221900/371472 [6:59:32<12:25:43,  3.34it/s]
 60%|█████▉    | 221901/371472 [6:59:32<13:46:27,  3.02it/s]
 60%|█████▉    | 221902/371472 [6:59:33<13:19:01,  3.12it/s]
 60%|█████▉    | 221903/371472 [6:59:33<12:50:00,  3.24it/s]
 60%|█████▉    | 221904/371472 [6:59:33<12:35:20,  3.30it/s]
 60%|█████▉    | 221905/371472 [6:59:34<12:16:10,  3.39it/s]
 60%|█████▉    | 221906/371472 [6:59:34<11:56:39,  3.48it/s]
 60%|█████▉    | 221907/371472 [6:59:34<12:08:16,  3.42it/s]
 60%|█████▉    | 221908/371472 [6:59:34<11:58:07,  3.47it/s]
 60%|█████▉    | 221909/371472 [6:59:35<12:07:37,  3.43it/s]
 60%|█████▉    | 221910/371472 [6:59:35<12:19:01,  3.37it/s]
 60%|█████▉    | 221911/371472 [6:59:35<12:11:56,  3.41it/s]
 60%|█████▉    | 221912/371472 [6:59:36<12:28:32,  3.33it/s]
 60%|█████▉    | 221913/371472 [6:59:36<12:16:22,  3.39it/s]
 60%|█████▉    | 221914/371472 [6:59:36<12:07:09,  3.43it/s]
 60%|█████▉    | 221915/371472 [6:59:36<12:08:55,  3.42it/s]
 60%|█████▉    | 221916/371472 [6:59:37<12:28:18,  3.33it/s]
 60%|█████▉    | 221917/371472 [6:59:37<12:18:16,  3.38it/s]
 60%|█████▉    | 221918/371472 [6:59:37<12:12:36,  3.40it/s]
 60%|█████▉    | 221919/371472 [6:59:38<12:22:06,  3.36it/s]
 60%|█████▉    | 221920/371472 [6:59:38<12:18:32,  3.37it/s]
                                                            
{'loss': 2.7427, 'learning_rate': 4.625288198409791e-07, 'epoch': 9.56}
+
 60%|█████▉    | 221920/371472 [6:59:38<12:18:32,  3.37it/s]
 60%|█████▉    | 221921/371472 [6:59:38<12:32:06,  3.31it/s]
 60%|█████▉    | 221922/371472 [6:59:39<12:25:44,  3.34it/s]
 60%|█████▉    | 221923/371472 [6:59:39<12:44:11,  3.26it/s]
 60%|█████▉    | 221924/371472 [6:59:39<12:35:54,  3.30it/s]
 60%|█████▉    | 221925/371472 [6:59:40<13:11:52,  3.15it/s]
 60%|█████▉    | 221926/371472 [6:59:40<12:48:36,  3.24it/s]
 60%|█████▉    | 221927/371472 [6:59:40<13:41:43,  3.03it/s]
 60%|█████▉    | 221928/371472 [6:59:40<12:52:12,  3.23it/s]
 60%|█████▉    | 221929/371472 [6:59:41<12:34:21,  3.30it/s]
 60%|█████▉    | 221930/371472 [6:59:41<12:13:34,  3.40it/s]
 60%|█████▉    | 221931/371472 [6:59:41<12:10:34,  3.41it/s]
 60%|█████▉    | 221932/371472 [6:59:42<11:57:10,  3.48it/s]
 60%|█████▉    | 221933/371472 [6:59:42<12:07:21,  3.43it/s]
 60%|█████▉    | 221934/371472 [6:59:42<12:11:09,  3.41it/s]
 60%|█████▉    | 221935/371472 [6:59:42<12:11:11,  3.41it/s]
 60%|█████▉    | 221936/371472 [6:59:43<12:37:46,  3.29it/s]
 60%|█████▉    | 221937/371472 [6:59:43<12:36:43,  3.29it/s]
 60%|█████▉    | 221938/371472 [6:59:43<13:12:28,  3.14it/s]
 60%|█████▉    | 221939/371472 [6:59:44<13:26:45,  3.09it/s]
 60%|█████▉    | 221940/371472 [6:59:44<13:06:22,  3.17it/s]
                                                            
{'loss': 2.7459, 'learning_rate': 4.624803378655002e-07, 'epoch': 9.56}
+
 60%|█████▉    | 221940/371472 [6:59:44<13:06:22,  3.17it/s]
 60%|█████▉    | 221941/371472 [6:59:44<12:28:36,  3.33it/s]
 60%|█████▉    | 221942/371472 [6:59:45<12:11:26,  3.41it/s]
 60%|█████▉    | 221943/371472 [6:59:45<12:07:18,  3.43it/s]
 60%|█████▉    | 221944/371472 [6:59:45<12:15:06,  3.39it/s]
 60%|█████▉    | 221945/371472 [6:59:46<12:27:31,  3.33it/s]
 60%|█████▉    | 221946/371472 [6:59:46<12:16:47,  3.38it/s]
 60%|█████▉    | 221947/371472 [6:59:46<11:55:45,  3.48it/s]
 60%|█████▉    | 221948/371472 [6:59:46<12:30:53,  3.32it/s]
 60%|█████▉    | 221949/371472 [6:59:47<12:26:01,  3.34it/s]
 60%|█████▉    | 221950/371472 [6:59:47<12:38:49,  3.28it/s]
 60%|█████▉    | 221951/371472 [6:59:47<12:22:52,  3.35it/s]
 60%|█████▉    | 221952/371472 [6:59:48<12:17:52,  3.38it/s]
 60%|█████▉    | 221953/371472 [6:59:48<12:01:05,  3.46it/s]
 60%|█████▉    | 221954/371472 [6:59:48<11:47:23,  3.52it/s]
 60%|█████▉    | 221955/371472 [6:59:48<12:09:03,  3.42it/s]
 60%|█████▉    | 221956/371472 [6:59:49<12:47:38,  3.25it/s]
 60%|█████▉    | 221957/371472 [6:59:49<12:39:31,  3.28it/s]
 60%|█████▉    | 221958/371472 [6:59:49<12:31:13,  3.32it/s]
 60%|█████▉    | 221959/371472 [6:59:50<12:22:09,  3.36it/s]
 60%|█████▉    | 221960/371472 [6:59:50<12:03:50,  3.44it/s]
                                                            
{'loss': 2.6571, 'learning_rate': 4.624318558900213e-07, 'epoch': 9.56}
+
 60%|█████▉    | 221960/371472 [6:59:50<12:03:50,  3.44it/s]
 60%|█████▉    | 221961/371472 [6:59:50<11:55:00,  3.49it/s]
 60%|█████▉    | 221962/371472 [6:59:51<11:44:21,  3.54it/s]
 60%|█████▉    | 221963/371472 [6:59:51<11:29:07,  3.62it/s]
 60%|█████▉    | 221964/371472 [6:59:51<11:51:42,  3.50it/s]
 60%|█████▉    | 221965/371472 [6:59:51<11:41:18,  3.55it/s]
 60%|█████▉    | 221966/371472 [6:59:52<11:36:34,  3.58it/s]
 60%|█████▉    | 221967/371472 [6:59:52<11:42:44,  3.55it/s]
 60%|█████▉    | 221968/371472 [6:59:52<12:01:10,  3.46it/s]
 60%|█████▉    | 221969/371472 [6:59:53<12:35:37,  3.30it/s]
 60%|█████▉    | 221970/371472 [6:59:53<13:35:41,  3.05it/s]
 60%|█████▉    | 221971/371472 [6:59:53<13:20:55,  3.11it/s]
 60%|█████▉    | 221972/371472 [6:59:54<12:44:11,  3.26it/s]
 60%|█████▉    | 221973/371472 [6:59:54<12:35:07,  3.30it/s]
 60%|█████▉    | 221974/371472 [6:59:54<12:28:28,  3.33it/s]
 60%|█████▉    | 221975/371472 [6:59:54<11:59:50,  3.46it/s]
 60%|█████▉    | 221976/371472 [6:59:55<11:55:41,  3.48it/s]
 60%|█████▉    | 221977/371472 [6:59:55<12:46:15,  3.25it/s]
 60%|█████▉    | 221978/371472 [6:59:55<12:20:02,  3.37it/s]
 60%|█████▉    | 221979/371472 [6:59:56<12:22:18,  3.36it/s]
 60%|█████▉    | 221980/371472 [6:59:56<12:20:36,  3.36it/s]
                                                            
{'loss': 2.819, 'learning_rate': 4.623833739145425e-07, 'epoch': 9.56}
+
 60%|█████▉    | 221980/371472 [6:59:56<12:20:36,  3.36it/s]
 60%|█████▉    | 221981/371472 [6:59:56<12:56:50,  3.21it/s]
 60%|█████▉    | 221982/371472 [6:59:57<13:52:54,  2.99it/s]
 60%|█████▉    | 221983/371472 [6:59:57<13:21:42,  3.11it/s]
 60%|█████▉    | 221984/371472 [6:59:57<13:48:54,  3.01it/s]
 60%|█████▉    | 221985/371472 [6:59:58<14:19:33,  2.90it/s]
 60%|█████▉    | 221986/371472 [6:59:58<14:15:00,  2.91it/s]
 60%|█████▉    | 221987/371472 [6:59:58<14:12:31,  2.92it/s]
 60%|█████▉    | 221988/371472 [6:59:59<13:56:01,  2.98it/s]
 60%|█████▉    | 221989/371472 [6:59:59<13:23:48,  3.10it/s]
 60%|█████▉    | 221990/371472 [6:59:59<12:50:23,  3.23it/s]
 60%|█████▉    | 221991/371472 [6:59:59<12:32:03,  3.31it/s]
 60%|█████▉    | 221992/371472 [7:00:00<12:10:07,  3.41it/s]
 60%|█████▉    | 221993/371472 [7:00:00<11:58:41,  3.47it/s]
 60%|█████▉    | 221994/371472 [7:00:00<12:53:49,  3.22it/s]
 60%|█████▉    | 221995/371472 [7:00:01<12:26:58,  3.34it/s]
 60%|█████▉    | 221996/371472 [7:00:01<12:23:27,  3.35it/s]
 60%|█████▉    | 221997/371472 [7:00:01<12:25:47,  3.34it/s]
 60%|█████▉    | 221998/371472 [7:00:02<12:22:40,  3.35it/s]
 60%|█████▉    | 221999/371472 [7:00:02<12:27:30,  3.33it/s]
 60%|█████▉    | 222000/371472 [7:00:02<12:17:22,  3.38it/s]
                                                            
{'loss': 2.8205, 'learning_rate': 4.623348919390635e-07, 'epoch': 9.56}
+
 60%|█████▉    | 222000/371472 [7:00:02<12:17:22,  3.38it/s]
 60%|█████▉    | 222001/371472 [7:00:02<12:13:23,  3.40it/s]
 60%|█████▉    | 222002/371472 [7:00:03<12:57:56,  3.20it/s]
 60%|█████▉    | 222003/371472 [7:00:03<12:26:04,  3.34it/s]
 60%|█████▉    | 222004/371472 [7:00:03<11:54:13,  3.49it/s]
 60%|█████▉    | 222005/371472 [7:00:04<12:08:50,  3.42it/s]
 60%|█████▉    | 222006/371472 [7:00:04<11:46:35,  3.53it/s]
 60%|█████▉    | 222007/371472 [7:00:04<11:32:39,  3.60it/s]
 60%|█████▉    | 222008/371472 [7:00:04<12:13:49,  3.39it/s]
 60%|█████▉    | 222009/371472 [7:00:05<11:57:15,  3.47it/s]
 60%|█████▉    | 222010/371472 [7:00:05<12:10:58,  3.41it/s]
 60%|█████▉    | 222011/371472 [7:00:05<12:12:11,  3.40it/s]
 60%|█████▉    | 222012/371472 [7:00:06<12:08:00,  3.42it/s]
 60%|█████▉    | 222013/371472 [7:00:06<11:48:16,  3.52it/s]
 60%|█████▉    | 222014/371472 [7:00:06<11:43:39,  3.54it/s]
 60%|█████▉    | 222015/371472 [7:00:06<11:38:40,  3.57it/s]
 60%|█████▉    | 222016/371472 [7:00:07<11:33:02,  3.59it/s]
 60%|█████▉    | 222017/371472 [7:00:07<12:13:48,  3.39it/s]
 60%|█████▉    | 222018/371472 [7:00:07<12:21:18,  3.36it/s]
 60%|█████▉    | 222019/371472 [7:00:08<12:21:07,  3.36it/s]
 60%|█████▉    | 222020/371472 [7:00:08<11:57:39,  3.47it/s]
                                                            
{'loss': 2.8551, 'learning_rate': 4.6228640996358467e-07, 'epoch': 9.56}
+
 60%|█████▉    | 222020/371472 [7:00:08<11:57:39,  3.47it/s]
 60%|█████▉    | 222021/371472 [7:00:08<11:59:32,  3.46it/s]
 60%|█████▉    | 222022/371472 [7:00:09<11:46:47,  3.52it/s]
 60%|█████▉    | 222023/371472 [7:00:09<12:56:50,  3.21it/s]
 60%|█████▉    | 222024/371472 [7:00:09<12:32:01,  3.31it/s]
 60%|█████▉    | 222025/371472 [7:00:09<12:15:27,  3.39it/s]
 60%|█████▉    | 222026/371472 [7:00:10<12:23:39,  3.35it/s]
 60%|█████▉    | 222027/371472 [7:00:10<12:37:46,  3.29it/s]
 60%|█████▉    | 222028/371472 [7:00:10<12:15:51,  3.38it/s]
 60%|█████▉    | 222029/371472 [7:00:11<12:08:16,  3.42it/s]
 60%|█████▉    | 222030/371472 [7:00:11<12:12:46,  3.40it/s]
 60%|█████▉    | 222031/371472 [7:00:11<12:09:56,  3.41it/s]
 60%|█████▉    | 222032/371472 [7:00:11<11:55:10,  3.48it/s]
 60%|█████▉    | 222033/371472 [7:00:12<12:19:23,  3.37it/s]
 60%|█████▉    | 222034/371472 [7:00:12<12:07:19,  3.42it/s]
 60%|█████▉    | 222035/371472 [7:00:12<12:09:02,  3.42it/s]
 60%|█████▉    | 222036/371472 [7:00:13<11:48:01,  3.52it/s]
 60%|█████▉    | 222037/371472 [7:00:13<12:10:22,  3.41it/s]
 60%|█████▉    | 222038/371472 [7:00:13<12:06:24,  3.43it/s]
 60%|█████▉    | 222039/371472 [7:00:14<12:30:55,  3.32it/s]
 60%|█████▉    | 222040/371472 [7:00:14<12:20:48,  3.36it/s]
                                                            
{'loss': 2.8075, 'learning_rate': 4.6223792798810574e-07, 'epoch': 9.56}
+
 60%|█████▉    | 222040/371472 [7:00:14<12:20:48,  3.36it/s]
 60%|█████▉    | 222041/371472 [7:00:14<11:54:33,  3.49it/s]
 60%|█████▉    | 222042/371472 [7:00:14<11:58:10,  3.47it/s]
 60%|█████▉    | 222043/371472 [7:00:15<11:36:14,  3.58it/s]
 60%|█████▉    | 222044/371472 [7:00:15<12:09:54,  3.41it/s]
 60%|█████▉    | 222045/371472 [7:00:15<12:13:45,  3.39it/s]
 60%|█████▉    | 222046/371472 [7:00:16<11:53:56,  3.49it/s]
 60%|█████▉    | 222047/371472 [7:00:16<11:29:41,  3.61it/s]
 60%|█████▉    | 222048/371472 [7:00:16<11:59:21,  3.46it/s]
 60%|█████▉    | 222049/371472 [7:00:16<11:41:23,  3.55it/s]
 60%|█████▉    | 222050/371472 [7:00:17<11:23:54,  3.64it/s]
 60%|█████▉    | 222051/371472 [7:00:17<11:24:15,  3.64it/s]
 60%|█████▉    | 222052/371472 [7:00:17<11:17:02,  3.68it/s]
 60%|█████▉    | 222053/371472 [7:00:18<12:04:35,  3.44it/s]
 60%|█████▉    | 222054/371472 [7:00:18<12:47:35,  3.24it/s]
 60%|█████▉    | 222055/371472 [7:00:18<12:13:13,  3.40it/s]
 60%|█████▉    | 222056/371472 [7:00:18<12:12:35,  3.40it/s]
 60%|█████▉    | 222057/371472 [7:00:19<11:45:02,  3.53it/s]
 60%|█████▉    | 222058/371472 [7:00:19<11:53:09,  3.49it/s]
 60%|█████▉    | 222059/371472 [7:00:19<11:54:17,  3.49it/s]
 60%|█████▉    | 222060/371472 [7:00:20<11:44:47,  3.53it/s]
                                                            
{'loss': 2.7886, 'learning_rate': 4.6218944601262687e-07, 'epoch': 9.56}
+
 60%|█████▉    | 222060/371472 [7:00:20<11:44:47,  3.53it/s]
 60%|█████▉    | 222061/371472 [7:00:20<11:29:15,  3.61it/s]
 60%|█████▉    | 222062/371472 [7:00:20<11:20:01,  3.66it/s]
 60%|█████▉    | 222063/371472 [7:00:20<11:42:14,  3.55it/s]
 60%|█████▉    | 222064/371472 [7:00:21<11:38:23,  3.57it/s]
 60%|█████▉    | 222065/371472 [7:00:21<11:47:42,  3.52it/s]
 60%|█████▉    | 222066/371472 [7:00:21<11:26:45,  3.63it/s]
 60%|█████▉    | 222067/371472 [7:00:21<11:25:09,  3.63it/s]
 60%|█████▉    | 222068/371472 [7:00:22<11:31:09,  3.60it/s]
 60%|█████▉    | 222069/371472 [7:00:22<11:52:30,  3.49it/s]
 60%|█████▉    | 222070/371472 [7:00:22<12:19:46,  3.37it/s]
 60%|█████▉    | 222071/371472 [7:00:23<13:09:34,  3.15it/s]
 60%|█████▉    | 222072/371472 [7:00:23<13:13:14,  3.14it/s]
 60%|█████▉    | 222073/371472 [7:00:23<12:42:49,  3.26it/s]
 60%|█████▉    | 222074/371472 [7:00:24<12:31:43,  3.31it/s]
 60%|█████▉    | 222075/371472 [7:00:24<11:47:08,  3.52it/s]
 60%|█████▉    | 222076/371472 [7:00:24<11:42:40,  3.54it/s]
 60%|█████▉    | 222077/371472 [7:00:24<11:51:58,  3.50it/s]
 60%|█████▉    | 222078/371472 [7:00:25<11:25:58,  3.63it/s]
 60%|█████▉    | 222079/371472 [7:00:25<11:20:59,  3.66it/s]
 60%|█████▉    | 222080/371472 [7:00:25<11:43:54,  3.54it/s]
                                                            
{'loss': 2.8636, 'learning_rate': 4.6214096403714794e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222080/371472 [7:00:25<11:43:54,  3.54it/s]
 60%|█████▉    | 222081/371472 [7:00:26<12:13:09,  3.40it/s]
 60%|█████▉    | 222082/371472 [7:00:26<11:49:41,  3.51it/s]
 60%|█████▉    | 222083/371472 [7:00:26<11:40:06,  3.56it/s]
 60%|█████▉    | 222084/371472 [7:00:26<11:28:38,  3.62it/s]
 60%|█████▉    | 222085/371472 [7:00:27<11:27:09,  3.62it/s]
 60%|█████▉    | 222086/371472 [7:00:27<11:21:45,  3.65it/s]
 60%|█████▉    | 222087/371472 [7:00:27<11:11:39,  3.71it/s]
 60%|█████▉    | 222088/371472 [7:00:28<11:15:34,  3.69it/s]
 60%|█████▉    | 222089/371472 [7:00:28<11:46:40,  3.52it/s]
 60%|█████▉    | 222090/371472 [7:00:28<12:00:00,  3.46it/s]
 60%|█████▉    | 222091/371472 [7:00:28<12:05:59,  3.43it/s]
 60%|█████▉    | 222092/371472 [7:00:29<11:54:59,  3.48it/s]
 60%|█████▉    | 222093/371472 [7:00:29<11:50:15,  3.51it/s]
 60%|█████▉    | 222094/371472 [7:00:29<11:40:34,  3.55it/s]
 60%|█████▉    | 222095/371472 [7:00:30<11:39:47,  3.56it/s]
 60%|█████▉    | 222096/371472 [7:00:30<11:20:41,  3.66it/s]
 60%|█████▉    | 222097/371472 [7:00:30<11:17:24,  3.68it/s]
 60%|█████▉    | 222098/371472 [7:00:30<11:57:47,  3.47it/s]
 60%|█████▉    | 222099/371472 [7:00:31<11:50:42,  3.50it/s]
 60%|█████▉    | 222100/371472 [7:00:31<12:24:33,  3.34it/s]
                                                            
{'loss': 2.7891, 'learning_rate': 4.620924820616691e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222100/371472 [7:00:31<12:24:33,  3.34it/s]
 60%|█████▉    | 222101/371472 [7:00:31<12:30:52,  3.32it/s]
 60%|█████▉    | 222102/371472 [7:00:32<12:38:47,  3.28it/s]
 60%|█████▉    | 222103/371472 [7:00:32<13:20:23,  3.11it/s]
 60%|█████▉    | 222104/371472 [7:00:32<13:25:52,  3.09it/s]
 60%|█████▉    | 222105/371472 [7:00:33<13:10:34,  3.15it/s]
 60%|█████▉    | 222106/371472 [7:00:33<13:11:35,  3.14it/s]
 60%|█████▉    | 222107/371472 [7:00:33<12:49:18,  3.24it/s]
 60%|█████▉    | 222108/371472 [7:00:33<12:25:48,  3.34it/s]
 60%|█████▉    | 222109/371472 [7:00:34<12:38:25,  3.28it/s]
 60%|█████▉    | 222110/371472 [7:00:34<12:11:47,  3.40it/s]
 60%|█████▉    | 222111/371472 [7:00:34<12:01:46,  3.45it/s]
 60%|█████▉    | 222112/371472 [7:00:35<11:45:57,  3.53it/s]
 60%|█████▉    | 222113/371472 [7:00:35<11:59:06,  3.46it/s]
 60%|█████▉    | 222114/371472 [7:00:35<12:01:19,  3.45it/s]
 60%|█████▉    | 222115/371472 [7:00:35<11:51:39,  3.50it/s]
 60%|█████▉    | 222116/371472 [7:00:36<12:58:02,  3.20it/s]
 60%|█████▉    | 222117/371472 [7:00:36<13:27:57,  3.08it/s]
 60%|█████▉    | 222118/371472 [7:00:37<13:25:23,  3.09it/s]
 60%|█████▉    | 222119/371472 [7:00:37<12:50:08,  3.23it/s]
 60%|█████▉    | 222120/371472 [7:00:37<12:43:29,  3.26it/s]
                                                            
{'loss': 2.7293, 'learning_rate': 4.6204400008619013e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222120/371472 [7:00:37<12:43:29,  3.26it/s]
 60%|█████▉    | 222121/371472 [7:00:37<13:29:54,  3.07it/s]
 60%|█████▉    | 222122/371472 [7:00:38<12:58:20,  3.20it/s]
 60%|█████▉    | 222123/371472 [7:00:38<12:22:39,  3.35it/s]
 60%|█████▉    | 222124/371472 [7:00:38<12:02:53,  3.44it/s]
 60%|█████▉    | 222125/371472 [7:00:39<12:08:14,  3.42it/s]
 60%|█████▉    | 222126/371472 [7:00:39<12:02:18,  3.45it/s]
 60%|█████▉    | 222127/371472 [7:00:39<11:57:39,  3.47it/s]
 60%|█████▉    | 222128/371472 [7:00:40<12:44:29,  3.26it/s]
 60%|█████▉    | 222129/371472 [7:00:40<12:59:36,  3.19it/s]
 60%|█████▉    | 222130/371472 [7:00:40<12:49:11,  3.24it/s]
 60%|█████▉    | 222131/371472 [7:00:40<12:37:54,  3.28it/s]
 60%|█████▉    | 222132/371472 [7:00:41<12:57:03,  3.20it/s]
 60%|█████▉    | 222133/371472 [7:00:41<12:43:00,  3.26it/s]
 60%|█████▉    | 222134/371472 [7:00:41<12:36:55,  3.29it/s]
 60%|█████▉    | 222135/371472 [7:00:42<12:29:52,  3.32it/s]
 60%|█████▉    | 222136/371472 [7:00:42<12:09:59,  3.41it/s]
 60%|█████▉    | 222137/371472 [7:00:42<12:00:43,  3.45it/s]
 60%|█████▉    | 222138/371472 [7:00:43<12:24:20,  3.34it/s]
 60%|█████▉    | 222139/371472 [7:00:43<12:16:54,  3.38it/s]
 60%|█████▉    | 222140/371472 [7:00:43<12:06:47,  3.42it/s]
                                                            
{'loss': 2.7045, 'learning_rate': 4.619955181107113e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222140/371472 [7:00:43<12:06:47,  3.42it/s]
 60%|█████▉    | 222141/371472 [7:00:43<12:27:03,  3.33it/s]
 60%|█████▉    | 222142/371472 [7:00:44<13:04:22,  3.17it/s]
 60%|█████▉    | 222143/371472 [7:00:44<13:15:41,  3.13it/s]
 60%|█████▉    | 222144/371472 [7:00:44<13:04:14,  3.17it/s]
 60%|█████▉    | 222145/371472 [7:00:45<12:41:42,  3.27it/s]
 60%|█████▉    | 222146/371472 [7:00:45<12:18:47,  3.37it/s]
 60%|█████▉    | 222147/371472 [7:00:45<11:57:28,  3.47it/s]
 60%|█████▉    | 222148/371472 [7:00:46<12:48:27,  3.24it/s]
 60%|█████▉    | 222149/371472 [7:00:46<13:24:16,  3.09it/s]
 60%|█████▉    | 222150/371472 [7:00:46<12:52:19,  3.22it/s]
 60%|█████▉    | 222151/371472 [7:00:47<12:34:58,  3.30it/s]
 60%|█████▉    | 222152/371472 [7:00:47<13:11:54,  3.14it/s]
 60%|█████▉    | 222153/371472 [7:00:47<13:40:55,  3.03it/s]
 60%|█████▉    | 222154/371472 [7:00:48<13:36:44,  3.05it/s]
 60%|█████▉    | 222155/371472 [7:00:48<14:10:17,  2.93it/s]
 60%|█████▉    | 222156/371472 [7:00:48<13:16:42,  3.12it/s]
 60%|█████▉    | 222157/371472 [7:00:48<12:57:43,  3.20it/s]
 60%|█████▉    | 222158/371472 [7:00:49<12:56:29,  3.20it/s]
 60%|█████▉    | 222159/371472 [7:00:49<12:30:23,  3.32it/s]
 60%|█████▉    | 222160/371472 [7:00:49<12:48:35,  3.24it/s]
                                                            
{'loss': 2.6255, 'learning_rate': 4.619470361352324e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222160/371472 [7:00:49<12:48:35,  3.24it/s]
 60%|█████▉    | 222161/371472 [7:00:50<12:27:54,  3.33it/s]
 60%|█████▉    | 222162/371472 [7:00:50<12:26:51,  3.33it/s]
 60%|█████▉    | 222163/371472 [7:00:50<12:54:33,  3.21it/s]
 60%|█████▉    | 222164/371472 [7:00:51<12:26:43,  3.33it/s]
 60%|█████▉    | 222165/371472 [7:00:51<12:49:31,  3.23it/s]
 60%|█████▉    | 222166/371472 [7:00:51<13:07:11,  3.16it/s]
 60%|█████▉    | 222167/371472 [7:00:52<12:45:23,  3.25it/s]
 60%|█████▉    | 222168/371472 [7:00:52<12:33:25,  3.30it/s]
 60%|█████▉    | 222169/371472 [7:00:52<12:41:20,  3.27it/s]
 60%|█████▉    | 222170/371472 [7:00:52<12:27:26,  3.33it/s]
 60%|█████▉    | 222171/371472 [7:00:53<12:15:21,  3.38it/s]
 60%|█████▉    | 222172/371472 [7:00:53<12:05:35,  3.43it/s]
 60%|█████▉    | 222173/371472 [7:00:53<12:35:39,  3.29it/s]
 60%|█████▉    | 222174/371472 [7:00:54<12:45:04,  3.25it/s]
 60%|█████▉    | 222175/371472 [7:00:54<12:43:28,  3.26it/s]
 60%|█████▉    | 222176/371472 [7:00:54<12:17:53,  3.37it/s]
 60%|█████▉    | 222177/371472 [7:00:55<12:19:46,  3.36it/s]
 60%|█████▉    | 222178/371472 [7:00:55<12:03:19,  3.44it/s]
 60%|█████▉    | 222179/371472 [7:00:55<12:41:18,  3.27it/s]
 60%|█████▉    | 222180/371472 [7:00:55<12:45:23,  3.25it/s]
                                                            
{'loss': 2.6517, 'learning_rate': 4.6189855415975345e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222180/371472 [7:00:55<12:45:23,  3.25it/s]
 60%|█████▉    | 222181/371472 [7:00:56<12:35:40,  3.29it/s]
 60%|█████▉    | 222182/371472 [7:00:56<12:20:44,  3.36it/s]
 60%|█████▉    | 222183/371472 [7:00:56<11:56:20,  3.47it/s]
 60%|█████▉    | 222184/371472 [7:00:57<12:04:44,  3.43it/s]
 60%|█████▉    | 222185/371472 [7:00:57<11:41:52,  3.54it/s]
 60%|█████▉    | 222186/371472 [7:00:57<11:32:11,  3.59it/s]
 60%|█████▉    | 222187/371472 [7:00:57<11:48:13,  3.51it/s]
 60%|█████▉    | 222188/371472 [7:00:58<12:47:45,  3.24it/s]
 60%|█████▉    | 222189/371472 [7:00:58<12:36:03,  3.29it/s]
 60%|█████▉    | 222190/371472 [7:00:58<12:20:51,  3.36it/s]
 60%|█████▉    | 222191/371472 [7:00:59<12:09:10,  3.41it/s]
 60%|█████▉    | 222192/371472 [7:00:59<11:45:11,  3.53it/s]
 60%|█████▉    | 222193/371472 [7:00:59<11:49:14,  3.51it/s]
 60%|█████▉    | 222194/371472 [7:01:00<11:58:54,  3.46it/s]
 60%|█████▉    | 222195/371472 [7:01:00<12:10:52,  3.40it/s]
 60%|█████▉    | 222196/371472 [7:01:00<12:18:22,  3.37it/s]
 60%|█████▉    | 222197/371472 [7:01:00<12:06:03,  3.43it/s]
 60%|█████▉    | 222198/371472 [7:01:01<12:05:56,  3.43it/s]
 60%|█████▉    | 222199/371472 [7:01:01<12:03:19,  3.44it/s]
 60%|█████▉    | 222200/371472 [7:01:01<12:12:06,  3.40it/s]
                                                            
{'loss': 2.5779, 'learning_rate': 4.618500721842746e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222200/371472 [7:01:01<12:12:06,  3.40it/s]
 60%|█████▉    | 222201/371472 [7:01:02<11:48:15,  3.51it/s]
 60%|█████▉    | 222202/371472 [7:01:02<12:04:49,  3.43it/s]
 60%|█████▉    | 222203/371472 [7:01:02<12:00:30,  3.45it/s]
 60%|█████▉    | 222204/371472 [7:01:02<11:54:49,  3.48it/s]
 60%|█████▉    | 222205/371472 [7:01:03<12:08:16,  3.42it/s]
 60%|█████▉    | 222206/371472 [7:01:03<12:13:31,  3.39it/s]
 60%|█████▉    | 222207/371472 [7:01:03<12:08:57,  3.41it/s]
 60%|█████▉    | 222208/371472 [7:01:04<12:14:35,  3.39it/s]
 60%|█████▉    | 222209/371472 [7:01:04<12:17:07,  3.37it/s]
 60%|█████▉    | 222210/371472 [7:01:04<12:58:29,  3.20it/s]
 60%|█████▉    | 222211/371472 [7:01:05<13:39:47,  3.03it/s]
 60%|█████▉    | 222212/371472 [7:01:05<13:23:27,  3.10it/s]
 60%|█████▉    | 222213/371472 [7:01:05<13:17:58,  3.12it/s]
 60%|█████▉    | 222214/371472 [7:01:06<13:06:19,  3.16it/s]
 60%|█████▉    | 222215/371472 [7:01:06<13:23:50,  3.09it/s]
 60%|█████▉    | 222216/371472 [7:01:06<13:20:30,  3.11it/s]
 60%|█████▉    | 222217/371472 [7:01:07<13:03:12,  3.18it/s]
 60%|█████▉    | 222218/371472 [7:01:07<13:36:55,  3.05it/s]
 60%|█████▉    | 222219/371472 [7:01:07<13:27:15,  3.08it/s]
 60%|█████▉    | 222220/371472 [7:01:08<13:24:28,  3.09it/s]
                                                            
{'loss': 2.6227, 'learning_rate': 4.6180159020879565e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222220/371472 [7:01:08<13:24:28,  3.09it/s]
 60%|█████▉    | 222221/371472 [7:01:08<12:49:35,  3.23it/s]
 60%|█████▉    | 222222/371472 [7:01:08<12:57:49,  3.20it/s]
 60%|█████▉    | 222223/371472 [7:01:08<12:41:42,  3.27it/s]
 60%|█████▉    | 222224/371472 [7:01:09<12:12:01,  3.40it/s]
 60%|█████▉    | 222225/371472 [7:01:09<11:59:31,  3.46it/s]
 60%|█████▉    | 222226/371472 [7:01:09<11:59:56,  3.46it/s]
 60%|█████▉    | 222227/371472 [7:01:10<11:49:41,  3.50it/s]
 60%|█████▉    | 222228/371472 [7:01:10<11:41:21,  3.55it/s]
 60%|█████▉    | 222229/371472 [7:01:10<12:07:05,  3.42it/s]
 60%|█████▉    | 222230/371472 [7:01:10<11:49:36,  3.51it/s]
 60%|█████▉    | 222231/371472 [7:01:11<11:43:07,  3.54it/s]
 60%|█████▉    | 222232/371472 [7:01:11<11:55:53,  3.47it/s]
 60%|█████▉    | 222233/371472 [7:01:11<12:02:54,  3.44it/s]
 60%|█████▉    | 222234/371472 [7:01:12<12:23:28,  3.35it/s]
 60%|█████▉    | 222235/371472 [7:01:12<12:56:29,  3.20it/s]
 60%|█████▉    | 222236/371472 [7:01:12<12:35:20,  3.29it/s]
 60%|█████▉    | 222237/371472 [7:01:13<12:58:42,  3.19it/s]
 60%|█████▉    | 222238/371472 [7:01:13<12:25:24,  3.34it/s]
 60%|█████▉    | 222239/371472 [7:01:13<12:15:04,  3.38it/s]
 60%|█████▉    | 222240/371472 [7:01:13<12:21:05,  3.36it/s]
                                                            
{'loss': 2.8602, 'learning_rate': 4.6175310823331683e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222240/371472 [7:01:13<12:21:05,  3.36it/s]
 60%|█████▉    | 222241/371472 [7:01:14<12:29:35,  3.32it/s]
 60%|█████▉    | 222242/371472 [7:01:14<13:40:32,  3.03it/s]
 60%|█████▉    | 222243/371472 [7:01:15<14:52:17,  2.79it/s]
 60%|█████▉    | 222244/371472 [7:01:15<13:55:50,  2.98it/s]
 60%|█████▉    | 222245/371472 [7:01:15<13:08:17,  3.16it/s]
 60%|█████▉    | 222246/371472 [7:01:15<12:51:05,  3.23it/s]
 60%|█████▉    | 222247/371472 [7:01:16<13:40:23,  3.03it/s]
 60%|█���███▉    | 222248/371472 [7:01:16<12:51:51,  3.22it/s]
 60%|█████▉    | 222249/371472 [7:01:16<13:13:49,  3.13it/s]
 60%|█████▉    | 222250/371472 [7:01:17<13:12:24,  3.14it/s]
 60%|█████▉    | 222251/371472 [7:01:17<12:47:23,  3.24it/s]
 60%|█████▉    | 222252/371472 [7:01:17<12:31:04,  3.31it/s]
 60%|█████▉    | 222253/371472 [7:01:18<13:34:38,  3.05it/s]
 60%|█████▉    | 222254/371472 [7:01:18<12:46:14,  3.25it/s]
 60%|█████▉    | 222255/371472 [7:01:18<12:13:04,  3.39it/s]
 60%|█████▉    | 222256/371472 [7:01:18<12:26:20,  3.33it/s]
 60%|█████▉    | 222257/371472 [7:01:19<12:25:32,  3.34it/s]
 60%|█████▉    | 222258/371472 [7:01:19<12:13:11,  3.39it/s]
 60%|█████▉    | 222259/371472 [7:01:19<12:06:48,  3.42it/s]
 60%|█████▉    | 222260/371472 [7:01:20<11:54:21,  3.48it/s]
                                                            
{'loss': 2.7164, 'learning_rate': 4.6170462625783785e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222260/371472 [7:01:20<11:54:21,  3.48it/s]
 60%|█████▉    | 222261/371472 [7:01:20<12:00:45,  3.45it/s]
 60%|█████▉    | 222262/371472 [7:01:20<11:56:10,  3.47it/s]
 60%|█████▉    | 222263/371472 [7:01:20<12:00:37,  3.45it/s]
 60%|█████▉    | 222264/371472 [7:01:21<11:56:10,  3.47it/s]
 60%|█████▉    | 222265/371472 [7:01:21<11:58:32,  3.46it/s]
 60%|█████▉    | 222266/371472 [7:01:21<11:47:54,  3.51it/s]
 60%|█████▉    | 222267/371472 [7:01:22<11:36:14,  3.57it/s]
 60%|█████▉    | 222268/371472 [7:01:22<11:27:32,  3.62it/s]
 60%|█████▉    | 222269/371472 [7:01:22<11:49:32,  3.50it/s]
 60%|█████▉    | 222270/371472 [7:01:22<12:23:44,  3.34it/s]
 60%|█████▉    | 222271/371472 [7:01:23<12:03:45,  3.44it/s]
 60%|█████▉    | 222272/371472 [7:01:23<11:53:55,  3.48it/s]
 60%|█████▉    | 222273/371472 [7:01:23<12:44:19,  3.25it/s]
 60%|█████▉    | 222274/371472 [7:01:24<12:33:09,  3.30it/s]
 60%|█████▉    | 222275/371472 [7:01:24<12:33:08,  3.30it/s]
 60%|█████▉    | 222276/371472 [7:01:24<12:19:36,  3.36it/s]
 60%|█████▉    | 222277/371472 [7:01:25<12:12:48,  3.39it/s]
 60%|█████▉    | 222278/371472 [7:01:25<12:21:40,  3.35it/s]
 60%|█████▉    | 222279/371472 [7:01:25<12:05:41,  3.43it/s]
 60%|█████▉    | 222280/371472 [7:01:25<11:56:29,  3.47it/s]
                                                            
{'loss': 2.6927, 'learning_rate': 4.616561442823591e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222280/371472 [7:01:25<11:56:29,  3.47it/s]
 60%|█████▉    | 222281/371472 [7:01:26<12:58:33,  3.19it/s]
 60%|█████▉    | 222282/371472 [7:01:26<12:22:12,  3.35it/s]
 60%|█████▉    | 222283/371472 [7:01:26<12:37:36,  3.28it/s]
 60%|█████▉    | 222284/371472 [7:01:27<12:22:45,  3.35it/s]
 60%|█████▉    | 222285/371472 [7:01:27<12:16:00,  3.38it/s]
 60%|█████▉    | 222286/371472 [7:01:27<12:26:53,  3.33it/s]
 60%|█████▉    | 222287/371472 [7:01:28<13:03:24,  3.17it/s]
 60%|█████▉    | 222288/371472 [7:01:28<13:01:47,  3.18it/s]
 60%|█████▉    | 222289/371472 [7:01:28<12:46:15,  3.24it/s]
 60%|█████▉    | 222290/371472 [7:01:29<12:29:17,  3.32it/s]
 60%|█████▉    | 222291/371472 [7:01:29<12:32:00,  3.31it/s]
 60%|█████▉    | 222292/371472 [7:01:29<13:34:31,  3.05it/s]
 60%|█████▉    | 222293/371472 [7:01:30<13:38:56,  3.04it/s]
 60%|█████▉    | 222294/371472 [7:01:30<13:14:06,  3.13it/s]
 60%|█████▉    | 222295/371472 [7:01:30<12:37:15,  3.28it/s]
 60%|█████▉    | 222296/371472 [7:01:30<12:23:53,  3.34it/s]
 60%|█████▉    | 222297/371472 [7:01:31<12:18:35,  3.37it/s]
 60%|█████▉    | 222298/371472 [7:01:31<12:58:37,  3.19it/s]
 60%|█████▉    | 222299/371472 [7:01:31<13:24:33,  3.09it/s]
 60%|█████▉    | 222300/371472 [7:01:32<12:53:54,  3.21it/s]
                                                            
{'loss': 2.776, 'learning_rate': 4.616076623068801e-07, 'epoch': 9.57}
+
 60%|█████▉    | 222300/371472 [7:01:32<12:53:54,  3.21it/s]
 60%|█████▉    | 222301/371472 [7:01:32<12:59:39,  3.19it/s]
 60%|█████▉    | 222302/371472 [7:01:32<12:25:58,  3.33it/s]
 60%|█████▉    | 222303/371472 [7:01:33<12:54:47,  3.21it/s]
 60%|█████▉    | 222304/371472 [7:01:33<12:54:22,  3.21it/s]
 60%|█████▉    | 222305/371472 [7:01:33<12:34:16,  3.30it/s]
 60%|█████▉    | 222306/371472 [7:01:33<12:16:46,  3.37it/s]
 60%|█████▉    | 222307/371472 [7:01:34<12:22:28,  3.35it/s]
 60%|█████▉    | 222308/371472 [7:01:34<12:09:51,  3.41it/s]
 60%|█████▉    | 222309/371472 [7:01:34<13:23:07,  3.10it/s]
 60%|█████▉    | 222310/371472 [7:01:35<13:50:18,  2.99it/s]
 60%|█████▉    | 222311/371472 [7:01:35<13:26:16,  3.08it/s]
 60%|█████▉    | 222312/371472 [7:01:35<13:00:19,  3.19it/s]
 60%|█████▉    | 222313/371472 [7:01:36<12:27:28,  3.33it/s]
 60%|█████▉    | 222314/371472 [7:01:36<12:18:50,  3.36it/s]
 60%|█████▉    | 222315/371472 [7:01:36<12:07:22,  3.42it/s]
 60%|█████▉    | 222316/371472 [7:01:37<12:06:06,  3.42it/s]
 60%|█████▉    | 222317/371472 [7:01:37<11:49:26,  3.50it/s]
 60%|█████▉    | 222318/371472 [7:01:37<11:54:37,  3.48it/s]
 60%|█████▉    | 222319/371472 [7:01:37<12:21:17,  3.35it/s]
 60%|█████▉    | 222320/371472 [7:01:38<12:24:42,  3.34it/s]
                                                            
{'loss': 2.761, 'learning_rate': 4.615591803314012e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222320/371472 [7:01:38<12:24:42,  3.34it/s]
 60%|█████▉    | 222321/371472 [7:01:38<13:03:43,  3.17it/s]
 60%|█████▉    | 222322/371472 [7:01:38<12:36:56,  3.28it/s]
 60%|█████▉    | 222323/371472 [7:01:39<13:04:22,  3.17it/s]
 60%|█████▉    | 222324/371472 [7:01:39<12:39:52,  3.27it/s]
 60%|█████▉    | 222325/371472 [7:01:39<12:17:45,  3.37it/s]
 60%|█████▉    | 222326/371472 [7:01:40<12:24:12,  3.34it/s]
 60%|█████▉    | 222327/371472 [7:01:40<12:06:31,  3.42it/s]
 60%|█████▉    | 222328/371472 [7:01:40<11:38:10,  3.56it/s]
 60%|█████▉    | 222329/371472 [7:01:40<11:55:46,  3.47it/s]
 60%|█████▉    | 222330/371472 [7:01:41<11:56:27,  3.47it/s]
 60%|█████▉    | 222331/371472 [7:01:41<12:28:58,  3.32it/s]
 60%|█████▉    | 222332/371472 [7:01:41<12:41:25,  3.26it/s]
 60%|█████▉    | 222333/371472 [7:01:42<12:26:06,  3.33it/s]
 60%|█████▉    | 222334/371472 [7:01:42<11:56:18,  3.47it/s]
 60%|█████▉    | 222335/371472 [7:01:42<11:57:59,  3.46it/s]
 60%|█████▉    | 222336/371472 [7:01:42<11:51:13,  3.49it/s]
 60%|█████▉    | 222337/371472 [7:01:43<11:53:23,  3.48it/s]
 60%|█████▉    | 222338/371472 [7:01:43<12:09:08,  3.41it/s]
 60%|█████▉    | 222339/371472 [7:01:43<13:09:45,  3.15it/s]
 60%|█████▉    | 222340/371472 [7:01:44<12:55:31,  3.20it/s]
                                                            
{'loss': 2.7828, 'learning_rate': 4.615106983559223e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222340/371472 [7:01:44<12:55:31,  3.20it/s]
 60%|█████▉    | 222341/371472 [7:01:44<12:39:57,  3.27it/s]
 60%|█████▉    | 222342/371472 [7:01:44<12:30:56,  3.31it/s]
 60%|█████▉    | 222343/371472 [7:01:45<12:24:17,  3.34it/s]
 60%|█████▉    | 222344/371472 [7:01:45<12:27:23,  3.33it/s]
 60%|█████▉    | 222345/371472 [7:01:45<13:49:03,  3.00it/s]
 60%|█████▉    | 222346/371472 [7:01:46<13:11:06,  3.14it/s]
 60%|█████▉    | 222347/371472 [7:01:46<12:43:59,  3.25it/s]
 60%|█████▉    | 222348/371472 [7:01:46<12:16:18,  3.38it/s]
 60%|█████▉    | 222349/371472 [7:01:47<13:10:46,  3.14it/s]
 60%|█████▉    | 222350/371472 [7:01:47<12:28:47,  3.32it/s]
 60%|█████▉    | 222351/371472 [7:01:47<12:12:31,  3.39it/s]
 60%|█████▉    | 222352/371472 [7:01:47<12:21:06,  3.35it/s]
 60%|█████▉    | 222353/371472 [7:01:48<12:19:53,  3.36it/s]
 60%|█████▉    | 222354/371472 [7:01:48<12:35:24,  3.29it/s]
 60%|█████▉    | 222355/371472 [7:01:48<12:23:18,  3.34it/s]
 60%|█████▉    | 222356/371472 [7:01:49<12:39:28,  3.27it/s]
 60%|█████▉    | 222357/371472 [7:01:49<12:18:57,  3.36it/s]
 60%|█████▉    | 222358/371472 [7:01:49<12:43:17,  3.26it/s]
 60%|█████▉    | 222359/371472 [7:01:49<12:18:22,  3.37it/s]
 60%|█████▉    | 222360/371472 [7:01:50<12:04:52,  3.43it/s]
                                                            
{'loss': 2.742, 'learning_rate': 4.6146221638044347e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222360/371472 [7:01:50<12:04:52,  3.43it/s]
 60%|█████▉    | 222361/371472 [7:01:50<11:55:09,  3.48it/s]
 60%|█████▉    | 222362/371472 [7:01:50<11:40:37,  3.55it/s]
 60%|█████▉    | 222363/371472 [7:01:51<11:37:26,  3.56it/s]
 60%|█████▉    | 222364/371472 [7:01:51<11:35:55,  3.57it/s]
 60%|█████▉    | 222365/371472 [7:01:51<11:52:40,  3.49it/s]
 60%|█████▉    | 222366/371472 [7:01:51<11:52:07,  3.49it/s]
 60%|█████▉    | 222367/371472 [7:01:52<11:58:50,  3.46it/s]
 60%|█████▉    | 222368/371472 [7:01:52<11:58:11,  3.46it/s]
 60%|█████▉    | 222369/371472 [7:01:52<12:13:04,  3.39it/s]
 60%|█████▉    | 222370/371472 [7:01:53<12:27:49,  3.32it/s]
 60%|█████▉    | 222371/371472 [7:01:53<12:37:25,  3.28it/s]
 60%|█████▉    | 222372/371472 [7:01:53<12:27:25,  3.32it/s]
 60%|█████▉    | 222373/371472 [7:01:54<12:21:00,  3.35it/s]
 60%|█████▉    | 222374/371472 [7:01:54<12:35:38,  3.29it/s]
 60%|█████▉    | 222375/371472 [7:01:54<12:03:37,  3.43it/s]
 60%|█████▉    | 222376/371472 [7:01:54<11:52:00,  3.49it/s]
 60%|█████▉    | 222377/371472 [7:01:55<11:56:14,  3.47it/s]
 60%|█████▉    | 222378/371472 [7:01:55<12:04:20,  3.43it/s]
 60%|█████▉    | 222379/371472 [7:01:55<12:00:24,  3.45it/s]
 60%|█████▉    | 222380/371472 [7:01:56<11:52:52,  3.49it/s]
                                                            
{'loss': 2.8463, 'learning_rate': 4.614137344049645e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222380/371472 [7:01:56<11:52:52,  3.49it/s]
 60%|█████▉    | 222381/371472 [7:01:56<12:05:37,  3.42it/s]
 60%|█████▉    | 222382/371472 [7:01:56<11:59:14,  3.45it/s]
 60%|█████▉    | 222383/371472 [7:01:56<11:51:58,  3.49it/s]
 60%|█████▉    | 222384/371472 [7:01:57<11:45:01,  3.52it/s]
 60%|█████▉    | 222385/371472 [7:01:57<11:34:41,  3.58it/s]
 60%|█████▉    | 222386/371472 [7:01:57<12:00:39,  3.45it/s]
 60%|█████▉    | 222387/371472 [7:01:58<12:11:32,  3.40it/s]
 60%|█████▉    | 222388/371472 [7:01:58<12:05:27,  3.43it/s]
 60%|█████▉    | 222389/371472 [7:01:58<11:52:01,  3.49it/s]
 60%|█████▉    | 222390/371472 [7:01:58<11:38:13,  3.56it/s]
 60%|█████▉    | 222391/371472 [7:01:59<12:00:25,  3.45it/s]
 60%|█████▉    | 222392/371472 [7:01:59<12:13:37,  3.39it/s]
 60%|█████▉    | 222393/371472 [7:01:59<12:06:18,  3.42it/s]
 60%|█████▉    | 222394/371472 [7:02:00<12:11:40,  3.40it/s]
 60%|█████▉    | 222395/371472 [7:02:00<12:13:27,  3.39it/s]
 60%|█████▉    | 222396/371472 [7:02:00<12:42:46,  3.26it/s]
 60%|█████▉    | 222397/371472 [7:02:01<12:59:54,  3.19it/s]
 60%|█████▉    | 222398/371472 [7:02:01<12:45:05,  3.25it/s]
 60%|█████▉    | 222399/371472 [7:02:01<12:14:23,  3.38it/s]
 60%|█████▉    | 222400/371472 [7:02:01<12:33:08,  3.30it/s]
                                                            
{'loss': 2.9185, 'learning_rate': 4.6136525242948566e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222400/371472 [7:02:01<12:33:08,  3.30it/s]
 60%|█████▉    | 222401/371472 [7:02:02<12:48:53,  3.23it/s]
 60%|█████▉    | 222402/371472 [7:02:02<12:16:18,  3.37it/s]
 60%|█████▉    | 222403/371472 [7:02:02<12:43:46,  3.25it/s]
 60%|█████▉    | 222404/371472 [7:02:03<12:36:10,  3.29it/s]
 60%|█████▉    | 222405/371472 [7:02:03<12:30:09,  3.31it/s]
 60%|█████▉    | 222406/371472 [7:02:03<12:39:45,  3.27it/s]
 60%|█████▉    | 222407/371472 [7:02:04<12:09:35,  3.41it/s]
 60%|█████▉    | 222408/371472 [7:02:04<12:06:41,  3.42it/s]
 60%|█████▉    | 222409/371472 [7:02:04<11:47:26,  3.51it/s]
 60%|█████▉    | 222410/371472 [7:02:04<11:53:29,  3.48it/s]
 60%|█████▉    | 222411/371472 [7:02:05<12:24:25,  3.34it/s]
 60%|█████▉    | 222412/371472 [7:02:05<12:23:54,  3.34it/s]
 60%|█████▉    | 222413/371472 [7:02:05<12:04:29,  3.43it/s]
 60%|█████▉    | 222414/371472 [7:02:06<12:22:34,  3.35it/s]
 60%|█████▉    | 222415/371472 [7:02:06<11:53:38,  3.48it/s]
 60%|█████▉    | 222416/371472 [7:02:06<11:44:17,  3.53it/s]
 60%|█████▉    | 222417/371472 [7:02:06<11:40:52,  3.54it/s]
 60%|█████▉    | 222418/371472 [7:02:07<11:38:01,  3.56it/s]
 60%|█████▉    | 222419/371472 [7:02:07<12:31:48,  3.30it/s]
 60%|█████▉    | 222420/371472 [7:02:07<12:36:40,  3.28it/s]
                                                            
{'loss': 2.8181, 'learning_rate': 4.6131677045400674e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222420/371472 [7:02:07<12:36:40,  3.28it/s]
 60%|█████▉    | 222421/371472 [7:02:08<13:15:36,  3.12it/s]
 60%|█████▉    | 222422/371472 [7:02:08<13:36:25,  3.04it/s]
 60%|█████▉    | 222423/371472 [7:02:08<13:06:21,  3.16it/s]
 60%|█████▉    | 222424/371472 [7:02:09<13:37:28,  3.04it/s]
 60%|█████▉    | 222425/371472 [7:02:09<12:48:48,  3.23it/s]
 60%|█████▉    | 222426/371472 [7:02:09<12:12:03,  3.39it/s]
 60%|█████▉    | 222427/371472 [7:02:10<11:55:21,  3.47it/s]
 60%|█████▉    | 222428/371472 [7:02:10<11:45:27,  3.52it/s]
 60%|█████▉    | 222429/371472 [7:02:10<11:49:10,  3.50it/s]
 60%|█████▉    | 222430/371472 [7:02:10<11:42:16,  3.54it/s]
 60%|█████▉    | 222431/371472 [7:02:11<12:03:43,  3.43it/s]
 60%|█████▉    | 222432/371472 [7:02:11<12:10:11,  3.40it/s]
 60%|█████▉    | 222433/371472 [7:02:11<12:20:49,  3.35it/s]
 60%|█████▉    | 222434/371472 [7:02:12<12:39:54,  3.27it/s]
 60%|█████▉    | 222435/371472 [7:02:12<12:57:50,  3.19it/s]
 60%|█████▉    | 222436/371472 [7:02:12<13:15:50,  3.12it/s]
 60%|█████▉    | 222437/371472 [7:02:13<12:54:50,  3.21it/s]
 60%|█████▉    | 222438/371472 [7:02:13<13:26:30,  3.08it/s]
 60%|█████▉    | 222439/371472 [7:02:13<12:48:30,  3.23it/s]
 60%|█████▉    | 222440/371472 [7:02:14<13:15:44,  3.12it/s]
                                                            
{'loss': 2.619, 'learning_rate': 4.6126828847852786e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222440/371472 [7:02:14<13:15:44,  3.12it/s]
 60%|█████▉    | 222441/371472 [7:02:14<12:57:14,  3.20it/s]
 60%|█████▉    | 222442/371472 [7:02:14<12:58:43,  3.19it/s]
 60%|█████▉    | 222443/371472 [7:02:14<12:52:31,  3.22it/s]
 60%|█████▉    | 222444/371472 [7:02:15<13:30:35,  3.06it/s]
 60%|█████▉    | 222445/371472 [7:02:15<12:54:46,  3.21it/s]
 60%|█████▉    | 222446/371472 [7:02:15<12:37:01,  3.28it/s]
 60%|█████▉    | 222447/371472 [7:02:16<12:15:00,  3.38it/s]
 60%|█████▉    | 222448/371472 [7:02:16<11:47:29,  3.51it/s]
 60%|█████▉    | 222449/371472 [7:02:16<11:35:55,  3.57it/s]
 60%|█████▉    | 222450/371472 [7:02:17<12:14:54,  3.38it/s]
 60%|█████▉    | 222451/371472 [7:02:17<12:28:07,  3.32it/s]
 60%|█████▉    | 222452/371472 [7:02:17<12:17:21,  3.37it/s]
 60%|█████▉    | 222453/371472 [7:02:17<12:39:14,  3.27it/s]
 60%|█████▉    | 222454/371472 [7:02:18<12:33:11,  3.30it/s]
 60%|█████▉    | 222455/371472 [7:02:18<12:20:58,  3.35it/s]
 60%|█████▉    | 222456/371472 [7:02:18<12:36:31,  3.28it/s]
 60%|█████▉    | 222457/371472 [7:02:19<12:35:21,  3.29it/s]
 60%|█████▉    | 222458/371472 [7:02:19<12:55:37,  3.20it/s]
 60%|█████▉    | 222459/371472 [7:02:19<13:39:31,  3.03it/s]
 60%|█████▉    | 222460/371472 [7:02:20<13:10:25,  3.14it/s]
                                                            
{'loss': 2.8647, 'learning_rate': 4.6121980650304893e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222460/371472 [7:02:20<13:10:25,  3.14it/s]
 60%|█████▉    | 222461/371472 [7:02:20<12:47:40,  3.24it/s]
 60%|█████▉    | 222462/371472 [7:02:20<12:51:54,  3.22it/s]
 60%|█████▉    | 222463/371472 [7:02:21<12:37:06,  3.28it/s]
 60%|█████▉    | 222464/371472 [7:02:21<12:20:42,  3.35it/s]
 60%|█████▉    | 222465/371472 [7:02:21<12:56:59,  3.20it/s]
 60%|█████▉    | 222466/371472 [7:02:21<12:34:24,  3.29it/s]
 60%|█████▉    | 222467/371472 [7:02:22<12:33:36,  3.30it/s]
 60%|█████▉    | 222468/371472 [7:02:22<14:27:46,  2.86it/s]
 60%|█████▉    | 222469/371472 [7:02:23<13:56:22,  2.97it/s]
 60%|█████▉    | 222470/371472 [7:02:23<13:11:29,  3.14it/s]
 60%|█████▉    | 222471/371472 [7:02:23<13:02:10,  3.17it/s]
 60%|█████▉    | 222472/371472 [7:02:23<12:36:27,  3.28it/s]
 60%|█████▉    | 222473/371472 [7:02:24<12:39:03,  3.27it/s]
 60%|█████▉    | 222474/371472 [7:02:24<12:27:33,  3.32it/s]
 60%|█████▉    | 222475/371472 [7:02:24<12:14:14,  3.38it/s]
 60%|█████▉    | 222476/371472 [7:02:25<11:58:42,  3.46it/s]
 60%|█████▉    | 222477/371472 [7:02:25<12:47:05,  3.24it/s]
 60%|█████▉    | 222478/371472 [7:02:25<12:29:32,  3.31it/s]
 60%|█████▉    | 222479/371472 [7:02:25<12:26:44,  3.33it/s]
 60%|█████▉    | 222480/371472 [7:02:26<12:58:42,  3.19it/s]
                                                            
{'loss': 2.7904, 'learning_rate': 4.611713245275701e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222480/371472 [7:02:26<12:58:42,  3.19it/s]
 60%|█████▉    | 222481/371472 [7:02:26<13:13:57,  3.13it/s]
 60%|█████▉    | 222482/371472 [7:02:26<12:48:42,  3.23it/s]
 60%|█████▉    | 222483/371472 [7:02:27<13:08:55,  3.15it/s]
 60%|█████▉    | 222484/371472 [7:02:27<12:56:12,  3.20it/s]
 60%|█████▉    | 222485/371472 [7:02:27<12:44:33,  3.25it/s]
 60%|█████▉    | 222486/371472 [7:02:28<12:35:31,  3.29it/s]
 60%|█████▉    | 222487/371472 [7:02:28<12:13:34,  3.38it/s]
 60%|█████▉    | 222488/371472 [7:02:28<13:03:13,  3.17it/s]
 60%|█████▉    | 222489/371472 [7:02:29<13:06:42,  3.16it/s]
 60%|█████▉    | 222490/371472 [7:02:29<12:32:57,  3.30it/s]
 60%|█████▉    | 222491/371472 [7:02:29<12:10:50,  3.40it/s]
 60%|█████▉    | 222492/371472 [7:02:30<12:43:33,  3.25it/s]
 60%|█████▉    | 222493/371472 [7:02:30<12:26:13,  3.33it/s]
 60%|█████▉    | 222494/371472 [7:02:30<12:17:36,  3.37it/s]
 60%|█████▉    | 222495/371472 [7:02:30<12:07:04,  3.41it/s]
 60%|█████▉    | 222496/371472 [7:02:31<12:11:12,  3.40it/s]
 60%|█████▉    | 222497/371472 [7:02:31<12:04:35,  3.43it/s]
 60%|█████▉    | 222498/371472 [7:02:31<12:09:00,  3.41it/s]
 60%|█████▉    | 222499/371472 [7:02:32<11:58:19,  3.46it/s]
 60%|█████▉    | 222500/371472 [7:02:32<12:03:33,  3.43it/s]
                                                            
{'loss': 2.6804, 'learning_rate': 4.6112284255209113e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222500/371472 [7:02:32<12:03:33,  3.43it/s]
 60%|█████▉    | 222501/371472 [7:02:32<12:10:57,  3.40it/s]
 60%|█████▉    | 222502/371472 [7:02:32<12:18:28,  3.36it/s]
 60%|█████▉    | 222503/371472 [7:02:33<12:33:15,  3.30it/s]
 60%|█████▉    | 222504/371472 [7:02:33<12:24:31,  3.33it/s]
 60%|█████▉    | 222505/371472 [7:02:33<13:07:49,  3.15it/s]
 60%|█████▉    | 222506/371472 [7:02:34<12:59:01,  3.19it/s]
 60%|█████▉    | 222507/371472 [7:02:34<13:01:49,  3.18it/s]
 60%|█████▉    | 222508/371472 [7:02:34<12:37:39,  3.28it/s]
 60%|█████▉    | 222509/371472 [7:02:35<13:11:18,  3.14it/s]
 60%|█████▉    | 222510/371472 [7:02:35<12:46:43,  3.24it/s]
 60%|█████▉    | 222511/371472 [7:02:35<12:20:00,  3.35it/s]
 60%|█████▉    | 222512/371472 [7:02:36<13:10:45,  3.14it/s]
 60%|█████▉    | 222513/371472 [7:02:36<13:12:13,  3.13it/s]
 60%|█████▉    | 222514/371472 [7:02:36<12:53:49,  3.21it/s]
 60%|█████▉    | 222515/371472 [7:02:36<12:33:08,  3.30it/s]
 60%|█████▉    | 222516/371472 [7:02:37<12:13:02,  3.39it/s]
 60%|█████▉    | 222517/371472 [7:02:37<12:14:28,  3.38it/s]
 60%|█████▉    | 222518/371472 [7:02:37<12:24:18,  3.34it/s]
 60%|█████▉    | 222519/371472 [7:02:38<12:25:12,  3.33it/s]
 60%|█████▉    | 222520/371472 [7:02:38<12:14:38,  3.38it/s]
                                                            
{'loss': 2.7771, 'learning_rate': 4.610743605766123e-07, 'epoch': 9.58}
+
 60%|█████▉    | 222520/371472 [7:02:38<12:14:38,  3.38it/s]
 60%|█████▉    | 222521/371472 [7:02:38<11:52:50,  3.48it/s]
 60%|█████▉    | 222522/371472 [7:02:39<11:59:20,  3.45it/s]
 60%|█████▉    | 222523/371472 [7:02:39<12:05:21,  3.42it/s]
 60%|█████▉    | 222524/371472 [7:02:39<11:49:11,  3.50it/s]
 60%|█████▉    | 222525/371472 [7:02:39<11:56:51,  3.46it/s]
 60%|█████▉    | 222526/371472 [7:02:40<12:26:08,  3.33it/s]
 60%|█████▉    | 222527/371472 [7:02:40<12:05:09,  3.42it/s]
 60%|█████▉    | 222528/371472 [7:02:40<12:04:58,  3.42it/s]
 60%|█████▉    | 222529/371472 [7:02:41<12:12:09,  3.39it/s]
 60%|█████▉    | 222530/371472 [7:02:41<12:39:55,  3.27it/s]
 60%|█████▉    | 222531/371472 [7:02:41<12:55:37,  3.20it/s]
 60%|█████▉    | 222532/371472 [7:02:42<12:51:48,  3.22it/s]
 60%|█████▉    | 222533/371472 [7:02:42<12:43:17,  3.25it/s]
 60%|█████▉    | 222534/371472 [7:02:42<12:26:57,  3.32it/s]
 60%|█████▉    | 222535/371472 [7:02:42<12:14:03,  3.38it/s]
 60%|█████▉    | 222536/371472 [7:02:43<12:18:08,  3.36it/s]
 60%|█████▉    | 222537/371472 [7:02:43<12:28:25,  3.32it/s]
 60%|█████▉    | 222538/371472 [7:02:43<12:26:07,  3.33it/s]
 60%|█████▉    | 222539/371472 [7:02:44<12:06:22,  3.42it/s]
 60%|█████▉    | 222540/371472 [7:02:44<11:45:35,  3.52it/s]
                                                            
{'loss': 2.8796, 'learning_rate': 4.610258786011334e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222540/371472 [7:02:44<11:45:35,  3.52it/s]
 60%|█████▉    | 222541/371472 [7:02:44<11:51:17,  3.49it/s]
 60%|█████▉    | 222542/371472 [7:02:44<11:52:52,  3.48it/s]
 60%|█████▉    | 222543/371472 [7:02:45<11:52:18,  3.48it/s]
 60%|█████▉    | 222544/371472 [7:02:45<12:30:46,  3.31it/s]
 60%|█████▉    | 222545/371472 [7:02:45<12:17:59,  3.36it/s]
 60%|█████▉    | 222546/371472 [7:02:46<11:56:53,  3.46it/s]
 60%|█████▉    | 222547/371472 [7:02:46<12:02:25,  3.44it/s]
 60%|█████▉    | 222548/371472 [7:02:46<11:59:59,  3.45it/s]
 60%|█████▉    | 222549/371472 [7:02:47<12:33:47,  3.29it/s]
 60%|█████▉    | 222550/371472 [7:02:47<12:20:42,  3.35it/s]
 60%|█████▉    | 222551/371472 [7:02:47<12:02:42,  3.43it/s]
 60%|█████▉    | 222552/371472 [7:02:47<11:59:13,  3.45it/s]
 60%|█████▉    | 222553/371472 [7:02:48<12:04:16,  3.43it/s]
 60%|█████▉    | 222554/371472 [7:02:48<12:04:03,  3.43it/s]
 60%|█████▉    | 222555/371472 [7:02:48<12:23:33,  3.34it/s]
 60%|█████▉    | 222556/371472 [7:02:49<11:53:07,  3.48it/s]
 60%|█████▉    | 222557/371472 [7:02:49<11:40:49,  3.54it/s]
 60%|█████▉    | 222558/371472 [7:02:49<12:11:32,  3.39it/s]
 60%|█████▉    | 222559/371472 [7:02:49<12:00:45,  3.44it/s]
 60%|█████▉    | 222560/371472 [7:02:50<13:19:20,  3.10it/s]
                                                            
{'loss': 2.6521, 'learning_rate': 4.609773966256545e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222560/371472 [7:02:50<13:19:20,  3.10it/s]
 60%|█████▉    | 222561/371472 [7:02:50<13:02:25,  3.17it/s]
 60%|█████▉    | 222562/371472 [7:02:50<12:24:56,  3.33it/s]
 60%|█████▉    | 222563/371472 [7:02:51<12:21:18,  3.35it/s]
 60%|█████▉    | 222564/371472 [7:02:51<12:23:32,  3.34it/s]
 60%|█████▉    | 222565/371472 [7:02:51<12:00:20,  3.45it/s]
 60%|█████▉    | 222566/371472 [7:02:52<11:46:13,  3.51it/s]
 60%|█████▉    | 222567/371472 [7:02:52<12:30:06,  3.31it/s]
 60%|█████▉    | 222568/371472 [7:02:52<14:35:27,  2.83it/s]
 60%|█████▉    | 222569/371472 [7:02:53<14:24:16,  2.87it/s]
 60%|█████▉    | 222570/371472 [7:02:53<13:34:12,  3.05it/s]
 60%|█████▉    | 222571/371472 [7:02:53<12:52:13,  3.21it/s]
 60%|█████▉    | 222572/371472 [7:02:53<12:28:40,  3.31it/s]
 60%|█████▉    | 222573/371472 [7:02:54<12:36:57,  3.28it/s]
 60%|█████▉    | 222574/371472 [7:02:54<12:17:29,  3.36it/s]
 60%|█████▉    | 222575/371472 [7:02:54<11:55:22,  3.47it/s]
 60%|█████▉    | 222576/371472 [7:02:55<12:42:19,  3.26it/s]
 60%|█████▉    | 222577/371472 [7:02:55<12:46:57,  3.24it/s]
 60%|█████▉    | 222578/371472 [7:02:55<12:45:12,  3.24it/s]
 60%|█████▉    | 222579/371472 [7:02:56<12:33:27,  3.29it/s]
 60%|█████▉    | 222580/371472 [7:02:56<12:04:45,  3.42it/s]
                                                            
{'loss': 2.858, 'learning_rate': 4.6092891465017557e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222580/371472 [7:02:56<12:04:45,  3.42it/s]
 60%|█████▉    | 222581/371472 [7:02:56<12:31:41,  3.30it/s]
 60%|█████▉    | 222582/371472 [7:02:56<12:08:44,  3.41it/s]
 60%|█████▉    | 222583/371472 [7:02:57<12:23:04,  3.34it/s]
 60%|█████▉    | 222584/371472 [7:02:57<11:53:32,  3.48it/s]
 60%|█████▉    | 222585/371472 [7:02:57<12:19:39,  3.35it/s]
 60%|█████▉    | 222586/371472 [7:02:58<13:51:02,  2.99it/s]
 60%|█████▉    | 222587/371472 [7:02:58<13:31:59,  3.06it/s]
 60%|█████▉    | 222588/371472 [7:02:58<13:05:01,  3.16it/s]
 60%|█████▉    | 222589/371472 [7:02:59<12:33:31,  3.29it/s]
 60%|█████▉    | 222590/371472 [7:02:59<12:40:22,  3.26it/s]
 60%|█████▉    | 222591/371472 [7:02:59<13:18:24,  3.11it/s]
 60%|█████▉    | 222592/371472 [7:03:00<12:43:48,  3.25it/s]
 60%|█████▉    | 222593/371472 [7:03:00<12:35:28,  3.28it/s]
 60%|█████▉    | 222594/371472 [7:03:00<12:20:32,  3.35it/s]
 60%|█████▉    | 222595/371472 [7:03:01<12:58:01,  3.19it/s]
 60%|█████▉    | 222596/371472 [7:03:01<13:10:13,  3.14it/s]
 60%|█████▉    | 222597/371472 [7:03:01<13:04:21,  3.16it/s]
 60%|█████▉    | 222598/371472 [7:03:02<13:02:24,  3.17it/s]
 60%|█████▉    | 222599/371472 [7:03:02<12:49:12,  3.23it/s]
 60%|█████▉    | 222600/371472 [7:03:02<12:47:04,  3.23it/s]
                                                            
{'loss': 2.6884, 'learning_rate': 4.6088043267469675e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222600/371472 [7:03:02<12:47:04,  3.23it/s]
 60%|█████▉    | 222601/371472 [7:03:02<12:41:16,  3.26it/s]
 60%|█████▉    | 222602/371472 [7:03:03<12:18:48,  3.36it/s]
 60%|█████▉    | 222603/371472 [7:03:03<12:18:54,  3.36it/s]
 60%|█████▉    | 222604/371472 [7:03:03<12:08:21,  3.41it/s]
 60%|█████▉    | 222605/371472 [7:03:04<12:03:02,  3.43it/s]
 60%|█████▉    | 222606/371472 [7:03:04<11:58:26,  3.45it/s]
 60%|█████▉    | 222607/371472 [7:03:04<13:14:52,  3.12it/s]
 60%|█████▉    | 222608/371472 [7:03:05<12:56:51,  3.19it/s]
 60%|█████▉    | 222609/371472 [7:03:05<12:42:57,  3.25it/s]
 60%|█████▉    | 222610/371472 [7:03:05<12:22:18,  3.34it/s]
 60%|█████▉    | 222611/371472 [7:03:05<12:45:44,  3.24it/s]
 60%|█████▉    | 222612/371472 [7:03:06<12:18:53,  3.36it/s]
 60%|█████▉    | 222613/371472 [7:03:06<12:05:52,  3.42it/s]
 60%|█████▉    | 222614/371472 [7:03:06<12:43:15,  3.25it/s]
 60%|█████▉    | 222615/371472 [7:03:07<12:26:17,  3.32it/s]
 60%|█████▉    | 222616/371472 [7:03:07<13:06:10,  3.16it/s]
 60%|█████▉    | 222617/371472 [7:03:07<13:02:34,  3.17it/s]
 60%|█████▉    | 222618/371472 [7:03:08<12:55:26,  3.20it/s]
 60%|█████▉    | 222619/371472 [7:03:08<12:47:05,  3.23it/s]
 60%|█████▉    | 222620/371472 [7:03:08<13:10:29,  3.14it/s]
                                                            
{'loss': 2.8, 'learning_rate': 4.608319506992178e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222620/371472 [7:03:08<13:10:29,  3.14it/s]
 60%|█████▉    | 222621/371472 [7:03:09<13:04:05,  3.16it/s]
 60%|█████▉    | 222622/371472 [7:03:09<12:35:46,  3.28it/s]
 60%|█████▉    | 222623/371472 [7:03:09<13:12:29,  3.13it/s]
 60%|█████▉    | 222624/371472 [7:03:10<13:30:08,  3.06it/s]
 60%|█████▉    | 222625/371472 [7:03:10<12:47:32,  3.23it/s]
 60%|█████▉    | 222626/371472 [7:03:10<12:33:11,  3.29it/s]
 60%|█████▉    | 222627/371472 [7:03:10<12:29:53,  3.31it/s]
 60%|█████▉    | 222628/371472 [7:03:11<12:20:09,  3.35it/s]
 60%|█████▉    | 222629/371472 [7:03:11<12:05:32,  3.42it/s]
 60%|█████▉    | 222630/371472 [7:03:11<11:54:14,  3.47it/s]
 60%|█████▉    | 222631/371472 [7:03:11<11:47:01,  3.51it/s]
 60%|█████▉    | 222632/371472 [7:03:12<11:46:36,  3.51it/s]
 60%|█████▉    | 222633/371472 [7:03:12<11:45:09,  3.52it/s]
 60%|█████▉    | 222634/371472 [7:03:12<11:56:40,  3.46it/s]
 60%|█████▉    | 222635/371472 [7:03:13<11:48:32,  3.50it/s]
 60%|█████▉    | 222636/371472 [7:03:13<11:59:30,  3.45it/s]
 60%|█████▉    | 222637/371472 [7:03:13<11:46:23,  3.51it/s]
 60%|█████▉    | 222638/371472 [7:03:13<11:44:03,  3.52it/s]
 60%|█████▉    | 222639/371472 [7:03:14<11:47:09,  3.51it/s]
 60%|█████▉    | 222640/371472 [7:03:14<11:58:49,  3.45it/s]
                                                            
{'loss': 2.8533, 'learning_rate': 4.6078346872373895e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222640/371472 [7:03:14<11:58:49,  3.45it/s]
 60%|█████▉    | 222641/371472 [7:03:14<11:46:27,  3.51it/s]
 60%|█████▉    | 222642/371472 [7:03:15<11:51:05,  3.49it/s]
 60%|█████▉    | 222643/371472 [7:03:15<12:03:07,  3.43it/s]
 60%|█████▉    | 222644/371472 [7:03:15<12:51:39,  3.21it/s]
 60%|█████▉    | 222645/371472 [7:03:16<12:37:25,  3.27it/s]
 60%|█████▉    | 222646/371472 [7:03:16<12:14:29,  3.38it/s]
 60%|█████▉    | 222647/371472 [7:03:16<12:06:40,  3.41it/s]
 60%|█████▉    | 222648/371472 [7:03:16<12:14:36,  3.38it/s]
 60%|█████▉    | 222649/371472 [7:03:17<12:15:52,  3.37it/s]
 60%|█████▉    | 222650/371472 [7:03:17<12:37:41,  3.27it/s]
 60%|█████▉    | 222651/371472 [7:03:17<12:24:02,  3.33it/s]
 60%|█████▉    | 222652/371472 [7:03:18<12:29:51,  3.31it/s]
 60%|█████▉    | 222653/371472 [7:03:18<14:19:37,  2.89it/s]
 60%|█████▉    | 222654/371472 [7:03:18<14:25:43,  2.86it/s]
 60%|█████▉    | 222655/371472 [7:03:19<13:40:42,  3.02it/s]
 60%|█████▉    | 222656/371472 [7:03:19<13:45:34,  3.00it/s]
 60%|█████▉    | 222657/371472 [7:03:19<13:33:30,  3.05it/s]
 60%|█████▉    | 222658/371472 [7:03:20<13:17:05,  3.11it/s]
 60%|█████▉    | 222659/371472 [7:03:20<12:55:11,  3.20it/s]
 60%|█████▉    | 222660/371472 [7:03:20<12:47:13,  3.23it/s]
                                                            
{'loss': 2.6732, 'learning_rate': 4.6073498674826e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222660/371472 [7:03:20<12:47:13,  3.23it/s]
 60%|█████▉    | 222661/371472 [7:03:21<13:22:28,  3.09it/s]
 60%|█████▉    | 222662/371472 [7:03:21<13:09:42,  3.14it/s]
 60%|█████▉    | 222663/371472 [7:03:21<12:37:01,  3.28it/s]
 60%|█████▉    | 222664/371472 [7:03:22<12:35:59,  3.28it/s]
 60%|█████▉    | 222665/371472 [7:03:22<12:13:15,  3.38it/s]
 60%|█████▉    | 222666/371472 [7:03:22<12:12:50,  3.38it/s]
 60%|█████▉    | 222667/371472 [7:03:22<12:00:06,  3.44it/s]
 60%|█████▉    | 222668/371472 [7:03:23<12:19:02,  3.36it/s]
 60%|█████▉    | 222669/371472 [7:03:23<12:20:45,  3.35it/s]
 60%|█████▉    | 222670/371472 [7:03:23<12:11:19,  3.39it/s]
 60%|█████▉    | 222671/371472 [7:03:24<11:54:01,  3.47it/s]
 60%|█████▉    | 222672/371472 [7:03:24<12:00:57,  3.44it/s]
 60%|█████▉    | 222673/371472 [7:03:24<12:14:59,  3.37it/s]
 60%|█████▉    | 222674/371472 [7:03:24<12:09:48,  3.40it/s]
 60%|█████▉    | 222675/371472 [7:03:25<12:12:07,  3.39it/s]
 60%|█████▉    | 222676/371472 [7:03:25<12:07:09,  3.41it/s]
 60%|█████▉    | 222677/371472 [7:03:25<12:00:35,  3.44it/s]
 60%|█████▉    | 222678/371472 [7:03:26<12:04:39,  3.42it/s]
 60%|████���▉    | 222679/371472 [7:03:26<12:08:22,  3.40it/s]
 60%|█████▉    | 222680/371472 [7:03:26<11:51:23,  3.49it/s]
                                                            
{'loss': 2.7219, 'learning_rate': 4.606865047727812e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222680/371472 [7:03:26<11:51:23,  3.49it/s]
 60%|█████▉    | 222681/371472 [7:03:27<12:20:15,  3.35it/s]
 60%|█████▉    | 222682/371472 [7:03:27<12:30:40,  3.30it/s]
 60%|█████▉    | 222683/371472 [7:03:27<11:58:07,  3.45it/s]
 60%|█████▉    | 222684/371472 [7:03:27<12:10:23,  3.40it/s]
 60%|█████▉    | 222685/371472 [7:03:28<12:16:14,  3.37it/s]
 60%|█████▉    | 222686/371472 [7:03:28<12:29:08,  3.31it/s]
 60%|█████▉    | 222687/371472 [7:03:28<12:59:46,  3.18it/s]
 60%|█████▉    | 222688/371472 [7:03:29<12:47:35,  3.23it/s]
 60%|█████▉    | 222689/371472 [7:03:29<12:45:36,  3.24it/s]
 60%|█████▉    | 222690/371472 [7:03:29<12:29:54,  3.31it/s]
 60%|█████▉    | 222691/371472 [7:03:30<12:15:14,  3.37it/s]
 60%|█████▉    | 222692/371472 [7:03:30<13:12:53,  3.13it/s]
 60%|█████▉    | 222693/371472 [7:03:30<13:03:55,  3.16it/s]
 60%|█████▉    | 222694/371472 [7:03:31<12:39:12,  3.27it/s]
 60%|█████▉    | 222695/371472 [7:03:31<12:17:22,  3.36it/s]
 60%|█████▉    | 222696/371472 [7:03:31<12:33:29,  3.29it/s]
 60%|█████▉    | 222697/371472 [7:03:31<12:38:07,  3.27it/s]
 60%|█████▉    | 222698/371472 [7:03:32<12:18:07,  3.36it/s]
 60%|█████▉    | 222699/371472 [7:03:32<12:22:25,  3.34it/s]
 60%|█████▉    | 222700/371472 [7:03:32<12:14:13,  3.38it/s]
                                                            
{'loss': 2.6791, 'learning_rate': 4.6063802279730227e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222700/371472 [7:03:32<12:14:13,  3.38it/s]
 60%|█████▉    | 222701/371472 [7:03:33<12:41:51,  3.25it/s]
 60%|█████▉    | 222702/371472 [7:03:33<12:48:57,  3.22it/s]
 60%|█████▉    | 222703/371472 [7:03:33<13:05:28,  3.16it/s]
 60%|█████▉    | 222704/371472 [7:03:34<12:45:07,  3.24it/s]
 60%|█████▉    | 222705/371472 [7:03:34<12:18:34,  3.36it/s]
 60%|█████▉    | 222706/371472 [7:03:34<12:15:03,  3.37it/s]
 60%|█████▉    | 222707/371472 [7:03:34<11:54:49,  3.47it/s]
 60%|█████▉    | 222708/371472 [7:03:35<11:56:46,  3.46it/s]
 60%|█████▉    | 222709/371472 [7:03:35<12:11:56,  3.39it/s]
 60%|█████▉    | 222710/371472 [7:03:35<12:39:38,  3.26it/s]
 60%|█████▉    | 222711/371472 [7:03:36<12:43:14,  3.25it/s]
 60%|█████▉    | 222712/371472 [7:03:36<12:37:32,  3.27it/s]
 60%|█████▉    | 222713/371472 [7:03:36<12:34:55,  3.28it/s]
 60%|█████▉    | 222714/371472 [7:03:37<12:35:50,  3.28it/s]
 60%|█████▉    | 222715/371472 [7:03:37<12:37:08,  3.27it/s]
 60%|█████▉    | 222716/371472 [7:03:37<12:26:19,  3.32it/s]
 60%|█████▉    | 222717/371472 [7:03:38<13:44:38,  3.01it/s]
 60%|█████▉    | 222718/371472 [7:03:38<13:09:45,  3.14it/s]
 60%|█████▉    | 222719/371472 [7:03:38<12:57:09,  3.19it/s]
 60%|█████▉    | 222720/371472 [7:03:38<12:29:25,  3.31it/s]
                                                            
{'loss': 2.8623, 'learning_rate': 4.605895408218233e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222720/371472 [7:03:38<12:29:25,  3.31it/s]
 60%|█████▉    | 222721/371472 [7:03:39<12:21:57,  3.34it/s]
 60%|█████▉    | 222722/371472 [7:03:39<12:10:40,  3.39it/s]
 60%|█████▉    | 222723/371472 [7:03:39<12:09:54,  3.40it/s]
 60%|█████▉    | 222724/371472 [7:03:40<12:06:12,  3.41it/s]
 60%|█████▉    | 222725/371472 [7:03:40<12:40:25,  3.26it/s]
 60%|█████▉    | 222726/371472 [7:03:40<12:43:25,  3.25it/s]
 60%|█████▉    | 222727/371472 [7:03:41<12:41:36,  3.26it/s]
 60%|█████▉    | 222728/371472 [7:03:41<12:33:38,  3.29it/s]
 60%|█████▉    | 222729/371472 [7:03:41<12:09:01,  3.40it/s]
 60%|█████▉    | 222730/371472 [7:03:41<12:04:17,  3.42it/s]
 60%|█████▉    | 222731/371472 [7:03:42<11:55:43,  3.46it/s]
 60%|█████▉    | 222732/371472 [7:03:42<12:25:08,  3.33it/s]
 60%|█████▉    | 222733/371472 [7:03:42<12:48:28,  3.23it/s]
 60%|█████▉    | 222734/371472 [7:03:43<12:33:43,  3.29it/s]
 60%|█████▉    | 222735/371472 [7:03:43<13:04:40,  3.16it/s]
 60%|█████▉    | 222736/371472 [7:03:43<13:01:51,  3.17it/s]
 60%|█████▉    | 222737/371472 [7:03:44<13:42:53,  3.01it/s]
 60%|█████▉    | 222738/371472 [7:03:44<13:02:58,  3.17it/s]
 60%|█████▉    | 222739/371472 [7:03:44<12:50:19,  3.22it/s]
 60%|█████▉    | 222740/371472 [7:03:45<13:18:28,  3.10it/s]
                                                            
{'loss': 2.7245, 'learning_rate': 4.6054105884634446e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222740/371472 [7:03:45<13:18:28,  3.10it/s]
 60%|█████▉    | 222741/371472 [7:03:45<13:03:13,  3.16it/s]
 60%|█████▉    | 222742/371472 [7:03:45<12:49:23,  3.22it/s]
 60%|█████▉    | 222743/371472 [7:03:46<13:04:06,  3.16it/s]
 60%|█████▉    | 222744/371472 [7:03:46<12:43:30,  3.25it/s]
 60%|█████▉    | 222745/371472 [7:03:46<12:40:02,  3.26it/s]
 60%|█████▉    | 222746/371472 [7:03:46<12:22:13,  3.34it/s]
 60%|█████▉    | 222747/371472 [7:03:47<12:23:18,  3.33it/s]
 60%|█████▉    | 222748/371472 [7:03:47<11:53:03,  3.48it/s]
 60%|█████▉    | 222749/371472 [7:03:47<11:57:18,  3.46it/s]
 60%|█████▉    | 222750/371472 [7:03:48<12:32:46,  3.29it/s]
 60%|█████▉    | 222751/371472 [7:03:48<12:21:37,  3.34it/s]
 60%|█████▉    | 222752/371472 [7:03:48<12:14:17,  3.38it/s]
 60%|█████▉    | 222753/371472 [7:03:48<11:52:56,  3.48it/s]
 60%|█████▉    | 222754/371472 [7:03:49<11:39:18,  3.54it/s]
 60%|█████▉    | 222755/371472 [7:03:49<11:42:11,  3.53it/s]
 60%|█████▉    | 222756/371472 [7:03:49<11:39:45,  3.54it/s]
 60%|█████▉    | 222757/371472 [7:03:50<11:28:02,  3.60it/s]
 60%|█████▉    | 222758/371472 [7:03:50<11:15:24,  3.67it/s]
 60%|█████▉    | 222759/371472 [7:03:50<12:04:14,  3.42it/s]
 60%|█████▉    | 222760/371472 [7:03:50<12:10:12,  3.39it/s]
                                                            
{'loss': 2.64, 'learning_rate': 4.604925768708655e-07, 'epoch': 9.59}
+
 60%|█████▉    | 222760/371472 [7:03:50<12:10:12,  3.39it/s]
 60%|█████▉    | 222761/371472 [7:03:51<12:14:36,  3.37it/s]
 60%|█████▉    | 222762/371472 [7:03:51<12:24:40,  3.33it/s]
 60%|█████▉    | 222763/371472 [7:03:51<12:48:47,  3.22it/s]
 60%|█████▉    | 222764/371472 [7:03:52<12:35:22,  3.28it/s]
 60%|█████▉    | 222765/371472 [7:03:52<12:46:06,  3.24it/s]
 60%|█████▉    | 222766/371472 [7:03:52<12:05:27,  3.42it/s]
 60%|█████▉    | 222767/371472 [7:03:53<11:58:44,  3.45it/s]
 60%|█████▉    | 222768/371472 [7:03:53<11:55:27,  3.46it/s]
 60%|█████▉    | 222769/371472 [7:03:53<11:47:28,  3.50it/s]
 60%|█████▉    | 222770/371472 [7:03:53<12:13:56,  3.38it/s]
 60%|█████▉    | 222771/371472 [7:03:54<12:33:08,  3.29it/s]
 60%|█████▉    | 222772/371472 [7:03:54<14:22:07,  2.87it/s]
 60%|█████▉    | 222773/371472 [7:03:54<13:33:42,  3.05it/s]
 60%|█████▉    | 222774/371472 [7:03:55<13:02:30,  3.17it/s]
 60%|█████▉    | 222775/371472 [7:03:55<12:40:18,  3.26it/s]
 60%|█████▉    | 222776/371472 [7:03:55<13:01:20,  3.17it/s]
 60%|█████▉    | 222777/371472 [7:03:56<12:36:45,  3.27it/s]
 60%|█████▉    | 222778/371472 [7:03:56<12:56:47,  3.19it/s]
 60%|█████▉    | 222779/371472 [7:03:56<12:27:46,  3.31it/s]
 60%|█████▉    | 222780/371472 [7:03:57<12:16:50,  3.36it/s]
                                                            
{'loss': 2.7437, 'learning_rate': 4.6044409489538666e-07, 'epoch': 9.6}
+
 60%|█████▉    | 222780/371472 [7:03:57<12:16:50,  3.36it/s]
 60%|█████▉    | 222781/371472 [7:03:57<12:12:47,  3.38it/s]
 60%|█████▉    | 222782/371472 [7:03:57<11:50:56,  3.49it/s]
 60%|█████▉    | 222783/371472 [7:03:57<11:58:37,  3.45it/s]
 60%|█████▉    | 222784/371472 [7:03:58<12:01:07,  3.44it/s]
 60%|█████▉    | 222785/371472 [7:03:58<12:06:25,  3.41it/s]
 60%|█████▉    | 222786/371472 [7:03:58<12:03:45,  3.42it/s]
 60%|█████▉    | 222787/371472 [7:03:59<12:08:52,  3.40it/s]
 60%|█████▉    | 222788/371472 [7:03:59<12:15:14,  3.37it/s]
 60%|█████▉    | 222789/371472 [7:03:59<12:09:12,  3.40it/s]
 60%|█████▉    | 222790/371472 [7:03:59<12:08:58,  3.40it/s]
 60%|█████▉    | 222791/371472 [7:04:00<12:24:33,  3.33it/s]
 60%|█████▉    | 222792/371472 [7:04:00<12:12:03,  3.38it/s]
 60%|█████▉    | 222793/371472 [7:04:00<12:13:02,  3.38it/s]
 60%|█████▉    | 222794/371472 [7:04:01<12:17:16,  3.36it/s]
 60%|█████▉    | 222795/371472 [7:04:01<12:24:23,  3.33it/s]
 60%|█████▉    | 222796/371472 [7:04:01<13:15:31,  3.11it/s]
 60%|█████▉    | 222797/371472 [7:04:02<12:58:22,  3.18it/s]
 60%|█████▉    | 222798/371472 [7:04:02<12:33:03,  3.29it/s]
 60%|█████▉    | 222799/371472 [7:04:02<12:18:37,  3.35it/s]
 60%|█████▉    | 222800/371472 [7:04:02<12:19:32,  3.35it/s]
                                                            
{'loss': 2.7288, 'learning_rate': 4.6039561291990773e-07, 'epoch': 9.6}
+
 60%|█████▉    | 222800/371472 [7:04:02<12:19:32,  3.35it/s]
 60%|█████▉    | 222801/371472 [7:04:03<12:12:53,  3.38it/s]
 60%|█████▉    | 222802/371472 [7:04:03<11:49:52,  3.49it/s]
 60%|█████▉    | 222803/371472 [7:04:03<11:28:13,  3.60it/s]
 60%|█████▉    | 222804/371472 [7:04:04<11:26:04,  3.61it/s]
 60%|█████▉    | 222805/371472 [7:04:04<12:27:37,  3.31it/s]
 60%|█████▉    | 222806/371472 [7:04:04<12:24:16,  3.33it/s]
 60%|█████▉    | 222807/371472 [7:04:05<12:17:52,  3.36it/s]
 60%|█████▉    | 222808/371472 [7:04:05<12:30:21,  3.30it/s]
 60%|█████▉    | 222809/371472 [7:04:05<12:29:31,  3.31it/s]
 60%|█████▉    | 222810/371472 [7:04:05<12:16:05,  3.37it/s]
 60%|█████▉    | 222811/371472 [7:04:06<11:57:44,  3.45it/s]
 60%|█████▉    | 222812/371472 [7:04:06<11:52:30,  3.48it/s]
 60%|█████▉    | 222813/371472 [7:04:06<12:24:49,  3.33it/s]
 60%|█████▉    | 222814/371472 [7:04:07<12:15:16,  3.37it/s]
 60%|█████▉    | 222815/371472 [7:04:07<12:14:54,  3.37it/s]
 60%|█████▉    | 222816/371472 [7:04:07<12:31:57,  3.29it/s]
 60%|█████▉    | 222817/371472 [7:04:08<13:08:36,  3.14it/s]
 60%|█████▉    | 222818/371472 [7:04:08<13:10:50,  3.13it/s]
 60%|█████▉    | 222819/371472 [7:04:08<12:31:52,  3.30it/s]
 60%|█████▉    | 222820/371472 [7:04:08<12:23:34,  3.33it/s]
                                                            
{'loss': 2.8061, 'learning_rate': 4.6034713094442885e-07, 'epoch': 9.6}
+
 60%|█████▉    | 222820/371472 [7:04:08<12:23:34,  3.33it/s]
 60%|█████▉    | 222821/371472 [7:04:09<12:40:18,  3.26it/s]
 60%|█████▉    | 222822/371472 [7:04:09<12:39:04,  3.26it/s]
 60%|█████▉    | 222823/371472 [7:04:09<12:27:11,  3.32it/s]
 60%|█████▉    | 222824/371472 [7:04:10<12:49:28,  3.22it/s]
 60%|█████▉    | 222825/371472 [7:04:10<12:59:27,  3.18it/s]
 60%|█████▉    | 222826/371472 [7:04:10<12:53:19,  3.20it/s]
 60%|█████▉    | 222827/371472 [7:04:11<13:02:53,  3.16it/s]
 60%|█████▉    | 222828/371472 [7:04:11<13:05:24,  3.15it/s]
 60%|█████▉    | 222829/371472 [7:04:11<12:29:48,  3.30it/s]
 60%|█████▉    | 222830/371472 [7:04:12<12:18:06,  3.36it/s]
 60%|█████▉    | 222831/371472 [7:04:12<12:36:58,  3.27it/s]
 60%|█████▉    | 222832/371472 [7:04:12<12:54:15,  3.20it/s]
 60%|█████▉    | 222833/371472 [7:04:12<12:34:51,  3.28it/s]
 60%|█████▉    | 222834/371472 [7:04:13<12:23:35,  3.33it/s]
 60%|█████▉    | 222835/371472 [7:04:13<12:20:13,  3.35it/s]
 60%|█████▉    | 222836/371472 [7:04:13<12:32:34,  3.29it/s]
 60%|█████▉    | 222837/371472 [7:04:14<12:06:39,  3.41it/s]
 60%|█████▉    | 222838/371472 [7:04:14<12:47:56,  3.23it/s]
 60%|█████▉    | 222839/371472 [7:04:14<12:41:54,  3.25it/s]
 60%|█████▉    | 222840/371472 [7:04:15<12:44:00,  3.24it/s]
                                                            
{'loss': 2.8817, 'learning_rate': 4.602986489689499e-07, 'epoch': 9.6}
+
 60%|█████▉    | 222840/371472 [7:04:15<12:44:00,  3.24it/s]
 60%|█████▉    | 222841/371472 [7:04:15<12:29:13,  3.31it/s]
 60%|█████▉    | 222842/371472 [7:04:15<12:23:57,  3.33it/s]
 60%|█████▉    | 222843/371472 [7:04:16<12:38:27,  3.27it/s]
 60%|█████▉    | 222844/371472 [7:04:16<12:32:40,  3.29it/s]
 60%|█████▉    | 222845/371472 [7:04:16<12:15:55,  3.37it/s]
 60%|█████▉    | 222846/371472 [7:04:16<12:54:52,  3.20it/s]
 60%|█████▉    | 222847/371472 [7:04:17<13:03:01,  3.16it/s]
 60%|█████▉    | 222848/371472 [7:04:17<12:54:08,  3.20it/s]
 60%|█████▉    | 222849/371472 [7:04:17<12:40:53,  3.26it/s]
 60%|█████▉    | 222850/371472 [7:04:18<12:49:52,  3.22it/s]
 60%|█████▉    | 222851/371472 [7:04:18<12:22:00,  3.34it/s]
 60%|█████▉    | 222852/371472 [7:04:18<12:03:06,  3.43it/s]
 60%|█████▉    | 222853/371472 [7:04:19<12:03:40,  3.42it/s]
 60%|█████▉    | 222854/371472 [7:04:19<11:59:34,  3.44it/s]
 60%|█████▉    | 222855/371472 [7:04:19<11:58:14,  3.45it/s]
 60%|█████▉    | 222856/371472 [7:04:19<12:07:20,  3.41it/s]
 60%|█████▉    | 222857/371472 [7:04:20<12:40:12,  3.26it/s]
 60%|█████▉    | 222858/371472 [7:04:20<13:23:40,  3.08it/s]
 60%|█████▉    | 222859/371472 [7:04:20<12:57:03,  3.19it/s]
 60%|█████▉    | 222860/371472 [7:04:21<12:50:07,  3.22it/s]
                                                            
{'loss': 2.6967, 'learning_rate': 4.602501669934711e-07, 'epoch': 9.6}
+
 60%|█████▉    | 222860/371472 [7:04:21<12:50:07,  3.22it/s]
 60%|█████▉    | 222861/371472 [7:04:21<13:00:11,  3.17it/s]
 60%|█████▉    | 222862/371472 [7:04:21<13:02:40,  3.16it/s]
 60%|█████▉    | 222863/371472 [7:04:22<12:46:23,  3.23it/s]
 60%|█████▉    | 222864/371472 [7:04:22<12:28:57,  3.31it/s]
 60%|█████▉    | 222865/371472 [7:04:22<12:35:51,  3.28it/s]
 60%|█████▉    | 222866/371472 [7:04:23<12:48:49,  3.22it/s]
 60%|█████▉    | 222867/371472 [7:04:23<12:32:03,  3.29it/s]
 60%|█████▉    | 222868/371472 [7:04:23<12:06:19,  3.41it/s]
 60%|█████▉    | 222869/371472 [7:04:23<12:11:19,  3.39it/s]
 60%|█████▉    | 222870/371472 [7:04:24<11:56:18,  3.46it/s]
 60%|█████▉    | 222871/371472 [7:04:24<11:52:30,  3.48it/s]
 60%|█████▉    | 222872/371472 [7:04:24<12:03:09,  3.42it/s]
 60%|█████▉    | 222873/371472 [7:04:25<12:31:25,  3.30it/s]
 60%|█████▉    | 222874/371472 [7:04:25<12:05:40,  3.41it/s]
 60%|█████▉    | 222875/371472 [7:04:25<11:45:44,  3.51it/s]
 60%|█████▉    | 222876/371472 [7:04:25<11:39:23,  3.54it/s]
 60%|█████▉    | 222877/371472 [7:04:26<11:38:54,  3.54it/s]
 60%|█████▉    | 222878/371472 [7:04:26<11:59:41,  3.44it/s]
 60%|█████▉    | 222879/371472 [7:04:26<12:12:00,  3.38it/s]
 60%|█████▉    | 222880/371472 [7:04:27<12:02:56,  3.43it/s]
                                                            
{'loss': 2.8687, 'learning_rate': 4.602016850179922e-07, 'epoch': 9.6}
+
 60%|█████▉    | 222880/371472 [7:04:27<12:02:56,  3.43it/s]
 60%|█████▉    | 222881/371472 [7:04:27<11:45:59,  3.51it/s]
 60%|█████▉    | 222882/371472 [7:04:27<12:18:58,  3.35it/s]
 60%|█████▉    | 222883/371472 [7:04:28<12:40:12,  3.26it/s]
 60%|██████    | 222884/371472 [7:04:28<12:23:17,  3.33it/s]
 60%|██████    | 222885/371472 [7:04:28<12:34:51,  3.28it/s]
 60%|██████    | 222886/371472 [7:04:28<13:06:26,  3.15it/s]
 60%|██████    | 222887/371472 [7:04:29<13:08:58,  3.14it/s]
 60%|██████    | 222888/371472 [7:04:29<12:45:54,  3.23it/s]
 60%|██████    | 222889/371472 [7:04:30<14:40:51,  2.81it/s]
 60%|██████    | 222890/371472 [7:04:30<13:40:17,  3.02it/s]
 60%|██████    | 222891/371472 [7:04:30<13:09:44,  3.14it/s]
 60%|██████    | 222892/371472 [7:04:30<12:42:08,  3.25it/s]
 60%|██████    | 222893/371472 [7:04:31<12:42:08,  3.25it/s]
 60%|██████    | 222894/371472 [7:04:31<12:39:40,  3.26it/s]
 60%|██████    | 222895/371472 [7:04:31<12:26:59,  3.32it/s]
 60%|██████    | 222896/371472 [7:04:32<12:01:09,  3.43it/s]
 60%|██████    | 222897/371472 [7:04:32<11:59:18,  3.44it/s]
 60%|██████    | 222898/371472 [7:04:32<12:05:17,  3.41it/s]
 60%|██████    | 222899/371472 [7:04:32<12:00:29,  3.44it/s]
 60%|██████    | 222900/371472 [7:04:33<12:16:25,  3.36it/s]
                                                            
{'loss': 2.956, 'learning_rate': 4.601532030425133e-07, 'epoch': 9.6}
+
 60%|██████    | 222900/371472 [7:04:33<12:16:25,  3.36it/s]
 60%|██████    | 222901/371472 [7:04:33<12:15:28,  3.37it/s]
 60%|██████    | 222902/371472 [7:04:33<12:19:52,  3.35it/s]
 60%|██████    | 222903/371472 [7:04:34<12:08:12,  3.40it/s]
 60%|██████    | 222904/371472 [7:04:34<12:20:49,  3.34it/s]
 60%|██████    | 222905/371472 [7:04:34<13:26:56,  3.07it/s]
 60%|██████    | 222906/371472 [7:04:35<12:46:59,  3.23it/s]
 60%|██████    | 222907/371472 [7:04:35<12:44:14,  3.24it/s]
 60%|██████    | 222908/371472 [7:04:35<12:27:50,  3.31it/s]
 60%|██████    | 222909/371472 [7:04:35<12:08:16,  3.40it/s]
 60%|██████    | 222910/371472 [7:04:36<12:44:43,  3.24it/s]
 60%|██████    | 222911/371472 [7:04:36<12:45:29,  3.23it/s]
 60%|██████    | 222912/371472 [7:04:36<12:50:47,  3.21it/s]
 60%|██████    | 222913/371472 [7:04:37<13:04:20,  3.16it/s]
 60%|██████    | 222914/371472 [7:04:37<12:28:54,  3.31it/s]
 60%|██████    | 222915/371472 [7:04:37<13:02:53,  3.16it/s]
 60%|██████    | 222916/371472 [7:04:38<12:42:36,  3.25it/s]
 60%|██████    | 222917/371472 [7:04:38<12:20:42,  3.34it/s]
 60%|██████    | 222918/371472 [7:04:38<12:09:58,  3.39it/s]
 60%|██████    | 222919/371472 [7:04:39<12:37:40,  3.27it/s]
 60%|██████    | 222920/371472 [7:04:39<12:28:41,  3.31it/s]
                                                            
{'loss': 2.801, 'learning_rate': 4.6010472106703437e-07, 'epoch': 9.6}
+
 60%|██████    | 222920/371472 [7:04:39<12:28:41,  3.31it/s]
 60%|██████    | 222921/371472 [7:04:39<12:33:11,  3.29it/s]
 60%|██████    | 222922/371472 [7:04:40<13:49:09,  2.99it/s]
 60%|██████    | 222923/371472 [7:04:40<13:28:06,  3.06it/s]
 60%|██████    | 222924/371472 [7:04:40<13:43:15,  3.01it/s]
 60%|██████    | 222925/371472 [7:04:41<13:16:04,  3.11it/s]
 60%|██████    | 222926/371472 [7:04:41<12:41:08,  3.25it/s]
 60%|██████    | 222927/371472 [7:04:41<12:26:32,  3.32it/s]
 60%|██████    | 222928/371472 [7:04:41<12:09:10,  3.40it/s]
 60%|██████    | 222929/371472 [7:04:42<14:28:54,  2.85it/s]
 60%|██████    | 222930/371472 [7:04:42<13:53:42,  2.97it/s]
 60%|██████    | 222931/371472 [7:04:42<13:29:13,  3.06it/s]
 60%|██████    | 222932/371472 [7:04:43<13:23:34,  3.08it/s]
 60%|██████    | 222933/371472 [7:04:43<13:02:35,  3.16it/s]
 60%|██████    | 222934/371472 [7:04:43<13:04:29,  3.16it/s]
 60%|██████    | 222935/371472 [7:04:44<12:57:13,  3.19it/s]
 60%|██████    | 222936/371472 [7:04:44<13:56:01,  2.96it/s]
 60%|██████    | 222937/371472 [7:04:44<13:37:11,  3.03it/s]
 60%|██████    | 222938/371472 [7:04:45<13:00:00,  3.17it/s]
 60%|██████    | 222939/371472 [7:04:45<12:35:35,  3.28it/s]
 60%|██████    | 222940/371472 [7:04:45<12:12:34,  3.38it/s]
                                                            
{'loss': 2.7654, 'learning_rate': 4.600562390915555e-07, 'epoch': 9.6}
+
 60%|██████    | 222940/371472 [7:04:45<12:12:34,  3.38it/s]
 60%|██████    | 222941/371472 [7:04:46<12:04:57,  3.41it/s]
 60%|██████    | 222942/371472 [7:04:46<11:45:59,  3.51it/s]
 60%|██████    | 222943/371472 [7:04:46<11:39:03,  3.54it/s]
 60%|██████    | 222944/371472 [7:04:46<11:51:18,  3.48it/s]
 60%|██████    | 222945/371472 [7:04:47<12:01:18,  3.43it/s]
 60%|██████    | 222946/371472 [7:04:47<11:51:38,  3.48it/s]
 60%|██████    | 222947/371472 [7:04:47<11:34:09,  3.57it/s]
 60%|██████    | 222948/371472 [7:04:48<12:16:09,  3.36it/s]
 60%|██████    | 222949/371472 [7:04:48<12:07:09,  3.40it/s]
 60%|██████    | 222950/371472 [7:04:48<11:44:14,  3.51it/s]
 60%|██████    | 222951/371472 [7:04:48<11:32:11,  3.58it/s]
 60%|██████    | 222952/371472 [7:04:49<11:47:39,  3.50it/s]
 60%|██████    | 222953/371472 [7:04:49<11:54:24,  3.46it/s]
 60%|██████    | 222954/371472 [7:04:49<11:48:43,  3.49it/s]
 60%|██████    | 222955/371472 [7:04:50<12:06:23,  3.41it/s]
 60%|██████    | 222956/371472 [7:04:50<11:52:24,  3.47it/s]
 60%|██████    | 222957/371472 [7:04:50<11:39:46,  3.54it/s]
 60%|██████    | 222958/371472 [7:04:50<12:15:59,  3.36it/s]
 60%|██████    | 222959/371472 [7:04:51<12:09:31,  3.39it/s]
 60%|██████    | 222960/371472 [7:04:51<12:12:57,  3.38it/s]
                                                            
{'loss': 2.7122, 'learning_rate': 4.6000775711607657e-07, 'epoch': 9.6}
+
 60%|██████    | 222960/371472 [7:04:51<12:12:57,  3.38it/s]
 60%|██████    | 222961/371472 [7:04:51<12:30:24,  3.30it/s]
 60%|██████    | 222962/371472 [7:04:52<12:57:03,  3.19it/s]
 60%|██████    | 222963/371472 [7:04:52<13:00:46,  3.17it/s]
 60%|██████    | 222964/371472 [7:04:52<12:26:18,  3.32it/s]
 60%|██████    | 222965/371472 [7:04:53<12:20:41,  3.34it/s]
 60%|██████    | 222966/371472 [7:04:53<12:03:43,  3.42it/s]
 60%|██████    | 222967/371472 [7:04:53<12:23:51,  3.33it/s]
 60%|██████    | 222968/371472 [7:04:54<13:15:08,  3.11it/s]
 60%|██████    | 222969/371472 [7:04:54<13:07:56,  3.14it/s]
 60%|██████    | 222970/371472 [7:04:54<13:07:26,  3.14it/s]
 60%|██████    | 222971/371472 [7:04:54<12:45:31,  3.23it/s]
 60%|██████    | 222972/371472 [7:04:55<12:28:23,  3.31it/s]
 60%|██████    | 222973/371472 [7:04:55<12:14:06,  3.37it/s]
 60%|██████    | 222974/371472 [7:04:55<12:13:01,  3.38it/s]
 60%|██████    | 222975/371472 [7:04:56<11:50:38,  3.48it/s]
 60%|██████    | 222976/371472 [7:04:56<11:42:22,  3.52it/s]
 60%|██████    | 222977/371472 [7:04:56<12:01:52,  3.43it/s]
 60%|██████    | 222978/371472 [7:04:56<12:03:34,  3.42it/s]
 60%|██████    | 222979/371472 [7:04:57<11:52:23,  3.47it/s]
 60%|██████    | 222980/371472 [7:04:57<13:51:33,  2.98it/s]
                                                            
{'loss': 2.8072, 'learning_rate': 4.5995927514059774e-07, 'epoch': 9.6}
+
 60%|██████    | 222980/371472 [7:04:57<13:51:33,  2.98it/s]
 60%|██████    | 222981/371472 [7:04:57<13:27:31,  3.06it/s]
 60%|██████    | 222982/371472 [7:04:58<13:19:22,  3.10it/s]
 60%|██████    | 222983/371472 [7:04:58<12:38:03,  3.26it/s]
 60%|██████    | 222984/371472 [7:04:58<12:25:58,  3.32it/s]
 60%|██████    | 222985/371472 [7:04:59<12:11:05,  3.39it/s]
 60%|██████    | 222986/371472 [7:04:59<12:30:41,  3.30it/s]
 60%|██████    | 222987/371472 [7:04:59<12:33:23,  3.28it/s]
 60%|██████    | 222988/371472 [7:05:00<12:47:30,  3.22it/s]
 60%|██████    | 222989/371472 [7:05:00<13:48:57,  2.99it/s]
 60%|██████    | 222990/371472 [7:05:00<13:10:57,  3.13it/s]
 60%|██████    | 222991/371472 [7:05:01<13:11:45,  3.13it/s]
 60%|██████    | 222992/371472 [7:05:01<12:30:04,  3.30it/s]
 60%|██████    | 222993/371472 [7:05:01<13:14:28,  3.11it/s]
 60%|██████    | 222994/371472 [7:05:01<12:49:25,  3.22it/s]
 60%|██████    | 222995/371472 [7:05:02<12:37:17,  3.27it/s]
 60%|██████    | 222996/371472 [7:05:02<12:15:11,  3.37it/s]
 60%|██████    | 222997/371472 [7:05:02<11:59:53,  3.44it/s]
 60%|██████    | 222998/371472 [7:05:03<12:29:49,  3.30it/s]
 60%|██████    | 222999/371472 [7:05:03<12:14:10,  3.37it/s]
 60%|██████    | 223000/371472 [7:05:03<12:14:08,  3.37it/s]
                                                            
{'loss': 2.8184, 'learning_rate': 4.599107931651188e-07, 'epoch': 9.61}
+
 60%|██████    | 223000/371472 [7:05:03<12:14:08,  3.37it/s]
 60%|██████    | 223001/371472 [7:05:04<12:51:31,  3.21it/s]
 60%|██████    | 223002/371472 [7:05:04<12:37:59,  3.26it/s]
 60%|██████    | 223003/371472 [7:05:04<12:46:51,  3.23it/s]
 60%|██████    | 223004/371472 [7:05:05<13:25:16,  3.07it/s]
 60%|██████    | 223005/371472 [7:05:05<13:23:19,  3.08it/s]
 60%|██████    | 223006/371472 [7:05:05<13:03:21,  3.16it/s]
 60%|██████    | 223007/371472 [7:05:05<12:48:15,  3.22it/s]
 60%|██████    | 223008/371472 [7:05:06<12:31:33,  3.29it/s]
 60%|██████    | 223009/371472 [7:05:06<12:23:04,  3.33it/s]
 60%|██████    | 223010/371472 [7:05:06<12:48:32,  3.22it/s]
 60%|██████    | 223011/371472 [7:05:07<12:13:38,  3.37it/s]
 60%|██████    | 223012/371472 [7:05:07<12:27:50,  3.31it/s]
 60%|██████    | 223013/371472 [7:05:07<13:35:24,  3.03it/s]
 60%|██████    | 223014/371472 [7:05:08<13:07:04,  3.14it/s]
 60%|██████    | 223015/371472 [7:05:08<12:46:04,  3.23it/s]
 60%|██████    | 223016/371472 [7:05:08<12:55:43,  3.19it/s]
 60%|██████    | 223017/371472 [7:05:09<12:34:29,  3.28it/s]
 60%|██████    | 223018/371472 [7:05:09<12:22:51,  3.33it/s]
 60%|██████    | 223019/371472 [7:05:09<12:06:52,  3.40it/s]
 60%|██████    | 223020/371472 [7:05:09<11:53:40,  3.47it/s]
                                                            
{'loss': 2.8303, 'learning_rate': 4.5986231118963994e-07, 'epoch': 9.61}
+
 60%|██████    | 223020/371472 [7:05:09<11:53:40,  3.47it/s]
 60%|██████    | 223021/371472 [7:05:10<12:05:26,  3.41it/s]
 60%|██████    | 223022/371472 [7:05:10<12:11:42,  3.38it/s]
 60%|██████    | 223023/371472 [7:05:10<12:40:20,  3.25it/s]
 60%|██████    | 223024/371472 [7:05:11<12:26:36,  3.31it/s]
 60%|██████    | 223025/371472 [7:05:11<13:21:49,  3.09it/s]
 60%|██████    | 223026/371472 [7:05:11<12:49:46,  3.21it/s]
 60%|██████    | 223027/371472 [7:05:12<12:58:17,  3.18it/s]
 60%|██████    | 223028/371472 [7:05:12<13:00:54,  3.17it/s]
 60%|██████    | 223029/371472 [7:05:12<13:13:49,  3.12it/s]
 60%|██████    | 223030/371472 [7:05:13<12:46:37,  3.23it/s]
 60%|██████    | 223031/371472 [7:05:13<13:09:25,  3.13it/s]
 60%|██████    | 223032/371472 [7:05:13<12:55:10,  3.19it/s]
 60%|██████    | 223033/371472 [7:05:14<13:43:55,  3.00it/s]
 60%|██████    | 223034/371472 [7:05:14<13:21:20,  3.09it/s]
 60%|██████    | 223035/371472 [7:05:14<12:59:02,  3.18it/s]
 60%|██████    | 223036/371472 [7:05:14<12:14:44,  3.37it/s]
 60%|██████    | 223037/371472 [7:05:15<12:07:36,  3.40it/s]
 60%|██████    | 223038/371472 [7:05:15<11:55:57,  3.46it/s]
 60%|██████    | 223039/371472 [7:05:15<11:54:59,  3.46it/s]
 60%|██████    | 223040/371472 [7:05:16<11:57:25,  3.45it/s]
                                                            
{'loss': 2.8135, 'learning_rate': 4.59813829214161e-07, 'epoch': 9.61}
+
 60%|██████    | 223040/371472 [7:05:16<11:57:25,  3.45it/s]
 60%|██████    | 223041/371472 [7:05:16<12:34:40,  3.28it/s]
 60%|██████    | 223042/371472 [7:05:16<12:06:45,  3.40it/s]
 60%|██████    | 223043/371472 [7:05:16<12:06:36,  3.40it/s]
 60%|██████    | 223044/371472 [7:05:17<12:16:53,  3.36it/s]
 60%|██████    | 223045/371472 [7:05:17<12:09:43,  3.39it/s]
 60%|██████    | 223046/371472 [7:05:17<12:21:59,  3.33it/s]
 60%|██████    | 223047/371472 [7:05:18<12:16:10,  3.36it/s]
 60%|██████    | 223048/371472 [7:05:18<12:42:12,  3.25it/s]
 60%|██████    | 223049/371472 [7:05:18<12:34:06,  3.28it/s]
 60%|██████    | 223050/371472 [7:05:19<12:34:15,  3.28it/s]
 60%|██████    | 223051/371472 [7:05:19<12:07:08,  3.40it/s]
 60%|██████    | 223052/371472 [7:05:19<11:49:44,  3.49it/s]
 60%|██████    | 223053/371472 [7:05:19<12:07:00,  3.40it/s]
 60%|██████    | 223054/371472 [7:05:20<12:18:15,  3.35it/s]
 60%|██████    | 223055/371472 [7:05:20<12:01:01,  3.43it/s]
 60%|██████    | 223056/371472 [7:05:20<12:00:30,  3.43it/s]
 60%|██████    | 223057/371472 [7:05:21<11:49:49,  3.48it/s]
 60%|██████    | 223058/371472 [7:05:21<13:09:59,  3.13it/s]
 60%|██████    | 223059/371472 [7:05:21<13:13:34,  3.12it/s]
 60%|██████    | 223060/371472 [7:05:22<12:36:20,  3.27it/s]
                                                            
{'loss': 2.8092, 'learning_rate': 4.597653472386822e-07, 'epoch': 9.61}
+
 60%|██████    | 223060/371472 [7:05:22<12:36:20,  3.27it/s]
 60%|██████    | 223061/371472 [7:05:22<12:30:18,  3.30it/s]
 60%|██████    | 223062/371472 [7:05:22<12:12:44,  3.38it/s]
 60%|██████    | 223063/371472 [7:05:22<11:58:31,  3.44it/s]
 60%|██████    | 223064/371472 [7:05:23<12:48:50,  3.22it/s]
 60%|██████    | 223065/371472 [7:05:23<12:24:58,  3.32it/s]
 60%|██████    | 223066/371472 [7:05:23<12:37:41,  3.26it/s]
 60%|██████    | 223067/371472 [7:05:24<12:13:53,  3.37it/s]
 60%|██████    | 223068/371472 [7:05:24<11:56:57,  3.45it/s]
 60%|██████    | 223069/371472 [7:05:24<11:57:33,  3.45it/s]
 60%|██████    | 223070/371472 [7:05:25<12:03:35,  3.42it/s]
 60%|██████    | 223071/371472 [7:05:25<12:46:04,  3.23it/s]
 60%|██████    | 223072/371472 [7:05:25<12:39:16,  3.26it/s]
 60%|██████    | 223073/371472 [7:05:26<12:54:14,  3.19it/s]
 60%|██████    | 223074/371472 [7:05:26<12:19:26,  3.34it/s]
 60%|██████    | 223075/371472 [7:05:26<13:19:04,  3.10it/s]
 60%|██████    | 223076/371472 [7:05:26<13:13:58,  3.12it/s]
 60%|██████    | 223077/371472 [7:05:27<12:30:44,  3.29it/s]
 60%|██████    | 223078/371472 [7:05:27<12:18:09,  3.35it/s]
 60%|██████    | 223079/371472 [7:05:27<12:16:41,  3.36it/s]
 60%|██████    | 223080/371472 [7:05:28<12:14:55,  3.37it/s]
                                                            
{'loss': 2.8142, 'learning_rate': 4.597168652632032e-07, 'epoch': 9.61}
+
 60%|██████    | 223080/371472 [7:05:28<12:14:55,  3.37it/s]
 60%|██████    | 223081/371472 [7:05:28<14:03:11,  2.93it/s]
 60%|██████    | 223082/371472 [7:05:28<13:31:00,  3.05it/s]
 60%|██████    | 223083/371472 [7:05:29<13:26:43,  3.07it/s]
 60%|██████    | 223084/371472 [7:05:29<13:22:40,  3.08it/s]
 60%|██████    | 223085/371472 [7:05:29<13:05:09,  3.15it/s]
 60%|██████    | 223086/371472 [7:05:30<12:56:01,  3.19it/s]
 60%|██████    | 223087/371472 [7:05:30<12:44:04,  3.24it/s]
 60%|██████    | 223088/371472 [7:05:30<13:02:24,  3.16it/s]
 60%|██████    | 223089/371472 [7:05:31<12:38:55,  3.26it/s]
 60%|██████    | 223090/371472 [7:05:31<12:29:19,  3.30it/s]
 60%|██████    | 223091/371472 [7:05:31<12:37:56,  3.26it/s]
 60%|██████    | 223092/371472 [7:05:31<12:39:46,  3.25it/s]
 60%|██████    | 223093/371472 [7:05:32<12:37:27,  3.26it/s]
 60%|██████    | 223094/371472 [7:05:32<12:47:46,  3.22it/s]
 60%|██████    | 223095/371472 [7:05:32<13:06:26,  3.14it/s]
 60%|██████    | 223096/371472 [7:05:33<13:29:56,  3.05it/s]
 60%|██████    | 223097/371472 [7:05:33<12:47:01,  3.22it/s]
 60%|██████    | 223098/371472 [7:05:33<12:28:35,  3.30it/s]
 60%|██████    | 223099/371472 [7:05:34<11:56:28,  3.45it/s]
 60%|██████    | 223100/371472 [7:05:34<11:46:42,  3.50it/s]
                                                            
{'loss': 2.7048, 'learning_rate': 4.596683832877244e-07, 'epoch': 9.61}
+
 60%|██████    | 223100/371472 [7:05:34<11:46:42,  3.50it/s]
 60%|██████    | 223101/371472 [7:05:34<11:50:15,  3.48it/s]
 60%|██████    | 223102/371472 [7:05:34<12:06:40,  3.40it/s]
 60%|██████    | 223103/371472 [7:05:35<12:21:19,  3.34it/s]
 60%|██████    | 223104/371472 [7:05:35<12:33:29,  3.28it/s]
 60%|██████    | 223105/371472 [7:05:35<12:09:42,  3.39it/s]
 60%|██████    | 223106/371472 [7:05:36<12:16:21,  3.36it/s]
 60%|██████    | 223107/371472 [7:05:36<12:00:12,  3.43it/s]
 60%|██████    | 223108/371472 [7:05:36<12:02:48,  3.42it/s]
 60%|██████    | 223109/371472 [7:05:37<12:09:51,  3.39it/s]
 60%|██████    | 223110/371472 [7:05:37<11:58:07,  3.44it/s]
 60%|██████    | 223111/371472 [7:05:37<11:57:54,  3.44it/s]
 60%|██████    | 223112/371472 [7:05:37<12:20:15,  3.34it/s]
 60%|██████    | 223113/371472 [7:05:38<12:24:31,  3.32it/s]
 60%|██████    | 223114/371472 [7:05:38<12:16:44,  3.36it/s]
 60%|██████    | 223115/371472 [7:05:38<11:59:11,  3.44it/s]
 60%|██████    | 223116/371472 [7:05:39<12:47:43,  3.22it/s]
 60%|██████    | 223117/371472 [7:05:39<12:36:56,  3.27it/s]
 60%|██████    | 223118/371472 [7:05:39<12:44:56,  3.23it/s]
 60%|██████    | 223119/371472 [7:05:40<12:48:09,  3.22it/s]
 60%|██████    | 223120/371472 [7:05:40<12:45:38,  3.23it/s]
                                                            
{'loss': 2.6679, 'learning_rate': 4.596199013122454e-07, 'epoch': 9.61}
+
 60%|██████    | 223120/371472 [7:05:40<12:45:38,  3.23it/s]
 60%|██████    | 223121/371472 [7:05:40<12:46:12,  3.23it/s]
 60%|██████    | 223122/371472 [7:05:40<12:23:48,  3.32it/s]
 60%|██████    | 223123/371472 [7:05:41<12:44:08,  3.24it/s]
 60%|██████    | 223124/371472 [7:05:41<13:13:04,  3.12it/s]
 60%|██████    | 223125/371472 [7:05:42<13:40:13,  3.01it/s]
 60%|██████    | 223126/371472 [7:05:42<13:24:16,  3.07it/s]
 60%|██████    | 223127/371472 [7:05:42<14:21:16,  2.87it/s]
 60%|██████    | 223128/371472 [7:05:43<14:26:21,  2.85it/s]
 60%|██████    | 223129/371472 [7:05:43<14:17:34,  2.88it/s]
 60%|██████    | 223130/371472 [7:05:43<13:36:14,  3.03it/s]
 60%|██████    | 223131/371472 [7:05:44<13:25:31,  3.07it/s]
 60%|██████    | 223132/371472 [7:05:44<12:57:33,  3.18it/s]
 60%|██████    | 223133/371472 [7:05:44<13:30:33,  3.05it/s]
 60%|██████    | 223134/371472 [7:05:45<13:46:14,  2.99it/s]
 60%|██████    | 223135/371472 [7:05:45<13:33:31,  3.04it/s]
 60%|██████    | 223136/371472 [7:05:45<13:10:28,  3.13it/s]
 60%|██████    | 223137/371472 [7:05:46<13:52:36,  2.97it/s]
 60%|██████    | 223138/371472 [7:05:46<13:13:28,  3.12it/s]
 60%|██████    | 223139/371472 [7:05:46<13:19:02,  3.09it/s]
 60%|██████    | 223140/371472 [7:05:46<13:11:58,  3.12it/s]
                                                            
{'loss': 2.7028, 'learning_rate': 4.595714193367666e-07, 'epoch': 9.61}
+
 60%|██████    | 223140/371472 [7:05:46<13:11:58,  3.12it/s]
 60%|██████    | 223141/371472 [7:05:47<12:49:47,  3.21it/s]
 60%|██████    | 223142/371472 [7:05:47<13:17:35,  3.10it/s]
 60%|██████    | 223143/371472 [7:05:47<12:44:41,  3.23it/s]
 60%|██████    | 223144/371472 [7:05:48<13:24:42,  3.07it/s]
 60%|██████    | 223145/371472 [7:05:48<13:11:03,  3.13it/s]
 60%|██████    | 223146/371472 [7:05:48<12:55:11,  3.19it/s]
 60%|██████    | 223147/371472 [7:05:49<13:58:53,  2.95it/s]
 60%|██████    | 223148/371472 [7:05:49<13:25:44,  3.07it/s]
 60%|██████    | 223149/371472 [7:05:49<12:59:28,  3.17it/s]
 60%|██████    | 223150/371472 [7:05:50<13:02:43,  3.16it/s]
 60%|██████    | 223151/371472 [7:05:50<12:37:54,  3.26it/s]
 60%|██████    | 223152/371472 [7:05:50<12:39:23,  3.26it/s]
 60%|██████    | 223153/371472 [7:05:51<12:51:41,  3.20it/s]
 60%|██████    | 223154/371472 [7:05:51<12:31:23,  3.29it/s]
 60%|██████    | 223155/371472 [7:05:51<12:30:04,  3.30it/s]
 60%|██████    | 223156/371472 [7:05:51<12:52:15,  3.20it/s]
 60%|██████    | 223157/371472 [7:05:52<12:10:36,  3.38it/s]
 60%|██████    | 223158/371472 [7:05:52<12:03:11,  3.42it/s]
 60%|██████    | 223159/371472 [7:05:52<12:03:08,  3.42it/s]
 60%|██████    | 223160/371472 [7:05:53<11:42:47,  3.52it/s]
                                                            
{'loss': 2.5985, 'learning_rate': 4.5952293736128765e-07, 'epoch': 9.61}
+
 60%|██████    | 223160/371472 [7:05:53<11:42:47,  3.52it/s]
 60%|██████    | 223161/371472 [7:05:53<12:16:26,  3.36it/s]
 60%|██████    | 223162/371472 [7:05:53<12:22:22,  3.33it/s]
 60%|██████    | 223163/371472 [7:05:53<12:09:23,  3.39it/s]
 60%|██████    | 223164/371472 [7:05:54<12:00:45,  3.43it/s]
 60%|██████    | 223165/371472 [7:05:54<11:58:01,  3.44it/s]
 60%|██████    | 223166/371472 [7:05:54<12:07:22,  3.40it/s]
 60%|██████    | 223167/371472 [7:05:55<11:53:09,  3.47it/s]
 60%|██████    | 223168/371472 [7:05:55<12:38:55,  3.26it/s]
 60%|██████    | 223169/371472 [7:05:55<12:38:09,  3.26it/s]
 60%|██████    | 223170/371472 [7:05:56<14:27:47,  2.85it/s]
 60%|██████    | 223171/371472 [7:05:56<13:35:45,  3.03it/s]
 60%|██████    | 223172/371472 [7:05:56<13:11:35,  3.12it/s]
 60%|██████    | 223173/371472 [7:05:57<12:40:01,  3.25it/s]
 60%|██████    | 223174/371472 [7:05:57<13:07:39,  3.14it/s]
 60%|██████    | 223175/371472 [7:05:57<13:34:17,  3.04it/s]
 60%|██████    | 223176/371472 [7:05:58<13:21:29,  3.08it/s]
 60%|██████    | 223177/371472 [7:05:58<13:08:29,  3.13it/s]
 60%|██████    | 223178/371472 [7:05:58<13:16:44,  3.10it/s]
 60%|██████    | 223179/371472 [7:05:59<12:39:27,  3.25it/s]
 60%|██████    | 223180/371472 [7:05:59<12:30:21,  3.29it/s]
                                                            
{'loss': 2.6536, 'learning_rate': 4.5947445538580883e-07, 'epoch': 9.61}
+
 60%|██████    | 223180/371472 [7:05:59<12:30:21,  3.29it/s]
 60%|██████    | 223181/371472 [7:05:59<12:24:16,  3.32it/s]
 60%|██████    | 223182/371472 [7:05:59<12:21:12,  3.33it/s]
 60%|██████    | 223183/371472 [7:06:00<12:12:05,  3.38it/s]
 60%|██████    | 223184/371472 [7:06:00<11:46:21,  3.50it/s]
 60%|██████    | 223185/371472 [7:06:00<12:09:13,  3.39it/s]
 60%|██████    | 223186/371472 [7:06:01<12:36:23,  3.27it/s]
 60%|██████    | 223187/371472 [7:06:01<12:16:16,  3.36it/s]
 60%|██████    | 223188/371472 [7:06:01<12:12:27,  3.37it/s]
 60%|██████    | 223189/371472 [7:06:01<12:28:50,  3.30it/s]
 60%|██████    | 223190/371472 [7:06:02<12:23:03,  3.33it/s]
 60%|██████    | 223191/371472 [7:06:02<11:50:41,  3.48it/s]
 60%|██████    | 223192/371472 [7:06:02<12:12:19,  3.37it/s]
 60%|██████    | 223193/371472 [7:06:03<11:42:14,  3.52it/s]
 60%|██████    | 223194/371472 [7:06:03<11:33:12,  3.57it/s]
 60%|██████    | 223195/371472 [7:06:03<11:36:30,  3.55it/s]
 60%|██████    | 223196/371472 [7:06:03<11:30:39,  3.58it/s]
 60%|██████    | 223197/371472 [7:06:04<11:24:27,  3.61it/s]
 60%|██████    | 223198/371472 [7:06:04<11:09:14,  3.69it/s]
 60%|██████    | 223199/371472 [7:06:04<11:24:00,  3.61it/s]
 60%|██████    | 223200/371472 [7:06:05<11:35:30,  3.55it/s]
                                                            
{'loss': 2.7786, 'learning_rate': 4.5942597341032985e-07, 'epoch': 9.61}
+
 60%|██████    | 223200/371472 [7:06:05<11:35:30,  3.55it/s]
 60%|██████    | 223201/371472 [7:06:05<11:20:03,  3.63it/s]
 60%|██████    | 223202/371472 [7:06:05<11:18:45,  3.64it/s]
 60%|██████    | 223203/371472 [7:06:05<11:31:23,  3.57it/s]
 60%|██████    | 223204/371472 [7:06:06<11:48:30,  3.49it/s]
 60%|██████    | 223205/371472 [7:06:06<11:39:43,  3.53it/s]
 60%|██████    | 223206/371472 [7:06:06<11:44:24,  3.51it/s]
 60%|██████    | 223207/371472 [7:06:07<11:49:06,  3.48it/s]
 60%|██████    | 223208/371472 [7:06:07<11:56:04,  3.45it/s]
 60%|██████    | 223209/371472 [7:06:07<11:42:11,  3.52it/s]
 60%|██████    | 223210/371472 [7:06:07<11:49:16,  3.48it/s]
 60%|██████    | 223211/371472 [7:06:08<11:58:13,  3.44it/s]
 60%|██████    | 223212/371472 [7:06:08<11:42:38,  3.52it/s]
 60%|██████    | 223213/371472 [7:06:08<12:22:51,  3.33it/s]
 60%|██████    | 223214/371472 [7:06:09<11:55:07,  3.46it/s]
 60%|██████    | 223215/371472 [7:06:09<12:42:11,  3.24it/s]
 60%|██████    | 223216/371472 [7:06:09<13:28:47,  3.06it/s]
 60%|██████    | 223217/371472 [7:06:10<13:03:02,  3.16it/s]
 60%|██████    | 223218/371472 [7:06:10<13:36:45,  3.03it/s]
 60%|██████    | 223219/371472 [7:06:10<13:44:17,  3.00it/s]
 60%|██████    | 223220/371472 [7:06:11<13:14:38,  3.11it/s]
                                                            
{'loss': 2.8383, 'learning_rate': 4.59377491434851e-07, 'epoch': 9.61}
+
 60%|██████    | 223220/371472 [7:06:11<13:14:38,  3.11it/s]
 60%|██████    | 223221/371472 [7:06:11<13:10:17,  3.13it/s]
 60%|██████    | 223222/371472 [7:06:11<13:10:43,  3.12it/s]
 60%|██████    | 223223/371472 [7:06:12<13:05:24,  3.15it/s]
 60%|██████    | 223224/371472 [7:06:12<12:24:02,  3.32it/s]
 60%|██████    | 223225/371472 [7:06:12<12:41:21,  3.25it/s]
 60%|██████    | 223226/371472 [7:06:12<12:18:05,  3.35it/s]
 60%|██████    | 223227/371472 [7:06:13<12:02:40,  3.42it/s]
 60%|██████    | 223228/371472 [7:06:13<12:18:22,  3.35it/s]
 60%|██████    | 223229/371472 [7:06:13<12:49:50,  3.21it/s]
 60%|██████    | 223230/371472 [7:06:14<12:24:20,  3.32it/s]
 60%|██████    | 223231/371472 [7:06:14<13:07:26,  3.14it/s]
 60%|██████    | 223232/371472 [7:06:14<12:56:29,  3.18it/s]
 60%|██████    | 223233/371472 [7:06:15<12:34:39,  3.27it/s]
 60%|██████    | 223234/371472 [7:06:15<12:36:12,  3.27it/s]
 60%|██████    | 223235/371472 [7:06:15<13:09:53,  3.13it/s]
 60%|██████    | 223236/371472 [7:06:16<13:45:27,  2.99it/s]
 60%|██████    | 223237/371472 [7:06:16<12:57:55,  3.18it/s]
 60%|██████    | 223238/371472 [7:06:16<12:57:49,  3.18it/s]
 60%|██████    | 223239/371472 [7:06:16<12:44:04,  3.23it/s]
 60%|██████    | 223240/371472 [7:06:17<12:53:07,  3.20it/s]
                                                            
{'loss': 2.732, 'learning_rate': 4.593290094593721e-07, 'epoch': 9.62}
+
 60%|██████    | 223240/371472 [7:06:17<12:53:07,  3.20it/s]
 60%|██████    | 223241/371472 [7:06:17<12:19:05,  3.34it/s]
 60%|██████    | 223242/371472 [7:06:17<12:20:20,  3.34it/s]
 60%|██████    | 223243/371472 [7:06:18<12:31:10,  3.29it/s]
 60%|██████    | 223244/371472 [7:06:18<12:19:32,  3.34it/s]
 60%|██████    | 223245/371472 [7:06:18<12:24:08,  3.32it/s]
 60%|██████    | 223246/371472 [7:06:19<12:07:26,  3.40it/s]
 60%|██████    | 223247/371472 [7:06:19<12:17:51,  3.35it/s]
 60%|██████    | 223248/371472 [7:06:19<12:02:47,  3.42it/s]
 60%|██████    | 223249/371472 [7:06:19<12:16:29,  3.35it/s]
 60%|██████    | 223250/371472 [7:06:20<12:11:20,  3.38it/s]
 60%|██████    | 223251/371472 [7:06:20<12:02:04,  3.42it/s]
 60%|██████    | 223252/371472 [7:06:20<12:39:26,  3.25it/s]
 60%|██████    | 223253/371472 [7:06:21<12:14:56,  3.36it/s]
 60%|██████    | 223254/371472 [7:06:21<12:20:15,  3.34it/s]
 60%|██████    | 223255/371472 [7:06:21<12:39:06,  3.25it/s]
 60%|██████    | 223256/371472 [7:06:22<12:33:04,  3.28it/s]
 60%|██████    | 223257/371472 [7:06:22<12:11:41,  3.38it/s]
 60%|██████    | 223258/371472 [7:06:22<12:43:24,  3.24it/s]
 60%|██████    | 223259/371472 [7:06:22<12:28:36,  3.30it/s]
 60%|██████    | 223260/371472 [7:06:23<12:07:01,  3.40it/s]
                                                            
{'loss': 2.7582, 'learning_rate': 4.5928052748389317e-07, 'epoch': 9.62}
+
 60%|██████    | 223260/371472 [7:06:23<12:07:01,  3.40it/s]
 60%|██████    | 223261/371472 [7:06:23<12:08:45,  3.39it/s]
 60%|██████    | 223262/371472 [7:06:23<12:07:10,  3.40it/s]
 60%|██████    | 223263/371472 [7:06:24<12:59:33,  3.17it/s]
 60%|██████    | 223264/371472 [7:06:24<12:33:53,  3.28it/s]
 60%|██████    | 223265/371472 [7:06:24<12:08:35,  3.39it/s]
 60%|██████    | 223266/371472 [7:06:25<12:35:17,  3.27it/s]
 60%|██████    | 223267/371472 [7:06:25<13:14:53,  3.11it/s]
 60%|██████    | 223268/371472 [7:06:25<13:13:59,  3.11it/s]
 60%|██████    | 223269/371472 [7:06:26<13:24:04,  3.07it/s]
 60%|██████    | 223270/371472 [7:06:26<13:13:52,  3.11it/s]
 60%|██████    | 223271/371472 [7:06:26<13:06:27,  3.14it/s]
 60%|██████    | 223272/371472 [7:06:27<13:06:48,  3.14it/s]
 60%|██████    | 223273/371472 [7:06:27<12:35:04,  3.27it/s]
 60%|██████    | 223274/371472 [7:06:27<12:05:42,  3.40it/s]
 60%|██████    | 223275/371472 [7:06:27<12:46:33,  3.22it/s]
 60%|██████    | 223276/371472 [7:06:28<13:39:22,  3.01it/s]
 60%|██████    | 223277/371472 [7:06:28<13:16:14,  3.10it/s]
 60%|██████    | 223278/371472 [7:06:28<12:33:12,  3.28it/s]
 60%|██████    | 223279/371472 [7:06:29<12:09:45,  3.38it/s]
 60%|██████    | 223280/371472 [7:06:29<12:01:51,  3.42it/s]
                                                            
{'loss': 2.771, 'learning_rate': 4.592320455084143e-07, 'epoch': 9.62}
+
 60%|██████    | 223280/371472 [7:06:29<12:01:51,  3.42it/s]
 60%|██████    | 223281/371472 [7:06:29<11:46:43,  3.49it/s]
 60%|██████    | 223282/371472 [7:06:29<11:50:48,  3.47it/s]
 60%|██████    | 223283/371472 [7:06:30<11:40:23,  3.53it/s]
 60%|██████    | 223284/371472 [7:06:30<11:46:54,  3.49it/s]
 60%|██████    | 223285/371472 [7:06:30<11:36:43,  3.54it/s]
 60%|██████    | 223286/371472 [7:06:31<12:12:04,  3.37it/s]
 60%|██████    | 223287/371472 [7:06:31<11:56:41,  3.45it/s]
 60%|██████    | 223288/371472 [7:06:31<11:55:19,  3.45it/s]
 60%|██████    | 223289/371472 [7:06:31<11:38:52,  3.53it/s]
 60%|██████    | 223290/371472 [7:06:32<11:46:48,  3.49it/s]
 60%|██████    | 223291/371472 [7:06:32<11:46:53,  3.49it/s]
 60%|██████    | 223292/371472 [7:06:32<11:39:12,  3.53it/s]
 60%|██████    | 223293/371472 [7:06:33<12:10:40,  3.38it/s]
 60%|██████    | 223294/371472 [7:06:33<12:25:39,  3.31it/s]
 60%|██████    | 223295/371472 [7:06:33<12:14:13,  3.36it/s]
 60%|██████    | 223296/371472 [7:06:34<12:07:17,  3.40it/s]
 60%|██████    | 223297/371472 [7:06:34<11:48:54,  3.48it/s]
 60%|██████    | 223298/371472 [7:06:34<11:59:45,  3.43it/s]
 60%|██████    | 223299/371472 [7:06:34<12:37:51,  3.26it/s]
 60%|██████    | 223300/371472 [7:06:35<12:17:49,  3.35it/s]
                                                            
{'loss': 2.803, 'learning_rate': 4.5918356353293536e-07, 'epoch': 9.62}
+
 60%|██████    | 223300/371472 [7:06:35<12:17:49,  3.35it/s]
 60%|██████    | 223301/371472 [7:06:35<12:01:38,  3.42it/s]
 60%|██████    | 223302/371472 [7:06:35<11:47:51,  3.49it/s]
 60%|██████    | 223303/371472 [7:06:36<11:55:18,  3.45it/s]
 60%|██████    | 223304/371472 [7:06:36<11:34:45,  3.55it/s]
 60%|██████    | 223305/371472 [7:06:36<11:39:44,  3.53it/s]
 60%|██████    | 223306/371472 [7:06:36<11:46:43,  3.49it/s]
 60%|██████    | 223307/371472 [7:06:37<12:24:09,  3.32it/s]
 60%|██████    | 223308/371472 [7:06:37<12:21:36,  3.33it/s]
 60%|██████    | 223309/371472 [7:06:37<12:30:17,  3.29it/s]
 60%|██████    | 223310/371472 [7:06:38<13:15:03,  3.11it/s]
 60%|██████    | 223311/371472 [7:06:38<13:12:07,  3.12it/s]
 60%|██████    | 223312/371472 [7:06:38<12:30:47,  3.29it/s]
 60%|██████    | 223313/371472 [7:06:39<12:46:30,  3.22it/s]
 60%|██████    | 223314/371472 [7:06:39<12:32:14,  3.28it/s]
 60%|██████    | 223315/371472 [7:06:39<12:20:41,  3.33it/s]
 60%|██████    | 223316/371472 [7:06:40<12:02:13,  3.42it/s]
 60%|██████    | 223317/371472 [7:06:40<12:17:05,  3.35it/s]
 60%|██████    | 223318/371472 [7:06:40<12:14:41,  3.36it/s]
 60%|██████    | 223319/371472 [7:06:40<12:08:42,  3.39it/s]
 60%|██████    | 223320/371472 [7:06:41<12:19:46,  3.34it/s]
                                                            
{'loss': 2.7081, 'learning_rate': 4.5913508155745654e-07, 'epoch': 9.62}
+
 60%|██████    | 223320/371472 [7:06:41<12:19:46,  3.34it/s]
 60%|██████    | 223321/371472 [7:06:41<12:18:31,  3.34it/s]
 60%|██████    | 223322/371472 [7:06:41<11:56:36,  3.45it/s]
 60%|██████    | 223323/371472 [7:06:42<12:09:24,  3.39it/s]
 60%|██████    | 223324/371472 [7:06:42<12:12:54,  3.37it/s]
 60%|██████    | 223325/371472 [7:06:42<12:49:04,  3.21it/s]
 60%|██████    | 223326/371472 [7:06:43<12:39:49,  3.25it/s]
 60%|██████    | 223327/371472 [7:06:43<12:23:39,  3.32it/s]
 60%|██████    | 223328/371472 [7:06:43<12:11:53,  3.37it/s]
 60%|██████    | 223329/371472 [7:06:43<12:47:01,  3.22it/s]
 60%|██████    | 223330/371472 [7:06:44<13:04:24,  3.15it/s]
 60%|██████    | 223331/371472 [7:06:44<13:15:33,  3.10it/s]
 60%|██████    | 223332/371472 [7:06:44<12:59:37,  3.17it/s]
 60%|██████    | 223333/371472 [7:06:45<12:52:03,  3.20it/s]
 60%|██████    | 223334/371472 [7:06:45<12:15:21,  3.36it/s]
 60%|██████    | 223335/371472 [7:06:45<12:37:34,  3.26it/s]
 60%|██████    | 223336/371472 [7:06:46<12:29:03,  3.30it/s]
 60%|██████    | 223337/371472 [7:06:46<12:28:52,  3.30it/s]
 60%|██████    | 223338/371472 [7:06:46<12:51:22,  3.20it/s]
 60%|██████    | 223339/371472 [7:06:47<12:22:48,  3.32it/s]
 60%|██████    | 223340/371472 [7:06:47<12:10:41,  3.38it/s]
                                                            
{'loss': 2.8873, 'learning_rate': 4.5908659958197756e-07, 'epoch': 9.62}
+
 60%|██████    | 223340/371472 [7:06:47<12:10:41,  3.38it/s]
 60%|██████    | 223341/371472 [7:06:47<12:30:20,  3.29it/s]
 60%|██████    | 223342/371472 [7:06:47<12:47:06,  3.22it/s]
 60%|██████    | 223343/371472 [7:06:48<12:10:10,  3.38it/s]
 60%|██████    | 223344/371472 [7:06:48<11:48:59,  3.48it/s]
 60%|██████    | 223345/371472 [7:06:48<12:49:34,  3.21it/s]
 60%|██████    | 223346/371472 [7:06:49<12:14:58,  3.36it/s]
 60%|██████    | 223347/371472 [7:06:49<12:13:36,  3.37it/s]
 60%|██████    | 223348/371472 [7:06:49<13:37:38,  3.02it/s]
 60%|██████    | 223349/371472 [7:06:50<13:31:09,  3.04it/s]
 60%|██████    | 223350/371472 [7:06:50<12:58:09,  3.17it/s]
 60%|██████    | 223351/371472 [7:06:50<14:01:18,  2.93it/s]
 60%|██████    | 223352/371472 [7:06:51<13:03:13,  3.15it/s]
 60%|██████    | 223353/371472 [7:06:51<12:56:55,  3.18it/s]
 60%|██████    | 223354/371472 [7:06:51<13:00:08,  3.16it/s]
 60%|██████    | 223355/371472 [7:06:52<12:47:21,  3.22it/s]
 60%|██████    | 223356/371472 [7:06:52<12:35:41,  3.27it/s]
 60%|██████    | 223357/371472 [7:06:52<12:39:26,  3.25it/s]
 60%|██████    | 223358/371472 [7:06:52<12:05:54,  3.40it/s]
 60%|██████    | 223359/371472 [7:06:53<11:48:54,  3.48it/s]
 60%|██████    | 223360/371472 [7:06:53<11:48:04,  3.49it/s]
                                                            
{'loss': 2.863, 'learning_rate': 4.5903811760649874e-07, 'epoch': 9.62}
+
 60%|██████    | 223360/371472 [7:06:53<11:48:04,  3.49it/s]
 60%|██████    | 223361/371472 [7:06:53<12:09:59,  3.38it/s]
 60%|██████    | 223362/371472 [7:06:54<12:15:52,  3.35it/s]
 60%|██████    | 223363/371472 [7:06:54<12:36:26,  3.26it/s]
 60%|██████    | 223364/371472 [7:06:54<12:48:23,  3.21it/s]
 60%|██████    | 223365/371472 [7:06:55<12:39:05,  3.25it/s]
 60%|██████    | 223366/371472 [7:06:55<12:23:38,  3.32it/s]
 60%|██████    | 223367/371472 [7:06:55<12:08:31,  3.39it/s]
 60%|██████    | 223368/371472 [7:06:55<11:59:12,  3.43it/s]
 60%|██████    | 223369/371472 [7:06:56<12:03:16,  3.41it/s]
 60%|██████    | 223370/371472 [7:06:56<12:14:35,  3.36it/s]
 60%|██████    | 223371/371472 [7:06:56<11:58:25,  3.44it/s]
 60%|██████    | 223372/371472 [7:06:57<12:22:05,  3.33it/s]
 60%|██████    | 223373/371472 [7:06:57<12:28:57,  3.30it/s]
 60%|██████    | 223374/371472 [7:06:57<12:24:24,  3.32it/s]
 60%|██████    | 223375/371472 [7:06:57<12:28:11,  3.30it/s]
 60%|██████    | 223376/371472 [7:06:58<13:08:09,  3.13it/s]
 60%|██████    | 223377/371472 [7:06:58<12:48:33,  3.21it/s]
 60%|██████    | 223378/371472 [7:06:58<12:26:06,  3.31it/s]
 60%|██████    | 223379/371472 [7:06:59<12:13:53,  3.36it/s]
 60%|██████    | 223380/371472 [7:06:59<12:52:17,  3.20it/s]
                                                            
{'loss': 2.7993, 'learning_rate': 4.589896356310198e-07, 'epoch': 9.62}
+
 60%|██████    | 223380/371472 [7:06:59<12:52:17,  3.20it/s]
 60%|██████    | 223381/371472 [7:07:00<14:50:26,  2.77it/s]
 60%|██████    | 223382/371472 [7:07:00<14:10:42,  2.90it/s]
 60%|██████    | 223383/371472 [7:07:00<13:41:58,  3.00it/s]
 60%|██████    | 223384/371472 [7:07:00<13:07:47,  3.13it/s]
 60%|██████    | 223385/371472 [7:07:01<12:21:58,  3.33it/s]
 60%|██████    | 223386/371472 [7:07:01<11:55:38,  3.45it/s]
 60%|██████    | 223387/371472 [7:07:01<11:47:13,  3.49it/s]
 60%|██████    | 223388/371472 [7:07:02<11:55:04,  3.45it/s]
 60%|██████    | 223389/371472 [7:07:02<11:53:45,  3.46it/s]
 60%|██████    | 223390/371472 [7:07:02<12:36:03,  3.26it/s]
 60%|██████    | 223391/371472 [7:07:02<12:08:03,  3.39it/s]
 60%|██████    | 223392/371472 [7:07:03<11:50:35,  3.47it/s]
 60%|██████    | 223393/371472 [7:07:03<12:04:07,  3.41it/s]
 60%|██████    | 223394/371472 [7:07:03<11:49:54,  3.48it/s]
 60%|██████    | 223395/371472 [7:07:04<12:00:49,  3.42it/s]
 60%|██████    | 223396/371472 [7:07:04<11:50:39,  3.47it/s]
 60%|██████    | 223397/371472 [7:07:04<12:15:12,  3.36it/s]
 60%|██████    | 223398/371472 [7:07:04<12:16:15,  3.35it/s]
 60%|██████    | 223399/371472 [7:07:05<11:48:48,  3.48it/s]
 60%|██████    | 223400/371472 [7:07:05<11:48:10,  3.48it/s]
                                                            
{'loss': 2.6764, 'learning_rate': 4.5894115365554093e-07, 'epoch': 9.62}
+
 60%|██████    | 223400/371472 [7:07:05<11:48:10,  3.48it/s]
 60%|██████    | 223401/371472 [7:07:05<11:50:26,  3.47it/s]
 60%|██████    | 223402/371472 [7:07:06<11:49:15,  3.48it/s]
 60%|██████    | 223403/371472 [7:07:06<11:44:43,  3.50it/s]
 60%|██████    | 223404/371472 [7:07:06<11:45:43,  3.50it/s]
 60%|██████    | 223405/371472 [7:07:07<12:28:06,  3.30it/s]
 60%|██████    | 223406/371472 [7:07:07<12:14:33,  3.36it/s]
 60%|██████    | 223407/371472 [7:07:07<12:45:23,  3.22it/s]
 60%|██████    | 223408/371472 [7:07:07<12:45:48,  3.22it/s]
 60%|██████    | 223409/371472 [7:07:08<12:44:25,  3.23it/s]
 60%|██████    | 223410/371472 [7:07:08<12:51:25,  3.20it/s]
 60%|██████    | 223411/371472 [7:07:08<13:07:51,  3.13it/s]
 60%|██████    | 223412/371472 [7:07:09<13:40:52,  3.01it/s]
 60%|██████    | 223413/371472 [7:07:09<12:48:35,  3.21it/s]
 60%|██████    | 223414/371472 [7:07:09<13:03:42,  3.15it/s]
 60%|██████    | 223415/371472 [7:07:10<12:50:08,  3.20it/s]
 60%|██████    | 223416/371472 [7:07:10<12:21:50,  3.33it/s]
 60%|██████    | 223417/371472 [7:07:10<12:25:42,  3.31it/s]
 60%|██████    | 223418/371472 [7:07:11<12:15:49,  3.35it/s]
 60%|██████    | 223419/371472 [7:07:11<12:42:04,  3.24it/s]
 60%|██████    | 223420/371472 [7:07:11<12:05:23,  3.40it/s]
                                                            
{'loss': 2.8272, 'learning_rate': 4.58892671680062e-07, 'epoch': 9.62}
+
 60%|██████    | 223420/371472 [7:07:11<12:05:23,  3.40it/s]
 60%|██████    | 223421/371472 [7:07:11<12:15:27,  3.36it/s]
 60%|██████    | 223422/371472 [7:07:12<12:03:07,  3.41it/s]
 60%|██████    | 223423/371472 [7:07:12<11:54:07,  3.46it/s]
 60%|██████    | 223424/371472 [7:07:12<12:02:16,  3.42it/s]
 60%|██████    | 223425/371472 [7:07:13<11:58:46,  3.43it/s]
 60%|██████    | 223426/371472 [7:07:13<12:56:44,  3.18it/s]
 60%|██████    | 223427/371472 [7:07:13<12:53:41,  3.19it/s]
 60%|██████    | 223428/371472 [7:07:14<13:32:53,  3.04it/s]
 60%|██████    | 223429/371472 [7:07:14<13:13:30,  3.11it/s]
 60%|██████    | 223430/371472 [7:07:14<12:53:20,  3.19it/s]
 60%|██████    | 223431/371472 [7:07:14<12:10:04,  3.38it/s]
 60%|██████    | 223432/371472 [7:07:15<12:36:14,  3.26it/s]
 60%|██████    | 223433/371472 [7:07:15<12:23:05,  3.32it/s]
 60%|██████    | 223434/371472 [7:07:15<13:01:47,  3.16it/s]
 60%|██████    | 223435/371472 [7:07:16<13:04:09,  3.15it/s]
 60%|██████    | 223436/371472 [7:07:16<12:33:51,  3.27it/s]
 60%|██████    | 223437/371472 [7:07:16<13:02:42,  3.15it/s]
 60%|██████    | 223438/371472 [7:07:17<13:06:14,  3.14it/s]
 60%|██████    | 223439/371472 [7:07:17<12:25:00,  3.31it/s]
 60%|██████    | 223440/371472 [7:07:17<12:33:37,  3.27it/s]
                                                            
{'loss': 2.7148, 'learning_rate': 4.588441897045832e-07, 'epoch': 9.62}
+
 60%|██████    | 223440/371472 [7:07:17<12:33:37,  3.27it/s]
 60%|██████    | 223441/371472 [7:07:18<12:38:42,  3.25it/s]
 60%|██████    | 223442/371472 [7:07:18<12:09:47,  3.38it/s]
 60%|██████    | 223443/371472 [7:07:18<12:47:55,  3.21it/s]
 60%|██████    | 223444/371472 [7:07:19<12:46:26,  3.22it/s]
 60%|██████    | 223445/371472 [7:07:19<12:36:13,  3.26it/s]
 60%|██████    | 223446/371472 [7:07:19<12:30:49,  3.29it/s]
 60%|██████    | 223447/371472 [7:07:19<12:00:26,  3.42it/s]
 60%|██████    | 223448/371472 [7:07:20<12:10:18,  3.38it/s]
 60%|██████    | 223449/371472 [7:07:20<12:03:13,  3.41it/s]
 60%|██████    | 223450/371472 [7:07:20<12:21:01,  3.33it/s]
 60%|██████    | 223451/371472 [7:07:21<12:32:20,  3.28it/s]
 60%|██████    | 223452/371472 [7:07:21<12:15:08,  3.36it/s]
 60%|██████    | 223453/371472 [7:07:21<12:10:18,  3.38it/s]
 60%|██████    | 223454/371472 [7:07:22<12:40:53,  3.24it/s]
 60%|██████    | 223455/371472 [7:07:22<12:24:59,  3.31it/s]
 60%|██████    | 223456/371472 [7:07:22<12:01:06,  3.42it/s]
 60%|██████    | 223457/371472 [7:07:22<11:51:34,  3.47it/s]
 60%|██████    | 223458/371472 [7:07:23<11:55:29,  3.45it/s]
 60%|██████    | 223459/371472 [7:07:23<11:37:39,  3.54it/s]
 60%|██████    | 223460/371472 [7:07:23<13:31:39,  3.04it/s]
                                                            
{'loss': 2.7571, 'learning_rate': 4.587957077291042e-07, 'epoch': 9.62}
+
 60%|██████    | 223460/371472 [7:07:23<13:31:39,  3.04it/s]
 60%|██████    | 223461/371472 [7:07:24<13:46:32,  2.98it/s]
 60%|██████    | 223462/371472 [7:07:24<13:30:45,  3.04it/s]
 60%|██████    | 223463/371472 [7:07:24<12:49:43,  3.20it/s]
 60%|██████    | 223464/371472 [7:07:25<12:39:23,  3.25it/s]
 60%|██████    | 223465/371472 [7:07:25<13:04:52,  3.14it/s]
 60%|██████    | 223466/371472 [7:07:25<13:31:45,  3.04it/s]
 60%|██████    | 223467/371472 [7:07:26<12:47:21,  3.21it/s]
 60%|██████    | 223468/371472 [7:07:26<12:41:31,  3.24it/s]
 60%|██████    | 223469/371472 [7:07:26<12:18:24,  3.34it/s]
 60%|██████    | 223470/371472 [7:07:26<12:26:10,  3.31it/s]
 60%|██████    | 223471/371472 [7:07:27<12:36:58,  3.26it/s]
 60%|██████    | 223472/371472 [7:07:27<12:26:55,  3.30it/s]
 60%|██████    | 223473/371472 [7:07:27<12:24:46,  3.31it/s]
 60%|██████    | 223474/371472 [7:07:28<12:29:14,  3.29it/s]
 60%|██████    | 223475/371472 [7:07:28<12:03:41,  3.41it/s]
 60%|██████    | 223476/371472 [7:07:28<12:43:24,  3.23it/s]
 60%|██████    | 223477/371472 [7:07:29<13:05:39,  3.14it/s]
 60%|██████    | 223478/371472 [7:07:29<13:06:08,  3.14it/s]
 60%|██████    | 223479/371472 [7:07:29<13:24:29,  3.07it/s]
 60%|██████    | 223480/371472 [7:07:30<13:17:33,  3.09it/s]
                                                            
{'loss': 2.7363, 'learning_rate': 4.587472257536254e-07, 'epoch': 9.63}
+
 60%|██████    | 223480/371472 [7:07:30<13:17:33,  3.09it/s]
 60%|██████    | 223481/371472 [7:07:30<14:08:55,  2.91it/s]
 60%|██████    | 223482/371472 [7:07:30<13:21:30,  3.08it/s]
 60%|██████    | 223483/371472 [7:07:31<12:51:17,  3.20it/s]
 60%|██████    | 223484/371472 [7:07:31<12:21:53,  3.32it/s]
 60%|██████    | 223485/371472 [7:07:31<12:01:15,  3.42it/s]
 60%|██████    | 223486/371472 [7:07:31<12:20:01,  3.33it/s]
 60%|██████    | 223487/371472 [7:07:32<12:28:38,  3.29it/s]
 60%|██████    | 223488/371472 [7:07:32<11:59:29,  3.43it/s]
 60%|██████    | 223489/371472 [7:07:32<12:12:30,  3.37it/s]
 60%|██████    | 223490/371472 [7:07:33<12:24:07,  3.31it/s]
 60%|██████    | 223491/371472 [7:07:33<12:31:09,  3.28it/s]
 60%|██████    | 223492/371472 [7:07:33<12:31:56,  3.28it/s]
 60%|██████    | 223493/371472 [7:07:34<14:20:53,  2.86it/s]
 60%|██████    | 223494/371472 [7:07:34<13:48:57,  2.98it/s]
 60%|██████    | 223495/371472 [7:07:34<14:47:49,  2.78it/s]
 60%|██████    | 223496/371472 [7:07:35<13:48:18,  2.98it/s]
 60%|██████    | 223497/371472 [7:07:35<12:56:41,  3.18it/s]
 60%|██████    | 223498/371472 [7:07:35<12:28:25,  3.30it/s]
 60%|██████    | 223499/371472 [7:07:36<12:39:48,  3.25it/s]
 60%|██████    | 223500/371472 [7:07:36<12:56:01,  3.18it/s]
                                                            
{'loss': 2.7913, 'learning_rate': 4.5869874377814645e-07, 'epoch': 9.63}
+
 60%|██████    | 223500/371472 [7:07:36<12:56:01,  3.18it/s]
 60%|██████    | 223501/371472 [7:07:36<12:30:40,  3.29it/s]
 60%|██████    | 223502/371472 [7:07:36<12:13:58,  3.36it/s]
 60%|██████    | 223503/371472 [7:07:37<12:16:36,  3.35it/s]
 60%|██████    | 223504/371472 [7:07:37<12:33:24,  3.27it/s]
 60%|██████    | 223505/371472 [7:07:37<13:03:36,  3.15it/s]
 60%|██████    | 223506/371472 [7:07:38<12:20:30,  3.33it/s]
 60%|██████    | 223507/371472 [7:07:38<12:11:12,  3.37it/s]
 60%|██████    | 223508/371472 [7:07:38<12:10:04,  3.38it/s]
 60%|██████    | 223509/371472 [7:07:39<12:51:51,  3.19it/s]
 60%|██████    | 223510/371472 [7:07:39<12:25:33,  3.31it/s]
 60%|██████    | 223511/371472 [7:07:39<12:23:32,  3.32it/s]
 60%|██████    | 223512/371472 [7:07:39<12:15:28,  3.35it/s]
 60%|██████    | 223513/371472 [7:07:40<12:11:00,  3.37it/s]
 60%|██████    | 223514/371472 [7:07:40<12:28:52,  3.29it/s]
 60%|██████    | 223515/371472 [7:07:40<12:36:43,  3.26it/s]
 60%|██████    | 223516/371472 [7:07:41<12:52:49,  3.19it/s]
 60%|██████    | 223517/371472 [7:07:41<12:21:27,  3.33it/s]
 60%|██████    | 223518/371472 [7:07:41<12:11:03,  3.37it/s]
 60%|██████    | 223519/371472 [7:07:42<12:24:35,  3.31it/s]
 60%|██████    | 223520/371472 [7:07:42<11:57:00,  3.44it/s]
                                                            
{'loss': 2.8569, 'learning_rate': 4.5865026180266757e-07, 'epoch': 9.63}
+
 60%|██████    | 223520/371472 [7:07:42<11:57:00,  3.44it/s]
 60%|██████    | 223521/371472 [7:07:42<12:45:35,  3.22it/s]
 60%|██████    | 223522/371472 [7:07:43<12:28:52,  3.29it/s]
 60%|██████    | 223523/371472 [7:07:43<12:12:12,  3.37it/s]
 60%|██████    | 223524/371472 [7:07:43<12:04:59,  3.40it/s]
 60%|██████    | 223525/371472 [7:07:43<12:10:25,  3.38it/s]
 60%|██████    | 223526/371472 [7:07:44<12:05:11,  3.40it/s]
 60%|██████    | 223527/371472 [7:07:44<12:03:06,  3.41it/s]
 60%|██████    | 223528/371472 [7:07:44<12:05:02,  3.40it/s]
 60%|██████    | 223529/371472 [7:07:45<12:17:03,  3.35it/s]
 60%|██████    | 223530/371472 [7:07:45<12:02:09,  3.41it/s]
 60%|██████    | 223531/371472 [7:07:45<12:14:17,  3.36it/s]
 60%|██████    | 223532/371472 [7:07:45<11:52:36,  3.46it/s]
 60%|██████    | 223533/371472 [7:07:46<11:48:01,  3.48it/s]
 60%|██████    | 223534/371472 [7:07:46<12:05:50,  3.40it/s]
 60%|██████    | 223535/371472 [7:07:46<11:52:29,  3.46it/s]
 60%|██████    | 223536/371472 [7:07:47<11:48:29,  3.48it/s]
 60%|██████    | 223537/371472 [7:07:47<12:14:08,  3.36it/s]
 60%|██████    | 223538/371472 [7:07:47<12:10:43,  3.37it/s]
 60%|██████    | 223539/371472 [7:07:48<12:24:11,  3.31it/s]
 60%|██████    | 223540/371472 [7:07:48<12:24:02,  3.31it/s]
                                                            
{'loss': 2.9943, 'learning_rate': 4.586017798271886e-07, 'epoch': 9.63}
+
 60%|██████    | 223540/371472 [7:07:48<12:24:02,  3.31it/s]
 60%|██████    | 223541/371472 [7:07:48<12:17:07,  3.34it/s]
 60%|██████    | 223542/371472 [7:07:48<11:57:01,  3.44it/s]
 60%|██████    | 223543/371472 [7:07:49<12:02:09,  3.41it/s]
 60%|██████    | 223544/371472 [7:07:49<11:36:36,  3.54it/s]
 60%|██████    | 223545/371472 [7:07:49<11:31:26,  3.57it/s]
 60%|██████    | 223546/371472 [7:07:50<11:42:49,  3.51it/s]
 60%|██████    | 223547/371472 [7:07:50<11:35:53,  3.54it/s]
 60%|██████    | 223548/371472 [7:07:50<11:41:56,  3.51it/s]
 60%|██████    | 223549/371472 [7:07:50<11:18:21,  3.63it/s]
 60%|██████    | 223550/371472 [7:07:51<11:21:20,  3.62it/s]
 60%|██████    | 223551/371472 [7:07:51<11:14:56,  3.65it/s]
 60%|██████    | 223552/371472 [7:07:51<11:52:00,  3.46it/s]
 60%|██████    | 223553/371472 [7:07:51<11:45:40,  3.49it/s]
 60%|██████    | 223554/371472 [7:07:52<12:31:56,  3.28it/s]
 60%|██████    | 223555/371472 [7:07:52<12:23:33,  3.32it/s]
 60%|██████    | 223556/371472 [7:07:52<12:03:24,  3.41it/s]
 60%|██████    | 223557/371472 [7:07:53<12:11:59,  3.37it/s]
 60%|██████    | 223558/371472 [7:07:53<11:58:35,  3.43it/s]
 60%|██████    | 223559/371472 [7:07:53<11:58:26,  3.43it/s]
 60%|██████    | 223560/371472 [7:07:54<12:02:15,  3.41it/s]
                                                            
{'loss': 2.8718, 'learning_rate': 4.585532978517098e-07, 'epoch': 9.63}
+
 60%|██████    | 223560/371472 [7:07:54<12:02:15,  3.41it/s]
 60%|██████    | 223561/371472 [7:07:54<13:11:05,  3.12it/s]
 60%|██████    | 223562/371472 [7:07:54<12:20:11,  3.33it/s]
 60%|██████    | 223563/371472 [7:07:55<12:20:59,  3.33it/s]
 60%|██████    | 223564/371472 [7:07:55<13:20:19,  3.08it/s]
 60%|██████    | 223565/371472 [7:07:55<12:45:58,  3.22it/s]
 60%|██████    | 223566/371472 [7:07:55<12:35:31,  3.26it/s]
 60%|██████    | 223567/371472 [7:07:56<12:23:33,  3.32it/s]
 60%|██████    | 223568/371472 [7:07:56<12:08:08,  3.39it/s]
 60%|██████    | 223569/371472 [7:07:56<12:18:25,  3.34it/s]
 60%|██████    | 223570/371472 [7:07:57<12:14:40,  3.36it/s]
 60%|██████    | 223571/371472 [7:07:57<12:07:57,  3.39it/s]
 60%|██████    | 223572/371472 [7:07:57<11:55:17,  3.45it/s]
 60%|██████    | 223573/371472 [7:07:58<13:35:40,  3.02it/s]
 60%|██████    | 223574/371472 [7:07:58<12:47:00,  3.21it/s]
 60%|██████    | 223575/371472 [7:07:58<13:11:09,  3.12it/s]
 60%|██████    | 223576/371472 [7:07:59<12:58:49,  3.16it/s]
 60%|██████    | 223577/371472 [7:07:59<12:50:04,  3.20it/s]
 60%|██████    | 223578/371472 [7:07:59<14:02:41,  2.93it/s]
 60%|██████    | 223579/371472 [7:08:00<13:16:25,  3.09it/s]
 60%|██████    | 223580/371472 [7:08:00<12:45:52,  3.22it/s]
                                                            
{'loss': 2.7683, 'learning_rate': 4.5850481587623084e-07, 'epoch': 9.63}
+
 60%|██████    | 223580/371472 [7:08:00<12:45:52,  3.22it/s]
 60%|██████    | 223581/371472 [7:08:00<12:25:23,  3.31it/s]
 60%|██████    | 223582/371472 [7:08:00<12:13:27,  3.36it/s]
 60%|██████    | 223583/371472 [7:08:01<12:51:07,  3.20it/s]
 60%|██████    | 223584/371472 [7:08:01<12:52:53,  3.19it/s]
 60%|██████    | 223585/371472 [7:08:01<12:30:46,  3.28it/s]
 60%|██████    | 223586/371472 [7:08:02<12:38:50,  3.25it/s]
 60%|██████    | 223587/371472 [7:08:02<12:28:56,  3.29it/s]
 60%|██████    | 223588/371472 [7:08:02<12:29:16,  3.29it/s]
 60%|██████    | 223589/371472 [7:08:03<12:47:27,  3.21it/s]
 60%|██████    | 223590/371472 [7:08:03<12:31:09,  3.28it/s]
 60%|██████    | 223591/371472 [7:08:03<12:53:44,  3.19it/s]
 60%|██████    | 223592/371472 [7:08:04<13:45:55,  2.98it/s]
 60%|██████    | 223593/371472 [7:08:04<13:26:23,  3.06it/s]
 60%|██████    | 223594/371472 [7:08:04<13:27:14,  3.05it/s]
 60%|██████    | 223595/371472 [7:08:05<13:18:24,  3.09it/s]
 60%|██████    | 223596/371472 [7:08:05<12:44:14,  3.22it/s]
 60%|██████    | 223597/371472 [7:08:05<13:14:58,  3.10it/s]
 60%|██████    | 223598/371472 [7:08:05<12:47:39,  3.21it/s]
 60%|██████    | 223599/371472 [7:08:06<12:43:18,  3.23it/s]
 60%|████���█    | 223600/371472 [7:08:06<12:16:22,  3.35it/s]
                                                            
{'loss': 2.8745, 'learning_rate': 4.58456333900752e-07, 'epoch': 9.63}
+
 60%|██████    | 223600/371472 [7:08:06<12:16:22,  3.35it/s]
 60%|██████    | 223601/371472 [7:08:06<12:28:41,  3.29it/s]
 60%|██████    | 223602/371472 [7:08:07<12:08:08,  3.38it/s]
 60%|██████    | 223603/371472 [7:08:07<12:25:39,  3.31it/s]
 60%|██████    | 223604/371472 [7:08:07<12:13:21,  3.36it/s]
 60%|██████    | 223605/371472 [7:08:08<12:30:01,  3.29it/s]
 60%|██████    | 223606/371472 [7:08:08<13:35:51,  3.02it/s]
 60%|██████    | 223607/371472 [7:08:08<13:05:27,  3.14it/s]
 60%|██████    | 223608/371472 [7:08:09<13:32:55,  3.03it/s]
 60%|██████    | 223609/371472 [7:08:09<13:43:07,  2.99it/s]
 60%|██████    | 223610/371472 [7:08:09<13:12:20,  3.11it/s]
 60%|██████    | 223611/371472 [7:08:10<13:49:05,  2.97it/s]
 60%|██████    | 223612/371472 [7:08:10<13:57:57,  2.94it/s]
 60%|██████    | 223613/371472 [7:08:10<13:43:19,  2.99it/s]
 60%|██████    | 223614/371472 [7:08:11<15:33:15,  2.64it/s]
 60%|██████    | 223615/371472 [7:08:11<14:28:41,  2.84it/s]
 60%|██████    | 223616/371472 [7:08:11<14:42:02,  2.79it/s]
 60%|██████    | 223617/371472 [7:08:12<13:42:42,  3.00it/s]
 60%|██████    | 223618/371472 [7:08:12<12:53:42,  3.18it/s]
 60%|██████    | 223619/371472 [7:08:12<12:27:34,  3.30it/s]
 60%|██████    | 223620/371472 [7:08:13<12:10:15,  3.37it/s]
                                                            
{'loss': 2.806, 'learning_rate': 4.584078519252731e-07, 'epoch': 9.63}
+
 60%|██████    | 223620/371472 [7:08:13<12:10:15,  3.37it/s]
 60%|██████    | 223621/371472 [7:08:13<12:06:45,  3.39it/s]
 60%|██████    | 223622/371472 [7:08:13<11:45:07,  3.49it/s]
 60%|██████    | 223623/371472 [7:08:13<11:35:07,  3.54it/s]
 60%|██████    | 223624/371472 [7:08:14<11:48:22,  3.48it/s]
 60%|██████    | 223625/371472 [7:08:14<11:59:01,  3.43it/s]
 60%|██████    | 223626/371472 [7:08:14<12:45:12,  3.22it/s]
 60%|██████    | 223627/371472 [7:08:15<13:48:24,  2.97it/s]
 60%|██████    | 223628/371472 [7:08:15<13:05:19,  3.14it/s]
 60%|██████    | 223629/371472 [7:08:15<12:51:32,  3.19it/s]
 60%|██████    | 223630/371472 [7:08:16<12:37:32,  3.25it/s]
 60%|██████    | 223631/371472 [7:08:16<12:30:05,  3.28it/s]
 60%|██████    | 223632/371472 [7:08:16<12:29:30,  3.29it/s]
 60%|██████    | 223633/371472 [7:08:16<12:21:39,  3.32it/s]
 60%|██████    | 223634/371472 [7:08:17<12:04:11,  3.40it/s]
 60%|██████    | 223635/371472 [7:08:17<11:53:42,  3.45it/s]
 60%|██████    | 223636/371472 [7:08:17<11:41:00,  3.51it/s]
 60%|██████    | 223637/371472 [7:08:18<11:55:18,  3.44it/s]
 60%|██████    | 223638/371472 [7:08:18<12:12:19,  3.36it/s]
 60%|██████    | 223639/371472 [7:08:18<12:09:44,  3.38it/s]
 60%|██████    | 223640/371472 [7:08:19<12:22:46,  3.32it/s]
                                                            
{'loss': 2.7738, 'learning_rate': 4.583593699497942e-07, 'epoch': 9.63}
+
 60%|██████    | 223640/371472 [7:08:19<12:22:46,  3.32it/s]
 60%|██████    | 223641/371472 [7:08:19<12:16:31,  3.35it/s]
 60%|██████    | 223642/371472 [7:08:19<12:02:47,  3.41it/s]
 60%|██████    | 223643/371472 [7:08:19<12:01:16,  3.42it/s]
 60%|██████    | 223644/371472 [7:08:20<11:55:05,  3.45it/s]
 60%|██████    | 223645/371472 [7:08:20<11:59:20,  3.43it/s]
 60%|██████    | 223646/371472 [7:08:20<12:37:58,  3.25it/s]
 60%|██████    | 223647/371472 [7:08:21<14:29:45,  2.83it/s]
 60%|██████    | 223648/371472 [7:08:21<13:38:25,  3.01it/s]
 60%|██████    | 223649/371472 [7:08:21<13:09:27,  3.12it/s]
 60%|██████    | 223650/371472 [7:08:22<12:43:19,  3.23it/s]
 60%|██████    | 223651/371472 [7:08:22<12:18:15,  3.34it/s]
 60%|██████    | 223652/371472 [7:08:22<12:37:52,  3.25it/s]
 60%|██████    | 223653/371472 [7:08:23<12:21:15,  3.32it/s]
 60%|██████    | 223654/371472 [7:08:23<12:34:59,  3.26it/s]
 60%|██████    | 223655/371472 [7:08:23<12:08:55,  3.38it/s]
 60%|██████    | 223656/371472 [7:08:23<12:36:05,  3.26it/s]
 60%|██████    | 223657/371472 [7:08:24<12:44:11,  3.22it/s]
 60%|██████    | 223658/371472 [7:08:24<12:38:39,  3.25it/s]
 60%|██████    | 223659/371472 [7:08:24<12:26:22,  3.30it/s]
 60%|██████    | 223660/371472 [7:08:25<12:12:48,  3.36it/s]
                                                            
{'loss': 2.8604, 'learning_rate': 4.583108879743153e-07, 'epoch': 9.63}
+
 60%|██████    | 223660/371472 [7:08:25<12:12:48,  3.36it/s]
 60%|██████    | 223661/371472 [7:08:25<12:04:10,  3.40it/s]
 60%|██████    | 223662/371472 [7:08:25<11:54:35,  3.45it/s]
 60%|██████    | 223663/371472 [7:08:26<12:13:46,  3.36it/s]
 60%|██████    | 223664/371472 [7:08:26<12:29:53,  3.29it/s]
 60%|██████    | 223665/371472 [7:08:26<12:33:53,  3.27it/s]
 60%|██████    | 223666/371472 [7:08:26<12:26:47,  3.30it/s]
 60%|██████    | 223667/371472 [7:08:27<12:24:05,  3.31it/s]
 60%|██████    | 223668/371472 [7:08:27<12:28:03,  3.29it/s]
 60%|██████    | 223669/371472 [7:08:27<12:27:38,  3.29it/s]
 60%|██████    | 223670/371472 [7:08:28<12:50:23,  3.20it/s]
 60%|██████    | 223671/371472 [7:08:28<12:21:08,  3.32it/s]
 60%|██████    | 223672/371472 [7:08:28<12:12:00,  3.37it/s]
 60%|██████    | 223673/371472 [7:08:29<13:07:54,  3.13it/s]
 60%|██████    | 223674/371472 [7:08:29<13:08:27,  3.12it/s]
 60%|██████    | 223675/371472 [7:08:29<13:22:59,  3.07it/s]
 60%|██████    | 223676/371472 [7:08:30<13:09:05,  3.12it/s]
 60%|██████    | 223677/371472 [7:08:30<12:38:03,  3.25it/s]
 60%|██████    | 223678/371472 [7:08:30<12:30:07,  3.28it/s]
 60%|██████    | 223679/371472 [7:08:31<12:57:53,  3.17it/s]
 60%|██████    | 223680/371472 [7:08:31<12:54:12,  3.18it/s]
                                                            
{'loss': 2.8135, 'learning_rate': 4.5826240599883646e-07, 'epoch': 9.63}
+
 60%|██████    | 223680/371472 [7:08:31<12:54:12,  3.18it/s]
 60%|██████    | 223681/371472 [7:08:31<12:27:59,  3.29it/s]
 60%|██████    | 223682/371472 [7:08:31<12:01:16,  3.42it/s]
 60%|██████    | 223683/371472 [7:08:32<12:25:43,  3.30it/s]
 60%|██████    | 223684/371472 [7:08:32<12:10:08,  3.37it/s]
 60%|██████    | 223685/371472 [7:08:32<12:36:35,  3.26it/s]
 60%|██████    | 223686/371472 [7:08:33<13:02:39,  3.15it/s]
 60%|██████    | 223687/371472 [7:08:33<12:30:10,  3.28it/s]
 60%|██████    | 223688/371472 [7:08:33<12:07:15,  3.39it/s]
 60%|██████    | 223689/371472 [7:08:33<12:00:21,  3.42it/s]
 60%|██████    | 223690/371472 [7:08:34<11:35:55,  3.54it/s]
 60%|██████    | 223691/371472 [7:08:34<12:02:45,  3.41it/s]
 60%|██████    | 223692/371472 [7:08:34<12:01:03,  3.42it/s]
 60%|██████    | 223693/371472 [7:08:35<12:57:37,  3.17it/s]
 60%|██████    | 223694/371472 [7:08:35<12:54:24,  3.18it/s]
 60%|██████    | 223695/371472 [7:08:35<12:54:17,  3.18it/s]
 60%|██████    | 223696/371472 [7:08:36<12:45:15,  3.22it/s]
 60%|██████    | 223697/371472 [7:08:36<12:30:34,  3.28it/s]
 60%|██████    | 223698/371472 [7:08:36<12:41:20,  3.23it/s]
 60%|██████    | 223699/371472 [7:08:37<12:22:24,  3.32it/s]
 60%|██████    | 223700/371472 [7:08:37<12:21:15,  3.32it/s]
                                                            
{'loss': 2.8537, 'learning_rate': 4.5821392402335753e-07, 'epoch': 9.64}
+
 60%|██████    | 223700/371472 [7:08:37<12:21:15,  3.32it/s]
 60%|██████    | 223701/371472 [7:08:37<12:01:10,  3.42it/s]
 60%|██████    | 223702/371472 [7:08:37<12:52:27,  3.19it/s]
 60%|██████    | 223703/371472 [7:08:38<12:35:40,  3.26it/s]
 60%|██████    | 223704/371472 [7:08:38<12:19:41,  3.33it/s]
 60%|██████    | 223705/371472 [7:08:38<12:23:44,  3.31it/s]
 60%|██████    | 223706/371472 [7:08:39<12:23:42,  3.31it/s]
 60%|██████    | 223707/371472 [7:08:39<12:23:11,  3.31it/s]
 60%|██████    | 223708/371472 [7:08:39<12:34:06,  3.27it/s]
 60%|██████    | 223709/371472 [7:08:40<12:21:00,  3.32it/s]
 60%|██████    | 223710/371472 [7:08:40<11:56:26,  3.44it/s]
 60%|██████    | 223711/371472 [7:08:40<11:55:21,  3.44it/s]
 60%|██████    | 223712/371472 [7:08:40<12:35:50,  3.26it/s]
 60%|██████    | 223713/371472 [7:08:41<12:58:45,  3.16it/s]
 60%|██████    | 223714/371472 [7:08:41<12:30:20,  3.28it/s]
 60%|██████    | 223715/371472 [7:08:41<12:19:02,  3.33it/s]
 60%|██████    | 223716/371472 [7:08:42<11:53:08,  3.45it/s]
 60%|██████    | 223717/371472 [7:08:42<12:43:03,  3.23it/s]
 60%|██████    | 223718/371472 [7:08:42<12:26:54,  3.30it/s]
 60%|██████    | 223719/371472 [7:08:43<12:53:19,  3.18it/s]
 60%|██████    | 223720/371472 [7:08:43<12:39:18,  3.24it/s]
                                                            
{'loss': 2.7165, 'learning_rate': 4.5816544204787866e-07, 'epoch': 9.64}
+
 60%|██████    | 223720/371472 [7:08:43<12:39:18,  3.24it/s]
 60%|██████    | 223721/371472 [7:08:43<12:37:17,  3.25it/s]
 60%|██████    | 223722/371472 [7:08:44<12:44:46,  3.22it/s]
 60%|██████    | 223723/371472 [7:08:44<12:12:12,  3.36it/s]
 60%|██████    | 223724/371472 [7:08:44<12:02:27,  3.41it/s]
 60%|██████    | 223725/371472 [7:08:44<11:44:27,  3.50it/s]
 60%|██████    | 223726/371472 [7:08:45<12:26:21,  3.30it/s]
 60%|██████    | 223727/371472 [7:08:45<12:22:27,  3.32it/s]
 60%|██████    | 223728/371472 [7:08:45<12:02:41,  3.41it/s]
 60%|██████    | 223729/371472 [7:08:46<11:55:04,  3.44it/s]
 60%|██████    | 223730/371472 [7:08:46<11:39:34,  3.52it/s]
 60%|██████    | 223731/371472 [7:08:46<11:45:52,  3.49it/s]
 60%|██████    | 223732/371472 [7:08:47<12:57:37,  3.17it/s]
 60%|██████    | 223733/371472 [7:08:47<12:20:49,  3.32it/s]
 60%|██████    | 223734/371472 [7:08:47<12:29:02,  3.29it/s]
 60%|██████    | 223735/371472 [7:08:47<12:18:37,  3.33it/s]
 60%|██████    | 223736/371472 [7:08:48<12:03:07,  3.41it/s]
 60%|██████    | 223737/371472 [7:08:48<11:48:36,  3.47it/s]
 60%|██████    | 223738/371472 [7:08:48<11:45:20,  3.49it/s]
 60%|██████    | 223739/371472 [7:08:49<11:48:18,  3.48it/s]
 60%|██████    | 223740/371472 [7:08:49<11:40:35,  3.51it/s]
                                                            
{'loss': 2.6836, 'learning_rate': 4.5811696007239973e-07, 'epoch': 9.64}
+
 60%|██████    | 223740/371472 [7:08:49<11:40:35,  3.51it/s]
 60%|██████    | 223741/371472 [7:08:49<12:08:14,  3.38it/s]
 60%|██████    | 223742/371472 [7:08:49<12:07:34,  3.38it/s]
 60%|██████    | 223743/371472 [7:08:50<12:33:54,  3.27it/s]
 60%|██████    | 223744/371472 [7:08:50<13:28:17,  3.05it/s]
 60%|██████    | 223745/371472 [7:08:50<13:28:01,  3.05it/s]
 60%|██████    | 223746/371472 [7:08:51<14:15:13,  2.88it/s]
 60%|██████    | 223747/371472 [7:08:51<14:20:58,  2.86it/s]
 60%|██████    | 223748/371472 [7:08:52<14:08:30,  2.90it/s]
 60%|██████    | 223749/371472 [7:08:52<14:41:52,  2.79it/s]
 60%|██████    | 223750/371472 [7:08:52<14:05:37,  2.91it/s]
 60%|██████    | 223751/371472 [7:08:53<14:14:18,  2.88it/s]
 60%|██████    | 223752/371472 [7:08:53<13:41:59,  3.00it/s]
 60%|██████    | 223753/371472 [7:08:53<12:58:50,  3.16it/s]
 60%|██████    | 223754/371472 [7:08:53<12:28:41,  3.29it/s]
 60%|██████    | 223755/371472 [7:08:54<13:01:03,  3.15it/s]
 60%|██████    | 223756/371472 [7:08:54<13:02:19,  3.15it/s]
 60%|██████    | 223757/371472 [7:08:54<13:24:29,  3.06it/s]
 60%|██████    | 223758/371472 [7:08:55<12:59:25,  3.16it/s]
 60%|██████    | 223759/371472 [7:08:55<13:06:27,  3.13it/s]
 60%|██████    | 223760/371472 [7:08:55<12:44:01,  3.22it/s]
                                                            
{'loss': 2.6913, 'learning_rate': 4.580684780969209e-07, 'epoch': 9.64}
+
 60%|██████    | 223760/371472 [7:08:55<12:44:01,  3.22it/s]
 60%|██████    | 223761/371472 [7:08:56<12:31:46,  3.27it/s]
 60%|██████    | 223762/371472 [7:08:56<12:36:50,  3.25it/s]
 60%|██████    | 223763/371472 [7:08:56<12:21:34,  3.32it/s]
 60%|██████    | 223764/371472 [7:08:57<12:11:13,  3.37it/s]
 60%|██████    | 223765/371472 [7:08:57<12:20:10,  3.33it/s]
 60%|██████    | 223766/371472 [7:08:57<13:12:06,  3.11it/s]
 60%|██████    | 223767/371472 [7:08:58<13:02:07,  3.15it/s]
 60%|██████    | 223768/371472 [7:08:58<13:13:54,  3.10it/s]
 60%|██████    | 223769/371472 [7:08:58<12:40:37,  3.24it/s]
 60%|██████    | 223770/371472 [7:08:58<12:38:23,  3.25it/s]
 60%|██████    | 223771/371472 [7:08:59<12:55:00,  3.18it/s]
 60%|██████    | 223772/371472 [7:08:59<13:03:11,  3.14it/s]
 60%|██████    | 223773/371472 [7:08:59<12:57:14,  3.17it/s]
 60%|██████    | 223774/371472 [7:09:00<12:55:30,  3.17it/s]
 60%|██████    | 223775/371472 [7:09:00<12:24:19,  3.31it/s]
 60%|██████    | 223776/371472 [7:09:00<12:12:11,  3.36it/s]
 60%|██████    | 223777/371472 [7:09:01<11:52:54,  3.45it/s]
 60%|██████    | 223778/371472 [7:09:01<11:47:09,  3.48it/s]
 60%|██████    | 223779/371472 [7:09:01<12:38:01,  3.25it/s]
 60%|██████    | 223780/371472 [7:09:01<12:11:06,  3.37it/s]
                                                            
{'loss': 2.6725, 'learning_rate': 4.580199961214419e-07, 'epoch': 9.64}
+
 60%|██████    | 223780/371472 [7:09:01<12:11:06,  3.37it/s]
 60%|██████    | 223781/371472 [7:09:02<12:02:52,  3.41it/s]
 60%|█��████    | 223782/371472 [7:09:02<11:57:15,  3.43it/s]
 60%|██████    | 223783/371472 [7:09:02<11:54:23,  3.45it/s]
 60%|██████    | 223784/371472 [7:09:03<11:44:38,  3.49it/s]
 60%|██████    | 223785/371472 [7:09:03<12:07:21,  3.38it/s]
 60%|██████    | 223786/371472 [7:09:03<12:23:52,  3.31it/s]
 60%|██████    | 223787/371472 [7:09:03<11:58:27,  3.43it/s]
 60%|██████    | 223788/371472 [7:09:04<11:42:36,  3.50it/s]
 60%|██████    | 223789/371472 [7:09:04<11:42:18,  3.50it/s]
 60%|██████    | 223790/371472 [7:09:04<11:44:33,  3.49it/s]
 60%|██████    | 223791/371472 [7:09:05<12:02:00,  3.41it/s]
 60%|██████    | 223792/371472 [7:09:05<11:59:17,  3.42it/s]
 60%|██████    | 223793/371472 [7:09:05<12:03:43,  3.40it/s]
 60%|██████    | 223794/371472 [7:09:06<12:02:18,  3.41it/s]
 60%|██████    | 223795/371472 [7:09:06<11:49:23,  3.47it/s]
 60%|██████    | 223796/371472 [7:09:06<11:52:53,  3.45it/s]
 60%|██████    | 223797/371472 [7:09:06<11:44:41,  3.49it/s]
 60%|██████    | 223798/371472 [7:09:07<12:46:27,  3.21it/s]
 60%|██████    | 223799/371472 [7:09:07<12:26:38,  3.30it/s]
 60%|██████    | 223800/371472 [7:09:07<12:40:02,  3.24it/s]
                                                            
{'loss': 2.8223, 'learning_rate': 4.57971514145963e-07, 'epoch': 9.64}
+
 60%|██████    | 223800/371472 [7:09:07<12:40:02,  3.24it/s]
 60%|██████    | 223801/371472 [7:09:08<14:24:57,  2.85it/s]
 60%|██████    | 223802/371472 [7:09:08<13:48:28,  2.97it/s]
 60%|██████    | 223803/371472 [7:09:08<13:24:34,  3.06it/s]
 60%|██████    | 223804/371472 [7:09:09<13:20:54,  3.07it/s]
 60%|██████    | 223805/371472 [7:09:09<12:40:37,  3.24it/s]
 60%|██████    | 223806/371472 [7:09:09<12:33:06,  3.27it/s]
 60%|██████    | 223807/371472 [7:09:10<12:40:42,  3.24it/s]
 60%|██████    | 223808/371472 [7:09:10<12:26:48,  3.30it/s]
 60%|██████    | 223809/371472 [7:09:10<12:46:43,  3.21it/s]
 60%|██████    | 223810/371472 [7:09:11<12:59:27,  3.16it/s]
 60%|██████    | 223811/371472 [7:09:11<12:39:47,  3.24it/s]
 60%|██████    | 223812/371472 [7:09:11<13:16:17,  3.09it/s]
 60%|██████    | 223813/371472 [7:09:12<12:50:57,  3.19it/s]
 60%|██████    | 223814/371472 [7:09:12<12:39:02,  3.24it/s]
 60%|██████    | 223815/371472 [7:09:12<13:26:21,  3.05it/s]
 60%|██████    | 223816/371472 [7:09:12<12:59:08,  3.16it/s]
 60%|██████    | 223817/371472 [7:09:13<13:04:04,  3.14it/s]
 60%|██████    | 223818/371472 [7:09:13<12:44:47,  3.22it/s]
 60%|██████    | 223819/371472 [7:09:13<12:46:21,  3.21it/s]
 60%|██████    | 223820/371472 [7:09:14<12:43:49,  3.22it/s]
                                                            
{'loss': 2.7259, 'learning_rate': 4.579230321704842e-07, 'epoch': 9.64}
+
 60%|██████    | 223820/371472 [7:09:14<12:43:49,  3.22it/s]
 60%|██████    | 223821/371472 [7:09:14<12:28:21,  3.29it/s]
 60%|██████    | 223822/371472 [7:09:14<12:10:18,  3.37it/s]
 60%|██████    | 223823/371472 [7:09:15<11:49:43,  3.47it/s]
 60%|██████    | 223824/371472 [7:09:15<13:53:05,  2.95it/s]
 60%|██████    | 223825/371472 [7:09:15<13:24:24,  3.06it/s]
 60%|██████    | 223826/371472 [7:09:16<12:58:34,  3.16it/s]
 60%|██████    | 223827/371472 [7:09:16<12:56:26,  3.17it/s]
 60%|██████    | 223828/371472 [7:09:16<13:03:39,  3.14it/s]
 60%|██████    | 223829/371472 [7:09:17<12:33:06,  3.27it/s]
 60%|██████    | 223830/371472 [7:09:17<12:22:20,  3.31it/s]
 60%|██████    | 223831/371472 [7:09:17<12:21:51,  3.32it/s]
 60%|██████    | 223832/371472 [7:09:17<12:18:58,  3.33it/s]
 60%|██████    | 223833/371472 [7:09:18<12:07:21,  3.38it/s]
 60%|██████    | 223834/371472 [7:09:18<13:16:38,  3.09it/s]
 60%|██████    | 223835/371472 [7:09:18<12:48:34,  3.20it/s]
 60%|██████    | 223836/371472 [7:09:19<12:11:48,  3.36it/s]
 60%|██████    | 223837/371472 [7:09:19<12:55:09,  3.17it/s]
 60%|██████    | 223838/371472 [7:09:19<12:41:57,  3.23it/s]
 60%|██████    | 223839/371472 [7:09:20<13:06:18,  3.13it/s]
 60%|██████    | 223840/371472 [7:09:20<12:38:45,  3.24it/s]
                                                            
{'loss': 2.816, 'learning_rate': 4.578745501950052e-07, 'epoch': 9.64}
+
 60%|██████    | 223840/371472 [7:09:20<12:38:45,  3.24it/s]
 60%|██████    | 223841/371472 [7:09:20<12:21:06,  3.32it/s]
 60%|██████    | 223842/371472 [7:09:20<12:08:02,  3.38it/s]
 60%|██████    | 223843/371472 [7:09:21<12:28:44,  3.29it/s]
 60%|██████    | 223844/371472 [7:09:21<12:52:51,  3.18it/s]
 60%|██████    | 223845/371472 [7:09:21<12:26:18,  3.30it/s]
 60%|██████    | 223846/371472 [7:09:22<12:13:59,  3.35it/s]
 60%|██████    | 223847/371472 [7:09:22<12:23:22,  3.31it/s]
 60%|██████    | 223848/371472 [7:09:22<12:16:48,  3.34it/s]
 60%|██████    | 223849/371472 [7:09:23<11:57:58,  3.43it/s]
 60%|██████    | 223850/371472 [7:09:23<11:53:17,  3.45it/s]
 60%|██████    | 223851/371472 [7:09:23<12:02:42,  3.40it/s]
 60%|██████    | 223852/371472 [7:09:23<11:57:18,  3.43it/s]
 60%|██████    | 223853/371472 [7:09:24<11:54:03,  3.45it/s]
 60%|██████    | 223854/371472 [7:09:24<11:54:51,  3.44it/s]
 60%|██████    | 223855/371472 [7:09:24<12:02:51,  3.40it/s]
 60%|██████    | 223856/371472 [7:09:25<12:07:18,  3.38it/s]
 60%|██████    | 223857/371472 [7:09:25<12:08:19,  3.38it/s]
 60%|██████    | 223858/371472 [7:09:25<12:09:25,  3.37it/s]
 60%|██████    | 223859/371472 [7:09:25<11:59:47,  3.42it/s]
 60%|██████    | 223860/371472 [7:09:26<14:46:18,  2.78it/s]
                                                            
{'loss': 2.7359, 'learning_rate': 4.5782606821952637e-07, 'epoch': 9.64}
+
 60%|██████    | 223860/371472 [7:09:26<14:46:18,  2.78it/s]
 60%|██████    | 223861/371472 [7:09:26<14:00:31,  2.93it/s]
 60%|██████    | 223862/371472 [7:09:27<13:15:07,  3.09it/s]
 60%|██████    | 223863/371472 [7:09:27<12:41:25,  3.23it/s]
 60%|██████    | 223864/371472 [7:09:27<13:01:31,  3.15it/s]
 60%|██████    | 223865/371472 [7:09:28<13:03:05,  3.14it/s]
 60%|██████    | 223866/371472 [7:09:28<12:25:25,  3.30it/s]
 60%|██████    | 223867/371472 [7:09:28<12:15:50,  3.34it/s]
 60%|██████    | 223868/371472 [7:09:28<12:00:31,  3.41it/s]
 60%|██████    | 223869/371472 [7:09:29<12:50:33,  3.19it/s]
 60%|██████    | 223870/371472 [7:09:29<12:29:05,  3.28it/s]
 60%|██████    | 223871/371472 [7:09:29<12:19:02,  3.33it/s]
 60%|██████    | 223872/371472 [7:09:30<12:32:31,  3.27it/s]
 60%|██████    | 223873/371472 [7:09:30<12:31:25,  3.27it/s]
 60%|██████    | 223874/371472 [7:09:30<12:41:09,  3.23it/s]
 60%|██████    | 223875/371472 [7:09:31<12:22:57,  3.31it/s]
 60%|██████    | 223876/371472 [7:09:31<13:38:51,  3.00it/s]
 60%|██████    | 223877/371472 [7:09:31<12:55:24,  3.17it/s]
 60%|██████    | 223878/371472 [7:09:32<14:07:45,  2.90it/s]
 60%|██████    | 223879/371472 [7:09:32<13:11:38,  3.11it/s]
 60%|██████    | 223880/371472 [7:09:32<12:35:22,  3.26it/s]
                                                            
{'loss': 2.7473, 'learning_rate': 4.5777758624404744e-07, 'epoch': 9.64}
+
 60%|██████    | 223880/371472 [7:09:32<12:35:22,  3.26it/s]
 60%|██████    | 223881/371472 [7:09:33<13:19:04,  3.08it/s]
 60%|██████    | 223882/371472 [7:09:33<12:41:59,  3.23it/s]
 60%|██████    | 223883/371472 [7:09:33<12:38:18,  3.24it/s]
 60%|██████    | 223884/371472 [7:09:33<12:05:16,  3.39it/s]
 60%|██████    | 223885/371472 [7:09:34<11:55:00,  3.44it/s]
 60%|██████    | 223886/371472 [7:09:34<12:07:02,  3.38it/s]
 60%|██████    | 223887/371472 [7:09:34<12:02:59,  3.40it/s]
 60%|██████    | 223888/371472 [7:09:35<12:17:52,  3.33it/s]
 60%|██████    | 223889/371472 [7:09:35<12:05:45,  3.39it/s]
 60%|██████    | 223890/371472 [7:09:35<11:50:00,  3.46it/s]
 60%|██████    | 223891/371472 [7:09:35<11:49:26,  3.47it/s]
 60%|██████    | 223892/371472 [7:09:36<12:37:54,  3.25it/s]
 60%|██████    | 223893/371472 [7:09:36<12:26:35,  3.29it/s]
 60%|██████    | 223894/371472 [7:09:36<12:32:11,  3.27it/s]
 60%|██████    | 223895/371472 [7:09:37<12:26:49,  3.29it/s]
 60%|██████    | 223896/371472 [7:09:37<13:10:37,  3.11it/s]
 60%|██████    | 223897/371472 [7:09:37<12:58:12,  3.16it/s]
 60%|██████    | 223898/371472 [7:09:38<12:54:59,  3.17it/s]
 60%|██████    | 223899/371472 [7:09:38<13:15:24,  3.09it/s]
 60%|██████    | 223900/371472 [7:09:38<12:51:38,  3.19it/s]
                                                            
{'loss': 2.8182, 'learning_rate': 4.5772910426856857e-07, 'epoch': 9.64}
+
 60%|██████    | 223900/371472 [7:09:38<12:51:38,  3.19it/s]
 60%|██████    | 223901/371472 [7:09:39<12:35:07,  3.26it/s]
 60%|██████    | 223902/371472 [7:09:39<12:27:57,  3.29it/s]
 60%|██████    | 223903/371472 [7:09:39<12:18:50,  3.33it/s]
 60%|██████    | 223904/371472 [7:09:39<12:31:24,  3.27it/s]
 60%|█████��    | 223905/371472 [7:09:40<12:13:56,  3.35it/s]
 60%|██████    | 223906/371472 [7:09:40<11:53:31,  3.45it/s]
 60%|██████    | 223907/371472 [7:09:40<12:04:56,  3.39it/s]
 60%|██████    | 223908/371472 [7:09:41<11:45:05,  3.49it/s]
 60%|██████    | 223909/371472 [7:09:41<12:21:59,  3.31it/s]
 60%|██████    | 223910/371472 [7:09:41<12:08:35,  3.38it/s]
 60%|██████    | 223911/371472 [7:09:42<11:58:38,  3.42it/s]
 60%|██████    | 223912/371472 [7:09:42<11:50:13,  3.46it/s]
 60%|██████    | 223913/371472 [7:09:42<12:06:54,  3.38it/s]
 60%|██████    | 223914/371472 [7:09:42<11:45:46,  3.48it/s]
 60%|██████    | 223915/371472 [7:09:43<11:43:14,  3.50it/s]
 60%|██████    | 223916/371472 [7:09:43<12:30:16,  3.28it/s]
 60%|██████    | 223917/371472 [7:09:43<12:17:03,  3.34it/s]
 60%|██████    | 223918/371472 [7:09:44<12:10:12,  3.37it/s]
 60%|██████    | 223919/371472 [7:09:44<12:06:57,  3.38it/s]
 60%|██████    | 223920/371472 [7:09:44<11:49:28,  3.47it/s]
                                                            
{'loss': 2.7864, 'learning_rate': 4.5768062229308964e-07, 'epoch': 9.64}
+
 60%|██████    | 223920/371472 [7:09:44<11:49:28,  3.47it/s]
 60%|██████    | 223921/371472 [7:09:44<11:42:09,  3.50it/s]
 60%|██████    | 223922/371472 [7:09:45<12:43:01,  3.22it/s]
 60%|██████    | 223923/371472 [7:09:45<12:13:24,  3.35it/s]
 60%|██████    | 223924/371472 [7:09:45<11:49:15,  3.47it/s]
 60%|██████    | 223925/371472 [7:09:46<11:45:50,  3.48it/s]
 60%|██████    | 223926/371472 [7:09:46<11:29:28,  3.57it/s]
 60%|██████    | 223927/371472 [7:09:46<11:26:32,  3.58it/s]
 60%|██████    | 223928/371472 [7:09:46<11:33:42,  3.54it/s]
 60%|██████    | 223929/371472 [7:09:47<11:29:02,  3.57it/s]
 60%|██████    | 223930/371472 [7:09:47<11:22:14,  3.60it/s]
 60%|██████    | 223931/371472 [7:09:47<11:49:21,  3.47it/s]
 60%|██████    | 223932/371472 [7:09:48<12:02:16,  3.40it/s]
 60%|██████    | 223933/371472 [7:09:48<12:03:42,  3.40it/s]
 60%|██████    | 223934/371472 [7:09:48<12:04:22,  3.39it/s]
 60%|██████    | 223935/371472 [7:09:49<12:15:34,  3.34it/s]
 60%|██████    | 223936/371472 [7:09:49<12:11:09,  3.36it/s]
 60%|██████    | 223937/371472 [7:09:49<11:58:53,  3.42it/s]
 60%|██████    | 223938/371472 [7:09:49<11:38:25,  3.52it/s]
 60%|██████    | 223939/371472 [7:09:50<11:37:18,  3.53it/s]
 60%|██████    | 223940/371472 [7:09:50<11:35:11,  3.54it/s]
                                                            
{'loss': 2.8997, 'learning_rate': 4.576321403176108e-07, 'epoch': 9.65}
+
 60%|██████    | 223940/371472 [7:09:50<11:35:11,  3.54it/s]
 60%|██████    | 223941/371472 [7:09:50<12:08:06,  3.38it/s]
 60%|██████    | 223942/371472 [7:09:51<12:54:27,  3.17it/s]
 60%|██████    | 223943/371472 [7:09:51<12:18:20,  3.33it/s]
 60%|██████    | 223944/371472 [7:09:51<12:39:32,  3.24it/s]
 60%|██████    | 223945/371472 [7:09:51<12:39:52,  3.24it/s]
 60%|██████    | 223946/371472 [7:09:52<12:13:23,  3.35it/s]
 60%|██████    | 223947/371472 [7:09:52<12:17:45,  3.33it/s]
 60%|██████    | 223948/371472 [7:09:52<12:19:36,  3.32it/s]
 60%|██████    | 223949/371472 [7:09:53<12:02:07,  3.40it/s]
 60%|██████    | 223950/371472 [7:09:53<12:07:34,  3.38it/s]
 60%|██████    | 223951/371472 [7:09:53<12:19:46,  3.32it/s]
 60%|██████    | 223952/371472 [7:09:54<11:49:16,  3.47it/s]
 60%|██████    | 223953/371472 [7:09:54<11:32:31,  3.55it/s]
 60%|██████    | 223954/371472 [7:09:54<11:27:05,  3.58it/s]
 60%|██████    | 223955/371472 [7:09:54<12:25:29,  3.30it/s]
 60%|██████    | 223956/371472 [7:09:55<12:09:21,  3.37it/s]
 60%|██████    | 223957/371472 [7:09:55<12:42:29,  3.22it/s]
 60%|██████    | 223958/371472 [7:09:55<12:41:54,  3.23it/s]
 60%|██████    | 223959/371472 [7:09:56<12:30:48,  3.27it/s]
 60%|██████    | 223960/371472 [7:09:56<12:22:33,  3.31it/s]
                                                            
{'loss': 2.7875, 'learning_rate': 4.575836583421319e-07, 'epoch': 9.65}
+
 60%|██████    | 223960/371472 [7:09:56<12:22:33,  3.31it/s]
 60%|██████    | 223961/371472 [7:09:56<12:12:56,  3.35it/s]
 60%|██████    | 223962/371472 [7:09:57<12:26:41,  3.29it/s]
 60%|██████    | 223963/371472 [7:09:57<12:11:09,  3.36it/s]
 60%|██████    | 223964/371472 [7:09:57<12:01:06,  3.41it/s]
 60%|██████    | 223965/371472 [7:09:57<12:05:06,  3.39it/s]
 60%|██████    | 223966/371472 [7:09:58<12:01:53,  3.41it/s]
 60%|██████    | 223967/371472 [7:09:58<11:42:21,  3.50it/s]
 60%|██████    | 223968/371472 [7:09:58<11:42:56,  3.50it/s]
 60%|██████    | 223969/371472 [7:09:59<11:25:38,  3.59it/s]
 60%|██████    | 223970/371472 [7:09:59<11:52:44,  3.45it/s]
 60%|██████    | 223971/371472 [7:09:59<11:45:20,  3.49it/s]
 60%|██████    | 223972/371472 [7:09:59<11:40:29,  3.51it/s]
 60%|██████    | 223973/371472 [7:10:00<12:15:36,  3.34it/s]
 60%|██████    | 223974/371472 [7:10:00<11:56:55,  3.43it/s]
 60%|██████    | 223975/371472 [7:10:00<12:30:29,  3.28it/s]
 60%|██████    | 223976/371472 [7:10:01<12:10:11,  3.37it/s]
 60%|██████    | 223977/371472 [7:10:01<12:10:56,  3.36it/s]
 60%|██████    | 223978/371472 [7:10:01<12:38:03,  3.24it/s]
 60%|██████    | 223979/371472 [7:10:02<12:28:40,  3.28it/s]
 60%|██████    | 223980/371472 [7:10:02<12:21:22,  3.32it/s]
                                                            
{'loss': 2.7154, 'learning_rate': 4.57535176366653e-07, 'epoch': 9.65}
+
 60%|██████    | 223980/371472 [7:10:02<12:21:22,  3.32it/s]
 60%|██████    | 223981/371472 [7:10:02<12:58:21,  3.16it/s]
 60%|██████    | 223982/371472 [7:10:03<13:00:46,  3.15it/s]
 60%|██████    | 223983/371472 [7:10:03<13:27:09,  3.05it/s]
 60%|██████    | 223984/371472 [7:10:03<13:06:12,  3.13it/s]
 60%|██████    | 223985/371472 [7:10:03<12:46:29,  3.21it/s]
 60%|██████    | 223986/371472 [7:10:04<12:25:37,  3.30it/s]
 60%|██████    | 223987/371472 [7:10:04<12:06:42,  3.38it/s]
 60%|██████    | 223988/371472 [7:10:04<11:54:17,  3.44it/s]
 60%|██████    | 223989/371472 [7:10:05<11:43:09,  3.50it/s]
 60%|██████    | 223990/371472 [7:10:05<11:49:53,  3.46it/s]
 60%|██████    | 223991/371472 [7:10:05<12:16:04,  3.34it/s]
 60%|██████    | 223992/371472 [7:10:06<12:33:11,  3.26it/s]
 60%|██████    | 223993/371472 [7:10:06<12:15:49,  3.34it/s]
 60%|██████    | 223994/371472 [7:10:06<12:01:38,  3.41it/s]
 60%|██████    | 223995/371472 [7:10:06<12:39:11,  3.24it/s]
 60%|██████    | 223996/371472 [7:10:07<12:42:33,  3.22it/s]
 60%|██████    | 223997/371472 [7:10:07<12:40:06,  3.23it/s]
 60%|██████    | 223998/371472 [7:10:07<12:49:13,  3.20it/s]
 60%|██████    | 223999/371472 [7:10:08<12:50:03,  3.19it/s]
 60%|██████    | 224000/371472 [7:10:08<12:57:13,  3.16it/s]
                                                            
{'loss': 2.6767, 'learning_rate': 4.574866943911741e-07, 'epoch': 9.65}
+
 60%|██████    | 224000/371472 [7:10:08<12:57:13,  3.16it/s]
 60%|██████    | 224001/371472 [7:10:08<12:35:47,  3.25it/s]
 60%|██████    | 224002/371472 [7:10:09<12:44:45,  3.21it/s]
 60%|██████    | 224003/371472 [7:10:09<12:33:11,  3.26it/s]
 60%|██████    | 224004/371472 [7:10:09<12:12:17,  3.36it/s]
 60%|██████    | 224005/371472 [7:10:09<12:00:21,  3.41it/s]
 60%|██████    | 224006/371472 [7:10:10<11:54:17,  3.44it/s]
 60%|██████    | 224007/371472 [7:10:10<12:31:01,  3.27it/s]
 60%|██████    | 224008/371472 [7:10:10<12:11:50,  3.36it/s]
 60%|██████    | 224009/371472 [7:10:11<12:09:48,  3.37it/s]
 60%|██████    | 224010/371472 [7:10:11<12:20:28,  3.32it/s]
 60%|██████    | 224011/371472 [7:10:11<12:06:27,  3.38it/s]
 60%|██████    | 224012/371472 [7:10:12<11:51:00,  3.46it/s]
 60%|██████    | 224013/371472 [7:10:12<11:43:02,  3.50it/s]
 60%|██████    | 224014/371472 [7:10:12<11:44:58,  3.49it/s]
 60%|██████    | 224015/371472 [7:10:12<11:53:53,  3.44it/s]
 60%|██████    | 224016/371472 [7:10:13<11:51:19,  3.45it/s]
 60%|██████    | 224017/371472 [7:10:13<11:41:26,  3.50it/s]
 60%|██████    | 224018/371472 [7:10:13<12:01:31,  3.41it/s]
 60%|██████    | 224019/371472 [7:10:14<11:40:29,  3.51it/s]
 60%|██████    | 224020/371472 [7:10:14<12:27:35,  3.29it/s]
                                                            
{'loss': 2.8458, 'learning_rate': 4.5743821241569526e-07, 'epoch': 9.65}
+
 60%|██████    | 224020/371472 [7:10:14<12:27:35,  3.29it/s]
 60%|██████    | 224021/371472 [7:10:14<12:17:31,  3.33it/s]
 60%|██████    | 224022/371472 [7:10:14<12:17:03,  3.33it/s]
 60%|██████    | 224023/371472 [7:10:15<11:51:30,  3.45it/s]
 60%|██████    | 224024/371472 [7:10:15<11:54:13,  3.44it/s]
 60%|██████    | 224025/371472 [7:10:15<12:44:40,  3.21it/s]
 60%|██████    | 224026/371472 [7:10:16<12:22:06,  3.31it/s]
 60%|██████    | 224027/371472 [7:10:16<12:42:32,  3.22it/s]
 60%|██████    | 224028/371472 [7:10:16<12:25:56,  3.29it/s]
 60%|██████    | 224029/371472 [7:10:17<12:22:08,  3.31it/s]
 60%|██████    | 224030/371472 [7:10:17<12:31:35,  3.27it/s]
 60%|██████    | 224031/371472 [7:10:17<12:33:47,  3.26it/s]
 60%|██████    | 224032/371472 [7:10:18<12:44:38,  3.21it/s]
 60%|██████    | 224033/371472 [7:10:18<12:35:35,  3.25it/s]
 60%|██████    | 224034/371472 [7:10:18<12:36:55,  3.25it/s]
 60%|██████    | 224035/371472 [7:10:18<12:23:46,  3.30it/s]
 60%|██████    | 224036/371472 [7:10:19<12:33:31,  3.26it/s]
 60%|██████    | 224037/371472 [7:10:19<12:30:36,  3.27it/s]
 60%|██████    | 224038/371472 [7:10:19<13:05:31,  3.13it/s]
 60%|██████    | 224039/371472 [7:10:20<13:01:59,  3.14it/s]
 60%|██████    | 224040/371472 [7:10:20<13:05:35,  3.13it/s]
                                                            
{'loss': 2.8304, 'learning_rate': 4.573897304402163e-07, 'epoch': 9.65}
+
 60%|██████    | 224040/371472 [7:10:20<13:05:35,  3.13it/s]
 60%|██████    | 224041/371472 [7:10:20<12:48:52,  3.20it/s]
 60%|██████    | 224042/371472 [7:10:21<12:47:12,  3.20it/s]
 60%|██████    | 224043/371472 [7:10:21<12:51:39,  3.18it/s]
 60%|██████    | 224044/371472 [7:10:21<12:30:36,  3.27it/s]
 60%|██████    | 224045/371472 [7:10:22<12:14:08,  3.35it/s]
 60%|██████    | 224046/371472 [7:10:22<12:02:32,  3.40it/s]
 60%|██████    | 224047/371472 [7:10:22<11:35:25,  3.53it/s]
 60%|██████    | 224048/371472 [7:10:22<12:35:48,  3.25it/s]
 60%|██████    | 224049/371472 [7:10:23<13:16:23,  3.09it/s]
 60%|██████    | 224050/371472 [7:10:23<12:54:19,  3.17it/s]
 60%|██████    | 224051/371472 [7:10:23<13:00:08,  3.15it/s]
 60%|██████    | 224052/371472 [7:10:24<12:43:36,  3.22it/s]
 60%|██████    | 224053/371472 [7:10:24<12:39:41,  3.23it/s]
 60%|██████    | 224054/371472 [7:10:24<12:26:23,  3.29it/s]
 60%|██████    | 224055/371472 [7:10:25<12:38:27,  3.24it/s]
 60%|██████    | 224056/371472 [7:10:25<12:29:17,  3.28it/s]
 60%|██████    | 224057/371472 [7:10:25<13:17:18,  3.08it/s]
 60%|██████    | 224058/371472 [7:10:26<13:44:29,  2.98it/s]
 60%|██████    | 224059/371472 [7:10:26<13:25:30,  3.05it/s]
 60%|██████    | 224060/371472 [7:10:26<12:54:50,  3.17it/s]
                                                            
{'loss': 2.8133, 'learning_rate': 4.573412484647375e-07, 'epoch': 9.65}
+
 60%|██████    | 224060/371472 [7:10:26<12:54:50,  3.17it/s]
 60%|██████    | 224061/371472 [7:10:27<12:34:03,  3.26it/s]
 60%|██████    | 224062/371472 [7:10:27<12:09:32,  3.37it/s]
 60%|██████    | 224063/371472 [7:10:27<12:00:59,  3.41it/s]
 60%|██████    | 224064/371472 [7:10:27<11:49:38,  3.46it/s]
 60%|██████    | 224065/371472 [7:10:28<11:50:45,  3.46it/s]
 60%|██████    | 224066/371472 [7:10:28<12:10:13,  3.36it/s]
 60%|██████    | 224067/371472 [7:10:28<12:15:40,  3.34it/s]
 60%|██████    | 224068/371472 [7:10:29<12:12:13,  3.36it/s]
 60%|██████    | 224069/371472 [7:10:29<13:13:17,  3.10it/s]
 60%|██████    | 224070/371472 [7:10:29<12:56:06,  3.17it/s]
 60%|██████    | 224071/371472 [7:10:30<12:39:56,  3.23it/s]
 60%|██████    | 224072/371472 [7:10:30<12:38:06,  3.24it/s]
 60%|██████    | 224073/371472 [7:10:30<12:17:30,  3.33it/s]
 60%|██████    | 224074/371472 [7:10:30<12:09:21,  3.37it/s]
 60%|██████    | 224075/371472 [7:10:31<12:01:53,  3.40it/s]
 60%|██████    | 224076/371472 [7:10:31<11:33:48,  3.54it/s]
 60%|██████    | 224077/371472 [7:10:31<11:32:58,  3.54it/s]
 60%|██████    | 224078/371472 [7:10:32<11:37:10,  3.52it/s]
 60%|██████    | 224079/371472 [7:10:32<11:37:14,  3.52it/s]
 60%|██████    | 224080/371472 [7:10:32<11:42:30,  3.50it/s]
                                                            
{'loss': 2.7072, 'learning_rate': 4.5729276648925853e-07, 'epoch': 9.65}
+
 60%|██████    | 224080/371472 [7:10:32<11:42:30,  3.50it/s]
 60%|██████    | 224081/371472 [7:10:32<12:00:27,  3.41it/s]
 60%|██████    | 224082/371472 [7:10:33<12:01:56,  3.40it/s]
 60%|██████    | 224083/371472 [7:10:33<11:45:57,  3.48it/s]
 60%|██████    | 224084/371472 [7:10:33<11:47:46,  3.47it/s]
 60%|██████    | 224085/371472 [7:10:34<11:48:07,  3.47it/s]
 60%|██████    | 224086/371472 [7:10:34<11:49:28,  3.46it/s]
 60%|██████    | 224087/371472 [7:10:34<11:41:36,  3.50it/s]
 60%|██████    | 224088/371472 [7:10:34<11:52:17,  3.45it/s]
 60%|██████    | 224089/371472 [7:10:35<12:33:08,  3.26it/s]
 60%|██████    | 224090/371472 [7:10:35<12:37:36,  3.24it/s]
 60%|██████    | 224091/371472 [7:10:35<13:00:04,  3.15it/s]
 60%|██████    | 224092/371472 [7:10:36<12:33:52,  3.26it/s]
 60%|██████    | 224093/371472 [7:10:36<12:28:03,  3.28it/s]
 60%|██████    | 224094/371472 [7:10:36<12:08:44,  3.37it/s]
 60%|██████    | 224095/371472 [7:10:37<11:54:19,  3.44it/s]
 60%|██████    | 224096/371472 [7:10:37<11:41:39,  3.50it/s]
 60%|██████    | 224097/371472 [7:10:37<12:09:01,  3.37it/s]
 60%|██████    | 224098/371472 [7:10:38<13:31:10,  3.03it/s]
 60%|██████    | 224099/371472 [7:10:38<14:24:48,  2.84it/s]
 60%|██████    | 224100/371472 [7:10:38<13:55:53,  2.94it/s]
                                                            
{'loss': 2.8338, 'learning_rate': 4.5724428451377965e-07, 'epoch': 9.65}
+
 60%|██████    | 224100/371472 [7:10:38<13:55:53,  2.94it/s]
 60%|██████    | 224101/371472 [7:10:39<13:57:20,  2.93it/s]
 60%|██████    | 224102/371472 [7:10:39<13:46:13,  2.97it/s]
 60%|██████    | 224103/371472 [7:10:39<13:18:52,  3.07it/s]
 60%|██████    | 224104/371472 [7:10:40<13:47:43,  2.97it/s]
 60%|██████    | 224105/371472 [7:10:40<12:57:04,  3.16it/s]
 60%|██████    | 224106/371472 [7:10:40<12:35:02,  3.25it/s]
 60%|██████    | 224107/371472 [7:10:40<12:29:35,  3.28it/s]
 60%|██████    | 224108/371472 [7:10:41<12:27:16,  3.29it/s]
 60%|██████    | 224109/371472 [7:10:41<12:08:34,  3.37it/s]
 60%|██████    | 224110/371472 [7:10:41<12:24:16,  3.30it/s]
 60%|██████    | 224111/371472 [7:10:42<11:57:34,  3.42it/s]
 60%|██████    | 224112/371472 [7:10:42<11:35:22,  3.53it/s]
 60%|██████    | 224113/371472 [7:10:42<12:12:50,  3.35it/s]
 60%|██████    | 224114/371472 [7:10:43<12:31:05,  3.27it/s]
 60%|██████    | 224115/371472 [7:10:43<12:19:28,  3.32it/s]
 60%|██████    | 224116/371472 [7:10:43<12:25:23,  3.29it/s]
 60%|██████    | 224117/371472 [7:10:43<12:16:54,  3.33it/s]
 60%|██████    | 224118/371472 [7:10:44<11:55:06,  3.43it/s]
 60%|██████    | 224119/371472 [7:10:44<11:58:13,  3.42it/s]
 60%|██████    | 224120/371472 [7:10:44<11:55:34,  3.43it/s]
                                                            
{'loss': 2.6711, 'learning_rate': 4.571958025383007e-07, 'epoch': 9.65}
+
 60%|██████    | 224120/371472 [7:10:44<11:55:34,  3.43it/s]
 60%|██████    | 224121/371472 [7:10:45<11:37:37,  3.52it/s]
 60%|██████    | 224122/371472 [7:10:45<11:44:51,  3.48it/s]
 60%|██████    | 224123/371472 [7:10:45<12:30:06,  3.27it/s]
 60%|██████    | 224124/371472 [7:10:46<12:09:04,  3.37it/s]
 60%|██████    | 224125/371472 [7:10:46<12:44:22,  3.21it/s]
 60%|██████    | 224126/371472 [7:10:46<12:18:20,  3.33it/s]
 60%|██████    | 224127/371472 [7:10:46<12:14:47,  3.34it/s]
 60%|██████    | 224128/371472 [7:10:47<12:10:47,  3.36it/s]
 60%|██████    | 224129/371472 [7:10:47<12:03:40,  3.39it/s]
 60%|██████    | 224130/371472 [7:10:47<12:22:04,  3.31it/s]
 60%|██████    | 224131/371472 [7:10:48<12:32:45,  3.26it/s]
 60%|██████    | 224132/371472 [7:10:48<11:56:07,  3.43it/s]
 60%|██████    | 224133/371472 [7:10:48<12:31:10,  3.27it/s]
 60%|██████    | 224134/371472 [7:10:49<12:13:07,  3.35it/s]
 60%|██████    | 224135/371472 [7:10:49<12:07:05,  3.38it/s]
 60%|██████    | 224136/371472 [7:10:49<11:59:17,  3.41it/s]
 60%|██████    | 224137/371472 [7:10:49<12:21:39,  3.31it/s]
 60%|██████    | 224138/371472 [7:10:50<12:15:14,  3.34it/s]
 60%|██████    | 224139/371472 [7:10:50<12:06:36,  3.38it/s]
 60%|██████    | 224140/371472 [7:10:50<12:52:08,  3.18it/s]
                                                            
{'loss': 2.7503, 'learning_rate': 4.571473205628219e-07, 'epoch': 9.65}
+
 60%|██████    | 224140/371472 [7:10:50<12:52:08,  3.18it/s]
 60%|██████    | 224141/371472 [7:10:51<12:54:55,  3.17it/s]
 60%|██████    | 224142/371472 [7:10:51<13:31:14,  3.03it/s]
 60%|██████    | 224143/371472 [7:10:51<12:59:41,  3.15it/s]
 60%|██████    | 224144/371472 [7:10:52<13:11:09,  3.10it/s]
 60%|██████    | 224145/371472 [7:10:52<12:55:16,  3.17it/s]
 60%|██████    | 224146/371472 [7:10:52<12:28:46,  3.28it/s]
 60%|██████    | 224147/371472 [7:10:53<12:08:03,  3.37it/s]
 60%|██████    | 224148/371472 [7:10:53<12:34:13,  3.26it/s]
 60%|██████    | 224149/371472 [7:10:53<12:26:04,  3.29it/s]
 60%|██████    | 224150/371472 [7:10:53<12:10:21,  3.36it/s]
 60%|██████    | 224151/371472 [7:10:54<11:52:00,  3.45it/s]
 60%|██████    | 224152/371472 [7:10:54<12:41:21,  3.22it/s]
 60%|██████    | 224153/371472 [7:10:54<12:48:06,  3.20it/s]
 60%|██████    | 224154/371472 [7:10:55<13:01:29,  3.14it/s]
 60%|██████    | 224155/371472 [7:10:55<13:02:53,  3.14it/s]
 60%|██████    | 224156/371472 [7:10:55<12:31:31,  3.27it/s]
 60%|██████    | 224157/371472 [7:10:56<12:06:30,  3.38it/s]
 60%|██████    | 224158/371472 [7:10:56<11:59:06,  3.41it/s]
 60%|██████    | 224159/371472 [7:10:56<12:05:55,  3.38it/s]
 60%|██████    | 224160/371472 [7:10:56<11:59:47,  3.41it/s]
                                                            
{'loss': 2.7118, 'learning_rate': 4.570988385873429e-07, 'epoch': 9.65}
+
 60%|██████    | 224160/371472 [7:10:56<11:59:47,  3.41it/s]
 60%|██████    | 224161/371472 [7:10:57<11:44:42,  3.48it/s]
 60%|██████    | 224162/371472 [7:10:57<11:48:17,  3.47it/s]
 60%|██████    | 224163/371472 [7:10:57<11:42:41,  3.49it/s]
 60%|██████    | 224164/371472 [7:10:58<12:11:56,  3.35it/s]
 60%|██████    | 224165/371472 [7:10:58<12:17:47,  3.33it/s]
 60%|██████    | 224166/371472 [7:10:58<12:24:24,  3.30it/s]
 60%|██████    | 224167/371472 [7:10:59<12:15:23,  3.34it/s]
 60%|██████    | 224168/371472 [7:10:59<12:38:09,  3.24it/s]
 60%|██████    | 224169/371472 [7:10:59<12:13:11,  3.35it/s]
 60%|██████    | 224170/371472 [7:10:59<12:04:23,  3.39it/s]
 60%|██████    | 224171/371472 [7:11:00<11:47:25,  3.47it/s]
 60%|██████    | 224172/371472 [7:11:00<12:09:18,  3.37it/s]
 60%|██████    | 224173/371472 [7:11:00<12:08:24,  3.37it/s]
 60%|██████    | 224174/371472 [7:11:01<11:52:32,  3.45it/s]
 60%|██████    | 224175/371472 [7:11:01<11:37:10,  3.52it/s]
 60%|██████    | 224176/371472 [7:11:01<11:54:19,  3.44it/s]
 60%|██████    | 224177/371472 [7:11:01<12:10:10,  3.36it/s]
 60%|██████    | 224178/371472 [7:11:02<12:34:49,  3.25it/s]
 60%|██████    | 224179/371472 [7:11:02<12:11:22,  3.36it/s]
 60%|██████    | 224180/371472 [7:11:02<11:55:39,  3.43it/s]
                                                            
{'loss': 2.6771, 'learning_rate': 4.570503566118641e-07, 'epoch': 9.66}
+
 60%|██████    | 224180/371472 [7:11:02<11:55:39,  3.43it/s]
 60%|██████    | 224181/371472 [7:11:03<12:04:25,  3.39it/s]
 60%|██████    | 224182/371472 [7:11:03<11:55:59,  3.43it/s]
 60%|██████    | 224183/371472 [7:11:03<12:04:34,  3.39it/s]
 60%|██████    | 224184/371472 [7:11:04<12:01:54,  3.40it/s]
 60%|██████    | 224185/371472 [7:11:04<12:17:14,  3.33it/s]
 60%|██████    | 224186/371472 [7:11:04<12:17:02,  3.33it/s]
 60%|██████    | 224187/371472 [7:11:04<12:00:08,  3.41it/s]
 60%|██████    | 224188/371472 [7:11:05<11:39:17,  3.51it/s]
 60%|██████    | 224189/371472 [7:11:05<11:20:50,  3.61it/s]
 60%|██████    | 224190/371472 [7:11:05<11:46:02,  3.48it/s]
 60%|██████    | 224191/371472 [7:11:06<12:20:07,  3.32it/s]
 60%|██████    | 224192/371472 [7:11:06<12:07:25,  3.37it/s]
 60%|██████    | 224193/371472 [7:11:06<12:10:48,  3.36it/s]
 60%|██████    | 224194/371472 [7:11:07<12:53:41,  3.17it/s]
 60%|██████    | 224195/371472 [7:11:07<12:38:33,  3.24it/s]
 60%|██████    | 224196/371472 [7:11:07<12:23:32,  3.30it/s]
 60%|██████    | 224197/371472 [7:11:07<12:09:38,  3.36it/s]
 60%|██████    | 224198/371472 [7:11:08<12:36:25,  3.24it/s]
 60%|██████    | 224199/371472 [7:11:08<12:40:51,  3.23it/s]
 60%|██████    | 224200/371472 [7:11:08<12:19:18,  3.32it/s]
                                                            
{'loss': 2.7248, 'learning_rate': 4.5700187463638517e-07, 'epoch': 9.66}
+
 60%|██████    | 224200/371472 [7:11:08<12:19:18,  3.32it/s]
 60%|██████    | 224201/371472 [7:11:09<12:14:56,  3.34it/s]
 60%|██████    | 224202/371472 [7:11:09<12:11:30,  3.36it/s]
 60%|██████    | 224203/371472 [7:11:09<12:28:04,  3.28it/s]
 60%|██████    | 224204/371472 [7:11:10<12:40:20,  3.23it/s]
 60%|██████    | 224205/371472 [7:11:10<12:26:10,  3.29it/s]
 60%|██████    | 224206/371472 [7:11:10<12:06:22,  3.38it/s]
 60%|██████    | 224207/371472 [7:11:10<12:04:03,  3.39it/s]
 60%|██████    | 224208/371472 [7:11:11<11:39:40,  3.51it/s]
 60%|██████    | 224209/371472 [7:11:11<11:39:31,  3.51it/s]
 60%|██████    | 224210/371472 [7:11:11<12:38:15,  3.24it/s]
 60%|██████    | 224211/371472 [7:11:12<12:21:45,  3.31it/s]
 60%|██████    | 224212/371472 [7:11:12<12:09:54,  3.36it/s]
 60%|██████    | 224213/371472 [7:11:12<12:05:20,  3.38it/s]
 60%|██████    | 224214/371472 [7:11:13<12:32:32,  3.26it/s]
 60%|██████    | 224215/371472 [7:11:13<11:54:53,  3.43it/s]
 60%|██████    | 224216/371472 [7:11:13<11:44:33,  3.48it/s]
 60%|██████    | 224217/371472 [7:11:13<11:53:15,  3.44it/s]
 60%|██████    | 224218/371472 [7:11:14<13:02:57,  3.13it/s]
 60%|██████    | 224219/371472 [7:11:14<12:19:40,  3.32it/s]
 60%|██████    | 224220/371472 [7:11:14<12:05:22,  3.38it/s]
                                                            
{'loss': 2.8017, 'learning_rate': 4.569533926609063e-07, 'epoch': 9.66}
+
 60%|██████    | 224220/371472 [7:11:14<12:05:22,  3.38it/s]
 60%|██████    | 224221/371472 [7:11:15<12:35:10,  3.25it/s]
 60%|██████    | 224222/371472 [7:11:15<12:02:01,  3.40it/s]
 60%|██████    | 224223/371472 [7:11:15<11:53:11,  3.44it/s]
 60%|██████    | 224224/371472 [7:11:15<11:50:10,  3.46it/s]
 60%|██████    | 224225/371472 [7:11:16<11:39:12,  3.51it/s]
 60%|██████    | 224226/371472 [7:11:16<11:31:01,  3.55it/s]
 60%|██████    | 224227/371472 [7:11:16<11:38:36,  3.51it/s]
 60%|██████    | 224228/371472 [7:11:17<11:37:18,  3.52it/s]
 60%|██████    | 224229/371472 [7:11:17<11:30:33,  3.55it/s]
 60%|██████    | 224230/371472 [7:11:17<11:26:28,  3.57it/s]
 60%|██████    | 224231/371472 [7:11:17<11:52:09,  3.45it/s]
 60%|██████    | 224232/371472 [7:11:18<11:44:34,  3.48it/s]
 60%|██████    | 224233/371472 [7:11:18<12:04:29,  3.39it/s]
 60%|██████    | 224234/371472 [7:11:18<12:02:10,  3.40it/s]
 60%|██████    | 224235/371472 [7:11:19<11:58:26,  3.42it/s]
 60%|██████    | 224236/371472 [7:11:19<11:44:51,  3.48it/s]
 60%|██████    | 224237/371472 [7:11:19<11:57:47,  3.42it/s]
 60%|██████    | 224238/371472 [7:11:20<13:00:10,  3.15it/s]
 60%|██████    | 224239/371472 [7:11:20<12:53:10,  3.17it/s]
 60%|██████    | 224240/371472 [7:11:20<13:08:49,  3.11it/s]
                                                            
{'loss': 2.9738, 'learning_rate': 4.5690491068542736e-07, 'epoch': 9.66}
+
 60%|██████    | 224240/371472 [7:11:20<13:08:49,  3.11it/s]
 60%|██████    | 224241/371472 [7:11:21<13:07:27,  3.12it/s]
 60%|██████    | 224242/371472 [7:11:21<13:08:34,  3.11it/s]
 60%|██████    | 224243/371472 [7:11:21<12:58:39,  3.15it/s]
 60%|██████    | 224244/371472 [7:11:22<13:17:23,  3.08it/s]
 60%|██████    | 224245/371472 [7:11:22<13:44:53,  2.97it/s]
 60%|██████    | 224246/371472 [7:11:22<13:07:18,  3.12it/s]
 60%|██████    | 224247/371472 [7:11:22<12:40:03,  3.23it/s]
 60%|██████    | 224248/371472 [7:11:23<12:37:53,  3.24it/s]
 60%|██████    | 224249/371472 [7:11:23<12:47:58,  3.20it/s]
 60%|██████    | 224250/371472 [7:11:23<13:23:47,  3.05it/s]
 60%|██████    | 224251/371472 [7:11:24<13:33:19,  3.02it/s]
 60%|██████    | 224252/371472 [7:11:24<13:37:48,  3.00it/s]
 60%|██████    | 224253/371472 [7:11:24<13:49:48,  2.96it/s]
 60%|██████    | 224254/371472 [7:11:25<13:40:27,  2.99it/s]
 60%|██████    | 224255/371472 [7:11:25<13:56:06,  2.93it/s]
 60%|██████    | 224256/371472 [7:11:25<13:28:21,  3.04it/s]
 60%|██████    | 224257/371472 [7:11:26<12:47:16,  3.20it/s]
 60%|██████    | 224258/371472 [7:11:26<14:11:16,  2.88it/s]
 60%|██████    | 224259/371472 [7:11:27<14:29:04,  2.82it/s]
 60%|██████    | 224260/371472 [7:11:27<13:53:44,  2.94it/s]
                                                            
{'loss': 2.7204, 'learning_rate': 4.5685642870994854e-07, 'epoch': 9.66}
+
 60%|██████    | 224260/371472 [7:11:27<13:53:44,  2.94it/s]
 60%|██████    | 224261/371472 [7:11:27<13:39:14,  2.99it/s]
 60%|██████    | 224262/371472 [7:11:28<14:17:12,  2.86it/s]
 60%|██████    | 224263/371472 [7:11:28<13:18:52,  3.07it/s]
 60%|██████    | 224264/371472 [7:11:28<12:37:17,  3.24it/s]
 60%|██████    | 224265/371472 [7:11:28<12:52:29,  3.18it/s]
 60%|██████    | 224266/371472 [7:11:29<12:11:17,  3.35it/s]
 60%|██████    | 224267/371472 [7:11:29<12:09:29,  3.36it/s]
 60%|██████    | 224268/371472 [7:11:29<12:03:31,  3.39it/s]
 60%|██████    | 224269/371472 [7:11:30<11:42:24,  3.49it/s]
 60%|██████    | 224270/371472 [7:11:30<11:32:59,  3.54it/s]
 60%|██████    | 224271/371472 [7:11:30<12:40:55,  3.22it/s]
 60%|██████    | 224272/371472 [7:11:30<12:17:44,  3.33it/s]
 60%|██████    | 224273/371472 [7:11:31<13:07:10,  3.12it/s]
 60%|██████    | 224274/371472 [7:11:31<12:29:43,  3.27it/s]
 60%|██████    | 224275/371472 [7:11:31<12:24:47,  3.29it/s]
 60%|██████    | 224276/371472 [7:11:32<12:47:12,  3.20it/s]
 60%|██████    | 224277/371472 [7:11:32<12:27:29,  3.28it/s]
 60%|██████    | 224278/371472 [7:11:32<12:03:50,  3.39it/s]
 60%|██████    | 224279/371472 [7:11:33<12:36:01,  3.24it/s]
 60%|██████    | 224280/371472 [7:11:33<12:03:25,  3.39it/s]
                                                            
{'loss': 2.8758, 'learning_rate': 4.5680794673446956e-07, 'epoch': 9.66}
+
 60%|██████    | 224280/371472 [7:11:33<12:03:25,  3.39it/s]
 60%|██████    | 224281/371472 [7:11:33<11:51:30,  3.45it/s]
 60%|██████    | 224282/371472 [7:11:33<11:36:42,  3.52it/s]
 60%|██████    | 224283/371472 [7:11:34<11:44:50,  3.48it/s]
 60%|██████    | 224284/371472 [7:11:34<11:46:55,  3.47it/s]
 60%|██████    | 224285/371472 [7:11:34<11:46:23,  3.47it/s]
 60%|██████    | 224286/371472 [7:11:35<12:05:52,  3.38it/s]
 60%|██████    | 224287/371472 [7:11:35<13:17:03,  3.08it/s]
 60%|██████    | 224288/371472 [7:11:35<12:40:15,  3.23it/s]
 60%|██████    | 224289/371472 [7:11:36<12:42:50,  3.22it/s]
 60%|██████    | 224290/371472 [7:11:36<12:26:11,  3.29it/s]
 60%|██████    | 224291/371472 [7:11:36<12:04:42,  3.38it/s]
 60%|██████    | 224292/371472 [7:11:36<12:18:21,  3.32it/s]
 60%|██████    | 224293/371472 [7:11:37<12:55:51,  3.16it/s]
 60%|██████    | 224294/371472 [7:11:37<12:52:35,  3.17it/s]
 60%|██████    | 224295/371472 [7:11:37<12:36:05,  3.24it/s]
 60%|██████    | 224296/371472 [7:11:38<12:25:04,  3.29it/s]
 60%|██████    | 224297/371472 [7:11:38<12:06:03,  3.38it/s]
 60%|██████    | 224298/371472 [7:11:38<11:57:21,  3.42it/s]
 60%|██████    | 224299/371472 [7:11:39<12:00:30,  3.40it/s]
 60%|██████    | 224300/371472 [7:11:39<12:19:28,  3.32it/s]
                                                            
{'loss': 2.6574, 'learning_rate': 4.5675946475899063e-07, 'epoch': 9.66}
+
 60%|██████    | 224300/371472 [7:11:39<12:19:28,  3.32it/s]
 60%|██████    | 224301/371472 [7:11:39<11:53:52,  3.44it/s]
 60%|██████    | 224302/371472 [7:11:39<11:54:30,  3.43it/s]
 60%|██████    | 224303/371472 [7:11:40<11:49:54,  3.46it/s]
 60%|██████    | 224304/371472 [7:11:40<11:35:11,  3.53it/s]
 60%|██████    | 224305/371472 [7:11:40<11:42:07,  3.49it/s]
 60%|██████    | 224306/371472 [7:11:41<12:45:30,  3.20it/s]
 60%|██████    | 224307/371472 [7:11:41<12:46:30,  3.20it/s]
 60%|██████    | 224308/371472 [7:11:41<12:31:13,  3.26it/s]
 60%|██████    | 224309/371472 [7:11:42<12:41:41,  3.22it/s]
 60%|██████    | 224310/371472 [7:11:42<13:20:38,  3.06it/s]
 60%|██████    | 224311/371472 [7:11:42<13:01:29,  3.14it/s]
 60%|██████    | 224312/371472 [7:11:43<12:33:06,  3.26it/s]
 60%|██████    | 224313/371472 [7:11:43<12:11:08,  3.35it/s]
 60%|██████    | 224314/371472 [7:11:43<11:47:44,  3.47it/s]
 60%|██████    | 224315/371472 [7:11:43<11:38:43,  3.51it/s]
 60%|██████    | 224316/371472 [7:11:44<11:34:15,  3.53it/s]
 60%|██████    | 224317/371472 [7:11:44<11:20:54,  3.60it/s]
 60%|██████    | 224318/371472 [7:11:44<11:50:05,  3.45it/s]
 60%|██████    | 224319/371472 [7:11:45<12:13:23,  3.34it/s]
 60%|██████    | 224320/371472 [7:11:45<12:13:54,  3.34it/s]
                                                            
{'loss': 2.8197, 'learning_rate': 4.567109827835118e-07, 'epoch': 9.66}
+
 60%|██████    | 224320/371472 [7:11:45<12:13:54,  3.34it/s]
 60%|██████    | 224321/371472 [7:11:45<11:47:23,  3.47it/s]
 60%|██████    | 224322/371472 [7:11:45<12:02:53,  3.39it/s]
 60%|██████    | 224323/371472 [7:11:46<11:49:23,  3.46it/s]
 60%|██████    | 224324/371472 [7:11:46<11:33:24,  3.54it/s]
 60%|██████    | 224325/371472 [7:11:46<11:55:18,  3.43it/s]
 60%|██████    | 224326/371472 [7:11:47<11:46:54,  3.47it/s]
 60%|██████    | 224327/371472 [7:11:47<11:48:03,  3.46it/s]
 60%|██████    | 224328/371472 [7:11:47<11:38:27,  3.51it/s]
 60%|██████    | 224329/371472 [7:11:47<12:07:24,  3.37it/s]
 60%|██████    | 224330/371472 [7:11:48<11:53:10,  3.44it/s]
 60%|██████    | 224331/371472 [7:11:48<12:20:21,  3.31it/s]
 60%|██████    | 224332/371472 [7:11:48<12:38:53,  3.23it/s]
 60%|██████    | 224333/371472 [7:11:49<12:18:42,  3.32it/s]
 60%|██████    | 224334/371472 [7:11:49<11:55:57,  3.43it/s]
 60%|██████    | 224335/371472 [7:11:49<12:32:04,  3.26it/s]
 60%|██████    | 224336/371472 [7:11:50<12:12:04,  3.35it/s]
 60%|██████    | 224337/371472 [7:11:50<12:05:39,  3.38it/s]
 60%|██████    | 224338/371472 [7:11:50<11:44:59,  3.48it/s]
 60%|██████    | 224339/371472 [7:11:51<12:59:22,  3.15it/s]
 60%|██████    | 224340/371472 [7:11:51<12:20:47,  3.31it/s]
                                                            
{'loss': 2.7282, 'learning_rate': 4.566625008080329e-07, 'epoch': 9.66}
+
 60%|██████    | 224340/371472 [7:11:51<12:20:47,  3.31it/s]
 60%|██████    | 224341/371472 [7:11:51<12:08:20,  3.37it/s]
 60%|██████    | 224342/371472 [7:11:51<12:17:14,  3.33it/s]
 60%|██████    | 224343/371472 [7:11:52<11:49:18,  3.46it/s]
 60%|██████    | 224344/371472 [7:11:52<11:38:06,  3.51it/s]
 60%|██████    | 224345/371472 [7:11:52<11:50:18,  3.45it/s]
 60%|██████    | 224346/371472 [7:11:52<11:32:06,  3.54it/s]
 60%|██████    | 224347/371472 [7:11:53<11:46:23,  3.47it/s]
 60%|██████    | 224348/371472 [7:11:53<11:43:58,  3.48it/s]
 60%|██████    | 224349/371472 [7:11:53<11:44:59,  3.48it/s]
 60%|██████    | 224350/371472 [7:11:54<11:31:54,  3.54it/s]
 60%|██████    | 224351/371472 [7:11:54<11:47:03,  3.47it/s]
 60%|██████    | 224352/371472 [7:11:54<11:22:09,  3.59it/s]
 60%|██████    | 224353/371472 [7:11:54<11:12:42,  3.64it/s]
 60%|██████    | 224354/371472 [7:11:55<11:23:23,  3.59it/s]
 60%|██████    | 224355/371472 [7:11:55<12:27:05,  3.28it/s]
 60%|██████    | 224356/371472 [7:11:55<13:01:47,  3.14it/s]
 60%|██████    | 224357/371472 [7:11:56<12:36:10,  3.24it/s]
 60%|██████    | 224358/371472 [7:11:56<12:36:48,  3.24it/s]
 60%|██████    | 224359/371472 [7:11:56<12:30:25,  3.27it/s]
 60%|██████    | 224360/371472 [7:11:57<12:03:28,  3.39it/s]
                                                            
{'loss': 2.6115, 'learning_rate': 4.56614018832554e-07, 'epoch': 9.66}
+
 60%|██████    | 224360/371472 [7:11:57<12:03:28,  3.39it/s]
 60%|██████    | 224361/371472 [7:11:57<12:14:43,  3.34it/s]
 60%|██████    | 224362/371472 [7:11:57<12:30:31,  3.27it/s]
 60%|██████    | 224363/371472 [7:11:58<12:36:06,  3.24it/s]
 60%|██████    | 224364/371472 [7:11:58<12:51:43,  3.18it/s]
 60%|██████    | 224365/371472 [7:11:58<12:36:07,  3.24it/s]
 60%|██████    | 224366/371472 [7:11:58<12:25:28,  3.29it/s]
 60%|██████    | 224367/371472 [7:11:59<12:22:35,  3.30it/s]
 60%|██████    | 224368/371472 [7:11:59<11:57:16,  3.42it/s]
 60%|██████    | 224369/371472 [7:11:59<12:47:41,  3.19it/s]
 60%|██████    | 224370/371472 [7:12:00<12:03:06,  3.39it/s]
 60%|██████    | 224371/371472 [7:12:00<12:22:42,  3.30it/s]
 60%|██████    | 224372/371472 [7:12:00<12:13:24,  3.34it/s]
 60%|██████    | 224373/371472 [7:12:01<11:44:01,  3.48it/s]
 60%|██████    | 224374/371472 [7:12:01<11:37:19,  3.52it/s]
 60%|██████    | 224375/371472 [7:12:01<11:24:37,  3.58it/s]
 60%|██████    | 224376/371472 [7:12:01<11:21:25,  3.60it/s]
 60%|██████    | 224377/371472 [7:12:02<11:19:01,  3.61it/s]
 60%|██████    | 224378/371472 [7:12:02<11:19:59,  3.61it/s]
 60%|██████    | 224379/371472 [7:12:02<11:31:08,  3.55it/s]
 60%|██████    | 224380/371472 [7:12:03<12:27:56,  3.28it/s]
                                                            
{'loss': 2.7395, 'learning_rate': 4.565655368570751e-07, 'epoch': 9.66}
+
 60%|██████    | 224380/371472 [7:12:03<12:27:56,  3.28it/s]
 60%|██████    | 224381/371472 [7:12:03<11:58:57,  3.41it/s]
 60%|██████    | 224382/371472 [7:12:03<11:43:50,  3.48it/s]
 60%|██████    | 224383/371472 [7:12:03<11:36:39,  3.52it/s]
 60%|██████    | 224384/371472 [7:12:04<11:12:51,  3.64it/s]
 60%|██████    | 224385/371472 [7:12:04<11:54:28,  3.43it/s]
 60%|██████    | 224386/371472 [7:12:04<12:13:41,  3.34it/s]
 60%|██████    | 224387/371472 [7:12:05<12:08:12,  3.37it/s]
 60%|██████    | 224388/371472 [7:12:05<12:30:04,  3.27it/s]
 60%|██████    | 224389/371472 [7:12:05<12:02:52,  3.39it/s]
 60%|██████    | 224390/371472 [7:12:05<11:55:18,  3.43it/s]
 60%|██████    | 224391/371472 [7:12:06<11:37:30,  3.51it/s]
 60%|██████    | 224392/371472 [7:12:06<11:18:22,  3.61it/s]
 60%|██████    | 224393/371472 [7:12:06<11:19:37,  3.61it/s]
 60%|██████    | 224394/371472 [7:12:07<11:15:50,  3.63it/s]
 60%|██████    | 224395/371472 [7:12:07<11:08:00,  3.67it/s]
 60%|██████    | 224396/371472 [7:12:07<11:17:54,  3.62it/s]
 60%|██████    | 224397/371472 [7:12:07<11:42:50,  3.49it/s]
 60%|██████    | 224398/371472 [7:12:08<11:41:13,  3.50it/s]
 60%|██████    | 224399/371472 [7:12:08<12:41:20,  3.22it/s]
 60%|██████    | 224400/371472 [7:12:08<12:20:15,  3.31it/s]
                                                            
{'loss': 2.8541, 'learning_rate': 4.5651705488159625e-07, 'epoch': 9.67}
+
 60%|██████    | 224400/371472 [7:12:08<12:20:15,  3.31it/s]
 60%|██████    | 224401/371472 [7:12:09<11:56:44,  3.42it/s]
 60%|██████    | 224402/371472 [7:12:09<11:50:29,  3.45it/s]
 60%|██████    | 224403/371472 [7:12:09<12:22:41,  3.30it/s]
 60%|██████    | 224404/371472 [7:12:10<12:41:28,  3.22it/s]
 60%|██████    | 224405/371472 [7:12:10<12:53:47,  3.17it/s]
 60%|██████    | 224406/371472 [7:12:10<12:45:41,  3.20it/s]
 60%|██████    | 224407/371472 [7:12:11<13:11:45,  3.10it/s]
 60%|██████    | 224408/371472 [7:12:11<12:58:42,  3.15it/s]
 60%|██████    | 224409/371472 [7:12:11<13:20:43,  3.06it/s]
 60%|██████    | 224410/371472 [7:12:11<12:39:00,  3.23it/s]
 60%|██████    | 224411/371472 [7:12:12<12:22:05,  3.30it/s]
 60%|██████    | 224412/371472 [7:12:12<12:24:07,  3.29it/s]
 60%|██████    | 224413/371472 [7:12:12<12:02:50,  3.39it/s]
 60%|██████    | 224414/371472 [7:12:13<11:49:18,  3.46it/s]
 60%|██████    | 224415/371472 [7:12:13<11:40:02,  3.50it/s]
 60%|██████    | 224416/371472 [7:12:13<11:18:30,  3.61it/s]
 60%|██████    | 224417/371472 [7:12:13<11:42:39,  3.49it/s]
 60%|██████    | 224418/371472 [7:12:14<12:24:26,  3.29it/s]
 60%|██████    | 224419/371472 [7:12:14<12:05:00,  3.38it/s]
 60%|██████    | 224420/371472 [7:12:14<11:52:49,  3.44it/s]
                                                            
{'loss': 2.7594, 'learning_rate': 4.5646857290611727e-07, 'epoch': 9.67}
+
 60%|██████    | 224420/371472 [7:12:14<11:52:49,  3.44it/s]
 60%|██████    | 224421/371472 [7:12:15<11:59:02,  3.41it/s]
 60%|██████    | 224422/371472 [7:12:15<11:52:39,  3.44it/s]
 60%|██████    | 224423/371472 [7:12:15<12:10:02,  3.36it/s]
 60%|██████    | 224424/371472 [7:12:15<11:43:12,  3.49it/s]
 60%|██████    | 224425/371472 [7:12:16<11:43:09,  3.49it/s]
 60%|██████    | 224426/371472 [7:12:16<12:04:30,  3.38it/s]
 60%|██████    | 224427/371472 [7:12:16<12:04:09,  3.38it/s]
 60%|██████    | 224428/371472 [7:12:17<13:20:16,  3.06it/s]
 60%|██████    | 224429/371472 [7:12:17<13:50:24,  2.95it/s]
 60%|██████    | 224430/371472 [7:12:17<12:59:34,  3.14it/s]
 60%|██████    | 224431/371472 [7:12:18<12:32:40,  3.26it/s]
 60%|██████    | 224432/371472 [7:12:18<12:24:45,  3.29it/s]
 60%|██████    | 224433/371472 [7:12:18<13:29:43,  3.03it/s]
 60%|██████    | 224434/371472 [7:12:19<12:50:39,  3.18it/s]
 60%|██████    | 224435/371472 [7:12:19<12:21:30,  3.30it/s]
 60%|██████    | 224436/371472 [7:12:19<12:15:42,  3.33it/s]
 60%|██████    | 224437/371472 [7:12:19<11:41:17,  3.49it/s]
 60%|██████    | 224438/371472 [7:12:20<11:48:34,  3.46it/s]
 60%|██████    | 224439/371472 [7:12:20<12:08:07,  3.37it/s]
 60%|██████    | 224440/371472 [7:12:20<12:09:10,  3.36it/s]
                                                            
{'loss': 2.6516, 'learning_rate': 4.5642009093063845e-07, 'epoch': 9.67}
+
 60%|██████    | 224440/371472 [7:12:20<12:09:10,  3.36it/s]
 60%|██████    | 224441/371472 [7:12:21<12:12:48,  3.34it/s]
 60%|██████    | 224442/371472 [7:12:21<12:38:53,  3.23it/s]
 60%|██████    | 224443/371472 [7:12:21<12:53:26,  3.17it/s]
 60%|██████    | 224444/371472 [7:12:22<12:14:46,  3.33it/s]
 60%|██████    | 224445/371472 [7:12:22<12:16:24,  3.33it/s]
 60%|██████    | 224446/371472 [7:12:22<12:13:00,  3.34it/s]
 60%|██████    | 224447/371472 [7:12:23<12:19:58,  3.31it/s]
 60%|██████    | 224448/371472 [7:12:23<13:26:23,  3.04it/s]
 60%|██████    | 224449/371472 [7:12:23<13:08:48,  3.11it/s]
 60%|██████    | 224450/371472 [7:12:24<13:54:54,  2.93it/s]
 60%|██████    | 224451/371472 [7:12:24<13:26:52,  3.04it/s]
 60%|██████    | 224452/371472 [7:12:24<13:19:01,  3.07it/s]
 60%|██████    | 224453/371472 [7:12:24<12:36:06,  3.24it/s]
 60%|██████    | 224454/371472 [7:12:25<12:27:25,  3.28it/s]
 60%|██████    | 224455/371472 [7:12:25<12:07:14,  3.37it/s]
 60%|██████    | 224456/371472 [7:12:25<12:14:47,  3.33it/s]
 60%|██████    | 224457/371472 [7:12:26<11:44:08,  3.48it/s]
 60%|██████    | 224458/371472 [7:12:26<12:22:46,  3.30it/s]
 60%|██████    | 224459/371472 [7:12:26<11:54:16,  3.43it/s]
 60%|██████    | 224460/371472 [7:12:27<12:03:43,  3.39it/s]
                                                            
{'loss': 2.8379, 'learning_rate': 4.563716089551595e-07, 'epoch': 9.67}
+
 60%|██████    | 224460/371472 [7:12:27<12:03:43,  3.39it/s]
 60%|██████    | 224461/371472 [7:12:27<11:44:09,  3.48it/s]
 60%|██████    | 224462/371472 [7:12:27<11:24:17,  3.58it/s]
 60%|██████    | 224463/371472 [7:12:27<11:55:54,  3.42it/s]
 60%|██████    | 224464/371472 [7:12:28<11:53:45,  3.43it/s]
 60%|██████    | 224465/371472 [7:12:28<12:01:10,  3.40it/s]
 60%|██████    | 224466/371472 [7:12:28<12:23:13,  3.30it/s]
 60%|██████    | 224467/371472 [7:12:29<12:36:53,  3.24it/s]
 60%|██████    | 224468/371472 [7:12:29<12:19:43,  3.31it/s]
 60%|██████    | 224469/371472 [7:12:29<12:29:57,  3.27it/s]
 60%|██████    | 224470/371472 [7:12:30<12:26:22,  3.28it/s]
 60%|██████    | 224471/371472 [7:12:30<13:29:16,  3.03it/s]
 60%|██████    | 224472/371472 [7:12:30<13:46:34,  2.96it/s]
 60%|██████    | 224473/371472 [7:12:31<13:29:08,  3.03it/s]
 60%|██████    | 224474/371472 [7:12:31<12:54:26,  3.16it/s]
 60%|██████    | 224475/371472 [7:12:31<12:21:48,  3.30it/s]
 60%|██████    | 224476/371472 [7:12:31<12:06:36,  3.37it/s]
 60%|██████    | 224477/371472 [7:12:32<11:58:07,  3.41it/s]
 60%|██████    | 224478/371472 [7:12:32<11:50:37,  3.45it/s]
 60%|██████    | 224479/371472 [7:12:32<12:10:43,  3.35it/s]
 60%|██████    | 224480/371472 [7:12:33<12:04:25,  3.38it/s]
                                                            
{'loss': 2.675, 'learning_rate': 4.563231269796807e-07, 'epoch': 9.67}
+
 60%|██████    | 224480/371472 [7:12:33<12:04:25,  3.38it/s]
 60%|██████    | 224481/371472 [7:12:33<12:23:24,  3.30it/s]
 60%|██████    | 224482/371472 [7:12:33<12:03:03,  3.39it/s]
 60%|██████    | 224483/371472 [7:12:34<12:07:25,  3.37it/s]
 60%|██████    | 224484/371472 [7:12:34<11:58:25,  3.41it/s]
 60%|██████    | 224485/371472 [7:12:34<12:04:32,  3.38it/s]
 60%|██████    | 224486/371472 [7:12:34<12:18:30,  3.32it/s]
 60%|██████    | 224487/371472 [7:12:35<11:58:25,  3.41it/s]
 60%|██████    | 224488/371472 [7:12:35<12:06:34,  3.37it/s]
 60%|██████    | 224489/371472 [7:12:35<14:00:31,  2.91it/s]
 60%|██████    | 224490/371472 [7:12:36<13:18:36,  3.07it/s]
 60%|██████    | 224491/371472 [7:12:36<14:04:22,  2.90it/s]
 60%|██████    | 224492/371472 [7:12:36<13:23:36,  3.05it/s]
 60%|██████    | 224493/371472 [7:12:37<12:58:09,  3.15it/s]
 60%|██████    | 224494/371472 [7:12:37<12:48:09,  3.19it/s]
 60%|██████    | 224495/371472 [7:12:37<12:53:02,  3.17it/s]
 60%|██████    | 224496/371472 [7:12:38<13:24:55,  3.04it/s]
 60%|██████    | 224497/371472 [7:12:38<12:51:09,  3.18it/s]
 60%|██████    | 224498/371472 [7:12:38<12:22:08,  3.30it/s]
 60%|██████    | 224499/371472 [7:12:39<11:58:23,  3.41it/s]
 60%|██████    | 224500/371472 [7:12:39<11:58:37,  3.41it/s]
                                                            
{'loss': 2.8521, 'learning_rate': 4.562746450042017e-07, 'epoch': 9.67}
+
 60%|██████    | 224500/371472 [7:12:39<11:58:37,  3.41it/s]
 60%|██████    | 224501/371472 [7:12:39<11:41:59,  3.49it/s]
 60%|██████    | 224502/371472 [7:12:39<11:39:07,  3.50it/s]
 60%|██████    | 224503/371472 [7:12:40<11:44:05,  3.48it/s]
 60%|██████    | 224504/371472 [7:12:40<12:22:52,  3.30it/s]
 60%|██████    | 224505/371472 [7:12:40<12:14:09,  3.34it/s]
 60%|██████    | 224506/371472 [7:12:41<11:51:57,  3.44it/s]
 60%|██████    | 224507/371472 [7:12:41<12:00:31,  3.40it/s]
 60%|██████    | 224508/371472 [7:12:41<12:15:45,  3.33it/s]
 60%|██████    | 224509/371472 [7:12:41<12:03:53,  3.38it/s]
 60%|██████    | 224510/371472 [7:12:42<12:22:55,  3.30it/s]
 60%|██████    | 224511/371472 [7:12:42<13:50:51,  2.95it/s]
 60%|██████    | 224512/371472 [7:12:43<13:36:27,  3.00it/s]
 60%|██████    | 224513/371472 [7:12:43<13:01:31,  3.13it/s]
 60%|██████    | 224514/371472 [7:12:43<12:55:02,  3.16it/s]
 60%|██████    | 224515/371472 [7:12:43<12:39:22,  3.23it/s]
 60%|██████    | 224516/371472 [7:12:44<12:06:29,  3.37it/s]
 60%|██████    | 224517/371472 [7:12:44<11:56:44,  3.42it/s]
 60%|██████    | 224518/371472 [7:12:44<11:56:56,  3.42it/s]
 60%|██████    | 224519/371472 [7:12:45<11:34:42,  3.53it/s]
 60%|██████    | 224520/371472 [7:12:45<12:13:54,  3.34it/s]
                                                            
{'loss': 2.7813, 'learning_rate': 4.562261630287229e-07, 'epoch': 9.67}
+
 60%|██████    | 224520/371472 [7:12:45<12:13:54,  3.34it/s]
 60%|██████    | 224521/371472 [7:12:45<12:15:40,  3.33it/s]
 60%|██████    | 224522/371472 [7:12:45<11:57:07,  3.42it/s]
 60%|██████    | 224523/371472 [7:12:46<12:08:21,  3.36it/s]
 60%|██████    | 224524/371472 [7:12:46<12:37:28,  3.23it/s]
 60%|██████    | 224525/371472 [7:12:46<12:23:19,  3.29it/s]
 60%|██████    | 224526/371472 [7:12:47<12:21:20,  3.30it/s]
 60%|██████    | 224527/371472 [7:12:47<11:58:45,  3.41it/s]
 60%|██████    | 224528/371472 [7:12:47<12:34:48,  3.24it/s]
 60%|██████    | 224529/371472 [7:12:48<12:57:55,  3.15it/s]
 60%|██████    | 224530/371472 [7:12:48<12:55:34,  3.16it/s]
 60%|██████    | 224531/371472 [7:12:48<12:36:53,  3.24it/s]
 60%|██████    | 224532/371472 [7:12:48<12:11:40,  3.35it/s]
 60%|██████    | 224533/371472 [7:12:49<12:02:36,  3.39it/s]
 60%|██████    | 224534/371472 [7:12:49<12:10:42,  3.35it/s]
 60%|██████    | 224535/371472 [7:12:49<11:42:01,  3.49it/s]
 60%|██████    | 224536/371472 [7:12:50<11:32:04,  3.54it/s]
 60%|██████    | 224537/371472 [7:12:50<11:55:45,  3.42it/s]
 60%|██████    | 224538/371472 [7:12:50<11:55:28,  3.42it/s]
 60%|██████    | 224539/371472 [7:12:51<11:45:24,  3.47it/s]
 60%|██████    | 224540/371472 [7:12:51<11:52:02,  3.44it/s]
                                                            
{'loss': 2.7344, 'learning_rate': 4.561776810532439e-07, 'epoch': 9.67}
+
 60%|██████    | 224540/371472 [7:12:51<11:52:02,  3.44it/s]
 60%|██████    | 224541/371472 [7:12:51<12:01:58,  3.39it/s]
 60%|██████    | 224542/371472 [7:12:51<11:47:14,  3.46it/s]
 60%|██████    | 224543/371472 [7:12:52<11:36:31,  3.52it/s]
 60%|██████    | 224544/371472 [7:12:52<11:37:19,  3.51it/s]
 60%|██████    | 224545/371472 [7:12:52<12:39:12,  3.23it/s]
 60%|██████    | 224546/371472 [7:12:53<12:07:21,  3.37it/s]
 60%|██████    | 224547/371472 [7:12:53<11:56:35,  3.42it/s]
 60%|██████    | 224548/371472 [7:12:53<11:35:18,  3.52it/s]
 60%|██████    | 224549/371472 [7:12:53<11:34:40,  3.52it/s]
 60%|██████    | 224550/371472 [7:12:54<12:52:35,  3.17it/s]
 60%|██████    | 224551/371472 [7:12:54<12:50:43,  3.18it/s]
 60%|██████    | 224552/371472 [7:12:54<12:25:23,  3.29it/s]
 60%|██████    | 224553/371472 [7:12:55<12:02:10,  3.39it/s]
 60%|██████    | 224554/371472 [7:12:55<12:09:58,  3.35it/s]
 60%|██████    | 224555/371472 [7:12:55<11:45:23,  3.47it/s]
 60%|██████    | 224556/371472 [7:12:56<11:38:24,  3.51it/s]
 60%|██████    | 224557/371472 [7:12:56<11:34:59,  3.52it/s]
 60%|██████    | 224558/371472 [7:12:56<12:55:30,  3.16it/s]
 60%|██████    | 224559/371472 [7:12:56<12:33:58,  3.25it/s]
 60%|██████    | 224560/371472 [7:12:57<12:27:20,  3.28it/s]
                                                            
{'loss': 2.8612, 'learning_rate': 4.561291990777651e-07, 'epoch': 9.67}
+
 60%|██████    | 224560/371472 [7:12:57<12:27:20,  3.28it/s]
 60%|██████    | 224561/371472 [7:12:57<12:04:23,  3.38it/s]
 60%|██████    | 224562/371472 [7:12:57<11:53:46,  3.43it/s]
 60%|██████    | 224563/371472 [7:12:58<11:53:18,  3.43it/s]
 60%|██████    | 224564/371472 [7:12:58<11:29:28,  3.55it/s]
 60%|██████    | 224565/371472 [7:12:58<11:30:33,  3.55it/s]
 60%|██████    | 224566/371472 [7:12:58<11:18:33,  3.61it/s]
 60%|██████    | 224567/371472 [7:12:59<11:08:35,  3.66it/s]
 60%|██████    | 224568/371472 [7:12:59<11:04:10,  3.69it/s]
 60%|██████    | 224569/371472 [7:12:59<11:11:03,  3.65it/s]
 60%|██████    | 224570/371472 [7:13:00<11:48:04,  3.46it/s]
 60%|██████    | 224571/371472 [7:13:00<11:46:01,  3.47it/s]
 60%|██████    | 224572/371472 [7:13:00<11:54:28,  3.43it/s]
 60%|██████    | 224573/371472 [7:13:00<11:46:29,  3.47it/s]
 60%|██████    | 224574/371472 [7:13:01<11:56:54,  3.42it/s]
 60%|██████    | 224575/371472 [7:13:01<11:57:59,  3.41it/s]
 60%|██████    | 224576/371472 [7:13:01<11:40:55,  3.49it/s]
 60%|██████    | 224577/371472 [7:13:02<12:01:08,  3.39it/s]
 60%|██████    | 224578/371472 [7:13:02<12:05:41,  3.37it/s]
 60%|██████    | 224579/371472 [7:13:02<11:43:06,  3.48it/s]
 60%|██████    | 224580/371472 [7:13:02<11:57:21,  3.41it/s]
                                                            
{'loss': 2.7651, 'learning_rate': 4.5608071710228616e-07, 'epoch': 9.67}
+
 60%|██████    | 224580/371472 [7:13:02<11:57:21,  3.41it/s]
 60%|██████    | 224581/371472 [7:13:03<12:06:31,  3.37it/s]
 60%|██████    | 224582/371472 [7:13:03<12:14:20,  3.33it/s]
 60%|██████    | 224583/371472 [7:13:03<12:03:52,  3.38it/s]
 60%|██████    | 224584/371472 [7:13:04<12:02:37,  3.39it/s]
 60%|██████    | 224585/371472 [7:13:04<12:02:32,  3.39it/s]
 60%|██████    | 224586/371472 [7:13:04<12:40:06,  3.22it/s]
 60%|██████    | 224587/371472 [7:13:05<13:00:21,  3.14it/s]
 60%|██████    | 224588/371472 [7:13:05<13:23:06,  3.05it/s]
 60%|██████    | 224589/371472 [7:13:05<13:11:59,  3.09it/s]
 60%|██████    | 224590/371472 [7:13:06<12:38:35,  3.23it/s]
 60%|██████    | 224591/371472 [7:13:06<12:13:02,  3.34it/s]
 60%|██████    | 224592/371472 [7:13:06<11:57:18,  3.41it/s]
 60%|██████    | 224593/371472 [7:13:06<12:25:35,  3.28it/s]
 60%|██████    | 224594/371472 [7:13:07<12:07:46,  3.36it/s]
 60%|██████    | 224595/371472 [7:13:07<11:48:09,  3.46it/s]
 60%|██████    | 224596/371472 [7:13:07<11:33:56,  3.53it/s]
 60%|██████    | 224597/371472 [7:13:08<12:09:23,  3.36it/s]
 60%|██████    | 224598/371472 [7:13:08<12:04:32,  3.38it/s]
 60%|██████    | 224599/371472 [7:13:08<11:52:03,  3.44it/s]
 60%|██████    | 224600/371472 [7:13:09<12:21:30,  3.30it/s]
                                                            
{'loss': 2.8943, 'learning_rate': 4.560322351268073e-07, 'epoch': 9.67}
+
 60%|██████    | 224600/371472 [7:13:09<12:21:30,  3.30it/s]
 60%|██████    | 224601/371472 [7:13:09<12:18:40,  3.31it/s]
 60%|██████    | 224602/371472 [7:13:09<11:54:47,  3.42it/s]
 60%|██████    | 224603/371472 [7:13:09<11:44:49,  3.47it/s]
 60%|██████    | 224604/371472 [7:13:10<12:20:48,  3.30it/s]
 60%|██████    | 224605/371472 [7:13:10<12:00:27,  3.40it/s]
 60%|██████    | 224606/371472 [7:13:10<11:54:25,  3.43it/s]
 60%|██████    | 224607/371472 [7:13:11<12:04:04,  3.38it/s]
 60%|██████    | 224608/371472 [7:13:11<11:52:30,  3.44it/s]
 60%|██████    | 224609/371472 [7:13:11<12:46:24,  3.19it/s]
 60%|██████    | 224610/371472 [7:13:12<12:44:19,  3.20it/s]
 60%|██████    | 224611/371472 [7:13:12<12:12:42,  3.34it/s]
 60%|██████    | 224612/371472 [7:13:12<12:40:07,  3.22it/s]
 60%|██████    | 224613/371472 [7:13:12<12:27:07,  3.28it/s]
 60%|██████    | 224614/371472 [7:13:13<11:51:40,  3.44it/s]
 60%|██████    | 224615/371472 [7:13:13<11:39:27,  3.50it/s]
 60%|██████    | 224616/371472 [7:13:13<12:09:22,  3.36it/s]
 60%|██████    | 224617/371472 [7:13:14<12:12:35,  3.34it/s]
 60%|██████    | 224618/371472 [7:13:14<12:10:36,  3.35it/s]
 60%|██████    | 224619/371472 [7:13:14<11:43:31,  3.48it/s]
 60%|██████    | 224620/371472 [7:13:14<11:45:35,  3.47it/s]
                                                            
{'loss': 2.7203, 'learning_rate': 4.5598375315132836e-07, 'epoch': 9.67}
+
 60%|██████    | 224620/371472 [7:13:14<11:45:35,  3.47it/s]
 60%|██████    | 224621/371472 [7:13:15<11:41:18,  3.49it/s]
 60%|██████    | 224622/371472 [7:13:15<11:33:58,  3.53it/s]
 60%|██████    | 224623/371472 [7:13:15<11:54:27,  3.43it/s]
 60%|██████    | 224624/371472 [7:13:16<12:20:18,  3.31it/s]
 60%|██████    | 224625/371472 [7:13:16<12:03:00,  3.39it/s]
 60%|██████    | 224626/371472 [7:13:16<12:27:37,  3.27it/s]
 60%|██████    | 224627/371472 [7:13:17<12:07:55,  3.36it/s]
 60%|██████    | 224628/371472 [7:13:17<12:32:24,  3.25it/s]
 60%|██████    | 224629/371472 [7:13:17<12:22:59,  3.29it/s]
 60%|██████    | 224630/371472 [7:13:17<11:54:57,  3.42it/s]
 60%|██████    | 224631/371472 [7:13:18<11:26:17,  3.57it/s]
 60%|██████    | 224632/371472 [7:13:18<11:25:49,  3.57it/s]
 60%|██████    | 224633/371472 [7:13:18<11:25:37,  3.57it/s]
 60%|██████    | 224634/371472 [7:13:19<11:54:10,  3.43it/s]
 60%|██████    | 224635/371472 [7:13:19<11:32:59,  3.53it/s]
 60%|██████    | 224636/371472 [7:13:19<13:27:37,  3.03it/s]
 60%|██████    | 224637/371472 [7:13:20<13:01:16,  3.13it/s]
 60%|██████    | 224638/371472 [7:13:20<12:38:09,  3.23it/s]
 60%|██████    | 224639/371472 [7:13:20<12:38:18,  3.23it/s]
 60%|██████    | 224640/371472 [7:13:20<12:31:51,  3.25it/s]
                                                            
{'loss': 2.7841, 'learning_rate': 4.5593527117584954e-07, 'epoch': 9.68}
+
 60%|██████    | 224640/371472 [7:13:20<12:31:51,  3.25it/s]
 60%|██████    | 224641/371472 [7:13:21<12:04:54,  3.38it/s]
 60%|██████    | 224642/371472 [7:13:21<13:35:34,  3.00it/s]
 60%|██████    | 224643/371472 [7:13:21<13:04:08,  3.12it/s]
 60%|██████    | 224644/371472 [7:13:22<12:50:11,  3.18it/s]
 60%|██████    | 224645/371472 [7:13:22<12:34:34,  3.24it/s]
 60%|██████    | 224646/371472 [7:13:22<12:24:02,  3.29it/s]
 60%|██████    | 224647/371472 [7:13:23<12:42:03,  3.21it/s]
 60%|██████    | 224648/371472 [7:13:23<12:43:00,  3.21it/s]
 60%|██████    | 224649/371472 [7:13:23<12:17:38,  3.32it/s]
 60%|██████    | 224650/371472 [7:13:24<12:02:37,  3.39it/s]
 60%|██████    | 224651/371472 [7:13:24<12:22:48,  3.29it/s]
 60%|██████    | 224652/371472 [7:13:24<12:25:06,  3.28it/s]
 60%|██████    | 224653/371472 [7:13:24<11:49:13,  3.45it/s]
 60%|██████    | 224654/371472 [7:13:25<12:01:10,  3.39it/s]
 60%|██████    | 224655/371472 [7:13:25<11:51:19,  3.44it/s]
 60%|██████    | 224656/371472 [7:13:25<11:43:11,  3.48it/s]
 60%|██████    | 224657/371472 [7:13:26<11:46:27,  3.46it/s]
 60%|██████    | 224658/371472 [7:13:26<11:29:54,  3.55it/s]
 60%|██████    | 224659/371472 [7:13:26<11:30:55,  3.54it/s]
 60%|██████    | 224660/371472 [7:13:26<11:26:25,  3.56it/s]
                                                            
{'loss': 2.5049, 'learning_rate': 4.558867892003706e-07, 'epoch': 9.68}
+
 60%|██████    | 224660/371472 [7:13:26<11:26:25,  3.56it/s]
 60%|██████    | 224661/371472 [7:13:27<11:46:26,  3.46it/s]
 60%|██████    | 224662/371472 [7:13:27<11:55:43,  3.42it/s]
 60%|██████    | 224663/371472 [7:13:27<12:11:05,  3.35it/s]
 60%|██████    | 224664/371472 [7:13:28<12:25:21,  3.28it/s]
 60%|██████    | 224665/371472 [7:13:28<12:18:05,  3.32it/s]
 60%|██████    | 224666/371472 [7:13:28<12:00:16,  3.40it/s]
 60%|██████    | 224667/371472 [7:13:28<11:43:27,  3.48it/s]
 60%|██████    | 224668/371472 [7:13:29<11:33:11,  3.53it/s]
 60%|██████    | 224669/371472 [7:13:29<11:22:13,  3.59it/s]
 60%|██████    | 224670/371472 [7:13:29<11:21:55,  3.59it/s]
 60%|██████    | 224671/371472 [7:13:30<11:29:52,  3.55it/s]
 60%|██████    | 224672/371472 [7:13:30<11:23:12,  3.58it/s]
 60%|██████    | 224673/371472 [7:13:30<11:26:59,  3.56it/s]
 60%|██████    | 224674/371472 [7:13:30<11:26:28,  3.56it/s]
 60%|██████    | 224675/371472 [7:13:31<12:48:26,  3.18it/s]
 60%|██████    | 224676/371472 [7:13:31<12:21:41,  3.30it/s]
 60%|██████    | 224677/371472 [7:13:31<12:08:37,  3.36it/s]
 60%|██████    | 224678/371472 [7:13:32<12:06:43,  3.37it/s]
 60%|██████    | 224679/371472 [7:13:32<12:15:44,  3.33it/s]
 60%|██████    | 224680/371472 [7:13:32<12:05:53,  3.37it/s]
                                                            
{'loss': 2.7598, 'learning_rate': 4.5583830722489173e-07, 'epoch': 9.68}
+
 60%|██████    | 224680/371472 [7:13:32<12:05:53,  3.37it/s]
 60%|██████    | 224681/371472 [7:13:33<12:02:01,  3.39it/s]
 60%|██████    | 224682/371472 [7:13:33<12:07:53,  3.36it/s]
 60%|██████    | 224683/371472 [7:13:33<12:31:27,  3.26it/s]
 60%|██████    | 224684/371472 [7:13:33<12:21:04,  3.30it/s]
 60%|██████    | 224685/371472 [7:13:34<12:11:28,  3.34it/s]
 60%|██████    | 224686/371472 [7:13:34<11:48:19,  3.45it/s]
 60%|██████    | 224687/371472 [7:13:34<11:54:07,  3.43it/s]
 60%|██████    | 224688/371472 [7:13:35<13:01:13,  3.13it/s]
 60%|██████    | 224689/371472 [7:13:35<12:40:27,  3.22it/s]
 60%|██████    | 224690/371472 [7:13:35<12:28:18,  3.27it/s]
 60%|██████    | 224691/371472 [7:13:36<12:09:34,  3.35it/s]
 60%|██████    | 224692/371472 [7:13:36<12:12:23,  3.34it/s]
 60%|██████    | 224693/371472 [7:13:36<11:44:46,  3.47it/s]
 60%|██████    | 224694/371472 [7:13:36<11:44:54,  3.47it/s]
 60%|██████    | 224695/371472 [7:13:37<11:36:19,  3.51it/s]
 60%|██████    | 224696/371472 [7:13:37<12:14:15,  3.33it/s]
 60%|██████    | 224697/371472 [7:13:37<12:15:19,  3.33it/s]
 60%|██████    | 224698/371472 [7:13:38<12:06:41,  3.37it/s]
 60%|██████    | 224699/371472 [7:13:38<13:31:01,  3.02it/s]
 60%|██████    | 224700/371472 [7:13:38<13:15:27,  3.08it/s]
                                                            
{'loss': 2.9121, 'learning_rate': 4.557898252494128e-07, 'epoch': 9.68}
+
 60%|██████    | 224700/371472 [7:13:38<13:15:27,  3.08it/s]
 60%|██████    | 224701/371472 [7:13:39<12:39:23,  3.22it/s]
 60%|██████    | 224702/371472 [7:13:39<12:10:09,  3.35it/s]
 60%|██████    | 224703/371472 [7:13:39<11:46:23,  3.46it/s]
 60%|██████    | 224704/371472 [7:13:39<11:49:05,  3.45it/s]
 60%|██████    | 224705/371472 [7:13:40<12:02:08,  3.39it/s]
 60%|██████    | 224706/371472 [7:13:40<11:40:06,  3.49it/s]
 60%|██████    | 224707/371472 [7:13:40<11:37:53,  3.50it/s]
 60%|██████    | 224708/371472 [7:13:41<11:24:53,  3.57it/s]
 60%|██████    | 224709/371472 [7:13:41<11:23:03,  3.58it/s]
 60%|██████    | 224710/371472 [7:13:41<11:17:51,  3.61it/s]
 60%|██████    | 224711/371472 [7:13:41<11:25:18,  3.57it/s]
 60%|██████    | 224712/371472 [7:13:42<11:44:28,  3.47it/s]
 60%|██████    | 224713/371472 [7:13:42<11:53:18,  3.43it/s]
 60%|██████    | 224714/371472 [7:13:42<12:17:03,  3.32it/s]
 60%|██████    | 224715/371472 [7:13:43<12:30:59,  3.26it/s]
 60%|██████    | 224716/371472 [7:13:43<12:24:02,  3.29it/s]
 60%|██████    | 224717/371472 [7:13:43<12:04:36,  3.38it/s]
 60%|██████    | 224718/371472 [7:13:44<11:55:16,  3.42it/s]
 60%|██████    | 224719/371472 [7:13:44<12:18:21,  3.31it/s]
 60%|██████    | 224720/371472 [7:13:44<11:43:43,  3.48it/s]
                                                            
{'loss': 2.7836, 'learning_rate': 4.5574134327393393e-07, 'epoch': 9.68}
+
 60%|██████    | 224720/371472 [7:13:44<11:43:43,  3.48it/s]
 60%|██████    | 224721/371472 [7:13:44<11:36:28,  3.51it/s]
 60%|██████    | 224722/371472 [7:13:45<11:40:41,  3.49it/s]
 60%|██████    | 224723/371472 [7:13:45<11:45:27,  3.47it/s]
 60%|██████    | 224724/371472 [7:13:45<11:41:36,  3.49it/s]
 60%|██████    | 224725/371472 [7:13:46<11:50:24,  3.44it/s]
 60%|██████    | 224726/371472 [7:13:46<11:35:27,  3.52it/s]
 60%|██████    | 224727/371472 [7:13:46<11:31:18,  3.54it/s]
 60%|██████    | 224728/371472 [7:13:46<11:47:35,  3.46it/s]
 60%|██████    | 224729/371472 [7:13:47<11:29:48,  3.55it/s]
 60%|██████    | 224730/371472 [7:13:47<11:55:15,  3.42it/s]
 60%|██████    | 224731/371472 [7:13:47<11:46:51,  3.46it/s]
 60%|██████    | 224732/371472 [7:13:48<12:11:11,  3.34it/s]
 60%|██████    | 224733/371472 [7:13:48<11:59:25,  3.40it/s]
 60%|██████    | 224734/371472 [7:13:48<12:40:15,  3.22it/s]
 60%|██████    | 224735/371472 [7:13:49<12:43:39,  3.20it/s]
 60%|██████    | 224736/371472 [7:13:49<12:28:39,  3.27it/s]
 60%|██████    | 224737/371472 [7:13:49<12:55:16,  3.15it/s]
 60%|██████    | 224738/371472 [7:13:49<12:13:49,  3.33it/s]
 60%|██████    | 224739/371472 [7:13:50<12:08:56,  3.35it/s]
 60%|██████    | 224740/371472 [7:13:50<12:09:15,  3.35it/s]
                                                            
{'loss': 2.7268, 'learning_rate': 4.55692861298455e-07, 'epoch': 9.68}
+
 60%|██████    | 224740/371472 [7:13:50<12:09:15,  3.35it/s]
 61%|██████    | 224741/371472 [7:13:50<12:10:06,  3.35it/s]
 61%|██████    | 224742/371472 [7:13:51<11:57:05,  3.41it/s]
 61%|██████    | 224743/371472 [7:13:51<11:54:14,  3.42it/s]
 61%|██████    | 224744/371472 [7:13:51<11:54:53,  3.42it/s]
 61%|██████    | 224745/371472 [7:13:51<11:43:47,  3.47it/s]
 61%|██████    | 224746/371472 [7:13:52<11:26:30,  3.56it/s]
 61%|██████    | 224747/371472 [7:13:52<11:28:37,  3.55it/s]
 61%|██████    | 224748/371472 [7:13:52<11:44:10,  3.47it/s]
 61%|██████    | 224749/371472 [7:13:53<11:33:26,  3.53it/s]
 61%|██████    | 224750/371472 [7:13:53<11:38:33,  3.50it/s]
 61%|██████    | 224751/371472 [7:13:53<11:30:13,  3.54it/s]
 61%|██████    | 224752/371472 [7:13:54<12:58:13,  3.14it/s]
 61%|██████    | 224753/371472 [7:13:54<12:47:24,  3.19it/s]
 61%|██████    | 224754/371472 [7:13:54<12:12:23,  3.34it/s]
 61%|██████    | 224755/371472 [7:13:54<12:22:52,  3.29it/s]
 61%|██████    | 224756/371472 [7:13:55<12:19:11,  3.31it/s]
 61%|██████    | 224757/371472 [7:13:55<12:01:33,  3.39it/s]
 61%|██████    | 224758/371472 [7:13:55<12:19:06,  3.31it/s]
 61%|██████    | 224759/371472 [7:13:56<11:56:05,  3.41it/s]
 61%|██████    | 224760/371472 [7:13:56<11:58:39,  3.40it/s]
                                                            
{'loss': 2.6832, 'learning_rate': 4.556443793229762e-07, 'epoch': 9.68}
+
 61%|██████    | 224760/371472 [7:13:56<11:58:39,  3.40it/s]
 61%|██████    | 224761/371472 [7:13:56<11:57:30,  3.41it/s]
 61%|██████    | 224762/371472 [7:13:56<11:45:08,  3.47it/s]
 61%|██████    | 224763/371472 [7:13:57<11:54:54,  3.42it/s]
 61%|██████    | 224764/371472 [7:13:57<12:08:24,  3.36it/s]
 61%|██████    | 224765/371472 [7:13:57<12:12:26,  3.34it/s]
 61%|██████    | 224766/371472 [7:13:58<12:24:17,  3.29it/s]
 61%|██████    | 224767/371472 [7:13:58<12:43:07,  3.20it/s]
 61%|██████    | 224768/371472 [7:13:58<13:26:22,  3.03it/s]
 61%|██████    | 224769/371472 [7:13:59<13:17:40,  3.07it/s]
 61%|██████    | 224770/371472 [7:13:59<12:51:03,  3.17it/s]
 61%|██████    | 224771/371472 [7:13:59<12:24:04,  3.29it/s]
 61%|██████    | 224772/371472 [7:14:00<11:58:22,  3.40it/s]
 61%|██████    | 224773/371472 [7:14:00<12:55:36,  3.15it/s]
 61%|██████    | 224774/371472 [7:14:00<13:35:23,  3.00it/s]
 61%|██████    | 224775/371472 [7:14:01<12:56:19,  3.15it/s]
 61%|██████    | 224776/371472 [7:14:01<12:44:51,  3.20it/s]
 61%|██████    | 224777/371472 [7:14:01<13:41:37,  2.98it/s]
 61%|██████    | 224778/371472 [7:14:02<13:02:44,  3.12it/s]
 61%|██████    | 224779/371472 [7:14:02<12:26:04,  3.28it/s]
 61%|██████    | 224780/371472 [7:14:02<12:15:02,  3.33it/s]
                                                            
{'loss': 2.6138, 'learning_rate': 4.5559589734749725e-07, 'epoch': 9.68}
+
 61%|██████    | 224780/371472 [7:14:02<12:15:02,  3.33it/s]
 61%|██████    | 224781/371472 [7:14:02<12:12:09,  3.34it/s]
 61%|██████    | 224782/371472 [7:14:03<12:28:29,  3.27it/s]
 61%|██████    | 224783/371472 [7:14:03<13:09:38,  3.10it/s]
 61%|██████    | 224784/371472 [7:14:03<12:41:58,  3.21it/s]
 61%|██████    | 224785/371472 [7:14:04<12:44:32,  3.20it/s]
 61%|██████    | 224786/371472 [7:14:04<12:13:47,  3.33it/s]
 61%|██████    | 224787/371472 [7:14:04<12:05:38,  3.37it/s]
 61%|██████    | 224788/371472 [7:14:05<11:56:07,  3.41it/s]
 61%|██████    | 224789/371472 [7:14:05<12:08:08,  3.36it/s]
 61%|██████    | 224790/371472 [7:14:05<12:04:42,  3.37it/s]
 61%|██████    | 224791/371472 [7:14:05<11:54:32,  3.42it/s]
 61%|██████    | 224792/371472 [7:14:06<11:44:58,  3.47it/s]
 61%|██████    | 224793/371472 [7:14:06<11:41:17,  3.49it/s]
 61%|██████    | 224794/371472 [7:14:06<11:51:33,  3.44it/s]
 61%|██████    | 224795/371472 [7:14:07<11:36:49,  3.51it/s]
 61%|██████    | 224796/371472 [7:14:07<11:21:36,  3.59it/s]
 61%|██████    | 224797/371472 [7:14:07<11:26:44,  3.56it/s]
 61%|██████    | 224798/371472 [7:14:08<13:00:42,  3.13it/s]
 61%|██████    | 224799/371472 [7:14:08<12:44:44,  3.20it/s]
 61%|██████    | 224800/371472 [7:14:08<12:20:24,  3.30it/s]
                                                            
{'loss': 2.7521, 'learning_rate': 4.5554741537201837e-07, 'epoch': 9.68}
+
 61%|██████    | 224800/371472 [7:14:08<12:20:24,  3.30it/s]
 61%|██████    | 224801/371472 [7:14:08<12:45:17,  3.19it/s]
 61%|██████    | 224802/371472 [7:14:09<12:15:56,  3.32it/s]
 61%|██████    | 224803/371472 [7:14:09<12:10:09,  3.35it/s]
 61%|██████    | 224804/371472 [7:14:09<12:11:32,  3.34it/s]
 61%|██████    | 224805/371472 [7:14:10<12:04:24,  3.37it/s]
 61%|██████    | 224806/371472 [7:14:10<11:59:36,  3.40it/s]
 61%|██████    | 224807/371472 [7:14:10<11:49:21,  3.45it/s]
 61%|██████    | 224808/371472 [7:14:10<11:23:49,  3.57it/s]
 61%|██████    | 224809/371472 [7:14:11<11:30:06,  3.54it/s]
 61%|██████    | 224810/371472 [7:14:11<12:20:09,  3.30it/s]
 61%|██████    | 224811/371472 [7:14:11<12:09:38,  3.35it/s]
 61%|██████    | 224812/371472 [7:14:12<12:30:21,  3.26it/s]
 61%|██████    | 224813/371472 [7:14:12<12:12:36,  3.34it/s]
 61%|██████    | 224814/371472 [7:14:12<11:54:41,  3.42it/s]
 61%|██████    | 224815/371472 [7:14:13<11:51:22,  3.44it/s]
 61%|██████    | 224816/371472 [7:14:13<12:12:02,  3.34it/s]
 61%|██████    | 224817/371472 [7:14:13<12:15:35,  3.32it/s]
 61%|██████    | 224818/371472 [7:14:13<11:59:29,  3.40it/s]
 61%|██████    | 224819/371472 [7:14:14<11:42:44,  3.48it/s]
 61%|██████    | 224820/371472 [7:14:14<11:32:14,  3.53it/s]
                                                            
{'loss': 2.6972, 'learning_rate': 4.5549893339653944e-07, 'epoch': 9.68}
+
 61%|██████    | 224820/371472 [7:14:14<11:32:14,  3.53it/s]
 61%|██████    | 224821/371472 [7:14:14<12:19:04,  3.31it/s]
 61%|██████    | 224822/371472 [7:14:15<12:17:44,  3.31it/s]
 61%|██████    | 224823/371472 [7:14:15<12:14:34,  3.33it/s]
 61%|██████    | 224824/371472 [7:14:15<12:12:00,  3.34it/s]
 61%|██████    | 224825/371472 [7:14:15<11:59:00,  3.40it/s]
 61%|██████    | 224826/371472 [7:14:16<11:43:10,  3.48it/s]
 61%|██████    | 224827/371472 [7:14:16<11:28:47,  3.55it/s]
 61%|██████    | 224828/371472 [7:14:16<11:37:52,  3.50it/s]
 61%|██████    | 224829/371472 [7:14:17<11:58:48,  3.40it/s]
 61%|██████    | 224830/371472 [7:14:17<11:44:58,  3.47it/s]
 61%|██████    | 224831/371472 [7:14:17<11:54:51,  3.42it/s]
 61%|██████    | 224832/371472 [7:14:18<12:28:06,  3.27it/s]
 61%|██████    | 224833/371472 [7:14:18<12:15:57,  3.32it/s]
 61%|██████    | 224834/371472 [7:14:18<12:19:30,  3.30it/s]
 61%|██████    | 224835/371472 [7:14:19<13:16:32,  3.07it/s]
 61%|██████    | 224836/371472 [7:14:19<12:34:17,  3.24it/s]
 61%|██████    | 224837/371472 [7:14:19<12:12:44,  3.34it/s]
 61%|██████    | 224838/371472 [7:14:19<12:41:26,  3.21it/s]
 61%|██████    | 224839/371472 [7:14:20<12:57:01,  3.15it/s]
 61%|██████    | 224840/371472 [7:14:20<12:10:25,  3.35it/s]
                                                            
{'loss': 2.7531, 'learning_rate': 4.554504514210605e-07, 'epoch': 9.68}
+
 61%|██████    | 224840/371472 [7:14:20<12:10:25,  3.35it/s]
 61%|██████    | 224841/371472 [7:14:20<12:03:25,  3.38it/s]
 61%|██████    | 224842/371472 [7:14:21<12:01:08,  3.39it/s]
 61%|██████    | 224843/371472 [7:14:21<11:51:28,  3.43it/s]
 61%|██████    | 224844/371472 [7:14:21<12:01:41,  3.39it/s]
 61%|██████    | 224845/371472 [7:14:21<11:51:05,  3.44it/s]
 61%|██████    | 224846/371472 [7:14:22<11:29:51,  3.54it/s]
 61%|██████    | 224847/371472 [7:14:22<11:49:14,  3.45it/s]
 61%|██████    | 224848/371472 [7:14:22<11:41:40,  3.48it/s]
 61%|██████    | 224849/371472 [7:14:23<12:21:55,  3.29it/s]
 61%|██████    | 224850/371472 [7:14:23<12:21:26,  3.30it/s]
 61%|██████    | 224851/371472 [7:14:23<12:14:06,  3.33it/s]
 61%|██████    | 224852/371472 [7:14:24<11:47:38,  3.45it/s]
 61%|██████    | 224853/371472 [7:14:24<11:27:17,  3.56it/s]
 61%|██████    | 224854/371472 [7:14:24<11:32:25,  3.53it/s]
 61%|██████    | 224855/371472 [7:14:24<12:48:54,  3.18it/s]
 61%|██████    | 224856/371472 [7:14:25<12:54:38,  3.15it/s]
 61%|██████    | 224857/371472 [7:14:25<12:32:50,  3.25it/s]
 61%|██████    | 224858/371472 [7:14:25<12:12:54,  3.33it/s]
 61%|██████    | 224859/371472 [7:14:26<12:32:12,  3.25it/s]
 61%|██████    | 224860/371472 [7:14:26<12:24:06,  3.28it/s]
                                                            
{'loss': 2.6843, 'learning_rate': 4.5540196944558164e-07, 'epoch': 9.69}
+
 61%|██████    | 224860/371472 [7:14:26<12:24:06,  3.28it/s]
 61%|██████    | 224861/371472 [7:14:26<12:51:21,  3.17it/s]
 61%|██████    | 224862/371472 [7:14:27<12:51:10,  3.17it/s]
 61%|██████    | 224863/371472 [7:14:27<12:13:47,  3.33it/s]
 61%|██████    | 224864/371472 [7:14:27<12:33:11,  3.24it/s]
 61%|██████    | 224865/371472 [7:14:28<12:29:37,  3.26it/s]
 61%|██████    | 224866/371472 [7:14:28<12:34:09,  3.24it/s]
 61%|██████    | 224867/371472 [7:14:28<12:09:22,  3.35it/s]
 61%|██████    | 224868/371472 [7:14:28<12:19:27,  3.30it/s]
 61%|██████    | 224869/371472 [7:14:29<12:30:52,  3.25it/s]
 61%|██████    | 224870/371472 [7:14:29<12:21:16,  3.30it/s]
 61%|██████    | 224871/371472 [7:14:29<12:14:33,  3.33it/s]
 61%|██████    | 224872/371472 [7:14:30<11:53:19,  3.43it/s]
 61%|██████    | 224873/371472 [7:14:30<12:28:21,  3.26it/s]
 61%|██████    | 224874/371472 [7:14:30<11:59:46,  3.39it/s]
 61%|██████    | 224875/371472 [7:14:31<12:07:21,  3.36it/s]
 61%|██████    | 224876/371472 [7:14:31<11:54:11,  3.42it/s]
 61%|██████    | 224877/371472 [7:14:31<11:37:00,  3.51it/s]
 61%|██████    | 224878/371472 [7:14:31<11:39:18,  3.49it/s]
 61%|██████    | 224879/371472 [7:14:32<11:32:29,  3.53it/s]
 61%|██████    | 224880/371472 [7:14:32<12:06:46,  3.36it/s]
                                                            
{'loss': 2.8923, 'learning_rate': 4.553534874701027e-07, 'epoch': 9.69}
+
 61%|██████    | 224880/371472 [7:14:32<12:06:46,  3.36it/s]
 61%|██████    | 224881/371472 [7:14:32<11:56:25,  3.41it/s]
 61%|██████    | 224882/371472 [7:14:33<11:45:28,  3.46it/s]
 61%|██████    | 224883/371472 [7:14:33<12:30:09,  3.26it/s]
 61%|██████    | 224884/371472 [7:14:33<12:40:14,  3.21it/s]
 61%|██████    | 224885/371472 [7:14:33<12:27:58,  3.27it/s]
 61%|██████    | 224886/371472 [7:14:34<12:02:35,  3.38it/s]
 61%|██████    | 224887/371472 [7:14:34<11:54:49,  3.42it/s]
 61%|██████    | 224888/371472 [7:14:34<11:57:21,  3.41it/s]
 61%|██████    | 224889/371472 [7:14:35<12:31:40,  3.25it/s]
 61%|██████    | 224890/371472 [7:14:35<12:53:23,  3.16it/s]
 61%|██████    | 224891/371472 [7:14:35<13:08:04,  3.10it/s]
 61%|██████    | 224892/371472 [7:14:36<13:30:30,  3.01it/s]
 61%|██████    | 224893/371472 [7:14:36<13:45:49,  2.96it/s]
 61%|██████    | 224894/371472 [7:14:36<13:18:01,  3.06it/s]
 61%|██████    | 224895/371472 [7:14:37<12:35:37,  3.23it/s]
 61%|██████    | 224896/371472 [7:14:37<12:27:47,  3.27it/s]
 61%|██████    | 224897/371472 [7:14:37<12:27:39,  3.27it/s]
 61%|██████    | 224898/371472 [7:14:38<12:19:51,  3.30it/s]
 61%|██████    | 224899/371472 [7:14:38<12:06:01,  3.36it/s]
 61%|██████    | 224900/371472 [7:14:38<12:13:13,  3.33it/s]
                                                            
{'loss': 2.7335, 'learning_rate': 4.5530500549462384e-07, 'epoch': 9.69}
+
 61%|██████    | 224900/371472 [7:14:38<12:13:13,  3.33it/s]
 61%|██████    | 224901/371472 [7:14:38<12:43:59,  3.20it/s]
 61%|██████    | 224902/371472 [7:14:39<12:31:27,  3.25it/s]
 61%|██████    | 224903/371472 [7:14:39<12:16:38,  3.32it/s]
 61%|██████    | 224904/371472 [7:14:39<12:19:10,  3.30it/s]
 61%|██████    | 224905/371472 [7:14:40<13:05:03,  3.11it/s]
 61%|██████    | 224906/371472 [7:14:40<12:41:31,  3.21it/s]
 61%|██████    | 224907/371472 [7:14:40<12:27:37,  3.27it/s]
 61%|██████    | 224908/371472 [7:14:41<12:19:17,  3.30it/s]
 61%|██████    | 224909/371472 [7:14:41<12:18:25,  3.31it/s]
 61%|██████    | 224910/371472 [7:14:41<11:58:47,  3.40it/s]
 61%|██████    | 224911/371472 [7:14:41<12:10:29,  3.34it/s]
 61%|██████    | 224912/371472 [7:14:42<12:11:01,  3.34it/s]
 61%|██████    | 224913/371472 [7:14:42<12:26:29,  3.27it/s]
 61%|██████    | 224914/371472 [7:14:42<12:12:41,  3.33it/s]
 61%|██████    | 224915/371472 [7:14:43<12:18:14,  3.31it/s]
 61%|██████    | 224916/371472 [7:14:43<12:03:22,  3.38it/s]
 61%|██████    | 224917/371472 [7:14:43<12:46:59,  3.18it/s]
 61%|██████    | 224918/371472 [7:14:44<12:49:09,  3.18it/s]
 61%|██████    | 224919/371472 [7:14:44<12:27:22,  3.27it/s]
 61%|██████    | 224920/371472 [7:14:44<11:52:55,  3.43it/s]
                                                            
{'loss': 2.6646, 'learning_rate': 4.552565235191449e-07, 'epoch': 9.69}
+
 61%|██████    | 224920/371472 [7:14:44<11:52:55,  3.43it/s]
 61%|██████    | 224921/371472 [7:14:44<11:33:02,  3.52it/s]
 61%|██████    | 224922/371472 [7:14:45<11:26:44,  3.56it/s]
 61%|██████    | 224923/371472 [7:14:45<11:26:25,  3.56it/s]
 61%|██████    | 224924/371472 [7:14:45<11:38:35,  3.50it/s]
 61%|██████    | 224925/371472 [7:14:46<12:04:59,  3.37it/s]
 61%|██████    | 224926/371472 [7:14:46<12:42:57,  3.20it/s]
 61%|██████    | 224927/371472 [7:14:46<12:11:00,  3.34it/s]
 61%|██████    | 224928/371472 [7:14:47<11:45:04,  3.46it/s]
 61%|██████    | 224929/371472 [7:14:47<11:43:07,  3.47it/s]
 61%|██████    | 224930/371472 [7:14:47<12:03:13,  3.38it/s]
 61%|██████    | 224931/371472 [7:14:47<11:53:27,  3.42it/s]
 61%|██████    | 224932/371472 [7:14:48<11:42:15,  3.48it/s]
 61%|██████    | 224933/371472 [7:14:48<11:52:57,  3.43it/s]
 61%|██████    | 224934/371472 [7:14:48<11:46:44,  3.46it/s]
 61%|██████    | 224935/371472 [7:14:49<12:13:06,  3.33it/s]
 61%|██████    | 224936/371472 [7:14:49<12:04:34,  3.37it/s]
 61%|██████    | 224937/371472 [7:14:49<12:03:24,  3.38it/s]
 61%|██████    | 224938/371472 [7:14:49<11:52:47,  3.43it/s]
 61%|██████    | 224939/371472 [7:14:50<12:27:22,  3.27it/s]
 61%|██████    | 224940/371472 [7:14:50<12:23:15,  3.29it/s]
                                                            
{'loss': 2.695, 'learning_rate': 4.552080415436661e-07, 'epoch': 9.69}
+
 61%|██████    | 224940/371472 [7:14:50<12:23:15,  3.29it/s]
 61%|██████    | 224941/371472 [7:14:50<12:55:39,  3.15it/s]
 61%|██████    | 224942/371472 [7:14:51<12:29:50,  3.26it/s]
 61%|██████    | 224943/371472 [7:14:51<12:25:58,  3.27it/s]
 61%|██████    | 224944/371472 [7:14:51<12:29:18,  3.26it/s]
 61%|██████    | 224945/371472 [7:14:52<13:14:21,  3.07it/s]
 61%|██████    | 224946/371472 [7:14:52<12:44:39,  3.19it/s]
 61%|██████    | 224947/371472 [7:14:52<12:19:22,  3.30it/s]
 61%|██████    | 224948/371472 [7:14:53<12:27:36,  3.27it/s]
 61%|██████    | 224949/371472 [7:14:53<12:09:49,  3.35it/s]
 61%|██████    | 224950/371472 [7:14:53<11:48:58,  3.44it/s]
 61%|██████    | 224951/371472 [7:14:53<12:33:29,  3.24it/s]
 61%|██████    | 224952/371472 [7:14:54<12:24:32,  3.28it/s]
 61%|██████    | 224953/371472 [7:14:54<12:48:25,  3.18it/s]
 61%|██████    | 224954/371472 [7:14:54<12:41:50,  3.21it/s]
 61%|██████    | 224955/371472 [7:14:55<12:00:42,  3.39it/s]
 61%|██████    | 224956/371472 [7:14:55<11:54:41,  3.42it/s]
 61%|██████    | 224957/371472 [7:14:55<11:47:29,  3.45it/s]
 61%|██████    | 224958/371472 [7:14:56<12:09:45,  3.35it/s]
 61%|██████    | 224959/371472 [7:14:56<12:10:51,  3.34it/s]
 61%|██████    | 224960/371472 [7:14:56<11:52:11,  3.43it/s]
                                                            
{'loss': 2.7809, 'learning_rate': 4.5515955956818716e-07, 'epoch': 9.69}
+
 61%|██████    | 224960/371472 [7:14:56<11:52:11,  3.43it/s]
 61%|██████    | 224961/371472 [7:14:56<11:50:15,  3.44it/s]
 61%|██████    | 224962/371472 [7:14:57<12:33:30,  3.24it/s]
 61%|██████    | 224963/371472 [7:14:57<12:19:56,  3.30it/s]
 61%|██████    | 224964/371472 [7:14:57<12:07:18,  3.36it/s]
 61%|██████    | 224965/371472 [7:14:58<12:22:54,  3.29it/s]
 61%|██████    | 224966/371472 [7:14:58<12:05:54,  3.36it/s]
 61%|██████    | 224967/371472 [7:14:58<11:51:59,  3.43it/s]
 61%|██████    | 224968/371472 [7:14:58<11:28:26,  3.55it/s]
 61%|██████    | 224969/371472 [7:14:59<11:37:25,  3.50it/s]
 61%|██████    | 224970/371472 [7:14:59<12:41:22,  3.21it/s]
 61%|██████    | 224971/371472 [7:15:00<13:24:16,  3.04it/s]
 61%|██████    | 224972/371472 [7:15:00<12:47:54,  3.18it/s]
 61%|██████    | 224973/371472 [7:15:00<12:37:08,  3.22it/s]
 61%|██████    | 224974/371472 [7:15:00<12:20:21,  3.30it/s]
 61%|██████    | 224975/371472 [7:15:01<12:30:38,  3.25it/s]
 61%|██████    | 224976/371472 [7:15:01<13:11:32,  3.08it/s]
 61%|██████    | 224977/371472 [7:15:01<12:39:20,  3.22it/s]
 61%|██████    | 224978/371472 [7:15:02<12:23:10,  3.29it/s]
 61%|██████    | 224979/371472 [7:15:02<12:06:23,  3.36it/s]
 61%|██████    | 224980/371472 [7:15:02<12:11:12,  3.34it/s]
                                                            
{'loss': 2.7469, 'learning_rate': 4.551110775927083e-07, 'epoch': 9.69}
+
 61%|██████    | 224980/371472 [7:15:02<12:11:12,  3.34it/s]
 61%|██████    | 224981/371472 [7:15:03<12:33:23,  3.24it/s]
 61%|██████    | 224982/371472 [7:15:03<12:06:33,  3.36it/s]
 61%|██████    | 224983/371472 [7:15:03<12:07:35,  3.36it/s]
 61%|██████    | 224984/371472 [7:15:03<12:08:29,  3.35it/s]
 61%|██████    | 224985/371472 [7:15:04<11:56:29,  3.41it/s]
 61%|██████    | 224986/371472 [7:15:04<11:37:55,  3.50it/s]
 61%|██████    | 224987/371472 [7:15:04<11:54:38,  3.42it/s]
 61%|██████    | 224988/371472 [7:15:05<12:02:20,  3.38it/s]
 61%|██████    | 224989/371472 [7:15:05<11:58:24,  3.40it/s]
 61%|██████    | 224990/371472 [7:15:05<13:00:55,  3.13it/s]
 61%|██████    | 224991/371472 [7:15:06<12:31:45,  3.25it/s]
 61%|██████    | 224992/371472 [7:15:06<13:00:40,  3.13it/s]
 61%|██████    | 224993/371472 [7:15:06<13:43:55,  2.96it/s]
 61%|██████    | 224994/371472 [7:15:07<13:12:34,  3.08it/s]
 61%|██████    | 224995/371472 [7:15:07<12:41:33,  3.21it/s]
 61%|██████    | 224996/371472 [7:15:07<12:44:32,  3.19it/s]
 61%|██████    | 224997/371472 [7:15:07<12:16:28,  3.31it/s]
 61%|██████    | 224998/371472 [7:15:08<13:59:23,  2.91it/s]
 61%|██████    | 224999/371472 [7:15:08<12:51:44,  3.16it/s]
 61%|██████    | 225000/371472 [7:15:08<12:42:03,  3.20it/s]
                                                            
{'loss': 2.7765, 'learning_rate': 4.5506259561722935e-07, 'epoch': 9.69}
+
 61%|██████    | 225000/371472 [7:15:08<12:42:03,  3.20it/s]
 61%|██████    | 225001/371472 [7:15:09<12:26:05,  3.27it/s]
 61%|██████    | 225002/371472 [7:15:09<12:16:34,  3.31it/s]
 61%|██████    | 225003/371472 [7:15:09<12:00:41,  3.39it/s]
 61%|██████    | 225004/371472 [7:15:10<12:07:58,  3.35it/s]
 61%|██████    | 225005/371472 [7:15:10<11:59:09,  3.39it/s]
 61%|██████    | 225006/371472 [7:15:10<11:48:09,  3.45it/s]
 61%|██████    | 225007/371472 [7:15:10<11:30:54,  3.53it/s]
 61%|██████    | 225008/371472 [7:15:11<12:42:41,  3.20it/s]
 61%|██████    | 225009/371472 [7:15:11<12:44:58,  3.19it/s]
 61%|██████    | 225010/371472 [7:15:11<12:23:11,  3.28it/s]
 61%|██████    | 225011/371472 [7:15:12<12:47:05,  3.18it/s]
 61%|██████    | 225012/371472 [7:15:12<12:21:30,  3.29it/s]
 61%|██████    | 225013/371472 [7:15:12<11:46:04,  3.46it/s]
 61%|██████    | 225014/371472 [7:15:13<12:13:51,  3.33it/s]
 61%|██████    | 225015/371472 [7:15:13<12:02:52,  3.38it/s]
 61%|██████    | 225016/371472 [7:15:13<12:39:50,  3.21it/s]
 61%|██████    | 225017/371472 [7:15:14<13:46:36,  2.95it/s]
 61%|██████    | 225018/371472 [7:15:14<13:10:51,  3.09it/s]
 61%|██████    | 225019/371472 [7:15:14<13:08:01,  3.10it/s]
 61%|██████    | 225020/371472 [7:15:15<12:27:32,  3.27it/s]
                                                            
{'loss': 2.6461, 'learning_rate': 4.5501411364175053e-07, 'epoch': 9.69}
+
 61%|██████    | 225020/371472 [7:15:15<12:27:32,  3.27it/s]
 61%|██████    | 225021/371472 [7:15:15<12:56:36,  3.14it/s]
 61%|██████    | 225022/371472 [7:15:15<13:09:28,  3.09it/s]
 61%|██████    | 225023/371472 [7:15:15<12:38:50,  3.22it/s]
 61%|██████    | 225024/371472 [7:15:16<12:20:08,  3.30it/s]
 61%|██████    | 225025/371472 [7:15:16<12:42:47,  3.20it/s]
 61%|██████    | 225026/371472 [7:15:16<12:17:17,  3.31it/s]
 61%|██████    | 225027/371472 [7:15:17<11:53:41,  3.42it/s]
 61%|██████    | 225028/371472 [7:15:17<12:13:41,  3.33it/s]
 61%|██████    | 225029/371472 [7:15:17<12:08:00,  3.35it/s]
 61%|██████    | 225030/371472 [7:15:18<12:52:15,  3.16it/s]
 61%|██████    | 225031/371472 [7:15:18<12:19:03,  3.30it/s]
 61%|██████    | 225032/371472 [7:15:18<12:06:41,  3.36it/s]
 61%|██████    | 225033/371472 [7:15:18<12:23:00,  3.28it/s]
 61%|██████    | 225034/371472 [7:15:19<12:02:33,  3.38it/s]
 61%|██████    | 225035/371472 [7:15:19<12:06:36,  3.36it/s]
 61%|██████    | 225036/371472 [7:15:19<11:59:43,  3.39it/s]
 61%|██████    | 225037/371472 [7:15:20<12:07:27,  3.35it/s]
 61%|██████    | 225038/371472 [7:15:20<11:57:56,  3.40it/s]
 61%|██████    | 225039/371472 [7:15:20<11:34:06,  3.52it/s]
 61%|██████    | 225040/371472 [7:15:21<11:37:49,  3.50it/s]
                                                            
{'loss': 2.6859, 'learning_rate': 4.549656316662716e-07, 'epoch': 9.69}
+
 61%|██████    | 225040/371472 [7:15:21<11:37:49,  3.50it/s]
 61%|██████    | 225041/371472 [7:15:21<11:42:04,  3.48it/s]
 61%|██████    | 225042/371472 [7:15:21<11:34:13,  3.52it/s]
 61%|██████    | 225043/371472 [7:15:21<11:42:53,  3.47it/s]
 61%|██████    | 225044/371472 [7:15:22<11:39:39,  3.49it/s]
 61%|██████    | 225045/371472 [7:15:22<12:18:53,  3.30it/s]
 61%|██████    | 225046/371472 [7:15:22<12:00:23,  3.39it/s]
 61%|██████    | 225047/371472 [7:15:23<12:13:28,  3.33it/s]
 61%|██████    | 225048/371472 [7:15:23<12:05:22,  3.36it/s]
 61%|██████    | 225049/371472 [7:15:23<11:50:52,  3.43it/s]
 61%|██████    | 225050/371472 [7:15:23<12:08:18,  3.35it/s]
 61%|██████    | 225051/371472 [7:15:24<13:21:46,  3.04it/s]
 61%|██████    | 225052/371472 [7:15:24<12:51:20,  3.16it/s]
 61%|██████    | 225053/371472 [7:15:25<13:19:08,  3.05it/s]
 61%|██████    | 225054/371472 [7:15:25<13:03:30,  3.11it/s]
 61%|██████    | 225055/371472 [7:15:25<12:34:26,  3.23it/s]
 61%|██████    | 225056/371472 [7:15:25<12:00:48,  3.39it/s]
 61%|██████    | 225057/371472 [7:15:26<11:39:47,  3.49it/s]
 61%|██████    | 225058/371472 [7:15:26<12:18:06,  3.31it/s]
 61%|██████    | 225059/371472 [7:15:26<12:14:45,  3.32it/s]
 61%|██████    | 225060/371472 [7:15:27<12:15:43,  3.32it/s]
                                                            
{'loss': 2.7593, 'learning_rate': 4.549171496907927e-07, 'epoch': 9.69}
+
 61%|██████    | 225060/371472 [7:15:27<12:15:43,  3.32it/s]
 61%|██████    | 225061/371472 [7:15:27<12:13:29,  3.33it/s]
 61%|██████    | 225062/371472 [7:15:27<12:03:05,  3.37it/s]
 61%|██████    | 225063/371472 [7:15:27<12:27:04,  3.27it/s]
 61%|██████    | 225064/371472 [7:15:28<12:23:19,  3.28it/s]
 61%|██████    | 225065/371472 [7:15:28<12:27:47,  3.26it/s]
 61%|██████    | 225066/371472 [7:15:28<12:02:18,  3.38it/s]
 61%|██████    | 225067/371472 [7:15:29<11:54:43,  3.41it/s]
 61%|██████    | 225068/371472 [7:15:29<11:50:54,  3.43it/s]
 61%|██████    | 225069/371472 [7:15:29<11:42:44,  3.47it/s]
 61%|██████    | 225070/371472 [7:15:30<12:22:40,  3.29it/s]
 61%|██████    | 225071/371472 [7:15:30<11:55:00,  3.41it/s]
 61%|██████    | 225072/371472 [7:15:30<12:08:37,  3.35it/s]
 61%|██████    | 225073/371472 [7:15:31<13:11:40,  3.08it/s]
 61%|██████    | 225074/371472 [7:15:31<12:34:39,  3.23it/s]
 61%|██████    | 225075/371472 [7:15:31<13:14:32,  3.07it/s]
 61%|██████    | 225076/371472 [7:15:32<13:37:32,  2.98it/s]
 61%|██████    | 225077/371472 [7:15:32<12:55:07,  3.15it/s]
 61%|██████    | 225078/371472 [7:15:32<12:22:10,  3.29it/s]
 61%|██████    | 225079/371472 [7:15:32<12:13:09,  3.33it/s]
 61%|██████    | 225080/371472 [7:15:33<12:00:07,  3.39it/s]
                                                            
{'loss': 2.729, 'learning_rate': 4.548686677153138e-07, 'epoch': 9.69}
+
 61%|██████    | 225080/371472 [7:15:33<12:00:07,  3.39it/s]
 61%|██████    | 225081/371472 [7:15:33<12:27:49,  3.26it/s]
 61%|██████    | 225082/371472 [7:15:33<11:52:17,  3.43it/s]
 61%|██████    | 225083/371472 [7:15:34<11:40:17,  3.48it/s]
 61%|██████    | 225084/371472 [7:15:34<11:21:54,  3.58it/s]
 61%|██████    | 225085/371472 [7:15:34<12:46:23,  3.18it/s]
 61%|██████    | 225086/371472 [7:15:35<13:11:49,  3.08it/s]
 61%|██████    | 225087/371472 [7:15:35<12:35:26,  3.23it/s]
 61%|██████    | 225088/371472 [7:15:35<12:10:32,  3.34it/s]
 61%|██████    | 225089/371472 [7:15:35<12:05:06,  3.36it/s]
 61%|██████    | 225090/371472 [7:15:36<12:01:40,  3.38it/s]
 61%|██████    | 225091/371472 [7:15:36<12:02:54,  3.37it/s]
 61%|██████    | 225092/371472 [7:15:36<11:58:13,  3.40it/s]
 61%|██████    | 225093/371472 [7:15:37<11:47:27,  3.45it/s]
 61%|██████    | 225094/371472 [7:15:37<11:36:46,  3.50it/s]
 61%|██████    | 225095/371472 [7:15:37<12:04:08,  3.37it/s]
 61%|██████    | 225096/371472 [7:15:37<12:30:16,  3.25it/s]
 61%|██████    | 225097/371472 [7:15:38<12:22:43,  3.28it/s]
 61%|██████    | 225098/371472 [7:15:38<12:06:04,  3.36it/s]
 61%|██████    | 225099/371472 [7:15:38<12:03:50,  3.37it/s]
 61%|██████    | 225100/371472 [7:15:39<11:55:58,  3.41it/s]
                                                            
{'loss': 2.8962, 'learning_rate': 4.54820185739835e-07, 'epoch': 9.7}
+
 61%|██████    | 225100/371472 [7:15:39<11:55:58,  3.41it/s]
 61%|██████    | 225101/371472 [7:15:39<11:51:26,  3.43it/s]
 61%|██████    | 225102/371472 [7:15:39<12:03:03,  3.37it/s]
 61%|██████    | 225103/371472 [7:15:40<12:10:35,  3.34it/s]
 61%|██████    | 225104/371472 [7:15:40<11:50:00,  3.44it/s]
 61%|██████    | 225105/371472 [7:15:40<11:39:10,  3.49it/s]
 61%|██████    | 225106/371472 [7:15:40<11:39:19,  3.49it/s]
 61%|██████    | 225107/371472 [7:15:41<12:12:56,  3.33it/s]
 61%|██████    | 225108/371472 [7:15:41<11:53:56,  3.42it/s]
 61%|██████    | 225109/371472 [7:15:41<12:01:18,  3.38it/s]
 61%|██████    | 225110/371472 [7:15:42<12:02:39,  3.38it/s]
 61%|██████    | 225111/371472 [7:15:42<12:52:13,  3.16it/s]
 61%|██████    | 225112/371472 [7:15:42<12:32:38,  3.24it/s]
 61%|██████    | 225113/371472 [7:15:43<12:25:46,  3.27it/s]
 61%|██████    | 225114/371472 [7:15:43<12:27:15,  3.26it/s]
 61%|██████    | 225115/371472 [7:15:43<12:33:24,  3.24it/s]
 61%|██████    | 225116/371472 [7:15:43<12:13:55,  3.32it/s]
 61%|██████    | 225117/371472 [7:15:44<12:05:24,  3.36it/s]
 61%|██████    | 225118/371472 [7:15:44<11:46:35,  3.45it/s]
 61%|██████    | 225119/371472 [7:15:44<12:08:12,  3.35it/s]
 61%|██████    | 225120/371472 [7:15:45<12:02:53,  3.37it/s]
                                                            
{'loss': 2.7119, 'learning_rate': 4.54771703764356e-07, 'epoch': 9.7}
+
 61%|██████    | 225120/371472 [7:15:45<12:02:53,  3.37it/s]
 61%|██████    | 225121/371472 [7:15:45<12:19:11,  3.30it/s]
 61%|██████    | 225122/371472 [7:15:45<12:00:49,  3.38it/s]
 61%|██████    | 225123/371472 [7:15:45<11:48:49,  3.44it/s]
 61%|██████    | 225124/371472 [7:15:46<11:22:57,  3.57it/s]
 61%|██████    | 225125/371472 [7:15:46<11:25:48,  3.56it/s]
 61%|██████    | 225126/371472 [7:15:46<11:20:08,  3.59it/s]
 61%|██████    | 225127/371472 [7:15:47<12:34:49,  3.23it/s]
 61%|██████    | 225128/371472 [7:15:47<12:29:00,  3.26it/s]
 61%|██████    | 225129/371472 [7:15:47<13:00:40,  3.12it/s]
 61%|██████    | 225130/371472 [7:15:48<13:22:49,  3.04it/s]
 61%|██████    | 225131/371472 [7:15:48<12:46:02,  3.18it/s]
 61%|██████    | 225132/371472 [7:15:48<12:28:05,  3.26it/s]
 61%|██████    | 225133/371472 [7:15:49<12:11:57,  3.33it/s]
 61%|██████    | 225134/371472 [7:15:49<12:20:10,  3.30it/s]
 61%|██████    | 225135/371472 [7:15:49<12:19:22,  3.30it/s]
 61%|██████    | 225136/371472 [7:15:49<12:20:11,  3.29it/s]
 61%|██████    | 225137/371472 [7:15:50<12:24:48,  3.27it/s]
 61%|██████    | 225138/371472 [7:15:50<12:08:56,  3.35it/s]
 61%|██████    | 225139/371472 [7:15:50<11:57:54,  3.40it/s]
 61%|██████    | 225140/371472 [7:15:51<11:56:50,  3.40it/s]
                                                            
{'loss': 2.7855, 'learning_rate': 4.5472322178887717e-07, 'epoch': 9.7}
+
 61%|██████    | 225140/371472 [7:15:51<11:56:50,  3.40it/s]
 61%|██████    | 225141/371472 [7:15:51<12:31:38,  3.24it/s]
 61%|██████    | 225142/371472 [7:15:51<12:24:58,  3.27it/s]
 61%|██████    | 225143/371472 [7:15:52<12:12:14,  3.33it/s]
 61%|██████    | 225144/371472 [7:15:52<12:15:06,  3.32it/s]
 61%|██████    | 225145/371472 [7:15:52<12:02:25,  3.38it/s]
 61%|██████    | 225146/371472 [7:15:52<11:41:54,  3.47it/s]
 61%|██████    | 225147/371472 [7:15:53<11:28:28,  3.54it/s]
 61%|██████    | 225148/371472 [7:15:53<11:59:43,  3.39it/s]
 61%|██████    | 225149/371472 [7:15:53<11:40:14,  3.48it/s]
 61%|██████    | 225150/371472 [7:15:54<12:17:44,  3.31it/s]
 61%|██████    | 225151/371472 [7:15:54<11:54:19,  3.41it/s]
 61%|██████    | 225152/371472 [7:15:54<12:04:51,  3.36it/s]
 61%|██████    | 225153/371472 [7:15:54<11:52:52,  3.42it/s]
 61%|██████    | 225154/371472 [7:15:55<12:08:25,  3.35it/s]
 61%|██████    | 225155/371472 [7:15:55<12:16:40,  3.31it/s]
 61%|██████    | 225156/371472 [7:15:55<12:20:01,  3.30it/s]
 61%|██████    | 225157/371472 [7:15:56<12:00:24,  3.39it/s]
 61%|██████    | 225158/371472 [7:15:56<11:58:32,  3.39it/s]
 61%|██████    | 225159/371472 [7:15:56<11:51:34,  3.43it/s]
 61%|██████    | 225160/371472 [7:15:57<11:43:59,  3.46it/s]
                                                            
{'loss': 2.749, 'learning_rate': 4.5467473981339824e-07, 'epoch': 9.7}
+
 61%|██████    | 225160/371472 [7:15:57<11:43:59,  3.46it/s]
 61%|██████    | 225161/371472 [7:15:57<11:53:10,  3.42it/s]
 61%|██████    | 225162/371472 [7:15:57<12:01:28,  3.38it/s]
 61%|██████    | 225163/371472 [7:15:57<12:22:27,  3.28it/s]
 61%|██████    | 225164/371472 [7:15:58<12:26:58,  3.26it/s]
 61%|██████    | 225165/371472 [7:15:58<12:26:24,  3.27it/s]
 61%|██████    | 225166/371472 [7:15:58<12:26:48,  3.27it/s]
 61%|██████    | 225167/371472 [7:15:59<12:07:57,  3.35it/s]
 61%|██████    | 225168/371472 [7:15:59<12:02:53,  3.37it/s]
 61%|██████    | 225169/371472 [7:15:59<12:01:01,  3.38it/s]
 61%|██████    | 225170/371472 [7:16:00<11:49:28,  3.44it/s]
 61%|██████    | 225171/371472 [7:16:00<11:29:34,  3.54it/s]
 61%|██████    | 225172/371472 [7:16:00<11:53:40,  3.42it/s]
 61%|██████    | 225173/371472 [7:16:00<11:51:53,  3.43it/s]
 61%|██████    | 225174/371472 [7:16:01<11:48:23,  3.44it/s]
 61%|██████    | 225175/371472 [7:16:01<12:10:27,  3.34it/s]
 61%|██████    | 225176/371472 [7:16:01<11:47:47,  3.44it/s]
 61%|██████    | 225177/371472 [7:16:02<13:01:21,  3.12it/s]
 61%|██████    | 225178/371472 [7:16:02<13:18:06,  3.05it/s]
 61%|██████    | 225179/371472 [7:16:02<12:45:31,  3.19it/s]
 61%|██████    | 225180/371472 [7:16:03<12:14:21,  3.32it/s]
                                                            
{'loss': 2.5683, 'learning_rate': 4.5462625783791937e-07, 'epoch': 9.7}
+
 61%|██████    | 225180/371472 [7:16:03<12:14:21,  3.32it/s]
 61%|██████    | 225181/371472 [7:16:03<11:50:32,  3.43it/s]
 61%|██████    | 225182/371472 [7:16:03<11:36:59,  3.50it/s]
 61%|██████    | 225183/371472 [7:16:03<11:24:25,  3.56it/s]
 61%|██████    | 225184/371472 [7:16:04<11:36:21,  3.50it/s]
 61%|██████    | 225185/371472 [7:16:04<11:31:28,  3.53it/s]
 61%|██████    | 225186/371472 [7:16:04<12:14:25,  3.32it/s]
 61%|██████    | 225187/371472 [7:16:05<12:44:21,  3.19it/s]
 61%|██████    | 225188/371472 [7:16:05<12:38:11,  3.22it/s]
 61%|██████    | 225189/371472 [7:16:05<12:08:03,  3.35it/s]
 61%|██████    | 225190/371472 [7:16:05<11:40:58,  3.48it/s]
 61%|██████    | 225191/371472 [7:16:06<12:02:47,  3.37it/s]
 61%|██████    | 225192/371472 [7:16:06<11:41:34,  3.48it/s]
 61%|██████    | 225193/371472 [7:16:06<12:35:22,  3.23it/s]
 61%|██████    | 225194/371472 [7:16:07<12:46:50,  3.18it/s]
 61%|██████    | 225195/371472 [7:16:07<12:31:08,  3.25it/s]
 61%|██████    | 225196/371472 [7:16:07<12:22:14,  3.28it/s]
 61%|██████    | 225197/371472 [7:16:08<12:12:48,  3.33it/s]
 61%|██████    | 225198/371472 [7:16:08<12:05:46,  3.36it/s]
 61%|██████    | 225199/371472 [7:16:08<11:51:31,  3.43it/s]
 61%|██████    | 225200/371472 [7:16:08<11:55:30,  3.41it/s]
                                                            
{'loss': 2.6116, 'learning_rate': 4.5457777586244044e-07, 'epoch': 9.7}
+
 61%|██████    | 225200/371472 [7:16:08<11:55:30,  3.41it/s]
 61%|██████    | 225201/371472 [7:16:09<12:10:35,  3.34it/s]
 61%|██████    | 225202/371472 [7:16:09<12:16:37,  3.31it/s]
 61%|██████    | 225203/371472 [7:16:09<12:09:17,  3.34it/s]
 61%|██████    | 225204/371472 [7:16:10<11:56:03,  3.40it/s]
 61%|██████    | 225205/371472 [7:16:10<11:38:52,  3.49it/s]
 61%|██████    | 225206/371472 [7:16:10<11:37:16,  3.50it/s]
 61%|██████    | 225207/371472 [7:16:11<11:45:06,  3.46it/s]
 61%|██████    | 225208/371472 [7:16:11<11:37:01,  3.50it/s]
 61%|██████    | 225209/371472 [7:16:11<11:26:22,  3.55it/s]
 61%|██████    | 225210/371472 [7:16:11<11:50:24,  3.43it/s]
 61%|██████    | 225211/371472 [7:16:12<11:33:42,  3.51it/s]
 61%|██████    | 225212/371472 [7:16:12<11:17:37,  3.60it/s]
 61%|██████    | 225213/371472 [7:16:12<11:30:36,  3.53it/s]
 61%|██████    | 225214/371472 [7:16:12<11:29:21,  3.54it/s]
 61%|██████    | 225215/371472 [7:16:13<12:27:46,  3.26it/s]
 61%|██████    | 225216/371472 [7:16:13<12:20:54,  3.29it/s]
 61%|██████    | 225217/371472 [7:16:13<12:05:39,  3.36it/s]
 61%|██████    | 225218/371472 [7:16:14<11:57:35,  3.40it/s]
 61%|██████    | 225219/371472 [7:16:14<11:58:12,  3.39it/s]
 61%|██████    | 225220/371472 [7:16:14<11:35:37,  3.50it/s]
                                                            
{'loss': 2.7632, 'learning_rate': 4.545292938869616e-07, 'epoch': 9.7}
+
 61%|██████    | 225220/371472 [7:16:14<11:35:37,  3.50it/s]
 61%|██████    | 225221/371472 [7:16:15<11:13:09,  3.62it/s]
 61%|██████    | 225222/371472 [7:16:15<11:03:10,  3.68it/s]
 61%|██████    | 225223/371472 [7:16:15<11:34:43,  3.51it/s]
 61%|██████    | 225224/371472 [7:16:15<11:43:48,  3.46it/s]
 61%|██████    | 225225/371472 [7:16:16<11:34:13,  3.51it/s]
 61%|██████    | 225226/371472 [7:16:16<11:32:20,  3.52it/s]
 61%|██████    | 225227/371472 [7:16:16<11:23:12,  3.57it/s]
 61%|██████    | 225228/371472 [7:16:16<11:06:16,  3.66it/s]
 61%|██████    | 225229/371472 [7:16:17<11:23:38,  3.57it/s]
 61%|██████    | 225230/371472 [7:16:17<11:16:26,  3.60it/s]
 61%|██████    | 225231/371472 [7:16:17<11:13:46,  3.62it/s]
 61%|██████    | 225232/371472 [7:16:18<11:36:18,  3.50it/s]
 61%|██████    | 225233/371472 [7:16:18<11:31:57,  3.52it/s]
 61%|██████    | 225234/371472 [7:16:18<11:26:27,  3.55it/s]
 61%|██████    | 225235/371472 [7:16:19<12:26:30,  3.26it/s]
 61%|██████    | 225236/371472 [7:16:19<12:49:40,  3.17it/s]
 61%|██████    | 225237/371472 [7:16:19<13:30:57,  3.01it/s]
 61%|██████    | 225238/371472 [7:16:20<12:54:18,  3.15it/s]
 61%|██████    | 225239/371472 [7:16:20<13:18:36,  3.05it/s]
 61%|██████    | 225240/371472 [7:16:20<13:06:45,  3.10it/s]
                                                            
{'loss': 2.7693, 'learning_rate': 4.5448081191148263e-07, 'epoch': 9.7}
+
 61%|██████    | 225240/371472 [7:16:20<13:06:45,  3.10it/s]
 61%|██████    | 225241/371472 [7:16:21<13:02:04,  3.12it/s]
 61%|██████    | 225242/371472 [7:16:21<12:40:46,  3.20it/s]
 61%|██████    | 225243/371472 [7:16:21<13:17:11,  3.06it/s]
 61%|██████    | 225244/371472 [7:16:21<12:48:45,  3.17it/s]
 61%|██████    | 225245/371472 [7:16:22<12:25:56,  3.27it/s]
 61%|██████    | 225246/371472 [7:16:22<11:47:33,  3.44it/s]
 61%|██████    | 225247/371472 [7:16:22<11:39:45,  3.48it/s]
 61%|██████    | 225248/371472 [7:16:23<12:43:10,  3.19it/s]
 61%|██████    | 225249/371472 [7:16:23<12:21:24,  3.29it/s]
 61%|██████    | 225250/371472 [7:16:23<12:05:53,  3.36it/s]
 61%|██████    | 225251/371472 [7:16:24<12:21:06,  3.29it/s]
 61%|██████    | 225252/371472 [7:16:24<12:27:02,  3.26it/s]
 61%|██████    | 225253/371472 [7:16:24<12:46:08,  3.18it/s]
 61%|██████    | 225254/371472 [7:16:24<12:25:34,  3.27it/s]
 61%|██████    | 225255/371472 [7:16:25<12:38:25,  3.21it/s]
 61%|██████    | 225256/371472 [7:16:25<12:13:53,  3.32it/s]
 61%|██████    | 225257/371472 [7:16:25<11:59:30,  3.39it/s]
 61%|██████    | 225258/371472 [7:16:26<11:51:24,  3.43it/s]
 61%|██████    | 225259/371472 [7:16:26<11:34:02,  3.51it/s]
 61%|██████    | 225260/371472 [7:16:26<11:41:15,  3.47it/s]
                                                            
{'loss': 2.7074, 'learning_rate': 4.544323299360038e-07, 'epoch': 9.7}
+
 61%|██████    | 225260/371472 [7:16:26<11:41:15,  3.47it/s]
 61%|██████    | 225261/371472 [7:16:26<11:26:04,  3.55it/s]
 61%|██████    | 225262/371472 [7:16:27<11:32:34,  3.52it/s]
 61%|██████    | 225263/371472 [7:16:27<11:43:55,  3.46it/s]
 61%|██████    | 225264/371472 [7:16:27<11:48:08,  3.44it/s]
 61%|██████    | 225265/371472 [7:16:28<12:00:34,  3.38it/s]
 61%|██████    | 225266/371472 [7:16:28<12:43:14,  3.19it/s]
 61%|██████    | 225267/371472 [7:16:28<12:17:18,  3.30it/s]
 61%|██████    | 225268/371472 [7:16:29<11:47:52,  3.44it/s]
 61%|██████    | 225269/371472 [7:16:29<11:38:51,  3.49it/s]
 61%|██████    | 225270/371472 [7:16:29<12:10:19,  3.34it/s]
 61%|██████    | 225271/371472 [7:16:29<12:16:29,  3.31it/s]
 61%|██████    | 225272/371472 [7:16:30<11:58:52,  3.39it/s]
 61%|██████    | 225273/371472 [7:16:30<11:51:18,  3.43it/s]
 61%|██████    | 225274/371472 [7:16:30<11:25:46,  3.55it/s]
 61%|██████    | 225275/371472 [7:16:31<11:48:01,  3.44it/s]
 61%|██████    | 225276/371472 [7:16:31<11:48:43,  3.44it/s]
 61%|██████    | 225277/371472 [7:16:31<11:57:19,  3.40it/s]
 61%|██████    | 225278/371472 [7:16:31<11:58:56,  3.39it/s]
 61%|██████    | 225279/371472 [7:16:32<13:25:53,  3.02it/s]
 61%|██████    | 225280/371472 [7:16:32<13:01:47,  3.12it/s]
                                                            
{'loss': 2.7151, 'learning_rate': 4.543838479605249e-07, 'epoch': 9.7}
+
 61%|██████    | 225280/371472 [7:16:32<13:01:47,  3.12it/s]
 61%|██████    | 225281/371472 [7:16:33<12:42:21,  3.20it/s]
 61%|██████    | 225282/371472 [7:16:33<12:19:50,  3.29it/s]
 61%|██████    | 225283/371472 [7:16:33<12:12:19,  3.33it/s]
 61%|██████    | 225284/371472 [7:16:33<11:49:35,  3.43it/s]
 61%|██████    | 225285/371472 [7:16:34<11:50:20,  3.43it/s]
 61%|██████    | 225286/371472 [7:16:34<11:39:36,  3.48it/s]
 61%|██████    | 225287/371472 [7:16:34<11:49:05,  3.44it/s]
 61%|██████    | 225288/371472 [7:16:35<11:51:04,  3.43it/s]
 61%|██████    | 225289/371472 [7:16:35<11:49:05,  3.44it/s]
 61%|██████    | 225290/371472 [7:16:35<12:26:58,  3.26it/s]
 61%|██████    | 225291/371472 [7:16:35<12:13:50,  3.32it/s]
 61%|██████    | 225292/371472 [7:16:36<12:57:33,  3.13it/s]
 61%|██████    | 225293/371472 [7:16:36<12:43:09,  3.19it/s]
 61%|██████    | 225294/371472 [7:16:36<12:43:54,  3.19it/s]
 61%|██████    | 225295/371472 [7:16:37<12:50:20,  3.16it/s]
 61%|██████    | 225296/371472 [7:16:37<13:08:20,  3.09it/s]
 61%|██████    | 225297/371472 [7:16:37<13:14:11,  3.07it/s]
 61%|██████    | 225298/371472 [7:16:38<13:23:47,  3.03it/s]
 61%|██████    | 225299/371472 [7:16:38<13:22:32,  3.04it/s]
 61%|██████    | 225300/371472 [7:16:38<13:00:50,  3.12it/s]
                                                            
{'loss': 2.6543, 'learning_rate': 4.54335365985046e-07, 'epoch': 9.7}
+
 61%|██████    | 225300/371472 [7:16:38<13:00:50,  3.12it/s]
 61%|██████    | 225301/371472 [7:16:39<12:21:56,  3.28it/s]
 61%|██████    | 225302/371472 [7:16:39<11:56:56,  3.40it/s]
 61%|██████    | 225303/371472 [7:16:39<12:05:07,  3.36it/s]
 61%|██████    | 225304/371472 [7:16:39<11:49:11,  3.44it/s]
 61%|██████    | 225305/371472 [7:16:40<12:22:24,  3.28it/s]
 61%|██████    | 225306/371472 [7:16:40<12:13:57,  3.32it/s]
 61%|██████    | 225307/371472 [7:16:41<15:00:21,  2.71it/s]
 61%|██████    | 225308/371472 [7:16:41<14:00:46,  2.90it/s]
 61%|██████    | 225309/371472 [7:16:41<13:08:47,  3.09it/s]
 61%|██████    | 225310/371472 [7:16:42<13:20:04,  3.04it/s]
 61%|██████    | 225311/371472 [7:16:42<12:45:07,  3.18it/s]
 61%|██████    | 225312/371472 [7:16:42<12:24:18,  3.27it/s]
 61%|██████    | 225313/371472 [7:16:42<11:57:43,  3.39it/s]
 61%|██████    | 225314/371472 [7:16:43<13:05:22,  3.10it/s]
 61%|██████    | 225315/371472 [7:16:43<12:48:10,  3.17it/s]
 61%|██████    | 225316/371472 [7:16:43<13:00:29,  3.12it/s]
 61%|██████    | 225317/371472 [7:16:44<12:32:44,  3.24it/s]
 61%|██████    | 225318/371472 [7:16:44<12:39:27,  3.21it/s]
 61%|██████    | 225319/371472 [7:16:44<13:15:19,  3.06it/s]
 61%|██████    | 225320/371472 [7:16:45<13:36:11,  2.98it/s]
                                                            
{'loss': 2.9024, 'learning_rate': 4.54286884009567e-07, 'epoch': 9.7}
+
 61%|██████    | 225320/371472 [7:16:45<13:36:11,  2.98it/s]
 61%|██████    | 225321/371472 [7:16:45<12:51:29,  3.16it/s]
 61%|██████    | 225322/371472 [7:16:45<12:23:02,  3.28it/s]
 61%|██████    | 225323/371472 [7:16:46<11:58:43,  3.39it/s]
 61%|██████    | 225324/371472 [7:16:46<11:50:02,  3.43it/s]
 61%|██████    | 225325/371472 [7:16:46<12:12:35,  3.32it/s]
 61%|██████    | 225326/371472 [7:16:46<12:01:59,  3.37it/s]
 61%|██████    | 225327/371472 [7:16:47<11:40:53,  3.48it/s]
 61%|██████    | 225328/371472 [7:16:47<11:29:04,  3.53it/s]
 61%|██████    | 225329/371472 [7:16:47<11:40:21,  3.48it/s]
 61%|██████    | 225330/371472 [7:16:48<12:00:46,  3.38it/s]
 61%|██████    | 225331/371472 [7:16:48<11:34:52,  3.51it/s]
 61%|██████    | 225332/371472 [7:16:48<11:32:48,  3.52it/s]
 61%|██████    | 225333/371472 [7:16:48<11:21:42,  3.57it/s]
 61%|██████    | 225334/371472 [7:16:49<11:04:37,  3.66it/s]
 61%|██████    | 225335/371472 [7:16:49<11:10:52,  3.63it/s]
 61%|██████    | 225336/371472 [7:16:49<11:15:21,  3.61it/s]
 61%|██████    | 225337/371472 [7:16:50<11:24:36,  3.56it/s]
 61%|██████    | 225338/371472 [7:16:50<11:39:21,  3.48it/s]
 61%|██████    | 225339/371472 [7:16:50<11:27:22,  3.54it/s]
 61%|██████    | 225340/371472 [7:16:50<11:12:17,  3.62it/s]
                                                            
{'loss': 2.8344, 'learning_rate': 4.5423840203408826e-07, 'epoch': 9.71}
+
 61%|██████    | 225340/371472 [7:16:50<11:12:17,  3.62it/s]
 61%|██████    | 225341/371472 [7:16:51<11:19:50,  3.58it/s]
 61%|██████    | 225342/371472 [7:16:51<11:27:27,  3.54it/s]
 61%|██████    | 225343/371472 [7:16:51<12:01:45,  3.37it/s]
 61%|██████    | 225344/371472 [7:16:52<12:08:43,  3.34it/s]
 61%|██████    | 225345/371472 [7:16:52<11:52:01,  3.42it/s]
 61%|██████    | 225346/371472 [7:16:52<11:30:23,  3.53it/s]
 61%|██████    | 225347/371472 [7:16:52<11:33:41,  3.51it/s]
 61%|██████    | 225348/371472 [7:16:53<12:19:49,  3.29it/s]
 61%|██████    | 225349/371472 [7:16:53<12:06:33,  3.35it/s]
 61%|██████    | 225350/371472 [7:16:53<12:26:50,  3.26it/s]
 61%|██████    | 225351/371472 [7:16:54<12:06:11,  3.35it/s]
 61%|██████    | 225352/371472 [7:16:54<12:21:25,  3.28it/s]
 61%|██████    | 225353/371472 [7:16:54<11:54:12,  3.41it/s]
 61%|██████    | 225354/371472 [7:16:55<11:55:18,  3.40it/s]
 61%|██████    | 225355/371472 [7:16:55<11:58:29,  3.39it/s]
 61%|██████    | 225356/371472 [7:16:55<11:38:51,  3.48it/s]
 61%|██████    | 225357/371472 [7:16:55<11:25:29,  3.55it/s]
 61%|██████    | 225358/371472 [7:16:56<11:25:10,  3.55it/s]
 61%|██████    | 225359/371472 [7:16:56<11:10:44,  3.63it/s]
 61%|██████    | 225360/371472 [7:16:56<11:41:05,  3.47it/s]
                                                            
{'loss': 2.8408, 'learning_rate': 4.541899200586093e-07, 'epoch': 9.71}
+
 61%|██████    | 225360/371472 [7:16:56<11:41:05,  3.47it/s]
 61%|██████    | 225361/371472 [7:16:56<11:30:28,  3.53it/s]
 61%|██████    | 225362/371472 [7:16:57<11:20:54,  3.58it/s]
 61%|██████    | 225363/371472 [7:16:57<12:00:56,  3.38it/s]
 61%|██████    | 225364/371472 [7:16:57<12:06:27,  3.35it/s]
 61%|██████    | 225365/371472 [7:16:58<12:09:04,  3.34it/s]
 61%|██████    | 225366/371472 [7:16:58<12:20:20,  3.29it/s]
 61%|██████    | 225367/371472 [7:16:58<12:57:16,  3.13it/s]
 61%|██████    | 225368/371472 [7:16:59<12:12:22,  3.32it/s]
 61%|██████    | 225369/371472 [7:16:59<12:25:09,  3.27it/s]
 61%|██████    | 225370/371472 [7:16:59<11:58:17,  3.39it/s]
 61%|██████    | 225371/371472 [7:16:59<11:46:06,  3.45it/s]
 61%|██████    | 225372/371472 [7:17:00<11:50:59,  3.42it/s]
 61%|██████    | 225373/371472 [7:17:00<11:47:12,  3.44it/s]
 61%|██████    | 225374/371472 [7:17:00<11:55:07,  3.40it/s]
 61%|██████    | 225375/371472 [7:17:01<11:54:31,  3.41it/s]
 61%|██████    | 225376/371472 [7:17:01<12:06:29,  3.35it/s]
 61%|██████    | 225377/371472 [7:17:01<12:32:26,  3.24it/s]
 61%|██████    | 225378/371472 [7:17:02<13:47:09,  2.94it/s]
 61%|██████    | 225379/371472 [7:17:02<13:19:33,  3.05it/s]
 61%|██████    | 225380/371472 [7:17:02<12:47:27,  3.17it/s]
                                                            
{'loss': 2.6425, 'learning_rate': 4.5414143808313035e-07, 'epoch': 9.71}
+
 61%|██████    | 225380/371472 [7:17:02<12:47:27,  3.17it/s]
 61%|██████    | 225381/371472 [7:17:03<12:26:24,  3.26it/s]
 61%|██████    | 225382/371472 [7:17:03<12:10:51,  3.33it/s]
 61%|██████    | 225383/371472 [7:17:03<12:02:43,  3.37it/s]
 61%|██████    | 225384/371472 [7:17:03<12:10:07,  3.33it/s]
 61%|██████    | 225385/371472 [7:17:04<11:49:43,  3.43it/s]
 61%|██████    | 225386/371472 [7:17:04<11:45:49,  3.45it/s]
 61%|██████    | 225387/371472 [7:17:04<11:37:38,  3.49it/s]
 61%|██████    | 225388/371472 [7:17:05<11:33:51,  3.51it/s]
 61%|██████    | 225389/371472 [7:17:05<12:02:05,  3.37it/s]
 61%|██████    | 225390/371472 [7:17:05<11:57:12,  3.39it/s]
 61%|██████    | 225391/371472 [7:17:05<12:02:23,  3.37it/s]
 61%|██████    | 225392/371472 [7:17:06<11:59:19,  3.38it/s]
 61%|██████    | 225393/371472 [7:17:06<11:46:39,  3.45it/s]
 61%|██████    | 225394/371472 [7:17:06<11:42:21,  3.47it/s]
 61%|██████    | 225395/371472 [7:17:07<11:43:23,  3.46it/s]
 61%|██████    | 225396/371472 [7:17:07<11:37:16,  3.49it/s]
 61%|██████    | 225397/371472 [7:17:07<11:24:47,  3.56it/s]
 61%|██████    | 225398/371472 [7:17:07<11:40:19,  3.48it/s]
 61%|██████    | 225399/371472 [7:17:08<11:55:41,  3.40it/s]
 61%|██████    | 225400/371472 [7:17:08<12:04:09,  3.36it/s]
                                                            
{'loss': 2.8614, 'learning_rate': 4.540929561076515e-07, 'epoch': 9.71}
+
 61%|██████    | 225400/371472 [7:17:08<12:04:09,  3.36it/s]
 61%|██████    | 225401/371472 [7:17:08<12:15:57,  3.31it/s]
 61%|██████    | 225402/371472 [7:17:09<12:17:40,  3.30it/s]
 61%|██████    | 225403/371472 [7:17:09<12:30:03,  3.25it/s]
 61%|██████    | 225404/371472 [7:17:09<12:23:54,  3.27it/s]
 61%|██████    | 225405/371472 [7:17:10<12:09:21,  3.34it/s]
 61%|██████    | 225406/371472 [7:17:10<12:46:39,  3.18it/s]
 61%|██████    | 225407/371472 [7:17:10<12:27:52,  3.26it/s]
 61%|██████    | 225408/371472 [7:17:11<12:27:57,  3.25it/s]
 61%|██████    | 225409/371472 [7:17:11<13:32:59,  2.99it/s]
 61%|██████    | 225410/371472 [7:17:11<13:25:51,  3.02it/s]
 61%|██████    | 225411/371472 [7:17:12<14:18:16,  2.84it/s]
 61%|██████    | 225412/371472 [7:17:12<13:45:33,  2.95it/s]
 61%|██████    | 225413/371472 [7:17:12<13:07:37,  3.09it/s]
 61%|██████    | 225414/371472 [7:17:13<12:44:39,  3.18it/s]
 61%|██████    | 225415/371472 [7:17:13<13:04:31,  3.10it/s]
 61%|██████    | 225416/371472 [7:17:13<12:39:13,  3.21it/s]
 61%|██████    | 225417/371472 [7:17:14<12:21:41,  3.28it/s]
 61%|██████    | 225418/371472 [7:17:14<12:53:52,  3.15it/s]
 61%|██████    | 225419/371472 [7:17:14<12:52:30,  3.15it/s]
 61%|██████    | 225420/371472 [7:17:14<12:56:18,  3.14it/s]
                                                            
{'loss': 2.6933, 'learning_rate': 4.540444741321726e-07, 'epoch': 9.71}
+
 61%|██████    | 225420/371472 [7:17:14<12:56:18,  3.14it/s]
 61%|██████    | 225421/371472 [7:17:15<12:39:06,  3.21it/s]
 61%|██████    | 225422/371472 [7:17:15<12:18:33,  3.30it/s]
 61%|██████    | 225423/371472 [7:17:15<12:00:44,  3.38it/s]
 61%|██████    | 225424/371472 [7:17:16<11:52:43,  3.42it/s]
 61%|██████    | 225425/371472 [7:17:16<11:45:12,  3.45it/s]
 61%|██████    | 225426/371472 [7:17:16<11:45:45,  3.45it/s]
 61%|██████    | 225427/371472 [7:17:16<11:38:23,  3.49it/s]
 61%|██████    | 225428/371472 [7:17:17<11:32:38,  3.51it/s]
 61%|██████    | 225429/371472 [7:17:17<11:31:49,  3.52it/s]
 61%|██████    | 225430/371472 [7:17:17<11:40:00,  3.48it/s]
 61%|██████    | 225431/371472 [7:17:18<12:02:57,  3.37it/s]
 61%|██████    | 225432/371472 [7:17:18<12:02:40,  3.37it/s]
 61%|██████    | 225433/371472 [7:17:18<11:45:43,  3.45it/s]
 61%|██████    | 225434/371472 [7:17:19<11:34:15,  3.51it/s]
 61%|██████    | 225435/371472 [7:17:19<11:46:04,  3.45it/s]
 61%|██████    | 225436/371472 [7:17:19<11:45:16,  3.45it/s]
 61%|██████    | 225437/371472 [7:17:19<11:16:44,  3.60it/s]
 61%|██████    | 225438/371472 [7:17:20<11:18:26,  3.59it/s]
 61%|██████    | 225439/371472 [7:17:20<11:11:48,  3.62it/s]
 61%|██████    | 225440/371472 [7:17:20<11:29:47,  3.53it/s]
                                                            
{'loss': 2.6296, 'learning_rate': 4.539959921566937e-07, 'epoch': 9.71}
+
 61%|██████    | 225440/371472 [7:17:20<11:29:47,  3.53it/s]
 61%|██████    | 225441/371472 [7:17:20<11:21:02,  3.57it/s]
 61%|██████    | 225442/371472 [7:17:21<11:23:40,  3.56it/s]
 61%|██████    | 225443/371472 [7:17:21<11:15:41,  3.60it/s]
 61%|██████    | 225444/371472 [7:17:21<11:12:59,  3.62it/s]
 61%|██████    | 225445/371472 [7:17:22<11:05:41,  3.66it/s]
 61%|██████    | 225446/371472 [7:17:22<11:58:09,  3.39it/s]
 61%|██████    | 225447/371472 [7:17:22<12:33:49,  3.23it/s]
 61%|██████    | 225448/371472 [7:17:23<12:20:09,  3.29it/s]
 61%|██████    | 225449/371472 [7:17:23<12:08:17,  3.34it/s]
 61%|██████    | 225450/371472 [7:17:23<13:29:08,  3.01it/s]
 61%|██████    | 225451/371472 [7:17:24<12:45:32,  3.18it/s]
 61%|██████    | 225452/371472 [7:17:24<12:55:11,  3.14it/s]
 61%|██████    | 225453/371472 [7:17:24<12:24:26,  3.27it/s]
 61%|██████    | 225454/371472 [7:17:24<11:53:29,  3.41it/s]
 61%|██████    | 225455/371472 [7:17:25<12:33:06,  3.23it/s]
 61%|██████    | 225456/371472 [7:17:25<12:30:13,  3.24it/s]
 61%|██████    | 225457/371472 [7:17:25<12:09:22,  3.34it/s]
 61%|██████    | 225458/371472 [7:17:26<13:12:30,  3.07it/s]
 61%|██████    | 225459/371472 [7:17:26<13:40:57,  2.96it/s]
 61%|██████    | 225460/371472 [7:17:26<12:55:16,  3.14it/s]
                                                            
{'loss': 2.6936, 'learning_rate': 4.539475101812148e-07, 'epoch': 9.71}
+
 61%|██████    | 225460/371472 [7:17:26<12:55:16,  3.14it/s]
 61%|██████    | 225461/371472 [7:17:27<12:32:05,  3.24it/s]
 61%|██████    | 225462/371472 [7:17:27<12:41:08,  3.20it/s]
 61%|██████    | 225463/371472 [7:17:27<12:17:49,  3.30it/s]
 61%|██████    | 225464/371472 [7:17:28<12:38:46,  3.21it/s]
 61%|██████    | 225465/371472 [7:17:28<12:26:00,  3.26it/s]
 61%|██████    | 225466/371472 [7:17:28<12:39:18,  3.20it/s]
 61%|██████    | 225467/371472 [7:17:28<12:19:05,  3.29it/s]
 61%|██████    | 225468/371472 [7:17:29<12:00:18,  3.38it/s]
 61%|██████    | 225469/371472 [7:17:29<11:51:56,  3.42it/s]
 61%|██████    | 225470/371472 [7:17:29<12:17:20,  3.30it/s]
 61%|██████    | 225471/371472 [7:17:30<12:18:08,  3.30it/s]
 61%|██████    | 225472/371472 [7:17:30<12:34:30,  3.23it/s]
 61%|██████    | 225473/371472 [7:17:30<12:09:40,  3.33it/s]
 61%|██████    | 225474/371472 [7:17:31<12:38:40,  3.21it/s]
 61%|██████    | 225475/371472 [7:17:31<12:41:13,  3.20it/s]
 61%|██████    | 225476/371472 [7:17:31<12:18:12,  3.30it/s]
 61%|██████    | 225477/371472 [7:17:32<12:19:46,  3.29it/s]
 61%|██████    | 225478/371472 [7:17:32<12:17:14,  3.30it/s]
 61%|██████    | 225479/371472 [7:17:32<12:28:26,  3.25it/s]
 61%|██████    | 225480/371472 [7:17:32<12:10:37,  3.33it/s]
                                                            
{'loss': 2.6641, 'learning_rate': 4.5389902820573597e-07, 'epoch': 9.71}
+
 61%|██████    | 225480/371472 [7:17:32<12:10:37,  3.33it/s]
 61%|██████    | 225481/371472 [7:17:33<11:49:22,  3.43it/s]
 61%|██████    | 225482/371472 [7:17:33<11:41:07,  3.47it/s]
 61%|██████    | 225483/371472 [7:17:33<11:51:25,  3.42it/s]
 61%|██████    | 225484/371472 [7:17:34<12:31:59,  3.24it/s]
 61%|██████    | 225485/371472 [7:17:34<12:35:26,  3.22it/s]
 61%|██████    | 225486/371472 [7:17:34<12:32:34,  3.23it/s]
 61%|██████    | 225487/371472 [7:17:35<12:59:31,  3.12it/s]
 61%|██████    | 225488/371472 [7:17:35<12:33:21,  3.23it/s]
 61%|██████    | 225489/371472 [7:17:35<12:07:06,  3.35it/s]
 61%|██████    | 225490/371472 [7:17:35<12:54:07,  3.14it/s]
 61%|██████    | 225491/371472 [7:17:36<12:34:52,  3.22it/s]
 61%|██████    | 225492/371472 [7:17:36<12:47:22,  3.17it/s]
 61%|██████    | 225493/371472 [7:17:36<12:07:31,  3.34it/s]
 61%|██████    | 225494/371472 [7:17:37<12:46:01,  3.18it/s]
 61%|██████    | 225495/371472 [7:17:37<12:23:51,  3.27it/s]
 61%|██████    | 225496/371472 [7:17:37<12:35:19,  3.22it/s]
 61%|██████    | 225497/371472 [7:17:38<13:54:44,  2.91it/s]
 61%|██████    | 225498/371472 [7:17:38<13:07:15,  3.09it/s]
 61%|██████    | 225499/371472 [7:17:38<12:56:52,  3.13it/s]
 61%|██████    | 225500/371472 [7:17:39<13:04:30,  3.10it/s]
                                                            
{'loss': 2.8102, 'learning_rate': 4.53850546230257e-07, 'epoch': 9.71}
+
 61%|██████    | 225500/371472 [7:17:39<13:04:30,  3.10it/s]
 61%|██████    | 225501/371472 [7:17:39<12:29:49,  3.24it/s]
 61%|██████    | 225502/371472 [7:17:39<12:41:46,  3.19it/s]
 61%|██████    | 225503/371472 [7:17:40<13:01:54,  3.11it/s]
 61%|██████    | 225504/371472 [7:17:40<12:26:26,  3.26it/s]
 61%|██████    | 225505/371472 [7:17:40<12:00:22,  3.38it/s]
 61%|██████    | 225506/371472 [7:17:40<11:54:15,  3.41it/s]
 61%|██████    | 225507/371472 [7:17:41<12:24:13,  3.27it/s]
 61%|██████    | 225508/371472 [7:17:41<12:14:36,  3.31it/s]
 61%|██████    | 225509/371472 [7:17:41<11:45:42,  3.45it/s]
 61%|██████    | 225510/371472 [7:17:42<11:49:20,  3.43it/s]
 61%|██████    | 225511/371472 [7:17:42<12:16:21,  3.30it/s]
 61%|██████    | 225512/371472 [7:17:42<12:30:09,  3.24it/s]
 61%|██████    | 225513/371472 [7:17:43<12:19:16,  3.29it/s]
 61%|██████    | 225514/371472 [7:17:43<12:06:52,  3.35it/s]
 61%|██████    | 225515/371472 [7:17:43<11:59:56,  3.38it/s]
 61%|██████    | 225516/371472 [7:17:43<12:08:17,  3.34it/s]
 61%|██████    | 225517/371472 [7:17:44<12:50:30,  3.16it/s]
 61%|██████    | 225518/371472 [7:17:44<12:56:38,  3.13it/s]
 61%|██████    | 225519/371472 [7:17:44<12:44:23,  3.18it/s]
 61%|██████    | 225520/371472 [7:17:45<12:47:34,  3.17it/s]
                                                            
{'loss': 2.7152, 'learning_rate': 4.5380206425477816e-07, 'epoch': 9.71}
+
 61%|██████    | 225520/371472 [7:17:45<12:47:34,  3.17it/s]
 61%|██████    | 225521/371472 [7:17:45<12:37:59,  3.21it/s]
 61%|██████    | 225522/371472 [7:17:45<12:33:00,  3.23it/s]
 61%|██████    | 225523/371472 [7:17:46<12:28:15,  3.25it/s]
 61%|██████    | 225524/371472 [7:17:46<12:20:29,  3.28it/s]
 61%|██████    | 225525/371472 [7:17:46<12:04:25,  3.36it/s]
 61%|██████    | 225526/371472 [7:17:47<11:43:36,  3.46it/s]
 61%|██████    | 225527/371472 [7:17:47<12:09:56,  3.33it/s]
 61%|██████    | 225528/371472 [7:17:47<11:59:48,  3.38it/s]
 61%|██████    | 225529/371472 [7:17:47<11:41:14,  3.47it/s]
 61%|██████    | 225530/371472 [7:17:48<13:30:56,  3.00it/s]
 61%|██████    | 225531/371472 [7:17:48<12:49:14,  3.16it/s]
 61%|██████    | 225532/371472 [7:17:48<12:23:27,  3.27it/s]
 61%|██████    | 225533/371472 [7:17:49<12:37:40,  3.21it/s]
 61%|██████    | 225534/371472 [7:17:49<12:36:35,  3.21it/s]
 61%|██████    | 225535/371472 [7:17:49<12:41:57,  3.19it/s]
 61%|██████    | 225536/371472 [7:17:50<12:38:29,  3.21it/s]
 61%|██████    | 225537/371472 [7:17:50<12:31:35,  3.24it/s]
 61%|██████    | 225538/371472 [7:17:50<14:00:32,  2.89it/s]
 61%|██████    | 225539/371472 [7:17:51<13:14:13,  3.06it/s]
 61%|██████    | 225540/371472 [7:17:51<12:47:45,  3.17it/s]
                                                            
{'loss': 2.6994, 'learning_rate': 4.5375358227929923e-07, 'epoch': 9.71}
+
 61%|██████    | 225540/371472 [7:17:51<12:47:45,  3.17it/s]
 61%|██████    | 225541/371472 [7:17:51<12:22:40,  3.27it/s]
 61%|██████    | 225542/371472 [7:17:52<12:07:02,  3.35it/s]
 61%|██████    | 225543/371472 [7:17:52<11:59:36,  3.38it/s]
 61%|██████    | 225544/371472 [7:17:52<11:53:34,  3.41it/s]
 61%|██████    | 225545/371472 [7:17:52<12:27:29,  3.25it/s]
 61%|██████    | 225546/371472 [7:17:53<12:08:58,  3.34it/s]
 61%|██████    | 225547/371472 [7:17:53<11:50:17,  3.42it/s]
 61%|██████    | 225548/371472 [7:17:53<11:34:48,  3.50it/s]
 61%|██████    | 225549/371472 [7:17:54<11:39:20,  3.48it/s]
 61%|██████    | 225550/371472 [7:17:54<11:33:45,  3.51it/s]
 61%|██████    | 225551/371472 [7:17:54<11:37:24,  3.49it/s]
 61%|██████    | 225552/371472 [7:17:54<11:43:22,  3.46it/s]
 61%|██████    | 225553/371472 [7:17:55<11:35:38,  3.50it/s]
 61%|██████    | 225554/371472 [7:17:55<11:35:19,  3.50it/s]
 61%|██████    | 225555/371472 [7:17:55<12:01:47,  3.37it/s]
 61%|██████    | 225556/371472 [7:17:56<12:19:29,  3.29it/s]
 61%|██████    | 225557/371472 [7:17:56<12:01:51,  3.37it/s]
 61%|██████    | 225558/371472 [7:17:56<12:23:07,  3.27it/s]
 61%|██████    | 225559/371472 [7:17:57<12:00:52,  3.37it/s]
 61%|██████    | 225560/371472 [7:17:57<12:04:43,  3.36it/s]
                                                            
{'loss': 2.8739, 'learning_rate': 4.5370510030382036e-07, 'epoch': 9.72}
+
 61%|██████    | 225560/371472 [7:17:57<12:04:43,  3.36it/s]
 61%|██████    | 225561/371472 [7:17:57<11:55:26,  3.40it/s]
 61%|██████    | 225562/371472 [7:17:57<12:02:32,  3.37it/s]
 61%|██████    | 225563/371472 [7:17:58<13:13:18,  3.07it/s]
 61%|██████    | 225564/371472 [7:17:58<12:35:37,  3.22it/s]
 61%|██████    | 225565/371472 [7:17:58<13:16:44,  3.05it/s]
 61%|██████    | 225566/371472 [7:17:59<12:59:42,  3.12it/s]
 61%|██████    | 225567/371472 [7:17:59<12:29:46,  3.24it/s]
 61%|██████    | 225568/371472 [7:17:59<12:21:12,  3.28it/s]
 61%|██████    | 225569/371472 [7:18:00<12:13:53,  3.31it/s]
 61%|██████    | 225570/371472 [7:18:00<12:05:59,  3.35it/s]
 61%|██████    | 225571/371472 [7:18:00<12:50:30,  3.16it/s]
 61%|██████    | 225572/371472 [7:18:01<12:49:55,  3.16it/s]
 61%|██████    | 225573/371472 [7:18:01<12:27:08,  3.25it/s]
 61%|██████    | 225574/371472 [7:18:01<12:22:44,  3.27it/s]
 61%|██████    | 225575/371472 [7:18:02<13:44:02,  2.95it/s]
 61%|██████    | 225576/371472 [7:18:02<13:01:10,  3.11it/s]
 61%|██████    | 225577/371472 [7:18:02<12:43:07,  3.19it/s]
 61%|██████    | 225578/371472 [7:18:02<12:37:12,  3.21it/s]
 61%|██████    | 225579/371472 [7:18:03<12:25:07,  3.26it/s]
 61%|██████    | 225580/371472 [7:18:03<12:17:15,  3.30it/s]
                                                            
{'loss': 2.8303, 'learning_rate': 4.5365661832834143e-07, 'epoch': 9.72}
+
 61%|██████    | 225580/371472 [7:18:03<12:17:15,  3.30it/s]
 61%|██████    | 225581/371472 [7:18:03<12:28:03,  3.25it/s]
 61%|██████    | 225582/371472 [7:18:04<12:09:55,  3.33it/s]
 61%|██████    | 225583/371472 [7:18:04<11:51:30,  3.42it/s]
 61%|██████    | 225584/371472 [7:18:04<11:55:49,  3.40it/s]
 61%|██████    | 225585/371472 [7:18:05<11:49:29,  3.43it/s]
 61%|██████    | 225586/371472 [7:18:05<13:26:30,  3.01it/s]
 61%|██████    | 225587/371472 [7:18:05<12:43:53,  3.18it/s]
 61%|██████    | 225588/371472 [7:18:06<13:09:04,  3.08it/s]
 61%|██████    | 225589/371472 [7:18:06<13:27:31,  3.01it/s]
 61%|██████    | 225590/371472 [7:18:06<12:50:02,  3.16it/s]
 61%|██████    | 225591/371472 [7:18:06<12:36:55,  3.21it/s]
 61%|██████    | 225592/371472 [7:18:07<12:14:20,  3.31it/s]
 61%|██████    | 225593/371472 [7:18:07<12:58:50,  3.12it/s]
 61%|██████    | 225594/371472 [7:18:07<13:03:13,  3.10it/s]
 61%|██████    | 225595/371472 [7:18:08<12:39:52,  3.20it/s]
 61%|██████    | 225596/371472 [7:18:08<12:12:59,  3.32it/s]
 61%|██████    | 225597/371472 [7:18:08<12:25:38,  3.26it/s]
 61%|██████    | 225598/371472 [7:18:09<12:09:55,  3.33it/s]
 61%|██████    | 225599/371472 [7:18:09<11:54:57,  3.40it/s]
 61%|██████    | 225600/371472 [7:18:09<11:42:21,  3.46it/s]
                                                            
{'loss': 2.7013, 'learning_rate': 4.536081363528626e-07, 'epoch': 9.72}
+
 61%|██████    | 225600/371472 [7:18:09<11:42:21,  3.46it/s]
 61%|██████    | 225601/371472 [7:18:09<11:49:42,  3.43it/s]
 61%|██████    | 225602/371472 [7:18:10<12:35:38,  3.22it/s]
 61%|██████    | 225603/371472 [7:18:10<12:16:07,  3.30it/s]
 61%|██████    | 225604/371472 [7:18:10<12:09:42,  3.33it/s]
 61%|██████    | 225605/371472 [7:18:11<12:34:56,  3.22it/s]
 61%|██████    | 225606/371472 [7:18:11<12:34:43,  3.22it/s]
 61%|██████    | 225607/371472 [7:18:11<12:29:34,  3.24it/s]
 61%|██████    | 225608/371472 [7:18:12<12:04:34,  3.36it/s]
 61%|██████    | 225609/371472 [7:18:12<12:11:54,  3.32it/s]
 61%|██████    | 225610/371472 [7:18:12<12:36:49,  3.21it/s]
 61%|██████    | 225611/371472 [7:18:13<12:10:37,  3.33it/s]
 61%|██████    | 225612/371472 [7:18:13<12:49:30,  3.16it/s]
 61%|██████    | 225613/371472 [7:18:13<12:44:29,  3.18it/s]
 61%|██████    | 225614/371472 [7:18:14<12:27:36,  3.25it/s]
 61%|██████    | 225615/371472 [7:18:14<12:30:48,  3.24it/s]
 61%|██████    | 225616/371472 [7:18:14<12:42:45,  3.19it/s]
 61%|██████    | 225617/371472 [7:18:14<12:34:15,  3.22it/s]
 61%|██████    | 225618/371472 [7:18:15<12:20:54,  3.28it/s]
 61%|██████    | 225619/371472 [7:18:15<12:03:34,  3.36it/s]
 61%|██████    | 225620/371472 [7:18:15<12:36:46,  3.21it/s]
                                                            
{'loss': 2.8658, 'learning_rate': 4.5355965437738363e-07, 'epoch': 9.72}
+
 61%|██████    | 225620/371472 [7:18:15<12:36:46,  3.21it/s]
 61%|██████    | 225621/371472 [7:18:16<12:16:27,  3.30it/s]
 61%|██████    | 225622/371472 [7:18:16<12:01:34,  3.37it/s]
 61%|██████    | 225623/371472 [7:18:16<12:11:23,  3.32it/s]
 61%|██████    | 225624/371472 [7:18:17<12:14:30,  3.31it/s]
 61%|██████    | 225625/371472 [7:18:17<12:28:32,  3.25it/s]
 61%|██████    | 225626/371472 [7:18:17<12:30:11,  3.24it/s]
 61%|██████    | 225627/371472 [7:18:18<13:23:44,  3.02it/s]
 61%|██████    | 225628/371472 [7:18:18<12:55:49,  3.13it/s]
 61%|██████    | 225629/371472 [7:18:18<12:57:58,  3.12it/s]
 61%|██████    | 225630/371472 [7:18:19<13:22:35,  3.03it/s]
 61%|██████    | 225631/371472 [7:18:19<12:56:35,  3.13it/s]
 61%|██████    | 225632/371472 [7:18:19<12:39:06,  3.20it/s]
 61%|██████    | 225633/371472 [7:18:19<12:31:43,  3.23it/s]
 61%|██████    | 225634/371472 [7:18:20<12:15:32,  3.30it/s]
 61%|██████    | 225635/371472 [7:18:20<11:55:05,  3.40it/s]
 61%|██████    | 225636/371472 [7:18:20<12:00:13,  3.37it/s]
 61%|██████    | 225637/371472 [7:18:21<11:51:37,  3.42it/s]
 61%|██████    | 225638/371472 [7:18:21<12:01:52,  3.37it/s]
 61%|██████    | 225639/371472 [7:18:21<12:01:02,  3.37it/s]
 61%|██████    | 225640/371472 [7:18:21<11:45:26,  3.45it/s]
                                                            
{'loss': 2.8617, 'learning_rate': 4.535111724019048e-07, 'epoch': 9.72}
+
 61%|██████    | 225640/371472 [7:18:21<11:45:26,  3.45it/s]
 61%|██████    | 225641/371472 [7:18:22<11:42:01,  3.46it/s]
 61%|██████    | 225642/371472 [7:18:22<12:37:21,  3.21it/s]
 61%|██████    | 225643/371472 [7:18:22<12:54:12,  3.14it/s]
 61%|██████    | 225644/371472 [7:18:23<12:32:26,  3.23it/s]
 61%|██████    | 225645/371472 [7:18:23<12:12:47,  3.32it/s]
 61%|██████    | 225646/371472 [7:18:23<12:11:27,  3.32it/s]
 61%|██████    | 225647/371472 [7:18:24<12:09:30,  3.33it/s]
 61%|██████    | 225648/371472 [7:18:24<12:02:32,  3.36it/s]
 61%|██████    | 225649/371472 [7:18:24<11:46:29,  3.44it/s]
 61%|██████    | 225650/371472 [7:18:24<11:41:02,  3.47it/s]
 61%|██████    | 225651/371472 [7:18:25<11:31:11,  3.52it/s]
 61%|██████    | 225652/371472 [7:18:25<11:40:31,  3.47it/s]
 61%|██████    | 225653/371472 [7:18:25<12:28:13,  3.25it/s]
 61%|██████    | 225654/371472 [7:18:26<12:16:29,  3.30it/s]
 61%|██████    | 225655/371472 [7:18:26<12:18:17,  3.29it/s]
 61%|██████    | 225656/371472 [7:18:26<12:28:00,  3.25it/s]
 61%|██████    | 225657/371472 [7:18:27<12:29:12,  3.24it/s]
 61%|██████    | 225658/371472 [7:18:27<12:28:22,  3.25it/s]
 61%|██████    | 225659/371472 [7:18:27<12:12:18,  3.32it/s]
 61%|██████    | 225660/371472 [7:18:28<12:30:50,  3.24it/s]
                                                            
{'loss': 2.7165, 'learning_rate': 4.534626904264259e-07, 'epoch': 9.72}
+
 61%|██████    | 225660/371472 [7:18:28<12:30:50,  3.24it/s]
 61%|██████    | 225661/371472 [7:18:28<12:28:46,  3.25it/s]
 61%|██████    | 225662/371472 [7:18:28<12:08:14,  3.34it/s]
 61%|██████    | 225663/371472 [7:18:28<12:01:14,  3.37it/s]
 61%|██████    | 225664/371472 [7:18:29<11:48:46,  3.43it/s]
 61%|██████    | 225665/371472 [7:18:29<11:32:37,  3.51it/s]
 61%|██████    | 225666/371472 [7:18:29<12:01:21,  3.37it/s]
 61%|██████    | 225667/371472 [7:18:30<12:04:18,  3.36it/s]
 61%|██████    | 225668/371472 [7:18:30<11:53:19,  3.41it/s]
 61%|██████    | 225669/371472 [7:18:30<11:44:26,  3.45it/s]
 61%|██████    | 225670/371472 [7:18:30<11:59:13,  3.38it/s]
 61%|██████    | 225671/371472 [7:18:31<11:38:40,  3.48it/s]
 61%|██████    | 225672/371472 [7:18:31<11:27:49,  3.53it/s]
 61%|██████    | 225673/371472 [7:18:31<11:49:50,  3.42it/s]
 61%|██████    | 225674/371472 [7:18:32<11:35:06,  3.50it/s]
 61%|██████    | 225675/371472 [7:18:32<11:29:04,  3.53it/s]
 61%|██████    | 225676/371472 [7:18:32<11:27:52,  3.53it/s]
 61%|██████    | 225677/371472 [7:18:32<11:19:30,  3.58it/s]
 61%|██████    | 225678/371472 [7:18:33<11:52:09,  3.41it/s]
 61%|██████    | 225679/371472 [7:18:33<12:02:45,  3.36it/s]
 61%|██████    | 225680/371472 [7:18:33<12:02:56,  3.36it/s]
                                                            
{'loss': 2.6301, 'learning_rate': 4.53414208450947e-07, 'epoch': 9.72}
+
 61%|██████    | 225680/371472 [7:18:33<12:02:56,  3.36it/s]
 61%|██████    | 225681/371472 [7:18:34<11:42:51,  3.46it/s]
 61%|██████    | 225682/371472 [7:18:34<12:03:53,  3.36it/s]
 61%|██████    | 225683/371472 [7:18:34<11:56:48,  3.39it/s]
 61%|██████    | 225684/371472 [7:18:35<11:48:54,  3.43it/s]
 61%|██████    | 225685/371472 [7:18:35<12:43:23,  3.18it/s]
 61%|██████    | 225686/371472 [7:18:35<12:40:18,  3.20it/s]
 61%|██████    | 225687/371472 [7:18:35<12:21:32,  3.28it/s]
 61%|██████    | 225688/371472 [7:18:36<12:10:42,  3.33it/s]
 61%|██████    | 225689/371472 [7:18:36<12:04:16,  3.35it/s]
 61%|██████    | 225690/371472 [7:18:36<11:57:40,  3.39it/s]
 61%|██████    | 225691/371472 [7:18:37<11:42:23,  3.46it/s]
 61%|██████    | 225692/371472 [7:18:37<11:52:58,  3.41it/s]
 61%|██████    | 225693/371472 [7:18:37<11:59:37,  3.38it/s]
 61%|██████    | 225694/371472 [7:18:38<12:18:27,  3.29it/s]
 61%|██████    | 225695/371472 [7:18:38<12:16:21,  3.30it/s]
 61%|██████    | 225696/371472 [7:18:38<12:03:15,  3.36it/s]
 61%|██████    | 225697/371472 [7:18:38<11:56:42,  3.39it/s]
 61%|██████    | 225698/371472 [7:18:39<11:33:45,  3.50it/s]
 61%|██████    | 225699/371472 [7:18:39<13:07:22,  3.09it/s]
 61%|██████    | 225700/371472 [7:18:39<12:26:18,  3.26it/s]
                                                            
{'loss': 2.8198, 'learning_rate': 4.5336572647546807e-07, 'epoch': 9.72}
+
 61%|██████    | 225700/371472 [7:18:39<12:26:18,  3.26it/s]
 61%|██████    | 225701/371472 [7:18:40<12:34:18,  3.22it/s]
 61%|██████    | 225702/371472 [7:18:40<12:16:28,  3.30it/s]
 61%|██████    | 225703/371472 [7:18:40<12:22:48,  3.27it/s]
 61%|██████    | 225704/371472 [7:18:41<12:08:09,  3.34it/s]
 61%|██████    | 225705/371472 [7:18:41<11:58:56,  3.38it/s]
 61%|██████    | 225706/371472 [7:18:41<12:23:32,  3.27it/s]
 61%|██████    | 225707/371472 [7:18:41<12:02:39,  3.36it/s]
 61%|██████    | 225708/371472 [7:18:42<12:08:17,  3.34it/s]
 61%|██████    | 225709/371472 [7:18:42<12:04:14,  3.35it/s]
 61%|██████    | 225710/371472 [7:18:42<11:52:36,  3.41it/s]
 61%|██████    | 225711/371472 [7:18:43<11:46:00,  3.44it/s]
 61%|██████    | 225712/371472 [7:18:43<11:28:52,  3.53it/s]
 61%|██████    | 225713/371472 [7:18:43<12:06:13,  3.35it/s]
 61%|██████    | 225714/371472 [7:18:44<11:56:43,  3.39it/s]
 61%|██████    | 225715/371472 [7:18:44<12:03:12,  3.36it/s]
 61%|██████    | 225716/371472 [7:18:44<12:17:19,  3.29it/s]
 61%|██████    | 225717/371472 [7:18:44<11:59:11,  3.38it/s]
 61%|██████    | 225718/371472 [7:18:45<12:07:41,  3.34it/s]
 61%|██████    | 225719/371472 [7:18:45<11:47:45,  3.43it/s]
 61%|██████    | 225720/371472 [7:18:45<11:43:29,  3.45it/s]
                                                            
{'loss': 2.8984, 'learning_rate': 4.5331724449998925e-07, 'epoch': 9.72}
+
 61%|██████    | 225720/371472 [7:18:45<11:43:29,  3.45it/s]
 61%|██████    | 225721/371472 [7:18:46<11:49:20,  3.42it/s]
 61%|██████    | 225722/371472 [7:18:46<11:51:17,  3.42it/s]
 61%|██████    | 225723/371472 [7:18:46<11:31:50,  3.51it/s]
 61%|██████    | 225724/371472 [7:18:46<11:42:41,  3.46it/s]
 61%|██████    | 225725/371472 [7:18:47<11:38:17,  3.48it/s]
 61%|██████    | 225726/371472 [7:18:47<11:27:41,  3.53it/s]
 61%|██████    | 225727/371472 [7:18:47<11:31:23,  3.51it/s]
 61%|██████    | 225728/371472 [7:18:48<11:52:06,  3.41it/s]
 61%|██████    | 225729/371472 [7:18:48<11:51:34,  3.41it/s]
 61%|██████    | 225730/371472 [7:18:48<11:44:26,  3.45it/s]
 61%|██████    | 225731/371472 [7:18:48<11:57:12,  3.39it/s]
 61%|██████    | 225732/371472 [7:18:49<11:43:22,  3.45it/s]
 61%|██████    | 225733/371472 [7:18:49<11:23:38,  3.55it/s]
 61%|██████    | 225734/371472 [7:18:49<11:13:10,  3.61it/s]
 61%|██████    | 225735/371472 [7:18:50<11:18:57,  3.58it/s]
 61%|██████    | 225736/371472 [7:18:50<12:52:36,  3.14it/s]
 61%|██████    | 225737/371472 [7:18:50<12:27:12,  3.25it/s]
 61%|██████    | 225738/371472 [7:18:51<12:06:54,  3.34it/s]
 61%|██████    | 225739/371472 [7:18:51<12:15:11,  3.30it/s]
 61%|██████    | 225740/371472 [7:18:51<12:16:29,  3.30it/s]
                                                            
{'loss': 2.6888, 'learning_rate': 4.532687625245103e-07, 'epoch': 9.72}
+
 61%|██████    | 225740/371472 [7:18:51<12:16:29,  3.30it/s]
 61%|██████    | 225741/371472 [7:18:51<12:25:27,  3.26it/s]
 61%|██████    | 225742/371472 [7:18:52<13:09:29,  3.08it/s]
 61%|██████    | 225743/371472 [7:18:52<12:37:52,  3.20it/s]
 61%|██████    | 225744/371472 [7:18:52<12:31:59,  3.23it/s]
 61%|██████    | 225745/371472 [7:18:53<12:10:21,  3.33it/s]
 61%|██████    | 225746/371472 [7:18:53<11:59:58,  3.37it/s]
 61%|██████    | 225747/371472 [7:18:53<11:33:58,  3.50it/s]
 61%|██████    | 225748/371472 [7:18:54<11:39:39,  3.47it/s]
 61%|██████    | 225749/371472 [7:18:54<11:43:42,  3.45it/s]
 61%|██████    | 225750/371472 [7:18:54<12:14:36,  3.31it/s]
 61%|██████    | 225751/371472 [7:18:54<11:54:38,  3.40it/s]
 61%|██████    | 225752/371472 [7:18:55<11:49:02,  3.43it/s]
 61%|██████    | 225753/371472 [7:18:55<11:46:54,  3.44it/s]
 61%|██████    | 225754/371472 [7:18:55<11:45:18,  3.44it/s]
 61%|██████    | 225755/371472 [7:18:56<11:56:39,  3.39it/s]
 61%|██████    | 225756/371472 [7:18:56<11:51:11,  3.41it/s]
 61%|██████    | 225757/371472 [7:18:56<12:14:17,  3.31it/s]
 61%|██████    | 225758/371472 [7:18:57<12:22:35,  3.27it/s]
 61%|██████    | 225759/371472 [7:18:57<12:29:46,  3.24it/s]
 61%|██████    | 225760/371472 [7:18:57<12:29:56,  3.24it/s]
                                                            
{'loss': 2.8395, 'learning_rate': 4.5322028054903144e-07, 'epoch': 9.72}
+
 61%|██████    | 225760/371472 [7:18:57<12:29:56,  3.24it/s]
 61%|██████    | 225761/371472 [7:18:57<12:33:11,  3.22it/s]
 61%|██████    | 225762/371472 [7:18:58<12:16:43,  3.30it/s]
 61%|██████    | 225763/371472 [7:18:58<11:53:19,  3.40it/s]
 61%|██████    | 225764/371472 [7:18:58<13:38:38,  2.97it/s]
 61%|██████    | 225765/371472 [7:18:59<13:02:34,  3.10it/s]
 61%|██████    | 225766/371472 [7:18:59<12:15:20,  3.30it/s]
 61%|██████    | 225767/371472 [7:18:59<11:52:52,  3.41it/s]
 61%|██████    | 225768/371472 [7:19:00<11:38:16,  3.48it/s]
 61%|██████    | 225769/371472 [7:19:00<12:19:30,  3.28it/s]
 61%|██████    | 225770/371472 [7:19:00<12:14:07,  3.31it/s]
 61%|██████    | 225771/371472 [7:19:01<12:27:47,  3.25it/s]
 61%|██████    | 225772/371472 [7:19:01<12:26:51,  3.25it/s]
 61%|██████    | 225773/371472 [7:19:01<12:01:22,  3.37it/s]
 61%|██████    | 225774/371472 [7:19:01<12:51:35,  3.15it/s]
 61%|██████    | 225775/371472 [7:19:02<12:37:19,  3.21it/s]
 61%|██████    | 225776/371472 [7:19:02<12:35:20,  3.21it/s]
 61%|██████    | 225777/371472 [7:19:02<12:35:51,  3.21it/s]
 61%|██████    | 225778/371472 [7:19:03<12:59:32,  3.11it/s]
 61%|██████    | 225779/371472 [7:19:03<12:30:51,  3.23it/s]
 61%|██████    | 225780/371472 [7:19:03<12:10:18,  3.32it/s]
                                                            
{'loss': 2.8543, 'learning_rate': 4.531717985735525e-07, 'epoch': 9.72}
+
 61%|██████    | 225780/371472 [7:19:03<12:10:18,  3.32it/s]
 61%|██████    | 225781/371472 [7:19:04<12:30:19,  3.24it/s]
 61%|██████    | 225782/371472 [7:19:04<12:14:23,  3.31it/s]
 61%|██████    | 225783/371472 [7:19:04<12:30:49,  3.23it/s]
 61%|██████    | 225784/371472 [7:19:05<12:27:55,  3.25it/s]
 61%|██████    | 225785/371472 [7:19:05<12:12:50,  3.31it/s]
 61%|██████    | 225786/371472 [7:19:05<12:08:23,  3.33it/s]
 61%|██████    | 225787/371472 [7:19:05<11:44:36,  3.45it/s]
 61%|██████    | 225788/371472 [7:19:06<11:25:06,  3.54it/s]
 61%|██████    | 225789/371472 [7:19:06<11:10:04,  3.62it/s]
 61%|██████    | 225790/371472 [7:19:06<11:14:35,  3.60it/s]
 61%|██████    | 225791/371472 [7:19:06<11:05:48,  3.65it/s]
 61%|██████    | 225792/371472 [7:19:07<11:21:24,  3.56it/s]
 61%|██████    | 225793/371472 [7:19:07<11:11:40,  3.61it/s]
 61%|██████    | 225794/371472 [7:19:07<11:47:29,  3.43it/s]
 61%|██████    | 225795/371472 [7:19:08<11:40:06,  3.47it/s]
 61%|██████    | 225796/371472 [7:19:08<11:17:09,  3.59it/s]
 61%|██████    | 225797/371472 [7:19:08<11:57:35,  3.38it/s]
 61%|██████    | 225798/371472 [7:19:09<12:07:10,  3.34it/s]
 61%|██████    | 225799/371472 [7:19:09<12:31:41,  3.23it/s]
 61%|██████    | 225800/371472 [7:19:09<13:04:25,  3.10it/s]
                                                            
{'loss': 2.9374, 'learning_rate': 4.531233165980737e-07, 'epoch': 9.73}
+
 61%|██████    | 225800/371472 [7:19:09<13:04:25,  3.10it/s]
 61%|██████    | 225801/371472 [7:19:10<12:43:44,  3.18it/s]
 61%|██████    | 225802/371472 [7:19:10<11:59:53,  3.37it/s]
 61%|██████    | 225803/371472 [7:19:10<11:57:01,  3.39it/s]
 61%|██████    | 225804/371472 [7:19:10<11:59:53,  3.37it/s]
 61%|██████    | 225805/371472 [7:19:11<12:17:15,  3.29it/s]
 61%|██████    | 225806/371472 [7:19:11<12:01:39,  3.36it/s]
 61%|██████    | 225807/371472 [7:19:11<12:06:08,  3.34it/s]
 61%|██████    | 225808/371472 [7:19:12<12:11:39,  3.32it/s]
 61%|██████    | 225809/371472 [7:19:12<13:02:30,  3.10it/s]
 61%|██████    | 225810/371472 [7:19:12<12:34:37,  3.22it/s]
 61%|██████    | 225811/371472 [7:19:13<12:21:42,  3.27it/s]
 61%|██████    | 225812/371472 [7:19:13<12:31:58,  3.23it/s]
 61%|██████    | 225813/371472 [7:19:13<12:03:31,  3.36it/s]
 61%|██████    | 225814/371472 [7:19:13<11:54:13,  3.40it/s]
 61%|██████    | 225815/371472 [7:19:14<11:52:46,  3.41it/s]
 61%|██████    | 225816/371472 [7:19:14<11:45:48,  3.44it/s]
 61%|██████    | 225817/371472 [7:19:14<11:57:52,  3.38it/s]
 61%|██████    | 225818/371472 [7:19:15<11:55:31,  3.39it/s]
 61%|██████    | 225819/371472 [7:19:15<11:43:25,  3.45it/s]
 61%|██████    | 225820/371472 [7:19:15<11:35:23,  3.49it/s]
                                                            
{'loss': 2.6287, 'learning_rate': 4.530748346225947e-07, 'epoch': 9.73}
+
 61%|██████    | 225820/371472 [7:19:15<11:35:23,  3.49it/s]
 61%|██████    | 225821/371472 [7:19:15<11:56:38,  3.39it/s]
 61%|██████    | 225822/371472 [7:19:16<12:14:01,  3.31it/s]
 61%|██████    | 225823/371472 [7:19:16<11:50:27,  3.42it/s]
 61%|██████    | 225824/371472 [7:19:16<11:43:29,  3.45it/s]
 61%|██████    | 225825/371472 [7:19:17<11:45:37,  3.44it/s]
 61%|██████    | 225826/371472 [7:19:17<12:05:57,  3.34it/s]
 61%|██████    | 225827/371472 [7:19:17<12:27:42,  3.25it/s]
 61%|██████    | 225828/371472 [7:19:18<12:56:56,  3.12it/s]
 61%|██████    | 225829/371472 [7:19:18<12:44:00,  3.18it/s]
 61%|██████    | 225830/371472 [7:19:18<12:15:32,  3.30it/s]
 61%|██████    | 225831/371472 [7:19:18<11:55:40,  3.39it/s]
 61%|██████    | 225832/371472 [7:19:19<12:12:58,  3.31it/s]
 61%|██████    | 225833/371472 [7:19:19<11:59:07,  3.38it/s]
 61%|██████    | 225834/371472 [7:19:19<11:52:10,  3.41it/s]
 61%|██████    | 225835/371472 [7:19:20<11:36:25,  3.49it/s]
 61%|██████    | 225836/371472 [7:19:20<12:06:58,  3.34it/s]
 61%|██████    | 225837/371472 [7:19:20<12:20:37,  3.28it/s]
 61%|██████    | 225838/371472 [7:19:21<12:13:45,  3.31it/s]
 61%|██████    | 225839/371472 [7:19:21<11:55:26,  3.39it/s]
 61%|██████    | 225840/371472 [7:19:21<11:43:34,  3.45it/s]
                                                            
{'loss': 2.7455, 'learning_rate': 4.5302635264711594e-07, 'epoch': 9.73}
+
 61%|██████    | 225840/371472 [7:19:21<11:43:34,  3.45it/s]
 61%|██████    | 225841/371472 [7:19:22<12:54:27,  3.13it/s]
 61%|██████    | 225842/371472 [7:19:22<12:18:53,  3.28it/s]
 61%|██████    | 225843/371472 [7:19:22<12:11:24,  3.32it/s]
 61%|██████    | 225844/371472 [7:19:22<12:13:44,  3.31it/s]
 61%|██████    | 225845/371472 [7:19:23<11:43:44,  3.45it/s]
 61%|██████    | 225846/371472 [7:19:23<11:45:26,  3.44it/s]
 61%|██████    | 225847/371472 [7:19:23<11:48:01,  3.43it/s]
 61%|██████    | 225848/371472 [7:19:24<11:58:50,  3.38it/s]
 61%|██████    | 225849/371472 [7:19:24<11:39:05,  3.47it/s]
 61%|██████    | 225850/371472 [7:19:24<12:23:04,  3.27it/s]
 61%|██████    | 225851/371472 [7:19:24<12:11:27,  3.32it/s]
 61%|██████    | 225852/371472 [7:19:25<12:16:24,  3.30it/s]
 61%|██████    | 225853/371472 [7:19:25<12:33:58,  3.22it/s]
 61%|██████    | 225854/371472 [7:19:25<12:41:57,  3.19it/s]
 61%|██████    | 225855/371472 [7:19:26<12:23:34,  3.26it/s]
 61%|██████    | 225856/371472 [7:19:26<12:02:58,  3.36it/s]
 61%|██████    | 225857/371472 [7:19:26<12:04:04,  3.35it/s]
 61%|██████    | 225858/371472 [7:19:27<12:55:47,  3.13it/s]
 61%|██████    | 225859/371472 [7:19:27<13:00:48,  3.11it/s]
 61%|██████    | 225860/371472 [7:19:27<12:50:40,  3.15it/s]
                                                            
{'loss': 2.5992, 'learning_rate': 4.5297787067163696e-07, 'epoch': 9.73}
+
 61%|██████    | 225860/371472 [7:19:27<12:50:40,  3.15it/s]
 61%|██████    | 225861/371472 [7:19:28<13:24:49,  3.02it/s]
 61%|██████    | 225862/371472 [7:19:28<12:33:20,  3.22it/s]
 61%|██████    | 225863/371472 [7:19:28<12:29:47,  3.24it/s]
 61%|██████    | 225864/371472 [7:19:28<12:02:04,  3.36it/s]
 61%|██████    | 225865/371472 [7:19:29<11:56:54,  3.39it/s]
 61%|██████    | 225866/371472 [7:19:29<11:34:22,  3.49it/s]
 61%|██████    | 225867/371472 [7:19:29<11:49:10,  3.42it/s]
 61%|██████    | 225868/371472 [7:19:30<11:55:33,  3.39it/s]
 61%|██████    | 225869/371472 [7:19:30<11:36:15,  3.49it/s]
 61%|███���██    | 225870/371472 [7:19:30<11:38:12,  3.48it/s]
 61%|██████    | 225871/371472 [7:19:30<11:35:28,  3.49it/s]
 61%|██████    | 225872/371472 [7:19:31<11:33:48,  3.50it/s]
 61%|██████    | 225873/371472 [7:19:31<11:27:19,  3.53it/s]
 61%|██████    | 225874/371472 [7:19:31<11:41:12,  3.46it/s]
 61%|██████    | 225875/371472 [7:19:32<11:55:34,  3.39it/s]
 61%|██████    | 225876/371472 [7:19:32<12:25:53,  3.25it/s]
 61%|██████    | 225877/371472 [7:19:32<12:04:45,  3.35it/s]
 61%|██████    | 225878/371472 [7:19:33<11:39:40,  3.47it/s]
 61%|██████    | 225879/371472 [7:19:33<13:16:21,  3.05it/s]
 61%|██████    | 225880/371472 [7:19:33<12:31:29,  3.23it/s]
                                                            
{'loss': 2.8205, 'learning_rate': 4.529293886961581e-07, 'epoch': 9.73}
+
 61%|██████    | 225880/371472 [7:19:33<12:31:29,  3.23it/s]
 61%|██████    | 225881/371472 [7:19:34<13:09:20,  3.07it/s]
 61%|██████    | 225882/371472 [7:19:34<12:35:35,  3.21it/s]
 61%|██████    | 225883/371472 [7:19:34<12:16:15,  3.30it/s]
 61%|██████    | 225884/371472 [7:19:34<12:18:06,  3.29it/s]
 61%|██████    | 225885/371472 [7:19:35<12:02:53,  3.36it/s]
 61%|██████    | 225886/371472 [7:19:35<12:18:08,  3.29it/s]
 61%|██████    | 225887/371472 [7:19:35<11:52:20,  3.41it/s]
 61%|██████    | 225888/371472 [7:19:36<11:41:26,  3.46it/s]
 61%|██████    | 225889/371472 [7:19:36<11:35:07,  3.49it/s]
 61%|██████    | 225890/371472 [7:19:36<11:51:02,  3.41it/s]
 61%|██████    | 225891/371472 [7:19:37<12:14:33,  3.30it/s]
 61%|██████    | 225892/371472 [7:19:37<12:51:29,  3.14it/s]
 61%|██████    | 225893/371472 [7:19:37<12:32:42,  3.22it/s]
 61%|██████    | 225894/371472 [7:19:37<12:54:55,  3.13it/s]
 61%|██████    | 225895/371472 [7:19:38<12:28:47,  3.24it/s]
 61%|██████    | 225896/371472 [7:19:38<12:12:25,  3.31it/s]
 61%|██████    | 225897/371472 [7:19:38<11:47:54,  3.43it/s]
 61%|██████    | 225898/371472 [7:19:39<11:44:32,  3.44it/s]
 61%|██████    | 225899/371472 [7:19:39<11:22:34,  3.55it/s]
 61%|██████    | 225900/371472 [7:19:39<11:13:33,  3.60it/s]
                                                            
{'loss': 2.8776, 'learning_rate': 4.5288090672067916e-07, 'epoch': 9.73}
+
 61%|██████    | 225900/371472 [7:19:39<11:13:33,  3.60it/s]
 61%|██████    | 225901/371472 [7:19:39<11:29:07,  3.52it/s]
 61%|██████    | 225902/371472 [7:19:40<11:35:30,  3.49it/s]
 61%|██████    | 225903/371472 [7:19:40<12:04:58,  3.35it/s]
 61%|██████    | 225904/371472 [7:19:40<12:46:02,  3.17it/s]
 61%|██████    | 225905/371472 [7:19:41<12:45:21,  3.17it/s]
 61%|██████    | 225906/371472 [7:19:41<12:01:18,  3.36it/s]
 61%|██████    | 225907/371472 [7:19:41<12:12:03,  3.31it/s]
 61%|██████    | 225908/371472 [7:19:42<12:22:43,  3.27it/s]
 61%|██████    | 225909/371472 [7:19:42<12:11:29,  3.32it/s]
 61%|██████    | 225910/371472 [7:19:42<12:15:36,  3.30it/s]
 61%|██████    | 225911/371472 [7:19:42<11:58:01,  3.38it/s]
 61%|██████    | 225912/371472 [7:19:43<12:15:37,  3.30it/s]
 61%|██████    | 225913/371472 [7:19:43<11:45:37,  3.44it/s]
 61%|██████    | 225914/371472 [7:19:43<11:29:38,  3.52it/s]
 61%|██████    | 225915/371472 [7:19:44<11:14:01,  3.60it/s]
 61%|██████    | 225916/371472 [7:19:44<11:06:36,  3.64it/s]
 61%|██████    | 225917/371472 [7:19:44<12:35:02,  3.21it/s]
 61%|██████    | 225918/371472 [7:19:45<12:35:53,  3.21it/s]
 61%|██████    | 225919/371472 [7:19:45<12:53:17,  3.14it/s]
 61%|██████    | 225920/371472 [7:19:45<12:46:07,  3.17it/s]
                                                            
{'loss': 2.4803, 'learning_rate': 4.5283242474520023e-07, 'epoch': 9.73}
+
 61%|██████    | 225920/371472 [7:19:45<12:46:07,  3.17it/s]
 61%|██████    | 225921/371472 [7:19:46<13:01:41,  3.10it/s]
 61%|██████    | 225922/371472 [7:19:46<12:40:02,  3.19it/s]
 61%|██████    | 225923/371472 [7:19:46<12:30:23,  3.23it/s]
 61%|██████    | 225924/371472 [7:19:46<12:35:38,  3.21it/s]
 61%|██████    | 225925/371472 [7:19:47<12:13:12,  3.31it/s]
 61%|██████    | 225926/371472 [7:19:47<12:01:42,  3.36it/s]
 61%|██████    | 225927/371472 [7:19:47<11:47:57,  3.43it/s]
 61%|██████    | 225928/371472 [7:19:48<11:55:34,  3.39it/s]
 61%|██████    | 225929/371472 [7:19:48<11:36:55,  3.48it/s]
 61%|██████    | 225930/371472 [7:19:48<12:25:48,  3.25it/s]
 61%|██████    | 225931/371472 [7:19:49<12:44:32,  3.17it/s]
 61%|██████    | 225932/371472 [7:19:49<12:51:31,  3.14it/s]
 61%|██████    | 225933/371472 [7:19:49<12:33:13,  3.22it/s]
 61%|██████    | 225934/371472 [7:19:49<12:17:59,  3.29it/s]
 61%|██████    | 225935/371472 [7:19:50<12:15:29,  3.30it/s]
 61%|██████    | 225936/371472 [7:19:50<12:25:26,  3.25it/s]
 61%|██████    | 225937/371472 [7:19:50<12:02:25,  3.36it/s]
 61%|██████    | 225938/371472 [7:19:51<12:14:05,  3.30it/s]
 61%|██████    | 225939/371472 [7:19:51<11:52:35,  3.40it/s]
 61%|██████    | 225940/371472 [7:19:51<11:52:18,  3.41it/s]
                                                            
{'loss': 2.8727, 'learning_rate': 4.5278394276972135e-07, 'epoch': 9.73}
+
 61%|██████    | 225940/371472 [7:19:51<11:52:18,  3.41it/s]
 61%|██████    | 225941/371472 [7:19:52<11:41:52,  3.46it/s]
 61%|██████    | 225942/371472 [7:19:52<11:43:37,  3.45it/s]
 61%|██████    | 225943/371472 [7:19:52<11:48:17,  3.42it/s]
 61%|██████    | 225944/371472 [7:19:52<11:51:08,  3.41it/s]
 61%|██████    | 225945/371472 [7:19:53<12:06:37,  3.34it/s]
 61%|██████    | 225946/371472 [7:19:53<11:52:06,  3.41it/s]
 61%|██████    | 225947/371472 [7:19:53<12:20:48,  3.27it/s]
 61%|██████    | 225948/371472 [7:19:54<12:06:35,  3.34it/s]
 61%|██████    | 225949/371472 [7:19:54<11:53:24,  3.40it/s]
 61%|██████    | 225950/371472 [7:19:54<12:03:09,  3.35it/s]
 61%|██████    | 225951/371472 [7:19:55<12:58:57,  3.11it/s]
 61%|██████    | 225952/371472 [7:19:55<14:12:51,  2.84it/s]
 61%|██████    | 225953/371472 [7:19:55<13:40:49,  2.95it/s]
 61%|██████    | 225954/371472 [7:19:56<12:47:23,  3.16it/s]
 61%|██████    | 225955/371472 [7:19:56<13:05:27,  3.09it/s]
 61%|██████    | 225956/371472 [7:19:56<12:57:12,  3.12it/s]
 61%|██████    | 225957/371472 [7:19:57<12:58:34,  3.11it/s]
 61%|██████    | 225958/371472 [7:19:57<12:25:20,  3.25it/s]
 61%|██████    | 225959/371472 [7:19:57<12:27:16,  3.25it/s]
 61%|██████    | 225960/371472 [7:19:57<12:24:37,  3.26it/s]
                                                            
{'loss': 2.6881, 'learning_rate': 4.527354607942424e-07, 'epoch': 9.73}
+
 61%|██████    | 225960/371472 [7:19:57<12:24:37,  3.26it/s]
 61%|██████    | 225961/371472 [7:19:58<12:22:22,  3.27it/s]
 61%|██████    | 225962/371472 [7:19:58<12:05:05,  3.34it/s]
 61%|██████    | 225963/371472 [7:19:58<12:28:20,  3.24it/s]
 61%|██████    | 225964/371472 [7:19:59<12:15:11,  3.30it/s]
 61%|██████    | 225965/371472 [7:19:59<12:07:58,  3.33it/s]
 61%|██████    | 225966/371472 [7:19:59<12:04:56,  3.35it/s]
 61%|██████    | 225967/371472 [7:20:00<11:59:20,  3.37it/s]
 61%|██████    | 225968/371472 [7:20:00<11:48:26,  3.42it/s]
 61%|██████    | 225969/371472 [7:20:00<11:54:01,  3.40it/s]
 61%|██████    | 225970/371472 [7:20:00<11:41:05,  3.46it/s]
 61%|██████    | 225971/371472 [7:20:01<11:31:51,  3.51it/s]
 61%|██████    | 225972/371472 [7:20:01<11:36:12,  3.48it/s]
 61%|██████    | 225973/371472 [7:20:01<11:14:24,  3.60it/s]
 61%|██████    | 225974/371472 [7:20:02<14:49:46,  2.73it/s]
 61%|██████    | 225975/371472 [7:20:02<13:59:29,  2.89it/s]
 61%|██████    | 225976/371472 [7:20:02<14:03:56,  2.87it/s]
 61%|██████    | 225977/371472 [7:20:03<13:53:52,  2.91it/s]
 61%|██████    | 225978/371472 [7:20:03<13:07:43,  3.08it/s]
 61%|██████    | 225979/371472 [7:20:03<12:37:00,  3.20it/s]
 61%|██████    | 225980/371472 [7:20:04<12:14:02,  3.30it/s]
                                                            
{'loss': 2.6297, 'learning_rate': 4.526869788187636e-07, 'epoch': 9.73}
+
 61%|██████    | 225980/371472 [7:20:04<12:14:02,  3.30it/s]
 61%|██████    | 225981/371472 [7:20:04<11:58:10,  3.38it/s]
 61%|██████    | 225982/371472 [7:20:04<11:46:39,  3.43it/s]
 61%|██████    | 225983/371472 [7:20:04<11:30:49,  3.51it/s]
 61%|██████    | 225984/371472 [7:20:05<11:43:43,  3.45it/s]
 61%|██████    | 225985/371472 [7:20:05<11:26:28,  3.53it/s]
 61%|██████    | 225986/371472 [7:20:05<11:59:05,  3.37it/s]
 61%|██████    | 225987/371472 [7:20:06<11:57:56,  3.38it/s]
 61%|██████    | 225988/371472 [7:20:06<12:05:28,  3.34it/s]
 61%|██████    | 225989/371472 [7:20:06<12:01:15,  3.36it/s]
 61%|██████    | 225990/371472 [7:20:07<11:58:11,  3.38it/s]
 61%|██████    | 225991/371472 [7:20:07<12:02:09,  3.36it/s]
 61%|██████    | 225992/371472 [7:20:07<12:34:07,  3.22it/s]
 61%|██████    | 225993/371472 [7:20:08<12:58:26,  3.11it/s]
 61%|██████    | 225994/371472 [7:20:08<12:18:18,  3.28it/s]
 61%|██████    | 225995/371472 [7:20:08<12:05:15,  3.34it/s]
 61%|██████    | 225996/371472 [7:20:08<12:16:36,  3.29it/s]
 61%|██████    | 225997/371472 [7:20:09<12:33:58,  3.22it/s]
 61%|██████    | 225998/371472 [7:20:09<12:39:50,  3.19it/s]
 61%|██████    | 225999/371472 [7:20:09<12:57:54,  3.12it/s]
 61%|██████    | 226000/371472 [7:20:10<12:49:37,  3.15it/s]
                                                            
{'loss': 2.7619, 'learning_rate': 4.526384968432846e-07, 'epoch': 9.73}
+
 61%|██████    | 226000/371472 [7:20:10<12:49:37,  3.15it/s]
 61%|██████    | 226001/371472 [7:20:10<12:36:53,  3.20it/s]
 61%|██████    | 226002/371472 [7:20:10<12:05:17,  3.34it/s]
 61%|██████    | 226003/371472 [7:20:11<11:59:04,  3.37it/s]
 61%|██████    | 226004/371472 [7:20:11<12:18:45,  3.28it/s]
 61%|██████    | 226005/371472 [7:20:11<12:14:08,  3.30it/s]
 61%|██████    | 226006/371472 [7:20:11<11:51:13,  3.41it/s]
 61%|██████    | 226007/371472 [7:20:12<11:54:22,  3.39it/s]
 61%|██████    | 226008/371472 [7:20:12<11:40:22,  3.46it/s]
 61%|██████    | 226009/371472 [7:20:12<11:59:17,  3.37it/s]
 61%|██████    | 226010/371472 [7:20:13<11:40:34,  3.46it/s]
 61%|██████    | 226011/371472 [7:20:13<11:32:29,  3.50it/s]
 61%|██████    | 226012/371472 [7:20:13<11:38:12,  3.47it/s]
 61%|██████    | 226013/371472 [7:20:13<11:51:52,  3.41it/s]
 61%|██████    | 226014/371472 [7:20:14<12:04:30,  3.35it/s]
 61%|██████    | 226015/371472 [7:20:14<11:49:00,  3.42it/s]
 61%|██████    | 226016/371472 [7:20:14<11:38:52,  3.47it/s]
 61%|██████    | 226017/371472 [7:20:15<11:48:40,  3.42it/s]
 61%|██████    | 226018/371472 [7:20:15<11:40:05,  3.46it/s]
 61%|██████    | 226019/371472 [7:20:15<11:48:52,  3.42it/s]
 61%|██████    | 226020/371472 [7:20:16<11:47:54,  3.42it/s]
                                                            
{'loss': 2.8766, 'learning_rate': 4.525900148678058e-07, 'epoch': 9.74}
+
 61%|██████    | 226020/371472 [7:20:16<11:47:54,  3.42it/s]
 61%|██████    | 226021/371472 [7:20:16<11:47:15,  3.43it/s]
 61%|██████    | 226022/371472 [7:20:16<11:31:46,  3.50it/s]
 61%|██████    | 226023/371472 [7:20:16<12:02:46,  3.35it/s]
 61%|██████    | 226024/371472 [7:20:17<11:34:12,  3.49it/s]
 61%|██████    | 226025/371472 [7:20:17<11:44:08,  3.44it/s]
 61%|██████    | 226026/371472 [7:20:17<11:37:06,  3.48it/s]
 61%|██████    | 226027/371472 [7:20:18<11:45:51,  3.43it/s]
 61%|██████    | 226028/371472 [7:20:18<11:44:56,  3.44it/s]
 61%|██████    | 226029/371472 [7:20:18<11:30:38,  3.51it/s]
 61%|██████    | 226030/371472 [7:20:18<11:36:06,  3.48it/s]
 61%|██████    | 226031/371472 [7:20:19<11:34:01,  3.49it/s]
 61%|██████    | 226032/371472 [7:20:19<11:43:27,  3.45it/s]
 61%|██████    | 226033/371472 [7:20:19<11:35:30,  3.49it/s]
 61%|██████    | 226034/371472 [7:20:20<11:52:50,  3.40it/s]
 61%|██████    | 226035/371472 [7:20:20<12:16:46,  3.29it/s]
 61%|██████    | 226036/371472 [7:20:20<12:38:14,  3.20it/s]
 61%|██████    | 226037/371472 [7:20:21<12:32:42,  3.22it/s]
 61%|██████    | 226038/371472 [7:20:21<12:14:00,  3.30it/s]
 61%|██████    | 226039/371472 [7:20:21<12:19:04,  3.28it/s]
 61%|██████    | 226040/371472 [7:20:21<12:13:12,  3.31it/s]
                                                            
{'loss': 2.7204, 'learning_rate': 4.5254153289232687e-07, 'epoch': 9.74}
+
 61%|██████    | 226040/371472 [7:20:21<12:13:12,  3.31it/s]
 61%|██████    | 226041/371472 [7:20:22<12:22:07,  3.27it/s]
 61%|██████    | 226042/371472 [7:20:22<11:53:55,  3.40it/s]
 61%|██████    | 226043/371472 [7:20:22<12:22:21,  3.27it/s]
 61%|██████    | 226044/371472 [7:20:23<12:36:05,  3.21it/s]
 61%|██████    | 226045/371472 [7:20:23<12:49:26,  3.15it/s]
 61%|██████    | 226046/371472 [7:20:23<13:00:23,  3.11it/s]
 61%|██████    | 226047/371472 [7:20:24<12:31:50,  3.22it/s]
 61%|██████    | 226048/371472 [7:20:24<12:19:46,  3.28it/s]
 61%|██████    | 226049/371472 [7:20:24<12:11:38,  3.31it/s]
 61%|██████    | 226050/371472 [7:20:25<12:15:33,  3.30it/s]
 61%|██████    | 226051/371472 [7:20:25<12:48:44,  3.15it/s]
 61%|██████    | 226052/371472 [7:20:25<12:34:36,  3.21it/s]
 61%|██████    | 226053/371472 [7:20:25<12:16:05,  3.29it/s]
 61%|██████    | 226054/371472 [7:20:26<12:25:03,  3.25it/s]
 61%|██████    | 226055/371472 [7:20:26<12:54:45,  3.13it/s]
 61%|██████    | 226056/371472 [7:20:26<12:38:05,  3.20it/s]
 61%|██████    | 226057/371472 [7:20:27<12:55:59,  3.12it/s]
 61%|██████    | 226058/371472 [7:20:27<12:24:27,  3.26it/s]
 61%|██████    | 226059/371472 [7:20:27<12:38:37,  3.19it/s]
 61%|██████    | 226060/371472 [7:20:28<12:18:01,  3.28it/s]
                                                            
{'loss': 2.7272, 'learning_rate': 4.52493050916848e-07, 'epoch': 9.74}
+
 61%|██████    | 226060/371472 [7:20:28<12:18:01,  3.28it/s]
 61%|██████    | 226061/371472 [7:20:28<12:05:19,  3.34it/s]
 61%|██████    | 226062/371472 [7:20:28<11:59:45,  3.37it/s]
 61%|██████    | 226063/371472 [7:20:29<11:52:38,  3.40it/s]
 61%|██████    | 226064/371472 [7:20:29<12:25:57,  3.25it/s]
 61%|██████    | 226065/371472 [7:20:29<12:03:49,  3.35it/s]
 61%|██████    | 226066/371472 [7:20:29<11:52:28,  3.40it/s]
 61%|██████    | 226067/371472 [7:20:30<11:53:51,  3.39it/s]
 61%|██████    | 226068/371472 [7:20:30<11:43:47,  3.44it/s]
 61%|██████    | 226069/371472 [7:20:30<12:04:47,  3.34it/s]
 61%|██████    | 226070/371472 [7:20:31<11:55:51,  3.39it/s]
 61%|██████    | 226071/371472 [7:20:31<12:35:42,  3.21it/s]
 61%|██████    | 226072/371472 [7:20:31<12:53:58,  3.13it/s]
 61%|██████    | 226073/371472 [7:20:32<12:25:49,  3.25it/s]
 61%|██████    | 226074/371472 [7:20:32<12:04:19,  3.35it/s]
 61%|██████    | 226075/371472 [7:20:32<12:26:39,  3.25it/s]
 61%|██████    | 226076/371472 [7:20:32<12:19:40,  3.28it/s]
 61%|██████    | 226077/371472 [7:20:33<12:23:17,  3.26it/s]
 61%|██████    | 226078/371472 [7:20:33<12:04:18,  3.35it/s]
 61%|██████    | 226079/371472 [7:20:33<11:42:24,  3.45it/s]
 61%|██████    | 226080/371472 [7:20:34<11:41:17,  3.46it/s]
                                                            
{'loss': 2.8508, 'learning_rate': 4.5244456894136907e-07, 'epoch': 9.74}
+
 61%|██████    | 226080/371472 [7:20:34<11:41:17,  3.46it/s]
 61%|██████    | 226081/371472 [7:20:34<11:34:53,  3.49it/s]
 61%|██████    | 226082/371472 [7:20:34<12:52:18,  3.14it/s]
 61%|██████    | 226083/371472 [7:20:35<12:48:29,  3.15it/s]
 61%|██████    | 226084/371472 [7:20:35<13:24:48,  3.01it/s]
 61%|██████    | 226085/371472 [7:20:35<13:01:04,  3.10it/s]
 61%|██████    | 226086/371472 [7:20:36<13:14:47,  3.05it/s]
 61%|██████    | 226087/371472 [7:20:36<12:40:59,  3.18it/s]
 61%|██████    | 226088/371472 [7:20:36<13:13:12,  3.05it/s]
 61%|██████    | 226089/371472 [7:20:37<12:38:01,  3.20it/s]
 61%|██████    | 226090/371472 [7:20:37<12:50:00,  3.15it/s]
 61%|██████    | 226091/371472 [7:20:37<12:33:04,  3.22it/s]
 61%|██████    | 226092/371472 [7:20:38<12:53:02,  3.13it/s]
 61%|██████    | 226093/371472 [7:20:38<12:29:53,  3.23it/s]
 61%|██████    | 226094/371472 [7:20:38<12:22:43,  3.26it/s]
 61%|██████    | 226095/371472 [7:20:38<12:00:26,  3.36it/s]
 61%|██████    | 226096/371472 [7:20:39<11:58:17,  3.37it/s]
 61%|██████    | 226097/371472 [7:20:39<11:53:18,  3.40it/s]
 61%|██████    | 226098/371472 [7:20:39<11:40:42,  3.46it/s]
 61%|██████    | 226099/371472 [7:20:40<11:49:40,  3.41it/s]
 61%|██████    | 226100/371472 [7:20:40<11:49:06,  3.42it/s]
                                                            
{'loss': 2.7654, 'learning_rate': 4.5239608696589024e-07, 'epoch': 9.74}
+
 61%|██████    | 226100/371472 [7:20:40<11:49:06,  3.42it/s]
 61%|██████    | 226101/371472 [7:20:40<12:21:31,  3.27it/s]
 61%|██████    | 226102/371472 [7:20:41<12:54:18,  3.13it/s]
 61%|██████    | 226103/371472 [7:20:41<12:59:34,  3.11it/s]
 61%|██████    | 226104/371472 [7:20:41<12:27:32,  3.24it/s]
 61%|██████    | 226105/371472 [7:20:41<12:40:04,  3.19it/s]
 61%|██████    | 226106/371472 [7:20:42<12:35:18,  3.21it/s]
 61%|██████    | 226107/371472 [7:20:42<12:17:31,  3.28it/s]
 61%|██████    | 226108/371472 [7:20:42<12:14:54,  3.30it/s]
 61%|██████    | 226109/371472 [7:20:43<12:06:24,  3.34it/s]
 61%|██████    | 226110/371472 [7:20:43<11:49:27,  3.41it/s]
 61%|██████    | 226111/371472 [7:20:43<11:37:25,  3.47it/s]
 61%|██████    | 226112/371472 [7:20:43<11:57:27,  3.38it/s]
 61%|██████    | 226113/371472 [7:20:44<11:44:52,  3.44it/s]
 61%|██████    | 226114/371472 [7:20:44<11:44:59,  3.44it/s]
 61%|██████    | 226115/371472 [7:20:44<12:00:11,  3.36it/s]
 61%|██████    | 226116/371472 [7:20:45<12:07:33,  3.33it/s]
 61%|██████    | 226117/371472 [7:20:45<11:34:53,  3.49it/s]
 61%|██████    | 226118/371472 [7:20:45<11:23:06,  3.55it/s]
 61%|██████    | 226119/371472 [7:20:45<11:12:44,  3.60it/s]
 61%|██████    | 226120/371472 [7:20:46<11:36:56,  3.48it/s]
                                                            
{'loss': 2.7756, 'learning_rate': 4.523476049904113e-07, 'epoch': 9.74}
+
 61%|██████    | 226120/371472 [7:20:46<11:36:56,  3.48it/s]
 61%|██████    | 226121/371472 [7:20:46<12:06:04,  3.34it/s]
 61%|██████    | 226122/371472 [7:20:46<11:49:54,  3.41it/s]
 61%|██████    | 226123/371472 [7:20:47<11:41:10,  3.45it/s]
 61%|██████    | 226124/371472 [7:20:47<11:09:58,  3.62it/s]
 61%|██████    | 226125/371472 [7:20:47<11:05:55,  3.64it/s]
 61%|██████    | 226126/371472 [7:20:48<11:35:24,  3.48it/s]
 61%|██████    | 226127/371472 [7:20:48<12:31:31,  3.22it/s]
 61%|██████    | 226128/371472 [7:20:48<12:04:47,  3.34it/s]
 61%|██████    | 226129/371472 [7:20:48<12:27:11,  3.24it/s]
 61%|██████    | 226130/371472 [7:20:49<13:00:59,  3.10it/s]
 61%|██████    | 226131/371472 [7:20:49<12:16:45,  3.29it/s]
 61%|██████    | 226132/371472 [7:20:49<12:13:00,  3.30it/s]
 61%|██████    | 226133/371472 [7:20:50<12:06:02,  3.34it/s]
 61%|██████    | 226134/371472 [7:20:50<11:50:36,  3.41it/s]
 61%|██████    | 226135/371472 [7:20:50<11:40:25,  3.46it/s]
 61%|██████    | 226136/371472 [7:20:51<12:11:31,  3.31it/s]
 61%|██████    | 226137/371472 [7:20:51<12:18:43,  3.28it/s]
 61%|██████    | 226138/371472 [7:20:51<12:09:53,  3.32it/s]
 61%|██████    | 226139/371472 [7:20:51<11:46:52,  3.43it/s]
 61%|██████    | 226140/371472 [7:20:52<11:48:43,  3.42it/s]
                                                            
{'loss': 2.6627, 'learning_rate': 4.5229912301493244e-07, 'epoch': 9.74}
+
 61%|██████    | 226140/371472 [7:20:52<11:48:43,  3.42it/s]
 61%|██████    | 226141/371472 [7:20:52<12:02:18,  3.35it/s]
 61%|██████    | 226142/371472 [7:20:52<11:40:16,  3.46it/s]
 61%|██████    | 226143/371472 [7:20:53<11:39:58,  3.46it/s]
 61%|██████    | 226144/371472 [7:20:53<11:43:31,  3.44it/s]
 61%|██████    | 226145/371472 [7:20:53<11:45:02,  3.44it/s]
 61%|██████    | 226146/371472 [7:20:54<12:48:25,  3.15it/s]
 61%|██████    | 226147/371472 [7:20:54<12:33:33,  3.21it/s]
 61%|██████    | 226148/371472 [7:20:54<12:13:05,  3.30it/s]
 61%|██████    | 226149/371472 [7:20:54<12:13:19,  3.30it/s]
 61%|██████    | 226150/371472 [7:20:55<12:07:59,  3.33it/s]
 61%|██████    | 226151/371472 [7:20:55<12:02:10,  3.35it/s]
 61%|██████    | 226152/371472 [7:20:55<11:43:43,  3.44it/s]
 61%|██████    | 226153/371472 [7:20:56<11:29:00,  3.52it/s]
 61%|██████    | 226154/371472 [7:20:56<11:12:20,  3.60it/s]
 61%|██████    | 226155/371472 [7:20:56<11:16:15,  3.58it/s]
 61%|██████    | 226156/371472 [7:20:56<11:25:09,  3.53it/s]
 61%|██████    | 226157/371472 [7:20:57<11:31:53,  3.50it/s]
 61%|██████    | 226158/371472 [7:20:57<12:11:23,  3.31it/s]
 61%|██████    | 226159/371472 [7:20:57<12:01:57,  3.35it/s]
 61%|██████    | 226160/371472 [7:20:58<12:33:21,  3.21it/s]
                                                            
{'loss': 2.902, 'learning_rate': 4.522506410394535e-07, 'epoch': 9.74}
+
 61%|██████    | 226160/371472 [7:20:58<12:33:21,  3.21it/s]
 61%|██████    | 226161/371472 [7:20:58<12:09:15,  3.32it/s]
 61%|██████    | 226162/371472 [7:20:58<11:54:40,  3.39it/s]
 61%|██████    | 226163/371472 [7:20:59<11:39:38,  3.46it/s]
 61%|██████    | 226164/371472 [7:20:59<11:37:47,  3.47it/s]
 61%|██████    | 226165/371472 [7:20:59<11:21:45,  3.55it/s]
 61%|██████    | 226166/371472 [7:20:59<11:07:21,  3.63it/s]
 61%|██████    | 226167/371472 [7:21:00<11:21:58,  3.55it/s]
 61%|██████    | 226168/371472 [7:21:00<11:31:38,  3.50it/s]
 61%|██████    | 226169/371472 [7:21:00<11:20:53,  3.56it/s]
 61%|██████    | 226170/371472 [7:21:00<11:10:51,  3.61it/s]
 61%|██████    | 226171/371472 [7:21:01<11:00:33,  3.67it/s]
 61%|██████    | 226172/371472 [7:21:01<11:32:24,  3.50it/s]
 61%|██████    | 226173/371472 [7:21:01<11:26:20,  3.53it/s]
 61%|██████    | 226174/371472 [7:21:02<11:43:25,  3.44it/s]
 61%|██████    | 226175/371472 [7:21:02<11:49:29,  3.41it/s]
 61%|██████    | 226176/371472 [7:21:02<11:38:13,  3.47it/s]
 61%|██████    | 226177/371472 [7:21:02<11:21:34,  3.55it/s]
 61%|���█████    | 226178/371472 [7:21:03<11:21:50,  3.55it/s]
 61%|██████    | 226179/371472 [7:21:03<11:15:14,  3.59it/s]
 61%|██████    | 226180/371472 [7:21:03<11:15:33,  3.58it/s]
                                                            
{'loss': 2.956, 'learning_rate': 4.522021590639747e-07, 'epoch': 9.74}
+
 61%|██████    | 226180/371472 [7:21:03<11:15:33,  3.58it/s]
 61%|██████    | 226181/371472 [7:21:04<11:11:47,  3.60it/s]
 61%|██████    | 226182/371472 [7:21:04<11:12:02,  3.60it/s]
 61%|██████    | 226183/371472 [7:21:04<11:39:05,  3.46it/s]
 61%|██████    | 226184/371472 [7:21:04<11:30:56,  3.50it/s]
 61%|██████    | 226185/371472 [7:21:05<11:32:14,  3.50it/s]
 61%|██████    | 226186/371472 [7:21:05<11:39:23,  3.46it/s]
 61%|██████    | 226187/371472 [7:21:05<11:43:13,  3.44it/s]
 61%|██████    | 226188/371472 [7:21:06<11:57:47,  3.37it/s]
 61%|██████    | 226189/371472 [7:21:06<11:52:10,  3.40it/s]
 61%|██████    | 226190/371472 [7:21:06<11:27:03,  3.52it/s]
 61%|██████    | 226191/371472 [7:21:06<11:20:06,  3.56it/s]
 61%|██████    | 226192/371472 [7:21:07<12:27:15,  3.24it/s]
 61%|██████    | 226193/371472 [7:21:07<11:56:16,  3.38it/s]
 61%|██████    | 226194/371472 [7:21:07<11:43:06,  3.44it/s]
 61%|██████    | 226195/371472 [7:21:08<12:02:47,  3.35it/s]
 61%|██████    | 226196/371472 [7:21:08<11:37:09,  3.47it/s]
 61%|██████    | 226197/371472 [7:21:08<12:04:42,  3.34it/s]
 61%|██████    | 226198/371472 [7:21:09<11:48:06,  3.42it/s]
 61%|██████    | 226199/371472 [7:21:09<11:31:11,  3.50it/s]
 61%|██████    | 226200/371472 [7:21:09<11:44:12,  3.44it/s]
                                                            
{'loss': 2.7228, 'learning_rate': 4.521536770884957e-07, 'epoch': 9.74}
+
 61%|██████    | 226200/371472 [7:21:09<11:44:12,  3.44it/s]
 61%|██████    | 226201/371472 [7:21:09<12:06:58,  3.33it/s]
 61%|██████    | 226202/371472 [7:21:10<12:47:23,  3.16it/s]
 61%|██████    | 226203/371472 [7:21:10<12:46:47,  3.16it/s]
 61%|██████    | 226204/371472 [7:21:10<12:43:21,  3.17it/s]
 61%|██████    | 226205/371472 [7:21:11<12:26:44,  3.24it/s]
 61%|██████    | 226206/371472 [7:21:11<12:19:24,  3.27it/s]
 61%|██████    | 226207/371472 [7:21:11<12:30:33,  3.23it/s]
 61%|██████    | 226208/371472 [7:21:12<12:29:13,  3.23it/s]
 61%|██████    | 226209/371472 [7:21:12<12:12:05,  3.31it/s]
 61%|██████    | 226210/371472 [7:21:12<11:53:30,  3.39it/s]
 61%|██████    | 226211/371472 [7:21:13<11:58:19,  3.37it/s]
 61%|██████    | 226212/371472 [7:21:13<11:51:32,  3.40it/s]
 61%|██████    | 226213/371472 [7:21:13<12:04:31,  3.34it/s]
 61%|██████    | 226214/371472 [7:21:13<12:09:33,  3.32it/s]
 61%|██████    | 226215/371472 [7:21:14<12:07:03,  3.33it/s]
 61%|██████    | 226216/371472 [7:21:14<11:58:30,  3.37it/s]
 61%|██████    | 226217/371472 [7:21:14<11:41:10,  3.45it/s]
 61%|██████    | 226218/371472 [7:21:15<11:34:28,  3.49it/s]
 61%|██████    | 226219/371472 [7:21:15<12:23:19,  3.26it/s]
 61%|██████    | 226220/371472 [7:21:15<12:00:16,  3.36it/s]
                                                            
{'loss': 2.6514, 'learning_rate': 4.521051951130169e-07, 'epoch': 9.74}
+
 61%|██████    | 226220/371472 [7:21:15<12:00:16,  3.36it/s]
 61%|██████    | 226221/371472 [7:21:15<11:53:34,  3.39it/s]
 61%|██████    | 226222/371472 [7:21:16<11:50:32,  3.41it/s]
 61%|██████    | 226223/371472 [7:21:16<12:26:10,  3.24it/s]
 61%|██████    | 226224/371472 [7:21:16<12:24:44,  3.25it/s]
 61%|██████    | 226225/371472 [7:21:17<12:07:42,  3.33it/s]
 61%|██████    | 226226/371472 [7:21:17<11:55:31,  3.38it/s]
 61%|██████    | 226227/371472 [7:21:17<12:42:44,  3.17it/s]
 61%|██████    | 226228/371472 [7:21:18<12:26:20,  3.24it/s]
 61%|██████    | 226229/371472 [7:21:18<12:29:16,  3.23it/s]
 61%|██████    | 226230/371472 [7:21:18<12:05:15,  3.34it/s]
 61%|██████    | 226231/371472 [7:21:19<12:01:55,  3.35it/s]
 61%|██████    | 226232/371472 [7:21:19<11:48:32,  3.42it/s]
 61%|██████    | 226233/371472 [7:21:19<12:14:00,  3.30it/s]
 61%|██████    | 226234/371472 [7:21:19<11:49:48,  3.41it/s]
 61%|██████    | 226235/371472 [7:21:20<11:40:16,  3.46it/s]
 61%|██████    | 226236/371472 [7:21:20<11:31:27,  3.50it/s]
 61%|██████    | 226237/371472 [7:21:20<11:32:36,  3.49it/s]
 61%|██████    | 226238/371472 [7:21:21<11:20:58,  3.55it/s]
 61%|██████    | 226239/371472 [7:21:21<12:01:35,  3.35it/s]
 61%|██████    | 226240/371472 [7:21:21<11:36:03,  3.48it/s]
                                                            
{'loss': 2.7835, 'learning_rate': 4.5205671313753795e-07, 'epoch': 9.74}
+
 61%|██████    | 226240/371472 [7:21:21<11:36:03,  3.48it/s]
 61%|██████    | 226241/371472 [7:21:21<11:38:58,  3.46it/s]
 61%|██████    | 226242/371472 [7:21:22<11:28:34,  3.52it/s]
 61%|██████    | 226243/371472 [7:21:22<12:08:31,  3.32it/s]
 61%|██████    | 226244/371472 [7:21:22<14:11:18,  2.84it/s]
 61%|██████    | 226245/371472 [7:21:23<13:36:45,  2.96it/s]
 61%|██████    | 226246/371472 [7:21:23<13:09:31,  3.07it/s]
 61%|██████    | 226247/371472 [7:21:23<12:43:42,  3.17it/s]
 61%|██████    | 226248/371472 [7:21:24<12:41:41,  3.18it/s]
 61%|██████    | 226249/371472 [7:21:24<12:39:29,  3.19it/s]
 61%|██████    | 226250/371472 [7:21:24<12:13:23,  3.30it/s]
 61%|██████    | 226251/371472 [7:21:25<12:04:32,  3.34it/s]
 61%|██████    | 226252/371472 [7:21:25<12:26:39,  3.24it/s]
 61%|██████    | 226253/371472 [7:21:25<15:07:56,  2.67it/s]
 61%|██████    | 226254/371472 [7:21:26<14:00:20,  2.88it/s]
 61%|██████    | 226255/371472 [7:21:26<13:36:30,  2.96it/s]
 61%|██████    | 226256/371472 [7:21:26<13:49:39,  2.92it/s]
 61%|██████    | 226257/371472 [7:21:27<13:29:18,  2.99it/s]
 61%|██████    | 226258/371472 [7:21:27<12:48:18,  3.15it/s]
 61%|██████    | 226259/371472 [7:21:27<12:32:53,  3.21it/s]
 61%|██████    | 226260/371472 [7:21:28<12:32:59,  3.21it/s]
                                                            
{'loss': 2.768, 'learning_rate': 4.5200823116205913e-07, 'epoch': 9.75}
+
 61%|██████    | 226260/371472 [7:21:28<12:32:59,  3.21it/s]
 61%|██████    | 226261/371472 [7:21:28<13:01:45,  3.10it/s]
 61%|██████    | 226262/371472 [7:21:28<12:28:37,  3.23it/s]
 61%|██████    | 226263/371472 [7:21:29<12:31:39,  3.22it/s]
 61%|██████    | 226264/371472 [7:21:29<12:23:30,  3.26it/s]
 61%|██████    | 226265/371472 [7:21:29<12:31:57,  3.22it/s]
 61%|██████    | 226266/371472 [7:21:29<12:25:53,  3.24it/s]
 61%|██████    | 226267/371472 [7:21:30<12:47:56,  3.15it/s]
 61%|██████    | 226268/371472 [7:21:30<12:33:08,  3.21it/s]
 61%|██████    | 226269/371472 [7:21:30<11:59:06,  3.37it/s]
 61%|██████    | 226270/371472 [7:21:31<12:17:57,  3.28it/s]
 61%|██████    | 226271/371472 [7:21:31<12:48:33,  3.15it/s]
 61%|██████    | 226272/371472 [7:21:31<13:18:34,  3.03it/s]
 61%|██████    | 226273/371472 [7:21:32<12:58:53,  3.11it/s]
 61%|██████    | 226274/371472 [7:21:32<13:21:19,  3.02it/s]
 61%|██████    | 226275/371472 [7:21:32<13:55:12,  2.90it/s]
 61%|██████    | 226276/371472 [7:21:33<13:19:42,  3.03it/s]
 61%|██████    | 226277/371472 [7:21:33<12:28:46,  3.23it/s]
 61%|██████    | 226278/371472 [7:21:33<12:12:50,  3.30it/s]
 61%|██████    | 226279/371472 [7:21:34<11:48:55,  3.41it/s]
 61%|██████    | 226280/371472 [7:21:34<12:18:11,  3.28it/s]
                                                            
{'loss': 2.919, 'learning_rate': 4.5195974918658015e-07, 'epoch': 9.75}
+
 61%|██████    | 226280/371472 [7:21:34<12:18:11,  3.28it/s]
 61%|██████    | 226281/371472 [7:21:34<12:14:17,  3.30it/s]
 61%|██████    | 226282/371472 [7:21:34<11:56:15,  3.38it/s]
 61%|██████    | 226283/371472 [7:21:35<11:43:38,  3.44it/s]
 61%|██████    | 226284/371472 [7:21:35<11:23:00,  3.54it/s]
 61%|██████    | 226285/371472 [7:21:35<11:41:43,  3.45it/s]
 61%|██████    | 226286/371472 [7:21:36<12:23:00,  3.26it/s]
 61%|██████    | 226287/371472 [7:21:36<11:59:35,  3.36it/s]
 61%|██████    | 226288/371472 [7:21:36<11:57:50,  3.37it/s]
 61%|██████    | 226289/371472 [7:21:37<11:54:34,  3.39it/s]
 61%|██████    | 226290/371472 [7:21:37<11:42:21,  3.45it/s]
 61%|██████    | 226291/371472 [7:21:37<12:13:05,  3.30it/s]
 61%|██████    | 226292/371472 [7:21:38<13:39:59,  2.95it/s]
 61%|██████    | 226293/371472 [7:21:38<12:59:11,  3.11it/s]
 61%|██████    | 226294/371472 [7:21:38<12:16:40,  3.28it/s]
 61%|██████    | 226295/371472 [7:21:38<12:12:00,  3.31it/s]
 61%|██████    | 226296/371472 [7:21:39<12:21:21,  3.26it/s]
 61%|██████    | 226297/371472 [7:21:39<12:19:11,  3.27it/s]
 61%|██████    | 226298/371472 [7:21:39<12:05:43,  3.33it/s]
 61%|██████    | 226299/371472 [7:21:40<12:04:39,  3.34it/s]
 61%|██████    | 226300/371472 [7:21:40<12:25:48,  3.24it/s]
                                                            
{'loss': 2.9138, 'learning_rate': 4.5191126721110133e-07, 'epoch': 9.75}
+
 61%|██████    | 226300/371472 [7:21:40<12:25:48,  3.24it/s]
 61%|██████    | 226301/371472 [7:21:40<12:16:44,  3.28it/s]
 61%|██████    | 226302/371472 [7:21:40<11:58:48,  3.37it/s]
 61%|██████    | 226303/371472 [7:21:41<11:58:03,  3.37it/s]
 61%|██████    | 226304/371472 [7:21:41<11:47:15,  3.42it/s]
 61%|██████    | 226305/371472 [7:21:41<11:39:13,  3.46it/s]
 61%|██████    | 226306/371472 [7:21:42<11:26:49,  3.52it/s]
 61%|██████    | 226307/371472 [7:21:42<12:04:56,  3.34it/s]
 61%|██████    | 226308/371472 [7:21:42<11:59:54,  3.36it/s]
 61%|██████    | 226309/371472 [7:21:43<11:42:06,  3.45it/s]
 61%|██████    | 226310/371472 [7:21:43<12:36:43,  3.20it/s]
 61%|██████    | 226311/371472 [7:21:43<12:24:46,  3.25it/s]
 61%|██████    | 226312/371472 [7:21:43<11:58:56,  3.37it/s]
 61%|██████    | 226313/371472 [7:21:44<11:49:58,  3.41it/s]
 61%|██████    | 226314/371472 [7:21:44<11:40:51,  3.45it/s]
 61%|██████    | 226315/371472 [7:21:44<12:29:03,  3.23it/s]
 61%|██████    | 226316/371472 [7:21:45<12:01:48,  3.35it/s]
 61%|██████    | 226317/371472 [7:21:45<11:44:49,  3.43it/s]
 61%|██████    | 226318/371472 [7:21:45<11:39:10,  3.46it/s]
 61%|██████    | 226319/371472 [7:21:45<11:39:20,  3.46it/s]
 61%|██████    | 226320/371472 [7:21:46<11:35:37,  3.48it/s]
                                                            
{'loss': 2.7485, 'learning_rate': 4.5186278523562235e-07, 'epoch': 9.75}
+
 61%|██████    | 226320/371472 [7:21:46<11:35:37,  3.48it/s]
 61%|██████    | 226321/371472 [7:21:46<11:41:46,  3.45it/s]
 61%|██████    | 226322/371472 [7:21:46<12:05:20,  3.34it/s]
 61%|██████    | 226323/371472 [7:21:47<12:18:33,  3.28it/s]
 61%|██████    | 226324/371472 [7:21:47<12:24:24,  3.25it/s]
 61%|██████    | 226325/371472 [7:21:47<12:46:17,  3.16it/s]
 61%|██████    | 226326/371472 [7:21:48<12:37:19,  3.19it/s]
 61%|██████    | 226327/371472 [7:21:48<12:25:35,  3.24it/s]
 61%|██████    | 226328/371472 [7:21:48<12:17:01,  3.28it/s]
 61%|██████    | 226329/371472 [7:21:49<12:00:31,  3.36it/s]
 61%|██████    | 226330/371472 [7:21:49<11:40:11,  3.45it/s]
 61%|██████    | 226331/371472 [7:21:49<11:28:07,  3.52it/s]
 61%|██████    | 226332/371472 [7:21:49<11:51:06,  3.40it/s]
 61%|██████    | 226333/371472 [7:21:50<11:39:52,  3.46it/s]
 61%|██████    | 226334/371472 [7:21:50<11:25:50,  3.53it/s]
 61%|██████    | 226335/371472 [7:21:50<11:25:27,  3.53it/s]
 61%|██████    | 226336/371472 [7:21:51<12:24:34,  3.25it/s]
 61%|██████    | 226337/371472 [7:21:51<12:08:17,  3.32it/s]
 61%|██████    | 226338/371472 [7:21:51<12:04:20,  3.34it/s]
 61%|██████    | 226339/371472 [7:21:51<11:54:48,  3.38it/s]
 61%|██████    | 226340/371472 [7:21:52<11:32:52,  3.49it/s]
                                                            
{'loss': 2.6993, 'learning_rate': 4.518143032601435e-07, 'epoch': 9.75}
+
 61%|██████    | 226340/371472 [7:21:52<11:32:52,  3.49it/s]
 61%|██████    | 226341/371472 [7:21:52<11:14:19,  3.59it/s]
 61%|██████    | 226342/371472 [7:21:52<10:57:52,  3.68it/s]
 61%|██████    | 226343/371472 [7:21:53<11:43:24,  3.44it/s]
 61%|██████    | 226344/371472 [7:21:53<12:09:13,  3.32it/s]
 61%|██████    | 226345/371472 [7:21:53<11:54:30,  3.39it/s]
 61%|██████    | 226346/371472 [7:21:54<13:08:29,  3.07it/s]
 61%|██████    | 226347/371472 [7:21:54<12:45:30,  3.16it/s]
 61%|██████    | 226348/371472 [7:21:54<12:24:02,  3.25it/s]
 61%|██████    | 226349/371472 [7:21:55<13:08:59,  3.07it/s]
 61%|██████    | 226350/371472 [7:21:55<12:47:57,  3.15it/s]
 61%|██████    | 226351/371472 [7:21:55<12:21:28,  3.26it/s]
 61%|██████    | 226352/371472 [7:21:55<12:06:33,  3.33it/s]
 61%|██████    | 226353/371472 [7:21:56<11:47:49,  3.42it/s]
 61%|██████    | 226354/371472 [7:21:56<11:53:01,  3.39it/s]
 61%|██████    | 226355/371472 [7:21:56<12:13:17,  3.30it/s]
 61%|██████    | 226356/371472 [7:21:57<12:18:18,  3.28it/s]
 61%|██████    | 226357/371472 [7:21:57<11:49:07,  3.41it/s]
 61%|██████    | 226358/371472 [7:21:57<12:32:21,  3.21it/s]
 61%|██████    | 226359/371472 [7:21:58<12:33:01,  3.21it/s]
 61%|██████    | 226360/371472 [7:21:58<12:11:59,  3.30it/s]
                                                            
{'loss': 2.944, 'learning_rate': 4.517658212846646e-07, 'epoch': 9.75}
+
 61%|██████    | 226360/371472 [7:21:58<12:11:59,  3.30it/s]
 61%|██████    | 226361/371472 [7:21:58<12:12:11,  3.30it/s]
 61%|██████    | 226362/371472 [7:21:58<11:55:01,  3.38it/s]
 61%|██████    | 226363/371472 [7:21:59<11:58:58,  3.36it/s]
 61%|██████    | 226364/371472 [7:21:59<11:42:54,  3.44it/s]
 61%|██████    | 226365/371472 [7:21:59<11:25:55,  3.53it/s]
 61%|██████    | 226366/371472 [7:22:00<11:11:11,  3.60it/s]
 61%|██████    | 226367/371472 [7:22:00<11:08:21,  3.62it/s]
 61%|██████    | 226368/371472 [7:22:00<11:36:46,  3.47it/s]
 61%|██████    | 226369/371472 [7:22:00<11:54:07,  3.39it/s]
 61%|██████    | 226370/371472 [7:22:01<13:25:27,  3.00it/s]
 61%|██████    | 226371/371472 [7:22:01<12:27:44,  3.23it/s]
 61%|██████    | 226372/371472 [7:22:01<12:43:46,  3.17it/s]
 61%|██████    | 226373/371472 [7:22:02<13:16:29,  3.04it/s]
 61%|██████    | 226374/371472 [7:22:02<13:47:36,  2.92it/s]
 61%|██████    | 226375/371472 [7:22:02<13:38:39,  2.95it/s]
 61%|██████    | 226376/371472 [7:22:03<12:49:42,  3.14it/s]
 61%|██████    | 226377/371472 [7:22:03<12:17:11,  3.28it/s]
 61%|██████    | 226378/371472 [7:22:03<11:51:32,  3.40it/s]
 61%|██████    | 226379/371472 [7:22:04<11:34:46,  3.48it/s]
 61%|██████    | 226380/371472 [7:22:04<11:46:40,  3.42it/s]
                                                            
{'loss': 2.892, 'learning_rate': 4.517173393091857e-07, 'epoch': 9.75}
+
 61%|██████    | 226380/371472 [7:22:04<11:46:40,  3.42it/s]
 61%|██████    | 226381/371472 [7:22:04<12:18:11,  3.28it/s]
 61%|██████    | 226382/371472 [7:22:05<12:20:11,  3.27it/s]
 61%|██████    | 226383/371472 [7:22:05<11:46:35,  3.42it/s]
 61%|██████    | 226384/371472 [7:22:05<12:05:52,  3.33it/s]
 61%|██████    | 226385/371472 [7:22:05<12:57:48,  3.11it/s]
 61%|██████    | 226386/371472 [7:22:06<12:23:19,  3.25it/s]
 61%|██████    | 226387/371472 [7:22:06<12:06:45,  3.33it/s]
 61%|██████    | 226388/371472 [7:22:06<11:54:06,  3.39it/s]
 61%|██████    | 226389/371472 [7:22:07<11:42:22,  3.44it/s]
 61%|██████    | 226390/371472 [7:22:07<12:03:48,  3.34it/s]
 61%|██████    | 226391/371472 [7:22:07<11:45:50,  3.43it/s]
 61%|██████    | 226392/371472 [7:22:07<11:43:12,  3.44it/s]
 61%|██████    | 226393/371472 [7:22:08<12:35:03,  3.20it/s]
 61%|██████    | 226394/371472 [7:22:08<12:04:58,  3.34it/s]
 61%|██████    | 226395/371472 [7:22:08<12:08:25,  3.32it/s]
 61%|██████    | 226396/371472 [7:22:09<12:24:13,  3.25it/s]
 61%|██████    | 226397/371472 [7:22:09<12:22:10,  3.26it/s]
 61%|██████    | 226398/371472 [7:22:09<12:58:28,  3.11it/s]
 61%|██████    | 226399/371472 [7:22:10<12:39:59,  3.18it/s]
 61%|██████    | 226400/371472 [7:22:10<12:24:00,  3.25it/s]
                                                            
{'loss': 2.6098, 'learning_rate': 4.516688573337068e-07, 'epoch': 9.75}
+
 61%|██████    | 226400/371472 [7:22:10<12:24:00,  3.25it/s]
 61%|██████    | 226401/371472 [7:22:10<13:04:28,  3.08it/s]
 61%|██████    | 226402/371472 [7:22:11<12:18:25,  3.27it/s]
 61%|██████    | 226403/371472 [7:22:11<12:13:35,  3.30it/s]
 61%|██████    | 226404/371472 [7:22:11<12:11:43,  3.30it/s]
 61%|██████    | 226405/371472 [7:22:11<11:36:22,  3.47it/s]
 61%|██████    | 226406/371472 [7:22:12<11:47:10,  3.42it/s]
 61%|██████    | 226407/371472 [7:22:12<11:46:55,  3.42it/s]
 61%|██████    | 226408/371472 [7:22:12<11:36:34,  3.47it/s]
 61%|██████    | 226409/371472 [7:22:13<11:14:37,  3.58it/s]
 61%|██████    | 226410/371472 [7:22:13<10:54:17,  3.70it/s]
 61%|██████    | 226411/371472 [7:22:13<10:52:30,  3.71it/s]
 61%|██████    | 226412/371472 [7:22:13<11:04:50,  3.64it/s]
 61%|██████    | 226413/371472 [7:22:14<11:34:59,  3.48it/s]
 61%|██████    | 226414/371472 [7:22:14<11:19:18,  3.56it/s]
 61%|██████    | 226415/371472 [7:22:14<11:41:54,  3.44it/s]
 61%|██████    | 226416/371472 [7:22:15<11:34:59,  3.48it/s]
 61%|██████    | 226417/371472 [7:22:15<11:21:29,  3.55it/s]
 61%|██████    | 226418/371472 [7:22:15<11:31:29,  3.50it/s]
 61%|██████    | 226419/371472 [7:22:15<11:15:59,  3.58it/s]
 61%|██████    | 226420/371472 [7:22:16<11:12:41,  3.59it/s]
                                                            
{'loss': 2.7225, 'learning_rate': 4.5162037535822797e-07, 'epoch': 9.75}
+
 61%|██████    | 226420/371472 [7:22:16<11:12:41,  3.59it/s]
 61%|██████    | 226421/371472 [7:22:16<11:30:28,  3.50it/s]
 61%|██████    | 226422/371472 [7:22:16<11:19:05,  3.56it/s]
 61%|██████    | 226423/371472 [7:22:17<11:37:14,  3.47it/s]
 61%|██████    | 226424/371472 [7:22:17<11:27:37,  3.52it/s]
 61%|██████    | 226425/371472 [7:22:17<11:49:33,  3.41it/s]
 61%|██████    | 226426/371472 [7:22:17<11:37:45,  3.46it/s]
 61%|██████    | 226427/371472 [7:22:18<11:34:42,  3.48it/s]
 61%|██████    | 226428/371472 [7:22:18<11:12:06,  3.60it/s]
 61%|██████    | 226429/371472 [7:22:18<11:08:05,  3.62it/s]
 61%|██████    | 226430/371472 [7:22:19<11:05:09,  3.63it/s]
 61%|██████    | 226431/371472 [7:22:19<11:19:23,  3.56it/s]
 61%|██████    | 226432/371472 [7:22:19<11:18:34,  3.56it/s]
 61%|██████    | 226433/371472 [7:22:19<12:21:04,  3.26it/s]
 61%|██████    | 226434/371472 [7:22:20<12:13:11,  3.30it/s]
 61%|██████    | 226435/371472 [7:22:20<11:49:48,  3.41it/s]
 61%|██████    | 226436/371472 [7:22:20<11:59:39,  3.36it/s]
 61%|██████    | 226437/371472 [7:22:21<11:35:41,  3.47it/s]
 61%|██████    | 226438/371472 [7:22:21<12:09:47,  3.31it/s]
 61%|██████    | 226439/371472 [7:22:21<12:17:07,  3.28it/s]
 61%|██████    | 226440/371472 [7:22:22<11:55:34,  3.38it/s]
                                                            
{'loss': 2.8637, 'learning_rate': 4.5157189338274904e-07, 'epoch': 9.75}
+
 61%|██████    | 226440/371472 [7:22:22<11:55:34,  3.38it/s]
 61%|██████    | 226441/371472 [7:22:22<11:50:50,  3.40it/s]
 61%|██████    | 226442/371472 [7:22:22<11:46:41,  3.42it/s]
 61%|██████    | 226443/371472 [7:22:22<11:46:47,  3.42it/s]
 61%|██████    | 226444/371472 [7:22:23<12:14:28,  3.29it/s]
 61%|██████    | 226445/371472 [7:22:23<12:19:03,  3.27it/s]
 61%|██████    | 226446/371472 [7:22:23<12:24:31,  3.25it/s]
 61%|██████    | 226447/371472 [7:22:24<12:39:37,  3.18it/s]
 61%|██████    | 226448/371472 [7:22:24<13:04:02,  3.08it/s]
 61%|██████    | 226449/371472 [7:22:24<12:56:25,  3.11it/s]
 61%|██████    | 226450/371472 [7:22:25<12:58:44,  3.10it/s]
 61%|██████    | 226451/371472 [7:22:25<13:03:15,  3.09it/s]
 61%|██████    | 226452/371472 [7:22:25<12:52:09,  3.13it/s]
 61%|██████    | 226453/371472 [7:22:26<12:23:45,  3.25it/s]
 61%|██████    | 226454/371472 [7:22:26<11:58:59,  3.36it/s]
 61%|██████    | 226455/371472 [7:22:26<11:43:39,  3.43it/s]
 61%|██████    | 226456/371472 [7:22:26<12:16:01,  3.28it/s]
 61%|██████    | 226457/371472 [7:22:27<11:57:42,  3.37it/s]
 61%|██████    | 226458/371472 [7:22:27<11:38:59,  3.46it/s]
 61%|██████    | 226459/371472 [7:22:27<11:48:11,  3.41it/s]
 61%|██████    | 226460/371472 [7:22:28<11:55:39,  3.38it/s]
                                                            
{'loss': 2.9834, 'learning_rate': 4.5152341140727006e-07, 'epoch': 9.75}
+
 61%|██████    | 226460/371472 [7:22:28<11:55:39,  3.38it/s]
 61%|██████    | 226461/371472 [7:22:28<12:23:54,  3.25it/s]
 61%|██████    | 226462/371472 [7:22:28<12:48:10,  3.15it/s]
 61%|██████    | 226463/371472 [7:22:29<12:46:45,  3.15it/s]
 61%|██████    | 226464/371472 [7:22:29<12:13:13,  3.30it/s]
 61%|██████    | 226465/371472 [7:22:29<11:59:00,  3.36it/s]
 61%|██████    | 226466/371472 [7:22:29<11:34:49,  3.48it/s]
 61%|██████    | 226467/371472 [7:22:30<11:24:28,  3.53it/s]
 61%|██████    | 226468/371472 [7:22:30<11:32:45,  3.49it/s]
 61%|██████    | 226469/371472 [7:22:30<11:26:42,  3.52it/s]
 61%|██████    | 226470/371472 [7:22:31<11:21:20,  3.55it/s]
 61%|██████    | 226471/371472 [7:22:31<11:20:32,  3.55it/s]
 61%|██████    | 226472/371472 [7:22:31<11:34:02,  3.48it/s]
 61%|██████    | 226473/371472 [7:22:31<11:24:28,  3.53it/s]
 61%|██████    | 226474/371472 [7:22:32<11:08:58,  3.61it/s]
 61%|██████    | 226475/371472 [7:22:32<11:20:28,  3.55it/s]
 61%|██████    | 226476/371472 [7:22:32<11:49:25,  3.41it/s]
 61%|██████    | 226477/371472 [7:22:33<11:30:14,  3.50it/s]
 61%|██████    | 226478/371472 [7:22:33<11:21:45,  3.54it/s]
 61%|██████    | 226479/371472 [7:22:33<11:11:40,  3.60it/s]
 61%|██████    | 226480/371472 [7:22:33<12:26:41,  3.24it/s]
                                                            
{'loss': 2.8666, 'learning_rate': 4.5147492943179124e-07, 'epoch': 9.75}
+
 61%|██████    | 226480/371472 [7:22:33<12:26:41,  3.24it/s]
 61%|██████    | 226481/371472 [7:22:34<12:12:45,  3.30it/s]
 61%|██████    | 226482/371472 [7:22:34<11:43:51,  3.43it/s]
 61%|█���████    | 226483/371472 [7:22:34<11:42:50,  3.44it/s]
 61%|██████    | 226484/371472 [7:22:35<11:35:22,  3.48it/s]
 61%|██████    | 226485/371472 [7:22:35<11:27:45,  3.51it/s]
 61%|██████    | 226486/371472 [7:22:35<11:24:58,  3.53it/s]
 61%|██████    | 226487/371472 [7:22:35<11:26:02,  3.52it/s]
 61%|██████    | 226488/371472 [7:22:36<11:20:08,  3.55it/s]
 61%|██████    | 226489/371472 [7:22:36<11:31:21,  3.50it/s]
 61%|██████    | 226490/371472 [7:22:36<11:37:32,  3.46it/s]
 61%|██████    | 226491/371472 [7:22:37<11:31:04,  3.50it/s]
 61%|██████    | 226492/371472 [7:22:37<11:24:09,  3.53it/s]
 61%|██████    | 226493/371472 [7:22:37<11:41:22,  3.45it/s]
 61%|██████    | 226494/371472 [7:22:37<11:41:33,  3.44it/s]
 61%|██████    | 226495/371472 [7:22:38<11:28:47,  3.51it/s]
 61%|██████    | 226496/371472 [7:22:38<11:57:16,  3.37it/s]
 61%|██████    | 226497/371472 [7:22:38<12:15:49,  3.28it/s]
 61%|██████    | 226498/371472 [7:22:39<11:52:13,  3.39it/s]
 61%|██████    | 226499/371472 [7:22:39<11:28:25,  3.51it/s]
 61%|██████    | 226500/371472 [7:22:39<12:40:10,  3.18it/s]
                                                            
{'loss': 2.7582, 'learning_rate': 4.514264474563123e-07, 'epoch': 9.76}
+
 61%|██████    | 226500/371472 [7:22:39<12:40:10,  3.18it/s]
 61%|██████    | 226501/371472 [7:22:40<12:19:13,  3.27it/s]
 61%|██████    | 226502/371472 [7:22:40<11:49:28,  3.41it/s]
 61%|██████    | 226503/371472 [7:22:40<12:35:46,  3.20it/s]
 61%|██████    | 226504/371472 [7:22:41<12:34:19,  3.20it/s]
 61%|██████    | 226505/371472 [7:22:41<12:37:06,  3.19it/s]
 61%|██████    | 226506/371472 [7:22:41<12:46:28,  3.15it/s]
 61%|██████    | 226507/371472 [7:22:42<13:10:43,  3.06it/s]
 61%|██████    | 226508/371472 [7:22:42<12:36:59,  3.19it/s]
 61%|██████    | 226509/371472 [7:22:42<12:36:31,  3.19it/s]
 61%|██████    | 226510/371472 [7:22:42<12:17:01,  3.28it/s]
 61%|██████    | 226511/371472 [7:22:43<11:46:31,  3.42it/s]
 61%|██████    | 226512/371472 [7:22:43<11:20:56,  3.55it/s]
 61%|██████    | 226513/371472 [7:22:43<11:20:24,  3.55it/s]
 61%|██████    | 226514/371472 [7:22:43<11:35:16,  3.47it/s]
 61%|██████    | 226515/371472 [7:22:44<11:16:33,  3.57it/s]
 61%|██████    | 226516/371472 [7:22:44<11:10:58,  3.60it/s]
 61%|██████    | 226517/371472 [7:22:44<11:29:44,  3.50it/s]
 61%|██████    | 226518/371472 [7:22:45<11:29:42,  3.50it/s]
 61%|██████    | 226519/371472 [7:22:45<11:15:59,  3.57it/s]
 61%|██████    | 226520/371472 [7:22:45<11:20:54,  3.55it/s]
                                                            
{'loss': 2.7784, 'learning_rate': 4.5137796548083343e-07, 'epoch': 9.76}
+
 61%|██████    | 226520/371472 [7:22:45<11:20:54,  3.55it/s]
 61%|██████    | 226521/371472 [7:22:45<11:56:54,  3.37it/s]
 61%|██████    | 226522/371472 [7:22:46<12:18:35,  3.27it/s]
 61%|██████    | 226523/371472 [7:22:46<13:27:02,  2.99it/s]
 61%|██████    | 226524/371472 [7:22:46<12:36:15,  3.19it/s]
 61%|██████    | 226525/371472 [7:22:47<12:07:07,  3.32it/s]
 61%|██████    | 226526/371472 [7:22:47<11:59:06,  3.36it/s]
 61%|██████    | 226527/371472 [7:22:47<11:57:23,  3.37it/s]
 61%|██████    | 226528/371472 [7:22:48<12:02:23,  3.34it/s]
 61%|██████    | 226529/371472 [7:22:48<11:34:52,  3.48it/s]
 61%|██████    | 226530/371472 [7:22:48<11:56:02,  3.37it/s]
 61%|██████    | 226531/371472 [7:22:49<11:50:11,  3.40it/s]
 61%|██████    | 226532/371472 [7:22:49<11:49:19,  3.41it/s]
 61%|██████    | 226533/371472 [7:22:49<11:30:31,  3.50it/s]
 61%|██████    | 226534/371472 [7:22:49<11:38:52,  3.46it/s]
 61%|██████    | 226535/371472 [7:22:50<11:48:23,  3.41it/s]
 61%|██████    | 226536/371472 [7:22:50<11:19:59,  3.55it/s]
 61%|██████    | 226537/371472 [7:22:50<11:18:21,  3.56it/s]
 61%|██████    | 226538/371472 [7:22:50<11:20:17,  3.55it/s]
 61%|██████    | 226539/371472 [7:22:51<11:34:02,  3.48it/s]
 61%|██████    | 226540/371472 [7:22:51<13:12:44,  3.05it/s]
                                                            
{'loss': 2.8077, 'learning_rate': 4.513294835053545e-07, 'epoch': 9.76}
+
 61%|██████    | 226540/371472 [7:22:51<13:12:44,  3.05it/s]
 61%|██████    | 226541/371472 [7:22:52<13:21:53,  3.01it/s]
 61%|██████    | 226542/371472 [7:22:52<13:08:37,  3.06it/s]
 61%|██████    | 226543/371472 [7:22:52<13:37:52,  2.95it/s]
 61%|██████    | 226544/371472 [7:22:53<12:55:34,  3.11it/s]
 61%|██████    | 226545/371472 [7:22:53<12:14:30,  3.29it/s]
 61%|██████    | 226546/371472 [7:22:53<12:13:51,  3.29it/s]
 61%|██████    | 226547/371472 [7:22:53<11:59:17,  3.36it/s]
 61%|██████    | 226548/371472 [7:22:54<11:57:41,  3.37it/s]
 61%|██████    | 226549/371472 [7:22:54<11:50:53,  3.40it/s]
 61%|██████    | 226550/371472 [7:22:54<11:39:55,  3.45it/s]
 61%|██████    | 226551/371472 [7:22:55<12:09:04,  3.31it/s]
 61%|██████    | 226552/371472 [7:22:55<11:53:28,  3.39it/s]
 61%|██████    | 226553/371472 [7:22:55<11:45:49,  3.42it/s]
 61%|██████    | 226554/371472 [7:22:55<11:50:09,  3.40it/s]
 61%|██████    | 226555/371472 [7:22:56<11:49:05,  3.41it/s]
 61%|██████    | 226556/371472 [7:22:56<12:11:21,  3.30it/s]
 61%|██████    | 226557/371472 [7:22:56<12:21:03,  3.26it/s]
 61%|██████    | 226558/371472 [7:22:57<12:10:30,  3.31it/s]
 61%|██████    | 226559/371472 [7:22:57<11:56:34,  3.37it/s]
 61%|██████    | 226560/371472 [7:22:57<12:31:26,  3.21it/s]
                                                            
{'loss': 2.8165, 'learning_rate': 4.512810015298757e-07, 'epoch': 9.76}
+
 61%|██████    | 226560/371472 [7:22:57<12:31:26,  3.21it/s]
 61%|██████    | 226561/371472 [7:22:58<12:21:08,  3.26it/s]
 61%|██████    | 226562/371472 [7:22:58<12:11:39,  3.30it/s]
 61%|██████    | 226563/371472 [7:22:58<11:46:08,  3.42it/s]
 61%|██████    | 226564/371472 [7:22:58<11:36:52,  3.47it/s]
 61%|██████    | 226565/371472 [7:22:59<11:31:15,  3.49it/s]
 61%|██████    | 226566/371472 [7:22:59<11:24:38,  3.53it/s]
 61%|██████    | 226567/371472 [7:22:59<11:20:51,  3.55it/s]
 61%|██████    | 226568/371472 [7:23:00<11:09:04,  3.61it/s]
 61%|██████    | 226569/371472 [7:23:00<11:01:29,  3.65it/s]
 61%|██████    | 226570/371472 [7:23:00<11:11:44,  3.60it/s]
 61%|██████    | 226571/371472 [7:23:00<11:41:27,  3.44it/s]
 61%|██████    | 226572/371472 [7:23:01<11:40:30,  3.45it/s]
 61%|██████    | 226573/371472 [7:23:01<11:33:08,  3.48it/s]
 61%|██████    | 226574/371472 [7:23:01<12:01:21,  3.35it/s]
 61%|██████    | 226575/371472 [7:23:02<12:43:37,  3.16it/s]
 61%|██████    | 226576/371472 [7:23:02<12:22:03,  3.25it/s]
 61%|██████    | 226577/371472 [7:23:02<12:13:09,  3.29it/s]
 61%|██████    | 226578/371472 [7:23:03<11:57:01,  3.37it/s]
 61%|██████    | 226579/371472 [7:23:03<11:47:23,  3.41it/s]
 61%|██████    | 226580/371472 [7:23:03<12:10:27,  3.31it/s]
                                                            
{'loss': 2.779, 'learning_rate': 4.512325195543967e-07, 'epoch': 9.76}
+
 61%|██████    | 226580/371472 [7:23:03<12:10:27,  3.31it/s]
 61%|██████    | 226581/371472 [7:23:03<11:44:50,  3.43it/s]
 61%|██████    | 226582/371472 [7:23:04<12:04:28,  3.33it/s]
 61%|██████    | 226583/371472 [7:23:04<11:49:58,  3.40it/s]
 61%|██████    | 226584/371472 [7:23:04<11:54:19,  3.38it/s]
 61%|██████    | 226585/371472 [7:23:05<11:49:49,  3.40it/s]
 61%|██████    | 226586/371472 [7:23:05<11:39:25,  3.45it/s]
 61%|██████    | 226587/371472 [7:23:05<11:35:28,  3.47it/s]
 61%|██████    | 226588/371472 [7:23:05<11:36:33,  3.47it/s]
 61%|██████    | 226589/371472 [7:23:06<11:32:59,  3.48it/s]
 61%|██████    | 226590/371472 [7:23:06<11:35:36,  3.47it/s]
 61%|██████    | 226591/371472 [7:23:06<11:33:20,  3.48it/s]
 61%|██████    | 226592/371472 [7:23:07<11:59:41,  3.36it/s]
 61%|██████    | 226593/371472 [7:23:07<11:47:11,  3.41it/s]
 61%|██████    | 226594/371472 [7:23:07<11:45:40,  3.42it/s]
 61%|██████    | 226595/371472 [7:23:08<12:27:57,  3.23it/s]
 61%|██████    | 226596/371472 [7:23:08<12:09:49,  3.31it/s]
 61%|██████    | 226597/371472 [7:23:08<12:04:01,  3.33it/s]
 61%|██████    | 226598/371472 [7:23:08<12:00:36,  3.35it/s]
 61%|██████    | 226599/371472 [7:23:09<12:02:03,  3.34it/s]
 61%|██████    | 226600/371472 [7:23:09<11:29:31,  3.50it/s]
                                                            
{'loss': 2.6152, 'learning_rate': 4.511840375789179e-07, 'epoch': 9.76}
+
 61%|██████    | 226600/371472 [7:23:09<11:29:31,  3.50it/s]
 61%|██████    | 226601/371472 [7:23:09<11:37:23,  3.46it/s]
 61%|██████    | 226602/371472 [7:23:10<11:44:54,  3.43it/s]
 61%|██████    | 226603/371472 [7:23:10<11:33:52,  3.48it/s]
 61%|██████    | 226604/371472 [7:23:10<11:46:09,  3.42it/s]
 61%|██████    | 226605/371472 [7:23:10<11:43:17,  3.43it/s]
 61%|█████��    | 226606/371472 [7:23:11<13:44:33,  2.93it/s]
 61%|██████    | 226607/371472 [7:23:11<12:59:42,  3.10it/s]
 61%|██████    | 226608/371472 [7:23:11<12:35:50,  3.19it/s]
 61%|██████    | 226609/371472 [7:23:12<12:45:15,  3.15it/s]
 61%|██████    | 226610/371472 [7:23:12<12:18:00,  3.27it/s]
 61%|██████    | 226611/371472 [7:23:12<11:44:58,  3.42it/s]
 61%|██████    | 226612/371472 [7:23:13<11:31:52,  3.49it/s]
 61%|██████    | 226613/371472 [7:23:13<11:26:32,  3.52it/s]
 61%|██████    | 226614/371472 [7:23:13<11:10:16,  3.60it/s]
 61%|██████    | 226615/371472 [7:23:13<11:11:32,  3.60it/s]
 61%|██████    | 226616/371472 [7:23:14<12:03:03,  3.34it/s]
 61%|██████    | 226617/371472 [7:23:14<11:38:59,  3.45it/s]
 61%|██████    | 226618/371472 [7:23:14<11:31:13,  3.49it/s]
 61%|██████    | 226619/371472 [7:23:15<11:28:12,  3.51it/s]
 61%|██████    | 226620/371472 [7:23:15<11:25:05,  3.52it/s]
                                                            
{'loss': 2.727, 'learning_rate': 4.5113555560343895e-07, 'epoch': 9.76}
+
 61%|██████    | 226620/371472 [7:23:15<11:25:05,  3.52it/s]
 61%|██████    | 226621/371472 [7:23:15<11:29:48,  3.50it/s]
 61%|██████    | 226622/371472 [7:23:15<11:16:19,  3.57it/s]
 61%|██████    | 226623/371472 [7:23:16<11:35:08,  3.47it/s]
 61%|██████    | 226624/371472 [7:23:16<11:23:59,  3.53it/s]
 61%|██████    | 226625/371472 [7:23:16<11:37:07,  3.46it/s]
 61%|██████    | 226626/371472 [7:23:17<12:56:04,  3.11it/s]
 61%|██████    | 226627/371472 [7:23:17<12:15:45,  3.28it/s]
 61%|██████    | 226628/371472 [7:23:17<12:16:11,  3.28it/s]
 61%|██████    | 226629/371472 [7:23:18<12:17:53,  3.27it/s]
 61%|██████    | 226630/371472 [7:23:18<12:23:29,  3.25it/s]
 61%|██████    | 226631/371472 [7:23:18<12:03:33,  3.34it/s]
 61%|██████    | 226632/371472 [7:23:18<11:45:15,  3.42it/s]
 61%|██████    | 226633/371472 [7:23:19<11:44:57,  3.42it/s]
 61%|██████    | 226634/371472 [7:23:19<11:42:08,  3.44it/s]
 61%|██████    | 226635/371472 [7:23:19<12:04:48,  3.33it/s]
 61%|██████    | 226636/371472 [7:23:20<11:56:27,  3.37it/s]
 61%|██████    | 226637/371472 [7:23:20<11:29:53,  3.50it/s]
 61%|██████    | 226638/371472 [7:23:20<12:28:09,  3.23it/s]
 61%|██████    | 226639/371472 [7:23:21<12:12:57,  3.29it/s]
 61%|██████    | 226640/371472 [7:23:21<12:16:30,  3.28it/s]
                                                            
{'loss': 2.7786, 'learning_rate': 4.5108707362796007e-07, 'epoch': 9.76}
+
 61%|██████    | 226640/371472 [7:23:21<12:16:30,  3.28it/s]
 61%|██████    | 226641/371472 [7:23:21<12:34:20,  3.20it/s]
 61%|██████    | 226642/371472 [7:23:22<12:49:13,  3.14it/s]
 61%|██████    | 226643/371472 [7:23:22<12:28:52,  3.22it/s]
 61%|██████    | 226644/371472 [7:23:22<12:07:34,  3.32it/s]
 61%|██████    | 226645/371472 [7:23:22<11:37:16,  3.46it/s]
 61%|██████    | 226646/371472 [7:23:23<12:13:47,  3.29it/s]
 61%|██████    | 226647/371472 [7:23:23<12:01:23,  3.35it/s]
 61%|██████    | 226648/371472 [7:23:23<11:53:54,  3.38it/s]
 61%|██████    | 226649/371472 [7:23:24<11:46:06,  3.42it/s]
 61%|██████    | 226650/371472 [7:23:24<11:46:18,  3.42it/s]
 61%|██████    | 226651/371472 [7:23:24<11:34:14,  3.48it/s]
 61%|██████    | 226652/371472 [7:23:24<11:47:54,  3.41it/s]
 61%|██████    | 226653/371472 [7:23:25<11:38:01,  3.46it/s]
 61%|██████    | 226654/371472 [7:23:25<12:14:23,  3.29it/s]
 61%|██████    | 226655/371472 [7:23:25<11:54:13,  3.38it/s]
 61%|██████    | 226656/371472 [7:23:26<12:20:14,  3.26it/s]
 61%|██████    | 226657/371472 [7:23:26<11:49:10,  3.40it/s]
 61%|██████    | 226658/371472 [7:23:26<11:35:26,  3.47it/s]
 61%|██████    | 226659/371472 [7:23:26<11:31:17,  3.49it/s]
 61%|██████    | 226660/371472 [7:23:27<11:17:50,  3.56it/s]
                                                            
{'loss': 2.8263, 'learning_rate': 4.5103859165248114e-07, 'epoch': 9.76}
+
 61%|██████    | 226660/371472 [7:23:27<11:17:50,  3.56it/s]
 61%|██████    | 226661/371472 [7:23:27<11:32:27,  3.49it/s]
 61%|██████    | 226662/371472 [7:23:27<11:54:27,  3.38it/s]
 61%|██████    | 226663/371472 [7:23:28<12:58:19,  3.10it/s]
 61%|██████    | 226664/371472 [7:23:28<13:20:30,  3.01it/s]
 61%|██████    | 226665/371472 [7:23:28<12:51:25,  3.13it/s]
 61%|██████    | 226666/371472 [7:23:29<12:25:56,  3.24it/s]
 61%|██████    | 226667/371472 [7:23:29<12:03:41,  3.33it/s]
 61%|██████    | 226668/371472 [7:23:29<12:30:16,  3.22it/s]
 61%|██████    | 226669/371472 [7:23:30<12:03:59,  3.33it/s]
 61%|██████    | 226670/371472 [7:23:30<12:54:23,  3.12it/s]
 61%|██████    | 226671/371472 [7:23:30<13:26:46,  2.99it/s]
 61%|██████    | 226672/371472 [7:23:31<13:10:22,  3.05it/s]
 61%|██████    | 226673/371472 [7:23:31<12:49:41,  3.14it/s]
 61%|██████    | 226674/371472 [7:23:31<12:17:05,  3.27it/s]
 61%|██████    | 226675/371472 [7:23:31<12:10:29,  3.30it/s]
 61%|██████    | 226676/371472 [7:23:32<12:00:34,  3.35it/s]
 61%|██████    | 226677/371472 [7:23:32<12:14:11,  3.29it/s]
 61%|██████    | 226678/371472 [7:23:32<11:57:22,  3.36it/s]
 61%|██████    | 226679/371472 [7:23:33<11:55:25,  3.37it/s]
 61%|██████    | 226680/371472 [7:23:33<11:51:31,  3.39it/s]
                                                            
{'loss': 2.759, 'learning_rate': 4.5099010967700227e-07, 'epoch': 9.76}
+
 61%|██████    | 226680/371472 [7:23:33<11:51:31,  3.39it/s]
 61%|██████    | 226681/371472 [7:23:33<11:55:28,  3.37it/s]
 61%|██████    | 226682/371472 [7:23:34<11:54:46,  3.38it/s]
 61%|██████    | 226683/371472 [7:23:34<11:43:10,  3.43it/s]
 61%|██████    | 226684/371472 [7:23:34<11:45:27,  3.42it/s]
 61%|██████    | 226685/371472 [7:23:34<11:40:16,  3.45it/s]
 61%|██████    | 226686/371472 [7:23:35<11:25:44,  3.52it/s]
 61%|██████    | 226687/371472 [7:23:35<11:25:41,  3.52it/s]
 61%|██████    | 226688/371472 [7:23:35<11:15:52,  3.57it/s]
 61%|██████    | 226689/371472 [7:23:36<11:31:09,  3.49it/s]
 61%|██████    | 226690/371472 [7:23:36<11:46:13,  3.42it/s]
 61%|██████    | 226691/371472 [7:23:36<11:56:59,  3.37it/s]
 61%|██████    | 226692/371472 [7:23:37<12:46:51,  3.15it/s]
 61%|██████    | 226693/371472 [7:23:37<12:32:57,  3.20it/s]
 61%|██████    | 226694/371472 [7:23:37<12:03:34,  3.33it/s]
 61%|██████    | 226695/371472 [7:23:37<12:14:17,  3.29it/s]
 61%|██████    | 226696/371472 [7:23:38<12:18:50,  3.27it/s]
 61%|██████    | 226697/371472 [7:23:38<12:08:53,  3.31it/s]
 61%|██████    | 226698/371472 [7:23:38<12:04:57,  3.33it/s]
 61%|██████    | 226699/371472 [7:23:39<11:42:23,  3.44it/s]
 61%|██████    | 226700/371472 [7:23:39<11:25:40,  3.52it/s]
                                                            
{'loss': 2.9038, 'learning_rate': 4.5094162770152334e-07, 'epoch': 9.76}
+
 61%|██████    | 226700/371472 [7:23:39<11:25:40,  3.52it/s]
 61%|██████    | 226701/371472 [7:23:39<11:10:52,  3.60it/s]
 61%|██████    | 226702/371472 [7:23:39<11:50:42,  3.39it/s]
 61%|██████    | 226703/371472 [7:23:40<11:56:01,  3.37it/s]
 61%|██████    | 226704/371472 [7:23:40<11:58:54,  3.36it/s]
 61%|██████    | 226705/371472 [7:23:40<12:05:01,  3.33it/s]
 61%|██████    | 226706/371472 [7:23:41<11:56:15,  3.37it/s]
 61%|██████    | 226707/371472 [7:23:41<11:49:19,  3.40it/s]
 61%|██████    | 226708/371472 [7:23:41<12:40:09,  3.17it/s]
 61%|██████    | 226709/371472 [7:23:42<12:37:16,  3.19it/s]
 61%|██████    | 226710/371472 [7:23:42<12:20:20,  3.26it/s]
 61%|██████    | 226711/371472 [7:23:42<12:02:29,  3.34it/s]
 61%|██████    | 226712/371472 [7:23:43<12:55:42,  3.11it/s]
 61%|██████    | 226713/371472 [7:23:43<13:25:40,  2.99it/s]
 61%|██████    | 226714/371472 [7:23:43<12:50:49,  3.13it/s]
 61%|██████    | 226715/371472 [7:23:43<12:24:47,  3.24it/s]
 61%|██████    | 226716/371472 [7:23:44<12:02:39,  3.34it/s]
 61%|██████    | 226717/371472 [7:23:44<12:25:19,  3.24it/s]
 61%|██████    | 226718/371472 [7:23:44<11:57:15,  3.36it/s]
 61%|██████    | 226719/371472 [7:23:45<11:49:22,  3.40it/s]
 61%|██████    | 226720/371472 [7:23:45<11:48:11,  3.41it/s]
                                                            
{'loss': 2.7489, 'learning_rate': 4.508931457260445e-07, 'epoch': 9.77}
+
 61%|██████    | 226720/371472 [7:23:45<11:48:11,  3.41it/s]
 61%|██████    | 226721/371472 [7:23:45<11:48:21,  3.41it/s]
 61%|██████    | 226722/371472 [7:23:46<11:48:07,  3.41it/s]
 61%|██████    | 226723/371472 [7:23:46<11:48:21,  3.41it/s]
 61%|██████    | 226724/371472 [7:23:46<11:20:36,  3.54it/s]
 61%|██████    | 226725/371472 [7:23:46<11:01:36,  3.65it/s]
 61%|██████    | 226726/371472 [7:23:47<11:36:59,  3.46it/s]
 61%|██████    | 226727/371472 [7:23:47<11:19:32,  3.55it/s]
 61%|██████    | 226728/371472 [7:23:47<11:11:07,  3.59it/s]
 61%|██████    | 226729/371472 [7:23:48<12:03:08,  3.34it/s]
 61%|██████    | 226730/371472 [7:23:48<11:32:31,  3.48it/s]
 61%|██████    | 226731/371472 [7:23:48<11:20:02,  3.55it/s]
 61%|██████    | 226732/371472 [7:23:48<10:58:40,  3.66it/s]
 61%|██████    | 226733/371472 [7:23:49<11:10:27,  3.60it/s]
 61%|██████    | 226734/371472 [7:23:49<11:40:44,  3.44it/s]
 61%|██████    | 226735/371472 [7:23:49<11:51:06,  3.39it/s]
 61%|██████    | 226736/371472 [7:23:50<11:53:10,  3.38it/s]
 61%|██████    | 226737/371472 [7:23:50<11:37:54,  3.46it/s]
 61%|██████    | 226738/371472 [7:23:50<11:34:19,  3.47it/s]
 61%|██████    | 226739/371472 [7:23:50<11:53:20,  3.38it/s]
 61%|██████    | 226740/371472 [7:23:51<11:42:01,  3.44it/s]
                                                            
{'loss': 2.7452, 'learning_rate': 4.508446637505656e-07, 'epoch': 9.77}
+
 61%|██████    | 226740/371472 [7:23:51<11:42:01,  3.44it/s]
 61%|██████    | 226741/371472 [7:23:51<11:52:33,  3.39it/s]
 61%|██████    | 226742/371472 [7:23:51<11:38:42,  3.45it/s]
 61%|██████    | 226743/371472 [7:23:52<11:40:50,  3.44it/s]
 61%|██████    | 226744/371472 [7:23:52<11:26:42,  3.51it/s]
 61%|██████    | 226745/371472 [7:23:52<11:23:17,  3.53it/s]
 61%|██████    | 226746/371472 [7:23:52<11:23:44,  3.53it/s]
 61%|██████    | 226747/371472 [7:23:53<11:01:20,  3.65it/s]
 61%|██████    | 226748/371472 [7:23:53<11:11:15,  3.59it/s]
 61%|██████    | 226749/371472 [7:23:53<10:55:29,  3.68it/s]
 61%|██████    | 226750/371472 [7:23:54<11:25:59,  3.52it/s]
 61%|██████    | 226751/371472 [7:23:54<10:59:35,  3.66it/s]
 61%|██████    | 226752/371472 [7:23:54<11:40:38,  3.44it/s]
 61%|██████    | 226753/371472 [7:23:54<11:33:34,  3.48it/s]
 61%|██████    | 226754/371472 [7:23:55<11:36:41,  3.46it/s]
 61%|██████    | 226755/371472 [7:23:55<12:41:38,  3.17it/s]
 61%|██████    | 226756/371472 [7:23:55<12:47:27,  3.14it/s]
 61%|██████    | 226757/371472 [7:23:56<12:39:47,  3.17it/s]
 61%|██████    | 226758/371472 [7:23:56<11:58:53,  3.35it/s]
 61%|██████    | 226759/371472 [7:23:56<11:51:03,  3.39it/s]
 61%|██████    | 226760/371472 [7:23:57<11:50:21,  3.40it/s]
                                                            
{'loss': 2.7395, 'learning_rate': 4.507961817750867e-07, 'epoch': 9.77}
+
 61%|██████    | 226760/371472 [7:23:57<11:50:21,  3.40it/s]
 61%|██████    | 226761/371472 [7:23:57<11:22:41,  3.53it/s]
 61%|██████    | 226762/371472 [7:23:57<11:40:40,  3.44it/s]
 61%|██████    | 226763/371472 [7:23:57<11:46:44,  3.41it/s]
 61%|██████    | 226764/371472 [7:23:58<11:38:02,  3.46it/s]
 61%|██████    | 226765/371472 [7:23:58<11:44:02,  3.43it/s]
 61%|██████    | 226766/371472 [7:23:58<11:27:27,  3.51it/s]
 61%|██████    | 226767/371472 [7:23:59<12:04:48,  3.33it/s]
 61%|██████    | 226768/371472 [7:23:59<12:04:21,  3.33it/s]
 61%|██████    | 226769/371472 [7:23:59<12:36:37,  3.19it/s]
 61%|██████    | 226770/371472 [7:24:00<13:23:02,  3.00it/s]
 61%|██████    | 226771/371472 [7:24:00<13:25:35,  2.99it/s]
 61%|██████    | 226772/371472 [7:24:00<12:59:39,  3.09it/s]
 61%|██████    | 226773/371472 [7:24:01<13:18:53,  3.02it/s]
 61%|██████    | 226774/371472 [7:24:01<12:36:26,  3.19it/s]
 61%|██████    | 226775/371472 [7:24:01<12:05:53,  3.32it/s]
 61%|██████    | 226776/371472 [7:24:01<11:44:53,  3.42it/s]
 61%|██████    | 226777/371472 [7:24:02<11:39:53,  3.45it/s]
 61%|██████    | 226778/371472 [7:24:02<11:35:28,  3.47it/s]
 61%|██████    | 226779/371472 [7:24:02<11:28:54,  3.50it/s]
 61%|██████    | 226780/371472 [7:24:03<11:55:30,  3.37it/s]
                                                            
{'loss': 2.7063, 'learning_rate': 4.507476997996078e-07, 'epoch': 9.77}
+
 61%|██████    | 226780/371472 [7:24:03<11:55:30,  3.37it/s]
 61%|██████    | 226781/371472 [7:24:03<12:18:31,  3.27it/s]
 61%|██████    | 226782/371472 [7:24:03<11:48:04,  3.41it/s]
 61%|██████    | 226783/371472 [7:24:03<12:03:55,  3.33it/s]
 61%|██████    | 226784/371472 [7:24:04<11:32:16,  3.48it/s]
 61%|██████    | 226785/371472 [7:24:04<11:30:03,  3.49it/s]
 61%|██████    | 226786/371472 [7:24:04<11:37:51,  3.46it/s]
 61%|██████    | 226787/371472 [7:24:05<11:15:01,  3.57it/s]
 61%|██████    | 226788/371472 [7:24:05<11:15:47,  3.57it/s]
 61%|██████    | 226789/371472 [7:24:05<11:15:44,  3.57it/s]
 61%|██████    | 226790/371472 [7:24:05<11:36:51,  3.46it/s]
 61%|██████    | 226791/371472 [7:24:06<11:23:10,  3.53it/s]
 61%|██████    | 226792/371472 [7:24:06<11:38:42,  3.45it/s]
 61%|██████    | 226793/371472 [7:24:06<11:40:00,  3.44it/s]
 61%|██████    | 226794/371472 [7:24:07<11:56:10,  3.37it/s]
 61%|██████    | 226795/371472 [7:24:07<11:58:27,  3.36it/s]
 61%|██████    | 226796/371472 [7:24:07<11:42:08,  3.43it/s]
 61%|██████    | 226797/371472 [7:24:07<11:49:43,  3.40it/s]
 61%|██████    | 226798/371472 [7:24:08<12:03:32,  3.33it/s]
 61%|██████    | 226799/371472 [7:24:08<12:17:34,  3.27it/s]
 61%|██████    | 226800/371472 [7:24:08<12:41:23,  3.17it/s]
                                                            
{'loss': 2.7776, 'learning_rate': 4.5069921782412896e-07, 'epoch': 9.77}
+
 61%|██████    | 226800/371472 [7:24:08<12:41:23,  3.17it/s]
 61%|██████    | 226801/371472 [7:24:09<13:18:11,  3.02it/s]
 61%|██████    | 226802/371472 [7:24:09<12:53:22,  3.12it/s]
 61%|██████    | 226803/371472 [7:24:09<12:06:54,  3.32it/s]
 61%|██████    | 226804/371472 [7:24:10<13:21:18,  3.01it/s]
 61%|██████    | 226805/371472 [7:24:10<12:39:13,  3.18it/s]
 61%|██████    | 226806/371472 [7:24:10<12:16:44,  3.27it/s]
 61%|██████    | 226807/371472 [7:24:11<11:59:08,  3.35it/s]
 61%|██████    | 226808/371472 [7:24:11<11:42:18,  3.43it/s]
 61%|██████    | 226809/371472 [7:24:11<11:54:36,  3.37it/s]
 61%|██████    | 226810/371472 [7:24:11<11:45:53,  3.42it/s]
 61%|██████    | 226811/371472 [7:24:12<11:35:04,  3.47it/s]
 61%|██████    | 226812/371472 [7:24:12<11:29:10,  3.50it/s]
 61%|██████    | 226813/371472 [7:24:12<11:34:21,  3.47it/s]
 61%|██████    | 226814/371472 [7:24:13<11:29:34,  3.50it/s]
 61%|██████    | 226815/371472 [7:24:13<11:50:53,  3.39it/s]
 61%|██████    | 226816/371472 [7:24:13<11:58:41,  3.35it/s]
 61%|██████    | 226817/371472 [7:24:14<11:43:25,  3.43it/s]
 61%|██████    | 226818/371472 [7:24:14<12:03:57,  3.33it/s]
 61%|██████    | 226819/371472 [7:24:14<11:55:11,  3.37it/s]
 61%|██████    | 226820/371472 [7:24:14<11:50:58,  3.39it/s]
                                                            
{'loss': 2.8116, 'learning_rate': 4.5065073584865003e-07, 'epoch': 9.77}
+
 61%|██████    | 226820/371472 [7:24:14<11:50:58,  3.39it/s]
 61%|██████    | 226821/371472 [7:24:15<11:44:42,  3.42it/s]
 61%|██████    | 226822/371472 [7:24:15<11:36:40,  3.46it/s]
 61%|██████    | 226823/371472 [7:24:15<12:55:28,  3.11it/s]
 61%|██████    | 226824/371472 [7:24:16<12:36:31,  3.19it/s]
 61%|██████    | 226825/371472 [7:24:16<12:21:27,  3.25it/s]
 61%|██████    | 226826/371472 [7:24:16<12:23:22,  3.24it/s]
 61%|██████    | 226827/371472 [7:24:17<11:58:46,  3.35it/s]
 61%|██████    | 226828/371472 [7:24:17<11:36:07,  3.46it/s]
 61%|██████    | 226829/371472 [7:24:17<11:28:52,  3.50it/s]
 61%|██████    | 226830/371472 [7:24:17<11:55:48,  3.37it/s]
 61%|██████    | 226831/371472 [7:24:18<11:59:01,  3.35it/s]
 61%|██████    | 226832/371472 [7:24:18<11:54:03,  3.38it/s]
 61%|██████    | 226833/371472 [7:24:18<11:37:02,  3.46it/s]
 61%|██████    | 226834/371472 [7:24:19<11:21:46,  3.54it/s]
 61%|██████    | 226835/371472 [7:24:19<11:25:35,  3.52it/s]
 61%|██████    | 226836/371472 [7:24:19<11:26:50,  3.51it/s]
 61%|██████    | 226837/371472 [7:24:19<11:25:02,  3.52it/s]
 61%|██████    | 226838/371472 [7:24:20<12:04:43,  3.33it/s]
 61%|██████    | 226839/371472 [7:24:20<12:19:57,  3.26it/s]
 61%|██████    | 226840/371472 [7:24:20<12:16:10,  3.27it/s]
                                                            
{'loss': 2.9207, 'learning_rate': 4.5060225387317116e-07, 'epoch': 9.77}
+
 61%|██████    | 226840/371472 [7:24:20<12:16:10,  3.27it/s]
 61%|██████    | 226841/371472 [7:24:21<13:00:44,  3.09it/s]
 61%|██████    | 226842/371472 [7:24:21<12:49:01,  3.13it/s]
 61%|██████    | 226843/371472 [7:24:21<12:39:20,  3.17it/s]
 61%|██████    | 226844/371472 [7:24:22<12:13:52,  3.28it/s]
 61%|██████    | 226845/371472 [7:24:22<11:51:47,  3.39it/s]
 61%|██████    | 226846/371472 [7:24:22<12:07:22,  3.31it/s]
 61%|██████    | 226847/371472 [7:24:23<12:07:02,  3.32it/s]
 61%|██████    | 226848/371472 [7:24:23<11:57:41,  3.36it/s]
 61%|██████    | 226849/371472 [7:24:23<11:49:14,  3.40it/s]
 61%|██████    | 226850/371472 [7:24:23<11:41:07,  3.44it/s]
 61%|██████    | 226851/371472 [7:24:24<11:25:50,  3.51it/s]
 61%|██████    | 226852/371472 [7:24:24<11:17:47,  3.56it/s]
 61%|██████    | 226853/371472 [7:24:24<11:13:55,  3.58it/s]
 61%|██████    | 226854/371472 [7:24:25<11:41:56,  3.43it/s]
 61%|██████    | 226855/371472 [7:24:25<11:34:14,  3.47it/s]
 61%|██████    | 226856/371472 [7:24:25<11:32:10,  3.48it/s]
 61%|██████    | 226857/371472 [7:24:25<11:37:29,  3.46it/s]
 61%|██████    | 226858/371472 [7:24:26<11:33:44,  3.47it/s]
 61%|██████    | 226859/371472 [7:24:26<11:41:25,  3.44it/s]
 61%|██████    | 226860/371472 [7:24:26<12:26:20,  3.23it/s]
                                                            
{'loss': 2.7321, 'learning_rate': 4.5055377189769223e-07, 'epoch': 9.77}
+
 61%|██████    | 226860/371472 [7:24:26<12:26:20,  3.23it/s]
 61%|██████    | 226861/371472 [7:24:27<12:11:44,  3.29it/s]
 61%|██████    | 226862/371472 [7:24:27<12:13:17,  3.29it/s]
 61%|██████    | 226863/371472 [7:24:27<11:53:16,  3.38it/s]
 61%|██████    | 226864/371472 [7:24:28<12:25:45,  3.23it/s]
 61%|██████    | 226865/371472 [7:24:28<12:22:46,  3.24it/s]
 61%|██████    | 226866/371472 [7:24:28<11:52:16,  3.38it/s]
 61%|██████    | 226867/371472 [7:24:28<12:03:36,  3.33it/s]
 61%|██████    | 226868/371472 [7:24:29<11:43:50,  3.42it/s]
 61%|██████    | 226869/371472 [7:24:29<11:33:10,  3.48it/s]
 61%|██████    | 226870/371472 [7:24:29<12:24:38,  3.24it/s]
 61%|██████    | 226871/371472 [7:24:30<12:12:06,  3.29it/s]
 61%|██████    | 226872/371472 [7:24:30<11:45:57,  3.41it/s]
 61%|██████    | 226873/371472 [7:24:30<12:18:01,  3.27it/s]
 61%|██████    | 226874/371472 [7:24:31<12:26:25,  3.23it/s]
 61%|██████    | 226875/371472 [7:24:31<12:40:12,  3.17it/s]
 61%|██████    | 226876/371472 [7:24:31<12:17:40,  3.27it/s]
 61%|██████    | 226877/371472 [7:24:31<12:02:29,  3.34it/s]
 61%|██████    | 226878/371472 [7:24:32<11:56:40,  3.36it/s]
 61%|██████    | 226879/371472 [7:24:32<11:43:07,  3.43it/s]
 61%|██████    | 226880/371472 [7:24:32<11:40:00,  3.44it/s]
                                                            
{'loss': 2.7426, 'learning_rate': 4.505052899222134e-07, 'epoch': 9.77}
+
 61%|██████    | 226880/371472 [7:24:32<11:40:00,  3.44it/s]
 61%|██████    | 226881/371472 [7:24:33<12:06:53,  3.32it/s]
 61%|██████    | 226882/371472 [7:24:33<11:41:44,  3.43it/s]
 61%|██████    | 226883/371472 [7:24:33<11:31:01,  3.49it/s]
 61%|██████    | 226884/371472 [7:24:33<11:20:00,  3.54it/s]
 61%|██████    | 226885/371472 [7:24:34<11:44:04,  3.42it/s]
 61%|██████    | 226886/371472 [7:24:34<11:45:01,  3.42it/s]
 61%|██████    | 226887/371472 [7:24:34<11:42:23,  3.43it/s]
 61%|██████    | 226888/371472 [7:24:35<11:23:20,  3.53it/s]
 61%|██████    | 226889/371472 [7:24:35<11:18:31,  3.55it/s]
 61%|██████    | 226890/371472 [7:24:35<11:15:48,  3.57it/s]
 61%|██████    | 226891/371472 [7:24:35<11:27:51,  3.50it/s]
 61%|██████    | 226892/371472 [7:24:36<11:24:54,  3.52it/s]
 61%|██████    | 226893/371472 [7:24:36<11:45:36,  3.41it/s]
 61%|██████    | 226894/371472 [7:24:36<11:28:58,  3.50it/s]
 61%|██████    | 226895/371472 [7:24:37<11:28:45,  3.50it/s]
 61%|██████    | 226896/371472 [7:24:37<13:04:21,  3.07it/s]
 61%|██████    | 226897/371472 [7:24:37<12:39:10,  3.17it/s]
 61%|██████    | 226898/371472 [7:24:38<12:41:07,  3.17it/s]
 61%|██████    | 226899/371472 [7:24:38<12:20:37,  3.25it/s]
 61%|██████    | 226900/371472 [7:24:38<12:23:47,  3.24it/s]
                                                            
{'loss': 2.8496, 'learning_rate': 4.504568079467344e-07, 'epoch': 9.77}
+
 61%|██████    | 226900/371472 [7:24:38<12:23:47,  3.24it/s]
 61%|██████    | 226901/371472 [7:24:38<11:56:29,  3.36it/s]
 61%|██████    | 226902/371472 [7:24:39<11:26:04,  3.51it/s]
 61%|██████    | 226903/371472 [7:24:39<11:17:39,  3.56it/s]
 61%|██████    | 226904/371472 [7:24:39<11:32:09,  3.48it/s]
 61%|██████    | 226905/371472 [7:24:40<11:29:14,  3.50it/s]
 61%|██████    | 226906/371472 [7:24:40<11:31:27,  3.48it/s]
 61%|██████    | 226907/371472 [7:24:40<11:39:20,  3.45it/s]
 61%|██████    | 226908/371472 [7:24:40<11:31:19,  3.49it/s]
 61%|██████    | 226909/371472 [7:24:41<11:49:26,  3.40it/s]
 61%|██████    | 226910/371472 [7:24:41<11:37:30,  3.45it/s]
 61%|██████    | 226911/371472 [7:24:41<11:43:45,  3.42it/s]
 61%|██████    | 226912/371472 [7:24:42<12:43:00,  3.16it/s]
 61%|██████    | 226913/371472 [7:24:42<12:26:24,  3.23it/s]
 61%|██████    | 226914/371472 [7:24:42<12:13:24,  3.29it/s]
 61%|██████    | 226915/371472 [7:24:43<12:20:03,  3.26it/s]
 61%|██████    | 226916/371472 [7:24:43<12:07:34,  3.31it/s]
 61%|██████    | 226917/371472 [7:24:43<12:13:42,  3.28it/s]
 61%|██████    | 226918/371472 [7:24:43<11:44:25,  3.42it/s]
 61%|██████    | 226919/371472 [7:24:44<11:37:51,  3.45it/s]
 61%|██████    | 226920/371472 [7:24:44<11:30:27,  3.49it/s]
                                                            
{'loss': 2.6321, 'learning_rate': 4.504083259712556e-07, 'epoch': 9.77}
+
 61%|██████    | 226920/371472 [7:24:44<11:30:27,  3.49it/s]
 61%|██████    | 226921/371472 [7:24:44<11:22:48,  3.53it/s]
 61%|██████    | 226922/371472 [7:24:45<11:25:52,  3.51it/s]
 61%|██████    | 226923/371472 [7:24:45<11:02:39,  3.64it/s]
 61%|██████    | 226924/371472 [7:24:45<11:08:21,  3.60it/s]
 61%|██████    | 226925/371472 [7:24:45<11:11:52,  3.59it/s]
 61%|██████    | 226926/371472 [7:24:46<11:02:24,  3.64it/s]
 61%|██████    | 226927/371472 [7:24:46<11:18:45,  3.55it/s]
 61%|██████    | 226928/371472 [7:24:46<11:08:03,  3.61it/s]
 61%|██████    | 226929/371472 [7:24:47<11:19:48,  3.54it/s]
 61%|██████    | 226930/371472 [7:24:47<11:35:08,  3.47it/s]
 61%|██████    | 226931/371472 [7:24:47<11:16:18,  3.56it/s]
 61%|██████    | 226932/371472 [7:24:47<11:36:28,  3.46it/s]
 61%|██████    | 226933/371472 [7:24:48<12:43:53,  3.15it/s]
 61%|██████    | 226934/371472 [7:24:48<12:18:12,  3.26it/s]
 61%|██████    | 226935/371472 [7:24:48<11:55:07,  3.37it/s]
 61%|██████    | 226936/371472 [7:24:49<12:31:07,  3.21it/s]
 61%|██████    | 226937/371472 [7:24:49<12:07:44,  3.31it/s]
 61%|██████    | 226938/371472 [7:24:49<11:46:50,  3.41it/s]
 61%|██████    | 226939/371472 [7:24:50<12:23:23,  3.24it/s]
 61%|██████    | 226940/371472 [7:24:50<12:09:03,  3.30it/s]
                                                            
{'loss': 2.8901, 'learning_rate': 4.503598439957767e-07, 'epoch': 9.77}
+
 61%|██████    | 226940/371472 [7:24:50<12:09:03,  3.30it/s]
 61%|██████    | 226941/371472 [7:24:50<12:08:36,  3.31it/s]
 61%|██████    | 226942/371472 [7:24:51<12:06:57,  3.31it/s]
 61%|██████    | 226943/371472 [7:24:51<12:24:45,  3.23it/s]
 61%|██████    | 226944/371472 [7:24:51<12:13:05,  3.29it/s]
 61%|██████    | 226945/371472 [7:24:51<11:39:00,  3.45it/s]
 61%|██████    | 226946/371472 [7:24:52<11:36:35,  3.46it/s]
 61%|██████    | 226947/371472 [7:24:52<11:34:47,  3.47it/s]
 61%|██████    | 226948/371472 [7:24:52<11:29:17,  3.49it/s]
 61%|██████    | 226949/371472 [7:24:53<11:45:51,  3.41it/s]
 61%|██████    | 226950/371472 [7:24:53<12:07:52,  3.31it/s]
 61%|██████    | 226951/371472 [7:24:53<12:03:12,  3.33it/s]
 61%|██████    | 226952/371472 [7:24:53<11:35:27,  3.46it/s]
 61%|██████    | 226953/371472 [7:24:54<11:33:50,  3.47it/s]
 61%|██████    | 226954/371472 [7:24:54<11:48:03,  3.40it/s]
 61%|██████    | 226955/371472 [7:24:54<11:45:44,  3.41it/s]
 61%|██████    | 226956/371472 [7:24:55<11:44:36,  3.42it/s]
 61%|██████    | 226957/371472 [7:24:55<11:49:03,  3.40it/s]
 61%|██████    | 226958/371472 [7:24:55<11:42:33,  3.43it/s]
 61%|██████    | 226959/371472 [7:24:55<11:17:57,  3.55it/s]
 61%|██████    | 226960/371472 [7:24:56<11:27:57,  3.50it/s]
                                                            
{'loss': 2.7151, 'learning_rate': 4.503113620202978e-07, 'epoch': 9.78}
+
 61%|██████    | 226960/371472 [7:24:56<11:27:57,  3.50it/s]
 61%|██████    | 226961/371472 [7:24:56<11:18:40,  3.55it/s]
 61%|██████    | 226962/371472 [7:24:56<11:30:15,  3.49it/s]
 61%|██████    | 226963/371472 [7:24:57<12:14:59,  3.28it/s]
 61%|██████    | 226964/371472 [7:24:57<11:51:28,  3.39it/s]
 61%|██████    | 226965/371472 [7:24:57<11:43:08,  3.43it/s]
 61%|██████    | 226966/371472 [7:24:58<11:43:26,  3.42it/s]
 61%|██████    | 226967/371472 [7:24:58<12:32:50,  3.20it/s]
 61%|██████    | 226968/371472 [7:24:58<12:18:27,  3.26it/s]
 61%|██████    | 226969/371472 [7:24:58<11:48:54,  3.40it/s]
 61%|██████    | 226970/371472 [7:24:59<11:56:02,  3.36it/s]
 61%|██████    | 226971/371472 [7:24:59<12:20:51,  3.25it/s]
 61%|██████    | 226972/371472 [7:24:59<12:19:02,  3.26it/s]
 61%|██████    | 226973/371472 [7:25:00<11:53:19,  3.38it/s]
 61%|██████    | 226974/371472 [7:25:00<11:38:56,  3.45it/s]
 61%|██████    | 226975/371472 [7:25:00<11:53:22,  3.38it/s]
 61%|██████    | 226976/371472 [7:25:01<11:41:29,  3.43it/s]
 61%|██████    | 226977/371472 [7:25:01<12:08:50,  3.30it/s]
 61%|██████    | 226978/371472 [7:25:01<12:31:30,  3.20it/s]
 61%|██████    | 226979/371472 [7:25:01<12:22:25,  3.24it/s]
 61%|██████    | 226980/371472 [7:25:02<12:16:45,  3.27it/s]
                                                            
{'loss': 2.6635, 'learning_rate': 4.5026288004481887e-07, 'epoch': 9.78}
+
 61%|██████    | 226980/371472 [7:25:02<12:16:45,  3.27it/s]
 61%|██████    | 226981/371472 [7:25:02<12:03:48,  3.33it/s]
 61%|██████    | 226982/371472 [7:25:02<12:02:38,  3.33it/s]
 61%|██████    | 226983/371472 [7:25:03<12:55:42,  3.10it/s]
 61%|██████    | 226984/371472 [7:25:03<12:37:02,  3.18it/s]
 61%|██████    | 226985/371472 [7:25:03<12:14:20,  3.28it/s]
 61%|██████    | 226986/371472 [7:25:04<11:52:27,  3.38it/s]
 61%|██████    | 226987/371472 [7:25:04<11:43:11,  3.42it/s]
 61%|██████    | 226988/371472 [7:25:04<12:16:52,  3.27it/s]
 61%|██████    | 226989/371472 [7:25:04<11:49:39,  3.39it/s]
 61%|██████    | 226990/371472 [7:25:05<11:49:13,  3.40it/s]
 61%|██████    | 226991/371472 [7:25:05<12:12:16,  3.29it/s]
 61%|██████    | 226992/371472 [7:25:05<12:28:26,  3.22it/s]
 61%|██████    | 226993/371472 [7:25:06<12:16:42,  3.27it/s]
 61%|██████    | 226994/371472 [7:25:06<11:58:38,  3.35it/s]
 61%|██████    | 226995/371472 [7:25:06<11:40:36,  3.44it/s]
 61%|██████    | 226996/371472 [7:25:07<11:44:26,  3.42it/s]
 61%|██████    | 226997/371472 [7:25:07<11:49:45,  3.39it/s]
 61%|██████    | 226998/371472 [7:25:07<11:57:41,  3.36it/s]
 61%|██████    | 226999/371472 [7:25:07<12:07:52,  3.31it/s]
 61%|██████    | 227000/371472 [7:25:08<12:09:05,  3.30it/s]
                                                            
{'loss': 2.6493, 'learning_rate': 4.5021439806933994e-07, 'epoch': 9.78}
+
 61%|██████    | 227000/371472 [7:25:08<12:09:05,  3.30it/s]
 61%|██████    | 227001/371472 [7:25:08<11:51:59,  3.38it/s]
 61%|██████    | 227002/371472 [7:25:08<12:15:19,  3.27it/s]
 61%|██████    | 227003/371472 [7:25:09<11:45:07,  3.41it/s]
 61%|██████    | 227004/371472 [7:25:09<11:27:26,  3.50it/s]
 61%|██████    | 227005/371472 [7:25:09<11:32:32,  3.48it/s]
 61%|██████    | 227006/371472 [7:25:10<11:38:34,  3.45it/s]
 61%|██████    | 227007/371472 [7:25:10<13:33:32,  2.96it/s]
 61%|██████    | 227008/371472 [7:25:10<12:38:54,  3.17it/s]
 61%|██████    | 227009/371472 [7:25:11<12:21:57,  3.25it/s]
 61%|██████    | 227010/371472 [7:25:11<12:11:29,  3.29it/s]
 61%|██████    | 227011/371472 [7:25:11<12:48:15,  3.13it/s]
 61%|██████    | 227012/371472 [7:25:11<12:12:48,  3.29it/s]
 61%|██████    | 227013/371472 [7:25:12<12:06:28,  3.31it/s]
 61%|██████    | 227014/371472 [7:25:12<12:07:33,  3.31it/s]
 61%|██████    | 227015/371472 [7:25:12<11:55:28,  3.37it/s]
 61%|██████    | 227016/371472 [7:25:13<12:34:53,  3.19it/s]
 61%|██████    | 227017/371472 [7:25:13<12:58:13,  3.09it/s]
 61%|██████    | 227018/371472 [7:25:13<12:21:05,  3.25it/s]
 61%|██████    | 227019/371472 [7:25:14<12:07:00,  3.31it/s]
 61%|██████    | 227020/371472 [7:25:14<11:55:43,  3.36it/s]
                                                            
{'loss': 2.8145, 'learning_rate': 4.5016591609386107e-07, 'epoch': 9.78}
+
 61%|██████    | 227020/371472 [7:25:14<11:55:43,  3.36it/s]
 61%|██████    | 227021/371472 [7:25:14<12:02:42,  3.33it/s]
 61%|██████    | 227022/371472 [7:25:14<12:05:19,  3.32it/s]
 61%|██████    | 227023/371472 [7:25:15<11:59:21,  3.35it/s]
 61%|██████    | 227024/371472 [7:25:15<11:54:48,  3.37it/s]
 61%|██████    | 227025/371472 [7:25:15<11:42:47,  3.43it/s]
 61%|██████    | 227026/371472 [7:25:16<11:50:34,  3.39it/s]
 61%|██████    | 227027/371472 [7:25:16<12:01:45,  3.34it/s]
 61%|██████    | 227028/371472 [7:25:16<11:48:10,  3.40it/s]
 61%|██████    | 227029/371472 [7:25:17<11:51:48,  3.38it/s]
 61%|██████    | 227030/371472 [7:25:17<11:50:28,  3.39it/s]
 61%|██████    | 227031/371472 [7:25:17<11:40:59,  3.43it/s]
 61%|██████    | 227032/371472 [7:25:17<11:36:18,  3.46it/s]
 61%|██████    | 227033/371472 [7:25:18<11:36:38,  3.46it/s]
 61%|██████    | 227034/371472 [7:25:18<11:28:34,  3.50it/s]
 61%|██████    | 227035/371472 [7:25:18<11:12:51,  3.58it/s]
 61%|██████    | 227036/371472 [7:25:19<11:34:48,  3.46it/s]
 61%|█████���    | 227037/371472 [7:25:19<12:02:20,  3.33it/s]
 61%|██████    | 227038/371472 [7:25:19<11:43:13,  3.42it/s]
 61%|██████    | 227039/371472 [7:25:19<11:27:37,  3.50it/s]
 61%|██████    | 227040/371472 [7:25:20<11:30:41,  3.49it/s]
                                                            
{'loss': 2.7313, 'learning_rate': 4.5011743411838214e-07, 'epoch': 9.78}
+
 61%|██████    | 227040/371472 [7:25:20<11:30:41,  3.49it/s]
 61%|██████    | 227041/371472 [7:25:20<11:30:01,  3.49it/s]
 61%|██████    | 227042/371472 [7:25:20<11:16:44,  3.56it/s]
 61%|██████    | 227043/371472 [7:25:21<11:23:39,  3.52it/s]
 61%|██████    | 227044/371472 [7:25:21<11:37:21,  3.45it/s]
 61%|██████    | 227045/371472 [7:25:21<11:44:17,  3.42it/s]
 61%|██████    | 227046/371472 [7:25:21<11:46:29,  3.41it/s]
 61%|██████    | 227047/371472 [7:25:22<12:11:11,  3.29it/s]
 61%|██████    | 227048/371472 [7:25:22<11:32:04,  3.48it/s]
 61%|██████    | 227049/371472 [7:25:22<11:44:20,  3.42it/s]
 61%|██████    | 227050/371472 [7:25:23<11:46:37,  3.41it/s]
 61%|██████    | 227051/371472 [7:25:23<11:34:52,  3.46it/s]
 61%|██████    | 227052/371472 [7:25:23<11:54:45,  3.37it/s]
 61%|██████    | 227053/371472 [7:25:24<12:16:05,  3.27it/s]
 61%|██████    | 227054/371472 [7:25:24<12:43:42,  3.15it/s]
 61%|██████    | 227055/371472 [7:25:24<12:11:09,  3.29it/s]
 61%|██████    | 227056/371472 [7:25:24<11:59:54,  3.34it/s]
 61%|██████    | 227057/371472 [7:25:25<11:44:35,  3.42it/s]
 61%|██████    | 227058/371472 [7:25:25<11:50:58,  3.39it/s]
 61%|██████    | 227059/371472 [7:25:25<11:30:14,  3.49it/s]
 61%|██████    | 227060/371472 [7:25:26<11:20:35,  3.54it/s]
                                                            
{'loss': 2.6517, 'learning_rate': 4.500689521429033e-07, 'epoch': 9.78}
+
 61%|██████    | 227060/371472 [7:25:26<11:20:35,  3.54it/s]
 61%|██████    | 227061/371472 [7:25:26<11:11:57,  3.58it/s]
 61%|██████    | 227062/371472 [7:25:26<11:14:00,  3.57it/s]
 61%|██████    | 227063/371472 [7:25:26<11:16:58,  3.56it/s]
 61%|██████    | 227064/371472 [7:25:27<11:26:35,  3.51it/s]
 61%|██████    | 227065/371472 [7:25:27<11:42:44,  3.42it/s]
 61%|██████    | 227066/371472 [7:25:27<12:29:23,  3.21it/s]
 61%|██████    | 227067/371472 [7:25:28<12:11:22,  3.29it/s]
 61%|██████    | 227068/371472 [7:25:28<12:09:01,  3.30it/s]
 61%|██████    | 227069/371472 [7:25:28<11:52:05,  3.38it/s]
 61%|██████    | 227070/371472 [7:25:29<11:33:06,  3.47it/s]
 61%|██████    | 227071/371472 [7:25:29<12:45:12,  3.15it/s]
 61%|██████    | 227072/371472 [7:25:29<12:10:12,  3.30it/s]
 61%|██████    | 227073/371472 [7:25:29<11:59:39,  3.34it/s]
 61%|██████    | 227074/371472 [7:25:30<11:38:08,  3.45it/s]
 61%|██████    | 227075/371472 [7:25:30<11:33:39,  3.47it/s]
 61%|██████    | 227076/371472 [7:25:30<11:58:17,  3.35it/s]
 61%|██████    | 227077/371472 [7:25:31<11:33:13,  3.47it/s]
 61%|██████    | 227078/371472 [7:25:31<11:32:52,  3.47it/s]
 61%|██████    | 227079/371472 [7:25:31<11:53:40,  3.37it/s]
 61%|██████    | 227080/371472 [7:25:32<12:08:13,  3.30it/s]
                                                            
{'loss': 2.7803, 'learning_rate': 4.5002047016742433e-07, 'epoch': 9.78}
+
 61%|██████    | 227080/371472 [7:25:32<12:08:13,  3.30it/s]
 61%|██████    | 227081/371472 [7:25:32<11:52:36,  3.38it/s]
 61%|██████    | 227082/371472 [7:25:32<11:38:49,  3.44it/s]
 61%|██████    | 227083/371472 [7:25:32<11:37:52,  3.45it/s]
 61%|██████    | 227084/371472 [7:25:33<12:15:30,  3.27it/s]
 61%|██████    | 227085/371472 [7:25:33<12:31:45,  3.20it/s]
 61%|██████    | 227086/371472 [7:25:33<12:20:15,  3.25it/s]
 61%|██████    | 227087/371472 [7:25:34<12:27:44,  3.22it/s]
 61%|██████    | 227088/371472 [7:25:34<11:58:19,  3.35it/s]
 61%|██████    | 227089/371472 [7:25:34<11:46:34,  3.41it/s]
 61%|██████    | 227090/371472 [7:25:34<11:27:03,  3.50it/s]
 61%|██████    | 227091/371472 [7:25:35<11:25:39,  3.51it/s]
 61%|██████    | 227092/371472 [7:25:35<12:40:49,  3.16it/s]
 61%|██████    | 227093/371472 [7:25:35<12:16:06,  3.27it/s]
 61%|██████    | 227094/371472 [7:25:36<12:10:07,  3.30it/s]
 61%|██████    | 227095/371472 [7:25:36<11:44:51,  3.41it/s]
 61%|██████    | 227096/371472 [7:25:36<11:37:49,  3.45it/s]
 61%|██████    | 227097/371472 [7:25:37<11:28:42,  3.49it/s]
 61%|██████    | 227098/371472 [7:25:37<11:52:01,  3.38it/s]
 61%|██████    | 227099/371472 [7:25:37<11:46:28,  3.41it/s]
 61%|██████    | 227100/371472 [7:25:37<11:39:45,  3.44it/s]
                                                            
{'loss': 2.795, 'learning_rate': 4.4997198819194546e-07, 'epoch': 9.78}
+
 61%|██████    | 227100/371472 [7:25:37<11:39:45,  3.44it/s]
 61%|██████    | 227101/371472 [7:25:38<11:22:38,  3.52it/s]
 61%|██████    | 227102/371472 [7:25:38<11:22:33,  3.53it/s]
 61%|██████    | 227103/371472 [7:25:38<11:19:06,  3.54it/s]
 61%|██████    | 227104/371472 [7:25:39<11:26:38,  3.50it/s]
 61%|██████    | 227105/371472 [7:25:39<11:18:45,  3.54it/s]
 61%|██████    | 227106/371472 [7:25:39<11:18:40,  3.55it/s]
 61%|██████    | 227107/371472 [7:25:39<11:17:06,  3.55it/s]
 61%|██████    | 227108/371472 [7:25:40<11:50:53,  3.38it/s]
 61%|██████    | 227109/371472 [7:25:40<11:38:47,  3.44it/s]
 61%|██████    | 227110/371472 [7:25:40<12:00:04,  3.34it/s]
 61%|██████    | 227111/371472 [7:25:41<12:05:16,  3.32it/s]
 61%|██████    | 227112/371472 [7:25:41<13:16:57,  3.02it/s]
 61%|██████    | 227113/371472 [7:25:41<12:29:34,  3.21it/s]
 61%|██████    | 227114/371472 [7:25:42<12:26:26,  3.22it/s]
 61%|██████    | 227115/371472 [7:25:42<11:58:01,  3.35it/s]
 61%|██████    | 227116/371472 [7:25:42<11:49:19,  3.39it/s]
 61%|██████    | 227117/371472 [7:25:43<12:29:03,  3.21it/s]
 61%|██████    | 227118/371472 [7:25:43<12:11:59,  3.29it/s]
 61%|██████    | 227119/371472 [7:25:43<12:21:32,  3.24it/s]
 61%|██████    | 227120/371472 [7:25:43<11:44:18,  3.42it/s]
                                                            
{'loss': 2.7965, 'learning_rate': 4.499235062164666e-07, 'epoch': 9.78}
+
 61%|██████    | 227120/371472 [7:25:43<11:44:18,  3.42it/s]
 61%|██████    | 227121/371472 [7:25:44<13:03:31,  3.07it/s]
 61%|██████    | 227122/371472 [7:25:44<12:55:05,  3.10it/s]
 61%|██████    | 227123/371472 [7:25:44<13:20:25,  3.01it/s]
 61%|██████    | 227124/371472 [7:25:45<13:30:48,  2.97it/s]
 61%|██████    | 227125/371472 [7:25:45<13:10:30,  3.04it/s]
 61%|██████    | 227126/371472 [7:25:45<12:53:40,  3.11it/s]
 61%|██████    | 227127/371472 [7:25:46<12:59:43,  3.09it/s]
 61%|██████    | 227128/371472 [7:25:46<12:29:06,  3.21it/s]
 61%|██████    | 227129/371472 [7:25:46<12:10:41,  3.29it/s]
 61%|██████    | 227130/371472 [7:25:47<12:40:06,  3.16it/s]
 61%|██████    | 227131/371472 [7:25:47<12:06:39,  3.31it/s]
 61%|██████    | 227132/371472 [7:25:47<11:49:24,  3.39it/s]
 61%|██████    | 227133/371472 [7:25:48<12:24:55,  3.23it/s]
 61%|██████    | 227134/371472 [7:25:48<12:36:39,  3.18it/s]
 61%|██████    | 227135/371472 [7:25:48<13:06:24,  3.06it/s]
 61%|██████    | 227136/371472 [7:25:49<12:48:21,  3.13it/s]
 61%|██████    | 227137/371472 [7:25:49<12:31:25,  3.20it/s]
 61%|██████    | 227138/371472 [7:25:49<12:07:20,  3.31it/s]
 61%|██████    | 227139/371472 [7:25:49<11:47:44,  3.40it/s]
 61%|██████    | 227140/371472 [7:25:50<11:31:46,  3.48it/s]
                                                            
{'loss': 2.7508, 'learning_rate': 4.498750242409877e-07, 'epoch': 9.78}
+
 61%|██████    | 227140/371472 [7:25:50<11:31:46,  3.48it/s]
 61%|██████    | 227141/371472 [7:25:50<12:11:46,  3.29it/s]
 61%|██████    | 227142/371472 [7:25:50<11:57:20,  3.35it/s]
 61%|██████    | 227143/371472 [7:25:51<11:33:01,  3.47it/s]
 61%|██████    | 227144/371472 [7:25:51<12:04:03,  3.32it/s]
 61%|██████    | 227145/371472 [7:25:51<12:07:23,  3.31it/s]
 61%|██████    | 227146/371472 [7:25:51<12:01:24,  3.33it/s]
 61%|██████    | 227147/371472 [7:25:52<12:01:34,  3.33it/s]
 61%|██████    | 227148/371472 [7:25:52<11:39:23,  3.44it/s]
 61%|██████    | 227149/371472 [7:25:52<11:23:53,  3.52it/s]
 61%|██████    | 227150/371472 [7:25:53<11:19:25,  3.54it/s]
 61%|██████    | 227151/371472 [7:25:53<11:22:41,  3.52it/s]
 61%|██████    | 227152/371472 [7:25:53<11:38:06,  3.45it/s]
 61%|██████    | 227153/371472 [7:25:53<11:23:43,  3.52it/s]
 61%|██████    | 227154/371472 [7:25:54<11:33:18,  3.47it/s]
 61%|██████    | 227155/371472 [7:25:54<11:55:37,  3.36it/s]
 61%|██████    | 227156/371472 [7:25:54<11:42:58,  3.42it/s]
 61%|██████    | 227157/371472 [7:25:55<11:41:32,  3.43it/s]
 61%|██████    | 227158/371472 [7:25:55<11:29:43,  3.49it/s]
 61%|██████    | 227159/371472 [7:25:55<11:18:45,  3.54it/s]
 61%|██████    | 227160/371472 [7:25:56<12:26:39,  3.22it/s]
                                                            
{'loss': 2.6297, 'learning_rate': 4.498265422655088e-07, 'epoch': 9.78}
+
 61%|██████    | 227160/371472 [7:25:56<12:26:39,  3.22it/s]
 61%|██████    | 227161/371472 [7:25:56<12:14:42,  3.27it/s]
 61%|██████    | 227162/371472 [7:25:56<12:02:27,  3.33it/s]
 61%|██████    | 227163/371472 [7:25:56<12:12:56,  3.28it/s]
 61%|██████    | 227164/371472 [7:25:57<11:44:59,  3.41it/s]
 61%|██████    | 227165/371472 [7:25:57<12:04:43,  3.32it/s]
 61%|██████    | 227166/371472 [7:25:57<11:51:58,  3.38it/s]
 61%|██████    | 227167/371472 [7:25:58<11:45:28,  3.41it/s]
 61%|██████    | 227168/371472 [7:25:58<11:57:04,  3.35it/s]
 61%|██████    | 227169/371472 [7:25:58<11:32:06,  3.47it/s]
 61%|██████    | 227170/371472 [7:25:59<12:16:32,  3.27it/s]
 61%|██████    | 227171/371472 [7:25:59<11:55:37,  3.36it/s]
 61%|██████    | 227172/371472 [7:25:59<11:46:25,  3.40it/s]
 61%|██████    | 227173/371472 [7:25:59<11:43:31,  3.42it/s]
 61%|██████    | 227174/371472 [7:26:00<11:37:25,  3.45it/s]
 61%|██████    | 227175/371472 [7:26:00<12:23:14,  3.24it/s]
 61%|██████    | 227176/371472 [7:26:00<11:55:26,  3.36it/s]
 61%|██████    | 227177/371472 [7:26:01<12:01:19,  3.33it/s]
 61%|██████    | 227178/371472 [7:26:01<12:01:09,  3.33it/s]
 61%|██████    | 227179/371472 [7:26:01<11:47:08,  3.40it/s]
 61%|██████    | 227180/371472 [7:26:02<12:13:40,  3.28it/s]
                                                            
{'loss': 2.8588, 'learning_rate': 4.4977806029002996e-07, 'epoch': 9.79}
+
 61%|██████    | 227180/371472 [7:26:02<12:13:40,  3.28it/s]
 61%|██████    | 227181/371472 [7:26:02<11:58:44,  3.35it/s]
 61%|██████    | 227182/371472 [7:26:02<13:30:48,  2.97it/s]
 61%|██████    | 227183/371472 [7:26:02<12:28:56,  3.21it/s]
 61%|██████    | 227184/371472 [7:26:03<12:57:07,  3.09it/s]
 61%|██████    | 227185/371472 [7:26:03<12:43:04,  3.15it/s]
 61%|██████    | 227186/371472 [7:26:03<12:02:39,  3.33it/s]
 61%|██████    | 227187/371472 [7:26:04<11:40:44,  3.43it/s]
 61%|██████    | 227188/371472 [7:26:04<11:43:53,  3.42it/s]
 61%|██████    | 227189/371472 [7:26:04<11:56:01,  3.36it/s]
 61%|██████    | 227190/371472 [7:26:05<12:21:07,  3.24it/s]
 61%|██████    | 227191/371472 [7:26:05<12:10:38,  3.29it/s]
 61%|██████    | 227192/371472 [7:26:05<11:50:14,  3.39it/s]
 61%|██████    | 227193/371472 [7:26:05<11:33:54,  3.47it/s]
 61%|██████    | 227194/371472 [7:26:06<11:29:53,  3.49it/s]
 61%|██████    | 227195/371472 [7:26:06<12:08:39,  3.30it/s]
 61%|██████    | 227196/371472 [7:26:06<12:15:34,  3.27it/s]
 61%|██████    | 227197/371472 [7:26:07<12:25:55,  3.22it/s]
 61%|██████    | 227198/371472 [7:26:07<12:59:59,  3.08it/s]
 61%|██████    | 227199/371472 [7:26:07<13:14:23,  3.03it/s]
 61%|██████    | 227200/371472 [7:26:08<12:36:19,  3.18it/s]
                                                            
{'loss': 2.747, 'learning_rate': 4.4972957831455103e-07, 'epoch': 9.79}
+
 61%|██████    | 227200/371472 [7:26:08<12:36:19,  3.18it/s]
 61%|██████    | 227201/371472 [7:26:08<12:13:39,  3.28it/s]
 61%|██████    | 227202/371472 [7:26:08<12:19:45,  3.25it/s]
 61%|██████    | 227203/371472 [7:26:09<12:21:26,  3.24it/s]
 61%|██████    | 227204/371472 [7:26:09<11:47:36,  3.40it/s]
 61%|██████    | 227205/371472 [7:26:09<11:45:38,  3.41it/s]
 61%|██████    | 227206/371472 [7:26:09<11:52:33,  3.37it/s]
 61%|██████    | 227207/371472 [7:26:10<11:35:01,  3.46it/s]
 61%|██████    | 227208/371472 [7:26:10<11:49:56,  3.39it/s]
 61%|██████    | 227209/371472 [7:26:10<11:40:58,  3.43it/s]
 61%|██████    | 227210/371472 [7:26:11<11:29:53,  3.49it/s]
 61%|██████    | 227211/371472 [7:26:11<11:16:07,  3.56it/s]
 61%|██████    | 227212/371472 [7:26:11<11:23:03,  3.52it/s]
 61%|██████    | 227213/371472 [7:26:11<12:10:04,  3.29it/s]
 61%|██████    | 227214/371472 [7:26:12<11:56:11,  3.36it/s]
 61%|██████    | 227215/371472 [7:26:12<11:36:19,  3.45it/s]
 61%|██████    | 227216/371472 [7:26:12<11:45:27,  3.41it/s]
 61%|██████    | 227217/371472 [7:26:13<12:01:12,  3.33it/s]
 61%|██████    | 227218/371472 [7:26:13<12:15:02,  3.27it/s]
 61%|██████    | 227219/371472 [7:26:13<12:54:34,  3.10it/s]
 61%|██████    | 227220/371472 [7:26:14<12:45:43,  3.14it/s]
                                                            
{'loss': 2.8575, 'learning_rate': 4.4968109633907215e-07, 'epoch': 9.79}
+
 61%|██████    | 227220/371472 [7:26:14<12:45:43,  3.14it/s]
 61%|██████    | 227221/371472 [7:26:14<12:40:59,  3.16it/s]
 61%|██████    | 227222/371472 [7:26:14<12:22:25,  3.24it/s]
 61%|██████    | 227223/371472 [7:26:15<12:04:26,  3.32it/s]
 61%|██████    | 227224/371472 [7:26:15<11:49:48,  3.39it/s]
 61%|██████    | 227225/371472 [7:26:15<11:34:17,  3.46it/s]
 61%|██████    | 227226/371472 [7:26:15<11:47:21,  3.40it/s]
 61%|██████    | 227227/371472 [7:26:16<11:41:54,  3.43it/s]
 61%|██████    | 227228/371472 [7:26:16<11:45:57,  3.41it/s]
 61%|██████    | 227229/371472 [7:26:16<11:23:18,  3.52it/s]
 61%|██████    | 227230/371472 [7:26:17<11:17:06,  3.55it/s]
 61%|██████    | 227231/371472 [7:26:17<11:39:06,  3.44it/s]
 61%|██████    | 227232/371472 [7:26:17<11:35:25,  3.46it/s]
 61%|██████    | 227233/371472 [7:26:17<11:46:12,  3.40it/s]
 61%|██████    | 227234/371472 [7:26:18<11:40:12,  3.43it/s]
 61%|██████    | 227235/371472 [7:26:18<11:46:54,  3.40it/s]
 61%|██████    | 227236/371472 [7:26:18<12:37:27,  3.17it/s]
 61%|██████    | 227237/371472 [7:26:19<12:42:19,  3.15it/s]
 61%|██████    | 227238/371472 [7:26:19<12:28:01,  3.21it/s]
 61%|██████    | 227239/371472 [7:26:19<12:08:37,  3.30it/s]
 61%|██████    | 227240/371472 [7:26:20<12:16:24,  3.26it/s]
                                                            
{'loss': 2.863, 'learning_rate': 4.496326143635932e-07, 'epoch': 9.79}
+
 61%|██████    | 227240/371472 [7:26:20<12:16:24,  3.26it/s]
 61%|██████    | 227241/371472 [7:26:20<12:04:55,  3.32it/s]
 61%|██████    | 227242/371472 [7:26:20<12:44:31,  3.14it/s]
 61%|██████    | 227243/371472 [7:26:21<12:38:19,  3.17it/s]
 61%|██████    | 227244/371472 [7:26:21<12:26:46,  3.22it/s]
 61%|██████    | 227245/371472 [7:26:21<12:17:00,  3.26it/s]
 61%|██████    | 227246/371472 [7:26:21<12:21:10,  3.24it/s]
 61%|██████    | 227247/371472 [7:26:22<11:58:53,  3.34it/s]
 61%|██████    | 227248/371472 [7:26:22<11:56:05,  3.36it/s]
 61%|██████    | 227249/371472 [7:26:22<11:52:41,  3.37it/s]
 61%|██████    | 227250/371472 [7:26:23<11:40:03,  3.43it/s]
 61%|██████    | 227251/371472 [7:26:23<11:59:07,  3.34it/s]
 61%|██████    | 227252/371472 [7:26:23<12:03:13,  3.32it/s]
 61%|██████    | 227253/371472 [7:26:24<12:10:05,  3.29it/s]
 61%|██████    | 227254/371472 [7:26:24<11:35:57,  3.45it/s]
 61%|██████    | 227255/371472 [7:26:24<11:25:46,  3.50it/s]
 61%|██████    | 227256/371472 [7:26:24<11:51:09,  3.38it/s]
 61%|██████    | 227257/371472 [7:26:25<12:05:27,  3.31it/s]
 61%|██████    | 227258/371472 [7:26:25<11:41:08,  3.43it/s]
 61%|██████    | 227259/371472 [7:26:25<11:29:23,  3.49it/s]
 61%|██████    | 227260/371472 [7:26:26<11:48:34,  3.39it/s]
                                                            
{'loss': 2.7117, 'learning_rate': 4.495841323881144e-07, 'epoch': 9.79}
+
 61%|██████    | 227260/371472 [7:26:26<11:48:34,  3.39it/s]
 61%|██████    | 227261/371472 [7:26:26<11:39:30,  3.44it/s]
 61%|██████    | 227262/371472 [7:26:26<11:23:17,  3.52it/s]
 61%|██████    | 227263/371472 [7:26:26<11:22:06,  3.52it/s]
 61%|██████    | 227264/371472 [7:26:27<11:17:46,  3.55it/s]
 61%|██████    | 227265/371472 [7:26:27<11:15:03,  3.56it/s]
 61%|██████    | 227266/371472 [7:26:27<11:15:01,  3.56it/s]
 61%|██████    | 227267/371472 [7:26:28<11:38:53,  3.44it/s]
 61%|██████    | 227268/371472 [7:26:28<11:27:19,  3.50it/s]
 61%|██████    | 227269/371472 [7:26:28<11:31:58,  3.47it/s]
 61%|██████    | 227270/371472 [7:26:28<12:16:42,  3.26it/s]
 61%|██████    | 227271/371472 [7:26:29<12:11:39,  3.28it/s]
 61%|██████    | 227272/371472 [7:26:29<12:30:11,  3.20it/s]
 61%|██████    | 227273/371472 [7:26:29<11:56:13,  3.36it/s]
 61%|██████    | 227274/371472 [7:26:30<11:50:29,  3.38it/s]
 61%|██████    | 227275/371472 [7:26:30<11:54:37,  3.36it/s]
 61%|██████    | 227276/371472 [7:26:30<12:07:39,  3.30it/s]
 61%|██████    | 227277/371472 [7:26:31<12:20:01,  3.25it/s]
 61%|██████    | 227278/371472 [7:26:31<11:52:01,  3.38it/s]
 61%|██████    | 227279/371472 [7:26:31<11:39:55,  3.43it/s]
 61%|██████    | 227280/371472 [7:26:31<11:38:07,  3.44it/s]
                                                            
{'loss': 2.7848, 'learning_rate': 4.495356504126354e-07, 'epoch': 9.79}
+
 61%|██████    | 227280/371472 [7:26:31<11:38:07,  3.44it/s]
 61%|██████    | 227281/371472 [7:26:32<11:41:56,  3.42it/s]
 61%|██████    | 227282/371472 [7:26:32<11:55:03,  3.36it/s]
 61%|██████    | 227283/371472 [7:26:32<11:41:01,  3.43it/s]
 61%|██████    | 227284/371472 [7:26:33<11:26:29,  3.50it/s]
 61%|██████    | 227285/371472 [7:26:33<11:21:06,  3.53it/s]
 61%|██████    | 227286/371472 [7:26:33<11:41:49,  3.42it/s]
 61%|██████    | 227287/371472 [7:26:33<11:48:00,  3.39it/s]
 61%|██████    | 227288/371472 [7:26:34<11:57:28,  3.35it/s]
 61%|██████    | 227289/371472 [7:26:34<13:02:26,  3.07it/s]
 61%|██████    | 227290/371472 [7:26:34<12:16:36,  3.26it/s]
 61%|██████    | 227291/371472 [7:26:35<11:54:20,  3.36it/s]
 61%|██████    | 227292/371472 [7:26:35<13:05:27,  3.06it/s]
 61%|██████    | 227293/371472 [7:26:35<12:44:38,  3.14it/s]
 61%|██████    | 227294/371472 [7:26:36<12:06:53,  3.31it/s]
 61%|██████    | 227295/371472 [7:26:36<12:12:14,  3.28it/s]
 61%|██████    | 227296/371472 [7:26:36<11:56:53,  3.35it/s]
 61%|██████    | 227297/371472 [7:26:37<11:53:52,  3.37it/s]
 61%|██████    | 227298/371472 [7:26:37<11:58:06,  3.35it/s]
 61%|██████    | 227299/371472 [7:26:37<12:24:55,  3.23it/s]
 61%|██████    | 227300/371472 [7:26:37<12:16:57,  3.26it/s]
                                                            
{'loss': 2.6425, 'learning_rate': 4.494871684371566e-07, 'epoch': 9.79}
+
 61%|██████    | 227300/371472 [7:26:37<12:16:57,  3.26it/s]
 61%|██████    | 227301/371472 [7:26:38<11:48:42,  3.39it/s]
 61%|██████    | 227302/371472 [7:26:38<11:49:21,  3.39it/s]
 61%|██████    | 227303/371472 [7:26:38<11:22:20,  3.52it/s]
 61%|██████    | 227304/371472 [7:26:39<11:06:48,  3.60it/s]
 61%|██████    | 227305/371472 [7:26:39<11:05:21,  3.61it/s]
 61%|██████    | 227306/371472 [7:26:39<11:51:37,  3.38it/s]
 61%|██████    | 227307/371472 [7:26:39<11:53:40,  3.37it/s]
 61%|██████    | 227308/371472 [7:26:40<11:53:30,  3.37it/s]
 61%|██████    | 227309/371472 [7:26:40<11:43:15,  3.42it/s]
 61%|██████    | 227310/371472 [7:26:40<11:35:46,  3.45it/s]
 61%|██████    | 227311/371472 [7:26:41<11:36:27,  3.45it/s]
 61%|██████    | 227312/371472 [7:26:41<12:29:07,  3.21it/s]
 61%|██████    | 227313/371472 [7:26:41<12:01:10,  3.33it/s]
 61%|██████    | 227314/371472 [7:26:42<12:16:01,  3.26it/s]
 61%|██████    | 227315/371472 [7:26:42<12:10:48,  3.29it/s]
 61%|██████    | 227316/371472 [7:26:42<11:53:05,  3.37it/s]
 61%|██████    | 227317/371472 [7:26:42<11:25:57,  3.50it/s]
 61%|██████    | 227318/371472 [7:26:43<12:22:22,  3.24it/s]
 61%|██████    | 227319/371472 [7:26:43<12:28:36,  3.21it/s]
 61%|██████    | 227320/371472 [7:26:43<12:01:34,  3.33it/s]
                                                            
{'loss': 2.7465, 'learning_rate': 4.4943868646167767e-07, 'epoch': 9.79}
+
 61%|██████    | 227320/371472 [7:26:43<12:01:34,  3.33it/s]
 61%|██████    | 227321/371472 [7:26:44<12:18:00,  3.26it/s]
 61%|██████    | 227322/371472 [7:26:44<12:19:48,  3.25it/s]
 61%|██████    | 227323/371472 [7:26:44<12:04:30,  3.32it/s]
 61%|██████    | 227324/371472 [7:26:45<12:26:35,  3.22it/s]
 61%|██████    | 227325/371472 [7:26:45<13:06:11,  3.06it/s]
 61%|██████    | 227326/371472 [7:26:45<12:39:31,  3.16it/s]
 61%|██████    | 227327/371472 [7:26:46<12:03:01,  3.32it/s]
 61%|██████    | 227328/371472 [7:26:46<11:38:51,  3.44it/s]
 61%|██████    | 227329/371472 [7:26:46<11:57:09,  3.35it/s]
 61%|██████    | 227330/371472 [7:26:46<12:05:16,  3.31it/s]
 61%|██████    | 227331/371472 [7:26:47<12:05:32,  3.31it/s]
 61%|██████    | 227332/371472 [7:26:47<12:32:30,  3.19it/s]
 61%|██████    | 227333/371472 [7:26:47<12:20:35,  3.24it/s]
 61%|██████    | 227334/371472 [7:26:48<12:36:21,  3.18it/s]
 61%|██████    | 227335/371472 [7:26:48<12:13:55,  3.27it/s]
 61%|██████    | 227336/371472 [7:26:48<11:54:25,  3.36it/s]
 61%|██████    | 227337/371472 [7:26:49<11:35:03,  3.46it/s]
 61%|██████    | 227338/371472 [7:26:49<11:21:17,  3.53it/s]
 61%|██████    | 227339/371472 [7:26:49<11:07:02,  3.60it/s]
 61%|██████    | 227340/371472 [7:26:49<11:00:16,  3.64it/s]
                                                            
{'loss': 2.872, 'learning_rate': 4.493902044861988e-07, 'epoch': 9.79}
+
 61%|██████    | 227340/371472 [7:26:49<11:00:16,  3.64it/s]
 61%|██████    | 227341/371472 [7:26:50<11:20:35,  3.53it/s]
 61%|██████    | 227342/371472 [7:26:50<11:24:39,  3.51it/s]
 61%|██████    | 227343/371472 [7:26:50<12:30:18,  3.20it/s]
 61%|██████    | 227344/371472 [7:26:51<12:05:05,  3.31it/s]
 61%|██████    | 227345/371472 [7:26:51<12:02:50,  3.32it/s]
 61%|██████    | 227346/371472 [7:26:51<12:18:51,  3.25it/s]
 61%|██████    | 227347/371472 [7:26:51<11:46:59,  3.40it/s]
 61%|██████    | 227348/371472 [7:26:52<11:46:52,  3.40it/s]
 61%|██████    | 227349/371472 [7:26:52<11:35:42,  3.45it/s]
 61%|██████    | 227350/371472 [7:26:52<11:19:45,  3.53it/s]
 61%|██████    | 227351/371472 [7:26:53<11:11:54,  3.57it/s]
 61%|██████    | 227352/371472 [7:26:53<11:09:23,  3.59it/s]
 61%|██████    | 227353/371472 [7:26:53<11:51:36,  3.38it/s]
 61%|██████    | 227354/371472 [7:26:53<11:33:09,  3.47it/s]
 61%|██████    | 227355/371472 [7:26:54<11:31:08,  3.48it/s]
 61%|██████    | 227356/371472 [7:26:54<11:27:24,  3.49it/s]
 61%|██████    | 227357/371472 [7:26:54<11:11:54,  3.57it/s]
 61%|██████    | 227358/371472 [7:26:55<10:57:07,  3.66it/s]
 61%|██████    | 227359/371472 [7:26:55<11:39:07,  3.44it/s]
 61%|██████    | 227360/371472 [7:26:55<12:04:29,  3.32it/s]
                                                            
{'loss': 2.7169, 'learning_rate': 4.4934172251071986e-07, 'epoch': 9.79}
+
 61%|██████    | 227360/371472 [7:26:55<12:04:29,  3.32it/s]
 61%|██████    | 227361/371472 [7:26:56<11:53:49,  3.36it/s]
 61%|██████    | 227362/371472 [7:26:56<11:24:07,  3.51it/s]
 61%|██████    | 227363/371472 [7:26:56<11:48:15,  3.39it/s]
 61%|██████    | 227364/371472 [7:26:56<11:29:49,  3.48it/s]
 61%|██████    | 227365/371472 [7:26:57<11:16:02,  3.55it/s]
 61%|██████    | 227366/371472 [7:26:57<12:40:40,  3.16it/s]
 61%|██████    | 227367/371472 [7:26:57<12:32:36,  3.19it/s]
 61%|██████    | 227368/371472 [7:26:58<12:39:01,  3.16it/s]
 61%|██████    | 227369/371472 [7:26:58<12:00:10,  3.33it/s]
 61%|██████    | 227370/371472 [7:26:58<11:35:41,  3.45it/s]
 61%|██████    | 227371/371472 [7:26:59<12:39:45,  3.16it/s]
 61%|██████    | 227372/371472 [7:26:59<12:32:42,  3.19it/s]
 61%|██████    | 227373/371472 [7:26:59<12:04:26,  3.32it/s]
 61%|██████    | 227374/371472 [7:26:59<11:46:47,  3.40it/s]
 61%|██████    | 227375/371472 [7:27:00<11:28:18,  3.49it/s]
 61%|██████    | 227376/371472 [7:27:00<11:43:09,  3.42it/s]
 61%|██████    | 227377/371472 [7:27:00<11:29:45,  3.48it/s]
 61%|██████    | 227378/371472 [7:27:01<13:17:20,  3.01it/s]
 61%|██████    | 227379/371472 [7:27:01<12:36:00,  3.18it/s]
 61%|██████    | 227380/371472 [7:27:01<12:18:08,  3.25it/s]
                                                            
{'loss': 2.8158, 'learning_rate': 4.4929324053524104e-07, 'epoch': 9.79}
+
 61%|██████    | 227380/371472 [7:27:01<12:18:08,  3.25it/s]
 61%|██████    | 227381/371472 [7:27:02<12:12:30,  3.28it/s]
 61%|██████    | 227382/371472 [7:27:02<12:27:48,  3.21it/s]
 61%|██████    | 227383/371472 [7:27:02<12:23:57,  3.23it/s]
 61%|██████    | 227384/371472 [7:27:02<11:52:51,  3.37it/s]
 61%|██████    | 227385/371472 [7:27:03<11:49:11,  3.39it/s]
 61%|██████    | 227386/371472 [7:27:03<11:30:57,  3.48it/s]
 61%|██████    | 227387/371472 [7:27:03<12:11:59,  3.28it/s]
 61%|██████    | 227388/371472 [7:27:04<12:07:11,  3.30it/s]
 61%|██████    | 227389/371472 [7:27:04<11:24:40,  3.51it/s]
 61%|██████    | 227390/371472 [7:27:04<11:31:12,  3.47it/s]
 61%|██████    | 227391/371472 [7:27:04<11:07:37,  3.60it/s]
 61%|██████    | 227392/371472 [7:27:05<12:14:33,  3.27it/s]
 61%|██████    | 227393/371472 [7:27:05<11:52:21,  3.37it/s]
 61%|██████    | 227394/371472 [7:27:05<11:40:14,  3.43it/s]
 61%|██████    | 227395/371472 [7:27:06<11:40:40,  3.43it/s]
 61%|██████    | 227396/371472 [7:27:06<12:19:01,  3.25it/s]
 61%|██████    | 227397/371472 [7:27:06<12:00:26,  3.33it/s]
 61%|██████    | 227398/371472 [7:27:07<13:03:20,  3.07it/s]
 61%|██████    | 227399/371472 [7:27:07<13:05:07,  3.06it/s]
 61%|██████    | 227400/371472 [7:27:07<12:52:56,  3.11it/s]
                                                            
{'loss': 2.7835, 'learning_rate': 4.4924475855976206e-07, 'epoch': 9.79}
+
 61%|██████    | 227400/371472 [7:27:07<12:52:56,  3.11it/s]
 61%|██████    | 227401/371472 [7:27:08<13:02:08,  3.07it/s]
 61%|██████    | 227402/371472 [7:27:08<12:23:33,  3.23it/s]
 61%|██████    | 227403/371472 [7:27:08<13:15:21,  3.02it/s]
 61%|██████    | 227404/371472 [7:27:09<12:22:43,  3.23it/s]
 61%|██████    | 227405/371472 [7:27:09<12:00:44,  3.33it/s]
 61%|██████    | 227406/371472 [7:27:09<11:45:14,  3.40it/s]
 61%|██████    | 227407/371472 [7:27:09<11:31:31,  3.47it/s]
 61%|██████    | 227408/371472 [7:27:10<11:14:27,  3.56it/s]
 61%|██████    | 227409/371472 [7:27:10<11:15:58,  3.55it/s]
 61%|██████    | 227410/371472 [7:27:10<11:08:44,  3.59it/s]
 61%|██████    | 227411/371472 [7:27:11<11:13:39,  3.56it/s]
 61%|██████    | 227412/371472 [7:27:11<11:48:07,  3.39it/s]
 61%|██████    | 227413/371472 [7:27:11<11:59:16,  3.34it/s]
 61%|██████    | 227414/371472 [7:27:11<12:12:29,  3.28it/s]
 61%|██████    | 227415/371472 [7:27:12<12:11:44,  3.28it/s]
 61%|██████    | 227416/371472 [7:27:12<11:52:58,  3.37it/s]
 61%|██████    | 227417/371472 [7:27:12<11:39:21,  3.43it/s]
 61%|██████    | 227418/371472 [7:27:13<11:55:29,  3.36it/s]
 61%|██████    | 227419/371472 [7:27:13<11:36:11,  3.45it/s]
 61%|██████    | 227420/371472 [7:27:13<11:08:45,  3.59it/s]
                                                            
{'loss': 2.6498, 'learning_rate': 4.4919627658428324e-07, 'epoch': 9.8}
+
 61%|██████    | 227420/371472 [7:27:13<11:08:45,  3.59it/s]
 61%|██████    | 227421/371472 [7:27:13<11:25:36,  3.50it/s]
 61%|██████    | 227422/371472 [7:27:14<12:03:37,  3.32it/s]
 61%|██████    | 227423/371472 [7:27:14<11:47:14,  3.39it/s]
 61%|██████    | 227424/371472 [7:27:14<11:36:04,  3.45it/s]
 61%|██████    | 227425/371472 [7:27:15<11:29:23,  3.48it/s]
 61%|██████    | 227426/371472 [7:27:15<11:04:06,  3.62it/s]
 61%|██████    | 227427/371472 [7:27:15<11:02:58,  3.62it/s]
 61%|██████    | 227428/371472 [7:27:15<11:00:20,  3.64it/s]
 61%|██████    | 227429/371472 [7:27:16<11:15:01,  3.56it/s]
 61%|██████    | 227430/371472 [7:27:16<10:58:27,  3.65it/s]
 61%|██████    | 227431/371472 [7:27:16<11:04:44,  3.61it/s]
 61%|██████    | 227432/371472 [7:27:17<11:11:34,  3.57it/s]
 61%|██████    | 227433/371472 [7:27:17<11:16:30,  3.55it/s]
 61%|██████    | 227434/371472 [7:27:17<11:14:58,  3.56it/s]
 61%|██████    | 227435/371472 [7:27:17<11:11:35,  3.57it/s]
 61%|██████    | 227436/371472 [7:27:18<11:40:42,  3.43it/s]
 61%|██████    | 227437/371472 [7:27:18<11:44:08,  3.41it/s]
 61%|██████    | 227438/371472 [7:27:18<11:22:31,  3.52it/s]
 61%|██████    | 227439/371472 [7:27:19<11:13:08,  3.57it/s]
 61%|██████    | 227440/371472 [7:27:19<10:52:59,  3.68it/s]
                                                            
{'loss': 2.7942, 'learning_rate': 4.491477946088043e-07, 'epoch': 9.8}
+
 61%|██████    | 227440/371472 [7:27:19<10:52:59,  3.68it/s]
 61%|██████    | 227441/371472 [7:27:19<11:05:16,  3.61it/s]
 61%|██████    | 227442/371472 [7:27:19<11:28:14,  3.49it/s]
 61%|██████    | 227443/371472 [7:27:20<11:18:09,  3.54it/s]
 61%|██████    | 227444/371472 [7:27:20<11:11:23,  3.58it/s]
 61%|██████    | 227445/371472 [7:27:20<11:07:07,  3.60it/s]
 61%|██████    | 227446/371472 [7:27:21<11:01:01,  3.63it/s]
 61%|██████    | 227447/371472 [7:27:21<10:54:07,  3.67it/s]
 61%|██████    | 227448/371472 [7:27:21<10:58:10,  3.65it/s]
 61%|██████    | 227449/371472 [7:27:21<10:50:31,  3.69it/s]
 61%|██████    | 227450/371472 [7:27:22<10:48:03,  3.70it/s]
 61%|██████    | 227451/371472 [7:27:22<10:46:39,  3.71it/s]
 61%|██████    | 227452/371472 [7:27:22<11:00:46,  3.63it/s]
 61%|██████    | 227453/371472 [7:27:22<11:19:54,  3.53it/s]
 61%|██████    | 227454/371472 [7:27:23<11:38:21,  3.44it/s]
 61%|██████    | 227455/371472 [7:27:23<11:38:56,  3.43it/s]
 61%|██████    | 227456/371472 [7:27:23<11:19:49,  3.53it/s]
 61%|██████    | 227457/371472 [7:27:24<12:37:05,  3.17it/s]
 61%|██████    | 227458/371472 [7:27:24<12:15:09,  3.26it/s]
 61%|██████    | 227459/371472 [7:27:24<12:05:36,  3.31it/s]
 61%|██████    | 227460/371472 [7:27:25<12:59:58,  3.08it/s]
                                                            
{'loss': 2.7132, 'learning_rate': 4.4909931263332543e-07, 'epoch': 9.8}
+
 61%|██████    | 227460/371472 [7:27:25<12:59:58,  3.08it/s]
 61%|██████    | 227461/371472 [7:27:25<12:25:45,  3.22it/s]
 61%|██████    | 227462/371472 [7:27:25<12:09:38,  3.29it/s]
 61%|██████    | 227463/371472 [7:27:25<11:47:58,  3.39it/s]
 61%|██████    | 227464/371472 [7:27:26<11:48:32,  3.39it/s]
 61%|██████    | 227465/371472 [7:27:26<11:51:54,  3.37it/s]
 61%|██████    | 227466/371472 [7:27:26<11:44:44,  3.41it/s]
 61%|██████    | 227467/371472 [7:27:27<12:13:19,  3.27it/s]
 61%|██████    | 227468/371472 [7:27:27<11:41:39,  3.42it/s]
 61%|██████    | 227469/371472 [7:27:27<11:59:35,  3.34it/s]
 61%|██████    | 227470/371472 [7:27:28<12:09:36,  3.29it/s]
 61%|██████    | 227471/371472 [7:27:28<11:46:09,  3.40it/s]
 61%|██████    | 227472/371472 [7:27:28<11:32:39,  3.46it/s]
 61%|██████    | 227473/371472 [7:27:28<11:29:41,  3.48it/s]
 61%|██████    | 227474/371472 [7:27:29<11:48:31,  3.39it/s]
 61%|██████    | 227475/371472 [7:27:29<12:02:56,  3.32it/s]
 61%|██████    | 227476/371472 [7:27:29<12:17:35,  3.25it/s]
 61%|██████    | 227477/371472 [7:27:30<11:53:05,  3.37it/s]
 61%|██████    | 227478/371472 [7:27:30<12:04:11,  3.31it/s]
 61%|██████    | 227479/371472 [7:27:30<11:46:06,  3.40it/s]
 61%|██████    | 227480/371472 [7:27:31<11:41:04,  3.42it/s]
                                                            
{'loss': 2.773, 'learning_rate': 4.490508306578465e-07, 'epoch': 9.8}
+
 61%|██████    | 227480/371472 [7:27:31<11:41:04,  3.42it/s]
 61%|██████    | 227481/371472 [7:27:31<12:12:40,  3.28it/s]
 61%|██████    | 227482/371472 [7:27:31<12:17:32,  3.25it/s]
 61%|██████    | 227483/371472 [7:27:31<11:44:55,  3.40it/s]
 61%|██████    | 227484/371472 [7:27:32<12:20:13,  3.24it/s]
 61%|██████    | 227485/371472 [7:27:32<11:46:04,  3.40it/s]
 61%|██████    | 227486/371472 [7:27:32<11:35:44,  3.45it/s]
 61%|██████    | 227487/371472 [7:27:33<11:44:08,  3.41it/s]
 61%|██████    | 227488/371472 [7:27:33<12:03:32,  3.32it/s]
 61%|██████    | 227489/371472 [7:27:33<11:50:41,  3.38it/s]
 61%|██████    | 227490/371472 [7:27:34<11:38:02,  3.44it/s]
 61%|██████    | 227491/371472 [7:27:34<11:34:57,  3.45it/s]
 61%|██████    | 227492/371472 [7:27:34<11:25:37,  3.50it/s]
 61%|██████    | 227493/371472 [7:27:34<11:22:23,  3.52it/s]
 61%|██████    | 227494/371472 [7:27:35<11:48:16,  3.39it/s]
 61%|██████    | 227495/371472 [7:27:35<11:11:32,  3.57it/s]
 61%|██████    | 227496/371472 [7:27:35<11:27:34,  3.49it/s]
 61%|██████    | 227497/371472 [7:27:36<11:38:38,  3.43it/s]
 61%|██████    | 227498/371472 [7:27:36<11:25:27,  3.50it/s]
 61%|██████    | 227499/371472 [7:27:36<11:20:56,  3.52it/s]
 61%|██████    | 227500/371472 [7:27:36<11:19:14,  3.53it/s]
                                                            
{'loss': 2.5229, 'learning_rate': 4.490023486823677e-07, 'epoch': 9.8}
+
 61%|██████    | 227500/371472 [7:27:36<11:19:14,  3.53it/s]
 61%|██████    | 227501/371472 [7:27:37<11:16:18,  3.55it/s]
 61%|██████    | 227502/371472 [7:27:37<12:10:50,  3.28it/s]
 61%|██████    | 227503/371472 [7:27:37<12:07:57,  3.30it/s]
 61%|██████    | 227504/371472 [7:27:38<13:11:16,  3.03it/s]
 61%|██████    | 227505/371472 [7:27:38<12:46:48,  3.13it/s]
 61%|██████    | 227506/371472 [7:27:38<12:38:21,  3.16it/s]
 61%|██████    | 227507/371472 [7:27:39<12:11:17,  3.28it/s]
 61%|██████    | 227508/371472 [7:27:39<11:35:43,  3.45it/s]
 61%|██████    | 227509/371472 [7:27:39<11:30:21,  3.48it/s]
 61%|██████    | 227510/371472 [7:27:39<11:33:15,  3.46it/s]
 61%|██████    | 227511/371472 [7:27:40<11:45:05,  3.40it/s]
 61%|██████    | 227512/371472 [7:27:40<11:33:52,  3.46it/s]
 61%|██████    | 227513/371472 [7:27:40<11:35:26,  3.45it/s]
 61%|██████    | 227514/371472 [7:27:41<13:30:33,  2.96it/s]
 61%|██████    | 227515/371472 [7:27:41<12:40:57,  3.15it/s]
 61%|██████    | 227516/371472 [7:27:41<12:40:21,  3.16it/s]
 61%|██████    | 227517/371472 [7:27:42<12:12:16,  3.28it/s]
 61%|██████    | 227518/371472 [7:27:42<11:38:40,  3.43it/s]
 61%|██████    | 227519/371472 [7:27:42<11:59:14,  3.34it/s]
 61%|██████    | 227520/371472 [7:27:42<12:14:01,  3.27it/s]
                                                            
{'loss': 2.7793, 'learning_rate': 4.4895386670688875e-07, 'epoch': 9.8}
+
 61%|██████    | 227520/371472 [7:27:42<12:14:01,  3.27it/s]
 61%|██████    | 227521/371472 [7:27:43<12:00:28,  3.33it/s]
 61%|██████    | 227522/371472 [7:27:43<11:33:40,  3.46it/s]
 61%|██████    | 227523/371472 [7:27:43<11:46:14,  3.40it/s]
 61%|██████    | 227524/371472 [7:27:44<11:37:02,  3.44it/s]
 61%|██████    | 227525/371472 [7:27:44<12:10:18,  3.29it/s]
 61%|██████    | 227526/371472 [7:27:44<12:09:38,  3.29it/s]
 61%|█���████▏   | 227527/371472 [7:27:45<11:53:49,  3.36it/s]
 61%|██████▏   | 227528/371472 [7:27:45<11:24:50,  3.50it/s]
 61%|██████▏   | 227529/371472 [7:27:45<11:38:08,  3.44it/s]
 61%|██████▏   | 227530/371472 [7:27:45<11:35:22,  3.45it/s]
 61%|██████▏   | 227531/371472 [7:27:46<11:24:40,  3.50it/s]
 61%|██████▏   | 227532/371472 [7:27:46<12:31:23,  3.19it/s]
 61%|██████▏   | 227533/371472 [7:27:46<11:59:12,  3.34it/s]
 61%|██████▏   | 227534/371472 [7:27:47<12:26:49,  3.21it/s]
 61%|██████▏   | 227535/371472 [7:27:47<12:00:17,  3.33it/s]
 61%|██████▏   | 227536/371472 [7:27:47<12:45:33,  3.13it/s]
 61%|██████▏   | 227537/371472 [7:27:48<12:24:37,  3.22it/s]
 61%|██████▏   | 227538/371472 [7:27:48<11:50:32,  3.38it/s]
 61%|██████▏   | 227539/371472 [7:27:48<11:28:02,  3.49it/s]
 61%|██████▏   | 227540/371472 [7:27:48<11:43:11,  3.41it/s]
                                                            
{'loss': 2.9072, 'learning_rate': 4.4890538473140977e-07, 'epoch': 9.8}
+
 61%|██████▏   | 227540/371472 [7:27:48<11:43:11,  3.41it/s]
 61%|██████▏   | 227541/371472 [7:27:49<11:49:20,  3.38it/s]
 61%|██████▏   | 227542/371472 [7:27:49<11:15:11,  3.55it/s]
 61%|██████▏   | 227543/371472 [7:27:49<11:09:19,  3.58it/s]
 61%|██████▏   | 227544/371472 [7:27:50<11:10:10,  3.58it/s]
 61%|██████▏   | 227545/371472 [7:27:50<11:37:07,  3.44it/s]
 61%|██████▏   | 227546/371472 [7:27:50<11:38:24,  3.43it/s]
 61%|██████▏   | 227547/371472 [7:27:50<11:38:53,  3.43it/s]
 61%|██████▏   | 227548/371472 [7:27:51<12:36:55,  3.17it/s]
 61%|██████▏   | 227549/371472 [7:27:51<12:19:01,  3.25it/s]
 61%|██████▏   | 227550/371472 [7:27:51<12:04:48,  3.31it/s]
 61%|██████▏   | 227551/371472 [7:27:52<11:53:19,  3.36it/s]
 61%|██████▏   | 227552/371472 [7:27:52<11:31:55,  3.47it/s]
 61%|██████▏   | 227553/371472 [7:27:52<11:50:31,  3.38it/s]
 61%|██████▏   | 227554/371472 [7:27:53<11:47:59,  3.39it/s]
 61%|██████▏   | 227555/371472 [7:27:53<11:16:23,  3.55it/s]
 61%|██████▏   | 227556/371472 [7:27:53<11:41:33,  3.42it/s]
 61%|██████▏   | 227557/371472 [7:27:53<11:26:36,  3.49it/s]
 61%|██████▏   | 227558/371472 [7:27:54<12:10:40,  3.28it/s]
 61%|██████▏   | 227559/371472 [7:27:54<11:48:50,  3.38it/s]
 61%|██████▏   | 227560/371472 [7:27:54<12:35:53,  3.17it/s]
                                                            
{'loss': 2.8125, 'learning_rate': 4.4885690275593095e-07, 'epoch': 9.8}
+
 61%|██████▏   | 227560/371472 [7:27:54<12:35:53,  3.17it/s]
 61%|██████▏   | 227561/371472 [7:27:55<12:17:51,  3.25it/s]
 61%|██████▏   | 227562/371472 [7:27:55<12:32:47,  3.19it/s]
 61%|██████▏   | 227563/371472 [7:27:55<12:31:14,  3.19it/s]
 61%|██████▏   | 227564/371472 [7:27:56<11:58:55,  3.34it/s]
 61%|██████▏   | 227565/371472 [7:27:56<11:44:04,  3.41it/s]
 61%|██████▏   | 227566/371472 [7:27:56<11:16:46,  3.54it/s]
 61%|██████▏   | 227567/371472 [7:27:56<11:59:36,  3.33it/s]
 61%|██████▏   | 227568/371472 [7:27:57<11:39:08,  3.43it/s]
 61%|██████▏   | 227569/371472 [7:27:57<11:46:33,  3.39it/s]
 61%|██████▏   | 227570/371472 [7:27:57<11:29:58,  3.48it/s]
 61%|██████▏   | 227571/371472 [7:27:58<11:43:42,  3.41it/s]
 61%|██████▏   | 227572/371472 [7:27:58<11:16:19,  3.55it/s]
 61%|██████▏   | 227573/371472 [7:27:58<12:35:09,  3.18it/s]
 61%|██████▏   | 227574/371472 [7:27:59<12:05:46,  3.30it/s]
 61%|██████▏   | 227575/371472 [7:27:59<11:29:42,  3.48it/s]
 61%|██████▏   | 227576/371472 [7:27:59<12:00:28,  3.33it/s]
 61%|██████▏   | 227577/371472 [7:27:59<11:44:00,  3.41it/s]
 61%|██████▏   | 227578/371472 [7:28:00<11:44:01,  3.41it/s]
 61%|██████▏   | 227579/371472 [7:28:00<11:37:40,  3.44it/s]
 61%|██████▏   | 227580/371472 [7:28:00<11:55:16,  3.35it/s]
                                                            
{'loss': 2.8258, 'learning_rate': 4.48808420780452e-07, 'epoch': 9.8}
+
 61%|██████▏   | 227580/371472 [7:28:00<11:55:16,  3.35it/s]
 61%|██████▏   | 227581/371472 [7:28:01<11:59:14,  3.33it/s]
 61%|██████▏   | 227582/371472 [7:28:01<11:51:15,  3.37it/s]
 61%|██████▏   | 227583/371472 [7:28:01<11:41:14,  3.42it/s]
 61%|██████▏   | 227584/371472 [7:28:01<11:45:57,  3.40it/s]
 61%|██████▏   | 227585/371472 [7:28:02<11:26:14,  3.49it/s]
 61%|██████▏   | 227586/371472 [7:28:02<11:39:40,  3.43it/s]
 61%|██████▏   | 227587/371472 [7:28:02<11:35:55,  3.45it/s]
 61%|██████▏   | 227588/371472 [7:28:03<11:12:04,  3.57it/s]
 61%|██████▏   | 227589/371472 [7:28:03<11:11:12,  3.57it/s]
 61%|██████▏   | 227590/371472 [7:28:03<11:59:19,  3.33it/s]
 61%|██████▏   | 227591/371472 [7:28:03<12:09:44,  3.29it/s]
 61%|██████▏   | 227592/371472 [7:28:04<12:05:59,  3.30it/s]
 61%|██████▏   | 227593/371472 [7:28:04<11:46:05,  3.40it/s]
 61%|██████▏   | 227594/371472 [7:28:04<11:46:07,  3.40it/s]
 61%|██████▏   | 227595/371472 [7:28:05<11:19:14,  3.53it/s]
 61%|██████▏   | 227596/371472 [7:28:05<11:24:47,  3.50it/s]
 61%|██████▏   | 227597/371472 [7:28:05<11:20:28,  3.52it/s]
 61%|██████▏   | 227598/371472 [7:28:05<11:26:56,  3.49it/s]
 61%|██████▏   | 227599/371472 [7:28:06<11:32:15,  3.46it/s]
 61%|██████▏   | 227600/371472 [7:28:06<13:41:56,  2.92it/s]
                                                            
{'loss': 2.7891, 'learning_rate': 4.4875993880497315e-07, 'epoch': 9.8}
+
 61%|██████▏   | 227600/371472 [7:28:06<13:41:56,  2.92it/s]
 61%|██████▏   | 227601/371472 [7:28:07<13:04:57,  3.05it/s]
 61%|██████▏   | 227602/371472 [7:28:07<12:45:03,  3.13it/s]
 61%|██████▏   | 227603/371472 [7:28:07<12:16:49,  3.25it/s]
 61%|██████▏   | 227604/371472 [7:28:07<12:10:38,  3.28it/s]
 61%|██████▏   | 227605/371472 [7:28:08<11:55:49,  3.35it/s]
 61%|██████▏   | 227606/371472 [7:28:08<12:03:32,  3.31it/s]
 61%|██████▏   | 227607/371472 [7:28:08<11:52:30,  3.37it/s]
 61%|██████▏   | 227608/371472 [7:28:09<11:52:35,  3.36it/s]
 61%|██████▏   | 227609/371472 [7:28:09<12:04:39,  3.31it/s]
 61%|██████▏   | 227610/371472 [7:28:09<12:55:01,  3.09it/s]
 61%|██████▏   | 227611/371472 [7:28:10<12:48:37,  3.12it/s]
 61%|██████▏   | 227612/371472 [7:28:10<12:26:09,  3.21it/s]
 61%|██████▏   | 227613/371472 [7:28:10<11:47:01,  3.39it/s]
 61%|██████▏   | 227614/371472 [7:28:10<11:47:40,  3.39it/s]
 61%|██████▏   | 227615/371472 [7:28:11<12:07:48,  3.29it/s]
 61%|██████▏   | 227616/371472 [7:28:11<12:11:08,  3.28it/s]
 61%|██████▏   | 227617/371472 [7:28:11<12:01:22,  3.32it/s]
 61%|██████▏   | 227618/371472 [7:28:12<12:03:35,  3.31it/s]
 61%|██████▏   | 227619/371472 [7:28:12<11:35:25,  3.45it/s]
 61%|██████▏   | 227620/371472 [7:28:12<12:00:18,  3.33it/s]
                                                            
{'loss': 2.979, 'learning_rate': 4.487114568294942e-07, 'epoch': 9.8}
+
 61%|██████▏   | 227620/371472 [7:28:12<12:00:18,  3.33it/s]
 61%|██████▏   | 227621/371472 [7:28:13<11:44:46,  3.40it/s]
 61%|██████▏   | 227622/371472 [7:28:13<11:39:08,  3.43it/s]
 61%|██████▏   | 227623/371472 [7:28:13<11:47:50,  3.39it/s]
 61%|██████▏   | 227624/371472 [7:28:13<11:30:07,  3.47it/s]
 61%|██████▏   | 227625/371472 [7:28:14<11:16:53,  3.54it/s]
 61%|██████▏   | 227626/371472 [7:28:14<11:08:04,  3.59it/s]
 61%|██████▏   | 227627/371472 [7:28:14<11:32:07,  3.46it/s]
 61%|██████▏   | 227628/371472 [7:28:15<11:28:42,  3.48it/s]
 61%|██████▏   | 227629/371472 [7:28:15<11:20:41,  3.52it/s]
 61%|██████▏   | 227630/371472 [7:28:15<11:27:41,  3.49it/s]
 61%|██████▏   | 227631/371472 [7:28:15<12:27:28,  3.21it/s]
 61%|██████▏   | 227632/371472 [7:28:16<12:18:45,  3.25it/s]
 61%|██████▏   | 227633/371472 [7:28:16<12:18:06,  3.25it/s]
 61%|██████▏   | 227634/371472 [7:28:16<12:18:11,  3.25it/s]
 61%|██████▏   | 227635/371472 [7:28:17<12:30:24,  3.19it/s]
 61%|██████▏   | 227636/371472 [7:28:17<12:00:39,  3.33it/s]
 61%|██████▏   | 227637/371472 [7:28:17<11:51:05,  3.37it/s]
 61%|██████▏   | 227638/371472 [7:28:18<11:41:36,  3.42it/s]
 61%|██████▏   | 227639/371472 [7:28:18<11:41:13,  3.42it/s]
 61%|██████▏   | 227640/371472 [7:28:18<11:39:23,  3.43it/s]
                                                            
{'loss': 2.9353, 'learning_rate': 4.486629748540154e-07, 'epoch': 9.8}
+
 61%|██████▏   | 227640/371472 [7:28:18<11:39:23,  3.43it/s]
 61%|██████▏   | 227641/371472 [7:28:18<11:49:54,  3.38it/s]
 61%|██████▏   | 227642/371472 [7:28:19<12:07:28,  3.30it/s]
 61%|██████▏   | 227643/371472 [7:28:19<11:39:16,  3.43it/s]
 61%|██████▏   | 227644/371472 [7:28:19<11:40:59,  3.42it/s]
 61%|██████▏   | 227645/371472 [7:28:20<11:36:55,  3.44it/s]
 61%|██████▏   | 227646/371472 [7:28:20<11:32:20,  3.46it/s]
 61%|██████▏   | 227647/371472 [7:28:20<11:38:37,  3.43it/s]
 61%|██████▏   | 227648/371472 [7:28:20<11:29:43,  3.48it/s]
 61%|██████▏   | 227649/371472 [7:28:21<11:21:06,  3.52it/s]
 61%|██████▏   | 227650/371472 [7:28:21<12:06:19,  3.30it/s]
 61%|██████▏   | 227651/371472 [7:28:21<12:16:12,  3.26it/s]
 61%|██████▏   | 227652/371472 [7:28:22<13:22:30,  2.99it/s]
 61%|██████▏   | 227653/371472 [7:28:22<13:20:15,  3.00it/s]
 61%|██████▏   | 227654/371472 [7:28:22<12:50:51,  3.11it/s]
 61%|██████▏   | 227655/371472 [7:28:23<12:33:34,  3.18it/s]
 61%|██████▏   | 227656/371472 [7:28:23<12:11:52,  3.28it/s]
 61%|██████▏   | 227657/371472 [7:28:23<11:54:26,  3.35it/s]
 61%|██████▏   | 227658/371472 [7:28:24<11:35:05,  3.45it/s]
 61%|██████▏   | 227659/371472 [7:28:24<11:36:32,  3.44it/s]
 61%|██████▏   | 227660/371472 [7:28:24<11:30:00,  3.47it/s]
                                                            
{'loss': 2.6931, 'learning_rate': 4.486144928785364e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227660/371472 [7:28:24<11:30:00,  3.47it/s]
 61%|██████▏   | 227661/371472 [7:28:24<11:33:31,  3.46it/s]
 61%|██████▏   | 227662/371472 [7:28:25<11:40:46,  3.42it/s]
 61%|██████▏   | 227663/371472 [7:28:25<11:17:48,  3.54it/s]
 61%|██████▏   | 227664/371472 [7:28:25<12:11:53,  3.27it/s]
 61%|██████▏   | 227665/371472 [7:28:26<12:08:38,  3.29it/s]
 61%|██████▏   | 227666/371472 [7:28:26<11:56:53,  3.34it/s]
 61%|██████▏   | 227667/371472 [7:28:26<11:31:17,  3.47it/s]
 61%|██████▏   | 227668/371472 [7:28:26<11:21:10,  3.52it/s]
 61%|██████▏   | 227669/371472 [7:28:27<11:10:14,  3.58it/s]
 61%|██████▏   | 227670/371472 [7:28:27<11:28:43,  3.48it/s]
 61%|██████▏   | 227671/371472 [7:28:27<11:22:53,  3.51it/s]
 61%|██████▏   | 227672/371472 [7:28:28<11:20:51,  3.52it/s]
 61%|██████▏   | 227673/371472 [7:28:28<11:05:53,  3.60it/s]
 61%|██████▏   | 227674/371472 [7:28:28<11:34:51,  3.45it/s]
 61%|██████▏   | 227675/371472 [7:28:28<11:29:25,  3.48it/s]
 61%|██████▏   | 227676/371472 [7:28:29<11:55:31,  3.35it/s]
 61%|██████▏   | 227677/371472 [7:28:29<11:49:41,  3.38it/s]
 61%|██████▏   | 227678/371472 [7:28:29<12:24:40,  3.22it/s]
 61%|██████▏   | 227679/371472 [7:28:30<12:30:08,  3.19it/s]
 61%|██████▏   | 227680/371472 [7:28:30<13:02:41,  3.06it/s]
                                                            
{'loss': 2.7263, 'learning_rate': 4.485660109030576e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227680/371472 [7:28:30<13:02:41,  3.06it/s]
 61%|██████▏   | 227681/371472 [7:28:30<13:23:55,  2.98it/s]
 61%|██████▏   | 227682/371472 [7:28:31<12:44:52,  3.13it/s]
 61%|██████▏   | 227683/371472 [7:28:31<12:29:49,  3.20it/s]
 61%|██████▏   | 227684/371472 [7:28:31<12:38:14,  3.16it/s]
 61%|██████▏   | 227685/371472 [7:28:32<12:23:58,  3.22it/s]
 61%|██████▏   | 227686/371472 [7:28:32<11:59:09,  3.33it/s]
 61%|██████▏   | 227687/371472 [7:28:32<12:09:19,  3.29it/s]
 61%|██████▏   | 227688/371472 [7:28:33<11:49:49,  3.38it/s]
 61%|██████▏   | 227689/371472 [7:28:33<12:35:19,  3.17it/s]
 61%|██████▏   | 227690/371472 [7:28:33<11:52:46,  3.36it/s]
 61%|██████▏   | 227691/371472 [7:28:33<11:48:06,  3.38it/s]
 61%|██████▏   | 227692/371472 [7:28:34<11:16:12,  3.54it/s]
 61%|██████▏   | 227693/371472 [7:28:34<11:29:27,  3.48it/s]
 61%|██████▏   | 227694/371472 [7:28:34<11:42:49,  3.41it/s]
 61%|██████▏   | 227695/371472 [7:28:35<11:26:42,  3.49it/s]
 61%|██████▏   | 227696/371472 [7:28:35<11:40:36,  3.42it/s]
 61%|██████▏   | 227697/371472 [7:28:35<11:39:40,  3.42it/s]
 61%|██████▏   | 227698/371472 [7:28:36<13:31:14,  2.95it/s]
 61%|██████▏   | 227699/371472 [7:28:36<12:41:23,  3.15it/s]
 61%|██████▏   | 227700/371472 [7:28:36<12:10:17,  3.28it/s]
                                                            
{'loss': 2.6593, 'learning_rate': 4.4851752892757866e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227700/371472 [7:28:36<12:10:17,  3.28it/s]
 61%|██████▏   | 227701/371472 [7:28:36<12:35:23,  3.17it/s]
 61%|██████▏   | 227702/371472 [7:28:37<12:03:37,  3.31it/s]
 61%|██████▏   | 227703/371472 [7:28:37<12:12:43,  3.27it/s]
 61%|██████▏   | 227704/371472 [7:28:37<12:08:37,  3.29it/s]
 61%|██████▏   | 227705/371472 [7:28:38<12:28:41,  3.20it/s]
 61%|██████▏   | 227706/371472 [7:28:38<11:54:14,  3.35it/s]
 61%|██████▏   | 227707/371472 [7:28:38<11:51:37,  3.37it/s]
 61%|██████▏   | 227708/371472 [7:28:39<11:32:59,  3.46it/s]
 61%|██████▏   | 227709/371472 [7:28:39<11:52:57,  3.36it/s]
 61%|██████▏   | 227710/371472 [7:28:39<11:40:58,  3.42it/s]
 61%|██████▏   | 227711/371472 [7:28:39<12:10:13,  3.28it/s]
 61%|██████▏   | 227712/371472 [7:28:40<11:59:12,  3.33it/s]
 61%|██████▏   | 227713/371472 [7:28:40<11:32:28,  3.46it/s]
 61%|██████▏   | 227714/371472 [7:28:40<11:56:00,  3.35it/s]
 61%|██████▏   | 227715/371472 [7:28:41<11:57:06,  3.34it/s]
 61%|██████▏   | 227716/371472 [7:28:41<11:36:41,  3.44it/s]
 61%|██████▏   | 227717/371472 [7:28:41<11:26:55,  3.49it/s]
 61%|██████▏   | 227718/371472 [7:28:41<11:38:04,  3.43it/s]
 61%|██████▏   | 227719/371472 [7:28:42<11:13:14,  3.56it/s]
 61%|██████▏   | 227720/371472 [7:28:42<10:51:06,  3.68it/s]
                                                            
{'loss': 2.6925, 'learning_rate': 4.484690469520998e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227720/371472 [7:28:42<10:51:06,  3.68it/s]
 61%|██████▏   | 227721/371472 [7:28:42<10:42:27,  3.73it/s]
 61%|██████▏   | 227722/371472 [7:28:43<11:24:18,  3.50it/s]
 61%|██████▏   | 227723/371472 [7:28:43<11:24:00,  3.50it/s]
 61%|██████▏   | 227724/371472 [7:28:43<11:50:39,  3.37it/s]
 61%|██████▏   | 227725/371472 [7:28:43<11:39:57,  3.42it/s]
 61%|██████▏   | 227726/371472 [7:28:44<11:40:07,  3.42it/s]
 61%|██████▏   | 227727/371472 [7:28:44<11:20:24,  3.52it/s]
 61%|██████▏   | 227728/371472 [7:28:44<11:27:51,  3.48it/s]
 61%|██████▏   | 227729/371472 [7:28:45<11:31:08,  3.47it/s]
 61%|██████▏   | 227730/371472 [7:28:45<11:03:44,  3.61it/s]
 61%|██████▏   | 227731/371472 [7:28:45<11:13:54,  3.55it/s]
 61%|██████▏   | 227732/371472 [7:28:45<11:50:11,  3.37it/s]
 61%|██████▏   | 227733/371472 [7:28:46<11:35:17,  3.45it/s]
 61%|██████▏   | 227734/371472 [7:28:46<11:39:12,  3.43it/s]
 61%|██████▏   | 227735/371472 [7:28:46<11:37:37,  3.43it/s]
 61%|██████▏   | 227736/371472 [7:28:47<11:23:05,  3.51it/s]
 61%|██████▏   | 227737/371472 [7:28:47<11:09:34,  3.58it/s]
 61%|██████▏   | 227738/371472 [7:28:47<11:06:28,  3.59it/s]
 61%|██████▏   | 227739/371472 [7:28:47<11:10:20,  3.57it/s]
 61%|██████▏   | 227740/371472 [7:28:48<10:54:16,  3.66it/s]
                                                            
{'loss': 2.8602, 'learning_rate': 4.4842056497662086e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227740/371472 [7:28:48<10:54:16,  3.66it/s]
 61%|██████▏   | 227741/371472 [7:28:48<11:24:55,  3.50it/s]
 61%|██████▏   | 227742/371472 [7:28:48<11:21:45,  3.51it/s]
 61%|██████▏   | 227743/371472 [7:28:49<11:14:04,  3.55it/s]
 61%|██████▏   | 227744/371472 [7:28:49<11:00:01,  3.63it/s]
 61%|██████▏   | 227745/371472 [7:28:49<11:15:41,  3.55it/s]
 61%|██████▏   | 227746/371472 [7:28:49<11:11:36,  3.57it/s]
 61%|██████▏   | 227747/371472 [7:28:50<11:09:28,  3.58it/s]
 61%|██████▏   | 227748/371472 [7:28:50<11:56:38,  3.34it/s]
 61%|██████▏   | 227749/371472 [7:28:50<11:52:16,  3.36it/s]
 61%|██████▏   | 227750/371472 [7:28:51<11:36:50,  3.44it/s]
 61%|██████▏   | 227751/371472 [7:28:51<11:17:22,  3.54it/s]
 61%|██████▏   | 227752/371472 [7:28:51<11:05:41,  3.60it/s]
 61%|██████▏   | 227753/371472 [7:28:51<11:02:20,  3.62it/s]
 61%|██████▏   | 227754/371472 [7:28:52<11:31:44,  3.46it/s]
 61%|██████▏   | 227755/371472 [7:28:52<11:25:31,  3.49it/s]
 61%|██████▏   | 227756/371472 [7:28:52<12:02:52,  3.31it/s]
 61%|██████▏   | 227757/371472 [7:28:53<11:29:12,  3.48it/s]
 61%|██████▏   | 227758/371472 [7:28:53<12:13:13,  3.27it/s]
 61%|██████▏   | 227759/371472 [7:28:53<11:36:16,  3.44it/s]
 61%|██████▏   | 227760/371472 [7:28:54<12:06:47,  3.30it/s]
                                                            
{'loss': 2.7879, 'learning_rate': 4.4837208300114204e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227760/371472 [7:28:54<12:06:47,  3.30it/s]
 61%|██████▏   | 227761/371472 [7:28:54<12:16:55,  3.25it/s]
 61%|██████▏   | 227762/371472 [7:28:54<12:38:22,  3.16it/s]
 61%|██████▏   | 227763/371472 [7:28:54<12:20:33,  3.23it/s]
 61%|██████▏   | 227764/371472 [7:28:55<12:35:02,  3.17it/s]
 61%|██████▏   | 227765/371472 [7:28:55<12:31:46,  3.19it/s]
 61%|██████▏   | 227766/371472 [7:28:55<12:07:20,  3.29it/s]
 61%|██████▏   | 227767/371472 [7:28:56<11:45:35,  3.39it/s]
 61%|██████▏   | 227768/371472 [7:28:56<11:25:13,  3.50it/s]
 61%|██████▏   | 227769/371472 [7:28:56<11:38:38,  3.43it/s]
 61%|██████▏   | 227770/371472 [7:28:57<11:37:29,  3.43it/s]
 61%|██████▏   | 227771/371472 [7:28:57<11:27:23,  3.48it/s]
 61%|██████▏   | 227772/371472 [7:28:57<11:07:12,  3.59it/s]
 61%|██████▏   | 227773/371472 [7:28:57<12:05:17,  3.30it/s]
 61%|██████▏   | 227774/371472 [7:28:58<11:43:38,  3.40it/s]
 61%|██████▏   | 227775/371472 [7:28:58<11:45:13,  3.40it/s]
 61%|██████▏   | 227776/371472 [7:28:58<11:40:09,  3.42it/s]
 61%|██████▏   | 227777/371472 [7:28:59<12:55:41,  3.09it/s]
 61%|██████▏   | 227778/371472 [7:28:59<12:15:30,  3.26it/s]
 61%|██████▏   | 227779/371472 [7:28:59<12:23:58,  3.22it/s]
 61%|██████▏   | 227780/371472 [7:29:00<11:54:02,  3.35it/s]
                                                            
{'loss': 3.0059, 'learning_rate': 4.4832360102566305e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227780/371472 [7:29:00<11:54:02,  3.35it/s]
 61%|██████▏   | 227781/371472 [7:29:00<11:41:43,  3.41it/s]
 61%|██████▏   | 227782/371472 [7:29:00<12:10:16,  3.28it/s]
 61%|██████▏   | 227783/371472 [7:29:00<11:55:45,  3.35it/s]
 61%|██████▏   | 227784/371472 [7:29:01<12:59:40,  3.07it/s]
 61%|██████▏   | 227785/371472 [7:29:01<12:32:38,  3.18it/s]
 61%|██████▏   | 227786/371472 [7:29:01<13:01:27,  3.06it/s]
 61%|██████▏   | 227787/371472 [7:29:02<13:03:24,  3.06it/s]
 61%|██████▏   | 227788/371472 [7:29:02<12:10:52,  3.28it/s]
 61%|██████▏   | 227789/371472 [7:29:02<12:45:07,  3.13it/s]
 61%|██████▏   | 227790/371472 [7:29:03<12:14:54,  3.26it/s]
 61%|██████▏   | 227791/371472 [7:29:03<11:45:18,  3.40it/s]
 61%|██████▏   | 227792/371472 [7:29:03<11:33:08,  3.45it/s]
 61%|██████▏   | 227793/371472 [7:29:04<11:27:20,  3.48it/s]
 61%|██████▏   | 227794/371472 [7:29:04<11:29:07,  3.47it/s]
 61%|██████▏   | 227795/371472 [7:29:04<11:47:53,  3.38it/s]
 61%|██████▏   | 227796/371472 [7:29:04<11:38:51,  3.43it/s]
 61%|██████▏   | 227797/371472 [7:29:05<11:29:40,  3.47it/s]
 61%|██████▏   | 227798/371472 [7:29:05<11:52:31,  3.36it/s]
 61%|██████▏   | 227799/371472 [7:29:05<11:57:57,  3.34it/s]
 61%|██████▏   | 227800/371472 [7:29:06<11:45:46,  3.39it/s]
                                                            
{'loss': 2.7912, 'learning_rate': 4.4827511905018423e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227800/371472 [7:29:06<11:45:46,  3.39it/s]
 61%|██████▏   | 227801/371472 [7:29:06<12:06:58,  3.29it/s]
 61%|██████▏   | 227802/371472 [7:29:06<12:05:24,  3.30it/s]
 61%|██████▏   | 227803/371472 [7:29:06<11:53:03,  3.36it/s]
 61%|██████▏   | 227804/371472 [7:29:07<11:50:48,  3.37it/s]
 61%|██████▏   | 227805/371472 [7:29:07<11:42:37,  3.41it/s]
 61%|██████▏   | 227806/371472 [7:29:07<12:22:28,  3.22it/s]
 61%|██████▏   | 227807/371472 [7:29:08<11:58:14,  3.33it/s]
 61%|██████▏   | 227808/371472 [7:29:08<11:54:40,  3.35it/s]
 61%|██████▏   | 227809/371472 [7:29:08<11:42:22,  3.41it/s]
 61%|██████▏   | 227810/371472 [7:29:09<12:21:46,  3.23it/s]
 61%|██████▏   | 227811/371472 [7:29:09<13:06:54,  3.04it/s]
 61%|██████▏   | 227812/371472 [7:29:09<13:15:01,  3.01it/s]
 61%|██████▏   | 227813/371472 [7:29:10<12:31:55,  3.18it/s]
 61%|██████▏   | 227814/371472 [7:29:10<12:03:59,  3.31it/s]
 61%|██████▏   | 227815/371472 [7:29:10<12:14:16,  3.26it/s]
 61%|██████▏   | 227816/371472 [7:29:11<12:28:04,  3.20it/s]
 61%|██████▏   | 227817/371472 [7:29:11<12:47:07,  3.12it/s]
 61%|██████▏   | 227818/371472 [7:29:11<12:33:40,  3.18it/s]
 61%|██████▏   | 227819/371472 [7:29:11<12:25:58,  3.21it/s]
 61%|██████▏   | 227820/371472 [7:29:12<12:49:51,  3.11it/s]
                                                            
{'loss': 2.9112, 'learning_rate': 4.482266370747053e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227820/371472 [7:29:12<12:49:51,  3.11it/s]
 61%|██████▏   | 227821/371472 [7:29:12<13:22:07,  2.98it/s]
 61%|██████▏   | 227822/371472 [7:29:12<12:46:03,  3.13it/s]
 61%|██████▏   | 227823/371472 [7:29:13<12:18:03,  3.24it/s]
 61%|██████▏   | 227824/371472 [7:29:13<12:09:22,  3.28it/s]
 61%|██████▏   | 227825/371472 [7:29:13<11:59:19,  3.33it/s]
 61%|██████▏   | 227826/371472 [7:29:14<11:44:27,  3.40it/s]
 61%|██████▏   | 227827/371472 [7:29:14<12:18:27,  3.24it/s]
 61%|██████▏   | 227828/371472 [7:29:14<12:01:29,  3.32it/s]
 61%|██████▏   | 227829/371472 [7:29:15<12:08:00,  3.29it/s]
 61%|██████▏   | 227830/371472 [7:29:15<11:56:12,  3.34it/s]
 61%|██████▏   | 227831/371472 [7:29:15<11:42:33,  3.41it/s]
 61%|██████▏   | 227832/371472 [7:29:15<11:46:11,  3.39it/s]
 61%|██████▏   | 227833/371472 [7:29:16<11:54:26,  3.35it/s]
 61%|██████▏   | 227834/371472 [7:29:16<12:30:23,  3.19it/s]
 61%|██████▏   | 227835/371472 [7:29:16<12:04:26,  3.30it/s]
 61%|██████▏   | 227836/371472 [7:29:17<11:48:38,  3.38it/s]
 61%|██████▏   | 227837/371472 [7:29:17<12:30:08,  3.19it/s]
 61%|██████▏   | 227838/371472 [7:29:17<13:58:45,  2.85it/s]
 61%|██████▏   | 227839/371472 [7:29:18<13:32:31,  2.95it/s]
 61%|██████▏   | 227840/371472 [7:29:18<13:15:51,  3.01it/s]
                                                            
{'loss': 2.8648, 'learning_rate': 4.4817815509922643e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227840/371472 [7:29:18<13:15:51,  3.01it/s]
 61%|██████▏   | 227841/371472 [7:29:18<13:39:48,  2.92it/s]
 61%|██████▏   | 227842/371472 [7:29:19<14:04:48,  2.83it/s]
 61%|██████▏   | 227843/371472 [7:29:19<13:19:22,  2.99it/s]
 61%|██████▏   | 227844/371472 [7:29:19<12:37:00,  3.16it/s]
 61%|██████▏   | 227845/371472 [7:29:20<12:38:15,  3.16it/s]
 61%|██████▏   | 227846/371472 [7:29:20<12:24:34,  3.21it/s]
 61%|██████▏   | 227847/371472 [7:29:20<11:53:16,  3.36it/s]
 61%|██████▏   | 227848/371472 [7:29:21<11:48:29,  3.38it/s]
 61%|██████▏   | 227849/371472 [7:29:21<11:41:51,  3.41it/s]
 61%|██████▏   | 227850/371472 [7:29:21<11:19:31,  3.52it/s]
 61%|██████▏   | 227851/371472 [7:29:21<11:09:40,  3.57it/s]
 61%|██████▏   | 227852/371472 [7:29:22<11:39:55,  3.42it/s]
 61%|██████▏   | 227853/371472 [7:29:22<11:33:36,  3.45it/s]
 61%|██████▏   | 227854/371472 [7:29:22<11:20:21,  3.52it/s]
 61%|██████▏   | 227855/371472 [7:29:23<11:16:25,  3.54it/s]
 61%|██████▏   | 227856/371472 [7:29:23<11:52:48,  3.36it/s]
 61%|██████▏   | 227857/371472 [7:29:23<11:29:19,  3.47it/s]
 61%|██████▏   | 227858/371472 [7:29:23<11:24:34,  3.50it/s]
 61%|██████▏   | 227859/371472 [7:29:24<11:27:47,  3.48it/s]
 61%|██████▏   | 227860/371472 [7:29:24<11:51:13,  3.37it/s]
                                                            
{'loss': 2.9697, 'learning_rate': 4.481296731237475e-07, 'epoch': 9.81}
+
 61%|██████▏   | 227860/371472 [7:29:24<11:51:13,  3.37it/s]
 61%|██████▏   | 227861/371472 [7:29:24<11:30:14,  3.47it/s]
 61%|██████▏   | 227862/371472 [7:29:25<11:21:44,  3.51it/s]
 61%|██████▏   | 227863/371472 [7:29:25<10:59:02,  3.63it/s]
 61%|██████▏   | 227864/371472 [7:29:25<11:04:21,  3.60it/s]
 61%|██████▏   | 227865/371472 [7:29:25<11:15:51,  3.54it/s]
 61%|██████▏   | 227866/371472 [7:29:26<11:24:07,  3.50it/s]
 61%|██████▏   | 227867/371472 [7:29:26<12:45:21,  3.13it/s]
 61%|██████▏   | 227868/371472 [7:29:26<12:18:57,  3.24it/s]
 61%|██████▏   | 227869/371472 [7:29:27<11:50:53,  3.37it/s]
 61%|██████▏   | 227870/371472 [7:29:27<12:05:47,  3.30it/s]
 61%|██████▏   | 227871/371472 [7:29:27<11:46:39,  3.39it/s]
 61%|██████▏   | 227872/371472 [7:29:28<12:49:01,  3.11it/s]
 61%|██████▏   | 227873/371472 [7:29:28<12:24:55,  3.21it/s]
 61%|██████▏   | 227874/371472 [7:29:28<12:17:03,  3.25it/s]
 61%|██████▏   | 227875/371472 [7:29:28<11:48:47,  3.38it/s]
 61%|██████▏   | 227876/371472 [7:29:29<11:36:27,  3.44it/s]
 61%|██████▏   | 227877/371472 [7:29:29<11:39:53,  3.42it/s]
 61%|██████▏   | 227878/371472 [7:29:29<11:15:16,  3.54it/s]
 61%|██████▏   | 227879/371472 [7:29:30<11:21:42,  3.51it/s]
 61%|██████▏   | 227880/371472 [7:29:30<11:39:41,  3.42it/s]
                                                            
{'loss': 2.8356, 'learning_rate': 4.480811911482687e-07, 'epoch': 9.82}
+
 61%|██████▏   | 227880/371472 [7:29:30<11:39:41,  3.42it/s]
 61%|██████▏   | 227881/371472 [7:29:30<11:34:47,  3.44it/s]
 61%|██████▏   | 227882/371472 [7:29:30<11:34:44,  3.44it/s]
 61%|██████▏   | 227883/371472 [7:29:31<11:23:20,  3.50it/s]
 61%|██████▏   | 227884/371472 [7:29:31<11:41:07,  3.41it/s]
 61%|██████▏   | 227885/371472 [7:29:31<11:47:57,  3.38it/s]
 61%|██████▏   | 227886/371472 [7:29:32<12:06:47,  3.29it/s]
 61%|██████▏   | 227887/371472 [7:29:32<13:06:48,  3.04it/s]
 61%|██████▏   | 227888/371472 [7:29:32<12:31:17,  3.19it/s]
 61%|██████▏   | 227889/371472 [7:29:33<12:12:25,  3.27it/s]
 61%|██████▏   | 227890/371472 [7:29:33<11:59:25,  3.33it/s]
 61%|██████▏   | 227891/371472 [7:29:33<11:55:05,  3.35it/s]
 61%|██████▏   | 227892/371472 [7:29:34<11:59:19,  3.33it/s]
 61%|██████▏   | 227893/371472 [7:29:34<11:55:41,  3.34it/s]
 61%|██████▏   | 227894/371472 [7:29:34<11:49:44,  3.37it/s]
 61%|██████▏   | 227895/371472 [7:29:34<11:51:33,  3.36it/s]
 61%|██████▏   | 227896/371472 [7:29:35<11:44:07,  3.40it/s]
 61%|██████▏   | 227897/371472 [7:29:35<11:29:52,  3.47it/s]
 61%|██████▏   | 227898/371472 [7:29:35<13:11:49,  3.02it/s]
 61%|██████▏   | 227899/371472 [7:29:36<13:15:53,  3.01it/s]
 61%|██████▏   | 227900/371472 [7:29:36<12:28:24,  3.20it/s]
                                                            
{'loss': 2.8096, 'learning_rate': 4.4803270917278975e-07, 'epoch': 9.82}
+
 61%|██████▏   | 227900/371472 [7:29:36<12:28:24,  3.20it/s]
 61%|██████▏   | 227901/371472 [7:29:36<11:57:26,  3.34it/s]
 61%|██████▏   | 227902/371472 [7:29:37<12:17:47,  3.24it/s]
 61%|██████▏   | 227903/371472 [7:29:37<12:04:14,  3.30it/s]
 61%|██████▏   | 227904/371472 [7:29:37<11:36:53,  3.43it/s]
 61%|██████▏   | 227905/371472 [7:29:37<11:42:40,  3.41it/s]
 61%|██████▏   | 227906/371472 [7:29:38<12:14:35,  3.26it/s]
 61%|██████▏   | 227907/371472 [7:29:38<11:48:41,  3.38it/s]
 61%|██████▏   | 227908/371472 [7:29:38<11:28:13,  3.48it/s]
 61%|██████▏   | 227909/371472 [7:29:39<11:20:30,  3.52it/s]
 61%|██████▏   | 227910/371472 [7:29:39<11:38:18,  3.43it/s]
 61%|██████▏   | 227911/371472 [7:29:39<11:24:52,  3.49it/s]
 61%|██████▏   | 227912/371472 [7:29:39<11:23:17,  3.50it/s]
 61%|██████▏   | 227913/371472 [7:29:40<11:16:42,  3.54it/s]
 61%|██████▏   | 227914/371472 [7:29:40<11:12:30,  3.56it/s]
 61%|██████▏   | 227915/371472 [7:29:40<11:11:03,  3.57it/s]
 61%|██████▏   | 227916/371472 [7:29:41<11:15:03,  3.54it/s]
 61%|██████▏   | 227917/371472 [7:29:41<11:08:19,  3.58it/s]
 61%|██████▏   | 227918/371472 [7:29:41<10:58:39,  3.63it/s]
 61%|██████▏   | 227919/371472 [7:29:41<12:10:51,  3.27it/s]
 61%|██████▏   | 227920/371472 [7:29:42<11:39:07,  3.42it/s]
                                                            
{'loss': 2.8205, 'learning_rate': 4.4798422719731087e-07, 'epoch': 9.82}
+
 61%|██████▏   | 227920/371472 [7:29:42<11:39:07,  3.42it/s]
 61%|██████▏   | 227921/371472 [7:29:42<12:43:59,  3.13it/s]
 61%|██████▏   | 227922/371472 [7:29:43<13:13:47,  3.01it/s]
 61%|██████▏   | 227923/371472 [7:29:43<13:04:22,  3.05it/s]
 61%|██████▏   | 227924/371472 [7:29:43<13:17:36,  3.00it/s]
 61%|██████▏   | 227925/371472 [7:29:44<13:37:03,  2.93it/s]
 61%|██████▏   | 227926/371472 [7:29:44<14:00:54,  2.85it/s]
 61%|██████▏   | 227927/371472 [7:29:44<13:37:40,  2.93it/s]
 61%|██████▏   | 227928/371472 [7:29:45<13:00:40,  3.06it/s]
 61%|██████▏   | 227929/371472 [7:29:45<13:04:58,  3.05it/s]
 61%|██████▏   | 227930/371472 [7:29:45<13:04:55,  3.05it/s]
 61%|██████▏   | 227931/371472 [7:29:45<12:59:33,  3.07it/s]
 61%|██████▏   | 227932/371472 [7:29:46<12:40:44,  3.14it/s]
 61%|██████▏   | 227933/371472 [7:29:46<12:15:38,  3.25it/s]
 61%|██████▏   | 227934/371472 [7:29:46<12:01:08,  3.32it/s]
 61%|██████▏   | 227935/371472 [7:29:47<11:51:49,  3.36it/s]
 61%|██████▏   | 227936/371472 [7:29:47<11:51:19,  3.36it/s]
 61%|██████▏   | 227937/371472 [7:29:47<12:04:45,  3.30it/s]
 61%|██████▏   | 227938/371472 [7:29:48<12:15:02,  3.25it/s]
 61%|██████▏   | 227939/371472 [7:29:48<11:59:47,  3.32it/s]
 61%|██████▏   | 227940/371472 [7:29:48<12:00:02,  3.32it/s]
                                                            
{'loss': 2.9274, 'learning_rate': 4.4793574522183194e-07, 'epoch': 9.82}
+
 61%|██████▏   | 227940/371472 [7:29:48<12:00:02,  3.32it/s]
 61%|██████▏   | 227941/371472 [7:29:48<11:45:03,  3.39it/s]
 61%|██████▏   | 227942/371472 [7:29:49<11:48:37,  3.38it/s]
 61%|██████▏   | 227943/371472 [7:29:49<11:35:44,  3.44it/s]
 61%|██████▏   | 227944/371472 [7:29:49<11:46:11,  3.39it/s]
 61%|██████▏   | 227945/371472 [7:29:50<11:46:38,  3.39it/s]
 61%|█��████▏   | 227946/371472 [7:29:50<11:35:44,  3.44it/s]
 61%|██████▏   | 227947/371472 [7:29:50<11:32:18,  3.46it/s]
 61%|██████▏   | 227948/371472 [7:29:50<11:25:28,  3.49it/s]
 61%|██████▏   | 227949/371472 [7:29:51<11:30:48,  3.46it/s]
 61%|██████▏   | 227950/371472 [7:29:51<11:12:50,  3.56it/s]
 61%|██████▏   | 227951/371472 [7:29:51<11:20:34,  3.51it/s]
 61%|██████▏   | 227952/371472 [7:29:52<11:27:03,  3.48it/s]
 61%|██████▏   | 227953/371472 [7:29:52<11:27:57,  3.48it/s]
 61%|██████▏   | 227954/371472 [7:29:52<11:47:29,  3.38it/s]
 61%|██████▏   | 227955/371472 [7:29:53<12:33:31,  3.17it/s]
 61%|██████▏   | 227956/371472 [7:29:53<12:04:06,  3.30it/s]
 61%|██████▏   | 227957/371472 [7:29:53<11:32:34,  3.45it/s]
 61%|██████▏   | 227958/371472 [7:29:53<11:46:25,  3.39it/s]
 61%|██████▏   | 227959/371472 [7:29:54<11:45:45,  3.39it/s]
 61%|██████▏   | 227960/371472 [7:29:54<11:30:35,  3.46it/s]
                                                            
{'loss': 2.7424, 'learning_rate': 4.478872632463531e-07, 'epoch': 9.82}
+
 61%|██████▏   | 227960/371472 [7:29:54<11:30:35,  3.46it/s]
 61%|██████▏   | 227961/371472 [7:29:54<11:42:18,  3.41it/s]
 61%|██████▏   | 227962/371472 [7:29:55<12:07:29,  3.29it/s]
 61%|██████▏   | 227963/371472 [7:29:55<12:20:52,  3.23it/s]
 61%|██████▏   | 227964/371472 [7:29:55<12:01:38,  3.31it/s]
 61%|██████▏   | 227965/371472 [7:29:56<11:52:16,  3.36it/s]
 61%|██████▏   | 227966/371472 [7:29:56<11:53:46,  3.35it/s]
 61%|██████▏   | 227967/371472 [7:29:56<11:41:31,  3.41it/s]
 61%|██████▏   | 227968/371472 [7:29:56<11:52:43,  3.36it/s]
 61%|██████▏   | 227969/371472 [7:29:57<11:35:59,  3.44it/s]
 61%|██████▏   | 227970/371472 [7:29:57<11:25:43,  3.49it/s]
 61%|██████▏   | 227971/371472 [7:29:57<11:53:43,  3.35it/s]
 61%|██████▏   | 227972/371472 [7:29:58<12:23:58,  3.21it/s]
 61%|██████▏   | 227973/371472 [7:29:58<11:59:55,  3.32it/s]
 61%|██████▏   | 227974/371472 [7:29:58<11:45:20,  3.39it/s]
 61%|██████▏   | 227975/371472 [7:29:58<11:45:31,  3.39it/s]
 61%|██████▏   | 227976/371472 [7:29:59<12:40:44,  3.14it/s]
 61%|██████▏   | 227977/371472 [7:29:59<13:11:24,  3.02it/s]
 61%|██████▏   | 227978/371472 [7:30:00<12:51:34,  3.10it/s]
 61%|██████▏   | 227979/371472 [7:30:00<12:33:46,  3.17it/s]
 61%|██████▏   | 227980/371472 [7:30:00<12:49:05,  3.11it/s]
                                                            
{'loss': 2.7874, 'learning_rate': 4.4783878127087414e-07, 'epoch': 9.82}
+
 61%|██████▏   | 227980/371472 [7:30:00<12:49:05,  3.11it/s]
 61%|██████▏   | 227981/371472 [7:30:00<12:26:23,  3.20it/s]
 61%|██████▏   | 227982/371472 [7:30:01<12:02:27,  3.31it/s]
 61%|██████▏   | 227983/371472 [7:30:01<11:55:03,  3.34it/s]
 61%|██████▏   | 227984/371472 [7:30:01<11:59:59,  3.32it/s]
 61%|██████▏   | 227985/371472 [7:30:02<12:24:22,  3.21it/s]
 61%|██████▏   | 227986/371472 [7:30:02<12:18:39,  3.24it/s]
 61%|██████▏   | 227987/371472 [7:30:02<12:26:30,  3.20it/s]
 61%|██████▏   | 227988/371472 [7:30:03<13:33:13,  2.94it/s]
 61%|██████▏   | 227989/371472 [7:30:03<12:46:50,  3.12it/s]
 61%|██████▏   | 227990/371472 [7:30:03<12:23:11,  3.22it/s]
 61%|██████▏   | 227991/371472 [7:30:04<12:08:36,  3.28it/s]
 61%|██████▏   | 227992/371472 [7:30:04<11:58:24,  3.33it/s]
 61%|██████▏   | 227993/371472 [7:30:04<12:33:13,  3.17it/s]
 61%|██████▏   | 227994/371472 [7:30:05<12:43:49,  3.13it/s]
 61%|██████▏   | 227995/371472 [7:30:05<12:30:45,  3.19it/s]
 61%|██████▏   | 227996/371472 [7:30:05<11:58:43,  3.33it/s]
 61%|██████▏   | 227997/371472 [7:30:05<11:50:32,  3.37it/s]
 61%|██████▏   | 227998/371472 [7:30:06<11:32:41,  3.45it/s]
 61%|██████▏   | 227999/371472 [7:30:06<11:11:02,  3.56it/s]
 61%|██████▏   | 228000/371472 [7:30:06<11:03:04,  3.61it/s]
                                                            
{'loss': 2.9248, 'learning_rate': 4.477902992953953e-07, 'epoch': 9.82}
+
 61%|██████▏   | 228000/371472 [7:30:06<11:03:04,  3.61it/s]
 61%|██████▏   | 228001/371472 [7:30:06<11:15:21,  3.54it/s]
 61%|██████▏   | 228002/371472 [7:30:07<11:01:30,  3.61it/s]
 61%|██████▏   | 228003/371472 [7:30:07<11:26:36,  3.48it/s]
 61%|██████▏   | 228004/371472 [7:30:07<12:15:32,  3.25it/s]
 61%|██████▏   | 228005/371472 [7:30:08<13:11:49,  3.02it/s]
 61%|██████▏   | 228006/371472 [7:30:08<12:46:43,  3.12it/s]
 61%|██████▏   | 228007/371472 [7:30:08<12:40:51,  3.14it/s]
 61%|██████▏   | 228008/371472 [7:30:09<12:32:18,  3.18it/s]
 61%|██████▏   | 228009/371472 [7:30:09<12:27:59,  3.20it/s]
 61%|██████▏   | 228010/371472 [7:30:09<11:49:14,  3.37it/s]
 61%|██████▏   | 228011/371472 [7:30:10<11:52:15,  3.36it/s]
 61%|██████▏   | 228012/371472 [7:30:10<11:41:45,  3.41it/s]
 61%|██████▏   | 228013/371472 [7:30:10<11:29:44,  3.47it/s]
 61%|██████▏   | 228014/371472 [7:30:10<11:27:28,  3.48it/s]
 61%|██████▏   | 228015/371472 [7:30:11<11:23:32,  3.50it/s]
 61%|██████▏   | 228016/371472 [7:30:11<11:26:40,  3.48it/s]
 61%|██████▏   | 228017/371472 [7:30:11<11:34:45,  3.44it/s]
 61%|██████▏   | 228018/371472 [7:30:12<11:37:00,  3.43it/s]
 61%|██████▏   | 228019/371472 [7:30:12<11:35:20,  3.44it/s]
 61%|██████▏   | 228020/371472 [7:30:12<11:54:41,  3.35it/s]
                                                            
{'loss': 2.7727, 'learning_rate': 4.477418173199164e-07, 'epoch': 9.82}
+
 61%|██████▏   | 228020/371472 [7:30:12<11:54:41,  3.35it/s]
 61%|██████▏   | 228021/371472 [7:30:12<12:05:36,  3.29it/s]
 61%|██████▏   | 228022/371472 [7:30:13<12:18:42,  3.24it/s]
 61%|██████▏   | 228023/371472 [7:30:13<12:05:50,  3.29it/s]
 61%|██████▏   | 228024/371472 [7:30:13<12:20:46,  3.23it/s]
 61%|██████▏   | 228025/371472 [7:30:14<12:05:55,  3.29it/s]
 61%|██████▏   | 228026/371472 [7:30:14<11:47:29,  3.38it/s]
 61%|██████▏   | 228027/371472 [7:30:14<12:17:44,  3.24it/s]
 61%|██████▏   | 228028/371472 [7:30:15<12:10:51,  3.27it/s]
 61%|██████▏   | 228029/371472 [7:30:15<12:06:42,  3.29it/s]
 61%|██████▏   | 228030/371472 [7:30:15<11:56:06,  3.34it/s]
 61%|██████▏   | 228031/371472 [7:30:15<11:34:11,  3.44it/s]
 61%|██████▏   | 228032/371472 [7:30:16<11:31:00,  3.46it/s]
 61%|██████▏   | 228033/371472 [7:30:16<11:52:56,  3.35it/s]
 61%|██████▏   | 228034/371472 [7:30:16<12:24:34,  3.21it/s]
 61%|██████▏   | 228035/371472 [7:30:17<12:05:53,  3.29it/s]
 61%|██████▏   | 228036/371472 [7:30:17<11:44:03,  3.40it/s]
 61%|██████▏   | 228037/371472 [7:30:17<11:34:44,  3.44it/s]
 61%|██████▏   | 228038/371472 [7:30:18<11:58:20,  3.33it/s]
 61%|██████▏   | 228039/371472 [7:30:18<11:58:16,  3.33it/s]
 61%|██████▏   | 228040/371472 [7:30:18<11:56:33,  3.34it/s]
                                                            
{'loss': 2.5964, 'learning_rate': 4.4769333534443757e-07, 'epoch': 9.82}
+
 61%|██████▏   | 228040/371472 [7:30:18<11:56:33,  3.34it/s]
 61%|██████▏   | 228041/371472 [7:30:19<12:00:22,  3.32it/s]
 61%|██████▏   | 228042/371472 [7:30:19<11:50:51,  3.36it/s]
 61%|██████▏   | 228043/371472 [7:30:19<11:40:47,  3.41it/s]
 61%|██████▏   | 228044/371472 [7:30:20<13:28:02,  2.96it/s]
 61%|██████▏   | 228045/371472 [7:30:20<12:45:07,  3.12it/s]
 61%|██████▏   | 228046/371472 [7:30:20<13:24:30,  2.97it/s]
 61%|██████▏   | 228047/371472 [7:30:20<13:14:06,  3.01it/s]
 61%|██████▏   | 228048/371472 [7:30:21<12:53:56,  3.09it/s]
 61%|██████▏   | 228049/371472 [7:30:21<12:23:58,  3.21it/s]
 61%|██████▏   | 228050/371472 [7:30:21<13:25:32,  2.97it/s]
 61%|██████▏   | 228051/371472 [7:30:22<12:40:41,  3.14it/s]
 61%|██████▏   | 228052/371472 [7:30:22<13:15:36,  3.00it/s]
 61%|██████▏   | 228053/371472 [7:30:22<12:51:42,  3.10it/s]
 61%|██████▏   | 228054/371472 [7:30:23<12:16:00,  3.25it/s]
 61%|██████▏   | 228055/371472 [7:30:23<12:25:28,  3.21it/s]
 61%|██████▏   | 228056/371472 [7:30:23<12:02:05,  3.31it/s]
 61%|██████▏   | 228057/371472 [7:30:24<11:40:37,  3.41it/s]
 61%|██████▏   | 228058/371472 [7:30:24<12:07:16,  3.29it/s]
 61%|██████▏   | 228059/371472 [7:30:24<11:27:05,  3.48it/s]
 61%|██████▏   | 228060/371472 [7:30:24<11:18:30,  3.52it/s]
                                                            
{'loss': 2.824, 'learning_rate': 4.476448533689586e-07, 'epoch': 9.82}
+
 61%|██████▏   | 228060/371472 [7:30:24<11:18:30,  3.52it/s]
 61%|██████▏   | 228061/371472 [7:30:25<11:24:53,  3.49it/s]
 61%|██████▏   | 228062/371472 [7:30:25<11:28:40,  3.47it/s]
 61%|██████▏   | 228063/371472 [7:30:25<11:33:17,  3.45it/s]
 61%|██████▏   | 228064/371472 [7:30:26<11:51:13,  3.36it/s]
 61%|██████▏   | 228065/371472 [7:30:26<11:43:02,  3.40it/s]
 61%|██████▏   | 228066/371472 [7:30:26<11:52:41,  3.35it/s]
 61%|██████▏   | 228067/371472 [7:30:27<11:53:35,  3.35it/s]
 61%|██████▏   | 228068/371472 [7:30:27<12:04:51,  3.30it/s]
 61%|██████▏   | 228069/371472 [7:30:27<13:05:01,  3.04it/s]
 61%|██████▏   | 228070/371472 [7:30:28<13:07:19,  3.04it/s]
 61%|██████▏   | 228071/371472 [7:30:28<12:31:36,  3.18it/s]
 61%|██████▏   | 228072/371472 [7:30:28<11:52:07,  3.36it/s]
 61%|██████▏   | 228073/371472 [7:30:28<11:49:54,  3.37it/s]
 61%|██████▏   | 228074/371472 [7:30:29<11:58:31,  3.33it/s]
 61%|██████▏   | 228075/371472 [7:30:29<11:35:43,  3.44it/s]
 61%|██████▏   | 228076/371472 [7:30:29<11:47:31,  3.38it/s]
 61%|██████▏   | 228077/371472 [7:30:30<11:43:52,  3.40it/s]
 61%|██████▏   | 228078/371472 [7:30:30<11:31:43,  3.46it/s]
 61%|██████▏   | 228079/371472 [7:30:30<11:10:59,  3.56it/s]
 61%|██████▏   | 228080/371472 [7:30:30<11:31:40,  3.46it/s]
                                                            
{'loss': 2.6053, 'learning_rate': 4.4759637139347966e-07, 'epoch': 9.82}
+
 61%|██████▏   | 228080/371472 [7:30:30<11:31:40,  3.46it/s]
 61%|██████▏   | 228081/371472 [7:30:31<11:14:04,  3.55it/s]
 61%|██████▏   | 228082/371472 [7:30:31<11:32:26,  3.45it/s]
 61%|██████▏   | 228083/371472 [7:30:31<11:18:20,  3.52it/s]
 61%|██████▏   | 228084/371472 [7:30:32<11:14:28,  3.54it/s]
 61%|██████▏   | 228085/371472 [7:30:32<11:26:19,  3.48it/s]
 61%|██████▏   | 228086/371472 [7:30:32<11:08:54,  3.57it/s]
 61%|██████▏   | 228087/371472 [7:30:32<11:18:02,  3.52it/s]
 61%|██████▏   | 228088/371472 [7:30:33<11:17:53,  3.53it/s]
 61%|██████▏   | 228089/371472 [7:30:33<11:10:16,  3.57it/s]
 61%|██████▏   | 228090/371472 [7:30:33<11:02:57,  3.60it/s]
 61%|██████▏   | 228091/371472 [7:30:34<11:25:13,  3.49it/s]
 61%|██████▏   | 228092/371472 [7:30:34<11:20:51,  3.51it/s]
 61%|██████▏   | 228093/371472 [7:30:34<11:44:22,  3.39it/s]
 61%|██████▏   | 228094/371472 [7:30:34<11:57:31,  3.33it/s]
 61%|██████▏   | 228095/371472 [7:30:35<12:18:27,  3.24it/s]
 61%|██████▏   | 228096/371472 [7:30:35<11:49:43,  3.37it/s]
 61%|██████▏   | 228097/371472 [7:30:35<11:39:55,  3.41it/s]
 61%|██████▏   | 228098/371472 [7:30:36<11:12:48,  3.55it/s]
 61%|██████▏   | 228099/371472 [7:30:36<11:18:56,  3.52it/s]
 61%|██████▏   | 228100/371472 [7:30:36<11:37:51,  3.42it/s]
                                                            
{'loss': 2.831, 'learning_rate': 4.475478894180008e-07, 'epoch': 9.82}
+
 61%|██████▏   | 228100/371472 [7:30:36<11:37:51,  3.42it/s]
 61%|██████▏   | 228101/371472 [7:30:36<11:33:19,  3.45it/s]
 61%|██████▏   | 228102/371472 [7:30:37<11:57:02,  3.33it/s]
 61%|██████▏   | 228103/371472 [7:30:37<11:50:10,  3.36it/s]
 61%|██████▏   | 228104/371472 [7:30:37<11:42:04,  3.40it/s]
 61%|██████▏   | 228105/371472 [7:30:38<11:35:11,  3.44it/s]
 61%|██████▏   | 228106/371472 [7:30:38<11:21:47,  3.50it/s]
 61%|██████▏   | 228107/371472 [7:30:38<11:37:39,  3.42it/s]
 61%|██████▏   | 228108/371472 [7:30:38<11:20:08,  3.51it/s]
 61%|██████▏   | 228109/371472 [7:30:39<11:22:40,  3.50it/s]
 61%|██████▏   | 228110/371472 [7:30:39<11:41:56,  3.40it/s]
 61%|██████▏   | 228111/371472 [7:30:39<11:37:34,  3.43it/s]
 61%|██████▏   | 228112/371472 [7:30:40<11:32:08,  3.45it/s]
 61%|██████▏   | 228113/371472 [7:30:40<11:28:37,  3.47it/s]
 61%|██████▏   | 228114/371472 [7:30:40<11:31:08,  3.46it/s]
 61%|██████▏   | 228115/371472 [7:30:41<11:35:54,  3.43it/s]
 61%|██████▏   | 228116/371472 [7:30:41<11:24:09,  3.49it/s]
 61%|██████▏   | 228117/371472 [7:30:41<11:21:30,  3.51it/s]
 61%|██████▏   | 228118/371472 [7:30:41<11:36:43,  3.43it/s]
 61%|██████▏   | 228119/371472 [7:30:42<11:32:44,  3.45it/s]
 61%|██████▏   | 228120/371472 [7:30:42<12:17:13,  3.24it/s]
                                                            
{'loss': 2.7021, 'learning_rate': 4.4749940744252185e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228120/371472 [7:30:42<12:17:13,  3.24it/s]
 61%|██████▏   | 228121/371472 [7:30:42<12:02:59,  3.30it/s]
 61%|██████▏   | 228122/371472 [7:30:43<12:07:00,  3.29it/s]
 61%|██████▏   | 228123/371472 [7:30:43<11:50:10,  3.36it/s]
 61%|██████▏   | 228124/371472 [7:30:43<11:41:45,  3.40it/s]
 61%|██████▏   | 228125/371472 [7:30:43<11:39:05,  3.42it/s]
 61%|██████▏   | 228126/371472 [7:30:44<11:31:28,  3.46it/s]
 61%|██████▏   | 228127/371472 [7:30:44<11:28:21,  3.47it/s]
 61%|██████▏   | 228128/371472 [7:30:44<11:42:41,  3.40it/s]
 61%|██████▏   | 228129/371472 [7:30:45<11:29:16,  3.47it/s]
 61%|██████▏   | 228130/371472 [7:30:45<11:32:34,  3.45it/s]
 61%|██████▏   | 228131/371472 [7:30:45<11:21:18,  3.51it/s]
 61%|██████▏   | 228132/371472 [7:30:45<11:24:47,  3.49it/s]
 61%|██████▏   | 228133/371472 [7:30:46<12:14:12,  3.25it/s]
 61%|██████▏   | 228134/371472 [7:30:46<12:09:54,  3.27it/s]
 61%|██████▏   | 228135/371472 [7:30:46<11:51:39,  3.36it/s]
 61%|██████▏   | 228136/371472 [7:30:47<12:38:06,  3.15it/s]
 61%|██████▏   | 228137/371472 [7:30:47<12:18:11,  3.24it/s]
 61%|██████▏   | 228138/371472 [7:30:47<12:12:02,  3.26it/s]
 61%|██████▏   | 228139/371472 [7:30:48<12:34:03,  3.17it/s]
 61%|██████▏   | 228140/371472 [7:30:48<12:32:03,  3.18it/s]
                                                            
{'loss': 2.6783, 'learning_rate': 4.4745092546704303e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228140/371472 [7:30:48<12:32:03,  3.18it/s]
 61%|██████▏   | 228141/371472 [7:30:48<12:13:06,  3.26it/s]
 61%|██████▏   | 228142/371472 [7:30:49<12:02:56,  3.30it/s]
 61%|██████▏   | 228143/371472 [7:30:49<12:09:32,  3.27it/s]
 61%|██████▏   | 228144/371472 [7:30:49<12:28:40,  3.19it/s]
 61%|██████▏   | 228145/371472 [7:30:50<11:54:21,  3.34it/s]
 61%|██████▏   | 228146/371472 [7:30:50<11:59:26,  3.32it/s]
 61%|██████▏   | 228147/371472 [7:30:50<11:29:35,  3.46it/s]
 61%|██████▏   | 228148/371472 [7:30:50<11:27:08,  3.48it/s]
 61%|██████▏   | 228149/371472 [7:30:51<11:21:06,  3.51it/s]
 61%|██████▏   | 228150/371472 [7:30:51<11:32:04,  3.45it/s]
 61%|██████▏   | 228151/371472 [7:30:51<11:31:40,  3.45it/s]
 61%|██████▏   | 228152/371472 [7:30:52<11:40:26,  3.41it/s]
 61%|██████▏   | 228153/371472 [7:30:52<11:27:00,  3.48it/s]
 61%|██████▏   | 228154/371472 [7:30:52<11:20:17,  3.51it/s]
 61%|██████▏   | 228155/371472 [7:30:52<11:17:10,  3.53it/s]
 61%|██████▏   | 228156/371472 [7:30:53<10:58:30,  3.63it/s]
 61%|██████▏   | 228157/371472 [7:30:53<12:13:19,  3.26it/s]
 61%|██████▏   | 228158/371472 [7:30:53<11:59:44,  3.32it/s]
 61%|██████▏   | 228159/371472 [7:30:54<11:54:24,  3.34it/s]
 61%|██████▏   | 228160/371472 [7:30:54<11:31:20,  3.45it/s]
                                                            
{'loss': 2.8846, 'learning_rate': 4.474024434915641e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228160/371472 [7:30:54<11:31:20,  3.45it/s]
 61%|██████▏   | 228161/371472 [7:30:54<11:17:11,  3.53it/s]
 61%|██████▏   | 228162/371472 [7:30:54<10:56:10,  3.64it/s]
 61%|██████▏   | 228163/371472 [7:30:55<11:13:34,  3.55it/s]
 61%|██████▏   | 228164/371472 [7:30:55<11:03:16,  3.60it/s]
 61%|██████▏   | 228165/371472 [7:30:55<11:26:23,  3.48it/s]
 61%|██████▏   | 228166/371472 [7:30:56<11:23:57,  3.49it/s]
 61%|██████▏   | 228167/371472 [7:30:56<11:40:58,  3.41it/s]
 61%|██████▏   | 228168/371472 [7:30:56<11:25:33,  3.48it/s]
 61%|██████▏   | 228169/371472 [7:30:56<12:30:25,  3.18it/s]
 61%|██████▏   | 228170/371472 [7:30:57<12:03:37,  3.30it/s]
 61%|██████▏   | 228171/371472 [7:30:57<11:55:26,  3.34it/s]
 61%|██████▏   | 228172/371472 [7:30:57<11:55:45,  3.34it/s]
 61%|██████▏   | 228173/371472 [7:30:58<11:53:01,  3.35it/s]
 61%|██████▏   | 228174/371472 [7:30:58<11:59:36,  3.32it/s]
 61%|██████▏   | 228175/371472 [7:30:58<11:40:03,  3.41it/s]
 61%|██████▏   | 228176/371472 [7:30:59<12:02:32,  3.31it/s]
 61%|██████▏   | 228177/371472 [7:30:59<11:33:28,  3.44it/s]
 61%|██████▏   | 228178/371472 [7:30:59<12:15:28,  3.25it/s]
 61%|██████▏   | 228179/371472 [7:30:59<11:54:14,  3.34it/s]
 61%|██████▏   | 228180/371472 [7:31:00<12:13:14,  3.26it/s]
                                                            
{'loss': 2.8144, 'learning_rate': 4.473539615160852e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228180/371472 [7:31:00<12:13:14,  3.26it/s]
 61%|██████▏   | 228181/371472 [7:31:00<11:55:32,  3.34it/s]
 61%|██████▏   | 228182/371472 [7:31:00<11:48:51,  3.37it/s]
 61%|██████▏   | 228183/371472 [7:31:01<12:12:44,  3.26it/s]
 61%|██████▏   | 228184/371472 [7:31:01<12:20:42,  3.22it/s]
 61%|██████▏   | 228185/371472 [7:31:01<12:07:47,  3.28it/s]
 61%|██████▏   | 228186/371472 [7:31:02<11:33:28,  3.44it/s]
 61%|██████▏   | 228187/371472 [7:31:02<11:40:36,  3.41it/s]
 61%|██████▏   | 228188/371472 [7:31:02<11:34:21,  3.44it/s]
 61%|██████▏   | 228189/371472 [7:31:02<11:24:10,  3.49it/s]
 61%|██████▏   | 228190/371472 [7:31:03<11:18:16,  3.52it/s]
 61%|██████▏   | 228191/371472 [7:31:03<11:20:35,  3.51it/s]
 61%|██████▏   | 228192/371472 [7:31:03<11:23:50,  3.49it/s]
 61%|██████▏   | 228193/371472 [7:31:04<11:22:21,  3.50it/s]
 61%|██████▏   | 228194/371472 [7:31:04<11:14:15,  3.54it/s]
 61%|██████▏   | 228195/371472 [7:31:04<10:59:20,  3.62it/s]
 61%|██████▏   | 228196/371472 [7:31:04<11:51:06,  3.36it/s]
 61%|██████▏   | 228197/371472 [7:31:05<12:00:14,  3.32it/s]
 61%|██████▏   | 228198/371472 [7:31:05<12:06:00,  3.29it/s]
 61%|██████▏   | 228199/371472 [7:31:05<11:50:38,  3.36it/s]
 61%|██████▏   | 228200/371472 [7:31:06<11:25:28,  3.48it/s]
                                                            
{'loss': 2.8399, 'learning_rate': 4.4730547954060635e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228200/371472 [7:31:06<11:25:28,  3.48it/s]
 61%|██████▏   | 228201/371472 [7:31:06<11:10:30,  3.56it/s]
 61%|██████▏   | 228202/371472 [7:31:06<10:58:36,  3.63it/s]
 61%|██████▏   | 228203/371472 [7:31:06<10:55:36,  3.64it/s]
 61%|██████▏   | 228204/371472 [7:31:07<11:25:25,  3.48it/s]
 61%|██████▏   | 228205/371472 [7:31:07<11:00:05,  3.62it/s]
 61%|██████▏   | 228206/371472 [7:31:07<11:04:51,  3.59it/s]
 61%|██████▏   | 228207/371472 [7:31:08<11:03:53,  3.60it/s]
 61%|██████▏   | 228208/371472 [7:31:08<10:59:25,  3.62it/s]
 61%|██████▏   | 228209/371472 [7:31:08<11:04:30,  3.59it/s]
 61%|██████▏   | 228210/371472 [7:31:08<10:49:24,  3.68it/s]
 61%|██████▏   | 228211/371472 [7:31:09<10:56:11,  3.64it/s]
 61%|██████▏   | 228212/371472 [7:31:09<10:50:32,  3.67it/s]
 61%|██████▏   | 228213/371472 [7:31:09<10:58:23,  3.63it/s]
 61%|██████▏   | 228214/371472 [7:31:09<11:06:56,  3.58it/s]
 61%|██████▏   | 228215/371472 [7:31:10<11:00:28,  3.61it/s]
 61%|██████▏   | 228216/371472 [7:31:10<11:17:45,  3.52it/s]
 61%|██████▏   | 228217/371472 [7:31:10<11:34:56,  3.44it/s]
 61%|██████▏   | 228218/371472 [7:31:11<11:22:31,  3.50it/s]
 61%|██████▏   | 228219/371472 [7:31:11<11:16:22,  3.53it/s]
 61%|██████▏   | 228220/371472 [7:31:11<10:58:42,  3.62it/s]
                                                            
{'loss': 2.9469, 'learning_rate': 4.4725699756512747e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228220/371472 [7:31:11<10:58:42,  3.62it/s]
 61%|██████▏   | 228221/371472 [7:31:11<11:19:49,  3.51it/s]
 61%|██████▏   | 228222/371472 [7:31:12<11:27:59,  3.47it/s]
 61%|██████▏   | 228223/371472 [7:31:12<11:38:12,  3.42it/s]
 61%|██████▏   | 228224/371472 [7:31:12<11:40:07,  3.41it/s]
 61%|██████▏   | 228225/371472 [7:31:13<12:16:06,  3.24it/s]
 61%|██████▏   | 228226/371472 [7:31:13<11:41:33,  3.40it/s]
 61%|██████▏   | 228227/371472 [7:31:13<11:36:51,  3.43it/s]
 61%|██████▏   | 228228/371472 [7:31:14<11:39:30,  3.41it/s]
 61%|██████▏   | 228229/371472 [7:31:14<11:42:49,  3.40it/s]
 61%|██████▏   | 228230/371472 [7:31:14<12:21:44,  3.22it/s]
 61%|██████▏   | 228231/371472 [7:31:14<11:59:59,  3.32it/s]
 61%|██████▏   | 228232/371472 [7:31:15<11:59:48,  3.32it/s]
 61%|██████▏   | 228233/371472 [7:31:15<11:33:52,  3.44it/s]
 61%|██████▏   | 228234/371472 [7:31:15<11:31:47,  3.45it/s]
 61%|██████▏   | 228235/371472 [7:31:16<11:23:23,  3.49it/s]
 61%|██████▏   | 228236/371472 [7:31:16<11:49:08,  3.37it/s]
 61%|██████▏   | 228237/371472 [7:31:16<11:26:50,  3.48it/s]
 61%|██████▏   | 228238/371472 [7:31:16<11:08:26,  3.57it/s]
 61%|██████▏   | 228239/371472 [7:31:17<11:23:44,  3.49it/s]
 61%|██████▏   | 228240/371472 [7:31:17<11:33:51,  3.44it/s]
                                                            
{'loss': 2.7132, 'learning_rate': 4.472085155896485e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228240/371472 [7:31:17<11:33:51,  3.44it/s]
 61%|██████▏   | 228241/371472 [7:31:17<12:00:27,  3.31it/s]
 61%|██████▏   | 228242/371472 [7:31:18<11:48:40,  3.37it/s]
 61%|██████▏   | 228243/371472 [7:31:18<12:16:19,  3.24it/s]
 61%|██████▏   | 228244/371472 [7:31:18<13:23:38,  2.97it/s]
 61%|██████▏   | 228245/371472 [7:31:19<12:36:40,  3.15it/s]
 61%|██████▏   | 228246/371472 [7:31:19<13:17:08,  2.99it/s]
 61%|██████▏   | 228247/371472 [7:31:19<13:00:37,  3.06it/s]
 61%|██████▏   | 228248/371472 [7:31:20<12:18:33,  3.23it/s]
 61%|██████▏   | 228249/371472 [7:31:20<12:14:38,  3.25it/s]
 61%|██████▏   | 228250/371472 [7:31:20<12:01:20,  3.31it/s]
 61%|██████▏   | 228251/371472 [7:31:20<11:42:53,  3.40it/s]
 61%|██████▏   | 228252/371472 [7:31:21<11:47:03,  3.38it/s]
 61%|██████▏   | 228253/371472 [7:31:21<11:26:01,  3.48it/s]
 61%|██████▏   | 228254/371472 [7:31:21<11:31:08,  3.45it/s]
 61%|██████▏   | 228255/371472 [7:31:22<11:59:40,  3.32it/s]
 61%|██████▏   | 228256/371472 [7:31:22<11:50:18,  3.36it/s]
 61%|██████▏   | 228257/371472 [7:31:22<11:41:32,  3.40it/s]
 61%|██████▏   | 228258/371472 [7:31:23<11:21:12,  3.50it/s]
 61%|██████▏   | 228259/371472 [7:31:23<11:35:47,  3.43it/s]
 61%|██████▏   | 228260/371472 [7:31:23<11:34:41,  3.44it/s]
                                                            
{'loss': 2.6978, 'learning_rate': 4.4716003361416967e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228260/371472 [7:31:23<11:34:41,  3.44it/s]
 61%|██████▏   | 228261/371472 [7:31:23<11:25:05,  3.48it/s]
 61%|██████▏   | 228262/371472 [7:31:24<11:32:39,  3.45it/s]
 61%|██████▏   | 228263/371472 [7:31:24<11:25:25,  3.48it/s]
 61%|██████▏   | 228264/371472 [7:31:24<12:13:38,  3.25it/s]
 61%|██████▏   | 228265/371472 [7:31:25<11:50:50,  3.36it/s]
 61%|██████▏   | 228266/371472 [7:31:25<11:47:07,  3.38it/s]
 61%|██████▏   | 228267/371472 [7:31:25<12:48:02,  3.11it/s]
 61%|██████▏   | 228268/371472 [7:31:26<12:20:39,  3.22it/s]
 61%|██████▏   | 228269/371472 [7:31:26<11:57:21,  3.33it/s]
 61%|██████▏   | 228270/371472 [7:31:26<11:54:38,  3.34it/s]
 61%|██████▏   | 228271/371472 [7:31:26<11:37:08,  3.42it/s]
 61%|██████▏   | 228272/371472 [7:31:27<11:30:34,  3.46it/s]
 61%|██████▏   | 228273/371472 [7:31:27<11:33:17,  3.44it/s]
 61%|██████▏   | 228274/371472 [7:31:27<11:43:55,  3.39it/s]
 61%|██████▏   | 228275/371472 [7:31:28<12:09:59,  3.27it/s]
 61%|██████▏   | 228276/371472 [7:31:28<11:57:43,  3.33it/s]
 61%|██████▏   | 228277/371472 [7:31:28<11:35:21,  3.43it/s]
 61%|██████▏   | 228278/371472 [7:31:28<11:35:13,  3.43it/s]
 61%|██████▏   | 228279/371472 [7:31:29<11:33:25,  3.44it/s]
 61%|██████▏   | 228280/371472 [7:31:29<12:31:02,  3.18it/s]
                                                            
{'loss': 2.8289, 'learning_rate': 4.4711155163869074e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228280/371472 [7:31:29<12:31:02,  3.18it/s]
 61%|██████▏   | 228281/371472 [7:31:29<12:34:00,  3.17it/s]
 61%|██████▏   | 228282/371472 [7:31:30<12:38:21,  3.15it/s]
 61%|██████▏   | 228283/371472 [7:31:30<12:10:24,  3.27it/s]
 61%|██████▏   | 228284/371472 [7:31:30<11:45:33,  3.38it/s]
 61%|██████▏   | 228285/371472 [7:31:31<11:35:49,  3.43it/s]
 61%|██████▏   | 228286/371472 [7:31:31<11:24:22,  3.49it/s]
 61%|██████▏   | 228287/371472 [7:31:31<11:16:35,  3.53it/s]
 61%|██████▏   | 228288/371472 [7:31:31<11:19:33,  3.51it/s]
 61%|██████▏   | 228289/371472 [7:31:32<11:12:42,  3.55it/s]
 61%|██████▏   | 228290/371472 [7:31:32<11:10:09,  3.56it/s]
 61%|██████▏   | 228291/371472 [7:31:32<11:18:43,  3.52it/s]
 61%|██████▏   | 228292/371472 [7:31:33<11:09:39,  3.56it/s]
 61%|██████▏   | 228293/371472 [7:31:33<10:57:32,  3.63it/s]
 61%|██████▏   | 228294/371472 [7:31:33<11:15:11,  3.53it/s]
 61%|██████▏   | 228295/371472 [7:31:33<11:22:36,  3.50it/s]
 61%|██████▏   | 228296/371472 [7:31:34<11:08:39,  3.57it/s]
 61%|██████▏   | 228297/371472 [7:31:34<11:05:19,  3.59it/s]
 61%|██████▏   | 228298/371472 [7:31:34<11:40:26,  3.41it/s]
 61%|██████▏   | 228299/371472 [7:31:35<11:44:16,  3.39it/s]
 61%|██████▏   | 228300/371472 [7:31:35<11:33:41,  3.44it/s]
                                                            
{'loss': 2.6652, 'learning_rate': 4.4706306966321187e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228300/371472 [7:31:35<11:33:41,  3.44it/s]
 61%|██████▏   | 228301/371472 [7:31:35<11:10:02,  3.56it/s]
 61%|██████▏   | 228302/371472 [7:31:35<11:05:18,  3.59it/s]
 61%|██████▏   | 228303/371472 [7:31:36<11:07:19,  3.58it/s]
 61%|██████▏   | 228304/371472 [7:31:36<11:11:41,  3.55it/s]
 61%|██████▏   | 228305/371472 [7:31:36<11:07:44,  3.57it/s]
 61%|██████▏   | 228306/371472 [7:31:37<11:15:22,  3.53it/s]
 61%|██████▏   | 228307/371472 [7:31:37<11:22:45,  3.49it/s]
 61%|██████▏   | 228308/371472 [7:31:37<11:13:55,  3.54it/s]
 61%|██████▏   | 228309/371472 [7:31:37<11:57:17,  3.33it/s]
 61%|██████▏   | 228310/371472 [7:31:38<11:51:13,  3.35it/s]
 61%|██████▏   | 228311/371472 [7:31:38<11:50:16,  3.36it/s]
 61%|██████▏   | 228312/371472 [7:31:38<11:27:27,  3.47it/s]
 61%|██████▏   | 228313/371472 [7:31:39<11:24:11,  3.49it/s]
 61%|██████▏   | 228314/371472 [7:31:39<12:14:25,  3.25it/s]
 61%|██████▏   | 228315/371472 [7:31:39<12:35:34,  3.16it/s]
 61%|██████▏   | 228316/371472 [7:31:40<13:05:03,  3.04it/s]
 61%|██████▏   | 228317/371472 [7:31:40<13:18:08,  2.99it/s]
 61%|██████▏   | 228318/371472 [7:31:40<12:46:24,  3.11it/s]
 61%|██████▏   | 228319/371472 [7:31:41<12:32:52,  3.17it/s]
 61%|██████▏   | 228320/371472 [7:31:41<12:29:49,  3.18it/s]
                                                            
{'loss': 2.8793, 'learning_rate': 4.4701458768773294e-07, 'epoch': 9.83}
+
 61%|██████▏   | 228320/371472 [7:31:41<12:29:49,  3.18it/s]
 61%|██████▏   | 228321/371472 [7:31:41<12:21:47,  3.22it/s]
 61%|██████▏   | 228322/371472 [7:31:41<12:11:13,  3.26it/s]
 61%|██████▏   | 228323/371472 [7:31:42<11:55:58,  3.33it/s]
 61%|██████▏   | 228324/371472 [7:31:42<12:06:26,  3.28it/s]
 61%|██████▏   | 228325/371472 [7:31:42<12:10:41,  3.27it/s]
 61%|██████▏   | 228326/371472 [7:31:43<12:25:29,  3.20it/s]
 61%|██████▏   | 228327/371472 [7:31:43<12:02:39,  3.30it/s]
 61%|██████▏   | 228328/371472 [7:31:43<11:56:33,  3.33it/s]
 61%|██████▏   | 228329/371472 [7:31:44<11:26:49,  3.47it/s]
 61%|██████▏   | 228330/371472 [7:31:44<11:32:42,  3.44it/s]
 61%|██████▏   | 228331/371472 [7:31:44<11:21:46,  3.50it/s]
 61%|██████▏   | 228332/371472 [7:31:44<11:03:32,  3.60it/s]
 61%|██████▏   | 228333/371472 [7:31:45<11:17:25,  3.52it/s]
 61%|██████▏   | 228334/371472 [7:31:45<11:40:53,  3.40it/s]
 61%|██████▏   | 228335/371472 [7:31:45<11:24:14,  3.49it/s]
 61%|██████▏   | 228336/371472 [7:31:46<11:25:10,  3.48it/s]
 61%|██████▏   | 228337/371472 [7:31:46<11:42:09,  3.40it/s]
 61%|██████▏   | 228338/371472 [7:31:46<11:39:11,  3.41it/s]
 61%|██████▏   | 228339/371472 [7:31:46<11:37:42,  3.42it/s]
 61%|██████▏   | 228340/371472 [7:31:47<11:44:49,  3.38it/s]
                                                            
{'loss': 2.6363, 'learning_rate': 4.469661057122541e-07, 'epoch': 9.84}
+
 61%|██████▏   | 228340/371472 [7:31:47<11:44:49,  3.38it/s]
 61%|██████▏   | 228341/371472 [7:31:47<11:47:03,  3.37it/s]
 61%|██████▏   | 228342/371472 [7:31:47<11:33:48,  3.44it/s]
 61%|██████▏   | 228343/371472 [7:31:48<11:41:54,  3.40it/s]
 61%|██████▏   | 228344/371472 [7:31:48<11:31:44,  3.45it/s]
 61%|██████▏   | 228345/371472 [7:31:48<11:41:16,  3.40it/s]
 61%|██████▏   | 228346/371472 [7:31:49<11:42:46,  3.39it/s]
 61%|██████▏   | 228347/371472 [7:31:49<11:32:27,  3.44it/s]
 61%|██████▏   | 228348/371472 [7:31:49<11:50:25,  3.36it/s]
 61%|██████▏   | 228349/371472 [7:31:49<11:46:23,  3.38it/s]
 61%|██████▏   | 228350/371472 [7:31:50<11:38:39,  3.41it/s]
 61%|██████▏   | 228351/371472 [7:31:50<12:18:50,  3.23it/s]
 61%|██████▏   | 228352/371472 [7:31:50<12:42:49,  3.13it/s]
 61%|██████▏   | 228353/371472 [7:31:51<12:41:14,  3.13it/s]
 61%|██████▏   | 228354/371472 [7:31:51<12:14:42,  3.25it/s]
 61%|██████▏   | 228355/371472 [7:31:51<11:53:43,  3.34it/s]
 61%|██████▏   | 228356/371472 [7:31:52<11:27:48,  3.47it/s]
 61%|██████▏   | 228357/371472 [7:31:52<11:47:42,  3.37it/s]
 61%|██████▏   | 228358/371472 [7:31:52<11:36:14,  3.43it/s]
 61%|██████▏   | 228359/371472 [7:31:52<12:33:27,  3.17it/s]
 61%|██████▏   | 228360/371472 [7:31:53<12:13:38,  3.25it/s]
                                                            
{'loss': 2.6278, 'learning_rate': 4.4691762373677513e-07, 'epoch': 9.84}
+
 61%|██████▏   | 228360/371472 [7:31:53<12:13:38,  3.25it/s]
 61%|██████▏   | 228361/371472 [7:31:53<12:19:19,  3.23it/s]
 61%|██████▏   | 228362/371472 [7:31:53<12:02:21,  3.30it/s]
 61%|██████▏   | 228363/371472 [7:31:54<12:13:52,  3.25it/s]
 61%|██████▏   | 228364/371472 [7:31:54<12:05:12,  3.29it/s]
 61%|██████▏   | 228365/371472 [7:31:54<13:00:50,  3.05it/s]
 61%|██████▏   | 228366/371472 [7:31:55<13:29:05,  2.95it/s]
 61%|██████▏   | 228367/371472 [7:31:55<13:00:40,  3.06it/s]
 61%|██████▏   | 228368/371472 [7:31:55<12:52:12,  3.09it/s]
 61%|██████▏   | 228369/371472 [7:31:56<12:24:23,  3.20it/s]
 61%|██████▏   | 228370/371472 [7:31:56<11:59:00,  3.32it/s]
 61%|██████▏   | 228371/371472 [7:31:56<11:40:40,  3.40it/s]
 61%|██████▏   | 228372/371472 [7:31:56<11:38:56,  3.41it/s]
 61%|██████▏   | 228373/371472 [7:31:57<11:37:46,  3.42it/s]
 61%|██████▏   | 228374/371472 [7:31:57<11:38:15,  3.42it/s]
 61%|██████▏   | 228375/371472 [7:31:57<11:59:23,  3.32it/s]
 61%|██████▏   | 228376/371472 [7:31:58<12:31:06,  3.18it/s]
 61%|██████▏   | 228377/371472 [7:31:58<12:56:20,  3.07it/s]
 61%|██████▏   | 228378/371472 [7:31:58<12:38:17,  3.15it/s]
 61%|██████▏   | 228379/371472 [7:31:59<12:23:33,  3.21it/s]
 61%|██████▏   | 228380/371472 [7:31:59<12:22:37,  3.21it/s]
                                                            
{'loss': 2.6308, 'learning_rate': 4.468691417612963e-07, 'epoch': 9.84}
+
 61%|██████▏   | 228380/371472 [7:31:59<12:22:37,  3.21it/s]
 61%|██████▏   | 228381/371472 [7:31:59<12:13:57,  3.25it/s]
 61%|██████▏   | 228382/371472 [7:32:00<11:40:52,  3.40it/s]
 61%|██████▏   | 228383/371472 [7:32:00<11:35:39,  3.43it/s]
 61%|██████▏   | 228384/371472 [7:32:00<11:27:08,  3.47it/s]
 61%|██████▏   | 228385/371472 [7:32:00<11:14:52,  3.53it/s]
 61%|██████▏   | 228386/371472 [7:32:01<12:43:26,  3.12it/s]
 61%|██████▏   | 228387/371472 [7:32:01<12:42:54,  3.13it/s]
 61%|██████▏   | 228388/371472 [7:32:01<12:28:24,  3.19it/s]
 61%|██████▏   | 228389/371472 [7:32:02<11:56:53,  3.33it/s]
 61%|██████▏   | 228390/371472 [7:32:02<11:49:04,  3.36it/s]
 61%|██████▏   | 228391/371472 [7:32:02<11:46:45,  3.37it/s]
 61%|██████▏   | 228392/371472 [7:32:03<12:17:02,  3.24it/s]
 61%|██████▏   | 228393/371472 [7:32:03<11:57:24,  3.32it/s]
 61%|██████▏   | 228394/371472 [7:32:03<12:21:50,  3.21it/s]
 61%|██████▏   | 228395/371472 [7:32:04<11:57:13,  3.32it/s]
 61%|██████▏   | 228396/371472 [7:32:04<11:45:05,  3.38it/s]
 61%|██████▏   | 228397/371472 [7:32:04<11:50:39,  3.36it/s]
 61%|██████▏   | 228398/371472 [7:32:04<11:38:30,  3.41it/s]
 61%|██████▏   | 228399/371472 [7:32:05<12:08:55,  3.27it/s]
 61%|██████▏   | 228400/371472 [7:32:05<11:55:35,  3.33it/s]
                                                            
{'loss': 2.734, 'learning_rate': 4.468206597858174e-07, 'epoch': 9.84}
+
 61%|██████▏   | 228400/371472 [7:32:05<11:55:35,  3.33it/s]
 61%|██████▏   | 228401/371472 [7:32:06<15:02:58,  2.64it/s]
 61%|██████▏   | 228402/371472 [7:32:06<14:00:49,  2.84it/s]
 61%|██████▏   | 228403/371472 [7:32:06<13:12:08,  3.01it/s]
 61%|██████▏   | 228404/371472 [7:32:06<12:22:42,  3.21it/s]
 61%|██████▏   | 228405/371472 [7:32:07<12:04:29,  3.29it/s]
 61%|██████▏   | 228406/371472 [7:32:07<11:42:39,  3.39it/s]
 61%|██████▏   | 228407/371472 [7:32:07<11:36:16,  3.42it/s]
 61%|██████▏   | 228408/371472 [7:32:08<12:48:56,  3.10it/s]
 61%|██████▏   | 228409/371472 [7:32:08<12:30:10,  3.18it/s]
 61%|██████▏   | 228410/371472 [7:32:08<12:33:31,  3.16it/s]
 61%|██████▏   | 228411/371472 [7:32:09<12:15:56,  3.24it/s]
 61%|██████▏   | 228412/371472 [7:32:09<12:15:58,  3.24it/s]
 61%|██████▏   | 228413/371472 [7:32:09<11:45:54,  3.38it/s]
 61%|██████▏   | 228414/371472 [7:32:09<11:57:17,  3.32it/s]
 61%|██████▏   | 228415/371472 [7:32:10<11:50:07,  3.36it/s]
 61%|██████▏   | 228416/371472 [7:32:10<11:39:03,  3.41it/s]
 61%|██████▏   | 228417/371472 [7:32:10<11:27:47,  3.47it/s]
 61%|██████▏   | 228418/371472 [7:32:11<11:04:25,  3.59it/s]
 61%|██████▏   | 228419/371472 [7:32:11<11:15:40,  3.53it/s]
 61%|██████▏   | 228420/371472 [7:32:11<11:10:02,  3.56it/s]
                                                            
{'loss': 2.6363, 'learning_rate': 4.467721778103385e-07, 'epoch': 9.84}
+
 61%|██████▏   | 228420/371472 [7:32:11<11:10:02,  3.56it/s]
 61%|██████▏   | 228421/371472 [7:32:11<11:48:58,  3.36it/s]
 61%|██████▏   | 228422/371472 [7:32:12<11:35:10,  3.43it/s]
 61%|██████▏   | 228423/371472 [7:32:12<11:26:33,  3.47it/s]
 61%|██████▏   | 228424/371472 [7:32:12<11:25:49,  3.48it/s]
 61%|██████▏   | 228425/371472 [7:32:13<12:31:28,  3.17it/s]
 61%|██████▏   | 228426/371472 [7:32:13<12:11:12,  3.26it/s]
 61%|██████▏   | 228427/371472 [7:32:13<11:47:07,  3.37it/s]
 61%|██████▏   | 228428/371472 [7:32:14<12:01:37,  3.30it/s]
 61%|██████▏   | 228429/371472 [7:32:14<11:36:58,  3.42it/s]
 61%|██████▏   | 228430/371472 [7:32:14<12:00:10,  3.31it/s]
 61%|██████▏   | 228431/371472 [7:32:14<11:46:37,  3.37it/s]
 61%|██████▏   | 228432/371472 [7:32:15<11:51:25,  3.35it/s]
 61%|██████▏   | 228433/371472 [7:32:15<11:57:40,  3.32it/s]
 61%|██████▏   | 228434/371472 [7:32:15<11:44:59,  3.38it/s]
 61%|██████▏   | 228435/371472 [7:32:16<12:06:38,  3.28it/s]
 61%|██████▏   | 228436/371472 [7:32:16<11:46:04,  3.38it/s]
 61%|██████▏   | 228437/371472 [7:32:16<11:33:30,  3.44it/s]
 61%|██████▏   | 228438/371472 [7:32:17<12:05:00,  3.29it/s]
 61%|██████▏   | 228439/371472 [7:32:17<12:18:39,  3.23it/s]
 61%|██████▏   | 228440/371472 [7:32:17<12:39:15,  3.14it/s]
                                                            
{'loss': 2.7233, 'learning_rate': 4.467236958348596e-07, 'epoch': 9.84}
+
 61%|██████▏   | 228440/371472 [7:32:17<12:39:15,  3.14it/s]
 61%|██████▏   | 228441/371472 [7:32:18<12:47:58,  3.10it/s]
 61%|██████▏   | 228442/371472 [7:32:18<12:09:46,  3.27it/s]
 61%|██████▏   | 228443/371472 [7:32:18<11:48:07,  3.37it/s]
 61%|██████▏   | 228444/371472 [7:32:18<11:42:05,  3.40it/s]
 61%|██████▏   | 228445/371472 [7:32:19<11:49:04,  3.36it/s]
 61%|██████▏   | 228446/371472 [7:32:19<11:39:54,  3.41it/s]
 61%|██████▏   | 228447/371472 [7:32:19<11:47:01,  3.37it/s]
 61%|██████▏   | 228448/371472 [7:32:20<12:14:14,  3.25it/s]
 61%|██████▏   | 228449/371472 [7:32:20<12:08:17,  3.27it/s]
 61%|██████▏   | 228450/371472 [7:32:20<12:23:08,  3.21it/s]
 61%|██████▏   | 228451/371472 [7:32:21<12:25:43,  3.20it/s]
 61%|██████▏   | 228452/371472 [7:32:21<11:58:18,  3.32it/s]
 61%|██████▏   | 228453/371472 [7:32:21<11:36:11,  3.42it/s]
 61%|██████▏   | 228454/371472 [7:32:21<11:56:30,  3.33it/s]
 61%|██████▏   | 228455/371472 [7:32:22<12:15:48,  3.24it/s]
 62%|██████▏   | 228456/371472 [7:32:22<11:42:40,  3.39it/s]
 62%|██████▏   | 228457/371472 [7:32:22<11:51:15,  3.35it/s]
 62%|██████▏   | 228458/371472 [7:32:23<11:49:58,  3.36it/s]
 62%|██████▏   | 228459/371472 [7:32:23<11:31:40,  3.45it/s]
 62%|██████▏   | 228460/371472 [7:32:23<11:31:39,  3.45it/s]
                                                            
{'loss': 2.8116, 'learning_rate': 4.466752138593807e-07, 'epoch': 9.84}
+
 62%|██████▏   | 228460/371472 [7:32:23<11:31:39,  3.45it/s]
 62%|██████▏   | 228461/371472 [7:32:23<11:38:05,  3.41it/s]
 62%|██████▏   | 228462/371472 [7:32:24<11:35:41,  3.43it/s]
 62%|██████▏   | 228463/371472 [7:32:24<11:23:30,  3.49it/s]
 62%|██████▏   | 228464/371472 [7:32:24<11:35:23,  3.43it/s]
 62%|██████▏   | 228465/371472 [7:32:25<11:59:23,  3.31it/s]
 62%|██████▏   | 228466/371472 [7:32:25<11:47:44,  3.37it/s]
 62%|██████▏   | 228467/371472 [7:32:25<11:33:48,  3.44it/s]
 62%|██████▏   | 228468/371472 [7:32:25<11:32:18,  3.44it/s]
 62%|██████▏   | 228469/371472 [7:32:26<11:27:11,  3.47it/s]
 62%|██████▏   | 228470/371472 [7:32:26<11:33:07,  3.44it/s]
 62%|██████▏   | 228471/371472 [7:32:26<11:58:30,  3.32it/s]
 62%|██████▏   | 228472/371472 [7:32:27<11:59:39,  3.31it/s]
 62%|██████▏   | 228473/371472 [7:32:27<11:37:02,  3.42it/s]
 62%|██████▏   | 228474/371472 [7:32:27<11:54:08,  3.34it/s]
 62%|██████▏   | 228475/371472 [7:32:28<12:04:27,  3.29it/s]
 62%|██████▏   | 228476/371472 [7:32:28<11:55:48,  3.33it/s]
 62%|██████▏   | 228477/371472 [7:32:28<11:41:40,  3.40it/s]
 62%|██████▏   | 228478/371472 [7:32:28<11:30:46,  3.45it/s]
 62%|██████▏   | 228479/371472 [7:32:29<11:11:26,  3.55it/s]
 62%|██████▏   | 228480/371472 [7:32:29<11:26:21,  3.47it/s]
                                                            
{'loss': 2.937, 'learning_rate': 4.4662673188390177e-07, 'epoch': 9.84}
+
 62%|██████▏   | 228480/371472 [7:32:29<11:26:21,  3.47it/s]
 62%|██████▏   | 228481/371472 [7:32:29<11:29:32,  3.46it/s]
 62%|██████▏   | 228482/371472 [7:32:30<12:01:54,  3.30it/s]
 62%|██████▏   | 228483/371472 [7:32:30<11:54:56,  3.33it/s]
 62%|██████▏   | 228484/371472 [7:32:30<11:37:14,  3.42it/s]
 62%|██████▏   | 228485/371472 [7:32:30<11:19:49,  3.51it/s]
 62%|██████▏   | 228486/371472 [7:32:31<11:21:21,  3.50it/s]
 62%|██████▏   | 228487/371472 [7:32:31<11:39:09,  3.41it/s]
 62%|██████▏   | 228488/371472 [7:32:31<11:30:13,  3.45it/s]
 62%|██████▏   | 228489/371472 [7:32:32<11:23:32,  3.49it/s]
 62%|██████▏   | 228490/371472 [7:32:32<11:15:11,  3.53it/s]
 62%|██████▏   | 228491/371472 [7:32:32<11:09:35,  3.56it/s]
 62%|██████▏   | 228492/371472 [7:32:32<11:12:48,  3.54it/s]
 62%|██████▏   | 228493/371472 [7:32:33<12:11:44,  3.26it/s]
 62%|██████▏   | 228494/371472 [7:32:33<11:53:43,  3.34it/s]
 62%|██████▏   | 228495/371472 [7:32:33<11:56:24,  3.33it/s]
 62%|██████▏   | 228496/371472 [7:32:34<11:46:48,  3.37it/s]
 62%|██████▏   | 228497/371472 [7:32:34<11:30:12,  3.45it/s]
 62%|██████▏   | 228498/371472 [7:32:34<11:43:26,  3.39it/s]
 62%|██████▏   | 228499/371472 [7:32:35<11:35:35,  3.43it/s]
 62%|██████▏   | 228500/371472 [7:32:35<11:24:15,  3.48it/s]
                                                            
{'loss': 2.6129, 'learning_rate': 4.4657824990842295e-07, 'epoch': 9.84}
+
 62%|██████▏   | 228500/371472 [7:32:35<11:24:15,  3.48it/s]
 62%|██████▏   | 228501/371472 [7:32:35<11:25:04,  3.48it/s]
 62%|██████▏   | 228502/371472 [7:32:35<11:14:18,  3.53it/s]
 62%|██████▏   | 228503/371472 [7:32:36<11:15:39,  3.53it/s]
 62%|██████▏   | 228504/371472 [7:32:36<11:21:02,  3.50it/s]
 62%|██████▏   | 228505/371472 [7:32:36<11:15:13,  3.53it/s]
 62%|██████▏   | 228506/371472 [7:32:37<11:10:08,  3.56it/s]
 62%|██████▏   | 228507/371472 [7:32:37<11:43:44,  3.39it/s]
 62%|██████▏   | 228508/371472 [7:32:37<11:34:39,  3.43it/s]
 62%|██████▏   | 228509/371472 [7:32:37<11:44:10,  3.38it/s]
 62%|██████▏   | 228510/371472 [7:32:38<12:06:40,  3.28it/s]
 62%|██████▏   | 228511/371472 [7:32:38<11:47:22,  3.37it/s]
 62%|██████▏   | 228512/371472 [7:32:38<11:21:30,  3.50it/s]
 62%|██████▏   | 228513/371472 [7:32:39<11:02:47,  3.59it/s]
 62%|██████▏   | 228514/371472 [7:32:39<11:00:37,  3.61it/s]
 62%|██████▏   | 228515/371472 [7:32:39<10:54:53,  3.64it/s]
 62%|██████▏   | 228516/371472 [7:32:39<11:13:09,  3.54it/s]
 62%|██████▏   | 228517/371472 [7:32:40<11:17:47,  3.52it/s]
 62%|██████▏   | 228518/371472 [7:32:40<12:01:28,  3.30it/s]
 62%|██████▏   | 228519/371472 [7:32:40<12:51:40,  3.09it/s]
 62%|██████▏   | 228520/371472 [7:32:41<13:08:30,  3.02it/s]
                                                            
{'loss': 2.6577, 'learning_rate': 4.46529767932944e-07, 'epoch': 9.84}
+
 62%|██████▏   | 228520/371472 [7:32:41<13:08:30,  3.02it/s]
 62%|██████▏   | 228521/371472 [7:32:41<12:24:14,  3.20it/s]
 62%|██████▏   | 228522/371472 [7:32:41<12:08:02,  3.27it/s]
 62%|██████▏   | 228523/371472 [7:32:42<11:42:00,  3.39it/s]
 62%|██████▏   | 228524/371472 [7:32:42<11:32:24,  3.44it/s]
 62%|██████▏   | 228525/371472 [7:32:42<11:32:14,  3.44it/s]
 62%|██████▏   | 228526/371472 [7:32:42<11:35:26,  3.43it/s]
 62%|██████▏   | 228527/371472 [7:32:43<12:21:15,  3.21it/s]
 62%|██████▏   | 228528/371472 [7:32:43<12:08:10,  3.27it/s]
 62%|██████▏   | 228529/371472 [7:32:44<13:19:27,  2.98it/s]
 62%|██████▏   | 228530/371472 [7:32:44<12:36:30,  3.15it/s]
 62%|██████▏   | 228531/371472 [7:32:44<12:13:21,  3.25it/s]
 62%|██████▏   | 228532/371472 [7:32:44<12:00:30,  3.31it/s]
 62%|██████▏   | 228533/371472 [7:32:45<12:18:55,  3.22it/s]
 62%|██████▏   | 228534/371472 [7:32:45<12:14:35,  3.24it/s]
 62%|██████▏   | 228535/371472 [7:32:45<11:49:26,  3.36it/s]
 62%|██████▏   | 228536/371472 [7:32:46<11:22:22,  3.49it/s]
 62%|██████▏   | 228537/371472 [7:32:46<11:21:20,  3.50it/s]
 62%|██████▏   | 228538/371472 [7:32:46<12:01:01,  3.30it/s]
 62%|██████▏   | 228539/371472 [7:32:46<11:42:09,  3.39it/s]
 62%|██████▏   | 228540/371472 [7:32:47<11:37:15,  3.42it/s]
                                                            
{'loss': 2.8493, 'learning_rate': 4.4648128595746515e-07, 'epoch': 9.84}
+
 62%|██████▏   | 228540/371472 [7:32:47<11:37:15,  3.42it/s]
 62%|██████▏   | 228541/371472 [7:32:47<11:31:29,  3.45it/s]
 62%|██████▏   | 228542/371472 [7:32:47<12:16:46,  3.23it/s]
 62%|██████▏   | 228543/371472 [7:32:48<12:07:07,  3.28it/s]
 62%|██████▏   | 228544/371472 [7:32:48<11:44:08,  3.38it/s]
 62%|██████▏   | 228545/371472 [7:32:48<11:50:30,  3.35it/s]
 62%|██████▏   | 228546/371472 [7:32:49<11:50:42,  3.35it/s]
 62%|██████▏   | 228547/371472 [7:32:49<11:51:18,  3.35it/s]
 62%|██████▏   | 228548/371472 [7:32:49<11:49:32,  3.36it/s]
 62%|██████▏   | 228549/371472 [7:32:49<11:49:41,  3.36it/s]
 62%|██████▏   | 228550/371472 [7:32:50<11:46:38,  3.37it/s]
 62%|██████▏   | 228551/371472 [7:32:50<11:23:17,  3.49it/s]
 62%|██████▏   | 228552/371472 [7:32:50<11:12:50,  3.54it/s]
 62%|██████▏   | 228553/371472 [7:32:51<11:06:02,  3.58it/s]
 62%|██████▏   | 228554/371472 [7:32:51<11:44:11,  3.38it/s]
 62%|██████▏   | 228555/371472 [7:32:51<11:46:54,  3.37it/s]
 62%|██████▏   | 228556/371472 [7:32:51<11:56:59,  3.32it/s]
 62%|██████▏   | 228557/371472 [7:32:52<11:53:43,  3.34it/s]
 62%|██████▏   | 228558/371472 [7:32:52<11:43:15,  3.39it/s]
 62%|██████▏   | 228559/371472 [7:32:52<12:40:12,  3.13it/s]
 62%|██████▏   | 228560/371472 [7:32:53<12:06:35,  3.28it/s]
                                                            
{'loss': 2.8479, 'learning_rate': 4.464328039819862e-07, 'epoch': 9.84}
+
 62%|██████▏   | 228560/371472 [7:32:53<12:06:35,  3.28it/s]
 62%|██████▏   | 228561/371472 [7:32:53<12:33:14,  3.16it/s]
 62%|██████▏   | 228562/371472 [7:32:53<12:24:45,  3.20it/s]
 62%|██████▏   | 228563/371472 [7:32:54<11:49:03,  3.36it/s]
 62%|██████▏   | 228564/371472 [7:32:54<11:35:37,  3.42it/s]
 62%|██████▏   | 228565/371472 [7:32:54<11:52:32,  3.34it/s]
 62%|██████▏   | 228566/371472 [7:32:55<11:39:27,  3.41it/s]
 62%|██████▏   | 228567/371472 [7:32:55<11:24:27,  3.48it/s]
 62%|██████▏   | 228568/371472 [7:32:55<12:34:34,  3.16it/s]
 62%|██████▏   | 228569/371472 [7:32:56<12:43:41,  3.12it/s]
 62%|██████▏   | 228570/371472 [7:32:56<13:06:04,  3.03it/s]
 62%|██████▏   | 228571/371472 [7:32:56<12:31:51,  3.17it/s]
 62%|██████▏   | 228572/371472 [7:32:56<12:03:10,  3.29it/s]
 62%|██████▏   | 228573/371472 [7:32:57<12:07:52,  3.27it/s]
 62%|██████▏   | 228574/371472 [7:32:57<13:00:47,  3.05it/s]
 62%|██████▏   | 228575/371472 [7:32:57<12:46:21,  3.11it/s]
 62%|██████▏   | 228576/371472 [7:32:58<13:02:23,  3.04it/s]
 62%|██████▏   | 228577/371472 [7:32:58<12:45:10,  3.11it/s]
 62%|██████▏   | 228578/371472 [7:32:58<13:03:04,  3.04it/s]
 62%|██████▏   | 228579/371472 [7:32:59<12:30:36,  3.17it/s]
 62%|██████▏   | 228580/371472 [7:32:59<12:04:02,  3.29it/s]
                                                            
{'loss': 2.7164, 'learning_rate': 4.463843220065074e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228580/371472 [7:32:59<12:04:02,  3.29it/s]
 62%|██████▏   | 228581/371472 [7:32:59<11:53:53,  3.34it/s]
 62%|██████▏   | 228582/371472 [7:33:00<11:45:20,  3.38it/s]
 62%|██████▏   | 228583/371472 [7:33:00<11:25:28,  3.47it/s]
 62%|██████▏   | 228584/371472 [7:33:00<11:17:21,  3.52it/s]
 62%|██████▏   | 228585/371472 [7:33:00<11:17:22,  3.52it/s]
 62%|██████▏   | 228586/371472 [7:33:01<11:09:12,  3.56it/s]
 62%|██████▏   | 228587/371472 [7:33:01<11:51:44,  3.35it/s]
 62%|██████▏   | 228588/371472 [7:33:01<11:33:41,  3.43it/s]
 62%|██████▏   | 228589/371472 [7:33:02<11:28:04,  3.46it/s]
 62%|██████▏   | 228590/371472 [7:33:02<11:28:35,  3.46it/s]
 62%|██████▏   | 228591/371472 [7:33:02<11:28:53,  3.46it/s]
 62%|██████▏   | 228592/371472 [7:33:02<11:34:21,  3.43it/s]
 62%|██████▏   | 228593/371472 [7:33:03<11:46:49,  3.37it/s]
 62%|██████▏   | 228594/371472 [7:33:03<11:45:31,  3.38it/s]
 62%|██████▏   | 228595/371472 [7:33:03<12:10:39,  3.26it/s]
 62%|██████▏   | 228596/371472 [7:33:04<12:05:10,  3.28it/s]
 62%|██████▏   | 228597/371472 [7:33:04<11:33:00,  3.44it/s]
 62%|██████▏   | 228598/371472 [7:33:04<11:25:25,  3.47it/s]
 62%|██████▏   | 228599/371472 [7:33:05<13:07:33,  3.02it/s]
 62%|██████▏   | 228600/371472 [7:33:05<12:57:45,  3.06it/s]
                                                            
{'loss': 2.7004, 'learning_rate': 4.4633584003102847e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228600/371472 [7:33:05<12:57:45,  3.06it/s]
 62%|██████▏   | 228601/371472 [7:33:05<12:29:22,  3.18it/s]
 62%|██████▏   | 228602/371472 [7:33:06<12:08:51,  3.27it/s]
 62%|██████▏   | 228603/371472 [7:33:06<11:39:49,  3.40it/s]
 62%|██████▏   | 228604/371472 [7:33:06<12:05:56,  3.28it/s]
 62%|██████▏   | 228605/371472 [7:33:06<12:09:45,  3.26it/s]
 62%|██████▏   | 228606/371472 [7:33:07<12:15:12,  3.24it/s]
 62%|██████▏   | 228607/371472 [7:33:07<12:25:49,  3.19it/s]
 62%|██████▏   | 228608/371472 [7:33:07<12:25:56,  3.19it/s]
 62%|██████▏   | 228609/371472 [7:33:08<12:38:37,  3.14it/s]
 62%|██████▏   | 228610/371472 [7:33:08<12:53:52,  3.08it/s]
 62%|██████▏   | 228611/371472 [7:33:08<12:24:02,  3.20it/s]
 62%|██████▏   | 228612/371472 [7:33:09<12:37:42,  3.14it/s]
 62%|██████▏   | 228613/371472 [7:33:09<13:39:12,  2.91it/s]
 62%|██████▏   | 228614/371472 [7:33:09<13:43:01,  2.89it/s]
 62%|██████▏   | 228615/371472 [7:33:10<13:13:40,  3.00it/s]
 62%|██████▏   | 228616/371472 [7:33:10<12:32:40,  3.16it/s]
 62%|██████▏   | 228617/371472 [7:33:10<12:38:04,  3.14it/s]
 62%|██████▏   | 228618/371472 [7:33:11<12:18:22,  3.22it/s]
 62%|██████▏   | 228619/371472 [7:33:11<11:53:53,  3.34it/s]
 62%|██████▏   | 228620/371472 [7:33:11<11:57:49,  3.32it/s]
                                                            
{'loss': 2.6577, 'learning_rate': 4.462873580555495e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228620/371472 [7:33:11<11:57:49,  3.32it/s]
 62%|██████▏   | 228621/371472 [7:33:11<11:50:59,  3.35it/s]
 62%|██████▏   | 228622/371472 [7:33:12<11:50:35,  3.35it/s]
 62%|██████▏   | 228623/371472 [7:33:12<11:45:36,  3.37it/s]
 62%|██████▏   | 228624/371472 [7:33:12<11:35:15,  3.42it/s]
 62%|██████▏   | 228625/371472 [7:33:13<11:37:38,  3.41it/s]
 62%|██████▏   | 228626/371472 [7:33:13<11:15:00,  3.53it/s]
 62%|██████▏   | 228627/371472 [7:33:13<11:53:08,  3.34it/s]
 62%|██████▏   | 228628/371472 [7:33:14<11:31:51,  3.44it/s]
 62%|██████▏   | 228629/371472 [7:33:14<11:21:48,  3.49it/s]
 62%|██████▏   | 228630/371472 [7:33:14<11:08:40,  3.56it/s]
 62%|██████▏   | 228631/371472 [7:33:14<11:31:51,  3.44it/s]
 62%|██████▏   | 228632/371472 [7:33:15<11:55:31,  3.33it/s]
 62%|██████▏   | 228633/371472 [7:33:15<12:19:24,  3.22it/s]
 62%|██████▏   | 228634/371472 [7:33:15<12:26:31,  3.19it/s]
 62%|██████▏   | 228635/371472 [7:33:16<12:13:38,  3.24it/s]
 62%|██████▏   | 228636/371472 [7:33:16<12:13:26,  3.25it/s]
 62%|██████▏   | 228637/371472 [7:33:16<12:02:37,  3.29it/s]
 62%|██████▏   | 228638/371472 [7:33:17<12:54:43,  3.07it/s]
 62%|██████▏   | 228639/371472 [7:33:17<12:13:11,  3.25it/s]
 62%|██████▏   | 228640/371472 [7:33:17<11:56:06,  3.32it/s]
                                                            
{'loss': 2.7832, 'learning_rate': 4.4623887608007066e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228640/371472 [7:33:17<11:56:06,  3.32it/s]
 62%|██████▏   | 228641/371472 [7:33:17<11:54:39,  3.33it/s]
 62%|██████▏   | 228642/371472 [7:33:18<11:30:47,  3.45it/s]
 62%|██████▏   | 228643/371472 [7:33:18<11:33:55,  3.43it/s]
 62%|██████▏   | 228644/371472 [7:33:18<11:32:55,  3.44it/s]
 62%|██████▏   | 228645/371472 [7:33:19<11:24:06,  3.48it/s]
 62%|██████▏   | 228646/371472 [7:33:19<11:12:02,  3.54it/s]
 62%|██████▏   | 228647/371472 [7:33:19<11:36:16,  3.42it/s]
 62%|██████▏   | 228648/371472 [7:33:19<11:35:31,  3.42it/s]
 62%|██████▏   | 228649/371472 [7:33:20<11:22:15,  3.49it/s]
 62%|██████▏   | 228650/371472 [7:33:20<11:20:18,  3.50it/s]
 62%|██████▏   | 228651/371472 [7:33:20<11:07:21,  3.57it/s]
 62%|██████▏   | 228652/371472 [7:33:21<11:10:18,  3.55it/s]
 62%|██████▏   | 228653/371472 [7:33:21<11:19:35,  3.50it/s]
 62%|██████▏   | 228654/371472 [7:33:21<11:27:08,  3.46it/s]
 62%|██████▏   | 228655/371472 [7:33:21<11:22:46,  3.49it/s]
 62%|██████▏   | 228656/371472 [7:33:22<11:21:35,  3.49it/s]
 62%|██████▏   | 228657/371472 [7:33:22<11:50:21,  3.35it/s]
 62%|██████▏   | 228658/371472 [7:33:22<11:54:47,  3.33it/s]
 62%|██████▏   | 228659/371472 [7:33:23<11:44:31,  3.38it/s]
 62%|██████▏   | 228660/371472 [7:33:23<11:48:57,  3.36it/s]
                                                            
{'loss': 2.7868, 'learning_rate': 4.4619039410459173e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228660/371472 [7:33:23<11:48:57,  3.36it/s]
 62%|██████▏   | 228661/371472 [7:33:23<11:53:25,  3.34it/s]
 62%|██████▏   | 228662/371472 [7:33:24<11:34:35,  3.43it/s]
 62%|██████▏   | 228663/371472 [7:33:24<11:20:36,  3.50it/s]
 62%|██████▏   | 228664/371472 [7:33:24<11:23:09,  3.48it/s]
 62%|██████▏   | 228665/371472 [7:33:24<11:11:57,  3.54it/s]
 62%|██████▏   | 228666/371472 [7:33:25<11:15:01,  3.53it/s]
 62%|██████▏   | 228667/371472 [7:33:25<11:15:07,  3.53it/s]
 62%|██████▏   | 228668/371472 [7:33:25<12:05:46,  3.28it/s]
 62%|██████▏   | 228669/371472 [7:33:26<11:54:09,  3.33it/s]
 62%|██████▏   | 228670/371472 [7:33:26<11:49:03,  3.36it/s]
 62%|██████▏   | 228671/371472 [7:33:26<11:28:16,  3.46it/s]
 62%|██████▏   | 228672/371472 [7:33:27<12:18:49,  3.22it/s]
 62%|██████▏   | 228673/371472 [7:33:27<11:49:54,  3.35it/s]
 62%|██████▏   | 228674/371472 [7:33:27<11:59:33,  3.31it/s]
 62%|██████▏   | 228675/371472 [7:33:27<11:57:53,  3.32it/s]
 62%|██████▏   | 228676/371472 [7:33:28<11:39:30,  3.40it/s]
 62%|██████▏   | 228677/371472 [7:33:28<11:20:37,  3.50it/s]
 62%|██████▏   | 228678/371472 [7:33:28<11:41:42,  3.39it/s]
 62%|██████▏   | 228679/371472 [7:33:29<11:30:44,  3.45it/s]
 62%|██████▏   | 228680/371472 [7:33:29<11:30:24,  3.45it/s]
                                                            
{'loss': 2.7001, 'learning_rate': 4.4614191212911286e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228680/371472 [7:33:29<11:30:24,  3.45it/s]
 62%|██████▏   | 228681/371472 [7:33:29<11:20:31,  3.50it/s]
 62%|██████▏   | 228682/371472 [7:33:29<12:15:23,  3.24it/s]
 62%|██████▏   | 228683/371472 [7:33:30<12:13:05,  3.25it/s]
 62%|██████▏   | 228684/371472 [7:33:30<11:45:53,  3.37it/s]
 62%|██████▏   | 228685/371472 [7:33:30<11:38:10,  3.41it/s]
 62%|██████▏   | 228686/371472 [7:33:31<12:05:35,  3.28it/s]
 62%|██████▏   | 228687/371472 [7:33:31<12:08:45,  3.27it/s]
 62%|██████▏   | 228688/371472 [7:33:31<12:23:53,  3.20it/s]
 62%|██████▏   | 228689/371472 [7:33:32<11:59:31,  3.31it/s]
 62%|██████▏   | 228690/371472 [7:33:32<11:53:34,  3.33it/s]
 62%|██████▏   | 228691/371472 [7:33:32<12:32:56,  3.16it/s]
 62%|██████▏   | 228692/371472 [7:33:32<11:57:24,  3.32it/s]
 62%|██████▏   | 228693/371472 [7:33:33<12:16:43,  3.23it/s]
 62%|██████▏   | 228694/371472 [7:33:33<11:51:14,  3.35it/s]
 62%|██████▏   | 228695/371472 [7:33:33<11:28:39,  3.46it/s]
 62%|██████▏   | 228696/371472 [7:33:34<11:46:04,  3.37it/s]
 62%|██████▏   | 228697/371472 [7:33:34<11:32:19,  3.44it/s]
 62%|██████▏   | 228698/371472 [7:33:34<11:24:54,  3.47it/s]
 62%|██████▏   | 228699/371472 [7:33:34<11:09:45,  3.55it/s]
 62%|██████▏   | 228700/371472 [7:33:35<11:21:32,  3.49it/s]
                                                            
{'loss': 2.7618, 'learning_rate': 4.4609343015363393e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228700/371472 [7:33:35<11:21:32,  3.49it/s]
 62%|██████▏   | 228701/371472 [7:33:35<11:48:43,  3.36it/s]
 62%|██████▏   | 228702/371472 [7:33:35<11:37:42,  3.41it/s]
 62%|██████▏   | 228703/371472 [7:33:36<11:19:02,  3.50it/s]
 62%|██████▏   | 228704/371472 [7:33:36<11:13:07,  3.53it/s]
 62%|██████▏   | 228705/371472 [7:33:36<11:32:33,  3.44it/s]
 62%|██████▏   | 228706/371472 [7:33:37<11:32:54,  3.43it/s]
 62%|██████▏   | 228707/371472 [7:33:37<11:42:35,  3.39it/s]
 62%|██████▏   | 228708/371472 [7:33:37<11:21:30,  3.49it/s]
 62%|██████▏   | 228709/371472 [7:33:37<12:08:15,  3.27it/s]
 62%|██████▏   | 228710/371472 [7:33:38<11:46:26,  3.37it/s]
 62%|██████▏   | 228711/371472 [7:33:38<11:36:56,  3.41it/s]
 62%|██████▏   | 228712/371472 [7:33:38<11:45:08,  3.37it/s]
 62%|██████▏   | 228713/371472 [7:33:39<11:30:37,  3.45it/s]
 62%|██████▏   | 228714/371472 [7:33:39<12:22:51,  3.20it/s]
 62%|██████▏   | 228715/371472 [7:33:39<11:53:14,  3.34it/s]
 62%|██████▏   | 228716/371472 [7:33:40<11:52:28,  3.34it/s]
 62%|██████▏   | 228717/371472 [7:33:40<12:29:34,  3.17it/s]
 62%|██████▏   | 228718/371472 [7:33:40<12:02:54,  3.29it/s]
 62%|██████▏   | 228719/371472 [7:33:40<11:43:05,  3.38it/s]
 62%|██████▏   | 228720/371472 [7:33:41<11:44:28,  3.38it/s]
                                                            
{'loss': 2.7038, 'learning_rate': 4.460449481781551e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228720/371472 [7:33:41<11:44:28,  3.38it/s]
 62%|██████▏   | 228721/371472 [7:33:41<11:43:45,  3.38it/s]
 62%|██████▏   | 228722/371472 [7:33:41<11:29:46,  3.45it/s]
 62%|██████▏   | 228723/371472 [7:33:42<11:26:37,  3.47it/s]
 62%|███���██▏   | 228724/371472 [7:33:42<11:12:09,  3.54it/s]
 62%|██████▏   | 228725/371472 [7:33:42<11:19:23,  3.50it/s]
 62%|██████▏   | 228726/371472 [7:33:42<11:01:40,  3.60it/s]
 62%|██████▏   | 228727/371472 [7:33:43<11:36:18,  3.42it/s]
 62%|██████▏   | 228728/371472 [7:33:43<11:16:38,  3.52it/s]
 62%|██████▏   | 228729/371472 [7:33:43<11:28:36,  3.45it/s]
 62%|██████▏   | 228730/371472 [7:33:44<12:07:15,  3.27it/s]
 62%|██████▏   | 228731/371472 [7:33:44<12:41:21,  3.12it/s]
 62%|██████▏   | 228732/371472 [7:33:44<12:16:23,  3.23it/s]
 62%|██████▏   | 228733/371472 [7:33:45<11:54:33,  3.33it/s]
 62%|██████▏   | 228734/371472 [7:33:45<12:11:50,  3.25it/s]
 62%|██████▏   | 228735/371472 [7:33:45<11:54:23,  3.33it/s]
 62%|██████▏   | 228736/371472 [7:33:45<11:36:05,  3.42it/s]
 62%|██████▏   | 228737/371472 [7:33:46<11:57:32,  3.32it/s]
 62%|██████▏   | 228738/371472 [7:33:46<11:52:12,  3.34it/s]
 62%|██████▏   | 228739/371472 [7:33:46<11:32:52,  3.43it/s]
 62%|██████▏   | 228740/371472 [7:33:47<11:35:22,  3.42it/s]
                                                            
{'loss': 2.9747, 'learning_rate': 4.459964662026761e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228740/371472 [7:33:47<11:35:22,  3.42it/s]
 62%|██████▏   | 228741/371472 [7:33:47<11:35:52,  3.42it/s]
 62%|██████▏   | 228742/371472 [7:33:47<11:41:59,  3.39it/s]
 62%|██████▏   | 228743/371472 [7:33:48<12:08:06,  3.27it/s]
 62%|██████▏   | 228744/371472 [7:33:48<12:37:21,  3.14it/s]
 62%|██████▏   | 228745/371472 [7:33:48<12:07:04,  3.27it/s]
 62%|██████▏   | 228746/371472 [7:33:48<11:58:11,  3.31it/s]
 62%|██████▏   | 228747/371472 [7:33:49<11:32:22,  3.44it/s]
 62%|██████▏   | 228748/371472 [7:33:49<11:41:19,  3.39it/s]
 62%|██████▏   | 228749/371472 [7:33:49<11:19:49,  3.50it/s]
 62%|██████▏   | 228750/371472 [7:33:50<11:43:07,  3.38it/s]
 62%|██████▏   | 228751/371472 [7:33:50<11:17:12,  3.51it/s]
 62%|██████▏   | 228752/371472 [7:33:50<11:20:48,  3.49it/s]
 62%|██████▏   | 228753/371472 [7:33:50<11:10:15,  3.55it/s]
 62%|██████▏   | 228754/371472 [7:33:51<10:57:02,  3.62it/s]
 62%|██████▏   | 228755/371472 [7:33:51<11:05:52,  3.57it/s]
 62%|██████▏   | 228756/371472 [7:33:51<11:05:55,  3.57it/s]
 62%|██████▏   | 228757/371472 [7:33:52<11:06:16,  3.57it/s]
 62%|██████▏   | 228758/371472 [7:33:52<10:58:03,  3.61it/s]
 62%|██████▏   | 228759/371472 [7:33:52<11:17:58,  3.51it/s]
 62%|██████▏   | 228760/371472 [7:33:52<11:29:05,  3.45it/s]
                                                            
{'loss': 2.7802, 'learning_rate': 4.459479842271973e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228760/371472 [7:33:52<11:29:05,  3.45it/s]
 62%|██████▏   | 228761/371472 [7:33:53<11:37:18,  3.41it/s]
 62%|██████▏   | 228762/371472 [7:33:53<11:33:31,  3.43it/s]
 62%|██████▏   | 228763/371472 [7:33:53<11:37:43,  3.41it/s]
 62%|██████▏   | 228764/371472 [7:33:54<11:13:55,  3.53it/s]
 62%|██████▏   | 228765/371472 [7:33:54<11:13:52,  3.53it/s]
 62%|██████▏   | 228766/371472 [7:33:54<13:20:43,  2.97it/s]
 62%|██████▏   | 228767/371472 [7:33:55<13:05:55,  3.03it/s]
 62%|██████▏   | 228768/371472 [7:33:55<12:19:07,  3.22it/s]
 62%|██████▏   | 228769/371472 [7:33:55<12:12:57,  3.24it/s]
 62%|██████▏   | 228770/371472 [7:33:56<12:21:06,  3.21it/s]
 62%|██████▏   | 228771/371472 [7:33:56<11:48:01,  3.36it/s]
 62%|██████▏   | 228772/371472 [7:33:56<11:41:25,  3.39it/s]
 62%|██████▏   | 228773/371472 [7:33:56<11:33:58,  3.43it/s]
 62%|██████▏   | 228774/371472 [7:33:57<11:34:17,  3.43it/s]
 62%|██████▏   | 228775/371472 [7:33:57<12:03:26,  3.29it/s]
 62%|██████▏   | 228776/371472 [7:33:57<11:44:20,  3.38it/s]
 62%|██████▏   | 228777/371472 [7:33:58<11:56:31,  3.32it/s]
 62%|██████▏   | 228778/371472 [7:33:58<11:37:35,  3.41it/s]
 62%|██████▏   | 228779/371472 [7:33:58<11:29:36,  3.45it/s]
 62%|██████▏   | 228780/371472 [7:33:58<11:17:11,  3.51it/s]
                                                            
{'loss': 2.7647, 'learning_rate': 4.458995022517184e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228780/371472 [7:33:58<11:17:11,  3.51it/s]
 62%|██████▏   | 228781/371472 [7:33:59<11:06:38,  3.57it/s]
 62%|██████▏   | 228782/371472 [7:33:59<11:23:39,  3.48it/s]
 62%|██████▏   | 228783/371472 [7:33:59<11:15:47,  3.52it/s]
 62%|██████▏   | 228784/371472 [7:34:00<11:18:37,  3.50it/s]
 62%|██████▏   | 228785/371472 [7:34:00<12:08:30,  3.26it/s]
 62%|██████▏   | 228786/371472 [7:34:00<11:43:16,  3.38it/s]
 62%|██████▏   | 228787/371472 [7:34:00<11:20:18,  3.50it/s]
 62%|██████▏   | 228788/371472 [7:34:01<11:23:20,  3.48it/s]
 62%|██████▏   | 228789/371472 [7:34:01<11:26:18,  3.46it/s]
 62%|██████▏   | 228790/371472 [7:34:01<11:31:31,  3.44it/s]
 62%|██████▏   | 228791/371472 [7:34:02<11:24:56,  3.47it/s]
 62%|██████▏   | 228792/371472 [7:34:02<11:17:38,  3.51it/s]
 62%|██████▏   | 228793/371472 [7:34:02<11:38:52,  3.40it/s]
 62%|██████▏   | 228794/371472 [7:34:02<11:22:12,  3.49it/s]
 62%|██████▏   | 228795/371472 [7:34:03<11:06:13,  3.57it/s]
 62%|██████▏   | 228796/371472 [7:34:03<10:59:03,  3.61it/s]
 62%|██████▏   | 228797/371472 [7:34:03<11:51:49,  3.34it/s]
 62%|██████▏   | 228798/371472 [7:34:04<11:28:02,  3.46it/s]
 62%|██████▏   | 228799/371472 [7:34:04<11:02:52,  3.59it/s]
 62%|██████▏   | 228800/371472 [7:34:04<11:20:10,  3.50it/s]
                                                            
{'loss': 2.8517, 'learning_rate': 4.458510202762395e-07, 'epoch': 9.85}
+
 62%|██████▏   | 228800/371472 [7:34:04<11:20:10,  3.50it/s]
 62%|██████▏   | 228801/371472 [7:34:04<11:09:40,  3.55it/s]
 62%|██████▏   | 228802/371472 [7:34:05<11:03:28,  3.58it/s]
 62%|██████▏   | 228803/371472 [7:34:05<11:20:45,  3.49it/s]
 62%|██████▏   | 228804/371472 [7:34:05<11:07:58,  3.56it/s]
 62%|██████▏   | 228805/371472 [7:34:06<11:02:24,  3.59it/s]
 62%|██████▏   | 228806/371472 [7:34:06<11:49:36,  3.35it/s]
 62%|██████▏   | 228807/371472 [7:34:06<11:55:37,  3.32it/s]
 62%|██████▏   | 228808/371472 [7:34:06<11:33:43,  3.43it/s]
 62%|██████▏   | 228809/371472 [7:34:07<12:11:47,  3.25it/s]
 62%|██████▏   | 228810/371472 [7:34:07<11:59:07,  3.31it/s]
 62%|██████▏   | 228811/371472 [7:34:07<12:01:57,  3.29it/s]
 62%|██████▏   | 228812/371472 [7:34:08<12:02:14,  3.29it/s]
 62%|██████▏   | 228813/371472 [7:34:08<11:44:46,  3.37it/s]
 62%|██████▏   | 228814/371472 [7:34:08<11:50:27,  3.35it/s]
 62%|██████▏   | 228815/371472 [7:34:09<11:38:54,  3.40it/s]
 62%|██████▏   | 228816/371472 [7:34:09<11:46:02,  3.37it/s]
 62%|██████▏   | 228817/371472 [7:34:09<12:11:59,  3.25it/s]
 62%|██████▏   | 228818/371472 [7:34:09<11:32:27,  3.43it/s]
 62%|██████▏   | 228819/371472 [7:34:10<11:53:08,  3.33it/s]
 62%|██████▏   | 228820/371472 [7:34:10<12:12:14,  3.25it/s]
                                                            
{'loss': 2.6253, 'learning_rate': 4.4580253830076057e-07, 'epoch': 9.86}
+
 62%|██████▏   | 228820/371472 [7:34:10<12:12:14,  3.25it/s]
 62%|██████▏   | 228821/371472 [7:34:10<12:00:06,  3.30it/s]
 62%|██████▏   | 228822/371472 [7:34:11<11:31:40,  3.44it/s]
 62%|██████▏   | 228823/371472 [7:34:11<11:29:36,  3.45it/s]
 62%|██████▏   | 228824/371472 [7:34:11<11:17:12,  3.51it/s]
 62%|██████▏   | 228825/371472 [7:34:12<11:02:05,  3.59it/s]
 62%|██████▏   | 228826/371472 [7:34:12<11:03:04,  3.59it/s]
 62%|██████▏   | 228827/371472 [7:34:12<10:56:37,  3.62it/s]
 62%|██████▏   | 228828/371472 [7:34:12<11:01:54,  3.59it/s]
 62%|██████▏   | 228829/371472 [7:34:13<11:29:51,  3.45it/s]
 62%|██████▏   | 228830/371472 [7:34:13<11:32:55,  3.43it/s]
 62%|██████▏   | 228831/371472 [7:34:13<11:30:17,  3.44it/s]
 62%|██████▏   | 228832/371472 [7:34:14<11:35:36,  3.42it/s]
 62%|██████▏   | 228833/371472 [7:34:14<11:30:32,  3.44it/s]
 62%|██████▏   | 228834/371472 [7:34:14<11:31:13,  3.44it/s]
 62%|██████▏   | 228835/371472 [7:34:14<11:14:10,  3.53it/s]
 62%|██████▏   | 228836/371472 [7:34:15<11:01:03,  3.60it/s]
 62%|██████▏   | 228837/371472 [7:34:15<12:50:32,  3.09it/s]
 62%|██████▏   | 228838/371472 [7:34:15<12:26:03,  3.19it/s]
 62%|██████▏   | 228839/371472 [7:34:16<12:25:36,  3.19it/s]
 62%|██████▏   | 228840/371472 [7:34:16<12:05:42,  3.28it/s]
                                                            
{'loss': 2.6648, 'learning_rate': 4.4575405632528175e-07, 'epoch': 9.86}
+
 62%|██████▏   | 228840/371472 [7:34:16<12:05:42,  3.28it/s]
 62%|██████▏   | 228841/371472 [7:34:16<11:51:52,  3.34it/s]
 62%|██████▏   | 228842/371472 [7:34:17<11:45:55,  3.37it/s]
 62%|██████▏   | 228843/371472 [7:34:17<11:36:41,  3.41it/s]
 62%|██████▏   | 228844/371472 [7:34:17<11:25:20,  3.47it/s]
 62%|██████▏   | 228845/371472 [7:34:17<11:45:26,  3.37it/s]
 62%|██████▏   | 228846/371472 [7:34:18<11:41:04,  3.39it/s]
 62%|██████▏   | 228847/371472 [7:34:18<11:27:54,  3.46it/s]
 62%|██████▏   | 228848/371472 [7:34:18<11:52:33,  3.34it/s]
 62%|██████▏   | 228849/371472 [7:34:19<12:46:01,  3.10it/s]
 62%|██████▏   | 228850/371472 [7:34:19<13:33:33,  2.92it/s]
 62%|██████▏   | 228851/371472 [7:34:19<12:44:50,  3.11it/s]
 62%|██████▏   | 228852/371472 [7:34:20<12:29:50,  3.17it/s]
 62%|██████▏   | 228853/371472 [7:34:20<11:59:08,  3.31it/s]
 62%|██████▏   | 228854/371472 [7:34:20<11:42:38,  3.38it/s]
 62%|██████▏   | 228855/371472 [7:34:21<12:05:46,  3.28it/s]
 62%|██████▏   | 228856/371472 [7:34:21<11:46:19,  3.37it/s]
 62%|██████▏   | 228857/371472 [7:34:21<11:29:27,  3.45it/s]
 62%|██████▏   | 228858/371472 [7:34:21<12:31:59,  3.16it/s]
 62%|██████▏   | 228859/371472 [7:34:22<11:55:46,  3.32it/s]
 62%|██████▏   | 228860/371472 [7:34:22<11:42:36,  3.38it/s]
                                                            
{'loss': 2.7749, 'learning_rate': 4.4570557434980277e-07, 'epoch': 9.86}
+
 62%|██████▏   | 228860/371472 [7:34:22<11:42:36,  3.38it/s]
 62%|██████▏   | 228861/371472 [7:34:22<11:52:28,  3.34it/s]
 62%|██████▏   | 228862/371472 [7:34:23<11:37:34,  3.41it/s]
 62%|██████▏   | 228863/371472 [7:34:23<11:22:10,  3.48it/s]
 62%|██████▏   | 228864/371472 [7:34:23<11:46:32,  3.36it/s]
 62%|██████▏   | 228865/371472 [7:34:23<11:43:48,  3.38it/s]
 62%|██████▏   | 228866/371472 [7:34:24<12:12:49,  3.24it/s]
 62%|██████▏   | 228867/371472 [7:34:24<12:25:53,  3.19it/s]
 62%|██████▏   | 228868/371472 [7:34:24<12:06:19,  3.27it/s]
 62%|██████▏   | 228869/371472 [7:34:25<12:04:24,  3.28it/s]
 62%|██████▏   | 228870/371472 [7:34:25<11:54:05,  3.33it/s]
 62%|██████▏   | 228871/371472 [7:34:25<11:50:29,  3.35it/s]
 62%|██████▏   | 228872/371472 [7:34:26<11:34:59,  3.42it/s]
 62%|██████▏   | 228873/371472 [7:34:26<11:47:35,  3.36it/s]
 62%|██████▏   | 228874/371472 [7:34:26<12:11:24,  3.25it/s]
 62%|██████▏   | 228875/371472 [7:34:27<12:11:34,  3.25it/s]
 62%|██████▏   | 228876/371472 [7:34:27<11:54:31,  3.33it/s]
 62%|██████▏   | 228877/371472 [7:34:27<11:40:50,  3.39it/s]
 62%|██████▏   | 228878/371472 [7:34:27<11:34:56,  3.42it/s]
 62%|██████▏   | 228879/371472 [7:34:28<11:59:46,  3.30it/s]
 62%|██████▏   | 228880/371472 [7:34:28<11:37:33,  3.41it/s]
                                                            
{'loss': 2.6959, 'learning_rate': 4.456570923743239e-07, 'epoch': 9.86}
+
 62%|██████▏   | 228880/371472 [7:34:28<11:37:33,  3.41it/s]
 62%|██████▏   | 228881/371472 [7:34:28<11:33:11,  3.43it/s]
 62%|██████▏   | 228882/371472 [7:34:29<11:43:13,  3.38it/s]
 62%|██████▏   | 228883/371472 [7:34:29<11:21:48,  3.49it/s]
 62%|██████▏   | 228884/371472 [7:34:29<11:21:14,  3.49it/s]
 62%|██████▏   | 228885/371472 [7:34:29<11:20:07,  3.49it/s]
 62%|██████▏   | 228886/371472 [7:34:30<11:17:46,  3.51it/s]
 62%|██████▏   | 228887/371472 [7:34:30<11:22:18,  3.48it/s]
 62%|██████▏   | 228888/371472 [7:34:30<11:42:09,  3.38it/s]
 62%|██████▏   | 228889/371472 [7:34:31<11:53:39,  3.33it/s]
 62%|██████▏   | 228890/371472 [7:34:31<11:54:25,  3.33it/s]
 62%|██████▏   | 228891/371472 [7:34:31<11:54:52,  3.32it/s]
 62%|██████▏   | 228892/371472 [7:34:32<11:28:02,  3.45it/s]
 62%|██████▏   | 228893/371472 [7:34:32<11:25:38,  3.47it/s]
 62%|██████▏   | 228894/371472 [7:34:32<11:10:09,  3.55it/s]
 62%|██████▏   | 228895/371472 [7:34:32<11:06:34,  3.56it/s]
 62%|██████▏   | 228896/371472 [7:34:33<11:28:19,  3.45it/s]
 62%|██████▏   | 228897/371472 [7:34:33<11:21:56,  3.48it/s]
 62%|██████▏   | 228898/371472 [7:34:33<11:38:51,  3.40it/s]
 62%|██████▏   | 228899/371472 [7:34:34<12:22:11,  3.20it/s]
 62%|██████▏   | 228900/371472 [7:34:34<12:43:09,  3.11it/s]
                                                            
{'loss': 2.743, 'learning_rate': 4.45608610398845e-07, 'epoch': 9.86}
+
 62%|██████▏   | 228900/371472 [7:34:34<12:43:09,  3.11it/s]
 62%|██████▏   | 228901/371472 [7:34:34<12:53:12,  3.07it/s]
 62%|██████▏   | 228902/371472 [7:34:35<12:53:03,  3.07it/s]
 62%|██████▏   | 228903/371472 [7:34:35<12:22:01,  3.20it/s]
 62%|██████▏   | 228904/371472 [7:34:35<12:06:38,  3.27it/s]
 62%|██████▏   | 228905/371472 [7:34:35<11:38:04,  3.40it/s]
 62%|██████▏   | 228906/371472 [7:34:36<11:26:46,  3.46it/s]
 62%|██████▏   | 228907/371472 [7:34:36<11:23:38,  3.48it/s]
 62%|██████▏   | 228908/371472 [7:34:36<11:52:03,  3.34it/s]
 62%|██████▏   | 228909/371472 [7:34:37<11:51:16,  3.34it/s]
 62%|██████▏   | 228910/371472 [7:34:37<12:11:40,  3.25it/s]
 62%|██████▏   | 228911/371472 [7:34:37<11:58:14,  3.31it/s]
 62%|██████▏   | 228912/371472 [7:34:38<12:24:34,  3.19it/s]
 62%|██████▏   | 228913/371472 [7:34:38<12:33:00,  3.16it/s]
 62%|██████▏   | 228914/371472 [7:34:38<12:07:29,  3.27it/s]
 62%|██████▏   | 228915/371472 [7:34:38<11:46:00,  3.37it/s]
 62%|██████▏   | 228916/371472 [7:34:39<11:50:21,  3.34it/s]
 62%|██████▏   | 228917/371472 [7:34:39<11:41:53,  3.39it/s]
 62%|██████▏   | 228918/371472 [7:34:39<11:18:44,  3.50it/s]
 62%|██████▏   | 228919/371472 [7:34:40<11:03:27,  3.58it/s]
 62%|██████▏   | 228920/371472 [7:34:40<11:42:12,  3.38it/s]
                                                            
{'loss': 2.747, 'learning_rate': 4.4556012842336614e-07, 'epoch': 9.86}
+
 62%|██████▏   | 228920/371472 [7:34:40<11:42:12,  3.38it/s]
 62%|██████▏   | 228921/371472 [7:34:40<11:39:49,  3.39it/s]
 62%|██████▏   | 228922/371472 [7:34:41<11:46:39,  3.36it/s]
 62%|██████▏   | 228923/371472 [7:34:41<11:41:20,  3.39it/s]
 62%|██████▏   | 228924/371472 [7:34:41<12:39:01,  3.13it/s]
 62%|██████▏   | 228925/371472 [7:34:41<12:06:02,  3.27it/s]
 62%|██████▏   | 228926/371472 [7:34:42<11:50:58,  3.34it/s]
 62%|██████▏   | 228927/371472 [7:34:42<12:04:01,  3.28it/s]
 62%|██████▏   | 228928/371472 [7:34:42<12:10:46,  3.25it/s]
 62%|██████▏   | 228929/371472 [7:34:43<11:41:10,  3.39it/s]
 62%|██████▏   | 228930/371472 [7:34:43<11:48:58,  3.35it/s]
 62%|██████▏   | 228931/371472 [7:34:43<12:26:51,  3.18it/s]
 62%|██████▏   | 228932/371472 [7:34:44<12:25:00,  3.19it/s]
 62%|██████▏   | 228933/371472 [7:34:44<12:26:24,  3.18it/s]
 62%|██████▏   | 228934/371472 [7:34:44<12:21:10,  3.21it/s]
 62%|██████▏   | 228935/371472 [7:34:45<12:41:45,  3.12it/s]
 62%|██████▏   | 228936/371472 [7:34:45<12:11:24,  3.25it/s]
 62%|██████▏   | 228937/371472 [7:34:45<11:49:11,  3.35it/s]
 62%|██████▏   | 228938/371472 [7:34:45<11:42:59,  3.38it/s]
 62%|██████▏   | 228939/371472 [7:34:46<11:36:39,  3.41it/s]
 62%|██████▏   | 228940/371472 [7:34:46<11:34:17,  3.42it/s]
                                                            
{'loss': 2.6789, 'learning_rate': 4.455116464478872e-07, 'epoch': 9.86}
+
 62%|██████▏   | 228940/371472 [7:34:46<11:34:17,  3.42it/s]
 62%|██████▏   | 228941/371472 [7:34:46<11:43:18,  3.38it/s]
 62%|██████▏   | 228942/371472 [7:34:47<11:18:20,  3.50it/s]
 62%|██████▏   | 228943/371472 [7:34:47<11:18:50,  3.50it/s]
 62%|██████▏   | 228944/371472 [7:34:47<11:05:06,  3.57it/s]
 62%|██████▏   | 228945/371472 [7:34:48<12:28:51,  3.17it/s]
 62%|██████▏   | 228946/371472 [7:34:48<12:41:31,  3.12it/s]
 62%|██████▏   | 228947/371472 [7:34:48<12:14:52,  3.23it/s]
 62%|██████▏   | 228948/371472 [7:34:48<12:17:30,  3.22it/s]
 62%|██████▏   | 228949/371472 [7:34:49<11:54:41,  3.32it/s]
 62%|██████▏   | 228950/371472 [7:34:49<11:36:54,  3.41it/s]
 62%|██████▏   | 228951/371472 [7:34:49<11:37:08,  3.41it/s]
 62%|██████▏   | 228952/371472 [7:34:50<11:19:50,  3.49it/s]
 62%|██████▏   | 228953/371472 [7:34:50<11:21:53,  3.48it/s]
 62%|██████▏   | 228954/371472 [7:34:50<11:17:08,  3.51it/s]
 62%|██████▏   | 228955/371472 [7:34:50<11:29:09,  3.45it/s]
 62%|██████▏   | 228956/371472 [7:34:51<11:50:38,  3.34it/s]
 62%|██████▏   | 228957/371472 [7:34:51<11:48:19,  3.35it/s]
 62%|██████▏   | 228958/371472 [7:34:51<11:38:07,  3.40it/s]
 62%|██████▏   | 228959/371472 [7:34:52<11:17:37,  3.51it/s]
 62%|██████▏   | 228960/371472 [7:34:52<11:13:37,  3.53it/s]
                                                            
{'loss': 2.7587, 'learning_rate': 4.454631644724084e-07, 'epoch': 9.86}
+
 62%|██████▏   | 228960/371472 [7:34:52<11:13:37,  3.53it/s]
 62%|██████▏   | 228961/371472 [7:34:52<11:25:34,  3.46it/s]
 62%|██████▏   | 228962/371472 [7:34:52<11:25:09,  3.47it/s]
 62%|██████▏   | 228963/371472 [7:34:53<12:18:37,  3.22it/s]
 62%|██████▏   | 228964/371472 [7:34:53<11:53:50,  3.33it/s]
 62%|██████▏   | 228965/371472 [7:34:53<12:04:07,  3.28it/s]
 62%|██████▏   | 228966/371472 [7:34:54<11:48:28,  3.35it/s]
 62%|██████▏   | 228967/371472 [7:34:54<11:29:29,  3.44it/s]
 62%|██████▏   | 228968/371472 [7:34:54<11:24:20,  3.47it/s]
 62%|██████▏   | 228969/371472 [7:34:55<11:21:01,  3.49it/s]
 62%|██████▏   | 228970/371472 [7:34:55<11:20:27,  3.49it/s]
 62%|██████▏   | 228971/371472 [7:34:55<11:13:32,  3.53it/s]
 62%|██████▏   | 228972/371472 [7:34:55<11:08:24,  3.55it/s]
 62%|██████▏   | 228973/371472 [7:34:56<11:11:46,  3.54it/s]
 62%|██████▏   | 228974/371472 [7:34:56<12:14:21,  3.23it/s]
 62%|██████▏   | 228975/371472 [7:34:56<12:23:07,  3.20it/s]
 62%|██████▏   | 228976/371472 [7:34:57<12:00:13,  3.30it/s]
 62%|██████▏   | 228977/371472 [7:34:57<11:50:54,  3.34it/s]
 62%|██████▏   | 228978/371472 [7:34:57<11:45:24,  3.37it/s]
 62%|██████▏   | 228979/371472 [7:34:58<11:45:06,  3.37it/s]
 62%|██████▏   | 228980/371472 [7:34:58<11:29:07,  3.45it/s]
                                                            
{'loss': 2.7325, 'learning_rate': 4.4541468249692946e-07, 'epoch': 9.86}
+
 62%|██████▏   | 228980/371472 [7:34:58<11:29:07,  3.45it/s]
 62%|██████▏   | 228981/371472 [7:34:58<12:02:15,  3.29it/s]
 62%|██████▏   | 228982/371472 [7:34:58<11:52:07,  3.33it/s]
 62%|██████▏   | 228983/371472 [7:34:59<11:34:23,  3.42it/s]
 62%|██████▏   | 228984/371472 [7:34:59<11:32:37,  3.43it/s]
 62%|██████▏   | 228985/371472 [7:34:59<11:57:19,  3.31it/s]
 62%|██████▏   | 228986/371472 [7:35:00<11:47:21,  3.36it/s]
 62%|██████▏   | 228987/371472 [7:35:00<12:14:02,  3.24it/s]
 62%|██████▏   | 228988/371472 [7:35:00<11:59:14,  3.30it/s]
 62%|██████▏   | 228989/371472 [7:35:01<12:32:46,  3.15it/s]
 62%|██████▏   | 228990/371472 [7:35:01<12:21:52,  3.20it/s]
 62%|██████▏   | 228991/371472 [7:35:01<12:40:25,  3.12it/s]
 62%|██████▏   | 228992/371472 [7:35:01<12:07:20,  3.26it/s]
 62%|██████▏   | 228993/371472 [7:35:02<11:45:50,  3.36it/s]
 62%|██████▏   | 228994/371472 [7:35:02<12:11:05,  3.25it/s]
 62%|██████▏   | 228995/371472 [7:35:02<11:56:58,  3.31it/s]
 62%|██████▏   | 228996/371472 [7:35:03<11:50:56,  3.34it/s]
 62%|██████▏   | 228997/371472 [7:35:03<11:45:12,  3.37it/s]
 62%|██████▏   | 228998/371472 [7:35:03<11:36:09,  3.41it/s]
 62%|██████▏   | 228999/371472 [7:35:04<12:00:29,  3.30it/s]
 62%|██████▏   | 229000/371472 [7:35:04<11:36:08,  3.41it/s]
                                                            
{'loss': 2.6533, 'learning_rate': 4.453662005214506e-07, 'epoch': 9.86}
+
 62%|██████▏   | 229000/371472 [7:35:04<11:36:08,  3.41it/s]
 62%|██████▏   | 229001/371472 [7:35:04<12:33:01,  3.15it/s]
 62%|██████▏   | 229002/371472 [7:35:05<12:12:02,  3.24it/s]
 62%|██████▏   | 229003/371472 [7:35:05<11:57:51,  3.31it/s]
 62%|██████▏   | 229004/371472 [7:35:05<13:06:25,  3.02it/s]
 62%|██████▏   | 229005/371472 [7:35:05<12:16:13,  3.23it/s]
 62%|██████▏   | 229006/371472 [7:35:06<11:52:28,  3.33it/s]
 62%|██████▏   | 229007/371472 [7:35:06<11:27:24,  3.45it/s]
 62%|██████▏   | 229008/371472 [7:35:06<11:47:22,  3.36it/s]
 62%|██████▏   | 229009/371472 [7:35:07<11:26:13,  3.46it/s]
 62%|██████▏   | 229010/371472 [7:35:07<11:21:33,  3.48it/s]
 62%|██████▏   | 229011/371472 [7:35:07<11:42:55,  3.38it/s]
 62%|██████▏   | 229012/371472 [7:35:07<11:30:11,  3.44it/s]
 62%|██████▏   | 229013/371472 [7:35:08<11:28:51,  3.45it/s]
 62%|██████▏   | 229014/371472 [7:35:08<11:42:11,  3.38it/s]
 62%|██████▏   | 229015/371472 [7:35:08<11:21:27,  3.48it/s]
 62%|██████▏   | 229016/371472 [7:35:09<11:30:21,  3.44it/s]
 62%|██████▏   | 229017/371472 [7:35:09<11:29:52,  3.44it/s]
 62%|██████▏   | 229018/371472 [7:35:09<11:23:57,  3.47it/s]
 62%|██████▏   | 229019/371472 [7:35:10<12:01:33,  3.29it/s]
 62%|██████▏   | 229020/371472 [7:35:10<11:37:41,  3.40it/s]
                                                            
{'loss': 2.7957, 'learning_rate': 4.4531771854597166e-07, 'epoch': 9.86}
+
 62%|██████▏   | 229020/371472 [7:35:10<11:37:41,  3.40it/s]
 62%|██████▏   | 229021/371472 [7:35:10<11:43:38,  3.37it/s]
 62%|██████▏   | 229022/371472 [7:35:10<11:39:26,  3.39it/s]
 62%|██████▏   | 229023/371472 [7:35:11<11:13:24,  3.53it/s]
 62%|██████▏   | 229024/371472 [7:35:11<11:27:47,  3.45it/s]
 62%|██████▏   | 229025/371472 [7:35:11<11:32:52,  3.43it/s]
 62%|██████▏   | 229026/371472 [7:35:12<11:35:37,  3.41it/s]
 62%|██████▏   | 229027/371472 [7:35:12<11:38:30,  3.40it/s]
 62%|██████▏   | 229028/371472 [7:35:12<12:29:22,  3.17it/s]
 62%|██████▏   | 229029/371472 [7:35:12<12:09:12,  3.26it/s]
 62%|██████▏   | 229030/371472 [7:35:13<12:13:54,  3.23it/s]
 62%|██████▏   | 229031/371472 [7:35:13<12:04:39,  3.28it/s]
 62%|██████▏   | 229032/371472 [7:35:13<11:57:01,  3.31it/s]
 62%|██████▏   | 229033/371472 [7:35:14<11:41:07,  3.39it/s]
 62%|██████▏   | 229034/371472 [7:35:14<11:34:41,  3.42it/s]
 62%|██████▏   | 229035/371472 [7:35:14<12:23:44,  3.19it/s]
 62%|██████▏   | 229036/371472 [7:35:15<12:31:39,  3.16it/s]
 62%|██████▏   | 229037/371472 [7:35:15<12:03:39,  3.28it/s]
 62%|██████▏   | 229038/371472 [7:35:15<11:46:13,  3.36it/s]
 62%|██████▏   | 229039/371472 [7:35:16<11:39:45,  3.39it/s]
 62%|██████▏   | 229040/371472 [7:35:16<11:47:03,  3.36it/s]
                                                            
{'loss': 2.7182, 'learning_rate': 4.4526923657049283e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229040/371472 [7:35:16<11:47:03,  3.36it/s]
 62%|██████▏   | 229041/371472 [7:35:16<12:23:07,  3.19it/s]
 62%|██████▏   | 229042/371472 [7:35:16<12:01:54,  3.29it/s]
 62%|██████▏   | 229043/371472 [7:35:17<11:41:34,  3.38it/s]
 62%|██████▏   | 229044/371472 [7:35:17<11:42:20,  3.38it/s]
 62%|██████▏   | 229045/371472 [7:35:17<11:29:21,  3.44it/s]
 62%|██████▏   | 229046/371472 [7:35:18<11:42:13,  3.38it/s]
 62%|██████▏   | 229047/371472 [7:35:18<11:20:55,  3.49it/s]
 62%|██████▏   | 229048/371472 [7:35:18<11:27:07,  3.45it/s]
 62%|██████▏   | 229049/371472 [7:35:18<11:37:08,  3.40it/s]
 62%|██████▏   | 229050/371472 [7:35:19<12:57:37,  3.05it/s]
 62%|██████▏   | 229051/371472 [7:35:19<12:34:11,  3.15it/s]
 62%|██████▏   | 229052/371472 [7:35:19<12:08:39,  3.26it/s]
 62%|██████▏   | 229053/371472 [7:35:20<11:37:34,  3.40it/s]
 62%|██████▏   | 229054/371472 [7:35:20<11:42:20,  3.38it/s]
 62%|██████▏   | 229055/371472 [7:35:20<11:16:37,  3.51it/s]
 62%|██████▏   | 229056/371472 [7:35:21<11:36:19,  3.41it/s]
 62%|██████▏   | 229057/371472 [7:35:21<12:32:21,  3.15it/s]
 62%|██████▏   | 229058/371472 [7:35:21<12:37:11,  3.13it/s]
 62%|██████▏   | 229059/371472 [7:35:22<12:18:36,  3.21it/s]
 62%|██████▏   | 229060/371472 [7:35:22<12:02:22,  3.29it/s]
                                                            
{'loss': 2.5773, 'learning_rate': 4.4522075459501385e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229060/371472 [7:35:22<12:02:22,  3.29it/s]
 62%|██████▏   | 229061/371472 [7:35:22<11:42:48,  3.38it/s]
 62%|██████▏   | 229062/371472 [7:35:22<12:08:14,  3.26it/s]
 62%|██████▏   | 229063/371472 [7:35:23<11:53:51,  3.32it/s]
 62%|██████▏   | 229064/371472 [7:35:23<12:54:51,  3.06it/s]
 62%|██████▏   | 229065/371472 [7:35:23<13:12:00,  3.00it/s]
 62%|██████▏   | 229066/371472 [7:35:24<13:25:24,  2.95it/s]
 62%|██████▏   | 229067/371472 [7:35:24<12:40:19,  3.12it/s]
 62%|██████▏   | 229068/371472 [7:35:24<12:22:31,  3.20it/s]
 62%|██████▏   | 229069/371472 [7:35:25<12:26:54,  3.18it/s]
 62%|██████▏   | 229070/371472 [7:35:25<12:04:21,  3.28it/s]
 62%|██████▏   | 229071/371472 [7:35:25<11:50:38,  3.34it/s]
 62%|██████▏   | 229072/371472 [7:35:26<11:31:06,  3.43it/s]
 62%|██████▏   | 229073/371472 [7:35:26<11:26:04,  3.46it/s]
 62%|██████▏   | 229074/371472 [7:35:26<11:27:09,  3.45it/s]
 62%|██████▏   | 229075/371472 [7:35:26<11:21:07,  3.48it/s]
 62%|██████▏   | 229076/371472 [7:35:27<11:28:50,  3.45it/s]
 62%|██████▏   | 229077/371472 [7:35:27<11:58:17,  3.30it/s]
 62%|██████▏   | 229078/371472 [7:35:27<12:58:49,  3.05it/s]
 62%|██████▏   | 229079/371472 [7:35:28<13:08:12,  3.01it/s]
 62%|██████▏   | 229080/371472 [7:35:28<13:06:49,  3.02it/s]
                                                            
{'loss': 2.9397, 'learning_rate': 4.4517227261953503e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229080/371472 [7:35:28<13:06:49,  3.02it/s]
 62%|██████▏   | 229081/371472 [7:35:28<12:55:58,  3.06it/s]
 62%|██████▏   | 229082/371472 [7:35:29<12:37:26,  3.13it/s]
 62%|██████���   | 229083/371472 [7:35:29<12:57:00,  3.05it/s]
 62%|██████▏   | 229084/371472 [7:35:29<12:33:00,  3.15it/s]
 62%|██████▏   | 229085/371472 [7:35:30<12:26:28,  3.18it/s]
 62%|██████▏   | 229086/371472 [7:35:30<12:09:15,  3.25it/s]
 62%|██████▏   | 229087/371472 [7:35:30<12:16:50,  3.22it/s]
 62%|██████▏   | 229088/371472 [7:35:31<11:59:06,  3.30it/s]
 62%|██████▏   | 229089/371472 [7:35:31<11:46:41,  3.36it/s]
 62%|██████▏   | 229090/371472 [7:35:31<11:37:29,  3.40it/s]
 62%|██████▏   | 229091/371472 [7:35:31<11:49:55,  3.34it/s]
 62%|██████▏   | 229092/371472 [7:35:32<11:54:07,  3.32it/s]
 62%|██████▏   | 229093/371472 [7:35:32<11:55:40,  3.32it/s]
 62%|██████▏   | 229094/371472 [7:35:32<11:39:38,  3.39it/s]
 62%|██████▏   | 229095/371472 [7:35:33<11:47:15,  3.36it/s]
 62%|██████▏   | 229096/371472 [7:35:33<11:17:43,  3.50it/s]
 62%|██████▏   | 229097/371472 [7:35:33<11:11:29,  3.53it/s]
 62%|██████▏   | 229098/371472 [7:35:33<11:18:03,  3.50it/s]
 62%|██████▏   | 229099/371472 [7:35:34<11:07:17,  3.56it/s]
 62%|██████▏   | 229100/371472 [7:35:34<10:58:26,  3.60it/s]
                                                            
{'loss': 2.7843, 'learning_rate': 4.451237906440561e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229100/371472 [7:35:34<10:58:26,  3.60it/s]
 62%|██████▏   | 229101/371472 [7:35:34<11:25:20,  3.46it/s]
 62%|██████▏   | 229102/371472 [7:35:35<11:27:45,  3.45it/s]
 62%|██████▏   | 229103/371472 [7:35:35<11:49:24,  3.34it/s]
 62%|██████▏   | 229104/371472 [7:35:35<11:55:14,  3.32it/s]
 62%|██████▏   | 229105/371472 [7:35:36<11:57:51,  3.31it/s]
 62%|██████▏   | 229106/371472 [7:35:36<11:59:28,  3.30it/s]
 62%|██████▏   | 229107/371472 [7:35:36<11:39:11,  3.39it/s]
 62%|██████▏   | 229108/371472 [7:35:36<11:30:54,  3.43it/s]
 62%|██████▏   | 229109/371472 [7:35:37<11:40:05,  3.39it/s]
 62%|██████▏   | 229110/371472 [7:35:37<11:55:39,  3.32it/s]
 62%|██████▏   | 229111/371472 [7:35:37<11:50:03,  3.34it/s]
 62%|██████▏   | 229112/371472 [7:35:38<11:51:40,  3.33it/s]
 62%|██████▏   | 229113/371472 [7:35:38<12:04:41,  3.27it/s]
 62%|██████▏   | 229114/371472 [7:35:38<11:29:47,  3.44it/s]
 62%|██████▏   | 229115/371472 [7:35:38<11:11:17,  3.53it/s]
 62%|██████▏   | 229116/371472 [7:35:39<12:08:45,  3.26it/s]
 62%|██████▏   | 229117/371472 [7:35:39<12:03:35,  3.28it/s]
 62%|██████▏   | 229118/371472 [7:35:39<11:33:25,  3.42it/s]
 62%|██████▏   | 229119/371472 [7:35:40<11:12:43,  3.53it/s]
 62%|██████▏   | 229120/371472 [7:35:40<11:15:48,  3.51it/s]
                                                            
{'loss': 2.7145, 'learning_rate': 4.450753086685772e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229120/371472 [7:35:40<11:15:48,  3.51it/s]
 62%|██████▏   | 229121/371472 [7:35:40<11:07:01,  3.56it/s]
 62%|██████▏   | 229122/371472 [7:35:41<11:05:34,  3.56it/s]
 62%|██████▏   | 229123/371472 [7:35:41<11:10:23,  3.54it/s]
 62%|██████▏   | 229124/371472 [7:35:41<11:49:44,  3.34it/s]
 62%|██████▏   | 229125/371472 [7:35:41<11:59:56,  3.30it/s]
 62%|██████▏   | 229126/371472 [7:35:42<12:09:59,  3.25it/s]
 62%|██████▏   | 229127/371472 [7:35:42<11:48:07,  3.35it/s]
 62%|██████▏   | 229128/371472 [7:35:42<11:51:03,  3.34it/s]
 62%|██████▏   | 229129/371472 [7:35:43<11:54:06,  3.32it/s]
 62%|██████▏   | 229130/371472 [7:35:43<11:38:06,  3.40it/s]
 62%|██████▏   | 229131/371472 [7:35:43<11:56:32,  3.31it/s]
 62%|██████▏   | 229132/371472 [7:35:44<11:40:24,  3.39it/s]
 62%|██████▏   | 229133/371472 [7:35:44<11:26:08,  3.46it/s]
 62%|██████▏   | 229134/371472 [7:35:44<11:18:54,  3.49it/s]
 62%|██████▏   | 229135/371472 [7:35:44<11:04:16,  3.57it/s]
 62%|██████▏   | 229136/371472 [7:35:45<11:15:05,  3.51it/s]
 62%|██████▏   | 229137/371472 [7:35:45<11:16:45,  3.51it/s]
 62%|██████▏   | 229138/371472 [7:35:45<11:20:50,  3.48it/s]
 62%|██████▏   | 229139/371472 [7:35:46<11:39:07,  3.39it/s]
 62%|██████▏   | 229140/371472 [7:35:46<11:53:38,  3.32it/s]
                                                            
{'loss': 2.9599, 'learning_rate': 4.450268266930983e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229140/371472 [7:35:46<11:53:38,  3.32it/s]
 62%|██████▏   | 229141/371472 [7:35:46<11:33:03,  3.42it/s]
 62%|██████▏   | 229142/371472 [7:35:46<11:45:02,  3.36it/s]
 62%|██████▏   | 229143/371472 [7:35:47<11:58:22,  3.30it/s]
 62%|██████▏   | 229144/371472 [7:35:47<11:50:23,  3.34it/s]
 62%|██████▏   | 229145/371472 [7:35:47<11:53:34,  3.32it/s]
 62%|██████▏   | 229146/371472 [7:35:48<11:52:51,  3.33it/s]
 62%|██████▏   | 229147/371472 [7:35:48<11:32:10,  3.43it/s]
 62%|██████▏   | 229148/371472 [7:35:48<11:24:34,  3.47it/s]
 62%|██████▏   | 229149/371472 [7:35:48<11:21:56,  3.48it/s]
 62%|██████▏   | 229150/371472 [7:35:49<11:14:59,  3.51it/s]
 62%|██████▏   | 229151/371472 [7:35:49<11:29:09,  3.44it/s]
 62%|██████▏   | 229152/371472 [7:35:49<11:15:54,  3.51it/s]
 62%|██████▏   | 229153/371472 [7:35:50<12:05:04,  3.27it/s]
 62%|██████▏   | 229154/371472 [7:35:50<12:09:02,  3.25it/s]
 62%|██████▏   | 229155/371472 [7:35:50<11:45:24,  3.36it/s]
 62%|██████▏   | 229156/371472 [7:35:51<12:11:12,  3.24it/s]
 62%|██████▏   | 229157/371472 [7:35:51<11:54:50,  3.32it/s]
 62%|██████▏   | 229158/371472 [7:35:51<11:35:16,  3.41it/s]
 62%|██████▏   | 229159/371472 [7:35:51<11:29:14,  3.44it/s]
 62%|██████▏   | 229160/371472 [7:35:52<12:59:15,  3.04it/s]
                                                            
{'loss': 2.6404, 'learning_rate': 4.4497834471761937e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229160/371472 [7:35:52<12:59:15,  3.04it/s]
 62%|██████▏   | 229161/371472 [7:35:52<12:36:29,  3.14it/s]
 62%|██████▏   | 229162/371472 [7:35:52<12:07:22,  3.26it/s]
 62%|██████▏   | 229163/371472 [7:35:53<12:03:05,  3.28it/s]
 62%|██████▏   | 229164/371472 [7:35:53<11:54:46,  3.32it/s]
 62%|██████▏   | 229165/371472 [7:35:53<11:45:20,  3.36it/s]
 62%|██████▏   | 229166/371472 [7:35:54<11:50:28,  3.34it/s]
 62%|██████▏   | 229167/371472 [7:35:54<11:39:18,  3.39it/s]
 62%|██████▏   | 229168/371472 [7:35:54<11:26:58,  3.45it/s]
 62%|██████▏   | 229169/371472 [7:35:54<11:15:01,  3.51it/s]
 62%|██████▏   | 229170/371472 [7:35:55<11:45:26,  3.36it/s]
 62%|██████▏   | 229171/371472 [7:35:55<11:37:31,  3.40it/s]
 62%|██████▏   | 229172/371472 [7:35:55<11:30:42,  3.43it/s]
 62%|██████▏   | 229173/371472 [7:35:56<12:28:10,  3.17it/s]
 62%|██████▏   | 229174/371472 [7:35:56<11:58:38,  3.30it/s]
 62%|██████▏   | 229175/371472 [7:35:56<11:49:14,  3.34it/s]
 62%|██████▏   | 229176/371472 [7:35:57<11:35:21,  3.41it/s]
 62%|██████▏   | 229177/371472 [7:35:57<11:22:50,  3.47it/s]
 62%|██████▏   | 229178/371472 [7:35:57<11:40:58,  3.38it/s]
 62%|██████▏   | 229179/371472 [7:35:58<12:21:30,  3.20it/s]
 62%|██████▏   | 229180/371472 [7:35:58<12:27:15,  3.17it/s]
                                                            
{'loss': 2.5842, 'learning_rate': 4.449298627421405e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229180/371472 [7:35:58<12:27:15,  3.17it/s]
 62%|██████▏   | 229181/371472 [7:35:58<12:18:50,  3.21it/s]
 62%|██████▏   | 229182/371472 [7:35:58<11:59:54,  3.29it/s]
 62%|██████▏   | 229183/371472 [7:35:59<12:02:29,  3.28it/s]
 62%|██████▏   | 229184/371472 [7:35:59<12:18:07,  3.21it/s]
 62%|██████▏   | 229185/371472 [7:35:59<12:07:20,  3.26it/s]
 62%|██████▏   | 229186/371472 [7:36:00<12:08:50,  3.25it/s]
 62%|██████▏   | 229187/371472 [7:36:00<12:14:09,  3.23it/s]
 62%|██████▏   | 229188/371472 [7:36:00<11:47:11,  3.35it/s]
 62%|██████▏   | 229189/371472 [7:36:01<11:38:14,  3.40it/s]
 62%|██████▏   | 229190/371472 [7:36:01<11:37:23,  3.40it/s]
 62%|██████▏   | 229191/371472 [7:36:01<12:04:23,  3.27it/s]
 62%|██████▏   | 229192/371472 [7:36:02<12:35:01,  3.14it/s]
 62%|██████▏   | 229193/371472 [7:36:02<12:01:39,  3.29it/s]
 62%|██████▏   | 229194/371472 [7:36:02<12:53:43,  3.06it/s]
 62%|██████▏   | 229195/371472 [7:36:02<12:25:56,  3.18it/s]
 62%|██████▏   | 229196/371472 [7:36:03<12:01:14,  3.29it/s]
 62%|██████▏   | 229197/371472 [7:36:03<11:46:59,  3.35it/s]
 62%|██████▏   | 229198/371472 [7:36:03<11:36:16,  3.41it/s]
 62%|██████▏   | 229199/371472 [7:36:04<12:14:36,  3.23it/s]
 62%|██████▏   | 229200/371472 [7:36:04<11:43:10,  3.37it/s]
                                                            
{'loss': 2.7618, 'learning_rate': 4.4488138076666156e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229200/371472 [7:36:04<11:43:10,  3.37it/s]
 62%|██████▏   | 229201/371472 [7:36:04<11:33:56,  3.42it/s]
 62%|██████▏   | 229202/371472 [7:36:04<11:33:27,  3.42it/s]
 62%|██████▏   | 229203/371472 [7:36:05<12:01:03,  3.29it/s]
 62%|██████▏   | 229204/371472 [7:36:05<12:49:59,  3.08it/s]
 62%|██████▏   | 229205/371472 [7:36:05<12:36:58,  3.13it/s]
 62%|██████▏   | 229206/371472 [7:36:06<12:56:59,  3.05it/s]
 62%|██████▏   | 229207/371472 [7:36:06<13:40:29,  2.89it/s]
 62%|██████▏   | 229208/371472 [7:36:07<13:01:46,  3.03it/s]
 62%|██████▏   | 229209/371472 [7:36:07<12:28:31,  3.17it/s]
 62%|██████▏   | 229210/371472 [7:36:07<12:12:05,  3.24it/s]
 62%|██████▏   | 229211/371472 [7:36:07<12:24:31,  3.18it/s]
 62%|██████▏   | 229212/371472 [7:36:08<13:12:18,  2.99it/s]
 62%|██████▏   | 229213/371472 [7:36:08<13:13:52,  2.99it/s]
 62%|██████▏   | 229214/371472 [7:36:08<12:33:10,  3.15it/s]
 62%|██████▏   | 229215/371472 [7:36:09<11:53:27,  3.32it/s]
 62%|██████▏   | 229216/371472 [7:36:09<12:09:15,  3.25it/s]
 62%|██████▏   | 229217/371472 [7:36:09<12:14:54,  3.23it/s]
 62%|██████▏   | 229218/371472 [7:36:10<11:43:45,  3.37it/s]
 62%|██████▏   | 229219/371472 [7:36:10<11:46:01,  3.36it/s]
 62%|██████▏   | 229220/371472 [7:36:10<11:35:42,  3.41it/s]
                                                            
{'loss': 2.8299, 'learning_rate': 4.4483289879118274e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229220/371472 [7:36:10<11:35:42,  3.41it/s]
 62%|██████▏   | 229221/371472 [7:36:10<11:32:28,  3.42it/s]
 62%|██████▏   | 229222/371472 [7:36:11<11:20:11,  3.49it/s]
 62%|██████▏   | 229223/371472 [7:36:11<11:30:02,  3.44it/s]
 62%|██████▏   | 229224/371472 [7:36:11<12:23:21,  3.19it/s]
 62%|██████▏   | 229225/371472 [7:36:12<11:58:44,  3.30it/s]
 62%|██████▏   | 229226/371472 [7:36:12<11:56:18,  3.31it/s]
 62%|██████▏   | 229227/371472 [7:36:12<11:32:06,  3.43it/s]
 62%|██████▏   | 229228/371472 [7:36:13<11:40:47,  3.38it/s]
 62%|██████▏   | 229229/371472 [7:36:13<11:26:38,  3.45it/s]
 62%|██████▏   | 229230/371472 [7:36:13<11:24:06,  3.47it/s]
 62%|██████▏   | 229231/371472 [7:36:13<11:17:17,  3.50it/s]
 62%|██████▏   | 229232/371472 [7:36:14<11:04:04,  3.57it/s]
 62%|██████▏   | 229233/371472 [7:36:14<10:58:12,  3.60it/s]
 62%|██████▏   | 229234/371472 [7:36:14<11:09:27,  3.54it/s]
 62%|██████▏   | 229235/371472 [7:36:15<11:24:35,  3.46it/s]
 62%|██████▏   | 229236/371472 [7:36:15<11:24:45,  3.46it/s]
 62%|██████▏   | 229237/371472 [7:36:15<11:32:57,  3.42it/s]
 62%|██████▏   | 229238/371472 [7:36:15<11:46:44,  3.35it/s]
 62%|██████▏   | 229239/371472 [7:36:16<11:43:39,  3.37it/s]
 62%|██████▏   | 229240/371472 [7:36:16<12:14:49,  3.23it/s]
                                                            
{'loss': 2.8898, 'learning_rate': 4.447844168157038e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229240/371472 [7:36:16<12:14:49,  3.23it/s]
 62%|██████▏   | 229241/371472 [7:36:16<12:15:40,  3.22it/s]
 62%|██████▏   | 229242/371472 [7:36:17<12:45:18,  3.10it/s]
 62%|██████▏   | 229243/371472 [7:36:17<11:54:33,  3.32it/s]
 62%|██████▏   | 229244/371472 [7:36:17<12:02:38,  3.28it/s]
 62%|██████▏   | 229245/371472 [7:36:18<11:57:08,  3.31it/s]
 62%|██████▏   | 229246/371472 [7:36:18<11:50:13,  3.34it/s]
 62%|██████▏   | 229247/371472 [7:36:18<11:39:58,  3.39it/s]
 62%|██████▏   | 229248/371472 [7:36:19<12:29:12,  3.16it/s]
 62%|██████▏   | 229249/371472 [7:36:19<12:29:36,  3.16it/s]
 62%|██████▏   | 229250/371472 [7:36:19<12:28:29,  3.17it/s]
 62%|██████▏   | 229251/371472 [7:36:19<12:31:46,  3.15it/s]
 62%|██████▏   | 229252/371472 [7:36:20<13:28:44,  2.93it/s]
 62%|██████▏   | 229253/371472 [7:36:20<13:26:24,  2.94it/s]
 62%|██████▏   | 229254/371472 [7:36:21<13:00:06,  3.04it/s]
 62%|██████▏   | 229255/371472 [7:36:21<12:35:24,  3.14it/s]
 62%|██████▏   | 229256/371472 [7:36:21<11:55:20,  3.31it/s]
 62%|██████▏   | 229257/371472 [7:36:21<11:35:36,  3.41it/s]
 62%|██████▏   | 229258/371472 [7:36:22<11:52:03,  3.33it/s]
 62%|██████▏   | 229259/371472 [7:36:22<11:37:58,  3.40it/s]
 62%|██████▏   | 229260/371472 [7:36:22<12:52:07,  3.07it/s]
                                                            
{'loss': 2.6774, 'learning_rate': 4.4473593484022494e-07, 'epoch': 9.87}
+
 62%|██████▏   | 229260/371472 [7:36:22<12:52:07,  3.07it/s]
 62%|██████▏   | 229261/371472 [7:36:23<13:21:36,  2.96it/s]
 62%|██████▏   | 229262/371472 [7:36:23<13:15:23,  2.98it/s]
 62%|██████▏   | 229263/371472 [7:36:23<12:29:55,  3.16it/s]
 62%|██████▏   | 229264/371472 [7:36:24<12:31:30,  3.15it/s]
 62%|██████▏   | 229265/371472 [7:36:24<12:00:30,  3.29it/s]
 62%|██████▏   | 229266/371472 [7:36:24<11:37:07,  3.40it/s]
 62%|██████▏   | 229267/371472 [7:36:24<11:33:02,  3.42it/s]
 62%|██████▏   | 229268/371472 [7:36:25<12:10:12,  3.25it/s]
 62%|██████▏   | 229269/371472 [7:36:25<12:16:06,  3.22it/s]
 62%|██████▏   | 229270/371472 [7:36:25<11:49:55,  3.34it/s]
 62%|██████▏   | 229271/371472 [7:36:26<11:45:08,  3.36it/s]
 62%|██████▏   | 229272/371472 [7:36:26<11:39:18,  3.39it/s]
 62%|██████▏   | 229273/371472 [7:36:26<11:29:31,  3.44it/s]
 62%|██████▏   | 229274/371472 [7:36:27<11:49:49,  3.34it/s]
 62%|██████▏   | 229275/371472 [7:36:27<11:56:17,  3.31it/s]
 62%|██████▏   | 229276/371472 [7:36:27<11:37:17,  3.40it/s]
 62%|██████▏   | 229277/371472 [7:36:27<11:50:57,  3.33it/s]
 62%|██████▏   | 229278/371472 [7:36:28<12:05:48,  3.27it/s]
 62%|██████▏   | 229279/371472 [7:36:28<11:51:40,  3.33it/s]
 62%|██████▏   | 229280/371472 [7:36:28<11:33:12,  3.42it/s]
                                                            
{'loss': 2.8864, 'learning_rate': 4.44687452864746e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229280/371472 [7:36:28<11:33:12,  3.42it/s]
 62%|██████▏   | 229281/371472 [7:36:29<11:23:06,  3.47it/s]
 62%|██████▏   | 229282/371472 [7:36:29<11:34:00,  3.41it/s]
 62%|██████▏   | 229283/371472 [7:36:29<11:24:47,  3.46it/s]
 62%|██████▏   | 229284/371472 [7:36:30<12:37:59,  3.13it/s]
 62%|██████▏   | 229285/371472 [7:36:30<12:15:12,  3.22it/s]
 62%|██████▏   | 229286/371472 [7:36:30<12:19:53,  3.20it/s]
 62%|██████▏   | 229287/371472 [7:36:31<12:18:35,  3.21it/s]
 62%|██████▏   | 229288/371472 [7:36:31<12:23:43,  3.19it/s]
 62%|██████▏   | 229289/371472 [7:36:31<12:51:55,  3.07it/s]
 62%|██████▏   | 229290/371472 [7:36:31<12:28:49,  3.16it/s]
 62%|██████▏   | 229291/371472 [7:36:32<12:20:09,  3.20it/s]
 62%|██████▏   | 229292/371472 [7:36:32<12:08:44,  3.25it/s]
 62%|██████▏   | 229293/371472 [7:36:32<12:18:06,  3.21it/s]
 62%|██████▏   | 229294/371472 [7:36:33<11:53:53,  3.32it/s]
 62%|██████▏   | 229295/371472 [7:36:33<11:42:26,  3.37it/s]
 62%|██████▏   | 229296/371472 [7:36:33<11:26:59,  3.45it/s]
 62%|██████▏   | 229297/371472 [7:36:34<12:14:18,  3.23it/s]
 62%|██████▏   | 229298/371472 [7:36:34<12:50:22,  3.08it/s]
 62%|██████▏   | 229299/371472 [7:36:34<12:16:49,  3.22it/s]
 62%|██████▏   | 229300/371472 [7:36:34<11:35:09,  3.41it/s]
                                                            
{'loss': 2.6506, 'learning_rate': 4.446389708892672e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229300/371472 [7:36:35<11:35:09,  3.41it/s]
 62%|██████▏   | 229301/371472 [7:36:35<12:31:16,  3.15it/s]
 62%|██████▏   | 229302/371472 [7:36:35<12:29:17,  3.16it/s]
 62%|██████▏   | 229303/371472 [7:36:35<12:12:48,  3.23it/s]
 62%|██████▏   | 229304/371472 [7:36:36<11:51:54,  3.33it/s]
 62%|██████▏   | 229305/371472 [7:36:36<11:31:53,  3.42it/s]
 62%|██████▏   | 229306/371472 [7:36:36<11:24:23,  3.46it/s]
 62%|██████▏   | 229307/371472 [7:36:37<11:46:29,  3.35it/s]
 62%|██████▏   | 229308/371472 [7:36:37<11:51:42,  3.33it/s]
 62%|██████▏   | 229309/371472 [7:36:37<12:36:33,  3.13it/s]
 62%|██████▏   | 229310/371472 [7:36:38<13:10:43,  3.00it/s]
 62%|██████▏   | 229311/371472 [7:36:38<12:23:31,  3.19it/s]
 62%|██████▏   | 229312/371472 [7:36:38<12:41:29,  3.11it/s]
 62%|██████▏   | 229313/371472 [7:36:39<12:11:26,  3.24it/s]
 62%|██████▏   | 229314/371472 [7:36:39<11:44:28,  3.36it/s]
 62%|██████▏   | 229315/371472 [7:36:39<12:46:50,  3.09it/s]
 62%|██████▏   | 229316/371472 [7:36:39<12:15:43,  3.22it/s]
 62%|██████▏   | 229317/371472 [7:36:40<12:02:11,  3.28it/s]
 62%|██████▏   | 229318/371472 [7:36:40<11:48:51,  3.34it/s]
 62%|██████▏   | 229319/371472 [7:36:40<11:41:42,  3.38it/s]
 62%|██████▏   | 229320/371472 [7:36:41<12:06:35,  3.26it/s]
                                                            
{'loss': 2.6895, 'learning_rate': 4.445904889137882e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229320/371472 [7:36:41<12:06:35,  3.26it/s]
 62%|██████▏   | 229321/371472 [7:36:41<12:18:50,  3.21it/s]
 62%|██████▏   | 229322/371472 [7:36:41<12:27:40,  3.17it/s]
 62%|██████▏   | 229323/371472 [7:36:42<12:06:36,  3.26it/s]
 62%|██████▏   | 229324/371472 [7:36:42<12:24:09,  3.18it/s]
 62%|██████▏   | 229325/371472 [7:36:42<12:37:11,  3.13it/s]
 62%|██████▏   | 229326/371472 [7:36:43<12:28:08,  3.17it/s]
 62%|██████▏   | 229327/371472 [7:36:43<12:23:50,  3.18it/s]
 62%|██████▏   | 229328/371472 [7:36:43<11:48:43,  3.34it/s]
 62%|██████▏   | 229329/371472 [7:36:43<11:48:02,  3.35it/s]
 62%|██████▏   | 229330/371472 [7:36:44<11:33:17,  3.42it/s]
 62%|██████▏   | 229331/371472 [7:36:44<11:32:58,  3.42it/s]
 62%|██████▏   | 229332/371472 [7:36:44<11:27:53,  3.44it/s]
 62%|██████▏   | 229333/371472 [7:36:45<11:30:43,  3.43it/s]
 62%|██████▏   | 229334/371472 [7:36:45<12:39:49,  3.12it/s]
 62%|██████▏   | 229335/371472 [7:36:45<12:16:18,  3.22it/s]
 62%|██████▏   | 229336/371472 [7:36:46<12:13:00,  3.23it/s]
 62%|██████▏   | 229337/371472 [7:36:46<11:44:07,  3.36it/s]
 62%|██████▏   | 229338/371472 [7:36:46<11:30:32,  3.43it/s]
 62%|██████▏   | 229339/371472 [7:36:47<12:21:48,  3.19it/s]
 62%|██████▏   | 229340/371472 [7:36:47<12:05:28,  3.27it/s]
                                                            
{'loss': 2.64, 'learning_rate': 4.445420069383094e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229340/371472 [7:36:47<12:05:28,  3.27it/s]
 62%|██████▏   | 229341/371472 [7:36:47<12:40:19,  3.12it/s]
 62%|██████▏   | 229342/371472 [7:36:47<12:20:16,  3.20it/s]
 62%|██████▏   | 229343/371472 [7:36:48<12:44:56,  3.10it/s]
 62%|██████▏   | 229344/371472 [7:36:48<12:49:47,  3.08it/s]
 62%|██████▏   | 229345/371472 [7:36:48<12:16:46,  3.22it/s]
 62%|██████▏   | 229346/371472 [7:36:49<12:10:59,  3.24it/s]
 62%|██████▏   | 229347/371472 [7:36:49<12:41:51,  3.11it/s]
 62%|██████▏   | 229348/371472 [7:36:49<12:08:30,  3.25it/s]
 62%|██████▏   | 229349/371472 [7:36:50<11:52:19,  3.33it/s]
 62%|██████▏   | 229350/371472 [7:36:50<11:27:37,  3.44it/s]
 62%|██████▏   | 229351/371472 [7:36:50<11:36:45,  3.40it/s]
 62%|██████▏   | 229352/371472 [7:36:51<11:53:56,  3.32it/s]
 62%|██████▏   | 229353/371472 [7:36:51<11:36:19,  3.40it/s]
 62%|██████▏   | 229354/371472 [7:36:51<12:03:20,  3.27it/s]
 62%|██████▏   | 229355/371472 [7:36:51<11:37:27,  3.40it/s]
 62%|██████▏   | 229356/371472 [7:36:52<11:38:01,  3.39it/s]
 62%|██████▏   | 229357/371472 [7:36:52<11:21:50,  3.47it/s]
 62%|██████▏   | 229358/371472 [7:36:52<11:29:01,  3.44it/s]
 62%|██████▏   | 229359/371472 [7:36:53<11:10:35,  3.53it/s]
 62%|██████▏   | 229360/371472 [7:36:53<11:15:16,  3.51it/s]
                                                            
{'loss': 2.7518, 'learning_rate': 4.4449352496283045e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229360/371472 [7:36:53<11:15:16,  3.51it/s]
 62%|██████▏   | 229361/371472 [7:36:53<11:19:35,  3.49it/s]
 62%|██████▏   | 229362/371472 [7:36:53<11:39:37,  3.39it/s]
 62%|██████▏   | 229363/371472 [7:36:54<12:09:13,  3.25it/s]
 62%|██████▏   | 229364/371472 [7:36:54<12:05:52,  3.26it/s]
 62%|██████▏   | 229365/371472 [7:36:54<11:48:27,  3.34it/s]
 62%|██████▏   | 229366/371472 [7:36:55<12:38:33,  3.12it/s]
 62%|██████▏   | 229367/371472 [7:36:55<13:04:05,  3.02it/s]
 62%|██████▏   | 229368/371472 [7:36:55<12:56:35,  3.05it/s]
 62%|██████▏   | 229369/371472 [7:36:56<12:08:16,  3.25it/s]
 62%|██████▏   | 229370/371472 [7:36:56<12:14:36,  3.22it/s]
 62%|██████▏   | 229371/371472 [7:36:56<12:22:34,  3.19it/s]
 62%|██████▏   | 229372/371472 [7:36:57<12:08:43,  3.25it/s]
 62%|██████▏   | 229373/371472 [7:36:57<11:54:17,  3.32it/s]
 62%|██████▏   | 229374/371472 [7:36:57<11:48:23,  3.34it/s]
 62%|██████▏   | 229375/371472 [7:36:57<11:39:31,  3.39it/s]
 62%|██████▏   | 229376/371472 [7:36:58<12:31:50,  3.15it/s]
 62%|██████▏   | 229377/371472 [7:36:58<12:15:06,  3.22it/s]
 62%|██████▏   | 229378/371472 [7:36:58<12:05:46,  3.26it/s]
 62%|██████▏   | 229379/371472 [7:36:59<12:24:35,  3.18it/s]
 62%|██████▏   | 229380/371472 [7:36:59<12:34:55,  3.14it/s]
                                                            
{'loss': 2.5919, 'learning_rate': 4.444450429873516e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229380/371472 [7:36:59<12:34:55,  3.14it/s]
 62%|██████▏   | 229381/371472 [7:36:59<12:15:07,  3.22it/s]
 62%|██████▏   | 229382/371472 [7:37:00<11:43:21,  3.37it/s]
 62%|██████▏   | 229383/371472 [7:37:00<11:33:35,  3.41it/s]
 62%|██████▏   | 229384/371472 [7:37:00<11:46:08,  3.35it/s]
 62%|██████▏   | 229385/371472 [7:37:00<11:33:32,  3.41it/s]
 62%|██████▏   | 229386/371472 [7:37:01<11:36:08,  3.40it/s]
 62%|██████▏   | 229387/371472 [7:37:01<11:25:22,  3.46it/s]
 62%|██████▏   | 229388/371472 [7:37:01<12:04:51,  3.27it/s]
 62%|██████▏   | 229389/371472 [7:37:02<11:49:47,  3.34it/s]
 62%|██████▏   | 229390/371472 [7:37:02<11:50:52,  3.33it/s]
 62%|██████▏   | 229391/371472 [7:37:02<12:34:07,  3.14it/s]
 62%|██████▏   | 229392/371472 [7:37:03<12:03:31,  3.27it/s]
 62%|██████▏   | 229393/371472 [7:37:03<12:51:06,  3.07it/s]
 62%|██████▏   | 229394/371472 [7:37:03<12:51:47,  3.07it/s]
 62%|██████▏   | 229395/371472 [7:37:04<12:09:57,  3.24it/s]
 62%|██████▏   | 229396/371472 [7:37:04<12:26:28,  3.17it/s]
 62%|██████▏   | 229397/371472 [7:37:04<11:46:10,  3.35it/s]
 62%|██████▏   | 229398/371472 [7:37:05<12:03:10,  3.27it/s]
 62%|██████▏   | 229399/371472 [7:37:05<11:38:21,  3.39it/s]
 62%|██████▏   | 229400/371472 [7:37:05<11:50:17,  3.33it/s]
                                                            
{'loss': 2.5162, 'learning_rate': 4.4439656101187265e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229400/371472 [7:37:05<11:50:17,  3.33it/s]
 62%|██████▏   | 229401/371472 [7:37:05<11:35:36,  3.40it/s]
 62%|██████▏   | 229402/371472 [7:37:06<11:22:22,  3.47it/s]
 62%|██████▏   | 229403/371472 [7:37:06<11:23:25,  3.46it/s]
 62%|██████▏   | 229404/371472 [7:37:06<11:22:02,  3.47it/s]
 62%|██████▏   | 229405/371472 [7:37:07<11:24:06,  3.46it/s]
 62%|██████▏   | 229406/371472 [7:37:07<11:31:19,  3.42it/s]
 62%|██████▏   | 229407/371472 [7:37:07<11:55:33,  3.31it/s]
 62%|██████▏   | 229408/371472 [7:37:07<11:38:06,  3.39it/s]
 62%|██████▏   | 229409/371472 [7:37:08<11:28:32,  3.44it/s]
 62%|██████▏   | 229410/371472 [7:37:08<11:21:59,  3.47it/s]
 62%|██████▏   | 229411/371472 [7:37:08<11:19:43,  3.48it/s]
 62%|██████▏   | 229412/371472 [7:37:09<11:26:42,  3.45it/s]
 62%|██████▏   | 229413/371472 [7:37:09<11:01:29,  3.58it/s]
 62%|██████▏   | 229414/371472 [7:37:09<10:49:08,  3.65it/s]
 62%|██████▏   | 229415/371472 [7:37:09<11:07:05,  3.55it/s]
 62%|██████▏   | 229416/371472 [7:37:10<11:12:47,  3.52it/s]
 62%|██████▏   | 229417/371472 [7:37:10<10:56:38,  3.61it/s]
 62%|██████▏   | 229418/371472 [7:37:10<11:06:40,  3.55it/s]
 62%|██████▏   | 229419/371472 [7:37:11<11:05:16,  3.56it/s]
 62%|██████▏   | 229420/371472 [7:37:11<11:11:59,  3.52it/s]
                                                            
{'loss': 2.6462, 'learning_rate': 4.4434807903639383e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229420/371472 [7:37:11<11:11:59,  3.52it/s]
 62%|██████▏   | 229421/371472 [7:37:11<11:21:48,  3.47it/s]
 62%|██████▏   | 229422/371472 [7:37:11<11:21:30,  3.47it/s]
 62%|██████▏   | 229423/371472 [7:37:12<11:29:28,  3.43it/s]
 62%|██████▏   | 229424/371472 [7:37:12<11:20:32,  3.48it/s]
 62%|██████▏   | 229425/371472 [7:37:12<11:34:59,  3.41it/s]
 62%|██████▏   | 229426/371472 [7:37:13<11:25:57,  3.45it/s]
 62%|██████▏   | 229427/371472 [7:37:13<11:22:51,  3.47it/s]
 62%|██████▏   | 229428/371472 [7:37:13<11:17:20,  3.50it/s]
 62%|██████▏   | 229429/371472 [7:37:13<11:11:06,  3.53it/s]
 62%|██████▏   | 229430/371472 [7:37:14<11:53:19,  3.32it/s]
 62%|██████▏   | 229431/371472 [7:37:14<11:26:15,  3.45it/s]
 62%|██████▏   | 229432/371472 [7:37:14<12:06:52,  3.26it/s]
 62%|██████▏   | 229433/371472 [7:37:15<12:31:14,  3.15it/s]
 62%|██████▏   | 229434/371472 [7:37:15<12:23:03,  3.19it/s]
 62%|██████▏   | 229435/371472 [7:37:15<12:24:53,  3.18it/s]
 62%|██████▏   | 229436/371472 [7:37:16<11:56:13,  3.31it/s]
 62%|██████▏   | 229437/371472 [7:37:16<11:43:37,  3.36it/s]
 62%|██████▏   | 229438/371472 [7:37:16<12:04:25,  3.27it/s]
 62%|██████▏   | 229439/371472 [7:37:16<12:04:21,  3.27it/s]
 62%|██████▏   | 229440/371472 [7:37:17<11:42:32,  3.37it/s]
                                                            
{'loss': 2.7029, 'learning_rate': 4.4429959706091485e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229440/371472 [7:37:17<11:42:32,  3.37it/s]
 62%|██████▏   | 229441/371472 [7:37:17<12:09:56,  3.24it/s]
 62%|██████▏   | 229442/371472 [7:37:17<11:42:11,  3.37it/s]
 62%|██████▏   | 229443/371472 [7:37:18<11:21:34,  3.47it/s]
 62%|██████▏   | 229444/371472 [7:37:18<11:36:35,  3.40it/s]
 62%|██████▏   | 229445/371472 [7:37:18<14:01:50,  2.81it/s]
 62%|██████▏   | 229446/371472 [7:37:19<14:00:40,  2.82it/s]
 62%|██████▏   | 229447/371472 [7:37:19<13:04:48,  3.02it/s]
 62%|██████▏   | 229448/371472 [7:37:19<12:55:13,  3.05it/s]
 62%|██████▏   | 229449/371472 [7:37:20<12:33:27,  3.14it/s]
 62%|██████▏   | 229450/371472 [7:37:20<12:13:19,  3.23it/s]
 62%|██████▏   | 229451/371472 [7:37:20<11:51:38,  3.33it/s]
 62%|██████▏   | 229452/371472 [7:37:21<11:36:40,  3.40it/s]
 62%|██████▏   | 229453/371472 [7:37:21<11:27:17,  3.44it/s]
 62%|██████▏   | 229454/371472 [7:37:21<11:26:09,  3.45it/s]
 62%|██████▏   | 229455/371472 [7:37:21<12:15:59,  3.22it/s]
 62%|██████▏   | 229456/371472 [7:37:22<12:12:05,  3.23it/s]
 62%|██████▏   | 229457/371472 [7:37:22<11:45:39,  3.35it/s]
 62%|██████▏   | 229458/371472 [7:37:22<11:54:40,  3.31it/s]
 62%|██████▏   | 229459/371472 [7:37:23<11:43:29,  3.36it/s]
 62%|██████▏   | 229460/371472 [7:37:23<11:29:19,  3.43it/s]
                                                            
{'loss': 2.8173, 'learning_rate': 4.44251115085436e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229460/371472 [7:37:23<11:29:19,  3.43it/s]
 62%|██████▏   | 229461/371472 [7:37:23<11:24:46,  3.46it/s]
 62%|██████▏   | 229462/371472 [7:37:23<11:17:11,  3.50it/s]
 62%|██████▏   | 229463/371472 [7:37:24<11:44:35,  3.36it/s]
 62%|██████▏   | 229464/371472 [7:37:24<11:28:59,  3.44it/s]
 62%|██████▏   | 229465/371472 [7:37:24<12:03:31,  3.27it/s]
 62%|██████▏   | 229466/371472 [7:37:25<12:03:22,  3.27it/s]
 62%|██████▏   | 229467/371472 [7:37:25<12:12:28,  3.23it/s]
 62%|██████▏   | 229468/371472 [7:37:25<11:58:09,  3.30it/s]
 62%|██████▏   | 229469/371472 [7:37:26<11:48:09,  3.34it/s]
 62%|██████▏   | 229470/371472 [7:37:26<11:09:46,  3.53it/s]
 62%|██████▏   | 229471/371472 [7:37:26<11:23:02,  3.46it/s]
 62%|██████▏   | 229472/371472 [7:37:27<12:08:48,  3.25it/s]
 62%|██████▏   | 229473/371472 [7:37:27<11:44:17,  3.36it/s]
 62%|██████▏   | 229474/371472 [7:37:27<12:00:33,  3.28it/s]
 62%|██████▏   | 229475/371472 [7:37:27<11:58:56,  3.29it/s]
 62%|██████▏   | 229476/371472 [7:37:28<11:20:07,  3.48it/s]
 62%|██████▏   | 229477/371472 [7:37:28<11:29:13,  3.43it/s]
 62%|██████▏   | 229478/371472 [7:37:28<11:34:30,  3.41it/s]
 62%|██████▏   | 229479/371472 [7:37:29<11:58:45,  3.29it/s]
 62%|██████▏   | 229480/371472 [7:37:29<11:40:28,  3.38it/s]
                                                            
{'loss': 2.7525, 'learning_rate': 4.442026331099571e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229480/371472 [7:37:29<11:40:28,  3.38it/s]
 62%|██████▏   | 229481/371472 [7:37:29<11:38:07,  3.39it/s]
 62%|██████▏   | 229482/371472 [7:37:29<11:28:44,  3.44it/s]
 62%|██████▏   | 229483/371472 [7:37:30<11:25:57,  3.45it/s]
 62%|██████▏   | 229484/371472 [7:37:30<11:08:38,  3.54it/s]
 62%|██████▏   | 229485/371472 [7:37:30<12:05:42,  3.26it/s]
 62%|██████▏   | 229486/371472 [7:37:31<12:06:25,  3.26it/s]
 62%|██████▏   | 229487/371472 [7:37:31<11:45:17,  3.36it/s]
 62%|██████▏   | 229488/371472 [7:37:31<11:29:17,  3.43it/s]
 62%|██████▏   | 229489/371472 [7:37:32<11:45:40,  3.35it/s]
 62%|██████▏   | 229490/371472 [7:37:32<11:40:08,  3.38it/s]
 62%|██████▏   | 229491/371472 [7:37:32<11:38:21,  3.39it/s]
 62%|██████▏   | 229492/371472 [7:37:32<11:43:26,  3.36it/s]
 62%|██████▏   | 229493/371472 [7:37:33<12:56:48,  3.05it/s]
 62%|██████▏   | 229494/371472 [7:37:33<12:36:02,  3.13it/s]
 62%|██████▏   | 229495/371472 [7:37:33<12:07:11,  3.25it/s]
 62%|██████▏   | 229496/371472 [7:37:34<11:54:35,  3.31it/s]
 62%|██████▏   | 229497/371472 [7:37:34<11:53:51,  3.31it/s]
 62%|██████▏   | 229498/371472 [7:37:34<11:35:47,  3.40it/s]
 62%|██████▏   | 229499/371472 [7:37:35<11:15:06,  3.50it/s]
 62%|██████▏   | 229500/371472 [7:37:35<11:22:18,  3.47it/s]
                                                            
{'loss': 2.6046, 'learning_rate': 4.441541511344782e-07, 'epoch': 9.88}
+
 62%|██████▏   | 229500/371472 [7:37:35<11:22:18,  3.47it/s]
 62%|██████▏   | 229501/371472 [7:37:35<12:28:51,  3.16it/s]
 62%|██████��   | 229502/371472 [7:37:36<12:17:00,  3.21it/s]
 62%|██████▏   | 229503/371472 [7:37:36<11:45:16,  3.35it/s]
 62%|██████▏   | 229504/371472 [7:37:36<11:36:12,  3.40it/s]
 62%|██████▏   | 229505/371472 [7:37:36<11:33:16,  3.41it/s]
 62%|██████▏   | 229506/371472 [7:37:37<11:51:10,  3.33it/s]
 62%|██████▏   | 229507/371472 [7:37:37<11:42:42,  3.37it/s]
 62%|██████▏   | 229508/371472 [7:37:37<12:43:25,  3.10it/s]
 62%|██████▏   | 229509/371472 [7:37:38<12:45:04,  3.09it/s]
 62%|██████▏   | 229510/371472 [7:37:38<12:30:41,  3.15it/s]
 62%|██████▏   | 229511/371472 [7:37:38<12:10:15,  3.24it/s]
 62%|██████▏   | 229512/371472 [7:37:39<13:08:30,  3.00it/s]
 62%|██████▏   | 229513/371472 [7:37:39<13:08:13,  3.00it/s]
 62%|██████▏   | 229514/371472 [7:37:39<13:14:40,  2.98it/s]
 62%|██████▏   | 229515/371472 [7:37:40<12:30:37,  3.15it/s]
 62%|██████▏   | 229516/371472 [7:37:40<12:09:48,  3.24it/s]
 62%|██████▏   | 229517/371472 [7:37:40<11:51:54,  3.32it/s]
 62%|██████▏   | 229518/371472 [7:37:40<11:39:24,  3.38it/s]
 62%|██████▏   | 229519/371472 [7:37:41<11:29:33,  3.43it/s]
 62%|██████▏   | 229520/371472 [7:37:41<11:30:27,  3.43it/s]
                                                            
{'loss': 2.6568, 'learning_rate': 4.441056691589993e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229520/371472 [7:37:41<11:30:27,  3.43it/s]
 62%|██████▏   | 229521/371472 [7:37:41<12:13:23,  3.23it/s]
 62%|██████▏   | 229522/371472 [7:37:42<11:53:10,  3.32it/s]
 62%|██████▏   | 229523/371472 [7:37:42<11:41:44,  3.37it/s]
 62%|██████▏   | 229524/371472 [7:37:42<11:43:34,  3.36it/s]
 62%|██████▏   | 229525/371472 [7:37:43<11:23:56,  3.46it/s]
 62%|██████▏   | 229526/371472 [7:37:43<11:42:20,  3.37it/s]
 62%|██████▏   | 229527/371472 [7:37:43<11:24:15,  3.46it/s]
 62%|██████▏   | 229528/371472 [7:37:43<11:14:33,  3.51it/s]
 62%|██████▏   | 229529/371472 [7:37:44<11:10:04,  3.53it/s]
 62%|██████▏   | 229530/371472 [7:37:44<11:17:56,  3.49it/s]
 62%|██████▏   | 229531/371472 [7:37:44<11:09:29,  3.53it/s]
 62%|██████▏   | 229532/371472 [7:37:45<11:13:14,  3.51it/s]
 62%|██████▏   | 229533/371472 [7:37:45<12:12:16,  3.23it/s]
 62%|██████▏   | 229534/371472 [7:37:45<12:25:43,  3.17it/s]
 62%|██████▏   | 229535/371472 [7:37:46<12:05:39,  3.26it/s]
 62%|██████▏   | 229536/371472 [7:37:46<12:54:04,  3.06it/s]
 62%|██████▏   | 229537/371472 [7:37:46<12:52:49,  3.06it/s]
 62%|██████▏   | 229538/371472 [7:37:47<12:40:48,  3.11it/s]
 62%|██████▏   | 229539/371472 [7:37:47<12:04:04,  3.27it/s]
 62%|██████▏   | 229540/371472 [7:37:47<11:43:30,  3.36it/s]
                                                            
{'loss': 2.8816, 'learning_rate': 4.4405718718352047e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229540/371472 [7:37:47<11:43:30,  3.36it/s]
 62%|██████▏   | 229541/371472 [7:37:47<11:52:37,  3.32it/s]
 62%|██████▏   | 229542/371472 [7:37:48<11:57:25,  3.30it/s]
 62%|██████▏   | 229543/371472 [7:37:48<11:39:48,  3.38it/s]
 62%|██████▏   | 229544/371472 [7:37:48<11:44:44,  3.36it/s]
 62%|██████▏   | 229545/371472 [7:37:49<12:02:32,  3.27it/s]
 62%|██████▏   | 229546/371472 [7:37:49<12:42:48,  3.10it/s]
 62%|██████▏   | 229547/371472 [7:37:49<12:48:32,  3.08it/s]
 62%|██████▏   | 229548/371472 [7:37:50<12:35:13,  3.13it/s]
 62%|██████▏   | 229549/371472 [7:37:50<12:16:34,  3.21it/s]
 62%|██████▏   | 229550/371472 [7:37:50<12:08:06,  3.25it/s]
 62%|██████▏   | 229551/371472 [7:37:50<12:17:49,  3.21it/s]
 62%|██████▏   | 229552/371472 [7:37:51<12:09:08,  3.24it/s]
 62%|██████▏   | 229553/371472 [7:37:51<11:41:58,  3.37it/s]
 62%|██████▏   | 229554/371472 [7:37:51<11:31:00,  3.42it/s]
 62%|██████▏   | 229555/371472 [7:37:52<11:29:20,  3.43it/s]
 62%|██████▏   | 229556/371472 [7:37:52<11:35:40,  3.40it/s]
 62%|██████▏   | 229557/371472 [7:37:52<11:39:09,  3.38it/s]
 62%|██████▏   | 229558/371472 [7:37:53<12:15:18,  3.22it/s]
 62%|██████▏   | 229559/371472 [7:37:53<11:54:09,  3.31it/s]
 62%|██████▏   | 229560/371472 [7:37:53<11:48:56,  3.34it/s]
                                                            
{'loss': 2.6224, 'learning_rate': 4.440087052080415e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229560/371472 [7:37:53<11:48:56,  3.34it/s]
 62%|██████▏   | 229561/371472 [7:37:53<11:48:33,  3.34it/s]
 62%|██████▏   | 229562/371472 [7:37:54<11:41:17,  3.37it/s]
 62%|██████▏   | 229563/371472 [7:37:54<11:55:37,  3.31it/s]
 62%|██████▏   | 229564/371472 [7:37:54<12:03:51,  3.27it/s]
 62%|██████▏   | 229565/371472 [7:37:55<11:58:04,  3.29it/s]
 62%|██████▏   | 229566/371472 [7:37:55<11:43:05,  3.36it/s]
 62%|██████▏   | 229567/371472 [7:37:55<11:46:26,  3.35it/s]
 62%|██████▏   | 229568/371472 [7:37:56<11:34:48,  3.40it/s]
 62%|██████▏   | 229569/371472 [7:37:56<11:56:52,  3.30it/s]
 62%|██████▏   | 229570/371472 [7:37:56<12:00:01,  3.28it/s]
 62%|██████▏   | 229571/371472 [7:37:57<12:42:21,  3.10it/s]
 62%|██████▏   | 229572/371472 [7:37:57<12:18:48,  3.20it/s]
 62%|██████▏   | 229573/371472 [7:37:57<12:21:57,  3.19it/s]
 62%|██████▏   | 229574/371472 [7:37:57<12:26:48,  3.17it/s]
 62%|██████▏   | 229575/371472 [7:37:58<12:15:20,  3.22it/s]
 62%|██████▏   | 229576/371472 [7:37:58<11:54:55,  3.31it/s]
 62%|██████▏   | 229577/371472 [7:37:58<11:39:27,  3.38it/s]
 62%|██████▏   | 229578/371472 [7:37:59<11:26:40,  3.44it/s]
 62%|██████▏   | 229579/371472 [7:37:59<11:16:43,  3.49it/s]
 62%|██████▏   | 229580/371472 [7:37:59<11:23:29,  3.46it/s]
                                                            
{'loss': 2.8357, 'learning_rate': 4.4396022323256266e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229580/371472 [7:37:59<11:23:29,  3.46it/s]
 62%|██████▏   | 229581/371472 [7:37:59<11:17:59,  3.49it/s]
 62%|██████▏   | 229582/371472 [7:38:00<11:08:21,  3.54it/s]
 62%|██████▏   | 229583/371472 [7:38:00<13:06:33,  3.01it/s]
 62%|██████▏   | 229584/371472 [7:38:01<13:07:17,  3.00it/s]
 62%|██████▏   | 229585/371472 [7:38:01<12:57:04,  3.04it/s]
 62%|██████▏   | 229586/371472 [7:38:01<12:13:17,  3.22it/s]
 62%|██████▏   | 229587/371472 [7:38:01<11:42:13,  3.37it/s]
 62%|██████▏   | 229588/371472 [7:38:02<11:39:50,  3.38it/s]
 62%|██████▏   | 229589/371472 [7:38:02<11:20:02,  3.48it/s]
 62%|██████▏   | 229590/371472 [7:38:02<11:17:13,  3.49it/s]
 62%|██████▏   | 229591/371472 [7:38:02<11:04:23,  3.56it/s]
 62%|██████▏   | 229592/371472 [7:38:03<10:45:27,  3.66it/s]
 62%|██████▏   | 229593/371472 [7:38:03<11:27:57,  3.44it/s]
 62%|██████▏   | 229594/371472 [7:38:03<11:59:18,  3.29it/s]
 62%|██████▏   | 229595/371472 [7:38:04<12:00:04,  3.28it/s]
 62%|██████▏   | 229596/371472 [7:38:04<12:37:21,  3.12it/s]
 62%|██████▏   | 229597/371472 [7:38:04<13:14:31,  2.98it/s]
 62%|██████▏   | 229598/371472 [7:38:05<12:52:18,  3.06it/s]
 62%|██████▏   | 229599/371472 [7:38:05<12:34:49,  3.13it/s]
 62%|██████▏   | 229600/371472 [7:38:05<12:09:51,  3.24it/s]
                                                            
{'loss': 2.8233, 'learning_rate': 4.4391174125708374e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229600/371472 [7:38:05<12:09:51,  3.24it/s]
 62%|██████▏   | 229601/371472 [7:38:06<11:58:29,  3.29it/s]
 62%|██████▏   | 229602/371472 [7:38:06<11:39:40,  3.38it/s]
 62%|██████▏   | 229603/371472 [7:38:06<11:28:26,  3.43it/s]
 62%|██████▏   | 229604/371472 [7:38:06<11:12:29,  3.52it/s]
 62%|██████▏   | 229605/371472 [7:38:07<11:15:48,  3.50it/s]
 62%|██████▏   | 229606/371472 [7:38:07<11:21:15,  3.47it/s]
 62%|██████▏   | 229607/371472 [7:38:07<11:22:24,  3.46it/s]
 62%|██████▏   | 229608/371472 [7:38:08<12:20:48,  3.19it/s]
 62%|██████▏   | 229609/371472 [7:38:08<12:23:24,  3.18it/s]
 62%|██████▏   | 229610/371472 [7:38:08<11:59:35,  3.29it/s]
 62%|██████▏   | 229611/371472 [7:38:09<11:58:44,  3.29it/s]
 62%|██████▏   | 229612/371472 [7:38:09<12:19:39,  3.20it/s]
 62%|██████▏   | 229613/371472 [7:38:09<11:48:17,  3.34it/s]
 62%|██████▏   | 229614/371472 [7:38:10<12:38:33,  3.12it/s]
 62%|██████▏   | 229615/371472 [7:38:10<11:55:17,  3.31it/s]
 62%|██████▏   | 229616/371472 [7:38:10<12:09:16,  3.24it/s]
 62%|██████▏   | 229617/371472 [7:38:10<12:27:54,  3.16it/s]
 62%|██████▏   | 229618/371472 [7:38:11<12:04:53,  3.26it/s]
 62%|██████▏   | 229619/371472 [7:38:11<12:06:33,  3.25it/s]
 62%|██████▏   | 229620/371472 [7:38:11<12:01:37,  3.28it/s]
                                                            
{'loss': 2.7707, 'learning_rate': 4.4386325928160486e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229620/371472 [7:38:11<12:01:37,  3.28it/s]
 62%|██████▏   | 229621/371472 [7:38:12<11:52:59,  3.32it/s]
 62%|██████▏   | 229622/371472 [7:38:12<11:42:48,  3.36it/s]
 62%|██████▏   | 229623/371472 [7:38:12<11:59:56,  3.28it/s]
 62%|██████▏   | 229624/371472 [7:38:13<12:07:07,  3.25it/s]
 62%|██████▏   | 229625/371472 [7:38:13<11:57:10,  3.30it/s]
 62%|██████▏   | 229626/371472 [7:38:13<12:31:34,  3.15it/s]
 62%|██████▏   | 229627/371472 [7:38:14<12:11:53,  3.23it/s]
 62%|██████▏   | 229628/371472 [7:38:14<11:59:19,  3.29it/s]
 62%|██████▏   | 229629/371472 [7:38:14<12:16:01,  3.21it/s]
 62%|██████▏   | 229630/371472 [7:38:14<11:49:12,  3.33it/s]
 62%|██████▏   | 229631/371472 [7:38:15<11:25:41,  3.45it/s]
 62%|██████▏   | 229632/371472 [7:38:15<11:16:52,  3.49it/s]
 62%|██████▏   | 229633/371472 [7:38:15<11:19:53,  3.48it/s]
 62%|██████▏   | 229634/371472 [7:38:16<11:20:09,  3.48it/s]
 62%|██████▏   | 229635/371472 [7:38:16<11:47:09,  3.34it/s]
 62%|██████▏   | 229636/371472 [7:38:16<11:51:00,  3.32it/s]
 62%|██████▏   | 229637/371472 [7:38:17<13:15:02,  2.97it/s]
 62%|██████▏   | 229638/371472 [7:38:17<12:51:20,  3.06it/s]
 62%|██████▏   | 229639/371472 [7:38:17<12:23:44,  3.18it/s]
 62%|██████▏   | 229640/371472 [7:38:17<12:16:08,  3.21it/s]
                                                            
{'loss': 2.5705, 'learning_rate': 4.4381477730612593e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229640/371472 [7:38:17<12:16:08,  3.21it/s]
 62%|██████▏   | 229641/371472 [7:38:18<11:52:16,  3.32it/s]
 62%|██████▏   | 229642/371472 [7:38:18<11:51:51,  3.32it/s]
 62%|██████▏   | 229643/371472 [7:38:18<12:01:41,  3.28it/s]
 62%|██████▏   | 229644/371472 [7:38:19<11:40:46,  3.37it/s]
 62%|██████▏   | 229645/371472 [7:38:19<11:34:43,  3.40it/s]
 62%|██████▏   | 229646/371472 [7:38:19<11:49:11,  3.33it/s]
 62%|██████▏   | 229647/371472 [7:38:20<11:42:04,  3.37it/s]
 62%|██████▏   | 229648/371472 [7:38:20<11:26:34,  3.44it/s]
 62%|██████▏   | 229649/371472 [7:38:20<11:22:09,  3.47it/s]
 62%|██████▏   | 229650/371472 [7:38:20<11:45:34,  3.35it/s]
 62%|██████▏   | 229651/371472 [7:38:21<11:44:36,  3.35it/s]
 62%|██████▏   | 229652/371472 [7:38:21<12:00:51,  3.28it/s]
 62%|██████▏   | 229653/371472 [7:38:21<12:01:57,  3.27it/s]
 62%|██████▏   | 229654/371472 [7:38:22<11:57:34,  3.29it/s]
 62%|██████▏   | 229655/371472 [7:38:22<11:35:04,  3.40it/s]
 62%|██████▏   | 229656/371472 [7:38:22<11:22:10,  3.46it/s]
 62%|██████▏   | 229657/371472 [7:38:22<11:14:23,  3.50it/s]
 62%|██████▏   | 229658/371472 [7:38:23<11:17:21,  3.49it/s]
 62%|██████▏   | 229659/371472 [7:38:23<11:12:20,  3.52it/s]
 62%|██████▏   | 229660/371472 [7:38:23<11:32:34,  3.41it/s]
                                                            
{'loss': 2.7595, 'learning_rate': 4.437662953306471e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229660/371472 [7:38:23<11:32:34,  3.41it/s]
 62%|██████▏   | 229661/371472 [7:38:24<12:07:35,  3.25it/s]
 62%|██████▏   | 229662/371472 [7:38:24<11:50:38,  3.33it/s]
 62%|██████▏   | 229663/371472 [7:38:24<11:40:25,  3.37it/s]
 62%|██████▏   | 229664/371472 [7:38:25<11:23:42,  3.46it/s]
 62%|██████▏   | 229665/371472 [7:38:25<11:14:10,  3.51it/s]
 62%|██████▏   | 229666/371472 [7:38:25<11:35:00,  3.40it/s]
 62%|██████▏   | 229667/371472 [7:38:25<11:45:31,  3.35it/s]
 62%|██████▏   | 229668/371472 [7:38:26<11:26:59,  3.44it/s]
 62%|██████▏   | 229669/371472 [7:38:26<11:17:37,  3.49it/s]
 62%|██████▏   | 229670/371472 [7:38:26<11:26:44,  3.44it/s]
 62%|██████▏   | 229671/371472 [7:38:27<11:42:40,  3.36it/s]
 62%|██████▏   | 229672/371472 [7:38:27<11:33:34,  3.41it/s]
 62%|██████▏   | 229673/371472 [7:38:27<11:28:36,  3.43it/s]
 62%|██████▏   | 229674/371472 [7:38:28<12:10:31,  3.24it/s]
 62%|██████▏   | 229675/371472 [7:38:28<11:58:09,  3.29it/s]
 62%|██████▏   | 229676/371472 [7:38:28<12:04:54,  3.26it/s]
 62%|██████▏   | 229677/371472 [7:38:28<11:51:29,  3.32it/s]
 62%|██████▏   | 229678/371472 [7:38:29<11:58:31,  3.29it/s]
 62%|██████▏   | 229679/371472 [7:38:29<12:19:03,  3.20it/s]
 62%|██████▏   | 229680/371472 [7:38:29<11:57:17,  3.29it/s]
                                                            
{'loss': 2.756, 'learning_rate': 4.437178133551682e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229680/371472 [7:38:29<11:57:17,  3.29it/s]
 62%|██████▏   | 229681/371472 [7:38:30<11:55:11,  3.30it/s]
 62%|██████▏   | 229682/371472 [7:38:30<12:07:09,  3.25it/s]
 62%|██████▏   | 229683/371472 [7:38:30<11:43:42,  3.36it/s]
 62%|██████▏   | 229684/371472 [7:38:31<11:32:27,  3.41it/s]
 62%|██████▏   | 229685/371472 [7:38:31<11:39:56,  3.38it/s]
 62%|██████▏   | 229686/371472 [7:38:31<11:54:04,  3.31it/s]
 62%|██████▏   | 229687/371472 [7:38:31<11:38:26,  3.38it/s]
 62%|██████▏   | 229688/371472 [7:38:32<12:13:57,  3.22it/s]
 62%|██████▏   | 229689/371472 [7:38:32<12:44:20,  3.09it/s]
 62%|██████▏   | 229690/371472 [7:38:32<12:39:08,  3.11it/s]
 62%|██████▏   | 229691/371472 [7:38:33<12:07:54,  3.25it/s]
 62%|██████▏   | 229692/371472 [7:38:33<11:56:33,  3.30it/s]
 62%|██████▏   | 229693/371472 [7:38:33<11:37:10,  3.39it/s]
 62%|██████▏   | 229694/371472 [7:38:34<11:16:26,  3.49it/s]
 62%|██████▏   | 229695/371472 [7:38:34<11:30:48,  3.42it/s]
 62%|██████▏   | 229696/371472 [7:38:34<11:24:12,  3.45it/s]
 62%|██████▏   | 229697/371472 [7:38:34<11:14:22,  3.50it/s]
 62%|██████▏   | 229698/371472 [7:38:35<11:52:18,  3.32it/s]
 62%|██████▏   | 229699/371472 [7:38:35<11:50:11,  3.33it/s]
 62%|██████▏   | 229700/371472 [7:38:35<11:51:39,  3.32it/s]
                                                            
{'loss': 2.6594, 'learning_rate': 4.436693313796892e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229700/371472 [7:38:35<11:51:39,  3.32it/s]
 62%|██████▏   | 229701/371472 [7:38:36<12:00:46,  3.28it/s]
 62%|██████▏   | 229702/371472 [7:38:36<11:56:54,  3.30it/s]
 62%|██████▏   | 229703/371472 [7:38:36<12:22:54,  3.18it/s]
 62%|██████▏   | 229704/371472 [7:38:37<11:57:09,  3.29it/s]
 62%|██████▏   | 229705/371472 [7:38:37<11:31:26,  3.42it/s]
 62%|██████▏   | 229706/371472 [7:38:37<11:53:44,  3.31it/s]
 62%|██████▏   | 229707/371472 [7:38:38<12:25:14,  3.17it/s]
 62%|██████▏   | 229708/371472 [7:38:38<11:55:55,  3.30it/s]
 62%|██████▏   | 229709/371472 [7:38:38<11:36:12,  3.39it/s]
 62%|██████▏   | 229710/371472 [7:38:38<11:41:55,  3.37it/s]
 62%|██████▏   | 229711/371472 [7:38:39<13:06:20,  3.00it/s]
 62%|██████▏   | 229712/371472 [7:38:39<12:36:05,  3.12it/s]
 62%|██████▏   | 229713/371472 [7:38:39<12:16:20,  3.21it/s]
 62%|██████▏   | 229714/371472 [7:38:40<14:52:56,  2.65it/s]
 62%|██████▏   | 229715/371472 [7:38:40<13:40:12,  2.88it/s]
 62%|██████▏   | 229716/371472 [7:38:40<12:55:16,  3.05it/s]
 62%|██████▏   | 229717/371472 [7:38:41<12:22:07,  3.18it/s]
 62%|██████▏   | 229718/371472 [7:38:41<12:51:45,  3.06it/s]
 62%|██████▏   | 229719/371472 [7:38:41<12:27:24,  3.16it/s]
 62%|██████▏   | 229720/371472 [7:38:42<11:56:19,  3.30it/s]
                                                            
{'loss': 2.7264, 'learning_rate': 4.436208494042104e-07, 'epoch': 9.89}
+
 62%|██████▏   | 229720/371472 [7:38:42<11:56:19,  3.30it/s]
 62%|██████▏   | 229721/371472 [7:38:42<11:57:44,  3.29it/s]
 62%|██████▏   | 229722/371472 [7:38:42<11:43:17,  3.36it/s]
 62%|██████▏   | 229723/371472 [7:38:43<11:30:50,  3.42it/s]
 62%|██████▏   | 229724/371472 [7:38:43<12:03:40,  3.26it/s]
 62%|██████▏   | 229725/371472 [7:38:43<11:38:45,  3.38it/s]
 62%|██████▏   | 229726/371472 [7:38:44<12:32:51,  3.14it/s]
 62%|██████▏   | 229727/371472 [7:38:44<12:05:07,  3.26it/s]
 62%|██████▏   | 229728/371472 [7:38:44<11:41:26,  3.37it/s]
 62%|██████▏   | 229729/371472 [7:38:44<11:45:18,  3.35it/s]
 62%|██████▏   | 229730/371472 [7:38:45<11:55:17,  3.30it/s]
 62%|██████▏   | 229731/371472 [7:38:45<11:35:51,  3.39it/s]
 62%|██████▏   | 229732/371472 [7:38:45<11:37:07,  3.39it/s]
 62%|██████▏   | 229733/371472 [7:38:46<11:25:06,  3.45it/s]
 62%|██████▏   | 229734/371472 [7:38:46<11:27:21,  3.44it/s]
 62%|██████▏   | 229735/371472 [7:38:46<11:29:08,  3.43it/s]
 62%|██████▏   | 229736/371472 [7:38:46<11:44:25,  3.35it/s]
 62%|██████▏   | 229737/371472 [7:38:47<11:54:39,  3.31it/s]
 62%|██████▏   | 229738/371472 [7:38:47<11:42:15,  3.36it/s]
 62%|██████▏   | 229739/371472 [7:38:47<11:49:27,  3.33it/s]
 62%|██████▏   | 229740/371472 [7:38:48<11:57:57,  3.29it/s]
                                                            
{'loss': 2.8597, 'learning_rate': 4.4357236742873145e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229740/371472 [7:38:48<11:57:57,  3.29it/s]
 62%|██████▏   | 229741/371472 [7:38:48<11:40:08,  3.37it/s]
 62%|██████▏   | 229742/371472 [7:38:48<11:34:07,  3.40it/s]
 62%|██████▏   | 229743/371472 [7:38:49<11:26:04,  3.44it/s]
 62%|██████▏   | 229744/371472 [7:38:49<11:22:14,  3.46it/s]
 62%|██████▏   | 229745/371472 [7:38:49<11:16:40,  3.49it/s]
 62%|██████▏   | 229746/371472 [7:38:49<11:26:44,  3.44it/s]
 62%|██████▏   | 229747/371472 [7:38:50<11:39:21,  3.38it/s]
 62%|██████▏   | 229748/371472 [7:38:50<11:30:30,  3.42it/s]
 62%|██████▏   | 229749/371472 [7:38:50<11:26:02,  3.44it/s]
 62%|██████▏   | 229750/371472 [7:38:51<11:21:49,  3.46it/s]
 62%|██████▏   | 229751/371472 [7:38:51<11:30:52,  3.42it/s]
 62%|██████▏   | 229752/371472 [7:38:51<11:33:44,  3.40it/s]
 62%|██████▏   | 229753/371472 [7:38:51<12:03:31,  3.26it/s]
 62%|██████▏   | 229754/371472 [7:38:52<11:38:22,  3.38it/s]
 62%|██████▏   | 229755/371472 [7:38:52<11:30:20,  3.42it/s]
 62%|██████▏   | 229756/371472 [7:38:52<11:35:00,  3.40it/s]
 62%|██████▏   | 229757/371472 [7:38:53<11:28:20,  3.43it/s]
 62%|██████▏   | 229758/371472 [7:38:53<12:22:25,  3.18it/s]
 62%|██████▏   | 229759/371472 [7:38:53<11:48:43,  3.33it/s]
 62%|██████▏   | 229760/371472 [7:38:54<11:59:24,  3.28it/s]
                                                            
{'loss': 2.7373, 'learning_rate': 4.4352388545325257e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229760/371472 [7:38:54<11:59:24,  3.28it/s]
 62%|██████▏   | 229761/371472 [7:38:54<12:03:13,  3.27it/s]
 62%|██████▏   | 229762/371472 [7:38:54<12:16:11,  3.21it/s]
 62%|██████▏   | 229763/371472 [7:38:55<12:15:39,  3.21it/s]
 62%|██████▏   | 229764/371472 [7:38:55<12:24:23,  3.17it/s]
 62%|██████▏   | 229765/371472 [7:38:55<12:07:23,  3.25it/s]
 62%|██████▏   | 229766/371472 [7:38:55<12:25:10,  3.17it/s]
 62%|██████▏   | 229767/371472 [7:38:56<12:03:47,  3.26it/s]
 62%|██████▏   | 229768/371472 [7:38:56<12:19:35,  3.19it/s]
 62%|██████▏   | 229769/371472 [7:38:56<12:19:33,  3.19it/s]
 62%|██████▏   | 229770/371472 [7:38:57<11:44:44,  3.35it/s]
 62%|██████▏   | 229771/371472 [7:38:57<12:03:36,  3.26it/s]
 62%|██████▏   | 229772/371472 [7:38:57<11:40:22,  3.37it/s]
 62%|██████▏   | 229773/371472 [7:38:58<12:23:11,  3.18it/s]
 62%|██████▏   | 229774/371472 [7:38:58<12:03:37,  3.26it/s]
 62%|██████▏   | 229775/371472 [7:38:58<11:39:37,  3.38it/s]
 62%|██████▏   | 229776/371472 [7:38:59<12:41:55,  3.10it/s]
 62%|██████▏   | 229777/371472 [7:38:59<12:47:46,  3.08it/s]
 62%|██████▏   | 229778/371472 [7:38:59<12:03:18,  3.26it/s]
 62%|██████▏   | 229779/371472 [7:38:59<11:45:28,  3.35it/s]
 62%|██████▏   | 229780/371472 [7:39:00<11:34:43,  3.40it/s]
                                                            
{'loss': 2.7717, 'learning_rate': 4.4347540347777364e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229780/371472 [7:39:00<11:34:43,  3.40it/s]
 62%|██████▏   | 229781/371472 [7:39:00<12:37:03,  3.12it/s]
 62%|██████▏   | 229782/371472 [7:39:00<12:07:30,  3.25it/s]
 62%|██████▏   | 229783/371472 [7:39:01<11:57:48,  3.29it/s]
 62%|██████▏   | 229784/371472 [7:39:01<11:50:51,  3.32it/s]
 62%|██████▏   | 229785/371472 [7:39:01<12:20:16,  3.19it/s]
 62%|██████▏   | 229786/371472 [7:39:02<11:52:31,  3.31it/s]
 62%|██████▏   | 229787/371472 [7:39:02<11:43:38,  3.36it/s]
 62%|██████▏   | 229788/371472 [7:39:02<11:51:34,  3.32it/s]
 62%|██████▏   | 229789/371472 [7:39:02<11:43:33,  3.36it/s]
 62%|██████▏   | 229790/371472 [7:39:03<11:25:32,  3.44it/s]
 62%|██████▏   | 229791/371472 [7:39:03<11:26:16,  3.44it/s]
 62%|██████▏   | 229792/371472 [7:39:03<11:27:14,  3.44it/s]
 62%|██████▏   | 229793/371472 [7:39:04<11:42:02,  3.36it/s]
 62%|██████▏   | 229794/371472 [7:39:04<11:23:38,  3.45it/s]
 62%|██████▏   | 229795/371472 [7:39:04<11:37:29,  3.39it/s]
 62%|██████▏   | 229796/371472 [7:39:04<11:20:10,  3.47it/s]
 62%|██████▏   | 229797/371472 [7:39:05<12:19:49,  3.19it/s]
 62%|██████▏   | 229798/371472 [7:39:05<12:02:36,  3.27it/s]
 62%|██████▏   | 229799/371472 [7:39:05<11:44:07,  3.35it/s]
 62%|██████▏   | 229800/371472 [7:39:06<11:37:19,  3.39it/s]
                                                            
{'loss': 2.8305, 'learning_rate': 4.434269215022948e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229800/371472 [7:39:06<11:37:19,  3.39it/s]
 62%|██████▏   | 229801/371472 [7:39:06<11:34:52,  3.40it/s]
 62%|██████▏   | 229802/371472 [7:39:06<11:25:44,  3.44it/s]
 62%|██████▏   | 229803/371472 [7:39:07<11:37:42,  3.38it/s]
 62%|██████▏   | 229804/371472 [7:39:07<11:38:53,  3.38it/s]
 62%|██████▏   | 229805/371472 [7:39:07<12:13:43,  3.22it/s]
 62%|██████▏   | 229806/371472 [7:39:08<12:31:02,  3.14it/s]
 62%|██████▏   | 229807/371472 [7:39:08<12:28:00,  3.16it/s]
 62%|██████▏   | 229808/371472 [7:39:08<12:01:16,  3.27it/s]
 62%|██████▏   | 229809/371472 [7:39:08<11:48:36,  3.33it/s]
 62%|██████▏   | 229810/371472 [7:39:09<11:22:33,  3.46it/s]
 62%|██████▏   | 229811/371472 [7:39:09<12:10:13,  3.23it/s]
 62%|██████▏   | 229812/371472 [7:39:09<12:06:23,  3.25it/s]
 62%|██████▏   | 229813/371472 [7:39:10<12:03:54,  3.26it/s]
 62%|██████▏   | 229814/371472 [7:39:10<11:48:44,  3.33it/s]
 62%|██████▏   | 229815/371472 [7:39:10<11:53:03,  3.31it/s]
 62%|██████▏   | 229816/371472 [7:39:11<11:57:59,  3.29it/s]
 62%|██████▏   | 229817/371472 [7:39:11<12:05:21,  3.25it/s]
 62%|██████▏   | 229818/371472 [7:39:11<11:54:45,  3.30it/s]
 62%|██████▏   | 229819/371472 [7:39:11<11:54:34,  3.30it/s]
 62%|██████▏   | 229820/371472 [7:39:12<11:44:01,  3.35it/s]
                                                            
{'loss': 2.6757, 'learning_rate': 4.4337843952681584e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229820/371472 [7:39:12<11:44:01,  3.35it/s]
 62%|██████▏   | 229821/371472 [7:39:12<11:45:47,  3.34it/s]
 62%|██████▏   | 229822/371472 [7:39:12<11:35:47,  3.39it/s]
 62%|██████▏   | 229823/371472 [7:39:13<11:36:39,  3.39it/s]
 62%|██████▏   | 229824/371472 [7:39:13<11:53:24,  3.31it/s]
 62%|██████▏   | 229825/371472 [7:39:13<11:37:26,  3.38it/s]
 62%|██████▏   | 229826/371472 [7:39:14<11:44:58,  3.35it/s]
 62%|██████▏   | 229827/371472 [7:39:14<11:46:04,  3.34it/s]
 62%|██████▏   | 229828/371472 [7:39:14<11:45:56,  3.34it/s]
 62%|██████▏   | 229829/371472 [7:39:15<12:29:42,  3.15it/s]
 62%|██████▏   | 229830/371472 [7:39:15<12:32:57,  3.14it/s]
 62%|██████▏   | 229831/371472 [7:39:15<12:14:44,  3.21it/s]
 62%|██████▏   | 229832/371472 [7:39:15<12:09:12,  3.24it/s]
 62%|██████▏   | 229833/371472 [7:39:16<12:06:18,  3.25it/s]
 62%|██████▏   | 229834/371472 [7:39:16<12:02:20,  3.27it/s]
 62%|██████▏   | 229835/371472 [7:39:16<11:35:07,  3.40it/s]
 62%|██████▏   | 229836/371472 [7:39:17<11:40:33,  3.37it/s]
 62%|██████▏   | 229837/371472 [7:39:17<11:36:40,  3.39it/s]
 62%|██████▏   | 229838/371472 [7:39:17<11:13:25,  3.51it/s]
 62%|██████▏   | 229839/371472 [7:39:17<11:47:43,  3.34it/s]
 62%|██████▏   | 229840/371472 [7:39:18<12:35:48,  3.12it/s]
                                                            
{'loss': 2.5936, 'learning_rate': 4.43329957551337e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229840/371472 [7:39:18<12:35:48,  3.12it/s]
 62%|██████▏   | 229841/371472 [7:39:18<12:44:22,  3.09it/s]
 62%|██████▏   | 229842/371472 [7:39:18<12:11:03,  3.23it/s]
 62%|██████▏   | 229843/371472 [7:39:19<11:55:43,  3.30it/s]
 62%|██████▏   | 229844/371472 [7:39:19<11:50:07,  3.32it/s]
 62%|██████▏   | 229845/371472 [7:39:19<11:46:32,  3.34it/s]
 62%|██████▏   | 229846/371472 [7:39:20<11:39:16,  3.38it/s]
 62%|██████▏   | 229847/371472 [7:39:20<11:24:28,  3.45it/s]
 62%|██████▏   | 229848/371472 [7:39:20<11:49:20,  3.33it/s]
 62%|██████▏   | 229849/371472 [7:39:21<11:28:28,  3.43it/s]
 62%|██████▏   | 229850/371472 [7:39:21<11:14:02,  3.50it/s]
 62%|██████▏   | 229851/371472 [7:39:21<12:07:17,  3.25it/s]
 62%|██████▏   | 229852/371472 [7:39:21<11:56:14,  3.30it/s]
 62%|██████▏   | 229853/371472 [7:39:22<11:43:37,  3.35it/s]
 62%|██████▏   | 229854/371472 [7:39:22<12:20:28,  3.19it/s]
 62%|██████▏   | 229855/371472 [7:39:22<11:54:30,  3.30it/s]
 62%|██████▏   | 229856/371472 [7:39:23<11:52:43,  3.31it/s]
 62%|██████▏   | 229857/371472 [7:39:23<11:41:07,  3.37it/s]
 62%|██████▏   | 229858/371472 [7:39:23<11:24:42,  3.45it/s]
 62%|██████▏   | 229859/371472 [7:39:24<11:29:35,  3.42it/s]
 62%|██████▏   | 229860/371472 [7:39:24<11:57:26,  3.29it/s]
                                                            
{'loss': 2.8563, 'learning_rate': 4.432814755758581e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229860/371472 [7:39:24<11:57:26,  3.29it/s]
 62%|██████▏   | 229861/371472 [7:39:24<11:40:02,  3.37it/s]
 62%|██████▏   | 229862/371472 [7:39:24<12:06:35,  3.25it/s]
 62%|██████▏   | 229863/371472 [7:39:25<11:52:14,  3.31it/s]
 62%|██████▏   | 229864/371472 [7:39:25<11:59:59,  3.28it/s]
 62%|██████▏   | 229865/371472 [7:39:25<12:04:21,  3.26it/s]
 62%|██████▏   | 229866/371472 [7:39:26<12:20:49,  3.19it/s]
 62%|██████▏   | 229867/371472 [7:39:26<12:51:07,  3.06it/s]
 62%|██████▏   | 229868/371472 [7:39:26<12:52:45,  3.05it/s]
 62%|██████▏   | 229869/371472 [7:39:27<12:22:26,  3.18it/s]
 62%|██████▏   | 229870/371472 [7:39:27<11:59:00,  3.28it/s]
 62%|██████▏   | 229871/371472 [7:39:27<11:55:11,  3.30it/s]
 62%|██████▏   | 229872/371472 [7:39:28<11:52:16,  3.31it/s]
 62%|██████▏   | 229873/371472 [7:39:28<11:56:44,  3.29it/s]
 62%|██████▏   | 229874/371472 [7:39:28<11:45:14,  3.35it/s]
 62%|██████▏   | 229875/371472 [7:39:28<11:31:12,  3.41it/s]
 62%|██████▏   | 229876/371472 [7:39:29<11:13:46,  3.50it/s]
 62%|██████▏   | 229877/371472 [7:39:29<11:59:59,  3.28it/s]
 62%|██████▏   | 229878/371472 [7:39:29<12:12:55,  3.22it/s]
 62%|██████▏   | 229879/371472 [7:39:30<12:00:09,  3.28it/s]
 62%|██████▏   | 229880/371472 [7:39:30<11:38:52,  3.38it/s]
                                                            
{'loss': 2.6284, 'learning_rate': 4.432329936003792e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229880/371472 [7:39:30<11:38:52,  3.38it/s]
 62%|██████▏   | 229881/371472 [7:39:30<11:38:25,  3.38it/s]
 62%|██████▏   | 229882/371472 [7:39:31<11:42:30,  3.36it/s]
 62%|██████▏   | 229883/371472 [7:39:31<11:46:41,  3.34it/s]
 62%|██████▏   | 229884/371472 [7:39:31<11:36:34,  3.39it/s]
 62%|██████▏   | 229885/371472 [7:39:31<11:40:45,  3.37it/s]
 62%|██████▏   | 229886/371472 [7:39:32<12:16:03,  3.21it/s]
 62%|██████▏   | 229887/371472 [7:39:32<13:05:40,  3.00it/s]
 62%|██████▏   | 229888/371472 [7:39:32<12:58:09,  3.03it/s]
 62%|██████▏   | 229889/371472 [7:39:33<12:28:03,  3.15it/s]
 62%|██████▏   | 229890/371472 [7:39:33<12:06:42,  3.25it/s]
 62%|██████▏   | 229891/371472 [7:39:33<12:07:41,  3.24it/s]
 62%|██████▏   | 229892/371472 [7:39:34<11:58:13,  3.29it/s]
 62%|██████▏   | 229893/371472 [7:39:34<11:45:59,  3.34it/s]
 62%|██████▏   | 229894/371472 [7:39:34<11:37:52,  3.38it/s]
 62%|██████▏   | 229895/371472 [7:39:35<11:32:45,  3.41it/s]
 62%|██████▏   | 229896/371472 [7:39:35<12:18:14,  3.20it/s]
 62%|██████▏   | 229897/371472 [7:39:35<12:32:10,  3.14it/s]
 62%|██████▏   | 229898/371472 [7:39:35<12:10:30,  3.23it/s]
 62%|██████▏   | 229899/371472 [7:39:36<11:51:59,  3.31it/s]
 62%|██████▏   | 229900/371472 [7:39:36<11:23:13,  3.45it/s]
                                                            
{'loss': 2.6192, 'learning_rate': 4.431845116249003e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229900/371472 [7:39:36<11:23:13,  3.45it/s]
 62%|██████▏   | 229901/371472 [7:39:36<11:31:16,  3.41it/s]
 62%|██████▏   | 229902/371472 [7:39:37<11:13:17,  3.50it/s]
 62%|██████▏   | 229903/371472 [7:39:37<11:24:04,  3.45it/s]
 62%|██████▏   | 229904/371472 [7:39:37<11:37:36,  3.38it/s]
 62%|██████▏   | 229905/371472 [7:39:38<11:53:20,  3.31it/s]
 62%|██████▏   | 229906/371472 [7:39:38<11:50:22,  3.32it/s]
 62%|██████▏   | 229907/371472 [7:39:38<11:57:15,  3.29it/s]
 62%|██████▏   | 229908/371472 [7:39:38<11:51:33,  3.32it/s]
 62%|██████▏   | 229909/371472 [7:39:39<11:43:35,  3.35it/s]
 62%|██████▏   | 229910/371472 [7:39:39<11:45:07,  3.35it/s]
 62%|██████▏   | 229911/371472 [7:39:39<11:39:49,  3.37it/s]
 62%|██████▏   | 229912/371472 [7:39:40<11:54:14,  3.30it/s]
 62%|██████▏   | 229913/371472 [7:39:40<11:33:51,  3.40it/s]
 62%|██████▏   | 229914/371472 [7:39:40<11:28:56,  3.42it/s]
 62%|██████▏   | 229915/371472 [7:39:40<11:17:32,  3.48it/s]
 62%|██████▏   | 229916/371472 [7:39:41<11:02:21,  3.56it/s]
 62%|██████▏   | 229917/371472 [7:39:41<12:03:26,  3.26it/s]
 62%|██████▏   | 229918/371472 [7:39:41<11:29:38,  3.42it/s]
 62%|██████▏   | 229919/371472 [7:39:42<11:36:00,  3.39it/s]
 62%|██████▏   | 229920/371472 [7:39:42<11:22:14,  3.46it/s]
                                                            
{'loss': 2.6951, 'learning_rate': 4.4313602964942146e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229920/371472 [7:39:42<11:22:14,  3.46it/s]
 62%|██████▏   | 229921/371472 [7:39:42<11:08:36,  3.53it/s]
 62%|██████▏   | 229922/371472 [7:39:43<11:51:41,  3.31it/s]
 62%|██████▏   | 229923/371472 [7:39:43<11:54:47,  3.30it/s]
 62%|██████▏   | 229924/371472 [7:39:43<11:59:42,  3.28it/s]
 62%|██████▏   | 229925/371472 [7:39:43<11:43:25,  3.35it/s]
 62%|██████▏   | 229926/371472 [7:39:44<11:31:56,  3.41it/s]
 62%|██████▏   | 229927/371472 [7:39:44<11:29:46,  3.42it/s]
 62%|██████▏   | 229928/371472 [7:39:44<11:14:43,  3.50it/s]
 62%|██████▏   | 229929/371472 [7:39:45<11:10:52,  3.52it/s]
 62%|██████▏   | 229930/371472 [7:39:45<11:08:06,  3.53it/s]
 62%|██████▏   | 229931/371472 [7:39:45<11:02:20,  3.56it/s]
 62%|██████▏   | 229932/371472 [7:39:45<12:00:45,  3.27it/s]
 62%|██████▏   | 229933/371472 [7:39:46<11:41:31,  3.36it/s]
 62%|██████▏   | 229934/371472 [7:39:46<11:48:54,  3.33it/s]
 62%|██████▏   | 229935/371472 [7:39:46<11:26:17,  3.44it/s]
 62%|██████▏   | 229936/371472 [7:39:47<12:04:00,  3.26it/s]
 62%|██████▏   | 229937/371472 [7:39:47<12:01:28,  3.27it/s]
 62%|██████▏   | 229938/371472 [7:39:47<12:14:49,  3.21it/s]
 62%|██████▏   | 229939/371472 [7:39:48<12:20:33,  3.19it/s]
 62%|██████▏   | 229940/371472 [7:39:48<11:56:24,  3.29it/s]
                                                            
{'loss': 2.7005, 'learning_rate': 4.4308754767394253e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229940/371472 [7:39:48<11:56:24,  3.29it/s]
 62%|██████▏   | 229941/371472 [7:39:48<12:11:22,  3.23it/s]
 62%|██████▏   | 229942/371472 [7:39:49<11:42:18,  3.36it/s]
 62%|██████▏   | 229943/371472 [7:39:49<11:32:32,  3.41it/s]
 62%|██████▏   | 229944/371472 [7:39:49<11:21:38,  3.46it/s]
 62%|██████▏   | 229945/371472 [7:39:49<11:13:53,  3.50it/s]
 62%|██████▏   | 229946/371472 [7:39:50<11:16:59,  3.48it/s]
 62%|██████▏   | 229947/371472 [7:39:50<11:12:53,  3.51it/s]
 62%|██████▏   | 229948/371472 [7:39:50<11:11:48,  3.51it/s]
 62%|██████▏   | 229949/371472 [7:39:51<11:51:53,  3.31it/s]
 62%|██████▏   | 229950/371472 [7:39:51<11:28:39,  3.43it/s]
 62%|██████▏   | 229951/371472 [7:39:51<11:33:53,  3.40it/s]
 62%|██████▏   | 229952/371472 [7:39:51<11:25:21,  3.44it/s]
 62%|██████▏   | 229953/371472 [7:39:52<11:18:16,  3.48it/s]
 62%|██████▏   | 229954/371472 [7:39:52<11:41:21,  3.36it/s]
 62%|██████▏   | 229955/371472 [7:39:52<11:20:26,  3.47it/s]
 62%|██████▏   | 229956/371472 [7:39:53<11:31:42,  3.41it/s]
 62%|██████▏   | 229957/371472 [7:39:53<13:36:13,  2.89it/s]
 62%|██████▏   | 229958/371472 [7:39:53<13:58:11,  2.81it/s]
 62%|██████▏   | 229959/371472 [7:39:54<13:28:30,  2.92it/s]
 62%|██████▏   | 229960/371472 [7:39:54<13:24:41,  2.93it/s]
                                                            
{'loss': 2.846, 'learning_rate': 4.4303906569846366e-07, 'epoch': 9.9}
+
 62%|██████▏   | 229960/371472 [7:39:54<13:24:41,  2.93it/s]
 62%|██████▏   | 229961/371472 [7:39:54<12:43:40,  3.09it/s]
 62%|██████▏   | 229962/371472 [7:39:55<12:29:06,  3.15it/s]
 62%|██████▏   | 229963/371472 [7:39:55<13:35:46,  2.89it/s]
 62%|██████▏   | 229964/371472 [7:39:55<12:54:05,  3.05it/s]
 62%|██████▏   | 229965/371472 [7:39:56<12:28:27,  3.15it/s]
 62%|██████▏   | 229966/371472 [7:39:56<12:06:03,  3.25it/s]
 62%|██████▏   | 229967/371472 [7:39:56<12:25:14,  3.16it/s]
 62%|██████▏   | 229968/371472 [7:39:57<12:39:05,  3.11it/s]
 62%|██████▏   | 229969/371472 [7:39:57<11:59:46,  3.28it/s]
 62%|██████▏   | 229970/371472 [7:39:57<11:51:23,  3.32it/s]
 62%|██████▏   | 229971/371472 [7:39:57<11:30:03,  3.42it/s]
 62%|██████▏   | 229972/371472 [7:39:58<11:39:54,  3.37it/s]
 62%|██████▏   | 229973/371472 [7:39:58<11:56:01,  3.29it/s]
 62%|██████▏   | 229974/371472 [7:39:58<11:55:20,  3.30it/s]
 62%|██████▏   | 229975/371472 [7:39:59<11:45:10,  3.34it/s]
 62%|██████▏   | 229976/371472 [7:39:59<12:40:12,  3.10it/s]
 62%|██████▏   | 229977/371472 [7:39:59<12:30:59,  3.14it/s]
 62%|██████▏   | 229978/371472 [7:40:00<12:39:20,  3.11it/s]
 62%|██████▏   | 229979/371472 [7:40:00<12:29:45,  3.15it/s]
 62%|██████▏   | 229980/371472 [7:40:00<12:32:35,  3.13it/s]
                                                            
{'loss': 2.8555, 'learning_rate': 4.429905837229848e-07, 'epoch': 9.91}
+
 62%|██████▏   | 229980/371472 [7:40:00<12:32:35,  3.13it/s]
 62%|██████▏   | 229981/371472 [7:40:01<12:17:50,  3.20it/s]
 62%|██████▏   | 229982/371472 [7:40:01<12:05:01,  3.25it/s]
 62%|██████▏   | 229983/371472 [7:40:01<11:59:58,  3.28it/s]
 62%|██████▏   | 229984/371472 [7:40:02<11:59:34,  3.28it/s]
 62%|██████▏   | 229985/371472 [7:40:02<12:00:22,  3.27it/s]
 62%|██████▏   | 229986/371472 [7:40:02<11:58:16,  3.28it/s]
 62%|██████▏   | 229987/371472 [7:40:02<12:27:37,  3.15it/s]
 62%|██████▏   | 229988/371472 [7:40:03<12:16:45,  3.20it/s]
 62%|██████▏   | 229989/371472 [7:40:03<12:18:41,  3.19it/s]
 62%|██████▏   | 229990/371472 [7:40:03<12:03:42,  3.26it/s]
 62%|██████▏   | 229991/371472 [7:40:04<11:57:49,  3.28it/s]
 62%|██████▏   | 229992/371472 [7:40:04<12:22:24,  3.18it/s]
 62%|██████▏   | 229993/371472 [7:40:04<13:22:46,  2.94it/s]
 62%|██████▏   | 229994/371472 [7:40:05<12:54:06,  3.05it/s]
 62%|██████▏   | 229995/371472 [7:40:05<12:35:43,  3.12it/s]
 62%|██████▏   | 229996/371472 [7:40:05<12:31:47,  3.14it/s]
 62%|██████▏   | 229997/371472 [7:40:06<12:21:16,  3.18it/s]
 62%|██████▏   | 229998/371472 [7:40:06<12:28:26,  3.15it/s]
 62%|██████▏   | 229999/371472 [7:40:06<12:10:27,  3.23it/s]
 62%|██████▏   | 230000/371472 [7:40:07<12:01:35,  3.27it/s]
                                                            
{'loss': 2.6858, 'learning_rate': 4.429421017475059e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230000/371472 [7:40:07<12:01:35,  3.27it/s]
 62%|██████▏   | 230001/371472 [7:40:07<12:05:05,  3.25it/s]
 62%|██████▏   | 230002/371472 [7:40:07<12:06:46,  3.24it/s]
 62%|██████▏   | 230003/371472 [7:40:07<12:01:09,  3.27it/s]
 62%|██████▏   | 230004/371472 [7:40:08<11:36:26,  3.39it/s]
 62%|██████▏   | 230005/371472 [7:40:08<11:14:57,  3.49it/s]
 62%|██████▏   | 230006/371472 [7:40:08<11:16:50,  3.48it/s]
 62%|██████▏   | 230007/371472 [7:40:09<11:12:31,  3.51it/s]
 62%|██████▏   | 230008/371472 [7:40:09<11:19:37,  3.47it/s]
 62%|██████▏   | 230009/371472 [7:40:09<11:51:32,  3.31it/s]
 62%|██████▏   | 230010/371472 [7:40:10<12:21:49,  3.18it/s]
 62%|██████▏   | 230011/371472 [7:40:10<12:03:59,  3.26it/s]
 62%|██████▏   | 230012/371472 [7:40:10<12:12:25,  3.22it/s]
 62%|██████▏   | 230013/371472 [7:40:11<12:44:57,  3.08it/s]
 62%|██████▏   | 230014/371472 [7:40:11<13:29:17,  2.91it/s]
 62%|██████▏   | 230015/371472 [7:40:11<12:54:05,  3.05it/s]
 62%|██████▏   | 230016/371472 [7:40:12<13:10:37,  2.98it/s]
 62%|██████▏   | 230017/371472 [7:40:12<12:36:23,  3.12it/s]
 62%|██████▏   | 230018/371472 [7:40:12<13:08:02,  2.99it/s]
 62%|██████▏   | 230019/371472 [7:40:12<12:45:58,  3.08it/s]
 62%|██████▏   | 230020/371472 [7:40:13<12:43:39,  3.09it/s]
                                                            
{'loss': 2.6543, 'learning_rate': 4.428936197720269e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230020/371472 [7:40:13<12:43:39,  3.09it/s]
 62%|██████▏   | 230021/371472 [7:40:13<13:08:31,  2.99it/s]
 62%|██████▏   | 230022/371472 [7:40:13<12:52:11,  3.05it/s]
 62%|██████▏   | 230023/371472 [7:40:14<12:34:34,  3.12it/s]
 62%|██████▏   | 230024/371472 [7:40:14<12:01:53,  3.27it/s]
 62%|██████▏   | 230025/371472 [7:40:14<11:36:45,  3.38it/s]
 62%|██████▏   | 230026/371472 [7:40:15<12:22:41,  3.17it/s]
 62%|██████▏   | 230027/371472 [7:40:15<11:54:49,  3.30it/s]
 62%|██████▏   | 230028/371472 [7:40:15<11:23:49,  3.45it/s]
 62%|██████▏   | 230029/371472 [7:40:16<11:25:24,  3.44it/s]
 62%|██████▏   | 230030/371472 [7:40:16<11:22:41,  3.45it/s]
 62%|██████▏   | 230031/371472 [7:40:16<11:05:14,  3.54it/s]
 62%|██████▏   | 230032/371472 [7:40:16<12:15:14,  3.21it/s]
 62%|██████▏   | 230033/371472 [7:40:17<12:05:25,  3.25it/s]
 62%|██████▏   | 230034/371472 [7:40:17<12:34:01,  3.13it/s]
 62%|██████▏   | 230035/371472 [7:40:17<12:44:52,  3.08it/s]
 62%|██████▏   | 230036/371472 [7:40:18<12:18:26,  3.19it/s]
 62%|██████▏   | 230037/371472 [7:40:18<13:36:54,  2.89it/s]
 62%|██████▏   | 230038/371472 [7:40:18<13:34:34,  2.89it/s]
 62%|██████▏   | 230039/371472 [7:40:19<13:01:58,  3.01it/s]
 62%|██████▏   | 230040/371472 [7:40:19<12:37:08,  3.11it/s]
                                                            
{'loss': 2.872, 'learning_rate': 4.428451377965481e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230040/371472 [7:40:19<12:37:08,  3.11it/s]
 62%|██████▏   | 230041/371472 [7:40:19<12:24:07,  3.17it/s]
 62%|██████▏   | 230042/371472 [7:40:20<12:38:03,  3.11it/s]
 62%|██████▏   | 230043/371472 [7:40:20<12:19:42,  3.19it/s]
 62%|██████▏   | 230044/371472 [7:40:20<11:53:16,  3.30it/s]
 62%|██████▏   | 230045/371472 [7:40:21<11:40:33,  3.36it/s]
 62%|██████▏   | 230046/371472 [7:40:21<12:11:23,  3.22it/s]
 62%|██████▏   | 230047/371472 [7:40:21<12:03:39,  3.26it/s]
 62%|██████▏   | 230048/371472 [7:40:22<12:03:12,  3.26it/s]
 62%|██████▏   | 230049/371472 [7:40:22<11:49:21,  3.32it/s]
 62%|██████▏   | 230050/371472 [7:40:22<11:48:46,  3.33it/s]
 62%|██████▏   | 230051/371472 [7:40:22<11:52:11,  3.31it/s]
 62%|██████▏   | 230052/371472 [7:40:23<12:03:01,  3.26it/s]
 62%|██████▏   | 230053/371472 [7:40:23<12:37:59,  3.11it/s]
 62%|██████▏   | 230054/371472 [7:40:23<12:10:04,  3.23it/s]
 62%|██████▏   | 230055/371472 [7:40:24<12:06:50,  3.24it/s]
 62%|██████▏   | 230056/371472 [7:40:24<11:56:38,  3.29it/s]
 62%|██████▏   | 230057/371472 [7:40:24<11:51:48,  3.31it/s]
 62%|██████▏   | 230058/371472 [7:40:25<11:30:55,  3.41it/s]
 62%|██████▏   | 230059/371472 [7:40:25<11:17:18,  3.48it/s]
 62%|██████▏   | 230060/371472 [7:40:25<11:35:43,  3.39it/s]
                                                            
{'loss': 2.9425, 'learning_rate': 4.427966558210692e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230060/371472 [7:40:25<11:35:43,  3.39it/s]
 62%|██████▏   | 230061/371472 [7:40:25<11:26:14,  3.43it/s]
 62%|██████▏   | 230062/371472 [7:40:26<11:24:38,  3.44it/s]
 62%|██████▏   | 230063/371472 [7:40:26<11:12:58,  3.50it/s]
 62%|██████▏   | 230064/371472 [7:40:26<11:33:29,  3.40it/s]
 62%|██████▏   | 230065/371472 [7:40:27<11:46:32,  3.34it/s]
 62%|██████▏   | 230066/371472 [7:40:27<11:20:16,  3.46it/s]
 62%|██████▏   | 230067/371472 [7:40:27<12:04:37,  3.25it/s]
 62%|██████▏   | 230068/371472 [7:40:28<12:30:33,  3.14it/s]
 62%|██████▏   | 230069/371472 [7:40:28<12:41:22,  3.10it/s]
 62%|██████▏   | 230070/371472 [7:40:28<12:06:54,  3.24it/s]
 62%|██████▏   | 230071/371472 [7:40:28<11:49:47,  3.32it/s]
 62%|██████▏   | 230072/371472 [7:40:29<11:39:04,  3.37it/s]
 62%|██████▏   | 230073/371472 [7:40:29<11:25:31,  3.44it/s]
 62%|██████▏   | 230074/371472 [7:40:29<11:44:05,  3.35it/s]
 62%|██████▏   | 230075/371472 [7:40:30<11:44:31,  3.34it/s]
 62%|██████▏   | 230076/371472 [7:40:30<12:52:09,  3.05it/s]
 62%|██████▏   | 230077/371472 [7:40:30<12:15:14,  3.21it/s]
 62%|██████▏   | 230078/371472 [7:40:31<12:04:12,  3.25it/s]
 62%|██████▏   | 230079/371472 [7:40:31<11:51:38,  3.31it/s]
 62%|██████▏   | 230080/371472 [7:40:31<11:33:16,  3.40it/s]
                                                            
{'loss': 2.7322, 'learning_rate': 4.427481738455903e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230080/371472 [7:40:31<11:33:16,  3.40it/s]
 62%|██████▏   | 230081/371472 [7:40:31<11:33:05,  3.40it/s]
 62%|██████▏   | 230082/371472 [7:40:32<11:37:14,  3.38it/s]
 62%|██████▏   | 230083/371472 [7:40:32<11:30:50,  3.41it/s]
 62%|██████▏   | 230084/371472 [7:40:32<12:04:59,  3.25it/s]
 62%|██████▏   | 230085/371472 [7:40:33<11:56:29,  3.29it/s]
 62%|██████▏   | 230086/371472 [7:40:33<12:06:14,  3.24it/s]
 62%|██████▏   | 230087/371472 [7:40:33<12:00:12,  3.27it/s]
 62%|██████▏   | 230088/371472 [7:40:34<12:09:16,  3.23it/s]
 62%|██████▏   | 230089/371472 [7:40:34<11:44:56,  3.34it/s]
 62%|██████▏   | 230090/371472 [7:40:34<11:50:05,  3.32it/s]
 62%|██████▏   | 230091/371472 [7:40:35<12:03:19,  3.26it/s]
 62%|██████▏   | 230092/371472 [7:40:35<11:39:40,  3.37it/s]
 62%|██████▏   | 230093/371472 [7:40:35<12:30:16,  3.14it/s]
 62%|██████▏   | 230094/371472 [7:40:35<12:03:24,  3.26it/s]
 62%|██████▏   | 230095/371472 [7:40:36<12:18:42,  3.19it/s]
 62%|██████▏   | 230096/371472 [7:40:36<12:45:50,  3.08it/s]
 62%|██████▏   | 230097/371472 [7:40:36<12:29:43,  3.14it/s]
 62%|██████▏   | 230098/371472 [7:40:37<12:15:35,  3.20it/s]
 62%|██████▏   | 230099/371472 [7:40:37<11:55:06,  3.29it/s]
 62%|██████▏   | 230100/371472 [7:40:37<12:01:26,  3.27it/s]
                                                            
{'loss': 2.5811, 'learning_rate': 4.4269969187011137e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230100/371472 [7:40:37<12:01:26,  3.27it/s]
 62%|██████▏   | 230101/371472 [7:40:38<11:49:04,  3.32it/s]
 62%|██████▏   | 230102/371472 [7:40:38<11:26:49,  3.43it/s]
 62%|██████▏   | 230103/371472 [7:40:38<11:45:54,  3.34it/s]
 62%|██████▏   | 230104/371472 [7:40:39<12:04:43,  3.25it/s]
 62%|██████▏   | 230105/371472 [7:40:39<11:49:13,  3.32it/s]
 62%|██████▏   | 230106/371472 [7:40:39<11:53:32,  3.30it/s]
 62%|██████▏   | 230107/371472 [7:40:39<12:10:54,  3.22it/s]
 62%|██████▏   | 230108/371472 [7:40:40<11:45:32,  3.34it/s]
 62%|██████▏   | 230109/371472 [7:40:40<11:50:00,  3.32it/s]
 62%|██████▏   | 230110/371472 [7:40:40<11:59:44,  3.27it/s]
 62%|██████▏   | 230111/371472 [7:40:41<12:07:23,  3.24it/s]
 62%|██████▏   | 230112/371472 [7:40:41<12:32:01,  3.13it/s]
 62%|██████▏   | 230113/371472 [7:40:41<12:18:03,  3.19it/s]
 62%|██████▏   | 230114/371472 [7:40:42<12:24:42,  3.16it/s]
 62%|██████▏   | 230115/371472 [7:40:42<12:06:48,  3.24it/s]
 62%|██████▏   | 230116/371472 [7:40:42<12:24:10,  3.17it/s]
 62%|██████▏   | 230117/371472 [7:40:43<12:02:29,  3.26it/s]
 62%|██████▏   | 230118/371472 [7:40:43<11:49:52,  3.32it/s]
 62%|██████▏   | 230119/371472 [7:40:43<11:41:50,  3.36it/s]
 62%|██████▏   | 230120/371472 [7:40:43<11:44:59,  3.34it/s]
                                                            
{'loss': 2.7535, 'learning_rate': 4.4265120989463255e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230120/371472 [7:40:43<11:44:59,  3.34it/s]
 62%|██████▏   | 230121/371472 [7:40:44<11:45:10,  3.34it/s]
 62%|██████▏   | 230122/371472 [7:40:44<11:53:25,  3.30it/s]
 62%|██████▏   | 230123/371472 [7:40:44<11:59:20,  3.27it/s]
 62%|██████▏   | 230124/371472 [7:40:45<11:31:25,  3.41it/s]
 62%|██████▏   | 230125/371472 [7:40:45<11:12:52,  3.50it/s]
 62%|██████▏   | 230126/371472 [7:40:45<11:26:57,  3.43it/s]
 62%|██████▏   | 230127/371472 [7:40:46<12:13:58,  3.21it/s]
 62%|██████▏   | 230128/371472 [7:40:46<12:36:29,  3.11it/s]
 62%|██████▏   | 230129/371472 [7:40:46<12:08:19,  3.23it/s]
 62%|██████▏   | 230130/371472 [7:40:46<12:13:43,  3.21it/s]
 62%|██████▏   | 230131/371472 [7:40:47<12:00:33,  3.27it/s]
 62%|██████▏   | 230132/371472 [7:40:47<11:36:54,  3.38it/s]
 62%|██████▏   | 230133/371472 [7:40:47<11:16:13,  3.48it/s]
 62%|██████▏   | 230134/371472 [7:40:48<12:30:30,  3.14it/s]
 62%|██████▏   | 230135/371472 [7:40:48<12:20:27,  3.18it/s]
 62%|██████▏   | 230136/371472 [7:40:48<12:00:10,  3.27it/s]
 62%|██████▏   | 230137/371472 [7:40:49<11:50:16,  3.32it/s]
 62%|██████▏   | 230138/371472 [7:40:49<11:50:08,  3.32it/s]
 62%|██████▏   | 230139/371472 [7:40:49<11:46:39,  3.33it/s]
 62%|██████▏   | 230140/371472 [7:40:49<11:22:06,  3.45it/s]
                                                            
{'loss': 2.7364, 'learning_rate': 4.4260272791915357e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230140/371472 [7:40:49<11:22:06,  3.45it/s]
 62%|██████▏   | 230141/371472 [7:40:50<12:01:10,  3.27it/s]
 62%|██████▏   | 230142/371472 [7:40:50<11:46:13,  3.34it/s]
 62%|██████▏   | 230143/371472 [7:40:50<11:31:54,  3.40it/s]
 62%|██████▏   | 230144/371472 [7:40:51<13:34:17,  2.89it/s]
 62%|██████▏   | 230145/371472 [7:40:51<12:44:06,  3.08it/s]
 62%|██████▏   | 230146/371472 [7:40:51<12:03:02,  3.26it/s]
 62%|██████▏   | 230147/371472 [7:40:52<11:53:19,  3.30it/s]
 62%|██████▏   | 230148/371472 [7:40:52<11:37:09,  3.38it/s]
 62%|██████▏   | 230149/371472 [7:40:52<11:23:19,  3.45it/s]
 62%|██████▏   | 230150/371472 [7:40:52<11:24:35,  3.44it/s]
 62%|██████▏   | 230151/371472 [7:40:53<11:17:56,  3.47it/s]
 62%|██████▏   | 230152/371472 [7:40:53<11:46:56,  3.33it/s]
 62%|██████▏   | 230153/371472 [7:40:53<11:46:05,  3.34it/s]
 62%|██████▏   | 230154/371472 [7:40:54<11:28:11,  3.42it/s]
 62%|██████▏   | 230155/371472 [7:40:54<12:09:56,  3.23it/s]
 62%|██████▏   | 230156/371472 [7:40:54<11:53:06,  3.30it/s]
 62%|██████▏   | 230157/371472 [7:40:55<12:06:06,  3.24it/s]
 62%|██████▏   | 230158/371472 [7:40:55<11:55:30,  3.29it/s]
 62%|██████▏   | 230159/371472 [7:40:55<11:44:01,  3.35it/s]
 62%|██████▏   | 230160/371472 [7:40:56<11:30:27,  3.41it/s]
                                                            
{'loss': 2.8359, 'learning_rate': 4.4255424594367474e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230160/371472 [7:40:56<11:30:27,  3.41it/s]
 62%|██████▏   | 230161/371472 [7:40:56<12:04:16,  3.25it/s]
 62%|██████▏   | 230162/371472 [7:40:56<11:52:49,  3.30it/s]
 62%|██████▏   | 230163/371472 [7:40:56<12:12:28,  3.22it/s]
 62%|██████▏   | 230164/371472 [7:40:57<11:49:34,  3.32it/s]
 62%|██████▏   | 230165/371472 [7:40:57<11:31:29,  3.41it/s]
 62%|██████▏   | 230166/371472 [7:40:57<11:20:19,  3.46it/s]
 62%|██████▏   | 230167/371472 [7:40:58<11:57:16,  3.28it/s]
 62%|██████▏   | 230168/371472 [7:40:58<12:51:17,  3.05it/s]
 62%|██████▏   | 230169/371472 [7:40:58<12:30:20,  3.14it/s]
 62%|██████▏   | 230170/371472 [7:40:59<12:05:14,  3.25it/s]
 62%|██████▏   | 230171/371472 [7:40:59<12:22:14,  3.17it/s]
 62%|██████▏   | 230172/371472 [7:40:59<11:46:01,  3.34it/s]
 62%|██████▏   | 230173/371472 [7:40:59<11:35:43,  3.38it/s]
 62%|██████▏   | 230174/371472 [7:41:00<11:48:38,  3.32it/s]
 62%|██████▏   | 230175/371472 [7:41:00<11:47:10,  3.33it/s]
 62%|██████▏   | 230176/371472 [7:41:00<11:37:07,  3.38it/s]
 62%|██████▏   | 230177/371472 [7:41:01<12:51:26,  3.05it/s]
 62%|██████▏   | 230178/371472 [7:41:01<12:02:48,  3.26it/s]
 62%|██████▏   | 230179/371472 [7:41:01<11:44:46,  3.34it/s]
 62%|██████▏   | 230180/371472 [7:41:02<11:28:53,  3.42it/s]
                                                            
{'loss': 2.8603, 'learning_rate': 4.425057639681958e-07, 'epoch': 9.91}
+
 62%|██████▏   | 230180/371472 [7:41:02<11:28:53,  3.42it/s]
 62%|██████▏   | 230181/371472 [7:41:02<11:21:27,  3.46it/s]
 62%|██████▏   | 230182/371472 [7:41:02<11:44:00,  3.34it/s]
 62%|██████▏   | 230183/371472 [7:41:02<11:37:47,  3.37it/s]
 62%|██████▏   | 230184/371472 [7:41:03<11:38:08,  3.37it/s]
 62%|██████▏   | 230185/371472 [7:41:03<11:37:40,  3.38it/s]
 62%|██████▏   | 230186/371472 [7:41:03<11:36:37,  3.38it/s]
 62%|██████▏   | 230187/371472 [7:41:04<11:29:20,  3.42it/s]
 62%|██████▏   | 230188/371472 [7:41:04<11:12:30,  3.50it/s]
 62%|██████▏   | 230189/371472 [7:41:04<11:24:45,  3.44it/s]
 62%|██████▏   | 230190/371472 [7:41:05<11:34:57,  3.39it/s]
 62%|██████▏   | 230191/371472 [7:41:05<11:35:04,  3.39it/s]
 62%|██████▏   | 230192/371472 [7:41:05<11:29:52,  3.41it/s]
 62%|██████▏   | 230193/371472 [7:41:05<11:29:46,  3.41it/s]
 62%|██████▏   | 230194/371472 [7:41:06<11:22:04,  3.45it/s]
 62%|██████▏   | 230195/371472 [7:41:06<11:31:37,  3.40it/s]
 62%|██████▏   | 230196/371472 [7:41:06<11:16:30,  3.48it/s]
 62%|██████▏   | 230197/371472 [7:41:07<12:08:35,  3.23it/s]
 62%|██████▏   | 230198/371472 [7:41:07<11:44:08,  3.34it/s]
 62%|██████▏   | 230199/371472 [7:41:07<11:28:57,  3.42it/s]
 62%|██████▏   | 230200/371472 [7:41:08<11:53:09,  3.30it/s]
                                                            
{'loss': 2.6994, 'learning_rate': 4.4245728199271694e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230200/371472 [7:41:08<11:53:09,  3.30it/s]
 62%|██████▏   | 230201/371472 [7:41:08<11:54:26,  3.30it/s]
 62%|██████▏   | 230202/371472 [7:41:08<11:49:15,  3.32it/s]
 62%|██████▏   | 230203/371472 [7:41:08<11:34:42,  3.39it/s]
 62%|██████▏   | 230204/371472 [7:41:09<12:06:07,  3.24it/s]
 62%|██████▏   | 230205/371472 [7:41:09<11:56:57,  3.28it/s]
 62%|██████▏   | 230206/371472 [7:41:09<11:31:16,  3.41it/s]
 62%|██████▏   | 230207/371472 [7:41:10<11:21:19,  3.46it/s]
 62%|██████▏   | 230208/371472 [7:41:10<11:24:58,  3.44it/s]
 62%|██████▏   | 230209/371472 [7:41:10<11:28:04,  3.42it/s]
 62%|██████▏   | 230210/371472 [7:41:10<11:21:51,  3.45it/s]
 62%|██████▏   | 230211/371472 [7:41:11<11:27:20,  3.43it/s]
 62%|██████▏   | 230212/371472 [7:41:11<11:19:38,  3.46it/s]
 62%|██████▏   | 230213/371472 [7:41:11<11:22:45,  3.45it/s]
 62%|██████▏   | 230214/371472 [7:41:12<11:25:52,  3.43it/s]
 62%|██████▏   | 230215/371472 [7:41:12<12:04:32,  3.25it/s]
 62%|██████▏   | 230216/371472 [7:41:12<12:41:01,  3.09it/s]
 62%|██████▏   | 230217/371472 [7:41:13<13:05:42,  3.00it/s]
 62%|██████▏   | 230218/371472 [7:41:13<13:39:40,  2.87it/s]
 62%|██████▏   | 230219/371472 [7:41:13<13:04:49,  3.00it/s]
 62%|██████▏   | 230220/371472 [7:41:14<12:48:36,  3.06it/s]
                                                            
{'loss': 2.71, 'learning_rate': 4.42408800017238e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230220/371472 [7:41:14<12:48:36,  3.06it/s]
 62%|██████▏   | 230221/371472 [7:41:14<12:39:41,  3.10it/s]
 62%|██████▏   | 230222/371472 [7:41:14<12:18:49,  3.19it/s]
 62%|██████▏   | 230223/371472 [7:41:15<12:07:39,  3.24it/s]
 62%|██████▏   | 230224/371472 [7:41:15<12:25:17,  3.16it/s]
 62%|██████▏   | 230225/371472 [7:41:15<12:08:23,  3.23it/s]
 62%|██████▏   | 230226/371472 [7:41:15<11:55:33,  3.29it/s]
 62%|██████▏   | 230227/371472 [7:41:16<12:16:10,  3.20it/s]
 62%|██████▏   | 230228/371472 [7:41:16<12:00:33,  3.27it/s]
 62%|██████▏   | 230229/371472 [7:41:16<11:57:39,  3.28it/s]
 62%|██████▏   | 230230/371472 [7:41:17<11:50:37,  3.31it/s]
 62%|██████▏   | 230231/371472 [7:41:17<11:51:31,  3.31it/s]
 62%|██████▏   | 230232/371472 [7:41:17<11:54:13,  3.30it/s]
 62%|██████▏   | 230233/371472 [7:41:18<11:57:45,  3.28it/s]
 62%|██████▏   | 230234/371472 [7:41:18<11:51:03,  3.31it/s]
 62%|██████▏   | 230235/371472 [7:41:18<12:11:10,  3.22it/s]
 62%|██████▏   | 230236/371472 [7:41:19<11:50:31,  3.31it/s]
 62%|██████▏   | 230237/371472 [7:41:19<11:48:40,  3.32it/s]
 62%|██████▏   | 230238/371472 [7:41:19<12:05:19,  3.25it/s]
 62%|██████▏   | 230239/371472 [7:41:19<12:05:19,  3.25it/s]
 62%|██████▏   | 230240/371472 [7:41:20<12:37:35,  3.11it/s]
                                                            
{'loss': 2.9023, 'learning_rate': 4.423603180417591e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230240/371472 [7:41:20<12:37:35,  3.11it/s]
 62%|██████▏   | 230241/371472 [7:41:20<12:02:11,  3.26it/s]
 62%|██████▏   | 230242/371472 [7:41:20<11:47:53,  3.33it/s]
 62%|██████▏   | 230243/371472 [7:41:21<11:41:20,  3.36it/s]
 62%|██████▏   | 230244/371472 [7:41:21<11:37:31,  3.37it/s]
 62%|██████▏   | 230245/371472 [7:41:21<11:34:38,  3.39it/s]
 62%|██████▏   | 230246/371472 [7:41:22<11:33:53,  3.39it/s]
 62%|██████▏   | 230247/371472 [7:41:22<11:26:52,  3.43it/s]
 62%|██████▏   | 230248/371472 [7:41:22<11:22:38,  3.45it/s]
 62%|██████▏   | 230249/371472 [7:41:22<12:05:51,  3.24it/s]
 62%|██████▏   | 230250/371472 [7:41:23<12:26:05,  3.15it/s]
 62%|██████▏   | 230251/371472 [7:41:23<13:16:14,  2.96it/s]
 62%|██████▏   | 230252/371472 [7:41:24<12:46:55,  3.07it/s]
 62%|██████▏   | 230253/371472 [7:41:24<12:02:55,  3.26it/s]
 62%|██████▏   | 230254/371472 [7:41:24<11:41:40,  3.35it/s]
 62%|██████▏   | 230255/371472 [7:41:24<11:36:53,  3.38it/s]
 62%|██████▏   | 230256/371472 [7:41:25<12:00:39,  3.27it/s]
 62%|██████▏   | 230257/371472 [7:41:25<11:50:42,  3.31it/s]
 62%|██████▏   | 230258/371472 [7:41:25<11:38:35,  3.37it/s]
 62%|██████▏   | 230259/371472 [7:41:26<11:31:19,  3.40it/s]
 62%|██████▏   | 230260/371472 [7:41:26<12:08:27,  3.23it/s]
                                                            
{'loss': 2.8213, 'learning_rate': 4.423118360662802e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230260/371472 [7:41:26<12:08:27,  3.23it/s]
 62%|██████▏   | 230261/371472 [7:41:26<11:41:45,  3.35it/s]
 62%|██████▏   | 230262/371472 [7:41:27<12:24:43,  3.16it/s]
 62%|██████▏   | 230263/371472 [7:41:27<12:07:32,  3.23it/s]
 62%|██████▏   | 230264/371472 [7:41:27<11:55:01,  3.29it/s]
 62%|██████▏   | 230265/371472 [7:41:27<11:58:17,  3.28it/s]
 62%|██████▏   | 230266/371472 [7:41:28<12:14:56,  3.20it/s]
 62%|██████▏   | 230267/371472 [7:41:28<11:46:40,  3.33it/s]
 62%|██████▏   | 230268/371472 [7:41:28<11:33:03,  3.40it/s]
 62%|██████▏   | 230269/371472 [7:41:29<12:04:30,  3.25it/s]
 62%|██████▏   | 230270/371472 [7:41:29<11:58:56,  3.27it/s]
 62%|██████▏   | 230271/371472 [7:41:29<11:37:43,  3.37it/s]
 62%|██████▏   | 230272/371472 [7:41:29<11:15:49,  3.48it/s]
 62%|██████▏   | 230273/371472 [7:41:30<11:18:52,  3.47it/s]
 62%|██████▏   | 230274/371472 [7:41:30<11:58:01,  3.28it/s]
 62%|██████▏   | 230275/371472 [7:41:30<11:37:01,  3.38it/s]
 62%|██████▏   | 230276/371472 [7:41:31<12:11:46,  3.22it/s]
 62%|██████▏   | 230277/371472 [7:41:31<11:55:12,  3.29it/s]
 62%|██████▏   | 230278/371472 [7:41:31<11:28:01,  3.42it/s]
 62%|██████▏   | 230279/371472 [7:41:32<14:08:09,  2.77it/s]
 62%|██████▏   | 230280/371472 [7:41:32<13:47:46,  2.84it/s]
                                                            
{'loss': 2.7915, 'learning_rate': 4.422633540908013e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230280/371472 [7:41:32<13:47:46,  2.84it/s]
 62%|██████▏   | 230281/371472 [7:41:32<13:22:59,  2.93it/s]
 62%|██████▏   | 230282/371472 [7:41:33<12:33:52,  3.12it/s]
 62%|██████▏   | 230283/371472 [7:41:33<12:13:07,  3.21it/s]
 62%|██████▏   | 230284/371472 [7:41:33<12:16:49,  3.19it/s]
 62%|██████▏   | 230285/371472 [7:41:34<11:55:54,  3.29it/s]
 62%|██████▏   | 230286/371472 [7:41:34<11:38:32,  3.37it/s]
 62%|██████▏   | 230287/371472 [7:41:34<11:53:51,  3.30it/s]
 62%|██████▏   | 230288/371472 [7:41:35<12:28:56,  3.14it/s]
 62%|██████▏   | 230289/371472 [7:41:35<12:28:09,  3.15it/s]
 62%|██████▏   | 230290/371472 [7:41:35<11:52:04,  3.30it/s]
 62%|██████▏   | 230291/371472 [7:41:35<11:30:46,  3.41it/s]
 62%|██████▏   | 230292/371472 [7:41:36<11:39:52,  3.36it/s]
 62%|██████▏   | 230293/371472 [7:41:36<11:23:38,  3.44it/s]
 62%|██████▏   | 230294/371472 [7:41:36<11:14:29,  3.49it/s]
 62%|██████▏   | 230295/371472 [7:41:37<11:17:29,  3.47it/s]
 62%|██████▏   | 230296/371472 [7:41:37<11:37:55,  3.37it/s]
 62%|██████▏   | 230297/371472 [7:41:37<11:40:12,  3.36it/s]
 62%|██████▏   | 230298/371472 [7:41:37<11:47:47,  3.32it/s]
 62%|██████▏   | 230299/371472 [7:41:38<11:56:06,  3.29it/s]
 62%|██████▏   | 230300/371472 [7:41:38<11:43:09,  3.35it/s]
                                                            
{'loss': 2.7525, 'learning_rate': 4.4221487211532246e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230300/371472 [7:41:38<11:43:09,  3.35it/s]
 62%|██████▏   | 230301/371472 [7:41:38<11:38:18,  3.37it/s]
 62%|██████▏   | 230302/371472 [7:41:39<11:23:55,  3.44it/s]
 62%|██████▏   | 230303/371472 [7:41:39<11:28:22,  3.42it/s]
 62%|██████▏   | 230304/371472 [7:41:39<11:27:39,  3.42it/s]
 62%|██████▏   | 230305/371472 [7:41:40<11:32:51,  3.40it/s]
 62%|██████▏   | 230306/371472 [7:41:40<11:44:31,  3.34it/s]
 62%|██████▏   | 230307/371472 [7:41:40<11:23:59,  3.44it/s]
 62%|██████▏   | 230308/371472 [7:41:40<12:04:22,  3.25it/s]
 62%|██████▏   | 230309/371472 [7:41:41<12:53:54,  3.04it/s]
 62%|██████▏   | 230310/371472 [7:41:41<12:33:33,  3.12it/s]
 62%|██████▏   | 230311/371472 [7:41:41<12:06:49,  3.24it/s]
 62%|██████▏   | 230312/371472 [7:41:42<12:40:00,  3.10it/s]
 62%|██████▏   | 230313/371472 [7:41:42<12:12:36,  3.21it/s]
 62%|██████▏   | 230314/371472 [7:41:42<11:54:24,  3.29it/s]
 62%|██████▏   | 230315/371472 [7:41:43<11:39:53,  3.36it/s]
 62%|██████▏   | 230316/371472 [7:41:43<12:05:32,  3.24it/s]
 62%|██████▏   | 230317/371472 [7:41:43<11:55:26,  3.29it/s]
 62%|██████▏   | 230318/371472 [7:41:44<11:39:31,  3.36it/s]
 62%|██████▏   | 230319/371472 [7:41:44<11:51:55,  3.30it/s]
 62%|██████▏   | 230320/371472 [7:41:44<11:34:16,  3.39it/s]
                                                            
{'loss': 2.7287, 'learning_rate': 4.4216639013984353e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230320/371472 [7:41:44<11:34:16,  3.39it/s]
 62%|██████▏   | 230321/371472 [7:41:44<11:54:27,  3.29it/s]
 62%|██████▏   | 230322/371472 [7:41:45<11:52:32,  3.30it/s]
 62%|██████▏   | 230323/371472 [7:41:45<11:36:37,  3.38it/s]
 62%|██████▏   | 230324/371472 [7:41:45<11:19:02,  3.46it/s]
 62%|██████▏   | 230325/371472 [7:41:46<11:08:58,  3.52it/s]
 62%|██████▏   | 230326/371472 [7:41:46<11:57:54,  3.28it/s]
 62%|██████▏   | 230327/371472 [7:41:46<11:42:05,  3.35it/s]
 62%|██████▏   | 230328/371472 [7:41:47<11:31:57,  3.40it/s]
 62%|██████▏   | 230329/371472 [7:41:47<11:58:38,  3.27it/s]
 62%|██████▏   | 230330/371472 [7:41:47<11:35:03,  3.38it/s]
 62%|██████▏   | 230331/371472 [7:41:47<11:53:13,  3.30it/s]
 62%|██████▏   | 230332/371472 [7:41:48<11:39:21,  3.36it/s]
 62%|██████▏   | 230333/371472 [7:41:48<11:30:22,  3.41it/s]
 62%|██████▏   | 230334/371472 [7:41:48<11:26:42,  3.43it/s]
 62%|██████▏   | 230335/371472 [7:41:49<11:32:03,  3.40it/s]
 62%|██████▏   | 230336/371472 [7:41:49<11:47:02,  3.33it/s]
 62%|██████▏   | 230337/371472 [7:41:49<12:05:53,  3.24it/s]
 62%|██████▏   | 230338/371472 [7:41:50<11:47:09,  3.33it/s]
 62%|██████▏   | 230339/371472 [7:41:50<12:09:17,  3.23it/s]
 62%|██████▏   | 230340/371472 [7:41:50<12:31:10,  3.13it/s]
                                                            
{'loss': 2.7031, 'learning_rate': 4.4211790816436465e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230340/371472 [7:41:50<12:31:10,  3.13it/s]
 62%|██████▏   | 230341/371472 [7:41:50<12:21:10,  3.17it/s]
 62%|██████▏   | 230342/371472 [7:41:51<12:04:51,  3.25it/s]
 62%|██████▏   | 230343/371472 [7:41:51<12:12:39,  3.21it/s]
 62%|██████▏   | 230344/371472 [7:41:51<11:45:40,  3.33it/s]
 62%|██████▏   | 230345/371472 [7:41:52<11:57:35,  3.28it/s]
 62%|██████▏   | 230346/371472 [7:41:52<12:50:55,  3.05it/s]
 62%|██████▏   | 230347/371472 [7:41:52<12:44:08,  3.08it/s]
 62%|██████▏   | 230348/371472 [7:41:53<12:24:15,  3.16it/s]
 62%|██████▏   | 230349/371472 [7:41:53<12:12:33,  3.21it/s]
 62%|██████▏   | 230350/371472 [7:41:53<12:13:23,  3.21it/s]
 62%|██████▏   | 230351/371472 [7:41:54<11:50:22,  3.31it/s]
 62%|██████▏   | 230352/371472 [7:41:54<11:39:35,  3.36it/s]
 62%|██████▏   | 230353/371472 [7:41:54<11:20:29,  3.46it/s]
 62%|██████▏   | 230354/371472 [7:41:54<11:24:13,  3.44it/s]
 62%|██████▏   | 230355/371472 [7:41:55<11:52:32,  3.30it/s]
 62%|██████▏   | 230356/371472 [7:41:55<11:39:51,  3.36it/s]
 62%|██████▏   | 230357/371472 [7:41:55<11:33:16,  3.39it/s]
 62%|██████▏   | 230358/371472 [7:41:56<11:15:54,  3.48it/s]
 62%|██████▏   | 230359/371472 [7:41:56<11:31:47,  3.40it/s]
 62%|██████▏   | 230360/371472 [7:41:56<12:12:15,  3.21it/s]
                                                            
{'loss': 2.6911, 'learning_rate': 4.420694261888857e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230360/371472 [7:41:56<12:12:15,  3.21it/s]
 62%|██████▏   | 230361/371472 [7:41:57<11:59:31,  3.27it/s]
 62%|██████▏   | 230362/371472 [7:41:57<11:46:37,  3.33it/s]
 62%|██████▏   | 230363/371472 [7:41:57<11:46:18,  3.33it/s]
 62%|██████▏   | 230364/371472 [7:41:57<11:27:53,  3.42it/s]
 62%|██████▏   | 230365/371472 [7:41:58<11:06:56,  3.53it/s]
 62%|██████▏   | 230366/371472 [7:41:58<10:52:02,  3.61it/s]
 62%|██████▏   | 230367/371472 [7:41:58<11:11:21,  3.50it/s]
 62%|██████▏   | 230368/371472 [7:41:59<11:09:04,  3.51it/s]
 62%|██████▏   | 230369/371472 [7:41:59<12:41:48,  3.09it/s]
 62%|██████▏   | 230370/371472 [7:41:59<12:00:56,  3.26it/s]
 62%|██████▏   | 230371/371472 [7:41:59<11:29:27,  3.41it/s]
 62%|██████▏   | 230372/371472 [7:42:00<11:31:50,  3.40it/s]
 62%|██████▏   | 230373/371472 [7:42:00<11:13:47,  3.49it/s]
 62%|██████▏   | 230374/371472 [7:42:00<10:57:32,  3.58it/s]
 62%|██████▏   | 230375/371472 [7:42:01<11:33:31,  3.39it/s]
 62%|██████▏   | 230376/371472 [7:42:01<11:15:04,  3.48it/s]
 62%|██████▏   | 230377/371472 [7:42:01<11:05:24,  3.53it/s]
 62%|██████▏   | 230378/371472 [7:42:01<11:00:12,  3.56it/s]
 62%|██████▏   | 230379/371472 [7:42:02<11:17:50,  3.47it/s]
 62%|██████▏   | 230380/371472 [7:42:02<11:06:13,  3.53it/s]
                                                            
{'loss': 2.6716, 'learning_rate': 4.420209442134069e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230380/371472 [7:42:02<11:06:13,  3.53it/s]
 62%|██████▏   | 230381/371472 [7:42:02<11:31:26,  3.40it/s]
 62%|██████▏   | 230382/371472 [7:42:03<11:23:10,  3.44it/s]
 62%|██████▏   | 230383/371472 [7:42:03<11:29:46,  3.41it/s]
 62%|██████▏   | 230384/371472 [7:42:03<11:21:23,  3.45it/s]
 62%|██████▏   | 230385/371472 [7:42:04<11:31:38,  3.40it/s]
 62%|██████▏   | 230386/371472 [7:42:04<11:28:34,  3.41it/s]
 62%|██████▏   | 230387/371472 [7:42:04<11:25:18,  3.43it/s]
 62%|██████▏   | 230388/371472 [7:42:04<11:33:04,  3.39it/s]
 62%|██████▏   | 230389/371472 [7:42:05<11:30:41,  3.40it/s]
 62%|██████▏   | 230390/371472 [7:42:05<12:30:32,  3.13it/s]
 62%|██████▏   | 230391/371472 [7:42:05<12:44:29,  3.08it/s]
 62%|██████▏   | 230392/371472 [7:42:06<12:07:18,  3.23it/s]
 62%|██████▏   | 230393/371472 [7:42:06<11:43:55,  3.34it/s]
 62%|██████▏   | 230394/371472 [7:42:06<11:29:17,  3.41it/s]
 62%|██████▏   | 230395/371472 [7:42:07<11:25:45,  3.43it/s]
 62%|██████▏   | 230396/371472 [7:42:07<11:32:28,  3.40it/s]
 62%|██████▏   | 230397/371472 [7:42:07<11:28:03,  3.42it/s]
 62%|██████▏   | 230398/371472 [7:42:07<11:20:59,  3.45it/s]
 62%|██████▏   | 230399/371472 [7:42:08<11:59:54,  3.27it/s]
 62%|██████▏   | 230400/371472 [7:42:08<11:41:55,  3.35it/s]
                                                            
{'loss': 2.8474, 'learning_rate': 4.4197246223792797e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230400/371472 [7:42:08<11:41:55,  3.35it/s]
 62%|██████▏   | 230401/371472 [7:42:08<11:32:46,  3.39it/s]
 62%|██████▏   | 230402/371472 [7:42:09<11:28:25,  3.42it/s]
 62%|██████▏   | 230403/371472 [7:42:09<11:17:41,  3.47it/s]
 62%|██████▏   | 230404/371472 [7:42:09<11:04:24,  3.54it/s]
 62%|██████▏   | 230405/371472 [7:42:09<10:54:14,  3.59it/s]
 62%|██████▏   | 230406/371472 [7:42:10<11:07:23,  3.52it/s]
 62%|██████▏   | 230407/371472 [7:42:10<10:58:48,  3.57it/s]
 62%|██████▏   | 230408/371472 [7:42:10<11:03:40,  3.54it/s]
 62%|██████▏   | 230409/371472 [7:42:11<11:23:54,  3.44it/s]
 62%|██████▏   | 230410/371472 [7:42:11<11:26:51,  3.42it/s]
 62%|██████▏   | 230411/371472 [7:42:11<11:58:30,  3.27it/s]
 62%|██████▏   | 230412/371472 [7:42:12<12:35:37,  3.11it/s]
 62%|██████▏   | 230413/371472 [7:42:12<12:16:13,  3.19it/s]
 62%|██████▏   | 230414/371472 [7:42:12<11:47:10,  3.32it/s]
 62%|██████▏   | 230415/371472 [7:42:12<11:48:13,  3.32it/s]
 62%|██████▏   | 230416/371472 [7:42:13<11:37:20,  3.37it/s]
 62%|██████▏   | 230417/371472 [7:42:13<11:38:50,  3.36it/s]
 62%|██████▏   | 230418/371472 [7:42:13<11:20:44,  3.45it/s]
 62%|██████▏   | 230419/371472 [7:42:14<11:03:31,  3.54it/s]
 62%|██████▏   | 230420/371472 [7:42:14<11:43:26,  3.34it/s]
                                                            
{'loss': 2.5551, 'learning_rate': 4.419239802624491e-07, 'epoch': 9.92}
+
 62%|██████▏   | 230420/371472 [7:42:14<11:43:26,  3.34it/s]
 62%|██████▏   | 230421/371472 [7:42:14<11:29:39,  3.41it/s]
 62%|██████▏   | 230422/371472 [7:42:14<11:33:02,  3.39it/s]
 62%|██████▏   | 230423/371472 [7:42:15<12:17:30,  3.19it/s]
 62%|██████▏   | 230424/371472 [7:42:15<11:55:08,  3.29it/s]
 62%|██████▏   | 230425/371472 [7:42:15<12:11:36,  3.21it/s]
 62%|██████▏   | 230426/371472 [7:42:16<12:03:04,  3.25it/s]
 62%|██████▏   | 230427/371472 [7:42:16<11:43:28,  3.34it/s]
 62%|██████▏   | 230428/371472 [7:42:16<11:35:44,  3.38it/s]
 62%|██████▏   | 230429/371472 [7:42:17<11:16:52,  3.47it/s]
 62%|██████▏   | 230430/371472 [7:42:17<11:23:21,  3.44it/s]
 62%|██████▏   | 230431/371472 [7:42:17<12:06:38,  3.23it/s]
 62%|██████▏   | 230432/371472 [7:42:18<12:23:22,  3.16it/s]
 62%|██████▏   | 230433/371472 [7:42:18<12:11:27,  3.21it/s]
 62%|██████▏   | 230434/371472 [7:42:18<12:39:54,  3.09it/s]
 62%|██████▏   | 230435/371472 [7:42:18<12:06:47,  3.23it/s]
 62%|██████▏   | 230436/371472 [7:42:19<12:12:06,  3.21it/s]
 62%|██████▏   | 230437/371472 [7:42:19<12:13:35,  3.20it/s]
 62%|██████▏   | 230438/371472 [7:42:19<12:18:57,  3.18it/s]
 62%|██████▏   | 230439/371472 [7:42:20<12:31:47,  3.13it/s]
 62%|██████▏   | 230440/371472 [7:42:20<11:54:55,  3.29it/s]
                                                            
{'loss': 2.7081, 'learning_rate': 4.4187549828697017e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230440/371472 [7:42:20<11:54:55,  3.29it/s]
 62%|██████▏   | 230441/371472 [7:42:20<12:29:29,  3.14it/s]
 62%|██████▏   | 230442/371472 [7:42:21<12:20:01,  3.18it/s]
 62%|██████▏   | 230443/371472 [7:42:21<12:51:43,  3.05it/s]
 62%|██████▏   | 230444/371472 [7:42:21<12:24:44,  3.16it/s]
 62%|██████▏   | 230445/371472 [7:42:22<12:16:25,  3.19it/s]
 62%|██████▏   | 230446/371472 [7:42:22<12:01:35,  3.26it/s]
 62%|██████▏   | 230447/371472 [7:42:22<12:01:01,  3.26it/s]
 62%|██████▏   | 230448/371472 [7:42:23<12:13:45,  3.20it/s]
 62%|██████▏   | 230449/371472 [7:42:23<11:59:48,  3.27it/s]
 62%|██████▏   | 230450/371472 [7:42:23<11:40:51,  3.35it/s]
 62%|██████▏   | 230451/371472 [7:42:23<11:39:40,  3.36it/s]
 62%|██████▏   | 230452/371472 [7:42:24<11:37:28,  3.37it/s]
 62%|██████▏   | 230453/371472 [7:42:24<11:29:00,  3.41it/s]
 62%|██████▏   | 230454/371472 [7:42:24<12:12:17,  3.21it/s]
 62%|██████▏   | 230455/371472 [7:42:25<11:58:06,  3.27it/s]
 62%|██████▏   | 230456/371472 [7:42:25<11:48:34,  3.32it/s]
 62%|██████▏   | 230457/371472 [7:42:25<12:19:26,  3.18it/s]
 62%|██████▏   | 230458/371472 [7:42:26<12:03:33,  3.25it/s]
 62%|██████▏   | 230459/371472 [7:42:26<12:21:29,  3.17it/s]
 62%|██████▏   | 230460/371472 [7:42:26<11:53:10,  3.30it/s]
                                                            
{'loss': 2.7313, 'learning_rate': 4.418270163114913e-07, 'epoch': 9.93}
+
 62%|██���███▏   | 230460/371472 [7:42:26<11:53:10,  3.30it/s]
 62%|██████▏   | 230461/371472 [7:42:26<11:30:23,  3.40it/s]
 62%|██████▏   | 230462/371472 [7:42:27<12:30:05,  3.13it/s]
 62%|██████▏   | 230463/371472 [7:42:27<12:28:42,  3.14it/s]
 62%|██████▏   | 230464/371472 [7:42:27<12:05:08,  3.24it/s]
 62%|██████▏   | 230465/371472 [7:42:28<12:25:14,  3.15it/s]
 62%|██████▏   | 230466/371472 [7:42:28<13:20:04,  2.94it/s]
 62%|██████▏   | 230467/371472 [7:42:28<12:21:40,  3.17it/s]
 62%|██████▏   | 230468/371472 [7:42:29<11:45:08,  3.33it/s]
 62%|██████▏   | 230469/371472 [7:42:29<11:26:21,  3.42it/s]
 62%|██████▏   | 230470/371472 [7:42:29<11:26:31,  3.42it/s]
 62%|██████▏   | 230471/371472 [7:42:30<11:23:57,  3.44it/s]
 62%|██████▏   | 230472/371472 [7:42:30<11:22:27,  3.44it/s]
 62%|██████▏   | 230473/371472 [7:42:30<11:17:37,  3.47it/s]
 62%|██████▏   | 230474/371472 [7:42:30<11:51:44,  3.30it/s]
 62%|██████▏   | 230475/371472 [7:42:31<11:38:21,  3.36it/s]
 62%|██████▏   | 230476/371472 [7:42:31<11:24:09,  3.43it/s]
 62%|██████▏   | 230477/371472 [7:42:31<11:10:46,  3.50it/s]
 62%|██████▏   | 230478/371472 [7:42:32<11:11:35,  3.50it/s]
 62%|██████▏   | 230479/371472 [7:42:32<11:38:37,  3.36it/s]
 62%|██████▏   | 230480/371472 [7:42:32<11:31:56,  3.40it/s]
                                                            
{'loss': 2.8119, 'learning_rate': 4.4177853433601236e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230480/371472 [7:42:32<11:31:56,  3.40it/s]
 62%|██████▏   | 230481/371472 [7:42:33<12:21:38,  3.17it/s]
 62%|██████▏   | 230482/371472 [7:42:33<13:00:33,  3.01it/s]
 62%|██████▏   | 230483/371472 [7:42:33<12:34:16,  3.12it/s]
 62%|██████▏   | 230484/371472 [7:42:34<12:17:54,  3.18it/s]
 62%|██████▏   | 230485/371472 [7:42:34<12:38:12,  3.10it/s]
 62%|██████▏   | 230486/371472 [7:42:34<12:12:50,  3.21it/s]
 62%|██████▏   | 230487/371472 [7:42:34<12:07:47,  3.23it/s]
 62%|██████▏   | 230488/371472 [7:42:35<12:02:58,  3.25it/s]
 62%|██████▏   | 230489/371472 [7:42:35<11:50:08,  3.31it/s]
 62%|██████▏   | 230490/371472 [7:42:35<11:32:22,  3.39it/s]
 62%|██████▏   | 230491/371472 [7:42:36<11:27:07,  3.42it/s]
 62%|██████▏   | 230492/371472 [7:42:36<11:35:01,  3.38it/s]
 62%|██████▏   | 230493/371472 [7:42:36<11:35:43,  3.38it/s]
 62%|██████▏   | 230494/371472 [7:42:37<11:28:27,  3.41it/s]
 62%|██████▏   | 230495/371472 [7:42:37<11:27:21,  3.42it/s]
 62%|██████▏   | 230496/371472 [7:42:37<11:28:58,  3.41it/s]
 62%|██████▏   | 230497/371472 [7:42:37<11:37:22,  3.37it/s]
 62%|██████▏   | 230498/371472 [7:42:38<11:30:08,  3.40it/s]
 62%|██████▏   | 230499/371472 [7:42:38<11:48:31,  3.32it/s]
 62%|██████▏   | 230500/371472 [7:42:38<11:31:09,  3.40it/s]
                                                            
{'loss': 2.7096, 'learning_rate': 4.4173005236053354e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230500/371472 [7:42:38<11:31:09,  3.40it/s]
 62%|██████▏   | 230501/371472 [7:42:39<11:56:48,  3.28it/s]
 62%|██████▏   | 230502/371472 [7:42:39<12:12:35,  3.21it/s]
 62%|██████▏   | 230503/371472 [7:42:39<12:23:28,  3.16it/s]
 62%|██████▏   | 230504/371472 [7:42:40<11:51:19,  3.30it/s]
 62%|██████▏   | 230505/371472 [7:42:40<12:00:56,  3.26it/s]
 62%|██████▏   | 230506/371472 [7:42:40<12:08:39,  3.22it/s]
 62%|██████▏   | 230507/371472 [7:42:40<11:46:19,  3.33it/s]
 62%|██████▏   | 230508/371472 [7:42:41<11:51:25,  3.30it/s]
 62%|██████▏   | 230509/371472 [7:42:41<11:51:16,  3.30it/s]
 62%|██████▏   | 230510/371472 [7:42:41<11:44:39,  3.33it/s]
 62%|██████▏   | 230511/371472 [7:42:42<11:38:26,  3.36it/s]
 62%|██████▏   | 230512/371472 [7:42:42<11:52:18,  3.30it/s]
 62%|██████▏   | 230513/371472 [7:42:42<12:03:18,  3.25it/s]
 62%|██████▏   | 230514/371472 [7:42:43<12:28:10,  3.14it/s]
 62%|██████▏   | 230515/371472 [7:42:43<12:35:55,  3.11it/s]
 62%|██████▏   | 230516/371472 [7:42:43<12:06:04,  3.24it/s]
 62%|██████▏   | 230517/371472 [7:42:44<12:34:48,  3.11it/s]
 62%|██████▏   | 230518/371472 [7:42:44<12:23:30,  3.16it/s]
 62%|██████▏   | 230519/371472 [7:42:44<12:14:29,  3.20it/s]
 62%|██████▏   | 230520/371472 [7:42:45<12:14:06,  3.20it/s]
                                                            
{'loss': 2.6679, 'learning_rate': 4.4168157038505456e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230520/371472 [7:42:45<12:14:06,  3.20it/s]
 62%|██████▏   | 230521/371472 [7:42:45<11:46:58,  3.32it/s]
 62%|██████▏   | 230522/371472 [7:42:45<12:03:02,  3.25it/s]
 62%|██████▏   | 230523/371472 [7:42:45<12:31:40,  3.13it/s]
 62%|██████▏   | 230524/371472 [7:42:46<12:17:57,  3.18it/s]
 62%|██████▏   | 230525/371472 [7:42:46<12:19:39,  3.18it/s]
 62%|██████▏   | 230526/371472 [7:42:46<12:07:48,  3.23it/s]
 62%|██████▏   | 230527/371472 [7:42:47<12:22:46,  3.16it/s]
 62%|██████▏   | 230528/371472 [7:42:47<12:17:37,  3.18it/s]
 62%|██████▏   | 230529/371472 [7:42:47<12:04:08,  3.24it/s]
 62%|██████▏   | 230530/371472 [7:42:48<12:10:34,  3.22it/s]
 62%|██████▏   | 230531/371472 [7:42:48<11:52:02,  3.30it/s]
 62%|██████▏   | 230532/371472 [7:42:48<11:40:21,  3.35it/s]
 62%|██████▏   | 230533/371472 [7:42:48<11:21:53,  3.44it/s]
 62%|██████▏   | 230534/371472 [7:42:49<11:49:03,  3.31it/s]
 62%|██████▏   | 230535/371472 [7:42:49<11:41:10,  3.35it/s]
 62%|██████▏   | 230536/371472 [7:42:49<11:39:02,  3.36it/s]
 62%|██████▏   | 230537/371472 [7:42:50<12:45:31,  3.07it/s]
 62%|██████▏   | 230538/371472 [7:42:50<12:42:44,  3.08it/s]
 62%|██████▏   | 230539/371472 [7:42:50<12:19:35,  3.18it/s]
 62%|██████▏   | 230540/371472 [7:42:51<11:48:11,  3.32it/s]
                                                            
{'loss': 2.758, 'learning_rate': 4.4163308840957574e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230540/371472 [7:42:51<11:48:11,  3.32it/s]
 62%|██████▏   | 230541/371472 [7:42:51<11:22:24,  3.44it/s]
 62%|██████▏   | 230542/371472 [7:42:51<11:16:13,  3.47it/s]
 62%|██████▏   | 230543/371472 [7:42:51<11:20:51,  3.45it/s]
 62%|██████▏   | 230544/371472 [7:42:52<11:19:47,  3.46it/s]
 62%|██████▏   | 230545/371472 [7:42:52<11:31:09,  3.40it/s]
 62%|██████▏   | 230546/371472 [7:42:52<11:37:04,  3.37it/s]
 62%|██████▏   | 230547/371472 [7:42:53<12:48:50,  3.05it/s]
 62%|██████▏   | 230548/371472 [7:42:53<12:48:58,  3.05it/s]
 62%|██████▏   | 230549/371472 [7:42:54<13:48:28,  2.83it/s]
 62%|██████▏   | 230550/371472 [7:42:54<12:53:46,  3.04it/s]
 62%|██████▏   | 230551/371472 [7:42:54<12:32:20,  3.12it/s]
 62%|██████▏   | 230552/371472 [7:42:54<12:04:25,  3.24it/s]
 62%|██████▏   | 230553/371472 [7:42:55<12:30:32,  3.13it/s]
 62%|██████▏   | 230554/371472 [7:42:55<12:08:33,  3.22it/s]
 62%|██████▏   | 230555/371472 [7:42:55<11:50:26,  3.31it/s]
 62%|██████▏   | 230556/371472 [7:42:56<11:59:02,  3.27it/s]
 62%|██████▏   | 230557/371472 [7:42:56<12:09:43,  3.22it/s]
 62%|██████▏   | 230558/371472 [7:42:56<11:43:20,  3.34it/s]
 62%|██████▏   | 230559/371472 [7:42:57<11:35:39,  3.38it/s]
 62%|██████▏   | 230560/371472 [7:42:57<11:48:12,  3.32it/s]
                                                            
{'loss': 2.6794, 'learning_rate': 4.415846064340968e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230560/371472 [7:42:57<11:48:12,  3.32it/s]
 62%|██████▏   | 230561/371472 [7:42:57<11:49:11,  3.31it/s]
 62%|██████▏   | 230562/371472 [7:42:57<12:04:47,  3.24it/s]
 62%|██████▏   | 230563/371472 [7:42:58<11:43:00,  3.34it/s]
 62%|██████▏   | 230564/371472 [7:42:58<11:48:14,  3.32it/s]
 62%|██████▏   | 230565/371472 [7:42:58<11:56:09,  3.28it/s]
 62%|██████▏   | 230566/371472 [7:42:59<12:05:32,  3.24it/s]
 62%|██████▏   | 230567/371472 [7:42:59<11:41:09,  3.35it/s]
 62%|██████▏   | 230568/371472 [7:42:59<11:30:38,  3.40it/s]
 62%|██████▏   | 230569/371472 [7:42:59<11:03:22,  3.54it/s]
 62%|██████▏   | 230570/371472 [7:43:00<11:22:27,  3.44it/s]
 62%|██████▏   | 230571/371472 [7:43:00<11:48:13,  3.32it/s]
 62%|██████▏   | 230572/371472 [7:43:00<12:24:36,  3.15it/s]
 62%|██████▏   | 230573/371472 [7:43:01<12:13:15,  3.20it/s]
 62%|██████▏   | 230574/371472 [7:43:01<11:56:51,  3.28it/s]
 62%|██████▏   | 230575/371472 [7:43:01<11:41:46,  3.35it/s]
 62%|██████▏   | 230576/371472 [7:43:02<11:44:58,  3.33it/s]
 62%|██████▏   | 230577/371472 [7:43:02<12:18:57,  3.18it/s]
 62%|██████▏   | 230578/371472 [7:43:02<12:13:49,  3.20it/s]
 62%|██████▏   | 230579/371472 [7:43:03<11:56:16,  3.28it/s]
 62%|██████▏   | 230580/371472 [7:43:03<11:57:00,  3.27it/s]
                                                            
{'loss': 2.6742, 'learning_rate': 4.4153612445861793e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230580/371472 [7:43:03<11:57:00,  3.27it/s]
 62%|██████▏   | 230581/371472 [7:43:03<11:57:24,  3.27it/s]
 62%|██████▏   | 230582/371472 [7:43:04<12:00:33,  3.26it/s]
 62%|██████▏   | 230583/371472 [7:43:04<12:03:13,  3.25it/s]
 62%|██████▏   | 230584/371472 [7:43:04<11:40:56,  3.35it/s]
 62%|██████▏   | 230585/371472 [7:43:04<11:27:08,  3.42it/s]
 62%|██████▏   | 230586/371472 [7:43:05<11:30:56,  3.40it/s]
 62%|██████▏   | 230587/371472 [7:43:05<11:35:30,  3.38it/s]
 62%|██████▏   | 230588/371472 [7:43:05<11:38:53,  3.36it/s]
 62%|██████▏   | 230589/371472 [7:43:06<11:46:40,  3.32it/s]
 62%|██████▏   | 230590/371472 [7:43:06<11:46:26,  3.32it/s]
 62%|██████▏   | 230591/371472 [7:43:06<11:34:06,  3.38it/s]
 62%|██████▏   | 230592/371472 [7:43:06<11:18:28,  3.46it/s]
 62%|██████▏   | 230593/371472 [7:43:07<11:11:31,  3.50it/s]
 62%|██████▏   | 230594/371472 [7:43:07<11:23:51,  3.43it/s]
 62%|██████▏   | 230595/371472 [7:43:07<12:08:10,  3.22it/s]
 62%|██████▏   | 230596/371472 [7:43:08<11:48:13,  3.32it/s]
 62%|██████▏   | 230597/371472 [7:43:08<12:33:20,  3.12it/s]
 62%|██████▏   | 230598/371472 [7:43:08<12:24:35,  3.15it/s]
 62%|██████▏   | 230599/371472 [7:43:09<11:55:44,  3.28it/s]
 62%|██████▏   | 230600/371472 [7:43:09<11:47:02,  3.32it/s]
                                                            
{'loss': 2.6609, 'learning_rate': 4.41487642483139e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230600/371472 [7:43:09<11:47:02,  3.32it/s]
 62%|██████▏   | 230601/371472 [7:43:09<11:41:40,  3.35it/s]
 62%|██████▏   | 230602/371472 [7:43:10<11:46:58,  3.32it/s]
 62%|██████▏   | 230603/371472 [7:43:10<11:41:57,  3.34it/s]
 62%|██████▏   | 230604/371472 [7:43:10<11:32:09,  3.39it/s]
 62%|██████▏   | 230605/371472 [7:43:10<11:16:43,  3.47it/s]
 62%|██████▏   | 230606/371472 [7:43:11<11:15:45,  3.47it/s]
 62%|██████▏   | 230607/371472 [7:43:11<11:12:59,  3.49it/s]
 62%|██████▏   | 230608/371472 [7:43:11<11:06:51,  3.52it/s]
 62%|██████▏   | 230609/371472 [7:43:12<11:47:17,  3.32it/s]
 62%|██████▏   | 230610/371472 [7:43:12<11:35:31,  3.38it/s]
 62%|██████▏   | 230611/371472 [7:43:12<11:24:36,  3.43it/s]
 62%|██████▏   | 230612/371472 [7:43:12<11:52:21,  3.30it/s]
 62%|██████▏   | 230613/371472 [7:43:13<12:17:25,  3.18it/s]
 62%|██████▏   | 230614/371472 [7:43:13<12:03:15,  3.25it/s]
 62%|██████▏   | 230615/371472 [7:43:13<11:37:02,  3.37it/s]
 62%|██████▏   | 230616/371472 [7:43:14<12:08:46,  3.22it/s]
 62%|██████▏   | 230617/371472 [7:43:14<12:19:39,  3.17it/s]
 62%|██████▏   | 230618/371472 [7:43:14<11:53:14,  3.29it/s]
 62%|██████▏   | 230619/371472 [7:43:15<12:01:14,  3.25it/s]
 62%|██████▏   | 230620/371472 [7:43:15<12:30:34,  3.13it/s]
                                                            
{'loss': 2.8234, 'learning_rate': 4.414391605076602e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230620/371472 [7:43:15<12:30:34,  3.13it/s]
 62%|██████▏   | 230621/371472 [7:43:15<12:04:50,  3.24it/s]
 62%|██████▏   | 230622/371472 [7:43:16<11:45:59,  3.33it/s]
 62%|██████▏   | 230623/371472 [7:43:16<11:54:41,  3.28it/s]
 62%|██████▏   | 230624/371472 [7:43:16<11:53:21,  3.29it/s]
 62%|██████▏   | 230625/371472 [7:43:16<11:26:15,  3.42it/s]
 62%|██████▏   | 230626/371472 [7:43:17<11:29:44,  3.40it/s]
 62%|██████▏   | 230627/371472 [7:43:17<11:29:39,  3.40it/s]
 62%|██████▏   | 230628/371472 [7:43:17<11:36:46,  3.37it/s]
 62%|██████▏   | 230629/371472 [7:43:18<11:52:03,  3.30it/s]
 62%|██████▏   | 230630/371472 [7:43:18<12:07:58,  3.22it/s]
 62%|██████▏   | 230631/371472 [7:43:18<11:59:36,  3.26it/s]
 62%|██████▏   | 230632/371472 [7:43:19<11:34:50,  3.38it/s]
 62%|██████▏   | 230633/371472 [7:43:19<11:23:46,  3.43it/s]
 62%|██████▏   | 230634/371472 [7:43:19<11:56:30,  3.28it/s]
 62%|██████▏   | 230635/371472 [7:43:19<11:35:23,  3.38it/s]
 62%|██████▏   | 230636/371472 [7:43:20<11:31:04,  3.40it/s]
 62%|██████▏   | 230637/371472 [7:43:20<11:15:24,  3.48it/s]
 62%|██████▏   | 230638/371472 [7:43:20<11:36:11,  3.37it/s]
 62%|██████▏   | 230639/371472 [7:43:21<11:16:45,  3.47it/s]
 62%|██████▏   | 230640/371472 [7:43:21<11:03:13,  3.54it/s]
                                                            
{'loss': 2.7093, 'learning_rate': 4.413906785321812e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230640/371472 [7:43:21<11:03:13,  3.54it/s]
 62%|██████▏   | 230641/371472 [7:43:21<11:00:03,  3.56it/s]
 62%|██████▏   | 230642/371472 [7:43:21<11:54:35,  3.28it/s]
 62%|██████▏   | 230643/371472 [7:43:22<11:29:15,  3.41it/s]
 62%|██████▏   | 230644/371472 [7:43:22<11:23:11,  3.44it/s]
 62%|██████▏   | 230645/371472 [7:43:22<11:14:20,  3.48it/s]
 62%|██████▏   | 230646/371472 [7:43:23<11:16:19,  3.47it/s]
 62%|██████▏   | 230647/371472 [7:43:23<11:16:18,  3.47it/s]
 62%|██████▏   | 230648/371472 [7:43:23<11:13:10,  3.49it/s]
 62%|██████▏   | 230649/371472 [7:43:24<12:41:17,  3.08it/s]
 62%|██████▏   | 230650/371472 [7:43:24<12:01:17,  3.25it/s]
 62%|██████▏   | 230651/371472 [7:43:24<13:01:46,  3.00it/s]
 62%|██████▏   | 230652/371472 [7:43:25<12:44:50,  3.07it/s]
 62%|██████▏   | 230653/371472 [7:43:25<12:20:40,  3.17it/s]
 62%|██████▏   | 230654/371472 [7:43:25<12:07:24,  3.23it/s]
 62%|██████▏   | 230655/371472 [7:43:25<11:38:36,  3.36it/s]
 62%|██████▏   | 230656/371472 [7:43:26<12:35:15,  3.11it/s]
 62%|██████▏   | 230657/371472 [7:43:26<12:08:05,  3.22it/s]
 62%|██████▏   | 230658/371472 [7:43:26<11:53:02,  3.29it/s]
 62%|██████▏   | 230659/371472 [7:43:27<11:56:50,  3.27it/s]
 62%|██████▏   | 230660/371472 [7:43:27<12:11:57,  3.21it/s]
                                                            
{'loss': 2.6735, 'learning_rate': 4.413421965567023e-07, 'epoch': 9.93}
+
 62%|██████▏   | 230660/371472 [7:43:27<12:11:57,  3.21it/s]
 62%|██████▏   | 230661/371472 [7:43:27<12:16:52,  3.18it/s]
 62%|██████▏   | 230662/371472 [7:43:28<12:53:21,  3.03it/s]
 62%|██████▏   | 230663/371472 [7:43:28<12:41:16,  3.08it/s]
 62%|██████▏   | 230664/371472 [7:43:28<12:14:45,  3.19it/s]
 62%|██████▏   | 230665/371472 [7:43:29<12:06:29,  3.23it/s]
 62%|██████▏   | 230666/371472 [7:43:29<11:52:04,  3.30it/s]
 62%|██████▏   | 230667/371472 [7:43:29<11:45:32,  3.33it/s]
 62%|██████▏   | 230668/371472 [7:43:29<11:31:56,  3.39it/s]
 62%|██████▏   | 230669/371472 [7:43:30<11:28:47,  3.41it/s]
 62%|██████▏   | 230670/371472 [7:43:30<11:32:52,  3.39it/s]
 62%|██████▏   | 230671/371472 [7:43:30<11:30:50,  3.40it/s]
 62%|██████▏   | 230672/371472 [7:43:31<11:29:47,  3.40it/s]
 62%|██████▏   | 230673/371472 [7:43:31<11:21:54,  3.44it/s]
 62%|██████▏   | 230674/371472 [7:43:31<11:02:23,  3.54it/s]
 62%|██████▏   | 230675/371472 [7:43:31<10:58:08,  3.57it/s]
 62%|██████▏   | 230676/371472 [7:43:32<11:09:08,  3.51it/s]
 62%|██████▏   | 230677/371472 [7:43:32<11:30:09,  3.40it/s]
 62%|██████▏   | 230678/371472 [7:43:32<11:46:54,  3.32it/s]
 62%|██████▏   | 230679/371472 [7:43:33<11:33:53,  3.38it/s]
 62%|██████▏   | 230680/371472 [7:43:33<11:33:10,  3.39it/s]
                                                            
{'loss': 2.7809, 'learning_rate': 4.4129371458122345e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230680/371472 [7:43:33<11:33:10,  3.39it/s]
 62%|██████▏   | 230681/371472 [7:43:33<11:29:06,  3.41it/s]
 62%|██████▏   | 230682/371472 [7:43:34<12:07:16,  3.23it/s]
 62%|██████▏   | 230683/371472 [7:43:34<12:15:51,  3.19it/s]
 62%|██████▏   | 230684/371472 [7:43:34<12:47:46,  3.06it/s]
 62%|██████▏   | 230685/371472 [7:43:35<12:20:40,  3.17it/s]
 62%|██████▏   | 230686/371472 [7:43:35<11:53:49,  3.29it/s]
 62%|██████▏   | 230687/371472 [7:43:35<11:47:45,  3.32it/s]
 62%|██████▏   | 230688/371472 [7:43:35<11:39:19,  3.36it/s]
 62%|██████▏   | 230689/371472 [7:43:36<11:49:29,  3.31it/s]
 62%|██████▏   | 230690/371472 [7:43:36<11:34:28,  3.38it/s]
 62%|██████▏   | 230691/371472 [7:43:36<11:18:38,  3.46it/s]
 62%|██████▏   | 230692/371472 [7:43:37<11:58:02,  3.27it/s]
 62%|██████▏   | 230693/371472 [7:43:37<12:12:03,  3.21it/s]
 62%|██████▏   | 230694/371472 [7:43:37<11:35:08,  3.38it/s]
 62%|██████▏   | 230695/371472 [7:43:38<12:01:01,  3.25it/s]
 62%|██████▏   | 230696/371472 [7:43:38<12:10:45,  3.21it/s]
 62%|██████▏   | 230697/371472 [7:43:38<12:08:10,  3.22it/s]
 62%|██████▏   | 230698/371472 [7:43:38<11:50:47,  3.30it/s]
 62%|██████▏   | 230699/371472 [7:43:39<11:53:37,  3.29it/s]
 62%|██████▏   | 230700/371472 [7:43:39<11:50:03,  3.30it/s]
                                                            
{'loss': 2.7143, 'learning_rate': 4.412452326057446e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230700/371472 [7:43:39<11:50:03,  3.30it/s]
 62%|██████▏   | 230701/371472 [7:43:39<12:45:38,  3.06it/s]
 62%|██████▏   | 230702/371472 [7:43:40<13:34:43,  2.88it/s]
 62%|██████▏   | 230703/371472 [7:43:40<13:41:16,  2.86it/s]
 62%|██████▏   | 230704/371472 [7:43:40<13:12:13,  2.96it/s]
 62%|██████▏   | 230705/371472 [7:43:41<12:41:16,  3.08it/s]
 62%|██████▏   | 230706/371472 [7:43:41<12:37:34,  3.10it/s]
 62%|██████▏   | 230707/371472 [7:43:41<12:12:37,  3.20it/s]
 62%|██████▏   | 230708/371472 [7:43:42<12:16:05,  3.19it/s]
 62%|██████▏   | 230709/371472 [7:43:42<11:40:16,  3.35it/s]
 62%|██████▏   | 230710/371472 [7:43:42<11:52:39,  3.29it/s]
 62%|██████▏   | 230711/371472 [7:43:43<11:35:08,  3.37it/s]
 62%|██████▏   | 230712/371472 [7:43:43<11:23:57,  3.43it/s]
 62%|██████▏   | 230713/371472 [7:43:43<11:15:48,  3.47it/s]
 62%|██████▏   | 230714/371472 [7:43:43<11:06:42,  3.52it/s]
 62%|██████▏   | 230715/371472 [7:43:44<10:57:24,  3.57it/s]
 62%|██████▏   | 230716/371472 [7:43:44<10:53:01,  3.59it/s]
 62%|██████▏   | 230717/371472 [7:43:44<10:48:27,  3.62it/s]
 62%|██████▏   | 230718/371472 [7:43:45<11:04:27,  3.53it/s]
 62%|██████▏   | 230719/371472 [7:43:45<10:49:35,  3.61it/s]
 62%|██████▏   | 230720/371472 [7:43:45<10:53:27,  3.59it/s]
                                                            
{'loss': 2.7614, 'learning_rate': 4.4119675063026565e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230720/371472 [7:43:45<10:53:27,  3.59it/s]
 62%|██████▏   | 230721/371472 [7:43:45<11:05:19,  3.53it/s]
 62%|██████▏   | 230722/371472 [7:43:46<11:25:14,  3.42it/s]
 62%|██████▏   | 230723/371472 [7:43:46<11:29:07,  3.40it/s]
 62%|██████▏   | 230724/371472 [7:43:46<11:24:41,  3.43it/s]
 62%|██████▏   | 230725/371472 [7:43:47<11:20:44,  3.45it/s]
 62%|██████▏   | 230726/371472 [7:43:47<11:22:36,  3.44it/s]
 62%|██████▏   | 230727/371472 [7:43:47<11:09:22,  3.50it/s]
 62%|██████▏   | 230728/371472 [7:43:47<11:25:37,  3.42it/s]
 62%|██████▏   | 230729/371472 [7:43:48<11:14:13,  3.48it/s]
 62%|██████▏   | 230730/371472 [7:43:48<11:07:11,  3.52it/s]
 62%|██████▏   | 230731/371472 [7:43:48<11:23:38,  3.43it/s]
 62%|██████▏   | 230732/371472 [7:43:49<11:39:51,  3.35it/s]
 62%|██████▏   | 230733/371472 [7:43:49<11:36:12,  3.37it/s]
 62%|██████▏   | 230734/371472 [7:43:49<11:46:24,  3.32it/s]
 62%|██████▏   | 230735/371472 [7:43:49<11:35:19,  3.37it/s]
 62%|██████▏   | 230736/371472 [7:43:50<11:08:52,  3.51it/s]
 62%|██████▏   | 230737/371472 [7:43:50<10:57:57,  3.56it/s]
 62%|██████▏   | 230738/371472 [7:43:50<10:51:23,  3.60it/s]
 62%|██████▏   | 230739/371472 [7:43:51<10:40:02,  3.66it/s]
 62%|██████▏   | 230740/371472 [7:43:51<11:13:17,  3.48it/s]
                                                            
{'loss': 2.6715, 'learning_rate': 4.411482686547868e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230740/371472 [7:43:51<11:13:17,  3.48it/s]
 62%|██████▏   | 230741/371472 [7:43:51<11:14:58,  3.47it/s]
 62%|██████▏   | 230742/371472 [7:43:51<11:34:19,  3.38it/s]
 62%|██████▏   | 230743/371472 [7:43:52<11:40:00,  3.35it/s]
 62%|██████▏   | 230744/371472 [7:43:52<11:31:17,  3.39it/s]
 62%|██████▏   | 230745/371472 [7:43:52<11:17:40,  3.46it/s]
 62%|██████▏   | 230746/371472 [7:43:53<10:54:57,  3.58it/s]
 62%|██████▏   | 230747/371472 [7:43:53<11:06:44,  3.52it/s]
 62%|██████▏   | 230748/371472 [7:43:53<10:59:44,  3.56it/s]
 62%|██████▏   | 230749/371472 [7:43:53<10:47:37,  3.62it/s]
 62%|██████▏   | 230750/371472 [7:43:54<11:13:29,  3.48it/s]
 62%|██████▏   | 230751/371472 [7:43:54<11:07:15,  3.51it/s]
 62%|██████▏   | 230752/371472 [7:43:54<11:06:46,  3.52it/s]
 62%|██████▏   | 230753/371472 [7:43:55<11:17:12,  3.46it/s]
 62%|██████▏   | 230754/371472 [7:43:55<11:22:54,  3.43it/s]
 62%|██████▏   | 230755/371472 [7:43:55<11:14:16,  3.48it/s]
 62%|██████▏   | 230756/371472 [7:43:55<11:03:11,  3.54it/s]
 62%|██████▏   | 230757/371472 [7:43:56<11:33:32,  3.38it/s]
 62%|██████▏   | 230758/371472 [7:43:56<11:42:22,  3.34it/s]
 62%|██████▏   | 230759/371472 [7:43:56<11:38:35,  3.36it/s]
 62%|██████▏   | 230760/371472 [7:43:57<11:40:41,  3.35it/s]
                                                            
{'loss': 2.9459, 'learning_rate': 4.410997866793079e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230760/371472 [7:43:57<11:40:41,  3.35it/s]
 62%|██████▏   | 230761/371472 [7:43:57<11:45:39,  3.32it/s]
 62%|██████▏   | 230762/371472 [7:43:57<11:36:02,  3.37it/s]
 62%|██████▏   | 230763/371472 [7:43:58<11:38:59,  3.36it/s]
 62%|██████▏   | 230764/371472 [7:43:58<11:39:18,  3.35it/s]
 62%|██████▏   | 230765/371472 [7:43:58<12:02:59,  3.24it/s]
 62%|██████▏   | 230766/371472 [7:43:59<11:59:25,  3.26it/s]
 62%|██████▏   | 230767/371472 [7:43:59<11:44:48,  3.33it/s]
 62%|██████▏   | 230768/371472 [7:43:59<11:18:13,  3.46it/s]
 62%|██████▏   | 230769/371472 [7:43:59<10:57:43,  3.57it/s]
 62%|██████▏   | 230770/371472 [7:44:00<10:56:12,  3.57it/s]
 62%|██████▏   | 230771/371472 [7:44:00<10:50:38,  3.60it/s]
 62%|██████▏   | 230772/371472 [7:44:00<11:26:08,  3.42it/s]
 62%|██████▏   | 230773/371472 [7:44:01<11:57:50,  3.27it/s]
 62%|██████▏   | 230774/371472 [7:44:01<12:15:15,  3.19it/s]
 62%|██████▏   | 230775/371472 [7:44:01<12:17:16,  3.18it/s]
 62%|██████▏   | 230776/371472 [7:44:01<11:56:11,  3.27it/s]
 62%|██████▏   | 230777/371472 [7:44:02<11:34:18,  3.38it/s]
 62%|██████▏   | 230778/371472 [7:44:02<11:35:41,  3.37it/s]
 62%|██████▏   | 230779/371472 [7:44:02<11:30:09,  3.40it/s]
 62%|██████▏   | 230780/371472 [7:44:03<11:20:44,  3.44it/s]
                                                            
{'loss': 2.4877, 'learning_rate': 4.410513047038289e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230780/371472 [7:44:03<11:20:44,  3.44it/s]
 62%|██████▏   | 230781/371472 [7:44:03<12:11:01,  3.21it/s]
 62%|██████▏   | 230782/371472 [7:44:03<12:20:37,  3.17it/s]
 62%|██████▏   | 230783/371472 [7:44:04<12:14:28,  3.19it/s]
 62%|██████▏   | 230784/371472 [7:44:04<11:44:00,  3.33it/s]
 62%|██████▏   | 230785/371472 [7:44:04<11:23:51,  3.43it/s]
 62%|██████▏   | 230786/371472 [7:44:04<11:21:54,  3.44it/s]
 62%|██████▏   | 230787/371472 [7:44:05<11:22:04,  3.44it/s]
 62%|██████▏   | 230788/371472 [7:44:05<11:03:21,  3.53it/s]
 62%|██████▏   | 230789/371472 [7:44:05<11:31:03,  3.39it/s]
 62%|██████▏   | 230790/371472 [7:44:06<11:33:40,  3.38it/s]
 62%|██████▏   | 230791/371472 [7:44:06<11:59:35,  3.26it/s]
 62%|██████▏   | 230792/371472 [7:44:06<11:46:07,  3.32it/s]
 62%|██████▏   | 230793/371472 [7:44:07<11:34:38,  3.38it/s]
 62%|██████▏   | 230794/371472 [7:44:07<11:38:41,  3.36it/s]
 62%|██████▏   | 230795/371472 [7:44:07<13:02:53,  2.99it/s]
 62%|██████▏   | 230796/371472 [7:44:08<12:33:52,  3.11it/s]
 62%|██████▏   | 230797/371472 [7:44:08<11:51:09,  3.30it/s]
 62%|██████▏   | 230798/371472 [7:44:08<11:54:53,  3.28it/s]
 62%|██████▏   | 230799/371472 [7:44:08<11:39:15,  3.35it/s]
 62%|██████▏   | 230800/371472 [7:44:09<11:37:18,  3.36it/s]
                                                            
{'loss': 2.8954, 'learning_rate': 4.410028227283501e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230800/371472 [7:44:09<11:37:18,  3.36it/s]
 62%|██████▏   | 230801/371472 [7:44:09<11:28:37,  3.40it/s]
 62%|██████▏   | 230802/371472 [7:44:09<11:04:18,  3.53it/s]
 62%|██████▏   | 230803/371472 [7:44:09<10:58:31,  3.56it/s]
 62%|██████▏   | 230804/371472 [7:44:10<11:01:55,  3.54it/s]
 62%|██████▏   | 230805/371472 [7:44:10<10:55:50,  3.57it/s]
 62%|██████▏   | 230806/371472 [7:44:10<10:58:40,  3.56it/s]
 62%|██████▏   | 230807/371472 [7:44:11<11:22:29,  3.44it/s]
 62%|██████▏   | 230808/371472 [7:44:11<11:43:04,  3.33it/s]
 62%|██████▏   | 230809/371472 [7:44:11<12:04:10,  3.24it/s]
 62%|██████▏   | 230810/371472 [7:44:12<11:50:07,  3.30it/s]
 62%|██████▏   | 230811/371472 [7:44:12<11:33:22,  3.38it/s]
 62%|██████▏   | 230812/371472 [7:44:12<11:25:20,  3.42it/s]
 62%|██████▏   | 230813/371472 [7:44:12<11:30:23,  3.40it/s]
 62%|██████▏   | 230814/371472 [7:44:13<11:30:12,  3.40it/s]
 62%|██████▏   | 230815/371472 [7:44:13<11:04:02,  3.53it/s]
 62%|██████▏   | 230816/371472 [7:44:13<11:02:11,  3.54it/s]
 62%|██████▏   | 230817/371472 [7:44:14<10:56:50,  3.57it/s]
 62%|██████▏   | 230818/371472 [7:44:14<10:54:58,  3.58it/s]
 62%|██████▏   | 230819/371472 [7:44:14<11:22:52,  3.43it/s]
 62%|██████▏   | 230820/371472 [7:44:14<11:35:08,  3.37it/s]
                                                            
{'loss': 2.7721, 'learning_rate': 4.409543407528711e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230820/371472 [7:44:14<11:35:08,  3.37it/s]
 62%|██████▏   | 230821/371472 [7:44:15<11:58:33,  3.26it/s]
 62%|██████▏   | 230822/371472 [7:44:15<11:47:41,  3.31it/s]
 62%|██████▏   | 230823/371472 [7:44:15<11:40:53,  3.34it/s]
 62%|██████▏   | 230824/371472 [7:44:16<11:16:23,  3.47it/s]
 62%|██████▏   | 230825/371472 [7:44:16<11:07:17,  3.51it/s]
 62%|██████▏   | 230826/371472 [7:44:16<11:26:02,  3.42it/s]
 62%|██████▏   | 230827/371472 [7:44:16<11:08:53,  3.50it/s]
 62%|██████▏   | 230828/371472 [7:44:17<11:02:00,  3.54it/s]
 62%|██████▏   | 230829/371472 [7:44:17<11:11:23,  3.49it/s]
 62%|██████▏   | 230830/371472 [7:44:17<10:58:58,  3.56it/s]
 62%|██████▏   | 230831/371472 [7:44:18<11:09:41,  3.50it/s]
 62%|██████▏   | 230832/371472 [7:44:18<11:03:26,  3.53it/s]
 62%|██████▏   | 230833/371472 [7:44:18<11:03:52,  3.53it/s]
 62%|██████▏   | 230834/371472 [7:44:19<11:25:47,  3.42it/s]
 62%|██████▏   | 230835/371472 [7:44:19<11:18:25,  3.45it/s]
 62%|██████▏   | 230836/371472 [7:44:19<11:07:17,  3.51it/s]
 62%|██████▏   | 230837/371472 [7:44:19<11:06:45,  3.52it/s]
 62%|██████▏   | 230838/371472 [7:44:20<11:07:04,  3.51it/s]
 62%|██████▏   | 230839/371472 [7:44:20<11:33:07,  3.38it/s]
 62%|██████▏   | 230840/371472 [7:44:20<11:20:29,  3.44it/s]
                                                            
{'loss': 2.6864, 'learning_rate': 4.409058587773923e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230840/371472 [7:44:20<11:20:29,  3.44it/s]
 62%|██████▏   | 230841/371472 [7:44:21<11:59:09,  3.26it/s]
 62%|██████▏   | 230842/371472 [7:44:21<12:12:15,  3.20it/s]
 62%|██████▏   | 230843/371472 [7:44:21<11:50:12,  3.30it/s]
 62%|██████▏   | 230844/371472 [7:44:21<11:43:53,  3.33it/s]
 62%|██████▏   | 230845/371472 [7:44:22<11:23:33,  3.43it/s]
 62%|██████▏   | 230846/371472 [7:44:22<11:44:10,  3.33it/s]
 62%|██████▏   | 230847/371472 [7:44:22<11:26:52,  3.41it/s]
 62%|██████▏   | 230848/371472 [7:44:23<11:53:09,  3.29it/s]
 62%|██████▏   | 230849/371472 [7:44:23<11:47:33,  3.31it/s]
 62%|██████▏   | 230850/371472 [7:44:23<11:36:16,  3.37it/s]
 62%|██████▏   | 230851/371472 [7:44:24<11:16:08,  3.47it/s]
 62%|██████▏   | 230852/371472 [7:44:24<11:05:17,  3.52it/s]
 62%|██████▏   | 230853/371472 [7:44:24<12:00:38,  3.25it/s]
 62%|██████▏   | 230854/371472 [7:44:24<11:36:50,  3.36it/s]
 62%|██████▏   | 230855/371472 [7:44:25<12:11:11,  3.21it/s]
 62%|██████▏   | 230856/371472 [7:44:25<11:59:23,  3.26it/s]
 62%|██████▏   | 230857/371472 [7:44:25<11:25:47,  3.42it/s]
 62%|██████▏   | 230858/371472 [7:44:26<11:16:39,  3.46it/s]
 62%|██████▏   | 230859/371472 [7:44:26<11:23:28,  3.43it/s]
 62%|██████▏   | 230860/371472 [7:44:26<11:19:34,  3.45it/s]
                                                            
{'loss': 2.6257, 'learning_rate': 4.4085737680191336e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230860/371472 [7:44:26<11:19:34,  3.45it/s]
 62%|██████▏   | 230861/371472 [7:44:26<11:20:45,  3.44it/s]
 62%|██████▏   | 230862/371472 [7:44:27<10:57:30,  3.56it/s]
 62%|██████▏   | 230863/371472 [7:44:27<11:18:27,  3.45it/s]
 62%|██████▏   | 230864/371472 [7:44:27<11:11:34,  3.49it/s]
 62%|██████▏   | 230865/371472 [7:44:28<11:12:39,  3.48it/s]
 62%|██████▏   | 230866/371472 [7:44:28<11:00:14,  3.55it/s]
 62%|██████▏   | 230867/371472 [7:44:28<11:04:38,  3.53it/s]
 62%|██████▏   | 230868/371472 [7:44:28<11:06:54,  3.51it/s]
 62%|██████▏   | 230869/371472 [7:44:29<11:02:48,  3.54it/s]
 62%|██████▏   | 230870/371472 [7:44:29<11:11:14,  3.49it/s]
 62%|██████▏   | 230871/371472 [7:44:29<11:09:11,  3.50it/s]
 62%|██████▏   | 230872/371472 [7:44:30<11:12:36,  3.48it/s]
 62%|██████▏   | 230873/371472 [7:44:30<10:55:52,  3.57it/s]
 62%|██████▏   | 230874/371472 [7:44:30<12:23:16,  3.15it/s]
 62%|██████▏   | 230875/371472 [7:44:31<12:10:37,  3.21it/s]
 62%|██████▏   | 230876/371472 [7:44:31<12:07:31,  3.22it/s]
 62%|██████▏   | 230877/371472 [7:44:31<11:45:58,  3.32it/s]
 62%|██████▏   | 230878/371472 [7:44:31<11:34:48,  3.37it/s]
 62%|██████▏   | 230879/371472 [7:44:32<11:26:51,  3.41it/s]
 62%|██████▏   | 230880/371472 [7:44:32<11:22:20,  3.43it/s]
                                                            
{'loss': 2.7408, 'learning_rate': 4.4080889482643453e-07, 'epoch': 9.94}
+
 62%|██████▏   | 230880/371472 [7:44:32<11:22:20,  3.43it/s]
 62%|██████▏   | 230881/371472 [7:44:32<12:16:37,  3.18it/s]
 62%|██████▏   | 230882/371472 [7:44:33<12:10:31,  3.21it/s]
 62%|██████▏   | 230883/371472 [7:44:33<11:49:14,  3.30it/s]
 62%|██████▏   | 230884/371472 [7:44:33<11:44:06,  3.33it/s]
 62%|██████▏   | 230885/371472 [7:44:34<11:38:47,  3.35it/s]
 62%|██████▏   | 230886/371472 [7:44:34<11:32:22,  3.38it/s]
 62%|██████▏   | 230887/371472 [7:44:34<12:38:49,  3.09it/s]
 62%|██████▏   | 230888/371472 [7:44:35<12:25:14,  3.14it/s]
 62%|██████▏   | 230889/371472 [7:44:35<12:15:18,  3.19it/s]
 62%|██████▏   | 230890/371472 [7:44:35<11:59:51,  3.25it/s]
 62%|██████▏   | 230891/371472 [7:44:35<12:01:18,  3.25it/s]
 62%|██████▏   | 230892/371472 [7:44:36<11:58:20,  3.26it/s]
 62%|██████▏   | 230893/371472 [7:44:36<11:31:04,  3.39it/s]
 62%|██████▏   | 230894/371472 [7:44:36<11:13:30,  3.48it/s]
 62%|██████▏   | 230895/371472 [7:44:37<11:21:52,  3.44it/s]
 62%|██████▏   | 230896/371472 [7:44:37<12:26:02,  3.14it/s]
 62%|██████▏   | 230897/371472 [7:44:37<12:21:27,  3.16it/s]
 62%|██████▏   | 230898/371472 [7:44:38<12:19:03,  3.17it/s]
 62%|██████▏   | 230899/371472 [7:44:38<11:49:33,  3.30it/s]
 62%|██████▏   | 230900/371472 [7:44:38<12:57:04,  3.01it/s]
                                                            
{'loss': 2.8327, 'learning_rate': 4.4076041285095555e-07, 'epoch': 9.95}
+
 62%|██████▏   | 230900/371472 [7:44:38<12:57:04,  3.01it/s]
 62%|██████▏   | 230901/371472 [7:44:39<12:46:19,  3.06it/s]
 62%|██████▏   | 230902/371472 [7:44:39<12:10:52,  3.21it/s]
 62%|██████▏   | 230903/371472 [7:44:39<11:55:44,  3.27it/s]
 62%|██████▏   | 230904/371472 [7:44:39<11:50:11,  3.30it/s]
 62%|██████▏   | 230905/371472 [7:44:40<11:43:02,  3.33it/s]
 62%|██████▏   | 230906/371472 [7:44:40<11:47:15,  3.31it/s]
 62%|██████▏   | 230907/371472 [7:44:40<11:29:57,  3.40it/s]
 62%|██████▏   | 230908/371472 [7:44:41<11:33:57,  3.38it/s]
 62%|██████▏   | 230909/371472 [7:44:41<11:37:51,  3.36it/s]
 62%|██████▏   | 230910/371472 [7:44:41<11:26:30,  3.41it/s]
 62%|██████▏   | 230911/371472 [7:44:42<11:29:07,  3.40it/s]
 62%|██████▏   | 230912/371472 [7:44:42<11:12:23,  3.48it/s]
 62%|██████▏   | 230913/371472 [7:44:42<11:55:30,  3.27it/s]
 62%|██████▏   | 230914/371472 [7:44:43<13:11:42,  2.96it/s]
 62%|██████▏   | 230915/371472 [7:44:43<12:55:46,  3.02it/s]
 62%|██████▏   | 230916/371472 [7:44:43<12:48:34,  3.05it/s]
 62%|██████▏   | 230917/371472 [7:44:43<12:12:21,  3.20it/s]
 62%|██████▏   | 230918/371472 [7:44:44<12:07:57,  3.22it/s]
 62%|██████▏   | 230919/371472 [7:44:44<12:11:26,  3.20it/s]
 62%|██████▏   | 230920/371472 [7:44:44<12:20:00,  3.17it/s]
                                                            
{'loss': 2.7708, 'learning_rate': 4.4071193087547673e-07, 'epoch': 9.95}
+
 62%|██████▏   | 230920/371472 [7:44:44<12:20:00,  3.17it/s]
 62%|██████▏   | 230921/371472 [7:44:45<11:45:26,  3.32it/s]
 62%|██████▏   | 230922/371472 [7:44:45<11:19:49,  3.45it/s]
 62%|██████▏   | 230923/371472 [7:44:45<11:18:13,  3.45it/s]
 62%|██████▏   | 230924/371472 [7:44:46<11:18:51,  3.45it/s]
 62%|██████▏   | 230925/371472 [7:44:46<10:59:15,  3.55it/s]
 62%|██████▏   | 230926/371472 [7:44:46<10:49:54,  3.60it/s]
 62%|██████▏   | 230927/371472 [7:44:46<11:00:03,  3.55it/s]
 62%|██████▏   | 230928/371472 [7:44:47<11:06:34,  3.51it/s]
 62%|██████▏   | 230929/371472 [7:44:47<11:05:36,  3.52it/s]
 62%|██████▏   | 230930/371472 [7:44:47<11:33:17,  3.38it/s]
 62%|██████▏   | 230931/371472 [7:44:48<11:45:40,  3.32it/s]
 62%|██████▏   | 230932/371472 [7:44:48<11:37:04,  3.36it/s]
 62%|██████▏   | 230933/371472 [7:44:48<11:53:08,  3.28it/s]
 62%|██████▏   | 230934/371472 [7:44:48<11:29:08,  3.40it/s]
 62%|██████▏   | 230935/371472 [7:44:49<11:17:40,  3.46it/s]
 62%|██████▏   | 230936/371472 [7:44:49<15:32:26,  2.51it/s]
 62%|██████▏   | 230937/371472 [7:44:50<14:09:50,  2.76it/s]
 62%|██████▏   | 230938/371472 [7:44:50<13:22:01,  2.92it/s]
 62%|██████▏   | 230939/371472 [7:44:50<12:53:33,  3.03it/s]
 62%|██████▏   | 230940/371472 [7:44:51<12:20:48,  3.16it/s]
                                                            
{'loss': 2.6885, 'learning_rate': 4.406634488999978e-07, 'epoch': 9.95}
+
 62%|██████▏   | 230940/371472 [7:44:51<12:20:48,  3.16it/s]
 62%|██████▏   | 230941/371472 [7:44:51<11:49:00,  3.30it/s]
 62%|██████▏   | 230942/371472 [7:44:51<11:47:36,  3.31it/s]
 62%|██████▏   | 230943/371472 [7:44:51<11:50:07,  3.30it/s]
 62%|██████▏   | 230944/371472 [7:44:52<11:30:45,  3.39it/s]
 62%|██████▏   | 230945/371472 [7:44:52<11:31:54,  3.39it/s]
 62%|██████▏   | 230946/371472 [7:44:52<11:42:33,  3.33it/s]
 62%|██████▏   | 230947/371472 [7:44:53<11:43:31,  3.33it/s]
 62%|██████▏   | 230948/371472 [7:44:53<12:04:16,  3.23it/s]
 62%|██████▏   | 230949/371472 [7:44:53<11:59:18,  3.26it/s]
 62%|██████▏   | 230950/371472 [7:44:54<11:40:43,  3.34it/s]
 62%|██████▏   | 230951/371472 [7:44:54<11:20:08,  3.44it/s]
 62%|██████▏   | 230952/371472 [7:44:54<11:19:51,  3.44it/s]
 62%|██████▏   | 230953/371472 [7:44:54<11:30:39,  3.39it/s]
 62%|██████▏   | 230954/371472 [7:44:55<11:32:19,  3.38it/s]
 62%|██████▏   | 230955/371472 [7:44:55<11:48:51,  3.30it/s]
 62%|██████▏   | 230956/371472 [7:44:55<11:37:38,  3.36it/s]
 62%|██████▏   | 230957/371472 [7:44:56<12:05:00,  3.23it/s]
 62%|██████▏   | 230958/371472 [7:44:56<12:35:25,  3.10it/s]
 62%|██████▏   | 230959/371472 [7:44:56<12:01:06,  3.25it/s]
 62%|██████▏   | 230960/371472 [7:44:57<11:58:19,  3.26it/s]
                                                            
{'loss': 2.8345, 'learning_rate': 4.4061496692451893e-07, 'epoch': 9.95}
+
 62%|██████▏   | 230960/371472 [7:44:57<11:58:19,  3.26it/s]
 62%|██████▏   | 230961/371472 [7:44:57<11:33:39,  3.38it/s]
 62%|██████▏   | 230962/371472 [7:44:57<11:27:23,  3.41it/s]
 62%|██████▏   | 230963/371472 [7:44:57<11:13:10,  3.48it/s]
 62%|██████▏   | 230964/371472 [7:44:58<11:55:24,  3.27it/s]
 62%|██████▏   | 230965/371472 [7:44:58<11:31:11,  3.39it/s]
 62%|██████▏   | 230966/371472 [7:44:58<11:41:57,  3.34it/s]
 62%|██████▏   | 230967/371472 [7:44:59<11:37:15,  3.36it/s]
 62%|██████▏   | 230968/371472 [7:44:59<12:00:41,  3.25it/s]
 62%|██████▏   | 230969/371472 [7:44:59<12:32:13,  3.11it/s]
 62%|██████▏   | 230970/371472 [7:45:00<12:14:58,  3.19it/s]
 62%|██████▏   | 230971/371472 [7:45:00<11:48:48,  3.30it/s]
 62%|██████▏   | 230972/371472 [7:45:00<11:37:40,  3.36it/s]
 62%|██████▏   | 230973/371472 [7:45:00<11:36:40,  3.36it/s]
 62%|██████▏   | 230974/371472 [7:45:01<11:25:45,  3.41it/s]
 62%|██████▏   | 230975/371472 [7:45:01<12:04:54,  3.23it/s]
 62%|██████▏   | 230976/371472 [7:45:01<12:08:14,  3.22it/s]
 62%|██████▏   | 230977/371472 [7:45:02<11:43:57,  3.33it/s]
 62%|██████▏   | 230978/371472 [7:45:02<12:07:54,  3.22it/s]
 62%|██████▏   | 230979/371472 [7:45:02<11:55:34,  3.27it/s]
 62%|██████▏   | 230980/371472 [7:45:03<11:47:28,  3.31it/s]
                                                            
{'loss': 2.7501, 'learning_rate': 4.4056648494904e-07, 'epoch': 9.95}
+
 62%|██████▏   | 230980/371472 [7:45:03<11:47:28,  3.31it/s]
 62%|██████▏   | 230981/371472 [7:45:03<11:26:25,  3.41it/s]
 62%|██████▏   | 230982/371472 [7:45:03<11:18:17,  3.45it/s]
 62%|██████▏   | 230983/371472 [7:45:03<11:17:21,  3.46it/s]
 62%|██████▏   | 230984/371472 [7:45:04<12:21:12,  3.16it/s]
 62%|██████▏   | 230985/371472 [7:45:04<11:56:21,  3.27it/s]
 62%|██████▏   | 230986/371472 [7:45:04<11:39:10,  3.35it/s]
 62%|██████▏   | 230987/371472 [7:45:05<11:30:37,  3.39it/s]
 62%|██████▏   | 230988/371472 [7:45:05<11:21:25,  3.44it/s]
 62%|██████▏   | 230989/371472 [7:45:05<11:18:15,  3.45it/s]
 62%|██████▏   | 230990/371472 [7:45:06<11:21:13,  3.44it/s]
 62%|██████▏   | 230991/371472 [7:45:06<11:38:14,  3.35it/s]
 62%|██████▏   | 230992/371472 [7:45:06<11:32:21,  3.38it/s]
 62%|██████▏   | 230993/371472 [7:45:06<11:55:22,  3.27it/s]
 62%|██████▏   | 230994/371472 [7:45:07<11:34:12,  3.37it/s]
 62%|██████▏   | 230995/371472 [7:45:07<11:25:17,  3.42it/s]
 62%|██████▏   | 230996/371472 [7:45:07<11:20:46,  3.44it/s]
 62%|██████▏   | 230997/371472 [7:45:08<11:46:49,  3.31it/s]
 62%|██████▏   | 230998/371472 [7:45:08<11:37:13,  3.36it/s]
 62%|██████▏   | 230999/371472 [7:45:08<11:32:59,  3.38it/s]
 62%|██████▏   | 231000/371472 [7:45:08<11:11:34,  3.49it/s]
                                                            
{'loss': 2.7741, 'learning_rate': 4.405180029735612e-07, 'epoch': 9.95}
+
 62%|██████▏   | 231000/371472 [7:45:08<11:11:34,  3.49it/s]
 62%|██████▏   | 231001/371472 [7:45:09<11:12:22,  3.48it/s]
 62%|██████▏   | 231002/371472 [7:45:09<11:09:54,  3.49it/s]
 62%|██████▏   | 231003/371472 [7:45:09<11:02:30,  3.53it/s]
 62%|██████▏   | 231004/371472 [7:45:10<11:12:10,  3.48it/s]
 62%|██████▏   | 231005/371472 [7:45:10<11:13:33,  3.48it/s]
 62%|██████▏   | 231006/371472 [7:45:10<11:03:47,  3.53it/s]
 62%|██████▏   | 231007/371472 [7:45:10<11:25:02,  3.42it/s]
 62%|██████▏   | 231008/371472 [7:45:11<11:39:27,  3.35it/s]
 62%|██████▏   | 231009/371472 [7:45:11<11:50:07,  3.30it/s]
 62%|██████▏   | 231010/371472 [7:45:11<11:43:35,  3.33it/s]
 62%|██████▏   | 231011/371472 [7:45:12<11:54:59,  3.27it/s]
 62%|██████▏   | 231012/371472 [7:45:12<12:18:24,  3.17it/s]
 62%|██████▏   | 231013/371472 [7:45:12<12:11:44,  3.20it/s]
 62%|██████▏   | 231014/371472 [7:45:13<11:57:27,  3.26it/s]
 62%|██████▏   | 231015/371472 [7:45:13<11:27:18,  3.41it/s]
 62%|██████▏   | 231016/371472 [7:45:13<11:24:37,  3.42it/s]
 62%|██████▏   | 231017/371472 [7:45:14<11:46:08,  3.32it/s]
 62%|██████▏   | 231018/371472 [7:45:14<11:58:24,  3.26it/s]
 62%|██████▏   | 231019/371472 [7:45:14<11:49:20,  3.30it/s]
 62%|██████▏   | 231020/371472 [7:45:14<12:10:04,  3.21it/s]
                                                            
{'loss': 2.6325, 'learning_rate': 4.4046952099808225e-07, 'epoch': 9.95}
+
 62%|██████▏   | 231020/371472 [7:45:14<12:10:04,  3.21it/s]
 62%|██████▏   | 231021/371472 [7:45:15<11:46:07,  3.32it/s]
 62%|██████▏   | 231022/371472 [7:45:15<11:55:51,  3.27it/s]
 62%|██████▏   | 231023/371472 [7:45:15<11:35:11,  3.37it/s]
 62%|██████▏   | 231024/371472 [7:45:16<11:28:03,  3.40it/s]
 62%|██████▏   | 231025/371472 [7:45:16<11:17:36,  3.45it/s]
 62%|██████▏   | 231026/371472 [7:45:16<12:14:26,  3.19it/s]
 62%|██████▏   | 231027/371472 [7:45:17<12:06:34,  3.22it/s]
 62%|██████▏   | 231028/371472 [7:45:17<12:17:33,  3.17it/s]
 62%|██████▏   | 231029/371472 [7:45:17<12:14:53,  3.19it/s]
 62%|██████▏   | 231030/371472 [7:45:18<12:04:49,  3.23it/s]
 62%|██████▏   | 231031/371472 [7:45:18<11:47:47,  3.31it/s]
 62%|██████▏   | 231032/371472 [7:45:18<12:41:30,  3.07it/s]
 62%|██████▏   | 231033/371472 [7:45:18<12:00:04,  3.25it/s]
 62%|██████▏   | 231034/371472 [7:45:19<11:53:07,  3.28it/s]
 62%|██████▏   | 231035/371472 [7:45:19<11:26:37,  3.41it/s]
 62%|██████▏   | 231036/371472 [7:45:19<11:20:09,  3.44it/s]
 62%|██████▏   | 231037/371472 [7:45:20<11:20:44,  3.44it/s]
 62%|██████▏   | 231038/371472 [7:45:20<11:08:43,  3.50it/s]
 62%|██████▏   | 231039/371472 [7:45:20<11:21:12,  3.44it/s]
 62%|██████▏   | 231040/371472 [7:45:21<11:50:46,  3.29it/s]
                                                            
{'loss': 2.8222, 'learning_rate': 4.4042103902260337e-07, 'epoch': 9.95}
+
 62%|██████▏   | 231040/371472 [7:45:21<11:50:46,  3.29it/s]
 62%|██████▏   | 231041/371472 [7:45:21<11:54:01,  3.28it/s]
 62%|██████▏   | 231042/371472 [7:45:21<12:21:30,  3.16it/s]
 62%|██████▏   | 231043/371472 [7:45:21<11:32:45,  3.38it/s]
 62%|██████▏   | 231044/371472 [7:45:22<11:50:34,  3.29it/s]
 62%|██████▏   | 231045/371472 [7:45:22<11:23:43,  3.42it/s]
 62%|██████▏   | 231046/371472 [7:45:22<11:29:28,  3.39it/s]
 62%|██████▏   | 231047/371472 [7:45:23<11:46:09,  3.31it/s]
 62%|██████▏   | 231048/371472 [7:45:23<12:01:38,  3.24it/s]
 62%|██████▏   | 231049/371472 [7:45:23<12:09:25,  3.21it/s]
 62%|██████▏   | 231050/371472 [7:45:24<11:50:38,  3.29it/s]
 62%|██████▏   | 231051/371472 [7:45:24<11:21:12,  3.44it/s]
 62%|██████▏   | 231052/371472 [7:45:24<11:38:54,  3.35it/s]
 62%|██████▏   | 231053/371472 [7:45:24<11:22:55,  3.43it/s]
 62%|██████▏   | 231054/371472 [7:45:25<11:44:59,  3.32it/s]
 62%|██████▏   | 231055/371472 [7:45:25<12:17:03,  3.18it/s]
 62%|██████▏   | 231056/371472 [7:45:25<12:08:28,  3.21it/s]
 62%|██████▏   | 231057/371472 [7:45:26<11:36:54,  3.36it/s]
 62%|██████▏   | 231058/371472 [7:45:26<12:08:57,  3.21it/s]
 62%|██████▏   | 231059/371472 [7:45:26<11:41:20,  3.34it/s]
 62%|██████▏   | 231060/371472 [7:45:27<11:54:43,  3.27it/s]
                                                            
{'loss': 2.7223, 'learning_rate': 4.4037255704712444e-07, 'epoch': 9.95}
+
 62%|██████▏   | 231060/371472 [7:45:27<11:54:43,  3.27it/s]
 62%|██████▏   | 231061/371472 [7:45:27<11:59:51,  3.25it/s]
 62%|██████▏   | 231062/371472 [7:45:27<12:29:21,  3.12it/s]
 62%|██████▏   | 231063/371472 [7:45:28<12:46:22,  3.05it/s]
 62%|██████▏   | 231064/371472 [7:45:28<12:22:13,  3.15it/s]
 62%|██████▏   | 231065/371472 [7:45:28<11:48:08,  3.30it/s]
 62%|██████▏   | 231066/371472 [7:45:28<11:59:54,  3.25it/s]
 62%|██████▏   | 231067/371472 [7:45:29<11:31:05,  3.39it/s]
 62%|██████▏   | 231068/371472 [7:45:29<11:36:21,  3.36it/s]
 62%|██████▏   | 231069/371472 [7:45:29<11:28:50,  3.40it/s]
 62%|██████▏   | 231070/371472 [7:45:30<11:26:54,  3.41it/s]
 62%|██████▏   | 231071/371472 [7:45:30<11:40:19,  3.34it/s]
 62%|██████▏   | 231072/371472 [7:45:30<11:20:18,  3.44it/s]
 62%|██████▏   | 231073/371472 [7:45:31<11:50:33,  3.29it/s]
 62%|██████▏   | 231074/371472 [7:45:31<12:46:29,  3.05it/s]
 62%|██████▏   | 231075/371472 [7:45:31<12:09:10,  3.21it/s]
 62%|██████▏   | 231076/371472 [7:45:32<12:18:45,  3.17it/s]
 62%|██████▏   | 231077/371472 [7:45:32<12:07:27,  3.22it/s]
 62%|██████▏   | 231078/371472 [7:45:32<11:38:52,  3.35it/s]
 62%|██████▏   | 231079/371472 [7:45:32<12:02:21,  3.24it/s]
 62%|██████▏   | 231080/371472 [7:45:33<12:09:55,  3.21it/s]
                                                            
{'loss': 2.5351, 'learning_rate': 4.403240750716456e-07, 'epoch': 9.95}
+
 62%|██████▏   | 231080/371472 [7:45:33<12:09:55,  3.21it/s]
 62%|██████▏   | 231081/371472 [7:45:33<12:35:49,  3.10it/s]
 62%|██████▏   | 231082/371472 [7:45:33<12:01:49,  3.24it/s]
 62%|██████▏   | 231083/371472 [7:45:34<12:01:18,  3.24it/s]
 62%|██████▏   | 231084/371472 [7:45:34<11:47:57,  3.31it/s]
 62%|██████▏   | 231085/371472 [7:45:34<11:33:28,  3.37it/s]
 62%|██████▏   | 231086/371472 [7:45:35<11:58:59,  3.25it/s]
 62%|██████▏   | 231087/371472 [7:45:35<12:48:36,  3.04it/s]
 62%|██████▏   | 231088/371472 [7:45:35<12:31:15,  3.11it/s]
 62%|██████▏   | 231089/371472 [7:45:36<12:12:33,  3.19it/s]
 62%|██████▏   | 231090/371472 [7:45:36<12:33:17,  3.11it/s]
 62%|██████▏   | 231091/371472 [7:45:36<12:44:42,  3.06it/s]
 62%|██████▏   | 231092/371472 [7:45:36<11:57:42,  3.26it/s]
 62%|██████▏   | 231093/371472 [7:45:37<12:54:53,  3.02it/s]
 62%|██████▏   | 231094/371472 [7:45:37<12:20:08,  3.16it/s]
 62%|██████▏   | 231095/371472 [7:45:38<13:06:42,  2.97it/s]
 62%|██████▏   | 231096/371472 [7:45:38<12:57:44,  3.01it/s]
 62%|██████▏   | 231097/371472 [7:45:38<12:49:40,  3.04it/s]
 62%|██████▏   | 231098/371472 [7:45:38<12:29:25,  3.12it/s]
 62%|██████▏   | 231099/371472 [7:45:39<12:41:19,  3.07it/s]
 62%|██████▏   | 231100/371472 [7:45:39<12:21:06,  3.16it/s]
                                                            
{'loss': 2.6932, 'learning_rate': 4.4027559309616664e-07, 'epoch': 9.95}
+
 62%|██████▏   | 231100/371472 [7:45:39<12:21:06,  3.16it/s]
 62%|██████▏   | 231101/371472 [7:45:39<11:46:08,  3.31it/s]
 62%|██████▏   | 231102/371472 [7:45:40<11:27:14,  3.40it/s]
 62%|██████▏   | 231103/371472 [7:45:40<11:10:36,  3.49it/s]
 62%|██████▏   | 231104/371472 [7:45:40<11:12:01,  3.48it/s]
 62%|██████▏   | 231105/371472 [7:45:40<11:13:54,  3.47it/s]
 62%|██████▏   | 231106/371472 [7:45:41<10:57:51,  3.56it/s]
 62%|██████▏   | 231107/371472 [7:45:41<11:17:55,  3.45it/s]
 62%|██████▏   | 231108/371472 [7:45:41<10:57:54,  3.56it/s]
 62%|██████▏   | 231109/371472 [7:45:42<11:10:07,  3.49it/s]
 62%|██████▏   | 231110/371472 [7:45:42<11:10:39,  3.49it/s]
 62%|██████▏   | 231111/371472 [7:45:42<11:05:54,  3.51it/s]
 62%|██████▏   | 231112/371472 [7:45:43<11:22:02,  3.43it/s]
 62%|██████▏   | 231113/371472 [7:45:43<11:02:43,  3.53it/s]
 62%|██████▏   | 231114/371472 [7:45:43<11:09:13,  3.50it/s]
 62%|██████▏   | 231115/371472 [7:45:43<11:11:16,  3.48it/s]
 62%|██████▏   | 231116/371472 [7:45:44<11:07:55,  3.50it/s]
 62%|██████▏   | 231117/371472 [7:45:44<11:07:38,  3.50it/s]
 62%|██████▏   | 231118/371472 [7:45:44<11:11:43,  3.48it/s]
 62%|██████▏   | 231119/371472 [7:45:45<12:15:55,  3.18it/s]
 62%|██████▏   | 231120/371472 [7:45:45<11:52:01,  3.29it/s]
                                                            
{'loss': 2.8151, 'learning_rate': 4.402271111206878e-07, 'epoch': 9.95}
+
 62%|██████▏   | 231120/371472 [7:45:45<11:52:01,  3.29it/s]
 62%|██████▏   | 231121/371472 [7:45:45<11:43:39,  3.32it/s]
 62%|██████▏   | 231122/371472 [7:45:45<11:42:05,  3.33it/s]
 62%|██████▏   | 231123/371472 [7:45:46<11:32:27,  3.38it/s]
 62%|██████▏   | 231124/371472 [7:45:46<11:20:37,  3.44it/s]
 62%|██████▏   | 231125/371472 [7:45:46<10:57:18,  3.56it/s]
 62%|██████▏   | 231126/371472 [7:45:47<11:07:20,  3.51it/s]
 62%|██████▏   | 231127/371472 [7:45:47<11:04:03,  3.52it/s]
 62%|██████▏   | 231128/371472 [7:45:47<11:05:51,  3.51it/s]
 62%|██████▏   | 231129/371472 [7:45:47<11:34:42,  3.37it/s]
 62%|██████▏   | 231130/371472 [7:45:48<11:30:45,  3.39it/s]
 62%|██████▏   | 231131/371472 [7:45:48<12:06:21,  3.22it/s]
 62%|██████▏   | 231132/371472 [7:45:48<12:23:07,  3.15it/s]
 62%|██████▏   | 231133/371472 [7:45:49<12:11:29,  3.20it/s]
 62%|██████▏   | 231134/371472 [7:45:49<11:57:22,  3.26it/s]
 62%|██████▏   | 231135/371472 [7:45:49<12:07:34,  3.21it/s]
 62%|██████▏   | 231136/371472 [7:45:50<12:11:57,  3.20it/s]
 62%|██████▏   | 231137/371472 [7:45:50<12:23:22,  3.15it/s]
 62%|██████▏   | 231138/371472 [7:45:50<11:59:19,  3.25it/s]
 62%|██████▏   | 231139/371472 [7:45:51<11:45:49,  3.31it/s]
 62%|██████▏   | 231140/371472 [7:45:51<11:32:26,  3.38it/s]
                                                            
{'loss': 2.5107, 'learning_rate': 4.401786291452089e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231140/371472 [7:45:51<11:32:26,  3.38it/s]
 62%|██████▏   | 231141/371472 [7:45:51<11:17:33,  3.45it/s]
 62%|██████▏   | 231142/371472 [7:45:51<12:08:27,  3.21it/s]
 62%|██████▏   | 231143/371472 [7:45:52<11:55:03,  3.27it/s]
 62%|██████▏   | 231144/371472 [7:45:52<11:36:18,  3.36it/s]
 62%|██████▏   | 231145/371472 [7:45:52<11:58:35,  3.25it/s]
 62%|██████▏   | 231146/371472 [7:45:53<11:51:28,  3.29it/s]
 62%|██████▏   | 231147/371472 [7:45:53<11:47:11,  3.31it/s]
 62%|██████▏   | 231148/371472 [7:45:53<11:37:24,  3.35it/s]
 62%|██████▏   | 231149/371472 [7:45:54<11:20:31,  3.44it/s]
 62%|██████▏   | 231150/371472 [7:45:54<11:20:54,  3.43it/s]
 62%|██████▏   | 231151/371472 [7:45:54<12:14:41,  3.18it/s]
 62%|██████▏   | 231152/371472 [7:45:55<11:54:56,  3.27it/s]
 62%|██████▏   | 231153/371472 [7:45:55<11:55:07,  3.27it/s]
 62%|██████▏   | 231154/371472 [7:45:55<11:37:40,  3.35it/s]
 62%|██████▏   | 231155/371472 [7:45:55<11:28:13,  3.40it/s]
 62%|██████▏   | 231156/371472 [7:45:56<11:43:52,  3.32it/s]
 62%|██████▏   | 231157/371472 [7:45:56<11:51:07,  3.29it/s]
 62%|██████▏   | 231158/371472 [7:45:56<11:47:55,  3.30it/s]
 62%|██████▏   | 231159/371472 [7:45:57<11:31:44,  3.38it/s]
 62%|██████▏   | 231160/371472 [7:45:57<11:15:33,  3.46it/s]
                                                            
{'loss': 2.6976, 'learning_rate': 4.4013014716973e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231160/371472 [7:45:57<11:15:33,  3.46it/s]
 62%|██████▏   | 231161/371472 [7:45:57<11:52:36,  3.28it/s]
 62%|██████▏   | 231162/371472 [7:45:58<12:02:20,  3.24it/s]
 62%|██████▏   | 231163/371472 [7:45:58<13:07:50,  2.97it/s]
 62%|██████▏   | 231164/371472 [7:45:58<12:35:59,  3.09it/s]
 62%|██████▏   | 231165/371472 [7:45:59<12:21:27,  3.15it/s]
 62%|██████▏   | 231166/371472 [7:45:59<14:27:29,  2.70it/s]
 62%|██████▏   | 231167/371472 [7:45:59<13:26:32,  2.90it/s]
 62%|██████▏   | 231168/371472 [7:46:00<13:04:46,  2.98it/s]
 62%|██████▏   | 231169/371472 [7:46:00<12:27:58,  3.13it/s]
 62%|██████▏   | 231170/371472 [7:46:00<11:57:59,  3.26it/s]
 62%|██████▏   | 231171/371472 [7:46:00<11:28:29,  3.40it/s]
 62%|██████▏   | 231172/371472 [7:46:01<11:20:11,  3.44it/s]
 62%|██████▏   | 231173/371472 [7:46:01<11:19:05,  3.44it/s]
 62%|██████▏   | 231174/371472 [7:46:01<11:17:34,  3.45it/s]
 62%|██████▏   | 231175/371472 [7:46:02<11:08:42,  3.50it/s]
 62%|██████▏   | 231176/371472 [7:46:02<11:08:06,  3.50it/s]
 62%|██████▏   | 231177/371472 [7:46:02<11:16:59,  3.45it/s]
 62%|██████▏   | 231178/371472 [7:46:02<11:14:49,  3.46it/s]
 62%|██████▏   | 231179/371472 [7:46:03<11:10:03,  3.49it/s]
 62%|██████▏   | 231180/371472 [7:46:03<11:10:03,  3.49it/s]
                                                            
{'loss': 2.8091, 'learning_rate': 4.400816651942511e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231180/371472 [7:46:03<11:10:03,  3.49it/s]
 62%|██████▏   | 231181/371472 [7:46:03<11:05:05,  3.52it/s]
 62%|██████▏   | 231182/371472 [7:46:04<11:31:18,  3.38it/s]
 62%|██████▏   | 231183/371472 [7:46:04<11:19:08,  3.44it/s]
 62%|██████▏   | 231184/371472 [7:46:04<11:35:40,  3.36it/s]
 62%|██████▏   | 231185/371472 [7:46:05<11:45:28,  3.31it/s]
 62%|██████▏   | 231186/371472 [7:46:05<11:24:38,  3.42it/s]
 62%|██████▏   | 231187/371472 [7:46:05<12:43:18,  3.06it/s]
 62%|██████▏   | 231188/371472 [7:46:05<12:20:12,  3.16it/s]
 62%|██████▏   | 231189/371472 [7:46:06<12:14:22,  3.18it/s]
 62%|██████▏   | 231190/371472 [7:46:06<11:47:53,  3.30it/s]
 62%|██████▏   | 231191/371472 [7:46:06<11:38:31,  3.35it/s]
 62%|██████▏   | 231192/371472 [7:46:07<11:24:43,  3.41it/s]
 62%|██████▏   | 231193/371472 [7:46:07<11:17:43,  3.45it/s]
 62%|██████▏   | 231194/371472 [7:46:07<11:23:13,  3.42it/s]
 62%|██████▏   | 231195/371472 [7:46:08<11:31:09,  3.38it/s]
 62%|██████▏   | 231196/371472 [7:46:08<11:26:19,  3.41it/s]
 62%|██████▏   | 231197/371472 [7:46:08<12:10:39,  3.20it/s]
 62%|██████▏   | 231198/371472 [7:46:08<11:55:27,  3.27it/s]
 62%|██████▏   | 231199/371472 [7:46:09<12:03:44,  3.23it/s]
 62%|██████▏   | 231200/371472 [7:46:09<12:43:09,  3.06it/s]
                                                            
{'loss': 2.5837, 'learning_rate': 4.4003318321877226e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231200/371472 [7:46:09<12:43:09,  3.06it/s]
 62%|██████▏   | 231201/371472 [7:46:09<12:01:00,  3.24it/s]
 62%|██████▏   | 231202/371472 [7:46:10<11:41:35,  3.33it/s]
 62%|██████▏   | 231203/371472 [7:46:10<12:12:06,  3.19it/s]
 62%|██████▏   | 231204/371472 [7:46:10<11:49:49,  3.29it/s]
 62%|██████▏   | 231205/371472 [7:46:11<11:40:13,  3.34it/s]
 62%|██████▏   | 231206/371472 [7:46:11<12:04:45,  3.23it/s]
 62%|██████▏   | 231207/371472 [7:46:11<12:30:20,  3.12it/s]
 62%|██████▏   | 231208/371472 [7:46:12<12:02:25,  3.24it/s]
 62%|██████▏   | 231209/371472 [7:46:12<11:55:51,  3.27it/s]
 62%|██████▏   | 231210/371472 [7:46:12<11:30:25,  3.39it/s]
 62%|██████▏   | 231211/371472 [7:46:13<12:26:51,  3.13it/s]
 62%|██████▏   | 231212/371472 [7:46:13<12:23:36,  3.14it/s]
 62%|██████▏   | 231213/371472 [7:46:13<11:56:40,  3.26it/s]
 62%|██████▏   | 231214/371472 [7:46:13<11:44:16,  3.32it/s]
 62%|██████▏   | 231215/371472 [7:46:14<11:18:17,  3.45it/s]
 62%|██████▏   | 231216/371472 [7:46:14<11:13:02,  3.47it/s]
 62%|██████▏   | 231217/371472 [7:46:14<11:43:38,  3.32it/s]
 62%|██████▏   | 231218/371472 [7:46:15<11:47:45,  3.30it/s]
 62%|██████▏   | 231219/371472 [7:46:15<12:32:15,  3.11it/s]
 62%|██████▏   | 231220/371472 [7:46:15<12:58:47,  3.00it/s]
                                                            
{'loss': 2.809, 'learning_rate': 4.399847012432933e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231220/371472 [7:46:15<12:58:47,  3.00it/s]
 62%|██████▏   | 231221/371472 [7:46:16<12:53:44,  3.02it/s]
 62%|██████▏   | 231222/371472 [7:46:16<12:17:10,  3.17it/s]
 62%|██████▏   | 231223/371472 [7:46:16<12:08:56,  3.21it/s]
 62%|██████▏   | 231224/371472 [7:46:17<11:53:15,  3.28it/s]
 62%|██████▏   | 231225/371472 [7:46:17<11:28:18,  3.40it/s]
 62%|██████▏   | 231226/371472 [7:46:17<11:14:05,  3.47it/s]
 62%|██████▏   | 231227/371472 [7:46:17<11:01:16,  3.53it/s]
 62%|██████▏   | 231228/371472 [7:46:18<11:13:11,  3.47it/s]
 62%|██████▏   | 231229/371472 [7:46:18<10:49:16,  3.60it/s]
 62%|██████▏   | 231230/371472 [7:46:18<10:31:37,  3.70it/s]
 62%|██████▏   | 231231/371472 [7:46:18<10:49:13,  3.60it/s]
 62%|██████▏   | 231232/371472 [7:46:19<10:48:38,  3.60it/s]
 62%|██████▏   | 231233/371472 [7:46:19<10:57:05,  3.56it/s]
 62%|██████▏   | 231234/371472 [7:46:19<11:10:39,  3.49it/s]
 62%|██████▏   | 231235/371472 [7:46:20<11:12:12,  3.48it/s]
 62%|██████▏   | 231236/371472 [7:46:20<11:22:54,  3.42it/s]
 62%|██████▏   | 231237/371472 [7:46:20<11:23:16,  3.42it/s]
 62%|██████▏   | 231238/371472 [7:46:21<12:21:40,  3.15it/s]
 62%|██████▏   | 231239/371472 [7:46:21<12:55:47,  3.01it/s]
 62%|██████▏   | 231240/371472 [7:46:21<13:19:49,  2.92it/s]
                                                            
{'loss': 2.5785, 'learning_rate': 4.3993621926781446e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231240/371472 [7:46:21<13:19:49,  2.92it/s]
 62%|██████▏   | 231241/371472 [7:46:22<12:33:14,  3.10it/s]
 62%|██████▏   | 231242/371472 [7:46:22<12:16:10,  3.17it/s]
 62%|██████▏   | 231243/371472 [7:46:22<11:32:57,  3.37it/s]
 62%|██████▏   | 231244/371472 [7:46:22<11:52:51,  3.28it/s]
 62%|██████▏   | 231245/371472 [7:46:23<12:08:27,  3.21it/s]
 62%|██████▏   | 231246/371472 [7:46:23<11:39:44,  3.34it/s]
 62%|██████▏   | 231247/371472 [7:46:23<11:28:37,  3.39it/s]
 62%|██████▏   | 231248/371472 [7:46:24<11:10:05,  3.49it/s]
 62%|██████▏   | 231249/371472 [7:46:24<11:19:42,  3.44it/s]
 62%|██████▏   | 231250/371472 [7:46:24<10:58:26,  3.55it/s]
 62%|██████▏   | 231251/371472 [7:46:24<10:48:52,  3.60it/s]
 62%|██████▏   | 231252/371472 [7:46:25<10:57:58,  3.55it/s]
 62%|██████▏   | 231253/371472 [7:46:25<11:03:55,  3.52it/s]
 62%|██████▏   | 231254/371472 [7:46:25<11:45:10,  3.31it/s]
 62%|██████▏   | 231255/371472 [7:46:26<11:32:03,  3.38it/s]
 62%|██████▏   | 231256/371472 [7:46:26<11:42:40,  3.33it/s]
 62%|██████▏   | 231257/371472 [7:46:26<11:32:17,  3.38it/s]
 62%|██████▏   | 231258/371472 [7:46:26<11:25:02,  3.41it/s]
 62%|██████▏   | 231259/371472 [7:46:27<11:08:06,  3.50it/s]
 62%|██████▏   | 231260/371472 [7:46:27<11:04:28,  3.52it/s]
                                                            
{'loss': 2.7323, 'learning_rate': 4.3988773729233553e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231260/371472 [7:46:27<11:04:28,  3.52it/s]
 62%|██████▏   | 231261/371472 [7:46:27<11:07:41,  3.50it/s]
 62%|██████▏   | 231262/371472 [7:46:28<11:43:31,  3.32it/s]
 62%|██████▏   | 231263/371472 [7:46:28<11:26:37,  3.40it/s]
 62%|██████▏   | 231264/371472 [7:46:28<11:38:22,  3.35it/s]
 62%|██████▏   | 231265/371472 [7:46:29<11:45:13,  3.31it/s]
 62%|██████▏   | 231266/371472 [7:46:29<11:19:53,  3.44it/s]
 62%|██████▏   | 231267/371472 [7:46:29<11:13:53,  3.47it/s]
 62%|██████▏   | 231268/371472 [7:46:30<16:42:26,  2.33it/s]
 62%|██████▏   | 231269/371472 [7:46:30<15:00:43,  2.59it/s]
 62%|██████▏   | 231270/371472 [7:46:30<13:48:52,  2.82it/s]
 62%|██████▏   | 231271/371472 [7:46:31<13:43:04,  2.84it/s]
 62%|██████▏   | 231272/371472 [7:46:31<12:41:34,  3.07it/s]
 62%|██████▏   | 231273/371472 [7:46:31<12:20:11,  3.16it/s]
 62%|██████▏   | 231274/371472 [7:46:32<12:38:58,  3.08it/s]
 62%|██████▏   | 231275/371472 [7:46:32<12:03:41,  3.23it/s]
 62%|██████▏   | 231276/371472 [7:46:32<11:57:11,  3.26it/s]
 62%|██████▏   | 231277/371472 [7:46:33<11:51:57,  3.28it/s]
 62%|██████▏   | 231278/371472 [7:46:33<11:18:02,  3.45it/s]
 62%|██████▏   | 231279/371472 [7:46:33<11:07:28,  3.50it/s]
 62%|██████▏   | 231280/371472 [7:46:33<11:14:49,  3.46it/s]
                                                            
{'loss': 2.7423, 'learning_rate': 4.3983925531685665e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231280/371472 [7:46:33<11:14:49,  3.46it/s]
 62%|██████▏   | 231281/371472 [7:46:34<11:14:42,  3.46it/s]
 62%|██████▏   | 231282/371472 [7:46:34<10:50:21,  3.59it/s]
 62%|██████▏   | 231283/371472 [7:46:34<11:29:41,  3.39it/s]
 62%|██████▏   | 231284/371472 [7:46:35<11:47:37,  3.30it/s]
 62%|██████▏   | 231285/371472 [7:46:35<11:19:50,  3.44it/s]
 62%|██████▏   | 231286/371472 [7:46:35<10:57:54,  3.55it/s]
 62%|██████▏   | 231287/371472 [7:46:36<12:15:50,  3.18it/s]
 62%|██████▏   | 231288/371472 [7:46:36<12:24:43,  3.14it/s]
 62%|██████▏   | 231289/371472 [7:46:36<11:38:31,  3.34it/s]
 62%|██████▏   | 231290/371472 [7:46:36<11:31:58,  3.38it/s]
 62%|██████▏   | 231291/371472 [7:46:37<11:40:50,  3.33it/s]
 62%|██████▏   | 231292/371472 [7:46:37<11:59:16,  3.25it/s]
 62%|██████▏   | 231293/371472 [7:46:37<12:14:03,  3.18it/s]
 62%|██████▏   | 231294/371472 [7:46:38<12:04:45,  3.22it/s]
 62%|██████▏   | 231295/371472 [7:46:38<12:42:15,  3.06it/s]
 62%|██████▏   | 231296/371472 [7:46:38<12:17:44,  3.17it/s]
 62%|██████▏   | 231297/371472 [7:46:39<12:19:34,  3.16it/s]
 62%|██████▏   | 231298/371472 [7:46:39<11:43:58,  3.32it/s]
 62%|██████▏   | 231299/371472 [7:46:39<11:37:24,  3.35it/s]
 62%|██████▏   | 231300/371472 [7:46:39<11:44:14,  3.32it/s]
                                                            
{'loss': 2.8942, 'learning_rate': 4.397907733413777e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231300/371472 [7:46:39<11:44:14,  3.32it/s]
 62%|██████▏   | 231301/371472 [7:46:40<11:46:54,  3.30it/s]
 62%|██████▏   | 231302/371472 [7:46:40<11:26:37,  3.40it/s]
 62%|██████▏   | 231303/371472 [7:46:40<11:26:29,  3.40it/s]
 62%|██████▏   | 231304/371472 [7:46:41<11:39:32,  3.34it/s]
 62%|██████▏   | 231305/371472 [7:46:41<11:19:31,  3.44it/s]
 62%|██████▏   | 231306/371472 [7:46:41<11:50:16,  3.29it/s]
 62%|██████▏   | 231307/371472 [7:46:42<11:48:36,  3.30it/s]
 62%|██████▏   | 231308/371472 [7:46:42<11:39:04,  3.34it/s]
 62%|██████▏   | 231309/371472 [7:46:42<11:35:49,  3.36it/s]
 62%|██████▏   | 231310/371472 [7:46:42<11:31:46,  3.38it/s]
 62%|██████▏   | 231311/371472 [7:46:43<11:22:44,  3.42it/s]
 62%|██████▏   | 231312/371472 [7:46:43<11:36:52,  3.35it/s]
 62%|██████▏   | 231313/371472 [7:46:43<11:43:22,  3.32it/s]
 62%|██████▏   | 231314/371472 [7:46:44<11:40:18,  3.34it/s]
 62%|██████▏   | 231315/371472 [7:46:44<11:28:04,  3.39it/s]
 62%|██████▏   | 231316/371472 [7:46:44<11:12:47,  3.47it/s]
 62%|██████▏   | 231317/371472 [7:46:45<12:15:44,  3.17it/s]
 62%|██████▏   | 231318/371472 [7:46:45<12:12:13,  3.19it/s]
 62%|██████▏   | 231319/371472 [7:46:45<12:45:04,  3.05it/s]
 62%|██████▏   | 231320/371472 [7:46:46<12:04:18,  3.22it/s]
                                                            
{'loss': 2.6899, 'learning_rate': 4.397422913658988e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231320/371472 [7:46:46<12:04:18,  3.22it/s]
 62%|██████▏   | 231321/371472 [7:46:46<11:55:54,  3.26it/s]
 62%|██████▏   | 231322/371472 [7:46:46<11:55:37,  3.26it/s]
 62%|██████▏   | 231323/371472 [7:46:46<11:40:57,  3.33it/s]
 62%|██████▏   | 231324/371472 [7:46:47<11:39:31,  3.34it/s]
 62%|██████▏   | 231325/371472 [7:46:47<11:58:30,  3.25it/s]
 62%|██████▏   | 231326/371472 [7:46:47<12:17:37,  3.17it/s]
 62%|██████▏   | 231327/371472 [7:46:48<11:56:25,  3.26it/s]
 62%|██████▏   | 231328/371472 [7:46:48<12:04:39,  3.22it/s]
 62%|██████▏   | 231329/371472 [7:46:48<11:38:04,  3.35it/s]
 62%|██████▏   | 231330/371472 [7:46:49<11:49:55,  3.29it/s]
 62%|██████▏   | 231331/371472 [7:46:49<12:15:33,  3.18it/s]
 62%|██████▏   | 231332/371472 [7:46:49<11:53:58,  3.27it/s]
 62%|██████▏   | 231333/371472 [7:46:50<11:59:21,  3.25it/s]
 62%|██████▏   | 231334/371472 [7:46:50<12:08:48,  3.20it/s]
 62%|██████▏   | 231335/371472 [7:46:50<12:54:10,  3.02it/s]
 62%|██████▏   | 231336/371472 [7:46:50<12:16:59,  3.17it/s]
 62%|██████▏   | 231337/371472 [7:46:51<13:22:55,  2.91it/s]
 62%|██████▏   | 231338/371472 [7:46:51<12:54:12,  3.02it/s]
 62%|██████▏   | 231339/371472 [7:46:52<12:43:40,  3.06it/s]
 62%|██████▏   | 231340/371472 [7:46:52<12:17:21,  3.17it/s]
                                                            
{'loss': 2.6318, 'learning_rate': 4.396938093904199e-07, 'epoch': 9.96}
+
 62%|██████▏   | 231340/371472 [7:46:52<12:17:21,  3.17it/s]
 62%|██████▏   | 231341/371472 [7:46:52<12:08:16,  3.21it/s]
 62%|██████▏   | 231342/371472 [7:46:52<11:48:34,  3.30it/s]
 62%|██████▏   | 231343/371472 [7:46:53<11:25:14,  3.41it/s]
 62%|██████▏   | 231344/371472 [7:46:53<11:14:24,  3.46it/s]
 62%|██████▏   | 231345/371472 [7:46:53<11:02:40,  3.52it/s]
 62%|██████▏   | 231346/371472 [7:46:53<10:49:55,  3.59it/s]
 62%|██████▏   | 231347/371472 [7:46:54<10:55:31,  3.56it/s]
 62%|██████▏   | 231348/371472 [7:46:54<10:50:41,  3.59it/s]
 62%|██████▏   | 231349/371472 [7:46:54<10:37:45,  3.66it/s]
 62%|██████▏   | 231350/371472 [7:46:55<11:15:52,  3.46it/s]
 62%|██████▏   | 231351/371472 [7:46:55<11:23:21,  3.42it/s]
 62%|██████▏   | 231352/371472 [7:46:55<11:09:22,  3.49it/s]
 62%|██████▏   | 231353/371472 [7:46:55<11:21:57,  3.42it/s]
 62%|██████▏   | 231354/371472 [7:46:56<11:15:07,  3.46it/s]
 62%|██████▏   | 231355/371472 [7:46:56<11:06:27,  3.50it/s]
 62%|██████▏   | 231356/371472 [7:46:56<11:54:22,  3.27it/s]
 62%|██████▏   | 231357/371472 [7:46:57<12:36:14,  3.09it/s]
 62%|██████▏   | 231358/371472 [7:46:57<13:15:37,  2.94it/s]
 62%|██████▏   | 231359/371472 [7:46:58<14:54:12,  2.61it/s]
 62%|██████▏   | 231360/371472 [7:46:58<13:34:05,  2.87it/s]
                                                            
{'loss': 2.7993, 'learning_rate': 4.39645327414941e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231360/371472 [7:46:58<13:34:05,  2.87it/s]
 62%|██████▏   | 231361/371472 [7:46:58<12:24:42,  3.14it/s]
 62%|██████▏   | 231362/371472 [7:46:58<12:01:12,  3.24it/s]
 62%|██████▏   | 231363/371472 [7:46:59<11:58:51,  3.25it/s]
 62%|██████▏   | 231364/371472 [7:46:59<12:04:01,  3.23it/s]
 62%|██████▏   | 231365/371472 [7:46:59<11:27:42,  3.40it/s]
 62%|██████▏   | 231366/371472 [7:47:00<11:35:12,  3.36it/s]
 62%|██████▏   | 231367/371472 [7:47:00<11:25:54,  3.40it/s]
 62%|██████▏   | 231368/371472 [7:47:00<11:16:40,  3.45it/s]
 62%|██████▏   | 231369/371472 [7:47:00<11:09:18,  3.49it/s]
 62%|██████▏   | 231370/371472 [7:47:01<11:15:12,  3.46it/s]
 62%|██████▏   | 231371/371472 [7:47:01<10:50:52,  3.59it/s]
 62%|██████▏   | 231372/371472 [7:47:01<10:32:36,  3.69it/s]
 62%|██████▏   | 231373/371472 [7:47:02<11:08:03,  3.50it/s]
 62%|██████▏   | 231374/371472 [7:47:02<12:08:08,  3.21it/s]
 62%|██████▏   | 231375/371472 [7:47:02<12:01:50,  3.23it/s]
 62%|██████▏   | 231376/371472 [7:47:03<11:31:05,  3.38it/s]
 62%|██████▏   | 231377/371472 [7:47:03<11:28:31,  3.39it/s]
 62%|██████▏   | 231378/371472 [7:47:03<13:18:21,  2.92it/s]
 62%|██████▏   | 231379/371472 [7:47:04<12:14:27,  3.18it/s]
 62%|██████▏   | 231380/371472 [7:47:04<11:42:11,  3.33it/s]
                                                            
{'loss': 2.8087, 'learning_rate': 4.3959684543946217e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231380/371472 [7:47:04<11:42:11,  3.33it/s]
 62%|██████▏   | 231381/371472 [7:47:04<11:35:21,  3.36it/s]
 62%|██████▏   | 231382/371472 [7:47:04<11:06:43,  3.50it/s]
 62%|██████▏   | 231383/371472 [7:47:05<10:48:16,  3.60it/s]
 62%|██████▏   | 231384/371472 [7:47:05<11:26:41,  3.40it/s]
 62%|██████▏   | 231385/371472 [7:47:05<11:20:12,  3.43it/s]
 62%|██████▏   | 231386/371472 [7:47:06<11:15:17,  3.46it/s]
 62%|██████▏   | 231387/371472 [7:47:06<13:18:28,  2.92it/s]
 62%|██████▏   | 231388/371472 [7:47:06<12:28:11,  3.12it/s]
 62%|██████▏   | 231389/371472 [7:47:07<12:45:19,  3.05it/s]
 62%|██████▏   | 231390/371472 [7:47:07<12:18:10,  3.16it/s]
 62%|██████▏   | 231391/371472 [7:47:07<12:25:56,  3.13it/s]
 62%|██████▏   | 231392/371472 [7:47:08<12:48:12,  3.04it/s]
 62%|██████▏   | 231393/371472 [7:47:08<12:20:23,  3.15it/s]
 62%|██████▏   | 231394/371472 [7:47:08<12:21:20,  3.15it/s]
 62%|██████▏   | 231395/371472 [7:47:09<12:58:00,  3.00it/s]
 62%|██████▏   | 231396/371472 [7:47:09<12:46:52,  3.04it/s]
 62%|██████▏   | 231397/371472 [7:47:09<12:11:33,  3.19it/s]
 62%|██████▏   | 231398/371472 [7:47:10<14:11:19,  2.74it/s]
 62%|██████▏   | 231399/371472 [7:47:10<13:14:23,  2.94it/s]
 62%|██████▏   | 231400/371472 [7:47:10<12:25:23,  3.13it/s]
                                                            
{'loss': 2.7006, 'learning_rate': 4.3954836346398324e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231400/371472 [7:47:10<12:25:23,  3.13it/s]
 62%|██████▏   | 231401/371472 [7:47:10<12:31:42,  3.11it/s]
 62%|██████▏   | 231402/371472 [7:47:11<12:22:02,  3.15it/s]
 62%|██████▏   | 231403/371472 [7:47:11<12:03:37,  3.23it/s]
 62%|██████▏   | 231404/371472 [7:47:11<12:00:04,  3.24it/s]
 62%|██████▏   | 231405/371472 [7:47:12<12:06:10,  3.21it/s]
 62%|██████▏   | 231406/371472 [7:47:12<12:09:41,  3.20it/s]
 62%|██████▏   | 231407/371472 [7:47:12<11:43:20,  3.32it/s]
 62%|██████▏   | 231408/371472 [7:47:13<11:16:35,  3.45it/s]
 62%|██████▏   | 231409/371472 [7:47:13<12:37:28,  3.08it/s]
 62%|██████▏   | 231410/371472 [7:47:13<12:23:04,  3.14it/s]
 62%|██████▏   | 231411/371472 [7:47:14<11:59:51,  3.24it/s]
 62%|██████▏   | 231412/371472 [7:47:14<11:41:35,  3.33it/s]
 62%|██████▏   | 231413/371472 [7:47:14<11:28:25,  3.39it/s]
 62%|██████▏   | 231414/371472 [7:47:14<11:13:20,  3.47it/s]
 62%|██████▏   | 231415/371472 [7:47:15<11:33:12,  3.37it/s]
 62%|██████▏   | 231416/371472 [7:47:15<11:12:57,  3.47it/s]
 62%|██████▏   | 231417/371472 [7:47:15<11:00:12,  3.54it/s]
 62%|██████▏   | 231418/371472 [7:47:16<11:24:50,  3.41it/s]
 62%|██████▏   | 231419/371472 [7:47:16<11:07:12,  3.50it/s]
 62%|██████▏   | 231420/371472 [7:47:16<11:28:01,  3.39it/s]
                                                            
{'loss': 2.7229, 'learning_rate': 4.3949988148850437e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231420/371472 [7:47:16<11:28:01,  3.39it/s]
 62%|██████▏   | 231421/371472 [7:47:16<11:37:28,  3.35it/s]
 62%|██████▏   | 231422/371472 [7:47:17<11:17:08,  3.45it/s]
 62%|██████▏   | 231423/371472 [7:47:17<11:39:24,  3.34it/s]
 62%|██████▏   | 231424/371472 [7:47:17<12:16:22,  3.17it/s]
 62%|██████▏   | 231425/371472 [7:47:18<11:47:14,  3.30it/s]
 62%|██████▏   | 231426/371472 [7:47:18<11:37:22,  3.35it/s]
 62%|██████▏   | 231427/371472 [7:47:18<11:10:40,  3.48it/s]
 62%|██████▏   | 231428/371472 [7:47:19<12:03:11,  3.23it/s]
 62%|██████▏   | 231429/371472 [7:47:19<11:50:31,  3.28it/s]
 62%|██████▏   | 231430/371472 [7:47:19<11:38:41,  3.34it/s]
 62%|██████▏   | 231431/371472 [7:47:19<11:28:28,  3.39it/s]
 62%|██████▏   | 231432/371472 [7:47:20<12:55:19,  3.01it/s]
 62%|██████▏   | 231433/371472 [7:47:20<12:34:25,  3.09it/s]
 62%|██████▏   | 231434/371472 [7:47:20<11:59:42,  3.24it/s]
 62%|██████▏   | 231435/371472 [7:47:21<11:52:53,  3.27it/s]
 62%|██████▏   | 231436/371472 [7:47:21<11:31:21,  3.38it/s]
 62%|██████▏   | 231437/371472 [7:47:21<11:32:30,  3.37it/s]
 62%|██████▏   | 231438/371472 [7:47:22<11:26:44,  3.40it/s]
 62%|██████▏   | 231439/371472 [7:47:22<11:52:21,  3.28it/s]
 62%|██████▏   | 231440/371472 [7:47:22<11:42:53,  3.32it/s]
                                                            
{'loss': 2.6935, 'learning_rate': 4.3945139951302544e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231440/371472 [7:47:22<11:42:53,  3.32it/s]
 62%|██████▏   | 231441/371472 [7:47:23<12:36:13,  3.09it/s]
 62%|██████▏   | 231442/371472 [7:47:23<11:56:17,  3.26it/s]
 62%|██████▏   | 231443/371472 [7:47:23<11:31:40,  3.37it/s]
 62%|██████▏   | 231444/371472 [7:47:23<11:14:10,  3.46it/s]
 62%|██████▏   | 231445/371472 [7:47:24<11:01:03,  3.53it/s]
 62%|██████▏   | 231446/371472 [7:47:24<10:52:28,  3.58it/s]
 62%|██████▏   | 231447/371472 [7:47:24<11:21:34,  3.42it/s]
 62%|██████▏   | 231448/371472 [7:47:25<11:13:12,  3.47it/s]
 62%|██████▏   | 231449/371472 [7:47:25<11:36:01,  3.35it/s]
 62%|██████▏   | 231450/371472 [7:47:25<11:08:57,  3.49it/s]
 62%|██████▏   | 231451/371472 [7:47:25<11:05:10,  3.51it/s]
 62%|██████▏   | 231452/371472 [7:47:26<11:29:12,  3.39it/s]
 62%|██████▏   | 231453/371472 [7:47:26<11:22:28,  3.42it/s]
 62%|██████▏   | 231454/371472 [7:47:26<11:05:52,  3.50it/s]
 62%|██████▏   | 231455/371472 [7:47:27<11:00:50,  3.53it/s]
 62%|██████▏   | 231456/371472 [7:47:27<11:36:27,  3.35it/s]
 62%|██████▏   | 231457/371472 [7:47:27<11:16:01,  3.45it/s]
 62%|██████▏   | 231458/371472 [7:47:27<11:34:05,  3.36it/s]
 62%|██████▏   | 231459/371472 [7:47:28<11:46:14,  3.30it/s]
 62%|██████▏   | 231460/371472 [7:47:28<12:10:07,  3.20it/s]
                                                            
{'loss': 2.8356, 'learning_rate': 4.394029175375466e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231460/371472 [7:47:28<12:10:07,  3.20it/s]
 62%|██████▏   | 231461/371472 [7:47:28<11:55:48,  3.26it/s]
 62%|██████▏   | 231462/371472 [7:47:29<11:44:31,  3.31it/s]
 62%|██████▏   | 231463/371472 [7:47:29<11:15:12,  3.46it/s]
 62%|██████▏   | 231464/371472 [7:47:29<11:05:20,  3.51it/s]
 62%|██████▏   | 231465/371472 [7:47:30<10:40:24,  3.64it/s]
 62%|██████▏   | 231466/371472 [7:47:30<10:38:36,  3.65it/s]
 62%|██████▏   | 231467/371472 [7:47:30<11:12:44,  3.47it/s]
 62%|██████▏   | 231468/371472 [7:47:30<10:50:26,  3.59it/s]
 62%|██████▏   | 231469/371472 [7:47:31<11:04:13,  3.51it/s]
 62%|██████▏   | 231470/371472 [7:47:31<11:36:21,  3.35it/s]
 62%|██████▏   | 231471/371472 [7:47:31<11:37:46,  3.34it/s]
 62%|██████▏   | 231472/371472 [7:47:32<12:19:09,  3.16it/s]
 62%|██████▏   | 231473/371472 [7:47:32<11:56:52,  3.25it/s]
 62%|██████▏   | 231474/371472 [7:47:32<11:24:52,  3.41it/s]
 62%|██████▏   | 231475/371472 [7:47:32<11:13:00,  3.47it/s]
 62%|██████▏   | 231476/371472 [7:47:33<11:40:06,  3.33it/s]
 62%|██████▏   | 231477/371472 [7:47:33<12:30:55,  3.11it/s]
 62%|██████▏   | 231478/371472 [7:47:33<11:50:26,  3.28it/s]
 62%|██████▏   | 231479/371472 [7:47:34<11:33:14,  3.37it/s]
 62%|██████▏   | 231480/371472 [7:47:34<11:33:51,  3.36it/s]
                                                            
{'loss': 2.8626, 'learning_rate': 4.3935443556206763e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231480/371472 [7:47:34<11:33:51,  3.36it/s]
 62%|██████▏   | 231481/371472 [7:47:34<11:33:05,  3.37it/s]
 62%|██████▏   | 231482/371472 [7:47:35<12:10:10,  3.20it/s]
 62%|██████▏   | 231483/371472 [7:47:35<12:09:11,  3.20it/s]
 62%|██████▏   | 231484/371472 [7:47:35<11:43:42,  3.32it/s]
 62%|██████▏   | 231485/371472 [7:47:36<11:29:30,  3.38it/s]
 62%|██████▏   | 231486/371472 [7:47:36<11:25:51,  3.40it/s]
 62%|██████▏   | 231487/371472 [7:47:36<11:29:39,  3.38it/s]
 62%|██████▏   | 231488/371472 [7:47:36<11:45:46,  3.31it/s]
 62%|██████▏   | 231489/371472 [7:47:37<12:57:52,  3.00it/s]
 62%|██████▏   | 231490/371472 [7:47:37<12:08:47,  3.20it/s]
 62%|██████▏   | 231491/371472 [7:47:37<12:19:50,  3.15it/s]
 62%|██████▏   | 231492/371472 [7:47:38<11:58:41,  3.25it/s]
 62%|██████▏   | 231493/371472 [7:47:38<11:25:20,  3.40it/s]
 62%|██████▏   | 231494/371472 [7:47:38<11:04:01,  3.51it/s]
 62%|██████▏   | 231495/371472 [7:47:39<11:07:54,  3.49it/s]
 62%|██████▏   | 231496/371472 [7:47:39<11:46:46,  3.30it/s]
 62%|██████▏   | 231497/371472 [7:47:39<11:29:34,  3.38it/s]
 62%|██████▏   | 231498/371472 [7:47:39<11:36:46,  3.35it/s]
 62%|██████▏   | 231499/371472 [7:47:40<11:12:26,  3.47it/s]
 62%|██████▏   | 231500/371472 [7:47:40<10:55:51,  3.56it/s]
                                                            
{'loss': 2.6645, 'learning_rate': 4.393059535865888e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231500/371472 [7:47:40<10:55:51,  3.56it/s]
 62%|██████▏   | 231501/371472 [7:47:40<12:36:53,  3.08it/s]
 62%|██████▏   | 231502/371472 [7:47:41<12:15:25,  3.17it/s]
 62%|██████▏   | 231503/371472 [7:47:41<12:49:39,  3.03it/s]
 62%|██████▏   | 231504/371472 [7:47:41<12:22:04,  3.14it/s]
 62%|██████▏   | 231505/371472 [7:47:42<12:20:07,  3.15it/s]
 62%|██████▏   | 231506/371472 [7:47:42<11:50:56,  3.28it/s]
 62%|██████▏   | 231507/371472 [7:47:42<11:24:13,  3.41it/s]
 62%|██████▏   | 231508/371472 [7:47:42<11:04:45,  3.51it/s]
 62%|██████▏   | 231509/371472 [7:47:43<10:58:01,  3.55it/s]
 62%|██████▏   | 231510/371472 [7:47:43<11:14:19,  3.46it/s]
 62%|██████▏   | 231511/371472 [7:47:43<11:24:51,  3.41it/s]
 62%|██████▏   | 231512/371472 [7:47:44<11:04:35,  3.51it/s]
 62%|██████▏   | 231513/371472 [7:47:44<11:22:32,  3.42it/s]
 62%|██████▏   | 231514/371472 [7:47:44<11:15:43,  3.45it/s]
 62%|██████▏   | 231515/371472 [7:47:45<11:14:16,  3.46it/s]
 62%|██████▏   | 231516/371472 [7:47:45<11:12:44,  3.47it/s]
 62%|██████▏   | 231517/371472 [7:47:45<11:04:50,  3.51it/s]
 62%|██████▏   | 231518/371472 [7:47:45<11:23:54,  3.41it/s]
 62%|██████▏   | 231519/371472 [7:47:46<11:25:08,  3.40it/s]
 62%|██████▏   | 231520/371472 [7:47:46<11:37:22,  3.34it/s]
                                                            
{'loss': 2.7563, 'learning_rate': 4.392574716111099e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231520/371472 [7:47:46<11:37:22,  3.34it/s]
 62%|██████▏   | 231521/371472 [7:47:46<11:28:29,  3.39it/s]
 62%|██████▏   | 231522/371472 [7:47:47<11:28:50,  3.39it/s]
 62%|██████▏   | 231523/371472 [7:47:47<11:28:48,  3.39it/s]
 62%|██████▏   | 231524/371472 [7:47:47<11:28:32,  3.39it/s]
 62%|██████▏   | 231525/371472 [7:47:47<11:31:14,  3.37it/s]
 62%|██████▏   | 231526/371472 [7:47:48<11:57:35,  3.25it/s]
 62%|██████▏   | 231527/371472 [7:47:48<11:38:46,  3.34it/s]
 62%|██████▏   | 231528/371472 [7:47:48<11:38:35,  3.34it/s]
 62%|██████▏   | 231529/371472 [7:47:49<11:36:07,  3.35it/s]
 62%|██████▏   | 231530/371472 [7:47:49<11:22:26,  3.42it/s]
 62%|██████▏   | 231531/371472 [7:47:49<11:11:57,  3.47it/s]
 62%|██████▏   | 231532/371472 [7:47:50<11:37:51,  3.34it/s]
 62%|██████▏   | 231533/371472 [7:47:50<11:36:41,  3.35it/s]
 62%|██████▏   | 231534/371472 [7:47:50<11:22:30,  3.42it/s]
 62%|██████▏   | 231535/371472 [7:47:50<11:13:04,  3.47it/s]
 62%|██████▏   | 231536/371472 [7:47:51<11:07:07,  3.50it/s]
 62%|██████▏   | 231537/371472 [7:47:51<11:19:14,  3.43it/s]
 62%|██████▏   | 231538/371472 [7:47:51<11:27:11,  3.39it/s]
 62%|██████▏   | 231539/371472 [7:47:52<11:22:37,  3.42it/s]
 62%|██████��   | 231540/371472 [7:47:52<12:06:22,  3.21it/s]
                                                            
{'loss': 2.7228, 'learning_rate': 4.39208989635631e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231540/371472 [7:47:52<12:06:22,  3.21it/s]
 62%|██████▏   | 231541/371472 [7:47:52<11:58:32,  3.25it/s]
 62%|██████▏   | 231542/371472 [7:47:53<11:25:57,  3.40it/s]
 62%|██████▏   | 231543/371472 [7:47:53<11:12:26,  3.47it/s]
 62%|██████▏   | 231544/371472 [7:47:53<11:03:30,  3.51it/s]
 62%|██████▏   | 231545/371472 [7:47:53<11:23:23,  3.41it/s]
 62%|██████▏   | 231546/371472 [7:47:54<11:53:59,  3.27it/s]
 62%|██████▏   | 231547/371472 [7:47:54<11:56:51,  3.25it/s]
 62%|██████▏   | 231548/371472 [7:47:54<11:42:12,  3.32it/s]
 62%|██████▏   | 231549/371472 [7:47:55<11:54:48,  3.26it/s]
 62%|██████▏   | 231550/371472 [7:47:55<11:56:36,  3.25it/s]
 62%|██████▏   | 231551/371472 [7:47:55<12:07:08,  3.21it/s]
 62%|██████▏   | 231552/371472 [7:47:56<11:43:02,  3.32it/s]
 62%|██████▏   | 231553/371472 [7:47:56<11:41:13,  3.33it/s]
 62%|██████▏   | 231554/371472 [7:47:56<11:08:44,  3.49it/s]
 62%|██████▏   | 231555/371472 [7:47:56<11:07:41,  3.49it/s]
 62%|██████▏   | 231556/371472 [7:47:57<11:46:55,  3.30it/s]
 62%|██████▏   | 231557/371472 [7:47:57<11:52:48,  3.27it/s]
 62%|██████▏   | 231558/371472 [7:47:57<11:31:25,  3.37it/s]
 62%|██████▏   | 231559/371472 [7:47:58<11:58:15,  3.25it/s]
 62%|██████▏   | 231560/371472 [7:47:58<11:41:16,  3.33it/s]
                                                            
{'loss': 2.7645, 'learning_rate': 4.391605076601521e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231560/371472 [7:47:58<11:41:16,  3.33it/s]
 62%|██████▏   | 231561/371472 [7:47:58<11:36:20,  3.35it/s]
 62%|██████▏   | 231562/371472 [7:47:59<11:32:13,  3.37it/s]
 62%|██████▏   | 231563/371472 [7:47:59<11:27:56,  3.39it/s]
 62%|██████▏   | 231564/371472 [7:47:59<11:49:59,  3.28it/s]
 62%|██████▏   | 231565/371472 [7:47:59<12:02:44,  3.23it/s]
 62%|██████▏   | 231566/371472 [7:48:00<12:02:17,  3.23it/s]
 62%|██████▏   | 231567/371472 [7:48:00<11:46:35,  3.30it/s]
 62%|██████▏   | 231568/371472 [7:48:00<12:12:05,  3.19it/s]
 62%|██████▏   | 231569/371472 [7:48:01<11:53:53,  3.27it/s]
 62%|██████▏   | 231570/371472 [7:48:01<12:13:54,  3.18it/s]
 62%|██████▏   | 231571/371472 [7:48:01<12:45:06,  3.05it/s]
 62%|██████▏   | 231572/371472 [7:48:02<12:13:21,  3.18it/s]
 62%|██████▏   | 231573/371472 [7:48:02<11:44:26,  3.31it/s]
 62%|██████▏   | 231574/371472 [7:48:02<12:10:10,  3.19it/s]
 62%|██████▏   | 231575/371472 [7:48:03<11:55:48,  3.26it/s]
 62%|██████▏   | 231576/371472 [7:48:03<11:41:46,  3.32it/s]
 62%|██████▏   | 231577/371472 [7:48:03<11:50:54,  3.28it/s]
 62%|██████▏   | 231578/371472 [7:48:03<11:46:19,  3.30it/s]
 62%|██████▏   | 231579/371472 [7:48:04<12:12:56,  3.18it/s]
 62%|██████▏   | 231580/371472 [7:48:04<11:51:16,  3.28it/s]
                                                            
{'loss': 2.7895, 'learning_rate': 4.3911202568467325e-07, 'epoch': 9.97}
+
 62%|██████▏   | 231580/371472 [7:48:04<11:51:16,  3.28it/s]
 62%|██████▏   | 231581/371472 [7:48:04<11:31:19,  3.37it/s]
 62%|██████▏   | 231582/371472 [7:48:05<11:08:04,  3.49it/s]
 62%|██████▏   | 231583/371472 [7:48:05<11:43:29,  3.31it/s]
 62%|██████▏   | 231584/371472 [7:48:05<11:37:13,  3.34it/s]
 62%|██████▏   | 231585/371472 [7:48:06<11:18:27,  3.44it/s]
 62%|██████▏   | 231586/371472 [7:48:06<10:56:57,  3.55it/s]
 62%|██████▏   | 231587/371472 [7:48:06<11:40:27,  3.33it/s]
 62%|██████▏   | 231588/371472 [7:48:06<11:29:17,  3.38it/s]
 62%|██████▏   | 231589/371472 [7:48:07<11:20:00,  3.43it/s]
 62%|██████▏   | 231590/371472 [7:48:07<11:14:44,  3.46it/s]
 62%|██████▏   | 231591/371472 [7:48:07<11:35:29,  3.35it/s]
 62%|██████▏   | 231592/371472 [7:48:08<12:05:35,  3.21it/s]
 62%|██████▏   | 231593/371472 [7:48:08<11:55:12,  3.26it/s]
 62%|██████▏   | 231594/371472 [7:48:08<11:51:57,  3.27it/s]
 62%|██████▏   | 231595/371472 [7:48:09<11:34:34,  3.36it/s]
 62%|██████▏   | 231596/371472 [7:48:09<11:24:52,  3.40it/s]
 62%|██████▏   | 231597/371472 [7:48:09<11:13:24,  3.46it/s]
 62%|██████▏   | 231598/371472 [7:48:09<11:08:47,  3.49it/s]
 62%|██████▏   | 231599/371472 [7:48:10<11:15:50,  3.45it/s]
 62%|███���██▏   | 231600/371472 [7:48:10<11:00:49,  3.53it/s]
                                                            
{'loss': 2.75, 'learning_rate': 4.3906354370919427e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231600/371472 [7:48:10<11:00:49,  3.53it/s]
 62%|██████▏   | 231601/371472 [7:48:10<10:55:15,  3.56it/s]
 62%|██████▏   | 231602/371472 [7:48:11<11:13:34,  3.46it/s]
 62%|██████▏   | 231603/371472 [7:48:11<11:19:51,  3.43it/s]
 62%|██████▏   | 231604/371472 [7:48:11<11:06:13,  3.50it/s]
 62%|██████▏   | 231605/371472 [7:48:11<11:45:43,  3.30it/s]
 62%|██████▏   | 231606/371472 [7:48:12<11:42:27,  3.32it/s]
 62%|██████▏   | 231607/371472 [7:48:12<11:29:20,  3.38it/s]
 62%|██████▏   | 231608/371472 [7:48:12<11:11:11,  3.47it/s]
 62%|██████▏   | 231609/371472 [7:48:13<10:50:08,  3.59it/s]
 62%|██████▏   | 231610/371472 [7:48:13<10:33:53,  3.68it/s]
 62%|██████▏   | 231611/371472 [7:48:13<10:29:39,  3.70it/s]
 62%|██████▏   | 231612/371472 [7:48:13<11:00:26,  3.53it/s]
 62%|██████▏   | 231613/371472 [7:48:14<11:00:18,  3.53it/s]
 62%|██████▏   | 231614/371472 [7:48:14<11:35:55,  3.35it/s]
 62%|██████▏   | 231615/371472 [7:48:14<11:19:03,  3.43it/s]
 62%|██████▏   | 231616/371472 [7:48:15<11:16:06,  3.45it/s]
 62%|██████▏   | 231617/371472 [7:48:15<11:40:25,  3.33it/s]
 62%|██████▏   | 231618/371472 [7:48:15<11:19:23,  3.43it/s]
 62%|██████▏   | 231619/371472 [7:48:15<12:04:55,  3.22it/s]
 62%|██████▏   | 231620/371472 [7:48:16<12:00:38,  3.23it/s]
                                                            
{'loss': 2.7876, 'learning_rate': 4.3901506173371545e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231620/371472 [7:48:16<12:00:38,  3.23it/s]
 62%|██████▏   | 231621/371472 [7:48:16<12:07:54,  3.20it/s]
 62%|██████▏   | 231622/371472 [7:48:16<11:53:47,  3.27it/s]
 62%|██████▏   | 231623/371472 [7:48:17<12:00:12,  3.24it/s]
 62%|██████▏   | 231624/371472 [7:48:17<11:30:19,  3.38it/s]
 62%|██████▏   | 231625/371472 [7:48:17<11:20:19,  3.43it/s]
 62%|██████▏   | 231626/371472 [7:48:18<11:32:12,  3.37it/s]
 62%|██████▏   | 231627/371472 [7:48:18<11:28:43,  3.38it/s]
 62%|██████▏   | 231628/371472 [7:48:18<11:01:41,  3.52it/s]
 62%|██████▏   | 231629/371472 [7:48:18<11:02:23,  3.52it/s]
 62%|██████▏   | 231630/371472 [7:48:19<11:32:47,  3.36it/s]
 62%|██████▏   | 231631/371472 [7:48:19<11:09:19,  3.48it/s]
 62%|██████▏   | 231632/371472 [7:48:19<10:55:36,  3.55it/s]
 62%|██████▏   | 231633/371472 [7:48:20<10:45:46,  3.61it/s]
 62%|██████▏   | 231634/371472 [7:48:20<10:55:20,  3.56it/s]
 62%|██████▏   | 231635/371472 [7:48:20<10:55:37,  3.55it/s]
 62%|██████▏   | 231636/371472 [7:48:20<10:51:54,  3.58it/s]
 62%|██████▏   | 231637/371472 [7:48:21<10:49:02,  3.59it/s]
 62%|██████▏   | 231638/371472 [7:48:21<10:58:55,  3.54it/s]
 62%|██████▏   | 231639/371472 [7:48:21<11:44:45,  3.31it/s]
 62%|██████▏   | 231640/371472 [7:48:22<11:32:54,  3.36it/s]
                                                            
{'loss': 2.5934, 'learning_rate': 4.389665797582365e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231640/371472 [7:48:22<11:32:54,  3.36it/s]
 62%|██████▏   | 231641/371472 [7:48:22<11:35:09,  3.35it/s]
 62%|██████▏   | 231642/371472 [7:48:22<11:45:40,  3.30it/s]
 62%|██████▏   | 231643/371472 [7:48:22<11:12:53,  3.46it/s]
 62%|██████▏   | 231644/371472 [7:48:23<11:13:18,  3.46it/s]
 62%|██████▏   | 231645/371472 [7:48:23<11:27:13,  3.39it/s]
 62%|██████▏   | 231646/371472 [7:48:23<11:18:41,  3.43it/s]
 62%|██████▏   | 231647/371472 [7:48:24<11:10:50,  3.47it/s]
 62%|██████▏   | 231648/371472 [7:48:24<11:17:20,  3.44it/s]
 62%|██████▏   | 231649/371472 [7:48:24<10:57:09,  3.55it/s]
 62%|██████▏   | 231650/371472 [7:48:25<11:24:13,  3.41it/s]
 62%|██████▏   | 231651/371472 [7:48:25<11:32:22,  3.37it/s]
 62%|██████▏   | 231652/371472 [7:48:25<11:15:06,  3.45it/s]
 62%|██████▏   | 231653/371472 [7:48:25<11:14:28,  3.45it/s]
 62%|██████▏   | 231654/371472 [7:48:26<11:36:36,  3.35it/s]
 62%|██████▏   | 231655/371472 [7:48:26<11:16:26,  3.44it/s]
 62%|██████▏   | 231656/371472 [7:48:26<11:07:49,  3.49it/s]
 62%|██████▏   | 231657/371472 [7:48:27<11:44:24,  3.31it/s]
 62%|██████▏   | 231658/371472 [7:48:27<12:00:19,  3.24it/s]
 62%|██████▏   | 231659/371472 [7:48:27<11:56:06,  3.25it/s]
 62%|██████▏   | 231660/371472 [7:48:28<11:48:17,  3.29it/s]
                                                            
{'loss': 2.8632, 'learning_rate': 4.3891809778275765e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231660/371472 [7:48:28<11:48:17,  3.29it/s]
 62%|██████▏   | 231661/371472 [7:48:28<11:32:59,  3.36it/s]
 62%|██████▏   | 231662/371472 [7:48:28<11:06:11,  3.50it/s]
 62%|██████▏   | 231663/371472 [7:48:28<10:43:05,  3.62it/s]
 62%|██████▏   | 231664/371472 [7:48:29<10:41:30,  3.63it/s]
 62%|██████▏   | 231665/371472 [7:48:29<11:03:10,  3.51it/s]
 62%|██████▏   | 231666/371472 [7:48:29<11:37:50,  3.34it/s]
 62%|██████▏   | 231667/371472 [7:48:30<11:29:15,  3.38it/s]
 62%|██████▏   | 231668/371472 [7:48:30<11:11:09,  3.47it/s]
 62%|██████▏   | 231669/371472 [7:48:30<10:52:12,  3.57it/s]
 62%|██████▏   | 231670/371472 [7:48:30<11:19:04,  3.43it/s]
 62%|██████▏   | 231671/371472 [7:48:31<11:13:22,  3.46it/s]
 62%|██████▏   | 231672/371472 [7:48:31<11:08:06,  3.49it/s]
 62%|██████▏   | 231673/371472 [7:48:31<11:02:29,  3.52it/s]
 62%|██████▏   | 231674/371472 [7:48:31<11:12:44,  3.46it/s]
 62%|██████▏   | 231675/371472 [7:48:32<12:17:09,  3.16it/s]
 62%|██████▏   | 231676/371472 [7:48:32<11:53:41,  3.26it/s]
 62%|██████▏   | 231677/371472 [7:48:32<11:38:55,  3.33it/s]
 62%|██████▏   | 231678/371472 [7:48:33<11:34:03,  3.36it/s]
 62%|██████▏   | 231679/371472 [7:48:33<11:31:18,  3.37it/s]
 62%|██████▏   | 231680/371472 [7:48:33<11:34:51,  3.35it/s]
                                                            
{'loss': 2.6887, 'learning_rate': 4.388696158072787e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231680/371472 [7:48:33<11:34:51,  3.35it/s]
 62%|██████▏   | 231681/371472 [7:48:34<11:24:28,  3.40it/s]
 62%|██████▏   | 231682/371472 [7:48:34<11:16:58,  3.44it/s]
 62%|██████▏   | 231683/371472 [7:48:34<10:57:18,  3.54it/s]
 62%|██████▏   | 231684/371472 [7:48:34<10:45:12,  3.61it/s]
 62%|██████▏   | 231685/371472 [7:48:35<10:56:10,  3.55it/s]
 62%|██████▏   | 231686/371472 [7:48:35<10:32:10,  3.69it/s]
 62%|██████▏   | 231687/371472 [7:48:35<11:02:28,  3.52it/s]
 62%|██████▏   | 231688/371472 [7:48:36<10:48:02,  3.60it/s]
 62%|██████▏   | 231689/371472 [7:48:36<11:53:57,  3.26it/s]
 62%|██████▏   | 231690/371472 [7:48:36<12:10:45,  3.19it/s]
 62%|██████▏   | 231691/371472 [7:48:37<11:58:27,  3.24it/s]
 62%|██████▏   | 231692/371472 [7:48:37<11:38:49,  3.33it/s]
 62%|██████▏   | 231693/371472 [7:48:37<11:19:18,  3.43it/s]
 62%|██████▏   | 231694/371472 [7:48:37<11:54:54,  3.26it/s]
 62%|██████▏   | 231695/371472 [7:48:38<12:09:30,  3.19it/s]
 62%|██████▏   | 231696/371472 [7:48:38<11:48:11,  3.29it/s]
 62%|██████▏   | 231697/371472 [7:48:38<11:44:56,  3.30it/s]
 62%|██████▏   | 231698/371472 [7:48:39<11:33:31,  3.36it/s]
 62%|██████▏   | 231699/371472 [7:48:39<11:28:53,  3.38it/s]
 62%|██████▏   | 231700/371472 [7:48:39<11:47:10,  3.29it/s]
                                                            
{'loss': 2.7499, 'learning_rate': 4.388211338317999e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231700/371472 [7:48:39<11:47:10,  3.29it/s]
 62%|██████▏   | 231701/371472 [7:48:40<11:31:13,  3.37it/s]
 62%|██████▏   | 231702/371472 [7:48:40<11:19:52,  3.43it/s]
 62%|██████▏   | 231703/371472 [7:48:40<11:11:08,  3.47it/s]
 62%|██████▏   | 231704/371472 [7:48:40<10:59:30,  3.53it/s]
 62%|██████▏   | 231705/371472 [7:48:41<10:50:50,  3.58it/s]
 62%|██████▏   | 231706/371472 [7:48:41<10:39:04,  3.65it/s]
 62%|██████▏   | 231707/371472 [7:48:41<10:35:28,  3.67it/s]
 62%|██████▏   | 231708/371472 [7:48:41<11:19:03,  3.43it/s]
 62%|██████▏   | 231709/371472 [7:48:42<12:20:58,  3.14it/s]
 62%|██████▏   | 231710/371472 [7:48:42<11:41:21,  3.32it/s]
 62%|██████▏   | 231711/371472 [7:48:42<11:21:20,  3.42it/s]
 62%|██████▏   | 231712/371472 [7:48:43<11:05:08,  3.50it/s]
 62%|██████▏   | 231713/371472 [7:48:43<11:27:32,  3.39it/s]
 62%|██████▏   | 231714/371472 [7:48:43<11:06:02,  3.50it/s]
 62%|██████▏   | 231715/371472 [7:48:44<11:12:51,  3.46it/s]
 62%|██████▏   | 231716/371472 [7:48:44<10:49:53,  3.58it/s]
 62%|██████▏   | 231717/371472 [7:48:44<11:30:05,  3.38it/s]
 62%|██████▏   | 231718/371472 [7:48:44<11:37:09,  3.34it/s]
 62%|██████▏   | 231719/371472 [7:48:45<11:24:20,  3.40it/s]
 62%|██████▏   | 231720/371472 [7:48:45<10:55:04,  3.56it/s]
                                                            
{'loss': 2.7217, 'learning_rate': 4.3877265185632097e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231720/371472 [7:48:45<10:55:04,  3.56it/s]
 62%|██████▏   | 231721/371472 [7:48:45<10:50:03,  3.58it/s]
 62%|██████▏   | 231722/371472 [7:48:46<11:44:33,  3.31it/s]
 62%|██████▏   | 231723/371472 [7:48:46<11:26:54,  3.39it/s]
 62%|██████▏   | 231724/371472 [7:48:46<11:21:00,  3.42it/s]
 62%|██████▏   | 231725/371472 [7:48:46<11:07:48,  3.49it/s]
 62%|██████▏   | 231726/371472 [7:48:47<11:06:40,  3.49it/s]
 62%|██████▏   | 231727/371472 [7:48:47<11:34:07,  3.36it/s]
 62%|██████▏   | 231728/371472 [7:48:47<11:40:18,  3.33it/s]
 62%|██████▏   | 231729/371472 [7:48:48<11:47:19,  3.29it/s]
 62%|██████▏   | 231730/371472 [7:48:48<11:29:56,  3.38it/s]
 62%|██████▏   | 231731/371472 [7:48:48<11:10:21,  3.47it/s]
 62%|██████▏   | 231732/371472 [7:48:49<11:13:23,  3.46it/s]
 62%|██████▏   | 231733/371472 [7:48:49<11:21:56,  3.42it/s]
 62%|██████▏   | 231734/371472 [7:48:49<11:01:34,  3.52it/s]
 62%|██████▏   | 231735/371472 [7:48:49<11:51:38,  3.27it/s]
 62%|██████▏   | 231736/371472 [7:48:50<11:36:21,  3.34it/s]
 62%|██████▏   | 231737/371472 [7:48:50<11:26:18,  3.39it/s]
 62%|██████▏   | 231738/371472 [7:48:50<10:56:40,  3.55it/s]
 62%|██████▏   | 231739/371472 [7:48:51<11:05:50,  3.50it/s]
 62%|██████▏   | 231740/371472 [7:48:51<10:49:47,  3.58it/s]
                                                            
{'loss': 2.64, 'learning_rate': 4.387241698808421e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231740/371472 [7:48:51<10:49:47,  3.58it/s]
 62%|██████▏   | 231741/371472 [7:48:51<10:40:01,  3.64it/s]
 62%|██████▏   | 231742/371472 [7:48:51<10:42:30,  3.62it/s]
 62%|██████▏   | 231743/371472 [7:48:52<12:13:58,  3.17it/s]
 62%|██████▏   | 231744/371472 [7:48:52<12:15:16,  3.17it/s]
 62%|██████▏   | 231745/371472 [7:48:52<12:21:02,  3.14it/s]
 62%|██████▏   | 231746/371472 [7:48:53<12:25:13,  3.12it/s]
 62%|██████▏   | 231747/371472 [7:48:53<11:44:36,  3.30it/s]
 62%|██████▏   | 231748/371472 [7:48:53<11:24:29,  3.40it/s]
 62%|██████▏   | 231749/371472 [7:48:54<11:43:37,  3.31it/s]
 62%|██████▏   | 231750/371472 [7:48:54<11:44:01,  3.31it/s]
 62%|██████▏   | 231751/371472 [7:48:54<12:20:21,  3.15it/s]
 62%|██████▏   | 231752/371472 [7:48:55<12:09:46,  3.19it/s]
 62%|██████▏   | 231753/371472 [7:48:55<11:45:55,  3.30it/s]
 62%|██████▏   | 231754/371472 [7:48:55<11:48:26,  3.29it/s]
 62%|██████▏   | 231755/371472 [7:48:55<11:30:54,  3.37it/s]
 62%|██████▏   | 231756/371472 [7:48:56<11:07:50,  3.49it/s]
 62%|██████▏   | 231757/371472 [7:48:56<11:11:45,  3.47it/s]
 62%|██████▏   | 231758/371472 [7:48:56<11:19:42,  3.43it/s]
 62%|██████▏   | 231759/371472 [7:48:57<11:01:02,  3.52it/s]
 62%|██████▏   | 231760/371472 [7:48:57<10:38:46,  3.65it/s]
                                                            
{'loss': 2.6802, 'learning_rate': 4.386756879053632e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231760/371472 [7:48:57<10:38:46,  3.65it/s]
 62%|██████▏   | 231761/371472 [7:48:57<10:51:11,  3.58it/s]
 62%|██████▏   | 231762/371472 [7:48:57<10:57:10,  3.54it/s]
 62%|██████▏   | 231763/371472 [7:48:58<11:38:00,  3.34it/s]
 62%|██████▏   | 231764/371472 [7:48:58<11:14:29,  3.45it/s]
 62%|██████▏   | 231765/371472 [7:48:58<11:10:29,  3.47it/s]
 62%|██████▏   | 231766/371472 [7:48:59<10:59:52,  3.53it/s]
 62%|██████▏   | 231767/371472 [7:48:59<11:20:18,  3.42it/s]
 62%|██████▏   | 231768/371472 [7:48:59<11:53:13,  3.26it/s]
 62%|██████▏   | 231769/371472 [7:48:59<11:33:08,  3.36it/s]
 62%|██████▏   | 231770/371472 [7:49:00<11:21:13,  3.42it/s]
 62%|██████▏   | 231771/371472 [7:49:00<11:07:50,  3.49it/s]
 62%|██████▏   | 231772/371472 [7:49:00<11:07:13,  3.49it/s]
 62%|██████▏   | 231773/371472 [7:49:01<12:14:00,  3.17it/s]
 62%|██████▏   | 231774/371472 [7:49:01<11:53:15,  3.26it/s]
 62%|██████▏   | 231775/371472 [7:49:01<11:28:49,  3.38it/s]
 62%|██████▏   | 231776/371472 [7:49:02<12:08:50,  3.19it/s]
 62%|██████▏   | 231777/371472 [7:49:02<12:14:09,  3.17it/s]
 62%|██████▏   | 231778/371472 [7:49:02<11:56:35,  3.25it/s]
 62%|██████▏   | 231779/371472 [7:49:02<11:28:43,  3.38it/s]
 62%|██████▏   | 231780/371472 [7:49:03<11:11:49,  3.47it/s]
                                                            
{'loss': 2.7785, 'learning_rate': 4.3862720592988434e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231780/371472 [7:49:03<11:11:49,  3.47it/s]
 62%|██████▏   | 231781/371472 [7:49:03<11:11:14,  3.47it/s]
 62%|██████▏   | 231782/371472 [7:49:03<11:08:43,  3.48it/s]
 62%|██████▏   | 231783/371472 [7:49:04<11:00:01,  3.53it/s]
 62%|██████▏   | 231784/371472 [7:49:04<10:45:22,  3.61it/s]
 62%|██████▏   | 231785/371472 [7:49:04<10:29:10,  3.70it/s]
 62%|██████▏   | 231786/371472 [7:49:04<10:33:58,  3.67it/s]
 62%|██████▏   | 231787/371472 [7:49:05<10:34:21,  3.67it/s]
 62%|██████▏   | 231788/371472 [7:49:05<10:32:53,  3.68it/s]
 62%|██████▏   | 231789/371472 [7:49:05<10:35:09,  3.67it/s]
 62%|██████▏   | 231790/371472 [7:49:06<11:38:22,  3.33it/s]
 62%|██████▏   | 231791/371472 [7:49:06<11:48:14,  3.29it/s]
 62%|██████▏   | 231792/371472 [7:49:06<11:48:14,  3.29it/s]
 62%|██████▏   | 231793/371472 [7:49:07<11:58:50,  3.24it/s]
 62%|██████▏   | 231794/371472 [7:49:07<11:31:41,  3.37it/s]
 62%|██████▏   | 231795/371472 [7:49:07<11:26:16,  3.39it/s]
 62%|██████▏   | 231796/371472 [7:49:07<12:02:10,  3.22it/s]
 62%|██████▏   | 231797/371472 [7:49:08<11:52:18,  3.27it/s]
 62%|██████▏   | 231798/371472 [7:49:08<11:57:58,  3.24it/s]
 62%|██████▏   | 231799/371472 [7:49:08<11:43:58,  3.31it/s]
 62%|██████▏   | 231800/371472 [7:49:09<11:33:06,  3.36it/s]
                                                            
{'loss': 2.7331, 'learning_rate': 4.3857872395440536e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231800/371472 [7:49:09<11:33:06,  3.36it/s]
 62%|██████▏   | 231801/371472 [7:49:09<11:23:14,  3.41it/s]
 62%|██████▏   | 231802/371472 [7:49:09<11:14:25,  3.45it/s]
 62%|██████▏   | 231803/371472 [7:49:09<10:55:19,  3.55it/s]
 62%|██████▏   | 231804/371472 [7:49:10<10:49:34,  3.58it/s]
 62%|██████▏   | 231805/371472 [7:49:10<11:29:53,  3.37it/s]
 62%|██████▏   | 231806/371472 [7:49:10<12:06:10,  3.21it/s]
 62%|██████▏   | 231807/371472 [7:49:11<11:30:16,  3.37it/s]
 62%|██████▏   | 231808/371472 [7:49:11<12:05:49,  3.21it/s]
 62%|██████▏   | 231809/371472 [7:49:11<11:52:28,  3.27it/s]
 62%|██████▏   | 231810/371472 [7:49:12<11:40:33,  3.32it/s]
 62%|██████▏   | 231811/371472 [7:49:12<11:42:38,  3.31it/s]
 62%|██████▏   | 231812/371472 [7:49:12<11:43:43,  3.31it/s]
 62%|██████▏   | 231813/371472 [7:49:12<11:44:49,  3.30it/s]
 62%|██████▏   | 231814/371472 [7:49:13<11:47:28,  3.29it/s]
 62%|██████▏   | 231815/371472 [7:49:13<12:12:26,  3.18it/s]
 62%|██████▏   | 231816/371472 [7:49:13<11:52:24,  3.27it/s]
 62%|██████▏   | 231817/371472 [7:49:14<11:43:02,  3.31it/s]
 62%|██████▏   | 231818/371472 [7:49:14<11:51:26,  3.27it/s]
 62%|██████▏   | 231819/371472 [7:49:14<11:30:55,  3.37it/s]
 62%|██████▏   | 231820/371472 [7:49:15<11:21:45,  3.41it/s]
                                                            
{'loss': 2.6514, 'learning_rate': 4.3853024197892654e-07, 'epoch': 9.98}
+
 62%|██████▏   | 231820/371472 [7:49:15<11:21:45,  3.41it/s]
 62%|██████▏   | 231821/371472 [7:49:15<11:21:10,  3.42it/s]
 62%|██████▏   | 231822/371472 [7:49:15<11:22:21,  3.41it/s]
 62%|██████▏   | 231823/371472 [7:49:15<11:09:03,  3.48it/s]
 62%|██████▏   | 231824/371472 [7:49:16<11:35:50,  3.34it/s]
 62%|██████▏   | 231825/371472 [7:49:16<12:39:49,  3.06it/s]
 62%|██████▏   | 231826/371472 [7:49:16<12:08:49,  3.19it/s]
 62%|██████▏   | 231827/371472 [7:49:17<11:41:38,  3.32it/s]
 62%|██████▏   | 231828/371472 [7:49:17<11:11:55,  3.46it/s]
 62%|██████▏   | 231829/371472 [7:49:17<11:19:05,  3.43it/s]
 62%|██████▏   | 231830/371472 [7:49:18<12:30:54,  3.10it/s]
 62%|██████▏   | 231831/371472 [7:49:18<12:09:21,  3.19it/s]
 62%|██████▏   | 231832/371472 [7:49:18<11:39:08,  3.33it/s]
 62%|██████▏   | 231833/371472 [7:49:19<12:18:01,  3.15it/s]
 62%|██████▏   | 231834/371472 [7:49:19<12:01:59,  3.22it/s]
 62%|██████▏   | 231835/371472 [7:49:19<11:35:45,  3.34it/s]
 62%|██████▏   | 231836/371472 [7:49:19<12:03:23,  3.22it/s]
 62%|██████▏   | 231837/371472 [7:49:20<11:30:07,  3.37it/s]
 62%|██████▏   | 231838/371472 [7:49:20<11:45:23,  3.30it/s]
 62%|██████▏   | 231839/371472 [7:49:20<11:52:56,  3.26it/s]
 62%|██████▏   | 231840/371472 [7:49:21<11:34:47,  3.35it/s]
                                                            
{'loss': 2.8064, 'learning_rate': 4.384817600034476e-07, 'epoch': 9.99}
+
 62%|██████▏   | 231840/371472 [7:49:21<11:34:47,  3.35it/s]
 62%|██████▏   | 231841/371472 [7:49:21<11:37:27,  3.34it/s]
 62%|██████▏   | 231842/371472 [7:49:21<11:35:07,  3.35it/s]
 62%|██████▏   | 231843/371472 [7:49:22<11:54:15,  3.26it/s]
 62%|██████▏   | 231844/371472 [7:49:22<11:39:45,  3.33it/s]
 62%|██████▏   | 231845/371472 [7:49:22<11:42:32,  3.31it/s]
 62%|██████▏   | 231846/371472 [7:49:22<11:20:39,  3.42it/s]
 62%|██████▏   | 231847/371472 [7:49:23<11:24:44,  3.40it/s]
 62%|██████▏   | 231848/371472 [7:49:23<11:09:47,  3.47it/s]
 62%|██████▏   | 231849/371472 [7:49:23<11:13:31,  3.46it/s]
 62%|██████▏   | 231850/371472 [7:49:24<11:08:56,  3.48it/s]
 62%|██████▏   | 231851/371472 [7:49:24<11:02:40,  3.51it/s]
 62%|██████▏   | 231852/371472 [7:49:24<10:44:21,  3.61it/s]
 62%|██████▏   | 231853/371472 [7:49:24<10:51:40,  3.57it/s]
 62%|██████▏   | 231854/371472 [7:49:25<10:57:53,  3.54it/s]
 62%|██████▏   | 231855/371472 [7:49:25<11:11:09,  3.47it/s]
 62%|██████▏   | 231856/371472 [7:49:25<11:28:49,  3.38it/s]
 62%|██████▏   | 231857/371472 [7:49:26<11:37:03,  3.34it/s]
 62%|██████▏   | 231858/371472 [7:49:26<11:32:20,  3.36it/s]
 62%|██████▏   | 231859/371472 [7:49:26<11:30:27,  3.37it/s]
 62%|██████▏   | 231860/371472 [7:49:27<11:35:42,  3.34it/s]
                                                            
{'loss': 2.5903, 'learning_rate': 4.384332780279686e-07, 'epoch': 9.99}
+
 62%|██████▏   | 231860/371472 [7:49:27<11:35:42,  3.34it/s]
 62%|██████▏   | 231861/371472 [7:49:27<11:18:05,  3.43it/s]
 62%|██████▏   | 231862/371472 [7:49:27<12:29:56,  3.10it/s]
 62%|██████▏   | 231863/371472 [7:49:28<12:28:53,  3.11it/s]
 62%|██████▏   | 231864/371472 [7:49:28<11:44:46,  3.30it/s]
 62%|██████▏   | 231865/371472 [7:49:28<11:18:34,  3.43it/s]
 62%|██████▏   | 231866/371472 [7:49:28<11:01:23,  3.52it/s]
 62%|██████▏   | 231867/371472 [7:49:29<11:30:33,  3.37it/s]
 62%|██████▏   | 231868/371472 [7:49:29<11:12:43,  3.46it/s]
 62%|██████▏   | 231869/371472 [7:49:29<11:18:30,  3.43it/s]
 62%|██████▏   | 231870/371472 [7:49:30<11:19:44,  3.42it/s]
 62%|██████▏   | 231871/371472 [7:49:30<11:41:45,  3.32it/s]
 62%|██████▏   | 231872/371472 [7:49:30<11:53:26,  3.26it/s]
 62%|██████▏   | 231873/371472 [7:49:30<11:37:08,  3.34it/s]
 62%|██████▏   | 231874/371472 [7:49:31<13:20:33,  2.91it/s]
 62%|██████▏   | 231875/371472 [7:49:31<13:01:19,  2.98it/s]
 62%|██████▏   | 231876/371472 [7:49:31<12:18:23,  3.15it/s]
 62%|██████▏   | 231877/371472 [7:49:32<12:22:40,  3.13it/s]
 62%|██████▏   | 231878/371472 [7:49:32<11:50:32,  3.27it/s]
 62%|██████▏   | 231879/371472 [7:49:32<11:27:28,  3.38it/s]
 62%|██████▏   | 231880/371472 [7:49:33<11:10:48,  3.47it/s]
                                                            
{'loss': 2.7847, 'learning_rate': 4.383847960524898e-07, 'epoch': 9.99}
+
 62%|██████▏   | 231880/371472 [7:49:33<11:10:48,  3.47it/s]
 62%|██████▏   | 231881/371472 [7:49:33<11:43:51,  3.31it/s]
 62%|██████▏   | 231882/371472 [7:49:33<11:35:15,  3.35it/s]
 62%|██████▏   | 231883/371472 [7:49:34<11:19:52,  3.42it/s]
 62%|██████▏   | 231884/371472 [7:49:34<11:30:39,  3.37it/s]
 62%|██████▏   | 231885/371472 [7:49:34<11:26:25,  3.39it/s]
 62%|██████▏   | 231886/371472 [7:49:34<11:13:19,  3.46it/s]
 62%|██████▏   | 231887/371472 [7:49:35<11:17:55,  3.43it/s]
 62%|██████▏   | 231888/371472 [7:49:35<11:12:19,  3.46it/s]
 62%|██████▏   | 231889/371472 [7:49:35<10:56:12,  3.55it/s]
 62%|██████▏   | 231890/371472 [7:49:36<10:58:00,  3.54it/s]
 62%|██████▏   | 231891/371472 [7:49:36<10:41:44,  3.63it/s]
 62%|██████▏   | 231892/371472 [7:49:36<10:37:37,  3.65it/s]
 62%|██████▏   | 231893/371472 [7:49:36<11:11:04,  3.47it/s]
 62%|██████▏   | 231894/371472 [7:49:37<11:45:13,  3.30it/s]
 62%|██████▏   | 231895/371472 [7:49:37<11:57:14,  3.24it/s]
 62%|██████▏   | 231896/371472 [7:49:37<11:50:22,  3.27it/s]
 62%|██████▏   | 231897/371472 [7:49:38<12:22:42,  3.13it/s]
 62%|██████▏   | 231898/371472 [7:49:38<12:36:16,  3.08it/s]
 62%|██████▏   | 231899/371472 [7:49:38<12:14:48,  3.17it/s]
 62%|██████▏   | 231900/371472 [7:49:39<11:39:26,  3.33it/s]
                                                            
{'loss': 2.7971, 'learning_rate': 4.383363140770109e-07, 'epoch': 9.99}
+
 62%|██████▏   | 231900/371472 [7:49:39<11:39:26,  3.33it/s]
 62%|██████▏   | 231901/371472 [7:49:39<11:56:27,  3.25it/s]
 62%|██████▏   | 231902/371472 [7:49:39<12:29:54,  3.10it/s]
 62%|██████▏   | 231903/371472 [7:49:40<12:18:05,  3.15it/s]
 62%|██████▏   | 231904/371472 [7:49:40<11:53:56,  3.26it/s]
 62%|██████▏   | 231905/371472 [7:49:40<12:17:13,  3.16it/s]
 62%|██████▏   | 231906/371472 [7:49:40<11:41:44,  3.31it/s]
 62%|██████▏   | 231907/371472 [7:49:41<11:19:44,  3.42it/s]
 62%|██████▏   | 231908/371472 [7:49:41<10:52:40,  3.56it/s]
 62%|██████▏   | 231909/371472 [7:49:41<12:13:20,  3.17it/s]
 62%|██████▏   | 231910/371472 [7:49:42<11:59:46,  3.23it/s]
 62%|██████▏   | 231911/371472 [7:49:42<11:54:31,  3.26it/s]
 62%|██████▏   | 231912/371472 [7:49:42<11:54:08,  3.26it/s]
 62%|██████▏   | 231913/371472 [7:49:43<11:44:43,  3.30it/s]
 62%|██████▏   | 231914/371472 [7:49:43<12:05:17,  3.21it/s]
 62%|██████▏   | 231915/371472 [7:49:43<11:35:04,  3.35it/s]
 62%|██████▏   | 231916/371472 [7:49:43<11:22:14,  3.41it/s]
 62%|██████▏   | 231917/371472 [7:49:44<12:01:24,  3.22it/s]
 62%|██████▏   | 231918/371472 [7:49:44<11:38:29,  3.33it/s]
 62%|██████▏   | 231919/371472 [7:49:44<11:49:44,  3.28it/s]
 62%|██████▏   | 231920/371472 [7:49:45<11:17:07,  3.43it/s]
                                                            
{'loss': 2.9441, 'learning_rate': 4.38287832101532e-07, 'epoch': 9.99}
+
 62%|██████▏   | 231920/371472 [7:49:45<11:17:07,  3.43it/s]
 62%|██████▏   | 231921/371472 [7:49:45<11:09:04,  3.48it/s]
 62%|██████▏   | 231922/371472 [7:49:45<11:08:08,  3.48it/s]
 62%|██████▏   | 231923/371472 [7:49:45<10:55:11,  3.55it/s]
 62%|██████▏   | 231924/371472 [7:49:46<10:46:32,  3.60it/s]
 62%|██████▏   | 231925/371472 [7:49:46<11:17:36,  3.43it/s]
 62%|██████▏   | 231926/371472 [7:49:46<11:47:45,  3.29it/s]
 62%|██████▏   | 231927/371472 [7:49:47<11:52:14,  3.27it/s]
 62%|██████▏   | 231928/371472 [7:49:47<11:42:47,  3.31it/s]
 62%|██████▏   | 231929/371472 [7:49:47<11:48:51,  3.28it/s]
 62%|██████▏   | 231930/371472 [7:49:48<11:55:03,  3.25it/s]
 62%|██████▏   | 231931/371472 [7:49:48<11:24:47,  3.40it/s]
 62%|██████▏   | 231932/371472 [7:49:48<11:25:45,  3.39it/s]
 62%|██████▏   | 231933/371472 [7:49:48<11:14:06,  3.45it/s]
 62%|██████▏   | 231934/371472 [7:49:49<11:09:16,  3.47it/s]
 62%|██████▏   | 231935/371472 [7:49:49<11:36:59,  3.34it/s]
 62%|██████▏   | 231936/371472 [7:49:49<11:24:16,  3.40it/s]
 62%|██████▏   | 231937/371472 [7:49:50<11:49:00,  3.28it/s]
 62%|██████▏   | 231938/371472 [7:49:50<11:38:59,  3.33it/s]
 62%|██████▏   | 231939/371472 [7:49:50<11:22:34,  3.41it/s]
 62%|██████▏   | 231940/371472 [7:49:51<11:34:10,  3.35it/s]
                                                            
{'loss': 2.6663, 'learning_rate': 4.3823935012605307e-07, 'epoch': 9.99}
+
 62%|██████▏   | 231940/371472 [7:49:51<11:34:10,  3.35it/s]
 62%|██████▏   | 231941/371472 [7:49:51<12:46:28,  3.03it/s]
 62%|██████▏   | 231942/371472 [7:49:51<12:06:30,  3.20it/s]
 62%|██████▏   | 231943/371472 [7:49:52<12:11:08,  3.18it/s]
 62%|██████▏   | 231944/371472 [7:49:52<11:34:19,  3.35it/s]
 62%|██████▏   | 231945/371472 [7:49:52<11:07:39,  3.48it/s]
 62%|██████▏   | 231946/371472 [7:49:52<11:08:55,  3.48it/s]
 62%|██████▏   | 231947/371472 [7:49:53<11:01:38,  3.51it/s]
 62%|██████▏   | 231948/371472 [7:49:53<10:58:53,  3.53it/s]
 62%|██████▏   | 231949/371472 [7:49:53<10:58:02,  3.53it/s]
 62%|██████▏   | 231950/371472 [7:49:53<10:44:26,  3.61it/s]
 62%|██████▏   | 231951/371472 [7:49:54<10:43:10,  3.62it/s]
 62%|██████▏   | 231952/371472 [7:49:54<11:00:28,  3.52it/s]
 62%|██████▏   | 231953/371472 [7:49:54<10:57:48,  3.53it/s]
 62%|██████▏   | 231954/371472 [7:49:55<11:00:51,  3.52it/s]
 62%|██████▏   | 231955/371472 [7:49:55<10:46:14,  3.60it/s]
 62%|██████▏   | 231956/371472 [7:49:55<11:08:50,  3.48it/s]
 62%|██████▏   | 231957/371472 [7:49:56<11:35:18,  3.34it/s]
 62%|██████▏   | 231958/371472 [7:49:56<11:25:22,  3.39it/s]
 62%|██████▏   | 231959/371472 [7:49:56<11:10:40,  3.47it/s]
 62%|██████▏   | 231960/371472 [7:49:56<10:57:44,  3.54it/s]
                                                            
{'loss': 2.7285, 'learning_rate': 4.3819086815057425e-07, 'epoch': 9.99}
+
 62%|██████▏   | 231960/371472 [7:49:56<10:57:44,  3.54it/s]
 62%|██████▏   | 231961/371472 [7:49:57<10:54:03,  3.56it/s]
 62%|██████▏   | 231962/371472 [7:49:57<11:16:20,  3.44it/s]
 62%|██████▏   | 231963/371472 [7:49:57<11:03:36,  3.50it/s]
 62%|██████▏   | 231964/371472 [7:49:58<11:25:25,  3.39it/s]
 62%|██████▏   | 231965/371472 [7:49:58<13:20:19,  2.91it/s]
 62%|██████▏   | 231966/371472 [7:49:58<12:14:52,  3.16it/s]
 62%|██████▏   | 231967/371472 [7:49:59<11:57:45,  3.24it/s]
 62%|██████▏   | 231968/371472 [7:49:59<11:33:34,  3.35it/s]
 62%|██████▏   | 231969/371472 [7:49:59<12:06:10,  3.20it/s]
 62%|██████▏   | 231970/371472 [7:49:59<11:54:26,  3.25it/s]
 62%|██████▏   | 231971/371472 [7:50:00<11:52:52,  3.26it/s]
 62%|██████▏   | 231972/371472 [7:50:00<11:48:58,  3.28it/s]
 62%|██████▏   | 231973/371472 [7:50:00<11:34:12,  3.35it/s]
 62%|██████▏   | 231974/371472 [7:50:01<11:16:33,  3.44it/s]
 62%|██████▏   | 231975/371472 [7:50:01<11:21:22,  3.41it/s]
 62%|██████▏   | 231976/371472 [7:50:01<10:56:34,  3.54it/s]
 62%|██████▏   | 231977/371472 [7:50:01<10:45:13,  3.60it/s]
 62%|██████▏   | 231978/371472 [7:50:02<10:42:42,  3.62it/s]
 62%|██████▏   | 231979/371472 [7:50:02<10:58:18,  3.53it/s]
 62%|██████▏   | 231980/371472 [7:50:02<10:53:47,  3.56it/s]
                                                            
{'loss': 2.6635, 'learning_rate': 4.3814238617509527e-07, 'epoch': 9.99}
+
 62%|██████▏   | 231980/371472 [7:50:02<10:53:47,  3.56it/s]
 62%|██████▏   | 231981/371472 [7:50:03<11:02:37,  3.51it/s]
 62%|██████▏   | 231982/371472 [7:50:03<11:00:48,  3.52it/s]
 62%|██████▏   | 231983/371472 [7:50:03<10:58:12,  3.53it/s]
 62%|██████▏   | 231984/371472 [7:50:03<10:53:26,  3.56it/s]
 62%|██████▏   | 231985/371472 [7:50:04<11:20:45,  3.41it/s]
 62%|██████▏   | 231986/371472 [7:50:04<11:09:39,  3.47it/s]
 62%|██████▏   | 231987/371472 [7:50:04<11:44:45,  3.30it/s]
 62%|██████▏   | 231988/371472 [7:50:05<12:15:25,  3.16it/s]
 62%|██████▏   | 231989/371472 [7:50:05<11:59:32,  3.23it/s]
 62%|██████▏   | 231990/371472 [7:50:05<11:38:42,  3.33it/s]
 62%|██████▏   | 231991/371472 [7:50:06<11:23:05,  3.40it/s]
 62%|██████▏   | 231992/371472 [7:50:06<11:07:22,  3.48it/s]
 62%|██████▏   | 231993/371472 [7:50:06<10:44:23,  3.61it/s]
 62%|██████▏   | 231994/371472 [7:50:06<10:40:03,  3.63it/s]
 62%|██████▏   | 231995/371472 [7:50:07<11:05:41,  3.49it/s]
 62%|██████▏   | 231996/371472 [7:50:07<10:49:23,  3.58it/s]
 62%|██████▏   | 231997/371472 [7:50:07<10:32:23,  3.68it/s]
 62%|██████▏   | 231998/371472 [7:50:07<10:38:04,  3.64it/s]
 62%|██████▏   | 231999/371472 [7:50:08<10:38:47,  3.64it/s]
 62%|██████▏   | 232000/371472 [7:50:08<10:39:41,  3.63it/s]
                                                            
{'loss': 2.7147, 'learning_rate': 4.3809390419961644e-07, 'epoch': 9.99}
+
 62%|██████▏   | 232000/371472 [7:50:08<10:39:41,  3.63it/s]
 62%|██████▏   | 232001/371472 [7:50:08<10:38:51,  3.64it/s]
 62%|██████▏   | 232002/371472 [7:50:09<10:37:06,  3.65it/s]
 62%|██████▏   | 232003/371472 [7:50:09<10:45:52,  3.60it/s]
 62%|██████▏   | 232004/371472 [7:50:09<10:50:07,  3.58it/s]
 62%|██████▏   | 232005/371472 [7:50:09<11:24:26,  3.40it/s]
 62%|██████▏   | 232006/371472 [7:50:10<11:23:49,  3.40it/s]
 62%|██████▏   | 232007/371472 [7:50:10<11:28:17,  3.38it/s]
 62%|██████▏   | 232008/371472 [7:50:10<11:17:06,  3.43it/s]
 62%|██████▏   | 232009/371472 [7:50:11<11:25:53,  3.39it/s]
 62%|██████▏   | 232010/371472 [7:50:11<11:09:51,  3.47it/s]
 62%|██████▏   | 232011/371472 [7:50:11<11:05:02,  3.50it/s]
 62%|██████▏   | 232012/371472 [7:50:12<11:21:58,  3.41it/s]
 62%|██████▏   | 232013/371472 [7:50:12<11:09:40,  3.47it/s]
 62%|██████▏   | 232014/371472 [7:50:12<11:29:10,  3.37it/s]
 62%|██████▏   | 232015/371472 [7:50:12<11:12:27,  3.46it/s]
 62%|██████▏   | 232016/371472 [7:50:13<11:05:52,  3.49it/s]
 62%|██████▏   | 232017/371472 [7:50:13<10:59:48,  3.52it/s]
 62%|██████▏   | 232018/371472 [7:50:13<11:36:48,  3.34it/s]
 62%|██████▏   | 232019/371472 [7:50:14<12:15:03,  3.16it/s]
 62%|██████▏   | 232020/371472 [7:50:14<11:38:29,  3.33it/s]
                                                            
{'loss': 2.808, 'learning_rate': 4.380454222241375e-07, 'epoch': 9.99}
+
 62%|██████▏   | 232020/371472 [7:50:14<11:38:29,  3.33it/s]
 62%|██████▏   | 232021/371472 [7:50:14<11:17:31,  3.43it/s]
 62%|██████▏   | 232022/371472 [7:50:14<11:42:31,  3.31it/s]
 62%|██████▏   | 232023/371472 [7:50:15<11:39:09,  3.32it/s]
 62%|██████▏   | 232024/371472 [7:50:15<11:11:37,  3.46it/s]
 62%|██████▏   | 232025/371472 [7:50:15<11:33:42,  3.35it/s]
 62%|██████▏   | 232026/371472 [7:50:16<11:41:42,  3.31it/s]
 62%|██████▏   | 232027/371472 [7:50:16<11:55:16,  3.25it/s]
 62%|██████▏   | 232028/371472 [7:50:16<11:18:58,  3.42it/s]
 62%|██████▏   | 232029/371472 [7:50:17<11:05:46,  3.49it/s]
 62%|██████▏   | 232030/371472 [7:50:17<10:55:46,  3.54it/s]
 62%|██████▏   | 232031/371472 [7:50:17<10:58:55,  3.53it/s]
 62%|██████▏   | 232032/371472 [7:50:17<11:15:07,  3.44it/s]
 62%|██████▏   | 232033/371472 [7:50:18<11:03:32,  3.50it/s]
 62%|██████▏   | 232034/371472 [7:50:18<11:03:39,  3.50it/s]
 62%|██████▏   | 232035/371472 [7:50:18<10:39:30,  3.63it/s]
 62%|██████▏   | 232036/371472 [7:50:18<10:42:00,  3.62it/s]
 62%|██████▏   | 232037/371472 [7:50:19<11:13:31,  3.45it/s]
 62%|██████▏   | 232038/371472 [7:50:19<11:21:18,  3.41it/s]
 62%|██████▏   | 232039/371472 [7:50:19<11:07:43,  3.48it/s]
 62%|██████▏   | 232040/371472 [7:50:20<11:18:26,  3.43it/s]
                                                            
{'loss': 2.8795, 'learning_rate': 4.3799694024865864e-07, 'epoch': 9.99}
+
 62%|██████▏   | 232040/371472 [7:50:20<11:18:26,  3.43it/s]
 62%|██████▏   | 232041/371472 [7:50:20<11:06:05,  3.49it/s]
 62%|██████▏   | 232042/371472 [7:50:20<11:43:51,  3.30it/s]
 62%|██████▏   | 232043/371472 [7:50:21<11:16:39,  3.43it/s]
 62%|██████▏   | 232044/371472 [7:50:21<11:42:25,  3.31it/s]
 62%|██████▏   | 232045/371472 [7:50:21<11:33:30,  3.35it/s]
 62%|██████▏   | 232046/371472 [7:50:22<12:49:17,  3.02it/s]
 62%|██████▏   | 232047/371472 [7:50:22<12:14:34,  3.16it/s]
 62%|██████▏   | 232048/371472 [7:50:22<11:51:29,  3.27it/s]
 62%|██████▏   | 232049/371472 [7:50:22<11:52:03,  3.26it/s]
 62%|██████▏   | 232050/371472 [7:50:23<11:43:23,  3.30it/s]
 62%|██████▏   | 232051/371472 [7:50:23<11:36:57,  3.33it/s]
 62%|██████▏   | 232052/371472 [7:50:23<12:06:35,  3.20it/s]
 62%|██████▏   | 232053/371472 [7:50:24<11:46:23,  3.29it/s]
 62%|██████▏   | 232054/371472 [7:50:24<11:53:11,  3.26it/s]
 62%|██████▏   | 232055/371472 [7:50:24<12:05:18,  3.20it/s]
 62%|██████▏   | 232056/371472 [7:50:25<11:39:07,  3.32it/s]
 62%|██████▏   | 232057/371472 [7:50:25<11:19:19,  3.42it/s]
 62%|██████▏   | 232058/371472 [7:50:25<12:28:38,  3.10it/s]
 62%|██████▏   | 232059/371472 [7:50:26<12:25:44,  3.12it/s]
 62%|██████▏   | 232060/371472 [7:50:26<11:59:33,  3.23it/s]
                                                            
{'loss': 2.7803, 'learning_rate': 4.379484582731797e-07, 'epoch': 10.0}
+
 62%|██████▏   | 232060/371472 [7:50:26<11:59:33,  3.23it/s]
 62%|██████▏   | 232061/371472 [7:50:26<12:12:51,  3.17it/s]
 62%|██████▏   | 232062/371472 [7:50:26<12:11:15,  3.18it/s]
 62%|██████▏   | 232063/371472 [7:50:27<11:51:49,  3.26it/s]
 62%|██████▏   | 232064/371472 [7:50:27<11:58:10,  3.24it/s]
 62%|██████▏   | 232065/371472 [7:50:27<11:42:49,  3.31it/s]
 62%|██████▏   | 232066/371472 [7:50:28<11:55:06,  3.25it/s]
 62%|██████▏   | 232067/371472 [7:50:28<11:50:34,  3.27it/s]
 62%|██████▏   | 232068/371472 [7:50:28<11:17:00,  3.43it/s]
 62%|██████▏   | 232069/371472 [7:50:29<12:02:52,  3.21it/s]
 62%|██████▏   | 232070/371472 [7:50:29<12:06:56,  3.20it/s]
 62%|██████▏   | 232071/371472 [7:50:29<11:41:01,  3.31it/s]
 62%|██████▏   | 232072/371472 [7:50:30<11:43:20,  3.30it/s]
 62%|██████▏   | 232073/371472 [7:50:30<12:47:28,  3.03it/s]
 62%|██████▏   | 232074/371472 [7:50:30<12:54:40,  3.00it/s]
 62%|██████▏   | 232075/371472 [7:50:31<13:28:22,  2.87it/s]
 62%|██████▏   | 232076/371472 [7:50:31<12:33:19,  3.08it/s]
 62%|██████▏   | 232077/371472 [7:50:31<12:01:17,  3.22it/s]
 62%|██████▏   | 232078/371472 [7:50:31<12:15:37,  3.16it/s]
 62%|██████▏   | 232079/371472 [7:50:32<11:49:09,  3.28it/s]
 62%|██████▏   | 232080/371472 [7:50:32<12:06:32,  3.20it/s]
                                                            
{'loss': 2.7404, 'learning_rate': 4.378999762977009e-07, 'epoch': 10.0}
+
 62%|██████▏   | 232080/371472 [7:50:32<12:06:32,  3.20it/s]
 62%|██████▏   | 232081/371472 [7:50:32<12:03:35,  3.21it/s]
 62%|██████▏   | 232082/371472 [7:50:33<11:40:44,  3.32it/s]
 62%|██████▏   | 232083/371472 [7:50:33<12:20:10,  3.14it/s]
 62%|██████▏   | 232084/371472 [7:50:33<11:50:14,  3.27it/s]
 62%|██████▏   | 232085/371472 [7:50:34<11:32:34,  3.35it/s]
 62%|██████▏   | 232086/371472 [7:50:34<11:14:49,  3.44it/s]
 62%|██████▏   | 232087/371472 [7:50:34<10:53:31,  3.55it/s]
 62%|██████▏   | 232088/371472 [7:50:35<12:11:26,  3.18it/s]
 62%|██████▏   | 232089/371472 [7:50:35<11:39:54,  3.32it/s]
 62%|██████▏   | 232090/371472 [7:50:35<13:05:03,  2.96it/s]
 62%|██████▏   | 232091/371472 [7:50:36<12:37:13,  3.07it/s]
 62%|██████▏   | 232092/371472 [7:50:36<12:17:09,  3.15it/s]
 62%|██████▏   | 232093/371472 [7:50:36<11:54:50,  3.25it/s]
 62%|██████▏   | 232094/371472 [7:50:36<12:36:03,  3.07it/s]
 62%|██████▏   | 232095/371472 [7:50:37<11:59:04,  3.23it/s]
 62%|██████▏   | 232096/371472 [7:50:37<11:38:01,  3.33it/s]
 62%|██████▏   | 232097/371472 [7:50:37<11:31:33,  3.36it/s]
 62%|██████▏   | 232098/371472 [7:50:38<11:30:17,  3.37it/s]
 62%|██████▏   | 232099/371472 [7:50:38<12:42:27,  3.05it/s]
 62%|██████▏   | 232100/371472 [7:50:38<12:41:20,  3.05it/s]
                                                            
{'loss': 2.8107, 'learning_rate': 4.3785149432222196e-07, 'epoch': 10.0}
+
 62%|██████▏   | 232100/371472 [7:50:38<12:41:20,  3.05it/s]
 62%|██████▏   | 232101/371472 [7:50:39<11:55:29,  3.25it/s]
 62%|██████▏   | 232102/371472 [7:50:39<11:33:35,  3.35it/s]
 62%|██████▏   | 232103/371472 [7:50:39<11:09:12,  3.47it/s]
 62%|██████▏   | 232104/371472 [7:50:39<11:07:04,  3.48it/s]
 62%|██████▏   | 232105/371472 [7:50:40<12:15:05,  3.16it/s]
 62%|██████▏   | 232106/371472 [7:50:40<12:53:44,  3.00it/s]
 62%|██████▏   | 232107/371472 [7:50:41<12:51:02,  3.01it/s]
 62%|██████▏   | 232108/371472 [7:50:41<12:50:02,  3.02it/s]
 62%|██████▏   | 232109/371472 [7:50:41<12:16:45,  3.15it/s]
 62%|██████▏   | 232110/371472 [7:50:41<12:02:23,  3.22it/s]
 62%|██████▏   | 232111/371472 [7:50:42<11:47:55,  3.28it/s]
 62%|██████▏   | 232112/371472 [7:50:42<11:15:01,  3.44it/s]
 62%|██████▏   | 232113/371472 [7:50:42<11:13:25,  3.45it/s]
 62%|██████▏   | 232114/371472 [7:50:43<11:05:53,  3.49it/s]
 62%|██████▏   | 232115/371472 [7:50:43<11:17:16,  3.43it/s]
 62%|██████▏   | 232116/371472 [7:50:43<12:03:19,  3.21it/s]
 62%|██████▏   | 232117/371472 [7:50:43<11:28:53,  3.37it/s]
 62%|██████▏   | 232118/371472 [7:50:44<11:56:40,  3.24it/s]
 62%|██████▏   | 232119/371472 [7:50:44<11:28:29,  3.37it/s]
 62%|██████▏   | 232120/371472 [7:50:44<12:56:26,  2.99it/s]
                                                            
{'loss': 2.8, 'learning_rate': 4.378030123467431e-07, 'epoch': 10.0}
+
 62%|██████▏   | 232120/371472 [7:50:44<12:56:26,  2.99it/s]
 62%|██████▏   | 232121/371472 [7:50:45<12:50:34,  3.01it/s]
 62%|██████▏   | 232122/371472 [7:50:45<12:53:47,  3.00it/s]
 62%|██████▏   | 232123/371472 [7:50:45<12:09:37,  3.18it/s]
 62%|██████▏   | 232124/371472 [7:50:46<11:45:09,  3.29it/s]
 62%|██████▏   | 232125/371472 [7:50:46<11:15:05,  3.44it/s]
 62%|██████▏   | 232126/371472 [7:50:46<11:28:10,  3.37it/s]
 62%|██████▏   | 232127/371472 [7:50:47<11:17:04,  3.43it/s]
 62%|██████▏   | 232128/371472 [7:50:47<12:02:43,  3.21it/s]
 62%|██████▏   | 232129/371472 [7:50:47<11:38:41,  3.32it/s]
 62%|██████▏   | 232130/371472 [7:50:48<12:08:48,  3.19it/s]
 62%|██████▏   | 232131/371472 [7:50:48<12:01:52,  3.22it/s]
 62%|██████▏   | 232132/371472 [7:50:48<11:49:48,  3.27it/s]
 62%|██████▏   | 232133/371472 [7:50:48<11:53:36,  3.25it/s]
 62%|██████▏   | 232134/371472 [7:50:49<11:58:34,  3.23it/s]
 62%|██████▏   | 232135/371472 [7:50:49<13:02:13,  2.97it/s]
 62%|██████▏   | 232136/371472 [7:50:50<13:10:53,  2.94it/s]
 62%|██████▏   | 232137/371472 [7:50:50<12:34:45,  3.08it/s]
 62%|██████▏   | 232138/371472 [7:50:50<11:54:28,  3.25it/s]
 62%|██████▏   | 232139/371472 [7:50:50<11:19:13,  3.42it/s]
 62%|██████▏   | 232140/371472 [7:50:51<11:22:03,  3.40it/s]
                                                            
{'loss': 2.71, 'learning_rate': 4.3775453037126416e-07, 'epoch': 10.0}
+
 62%|██████▏   | 232140/371472 [7:50:51<11:22:03,  3.40it/s]
 62%|██████▏   | 232141/371472 [7:50:51<11:11:43,  3.46it/s]
 62%|██████▏   | 232142/371472 [7:50:51<11:28:27,  3.37it/s]
 62%|██████▏   | 232143/371472 [7:50:51<11:21:39,  3.41it/s]
 62%|██████▏   | 232144/371472 [7:50:52<11:24:23,  3.39it/s]
 62%|██████▏   | 232145/371472 [7:50:52<11:38:19,  3.33it/s]
 62%|██████▏   | 232146/371472 [7:50:52<11:30:00,  3.37it/s]
 62%|██████▏   | 232147/371472 [7:50:53<11:41:22,  3.31it/s]
 62%|██████▏   | 232148/371472 [7:50:53<11:36:16,  3.34it/s]
 62%|██████▏   | 232149/371472 [7:50:53<11:31:49,  3.36it/s]
 62%|██████▏   | 232150/371472 [7:50:54<11:49:43,  3.27it/s]
 62%|██████▏   | 232151/371472 [7:50:54<11:25:31,  3.39it/s]
 62%|██████▏   | 232152/371472 [7:50:54<11:00:53,  3.51it/s]
 62%|██████▏   | 232153/371472 [7:50:54<11:34:39,  3.34it/s]
 62%|██████▏   | 232154/371472 [7:50:55<11:09:02,  3.47it/s]
 62%|██████▏   | 232155/371472 [7:50:55<11:33:13,  3.35it/s]
 62%|██████▏   | 232156/371472 [7:50:55<11:23:20,  3.40it/s]
 62%|██████▏   | 232157/371472 [7:50:56<11:17:42,  3.43it/s]
 62%|██████▏   | 232158/371472 [7:50:56<11:09:16,  3.47it/s]
 62%|██████▏   | 232159/371472 [7:50:56<11:13:43,  3.45it/s]
 62%|██████▏   | 232160/371472 [7:50:56<11:08:52,  3.47it/s]
                                                            
{'loss': 2.729, 'learning_rate': 4.3770604839578533e-07, 'epoch': 10.0}
+
 62%|██████▏   | 232160/371472 [7:50:56<11:08:52,  3.47it/s]
 62%|██████▏   | 232161/371472 [7:50:57<11:09:31,  3.47it/s]
 62%|██████▏   | 232162/371472 [7:50:57<10:50:20,  3.57it/s]
 62%|██████▏   | 232163/371472 [7:50:57<10:56:24,  3.54it/s]
 62%|██████▏   | 232164/371472 [7:50:58<11:01:42,  3.51it/s]
 62%|██████▏   | 232165/371472 [7:50:58<10:49:02,  3.58it/s]
 62%|██████▏   | 232166/371472 [7:50:58<10:54:52,  3.55it/s]
 62%|██████▏   | 232167/371472 [7:50:58<11:20:59,  3.41it/s]
 62%|██████▏   | 232168/371472 [7:50:59<11:05:30,  3.49it/s]
 62%|██████▏   | 232169/371472 [7:50:59<11:04:00,  3.50it/s]
 62%|██████▎   | 232170/371472 [7:50:59<11:30:57,  3.36it/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()
+
 63%|██████▎   | 232171/371472 [7:51:30<364:14:43,  9.41s/it]
 63%|██████▎   | 232172/371472 [7:51:30<258:36:42,  6.68s/it]
 63%|██████▎   | 232173/371472 [7:51:31<184:38:21,  4.77s/it]
 63%|██████▎   | 232174/371472 [7:51:31<132:33:56,  3.43s/it]
 63%|██████▎   | 232175/371472 [7:51:31<96:38:33,  2.50s/it] 
 63%|██████▎   | 232176/371472 [7:51:32<72:03:50,  1.86s/it]
 63%|██████▎   | 232177/371472 [7:51:32<53:35:30,  1.39s/it]
 63%|██████▎   | 232178/371472 [7:51:32<40:49:47,  1.06s/it]
 63%|██████▎   | 232179/371472 [7:51:33<31:57:05,  1.21it/s]
 63%|██████▎   | 232180/371472 [7:51:33<25:48:11,  1.50it/s]
                                                            
{'loss': 2.8009, 'learning_rate': 4.376575664203064e-07, 'epoch': 10.0}
+
 63%|██████▎   | 232180/371472 [7:51:33<25:48:11,  1.50it/s]
 63%|██████▎   | 232181/371472 [7:51:33<21:27:59,  1.80it/s]
 63%|██████▎   | 232182/371472 [7:51:33<18:24:27,  2.10it/s]
 63%|██████▎   | 232183/371472 [7:51:34<16:21:29,  2.37it/s]
 63%|██████▎   | 232184/371472 [7:51:34<15:22:41,  2.52it/s]
 63%|██████▎   | 232185/371472 [7:51:34<14:53:05,  2.60it/s]
 63%|██████▎   | 232186/371472 [7:51:35<14:44:11,  2.63it/s]
 63%|██████▎   | 232187/371472 [7:51:35<14:56:31,  2.59it/s]
 63%|██████▎   | 232188/371472 [7:51:36<14:33:29,  2.66it/s]
 63%|██████▎   | 232189/371472 [7:51:36<14:07:18,  2.74it/s]
 63%|██████▎   | 232190/371472 [7:51:36<14:05:31,  2.75it/s]
 63%|██████▎   | 232191/371472 [7:51:37<13:24:55,  2.88it/s]
 63%|██████▎   | 232192/371472 [7:51:37<12:53:51,  3.00it/s]
 63%|██████▎   | 232193/371472 [7:51:37<12:37:29,  3.06it/s]
 63%|██████▎   | 232194/371472 [7:51:38<13:07:53,  2.95it/s]
 63%|██████▎   | 232195/371472 [7:51:38<13:06:13,  2.95it/s]
 63%|██████▎   | 232196/371472 [7:51:38<12:58:16,  2.98it/s]
 63%|██████▎   | 232197/371472 [7:51:39<13:49:56,  2.80it/s]
 63%|██████▎   | 232198/371472 [7:51:39<14:38:58,  2.64it/s]
 63%|██████▎   | 232199/371472 [7:51:39<14:16:27,  2.71it/s]
 63%|██████▎   | 232200/371472 [7:51:40<14:17:25,  2.71it/s]
                                                            
{'loss': 2.826, 'learning_rate': 4.3760908444482753e-07, 'epoch': 10.0}
+
 63%|██████▎   | 232200/371472 [7:51:40<14:17:25,  2.71it/s]
 63%|██████▎   | 232201/371472 [7:51:40<13:48:32,  2.80it/s]
 63%|██████▎   | 232202/371472 [7:51:40<13:29:04,  2.87it/s]
 63%|██████▎   | 232203/371472 [7:51:41<13:21:46,  2.90it/s]
 63%|██████▎   | 232204/371472 [7:51:41<13:15:01,  2.92it/s]
 63%|██████▎   | 232205/371472 [7:51:41<12:57:03,  2.99it/s]
 63%|██████▎   | 232206/371472 [7:51:42<12:46:39,  3.03it/s]
 63%|██████▎   | 232207/371472 [7:51:42<12:19:07,  3.14it/s]
 63%|██████▎   | 232208/371472 [7:51:42<12:36:23,  3.07it/s]
 63%|██████▎   | 232209/371472 [7:51:43<12:24:33,  3.12it/s]
 63%|██████▎   | 232210/371472 [7:51:43<12:07:32,  3.19it/s]
 63%|██████▎   | 232211/371472 [7:51:43<11:48:31,  3.28it/s]
 63%|██████▎   | 232212/371472 [7:51:44<12:20:54,  3.13it/s]
 63%|██████▎   | 232213/371472 [7:51:44<12:20:41,  3.13it/s]
 63%|██████▎   | 232214/371472 [7:51:44<11:55:11,  3.25it/s]
 63%|██████▎   | 232215/371472 [7:51:45<12:05:33,  3.20it/s]
 63%|██████▎   | 232216/371472 [7:51:45<12:01:44,  3.22it/s]
 63%|██████▎   | 232217/371472 [7:51:45<12:40:41,  3.05it/s]
 63%|██████▎   | 232218/371472 [7:51:45<12:28:23,  3.10it/s]
 63%|██████▎   | 232219/371472 [7:51:46<12:56:22,  2.99it/s]
 63%|██████▎   | 232220/371472 [7:51:46<13:30:17,  2.86it/s]
                                                            
{'loss': 2.8589, 'learning_rate': 4.375606024693486e-07, 'epoch': 10.0}
+
 63%|██████▎   | 232220/371472 [7:51:46<13:30:17,  2.86it/s]
 63%|██████▎   | 232221/371472 [7:51:47<13:07:52,  2.95it/s]
 63%|██████▎   | 232222/371472 [7:51:47<12:56:32,  2.99it/s]
 63%|██████▎   | 232223/371472 [7:51:47<12:30:23,  3.09it/s]
 63%|██████▎   | 232224/371472 [7:51:48<12:38:14,  3.06it/s]
 63%|██████▎   | 232225/371472 [7:51:48<13:15:29,  2.92it/s]
 63%|██████▎   | 232226/371472 [7:51:48<12:39:06,  3.06it/s]
 63%|██████▎   | 232227/371472 [7:51:48<12:06:59,  3.19it/s]
 63%|██████▎   | 232228/371472 [7:51:49<11:38:43,  3.32it/s]
 63%|██████▎   | 232229/371472 [7:51:49<11:23:10,  3.40it/s]
 63%|██████▎   | 232230/371472 [7:51:49<11:13:45,  3.44it/s]
 63%|██████▎   | 232231/371472 [7:51:50<11:20:16,  3.41it/s]
 63%|██████▎   | 232232/371472 [7:51:50<11:48:38,  3.27it/s]
 63%|██████▎   | 232233/371472 [7:51:50<12:10:48,  3.18it/s]
 63%|██████▎   | 232234/371472 [7:51:51<11:31:39,  3.36it/s]
 63%|██████▎   | 232235/371472 [7:51:51<11:19:25,  3.42it/s]
 63%|██████▎   | 232236/371472 [7:51:51<11:14:10,  3.44it/s]
 63%|██████▎   | 232237/371472 [7:51:51<11:56:32,  3.24it/s]
 63%|██████▎   | 232238/371472 [7:51:52<11:29:24,  3.37it/s]
 63%|██████▎   | 232239/371472 [7:51:52<11:15:57,  3.43it/s]
 63%|██████▎   | 232240/371472 [7:51:52<11:43:56,  3.30it/s]
                                                            
{'loss': 2.6534, 'learning_rate': 4.375121204938697e-07, 'epoch': 10.0}
+
 63%|██████▎   | 232240/371472 [7:51:52<11:43:56,  3.30it/s]
 63%|██████▎   | 232241/371472 [7:51:53<11:25:47,  3.38it/s]
 63%|██████▎   | 232242/371472 [7:51:53<11:13:17,  3.45it/s]
 63%|██████▎   | 232243/371472 [7:51:53<11:07:55,  3.47it/s]
 63%|██████▎   | 232244/371472 [7:51:53<11:42:15,  3.30it/s]
 63%|██████▎   | 232245/371472 [7:51:54<11:38:56,  3.32it/s]
 63%|██████▎   | 232246/371472 [7:51:54<11:41:56,  3.31it/s]
 63%|██████▎   | 232247/371472 [7:51:54<11:40:21,  3.31it/s]
 63%|██████▎   | 232248/371472 [7:51:55<11:33:09,  3.35it/s]
 63%|██████▎   | 232249/371472 [7:51:55<11:24:32,  3.39it/s]
 63%|██████▎   | 232250/371472 [7:51:55<11:45:24,  3.29it/s]
 63%|██████▎   | 232251/371472 [7:51:56<11:50:49,  3.26it/s]
 63%|██████▎   | 232252/371472 [7:51:56<11:44:24,  3.29it/s]
 63%|██████▎   | 232253/371472 [7:51:56<11:53:55,  3.25it/s]
 63%|██████▎   | 232254/371472 [7:51:57<12:09:11,  3.18it/s]
 63%|██████▎   | 232255/371472 [7:51:57<12:26:17,  3.11it/s]
 63%|██████▎   | 232256/371472 [7:51:57<12:16:03,  3.15it/s]
 63%|██████▎   | 232257/371472 [7:51:58<12:18:06,  3.14it/s]
 63%|██████▎   | 232258/371472 [7:51:58<12:05:43,  3.20it/s]
 63%|██████▎   | 232259/371472 [7:51:58<11:58:33,  3.23it/s]
 63%|██████▎   | 232260/371472 [7:51:58<12:21:36,  3.13it/s]
                                                            
{'loss': 2.6214, 'learning_rate': 4.374636385183908e-07, 'epoch': 10.0}
+
 63%|██████▎   | 232260/371472 [7:51:58<12:21:36,  3.13it/s]
 63%|██████▎   | 232261/371472 [7:51:59<11:54:56,  3.25it/s]
 63%|██████▎   | 232262/371472 [7:51:59<11:43:39,  3.30it/s]
 63%|██████▎   | 232263/371472 [7:51:59<12:01:22,  3.22it/s]
 63%|██████▎   | 232264/371472 [7:52:00<12:07:15,  3.19it/s]
 63%|██████▎   | 232265/371472 [7:52:00<12:07:16,  3.19it/s]
 63%|██████▎   | 232266/371472 [7:52:00<12:06:36,  3.19it/s]
 63%|██████▎   | 232267/371472 [7:52:01<11:56:35,  3.24it/s]
 63%|██████▎   | 232268/371472 [7:52:01<12:24:41,  3.12it/s]
 63%|██████▎   | 232269/371472 [7:52:01<12:17:57,  3.14it/s]
 63%|██████▎   | 232270/371472 [7:52:02<11:49:20,  3.27it/s]
 63%|██████▎   | 232271/371472 [7:52:02<11:48:09,  3.28it/s]
 63%|██████▎   | 232272/371472 [7:52:02<12:25:54,  3.11it/s]
 63%|██████▎   | 232273/371472 [7:52:03<12:11:21,  3.17it/s]
 63%|██████▎   | 232274/371472 [7:52:03<12:00:13,  3.22it/s]
 63%|██████▎   | 232275/371472 [7:52:03<11:41:20,  3.31it/s]
 63%|██████▎   | 232276/371472 [7:52:03<11:23:42,  3.39it/s]
 63%|██████▎   | 232277/371472 [7:52:04<12:27:35,  3.10it/s]
 63%|██████▎   | 232278/371472 [7:52:04<12:21:53,  3.13it/s]
 63%|██████▎   | 232279/371472 [7:52:04<12:18:03,  3.14it/s]
 63%|██████▎   | 232280/371472 [7:52:05<13:00:48,  2.97it/s]
                                                            
{'loss': 2.706, 'learning_rate': 4.37415156542912e-07, 'epoch': 10.0}
+
 63%|██████▎   | 232280/371472 [7:52:05<13:00:48,  2.97it/s]
 63%|██████▎   | 232281/371472 [7:52:05<13:24:12,  2.88it/s]
 63%|██████▎   | 232282/371472 [7:52:05<12:20:28,  3.13it/s]
 63%|██████▎   | 232283/371472 [7:52:06<13:23:19,  2.89it/s]
 63%|██████▎   | 232284/371472 [7:52:06<12:41:50,  3.04it/s]
 63%|██████▎   | 232285/371472 [7:52:06<12:35:55,  3.07it/s]
 63%|██████▎   | 232286/371472 [7:52:07<12:23:15,  3.12it/s]
 63%|██████▎   | 232287/371472 [7:52:07<12:22:50,  3.12it/s]
 63%|██████▎   | 232288/371472 [7:52:07<12:27:33,  3.10it/s]
 63%|██████▎   | 232289/371472 [7:52:08<13:01:08,  2.97it/s]
 63%|██████▎   | 232290/371472 [7:52:08<12:29:08,  3.10it/s]
 63%|██████▎   | 232291/371472 [7:52:08<12:22:48,  3.12it/s]
 63%|██████▎   | 232292/371472 [7:52:09<12:29:36,  3.09it/s]
 63%|██████▎   | 232293/371472 [7:52:09<12:33:58,  3.08it/s]
 63%|██████▎   | 232294/371472 [7:52:09<12:04:59,  3.20it/s]
 63%|██████▎   | 232295/371472 [7:52:10<12:14:07,  3.16it/s]
 63%|██████▎   | 232296/371472 [7:52:10<13:34:07,  2.85it/s]
 63%|██████▎   | 232297/371472 [7:52:10<13:06:54,  2.95it/s]
 63%|██████▎   | 232298/371472 [7:52:11<12:54:01,  3.00it/s]
 63%|██████▎   | 232299/371472 [7:52:11<12:59:38,  2.98it/s]
 63%|██████▎   | 232300/371472 [7:52:11<13:06:07,  2.95it/s]
                                                            
{'loss': 2.7396, 'learning_rate': 4.37366674567433e-07, 'epoch': 10.01}
+
 63%|██████▎   | 232300/371472 [7:52:11<13:06:07,  2.95it/s]
 63%|██████▎   | 232301/371472 [7:52:12<12:35:24,  3.07it/s]
 63%|██████▎   | 232302/371472 [7:52:12<11:58:09,  3.23it/s]
 63%|██████▎   | 232303/371472 [7:52:12<11:30:09,  3.36it/s]
\ No newline at end of file